| 2021-01-15 16:27:19,924 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 16:27:19,927 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): XLMRobertaModel( | |
| (embeddings): RobertaEmbeddings( | |
| (word_embeddings): Embedding(250002, 1024, padding_idx=1) | |
| (position_embeddings): Embedding(514, 1024, padding_idx=1) | |
| (token_type_embeddings): Embedding(1, 1024) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): RobertaEncoder( | |
| (layer): ModuleList( | |
| (0): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (1): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (2): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (3): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (4): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (5): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (6): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (7): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (8): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (9): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (10): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (11): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (12): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (13): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (14): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (15): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (16): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (17): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (18): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (19): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (20): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (21): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (22): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (23): RobertaLayer( | |
| (attention): RobertaAttention( | |
| (self): RobertaSelfAttention( | |
| (query): Linear(in_features=1024, out_features=1024, bias=True) | |
| (key): Linear(in_features=1024, out_features=1024, bias=True) | |
| (value): Linear(in_features=1024, out_features=1024, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): RobertaSelfOutput( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): RobertaIntermediate( | |
| (dense): Linear(in_features=1024, out_features=4096, bias=True) | |
| ) | |
| (output): RobertaOutput( | |
| (dense): Linear(in_features=4096, out_features=1024, bias=True) | |
| (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): RobertaPooler( | |
| (dense): Linear(in_features=1024, out_features=1024, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (word_dropout): WordDropout(p=0.05) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=1024, out_features=20, bias=True) | |
| (beta): 1.0 | |
| (weights): None | |
| (weight_tensor) None | |
| )" | |
| 2021-01-15 16:27:19,928 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 16:27:19,928 Corpus: "Corpus: 12705 train + 3068 dev + 3160 test sentences" | |
| 2021-01-15 16:27:19,928 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 16:27:19,928 Parameters: | |
| 2021-01-15 16:27:19,928 - learning_rate: "5e-06" | |
| 2021-01-15 16:27:19,928 - mini_batch_size: "4" | |
| 2021-01-15 16:27:19,928 - patience: "3" | |
| 2021-01-15 16:27:19,928 - anneal_factor: "0.5" | |
| 2021-01-15 16:27:19,928 - max_epochs: "20" | |
| 2021-01-15 16:27:19,928 - shuffle: "True" | |
| 2021-01-15 16:27:19,928 - train_with_dev: "True" | |
| 2021-01-15 16:27:19,928 - batch_growth_annealing: "False" | |
| 2021-01-15 16:27:19,928 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 16:27:19,928 Model training base path: "resources/contextdrop/flert-de-ft+dev-xlm-roberta-large-context+drop-64-True-42" | |
| 2021-01-15 16:27:19,928 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 16:27:19,929 Device: cuda:2 | |
| 2021-01-15 16:27:19,929 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 16:27:19,929 Embeddings storage mode: none | |
| 2021-01-15 16:27:19,939 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 16:29:48,177 epoch 1 - iter 394/3944 - loss 0.58149384 - samples/sec: 10.63 - lr: 0.000005 | |
| 2021-01-15 16:32:16,470 epoch 1 - iter 788/3944 - loss 0.43146001 - samples/sec: 10.63 - lr: 0.000005 | |
| 2021-01-15 16:34:43,836 epoch 1 - iter 1182/3944 - loss 0.38010955 - samples/sec: 10.70 - lr: 0.000005 | |
| 2021-01-15 16:37:11,698 epoch 1 - iter 1576/3944 - loss 0.34431028 - samples/sec: 10.66 - lr: 0.000005 | |
| 2021-01-15 16:39:39,747 epoch 1 - iter 1970/3944 - loss 0.32744939 - samples/sec: 10.65 - lr: 0.000005 | |
| 2021-01-15 16:42:07,631 epoch 1 - iter 2364/3944 - loss 0.31857823 - samples/sec: 10.66 - lr: 0.000005 | |
| 2021-01-15 16:44:34,485 epoch 1 - iter 2758/3944 - loss 0.30456838 - samples/sec: 10.73 - lr: 0.000005 | |
| 2021-01-15 16:47:02,394 epoch 1 - iter 3152/3944 - loss 0.29905511 - samples/sec: 10.66 - lr: 0.000005 | |
| 2021-01-15 16:49:29,868 epoch 1 - iter 3546/3944 - loss 0.29295683 - samples/sec: 10.69 - lr: 0.000005 | |
| 2021-01-15 16:51:58,152 epoch 1 - iter 3940/3944 - loss 0.28678117 - samples/sec: 10.63 - lr: 0.000005 | |
| 2021-01-15 16:51:59,459 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 16:51:59,459 EPOCH 1 done: loss 0.2866 - lr 0.0000050 | |
| 2021-01-15 16:51:59,459 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 16:51:59,462 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 16:54:27,337 epoch 2 - iter 394/3944 - loss 0.23763366 - samples/sec: 10.66 - lr: 0.000005 | |
| 2021-01-15 16:56:55,082 epoch 2 - iter 788/3944 - loss 0.20691177 - samples/sec: 10.67 - lr: 0.000005 | |
| 2021-01-15 16:59:22,869 epoch 2 - iter 1182/3944 - loss 0.21072023 - samples/sec: 10.66 - lr: 0.000005 | |
| 2021-01-15 17:01:50,770 epoch 2 - iter 1576/3944 - loss 0.20705774 - samples/sec: 10.66 - lr: 0.000005 | |
| 2021-01-15 17:04:18,029 epoch 2 - iter 1970/3944 - loss 0.20345128 - samples/sec: 10.70 - lr: 0.000005 | |
| 2021-01-15 17:06:45,050 epoch 2 - iter 2364/3944 - loss 0.19762390 - samples/sec: 10.72 - lr: 0.000005 | |
| 2021-01-15 17:09:11,995 epoch 2 - iter 2758/3944 - loss 0.20206661 - samples/sec: 10.73 - lr: 0.000005 | |
| 2021-01-15 17:11:39,892 epoch 2 - iter 3152/3944 - loss 0.19768991 - samples/sec: 10.66 - lr: 0.000005 | |
| 2021-01-15 17:14:07,315 epoch 2 - iter 3546/3944 - loss 0.20115805 - samples/sec: 10.69 - lr: 0.000005 | |
| 2021-01-15 17:16:34,784 epoch 2 - iter 3940/3944 - loss 0.19983876 - samples/sec: 10.69 - lr: 0.000005 | |
| 2021-01-15 17:16:36,073 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 17:16:36,074 EPOCH 2 done: loss 0.1996 - lr 0.0000049 | |
| 2021-01-15 17:16:36,074 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 17:16:36,077 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 17:19:03,268 epoch 3 - iter 394/3944 - loss 0.16475767 - samples/sec: 10.71 - lr: 0.000005 | |
| 2021-01-15 17:21:30,430 epoch 3 - iter 788/3944 - loss 0.16467943 - samples/sec: 10.71 - lr: 0.000005 | |
| 2021-01-15 17:23:57,785 epoch 3 - iter 1182/3944 - loss 0.16820842 - samples/sec: 10.70 - lr: 0.000005 | |
| 2021-01-15 17:26:25,077 epoch 3 - iter 1576/3944 - loss 0.17111347 - samples/sec: 10.70 - lr: 0.000005 | |
| 2021-01-15 17:28:51,818 epoch 3 - iter 1970/3944 - loss 0.17649180 - samples/sec: 10.74 - lr: 0.000005 | |
| 2021-01-15 17:31:18,679 epoch 3 - iter 2364/3944 - loss 0.18734800 - samples/sec: 10.73 - lr: 0.000005 | |
| 2021-01-15 17:33:45,680 epoch 3 - iter 2758/3944 - loss 0.18971106 - samples/sec: 10.72 - lr: 0.000005 | |
| 2021-01-15 17:36:13,246 epoch 3 - iter 3152/3944 - loss 0.18746164 - samples/sec: 10.68 - lr: 0.000005 | |
| 2021-01-15 17:38:40,672 epoch 3 - iter 3546/3944 - loss 0.19218287 - samples/sec: 10.69 - lr: 0.000005 | |
| 2021-01-15 17:41:07,957 epoch 3 - iter 3940/3944 - loss 0.19381799 - samples/sec: 10.70 - lr: 0.000005 | |
| 2021-01-15 17:41:09,257 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 17:41:09,257 EPOCH 3 done: loss 0.1938 - lr 0.0000047 | |
| 2021-01-15 17:41:09,257 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 17:41:09,260 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 17:43:36,593 epoch 4 - iter 394/3944 - loss 0.16488209 - samples/sec: 10.70 - lr: 0.000005 | |
| 2021-01-15 17:46:04,133 epoch 4 - iter 788/3944 - loss 0.17473605 - samples/sec: 10.68 - lr: 0.000005 | |
| 2021-01-15 17:48:31,440 epoch 4 - iter 1182/3944 - loss 0.16738039 - samples/sec: 10.70 - lr: 0.000005 | |
| 2021-01-15 17:50:58,858 epoch 4 - iter 1576/3944 - loss 0.16596805 - samples/sec: 10.69 - lr: 0.000005 | |
| 2021-01-15 17:53:26,260 epoch 4 - iter 1970/3944 - loss 0.16483490 - samples/sec: 10.69 - lr: 0.000005 | |
| 2021-01-15 17:55:53,072 epoch 4 - iter 2364/3944 - loss 0.16752558 - samples/sec: 10.74 - lr: 0.000005 | |
| 2021-01-15 17:58:19,944 epoch 4 - iter 2758/3944 - loss 0.16537132 - samples/sec: 10.73 - lr: 0.000005 | |
| 2021-01-15 18:00:47,459 epoch 4 - iter 3152/3944 - loss 0.16501133 - samples/sec: 10.68 - lr: 0.000005 | |
| 2021-01-15 18:03:15,474 epoch 4 - iter 3546/3944 - loss 0.16726116 - samples/sec: 10.65 - lr: 0.000005 | |
| 2021-01-15 18:05:43,265 epoch 4 - iter 3940/3944 - loss 0.16914137 - samples/sec: 10.66 - lr: 0.000005 | |
| 2021-01-15 18:05:44,543 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 18:05:44,543 EPOCH 4 done: loss 0.1690 - lr 0.0000045 | |
| 2021-01-15 18:05:44,543 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 18:05:44,547 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 18:08:12,011 epoch 5 - iter 394/3944 - loss 0.15833616 - samples/sec: 10.69 - lr: 0.000004 | |
| 2021-01-15 18:10:38,832 epoch 5 - iter 788/3944 - loss 0.16551527 - samples/sec: 10.74 - lr: 0.000004 | |
| 2021-01-15 18:13:06,451 epoch 5 - iter 1182/3944 - loss 0.17177677 - samples/sec: 10.68 - lr: 0.000004 | |
| 2021-01-15 18:15:34,493 epoch 5 - iter 1576/3944 - loss 0.17301128 - samples/sec: 10.65 - lr: 0.000004 | |
| 2021-01-15 18:18:03,239 epoch 5 - iter 1970/3944 - loss 0.17650116 - samples/sec: 10.60 - lr: 0.000004 | |
| 2021-01-15 18:20:32,247 epoch 5 - iter 2364/3944 - loss 0.17631064 - samples/sec: 10.58 - lr: 0.000004 | |
| 2021-01-15 18:22:59,227 epoch 5 - iter 2758/3944 - loss 0.17537379 - samples/sec: 10.72 - lr: 0.000004 | |
| 2021-01-15 18:25:24,556 epoch 5 - iter 3152/3944 - loss 0.17617518 - samples/sec: 10.85 - lr: 0.000004 | |
| 2021-01-15 18:27:50,096 epoch 5 - iter 3546/3944 - loss 0.17367857 - samples/sec: 10.83 - lr: 0.000004 | |
| 2021-01-15 18:30:16,704 epoch 5 - iter 3940/3944 - loss 0.17093901 - samples/sec: 10.75 - lr: 0.000004 | |
| 2021-01-15 18:30:18,004 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 18:30:18,004 EPOCH 5 done: loss 0.1708 - lr 0.0000043 | |
| 2021-01-15 18:30:18,004 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 18:30:18,007 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 18:32:42,968 epoch 6 - iter 394/3944 - loss 0.17698825 - samples/sec: 10.87 - lr: 0.000004 | |
| 2021-01-15 18:35:08,371 epoch 6 - iter 788/3944 - loss 0.16713416 - samples/sec: 10.84 - lr: 0.000004 | |
| 2021-01-15 18:37:34,014 epoch 6 - iter 1182/3944 - loss 0.16902562 - samples/sec: 10.82 - lr: 0.000004 | |
| 2021-01-15 18:40:00,144 epoch 6 - iter 1576/3944 - loss 0.16574844 - samples/sec: 10.79 - lr: 0.000004 | |
| 2021-01-15 18:42:26,534 epoch 6 - iter 1970/3944 - loss 0.16657012 - samples/sec: 10.77 - lr: 0.000004 | |
| 2021-01-15 18:44:52,613 epoch 6 - iter 2364/3944 - loss 0.16641916 - samples/sec: 10.79 - lr: 0.000004 | |
| 2021-01-15 18:47:17,983 epoch 6 - iter 2758/3944 - loss 0.16274268 - samples/sec: 10.84 - lr: 0.000004 | |
| 2021-01-15 18:49:43,878 epoch 6 - iter 3152/3944 - loss 0.16172776 - samples/sec: 10.80 - lr: 0.000004 | |
| 2021-01-15 18:52:09,331 epoch 6 - iter 3546/3944 - loss 0.16291188 - samples/sec: 10.84 - lr: 0.000004 | |
| 2021-01-15 18:54:34,272 epoch 6 - iter 3940/3944 - loss 0.16208591 - samples/sec: 10.87 - lr: 0.000004 | |
| 2021-01-15 18:54:35,553 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 18:54:35,553 EPOCH 6 done: loss 0.1621 - lr 0.0000040 | |
| 2021-01-15 18:54:35,553 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 18:54:35,556 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 18:57:00,031 epoch 7 - iter 394/3944 - loss 0.15674837 - samples/sec: 10.91 - lr: 0.000004 | |
| 2021-01-15 18:59:25,217 epoch 7 - iter 788/3944 - loss 0.16222971 - samples/sec: 10.86 - lr: 0.000004 | |
| 2021-01-15 19:01:50,483 epoch 7 - iter 1182/3944 - loss 0.17608659 - samples/sec: 10.85 - lr: 0.000004 | |
| 2021-01-15 19:04:15,644 epoch 7 - iter 1576/3944 - loss 0.17042676 - samples/sec: 10.86 - lr: 0.000004 | |
| 2021-01-15 19:06:40,626 epoch 7 - iter 1970/3944 - loss 0.16835536 - samples/sec: 10.87 - lr: 0.000004 | |
| 2021-01-15 19:09:06,269 epoch 7 - iter 2364/3944 - loss 0.17005717 - samples/sec: 10.82 - lr: 0.000004 | |
| 2021-01-15 19:11:30,455 epoch 7 - iter 2758/3944 - loss 0.16986731 - samples/sec: 10.93 - lr: 0.000004 | |
| 2021-01-15 19:13:55,363 epoch 7 - iter 3152/3944 - loss 0.16607768 - samples/sec: 10.88 - lr: 0.000004 | |
| 2021-01-15 19:16:20,669 epoch 7 - iter 3546/3944 - loss 0.16408475 - samples/sec: 10.85 - lr: 0.000004 | |
| 2021-01-15 19:18:46,350 epoch 7 - iter 3940/3944 - loss 0.16187247 - samples/sec: 10.82 - lr: 0.000004 | |
| 2021-01-15 19:18:47,632 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 19:18:47,632 EPOCH 7 done: loss 0.1619 - lr 0.0000036 | |
| 2021-01-15 19:18:47,632 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 19:18:47,635 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 19:21:13,232 epoch 8 - iter 394/3944 - loss 0.15860862 - samples/sec: 10.83 - lr: 0.000004 | |
| 2021-01-15 19:23:37,769 epoch 8 - iter 788/3944 - loss 0.16488914 - samples/sec: 10.90 - lr: 0.000004 | |
| 2021-01-15 19:26:03,243 epoch 8 - iter 1182/3944 - loss 0.16503533 - samples/sec: 10.83 - lr: 0.000004 | |
| 2021-01-15 19:28:28,171 epoch 8 - iter 1576/3944 - loss 0.16139434 - samples/sec: 10.88 - lr: 0.000003 | |
| 2021-01-15 19:30:53,669 epoch 8 - iter 1970/3944 - loss 0.15723985 - samples/sec: 10.83 - lr: 0.000003 | |
| 2021-01-15 19:33:18,230 epoch 8 - iter 2364/3944 - loss 0.15695920 - samples/sec: 10.90 - lr: 0.000003 | |
| 2021-01-15 19:35:43,271 epoch 8 - iter 2758/3944 - loss 0.15942351 - samples/sec: 10.87 - lr: 0.000003 | |
| 2021-01-15 19:38:07,861 epoch 8 - iter 3152/3944 - loss 0.16047035 - samples/sec: 10.90 - lr: 0.000003 | |
| 2021-01-15 19:40:31,578 epoch 8 - iter 3546/3944 - loss 0.15915561 - samples/sec: 10.97 - lr: 0.000003 | |
| 2021-01-15 19:42:56,291 epoch 8 - iter 3940/3944 - loss 0.15889894 - samples/sec: 10.89 - lr: 0.000003 | |
| 2021-01-15 19:42:57,531 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 19:42:57,531 EPOCH 8 done: loss 0.1591 - lr 0.0000033 | |
| 2021-01-15 19:42:57,531 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 19:42:57,534 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 19:45:22,077 epoch 9 - iter 394/3944 - loss 0.15628960 - samples/sec: 10.90 - lr: 0.000003 | |
| 2021-01-15 19:47:46,787 epoch 9 - iter 788/3944 - loss 0.15383703 - samples/sec: 10.89 - lr: 0.000003 | |
| 2021-01-15 19:50:11,703 epoch 9 - iter 1182/3944 - loss 0.14587839 - samples/sec: 10.88 - lr: 0.000003 | |
| 2021-01-15 19:52:36,604 epoch 9 - iter 1576/3944 - loss 0.14536078 - samples/sec: 10.88 - lr: 0.000003 | |
| 2021-01-15 19:55:01,857 epoch 9 - iter 1970/3944 - loss 0.14842223 - samples/sec: 10.85 - lr: 0.000003 | |
| 2021-01-15 19:57:26,976 epoch 9 - iter 2364/3944 - loss 0.14781136 - samples/sec: 10.86 - lr: 0.000003 | |
| 2021-01-15 19:59:52,570 epoch 9 - iter 2758/3944 - loss 0.14980740 - samples/sec: 10.83 - lr: 0.000003 | |
| 2021-01-15 20:02:16,766 epoch 9 - iter 3152/3944 - loss 0.15147019 - samples/sec: 10.93 - lr: 0.000003 | |
| 2021-01-15 20:04:41,587 epoch 9 - iter 3546/3944 - loss 0.14992780 - samples/sec: 10.88 - lr: 0.000003 | |
| 2021-01-15 20:07:07,065 epoch 9 - iter 3940/3944 - loss 0.14688711 - samples/sec: 10.83 - lr: 0.000003 | |
| 2021-01-15 20:07:08,315 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 20:07:08,315 EPOCH 9 done: loss 0.1469 - lr 0.0000029 | |
| 2021-01-15 20:07:08,315 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 20:07:08,318 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 20:09:33,307 epoch 10 - iter 394/3944 - loss 0.15646665 - samples/sec: 10.87 - lr: 0.000003 | |
| 2021-01-15 20:11:57,958 epoch 10 - iter 788/3944 - loss 0.15117971 - samples/sec: 10.90 - lr: 0.000003 | |
| 2021-01-15 20:14:23,257 epoch 10 - iter 1182/3944 - loss 0.15319049 - samples/sec: 10.85 - lr: 0.000003 | |
| 2021-01-15 20:16:47,405 epoch 10 - iter 1576/3944 - loss 0.14632406 - samples/sec: 10.93 - lr: 0.000003 | |
| 2021-01-15 20:19:13,077 epoch 10 - iter 1970/3944 - loss 0.14880268 - samples/sec: 10.82 - lr: 0.000003 | |
| 2021-01-15 20:21:37,974 epoch 10 - iter 2364/3944 - loss 0.14738769 - samples/sec: 10.88 - lr: 0.000003 | |
| 2021-01-15 20:24:02,312 epoch 10 - iter 2758/3944 - loss 0.14992138 - samples/sec: 10.92 - lr: 0.000003 | |
| 2021-01-15 20:26:26,416 epoch 10 - iter 3152/3944 - loss 0.14923992 - samples/sec: 10.94 - lr: 0.000003 | |
| 2021-01-15 20:28:50,624 epoch 10 - iter 3546/3944 - loss 0.14988541 - samples/sec: 10.93 - lr: 0.000003 | |
| 2021-01-15 20:31:15,232 epoch 10 - iter 3940/3944 - loss 0.14923823 - samples/sec: 10.90 - lr: 0.000003 | |
| 2021-01-15 20:31:16,444 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 20:31:16,445 EPOCH 10 done: loss 0.1492 - lr 0.0000025 | |
| 2021-01-15 20:31:16,445 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 20:31:16,447 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 20:33:41,402 epoch 11 - iter 394/3944 - loss 0.16146740 - samples/sec: 10.87 - lr: 0.000002 | |
| 2021-01-15 20:36:05,837 epoch 11 - iter 788/3944 - loss 0.16349808 - samples/sec: 10.91 - lr: 0.000002 | |
| 2021-01-15 20:38:30,901 epoch 11 - iter 1182/3944 - loss 0.15115769 - samples/sec: 10.87 - lr: 0.000002 | |
| 2021-01-15 20:40:55,438 epoch 11 - iter 1576/3944 - loss 0.14705117 - samples/sec: 10.90 - lr: 0.000002 | |
| 2021-01-15 20:43:20,378 epoch 11 - iter 1970/3944 - loss 0.14991591 - samples/sec: 10.87 - lr: 0.000002 | |
| 2021-01-15 20:45:45,151 epoch 11 - iter 2364/3944 - loss 0.15439655 - samples/sec: 10.89 - lr: 0.000002 | |
| 2021-01-15 20:48:09,941 epoch 11 - iter 2758/3944 - loss 0.15580945 - samples/sec: 10.89 - lr: 0.000002 | |
| 2021-01-15 20:50:34,492 epoch 11 - iter 3152/3944 - loss 0.15253824 - samples/sec: 10.90 - lr: 0.000002 | |
| 2021-01-15 20:52:58,700 epoch 11 - iter 3546/3944 - loss 0.15092320 - samples/sec: 10.93 - lr: 0.000002 | |
| 2021-01-15 20:55:23,174 epoch 11 - iter 3940/3944 - loss 0.15157769 - samples/sec: 10.91 - lr: 0.000002 | |
| 2021-01-15 20:55:24,418 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 20:55:24,418 EPOCH 11 done: loss 0.1515 - lr 0.0000021 | |
| 2021-01-15 20:55:24,418 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 20:55:24,421 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 20:57:49,024 epoch 12 - iter 394/3944 - loss 0.13353775 - samples/sec: 10.90 - lr: 0.000002 | |
| 2021-01-15 21:00:13,363 epoch 12 - iter 788/3944 - loss 0.12481125 - samples/sec: 10.92 - lr: 0.000002 | |
| 2021-01-15 21:02:37,921 epoch 12 - iter 1182/3944 - loss 0.13012621 - samples/sec: 10.90 - lr: 0.000002 | |
| 2021-01-15 21:05:02,587 epoch 12 - iter 1576/3944 - loss 0.13179293 - samples/sec: 10.90 - lr: 0.000002 | |
| 2021-01-15 21:07:27,496 epoch 12 - iter 1970/3944 - loss 0.13504151 - samples/sec: 10.88 - lr: 0.000002 | |
| 2021-01-15 21:09:52,384 epoch 12 - iter 2364/3944 - loss 0.13639646 - samples/sec: 10.88 - lr: 0.000002 | |
| 2021-01-15 21:12:16,819 epoch 12 - iter 2758/3944 - loss 0.13538659 - samples/sec: 10.91 - lr: 0.000002 | |
| 2021-01-15 21:14:41,429 epoch 12 - iter 3152/3944 - loss 0.13401163 - samples/sec: 10.90 - lr: 0.000002 | |
| 2021-01-15 21:17:06,129 epoch 12 - iter 3546/3944 - loss 0.13558124 - samples/sec: 10.89 - lr: 0.000002 | |
| 2021-01-15 21:19:30,783 epoch 12 - iter 3940/3944 - loss 0.13632296 - samples/sec: 10.90 - lr: 0.000002 | |
| 2021-01-15 21:19:32,074 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 21:19:32,075 EPOCH 12 done: loss 0.1365 - lr 0.0000017 | |
| 2021-01-15 21:19:32,075 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 21:19:32,086 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 21:21:56,456 epoch 13 - iter 394/3944 - loss 0.13665988 - samples/sec: 10.92 - lr: 0.000002 | |
| 2021-01-15 21:24:21,213 epoch 13 - iter 788/3944 - loss 0.13434678 - samples/sec: 10.89 - lr: 0.000002 | |
| 2021-01-15 21:26:45,716 epoch 13 - iter 1182/3944 - loss 0.14362465 - samples/sec: 10.91 - lr: 0.000002 | |
| 2021-01-15 21:29:10,027 epoch 13 - iter 1576/3944 - loss 0.14463862 - samples/sec: 10.92 - lr: 0.000002 | |
| 2021-01-15 21:31:35,804 epoch 13 - iter 1970/3944 - loss 0.14445941 - samples/sec: 10.81 - lr: 0.000002 | |
| 2021-01-15 21:34:02,830 epoch 13 - iter 2364/3944 - loss 0.14383136 - samples/sec: 10.72 - lr: 0.000002 | |
| 2021-01-15 21:36:29,998 epoch 13 - iter 2758/3944 - loss 0.14458719 - samples/sec: 10.71 - lr: 0.000001 | |
| 2021-01-15 21:38:58,765 epoch 13 - iter 3152/3944 - loss 0.14583862 - samples/sec: 10.59 - lr: 0.000001 | |
| 2021-01-15 21:41:27,066 epoch 13 - iter 3546/3944 - loss 0.14570568 - samples/sec: 10.63 - lr: 0.000001 | |
| 2021-01-15 21:43:53,640 epoch 13 - iter 3940/3944 - loss 0.14616666 - samples/sec: 10.75 - lr: 0.000001 | |
| 2021-01-15 21:43:54,933 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 21:43:54,933 EPOCH 13 done: loss 0.1461 - lr 0.0000014 | |
| 2021-01-15 21:43:54,933 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 21:43:54,953 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 21:46:22,842 epoch 14 - iter 394/3944 - loss 0.12543846 - samples/sec: 10.66 - lr: 0.000001 | |
| 2021-01-15 21:48:49,756 epoch 14 - iter 788/3944 - loss 0.12854973 - samples/sec: 10.73 - lr: 0.000001 | |
| 2021-01-15 21:51:16,782 epoch 14 - iter 1182/3944 - loss 0.12800828 - samples/sec: 10.72 - lr: 0.000001 | |
| 2021-01-15 21:53:43,875 epoch 14 - iter 1576/3944 - loss 0.13018865 - samples/sec: 10.72 - lr: 0.000001 | |
| 2021-01-15 21:56:11,947 epoch 14 - iter 1970/3944 - loss 0.13230140 - samples/sec: 10.64 - lr: 0.000001 | |
| 2021-01-15 21:58:40,070 epoch 14 - iter 2364/3944 - loss 0.13276864 - samples/sec: 10.64 - lr: 0.000001 | |
| 2021-01-15 22:01:07,197 epoch 14 - iter 2758/3944 - loss 0.13188423 - samples/sec: 10.71 - lr: 0.000001 | |
| 2021-01-15 22:03:33,892 epoch 14 - iter 3152/3944 - loss 0.13622326 - samples/sec: 10.74 - lr: 0.000001 | |
| 2021-01-15 22:06:01,226 epoch 14 - iter 3546/3944 - loss 0.13623591 - samples/sec: 10.70 - lr: 0.000001 | |
| 2021-01-15 22:08:29,247 epoch 14 - iter 3940/3944 - loss 0.13681664 - samples/sec: 10.65 - lr: 0.000001 | |
| 2021-01-15 22:08:30,571 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 22:08:30,571 EPOCH 14 done: loss 0.1367 - lr 0.0000010 | |
| 2021-01-15 22:08:30,571 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 22:08:30,619 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 22:10:58,784 epoch 15 - iter 394/3944 - loss 0.14687040 - samples/sec: 10.64 - lr: 0.000001 | |
| 2021-01-15 22:13:25,824 epoch 15 - iter 788/3944 - loss 0.13773561 - samples/sec: 10.72 - lr: 0.000001 | |
| 2021-01-15 22:15:52,774 epoch 15 - iter 1182/3944 - loss 0.13724811 - samples/sec: 10.73 - lr: 0.000001 | |
| 2021-01-15 22:18:19,309 epoch 15 - iter 1576/3944 - loss 0.14105250 - samples/sec: 10.76 - lr: 0.000001 | |
| 2021-01-15 22:20:46,418 epoch 15 - iter 1970/3944 - loss 0.13929364 - samples/sec: 10.71 - lr: 0.000001 | |
| 2021-01-15 22:23:12,930 epoch 15 - iter 2364/3944 - loss 0.13891907 - samples/sec: 10.76 - lr: 0.000001 | |
| 2021-01-15 22:25:40,051 epoch 15 - iter 2758/3944 - loss 0.13941754 - samples/sec: 10.71 - lr: 0.000001 | |
| 2021-01-15 22:28:06,583 epoch 15 - iter 3152/3944 - loss 0.14071295 - samples/sec: 10.76 - lr: 0.000001 | |
| 2021-01-15 22:30:32,954 epoch 15 - iter 3546/3944 - loss 0.13981342 - samples/sec: 10.77 - lr: 0.000001 | |
| 2021-01-15 22:33:00,397 epoch 15 - iter 3940/3944 - loss 0.13880390 - samples/sec: 10.69 - lr: 0.000001 | |
| 2021-01-15 22:33:01,714 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 22:33:01,715 EPOCH 15 done: loss 0.1387 - lr 0.0000007 | |
| 2021-01-15 22:33:01,715 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 22:33:01,718 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 22:35:29,035 epoch 16 - iter 394/3944 - loss 0.14291727 - samples/sec: 10.70 - lr: 0.000001 | |
| 2021-01-15 22:37:56,417 epoch 16 - iter 788/3944 - loss 0.13149588 - samples/sec: 10.69 - lr: 0.000001 | |
| 2021-01-15 22:40:23,990 epoch 16 - iter 1182/3944 - loss 0.13203036 - samples/sec: 10.68 - lr: 0.000001 | |
| 2021-01-15 22:42:51,538 epoch 16 - iter 1576/3944 - loss 0.13134927 - samples/sec: 10.68 - lr: 0.000001 | |
| 2021-01-15 22:45:19,113 epoch 16 - iter 1970/3944 - loss 0.13179903 - samples/sec: 10.68 - lr: 0.000001 | |
| 2021-01-15 22:47:46,156 epoch 16 - iter 2364/3944 - loss 0.13354076 - samples/sec: 10.72 - lr: 0.000001 | |
| 2021-01-15 22:50:13,300 epoch 16 - iter 2758/3944 - loss 0.13476940 - samples/sec: 10.71 - lr: 0.000001 | |
| 2021-01-15 22:52:38,377 epoch 16 - iter 3152/3944 - loss 0.13497255 - samples/sec: 10.86 - lr: 0.000001 | |
| 2021-01-15 22:55:03,400 epoch 16 - iter 3546/3944 - loss 0.13634147 - samples/sec: 10.87 - lr: 0.000001 | |
| 2021-01-15 22:57:27,892 epoch 16 - iter 3940/3944 - loss 0.13727031 - samples/sec: 10.91 - lr: 0.000000 | |
| 2021-01-15 22:57:29,178 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 22:57:29,178 EPOCH 16 done: loss 0.1376 - lr 0.0000005 | |
| 2021-01-15 22:57:29,178 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 22:57:29,181 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 22:59:53,548 epoch 17 - iter 394/3944 - loss 0.14524632 - samples/sec: 10.92 - lr: 0.000000 | |
| 2021-01-15 23:02:18,357 epoch 17 - iter 788/3944 - loss 0.14652155 - samples/sec: 10.88 - lr: 0.000000 | |
| 2021-01-15 23:04:43,610 epoch 17 - iter 1182/3944 - loss 0.13884438 - samples/sec: 10.85 - lr: 0.000000 | |
| 2021-01-15 23:07:08,806 epoch 17 - iter 1576/3944 - loss 0.13549453 - samples/sec: 10.86 - lr: 0.000000 | |
| 2021-01-15 23:09:34,317 epoch 17 - iter 1970/3944 - loss 0.13560330 - samples/sec: 10.83 - lr: 0.000000 | |
| 2021-01-15 23:11:59,595 epoch 17 - iter 2364/3944 - loss 0.13972037 - samples/sec: 10.85 - lr: 0.000000 | |
| 2021-01-15 23:14:24,656 epoch 17 - iter 2758/3944 - loss 0.14040167 - samples/sec: 10.87 - lr: 0.000000 | |
| 2021-01-15 23:16:49,375 epoch 17 - iter 3152/3944 - loss 0.13946642 - samples/sec: 10.89 - lr: 0.000000 | |
| 2021-01-15 23:19:15,069 epoch 17 - iter 3546/3944 - loss 0.13849877 - samples/sec: 10.82 - lr: 0.000000 | |
| 2021-01-15 23:21:40,239 epoch 17 - iter 3940/3944 - loss 0.13743522 - samples/sec: 10.86 - lr: 0.000000 | |
| 2021-01-15 23:21:41,530 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 23:21:41,530 EPOCH 17 done: loss 0.1373 - lr 0.0000003 | |
| 2021-01-15 23:21:41,530 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 23:21:41,533 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 23:24:07,941 epoch 18 - iter 394/3944 - loss 0.13214318 - samples/sec: 10.77 - lr: 0.000000 | |
| 2021-01-15 23:26:34,009 epoch 18 - iter 788/3944 - loss 0.14259440 - samples/sec: 10.79 - lr: 0.000000 | |
| 2021-01-15 23:29:00,116 epoch 18 - iter 1182/3944 - loss 0.13753739 - samples/sec: 10.79 - lr: 0.000000 | |
| 2021-01-15 23:31:25,087 epoch 18 - iter 1576/3944 - loss 0.13957844 - samples/sec: 10.87 - lr: 0.000000 | |
| 2021-01-15 23:33:50,076 epoch 18 - iter 1970/3944 - loss 0.13743370 - samples/sec: 10.87 - lr: 0.000000 | |
| 2021-01-15 23:36:14,776 epoch 18 - iter 2364/3944 - loss 0.13970779 - samples/sec: 10.89 - lr: 0.000000 | |
| 2021-01-15 23:38:38,473 epoch 18 - iter 2758/3944 - loss 0.13932537 - samples/sec: 10.97 - lr: 0.000000 | |
| 2021-01-15 23:41:03,249 epoch 18 - iter 3152/3944 - loss 0.13745278 - samples/sec: 10.89 - lr: 0.000000 | |
| 2021-01-15 23:43:28,499 epoch 18 - iter 3546/3944 - loss 0.13924606 - samples/sec: 10.85 - lr: 0.000000 | |
| 2021-01-15 23:45:53,779 epoch 18 - iter 3940/3944 - loss 0.13920658 - samples/sec: 10.85 - lr: 0.000000 | |
| 2021-01-15 23:45:55,039 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 23:45:55,040 EPOCH 18 done: loss 0.1400 - lr 0.0000001 | |
| 2021-01-15 23:45:55,040 BAD EPOCHS (no improvement): 4 | |
| 2021-01-15 23:45:55,060 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-15 23:48:19,848 epoch 19 - iter 394/3944 - loss 0.12011491 - samples/sec: 10.89 - lr: 0.000000 | |
| 2021-01-15 23:50:45,410 epoch 19 - iter 788/3944 - loss 0.12712191 - samples/sec: 10.83 - lr: 0.000000 | |
| 2021-01-15 23:53:10,309 epoch 19 - iter 1182/3944 - loss 0.12601271 - samples/sec: 10.88 - lr: 0.000000 | |
| 2021-01-15 23:55:35,025 epoch 19 - iter 1576/3944 - loss 0.12838937 - samples/sec: 10.89 - lr: 0.000000 | |
| 2021-01-15 23:57:59,862 epoch 19 - iter 1970/3944 - loss 0.13018004 - samples/sec: 10.88 - lr: 0.000000 | |
| 2021-01-16 00:00:24,890 epoch 19 - iter 2364/3944 - loss 0.12867846 - samples/sec: 10.87 - lr: 0.000000 | |
| 2021-01-16 00:02:49,627 epoch 19 - iter 2758/3944 - loss 0.12932283 - samples/sec: 10.89 - lr: 0.000000 | |
| 2021-01-16 00:05:14,400 epoch 19 - iter 3152/3944 - loss 0.12859496 - samples/sec: 10.89 - lr: 0.000000 | |
| 2021-01-16 00:07:39,476 epoch 19 - iter 3546/3944 - loss 0.12980219 - samples/sec: 10.86 - lr: 0.000000 | |
| 2021-01-16 00:10:04,796 epoch 19 - iter 3940/3944 - loss 0.13157911 - samples/sec: 10.85 - lr: 0.000000 | |
| 2021-01-16 00:10:06,033 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-16 00:10:06,033 EPOCH 19 done: loss 0.1316 - lr 0.0000000 | |
| 2021-01-16 00:10:06,033 BAD EPOCHS (no improvement): 4 | |
| 2021-01-16 00:10:06,036 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-16 00:12:31,453 epoch 20 - iter 394/3944 - loss 0.12043092 - samples/sec: 10.84 - lr: 0.000000 | |
| 2021-01-16 00:14:56,680 epoch 20 - iter 788/3944 - loss 0.13192874 - samples/sec: 10.85 - lr: 0.000000 | |
| 2021-01-16 00:17:21,816 epoch 20 - iter 1182/3944 - loss 0.13095020 - samples/sec: 10.86 - lr: 0.000000 | |
| 2021-01-16 00:19:46,815 epoch 20 - iter 1576/3944 - loss 0.13423819 - samples/sec: 10.87 - lr: 0.000000 | |
| 2021-01-16 00:22:12,079 epoch 20 - iter 1970/3944 - loss 0.13458985 - samples/sec: 10.85 - lr: 0.000000 | |
| 2021-01-16 00:24:37,900 epoch 20 - iter 2364/3944 - loss 0.13241959 - samples/sec: 10.81 - lr: 0.000000 | |
| 2021-01-16 00:27:03,059 epoch 20 - iter 2758/3944 - loss 0.13235752 - samples/sec: 10.86 - lr: 0.000000 | |
| 2021-01-16 00:29:28,845 epoch 20 - iter 3152/3944 - loss 0.13390899 - samples/sec: 10.81 - lr: 0.000000 | |
| 2021-01-16 00:31:54,866 epoch 20 - iter 3546/3944 - loss 0.13467390 - samples/sec: 10.79 - lr: 0.000000 | |
| 2021-01-16 00:34:19,750 epoch 20 - iter 3940/3944 - loss 0.13514658 - samples/sec: 10.88 - lr: 0.000000 | |
| 2021-01-16 00:34:21,013 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-16 00:34:21,013 EPOCH 20 done: loss 0.1353 - lr 0.0000000 | |
| 2021-01-16 00:34:21,013 BAD EPOCHS (no improvement): 4 | |
| 2021-01-16 00:34:59,015 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-16 00:34:59,015 Testing using best model ... | |
| 2021-01-16 00:36:54,780 0.9319 0.9145 0.9231 | |
| 2021-01-16 00:36:54,780 | |
| Results: | |
| - F1-score (micro) 0.9231 | |
| - F1-score (macro) 0.8691 | |
| By class: | |
| LOC tp: 981 - fp: 62 - fn: 70 - precision: 0.9406 - recall: 0.9334 - f1-score: 0.9370 | |
| MISC tp: 128 - fp: 26 - fn: 78 - precision: 0.8312 - recall: 0.6214 - f1-score: 0.7111 | |
| ORG tp: 497 - fp: 87 - fn: 87 - precision: 0.8510 - recall: 0.8510 - f1-score: 0.8510 | |
| PER tp: 1184 - fp: 29 - fn: 26 - precision: 0.9761 - recall: 0.9785 - f1-score: 0.9773 | |
| 2021-01-16 00:36:54,780 ---------------------------------------------------------------------------------------------------- | |