| 2023-10-17 21:41:01,738 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:41:01,740 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): ElectraModel( | |
| (embeddings): ElectraEmbeddings( | |
| (word_embeddings): Embedding(32001, 768) | |
| (position_embeddings): Embedding(512, 768) | |
| (token_type_embeddings): Embedding(2, 768) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): ElectraEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x ElectraLayer( | |
| (attention): ElectraAttention( | |
| (self): ElectraSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): ElectraSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): ElectraIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): ElectraOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=17, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 21:41:01,740 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:41:01,741 MultiCorpus: 20847 train + 1123 dev + 3350 test sentences | |
| - NER_HIPE_2022 Corpus: 20847 train + 1123 dev + 3350 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/de/with_doc_seperator | |
| 2023-10-17 21:41:01,741 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:41:01,741 Train: 20847 sentences | |
| 2023-10-17 21:41:01,741 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 21:41:01,741 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:41:01,741 Training Params: | |
| 2023-10-17 21:41:01,741 - learning_rate: "3e-05" | |
| 2023-10-17 21:41:01,741 - mini_batch_size: "8" | |
| 2023-10-17 21:41:01,741 - max_epochs: "10" | |
| 2023-10-17 21:41:01,741 - shuffle: "True" | |
| 2023-10-17 21:41:01,741 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:41:01,741 Plugins: | |
| 2023-10-17 21:41:01,741 - TensorboardLogger | |
| 2023-10-17 21:41:01,742 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 21:41:01,742 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:41:01,742 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 21:41:01,742 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 21:41:01,742 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:41:01,742 Computation: | |
| 2023-10-17 21:41:01,742 - compute on device: cuda:0 | |
| 2023-10-17 21:41:01,742 - embedding storage: none | |
| 2023-10-17 21:41:01,742 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:41:01,742 Model training base path: "hmbench-newseye/de-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-17 21:41:01,742 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:41:01,742 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:41:01,742 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 21:41:30,337 epoch 1 - iter 260/2606 - loss 2.41881760 - time (sec): 28.59 - samples/sec: 1339.66 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 21:41:58,087 epoch 1 - iter 520/2606 - loss 1.45243831 - time (sec): 56.34 - samples/sec: 1322.89 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 21:42:26,584 epoch 1 - iter 780/2606 - loss 1.09141288 - time (sec): 84.84 - samples/sec: 1291.54 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 21:42:54,874 epoch 1 - iter 1040/2606 - loss 0.88178923 - time (sec): 113.13 - samples/sec: 1301.26 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 21:43:21,592 epoch 1 - iter 1300/2606 - loss 0.76182440 - time (sec): 139.85 - samples/sec: 1304.18 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 21:43:49,305 epoch 1 - iter 1560/2606 - loss 0.67181695 - time (sec): 167.56 - samples/sec: 1302.49 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 21:44:17,308 epoch 1 - iter 1820/2606 - loss 0.60318561 - time (sec): 195.56 - samples/sec: 1315.48 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 21:44:45,117 epoch 1 - iter 2080/2606 - loss 0.55727278 - time (sec): 223.37 - samples/sec: 1321.33 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 21:45:13,289 epoch 1 - iter 2340/2606 - loss 0.51688287 - time (sec): 251.54 - samples/sec: 1318.03 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 21:45:40,267 epoch 1 - iter 2600/2606 - loss 0.48599856 - time (sec): 278.52 - samples/sec: 1315.17 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 21:45:40,928 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:45:40,928 EPOCH 1 done: loss 0.4850 - lr: 0.000030 | |
| 2023-10-17 21:45:48,508 DEV : loss 0.14276579022407532 - f1-score (micro avg) 0.3183 | |
| 2023-10-17 21:45:48,562 saving best model | |
| 2023-10-17 21:45:49,113 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:46:16,813 epoch 2 - iter 260/2606 - loss 0.17577471 - time (sec): 27.70 - samples/sec: 1306.48 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 21:46:43,370 epoch 2 - iter 520/2606 - loss 0.16721643 - time (sec): 54.25 - samples/sec: 1340.06 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 21:47:08,929 epoch 2 - iter 780/2606 - loss 0.16285204 - time (sec): 79.81 - samples/sec: 1361.90 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 21:47:33,597 epoch 2 - iter 1040/2606 - loss 0.16796041 - time (sec): 104.48 - samples/sec: 1376.52 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 21:48:03,270 epoch 2 - iter 1300/2606 - loss 0.16172000 - time (sec): 134.15 - samples/sec: 1353.77 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 21:48:32,798 epoch 2 - iter 1560/2606 - loss 0.16200037 - time (sec): 163.68 - samples/sec: 1331.55 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 21:48:59,085 epoch 2 - iter 1820/2606 - loss 0.15970481 - time (sec): 189.97 - samples/sec: 1328.64 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 21:49:27,191 epoch 2 - iter 2080/2606 - loss 0.15777567 - time (sec): 218.08 - samples/sec: 1341.26 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 21:49:55,624 epoch 2 - iter 2340/2606 - loss 0.15570657 - time (sec): 246.51 - samples/sec: 1346.43 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 21:50:21,968 epoch 2 - iter 2600/2606 - loss 0.15259905 - time (sec): 272.85 - samples/sec: 1343.85 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 21:50:22,589 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:50:22,589 EPOCH 2 done: loss 0.1526 - lr: 0.000027 | |
| 2023-10-17 21:50:34,223 DEV : loss 0.17080335319042206 - f1-score (micro avg) 0.3148 | |
| 2023-10-17 21:50:34,279 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:51:00,649 epoch 3 - iter 260/2606 - loss 0.11935628 - time (sec): 26.37 - samples/sec: 1368.32 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 21:51:27,685 epoch 3 - iter 520/2606 - loss 0.11145962 - time (sec): 53.40 - samples/sec: 1374.95 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 21:51:53,191 epoch 3 - iter 780/2606 - loss 0.10854384 - time (sec): 78.91 - samples/sec: 1367.28 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 21:52:19,738 epoch 3 - iter 1040/2606 - loss 0.11018127 - time (sec): 105.46 - samples/sec: 1390.48 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 21:52:46,253 epoch 3 - iter 1300/2606 - loss 0.11016333 - time (sec): 131.97 - samples/sec: 1384.32 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 21:53:12,837 epoch 3 - iter 1560/2606 - loss 0.10902383 - time (sec): 158.56 - samples/sec: 1382.86 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 21:53:39,943 epoch 3 - iter 1820/2606 - loss 0.10842064 - time (sec): 185.66 - samples/sec: 1386.69 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 21:54:06,490 epoch 3 - iter 2080/2606 - loss 0.10894065 - time (sec): 212.21 - samples/sec: 1385.76 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 21:54:32,765 epoch 3 - iter 2340/2606 - loss 0.10851408 - time (sec): 238.48 - samples/sec: 1378.78 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 21:55:00,409 epoch 3 - iter 2600/2606 - loss 0.10879450 - time (sec): 266.13 - samples/sec: 1376.64 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 21:55:01,017 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:55:01,017 EPOCH 3 done: loss 0.1088 - lr: 0.000023 | |
| 2023-10-17 21:55:13,477 DEV : loss 0.15336216986179352 - f1-score (micro avg) 0.3868 | |
| 2023-10-17 21:55:13,545 saving best model | |
| 2023-10-17 21:55:14,189 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:55:42,008 epoch 4 - iter 260/2606 - loss 0.08171917 - time (sec): 27.82 - samples/sec: 1339.60 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 21:56:08,740 epoch 4 - iter 520/2606 - loss 0.07405963 - time (sec): 54.55 - samples/sec: 1348.05 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 21:56:36,186 epoch 4 - iter 780/2606 - loss 0.07507318 - time (sec): 81.99 - samples/sec: 1355.98 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 21:57:02,099 epoch 4 - iter 1040/2606 - loss 0.07869775 - time (sec): 107.91 - samples/sec: 1354.92 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 21:57:28,178 epoch 4 - iter 1300/2606 - loss 0.08300475 - time (sec): 133.99 - samples/sec: 1359.02 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 21:57:55,360 epoch 4 - iter 1560/2606 - loss 0.08367761 - time (sec): 161.17 - samples/sec: 1355.40 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 21:58:21,927 epoch 4 - iter 1820/2606 - loss 0.08344334 - time (sec): 187.74 - samples/sec: 1360.67 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 21:58:49,443 epoch 4 - iter 2080/2606 - loss 0.08237646 - time (sec): 215.25 - samples/sec: 1364.99 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 21:59:17,124 epoch 4 - iter 2340/2606 - loss 0.08147344 - time (sec): 242.93 - samples/sec: 1357.74 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 21:59:44,398 epoch 4 - iter 2600/2606 - loss 0.08031963 - time (sec): 270.21 - samples/sec: 1355.48 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 21:59:45,164 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:59:45,164 EPOCH 4 done: loss 0.0802 - lr: 0.000020 | |
| 2023-10-17 21:59:57,012 DEV : loss 0.2895336449146271 - f1-score (micro avg) 0.382 | |
| 2023-10-17 21:59:57,071 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:00:24,322 epoch 5 - iter 260/2606 - loss 0.03463138 - time (sec): 27.25 - samples/sec: 1320.83 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 22:00:51,439 epoch 5 - iter 520/2606 - loss 0.04332343 - time (sec): 54.37 - samples/sec: 1373.95 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 22:01:19,415 epoch 5 - iter 780/2606 - loss 0.04395028 - time (sec): 82.34 - samples/sec: 1382.89 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 22:01:46,086 epoch 5 - iter 1040/2606 - loss 0.04564615 - time (sec): 109.01 - samples/sec: 1367.83 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 22:02:14,157 epoch 5 - iter 1300/2606 - loss 0.05201596 - time (sec): 137.08 - samples/sec: 1355.49 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 22:02:42,089 epoch 5 - iter 1560/2606 - loss 0.05280423 - time (sec): 165.02 - samples/sec: 1356.56 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 22:03:09,017 epoch 5 - iter 1820/2606 - loss 0.05187602 - time (sec): 191.94 - samples/sec: 1356.32 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 22:03:37,004 epoch 5 - iter 2080/2606 - loss 0.05433704 - time (sec): 219.93 - samples/sec: 1351.69 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 22:04:04,460 epoch 5 - iter 2340/2606 - loss 0.05417178 - time (sec): 247.39 - samples/sec: 1345.10 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 22:04:30,839 epoch 5 - iter 2600/2606 - loss 0.05457916 - time (sec): 273.77 - samples/sec: 1339.43 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 22:04:31,375 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:04:31,376 EPOCH 5 done: loss 0.0549 - lr: 0.000017 | |
| 2023-10-17 22:04:43,480 DEV : loss 0.2547551393508911 - f1-score (micro avg) 0.4078 | |
| 2023-10-17 22:04:43,539 saving best model | |
| 2023-10-17 22:04:45,029 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:05:12,277 epoch 6 - iter 260/2606 - loss 0.04878224 - time (sec): 27.24 - samples/sec: 1405.82 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 22:05:39,489 epoch 6 - iter 520/2606 - loss 0.04226937 - time (sec): 54.46 - samples/sec: 1361.63 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 22:06:07,668 epoch 6 - iter 780/2606 - loss 0.04025396 - time (sec): 82.63 - samples/sec: 1361.16 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 22:06:36,370 epoch 6 - iter 1040/2606 - loss 0.04013309 - time (sec): 111.34 - samples/sec: 1351.86 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 22:07:03,268 epoch 6 - iter 1300/2606 - loss 0.04108149 - time (sec): 138.23 - samples/sec: 1347.18 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 22:07:30,138 epoch 6 - iter 1560/2606 - loss 0.04185494 - time (sec): 165.10 - samples/sec: 1328.03 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 22:07:58,967 epoch 6 - iter 1820/2606 - loss 0.04144739 - time (sec): 193.93 - samples/sec: 1311.99 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 22:08:29,097 epoch 6 - iter 2080/2606 - loss 0.04073086 - time (sec): 224.06 - samples/sec: 1297.46 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 22:08:58,487 epoch 6 - iter 2340/2606 - loss 0.03975708 - time (sec): 253.45 - samples/sec: 1294.51 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 22:09:27,224 epoch 6 - iter 2600/2606 - loss 0.03991100 - time (sec): 282.19 - samples/sec: 1298.71 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 22:09:27,970 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:09:27,970 EPOCH 6 done: loss 0.0398 - lr: 0.000013 | |
| 2023-10-17 22:09:40,547 DEV : loss 0.4081049859523773 - f1-score (micro avg) 0.3431 | |
| 2023-10-17 22:09:40,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:10:09,222 epoch 7 - iter 260/2606 - loss 0.02307160 - time (sec): 28.62 - samples/sec: 1321.09 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 22:10:36,227 epoch 7 - iter 520/2606 - loss 0.02420388 - time (sec): 55.62 - samples/sec: 1331.24 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 22:11:02,363 epoch 7 - iter 780/2606 - loss 0.02718461 - time (sec): 81.76 - samples/sec: 1326.55 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 22:11:30,000 epoch 7 - iter 1040/2606 - loss 0.02714358 - time (sec): 109.40 - samples/sec: 1318.94 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 22:11:57,405 epoch 7 - iter 1300/2606 - loss 0.02836831 - time (sec): 136.80 - samples/sec: 1323.99 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 22:12:24,676 epoch 7 - iter 1560/2606 - loss 0.02987251 - time (sec): 164.07 - samples/sec: 1318.13 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 22:12:52,857 epoch 7 - iter 1820/2606 - loss 0.03103589 - time (sec): 192.25 - samples/sec: 1317.49 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 22:13:21,970 epoch 7 - iter 2080/2606 - loss 0.03055732 - time (sec): 221.37 - samples/sec: 1335.62 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 22:13:48,595 epoch 7 - iter 2340/2606 - loss 0.03040091 - time (sec): 247.99 - samples/sec: 1331.18 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 22:14:17,409 epoch 7 - iter 2600/2606 - loss 0.02959375 - time (sec): 276.81 - samples/sec: 1325.42 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 22:14:17,997 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:14:17,998 EPOCH 7 done: loss 0.0296 - lr: 0.000010 | |
| 2023-10-17 22:14:30,249 DEV : loss 0.3910466134548187 - f1-score (micro avg) 0.3948 | |
| 2023-10-17 22:14:30,311 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:14:59,837 epoch 8 - iter 260/2606 - loss 0.01803369 - time (sec): 29.52 - samples/sec: 1226.36 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 22:15:29,377 epoch 8 - iter 520/2606 - loss 0.01820685 - time (sec): 59.06 - samples/sec: 1237.49 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 22:15:57,969 epoch 8 - iter 780/2606 - loss 0.02046211 - time (sec): 87.65 - samples/sec: 1221.52 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 22:16:26,861 epoch 8 - iter 1040/2606 - loss 0.02034776 - time (sec): 116.55 - samples/sec: 1226.47 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 22:16:54,705 epoch 8 - iter 1300/2606 - loss 0.02070951 - time (sec): 144.39 - samples/sec: 1239.18 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 22:17:24,823 epoch 8 - iter 1560/2606 - loss 0.02093510 - time (sec): 174.51 - samples/sec: 1242.35 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 22:17:53,158 epoch 8 - iter 1820/2606 - loss 0.02094885 - time (sec): 202.84 - samples/sec: 1268.83 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 22:18:19,676 epoch 8 - iter 2080/2606 - loss 0.02190230 - time (sec): 229.36 - samples/sec: 1285.32 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 22:18:45,912 epoch 8 - iter 2340/2606 - loss 0.02114848 - time (sec): 255.60 - samples/sec: 1289.55 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 22:19:13,924 epoch 8 - iter 2600/2606 - loss 0.02115871 - time (sec): 283.61 - samples/sec: 1292.71 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 22:19:14,479 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:19:14,479 EPOCH 8 done: loss 0.0211 - lr: 0.000007 | |
| 2023-10-17 22:19:26,148 DEV : loss 0.47483888268470764 - f1-score (micro avg) 0.3777 | |
| 2023-10-17 22:19:26,208 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:19:53,934 epoch 9 - iter 260/2606 - loss 0.01536404 - time (sec): 27.72 - samples/sec: 1404.80 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 22:20:21,780 epoch 9 - iter 520/2606 - loss 0.01572720 - time (sec): 55.57 - samples/sec: 1350.13 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 22:20:48,491 epoch 9 - iter 780/2606 - loss 0.01641070 - time (sec): 82.28 - samples/sec: 1334.73 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 22:21:15,768 epoch 9 - iter 1040/2606 - loss 0.01560086 - time (sec): 109.56 - samples/sec: 1317.73 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 22:21:43,567 epoch 9 - iter 1300/2606 - loss 0.01474722 - time (sec): 137.36 - samples/sec: 1306.20 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 22:22:11,099 epoch 9 - iter 1560/2606 - loss 0.01463560 - time (sec): 164.89 - samples/sec: 1315.07 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 22:22:37,886 epoch 9 - iter 1820/2606 - loss 0.01501095 - time (sec): 191.68 - samples/sec: 1325.15 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 22:23:06,405 epoch 9 - iter 2080/2606 - loss 0.01553135 - time (sec): 220.19 - samples/sec: 1329.33 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 22:23:35,222 epoch 9 - iter 2340/2606 - loss 0.01541101 - time (sec): 249.01 - samples/sec: 1325.15 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 22:24:03,048 epoch 9 - iter 2600/2606 - loss 0.01570046 - time (sec): 276.84 - samples/sec: 1324.46 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 22:24:03,604 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:24:03,604 EPOCH 9 done: loss 0.0157 - lr: 0.000003 | |
| 2023-10-17 22:24:14,552 DEV : loss 0.47549542784690857 - f1-score (micro avg) 0.3929 | |
| 2023-10-17 22:24:14,609 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:24:42,909 epoch 10 - iter 260/2606 - loss 0.00798516 - time (sec): 28.30 - samples/sec: 1324.71 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 22:25:11,407 epoch 10 - iter 520/2606 - loss 0.00933529 - time (sec): 56.79 - samples/sec: 1311.98 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 22:25:38,748 epoch 10 - iter 780/2606 - loss 0.01029313 - time (sec): 84.14 - samples/sec: 1299.42 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 22:26:05,195 epoch 10 - iter 1040/2606 - loss 0.01032349 - time (sec): 110.58 - samples/sec: 1300.06 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 22:26:32,397 epoch 10 - iter 1300/2606 - loss 0.01015852 - time (sec): 137.79 - samples/sec: 1330.73 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 22:26:59,813 epoch 10 - iter 1560/2606 - loss 0.01048293 - time (sec): 165.20 - samples/sec: 1335.02 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 22:27:27,229 epoch 10 - iter 1820/2606 - loss 0.01032360 - time (sec): 192.62 - samples/sec: 1347.71 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 22:27:55,194 epoch 10 - iter 2080/2606 - loss 0.00994780 - time (sec): 220.58 - samples/sec: 1339.62 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 22:28:21,684 epoch 10 - iter 2340/2606 - loss 0.01011531 - time (sec): 247.07 - samples/sec: 1335.36 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 22:28:49,738 epoch 10 - iter 2600/2606 - loss 0.00998687 - time (sec): 275.13 - samples/sec: 1332.80 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 22:28:50,269 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:28:50,270 EPOCH 10 done: loss 0.0100 - lr: 0.000000 | |
| 2023-10-17 22:29:01,249 DEV : loss 0.4655146896839142 - f1-score (micro avg) 0.4053 | |
| 2023-10-17 22:29:01,827 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:29:01,829 Loading model from best epoch ... | |
| 2023-10-17 22:29:04,090 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 | |
| 2023-10-17 22:29:23,043 | |
| Results: | |
| - F-score (micro) 0.42 | |
| - F-score (macro) 0.2892 | |
| - Accuracy 0.27 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.5235 0.4316 0.4731 1214 | |
| PER 0.4428 0.4022 0.4215 808 | |
| ORG 0.2582 0.2663 0.2622 353 | |
| HumanProd 0.0000 0.0000 0.0000 15 | |
| micro avg 0.4490 0.3946 0.4200 2390 | |
| macro avg 0.3061 0.2750 0.2892 2390 | |
| weighted avg 0.4537 0.3946 0.4216 2390 | |
| 2023-10-17 22:29:23,043 ---------------------------------------------------------------------------------------------------- | |