| 2023-10-17 18:52:00,708 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:52:00,710 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=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 18:52:00,710 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:52:00,710 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences | |
| - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator | |
| 2023-10-17 18:52:00,710 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:52:00,710 Train: 14465 sentences | |
| 2023-10-17 18:52:00,710 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 18:52:00,710 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:52:00,710 Training Params: | |
| 2023-10-17 18:52:00,710 - learning_rate: "3e-05" | |
| 2023-10-17 18:52:00,710 - mini_batch_size: "8" | |
| 2023-10-17 18:52:00,710 - max_epochs: "10" | |
| 2023-10-17 18:52:00,710 - shuffle: "True" | |
| 2023-10-17 18:52:00,710 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:52:00,710 Plugins: | |
| 2023-10-17 18:52:00,710 - TensorboardLogger | |
| 2023-10-17 18:52:00,711 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 18:52:00,711 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:52:00,711 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 18:52:00,711 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 18:52:00,711 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:52:00,711 Computation: | |
| 2023-10-17 18:52:00,711 - compute on device: cuda:0 | |
| 2023-10-17 18:52:00,711 - embedding storage: none | |
| 2023-10-17 18:52:00,711 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:52:00,711 Model training base path: "hmbench-letemps/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 18:52:00,711 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:52:00,711 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:52:00,711 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 18:52:13,715 epoch 1 - iter 180/1809 - loss 2.28258934 - time (sec): 13.00 - samples/sec: 2789.82 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:52:26,579 epoch 1 - iter 360/1809 - loss 1.24974822 - time (sec): 25.87 - samples/sec: 2901.45 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:52:39,333 epoch 1 - iter 540/1809 - loss 0.89210105 - time (sec): 38.62 - samples/sec: 2915.35 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:52:51,661 epoch 1 - iter 720/1809 - loss 0.71541122 - time (sec): 50.95 - samples/sec: 2906.71 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:53:04,504 epoch 1 - iter 900/1809 - loss 0.59767207 - time (sec): 63.79 - samples/sec: 2913.38 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:53:17,623 epoch 1 - iter 1080/1809 - loss 0.51371059 - time (sec): 76.91 - samples/sec: 2926.72 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:53:31,474 epoch 1 - iter 1260/1809 - loss 0.45457977 - time (sec): 90.76 - samples/sec: 2909.10 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:53:44,938 epoch 1 - iter 1440/1809 - loss 0.41231541 - time (sec): 104.23 - samples/sec: 2889.17 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:53:58,080 epoch 1 - iter 1620/1809 - loss 0.37675173 - time (sec): 117.37 - samples/sec: 2890.05 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:54:11,681 epoch 1 - iter 1800/1809 - loss 0.34914029 - time (sec): 130.97 - samples/sec: 2887.66 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:54:12,286 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:54:12,287 EPOCH 1 done: loss 0.3480 - lr: 0.000030 | |
| 2023-10-17 18:54:17,839 DEV : loss 0.10930902510881424 - f1-score (micro avg) 0.5978 | |
| 2023-10-17 18:54:17,881 saving best model | |
| 2023-10-17 18:54:18,405 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:54:30,964 epoch 2 - iter 180/1809 - loss 0.10650053 - time (sec): 12.56 - samples/sec: 2959.31 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:54:44,030 epoch 2 - iter 360/1809 - loss 0.09585977 - time (sec): 25.62 - samples/sec: 2997.96 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:54:57,016 epoch 2 - iter 540/1809 - loss 0.09384622 - time (sec): 38.61 - samples/sec: 2975.16 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:55:09,680 epoch 2 - iter 720/1809 - loss 0.09091547 - time (sec): 51.27 - samples/sec: 2959.73 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:55:22,557 epoch 2 - iter 900/1809 - loss 0.09225937 - time (sec): 64.15 - samples/sec: 2959.26 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:55:35,377 epoch 2 - iter 1080/1809 - loss 0.09010366 - time (sec): 76.97 - samples/sec: 2966.15 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:55:48,422 epoch 2 - iter 1260/1809 - loss 0.08952091 - time (sec): 90.02 - samples/sec: 2971.74 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:56:01,089 epoch 2 - iter 1440/1809 - loss 0.08943201 - time (sec): 102.68 - samples/sec: 2954.82 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:56:14,452 epoch 2 - iter 1620/1809 - loss 0.08793406 - time (sec): 116.05 - samples/sec: 2928.46 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:56:27,318 epoch 2 - iter 1800/1809 - loss 0.08729226 - time (sec): 128.91 - samples/sec: 2933.17 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:56:27,923 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:56:27,924 EPOCH 2 done: loss 0.0871 - lr: 0.000027 | |
| 2023-10-17 18:56:34,962 DEV : loss 0.12650814652442932 - f1-score (micro avg) 0.6702 | |
| 2023-10-17 18:56:35,002 saving best model | |
| 2023-10-17 18:56:35,614 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:56:48,417 epoch 3 - iter 180/1809 - loss 0.06478131 - time (sec): 12.80 - samples/sec: 2971.79 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:57:01,042 epoch 3 - iter 360/1809 - loss 0.06198826 - time (sec): 25.43 - samples/sec: 2962.13 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:57:13,921 epoch 3 - iter 540/1809 - loss 0.06502424 - time (sec): 38.30 - samples/sec: 2957.71 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:57:26,694 epoch 3 - iter 720/1809 - loss 0.06650593 - time (sec): 51.08 - samples/sec: 2945.63 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:57:39,977 epoch 3 - iter 900/1809 - loss 0.06659994 - time (sec): 64.36 - samples/sec: 2926.54 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:57:52,785 epoch 3 - iter 1080/1809 - loss 0.06578702 - time (sec): 77.17 - samples/sec: 2926.83 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:58:06,364 epoch 3 - iter 1260/1809 - loss 0.06364589 - time (sec): 90.75 - samples/sec: 2931.13 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:58:20,302 epoch 3 - iter 1440/1809 - loss 0.06291425 - time (sec): 104.69 - samples/sec: 2908.03 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:58:33,778 epoch 3 - iter 1620/1809 - loss 0.06208188 - time (sec): 118.16 - samples/sec: 2889.68 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:58:47,159 epoch 3 - iter 1800/1809 - loss 0.06263994 - time (sec): 131.54 - samples/sec: 2877.10 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:58:47,795 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:58:47,795 EPOCH 3 done: loss 0.0626 - lr: 0.000023 | |
| 2023-10-17 18:58:54,045 DEV : loss 0.12355589121580124 - f1-score (micro avg) 0.5872 | |
| 2023-10-17 18:58:54,085 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:59:07,267 epoch 4 - iter 180/1809 - loss 0.03666583 - time (sec): 13.18 - samples/sec: 2968.80 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:59:20,573 epoch 4 - iter 360/1809 - loss 0.04027279 - time (sec): 26.49 - samples/sec: 2843.54 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:59:34,773 epoch 4 - iter 540/1809 - loss 0.04343845 - time (sec): 40.69 - samples/sec: 2790.97 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:59:48,888 epoch 4 - iter 720/1809 - loss 0.04472054 - time (sec): 54.80 - samples/sec: 2765.20 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 19:00:02,898 epoch 4 - iter 900/1809 - loss 0.04626259 - time (sec): 68.81 - samples/sec: 2763.89 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 19:00:16,800 epoch 4 - iter 1080/1809 - loss 0.04635190 - time (sec): 82.71 - samples/sec: 2761.61 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 19:00:29,571 epoch 4 - iter 1260/1809 - loss 0.04645411 - time (sec): 95.48 - samples/sec: 2776.58 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 19:00:42,905 epoch 4 - iter 1440/1809 - loss 0.04596775 - time (sec): 108.82 - samples/sec: 2796.26 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 19:00:56,051 epoch 4 - iter 1620/1809 - loss 0.04613201 - time (sec): 121.96 - samples/sec: 2806.25 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 19:01:08,814 epoch 4 - iter 1800/1809 - loss 0.04664147 - time (sec): 134.73 - samples/sec: 2806.50 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 19:01:09,439 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:01:09,439 EPOCH 4 done: loss 0.0466 - lr: 0.000020 | |
| 2023-10-17 19:01:16,574 DEV : loss 0.20206163823604584 - f1-score (micro avg) 0.6504 | |
| 2023-10-17 19:01:16,614 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:01:29,149 epoch 5 - iter 180/1809 - loss 0.02937075 - time (sec): 12.53 - samples/sec: 2950.05 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 19:01:42,017 epoch 5 - iter 360/1809 - loss 0.03242653 - time (sec): 25.40 - samples/sec: 2946.71 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 19:01:54,818 epoch 5 - iter 540/1809 - loss 0.03272337 - time (sec): 38.20 - samples/sec: 2947.20 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 19:02:07,931 epoch 5 - iter 720/1809 - loss 0.03365088 - time (sec): 51.32 - samples/sec: 2943.60 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 19:02:20,754 epoch 5 - iter 900/1809 - loss 0.03447276 - time (sec): 64.14 - samples/sec: 2938.08 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 19:02:33,631 epoch 5 - iter 1080/1809 - loss 0.03437117 - time (sec): 77.02 - samples/sec: 2950.11 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 19:02:46,395 epoch 5 - iter 1260/1809 - loss 0.03449813 - time (sec): 89.78 - samples/sec: 2945.56 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 19:02:59,134 epoch 5 - iter 1440/1809 - loss 0.03583856 - time (sec): 102.52 - samples/sec: 2950.78 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 19:03:11,969 epoch 5 - iter 1620/1809 - loss 0.03533839 - time (sec): 115.35 - samples/sec: 2943.55 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 19:03:24,864 epoch 5 - iter 1800/1809 - loss 0.03477947 - time (sec): 128.25 - samples/sec: 2946.66 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 19:03:25,466 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:03:25,466 EPOCH 5 done: loss 0.0347 - lr: 0.000017 | |
| 2023-10-17 19:03:32,608 DEV : loss 0.26585522294044495 - f1-score (micro avg) 0.6403 | |
| 2023-10-17 19:03:32,648 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:03:45,303 epoch 6 - iter 180/1809 - loss 0.02901171 - time (sec): 12.65 - samples/sec: 2971.87 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 19:03:58,369 epoch 6 - iter 360/1809 - loss 0.02498842 - time (sec): 25.72 - samples/sec: 2950.77 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 19:04:11,132 epoch 6 - iter 540/1809 - loss 0.02262579 - time (sec): 38.48 - samples/sec: 2953.97 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 19:04:24,024 epoch 6 - iter 720/1809 - loss 0.02208957 - time (sec): 51.37 - samples/sec: 2960.86 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 19:04:37,341 epoch 6 - iter 900/1809 - loss 0.02333084 - time (sec): 64.69 - samples/sec: 2953.20 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 19:04:50,111 epoch 6 - iter 1080/1809 - loss 0.02330581 - time (sec): 77.46 - samples/sec: 2952.63 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 19:05:02,800 epoch 6 - iter 1260/1809 - loss 0.02337206 - time (sec): 90.15 - samples/sec: 2963.00 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 19:05:15,888 epoch 6 - iter 1440/1809 - loss 0.02308956 - time (sec): 103.24 - samples/sec: 2952.06 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 19:05:28,581 epoch 6 - iter 1620/1809 - loss 0.02310559 - time (sec): 115.93 - samples/sec: 2947.92 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 19:05:41,069 epoch 6 - iter 1800/1809 - loss 0.02341078 - time (sec): 128.42 - samples/sec: 2943.51 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 19:05:41,734 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:05:41,734 EPOCH 6 done: loss 0.0233 - lr: 0.000013 | |
| 2023-10-17 19:05:48,183 DEV : loss 0.3086238503456116 - f1-score (micro avg) 0.6503 | |
| 2023-10-17 19:05:48,225 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:06:01,564 epoch 7 - iter 180/1809 - loss 0.01807542 - time (sec): 13.34 - samples/sec: 2810.00 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 19:06:15,381 epoch 7 - iter 360/1809 - loss 0.01576264 - time (sec): 27.15 - samples/sec: 2773.21 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 19:06:27,999 epoch 7 - iter 540/1809 - loss 0.01466161 - time (sec): 39.77 - samples/sec: 2799.51 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 19:06:40,910 epoch 7 - iter 720/1809 - loss 0.01674336 - time (sec): 52.68 - samples/sec: 2854.34 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 19:06:53,287 epoch 7 - iter 900/1809 - loss 0.01690733 - time (sec): 65.06 - samples/sec: 2876.06 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 19:07:06,360 epoch 7 - iter 1080/1809 - loss 0.01654140 - time (sec): 78.13 - samples/sec: 2883.90 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 19:07:19,309 epoch 7 - iter 1260/1809 - loss 0.01661279 - time (sec): 91.08 - samples/sec: 2898.11 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 19:07:32,299 epoch 7 - iter 1440/1809 - loss 0.01634721 - time (sec): 104.07 - samples/sec: 2894.84 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 19:07:44,924 epoch 7 - iter 1620/1809 - loss 0.01679032 - time (sec): 116.70 - samples/sec: 2910.94 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 19:07:57,626 epoch 7 - iter 1800/1809 - loss 0.01648901 - time (sec): 129.40 - samples/sec: 2921.97 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 19:07:58,230 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:07:58,230 EPOCH 7 done: loss 0.0165 - lr: 0.000010 | |
| 2023-10-17 19:08:05,481 DEV : loss 0.34659674763679504 - f1-score (micro avg) 0.632 | |
| 2023-10-17 19:08:05,522 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:08:18,671 epoch 8 - iter 180/1809 - loss 0.00915215 - time (sec): 13.15 - samples/sec: 2787.60 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 19:08:31,720 epoch 8 - iter 360/1809 - loss 0.00930872 - time (sec): 26.20 - samples/sec: 2811.43 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 19:08:45,704 epoch 8 - iter 540/1809 - loss 0.01003110 - time (sec): 40.18 - samples/sec: 2780.09 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 19:08:59,427 epoch 8 - iter 720/1809 - loss 0.01169323 - time (sec): 53.90 - samples/sec: 2763.02 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 19:09:13,561 epoch 8 - iter 900/1809 - loss 0.01138645 - time (sec): 68.04 - samples/sec: 2763.43 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 19:09:28,039 epoch 8 - iter 1080/1809 - loss 0.01169517 - time (sec): 82.51 - samples/sec: 2733.67 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 19:09:41,516 epoch 8 - iter 1260/1809 - loss 0.01153351 - time (sec): 95.99 - samples/sec: 2735.49 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 19:09:55,382 epoch 8 - iter 1440/1809 - loss 0.01223461 - time (sec): 109.86 - samples/sec: 2738.43 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 19:10:09,151 epoch 8 - iter 1620/1809 - loss 0.01213000 - time (sec): 123.63 - samples/sec: 2743.07 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 19:10:23,760 epoch 8 - iter 1800/1809 - loss 0.01167306 - time (sec): 138.24 - samples/sec: 2735.18 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 19:10:24,463 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:10:24,463 EPOCH 8 done: loss 0.0118 - lr: 0.000007 | |
| 2023-10-17 19:10:30,861 DEV : loss 0.3742707073688507 - f1-score (micro avg) 0.6569 | |
| 2023-10-17 19:10:30,904 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:10:45,043 epoch 9 - iter 180/1809 - loss 0.01079518 - time (sec): 14.14 - samples/sec: 2667.85 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 19:10:59,146 epoch 9 - iter 360/1809 - loss 0.00876799 - time (sec): 28.24 - samples/sec: 2658.25 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 19:11:13,369 epoch 9 - iter 540/1809 - loss 0.00753337 - time (sec): 42.46 - samples/sec: 2635.77 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 19:11:27,223 epoch 9 - iter 720/1809 - loss 0.00737339 - time (sec): 56.32 - samples/sec: 2633.17 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 19:11:40,338 epoch 9 - iter 900/1809 - loss 0.00736290 - time (sec): 69.43 - samples/sec: 2684.24 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 19:11:52,078 epoch 9 - iter 1080/1809 - loss 0.00776742 - time (sec): 81.17 - samples/sec: 2771.41 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 19:12:04,124 epoch 9 - iter 1260/1809 - loss 0.00759926 - time (sec): 93.22 - samples/sec: 2820.58 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 19:12:15,927 epoch 9 - iter 1440/1809 - loss 0.00718286 - time (sec): 105.02 - samples/sec: 2865.46 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 19:12:27,689 epoch 9 - iter 1620/1809 - loss 0.00764832 - time (sec): 116.78 - samples/sec: 2915.65 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 19:12:39,260 epoch 9 - iter 1800/1809 - loss 0.00771228 - time (sec): 128.35 - samples/sec: 2948.74 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 19:12:39,777 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:12:39,777 EPOCH 9 done: loss 0.0077 - lr: 0.000003 | |
| 2023-10-17 19:12:46,785 DEV : loss 0.3763969838619232 - f1-score (micro avg) 0.657 | |
| 2023-10-17 19:12:46,835 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:13:00,924 epoch 10 - iter 180/1809 - loss 0.00366108 - time (sec): 14.09 - samples/sec: 2664.13 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 19:13:14,564 epoch 10 - iter 360/1809 - loss 0.00360582 - time (sec): 27.73 - samples/sec: 2693.32 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 19:13:27,619 epoch 10 - iter 540/1809 - loss 0.00387035 - time (sec): 40.78 - samples/sec: 2769.23 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 19:13:41,002 epoch 10 - iter 720/1809 - loss 0.00394948 - time (sec): 54.17 - samples/sec: 2800.28 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 19:13:54,695 epoch 10 - iter 900/1809 - loss 0.00373659 - time (sec): 67.86 - samples/sec: 2815.70 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 19:14:08,138 epoch 10 - iter 1080/1809 - loss 0.00427956 - time (sec): 81.30 - samples/sec: 2815.21 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 19:14:22,036 epoch 10 - iter 1260/1809 - loss 0.00426728 - time (sec): 95.20 - samples/sec: 2798.15 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 19:14:35,919 epoch 10 - iter 1440/1809 - loss 0.00454799 - time (sec): 109.08 - samples/sec: 2790.47 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 19:14:49,267 epoch 10 - iter 1620/1809 - loss 0.00463397 - time (sec): 122.43 - samples/sec: 2784.15 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 19:15:03,058 epoch 10 - iter 1800/1809 - loss 0.00481728 - time (sec): 136.22 - samples/sec: 2776.43 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 19:15:03,681 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:15:03,682 EPOCH 10 done: loss 0.0048 - lr: 0.000000 | |
| 2023-10-17 19:15:10,958 DEV : loss 0.3807702958583832 - f1-score (micro avg) 0.6587 | |
| 2023-10-17 19:15:11,520 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:15:11,522 Loading model from best epoch ... | |
| 2023-10-17 19:15:13,239 SequenceTagger predicts: Dictionary with 13 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 | |
| 2023-10-17 19:15:21,331 | |
| Results: | |
| - F-score (micro) 0.6784 | |
| - F-score (macro) 0.4668 | |
| - Accuracy 0.5229 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.6593 0.8122 0.7278 591 | |
| pers 0.6018 0.7619 0.6724 357 | |
| org 0.0000 0.0000 0.0000 79 | |
| micro avg 0.6319 0.7322 0.6784 1027 | |
| macro avg 0.4204 0.5247 0.4668 1027 | |
| weighted avg 0.5886 0.7322 0.6526 1027 | |
| 2023-10-17 19:15:21,332 ---------------------------------------------------------------------------------------------------- | |