| 2023-10-18 16:42:59,399 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:42:59,399 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(32001, 128) | |
| (position_embeddings): Embedding(512, 128) | |
| (token_type_embeddings): Embedding(2, 128) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): BertEncoder( | |
| (layer): ModuleList( | |
| (0-1): 2 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=128, out_features=128, bias=True) | |
| (key): Linear(in_features=128, out_features=128, bias=True) | |
| (value): Linear(in_features=128, out_features=128, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=128, out_features=512, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=512, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=128, out_features=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-18 16:42:59,399 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:42:59,399 MultiCorpus: 966 train + 219 dev + 204 test sentences | |
| - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator | |
| 2023-10-18 16:42:59,400 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:42:59,400 Train: 966 sentences | |
| 2023-10-18 16:42:59,400 (train_with_dev=False, train_with_test=False) | |
| 2023-10-18 16:42:59,400 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:42:59,400 Training Params: | |
| 2023-10-18 16:42:59,400 - learning_rate: "3e-05" | |
| 2023-10-18 16:42:59,400 - mini_batch_size: "8" | |
| 2023-10-18 16:42:59,400 - max_epochs: "10" | |
| 2023-10-18 16:42:59,400 - shuffle: "True" | |
| 2023-10-18 16:42:59,400 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:42:59,400 Plugins: | |
| 2023-10-18 16:42:59,400 - TensorboardLogger | |
| 2023-10-18 16:42:59,400 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-18 16:42:59,400 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:42:59,400 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-18 16:42:59,400 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-18 16:42:59,400 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:42:59,400 Computation: | |
| 2023-10-18 16:42:59,400 - compute on device: cuda:0 | |
| 2023-10-18 16:42:59,400 - embedding storage: none | |
| 2023-10-18 16:42:59,400 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:42:59,400 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-18 16:42:59,400 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:42:59,400 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:42:59,400 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-18 16:42:59,672 epoch 1 - iter 12/121 - loss 3.85185501 - time (sec): 0.27 - samples/sec: 9573.26 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:42:59,949 epoch 1 - iter 24/121 - loss 3.87278732 - time (sec): 0.55 - samples/sec: 9221.37 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:43:00,225 epoch 1 - iter 36/121 - loss 3.76772014 - time (sec): 0.82 - samples/sec: 9363.58 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:43:00,494 epoch 1 - iter 48/121 - loss 3.68456814 - time (sec): 1.09 - samples/sec: 9374.28 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:43:00,754 epoch 1 - iter 60/121 - loss 3.61486515 - time (sec): 1.35 - samples/sec: 9329.91 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:43:01,021 epoch 1 - iter 72/121 - loss 3.51566729 - time (sec): 1.62 - samples/sec: 9069.58 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:43:01,244 epoch 1 - iter 84/121 - loss 3.39647856 - time (sec): 1.84 - samples/sec: 9228.74 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:43:01,498 epoch 1 - iter 96/121 - loss 3.24751305 - time (sec): 2.10 - samples/sec: 9398.28 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:43:01,773 epoch 1 - iter 108/121 - loss 3.09721141 - time (sec): 2.37 - samples/sec: 9320.21 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:43:02,042 epoch 1 - iter 120/121 - loss 2.94358352 - time (sec): 2.64 - samples/sec: 9307.13 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 16:43:02,062 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:02,062 EPOCH 1 done: loss 2.9349 - lr: 0.000030 | |
| 2023-10-18 16:43:02,577 DEV : loss 0.8185554146766663 - f1-score (micro avg) 0.0 | |
| 2023-10-18 16:43:02,582 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:02,872 epoch 2 - iter 12/121 - loss 1.12961394 - time (sec): 0.29 - samples/sec: 9640.37 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 16:43:03,142 epoch 2 - iter 24/121 - loss 1.04321885 - time (sec): 0.56 - samples/sec: 9687.58 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:43:03,400 epoch 2 - iter 36/121 - loss 1.00364866 - time (sec): 0.82 - samples/sec: 9213.60 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:43:03,660 epoch 2 - iter 48/121 - loss 0.94936840 - time (sec): 1.08 - samples/sec: 9130.45 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:43:03,931 epoch 2 - iter 60/121 - loss 0.91757724 - time (sec): 1.35 - samples/sec: 9065.02 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 16:43:04,194 epoch 2 - iter 72/121 - loss 0.88263814 - time (sec): 1.61 - samples/sec: 9063.08 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 16:43:04,464 epoch 2 - iter 84/121 - loss 0.85720978 - time (sec): 1.88 - samples/sec: 9185.69 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 16:43:04,738 epoch 2 - iter 96/121 - loss 0.82606464 - time (sec): 2.16 - samples/sec: 9154.53 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:43:05,005 epoch 2 - iter 108/121 - loss 0.81249538 - time (sec): 2.42 - samples/sec: 9127.63 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:43:05,267 epoch 2 - iter 120/121 - loss 0.80233778 - time (sec): 2.68 - samples/sec: 9170.42 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:43:05,285 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:05,285 EPOCH 2 done: loss 0.8022 - lr: 0.000027 | |
| 2023-10-18 16:43:05,714 DEV : loss 0.6076887249946594 - f1-score (micro avg) 0.0 | |
| 2023-10-18 16:43:05,720 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:05,994 epoch 3 - iter 12/121 - loss 0.61725437 - time (sec): 0.27 - samples/sec: 9910.75 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:43:06,264 epoch 3 - iter 24/121 - loss 0.66429884 - time (sec): 0.54 - samples/sec: 9145.42 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:43:06,533 epoch 3 - iter 36/121 - loss 0.65601765 - time (sec): 0.81 - samples/sec: 9288.98 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:43:06,793 epoch 3 - iter 48/121 - loss 0.66644416 - time (sec): 1.07 - samples/sec: 9214.94 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 16:43:07,070 epoch 3 - iter 60/121 - loss 0.66916532 - time (sec): 1.35 - samples/sec: 9375.86 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 16:43:07,330 epoch 3 - iter 72/121 - loss 0.67003985 - time (sec): 1.61 - samples/sec: 9236.10 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 16:43:07,595 epoch 3 - iter 84/121 - loss 0.65481501 - time (sec): 1.88 - samples/sec: 9106.49 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:43:07,883 epoch 3 - iter 96/121 - loss 0.63895133 - time (sec): 2.16 - samples/sec: 9105.75 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:43:08,148 epoch 3 - iter 108/121 - loss 0.63920953 - time (sec): 2.43 - samples/sec: 9194.01 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:43:08,406 epoch 3 - iter 120/121 - loss 0.63723360 - time (sec): 2.69 - samples/sec: 9163.22 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 16:43:08,424 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:08,424 EPOCH 3 done: loss 0.6359 - lr: 0.000023 | |
| 2023-10-18 16:43:08,843 DEV : loss 0.49888041615486145 - f1-score (micro avg) 0.03 | |
| 2023-10-18 16:43:08,848 saving best model | |
| 2023-10-18 16:43:08,878 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:09,144 epoch 4 - iter 12/121 - loss 0.53142606 - time (sec): 0.27 - samples/sec: 9930.30 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 16:43:09,433 epoch 4 - iter 24/121 - loss 0.57018036 - time (sec): 0.55 - samples/sec: 9275.00 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 16:43:09,718 epoch 4 - iter 36/121 - loss 0.59227772 - time (sec): 0.84 - samples/sec: 8979.18 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 16:43:09,991 epoch 4 - iter 48/121 - loss 0.58826865 - time (sec): 1.11 - samples/sec: 9185.34 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 16:43:10,261 epoch 4 - iter 60/121 - loss 0.58871767 - time (sec): 1.38 - samples/sec: 9265.19 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 16:43:10,534 epoch 4 - iter 72/121 - loss 0.58708344 - time (sec): 1.66 - samples/sec: 9224.19 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:43:10,795 epoch 4 - iter 84/121 - loss 0.57480994 - time (sec): 1.92 - samples/sec: 9245.62 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:43:11,057 epoch 4 - iter 96/121 - loss 0.58147548 - time (sec): 2.18 - samples/sec: 9159.63 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:43:11,315 epoch 4 - iter 108/121 - loss 0.57476321 - time (sec): 2.44 - samples/sec: 9108.84 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 16:43:11,579 epoch 4 - iter 120/121 - loss 0.56654968 - time (sec): 2.70 - samples/sec: 9099.69 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 16:43:11,599 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:11,599 EPOCH 4 done: loss 0.5653 - lr: 0.000020 | |
| 2023-10-18 16:43:12,023 DEV : loss 0.45119330286979675 - f1-score (micro avg) 0.2213 | |
| 2023-10-18 16:43:12,027 saving best model | |
| 2023-10-18 16:43:12,062 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:12,341 epoch 5 - iter 12/121 - loss 0.44292282 - time (sec): 0.28 - samples/sec: 8956.51 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 16:43:12,597 epoch 5 - iter 24/121 - loss 0.46549219 - time (sec): 0.53 - samples/sec: 9295.90 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:43:12,867 epoch 5 - iter 36/121 - loss 0.47270373 - time (sec): 0.80 - samples/sec: 9017.24 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:43:13,135 epoch 5 - iter 48/121 - loss 0.49544481 - time (sec): 1.07 - samples/sec: 9027.96 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:43:13,393 epoch 5 - iter 60/121 - loss 0.50228593 - time (sec): 1.33 - samples/sec: 9129.47 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:43:13,675 epoch 5 - iter 72/121 - loss 0.50512726 - time (sec): 1.61 - samples/sec: 9157.28 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:43:13,951 epoch 5 - iter 84/121 - loss 0.51537519 - time (sec): 1.89 - samples/sec: 9104.24 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:43:14,229 epoch 5 - iter 96/121 - loss 0.50991046 - time (sec): 2.17 - samples/sec: 9039.56 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 16:43:14,495 epoch 5 - iter 108/121 - loss 0.51278818 - time (sec): 2.43 - samples/sec: 8956.94 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 16:43:14,772 epoch 5 - iter 120/121 - loss 0.50968130 - time (sec): 2.71 - samples/sec: 9097.58 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 16:43:14,791 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:14,791 EPOCH 5 done: loss 0.5100 - lr: 0.000017 | |
| 2023-10-18 16:43:15,228 DEV : loss 0.3984816372394562 - f1-score (micro avg) 0.3357 | |
| 2023-10-18 16:43:15,232 saving best model | |
| 2023-10-18 16:43:15,266 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:15,540 epoch 6 - iter 12/121 - loss 0.40809204 - time (sec): 0.27 - samples/sec: 9149.92 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 16:43:15,816 epoch 6 - iter 24/121 - loss 0.49407097 - time (sec): 0.55 - samples/sec: 8978.65 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 16:43:16,078 epoch 6 - iter 36/121 - loss 0.51909438 - time (sec): 0.81 - samples/sec: 8907.78 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 16:43:16,354 epoch 6 - iter 48/121 - loss 0.50861620 - time (sec): 1.09 - samples/sec: 8781.35 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:43:16,619 epoch 6 - iter 60/121 - loss 0.51626710 - time (sec): 1.35 - samples/sec: 8981.29 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:43:16,893 epoch 6 - iter 72/121 - loss 0.49675819 - time (sec): 1.63 - samples/sec: 9097.55 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:43:17,178 epoch 6 - iter 84/121 - loss 0.48514762 - time (sec): 1.91 - samples/sec: 9129.35 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:43:17,453 epoch 6 - iter 96/121 - loss 0.48487073 - time (sec): 2.19 - samples/sec: 9028.79 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:43:17,714 epoch 6 - iter 108/121 - loss 0.48417826 - time (sec): 2.45 - samples/sec: 9049.10 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:43:17,982 epoch 6 - iter 120/121 - loss 0.46985100 - time (sec): 2.72 - samples/sec: 9065.97 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 16:43:18,005 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:18,005 EPOCH 6 done: loss 0.4698 - lr: 0.000013 | |
| 2023-10-18 16:43:18,435 DEV : loss 0.3863314986228943 - f1-score (micro avg) 0.3649 | |
| 2023-10-18 16:43:18,440 saving best model | |
| 2023-10-18 16:43:18,473 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:18,708 epoch 7 - iter 12/121 - loss 0.50490179 - time (sec): 0.23 - samples/sec: 9436.56 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 16:43:18,972 epoch 7 - iter 24/121 - loss 0.44217131 - time (sec): 0.50 - samples/sec: 9541.00 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 16:43:19,233 epoch 7 - iter 36/121 - loss 0.43610264 - time (sec): 0.76 - samples/sec: 9371.59 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:43:19,495 epoch 7 - iter 48/121 - loss 0.46315148 - time (sec): 1.02 - samples/sec: 9526.77 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:43:19,766 epoch 7 - iter 60/121 - loss 0.45168127 - time (sec): 1.29 - samples/sec: 9695.96 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:43:20,027 epoch 7 - iter 72/121 - loss 0.43779015 - time (sec): 1.55 - samples/sec: 9475.03 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 16:43:20,297 epoch 7 - iter 84/121 - loss 0.44222989 - time (sec): 1.82 - samples/sec: 9512.41 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 16:43:20,561 epoch 7 - iter 96/121 - loss 0.44964141 - time (sec): 2.09 - samples/sec: 9433.70 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 16:43:20,823 epoch 7 - iter 108/121 - loss 0.44717098 - time (sec): 2.35 - samples/sec: 9392.54 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:43:21,101 epoch 7 - iter 120/121 - loss 0.44474721 - time (sec): 2.63 - samples/sec: 9366.42 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:43:21,121 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:21,121 EPOCH 7 done: loss 0.4451 - lr: 0.000010 | |
| 2023-10-18 16:43:21,553 DEV : loss 0.3575003147125244 - f1-score (micro avg) 0.4161 | |
| 2023-10-18 16:43:21,558 saving best model | |
| 2023-10-18 16:43:21,592 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:21,864 epoch 8 - iter 12/121 - loss 0.54495607 - time (sec): 0.27 - samples/sec: 8285.53 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:43:22,132 epoch 8 - iter 24/121 - loss 0.49485416 - time (sec): 0.54 - samples/sec: 8706.66 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:43:22,394 epoch 8 - iter 36/121 - loss 0.46710902 - time (sec): 0.80 - samples/sec: 9091.12 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:43:22,656 epoch 8 - iter 48/121 - loss 0.44836209 - time (sec): 1.06 - samples/sec: 9227.45 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:43:22,922 epoch 8 - iter 60/121 - loss 0.45007509 - time (sec): 1.33 - samples/sec: 9392.57 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:43:23,168 epoch 8 - iter 72/121 - loss 0.44193922 - time (sec): 1.58 - samples/sec: 9222.71 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:43:23,434 epoch 8 - iter 84/121 - loss 0.44089643 - time (sec): 1.84 - samples/sec: 9307.71 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:43:23,698 epoch 8 - iter 96/121 - loss 0.43841319 - time (sec): 2.11 - samples/sec: 9258.59 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:43:23,959 epoch 8 - iter 108/121 - loss 0.43416018 - time (sec): 2.37 - samples/sec: 9311.46 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 16:43:24,221 epoch 8 - iter 120/121 - loss 0.43434301 - time (sec): 2.63 - samples/sec: 9373.10 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 16:43:24,238 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:24,238 EPOCH 8 done: loss 0.4345 - lr: 0.000007 | |
| 2023-10-18 16:43:24,671 DEV : loss 0.3573443591594696 - f1-score (micro avg) 0.4237 | |
| 2023-10-18 16:43:24,675 saving best model | |
| 2023-10-18 16:43:24,709 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:24,989 epoch 9 - iter 12/121 - loss 0.39487327 - time (sec): 0.28 - samples/sec: 9096.70 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:43:25,269 epoch 9 - iter 24/121 - loss 0.45883792 - time (sec): 0.56 - samples/sec: 8782.95 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:43:25,535 epoch 9 - iter 36/121 - loss 0.43858190 - time (sec): 0.83 - samples/sec: 8701.67 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:43:25,805 epoch 9 - iter 48/121 - loss 0.42548116 - time (sec): 1.10 - samples/sec: 8703.59 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:43:26,065 epoch 9 - iter 60/121 - loss 0.42028047 - time (sec): 1.35 - samples/sec: 8638.47 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:43:26,360 epoch 9 - iter 72/121 - loss 0.42455413 - time (sec): 1.65 - samples/sec: 8842.75 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:43:26,636 epoch 9 - iter 84/121 - loss 0.41215450 - time (sec): 1.93 - samples/sec: 8963.72 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:43:26,915 epoch 9 - iter 96/121 - loss 0.41780934 - time (sec): 2.21 - samples/sec: 8914.43 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:43:27,191 epoch 9 - iter 108/121 - loss 0.41478210 - time (sec): 2.48 - samples/sec: 8885.11 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:43:27,482 epoch 9 - iter 120/121 - loss 0.41979945 - time (sec): 2.77 - samples/sec: 8836.42 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:43:27,503 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:27,503 EPOCH 9 done: loss 0.4203 - lr: 0.000004 | |
| 2023-10-18 16:43:27,933 DEV : loss 0.3431694507598877 - f1-score (micro avg) 0.4352 | |
| 2023-10-18 16:43:27,938 saving best model | |
| 2023-10-18 16:43:27,972 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:28,249 epoch 10 - iter 12/121 - loss 0.42365815 - time (sec): 0.28 - samples/sec: 8805.21 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:43:28,521 epoch 10 - iter 24/121 - loss 0.38236089 - time (sec): 0.55 - samples/sec: 8656.51 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:43:28,790 epoch 10 - iter 36/121 - loss 0.41234823 - time (sec): 0.82 - samples/sec: 8795.10 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:43:29,068 epoch 10 - iter 48/121 - loss 0.41965928 - time (sec): 1.10 - samples/sec: 8730.70 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 16:43:29,331 epoch 10 - iter 60/121 - loss 0.40211273 - time (sec): 1.36 - samples/sec: 8603.41 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 16:43:29,603 epoch 10 - iter 72/121 - loss 0.41324752 - time (sec): 1.63 - samples/sec: 8790.83 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 16:43:29,868 epoch 10 - iter 84/121 - loss 0.42482985 - time (sec): 1.90 - samples/sec: 8850.53 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 16:43:30,147 epoch 10 - iter 96/121 - loss 0.42632763 - time (sec): 2.17 - samples/sec: 8980.02 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 16:43:30,429 epoch 10 - iter 108/121 - loss 0.41944164 - time (sec): 2.46 - samples/sec: 8938.28 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 16:43:30,706 epoch 10 - iter 120/121 - loss 0.41403093 - time (sec): 2.73 - samples/sec: 8986.60 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-18 16:43:30,725 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:30,725 EPOCH 10 done: loss 0.4125 - lr: 0.000000 | |
| 2023-10-18 16:43:31,154 DEV : loss 0.3414144515991211 - f1-score (micro avg) 0.4372 | |
| 2023-10-18 16:43:31,158 saving best model | |
| 2023-10-18 16:43:31,217 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:43:31,218 Loading model from best epoch ... | |
| 2023-10-18 16:43:31,420 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date | |
| 2023-10-18 16:43:31,695 | |
| Results: | |
| - F-score (micro) 0.3969 | |
| - F-score (macro) 0.1862 | |
| - Accuracy 0.2566 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.4012 0.5039 0.4467 129 | |
| pers 0.5398 0.4388 0.4841 139 | |
| work 0.0000 0.0000 0.0000 80 | |
| loc 0.0000 0.0000 0.0000 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.4582 0.3500 0.3969 360 | |
| macro avg 0.1882 0.1885 0.1862 360 | |
| weighted avg 0.3522 0.3500 0.3470 360 | |
| 2023-10-18 16:43:31,695 ---------------------------------------------------------------------------------------------------- | |