| 2021-01-20 22:30:34,817 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-20 22:30:34,820 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 | |
| )" | |
| 2021-01-20 22:30:34,821 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-20 22:30:34,821 Corpus: "Corpus: 16093 train + 2969 dev + 5314 test sentences" | |
| 2021-01-20 22:30:34,821 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-20 22:30:34,821 Parameters: | |
| 2021-01-20 22:30:34,821 - learning_rate: "5e-06" | |
| 2021-01-20 22:30:34,821 - mini_batch_size: "4" | |
| 2021-01-20 22:30:34,821 - patience: "3" | |
| 2021-01-20 22:30:34,821 - anneal_factor: "0.5" | |
| 2021-01-20 22:30:34,822 - max_epochs: "20" | |
| 2021-01-20 22:30:34,822 - shuffle: "True" | |
| 2021-01-20 22:30:34,822 - train_with_dev: "True" | |
| 2021-01-20 22:30:34,822 - batch_growth_annealing: "False" | |
| 2021-01-20 22:30:34,822 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-20 22:30:34,822 Model training base path: "resources/contextdrop/flert-nl-ft+dev-xlm-roberta-large-context+drop-64-True-127" | |
| 2021-01-20 22:30:34,822 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-20 22:30:34,822 Device: cuda:0 | |
| 2021-01-20 22:30:34,822 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-20 22:30:34,822 Embeddings storage mode: none | |
| 2021-01-20 22:30:34,833 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-20 22:34:24,138 epoch 1 - iter 476/4766 - loss 0.75007446 - samples/sec: 8.30 - lr: 0.000005 | |
| 2021-01-20 22:38:11,813 epoch 1 - iter 952/4766 - loss 0.55138470 - samples/sec: 8.36 - lr: 0.000005 | |
| 2021-01-20 22:42:03,548 epoch 1 - iter 1428/4766 - loss 0.46882800 - samples/sec: 8.22 - lr: 0.000005 | |
| 2021-01-20 22:45:56,496 epoch 1 - iter 1904/4766 - loss 0.42568348 - samples/sec: 8.17 - lr: 0.000005 | |
| 2021-01-20 22:49:48,705 epoch 1 - iter 2380/4766 - loss 0.40460601 - samples/sec: 8.20 - lr: 0.000005 | |
| 2021-01-20 22:53:40,511 epoch 1 - iter 2856/4766 - loss 0.38479376 - samples/sec: 8.21 - lr: 0.000005 | |
| 2021-01-20 22:57:31,693 epoch 1 - iter 3332/4766 - loss 0.36783532 - samples/sec: 8.24 - lr: 0.000005 | |
| 2021-01-20 23:01:24,894 epoch 1 - iter 3808/4766 - loss 0.35297261 - samples/sec: 8.17 - lr: 0.000005 | |
| 2021-01-20 23:05:16,842 epoch 1 - iter 4284/4766 - loss 0.33562353 - samples/sec: 8.21 - lr: 0.000005 | |
| 2021-01-20 23:09:08,356 epoch 1 - iter 4760/4766 - loss 0.32624764 - samples/sec: 8.22 - lr: 0.000005 | |
| 2021-01-20 23:09:11,043 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-20 23:09:11,044 EPOCH 1 done: loss 0.3260 - lr 0.0000050 | |
| 2021-01-20 23:09:11,044 BAD EPOCHS (no improvement): 4 | |
| 2021-01-20 23:09:11,056 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-20 23:13:02,174 epoch 2 - iter 476/4766 - loss 0.19592687 - samples/sec: 8.24 - lr: 0.000005 | |
| 2021-01-20 23:16:52,896 epoch 2 - iter 952/4766 - loss 0.19343522 - samples/sec: 8.25 - lr: 0.000005 | |
| 2021-01-20 23:20:44,314 epoch 2 - iter 1428/4766 - loss 0.19096819 - samples/sec: 8.23 - lr: 0.000005 | |
| 2021-01-20 23:24:34,798 epoch 2 - iter 1904/4766 - loss 0.20419720 - samples/sec: 8.26 - lr: 0.000005 | |
| 2021-01-20 23:28:25,592 epoch 2 - iter 2380/4766 - loss 0.20562715 - samples/sec: 8.25 - lr: 0.000005 | |
| 2021-01-20 23:32:18,034 epoch 2 - iter 2856/4766 - loss 0.21479885 - samples/sec: 8.19 - lr: 0.000005 | |
| 2021-01-20 23:36:11,088 epoch 2 - iter 3332/4766 - loss 0.22119955 - samples/sec: 8.17 - lr: 0.000005 | |
| 2021-01-20 23:39:57,520 epoch 2 - iter 3808/4766 - loss 0.22084426 - samples/sec: 8.41 - lr: 0.000005 | |
| 2021-01-20 23:43:40,262 epoch 2 - iter 4284/4766 - loss 0.22666022 - samples/sec: 8.55 - lr: 0.000005 | |
| 2021-01-20 23:47:22,340 epoch 2 - iter 4760/4766 - loss 0.22898245 - samples/sec: 8.57 - lr: 0.000005 | |
| 2021-01-20 23:47:24,928 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-20 23:47:24,928 EPOCH 2 done: loss 0.2291 - lr 0.0000049 | |
| 2021-01-20 23:47:24,928 BAD EPOCHS (no improvement): 4 | |
| 2021-01-20 23:47:24,932 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-20 23:51:06,331 epoch 3 - iter 476/4766 - loss 0.17300695 - samples/sec: 8.60 - lr: 0.000005 | |
| 2021-01-20 23:54:48,800 epoch 3 - iter 952/4766 - loss 0.18720678 - samples/sec: 8.56 - lr: 0.000005 | |
| 2021-01-20 23:58:33,629 epoch 3 - iter 1428/4766 - loss 0.18315013 - samples/sec: 8.47 - lr: 0.000005 | |
| 2021-01-21 00:02:15,888 epoch 3 - iter 1904/4766 - loss 0.18674032 - samples/sec: 8.57 - lr: 0.000005 | |
| 2021-01-21 00:05:57,520 epoch 3 - iter 2380/4766 - loss 0.19216686 - samples/sec: 8.59 - lr: 0.000005 | |
| 2021-01-21 00:09:39,305 epoch 3 - iter 2856/4766 - loss 0.19094677 - samples/sec: 8.59 - lr: 0.000005 | |
| 2021-01-21 00:13:20,604 epoch 3 - iter 3332/4766 - loss 0.18956430 - samples/sec: 8.60 - lr: 0.000005 | |
| 2021-01-21 00:17:01,961 epoch 3 - iter 3808/4766 - loss 0.18552889 - samples/sec: 8.60 - lr: 0.000005 | |
| 2021-01-21 00:20:43,755 epoch 3 - iter 4284/4766 - loss 0.18237621 - samples/sec: 8.59 - lr: 0.000005 | |
| 2021-01-21 00:24:26,424 epoch 3 - iter 4760/4766 - loss 0.18548491 - samples/sec: 8.55 - lr: 0.000005 | |
| 2021-01-21 00:24:29,094 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 00:24:29,094 EPOCH 3 done: loss 0.1856 - lr 0.0000047 | |
| 2021-01-21 00:24:29,094 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 00:24:29,113 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 00:28:10,733 epoch 4 - iter 476/4766 - loss 0.16395309 - samples/sec: 8.59 - lr: 0.000005 | |
| 2021-01-21 00:31:51,536 epoch 4 - iter 952/4766 - loss 0.15725064 - samples/sec: 8.62 - lr: 0.000005 | |
| 2021-01-21 00:35:32,411 epoch 4 - iter 1428/4766 - loss 0.15046027 - samples/sec: 8.62 - lr: 0.000005 | |
| 2021-01-21 00:39:11,999 epoch 4 - iter 1904/4766 - loss 0.15211000 - samples/sec: 8.67 - lr: 0.000005 | |
| 2021-01-21 00:42:52,983 epoch 4 - iter 2380/4766 - loss 0.15810432 - samples/sec: 8.62 - lr: 0.000005 | |
| 2021-01-21 00:46:35,874 epoch 4 - iter 2856/4766 - loss 0.15986602 - samples/sec: 8.54 - lr: 0.000005 | |
| 2021-01-21 00:50:17,362 epoch 4 - iter 3332/4766 - loss 0.15994249 - samples/sec: 8.60 - lr: 0.000005 | |
| 2021-01-21 00:53:58,810 epoch 4 - iter 3808/4766 - loss 0.15891707 - samples/sec: 8.60 - lr: 0.000005 | |
| 2021-01-21 00:57:39,682 epoch 4 - iter 4284/4766 - loss 0.16493451 - samples/sec: 8.62 - lr: 0.000005 | |
| 2021-01-21 01:01:20,887 epoch 4 - iter 4760/4766 - loss 0.16578159 - samples/sec: 8.61 - lr: 0.000005 | |
| 2021-01-21 01:01:23,546 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 01:01:23,546 EPOCH 4 done: loss 0.1656 - lr 0.0000045 | |
| 2021-01-21 01:01:23,546 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 01:01:23,549 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 01:05:05,137 epoch 5 - iter 476/4766 - loss 0.16713775 - samples/sec: 8.59 - lr: 0.000004 | |
| 2021-01-21 01:08:46,452 epoch 5 - iter 952/4766 - loss 0.15990526 - samples/sec: 8.60 - lr: 0.000004 | |
| 2021-01-21 01:12:28,191 epoch 5 - iter 1428/4766 - loss 0.16156578 - samples/sec: 8.59 - lr: 0.000004 | |
| 2021-01-21 01:16:08,457 epoch 5 - iter 1904/4766 - loss 0.16763724 - samples/sec: 8.64 - lr: 0.000004 | |
| 2021-01-21 01:19:50,350 epoch 5 - iter 2380/4766 - loss 0.16378794 - samples/sec: 8.58 - lr: 0.000004 | |
| 2021-01-21 01:23:30,578 epoch 5 - iter 2856/4766 - loss 0.16849384 - samples/sec: 8.65 - lr: 0.000004 | |
| 2021-01-21 01:27:10,395 epoch 5 - iter 3332/4766 - loss 0.16382910 - samples/sec: 8.66 - lr: 0.000004 | |
| 2021-01-21 01:30:51,552 epoch 5 - iter 3808/4766 - loss 0.16654785 - samples/sec: 8.61 - lr: 0.000004 | |
| 2021-01-21 01:34:33,151 epoch 5 - iter 4284/4766 - loss 0.16617839 - samples/sec: 8.59 - lr: 0.000004 | |
| 2021-01-21 01:38:13,465 epoch 5 - iter 4760/4766 - loss 0.16489933 - samples/sec: 8.64 - lr: 0.000004 | |
| 2021-01-21 01:38:16,065 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 01:38:16,065 EPOCH 5 done: loss 0.1648 - lr 0.0000043 | |
| 2021-01-21 01:38:16,066 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 01:38:16,069 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 01:41:56,751 epoch 6 - iter 476/4766 - loss 0.15331536 - samples/sec: 8.63 - lr: 0.000004 | |
| 2021-01-21 01:45:37,683 epoch 6 - iter 952/4766 - loss 0.16628115 - samples/sec: 8.62 - lr: 0.000004 | |
| 2021-01-21 01:49:18,657 epoch 6 - iter 1428/4766 - loss 0.16559479 - samples/sec: 8.62 - lr: 0.000004 | |
| 2021-01-21 01:52:59,337 epoch 6 - iter 1904/4766 - loss 0.16505749 - samples/sec: 8.63 - lr: 0.000004 | |
| 2021-01-21 01:56:41,398 epoch 6 - iter 2380/4766 - loss 0.16408360 - samples/sec: 8.57 - lr: 0.000004 | |
| 2021-01-21 02:00:22,782 epoch 6 - iter 2856/4766 - loss 0.16367926 - samples/sec: 8.60 - lr: 0.000004 | |
| 2021-01-21 02:04:04,491 epoch 6 - iter 3332/4766 - loss 0.16323212 - samples/sec: 8.59 - lr: 0.000004 | |
| 2021-01-21 02:07:46,417 epoch 6 - iter 3808/4766 - loss 0.16476110 - samples/sec: 8.58 - lr: 0.000004 | |
| 2021-01-21 02:11:27,402 epoch 6 - iter 4284/4766 - loss 0.16556307 - samples/sec: 8.62 - lr: 0.000004 | |
| 2021-01-21 02:15:08,877 epoch 6 - iter 4760/4766 - loss 0.16431570 - samples/sec: 8.60 - lr: 0.000004 | |
| 2021-01-21 02:15:11,479 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 02:15:11,480 EPOCH 6 done: loss 0.1648 - lr 0.0000040 | |
| 2021-01-21 02:15:11,480 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 02:15:11,483 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 02:18:51,563 epoch 7 - iter 476/4766 - loss 0.16677021 - samples/sec: 8.65 - lr: 0.000004 | |
| 2021-01-21 02:22:33,148 epoch 7 - iter 952/4766 - loss 0.15199812 - samples/sec: 8.59 - lr: 0.000004 | |
| 2021-01-21 02:26:14,043 epoch 7 - iter 1428/4766 - loss 0.15998079 - samples/sec: 8.62 - lr: 0.000004 | |
| 2021-01-21 02:29:54,619 epoch 7 - iter 1904/4766 - loss 0.16023978 - samples/sec: 8.63 - lr: 0.000004 | |
| 2021-01-21 02:33:35,634 epoch 7 - iter 2380/4766 - loss 0.15702676 - samples/sec: 8.62 - lr: 0.000004 | |
| 2021-01-21 02:37:16,548 epoch 7 - iter 2856/4766 - loss 0.15350997 - samples/sec: 8.62 - lr: 0.000004 | |
| 2021-01-21 02:40:57,346 epoch 7 - iter 3332/4766 - loss 0.15488921 - samples/sec: 8.62 - lr: 0.000004 | |
| 2021-01-21 02:44:38,614 epoch 7 - iter 3808/4766 - loss 0.15987947 - samples/sec: 8.61 - lr: 0.000004 | |
| 2021-01-21 02:48:20,175 epoch 7 - iter 4284/4766 - loss 0.16276295 - samples/sec: 8.59 - lr: 0.000004 | |
| 2021-01-21 02:52:01,908 epoch 7 - iter 4760/4766 - loss 0.16197284 - samples/sec: 8.59 - lr: 0.000004 | |
| 2021-01-21 02:52:04,547 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 02:52:04,547 EPOCH 7 done: loss 0.1620 - lr 0.0000036 | |
| 2021-01-21 02:52:04,547 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 02:52:04,550 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 02:55:44,290 epoch 8 - iter 476/4766 - loss 0.12739570 - samples/sec: 8.67 - lr: 0.000004 | |
| 2021-01-21 02:59:24,874 epoch 8 - iter 952/4766 - loss 0.13459088 - samples/sec: 8.63 - lr: 0.000004 | |
| 2021-01-21 03:03:05,915 epoch 8 - iter 1428/4766 - loss 0.13249889 - samples/sec: 8.61 - lr: 0.000004 | |
| 2021-01-21 03:07:51,438 epoch 8 - iter 1904/4766 - loss 0.13557002 - samples/sec: 6.67 - lr: 0.000003 | |
| 2021-01-21 03:11:32,960 epoch 8 - iter 2380/4766 - loss 0.13750847 - samples/sec: 8.60 - lr: 0.000003 | |
| 2021-01-21 03:15:15,240 epoch 8 - iter 2856/4766 - loss 0.13920395 - samples/sec: 8.57 - lr: 0.000003 | |
| 2021-01-21 03:18:56,540 epoch 8 - iter 3332/4766 - loss 0.14196834 - samples/sec: 8.60 - lr: 0.000003 | |
| 2021-01-21 03:22:38,133 epoch 8 - iter 3808/4766 - loss 0.14013979 - samples/sec: 8.59 - lr: 0.000003 | |
| 2021-01-21 03:26:20,491 epoch 8 - iter 4284/4766 - loss 0.14057112 - samples/sec: 8.56 - lr: 0.000003 | |
| 2021-01-21 03:30:01,506 epoch 8 - iter 4760/4766 - loss 0.13849626 - samples/sec: 8.62 - lr: 0.000003 | |
| 2021-01-21 03:30:04,136 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 03:30:04,136 EPOCH 8 done: loss 0.1390 - lr 0.0000033 | |
| 2021-01-21 03:30:04,136 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 03:30:04,139 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 03:33:43,789 epoch 9 - iter 476/4766 - loss 0.10898947 - samples/sec: 8.67 - lr: 0.000003 | |
| 2021-01-21 03:37:24,937 epoch 9 - iter 952/4766 - loss 0.13779523 - samples/sec: 8.61 - lr: 0.000003 | |
| 2021-01-21 03:41:06,312 epoch 9 - iter 1428/4766 - loss 0.13999643 - samples/sec: 8.60 - lr: 0.000003 | |
| 2021-01-21 03:44:48,413 epoch 9 - iter 1904/4766 - loss 0.14934964 - samples/sec: 8.57 - lr: 0.000003 | |
| 2021-01-21 03:48:28,888 epoch 9 - iter 2380/4766 - loss 0.14817911 - samples/sec: 8.64 - lr: 0.000003 | |
| 2021-01-21 03:52:09,651 epoch 9 - iter 2856/4766 - loss 0.14990197 - samples/sec: 8.63 - lr: 0.000003 | |
| 2021-01-21 03:55:50,402 epoch 9 - iter 3332/4766 - loss 0.15379190 - samples/sec: 8.63 - lr: 0.000003 | |
| 2021-01-21 03:59:32,243 epoch 9 - iter 3808/4766 - loss 0.15360767 - samples/sec: 8.58 - lr: 0.000003 | |
| 2021-01-21 04:03:12,525 epoch 9 - iter 4284/4766 - loss 0.15584102 - samples/sec: 8.64 - lr: 0.000003 | |
| 2021-01-21 04:06:52,524 epoch 9 - iter 4760/4766 - loss 0.15575696 - samples/sec: 8.66 - lr: 0.000003 | |
| 2021-01-21 04:06:55,162 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 04:06:55,162 EPOCH 9 done: loss 0.1559 - lr 0.0000029 | |
| 2021-01-21 04:06:55,162 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 04:06:55,174 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 04:10:34,900 epoch 10 - iter 476/4766 - loss 0.16271080 - samples/sec: 8.67 - lr: 0.000003 | |
| 2021-01-21 04:14:20,175 epoch 10 - iter 952/4766 - loss 0.16397437 - samples/sec: 8.45 - lr: 0.000003 | |
| 2021-01-21 04:18:06,987 epoch 10 - iter 1428/4766 - loss 0.15725672 - samples/sec: 8.40 - lr: 0.000003 | |
| 2021-01-21 04:21:49,215 epoch 10 - iter 1904/4766 - loss 0.15423771 - samples/sec: 8.57 - lr: 0.000003 | |
| 2021-01-21 04:25:28,895 epoch 10 - iter 2380/4766 - loss 0.15973856 - samples/sec: 8.67 - lr: 0.000003 | |
| 2021-01-21 04:29:23,464 epoch 10 - iter 2856/4766 - loss 0.16022188 - samples/sec: 8.12 - lr: 0.000003 | |
| 2021-01-21 04:33:45,631 epoch 10 - iter 3332/4766 - loss 0.16116028 - samples/sec: 7.26 - lr: 0.000003 | |
| 2021-01-21 04:37:33,764 epoch 10 - iter 3808/4766 - loss 0.16539610 - samples/sec: 8.35 - lr: 0.000003 | |
| 2021-01-21 04:42:13,315 epoch 10 - iter 4284/4766 - loss 0.16546677 - samples/sec: 6.81 - lr: 0.000003 | |
| 2021-01-21 04:45:59,709 epoch 10 - iter 4760/4766 - loss 0.16271866 - samples/sec: 8.41 - lr: 0.000003 | |
| 2021-01-21 04:46:02,392 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 04:46:02,392 EPOCH 10 done: loss 0.1625 - lr 0.0000025 | |
| 2021-01-21 04:46:02,392 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 04:46:02,396 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 04:49:48,063 epoch 11 - iter 476/4766 - loss 0.12302402 - samples/sec: 8.44 - lr: 0.000002 | |
| 2021-01-21 04:53:27,641 epoch 11 - iter 952/4766 - loss 0.14938588 - samples/sec: 8.67 - lr: 0.000002 | |
| 2021-01-21 04:57:17,073 epoch 11 - iter 1428/4766 - loss 0.15249822 - samples/sec: 8.30 - lr: 0.000002 | |
| 2021-01-21 05:01:04,811 epoch 11 - iter 1904/4766 - loss 0.15278022 - samples/sec: 8.36 - lr: 0.000002 | |
| 2021-01-21 05:04:54,048 epoch 11 - iter 2380/4766 - loss 0.14726127 - samples/sec: 8.31 - lr: 0.000002 | |
| 2021-01-21 05:08:43,193 epoch 11 - iter 2856/4766 - loss 0.14789523 - samples/sec: 8.31 - lr: 0.000002 | |
| 2021-01-21 05:13:06,493 epoch 11 - iter 3332/4766 - loss 0.14714088 - samples/sec: 7.23 - lr: 0.000002 | |
| 2021-01-21 05:16:50,965 epoch 11 - iter 3808/4766 - loss 0.14520739 - samples/sec: 8.48 - lr: 0.000002 | |
| 2021-01-21 05:20:39,478 epoch 11 - iter 4284/4766 - loss 0.14887415 - samples/sec: 8.33 - lr: 0.000002 | |
| 2021-01-21 05:24:29,111 epoch 11 - iter 4760/4766 - loss 0.14659288 - samples/sec: 8.29 - lr: 0.000002 | |
| 2021-01-21 05:24:31,802 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 05:24:31,802 EPOCH 11 done: loss 0.1467 - lr 0.0000021 | |
| 2021-01-21 05:24:31,802 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 05:24:31,805 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 05:28:14,475 epoch 12 - iter 476/4766 - loss 0.15315567 - samples/sec: 8.55 - lr: 0.000002 | |
| 2021-01-21 05:31:59,651 epoch 12 - iter 952/4766 - loss 0.16653427 - samples/sec: 8.46 - lr: 0.000002 | |
| 2021-01-21 05:35:41,742 epoch 12 - iter 1428/4766 - loss 0.15943798 - samples/sec: 8.57 - lr: 0.000002 | |
| 2021-01-21 05:39:23,773 epoch 12 - iter 1904/4766 - loss 0.14738183 - samples/sec: 8.58 - lr: 0.000002 | |
| 2021-01-21 05:43:07,737 epoch 12 - iter 2380/4766 - loss 0.14768732 - samples/sec: 8.50 - lr: 0.000002 | |
| 2021-01-21 05:46:50,097 epoch 12 - iter 2856/4766 - loss 0.14579714 - samples/sec: 8.56 - lr: 0.000002 | |
| 2021-01-21 05:50:30,750 epoch 12 - iter 3332/4766 - loss 0.14426661 - samples/sec: 8.63 - lr: 0.000002 | |
| 2021-01-21 05:54:10,533 epoch 12 - iter 3808/4766 - loss 0.14331669 - samples/sec: 8.66 - lr: 0.000002 | |
| 2021-01-21 05:57:51,040 epoch 12 - iter 4284/4766 - loss 0.14558392 - samples/sec: 8.64 - lr: 0.000002 | |
| 2021-01-21 06:01:31,114 epoch 12 - iter 4760/4766 - loss 0.14487869 - samples/sec: 8.65 - lr: 0.000002 | |
| 2021-01-21 06:01:33,698 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 06:01:33,699 EPOCH 12 done: loss 0.1448 - lr 0.0000017 | |
| 2021-01-21 06:01:33,699 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 06:01:33,728 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 06:05:13,916 epoch 13 - iter 476/4766 - loss 0.14655107 - samples/sec: 8.65 - lr: 0.000002 | |
| 2021-01-21 06:09:00,692 epoch 13 - iter 952/4766 - loss 0.15434704 - samples/sec: 8.40 - lr: 0.000002 | |
| 2021-01-21 06:13:01,021 epoch 13 - iter 1428/4766 - loss 0.14097797 - samples/sec: 7.92 - lr: 0.000002 | |
| 2021-01-21 06:16:53,666 epoch 13 - iter 1904/4766 - loss 0.14277714 - samples/sec: 8.18 - lr: 0.000002 | |
| 2021-01-21 06:20:42,859 epoch 13 - iter 2380/4766 - loss 0.14354307 - samples/sec: 8.31 - lr: 0.000002 | |
| 2021-01-21 06:24:31,146 epoch 13 - iter 2856/4766 - loss 0.14679997 - samples/sec: 8.34 - lr: 0.000002 | |
| 2021-01-21 06:28:19,832 epoch 13 - iter 3332/4766 - loss 0.14780579 - samples/sec: 8.33 - lr: 0.000001 | |
| 2021-01-21 06:32:08,563 epoch 13 - iter 3808/4766 - loss 0.14877294 - samples/sec: 8.32 - lr: 0.000001 | |
| 2021-01-21 06:35:55,834 epoch 13 - iter 4284/4766 - loss 0.14803883 - samples/sec: 8.38 - lr: 0.000001 | |
| 2021-01-21 06:39:44,884 epoch 13 - iter 4760/4766 - loss 0.15072743 - samples/sec: 8.31 - lr: 0.000001 | |
| 2021-01-21 06:39:47,605 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 06:39:47,605 EPOCH 13 done: loss 0.1512 - lr 0.0000014 | |
| 2021-01-21 06:39:47,605 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 06:39:47,610 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 06:43:34,894 epoch 14 - iter 476/4766 - loss 0.11684375 - samples/sec: 8.38 - lr: 0.000001 | |
| 2021-01-21 06:47:22,075 epoch 14 - iter 952/4766 - loss 0.13685666 - samples/sec: 8.38 - lr: 0.000001 | |
| 2021-01-21 06:51:09,835 epoch 14 - iter 1428/4766 - loss 0.15137543 - samples/sec: 8.36 - lr: 0.000001 | |
| 2021-01-21 06:54:56,328 epoch 14 - iter 1904/4766 - loss 0.15223388 - samples/sec: 8.41 - lr: 0.000001 | |
| 2021-01-21 06:58:43,179 epoch 14 - iter 2380/4766 - loss 0.15232770 - samples/sec: 8.39 - lr: 0.000001 | |
| 2021-01-21 07:02:29,960 epoch 14 - iter 2856/4766 - loss 0.15376646 - samples/sec: 8.40 - lr: 0.000001 | |
| 2021-01-21 07:06:16,979 epoch 14 - iter 3332/4766 - loss 0.14910628 - samples/sec: 8.39 - lr: 0.000001 | |
| 2021-01-21 07:10:05,313 epoch 14 - iter 3808/4766 - loss 0.15073272 - samples/sec: 8.34 - lr: 0.000001 | |
| 2021-01-21 07:13:52,950 epoch 14 - iter 4284/4766 - loss 0.14982179 - samples/sec: 8.36 - lr: 0.000001 | |
| 2021-01-21 07:17:41,726 epoch 14 - iter 4760/4766 - loss 0.14669553 - samples/sec: 8.32 - lr: 0.000001 | |
| 2021-01-21 07:17:44,436 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 07:17:44,436 EPOCH 14 done: loss 0.1467 - lr 0.0000010 | |
| 2021-01-21 07:17:44,436 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 07:17:44,439 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 07:21:32,208 epoch 15 - iter 476/4766 - loss 0.15710687 - samples/sec: 8.36 - lr: 0.000001 | |
| 2021-01-21 07:25:20,097 epoch 15 - iter 952/4766 - loss 0.15127131 - samples/sec: 8.36 - lr: 0.000001 | |
| 2021-01-21 07:29:09,242 epoch 15 - iter 1428/4766 - loss 0.15385280 - samples/sec: 8.31 - lr: 0.000001 | |
| 2021-01-21 07:32:56,645 epoch 15 - iter 1904/4766 - loss 0.15263483 - samples/sec: 8.37 - lr: 0.000001 | |
| 2021-01-21 07:36:44,549 epoch 15 - iter 2380/4766 - loss 0.15494254 - samples/sec: 8.35 - lr: 0.000001 | |
| 2021-01-21 07:40:31,861 epoch 15 - iter 2856/4766 - loss 0.14994557 - samples/sec: 8.38 - lr: 0.000001 | |
| 2021-01-21 07:44:20,745 epoch 15 - iter 3332/4766 - loss 0.15018726 - samples/sec: 8.32 - lr: 0.000001 | |
| 2021-01-21 07:48:07,710 epoch 15 - iter 3808/4766 - loss 0.14815315 - samples/sec: 8.39 - lr: 0.000001 | |
| 2021-01-21 07:51:58,674 epoch 15 - iter 4284/4766 - loss 0.14728940 - samples/sec: 8.24 - lr: 0.000001 | |
| 2021-01-21 07:55:50,263 epoch 15 - iter 4760/4766 - loss 0.14723711 - samples/sec: 8.22 - lr: 0.000001 | |
| 2021-01-21 07:55:53,003 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 07:55:53,003 EPOCH 15 done: loss 0.1473 - lr 0.0000007 | |
| 2021-01-21 07:55:53,003 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 07:55:53,008 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 07:59:44,568 epoch 16 - iter 476/4766 - loss 0.13166130 - samples/sec: 8.22 - lr: 0.000001 | |
| 2021-01-21 08:03:36,181 epoch 16 - iter 952/4766 - loss 0.14175737 - samples/sec: 8.22 - lr: 0.000001 | |
| 2021-01-21 08:07:28,882 epoch 16 - iter 1428/4766 - loss 0.14304356 - samples/sec: 8.18 - lr: 0.000001 | |
| 2021-01-21 08:11:20,434 epoch 16 - iter 1904/4766 - loss 0.14622200 - samples/sec: 8.22 - lr: 0.000001 | |
| 2021-01-21 08:15:12,406 epoch 16 - iter 2380/4766 - loss 0.14768067 - samples/sec: 8.21 - lr: 0.000001 | |
| 2021-01-21 08:19:04,996 epoch 16 - iter 2856/4766 - loss 0.14707410 - samples/sec: 8.19 - lr: 0.000001 | |
| 2021-01-21 08:22:56,583 epoch 16 - iter 3332/4766 - loss 0.14688055 - samples/sec: 8.22 - lr: 0.000001 | |
| 2021-01-21 08:27:15,003 epoch 16 - iter 3808/4766 - loss 0.14730450 - samples/sec: 7.37 - lr: 0.000001 | |
| 2021-01-21 08:31:07,174 epoch 16 - iter 4284/4766 - loss 0.14827136 - samples/sec: 8.20 - lr: 0.000001 | |
| 2021-01-21 08:34:59,482 epoch 16 - iter 4760/4766 - loss 0.14568427 - samples/sec: 8.20 - lr: 0.000000 | |
| 2021-01-21 08:35:02,197 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 08:35:02,198 EPOCH 16 done: loss 0.1456 - lr 0.0000005 | |
| 2021-01-21 08:35:02,198 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 08:35:02,216 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 08:38:52,372 epoch 17 - iter 476/4766 - loss 0.12585091 - samples/sec: 8.27 - lr: 0.000000 | |
| 2021-01-21 08:42:26,708 epoch 17 - iter 952/4766 - loss 0.13980769 - samples/sec: 8.88 - lr: 0.000000 | |
| 2021-01-21 08:45:38,094 epoch 17 - iter 1428/4766 - loss 0.13790265 - samples/sec: 9.95 - lr: 0.000000 | |
| 2021-01-21 08:48:48,648 epoch 17 - iter 1904/4766 - loss 0.13518588 - samples/sec: 9.99 - lr: 0.000000 | |
| 2021-01-21 08:52:38,876 epoch 17 - iter 2380/4766 - loss 0.14102829 - samples/sec: 8.27 - lr: 0.000000 | |
| 2021-01-21 08:58:28,052 epoch 17 - iter 2856/4766 - loss 0.13996114 - samples/sec: 5.45 - lr: 0.000000 | |
| 2021-01-21 09:04:23,763 epoch 17 - iter 3332/4766 - loss 0.13826631 - samples/sec: 5.35 - lr: 0.000000 | |
| 2021-01-21 09:07:47,606 epoch 17 - iter 3808/4766 - loss 0.13959091 - samples/sec: 9.34 - lr: 0.000000 | |
| 2021-01-21 09:10:58,844 epoch 17 - iter 4284/4766 - loss 0.13834961 - samples/sec: 9.96 - lr: 0.000000 | |
| 2021-01-21 09:14:07,816 epoch 17 - iter 4760/4766 - loss 0.14037759 - samples/sec: 10.08 - lr: 0.000000 | |
| 2021-01-21 09:14:10,160 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 09:14:10,160 EPOCH 17 done: loss 0.1403 - lr 0.0000003 | |
| 2021-01-21 09:14:10,160 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 09:14:10,181 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 09:17:20,231 epoch 18 - iter 476/4766 - loss 0.13481177 - samples/sec: 10.02 - lr: 0.000000 | |
| 2021-01-21 09:20:31,285 epoch 18 - iter 952/4766 - loss 0.12601264 - samples/sec: 9.97 - lr: 0.000000 | |
| 2021-01-21 09:23:41,236 epoch 18 - iter 1428/4766 - loss 0.12608326 - samples/sec: 10.02 - lr: 0.000000 | |
| 2021-01-21 09:26:51,839 epoch 18 - iter 1904/4766 - loss 0.13399083 - samples/sec: 9.99 - lr: 0.000000 | |
| 2021-01-21 09:30:03,764 epoch 18 - iter 2380/4766 - loss 0.13876490 - samples/sec: 9.92 - lr: 0.000000 | |
| 2021-01-21 09:33:15,574 epoch 18 - iter 2856/4766 - loss 0.13878700 - samples/sec: 9.93 - lr: 0.000000 | |
| 2021-01-21 09:36:26,971 epoch 18 - iter 3332/4766 - loss 0.14409246 - samples/sec: 9.95 - lr: 0.000000 | |
| 2021-01-21 09:39:37,934 epoch 18 - iter 3808/4766 - loss 0.14454244 - samples/sec: 9.97 - lr: 0.000000 | |
| 2021-01-21 09:42:48,260 epoch 18 - iter 4284/4766 - loss 0.14386075 - samples/sec: 10.00 - lr: 0.000000 | |
| 2021-01-21 09:45:58,345 epoch 18 - iter 4760/4766 - loss 0.14489400 - samples/sec: 10.02 - lr: 0.000000 | |
| 2021-01-21 09:46:00,567 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 09:46:00,567 EPOCH 18 done: loss 0.1448 - lr 0.0000001 | |
| 2021-01-21 09:46:00,567 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 09:46:00,570 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 09:49:13,016 epoch 19 - iter 476/4766 - loss 0.16550822 - samples/sec: 9.89 - lr: 0.000000 | |
| 2021-01-21 09:52:27,091 epoch 19 - iter 952/4766 - loss 0.13214122 - samples/sec: 9.81 - lr: 0.000000 | |
| 2021-01-21 09:55:42,085 epoch 19 - iter 1428/4766 - loss 0.13831234 - samples/sec: 9.77 - lr: 0.000000 | |
| 2021-01-21 09:58:56,680 epoch 19 - iter 1904/4766 - loss 0.13832571 - samples/sec: 9.79 - lr: 0.000000 | |
| 2021-01-21 10:02:12,350 epoch 19 - iter 2380/4766 - loss 0.13808449 - samples/sec: 9.73 - lr: 0.000000 | |
| 2021-01-21 10:05:26,205 epoch 19 - iter 2856/4766 - loss 0.13753814 - samples/sec: 9.82 - lr: 0.000000 | |
| 2021-01-21 10:08:40,777 epoch 19 - iter 3332/4766 - loss 0.13826467 - samples/sec: 9.79 - lr: 0.000000 | |
| 2021-01-21 10:11:55,648 epoch 19 - iter 3808/4766 - loss 0.14029889 - samples/sec: 9.77 - lr: 0.000000 | |
| 2021-01-21 10:15:10,349 epoch 19 - iter 4284/4766 - loss 0.13696667 - samples/sec: 9.78 - lr: 0.000000 | |
| 2021-01-21 10:18:24,777 epoch 19 - iter 4760/4766 - loss 0.13874853 - samples/sec: 9.79 - lr: 0.000000 | |
| 2021-01-21 10:18:27,049 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 10:18:27,049 EPOCH 19 done: loss 0.1386 - lr 0.0000000 | |
| 2021-01-21 10:18:27,049 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 10:18:27,582 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 10:21:42,494 epoch 20 - iter 476/4766 - loss 0.11851291 - samples/sec: 9.77 - lr: 0.000000 | |
| 2021-01-21 10:24:56,145 epoch 20 - iter 952/4766 - loss 0.13441288 - samples/sec: 9.83 - lr: 0.000000 | |
| 2021-01-21 10:28:10,170 epoch 20 - iter 1428/4766 - loss 0.14083137 - samples/sec: 9.81 - lr: 0.000000 | |
| 2021-01-21 10:31:25,784 epoch 20 - iter 1904/4766 - loss 0.14039091 - samples/sec: 9.73 - lr: 0.000000 | |
| 2021-01-21 10:34:40,300 epoch 20 - iter 2380/4766 - loss 0.14164687 - samples/sec: 9.79 - lr: 0.000000 | |
| 2021-01-21 10:37:54,324 epoch 20 - iter 2856/4766 - loss 0.13843665 - samples/sec: 9.81 - lr: 0.000000 | |
| 2021-01-21 10:41:05,695 epoch 20 - iter 3332/4766 - loss 0.13902040 - samples/sec: 9.95 - lr: 0.000000 | |
| 2021-01-21 10:44:16,299 epoch 20 - iter 3808/4766 - loss 0.13728566 - samples/sec: 9.99 - lr: 0.000000 | |
| 2021-01-21 10:47:26,320 epoch 20 - iter 4284/4766 - loss 0.13661214 - samples/sec: 10.02 - lr: 0.000000 | |
| 2021-01-21 10:50:35,967 epoch 20 - iter 4760/4766 - loss 0.13488013 - samples/sec: 10.04 - lr: 0.000000 | |
| 2021-01-21 10:50:38,248 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 10:50:38,248 EPOCH 20 done: loss 0.1348 - lr 0.0000000 | |
| 2021-01-21 10:50:38,248 BAD EPOCHS (no improvement): 4 | |
| 2021-01-21 10:51:28,424 ---------------------------------------------------------------------------------------------------- | |
| 2021-01-21 10:51:28,425 Testing using best model ... | |
| 2021-01-21 10:54:06,963 0.9530 0.9520 0.9525 | |
| 2021-01-21 10:54:06,963 | |
| Results: | |
| - F1-score (micro) 0.9525 | |
| - F1-score (macro) 0.9528 | |
| By class: | |
| LOC tp: 751 - fp: 36 - fn: 23 - precision: 0.9543 - recall: 0.9703 - f1-score: 0.9622 | |
| MISC tp: 1095 - fp: 56 - fn: 92 - precision: 0.9513 - recall: 0.9225 - f1-score: 0.9367 | |
| ORG tp: 834 - fp: 59 - fn: 48 - precision: 0.9339 - recall: 0.9456 - f1-score: 0.9397 | |
| PER tp: 1072 - fp: 34 - fn: 26 - precision: 0.9693 - recall: 0.9763 - f1-score: 0.9728 | |
| 2021-01-21 10:54:06,963 ---------------------------------------------------------------------------------------------------- | |