Last active
July 27, 2021 19:58
-
-
Save zarzen/d91b9e98ec641d74305281a2bdc2713a to your computer and use it in GitHub Desktop.
DeepSpeed Debug logs
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
21: M9 P[5, 6] avail 3.1e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 5.1e+03, inflight [9] | |
-gather param for module 3: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
[2021-07-07 21:16:52,635] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 9 | |
[2021-07-07 21:16:52,635] [INFO] [stage3.py:42:print_rank_0] module id 9 handle is None | |
22: M23 P[] avail 3.1e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [0, 23, 2, 1, 3] | |
[2021-07-07 21:16:52,636] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 23 | |
[2021-07-07 21:16:52,636] [INFO] [stage3.py:42:print_rank_0] module id 23 handle is None | |
-gather param for module 24: {'id': 151, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
[2021-07-07 21:16:52,636] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 151, 'status': 'INFLIGHT', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
23: M24 P[151, 152] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 8.5e+07, inflight [24, 0, 2, 1, 3] | |
[2021-07-07 21:16:52,636] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 24 | |
[2021-07-07 21:16:52,637] [INFO] [stage3.py:42:print_rank_0] module id 24 handle is <deepspeed.runtime.zero.partition_parameters.AllGatherCoalescedHandle object at 0x7f7bc632dd90> | |
24: M25 P[] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [0, 2, 1, 25, 3] | |
[2021-07-07 21:16:52,642] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 25 | |
[2021-07-07 21:16:52,642] [INFO] [stage3.py:42:print_rank_0] module id 25 handle is None | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
25: M26 P[153] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [0, 2, 1, 26, 3] | |
[2021-07-07 21:16:52,642] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 26 | |
[2021-07-07 21:16:52,642] [INFO] [stage3.py:42:print_rank_0] module id 26 handle is None | |
26: M27 P[] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [0, 2, 1, 27, 3] | |
[2021-07-07 21:16:52,642] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 27 | |
[2021-07-07 21:16:52,642] [INFO] [stage3.py:42:print_rank_0] module id 27 handle is None | |
-gather param for module 28: {'id': 154, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
[2021-07-07 21:16:52,643] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 154, 'status': 'INFLIGHT', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
27: M28 P[154, 155] avail 3.3e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 8.5e+07, inflight [0, 2, 28, 1, 3] | |
[2021-07-07 21:16:52,643] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 28 | |
[2021-07-07 21:16:52,643] [INFO] [stage3.py:42:print_rank_0] module id 28 handle is <deepspeed.runtime.zero.partition_parameters.AllGatherCoalescedHandle object at 0x7f7bc632dd90> | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
28: M29 P[156, 157] avail 3.3e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [0, 29, 2, 1, 3] | |
[2021-07-07 21:16:52,644] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 29 | |
[2021-07-07 21:16:52,644] [INFO] [stage3.py:42:print_rank_0] module id 29 handle is None | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
29: M30 P[0] avail 3.3e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [0, 2, 30, 1, 3] | |
[2021-07-07 21:16:52,644] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 30 | |
[2021-07-07 21:16:52,644] [INFO] [stage3.py:42:print_rank_0] module id 30 handle is None | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
30: M31 P[158, 159] avail 3.3e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [0, 2, 1, 31, 3] | |
[2021-07-07 21:16:52,645] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 31 | |
[2021-07-07 21:16:52,645] [INFO] [stage3.py:42:print_rank_0] module id 31 handle is None | |
[2021-07-07 21:16:52,647] [INFO] [stage3.py:42:print_rank_0] current submodule in __inflight_module_manager, module id 0 | |
31: M0 P[] avail 3.3e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [1, 3, 0, 2] | |
[2021-07-07 21:16:52,647] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 0 | |
[2021-07-07 21:16:52,647] [INFO] [stage3.py:42:print_rank_0] module id 0 handle is None | |
32: M25 P[] avail 3.3e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [1, 25, 3, 2] | |
[2021-07-07 21:16:52,648] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 25 | |
[2021-07-07 21:16:52,648] [INFO] [stage3.py:42:print_rank_0] module id 25 handle is None | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
33: M31 P[158, 159] avail 3.3e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [31, 1, 3, 2] | |
[2021-07-07 21:16:52,648] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 31 | |
[2021-07-07 21:16:52,648] [INFO] [stage3.py:42:print_rank_0] module id 31 handle is None | |
[2021-07-07 21:16:52,648] [INFO] [stage3.py:42:print_rank_0] sub_module Linear, sub_module id 31, param {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
[2021-07-07 21:16:52,648] [INFO] [stage3.py:42:print_rank_0] sub_module Linear, sub_module id 31, param {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
34: M26 P[153] avail 3.3e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [1, 26, 3, 2] | |
[2021-07-07 21:16:52,649] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 26 | |
[2021-07-07 21:16:52,649] [INFO] [stage3.py:42:print_rank_0] module id 26 handle is None | |
[2021-07-07 21:16:52,649] [INFO] [stage3.py:42:print_rank_0] sub_module BertLMPredictionHead, sub_module id 26, param {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
35: M30 P[0] avail 3.3e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [1, 30, 3, 2] | |
[2021-07-07 21:16:52,649] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 30 | |
[2021-07-07 21:16:52,649] [INFO] [stage3.py:42:print_rank_0] module id 30 handle is None | |
[2021-07-07 21:16:52,649] [INFO] [stage3.py:42:print_rank_0] sub_module Linear, sub_module id 30, param {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
-release param: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
36: M27 P[] avail 2.5e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [1, 3, 27, 2] | |
[2021-07-07 21:16:52,650] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 27 | |
[2021-07-07 21:16:52,650] [INFO] [stage3.py:42:print_rank_0] module id 27 handle is None | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
37: M29 P[156, 157] avail 2.5e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [1, 3, 29, 2] | |
[2021-07-07 21:16:52,650] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 29 | |
[2021-07-07 21:16:52,650] [INFO] [stage3.py:42:print_rank_0] module id 29 handle is None | |
[2021-07-07 21:16:52,650] [INFO] [stage3.py:42:print_rank_0] sub_module FusedLayerNorm, sub_module id 29, param {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
[2021-07-07 21:16:52,650] [INFO] [stage3.py:42:print_rank_0] sub_module FusedLayerNorm, sub_module id 29, param {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 28: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
38: M28 P[154, 155] avail 2.5e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 8.5e+07, inflight [1, 28, 3, 2] | |
[2021-07-07 21:16:52,650] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 28 | |
[2021-07-07 21:16:52,651] [INFO] [stage3.py:42:print_rank_0] module id 28 handle is None | |
[2021-07-07 21:16:52,651] [INFO] [stage3.py:42:print_rank_0] sub_module LinearActivation, sub_module id 28, param {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
[2021-07-07 21:16:52,651] [INFO] [stage3.py:42:print_rank_0] sub_module LinearActivation, sub_module id 28, param {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
-release param: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
[2021-07-07 21:16:52,651] [INFO] [stage3.py:42:print_rank_0] current submodule in __inflight_module_manager, module id 1 | |
39: M1 P[] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [1, 3, 2] | |
[2021-07-07 21:16:52,651] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 1 | |
[2021-07-07 21:16:52,651] [INFO] [stage3.py:42:print_rank_0] module id 1 handle is None | |
40: M23 P[] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [2, 3, 23] | |
[2021-07-07 21:16:52,652] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 23 | |
[2021-07-07 21:16:52,652] [INFO] [stage3.py:42:print_rank_0] module id 23 handle is None | |
-gather param for module 24: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
41: M24 P[151, 152] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 8.5e+07, inflight [2, 24, 3] | |
[2021-07-07 21:16:52,652] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 24 | |
[2021-07-07 21:16:52,652] [INFO] [stage3.py:42:print_rank_0] module id 24 handle is None | |
[2021-07-07 21:16:52,652] [INFO] [stage3.py:42:print_rank_0] sub_module LinearActivation, sub_module id 24, param {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
[2021-07-07 21:16:52,652] [INFO] [stage3.py:42:print_rank_0] sub_module LinearActivation, sub_module id 24, param {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
-release param: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
42: M9 P[5, 6] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [2, 9, 3] | |
[2021-07-07 21:16:52,653] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 9 | |
[2021-07-07 21:16:52,653] [INFO] [stage3.py:42:print_rank_0] module id 9 handle is None | |
[2021-07-07 21:16:52,653] [INFO] [stage3.py:42:print_rank_0] sub_module FusedLayerNorm, sub_module id 9, param {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
[2021-07-07 21:16:52,653] [INFO] [stage3.py:42:print_rank_0] sub_module FusedLayerNorm, sub_module id 9, param {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 19: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
43: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 3, 19] | |
[2021-07-07 21:16:52,654] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 19 | |
[2021-07-07 21:16:52,654] [INFO] [stage3.py:42:print_rank_0] module id 19 handle is None | |
-gather param for module 20: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
44: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 3, 20] | |
[2021-07-07 21:16:52,655] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 20 | |
[2021-07-07 21:16:52,655] [INFO] [stage3.py:42:print_rank_0] module id 20 handle is None | |
-gather param for module 21: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
45: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 21, 3] | |
[2021-07-07 21:16:52,660] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 21 | |
[2021-07-07 21:16:52,660] [INFO] [stage3.py:42:print_rank_0] module id 21 handle is None | |
-gather param for module 22: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
46: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 22, 3] | |
[2021-07-07 21:16:52,666] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 22 | |
[2021-07-07 21:16:52,666] [INFO] [stage3.py:42:print_rank_0] module id 22 handle is None | |
-gather param for module 22: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
47: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 22, 3] | |
[2021-07-07 21:16:52,672] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 22 | |
[2021-07-07 21:16:52,672] [INFO] [stage3.py:42:print_rank_0] module id 22 handle is None | |
[2021-07-07 21:16:52,672] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
[2021-07-07 21:16:52,672] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
[2021-07-07 21:16:52,672] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
[2021-07-07 21:16:52,672] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
[2021-07-07 21:16:52,672] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
[2021-07-07 21:16:52,672] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
[2021-07-07 21:16:52,672] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
[2021-07-07 21:16:52,673] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
[2021-07-07 21:16:52,673] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
[2021-07-07 21:16:52,673] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
[2021-07-07 21:16:52,673] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
[2021-07-07 21:16:52,673] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 22, param {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-release param: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 21: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
48: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 1.6e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 21, 3] | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 21 | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] module id 21 handle is None | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
[2021-07-07 21:16:52,679] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 21, param {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-release param: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 20: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
49: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 7.9e+07, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 3, 20] | |
[2021-07-07 21:16:52,691] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 20 | |
[2021-07-07 21:16:52,691] [INFO] [stage3.py:42:print_rank_0] module id 20 handle is None | |
[2021-07-07 21:16:52,691] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
[2021-07-07 21:16:52,691] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
[2021-07-07 21:16:52,691] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
[2021-07-07 21:16:52,691] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
[2021-07-07 21:16:52,691] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
[2021-07-07 21:16:52,691] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
[2021-07-07 21:16:52,691] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
[2021-07-07 21:16:52,691] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
[2021-07-07 21:16:52,691] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
[2021-07-07 21:16:52,692] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
[2021-07-07 21:16:52,692] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
[2021-07-07 21:16:52,692] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 20, param {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-release param: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 19: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
50: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 4.6e+05, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 3, 19] | |
[2021-07-07 21:16:52,704] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 19 | |
[2021-07-07 21:16:52,704] [INFO] [stage3.py:42:print_rank_0] module id 19 handle is None | |
[2021-07-07 21:16:52,704] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
[2021-07-07 21:16:52,704] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
[2021-07-07 21:16:52,704] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
[2021-07-07 21:16:52,704] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
[2021-07-07 21:16:52,704] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
[2021-07-07 21:16:52,704] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
[2021-07-07 21:16:52,704] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
[2021-07-07 21:16:52,704] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
[2021-07-07 21:16:52,705] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
[2021-07-07 21:16:52,705] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
[2021-07-07 21:16:52,705] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
[2021-07-07 21:16:52,705] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 19, param {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-release param: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 15: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,718] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 55, 'status': 'INFLIGHT', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,718] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 57, 'status': 'INFLIGHT', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,718] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 61, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,718] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 63, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
51: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 4.6e+05, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 15, 3] | |
[2021-07-07 21:16:52,719] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 15 | |
[2021-07-07 21:16:52,719] [INFO] [stage3.py:42:print_rank_0] module id 15 handle is <deepspeed.runtime.zero.partition_parameters.AllGatherCoalescedHandle object at 0x7f7bc632d810> | |
-gather param for module 16: {'id': 67, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,752] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 67, 'status': 'INFLIGHT', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,752] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 69, 'status': 'INFLIGHT', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,752] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 73, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,752] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 75, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
52: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 7.9e+07, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [16, 2, 3] | |
[2021-07-07 21:16:52,753] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 16 | |
[2021-07-07 21:16:52,753] [INFO] [stage3.py:42:print_rank_0] module id 16 handle is <deepspeed.runtime.zero.partition_parameters.AllGatherCoalescedHandle object at 0x7f7bc632d690> | |
-gather param for module 17: {'id': 79, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,786] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 79, 'status': 'INFLIGHT', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,786] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 81, 'status': 'INFLIGHT', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,786] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 85, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,786] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 87, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
53: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 1.6e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [17, 2, 3] | |
[2021-07-07 21:16:52,786] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 17 | |
[2021-07-07 21:16:52,786] [INFO] [stage3.py:42:print_rank_0] module id 17 handle is <deepspeed.runtime.zero.partition_parameters.AllGatherCoalescedHandle object at 0x7f7bc632df90> | |
-gather param for module 18: {'id': 91, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,819] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 91, 'status': 'INFLIGHT', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,819] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 93, 'status': 'INFLIGHT', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,819] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 97, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,819] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 99, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
54: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 3, 18] | |
[2021-07-07 21:16:52,819] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 18 | |
[2021-07-07 21:16:52,820] [INFO] [stage3.py:42:print_rank_0] module id 18 handle is <deepspeed.runtime.zero.partition_parameters.AllGatherCoalescedHandle object at 0x7f7bc632d810> | |
-gather param for module 18: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
55: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 3, 18] | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 18 | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] module id 18 handle is None | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
[2021-07-07 21:16:52,852] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 18, param {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-release param: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 17: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
56: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 1.6e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [17, 2, 3] | |
[2021-07-07 21:16:52,858] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 17 | |
[2021-07-07 21:16:52,858] [INFO] [stage3.py:42:print_rank_0] module id 17 handle is None | |
[2021-07-07 21:16:52,858] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,858] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,858] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,858] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,858] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,858] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,858] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,858] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,859] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,859] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,859] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
[2021-07-07 21:16:52,859] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 17, param {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-release param: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 16: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
57: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 7.9e+07, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [16, 2, 3] | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 16 | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] module id 16 handle is None | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
[2021-07-07 21:16:52,869] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 16, param {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-release param: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 15: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
58: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 4.6e+05, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 15, 3] | |
[2021-07-07 21:16:52,881] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 15 | |
[2021-07-07 21:16:52,881] [INFO] [stage3.py:42:print_rank_0] module id 15 handle is None | |
[2021-07-07 21:16:52,881] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,881] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,881] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,881] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,882] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,882] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,882] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,882] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,882] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,882] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,882] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
[2021-07-07 21:16:52,882] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 15, param {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-release param: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:52,918] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 7, 'status': 'INFLIGHT', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:52,918] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 9, 'status': 'INFLIGHT', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:52,918] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 13, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:52,918] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 15, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
59: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 4.6e+05, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 11, 3] | |
[2021-07-07 21:16:52,919] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 11 | |
[2021-07-07 21:16:52,919] [INFO] [stage3.py:42:print_rank_0] module id 11 handle is <deepspeed.runtime.zero.partition_parameters.AllGatherCoalescedHandle object at 0x7f7bc632d690> | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:52,971] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 19, 'status': 'INFLIGHT', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:52,972] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 21, 'status': 'INFLIGHT', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:52,972] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 25, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:52,972] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 27, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
60: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 7.9e+07, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 3, 12] | |
[2021-07-07 21:16:52,972] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 12 | |
[2021-07-07 21:16:52,972] [INFO] [stage3.py:42:print_rank_0] module id 12 handle is <deepspeed.runtime.zero.partition_parameters.AllGatherCoalescedHandle object at 0x7f7bc632df90> | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,022] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 31, 'status': 'INFLIGHT', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,023] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 33, 'status': 'INFLIGHT', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,023] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 37, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,023] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 39, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
61: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 31, 33, 37, 39] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [13, 2, 3] | |
[2021-07-07 21:16:53,023] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 13 | |
[2021-07-07 21:16:53,023] [INFO] [stage3.py:42:print_rank_0] module id 13 handle is <deepspeed.runtime.zero.partition_parameters.AllGatherCoalescedHandle object at 0x7f7bc632dd50> | |
-gather param for module 14: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,072] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 43, 'status': 'INFLIGHT', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,073] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 45, 'status': 'INFLIGHT', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,073] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 49, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,073] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 51, 'status': 'INFLIGHT', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
62: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 3, 14] | |
[2021-07-07 21:16:53,073] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 14 | |
[2021-07-07 21:16:53,073] [INFO] [stage3.py:42:print_rank_0] module id 14 handle is <deepspeed.runtime.zero.partition_parameters.AllGatherCoalescedHandle object at 0x7f7bc632d690> | |
-gather param for module 14: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
63: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 3, 14] | |
[2021-07-07 21:16:53,124] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 14 | |
[2021-07-07 21:16:53,124] [INFO] [stage3.py:42:print_rank_0] module id 14 handle is None | |
[2021-07-07 21:16:53,124] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,124] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,124] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,124] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,124] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,124] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,124] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,125] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,125] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,125] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,125] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
[2021-07-07 21:16:53,125] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 14, param {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 13: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
64: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 31, 33, 37, 39] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [13, 2, 3] | |
[2021-07-07 21:16:53,131] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 13 | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] module id 13 handle is None | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
[2021-07-07 21:16:53,132] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 13, param {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 12: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
65: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 3, 12] | |
[2021-07-07 21:16:53,145] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 12 | |
[2021-07-07 21:16:53,145] [INFO] [stage3.py:42:print_rank_0] module id 12 handle is None | |
[2021-07-07 21:16:53,145] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:53,145] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:53,146] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:53,146] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:53,146] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:53,146] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:53,146] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:53,146] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:53,146] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:53,146] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:53,146] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
[2021-07-07 21:16:53,146] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 12, param {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 11: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
66: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 1.6e+08, inflight [2, 11, 3] | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 11 | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] module id 11 handle is None | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,160] [INFO] [stage3.py:42:print_rank_0] sub_module DeepSpeedTransformerLayer, sub_module id 11, param {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
[2021-07-07 21:16:53,174] [INFO] [stage3.py:42:print_rank_0] current submodule in __inflight_module_manager, module id 2 | |
67: M2 P[] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [2, 3] | |
[2021-07-07 21:16:53,174] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 2 | |
[2021-07-07 21:16:53,174] [INFO] [stage3.py:42:print_rank_0] module id 2 handle is None | |
68: M7 P[] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [7, 3] | |
[2021-07-07 21:16:53,174] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 7 | |
[2021-07-07 21:16:53,174] [INFO] [stage3.py:42:print_rank_0] module id 7 handle is None | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
69: M6 P[3, 4] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [6, 3] | |
[2021-07-07 21:16:53,174] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 6 | |
[2021-07-07 21:16:53,174] [INFO] [stage3.py:42:print_rank_0] module id 6 handle is None | |
[2021-07-07 21:16:53,174] [INFO] [stage3.py:42:print_rank_0] sub_module FusedLayerNorm, sub_module id 6, param {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
[2021-07-07 21:16:53,174] [INFO] [stage3.py:42:print_rank_0] sub_module FusedLayerNorm, sub_module id 6, param {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
70: M5 P[2] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [5, 3] | |
[2021-07-07 21:16:53,175] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 5 | |
[2021-07-07 21:16:53,175] [INFO] [stage3.py:42:print_rank_0] module id 5 handle is None | |
[2021-07-07 21:16:53,175] [INFO] [stage3.py:42:print_rank_0] sub_module Embedding, sub_module id 5, param {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
[2021-07-07 21:16:53,189] [INFO] [utils.py:629:info_rank_0] all_gather_coalesced {'id': 1, 'status': 'INFLIGHT', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
71: M4 P[1] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.9e+07, inflight [4, 3] | |
[2021-07-07 21:16:53,189] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 4 | |
[2021-07-07 21:16:53,190] [INFO] [stage3.py:42:print_rank_0] module id 4 handle is <deepspeed.runtime.zero.partition_parameters.AllGatherCoalescedHandle object at 0x7f7bc632d390> | |
[2021-07-07 21:16:53,190] [INFO] [stage3.py:42:print_rank_0] sub_module Embedding, sub_module id 4, param {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
[2021-07-07 21:16:53,191] [INFO] [stage3.py:42:print_rank_0] current submodule in __inflight_module_manager, module id 3 | |
72: M3 P[0] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.8e+02, n_inflight 7.8e+07, inflight [3] | |
[2021-07-07 21:16:53,191] [INFO] [stage3.py:42:print_rank_0] wait_for_fetch current submodule id 3 | |
[2021-07-07 21:16:53,191] [INFO] [stage3.py:42:print_rank_0] module id 3 handle is None | |
[2021-07-07 21:16:53,191] [INFO] [stage3.py:42:print_rank_0] sub_module Embedding, sub_module id 3, param {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
0%| | 9/152966 [00:17<81:54:53, 1.93s/it] | |
0%| | 9/152942 [00:17<82:10:34, 1.93s/it] | |
Traceback (most recent call last): | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 607, in <module> | |
Traceback (most recent call last): | |
0%| | 9/152613 [00:17<81:51:11, 1.93s/it] File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 607, in <module> | |
main() | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 600, in main | |
main() | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 600, in main | |
run(args, model, optimizer, start_epoch) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 566, in run | |
Traceback (most recent call last): | |
run(args, model, optimizer, start_epoch) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 566, in run | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 607, in <module> | |
train(args, index, model, optimizer, pretrain_dataset_provider) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 179, in train | |
model.network.backward(loss) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
0%| | 9/152794 [00:17<81:55:18, 1.93s/it] return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/engine.py", line 1191, in backward | |
train(args, index, model, optimizer, pretrain_dataset_provider) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 179, in train | |
model.network.backward(loss) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/engine.py", line 1191, in backward | |
main() | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 600, in main | |
self.optimizer.backward(loss) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 2823, in backward | |
run(args, model, optimizer, start_epoch) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 566, in run | |
self.optimizer.backward(loss) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
Traceback (most recent call last): | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 607, in <module> | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 2823, in backward | |
train(args, index, model, optimizer, pretrain_dataset_provider) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 179, in train | |
model.network.backward(loss) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/engine.py", line 1191, in backward | |
main() | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 600, in main | |
self.optimizer.backward(loss) | |
run(args, model, optimizer, start_epoch) File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 566, in run | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 2823, in backward | |
self.loss_scaler.backward(loss.float(), retain_graph=retain_graph) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/fp16/loss_scaler.py", line 53, in backward | |
train(args, index, model, optimizer, pretrain_dataset_provider)scaled_loss.backward(retain_graph=retain_graph) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 179, in train | |
File "/usr/local/lib64/python3.7/site-packages/torch/tensor.py", line 233, in backward | |
self.loss_scaler.backward(loss.float(), retain_graph=retain_graph) | |
model.network.backward(loss) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/fp16/loss_scaler.py", line 53, in backward | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs) | |
File "/usr/local/lib64/python3.7/site-packages/torch/autograd/__init__.py", line 147, in backward | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/engine.py", line 1191, in backward | |
scaled_loss.backward(retain_graph=retain_graph) | |
File "/usr/local/lib64/python3.7/site-packages/torch/tensor.py", line 233, in backward | |
allow_unreachable=True, accumulate_grad=True) # allow_unreachable flag | |
RuntimeError: The size of tensor a (0) must match the size of tensor b (2560) at non-singleton dimension 1 | |
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs) | |
File "/usr/local/lib64/python3.7/site-packages/torch/autograd/__init__.py", line 147, in backward | |
allow_unreachable=True, accumulate_grad=True) # allow_unreachable flag | |
RuntimeError: The size of tensor a (0) must match the size of tensor b (2560) at non-singleton dimension 1 | |
self.optimizer.backward(loss) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 2823, in backward | |
self.loss_scaler.backward(loss.float(), retain_graph=retain_graph) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/fp16/loss_scaler.py", line 53, in backward | |
scaled_loss.backward(retain_graph=retain_graph) | |
File "/usr/local/lib64/python3.7/site-packages/torch/tensor.py", line 233, in backward | |
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs) | |
File "/usr/local/lib64/python3.7/site-packages/torch/autograd/__init__.py", line 147, in backward | |
allow_unreachable=True, accumulate_grad=True) # allow_unreachable flag | |
RuntimeError: The size of tensor a (0) must match the size of tensor b (2560) at non-singleton dimension 1 | |
self.loss_scaler.backward(loss.float(), retain_graph=retain_graph) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/fp16/loss_scaler.py", line 53, in backward | |
scaled_loss.backward(retain_graph=retain_graph) | |
File "/usr/local/lib64/python3.7/site-packages/torch/tensor.py", line 233, in backward | |
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs) | |
File "/usr/local/lib64/python3.7/site-packages/torch/autograd/__init__.py", line 147, in backward | |
allow_unreachable=True, accumulate_grad=True) # allow_unreachable flag | |
RuntimeError: The size of tensor a (0) must match the size of tensor b (2560) at non-singleton dimension 1 | |
Killing subprocess 43838 | |
Killing subprocess 43839 | |
Killing subprocess 43840 | |
Killing subprocess 43841 | |
Traceback (most recent call last): | |
File "/usr/lib64/python3.7/runpy.py", line 193, in _run_module_as_main | |
"__main__", mod_spec) | |
File "/usr/lib64/python3.7/runpy.py", line 85, in _run_code | |
exec(code, run_globals) | |
File "/home/ec2-user/DeepSpeed/deepspeed/launcher/launch.py", line 171, in <module> | |
main() | |
File "/home/ec2-user/DeepSpeed/deepspeed/launcher/launch.py", line 161, in main | |
sigkill_handler(signal.SIGTERM, None) # not coming back | |
File "/home/ec2-user/DeepSpeed/deepspeed/launcher/launch.py", line 139, in sigkill_handler | |
raise subprocess.CalledProcessError(returncode=last_return_code, cmd=cmd) | |
subprocess.CalledProcessError: Command '['/bin/python3', '-u', '/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py', '--local_rank=3', '--max_seq_length', '512', '--print_steps', '10', '--deepspeed', '--data_path_prefix', '/home/ec2-user/bert-data-nv', '--use_nvidia_dataset', '--rewarmup', '--lr_schedule', 'EE', '--attention_dropout_checkpoint', '--lr_offset', '0.0', '--gelu_checkpoint', '--deepspeed_transformer_kernel', '--max_steps', '20', '--ckpt_to_save', '200', '--output_dir', '/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-07_21:16:05/', '--cf', '/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', '--deepspeed_config', '/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', '--job_name', 'zero3_1node_profile_2021-07-07_21:16:05']' returned non-zero exit status 1. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[2021-07-06 19:29:23,081] [WARNING] [runner.py:122:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only. | |
[2021-07-06 19:29:23,190] [INFO] [runner.py:360:main] cmd = /bin/python3 -u -m deepspeed.launcher.launch --world_info=eyJsb2NhbGhvc3QiOiBbMCwgMSwgMiwgM119 --master_addr=127.0.0.1 --master_port=29500 /home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py --max_seq_length 512 --print_steps 10 --deepspeed --data_path_prefix /home/ec2-user/bert-data-nv --use_nvidia_dataset --rewarmup --lr_schedule EE --attention_dropout_checkpoint --lr_offset 0.0 --gelu_checkpoint --deepspeed_transformer_kernel --max_steps 5 --ckpt_to_save 200 --output_dir /home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-06_19:29:22/ --cf /home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json --deepspeed_config /home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json --job_name zero3_1node_profile_2021-07-06_19:29:22 | |
[2021-07-06 19:29:23,968] [INFO] [launch.py:80:main] WORLD INFO DICT: {'localhost': [0, 1, 2, 3]} | |
[2021-07-06 19:29:23,968] [INFO] [launch.py:89:main] nnodes=1, num_local_procs=4, node_rank=0 | |
[2021-07-06 19:29:23,968] [INFO] [launch.py:101:main] global_rank_mapping=defaultdict(<class 'list'>, {'localhost': [0, 1, 2, 3]}) | |
[2021-07-06 19:29:23,968] [INFO] [launch.py:102:main] dist_world_size=4 | |
[2021-07-06 19:29:23,968] [INFO] [launch.py:105:main] Setting CUDA_VISIBLE_DEVICES=0,1,2,3 | |
Running Config File: zero3_1node_profile_2021-07-06_19:29:22 | |
Args = Namespace(attention_dropout_checkpoint=True, ckpt_to_save=[200], config={'train_batch_size': 64, 'train_micro_batch_size_per_gpu': 2, 'steps_per_print': 100, 'prescale_gradients': False, 'bert_token_file': 'bert-large-uncased', 'bert_model_config': {'vocab_size_or_config_json_file': 32003, 'hidden_size': 2560, 'num_hidden_layers': 12, 'num_attention_heads': 40, 'intermediate_size': 10240, 'hidden_act': 'gelu', 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'initializer_range': 0.02}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'reduce_scatter': False, 'contiguous_gradients': False}, 'zero_allow_untested_optimizer': True, 'optimizer': {'type': 'Adam', 'params': {'lr': 0.0001, 'weight_decay': 0.01, 'bias_correction': True, 'eps': 1e-06}}, 'gradient_clipping': 1.0, 'wall_clock_breakdown': True, 'fp16': {'enabled': True, 'loss_scale': 0, 'initial_scale_power': 20, 'loss_scale_window': 1000}, 'data': {'flags': {'pretrain_dataset': True, 'pretrain_type': 'wiki_bc'}, 'datasets': {'pretrain_dataset': '512/wikicorpus_en'}}, 'training': {'num_epochs': 20, 'warmup_proportion': 0.02, 'learning_rate': 0.002, 'num_workers': 4, 'async_worker': True, 'decay_rate': 0.9, 'decay_step': 150, 'total_training_steps': 15000}}, config_file='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', data_path_prefix='/home/ec2-user/bert-data-nv', deepscale=False, deepscale_config=None, deepspeed=True, deepspeed_config='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', deepspeed_mpi=False, deepspeed_sparse_attention=False, deepspeed_transformer_kernel=True, do_lower_case=True, finetune=False, gelu_checkpoint=True, job_name='zero3_1node_profile_2021-07-06_19:29:22', load_checkpoint_id=None, load_training_checkpoint=None, local_rank=3, logger=<turing.logger.Logger object at 0x7fbc33b3cfd0>, lr_offset=0.0, lr_schedule='EE', max_predictions_per_seq=80, max_seq_length=512, max_steps=5, max_steps_per_epoch=9223372036854775807, no_cuda=False, normalize_invertible=False, output_dir='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-06_19:29:22/', print_steps=10, progressive_layer_drop=False, refresh_bucket_size=1, rewarmup=True, seed=42, stochastic_mode=False, use_nvidia_dataset=True, use_pretrain=False, validation_data_path_prefix=None) | |
Running Config File: zero3_1node_profile_2021-07-06_19:29:22 | |
Args = Namespace(attention_dropout_checkpoint=True, ckpt_to_save=[200], config={'train_batch_size': 64, 'train_micro_batch_size_per_gpu': 2, 'steps_per_print': 100, 'prescale_gradients': False, 'bert_token_file': 'bert-large-uncased', 'bert_model_config': {'vocab_size_or_config_json_file': 32003, 'hidden_size': 2560, 'num_hidden_layers': 12, 'num_attention_heads': 40, 'intermediate_size': 10240, 'hidden_act': 'gelu', 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'initializer_range': 0.02}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'reduce_scatter': False, 'contiguous_gradients': False}, 'zero_allow_untested_optimizer': True, 'optimizer': {'type': 'Adam', 'params': {'lr': 0.0001, 'weight_decay': 0.01, 'bias_correction': True, 'eps': 1e-06}}, 'gradient_clipping': 1.0, 'wall_clock_breakdown': True, 'fp16': {'enabled': True, 'loss_scale': 0, 'initial_scale_power': 20, 'loss_scale_window': 1000}, 'data': {'flags': {'pretrain_dataset': True, 'pretrain_type': 'wiki_bc'}, 'datasets': {'pretrain_dataset': '512/wikicorpus_en'}}, 'training': {'num_epochs': 20, 'warmup_proportion': 0.02, 'learning_rate': 0.002, 'num_workers': 4, 'async_worker': True, 'decay_rate': 0.9, 'decay_step': 150, 'total_training_steps': 15000}}, config_file='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', data_path_prefix='/home/ec2-user/bert-data-nv', deepscale=False, deepscale_config=None, deepspeed=True, deepspeed_config='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', deepspeed_mpi=False, deepspeed_sparse_attention=False, deepspeed_transformer_kernel=True, do_lower_case=True, finetune=False, gelu_checkpoint=True, job_name='zero3_1node_profile_2021-07-06_19:29:22', load_checkpoint_id=None, load_training_checkpoint=None, local_rank=0, logger=<turing.logger.Logger object at 0x7f990884dfd0>, lr_offset=0.0, lr_schedule='EE', max_predictions_per_seq=80, max_seq_length=512, max_steps=5, max_steps_per_epoch=9223372036854775807, no_cuda=False, normalize_invertible=False, output_dir='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-06_19:29:22/', print_steps=10, progressive_layer_drop=False, refresh_bucket_size=1, rewarmup=True, seed=42, stochastic_mode=False, use_nvidia_dataset=True, use_pretrain=False, validation_data_path_prefix=None) | |
Running Config File: zero3_1node_profile_2021-07-06_19:29:22 | |
Args = Namespace(attention_dropout_checkpoint=True, ckpt_to_save=[200], config={'train_batch_size': 64, 'train_micro_batch_size_per_gpu': 2, 'steps_per_print': 100, 'prescale_gradients': False, 'bert_token_file': 'bert-large-uncased', 'bert_model_config': {'vocab_size_or_config_json_file': 32003, 'hidden_size': 2560, 'num_hidden_layers': 12, 'num_attention_heads': 40, 'intermediate_size': 10240, 'hidden_act': 'gelu', 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'initializer_range': 0.02}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'reduce_scatter': False, 'contiguous_gradients': False}, 'zero_allow_untested_optimizer': True, 'optimizer': {'type': 'Adam', 'params': {'lr': 0.0001, 'weight_decay': 0.01, 'bias_correction': True, 'eps': 1e-06}}, 'gradient_clipping': 1.0, 'wall_clock_breakdown': True, 'fp16': {'enabled': True, 'loss_scale': 0, 'initial_scale_power': 20, 'loss_scale_window': 1000}, 'data': {'flags': {'pretrain_dataset': True, 'pretrain_type': 'wiki_bc'}, 'datasets': {'pretrain_dataset': '512/wikicorpus_en'}}, 'training': {'num_epochs': 20, 'warmup_proportion': 0.02, 'learning_rate': 0.002, 'num_workers': 4, 'async_worker': True, 'decay_rate': 0.9, 'decay_step': 150, 'total_training_steps': 15000}}, config_file='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', data_path_prefix='/home/ec2-user/bert-data-nv', deepscale=False, deepscale_config=None, deepspeed=True, deepspeed_config='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', deepspeed_mpi=False, deepspeed_sparse_attention=False, deepspeed_transformer_kernel=True, do_lower_case=True, finetune=False, gelu_checkpoint=True, job_name='zero3_1node_profile_2021-07-06_19:29:22', load_checkpoint_id=None, load_training_checkpoint=None, local_rank=2, logger=<turing.logger.Logger object at 0x7faf4fa37fd0>, lr_offset=0.0, lr_schedule='EE', max_predictions_per_seq=80, max_seq_length=512, max_steps=5, max_steps_per_epoch=9223372036854775807, no_cuda=False, normalize_invertible=False, output_dir='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-06_19:29:22/', print_steps=10, progressive_layer_drop=False, refresh_bucket_size=1, rewarmup=True, seed=42, stochastic_mode=False, use_nvidia_dataset=True, use_pretrain=False, validation_data_path_prefix=None) | |
Running Config File: zero3_1node_profile_2021-07-06_19:29:22 | |
Args = Namespace(attention_dropout_checkpoint=True, ckpt_to_save=[200], config={'train_batch_size': 64, 'train_micro_batch_size_per_gpu': 2, 'steps_per_print': 100, 'prescale_gradients': False, 'bert_token_file': 'bert-large-uncased', 'bert_model_config': {'vocab_size_or_config_json_file': 32003, 'hidden_size': 2560, 'num_hidden_layers': 12, 'num_attention_heads': 40, 'intermediate_size': 10240, 'hidden_act': 'gelu', 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'initializer_range': 0.02}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'reduce_scatter': False, 'contiguous_gradients': False}, 'zero_allow_untested_optimizer': True, 'optimizer': {'type': 'Adam', 'params': {'lr': 0.0001, 'weight_decay': 0.01, 'bias_correction': True, 'eps': 1e-06}}, 'gradient_clipping': 1.0, 'wall_clock_breakdown': True, 'fp16': {'enabled': True, 'loss_scale': 0, 'initial_scale_power': 20, 'loss_scale_window': 1000}, 'data': {'flags': {'pretrain_dataset': True, 'pretrain_type': 'wiki_bc'}, 'datasets': {'pretrain_dataset': '512/wikicorpus_en'}}, 'training': {'num_epochs': 20, 'warmup_proportion': 0.02, 'learning_rate': 0.002, 'num_workers': 4, 'async_worker': True, 'decay_rate': 0.9, 'decay_step': 150, 'total_training_steps': 15000}}, config_file='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', data_path_prefix='/home/ec2-user/bert-data-nv', deepscale=False, deepscale_config=None, deepspeed=True, deepspeed_config='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', deepspeed_mpi=False, deepspeed_sparse_attention=False, deepspeed_transformer_kernel=True, do_lower_case=True, finetune=False, gelu_checkpoint=True, job_name='zero3_1node_profile_2021-07-06_19:29:22', load_checkpoint_id=None, load_training_checkpoint=None, local_rank=1, logger=<turing.logger.Logger object at 0x7fe9d9750fd0>, lr_offset=0.0, lr_schedule='EE', max_predictions_per_seq=80, max_seq_length=512, max_steps=5, max_steps_per_epoch=9223372036854775807, no_cuda=False, normalize_invertible=False, output_dir='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-06_19:29:22/', print_steps=10, progressive_layer_drop=False, refresh_bucket_size=1, rewarmup=True, seed=42, stochastic_mode=False, use_nvidia_dataset=True, use_pretrain=False, validation_data_path_prefix=None) | |
07/06/2021 19:29:25 - INFO - pytorch_pretrained_bert.tokenization - loading vocabulary file https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt from cache at /home/ec2-user/.pytorch_pretrained_bert/9b3c03a36e83b13d5ba95ac965c9f9074a99e14340c523ab405703179e79fc46.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084 | |
07/06/2021 19:29:25 - INFO - pytorch_pretrained_bert.tokenization - loading vocabulary file https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt from cache at /home/ec2-user/.pytorch_pretrained_bert/9b3c03a36e83b13d5ba95ac965c9f9074a99e14340c523ab405703179e79fc46.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084 | |
07/06/2021 19:29:25 - INFO - pytorch_pretrained_bert.tokenization - loading vocabulary file https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt from cache at /home/ec2-user/.pytorch_pretrained_bert/9b3c03a36e83b13d5ba95ac965c9f9074a99e14340c523ab405703179e79fc46.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084 | |
07/06/2021 19:29:25 - INFO - pytorch_pretrained_bert.tokenization - loading vocabulary file https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt from cache at /home/ec2-user/.pytorch_pretrained_bert/9b3c03a36e83b13d5ba95ac965c9f9074a99e14340c523ab405703179e79fc46.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084 | |
07/06/2021 19:29:25 - WARNING - root - Skipping validation because validation_data_path_prefix is unspecified | |
07/06/2021 19:29:25 - WARNING - root - Early training exit is set after 5 global steps | |
[2021-07-06 19:29:25,241] [INFO] [distributed.py:47:init_distributed] Initializing torch distributed with backend: nccl | |
07/06/2021 19:29:25 - WARNING - root - Skipping validation because validation_data_path_prefix is unspecified | |
07/06/2021 19:29:25 - WARNING - root - Early training exit is set after 5 global steps | |
[2021-07-06 19:29:25,246] [INFO] [distributed.py:47:init_distributed] Initializing torch distributed with backend: nccl | |
07/06/2021 19:29:25 - WARNING - root - Skipping validation because validation_data_path_prefix is unspecified | |
07/06/2021 19:29:25 - WARNING - root - Early training exit is set after 5 global steps | |
[2021-07-06 19:29:25,248] [INFO] [distributed.py:47:init_distributed] Initializing torch distributed with backend: nccl | |
07/06/2021 19:29:25 - WARNING - root - Skipping validation because validation_data_path_prefix is unspecified | |
07/06/2021 19:29:25 - WARNING - root - Early training exit is set after 5 global steps | |
[2021-07-06 19:29:25,254] [INFO] [distributed.py:47:init_distributed] Initializing torch distributed with backend: nccl | |
VOCAB SIZE: 30528 | |
VOCAB SIZE: 30528 | |
VOCAB SIZE: 30528 | |
VOCAB SIZE: 30528 | |
DeepSpeed Transformer config is {'layer_id': 0, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 0, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 0, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
DeepSpeed Transformer config is {'layer_id': 0, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Detected CUDA files, patching ldflags | |
Emitting ninja build file /home/ec2-user/.cache/torch_extensions/transformer/build.ninja... | |
Building extension module transformer... | |
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) | |
ninja: no work to do. | |
Loading extension module transformer... | |
Time to load transformer op: 0.16208815574645996 seconds | |
Loading extension module transformer... | |
Time to load transformer op: 0.2033708095550537 seconds | |
Loading extension module transformer... | |
Time to load transformer op: 0.2032008171081543 seconds | |
Loading extension module transformer... | |
Time to load transformer op: 0.20306730270385742 seconds | |
layer #0 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 1, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #0 is created with date type [half]. | |
layer #0 is created with date type [half]. | |
layer #0 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 1, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 1, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 1, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #1 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 2, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #1 is created with date type [half]. | |
layer #1 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 2, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #1 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 2, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 2, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #2 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 3, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #2 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 3, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #2 is created with date type [half]. | |
layer #2 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 3, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 3, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #3 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 4, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #3 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 4, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #3 is created with date type [half]. | |
layer #3 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 4, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 4, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #4 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 5, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #4 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 5, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #4 is created with date type [half]. | |
layer #4 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 5, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 5, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #5 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 6, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #5 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 6, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #5 is created with date type [half]. | |
layer #5 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 6, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 6, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #6 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 7, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #6 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 7, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #6 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 7, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #6 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 7, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #7 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 8, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #7 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 8, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #7 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 8, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #7 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 8, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #8 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 9, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #8 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 9, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #8 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 9, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #8 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 9, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #9 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 10, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #9 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 10, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #9 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 10, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #9 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 10, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #10 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 11, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #10 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 11, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #10 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 11, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #10 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 11, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 12, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #11 is created with date type [half]. | |
layer #11 is created with date type [half]. | |
layer #11 is created with date type [half]. | |
layer #11 is created with date type [half]. | |
07/06/2021 19:29:40 - INFO - nvidia.modelingpreln - Init BERT pretrain model | |
07/06/2021 19:29:40 - INFO - nvidia.modelingpreln - Init BERT pretrain model | |
07/06/2021 19:29:40 - INFO - nvidia.modelingpreln - Init BERT pretrain model | |
07/06/2021 19:29:40 - INFO - nvidia.modelingpreln - Init BERT pretrain model | |
[2021-07-06 19:29:42,470] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.4.3+edb04db, git-hash=edb04db, git-branch=zhen/pipeline_impr | |
[2021-07-06 19:29:43,983] [INFO] [utils.py:13:_initialize_parameter_parallel_groups] data_parallel_size: 4, parameter_parallel_size: 4 | |
[2021-07-06 19:29:44,164] [INFO] [utils.py:13:_initialize_parameter_parallel_groups] data_parallel_size: 4, parameter_parallel_size: 4 | |
[2021-07-06 19:29:44,331] [INFO] [utils.py:13:_initialize_parameter_parallel_groups] data_parallel_size: 4, parameter_parallel_size: 4 | |
[2021-07-06 19:29:44,411] [INFO] [utils.py:13:_initialize_parameter_parallel_groups] data_parallel_size: 4, parameter_parallel_size: 4 | |
[2021-07-06 19:29:44,471] [INFO] [engine.py:177:__init__] DeepSpeed Flops Profiler Enabled: False | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Detected CUDA files, patching ldflags | |
Emitting ninja build file /home/ec2-user/.cache/torch_extensions/fused_adam/build.ninja... | |
Building extension module fused_adam... | |
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) | |
ninja: no work to do. | |
Loading extension module fused_adam... | |
Time to load fused_adam op: 0.19509577751159668 seconds | |
Loading extension module fused_adam... | |
Loading extension module fused_adam... | |
Time to load fused_adam op: 0.20230555534362793 seconds | |
Time to load fused_adam op: 0.20225286483764648 seconds | |
Loading extension module fused_adam... | |
Time to load fused_adam op: 0.2023007869720459 seconds | |
[2021-07-06 19:29:44,841] [INFO] [engine.py:707:_configure_optimizer] Using DeepSpeed Optimizer param name adam as basic optimizer | |
[2021-07-06 19:29:44,841] [INFO] [engine.py:711:_configure_optimizer] DeepSpeed Basic Optimizer = FusedAdam | |
[2021-07-06 19:29:44,841] [INFO] [utils.py:44:is_zero_supported_optimizer] Checking ZeRO support for optimizer=FusedAdam type=<class 'deepspeed.ops.adam.fused_adam.FusedAdam'> | |
[2021-07-06 19:29:44,841] [INFO] [logging.py:68:log_dist] [Rank 0] Creating fp16 ZeRO stage 3 optimizer | |
[2021-07-06 19:29:44,841] [INFO] [engine.py:935:_configure_zero_optimizer] Initializing ZeRO Stage 3 | |
[2021-07-06 19:29:44,845] [INFO] [stage3.py:495:__init__] Reduce bucket size 500000000 | |
[2021-07-06 19:29:44,845] [INFO] [stage3.py:496:__init__] Allgather bucket size 50000000 | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root...Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Emitting ninja build file /home/ec2-user/.cache/torch_extensions/utils/build.ninja... | |
Building extension module utils... | |
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) | |
ninja: no work to do. | |
Loading extension module utils... | |
Time to load utils op: 0.18239712715148926 seconds | |
Loading extension module utils... | |
Loading extension module utils... | |
Loading extension module utils... | |
Time to load utils op: 0.20194101333618164 seconds | |
Time to load utils op: 0.20187997817993164 seconds | |
Time to load utils op: 0.2019813060760498 seconds | |
[2021-07-06 19:29:45,733] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | init_optimizer_state: 54.60 | |
[2021-07-06 19:29:45,733] [INFO] [stage3.py:686:__init__] optimizer state initialized | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root...Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root...Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Emitting ninja build file /home/ec2-user/.cache/torch_extensions/communication/build.ninja... | |
Building extension module communication... | |
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) | |
ninja: no work to do. | |
Loading extension module communication... | |
Time to load communication op: 0.18649578094482422 seconds | |
Loading extension module communication...Loading extension module communication... | |
Loading extension module communication... | |
Time to load communication op: 0.2023775577545166 secondsTime to load communication op: 0.2023792266845703 seconds | |
Time to load communication op: 0.20232820510864258 seconds | |
[2021-07-06 19:29:46,378] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = adam | |
[2021-07-06 19:29:46,378] [INFO] [engine.py:513:_configure_lr_scheduler] DeepSpeed using client LR scheduler | |
[2021-07-06 19:29:46,378] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = None | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root...Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
[2021-07-06 19:29:46,378] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0001, 0.0001], mom=[(0.9, 0.999), (0.9, 0.999)] | |
[2021-07-06 19:29:46,378] [INFO] [config.py:900:print] DeepSpeedEngine configuration: | |
No modifications detected for re-loaded extension module utils, skipping build step... | |
No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... | |
Loading extension module utils... | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
Time to load utils op: 0.0003921985626220703 seconds | |
Time to load utils op: 0.00039267539978027344 seconds | |
No modifications detected for re-loaded extension module utils, skipping build step... | |
Loading extension module utils... | |
Time to load utils op: 0.00048732757568359375 seconds | |
[2021-07-06 19:29:46,378] [INFO] [config.py:904:print] activation_checkpointing_config { | |
"partition_activations": false, | |
"contiguous_memory_optimization": false, | |
"cpu_checkpointing": false, | |
"number_checkpoints": null, | |
"synchronize_checkpoint_boundary": false, | |
"profile": false | |
} | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] allreduce_always_fp32 ........ False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] amp_enabled .................. False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] amp_params ................... False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] checkpoint_tag_validation_enabled True | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] checkpoint_tag_validation_fail False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] disable_allgather ............ False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] dump_state ................... False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] dynamic_loss_scale_args ...... {'init_scale': 1048576, 'scale_window': 1000, 'delayed_shift': 2, 'min_scale': 1} | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] eigenvalue_enabled ........... False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] eigenvalue_gas_boundary_resolution 1 | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] eigenvalue_layer_name ........ bert.encoder.layer | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] eigenvalue_layer_num ......... 0 | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] eigenvalue_max_iter .......... 100 | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] eigenvalue_stability ......... 1e-06 | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] eigenvalue_tol ............... 0.01 | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] eigenvalue_verbose ........... False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] elasticity_enabled ........... False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] flops_profiler_config ........ { | |
"enabled": false, | |
"profile_step": 1, | |
"module_depth": -1, | |
"top_modules": 1, | |
"detailed": true, | |
"output_file": null | |
} | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] fp16_enabled ................. True | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] fp16_mixed_quantize .......... False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] global_rank .................. 0 | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] gradient_accumulation_steps .. 8 | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] gradient_clipping ............ 1.0 | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] gradient_predivide_factor .... 1.0 | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] initial_dynamic_scale ........ 1048576 | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] loss_scale ................... 0 | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] memory_breakdown ............. False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] optimizer_legacy_fusion ...... False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] optimizer_name ............... adam | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] optimizer_params ............. {'lr': 0.0001, 'weight_decay': 0.01, 'bias_correction': True, 'eps': 1e-06} | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] pld_enabled .................. False | |
[2021-07-06 19:29:46,379] [INFO] [config.py:904:print] pld_params ................... False | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] prescale_gradients ........... False | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] quantize_change_rate ......... 0.001 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] quantize_groups .............. 1 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] quantize_offset .............. 1000 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] quantize_period .............. 1000 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] quantize_rounding ............ 0 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] quantize_start_bits .......... 16 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] quantize_target_bits ......... 8 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] quantize_training_enabled .... False | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] quantize_type ................ 0 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] quantize_verbose ............. False | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] scheduler_name ............... None | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] scheduler_params ............. None | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] sparse_attention ............. None | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] sparse_gradients_enabled ..... False | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] steps_per_print .............. 100 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] tensorboard_enabled .......... False | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] tensorboard_job_name ......... DeepSpeedJobName | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] tensorboard_output_path ...... | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] train_batch_size ............. 64 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] train_micro_batch_size_per_gpu 2 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] use_quantizer_kernel ......... False | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] wall_clock_breakdown ......... True | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] world_size ................... 4 | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] zero_allow_untested_optimizer True | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] zero_config .................. { | |
"stage": 3, | |
"contiguous_gradients": false, | |
"reduce_scatter": false, | |
"reduce_bucket_size": 5.000000e+08, | |
"allgather_partitions": true, | |
"allgather_bucket_size": 5.000000e+08, | |
"overlap_comm": true, | |
"load_from_fp32_weights": true, | |
"elastic_checkpoint": true, | |
"offload_param": null, | |
"offload_optimizer": null, | |
"sub_group_size": 1.000000e+09, | |
"prefetch_bucket_size": 5.000000e+07, | |
"param_persistence_threshold": 1.000000e+05, | |
"max_live_parameters": 1.000000e+09, | |
"max_reuse_distance": 1.000000e+09, | |
"gather_fp16_weights_on_model_save": false, | |
"ignore_unused_parameters": true, | |
"legacy_stage1": false | |
} | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] zero_enabled ................. True | |
[2021-07-06 19:29:46,380] [INFO] [config.py:904:print] zero_optimization_stage ...... 3 | |
[2021-07-06 19:29:46,381] [INFO] [config.py:911:print] json = { | |
"train_batch_size": 64, | |
"train_micro_batch_size_per_gpu": 2, | |
"steps_per_print": 100, | |
"prescale_gradients": false, | |
"bert_token_file": "bert-large-uncased", | |
"bert_model_config": { | |
"vocab_size_or_config_json_file": 3.200300e+04, | |
"hidden_size": 2.560000e+03, | |
"num_hidden_layers": 12, | |
"num_attention_heads": 40, | |
"intermediate_size": 1.024000e+04, | |
"hidden_act": "gelu", | |
"hidden_dropout_prob": 0.1, | |
"attention_probs_dropout_prob": 0.1, | |
"max_position_embeddings": 512, | |
"initializer_range": 0.02 | |
}, | |
"zero_optimization": { | |
"stage": 3, | |
"overlap_comm": true, | |
"reduce_scatter": false, | |
"contiguous_gradients": false | |
}, | |
"zero_allow_untested_optimizer": true, | |
"optimizer": { | |
"type": "Adam", | |
"params": { | |
"lr": 0.0001, | |
"weight_decay": 0.01, | |
"bias_correction": true, | |
"eps": 1e-06 | |
} | |
}, | |
"gradient_clipping": 1.0, | |
"wall_clock_breakdown": true, | |
"fp16": { | |
"enabled": true, | |
"loss_scale": 0, | |
"initial_scale_power": 20, | |
"loss_scale_window": 1000 | |
}, | |
"data": { | |
"flags": { | |
"pretrain_dataset": true, | |
"pretrain_type": "wiki_bc" | |
}, | |
"mixed_seq_datasets": { | |
"128": { | |
"pretrain_dataset": "128/wikicorpus_en" | |
}, | |
"512": { | |
"pretrain_dataset": "512/wikicorpus_en" | |
} | |
} | |
}, | |
"mixed_seq_training": { | |
"128": { | |
"num_epochs": 16, | |
"warmup_proportion": 0.06, | |
"learning_rate": 0.011, | |
"num_workers": 4, | |
"async_worker": true, | |
"decay_rate": 0.9, | |
"decay_step": 250, | |
"total_training_steps": 0 | |
}, | |
"512": { | |
"num_epochs": 20, | |
"warmup_proportion": 0.02, | |
"learning_rate": 0.002, | |
"num_workers": 4, | |
"async_worker": true, | |
"decay_rate": 0.9, | |
"decay_step": 150, | |
"total_training_steps": 1.500000e+04 | |
} | |
} | |
} | |
Using /home/ec2-user/.cache/torch_extensions as PyTorch extensions root... | |
No modifications detected for re-loaded extension module utils, skipping build step... | |
Loading extension module utils... | |
Time to load utils op: 0.0003666877746582031 seconds | |
07/06/2021 19:29:46 - INFO - turing.logger - NvidiaBertDatasetProvider - Initialization: num_files = 256 | |
07/06/2021 19:29:46 - INFO - turing.logger - Training Epoch: 1 | |
07/06/2021 19:29:51 - INFO - turing.logger - worker-0: begin epoch 1 current_sample_count 0 shard_length 305883 global_data_samples 0 | |
0%| | 0/152942 [00:00<?, ?it/s] | |
0%| | 0/152613 [00:00<?, ?it/s] | |
0%| | 0/152966 [00:00<?, ?it/s] | |
0%| | 0/152794 [00:00<?, ?it/s]/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
0: M0 P[] avail 0.0e+00, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [0] | |
1: M1 P[] avail 0.0e+00, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [1] | |
2: M2 P[] avail 0.0e+00, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [2] | |
-gather param for module 3: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
3: M3 P[0] avail 7.8e+07, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.8e+07, inflight [3] | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia_bert_dataset_provider.py:74: UserWarning: This overload of nonzero is deprecated: | |
nonzero() | |
Consider using one of the following signatures instead: | |
nonzero(*, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.) | |
padded_mask_indices = (masked_lm_positions == 0).nonzero() | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
4: M4 P[1] avail 7.9e+07, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 5: {'id': 2, 'status': 'NOT_AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
5: M5 P[2] avail 7.9e+07, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 5.1e+03, inflight [5] | |
-gather param for module 6: {'id': 3, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
6: M6 P[3, 4] avail 7.9e+07, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 5.1e+03, inflight [6] | |
7: M7 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [7] | |
8: M8 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [8] | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
9: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.6e+08, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [11] | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
10: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 2.4e+08, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
11: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 3.2e+08, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 14: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
12: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 3.9e+08, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 15: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
13: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 4.7e+08, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 16: {'id': 67, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
14: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 5.5e+08, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 17: {'id': 79, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
15: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 6.3e+08, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 18: {'id': 91, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
16: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 7.1e+08, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 19: {'id': 103, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
17: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 7.9e+08, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 20: {'id': 115, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
18: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 8.7e+08, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 21: {'id': 127, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
19: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 9.4e+08, max_avail 5.0e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 22: {'id': 139, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'NOT_AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'NOT_AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
20: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -2.4e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 9: {'id': 5, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
21: M9 P[5, 6] avail 1.0e+09, max_avail -2.4e+07, queue_sz 0.0e+00, n_inflight 5.1e+03, inflight [9] | |
22: M23 P[] avail 1.0e+09, max_avail -2.4e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
23: M24 P[151, 152] avail 1.0e+09, max_avail -3.0e+07, queue_sz 0.0e+00, n_inflight 6.6e+06, inflight [24] | |
24: M25 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 26: {'id': 153, 'status': 'NOT_AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
25: M26 P[153] avail 1.0e+09, max_avail -3.0e+07, queue_sz 0.0e+00, n_inflight 3.1e+04, inflight [26] | |
26: M27 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 28: {'id': 154, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
27: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 6.6e+06, inflight [28] | |
-gather param for module 29: {'id': 156, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'NOT_AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
28: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
29: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.8e+07, inflight [30] | |
-gather param for module 31: {'id': 158, 'status': 'NOT_AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'NOT_AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
30: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 5.1e+03, inflight [31] | |
31: M0 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [0] | |
32: M25 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
33: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 5.1e+03, inflight [31] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
34: M26 P[153] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 3.1e+04, inflight [26] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
35: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.8e+07, inflight [30] | |
36: M27 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
37: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 28: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
38: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 6.6e+06, inflight [28] | |
39: M1 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [1] | |
40: M23 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
41: M24 P[151, 152] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 6.6e+06, inflight [24] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
42: M9 P[5, 6] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 5.1e+03, inflight [9] | |
-gather param for module 22: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
43: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 21: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
44: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 20: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
45: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 19: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
46: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 18: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
47: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 17: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
48: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 16: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
49: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 15: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
50: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 14: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
51: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 13: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
52: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 12: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
53: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 11: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
54: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.9e+07, inflight [11] | |
55: M2 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [2] | |
56: M7 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 0.0e+00, inflight [7] | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
57: M6 P[3, 4] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 5.1e+03, inflight [6] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
58: M5 P[2] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 5.1e+03, inflight [5] | |
-gather param for module 4: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
59: M4 P[1] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 3: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
60: M3 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 0.0e+00, n_inflight 7.8e+07, inflight [3] | |
-release param: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
[2021-07-06 19:29:52,749] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward_microstep: 624.36 | backward_microstep: 827.56 | backward_inner_microstep: 768.84 | backward_allreduce_microstep: 58.66 | step_microstep: 0.04 | |
0%| | 1/152794 [00:01<64:17:22, 1.51s/it] | |
0%| | 1/152966 [00:01<66:51:16, 1.57s/it] | |
0%| | 1/152613 [00:01<67:10:00, 1.58s/it][2021-07-06 19:29:52,749] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward: 624.34 | backward: 827.54 | backward_inner: 768.77 | backward_allreduce: 58.64 | step: 0.02 | |
0%| | 1/152942 [00:01<68:33:34, 1.61s/it]0: M0 P[] avail 4.6e+05, max_avail 5.0e+07, queue_sz 6.1e+01, n_inflight 0.0e+00, inflight [0] | |
-gather param for module 3: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
1: M1 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 5.7e+01, n_inflight 7.8e+07, inflight [1, 3, 2] | |
2: M2 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 5.7e+01, n_inflight 7.8e+07, inflight [2, 3] | |
3: M3 P[0] avail 7.9e+07, max_avail 5.0e+07, queue_sz 5.7e+01, n_inflight 7.8e+07, inflight [3] | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
4: M4 P[1] avail 8.0e+07, max_avail 5.0e+07, queue_sz 5.7e+01, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
5: M5 P[2] avail 1.6e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [8, 5, 6, 7, 11] | |
6: M6 P[3, 4] avail 1.6e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [8, 7, 11, 6] | |
7: M7 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [8, 11, 7] | |
8: M8 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [8, 11] | |
9: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.6e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [11] | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
10: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 2.4e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
11: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 3.2e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 14: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
12: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 3.9e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 15: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
13: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 4.7e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 16: {'id': 67, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
14: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 5.5e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 17: {'id': 79, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
15: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 6.3e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 18: {'id': 91, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
16: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 7.1e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 19: {'id': 103, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
17: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 7.9e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 20: {'id': 115, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
18: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 8.7e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 21: {'id': 127, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
19: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 9.4e+08, max_avail 5.0e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 22: {'id': 139, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
20: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -2.4e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
21: M9 P[5, 6] avail 1.0e+09, max_avail -2.4e+07, queue_sz 5.1e+01, n_inflight 5.1e+03, inflight [9] | |
22: M23 P[] avail 1.0e+09, max_avail -2.4e+07, queue_sz 5.1e+01, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
23: M24 P[151, 152] avail 1.0e+09, max_avail -3.0e+07, queue_sz 5.1e+01, n_inflight 6.6e+06, inflight [24] | |
24: M25 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 5.1e+01, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
25: M26 P[153] avail 1.0e+09, max_avail -3.0e+07, queue_sz 5.1e+01, n_inflight 3.1e+04, inflight [26] | |
26: M27 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 5.1e+01, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 28: {'id': 154, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
27: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 6.6e+06, inflight [28] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
28: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
29: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.8e+07, inflight [30] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
30: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 5.1e+03, inflight [31] | |
31: M0 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 0.0e+00, inflight [0] | |
32: M25 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
33: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 5.1e+03, inflight [31] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
34: M26 P[153] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 3.1e+04, inflight [26] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
35: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.8e+07, inflight [30] | |
36: M27 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
37: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 28: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
38: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 6.6e+06, inflight [28] | |
39: M1 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 0.0e+00, inflight [1] | |
40: M23 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
41: M24 P[151, 152] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 6.6e+06, inflight [24] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
42: M9 P[5, 6] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 5.1e+03, inflight [9] | |
-gather param for module 22: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
43: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 21: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
44: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 20: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
45: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 19: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
46: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 18: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
47: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 17: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
48: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 16: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
49: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 15: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
50: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 14: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
51: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 13: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
52: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 12: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
53: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 11: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
54: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.9e+07, inflight [11] | |
55: M2 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 0.0e+00, inflight [2] | |
56: M7 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 0.0e+00, inflight [7] | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
57: M6 P[3, 4] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 5.1e+03, inflight [6] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
58: M5 P[2] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 5.1e+03, inflight [5] | |
-gather param for module 4: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
59: M4 P[1] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 3: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
60: M3 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 5.1e+01, n_inflight 7.8e+07, inflight [3] | |
-release param: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
[2021-07-06 19:29:54,295] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward_microstep: 730.98 | backward_microstep: 813.25 | backward_inner_microstep: 754.98 | backward_allreduce_microstep: 58.22 | step_microstep: 0.03 | |
0%| | 2/152966 [00:03<65:41:13, 1.55s/it][2021-07-06 19:29:54,295] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward: 730.96 | backward: 813.24 | backward_inner: 754.94 | backward_allreduce: 58.20 | step: 0.02 | |
0%| | 2/152794 [00:03<65:36:47, 1.55s/it] | |
0%| | 2/152613 [00:03<65:32:14, 1.55s/it] | |
0%| | 2/152942 [00:03<65:40:07, 1.55s/it]0: M0 P[] avail 4.6e+05, max_avail 5.0e+07, queue_sz 1.2e+02, n_inflight 0.0e+00, inflight [0] | |
-gather param for module 3: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
1: M1 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 1.2e+02, n_inflight 7.8e+07, inflight [1, 3, 2] | |
2: M2 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 1.2e+02, n_inflight 7.8e+07, inflight [2, 3] | |
3: M3 P[0] avail 7.9e+07, max_avail 5.0e+07, queue_sz 1.2e+02, n_inflight 7.8e+07, inflight [3] | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
4: M4 P[1] avail 8.0e+07, max_avail 5.0e+07, queue_sz 1.2e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
5: M5 P[2] avail 1.6e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [8, 5, 6, 7, 11] | |
6: M6 P[3, 4] avail 1.6e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [8, 7, 11, 6] | |
7: M7 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [8, 11, 7] | |
8: M8 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [8, 11] | |
9: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.6e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [11] | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
10: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 2.4e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
11: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 3.2e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 14: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
12: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 3.9e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 15: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
13: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 4.7e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 16: {'id': 67, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
14: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 5.5e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 17: {'id': 79, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
15: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 6.3e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 18: {'id': 91, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
16: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 7.1e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 19: {'id': 103, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
17: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 7.9e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 20: {'id': 115, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
18: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 8.7e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 21: {'id': 127, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
19: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 9.4e+08, max_avail 5.0e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 22: {'id': 139, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
20: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -2.4e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
21: M9 P[5, 6] avail 1.0e+09, max_avail -2.4e+07, queue_sz 1.1e+02, n_inflight 5.1e+03, inflight [9] | |
22: M23 P[] avail 1.0e+09, max_avail -2.4e+07, queue_sz 1.1e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
23: M24 P[151, 152] avail 1.0e+09, max_avail -3.0e+07, queue_sz 1.1e+02, n_inflight 6.6e+06, inflight [24] | |
24: M25 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 1.1e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
25: M26 P[153] avail 1.0e+09, max_avail -3.0e+07, queue_sz 1.1e+02, n_inflight 3.1e+04, inflight [26] | |
26: M27 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 1.1e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 28: {'id': 154, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
27: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 6.6e+06, inflight [28] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
28: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
29: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.8e+07, inflight [30] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
30: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 5.1e+03, inflight [31] | |
31: M0 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 0.0e+00, inflight [0] | |
32: M25 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
33: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 5.1e+03, inflight [31] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
34: M26 P[153] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 3.1e+04, inflight [26] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
35: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.8e+07, inflight [30] | |
36: M27 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
37: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 28: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
38: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 6.6e+06, inflight [28] | |
39: M1 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 0.0e+00, inflight [1] | |
40: M23 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
41: M24 P[151, 152] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 6.6e+06, inflight [24] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
42: M9 P[5, 6] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 5.1e+03, inflight [9] | |
-gather param for module 22: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
43: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 21: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
44: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 20: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
45: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 19: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
46: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 18: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
47: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 17: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
48: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 16: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
49: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 15: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
50: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 14: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
51: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 13: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
52: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 12: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
53: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 11: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
54: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.9e+07, inflight [11] | |
55: M2 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 0.0e+00, inflight [2] | |
56: M7 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 0.0e+00, inflight [7] | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
57: M6 P[3, 4] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 5.1e+03, inflight [6] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
58: M5 P[2] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 5.1e+03, inflight [5] | |
-gather param for module 4: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
59: M4 P[1] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 3: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
60: M3 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.1e+02, n_inflight 7.8e+07, inflight [3] | |
-release param: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
0%| | 3/152613 [00:04<62:59:10, 1.49s/it][2021-07-06 19:29:55,781] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward_microstep: 434.48 | backward_microstep: 1050.16 | backward_inner_microstep: 991.84 | backward_allreduce_microstep: 58.27 | step_microstep: 0.04 | |
0%| | 3/152966 [00:04<63:08:16, 1.49s/it] | |
0%| | 3/152794 [00:04<63:03:53, 1.49s/it][2021-07-06 19:29:55,781] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward: 434.45 | backward: 1050.14 | backward_inner: 991.79 | backward_allreduce: 58.25 | step: 0.03 | |
0%| | 3/152942 [00:04<63:07:41, 1.49s/it]0: M0 P[] avail 4.6e+05, max_avail 5.0e+07, queue_sz 1.8e+02, n_inflight 0.0e+00, inflight [0] | |
-gather param for module 3: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
1: M1 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 1.8e+02, n_inflight 7.8e+07, inflight [1, 3, 2] | |
2: M2 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 1.8e+02, n_inflight 7.8e+07, inflight [2, 3] | |
3: M3 P[0] avail 7.9e+07, max_avail 5.0e+07, queue_sz 1.8e+02, n_inflight 7.8e+07, inflight [3] | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
4: M4 P[1] avail 8.0e+07, max_avail 5.0e+07, queue_sz 1.8e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
5: M5 P[2] avail 1.6e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [8, 5, 6, 7, 11] | |
6: M6 P[3, 4] avail 1.6e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [8, 7, 11, 6] | |
7: M7 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [8, 11, 7] | |
8: M8 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [8, 11] | |
9: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.6e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [11] | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
10: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 2.4e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
11: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 3.2e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 14: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
12: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 3.9e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 15: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
13: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 4.7e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 16: {'id': 67, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
14: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 5.5e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 17: {'id': 79, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
15: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 6.3e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 18: {'id': 91, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
16: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 7.1e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 19: {'id': 103, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
17: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 7.9e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 20: {'id': 115, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
18: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 8.7e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 21: {'id': 127, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
19: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 9.4e+08, max_avail 5.0e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 22: {'id': 139, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
20: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -2.4e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
21: M9 P[5, 6] avail 1.0e+09, max_avail -2.4e+07, queue_sz 1.7e+02, n_inflight 5.1e+03, inflight [9] | |
22: M23 P[] avail 1.0e+09, max_avail -2.4e+07, queue_sz 1.7e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
23: M24 P[151, 152] avail 1.0e+09, max_avail -3.0e+07, queue_sz 1.7e+02, n_inflight 6.6e+06, inflight [24] | |
24: M25 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 1.7e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
25: M26 P[153] avail 1.0e+09, max_avail -3.0e+07, queue_sz 1.7e+02, n_inflight 3.1e+04, inflight [26] | |
26: M27 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 1.7e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 28: {'id': 154, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
27: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 6.6e+06, inflight [28] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
28: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
29: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.8e+07, inflight [30] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
30: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 5.1e+03, inflight [31] | |
31: M0 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 0.0e+00, inflight [0] | |
32: M25 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
33: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 5.1e+03, inflight [31] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
34: M26 P[153] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 3.1e+04, inflight [26] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
35: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.8e+07, inflight [30] | |
36: M27 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
37: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 28: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
38: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 6.6e+06, inflight [28] | |
39: M1 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 0.0e+00, inflight [1] | |
40: M23 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
41: M24 P[151, 152] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 6.6e+06, inflight [24] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
42: M9 P[5, 6] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 5.1e+03, inflight [9] | |
-gather param for module 22: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
43: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 21: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
44: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 20: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
45: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 19: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
46: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 18: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
47: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 17: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
48: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 16: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
49: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 15: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
50: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 14: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
51: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 13: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
52: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 12: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
53: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 11: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
54: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.9e+07, inflight [11] | |
55: M2 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 0.0e+00, inflight [2] | |
56: M7 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 0.0e+00, inflight [7] | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
57: M6 P[3, 4] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 5.1e+03, inflight [6] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
58: M5 P[2] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 5.1e+03, inflight [5] | |
-gather param for module 4: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
59: M4 P[1] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 3: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
60: M3 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 1.7e+02, n_inflight 7.8e+07, inflight [3] | |
-release param: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
0%| | 4/152613 [00:05<52:44:02, 1.24s/it][2021-07-06 19:29:57,025] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward_microstep: 434.14 | backward_microstep: 808.52 | backward_inner_microstep: 749.51 | backward_allreduce_microstep: 58.97 | step_microstep: 0.04 | |
[2021-07-06 19:29:57,025] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward: 434.11 | backward: 808.50 | backward_inner: 749.46 | backward_allreduce: 58.95 | step: 0.03 | |
0%| | 4/152794 [00:05<52:48:01, 1.24s/it] | |
0%| | 4/152966 [00:05<52:51:44, 1.24s/it] | |
0%| | 4/152942 [00:05<52:50:56, 1.24s/it]0: M0 P[] avail 4.6e+05, max_avail 5.0e+07, queue_sz 2.4e+02, n_inflight 0.0e+00, inflight [0] | |
-gather param for module 3: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
1: M1 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 2.4e+02, n_inflight 7.8e+07, inflight [1, 3, 2] | |
2: M2 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 2.4e+02, n_inflight 7.8e+07, inflight [2, 3] | |
3: M3 P[0] avail 7.9e+07, max_avail 5.0e+07, queue_sz 2.4e+02, n_inflight 7.8e+07, inflight [3] | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
4: M4 P[1] avail 8.0e+07, max_avail 5.0e+07, queue_sz 2.4e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
5: M5 P[2] avail 1.6e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [8, 5, 6, 7, 11] | |
6: M6 P[3, 4] avail 1.6e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [8, 7, 11, 6] | |
7: M7 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [8, 11, 7] | |
8: M8 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [8, 11] | |
9: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.6e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [11] | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
10: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 2.4e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
11: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 3.2e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 14: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
12: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 3.9e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 15: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
13: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 4.7e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 16: {'id': 67, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
14: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 5.5e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 17: {'id': 79, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
15: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 6.3e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 18: {'id': 91, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
16: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 7.1e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 19: {'id': 103, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
17: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 7.9e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 20: {'id': 115, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
18: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 8.7e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 21: {'id': 127, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
19: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 9.4e+08, max_avail 5.0e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 22: {'id': 139, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
20: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -2.4e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
21: M9 P[5, 6] avail 1.0e+09, max_avail -2.4e+07, queue_sz 2.3e+02, n_inflight 5.1e+03, inflight [9] | |
22: M23 P[] avail 1.0e+09, max_avail -2.4e+07, queue_sz 2.3e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
23: M24 P[151, 152] avail 1.0e+09, max_avail -3.0e+07, queue_sz 2.3e+02, n_inflight 6.6e+06, inflight [24] | |
24: M25 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 2.3e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
25: M26 P[153] avail 1.0e+09, max_avail -3.0e+07, queue_sz 2.3e+02, n_inflight 3.1e+04, inflight [26] | |
26: M27 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 2.3e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 28: {'id': 154, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
27: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 6.6e+06, inflight [28] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
28: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
29: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.8e+07, inflight [30] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
30: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 5.1e+03, inflight [31] | |
31: M0 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 0.0e+00, inflight [0] | |
32: M25 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
33: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 5.1e+03, inflight [31] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
34: M26 P[153] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 3.1e+04, inflight [26] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
35: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.8e+07, inflight [30] | |
36: M27 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
37: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 28: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
38: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 6.6e+06, inflight [28] | |
39: M1 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 0.0e+00, inflight [1] | |
40: M23 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
41: M24 P[151, 152] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 6.6e+06, inflight [24] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
42: M9 P[5, 6] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 5.1e+03, inflight [9] | |
-gather param for module 22: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
43: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 21: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
44: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 20: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
45: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 19: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
46: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 18: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
47: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 17: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
48: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 16: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
49: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 15: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
50: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 14: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
51: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 13: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
52: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 12: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
53: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 11: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
54: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.9e+07, inflight [11] | |
55: M2 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 0.0e+00, inflight [2] | |
56: M7 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 0.0e+00, inflight [7] | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
57: M6 P[3, 4] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 5.1e+03, inflight [6] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
58: M5 P[2] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 5.1e+03, inflight [5] | |
-gather param for module 4: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
59: M4 P[1] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 3: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
60: M3 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 2.3e+02, n_inflight 7.8e+07, inflight [3] | |
-release param: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
[2021-07-06 19:29:58,266] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward_microstep: 434.13 | backward_microstep: 806.31 | backward_inner_microstep: 747.69 | backward_allreduce_microstep: 58.58 | step_microstep: 0.04 | |
0%| | 5/152613 [00:07<52:38:56, 1.24s/it][2021-07-06 19:29:58,267] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward: 434.10 | backward: 806.29 | backward_inner: 747.65 | backward_allreduce: 58.56 | step: 0.03 | |
0%| | 5/152966 [00:07<52:45:57, 1.24s/it] | |
0%| | 5/152794 [00:07<52:42:32, 1.24s/it] | |
0%| | 5/152942 [00:07<52:45:33, 1.24s/it]0: M0 P[] avail 4.6e+05, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 0.0e+00, inflight [0] | |
-gather param for module 3: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
1: M1 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.8e+07, inflight [1, 3, 2] | |
2: M2 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.8e+07, inflight [2, 3] | |
3: M3 P[0] avail 7.9e+07, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.8e+07, inflight [3] | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
4: M4 P[1] avail 8.0e+07, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
5: M5 P[2] avail 1.6e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [8, 5, 6, 7, 11] | |
6: M6 P[3, 4] avail 1.6e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [8, 7, 11, 6] | |
7: M7 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [8, 11, 7] | |
8: M8 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [8, 11] | |
9: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.6e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [11] | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
10: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 2.4e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
11: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 3.2e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 14: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
12: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 3.9e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 15: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
13: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 4.7e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 16: {'id': 67, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
14: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 5.5e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 17: {'id': 79, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
15: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 6.3e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 18: {'id': 91, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
16: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 7.1e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 19: {'id': 103, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
17: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 7.9e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 20: {'id': 115, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
18: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 8.7e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 21: {'id': 127, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
19: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 9.4e+08, max_avail 5.0e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 22: {'id': 139, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
20: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -2.4e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
21: M9 P[5, 6] avail 1.0e+09, max_avail -2.4e+07, queue_sz 3.0e+02, n_inflight 5.1e+03, inflight [9] | |
22: M23 P[] avail 1.0e+09, max_avail -2.4e+07, queue_sz 3.0e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
23: M24 P[151, 152] avail 1.0e+09, max_avail -3.0e+07, queue_sz 3.0e+02, n_inflight 6.6e+06, inflight [24] | |
24: M25 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 3.0e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
25: M26 P[153] avail 1.0e+09, max_avail -3.0e+07, queue_sz 3.0e+02, n_inflight 3.1e+04, inflight [26] | |
26: M27 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 3.0e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 28: {'id': 154, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
27: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 6.6e+06, inflight [28] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
28: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
29: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.8e+07, inflight [30] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
30: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 5.1e+03, inflight [31] | |
31: M0 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 0.0e+00, inflight [0] | |
32: M25 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
33: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 5.1e+03, inflight [31] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
34: M26 P[153] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 3.1e+04, inflight [26] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
35: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.8e+07, inflight [30] | |
36: M27 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
37: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 28: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
38: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 6.6e+06, inflight [28] | |
39: M1 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 0.0e+00, inflight [1] | |
40: M23 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
41: M24 P[151, 152] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 6.6e+06, inflight [24] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
42: M9 P[5, 6] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 5.1e+03, inflight [9] | |
-gather param for module 22: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
43: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 21: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
44: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 20: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
45: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 19: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
46: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 18: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
47: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 17: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
48: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 16: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
49: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 15: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
50: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 14: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
51: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 13: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
52: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 12: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
53: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 11: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
54: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.9e+07, inflight [11] | |
55: M2 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 0.0e+00, inflight [2] | |
56: M7 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 0.0e+00, inflight [7] | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
57: M6 P[3, 4] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 5.1e+03, inflight [6] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
58: M5 P[2] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 5.1e+03, inflight [5] | |
-gather param for module 4: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
59: M4 P[1] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 3: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
60: M3 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.0e+02, n_inflight 7.8e+07, inflight [3] | |
-release param: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
[2021-07-06 19:30:02,716] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward_microstep: 434.58 | backward_microstep: 4013.80 | backward_inner_microstep: 2298.36 | backward_allreduce_microstep: 1715.39 | step_microstep: 0.04 | |
[2021-07-06 19:30:02,717] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward: 434.55 | backward: 4013.78 | backward_inner: 2298.32 | backward_allreduce: 1715.37 | step: 0.03 | |
0%| | 6/152794 [00:11<188:51:11, 4.45s/it] | |
0%| | 6/152613 [00:11<188:38:13, 4.45s/it] | |
0%| | 6/152942 [00:11<189:02:22, 4.45s/it] | |
0%| | 6/152966 [00:11<189:04:27, 4.45s/it]0: M0 P[] avail 4.6e+05, max_avail 5.0e+07, queue_sz 3.7e+02, n_inflight 0.0e+00, inflight [0] | |
-gather param for module 3: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
1: M1 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.8e+07, inflight [1, 3, 2] | |
2: M2 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.8e+07, inflight [2, 3] | |
3: M3 P[0] avail 7.9e+07, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.8e+07, inflight [3] | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
4: M4 P[1] avail 8.0e+07, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
5: M5 P[2] avail 1.6e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [8, 5, 6, 7, 11] | |
6: M6 P[3, 4] avail 1.6e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [8, 7, 11, 6] | |
7: M7 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [8, 11, 7] | |
8: M8 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [8, 11] | |
9: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.6e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [11] | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
10: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 2.4e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
11: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 3.2e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 14: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
12: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 3.9e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 15: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
13: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 4.7e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 16: {'id': 67, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
14: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 5.5e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 17: {'id': 79, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
15: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 6.3e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 18: {'id': 91, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
16: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 7.1e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 19: {'id': 103, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
17: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 7.9e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 20: {'id': 115, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
18: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 8.7e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 21: {'id': 127, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
19: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 9.4e+08, max_avail 5.0e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 22: {'id': 139, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
20: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -2.4e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
21: M9 P[5, 6] avail 1.0e+09, max_avail -2.4e+07, queue_sz 3.6e+02, n_inflight 5.1e+03, inflight [9] | |
22: M23 P[] avail 1.0e+09, max_avail -2.4e+07, queue_sz 3.6e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
23: M24 P[151, 152] avail 1.0e+09, max_avail -3.0e+07, queue_sz 3.6e+02, n_inflight 6.6e+06, inflight [24] | |
24: M25 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 3.6e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
25: M26 P[153] avail 1.0e+09, max_avail -3.0e+07, queue_sz 3.6e+02, n_inflight 3.1e+04, inflight [26] | |
26: M27 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 3.6e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 28: {'id': 154, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
27: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 6.6e+06, inflight [28] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
28: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
29: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.8e+07, inflight [30] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
30: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 5.1e+03, inflight [31] | |
31: M0 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 0.0e+00, inflight [0] | |
32: M25 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
33: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 5.1e+03, inflight [31] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
34: M26 P[153] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 3.1e+04, inflight [26] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
35: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.8e+07, inflight [30] | |
36: M27 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
37: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 28: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
38: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 6.6e+06, inflight [28] | |
39: M1 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 0.0e+00, inflight [1] | |
40: M23 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
41: M24 P[151, 152] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 6.6e+06, inflight [24] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
42: M9 P[5, 6] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 5.1e+03, inflight [9] | |
-gather param for module 22: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
43: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 21: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
44: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 20: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
45: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 19: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
46: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 18: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
47: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 17: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
48: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 16: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
49: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 15: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
50: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 14: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
51: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 13: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
52: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 12: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
53: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 11: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
54: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.9e+07, inflight [11] | |
55: M2 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 0.0e+00, inflight [2] | |
56: M7 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 0.0e+00, inflight [7] | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
57: M6 P[3, 4] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 5.1e+03, inflight [6] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
58: M5 P[2] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 5.1e+03, inflight [5] | |
-gather param for module 4: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
59: M4 P[1] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 3: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
60: M3 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 3.6e+02, n_inflight 7.8e+07, inflight [3] | |
-release param: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
[2021-07-06 19:30:03,961] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward_microstep: 434.23 | backward_microstep: 809.21 | backward_inner_microstep: 751.33 | backward_allreduce_microstep: 57.84 | step_microstep: 0.04 | |
0%| | 7/152966 [00:12<52:52:42, 1.24s/it] [2021-07-06 19:30:03,961] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward: 434.20 | backward: 809.20 | backward_inner: 751.30 | backward_allreduce: 57.82 | step: 0.03 | |
0%| | 7/152794 [00:12<52:49:51, 1.24s/it] | |
0%| | 7/152613 [00:12<52:46:02, 1.24s/it] | |
0%| | 7/152942 [00:12<52:52:42, 1.24s/it] 0: M0 P[] avail 4.6e+05, max_avail 5.0e+07, queue_sz 4.3e+02, n_inflight 0.0e+00, inflight [0] | |
-gather param for module 3: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
1: M1 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.8e+07, inflight [1, 3, 2] | |
2: M2 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.8e+07, inflight [2, 3] | |
3: M3 P[0] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.8e+07, inflight [3] | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
4: M4 P[1] avail 8.0e+07, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
5: M5 P[2] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [8, 5, 6, 7, 11] | |
6: M6 P[3, 4] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [8, 7, 11, 6] | |
7: M7 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [8, 11, 7] | |
8: M8 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [8, 11] | |
9: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [11] | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
10: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 2.4e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
11: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 3.2e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 14: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
12: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 3.9e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 15: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
13: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 4.7e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 16: {'id': 67, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
14: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 5.5e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 17: {'id': 79, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
15: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 6.3e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 18: {'id': 91, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
16: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 7.1e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 19: {'id': 103, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
17: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 7.9e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 20: {'id': 115, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
18: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 8.7e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 21: {'id': 127, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
19: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 9.4e+08, max_avail 5.0e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 22: {'id': 139, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
20: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -2.4e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
21: M9 P[5, 6] avail 1.0e+09, max_avail -2.4e+07, queue_sz 4.2e+02, n_inflight 5.1e+03, inflight [9] | |
22: M23 P[] avail 1.0e+09, max_avail -2.4e+07, queue_sz 4.2e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
23: M24 P[151, 152] avail 1.0e+09, max_avail -3.0e+07, queue_sz 4.2e+02, n_inflight 6.6e+06, inflight [24] | |
24: M25 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 4.2e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
25: M26 P[153] avail 1.0e+09, max_avail -3.0e+07, queue_sz 4.2e+02, n_inflight 3.1e+04, inflight [26] | |
26: M27 P[] avail 1.0e+09, max_avail -3.0e+07, queue_sz 4.2e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 28: {'id': 154, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
27: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 6.6e+06, inflight [28] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
28: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
29: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.8e+07, inflight [30] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
30: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 5.1e+03, inflight [31] | |
31: M0 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 0.0e+00, inflight [0] | |
32: M25 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 0.0e+00, inflight [25] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
33: M31 P[158, 159] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 5.1e+03, inflight [31] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
34: M26 P[153] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 3.1e+04, inflight [26] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
35: M30 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.8e+07, inflight [30] | |
36: M27 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 0.0e+00, inflight [27] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
37: M29 P[156, 157] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 5.1e+03, inflight [29] | |
-gather param for module 28: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
38: M28 P[154, 155] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 6.6e+06, inflight [28] | |
39: M1 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 0.0e+00, inflight [1] | |
40: M23 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 0.0e+00, inflight [23] | |
-gather param for module 24: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
41: M24 P[151, 152] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 6.6e+06, inflight [24] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
42: M9 P[5, 6] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 5.1e+03, inflight [9] | |
-gather param for module 22: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
43: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 21: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
44: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 20: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
45: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 19: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
46: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 18: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
47: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 17: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
48: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 16: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
49: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [16] | |
-gather param for module 15: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
50: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [15] | |
-gather param for module 14: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
51: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [14] | |
-gather param for module 13: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
52: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [13] | |
-gather param for module 12: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
53: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 11: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
54: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.9e+07, inflight [11] | |
55: M2 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 0.0e+00, inflight [2] | |
56: M7 P[] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 0.0e+00, inflight [7] | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
57: M6 P[3, 4] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 5.1e+03, inflight [6] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
58: M5 P[2] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 5.1e+03, inflight [5] | |
-gather param for module 4: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
59: M4 P[1] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 3: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
60: M3 P[0] avail 1.0e+09, max_avail -3.7e+07, queue_sz 4.2e+02, n_inflight 7.8e+07, inflight [3] | |
-release param: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
module trace: [0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 9, 23, 24, 25, 26, 27, 28, 29, 30, 31, 0, 25, 31, 26, 30, 27, 29, 28, 1, 23, 24, 9, 22, 21, 20, 19, 18, 17, 16, 15, 14, 13, 12, 11, 2, 7, 6, 5, 4, 3, 0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 9, 23, 24, 25, 26, 27, 28, 29, 30, 31, 0, 25, 31, 26, 30, 27, 29, 28, 1, 23, 24, 9, 22, 21, 20, 19, 18, 17, 16, 15, 14, 13, 12, 11, 2, 7, 6, 5, 4, 3, 0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 9, 23, 24, 25, 26, 27, 28, 29, 30, 31, 0, 25, 31, 26, 30, 27, 29, 28, 1, 23, 24, 9, 22, 21, 20, 19, 18, 17, 16, 15, 14, 13, 12, 11, 2, 7, 6, 5, 4, 3, 0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 9, 23, 24, 25, 26, 27, 28, 29, 30, 31, 0, 25, 31, 26, 30, 27, 29, 28, 1, 23, 24, 9, 22, 21, 20, 19, 18, 17, 16, 15, 14, 13, 12, 11, 2, 7, 6, 5, 4, 3, 0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 9, 23, 24, 25, 26, 27, 28, 29, 30, 31, 0, 25, 31, 26, 30, 27, 29, 28, 1, 23, 24, 9, 22, 21, 20, 19, 18, 17, 16, 15, 14, 13, 12, 11, 2, 7, 6, 5, 4, 3, 0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 9, 23, 24, 25, 26, 27, 28, 29, 30, 31, 0, 25, 31, 26, 30, 27, 29, 28, 1, 23, 24, 9, 22, 21, 20, 19, 18, 17, 16, 15, 14, 13, 12, 11, 2, 7, 6, 5, 4, 3, 0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 9, 23, 24, 25, 26, 27, 28, 29, 30, 31, 0, 25, 31, 26, 30, 27, 29, 28, 1, 23, 24, 9, 22, 21, 20, 19, 18, 17, 16, 15, 14, 13, 12, 11, 2, 7, 6, 5, 4, 3, 0, 1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 9, 23, 24, 25, 26, 27, 28, 29, 30, 31, 0, 25, 31, 26, 30, 27, 29, 28, 1, 23, 24, 9, 22, 21, 20, 19, 18, 17, 16, 15, 14, 13, 12, 11, 2, 7, 6, 5, 4, 3] | |
[2021-07-06 19:30:05,208] [INFO] [stage3.py:2566:_overflow_clean_up] [deepscale] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 1048576, reducing to 1048576 | |
0%| | 8/152613 [00:14<52:52:39, 1.25s/it] | |
0%| | 8/152794 [00:13<52:56:32, 1.25s/it] | |
0%| | 8/152966 [00:14<53:00:22, 1.25s/it][2021-07-06 19:30:05,209] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward_microstep: 434.28 | backward_microstep: 808.74 | backward_inner_microstep: 750.87 | backward_allreduce_microstep: 57.82 | step_microstep: 2.96 | |
[2021-07-06 19:30:05,209] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward: 434.25 | backward: 808.72 | backward_inner: 750.85 | backward_allreduce: 57.80 | step: 2.94 | |
0%| | 8/152942 [00:14<52:59:49, 1.25s/it]0: M0 P[] avail 4.6e+05, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 0.0e+00, inflight [0] | |
-gather param for module 3: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
1: M1 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.8e+07, inflight [1, 3, 2] | |
2: M2 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.8e+07, inflight [2, 3] | |
3: M3 P[0] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.8e+07, inflight [3] | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
4: M4 P[1] avail 8.0e+07, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.3e+06, inflight [4] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-release param: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': set()} | |
5: M5 P[2] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [8, 5, 6, 7, 11] | |
6: M6 P[3, 4] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [8, 7, 11, 6] | |
7: M7 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [8, 11, 7] | |
8: M8 P[] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [8, 11] | |
9: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [11] | |
-release param: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
10: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12] | |
-release param: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
11: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [13] | |
-release param: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 14: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
12: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [14] | |
-release param: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 15: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
13: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [15] | |
-release param: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 16: {'id': 67, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
14: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [16] | |
-release param: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 17: {'id': 79, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
15: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [17] | |
-gather param for module 18: {'id': 91, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
16: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 2.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [18] | |
-gather param for module 19: {'id': 103, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
17: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 3.1e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [19] | |
-gather param for module 20: {'id': 115, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
18: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 3.9e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [20] | |
-gather param for module 21: {'id': 127, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
19: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 4.7e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [21] | |
-gather param for module 22: {'id': 139, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
20: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 5.5e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [22] | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
21: M9 P[5, 6] avail 5.5e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 5.1e+03, inflight [9] | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
22: M23 P[] avail 6.3e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 23] | |
-gather param for module 24: {'id': 151, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
23: M24 P[151, 152] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 8.5e+07, inflight [12, 24] | |
24: M25 P[] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 25] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
25: M26 P[153] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 26] | |
26: M27 P[] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 27] | |
-gather param for module 28: {'id': 154, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
27: M28 P[154, 155] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 8.5e+07, inflight [12, 28] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
28: M29 P[156, 157] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [29, 12] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
29: M30 P[0] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [12, 30] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
30: M31 P[158, 159] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 31] | |
31: M0 P[] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [0, 12] | |
32: M25 P[] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 25] | |
-gather param for module 31: {'id': 158, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {31}} | |
-gather param for module 31: {'id': 159, 'status': 'AVAILABLE', 'numel': 2, 'persist': True, 'active_sub_modules': {31}} | |
33: M31 P[158, 159] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 31] | |
-gather param for module 26: {'id': 153, 'status': 'AVAILABLE', 'numel': 30528, 'persist': True, 'active_sub_modules': {26}} | |
34: M26 P[153] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 26] | |
-gather param for module 30: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
35: M30 P[0] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [12, 30] | |
36: M27 P[] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 27] | |
-gather param for module 29: {'id': 156, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
-gather param for module 29: {'id': 157, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {29}} | |
37: M29 P[156, 157] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [29, 12] | |
-gather param for module 28: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {28}} | |
-gather param for module 28: {'id': 155, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {28}} | |
38: M28 P[154, 155] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 8.5e+07, inflight [12, 28] | |
-release param: {'id': 154, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
39: M1 P[] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 1] | |
40: M23 P[] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 23] | |
-gather param for module 24: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {24}} | |
-gather param for module 24: {'id': 152, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {24}} | |
41: M24 P[151, 152] avail 6.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 8.5e+07, inflight [12, 24] | |
-release param: {'id': 151, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 9: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
-gather param for module 9: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {9}} | |
42: M9 P[5, 6] avail 6.3e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12, 9] | |
-gather param for module 22: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 140, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 142, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 143, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 144, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 146, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 148, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 149, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
-gather param for module 22: {'id': 150, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {22}} | |
43: M22 P[139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150] avail 6.3e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [12, 22] | |
-release param: {'id': 139, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 141, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 145, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 147, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 21: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 128, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 130, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 131, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 132, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 134, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 136, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 137, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
-gather param for module 21: {'id': 138, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {21}} | |
44: M21 P[127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138] avail 5.5e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [12, 21] | |
-release param: {'id': 127, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 129, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 133, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 135, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 20: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 116, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 118, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 119, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 120, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 122, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 124, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 125, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
-gather param for module 20: {'id': 126, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {20}} | |
45: M20 P[115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126] avail 4.7e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [12, 20] | |
-release param: {'id': 115, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 117, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 121, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 123, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 19: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 104, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 106, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 107, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 108, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 110, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 112, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 113, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
-gather param for module 19: {'id': 114, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {19}} | |
46: M19 P[103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114] avail 3.9e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [12, 19] | |
-release param: {'id': 103, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 105, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 109, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 111, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 18: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 92, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 94, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 95, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 96, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 98, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 100, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 101, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
-gather param for module 18: {'id': 102, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {18}} | |
47: M18 P[91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102] avail 3.1e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [12, 18] | |
-release param: {'id': 91, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 93, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 97, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 99, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 17: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 80, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 82, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 83, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 84, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 86, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 88, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 89, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
-gather param for module 17: {'id': 90, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {17}} | |
48: M17 P[79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90] avail 2.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [12, 17] | |
-release param: {'id': 79, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 81, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 85, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 87, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 16: {'id': 67, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 68, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 69, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 70, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 71, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 72, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 73, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 74, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 75, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 76, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 77, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
-gather param for module 16: {'id': 78, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {16}} | |
49: M16 P[67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78] avail 2.4e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [16, 12] | |
-gather param for module 15: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 56, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 58, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 62, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 64, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 65, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
-gather param for module 15: {'id': 66, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {15}} | |
50: M15 P[55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66] avail 3.1e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [12, 15] | |
-gather param for module 14: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
-gather param for module 14: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {14}} | |
51: M14 P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] avail 3.9e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [12, 14] | |
-gather param for module 13: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
52: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 4.7e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [13, 12] | |
53: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 4.7e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [12] | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
54: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 5.5e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [11] | |
55: M2 P[] avail 5.5e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 0.0e+00, inflight [2] | |
-gather param for module 13: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
-gather param for module 13: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {13}} | |
56: M7 P[] avail 5.5e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [13, 7] | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
57: M6 P[3, 4] avail 5.5e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [13, 6] | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
58: M5 P[2] avail 5.5e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 7.9e+07, inflight [13, 5] | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
59: M4 P[1] avail 5.5e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 8.0e+07, inflight [13, 4] | |
-gather param for module 3: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3, 30}} | |
60: M3 P[0] avail 5.5e+08, max_avail 5.0e+07, queue_sz 4.8e+02, n_inflight 1.6e+08, inflight [13, 3] | |
-release param: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 55, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 57, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 61, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 63, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 67, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 69, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 73, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 75, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
[2021-07-06 19:30:06,626] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward_microstep: 476.46 | backward_microstep: 939.61 | backward_inner_microstep: 881.54 | backward_allreduce_microstep: 58.02 | step_microstep: 0.04 | |
[2021-07-06 19:30:06,626] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward: 476.44 | backward: 939.59 | backward_inner: 881.52 | backward_allreduce: 58.00 | step: 0.02 | |
0%| | 9/152966 [00:15<60:13:11, 1.42s/it] | |
0%| | 9/152613 [00:15<60:05:02, 1.42s/it] | |
0%| | 9/152794 [00:15<60:09:21, 1.42s/it] | |
0%| | 9/152942 [00:15<60:12:26, 1.42s/it]0: M0 P[] avail 4.6e+05, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 7.9e+07, inflight [0, 13] | |
1: M1 P[] avail 4.6e+05, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 7.9e+07, inflight [13, 1] | |
2: M2 P[] avail 4.6e+05, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 7.9e+07, inflight [13, 2] | |
-gather param for module 3: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 78151680, 'persist': False, 'active_sub_modules': {3}} | |
3: M3 P[0] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 1.6e+08, inflight [13, 3] | |
-gather param for module 4: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': {4}} | |
4: M4 P[1] avail 8.0e+07, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 8.0e+07, inflight [13, 4] | |
-release param: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 5: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'persist': True, 'active_sub_modules': {5}} | |
5: M5 P[2] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 7.9e+07, inflight [13, 5] | |
-gather param for module 6: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
-gather param for module 6: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {6}} | |
6: M6 P[3, 4] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 7.9e+07, inflight [13, 6] | |
7: M7 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 7.9e+07, inflight [13, 7] | |
8: M8 P[] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 7.9e+07, inflight [8, 13] | |
-gather param for module 11: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
-gather param for module 11: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {11}} | |
9: M11 P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 1.6e+08, inflight [13, 11] | |
-release param: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-gather param for module 12: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
-gather param for module 12: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'persist': True, 'active_sub_modules': {12}} | |
10: M12 P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] avail 1.6e+08, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 1.6e+08, inflight [13, 12] | |
-release param: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
-release param: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'persist': False, 'active_sub_modules': set()} | |
11: M13 P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] avail 7.9e+07, max_avail 5.0e+07, queue_sz 4.9e+02, n_inflight 7.9e+07, inflight [13] | |
0%| | 9/152966 [00:15<73:46:52, 1.74s/it] | |
Traceback (most recent call last): | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 607, in <module> | |
main() | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 600, in main | |
run(args, model, optimizer, start_epoch) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 566, in run | |
train(args, index, model, optimizer, pretrain_dataset_provider) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 169, in train | |
loss = model.network(batch) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
result = self.forward(*input, **kwargs) | |
0%| | 9/152942 [00:15<73:57:54, 1.74s/it] File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/engine.py", line 1104, in forward | |
0%| | 9/152794 [00:15<73:25:43, 1.73s/it] | |
loss = self.module(*inputs, **kwargs) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 1136, in forward | |
Traceback (most recent call last): | |
Traceback (most recent call last): | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 607, in <module> | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 607, in <module> | |
checkpoint_activations=checkpoint_activations)main() | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
main() File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 600, in main | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 600, in main | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 1051, in forward | |
run(args, model, optimizer, start_epoch) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 566, in run | |
run(args, model, optimizer, start_epoch) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 566, in run | |
train(args, index, model, optimizer, pretrain_dataset_provider) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 169, in train | |
train(args, index, model, optimizer, pretrain_dataset_provider) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 169, in train | |
loss = model.network(batch) | |
checkpoint_activations=checkpoint_activations) File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
loss = model.network(batch) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
0%| | 9/152613 [00:15<73:40:32, 1.74s/it] | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 648, in forward | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/engine.py", line 1104, in forward | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/engine.py", line 1104, in forward | |
hidden_states = layer_module(hidden_states, attention_mask) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 748, in _call_impl | |
loss = self.module(*inputs, **kwargs) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
hook_result = hook(self, input, result) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 1332, in _post_forward_module_hook | |
loss = self.module(*inputs, **kwargs) | |
Traceback (most recent call last): | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 607, in <module> | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 1136, in forward | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 1136, in forward | |
main() | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 600, in main | |
self.post_sub_module_forward_function(module) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 1414, in post_sub_module_forward_function | |
checkpoint_activations=checkpoint_activations) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
run(args, model, optimizer, start_epoch) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 566, in run | |
checkpoint_activations=checkpoint_activations) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 1051, in forward | |
train(args, index, model, optimizer, pretrain_dataset_provider) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py", line 169, in train | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 1051, in forward | |
loss = model.network(batch) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
self.param_coordinator.release_sub_module(sub_module) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 330, in release_sub_module | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
checkpoint_activations=checkpoint_activations) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
param.ds_active_sub_modules.remove(submodule.id)return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/engine.py", line 1104, in forward | |
KeyError: 13 | |
checkpoint_activations=checkpoint_activations) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 648, in forward | |
result = self.forward(*input, **kwargs)loss = self.module(*inputs, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 648, in forward | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
hidden_states = layer_module(hidden_states, attention_mask) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 748, in _call_impl | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 1136, in forward | |
hidden_states = layer_module(hidden_states, attention_mask) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 748, in _call_impl | |
hook_result = hook(self, input, result) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 1332, in _post_forward_module_hook | |
hook_result = hook(self, input, result) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 1332, in _post_forward_module_hook | |
checkpoint_activations=checkpoint_activations) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
self.post_sub_module_forward_function(module) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 1051, in forward | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 1414, in post_sub_module_forward_function | |
self.post_sub_module_forward_function(module) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 1414, in post_sub_module_forward_function | |
checkpoint_activations=checkpoint_activations) | |
File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 744, in _call_impl | |
self.param_coordinator.release_sub_module(sub_module) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 330, in release_sub_module | |
result = self.forward(*input, **kwargs) | |
File "/home/ec2-user/DeepSpeedExamples/bing_bert/nvidia/modelingpreln.py", line 648, in forward | |
self.param_coordinator.release_sub_module(sub_module) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 330, in release_sub_module | |
param.ds_active_sub_modules.remove(submodule.id) | |
KeyError: 13 | |
param.ds_active_sub_modules.remove(submodule.id) | |
hidden_states = layer_module(hidden_states, attention_mask)KeyError | |
: File "/usr/local/lib64/python3.7/site-packages/torch/nn/modules/module.py", line 748, in _call_impl | |
13 | |
hook_result = hook(self, input, result) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 1332, in _post_forward_module_hook | |
self.post_sub_module_forward_function(module) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 1414, in post_sub_module_forward_function | |
self.param_coordinator.release_sub_module(sub_module) | |
File "/home/ec2-user/DeepSpeed/deepspeed/utils/nvtx.py", line 9, in wrapped_fn | |
return func(*args, **kwargs) | |
File "/home/ec2-user/DeepSpeed/deepspeed/runtime/zero/stage3.py", line 330, in release_sub_module | |
param.ds_active_sub_modules.remove(submodule.id) | |
KeyError: 13 | |
Killing subprocess 21642 | |
Killing subprocess 21643 | |
Killing subprocess 21644 | |
Killing subprocess 21645 | |
Traceback (most recent call last): | |
File "/usr/lib64/python3.7/runpy.py", line 193, in _run_module_as_main | |
"__main__", mod_spec) | |
File "/usr/lib64/python3.7/runpy.py", line 85, in _run_code | |
exec(code, run_globals) | |
File "/home/ec2-user/DeepSpeed/deepspeed/launcher/launch.py", line 171, in <module> | |
main() | |
File "/home/ec2-user/DeepSpeed/deepspeed/launcher/launch.py", line 161, in main | |
sigkill_handler(signal.SIGTERM, None) # not coming back | |
File "/home/ec2-user/DeepSpeed/deepspeed/launcher/launch.py", line 139, in sigkill_handler | |
raise subprocess.CalledProcessError(returncode=last_return_code, cmd=cmd) | |
subprocess.CalledProcessError: Command '['/bin/python3', '-u', '/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py', '--local_rank=3', '--max_seq_length', '512', '--print_steps', '10', '--deepspeed', '--data_path_prefix', '/home/ec2-user/bert-data-nv', '--use_nvidia_dataset', '--rewarmup', '--lr_schedule', 'EE', '--attention_dropout_checkpoint', '--lr_offset', '0.0', '--gelu_checkpoint', '--deepspeed_transformer_kernel', '--max_steps', '5', '--ckpt_to_save', '200', '--output_dir', '/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-06_19:29:22/', '--cf', '/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', '--deepspeed_config', '/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', '--job_name', 'zero3_1node_profile_2021-07-06_19:29:22']' returned non-zero exit status 1. |
This file has been truncated, but you can view the full file.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[2021-07-27 19:28:28,518] [WARNING] [runner.py:122:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only. | |
[2021-07-27 19:28:28,632] [INFO] [runner.py:360:main] cmd = /bin/python3 -u -m deepspeed.launcher.launch --world_info=eyJsb2NhbGhvc3QiOiBbMCwgMSwgMiwgM119 --master_addr=127.0.0.1 --master_port=29500 /home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../../deepspeed_train.py --max_seq_length 512 --print_steps 10 --deepspeed --data_path_prefix /home/ec2-user/bert-data-nv --use_nvidia_dataset --rewarmup --lr_schedule EE --attention_dropout_checkpoint --lr_offset 0.0 --gelu_checkpoint --deepspeed_transformer_kernel --max_steps 5 --ckpt_to_save 200 --output_dir /home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-27_19:28:27/ --cf /home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json --deepspeed_config /home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json --job_name zero3_1node_profile_2021-07-27_19:28:27 | |
[2021-07-27 19:28:29,456] [INFO] [launch.py:80:main] WORLD INFO DICT: {'localhost': [0, 1, 2, 3]} | |
[2021-07-27 19:28:29,456] [INFO] [launch.py:89:main] nnodes=1, num_local_procs=4, node_rank=0 | |
[2021-07-27 19:28:29,456] [INFO] [launch.py:101:main] global_rank_mapping=defaultdict(<class 'list'>, {'localhost': [0, 1, 2, 3]}) | |
[2021-07-27 19:28:29,456] [INFO] [launch.py:102:main] dist_world_size=4 | |
[2021-07-27 19:28:29,456] [INFO] [launch.py:105:main] Setting CUDA_VISIBLE_DEVICES=0,1,2,3 | |
Running Config File: zero3_1node_profile_2021-07-27_19:28:27 | |
Args = Namespace(attention_dropout_checkpoint=True, ckpt_to_save=[200], config={'train_batch_size': 64, 'train_micro_batch_size_per_gpu': 2, 'steps_per_print': 100, 'prescale_gradients': False, 'bert_token_file': 'bert-large-uncased', 'bert_model_config': {'vocab_size_or_config_json_file': 32003, 'hidden_size': 2560, 'num_hidden_layers': 4, 'num_attention_heads': 40, 'intermediate_size': 10240, 'hidden_act': 'gelu', 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'initializer_range': 0.02}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'reduce_scatter': False, 'contiguous_gradients': False}, 'zero_allow_untested_optimizer': True, 'optimizer': {'type': 'Adam', 'params': {'lr': 0.0001, 'weight_decay': 0.01, 'bias_correction': True, 'eps': 1e-06}}, 'gradient_clipping': 1.0, 'wall_clock_breakdown': True, 'fp16': {'enabled': True, 'loss_scale': 0, 'initial_scale_power': 20, 'loss_scale_window': 1000}, 'data': {'flags': {'pretrain_dataset': True, 'pretrain_type': 'wiki_bc'}, 'datasets': {'pretrain_dataset': '512/wikicorpus_en'}}, 'training': {'num_epochs': 20, 'warmup_proportion': 0.02, 'learning_rate': 0.002, 'num_workers': 4, 'async_worker': True, 'decay_rate': 0.9, 'decay_step': 150, 'total_training_steps': 15000}}, config_file='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', data_path_prefix='/home/ec2-user/bert-data-nv', deepscale=False, deepscale_config=None, deepspeed=True, deepspeed_config='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', deepspeed_mpi=False, deepspeed_sparse_attention=False, deepspeed_transformer_kernel=True, do_lower_case=True, finetune=False, gelu_checkpoint=True, job_name='zero3_1node_profile_2021-07-27_19:28:27', load_checkpoint_id=None, load_training_checkpoint=None, local_rank=1, logger=<turing.logger.Logger object at 0x7f380a2fbe50>, lr_offset=0.0, lr_schedule='EE', max_predictions_per_seq=80, max_seq_length=512, max_steps=5, max_steps_per_epoch=9223372036854775807, no_cuda=False, normalize_invertible=False, output_dir='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-27_19:28:27/', print_steps=10, progressive_layer_drop=False, refresh_bucket_size=1, rewarmup=True, seed=42, stochastic_mode=False, use_nvidia_dataset=True, use_pretrain=False, validation_data_path_prefix=None) | |
Running Config File: zero3_1node_profile_2021-07-27_19:28:27 | |
Args = Namespace(attention_dropout_checkpoint=True, ckpt_to_save=[200], config={'train_batch_size': 64, 'train_micro_batch_size_per_gpu': 2, 'steps_per_print': 100, 'prescale_gradients': False, 'bert_token_file': 'bert-large-uncased', 'bert_model_config': {'vocab_size_or_config_json_file': 32003, 'hidden_size': 2560, 'num_hidden_layers': 4, 'num_attention_heads': 40, 'intermediate_size': 10240, 'hidden_act': 'gelu', 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'initializer_range': 0.02}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'reduce_scatter': False, 'contiguous_gradients': False}, 'zero_allow_untested_optimizer': True, 'optimizer': {'type': 'Adam', 'params': {'lr': 0.0001, 'weight_decay': 0.01, 'bias_correction': True, 'eps': 1e-06}}, 'gradient_clipping': 1.0, 'wall_clock_breakdown': True, 'fp16': {'enabled': True, 'loss_scale': 0, 'initial_scale_power': 20, 'loss_scale_window': 1000}, 'data': {'flags': {'pretrain_dataset': True, 'pretrain_type': 'wiki_bc'}, 'datasets': {'pretrain_dataset': '512/wikicorpus_en'}}, 'training': {'num_epochs': 20, 'warmup_proportion': 0.02, 'learning_rate': 0.002, 'num_workers': 4, 'async_worker': True, 'decay_rate': 0.9, 'decay_step': 150, 'total_training_steps': 15000}}, config_file='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', data_path_prefix='/home/ec2-user/bert-data-nv', deepscale=False, deepscale_config=None, deepspeed=True, deepspeed_config='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', deepspeed_mpi=False, deepspeed_sparse_attention=False, deepspeed_transformer_kernel=True, do_lower_case=True, finetune=False, gelu_checkpoint=True, job_name='zero3_1node_profile_2021-07-27_19:28:27', load_checkpoint_id=None, load_training_checkpoint=None, local_rank=0, logger=<turing.logger.Logger object at 0x7fee20c7ca50>, lr_offset=0.0, lr_schedule='EE', max_predictions_per_seq=80, max_seq_length=512, max_steps=5, max_steps_per_epoch=9223372036854775807, no_cuda=False, normalize_invertible=False, output_dir='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-27_19:28:27/', print_steps=10, progressive_layer_drop=False, refresh_bucket_size=1, rewarmup=True, seed=42, stochastic_mode=False, use_nvidia_dataset=True, use_pretrain=False, validation_data_path_prefix=None) | |
Running Config File: zero3_1node_profile_2021-07-27_19:28:27 | |
Args = Namespace(attention_dropout_checkpoint=True, ckpt_to_save=[200], config={'train_batch_size': 64, 'train_micro_batch_size_per_gpu': 2, 'steps_per_print': 100, 'prescale_gradients': False, 'bert_token_file': 'bert-large-uncased', 'bert_model_config': {'vocab_size_or_config_json_file': 32003, 'hidden_size': 2560, 'num_hidden_layers': 4, 'num_attention_heads': 40, 'intermediate_size': 10240, 'hidden_act': 'gelu', 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'initializer_range': 0.02}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'reduce_scatter': False, 'contiguous_gradients': False}, 'zero_allow_untested_optimizer': True, 'optimizer': {'type': 'Adam', 'params': {'lr': 0.0001, 'weight_decay': 0.01, 'bias_correction': True, 'eps': 1e-06}}, 'gradient_clipping': 1.0, 'wall_clock_breakdown': True, 'fp16': {'enabled': True, 'loss_scale': 0, 'initial_scale_power': 20, 'loss_scale_window': 1000}, 'data': {'flags': {'pretrain_dataset': True, 'pretrain_type': 'wiki_bc'}, 'datasets': {'pretrain_dataset': '512/wikicorpus_en'}}, 'training': {'num_epochs': 20, 'warmup_proportion': 0.02, 'learning_rate': 0.002, 'num_workers': 4, 'async_worker': True, 'decay_rate': 0.9, 'decay_step': 150, 'total_training_steps': 15000}}, config_file='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', data_path_prefix='/home/ec2-user/bert-data-nv', deepscale=False, deepscale_config=None, deepspeed=True, deepspeed_config='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', deepspeed_mpi=False, deepspeed_sparse_attention=False, deepspeed_transformer_kernel=True, do_lower_case=True, finetune=False, gelu_checkpoint=True, job_name='zero3_1node_profile_2021-07-27_19:28:27', load_checkpoint_id=None, load_training_checkpoint=None, local_rank=2, logger=<turing.logger.Logger object at 0x7f8d1e442e50>, lr_offset=0.0, lr_schedule='EE', max_predictions_per_seq=80, max_seq_length=512, max_steps=5, max_steps_per_epoch=9223372036854775807, no_cuda=False, normalize_invertible=False, output_dir='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-27_19:28:27/', print_steps=10, progressive_layer_drop=False, refresh_bucket_size=1, rewarmup=True, seed=42, stochastic_mode=False, use_nvidia_dataset=True, use_pretrain=False, validation_data_path_prefix=None) | |
Running Config File: zero3_1node_profile_2021-07-27_19:28:27 | |
Args = Namespace(attention_dropout_checkpoint=True, ckpt_to_save=[200], config={'train_batch_size': 64, 'train_micro_batch_size_per_gpu': 2, 'steps_per_print': 100, 'prescale_gradients': False, 'bert_token_file': 'bert-large-uncased', 'bert_model_config': {'vocab_size_or_config_json_file': 32003, 'hidden_size': 2560, 'num_hidden_layers': 4, 'num_attention_heads': 40, 'intermediate_size': 10240, 'hidden_act': 'gelu', 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'initializer_range': 0.02}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'reduce_scatter': False, 'contiguous_gradients': False}, 'zero_allow_untested_optimizer': True, 'optimizer': {'type': 'Adam', 'params': {'lr': 0.0001, 'weight_decay': 0.01, 'bias_correction': True, 'eps': 1e-06}}, 'gradient_clipping': 1.0, 'wall_clock_breakdown': True, 'fp16': {'enabled': True, 'loss_scale': 0, 'initial_scale_power': 20, 'loss_scale_window': 1000}, 'data': {'flags': {'pretrain_dataset': True, 'pretrain_type': 'wiki_bc'}, 'datasets': {'pretrain_dataset': '512/wikicorpus_en'}}, 'training': {'num_epochs': 20, 'warmup_proportion': 0.02, 'learning_rate': 0.002, 'num_workers': 4, 'async_worker': True, 'decay_rate': 0.9, 'decay_step': 150, 'total_training_steps': 15000}}, config_file='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', data_path_prefix='/home/ec2-user/bert-data-nv', deepscale=False, deepscale_config=None, deepspeed=True, deepspeed_config='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../configs/zero3_1node_profile.json', deepspeed_mpi=False, deepspeed_sparse_attention=False, deepspeed_transformer_kernel=True, do_lower_case=True, finetune=False, gelu_checkpoint=True, job_name='zero3_1node_profile_2021-07-27_19:28:27', load_checkpoint_id=None, load_training_checkpoint=None, local_rank=3, logger=<turing.logger.Logger object at 0x7f57231ffe50>, lr_offset=0.0, lr_schedule='EE', max_predictions_per_seq=80, max_seq_length=512, max_steps=5, max_steps_per_epoch=9223372036854775807, no_cuda=False, normalize_invertible=False, output_dir='/home/ec2-user/DeepSpeedExamples/bing_bert/zero_opt_experiments/scripts/../outputs/zero3_1node_profile_2021-07-27_19:28:27/', print_steps=10, progressive_layer_drop=False, refresh_bucket_size=1, rewarmup=True, seed=42, stochastic_mode=False, use_nvidia_dataset=True, use_pretrain=False, validation_data_path_prefix=None) | |
07/27/2021 19:28:30 - INFO - pytorch_pretrained_bert.tokenization - loading vocabulary file https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt from cache at /home/ec2-user/.pytorch_pretrained_bert/9b3c03a36e83b13d5ba95ac965c9f9074a99e14340c523ab405703179e79fc46.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084 | |
07/27/2021 19:28:30 - INFO - pytorch_pretrained_bert.tokenization - loading vocabulary file https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt from cache at /home/ec2-user/.pytorch_pretrained_bert/9b3c03a36e83b13d5ba95ac965c9f9074a99e14340c523ab405703179e79fc46.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084 | |
07/27/2021 19:28:30 - INFO - pytorch_pretrained_bert.tokenization - loading vocabulary file https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt from cache at /home/ec2-user/.pytorch_pretrained_bert/9b3c03a36e83b13d5ba95ac965c9f9074a99e14340c523ab405703179e79fc46.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084 | |
07/27/2021 19:28:30 - INFO - pytorch_pretrained_bert.tokenization - loading vocabulary file https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt from cache at /home/ec2-user/.pytorch_pretrained_bert/9b3c03a36e83b13d5ba95ac965c9f9074a99e14340c523ab405703179e79fc46.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084 | |
07/27/2021 19:28:30 - WARNING - root - Skipping validation because validation_data_path_prefix is unspecified | |
07/27/2021 19:28:30 - WARNING - root - Early training exit is set after 5 global steps | |
[2021-07-27 19:28:30,869] [INFO] [distributed.py:47:init_distributed] Initializing torch distributed with backend: nccl | |
07/27/2021 19:28:30 - WARNING - root - Skipping validation because validation_data_path_prefix is unspecified | |
07/27/2021 19:28:30 - WARNING - root - Early training exit is set after 5 global steps | |
[2021-07-27 19:28:30,883] [INFO] [distributed.py:47:init_distributed] Initializing torch distributed with backend: nccl | |
07/27/2021 19:28:30 - INFO - torch.distributed.distributed_c10d - Added key: store_based_barrier_key:1 to store for rank: 1 | |
07/27/2021 19:28:30 - WARNING - root - Skipping validation because validation_data_path_prefix is unspecified | |
07/27/2021 19:28:30 - WARNING - root - Early training exit is set after 5 global steps | |
[2021-07-27 19:28:30,886] [INFO] [distributed.py:47:init_distributed] Initializing torch distributed with backend: nccl | |
07/27/2021 19:28:30 - INFO - torch.distributed.distributed_c10d - Added key: store_based_barrier_key:1 to store for rank: 3 | |
07/27/2021 19:28:30 - WARNING - root - Skipping validation because validation_data_path_prefix is unspecified | |
07/27/2021 19:28:30 - WARNING - root - Early training exit is set after 5 global steps | |
[2021-07-27 19:28:30,893] [INFO] [distributed.py:47:init_distributed] Initializing torch distributed with backend: nccl | |
07/27/2021 19:28:30 - INFO - torch.distributed.distributed_c10d - Added key: store_based_barrier_key:1 to store for rank: 2 | |
07/27/2021 19:28:30 - INFO - torch.distributed.distributed_c10d - Added key: store_based_barrier_key:1 to store for rank: 0 | |
07/27/2021 19:28:30 - INFO - torch.distributed.distributed_c10d - Rank 0: Completed store-based barrier for key:store_based_barrier_key:1 with 4 nodes. | |
07/27/2021 19:28:30 - INFO - torch.distributed.distributed_c10d - Rank 2: Completed store-based barrier for key:store_based_barrier_key:1 with 4 nodes. | |
07/27/2021 19:28:30 - INFO - torch.distributed.distributed_c10d - Rank 1: Completed store-based barrier for key:store_based_barrier_key:1 with 4 nodes. | |
07/27/2021 19:28:30 - INFO - torch.distributed.distributed_c10d - Rank 3: Completed store-based barrier for key:store_based_barrier_key:1 with 4 nodes. | |
VOCAB SIZE: 30528 | |
VOCAB SIZE: 30528 | |
VOCAB SIZE: 30528 | |
VOCAB SIZE: 30528 | |
DeepSpeed Transformer config is {'layer_id': 0, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 0, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 0, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 0, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Detected CUDA files, patching ldflags | |
Emitting ninja build file /home/ec2-user/.cache/torch_extensions/py37_cu110/transformer/build.ninja... | |
Building extension module transformer... | |
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) | |
ninja: no work to do. | |
Loading extension module transformer... | |
Time to load transformer op: 0.11566448211669922 seconds | |
Loading extension module transformer... | |
Time to load transformer op: 0.20320391654968262 seconds | |
Loading extension module transformer... | |
Loading extension module transformer... | |
Time to load transformer op: 0.20311331748962402 seconds | |
Time to load transformer op: 0.20307397842407227 seconds | |
layer #0 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 1, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #0 is created with date type [half]. | |
layer #0 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 1, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #0 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 1, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 1, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #1 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 2, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #1 is created with date type [half]. | |
layer #1 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 2, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #1 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 2, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 2, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #2 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 3, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 0, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
Accounting for accumulation on the residual path | |
layer #2 is created with date type [half]. | |
layer #2 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 3, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 3, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
DeepSpeed Transformer config is {'layer_id': 3, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 1, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #2 is created with date type [half]. | |
DeepSpeed Transformer config is {'layer_id': 3, 'batch_size': 2, 'hidden_size': 2560, 'intermediate_size': 10240, 'heads': 40, 'attn_dropout_ratio': 0.1, 'hidden_dropout_ratio': 0.1, 'num_hidden_layers': 4, 'initializer_range': 0.02, 'fp16': True, 'pre_layer_norm': True, 'local_rank': 2, 'seed': 42, 'normalize_invertible': False, 'gelu_checkpoint': True, 'adjust_init_range': True, 'test_gemm': False, 'layer_norm_eps': 1e-12, 'training': True, 'is_grad_enabled': True, 'attn_dropout_checkpoint': True, 'stochastic_mode': False, 'huggingface': False} | |
layer #3 is created with date type [half]. | |
layer #3 is created with date type [half]. | |
layer #3 is created with date type [half]. | |
layer #3 is created with date type [half]. | |
07/27/2021 19:28:36 - INFO - nvidia.modelingpreln - Init BERT pretrain model | |
07/27/2021 19:28:36 - INFO - nvidia.modelingpreln - Init BERT pretrain model | |
07/27/2021 19:28:36 - INFO - nvidia.modelingpreln - Init BERT pretrain model | |
07/27/2021 19:28:36 - INFO - nvidia.modelingpreln - Init BERT pretrain model | |
[2021-07-27 19:28:37,711] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.4.4+0d1ac060, git-hash=0d1ac060, git-branch=HEAD | |
[2021-07-27 19:28:39,714] [INFO] [utils.py:13:_initialize_parameter_parallel_groups] data_parallel_size: 4, parameter_parallel_size: 4 | |
07/27/2021 19:28:39 - INFO - torch.distributed.distributed_c10d - Added key: store_based_barrier_key:2 to store for rank: 0 | |
[2021-07-27 19:28:39,874] [INFO] [utils.py:13:_initialize_parameter_parallel_groups] data_parallel_size: 4, parameter_parallel_size: 4 | |
07/27/2021 19:28:39 - INFO - torch.distributed.distributed_c10d - Added key: store_based_barrier_key:2 to store for rank: 3 | |
[2021-07-27 19:28:39,901] [INFO] [utils.py:13:_initialize_parameter_parallel_groups] data_parallel_size: 4, parameter_parallel_size: 4 | |
07/27/2021 19:28:39 - INFO - torch.distributed.distributed_c10d - Added key: store_based_barrier_key:2 to store for rank: 1 | |
[2021-07-27 19:28:39,912] [INFO] [utils.py:13:_initialize_parameter_parallel_groups] data_parallel_size: 4, parameter_parallel_size: 4 | |
07/27/2021 19:28:39 - INFO - torch.distributed.distributed_c10d - Added key: store_based_barrier_key:2 to store for rank: 2 | |
07/27/2021 19:28:39 - INFO - torch.distributed.distributed_c10d - Rank 2: Completed store-based barrier for key:store_based_barrier_key:2 with 4 nodes. | |
07/27/2021 19:28:39 - INFO - torch.distributed.distributed_c10d - Rank 3: Completed store-based barrier for key:store_based_barrier_key:2 with 4 nodes. | |
07/27/2021 19:28:39 - INFO - torch.distributed.distributed_c10d - Rank 0: Completed store-based barrier for key:store_based_barrier_key:2 with 4 nodes. | |
07/27/2021 19:28:39 - INFO - torch.distributed.distributed_c10d - Rank 1: Completed store-based barrier for key:store_based_barrier_key:2 with 4 nodes. | |
[2021-07-27 19:28:40,014] [INFO] [engine.py:180:__init__] DeepSpeed Flops Profiler Enabled: False | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Detected CUDA files, patching ldflags | |
Emitting ninja build file /home/ec2-user/.cache/torch_extensions/py37_cu110/fused_adam/build.ninja... | |
Building extension module fused_adam... | |
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) | |
ninja: no work to do. | |
Loading extension module fused_adam... | |
Time to load fused_adam op: 0.1814718246459961 seconds | |
[2021-07-27 19:28:40,249] [INFO] [engine.py:710:_configure_optimizer] Using DeepSpeed Optimizer param name adam as basic optimizer | |
[2021-07-27 19:28:40,250] [INFO] [engine.py:714:_configure_optimizer] DeepSpeed Basic Optimizer = FusedAdam | |
[2021-07-27 19:28:40,250] [INFO] [utils.py:44:is_zero_supported_optimizer] Checking ZeRO support for optimizer=FusedAdam type=<class 'deepspeed.ops.adam.fused_adam.FusedAdam'> | |
[2021-07-27 19:28:40,250] [INFO] [logging.py:68:log_dist] [Rank 0] Creating fp16 ZeRO stage 3 optimizer | |
[2021-07-27 19:28:40,250] [INFO] [engine.py:938:_configure_zero_optimizer] Initializing ZeRO Stage 3 | |
[2021-07-27 19:28:40,253] [INFO] [stage3.py:516:__init__] Reduce bucket size 500000000 | |
[2021-07-27 19:28:40,253] [INFO] [stage3.py:517:__init__] Allgather bucket size 50000000 | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Loading extension module fused_adam... | |
Time to load fused_adam op: 0.20212721824645996 seconds | |
Loading extension module fused_adam... | |
Time to load fused_adam op: 0.2021317481994629 seconds | |
Loading extension module fused_adam... | |
Time to load fused_adam op: 0.20204472541809082 seconds | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
Emitting ninja build file /home/ec2-user/.cache/torch_extensions/py37_cu110/utils/build.ninja... | |
Building extension module utils... | |
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) | |
ninja: no work to do. | |
Loading extension module utils... | |
Time to load utils op: 0.166642427444458 seconds | |
Loading extension module utils... | |
Loading extension module utils... | |
Time to load utils op: 0.20189309120178223 seconds | |
Time to load utils op: 0.20183396339416504 seconds | |
Loading extension module utils... | |
Time to load utils op: 0.20169663429260254 seconds | |
[2021-07-27 19:28:40,872] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | init_optimizer_state: 21.68 | |
[2021-07-27 19:28:40,873] [INFO] [stage3.py:709:__init__] optimizer state initialized | |
[2021-07-27 19:28:40,903] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = adam | |
[2021-07-27 19:28:40,903] [INFO] [engine.py:516:_configure_lr_scheduler] DeepSpeed using client LR scheduler | |
[2021-07-27 19:28:40,903] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = None | |
[2021-07-27 19:28:40,903] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0001, 0.0001], mom=[(0.9, 0.999), (0.9, 0.999)] | |
[2021-07-27 19:28:40,903] [INFO] [config.py:900:print] DeepSpeedEngine configuration: | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
No modifications detected for re-loaded extension module utils, skipping build step... | |
Loading extension module utils... | |
Time to load utils op: 0.0003314018249511719 seconds | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] activation_checkpointing_config { | |
"partition_activations": false, | |
"contiguous_memory_optimization": false, | |
"cpu_checkpointing": false, | |
"number_checkpoints": null, | |
"synchronize_checkpoint_boundary": false, | |
"profile": false | |
} | |
No modifications detected for re-loaded extension module utils, skipping build step... | |
Loading extension module utils... | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] allreduce_always_fp32 ........ False | |
Time to load utils op: 0.0003123283386230469 seconds | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] amp_enabled .................. False | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] amp_params ................... False | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] checkpoint_tag_validation_enabled True | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] checkpoint_tag_validation_fail False | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] disable_allgather ............ False | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] dump_state ................... False | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] dynamic_loss_scale_args ...... {'init_scale': 1048576, 'scale_window': 1000, 'delayed_shift': 2, 'min_scale': 1} | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] eigenvalue_enabled ........... False | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] eigenvalue_gas_boundary_resolution 1 | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] eigenvalue_layer_name ........ bert.encoder.layer | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] eigenvalue_layer_num ......... 0 | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] eigenvalue_max_iter .......... 100 | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] eigenvalue_stability ......... 1e-06 | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] eigenvalue_tol ............... 0.01 | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] eigenvalue_verbose ........... False | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] elasticity_enabled ........... False | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] flops_profiler_config ........ { | |
"enabled": false, | |
"profile_step": 1, | |
"module_depth": -1, | |
"top_modules": 1, | |
"detailed": true, | |
"output_file": null | |
} | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] fp16_enabled ................. True | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] fp16_mixed_quantize .......... False | |
No modifications detected for re-loaded extension module utils, skipping build step... | |
Loading extension module utils... | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] global_rank .................. 0 | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] gradient_accumulation_steps .. 8 | |
[2021-07-27 19:28:40,904] [INFO] [config.py:904:print] gradient_clipping ............ 1.0 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] gradient_predivide_factor .... 1.0 | |
Time to load utils op: 0.0003952980041503906 seconds | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] initial_dynamic_scale ........ 1048576 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] loss_scale ................... 0 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] memory_breakdown ............. False | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] optimizer_legacy_fusion ...... False | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] optimizer_name ............... adam | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] optimizer_params ............. {'lr': 0.0001, 'weight_decay': 0.01, 'bias_correction': True, 'eps': 1e-06} | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] pld_enabled .................. False | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] pld_params ................... False | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] prescale_gradients ........... False | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] quantize_change_rate ......... 0.001 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] quantize_groups .............. 1 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] quantize_offset .............. 1000 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] quantize_period .............. 1000 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] quantize_rounding ............ 0 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] quantize_start_bits .......... 16 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] quantize_target_bits ......... 8 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] quantize_training_enabled .... False | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] quantize_type ................ 0 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] quantize_verbose ............. False | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] scheduler_name ............... None | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] scheduler_params ............. None | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] sparse_attention ............. None | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] sparse_gradients_enabled ..... False | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] steps_per_print .............. 100 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] tensorboard_enabled .......... False | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] tensorboard_job_name ......... DeepSpeedJobName | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] tensorboard_output_path ...... | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] train_batch_size ............. 64 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] train_micro_batch_size_per_gpu 2 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] use_quantizer_kernel ......... False | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] wall_clock_breakdown ......... True | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] world_size ................... 4 | |
[2021-07-27 19:28:40,905] [INFO] [config.py:904:print] zero_allow_untested_optimizer True | |
[2021-07-27 19:28:40,906] [INFO] [config.py:904:print] zero_config .................. { | |
"stage": 3, | |
"contiguous_gradients": false, | |
"reduce_scatter": false, | |
"reduce_bucket_size": 5.000000e+08, | |
"allgather_partitions": true, | |
"allgather_bucket_size": 5.000000e+08, | |
"overlap_comm": true, | |
"load_from_fp32_weights": true, | |
"elastic_checkpoint": true, | |
"offload_param": null, | |
"offload_optimizer": null, | |
"sub_group_size": 1.000000e+09, | |
"prefetch_bucket_size": 5.000000e+07, | |
"param_persistence_threshold": 1.000000e+05, | |
"max_live_parameters": 1.000000e+09, | |
"max_reuse_distance": 1.000000e+09, | |
"gather_fp16_weights_on_model_save": false, | |
"ignore_unused_parameters": true, | |
"legacy_stage1": false | |
} | |
[2021-07-27 19:28:40,906] [INFO] [config.py:904:print] zero_enabled ................. True | |
[2021-07-27 19:28:40,906] [INFO] [config.py:904:print] zero_optimization_stage ...... 3 | |
[2021-07-27 19:28:40,906] [INFO] [config.py:911:print] json = { | |
"train_batch_size": 64, | |
"train_micro_batch_size_per_gpu": 2, | |
"steps_per_print": 100, | |
"prescale_gradients": false, | |
"bert_token_file": "bert-large-uncased", | |
"bert_model_config": { | |
"vocab_size_or_config_json_file": 3.200300e+04, | |
"hidden_size": 2.560000e+03, | |
"num_hidden_layers": 4, | |
"num_attention_heads": 40, | |
"intermediate_size": 1.024000e+04, | |
"hidden_act": "gelu", | |
"hidden_dropout_prob": 0.1, | |
"attention_probs_dropout_prob": 0.1, | |
"max_position_embeddings": 512, | |
"initializer_range": 0.02 | |
}, | |
"zero_optimization": { | |
"stage": 3, | |
"overlap_comm": true, | |
"reduce_scatter": false, | |
"contiguous_gradients": false | |
}, | |
"zero_allow_untested_optimizer": true, | |
"optimizer": { | |
"type": "Adam", | |
"params": { | |
"lr": 0.0001, | |
"weight_decay": 0.01, | |
"bias_correction": true, | |
"eps": 1e-06 | |
} | |
}, | |
"gradient_clipping": 1.0, | |
"wall_clock_breakdown": true, | |
"fp16": { | |
"enabled": true, | |
"loss_scale": 0, | |
"initial_scale_power": 20, | |
"loss_scale_window": 1000 | |
}, | |
"data": { | |
"flags": { | |
"pretrain_dataset": true, | |
"pretrain_type": "wiki_bc" | |
}, | |
"mixed_seq_datasets": { | |
"128": { | |
"pretrain_dataset": "128/wikicorpus_en" | |
}, | |
"512": { | |
"pretrain_dataset": "512/wikicorpus_en" | |
} | |
} | |
}, | |
"mixed_seq_training": { | |
"128": { | |
"num_epochs": 16, | |
"warmup_proportion": 0.06, | |
"learning_rate": 0.011, | |
"num_workers": 4, | |
"async_worker": true, | |
"decay_rate": 0.9, | |
"decay_step": 250, | |
"total_training_steps": 0 | |
}, | |
"512": { | |
"num_epochs": 20, | |
"warmup_proportion": 0.02, | |
"learning_rate": 0.002, | |
"num_workers": 4, | |
"async_worker": true, | |
"decay_rate": 0.9, | |
"decay_step": 150, | |
"total_training_steps": 1.500000e+04 | |
} | |
} | |
} | |
Using /home/ec2-user/.cache/torch_extensions/py37_cu110 as PyTorch extensions root... | |
No modifications detected for re-loaded extension module utils, skipping build step... | |
Loading extension module utils... | |
Time to load utils op: 0.0004074573516845703 seconds | |
07/27/2021 19:28:40 - INFO - turing.logger - NvidiaBertDatasetProvider - Initialization: num_files = 256 | |
07/27/2021 19:28:40 - INFO - turing.logger - Training Epoch: 1 | |
07/27/2021 19:28:45 - INFO - turing.logger - worker-0: begin epoch 1 current_sample_count 0 shard_length 305883 global_data_samples 0 | |
0%| | 0/152794 [00:00<?, ?it/s] | |
0%| | 0/152942 [00:00<?, ?it/s] | |
0%| | 0/152966 [00:00<?, ?it/s] | |
0%| | 0/152613 [00:00<?, ?it/s]0: M0(BertForPreTrainingPreLN) P[] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
1: M1(BertModel) P[] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
2: M2(BertEmbeddings) P[] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
3: M3(Embedding) P[0] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 78151680, 'shape': (0,), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {3}} xGB | |
-release: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
4: M4(Embedding) P[1] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 1310720, 'shape': (0,), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'ds_numel': 1310720, 'shape': (512, 2560), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {4}} xGB | |
-release: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'ds_numel': 1310720, 'shape': (512, 2560), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
5: M5(Embedding) P[2] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 2, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 5120, 'shape': (0,), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {5}} xGB | |
-release: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
6: M6(FusedLayerNorm) P[3, 4] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 3, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 4, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {6}} xGB | |
-wait: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {6}} xGB | |
-release: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
7: M7(Dropout) P[] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
8: M8(BertEncoder) P[] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
9: M11(DeepSpeedTransformerLayer) P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 17, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 18, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 11, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 8, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 10, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 12, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 14, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 16, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-release: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
10: M12(DeepSpeedTransformerLayer) P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 29, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 30, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 20, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 23, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 22, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 24, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 26, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 28, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-release: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
11: M13(DeepSpeedTransformerLayer) P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 41, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 34, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 32, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 35, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 36, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 38, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 40, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 42, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-release: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
12: M14(DeepSpeedTransformerLayer) P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 44, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 47, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 46, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 48, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 50, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 52, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 53, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 54, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-release: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
13: M9(FusedLayerNorm) P[5, 6] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 5, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 6, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {9}} xGB | |
-wait: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {9}} xGB | |
-release: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
14: M15(BertPooler) P[] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
15: M16(LinearActivation) P[55, 56] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 56, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 55, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {16}} xGB | |
-wait: {'id': 56, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {16}} xGB | |
-release: {'id': 55, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 56, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
16: M17(BertPreTrainingHeads) P[] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
17: M18(BertLMPredictionHead) P[57] {'avail': '0.0e+00', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 30528, 'shape': (0,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 57, 'status': 'AVAILABLE', 'numel': 30528, 'ds_numel': 30528, 'shape': (30528,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {18}} xGB | |
18: M19(BertPredictionHeadTransform) P[] {'avail': '3.1e+04', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
19: M20(LinearActivation) P[58, 59] {'avail': '3.1e+04', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 58, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 59, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 58, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {20}} xGB | |
-wait: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {20}} xGB | |
-release: {'id': 58, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
20: M21(FusedLayerNorm) P[60, 61] {'avail': '3.1e+04', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 60, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {21}} xGB | |
-wait: {'id': 61, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {21}} xGB | |
-release: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 61, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
21: M22(Linear) P[0] {'avail': '3.1e+04', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {22}} xGB | |
-release: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 57, 'status': 'AVAILABLE', 'numel': 30528, 'ds_numel': 30528, 'shape': (30528,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
22: M23(Linear) P[62, 63] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 62, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 5120, 'shape': (0,), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2, 'shape': (0,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 62, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {23}} xGB | |
-wait: {'id': 63, 'status': 'AVAILABLE', 'numel': 2, 'ds_numel': 2, 'shape': (2,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {23}} xGB | |
-release: {'id': 62, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 63, 'status': 'AVAILABLE', 'numel': 2, 'ds_numel': 2, 'shape': (2,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
23: M0(BertForPreTrainingPreLN) P[] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
24: M17(BertPreTrainingHeads) P[] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
25: M17(BertPreTrainingHeads) P[] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
26: M23(Linear) P[62, 63] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 62, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 5120, 'shape': (0,), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2, 'shape': (0,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 62, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {23}} xGB | |
-wait: {'id': 63, 'status': 'AVAILABLE', 'numel': 2, 'ds_numel': 2, 'shape': (2,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {23}} xGB | |
-release: {'id': 62, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': (2, 2560), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 63, 'status': 'AVAILABLE', 'numel': 2, 'ds_numel': 2, 'shape': (2,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': (2,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
27: M18(BertLMPredictionHead) P[57, 0] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 30528, 'shape': (0,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 78151680, 'shape': (0,), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 57, 'status': 'AVAILABLE', 'numel': 30528, 'ds_numel': 30528, 'shape': (30528,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {18}} xGB | |
-wait: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {18}} xGB | |
28: M22(Linear) P[0] {'avail': '3.1e+04', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {18}}, xGB | |
-wait: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {18, 22}} xGB | |
29: M19(BertPredictionHeadTransform) P[] {'avail': '3.1e+04', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
30: M21(FusedLayerNorm) P[60, 61] {'avail': '3.1e+04', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 60, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {21}} xGB | |
-wait: {'id': 61, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {21}} xGB | |
-release: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 61, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
31: M20(LinearActivation) P[58, 59] {'avail': '3.1e+04', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 58, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 59, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 58, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {20}} xGB | |
-wait: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {20}} xGB | |
-release: {'id': 58, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 57, 'status': 'AVAILABLE', 'numel': 30528, 'ds_numel': 30528, 'shape': (30528,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': (30528,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
32: M1(BertModel) P[] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
33: M1(BertModel) P[] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
34: M15(BertPooler) P[] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
35: M16(LinearActivation) P[55, 56] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 56, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 55, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {16}} xGB | |
-wait: {'id': 56, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {16}} xGB | |
-release: {'id': 55, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 56, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
36: M9(FusedLayerNorm) P[5, 6] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 5, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 6, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {9}} xGB | |
-wait: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {9}} xGB | |
-release: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
37: M14(DeepSpeedTransformerLayer) P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 44, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 47, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 46, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 48, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 50, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 52, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 53, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 54, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-release: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': (7680, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': (7680,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': (10240, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': (10240,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': (2560, 10240), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
38: M13(DeepSpeedTransformerLayer) P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 41, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 34, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 32, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 35, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 36, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 38, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 40, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 42, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-release: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': (7680, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': (7680,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': (10240, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': (10240,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': (2560, 10240), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
39: M12(DeepSpeedTransformerLayer) P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 29, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 30, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 20, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 23, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 22, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 24, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 26, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 28, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-release: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': (7680, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': (7680,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': (10240, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': (10240,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': (2560, 10240), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
40: M11(DeepSpeedTransformerLayer) P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 17, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 18, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 11, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 8, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 10, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 12, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 14, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 16, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-release: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': (7680, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': (7680,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': (10240, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': (10240,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': (2560, 10240), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
41: M2(BertEmbeddings) P[] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
42: M7(Dropout) P[] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
43: M6(FusedLayerNorm) P[3, 4] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 3, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 4, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {6}} xGB | |
-wait: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {6}} xGB | |
-release: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
44: M5(Embedding) P[2] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 2, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 5120, 'shape': (0,), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {5}} xGB | |
45: M4(Embedding) P[1] {'avail': '-7.8e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 1310720, 'shape': (0,), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'ds_numel': 1310720, 'shape': (512, 2560), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {4}} xGB | |
46: M3(Embedding) P[0] {'avail': '-7.7e+07', 'queue_sz': '0', 'inflight': [], 'allocated': 'xGB'} | |
-fetch: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 78151680, 'shape': (0,), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {3}} xGB | |
-release: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': (30528, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'ds_numel': 1310720, 'shape': (512, 2560), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': (512, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': (2, 2560), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-partition grad for: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2, 'shape': (0,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': (2,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 62, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 5120, 'shape': (0,), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': (2, 2560), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 30528, 'shape': (0,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': (30528,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 60, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 59, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 58, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 5, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 6, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': (7680, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 44, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': (7680,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 48, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 54, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 53, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 52, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': (2560, 10240), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 50, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': (10240,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 47, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': (10240, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 46, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': (7680, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 32, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': (7680,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 36, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 42, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 41, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 40, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': (2560, 10240), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 38, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': (10240,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 35, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': (10240, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 34, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': (7680, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 20, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': (7680,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 24, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 30, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 29, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 28, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': (2560, 10240), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 26, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': (10240,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 23, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': (10240, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 22, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': (7680, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 8, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': (7680,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 12, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 18, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 17, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 16, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': (2560, 10240), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 14, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': (10240,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 11, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': (10240, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 10, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 3, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 4, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()} | |
-partition grad for: {'id': 2, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 5120, 'shape': (0,), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': (2, 2560), 'persist': True, 'active_sub_modules': set()} | |
0%| | 1/152794 [00:01<49:37:49, 1.17s/it]-partition grad for: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 1310720, 'shape': (0,), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': (512, 2560), 'persist': False, 'active_sub_modules': set()} | |
-partition grad for: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 78151680, 'shape': (0,), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': (30528, 2560), 'persist': False, 'active_sub_modules': set()} | |
0%| | 1/152613 [00:01<45:17:23, 1.07s/it] | |
0%| | 1/152966 [00:01<46:13:00, 1.09s/it][2021-07-27 19:28:46,855] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward_microstep: 341.51 | backward_microstep: 519.68 | backward_inner_microstep: 230.03 | backward_allreduce_microstep: 289.59 | step_microstep: 0.04 | |
[2021-07-27 19:28:46,855] [INFO] [logging.py:68:log_dist] [Rank 0] rank=0 time (ms) | forward: 341.48 | backward: 519.66 | backward_inner: 229.99 | backward_allreduce: 289.57 | step: 0.02 | |
0%| | 1/152942 [00:01<48:48:46, 1.15s/it]0: M0(BertForPreTrainingPreLN) P[] {'avail': '-7.8e+07', 'queue_sz': '131', 'inflight': [], 'allocated': 'xGB'} | |
-prefetch: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 78151680, 'shape': (0,), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
1: M1(BertModel) P[] {'avail': '0.0e+00', 'queue_sz': '130', 'inflight': [0], 'allocated': 'xGB'} | |
-prefetch: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 1310720, 'shape': (0,), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 17, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 3, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 4, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 2, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 5120, 'shape': (0,), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 18, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 11, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 8, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 10, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 12, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
2: M2(BertEmbeddings) P[] {'avail': '5.4e+07', 'queue_sz': '117', 'inflight': [0, 1, 17, 3, 4, 2, 18, 7, 11, 8, 9, 10, 12, 13], 'allocated': 'xGB'} | |
-prefetch: {'id': 14, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 29, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 16, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 30, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 20, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 23, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
3: M3(Embedding) P[0] {'avail': '1.1e+08', 'queue_sz': '108', 'inflight': [0, 1, 17, 3, 4, 2, 18, 7, 11, 8, 9, 10, 12, 13, 14, 15, 29, 16, 30, 19, 20, 23, 21], 'allocated': 'xGB'} | |
-fetch: {'id': 0, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 78151680, 'shape': (0,), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 22, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 26, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 24, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {3}} xGB | |
-release: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
4: M4(Embedding) P[1] {'avail': '8.1e+07', 'queue_sz': '103', 'inflight': [1, 17, 3, 4, 2, 18, 7, 11, 8, 9, 10, 12, 13, 14, 15, 29, 16, 30, 19, 20, 23, 21, 22, 25, 26, 24, 27], 'allocated': 'xGB'} | |
-fetch: {'id': 1, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 1310720, 'shape': (0,), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 28, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 34, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 31, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 41, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 33, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 32, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 35, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 36, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'ds_numel': 1310720, 'shape': (512, 2560), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {4}} xGB | |
-release: {'id': 1, 'status': 'AVAILABLE', 'numel': 1310720, 'ds_numel': 1310720, 'shape': (512, 2560), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
5: M5(Embedding) P[2] {'avail': '1.3e+08', 'queue_sz': '94', 'inflight': [17, 3, 4, 2, 18, 7, 11, 8, 9, 10, 12, 13, 14, 15, 29, 16, 30, 19, 20, 23, 21, 22, 25, 26, 24, 27, 28, 34, 31, 41, 33, 32, 35, 36, 37], 'allocated': 'xGB'} | |
-fetch: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 38, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 42, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 40, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 43, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 44, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 47, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 45, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {5}} xGB | |
-release: {'id': 2, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
6: M6(FusedLayerNorm) P[3, 4] {'avail': '1.8e+08', 'queue_sz': '86', 'inflight': [17, 3, 4, 18, 7, 11, 8, 9, 10, 12, 13, 14, 15, 29, 16, 30, 19, 20, 23, 21, 22, 25, 26, 24, 27, 28, 34, 31, 41, 33, 32, 35, 36, 37, 38, 39, 42, 40, 43, 44, 47, 45], 'allocated': 'xGB'} | |
-fetch: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 46, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 50, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 49, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 48, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 51, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {6}} xGB | |
-wait: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {6}} xGB | |
-release: {'id': 3, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 4, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
7: M7(Dropout) P[] {'avail': '2.4e+08', 'queue_sz': '81', 'inflight': [17, 18, 7, 11, 8, 9, 10, 12, 13, 14, 15, 29, 16, 30, 19, 20, 23, 21, 22, 25, 26, 24, 27, 28, 34, 31, 41, 33, 32, 35, 36, 37, 38, 39, 42, 40, 43, 44, 47, 45, 46, 50, 49, 48, 51], 'allocated': 'xGB'} | |
-prefetch: {'id': 60, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 61, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 0, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 78151680, 'shape': (0,), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 52, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 54, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 5, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 6, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 53, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 55, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 56, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 57, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 30528, 'shape': (0,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 58, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 59, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
8: M8(BertEncoder) P[] {'avail': '3.3e+08', 'queue_sz': '68', 'inflight': [17, 18, 7, 11, 8, 9, 10, 12, 13, 14, 15, 29, 16, 30, 19, 20, 23, 21, 22, 25, 26, 24, 27, 28, 34, 31, 41, 33, 32, 35, 36, 37, 38, 39, 42, 40, 43, 44, 47, 45, 46, 50, 49, 48, 51, 60, 61, 0, 52, 54, 5, 6, 53, 55, 56, 57, 58, 59], 'allocated': 'xGB'} | |
-prefetch: {'id': 62, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 5120, 'shape': (0,), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 57, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 30528, 'shape': (0,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 0, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 78151680, 'shape': (0,), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2, 'shape': (0,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
9: M11(DeepSpeedTransformerLayer) P[7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18] {'avail': '3.3e+08', 'queue_sz': '62', 'inflight': [17, 18, 7, 11, 8, 9, 10, 12, 13, 14, 15, 29, 16, 30, 19, 20, 23, 21, 22, 25, 26, 24, 27, 28, 34, 31, 41, 33, 32, 35, 36, 37, 38, 39, 42, 40, 43, 44, 47, 45, 46, 50, 49, 48, 51, 60, 61, 0, 52, 54, 5, 6, 53, 55, 56, 57, 58, 59, 62, 63], 'allocated': 'xGB'} | |
-fetch: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 14, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 15, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 16, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 0, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 78151680, 'shape': (0,), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-wait: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {11}} xGB | |
-release: {'id': 7, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 8, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 9, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 10, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 11, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 12, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 13, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 14, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 15, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 16, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 17, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 18, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
10: M12(DeepSpeedTransformerLayer) P[19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30] {'avail': '2.5e+08', 'queue_sz': '61', 'inflight': [29, 30, 19, 20, 23, 21, 22, 25, 26, 24, 27, 28, 34, 31, 41, 33, 32, 35, 36, 37, 38, 39, 42, 40, 43, 44, 47, 45, 46, 50, 49, 48, 51, 60, 61, 0, 52, 54, 5, 6, 53, 55, 56, 57, 58, 59, 62, 63], 'allocated': 'xGB'} | |
-fetch: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 22, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 24, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 25, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 26, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 27, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 28, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 47, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 48, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 49, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 60, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 55, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 59, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 61, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 58, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 56, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 5, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 6, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 43, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 44, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 45, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 46, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-wait: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {12}} xGB | |
-release: {'id': 19, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 20, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 21, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 22, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 23, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 24, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 25, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 26, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 27, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 28, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 29, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 30, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
11: M13(DeepSpeedTransformerLayer) P[31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42] {'avail': '1.7e+08', 'queue_sz': '46', 'inflight': [34, 31, 41, 33, 32, 35, 36, 37, 38, 39, 42, 40, 43, 44, 47, 45, 46, 50, 49, 48, 51, 60, 61, 0, 52, 54, 5, 6, 53, 55, 56, 57, 58, 59, 62, 63], 'allocated': 'xGB'} | |
-fetch: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 38, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 39, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 40, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 42, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 50, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 54, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 52, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 51, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 53, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-wait: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {13}} xGB | |
-release: {'id': 31, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 32, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 33, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 34, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 35, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 36, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 37, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 38, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 39, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 40, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 41, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 42, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
12: M14(DeepSpeedTransformerLayer) P[43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] {'avail': '9.2e+07', 'queue_sz': '37', 'inflight': [43, 44, 47, 45, 46, 50, 49, 48, 51, 60, 61, 0, 52, 54, 5, 6, 53, 55, 56, 57, 58, 59, 62, 63], 'allocated': 'xGB'} | |
-fetch: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 46, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 48, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 49, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 50, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 51, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 52, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 53, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 54, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 32, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 36, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 37, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 35, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 38, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 39, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-wait: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {14}} xGB | |
-release: {'id': 43, 'status': 'AVAILABLE', 'numel': 19660800, 'ds_numel': 19660800, 'shape': (7680, 2560), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 44, 'status': 'AVAILABLE', 'numel': 7680, 'ds_numel': 7680, 'shape': (7680,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 45, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 46, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 47, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 48, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 49, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (10240, 2560), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 50, 'status': 'AVAILABLE', 'numel': 10240, 'ds_numel': 10240, 'shape': (10240,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 51, 'status': 'AVAILABLE', 'numel': 26214400, 'ds_numel': 26214400, 'shape': (2560, 10240), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 52, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 53, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 54, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
13: M9(FusedLayerNorm) P[5, 6] {'avail': '6.6e+07', 'queue_sz': '31', 'inflight': [60, 61, 0, 5, 6, 55, 56, 57, 58, 59, 62, 63, 32, 36, 37, 35, 38, 39], 'allocated': 'xGB'} | |
-fetch: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 25, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 40, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 42, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 29, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 19, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 30, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 20, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 23, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 21, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 22, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 24, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {9}} xGB | |
-wait: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {9}} xGB | |
-release: {'id': 5, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 6, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
14: M15(BertPooler) P[] {'avail': '1.2e+08', 'queue_sz': '20', 'inflight': [60, 61, 0, 55, 56, 57, 58, 59, 62, 63, 32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24], 'allocated': 'xGB'} | |
-prefetch: {'id': 26, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 28, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 18, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 17, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 27, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 7, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 19660800, 'shape': (0,), 'ds_shape': (7680, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 11, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 8, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 7680, 'shape': (0,), 'ds_shape': (7680,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 9, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 6553600, 'shape': (0,), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
15: M16(LinearActivation) P[55, 56] {'avail': '1.7e+08', 'queue_sz': '11', 'inflight': [60, 61, 0, 55, 56, 57, 58, 59, 62, 63, 32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9], 'allocated': 'xGB'} | |
-fetch: {'id': 55, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 56, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 10, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 12, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 15, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (2560, 10240), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 13, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 26214400, 'shape': (0,), 'ds_shape': (10240, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 14, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 10240, 'shape': (0,), 'ds_shape': (10240,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 55, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': {16}} xGB | |
-wait: {'id': 56, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': {16}} xGB | |
-release: {'id': 55, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': (2560, 2560), 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 56, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': (2560,), 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
16: M17(BertPreTrainingHeads) P[] {'avail': '2.2e+08', 'queue_sz': '6', 'inflight': [60, 61, 0, 57, 58, 59, 62, 63, 32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9, 10, 12, 15, 13, 14], 'allocated': 'xGB'} | |
-prefetch: {'id': 16, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 1, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 1310720, 'shape': (0,), 'ds_shape': (512, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 3, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 4, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2560, 'shape': (0,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 2, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 5120, 'shape': (0,), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-prefetch: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
17: M18(BertLMPredictionHead) P[57, 0] {'avail': '2.2e+08', 'queue_sz': '0', 'inflight': [60, 61, 0, 57, 58, 59, 62, 63, 32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9, 10, 12, 15, 13, 14, 16, 1, 3, 4, 2], 'allocated': 'xGB'} | |
-fetch: {'id': 57, 'status': 'AVAILABLE', 'numel': 30528, 'ds_numel': 30528, 'shape': (30528,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 57, 'status': 'AVAILABLE', 'numel': 30528, 'ds_numel': 30528, 'shape': (30528,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {18}} xGB | |
-wait: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {18}} xGB | |
18: M19(BertPredictionHeadTransform) P[] {'avail': '2.2e+08', 'queue_sz': '0', 'inflight': [60, 61, 58, 59, 62, 63, 32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9, 10, 12, 15, 13, 14, 16, 1, 3, 4, 2], 'allocated': 'xGB'} | |
19: M20(LinearActivation) P[58, 59] {'avail': '2.2e+08', 'queue_sz': '0', 'inflight': [60, 61, 58, 59, 62, 63, 32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9, 10, 12, 15, 13, 14, 16, 1, 3, 4, 2], 'allocated': 'xGB'} | |
-fetch: {'id': 58, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 58, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {20}} xGB | |
-wait: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {20}} xGB | |
-release: {'id': 58, 'status': 'AVAILABLE', 'numel': 6553600, 'ds_numel': 6553600, 'shape': (2560, 2560), 'ds_shape': (2560, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 59, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
20: M21(FusedLayerNorm) P[60, 61] {'avail': '2.1e+08', 'queue_sz': '0', 'inflight': [60, 61, 62, 63, 32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9, 10, 12, 15, 13, 14, 16, 1, 3, 4, 2], 'allocated': 'xGB'} | |
-fetch: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 61, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {21}} xGB | |
-wait: {'id': 61, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {21}} xGB | |
-release: {'id': 60, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 61, 'status': 'AVAILABLE', 'numel': 2560, 'ds_numel': 2560, 'shape': (2560,), 'ds_shape': (2560,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
21: M22(Linear) P[0] {'avail': '2.1e+08', 'queue_sz': '0', 'inflight': [62, 63, 32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9, 10, 12, 15, 13, 14, 16, 1, 3, 4, 2], 'allocated': 'xGB'} | |
-fetch: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {18}}, xGB | |
-wait: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': {18, 22}} xGB | |
-release: {'id': 57, 'status': 'AVAILABLE', 'numel': 30528, 'ds_numel': 30528, 'shape': (30528,), 'ds_shape': (30528,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 0, 'status': 'AVAILABLE', 'numel': 78151680, 'ds_numel': 78151680, 'shape': (30528, 2560), 'ds_shape': (30528, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': False, 'active_sub_modules': set()}, xGB -> xGB | |
22: M23(Linear) P[62, 63] {'avail': '1.3e+08', 'queue_sz': '0', 'inflight': [62, 63, 32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9, 10, 12, 15, 13, 14, 16, 1, 3, 4, 2], 'allocated': 'xGB'} | |
-fetch: {'id': 62, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 5120, 'shape': (0,), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 63, 'status': 'INFLIGHT', 'numel': 0, 'ds_numel': 2, 'shape': (0,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 62, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {23}} xGB | |
-wait: {'id': 63, 'status': 'AVAILABLE', 'numel': 2, 'ds_numel': 2, 'shape': (2,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {23}} xGB | |
-release: {'id': 62, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
-release: {'id': 63, 'status': 'AVAILABLE', 'numel': 2, 'ds_numel': 2, 'shape': (2,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB -> xGB | |
23: M0(BertForPreTrainingPreLN) P[] {'avail': '1.3e+08', 'queue_sz': '0', 'inflight': [32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9, 10, 12, 15, 13, 14, 16, 1, 3, 4, 2], 'allocated': 'xGB'} | |
24: M17(BertPreTrainingHeads) P[] {'avail': '1.3e+08', 'queue_sz': '0', 'inflight': [32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9, 10, 12, 15, 13, 14, 16, 1, 3, 4, 2], 'allocated': 'xGB'} | |
25: M17(BertPreTrainingHeads) P[] {'avail': '1.3e+08', 'queue_sz': '0', 'inflight': [32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9, 10, 12, 15, 13, 14, 16, 1, 3, 4, 2], 'allocated': 'xGB'} | |
26: M23(Linear) P[62, 63] {'avail': '1.3e+08', 'queue_sz': '0', 'inflight': [32, 36, 37, 35, 38, 39, 25, 40, 42, 29, 19, 30, 20, 23, 21, 22, 24, 26, 28, 18, 17, 27, 7, 11, 8, 9, 10, 12, 15, 13, 14, 16, 1, 3, 4, 2], 'allocated': 'xGB'} | |
-fetch: {'id': 62, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 5120, 'shape': (0,), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-fetch: {'id': 63, 'status': 'NOT_AVAILABLE', 'numel': 0, 'ds_numel': 2, 'shape': (0,), 'ds_shape': (2,), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': set()}, xGB | |
-wait: {'id': 62, 'status': 'AVAILABLE', 'numel': 5120, 'ds_numel': 5120, 'shape': (2, 2560), 'ds_shape': (2, 2560), 'requires_grad': True, 'grad_shape': None, 'persist': True, 'active_sub_modules': {23}} xGB | |
-wait: {'id': 63, 'status': 'AVAILABLE', 'numel': 2, 'ds_numel': 2, 'shape': (2,), 'ds_shape': (2 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment