2023-10-11 03:16:41,684 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:16:41,686 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): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True) (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): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True) (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): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True) (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): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) ) (final_layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) (locked_dropout): LockedDropout(p=0.5) (linear): Linear(in_features=1472, out_features=17, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-11 03:16:41,686 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:16:41,686 MultiCorpus: 1166 train + 165 dev + 415 test sentences - NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator 2023-10-11 03:16:41,686 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:16:41,687 Train: 1166 sentences 2023-10-11 03:16:41,687 (train_with_dev=False, train_with_test=False) 2023-10-11 03:16:41,687 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:16:41,687 Training Params: 2023-10-11 03:16:41,687 - learning_rate: "0.00015" 2023-10-11 03:16:41,687 - mini_batch_size: "4" 2023-10-11 03:16:41,687 - max_epochs: "10" 2023-10-11 03:16:41,687 - shuffle: "True" 2023-10-11 03:16:41,687 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:16:41,687 Plugins: 2023-10-11 03:16:41,687 - TensorboardLogger 2023-10-11 03:16:41,687 - LinearScheduler | warmup_fraction: '0.1' 2023-10-11 03:16:41,687 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:16:41,687 Final evaluation on model from best epoch (best-model.pt) 2023-10-11 03:16:41,688 - metric: "('micro avg', 'f1-score')" 2023-10-11 03:16:41,688 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:16:41,688 Computation: 2023-10-11 03:16:41,688 - compute on device: cuda:0 2023-10-11 03:16:41,688 - embedding storage: none 2023-10-11 03:16:41,688 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:16:41,688 Model training base path: "hmbench-newseye/fi-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-5" 2023-10-11 03:16:41,688 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:16:41,688 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:16:41,688 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-11 03:16:51,822 epoch 1 - iter 29/292 - loss 2.81977350 - time (sec): 10.13 - samples/sec: 425.59 - lr: 0.000014 - momentum: 0.000000 2023-10-11 03:17:01,805 epoch 1 - iter 58/292 - loss 2.80688640 - time (sec): 20.12 - samples/sec: 410.33 - lr: 0.000029 - momentum: 0.000000 2023-10-11 03:17:12,096 epoch 1 - iter 87/292 - loss 2.78279036 - time (sec): 30.41 - samples/sec: 401.92 - lr: 0.000044 - momentum: 0.000000 2023-10-11 03:17:23,906 epoch 1 - iter 116/292 - loss 2.71003813 - time (sec): 42.22 - samples/sec: 413.94 - lr: 0.000059 - momentum: 0.000000 2023-10-11 03:17:34,740 epoch 1 - iter 145/292 - loss 2.62475305 - time (sec): 53.05 - samples/sec: 411.03 - lr: 0.000074 - momentum: 0.000000 2023-10-11 03:17:45,468 epoch 1 - iter 174/292 - loss 2.52043100 - time (sec): 63.78 - samples/sec: 419.27 - lr: 0.000089 - momentum: 0.000000 2023-10-11 03:17:56,403 epoch 1 - iter 203/292 - loss 2.39946272 - time (sec): 74.71 - samples/sec: 432.12 - lr: 0.000104 - momentum: 0.000000 2023-10-11 03:18:06,391 epoch 1 - iter 232/292 - loss 2.29647806 - time (sec): 84.70 - samples/sec: 430.10 - lr: 0.000119 - momentum: 0.000000 2023-10-11 03:18:16,949 epoch 1 - iter 261/292 - loss 2.17952313 - time (sec): 95.26 - samples/sec: 427.15 - lr: 0.000134 - momentum: 0.000000 2023-10-11 03:18:26,723 epoch 1 - iter 290/292 - loss 2.07842445 - time (sec): 105.03 - samples/sec: 422.13 - lr: 0.000148 - momentum: 0.000000 2023-10-11 03:18:27,176 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:18:27,176 EPOCH 1 done: loss 2.0752 - lr: 0.000148 2023-10-11 03:18:32,996 DEV : loss 0.7023366689682007 - f1-score (micro avg) 0.0 2023-10-11 03:18:33,006 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:18:42,653 epoch 2 - iter 29/292 - loss 0.73892904 - time (sec): 9.65 - samples/sec: 453.80 - lr: 0.000148 - momentum: 0.000000 2023-10-11 03:18:52,419 epoch 2 - iter 58/292 - loss 0.67633155 - time (sec): 19.41 - samples/sec: 442.23 - lr: 0.000147 - momentum: 0.000000 2023-10-11 03:19:02,214 epoch 2 - iter 87/292 - loss 0.66210392 - time (sec): 29.21 - samples/sec: 434.94 - lr: 0.000145 - momentum: 0.000000 2023-10-11 03:19:12,942 epoch 2 - iter 116/292 - loss 0.60646101 - time (sec): 39.93 - samples/sec: 435.65 - lr: 0.000143 - momentum: 0.000000 2023-10-11 03:19:23,013 epoch 2 - iter 145/292 - loss 0.65710441 - time (sec): 50.00 - samples/sec: 445.08 - lr: 0.000142 - momentum: 0.000000 2023-10-11 03:19:33,309 epoch 2 - iter 174/292 - loss 0.62278384 - time (sec): 60.30 - samples/sec: 443.37 - lr: 0.000140 - momentum: 0.000000 2023-10-11 03:19:43,005 epoch 2 - iter 203/292 - loss 0.59076254 - time (sec): 70.00 - samples/sec: 446.10 - lr: 0.000138 - momentum: 0.000000 2023-10-11 03:19:51,530 epoch 2 - iter 232/292 - loss 0.56424704 - time (sec): 78.52 - samples/sec: 444.22 - lr: 0.000137 - momentum: 0.000000 2023-10-11 03:20:01,917 epoch 2 - iter 261/292 - loss 0.55417964 - time (sec): 88.91 - samples/sec: 438.36 - lr: 0.000135 - momentum: 0.000000 2023-10-11 03:20:13,521 epoch 2 - iter 290/292 - loss 0.53594965 - time (sec): 100.51 - samples/sec: 439.75 - lr: 0.000134 - momentum: 0.000000 2023-10-11 03:20:14,065 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:20:14,066 EPOCH 2 done: loss 0.5351 - lr: 0.000134 2023-10-11 03:20:20,195 DEV : loss 0.297545462846756 - f1-score (micro avg) 0.0 2023-10-11 03:20:20,205 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:20:30,000 epoch 3 - iter 29/292 - loss 0.37459476 - time (sec): 9.79 - samples/sec: 407.46 - lr: 0.000132 - momentum: 0.000000 2023-10-11 03:20:38,908 epoch 3 - iter 58/292 - loss 0.36871425 - time (sec): 18.70 - samples/sec: 425.66 - lr: 0.000130 - momentum: 0.000000 2023-10-11 03:20:48,697 epoch 3 - iter 87/292 - loss 0.34885003 - time (sec): 28.49 - samples/sec: 439.40 - lr: 0.000128 - momentum: 0.000000 2023-10-11 03:20:58,273 epoch 3 - iter 116/292 - loss 0.32808207 - time (sec): 38.06 - samples/sec: 451.47 - lr: 0.000127 - momentum: 0.000000 2023-10-11 03:21:07,349 epoch 3 - iter 145/292 - loss 0.32374212 - time (sec): 47.14 - samples/sec: 452.13 - lr: 0.000125 - momentum: 0.000000 2023-10-11 03:21:17,462 epoch 3 - iter 174/292 - loss 0.30495891 - time (sec): 57.25 - samples/sec: 455.18 - lr: 0.000123 - momentum: 0.000000 2023-10-11 03:21:27,598 epoch 3 - iter 203/292 - loss 0.32430122 - time (sec): 67.39 - samples/sec: 455.47 - lr: 0.000122 - momentum: 0.000000 2023-10-11 03:21:36,787 epoch 3 - iter 232/292 - loss 0.32165796 - time (sec): 76.58 - samples/sec: 452.27 - lr: 0.000120 - momentum: 0.000000 2023-10-11 03:21:47,217 epoch 3 - iter 261/292 - loss 0.31557249 - time (sec): 87.01 - samples/sec: 456.71 - lr: 0.000119 - momentum: 0.000000 2023-10-11 03:21:56,871 epoch 3 - iter 290/292 - loss 0.31177726 - time (sec): 96.66 - samples/sec: 456.37 - lr: 0.000117 - momentum: 0.000000 2023-10-11 03:21:57,461 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:21:57,461 EPOCH 3 done: loss 0.3101 - lr: 0.000117 2023-10-11 03:22:03,017 DEV : loss 0.2035694271326065 - f1-score (micro avg) 0.4298 2023-10-11 03:22:03,027 saving best model 2023-10-11 03:22:04,096 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:22:14,038 epoch 4 - iter 29/292 - loss 0.20110119 - time (sec): 9.94 - samples/sec: 475.37 - lr: 0.000115 - momentum: 0.000000 2023-10-11 03:22:24,401 epoch 4 - iter 58/292 - loss 0.17826557 - time (sec): 20.30 - samples/sec: 495.26 - lr: 0.000113 - momentum: 0.000000 2023-10-11 03:22:34,413 epoch 4 - iter 87/292 - loss 0.20996155 - time (sec): 30.31 - samples/sec: 484.16 - lr: 0.000112 - momentum: 0.000000 2023-10-11 03:22:44,346 epoch 4 - iter 116/292 - loss 0.21692770 - time (sec): 40.25 - samples/sec: 482.16 - lr: 0.000110 - momentum: 0.000000 2023-10-11 03:22:53,827 epoch 4 - iter 145/292 - loss 0.21814470 - time (sec): 49.73 - samples/sec: 479.47 - lr: 0.000108 - momentum: 0.000000 2023-10-11 03:23:03,233 epoch 4 - iter 174/292 - loss 0.21089514 - time (sec): 59.14 - samples/sec: 474.44 - lr: 0.000107 - momentum: 0.000000 2023-10-11 03:23:12,483 epoch 4 - iter 203/292 - loss 0.21084487 - time (sec): 68.38 - samples/sec: 467.12 - lr: 0.000105 - momentum: 0.000000 2023-10-11 03:23:22,118 epoch 4 - iter 232/292 - loss 0.20482475 - time (sec): 78.02 - samples/sec: 463.58 - lr: 0.000104 - momentum: 0.000000 2023-10-11 03:23:30,759 epoch 4 - iter 261/292 - loss 0.20151559 - time (sec): 86.66 - samples/sec: 456.03 - lr: 0.000102 - momentum: 0.000000 2023-10-11 03:23:40,714 epoch 4 - iter 290/292 - loss 0.20188943 - time (sec): 96.62 - samples/sec: 458.75 - lr: 0.000100 - momentum: 0.000000 2023-10-11 03:23:41,130 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:23:41,131 EPOCH 4 done: loss 0.2023 - lr: 0.000100 2023-10-11 03:23:46,947 DEV : loss 0.15248891711235046 - f1-score (micro avg) 0.6021 2023-10-11 03:23:46,957 saving best model 2023-10-11 03:23:49,630 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:23:59,366 epoch 5 - iter 29/292 - loss 0.15498313 - time (sec): 9.73 - samples/sec: 459.85 - lr: 0.000098 - momentum: 0.000000 2023-10-11 03:24:09,829 epoch 5 - iter 58/292 - loss 0.13333345 - time (sec): 20.19 - samples/sec: 473.04 - lr: 0.000097 - momentum: 0.000000 2023-10-11 03:24:20,042 epoch 5 - iter 87/292 - loss 0.14821866 - time (sec): 30.41 - samples/sec: 470.84 - lr: 0.000095 - momentum: 0.000000 2023-10-11 03:24:30,243 epoch 5 - iter 116/292 - loss 0.14730098 - time (sec): 40.61 - samples/sec: 470.32 - lr: 0.000093 - momentum: 0.000000 2023-10-11 03:24:40,156 epoch 5 - iter 145/292 - loss 0.15044218 - time (sec): 50.52 - samples/sec: 466.81 - lr: 0.000092 - momentum: 0.000000 2023-10-11 03:24:50,125 epoch 5 - iter 174/292 - loss 0.14812398 - time (sec): 60.49 - samples/sec: 460.27 - lr: 0.000090 - momentum: 0.000000 2023-10-11 03:24:59,576 epoch 5 - iter 203/292 - loss 0.14525037 - time (sec): 69.94 - samples/sec: 454.03 - lr: 0.000089 - momentum: 0.000000 2023-10-11 03:25:09,036 epoch 5 - iter 232/292 - loss 0.14314177 - time (sec): 79.40 - samples/sec: 446.58 - lr: 0.000087 - momentum: 0.000000 2023-10-11 03:25:19,457 epoch 5 - iter 261/292 - loss 0.13766737 - time (sec): 89.82 - samples/sec: 448.05 - lr: 0.000085 - momentum: 0.000000 2023-10-11 03:25:29,102 epoch 5 - iter 290/292 - loss 0.13520449 - time (sec): 99.47 - samples/sec: 445.86 - lr: 0.000084 - momentum: 0.000000 2023-10-11 03:25:29,548 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:25:29,549 EPOCH 5 done: loss 0.1354 - lr: 0.000084 2023-10-11 03:25:35,482 DEV : loss 0.12166187167167664 - f1-score (micro avg) 0.7455 2023-10-11 03:25:35,492 saving best model 2023-10-11 03:25:38,127 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:25:47,622 epoch 6 - iter 29/292 - loss 0.08960265 - time (sec): 9.49 - samples/sec: 393.43 - lr: 0.000082 - momentum: 0.000000 2023-10-11 03:25:57,785 epoch 6 - iter 58/292 - loss 0.12767978 - time (sec): 19.65 - samples/sec: 396.46 - lr: 0.000080 - momentum: 0.000000 2023-10-11 03:26:08,293 epoch 6 - iter 87/292 - loss 0.11619278 - time (sec): 30.16 - samples/sec: 412.04 - lr: 0.000078 - momentum: 0.000000 2023-10-11 03:26:18,684 epoch 6 - iter 116/292 - loss 0.11102256 - time (sec): 40.55 - samples/sec: 410.65 - lr: 0.000077 - momentum: 0.000000 2023-10-11 03:26:29,492 epoch 6 - iter 145/292 - loss 0.10620087 - time (sec): 51.36 - samples/sec: 420.53 - lr: 0.000075 - momentum: 0.000000 2023-10-11 03:26:40,798 epoch 6 - iter 174/292 - loss 0.09868087 - time (sec): 62.67 - samples/sec: 424.26 - lr: 0.000074 - momentum: 0.000000 2023-10-11 03:26:50,496 epoch 6 - iter 203/292 - loss 0.10008914 - time (sec): 72.36 - samples/sec: 420.45 - lr: 0.000072 - momentum: 0.000000 2023-10-11 03:27:00,772 epoch 6 - iter 232/292 - loss 0.09776359 - time (sec): 82.64 - samples/sec: 412.02 - lr: 0.000070 - momentum: 0.000000 2023-10-11 03:27:12,362 epoch 6 - iter 261/292 - loss 0.09830523 - time (sec): 94.23 - samples/sec: 418.52 - lr: 0.000069 - momentum: 0.000000 2023-10-11 03:27:22,801 epoch 6 - iter 290/292 - loss 0.09807018 - time (sec): 104.67 - samples/sec: 421.15 - lr: 0.000067 - momentum: 0.000000 2023-10-11 03:27:23,552 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:27:23,553 EPOCH 6 done: loss 0.0974 - lr: 0.000067 2023-10-11 03:27:29,960 DEV : loss 0.11362636834383011 - f1-score (micro avg) 0.7778 2023-10-11 03:27:29,970 saving best model 2023-10-11 03:27:32,668 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:27:42,352 epoch 7 - iter 29/292 - loss 0.07419722 - time (sec): 9.67 - samples/sec: 394.50 - lr: 0.000065 - momentum: 0.000000 2023-10-11 03:27:52,002 epoch 7 - iter 58/292 - loss 0.07402345 - time (sec): 19.32 - samples/sec: 410.05 - lr: 0.000063 - momentum: 0.000000 2023-10-11 03:28:01,047 epoch 7 - iter 87/292 - loss 0.07690943 - time (sec): 28.37 - samples/sec: 401.83 - lr: 0.000062 - momentum: 0.000000 2023-10-11 03:28:12,534 epoch 7 - iter 116/292 - loss 0.07959332 - time (sec): 39.85 - samples/sec: 427.33 - lr: 0.000060 - momentum: 0.000000 2023-10-11 03:28:22,410 epoch 7 - iter 145/292 - loss 0.07518449 - time (sec): 49.73 - samples/sec: 424.22 - lr: 0.000059 - momentum: 0.000000 2023-10-11 03:28:32,859 epoch 7 - iter 174/292 - loss 0.07895677 - time (sec): 60.18 - samples/sec: 419.98 - lr: 0.000057 - momentum: 0.000000 2023-10-11 03:28:42,965 epoch 7 - iter 203/292 - loss 0.07832199 - time (sec): 70.29 - samples/sec: 422.31 - lr: 0.000055 - momentum: 0.000000 2023-10-11 03:28:53,183 epoch 7 - iter 232/292 - loss 0.07419731 - time (sec): 80.50 - samples/sec: 428.64 - lr: 0.000054 - momentum: 0.000000 2023-10-11 03:29:03,235 epoch 7 - iter 261/292 - loss 0.07485255 - time (sec): 90.56 - samples/sec: 433.91 - lr: 0.000052 - momentum: 0.000000 2023-10-11 03:29:13,519 epoch 7 - iter 290/292 - loss 0.07487242 - time (sec): 100.84 - samples/sec: 438.77 - lr: 0.000050 - momentum: 0.000000 2023-10-11 03:29:14,009 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:29:14,010 EPOCH 7 done: loss 0.0749 - lr: 0.000050 2023-10-11 03:29:19,721 DEV : loss 0.1100909486413002 - f1-score (micro avg) 0.7894 2023-10-11 03:29:19,730 saving best model 2023-10-11 03:29:22,380 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:29:32,069 epoch 8 - iter 29/292 - loss 0.06858685 - time (sec): 9.68 - samples/sec: 423.14 - lr: 0.000048 - momentum: 0.000000 2023-10-11 03:29:41,880 epoch 8 - iter 58/292 - loss 0.06385058 - time (sec): 19.50 - samples/sec: 433.12 - lr: 0.000047 - momentum: 0.000000 2023-10-11 03:29:51,908 epoch 8 - iter 87/292 - loss 0.06960465 - time (sec): 29.52 - samples/sec: 433.10 - lr: 0.000045 - momentum: 0.000000 2023-10-11 03:30:03,134 epoch 8 - iter 116/292 - loss 0.07164164 - time (sec): 40.75 - samples/sec: 437.11 - lr: 0.000044 - momentum: 0.000000 2023-10-11 03:30:13,585 epoch 8 - iter 145/292 - loss 0.07036557 - time (sec): 51.20 - samples/sec: 432.87 - lr: 0.000042 - momentum: 0.000000 2023-10-11 03:30:22,910 epoch 8 - iter 174/292 - loss 0.06603532 - time (sec): 60.53 - samples/sec: 427.80 - lr: 0.000040 - momentum: 0.000000 2023-10-11 03:30:33,264 epoch 8 - iter 203/292 - loss 0.06513753 - time (sec): 70.88 - samples/sec: 433.78 - lr: 0.000039 - momentum: 0.000000 2023-10-11 03:30:43,326 epoch 8 - iter 232/292 - loss 0.06712616 - time (sec): 80.94 - samples/sec: 436.36 - lr: 0.000037 - momentum: 0.000000 2023-10-11 03:30:52,519 epoch 8 - iter 261/292 - loss 0.06210932 - time (sec): 90.13 - samples/sec: 434.89 - lr: 0.000035 - momentum: 0.000000 2023-10-11 03:31:02,720 epoch 8 - iter 290/292 - loss 0.05877080 - time (sec): 100.34 - samples/sec: 440.52 - lr: 0.000034 - momentum: 0.000000 2023-10-11 03:31:03,298 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:31:03,298 EPOCH 8 done: loss 0.0588 - lr: 0.000034 2023-10-11 03:31:08,969 DEV : loss 0.11329486221075058 - f1-score (micro avg) 0.7913 2023-10-11 03:31:08,978 saving best model 2023-10-11 03:31:11,608 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:31:21,665 epoch 9 - iter 29/292 - loss 0.04382080 - time (sec): 10.05 - samples/sec: 457.28 - lr: 0.000032 - momentum: 0.000000 2023-10-11 03:31:30,877 epoch 9 - iter 58/292 - loss 0.05356168 - time (sec): 19.26 - samples/sec: 427.78 - lr: 0.000030 - momentum: 0.000000 2023-10-11 03:31:40,507 epoch 9 - iter 87/292 - loss 0.05086497 - time (sec): 28.89 - samples/sec: 429.42 - lr: 0.000029 - momentum: 0.000000 2023-10-11 03:31:50,143 epoch 9 - iter 116/292 - loss 0.05195064 - time (sec): 38.53 - samples/sec: 426.77 - lr: 0.000027 - momentum: 0.000000 2023-10-11 03:32:00,316 epoch 9 - iter 145/292 - loss 0.05449964 - time (sec): 48.70 - samples/sec: 441.65 - lr: 0.000025 - momentum: 0.000000 2023-10-11 03:32:09,886 epoch 9 - iter 174/292 - loss 0.05152749 - time (sec): 58.27 - samples/sec: 448.59 - lr: 0.000024 - momentum: 0.000000 2023-10-11 03:32:19,473 epoch 9 - iter 203/292 - loss 0.04877327 - time (sec): 67.86 - samples/sec: 452.81 - lr: 0.000022 - momentum: 0.000000 2023-10-11 03:32:29,586 epoch 9 - iter 232/292 - loss 0.04997456 - time (sec): 77.97 - samples/sec: 459.62 - lr: 0.000020 - momentum: 0.000000 2023-10-11 03:32:38,528 epoch 9 - iter 261/292 - loss 0.04881578 - time (sec): 86.92 - samples/sec: 459.93 - lr: 0.000019 - momentum: 0.000000 2023-10-11 03:32:47,820 epoch 9 - iter 290/292 - loss 0.04899412 - time (sec): 96.21 - samples/sec: 460.02 - lr: 0.000017 - momentum: 0.000000 2023-10-11 03:32:48,264 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:32:48,264 EPOCH 9 done: loss 0.0489 - lr: 0.000017 2023-10-11 03:32:53,792 DEV : loss 0.11269763857126236 - f1-score (micro avg) 0.7904 2023-10-11 03:32:53,801 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:33:02,891 epoch 10 - iter 29/292 - loss 0.04691422 - time (sec): 9.09 - samples/sec: 463.71 - lr: 0.000015 - momentum: 0.000000 2023-10-11 03:33:12,045 epoch 10 - iter 58/292 - loss 0.05143091 - time (sec): 18.24 - samples/sec: 457.69 - lr: 0.000014 - momentum: 0.000000 2023-10-11 03:33:22,171 epoch 10 - iter 87/292 - loss 0.04523086 - time (sec): 28.37 - samples/sec: 465.70 - lr: 0.000012 - momentum: 0.000000 2023-10-11 03:33:31,686 epoch 10 - iter 116/292 - loss 0.04088964 - time (sec): 37.88 - samples/sec: 465.65 - lr: 0.000010 - momentum: 0.000000 2023-10-11 03:33:41,168 epoch 10 - iter 145/292 - loss 0.04323243 - time (sec): 47.36 - samples/sec: 465.18 - lr: 0.000009 - momentum: 0.000000 2023-10-11 03:33:50,228 epoch 10 - iter 174/292 - loss 0.04318784 - time (sec): 56.43 - samples/sec: 457.83 - lr: 0.000007 - momentum: 0.000000 2023-10-11 03:34:00,927 epoch 10 - iter 203/292 - loss 0.04500761 - time (sec): 67.12 - samples/sec: 461.65 - lr: 0.000005 - momentum: 0.000000 2023-10-11 03:34:10,593 epoch 10 - iter 232/292 - loss 0.04463928 - time (sec): 76.79 - samples/sec: 458.99 - lr: 0.000004 - momentum: 0.000000 2023-10-11 03:34:20,237 epoch 10 - iter 261/292 - loss 0.04516349 - time (sec): 86.43 - samples/sec: 460.74 - lr: 0.000002 - momentum: 0.000000 2023-10-11 03:34:29,953 epoch 10 - iter 290/292 - loss 0.04578337 - time (sec): 96.15 - samples/sec: 457.82 - lr: 0.000000 - momentum: 0.000000 2023-10-11 03:34:30,663 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:34:30,664 EPOCH 10 done: loss 0.0454 - lr: 0.000000 2023-10-11 03:34:36,393 DEV : loss 0.11296340078115463 - f1-score (micro avg) 0.7913 2023-10-11 03:34:37,317 ---------------------------------------------------------------------------------------------------- 2023-10-11 03:34:37,318 Loading model from best epoch ... 2023-10-11 03:34:41,397 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd 2023-10-11 03:34:54,193 Results: - F-score (micro) 0.7433 - F-score (macro) 0.6945 - Accuracy 0.6094 By class: precision recall f1-score support PER 0.8065 0.8621 0.8333 348 LOC 0.6047 0.7854 0.6833 261 ORG 0.4255 0.3846 0.4040 52 HumanProd 0.9000 0.8182 0.8571 22 micro avg 0.6979 0.7950 0.7433 683 macro avg 0.6842 0.7126 0.6945 683 weighted avg 0.7034 0.7950 0.7441 683 2023-10-11 03:34:54,193 ----------------------------------------------------------------------------------------------------