| 2023-10-17 08:42:21,127 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:21,128 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): ElectraModel( | |
| (embeddings): ElectraEmbeddings( | |
| (word_embeddings): Embedding(32001, 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): ElectraEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x ElectraLayer( | |
| (attention): ElectraAttention( | |
| (self): ElectraSelfAttention( | |
| (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): ElectraSelfOutput( | |
| (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): ElectraIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): ElectraOutput( | |
| (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) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 08:42:21,128 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:21,128 MultiCorpus: 1100 train + 206 dev + 240 test sentences | |
| - NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator | |
| 2023-10-17 08:42:21,128 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:21,128 Train: 1100 sentences | |
| 2023-10-17 08:42:21,128 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 08:42:21,128 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:21,128 Training Params: | |
| 2023-10-17 08:42:21,128 - learning_rate: "3e-05" | |
| 2023-10-17 08:42:21,128 - mini_batch_size: "8" | |
| 2023-10-17 08:42:21,128 - max_epochs: "10" | |
| 2023-10-17 08:42:21,128 - shuffle: "True" | |
| 2023-10-17 08:42:21,128 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:21,128 Plugins: | |
| 2023-10-17 08:42:21,128 - TensorboardLogger | |
| 2023-10-17 08:42:21,128 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 08:42:21,129 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:21,129 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 08:42:21,129 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 08:42:21,129 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:21,129 Computation: | |
| 2023-10-17 08:42:21,129 - compute on device: cuda:0 | |
| 2023-10-17 08:42:21,129 - embedding storage: none | |
| 2023-10-17 08:42:21,129 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:21,129 Model training base path: "hmbench-ajmc/de-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-17 08:42:21,129 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:21,129 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:21,129 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 08:42:21,854 epoch 1 - iter 13/138 - loss 4.31476014 - time (sec): 0.72 - samples/sec: 2822.79 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 08:42:22,585 epoch 1 - iter 26/138 - loss 3.99737249 - time (sec): 1.46 - samples/sec: 2930.89 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 08:42:23,343 epoch 1 - iter 39/138 - loss 3.46571797 - time (sec): 2.21 - samples/sec: 2931.13 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 08:42:24,037 epoch 1 - iter 52/138 - loss 2.97126875 - time (sec): 2.91 - samples/sec: 2895.72 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 08:42:24,775 epoch 1 - iter 65/138 - loss 2.52941175 - time (sec): 3.65 - samples/sec: 2933.74 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 08:42:25,510 epoch 1 - iter 78/138 - loss 2.22775214 - time (sec): 4.38 - samples/sec: 2956.81 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 08:42:26,212 epoch 1 - iter 91/138 - loss 2.00794585 - time (sec): 5.08 - samples/sec: 2945.08 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 08:42:26,932 epoch 1 - iter 104/138 - loss 1.82609979 - time (sec): 5.80 - samples/sec: 2942.98 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 08:42:27,693 epoch 1 - iter 117/138 - loss 1.65615108 - time (sec): 6.56 - samples/sec: 2958.80 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 08:42:28,452 epoch 1 - iter 130/138 - loss 1.53558847 - time (sec): 7.32 - samples/sec: 2933.68 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 08:42:28,905 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:28,905 EPOCH 1 done: loss 1.4683 - lr: 0.000028 | |
| 2023-10-17 08:42:29,700 DEV : loss 0.2522817850112915 - f1-score (micro avg) 0.6919 | |
| 2023-10-17 08:42:29,704 saving best model | |
| 2023-10-17 08:42:30,038 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:30,752 epoch 2 - iter 13/138 - loss 0.39445211 - time (sec): 0.71 - samples/sec: 2967.78 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 08:42:31,490 epoch 2 - iter 26/138 - loss 0.31336558 - time (sec): 1.45 - samples/sec: 3003.11 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 08:42:32,240 epoch 2 - iter 39/138 - loss 0.28236782 - time (sec): 2.20 - samples/sec: 3031.48 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 08:42:32,985 epoch 2 - iter 52/138 - loss 0.26422656 - time (sec): 2.95 - samples/sec: 2983.42 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 08:42:33,782 epoch 2 - iter 65/138 - loss 0.26519379 - time (sec): 3.74 - samples/sec: 2953.62 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 08:42:34,539 epoch 2 - iter 78/138 - loss 0.25129620 - time (sec): 4.50 - samples/sec: 2912.26 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 08:42:35,269 epoch 2 - iter 91/138 - loss 0.23968809 - time (sec): 5.23 - samples/sec: 2941.67 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 08:42:35,988 epoch 2 - iter 104/138 - loss 0.22788837 - time (sec): 5.95 - samples/sec: 2936.99 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 08:42:36,700 epoch 2 - iter 117/138 - loss 0.21926415 - time (sec): 6.66 - samples/sec: 2917.77 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 08:42:37,412 epoch 2 - iter 130/138 - loss 0.21617202 - time (sec): 7.37 - samples/sec: 2935.11 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 08:42:37,831 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:37,832 EPOCH 2 done: loss 0.2122 - lr: 0.000027 | |
| 2023-10-17 08:42:38,471 DEV : loss 0.136094868183136 - f1-score (micro avg) 0.8052 | |
| 2023-10-17 08:42:38,476 saving best model | |
| 2023-10-17 08:42:38,947 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:39,747 epoch 3 - iter 13/138 - loss 0.12316564 - time (sec): 0.80 - samples/sec: 2961.87 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 08:42:40,544 epoch 3 - iter 26/138 - loss 0.12404480 - time (sec): 1.59 - samples/sec: 2897.14 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 08:42:41,287 epoch 3 - iter 39/138 - loss 0.11480159 - time (sec): 2.34 - samples/sec: 2870.19 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 08:42:42,102 epoch 3 - iter 52/138 - loss 0.10695535 - time (sec): 3.15 - samples/sec: 2891.91 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 08:42:42,815 epoch 3 - iter 65/138 - loss 0.10494999 - time (sec): 3.86 - samples/sec: 2863.59 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 08:42:43,531 epoch 3 - iter 78/138 - loss 0.10362754 - time (sec): 4.58 - samples/sec: 2879.58 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 08:42:44,296 epoch 3 - iter 91/138 - loss 0.10209598 - time (sec): 5.34 - samples/sec: 2860.32 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 08:42:45,073 epoch 3 - iter 104/138 - loss 0.10776742 - time (sec): 6.12 - samples/sec: 2872.03 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 08:42:45,788 epoch 3 - iter 117/138 - loss 0.11182793 - time (sec): 6.84 - samples/sec: 2878.32 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 08:42:46,490 epoch 3 - iter 130/138 - loss 0.11110087 - time (sec): 7.54 - samples/sec: 2867.79 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 08:42:46,940 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:46,940 EPOCH 3 done: loss 0.1114 - lr: 0.000024 | |
| 2023-10-17 08:42:47,585 DEV : loss 0.12306556105613708 - f1-score (micro avg) 0.8431 | |
| 2023-10-17 08:42:47,590 saving best model | |
| 2023-10-17 08:42:48,050 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:48,811 epoch 4 - iter 13/138 - loss 0.05055908 - time (sec): 0.76 - samples/sec: 2724.33 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 08:42:49,564 epoch 4 - iter 26/138 - loss 0.05999714 - time (sec): 1.51 - samples/sec: 2828.24 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 08:42:50,280 epoch 4 - iter 39/138 - loss 0.05952242 - time (sec): 2.23 - samples/sec: 2871.72 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 08:42:50,984 epoch 4 - iter 52/138 - loss 0.06306300 - time (sec): 2.93 - samples/sec: 2866.76 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 08:42:51,754 epoch 4 - iter 65/138 - loss 0.06470110 - time (sec): 3.70 - samples/sec: 2837.97 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 08:42:52,548 epoch 4 - iter 78/138 - loss 0.06501672 - time (sec): 4.50 - samples/sec: 2825.94 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 08:42:53,350 epoch 4 - iter 91/138 - loss 0.06752019 - time (sec): 5.30 - samples/sec: 2775.42 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 08:42:54,145 epoch 4 - iter 104/138 - loss 0.07386768 - time (sec): 6.09 - samples/sec: 2779.40 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 08:42:54,901 epoch 4 - iter 117/138 - loss 0.07854490 - time (sec): 6.85 - samples/sec: 2807.45 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 08:42:55,673 epoch 4 - iter 130/138 - loss 0.07735127 - time (sec): 7.62 - samples/sec: 2809.91 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 08:42:56,131 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:56,131 EPOCH 4 done: loss 0.0774 - lr: 0.000020 | |
| 2023-10-17 08:42:56,770 DEV : loss 0.14901405572891235 - f1-score (micro avg) 0.8304 | |
| 2023-10-17 08:42:56,775 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:42:57,533 epoch 5 - iter 13/138 - loss 0.10503772 - time (sec): 0.76 - samples/sec: 2952.98 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 08:42:58,295 epoch 5 - iter 26/138 - loss 0.09279653 - time (sec): 1.52 - samples/sec: 2921.06 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 08:42:59,018 epoch 5 - iter 39/138 - loss 0.07298891 - time (sec): 2.24 - samples/sec: 2948.60 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 08:42:59,711 epoch 5 - iter 52/138 - loss 0.07392072 - time (sec): 2.94 - samples/sec: 2922.49 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 08:43:00,441 epoch 5 - iter 65/138 - loss 0.07282703 - time (sec): 3.67 - samples/sec: 2970.36 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 08:43:01,168 epoch 5 - iter 78/138 - loss 0.07389848 - time (sec): 4.39 - samples/sec: 2972.00 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 08:43:01,978 epoch 5 - iter 91/138 - loss 0.06807313 - time (sec): 5.20 - samples/sec: 2917.85 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 08:43:02,766 epoch 5 - iter 104/138 - loss 0.06382031 - time (sec): 5.99 - samples/sec: 2909.59 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 08:43:03,521 epoch 5 - iter 117/138 - loss 0.06016507 - time (sec): 6.75 - samples/sec: 2893.37 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 08:43:04,311 epoch 5 - iter 130/138 - loss 0.05932611 - time (sec): 7.54 - samples/sec: 2870.69 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 08:43:04,750 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:04,750 EPOCH 5 done: loss 0.0591 - lr: 0.000017 | |
| 2023-10-17 08:43:05,392 DEV : loss 0.15867365896701813 - f1-score (micro avg) 0.8663 | |
| 2023-10-17 08:43:05,397 saving best model | |
| 2023-10-17 08:43:05,841 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:06,631 epoch 6 - iter 13/138 - loss 0.03829507 - time (sec): 0.79 - samples/sec: 2752.05 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 08:43:07,383 epoch 6 - iter 26/138 - loss 0.05233246 - time (sec): 1.54 - samples/sec: 2815.67 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 08:43:08,106 epoch 6 - iter 39/138 - loss 0.05500890 - time (sec): 2.26 - samples/sec: 2804.30 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 08:43:08,867 epoch 6 - iter 52/138 - loss 0.06415862 - time (sec): 3.02 - samples/sec: 2766.27 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 08:43:09,681 epoch 6 - iter 65/138 - loss 0.06291998 - time (sec): 3.84 - samples/sec: 2753.15 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 08:43:10,420 epoch 6 - iter 78/138 - loss 0.06174305 - time (sec): 4.58 - samples/sec: 2767.71 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 08:43:11,167 epoch 6 - iter 91/138 - loss 0.05728193 - time (sec): 5.32 - samples/sec: 2803.18 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 08:43:11,892 epoch 6 - iter 104/138 - loss 0.05798844 - time (sec): 6.05 - samples/sec: 2822.09 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 08:43:12,608 epoch 6 - iter 117/138 - loss 0.05304937 - time (sec): 6.77 - samples/sec: 2842.70 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 08:43:13,312 epoch 6 - iter 130/138 - loss 0.04993011 - time (sec): 7.47 - samples/sec: 2861.13 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 08:43:13,767 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:13,767 EPOCH 6 done: loss 0.0482 - lr: 0.000014 | |
| 2023-10-17 08:43:14,526 DEV : loss 0.15685421228408813 - f1-score (micro avg) 0.8726 | |
| 2023-10-17 08:43:14,534 saving best model | |
| 2023-10-17 08:43:15,003 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:15,765 epoch 7 - iter 13/138 - loss 0.04983007 - time (sec): 0.76 - samples/sec: 2870.19 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 08:43:16,502 epoch 7 - iter 26/138 - loss 0.03475219 - time (sec): 1.50 - samples/sec: 2922.14 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 08:43:17,208 epoch 7 - iter 39/138 - loss 0.02886498 - time (sec): 2.20 - samples/sec: 2866.18 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 08:43:17,935 epoch 7 - iter 52/138 - loss 0.03425018 - time (sec): 2.93 - samples/sec: 2857.08 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 08:43:18,753 epoch 7 - iter 65/138 - loss 0.03508862 - time (sec): 3.75 - samples/sec: 2876.50 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 08:43:19,501 epoch 7 - iter 78/138 - loss 0.03460306 - time (sec): 4.50 - samples/sec: 2885.39 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 08:43:20,267 epoch 7 - iter 91/138 - loss 0.04045553 - time (sec): 5.26 - samples/sec: 2871.82 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 08:43:21,025 epoch 7 - iter 104/138 - loss 0.03864251 - time (sec): 6.02 - samples/sec: 2881.57 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 08:43:21,815 epoch 7 - iter 117/138 - loss 0.03835696 - time (sec): 6.81 - samples/sec: 2859.21 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 08:43:22,568 epoch 7 - iter 130/138 - loss 0.03546041 - time (sec): 7.56 - samples/sec: 2858.15 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 08:43:23,012 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:23,013 EPOCH 7 done: loss 0.0374 - lr: 0.000010 | |
| 2023-10-17 08:43:23,696 DEV : loss 0.1706576645374298 - f1-score (micro avg) 0.8746 | |
| 2023-10-17 08:43:23,701 saving best model | |
| 2023-10-17 08:43:24,170 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:24,890 epoch 8 - iter 13/138 - loss 0.04044336 - time (sec): 0.72 - samples/sec: 2954.77 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 08:43:25,595 epoch 8 - iter 26/138 - loss 0.04068421 - time (sec): 1.42 - samples/sec: 2910.51 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 08:43:26,364 epoch 8 - iter 39/138 - loss 0.03132897 - time (sec): 2.19 - samples/sec: 2968.84 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 08:43:27,124 epoch 8 - iter 52/138 - loss 0.03476643 - time (sec): 2.95 - samples/sec: 2983.94 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 08:43:27,854 epoch 8 - iter 65/138 - loss 0.03209124 - time (sec): 3.68 - samples/sec: 2975.53 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 08:43:28,581 epoch 8 - iter 78/138 - loss 0.02808534 - time (sec): 4.41 - samples/sec: 2898.24 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 08:43:29,414 epoch 8 - iter 91/138 - loss 0.02747617 - time (sec): 5.24 - samples/sec: 2868.84 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 08:43:30,156 epoch 8 - iter 104/138 - loss 0.02860915 - time (sec): 5.98 - samples/sec: 2873.78 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 08:43:30,922 epoch 8 - iter 117/138 - loss 0.02787707 - time (sec): 6.75 - samples/sec: 2866.47 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 08:43:31,694 epoch 8 - iter 130/138 - loss 0.02708359 - time (sec): 7.52 - samples/sec: 2869.82 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 08:43:32,173 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:32,174 EPOCH 8 done: loss 0.0308 - lr: 0.000007 | |
| 2023-10-17 08:43:32,905 DEV : loss 0.17330265045166016 - f1-score (micro avg) 0.8661 | |
| 2023-10-17 08:43:32,910 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:33,643 epoch 9 - iter 13/138 - loss 0.02820571 - time (sec): 0.73 - samples/sec: 2936.12 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 08:43:34,431 epoch 9 - iter 26/138 - loss 0.02520018 - time (sec): 1.52 - samples/sec: 2972.56 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 08:43:35,190 epoch 9 - iter 39/138 - loss 0.02441085 - time (sec): 2.28 - samples/sec: 2891.07 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 08:43:35,896 epoch 9 - iter 52/138 - loss 0.02435248 - time (sec): 2.98 - samples/sec: 2863.14 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 08:43:36,616 epoch 9 - iter 65/138 - loss 0.02335632 - time (sec): 3.70 - samples/sec: 2920.26 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 08:43:37,389 epoch 9 - iter 78/138 - loss 0.02123109 - time (sec): 4.48 - samples/sec: 2911.98 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 08:43:38,114 epoch 9 - iter 91/138 - loss 0.02707885 - time (sec): 5.20 - samples/sec: 2895.11 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 08:43:38,898 epoch 9 - iter 104/138 - loss 0.02630153 - time (sec): 5.99 - samples/sec: 2870.94 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 08:43:39,652 epoch 9 - iter 117/138 - loss 0.02613663 - time (sec): 6.74 - samples/sec: 2860.56 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 08:43:40,373 epoch 9 - iter 130/138 - loss 0.02550976 - time (sec): 7.46 - samples/sec: 2873.67 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 08:43:40,843 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:40,843 EPOCH 9 done: loss 0.0251 - lr: 0.000004 | |
| 2023-10-17 08:43:41,569 DEV : loss 0.1836317479610443 - f1-score (micro avg) 0.8647 | |
| 2023-10-17 08:43:41,575 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:42,423 epoch 10 - iter 13/138 - loss 0.07535736 - time (sec): 0.85 - samples/sec: 2942.71 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 08:43:43,239 epoch 10 - iter 26/138 - loss 0.04941656 - time (sec): 1.66 - samples/sec: 2869.99 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 08:43:44,018 epoch 10 - iter 39/138 - loss 0.03775050 - time (sec): 2.44 - samples/sec: 2892.56 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 08:43:44,741 epoch 10 - iter 52/138 - loss 0.03160067 - time (sec): 3.17 - samples/sec: 2879.64 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 08:43:45,499 epoch 10 - iter 65/138 - loss 0.02873357 - time (sec): 3.92 - samples/sec: 2867.65 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 08:43:46,216 epoch 10 - iter 78/138 - loss 0.02560839 - time (sec): 4.64 - samples/sec: 2850.88 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 08:43:47,024 epoch 10 - iter 91/138 - loss 0.02344188 - time (sec): 5.45 - samples/sec: 2811.68 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 08:43:47,760 epoch 10 - iter 104/138 - loss 0.02289610 - time (sec): 6.18 - samples/sec: 2784.60 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 08:43:48,548 epoch 10 - iter 117/138 - loss 0.02234587 - time (sec): 6.97 - samples/sec: 2784.35 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 08:43:49,279 epoch 10 - iter 130/138 - loss 0.02359775 - time (sec): 7.70 - samples/sec: 2803.45 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 08:43:49,752 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:49,752 EPOCH 10 done: loss 0.0228 - lr: 0.000000 | |
| 2023-10-17 08:43:50,613 DEV : loss 0.18878225982189178 - f1-score (micro avg) 0.865 | |
| 2023-10-17 08:43:50,969 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 08:43:50,970 Loading model from best epoch ... | |
| 2023-10-17 08:43:52,371 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 | |
| 2023-10-17 08:43:52,997 | |
| Results: | |
| - F-score (micro) 0.9089 | |
| - F-score (macro) 0.6788 | |
| - Accuracy 0.841 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.9091 0.9091 0.9091 176 | |
| pers 0.9124 0.9766 0.9434 128 | |
| work 0.9000 0.8514 0.8750 74 | |
| object 0.0000 0.0000 0.0000 2 | |
| loc 1.0000 0.5000 0.6667 2 | |
| micro avg 0.9041 0.9136 0.9089 382 | |
| macro avg 0.7443 0.6474 0.6788 382 | |
| weighted avg 0.9042 0.9136 0.9080 382 | |
| 2023-10-17 08:43:52,997 ---------------------------------------------------------------------------------------------------- | |