| 2023-10-10 22:58:10,890 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 22:58:10,892 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() | |
| )" | |
| 2023-10-10 22:58:10,892 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 22:58:10,893 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 | |
| 2023-10-10 22:58:10,893 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 22:58:10,893 Train: 1166 sentences | |
| 2023-10-10 22:58:10,893 (train_with_dev=False, train_with_test=False) | |
| 2023-10-10 22:58:10,893 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 22:58:10,893 Training Params: | |
| 2023-10-10 22:58:10,893 - learning_rate: "0.00015" | |
| 2023-10-10 22:58:10,893 - mini_batch_size: "8" | |
| 2023-10-10 22:58:10,893 - max_epochs: "10" | |
| 2023-10-10 22:58:10,893 - shuffle: "True" | |
| 2023-10-10 22:58:10,893 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 22:58:10,893 Plugins: | |
| 2023-10-10 22:58:10,893 - TensorboardLogger | |
| 2023-10-10 22:58:10,894 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-10 22:58:10,894 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 22:58:10,894 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-10 22:58:10,894 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-10 22:58:10,894 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 22:58:10,894 Computation: | |
| 2023-10-10 22:58:10,894 - compute on device: cuda:0 | |
| 2023-10-10 22:58:10,894 - embedding storage: none | |
| 2023-10-10 22:58:10,894 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 22:58:10,894 Model training base path: "hmbench-newseye/fi-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-10 22:58:10,894 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 22:58:10,894 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 22:58:10,894 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-10 22:58:20,744 epoch 1 - iter 14/146 - loss 2.85080360 - time (sec): 9.85 - samples/sec: 508.04 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-10 22:58:29,270 epoch 1 - iter 28/146 - loss 2.84737208 - time (sec): 18.37 - samples/sec: 476.37 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-10 22:58:38,296 epoch 1 - iter 42/146 - loss 2.83617163 - time (sec): 27.40 - samples/sec: 485.34 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-10 22:58:47,385 epoch 1 - iter 56/146 - loss 2.82244913 - time (sec): 36.49 - samples/sec: 480.64 - lr: 0.000057 - momentum: 0.000000 | |
| 2023-10-10 22:58:56,369 epoch 1 - iter 70/146 - loss 2.79297253 - time (sec): 45.47 - samples/sec: 469.05 - lr: 0.000071 - momentum: 0.000000 | |
| 2023-10-10 22:59:05,074 epoch 1 - iter 84/146 - loss 2.74178364 - time (sec): 54.18 - samples/sec: 462.87 - lr: 0.000085 - momentum: 0.000000 | |
| 2023-10-10 22:59:14,215 epoch 1 - iter 98/146 - loss 2.67383737 - time (sec): 63.32 - samples/sec: 460.35 - lr: 0.000100 - momentum: 0.000000 | |
| 2023-10-10 22:59:23,588 epoch 1 - iter 112/146 - loss 2.59471648 - time (sec): 72.69 - samples/sec: 459.42 - lr: 0.000114 - momentum: 0.000000 | |
| 2023-10-10 22:59:32,864 epoch 1 - iter 126/146 - loss 2.50270095 - time (sec): 81.97 - samples/sec: 463.67 - lr: 0.000128 - momentum: 0.000000 | |
| 2023-10-10 22:59:42,548 epoch 1 - iter 140/146 - loss 2.40998070 - time (sec): 91.65 - samples/sec: 465.82 - lr: 0.000143 - momentum: 0.000000 | |
| 2023-10-10 22:59:46,352 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 22:59:46,352 EPOCH 1 done: loss 2.3739 - lr: 0.000143 | |
| 2023-10-10 22:59:51,751 DEV : loss 1.3572572469711304 - f1-score (micro avg) 0.0 | |
| 2023-10-10 22:59:51,762 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:00:00,609 epoch 2 - iter 14/146 - loss 1.35621053 - time (sec): 8.85 - samples/sec: 476.09 - lr: 0.000149 - momentum: 0.000000 | |
| 2023-10-10 23:00:10,228 epoch 2 - iter 28/146 - loss 1.27306197 - time (sec): 18.46 - samples/sec: 485.71 - lr: 0.000147 - momentum: 0.000000 | |
| 2023-10-10 23:00:19,552 epoch 2 - iter 42/146 - loss 1.20505413 - time (sec): 27.79 - samples/sec: 495.43 - lr: 0.000145 - momentum: 0.000000 | |
| 2023-10-10 23:00:28,035 epoch 2 - iter 56/146 - loss 1.14229062 - time (sec): 36.27 - samples/sec: 478.01 - lr: 0.000144 - momentum: 0.000000 | |
| 2023-10-10 23:00:37,032 epoch 2 - iter 70/146 - loss 1.06371575 - time (sec): 45.27 - samples/sec: 477.67 - lr: 0.000142 - momentum: 0.000000 | |
| 2023-10-10 23:00:44,657 epoch 2 - iter 84/146 - loss 1.03291390 - time (sec): 52.89 - samples/sec: 466.21 - lr: 0.000141 - momentum: 0.000000 | |
| 2023-10-10 23:00:53,889 epoch 2 - iter 98/146 - loss 0.97249437 - time (sec): 62.12 - samples/sec: 469.83 - lr: 0.000139 - momentum: 0.000000 | |
| 2023-10-10 23:01:03,403 epoch 2 - iter 112/146 - loss 0.91123270 - time (sec): 71.64 - samples/sec: 473.21 - lr: 0.000137 - momentum: 0.000000 | |
| 2023-10-10 23:01:12,183 epoch 2 - iter 126/146 - loss 0.86074670 - time (sec): 80.42 - samples/sec: 474.96 - lr: 0.000136 - momentum: 0.000000 | |
| 2023-10-10 23:01:21,088 epoch 2 - iter 140/146 - loss 0.82736123 - time (sec): 89.32 - samples/sec: 471.80 - lr: 0.000134 - momentum: 0.000000 | |
| 2023-10-10 23:01:25,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:01:25,200 EPOCH 2 done: loss 0.8534 - lr: 0.000134 | |
| 2023-10-10 23:01:31,340 DEV : loss 0.4602771997451782 - f1-score (micro avg) 0.0 | |
| 2023-10-10 23:01:31,350 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:01:40,294 epoch 3 - iter 14/146 - loss 0.58434813 - time (sec): 8.94 - samples/sec: 407.55 - lr: 0.000132 - momentum: 0.000000 | |
| 2023-10-10 23:01:48,865 epoch 3 - iter 28/146 - loss 0.51229680 - time (sec): 17.51 - samples/sec: 443.85 - lr: 0.000130 - momentum: 0.000000 | |
| 2023-10-10 23:01:58,385 epoch 3 - iter 42/146 - loss 0.60569011 - time (sec): 27.03 - samples/sec: 463.77 - lr: 0.000129 - momentum: 0.000000 | |
| 2023-10-10 23:02:06,775 epoch 3 - iter 56/146 - loss 0.57540816 - time (sec): 35.42 - samples/sec: 462.75 - lr: 0.000127 - momentum: 0.000000 | |
| 2023-10-10 23:02:15,652 epoch 3 - iter 70/146 - loss 0.54419923 - time (sec): 44.30 - samples/sec: 466.46 - lr: 0.000126 - momentum: 0.000000 | |
| 2023-10-10 23:02:25,245 epoch 3 - iter 84/146 - loss 0.52507541 - time (sec): 53.89 - samples/sec: 459.35 - lr: 0.000124 - momentum: 0.000000 | |
| 2023-10-10 23:02:35,262 epoch 3 - iter 98/146 - loss 0.50009096 - time (sec): 63.91 - samples/sec: 456.79 - lr: 0.000122 - momentum: 0.000000 | |
| 2023-10-10 23:02:45,700 epoch 3 - iter 112/146 - loss 0.47890839 - time (sec): 74.35 - samples/sec: 455.88 - lr: 0.000121 - momentum: 0.000000 | |
| 2023-10-10 23:02:55,929 epoch 3 - iter 126/146 - loss 0.46371610 - time (sec): 84.58 - samples/sec: 452.61 - lr: 0.000119 - momentum: 0.000000 | |
| 2023-10-10 23:03:06,048 epoch 3 - iter 140/146 - loss 0.45098021 - time (sec): 94.70 - samples/sec: 452.39 - lr: 0.000118 - momentum: 0.000000 | |
| 2023-10-10 23:03:09,921 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:03:09,921 EPOCH 3 done: loss 0.4549 - lr: 0.000118 | |
| 2023-10-10 23:03:15,900 DEV : loss 0.3545370399951935 - f1-score (micro avg) 0.1683 | |
| 2023-10-10 23:03:15,909 saving best model | |
| 2023-10-10 23:03:16,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:03:25,497 epoch 4 - iter 14/146 - loss 0.35955470 - time (sec): 8.69 - samples/sec: 469.20 - lr: 0.000115 - momentum: 0.000000 | |
| 2023-10-10 23:03:34,922 epoch 4 - iter 28/146 - loss 0.43915891 - time (sec): 18.12 - samples/sec: 466.27 - lr: 0.000114 - momentum: 0.000000 | |
| 2023-10-10 23:03:43,948 epoch 4 - iter 42/146 - loss 0.36828509 - time (sec): 27.14 - samples/sec: 469.10 - lr: 0.000112 - momentum: 0.000000 | |
| 2023-10-10 23:03:52,763 epoch 4 - iter 56/146 - loss 0.36449078 - time (sec): 35.96 - samples/sec: 462.14 - lr: 0.000111 - momentum: 0.000000 | |
| 2023-10-10 23:04:01,461 epoch 4 - iter 70/146 - loss 0.36634265 - time (sec): 44.65 - samples/sec: 461.38 - lr: 0.000109 - momentum: 0.000000 | |
| 2023-10-10 23:04:10,702 epoch 4 - iter 84/146 - loss 0.36530805 - time (sec): 53.90 - samples/sec: 458.20 - lr: 0.000107 - momentum: 0.000000 | |
| 2023-10-10 23:04:20,010 epoch 4 - iter 98/146 - loss 0.34785221 - time (sec): 63.20 - samples/sec: 460.69 - lr: 0.000106 - momentum: 0.000000 | |
| 2023-10-10 23:04:28,603 epoch 4 - iter 112/146 - loss 0.34537336 - time (sec): 71.80 - samples/sec: 460.94 - lr: 0.000104 - momentum: 0.000000 | |
| 2023-10-10 23:04:38,203 epoch 4 - iter 126/146 - loss 0.34816589 - time (sec): 81.40 - samples/sec: 461.70 - lr: 0.000103 - momentum: 0.000000 | |
| 2023-10-10 23:04:47,882 epoch 4 - iter 140/146 - loss 0.35021896 - time (sec): 91.08 - samples/sec: 465.67 - lr: 0.000101 - momentum: 0.000000 | |
| 2023-10-10 23:04:51,671 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:04:51,671 EPOCH 4 done: loss 0.3454 - lr: 0.000101 | |
| 2023-10-10 23:04:57,765 DEV : loss 0.2620405852794647 - f1-score (micro avg) 0.2198 | |
| 2023-10-10 23:04:57,775 saving best model | |
| 2023-10-10 23:05:06,005 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:05:14,754 epoch 5 - iter 14/146 - loss 0.33065727 - time (sec): 8.75 - samples/sec: 463.69 - lr: 0.000099 - momentum: 0.000000 | |
| 2023-10-10 23:05:24,485 epoch 5 - iter 28/146 - loss 0.27465261 - time (sec): 18.48 - samples/sec: 480.13 - lr: 0.000097 - momentum: 0.000000 | |
| 2023-10-10 23:05:33,372 epoch 5 - iter 42/146 - loss 0.27046333 - time (sec): 27.36 - samples/sec: 469.02 - lr: 0.000096 - momentum: 0.000000 | |
| 2023-10-10 23:05:42,165 epoch 5 - iter 56/146 - loss 0.26438058 - time (sec): 36.16 - samples/sec: 469.49 - lr: 0.000094 - momentum: 0.000000 | |
| 2023-10-10 23:05:50,851 epoch 5 - iter 70/146 - loss 0.27496324 - time (sec): 44.84 - samples/sec: 465.23 - lr: 0.000092 - momentum: 0.000000 | |
| 2023-10-10 23:06:01,117 epoch 5 - iter 84/146 - loss 0.30009690 - time (sec): 55.11 - samples/sec: 473.85 - lr: 0.000091 - momentum: 0.000000 | |
| 2023-10-10 23:06:11,160 epoch 5 - iter 98/146 - loss 0.30356108 - time (sec): 65.15 - samples/sec: 473.78 - lr: 0.000089 - momentum: 0.000000 | |
| 2023-10-10 23:06:20,380 epoch 5 - iter 112/146 - loss 0.29759337 - time (sec): 74.37 - samples/sec: 475.74 - lr: 0.000088 - momentum: 0.000000 | |
| 2023-10-10 23:06:29,071 epoch 5 - iter 126/146 - loss 0.29582810 - time (sec): 83.06 - samples/sec: 470.80 - lr: 0.000086 - momentum: 0.000000 | |
| 2023-10-10 23:06:37,398 epoch 5 - iter 140/146 - loss 0.29412746 - time (sec): 91.39 - samples/sec: 466.97 - lr: 0.000084 - momentum: 0.000000 | |
| 2023-10-10 23:06:41,340 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:06:41,340 EPOCH 5 done: loss 0.2924 - lr: 0.000084 | |
| 2023-10-10 23:06:47,335 DEV : loss 0.233732670545578 - f1-score (micro avg) 0.294 | |
| 2023-10-10 23:06:47,344 saving best model | |
| 2023-10-10 23:06:55,188 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:07:04,904 epoch 6 - iter 14/146 - loss 0.21279716 - time (sec): 9.71 - samples/sec: 479.03 - lr: 0.000082 - momentum: 0.000000 | |
| 2023-10-10 23:07:13,663 epoch 6 - iter 28/146 - loss 0.23945889 - time (sec): 18.47 - samples/sec: 467.99 - lr: 0.000081 - momentum: 0.000000 | |
| 2023-10-10 23:07:22,417 epoch 6 - iter 42/146 - loss 0.22572971 - time (sec): 27.23 - samples/sec: 471.79 - lr: 0.000079 - momentum: 0.000000 | |
| 2023-10-10 23:07:31,554 epoch 6 - iter 56/146 - loss 0.23744901 - time (sec): 36.36 - samples/sec: 466.59 - lr: 0.000077 - momentum: 0.000000 | |
| 2023-10-10 23:07:40,351 epoch 6 - iter 70/146 - loss 0.24226304 - time (sec): 45.16 - samples/sec: 469.66 - lr: 0.000076 - momentum: 0.000000 | |
| 2023-10-10 23:07:48,887 epoch 6 - iter 84/146 - loss 0.24621321 - time (sec): 53.70 - samples/sec: 468.04 - lr: 0.000074 - momentum: 0.000000 | |
| 2023-10-10 23:07:58,610 epoch 6 - iter 98/146 - loss 0.26217291 - time (sec): 63.42 - samples/sec: 476.79 - lr: 0.000073 - momentum: 0.000000 | |
| 2023-10-10 23:08:07,909 epoch 6 - iter 112/146 - loss 0.26102990 - time (sec): 72.72 - samples/sec: 470.50 - lr: 0.000071 - momentum: 0.000000 | |
| 2023-10-10 23:08:16,844 epoch 6 - iter 126/146 - loss 0.25644519 - time (sec): 81.65 - samples/sec: 468.56 - lr: 0.000069 - momentum: 0.000000 | |
| 2023-10-10 23:08:25,543 epoch 6 - iter 140/146 - loss 0.25250192 - time (sec): 90.35 - samples/sec: 470.08 - lr: 0.000068 - momentum: 0.000000 | |
| 2023-10-10 23:08:29,489 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:08:29,490 EPOCH 6 done: loss 0.2498 - lr: 0.000068 | |
| 2023-10-10 23:08:35,694 DEV : loss 0.21416617929935455 - f1-score (micro avg) 0.428 | |
| 2023-10-10 23:08:35,705 saving best model | |
| 2023-10-10 23:08:40,902 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:08:50,396 epoch 7 - iter 14/146 - loss 0.20869646 - time (sec): 9.49 - samples/sec: 439.54 - lr: 0.000066 - momentum: 0.000000 | |
| 2023-10-10 23:09:00,761 epoch 7 - iter 28/146 - loss 0.19793080 - time (sec): 19.85 - samples/sec: 464.18 - lr: 0.000064 - momentum: 0.000000 | |
| 2023-10-10 23:09:09,488 epoch 7 - iter 42/146 - loss 0.19705387 - time (sec): 28.58 - samples/sec: 443.46 - lr: 0.000062 - momentum: 0.000000 | |
| 2023-10-10 23:09:18,807 epoch 7 - iter 56/146 - loss 0.21316354 - time (sec): 37.90 - samples/sec: 443.27 - lr: 0.000061 - momentum: 0.000000 | |
| 2023-10-10 23:09:26,780 epoch 7 - iter 70/146 - loss 0.20525473 - time (sec): 45.87 - samples/sec: 437.55 - lr: 0.000059 - momentum: 0.000000 | |
| 2023-10-10 23:09:35,299 epoch 7 - iter 84/146 - loss 0.20806961 - time (sec): 54.39 - samples/sec: 445.74 - lr: 0.000058 - momentum: 0.000000 | |
| 2023-10-10 23:09:44,917 epoch 7 - iter 98/146 - loss 0.20881775 - time (sec): 64.01 - samples/sec: 459.12 - lr: 0.000056 - momentum: 0.000000 | |
| 2023-10-10 23:09:54,303 epoch 7 - iter 112/146 - loss 0.20670940 - time (sec): 73.40 - samples/sec: 457.48 - lr: 0.000054 - momentum: 0.000000 | |
| 2023-10-10 23:10:03,027 epoch 7 - iter 126/146 - loss 0.21554904 - time (sec): 82.12 - samples/sec: 460.36 - lr: 0.000053 - momentum: 0.000000 | |
| 2023-10-10 23:10:12,759 epoch 7 - iter 140/146 - loss 0.20959678 - time (sec): 91.85 - samples/sec: 465.33 - lr: 0.000051 - momentum: 0.000000 | |
| 2023-10-10 23:10:16,496 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:10:16,496 EPOCH 7 done: loss 0.2096 - lr: 0.000051 | |
| 2023-10-10 23:10:22,427 DEV : loss 0.19345837831497192 - f1-score (micro avg) 0.485 | |
| 2023-10-10 23:10:22,437 saving best model | |
| 2023-10-10 23:10:32,162 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:10:41,415 epoch 8 - iter 14/146 - loss 0.18298293 - time (sec): 9.25 - samples/sec: 457.08 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-10 23:10:50,318 epoch 8 - iter 28/146 - loss 0.20041757 - time (sec): 18.15 - samples/sec: 467.68 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-10 23:10:59,244 epoch 8 - iter 42/146 - loss 0.18477550 - time (sec): 27.08 - samples/sec: 470.62 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-10 23:11:07,458 epoch 8 - iter 56/146 - loss 0.18939422 - time (sec): 35.29 - samples/sec: 460.11 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-10 23:11:16,672 epoch 8 - iter 70/146 - loss 0.20069635 - time (sec): 44.51 - samples/sec: 471.43 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-10 23:11:25,545 epoch 8 - iter 84/146 - loss 0.19917900 - time (sec): 53.38 - samples/sec: 463.97 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-10 23:11:35,352 epoch 8 - iter 98/146 - loss 0.18755072 - time (sec): 63.19 - samples/sec: 468.40 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-10 23:11:43,884 epoch 8 - iter 112/146 - loss 0.18603688 - time (sec): 71.72 - samples/sec: 466.09 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-10 23:11:53,379 epoch 8 - iter 126/146 - loss 0.18215187 - time (sec): 81.21 - samples/sec: 470.73 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-10 23:12:03,326 epoch 8 - iter 140/146 - loss 0.18026671 - time (sec): 91.16 - samples/sec: 473.98 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-10 23:12:06,714 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:12:06,714 EPOCH 8 done: loss 0.1781 - lr: 0.000035 | |
| 2023-10-10 23:12:12,668 DEV : loss 0.18470922112464905 - f1-score (micro avg) 0.5094 | |
| 2023-10-10 23:12:12,678 saving best model | |
| 2023-10-10 23:12:26,423 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:12:35,685 epoch 9 - iter 14/146 - loss 0.16655684 - time (sec): 9.26 - samples/sec: 465.12 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-10 23:12:44,294 epoch 9 - iter 28/146 - loss 0.16140822 - time (sec): 17.87 - samples/sec: 461.81 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-10 23:12:52,406 epoch 9 - iter 42/146 - loss 0.17856536 - time (sec): 25.98 - samples/sec: 448.97 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-10 23:13:01,225 epoch 9 - iter 56/146 - loss 0.17303316 - time (sec): 34.80 - samples/sec: 456.18 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-10 23:13:11,847 epoch 9 - iter 70/146 - loss 0.17994148 - time (sec): 45.42 - samples/sec: 477.28 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-10 23:13:19,828 epoch 9 - iter 84/146 - loss 0.17025472 - time (sec): 53.40 - samples/sec: 466.73 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-10 23:13:29,108 epoch 9 - iter 98/146 - loss 0.16961006 - time (sec): 62.68 - samples/sec: 473.92 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-10 23:13:38,011 epoch 9 - iter 112/146 - loss 0.16697591 - time (sec): 71.58 - samples/sec: 474.21 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-10 23:13:46,635 epoch 9 - iter 126/146 - loss 0.16595253 - time (sec): 80.21 - samples/sec: 475.12 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-10 23:13:55,901 epoch 9 - iter 140/146 - loss 0.16336951 - time (sec): 89.47 - samples/sec: 480.09 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-10 23:13:59,214 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:13:59,215 EPOCH 9 done: loss 0.1615 - lr: 0.000018 | |
| 2023-10-10 23:14:04,878 DEV : loss 0.18229743838310242 - f1-score (micro avg) 0.5605 | |
| 2023-10-10 23:14:04,887 saving best model | |
| 2023-10-10 23:14:15,726 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:14:25,016 epoch 10 - iter 14/146 - loss 0.16914234 - time (sec): 9.29 - samples/sec: 437.01 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-10 23:14:35,848 epoch 10 - iter 28/146 - loss 0.16172601 - time (sec): 20.12 - samples/sec: 436.43 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-10 23:14:45,866 epoch 10 - iter 42/146 - loss 0.15318731 - time (sec): 30.14 - samples/sec: 413.82 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-10 23:14:55,889 epoch 10 - iter 56/146 - loss 0.14649958 - time (sec): 40.16 - samples/sec: 416.17 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-10 23:15:06,068 epoch 10 - iter 70/146 - loss 0.14015652 - time (sec): 50.34 - samples/sec: 418.19 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-10 23:15:14,831 epoch 10 - iter 84/146 - loss 0.14204998 - time (sec): 59.10 - samples/sec: 419.73 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-10 23:15:24,600 epoch 10 - iter 98/146 - loss 0.14430949 - time (sec): 68.87 - samples/sec: 431.09 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-10 23:15:33,767 epoch 10 - iter 112/146 - loss 0.15183816 - time (sec): 78.04 - samples/sec: 439.05 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-10 23:15:42,602 epoch 10 - iter 126/146 - loss 0.14950005 - time (sec): 86.87 - samples/sec: 441.81 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-10 23:15:51,543 epoch 10 - iter 140/146 - loss 0.15184293 - time (sec): 95.81 - samples/sec: 448.71 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-10 23:15:54,868 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:15:54,868 EPOCH 10 done: loss 0.1505 - lr: 0.000001 | |
| 2023-10-10 23:16:00,814 DEV : loss 0.1794561892747879 - f1-score (micro avg) 0.5867 | |
| 2023-10-10 23:16:00,824 saving best model | |
| 2023-10-10 23:16:11,463 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-10 23:16:11,465 Loading model from best epoch ... | |
| 2023-10-10 23:16:15,063 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 | |
| 2023-10-10 23:16:27,864 | |
| Results: | |
| - F-score (micro) 0.6406 | |
| - F-score (macro) 0.3912 | |
| - Accuracy 0.5198 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.7484 0.6839 0.7147 348 | |
| LOC 0.5597 0.8084 0.6614 261 | |
| ORG 0.1852 0.1923 0.1887 52 | |
| HumanProd 0.0000 0.0000 0.0000 22 | |
| micro avg 0.6120 0.6720 0.6406 683 | |
| macro avg 0.3733 0.4212 0.3912 683 | |
| weighted avg 0.6093 0.6720 0.6313 683 | |
| 2023-10-10 23:16:27,864 ---------------------------------------------------------------------------------------------------- | |