| 2023-10-11 08:27:56,009 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:27:56,011 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 08:27:56,011 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:27:56,012 MultiCorpus: 1085 train + 148 dev + 364 test sentences | |
| - NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator | |
| 2023-10-11 08:27:56,012 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:27:56,012 Train: 1085 sentences | |
| 2023-10-11 08:27:56,012 (train_with_dev=False, train_with_test=False) | |
| 2023-10-11 08:27:56,012 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:27:56,012 Training Params: | |
| 2023-10-11 08:27:56,012 - learning_rate: "0.00015" | |
| 2023-10-11 08:27:56,012 - mini_batch_size: "4" | |
| 2023-10-11 08:27:56,012 - max_epochs: "10" | |
| 2023-10-11 08:27:56,012 - shuffle: "True" | |
| 2023-10-11 08:27:56,013 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:27:56,013 Plugins: | |
| 2023-10-11 08:27:56,013 - TensorboardLogger | |
| 2023-10-11 08:27:56,013 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-11 08:27:56,013 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:27:56,013 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-11 08:27:56,013 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-11 08:27:56,013 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:27:56,013 Computation: | |
| 2023-10-11 08:27:56,013 - compute on device: cuda:0 | |
| 2023-10-11 08:27:56,013 - embedding storage: none | |
| 2023-10-11 08:27:56,013 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:27:56,013 Model training base path: "hmbench-newseye/sv-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-11 08:27:56,014 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:27:56,014 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:27:56,014 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-11 08:28:05,746 epoch 1 - iter 27/272 - loss 2.82527220 - time (sec): 9.73 - samples/sec: 536.16 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-11 08:28:15,634 epoch 1 - iter 54/272 - loss 2.81578887 - time (sec): 19.62 - samples/sec: 555.40 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-11 08:28:25,349 epoch 1 - iter 81/272 - loss 2.79743887 - time (sec): 29.33 - samples/sec: 550.39 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-11 08:28:35,638 epoch 1 - iter 108/272 - loss 2.75063780 - time (sec): 39.62 - samples/sec: 552.67 - lr: 0.000059 - momentum: 0.000000 | |
| 2023-10-11 08:28:44,316 epoch 1 - iter 135/272 - loss 2.68811497 - time (sec): 48.30 - samples/sec: 539.80 - lr: 0.000074 - momentum: 0.000000 | |
| 2023-10-11 08:28:53,980 epoch 1 - iter 162/272 - loss 2.58887886 - time (sec): 57.96 - samples/sec: 543.38 - lr: 0.000089 - momentum: 0.000000 | |
| 2023-10-11 08:29:03,748 epoch 1 - iter 189/272 - loss 2.47848820 - time (sec): 67.73 - samples/sec: 544.97 - lr: 0.000104 - momentum: 0.000000 | |
| 2023-10-11 08:29:13,570 epoch 1 - iter 216/272 - loss 2.36431382 - time (sec): 77.55 - samples/sec: 544.94 - lr: 0.000119 - momentum: 0.000000 | |
| 2023-10-11 08:29:23,147 epoch 1 - iter 243/272 - loss 2.25308445 - time (sec): 87.13 - samples/sec: 542.88 - lr: 0.000133 - momentum: 0.000000 | |
| 2023-10-11 08:29:32,099 epoch 1 - iter 270/272 - loss 2.14779837 - time (sec): 96.08 - samples/sec: 538.86 - lr: 0.000148 - momentum: 0.000000 | |
| 2023-10-11 08:29:32,557 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:29:32,557 EPOCH 1 done: loss 2.1429 - lr: 0.000148 | |
| 2023-10-11 08:29:37,551 DEV : loss 0.8090639114379883 - f1-score (micro avg) 0.0 | |
| 2023-10-11 08:29:37,560 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:29:46,988 epoch 2 - iter 27/272 - loss 0.79380094 - time (sec): 9.43 - samples/sec: 514.96 - lr: 0.000148 - momentum: 0.000000 | |
| 2023-10-11 08:29:56,691 epoch 2 - iter 54/272 - loss 0.69639882 - time (sec): 19.13 - samples/sec: 524.13 - lr: 0.000147 - momentum: 0.000000 | |
| 2023-10-11 08:30:06,795 epoch 2 - iter 81/272 - loss 0.66949044 - time (sec): 29.23 - samples/sec: 528.89 - lr: 0.000145 - momentum: 0.000000 | |
| 2023-10-11 08:30:16,467 epoch 2 - iter 108/272 - loss 0.61712378 - time (sec): 38.91 - samples/sec: 531.11 - lr: 0.000143 - momentum: 0.000000 | |
| 2023-10-11 08:30:25,467 epoch 2 - iter 135/272 - loss 0.59387096 - time (sec): 47.90 - samples/sec: 523.98 - lr: 0.000142 - momentum: 0.000000 | |
| 2023-10-11 08:30:35,702 epoch 2 - iter 162/272 - loss 0.57455996 - time (sec): 58.14 - samples/sec: 533.22 - lr: 0.000140 - momentum: 0.000000 | |
| 2023-10-11 08:30:45,302 epoch 2 - iter 189/272 - loss 0.55870790 - time (sec): 67.74 - samples/sec: 532.34 - lr: 0.000138 - momentum: 0.000000 | |
| 2023-10-11 08:30:55,971 epoch 2 - iter 216/272 - loss 0.51696139 - time (sec): 78.41 - samples/sec: 538.06 - lr: 0.000137 - momentum: 0.000000 | |
| 2023-10-11 08:31:05,589 epoch 2 - iter 243/272 - loss 0.49305630 - time (sec): 88.03 - samples/sec: 536.68 - lr: 0.000135 - momentum: 0.000000 | |
| 2023-10-11 08:31:14,784 epoch 2 - iter 270/272 - loss 0.47744906 - time (sec): 97.22 - samples/sec: 531.86 - lr: 0.000134 - momentum: 0.000000 | |
| 2023-10-11 08:31:15,351 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:31:15,351 EPOCH 2 done: loss 0.4760 - lr: 0.000134 | |
| 2023-10-11 08:31:21,289 DEV : loss 0.2697048783302307 - f1-score (micro avg) 0.2098 | |
| 2023-10-11 08:31:21,297 saving best model | |
| 2023-10-11 08:31:22,188 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:31:30,509 epoch 3 - iter 27/272 - loss 0.31259444 - time (sec): 8.32 - samples/sec: 479.62 - lr: 0.000132 - momentum: 0.000000 | |
| 2023-10-11 08:31:40,176 epoch 3 - iter 54/272 - loss 0.28524280 - time (sec): 17.99 - samples/sec: 513.63 - lr: 0.000130 - momentum: 0.000000 | |
| 2023-10-11 08:31:49,465 epoch 3 - iter 81/272 - loss 0.26782153 - time (sec): 27.27 - samples/sec: 526.80 - lr: 0.000128 - momentum: 0.000000 | |
| 2023-10-11 08:31:58,900 epoch 3 - iter 108/272 - loss 0.26941576 - time (sec): 36.71 - samples/sec: 530.95 - lr: 0.000127 - momentum: 0.000000 | |
| 2023-10-11 08:32:08,682 epoch 3 - iter 135/272 - loss 0.27249015 - time (sec): 46.49 - samples/sec: 540.93 - lr: 0.000125 - momentum: 0.000000 | |
| 2023-10-11 08:32:18,933 epoch 3 - iter 162/272 - loss 0.26692047 - time (sec): 56.74 - samples/sec: 544.05 - lr: 0.000123 - momentum: 0.000000 | |
| 2023-10-11 08:32:28,570 epoch 3 - iter 189/272 - loss 0.27090264 - time (sec): 66.38 - samples/sec: 546.78 - lr: 0.000122 - momentum: 0.000000 | |
| 2023-10-11 08:32:37,583 epoch 3 - iter 216/272 - loss 0.26935437 - time (sec): 75.39 - samples/sec: 543.16 - lr: 0.000120 - momentum: 0.000000 | |
| 2023-10-11 08:32:48,200 epoch 3 - iter 243/272 - loss 0.26035213 - time (sec): 86.01 - samples/sec: 547.64 - lr: 0.000119 - momentum: 0.000000 | |
| 2023-10-11 08:32:57,570 epoch 3 - iter 270/272 - loss 0.25719703 - time (sec): 95.38 - samples/sec: 542.54 - lr: 0.000117 - momentum: 0.000000 | |
| 2023-10-11 08:32:58,034 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:32:58,034 EPOCH 3 done: loss 0.2574 - lr: 0.000117 | |
| 2023-10-11 08:33:03,831 DEV : loss 0.2006431519985199 - f1-score (micro avg) 0.5292 | |
| 2023-10-11 08:33:03,840 saving best model | |
| 2023-10-11 08:33:10,036 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:33:19,376 epoch 4 - iter 27/272 - loss 0.21238760 - time (sec): 9.33 - samples/sec: 506.80 - lr: 0.000115 - momentum: 0.000000 | |
| 2023-10-11 08:33:29,507 epoch 4 - iter 54/272 - loss 0.19368792 - time (sec): 19.47 - samples/sec: 542.44 - lr: 0.000113 - momentum: 0.000000 | |
| 2023-10-11 08:33:38,980 epoch 4 - iter 81/272 - loss 0.18826367 - time (sec): 28.94 - samples/sec: 537.79 - lr: 0.000112 - momentum: 0.000000 | |
| 2023-10-11 08:33:49,054 epoch 4 - iter 108/272 - loss 0.18386043 - time (sec): 39.01 - samples/sec: 544.59 - lr: 0.000110 - momentum: 0.000000 | |
| 2023-10-11 08:33:58,456 epoch 4 - iter 135/272 - loss 0.17239772 - time (sec): 48.41 - samples/sec: 547.58 - lr: 0.000108 - momentum: 0.000000 | |
| 2023-10-11 08:34:07,665 epoch 4 - iter 162/272 - loss 0.16928535 - time (sec): 57.62 - samples/sec: 544.77 - lr: 0.000107 - momentum: 0.000000 | |
| 2023-10-11 08:34:18,217 epoch 4 - iter 189/272 - loss 0.16232035 - time (sec): 68.18 - samples/sec: 551.16 - lr: 0.000105 - momentum: 0.000000 | |
| 2023-10-11 08:34:28,323 epoch 4 - iter 216/272 - loss 0.16453145 - time (sec): 78.28 - samples/sec: 546.45 - lr: 0.000103 - momentum: 0.000000 | |
| 2023-10-11 08:34:37,908 epoch 4 - iter 243/272 - loss 0.16620141 - time (sec): 87.87 - samples/sec: 540.65 - lr: 0.000102 - momentum: 0.000000 | |
| 2023-10-11 08:34:46,783 epoch 4 - iter 270/272 - loss 0.16558176 - time (sec): 96.74 - samples/sec: 535.57 - lr: 0.000100 - momentum: 0.000000 | |
| 2023-10-11 08:34:47,194 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:34:47,194 EPOCH 4 done: loss 0.1654 - lr: 0.000100 | |
| 2023-10-11 08:34:52,786 DEV : loss 0.15305934846401215 - f1-score (micro avg) 0.6691 | |
| 2023-10-11 08:34:52,794 saving best model | |
| 2023-10-11 08:34:57,813 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:35:08,083 epoch 5 - iter 27/272 - loss 0.11542380 - time (sec): 10.27 - samples/sec: 539.29 - lr: 0.000098 - momentum: 0.000000 | |
| 2023-10-11 08:35:17,686 epoch 5 - iter 54/272 - loss 0.12296413 - time (sec): 19.87 - samples/sec: 526.22 - lr: 0.000097 - momentum: 0.000000 | |
| 2023-10-11 08:35:26,789 epoch 5 - iter 81/272 - loss 0.12324075 - time (sec): 28.97 - samples/sec: 512.37 - lr: 0.000095 - momentum: 0.000000 | |
| 2023-10-11 08:35:36,462 epoch 5 - iter 108/272 - loss 0.11739274 - time (sec): 38.64 - samples/sec: 515.21 - lr: 0.000093 - momentum: 0.000000 | |
| 2023-10-11 08:35:46,648 epoch 5 - iter 135/272 - loss 0.11863495 - time (sec): 48.83 - samples/sec: 521.52 - lr: 0.000092 - momentum: 0.000000 | |
| 2023-10-11 08:35:56,318 epoch 5 - iter 162/272 - loss 0.11563924 - time (sec): 58.50 - samples/sec: 519.98 - lr: 0.000090 - momentum: 0.000000 | |
| 2023-10-11 08:36:06,215 epoch 5 - iter 189/272 - loss 0.11198930 - time (sec): 68.40 - samples/sec: 518.10 - lr: 0.000088 - momentum: 0.000000 | |
| 2023-10-11 08:36:16,740 epoch 5 - iter 216/272 - loss 0.10927879 - time (sec): 78.92 - samples/sec: 522.45 - lr: 0.000087 - momentum: 0.000000 | |
| 2023-10-11 08:36:26,361 epoch 5 - iter 243/272 - loss 0.11127709 - time (sec): 88.54 - samples/sec: 519.88 - lr: 0.000085 - momentum: 0.000000 | |
| 2023-10-11 08:36:36,707 epoch 5 - iter 270/272 - loss 0.10945143 - time (sec): 98.89 - samples/sec: 523.39 - lr: 0.000084 - momentum: 0.000000 | |
| 2023-10-11 08:36:37,167 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:36:37,167 EPOCH 5 done: loss 0.1097 - lr: 0.000084 | |
| 2023-10-11 08:36:43,351 DEV : loss 0.14368949830532074 - f1-score (micro avg) 0.7306 | |
| 2023-10-11 08:36:43,359 saving best model | |
| 2023-10-11 08:36:45,916 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:36:56,115 epoch 6 - iter 27/272 - loss 0.07539543 - time (sec): 10.19 - samples/sec: 525.87 - lr: 0.000082 - momentum: 0.000000 | |
| 2023-10-11 08:37:05,931 epoch 6 - iter 54/272 - loss 0.09543769 - time (sec): 20.01 - samples/sec: 506.27 - lr: 0.000080 - momentum: 0.000000 | |
| 2023-10-11 08:37:16,403 epoch 6 - iter 81/272 - loss 0.09161672 - time (sec): 30.48 - samples/sec: 517.70 - lr: 0.000078 - momentum: 0.000000 | |
| 2023-10-11 08:37:25,910 epoch 6 - iter 108/272 - loss 0.08558701 - time (sec): 39.99 - samples/sec: 514.59 - lr: 0.000077 - momentum: 0.000000 | |
| 2023-10-11 08:37:35,143 epoch 6 - iter 135/272 - loss 0.08995611 - time (sec): 49.22 - samples/sec: 507.75 - lr: 0.000075 - momentum: 0.000000 | |
| 2023-10-11 08:37:44,963 epoch 6 - iter 162/272 - loss 0.08413813 - time (sec): 59.04 - samples/sec: 509.34 - lr: 0.000073 - momentum: 0.000000 | |
| 2023-10-11 08:37:54,464 epoch 6 - iter 189/272 - loss 0.08426293 - time (sec): 68.54 - samples/sec: 507.32 - lr: 0.000072 - momentum: 0.000000 | |
| 2023-10-11 08:38:05,043 epoch 6 - iter 216/272 - loss 0.08373579 - time (sec): 79.12 - samples/sec: 510.97 - lr: 0.000070 - momentum: 0.000000 | |
| 2023-10-11 08:38:15,537 epoch 6 - iter 243/272 - loss 0.07977679 - time (sec): 89.62 - samples/sec: 514.48 - lr: 0.000069 - momentum: 0.000000 | |
| 2023-10-11 08:38:25,676 epoch 6 - iter 270/272 - loss 0.07725078 - time (sec): 99.76 - samples/sec: 517.38 - lr: 0.000067 - momentum: 0.000000 | |
| 2023-10-11 08:38:26,295 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:38:26,296 EPOCH 6 done: loss 0.0776 - lr: 0.000067 | |
| 2023-10-11 08:38:32,186 DEV : loss 0.14091677963733673 - f1-score (micro avg) 0.7487 | |
| 2023-10-11 08:38:32,194 saving best model | |
| 2023-10-11 08:38:33,123 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:38:42,014 epoch 7 - iter 27/272 - loss 0.06607874 - time (sec): 8.89 - samples/sec: 438.23 - lr: 0.000065 - momentum: 0.000000 | |
| 2023-10-11 08:38:53,029 epoch 7 - iter 54/272 - loss 0.07072193 - time (sec): 19.90 - samples/sec: 526.45 - lr: 0.000063 - momentum: 0.000000 | |
| 2023-10-11 08:39:03,606 epoch 7 - iter 81/272 - loss 0.06434231 - time (sec): 30.48 - samples/sec: 538.94 - lr: 0.000062 - momentum: 0.000000 | |
| 2023-10-11 08:39:13,896 epoch 7 - iter 108/272 - loss 0.06116880 - time (sec): 40.77 - samples/sec: 531.38 - lr: 0.000060 - momentum: 0.000000 | |
| 2023-10-11 08:39:23,694 epoch 7 - iter 135/272 - loss 0.06217545 - time (sec): 50.57 - samples/sec: 531.88 - lr: 0.000058 - momentum: 0.000000 | |
| 2023-10-11 08:39:33,282 epoch 7 - iter 162/272 - loss 0.06273333 - time (sec): 60.16 - samples/sec: 524.37 - lr: 0.000057 - momentum: 0.000000 | |
| 2023-10-11 08:39:43,044 epoch 7 - iter 189/272 - loss 0.06023536 - time (sec): 69.92 - samples/sec: 524.91 - lr: 0.000055 - momentum: 0.000000 | |
| 2023-10-11 08:39:52,205 epoch 7 - iter 216/272 - loss 0.05977588 - time (sec): 79.08 - samples/sec: 518.40 - lr: 0.000053 - momentum: 0.000000 | |
| 2023-10-11 08:40:02,331 epoch 7 - iter 243/272 - loss 0.05885531 - time (sec): 89.21 - samples/sec: 519.06 - lr: 0.000052 - momentum: 0.000000 | |
| 2023-10-11 08:40:12,657 epoch 7 - iter 270/272 - loss 0.05924263 - time (sec): 99.53 - samples/sec: 519.66 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-11 08:40:13,173 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:40:13,173 EPOCH 7 done: loss 0.0595 - lr: 0.000050 | |
| 2023-10-11 08:40:19,155 DEV : loss 0.14236551523208618 - f1-score (micro avg) 0.7731 | |
| 2023-10-11 08:40:19,164 saving best model | |
| 2023-10-11 08:40:21,752 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:40:31,183 epoch 8 - iter 27/272 - loss 0.04561038 - time (sec): 9.43 - samples/sec: 534.37 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-11 08:40:40,708 epoch 8 - iter 54/272 - loss 0.04281581 - time (sec): 18.95 - samples/sec: 526.40 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-11 08:40:51,411 epoch 8 - iter 81/272 - loss 0.04882565 - time (sec): 29.65 - samples/sec: 539.72 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-11 08:41:01,243 epoch 8 - iter 108/272 - loss 0.04678312 - time (sec): 39.49 - samples/sec: 529.16 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-11 08:41:11,088 epoch 8 - iter 135/272 - loss 0.04583440 - time (sec): 49.33 - samples/sec: 528.53 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-11 08:41:20,671 epoch 8 - iter 162/272 - loss 0.04565349 - time (sec): 58.91 - samples/sec: 532.04 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-11 08:41:29,823 epoch 8 - iter 189/272 - loss 0.04604960 - time (sec): 68.07 - samples/sec: 529.96 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-11 08:41:39,649 epoch 8 - iter 216/272 - loss 0.04541623 - time (sec): 77.89 - samples/sec: 534.53 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-11 08:41:48,976 epoch 8 - iter 243/272 - loss 0.04830839 - time (sec): 87.22 - samples/sec: 531.59 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-11 08:41:58,683 epoch 8 - iter 270/272 - loss 0.04705058 - time (sec): 96.93 - samples/sec: 532.86 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-11 08:41:59,240 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:41:59,241 EPOCH 8 done: loss 0.0472 - lr: 0.000034 | |
| 2023-10-11 08:42:04,937 DEV : loss 0.1399533450603485 - f1-score (micro avg) 0.7877 | |
| 2023-10-11 08:42:04,945 saving best model | |
| 2023-10-11 08:42:05,883 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:42:14,810 epoch 9 - iter 27/272 - loss 0.03068623 - time (sec): 8.93 - samples/sec: 507.55 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-11 08:42:24,940 epoch 9 - iter 54/272 - loss 0.02656723 - time (sec): 19.06 - samples/sec: 542.31 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-11 08:42:34,472 epoch 9 - iter 81/272 - loss 0.02819868 - time (sec): 28.59 - samples/sec: 542.87 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-11 08:42:43,997 epoch 9 - iter 108/272 - loss 0.03508973 - time (sec): 38.11 - samples/sec: 541.00 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-11 08:42:54,004 epoch 9 - iter 135/272 - loss 0.03637900 - time (sec): 48.12 - samples/sec: 536.69 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-11 08:43:05,395 epoch 9 - iter 162/272 - loss 0.03568471 - time (sec): 59.51 - samples/sec: 529.66 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-11 08:43:15,322 epoch 9 - iter 189/272 - loss 0.03486822 - time (sec): 69.44 - samples/sec: 520.12 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-11 08:43:25,598 epoch 9 - iter 216/272 - loss 0.03613166 - time (sec): 79.71 - samples/sec: 519.82 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-11 08:43:35,152 epoch 9 - iter 243/272 - loss 0.03922140 - time (sec): 89.27 - samples/sec: 515.74 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-11 08:43:45,659 epoch 9 - iter 270/272 - loss 0.03803645 - time (sec): 99.77 - samples/sec: 517.53 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-11 08:43:46,289 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:43:46,289 EPOCH 9 done: loss 0.0379 - lr: 0.000017 | |
| 2023-10-11 08:43:52,708 DEV : loss 0.1408960521221161 - f1-score (micro avg) 0.7784 | |
| 2023-10-11 08:43:52,719 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:44:02,018 epoch 10 - iter 27/272 - loss 0.02462086 - time (sec): 9.30 - samples/sec: 507.24 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-11 08:44:11,063 epoch 10 - iter 54/272 - loss 0.02805834 - time (sec): 18.34 - samples/sec: 489.03 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-11 08:44:20,606 epoch 10 - iter 81/272 - loss 0.03332562 - time (sec): 27.88 - samples/sec: 490.45 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-11 08:44:30,527 epoch 10 - iter 108/272 - loss 0.03136298 - time (sec): 37.81 - samples/sec: 505.40 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-11 08:44:41,197 epoch 10 - iter 135/272 - loss 0.03099600 - time (sec): 48.48 - samples/sec: 526.51 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-11 08:44:52,141 epoch 10 - iter 162/272 - loss 0.03378086 - time (sec): 59.42 - samples/sec: 539.65 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-11 08:45:02,208 epoch 10 - iter 189/272 - loss 0.03459241 - time (sec): 69.49 - samples/sec: 540.16 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-11 08:45:11,492 epoch 10 - iter 216/272 - loss 0.03427708 - time (sec): 78.77 - samples/sec: 531.53 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-11 08:45:20,905 epoch 10 - iter 243/272 - loss 0.03584933 - time (sec): 88.18 - samples/sec: 527.28 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-11 08:45:31,284 epoch 10 - iter 270/272 - loss 0.03499016 - time (sec): 98.56 - samples/sec: 525.50 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-11 08:45:31,735 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:45:31,735 EPOCH 10 done: loss 0.0350 - lr: 0.000000 | |
| 2023-10-11 08:45:37,835 DEV : loss 0.14018605649471283 - f1-score (micro avg) 0.782 | |
| 2023-10-11 08:45:38,743 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:45:38,745 Loading model from best epoch ... | |
| 2023-10-11 08:45:42,618 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG | |
| 2023-10-11 08:45:54,534 | |
| Results: | |
| - F-score (micro) 0.7593 | |
| - F-score (macro) 0.6641 | |
| - Accuracy 0.631 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.7466 0.8782 0.8071 312 | |
| PER 0.7115 0.8654 0.7809 208 | |
| ORG 0.4000 0.3273 0.3600 55 | |
| HumanProd 0.6538 0.7727 0.7083 22 | |
| micro avg 0.7077 0.8191 0.7593 597 | |
| macro avg 0.6280 0.7109 0.6641 597 | |
| weighted avg 0.6990 0.8191 0.7531 597 | |
| 2023-10-11 08:45:54,534 ---------------------------------------------------------------------------------------------------- | |