| 2023-10-18 16:14:19,586 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:19,586 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 16:14:19,586 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:19,586 MultiCorpus: 1214 train + 266 dev + 251 test sentences | |
| - NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator | |
| 2023-10-18 16:14:19,586 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:19,586 Train: 1214 sentences | |
| 2023-10-18 16:14:19,586 (train_with_dev=False, train_with_test=False) | |
| 2023-10-18 16:14:19,587 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:19,587 Training Params: | |
| 2023-10-18 16:14:19,587 - learning_rate: "3e-05" | |
| 2023-10-18 16:14:19,587 - mini_batch_size: "8" | |
| 2023-10-18 16:14:19,587 - max_epochs: "10" | |
| 2023-10-18 16:14:19,587 - shuffle: "True" | |
| 2023-10-18 16:14:19,587 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:19,587 Plugins: | |
| 2023-10-18 16:14:19,587 - TensorboardLogger | |
| 2023-10-18 16:14:19,587 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-18 16:14:19,587 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:19,587 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-18 16:14:19,587 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-18 16:14:19,587 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:19,587 Computation: | |
| 2023-10-18 16:14:19,587 - compute on device: cuda:0 | |
| 2023-10-18 16:14:19,587 - embedding storage: none | |
| 2023-10-18 16:14:19,587 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:19,587 Model training base path: "hmbench-ajmc/en-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-18 16:14:19,587 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:19,587 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:19,587 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-18 16:14:19,950 epoch 1 - iter 15/152 - loss 3.70740706 - time (sec): 0.36 - samples/sec: 7989.31 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:14:20,276 epoch 1 - iter 30/152 - loss 3.70891912 - time (sec): 0.69 - samples/sec: 8657.50 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:14:20,606 epoch 1 - iter 45/152 - loss 3.64714283 - time (sec): 1.02 - samples/sec: 8773.49 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:14:20,941 epoch 1 - iter 60/152 - loss 3.59271918 - time (sec): 1.35 - samples/sec: 8885.18 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:14:21,274 epoch 1 - iter 75/152 - loss 3.50024596 - time (sec): 1.69 - samples/sec: 9061.70 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:14:21,603 epoch 1 - iter 90/152 - loss 3.36782693 - time (sec): 2.02 - samples/sec: 9183.48 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:14:21,945 epoch 1 - iter 105/152 - loss 3.20758430 - time (sec): 2.36 - samples/sec: 9187.99 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:14:22,269 epoch 1 - iter 120/152 - loss 3.05292876 - time (sec): 2.68 - samples/sec: 9155.76 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 16:14:22,618 epoch 1 - iter 135/152 - loss 2.89385963 - time (sec): 3.03 - samples/sec: 9062.92 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:14:22,951 epoch 1 - iter 150/152 - loss 2.72722874 - time (sec): 3.36 - samples/sec: 9116.95 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:14:22,994 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:22,994 EPOCH 1 done: loss 2.7120 - lr: 0.000029 | |
| 2023-10-18 16:14:23,322 DEV : loss 0.8151066899299622 - f1-score (micro avg) 0.0 | |
| 2023-10-18 16:14:23,327 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:23,664 epoch 2 - iter 15/152 - loss 1.04272481 - time (sec): 0.34 - samples/sec: 9259.11 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 16:14:23,990 epoch 2 - iter 30/152 - loss 0.95691556 - time (sec): 0.66 - samples/sec: 9084.69 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:14:24,315 epoch 2 - iter 45/152 - loss 0.91316865 - time (sec): 0.99 - samples/sec: 9371.74 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:14:24,651 epoch 2 - iter 60/152 - loss 0.91248910 - time (sec): 1.32 - samples/sec: 9303.44 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:14:24,985 epoch 2 - iter 75/152 - loss 0.89845409 - time (sec): 1.66 - samples/sec: 9311.66 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 16:14:25,300 epoch 2 - iter 90/152 - loss 0.88716995 - time (sec): 1.97 - samples/sec: 9533.46 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 16:14:25,637 epoch 2 - iter 105/152 - loss 0.84976950 - time (sec): 2.31 - samples/sec: 9466.16 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 16:14:25,972 epoch 2 - iter 120/152 - loss 0.83046703 - time (sec): 2.64 - samples/sec: 9250.73 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:14:26,291 epoch 2 - iter 135/152 - loss 0.82753683 - time (sec): 2.96 - samples/sec: 9285.14 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:14:26,613 epoch 2 - iter 150/152 - loss 0.81527989 - time (sec): 3.29 - samples/sec: 9323.40 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:14:26,657 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:26,657 EPOCH 2 done: loss 0.8136 - lr: 0.000027 | |
| 2023-10-18 16:14:27,152 DEV : loss 0.6542724370956421 - f1-score (micro avg) 0.0 | |
| 2023-10-18 16:14:27,157 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:27,480 epoch 3 - iter 15/152 - loss 0.66380491 - time (sec): 0.32 - samples/sec: 9317.53 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:14:27,817 epoch 3 - iter 30/152 - loss 0.71312012 - time (sec): 0.66 - samples/sec: 9379.54 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:14:28,136 epoch 3 - iter 45/152 - loss 0.66878033 - time (sec): 0.98 - samples/sec: 9304.53 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:14:28,489 epoch 3 - iter 60/152 - loss 0.67676228 - time (sec): 1.33 - samples/sec: 9301.62 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 16:14:28,842 epoch 3 - iter 75/152 - loss 0.66316423 - time (sec): 1.68 - samples/sec: 9339.81 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 16:14:29,200 epoch 3 - iter 90/152 - loss 0.65454872 - time (sec): 2.04 - samples/sec: 9173.50 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 16:14:29,545 epoch 3 - iter 105/152 - loss 0.63681589 - time (sec): 2.39 - samples/sec: 9124.69 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:14:29,899 epoch 3 - iter 120/152 - loss 0.62456123 - time (sec): 2.74 - samples/sec: 9031.75 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:14:30,257 epoch 3 - iter 135/152 - loss 0.60695594 - time (sec): 3.10 - samples/sec: 9009.89 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:14:30,585 epoch 3 - iter 150/152 - loss 0.60126758 - time (sec): 3.43 - samples/sec: 8934.86 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 16:14:30,626 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:30,627 EPOCH 3 done: loss 0.5995 - lr: 0.000023 | |
| 2023-10-18 16:14:31,122 DEV : loss 0.47917139530181885 - f1-score (micro avg) 0.0041 | |
| 2023-10-18 16:14:31,127 saving best model | |
| 2023-10-18 16:14:31,160 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:31,487 epoch 4 - iter 15/152 - loss 0.55870288 - time (sec): 0.33 - samples/sec: 10231.76 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 16:14:31,805 epoch 4 - iter 30/152 - loss 0.59119756 - time (sec): 0.64 - samples/sec: 9546.87 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 16:14:32,286 epoch 4 - iter 45/152 - loss 0.53257898 - time (sec): 1.12 - samples/sec: 8394.70 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 16:14:32,616 epoch 4 - iter 60/152 - loss 0.53039907 - time (sec): 1.46 - samples/sec: 8428.69 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 16:14:32,958 epoch 4 - iter 75/152 - loss 0.53955919 - time (sec): 1.80 - samples/sec: 8640.88 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 16:14:33,290 epoch 4 - iter 90/152 - loss 0.51870706 - time (sec): 2.13 - samples/sec: 8760.09 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:14:33,607 epoch 4 - iter 105/152 - loss 0.50971416 - time (sec): 2.45 - samples/sec: 8968.46 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:14:33,942 epoch 4 - iter 120/152 - loss 0.50708301 - time (sec): 2.78 - samples/sec: 8988.34 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:14:34,257 epoch 4 - iter 135/152 - loss 0.50197658 - time (sec): 3.10 - samples/sec: 8963.27 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 16:14:34,580 epoch 4 - iter 150/152 - loss 0.49393271 - time (sec): 3.42 - samples/sec: 8961.06 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 16:14:34,628 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:34,629 EPOCH 4 done: loss 0.4940 - lr: 0.000020 | |
| 2023-10-18 16:14:35,141 DEV : loss 0.3989596664905548 - f1-score (micro avg) 0.245 | |
| 2023-10-18 16:14:35,147 saving best model | |
| 2023-10-18 16:14:35,193 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:35,520 epoch 5 - iter 15/152 - loss 0.46136293 - time (sec): 0.33 - samples/sec: 9427.18 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 16:14:35,882 epoch 5 - iter 30/152 - loss 0.47353895 - time (sec): 0.69 - samples/sec: 9220.21 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:14:36,219 epoch 5 - iter 45/152 - loss 0.48635178 - time (sec): 1.03 - samples/sec: 9575.75 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:14:36,532 epoch 5 - iter 60/152 - loss 0.46696894 - time (sec): 1.34 - samples/sec: 9650.20 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:14:36,857 epoch 5 - iter 75/152 - loss 0.44269793 - time (sec): 1.66 - samples/sec: 9544.65 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:14:37,185 epoch 5 - iter 90/152 - loss 0.45211746 - time (sec): 1.99 - samples/sec: 9421.92 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:14:37,521 epoch 5 - iter 105/152 - loss 0.44843539 - time (sec): 2.33 - samples/sec: 9392.83 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:14:37,875 epoch 5 - iter 120/152 - loss 0.44558332 - time (sec): 2.68 - samples/sec: 9223.79 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 16:14:38,226 epoch 5 - iter 135/152 - loss 0.43892253 - time (sec): 3.03 - samples/sec: 9087.19 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 16:14:38,584 epoch 5 - iter 150/152 - loss 0.43735788 - time (sec): 3.39 - samples/sec: 9025.35 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 16:14:38,627 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:38,627 EPOCH 5 done: loss 0.4350 - lr: 0.000017 | |
| 2023-10-18 16:14:39,137 DEV : loss 0.37336358428001404 - f1-score (micro avg) 0.3385 | |
| 2023-10-18 16:14:39,142 saving best model | |
| 2023-10-18 16:14:39,177 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:39,525 epoch 6 - iter 15/152 - loss 0.38909019 - time (sec): 0.35 - samples/sec: 8400.17 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 16:14:39,875 epoch 6 - iter 30/152 - loss 0.40703602 - time (sec): 0.70 - samples/sec: 8398.89 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 16:14:40,201 epoch 6 - iter 45/152 - loss 0.41827443 - time (sec): 1.02 - samples/sec: 8718.18 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 16:14:40,528 epoch 6 - iter 60/152 - loss 0.40297375 - time (sec): 1.35 - samples/sec: 8841.87 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:14:40,860 epoch 6 - iter 75/152 - loss 0.41614379 - time (sec): 1.68 - samples/sec: 9079.98 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:14:41,194 epoch 6 - iter 90/152 - loss 0.42604386 - time (sec): 2.02 - samples/sec: 9144.37 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:14:41,530 epoch 6 - iter 105/152 - loss 0.41944796 - time (sec): 2.35 - samples/sec: 9068.61 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:14:41,850 epoch 6 - iter 120/152 - loss 0.41276481 - time (sec): 2.67 - samples/sec: 9046.06 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:14:42,208 epoch 6 - iter 135/152 - loss 0.40953834 - time (sec): 3.03 - samples/sec: 9057.84 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:14:42,539 epoch 6 - iter 150/152 - loss 0.40883256 - time (sec): 3.36 - samples/sec: 9126.22 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 16:14:42,576 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:42,576 EPOCH 6 done: loss 0.4106 - lr: 0.000013 | |
| 2023-10-18 16:14:43,090 DEV : loss 0.3582286834716797 - f1-score (micro avg) 0.3661 | |
| 2023-10-18 16:14:43,095 saving best model | |
| 2023-10-18 16:14:43,128 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:43,489 epoch 7 - iter 15/152 - loss 0.36878538 - time (sec): 0.36 - samples/sec: 8297.34 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 16:14:43,844 epoch 7 - iter 30/152 - loss 0.37324167 - time (sec): 0.72 - samples/sec: 8516.14 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 16:14:44,161 epoch 7 - iter 45/152 - loss 0.39895662 - time (sec): 1.03 - samples/sec: 8596.00 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:14:44,508 epoch 7 - iter 60/152 - loss 0.38077778 - time (sec): 1.38 - samples/sec: 8568.20 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:14:44,860 epoch 7 - iter 75/152 - loss 0.37998547 - time (sec): 1.73 - samples/sec: 8621.10 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:14:45,217 epoch 7 - iter 90/152 - loss 0.37443302 - time (sec): 2.09 - samples/sec: 8701.48 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 16:14:45,550 epoch 7 - iter 105/152 - loss 0.36700582 - time (sec): 2.42 - samples/sec: 8829.17 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 16:14:45,873 epoch 7 - iter 120/152 - loss 0.37341692 - time (sec): 2.74 - samples/sec: 8864.26 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 16:14:46,195 epoch 7 - iter 135/152 - loss 0.37635494 - time (sec): 3.07 - samples/sec: 8949.42 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:14:46,522 epoch 7 - iter 150/152 - loss 0.38600423 - time (sec): 3.39 - samples/sec: 9020.34 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:14:46,566 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:46,566 EPOCH 7 done: loss 0.3840 - lr: 0.000010 | |
| 2023-10-18 16:14:47,084 DEV : loss 0.34290459752082825 - f1-score (micro avg) 0.3953 | |
| 2023-10-18 16:14:47,089 saving best model | |
| 2023-10-18 16:14:47,122 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:47,470 epoch 8 - iter 15/152 - loss 0.46128735 - time (sec): 0.35 - samples/sec: 9163.93 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:14:47,786 epoch 8 - iter 30/152 - loss 0.41739483 - time (sec): 0.66 - samples/sec: 9663.44 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:14:48,109 epoch 8 - iter 45/152 - loss 0.36445950 - time (sec): 0.99 - samples/sec: 9623.26 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:14:48,431 epoch 8 - iter 60/152 - loss 0.36194631 - time (sec): 1.31 - samples/sec: 9343.92 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:14:48,752 epoch 8 - iter 75/152 - loss 0.35672477 - time (sec): 1.63 - samples/sec: 9396.72 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:14:49,074 epoch 8 - iter 90/152 - loss 0.35745362 - time (sec): 1.95 - samples/sec: 9388.06 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:14:49,418 epoch 8 - iter 105/152 - loss 0.35927087 - time (sec): 2.30 - samples/sec: 9365.21 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:14:49,768 epoch 8 - iter 120/152 - loss 0.35874584 - time (sec): 2.65 - samples/sec: 9281.51 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 16:14:50,099 epoch 8 - iter 135/152 - loss 0.36692959 - time (sec): 2.98 - samples/sec: 9253.37 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 16:14:50,445 epoch 8 - iter 150/152 - loss 0.36907541 - time (sec): 3.32 - samples/sec: 9211.67 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 16:14:50,490 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:50,490 EPOCH 8 done: loss 0.3703 - lr: 0.000007 | |
| 2023-10-18 16:14:51,007 DEV : loss 0.3377641439437866 - f1-score (micro avg) 0.3968 | |
| 2023-10-18 16:14:51,013 saving best model | |
| 2023-10-18 16:14:51,045 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:51,382 epoch 9 - iter 15/152 - loss 0.36902711 - time (sec): 0.34 - samples/sec: 9605.47 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:14:51,694 epoch 9 - iter 30/152 - loss 0.36172452 - time (sec): 0.65 - samples/sec: 9401.82 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:14:52,022 epoch 9 - iter 45/152 - loss 0.36103385 - time (sec): 0.98 - samples/sec: 9248.33 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:14:52,342 epoch 9 - iter 60/152 - loss 0.36296944 - time (sec): 1.30 - samples/sec: 9338.97 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:14:52,664 epoch 9 - iter 75/152 - loss 0.35951793 - time (sec): 1.62 - samples/sec: 9304.75 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:14:52,990 epoch 9 - iter 90/152 - loss 0.35382745 - time (sec): 1.94 - samples/sec: 9276.69 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:14:53,324 epoch 9 - iter 105/152 - loss 0.35352197 - time (sec): 2.28 - samples/sec: 9196.41 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:14:53,678 epoch 9 - iter 120/152 - loss 0.35354054 - time (sec): 2.63 - samples/sec: 9264.16 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:14:54,009 epoch 9 - iter 135/152 - loss 0.35497994 - time (sec): 2.96 - samples/sec: 9298.85 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:14:54,344 epoch 9 - iter 150/152 - loss 0.35835628 - time (sec): 3.30 - samples/sec: 9285.09 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:14:54,388 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:54,388 EPOCH 9 done: loss 0.3582 - lr: 0.000004 | |
| 2023-10-18 16:14:54,923 DEV : loss 0.32884225249290466 - f1-score (micro avg) 0.4068 | |
| 2023-10-18 16:14:54,929 saving best model | |
| 2023-10-18 16:14:54,961 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:55,293 epoch 10 - iter 15/152 - loss 0.33695965 - time (sec): 0.33 - samples/sec: 9035.58 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:14:55,642 epoch 10 - iter 30/152 - loss 0.35601442 - time (sec): 0.68 - samples/sec: 8904.69 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:14:55,990 epoch 10 - iter 45/152 - loss 0.35541243 - time (sec): 1.03 - samples/sec: 8716.71 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 16:14:56,335 epoch 10 - iter 60/152 - loss 0.35564157 - time (sec): 1.37 - samples/sec: 8687.94 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 16:14:56,666 epoch 10 - iter 75/152 - loss 0.35549319 - time (sec): 1.71 - samples/sec: 8899.60 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 16:14:57,002 epoch 10 - iter 90/152 - loss 0.35639063 - time (sec): 2.04 - samples/sec: 8972.96 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 16:14:57,320 epoch 10 - iter 105/152 - loss 0.35591624 - time (sec): 2.36 - samples/sec: 9034.10 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 16:14:57,657 epoch 10 - iter 120/152 - loss 0.35145120 - time (sec): 2.70 - samples/sec: 9030.47 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 16:14:58,008 epoch 10 - iter 135/152 - loss 0.35301827 - time (sec): 3.05 - samples/sec: 8972.59 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 16:14:58,366 epoch 10 - iter 150/152 - loss 0.36004132 - time (sec): 3.40 - samples/sec: 8953.55 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-18 16:14:58,410 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:58,410 EPOCH 10 done: loss 0.3603 - lr: 0.000000 | |
| 2023-10-18 16:14:58,927 DEV : loss 0.3272362947463989 - f1-score (micro avg) 0.4073 | |
| 2023-10-18 16:14:58,932 saving best model | |
| 2023-10-18 16:14:58,992 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:14:58,993 Loading model from best epoch ... | |
| 2023-10-18 16:14:59,079 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-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object | |
| 2023-10-18 16:14:59,570 | |
| Results: | |
| - F-score (micro) 0.4629 | |
| - F-score (macro) 0.2828 | |
| - Accuracy 0.3074 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.4393 0.5033 0.4691 151 | |
| work 0.3194 0.4842 0.3849 95 | |
| pers 0.5385 0.5833 0.5600 96 | |
| loc 0.0000 0.0000 0.0000 3 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.4228 0.5115 0.4629 348 | |
| macro avg 0.2594 0.3142 0.2828 348 | |
| weighted avg 0.4264 0.5115 0.4631 348 | |
| 2023-10-18 16:14:59,570 ---------------------------------------------------------------------------------------------------- | |