Skip to content

Instantly share code, notes, and snippets.

@davidberard98

davidberard98/FSDP_T5-large_wrapping.txt

Last active November 18, 2022 01:03
Show Gist options
  • Save davidberard98/db7bdb10ec261383e89dcf36b632528a to your computer and use it in GitHub Desktop.
Save davidberard98/db7bdb10ec261383e89dcf36b632528a to your computer and use it in GitHub Desktop.
Download ZIP
Raw
FSDP_T5-large_wrapping.txt
FullyShardedDataParallel(
(_fsdp_wrapped_module): T5ForConditionalGeneration(
(shared): Embedding(32128, 1024)
(encoder): T5Stack(
(embed_tokens): Embedding(32128, 1024)
(block): ModuleList(
(0): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
(relative_attention_bias): Embedding(32, 16)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(1): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(2): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(3): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(4): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(5): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(6): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(7): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(8): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(9): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(10): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(11): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(12): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(13): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(14): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(15): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(16): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(17): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(18): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(19): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(20): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(21): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(22): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(23): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
)
(final_layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(decoder): T5Stack(
(embed_tokens): Embedding(32128, 1024)
(block): ModuleList(
(0): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
(relative_attention_bias): Embedding(32, 16)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(1): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(2): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(3): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(4): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(5): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(6): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(7): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(8): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(9): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(10): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(11): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(12): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(13): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(14): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(15): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(16): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(17): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(18): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(19): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(20): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(21): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(22): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(23): FullyShardedDataParallel(
(_fsdp_wrapped_module): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerCrossAttention(
(EncDecAttention): T5Attention(
(q): Linear(in_features=1024, out_features=1024, bias=False)
(k): Linear(in_features=1024, out_features=1024, bias=False)
(v): Linear(in_features=1024, out_features=1024, bias=False)
(o): Linear(in_features=1024, out_features=1024, bias=False)
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(2): T5LayerFF(
(DenseReluDense): T5DenseActDense(
(wi): Linear(in_features=1024, out_features=4096, bias=False)
(wo): Linear(in_features=4096, out_features=1024, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): ReLU()
)
(layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
)
(final_layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
(lm_head): Linear(in_features=1024, out_features=32128, bias=False)
)
)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment