| 2023-10-08 18:34:53,287 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:34:53,288 Model: "SequenceTagger( | |
| (embeddings): ByT5Embeddings( | |
| (model): T5EncoderModel( | |
| (shared): Embedding(384, 1472) | |
| (encoder): T5Stack( | |
| (embed_tokens): Embedding(384, 1472) | |
| (block): ModuleList( | |
| (0): T5Block( | |
| (layer): ModuleList( | |
| (0): T5LayerSelfAttention( | |
| (SelfAttention): T5Attention( | |
| (q): Linear(in_features=1472, out_features=384, bias=False) | |
| (k): Linear(in_features=1472, out_features=384, bias=False) | |
| (v): Linear(in_features=1472, out_features=384, bias=False) | |
| (o): Linear(in_features=384, out_features=1472, bias=False) | |
| (relative_attention_bias): Embedding(32, 6) | |
| ) | |
| (layer_norm): T5LayerNorm() | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (1): T5LayerFF( | |
| (DenseReluDense): T5DenseGatedActDense( | |
| (wi_0): Linear(in_features=1472, out_features=3584, bias=False) | |
| (wi_1): Linear(in_features=1472, out_features=3584, bias=False) | |
| (wo): Linear(in_features=3584, out_features=1472, bias=False) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| (act): NewGELUActivation() | |
| ) | |
| (layer_norm): T5LayerNorm() | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| (1-11): 11 x T5Block( | |
| (layer): ModuleList( | |
| (0): T5LayerSelfAttention( | |
| (SelfAttention): T5Attention( | |
| (q): Linear(in_features=1472, out_features=384, bias=False) | |
| (k): Linear(in_features=1472, out_features=384, bias=False) | |
| (v): Linear(in_features=1472, out_features=384, bias=False) | |
| (o): Linear(in_features=384, out_features=1472, bias=False) | |
| ) | |
| (layer_norm): T5LayerNorm() | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (1): T5LayerFF( | |
| (DenseReluDense): T5DenseGatedActDense( | |
| (wi_0): Linear(in_features=1472, out_features=3584, bias=False) | |
| (wi_1): Linear(in_features=1472, out_features=3584, bias=False) | |
| (wo): Linear(in_features=3584, out_features=1472, bias=False) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| (act): NewGELUActivation() | |
| ) | |
| (layer_norm): T5LayerNorm() | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (final_layer_norm): T5LayerNorm() | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=1472, out_features=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-08 18:34:53,288 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:34:53,288 MultiCorpus: 966 train + 219 dev + 204 test sentences | |
| - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /app/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator | |
| 2023-10-08 18:34:53,288 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:34:53,288 Train: 966 sentences | |
| 2023-10-08 18:34:53,288 (train_with_dev=False, train_with_test=False) | |
| 2023-10-08 18:34:53,288 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:34:53,288 Training Params: | |
| 2023-10-08 18:34:53,288 - learning_rate: "0.00016" | |
| 2023-10-08 18:34:53,289 - mini_batch_size: "4" | |
| 2023-10-08 18:34:53,289 - max_epochs: "10" | |
| 2023-10-08 18:34:53,289 - shuffle: "True" | |
| 2023-10-08 18:34:53,289 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:34:53,289 Plugins: | |
| 2023-10-08 18:34:53,289 - TensorboardLogger | |
| 2023-10-08 18:34:53,289 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-08 18:34:53,289 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:34:53,289 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-08 18:34:53,289 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-08 18:34:53,289 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:34:53,289 Computation: | |
| 2023-10-08 18:34:53,289 - compute on device: cuda:0 | |
| 2023-10-08 18:34:53,289 - embedding storage: none | |
| 2023-10-08 18:34:53,289 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:34:53,289 Model training base path: "hmbench-ajmc/fr-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-08 18:34:53,289 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:34:53,289 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:34:53,289 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-08 18:35:02,673 epoch 1 - iter 24/242 - loss 3.23249107 - time (sec): 9.38 - samples/sec: 233.30 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-08 18:35:12,678 epoch 1 - iter 48/242 - loss 3.22160902 - time (sec): 19.39 - samples/sec: 239.60 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-08 18:35:22,313 epoch 1 - iter 72/242 - loss 3.20323790 - time (sec): 29.02 - samples/sec: 238.81 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-08 18:35:32,243 epoch 1 - iter 96/242 - loss 3.14989613 - time (sec): 38.95 - samples/sec: 242.14 - lr: 0.000063 - momentum: 0.000000 | |
| 2023-10-08 18:35:42,136 epoch 1 - iter 120/242 - loss 3.06221572 - time (sec): 48.85 - samples/sec: 241.07 - lr: 0.000079 - momentum: 0.000000 | |
| 2023-10-08 18:35:52,824 epoch 1 - iter 144/242 - loss 2.95428246 - time (sec): 59.53 - samples/sec: 242.12 - lr: 0.000095 - momentum: 0.000000 | |
| 2023-10-08 18:36:02,538 epoch 1 - iter 168/242 - loss 2.85101367 - time (sec): 69.25 - samples/sec: 241.73 - lr: 0.000110 - momentum: 0.000000 | |
| 2023-10-08 18:36:12,394 epoch 1 - iter 192/242 - loss 2.74034409 - time (sec): 79.10 - samples/sec: 240.62 - lr: 0.000126 - momentum: 0.000000 | |
| 2023-10-08 18:36:23,043 epoch 1 - iter 216/242 - loss 2.60212408 - time (sec): 89.75 - samples/sec: 242.18 - lr: 0.000142 - momentum: 0.000000 | |
| 2023-10-08 18:36:33,989 epoch 1 - iter 240/242 - loss 2.45380672 - time (sec): 100.70 - samples/sec: 243.43 - lr: 0.000158 - momentum: 0.000000 | |
| 2023-10-08 18:36:34,764 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:36:34,764 EPOCH 1 done: loss 2.4415 - lr: 0.000158 | |
| 2023-10-08 18:36:41,310 DEV : loss 1.10421884059906 - f1-score (micro avg) 0.0 | |
| 2023-10-08 18:36:41,316 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:36:51,047 epoch 2 - iter 24/242 - loss 1.08751151 - time (sec): 9.73 - samples/sec: 233.42 - lr: 0.000158 - momentum: 0.000000 | |
| 2023-10-08 18:37:00,942 epoch 2 - iter 48/242 - loss 0.95694896 - time (sec): 19.62 - samples/sec: 237.71 - lr: 0.000157 - momentum: 0.000000 | |
| 2023-10-08 18:37:10,777 epoch 2 - iter 72/242 - loss 0.87876685 - time (sec): 29.46 - samples/sec: 241.59 - lr: 0.000155 - momentum: 0.000000 | |
| 2023-10-08 18:37:20,908 epoch 2 - iter 96/242 - loss 0.81302044 - time (sec): 39.59 - samples/sec: 243.27 - lr: 0.000153 - momentum: 0.000000 | |
| 2023-10-08 18:37:30,907 epoch 2 - iter 120/242 - loss 0.76456788 - time (sec): 49.59 - samples/sec: 242.03 - lr: 0.000151 - momentum: 0.000000 | |
| 2023-10-08 18:37:41,488 epoch 2 - iter 144/242 - loss 0.71887917 - time (sec): 60.17 - samples/sec: 244.47 - lr: 0.000150 - momentum: 0.000000 | |
| 2023-10-08 18:37:52,468 epoch 2 - iter 168/242 - loss 0.67430178 - time (sec): 71.15 - samples/sec: 243.56 - lr: 0.000148 - momentum: 0.000000 | |
| 2023-10-08 18:38:02,384 epoch 2 - iter 192/242 - loss 0.63672173 - time (sec): 81.07 - samples/sec: 243.01 - lr: 0.000146 - momentum: 0.000000 | |
| 2023-10-08 18:38:12,147 epoch 2 - iter 216/242 - loss 0.60703481 - time (sec): 90.83 - samples/sec: 242.11 - lr: 0.000144 - momentum: 0.000000 | |
| 2023-10-08 18:38:22,686 epoch 2 - iter 240/242 - loss 0.57778911 - time (sec): 101.37 - samples/sec: 242.90 - lr: 0.000142 - momentum: 0.000000 | |
| 2023-10-08 18:38:23,263 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:38:23,264 EPOCH 2 done: loss 0.5768 - lr: 0.000142 | |
| 2023-10-08 18:38:29,811 DEV : loss 0.36735957860946655 - f1-score (micro avg) 0.4525 | |
| 2023-10-08 18:38:29,817 saving best model | |
| 2023-10-08 18:38:30,707 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:38:40,732 epoch 3 - iter 24/242 - loss 0.33886112 - time (sec): 10.02 - samples/sec: 258.08 - lr: 0.000141 - momentum: 0.000000 | |
| 2023-10-08 18:38:50,182 epoch 3 - iter 48/242 - loss 0.35382038 - time (sec): 19.47 - samples/sec: 259.42 - lr: 0.000139 - momentum: 0.000000 | |
| 2023-10-08 18:39:00,142 epoch 3 - iter 72/242 - loss 0.32381848 - time (sec): 29.43 - samples/sec: 263.07 - lr: 0.000137 - momentum: 0.000000 | |
| 2023-10-08 18:39:09,488 epoch 3 - iter 96/242 - loss 0.31041884 - time (sec): 38.78 - samples/sec: 259.78 - lr: 0.000135 - momentum: 0.000000 | |
| 2023-10-08 18:39:18,559 epoch 3 - iter 120/242 - loss 0.29354167 - time (sec): 47.85 - samples/sec: 258.39 - lr: 0.000134 - momentum: 0.000000 | |
| 2023-10-08 18:39:27,561 epoch 3 - iter 144/242 - loss 0.28584160 - time (sec): 56.85 - samples/sec: 257.77 - lr: 0.000132 - momentum: 0.000000 | |
| 2023-10-08 18:39:37,506 epoch 3 - iter 168/242 - loss 0.28154401 - time (sec): 66.80 - samples/sec: 258.98 - lr: 0.000130 - momentum: 0.000000 | |
| 2023-10-08 18:39:47,261 epoch 3 - iter 192/242 - loss 0.27573225 - time (sec): 76.55 - samples/sec: 260.33 - lr: 0.000128 - momentum: 0.000000 | |
| 2023-10-08 18:39:56,248 epoch 3 - iter 216/242 - loss 0.26727131 - time (sec): 85.54 - samples/sec: 259.38 - lr: 0.000126 - momentum: 0.000000 | |
| 2023-10-08 18:40:05,584 epoch 3 - iter 240/242 - loss 0.26232951 - time (sec): 94.88 - samples/sec: 259.21 - lr: 0.000125 - momentum: 0.000000 | |
| 2023-10-08 18:40:06,193 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:40:06,193 EPOCH 3 done: loss 0.2619 - lr: 0.000125 | |
| 2023-10-08 18:40:12,021 DEV : loss 0.20984935760498047 - f1-score (micro avg) 0.5559 | |
| 2023-10-08 18:40:12,027 saving best model | |
| 2023-10-08 18:40:16,434 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:40:25,028 epoch 4 - iter 24/242 - loss 0.21633186 - time (sec): 8.59 - samples/sec: 255.58 - lr: 0.000123 - momentum: 0.000000 | |
| 2023-10-08 18:40:34,737 epoch 4 - iter 48/242 - loss 0.20499870 - time (sec): 18.30 - samples/sec: 264.52 - lr: 0.000121 - momentum: 0.000000 | |
| 2023-10-08 18:40:44,184 epoch 4 - iter 72/242 - loss 0.19040422 - time (sec): 27.75 - samples/sec: 262.04 - lr: 0.000119 - momentum: 0.000000 | |
| 2023-10-08 18:40:53,336 epoch 4 - iter 96/242 - loss 0.17803656 - time (sec): 36.90 - samples/sec: 262.39 - lr: 0.000118 - momentum: 0.000000 | |
| 2023-10-08 18:41:02,300 epoch 4 - iter 120/242 - loss 0.17506133 - time (sec): 45.86 - samples/sec: 262.28 - lr: 0.000116 - momentum: 0.000000 | |
| 2023-10-08 18:41:12,466 epoch 4 - iter 144/242 - loss 0.17147606 - time (sec): 56.03 - samples/sec: 264.39 - lr: 0.000114 - momentum: 0.000000 | |
| 2023-10-08 18:41:22,097 epoch 4 - iter 168/242 - loss 0.16370940 - time (sec): 65.66 - samples/sec: 264.89 - lr: 0.000112 - momentum: 0.000000 | |
| 2023-10-08 18:41:31,301 epoch 4 - iter 192/242 - loss 0.16311405 - time (sec): 74.87 - samples/sec: 263.15 - lr: 0.000110 - momentum: 0.000000 | |
| 2023-10-08 18:41:40,791 epoch 4 - iter 216/242 - loss 0.16120081 - time (sec): 84.35 - samples/sec: 262.63 - lr: 0.000109 - momentum: 0.000000 | |
| 2023-10-08 18:41:50,100 epoch 4 - iter 240/242 - loss 0.15725999 - time (sec): 93.66 - samples/sec: 262.00 - lr: 0.000107 - momentum: 0.000000 | |
| 2023-10-08 18:41:50,796 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:41:50,796 EPOCH 4 done: loss 0.1573 - lr: 0.000107 | |
| 2023-10-08 18:41:56,634 DEV : loss 0.14482806622982025 - f1-score (micro avg) 0.8417 | |
| 2023-10-08 18:41:56,640 saving best model | |
| 2023-10-08 18:42:01,009 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:42:10,593 epoch 5 - iter 24/242 - loss 0.14974282 - time (sec): 9.58 - samples/sec: 264.24 - lr: 0.000105 - momentum: 0.000000 | |
| 2023-10-08 18:42:19,980 epoch 5 - iter 48/242 - loss 0.12573972 - time (sec): 18.97 - samples/sec: 259.74 - lr: 0.000103 - momentum: 0.000000 | |
| 2023-10-08 18:42:29,922 epoch 5 - iter 72/242 - loss 0.12078938 - time (sec): 28.91 - samples/sec: 266.61 - lr: 0.000102 - momentum: 0.000000 | |
| 2023-10-08 18:42:39,756 epoch 5 - iter 96/242 - loss 0.11455455 - time (sec): 38.74 - samples/sec: 268.40 - lr: 0.000100 - momentum: 0.000000 | |
| 2023-10-08 18:42:49,278 epoch 5 - iter 120/242 - loss 0.11444902 - time (sec): 48.27 - samples/sec: 266.29 - lr: 0.000098 - momentum: 0.000000 | |
| 2023-10-08 18:42:58,251 epoch 5 - iter 144/242 - loss 0.11447821 - time (sec): 57.24 - samples/sec: 264.08 - lr: 0.000096 - momentum: 0.000000 | |
| 2023-10-08 18:43:07,744 epoch 5 - iter 168/242 - loss 0.10989477 - time (sec): 66.73 - samples/sec: 264.61 - lr: 0.000094 - momentum: 0.000000 | |
| 2023-10-08 18:43:16,374 epoch 5 - iter 192/242 - loss 0.11006937 - time (sec): 75.36 - samples/sec: 263.09 - lr: 0.000093 - momentum: 0.000000 | |
| 2023-10-08 18:43:25,524 epoch 5 - iter 216/242 - loss 0.10934520 - time (sec): 84.51 - samples/sec: 262.35 - lr: 0.000091 - momentum: 0.000000 | |
| 2023-10-08 18:43:34,623 epoch 5 - iter 240/242 - loss 0.10539988 - time (sec): 93.61 - samples/sec: 262.11 - lr: 0.000089 - momentum: 0.000000 | |
| 2023-10-08 18:43:35,364 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:43:35,365 EPOCH 5 done: loss 0.1050 - lr: 0.000089 | |
| 2023-10-08 18:43:41,168 DEV : loss 0.13649354875087738 - f1-score (micro avg) 0.8192 | |
| 2023-10-08 18:43:41,174 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:43:50,124 epoch 6 - iter 24/242 - loss 0.08990859 - time (sec): 8.95 - samples/sec: 251.23 - lr: 0.000087 - momentum: 0.000000 | |
| 2023-10-08 18:43:59,640 epoch 6 - iter 48/242 - loss 0.08114002 - time (sec): 18.46 - samples/sec: 259.64 - lr: 0.000086 - momentum: 0.000000 | |
| 2023-10-08 18:44:08,671 epoch 6 - iter 72/242 - loss 0.07601968 - time (sec): 27.50 - samples/sec: 258.12 - lr: 0.000084 - momentum: 0.000000 | |
| 2023-10-08 18:44:18,225 epoch 6 - iter 96/242 - loss 0.07610495 - time (sec): 37.05 - samples/sec: 260.00 - lr: 0.000082 - momentum: 0.000000 | |
| 2023-10-08 18:44:27,796 epoch 6 - iter 120/242 - loss 0.07416057 - time (sec): 46.62 - samples/sec: 261.13 - lr: 0.000080 - momentum: 0.000000 | |
| 2023-10-08 18:44:37,627 epoch 6 - iter 144/242 - loss 0.07373746 - time (sec): 56.45 - samples/sec: 263.64 - lr: 0.000078 - momentum: 0.000000 | |
| 2023-10-08 18:44:46,994 epoch 6 - iter 168/242 - loss 0.07727814 - time (sec): 65.82 - samples/sec: 265.41 - lr: 0.000077 - momentum: 0.000000 | |
| 2023-10-08 18:44:56,080 epoch 6 - iter 192/242 - loss 0.07713696 - time (sec): 74.90 - samples/sec: 263.20 - lr: 0.000075 - momentum: 0.000000 | |
| 2023-10-08 18:45:04,971 epoch 6 - iter 216/242 - loss 0.07461044 - time (sec): 83.80 - samples/sec: 262.06 - lr: 0.000073 - momentum: 0.000000 | |
| 2023-10-08 18:45:14,841 epoch 6 - iter 240/242 - loss 0.07542934 - time (sec): 93.67 - samples/sec: 261.63 - lr: 0.000071 - momentum: 0.000000 | |
| 2023-10-08 18:45:15,674 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:45:15,675 EPOCH 6 done: loss 0.0755 - lr: 0.000071 | |
| 2023-10-08 18:45:21,569 DEV : loss 0.12205741554498672 - f1-score (micro avg) 0.8346 | |
| 2023-10-08 18:45:21,576 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:45:29,908 epoch 7 - iter 24/242 - loss 0.04051827 - time (sec): 8.33 - samples/sec: 235.05 - lr: 0.000070 - momentum: 0.000000 | |
| 2023-10-08 18:45:39,504 epoch 7 - iter 48/242 - loss 0.05486241 - time (sec): 17.93 - samples/sec: 254.15 - lr: 0.000068 - momentum: 0.000000 | |
| 2023-10-08 18:45:48,946 epoch 7 - iter 72/242 - loss 0.05684543 - time (sec): 27.37 - samples/sec: 255.08 - lr: 0.000066 - momentum: 0.000000 | |
| 2023-10-08 18:45:58,785 epoch 7 - iter 96/242 - loss 0.06216082 - time (sec): 37.21 - samples/sec: 257.83 - lr: 0.000064 - momentum: 0.000000 | |
| 2023-10-08 18:46:08,303 epoch 7 - iter 120/242 - loss 0.05942616 - time (sec): 46.73 - samples/sec: 258.28 - lr: 0.000062 - momentum: 0.000000 | |
| 2023-10-08 18:46:17,017 epoch 7 - iter 144/242 - loss 0.05433522 - time (sec): 55.44 - samples/sec: 255.47 - lr: 0.000061 - momentum: 0.000000 | |
| 2023-10-08 18:46:26,640 epoch 7 - iter 168/242 - loss 0.05796718 - time (sec): 65.06 - samples/sec: 255.62 - lr: 0.000059 - momentum: 0.000000 | |
| 2023-10-08 18:46:36,464 epoch 7 - iter 192/242 - loss 0.05899844 - time (sec): 74.89 - samples/sec: 256.18 - lr: 0.000057 - momentum: 0.000000 | |
| 2023-10-08 18:46:46,862 epoch 7 - iter 216/242 - loss 0.05910219 - time (sec): 85.28 - samples/sec: 256.92 - lr: 0.000055 - momentum: 0.000000 | |
| 2023-10-08 18:46:57,126 epoch 7 - iter 240/242 - loss 0.05689392 - time (sec): 95.55 - samples/sec: 257.31 - lr: 0.000054 - momentum: 0.000000 | |
| 2023-10-08 18:46:57,730 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:46:57,730 EPOCH 7 done: loss 0.0568 - lr: 0.000054 | |
| 2023-10-08 18:47:03,836 DEV : loss 0.12814383208751678 - f1-score (micro avg) 0.8224 | |
| 2023-10-08 18:47:03,842 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:47:13,018 epoch 8 - iter 24/242 - loss 0.05203825 - time (sec): 9.17 - samples/sec: 229.12 - lr: 0.000052 - momentum: 0.000000 | |
| 2023-10-08 18:47:22,854 epoch 8 - iter 48/242 - loss 0.05392342 - time (sec): 19.01 - samples/sec: 244.54 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-08 18:47:33,063 epoch 8 - iter 72/242 - loss 0.05134362 - time (sec): 29.22 - samples/sec: 250.58 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-08 18:47:42,930 epoch 8 - iter 96/242 - loss 0.04471543 - time (sec): 39.09 - samples/sec: 250.19 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-08 18:47:53,157 epoch 8 - iter 120/242 - loss 0.04434398 - time (sec): 49.31 - samples/sec: 249.87 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-08 18:48:03,273 epoch 8 - iter 144/242 - loss 0.04464736 - time (sec): 59.43 - samples/sec: 250.14 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-08 18:48:13,650 epoch 8 - iter 168/242 - loss 0.04805001 - time (sec): 69.81 - samples/sec: 250.66 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-08 18:48:23,745 epoch 8 - iter 192/242 - loss 0.04571917 - time (sec): 79.90 - samples/sec: 249.68 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-08 18:48:33,544 epoch 8 - iter 216/242 - loss 0.04399139 - time (sec): 89.70 - samples/sec: 248.29 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-08 18:48:43,388 epoch 8 - iter 240/242 - loss 0.04459372 - time (sec): 99.54 - samples/sec: 247.39 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-08 18:48:43,916 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:48:43,917 EPOCH 8 done: loss 0.0445 - lr: 0.000036 | |
| 2023-10-08 18:48:50,468 DEV : loss 0.13605128228664398 - f1-score (micro avg) 0.8141 | |
| 2023-10-08 18:48:50,475 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:49:00,109 epoch 9 - iter 24/242 - loss 0.05381900 - time (sec): 9.63 - samples/sec: 231.71 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-08 18:49:09,640 epoch 9 - iter 48/242 - loss 0.04401043 - time (sec): 19.16 - samples/sec: 229.50 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-08 18:49:20,009 epoch 9 - iter 72/242 - loss 0.03846786 - time (sec): 29.53 - samples/sec: 233.84 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-08 18:49:30,133 epoch 9 - iter 96/242 - loss 0.04296229 - time (sec): 39.66 - samples/sec: 238.32 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-08 18:49:40,670 epoch 9 - iter 120/242 - loss 0.04404865 - time (sec): 50.19 - samples/sec: 241.47 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-08 18:49:51,280 epoch 9 - iter 144/242 - loss 0.04306141 - time (sec): 60.80 - samples/sec: 241.58 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-08 18:50:01,468 epoch 9 - iter 168/242 - loss 0.04150438 - time (sec): 70.99 - samples/sec: 242.14 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-08 18:50:11,340 epoch 9 - iter 192/242 - loss 0.04021125 - time (sec): 80.86 - samples/sec: 242.11 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-08 18:50:21,375 epoch 9 - iter 216/242 - loss 0.04084934 - time (sec): 90.90 - samples/sec: 242.30 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-08 18:50:31,565 epoch 9 - iter 240/242 - loss 0.03905588 - time (sec): 101.09 - samples/sec: 242.90 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-08 18:50:32,262 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:50:32,263 EPOCH 9 done: loss 0.0393 - lr: 0.000018 | |
| 2023-10-08 18:50:38,666 DEV : loss 0.1348445564508438 - f1-score (micro avg) 0.8256 | |
| 2023-10-08 18:50:38,672 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:50:48,750 epoch 10 - iter 24/242 - loss 0.03126737 - time (sec): 10.08 - samples/sec: 243.34 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-08 18:50:59,044 epoch 10 - iter 48/242 - loss 0.02421919 - time (sec): 20.37 - samples/sec: 248.74 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-08 18:51:08,723 epoch 10 - iter 72/242 - loss 0.02499859 - time (sec): 30.05 - samples/sec: 250.55 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-08 18:51:18,437 epoch 10 - iter 96/242 - loss 0.03022215 - time (sec): 39.76 - samples/sec: 254.00 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-08 18:51:27,131 epoch 10 - iter 120/242 - loss 0.03176207 - time (sec): 48.46 - samples/sec: 252.18 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-08 18:51:36,241 epoch 10 - iter 144/242 - loss 0.03286198 - time (sec): 57.57 - samples/sec: 252.07 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-08 18:51:45,628 epoch 10 - iter 168/242 - loss 0.03336583 - time (sec): 66.95 - samples/sec: 253.26 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-08 18:51:55,144 epoch 10 - iter 192/242 - loss 0.03282448 - time (sec): 76.47 - samples/sec: 254.72 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-08 18:52:04,668 epoch 10 - iter 216/242 - loss 0.03205261 - time (sec): 86.00 - samples/sec: 255.50 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-08 18:52:14,309 epoch 10 - iter 240/242 - loss 0.03366127 - time (sec): 95.64 - samples/sec: 256.99 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-08 18:52:15,017 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:52:15,017 EPOCH 10 done: loss 0.0337 - lr: 0.000000 | |
| 2023-10-08 18:52:20,852 DEV : loss 0.13635611534118652 - f1-score (micro avg) 0.8275 | |
| 2023-10-08 18:52:21,698 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 18:52:21,699 Loading model from best epoch ... | |
| 2023-10-08 18:52:24,820 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 | |
| 2023-10-08 18:52:30,519 | |
| Results: | |
| - F-score (micro) 0.7717 | |
| - F-score (macro) 0.4607 | |
| - Accuracy 0.6598 | |
| By class: | |
| precision recall f1-score support | |
| pers 0.7532 0.8561 0.8013 139 | |
| scope 0.7733 0.8992 0.8315 129 | |
| work 0.6667 0.6750 0.6708 80 | |
| loc 0.0000 0.0000 0.0000 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.7429 0.8028 0.7717 360 | |
| macro avg 0.4386 0.4861 0.4607 360 | |
| weighted avg 0.7161 0.8028 0.7564 360 | |
| 2023-10-08 18:52:30,519 ---------------------------------------------------------------------------------------------------- | |