firenet150x50_len22_4_trainval

I0405 13:48:26.366220 29564 solver.cpp:280] Solving 
I0405 13:48:26.366231 29564 solver.cpp:281] Learning Rate Policy: poly
I0405 13:48:26.526338 29564 solver.cpp:229] Iteration 0, loss = 4.30412
I0405 13:48:26.526379 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0
I0405 13:48:26.526397 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 13:48:26.526412 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0
I0405 13:48:26.526423 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0
I0405 13:48:26.526435 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.03125
I0405 13:48:26.526448 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0
I0405 13:48:26.526459 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0
I0405 13:48:26.526470 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0
I0405 13:48:26.526482 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0
I0405 13:48:26.526494 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0
I0405 13:48:26.526504 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 0
I0405 13:48:26.526515 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 0
I0405 13:48:26.526527 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 0
I0405 13:48:26.526538 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 0
I0405 13:48:26.526549 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 0
I0405 13:48:26.526561 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 0
I0405 13:48:26.526572 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 0
I0405 13:48:26.526583 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 0
I0405 13:48:26.526594 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 0
I0405 13:48:26.526605 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 0
I0405 13:48:26.526617 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 0
I0405 13:48:26.526628 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 0
I0405 13:48:26.526643 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 4.3041 (* 0.0454545 = 0.195641 loss)
I0405 13:48:26.526656 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 4.30408 (* 0.0454545 = 0.19564 loss)
I0405 13:48:26.526671 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 4.30403 (* 0.0454545 = 0.195638 loss)
I0405 13:48:26.526685 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 4.3041 (* 0.0454545 = 0.195641 loss)
I0405 13:48:26.526698 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 4.30404 (* 0.0454545 = 0.195638 loss)
I0405 13:48:26.526712 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 4.3041 (* 0.0454545 = 0.195641 loss)
I0405 13:48:26.526726 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 4.3042 (* 0.0454545 = 0.195645 loss)
I0405 13:48:26.526759 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 4.30421 (* 0.0454545 = 0.195646 loss)
I0405 13:48:26.526775 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 4.30422 (* 0.0454545 = 0.195646 loss)
I0405 13:48:26.526788 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 4.30416 (* 0.0454545 = 0.195644 loss)
I0405 13:48:26.526801 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.30404 (* 0.0454545 = 0.195638 loss)
I0405 13:48:26.526815 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 4.30381 (* 0.0454545 = 0.195628 loss)
I0405 13:48:26.526829 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 4.30409 (* 0.0454545 = 0.195641 loss)
I0405 13:48:26.526842 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 4.30411 (* 0.0454545 = 0.195641 loss)
I0405 13:48:26.526856 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.30418 (* 0.0454545 = 0.195645 loss)
I0405 13:48:26.526872 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.30418 (* 0.0454545 = 0.195644 loss)
I0405 13:48:26.526886 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 4.30424 (* 0.0454545 = 0.195647 loss)
I0405 13:48:26.526900 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 4.30417 (* 0.0454545 = 0.195644 loss)
I0405 13:48:26.526913 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.30409 (* 0.0454545 = 0.19564 loss)
I0405 13:48:26.526926 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.30424 (* 0.0454545 = 0.195647 loss)
I0405 13:48:26.526939 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 4.30425 (* 0.0454545 = 0.195648 loss)
I0405 13:48:26.526953 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.3039 (* 0.0454545 = 0.195632 loss)
I0405 13:48:26.526964 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 13:48:26.526976 29564 solver.cpp:245]     Train net output #45: total_confidence = 7.63848e-42
I0405 13:48:26.526998 29564 sgd_solver.cpp:106] Iteration 0, lr = 0.01
I0405 13:52:15.395735 29564 solver.cpp:229] Iteration 500, loss = 1.83152
I0405 13:52:15.395925 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 13:52:15.395946 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 13:52:15.395958 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 13:52:15.395970 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0
I0405 13:52:15.395982 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0
I0405 13:52:15.395993 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.0625
I0405 13:52:15.396005 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 13:52:15.396018 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 13:52:15.396030 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 13:52:15.396042 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 13:52:15.396054 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 13:52:15.396065 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 13:52:15.396095 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 13:52:15.396116 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 13:52:15.396128 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 13:52:15.396139 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 13:52:15.396150 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 13:52:15.396162 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 13:52:15.396173 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 13:52:15.396184 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 13:52:15.396196 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 13:52:15.396210 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 13:52:15.396229 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.86427 (* 0.0454545 = 0.175649 loss)
I0405 13:52:15.396242 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.91119 (* 0.0454545 = 0.177781 loss)
I0405 13:52:15.396256 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.86094 (* 0.0454545 = 0.175497 loss)
I0405 13:52:15.396270 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.99332 (* 0.0454545 = 0.181514 loss)
I0405 13:52:15.396284 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 4.11789 (* 0.0454545 = 0.187177 loss)
I0405 13:52:15.396297 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 4.11727 (* 0.0454545 = 0.187148 loss)
I0405 13:52:15.396311 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.63765 (* 0.0454545 = 0.0744388 loss)
I0405 13:52:15.396325 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.46804 (* 0.0454545 = 0.0212745 loss)
I0405 13:52:15.396338 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.265149 (* 0.0454545 = 0.0120522 loss)
I0405 13:52:15.396353 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0149141 (* 0.0454545 = 0.000677912 loss)
I0405 13:52:15.396368 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000276904 (* 0.0454545 = 1.25866e-05 loss)
I0405 13:52:15.396383 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000275334 (* 0.0454545 = 1.25152e-05 loss)
I0405 13:52:15.396396 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000246004 (* 0.0454545 = 1.1182e-05 loss)
I0405 13:52:15.396411 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.0002497 (* 0.0454545 = 1.135e-05 loss)
I0405 13:52:15.396425 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000310403 (* 0.0454545 = 1.41092e-05 loss)
I0405 13:52:15.396440 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000319382 (* 0.0454545 = 1.45173e-05 loss)
I0405 13:52:15.396453 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000306028 (* 0.0454545 = 1.39104e-05 loss)
I0405 13:52:15.396486 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000256154 (* 0.0454545 = 1.16434e-05 loss)
I0405 13:52:15.396502 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.00027652 (* 0.0454545 = 1.25691e-05 loss)
I0405 13:52:15.396515 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00028508 (* 0.0454545 = 1.29582e-05 loss)
I0405 13:52:15.396529 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000276597 (* 0.0454545 = 1.25726e-05 loss)
I0405 13:52:15.396543 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000264065 (* 0.0454545 = 1.2003e-05 loss)
I0405 13:52:15.396556 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 13:52:15.396567 29564 solver.cpp:245]     Train net output #45: total_confidence = 1.82457e-08
I0405 13:52:15.396582 29564 sgd_solver.cpp:106] Iteration 500, lr = 0.009995
I0405 13:56:03.983819 29564 solver.cpp:229] Iteration 1000, loss = 1.19877
I0405 13:56:03.983958 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0
I0405 13:56:03.983980 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 13:56:03.983994 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 13:56:03.984005 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 13:56:03.984017 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0
I0405 13:56:03.984030 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0
I0405 13:56:03.984041 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.84375
I0405 13:56:03.984052 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 13:56:03.984064 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 13:56:03.984099 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 13:56:03.984112 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 13:56:03.984124 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 13:56:03.984135 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 13:56:03.984146 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 13:56:03.984158 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 13:56:03.984169 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 13:56:03.984180 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 13:56:03.984191 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 13:56:03.984202 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 13:56:03.984213 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 13:56:03.984225 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 13:56:03.984236 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 13:56:03.984251 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.88808 (* 0.0454545 = 0.176731 loss)
I0405 13:56:03.984266 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.92502 (* 0.0454545 = 0.17841 loss)
I0405 13:56:03.984280 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.9565 (* 0.0454545 = 0.179841 loss)
I0405 13:56:03.984294 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.8184 (* 0.0454545 = 0.173564 loss)
I0405 13:56:03.984308 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 4.27721 (* 0.0454545 = 0.194418 loss)
I0405 13:56:03.984321 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 4.03196 (* 0.0454545 = 0.183271 loss)
I0405 13:56:03.984335 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.14511 (* 0.0454545 = 0.0520504 loss)
I0405 13:56:03.984349 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.45744 (* 0.0454545 = 0.0207927 loss)
I0405 13:56:03.984364 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0512234 (* 0.0454545 = 0.00232834 loss)
I0405 13:56:03.984377 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0177217 (* 0.0454545 = 0.000805534 loss)
I0405 13:56:03.984391 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000554886 (* 0.0454545 = 2.52221e-05 loss)
I0405 13:56:03.984405 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000553212 (* 0.0454545 = 2.5146e-05 loss)
I0405 13:56:03.984421 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000525835 (* 0.0454545 = 2.39016e-05 loss)
I0405 13:56:03.984434 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000533378 (* 0.0454545 = 2.42445e-05 loss)
I0405 13:56:03.984448 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000578702 (* 0.0454545 = 2.63046e-05 loss)
I0405 13:56:03.984462 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000590582 (* 0.0454545 = 2.68446e-05 loss)
I0405 13:56:03.984477 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.0005726 (* 0.0454545 = 2.60273e-05 loss)
I0405 13:56:03.984505 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000535132 (* 0.0454545 = 2.43242e-05 loss)
I0405 13:56:03.984524 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000561319 (* 0.0454545 = 2.55145e-05 loss)
I0405 13:56:03.984537 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00056246 (* 0.0454545 = 2.55663e-05 loss)
I0405 13:56:03.984551 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000554233 (* 0.0454545 = 2.51924e-05 loss)
I0405 13:56:03.984565 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000535792 (* 0.0454545 = 2.43542e-05 loss)
I0405 13:56:03.984577 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 13:56:03.984589 29564 solver.cpp:245]     Train net output #45: total_confidence = 1.43792e-08
I0405 13:56:03.984602 29564 sgd_solver.cpp:106] Iteration 1000, lr = 0.00999
I0405 13:59:52.818518 29564 solver.cpp:229] Iteration 1500, loss = 1.1907
I0405 13:59:52.818645 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 13:59:52.818665 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 13:59:52.818677 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 13:59:52.818689 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.03125
I0405 13:59:52.818701 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.0625
I0405 13:59:52.818713 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.03125
I0405 13:59:52.818727 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 13:59:52.818738 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 13:59:52.818750 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 13:59:52.818761 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 13:59:52.818773 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 13:59:52.818784 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 13:59:52.818795 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 13:59:52.818807 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 13:59:52.818819 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 13:59:52.818830 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 13:59:52.818841 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 13:59:52.818852 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 13:59:52.818863 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 13:59:52.818876 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 13:59:52.818886 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 13:59:52.818897 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 13:59:52.818912 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.7467 (* 0.0454545 = 0.170304 loss)
I0405 13:59:52.818928 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.72997 (* 0.0454545 = 0.169544 loss)
I0405 13:59:52.818941 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.77272 (* 0.0454545 = 0.171487 loss)
I0405 13:59:52.818956 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.6474 (* 0.0454545 = 0.165791 loss)
I0405 13:59:52.818970 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 4.01378 (* 0.0454545 = 0.182445 loss)
I0405 13:59:52.818984 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 4.03612 (* 0.0454545 = 0.18346 loss)
I0405 13:59:52.818999 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.13699 (* 0.0454545 = 0.0516814 loss)
I0405 13:59:52.819012 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.792425 (* 0.0454545 = 0.0360193 loss)
I0405 13:59:52.819026 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.481984 (* 0.0454545 = 0.0219083 loss)
I0405 13:59:52.819041 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0173699 (* 0.0454545 = 0.000789541 loss)
I0405 13:59:52.819054 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000550279 (* 0.0454545 = 2.50127e-05 loss)
I0405 13:59:52.819068 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000548482 (* 0.0454545 = 2.4931e-05 loss)
I0405 13:59:52.819082 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000541013 (* 0.0454545 = 2.45915e-05 loss)
I0405 13:59:52.819097 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000552146 (* 0.0454545 = 2.50976e-05 loss)
I0405 13:59:52.819111 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000567112 (* 0.0454545 = 2.57778e-05 loss)
I0405 13:59:52.819125 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000561806 (* 0.0454545 = 2.55366e-05 loss)
I0405 13:59:52.819139 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000557603 (* 0.0454545 = 2.53456e-05 loss)
I0405 13:59:52.819170 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000542487 (* 0.0454545 = 2.46585e-05 loss)
I0405 13:59:52.819185 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000557618 (* 0.0454545 = 2.53463e-05 loss)
I0405 13:59:52.819200 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000554045 (* 0.0454545 = 2.51839e-05 loss)
I0405 13:59:52.819213 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000557398 (* 0.0454545 = 2.53363e-05 loss)
I0405 13:59:52.819231 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000551339 (* 0.0454545 = 2.50609e-05 loss)
I0405 13:59:52.819243 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 13:59:52.819255 29564 solver.cpp:245]     Train net output #45: total_confidence = 1.00189e-08
I0405 13:59:52.819269 29564 sgd_solver.cpp:106] Iteration 1500, lr = 0.009985
I0405 14:03:41.431494 29564 solver.cpp:229] Iteration 2000, loss = 1.18388
I0405 14:03:41.431615 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 14:03:41.431634 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 14:03:41.431648 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 14:03:41.431659 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 14:03:41.431671 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.03125
I0405 14:03:41.431684 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0
I0405 14:03:41.431695 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 14:03:41.431707 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 14:03:41.431720 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 14:03:41.431730 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 14:03:41.431742 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:03:41.431754 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:03:41.431766 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:03:41.431777 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:03:41.431788 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:03:41.431799 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:03:41.431810 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:03:41.431821 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:03:41.431833 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:03:41.431844 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:03:41.431855 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:03:41.431867 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:03:41.431884 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.44432 (* 0.0454545 = 0.15656 loss)
I0405 14:03:41.431900 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.66235 (* 0.0454545 = 0.16647 loss)
I0405 14:03:41.431913 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.5963 (* 0.0454545 = 0.163468 loss)
I0405 14:03:41.431927 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.74647 (* 0.0454545 = 0.170294 loss)
I0405 14:03:41.431941 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.90941 (* 0.0454545 = 0.1777 loss)
I0405 14:03:41.431957 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.98601 (* 0.0454545 = 0.181182 loss)
I0405 14:03:41.431970 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.42139 (* 0.0454545 = 0.0646086 loss)
I0405 14:03:41.431983 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.614816 (* 0.0454545 = 0.0279462 loss)
I0405 14:03:41.431998 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.233619 (* 0.0454545 = 0.010619 loss)
I0405 14:03:41.432011 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.238961 (* 0.0454545 = 0.0108619 loss)
I0405 14:03:41.432026 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000341528 (* 0.0454545 = 1.5524e-05 loss)
I0405 14:03:41.432041 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000335269 (* 0.0454545 = 1.52395e-05 loss)
I0405 14:03:41.432055 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000335911 (* 0.0454545 = 1.52687e-05 loss)
I0405 14:03:41.432086 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000347265 (* 0.0454545 = 1.57848e-05 loss)
I0405 14:03:41.432104 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000350656 (* 0.0454545 = 1.59389e-05 loss)
I0405 14:03:41.432119 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000342731 (* 0.0454545 = 1.55787e-05 loss)
I0405 14:03:41.432133 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000342219 (* 0.0454545 = 1.55554e-05 loss)
I0405 14:03:41.432165 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000335618 (* 0.0454545 = 1.52554e-05 loss)
I0405 14:03:41.432181 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000339589 (* 0.0454545 = 1.54358e-05 loss)
I0405 14:03:41.432195 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000341371 (* 0.0454545 = 1.55169e-05 loss)
I0405 14:03:41.432209 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000341316 (* 0.0454545 = 1.55144e-05 loss)
I0405 14:03:41.432224 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000340134 (* 0.0454545 = 1.54606e-05 loss)
I0405 14:03:41.432235 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:03:41.432247 29564 solver.cpp:245]     Train net output #45: total_confidence = 1.93447e-08
I0405 14:03:41.432261 29564 sgd_solver.cpp:106] Iteration 2000, lr = 0.00998
I0405 14:07:30.400146 29564 solver.cpp:229] Iteration 2500, loss = 1.17555
I0405 14:07:30.400257 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.03125
I0405 14:07:30.400277 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 14:07:30.400290 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 14:07:30.400301 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 14:07:30.400313 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0
I0405 14:07:30.400326 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.0625
I0405 14:07:30.400337 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 14:07:30.400348 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 14:07:30.400360 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 14:07:30.400372 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 14:07:30.400383 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:07:30.400395 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:07:30.400406 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:07:30.400418 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:07:30.400429 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:07:30.400440 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:07:30.400451 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:07:30.400462 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:07:30.400473 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:07:30.400485 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:07:30.400496 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:07:30.400507 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:07:30.400522 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.61557 (* 0.0454545 = 0.164344 loss)
I0405 14:07:30.400537 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.67275 (* 0.0454545 = 0.166943 loss)
I0405 14:07:30.400550 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.79288 (* 0.0454545 = 0.172404 loss)
I0405 14:07:30.400564 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.60689 (* 0.0454545 = 0.16395 loss)
I0405 14:07:30.400578 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.97785 (* 0.0454545 = 0.180811 loss)
I0405 14:07:30.400591 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.8546 (* 0.0454545 = 0.175209 loss)
I0405 14:07:30.400605 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.91302 (* 0.0454545 = 0.0869555 loss)
I0405 14:07:30.400619 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.619855 (* 0.0454545 = 0.0281752 loss)
I0405 14:07:30.400632 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.413469 (* 0.0454545 = 0.0187941 loss)
I0405 14:07:30.400647 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0146159 (* 0.0454545 = 0.000664358 loss)
I0405 14:07:30.400661 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.0005236 (* 0.0454545 = 2.38e-05 loss)
I0405 14:07:30.400676 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000529918 (* 0.0454545 = 2.40872e-05 loss)
I0405 14:07:30.400691 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000519256 (* 0.0454545 = 2.36025e-05 loss)
I0405 14:07:30.400704 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000531179 (* 0.0454545 = 2.41445e-05 loss)
I0405 14:07:30.400718 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000529861 (* 0.0454545 = 2.40846e-05 loss)
I0405 14:07:30.400732 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000529804 (* 0.0454545 = 2.4082e-05 loss)
I0405 14:07:30.400748 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000531354 (* 0.0454545 = 2.41524e-05 loss)
I0405 14:07:30.400779 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000516318 (* 0.0454545 = 2.3469e-05 loss)
I0405 14:07:30.400794 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000526508 (* 0.0454545 = 2.39322e-05 loss)
I0405 14:07:30.400809 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000528772 (* 0.0454545 = 2.40351e-05 loss)
I0405 14:07:30.400822 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000532455 (* 0.0454545 = 2.42025e-05 loss)
I0405 14:07:30.400836 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000522905 (* 0.0454545 = 2.37684e-05 loss)
I0405 14:07:30.400848 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:07:30.400859 29564 solver.cpp:245]     Train net output #45: total_confidence = 2.47377e-08
I0405 14:07:30.400874 29564 sgd_solver.cpp:106] Iteration 2500, lr = 0.009975
I0405 14:11:19.208225 29564 solver.cpp:229] Iteration 3000, loss = 1.16758
I0405 14:11:19.208442 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.03125
I0405 14:11:19.208467 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 14:11:19.208480 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0
I0405 14:11:19.208492 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 14:11:19.208504 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.03125
I0405 14:11:19.208516 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 14:11:19.208529 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 14:11:19.208541 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 14:11:19.208554 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 14:11:19.208564 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 14:11:19.208576 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:11:19.208596 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:11:19.208612 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:11:19.208624 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:11:19.208636 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:11:19.208648 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:11:19.208662 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:11:19.208673 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:11:19.208684 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:11:19.208696 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:11:19.208708 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:11:19.208719 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:11:19.208734 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.67939 (* 0.0454545 = 0.167245 loss)
I0405 14:11:19.208748 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.86778 (* 0.0454545 = 0.175808 loss)
I0405 14:11:19.208762 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.78289 (* 0.0454545 = 0.171949 loss)
I0405 14:11:19.208777 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.62507 (* 0.0454545 = 0.164776 loss)
I0405 14:11:19.208791 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 4.0475 (* 0.0454545 = 0.183977 loss)
I0405 14:11:19.208806 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.72057 (* 0.0454545 = 0.169117 loss)
I0405 14:11:19.208822 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.24527 (* 0.0454545 = 0.056603 loss)
I0405 14:11:19.208843 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.421787 (* 0.0454545 = 0.0191722 loss)
I0405 14:11:19.208858 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.273627 (* 0.0454545 = 0.0124376 loss)
I0405 14:11:19.208873 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0268704 (* 0.0454545 = 0.00122138 loss)
I0405 14:11:19.208887 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.00115338 (* 0.0454545 = 5.24263e-05 loss)
I0405 14:11:19.208906 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.00109549 (* 0.0454545 = 4.97951e-05 loss)
I0405 14:11:19.208935 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.00111151 (* 0.0454545 = 5.0523e-05 loss)
I0405 14:11:19.208955 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.00112114 (* 0.0454545 = 5.0961e-05 loss)
I0405 14:11:19.208968 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.00111318 (* 0.0454545 = 5.0599e-05 loss)
I0405 14:11:19.208982 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.00110635 (* 0.0454545 = 5.02886e-05 loss)
I0405 14:11:19.208997 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.00110517 (* 0.0454545 = 5.02351e-05 loss)
I0405 14:11:19.209028 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.00109926 (* 0.0454545 = 4.99662e-05 loss)
I0405 14:11:19.209044 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.00110342 (* 0.0454545 = 5.01555e-05 loss)
I0405 14:11:19.209059 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00110897 (* 0.0454545 = 5.04079e-05 loss)
I0405 14:11:19.209072 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.00111115 (* 0.0454545 = 5.05068e-05 loss)
I0405 14:11:19.209086 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.00110925 (* 0.0454545 = 5.04207e-05 loss)
I0405 14:11:19.209100 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:11:19.209110 29564 solver.cpp:245]     Train net output #45: total_confidence = 1.90504e-08
I0405 14:11:19.209125 29564 sgd_solver.cpp:106] Iteration 3000, lr = 0.00997
I0405 14:15:07.974445 29564 solver.cpp:229] Iteration 3500, loss = 1.16134
I0405 14:15:07.974550 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 14:15:07.974570 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 14:15:07.974581 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 14:15:07.974593 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.03125
I0405 14:15:07.974606 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.0625
I0405 14:15:07.974617 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.25
I0405 14:15:07.974629 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 14:15:07.974642 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 14:15:07.974653 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 14:15:07.974664 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 14:15:07.974676 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:15:07.974690 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:15:07.974702 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:15:07.974714 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:15:07.974725 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:15:07.974736 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:15:07.974748 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:15:07.974759 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:15:07.974771 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:15:07.974781 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:15:07.974793 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:15:07.974804 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:15:07.974819 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.81317 (* 0.0454545 = 0.173326 loss)
I0405 14:15:07.974833 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.95322 (* 0.0454545 = 0.179692 loss)
I0405 14:15:07.974848 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.81625 (* 0.0454545 = 0.173466 loss)
I0405 14:15:07.974861 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.84216 (* 0.0454545 = 0.174644 loss)
I0405 14:15:07.974875 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.98354 (* 0.0454545 = 0.18107 loss)
I0405 14:15:07.974889 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.87404 (* 0.0454545 = 0.176093 loss)
I0405 14:15:07.974903 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.49992 (* 0.0454545 = 0.0681784 loss)
I0405 14:15:07.974917 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.773858 (* 0.0454545 = 0.0351754 loss)
I0405 14:15:07.974931 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.591337 (* 0.0454545 = 0.0268789 loss)
I0405 14:15:07.974946 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.24305 (* 0.0454545 = 0.0110477 loss)
I0405 14:15:07.974959 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.00103841 (* 0.0454545 = 4.72006e-05 loss)
I0405 14:15:07.974974 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.00100966 (* 0.0454545 = 4.58938e-05 loss)
I0405 14:15:07.974988 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.00101597 (* 0.0454545 = 4.61805e-05 loss)
I0405 14:15:07.975003 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.00103493 (* 0.0454545 = 4.70424e-05 loss)
I0405 14:15:07.975018 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.00101657 (* 0.0454545 = 4.62078e-05 loss)
I0405 14:15:07.975033 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.0010203 (* 0.0454545 = 4.63773e-05 loss)
I0405 14:15:07.975049 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.00101394 (* 0.0454545 = 4.60881e-05 loss)
I0405 14:15:07.975080 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.00102132 (* 0.0454545 = 4.64237e-05 loss)
I0405 14:15:07.975095 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.00101455 (* 0.0454545 = 4.6116e-05 loss)
I0405 14:15:07.975108 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.0010218 (* 0.0454545 = 4.64456e-05 loss)
I0405 14:15:07.975122 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.0010233 (* 0.0454545 = 4.65136e-05 loss)
I0405 14:15:07.975136 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.00102028 (* 0.0454545 = 4.63763e-05 loss)
I0405 14:15:07.975148 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:15:07.975160 29564 solver.cpp:245]     Train net output #45: total_confidence = 1.63369e-08
I0405 14:15:07.975173 29564 sgd_solver.cpp:106] Iteration 3500, lr = 0.009965
I0405 14:18:56.865790 29564 solver.cpp:229] Iteration 4000, loss = 1.15982
I0405 14:18:56.865916 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 14:18:56.865936 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 14:18:56.865947 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 14:18:56.865959 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 14:18:56.865972 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.03125
I0405 14:18:56.865983 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5625
I0405 14:18:56.865995 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 14:18:56.866006 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 14:18:56.866019 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 14:18:56.866029 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 14:18:56.866041 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:18:56.866053 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:18:56.866065 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:18:56.866076 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:18:56.866087 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:18:56.866098 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:18:56.866111 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:18:56.866122 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:18:56.866132 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:18:56.866144 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:18:56.866155 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:18:56.866168 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:18:56.866183 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.48443 (* 0.0454545 = 0.158383 loss)
I0405 14:18:56.866196 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.94061 (* 0.0454545 = 0.179119 loss)
I0405 14:18:56.866210 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.78767 (* 0.0454545 = 0.172167 loss)
I0405 14:18:56.866225 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.77084 (* 0.0454545 = 0.171402 loss)
I0405 14:18:56.866238 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.97025 (* 0.0454545 = 0.180466 loss)
I0405 14:18:56.866252 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.509 (* 0.0454545 = 0.1595 loss)
I0405 14:18:56.866266 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.5365 (* 0.0454545 = 0.0698409 loss)
I0405 14:18:56.866281 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.463285 (* 0.0454545 = 0.0210584 loss)
I0405 14:18:56.866296 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.25421 (* 0.0454545 = 0.011555 loss)
I0405 14:18:56.866309 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0198523 (* 0.0454545 = 0.000902379 loss)
I0405 14:18:56.866324 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000920496 (* 0.0454545 = 4.18407e-05 loss)
I0405 14:18:56.866338 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000909042 (* 0.0454545 = 4.13201e-05 loss)
I0405 14:18:56.866353 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000912397 (* 0.0454545 = 4.14726e-05 loss)
I0405 14:18:56.866366 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000920487 (* 0.0454545 = 4.18403e-05 loss)
I0405 14:18:56.866380 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000909082 (* 0.0454545 = 4.13219e-05 loss)
I0405 14:18:56.866394 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000911546 (* 0.0454545 = 4.14339e-05 loss)
I0405 14:18:56.866408 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000910504 (* 0.0454545 = 4.13866e-05 loss)
I0405 14:18:56.866438 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000913012 (* 0.0454545 = 4.15005e-05 loss)
I0405 14:18:56.866454 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000910287 (* 0.0454545 = 4.13767e-05 loss)
I0405 14:18:56.866467 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000921385 (* 0.0454545 = 4.18811e-05 loss)
I0405 14:18:56.866482 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000913217 (* 0.0454545 = 4.15099e-05 loss)
I0405 14:18:56.866495 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000908305 (* 0.0454545 = 4.12866e-05 loss)
I0405 14:18:56.866508 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:18:56.866518 29564 solver.cpp:245]     Train net output #45: total_confidence = 3.66924e-08
I0405 14:18:56.866531 29564 sgd_solver.cpp:106] Iteration 4000, lr = 0.00996
I0405 14:22:46.200162 29564 solver.cpp:229] Iteration 4500, loss = 1.15199
I0405 14:22:46.200268 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.125
I0405 14:22:46.200289 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 14:22:46.200300 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 14:22:46.200312 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 14:22:46.200325 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.03125
I0405 14:22:46.200336 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.3125
I0405 14:22:46.200350 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 14:22:46.200362 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.96875
I0405 14:22:46.200374 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 14:22:46.200387 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 14:22:46.200397 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:22:46.200409 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:22:46.200420 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:22:46.200433 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:22:46.200443 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:22:46.200455 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:22:46.200466 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:22:46.200479 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:22:46.200489 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:22:46.200500 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:22:46.200511 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:22:46.200523 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:22:46.200538 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.53094 (* 0.0454545 = 0.160497 loss)
I0405 14:22:46.200552 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.81042 (* 0.0454545 = 0.173201 loss)
I0405 14:22:46.200567 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.62747 (* 0.0454545 = 0.164885 loss)
I0405 14:22:46.200580 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.67171 (* 0.0454545 = 0.166896 loss)
I0405 14:22:46.200594 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.98641 (* 0.0454545 = 0.181201 loss)
I0405 14:22:46.200608 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.75485 (* 0.0454545 = 0.170675 loss)
I0405 14:22:46.200621 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.41047 (* 0.0454545 = 0.0641124 loss)
I0405 14:22:46.200635 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.218344 (* 0.0454545 = 0.00992471 loss)
I0405 14:22:46.200649 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0312096 (* 0.0454545 = 0.00141862 loss)
I0405 14:22:46.200664 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0145468 (* 0.0454545 = 0.000661216 loss)
I0405 14:22:46.200677 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000528008 (* 0.0454545 = 2.40004e-05 loss)
I0405 14:22:46.200691 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000513376 (* 0.0454545 = 2.33353e-05 loss)
I0405 14:22:46.200706 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.0005168 (* 0.0454545 = 2.34909e-05 loss)
I0405 14:22:46.200721 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.00051393 (* 0.0454545 = 2.33604e-05 loss)
I0405 14:22:46.200734 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000514951 (* 0.0454545 = 2.34069e-05 loss)
I0405 14:22:46.200748 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000514141 (* 0.0454545 = 2.337e-05 loss)
I0405 14:22:46.200762 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000515435 (* 0.0454545 = 2.34289e-05 loss)
I0405 14:22:46.200793 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000511056 (* 0.0454545 = 2.32298e-05 loss)
I0405 14:22:46.200809 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000516455 (* 0.0454545 = 2.34752e-05 loss)
I0405 14:22:46.200822 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000509454 (* 0.0454545 = 2.3157e-05 loss)
I0405 14:22:46.200836 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000517937 (* 0.0454545 = 2.35426e-05 loss)
I0405 14:22:46.200850 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000513193 (* 0.0454545 = 2.33269e-05 loss)
I0405 14:22:46.200862 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:22:46.200873 29564 solver.cpp:245]     Train net output #45: total_confidence = 2.4991e-08
I0405 14:22:46.200886 29564 sgd_solver.cpp:106] Iteration 4500, lr = 0.009955
I0405 14:26:34.960763 29564 solver.cpp:338] Iteration 5000, Testing net (#0)
I0405 14:26:45.252977 29564 solver.cpp:393] Test loss: 1.05789
I0405 14:26:45.253021 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0
I0405 14:26:45.253037 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.004
I0405 14:26:45.253051 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.005
I0405 14:26:45.253063 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.093
I0405 14:26:45.253074 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.212
I0405 14:26:45.253087 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.459
I0405 14:26:45.253098 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.894
I0405 14:26:45.253109 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 14:26:45.253121 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 14:26:45.253132 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 14:26:45.253144 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 14:26:45.253155 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 14:26:45.253166 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 14:26:45.253178 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 14:26:45.253190 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 14:26:45.253201 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 14:26:45.253211 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 14:26:45.253222 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 14:26:45.253233 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 14:26:45.253244 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 14:26:45.253255 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 14:26:45.253267 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 14:26:45.253280 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 3.49209 (* 0.0454545 = 0.158731 loss)
I0405 14:26:45.253294 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 3.89063 (* 0.0454545 = 0.176847 loss)
I0405 14:26:45.253309 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 3.72724 (* 0.0454545 = 0.16942 loss)
I0405 14:26:45.253322 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 3.73787 (* 0.0454545 = 0.169903 loss)
I0405 14:26:45.253335 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 3.62905 (* 0.0454545 = 0.164957 loss)
I0405 14:26:45.253348 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 3.5284 (* 0.0454545 = 0.160382 loss)
I0405 14:26:45.253362 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.869835 (* 0.0454545 = 0.039538 loss)
I0405 14:26:45.253376 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.297959 (* 0.0454545 = 0.0135436 loss)
I0405 14:26:45.253389 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0668295 (* 0.0454545 = 0.0030377 loss)
I0405 14:26:45.253403 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0295842 (* 0.0454545 = 0.00134474 loss)
I0405 14:26:45.253418 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 0.000327893 (* 0.0454545 = 1.49042e-05 loss)
I0405 14:26:45.253432 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 0.000339578 (* 0.0454545 = 1.54353e-05 loss)
I0405 14:26:45.253445 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 0.000364947 (* 0.0454545 = 1.65885e-05 loss)
I0405 14:26:45.253463 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 0.000335257 (* 0.0454545 = 1.5239e-05 loss)
I0405 14:26:45.253476 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 0.00033332 (* 0.0454545 = 1.51509e-05 loss)
I0405 14:26:45.253490 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 0.000335111 (* 0.0454545 = 1.52323e-05 loss)
I0405 14:26:45.253504 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 0.000355006 (* 0.0454545 = 1.61366e-05 loss)
I0405 14:26:45.253545 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 0.000330151 (* 0.0454545 = 1.50069e-05 loss)
I0405 14:26:45.253561 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 0.000366669 (* 0.0454545 = 1.66668e-05 loss)
I0405 14:26:45.253573 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 0.000320136 (* 0.0454545 = 1.45516e-05 loss)
I0405 14:26:45.253587 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 0.000332884 (* 0.0454545 = 1.51311e-05 loss)
I0405 14:26:45.253600 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 0.000339667 (* 0.0454545 = 1.54394e-05 loss)
I0405 14:26:45.253612 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0
I0405 14:26:45.253623 29564 solver.cpp:406]     Test net output #45: total_confidence = 2.51415e-07
I0405 14:26:45.368388 29564 solver.cpp:229] Iteration 5000, loss = 1.12655
I0405 14:26:45.368434 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.03125
I0405 14:26:45.368463 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 14:26:45.368487 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 14:26:45.368510 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 14:26:45.368532 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 14:26:45.368558 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 14:26:45.368583 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 14:26:45.368605 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 1
I0405 14:26:45.368628 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 14:26:45.368648 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 14:26:45.368667 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:26:45.368688 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:26:45.368710 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:26:45.368729 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:26:45.368749 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:26:45.368770 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:26:45.368791 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:26:45.368813 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:26:45.368834 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:26:45.368854 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:26:45.368875 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:26:45.368896 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:26:45.368927 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.78495 (* 0.0454545 = 0.172043 loss)
I0405 14:26:45.368954 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 4.06391 (* 0.0454545 = 0.184723 loss)
I0405 14:26:45.368980 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.91862 (* 0.0454545 = 0.178119 loss)
I0405 14:26:45.369006 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.88557 (* 0.0454545 = 0.176617 loss)
I0405 14:26:45.369031 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.16291 (* 0.0454545 = 0.143768 loss)
I0405 14:26:45.369061 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.4625 (* 0.0454545 = 0.157386 loss)
I0405 14:26:45.369088 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.09226 (* 0.0454545 = 0.0496483 loss)
I0405 14:26:45.369114 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.0664419 (* 0.0454545 = 0.00302009 loss)
I0405 14:26:45.369140 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0229121 (* 0.0454545 = 0.00104146 loss)
I0405 14:26:45.369166 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00893314 (* 0.0454545 = 0.000406052 loss)
I0405 14:26:45.369216 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000257604 (* 0.0454545 = 1.17093e-05 loss)
I0405 14:26:45.369245 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000267044 (* 0.0454545 = 1.21384e-05 loss)
I0405 14:26:45.369271 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000285758 (* 0.0454545 = 1.2989e-05 loss)
I0405 14:26:45.369297 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000260023 (* 0.0454545 = 1.18192e-05 loss)
I0405 14:26:45.369324 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000263903 (* 0.0454545 = 1.19956e-05 loss)
I0405 14:26:45.369349 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000262913 (* 0.0454545 = 1.19506e-05 loss)
I0405 14:26:45.369375 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000276884 (* 0.0454545 = 1.25856e-05 loss)
I0405 14:26:45.369400 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000261135 (* 0.0454545 = 1.18698e-05 loss)
I0405 14:26:45.369426 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000283478 (* 0.0454545 = 1.28854e-05 loss)
I0405 14:26:45.369453 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000250255 (* 0.0454545 = 1.13752e-05 loss)
I0405 14:26:45.369479 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000263113 (* 0.0454545 = 1.19597e-05 loss)
I0405 14:26:45.369510 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000264686 (* 0.0454545 = 1.20312e-05 loss)
I0405 14:26:45.369532 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:26:45.369554 29564 solver.cpp:245]     Train net output #45: total_confidence = 4.5363e-07
I0405 14:26:45.369577 29564 sgd_solver.cpp:106] Iteration 5000, lr = 0.00995
I0405 14:30:34.069612 29564 solver.cpp:229] Iteration 5500, loss = 1.10175
I0405 14:30:34.069775 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 14:30:34.069805 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 14:30:34.069829 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 14:30:34.069851 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 14:30:34.069874 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 14:30:34.069896 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 14:30:34.069919 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.59375
I0405 14:30:34.069949 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 14:30:34.069972 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 14:30:34.069993 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 14:30:34.070013 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:30:34.070034 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:30:34.070055 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:30:34.070076 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:30:34.070097 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:30:34.070117 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:30:34.070138 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:30:34.070158 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:30:34.070184 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:30:34.070206 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:30:34.070227 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:30:34.070248 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:30:34.070276 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.27145 (* 0.0454545 = 0.148702 loss)
I0405 14:30:34.070303 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.70634 (* 0.0454545 = 0.16847 loss)
I0405 14:30:34.070328 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.59191 (* 0.0454545 = 0.163269 loss)
I0405 14:30:34.070355 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.45207 (* 0.0454545 = 0.156912 loss)
I0405 14:30:34.070384 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.40027 (* 0.0454545 = 0.154558 loss)
I0405 14:30:34.070408 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.4392 (* 0.0454545 = 0.156327 loss)
I0405 14:30:34.070436 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.887 (* 0.0454545 = 0.0857726 loss)
I0405 14:30:34.070461 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.589515 (* 0.0454545 = 0.0267961 loss)
I0405 14:30:34.070487 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0357541 (* 0.0454545 = 0.00162519 loss)
I0405 14:30:34.070513 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.013427 (* 0.0454545 = 0.000610319 loss)
I0405 14:30:34.070540 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000339241 (* 0.0454545 = 1.54201e-05 loss)
I0405 14:30:34.070565 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000345828 (* 0.0454545 = 1.57195e-05 loss)
I0405 14:30:34.070591 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.00037059 (* 0.0454545 = 1.6845e-05 loss)
I0405 14:30:34.070618 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000345483 (* 0.0454545 = 1.57038e-05 loss)
I0405 14:30:34.070644 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000339111 (* 0.0454545 = 1.54141e-05 loss)
I0405 14:30:34.070670 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000342651 (* 0.0454545 = 1.5575e-05 loss)
I0405 14:30:34.070696 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000361458 (* 0.0454545 = 1.64299e-05 loss)
I0405 14:30:34.070744 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000334189 (* 0.0454545 = 1.51904e-05 loss)
I0405 14:30:34.070771 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000370826 (* 0.0454545 = 1.68557e-05 loss)
I0405 14:30:34.070798 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000326477 (* 0.0454545 = 1.48399e-05 loss)
I0405 14:30:34.070825 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000341354 (* 0.0454545 = 1.55161e-05 loss)
I0405 14:30:34.070852 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000347693 (* 0.0454545 = 1.58042e-05 loss)
I0405 14:30:34.070873 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:30:34.070894 29564 solver.cpp:245]     Train net output #45: total_confidence = 5.349e-07
I0405 14:30:34.070917 29564 sgd_solver.cpp:106] Iteration 5500, lr = 0.009945
I0405 14:34:23.085561 29564 solver.cpp:229] Iteration 6000, loss = 1.0922
I0405 14:34:23.085669 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 14:34:23.085688 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 14:34:23.085701 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0
I0405 14:34:23.085713 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 14:34:23.085726 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 14:34:23.085737 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 14:34:23.085749 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 14:34:23.085762 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 14:34:23.085773 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 14:34:23.085785 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 14:34:23.085796 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:34:23.085808 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:34:23.085819 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:34:23.085831 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:34:23.085842 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:34:23.085855 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:34:23.085865 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:34:23.085877 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:34:23.085888 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:34:23.085901 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:34:23.085911 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:34:23.085922 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:34:23.085938 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.49723 (* 0.0454545 = 0.158965 loss)
I0405 14:34:23.085953 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.55925 (* 0.0454545 = 0.161784 loss)
I0405 14:34:23.085968 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.66037 (* 0.0454545 = 0.16638 loss)
I0405 14:34:23.085980 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.55103 (* 0.0454545 = 0.161411 loss)
I0405 14:34:23.085994 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.29274 (* 0.0454545 = 0.14967 loss)
I0405 14:34:23.086007 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.31388 (* 0.0454545 = 0.150631 loss)
I0405 14:34:23.086021 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.56793 (* 0.0454545 = 0.0712695 loss)
I0405 14:34:23.086035 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.891659 (* 0.0454545 = 0.04053 loss)
I0405 14:34:23.086050 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.46258 (* 0.0454545 = 0.0210264 loss)
I0405 14:34:23.086063 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.44307 (* 0.0454545 = 0.0201396 loss)
I0405 14:34:23.086077 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.00255166 (* 0.0454545 = 0.000115985 loss)
I0405 14:34:23.086091 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.0026176 (* 0.0454545 = 0.000118982 loss)
I0405 14:34:23.086105 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.00276446 (* 0.0454545 = 0.000125657 loss)
I0405 14:34:23.086119 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.00258178 (* 0.0454545 = 0.000117354 loss)
I0405 14:34:23.086133 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.00256616 (* 0.0454545 = 0.000116644 loss)
I0405 14:34:23.086148 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.00257468 (* 0.0454545 = 0.000117031 loss)
I0405 14:34:23.086161 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.00277291 (* 0.0454545 = 0.000126041 loss)
I0405 14:34:23.086192 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.00251856 (* 0.0454545 = 0.00011448 loss)
I0405 14:34:23.086207 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.00273494 (* 0.0454545 = 0.000124316 loss)
I0405 14:34:23.086222 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00250649 (* 0.0454545 = 0.000113931 loss)
I0405 14:34:23.086236 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.00256929 (* 0.0454545 = 0.000116786 loss)
I0405 14:34:23.086251 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.00261657 (* 0.0454545 = 0.000118935 loss)
I0405 14:34:23.086262 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:34:23.086273 29564 solver.cpp:245]     Train net output #45: total_confidence = 2.51457e-07
I0405 14:34:23.086287 29564 sgd_solver.cpp:106] Iteration 6000, lr = 0.00994
I0405 14:38:11.970351 29564 solver.cpp:229] Iteration 6500, loss = 1.08306
I0405 14:38:11.970525 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 14:38:11.970556 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 14:38:11.970580 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 14:38:11.970603 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.03125
I0405 14:38:11.970625 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.15625
I0405 14:38:11.970648 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.28125
I0405 14:38:11.970672 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.59375
I0405 14:38:11.970695 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.96875
I0405 14:38:11.970717 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 14:38:11.970739 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 14:38:11.970760 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:38:11.970782 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:38:11.970801 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:38:11.970824 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:38:11.970844 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:38:11.970865 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:38:11.970885 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:38:11.970907 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:38:11.970927 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:38:11.970947 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:38:11.970968 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:38:11.970989 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:38:11.971015 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.25451 (* 0.0454545 = 0.147932 loss)
I0405 14:38:11.971045 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.60598 (* 0.0454545 = 0.163908 loss)
I0405 14:38:11.971074 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.60823 (* 0.0454545 = 0.16401 loss)
I0405 14:38:11.971117 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.71035 (* 0.0454545 = 0.168652 loss)
I0405 14:38:11.971144 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.45355 (* 0.0454545 = 0.15698 loss)
I0405 14:38:11.971170 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.44101 (* 0.0454545 = 0.156409 loss)
I0405 14:38:11.971196 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 2.13686 (* 0.0454545 = 0.0971302 loss)
I0405 14:38:11.971221 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.293885 (* 0.0454545 = 0.0133584 loss)
I0405 14:38:11.971247 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.228078 (* 0.0454545 = 0.0103672 loss)
I0405 14:38:11.971273 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0354082 (* 0.0454545 = 0.00160946 loss)
I0405 14:38:11.971299 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000966407 (* 0.0454545 = 4.39276e-05 loss)
I0405 14:38:11.971325 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.0009914 (* 0.0454545 = 4.50636e-05 loss)
I0405 14:38:11.971351 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.0010643 (* 0.0454545 = 4.83774e-05 loss)
I0405 14:38:11.971377 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000968283 (* 0.0454545 = 4.40129e-05 loss)
I0405 14:38:11.971403 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000952074 (* 0.0454545 = 4.32761e-05 loss)
I0405 14:38:11.971429 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000935229 (* 0.0454545 = 4.25104e-05 loss)
I0405 14:38:11.971454 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.00106192 (* 0.0454545 = 4.82692e-05 loss)
I0405 14:38:11.971498 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000926281 (* 0.0454545 = 4.21037e-05 loss)
I0405 14:38:11.971526 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.00100897 (* 0.0454545 = 4.58622e-05 loss)
I0405 14:38:11.971559 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000928249 (* 0.0454545 = 4.21932e-05 loss)
I0405 14:38:11.971585 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000965613 (* 0.0454545 = 4.38915e-05 loss)
I0405 14:38:11.971611 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000913082 (* 0.0454545 = 4.15037e-05 loss)
I0405 14:38:11.971632 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:38:11.971653 29564 solver.cpp:245]     Train net output #45: total_confidence = 5.94193e-07
I0405 14:38:11.971678 29564 sgd_solver.cpp:106] Iteration 6500, lr = 0.009935
I0405 14:42:01.002714 29564 solver.cpp:229] Iteration 7000, loss = 1.06486
I0405 14:42:01.002931 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 14:42:01.002962 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 14:42:01.002986 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 14:42:01.003012 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.21875
I0405 14:42:01.003036 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 14:42:01.003058 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 14:42:01.003078 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 14:42:01.003103 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 14:42:01.003123 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 14:42:01.003145 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 14:42:01.003170 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:42:01.003190 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:42:01.003211 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:42:01.003232 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:42:01.003252 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:42:01.003273 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:42:01.003293 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:42:01.003314 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:42:01.003335 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:42:01.003357 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:42:01.003378 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:42:01.003401 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:42:01.003428 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.50138 (* 0.0454545 = 0.159154 loss)
I0405 14:42:01.003456 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.77238 (* 0.0454545 = 0.171472 loss)
I0405 14:42:01.003484 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.85702 (* 0.0454545 = 0.175319 loss)
I0405 14:42:01.003509 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.65472 (* 0.0454545 = 0.166123 loss)
I0405 14:42:01.003536 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.55041 (* 0.0454545 = 0.161382 loss)
I0405 14:42:01.003562 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.0902 (* 0.0454545 = 0.140464 loss)
I0405 14:42:01.003588 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.68572 (* 0.0454545 = 0.0766236 loss)
I0405 14:42:01.003612 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 1.20901 (* 0.0454545 = 0.0549549 loss)
I0405 14:42:01.003636 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.676928 (* 0.0454545 = 0.0307695 loss)
I0405 14:42:01.003661 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.270819 (* 0.0454545 = 0.0123099 loss)
I0405 14:42:01.003686 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000182218 (* 0.0454545 = 8.28263e-06 loss)
I0405 14:42:01.003713 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000191501 (* 0.0454545 = 8.70458e-06 loss)
I0405 14:42:01.003744 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000219447 (* 0.0454545 = 9.97485e-06 loss)
I0405 14:42:01.003772 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000180597 (* 0.0454545 = 8.20893e-06 loss)
I0405 14:42:01.003799 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000185951 (* 0.0454545 = 8.45232e-06 loss)
I0405 14:42:01.003839 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000171381 (* 0.0454545 = 7.79003e-06 loss)
I0405 14:42:01.003866 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.00020623 (* 0.0454545 = 9.37411e-06 loss)
I0405 14:42:01.003913 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000164187 (* 0.0454545 = 7.46307e-06 loss)
I0405 14:42:01.003939 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000180207 (* 0.0454545 = 8.19123e-06 loss)
I0405 14:42:01.003964 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000176306 (* 0.0454545 = 8.01392e-06 loss)
I0405 14:42:01.003988 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000171182 (* 0.0454545 = 7.78099e-06 loss)
I0405 14:42:01.004011 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.00015834 (* 0.0454545 = 7.19726e-06 loss)
I0405 14:42:01.004034 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:42:01.004055 29564 solver.cpp:245]     Train net output #45: total_confidence = 3.44935e-05
I0405 14:42:01.004101 29564 sgd_solver.cpp:106] Iteration 7000, lr = 0.00993
I0405 14:45:49.967234 29564 solver.cpp:229] Iteration 7500, loss = 1.04539
I0405 14:45:49.967371 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 14:45:49.967392 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 14:45:49.967406 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 14:45:49.967417 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.03125
I0405 14:45:49.967429 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.15625
I0405 14:45:49.967440 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 14:45:49.967453 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.59375
I0405 14:45:49.967464 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 14:45:49.967475 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 14:45:49.967488 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 14:45:49.967499 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:45:49.967510 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:45:49.967521 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:45:49.967533 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:45:49.967547 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:45:49.967566 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:45:49.967581 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:45:49.967592 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:45:49.967603 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:45:49.967614 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:45:49.967625 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:45:49.967638 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:45:49.967653 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.93853 (* 0.0454545 = 0.133569 loss)
I0405 14:45:49.967666 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.63647 (* 0.0454545 = 0.165294 loss)
I0405 14:45:49.967680 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.52994 (* 0.0454545 = 0.160452 loss)
I0405 14:45:49.967694 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.46868 (* 0.0454545 = 0.157667 loss)
I0405 14:45:49.967708 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.20043 (* 0.0454545 = 0.145474 loss)
I0405 14:45:49.967721 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.01628 (* 0.0454545 = 0.137104 loss)
I0405 14:45:49.967736 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.86096 (* 0.0454545 = 0.0845893 loss)
I0405 14:45:49.967749 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.86129 (* 0.0454545 = 0.0391495 loss)
I0405 14:45:49.967762 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0292927 (* 0.0454545 = 0.00133149 loss)
I0405 14:45:49.967777 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0122027 (* 0.0454545 = 0.00055467 loss)
I0405 14:45:49.967790 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000147883 (* 0.0454545 = 6.72197e-06 loss)
I0405 14:45:49.967806 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000150257 (* 0.0454545 = 6.82987e-06 loss)
I0405 14:45:49.967821 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000166523 (* 0.0454545 = 7.56925e-06 loss)
I0405 14:45:49.967835 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000142367 (* 0.0454545 = 6.47122e-06 loss)
I0405 14:45:49.967849 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000142791 (* 0.0454545 = 6.49052e-06 loss)
I0405 14:45:49.967864 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000135645 (* 0.0454545 = 6.16567e-06 loss)
I0405 14:45:49.967877 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000155415 (* 0.0454545 = 7.06431e-06 loss)
I0405 14:45:49.967910 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000131075 (* 0.0454545 = 5.95794e-06 loss)
I0405 14:45:49.967924 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000135429 (* 0.0454545 = 6.15585e-06 loss)
I0405 14:45:49.967939 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000138298 (* 0.0454545 = 6.28628e-06 loss)
I0405 14:45:49.967953 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000135615 (* 0.0454545 = 6.16432e-06 loss)
I0405 14:45:49.967967 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000129522 (* 0.0454545 = 5.88738e-06 loss)
I0405 14:45:49.967979 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:45:49.967990 29564 solver.cpp:245]     Train net output #45: total_confidence = 4.86342e-06
I0405 14:45:49.968008 29564 sgd_solver.cpp:106] Iteration 7500, lr = 0.009925
I0405 14:49:39.144682 29564 solver.cpp:229] Iteration 8000, loss = 1.03291
I0405 14:49:39.144845 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.125
I0405 14:49:39.144866 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 14:49:39.144878 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 14:49:39.144891 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.21875
I0405 14:49:39.144903 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.34375
I0405 14:49:39.144917 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 14:49:39.144928 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 14:49:39.144939 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.96875
I0405 14:49:39.144951 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 14:49:39.144963 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 14:49:39.144974 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:49:39.144985 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:49:39.144997 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:49:39.145009 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:49:39.145020 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:49:39.145031 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:49:39.145042 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:49:39.145053 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:49:39.145069 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:49:39.145081 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:49:39.145092 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:49:39.145103 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:49:39.145120 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.18884 (* 0.0454545 = 0.144947 loss)
I0405 14:49:39.145134 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.51973 (* 0.0454545 = 0.159988 loss)
I0405 14:49:39.145148 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.42459 (* 0.0454545 = 0.155663 loss)
I0405 14:49:39.145162 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.36213 (* 0.0454545 = 0.152824 loss)
I0405 14:49:39.145176 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.77853 (* 0.0454545 = 0.126297 loss)
I0405 14:49:39.145190 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.58632 (* 0.0454545 = 0.11756 loss)
I0405 14:49:39.145205 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.20776 (* 0.0454545 = 0.0548981 loss)
I0405 14:49:39.145218 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.281023 (* 0.0454545 = 0.0127738 loss)
I0405 14:49:39.145232 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0530355 (* 0.0454545 = 0.00241071 loss)
I0405 14:49:39.145247 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0244706 (* 0.0454545 = 0.0011123 loss)
I0405 14:49:39.145262 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000430379 (* 0.0454545 = 1.95627e-05 loss)
I0405 14:49:39.145277 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000435025 (* 0.0454545 = 1.97739e-05 loss)
I0405 14:49:39.145292 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000459537 (* 0.0454545 = 2.0888e-05 loss)
I0405 14:49:39.145305 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.00041404 (* 0.0454545 = 1.882e-05 loss)
I0405 14:49:39.145320 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000408769 (* 0.0454545 = 1.85804e-05 loss)
I0405 14:49:39.145334 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.00038989 (* 0.0454545 = 1.77223e-05 loss)
I0405 14:49:39.145349 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000442837 (* 0.0454545 = 2.01289e-05 loss)
I0405 14:49:39.145380 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000387808 (* 0.0454545 = 1.76276e-05 loss)
I0405 14:49:39.145395 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000402898 (* 0.0454545 = 1.83136e-05 loss)
I0405 14:49:39.145408 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000408161 (* 0.0454545 = 1.85528e-05 loss)
I0405 14:49:39.145422 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000398607 (* 0.0454545 = 1.81185e-05 loss)
I0405 14:49:39.145437 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000378277 (* 0.0454545 = 1.71944e-05 loss)
I0405 14:49:39.145448 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:49:39.145459 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000232831
I0405 14:49:39.145474 29564 sgd_solver.cpp:106] Iteration 8000, lr = 0.00992
I0405 14:53:28.135673 29564 solver.cpp:229] Iteration 8500, loss = 1.03525
I0405 14:53:28.135804 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 14:53:28.135824 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 14:53:28.135838 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0
I0405 14:53:28.135849 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 14:53:28.135862 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.125
I0405 14:53:28.135874 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.21875
I0405 14:53:28.135886 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 14:53:28.135898 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 14:53:28.135910 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 14:53:28.135921 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 14:53:28.135936 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:53:28.135948 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:53:28.135959 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:53:28.135972 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:53:28.135982 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:53:28.135993 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:53:28.136005 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:53:28.136016 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:53:28.136028 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:53:28.136039 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:53:28.136050 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:53:28.136061 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:53:28.136099 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.51504 (* 0.0454545 = 0.159774 loss)
I0405 14:53:28.136116 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.83976 (* 0.0454545 = 0.174534 loss)
I0405 14:53:28.136129 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.80233 (* 0.0454545 = 0.172833 loss)
I0405 14:53:28.136144 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.75333 (* 0.0454545 = 0.170606 loss)
I0405 14:53:28.136158 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.45564 (* 0.0454545 = 0.157074 loss)
I0405 14:53:28.136173 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.3687 (* 0.0454545 = 0.153123 loss)
I0405 14:53:28.136186 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.71337 (* 0.0454545 = 0.0778804 loss)
I0405 14:53:28.136200 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.913805 (* 0.0454545 = 0.0415366 loss)
I0405 14:53:28.136214 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.429051 (* 0.0454545 = 0.0195023 loss)
I0405 14:53:28.136229 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.465603 (* 0.0454545 = 0.0211638 loss)
I0405 14:53:28.136243 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000374164 (* 0.0454545 = 1.70074e-05 loss)
I0405 14:53:28.136258 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000380929 (* 0.0454545 = 1.7315e-05 loss)
I0405 14:53:28.136272 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000404282 (* 0.0454545 = 1.83765e-05 loss)
I0405 14:53:28.136286 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000352934 (* 0.0454545 = 1.60424e-05 loss)
I0405 14:53:28.136301 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000363291 (* 0.0454545 = 1.65132e-05 loss)
I0405 14:53:28.136314 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000340369 (* 0.0454545 = 1.54713e-05 loss)
I0405 14:53:28.136328 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000386937 (* 0.0454545 = 1.7588e-05 loss)
I0405 14:53:28.136360 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000328752 (* 0.0454545 = 1.49433e-05 loss)
I0405 14:53:28.136376 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000359173 (* 0.0454545 = 1.63261e-05 loss)
I0405 14:53:28.136390 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000369593 (* 0.0454545 = 1.67997e-05 loss)
I0405 14:53:28.136404 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000346345 (* 0.0454545 = 1.57429e-05 loss)
I0405 14:53:28.136418 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000319694 (* 0.0454545 = 1.45316e-05 loss)
I0405 14:53:28.136430 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:53:28.136441 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000106176
I0405 14:53:28.136456 29564 sgd_solver.cpp:106] Iteration 8500, lr = 0.009915
I0405 14:57:17.222748 29564 solver.cpp:229] Iteration 9000, loss = 1.02918
I0405 14:57:17.222867 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.03125
I0405 14:57:17.222887 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 14:57:17.222898 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 14:57:17.222910 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.03125
I0405 14:57:17.222923 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.125
I0405 14:57:17.222934 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.28125
I0405 14:57:17.222946 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.625
I0405 14:57:17.222959 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.78125
I0405 14:57:17.222970 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 14:57:17.222982 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 14:57:17.222995 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 14:57:17.223006 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 14:57:17.223017 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 14:57:17.223028 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 14:57:17.223040 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 14:57:17.223052 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 14:57:17.223062 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 14:57:17.223074 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 14:57:17.223085 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 14:57:17.223096 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 14:57:17.223107 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 14:57:17.223119 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 14:57:17.223134 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.23176 (* 0.0454545 = 0.146898 loss)
I0405 14:57:17.223148 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.48778 (* 0.0454545 = 0.158536 loss)
I0405 14:57:17.223162 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.47197 (* 0.0454545 = 0.157817 loss)
I0405 14:57:17.223176 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.53846 (* 0.0454545 = 0.160839 loss)
I0405 14:57:17.223191 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.36119 (* 0.0454545 = 0.152781 loss)
I0405 14:57:17.223204 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.02256 (* 0.0454545 = 0.137389 loss)
I0405 14:57:17.223218 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.84431 (* 0.0454545 = 0.0838323 loss)
I0405 14:57:17.223232 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 1.09816 (* 0.0454545 = 0.0499164 loss)
I0405 14:57:17.223247 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.43933 (* 0.0454545 = 0.0199696 loss)
I0405 14:57:17.223259 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.222654 (* 0.0454545 = 0.0101206 loss)
I0405 14:57:17.223274 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000456803 (* 0.0454545 = 2.07638e-05 loss)
I0405 14:57:17.223289 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000458315 (* 0.0454545 = 2.08325e-05 loss)
I0405 14:57:17.223302 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000480255 (* 0.0454545 = 2.18298e-05 loss)
I0405 14:57:17.223316 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.00043189 (* 0.0454545 = 1.96314e-05 loss)
I0405 14:57:17.223330 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000438099 (* 0.0454545 = 1.99136e-05 loss)
I0405 14:57:17.223345 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000412502 (* 0.0454545 = 1.87501e-05 loss)
I0405 14:57:17.223358 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.00045832 (* 0.0454545 = 2.08327e-05 loss)
I0405 14:57:17.223389 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000401143 (* 0.0454545 = 1.82338e-05 loss)
I0405 14:57:17.223404 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000436926 (* 0.0454545 = 1.98603e-05 loss)
I0405 14:57:17.223419 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000443674 (* 0.0454545 = 2.0167e-05 loss)
I0405 14:57:17.223433 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000415547 (* 0.0454545 = 1.88885e-05 loss)
I0405 14:57:17.223448 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000391956 (* 0.0454545 = 1.78162e-05 loss)
I0405 14:57:17.223459 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 14:57:17.223471 29564 solver.cpp:245]     Train net output #45: total_confidence = 9.35114e-05
I0405 14:57:17.223484 29564 sgd_solver.cpp:106] Iteration 9000, lr = 0.00991
I0405 15:01:06.383548 29564 solver.cpp:229] Iteration 9500, loss = 1.02821
I0405 15:01:06.383687 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 15:01:06.383708 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 15:01:06.383719 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 15:01:06.383733 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 15:01:06.383744 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.15625
I0405 15:01:06.383756 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 15:01:06.383769 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 15:01:06.383780 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 15:01:06.383792 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.875
I0405 15:01:06.383803 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:01:06.383816 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:01:06.383826 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:01:06.383838 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:01:06.383852 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:01:06.383865 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:01:06.383877 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:01:06.383888 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:01:06.383900 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:01:06.383911 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:01:06.383924 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:01:06.383934 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:01:06.383945 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:01:06.383960 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.37391 (* 0.0454545 = 0.15336 loss)
I0405 15:01:06.383975 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.70318 (* 0.0454545 = 0.168327 loss)
I0405 15:01:06.383990 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.57609 (* 0.0454545 = 0.162549 loss)
I0405 15:01:06.384003 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.66453 (* 0.0454545 = 0.16657 loss)
I0405 15:01:06.384017 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.57231 (* 0.0454545 = 0.162378 loss)
I0405 15:01:06.384032 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.60585 (* 0.0454545 = 0.118448 loss)
I0405 15:01:06.384071 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.58504 (* 0.0454545 = 0.0720474 loss)
I0405 15:01:06.384088 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.627117 (* 0.0454545 = 0.0285053 loss)
I0405 15:01:06.384102 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.657052 (* 0.0454545 = 0.029866 loss)
I0405 15:01:06.384117 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0188284 (* 0.0454545 = 0.000855837 loss)
I0405 15:01:06.384131 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 9.69694e-05 (* 0.0454545 = 4.4077e-06 loss)
I0405 15:01:06.384145 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 9.50263e-05 (* 0.0454545 = 4.31938e-06 loss)
I0405 15:01:06.384160 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 9.83108e-05 (* 0.0454545 = 4.46867e-06 loss)
I0405 15:01:06.384173 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 9.09111e-05 (* 0.0454545 = 4.13232e-06 loss)
I0405 15:01:06.384187 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 9.23381e-05 (* 0.0454545 = 4.19718e-06 loss)
I0405 15:01:06.384202 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 9.11048e-05 (* 0.0454545 = 4.14113e-06 loss)
I0405 15:01:06.384215 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 9.45104e-05 (* 0.0454545 = 4.29593e-06 loss)
I0405 15:01:06.384246 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 9.15947e-05 (* 0.0454545 = 4.1634e-06 loss)
I0405 15:01:06.384263 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 9.07863e-05 (* 0.0454545 = 4.12665e-06 loss)
I0405 15:01:06.384279 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 9.30738e-05 (* 0.0454545 = 4.23063e-06 loss)
I0405 15:01:06.384294 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 8.72039e-05 (* 0.0454545 = 3.96382e-06 loss)
I0405 15:01:06.384308 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 8.76585e-05 (* 0.0454545 = 3.98448e-06 loss)
I0405 15:01:06.384320 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:01:06.384331 29564 solver.cpp:245]     Train net output #45: total_confidence = 4.51941e-05
I0405 15:01:06.384346 29564 sgd_solver.cpp:106] Iteration 9500, lr = 0.009905
I0405 15:04:55.430845 29564 solver.cpp:338] Iteration 10000, Testing net (#0)
I0405 15:05:05.741375 29564 solver.cpp:393] Test loss: 1.0075
I0405 15:05:05.741425 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.1
I0405 15:05:05.741451 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.027
I0405 15:05:05.741477 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.073
I0405 15:05:05.741498 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.078
I0405 15:05:05.741520 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.195
I0405 15:05:05.741544 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.502
I0405 15:05:05.741569 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.894
I0405 15:05:05.741590 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 15:05:05.741611 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 15:05:05.741642 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 15:05:05.741663 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 15:05:05.741684 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 15:05:05.741704 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 15:05:05.741724 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 15:05:05.741745 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 15:05:05.741765 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 15:05:05.741785 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 15:05:05.741806 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 15:05:05.741825 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 15:05:05.741844 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 15:05:05.741865 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 15:05:05.741885 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 15:05:05.741914 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 3.72013 (* 0.0454545 = 0.169097 loss)
I0405 15:05:05.741945 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 3.80327 (* 0.0454545 = 0.172876 loss)
I0405 15:05:05.741981 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 3.71799 (* 0.0454545 = 0.169 loss)
I0405 15:05:05.742008 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 3.60808 (* 0.0454545 = 0.164004 loss)
I0405 15:05:05.742033 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 3.49553 (* 0.0454545 = 0.158888 loss)
I0405 15:05:05.742059 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 2.57541 (* 0.0454545 = 0.117064 loss)
I0405 15:05:05.742089 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.864105 (* 0.0454545 = 0.0392775 loss)
I0405 15:05:05.742115 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.283985 (* 0.0454545 = 0.0129084 loss)
I0405 15:05:05.742141 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0671798 (* 0.0454545 = 0.00305363 loss)
I0405 15:05:05.742166 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0273463 (* 0.0454545 = 0.00124301 loss)
I0405 15:05:05.742192 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 0.000183531 (* 0.0454545 = 8.34232e-06 loss)
I0405 15:05:05.742219 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 0.000170689 (* 0.0454545 = 7.75858e-06 loss)
I0405 15:05:05.742245 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 0.000169147 (* 0.0454545 = 7.68849e-06 loss)
I0405 15:05:05.742275 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 0.000169928 (* 0.0454545 = 7.724e-06 loss)
I0405 15:05:05.742302 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 0.000169319 (* 0.0454545 = 7.69633e-06 loss)
I0405 15:05:05.742328 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 0.000168781 (* 0.0454545 = 7.67186e-06 loss)
I0405 15:05:05.742353 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 0.000164697 (* 0.0454545 = 7.48621e-06 loss)
I0405 15:05:05.742413 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 0.000172502 (* 0.0454545 = 7.84102e-06 loss)
I0405 15:05:05.742441 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 0.000167187 (* 0.0454545 = 7.59941e-06 loss)
I0405 15:05:05.742466 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 0.000169053 (* 0.0454545 = 7.68424e-06 loss)
I0405 15:05:05.742493 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 0.000159877 (* 0.0454545 = 7.26714e-06 loss)
I0405 15:05:05.742518 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 0.000166786 (* 0.0454545 = 7.58118e-06 loss)
I0405 15:05:05.742539 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0
I0405 15:05:05.742559 29564 solver.cpp:406]     Test net output #45: total_confidence = 9.05358e-05
I0405 15:05:05.857699 29564 solver.cpp:229] Iteration 10000, loss = 1.02236
I0405 15:05:05.857741 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 15:05:05.857769 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 15:05:05.857795 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 15:05:05.857817 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0
I0405 15:05:05.857839 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.125
I0405 15:05:05.857863 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 15:05:05.857888 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 15:05:05.857911 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 15:05:05.857944 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 15:05:05.857966 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:05:05.857988 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:05:05.858009 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:05:05.858031 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:05:05.858052 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:05:05.858072 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:05:05.858093 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:05:05.858114 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:05:05.858134 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:05:05.858155 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:05:05.858175 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:05:05.858196 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:05:05.858218 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:05:05.858249 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.13333 (* 0.0454545 = 0.142424 loss)
I0405 15:05:05.858286 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.48875 (* 0.0454545 = 0.158579 loss)
I0405 15:05:05.858314 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.24667 (* 0.0454545 = 0.147576 loss)
I0405 15:05:05.858340 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.58229 (* 0.0454545 = 0.162831 loss)
I0405 15:05:05.858366 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.24304 (* 0.0454545 = 0.147411 loss)
I0405 15:05:05.858392 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.97312 (* 0.0454545 = 0.135142 loss)
I0405 15:05:05.858417 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.50825 (* 0.0454545 = 0.0685566 loss)
I0405 15:05:05.858443 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.822252 (* 0.0454545 = 0.0373751 loss)
I0405 15:05:05.858470 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.448315 (* 0.0454545 = 0.020378 loss)
I0405 15:05:05.858496 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0124729 (* 0.0454545 = 0.000566952 loss)
I0405 15:05:05.858543 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 8.46498e-05 (* 0.0454545 = 3.84772e-06 loss)
I0405 15:05:05.858572 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 8.08526e-05 (* 0.0454545 = 3.67512e-06 loss)
I0405 15:05:05.858599 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 7.96904e-05 (* 0.0454545 = 3.62229e-06 loss)
I0405 15:05:05.858625 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 7.7406e-05 (* 0.0454545 = 3.51846e-06 loss)
I0405 15:05:05.858651 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 7.84938e-05 (* 0.0454545 = 3.5679e-06 loss)
I0405 15:05:05.858680 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 7.69289e-05 (* 0.0454545 = 3.49677e-06 loss)
I0405 15:05:05.858710 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.7626e-05 (* 0.0454545 = 3.52845e-06 loss)
I0405 15:05:05.858737 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 7.74397e-05 (* 0.0454545 = 3.51998e-06 loss)
I0405 15:05:05.858764 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.95745e-05 (* 0.0454545 = 3.61702e-06 loss)
I0405 15:05:05.858793 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 7.78716e-05 (* 0.0454545 = 3.53962e-06 loss)
I0405 15:05:05.858819 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.43264e-05 (* 0.0454545 = 3.37847e-06 loss)
I0405 15:05:05.858844 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 7.62214e-05 (* 0.0454545 = 3.46461e-06 loss)
I0405 15:05:05.858866 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:05:05.858888 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000202657
I0405 15:05:05.858912 29564 sgd_solver.cpp:106] Iteration 10000, lr = 0.0099
I0405 15:08:54.654465 29564 solver.cpp:229] Iteration 10500, loss = 1.01629
I0405 15:08:54.654669 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 15:08:54.654690 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 15:08:54.654702 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 15:08:54.654714 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 15:08:54.654726 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.125
I0405 15:08:54.654738 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.3125
I0405 15:08:54.654749 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.625
I0405 15:08:54.654762 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 15:08:54.654773 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 15:08:54.654784 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:08:54.654798 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:08:54.654810 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:08:54.654822 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:08:54.654834 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:08:54.654845 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:08:54.654856 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:08:54.654868 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:08:54.654880 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:08:54.654891 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:08:54.654902 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:08:54.654913 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:08:54.654924 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:08:54.654940 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.49286 (* 0.0454545 = 0.158767 loss)
I0405 15:08:54.654954 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.73455 (* 0.0454545 = 0.169752 loss)
I0405 15:08:54.654968 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.48192 (* 0.0454545 = 0.158269 loss)
I0405 15:08:54.654981 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.81129 (* 0.0454545 = 0.17324 loss)
I0405 15:08:54.654995 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.56079 (* 0.0454545 = 0.161854 loss)
I0405 15:08:54.655009 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.98298 (* 0.0454545 = 0.13559 loss)
I0405 15:08:54.655024 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.86277 (* 0.0454545 = 0.0846716 loss)
I0405 15:08:54.655037 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.780141 (* 0.0454545 = 0.035461 loss)
I0405 15:08:54.655051 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.795189 (* 0.0454545 = 0.0361449 loss)
I0405 15:08:54.655066 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0202316 (* 0.0454545 = 0.000919618 loss)
I0405 15:08:54.655079 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000205494 (* 0.0454545 = 9.34064e-06 loss)
I0405 15:08:54.655097 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000188273 (* 0.0454545 = 8.55784e-06 loss)
I0405 15:08:54.655124 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000193327 (* 0.0454545 = 8.78759e-06 loss)
I0405 15:08:54.655154 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000191877 (* 0.0454545 = 8.72169e-06 loss)
I0405 15:08:54.655184 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.00019005 (* 0.0454545 = 8.63865e-06 loss)
I0405 15:08:54.655210 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000183404 (* 0.0454545 = 8.33657e-06 loss)
I0405 15:08:54.655226 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000193621 (* 0.0454545 = 8.80093e-06 loss)
I0405 15:08:54.655254 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000200076 (* 0.0454545 = 9.09438e-06 loss)
I0405 15:08:54.655269 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000184226 (* 0.0454545 = 8.37389e-06 loss)
I0405 15:08:54.655283 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000180686 (* 0.0454545 = 8.21301e-06 loss)
I0405 15:08:54.655297 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000179167 (* 0.0454545 = 8.14396e-06 loss)
I0405 15:08:54.655311 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000195066 (* 0.0454545 = 8.86662e-06 loss)
I0405 15:08:54.655323 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:08:54.655334 29564 solver.cpp:245]     Train net output #45: total_confidence = 6.28171e-05
I0405 15:08:54.655349 29564 sgd_solver.cpp:106] Iteration 10500, lr = 0.009895
I0405 15:12:44.033658 29564 solver.cpp:229] Iteration 11000, loss = 1.00841
I0405 15:12:44.033792 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 15:12:44.033812 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 15:12:44.033824 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 15:12:44.033836 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 15:12:44.033849 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 15:12:44.033860 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 15:12:44.033872 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 15:12:44.033884 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 15:12:44.033895 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 15:12:44.033906 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:12:44.033918 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:12:44.033929 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:12:44.033942 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:12:44.033954 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:12:44.033965 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:12:44.033977 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:12:44.033988 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:12:44.033999 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:12:44.034010 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:12:44.034023 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:12:44.034034 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:12:44.034044 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:12:44.034060 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.09849 (* 0.0454545 = 0.14084 loss)
I0405 15:12:44.034073 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.21474 (* 0.0454545 = 0.146125 loss)
I0405 15:12:44.034087 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.33881 (* 0.0454545 = 0.151764 loss)
I0405 15:12:44.034101 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.29397 (* 0.0454545 = 0.149726 loss)
I0405 15:12:44.034114 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.78256 (* 0.0454545 = 0.12648 loss)
I0405 15:12:44.034128 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.16907 (* 0.0454545 = 0.0985942 loss)
I0405 15:12:44.034144 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.40291 (* 0.0454545 = 0.0637686 loss)
I0405 15:12:44.034158 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.966931 (* 0.0454545 = 0.0439514 loss)
I0405 15:12:44.034173 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0370055 (* 0.0454545 = 0.00168207 loss)
I0405 15:12:44.034188 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0104566 (* 0.0454545 = 0.000475301 loss)
I0405 15:12:44.034203 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 9.29196e-05 (* 0.0454545 = 4.22362e-06 loss)
I0405 15:12:44.034217 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 8.37384e-05 (* 0.0454545 = 3.80629e-06 loss)
I0405 15:12:44.034232 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 8.72257e-05 (* 0.0454545 = 3.9648e-06 loss)
I0405 15:12:44.034246 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 8.78976e-05 (* 0.0454545 = 3.99535e-06 loss)
I0405 15:12:44.034260 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 8.59833e-05 (* 0.0454545 = 3.90833e-06 loss)
I0405 15:12:44.034274 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 8.44946e-05 (* 0.0454545 = 3.84066e-06 loss)
I0405 15:12:44.034288 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 9.02568e-05 (* 0.0454545 = 4.10258e-06 loss)
I0405 15:12:44.034320 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 9.11227e-05 (* 0.0454545 = 4.14194e-06 loss)
I0405 15:12:44.034335 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 8.17422e-05 (* 0.0454545 = 3.71555e-06 loss)
I0405 15:12:44.034349 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 7.99799e-05 (* 0.0454545 = 3.63545e-06 loss)
I0405 15:12:44.034363 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 8.21064e-05 (* 0.0454545 = 3.73211e-06 loss)
I0405 15:12:44.034378 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 8.99652e-05 (* 0.0454545 = 4.08933e-06 loss)
I0405 15:12:44.034389 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:12:44.034400 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000641852
I0405 15:12:44.034415 29564 sgd_solver.cpp:106] Iteration 11000, lr = 0.00989
I0405 15:16:34.101570 29564 solver.cpp:229] Iteration 11500, loss = 0.998349
I0405 15:16:34.101681 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.125
I0405 15:16:34.101701 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 15:16:34.101714 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 15:16:34.101727 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 15:16:34.101738 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 15:16:34.101750 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.28125
I0405 15:16:34.101763 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.5625
I0405 15:16:34.101774 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 15:16:34.101786 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 15:16:34.101799 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:16:34.101810 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:16:34.101821 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:16:34.101832 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:16:34.101845 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:16:34.101855 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:16:34.101867 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:16:34.101878 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:16:34.101889 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:16:34.101900 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:16:34.101912 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:16:34.101923 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:16:34.101934 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:16:34.101949 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.96876 (* 0.0454545 = 0.134944 loss)
I0405 15:16:34.101964 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.32421 (* 0.0454545 = 0.151101 loss)
I0405 15:16:34.101979 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.48744 (* 0.0454545 = 0.15852 loss)
I0405 15:16:34.101992 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.35627 (* 0.0454545 = 0.152558 loss)
I0405 15:16:34.102005 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.07704 (* 0.0454545 = 0.139866 loss)
I0405 15:16:34.102021 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.80415 (* 0.0454545 = 0.127461 loss)
I0405 15:16:34.102036 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 2.07907 (* 0.0454545 = 0.094503 loss)
I0405 15:16:34.102051 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.488773 (* 0.0454545 = 0.022217 loss)
I0405 15:16:34.102064 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.463473 (* 0.0454545 = 0.021067 loss)
I0405 15:16:34.102078 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0152196 (* 0.0454545 = 0.000691799 loss)
I0405 15:16:34.102092 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000494962 (* 0.0454545 = 2.24983e-05 loss)
I0405 15:16:34.102108 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000424787 (* 0.0454545 = 1.93085e-05 loss)
I0405 15:16:34.102121 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000469754 (* 0.0454545 = 2.13525e-05 loss)
I0405 15:16:34.102135 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000467933 (* 0.0454545 = 2.12697e-05 loss)
I0405 15:16:34.102150 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000475336 (* 0.0454545 = 2.16062e-05 loss)
I0405 15:16:34.102164 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000474259 (* 0.0454545 = 2.15572e-05 loss)
I0405 15:16:34.102179 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000503119 (* 0.0454545 = 2.28691e-05 loss)
I0405 15:16:34.102208 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000520651 (* 0.0454545 = 2.36659e-05 loss)
I0405 15:16:34.102223 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000412382 (* 0.0454545 = 1.87446e-05 loss)
I0405 15:16:34.102237 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00045835 (* 0.0454545 = 2.08341e-05 loss)
I0405 15:16:34.102252 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000469456 (* 0.0454545 = 2.13389e-05 loss)
I0405 15:16:34.102267 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000487324 (* 0.0454545 = 2.21511e-05 loss)
I0405 15:16:34.102278 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0.03125
I0405 15:16:34.102293 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000100997
I0405 15:16:34.102308 29564 sgd_solver.cpp:106] Iteration 11500, lr = 0.009885
I0405 15:20:23.409225 29564 solver.cpp:229] Iteration 12000, loss = 0.986678
I0405 15:20:23.409447 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.125
I0405 15:20:23.409468 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 15:20:23.409481 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 15:20:23.409493 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 15:20:23.409505 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 15:20:23.409518 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 15:20:23.409528 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 15:20:23.409540 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 15:20:23.409553 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 15:20:23.409564 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:20:23.409575 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:20:23.409587 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:20:23.409598 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:20:23.409610 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:20:23.409621 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:20:23.409632 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:20:23.409643 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:20:23.409656 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:20:23.409668 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:20:23.409682 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:20:23.409693 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:20:23.409703 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:20:23.409719 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.81407 (* 0.0454545 = 0.127912 loss)
I0405 15:20:23.409734 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.16292 (* 0.0454545 = 0.143769 loss)
I0405 15:20:23.409747 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.10058 (* 0.0454545 = 0.140935 loss)
I0405 15:20:23.409761 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.2681 (* 0.0454545 = 0.14855 loss)
I0405 15:20:23.409775 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.81658 (* 0.0454545 = 0.128027 loss)
I0405 15:20:23.409790 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.20855 (* 0.0454545 = 0.100389 loss)
I0405 15:20:23.409802 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.2382 (* 0.0454545 = 0.0562816 loss)
I0405 15:20:23.409816 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.367116 (* 0.0454545 = 0.0166871 loss)
I0405 15:20:23.409831 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.185957 (* 0.0454545 = 0.0084526 loss)
I0405 15:20:23.409844 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0198691 (* 0.0454545 = 0.000903142 loss)
I0405 15:20:23.409859 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000219626 (* 0.0454545 = 9.983e-06 loss)
I0405 15:20:23.409886 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000200402 (* 0.0454545 = 9.10916e-06 loss)
I0405 15:20:23.409904 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000208112 (* 0.0454545 = 9.45963e-06 loss)
I0405 15:20:23.409919 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000214567 (* 0.0454545 = 9.75304e-06 loss)
I0405 15:20:23.409932 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000224329 (* 0.0454545 = 1.01968e-05 loss)
I0405 15:20:23.409946 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.00020644 (* 0.0454545 = 9.38366e-06 loss)
I0405 15:20:23.409960 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000209925 (* 0.0454545 = 9.54206e-06 loss)
I0405 15:20:23.409989 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000222979 (* 0.0454545 = 1.01354e-05 loss)
I0405 15:20:23.410004 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000196523 (* 0.0454545 = 8.93286e-06 loss)
I0405 15:20:23.410018 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000202325 (* 0.0454545 = 9.1966e-06 loss)
I0405 15:20:23.410032 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000213421 (* 0.0454545 = 9.70095e-06 loss)
I0405 15:20:23.410046 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000212977 (* 0.0454545 = 9.68077e-06 loss)
I0405 15:20:23.410058 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:20:23.410069 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000241453
I0405 15:20:23.410082 29564 sgd_solver.cpp:106] Iteration 12000, lr = 0.00988
I0405 15:24:12.556998 29564 solver.cpp:229] Iteration 12500, loss = 0.978997
I0405 15:24:12.557185 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.21875
I0405 15:24:12.557209 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 15:24:12.557224 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 15:24:12.557235 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.21875
I0405 15:24:12.557247 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 15:24:12.557260 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 15:24:12.557271 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 15:24:12.557283 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 15:24:12.557296 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 15:24:12.557307 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:24:12.557317 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:24:12.557328 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:24:12.557342 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:24:12.557353 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:24:12.557366 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:24:12.557379 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:24:12.557389 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:24:12.557400 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:24:12.557415 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:24:12.557426 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:24:12.557437 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:24:12.557448 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:24:12.557464 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.06846 (* 0.0454545 = 0.139475 loss)
I0405 15:24:12.557478 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.39412 (* 0.0454545 = 0.154278 loss)
I0405 15:24:12.557492 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.17204 (* 0.0454545 = 0.144184 loss)
I0405 15:24:12.557507 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.05024 (* 0.0454545 = 0.138647 loss)
I0405 15:24:12.557520 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.79374 (* 0.0454545 = 0.126988 loss)
I0405 15:24:12.557534 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.44265 (* 0.0454545 = 0.11103 loss)
I0405 15:24:12.557548 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.4356 (* 0.0454545 = 0.0652544 loss)
I0405 15:24:12.557561 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.404275 (* 0.0454545 = 0.0183761 loss)
I0405 15:24:12.557575 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0335448 (* 0.0454545 = 0.00152476 loss)
I0405 15:24:12.557590 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00801603 (* 0.0454545 = 0.000364365 loss)
I0405 15:24:12.557603 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.00114645 (* 0.0454545 = 5.21113e-05 loss)
I0405 15:24:12.557617 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.00105995 (* 0.0454545 = 4.81795e-05 loss)
I0405 15:24:12.557631 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.0011106 (* 0.0454545 = 5.04816e-05 loss)
I0405 15:24:12.557646 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.00114577 (* 0.0454545 = 5.20807e-05 loss)
I0405 15:24:12.557659 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.00120919 (* 0.0454545 = 5.49632e-05 loss)
I0405 15:24:12.557673 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.0011777 (* 0.0454545 = 5.3532e-05 loss)
I0405 15:24:12.557687 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.00120167 (* 0.0454545 = 5.46212e-05 loss)
I0405 15:24:12.557721 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.00125392 (* 0.0454545 = 5.69965e-05 loss)
I0405 15:24:12.557737 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.00105116 (* 0.0454545 = 4.77798e-05 loss)
I0405 15:24:12.557751 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00113005 (* 0.0454545 = 5.13659e-05 loss)
I0405 15:24:12.557765 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.00119393 (* 0.0454545 = 5.42695e-05 loss)
I0405 15:24:12.557780 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.00119991 (* 0.0454545 = 5.45413e-05 loss)
I0405 15:24:12.557791 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:24:12.557802 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000119003
I0405 15:24:12.557816 29564 sgd_solver.cpp:106] Iteration 12500, lr = 0.009875
I0405 15:28:01.903882 29564 solver.cpp:229] Iteration 13000, loss = 0.970281
I0405 15:28:01.903991 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 15:28:01.904011 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 15:28:01.904023 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 15:28:01.904036 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 15:28:01.904047 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.09375
I0405 15:28:01.904059 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 15:28:01.904093 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 15:28:01.904108 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 15:28:01.904119 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 15:28:01.904131 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:28:01.904144 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:28:01.904155 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:28:01.904166 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:28:01.904177 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:28:01.904188 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:28:01.904199 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:28:01.904211 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:28:01.904222 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:28:01.904233 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:28:01.904244 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:28:01.904256 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:28:01.904268 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:28:01.904283 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.01448 (* 0.0454545 = 0.137022 loss)
I0405 15:28:01.904297 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.52362 (* 0.0454545 = 0.160165 loss)
I0405 15:28:01.904311 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.56213 (* 0.0454545 = 0.161915 loss)
I0405 15:28:01.904325 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.29844 (* 0.0454545 = 0.149929 loss)
I0405 15:28:01.904338 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.42235 (* 0.0454545 = 0.155561 loss)
I0405 15:28:01.904352 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.69271 (* 0.0454545 = 0.122396 loss)
I0405 15:28:01.904366 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.23441 (* 0.0454545 = 0.0561095 loss)
I0405 15:28:01.904381 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.71267 (* 0.0454545 = 0.0323941 loss)
I0405 15:28:01.904395 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.377211 (* 0.0454545 = 0.017146 loss)
I0405 15:28:01.904409 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0121667 (* 0.0454545 = 0.000553032 loss)
I0405 15:28:01.904424 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000190727 (* 0.0454545 = 8.66942e-06 loss)
I0405 15:28:01.904444 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.00017552 (* 0.0454545 = 7.97816e-06 loss)
I0405 15:28:01.904459 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000195114 (* 0.0454545 = 8.86882e-06 loss)
I0405 15:28:01.904474 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000184574 (* 0.0454545 = 8.38972e-06 loss)
I0405 15:28:01.904487 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.00019458 (* 0.0454545 = 8.84453e-06 loss)
I0405 15:28:01.904501 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000185565 (* 0.0454545 = 8.43478e-06 loss)
I0405 15:28:01.904515 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000202093 (* 0.0454545 = 9.18603e-06 loss)
I0405 15:28:01.904546 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.00022397 (* 0.0454545 = 1.01804e-05 loss)
I0405 15:28:01.904561 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000172388 (* 0.0454545 = 7.83582e-06 loss)
I0405 15:28:01.904575 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00019102 (* 0.0454545 = 8.68271e-06 loss)
I0405 15:28:01.904590 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.00019889 (* 0.0454545 = 9.04047e-06 loss)
I0405 15:28:01.904604 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000192621 (* 0.0454545 = 8.7555e-06 loss)
I0405 15:28:01.904616 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:28:01.904628 29564 solver.cpp:245]     Train net output #45: total_confidence = 1.64449e-05
I0405 15:28:01.904641 29564 sgd_solver.cpp:106] Iteration 13000, lr = 0.00987
I0405 15:31:51.148743 29564 solver.cpp:229] Iteration 13500, loss = 0.968372
I0405 15:31:51.148912 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 15:31:51.148933 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 15:31:51.148946 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 15:31:51.148958 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 15:31:51.148970 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 15:31:51.148983 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 15:31:51.148995 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 15:31:51.149006 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 15:31:51.149019 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 15:31:51.149030 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:31:51.149041 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:31:51.149052 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:31:51.149065 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:31:51.149075 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:31:51.149087 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:31:51.149098 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:31:51.149109 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:31:51.149121 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:31:51.149132 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:31:51.149143 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:31:51.149158 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:31:51.149168 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:31:51.149183 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.19739 (* 0.0454545 = 0.145336 loss)
I0405 15:31:51.149199 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.41129 (* 0.0454545 = 0.155059 loss)
I0405 15:31:51.149212 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.39526 (* 0.0454545 = 0.15433 loss)
I0405 15:31:51.149226 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.28771 (* 0.0454545 = 0.149441 loss)
I0405 15:31:51.149240 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.06547 (* 0.0454545 = 0.139339 loss)
I0405 15:31:51.149253 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.69593 (* 0.0454545 = 0.122542 loss)
I0405 15:31:51.149267 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.54274 (* 0.0454545 = 0.0701244 loss)
I0405 15:31:51.149281 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.619292 (* 0.0454545 = 0.0281496 loss)
I0405 15:31:51.149294 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.206153 (* 0.0454545 = 0.00937061 loss)
I0405 15:31:51.149312 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0227198 (* 0.0454545 = 0.00103272 loss)
I0405 15:31:51.149327 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000237608 (* 0.0454545 = 1.08004e-05 loss)
I0405 15:31:51.149341 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000226222 (* 0.0454545 = 1.02828e-05 loss)
I0405 15:31:51.149355 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000242498 (* 0.0454545 = 1.10226e-05 loss)
I0405 15:31:51.149369 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000227662 (* 0.0454545 = 1.03483e-05 loss)
I0405 15:31:51.149384 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000254229 (* 0.0454545 = 1.15559e-05 loss)
I0405 15:31:51.149397 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000227409 (* 0.0454545 = 1.03368e-05 loss)
I0405 15:31:51.149411 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000251617 (* 0.0454545 = 1.14371e-05 loss)
I0405 15:31:51.149442 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000277829 (* 0.0454545 = 1.26286e-05 loss)
I0405 15:31:51.149457 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000224198 (* 0.0454545 = 1.01908e-05 loss)
I0405 15:31:51.149471 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000245403 (* 0.0454545 = 1.11547e-05 loss)
I0405 15:31:51.149485 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000257812 (* 0.0454545 = 1.17187e-05 loss)
I0405 15:31:51.149499 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000222004 (* 0.0454545 = 1.00911e-05 loss)
I0405 15:31:51.149512 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:31:51.149523 29564 solver.cpp:245]     Train net output #45: total_confidence = 2.30686e-05
I0405 15:31:51.149539 29564 sgd_solver.cpp:106] Iteration 13500, lr = 0.009865
I0405 15:35:40.517137 29564 solver.cpp:229] Iteration 14000, loss = 0.964783
I0405 15:35:40.517906 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 15:35:40.517927 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 15:35:40.517940 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0
I0405 15:35:40.517952 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 15:35:40.517964 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 15:35:40.517979 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 15:35:40.517992 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 15:35:40.518003 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 15:35:40.518015 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 15:35:40.518026 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 15:35:40.518038 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:35:40.518049 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:35:40.518062 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:35:40.518074 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:35:40.518085 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:35:40.518095 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:35:40.518107 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:35:40.518118 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:35:40.518129 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:35:40.518141 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:35:40.518151 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:35:40.518163 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:35:40.518178 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.867 (* 0.0454545 = 0.130318 loss)
I0405 15:35:40.518193 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.43272 (* 0.0454545 = 0.156033 loss)
I0405 15:35:40.518206 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.45086 (* 0.0454545 = 0.156857 loss)
I0405 15:35:40.518220 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.42351 (* 0.0454545 = 0.155614 loss)
I0405 15:35:40.518234 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.92716 (* 0.0454545 = 0.133053 loss)
I0405 15:35:40.518247 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.20351 (* 0.0454545 = 0.100159 loss)
I0405 15:35:40.518261 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.70963 (* 0.0454545 = 0.0777105 loss)
I0405 15:35:40.518275 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.590396 (* 0.0454545 = 0.0268362 loss)
I0405 15:35:40.518290 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.173583 (* 0.0454545 = 0.00789015 loss)
I0405 15:35:40.518304 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.163411 (* 0.0454545 = 0.00742776 loss)
I0405 15:35:40.518332 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000260435 (* 0.0454545 = 1.18379e-05 loss)
I0405 15:35:40.518348 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000257327 (* 0.0454545 = 1.16967e-05 loss)
I0405 15:35:40.518362 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000293107 (* 0.0454545 = 1.3323e-05 loss)
I0405 15:35:40.518384 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000255537 (* 0.0454545 = 1.16153e-05 loss)
I0405 15:35:40.518399 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000317692 (* 0.0454545 = 1.44406e-05 loss)
I0405 15:35:40.518414 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.00026931 (* 0.0454545 = 1.22414e-05 loss)
I0405 15:35:40.518429 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000319809 (* 0.0454545 = 1.45368e-05 loss)
I0405 15:35:40.518458 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000359521 (* 0.0454545 = 1.63419e-05 loss)
I0405 15:35:40.518473 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000244609 (* 0.0454545 = 1.11186e-05 loss)
I0405 15:35:40.518487 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000287565 (* 0.0454545 = 1.30712e-05 loss)
I0405 15:35:40.518501 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000301931 (* 0.0454545 = 1.37241e-05 loss)
I0405 15:35:40.518515 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000285193 (* 0.0454545 = 1.29633e-05 loss)
I0405 15:35:40.518527 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:35:40.518539 29564 solver.cpp:245]     Train net output #45: total_confidence = 4.09905e-05
I0405 15:35:40.518553 29564 sgd_solver.cpp:106] Iteration 14000, lr = 0.00986
I0405 15:39:29.907860 29564 solver.cpp:229] Iteration 14500, loss = 0.956122
I0405 15:39:29.907977 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 15:39:29.907997 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 15:39:29.908010 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 15:39:29.908022 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 15:39:29.908035 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.125
I0405 15:39:29.908047 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.25
I0405 15:39:29.908058 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.5625
I0405 15:39:29.908089 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 15:39:29.908104 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 15:39:29.908116 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:39:29.908128 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:39:29.908139 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:39:29.908150 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:39:29.908161 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:39:29.908172 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:39:29.908185 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:39:29.908195 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:39:29.908206 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:39:29.908218 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:39:29.908229 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:39:29.908241 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:39:29.908252 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:39:29.908267 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.00454 (* 0.0454545 = 0.13657 loss)
I0405 15:39:29.908282 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.16422 (* 0.0454545 = 0.143828 loss)
I0405 15:39:29.908296 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.25037 (* 0.0454545 = 0.147744 loss)
I0405 15:39:29.908309 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.19414 (* 0.0454545 = 0.145188 loss)
I0405 15:39:29.908324 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.0732 (* 0.0454545 = 0.139691 loss)
I0405 15:39:29.908337 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.03845 (* 0.0454545 = 0.138112 loss)
I0405 15:39:29.908351 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 2.00171 (* 0.0454545 = 0.090987 loss)
I0405 15:39:29.908365 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.673431 (* 0.0454545 = 0.0306105 loss)
I0405 15:39:29.908380 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.227133 (* 0.0454545 = 0.0103242 loss)
I0405 15:39:29.908393 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0318445 (* 0.0454545 = 0.00144748 loss)
I0405 15:39:29.908407 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000211826 (* 0.0454545 = 9.62847e-06 loss)
I0405 15:39:29.908424 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000226547 (* 0.0454545 = 1.02976e-05 loss)
I0405 15:39:29.908439 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000240073 (* 0.0454545 = 1.09124e-05 loss)
I0405 15:39:29.908453 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000210788 (* 0.0454545 = 9.58128e-06 loss)
I0405 15:39:29.908468 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000265848 (* 0.0454545 = 1.2084e-05 loss)
I0405 15:39:29.908484 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000226057 (* 0.0454545 = 1.02753e-05 loss)
I0405 15:39:29.908499 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000255655 (* 0.0454545 = 1.16207e-05 loss)
I0405 15:39:29.908529 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000289294 (* 0.0454545 = 1.31497e-05 loss)
I0405 15:39:29.908545 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000211685 (* 0.0454545 = 9.62203e-06 loss)
I0405 15:39:29.908560 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000247822 (* 0.0454545 = 1.12647e-05 loss)
I0405 15:39:29.908573 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000264505 (* 0.0454545 = 1.2023e-05 loss)
I0405 15:39:29.908586 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000234314 (* 0.0454545 = 1.06506e-05 loss)
I0405 15:39:29.908598 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:39:29.908610 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000126747
I0405 15:39:29.908623 29564 sgd_solver.cpp:106] Iteration 14500, lr = 0.009855
I0405 15:43:19.124881 29564 solver.cpp:338] Iteration 15000, Testing net (#0)
I0405 15:43:29.426411 29564 solver.cpp:393] Test loss: 0.865717
I0405 15:43:29.426460 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.33
I0405 15:43:29.426476 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.066
I0405 15:43:29.426491 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.085
I0405 15:43:29.426502 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.118
I0405 15:43:29.426514 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.23
I0405 15:43:29.426525 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.502
I0405 15:43:29.426537 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.894
I0405 15:43:29.426550 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 15:43:29.426561 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 15:43:29.426573 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 15:43:29.426584 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 15:43:29.426596 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 15:43:29.426607 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 15:43:29.426619 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 15:43:29.426630 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 15:43:29.426640 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 15:43:29.426651 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 15:43:29.426662 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 15:43:29.426673 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 15:43:29.426684 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 15:43:29.426697 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 15:43:29.426707 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 15:43:29.426723 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 3.01031 (* 0.0454545 = 0.136832 loss)
I0405 15:43:29.426736 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 3.20372 (* 0.0454545 = 0.145624 loss)
I0405 15:43:29.426750 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 3.30385 (* 0.0454545 = 0.150175 loss)
I0405 15:43:29.426764 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 3.20563 (* 0.0454545 = 0.14571 loss)
I0405 15:43:29.426779 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 3.03907 (* 0.0454545 = 0.138139 loss)
I0405 15:43:29.426791 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 2.16085 (* 0.0454545 = 0.0982204 loss)
I0405 15:43:29.426805 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.804186 (* 0.0454545 = 0.0365539 loss)
I0405 15:43:29.426820 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.241588 (* 0.0454545 = 0.0109813 loss)
I0405 15:43:29.426833 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0508498 (* 0.0454545 = 0.00231136 loss)
I0405 15:43:29.426847 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0251716 (* 0.0454545 = 0.00114417 loss)
I0405 15:43:29.426863 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 4.43829e-05 (* 0.0454545 = 2.0174e-06 loss)
I0405 15:43:29.426877 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 4.8262e-05 (* 0.0454545 = 2.19373e-06 loss)
I0405 15:43:29.426892 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 4.23755e-05 (* 0.0454545 = 1.92616e-06 loss)
I0405 15:43:29.426905 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 4.64831e-05 (* 0.0454545 = 2.11287e-06 loss)
I0405 15:43:29.426919 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 4.92342e-05 (* 0.0454545 = 2.23792e-06 loss)
I0405 15:43:29.426934 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 4.47337e-05 (* 0.0454545 = 2.03335e-06 loss)
I0405 15:43:29.426947 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 4.07529e-05 (* 0.0454545 = 1.85241e-06 loss)
I0405 15:43:29.426995 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 4.73628e-05 (* 0.0454545 = 2.15285e-06 loss)
I0405 15:43:29.427009 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 4.88892e-05 (* 0.0454545 = 2.22224e-06 loss)
I0405 15:43:29.427023 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 4.5482e-05 (* 0.0454545 = 2.06737e-06 loss)
I0405 15:43:29.427037 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 4.73006e-05 (* 0.0454545 = 2.15003e-06 loss)
I0405 15:43:29.427052 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 4.20186e-05 (* 0.0454545 = 1.90994e-06 loss)
I0405 15:43:29.427063 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0.001
I0405 15:43:29.427075 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.000463517
I0405 15:43:29.542510 29564 solver.cpp:229] Iteration 15000, loss = 0.945895
I0405 15:43:29.542557 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 15:43:29.542572 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 15:43:29.542585 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 15:43:29.542598 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 15:43:29.542609 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 15:43:29.542621 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 15:43:29.542634 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 15:43:29.542645 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.96875
I0405 15:43:29.542657 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 15:43:29.542670 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:43:29.542681 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:43:29.542692 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:43:29.542703 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:43:29.542714 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:43:29.542726 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:43:29.542737 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:43:29.542749 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:43:29.542762 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:43:29.542773 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:43:29.542783 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:43:29.542798 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:43:29.542809 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:43:29.542824 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.24188 (* 0.0454545 = 0.147358 loss)
I0405 15:43:29.542837 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.57951 (* 0.0454545 = 0.162705 loss)
I0405 15:43:29.542851 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.36664 (* 0.0454545 = 0.153029 loss)
I0405 15:43:29.542865 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.54995 (* 0.0454545 = 0.161361 loss)
I0405 15:43:29.542879 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.97899 (* 0.0454545 = 0.135409 loss)
I0405 15:43:29.542893 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.39573 (* 0.0454545 = 0.108897 loss)
I0405 15:43:29.542906 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.17731 (* 0.0454545 = 0.0535139 loss)
I0405 15:43:29.542920 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.265543 (* 0.0454545 = 0.0120701 loss)
I0405 15:43:29.542934 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.151809 (* 0.0454545 = 0.00690042 loss)
I0405 15:43:29.542948 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0053711 (* 0.0454545 = 0.000244141 loss)
I0405 15:43:29.542984 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.28778e-05 (* 0.0454545 = 1.94899e-06 loss)
I0405 15:43:29.542999 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 4.48315e-05 (* 0.0454545 = 2.0378e-06 loss)
I0405 15:43:29.543014 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 4.28544e-05 (* 0.0454545 = 1.94793e-06 loss)
I0405 15:43:29.543027 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 4.28357e-05 (* 0.0454545 = 1.94708e-06 loss)
I0405 15:43:29.543041 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.70228e-05 (* 0.0454545 = 2.1374e-06 loss)
I0405 15:43:29.543056 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.35769e-05 (* 0.0454545 = 1.98077e-06 loss)
I0405 15:43:29.543069 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 4.23737e-05 (* 0.0454545 = 1.92608e-06 loss)
I0405 15:43:29.543083 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 4.96653e-05 (* 0.0454545 = 2.25752e-06 loss)
I0405 15:43:29.543097 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.2854e-05 (* 0.0454545 = 1.94791e-06 loss)
I0405 15:43:29.543112 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.55721e-05 (* 0.0454545 = 2.07146e-06 loss)
I0405 15:43:29.543124 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 4.7427e-05 (* 0.0454545 = 2.15578e-06 loss)
I0405 15:43:29.543138 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.37545e-05 (* 0.0454545 = 1.98884e-06 loss)
I0405 15:43:29.543151 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:43:29.543162 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000387665
I0405 15:43:29.543177 29564 sgd_solver.cpp:106] Iteration 15000, lr = 0.00985
I0405 15:47:19.601919 29564 solver.cpp:229] Iteration 15500, loss = 0.950703
I0405 15:47:19.602083 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.125
I0405 15:47:19.602116 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 15:47:19.602136 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 15:47:19.602149 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 15:47:19.602161 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.09375
I0405 15:47:19.602174 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.1875
I0405 15:47:19.602185 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 15:47:19.602197 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 15:47:19.602208 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 15:47:19.602221 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 15:47:19.602231 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:47:19.602242 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:47:19.602254 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:47:19.602265 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:47:19.602277 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:47:19.602288 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:47:19.602299 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:47:19.602310 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:47:19.602321 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:47:19.602332 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:47:19.602344 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:47:19.602355 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:47:19.602370 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.84613 (* 0.0454545 = 0.12937 loss)
I0405 15:47:19.602385 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.37309 (* 0.0454545 = 0.153322 loss)
I0405 15:47:19.602398 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.40336 (* 0.0454545 = 0.154698 loss)
I0405 15:47:19.602416 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.45465 (* 0.0454545 = 0.15703 loss)
I0405 15:47:19.602430 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.20877 (* 0.0454545 = 0.145853 loss)
I0405 15:47:19.602444 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 3.19565 (* 0.0454545 = 0.145257 loss)
I0405 15:47:19.602458 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.60505 (* 0.0454545 = 0.072957 loss)
I0405 15:47:19.602471 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.411457 (* 0.0454545 = 0.0187026 loss)
I0405 15:47:19.602485 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.203791 (* 0.0454545 = 0.00926322 loss)
I0405 15:47:19.602499 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0120562 (* 0.0454545 = 0.000548009 loss)
I0405 15:47:19.602514 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000202151 (* 0.0454545 = 9.18869e-06 loss)
I0405 15:47:19.602527 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000221061 (* 0.0454545 = 1.00482e-05 loss)
I0405 15:47:19.602541 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000227869 (* 0.0454545 = 1.03577e-05 loss)
I0405 15:47:19.602555 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000196745 (* 0.0454545 = 8.94294e-06 loss)
I0405 15:47:19.602569 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.00023844 (* 0.0454545 = 1.08382e-05 loss)
I0405 15:47:19.602583 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000210417 (* 0.0454545 = 9.56439e-06 loss)
I0405 15:47:19.602597 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000229454 (* 0.0454545 = 1.04297e-05 loss)
I0405 15:47:19.602628 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000265364 (* 0.0454545 = 1.2062e-05 loss)
I0405 15:47:19.602644 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000199712 (* 0.0454545 = 9.07782e-06 loss)
I0405 15:47:19.602658 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000229661 (* 0.0454545 = 1.04391e-05 loss)
I0405 15:47:19.602672 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000235661 (* 0.0454545 = 1.07119e-05 loss)
I0405 15:47:19.602686 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000214767 (* 0.0454545 = 9.76213e-06 loss)
I0405 15:47:19.602699 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:47:19.602710 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000111837
I0405 15:47:19.602725 29564 sgd_solver.cpp:106] Iteration 15500, lr = 0.009845
I0405 15:51:08.932515 29564 solver.cpp:229] Iteration 16000, loss = 0.945956
I0405 15:51:08.932699 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 15:51:08.932720 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 15:51:08.932736 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 15:51:08.932749 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 15:51:08.932761 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.09375
I0405 15:51:08.932773 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.21875
I0405 15:51:08.932785 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 15:51:08.932797 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 15:51:08.932808 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 15:51:08.932821 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 15:51:08.932832 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:51:08.932843 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:51:08.932855 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:51:08.932868 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:51:08.932878 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:51:08.932890 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:51:08.932901 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:51:08.932912 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:51:08.932924 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:51:08.932935 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:51:08.932947 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:51:08.932958 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:51:08.932973 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.11464 (* 0.0454545 = 0.141574 loss)
I0405 15:51:08.932988 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.19378 (* 0.0454545 = 0.145172 loss)
I0405 15:51:08.933002 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.34309 (* 0.0454545 = 0.151958 loss)
I0405 15:51:08.933017 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.41228 (* 0.0454545 = 0.155104 loss)
I0405 15:51:08.933030 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.22078 (* 0.0454545 = 0.146399 loss)
I0405 15:51:08.933043 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.84392 (* 0.0454545 = 0.129269 loss)
I0405 15:51:08.933058 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.17586 (* 0.0454545 = 0.0534482 loss)
I0405 15:51:08.933071 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.62826 (* 0.0454545 = 0.0285573 loss)
I0405 15:51:08.933085 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.677735 (* 0.0454545 = 0.0308062 loss)
I0405 15:51:08.933099 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.471947 (* 0.0454545 = 0.0214521 loss)
I0405 15:51:08.933114 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 7.26103e-05 (* 0.0454545 = 3.30047e-06 loss)
I0405 15:51:08.933127 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 7.79357e-05 (* 0.0454545 = 3.54253e-06 loss)
I0405 15:51:08.933141 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 7.44773e-05 (* 0.0454545 = 3.38533e-06 loss)
I0405 15:51:08.933156 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 7.017e-05 (* 0.0454545 = 3.18955e-06 loss)
I0405 15:51:08.933169 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 8.01701e-05 (* 0.0454545 = 3.6441e-06 loss)
I0405 15:51:08.933183 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 7.54048e-05 (* 0.0454545 = 3.42749e-06 loss)
I0405 15:51:08.933197 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.2873e-05 (* 0.0454545 = 3.31241e-06 loss)
I0405 15:51:08.933229 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 8.52055e-05 (* 0.0454545 = 3.87298e-06 loss)
I0405 15:51:08.933244 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.2347e-05 (* 0.0454545 = 3.2885e-06 loss)
I0405 15:51:08.933259 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 8.103e-05 (* 0.0454545 = 3.68318e-06 loss)
I0405 15:51:08.933274 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 8.33271e-05 (* 0.0454545 = 3.7876e-06 loss)
I0405 15:51:08.933287 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 7.14803e-05 (* 0.0454545 = 3.2491e-06 loss)
I0405 15:51:08.933298 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:51:08.933310 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00090685
I0405 15:51:08.933325 29564 sgd_solver.cpp:106] Iteration 16000, lr = 0.00984
I0405 15:54:58.523903 29564 solver.cpp:229] Iteration 16500, loss = 0.936841
I0405 15:54:58.524011 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.03125
I0405 15:54:58.524030 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 15:54:58.524042 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 15:54:58.524055 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 15:54:58.524067 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 15:54:58.524101 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.3125
I0405 15:54:58.524114 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 15:54:58.524128 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 15:54:58.524140 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 15:54:58.524152 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 15:54:58.524164 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:54:58.524175 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:54:58.524188 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:54:58.524199 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:54:58.524209 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:54:58.524220 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:54:58.524231 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:54:58.524245 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:54:58.524257 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:54:58.524268 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:54:58.524281 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:54:58.524291 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:54:58.524307 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.02554 (* 0.0454545 = 0.137525 loss)
I0405 15:54:58.524322 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.5755 (* 0.0454545 = 0.162523 loss)
I0405 15:54:58.524335 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.40878 (* 0.0454545 = 0.154945 loss)
I0405 15:54:58.524349 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.30668 (* 0.0454545 = 0.150303 loss)
I0405 15:54:58.524363 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.17025 (* 0.0454545 = 0.144102 loss)
I0405 15:54:58.524377 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.75632 (* 0.0454545 = 0.125287 loss)
I0405 15:54:58.524391 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.62252 (* 0.0454545 = 0.0737508 loss)
I0405 15:54:58.524405 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.311339 (* 0.0454545 = 0.0141518 loss)
I0405 15:54:58.524418 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.353849 (* 0.0454545 = 0.016084 loss)
I0405 15:54:58.524432 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.209358 (* 0.0454545 = 0.00951628 loss)
I0405 15:54:58.524447 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000226792 (* 0.0454545 = 1.03087e-05 loss)
I0405 15:54:58.524461 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000236849 (* 0.0454545 = 1.07659e-05 loss)
I0405 15:54:58.524476 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000228034 (* 0.0454545 = 1.03652e-05 loss)
I0405 15:54:58.524489 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000231674 (* 0.0454545 = 1.05306e-05 loss)
I0405 15:54:58.524503 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000249587 (* 0.0454545 = 1.13449e-05 loss)
I0405 15:54:58.524518 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.00023181 (* 0.0454545 = 1.05368e-05 loss)
I0405 15:54:58.524533 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000211004 (* 0.0454545 = 9.59111e-06 loss)
I0405 15:54:58.524564 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000239487 (* 0.0454545 = 1.08858e-05 loss)
I0405 15:54:58.524579 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000222435 (* 0.0454545 = 1.01107e-05 loss)
I0405 15:54:58.524592 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000233581 (* 0.0454545 = 1.06173e-05 loss)
I0405 15:54:58.524605 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000240223 (* 0.0454545 = 1.09193e-05 loss)
I0405 15:54:58.524619 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000226394 (* 0.0454545 = 1.02906e-05 loss)
I0405 15:54:58.524631 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:54:58.524643 29564 solver.cpp:245]     Train net output #45: total_confidence = 6.9227e-05
I0405 15:54:58.524657 29564 sgd_solver.cpp:106] Iteration 16500, lr = 0.009835
I0405 15:58:48.676604 29564 solver.cpp:229] Iteration 17000, loss = 0.935537
I0405 15:58:48.676738 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 15:58:48.676759 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 15:58:48.676772 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 15:58:48.676784 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 15:58:48.676800 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.15625
I0405 15:58:48.676812 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 15:58:48.676826 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 15:58:48.676837 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 15:58:48.676849 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 15:58:48.676862 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 15:58:48.676873 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 15:58:48.676892 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 15:58:48.676904 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 15:58:48.676916 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 15:58:48.676928 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 15:58:48.676939 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 15:58:48.676950 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 15:58:48.676961 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 15:58:48.676973 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 15:58:48.676985 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 15:58:48.676995 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 15:58:48.677007 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 15:58:48.677022 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.02998 (* 0.0454545 = 0.137727 loss)
I0405 15:58:48.677038 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.27675 (* 0.0454545 = 0.148943 loss)
I0405 15:58:48.677052 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.29964 (* 0.0454545 = 0.149984 loss)
I0405 15:58:48.677067 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.15737 (* 0.0454545 = 0.143517 loss)
I0405 15:58:48.677088 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.04847 (* 0.0454545 = 0.138567 loss)
I0405 15:58:48.677101 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.56697 (* 0.0454545 = 0.116681 loss)
I0405 15:58:48.677115 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.38183 (* 0.0454545 = 0.0628106 loss)
I0405 15:58:48.677129 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.356133 (* 0.0454545 = 0.0161879 loss)
I0405 15:58:48.677144 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.193193 (* 0.0454545 = 0.00878148 loss)
I0405 15:58:48.677157 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.248609 (* 0.0454545 = 0.0113004 loss)
I0405 15:58:48.677172 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.00016187 (* 0.0454545 = 7.35774e-06 loss)
I0405 15:58:48.677186 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000172432 (* 0.0454545 = 7.83784e-06 loss)
I0405 15:58:48.677202 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000154041 (* 0.0454545 = 7.00187e-06 loss)
I0405 15:58:48.677217 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000159714 (* 0.0454545 = 7.25973e-06 loss)
I0405 15:58:48.677230 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000165156 (* 0.0454545 = 7.5071e-06 loss)
I0405 15:58:48.677244 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000164661 (* 0.0454545 = 7.4846e-06 loss)
I0405 15:58:48.677258 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000142483 (* 0.0454545 = 6.47651e-06 loss)
I0405 15:58:48.677289 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000161398 (* 0.0454545 = 7.33627e-06 loss)
I0405 15:58:48.677304 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000172302 (* 0.0454545 = 7.8319e-06 loss)
I0405 15:58:48.677319 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000166481 (* 0.0454545 = 7.56731e-06 loss)
I0405 15:58:48.677332 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000164223 (* 0.0454545 = 7.4647e-06 loss)
I0405 15:58:48.677347 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000154067 (* 0.0454545 = 7.00304e-06 loss)
I0405 15:58:48.677361 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 15:58:48.677373 29564 solver.cpp:245]     Train net output #45: total_confidence = 7.80372e-05
I0405 15:58:48.677387 29564 sgd_solver.cpp:106] Iteration 17000, lr = 0.00983
I0405 16:02:38.560196 29564 solver.cpp:229] Iteration 17500, loss = 0.937171
I0405 16:02:38.560436 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 16:02:38.560463 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 16:02:38.560477 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 16:02:38.560488 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.03125
I0405 16:02:38.560500 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 16:02:38.560513 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 16:02:38.560524 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 16:02:38.560537 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 16:02:38.560549 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 16:02:38.560560 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 16:02:38.560572 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:02:38.560585 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:02:38.560595 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:02:38.560607 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:02:38.560618 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:02:38.560631 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:02:38.560642 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:02:38.560652 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:02:38.560664 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:02:38.560675 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:02:38.560686 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:02:38.560698 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:02:38.560713 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.03435 (* 0.0454545 = 0.137925 loss)
I0405 16:02:38.560726 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.28475 (* 0.0454545 = 0.149307 loss)
I0405 16:02:38.560740 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.27079 (* 0.0454545 = 0.148672 loss)
I0405 16:02:38.560755 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.23558 (* 0.0454545 = 0.147072 loss)
I0405 16:02:38.560767 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.0918 (* 0.0454545 = 0.140536 loss)
I0405 16:02:38.560781 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.24371 (* 0.0454545 = 0.101987 loss)
I0405 16:02:38.560796 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.33987 (* 0.0454545 = 0.0609033 loss)
I0405 16:02:38.560809 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.624173 (* 0.0454545 = 0.0283715 loss)
I0405 16:02:38.560823 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.392503 (* 0.0454545 = 0.0178411 loss)
I0405 16:02:38.560837 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.383224 (* 0.0454545 = 0.0174193 loss)
I0405 16:02:38.560853 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000243536 (* 0.0454545 = 1.10698e-05 loss)
I0405 16:02:38.560868 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.00023936 (* 0.0454545 = 1.088e-05 loss)
I0405 16:02:38.560884 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000232872 (* 0.0454545 = 1.05851e-05 loss)
I0405 16:02:38.560899 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000239313 (* 0.0454545 = 1.08779e-05 loss)
I0405 16:02:38.560912 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000226361 (* 0.0454545 = 1.02891e-05 loss)
I0405 16:02:38.560926 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000232776 (* 0.0454545 = 1.05807e-05 loss)
I0405 16:02:38.560940 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000214409 (* 0.0454545 = 9.74584e-06 loss)
I0405 16:02:38.560968 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000222934 (* 0.0454545 = 1.01333e-05 loss)
I0405 16:02:38.560983 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000250224 (* 0.0454545 = 1.13738e-05 loss)
I0405 16:02:38.560997 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00023945 (* 0.0454545 = 1.08841e-05 loss)
I0405 16:02:38.561028 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000231005 (* 0.0454545 = 1.05002e-05 loss)
I0405 16:02:38.561044 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000219927 (* 0.0454545 = 9.99666e-06 loss)
I0405 16:02:38.561056 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:02:38.561069 29564 solver.cpp:245]     Train net output #45: total_confidence = 8.00725e-05
I0405 16:02:38.561081 29564 sgd_solver.cpp:106] Iteration 17500, lr = 0.009825
I0405 16:06:28.005138 29564 solver.cpp:229] Iteration 18000, loss = 0.927327
I0405 16:06:28.005275 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.125
I0405 16:06:28.005295 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 16:06:28.005308 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 16:06:28.005321 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.03125
I0405 16:06:28.005332 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 16:06:28.005344 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.28125
I0405 16:06:28.005357 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.625
I0405 16:06:28.005368 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 16:06:28.005380 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 16:06:28.005393 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 16:06:28.005404 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:06:28.005415 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:06:28.005427 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:06:28.005439 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:06:28.005450 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:06:28.005461 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:06:28.005473 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:06:28.005484 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:06:28.005496 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:06:28.005506 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:06:28.005518 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:06:28.005530 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:06:28.005545 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.84533 (* 0.0454545 = 0.129333 loss)
I0405 16:06:28.005560 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.02864 (* 0.0454545 = 0.137665 loss)
I0405 16:06:28.005574 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.21504 (* 0.0454545 = 0.146138 loss)
I0405 16:06:28.005589 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.25461 (* 0.0454545 = 0.147937 loss)
I0405 16:06:28.005602 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.87615 (* 0.0454545 = 0.130734 loss)
I0405 16:06:28.005616 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.45839 (* 0.0454545 = 0.111745 loss)
I0405 16:06:28.005630 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.60661 (* 0.0454545 = 0.0730277 loss)
I0405 16:06:28.005645 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.812869 (* 0.0454545 = 0.0369486 loss)
I0405 16:06:28.005658 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.360278 (* 0.0454545 = 0.0163763 loss)
I0405 16:06:28.005672 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0331852 (* 0.0454545 = 0.00150842 loss)
I0405 16:06:28.005686 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 7.79727e-05 (* 0.0454545 = 3.54421e-06 loss)
I0405 16:06:28.005704 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 8.37354e-05 (* 0.0454545 = 3.80616e-06 loss)
I0405 16:06:28.005718 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 7.91803e-05 (* 0.0454545 = 3.5991e-06 loss)
I0405 16:06:28.005733 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 8.02927e-05 (* 0.0454545 = 3.64967e-06 loss)
I0405 16:06:28.005748 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 8.30097e-05 (* 0.0454545 = 3.77317e-06 loss)
I0405 16:06:28.005761 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 7.66864e-05 (* 0.0454545 = 3.48575e-06 loss)
I0405 16:06:28.005775 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.41092e-05 (* 0.0454545 = 3.3686e-06 loss)
I0405 16:06:28.005806 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 7.78339e-05 (* 0.0454545 = 3.53791e-06 loss)
I0405 16:06:28.005822 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 8.62797e-05 (* 0.0454545 = 3.9218e-06 loss)
I0405 16:06:28.005836 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 8.00627e-05 (* 0.0454545 = 3.63921e-06 loss)
I0405 16:06:28.005851 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.93702e-05 (* 0.0454545 = 3.60774e-06 loss)
I0405 16:06:28.005864 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 7.41132e-05 (* 0.0454545 = 3.36878e-06 loss)
I0405 16:06:28.005880 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:06:28.005892 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000733008
I0405 16:06:28.005908 29564 sgd_solver.cpp:106] Iteration 18000, lr = 0.00982
I0405 16:10:17.767992 29564 solver.cpp:229] Iteration 18500, loss = 0.935033
I0405 16:10:17.768146 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 16:10:17.768167 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.1875
I0405 16:10:17.768182 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 16:10:17.768193 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 16:10:17.768205 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.125
I0405 16:10:17.768218 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5
I0405 16:10:17.768229 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 16:10:17.768240 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 16:10:17.768254 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 16:10:17.768266 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 16:10:17.768278 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:10:17.768290 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:10:17.768301 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:10:17.768313 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:10:17.768324 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:10:17.768335 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:10:17.768347 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:10:17.768358 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:10:17.768369 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:10:17.768381 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:10:17.768393 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:10:17.768404 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:10:17.768419 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.69035 (* 0.0454545 = 0.122289 loss)
I0405 16:10:17.768434 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.07666 (* 0.0454545 = 0.139848 loss)
I0405 16:10:17.768447 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.22349 (* 0.0454545 = 0.146522 loss)
I0405 16:10:17.768461 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.15686 (* 0.0454545 = 0.143494 loss)
I0405 16:10:17.768476 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.36542 (* 0.0454545 = 0.152974 loss)
I0405 16:10:17.768488 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.36947 (* 0.0454545 = 0.107703 loss)
I0405 16:10:17.768502 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.46613 (* 0.0454545 = 0.0666421 loss)
I0405 16:10:17.768517 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.366151 (* 0.0454545 = 0.0166432 loss)
I0405 16:10:17.768529 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.272741 (* 0.0454545 = 0.0123973 loss)
I0405 16:10:17.768543 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.336603 (* 0.0454545 = 0.0153001 loss)
I0405 16:10:17.768558 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.82991e-05 (* 0.0454545 = 1.74087e-06 loss)
I0405 16:10:17.768571 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.86716e-05 (* 0.0454545 = 1.7578e-06 loss)
I0405 16:10:17.768585 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.38428e-05 (* 0.0454545 = 1.53831e-06 loss)
I0405 16:10:17.768599 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.63207e-05 (* 0.0454545 = 1.65094e-06 loss)
I0405 16:10:17.768615 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.36415e-05 (* 0.0454545 = 1.52916e-06 loss)
I0405 16:10:17.768628 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.18595e-05 (* 0.0454545 = 1.9027e-06 loss)
I0405 16:10:17.768642 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.16745e-05 (* 0.0454545 = 1.43975e-06 loss)
I0405 16:10:17.768674 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.74273e-05 (* 0.0454545 = 1.70124e-06 loss)
I0405 16:10:17.768690 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 3.58063e-05 (* 0.0454545 = 1.62756e-06 loss)
I0405 16:10:17.768704 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.31395e-05 (* 0.0454545 = 1.96089e-06 loss)
I0405 16:10:17.768718 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.69802e-05 (* 0.0454545 = 1.68092e-06 loss)
I0405 16:10:17.768731 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.46627e-05 (* 0.0454545 = 1.57558e-06 loss)
I0405 16:10:17.768743 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:10:17.768755 29564 solver.cpp:245]     Train net output #45: total_confidence = 3.34945e-05
I0405 16:10:17.768769 29564 sgd_solver.cpp:106] Iteration 18500, lr = 0.009815
I0405 16:14:07.371347 29564 solver.cpp:229] Iteration 19000, loss = 0.92663
I0405 16:14:07.371533 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 16:14:07.371556 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 16:14:07.371569 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 16:14:07.371582 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 16:14:07.371593 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.09375
I0405 16:14:07.371604 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 16:14:07.371616 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.59375
I0405 16:14:07.371629 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 16:14:07.371641 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 16:14:07.371654 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 16:14:07.371666 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:14:07.371678 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:14:07.371690 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:14:07.371701 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:14:07.371712 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:14:07.371723 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:14:07.371734 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:14:07.371745 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:14:07.371757 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:14:07.371767 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:14:07.371779 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:14:07.371790 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:14:07.371806 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.96754 (* 0.0454545 = 0.134888 loss)
I0405 16:14:07.371821 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.49516 (* 0.0454545 = 0.158871 loss)
I0405 16:14:07.371835 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.4824 (* 0.0454545 = 0.158291 loss)
I0405 16:14:07.371850 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.47177 (* 0.0454545 = 0.157808 loss)
I0405 16:14:07.371863 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.22623 (* 0.0454545 = 0.146647 loss)
I0405 16:14:07.371877 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.61268 (* 0.0454545 = 0.118758 loss)
I0405 16:14:07.371891 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.90507 (* 0.0454545 = 0.0865941 loss)
I0405 16:14:07.371906 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.425533 (* 0.0454545 = 0.0193424 loss)
I0405 16:14:07.371920 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.183317 (* 0.0454545 = 0.0083326 loss)
I0405 16:14:07.371934 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0308287 (* 0.0454545 = 0.0014013 loss)
I0405 16:14:07.371949 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000170197 (* 0.0454545 = 7.73621e-06 loss)
I0405 16:14:07.371963 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000171118 (* 0.0454545 = 7.77808e-06 loss)
I0405 16:14:07.371978 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000173666 (* 0.0454545 = 7.89393e-06 loss)
I0405 16:14:07.371991 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.00015852 (* 0.0454545 = 7.20547e-06 loss)
I0405 16:14:07.372006 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000169147 (* 0.0454545 = 7.68851e-06 loss)
I0405 16:14:07.372020 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000168273 (* 0.0454545 = 7.64877e-06 loss)
I0405 16:14:07.372035 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000171266 (* 0.0454545 = 7.78482e-06 loss)
I0405 16:14:07.372066 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000181858 (* 0.0454545 = 8.26625e-06 loss)
I0405 16:14:07.372102 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000162996 (* 0.0454545 = 7.40892e-06 loss)
I0405 16:14:07.372117 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00018229 (* 0.0454545 = 8.28591e-06 loss)
I0405 16:14:07.372131 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000174868 (* 0.0454545 = 7.94856e-06 loss)
I0405 16:14:07.372145 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000169715 (* 0.0454545 = 7.71432e-06 loss)
I0405 16:14:07.372158 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:14:07.372169 29564 solver.cpp:245]     Train net output #45: total_confidence = 2.35167e-05
I0405 16:14:07.372184 29564 sgd_solver.cpp:106] Iteration 19000, lr = 0.00981
I0405 16:17:56.947706 29564 solver.cpp:229] Iteration 19500, loss = 0.921893
I0405 16:17:56.947844 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.03125
I0405 16:17:56.947862 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 16:17:56.947875 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 16:17:56.947887 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 16:17:56.947902 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 16:17:56.947914 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 16:17:56.947926 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 16:17:56.947938 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 16:17:56.947950 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 16:17:56.947962 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 16:17:56.947973 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:17:56.947985 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:17:56.947996 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:17:56.948009 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:17:56.948019 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:17:56.948030 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:17:56.948042 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:17:56.948053 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:17:56.948065 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:17:56.948097 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:17:56.948110 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:17:56.948122 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:17:56.948137 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.21962 (* 0.0454545 = 0.146346 loss)
I0405 16:17:56.948151 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.57956 (* 0.0454545 = 0.162707 loss)
I0405 16:17:56.948165 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.3728 (* 0.0454545 = 0.153309 loss)
I0405 16:17:56.948179 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.51996 (* 0.0454545 = 0.159998 loss)
I0405 16:17:56.948194 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.99917 (* 0.0454545 = 0.136326 loss)
I0405 16:17:56.948206 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.65966 (* 0.0454545 = 0.120894 loss)
I0405 16:17:56.948220 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.26064 (* 0.0454545 = 0.057302 loss)
I0405 16:17:56.948235 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.370871 (* 0.0454545 = 0.0168578 loss)
I0405 16:17:56.948248 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.134453 (* 0.0454545 = 0.00611148 loss)
I0405 16:17:56.948263 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.146216 (* 0.0454545 = 0.00664619 loss)
I0405 16:17:56.948279 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 5.60408e-05 (* 0.0454545 = 2.54731e-06 loss)
I0405 16:17:56.948295 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.5991e-05 (* 0.0454545 = 2.54505e-06 loss)
I0405 16:17:56.948309 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 4.95734e-05 (* 0.0454545 = 2.25334e-06 loss)
I0405 16:17:56.948323 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 5.3002e-05 (* 0.0454545 = 2.40918e-06 loss)
I0405 16:17:56.948338 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 5.26074e-05 (* 0.0454545 = 2.39124e-06 loss)
I0405 16:17:56.948351 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 5.04484e-05 (* 0.0454545 = 2.29311e-06 loss)
I0405 16:17:56.948365 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 4.46716e-05 (* 0.0454545 = 2.03053e-06 loss)
I0405 16:17:56.948393 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 4.6208e-05 (* 0.0454545 = 2.10037e-06 loss)
I0405 16:17:56.948408 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 5.70383e-05 (* 0.0454545 = 2.59265e-06 loss)
I0405 16:17:56.948422 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 5.22354e-05 (* 0.0454545 = 2.37434e-06 loss)
I0405 16:17:56.948436 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 4.95028e-05 (* 0.0454545 = 2.25013e-06 loss)
I0405 16:17:56.948451 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.96091e-05 (* 0.0454545 = 2.25496e-06 loss)
I0405 16:17:56.948463 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:17:56.948474 29564 solver.cpp:245]     Train net output #45: total_confidence = 2.61263e-05
I0405 16:17:56.948488 29564 sgd_solver.cpp:106] Iteration 19500, lr = 0.009805
I0405 16:21:46.409340 29564 solver.cpp:338] Iteration 20000, Testing net (#0)
I0405 16:21:56.706635 29564 solver.cpp:393] Test loss: 0.841183
I0405 16:21:56.706697 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.15
I0405 16:21:56.706712 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.074
I0405 16:21:56.706727 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.09
I0405 16:21:56.706738 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.129
I0405 16:21:56.706749 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.246
I0405 16:21:56.706760 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.506
I0405 16:21:56.706773 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.893
I0405 16:21:56.706785 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 16:21:56.706797 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 16:21:56.706809 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 16:21:56.706820 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 16:21:56.706832 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 16:21:56.706843 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 16:21:56.706854 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 16:21:56.706866 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 16:21:56.706876 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 16:21:56.706887 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 16:21:56.706898 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 16:21:56.706909 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 16:21:56.706920 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 16:21:56.706933 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 16:21:56.706943 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 16:21:56.706959 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 3.10181 (* 0.0454545 = 0.140991 loss)
I0405 16:21:56.706974 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 3.21545 (* 0.0454545 = 0.146157 loss)
I0405 16:21:56.706986 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 3.2207 (* 0.0454545 = 0.146396 loss)
I0405 16:21:56.707000 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 3.10271 (* 0.0454545 = 0.141032 loss)
I0405 16:21:56.707015 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 2.89067 (* 0.0454545 = 0.131394 loss)
I0405 16:21:56.707028 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 1.97616 (* 0.0454545 = 0.0898255 loss)
I0405 16:21:56.707042 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.705744 (* 0.0454545 = 0.0320793 loss)
I0405 16:21:56.707056 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.221434 (* 0.0454545 = 0.0100652 loss)
I0405 16:21:56.707069 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0473982 (* 0.0454545 = 0.00215447 loss)
I0405 16:21:56.707083 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0232042 (* 0.0454545 = 0.00105474 loss)
I0405 16:21:56.707098 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 6.77782e-05 (* 0.0454545 = 3.08083e-06 loss)
I0405 16:21:56.707113 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 6.47989e-05 (* 0.0454545 = 2.9454e-06 loss)
I0405 16:21:56.707126 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 6.18561e-05 (* 0.0454545 = 2.81164e-06 loss)
I0405 16:21:56.707140 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 6.37742e-05 (* 0.0454545 = 2.89883e-06 loss)
I0405 16:21:56.707154 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 6.67826e-05 (* 0.0454545 = 3.03557e-06 loss)
I0405 16:21:56.707168 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 6.03262e-05 (* 0.0454545 = 2.7421e-06 loss)
I0405 16:21:56.707182 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 5.86002e-05 (* 0.0454545 = 2.66364e-06 loss)
I0405 16:21:56.707232 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 6.18622e-05 (* 0.0454545 = 2.81192e-06 loss)
I0405 16:21:56.707248 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 6.70327e-05 (* 0.0454545 = 3.04694e-06 loss)
I0405 16:21:56.707262 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 6.11037e-05 (* 0.0454545 = 2.77744e-06 loss)
I0405 16:21:56.707276 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 6.24575e-05 (* 0.0454545 = 2.83898e-06 loss)
I0405 16:21:56.707291 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 6.25772e-05 (* 0.0454545 = 2.84442e-06 loss)
I0405 16:21:56.707304 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0.001
I0405 16:21:56.707314 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.000129186
I0405 16:21:56.822494 29564 solver.cpp:229] Iteration 20000, loss = 0.925324
I0405 16:21:56.822551 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 16:21:56.822568 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 16:21:56.822582 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 16:21:56.822593 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 16:21:56.822605 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 16:21:56.822618 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 16:21:56.822629 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.625
I0405 16:21:56.822641 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.75
I0405 16:21:56.822654 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 16:21:56.822665 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.90625
I0405 16:21:56.822676 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:21:56.822688 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:21:56.822701 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:21:56.822713 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:21:56.822724 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:21:56.822736 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:21:56.822747 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:21:56.822759 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:21:56.822770 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:21:56.822782 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:21:56.822793 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:21:56.822804 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:21:56.822819 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.96617 (* 0.0454545 = 0.134826 loss)
I0405 16:21:56.822834 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.32843 (* 0.0454545 = 0.151292 loss)
I0405 16:21:56.822849 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.39607 (* 0.0454545 = 0.154367 loss)
I0405 16:21:56.822862 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.17219 (* 0.0454545 = 0.14419 loss)
I0405 16:21:56.822876 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.61531 (* 0.0454545 = 0.118878 loss)
I0405 16:21:56.822890 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.30985 (* 0.0454545 = 0.104993 loss)
I0405 16:21:56.822904 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.80237 (* 0.0454545 = 0.0819258 loss)
I0405 16:21:56.822918 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 1.25931 (* 0.0454545 = 0.0572412 loss)
I0405 16:21:56.822932 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.479258 (* 0.0454545 = 0.0217844 loss)
I0405 16:21:56.822970 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.578146 (* 0.0454545 = 0.0262794 loss)
I0405 16:21:56.822986 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000846859 (* 0.0454545 = 3.84936e-05 loss)
I0405 16:21:56.823001 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000774687 (* 0.0454545 = 3.5213e-05 loss)
I0405 16:21:56.823015 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000691253 (* 0.0454545 = 3.14206e-05 loss)
I0405 16:21:56.823030 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000813052 (* 0.0454545 = 3.69569e-05 loss)
I0405 16:21:56.823045 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000797206 (* 0.0454545 = 3.62366e-05 loss)
I0405 16:21:56.823062 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000844798 (* 0.0454545 = 3.83999e-05 loss)
I0405 16:21:56.823076 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000738952 (* 0.0454545 = 3.35887e-05 loss)
I0405 16:21:56.823091 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000759874 (* 0.0454545 = 3.45397e-05 loss)
I0405 16:21:56.823104 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000864804 (* 0.0454545 = 3.93093e-05 loss)
I0405 16:21:56.823119 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00081036 (* 0.0454545 = 3.68345e-05 loss)
I0405 16:21:56.823133 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000755266 (* 0.0454545 = 3.43303e-05 loss)
I0405 16:21:56.823148 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000869854 (* 0.0454545 = 3.95388e-05 loss)
I0405 16:21:56.823159 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:21:56.823171 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000124871
I0405 16:21:56.823186 29564 sgd_solver.cpp:106] Iteration 20000, lr = 0.0098
I0405 16:25:46.686305 29564 solver.cpp:229] Iteration 20500, loss = 0.917616
I0405 16:25:46.686405 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 16:25:46.686424 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 16:25:46.686437 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0
I0405 16:25:46.686450 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 16:25:46.686460 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.375
I0405 16:25:46.686472 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 16:25:46.686485 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 16:25:46.686496 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 16:25:46.686507 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 16:25:46.686518 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 16:25:46.686530 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:25:46.686542 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:25:46.686553 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:25:46.686564 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:25:46.686575 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:25:46.686586 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:25:46.686597 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:25:46.686609 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:25:46.686620 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:25:46.686631 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:25:46.686645 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:25:46.686657 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:25:46.686672 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.98019 (* 0.0454545 = 0.135463 loss)
I0405 16:25:46.686686 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.35827 (* 0.0454545 = 0.152649 loss)
I0405 16:25:46.686700 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.61015 (* 0.0454545 = 0.164098 loss)
I0405 16:25:46.686714 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.19512 (* 0.0454545 = 0.145233 loss)
I0405 16:25:46.686728 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.4285 (* 0.0454545 = 0.110386 loss)
I0405 16:25:46.686741 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.12518 (* 0.0454545 = 0.0965992 loss)
I0405 16:25:46.686755 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.47173 (* 0.0454545 = 0.0668968 loss)
I0405 16:25:46.686769 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 1.01436 (* 0.0454545 = 0.0461071 loss)
I0405 16:25:46.686782 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.59077 (* 0.0454545 = 0.0268532 loss)
I0405 16:25:46.686795 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.366058 (* 0.0454545 = 0.016639 loss)
I0405 16:25:46.686810 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.55847e-05 (* 0.0454545 = 2.07203e-06 loss)
I0405 16:25:46.686823 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 4.38186e-05 (* 0.0454545 = 1.99175e-06 loss)
I0405 16:25:46.686837 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 4.20463e-05 (* 0.0454545 = 1.9112e-06 loss)
I0405 16:25:46.686852 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 4.22387e-05 (* 0.0454545 = 1.91994e-06 loss)
I0405 16:25:46.686866 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.16995e-05 (* 0.0454545 = 1.89543e-06 loss)
I0405 16:25:46.686880 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.05577e-05 (* 0.0454545 = 1.84353e-06 loss)
I0405 16:25:46.686893 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.98864e-05 (* 0.0454545 = 1.81302e-06 loss)
I0405 16:25:46.686923 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.86151e-05 (* 0.0454545 = 1.75523e-06 loss)
I0405 16:25:46.686939 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.52818e-05 (* 0.0454545 = 2.05826e-06 loss)
I0405 16:25:46.686954 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.28136e-05 (* 0.0454545 = 1.94607e-06 loss)
I0405 16:25:46.686967 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 4.0749e-05 (* 0.0454545 = 1.85223e-06 loss)
I0405 16:25:46.686983 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.93698e-05 (* 0.0454545 = 1.78954e-06 loss)
I0405 16:25:46.686996 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:25:46.687007 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000742693
I0405 16:25:46.687021 29564 sgd_solver.cpp:106] Iteration 20500, lr = 0.009795
I0405 16:29:36.756197 29564 solver.cpp:229] Iteration 21000, loss = 0.914948
I0405 16:29:36.756324 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.21875
I0405 16:29:36.756343 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 16:29:36.756356 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 16:29:36.756368 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 16:29:36.756381 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 16:29:36.756392 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.3125
I0405 16:29:36.756404 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 16:29:36.756415 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 16:29:36.756428 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 16:29:36.756438 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 16:29:36.756450 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:29:36.756463 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:29:36.756474 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:29:36.756485 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:29:36.756496 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:29:36.756508 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:29:36.756520 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:29:36.756531 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:29:36.756542 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:29:36.756553 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:29:36.756564 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:29:36.756577 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:29:36.756592 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.49471 (* 0.0454545 = 0.113396 loss)
I0405 16:29:36.756605 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.06486 (* 0.0454545 = 0.139312 loss)
I0405 16:29:36.756619 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.07499 (* 0.0454545 = 0.139772 loss)
I0405 16:29:36.756634 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.0844 (* 0.0454545 = 0.1402 loss)
I0405 16:29:36.756649 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.03398 (* 0.0454545 = 0.137908 loss)
I0405 16:29:36.756662 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.63144 (* 0.0454545 = 0.119611 loss)
I0405 16:29:36.756675 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.2607 (* 0.0454545 = 0.0573046 loss)
I0405 16:29:36.756690 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.290372 (* 0.0454545 = 0.0131987 loss)
I0405 16:29:36.756705 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.180122 (* 0.0454545 = 0.00818738 loss)
I0405 16:29:36.756718 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.17767 (* 0.0454545 = 0.00807592 loss)
I0405 16:29:36.756732 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000103343 (* 0.0454545 = 4.69739e-06 loss)
I0405 16:29:36.756747 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.00010183 (* 0.0454545 = 4.62866e-06 loss)
I0405 16:29:36.756762 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 9.34928e-05 (* 0.0454545 = 4.24967e-06 loss)
I0405 16:29:36.756777 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 9.55437e-05 (* 0.0454545 = 4.34289e-06 loss)
I0405 16:29:36.756790 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 9.59539e-05 (* 0.0454545 = 4.36154e-06 loss)
I0405 16:29:36.756804 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 8.80724e-05 (* 0.0454545 = 4.00329e-06 loss)
I0405 16:29:36.756819 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 8.45836e-05 (* 0.0454545 = 3.84471e-06 loss)
I0405 16:29:36.756846 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 8.6478e-05 (* 0.0454545 = 3.93082e-06 loss)
I0405 16:29:36.756861 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000100893 (* 0.0454545 = 4.58603e-06 loss)
I0405 16:29:36.756875 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 9.31313e-05 (* 0.0454545 = 4.23324e-06 loss)
I0405 16:29:36.756889 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 9.18504e-05 (* 0.0454545 = 4.17502e-06 loss)
I0405 16:29:36.756903 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 9.09999e-05 (* 0.0454545 = 4.13636e-06 loss)
I0405 16:29:36.756916 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:29:36.756927 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.0004224
I0405 16:29:36.756940 29564 sgd_solver.cpp:106] Iteration 21000, lr = 0.00979
I0405 16:33:26.486292 29564 solver.cpp:229] Iteration 21500, loss = 0.915589
I0405 16:33:26.486465 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 16:33:26.486486 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 16:33:26.486498 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 16:33:26.486510 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.25
I0405 16:33:26.486522 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 16:33:26.486536 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 16:33:26.486546 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 16:33:26.486558 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 16:33:26.486570 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 16:33:26.486582 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 16:33:26.486593 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:33:26.486605 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:33:26.486616 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:33:26.486627 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:33:26.486639 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:33:26.486650 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:33:26.486661 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:33:26.486672 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:33:26.486685 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:33:26.486696 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:33:26.486707 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:33:26.486718 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:33:26.486733 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.79133 (* 0.0454545 = 0.126878 loss)
I0405 16:33:26.486748 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.07348 (* 0.0454545 = 0.139704 loss)
I0405 16:33:26.486762 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.11363 (* 0.0454545 = 0.141529 loss)
I0405 16:33:26.486775 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.88833 (* 0.0454545 = 0.131288 loss)
I0405 16:33:26.486789 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.56165 (* 0.0454545 = 0.116439 loss)
I0405 16:33:26.486804 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.26416 (* 0.0454545 = 0.102916 loss)
I0405 16:33:26.486817 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.2104 (* 0.0454545 = 0.0550184 loss)
I0405 16:33:26.486831 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.660792 (* 0.0454545 = 0.030036 loss)
I0405 16:33:26.486846 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0672911 (* 0.0454545 = 0.00305869 loss)
I0405 16:33:26.486860 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0279626 (* 0.0454545 = 0.00127103 loss)
I0405 16:33:26.486876 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000191369 (* 0.0454545 = 8.69861e-06 loss)
I0405 16:33:26.486891 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.00018443 (* 0.0454545 = 8.38317e-06 loss)
I0405 16:33:26.486904 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000183158 (* 0.0454545 = 8.32535e-06 loss)
I0405 16:33:26.486918 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.00017639 (* 0.0454545 = 8.01775e-06 loss)
I0405 16:33:26.486932 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000185707 (* 0.0454545 = 8.44121e-06 loss)
I0405 16:33:26.486946 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000173175 (* 0.0454545 = 7.87159e-06 loss)
I0405 16:33:26.486960 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000177087 (* 0.0454545 = 8.04939e-06 loss)
I0405 16:33:26.486991 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000181558 (* 0.0454545 = 8.25262e-06 loss)
I0405 16:33:26.487006 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000189702 (* 0.0454545 = 8.62281e-06 loss)
I0405 16:33:26.487020 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000187585 (* 0.0454545 = 8.52661e-06 loss)
I0405 16:33:26.487035 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000174716 (* 0.0454545 = 7.94165e-06 loss)
I0405 16:33:26.487048 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000176653 (* 0.0454545 = 8.02968e-06 loss)
I0405 16:33:26.487061 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:33:26.487072 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000228302
I0405 16:33:26.487087 29564 sgd_solver.cpp:106] Iteration 21500, lr = 0.009785
I0405 16:37:16.806392 29564 solver.cpp:229] Iteration 22000, loss = 0.910457
I0405 16:37:16.806505 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 16:37:16.806525 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 16:37:16.806537 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 16:37:16.806550 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 16:37:16.806561 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.125
I0405 16:37:16.806573 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 16:37:16.806586 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 16:37:16.806597 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 16:37:16.806609 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 16:37:16.806620 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 16:37:16.806632 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:37:16.806646 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:37:16.806659 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:37:16.806670 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:37:16.806681 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:37:16.806692 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:37:16.806704 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:37:16.806715 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:37:16.806726 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:37:16.806738 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:37:16.806749 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:37:16.806761 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:37:16.806777 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.10474 (* 0.0454545 = 0.141124 loss)
I0405 16:37:16.806790 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.35839 (* 0.0454545 = 0.152654 loss)
I0405 16:37:16.806804 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.34188 (* 0.0454545 = 0.151904 loss)
I0405 16:37:16.806818 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.46718 (* 0.0454545 = 0.157599 loss)
I0405 16:37:16.806831 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.17387 (* 0.0454545 = 0.144267 loss)
I0405 16:37:16.806845 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.35272 (* 0.0454545 = 0.106942 loss)
I0405 16:37:16.806859 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.63666 (* 0.0454545 = 0.0743938 loss)
I0405 16:37:16.806874 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.417046 (* 0.0454545 = 0.0189566 loss)
I0405 16:37:16.806886 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.280166 (* 0.0454545 = 0.0127348 loss)
I0405 16:37:16.806901 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.15181 (* 0.0454545 = 0.00690047 loss)
I0405 16:37:16.806915 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000136364 (* 0.0454545 = 6.19836e-06 loss)
I0405 16:37:16.806929 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000122598 (* 0.0454545 = 5.57264e-06 loss)
I0405 16:37:16.806943 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000125088 (* 0.0454545 = 5.68583e-06 loss)
I0405 16:37:16.806958 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000125856 (* 0.0454545 = 5.72071e-06 loss)
I0405 16:37:16.806972 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000122777 (* 0.0454545 = 5.58076e-06 loss)
I0405 16:37:16.806987 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000124998 (* 0.0454545 = 5.68172e-06 loss)
I0405 16:37:16.807000 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000118476 (* 0.0454545 = 5.38527e-06 loss)
I0405 16:37:16.807031 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.00012303 (* 0.0454545 = 5.59226e-06 loss)
I0405 16:37:16.807046 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000133319 (* 0.0454545 = 6.05996e-06 loss)
I0405 16:37:16.807060 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000128825 (* 0.0454545 = 5.8557e-06 loss)
I0405 16:37:16.807075 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000119391 (* 0.0454545 = 5.42686e-06 loss)
I0405 16:37:16.807087 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000119239 (* 0.0454545 = 5.41995e-06 loss)
I0405 16:37:16.807099 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:37:16.807111 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000312691
I0405 16:37:16.807124 29564 sgd_solver.cpp:106] Iteration 22000, lr = 0.00978
I0405 16:41:06.994192 29564 solver.cpp:229] Iteration 22500, loss = 0.910531
I0405 16:41:06.994346 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 16:41:06.994365 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 16:41:06.994379 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 16:41:06.994390 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 16:41:06.994402 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 16:41:06.994415 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 16:41:06.994426 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 16:41:06.994437 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 16:41:06.994451 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 16:41:06.994462 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 16:41:06.994477 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:41:06.994488 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:41:06.994499 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:41:06.994511 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:41:06.994523 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:41:06.994534 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:41:06.994545 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:41:06.994556 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:41:06.994568 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:41:06.994580 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:41:06.994590 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:41:06.994606 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:41:06.994621 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.84864 (* 0.0454545 = 0.129484 loss)
I0405 16:41:06.994635 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.26707 (* 0.0454545 = 0.148503 loss)
I0405 16:41:06.994649 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.3054 (* 0.0454545 = 0.150245 loss)
I0405 16:41:06.994663 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.39036 (* 0.0454545 = 0.154107 loss)
I0405 16:41:06.994678 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.26613 (* 0.0454545 = 0.14846 loss)
I0405 16:41:06.994693 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.4102 (* 0.0454545 = 0.109555 loss)
I0405 16:41:06.994706 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.90522 (* 0.0454545 = 0.0411464 loss)
I0405 16:41:06.994720 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.393791 (* 0.0454545 = 0.0178996 loss)
I0405 16:41:06.994735 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.188788 (* 0.0454545 = 0.00858128 loss)
I0405 16:41:06.994752 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0142397 (* 0.0454545 = 0.000647257 loss)
I0405 16:41:06.994768 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000251032 (* 0.0454545 = 1.14105e-05 loss)
I0405 16:41:06.994782 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000230952 (* 0.0454545 = 1.04978e-05 loss)
I0405 16:41:06.994796 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000225847 (* 0.0454545 = 1.02658e-05 loss)
I0405 16:41:06.994810 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000230811 (* 0.0454545 = 1.04914e-05 loss)
I0405 16:41:06.994825 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.00023207 (* 0.0454545 = 1.05486e-05 loss)
I0405 16:41:06.994839 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000235836 (* 0.0454545 = 1.07198e-05 loss)
I0405 16:41:06.994853 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000219471 (* 0.0454545 = 9.97594e-06 loss)
I0405 16:41:06.994884 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000228509 (* 0.0454545 = 1.03868e-05 loss)
I0405 16:41:06.994899 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000242739 (* 0.0454545 = 1.10336e-05 loss)
I0405 16:41:06.994913 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000231654 (* 0.0454545 = 1.05297e-05 loss)
I0405 16:41:06.994928 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000230914 (* 0.0454545 = 1.04961e-05 loss)
I0405 16:41:06.994942 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000237549 (* 0.0454545 = 1.07977e-05 loss)
I0405 16:41:06.994954 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:41:06.994966 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00069723
I0405 16:41:06.994982 29564 sgd_solver.cpp:106] Iteration 22500, lr = 0.009775
I0405 16:44:57.369372 29564 solver.cpp:229] Iteration 23000, loss = 0.913343
I0405 16:44:57.369560 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.03125
I0405 16:44:57.369581 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 16:44:57.369593 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 16:44:57.369607 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 16:44:57.369621 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.0625
I0405 16:44:57.369632 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.28125
I0405 16:44:57.369644 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 16:44:57.369655 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 16:44:57.369668 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 16:44:57.369679 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 16:44:57.369690 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:44:57.369702 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:44:57.369714 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:44:57.369725 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:44:57.369737 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:44:57.369748 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:44:57.369760 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:44:57.369771 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:44:57.369783 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:44:57.369794 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:44:57.369807 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:44:57.369817 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:44:57.369832 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.34406 (* 0.0454545 = 0.152003 loss)
I0405 16:44:57.369846 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.63896 (* 0.0454545 = 0.165407 loss)
I0405 16:44:57.369860 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.52457 (* 0.0454545 = 0.160208 loss)
I0405 16:44:57.369874 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.67372 (* 0.0454545 = 0.166987 loss)
I0405 16:44:57.369889 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.40006 (* 0.0454545 = 0.154548 loss)
I0405 16:44:57.369902 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.95034 (* 0.0454545 = 0.134106 loss)
I0405 16:44:57.369915 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.71845 (* 0.0454545 = 0.0781115 loss)
I0405 16:44:57.369930 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.434738 (* 0.0454545 = 0.0197608 loss)
I0405 16:44:57.369943 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0166748 (* 0.0454545 = 0.000757944 loss)
I0405 16:44:57.369957 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0053613 (* 0.0454545 = 0.000243695 loss)
I0405 16:44:57.369972 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 6.83065e-05 (* 0.0454545 = 3.10484e-06 loss)
I0405 16:44:57.369987 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 6.41416e-05 (* 0.0454545 = 2.91553e-06 loss)
I0405 16:44:57.370000 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 6.69711e-05 (* 0.0454545 = 3.04414e-06 loss)
I0405 16:44:57.370014 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 6.44646e-05 (* 0.0454545 = 2.93021e-06 loss)
I0405 16:44:57.370028 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.34275e-05 (* 0.0454545 = 2.88307e-06 loss)
I0405 16:44:57.370043 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.13192e-05 (* 0.0454545 = 2.78724e-06 loss)
I0405 16:44:57.370056 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 6.43749e-05 (* 0.0454545 = 2.92613e-06 loss)
I0405 16:44:57.370084 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 6.23113e-05 (* 0.0454545 = 2.83233e-06 loss)
I0405 16:44:57.370098 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.66951e-05 (* 0.0454545 = 3.03159e-06 loss)
I0405 16:44:57.370113 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 6.33759e-05 (* 0.0454545 = 2.88072e-06 loss)
I0405 16:44:57.370127 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 6.37337e-05 (* 0.0454545 = 2.89699e-06 loss)
I0405 16:44:57.370141 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 6.36295e-05 (* 0.0454545 = 2.89225e-06 loss)
I0405 16:44:57.370153 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:44:57.370164 29564 solver.cpp:245]     Train net output #45: total_confidence = 3.14313e-05
I0405 16:44:57.370179 29564 sgd_solver.cpp:106] Iteration 23000, lr = 0.00977
I0405 16:48:47.660567 29564 solver.cpp:229] Iteration 23500, loss = 0.907179
I0405 16:48:47.660715 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.125
I0405 16:48:47.660738 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 16:48:47.660751 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 16:48:47.660764 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 16:48:47.660776 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.15625
I0405 16:48:47.660790 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.28125
I0405 16:48:47.660802 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.53125
I0405 16:48:47.660815 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.75
I0405 16:48:47.660827 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 16:48:47.660840 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 16:48:47.660851 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:48:47.660862 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:48:47.660873 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:48:47.660884 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:48:47.660897 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:48:47.660907 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:48:47.660918 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:48:47.660930 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:48:47.660941 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:48:47.660953 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:48:47.660964 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:48:47.660974 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:48:47.660990 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.87838 (* 0.0454545 = 0.130836 loss)
I0405 16:48:47.661005 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.9207 (* 0.0454545 = 0.132759 loss)
I0405 16:48:47.661017 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.26254 (* 0.0454545 = 0.148297 loss)
I0405 16:48:47.661031 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.03282 (* 0.0454545 = 0.137855 loss)
I0405 16:48:47.661046 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.00132 (* 0.0454545 = 0.136424 loss)
I0405 16:48:47.661059 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.52046 (* 0.0454545 = 0.114567 loss)
I0405 16:48:47.661073 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.91265 (* 0.0454545 = 0.0869386 loss)
I0405 16:48:47.661087 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.926509 (* 0.0454545 = 0.042114 loss)
I0405 16:48:47.661101 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.610704 (* 0.0454545 = 0.0277593 loss)
I0405 16:48:47.661115 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.392 (* 0.0454545 = 0.0178182 loss)
I0405 16:48:47.661129 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000102461 (* 0.0454545 = 4.6573e-06 loss)
I0405 16:48:47.661144 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 9.50164e-05 (* 0.0454545 = 4.31893e-06 loss)
I0405 16:48:47.661159 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 9.79713e-05 (* 0.0454545 = 4.45324e-06 loss)
I0405 16:48:47.661172 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 9.80969e-05 (* 0.0454545 = 4.45895e-06 loss)
I0405 16:48:47.661186 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 9.85416e-05 (* 0.0454545 = 4.47916e-06 loss)
I0405 16:48:47.661201 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 8.94176e-05 (* 0.0454545 = 4.06443e-06 loss)
I0405 16:48:47.661214 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 9.38959e-05 (* 0.0454545 = 4.26799e-06 loss)
I0405 16:48:47.661245 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 9.79719e-05 (* 0.0454545 = 4.45327e-06 loss)
I0405 16:48:47.661262 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 9.54952e-05 (* 0.0454545 = 4.34069e-06 loss)
I0405 16:48:47.661275 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 9.16024e-05 (* 0.0454545 = 4.16375e-06 loss)
I0405 16:48:47.661289 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 9.47039e-05 (* 0.0454545 = 4.30472e-06 loss)
I0405 16:48:47.661303 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000102361 (* 0.0454545 = 4.65277e-06 loss)
I0405 16:48:47.661316 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:48:47.661329 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00043428
I0405 16:48:47.661342 29564 sgd_solver.cpp:106] Iteration 23500, lr = 0.009765
I0405 16:52:38.924685 29564 solver.cpp:229] Iteration 24000, loss = 0.906987
I0405 16:52:38.924885 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 16:52:38.924904 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 16:52:38.924917 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 16:52:38.924929 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 16:52:38.924942 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 16:52:38.924954 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.625
I0405 16:52:38.924967 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 16:52:38.924978 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 16:52:38.924990 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 16:52:38.925001 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 16:52:38.925014 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:52:38.925025 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:52:38.925037 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:52:38.925050 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:52:38.925060 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:52:38.925071 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:52:38.925083 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:52:38.925094 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:52:38.925106 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:52:38.925117 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:52:38.925128 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:52:38.925139 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:52:38.925154 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.94792 (* 0.0454545 = 0.133996 loss)
I0405 16:52:38.925169 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.16242 (* 0.0454545 = 0.143746 loss)
I0405 16:52:38.925184 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.17124 (* 0.0454545 = 0.144147 loss)
I0405 16:52:38.925196 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.2862 (* 0.0454545 = 0.149373 loss)
I0405 16:52:38.925211 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.80692 (* 0.0454545 = 0.127587 loss)
I0405 16:52:38.925225 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.61985 (* 0.0454545 = 0.0736294 loss)
I0405 16:52:38.925240 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.799759 (* 0.0454545 = 0.0363527 loss)
I0405 16:52:38.925253 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.453939 (* 0.0454545 = 0.0206336 loss)
I0405 16:52:38.925267 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.171609 (* 0.0454545 = 0.00780041 loss)
I0405 16:52:38.925282 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.142308 (* 0.0454545 = 0.00646855 loss)
I0405 16:52:38.925297 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 7.26556e-05 (* 0.0454545 = 3.30253e-06 loss)
I0405 16:52:38.925312 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 6.7825e-05 (* 0.0454545 = 3.08295e-06 loss)
I0405 16:52:38.925325 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 6.72243e-05 (* 0.0454545 = 3.05565e-06 loss)
I0405 16:52:38.925339 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 6.70051e-05 (* 0.0454545 = 3.04569e-06 loss)
I0405 16:52:38.925356 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.68895e-05 (* 0.0454545 = 3.04043e-06 loss)
I0405 16:52:38.925370 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.42672e-05 (* 0.0454545 = 2.92124e-06 loss)
I0405 16:52:38.925384 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 6.08484e-05 (* 0.0454545 = 2.76584e-06 loss)
I0405 16:52:38.925416 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 5.95698e-05 (* 0.0454545 = 2.70772e-06 loss)
I0405 16:52:38.925431 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.68045e-05 (* 0.0454545 = 3.03657e-06 loss)
I0405 16:52:38.925446 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 6.40825e-05 (* 0.0454545 = 2.91284e-06 loss)
I0405 16:52:38.925459 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 6.57295e-05 (* 0.0454545 = 2.98771e-06 loss)
I0405 16:52:38.925474 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 6.11626e-05 (* 0.0454545 = 2.78012e-06 loss)
I0405 16:52:38.925487 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:52:38.925498 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000142646
I0405 16:52:38.925511 29564 sgd_solver.cpp:106] Iteration 24000, lr = 0.00976
I0405 16:56:29.664108 29564 solver.cpp:229] Iteration 24500, loss = 0.907831
I0405 16:56:29.664219 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 16:56:29.664239 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 16:56:29.664252 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 16:56:29.664264 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 16:56:29.664276 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.375
I0405 16:56:29.664288 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.59375
I0405 16:56:29.664300 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 16:56:29.664311 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 16:56:29.664324 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 16:56:29.664335 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 16:56:29.664347 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 16:56:29.664358 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 16:56:29.664371 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 16:56:29.664381 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 16:56:29.664393 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 16:56:29.664404 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 16:56:29.664415 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 16:56:29.664427 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 16:56:29.664438 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 16:56:29.664449 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 16:56:29.664460 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 16:56:29.664471 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 16:56:29.664489 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.04379 (* 0.0454545 = 0.138354 loss)
I0405 16:56:29.664504 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.12307 (* 0.0454545 = 0.141958 loss)
I0405 16:56:29.664518 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.30127 (* 0.0454545 = 0.150058 loss)
I0405 16:56:29.664531 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.96628 (* 0.0454545 = 0.134831 loss)
I0405 16:56:29.664546 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.64413 (* 0.0454545 = 0.120188 loss)
I0405 16:56:29.664559 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.77264 (* 0.0454545 = 0.0805744 loss)
I0405 16:56:29.664573 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.23312 (* 0.0454545 = 0.0560509 loss)
I0405 16:56:29.664587 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.521922 (* 0.0454545 = 0.0237237 loss)
I0405 16:56:29.664602 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0818824 (* 0.0454545 = 0.00372193 loss)
I0405 16:56:29.664615 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0281147 (* 0.0454545 = 0.00127794 loss)
I0405 16:56:29.664630 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000198758 (* 0.0454545 = 9.03444e-06 loss)
I0405 16:56:29.664644 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.0001659 (* 0.0454545 = 7.54092e-06 loss)
I0405 16:56:29.664659 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000198262 (* 0.0454545 = 9.01191e-06 loss)
I0405 16:56:29.664674 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000190239 (* 0.0454545 = 8.64723e-06 loss)
I0405 16:56:29.664687 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000190466 (* 0.0454545 = 8.65757e-06 loss)
I0405 16:56:29.664701 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.00016793 (* 0.0454545 = 7.6332e-06 loss)
I0405 16:56:29.664716 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.00019575 (* 0.0454545 = 8.89773e-06 loss)
I0405 16:56:29.664746 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000169403 (* 0.0454545 = 7.70013e-06 loss)
I0405 16:56:29.664762 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000175387 (* 0.0454545 = 7.97215e-06 loss)
I0405 16:56:29.664775 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000180358 (* 0.0454545 = 8.19809e-06 loss)
I0405 16:56:29.664789 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000198644 (* 0.0454545 = 9.02929e-06 loss)
I0405 16:56:29.664803 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000202263 (* 0.0454545 = 9.19375e-06 loss)
I0405 16:56:29.664816 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 16:56:29.664827 29564 solver.cpp:245]     Train net output #45: total_confidence = 9.3463e-05
I0405 16:56:29.664840 29564 sgd_solver.cpp:106] Iteration 24500, lr = 0.009755
I0405 17:00:19.844066 29564 solver.cpp:338] Iteration 25000, Testing net (#0)
I0405 17:00:30.108234 29564 solver.cpp:393] Test loss: 0.902006
I0405 17:00:30.108281 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.113
I0405 17:00:30.108307 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.075
I0405 17:00:30.108331 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.08
I0405 17:00:30.108355 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.131
I0405 17:00:30.108376 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.219
I0405 17:00:30.108397 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.506
I0405 17:00:30.108418 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.891
I0405 17:00:30.108439 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 17:00:30.108459 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 17:00:30.108482 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 17:00:30.108506 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 17:00:30.108528 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 17:00:30.108548 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 17:00:30.108567 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 17:00:30.108587 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 17:00:30.108608 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 17:00:30.108628 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 17:00:30.108647 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 17:00:30.108669 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 17:00:30.108690 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 17:00:30.108710 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 17:00:30.108729 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 17:00:30.108754 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 3.43168 (* 0.0454545 = 0.155986 loss)
I0405 17:00:30.108780 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 3.38997 (* 0.0454545 = 0.15409 loss)
I0405 17:00:30.108805 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 3.43179 (* 0.0454545 = 0.15599 loss)
I0405 17:00:30.108829 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 3.29325 (* 0.0454545 = 0.149693 loss)
I0405 17:00:30.108855 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 3.11312 (* 0.0454545 = 0.141505 loss)
I0405 17:00:30.108880 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 2.16199 (* 0.0454545 = 0.0982721 loss)
I0405 17:00:30.108906 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.685374 (* 0.0454545 = 0.0311534 loss)
I0405 17:00:30.108929 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.247247 (* 0.0454545 = 0.0112385 loss)
I0405 17:00:30.108955 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0602433 (* 0.0454545 = 0.00273833 loss)
I0405 17:00:30.108980 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0270347 (* 0.0454545 = 0.00122885 loss)
I0405 17:00:30.109005 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 0.000227296 (* 0.0454545 = 1.03316e-05 loss)
I0405 17:00:30.109030 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 0.000210804 (* 0.0454545 = 9.58199e-06 loss)
I0405 17:00:30.109055 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 0.000214178 (* 0.0454545 = 9.73537e-06 loss)
I0405 17:00:30.109079 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 0.000212654 (* 0.0454545 = 9.66609e-06 loss)
I0405 17:00:30.109103 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 0.000202015 (* 0.0454545 = 9.18248e-06 loss)
I0405 17:00:30.109129 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 0.000194703 (* 0.0454545 = 8.85015e-06 loss)
I0405 17:00:30.109155 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 0.000194811 (* 0.0454545 = 8.85505e-06 loss)
I0405 17:00:30.109218 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 0.000190102 (* 0.0454545 = 8.64101e-06 loss)
I0405 17:00:30.109244 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 0.000209457 (* 0.0454545 = 9.52078e-06 loss)
I0405 17:00:30.109268 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 0.00019699 (* 0.0454545 = 8.9541e-06 loss)
I0405 17:00:30.109293 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 0.000199284 (* 0.0454545 = 9.05837e-06 loss)
I0405 17:00:30.109318 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 0.000195722 (* 0.0454545 = 8.89643e-06 loss)
I0405 17:00:30.109338 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0
I0405 17:00:30.109359 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.000131673
I0405 17:00:30.224400 29564 solver.cpp:229] Iteration 25000, loss = 0.906876
I0405 17:00:30.224444 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 17:00:30.224472 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 17:00:30.224494 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 17:00:30.224517 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 17:00:30.224539 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 17:00:30.224560 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 17:00:30.224583 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 17:00:30.224606 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 17:00:30.224627 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 17:00:30.224648 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 17:00:30.224669 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:00:30.224689 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:00:30.224710 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:00:30.224732 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:00:30.224753 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:00:30.224774 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:00:30.224794 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:00:30.224815 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:00:30.224834 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:00:30.224855 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:00:30.224875 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:00:30.224897 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:00:30.224925 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.12799 (* 0.0454545 = 0.142181 loss)
I0405 17:00:30.224951 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.15692 (* 0.0454545 = 0.143496 loss)
I0405 17:00:30.224977 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.37655 (* 0.0454545 = 0.153479 loss)
I0405 17:00:30.225002 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.14705 (* 0.0454545 = 0.143048 loss)
I0405 17:00:30.225026 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.88633 (* 0.0454545 = 0.131197 loss)
I0405 17:00:30.225051 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.42406 (* 0.0454545 = 0.110185 loss)
I0405 17:00:30.225075 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.28995 (* 0.0454545 = 0.0586341 loss)
I0405 17:00:30.225105 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.436196 (* 0.0454545 = 0.0198271 loss)
I0405 17:00:30.225131 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.168606 (* 0.0454545 = 0.00766393 loss)
I0405 17:00:30.225159 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0203957 (* 0.0454545 = 0.000927078 loss)
I0405 17:00:30.225208 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000388991 (* 0.0454545 = 1.76814e-05 loss)
I0405 17:00:30.225235 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000366948 (* 0.0454545 = 1.66795e-05 loss)
I0405 17:00:30.225260 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000378269 (* 0.0454545 = 1.7194e-05 loss)
I0405 17:00:30.225286 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000375054 (* 0.0454545 = 1.70479e-05 loss)
I0405 17:00:30.225316 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000361806 (* 0.0454545 = 1.64457e-05 loss)
I0405 17:00:30.225340 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.00034237 (* 0.0454545 = 1.55623e-05 loss)
I0405 17:00:30.225365 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000349733 (* 0.0454545 = 1.5897e-05 loss)
I0405 17:00:30.225390 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000343522 (* 0.0454545 = 1.56146e-05 loss)
I0405 17:00:30.225415 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000358348 (* 0.0454545 = 1.62886e-05 loss)
I0405 17:00:30.225442 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000349728 (* 0.0454545 = 1.58967e-05 loss)
I0405 17:00:30.225469 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000343808 (* 0.0454545 = 1.56276e-05 loss)
I0405 17:00:30.225494 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000360465 (* 0.0454545 = 1.63848e-05 loss)
I0405 17:00:30.225517 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:00:30.225536 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000166169
I0405 17:00:30.225559 29564 sgd_solver.cpp:106] Iteration 25000, lr = 0.00975
I0405 17:04:20.432235 29564 solver.cpp:229] Iteration 25500, loss = 0.901547
I0405 17:04:20.432476 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.21875
I0405 17:04:20.432497 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 17:04:20.432509 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 17:04:20.432523 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 17:04:20.432534 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 17:04:20.432546 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.28125
I0405 17:04:20.432557 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.625
I0405 17:04:20.432569 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 17:04:20.432580 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 17:04:20.432591 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 17:04:20.432603 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:04:20.432615 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:04:20.432626 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:04:20.432637 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:04:20.432649 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:04:20.432660 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:04:20.432672 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:04:20.432682 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:04:20.432694 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:04:20.432705 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:04:20.432716 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:04:20.432729 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:04:20.432744 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.51737 (* 0.0454545 = 0.114426 loss)
I0405 17:04:20.432757 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.0277 (* 0.0454545 = 0.137623 loss)
I0405 17:04:20.432771 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.95632 (* 0.0454545 = 0.134378 loss)
I0405 17:04:20.432785 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.19117 (* 0.0454545 = 0.145053 loss)
I0405 17:04:20.432798 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.81198 (* 0.0454545 = 0.127817 loss)
I0405 17:04:20.432812 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.7415 (* 0.0454545 = 0.124614 loss)
I0405 17:04:20.432826 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.29571 (* 0.0454545 = 0.0588958 loss)
I0405 17:04:20.432840 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.646563 (* 0.0454545 = 0.0293892 loss)
I0405 17:04:20.432854 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.222332 (* 0.0454545 = 0.010106 loss)
I0405 17:04:20.432868 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00781516 (* 0.0454545 = 0.000355234 loss)
I0405 17:04:20.432883 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000229037 (* 0.0454545 = 1.04108e-05 loss)
I0405 17:04:20.432901 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000197358 (* 0.0454545 = 8.97084e-06 loss)
I0405 17:04:20.432915 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000210891 (* 0.0454545 = 9.58597e-06 loss)
I0405 17:04:20.432929 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000203219 (* 0.0454545 = 9.23722e-06 loss)
I0405 17:04:20.432945 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000203283 (* 0.0454545 = 9.24013e-06 loss)
I0405 17:04:20.432958 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000207342 (* 0.0454545 = 9.42462e-06 loss)
I0405 17:04:20.432971 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000209985 (* 0.0454545 = 9.54478e-06 loss)
I0405 17:04:20.433002 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000217875 (* 0.0454545 = 9.90341e-06 loss)
I0405 17:04:20.433018 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000191462 (* 0.0454545 = 8.70281e-06 loss)
I0405 17:04:20.433032 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000227956 (* 0.0454545 = 1.03617e-05 loss)
I0405 17:04:20.433046 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.00019909 (* 0.0454545 = 9.04956e-06 loss)
I0405 17:04:20.433060 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000210548 (* 0.0454545 = 9.57038e-06 loss)
I0405 17:04:20.433073 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:04:20.433084 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000142732
I0405 17:04:20.433099 29564 sgd_solver.cpp:106] Iteration 25500, lr = 0.009745
I0405 17:08:11.240216 29564 solver.cpp:229] Iteration 26000, loss = 0.898188
I0405 17:08:11.240324 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.21875
I0405 17:08:11.240344 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 17:08:11.240355 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 17:08:11.240368 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.25
I0405 17:08:11.240380 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 17:08:11.240391 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 17:08:11.240403 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 17:08:11.240414 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 17:08:11.240427 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 17:08:11.240438 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 17:08:11.240449 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:08:11.240461 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:08:11.240473 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:08:11.240483 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:08:11.240495 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:08:11.240506 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:08:11.240517 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:08:11.240528 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:08:11.240540 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:08:11.240551 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:08:11.240562 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:08:11.240573 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:08:11.240589 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.95747 (* 0.0454545 = 0.13443 loss)
I0405 17:08:11.240603 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.91955 (* 0.0454545 = 0.132707 loss)
I0405 17:08:11.240617 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.37517 (* 0.0454545 = 0.153417 loss)
I0405 17:08:11.240631 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.95944 (* 0.0454545 = 0.13452 loss)
I0405 17:08:11.240645 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.54936 (* 0.0454545 = 0.11588 loss)
I0405 17:08:11.240659 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.17553 (* 0.0454545 = 0.0988878 loss)
I0405 17:08:11.240674 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.25374 (* 0.0454545 = 0.056988 loss)
I0405 17:08:11.240687 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 1.05755 (* 0.0454545 = 0.0480703 loss)
I0405 17:08:11.240701 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.358963 (* 0.0454545 = 0.0163165 loss)
I0405 17:08:11.240715 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.209878 (* 0.0454545 = 0.00953989 loss)
I0405 17:08:11.240730 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.2468e-05 (* 0.0454545 = 1.93036e-06 loss)
I0405 17:08:11.240744 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 4.13949e-05 (* 0.0454545 = 1.88159e-06 loss)
I0405 17:08:11.240758 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.86673e-05 (* 0.0454545 = 1.7576e-06 loss)
I0405 17:08:11.240772 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.81009e-05 (* 0.0454545 = 1.73186e-06 loss)
I0405 17:08:11.240787 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.90159e-05 (* 0.0454545 = 1.77345e-06 loss)
I0405 17:08:11.240800 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 3.71416e-05 (* 0.0454545 = 1.68826e-06 loss)
I0405 17:08:11.240814 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.52785e-05 (* 0.0454545 = 1.60357e-06 loss)
I0405 17:08:11.240844 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.53437e-05 (* 0.0454545 = 1.60653e-06 loss)
I0405 17:08:11.240859 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 3.92413e-05 (* 0.0454545 = 1.78369e-06 loss)
I0405 17:08:11.240874 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.57571e-05 (* 0.0454545 = 1.62532e-06 loss)
I0405 17:08:11.240887 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.62622e-05 (* 0.0454545 = 1.64828e-06 loss)
I0405 17:08:11.240901 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.79333e-05 (* 0.0454545 = 1.72424e-06 loss)
I0405 17:08:11.240914 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:08:11.240926 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00037837
I0405 17:08:11.240939 29564 sgd_solver.cpp:106] Iteration 26000, lr = 0.00974
I0405 17:12:01.679661 29564 solver.cpp:229] Iteration 26500, loss = 0.897151
I0405 17:12:01.679909 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 17:12:01.679930 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 17:12:01.679942 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.1875
I0405 17:12:01.679955 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 17:12:01.679968 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 17:12:01.679980 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 17:12:01.679991 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 17:12:01.680003 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 17:12:01.680016 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 17:12:01.680027 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 17:12:01.680039 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:12:01.680058 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:12:01.680094 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:12:01.680107 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:12:01.680119 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:12:01.680130 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:12:01.680141 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:12:01.680152 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:12:01.680163 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:12:01.680174 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:12:01.680186 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:12:01.680197 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:12:01.680212 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.74982 (* 0.0454545 = 0.124992 loss)
I0405 17:12:01.680227 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.16766 (* 0.0454545 = 0.143984 loss)
I0405 17:12:01.680241 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.12891 (* 0.0454545 = 0.142223 loss)
I0405 17:12:01.680255 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.08776 (* 0.0454545 = 0.140353 loss)
I0405 17:12:01.680269 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.86345 (* 0.0454545 = 0.130157 loss)
I0405 17:12:01.680282 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.35933 (* 0.0454545 = 0.107242 loss)
I0405 17:12:01.680296 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.22476 (* 0.0454545 = 0.0556709 loss)
I0405 17:12:01.680312 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.300092 (* 0.0454545 = 0.0136406 loss)
I0405 17:12:01.680327 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.116854 (* 0.0454545 = 0.00531156 loss)
I0405 17:12:01.680341 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0264152 (* 0.0454545 = 0.00120069 loss)
I0405 17:12:01.680356 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000161365 (* 0.0454545 = 7.33478e-06 loss)
I0405 17:12:01.680371 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000158366 (* 0.0454545 = 7.19845e-06 loss)
I0405 17:12:01.680384 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000147136 (* 0.0454545 = 6.68799e-06 loss)
I0405 17:12:01.680398 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000142949 (* 0.0454545 = 6.49768e-06 loss)
I0405 17:12:01.680411 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000140272 (* 0.0454545 = 6.376e-06 loss)
I0405 17:12:01.680426 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000140779 (* 0.0454545 = 6.39904e-06 loss)
I0405 17:12:01.680439 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000130924 (* 0.0454545 = 5.95111e-06 loss)
I0405 17:12:01.680469 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000133295 (* 0.0454545 = 6.05887e-06 loss)
I0405 17:12:01.680483 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000144011 (* 0.0454545 = 6.54594e-06 loss)
I0405 17:12:01.680497 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000140628 (* 0.0454545 = 6.39219e-06 loss)
I0405 17:12:01.680511 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000142205 (* 0.0454545 = 6.46386e-06 loss)
I0405 17:12:01.680526 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000143437 (* 0.0454545 = 6.51986e-06 loss)
I0405 17:12:01.680537 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:12:01.680548 29564 solver.cpp:245]     Train net output #45: total_confidence = 1.74388e-05
I0405 17:12:01.680562 29564 sgd_solver.cpp:106] Iteration 26500, lr = 0.009735
I0405 17:15:52.063196 29564 solver.cpp:229] Iteration 27000, loss = 0.897092
I0405 17:15:52.063316 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 17:15:52.063336 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 17:15:52.063349 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 17:15:52.063361 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 17:15:52.063374 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.34375
I0405 17:15:52.063385 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 17:15:52.063397 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.59375
I0405 17:15:52.063410 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 17:15:52.063422 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 17:15:52.063434 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 17:15:52.063446 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:15:52.063457 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:15:52.063469 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:15:52.063480 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:15:52.063493 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:15:52.063503 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:15:52.063515 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:15:52.063529 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:15:52.063541 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:15:52.063552 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:15:52.063563 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:15:52.063575 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:15:52.063590 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.80489 (* 0.0454545 = 0.127495 loss)
I0405 17:15:52.063603 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.22032 (* 0.0454545 = 0.146378 loss)
I0405 17:15:52.063618 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.22563 (* 0.0454545 = 0.146619 loss)
I0405 17:15:52.063632 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.05709 (* 0.0454545 = 0.138959 loss)
I0405 17:15:52.063647 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.56995 (* 0.0454545 = 0.116816 loss)
I0405 17:15:52.063660 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.37172 (* 0.0454545 = 0.107805 loss)
I0405 17:15:52.063674 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.79181 (* 0.0454545 = 0.0814457 loss)
I0405 17:15:52.063689 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.583848 (* 0.0454545 = 0.0265385 loss)
I0405 17:15:52.063702 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.426971 (* 0.0454545 = 0.0194078 loss)
I0405 17:15:52.063716 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.383321 (* 0.0454545 = 0.0174237 loss)
I0405 17:15:52.063731 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.00014389 (* 0.0454545 = 6.54045e-06 loss)
I0405 17:15:52.063746 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000138445 (* 0.0454545 = 6.29297e-06 loss)
I0405 17:15:52.063760 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000137399 (* 0.0454545 = 6.24541e-06 loss)
I0405 17:15:52.063774 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000136473 (* 0.0454545 = 6.20332e-06 loss)
I0405 17:15:52.063788 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.00013003 (* 0.0454545 = 5.91047e-06 loss)
I0405 17:15:52.063802 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000127654 (* 0.0454545 = 5.80244e-06 loss)
I0405 17:15:52.063817 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000125818 (* 0.0454545 = 5.71899e-06 loss)
I0405 17:15:52.063846 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000127444 (* 0.0454545 = 5.79291e-06 loss)
I0405 17:15:52.063863 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000127989 (* 0.0454545 = 5.8177e-06 loss)
I0405 17:15:52.063876 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00013333 (* 0.0454545 = 6.06043e-06 loss)
I0405 17:15:52.063891 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000127816 (* 0.0454545 = 5.80981e-06 loss)
I0405 17:15:52.063905 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000131153 (* 0.0454545 = 5.96151e-06 loss)
I0405 17:15:52.063916 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:15:52.063928 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000375065
I0405 17:15:52.063942 29564 sgd_solver.cpp:106] Iteration 27000, lr = 0.00973
I0405 17:19:42.548249 29564 solver.cpp:229] Iteration 27500, loss = 0.890448
I0405 17:19:42.548362 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 17:19:42.548382 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 17:19:42.548394 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.1875
I0405 17:19:42.548406 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 17:19:42.548419 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.34375
I0405 17:19:42.548431 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 17:19:42.548442 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 17:19:42.548454 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.78125
I0405 17:19:42.548466 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 17:19:42.548478 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 17:19:42.548490 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:19:42.548503 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:19:42.548516 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:19:42.548527 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:19:42.548538 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:19:42.548550 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:19:42.548562 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:19:42.548573 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:19:42.548588 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:19:42.548599 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:19:42.548611 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:19:42.548622 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:19:42.548638 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.97448 (* 0.0454545 = 0.135204 loss)
I0405 17:19:42.548652 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.20335 (* 0.0454545 = 0.145607 loss)
I0405 17:19:42.548666 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.10228 (* 0.0454545 = 0.141013 loss)
I0405 17:19:42.548679 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.97181 (* 0.0454545 = 0.135082 loss)
I0405 17:19:42.548693 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.52744 (* 0.0454545 = 0.114884 loss)
I0405 17:19:42.548707 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.2735 (* 0.0454545 = 0.103341 loss)
I0405 17:19:42.548722 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.31437 (* 0.0454545 = 0.0597442 loss)
I0405 17:19:42.548737 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.842246 (* 0.0454545 = 0.0382839 loss)
I0405 17:19:42.548750 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.446593 (* 0.0454545 = 0.0202997 loss)
I0405 17:19:42.548764 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0302842 (* 0.0454545 = 0.00137655 loss)
I0405 17:19:42.548779 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000132534 (* 0.0454545 = 6.02429e-06 loss)
I0405 17:19:42.548794 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000123473 (* 0.0454545 = 5.61241e-06 loss)
I0405 17:19:42.548809 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000129169 (* 0.0454545 = 5.87132e-06 loss)
I0405 17:19:42.548822 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000113365 (* 0.0454545 = 5.15297e-06 loss)
I0405 17:19:42.548836 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000114311 (* 0.0454545 = 5.19597e-06 loss)
I0405 17:19:42.548851 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000111139 (* 0.0454545 = 5.05178e-06 loss)
I0405 17:19:42.548866 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000119035 (* 0.0454545 = 5.41066e-06 loss)
I0405 17:19:42.548897 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000114031 (* 0.0454545 = 5.18323e-06 loss)
I0405 17:19:42.548912 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000120622 (* 0.0454545 = 5.48284e-06 loss)
I0405 17:19:42.548926 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.00011788 (* 0.0454545 = 5.3582e-06 loss)
I0405 17:19:42.548940 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000107147 (* 0.0454545 = 4.87032e-06 loss)
I0405 17:19:42.548954 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000117886 (* 0.0454545 = 5.35845e-06 loss)
I0405 17:19:42.548967 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:19:42.548979 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000185104
I0405 17:19:42.548992 29564 sgd_solver.cpp:106] Iteration 27500, lr = 0.009725
I0405 17:23:33.474828 29564 solver.cpp:229] Iteration 28000, loss = 0.897026
I0405 17:23:33.475018 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 17:23:33.475038 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 17:23:33.475050 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 17:23:33.475062 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 17:23:33.475075 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 17:23:33.475086 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.3125
I0405 17:23:33.475098 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.625
I0405 17:23:33.475111 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.78125
I0405 17:23:33.475121 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 17:23:33.475133 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 17:23:33.475145 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:23:33.475157 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:23:33.475168 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:23:33.475179 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:23:33.475190 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:23:33.475205 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:23:33.475217 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:23:33.475230 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:23:33.475242 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:23:33.475253 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:23:33.475265 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:23:33.475276 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:23:33.475291 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.13527 (* 0.0454545 = 0.142512 loss)
I0405 17:23:33.475306 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.25824 (* 0.0454545 = 0.148102 loss)
I0405 17:23:33.475319 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.14863 (* 0.0454545 = 0.143119 loss)
I0405 17:23:33.475333 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.27133 (* 0.0454545 = 0.148697 loss)
I0405 17:23:33.475347 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.12795 (* 0.0454545 = 0.14218 loss)
I0405 17:23:33.475360 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.8647 (* 0.0454545 = 0.130213 loss)
I0405 17:23:33.475374 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.91824 (* 0.0454545 = 0.0871928 loss)
I0405 17:23:33.475389 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 1.15486 (* 0.0454545 = 0.0524938 loss)
I0405 17:23:33.475402 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.224068 (* 0.0454545 = 0.0101849 loss)
I0405 17:23:33.475416 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00602984 (* 0.0454545 = 0.000274083 loss)
I0405 17:23:33.475430 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000173345 (* 0.0454545 = 7.8793e-06 loss)
I0405 17:23:33.475445 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000169879 (* 0.0454545 = 7.72178e-06 loss)
I0405 17:23:33.475458 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000167322 (* 0.0454545 = 7.60555e-06 loss)
I0405 17:23:33.475473 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000162054 (* 0.0454545 = 7.36608e-06 loss)
I0405 17:23:33.475487 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000155526 (* 0.0454545 = 7.06936e-06 loss)
I0405 17:23:33.475502 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000145113 (* 0.0454545 = 6.59602e-06 loss)
I0405 17:23:33.475515 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.00014853 (* 0.0454545 = 6.75135e-06 loss)
I0405 17:23:33.475545 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000154427 (* 0.0454545 = 7.01939e-06 loss)
I0405 17:23:33.475561 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000160618 (* 0.0454545 = 7.30081e-06 loss)
I0405 17:23:33.475575 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000153416 (* 0.0454545 = 6.97347e-06 loss)
I0405 17:23:33.475589 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000154307 (* 0.0454545 = 7.01394e-06 loss)
I0405 17:23:33.475603 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.00015173 (* 0.0454545 = 6.89681e-06 loss)
I0405 17:23:33.475615 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:23:33.475626 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000184161
I0405 17:23:33.475641 29564 sgd_solver.cpp:106] Iteration 28000, lr = 0.00972
I0405 17:27:24.544528 29564 solver.cpp:229] Iteration 28500, loss = 0.894256
I0405 17:27:24.544661 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.21875
I0405 17:27:24.544692 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 17:27:24.544715 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 17:27:24.544740 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.34375
I0405 17:27:24.544762 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.46875
I0405 17:27:24.544783 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5625
I0405 17:27:24.544807 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 17:27:24.544829 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 17:27:24.544850 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 17:27:24.544872 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 17:27:24.544893 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:27:24.544916 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:27:24.544936 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:27:24.544957 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:27:24.544977 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:27:24.544997 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:27:24.545018 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:27:24.545044 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:27:24.545068 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:27:24.545089 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:27:24.545109 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:27:24.545128 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:27:24.545155 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.73495 (* 0.0454545 = 0.124316 loss)
I0405 17:27:24.545181 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.24896 (* 0.0454545 = 0.14768 loss)
I0405 17:27:24.545205 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.46054 (* 0.0454545 = 0.157297 loss)
I0405 17:27:24.545230 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.84533 (* 0.0454545 = 0.129333 loss)
I0405 17:27:24.545258 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.47498 (* 0.0454545 = 0.112499 loss)
I0405 17:27:24.545284 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.56715 (* 0.0454545 = 0.0712341 loss)
I0405 17:27:24.545308 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.75141 (* 0.0454545 = 0.034155 loss)
I0405 17:27:24.545334 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.290599 (* 0.0454545 = 0.0132091 loss)
I0405 17:27:24.545361 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.166349 (* 0.0454545 = 0.00756131 loss)
I0405 17:27:24.545385 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.163398 (* 0.0454545 = 0.00742718 loss)
I0405 17:27:24.545411 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.47293e-05 (* 0.0454545 = 1.5786e-06 loss)
I0405 17:27:24.545436 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.45803e-05 (* 0.0454545 = 1.57183e-06 loss)
I0405 17:27:24.545461 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.30975e-05 (* 0.0454545 = 1.50443e-06 loss)
I0405 17:27:24.545488 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.17692e-05 (* 0.0454545 = 1.44406e-06 loss)
I0405 17:27:24.545514 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.11452e-05 (* 0.0454545 = 1.41569e-06 loss)
I0405 17:27:24.545539 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 3.21026e-05 (* 0.0454545 = 1.45921e-06 loss)
I0405 17:27:24.545563 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 2.93513e-05 (* 0.0454545 = 1.33415e-06 loss)
I0405 17:27:24.545608 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.0277e-05 (* 0.0454545 = 1.37623e-06 loss)
I0405 17:27:24.545634 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.99213e-05 (* 0.0454545 = 1.36006e-06 loss)
I0405 17:27:24.545658 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.13686e-05 (* 0.0454545 = 1.42585e-06 loss)
I0405 17:27:24.545688 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.1039e-05 (* 0.0454545 = 1.41086e-06 loss)
I0405 17:27:24.545716 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.04876e-05 (* 0.0454545 = 1.3858e-06 loss)
I0405 17:27:24.545737 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:27:24.545758 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.0019338
I0405 17:27:24.545779 29564 sgd_solver.cpp:106] Iteration 28500, lr = 0.009715
I0405 17:31:15.659024 29564 solver.cpp:229] Iteration 29000, loss = 0.896314
I0405 17:31:15.659214 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 17:31:15.659236 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 17:31:15.659251 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 17:31:15.659263 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 17:31:15.659276 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 17:31:15.659286 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 17:31:15.659298 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 17:31:15.659309 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 17:31:15.659322 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 17:31:15.659334 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 17:31:15.659346 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:31:15.659358 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:31:15.659369 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:31:15.659380 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:31:15.659391 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:31:15.659402 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:31:15.659415 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:31:15.659425 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:31:15.659436 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:31:15.659447 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:31:15.659459 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:31:15.659471 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:31:15.659485 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.86013 (* 0.0454545 = 0.130006 loss)
I0405 17:31:15.659500 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.02756 (* 0.0454545 = 0.137617 loss)
I0405 17:31:15.659514 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.18718 (* 0.0454545 = 0.144872 loss)
I0405 17:31:15.659528 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.06113 (* 0.0454545 = 0.139142 loss)
I0405 17:31:15.659541 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.84677 (* 0.0454545 = 0.129399 loss)
I0405 17:31:15.659555 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.56905 (* 0.0454545 = 0.116775 loss)
I0405 17:31:15.659569 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.50159 (* 0.0454545 = 0.068254 loss)
I0405 17:31:15.659584 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.625972 (* 0.0454545 = 0.0284533 loss)
I0405 17:31:15.659597 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.193977 (* 0.0454545 = 0.00881712 loss)
I0405 17:31:15.659611 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.131145 (* 0.0454545 = 0.00596114 loss)
I0405 17:31:15.659626 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 7.88382e-05 (* 0.0454545 = 3.58355e-06 loss)
I0405 17:31:15.659639 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 7.07165e-05 (* 0.0454545 = 3.21439e-06 loss)
I0405 17:31:15.659653 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 7.69689e-05 (* 0.0454545 = 3.49859e-06 loss)
I0405 17:31:15.659667 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 7.19512e-05 (* 0.0454545 = 3.27051e-06 loss)
I0405 17:31:15.659682 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.50727e-05 (* 0.0454545 = 2.95785e-06 loss)
I0405 17:31:15.659695 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 7.26161e-05 (* 0.0454545 = 3.30073e-06 loss)
I0405 17:31:15.659709 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 6.95664e-05 (* 0.0454545 = 3.16211e-06 loss)
I0405 17:31:15.659741 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 6.94829e-05 (* 0.0454545 = 3.15832e-06 loss)
I0405 17:31:15.659756 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.98521e-05 (* 0.0454545 = 3.1751e-06 loss)
I0405 17:31:15.659771 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 7.10076e-05 (* 0.0454545 = 3.22762e-06 loss)
I0405 17:31:15.659785 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 6.95897e-05 (* 0.0454545 = 3.16317e-06 loss)
I0405 17:31:15.659798 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 7.16344e-05 (* 0.0454545 = 3.25611e-06 loss)
I0405 17:31:15.659811 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:31:15.659822 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000216207
I0405 17:31:15.659837 29564 sgd_solver.cpp:106] Iteration 29000, lr = 0.00971
I0405 17:35:07.240355 29564 solver.cpp:229] Iteration 29500, loss = 0.893307
I0405 17:35:07.240459 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 17:35:07.240483 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 17:35:07.240496 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 17:35:07.240509 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 17:35:07.240521 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.15625
I0405 17:35:07.240533 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.25
I0405 17:35:07.240545 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 17:35:07.240557 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 17:35:07.240571 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 17:35:07.240582 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 17:35:07.240593 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:35:07.240605 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:35:07.240617 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:35:07.240628 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:35:07.240640 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:35:07.240653 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:35:07.240664 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:35:07.240675 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:35:07.240686 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:35:07.240699 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:35:07.240710 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:35:07.240720 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:35:07.240736 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.69179 (* 0.0454545 = 0.122354 loss)
I0405 17:35:07.240749 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.03889 (* 0.0454545 = 0.138131 loss)
I0405 17:35:07.240764 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.00457 (* 0.0454545 = 0.136572 loss)
I0405 17:35:07.240778 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.89336 (* 0.0454545 = 0.131516 loss)
I0405 17:35:07.240792 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.81834 (* 0.0454545 = 0.128106 loss)
I0405 17:35:07.240808 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.74712 (* 0.0454545 = 0.124869 loss)
I0405 17:35:07.240823 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.27913 (* 0.0454545 = 0.0581421 loss)
I0405 17:35:07.240836 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.783573 (* 0.0454545 = 0.0356169 loss)
I0405 17:35:07.240851 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.35623 (* 0.0454545 = 0.0161923 loss)
I0405 17:35:07.240865 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.254137 (* 0.0454545 = 0.0115517 loss)
I0405 17:35:07.240880 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.08872e-05 (* 0.0454545 = 1.85851e-06 loss)
I0405 17:35:07.240895 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.92738e-05 (* 0.0454545 = 1.78517e-06 loss)
I0405 17:35:07.240909 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.82417e-05 (* 0.0454545 = 1.73826e-06 loss)
I0405 17:35:07.240923 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.81672e-05 (* 0.0454545 = 1.73487e-06 loss)
I0405 17:35:07.240937 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.60769e-05 (* 0.0454545 = 1.63986e-06 loss)
I0405 17:35:07.240952 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 3.61142e-05 (* 0.0454545 = 1.64155e-06 loss)
I0405 17:35:07.240965 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.50672e-05 (* 0.0454545 = 1.59397e-06 loss)
I0405 17:35:07.240996 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.67365e-05 (* 0.0454545 = 1.66984e-06 loss)
I0405 17:35:07.241011 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 3.72842e-05 (* 0.0454545 = 1.69474e-06 loss)
I0405 17:35:07.241025 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.71537e-05 (* 0.0454545 = 1.68881e-06 loss)
I0405 17:35:07.241039 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.66881e-05 (* 0.0454545 = 1.66764e-06 loss)
I0405 17:35:07.241053 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.64831e-05 (* 0.0454545 = 1.65832e-06 loss)
I0405 17:35:07.241065 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:35:07.241077 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000625936
I0405 17:35:07.241092 29564 sgd_solver.cpp:106] Iteration 29500, lr = 0.009705
I0405 17:38:58.009238 29564 solver.cpp:338] Iteration 30000, Testing net (#0)
I0405 17:39:08.267765 29564 solver.cpp:393] Test loss: 0.773282
I0405 17:39:08.267810 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.296
I0405 17:39:08.267827 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.091
I0405 17:39:08.267839 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.08
I0405 17:39:08.267853 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.154
I0405 17:39:08.267865 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.234
I0405 17:39:08.267877 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.523
I0405 17:39:08.267889 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.892
I0405 17:39:08.267900 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 17:39:08.267911 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 17:39:08.267922 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 17:39:08.267935 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 17:39:08.267946 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 17:39:08.267956 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 17:39:08.267968 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 17:39:08.267979 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 17:39:08.267990 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 17:39:08.268002 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 17:39:08.268013 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 17:39:08.268023 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 17:39:08.268034 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 17:39:08.268045 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 17:39:08.268056 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 17:39:08.268085 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 2.69056 (* 0.0454545 = 0.122298 loss)
I0405 17:39:08.268102 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 2.9956 (* 0.0454545 = 0.136164 loss)
I0405 17:39:08.268117 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 3.06394 (* 0.0454545 = 0.13927 loss)
I0405 17:39:08.268131 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 2.93961 (* 0.0454545 = 0.133619 loss)
I0405 17:39:08.268144 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 2.72331 (* 0.0454545 = 0.123787 loss)
I0405 17:39:08.268157 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 1.7288 (* 0.0454545 = 0.078582 loss)
I0405 17:39:08.268173 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.588081 (* 0.0454545 = 0.026731 loss)
I0405 17:39:08.268188 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.213626 (* 0.0454545 = 0.00971028 loss)
I0405 17:39:08.268201 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.044369 (* 0.0454545 = 0.00201677 loss)
I0405 17:39:08.268215 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0231651 (* 0.0454545 = 0.00105296 loss)
I0405 17:39:08.268229 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 0.000105164 (* 0.0454545 = 4.78016e-06 loss)
I0405 17:39:08.268244 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 9.87274e-05 (* 0.0454545 = 4.48761e-06 loss)
I0405 17:39:08.268257 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 0.000100374 (* 0.0454545 = 4.56248e-06 loss)
I0405 17:39:08.268271 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 9.89721e-05 (* 0.0454545 = 4.49873e-06 loss)
I0405 17:39:08.268286 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 9.41509e-05 (* 0.0454545 = 4.27958e-06 loss)
I0405 17:39:08.268301 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 9.01379e-05 (* 0.0454545 = 4.09718e-06 loss)
I0405 17:39:08.268314 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 9.30374e-05 (* 0.0454545 = 4.22897e-06 loss)
I0405 17:39:08.268362 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 9.27846e-05 (* 0.0454545 = 4.21748e-06 loss)
I0405 17:39:08.268378 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 9.69699e-05 (* 0.0454545 = 4.40772e-06 loss)
I0405 17:39:08.268391 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 9.10329e-05 (* 0.0454545 = 4.13786e-06 loss)
I0405 17:39:08.268405 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 9.2897e-05 (* 0.0454545 = 4.22259e-06 loss)
I0405 17:39:08.268419 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 9.66525e-05 (* 0.0454545 = 4.3933e-06 loss)
I0405 17:39:08.268431 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0
I0405 17:39:08.268443 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.000280943
I0405 17:39:08.383486 29564 solver.cpp:229] Iteration 30000, loss = 0.887349
I0405 17:39:08.383528 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.0625
I0405 17:39:08.383545 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 17:39:08.383558 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 17:39:08.383570 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 17:39:08.383582 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.40625
I0405 17:39:08.383594 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.3125
I0405 17:39:08.383606 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.625
I0405 17:39:08.383617 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 17:39:08.383630 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 17:39:08.383641 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 17:39:08.383653 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:39:08.383666 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:39:08.383677 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:39:08.383688 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:39:08.383699 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:39:08.383710 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:39:08.383721 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:39:08.383733 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:39:08.383745 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:39:08.383756 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:39:08.383767 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:39:08.383779 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:39:08.383792 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.97603 (* 0.0454545 = 0.135274 loss)
I0405 17:39:08.383806 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.01986 (* 0.0454545 = 0.137267 loss)
I0405 17:39:08.383821 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.94926 (* 0.0454545 = 0.134057 loss)
I0405 17:39:08.383833 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.17268 (* 0.0454545 = 0.144213 loss)
I0405 17:39:08.383847 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.39744 (* 0.0454545 = 0.108974 loss)
I0405 17:39:08.383864 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.22643 (* 0.0454545 = 0.101201 loss)
I0405 17:39:08.383879 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.41898 (* 0.0454545 = 0.064499 loss)
I0405 17:39:08.383893 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.960516 (* 0.0454545 = 0.0436598 loss)
I0405 17:39:08.383908 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.152193 (* 0.0454545 = 0.00691785 loss)
I0405 17:39:08.383939 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.183145 (* 0.0454545 = 0.00832476 loss)
I0405 17:39:08.383955 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000104048 (* 0.0454545 = 4.72944e-06 loss)
I0405 17:39:08.383970 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000116704 (* 0.0454545 = 5.30472e-06 loss)
I0405 17:39:08.383985 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000104012 (* 0.0454545 = 4.72782e-06 loss)
I0405 17:39:08.383998 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000106922 (* 0.0454545 = 4.86011e-06 loss)
I0405 17:39:08.384012 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000105121 (* 0.0454545 = 4.77822e-06 loss)
I0405 17:39:08.384026 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000101095 (* 0.0454545 = 4.59521e-06 loss)
I0405 17:39:08.384039 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 9.42179e-05 (* 0.0454545 = 4.28263e-06 loss)
I0405 17:39:08.384053 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 9.92735e-05 (* 0.0454545 = 4.51243e-06 loss)
I0405 17:39:08.384083 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.00010259 (* 0.0454545 = 4.6632e-06 loss)
I0405 17:39:08.384102 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 9.73478e-05 (* 0.0454545 = 4.4249e-06 loss)
I0405 17:39:08.384117 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 9.2855e-05 (* 0.0454545 = 4.22068e-06 loss)
I0405 17:39:08.384131 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 9.80352e-05 (* 0.0454545 = 4.45615e-06 loss)
I0405 17:39:08.384143 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:39:08.384155 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000587551
I0405 17:39:08.384172 29564 sgd_solver.cpp:106] Iteration 30000, lr = 0.0097
I0405 17:42:59.758301 29564 solver.cpp:229] Iteration 30500, loss = 0.890624
I0405 17:42:59.758561 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 17:42:59.758582 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 17:42:59.758595 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 17:42:59.758608 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 17:42:59.758620 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 17:42:59.758632 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 17:42:59.758644 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 17:42:59.758659 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 17:42:59.758672 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 17:42:59.758685 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 17:42:59.758697 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:42:59.758708 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:42:59.758719 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:42:59.758731 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:42:59.758743 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:42:59.758754 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:42:59.758766 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:42:59.758777 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:42:59.758790 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:42:59.758801 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:42:59.758812 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:42:59.758823 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:42:59.758839 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.533 (* 0.0454545 = 0.115137 loss)
I0405 17:42:59.758854 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.95701 (* 0.0454545 = 0.134409 loss)
I0405 17:42:59.758868 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.07722 (* 0.0454545 = 0.139874 loss)
I0405 17:42:59.758882 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.04866 (* 0.0454545 = 0.138575 loss)
I0405 17:42:59.758895 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.74385 (* 0.0454545 = 0.12472 loss)
I0405 17:42:59.758910 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.05799 (* 0.0454545 = 0.0935448 loss)
I0405 17:42:59.758924 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.896193 (* 0.0454545 = 0.040736 loss)
I0405 17:42:59.758939 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.336516 (* 0.0454545 = 0.0152962 loss)
I0405 17:42:59.758952 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.021998 (* 0.0454545 = 0.000999908 loss)
I0405 17:42:59.758967 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00635294 (* 0.0454545 = 0.00028877 loss)
I0405 17:42:59.758981 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.29315e-05 (* 0.0454545 = 1.49689e-06 loss)
I0405 17:42:59.758996 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.32612e-05 (* 0.0454545 = 1.51187e-06 loss)
I0405 17:42:59.759011 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.39731e-05 (* 0.0454545 = 1.54423e-06 loss)
I0405 17:42:59.759024 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.12717e-05 (* 0.0454545 = 1.42144e-06 loss)
I0405 17:42:59.759038 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.14245e-05 (* 0.0454545 = 1.42839e-06 loss)
I0405 17:42:59.759052 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 3.14263e-05 (* 0.0454545 = 1.42847e-06 loss)
I0405 17:42:59.759069 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.0443e-05 (* 0.0454545 = 1.38377e-06 loss)
I0405 17:42:59.759099 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.19294e-05 (* 0.0454545 = 1.45134e-06 loss)
I0405 17:42:59.759114 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.97982e-05 (* 0.0454545 = 1.35446e-06 loss)
I0405 17:42:59.759129 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.17243e-05 (* 0.0454545 = 1.44201e-06 loss)
I0405 17:42:59.759142 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.12402e-05 (* 0.0454545 = 1.42001e-06 loss)
I0405 17:42:59.759157 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.04466e-05 (* 0.0454545 = 1.38394e-06 loss)
I0405 17:42:59.759169 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:42:59.759181 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000663195
I0405 17:42:59.759194 29564 sgd_solver.cpp:106] Iteration 30500, lr = 0.009695
I0405 17:46:51.477682 29564 solver.cpp:229] Iteration 31000, loss = 0.88693
I0405 17:46:51.477790 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 17:46:51.477809 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 17:46:51.477823 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.1875
I0405 17:46:51.477834 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 17:46:51.477846 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 17:46:51.477859 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 17:46:51.477869 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 17:46:51.477881 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 17:46:51.477893 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 17:46:51.477905 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 17:46:51.477916 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:46:51.477928 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:46:51.477939 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:46:51.477952 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:46:51.477962 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:46:51.477973 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:46:51.477984 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:46:51.477995 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:46:51.478008 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:46:51.478018 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:46:51.478029 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:46:51.478040 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:46:51.478056 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.78232 (* 0.0454545 = 0.126469 loss)
I0405 17:46:51.478075 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.98051 (* 0.0454545 = 0.135478 loss)
I0405 17:46:51.478088 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.90055 (* 0.0454545 = 0.131843 loss)
I0405 17:46:51.478104 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.78209 (* 0.0454545 = 0.126458 loss)
I0405 17:46:51.478117 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.86439 (* 0.0454545 = 0.1302 loss)
I0405 17:46:51.478132 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.9033 (* 0.0454545 = 0.0865136 loss)
I0405 17:46:51.478145 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.20436 (* 0.0454545 = 0.0547435 loss)
I0405 17:46:51.478159 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.546809 (* 0.0454545 = 0.024855 loss)
I0405 17:46:51.478173 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.164054 (* 0.0454545 = 0.00745701 loss)
I0405 17:46:51.478190 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.021302 (* 0.0454545 = 0.000968271 loss)
I0405 17:46:51.478205 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000185882 (* 0.0454545 = 8.4492e-06 loss)
I0405 17:46:51.478220 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000187954 (* 0.0454545 = 8.54338e-06 loss)
I0405 17:46:51.478235 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000200464 (* 0.0454545 = 9.112e-06 loss)
I0405 17:46:51.478248 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.00018412 (* 0.0454545 = 8.3691e-06 loss)
I0405 17:46:51.478263 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000168762 (* 0.0454545 = 7.67101e-06 loss)
I0405 17:46:51.478277 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000177979 (* 0.0454545 = 8.08995e-06 loss)
I0405 17:46:51.478291 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000172834 (* 0.0454545 = 7.8561e-06 loss)
I0405 17:46:51.478322 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000174534 (* 0.0454545 = 7.93335e-06 loss)
I0405 17:46:51.478337 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000173068 (* 0.0454545 = 7.86674e-06 loss)
I0405 17:46:51.478350 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000173868 (* 0.0454545 = 7.90309e-06 loss)
I0405 17:46:51.478364 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.00016849 (* 0.0454545 = 7.65861e-06 loss)
I0405 17:46:51.478379 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000176158 (* 0.0454545 = 8.00716e-06 loss)
I0405 17:46:51.478390 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:46:51.478402 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000420971
I0405 17:46:51.478417 29564 sgd_solver.cpp:106] Iteration 31000, lr = 0.00969
I0405 17:50:42.637169 29564 solver.cpp:229] Iteration 31500, loss = 0.887862
I0405 17:50:42.637313 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.125
I0405 17:50:42.637332 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 17:50:42.637349 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 17:50:42.637362 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 17:50:42.637375 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 17:50:42.637387 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.28125
I0405 17:50:42.637399 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 17:50:42.637410 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.96875
I0405 17:50:42.637423 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 17:50:42.637434 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 17:50:42.637446 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:50:42.637457 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:50:42.637470 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:50:42.637480 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:50:42.637491 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:50:42.637502 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:50:42.637514 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:50:42.637526 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:50:42.637537 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:50:42.637548 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:50:42.637560 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:50:42.637572 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:50:42.637586 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.87591 (* 0.0454545 = 0.130723 loss)
I0405 17:50:42.637601 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.04676 (* 0.0454545 = 0.138489 loss)
I0405 17:50:42.637615 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.09824 (* 0.0454545 = 0.140829 loss)
I0405 17:50:42.637630 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.09861 (* 0.0454545 = 0.140846 loss)
I0405 17:50:42.637645 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.7404 (* 0.0454545 = 0.124564 loss)
I0405 17:50:42.637660 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.59028 (* 0.0454545 = 0.11774 loss)
I0405 17:50:42.637673 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.67996 (* 0.0454545 = 0.0763616 loss)
I0405 17:50:42.637687 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.233575 (* 0.0454545 = 0.010617 loss)
I0405 17:50:42.637702 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.16123 (* 0.0454545 = 0.00732866 loss)
I0405 17:50:42.637717 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.179591 (* 0.0454545 = 0.00816321 loss)
I0405 17:50:42.637730 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 8.67299e-05 (* 0.0454545 = 3.94227e-06 loss)
I0405 17:50:42.637745 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 8.28693e-05 (* 0.0454545 = 3.76679e-06 loss)
I0405 17:50:42.637759 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 8.49114e-05 (* 0.0454545 = 3.85961e-06 loss)
I0405 17:50:42.637773 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 8.18409e-05 (* 0.0454545 = 3.72004e-06 loss)
I0405 17:50:42.637786 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 7.53521e-05 (* 0.0454545 = 3.4251e-06 loss)
I0405 17:50:42.637801 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 8.25001e-05 (* 0.0454545 = 3.75e-06 loss)
I0405 17:50:42.637816 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.37143e-05 (* 0.0454545 = 3.35065e-06 loss)
I0405 17:50:42.637845 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 7.90779e-05 (* 0.0454545 = 3.59445e-06 loss)
I0405 17:50:42.637861 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.9e-05 (* 0.0454545 = 3.59091e-06 loss)
I0405 17:50:42.637876 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 8.57756e-05 (* 0.0454545 = 3.89889e-06 loss)
I0405 17:50:42.637889 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.95366e-05 (* 0.0454545 = 3.6153e-06 loss)
I0405 17:50:42.637903 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 7.63301e-05 (* 0.0454545 = 3.46955e-06 loss)
I0405 17:50:42.637915 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:50:42.637928 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000134873
I0405 17:50:42.637943 29564 sgd_solver.cpp:106] Iteration 31500, lr = 0.009685
I0405 17:54:33.654799 29564 solver.cpp:229] Iteration 32000, loss = 0.883081
I0405 17:54:33.654947 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 17:54:33.654968 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 17:54:33.654980 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 17:54:33.654994 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.03125
I0405 17:54:33.655006 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 17:54:33.655019 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 17:54:33.655030 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 17:54:33.655041 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 17:54:33.655053 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 17:54:33.655066 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 17:54:33.655077 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:54:33.655092 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:54:33.655104 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:54:33.655115 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:54:33.655128 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:54:33.655138 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:54:33.655150 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:54:33.655161 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:54:33.655172 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:54:33.655184 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:54:33.655195 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:54:33.655206 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:54:33.655222 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.93183 (* 0.0454545 = 0.133265 loss)
I0405 17:54:33.655236 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.01076 (* 0.0454545 = 0.136853 loss)
I0405 17:54:33.655251 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.9963 (* 0.0454545 = 0.136195 loss)
I0405 17:54:33.655264 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.15284 (* 0.0454545 = 0.143311 loss)
I0405 17:54:33.655278 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.89333 (* 0.0454545 = 0.131515 loss)
I0405 17:54:33.655292 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.11579 (* 0.0454545 = 0.0961725 loss)
I0405 17:54:33.655305 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.04048 (* 0.0454545 = 0.0472947 loss)
I0405 17:54:33.655319 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.578017 (* 0.0454545 = 0.0262735 loss)
I0405 17:54:33.655333 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.324491 (* 0.0454545 = 0.0147496 loss)
I0405 17:54:33.655347 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.255678 (* 0.0454545 = 0.0116217 loss)
I0405 17:54:33.655361 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 7.51013e-05 (* 0.0454545 = 3.4137e-06 loss)
I0405 17:54:33.655375 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 7.54623e-05 (* 0.0454545 = 3.4301e-06 loss)
I0405 17:54:33.655390 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 7.41251e-05 (* 0.0454545 = 3.36932e-06 loss)
I0405 17:54:33.655403 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 6.70643e-05 (* 0.0454545 = 3.04838e-06 loss)
I0405 17:54:33.655417 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.95182e-05 (* 0.0454545 = 3.15992e-06 loss)
I0405 17:54:33.655431 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 7.18261e-05 (* 0.0454545 = 3.26482e-06 loss)
I0405 17:54:33.655446 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 6.53808e-05 (* 0.0454545 = 2.97185e-06 loss)
I0405 17:54:33.655472 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 7.33713e-05 (* 0.0454545 = 3.33506e-06 loss)
I0405 17:54:33.655488 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.76439e-05 (* 0.0454545 = 3.07472e-06 loss)
I0405 17:54:33.655503 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 7.32197e-05 (* 0.0454545 = 3.32817e-06 loss)
I0405 17:54:33.655516 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.10882e-05 (* 0.0454545 = 3.23128e-06 loss)
I0405 17:54:33.655530 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 6.26737e-05 (* 0.0454545 = 2.84881e-06 loss)
I0405 17:54:33.655544 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:54:33.655557 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000212227
I0405 17:54:33.655570 29564 sgd_solver.cpp:106] Iteration 32000, lr = 0.00968
I0405 17:58:25.390166 29564 solver.cpp:229] Iteration 32500, loss = 0.886963
I0405 17:58:25.390259 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 17:58:25.390276 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 17:58:25.390290 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 17:58:25.390301 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.21875
I0405 17:58:25.390314 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 17:58:25.390326 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 17:58:25.390338 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 17:58:25.390349 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 17:58:25.390362 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 17:58:25.390373 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 17:58:25.390385 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 17:58:25.390396 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 17:58:25.390408 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 17:58:25.390419 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 17:58:25.390430 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 17:58:25.390441 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 17:58:25.390452 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 17:58:25.390463 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 17:58:25.390475 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 17:58:25.390486 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 17:58:25.390497 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 17:58:25.390508 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 17:58:25.390524 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.70035 (* 0.0454545 = 0.122743 loss)
I0405 17:58:25.390538 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.07881 (* 0.0454545 = 0.139946 loss)
I0405 17:58:25.390552 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.10153 (* 0.0454545 = 0.140979 loss)
I0405 17:58:25.390566 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.76958 (* 0.0454545 = 0.12589 loss)
I0405 17:58:25.390580 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.3753 (* 0.0454545 = 0.107968 loss)
I0405 17:58:25.390594 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.15284 (* 0.0454545 = 0.0978562 loss)
I0405 17:58:25.390609 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.1629 (* 0.0454545 = 0.0528591 loss)
I0405 17:58:25.390622 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.374017 (* 0.0454545 = 0.0170008 loss)
I0405 17:58:25.390636 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.454455 (* 0.0454545 = 0.020657 loss)
I0405 17:58:25.390651 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0244606 (* 0.0454545 = 0.00111185 loss)
I0405 17:58:25.390666 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000184123 (* 0.0454545 = 8.36925e-06 loss)
I0405 17:58:25.390681 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000178309 (* 0.0454545 = 8.10497e-06 loss)
I0405 17:58:25.390694 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.00017862 (* 0.0454545 = 8.11907e-06 loss)
I0405 17:58:25.390709 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000174453 (* 0.0454545 = 7.92967e-06 loss)
I0405 17:58:25.390723 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000167913 (* 0.0454545 = 7.6324e-06 loss)
I0405 17:58:25.390738 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000159956 (* 0.0454545 = 7.27075e-06 loss)
I0405 17:58:25.390753 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000163181 (* 0.0454545 = 7.4173e-06 loss)
I0405 17:58:25.390782 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000169284 (* 0.0454545 = 7.69475e-06 loss)
I0405 17:58:25.390797 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000168509 (* 0.0454545 = 7.65948e-06 loss)
I0405 17:58:25.390811 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000167443 (* 0.0454545 = 7.61104e-06 loss)
I0405 17:58:25.390826 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000171983 (* 0.0454545 = 7.81741e-06 loss)
I0405 17:58:25.390839 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000163234 (* 0.0454545 = 7.41973e-06 loss)
I0405 17:58:25.390851 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 17:58:25.390863 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000512341
I0405 17:58:25.390879 29564 sgd_solver.cpp:106] Iteration 32500, lr = 0.009675
I0405 18:02:16.639050 29564 solver.cpp:229] Iteration 33000, loss = 0.881066
I0405 18:02:16.639216 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.3125
I0405 18:02:16.639235 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.1875
I0405 18:02:16.639248 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.1875
I0405 18:02:16.639261 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 18:02:16.639273 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.40625
I0405 18:02:16.639286 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.65625
I0405 18:02:16.639297 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.875
I0405 18:02:16.639308 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 18:02:16.639320 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 18:02:16.639333 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 18:02:16.639344 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:02:16.639356 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:02:16.639367 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:02:16.639379 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:02:16.639390 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:02:16.639402 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:02:16.639413 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:02:16.639425 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:02:16.639441 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:02:16.639452 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:02:16.639463 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:02:16.639475 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:02:16.639490 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.35687 (* 0.0454545 = 0.10713 loss)
I0405 18:02:16.639505 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.78672 (* 0.0454545 = 0.126669 loss)
I0405 18:02:16.639519 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.9442 (* 0.0454545 = 0.133827 loss)
I0405 18:02:16.639533 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.11072 (* 0.0454545 = 0.141396 loss)
I0405 18:02:16.639547 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.32545 (* 0.0454545 = 0.105702 loss)
I0405 18:02:16.639561 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.26931 (* 0.0454545 = 0.0576957 loss)
I0405 18:02:16.639575 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.527974 (* 0.0454545 = 0.0239988 loss)
I0405 18:02:16.639590 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.236325 (* 0.0454545 = 0.0107421 loss)
I0405 18:02:16.639605 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.256138 (* 0.0454545 = 0.0116427 loss)
I0405 18:02:16.639621 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.296418 (* 0.0454545 = 0.0134735 loss)
I0405 18:02:16.639638 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 5.22337e-05 (* 0.0454545 = 2.37426e-06 loss)
I0405 18:02:16.639653 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.33106e-05 (* 0.0454545 = 2.42321e-06 loss)
I0405 18:02:16.639667 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 5.68303e-05 (* 0.0454545 = 2.5832e-06 loss)
I0405 18:02:16.639683 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 5.27143e-05 (* 0.0454545 = 2.3961e-06 loss)
I0405 18:02:16.639696 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.85173e-05 (* 0.0454545 = 2.20533e-06 loss)
I0405 18:02:16.639711 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 5.17752e-05 (* 0.0454545 = 2.35342e-06 loss)
I0405 18:02:16.639725 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 5.17653e-05 (* 0.0454545 = 2.35297e-06 loss)
I0405 18:02:16.639755 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 4.85504e-05 (* 0.0454545 = 2.20684e-06 loss)
I0405 18:02:16.639770 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 5.07925e-05 (* 0.0454545 = 2.30875e-06 loss)
I0405 18:02:16.639785 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.89789e-05 (* 0.0454545 = 2.22632e-06 loss)
I0405 18:02:16.639798 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 5.10664e-05 (* 0.0454545 = 2.3212e-06 loss)
I0405 18:02:16.639813 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.86617e-05 (* 0.0454545 = 2.2119e-06 loss)
I0405 18:02:16.639827 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:02:16.639837 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000622457
I0405 18:02:16.639852 29564 sgd_solver.cpp:106] Iteration 33000, lr = 0.00967
I0405 18:06:06.958649 29564 solver.cpp:229] Iteration 33500, loss = 0.88189
I0405 18:06:06.958780 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 18:06:06.958799 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 18:06:06.958812 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 18:06:06.958824 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 18:06:06.958837 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.15625
I0405 18:06:06.958848 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 18:06:06.958860 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 18:06:06.958873 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 18:06:06.958884 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 18:06:06.958895 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 18:06:06.958907 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:06:06.958919 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:06:06.958930 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:06:06.958941 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:06:06.958953 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:06:06.958964 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:06:06.958976 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:06:06.958987 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:06:06.958999 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:06:06.959010 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:06:06.959022 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:06:06.959033 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:06:06.959049 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.61494 (* 0.0454545 = 0.118861 loss)
I0405 18:06:06.959066 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.9249 (* 0.0454545 = 0.13295 loss)
I0405 18:06:06.959080 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.95732 (* 0.0454545 = 0.134424 loss)
I0405 18:06:06.959095 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.94349 (* 0.0454545 = 0.133795 loss)
I0405 18:06:06.959108 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.81973 (* 0.0454545 = 0.128169 loss)
I0405 18:06:06.959123 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.22787 (* 0.0454545 = 0.101267 loss)
I0405 18:06:06.959137 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.48598 (* 0.0454545 = 0.0675443 loss)
I0405 18:06:06.959151 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.374727 (* 0.0454545 = 0.0170331 loss)
I0405 18:06:06.959166 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0744086 (* 0.0454545 = 0.00338221 loss)
I0405 18:06:06.959180 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0287328 (* 0.0454545 = 0.00130603 loss)
I0405 18:06:06.959194 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000103445 (* 0.0454545 = 4.70205e-06 loss)
I0405 18:06:06.959209 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 9.82795e-05 (* 0.0454545 = 4.46725e-06 loss)
I0405 18:06:06.959223 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.00010305 (* 0.0454545 = 4.6841e-06 loss)
I0405 18:06:06.959239 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 9.76559e-05 (* 0.0454545 = 4.4389e-06 loss)
I0405 18:06:06.959254 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 9.75964e-05 (* 0.0454545 = 4.4362e-06 loss)
I0405 18:06:06.959267 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 9.92411e-05 (* 0.0454545 = 4.51096e-06 loss)
I0405 18:06:06.959281 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 9.64346e-05 (* 0.0454545 = 4.38339e-06 loss)
I0405 18:06:06.959311 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.00010117 (* 0.0454545 = 4.59864e-06 loss)
I0405 18:06:06.959327 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 9.19487e-05 (* 0.0454545 = 4.17949e-06 loss)
I0405 18:06:06.959342 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 9.69645e-05 (* 0.0454545 = 4.40748e-06 loss)
I0405 18:06:06.959355 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 9.84725e-05 (* 0.0454545 = 4.47602e-06 loss)
I0405 18:06:06.959369 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 9.61062e-05 (* 0.0454545 = 4.36847e-06 loss)
I0405 18:06:06.959383 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:06:06.959393 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000194459
I0405 18:06:06.959408 29564 sgd_solver.cpp:106] Iteration 33500, lr = 0.009665
I0405 18:09:59.248327 29564 solver.cpp:229] Iteration 34000, loss = 0.877774
I0405 18:09:59.248473 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 18:09:59.248493 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 18:09:59.248507 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 18:09:59.248518 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.25
I0405 18:09:59.248531 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 18:09:59.248543 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 18:09:59.248554 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.625
I0405 18:09:59.248566 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 18:09:59.248579 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 18:09:59.248590 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 18:09:59.248602 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:09:59.248613 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:09:59.248625 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:09:59.248636 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:09:59.248647 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:09:59.248659 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:09:59.248670 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:09:59.248682 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:09:59.248693 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:09:59.248705 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:09:59.248716 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:09:59.248728 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:09:59.248744 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.7915 (* 0.0454545 = 0.126886 loss)
I0405 18:09:59.248757 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.88835 (* 0.0454545 = 0.131289 loss)
I0405 18:09:59.248771 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.04253 (* 0.0454545 = 0.138297 loss)
I0405 18:09:59.248785 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.80941 (* 0.0454545 = 0.127701 loss)
I0405 18:09:59.248800 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.59526 (* 0.0454545 = 0.117966 loss)
I0405 18:09:59.248812 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.89866 (* 0.0454545 = 0.0863028 loss)
I0405 18:09:59.248826 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.37304 (* 0.0454545 = 0.0624107 loss)
I0405 18:09:59.248841 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.690988 (* 0.0454545 = 0.0314085 loss)
I0405 18:09:59.248853 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.33395 (* 0.0454545 = 0.0151795 loss)
I0405 18:09:59.248867 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.158363 (* 0.0454545 = 0.00719832 loss)
I0405 18:09:59.248883 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 9.50193e-05 (* 0.0454545 = 4.31906e-06 loss)
I0405 18:09:59.248896 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 9.45776e-05 (* 0.0454545 = 4.29898e-06 loss)
I0405 18:09:59.248911 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 9.23862e-05 (* 0.0454545 = 4.19937e-06 loss)
I0405 18:09:59.248925 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 8.51725e-05 (* 0.0454545 = 3.87148e-06 loss)
I0405 18:09:59.248939 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 8.46572e-05 (* 0.0454545 = 3.84806e-06 loss)
I0405 18:09:59.248953 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 9.3739e-05 (* 0.0454545 = 4.26086e-06 loss)
I0405 18:09:59.248968 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 9.14057e-05 (* 0.0454545 = 4.15481e-06 loss)
I0405 18:09:59.248996 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 8.8777e-05 (* 0.0454545 = 4.03532e-06 loss)
I0405 18:09:59.249011 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 9.34592e-05 (* 0.0454545 = 4.24815e-06 loss)
I0405 18:09:59.249025 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 8.68274e-05 (* 0.0454545 = 3.9467e-06 loss)
I0405 18:09:59.249039 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 8.72831e-05 (* 0.0454545 = 3.96742e-06 loss)
I0405 18:09:59.249053 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 8.66716e-05 (* 0.0454545 = 3.93962e-06 loss)
I0405 18:09:59.249066 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:09:59.249078 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.0013354
I0405 18:09:59.249092 29564 sgd_solver.cpp:106] Iteration 34000, lr = 0.00966
I0405 18:13:50.034175 29564 solver.cpp:229] Iteration 34500, loss = 0.88215
I0405 18:13:50.034407 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.125
I0405 18:13:50.034427 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 18:13:50.034441 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 18:13:50.034453 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 18:13:50.034466 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 18:13:50.034476 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 18:13:50.034488 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 18:13:50.034500 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 18:13:50.034512 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 18:13:50.034523 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 18:13:50.034535 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:13:50.034549 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:13:50.034561 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:13:50.034574 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:13:50.034585 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:13:50.034596 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:13:50.034607 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:13:50.034620 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:13:50.034631 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:13:50.034641 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:13:50.034653 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:13:50.034664 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:13:50.034680 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.00829 (* 0.0454545 = 0.136741 loss)
I0405 18:13:50.034695 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.00421 (* 0.0454545 = 0.136555 loss)
I0405 18:13:50.034709 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.08507 (* 0.0454545 = 0.140231 loss)
I0405 18:13:50.034723 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.16141 (* 0.0454545 = 0.1437 loss)
I0405 18:13:50.034737 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.62207 (* 0.0454545 = 0.119185 loss)
I0405 18:13:50.034751 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.37427 (* 0.0454545 = 0.107922 loss)
I0405 18:13:50.034765 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.28485 (* 0.0454545 = 0.0584025 loss)
I0405 18:13:50.034781 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.640628 (* 0.0454545 = 0.0291194 loss)
I0405 18:13:50.034796 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.423822 (* 0.0454545 = 0.0192646 loss)
I0405 18:13:50.034811 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.201957 (* 0.0454545 = 0.00917988 loss)
I0405 18:13:50.034826 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000406478 (* 0.0454545 = 1.84763e-05 loss)
I0405 18:13:50.034840 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000409529 (* 0.0454545 = 1.86149e-05 loss)
I0405 18:13:50.034854 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000400978 (* 0.0454545 = 1.82263e-05 loss)
I0405 18:13:50.034868 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000410752 (* 0.0454545 = 1.86705e-05 loss)
I0405 18:13:50.034885 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000387254 (* 0.0454545 = 1.76025e-05 loss)
I0405 18:13:50.034900 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000382856 (* 0.0454545 = 1.74026e-05 loss)
I0405 18:13:50.034915 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000396507 (* 0.0454545 = 1.80231e-05 loss)
I0405 18:13:50.034947 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000375425 (* 0.0454545 = 1.70648e-05 loss)
I0405 18:13:50.034962 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000397998 (* 0.0454545 = 1.80908e-05 loss)
I0405 18:13:50.034977 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000380431 (* 0.0454545 = 1.72923e-05 loss)
I0405 18:13:50.034991 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000374316 (* 0.0454545 = 1.70144e-05 loss)
I0405 18:13:50.035006 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000397233 (* 0.0454545 = 1.8056e-05 loss)
I0405 18:13:50.035017 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:13:50.035029 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00013877
I0405 18:13:50.035043 29564 sgd_solver.cpp:106] Iteration 34500, lr = 0.009655
I0405 18:17:40.364109 29564 solver.cpp:338] Iteration 35000, Testing net (#0)
I0405 18:17:50.632021 29564 solver.cpp:393] Test loss: 0.781735
I0405 18:17:50.632077 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.133
I0405 18:17:50.632097 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.106
I0405 18:17:50.632110 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.087
I0405 18:17:50.632122 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.154
I0405 18:17:50.632133 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.25
I0405 18:17:50.632145 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.516
I0405 18:17:50.632158 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.89
I0405 18:17:50.632169 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 18:17:50.632180 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 18:17:50.632191 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 18:17:50.632203 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 18:17:50.632215 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 18:17:50.632226 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 18:17:50.632237 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 18:17:50.632252 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 18:17:50.632264 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 18:17:50.632275 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 18:17:50.632287 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 18:17:50.632297 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 18:17:50.632308 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 18:17:50.632319 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 18:17:50.632330 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 18:17:50.632345 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 2.99511 (* 0.0454545 = 0.136141 loss)
I0405 18:17:50.632360 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 3.00947 (* 0.0454545 = 0.136794 loss)
I0405 18:17:50.632375 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 3.03299 (* 0.0454545 = 0.137863 loss)
I0405 18:17:50.632390 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 2.91562 (* 0.0454545 = 0.132528 loss)
I0405 18:17:50.632403 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 2.68693 (* 0.0454545 = 0.122133 loss)
I0405 18:17:50.632417 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 1.76637 (* 0.0454545 = 0.0802896 loss)
I0405 18:17:50.632431 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.518297 (* 0.0454545 = 0.0235589 loss)
I0405 18:17:50.632444 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.201439 (* 0.0454545 = 0.00915632 loss)
I0405 18:17:50.632458 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0463302 (* 0.0454545 = 0.00210592 loss)
I0405 18:17:50.632473 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0245213 (* 0.0454545 = 0.0011146 loss)
I0405 18:17:50.632488 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 9.52303e-05 (* 0.0454545 = 4.32865e-06 loss)
I0405 18:17:50.632501 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 9.08131e-05 (* 0.0454545 = 4.12787e-06 loss)
I0405 18:17:50.632516 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 9.36047e-05 (* 0.0454545 = 4.25476e-06 loss)
I0405 18:17:50.632530 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 9.39037e-05 (* 0.0454545 = 4.26835e-06 loss)
I0405 18:17:50.632544 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 8.79375e-05 (* 0.0454545 = 3.99716e-06 loss)
I0405 18:17:50.632558 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 8.60312e-05 (* 0.0454545 = 3.91051e-06 loss)
I0405 18:17:50.632572 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 8.71857e-05 (* 0.0454545 = 3.96299e-06 loss)
I0405 18:17:50.632619 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 8.89129e-05 (* 0.0454545 = 4.0415e-06 loss)
I0405 18:17:50.632635 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 8.95045e-05 (* 0.0454545 = 4.06839e-06 loss)
I0405 18:17:50.632649 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 8.45376e-05 (* 0.0454545 = 3.84262e-06 loss)
I0405 18:17:50.632663 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 8.81891e-05 (* 0.0454545 = 4.0086e-06 loss)
I0405 18:17:50.632678 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 9.08137e-05 (* 0.0454545 = 4.12789e-06 loss)
I0405 18:17:50.632690 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0.001
I0405 18:17:50.632701 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.000621769
I0405 18:17:50.747671 29564 solver.cpp:229] Iteration 35000, loss = 0.876853
I0405 18:17:50.747714 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 18:17:50.747730 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 18:17:50.747742 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 18:17:50.747755 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.21875
I0405 18:17:50.747767 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 18:17:50.747778 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 18:17:50.747791 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 18:17:50.747802 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 18:17:50.747814 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 18:17:50.747827 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 18:17:50.747838 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:17:50.747849 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:17:50.747861 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:17:50.747872 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:17:50.747884 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:17:50.747895 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:17:50.747906 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:17:50.747917 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:17:50.747930 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:17:50.747941 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:17:50.747953 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:17:50.747964 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:17:50.747979 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.86783 (* 0.0454545 = 0.130356 loss)
I0405 18:17:50.747993 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.21415 (* 0.0454545 = 0.146098 loss)
I0405 18:17:50.748006 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.31425 (* 0.0454545 = 0.150648 loss)
I0405 18:17:50.748020 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.29806 (* 0.0454545 = 0.149912 loss)
I0405 18:17:50.748034 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.99383 (* 0.0454545 = 0.136083 loss)
I0405 18:17:50.748049 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.30332 (* 0.0454545 = 0.104696 loss)
I0405 18:17:50.748061 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.3483 (* 0.0454545 = 0.0612863 loss)
I0405 18:17:50.748097 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.429218 (* 0.0454545 = 0.0195099 loss)
I0405 18:17:50.748114 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.308911 (* 0.0454545 = 0.0140414 loss)
I0405 18:17:50.748147 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.162398 (* 0.0454545 = 0.00738175 loss)
I0405 18:17:50.748164 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000127094 (* 0.0454545 = 5.77701e-06 loss)
I0405 18:17:50.748178 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000132697 (* 0.0454545 = 6.03169e-06 loss)
I0405 18:17:50.748193 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000128819 (* 0.0454545 = 5.85542e-06 loss)
I0405 18:17:50.748206 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000136104 (* 0.0454545 = 6.18657e-06 loss)
I0405 18:17:50.748219 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000122085 (* 0.0454545 = 5.54932e-06 loss)
I0405 18:17:50.748234 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000124921 (* 0.0454545 = 5.67823e-06 loss)
I0405 18:17:50.748248 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000118279 (* 0.0454545 = 5.3763e-06 loss)
I0405 18:17:50.748265 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000121488 (* 0.0454545 = 5.5222e-06 loss)
I0405 18:17:50.748282 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.00012571 (* 0.0454545 = 5.71408e-06 loss)
I0405 18:17:50.748297 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000119923 (* 0.0454545 = 5.45105e-06 loss)
I0405 18:17:50.748311 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000121268 (* 0.0454545 = 5.51218e-06 loss)
I0405 18:17:50.748325 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000119454 (* 0.0454545 = 5.42974e-06 loss)
I0405 18:17:50.748337 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:17:50.748349 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000279971
I0405 18:17:50.748363 29564 sgd_solver.cpp:106] Iteration 35000, lr = 0.00965
I0405 18:21:41.871330 29564 solver.cpp:229] Iteration 35500, loss = 0.877147
I0405 18:21:41.871588 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 18:21:41.871610 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 18:21:41.871623 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 18:21:41.871637 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 18:21:41.871650 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 18:21:41.871662 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 18:21:41.871675 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 18:21:41.871686 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.96875
I0405 18:21:41.871698 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 18:21:41.871709 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 18:21:41.871721 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:21:41.871732 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:21:41.871744 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:21:41.871755 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:21:41.871767 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:21:41.871778 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:21:41.871789 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:21:41.871801 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:21:41.871812 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:21:41.871824 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:21:41.871835 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:21:41.871847 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:21:41.871861 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 3.21089 (* 0.0454545 = 0.14595 loss)
I0405 18:21:41.871876 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.17682 (* 0.0454545 = 0.144401 loss)
I0405 18:21:41.871891 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.17117 (* 0.0454545 = 0.144144 loss)
I0405 18:21:41.871903 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.96475 (* 0.0454545 = 0.134761 loss)
I0405 18:21:41.871917 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.85849 (* 0.0454545 = 0.129931 loss)
I0405 18:21:41.871932 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.52126 (* 0.0454545 = 0.114603 loss)
I0405 18:21:41.871947 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.970223 (* 0.0454545 = 0.044101 loss)
I0405 18:21:41.871960 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.268083 (* 0.0454545 = 0.0121856 loss)
I0405 18:21:41.871974 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.260413 (* 0.0454545 = 0.011837 loss)
I0405 18:21:41.871989 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0159858 (* 0.0454545 = 0.000726626 loss)
I0405 18:21:41.872004 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000104114 (* 0.0454545 = 4.73244e-06 loss)
I0405 18:21:41.872017 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.00010746 (* 0.0454545 = 4.88453e-06 loss)
I0405 18:21:41.872031 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000110269 (* 0.0454545 = 5.01224e-06 loss)
I0405 18:21:41.872046 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000108864 (* 0.0454545 = 4.94837e-06 loss)
I0405 18:21:41.872061 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000100486 (* 0.0454545 = 4.56757e-06 loss)
I0405 18:21:41.872092 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 9.43859e-05 (* 0.0454545 = 4.29027e-06 loss)
I0405 18:21:41.872108 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000104477 (* 0.0454545 = 4.74897e-06 loss)
I0405 18:21:41.872138 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 9.9365e-05 (* 0.0454545 = 4.51659e-06 loss)
I0405 18:21:41.872153 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000103387 (* 0.0454545 = 4.69941e-06 loss)
I0405 18:21:41.872166 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 9.6277e-05 (* 0.0454545 = 4.37623e-06 loss)
I0405 18:21:41.872181 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000101712 (* 0.0454545 = 4.62329e-06 loss)
I0405 18:21:41.872195 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000103639 (* 0.0454545 = 4.71087e-06 loss)
I0405 18:21:41.872207 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:21:41.872218 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000117625
I0405 18:21:41.872232 29564 sgd_solver.cpp:106] Iteration 35500, lr = 0.009645
I0405 18:25:33.293083 29564 solver.cpp:229] Iteration 36000, loss = 0.87758
I0405 18:25:33.293210 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 18:25:33.293231 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 18:25:33.293243 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 18:25:33.293256 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 18:25:33.293267 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 18:25:33.293279 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 18:25:33.293292 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 18:25:33.293303 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 18:25:33.293314 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 18:25:33.293326 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 18:25:33.293337 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:25:33.293349 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:25:33.293360 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:25:33.293375 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:25:33.293386 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:25:33.293397 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:25:33.293409 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:25:33.293421 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:25:33.293431 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:25:33.293442 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:25:33.293455 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:25:33.293467 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:25:33.293483 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.75719 (* 0.0454545 = 0.125327 loss)
I0405 18:25:33.293498 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.17073 (* 0.0454545 = 0.144124 loss)
I0405 18:25:33.293510 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.01549 (* 0.0454545 = 0.137068 loss)
I0405 18:25:33.293524 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.92407 (* 0.0454545 = 0.132912 loss)
I0405 18:25:33.293537 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.95624 (* 0.0454545 = 0.134374 loss)
I0405 18:25:33.293551 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.20423 (* 0.0454545 = 0.100192 loss)
I0405 18:25:33.293565 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.21022 (* 0.0454545 = 0.0550098 loss)
I0405 18:25:33.293579 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.428875 (* 0.0454545 = 0.0194943 loss)
I0405 18:25:33.293593 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.146978 (* 0.0454545 = 0.00668084 loss)
I0405 18:25:33.293607 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.118301 (* 0.0454545 = 0.00537733 loss)
I0405 18:25:33.293622 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 5.67061e-05 (* 0.0454545 = 2.57755e-06 loss)
I0405 18:25:33.293635 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.44518e-05 (* 0.0454545 = 2.47508e-06 loss)
I0405 18:25:33.293650 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 5.69241e-05 (* 0.0454545 = 2.58746e-06 loss)
I0405 18:25:33.293664 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 5.31514e-05 (* 0.0454545 = 2.41597e-06 loss)
I0405 18:25:33.293678 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.96641e-05 (* 0.0454545 = 2.25746e-06 loss)
I0405 18:25:33.293691 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 5.44354e-05 (* 0.0454545 = 2.47434e-06 loss)
I0405 18:25:33.293705 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 5.01075e-05 (* 0.0454545 = 2.27761e-06 loss)
I0405 18:25:33.293736 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 5.40049e-05 (* 0.0454545 = 2.45477e-06 loss)
I0405 18:25:33.293752 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 5.51429e-05 (* 0.0454545 = 2.50649e-06 loss)
I0405 18:25:33.293766 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 5.33604e-05 (* 0.0454545 = 2.42547e-06 loss)
I0405 18:25:33.293781 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 5.35372e-05 (* 0.0454545 = 2.43351e-06 loss)
I0405 18:25:33.293794 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.88201e-05 (* 0.0454545 = 2.2191e-06 loss)
I0405 18:25:33.293807 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:25:33.293818 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000192633
I0405 18:25:33.293833 29564 sgd_solver.cpp:106] Iteration 36000, lr = 0.00964
I0405 18:29:23.869829 29564 solver.cpp:229] Iteration 36500, loss = 0.8792
I0405 18:29:23.869926 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 18:29:23.869956 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 18:29:23.869978 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 18:29:23.870002 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 18:29:23.870024 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.4375
I0405 18:29:23.870045 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5
I0405 18:29:23.870065 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 18:29:23.870087 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.96875
I0405 18:29:23.870110 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 18:29:23.870129 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 18:29:23.870151 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:29:23.870170 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:29:23.870189 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:29:23.870211 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:29:23.870234 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:29:23.870254 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:29:23.870278 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:29:23.870299 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:29:23.870321 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:29:23.870342 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:29:23.870360 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:29:23.870381 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:29:23.870407 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.53342 (* 0.0454545 = 0.115155 loss)
I0405 18:29:23.870435 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.03504 (* 0.0454545 = 0.137957 loss)
I0405 18:29:23.870462 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.94923 (* 0.0454545 = 0.134056 loss)
I0405 18:29:23.870487 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.91466 (* 0.0454545 = 0.132485 loss)
I0405 18:29:23.870512 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.21141 (* 0.0454545 = 0.100519 loss)
I0405 18:29:23.870537 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.7055 (* 0.0454545 = 0.0775228 loss)
I0405 18:29:23.870563 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.958676 (* 0.0454545 = 0.0435762 loss)
I0405 18:29:23.870589 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.137543 (* 0.0454545 = 0.00625197 loss)
I0405 18:29:23.870615 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0997611 (* 0.0454545 = 0.0045346 loss)
I0405 18:29:23.870641 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0119661 (* 0.0454545 = 0.000543914 loss)
I0405 18:29:23.870668 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 2.73057e-05 (* 0.0454545 = 1.24117e-06 loss)
I0405 18:29:23.870695 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 2.86433e-05 (* 0.0454545 = 1.30197e-06 loss)
I0405 18:29:23.870721 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 2.69369e-05 (* 0.0454545 = 1.2244e-06 loss)
I0405 18:29:23.870746 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 2.54094e-05 (* 0.0454545 = 1.15497e-06 loss)
I0405 18:29:23.870776 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 2.50704e-05 (* 0.0454545 = 1.13956e-06 loss)
I0405 18:29:23.870801 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 2.38428e-05 (* 0.0454545 = 1.08376e-06 loss)
I0405 18:29:23.870826 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 2.54373e-05 (* 0.0454545 = 1.15624e-06 loss)
I0405 18:29:23.870872 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 2.50908e-05 (* 0.0454545 = 1.14049e-06 loss)
I0405 18:29:23.870898 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.42098e-05 (* 0.0454545 = 1.10045e-06 loss)
I0405 18:29:23.870923 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.46959e-05 (* 0.0454545 = 1.12254e-06 loss)
I0405 18:29:23.870947 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 2.71865e-05 (* 0.0454545 = 1.23575e-06 loss)
I0405 18:29:23.870973 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 2.44073e-05 (* 0.0454545 = 1.10942e-06 loss)
I0405 18:29:23.870995 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:29:23.871014 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00175585
I0405 18:29:23.871038 29564 sgd_solver.cpp:106] Iteration 36500, lr = 0.009635
I0405 18:33:16.870301 29564 solver.cpp:229] Iteration 37000, loss = 0.87633
I0405 18:33:16.870527 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 18:33:16.870548 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.25
I0405 18:33:16.870559 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.21875
I0405 18:33:16.870573 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.21875
I0405 18:33:16.870584 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 18:33:16.870596 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 18:33:16.870607 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 18:33:16.870620 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 18:33:16.870630 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 18:33:16.870642 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 18:33:16.870654 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:33:16.870666 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:33:16.870676 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:33:16.870687 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:33:16.870699 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:33:16.870710 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:33:16.870723 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:33:16.870733 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:33:16.870744 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:33:16.870755 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:33:16.870767 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:33:16.870779 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:33:16.870793 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.76109 (* 0.0454545 = 0.125504 loss)
I0405 18:33:16.870807 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.92329 (* 0.0454545 = 0.132877 loss)
I0405 18:33:16.870821 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.952 (* 0.0454545 = 0.134182 loss)
I0405 18:33:16.870836 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.05731 (* 0.0454545 = 0.138969 loss)
I0405 18:33:16.870849 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.79319 (* 0.0454545 = 0.126963 loss)
I0405 18:33:16.870863 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.96372 (* 0.0454545 = 0.0892602 loss)
I0405 18:33:16.870877 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.35159 (* 0.0454545 = 0.0614357 loss)
I0405 18:33:16.870892 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.811301 (* 0.0454545 = 0.0368773 loss)
I0405 18:33:16.870908 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.533483 (* 0.0454545 = 0.0242492 loss)
I0405 18:33:16.870923 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.036812 (* 0.0454545 = 0.00167328 loss)
I0405 18:33:16.870936 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 6.84134e-05 (* 0.0454545 = 3.1097e-06 loss)
I0405 18:33:16.870950 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 6.36477e-05 (* 0.0454545 = 2.89308e-06 loss)
I0405 18:33:16.870965 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 6.72391e-05 (* 0.0454545 = 3.05632e-06 loss)
I0405 18:33:16.870978 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 6.63085e-05 (* 0.0454545 = 3.01402e-06 loss)
I0405 18:33:16.870992 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.09255e-05 (* 0.0454545 = 2.76934e-06 loss)
I0405 18:33:16.871006 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.58725e-05 (* 0.0454545 = 2.99421e-06 loss)
I0405 18:33:16.871021 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 6.22128e-05 (* 0.0454545 = 2.82786e-06 loss)
I0405 18:33:16.871047 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 6.62281e-05 (* 0.0454545 = 3.01037e-06 loss)
I0405 18:33:16.871062 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.31626e-05 (* 0.0454545 = 2.87103e-06 loss)
I0405 18:33:16.871076 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 6.39175e-05 (* 0.0454545 = 2.90534e-06 loss)
I0405 18:33:16.871090 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 6.31501e-05 (* 0.0454545 = 2.87046e-06 loss)
I0405 18:33:16.871104 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 5.9546e-05 (* 0.0454545 = 2.70664e-06 loss)
I0405 18:33:16.871117 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:33:16.871129 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000823716
I0405 18:33:16.871142 29564 sgd_solver.cpp:106] Iteration 37000, lr = 0.00963
I0405 18:37:08.339591 29564 solver.cpp:229] Iteration 37500, loss = 0.877377
I0405 18:37:08.339723 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 18:37:08.339743 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 18:37:08.339757 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0
I0405 18:37:08.339769 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.34375
I0405 18:37:08.339782 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 18:37:08.339793 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 18:37:08.339805 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 18:37:08.339818 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 18:37:08.339829 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 18:37:08.339841 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 18:37:08.339853 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:37:08.339864 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:37:08.339875 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:37:08.339889 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:37:08.339900 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:37:08.339911 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:37:08.339922 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:37:08.339933 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:37:08.339944 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:37:08.339956 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:37:08.339967 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:37:08.339978 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:37:08.339994 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.8922 (* 0.0454545 = 0.131464 loss)
I0405 18:37:08.340008 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.1283 (* 0.0454545 = 0.142196 loss)
I0405 18:37:08.340023 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.12721 (* 0.0454545 = 0.142146 loss)
I0405 18:37:08.340037 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.64393 (* 0.0454545 = 0.120179 loss)
I0405 18:37:08.340051 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.39563 (* 0.0454545 = 0.108892 loss)
I0405 18:37:08.340065 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.32142 (* 0.0454545 = 0.105519 loss)
I0405 18:37:08.340093 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.994247 (* 0.0454545 = 0.045193 loss)
I0405 18:37:08.340107 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.352384 (* 0.0454545 = 0.0160174 loss)
I0405 18:37:08.340121 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.27318 (* 0.0454545 = 0.0124173 loss)
I0405 18:37:08.340136 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.345822 (* 0.0454545 = 0.0157192 loss)
I0405 18:37:08.340150 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000561237 (* 0.0454545 = 2.55108e-05 loss)
I0405 18:37:08.340164 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000581195 (* 0.0454545 = 2.6418e-05 loss)
I0405 18:37:08.340178 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000548783 (* 0.0454545 = 2.49447e-05 loss)
I0405 18:37:08.340193 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000540293 (* 0.0454545 = 2.45588e-05 loss)
I0405 18:37:08.340209 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.00054086 (* 0.0454545 = 2.45846e-05 loss)
I0405 18:37:08.340222 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000552429 (* 0.0454545 = 2.51104e-05 loss)
I0405 18:37:08.340236 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000531201 (* 0.0454545 = 2.41455e-05 loss)
I0405 18:37:08.340271 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000530355 (* 0.0454545 = 2.4107e-05 loss)
I0405 18:37:08.340288 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000572927 (* 0.0454545 = 2.60422e-05 loss)
I0405 18:37:08.340302 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000529984 (* 0.0454545 = 2.40902e-05 loss)
I0405 18:37:08.340317 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000530221 (* 0.0454545 = 2.4101e-05 loss)
I0405 18:37:08.340332 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000557207 (* 0.0454545 = 2.53276e-05 loss)
I0405 18:37:08.340343 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:37:08.340355 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000794469
I0405 18:37:08.340368 29564 sgd_solver.cpp:106] Iteration 37500, lr = 0.009625
I0405 18:40:59.697118 29564 solver.cpp:229] Iteration 38000, loss = 0.874872
I0405 18:40:59.697319 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 18:40:59.697340 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 18:40:59.697353 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 18:40:59.697365 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 18:40:59.697378 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 18:40:59.697391 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 18:40:59.697403 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 18:40:59.697415 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 18:40:59.697427 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 18:40:59.697439 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 18:40:59.697451 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:40:59.697464 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:40:59.697476 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:40:59.697489 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:40:59.697501 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:40:59.697513 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:40:59.697525 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:40:59.697536 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:40:59.697547 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:40:59.697559 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:40:59.697571 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:40:59.697582 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:40:59.697597 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.99786 (* 0.0454545 = 0.136266 loss)
I0405 18:40:59.697612 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.36943 (* 0.0454545 = 0.153156 loss)
I0405 18:40:59.697625 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.09308 (* 0.0454545 = 0.140595 loss)
I0405 18:40:59.697639 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.09788 (* 0.0454545 = 0.140813 loss)
I0405 18:40:59.697654 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.51994 (* 0.0454545 = 0.114543 loss)
I0405 18:40:59.697667 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.11464 (* 0.0454545 = 0.0961198 loss)
I0405 18:40:59.697681 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.04246 (* 0.0454545 = 0.0473846 loss)
I0405 18:40:59.697696 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.272052 (* 0.0454545 = 0.012366 loss)
I0405 18:40:59.697710 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.167192 (* 0.0454545 = 0.00759964 loss)
I0405 18:40:59.697724 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.137756 (* 0.0454545 = 0.00626163 loss)
I0405 18:40:59.697738 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 8.02155e-05 (* 0.0454545 = 3.64616e-06 loss)
I0405 18:40:59.697753 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 7.35011e-05 (* 0.0454545 = 3.34096e-06 loss)
I0405 18:40:59.697767 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 7.49556e-05 (* 0.0454545 = 3.40707e-06 loss)
I0405 18:40:59.697784 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 7.40893e-05 (* 0.0454545 = 3.36769e-06 loss)
I0405 18:40:59.697798 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.97728e-05 (* 0.0454545 = 3.17149e-06 loss)
I0405 18:40:59.697813 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.85061e-05 (* 0.0454545 = 3.11391e-06 loss)
I0405 18:40:59.697827 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.5126e-05 (* 0.0454545 = 3.41482e-06 loss)
I0405 18:40:59.697859 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 7.3191e-05 (* 0.0454545 = 3.32686e-06 loss)
I0405 18:40:59.697875 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.89629e-05 (* 0.0454545 = 3.13468e-06 loss)
I0405 18:40:59.697888 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 7.28923e-05 (* 0.0454545 = 3.31329e-06 loss)
I0405 18:40:59.697906 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.28182e-05 (* 0.0454545 = 3.30992e-06 loss)
I0405 18:40:59.697921 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 6.96984e-05 (* 0.0454545 = 3.16811e-06 loss)
I0405 18:40:59.697932 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:40:59.697944 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000231068
I0405 18:40:59.697959 29564 sgd_solver.cpp:106] Iteration 38000, lr = 0.00962
I0405 18:44:51.802055 29564 solver.cpp:229] Iteration 38500, loss = 0.872364
I0405 18:44:51.802172 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 18:44:51.802191 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 18:44:51.802203 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 18:44:51.802216 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 18:44:51.802227 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.40625
I0405 18:44:51.802239 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 18:44:51.802251 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 18:44:51.802263 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 18:44:51.802274 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 18:44:51.802285 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 18:44:51.802297 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:44:51.802309 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:44:51.802320 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:44:51.802331 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:44:51.802342 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:44:51.802353 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:44:51.802366 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:44:51.802376 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:44:51.802387 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:44:51.802398 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:44:51.802410 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:44:51.802423 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:44:51.802438 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.83129 (* 0.0454545 = 0.128695 loss)
I0405 18:44:51.802451 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.10604 (* 0.0454545 = 0.141184 loss)
I0405 18:44:51.802464 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.21685 (* 0.0454545 = 0.14622 loss)
I0405 18:44:51.802479 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.9337 (* 0.0454545 = 0.13335 loss)
I0405 18:44:51.802492 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.63171 (* 0.0454545 = 0.119623 loss)
I0405 18:44:51.802510 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.18405 (* 0.0454545 = 0.0992752 loss)
I0405 18:44:51.802523 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.62421 (* 0.0454545 = 0.0738279 loss)
I0405 18:44:51.802537 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.655526 (* 0.0454545 = 0.0297967 loss)
I0405 18:44:51.802551 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.358736 (* 0.0454545 = 0.0163062 loss)
I0405 18:44:51.802567 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.01006 (* 0.0454545 = 0.000457273 loss)
I0405 18:44:51.802580 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 9.70494e-05 (* 0.0454545 = 4.41134e-06 loss)
I0405 18:44:51.802594 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 9.49921e-05 (* 0.0454545 = 4.31782e-06 loss)
I0405 18:44:51.802609 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 9.04824e-05 (* 0.0454545 = 4.11284e-06 loss)
I0405 18:44:51.802623 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 8.7333e-05 (* 0.0454545 = 3.96968e-06 loss)
I0405 18:44:51.802637 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 8.51663e-05 (* 0.0454545 = 3.8712e-06 loss)
I0405 18:44:51.802651 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 8.34648e-05 (* 0.0454545 = 3.79386e-06 loss)
I0405 18:44:51.802665 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 8.66872e-05 (* 0.0454545 = 3.94033e-06 loss)
I0405 18:44:51.802696 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 8.05681e-05 (* 0.0454545 = 3.66219e-06 loss)
I0405 18:44:51.802711 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 9.15036e-05 (* 0.0454545 = 4.15926e-06 loss)
I0405 18:44:51.802726 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 8.2166e-05 (* 0.0454545 = 3.73482e-06 loss)
I0405 18:44:51.802739 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.95161e-05 (* 0.0454545 = 3.61437e-06 loss)
I0405 18:44:51.802752 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 8.76861e-05 (* 0.0454545 = 3.98573e-06 loss)
I0405 18:44:51.802765 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:44:51.802778 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00134112
I0405 18:44:51.802791 29564 sgd_solver.cpp:106] Iteration 38500, lr = 0.009615
I0405 18:48:43.402501 29564 solver.cpp:229] Iteration 39000, loss = 0.869528
I0405 18:48:43.402659 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.21875
I0405 18:48:43.402691 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 18:48:43.402709 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 18:48:43.402721 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 18:48:43.402734 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 18:48:43.402746 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 18:48:43.402760 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 18:48:43.402772 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 18:48:43.402784 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 18:48:43.402796 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 18:48:43.402806 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:48:43.402818 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:48:43.402829 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:48:43.402840 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:48:43.402851 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:48:43.402864 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:48:43.402875 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:48:43.402886 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:48:43.402897 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:48:43.402909 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:48:43.402920 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:48:43.402930 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:48:43.402945 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.91126 (* 0.0454545 = 0.13233 loss)
I0405 18:48:43.402959 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.26 (* 0.0454545 = 0.148182 loss)
I0405 18:48:43.402977 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.11078 (* 0.0454545 = 0.141399 loss)
I0405 18:48:43.402992 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.15959 (* 0.0454545 = 0.143618 loss)
I0405 18:48:43.403005 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.16339 (* 0.0454545 = 0.143791 loss)
I0405 18:48:43.403019 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.73081 (* 0.0454545 = 0.124128 loss)
I0405 18:48:43.403033 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.61782 (* 0.0454545 = 0.0735372 loss)
I0405 18:48:43.403048 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.463425 (* 0.0454545 = 0.0210648 loss)
I0405 18:48:43.403061 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.160109 (* 0.0454545 = 0.00727769 loss)
I0405 18:48:43.403075 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00889849 (* 0.0454545 = 0.000404477 loss)
I0405 18:48:43.403090 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000122674 (* 0.0454545 = 5.57611e-06 loss)
I0405 18:48:43.403105 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.00012834 (* 0.0454545 = 5.83362e-06 loss)
I0405 18:48:43.403120 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000123433 (* 0.0454545 = 5.61057e-06 loss)
I0405 18:48:43.403133 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000121992 (* 0.0454545 = 5.54507e-06 loss)
I0405 18:48:43.403147 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000116018 (* 0.0454545 = 5.27354e-06 loss)
I0405 18:48:43.403162 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000124335 (* 0.0454545 = 5.6516e-06 loss)
I0405 18:48:43.403179 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000116483 (* 0.0454545 = 5.29467e-06 loss)
I0405 18:48:43.403208 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000114755 (* 0.0454545 = 5.21612e-06 loss)
I0405 18:48:43.403223 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.00012918 (* 0.0454545 = 5.87182e-06 loss)
I0405 18:48:43.403237 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000121308 (* 0.0454545 = 5.514e-06 loss)
I0405 18:48:43.403252 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.00011072 (* 0.0454545 = 5.03273e-06 loss)
I0405 18:48:43.403266 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000120095 (* 0.0454545 = 5.45887e-06 loss)
I0405 18:48:43.403278 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:48:43.403290 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000896178
I0405 18:48:43.403303 29564 sgd_solver.cpp:106] Iteration 39000, lr = 0.00961
I0405 18:52:35.114548 29564 solver.cpp:229] Iteration 39500, loss = 0.872486
I0405 18:52:35.114743 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 18:52:35.114763 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 18:52:35.114775 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 18:52:35.114789 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 18:52:35.114800 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.125
I0405 18:52:35.114812 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.3125
I0405 18:52:35.114825 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 18:52:35.114836 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 18:52:35.114847 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 18:52:35.114859 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 18:52:35.114871 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:52:35.114883 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:52:35.114895 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:52:35.114907 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:52:35.114917 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:52:35.114931 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:52:35.114943 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:52:35.114954 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:52:35.114966 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:52:35.114977 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:52:35.114992 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:52:35.115005 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:52:35.115020 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.74896 (* 0.0454545 = 0.124953 loss)
I0405 18:52:35.115034 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.98195 (* 0.0454545 = 0.135543 loss)
I0405 18:52:35.115048 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.09346 (* 0.0454545 = 0.140612 loss)
I0405 18:52:35.115062 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.13268 (* 0.0454545 = 0.142394 loss)
I0405 18:52:35.115077 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.89603 (* 0.0454545 = 0.131638 loss)
I0405 18:52:35.115090 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.45107 (* 0.0454545 = 0.111412 loss)
I0405 18:52:35.115105 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.23442 (* 0.0454545 = 0.0561102 loss)
I0405 18:52:35.115119 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.591897 (* 0.0454545 = 0.0269044 loss)
I0405 18:52:35.115134 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.286073 (* 0.0454545 = 0.0130033 loss)
I0405 18:52:35.115147 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.345683 (* 0.0454545 = 0.0157129 loss)
I0405 18:52:35.115162 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 8.43552e-05 (* 0.0454545 = 3.83433e-06 loss)
I0405 18:52:35.115176 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 8.00203e-05 (* 0.0454545 = 3.63729e-06 loss)
I0405 18:52:35.115190 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 8.46896e-05 (* 0.0454545 = 3.84953e-06 loss)
I0405 18:52:35.115206 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 8.1156e-05 (* 0.0454545 = 3.68891e-06 loss)
I0405 18:52:35.115219 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 7.80594e-05 (* 0.0454545 = 3.54816e-06 loss)
I0405 18:52:35.115234 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.80287e-05 (* 0.0454545 = 3.09221e-06 loss)
I0405 18:52:35.115248 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 8.24896e-05 (* 0.0454545 = 3.74953e-06 loss)
I0405 18:52:35.115279 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 7.93822e-05 (* 0.0454545 = 3.60828e-06 loss)
I0405 18:52:35.115295 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.87081e-05 (* 0.0454545 = 3.57764e-06 loss)
I0405 18:52:35.115309 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 7.97291e-05 (* 0.0454545 = 3.62405e-06 loss)
I0405 18:52:35.115324 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.07636e-05 (* 0.0454545 = 3.21653e-06 loss)
I0405 18:52:35.115339 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 8.26595e-05 (* 0.0454545 = 3.75725e-06 loss)
I0405 18:52:35.115350 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:52:35.115362 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000694972
I0405 18:52:35.115376 29564 sgd_solver.cpp:106] Iteration 39500, lr = 0.009605
I0405 18:56:25.934914 29564 solver.cpp:338] Iteration 40000, Testing net (#0)
I0405 18:56:36.210109 29564 solver.cpp:393] Test loss: 0.777896
I0405 18:56:36.210155 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.194
I0405 18:56:36.210172 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.072
I0405 18:56:36.210186 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.109
I0405 18:56:36.210197 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.136
I0405 18:56:36.210209 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.241
I0405 18:56:36.210222 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.512
I0405 18:56:36.210234 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.896
I0405 18:56:36.210247 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 18:56:36.210258 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 18:56:36.210269 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 18:56:36.210281 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 18:56:36.210292 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 18:56:36.210304 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 18:56:36.210314 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 18:56:36.210325 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 18:56:36.210336 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 18:56:36.210347 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 18:56:36.210358 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 18:56:36.210371 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 18:56:36.210381 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 18:56:36.210392 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 18:56:36.210403 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 18:56:36.210417 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 2.89908 (* 0.0454545 = 0.131776 loss)
I0405 18:56:36.210433 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 3.04403 (* 0.0454545 = 0.138365 loss)
I0405 18:56:36.210446 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 2.98717 (* 0.0454545 = 0.135781 loss)
I0405 18:56:36.210460 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 2.93295 (* 0.0454545 = 0.133316 loss)
I0405 18:56:36.210474 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 2.68775 (* 0.0454545 = 0.12217 loss)
I0405 18:56:36.210487 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 1.80358 (* 0.0454545 = 0.0819809 loss)
I0405 18:56:36.210501 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.475701 (* 0.0454545 = 0.0216228 loss)
I0405 18:56:36.210515 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.20895 (* 0.0454545 = 0.00949773 loss)
I0405 18:56:36.210530 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0489 (* 0.0454545 = 0.00222273 loss)
I0405 18:56:36.210543 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0244788 (* 0.0454545 = 0.00111267 loss)
I0405 18:56:36.210557 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 9.69563e-05 (* 0.0454545 = 4.40711e-06 loss)
I0405 18:56:36.210575 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 9.48256e-05 (* 0.0454545 = 4.31026e-06 loss)
I0405 18:56:36.210589 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 9.4543e-05 (* 0.0454545 = 4.29741e-06 loss)
I0405 18:56:36.210603 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 9.75338e-05 (* 0.0454545 = 4.43335e-06 loss)
I0405 18:56:36.210618 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 9.27405e-05 (* 0.0454545 = 4.21548e-06 loss)
I0405 18:56:36.210631 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 9.00966e-05 (* 0.0454545 = 4.0953e-06 loss)
I0405 18:56:36.210645 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 9.12214e-05 (* 0.0454545 = 4.14643e-06 loss)
I0405 18:56:36.210692 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 9.17695e-05 (* 0.0454545 = 4.17134e-06 loss)
I0405 18:56:36.210708 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 9.63457e-05 (* 0.0454545 = 4.37935e-06 loss)
I0405 18:56:36.210722 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 8.90542e-05 (* 0.0454545 = 4.04792e-06 loss)
I0405 18:56:36.210736 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 8.77739e-05 (* 0.0454545 = 3.98972e-06 loss)
I0405 18:56:36.210749 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 9.40879e-05 (* 0.0454545 = 4.27672e-06 loss)
I0405 18:56:36.210762 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0.002
I0405 18:56:36.210773 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.00195121
I0405 18:56:36.325340 29564 solver.cpp:229] Iteration 40000, loss = 0.866179
I0405 18:56:36.325379 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 18:56:36.325397 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 18:56:36.325408 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.21875
I0405 18:56:36.325422 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 18:56:36.325433 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 18:56:36.325445 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 18:56:36.325458 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 18:56:36.325469 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 18:56:36.325481 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 18:56:36.325494 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 18:56:36.325505 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 18:56:36.325517 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 18:56:36.325530 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 18:56:36.325541 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 18:56:36.325551 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 18:56:36.325563 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 18:56:36.325575 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 18:56:36.325587 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 18:56:36.325598 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 18:56:36.325609 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 18:56:36.325620 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 18:56:36.325631 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 18:56:36.325645 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.70328 (* 0.0454545 = 0.122876 loss)
I0405 18:56:36.325660 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.20929 (* 0.0454545 = 0.145877 loss)
I0405 18:56:36.325675 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.17299 (* 0.0454545 = 0.144227 loss)
I0405 18:56:36.325688 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.15847 (* 0.0454545 = 0.143567 loss)
I0405 18:56:36.325702 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.06927 (* 0.0454545 = 0.139512 loss)
I0405 18:56:36.325716 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.37222 (* 0.0454545 = 0.107828 loss)
I0405 18:56:36.325729 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.47477 (* 0.0454545 = 0.067035 loss)
I0405 18:56:36.325743 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.782552 (* 0.0454545 = 0.0355705 loss)
I0405 18:56:36.325757 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.278553 (* 0.0454545 = 0.0126615 loss)
I0405 18:56:36.325788 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.120815 (* 0.0454545 = 0.00549161 loss)
I0405 18:56:36.325805 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 6.55108e-05 (* 0.0454545 = 2.97776e-06 loss)
I0405 18:56:36.325822 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 6.56367e-05 (* 0.0454545 = 2.98348e-06 loss)
I0405 18:56:36.325836 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 6.70342e-05 (* 0.0454545 = 3.04701e-06 loss)
I0405 18:56:36.325850 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 6.50107e-05 (* 0.0454545 = 2.95503e-06 loss)
I0405 18:56:36.325865 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.23962e-05 (* 0.0454545 = 2.83619e-06 loss)
I0405 18:56:36.325880 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.38479e-05 (* 0.0454545 = 2.90218e-06 loss)
I0405 18:56:36.325892 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 6.16248e-05 (* 0.0454545 = 2.80113e-06 loss)
I0405 18:56:36.325906 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 5.92436e-05 (* 0.0454545 = 2.69289e-06 loss)
I0405 18:56:36.325919 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.96297e-05 (* 0.0454545 = 3.16499e-06 loss)
I0405 18:56:36.325933 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 6.15501e-05 (* 0.0454545 = 2.79773e-06 loss)
I0405 18:56:36.325947 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 6.22574e-05 (* 0.0454545 = 2.82988e-06 loss)
I0405 18:56:36.325961 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 6.3891e-05 (* 0.0454545 = 2.90414e-06 loss)
I0405 18:56:36.325973 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 18:56:36.325989 29564 solver.cpp:245]     Train net output #45: total_confidence = 5.6899e-05
I0405 18:56:36.326004 29564 sgd_solver.cpp:106] Iteration 40000, lr = 0.0096
I0405 19:00:27.795512 29564 solver.cpp:229] Iteration 40500, loss = 0.871718
I0405 19:00:27.795671 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 19:00:27.795693 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 19:00:27.795706 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 19:00:27.795719 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 19:00:27.795732 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 19:00:27.795743 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 19:00:27.795755 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 19:00:27.795766 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 19:00:27.795778 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 19:00:27.795790 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 19:00:27.795801 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:00:27.795814 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:00:27.795825 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:00:27.795836 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:00:27.795847 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:00:27.795858 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:00:27.795871 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:00:27.795882 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:00:27.795893 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:00:27.795904 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:00:27.795917 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:00:27.795928 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:00:27.795943 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.82258 (* 0.0454545 = 0.128299 loss)
I0405 19:00:27.795958 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.51768 (* 0.0454545 = 0.159895 loss)
I0405 19:00:27.795972 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.41078 (* 0.0454545 = 0.155036 loss)
I0405 19:00:27.795986 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.39129 (* 0.0454545 = 0.154149 loss)
I0405 19:00:27.796000 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.72994 (* 0.0454545 = 0.124088 loss)
I0405 19:00:27.796015 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.36822 (* 0.0454545 = 0.107646 loss)
I0405 19:00:27.796027 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.884593 (* 0.0454545 = 0.0402088 loss)
I0405 19:00:27.796042 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.313835 (* 0.0454545 = 0.0142652 loss)
I0405 19:00:27.796056 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.134778 (* 0.0454545 = 0.00612628 loss)
I0405 19:00:27.796082 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0209486 (* 0.0454545 = 0.00095221 loss)
I0405 19:00:27.796100 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.00576e-05 (* 0.0454545 = 1.36625e-06 loss)
I0405 19:00:27.796115 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.09033e-05 (* 0.0454545 = 1.4047e-06 loss)
I0405 19:00:27.796129 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.38787e-05 (* 0.0454545 = 1.53994e-06 loss)
I0405 19:00:27.796144 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.11196e-05 (* 0.0454545 = 1.41453e-06 loss)
I0405 19:00:27.796159 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.03484e-05 (* 0.0454545 = 1.37947e-06 loss)
I0405 19:00:27.796172 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 3.0587e-05 (* 0.0454545 = 1.39032e-06 loss)
I0405 19:00:27.796186 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 2.99871e-05 (* 0.0454545 = 1.36305e-06 loss)
I0405 19:00:27.796233 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.1375e-05 (* 0.0454545 = 1.42614e-06 loss)
I0405 19:00:27.796252 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 3.05309e-05 (* 0.0454545 = 1.38777e-06 loss)
I0405 19:00:27.796267 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.83662e-05 (* 0.0454545 = 1.28937e-06 loss)
I0405 19:00:27.796282 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.05235e-05 (* 0.0454545 = 1.38743e-06 loss)
I0405 19:00:27.796295 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.13769e-05 (* 0.0454545 = 1.42622e-06 loss)
I0405 19:00:27.796308 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:00:27.796319 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000198853
I0405 19:00:27.796334 29564 sgd_solver.cpp:106] Iteration 40500, lr = 0.009595
I0405 19:04:19.079613 29564 solver.cpp:229] Iteration 41000, loss = 0.866866
I0405 19:04:19.079819 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.09375
I0405 19:04:19.079839 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 19:04:19.079852 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 19:04:19.079865 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 19:04:19.079877 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 19:04:19.079888 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 19:04:19.079900 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 19:04:19.079913 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 19:04:19.079924 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 19:04:19.079936 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 19:04:19.079948 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:04:19.079959 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:04:19.079972 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:04:19.079982 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:04:19.079993 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:04:19.080004 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:04:19.080019 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:04:19.080030 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:04:19.080041 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:04:19.080054 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:04:19.080065 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:04:19.080093 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:04:19.080109 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.84373 (* 0.0454545 = 0.12926 loss)
I0405 19:04:19.080123 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.0627 (* 0.0454545 = 0.139214 loss)
I0405 19:04:19.080138 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.10706 (* 0.0454545 = 0.14123 loss)
I0405 19:04:19.080152 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.08673 (* 0.0454545 = 0.140306 loss)
I0405 19:04:19.080165 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.84979 (* 0.0454545 = 0.129536 loss)
I0405 19:04:19.080179 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.04121 (* 0.0454545 = 0.0927824 loss)
I0405 19:04:19.080193 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.50471 (* 0.0454545 = 0.0683961 loss)
I0405 19:04:19.080207 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 1.06884 (* 0.0454545 = 0.0485838 loss)
I0405 19:04:19.080220 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.217965 (* 0.0454545 = 0.00990749 loss)
I0405 19:04:19.080235 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.212355 (* 0.0454545 = 0.00965249 loss)
I0405 19:04:19.080250 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000186803 (* 0.0454545 = 8.49105e-06 loss)
I0405 19:04:19.080263 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000188418 (* 0.0454545 = 8.56446e-06 loss)
I0405 19:04:19.080277 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000183377 (* 0.0454545 = 8.33533e-06 loss)
I0405 19:04:19.080291 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000173265 (* 0.0454545 = 7.87568e-06 loss)
I0405 19:04:19.080305 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000173455 (* 0.0454545 = 7.88432e-06 loss)
I0405 19:04:19.080319 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000193772 (* 0.0454545 = 8.80783e-06 loss)
I0405 19:04:19.080333 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000171792 (* 0.0454545 = 7.80871e-06 loss)
I0405 19:04:19.080364 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000181165 (* 0.0454545 = 8.23475e-06 loss)
I0405 19:04:19.080380 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000184574 (* 0.0454545 = 8.38975e-06 loss)
I0405 19:04:19.080394 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000188872 (* 0.0454545 = 8.58508e-06 loss)
I0405 19:04:19.080409 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000184579 (* 0.0454545 = 8.38994e-06 loss)
I0405 19:04:19.080425 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000163405 (* 0.0454545 = 7.4275e-06 loss)
I0405 19:04:19.080438 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:04:19.080451 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000549077
I0405 19:04:19.080464 29564 sgd_solver.cpp:106] Iteration 41000, lr = 0.00959
I0405 19:08:10.360419 29564 solver.cpp:229] Iteration 41500, loss = 0.866203
I0405 19:08:10.360534 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.21875
I0405 19:08:10.360555 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 19:08:10.360569 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 19:08:10.360580 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.03125
I0405 19:08:10.360592 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.15625
I0405 19:08:10.360605 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 19:08:10.360617 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 19:08:10.360630 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 19:08:10.360641 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 19:08:10.360652 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 19:08:10.360664 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:08:10.360676 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:08:10.360687 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:08:10.360698 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:08:10.360710 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:08:10.360723 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:08:10.360733 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:08:10.360744 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:08:10.360756 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:08:10.360767 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:08:10.360779 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:08:10.360790 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:08:10.360805 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.68512 (* 0.0454545 = 0.122051 loss)
I0405 19:08:10.360819 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.02644 (* 0.0454545 = 0.137566 loss)
I0405 19:08:10.360833 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.18877 (* 0.0454545 = 0.144944 loss)
I0405 19:08:10.360847 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.04687 (* 0.0454545 = 0.138494 loss)
I0405 19:08:10.360862 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.80336 (* 0.0454545 = 0.127426 loss)
I0405 19:08:10.360875 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.20578 (* 0.0454545 = 0.100263 loss)
I0405 19:08:10.360889 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.03883 (* 0.0454545 = 0.0472196 loss)
I0405 19:08:10.360903 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.421888 (* 0.0454545 = 0.0191767 loss)
I0405 19:08:10.360918 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.20872 (* 0.0454545 = 0.00948729 loss)
I0405 19:08:10.360932 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00415655 (* 0.0454545 = 0.000188934 loss)
I0405 19:08:10.360946 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.02778e-05 (* 0.0454545 = 1.83081e-06 loss)
I0405 19:08:10.360961 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.98809e-05 (* 0.0454545 = 1.81277e-06 loss)
I0405 19:08:10.360975 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.83627e-05 (* 0.0454545 = 1.74376e-06 loss)
I0405 19:08:10.360990 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 4.04119e-05 (* 0.0454545 = 1.8369e-06 loss)
I0405 19:08:10.361003 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.87612e-05 (* 0.0454545 = 1.76187e-06 loss)
I0405 19:08:10.361017 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.05126e-05 (* 0.0454545 = 1.84148e-06 loss)
I0405 19:08:10.361032 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.67493e-05 (* 0.0454545 = 1.67042e-06 loss)
I0405 19:08:10.361063 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.87575e-05 (* 0.0454545 = 1.7617e-06 loss)
I0405 19:08:10.361079 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.00153e-05 (* 0.0454545 = 1.81888e-06 loss)
I0405 19:08:10.361093 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.98717e-05 (* 0.0454545 = 1.81235e-06 loss)
I0405 19:08:10.361107 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.74089e-05 (* 0.0454545 = 1.7004e-06 loss)
I0405 19:08:10.361122 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.8087e-05 (* 0.0454545 = 1.73123e-06 loss)
I0405 19:08:10.361135 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:08:10.361147 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000230284
I0405 19:08:10.361161 29564 sgd_solver.cpp:106] Iteration 41500, lr = 0.009585
I0405 19:12:02.460459 29564 solver.cpp:229] Iteration 42000, loss = 0.864958
I0405 19:12:02.460661 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.3125
I0405 19:12:02.460681 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 19:12:02.460695 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 19:12:02.460706 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 19:12:02.460718 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 19:12:02.460731 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 19:12:02.460742 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 19:12:02.460754 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 19:12:02.460765 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 19:12:02.460777 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 19:12:02.460788 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:12:02.460800 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:12:02.460811 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:12:02.460824 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:12:02.460835 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:12:02.460846 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:12:02.460858 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:12:02.460870 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:12:02.460880 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:12:02.460892 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:12:02.460903 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:12:02.460916 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:12:02.460930 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.2184 (* 0.0454545 = 0.100836 loss)
I0405 19:12:02.460945 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.14868 (* 0.0454545 = 0.143122 loss)
I0405 19:12:02.460959 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.93173 (* 0.0454545 = 0.13326 loss)
I0405 19:12:02.460973 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.0667 (* 0.0454545 = 0.139396 loss)
I0405 19:12:02.460988 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.49261 (* 0.0454545 = 0.1133 loss)
I0405 19:12:02.461001 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.3319 (* 0.0454545 = 0.105996 loss)
I0405 19:12:02.461015 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.70666 (* 0.0454545 = 0.0775754 loss)
I0405 19:12:02.461030 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.859578 (* 0.0454545 = 0.0390717 loss)
I0405 19:12:02.461043 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.281854 (* 0.0454545 = 0.0128116 loss)
I0405 19:12:02.461057 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0106709 (* 0.0454545 = 0.000485039 loss)
I0405 19:12:02.461072 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 8.92675e-05 (* 0.0454545 = 4.05761e-06 loss)
I0405 19:12:02.461086 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 8.92029e-05 (* 0.0454545 = 4.05468e-06 loss)
I0405 19:12:02.461100 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 9.01272e-05 (* 0.0454545 = 4.09669e-06 loss)
I0405 19:12:02.461114 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 8.31342e-05 (* 0.0454545 = 3.77883e-06 loss)
I0405 19:12:02.461128 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 8.47695e-05 (* 0.0454545 = 3.85316e-06 loss)
I0405 19:12:02.461143 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 8.71353e-05 (* 0.0454545 = 3.96069e-06 loss)
I0405 19:12:02.461156 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 8.50015e-05 (* 0.0454545 = 3.86371e-06 loss)
I0405 19:12:02.461187 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 8.36089e-05 (* 0.0454545 = 3.8004e-06 loss)
I0405 19:12:02.461205 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 9.0966e-05 (* 0.0454545 = 4.13482e-06 loss)
I0405 19:12:02.461220 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 8.76469e-05 (* 0.0454545 = 3.98395e-06 loss)
I0405 19:12:02.461236 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 8.61838e-05 (* 0.0454545 = 3.91745e-06 loss)
I0405 19:12:02.461249 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 8.23649e-05 (* 0.0454545 = 3.74386e-06 loss)
I0405 19:12:02.461261 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:12:02.461273 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000384456
I0405 19:12:02.461287 29564 sgd_solver.cpp:106] Iteration 42000, lr = 0.00958
I0405 19:15:53.421238 29564 solver.cpp:229] Iteration 42500, loss = 0.865654
I0405 19:15:53.421414 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.125
I0405 19:15:53.421435 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 19:15:53.421449 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 19:15:53.421461 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 19:15:53.421473 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.34375
I0405 19:15:53.421485 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 19:15:53.421497 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 19:15:53.421509 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 19:15:53.421521 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 19:15:53.421533 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 19:15:53.421545 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:15:53.421557 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:15:53.421568 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:15:53.421581 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:15:53.421591 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:15:53.421603 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:15:53.421614 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:15:53.421625 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:15:53.421638 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:15:53.421648 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:15:53.421660 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:15:53.421671 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:15:53.421686 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.78056 (* 0.0454545 = 0.126389 loss)
I0405 19:15:53.421703 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.19859 (* 0.0454545 = 0.14539 loss)
I0405 19:15:53.421717 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.20374 (* 0.0454545 = 0.145624 loss)
I0405 19:15:53.421731 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.10929 (* 0.0454545 = 0.141331 loss)
I0405 19:15:53.421746 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.68797 (* 0.0454545 = 0.122181 loss)
I0405 19:15:53.421761 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.03853 (* 0.0454545 = 0.0926605 loss)
I0405 19:15:53.421774 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.987358 (* 0.0454545 = 0.0448799 loss)
I0405 19:15:53.421788 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.549688 (* 0.0454545 = 0.0249858 loss)
I0405 19:15:53.421802 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.326894 (* 0.0454545 = 0.0148588 loss)
I0405 19:15:53.421818 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.143796 (* 0.0454545 = 0.00653619 loss)
I0405 19:15:53.421833 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.36831e-05 (* 0.0454545 = 1.98559e-06 loss)
I0405 19:15:53.421846 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 4.46863e-05 (* 0.0454545 = 2.0312e-06 loss)
I0405 19:15:53.421860 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 4.47076e-05 (* 0.0454545 = 2.03216e-06 loss)
I0405 19:15:53.421875 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 4.25405e-05 (* 0.0454545 = 1.93366e-06 loss)
I0405 19:15:53.421888 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.26425e-05 (* 0.0454545 = 1.93829e-06 loss)
I0405 19:15:53.421903 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.40976e-05 (* 0.0454545 = 2.00444e-06 loss)
I0405 19:15:53.421917 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.93385e-05 (* 0.0454545 = 1.78811e-06 loss)
I0405 19:15:53.421947 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 4.19118e-05 (* 0.0454545 = 1.90508e-06 loss)
I0405 19:15:53.421962 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.49451e-05 (* 0.0454545 = 2.04296e-06 loss)
I0405 19:15:53.421977 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.09918e-05 (* 0.0454545 = 1.86326e-06 loss)
I0405 19:15:53.421990 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.87199e-05 (* 0.0454545 = 1.76e-06 loss)
I0405 19:15:53.422005 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.01499e-05 (* 0.0454545 = 1.825e-06 loss)
I0405 19:15:53.422020 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:15:53.422032 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000998883
I0405 19:15:53.422046 29564 sgd_solver.cpp:106] Iteration 42500, lr = 0.009575
I0405 19:19:45.062664 29564 solver.cpp:229] Iteration 43000, loss = 0.860307
I0405 19:19:45.062763 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 19:19:45.062783 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 19:19:45.062795 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 19:19:45.062809 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 19:19:45.062832 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 19:19:45.062854 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5
I0405 19:19:45.062867 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 19:19:45.062880 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 19:19:45.062894 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.875
I0405 19:19:45.062906 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.90625
I0405 19:19:45.062918 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:19:45.062929 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:19:45.062942 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:19:45.062952 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:19:45.062964 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:19:45.062976 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:19:45.062988 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:19:45.062999 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:19:45.063011 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:19:45.063022 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:19:45.063033 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:19:45.063045 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:19:45.063060 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.95873 (* 0.0454545 = 0.134488 loss)
I0405 19:19:45.063074 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.07301 (* 0.0454545 = 0.139682 loss)
I0405 19:19:45.063088 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.21901 (* 0.0454545 = 0.146319 loss)
I0405 19:19:45.063104 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.08584 (* 0.0454545 = 0.140266 loss)
I0405 19:19:45.063118 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.70195 (* 0.0454545 = 0.122816 loss)
I0405 19:19:45.063133 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.90139 (* 0.0454545 = 0.0864266 loss)
I0405 19:19:45.063150 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.37064 (* 0.0454545 = 0.0623016 loss)
I0405 19:19:45.063164 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.71528 (* 0.0454545 = 0.0325127 loss)
I0405 19:19:45.063179 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.60382 (* 0.0454545 = 0.0274464 loss)
I0405 19:19:45.063192 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.422511 (* 0.0454545 = 0.019205 loss)
I0405 19:19:45.063206 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000100136 (* 0.0454545 = 4.55166e-06 loss)
I0405 19:19:45.063221 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 9.24426e-05 (* 0.0454545 = 4.20194e-06 loss)
I0405 19:19:45.063235 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 9.09499e-05 (* 0.0454545 = 4.13409e-06 loss)
I0405 19:19:45.063249 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 9.1853e-05 (* 0.0454545 = 4.17514e-06 loss)
I0405 19:19:45.063264 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 9.13249e-05 (* 0.0454545 = 4.15113e-06 loss)
I0405 19:19:45.063278 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 9.38928e-05 (* 0.0454545 = 4.26785e-06 loss)
I0405 19:19:45.063292 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 9.01991e-05 (* 0.0454545 = 4.09996e-06 loss)
I0405 19:19:45.063324 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 8.78102e-05 (* 0.0454545 = 3.99137e-06 loss)
I0405 19:19:45.063340 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 9.68835e-05 (* 0.0454545 = 4.40379e-06 loss)
I0405 19:19:45.063354 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 8.7746e-05 (* 0.0454545 = 3.98845e-06 loss)
I0405 19:19:45.063369 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 8.46091e-05 (* 0.0454545 = 3.84587e-06 loss)
I0405 19:19:45.063383 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 9.06076e-05 (* 0.0454545 = 4.11853e-06 loss)
I0405 19:19:45.063395 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:19:45.063407 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00130942
I0405 19:19:45.063421 29564 sgd_solver.cpp:106] Iteration 43000, lr = 0.00957
I0405 19:23:36.085948 29564 solver.cpp:229] Iteration 43500, loss = 0.862804
I0405 19:23:36.086133 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 19:23:36.086153 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 19:23:36.086165 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 19:23:36.086177 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.21875
I0405 19:23:36.086190 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 19:23:36.086202 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 19:23:36.086215 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 19:23:36.086225 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 1
I0405 19:23:36.086237 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 19:23:36.086248 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 19:23:36.086259 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:23:36.086272 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:23:36.086282 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:23:36.086294 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:23:36.086307 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:23:36.086318 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:23:36.086328 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:23:36.086340 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:23:36.086351 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:23:36.086362 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:23:36.086374 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:23:36.086385 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:23:36.086401 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.49357 (* 0.0454545 = 0.113344 loss)
I0405 19:23:36.086416 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.00379 (* 0.0454545 = 0.136536 loss)
I0405 19:23:36.086429 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.99682 (* 0.0454545 = 0.136219 loss)
I0405 19:23:36.086443 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.76924 (* 0.0454545 = 0.125874 loss)
I0405 19:23:36.086457 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.60016 (* 0.0454545 = 0.118189 loss)
I0405 19:23:36.086472 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.03151 (* 0.0454545 = 0.0923414 loss)
I0405 19:23:36.086484 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.02616 (* 0.0454545 = 0.0466435 loss)
I0405 19:23:36.086498 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.0515811 (* 0.0454545 = 0.0023446 loss)
I0405 19:23:36.086513 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0125797 (* 0.0454545 = 0.000571803 loss)
I0405 19:23:36.086539 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00393825 (* 0.0454545 = 0.000179011 loss)
I0405 19:23:36.086563 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 2.58881e-05 (* 0.0454545 = 1.17673e-06 loss)
I0405 19:23:36.086580 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 2.6268e-05 (* 0.0454545 = 1.194e-06 loss)
I0405 19:23:36.086593 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 2.5806e-05 (* 0.0454545 = 1.173e-06 loss)
I0405 19:23:36.086608 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 2.53589e-05 (* 0.0454545 = 1.15268e-06 loss)
I0405 19:23:36.086622 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 2.38799e-05 (* 0.0454545 = 1.08545e-06 loss)
I0405 19:23:36.086637 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 2.54633e-05 (* 0.0454545 = 1.15742e-06 loss)
I0405 19:23:36.086650 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 2.30864e-05 (* 0.0454545 = 1.04938e-06 loss)
I0405 19:23:36.086681 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 2.35782e-05 (* 0.0454545 = 1.07174e-06 loss)
I0405 19:23:36.086700 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.45729e-05 (* 0.0454545 = 1.11695e-06 loss)
I0405 19:23:36.086715 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.45729e-05 (* 0.0454545 = 1.11695e-06 loss)
I0405 19:23:36.086730 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 2.5739e-05 (* 0.0454545 = 1.16995e-06 loss)
I0405 19:23:36.086743 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 2.30342e-05 (* 0.0454545 = 1.04701e-06 loss)
I0405 19:23:36.086755 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:23:36.086766 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000877131
I0405 19:23:36.086783 29564 sgd_solver.cpp:106] Iteration 43500, lr = 0.009565
I0405 19:27:27.175858 29564 solver.cpp:229] Iteration 44000, loss = 0.859356
I0405 19:27:27.175997 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.34375
I0405 19:27:27.176017 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0
I0405 19:27:27.176029 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0
I0405 19:27:27.176041 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 19:27:27.176054 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 19:27:27.176065 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 19:27:27.176101 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 19:27:27.176115 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 19:27:27.176126 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 19:27:27.176138 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 19:27:27.176149 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:27:27.176162 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:27:27.176172 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:27:27.176183 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:27:27.176194 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:27:27.176205 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:27:27.176218 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:27:27.176229 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:27:27.176239 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:27:27.176250 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:27:27.176262 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:27:27.176273 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:27:27.176290 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.42813 (* 0.0454545 = 0.110369 loss)
I0405 19:27:27.176303 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.35971 (* 0.0454545 = 0.152714 loss)
I0405 19:27:27.176321 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.16774 (* 0.0454545 = 0.143988 loss)
I0405 19:27:27.176334 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.28281 (* 0.0454545 = 0.149219 loss)
I0405 19:27:27.176348 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.10805 (* 0.0454545 = 0.141275 loss)
I0405 19:27:27.176362 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.47508 (* 0.0454545 = 0.112504 loss)
I0405 19:27:27.176378 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.66811 (* 0.0454545 = 0.075823 loss)
I0405 19:27:27.176391 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.837175 (* 0.0454545 = 0.0380534 loss)
I0405 19:27:27.176405 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.121308 (* 0.0454545 = 0.00551402 loss)
I0405 19:27:27.176420 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0105869 (* 0.0454545 = 0.000481223 loss)
I0405 19:27:27.176434 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.65992e-05 (* 0.0454545 = 1.6636e-06 loss)
I0405 19:27:27.176448 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.71133e-05 (* 0.0454545 = 1.68697e-06 loss)
I0405 19:27:27.176462 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.37847e-05 (* 0.0454545 = 1.53567e-06 loss)
I0405 19:27:27.176476 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.70615e-05 (* 0.0454545 = 1.68461e-06 loss)
I0405 19:27:27.176491 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.50323e-05 (* 0.0454545 = 1.59238e-06 loss)
I0405 19:27:27.176504 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 3.32644e-05 (* 0.0454545 = 1.51202e-06 loss)
I0405 19:27:27.176518 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.43069e-05 (* 0.0454545 = 1.55941e-06 loss)
I0405 19:27:27.176550 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.33268e-05 (* 0.0454545 = 1.51486e-06 loss)
I0405 19:27:27.176565 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 3.81369e-05 (* 0.0454545 = 1.7335e-06 loss)
I0405 19:27:27.176580 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.33971e-05 (* 0.0454545 = 1.51805e-06 loss)
I0405 19:27:27.176594 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.1979e-05 (* 0.0454545 = 1.45359e-06 loss)
I0405 19:27:27.176609 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.40571e-05 (* 0.0454545 = 1.54805e-06 loss)
I0405 19:27:27.176620 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:27:27.176632 29564 solver.cpp:245]     Train net output #45: total_confidence = 8.58875e-05
I0405 19:27:27.176647 29564 sgd_solver.cpp:106] Iteration 44000, lr = 0.00956
I0405 19:31:18.475551 29564 solver.cpp:229] Iteration 44500, loss = 0.86463
I0405 19:31:18.475837 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.21875
I0405 19:31:18.475859 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 19:31:18.475872 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 19:31:18.475884 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 19:31:18.475898 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 19:31:18.475909 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 19:31:18.475921 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 19:31:18.475934 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 19:31:18.475945 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 19:31:18.475957 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 19:31:18.475968 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:31:18.475980 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:31:18.475992 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:31:18.476004 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:31:18.476018 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:31:18.476029 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:31:18.476042 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:31:18.476052 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:31:18.476063 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:31:18.476091 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:31:18.476104 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:31:18.476116 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:31:18.476131 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.70421 (* 0.0454545 = 0.122919 loss)
I0405 19:31:18.476145 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.97339 (* 0.0454545 = 0.135154 loss)
I0405 19:31:18.476160 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.01669 (* 0.0454545 = 0.137122 loss)
I0405 19:31:18.476173 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.05325 (* 0.0454545 = 0.138784 loss)
I0405 19:31:18.476187 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.73357 (* 0.0454545 = 0.124253 loss)
I0405 19:31:18.476202 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.96309 (* 0.0454545 = 0.0892312 loss)
I0405 19:31:18.476214 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.04099 (* 0.0454545 = 0.0473176 loss)
I0405 19:31:18.476228 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.552564 (* 0.0454545 = 0.0251165 loss)
I0405 19:31:18.476243 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.223785 (* 0.0454545 = 0.0101721 loss)
I0405 19:31:18.476256 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0237363 (* 0.0454545 = 0.00107892 loss)
I0405 19:31:18.476270 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.16103e-05 (* 0.0454545 = 1.89138e-06 loss)
I0405 19:31:18.476284 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 4.3408e-05 (* 0.0454545 = 1.97309e-06 loss)
I0405 19:31:18.476300 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 4.2086e-05 (* 0.0454545 = 1.913e-06 loss)
I0405 19:31:18.476313 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 4.05731e-05 (* 0.0454545 = 1.84423e-06 loss)
I0405 19:31:18.476327 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.85325e-05 (* 0.0454545 = 1.75148e-06 loss)
I0405 19:31:18.476341 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.06359e-05 (* 0.0454545 = 1.84709e-06 loss)
I0405 19:31:18.476356 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.83873e-05 (* 0.0454545 = 1.74488e-06 loss)
I0405 19:31:18.476385 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.64141e-05 (* 0.0454545 = 1.65519e-06 loss)
I0405 19:31:18.476400 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.41164e-05 (* 0.0454545 = 2.00529e-06 loss)
I0405 19:31:18.476414 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.94829e-05 (* 0.0454545 = 1.79468e-06 loss)
I0405 19:31:18.476428 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.73626e-05 (* 0.0454545 = 1.6983e-06 loss)
I0405 19:31:18.476443 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.23116e-05 (* 0.0454545 = 1.92326e-06 loss)
I0405 19:31:18.476454 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:31:18.476465 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000188747
I0405 19:31:18.476480 29564 sgd_solver.cpp:106] Iteration 44500, lr = 0.009555
I0405 19:35:10.750051 29564 solver.cpp:338] Iteration 45000, Testing net (#0)
I0405 19:35:21.019364 29564 solver.cpp:393] Test loss: 0.782577
I0405 19:35:21.019409 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.224
I0405 19:35:21.019425 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.102
I0405 19:35:21.019438 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.11
I0405 19:35:21.019451 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.136
I0405 19:35:21.019462 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.243
I0405 19:35:21.019474 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.518
I0405 19:35:21.019486 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.892
I0405 19:35:21.019498 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 19:35:21.019510 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 19:35:21.019521 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 19:35:21.019532 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 19:35:21.019544 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 19:35:21.019556 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 19:35:21.019567 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 19:35:21.019578 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 19:35:21.019589 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 19:35:21.019601 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 19:35:21.019613 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 19:35:21.019623 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 19:35:21.019635 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 19:35:21.019646 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 19:35:21.019657 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 19:35:21.019672 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 2.92583 (* 0.0454545 = 0.132992 loss)
I0405 19:35:21.019687 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 3.05019 (* 0.0454545 = 0.138645 loss)
I0405 19:35:21.019701 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 3.01725 (* 0.0454545 = 0.137148 loss)
I0405 19:35:21.019716 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 2.97248 (* 0.0454545 = 0.135113 loss)
I0405 19:35:21.019729 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 2.70128 (* 0.0454545 = 0.122786 loss)
I0405 19:35:21.019743 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 1.78093 (* 0.0454545 = 0.0809512 loss)
I0405 19:35:21.019757 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.486796 (* 0.0454545 = 0.0221271 loss)
I0405 19:35:21.019773 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.207165 (* 0.0454545 = 0.00941661 loss)
I0405 19:35:21.019786 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0482265 (* 0.0454545 = 0.00219211 loss)
I0405 19:35:21.019800 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0249914 (* 0.0454545 = 0.00113597 loss)
I0405 19:35:21.019814 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 0.000133711 (* 0.0454545 = 6.07779e-06 loss)
I0405 19:35:21.019829 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 0.000132423 (* 0.0454545 = 6.01925e-06 loss)
I0405 19:35:21.019845 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 0.000131815 (* 0.0454545 = 5.99161e-06 loss)
I0405 19:35:21.019860 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 0.000135126 (* 0.0454545 = 6.1421e-06 loss)
I0405 19:35:21.019875 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 0.000130083 (* 0.0454545 = 5.91285e-06 loss)
I0405 19:35:21.019888 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 0.000128284 (* 0.0454545 = 5.83111e-06 loss)
I0405 19:35:21.019902 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 0.00013147 (* 0.0454545 = 5.97589e-06 loss)
I0405 19:35:21.019950 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 0.000125493 (* 0.0454545 = 5.70422e-06 loss)
I0405 19:35:21.019966 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 0.000134875 (* 0.0454545 = 6.13067e-06 loss)
I0405 19:35:21.019980 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 0.000118947 (* 0.0454545 = 5.4067e-06 loss)
I0405 19:35:21.019994 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 0.000122882 (* 0.0454545 = 5.58554e-06 loss)
I0405 19:35:21.020009 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 0.000128895 (* 0.0454545 = 5.85886e-06 loss)
I0405 19:35:21.020020 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0.001
I0405 19:35:21.020031 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.00100068
I0405 19:35:21.134642 29564 solver.cpp:229] Iteration 45000, loss = 0.860581
I0405 19:35:21.134680 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 19:35:21.134697 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 19:35:21.134709 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 19:35:21.134722 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 19:35:21.134734 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.09375
I0405 19:35:21.134749 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.25
I0405 19:35:21.134763 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 19:35:21.134773 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 19:35:21.134786 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 19:35:21.134799 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 19:35:21.134809 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:35:21.134820 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:35:21.134832 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:35:21.134843 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:35:21.134855 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:35:21.134865 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:35:21.134878 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:35:21.134889 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:35:21.134901 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:35:21.134912 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:35:21.134923 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:35:21.134934 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:35:21.134948 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.75128 (* 0.0454545 = 0.125058 loss)
I0405 19:35:21.134963 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.27022 (* 0.0454545 = 0.148647 loss)
I0405 19:35:21.134976 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.18669 (* 0.0454545 = 0.14485 loss)
I0405 19:35:21.134990 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.12111 (* 0.0454545 = 0.141869 loss)
I0405 19:35:21.135004 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.13983 (* 0.0454545 = 0.142719 loss)
I0405 19:35:21.135017 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.67551 (* 0.0454545 = 0.121614 loss)
I0405 19:35:21.135031 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.34939 (* 0.0454545 = 0.0613361 loss)
I0405 19:35:21.135045 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.294369 (* 0.0454545 = 0.0133804 loss)
I0405 19:35:21.135058 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0719485 (* 0.0454545 = 0.00327039 loss)
I0405 19:35:21.135073 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0233161 (* 0.0454545 = 0.00105982 loss)
I0405 19:35:21.135103 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 7.78404e-05 (* 0.0454545 = 3.5382e-06 loss)
I0405 19:35:21.135123 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 8.03638e-05 (* 0.0454545 = 3.6529e-06 loss)
I0405 19:35:21.135138 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 7.77062e-05 (* 0.0454545 = 3.5321e-06 loss)
I0405 19:35:21.135151 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 7.61586e-05 (* 0.0454545 = 3.46176e-06 loss)
I0405 19:35:21.135166 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 7.43028e-05 (* 0.0454545 = 3.3774e-06 loss)
I0405 19:35:21.135180 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 7.38962e-05 (* 0.0454545 = 3.35892e-06 loss)
I0405 19:35:21.135195 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.32874e-05 (* 0.0454545 = 3.33125e-06 loss)
I0405 19:35:21.135208 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 7.02681e-05 (* 0.0454545 = 3.194e-06 loss)
I0405 19:35:21.135223 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.65126e-05 (* 0.0454545 = 3.47784e-06 loss)
I0405 19:35:21.135237 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 6.96778e-05 (* 0.0454545 = 3.16717e-06 loss)
I0405 19:35:21.135251 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.1654e-05 (* 0.0454545 = 3.257e-06 loss)
I0405 19:35:21.135265 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 7.10012e-05 (* 0.0454545 = 3.22733e-06 loss)
I0405 19:35:21.135277 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:35:21.135289 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000484363
I0405 19:35:21.135303 29564 sgd_solver.cpp:106] Iteration 45000, lr = 0.00955
I0405 19:39:13.244794 29564 solver.cpp:229] Iteration 45500, loss = 0.85806
I0405 19:39:13.244909 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 19:39:13.244927 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 19:39:13.244940 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 19:39:13.244952 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 19:39:13.244964 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 19:39:13.244976 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 19:39:13.244987 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 19:39:13.244999 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 19:39:13.245012 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 19:39:13.245024 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 19:39:13.245036 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:39:13.245048 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:39:13.245059 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:39:13.245070 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:39:13.245081 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:39:13.245093 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:39:13.245105 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:39:13.245115 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:39:13.245129 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:39:13.245141 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:39:13.245152 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:39:13.245167 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:39:13.245183 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.65933 (* 0.0454545 = 0.120879 loss)
I0405 19:39:13.245198 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.00139 (* 0.0454545 = 0.136427 loss)
I0405 19:39:13.245211 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.07172 (* 0.0454545 = 0.139623 loss)
I0405 19:39:13.245225 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.87451 (* 0.0454545 = 0.13066 loss)
I0405 19:39:13.245239 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.74978 (* 0.0454545 = 0.12499 loss)
I0405 19:39:13.245254 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.05059 (* 0.0454545 = 0.0932087 loss)
I0405 19:39:13.245267 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.775129 (* 0.0454545 = 0.0352331 loss)
I0405 19:39:13.245281 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.391861 (* 0.0454545 = 0.0178119 loss)
I0405 19:39:13.245296 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.236671 (* 0.0454545 = 0.0107578 loss)
I0405 19:39:13.245311 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.04185 (* 0.0454545 = 0.00190227 loss)
I0405 19:39:13.245324 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 7.16012e-06 (* 0.0454545 = 3.2546e-07 loss)
I0405 19:39:13.245339 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 8.1734e-06 (* 0.0454545 = 3.71518e-07 loss)
I0405 19:39:13.245354 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 6.99246e-06 (* 0.0454545 = 3.17839e-07 loss)
I0405 19:39:13.245368 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 6.48953e-06 (* 0.0454545 = 2.94979e-07 loss)
I0405 19:39:13.245383 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 7.25698e-06 (* 0.0454545 = 3.29863e-07 loss)
I0405 19:39:13.245398 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 7.5662e-06 (* 0.0454545 = 3.43918e-07 loss)
I0405 19:39:13.245412 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.18619e-06 (* 0.0454545 = 3.26645e-07 loss)
I0405 19:39:13.245443 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 7.68914e-06 (* 0.0454545 = 3.49507e-07 loss)
I0405 19:39:13.245458 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.18245e-06 (* 0.0454545 = 3.26475e-07 loss)
I0405 19:39:13.245472 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 7.18246e-06 (* 0.0454545 = 3.26476e-07 loss)
I0405 19:39:13.245487 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 6.7615e-06 (* 0.0454545 = 3.07341e-07 loss)
I0405 19:39:13.245501 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 6.30326e-06 (* 0.0454545 = 2.86512e-07 loss)
I0405 19:39:13.245513 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:39:13.245525 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00100105
I0405 19:39:13.245540 29564 sgd_solver.cpp:106] Iteration 45500, lr = 0.009545
I0405 19:43:04.164670 29564 solver.cpp:229] Iteration 46000, loss = 0.854223
I0405 19:43:04.164949 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.28125
I0405 19:43:04.164971 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 19:43:04.164984 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 19:43:04.164996 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 19:43:04.165009 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 19:43:04.165019 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 19:43:04.165031 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 19:43:04.165043 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 19:43:04.165055 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 19:43:04.165066 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 19:43:04.165078 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:43:04.165089 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:43:04.165101 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:43:04.165112 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:43:04.165123 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:43:04.165134 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:43:04.165145 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:43:04.165158 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:43:04.165169 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:43:04.165179 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:43:04.165190 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:43:04.165202 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:43:04.165217 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.47439 (* 0.0454545 = 0.112472 loss)
I0405 19:43:04.165235 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.84819 (* 0.0454545 = 0.129463 loss)
I0405 19:43:04.165249 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.79976 (* 0.0454545 = 0.127262 loss)
I0405 19:43:04.165263 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.89201 (* 0.0454545 = 0.131455 loss)
I0405 19:43:04.165277 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.43416 (* 0.0454545 = 0.110644 loss)
I0405 19:43:04.165292 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.9228 (* 0.0454545 = 0.0874 loss)
I0405 19:43:04.165305 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.953639 (* 0.0454545 = 0.0433472 loss)
I0405 19:43:04.165334 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.304285 (* 0.0454545 = 0.0138311 loss)
I0405 19:43:04.165350 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0178757 (* 0.0454545 = 0.000812531 loss)
I0405 19:43:04.165365 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00498504 (* 0.0454545 = 0.000226593 loss)
I0405 19:43:04.165380 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.78587e-05 (* 0.0454545 = 1.72085e-06 loss)
I0405 19:43:04.165395 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 4.73992e-05 (* 0.0454545 = 2.15451e-06 loss)
I0405 19:43:04.165410 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 4.05973e-05 (* 0.0454545 = 1.84533e-06 loss)
I0405 19:43:04.165424 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.9444e-05 (* 0.0454545 = 1.79291e-06 loss)
I0405 19:43:04.165439 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.20318e-05 (* 0.0454545 = 1.91054e-06 loss)
I0405 19:43:04.165453 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.3075e-05 (* 0.0454545 = 1.95795e-06 loss)
I0405 19:43:04.165467 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.78514e-05 (* 0.0454545 = 1.72052e-06 loss)
I0405 19:43:04.165495 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.79445e-05 (* 0.0454545 = 1.72475e-06 loss)
I0405 19:43:04.165510 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.16257e-05 (* 0.0454545 = 1.89208e-06 loss)
I0405 19:43:04.165525 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.91591e-05 (* 0.0454545 = 1.77996e-06 loss)
I0405 19:43:04.165539 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.53866e-05 (* 0.0454545 = 1.60848e-06 loss)
I0405 19:43:04.165554 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.91629e-05 (* 0.0454545 = 1.78013e-06 loss)
I0405 19:43:04.165565 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:43:04.165576 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000635381
I0405 19:43:04.165591 29564 sgd_solver.cpp:106] Iteration 46000, lr = 0.00954
I0405 19:46:55.787524 29564 solver.cpp:229] Iteration 46500, loss = 0.852908
I0405 19:46:55.787605 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 19:46:55.787622 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 19:46:55.787636 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0
I0405 19:46:55.787647 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 19:46:55.787659 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 19:46:55.787670 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 19:46:55.787683 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 19:46:55.787694 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.75
I0405 19:46:55.787705 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 19:46:55.787717 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 19:46:55.787729 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:46:55.787741 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:46:55.787752 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:46:55.787763 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:46:55.787775 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:46:55.787786 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:46:55.787797 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:46:55.787808 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:46:55.787820 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:46:55.787832 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:46:55.787842 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:46:55.787854 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:46:55.787869 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.80791 (* 0.0454545 = 0.127632 loss)
I0405 19:46:55.787883 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.19986 (* 0.0454545 = 0.145448 loss)
I0405 19:46:55.787897 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.24427 (* 0.0454545 = 0.147467 loss)
I0405 19:46:55.787910 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.98024 (* 0.0454545 = 0.135465 loss)
I0405 19:46:55.787925 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.7626 (* 0.0454545 = 0.125573 loss)
I0405 19:46:55.787938 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.27239 (* 0.0454545 = 0.10329 loss)
I0405 19:46:55.787951 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.24161 (* 0.0454545 = 0.0564369 loss)
I0405 19:46:55.787966 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 1.06243 (* 0.0454545 = 0.0482924 loss)
I0405 19:46:55.787982 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.480394 (* 0.0454545 = 0.0218361 loss)
I0405 19:46:55.787997 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.369464 (* 0.0454545 = 0.0167938 loss)
I0405 19:46:55.788010 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 2.55256e-05 (* 0.0454545 = 1.16026e-06 loss)
I0405 19:46:55.788024 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 2.63452e-05 (* 0.0454545 = 1.19751e-06 loss)
I0405 19:46:55.788039 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 2.6422e-05 (* 0.0454545 = 1.201e-06 loss)
I0405 19:46:55.788054 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 2.45756e-05 (* 0.0454545 = 1.11707e-06 loss)
I0405 19:46:55.788089 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 2.58928e-05 (* 0.0454545 = 1.17695e-06 loss)
I0405 19:46:55.788107 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 2.81957e-05 (* 0.0454545 = 1.28162e-06 loss)
I0405 19:46:55.788130 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 2.82425e-05 (* 0.0454545 = 1.28375e-06 loss)
I0405 19:46:55.788162 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 2.49279e-05 (* 0.0454545 = 1.13309e-06 loss)
I0405 19:46:55.788177 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.69471e-05 (* 0.0454545 = 1.22487e-06 loss)
I0405 19:46:55.788192 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.46427e-05 (* 0.0454545 = 1.12012e-06 loss)
I0405 19:46:55.788205 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 2.47528e-05 (* 0.0454545 = 1.12513e-06 loss)
I0405 19:46:55.788219 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 2.66049e-05 (* 0.0454545 = 1.20931e-06 loss)
I0405 19:46:55.788231 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:46:55.788242 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000596531
I0405 19:46:55.788255 29564 sgd_solver.cpp:106] Iteration 46500, lr = 0.009535
I0405 19:50:47.203490 29564 solver.cpp:229] Iteration 47000, loss = 0.851027
I0405 19:50:47.203608 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 19:50:47.203627 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 19:50:47.203640 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 19:50:47.203652 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 19:50:47.203665 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 19:50:47.203676 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 19:50:47.203688 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.59375
I0405 19:50:47.203701 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.75
I0405 19:50:47.203713 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 19:50:47.203727 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 19:50:47.203738 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:50:47.203750 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:50:47.203761 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:50:47.203773 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:50:47.203784 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:50:47.203795 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:50:47.203807 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:50:47.203819 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:50:47.203830 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:50:47.203841 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:50:47.203855 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:50:47.203866 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:50:47.203881 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.54783 (* 0.0454545 = 0.11581 loss)
I0405 19:50:47.203894 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.08137 (* 0.0454545 = 0.140062 loss)
I0405 19:50:47.203908 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.91395 (* 0.0454545 = 0.132452 loss)
I0405 19:50:47.203922 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.91849 (* 0.0454545 = 0.132658 loss)
I0405 19:50:47.203935 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.83898 (* 0.0454545 = 0.129045 loss)
I0405 19:50:47.203949 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.3311 (* 0.0454545 = 0.105959 loss)
I0405 19:50:47.203963 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.80765 (* 0.0454545 = 0.0821659 loss)
I0405 19:50:47.203977 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 1.16042 (* 0.0454545 = 0.0527464 loss)
I0405 19:50:47.203990 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.303922 (* 0.0454545 = 0.0138146 loss)
I0405 19:50:47.204005 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.122325 (* 0.0454545 = 0.00556025 loss)
I0405 19:50:47.204020 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 6.36907e-05 (* 0.0454545 = 2.89503e-06 loss)
I0405 19:50:47.204035 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 6.7979e-05 (* 0.0454545 = 3.08995e-06 loss)
I0405 19:50:47.204048 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 5.71142e-05 (* 0.0454545 = 2.5961e-06 loss)
I0405 19:50:47.204063 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 6.2695e-05 (* 0.0454545 = 2.84978e-06 loss)
I0405 19:50:47.204092 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.46755e-05 (* 0.0454545 = 2.93979e-06 loss)
I0405 19:50:47.204107 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.875e-05 (* 0.0454545 = 3.125e-06 loss)
I0405 19:50:47.204121 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 5.84416e-05 (* 0.0454545 = 2.65644e-06 loss)
I0405 19:50:47.204154 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 6.04391e-05 (* 0.0454545 = 2.74723e-06 loss)
I0405 19:50:47.204169 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.2754e-05 (* 0.0454545 = 3.307e-06 loss)
I0405 19:50:47.204183 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 6.5494e-05 (* 0.0454545 = 2.977e-06 loss)
I0405 19:50:47.204197 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 5.33787e-05 (* 0.0454545 = 2.42631e-06 loss)
I0405 19:50:47.204215 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 6.71324e-05 (* 0.0454545 = 3.05147e-06 loss)
I0405 19:50:47.204227 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:50:47.204238 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000524449
I0405 19:50:47.204252 29564 sgd_solver.cpp:106] Iteration 47000, lr = 0.00953
I0405 19:54:38.376016 29564 solver.cpp:229] Iteration 47500, loss = 0.85144
I0405 19:54:38.376233 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.15625
I0405 19:54:38.376253 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 19:54:38.376266 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 19:54:38.376278 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 19:54:38.376291 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 19:54:38.376303 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 19:54:38.376317 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 19:54:38.376328 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 19:54:38.376339 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 19:54:38.376351 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 19:54:38.376363 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:54:38.376374 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:54:38.376386 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:54:38.376397 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:54:38.376408 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:54:38.376420 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:54:38.376431 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:54:38.376442 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:54:38.376453 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:54:38.376466 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:54:38.376477 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:54:38.376487 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:54:38.376505 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.72704 (* 0.0454545 = 0.123956 loss)
I0405 19:54:38.376521 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.9249 (* 0.0454545 = 0.13295 loss)
I0405 19:54:38.376535 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.08084 (* 0.0454545 = 0.140038 loss)
I0405 19:54:38.376549 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.93674 (* 0.0454545 = 0.133488 loss)
I0405 19:54:38.376564 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.7615 (* 0.0454545 = 0.125523 loss)
I0405 19:54:38.376577 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.42358 (* 0.0454545 = 0.110163 loss)
I0405 19:54:38.376591 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.09685 (* 0.0454545 = 0.0498569 loss)
I0405 19:54:38.376605 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.689814 (* 0.0454545 = 0.0313552 loss)
I0405 19:54:38.376619 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0542523 (* 0.0454545 = 0.00246601 loss)
I0405 19:54:38.376634 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0180806 (* 0.0454545 = 0.000821848 loss)
I0405 19:54:38.376648 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 7.14605e-05 (* 0.0454545 = 3.24821e-06 loss)
I0405 19:54:38.376663 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 7.11183e-05 (* 0.0454545 = 3.23265e-06 loss)
I0405 19:54:38.376677 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 7.56769e-05 (* 0.0454545 = 3.43986e-06 loss)
I0405 19:54:38.376691 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 7.25532e-05 (* 0.0454545 = 3.29787e-06 loss)
I0405 19:54:38.376705 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 7.15285e-05 (* 0.0454545 = 3.25129e-06 loss)
I0405 19:54:38.376719 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.88302e-05 (* 0.0454545 = 3.12865e-06 loss)
I0405 19:54:38.376734 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.64662e-05 (* 0.0454545 = 3.47574e-06 loss)
I0405 19:54:38.376765 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 6.94606e-05 (* 0.0454545 = 3.1573e-06 loss)
I0405 19:54:38.376781 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.4597e-05 (* 0.0454545 = 2.93623e-06 loss)
I0405 19:54:38.376796 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 6.75287e-05 (* 0.0454545 = 3.06949e-06 loss)
I0405 19:54:38.376809 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.09191e-05 (* 0.0454545 = 3.2236e-06 loss)
I0405 19:54:38.376824 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 7.09902e-05 (* 0.0454545 = 3.22683e-06 loss)
I0405 19:54:38.376837 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:54:38.376847 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000975415
I0405 19:54:38.376862 29564 sgd_solver.cpp:106] Iteration 47500, lr = 0.009525
I0405 19:58:29.953346 29564 solver.cpp:229] Iteration 48000, loss = 0.853797
I0405 19:58:29.953502 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.1875
I0405 19:58:29.953526 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 19:58:29.953542 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 19:58:29.953554 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 19:58:29.953567 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 19:58:29.953579 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 19:58:29.953591 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 19:58:29.953603 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 19:58:29.953614 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 19:58:29.953626 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 19:58:29.953639 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 19:58:29.953649 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 19:58:29.953660 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 19:58:29.953672 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 19:58:29.953685 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 19:58:29.953696 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 19:58:29.953706 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 19:58:29.953718 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 19:58:29.953729 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 19:58:29.953742 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 19:58:29.953752 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 19:58:29.953763 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 19:58:29.953778 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.58323 (* 0.0454545 = 0.117419 loss)
I0405 19:58:29.953794 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.94602 (* 0.0454545 = 0.13391 loss)
I0405 19:58:29.953807 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.93883 (* 0.0454545 = 0.133583 loss)
I0405 19:58:29.953821 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.94514 (* 0.0454545 = 0.13387 loss)
I0405 19:58:29.953835 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.51702 (* 0.0454545 = 0.11441 loss)
I0405 19:58:29.953850 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.07092 (* 0.0454545 = 0.0941327 loss)
I0405 19:58:29.953865 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.10576 (* 0.0454545 = 0.0502617 loss)
I0405 19:58:29.953878 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.586932 (* 0.0454545 = 0.0266787 loss)
I0405 19:58:29.953892 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.09465 (* 0.0454545 = 0.00430227 loss)
I0405 19:58:29.953907 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0249878 (* 0.0454545 = 0.00113581 loss)
I0405 19:58:29.953922 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000121008 (* 0.0454545 = 5.50037e-06 loss)
I0405 19:58:29.953936 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000140855 (* 0.0454545 = 6.40251e-06 loss)
I0405 19:58:29.953950 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000127922 (* 0.0454545 = 5.81465e-06 loss)
I0405 19:58:29.953965 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000131955 (* 0.0454545 = 5.99794e-06 loss)
I0405 19:58:29.953979 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000132786 (* 0.0454545 = 6.03574e-06 loss)
I0405 19:58:29.953994 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000117962 (* 0.0454545 = 5.3619e-06 loss)
I0405 19:58:29.954008 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000126 (* 0.0454545 = 5.72728e-06 loss)
I0405 19:58:29.954036 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000117744 (* 0.0454545 = 5.35199e-06 loss)
I0405 19:58:29.954052 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000125119 (* 0.0454545 = 5.68723e-06 loss)
I0405 19:58:29.954066 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000119177 (* 0.0454545 = 5.41712e-06 loss)
I0405 19:58:29.954080 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000121453 (* 0.0454545 = 5.5206e-06 loss)
I0405 19:58:29.954095 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000125512 (* 0.0454545 = 5.70511e-06 loss)
I0405 19:58:29.954107 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 19:58:29.954119 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000648076
I0405 19:58:29.954133 29564 sgd_solver.cpp:106] Iteration 48000, lr = 0.00952
I0405 20:02:22.231181 29564 solver.cpp:229] Iteration 48500, loss = 0.849993
I0405 20:02:22.231365 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.21875
I0405 20:02:22.231384 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 20:02:22.231396 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 20:02:22.231408 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.28125
I0405 20:02:22.231420 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.15625
I0405 20:02:22.231432 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 20:02:22.231444 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.84375
I0405 20:02:22.231456 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 20:02:22.231467 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 20:02:22.231479 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 20:02:22.231492 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:02:22.231504 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:02:22.231515 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:02:22.231528 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:02:22.231539 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:02:22.231549 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:02:22.231560 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:02:22.231572 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:02:22.231583 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:02:22.231595 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:02:22.231606 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:02:22.231617 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:02:22.231632 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.81431 (* 0.0454545 = 0.127923 loss)
I0405 20:02:22.231647 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.94951 (* 0.0454545 = 0.134069 loss)
I0405 20:02:22.231660 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.06055 (* 0.0454545 = 0.139116 loss)
I0405 20:02:22.231674 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.79231 (* 0.0454545 = 0.126923 loss)
I0405 20:02:22.231688 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.03294 (* 0.0454545 = 0.137861 loss)
I0405 20:02:22.231703 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.00103 (* 0.0454545 = 0.0909561 loss)
I0405 20:02:22.231717 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.704987 (* 0.0454545 = 0.0320449 loss)
I0405 20:02:22.231731 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.560542 (* 0.0454545 = 0.0254792 loss)
I0405 20:02:22.231745 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.210116 (* 0.0454545 = 0.00955071 loss)
I0405 20:02:22.231760 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.176911 (* 0.0454545 = 0.00804139 loss)
I0405 20:02:22.231773 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 6.51413e-05 (* 0.0454545 = 2.96097e-06 loss)
I0405 20:02:22.231788 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 7.21629e-05 (* 0.0454545 = 3.28013e-06 loss)
I0405 20:02:22.231802 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 6.42378e-05 (* 0.0454545 = 2.9199e-06 loss)
I0405 20:02:22.231817 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 6.09888e-05 (* 0.0454545 = 2.77222e-06 loss)
I0405 20:02:22.231830 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.30088e-05 (* 0.0454545 = 2.86404e-06 loss)
I0405 20:02:22.231848 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 5.68441e-05 (* 0.0454545 = 2.58382e-06 loss)
I0405 20:02:22.231861 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 6.04061e-05 (* 0.0454545 = 2.74573e-06 loss)
I0405 20:02:22.231891 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 5.89399e-05 (* 0.0454545 = 2.67909e-06 loss)
I0405 20:02:22.231906 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.60788e-05 (* 0.0454545 = 3.00358e-06 loss)
I0405 20:02:22.231920 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 6.04749e-05 (* 0.0454545 = 2.74886e-06 loss)
I0405 20:02:22.231935 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 6.05711e-05 (* 0.0454545 = 2.75323e-06 loss)
I0405 20:02:22.231948 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 6.1326e-05 (* 0.0454545 = 2.78755e-06 loss)
I0405 20:02:22.231961 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:02:22.231972 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000227339
I0405 20:02:22.231986 29564 sgd_solver.cpp:106] Iteration 48500, lr = 0.009515
I0405 20:06:13.581295 29564 solver.cpp:229] Iteration 49000, loss = 0.848038
I0405 20:06:13.581398 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.3125
I0405 20:06:13.581418 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 20:06:13.581431 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 20:06:13.581444 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 20:06:13.581455 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 20:06:13.581467 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 20:06:13.581480 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.53125
I0405 20:06:13.581491 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 20:06:13.581503 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 20:06:13.581514 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 20:06:13.581526 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:06:13.581540 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:06:13.581552 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:06:13.581564 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:06:13.581575 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:06:13.581586 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:06:13.581598 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:06:13.581609 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:06:13.581620 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:06:13.581631 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:06:13.581642 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:06:13.581653 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:06:13.581670 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.21572 (* 0.0454545 = 0.100715 loss)
I0405 20:06:13.581683 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.08282 (* 0.0454545 = 0.140128 loss)
I0405 20:06:13.581697 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.06593 (* 0.0454545 = 0.13936 loss)
I0405 20:06:13.581712 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.05136 (* 0.0454545 = 0.138698 loss)
I0405 20:06:13.581725 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.61554 (* 0.0454545 = 0.118888 loss)
I0405 20:06:13.581738 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.83931 (* 0.0454545 = 0.0836052 loss)
I0405 20:06:13.581753 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.66634 (* 0.0454545 = 0.0757428 loss)
I0405 20:06:13.581766 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.422916 (* 0.0454545 = 0.0192235 loss)
I0405 20:06:13.581780 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0480659 (* 0.0454545 = 0.00218482 loss)
I0405 20:06:13.581794 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0132863 (* 0.0454545 = 0.000603924 loss)
I0405 20:06:13.581809 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 8.14686e-05 (* 0.0454545 = 3.70312e-06 loss)
I0405 20:06:13.581823 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 8.5539e-05 (* 0.0454545 = 3.88814e-06 loss)
I0405 20:06:13.581837 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 9.2441e-05 (* 0.0454545 = 4.20187e-06 loss)
I0405 20:06:13.581851 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 7.76567e-05 (* 0.0454545 = 3.52985e-06 loss)
I0405 20:06:13.581866 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 8.25519e-05 (* 0.0454545 = 3.75236e-06 loss)
I0405 20:06:13.581879 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.97305e-05 (* 0.0454545 = 3.16957e-06 loss)
I0405 20:06:13.581893 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.43093e-05 (* 0.0454545 = 3.37769e-06 loss)
I0405 20:06:13.581923 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 7.91532e-05 (* 0.0454545 = 3.59787e-06 loss)
I0405 20:06:13.581939 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.70397e-05 (* 0.0454545 = 3.50181e-06 loss)
I0405 20:06:13.581954 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 7.55378e-05 (* 0.0454545 = 3.43353e-06 loss)
I0405 20:06:13.581967 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 8.00309e-05 (* 0.0454545 = 3.63777e-06 loss)
I0405 20:06:13.581981 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 7.46047e-05 (* 0.0454545 = 3.39112e-06 loss)
I0405 20:06:13.581993 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:06:13.582005 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000619135
I0405 20:06:13.582018 29564 sgd_solver.cpp:106] Iteration 49000, lr = 0.00951
I0405 20:10:05.475030 29564 solver.cpp:229] Iteration 49500, loss = 0.847549
I0405 20:10:05.475142 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.40625
I0405 20:10:05.475160 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 20:10:05.475173 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 20:10:05.475186 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 20:10:05.475198 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 20:10:05.475210 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 20:10:05.475222 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.84375
I0405 20:10:05.475234 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 20:10:05.475245 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 20:10:05.475256 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 20:10:05.475267 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:10:05.475278 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:10:05.475291 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:10:05.475302 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:10:05.475316 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:10:05.475327 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:10:05.475342 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:10:05.475353 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:10:05.475365 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:10:05.475376 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:10:05.475388 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:10:05.475399 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:10:05.475415 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.10372 (* 0.0454545 = 0.0956237 loss)
I0405 20:10:05.475430 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.872 (* 0.0454545 = 0.130546 loss)
I0405 20:10:05.475443 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.07784 (* 0.0454545 = 0.139902 loss)
I0405 20:10:05.475456 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.87792 (* 0.0454545 = 0.130815 loss)
I0405 20:10:05.475471 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.48373 (* 0.0454545 = 0.112897 loss)
I0405 20:10:05.475484 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.67915 (* 0.0454545 = 0.0763248 loss)
I0405 20:10:05.475498 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.784341 (* 0.0454545 = 0.0356519 loss)
I0405 20:10:05.475512 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.349442 (* 0.0454545 = 0.0158837 loss)
I0405 20:10:05.475528 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.00737114 (* 0.0454545 = 0.000335052 loss)
I0405 20:10:05.475541 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00329015 (* 0.0454545 = 0.000149552 loss)
I0405 20:10:05.475556 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 2.55452e-05 (* 0.0454545 = 1.16115e-06 loss)
I0405 20:10:05.475570 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 2.5275e-05 (* 0.0454545 = 1.14887e-06 loss)
I0405 20:10:05.475585 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 2.56214e-05 (* 0.0454545 = 1.16461e-06 loss)
I0405 20:10:05.475600 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 2.41571e-05 (* 0.0454545 = 1.09805e-06 loss)
I0405 20:10:05.475613 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 2.52378e-05 (* 0.0454545 = 1.14717e-06 loss)
I0405 20:10:05.475627 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 2.28567e-05 (* 0.0454545 = 1.03894e-06 loss)
I0405 20:10:05.475641 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 2.39894e-05 (* 0.0454545 = 1.09043e-06 loss)
I0405 20:10:05.475672 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 2.26592e-05 (* 0.0454545 = 1.02997e-06 loss)
I0405 20:10:05.475688 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.7289e-05 (* 0.0454545 = 1.24041e-06 loss)
I0405 20:10:05.475703 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.24394e-05 (* 0.0454545 = 1.01997e-06 loss)
I0405 20:10:05.475716 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 2.50923e-05 (* 0.0454545 = 1.14056e-06 loss)
I0405 20:10:05.475731 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 2.28903e-05 (* 0.0454545 = 1.04047e-06 loss)
I0405 20:10:05.475744 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:10:05.475755 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000622913
I0405 20:10:05.475769 29564 sgd_solver.cpp:106] Iteration 49500, lr = 0.009505
I0405 20:13:56.428879 29564 solver.cpp:338] Iteration 50000, Testing net (#0)
I0405 20:14:06.689941 29564 solver.cpp:393] Test loss: 0.768383
I0405 20:14:06.689990 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.154
I0405 20:14:06.690017 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.099
I0405 20:14:06.690042 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.106
I0405 20:14:06.690064 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.15
I0405 20:14:06.690085 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.257
I0405 20:14:06.690105 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.529
I0405 20:14:06.690129 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.897
I0405 20:14:06.690150 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 20:14:06.690171 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 20:14:06.690191 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 20:14:06.690210 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 20:14:06.690232 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 20:14:06.690253 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 20:14:06.690274 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 20:14:06.690294 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 20:14:06.690312 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 20:14:06.690332 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 20:14:06.690351 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 20:14:06.690371 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 20:14:06.690393 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 20:14:06.690413 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 20:14:06.690433 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 20:14:06.690457 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 2.90338 (* 0.0454545 = 0.131972 loss)
I0405 20:14:06.690484 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 3.00067 (* 0.0454545 = 0.136394 loss)
I0405 20:14:06.690507 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 2.98727 (* 0.0454545 = 0.135785 loss)
I0405 20:14:06.690536 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 2.91075 (* 0.0454545 = 0.132307 loss)
I0405 20:14:06.690560 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 2.64378 (* 0.0454545 = 0.120172 loss)
I0405 20:14:06.690585 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 1.70754 (* 0.0454545 = 0.0776157 loss)
I0405 20:14:06.690611 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.483716 (* 0.0454545 = 0.0219871 loss)
I0405 20:14:06.690637 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.194794 (* 0.0454545 = 0.00885425 loss)
I0405 20:14:06.690661 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0472342 (* 0.0454545 = 0.00214701 loss)
I0405 20:14:06.690686 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0241243 (* 0.0454545 = 0.00109656 loss)
I0405 20:14:06.690712 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 0.000102316 (* 0.0454545 = 4.65072e-06 loss)
I0405 20:14:06.690737 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 0.000102395 (* 0.0454545 = 4.65434e-06 loss)
I0405 20:14:06.690760 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 0.000100212 (* 0.0454545 = 4.5551e-06 loss)
I0405 20:14:06.690784 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 9.99416e-05 (* 0.0454545 = 4.5428e-06 loss)
I0405 20:14:06.690809 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 9.87806e-05 (* 0.0454545 = 4.49003e-06 loss)
I0405 20:14:06.690834 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 9.3553e-05 (* 0.0454545 = 4.25241e-06 loss)
I0405 20:14:06.690858 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 9.42468e-05 (* 0.0454545 = 4.28394e-06 loss)
I0405 20:14:06.690928 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 8.92453e-05 (* 0.0454545 = 4.05661e-06 loss)
I0405 20:14:06.690955 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 9.96845e-05 (* 0.0454545 = 4.53111e-06 loss)
I0405 20:14:06.690980 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 9.22248e-05 (* 0.0454545 = 4.19204e-06 loss)
I0405 20:14:06.691004 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 8.91127e-05 (* 0.0454545 = 4.05058e-06 loss)
I0405 20:14:06.691030 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 9.29653e-05 (* 0.0454545 = 4.22569e-06 loss)
I0405 20:14:06.691051 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0.001
I0405 20:14:06.691071 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.000752091
I0405 20:14:06.805964 29564 solver.cpp:229] Iteration 50000, loss = 0.842541
I0405 20:14:06.806008 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.4375
I0405 20:14:06.806040 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 20:14:06.806064 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 20:14:06.806092 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 20:14:06.806114 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 20:14:06.806136 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5
I0405 20:14:06.806159 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 20:14:06.806180 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 20:14:06.806200 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 20:14:06.806221 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 20:14:06.806242 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:14:06.806264 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:14:06.806285 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:14:06.806305 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:14:06.806325 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:14:06.806345 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:14:06.806366 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:14:06.806385 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:14:06.806408 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:14:06.806428 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:14:06.806448 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:14:06.806468 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:14:06.806494 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.1356 (* 0.0454545 = 0.0970727 loss)
I0405 20:14:06.806519 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.87353 (* 0.0454545 = 0.130615 loss)
I0405 20:14:06.806545 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.99339 (* 0.0454545 = 0.136063 loss)
I0405 20:14:06.806570 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.98004 (* 0.0454545 = 0.135456 loss)
I0405 20:14:06.806596 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.59239 (* 0.0454545 = 0.117836 loss)
I0405 20:14:06.806622 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.17623 (* 0.0454545 = 0.0989197 loss)
I0405 20:14:06.806648 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.21301 (* 0.0454545 = 0.055137 loss)
I0405 20:14:06.806673 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.346913 (* 0.0454545 = 0.0157688 loss)
I0405 20:14:06.806699 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0162458 (* 0.0454545 = 0.000738447 loss)
I0405 20:14:06.806725 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00965686 (* 0.0454545 = 0.000438948 loss)
I0405 20:14:06.806771 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000115472 (* 0.0454545 = 5.24872e-06 loss)
I0405 20:14:06.806797 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000113976 (* 0.0454545 = 5.18073e-06 loss)
I0405 20:14:06.806823 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000115217 (* 0.0454545 = 5.23712e-06 loss)
I0405 20:14:06.806846 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000114043 (* 0.0454545 = 5.18375e-06 loss)
I0405 20:14:06.806874 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000114581 (* 0.0454545 = 5.20825e-06 loss)
I0405 20:14:06.806900 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000109911 (* 0.0454545 = 4.99595e-06 loss)
I0405 20:14:06.806926 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000111509 (* 0.0454545 = 5.0686e-06 loss)
I0405 20:14:06.806951 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000110931 (* 0.0454545 = 5.04234e-06 loss)
I0405 20:14:06.806975 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000119972 (* 0.0454545 = 5.45326e-06 loss)
I0405 20:14:06.806999 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000109959 (* 0.0454545 = 4.99815e-06 loss)
I0405 20:14:06.807024 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000111382 (* 0.0454545 = 5.0628e-06 loss)
I0405 20:14:06.807049 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000101263 (* 0.0454545 = 4.60286e-06 loss)
I0405 20:14:06.807070 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:14:06.807096 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000950022
I0405 20:14:06.807118 29564 sgd_solver.cpp:106] Iteration 50000, lr = 0.0095
I0405 20:17:57.943902 29564 solver.cpp:229] Iteration 50500, loss = 0.846187
I0405 20:17:57.944010 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.21875
I0405 20:17:57.944030 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 20:17:57.944042 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 20:17:57.944054 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 20:17:57.944067 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 20:17:57.944078 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 20:17:57.944089 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 20:17:57.944102 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.78125
I0405 20:17:57.944113 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 20:17:57.944124 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 20:17:57.944157 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:17:57.944178 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:17:57.944190 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:17:57.944202 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:17:57.944213 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:17:57.944224 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:17:57.944238 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:17:57.944250 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:17:57.944262 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:17:57.944272 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:17:57.944284 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:17:57.944295 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:17:57.944310 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.78984 (* 0.0454545 = 0.126811 loss)
I0405 20:17:57.944325 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.00338 (* 0.0454545 = 0.136517 loss)
I0405 20:17:57.944339 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.16785 (* 0.0454545 = 0.143993 loss)
I0405 20:17:57.944353 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.90245 (* 0.0454545 = 0.13193 loss)
I0405 20:17:57.944366 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.17083 (* 0.0454545 = 0.144129 loss)
I0405 20:17:57.944380 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.19459 (* 0.0454545 = 0.0997542 loss)
I0405 20:17:57.944394 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.05487 (* 0.0454545 = 0.0479485 loss)
I0405 20:17:57.944407 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.863349 (* 0.0454545 = 0.0392431 loss)
I0405 20:17:57.944422 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.53507 (* 0.0454545 = 0.0243214 loss)
I0405 20:17:57.944437 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0360254 (* 0.0454545 = 0.00163752 loss)
I0405 20:17:57.944450 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.01093e-05 (* 0.0454545 = 1.3686e-06 loss)
I0405 20:17:57.944465 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.22385e-05 (* 0.0454545 = 1.46538e-06 loss)
I0405 20:17:57.944479 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 2.89833e-05 (* 0.0454545 = 1.31742e-06 loss)
I0405 20:17:57.944494 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 2.9116e-05 (* 0.0454545 = 1.32345e-06 loss)
I0405 20:17:57.944507 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 2.88249e-05 (* 0.0454545 = 1.31022e-06 loss)
I0405 20:17:57.944521 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 3.01047e-05 (* 0.0454545 = 1.3684e-06 loss)
I0405 20:17:57.944535 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 2.7905e-05 (* 0.0454545 = 1.26841e-06 loss)
I0405 20:17:57.944566 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 2.77238e-05 (* 0.0454545 = 1.26017e-06 loss)
I0405 20:17:57.944582 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.99246e-05 (* 0.0454545 = 1.36021e-06 loss)
I0405 20:17:57.944597 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.66639e-05 (* 0.0454545 = 1.212e-06 loss)
I0405 20:17:57.944612 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 2.67015e-05 (* 0.0454545 = 1.2137e-06 loss)
I0405 20:17:57.944625 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 2.83874e-05 (* 0.0454545 = 1.29034e-06 loss)
I0405 20:17:57.944638 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:17:57.944649 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000225279
I0405 20:17:57.944663 29564 sgd_solver.cpp:106] Iteration 50500, lr = 0.009495
I0405 20:21:49.367291 29564 solver.cpp:229] Iteration 51000, loss = 0.839899
I0405 20:21:49.367494 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 20:21:49.367513 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 20:21:49.367527 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 20:21:49.367538 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 20:21:49.367550 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 20:21:49.367563 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 20:21:49.367574 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.625
I0405 20:21:49.367585 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.78125
I0405 20:21:49.367597 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 20:21:49.367609 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 20:21:49.367620 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:21:49.367631 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:21:49.367642 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:21:49.367655 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:21:49.367666 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:21:49.367676 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:21:49.367687 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:21:49.367699 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:21:49.367710 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:21:49.367722 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:21:49.367733 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:21:49.367744 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:21:49.367759 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.50928 (* 0.0454545 = 0.114058 loss)
I0405 20:21:49.367774 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.35555 (* 0.0454545 = 0.152525 loss)
I0405 20:21:49.367787 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.44816 (* 0.0454545 = 0.156734 loss)
I0405 20:21:49.367801 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.55308 (* 0.0454545 = 0.161504 loss)
I0405 20:21:49.367815 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.94775 (* 0.0454545 = 0.133989 loss)
I0405 20:21:49.367830 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.03584 (* 0.0454545 = 0.0925381 loss)
I0405 20:21:49.367843 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.71532 (* 0.0454545 = 0.0779691 loss)
I0405 20:21:49.367857 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 1.09574 (* 0.0454545 = 0.0498065 loss)
I0405 20:21:49.367871 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.741746 (* 0.0454545 = 0.0337157 loss)
I0405 20:21:49.367884 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.148286 (* 0.0454545 = 0.00674028 loss)
I0405 20:21:49.367899 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.80455e-05 (* 0.0454545 = 1.72934e-06 loss)
I0405 20:21:49.367913 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.48113e-05 (* 0.0454545 = 1.58233e-06 loss)
I0405 20:21:49.367926 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.55527e-05 (* 0.0454545 = 1.61603e-06 loss)
I0405 20:21:49.367940 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.57464e-05 (* 0.0454545 = 1.62484e-06 loss)
I0405 20:21:49.367954 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.55453e-05 (* 0.0454545 = 1.61569e-06 loss)
I0405 20:21:49.367967 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 3.77252e-05 (* 0.0454545 = 1.71478e-06 loss)
I0405 20:21:49.367981 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.35036e-05 (* 0.0454545 = 1.52289e-06 loss)
I0405 20:21:49.368012 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.73711e-05 (* 0.0454545 = 1.69869e-06 loss)
I0405 20:21:49.368028 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 3.41202e-05 (* 0.0454545 = 1.55092e-06 loss)
I0405 20:21:49.368042 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.59886e-05 (* 0.0454545 = 1.63585e-06 loss)
I0405 20:21:49.368057 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.21661e-05 (* 0.0454545 = 1.4621e-06 loss)
I0405 20:21:49.368093 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.26857e-05 (* 0.0454545 = 1.48571e-06 loss)
I0405 20:21:49.368108 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:21:49.368120 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00436227
I0405 20:21:49.368134 29564 sgd_solver.cpp:106] Iteration 51000, lr = 0.00949
I0405 20:25:41.331127 29564 solver.cpp:229] Iteration 51500, loss = 0.839004
I0405 20:25:41.331990 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.3125
I0405 20:25:41.332013 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 20:25:41.332027 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 20:25:41.332041 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 20:25:41.332052 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.375
I0405 20:25:41.332064 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5
I0405 20:25:41.332077 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 20:25:41.332088 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 1
I0405 20:25:41.332100 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 20:25:41.332129 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 20:25:41.332142 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:25:41.332154 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:25:41.332165 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:25:41.332177 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:25:41.332188 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:25:41.332200 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:25:41.332211 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:25:41.332222 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:25:41.332233 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:25:41.332245 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:25:41.332257 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:25:41.332272 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:25:41.332288 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.31588 (* 0.0454545 = 0.105267 loss)
I0405 20:25:41.332303 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.88138 (* 0.0454545 = 0.130972 loss)
I0405 20:25:41.332331 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.97753 (* 0.0454545 = 0.135342 loss)
I0405 20:25:41.332346 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.92472 (* 0.0454545 = 0.132942 loss)
I0405 20:25:41.332360 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.39238 (* 0.0454545 = 0.108745 loss)
I0405 20:25:41.332381 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.89942 (* 0.0454545 = 0.0863372 loss)
I0405 20:25:41.332397 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.07296 (* 0.0454545 = 0.048771 loss)
I0405 20:25:41.332412 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.0749662 (* 0.0454545 = 0.00340755 loss)
I0405 20:25:41.332427 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0208638 (* 0.0454545 = 0.000948354 loss)
I0405 20:25:41.332442 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00549365 (* 0.0454545 = 0.000249711 loss)
I0405 20:25:41.332456 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 5.38145e-05 (* 0.0454545 = 2.44612e-06 loss)
I0405 20:25:41.332471 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.44403e-05 (* 0.0454545 = 2.47456e-06 loss)
I0405 20:25:41.332485 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 5.46734e-05 (* 0.0454545 = 2.48516e-06 loss)
I0405 20:25:41.332500 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 5.19812e-05 (* 0.0454545 = 2.36278e-06 loss)
I0405 20:25:41.332515 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.99934e-05 (* 0.0454545 = 2.27243e-06 loss)
I0405 20:25:41.332528 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 5.14389e-05 (* 0.0454545 = 2.33813e-06 loss)
I0405 20:25:41.332542 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 4.94062e-05 (* 0.0454545 = 2.24574e-06 loss)
I0405 20:25:41.332573 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 5.12285e-05 (* 0.0454545 = 2.32857e-06 loss)
I0405 20:25:41.332589 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.97307e-05 (* 0.0454545 = 2.26049e-06 loss)
I0405 20:25:41.332604 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.91714e-05 (* 0.0454545 = 2.23507e-06 loss)
I0405 20:25:41.332617 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 4.87118e-05 (* 0.0454545 = 2.21417e-06 loss)
I0405 20:25:41.332633 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.69717e-05 (* 0.0454545 = 2.13508e-06 loss)
I0405 20:25:41.332644 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:25:41.332656 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000947328
I0405 20:25:41.332670 29564 sgd_solver.cpp:106] Iteration 51500, lr = 0.009485
I0405 20:29:33.034991 29564 solver.cpp:229] Iteration 52000, loss = 0.837471
I0405 20:29:33.035097 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.3125
I0405 20:29:33.035116 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 20:29:33.035130 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0
I0405 20:29:33.035145 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 20:29:33.035157 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 20:29:33.035168 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 20:29:33.035181 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 20:29:33.035192 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 20:29:33.035203 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 20:29:33.035215 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 20:29:33.035226 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:29:33.035238 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:29:33.035250 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:29:33.035261 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:29:33.035274 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:29:33.035284 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:29:33.035295 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:29:33.035306 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:29:33.035318 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:29:33.035331 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:29:33.035342 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:29:33.035353 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:29:33.035368 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.45978 (* 0.0454545 = 0.111808 loss)
I0405 20:29:33.035382 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.11932 (* 0.0454545 = 0.141787 loss)
I0405 20:29:33.035397 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.46158 (* 0.0454545 = 0.157345 loss)
I0405 20:29:33.035410 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.098 (* 0.0454545 = 0.140818 loss)
I0405 20:29:33.035424 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.68649 (* 0.0454545 = 0.122113 loss)
I0405 20:29:33.035439 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.21388 (* 0.0454545 = 0.100631 loss)
I0405 20:29:33.035452 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.83957 (* 0.0454545 = 0.0381623 loss)
I0405 20:29:33.035466 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.446684 (* 0.0454545 = 0.0203038 loss)
I0405 20:29:33.035480 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.305057 (* 0.0454545 = 0.0138662 loss)
I0405 20:29:33.035493 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.301799 (* 0.0454545 = 0.0137181 loss)
I0405 20:29:33.035508 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000103656 (* 0.0454545 = 4.71165e-06 loss)
I0405 20:29:33.035521 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000111329 (* 0.0454545 = 5.0604e-06 loss)
I0405 20:29:33.035536 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000110022 (* 0.0454545 = 5.00101e-06 loss)
I0405 20:29:33.035550 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000115588 (* 0.0454545 = 5.25398e-06 loss)
I0405 20:29:33.035564 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000113622 (* 0.0454545 = 5.16463e-06 loss)
I0405 20:29:33.035578 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000106594 (* 0.0454545 = 4.84519e-06 loss)
I0405 20:29:33.035591 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 9.66049e-05 (* 0.0454545 = 4.39113e-06 loss)
I0405 20:29:33.035624 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000102276 (* 0.0454545 = 4.64893e-06 loss)
I0405 20:29:33.035639 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000100873 (* 0.0454545 = 4.58515e-06 loss)
I0405 20:29:33.035652 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 9.96094e-05 (* 0.0454545 = 4.5277e-06 loss)
I0405 20:29:33.035665 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000108635 (* 0.0454545 = 4.93797e-06 loss)
I0405 20:29:33.035679 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000108575 (* 0.0454545 = 4.93525e-06 loss)
I0405 20:29:33.035692 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:29:33.035703 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000474257
I0405 20:29:33.035717 29564 sgd_solver.cpp:106] Iteration 52000, lr = 0.00948
I0405 20:33:25.997171 29564 solver.cpp:229] Iteration 52500, loss = 0.83269
I0405 20:33:25.997388 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 20:33:25.997417 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 20:33:25.997442 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 20:33:25.997465 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.21875
I0405 20:33:25.997488 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.34375
I0405 20:33:25.997509 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 20:33:25.997531 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 20:33:25.997555 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.96875
I0405 20:33:25.997575 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 20:33:25.997596 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 20:33:25.997617 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:33:25.997637 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:33:25.997659 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:33:25.997681 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:33:25.997702 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:33:25.997722 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:33:25.997743 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:33:25.997764 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:33:25.997784 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:33:25.997807 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:33:25.997828 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:33:25.997848 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:33:25.997875 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.52256 (* 0.0454545 = 0.114662 loss)
I0405 20:33:25.997900 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.97385 (* 0.0454545 = 0.135175 loss)
I0405 20:33:25.997926 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.95986 (* 0.0454545 = 0.134539 loss)
I0405 20:33:25.997951 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.75571 (* 0.0454545 = 0.125259 loss)
I0405 20:33:25.997975 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.43506 (* 0.0454545 = 0.110685 loss)
I0405 20:33:25.998006 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.8704 (* 0.0454545 = 0.085018 loss)
I0405 20:33:25.998034 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.829055 (* 0.0454545 = 0.0376843 loss)
I0405 20:33:25.998060 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.197875 (* 0.0454545 = 0.00899433 loss)
I0405 20:33:25.998086 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0165208 (* 0.0454545 = 0.000750948 loss)
I0405 20:33:25.998112 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00719674 (* 0.0454545 = 0.000327125 loss)
I0405 20:33:25.998142 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 8.436e-05 (* 0.0454545 = 3.83455e-06 loss)
I0405 20:33:25.998168 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 8.74807e-05 (* 0.0454545 = 3.9764e-06 loss)
I0405 20:33:25.998193 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 8.05562e-05 (* 0.0454545 = 3.66164e-06 loss)
I0405 20:33:25.998219 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 7.45863e-05 (* 0.0454545 = 3.39029e-06 loss)
I0405 20:33:25.998263 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 8.49608e-05 (* 0.0454545 = 3.86185e-06 loss)
I0405 20:33:25.998293 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 7.9969e-05 (* 0.0454545 = 3.63495e-06 loss)
I0405 20:33:25.998319 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.72617e-05 (* 0.0454545 = 3.5119e-06 loss)
I0405 20:33:25.998365 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 7.52703e-05 (* 0.0454545 = 3.42138e-06 loss)
I0405 20:33:25.998389 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.41794e-05 (* 0.0454545 = 3.37179e-06 loss)
I0405 20:33:25.998414 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 7.93361e-05 (* 0.0454545 = 3.60619e-06 loss)
I0405 20:33:25.998440 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.66978e-05 (* 0.0454545 = 3.48626e-06 loss)
I0405 20:33:25.998466 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 6.61838e-05 (* 0.0454545 = 3.00835e-06 loss)
I0405 20:33:25.998486 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:33:25.998507 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00693355
I0405 20:33:25.998529 29564 sgd_solver.cpp:106] Iteration 52500, lr = 0.009475
I0405 20:37:18.195638 29564 solver.cpp:229] Iteration 53000, loss = 0.837065
I0405 20:37:18.195757 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 20:37:18.195785 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.1875
I0405 20:37:18.195808 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 20:37:18.195832 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 20:37:18.195853 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.125
I0405 20:37:18.195874 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.3125
I0405 20:37:18.195895 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 20:37:18.195915 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 1
I0405 20:37:18.195937 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 20:37:18.195960 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 20:37:18.195981 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:37:18.196002 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:37:18.196022 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:37:18.196041 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:37:18.196061 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:37:18.196100 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:37:18.196125 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:37:18.196147 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:37:18.196168 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:37:18.196188 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:37:18.196208 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:37:18.196228 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:37:18.196255 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.3872 (* 0.0454545 = 0.108509 loss)
I0405 20:37:18.196281 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.06411 (* 0.0454545 = 0.139278 loss)
I0405 20:37:18.196307 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.12484 (* 0.0454545 = 0.142038 loss)
I0405 20:37:18.196332 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.03156 (* 0.0454545 = 0.137798 loss)
I0405 20:37:18.196362 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.83797 (* 0.0454545 = 0.128999 loss)
I0405 20:37:18.196390 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.36727 (* 0.0454545 = 0.107603 loss)
I0405 20:37:18.196416 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.962071 (* 0.0454545 = 0.0437305 loss)
I0405 20:37:18.196441 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.138303 (* 0.0454545 = 0.0062865 loss)
I0405 20:37:18.196467 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0180204 (* 0.0454545 = 0.000819108 loss)
I0405 20:37:18.196493 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00686802 (* 0.0454545 = 0.000312183 loss)
I0405 20:37:18.196519 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 2.31946e-05 (* 0.0454545 = 1.0543e-06 loss)
I0405 20:37:18.196545 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 2.08921e-05 (* 0.0454545 = 9.49641e-07 loss)
I0405 20:37:18.196570 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 2.43979e-05 (* 0.0454545 = 1.109e-06 loss)
I0405 20:37:18.196595 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 2.32505e-05 (* 0.0454545 = 1.05684e-06 loss)
I0405 20:37:18.196620 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 2.15627e-05 (* 0.0454545 = 9.80125e-07 loss)
I0405 20:37:18.196645 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 2.03967e-05 (* 0.0454545 = 9.27121e-07 loss)
I0405 20:37:18.196671 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 1.95547e-05 (* 0.0454545 = 8.88849e-07 loss)
I0405 20:37:18.196719 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 2.18459e-05 (* 0.0454545 = 9.92995e-07 loss)
I0405 20:37:18.196748 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.25351e-05 (* 0.0454545 = 1.02432e-06 loss)
I0405 20:37:18.196776 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.1872e-05 (* 0.0454545 = 9.94182e-07 loss)
I0405 20:37:18.196804 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 2.10151e-05 (* 0.0454545 = 9.55233e-07 loss)
I0405 20:37:18.196830 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 2.32616e-05 (* 0.0454545 = 1.05735e-06 loss)
I0405 20:37:18.196851 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:37:18.196871 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00137165
I0405 20:37:18.196893 29564 sgd_solver.cpp:106] Iteration 53000, lr = 0.00947
I0405 20:41:09.846488 29564 solver.cpp:229] Iteration 53500, loss = 0.82918
I0405 20:41:09.846737 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.34375
I0405 20:41:09.846760 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 20:41:09.846773 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 20:41:09.846786 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 20:41:09.846797 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 20:41:09.846808 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.3125
I0405 20:41:09.846819 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.53125
I0405 20:41:09.846832 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 20:41:09.846843 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 20:41:09.846855 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 20:41:09.846866 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:41:09.846879 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:41:09.846892 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:41:09.846904 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:41:09.846915 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:41:09.846926 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:41:09.846937 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:41:09.846948 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:41:09.846959 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:41:09.846971 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:41:09.846982 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:41:09.846993 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:41:09.847008 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.40242 (* 0.0454545 = 0.109201 loss)
I0405 20:41:09.847023 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.8482 (* 0.0454545 = 0.129464 loss)
I0405 20:41:09.847036 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.8006 (* 0.0454545 = 0.1273 loss)
I0405 20:41:09.847050 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.82071 (* 0.0454545 = 0.128214 loss)
I0405 20:41:09.847064 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.74032 (* 0.0454545 = 0.12456 loss)
I0405 20:41:09.847079 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.37931 (* 0.0454545 = 0.108151 loss)
I0405 20:41:09.847092 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.71896 (* 0.0454545 = 0.0781346 loss)
I0405 20:41:09.847106 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.982012 (* 0.0454545 = 0.0446369 loss)
I0405 20:41:09.847121 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.199456 (* 0.0454545 = 0.00906617 loss)
I0405 20:41:09.847134 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0138119 (* 0.0454545 = 0.000627814 loss)
I0405 20:41:09.847148 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 2.87131e-05 (* 0.0454545 = 1.30514e-06 loss)
I0405 20:41:09.847172 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 2.9928e-05 (* 0.0454545 = 1.36037e-06 loss)
I0405 20:41:09.847189 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.41008e-05 (* 0.0454545 = 1.55004e-06 loss)
I0405 20:41:09.847203 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 2.67575e-05 (* 0.0454545 = 1.21625e-06 loss)
I0405 20:41:09.847218 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 2.95492e-05 (* 0.0454545 = 1.34315e-06 loss)
I0405 20:41:09.847231 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 2.73388e-05 (* 0.0454545 = 1.24267e-06 loss)
I0405 20:41:09.847246 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 2.88983e-05 (* 0.0454545 = 1.31356e-06 loss)
I0405 20:41:09.847273 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 2.93406e-05 (* 0.0454545 = 1.33366e-06 loss)
I0405 20:41:09.847288 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.71224e-05 (* 0.0454545 = 1.23284e-06 loss)
I0405 20:41:09.847302 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.62095e-05 (* 0.0454545 = 1.19134e-06 loss)
I0405 20:41:09.847316 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.14666e-05 (* 0.0454545 = 1.4303e-06 loss)
I0405 20:41:09.847331 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 2.86378e-05 (* 0.0454545 = 1.30172e-06 loss)
I0405 20:41:09.847342 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:41:09.847354 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00035931
I0405 20:41:09.847368 29564 sgd_solver.cpp:106] Iteration 53500, lr = 0.009465
I0405 20:45:02.303689 29564 solver.cpp:229] Iteration 54000, loss = 0.828972
I0405 20:45:02.303805 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.40625
I0405 20:45:02.303824 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 20:45:02.303838 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 20:45:02.303849 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 20:45:02.303861 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 20:45:02.303874 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 20:45:02.303884 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 20:45:02.303896 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 20:45:02.303908 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 20:45:02.303920 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 20:45:02.303931 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:45:02.303943 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:45:02.303954 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:45:02.303966 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:45:02.303977 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:45:02.303988 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:45:02.303999 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:45:02.304010 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:45:02.304021 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:45:02.304033 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:45:02.304044 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:45:02.304055 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:45:02.304087 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.18932 (* 0.0454545 = 0.0995146 loss)
I0405 20:45:02.304105 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.0631 (* 0.0454545 = 0.139232 loss)
I0405 20:45:02.304119 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.18571 (* 0.0454545 = 0.144805 loss)
I0405 20:45:02.304133 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.04533 (* 0.0454545 = 0.138424 loss)
I0405 20:45:02.304147 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.98964 (* 0.0454545 = 0.135893 loss)
I0405 20:45:02.304162 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.45712 (* 0.0454545 = 0.111687 loss)
I0405 20:45:02.304174 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.960281 (* 0.0454545 = 0.0436491 loss)
I0405 20:45:02.304188 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.501839 (* 0.0454545 = 0.0228109 loss)
I0405 20:45:02.304206 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.149352 (* 0.0454545 = 0.00678874 loss)
I0405 20:45:02.304220 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0150007 (* 0.0454545 = 0.00068185 loss)
I0405 20:45:02.304235 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 5.88727e-05 (* 0.0454545 = 2.67603e-06 loss)
I0405 20:45:02.304250 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 6.71584e-05 (* 0.0454545 = 3.05266e-06 loss)
I0405 20:45:02.304263 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 6.63351e-05 (* 0.0454545 = 3.01523e-06 loss)
I0405 20:45:02.304276 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 5.72861e-05 (* 0.0454545 = 2.60391e-06 loss)
I0405 20:45:02.304291 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 5.94022e-05 (* 0.0454545 = 2.7001e-06 loss)
I0405 20:45:02.304304 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 5.87137e-05 (* 0.0454545 = 2.6688e-06 loss)
I0405 20:45:02.304318 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 6.07147e-05 (* 0.0454545 = 2.75976e-06 loss)
I0405 20:45:02.304350 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 6.09232e-05 (* 0.0454545 = 2.76924e-06 loss)
I0405 20:45:02.304365 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.51901e-05 (* 0.0454545 = 2.96319e-06 loss)
I0405 20:45:02.304380 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 6.24102e-05 (* 0.0454545 = 2.83683e-06 loss)
I0405 20:45:02.304394 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 5.68044e-05 (* 0.0454545 = 2.58202e-06 loss)
I0405 20:45:02.304407 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 5.7018e-05 (* 0.0454545 = 2.59173e-06 loss)
I0405 20:45:02.304420 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:45:02.304431 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000150502
I0405 20:45:02.304446 29564 sgd_solver.cpp:106] Iteration 54000, lr = 0.00946
I0405 20:48:54.000131 29564 solver.cpp:229] Iteration 54500, loss = 0.82438
I0405 20:48:54.000257 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.3125
I0405 20:48:54.000278 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 20:48:54.000291 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 20:48:54.000304 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.0625
I0405 20:48:54.000316 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 20:48:54.000329 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5625
I0405 20:48:54.000341 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 20:48:54.000354 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 20:48:54.000365 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 20:48:54.000376 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 20:48:54.000388 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:48:54.000401 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:48:54.000411 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:48:54.000423 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:48:54.000433 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:48:54.000445 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:48:54.000457 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:48:54.000468 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:48:54.000479 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:48:54.000490 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:48:54.000501 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:48:54.000514 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:48:54.000527 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.3519 (* 0.0454545 = 0.106905 loss)
I0405 20:48:54.000542 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.88196 (* 0.0454545 = 0.130998 loss)
I0405 20:48:54.000556 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.0729 (* 0.0454545 = 0.139677 loss)
I0405 20:48:54.000571 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.96115 (* 0.0454545 = 0.134598 loss)
I0405 20:48:54.000583 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.74915 (* 0.0454545 = 0.124961 loss)
I0405 20:48:54.000597 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.7331 (* 0.0454545 = 0.0787772 loss)
I0405 20:48:54.000612 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.642626 (* 0.0454545 = 0.0292103 loss)
I0405 20:48:54.000625 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.524018 (* 0.0454545 = 0.023819 loss)
I0405 20:48:54.000639 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.137762 (* 0.0454545 = 0.0062619 loss)
I0405 20:48:54.000653 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0112771 (* 0.0454545 = 0.000512595 loss)
I0405 20:48:54.000669 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.54904e-05 (* 0.0454545 = 2.06775e-06 loss)
I0405 20:48:54.000684 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 4.63972e-05 (* 0.0454545 = 2.10896e-06 loss)
I0405 20:48:54.000697 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 4.04649e-05 (* 0.0454545 = 1.83931e-06 loss)
I0405 20:48:54.000711 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.87734e-05 (* 0.0454545 = 1.76243e-06 loss)
I0405 20:48:54.000725 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.07427e-05 (* 0.0454545 = 1.85194e-06 loss)
I0405 20:48:54.000740 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.06435e-05 (* 0.0454545 = 1.84743e-06 loss)
I0405 20:48:54.000753 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.79237e-05 (* 0.0454545 = 1.72381e-06 loss)
I0405 20:48:54.000784 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.40429e-05 (* 0.0454545 = 1.54741e-06 loss)
I0405 20:48:54.000800 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.34965e-05 (* 0.0454545 = 1.97711e-06 loss)
I0405 20:48:54.000814 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.76742e-05 (* 0.0454545 = 1.71246e-06 loss)
I0405 20:48:54.000828 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.87361e-05 (* 0.0454545 = 1.76073e-06 loss)
I0405 20:48:54.000843 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.64967e-05 (* 0.0454545 = 1.65894e-06 loss)
I0405 20:48:54.000855 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:48:54.000867 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000506768
I0405 20:48:54.000882 29564 sgd_solver.cpp:106] Iteration 54500, lr = 0.009455
I0405 20:52:45.521280 29564 solver.cpp:338] Iteration 55000, Testing net (#0)
I0405 20:52:55.782263 29564 solver.cpp:393] Test loss: 0.737048
I0405 20:52:55.782311 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.281
I0405 20:52:55.782328 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.122
I0405 20:52:55.782341 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.149
I0405 20:52:55.782353 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.161
I0405 20:52:55.782366 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.262
I0405 20:52:55.782377 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.531
I0405 20:52:55.782388 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.892
I0405 20:52:55.782400 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.969
I0405 20:52:55.782412 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 20:52:55.782423 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 20:52:55.782434 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 20:52:55.782445 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 20:52:55.782457 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 20:52:55.782469 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 20:52:55.782480 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 20:52:55.782490 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 20:52:55.782502 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 20:52:55.782513 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 20:52:55.782524 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 20:52:55.782536 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 20:52:55.782546 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 20:52:55.782557 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 20:52:55.782572 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 2.67056 (* 0.0454545 = 0.121389 loss)
I0405 20:52:55.782588 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 2.85754 (* 0.0454545 = 0.129888 loss)
I0405 20:52:55.782600 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 2.86423 (* 0.0454545 = 0.130192 loss)
I0405 20:52:55.782614 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 2.8373 (* 0.0454545 = 0.128968 loss)
I0405 20:52:55.782629 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 2.58058 (* 0.0454545 = 0.117299 loss)
I0405 20:52:55.782642 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 1.67025 (* 0.0454545 = 0.0759204 loss)
I0405 20:52:55.782655 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.469877 (* 0.0454545 = 0.021358 loss)
I0405 20:52:55.782671 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.191508 (* 0.0454545 = 0.0087049 loss)
I0405 20:52:55.782686 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0466052 (* 0.0454545 = 0.00211842 loss)
I0405 20:52:55.782701 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0249541 (* 0.0454545 = 0.00113428 loss)
I0405 20:52:55.782716 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 0.000144078 (* 0.0454545 = 6.549e-06 loss)
I0405 20:52:55.782730 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 0.000156029 (* 0.0454545 = 7.09224e-06 loss)
I0405 20:52:55.782743 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 0.00014523 (* 0.0454545 = 6.60137e-06 loss)
I0405 20:52:55.782757 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 0.00013687 (* 0.0454545 = 6.22136e-06 loss)
I0405 20:52:55.782771 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 0.000144174 (* 0.0454545 = 6.55336e-06 loss)
I0405 20:52:55.782785 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 0.00013592 (* 0.0454545 = 6.1782e-06 loss)
I0405 20:52:55.782799 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 0.000135534 (* 0.0454545 = 6.16064e-06 loss)
I0405 20:52:55.782848 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 0.000132253 (* 0.0454545 = 6.01148e-06 loss)
I0405 20:52:55.782865 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 0.000135637 (* 0.0454545 = 6.16533e-06 loss)
I0405 20:52:55.782878 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 0.000132111 (* 0.0454545 = 6.00505e-06 loss)
I0405 20:52:55.782892 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 0.000127322 (* 0.0454545 = 5.78736e-06 loss)
I0405 20:52:55.782907 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 0.000138583 (* 0.0454545 = 6.29923e-06 loss)
I0405 20:52:55.782917 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0.001
I0405 20:52:55.782929 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.000902461
I0405 20:52:55.897347 29564 solver.cpp:229] Iteration 55000, loss = 0.826118
I0405 20:52:55.897394 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.3125
I0405 20:52:55.897423 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.1875
I0405 20:52:55.897445 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 20:52:55.897469 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 20:52:55.897491 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 20:52:55.897513 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5
I0405 20:52:55.897534 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 20:52:55.897557 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.96875
I0405 20:52:55.897578 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 20:52:55.897600 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 20:52:55.897620 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:52:55.897640 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:52:55.897661 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:52:55.897685 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:52:55.897704 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:52:55.897725 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:52:55.897745 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:52:55.897766 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:52:55.897788 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:52:55.897807 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:52:55.897827 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:52:55.897850 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:52:55.897877 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.37315 (* 0.0454545 = 0.107871 loss)
I0405 20:52:55.897903 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.03533 (* 0.0454545 = 0.137969 loss)
I0405 20:52:55.897928 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.88826 (* 0.0454545 = 0.131285 loss)
I0405 20:52:55.897953 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.77772 (* 0.0454545 = 0.12626 loss)
I0405 20:52:55.897977 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.32621 (* 0.0454545 = 0.105737 loss)
I0405 20:52:55.898002 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.78747 (* 0.0454545 = 0.0812487 loss)
I0405 20:52:55.898028 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.641113 (* 0.0454545 = 0.0291415 loss)
I0405 20:52:55.898053 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.275232 (* 0.0454545 = 0.0125105 loss)
I0405 20:52:55.898082 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.031741 (* 0.0454545 = 0.00144277 loss)
I0405 20:52:55.898108 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00872924 (* 0.0454545 = 0.000396784 loss)
I0405 20:52:55.898159 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000115532 (* 0.0454545 = 5.25147e-06 loss)
I0405 20:52:55.898185 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.00010766 (* 0.0454545 = 4.89362e-06 loss)
I0405 20:52:55.898211 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000106929 (* 0.0454545 = 4.86041e-06 loss)
I0405 20:52:55.898236 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 9.5629e-05 (* 0.0454545 = 4.34677e-06 loss)
I0405 20:52:55.898260 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.00010664 (* 0.0454545 = 4.84728e-06 loss)
I0405 20:52:55.898284 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000104771 (* 0.0454545 = 4.76234e-06 loss)
I0405 20:52:55.898309 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 9.60167e-05 (* 0.0454545 = 4.3644e-06 loss)
I0405 20:52:55.898334 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 9.48737e-05 (* 0.0454545 = 4.31244e-06 loss)
I0405 20:52:55.898361 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 9.97414e-05 (* 0.0454545 = 4.5337e-06 loss)
I0405 20:52:55.898387 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 9.80684e-05 (* 0.0454545 = 4.45765e-06 loss)
I0405 20:52:55.898412 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 9.22372e-05 (* 0.0454545 = 4.1926e-06 loss)
I0405 20:52:55.898444 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 9.68082e-05 (* 0.0454545 = 4.40037e-06 loss)
I0405 20:52:55.898466 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:52:55.898486 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000891456
I0405 20:52:55.898510 29564 sgd_solver.cpp:106] Iteration 55000, lr = 0.00945
I0405 20:56:47.492681 29564 solver.cpp:229] Iteration 55500, loss = 0.824517
I0405 20:56:47.492858 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.375
I0405 20:56:47.492878 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 20:56:47.492892 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 20:56:47.492904 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 20:56:47.492916 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 20:56:47.492928 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 20:56:47.492940 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 20:56:47.492952 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 20:56:47.492964 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 20:56:47.492975 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 20:56:47.492987 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 20:56:47.493000 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 20:56:47.493010 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 20:56:47.493021 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 20:56:47.493033 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 20:56:47.493044 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 20:56:47.493055 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 20:56:47.493067 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 20:56:47.493078 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 20:56:47.493089 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 20:56:47.493101 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 20:56:47.493113 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 20:56:47.493129 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.46009 (* 0.0454545 = 0.111822 loss)
I0405 20:56:47.493142 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.35046 (* 0.0454545 = 0.152294 loss)
I0405 20:56:47.493156 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.1974 (* 0.0454545 = 0.145337 loss)
I0405 20:56:47.493171 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.66418 (* 0.0454545 = 0.121099 loss)
I0405 20:56:47.493185 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.54867 (* 0.0454545 = 0.115849 loss)
I0405 20:56:47.493198 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.27612 (* 0.0454545 = 0.10346 loss)
I0405 20:56:47.493212 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.04583 (* 0.0454545 = 0.0475376 loss)
I0405 20:56:47.493227 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.710641 (* 0.0454545 = 0.0323019 loss)
I0405 20:56:47.493240 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.273155 (* 0.0454545 = 0.0124161 loss)
I0405 20:56:47.493255 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.252885 (* 0.0454545 = 0.0114948 loss)
I0405 20:56:47.493269 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 7.85528e-05 (* 0.0454545 = 3.57058e-06 loss)
I0405 20:56:47.493283 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 7.67281e-05 (* 0.0454545 = 3.48764e-06 loss)
I0405 20:56:47.493299 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 8.28812e-05 (* 0.0454545 = 3.76733e-06 loss)
I0405 20:56:47.493312 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 7.12074e-05 (* 0.0454545 = 3.2367e-06 loss)
I0405 20:56:47.493325 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 7.13538e-05 (* 0.0454545 = 3.24335e-06 loss)
I0405 20:56:47.493340 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 8.89845e-05 (* 0.0454545 = 4.04475e-06 loss)
I0405 20:56:47.493353 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 6.58007e-05 (* 0.0454545 = 2.99094e-06 loss)
I0405 20:56:47.493383 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 7.25981e-05 (* 0.0454545 = 3.29991e-06 loss)
I0405 20:56:47.493399 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.90517e-05 (* 0.0454545 = 3.59326e-06 loss)
I0405 20:56:47.493413 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 7.4516e-05 (* 0.0454545 = 3.38709e-06 loss)
I0405 20:56:47.493428 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 6.58847e-05 (* 0.0454545 = 2.99476e-06 loss)
I0405 20:56:47.493443 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 6.76228e-05 (* 0.0454545 = 3.07377e-06 loss)
I0405 20:56:47.493455 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 20:56:47.493466 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00160213
I0405 20:56:47.493480 29564 sgd_solver.cpp:106] Iteration 55500, lr = 0.009445
I0405 21:00:39.451901 29564 solver.cpp:229] Iteration 56000, loss = 0.823023
I0405 21:00:39.452008 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 21:00:39.452028 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 21:00:39.452040 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.25
I0405 21:00:39.452054 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.25
I0405 21:00:39.452066 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.4375
I0405 21:00:39.452080 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5625
I0405 21:00:39.452092 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 21:00:39.452105 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.96875
I0405 21:00:39.452117 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 21:00:39.452143 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 21:00:39.452159 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:00:39.452172 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:00:39.452183 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:00:39.452194 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:00:39.452205 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:00:39.452217 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:00:39.452229 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:00:39.452240 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:00:39.452252 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:00:39.452263 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:00:39.452275 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:00:39.452286 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:00:39.452301 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.46097 (* 0.0454545 = 0.111862 loss)
I0405 21:00:39.452316 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.98154 (* 0.0454545 = 0.135525 loss)
I0405 21:00:39.452329 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.99253 (* 0.0454545 = 0.136024 loss)
I0405 21:00:39.452343 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.67034 (* 0.0454545 = 0.121379 loss)
I0405 21:00:39.452358 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.22379 (* 0.0454545 = 0.101082 loss)
I0405 21:00:39.452370 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.6243 (* 0.0454545 = 0.073832 loss)
I0405 21:00:39.452384 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.658894 (* 0.0454545 = 0.0299497 loss)
I0405 21:00:39.452399 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.269329 (* 0.0454545 = 0.0122422 loss)
I0405 21:00:39.452414 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0296475 (* 0.0454545 = 0.00134761 loss)
I0405 21:00:39.452427 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00638691 (* 0.0454545 = 0.000290314 loss)
I0405 21:00:39.452441 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.6974e-05 (* 0.0454545 = 2.13518e-06 loss)
I0405 21:00:39.452455 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 4.61742e-05 (* 0.0454545 = 2.09883e-06 loss)
I0405 21:00:39.452469 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 5.11857e-05 (* 0.0454545 = 2.32662e-06 loss)
I0405 21:00:39.452484 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 4.53808e-05 (* 0.0454545 = 2.06276e-06 loss)
I0405 21:00:39.452498 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.55007e-05 (* 0.0454545 = 2.06821e-06 loss)
I0405 21:00:39.452512 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.34336e-05 (* 0.0454545 = 1.97426e-06 loss)
I0405 21:00:39.452527 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 4.74813e-05 (* 0.0454545 = 2.15824e-06 loss)
I0405 21:00:39.452558 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 4.12729e-05 (* 0.0454545 = 1.87604e-06 loss)
I0405 21:00:39.452574 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 3.89462e-05 (* 0.0454545 = 1.77028e-06 loss)
I0405 21:00:39.452590 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.06382e-05 (* 0.0454545 = 1.84719e-06 loss)
I0405 21:00:39.452605 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 4.30167e-05 (* 0.0454545 = 1.9553e-06 loss)
I0405 21:00:39.452620 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.86458e-05 (* 0.0454545 = 2.21117e-06 loss)
I0405 21:00:39.452631 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:00:39.452643 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000743622
I0405 21:00:39.452657 29564 sgd_solver.cpp:106] Iteration 56000, lr = 0.00944
I0405 21:04:31.182992 29564 solver.cpp:229] Iteration 56500, loss = 0.815774
I0405 21:04:31.183182 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.3125
I0405 21:04:31.183200 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 21:04:31.183213 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 21:04:31.183225 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 21:04:31.183238 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.125
I0405 21:04:31.183249 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 21:04:31.183261 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 21:04:31.183274 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 21:04:31.183285 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 21:04:31.183300 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 21:04:31.183311 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:04:31.183323 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:04:31.183336 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:04:31.183346 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:04:31.183358 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:04:31.183369 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:04:31.183380 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:04:31.183393 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:04:31.183403 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:04:31.183414 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:04:31.183425 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:04:31.183437 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:04:31.183452 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.80822 (* 0.0454545 = 0.127647 loss)
I0405 21:04:31.183467 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.92159 (* 0.0454545 = 0.1328 loss)
I0405 21:04:31.183482 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.35026 (* 0.0454545 = 0.152285 loss)
I0405 21:04:31.183496 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.1763 (* 0.0454545 = 0.144377 loss)
I0405 21:04:31.183511 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.05295 (* 0.0454545 = 0.13877 loss)
I0405 21:04:31.183524 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.25424 (* 0.0454545 = 0.102466 loss)
I0405 21:04:31.183538 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.21084 (* 0.0454545 = 0.0550381 loss)
I0405 21:04:31.183552 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.75003 (* 0.0454545 = 0.0340923 loss)
I0405 21:04:31.183570 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.205054 (* 0.0454545 = 0.00932065 loss)
I0405 21:04:31.183584 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.155367 (* 0.0454545 = 0.00706213 loss)
I0405 21:04:31.183599 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000134335 (* 0.0454545 = 6.10614e-06 loss)
I0405 21:04:31.183614 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000119502 (* 0.0454545 = 5.43191e-06 loss)
I0405 21:04:31.183629 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.0001355 (* 0.0454545 = 6.1591e-06 loss)
I0405 21:04:31.183642 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000126993 (* 0.0454545 = 5.77242e-06 loss)
I0405 21:04:31.183656 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000151412 (* 0.0454545 = 6.88236e-06 loss)
I0405 21:04:31.183670 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000135011 (* 0.0454545 = 6.13688e-06 loss)
I0405 21:04:31.183684 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000132941 (* 0.0454545 = 6.04275e-06 loss)
I0405 21:04:31.183717 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000138553 (* 0.0454545 = 6.29787e-06 loss)
I0405 21:04:31.183732 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000111212 (* 0.0454545 = 5.05508e-06 loss)
I0405 21:04:31.183747 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000101814 (* 0.0454545 = 4.62792e-06 loss)
I0405 21:04:31.183760 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000115665 (* 0.0454545 = 5.25751e-06 loss)
I0405 21:04:31.183774 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000112582 (* 0.0454545 = 5.11738e-06 loss)
I0405 21:04:31.183786 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:04:31.183797 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000861242
I0405 21:04:31.183811 29564 sgd_solver.cpp:106] Iteration 56500, lr = 0.009435
I0405 21:08:22.876871 29564 solver.cpp:229] Iteration 57000, loss = 0.821206
I0405 21:08:22.877002 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.34375
I0405 21:08:22.877025 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 21:08:22.877039 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 21:08:22.877051 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 21:08:22.877063 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 21:08:22.877075 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 21:08:22.877086 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.59375
I0405 21:08:22.877099 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 21:08:22.877111 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 21:08:22.877123 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 21:08:22.877135 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:08:22.877146 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:08:22.877158 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:08:22.877169 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:08:22.877180 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:08:22.877192 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:08:22.877203 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:08:22.877214 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:08:22.877226 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:08:22.877238 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:08:22.877249 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:08:22.877259 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:08:22.877274 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.3582 (* 0.0454545 = 0.107191 loss)
I0405 21:08:22.877288 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.27253 (* 0.0454545 = 0.148751 loss)
I0405 21:08:22.877303 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.26201 (* 0.0454545 = 0.148273 loss)
I0405 21:08:22.877317 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.1433 (* 0.0454545 = 0.142877 loss)
I0405 21:08:22.877333 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.99341 (* 0.0454545 = 0.136064 loss)
I0405 21:08:22.877348 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.65753 (* 0.0454545 = 0.120797 loss)
I0405 21:08:22.877363 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.29435 (* 0.0454545 = 0.0588343 loss)
I0405 21:08:22.877377 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.503817 (* 0.0454545 = 0.0229008 loss)
I0405 21:08:22.877391 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.285435 (* 0.0454545 = 0.0129743 loss)
I0405 21:08:22.877405 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00739205 (* 0.0454545 = 0.000336002 loss)
I0405 21:08:22.877420 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.80355e-05 (* 0.0454545 = 1.72889e-06 loss)
I0405 21:08:22.877434 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.46799e-05 (* 0.0454545 = 1.57636e-06 loss)
I0405 21:08:22.877449 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.62516e-05 (* 0.0454545 = 1.6478e-06 loss)
I0405 21:08:22.877466 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.40227e-05 (* 0.0454545 = 1.54649e-06 loss)
I0405 21:08:22.877481 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.07236e-05 (* 0.0454545 = 1.85107e-06 loss)
I0405 21:08:22.877496 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 3.51886e-05 (* 0.0454545 = 1.59948e-06 loss)
I0405 21:08:22.877509 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.41156e-05 (* 0.0454545 = 1.55071e-06 loss)
I0405 21:08:22.877552 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.7638e-05 (* 0.0454545 = 1.71082e-06 loss)
I0405 21:08:22.877568 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 3.23071e-05 (* 0.0454545 = 1.46851e-06 loss)
I0405 21:08:22.877583 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.41591e-05 (* 0.0454545 = 1.55268e-06 loss)
I0405 21:08:22.877599 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.61374e-05 (* 0.0454545 = 1.64261e-06 loss)
I0405 21:08:22.877614 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.16748e-05 (* 0.0454545 = 1.43977e-06 loss)
I0405 21:08:22.877625 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:08:22.877637 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00105903
I0405 21:08:22.877650 29564 sgd_solver.cpp:106] Iteration 57000, lr = 0.00943
I0405 21:12:15.757899 29564 solver.cpp:229] Iteration 57500, loss = 0.817643
I0405 21:12:15.758100 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.4375
I0405 21:12:15.758119 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.21875
I0405 21:12:15.758131 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 21:12:15.758144 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.21875
I0405 21:12:15.758157 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.15625
I0405 21:12:15.758168 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 21:12:15.758180 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 21:12:15.758191 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 21:12:15.758203 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 21:12:15.758214 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 21:12:15.758226 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:12:15.758237 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:12:15.758249 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:12:15.758260 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:12:15.758270 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:12:15.758282 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:12:15.758293 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:12:15.758304 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:12:15.758316 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:12:15.758327 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:12:15.758338 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:12:15.758349 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:12:15.758369 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.18219 (* 0.0454545 = 0.0991906 loss)
I0405 21:12:15.758384 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.95641 (* 0.0454545 = 0.134382 loss)
I0405 21:12:15.758399 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.98225 (* 0.0454545 = 0.135557 loss)
I0405 21:12:15.758412 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.93356 (* 0.0454545 = 0.133344 loss)
I0405 21:12:15.758425 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.82476 (* 0.0454545 = 0.128398 loss)
I0405 21:12:15.758440 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.83766 (* 0.0454545 = 0.0835301 loss)
I0405 21:12:15.758453 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.11297 (* 0.0454545 = 0.0505898 loss)
I0405 21:12:15.758467 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.663002 (* 0.0454545 = 0.0301365 loss)
I0405 21:12:15.758481 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0519154 (* 0.0454545 = 0.00235979 loss)
I0405 21:12:15.758496 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0214384 (* 0.0454545 = 0.000974475 loss)
I0405 21:12:15.758509 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 5.79354e-05 (* 0.0454545 = 2.63343e-06 loss)
I0405 21:12:15.758523 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.42817e-05 (* 0.0454545 = 2.46735e-06 loss)
I0405 21:12:15.758538 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 5.82726e-05 (* 0.0454545 = 2.64876e-06 loss)
I0405 21:12:15.758553 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 5.61552e-05 (* 0.0454545 = 2.55251e-06 loss)
I0405 21:12:15.758566 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.30124e-05 (* 0.0454545 = 2.8642e-06 loss)
I0405 21:12:15.758580 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 5.63848e-05 (* 0.0454545 = 2.56294e-06 loss)
I0405 21:12:15.758594 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 5.34057e-05 (* 0.0454545 = 2.42753e-06 loss)
I0405 21:12:15.758625 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 4.98044e-05 (* 0.0454545 = 2.26383e-06 loss)
I0405 21:12:15.758641 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 5.65428e-05 (* 0.0454545 = 2.57013e-06 loss)
I0405 21:12:15.758654 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 5.59082e-05 (* 0.0454545 = 2.54128e-06 loss)
I0405 21:12:15.758668 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 5.07127e-05 (* 0.0454545 = 2.30512e-06 loss)
I0405 21:12:15.758683 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 5.49323e-05 (* 0.0454545 = 2.49692e-06 loss)
I0405 21:12:15.758695 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:12:15.758708 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000891749
I0405 21:12:15.758720 29564 sgd_solver.cpp:106] Iteration 57500, lr = 0.009425
I0405 21:16:07.710180 29564 solver.cpp:229] Iteration 58000, loss = 0.816059
I0405 21:16:07.710362 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.34375
I0405 21:16:07.710383 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 21:16:07.710397 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 21:16:07.710408 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.21875
I0405 21:16:07.710420 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.34375
I0405 21:16:07.710433 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5625
I0405 21:16:07.710444 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.875
I0405 21:16:07.710456 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 21:16:07.710469 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 21:16:07.710480 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 21:16:07.710492 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:16:07.710505 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:16:07.710517 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:16:07.710530 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:16:07.710541 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:16:07.710552 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:16:07.710564 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:16:07.710575 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:16:07.710587 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:16:07.710598 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:16:07.710610 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:16:07.710621 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:16:07.710638 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.59732 (* 0.0454545 = 0.11806 loss)
I0405 21:16:07.710654 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.20317 (* 0.0454545 = 0.145599 loss)
I0405 21:16:07.710667 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.25816 (* 0.0454545 = 0.148098 loss)
I0405 21:16:07.710681 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.79697 (* 0.0454545 = 0.127135 loss)
I0405 21:16:07.710695 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.66937 (* 0.0454545 = 0.121335 loss)
I0405 21:16:07.710710 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.47288 (* 0.0454545 = 0.0669489 loss)
I0405 21:16:07.710723 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.473901 (* 0.0454545 = 0.021541 loss)
I0405 21:16:07.710737 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.384979 (* 0.0454545 = 0.017499 loss)
I0405 21:16:07.710752 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.258143 (* 0.0454545 = 0.0117338 loss)
I0405 21:16:07.710765 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.1261 (* 0.0454545 = 0.0057318 loss)
I0405 21:16:07.710780 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 6.11823e-05 (* 0.0454545 = 2.78101e-06 loss)
I0405 21:16:07.710795 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 6.31759e-05 (* 0.0454545 = 2.87163e-06 loss)
I0405 21:16:07.710809 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 6.44248e-05 (* 0.0454545 = 2.9284e-06 loss)
I0405 21:16:07.710824 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 5.81111e-05 (* 0.0454545 = 2.64141e-06 loss)
I0405 21:16:07.710839 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 5.73144e-05 (* 0.0454545 = 2.6052e-06 loss)
I0405 21:16:07.710852 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 5.27408e-05 (* 0.0454545 = 2.39731e-06 loss)
I0405 21:16:07.710866 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 6.13057e-05 (* 0.0454545 = 2.78662e-06 loss)
I0405 21:16:07.710901 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 5.3754e-05 (* 0.0454545 = 2.44337e-06 loss)
I0405 21:16:07.710916 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 5.36952e-05 (* 0.0454545 = 2.44069e-06 loss)
I0405 21:16:07.710929 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.97599e-05 (* 0.0454545 = 2.26181e-06 loss)
I0405 21:16:07.710943 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 6.22834e-05 (* 0.0454545 = 2.83107e-06 loss)
I0405 21:16:07.710958 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 5.18376e-05 (* 0.0454545 = 2.35625e-06 loss)
I0405 21:16:07.710969 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:16:07.710981 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000666282
I0405 21:16:07.710996 29564 sgd_solver.cpp:106] Iteration 58000, lr = 0.00942
I0405 21:19:59.155477 29564 solver.cpp:229] Iteration 58500, loss = 0.815101
I0405 21:19:59.155589 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.3125
I0405 21:19:59.155608 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 21:19:59.155622 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.1875
I0405 21:19:59.155633 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 21:19:59.155645 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 21:19:59.155658 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 21:19:59.155668 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.625
I0405 21:19:59.155680 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 21:19:59.155692 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 21:19:59.155704 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 21:19:59.155716 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:19:59.155727 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:19:59.155738 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:19:59.155750 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:19:59.155761 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:19:59.155772 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:19:59.155783 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:19:59.155794 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:19:59.155807 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:19:59.155817 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:19:59.155830 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:19:59.155843 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:19:59.155858 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.07101 (* 0.0454545 = 0.094137 loss)
I0405 21:19:59.155871 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.94943 (* 0.0454545 = 0.134065 loss)
I0405 21:19:59.155885 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.8079 (* 0.0454545 = 0.127632 loss)
I0405 21:19:59.155900 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.93582 (* 0.0454545 = 0.133446 loss)
I0405 21:19:59.155913 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.65793 (* 0.0454545 = 0.120815 loss)
I0405 21:19:59.155926 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.30446 (* 0.0454545 = 0.104748 loss)
I0405 21:19:59.155941 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.27073 (* 0.0454545 = 0.0577605 loss)
I0405 21:19:59.155954 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.60659 (* 0.0454545 = 0.0275723 loss)
I0405 21:19:59.155968 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.159906 (* 0.0454545 = 0.00726846 loss)
I0405 21:19:59.155982 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0194663 (* 0.0454545 = 0.000884832 loss)
I0405 21:19:59.155997 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000180275 (* 0.0454545 = 8.19433e-06 loss)
I0405 21:19:59.156011 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000192297 (* 0.0454545 = 8.74077e-06 loss)
I0405 21:19:59.156025 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000201899 (* 0.0454545 = 9.17721e-06 loss)
I0405 21:19:59.156039 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000193814 (* 0.0454545 = 8.80972e-06 loss)
I0405 21:19:59.156054 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000188231 (* 0.0454545 = 8.55596e-06 loss)
I0405 21:19:59.156088 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000192264 (* 0.0454545 = 8.73926e-06 loss)
I0405 21:19:59.156107 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000167214 (* 0.0454545 = 7.60061e-06 loss)
I0405 21:19:59.156138 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000184253 (* 0.0454545 = 8.37515e-06 loss)
I0405 21:19:59.156154 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.00019402 (* 0.0454545 = 8.81911e-06 loss)
I0405 21:19:59.156168 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000171709 (* 0.0454545 = 7.80493e-06 loss)
I0405 21:19:59.156183 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000174924 (* 0.0454545 = 7.95111e-06 loss)
I0405 21:19:59.156196 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000179839 (* 0.0454545 = 8.1745e-06 loss)
I0405 21:19:59.156210 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:19:59.156224 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000347317
I0405 21:19:59.156237 29564 sgd_solver.cpp:106] Iteration 58500, lr = 0.009415
I0405 21:23:51.212242 29564 solver.cpp:229] Iteration 59000, loss = 0.809161
I0405 21:23:51.212543 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.4375
I0405 21:23:51.212563 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 21:23:51.212576 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 21:23:51.212589 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 21:23:51.212600 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.09375
I0405 21:23:51.212612 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.3125
I0405 21:23:51.212625 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 21:23:51.212636 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 21:23:51.212648 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 21:23:51.212659 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 21:23:51.212671 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:23:51.212683 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:23:51.212695 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:23:51.212707 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:23:51.212718 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:23:51.212728 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:23:51.212740 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:23:51.212751 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:23:51.212764 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:23:51.212774 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:23:51.212786 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:23:51.212798 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:23:51.212815 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.35023 (* 0.0454545 = 0.106828 loss)
I0405 21:23:51.212828 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.91164 (* 0.0454545 = 0.132347 loss)
I0405 21:23:51.212842 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.80783 (* 0.0454545 = 0.127629 loss)
I0405 21:23:51.212857 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.94714 (* 0.0454545 = 0.133961 loss)
I0405 21:23:51.212870 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.02953 (* 0.0454545 = 0.137706 loss)
I0405 21:23:51.212884 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.38453 (* 0.0454545 = 0.108388 loss)
I0405 21:23:51.212898 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.4673 (* 0.0454545 = 0.0666954 loss)
I0405 21:23:51.212913 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.572567 (* 0.0454545 = 0.0260258 loss)
I0405 21:23:51.212926 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.311319 (* 0.0454545 = 0.0141509 loss)
I0405 21:23:51.212940 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0464404 (* 0.0454545 = 0.00211093 loss)
I0405 21:23:51.212959 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000180384 (* 0.0454545 = 8.19929e-06 loss)
I0405 21:23:51.212973 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000219528 (* 0.0454545 = 9.97854e-06 loss)
I0405 21:23:51.212988 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000206396 (* 0.0454545 = 9.38163e-06 loss)
I0405 21:23:51.213002 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000203406 (* 0.0454545 = 9.24573e-06 loss)
I0405 21:23:51.213016 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000213513 (* 0.0454545 = 9.70513e-06 loss)
I0405 21:23:51.213032 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000199656 (* 0.0454545 = 9.07529e-06 loss)
I0405 21:23:51.213047 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000182344 (* 0.0454545 = 8.28835e-06 loss)
I0405 21:23:51.213074 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000194679 (* 0.0454545 = 8.84903e-06 loss)
I0405 21:23:51.213089 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000196317 (* 0.0454545 = 8.92348e-06 loss)
I0405 21:23:51.213104 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000191161 (* 0.0454545 = 8.68913e-06 loss)
I0405 21:23:51.213117 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000184655 (* 0.0454545 = 8.39342e-06 loss)
I0405 21:23:51.213132 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000189907 (* 0.0454545 = 8.63214e-06 loss)
I0405 21:23:51.213145 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:23:51.213156 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000372767
I0405 21:23:51.213170 29564 sgd_solver.cpp:106] Iteration 59000, lr = 0.00941
I0405 21:27:42.535707 29564 solver.cpp:229] Iteration 59500, loss = 0.812189
I0405 21:27:42.535821 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.46875
I0405 21:27:42.535841 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 21:27:42.535854 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 21:27:42.535866 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 21:27:42.535879 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 21:27:42.535890 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 21:27:42.535902 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 21:27:42.535913 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 21:27:42.535925 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 21:27:42.535936 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 21:27:42.535948 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:27:42.535959 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:27:42.535971 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:27:42.535982 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:27:42.535994 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:27:42.536005 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:27:42.536016 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:27:42.536027 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:27:42.536038 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:27:42.536049 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:27:42.536062 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:27:42.536095 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:27:42.536113 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.00697 (* 0.0454545 = 0.0912261 loss)
I0405 21:27:42.536129 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.01683 (* 0.0454545 = 0.137129 loss)
I0405 21:27:42.536154 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.03449 (* 0.0454545 = 0.137931 loss)
I0405 21:27:42.536169 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.02635 (* 0.0454545 = 0.137562 loss)
I0405 21:27:42.536185 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.85848 (* 0.0454545 = 0.129931 loss)
I0405 21:27:42.536198 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.89554 (* 0.0454545 = 0.0861607 loss)
I0405 21:27:42.536212 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.985708 (* 0.0454545 = 0.0448049 loss)
I0405 21:27:42.536226 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.310137 (* 0.0454545 = 0.0140971 loss)
I0405 21:27:42.536240 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.111833 (* 0.0454545 = 0.0050833 loss)
I0405 21:27:42.536254 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0500011 (* 0.0454545 = 0.00227278 loss)
I0405 21:27:42.536268 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 2.5761e-05 (* 0.0454545 = 1.17096e-06 loss)
I0405 21:27:42.536283 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.02822e-05 (* 0.0454545 = 1.37646e-06 loss)
I0405 21:27:42.536298 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 2.45972e-05 (* 0.0454545 = 1.11805e-06 loss)
I0405 21:27:42.536311 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 2.58183e-05 (* 0.0454545 = 1.17356e-06 loss)
I0405 21:27:42.536325 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 2.48056e-05 (* 0.0454545 = 1.12753e-06 loss)
I0405 21:27:42.536339 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 2.77393e-05 (* 0.0454545 = 1.26088e-06 loss)
I0405 21:27:42.536353 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 2.41766e-05 (* 0.0454545 = 1.09893e-06 loss)
I0405 21:27:42.536386 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 2.22289e-05 (* 0.0454545 = 1.0104e-06 loss)
I0405 21:27:42.536401 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.47896e-05 (* 0.0454545 = 1.1268e-06 loss)
I0405 21:27:42.536415 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.28385e-05 (* 0.0454545 = 1.03811e-06 loss)
I0405 21:27:42.536429 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 2.57254e-05 (* 0.0454545 = 1.16933e-06 loss)
I0405 21:27:42.536443 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 2.56679e-05 (* 0.0454545 = 1.16672e-06 loss)
I0405 21:27:42.536455 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:27:42.536468 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000613998
I0405 21:27:42.536484 29564 sgd_solver.cpp:106] Iteration 59500, lr = 0.009405
I0405 21:31:34.631546 29564 solver.cpp:338] Iteration 60000, Testing net (#0)
I0405 21:31:44.912168 29564 solver.cpp:393] Test loss: 0.777785
I0405 21:31:44.912214 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.331
I0405 21:31:44.912230 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.124
I0405 21:31:44.912242 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.127
I0405 21:31:44.912257 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.155
I0405 21:31:44.912269 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.251
I0405 21:31:44.912281 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.539
I0405 21:31:44.912292 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.892
I0405 21:31:44.912303 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 21:31:44.912315 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 21:31:44.912327 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 21:31:44.912338 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 21:31:44.912349 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 21:31:44.912361 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 21:31:44.912371 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 21:31:44.912384 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 21:31:44.912395 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 21:31:44.912405 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 21:31:44.912416 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 21:31:44.912427 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 21:31:44.912438 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 21:31:44.912449 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 21:31:44.912461 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 21:31:44.912475 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 2.64148 (* 0.0454545 = 0.120067 loss)
I0405 21:31:44.912489 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 3.09037 (* 0.0454545 = 0.140471 loss)
I0405 21:31:44.912503 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 3.07847 (* 0.0454545 = 0.139931 loss)
I0405 21:31:44.912516 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 2.99563 (* 0.0454545 = 0.136165 loss)
I0405 21:31:44.912530 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 2.76015 (* 0.0454545 = 0.125462 loss)
I0405 21:31:44.912544 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 1.72869 (* 0.0454545 = 0.0785768 loss)
I0405 21:31:44.912559 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.503852 (* 0.0454545 = 0.0229024 loss)
I0405 21:31:44.912571 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.217208 (* 0.0454545 = 0.0098731 loss)
I0405 21:31:44.912585 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0599563 (* 0.0454545 = 0.00272529 loss)
I0405 21:31:44.912600 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0324541 (* 0.0454545 = 0.00147519 loss)
I0405 21:31:44.912613 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 0.000253878 (* 0.0454545 = 1.15399e-05 loss)
I0405 21:31:44.912627 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 0.00026925 (* 0.0454545 = 1.22386e-05 loss)
I0405 21:31:44.912642 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 0.000259033 (* 0.0454545 = 1.17742e-05 loss)
I0405 21:31:44.912657 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 0.000264209 (* 0.0454545 = 1.20095e-05 loss)
I0405 21:31:44.912670 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 0.000258016 (* 0.0454545 = 1.1728e-05 loss)
I0405 21:31:44.912684 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 0.00023636 (* 0.0454545 = 1.07436e-05 loss)
I0405 21:31:44.912698 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 0.000245672 (* 0.0454545 = 1.11669e-05 loss)
I0405 21:31:44.912746 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 0.000222901 (* 0.0454545 = 1.01319e-05 loss)
I0405 21:31:44.912762 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 0.000245701 (* 0.0454545 = 1.11683e-05 loss)
I0405 21:31:44.912776 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 0.000247209 (* 0.0454545 = 1.12368e-05 loss)
I0405 21:31:44.912791 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 0.000227149 (* 0.0454545 = 1.03249e-05 loss)
I0405 21:31:44.912804 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 0.000258334 (* 0.0454545 = 1.17425e-05 loss)
I0405 21:31:44.912816 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0
I0405 21:31:44.912827 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.00101389
I0405 21:31:45.027544 29564 solver.cpp:229] Iteration 60000, loss = 0.809542
I0405 21:31:45.027582 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.375
I0405 21:31:45.027600 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 21:31:45.027611 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 21:31:45.027624 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 21:31:45.027637 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.125
I0405 21:31:45.027648 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.34375
I0405 21:31:45.027660 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 21:31:45.027672 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 21:31:45.027683 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 21:31:45.027698 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 21:31:45.027709 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:31:45.027720 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:31:45.027731 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:31:45.027743 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:31:45.027755 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:31:45.027765 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:31:45.027776 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:31:45.027787 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:31:45.027801 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:31:45.027813 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:31:45.027825 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:31:45.027837 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:31:45.027850 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.19631 (* 0.0454545 = 0.0998322 loss)
I0405 21:31:45.027865 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.02242 (* 0.0454545 = 0.137383 loss)
I0405 21:31:45.027878 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.01055 (* 0.0454545 = 0.136843 loss)
I0405 21:31:45.027892 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.35054 (* 0.0454545 = 0.152297 loss)
I0405 21:31:45.027906 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 3.04838 (* 0.0454545 = 0.138563 loss)
I0405 21:31:45.027920 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.44266 (* 0.0454545 = 0.11103 loss)
I0405 21:31:45.027933 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.28417 (* 0.0454545 = 0.0583713 loss)
I0405 21:31:45.027947 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.722235 (* 0.0454545 = 0.0328289 loss)
I0405 21:31:45.027961 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0387269 (* 0.0454545 = 0.00176031 loss)
I0405 21:31:45.027976 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0206097 (* 0.0454545 = 0.000936804 loss)
I0405 21:31:45.028007 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 8.22451e-05 (* 0.0454545 = 3.73841e-06 loss)
I0405 21:31:45.028022 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 7.71848e-05 (* 0.0454545 = 3.5084e-06 loss)
I0405 21:31:45.028036 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 8.48575e-05 (* 0.0454545 = 3.85716e-06 loss)
I0405 21:31:45.028050 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 9.13863e-05 (* 0.0454545 = 4.15392e-06 loss)
I0405 21:31:45.028064 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 8.47408e-05 (* 0.0454545 = 3.85186e-06 loss)
I0405 21:31:45.028096 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 8.82168e-05 (* 0.0454545 = 4.00985e-06 loss)
I0405 21:31:45.028111 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.78697e-05 (* 0.0454545 = 3.53953e-06 loss)
I0405 21:31:45.028126 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 6.90256e-05 (* 0.0454545 = 3.13753e-06 loss)
I0405 21:31:45.028139 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.20643e-05 (* 0.0454545 = 3.27565e-06 loss)
I0405 21:31:45.028153 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 7.92242e-05 (* 0.0454545 = 3.6011e-06 loss)
I0405 21:31:45.028167 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.23026e-05 (* 0.0454545 = 3.28648e-06 loss)
I0405 21:31:45.028182 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 8.32581e-05 (* 0.0454545 = 3.78446e-06 loss)
I0405 21:31:45.028192 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:31:45.028204 29564 solver.cpp:245]     Train net output #45: total_confidence = 5.49805e-05
I0405 21:31:45.028218 29564 sgd_solver.cpp:106] Iteration 60000, lr = 0.0094
I0405 21:35:37.754698 29564 solver.cpp:229] Iteration 60500, loss = 0.804925
I0405 21:35:37.754824 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.4375
I0405 21:35:37.754844 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.1875
I0405 21:35:37.754856 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 21:35:37.754869 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 21:35:37.754881 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 21:35:37.754894 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 21:35:37.754905 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.65625
I0405 21:35:37.754916 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 21:35:37.754928 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.875
I0405 21:35:37.754940 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 21:35:37.754951 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:35:37.754963 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:35:37.754974 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:35:37.754987 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:35:37.754997 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:35:37.755008 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:35:37.755020 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:35:37.755034 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:35:37.755048 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:35:37.755059 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:35:37.755069 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:35:37.755081 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:35:37.755097 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.09623 (* 0.0454545 = 0.0952834 loss)
I0405 21:35:37.755111 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.77704 (* 0.0454545 = 0.126229 loss)
I0405 21:35:37.755125 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.91737 (* 0.0454545 = 0.132608 loss)
I0405 21:35:37.755139 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.96456 (* 0.0454545 = 0.134753 loss)
I0405 21:35:37.755153 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.47738 (* 0.0454545 = 0.112608 loss)
I0405 21:35:37.755167 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.15979 (* 0.0454545 = 0.0981724 loss)
I0405 21:35:37.755180 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.13193 (* 0.0454545 = 0.0514514 loss)
I0405 21:35:37.755198 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.515937 (* 0.0454545 = 0.0234517 loss)
I0405 21:35:37.755213 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.476543 (* 0.0454545 = 0.021661 loss)
I0405 21:35:37.755226 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.172809 (* 0.0454545 = 0.00785497 loss)
I0405 21:35:37.755240 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 6.59412e-05 (* 0.0454545 = 2.99733e-06 loss)
I0405 21:35:37.755255 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 7.4859e-05 (* 0.0454545 = 3.40268e-06 loss)
I0405 21:35:37.755270 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 7.07084e-05 (* 0.0454545 = 3.21402e-06 loss)
I0405 21:35:37.755283 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 7.45789e-05 (* 0.0454545 = 3.38995e-06 loss)
I0405 21:35:37.755298 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.63982e-05 (* 0.0454545 = 3.0181e-06 loss)
I0405 21:35:37.755312 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.31582e-05 (* 0.0454545 = 2.87083e-06 loss)
I0405 21:35:37.755326 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 7.18073e-05 (* 0.0454545 = 3.26397e-06 loss)
I0405 21:35:37.755353 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 6.6565e-05 (* 0.0454545 = 3.02568e-06 loss)
I0405 21:35:37.755369 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.24555e-05 (* 0.0454545 = 2.83889e-06 loss)
I0405 21:35:37.755383 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 6.27672e-05 (* 0.0454545 = 2.85305e-06 loss)
I0405 21:35:37.755398 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 6.10481e-05 (* 0.0454545 = 2.77491e-06 loss)
I0405 21:35:37.755411 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 6.40505e-05 (* 0.0454545 = 2.91139e-06 loss)
I0405 21:35:37.755424 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:35:37.755435 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00053562
I0405 21:35:37.755448 29564 sgd_solver.cpp:106] Iteration 60500, lr = 0.009395
I0405 21:39:29.837688 29564 solver.cpp:229] Iteration 61000, loss = 0.804579
I0405 21:39:29.837796 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.28125
I0405 21:39:29.837815 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 21:39:29.837828 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 21:39:29.837841 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 21:39:29.837852 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 21:39:29.837864 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 21:39:29.837877 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 21:39:29.837888 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 21:39:29.837899 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 21:39:29.837911 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 21:39:29.837924 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:39:29.837934 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:39:29.837946 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:39:29.837959 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:39:29.837970 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:39:29.837981 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:39:29.837992 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:39:29.838004 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:39:29.838016 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:39:29.838027 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:39:29.838038 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:39:29.838049 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:39:29.838064 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.50228 (* 0.0454545 = 0.11374 loss)
I0405 21:39:29.838079 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.05879 (* 0.0454545 = 0.139036 loss)
I0405 21:39:29.838093 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.99319 (* 0.0454545 = 0.136054 loss)
I0405 21:39:29.838106 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.08529 (* 0.0454545 = 0.140241 loss)
I0405 21:39:29.838120 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.74932 (* 0.0454545 = 0.124969 loss)
I0405 21:39:29.838135 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.24193 (* 0.0454545 = 0.101906 loss)
I0405 21:39:29.838150 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.2611 (* 0.0454545 = 0.0573229 loss)
I0405 21:39:29.838162 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.763208 (* 0.0454545 = 0.0346913 loss)
I0405 21:39:29.838176 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.29711 (* 0.0454545 = 0.013505 loss)
I0405 21:39:29.838191 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.295397 (* 0.0454545 = 0.0134272 loss)
I0405 21:39:29.838206 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.54126e-05 (* 0.0454545 = 1.60966e-06 loss)
I0405 21:39:29.838220 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.019e-05 (* 0.0454545 = 1.37227e-06 loss)
I0405 21:39:29.838234 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.22094e-05 (* 0.0454545 = 1.46407e-06 loss)
I0405 21:39:29.838249 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.1088e-05 (* 0.0454545 = 1.41309e-06 loss)
I0405 21:39:29.838263 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 2.75831e-05 (* 0.0454545 = 1.25378e-06 loss)
I0405 21:39:29.838277 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 2.83507e-05 (* 0.0454545 = 1.28867e-06 loss)
I0405 21:39:29.838291 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 2.77755e-05 (* 0.0454545 = 1.26252e-06 loss)
I0405 21:39:29.838322 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 2.85932e-05 (* 0.0454545 = 1.29969e-06 loss)
I0405 21:39:29.838338 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 3.21012e-05 (* 0.0454545 = 1.45915e-06 loss)
I0405 21:39:29.838352 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.56718e-05 (* 0.0454545 = 1.1669e-06 loss)
I0405 21:39:29.838366 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.05812e-05 (* 0.0454545 = 1.39005e-06 loss)
I0405 21:39:29.838382 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.33388e-05 (* 0.0454545 = 1.5154e-06 loss)
I0405 21:39:29.838393 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:39:29.838405 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000671729
I0405 21:39:29.838418 29564 sgd_solver.cpp:106] Iteration 61000, lr = 0.00939
I0405 21:43:22.427870 29564 solver.cpp:229] Iteration 61500, loss = 0.804815
I0405 21:43:22.428061 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.65625
I0405 21:43:22.428097 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.25
I0405 21:43:22.428110 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 21:43:22.428122 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 21:43:22.428134 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 21:43:22.428146 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 21:43:22.428158 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 21:43:22.428170 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 21:43:22.428181 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 21:43:22.428194 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 21:43:22.428205 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:43:22.428216 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:43:22.428227 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:43:22.428238 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:43:22.428251 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:43:22.428261 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:43:22.428273 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:43:22.428284 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:43:22.428295 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:43:22.428306 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:43:22.428318 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:43:22.428329 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:43:22.428344 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 1.40838 (* 0.0454545 = 0.0640172 loss)
I0405 21:43:22.428359 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.94791 (* 0.0454545 = 0.133996 loss)
I0405 21:43:22.428372 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.7215 (* 0.0454545 = 0.123704 loss)
I0405 21:43:22.428385 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.67662 (* 0.0454545 = 0.121665 loss)
I0405 21:43:22.428400 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.44028 (* 0.0454545 = 0.110922 loss)
I0405 21:43:22.428413 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.00962 (* 0.0454545 = 0.0913463 loss)
I0405 21:43:22.428427 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.0836 (* 0.0454545 = 0.0492548 loss)
I0405 21:43:22.428442 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.281024 (* 0.0454545 = 0.0127738 loss)
I0405 21:43:22.428455 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.119262 (* 0.0454545 = 0.005421 loss)
I0405 21:43:22.428469 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.010551 (* 0.0454545 = 0.000479592 loss)
I0405 21:43:22.428484 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.88779e-05 (* 0.0454545 = 1.76718e-06 loss)
I0405 21:43:22.428498 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 4.05758e-05 (* 0.0454545 = 1.84435e-06 loss)
I0405 21:43:22.428513 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 4.31592e-05 (* 0.0454545 = 1.96178e-06 loss)
I0405 21:43:22.428527 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 4.5331e-05 (* 0.0454545 = 2.0605e-06 loss)
I0405 21:43:22.428541 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.98266e-05 (* 0.0454545 = 1.8103e-06 loss)
I0405 21:43:22.428556 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.26087e-05 (* 0.0454545 = 1.93676e-06 loss)
I0405 21:43:22.428570 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.595e-05 (* 0.0454545 = 1.63409e-06 loss)
I0405 21:43:22.428602 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.93098e-05 (* 0.0454545 = 1.78681e-06 loss)
I0405 21:43:22.428617 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.14796e-05 (* 0.0454545 = 1.88544e-06 loss)
I0405 21:43:22.428632 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.05605e-05 (* 0.0454545 = 1.84366e-06 loss)
I0405 21:43:22.428645 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.53839e-05 (* 0.0454545 = 1.60836e-06 loss)
I0405 21:43:22.428659 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.07384e-05 (* 0.0454545 = 1.85174e-06 loss)
I0405 21:43:22.428671 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0.03125
I0405 21:43:22.428683 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00185746
I0405 21:43:22.428697 29564 sgd_solver.cpp:106] Iteration 61500, lr = 0.009385
I0405 21:47:15.153421 29564 solver.cpp:229] Iteration 62000, loss = 0.801027
I0405 21:47:15.153547 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.4375
I0405 21:47:15.153566 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 21:47:15.153578 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 21:47:15.153591 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.28125
I0405 21:47:15.153604 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.375
I0405 21:47:15.153615 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 21:47:15.153627 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.84375
I0405 21:47:15.153638 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 21:47:15.153650 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 21:47:15.153662 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 21:47:15.153674 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:47:15.153687 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:47:15.153697 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:47:15.153708 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:47:15.153720 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:47:15.153731 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:47:15.153743 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:47:15.153754 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:47:15.153765 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:47:15.153776 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:47:15.153787 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:47:15.153800 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:47:15.153815 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 1.96309 (* 0.0454545 = 0.0892312 loss)
I0405 21:47:15.153828 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.01643 (* 0.0454545 = 0.13711 loss)
I0405 21:47:15.153843 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.03588 (* 0.0454545 = 0.137995 loss)
I0405 21:47:15.153856 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.86916 (* 0.0454545 = 0.130417 loss)
I0405 21:47:15.153872 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.33598 (* 0.0454545 = 0.106181 loss)
I0405 21:47:15.153887 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.64435 (* 0.0454545 = 0.074743 loss)
I0405 21:47:15.153901 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.649853 (* 0.0454545 = 0.0295388 loss)
I0405 21:47:15.153916 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.514593 (* 0.0454545 = 0.0233906 loss)
I0405 21:47:15.153930 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.251607 (* 0.0454545 = 0.0114367 loss)
I0405 21:47:15.153944 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.261671 (* 0.0454545 = 0.0118941 loss)
I0405 21:47:15.153959 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 1.11986e-05 (* 0.0454545 = 5.09029e-07 loss)
I0405 21:47:15.153973 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 9.76431e-06 (* 0.0454545 = 4.43832e-07 loss)
I0405 21:47:15.153988 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 1.05429e-05 (* 0.0454545 = 4.79221e-07 loss)
I0405 21:47:15.154003 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 9.64131e-06 (* 0.0454545 = 4.38242e-07 loss)
I0405 21:47:15.154017 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 9.08992e-06 (* 0.0454545 = 4.13178e-07 loss)
I0405 21:47:15.154031 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 9.02656e-06 (* 0.0454545 = 4.10298e-07 loss)
I0405 21:47:15.154045 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 1.00362e-05 (* 0.0454545 = 4.56192e-07 loss)
I0405 21:47:15.154075 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 9.79779e-06 (* 0.0454545 = 4.45354e-07 loss)
I0405 21:47:15.154091 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 1.12284e-05 (* 0.0454545 = 5.10384e-07 loss)
I0405 21:47:15.154105 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 9.63386e-06 (* 0.0454545 = 4.37903e-07 loss)
I0405 21:47:15.154119 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 9.96914e-06 (* 0.0454545 = 4.53143e-07 loss)
I0405 21:47:15.154134 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 9.58913e-06 (* 0.0454545 = 4.3587e-07 loss)
I0405 21:47:15.154146 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:47:15.154157 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00107803
I0405 21:47:15.154171 29564 sgd_solver.cpp:106] Iteration 62000, lr = 0.00938
I0405 21:51:07.563786 29564 solver.cpp:229] Iteration 62500, loss = 0.800968
I0405 21:51:07.564055 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.5625
I0405 21:51:07.564096 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 21:51:07.564111 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 21:51:07.564124 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 21:51:07.564136 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 21:51:07.564148 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5625
I0405 21:51:07.564160 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 21:51:07.564172 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 21:51:07.564184 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 21:51:07.564196 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 21:51:07.564208 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:51:07.564219 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:51:07.564230 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:51:07.564242 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:51:07.564254 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:51:07.564265 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:51:07.564276 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:51:07.564287 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:51:07.564298 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:51:07.564309 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:51:07.564321 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:51:07.564332 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:51:07.564347 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 1.53607 (* 0.0454545 = 0.0698213 loss)
I0405 21:51:07.564363 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.72112 (* 0.0454545 = 0.123687 loss)
I0405 21:51:07.564376 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.94624 (* 0.0454545 = 0.13392 loss)
I0405 21:51:07.564390 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.64935 (* 0.0454545 = 0.120425 loss)
I0405 21:51:07.564405 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.56541 (* 0.0454545 = 0.11661 loss)
I0405 21:51:07.564419 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.63855 (* 0.0454545 = 0.0744796 loss)
I0405 21:51:07.564434 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.764607 (* 0.0454545 = 0.0347549 loss)
I0405 21:51:07.564447 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.257318 (* 0.0454545 = 0.0116963 loss)
I0405 21:51:07.564461 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.180264 (* 0.0454545 = 0.00819383 loss)
I0405 21:51:07.564476 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.195543 (* 0.0454545 = 0.0088883 loss)
I0405 21:51:07.564491 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.31554e-05 (* 0.0454545 = 1.50706e-06 loss)
I0405 21:51:07.564504 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.65587e-05 (* 0.0454545 = 1.66176e-06 loss)
I0405 21:51:07.564518 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.53455e-05 (* 0.0454545 = 1.60661e-06 loss)
I0405 21:51:07.564532 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 3.14615e-05 (* 0.0454545 = 1.43007e-06 loss)
I0405 21:51:07.564546 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.40457e-05 (* 0.0454545 = 1.54753e-06 loss)
I0405 21:51:07.564560 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 3.68824e-05 (* 0.0454545 = 1.67647e-06 loss)
I0405 21:51:07.564574 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.07783e-05 (* 0.0454545 = 1.39901e-06 loss)
I0405 21:51:07.564604 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.05382e-05 (* 0.0454545 = 1.3881e-06 loss)
I0405 21:51:07.564618 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 3.49463e-05 (* 0.0454545 = 1.58847e-06 loss)
I0405 21:51:07.564632 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 3.06314e-05 (* 0.0454545 = 1.39234e-06 loss)
I0405 21:51:07.564646 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.08055e-05 (* 0.0454545 = 1.40025e-06 loss)
I0405 21:51:07.564663 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 3.35278e-05 (* 0.0454545 = 1.52399e-06 loss)
I0405 21:51:07.564677 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:51:07.564688 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00260502
I0405 21:51:07.564702 29564 sgd_solver.cpp:106] Iteration 62500, lr = 0.009375
I0405 21:54:59.801003 29564 solver.cpp:229] Iteration 63000, loss = 0.79424
I0405 21:54:59.801157 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.375
I0405 21:54:59.801180 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 21:54:59.801193 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 21:54:59.801206 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 21:54:59.801219 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 21:54:59.801231 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5
I0405 21:54:59.801242 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.84375
I0405 21:54:59.801254 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 21:54:59.801266 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 21:54:59.801277 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 21:54:59.801290 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:54:59.801301 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:54:59.801312 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:54:59.801323 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:54:59.801334 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:54:59.801347 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:54:59.801357 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:54:59.801368 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:54:59.801379 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:54:59.801390 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:54:59.801403 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:54:59.801414 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:54:59.801429 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 1.82954 (* 0.0454545 = 0.0831608 loss)
I0405 21:54:59.801443 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.12679 (* 0.0454545 = 0.142127 loss)
I0405 21:54:59.801457 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.97111 (* 0.0454545 = 0.13505 loss)
I0405 21:54:59.801471 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.21062 (* 0.0454545 = 0.145937 loss)
I0405 21:54:59.801486 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.74577 (* 0.0454545 = 0.124808 loss)
I0405 21:54:59.801501 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.12641 (* 0.0454545 = 0.096655 loss)
I0405 21:54:59.801513 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.65518 (* 0.0454545 = 0.0297809 loss)
I0405 21:54:59.801527 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.314033 (* 0.0454545 = 0.0142742 loss)
I0405 21:54:59.801542 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0405344 (* 0.0454545 = 0.00184247 loss)
I0405 21:54:59.801555 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0161294 (* 0.0454545 = 0.000733153 loss)
I0405 21:54:59.801569 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.29775e-05 (* 0.0454545 = 1.95352e-06 loss)
I0405 21:54:59.801584 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.15158e-05 (* 0.0454545 = 2.34163e-06 loss)
I0405 21:54:59.801597 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.90399e-05 (* 0.0454545 = 1.77454e-06 loss)
I0405 21:54:59.801611 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 4.00923e-05 (* 0.0454545 = 1.82238e-06 loss)
I0405 21:54:59.801625 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 4.88716e-05 (* 0.0454545 = 2.22143e-06 loss)
I0405 21:54:59.801640 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.17863e-05 (* 0.0454545 = 1.89938e-06 loss)
I0405 21:54:59.801652 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 4.70205e-05 (* 0.0454545 = 2.13729e-06 loss)
I0405 21:54:59.801684 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.71391e-05 (* 0.0454545 = 1.68814e-06 loss)
I0405 21:54:59.801699 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.30555e-05 (* 0.0454545 = 1.95707e-06 loss)
I0405 21:54:59.801713 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.33636e-05 (* 0.0454545 = 1.97107e-06 loss)
I0405 21:54:59.801728 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 3.78953e-05 (* 0.0454545 = 1.72251e-06 loss)
I0405 21:54:59.801743 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.2795e-05 (* 0.0454545 = 1.94523e-06 loss)
I0405 21:54:59.801755 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:54:59.801769 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000648586
I0405 21:54:59.801784 29564 sgd_solver.cpp:106] Iteration 63000, lr = 0.00937
I0405 21:58:51.672319 29564 solver.cpp:229] Iteration 63500, loss = 0.791099
I0405 21:58:51.672444 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.40625
I0405 21:58:51.672464 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.21875
I0405 21:58:51.672477 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.03125
I0405 21:58:51.672489 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.3125
I0405 21:58:51.672502 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.46875
I0405 21:58:51.672513 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 21:58:51.672524 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 21:58:51.672536 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 21:58:51.672549 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 21:58:51.672559 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 21:58:51.672571 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 21:58:51.672582 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 21:58:51.672595 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 21:58:51.672605 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 21:58:51.672617 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 21:58:51.672628 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 21:58:51.672639 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 21:58:51.672651 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 21:58:51.672662 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 21:58:51.672673 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 21:58:51.672684 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 21:58:51.672696 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 21:58:51.672711 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.07743 (* 0.0454545 = 0.0944288 loss)
I0405 21:58:51.672725 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.6942 (* 0.0454545 = 0.122464 loss)
I0405 21:58:51.672740 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.14688 (* 0.0454545 = 0.14304 loss)
I0405 21:58:51.672754 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.53051 (* 0.0454545 = 0.115023 loss)
I0405 21:58:51.672767 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 1.91678 (* 0.0454545 = 0.0871262 loss)
I0405 21:58:51.672781 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.00881 (* 0.0454545 = 0.0913095 loss)
I0405 21:58:51.672796 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.712058 (* 0.0454545 = 0.0323663 loss)
I0405 21:58:51.672809 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.65672 (* 0.0454545 = 0.0298509 loss)
I0405 21:58:51.672823 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.4601 (* 0.0454545 = 0.0209136 loss)
I0405 21:58:51.672837 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.327644 (* 0.0454545 = 0.0148929 loss)
I0405 21:58:51.672852 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 6.66158e-05 (* 0.0454545 = 3.02799e-06 loss)
I0405 21:58:51.672866 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 7.33031e-05 (* 0.0454545 = 3.33196e-06 loss)
I0405 21:58:51.672880 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 6.04913e-05 (* 0.0454545 = 2.7496e-06 loss)
I0405 21:58:51.672894 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 6.11771e-05 (* 0.0454545 = 2.78078e-06 loss)
I0405 21:58:51.672909 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.86002e-05 (* 0.0454545 = 3.11819e-06 loss)
I0405 21:58:51.672924 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.36441e-05 (* 0.0454545 = 2.89291e-06 loss)
I0405 21:58:51.672937 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 6.34747e-05 (* 0.0454545 = 2.88521e-06 loss)
I0405 21:58:51.672967 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 5.87223e-05 (* 0.0454545 = 2.66919e-06 loss)
I0405 21:58:51.672983 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 6.44121e-05 (* 0.0454545 = 2.92782e-06 loss)
I0405 21:58:51.672997 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 6.54466e-05 (* 0.0454545 = 2.97485e-06 loss)
I0405 21:58:51.673012 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 5.92592e-05 (* 0.0454545 = 2.6936e-06 loss)
I0405 21:58:51.673025 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 5.90648e-05 (* 0.0454545 = 2.68476e-06 loss)
I0405 21:58:51.673038 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 21:58:51.673050 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00217719
I0405 21:58:51.673065 29564 sgd_solver.cpp:106] Iteration 63500, lr = 0.009365
I0405 22:02:44.024389 29564 solver.cpp:229] Iteration 64000, loss = 0.792084
I0405 22:02:44.024585 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.46875
I0405 22:02:44.024605 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.0625
I0405 22:02:44.024617 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 22:02:44.024631 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.28125
I0405 22:02:44.024642 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 22:02:44.024653 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5625
I0405 22:02:44.024665 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 22:02:44.024677 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 22:02:44.024689 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 22:02:44.024700 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 22:02:44.024714 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:02:44.024725 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:02:44.024737 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:02:44.024749 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:02:44.024760 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:02:44.024772 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:02:44.024783 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:02:44.024796 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:02:44.024806 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:02:44.024817 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:02:44.024829 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:02:44.024842 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:02:44.024857 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 1.80357 (* 0.0454545 = 0.0819806 loss)
I0405 22:02:44.024870 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.7169 (* 0.0454545 = 0.123495 loss)
I0405 22:02:44.024885 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.94936 (* 0.0454545 = 0.134062 loss)
I0405 22:02:44.024899 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.87594 (* 0.0454545 = 0.130724 loss)
I0405 22:02:44.024914 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.60265 (* 0.0454545 = 0.118302 loss)
I0405 22:02:44.024929 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.82375 (* 0.0454545 = 0.0828978 loss)
I0405 22:02:44.024942 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.909634 (* 0.0454545 = 0.041347 loss)
I0405 22:02:44.024956 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.71771 (* 0.0454545 = 0.0326232 loss)
I0405 22:02:44.024971 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.622978 (* 0.0454545 = 0.0283172 loss)
I0405 22:02:44.024984 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.502024 (* 0.0454545 = 0.0228193 loss)
I0405 22:02:44.024999 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.65212e-05 (* 0.0454545 = 2.1146e-06 loss)
I0405 22:02:44.025014 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.4306e-05 (* 0.0454545 = 2.46845e-06 loss)
I0405 22:02:44.025028 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 4.64811e-05 (* 0.0454545 = 2.11278e-06 loss)
I0405 22:02:44.025043 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 4.36364e-05 (* 0.0454545 = 1.98347e-06 loss)
I0405 22:02:44.025058 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 5.00596e-05 (* 0.0454545 = 2.27544e-06 loss)
I0405 22:02:44.025071 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.92624e-05 (* 0.0454545 = 2.2392e-06 loss)
I0405 22:02:44.025085 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 4.74654e-05 (* 0.0454545 = 2.15752e-06 loss)
I0405 22:02:44.025115 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 3.70359e-05 (* 0.0454545 = 1.68345e-06 loss)
I0405 22:02:44.025135 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 5.06222e-05 (* 0.0454545 = 2.30101e-06 loss)
I0405 22:02:44.025149 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.55375e-05 (* 0.0454545 = 2.06989e-06 loss)
I0405 22:02:44.025163 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 4.14462e-05 (* 0.0454545 = 1.88392e-06 loss)
I0405 22:02:44.025177 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.46848e-05 (* 0.0454545 = 2.03113e-06 loss)
I0405 22:02:44.025189 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:02:44.025202 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00253083
I0405 22:02:44.025215 29564 sgd_solver.cpp:106] Iteration 64000, lr = 0.00936
I0405 22:06:35.617768 29564 solver.cpp:229] Iteration 64500, loss = 0.792169
I0405 22:06:35.617904 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.28125
I0405 22:06:35.617924 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 22:06:35.617944 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 22:06:35.617960 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.3125
I0405 22:06:35.617972 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.1875
I0405 22:06:35.617985 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.59375
I0405 22:06:35.618005 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 22:06:35.618024 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 22:06:35.618036 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 22:06:35.618047 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 22:06:35.618058 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:06:35.618070 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:06:35.618082 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:06:35.618093 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:06:35.618104 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:06:35.618115 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:06:35.618127 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:06:35.618139 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:06:35.618149 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:06:35.618160 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:06:35.618171 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:06:35.618182 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:06:35.618197 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.44826 (* 0.0454545 = 0.111284 loss)
I0405 22:06:35.618212 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.7631 (* 0.0454545 = 0.125595 loss)
I0405 22:06:35.618227 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.00923 (* 0.0454545 = 0.136783 loss)
I0405 22:06:35.618239 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.74262 (* 0.0454545 = 0.124665 loss)
I0405 22:06:35.618253 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.82195 (* 0.0454545 = 0.12827 loss)
I0405 22:06:35.618268 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.0517 (* 0.0454545 = 0.0932589 loss)
I0405 22:06:35.618283 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.935275 (* 0.0454545 = 0.0425125 loss)
I0405 22:06:35.618296 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.27531 (* 0.0454545 = 0.0125141 loss)
I0405 22:06:35.618310 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.26618 (* 0.0454545 = 0.0120991 loss)
I0405 22:06:35.618324 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00466538 (* 0.0454545 = 0.000212063 loss)
I0405 22:06:35.618338 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000219418 (* 0.0454545 = 9.97355e-06 loss)
I0405 22:06:35.618352 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000225419 (* 0.0454545 = 1.02463e-05 loss)
I0405 22:06:35.618366 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000219093 (* 0.0454545 = 9.95875e-06 loss)
I0405 22:06:35.618383 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000202585 (* 0.0454545 = 9.20839e-06 loss)
I0405 22:06:35.618413 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000223765 (* 0.0454545 = 1.01711e-05 loss)
I0405 22:06:35.618443 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.000211836 (* 0.0454545 = 9.62889e-06 loss)
I0405 22:06:35.618486 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000204731 (* 0.0454545 = 9.30595e-06 loss)
I0405 22:06:35.618520 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.00018212 (* 0.0454545 = 8.27817e-06 loss)
I0405 22:06:35.618535 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000224586 (* 0.0454545 = 1.02084e-05 loss)
I0405 22:06:35.618549 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000211564 (* 0.0454545 = 9.61653e-06 loss)
I0405 22:06:35.618563 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.00018244 (* 0.0454545 = 8.29273e-06 loss)
I0405 22:06:35.618577 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000202575 (* 0.0454545 = 9.20794e-06 loss)
I0405 22:06:35.618592 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:06:35.618603 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000549167
I0405 22:06:35.618618 29564 sgd_solver.cpp:106] Iteration 64500, lr = 0.009355
I0405 22:10:27.856535 29564 solver.cpp:338] Iteration 65000, Testing net (#0)
I0405 22:10:38.128298 29564 solver.cpp:393] Test loss: 0.740262
I0405 22:10:38.128346 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.315
I0405 22:10:38.128362 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.141
I0405 22:10:38.128376 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.146
I0405 22:10:38.128387 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.164
I0405 22:10:38.128399 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.289
I0405 22:10:38.128410 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.544
I0405 22:10:38.128422 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.893
I0405 22:10:38.128433 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 22:10:38.128444 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 22:10:38.128456 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 22:10:38.128468 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 22:10:38.128480 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 22:10:38.128491 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 22:10:38.128502 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 22:10:38.128515 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 22:10:38.128525 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 22:10:38.128536 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 22:10:38.128547 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 22:10:38.128559 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 22:10:38.128569 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 22:10:38.128582 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 22:10:38.128592 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 22:10:38.128607 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 2.50072 (* 0.0454545 = 0.113669 loss)
I0405 22:10:38.128623 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 2.92555 (* 0.0454545 = 0.132979 loss)
I0405 22:10:38.128635 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 2.94173 (* 0.0454545 = 0.133715 loss)
I0405 22:10:38.128649 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 2.90285 (* 0.0454545 = 0.131948 loss)
I0405 22:10:38.128665 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 2.61447 (* 0.0454545 = 0.11884 loss)
I0405 22:10:38.128680 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 1.65994 (* 0.0454545 = 0.0754518 loss)
I0405 22:10:38.128693 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.467016 (* 0.0454545 = 0.021228 loss)
I0405 22:10:38.128707 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.197408 (* 0.0454545 = 0.00897308 loss)
I0405 22:10:38.128721 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0487873 (* 0.0454545 = 0.00221761 loss)
I0405 22:10:38.128736 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0261659 (* 0.0454545 = 0.00118936 loss)
I0405 22:10:38.128749 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 9.62871e-05 (* 0.0454545 = 4.37669e-06 loss)
I0405 22:10:38.128763 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 0.000103084 (* 0.0454545 = 4.68566e-06 loss)
I0405 22:10:38.128777 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 9.33648e-05 (* 0.0454545 = 4.24386e-06 loss)
I0405 22:10:38.128792 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 9.74204e-05 (* 0.0454545 = 4.4282e-06 loss)
I0405 22:10:38.128805 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 0.000101831 (* 0.0454545 = 4.62867e-06 loss)
I0405 22:10:38.128819 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 8.67052e-05 (* 0.0454545 = 3.94114e-06 loss)
I0405 22:10:38.128834 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 8.6947e-05 (* 0.0454545 = 3.95214e-06 loss)
I0405 22:10:38.128882 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 8.96003e-05 (* 0.0454545 = 4.07274e-06 loss)
I0405 22:10:38.128898 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 9.19971e-05 (* 0.0454545 = 4.18169e-06 loss)
I0405 22:10:38.128912 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 9.51282e-05 (* 0.0454545 = 4.32401e-06 loss)
I0405 22:10:38.128926 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 8.80604e-05 (* 0.0454545 = 4.00275e-06 loss)
I0405 22:10:38.128940 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 9.39869e-05 (* 0.0454545 = 4.27213e-06 loss)
I0405 22:10:38.128952 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0.001
I0405 22:10:38.128963 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.000624989
I0405 22:10:38.243957 29564 solver.cpp:229] Iteration 65000, loss = 0.78951
I0405 22:10:38.243998 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.4375
I0405 22:10:38.244014 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.03125
I0405 22:10:38.244025 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 22:10:38.244038 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.125
I0405 22:10:38.244050 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 22:10:38.244061 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5
I0405 22:10:38.244094 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.71875
I0405 22:10:38.244108 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 22:10:38.244120 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 22:10:38.244132 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 22:10:38.244144 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:10:38.244156 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:10:38.244168 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:10:38.244179 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:10:38.244189 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:10:38.244200 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:10:38.244212 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:10:38.244225 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:10:38.244235 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:10:38.244249 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:10:38.244261 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:10:38.244272 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:10:38.244287 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 1.69845 (* 0.0454545 = 0.0772024 loss)
I0405 22:10:38.244302 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.0131 (* 0.0454545 = 0.136959 loss)
I0405 22:10:38.244315 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.84513 (* 0.0454545 = 0.129324 loss)
I0405 22:10:38.244329 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.73364 (* 0.0454545 = 0.124257 loss)
I0405 22:10:38.244343 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.56027 (* 0.0454545 = 0.116376 loss)
I0405 22:10:38.244357 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.99284 (* 0.0454545 = 0.0905836 loss)
I0405 22:10:38.244370 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.11235 (* 0.0454545 = 0.0505613 loss)
I0405 22:10:38.244385 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.370025 (* 0.0454545 = 0.0168193 loss)
I0405 22:10:38.244400 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.217072 (* 0.0454545 = 0.00986691 loss)
I0405 22:10:38.244413 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00349594 (* 0.0454545 = 0.000158906 loss)
I0405 22:10:38.244446 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 6.26095e-05 (* 0.0454545 = 2.84589e-06 loss)
I0405 22:10:38.244460 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 6.16871e-05 (* 0.0454545 = 2.80396e-06 loss)
I0405 22:10:38.244474 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 6.4501e-05 (* 0.0454545 = 2.93186e-06 loss)
I0405 22:10:38.244489 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 6.2049e-05 (* 0.0454545 = 2.82041e-06 loss)
I0405 22:10:38.244503 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 6.61145e-05 (* 0.0454545 = 3.0052e-06 loss)
I0405 22:10:38.244518 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 6.34377e-05 (* 0.0454545 = 2.88353e-06 loss)
I0405 22:10:38.244532 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 5.90989e-05 (* 0.0454545 = 2.68631e-06 loss)
I0405 22:10:38.244546 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 5.29847e-05 (* 0.0454545 = 2.40839e-06 loss)
I0405 22:10:38.244560 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 5.58053e-05 (* 0.0454545 = 2.5366e-06 loss)
I0405 22:10:38.244575 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 5.74576e-05 (* 0.0454545 = 2.61171e-06 loss)
I0405 22:10:38.244588 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 5.4423e-05 (* 0.0454545 = 2.47377e-06 loss)
I0405 22:10:38.244606 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 5.53552e-05 (* 0.0454545 = 2.51615e-06 loss)
I0405 22:10:38.244617 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:10:38.244629 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00122941
I0405 22:10:38.244643 29564 sgd_solver.cpp:106] Iteration 65000, lr = 0.00935
I0405 22:14:30.155336 29564 solver.cpp:229] Iteration 65500, loss = 0.78227
I0405 22:14:30.155570 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 22:14:30.155588 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 22:14:30.155601 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.25
I0405 22:14:30.155613 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 22:14:30.155625 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 22:14:30.155639 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 22:14:30.155652 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 22:14:30.155663 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.875
I0405 22:14:30.155675 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 22:14:30.155688 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 22:14:30.155699 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:14:30.155710 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:14:30.155721 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:14:30.155733 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:14:30.155745 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:14:30.155755 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:14:30.155766 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:14:30.155778 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:14:30.155789 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:14:30.155800 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:14:30.155812 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:14:30.155824 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:14:30.155840 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.50681 (* 0.0454545 = 0.113946 loss)
I0405 22:14:30.155854 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.92416 (* 0.0454545 = 0.132916 loss)
I0405 22:14:30.155869 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.82716 (* 0.0454545 = 0.128507 loss)
I0405 22:14:30.155882 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.76676 (* 0.0454545 = 0.125762 loss)
I0405 22:14:30.155896 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.46701 (* 0.0454545 = 0.112137 loss)
I0405 22:14:30.155910 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.66802 (* 0.0454545 = 0.0758193 loss)
I0405 22:14:30.155923 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.865469 (* 0.0454545 = 0.0393395 loss)
I0405 22:14:30.155937 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.582242 (* 0.0454545 = 0.0264655 loss)
I0405 22:14:30.155951 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.253335 (* 0.0454545 = 0.0115152 loss)
I0405 22:14:30.155966 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.143654 (* 0.0454545 = 0.00652975 loss)
I0405 22:14:30.155980 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.00019803 (* 0.0454545 = 9.00135e-06 loss)
I0405 22:14:30.155995 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000251187 (* 0.0454545 = 1.14176e-05 loss)
I0405 22:14:30.156010 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 0.000219991 (* 0.0454545 = 9.99959e-06 loss)
I0405 22:14:30.156024 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000234283 (* 0.0454545 = 1.06492e-05 loss)
I0405 22:14:30.156039 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 0.000233903 (* 0.0454545 = 1.0632e-05 loss)
I0405 22:14:30.156054 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 0.00018847 (* 0.0454545 = 8.56681e-06 loss)
I0405 22:14:30.156087 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 0.000222948 (* 0.0454545 = 1.0134e-05 loss)
I0405 22:14:30.156123 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000186299 (* 0.0454545 = 8.46813e-06 loss)
I0405 22:14:30.156139 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 0.000194641 (* 0.0454545 = 8.8473e-06 loss)
I0405 22:14:30.156153 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 0.000214157 (* 0.0454545 = 9.73443e-06 loss)
I0405 22:14:30.156168 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 0.000199684 (* 0.0454545 = 9.07656e-06 loss)
I0405 22:14:30.156183 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 0.000218755 (* 0.0454545 = 9.94341e-06 loss)
I0405 22:14:30.156194 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:14:30.156209 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00339284
I0405 22:14:30.156224 29564 sgd_solver.cpp:106] Iteration 65500, lr = 0.009345
I0405 22:18:22.349535 29564 solver.cpp:229] Iteration 66000, loss = 0.787329
I0405 22:18:22.349634 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.25
I0405 22:18:22.349653 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.125
I0405 22:18:22.349666 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.09375
I0405 22:18:22.349679 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 22:18:22.349691 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 22:18:22.349702 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 22:18:22.349715 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 22:18:22.349726 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.96875
I0405 22:18:22.349738 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 22:18:22.349750 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 22:18:22.349761 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:18:22.349774 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:18:22.349786 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:18:22.349800 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:18:22.349812 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:18:22.349823 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:18:22.349834 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:18:22.349845 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:18:22.349858 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:18:22.349869 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:18:22.349879 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:18:22.349890 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:18:22.349905 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.19433 (* 0.0454545 = 0.0997421 loss)
I0405 22:18:22.349920 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.83205 (* 0.0454545 = 0.128729 loss)
I0405 22:18:22.349933 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.93469 (* 0.0454545 = 0.133395 loss)
I0405 22:18:22.349947 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.69949 (* 0.0454545 = 0.122704 loss)
I0405 22:18:22.349961 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.32793 (* 0.0454545 = 0.105815 loss)
I0405 22:18:22.349974 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.88275 (* 0.0454545 = 0.0855794 loss)
I0405 22:18:22.349990 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.965734 (* 0.0454545 = 0.043897 loss)
I0405 22:18:22.350004 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.192715 (* 0.0454545 = 0.00875975 loss)
I0405 22:18:22.350018 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0383551 (* 0.0454545 = 0.00174341 loss)
I0405 22:18:22.350033 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0106924 (* 0.0454545 = 0.00048602 loss)
I0405 22:18:22.350047 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 4.82693e-05 (* 0.0454545 = 2.19406e-06 loss)
I0405 22:18:22.350061 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.6447e-05 (* 0.0454545 = 2.56577e-06 loss)
I0405 22:18:22.350076 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 5.10004e-05 (* 0.0454545 = 2.3182e-06 loss)
I0405 22:18:22.350090 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 5.03169e-05 (* 0.0454545 = 2.28713e-06 loss)
I0405 22:18:22.350105 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 5.11402e-05 (* 0.0454545 = 2.32455e-06 loss)
I0405 22:18:22.350118 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.86887e-05 (* 0.0454545 = 2.21312e-06 loss)
I0405 22:18:22.350132 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 4.71163e-05 (* 0.0454545 = 2.14165e-06 loss)
I0405 22:18:22.350160 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 4.55624e-05 (* 0.0454545 = 2.07102e-06 loss)
I0405 22:18:22.350175 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 5.06784e-05 (* 0.0454545 = 2.30356e-06 loss)
I0405 22:18:22.350189 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.81115e-05 (* 0.0454545 = 2.18689e-06 loss)
I0405 22:18:22.350203 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 4.56725e-05 (* 0.0454545 = 2.07602e-06 loss)
I0405 22:18:22.350237 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 5.11813e-05 (* 0.0454545 = 2.32642e-06 loss)
I0405 22:18:22.350250 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:18:22.350261 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00204024
I0405 22:18:22.350275 29564 sgd_solver.cpp:106] Iteration 66000, lr = 0.00934
I0405 22:22:14.301017 29564 solver.cpp:229] Iteration 66500, loss = 0.781401
I0405 22:22:14.301218 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.34375
I0405 22:22:14.301237 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.21875
I0405 22:22:14.301249 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.21875
I0405 22:22:14.301261 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.28125
I0405 22:22:14.301273 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 22:22:14.301285 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.375
I0405 22:22:14.301297 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.8125
I0405 22:22:14.301309 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 22:22:14.301321 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 22:22:14.301332 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 22:22:14.301343 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:22:14.301354 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:22:14.301367 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:22:14.301378 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:22:14.301388 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:22:14.301399 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:22:14.301410 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:22:14.301421 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:22:14.301432 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:22:14.301445 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:22:14.301456 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:22:14.301467 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:22:14.301482 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.1627 (* 0.0454545 = 0.0983045 loss)
I0405 22:22:14.301497 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.42077 (* 0.0454545 = 0.110035 loss)
I0405 22:22:14.301512 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.81084 (* 0.0454545 = 0.127766 loss)
I0405 22:22:14.301525 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.62695 (* 0.0454545 = 0.119407 loss)
I0405 22:22:14.301539 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.72621 (* 0.0454545 = 0.123919 loss)
I0405 22:22:14.301553 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.13261 (* 0.0454545 = 0.0969369 loss)
I0405 22:22:14.301568 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.646619 (* 0.0454545 = 0.0293918 loss)
I0405 22:22:14.301581 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.267828 (* 0.0454545 = 0.012174 loss)
I0405 22:22:14.301595 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0276172 (* 0.0454545 = 0.00125533 loss)
I0405 22:22:14.301610 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00914611 (* 0.0454545 = 0.000415732 loss)
I0405 22:22:14.301625 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 0.000101238 (* 0.0454545 = 4.60173e-06 loss)
I0405 22:22:14.301640 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 0.000104301 (* 0.0454545 = 4.74094e-06 loss)
I0405 22:22:14.301653 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 9.56805e-05 (* 0.0454545 = 4.34911e-06 loss)
I0405 22:22:14.301667 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 0.000103181 (* 0.0454545 = 4.69005e-06 loss)
I0405 22:22:14.301681 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 8.29897e-05 (* 0.0454545 = 3.77226e-06 loss)
I0405 22:22:14.301695 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 8.67855e-05 (* 0.0454545 = 3.9448e-06 loss)
I0405 22:22:14.301709 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 9.67863e-05 (* 0.0454545 = 4.39938e-06 loss)
I0405 22:22:14.301739 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 0.000103701 (* 0.0454545 = 4.71367e-06 loss)
I0405 22:22:14.301754 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 9.68969e-05 (* 0.0454545 = 4.40441e-06 loss)
I0405 22:22:14.301769 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 8.57485e-05 (* 0.0454545 = 3.89766e-06 loss)
I0405 22:22:14.301782 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 8.40443e-05 (* 0.0454545 = 3.8202e-06 loss)
I0405 22:22:14.301797 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 8.68535e-05 (* 0.0454545 = 3.94789e-06 loss)
I0405 22:22:14.301810 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0.03125
I0405 22:22:14.301821 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.0153248
I0405 22:22:14.301836 29564 sgd_solver.cpp:106] Iteration 66500, lr = 0.009335
I0405 22:26:07.190371 29564 solver.cpp:229] Iteration 67000, loss = 0.779515
I0405 22:26:07.190521 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.28125
I0405 22:26:07.190551 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.15625
I0405 22:26:07.190573 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 22:26:07.190594 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 22:26:07.190618 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.25
I0405 22:26:07.190639 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5
I0405 22:26:07.190659 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.75
I0405 22:26:07.190680 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.90625
I0405 22:26:07.190701 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.9375
I0405 22:26:07.190723 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 22:26:07.190744 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:26:07.190765 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:26:07.190785 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:26:07.190805 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:26:07.190824 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:26:07.190845 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:26:07.190865 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:26:07.190886 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:26:07.190907 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:26:07.190927 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:26:07.190948 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:26:07.190971 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:26:07.190999 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.44991 (* 0.0454545 = 0.111359 loss)
I0405 22:26:07.191023 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.2834 (* 0.0454545 = 0.149245 loss)
I0405 22:26:07.191050 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.20293 (* 0.0454545 = 0.145588 loss)
I0405 22:26:07.191074 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.35978 (* 0.0454545 = 0.152717 loss)
I0405 22:26:07.191102 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.63612 (* 0.0454545 = 0.119824 loss)
I0405 22:26:07.191128 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.90859 (* 0.0454545 = 0.0867542 loss)
I0405 22:26:07.191153 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.28294 (* 0.0454545 = 0.0583154 loss)
I0405 22:26:07.191177 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.502715 (* 0.0454545 = 0.0228507 loss)
I0405 22:26:07.191202 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.230168 (* 0.0454545 = 0.0104622 loss)
I0405 22:26:07.191227 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0617882 (* 0.0454545 = 0.00280856 loss)
I0405 22:26:07.191253 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 5.68846e-05 (* 0.0454545 = 2.58566e-06 loss)
I0405 22:26:07.191277 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.78383e-05 (* 0.0454545 = 2.62901e-06 loss)
I0405 22:26:07.191303 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 5.66396e-05 (* 0.0454545 = 2.57453e-06 loss)
I0405 22:26:07.191328 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 5.94282e-05 (* 0.0454545 = 2.70128e-06 loss)
I0405 22:26:07.191354 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 5.09554e-05 (* 0.0454545 = 2.31616e-06 loss)
I0405 22:26:07.191380 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.93434e-05 (* 0.0454545 = 2.24288e-06 loss)
I0405 22:26:07.191406 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 5.29733e-05 (* 0.0454545 = 2.40788e-06 loss)
I0405 22:26:07.191452 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 4.49736e-05 (* 0.0454545 = 2.04425e-06 loss)
I0405 22:26:07.191479 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 5.83429e-05 (* 0.0454545 = 2.65195e-06 loss)
I0405 22:26:07.191504 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.47407e-05 (* 0.0454545 = 2.03367e-06 loss)
I0405 22:26:07.191535 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 5.10199e-05 (* 0.0454545 = 2.31909e-06 loss)
I0405 22:26:07.191561 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.24678e-05 (* 0.0454545 = 1.93036e-06 loss)
I0405 22:26:07.191583 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:26:07.191603 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.0060467
I0405 22:26:07.191627 29564 sgd_solver.cpp:106] Iteration 67000, lr = 0.00933
I0405 22:29:58.799440 29564 solver.cpp:229] Iteration 67500, loss = 0.775161
I0405 22:29:58.799566 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.53125
I0405 22:29:58.799595 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.25
I0405 22:29:58.799620 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.15625
I0405 22:29:58.799645 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 22:29:58.799666 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.40625
I0405 22:29:58.799687 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.4375
I0405 22:29:58.799707 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 22:29:58.799731 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 22:29:58.799752 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.96875
I0405 22:29:58.799772 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 22:29:58.799793 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:29:58.799813 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:29:58.799832 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:29:58.799852 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:29:58.799875 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:29:58.799896 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:29:58.799914 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:29:58.799934 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:29:58.799955 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:29:58.799979 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:29:58.799999 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:29:58.800020 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:29:58.800046 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 1.89324 (* 0.0454545 = 0.0860565 loss)
I0405 22:29:58.800093 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.73869 (* 0.0454545 = 0.124486 loss)
I0405 22:29:58.800123 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.06051 (* 0.0454545 = 0.139114 loss)
I0405 22:29:58.800149 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.90282 (* 0.0454545 = 0.131946 loss)
I0405 22:29:58.800174 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.33561 (* 0.0454545 = 0.106164 loss)
I0405 22:29:58.800199 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.88273 (* 0.0454545 = 0.0855788 loss)
I0405 22:29:58.800223 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.91088 (* 0.0454545 = 0.0414036 loss)
I0405 22:29:58.800248 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.372064 (* 0.0454545 = 0.016912 loss)
I0405 22:29:58.800273 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.108936 (* 0.0454545 = 0.00495163 loss)
I0405 22:29:58.800298 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00681405 (* 0.0454545 = 0.00030973 loss)
I0405 22:29:58.800324 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 1.83094e-05 (* 0.0454545 = 8.32246e-07 loss)
I0405 22:29:58.800349 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 1.87996e-05 (* 0.0454545 = 8.54525e-07 loss)
I0405 22:29:58.800375 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 1.83393e-05 (* 0.0454545 = 8.33604e-07 loss)
I0405 22:29:58.800402 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 1.69533e-05 (* 0.0454545 = 7.70604e-07 loss)
I0405 22:29:58.800428 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 1.78735e-05 (* 0.0454545 = 8.12432e-07 loss)
I0405 22:29:58.800452 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 2.44358e-05 (* 0.0454545 = 1.11072e-06 loss)
I0405 22:29:58.800477 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 1.83226e-05 (* 0.0454545 = 8.32847e-07 loss)
I0405 22:29:58.800524 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 1.58951e-05 (* 0.0454545 = 7.22503e-07 loss)
I0405 22:29:58.800551 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 1.77357e-05 (* 0.0454545 = 8.06167e-07 loss)
I0405 22:29:58.800575 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.07895e-05 (* 0.0454545 = 9.44977e-07 loss)
I0405 22:29:58.800606 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 1.57794e-05 (* 0.0454545 = 7.17246e-07 loss)
I0405 22:29:58.800631 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 1.89004e-05 (* 0.0454545 = 8.5911e-07 loss)
I0405 22:29:58.800652 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:29:58.800673 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00106704
I0405 22:29:58.800694 29564 sgd_solver.cpp:106] Iteration 67500, lr = 0.009325
I0405 22:33:50.081284 29564 solver.cpp:229] Iteration 68000, loss = 0.770231
I0405 22:33:50.081562 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.40625
I0405 22:33:50.081580 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 22:33:50.081593 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 22:33:50.081609 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 22:33:50.081622 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.21875
I0405 22:33:50.081634 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.3125
I0405 22:33:50.081646 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.625
I0405 22:33:50.081658 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 22:33:50.081670 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 22:33:50.081682 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 22:33:50.081693 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:33:50.081706 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:33:50.081717 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:33:50.081727 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:33:50.081739 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:33:50.081750 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:33:50.081761 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:33:50.081773 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:33:50.081784 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:33:50.081795 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:33:50.081809 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:33:50.081820 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:33:50.081835 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.32165 (* 0.0454545 = 0.105529 loss)
I0405 22:33:50.081850 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 3.31109 (* 0.0454545 = 0.150504 loss)
I0405 22:33:50.081863 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.34072 (* 0.0454545 = 0.151851 loss)
I0405 22:33:50.081877 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.02034 (* 0.0454545 = 0.137288 loss)
I0405 22:33:50.081892 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.90157 (* 0.0454545 = 0.13189 loss)
I0405 22:33:50.081905 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.56954 (* 0.0454545 = 0.116797 loss)
I0405 22:33:50.081919 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.50514 (* 0.0454545 = 0.0684155 loss)
I0405 22:33:50.081933 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.373601 (* 0.0454545 = 0.0169819 loss)
I0405 22:33:50.081948 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0178513 (* 0.0454545 = 0.000811421 loss)
I0405 22:33:50.081962 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00554224 (* 0.0454545 = 0.00025192 loss)
I0405 22:33:50.081977 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 5.73727e-05 (* 0.0454545 = 2.60785e-06 loss)
I0405 22:33:50.081991 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.12697e-05 (* 0.0454545 = 2.33044e-06 loss)
I0405 22:33:50.082008 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 5.84333e-05 (* 0.0454545 = 2.65606e-06 loss)
I0405 22:33:50.082023 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 4.9783e-05 (* 0.0454545 = 2.26286e-06 loss)
I0405 22:33:50.082037 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 5.04374e-05 (* 0.0454545 = 2.29261e-06 loss)
I0405 22:33:50.082051 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 5.12679e-05 (* 0.0454545 = 2.33036e-06 loss)
I0405 22:33:50.082067 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 5.20656e-05 (* 0.0454545 = 2.36662e-06 loss)
I0405 22:33:50.082093 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 4.92933e-05 (* 0.0454545 = 2.2406e-06 loss)
I0405 22:33:50.082109 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 5.44643e-05 (* 0.0454545 = 2.47565e-06 loss)
I0405 22:33:50.082123 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 5.29555e-05 (* 0.0454545 = 2.40707e-06 loss)
I0405 22:33:50.082137 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 4.98288e-05 (* 0.0454545 = 2.26494e-06 loss)
I0405 22:33:50.082152 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 5.64517e-05 (* 0.0454545 = 2.56598e-06 loss)
I0405 22:33:50.082165 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:33:50.082176 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00201641
I0405 22:33:50.082190 29564 sgd_solver.cpp:106] Iteration 68000, lr = 0.00932
I0405 22:37:42.219012 29564 solver.cpp:229] Iteration 68500, loss = 0.774291
I0405 22:37:42.219115 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.4375
I0405 22:37:42.219133 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.25
I0405 22:37:42.219146 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.1875
I0405 22:37:42.219158 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.15625
I0405 22:37:42.219171 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.34375
I0405 22:37:42.219182 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.53125
I0405 22:37:42.219193 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 22:37:42.219205 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 22:37:42.219218 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 22:37:42.219229 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.96875
I0405 22:37:42.219241 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:37:42.219254 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:37:42.219264 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:37:42.219275 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:37:42.219286 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:37:42.219298 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:37:42.219310 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:37:42.219321 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:37:42.219332 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:37:42.219343 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:37:42.219357 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:37:42.219367 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:37:42.219383 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 1.92804 (* 0.0454545 = 0.087638 loss)
I0405 22:37:42.219398 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.62167 (* 0.0454545 = 0.119167 loss)
I0405 22:37:42.219411 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.02803 (* 0.0454545 = 0.137638 loss)
I0405 22:37:42.219425 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.68076 (* 0.0454545 = 0.121853 loss)
I0405 22:37:42.219440 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.54688 (* 0.0454545 = 0.115767 loss)
I0405 22:37:42.219455 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.69348 (* 0.0454545 = 0.0769764 loss)
I0405 22:37:42.219468 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.964836 (* 0.0454545 = 0.0438562 loss)
I0405 22:37:42.219482 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.712686 (* 0.0454545 = 0.0323948 loss)
I0405 22:37:42.219496 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.466899 (* 0.0454545 = 0.0212227 loss)
I0405 22:37:42.219511 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.281326 (* 0.0454545 = 0.0127875 loss)
I0405 22:37:42.219526 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 5.38525e-05 (* 0.0454545 = 2.44784e-06 loss)
I0405 22:37:42.219539 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.81917e-05 (* 0.0454545 = 2.64508e-06 loss)
I0405 22:37:42.219554 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 5.26276e-05 (* 0.0454545 = 2.39216e-06 loss)
I0405 22:37:42.219568 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 5.41383e-05 (* 0.0454545 = 2.46083e-06 loss)
I0405 22:37:42.219583 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 5.52045e-05 (* 0.0454545 = 2.50929e-06 loss)
I0405 22:37:42.219596 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 4.61598e-05 (* 0.0454545 = 2.09817e-06 loss)
I0405 22:37:42.219611 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 5.51122e-05 (* 0.0454545 = 2.5051e-06 loss)
I0405 22:37:42.219643 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 4.73319e-05 (* 0.0454545 = 2.15145e-06 loss)
I0405 22:37:42.219658 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.99812e-05 (* 0.0454545 = 2.27187e-06 loss)
I0405 22:37:42.219672 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 5.27428e-05 (* 0.0454545 = 2.3974e-06 loss)
I0405 22:37:42.219689 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 4.68232e-05 (* 0.0454545 = 2.12833e-06 loss)
I0405 22:37:42.219704 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 5.21684e-05 (* 0.0454545 = 2.37129e-06 loss)
I0405 22:37:42.219717 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:37:42.219728 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.000787454
I0405 22:37:42.219741 29564 sgd_solver.cpp:106] Iteration 68500, lr = 0.009315
I0405 22:41:33.962854 29564 solver.cpp:229] Iteration 69000, loss = 0.770882
I0405 22:41:33.963076 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.46875
I0405 22:41:33.963095 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 22:41:33.963107 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 22:41:33.963121 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.1875
I0405 22:41:33.963134 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.28125
I0405 22:41:33.963145 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.40625
I0405 22:41:33.963157 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 22:41:33.963168 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.84375
I0405 22:41:33.963181 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 22:41:33.963192 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 22:41:33.963203 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:41:33.963214 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:41:33.963225 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:41:33.963238 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:41:33.963248 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:41:33.963260 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:41:33.963271 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:41:33.963282 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:41:33.963294 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:41:33.963304 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:41:33.963316 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:41:33.963327 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:41:33.963342 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 1.80476 (* 0.0454545 = 0.0820345 loss)
I0405 22:41:33.963356 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.67057 (* 0.0454545 = 0.12139 loss)
I0405 22:41:33.963371 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.75163 (* 0.0454545 = 0.125074 loss)
I0405 22:41:33.963384 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.98584 (* 0.0454545 = 0.13572 loss)
I0405 22:41:33.963398 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.37135 (* 0.0454545 = 0.107789 loss)
I0405 22:41:33.963413 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 2.37438 (* 0.0454545 = 0.107926 loss)
I0405 22:41:33.963426 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.03757 (* 0.0454545 = 0.0471625 loss)
I0405 22:41:33.963440 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.631376 (* 0.0454545 = 0.0286989 loss)
I0405 22:41:33.963455 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0231071 (* 0.0454545 = 0.00105032 loss)
I0405 22:41:33.963469 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00539053 (* 0.0454545 = 0.000245024 loss)
I0405 22:41:33.963485 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 2.84522e-05 (* 0.0454545 = 1.29328e-06 loss)
I0405 22:41:33.963498 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 2.69964e-05 (* 0.0454545 = 1.22711e-06 loss)
I0405 22:41:33.963512 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 2.65034e-05 (* 0.0454545 = 1.2047e-06 loss)
I0405 22:41:33.963527 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 2.60652e-05 (* 0.0454545 = 1.18478e-06 loss)
I0405 22:41:33.963541 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 2.77666e-05 (* 0.0454545 = 1.26212e-06 loss)
I0405 22:41:33.963556 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 2.83889e-05 (* 0.0454545 = 1.29041e-06 loss)
I0405 22:41:33.963569 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 2.68888e-05 (* 0.0454545 = 1.22222e-06 loss)
I0405 22:41:33.963600 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 2.61586e-05 (* 0.0454545 = 1.18903e-06 loss)
I0405 22:41:33.963615 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.59921e-05 (* 0.0454545 = 1.18146e-06 loss)
I0405 22:41:33.963629 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.54618e-05 (* 0.0454545 = 1.15736e-06 loss)
I0405 22:41:33.963644 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 2.09558e-05 (* 0.0454545 = 9.52538e-07 loss)
I0405 22:41:33.963659 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 1.80621e-05 (* 0.0454545 = 8.21006e-07 loss)
I0405 22:41:33.963670 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:41:33.963682 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00144444
I0405 22:41:33.963696 29564 sgd_solver.cpp:106] Iteration 69000, lr = 0.00931
I0405 22:45:26.475708 29564 solver.cpp:229] Iteration 69500, loss = 0.768303
I0405 22:45:26.475841 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.21875
I0405 22:45:26.475860 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.09375
I0405 22:45:26.475873 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.0625
I0405 22:45:26.475886 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.09375
I0405 22:45:26.475898 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.3125
I0405 22:45:26.475910 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.46875
I0405 22:45:26.475922 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.78125
I0405 22:45:26.475934 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 22:45:26.475945 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 22:45:26.475956 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 22:45:26.475970 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:45:26.475980 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:45:26.475992 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:45:26.476003 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:45:26.476016 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:45:26.476027 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:45:26.476037 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:45:26.476048 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:45:26.476060 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:45:26.476084 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:45:26.476099 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:45:26.476109 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:45:26.476125 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.46924 (* 0.0454545 = 0.112238 loss)
I0405 22:45:26.476140 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.97982 (* 0.0454545 = 0.135447 loss)
I0405 22:45:26.476153 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 3.05679 (* 0.0454545 = 0.138945 loss)
I0405 22:45:26.476167 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 3.24105 (* 0.0454545 = 0.147321 loss)
I0405 22:45:26.476181 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.54451 (* 0.0454545 = 0.11566 loss)
I0405 22:45:26.476196 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.84843 (* 0.0454545 = 0.0840198 loss)
I0405 22:45:26.476209 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.842697 (* 0.0454545 = 0.0383044 loss)
I0405 22:45:26.476223 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.413717 (* 0.0454545 = 0.0188053 loss)
I0405 22:45:26.476238 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.0335278 (* 0.0454545 = 0.00152399 loss)
I0405 22:45:26.476251 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.0103958 (* 0.0454545 = 0.000472536 loss)
I0405 22:45:26.476266 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 9.28685e-05 (* 0.0454545 = 4.22129e-06 loss)
I0405 22:45:26.476280 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 9.15552e-05 (* 0.0454545 = 4.1616e-06 loss)
I0405 22:45:26.476294 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 8.37188e-05 (* 0.0454545 = 3.8054e-06 loss)
I0405 22:45:26.476308 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 8.72734e-05 (* 0.0454545 = 3.96697e-06 loss)
I0405 22:45:26.476322 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 9.86082e-05 (* 0.0454545 = 4.48219e-06 loss)
I0405 22:45:26.476336 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 8.33612e-05 (* 0.0454545 = 3.78914e-06 loss)
I0405 22:45:26.476351 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 8.92459e-05 (* 0.0454545 = 4.05663e-06 loss)
I0405 22:45:26.476382 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 9.21111e-05 (* 0.0454545 = 4.18687e-06 loss)
I0405 22:45:26.476397 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 7.94528e-05 (* 0.0454545 = 3.61149e-06 loss)
I0405 22:45:26.476411 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 9.27504e-05 (* 0.0454545 = 4.21593e-06 loss)
I0405 22:45:26.476425 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 7.30127e-05 (* 0.0454545 = 3.31876e-06 loss)
I0405 22:45:26.476439 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 8.80888e-05 (* 0.0454545 = 4.00404e-06 loss)
I0405 22:45:26.476452 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:45:26.476464 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.00159681
I0405 22:45:26.476477 29564 sgd_solver.cpp:106] Iteration 69500, lr = 0.009305
I0405 22:49:18.306404 29564 solver.cpp:338] Iteration 70000, Testing net (#0)
I0405 22:49:28.562494 29564 solver.cpp:393] Test loss: 0.671108
I0405 22:49:28.562542 29564 solver.cpp:406]     Test net output #0: loss/accuracy01 = 0.377
I0405 22:49:28.562559 29564 solver.cpp:406]     Test net output #1: loss/accuracy02 = 0.195
I0405 22:49:28.562572 29564 solver.cpp:406]     Test net output #2: loss/accuracy03 = 0.175
I0405 22:49:28.562583 29564 solver.cpp:406]     Test net output #3: loss/accuracy04 = 0.222
I0405 22:49:28.562595 29564 solver.cpp:406]     Test net output #4: loss/accuracy05 = 0.308
I0405 22:49:28.562607 29564 solver.cpp:406]     Test net output #5: loss/accuracy06 = 0.559
I0405 22:49:28.562618 29564 solver.cpp:406]     Test net output #6: loss/accuracy07 = 0.899
I0405 22:49:28.562629 29564 solver.cpp:406]     Test net output #7: loss/accuracy08 = 0.97
I0405 22:49:28.562641 29564 solver.cpp:406]     Test net output #8: loss/accuracy09 = 0.995
I0405 22:49:28.562652 29564 solver.cpp:406]     Test net output #9: loss/accuracy10 = 0.998
I0405 22:49:28.562664 29564 solver.cpp:406]     Test net output #10: loss/accuracy11 = 1
I0405 22:49:28.562675 29564 solver.cpp:406]     Test net output #11: loss/accuracy12 = 1
I0405 22:49:28.562686 29564 solver.cpp:406]     Test net output #12: loss/accuracy13 = 1
I0405 22:49:28.562697 29564 solver.cpp:406]     Test net output #13: loss/accuracy14 = 1
I0405 22:49:28.562708 29564 solver.cpp:406]     Test net output #14: loss/accuracy15 = 1
I0405 22:49:28.562719 29564 solver.cpp:406]     Test net output #15: loss/accuracy16 = 1
I0405 22:49:28.562731 29564 solver.cpp:406]     Test net output #16: loss/accuracy17 = 1
I0405 22:49:28.562742 29564 solver.cpp:406]     Test net output #17: loss/accuracy18 = 1
I0405 22:49:28.562753 29564 solver.cpp:406]     Test net output #18: loss/accuracy19 = 1
I0405 22:49:28.562764 29564 solver.cpp:406]     Test net output #19: loss/accuracy20 = 1
I0405 22:49:28.562775 29564 solver.cpp:406]     Test net output #20: loss/accuracy21 = 1
I0405 22:49:28.562786 29564 solver.cpp:406]     Test net output #21: loss/accuracy22 = 1
I0405 22:49:28.562803 29564 solver.cpp:406]     Test net output #22: loss/loss01 = 2.14711 (* 0.0454545 = 0.0975961 loss)
I0405 22:49:28.562816 29564 solver.cpp:406]     Test net output #23: loss/loss02 = 2.61663 (* 0.0454545 = 0.118938 loss)
I0405 22:49:28.562830 29564 solver.cpp:406]     Test net output #24: loss/loss03 = 2.68823 (* 0.0454545 = 0.122192 loss)
I0405 22:49:28.562844 29564 solver.cpp:406]     Test net output #25: loss/loss04 = 2.64362 (* 0.0454545 = 0.120165 loss)
I0405 22:49:28.562858 29564 solver.cpp:406]     Test net output #26: loss/loss05 = 2.43742 (* 0.0454545 = 0.110792 loss)
I0405 22:49:28.562875 29564 solver.cpp:406]     Test net output #27: loss/loss06 = 1.53994 (* 0.0454545 = 0.0699975 loss)
I0405 22:49:28.562890 29564 solver.cpp:406]     Test net output #28: loss/loss07 = 0.425049 (* 0.0454545 = 0.0193204 loss)
I0405 22:49:28.562903 29564 solver.cpp:406]     Test net output #29: loss/loss08 = 0.192644 (* 0.0454545 = 0.00875655 loss)
I0405 22:49:28.562917 29564 solver.cpp:406]     Test net output #30: loss/loss09 = 0.0489488 (* 0.0454545 = 0.00222495 loss)
I0405 22:49:28.562932 29564 solver.cpp:406]     Test net output #31: loss/loss10 = 0.0240476 (* 0.0454545 = 0.00109307 loss)
I0405 22:49:28.562945 29564 solver.cpp:406]     Test net output #32: loss/loss11 = 6.21048e-05 (* 0.0454545 = 2.82295e-06 loss)
I0405 22:49:28.562959 29564 solver.cpp:406]     Test net output #33: loss/loss12 = 6.85464e-05 (* 0.0454545 = 3.11575e-06 loss)
I0405 22:49:28.562973 29564 solver.cpp:406]     Test net output #34: loss/loss13 = 6.40279e-05 (* 0.0454545 = 2.91036e-06 loss)
I0405 22:49:28.562988 29564 solver.cpp:406]     Test net output #35: loss/loss14 = 6.74663e-05 (* 0.0454545 = 3.06665e-06 loss)
I0405 22:49:28.563001 29564 solver.cpp:406]     Test net output #36: loss/loss15 = 6.51602e-05 (* 0.0454545 = 2.96183e-06 loss)
I0405 22:49:28.563016 29564 solver.cpp:406]     Test net output #37: loss/loss16 = 6.02009e-05 (* 0.0454545 = 2.73641e-06 loss)
I0405 22:49:28.563030 29564 solver.cpp:406]     Test net output #38: loss/loss17 = 5.74405e-05 (* 0.0454545 = 2.61093e-06 loss)
I0405 22:49:28.563077 29564 solver.cpp:406]     Test net output #39: loss/loss18 = 6.07843e-05 (* 0.0454545 = 2.76292e-06 loss)
I0405 22:49:28.563092 29564 solver.cpp:406]     Test net output #40: loss/loss19 = 6.43061e-05 (* 0.0454545 = 2.92301e-06 loss)
I0405 22:49:28.563107 29564 solver.cpp:406]     Test net output #41: loss/loss20 = 5.80721e-05 (* 0.0454545 = 2.63964e-06 loss)
I0405 22:49:28.563120 29564 solver.cpp:406]     Test net output #42: loss/loss21 = 5.85362e-05 (* 0.0454545 = 2.66074e-06 loss)
I0405 22:49:28.563134 29564 solver.cpp:406]     Test net output #43: loss/loss22 = 5.83152e-05 (* 0.0454545 = 2.65069e-06 loss)
I0405 22:49:28.563146 29564 solver.cpp:406]     Test net output #44: total_accuracy = 0.003
I0405 22:49:28.563158 29564 solver.cpp:406]     Test net output #45: total_confidence = 0.00430348
I0405 22:49:28.677342 29564 solver.cpp:229] Iteration 70000, loss = 0.768503
I0405 22:49:28.677379 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.34375
I0405 22:49:28.677395 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.21875
I0405 22:49:28.677408 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.21875
I0405 22:49:28.677419 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.21875
I0405 22:49:28.677431 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.34375
I0405 22:49:28.677443 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.5
I0405 22:49:28.677454 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.6875
I0405 22:49:28.677466 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.8125
I0405 22:49:28.677479 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 0.90625
I0405 22:49:28.677490 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 0.9375
I0405 22:49:28.677501 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:49:28.677513 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:49:28.677525 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:49:28.677536 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:49:28.677547 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:49:28.677558 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:49:28.677569 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:49:28.677582 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:49:28.677592 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:49:28.677603 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:49:28.677614 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:49:28.677625 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:49:28.677640 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.12392 (* 0.0454545 = 0.096542 loss)
I0405 22:49:28.677654 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.67779 (* 0.0454545 = 0.121718 loss)
I0405 22:49:28.677667 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.73406 (* 0.0454545 = 0.124275 loss)
I0405 22:49:28.677681 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.81331 (* 0.0454545 = 0.127878 loss)
I0405 22:49:28.677695 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.43411 (* 0.0454545 = 0.110641 loss)
I0405 22:49:28.677712 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.93451 (* 0.0454545 = 0.0879325 loss)
I0405 22:49:28.677726 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 1.21791 (* 0.0454545 = 0.0553595 loss)
I0405 22:49:28.677739 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.700563 (* 0.0454545 = 0.0318438 loss)
I0405 22:49:28.677753 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.394339 (* 0.0454545 = 0.0179245 loss)
I0405 22:49:28.677784 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.253616 (* 0.0454545 = 0.011528 loss)
I0405 22:49:28.677799 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 5.04593e-05 (* 0.0454545 = 2.2936e-06 loss)
I0405 22:49:28.677814 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 5.41182e-05 (* 0.0454545 = 2.45992e-06 loss)
I0405 22:49:28.677829 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 5.86603e-05 (* 0.0454545 = 2.66638e-06 loss)
I0405 22:49:28.677842 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 5.30174e-05 (* 0.0454545 = 2.40988e-06 loss)
I0405 22:49:28.677855 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 5.44795e-05 (* 0.0454545 = 2.47634e-06 loss)
I0405 22:49:28.677870 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 5.2743e-05 (* 0.0454545 = 2.39741e-06 loss)
I0405 22:49:28.677883 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 5.34718e-05 (* 0.0454545 = 2.43054e-06 loss)
I0405 22:49:28.677897 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 5.34548e-05 (* 0.0454545 = 2.42977e-06 loss)
I0405 22:49:28.677912 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 4.90003e-05 (* 0.0454545 = 2.22728e-06 loss)
I0405 22:49:28.677928 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 4.47748e-05 (* 0.0454545 = 2.03522e-06 loss)
I0405 22:49:28.677942 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 5.32285e-05 (* 0.0454545 = 2.41948e-06 loss)
I0405 22:49:28.677955 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 4.70836e-05 (* 0.0454545 = 2.14016e-06 loss)
I0405 22:49:28.677968 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:49:28.677979 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.0047996
I0405 22:49:28.677992 29564 sgd_solver.cpp:106] Iteration 70000, lr = 0.0093
I0405 22:53:20.521121 29564 solver.cpp:229] Iteration 70500, loss = 0.763873
I0405 22:53:20.521356 29564 solver.cpp:245]     Train net output #0: loss/accuracy01 = 0.40625
I0405 22:53:20.521376 29564 solver.cpp:245]     Train net output #1: loss/accuracy02 = 0.25
I0405 22:53:20.521389 29564 solver.cpp:245]     Train net output #2: loss/accuracy03 = 0.125
I0405 22:53:20.521400 29564 solver.cpp:245]     Train net output #3: loss/accuracy04 = 0.25
I0405 22:53:20.521412 29564 solver.cpp:245]     Train net output #4: loss/accuracy05 = 0.375
I0405 22:53:20.521425 29564 solver.cpp:245]     Train net output #5: loss/accuracy06 = 0.59375
I0405 22:53:20.521435 29564 solver.cpp:245]     Train net output #6: loss/accuracy07 = 0.90625
I0405 22:53:20.521447 29564 solver.cpp:245]     Train net output #7: loss/accuracy08 = 0.9375
I0405 22:53:20.521459 29564 solver.cpp:245]     Train net output #8: loss/accuracy09 = 1
I0405 22:53:20.521471 29564 solver.cpp:245]     Train net output #9: loss/accuracy10 = 1
I0405 22:53:20.521483 29564 solver.cpp:245]     Train net output #10: loss/accuracy11 = 1
I0405 22:53:20.521494 29564 solver.cpp:245]     Train net output #11: loss/accuracy12 = 1
I0405 22:53:20.521505 29564 solver.cpp:245]     Train net output #12: loss/accuracy13 = 1
I0405 22:53:20.521517 29564 solver.cpp:245]     Train net output #13: loss/accuracy14 = 1
I0405 22:53:20.521528 29564 solver.cpp:245]     Train net output #14: loss/accuracy15 = 1
I0405 22:53:20.521539 29564 solver.cpp:245]     Train net output #15: loss/accuracy16 = 1
I0405 22:53:20.521550 29564 solver.cpp:245]     Train net output #16: loss/accuracy17 = 1
I0405 22:53:20.521561 29564 solver.cpp:245]     Train net output #17: loss/accuracy18 = 1
I0405 22:53:20.521572 29564 solver.cpp:245]     Train net output #18: loss/accuracy19 = 1
I0405 22:53:20.521584 29564 solver.cpp:245]     Train net output #19: loss/accuracy20 = 1
I0405 22:53:20.521595 29564 solver.cpp:245]     Train net output #20: loss/accuracy21 = 1
I0405 22:53:20.521607 29564 solver.cpp:245]     Train net output #21: loss/accuracy22 = 1
I0405 22:53:20.521621 29564 solver.cpp:245]     Train net output #22: loss/loss01 = 2.214 (* 0.0454545 = 0.100637 loss)
I0405 22:53:20.521636 29564 solver.cpp:245]     Train net output #23: loss/loss02 = 2.73827 (* 0.0454545 = 0.124467 loss)
I0405 22:53:20.521649 29564 solver.cpp:245]     Train net output #24: loss/loss03 = 2.9467 (* 0.0454545 = 0.133941 loss)
I0405 22:53:20.521663 29564 solver.cpp:245]     Train net output #25: loss/loss04 = 2.63344 (* 0.0454545 = 0.119702 loss)
I0405 22:53:20.521677 29564 solver.cpp:245]     Train net output #26: loss/loss05 = 2.2057 (* 0.0454545 = 0.100259 loss)
I0405 22:53:20.521692 29564 solver.cpp:245]     Train net output #27: loss/loss06 = 1.55155 (* 0.0454545 = 0.070525 loss)
I0405 22:53:20.521705 29564 solver.cpp:245]     Train net output #28: loss/loss07 = 0.382458 (* 0.0454545 = 0.0173844 loss)
I0405 22:53:20.521719 29564 solver.cpp:245]     Train net output #29: loss/loss08 = 0.274554 (* 0.0454545 = 0.0124797 loss)
I0405 22:53:20.521733 29564 solver.cpp:245]     Train net output #30: loss/loss09 = 0.00807781 (* 0.0454545 = 0.000367173 loss)
I0405 22:53:20.521747 29564 solver.cpp:245]     Train net output #31: loss/loss10 = 0.00292341 (* 0.0454545 = 0.000132882 loss)
I0405 22:53:20.521761 29564 solver.cpp:245]     Train net output #32: loss/loss11 = 3.43316e-05 (* 0.0454545 = 1.56053e-06 loss)
I0405 22:53:20.521775 29564 solver.cpp:245]     Train net output #33: loss/loss12 = 3.5327e-05 (* 0.0454545 = 1.60577e-06 loss)
I0405 22:53:20.521790 29564 solver.cpp:245]     Train net output #34: loss/loss13 = 3.32325e-05 (* 0.0454545 = 1.51057e-06 loss)
I0405 22:53:20.521803 29564 solver.cpp:245]     Train net output #35: loss/loss14 = 2.93457e-05 (* 0.0454545 = 1.33389e-06 loss)
I0405 22:53:20.521817 29564 solver.cpp:245]     Train net output #36: loss/loss15 = 3.03404e-05 (* 0.0454545 = 1.37911e-06 loss)
I0405 22:53:20.521831 29564 solver.cpp:245]     Train net output #37: loss/loss16 = 3.12482e-05 (* 0.0454545 = 1.42037e-06 loss)
I0405 22:53:20.521845 29564 solver.cpp:245]     Train net output #38: loss/loss17 = 3.16097e-05 (* 0.0454545 = 1.43681e-06 loss)
I0405 22:53:20.521875 29564 solver.cpp:245]     Train net output #39: loss/loss18 = 2.84477e-05 (* 0.0454545 = 1.29308e-06 loss)
I0405 22:53:20.521890 29564 solver.cpp:245]     Train net output #40: loss/loss19 = 2.85108e-05 (* 0.0454545 = 1.29594e-06 loss)
I0405 22:53:20.521904 29564 solver.cpp:245]     Train net output #41: loss/loss20 = 2.99065e-05 (* 0.0454545 = 1.35939e-06 loss)
I0405 22:53:20.521919 29564 solver.cpp:245]     Train net output #42: loss/loss21 = 2.9389e-05 (* 0.0454545 = 1.33586e-06 loss)
I0405 22:53:20.521932 29564 solver.cpp:245]     Train net output #43: loss/loss22 = 2.97798e-05 (* 0.0454545 = 1.35363e-06 loss)
I0405 22:53:20.521945 29564 solver.cpp:245]     Train net output #44: total_accuracy = 0
I0405 22:53:20.521956 29564 solver.cpp:245]     Train net output #45: total_confidence = 0.0047478
I0405 22:53:20.521972 29564 sgd_solver.cpp:106] Iteration 70500, lr = 0.009295