| 2023-10-08 21:31:27,703 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:31:27,704 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 21:31:27,704 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:31:27,704 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 21:31:27,704 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:31:27,704 Train: 966 sentences | |
| 2023-10-08 21:31:27,704 (train_with_dev=False, train_with_test=False) | |
| 2023-10-08 21:31:27,705 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:31:27,705 Training Params: | |
| 2023-10-08 21:31:27,705 - learning_rate: "0.00016" | |
| 2023-10-08 21:31:27,705 - mini_batch_size: "8" | |
| 2023-10-08 21:31:27,705 - max_epochs: "10" | |
| 2023-10-08 21:31:27,705 - shuffle: "True" | |
| 2023-10-08 21:31:27,705 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:31:27,705 Plugins: | |
| 2023-10-08 21:31:27,705 - TensorboardLogger | |
| 2023-10-08 21:31:27,705 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-08 21:31:27,705 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:31:27,705 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-08 21:31:27,705 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-08 21:31:27,705 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:31:27,705 Computation: | |
| 2023-10-08 21:31:27,705 - compute on device: cuda:0 | |
| 2023-10-08 21:31:27,705 - embedding storage: none | |
| 2023-10-08 21:31:27,705 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:31:27,705 Model training base path: "hmbench-ajmc/fr-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-08 21:31:27,705 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:31:27,706 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:31:27,706 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-08 21:31:35,621 epoch 1 - iter 12/121 - loss 3.21166448 - time (sec): 7.91 - samples/sec: 280.39 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-08 21:31:44,349 epoch 1 - iter 24/121 - loss 3.20556874 - time (sec): 16.64 - samples/sec: 286.13 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-08 21:31:53,215 epoch 1 - iter 36/121 - loss 3.19507718 - time (sec): 25.51 - samples/sec: 287.67 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-08 21:32:01,324 epoch 1 - iter 48/121 - loss 3.18016809 - time (sec): 33.62 - samples/sec: 285.30 - lr: 0.000062 - momentum: 0.000000 | |
| 2023-10-08 21:32:09,771 epoch 1 - iter 60/121 - loss 3.14881989 - time (sec): 42.06 - samples/sec: 287.18 - lr: 0.000078 - momentum: 0.000000 | |
| 2023-10-08 21:32:18,794 epoch 1 - iter 72/121 - loss 3.09406347 - time (sec): 51.09 - samples/sec: 289.21 - lr: 0.000094 - momentum: 0.000000 | |
| 2023-10-08 21:32:27,531 epoch 1 - iter 84/121 - loss 3.03193705 - time (sec): 59.82 - samples/sec: 287.18 - lr: 0.000110 - momentum: 0.000000 | |
| 2023-10-08 21:32:36,394 epoch 1 - iter 96/121 - loss 2.95622833 - time (sec): 68.69 - samples/sec: 286.31 - lr: 0.000126 - momentum: 0.000000 | |
| 2023-10-08 21:32:45,229 epoch 1 - iter 108/121 - loss 2.87141440 - time (sec): 77.52 - samples/sec: 286.45 - lr: 0.000141 - momentum: 0.000000 | |
| 2023-10-08 21:32:53,831 epoch 1 - iter 120/121 - loss 2.79080138 - time (sec): 86.12 - samples/sec: 284.70 - lr: 0.000157 - momentum: 0.000000 | |
| 2023-10-08 21:32:54,609 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:32:54,609 EPOCH 1 done: loss 2.7821 - lr: 0.000157 | |
| 2023-10-08 21:33:00,387 DEV : loss 1.8131030797958374 - f1-score (micro avg) 0.0 | |
| 2023-10-08 21:33:00,393 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:33:09,217 epoch 2 - iter 12/121 - loss 1.79636265 - time (sec): 8.82 - samples/sec: 293.44 - lr: 0.000158 - momentum: 0.000000 | |
| 2023-10-08 21:33:18,393 epoch 2 - iter 24/121 - loss 1.68244545 - time (sec): 18.00 - samples/sec: 294.25 - lr: 0.000157 - momentum: 0.000000 | |
| 2023-10-08 21:33:26,790 epoch 2 - iter 36/121 - loss 1.57537534 - time (sec): 26.40 - samples/sec: 288.80 - lr: 0.000155 - momentum: 0.000000 | |
| 2023-10-08 21:33:35,523 epoch 2 - iter 48/121 - loss 1.47842825 - time (sec): 35.13 - samples/sec: 284.35 - lr: 0.000153 - momentum: 0.000000 | |
| 2023-10-08 21:33:44,473 epoch 2 - iter 60/121 - loss 1.38341861 - time (sec): 44.08 - samples/sec: 281.58 - lr: 0.000151 - momentum: 0.000000 | |
| 2023-10-08 21:33:53,695 epoch 2 - iter 72/121 - loss 1.30268725 - time (sec): 53.30 - samples/sec: 278.98 - lr: 0.000150 - momentum: 0.000000 | |
| 2023-10-08 21:34:02,865 epoch 2 - iter 84/121 - loss 1.23521232 - time (sec): 62.47 - samples/sec: 279.01 - lr: 0.000148 - momentum: 0.000000 | |
| 2023-10-08 21:34:11,289 epoch 2 - iter 96/121 - loss 1.17983078 - time (sec): 70.89 - samples/sec: 277.88 - lr: 0.000146 - momentum: 0.000000 | |
| 2023-10-08 21:34:19,830 epoch 2 - iter 108/121 - loss 1.11490372 - time (sec): 79.44 - samples/sec: 277.56 - lr: 0.000144 - momentum: 0.000000 | |
| 2023-10-08 21:34:28,449 epoch 2 - iter 120/121 - loss 1.06053368 - time (sec): 88.06 - samples/sec: 278.54 - lr: 0.000143 - momentum: 0.000000 | |
| 2023-10-08 21:34:29,093 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:34:29,094 EPOCH 2 done: loss 1.0556 - lr: 0.000143 | |
| 2023-10-08 21:34:34,906 DEV : loss 0.6444090008735657 - f1-score (micro avg) 0.0 | |
| 2023-10-08 21:34:34,912 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:34:43,184 epoch 3 - iter 12/121 - loss 0.58722550 - time (sec): 8.27 - samples/sec: 275.54 - lr: 0.000141 - momentum: 0.000000 | |
| 2023-10-08 21:34:52,072 epoch 3 - iter 24/121 - loss 0.59417629 - time (sec): 17.16 - samples/sec: 284.17 - lr: 0.000139 - momentum: 0.000000 | |
| 2023-10-08 21:35:00,791 epoch 3 - iter 36/121 - loss 0.59259042 - time (sec): 25.88 - samples/sec: 282.60 - lr: 0.000137 - momentum: 0.000000 | |
| 2023-10-08 21:35:09,468 epoch 3 - iter 48/121 - loss 0.58407643 - time (sec): 34.55 - samples/sec: 283.23 - lr: 0.000135 - momentum: 0.000000 | |
| 2023-10-08 21:35:18,218 epoch 3 - iter 60/121 - loss 0.57152014 - time (sec): 43.30 - samples/sec: 285.37 - lr: 0.000134 - momentum: 0.000000 | |
| 2023-10-08 21:35:26,404 epoch 3 - iter 72/121 - loss 0.54715064 - time (sec): 51.49 - samples/sec: 283.76 - lr: 0.000132 - momentum: 0.000000 | |
| 2023-10-08 21:35:34,981 epoch 3 - iter 84/121 - loss 0.53051696 - time (sec): 60.07 - samples/sec: 284.28 - lr: 0.000130 - momentum: 0.000000 | |
| 2023-10-08 21:35:43,807 epoch 3 - iter 96/121 - loss 0.51262726 - time (sec): 68.89 - samples/sec: 283.65 - lr: 0.000128 - momentum: 0.000000 | |
| 2023-10-08 21:35:52,760 epoch 3 - iter 108/121 - loss 0.48852958 - time (sec): 77.85 - samples/sec: 285.76 - lr: 0.000127 - momentum: 0.000000 | |
| 2023-10-08 21:36:01,236 epoch 3 - iter 120/121 - loss 0.47092846 - time (sec): 86.32 - samples/sec: 284.54 - lr: 0.000125 - momentum: 0.000000 | |
| 2023-10-08 21:36:01,800 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:36:01,801 EPOCH 3 done: loss 0.4715 - lr: 0.000125 | |
| 2023-10-08 21:36:07,771 DEV : loss 0.3705194294452667 - f1-score (micro avg) 0.4064 | |
| 2023-10-08 21:36:07,777 saving best model | |
| 2023-10-08 21:36:08,922 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:36:17,557 epoch 4 - iter 12/121 - loss 0.30532656 - time (sec): 8.63 - samples/sec: 260.10 - lr: 0.000123 - momentum: 0.000000 | |
| 2023-10-08 21:36:26,148 epoch 4 - iter 24/121 - loss 0.31458394 - time (sec): 17.22 - samples/sec: 273.89 - lr: 0.000121 - momentum: 0.000000 | |
| 2023-10-08 21:36:34,016 epoch 4 - iter 36/121 - loss 0.31803950 - time (sec): 25.09 - samples/sec: 272.41 - lr: 0.000120 - momentum: 0.000000 | |
| 2023-10-08 21:36:42,364 epoch 4 - iter 48/121 - loss 0.31800584 - time (sec): 33.44 - samples/sec: 276.21 - lr: 0.000118 - momentum: 0.000000 | |
| 2023-10-08 21:36:51,364 epoch 4 - iter 60/121 - loss 0.29918326 - time (sec): 42.44 - samples/sec: 280.69 - lr: 0.000116 - momentum: 0.000000 | |
| 2023-10-08 21:37:00,474 epoch 4 - iter 72/121 - loss 0.30078693 - time (sec): 51.55 - samples/sec: 282.22 - lr: 0.000114 - momentum: 0.000000 | |
| 2023-10-08 21:37:08,744 epoch 4 - iter 84/121 - loss 0.30342155 - time (sec): 59.82 - samples/sec: 282.75 - lr: 0.000113 - momentum: 0.000000 | |
| 2023-10-08 21:37:17,956 epoch 4 - iter 96/121 - loss 0.29833815 - time (sec): 69.03 - samples/sec: 285.24 - lr: 0.000111 - momentum: 0.000000 | |
| 2023-10-08 21:37:26,364 epoch 4 - iter 108/121 - loss 0.29213228 - time (sec): 77.44 - samples/sec: 285.53 - lr: 0.000109 - momentum: 0.000000 | |
| 2023-10-08 21:37:35,161 epoch 4 - iter 120/121 - loss 0.28600872 - time (sec): 86.24 - samples/sec: 285.21 - lr: 0.000107 - momentum: 0.000000 | |
| 2023-10-08 21:37:35,702 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:37:35,703 EPOCH 4 done: loss 0.2864 - lr: 0.000107 | |
| 2023-10-08 21:37:41,512 DEV : loss 0.26601657271385193 - f1-score (micro avg) 0.5204 | |
| 2023-10-08 21:37:41,517 saving best model | |
| 2023-10-08 21:37:45,886 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:37:54,116 epoch 5 - iter 12/121 - loss 0.23432641 - time (sec): 8.23 - samples/sec: 277.22 - lr: 0.000105 - momentum: 0.000000 | |
| 2023-10-08 21:38:03,245 epoch 5 - iter 24/121 - loss 0.23159006 - time (sec): 17.36 - samples/sec: 278.73 - lr: 0.000104 - momentum: 0.000000 | |
| 2023-10-08 21:38:12,229 epoch 5 - iter 36/121 - loss 0.23704500 - time (sec): 26.34 - samples/sec: 285.67 - lr: 0.000102 - momentum: 0.000000 | |
| 2023-10-08 21:38:20,653 epoch 5 - iter 48/121 - loss 0.24078930 - time (sec): 34.77 - samples/sec: 285.26 - lr: 0.000100 - momentum: 0.000000 | |
| 2023-10-08 21:38:29,660 epoch 5 - iter 60/121 - loss 0.23998293 - time (sec): 43.77 - samples/sec: 284.75 - lr: 0.000098 - momentum: 0.000000 | |
| 2023-10-08 21:38:38,636 epoch 5 - iter 72/121 - loss 0.23089916 - time (sec): 52.75 - samples/sec: 283.78 - lr: 0.000097 - momentum: 0.000000 | |
| 2023-10-08 21:38:47,327 epoch 5 - iter 84/121 - loss 0.22345391 - time (sec): 61.44 - samples/sec: 281.73 - lr: 0.000095 - momentum: 0.000000 | |
| 2023-10-08 21:38:56,444 epoch 5 - iter 96/121 - loss 0.21598786 - time (sec): 70.56 - samples/sec: 284.27 - lr: 0.000093 - momentum: 0.000000 | |
| 2023-10-08 21:39:04,708 epoch 5 - iter 108/121 - loss 0.21161077 - time (sec): 78.82 - samples/sec: 282.72 - lr: 0.000091 - momentum: 0.000000 | |
| 2023-10-08 21:39:12,919 epoch 5 - iter 120/121 - loss 0.20909319 - time (sec): 87.03 - samples/sec: 282.15 - lr: 0.000090 - momentum: 0.000000 | |
| 2023-10-08 21:39:13,508 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:39:13,508 EPOCH 5 done: loss 0.2096 - lr: 0.000090 | |
| 2023-10-08 21:39:19,503 DEV : loss 0.20941473543643951 - f1-score (micro avg) 0.6484 | |
| 2023-10-08 21:39:19,508 saving best model | |
| 2023-10-08 21:39:23,895 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:39:33,041 epoch 6 - iter 12/121 - loss 0.18803803 - time (sec): 9.14 - samples/sec: 288.36 - lr: 0.000088 - momentum: 0.000000 | |
| 2023-10-08 21:39:41,948 epoch 6 - iter 24/121 - loss 0.17673119 - time (sec): 18.05 - samples/sec: 283.58 - lr: 0.000086 - momentum: 0.000000 | |
| 2023-10-08 21:39:50,405 epoch 6 - iter 36/121 - loss 0.17204922 - time (sec): 26.51 - samples/sec: 280.70 - lr: 0.000084 - momentum: 0.000000 | |
| 2023-10-08 21:39:58,836 epoch 6 - iter 48/121 - loss 0.17883918 - time (sec): 34.94 - samples/sec: 274.47 - lr: 0.000082 - momentum: 0.000000 | |
| 2023-10-08 21:40:07,420 epoch 6 - iter 60/121 - loss 0.17037530 - time (sec): 43.52 - samples/sec: 272.75 - lr: 0.000081 - momentum: 0.000000 | |
| 2023-10-08 21:40:16,341 epoch 6 - iter 72/121 - loss 0.16322801 - time (sec): 52.44 - samples/sec: 273.36 - lr: 0.000079 - momentum: 0.000000 | |
| 2023-10-08 21:40:25,403 epoch 6 - iter 84/121 - loss 0.16137249 - time (sec): 61.51 - samples/sec: 274.75 - lr: 0.000077 - momentum: 0.000000 | |
| 2023-10-08 21:40:34,928 epoch 6 - iter 96/121 - loss 0.15730659 - time (sec): 71.03 - samples/sec: 275.47 - lr: 0.000075 - momentum: 0.000000 | |
| 2023-10-08 21:40:44,096 epoch 6 - iter 108/121 - loss 0.15850412 - time (sec): 80.20 - samples/sec: 275.17 - lr: 0.000074 - momentum: 0.000000 | |
| 2023-10-08 21:40:53,598 epoch 6 - iter 120/121 - loss 0.15656703 - time (sec): 89.70 - samples/sec: 273.95 - lr: 0.000072 - momentum: 0.000000 | |
| 2023-10-08 21:40:54,256 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:40:54,257 EPOCH 6 done: loss 0.1561 - lr: 0.000072 | |
| 2023-10-08 21:41:00,597 DEV : loss 0.17296475172042847 - f1-score (micro avg) 0.8248 | |
| 2023-10-08 21:41:00,603 saving best model | |
| 2023-10-08 21:41:04,984 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:41:13,812 epoch 7 - iter 12/121 - loss 0.13301191 - time (sec): 8.83 - samples/sec: 263.65 - lr: 0.000070 - momentum: 0.000000 | |
| 2023-10-08 21:41:22,884 epoch 7 - iter 24/121 - loss 0.13488940 - time (sec): 17.90 - samples/sec: 259.57 - lr: 0.000068 - momentum: 0.000000 | |
| 2023-10-08 21:41:32,271 epoch 7 - iter 36/121 - loss 0.12322713 - time (sec): 27.29 - samples/sec: 264.32 - lr: 0.000066 - momentum: 0.000000 | |
| 2023-10-08 21:41:41,269 epoch 7 - iter 48/121 - loss 0.12061266 - time (sec): 36.28 - samples/sec: 264.12 - lr: 0.000065 - momentum: 0.000000 | |
| 2023-10-08 21:41:50,423 epoch 7 - iter 60/121 - loss 0.12133471 - time (sec): 45.44 - samples/sec: 263.50 - lr: 0.000063 - momentum: 0.000000 | |
| 2023-10-08 21:41:59,980 epoch 7 - iter 72/121 - loss 0.12466745 - time (sec): 54.99 - samples/sec: 264.85 - lr: 0.000061 - momentum: 0.000000 | |
| 2023-10-08 21:42:09,959 epoch 7 - iter 84/121 - loss 0.12157869 - time (sec): 64.97 - samples/sec: 263.94 - lr: 0.000059 - momentum: 0.000000 | |
| 2023-10-08 21:42:19,799 epoch 7 - iter 96/121 - loss 0.12255567 - time (sec): 74.81 - samples/sec: 264.31 - lr: 0.000058 - momentum: 0.000000 | |
| 2023-10-08 21:42:29,242 epoch 7 - iter 108/121 - loss 0.12010957 - time (sec): 84.26 - samples/sec: 264.62 - lr: 0.000056 - momentum: 0.000000 | |
| 2023-10-08 21:42:38,404 epoch 7 - iter 120/121 - loss 0.11873726 - time (sec): 93.42 - samples/sec: 263.01 - lr: 0.000054 - momentum: 0.000000 | |
| 2023-10-08 21:42:39,023 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:42:39,023 EPOCH 7 done: loss 0.1193 - lr: 0.000054 | |
| 2023-10-08 21:42:45,499 DEV : loss 0.15980316698551178 - f1-score (micro avg) 0.8172 | |
| 2023-10-08 21:42:45,505 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:42:54,521 epoch 8 - iter 12/121 - loss 0.09638295 - time (sec): 9.01 - samples/sec: 258.69 - lr: 0.000052 - momentum: 0.000000 | |
| 2023-10-08 21:43:03,749 epoch 8 - iter 24/121 - loss 0.09546170 - time (sec): 18.24 - samples/sec: 267.40 - lr: 0.000051 - momentum: 0.000000 | |
| 2023-10-08 21:43:13,070 epoch 8 - iter 36/121 - loss 0.08445985 - time (sec): 27.56 - samples/sec: 267.34 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-08 21:43:22,538 epoch 8 - iter 48/121 - loss 0.08900468 - time (sec): 37.03 - samples/sec: 268.25 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-08 21:43:32,545 epoch 8 - iter 60/121 - loss 0.08897714 - time (sec): 47.04 - samples/sec: 267.88 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-08 21:43:41,929 epoch 8 - iter 72/121 - loss 0.09257647 - time (sec): 56.42 - samples/sec: 266.20 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-08 21:43:50,894 epoch 8 - iter 84/121 - loss 0.09215473 - time (sec): 65.39 - samples/sec: 264.18 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-08 21:44:00,184 epoch 8 - iter 96/121 - loss 0.09869736 - time (sec): 74.68 - samples/sec: 263.56 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-08 21:44:10,029 epoch 8 - iter 108/121 - loss 0.09812610 - time (sec): 84.52 - samples/sec: 264.24 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-08 21:44:19,112 epoch 8 - iter 120/121 - loss 0.09960459 - time (sec): 93.61 - samples/sec: 263.20 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-08 21:44:19,597 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:44:19,597 EPOCH 8 done: loss 0.0993 - lr: 0.000037 | |
| 2023-10-08 21:44:26,170 DEV : loss 0.15049293637275696 - f1-score (micro avg) 0.8193 | |
| 2023-10-08 21:44:26,179 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:44:35,831 epoch 9 - iter 12/121 - loss 0.06910157 - time (sec): 9.65 - samples/sec: 250.64 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-08 21:44:45,166 epoch 9 - iter 24/121 - loss 0.07832480 - time (sec): 18.99 - samples/sec: 257.66 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-08 21:44:54,473 epoch 9 - iter 36/121 - loss 0.07871226 - time (sec): 28.29 - samples/sec: 258.33 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-08 21:45:04,266 epoch 9 - iter 48/121 - loss 0.07976700 - time (sec): 38.09 - samples/sec: 262.69 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-08 21:45:13,300 epoch 9 - iter 60/121 - loss 0.07905326 - time (sec): 47.12 - samples/sec: 262.01 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-08 21:45:22,870 epoch 9 - iter 72/121 - loss 0.08407537 - time (sec): 56.69 - samples/sec: 262.69 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-08 21:45:32,345 epoch 9 - iter 84/121 - loss 0.08388859 - time (sec): 66.16 - samples/sec: 263.71 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-08 21:45:41,281 epoch 9 - iter 96/121 - loss 0.08408272 - time (sec): 75.10 - samples/sec: 262.09 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-08 21:45:50,852 epoch 9 - iter 108/121 - loss 0.08356777 - time (sec): 84.67 - samples/sec: 261.19 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-08 21:46:00,175 epoch 9 - iter 120/121 - loss 0.08488223 - time (sec): 94.00 - samples/sec: 261.99 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-08 21:46:00,664 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:46:00,664 EPOCH 9 done: loss 0.0846 - lr: 0.000019 | |
| 2023-10-08 21:46:07,146 DEV : loss 0.14527595043182373 - f1-score (micro avg) 0.8169 | |
| 2023-10-08 21:46:07,152 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:46:17,560 epoch 10 - iter 12/121 - loss 0.08353176 - time (sec): 10.41 - samples/sec: 273.58 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-08 21:46:26,823 epoch 10 - iter 24/121 - loss 0.08497474 - time (sec): 19.67 - samples/sec: 270.56 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-08 21:46:36,078 epoch 10 - iter 36/121 - loss 0.08914676 - time (sec): 28.92 - samples/sec: 270.12 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-08 21:46:44,735 epoch 10 - iter 48/121 - loss 0.08317598 - time (sec): 37.58 - samples/sec: 266.33 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-08 21:46:54,605 epoch 10 - iter 60/121 - loss 0.08104612 - time (sec): 47.45 - samples/sec: 266.14 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-08 21:47:04,434 epoch 10 - iter 72/121 - loss 0.08313807 - time (sec): 57.28 - samples/sec: 265.80 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-08 21:47:13,165 epoch 10 - iter 84/121 - loss 0.08085529 - time (sec): 66.01 - samples/sec: 264.09 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-08 21:47:22,358 epoch 10 - iter 96/121 - loss 0.08208188 - time (sec): 75.20 - samples/sec: 264.56 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-08 21:47:31,868 epoch 10 - iter 108/121 - loss 0.08103821 - time (sec): 84.72 - samples/sec: 264.24 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-08 21:47:40,524 epoch 10 - iter 120/121 - loss 0.07968567 - time (sec): 93.37 - samples/sec: 262.35 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-08 21:47:41,290 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:47:41,290 EPOCH 10 done: loss 0.0793 - lr: 0.000001 | |
| 2023-10-08 21:47:47,951 DEV : loss 0.14235417544841766 - f1-score (micro avg) 0.8225 | |
| 2023-10-08 21:47:48,823 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-08 21:47:48,824 Loading model from best epoch ... | |
| 2023-10-08 21:47:51,886 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 21:47:58,362 | |
| Results: | |
| - F-score (micro) 0.7703 | |
| - F-score (macro) 0.4636 | |
| - Accuracy 0.6582 | |
| By class: | |
| precision recall f1-score support | |
| pers 0.7468 0.8489 0.7946 139 | |
| scope 0.7655 0.8605 0.8102 129 | |
| work 0.7273 0.7000 0.7134 80 | |
| loc 0.0000 0.0000 0.0000 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.7500 0.7917 0.7703 360 | |
| macro avg 0.4479 0.4819 0.4636 360 | |
| weighted avg 0.7243 0.7917 0.7557 360 | |
| 2023-10-08 21:47:58,362 ---------------------------------------------------------------------------------------------------- | |