| 2023-10-24 13:12:30,385 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:12:30,386 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(64001, 768) | |
| (position_embeddings): Embedding(512, 768) | |
| (token_type_embeddings): Embedding(2, 768) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): BertEncoder( | |
| (layer): ModuleList( | |
| (0): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (1): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (2): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (3): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (4): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (5): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (6): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (7): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (8): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (9): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (10): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (11): BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=21, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-24 13:12:30,386 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:12:30,386 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences | |
| - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator | |
| 2023-10-24 13:12:30,386 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:12:30,386 Train: 5901 sentences | |
| 2023-10-24 13:12:30,386 (train_with_dev=False, train_with_test=False) | |
| 2023-10-24 13:12:30,386 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:12:30,386 Training Params: | |
| 2023-10-24 13:12:30,386 - learning_rate: "3e-05" | |
| 2023-10-24 13:12:30,386 - mini_batch_size: "8" | |
| 2023-10-24 13:12:30,386 - max_epochs: "10" | |
| 2023-10-24 13:12:30,386 - shuffle: "True" | |
| 2023-10-24 13:12:30,386 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:12:30,386 Plugins: | |
| 2023-10-24 13:12:30,387 - TensorboardLogger | |
| 2023-10-24 13:12:30,387 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-24 13:12:30,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:12:30,387 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-24 13:12:30,387 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-24 13:12:30,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:12:30,387 Computation: | |
| 2023-10-24 13:12:30,387 - compute on device: cuda:0 | |
| 2023-10-24 13:12:30,387 - embedding storage: none | |
| 2023-10-24 13:12:30,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:12:30,387 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-24 13:12:30,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:12:30,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:12:30,387 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-24 13:12:37,067 epoch 1 - iter 73/738 - loss 2.18161987 - time (sec): 6.68 - samples/sec: 2354.92 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-24 13:12:44,149 epoch 1 - iter 146/738 - loss 1.42985226 - time (sec): 13.76 - samples/sec: 2283.70 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-24 13:12:50,831 epoch 1 - iter 219/738 - loss 1.10599054 - time (sec): 20.44 - samples/sec: 2291.46 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-24 13:12:57,060 epoch 1 - iter 292/738 - loss 0.91769116 - time (sec): 26.67 - samples/sec: 2322.65 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-24 13:13:05,191 epoch 1 - iter 365/738 - loss 0.77452000 - time (sec): 34.80 - samples/sec: 2327.75 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-24 13:13:11,963 epoch 1 - iter 438/738 - loss 0.68331020 - time (sec): 41.58 - samples/sec: 2359.17 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-24 13:13:19,168 epoch 1 - iter 511/738 - loss 0.60818039 - time (sec): 48.78 - samples/sec: 2365.23 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-24 13:13:26,029 epoch 1 - iter 584/738 - loss 0.55818973 - time (sec): 55.64 - samples/sec: 2359.43 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-24 13:13:33,467 epoch 1 - iter 657/738 - loss 0.51160952 - time (sec): 63.08 - samples/sec: 2353.91 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-24 13:13:39,918 epoch 1 - iter 730/738 - loss 0.47724150 - time (sec): 69.53 - samples/sec: 2357.48 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-24 13:13:40,938 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:13:40,938 EPOCH 1 done: loss 0.4728 - lr: 0.000030 | |
| 2023-10-24 13:13:47,154 DEV : loss 0.10554392635822296 - f1-score (micro avg) 0.7528 | |
| 2023-10-24 13:13:47,175 saving best model | |
| 2023-10-24 13:13:47,725 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:13:54,266 epoch 2 - iter 73/738 - loss 0.13369869 - time (sec): 6.54 - samples/sec: 2400.65 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-24 13:14:01,134 epoch 2 - iter 146/738 - loss 0.13182120 - time (sec): 13.41 - samples/sec: 2353.28 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-24 13:14:07,956 epoch 2 - iter 219/738 - loss 0.13189987 - time (sec): 20.23 - samples/sec: 2362.32 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-24 13:14:14,726 epoch 2 - iter 292/738 - loss 0.12551263 - time (sec): 27.00 - samples/sec: 2339.53 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-24 13:14:21,473 epoch 2 - iter 365/738 - loss 0.12297520 - time (sec): 33.75 - samples/sec: 2346.93 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-24 13:14:28,306 epoch 2 - iter 438/738 - loss 0.12082661 - time (sec): 40.58 - samples/sec: 2341.88 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-24 13:14:35,634 epoch 2 - iter 511/738 - loss 0.12078839 - time (sec): 47.91 - samples/sec: 2359.93 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-24 13:14:43,365 epoch 2 - iter 584/738 - loss 0.11688290 - time (sec): 55.64 - samples/sec: 2357.67 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-24 13:14:50,105 epoch 2 - iter 657/738 - loss 0.11634259 - time (sec): 62.38 - samples/sec: 2356.32 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-24 13:14:57,762 epoch 2 - iter 730/738 - loss 0.11522082 - time (sec): 70.04 - samples/sec: 2349.93 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-24 13:14:58,512 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:14:58,512 EPOCH 2 done: loss 0.1151 - lr: 0.000027 | |
| 2023-10-24 13:15:07,005 DEV : loss 0.09679369628429413 - f1-score (micro avg) 0.7871 | |
| 2023-10-24 13:15:07,026 saving best model | |
| 2023-10-24 13:15:07,769 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:15:13,874 epoch 3 - iter 73/738 - loss 0.06119096 - time (sec): 6.10 - samples/sec: 2527.55 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-24 13:15:21,101 epoch 3 - iter 146/738 - loss 0.06385970 - time (sec): 13.33 - samples/sec: 2408.60 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-24 13:15:28,695 epoch 3 - iter 219/738 - loss 0.06608306 - time (sec): 20.93 - samples/sec: 2350.06 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-24 13:15:36,070 epoch 3 - iter 292/738 - loss 0.06260299 - time (sec): 28.30 - samples/sec: 2348.85 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-24 13:15:43,242 epoch 3 - iter 365/738 - loss 0.06272309 - time (sec): 35.47 - samples/sec: 2337.28 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-24 13:15:50,403 epoch 3 - iter 438/738 - loss 0.06424382 - time (sec): 42.63 - samples/sec: 2337.43 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-24 13:15:57,263 epoch 3 - iter 511/738 - loss 0.06412265 - time (sec): 49.49 - samples/sec: 2339.66 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-24 13:16:03,619 epoch 3 - iter 584/738 - loss 0.06489306 - time (sec): 55.85 - samples/sec: 2349.80 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-24 13:16:10,250 epoch 3 - iter 657/738 - loss 0.06455833 - time (sec): 62.48 - samples/sec: 2347.50 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-24 13:16:17,422 epoch 3 - iter 730/738 - loss 0.06554966 - time (sec): 69.65 - samples/sec: 2355.53 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-24 13:16:18,577 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:16:18,577 EPOCH 3 done: loss 0.0656 - lr: 0.000023 | |
| 2023-10-24 13:16:27,094 DEV : loss 0.1195509284734726 - f1-score (micro avg) 0.8074 | |
| 2023-10-24 13:16:27,115 saving best model | |
| 2023-10-24 13:16:27,857 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:16:34,341 epoch 4 - iter 73/738 - loss 0.03826326 - time (sec): 6.48 - samples/sec: 2323.82 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-24 13:16:40,745 epoch 4 - iter 146/738 - loss 0.03920578 - time (sec): 12.89 - samples/sec: 2352.56 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-24 13:16:47,380 epoch 4 - iter 219/738 - loss 0.04269634 - time (sec): 19.52 - samples/sec: 2347.37 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-24 13:16:53,782 epoch 4 - iter 292/738 - loss 0.03941502 - time (sec): 25.92 - samples/sec: 2350.87 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-24 13:17:01,518 epoch 4 - iter 365/738 - loss 0.04336450 - time (sec): 33.66 - samples/sec: 2339.39 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-24 13:17:09,372 epoch 4 - iter 438/738 - loss 0.04463978 - time (sec): 41.51 - samples/sec: 2330.02 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-24 13:17:17,052 epoch 4 - iter 511/738 - loss 0.04335848 - time (sec): 49.19 - samples/sec: 2333.73 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-24 13:17:24,654 epoch 4 - iter 584/738 - loss 0.04416947 - time (sec): 56.80 - samples/sec: 2342.98 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-24 13:17:31,897 epoch 4 - iter 657/738 - loss 0.04422596 - time (sec): 64.04 - samples/sec: 2338.84 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-24 13:17:38,254 epoch 4 - iter 730/738 - loss 0.04340328 - time (sec): 70.40 - samples/sec: 2341.64 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-24 13:17:38,892 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:17:38,893 EPOCH 4 done: loss 0.0434 - lr: 0.000020 | |
| 2023-10-24 13:17:47,395 DEV : loss 0.14306315779685974 - f1-score (micro avg) 0.8255 | |
| 2023-10-24 13:17:47,416 saving best model | |
| 2023-10-24 13:17:48,112 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:17:54,842 epoch 5 - iter 73/738 - loss 0.03252486 - time (sec): 6.73 - samples/sec: 2414.59 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-24 13:18:02,107 epoch 5 - iter 146/738 - loss 0.02695551 - time (sec): 13.99 - samples/sec: 2423.52 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-24 13:18:09,085 epoch 5 - iter 219/738 - loss 0.02469070 - time (sec): 20.97 - samples/sec: 2355.55 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-24 13:18:15,961 epoch 5 - iter 292/738 - loss 0.02799215 - time (sec): 27.85 - samples/sec: 2360.35 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-24 13:18:23,556 epoch 5 - iter 365/738 - loss 0.03089862 - time (sec): 35.44 - samples/sec: 2369.17 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-24 13:18:30,272 epoch 5 - iter 438/738 - loss 0.02992995 - time (sec): 42.16 - samples/sec: 2370.04 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-24 13:18:36,758 epoch 5 - iter 511/738 - loss 0.03020870 - time (sec): 48.65 - samples/sec: 2361.43 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-24 13:18:44,656 epoch 5 - iter 584/738 - loss 0.02894484 - time (sec): 56.54 - samples/sec: 2341.48 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-24 13:18:51,234 epoch 5 - iter 657/738 - loss 0.02917966 - time (sec): 63.12 - samples/sec: 2354.37 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-24 13:18:58,515 epoch 5 - iter 730/738 - loss 0.02891546 - time (sec): 70.40 - samples/sec: 2342.45 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-24 13:18:59,256 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:18:59,256 EPOCH 5 done: loss 0.0290 - lr: 0.000017 | |
| 2023-10-24 13:19:07,778 DEV : loss 0.17278100550174713 - f1-score (micro avg) 0.8353 | |
| 2023-10-24 13:19:07,800 saving best model | |
| 2023-10-24 13:19:08,554 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:19:15,847 epoch 6 - iter 73/738 - loss 0.02161928 - time (sec): 7.29 - samples/sec: 2358.73 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-24 13:19:21,872 epoch 6 - iter 146/738 - loss 0.02705650 - time (sec): 13.32 - samples/sec: 2391.93 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-24 13:19:28,868 epoch 6 - iter 219/738 - loss 0.02310291 - time (sec): 20.31 - samples/sec: 2372.71 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-24 13:19:36,807 epoch 6 - iter 292/738 - loss 0.02454477 - time (sec): 28.25 - samples/sec: 2397.80 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-24 13:19:43,311 epoch 6 - iter 365/738 - loss 0.02313850 - time (sec): 34.76 - samples/sec: 2387.53 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-24 13:19:49,707 epoch 6 - iter 438/738 - loss 0.02240292 - time (sec): 41.15 - samples/sec: 2378.88 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-24 13:19:55,818 epoch 6 - iter 511/738 - loss 0.02311644 - time (sec): 47.26 - samples/sec: 2369.82 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-24 13:20:02,974 epoch 6 - iter 584/738 - loss 0.02322732 - time (sec): 54.42 - samples/sec: 2367.98 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-24 13:20:10,794 epoch 6 - iter 657/738 - loss 0.02288665 - time (sec): 62.24 - samples/sec: 2368.39 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-24 13:20:18,200 epoch 6 - iter 730/738 - loss 0.02245972 - time (sec): 69.65 - samples/sec: 2364.74 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-24 13:20:18,854 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:20:18,855 EPOCH 6 done: loss 0.0223 - lr: 0.000013 | |
| 2023-10-24 13:20:27,379 DEV : loss 0.1752229779958725 - f1-score (micro avg) 0.8311 | |
| 2023-10-24 13:20:27,400 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:20:34,992 epoch 7 - iter 73/738 - loss 0.01696402 - time (sec): 7.59 - samples/sec: 2506.55 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-24 13:20:42,483 epoch 7 - iter 146/738 - loss 0.01606754 - time (sec): 15.08 - samples/sec: 2405.65 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-24 13:20:49,251 epoch 7 - iter 219/738 - loss 0.01446198 - time (sec): 21.85 - samples/sec: 2366.51 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-24 13:20:56,316 epoch 7 - iter 292/738 - loss 0.01432059 - time (sec): 28.91 - samples/sec: 2354.26 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-24 13:21:02,785 epoch 7 - iter 365/738 - loss 0.01467452 - time (sec): 35.38 - samples/sec: 2363.45 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-24 13:21:09,515 epoch 7 - iter 438/738 - loss 0.01528636 - time (sec): 42.11 - samples/sec: 2356.64 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-24 13:21:16,247 epoch 7 - iter 511/738 - loss 0.01555352 - time (sec): 48.85 - samples/sec: 2347.07 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-24 13:21:22,550 epoch 7 - iter 584/738 - loss 0.01567911 - time (sec): 55.15 - samples/sec: 2345.54 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-24 13:21:30,682 epoch 7 - iter 657/738 - loss 0.01546853 - time (sec): 63.28 - samples/sec: 2347.97 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-24 13:21:37,808 epoch 7 - iter 730/738 - loss 0.01529696 - time (sec): 70.41 - samples/sec: 2337.42 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-24 13:21:38,478 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:21:38,478 EPOCH 7 done: loss 0.0154 - lr: 0.000010 | |
| 2023-10-24 13:21:47,007 DEV : loss 0.18594373762607574 - f1-score (micro avg) 0.8365 | |
| 2023-10-24 13:21:47,028 saving best model | |
| 2023-10-24 13:21:47,720 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:21:54,425 epoch 8 - iter 73/738 - loss 0.00750537 - time (sec): 6.70 - samples/sec: 2238.98 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-24 13:22:01,617 epoch 8 - iter 146/738 - loss 0.00788359 - time (sec): 13.90 - samples/sec: 2269.45 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-24 13:22:08,824 epoch 8 - iter 219/738 - loss 0.00934315 - time (sec): 21.10 - samples/sec: 2322.77 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-24 13:22:16,377 epoch 8 - iter 292/738 - loss 0.01466951 - time (sec): 28.66 - samples/sec: 2371.90 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-24 13:22:22,773 epoch 8 - iter 365/738 - loss 0.01332356 - time (sec): 35.05 - samples/sec: 2373.74 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-24 13:22:30,133 epoch 8 - iter 438/738 - loss 0.01270781 - time (sec): 42.41 - samples/sec: 2367.04 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-24 13:22:36,550 epoch 8 - iter 511/738 - loss 0.01165258 - time (sec): 48.83 - samples/sec: 2364.33 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-24 13:22:43,352 epoch 8 - iter 584/738 - loss 0.01144850 - time (sec): 55.63 - samples/sec: 2364.87 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-24 13:22:50,962 epoch 8 - iter 657/738 - loss 0.01115597 - time (sec): 63.24 - samples/sec: 2359.28 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-24 13:22:57,811 epoch 8 - iter 730/738 - loss 0.01096523 - time (sec): 70.09 - samples/sec: 2347.47 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-24 13:22:58,511 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:22:58,512 EPOCH 8 done: loss 0.0109 - lr: 0.000007 | |
| 2023-10-24 13:23:07,041 DEV : loss 0.20139646530151367 - f1-score (micro avg) 0.8427 | |
| 2023-10-24 13:23:07,063 saving best model | |
| 2023-10-24 13:23:07,765 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:23:14,724 epoch 9 - iter 73/738 - loss 0.00257277 - time (sec): 6.96 - samples/sec: 2324.26 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-24 13:23:23,010 epoch 9 - iter 146/738 - loss 0.00730412 - time (sec): 15.24 - samples/sec: 2403.85 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-24 13:23:29,423 epoch 9 - iter 219/738 - loss 0.00609698 - time (sec): 21.66 - samples/sec: 2410.15 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-24 13:23:35,741 epoch 9 - iter 292/738 - loss 0.00544285 - time (sec): 27.98 - samples/sec: 2421.83 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-24 13:23:42,329 epoch 9 - iter 365/738 - loss 0.00635157 - time (sec): 34.56 - samples/sec: 2393.52 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-24 13:23:49,427 epoch 9 - iter 438/738 - loss 0.00672352 - time (sec): 41.66 - samples/sec: 2379.81 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-24 13:23:56,025 epoch 9 - iter 511/738 - loss 0.00663039 - time (sec): 48.26 - samples/sec: 2380.14 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-24 13:24:03,205 epoch 9 - iter 584/738 - loss 0.00714230 - time (sec): 55.44 - samples/sec: 2372.22 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-24 13:24:10,544 epoch 9 - iter 657/738 - loss 0.00737085 - time (sec): 62.78 - samples/sec: 2369.24 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-24 13:24:17,784 epoch 9 - iter 730/738 - loss 0.00770982 - time (sec): 70.02 - samples/sec: 2355.80 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-24 13:24:18,512 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:24:18,513 EPOCH 9 done: loss 0.0077 - lr: 0.000003 | |
| 2023-10-24 13:24:27,038 DEV : loss 0.21205534040927887 - f1-score (micro avg) 0.8366 | |
| 2023-10-24 13:24:27,060 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:24:34,370 epoch 10 - iter 73/738 - loss 0.00087160 - time (sec): 7.31 - samples/sec: 2298.01 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-24 13:24:40,795 epoch 10 - iter 146/738 - loss 0.00199352 - time (sec): 13.73 - samples/sec: 2346.39 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-24 13:24:47,446 epoch 10 - iter 219/738 - loss 0.00286730 - time (sec): 20.39 - samples/sec: 2358.58 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-24 13:24:54,218 epoch 10 - iter 292/738 - loss 0.00350713 - time (sec): 27.16 - samples/sec: 2358.90 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-24 13:25:01,059 epoch 10 - iter 365/738 - loss 0.00344795 - time (sec): 34.00 - samples/sec: 2340.08 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-24 13:25:07,969 epoch 10 - iter 438/738 - loss 0.00386173 - time (sec): 40.91 - samples/sec: 2319.16 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-24 13:25:14,691 epoch 10 - iter 511/738 - loss 0.00390650 - time (sec): 47.63 - samples/sec: 2328.71 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-24 13:25:21,256 epoch 10 - iter 584/738 - loss 0.00497431 - time (sec): 54.20 - samples/sec: 2330.43 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-24 13:25:28,442 epoch 10 - iter 657/738 - loss 0.00532116 - time (sec): 61.38 - samples/sec: 2357.16 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-24 13:25:36,894 epoch 10 - iter 730/738 - loss 0.00617810 - time (sec): 69.83 - samples/sec: 2357.54 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-24 13:25:37,571 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:25:37,572 EPOCH 10 done: loss 0.0061 - lr: 0.000000 | |
| 2023-10-24 13:25:46,103 DEV : loss 0.2109983116388321 - f1-score (micro avg) 0.8403 | |
| 2023-10-24 13:25:46,684 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 13:25:46,685 Loading model from best epoch ... | |
| 2023-10-24 13:25:48,551 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod | |
| 2023-10-24 13:25:55,248 | |
| Results: | |
| - F-score (micro) 0.7894 | |
| - F-score (macro) 0.6916 | |
| - Accuracy 0.6747 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8341 0.8846 0.8586 858 | |
| pers 0.7371 0.7989 0.7668 537 | |
| org 0.5547 0.5758 0.5651 132 | |
| time 0.5077 0.6111 0.5546 54 | |
| prod 0.7593 0.6721 0.7130 61 | |
| micro avg 0.7654 0.8149 0.7894 1642 | |
| macro avg 0.6786 0.7085 0.6916 1642 | |
| weighted avg 0.7664 0.8149 0.7896 1642 | |
| 2023-10-24 13:25:55,249 ---------------------------------------------------------------------------------------------------- | |