2023-10-17 20:05:58,315 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:05:58,316 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=21, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-17 20:05:58,316 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:05:58,316 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator 2023-10-17 20:05:58,317 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:05:58,317 Train: 5901 sentences 2023-10-17 20:05:58,317 (train_with_dev=False, train_with_test=False) 2023-10-17 20:05:58,317 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:05:58,317 Training Params: 2023-10-17 20:05:58,317 - learning_rate: "3e-05" 2023-10-17 20:05:58,317 - mini_batch_size: "4" 2023-10-17 20:05:58,317 - max_epochs: "10" 2023-10-17 20:05:58,317 - shuffle: "True" 2023-10-17 20:05:58,317 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:05:58,317 Plugins: 2023-10-17 20:05:58,317 - TensorboardLogger 2023-10-17 20:05:58,317 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 20:05:58,317 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:05:58,317 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 20:05:58,317 - metric: "('micro avg', 'f1-score')" 2023-10-17 20:05:58,317 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:05:58,317 Computation: 2023-10-17 20:05:58,317 - compute on device: cuda:0 2023-10-17 20:05:58,317 - embedding storage: none 2023-10-17 20:05:58,317 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:05:58,317 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1" 2023-10-17 20:05:58,317 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:05:58,317 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:05:58,317 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 20:06:05,703 epoch 1 - iter 147/1476 - loss 2.88376740 - time (sec): 7.38 - samples/sec: 2399.29 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:06:12,547 epoch 1 - iter 294/1476 - loss 1.83405663 - time (sec): 14.23 - samples/sec: 2329.66 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:06:20,094 epoch 1 - iter 441/1476 - loss 1.34685714 - time (sec): 21.78 - samples/sec: 2364.86 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:06:27,578 epoch 1 - iter 588/1476 - loss 1.08468691 - time (sec): 29.26 - samples/sec: 2373.41 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:06:34,521 epoch 1 - iter 735/1476 - loss 0.93275820 - time (sec): 36.20 - samples/sec: 2362.49 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:06:41,355 epoch 1 - iter 882/1476 - loss 0.83450367 - time (sec): 43.04 - samples/sec: 2330.69 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:06:48,377 epoch 1 - iter 1029/1476 - loss 0.75458015 - time (sec): 50.06 - samples/sec: 2317.34 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:06:55,693 epoch 1 - iter 1176/1476 - loss 0.68725226 - time (sec): 57.37 - samples/sec: 2303.13 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:07:03,442 epoch 1 - iter 1323/1476 - loss 0.63285062 - time (sec): 65.12 - samples/sec: 2281.72 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:07:10,621 epoch 1 - iter 1470/1476 - loss 0.58387807 - time (sec): 72.30 - samples/sec: 2294.27 - lr: 0.000030 - momentum: 0.000000 2023-10-17 20:07:10,883 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:07:10,883 EPOCH 1 done: loss 0.5825 - lr: 0.000030 2023-10-17 20:07:17,234 DEV : loss 0.12818463146686554 - f1-score (micro avg) 0.7213 2023-10-17 20:07:17,263 saving best model 2023-10-17 20:07:17,633 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:07:24,643 epoch 2 - iter 147/1476 - loss 0.13820773 - time (sec): 7.01 - samples/sec: 2385.67 - lr: 0.000030 - momentum: 0.000000 2023-10-17 20:07:32,026 epoch 2 - iter 294/1476 - loss 0.13981224 - time (sec): 14.39 - samples/sec: 2427.68 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:07:39,398 epoch 2 - iter 441/1476 - loss 0.13892246 - time (sec): 21.76 - samples/sec: 2406.79 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:07:46,926 epoch 2 - iter 588/1476 - loss 0.13506201 - time (sec): 29.29 - samples/sec: 2319.51 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:07:54,318 epoch 2 - iter 735/1476 - loss 0.13369013 - time (sec): 36.68 - samples/sec: 2242.62 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:08:01,477 epoch 2 - iter 882/1476 - loss 0.13371218 - time (sec): 43.84 - samples/sec: 2227.85 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:08:09,013 epoch 2 - iter 1029/1476 - loss 0.13126252 - time (sec): 51.38 - samples/sec: 2221.33 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:08:16,524 epoch 2 - iter 1176/1476 - loss 0.13158893 - time (sec): 58.89 - samples/sec: 2215.15 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:08:24,525 epoch 2 - iter 1323/1476 - loss 0.13111484 - time (sec): 66.89 - samples/sec: 2220.09 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:08:31,884 epoch 2 - iter 1470/1476 - loss 0.13044166 - time (sec): 74.25 - samples/sec: 2233.50 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:08:32,152 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:08:32,153 EPOCH 2 done: loss 0.1302 - lr: 0.000027 2023-10-17 20:08:43,623 DEV : loss 0.11906815320253372 - f1-score (micro avg) 0.8161 2023-10-17 20:08:43,656 saving best model 2023-10-17 20:08:44,148 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:08:51,602 epoch 3 - iter 147/1476 - loss 0.06487959 - time (sec): 7.45 - samples/sec: 2371.36 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:08:58,751 epoch 3 - iter 294/1476 - loss 0.07490643 - time (sec): 14.60 - samples/sec: 2407.47 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:09:05,781 epoch 3 - iter 441/1476 - loss 0.07115129 - time (sec): 21.63 - samples/sec: 2400.27 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:09:12,619 epoch 3 - iter 588/1476 - loss 0.07499880 - time (sec): 28.47 - samples/sec: 2387.22 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:09:19,700 epoch 3 - iter 735/1476 - loss 0.08049723 - time (sec): 35.55 - samples/sec: 2374.58 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:09:26,769 epoch 3 - iter 882/1476 - loss 0.08104214 - time (sec): 42.62 - samples/sec: 2339.21 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:09:34,338 epoch 3 - iter 1029/1476 - loss 0.08301973 - time (sec): 50.19 - samples/sec: 2344.05 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:09:41,499 epoch 3 - iter 1176/1476 - loss 0.08364485 - time (sec): 57.35 - samples/sec: 2332.93 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:09:48,739 epoch 3 - iter 1323/1476 - loss 0.08295442 - time (sec): 64.59 - samples/sec: 2321.23 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:09:56,409 epoch 3 - iter 1470/1476 - loss 0.08380446 - time (sec): 72.26 - samples/sec: 2296.93 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:09:56,681 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:09:56,681 EPOCH 3 done: loss 0.0838 - lr: 0.000023 2023-10-17 20:10:08,037 DEV : loss 0.1379304975271225 - f1-score (micro avg) 0.8223 2023-10-17 20:10:08,071 saving best model 2023-10-17 20:10:08,547 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:10:15,658 epoch 4 - iter 147/1476 - loss 0.05625078 - time (sec): 7.11 - samples/sec: 2241.51 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:10:23,083 epoch 4 - iter 294/1476 - loss 0.05457959 - time (sec): 14.53 - samples/sec: 2321.35 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:10:30,071 epoch 4 - iter 441/1476 - loss 0.05927497 - time (sec): 21.52 - samples/sec: 2279.64 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:10:37,495 epoch 4 - iter 588/1476 - loss 0.05943946 - time (sec): 28.94 - samples/sec: 2265.71 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:10:45,002 epoch 4 - iter 735/1476 - loss 0.06174984 - time (sec): 36.45 - samples/sec: 2202.49 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:10:52,447 epoch 4 - iter 882/1476 - loss 0.05984732 - time (sec): 43.90 - samples/sec: 2211.74 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:10:59,329 epoch 4 - iter 1029/1476 - loss 0.05718144 - time (sec): 50.78 - samples/sec: 2222.57 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:11:06,848 epoch 4 - iter 1176/1476 - loss 0.05612735 - time (sec): 58.30 - samples/sec: 2247.18 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:11:13,792 epoch 4 - iter 1323/1476 - loss 0.05566318 - time (sec): 65.24 - samples/sec: 2254.84 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:11:21,672 epoch 4 - iter 1470/1476 - loss 0.05600539 - time (sec): 73.12 - samples/sec: 2266.68 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:11:21,955 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:11:21,955 EPOCH 4 done: loss 0.0559 - lr: 0.000020 2023-10-17 20:11:33,291 DEV : loss 0.16167429089546204 - f1-score (micro avg) 0.846 2023-10-17 20:11:33,323 saving best model 2023-10-17 20:11:33,784 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:11:41,069 epoch 5 - iter 147/1476 - loss 0.03312893 - time (sec): 7.28 - samples/sec: 2445.55 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:11:47,781 epoch 5 - iter 294/1476 - loss 0.03390059 - time (sec): 13.99 - samples/sec: 2407.91 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:11:54,966 epoch 5 - iter 441/1476 - loss 0.03294051 - time (sec): 21.18 - samples/sec: 2384.13 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:12:02,147 epoch 5 - iter 588/1476 - loss 0.03900188 - time (sec): 28.36 - samples/sec: 2358.13 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:12:09,336 epoch 5 - iter 735/1476 - loss 0.03809314 - time (sec): 35.55 - samples/sec: 2359.36 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:12:16,735 epoch 5 - iter 882/1476 - loss 0.03709148 - time (sec): 42.95 - samples/sec: 2337.85 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:12:23,992 epoch 5 - iter 1029/1476 - loss 0.03763883 - time (sec): 50.21 - samples/sec: 2316.28 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:12:30,787 epoch 5 - iter 1176/1476 - loss 0.03885216 - time (sec): 57.00 - samples/sec: 2309.32 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:12:38,354 epoch 5 - iter 1323/1476 - loss 0.03762999 - time (sec): 64.57 - samples/sec: 2325.78 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:12:45,409 epoch 5 - iter 1470/1476 - loss 0.03723655 - time (sec): 71.62 - samples/sec: 2317.05 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:12:45,675 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:45,675 EPOCH 5 done: loss 0.0377 - lr: 0.000017 2023-10-17 20:12:57,231 DEV : loss 0.1790267527103424 - f1-score (micro avg) 0.8426 2023-10-17 20:12:57,261 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:13:04,516 epoch 6 - iter 147/1476 - loss 0.02474197 - time (sec): 7.25 - samples/sec: 2182.35 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:13:11,743 epoch 6 - iter 294/1476 - loss 0.02176561 - time (sec): 14.48 - samples/sec: 2281.17 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:13:19,002 epoch 6 - iter 441/1476 - loss 0.02055555 - time (sec): 21.74 - samples/sec: 2289.19 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:13:26,628 epoch 6 - iter 588/1476 - loss 0.02265555 - time (sec): 29.37 - samples/sec: 2240.42 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:13:33,937 epoch 6 - iter 735/1476 - loss 0.02383975 - time (sec): 36.68 - samples/sec: 2233.14 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:13:41,057 epoch 6 - iter 882/1476 - loss 0.02491593 - time (sec): 43.80 - samples/sec: 2228.19 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:13:48,543 epoch 6 - iter 1029/1476 - loss 0.02373826 - time (sec): 51.28 - samples/sec: 2242.09 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:13:55,584 epoch 6 - iter 1176/1476 - loss 0.02425560 - time (sec): 58.32 - samples/sec: 2255.37 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:14:02,711 epoch 6 - iter 1323/1476 - loss 0.02426721 - time (sec): 65.45 - samples/sec: 2257.42 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:14:10,120 epoch 6 - iter 1470/1476 - loss 0.02573153 - time (sec): 72.86 - samples/sec: 2275.89 - lr: 0.000013 - momentum: 0.000000 2023-10-17 20:14:10,406 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:14:10,406 EPOCH 6 done: loss 0.0256 - lr: 0.000013 2023-10-17 20:14:21,960 DEV : loss 0.1823473572731018 - f1-score (micro avg) 0.8415 2023-10-17 20:14:21,993 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:14:29,433 epoch 7 - iter 147/1476 - loss 0.01049509 - time (sec): 7.44 - samples/sec: 2270.28 - lr: 0.000013 - momentum: 0.000000 2023-10-17 20:14:36,187 epoch 7 - iter 294/1476 - loss 0.01510363 - time (sec): 14.19 - samples/sec: 2341.53 - lr: 0.000013 - momentum: 0.000000 2023-10-17 20:14:43,513 epoch 7 - iter 441/1476 - loss 0.01732408 - time (sec): 21.52 - samples/sec: 2376.45 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:14:50,969 epoch 7 - iter 588/1476 - loss 0.01690878 - time (sec): 28.97 - samples/sec: 2369.98 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:14:58,196 epoch 7 - iter 735/1476 - loss 0.02010782 - time (sec): 36.20 - samples/sec: 2330.85 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:15:05,260 epoch 7 - iter 882/1476 - loss 0.02004143 - time (sec): 43.27 - samples/sec: 2338.44 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:15:12,552 epoch 7 - iter 1029/1476 - loss 0.01839535 - time (sec): 50.56 - samples/sec: 2313.93 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:15:19,971 epoch 7 - iter 1176/1476 - loss 0.01888196 - time (sec): 57.98 - samples/sec: 2313.87 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:15:27,136 epoch 7 - iter 1323/1476 - loss 0.01831645 - time (sec): 65.14 - samples/sec: 2320.63 - lr: 0.000010 - momentum: 0.000000 2023-10-17 20:15:33,941 epoch 7 - iter 1470/1476 - loss 0.01784839 - time (sec): 71.95 - samples/sec: 2305.36 - lr: 0.000010 - momentum: 0.000000 2023-10-17 20:15:34,199 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:15:34,200 EPOCH 7 done: loss 0.0180 - lr: 0.000010 2023-10-17 20:15:45,643 DEV : loss 0.19402551651000977 - f1-score (micro avg) 0.8431 2023-10-17 20:15:45,677 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:15:52,842 epoch 8 - iter 147/1476 - loss 0.01320226 - time (sec): 7.16 - samples/sec: 2278.37 - lr: 0.000010 - momentum: 0.000000 2023-10-17 20:16:00,302 epoch 8 - iter 294/1476 - loss 0.01657591 - time (sec): 14.62 - samples/sec: 2333.78 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:16:07,287 epoch 8 - iter 441/1476 - loss 0.01541718 - time (sec): 21.61 - samples/sec: 2302.97 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:16:14,178 epoch 8 - iter 588/1476 - loss 0.01364886 - time (sec): 28.50 - samples/sec: 2306.16 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:16:21,411 epoch 8 - iter 735/1476 - loss 0.01449721 - time (sec): 35.73 - samples/sec: 2315.68 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:16:28,411 epoch 8 - iter 882/1476 - loss 0.01320813 - time (sec): 42.73 - samples/sec: 2299.05 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:16:36,244 epoch 8 - iter 1029/1476 - loss 0.01499181 - time (sec): 50.57 - samples/sec: 2327.41 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:16:43,224 epoch 8 - iter 1176/1476 - loss 0.01478780 - time (sec): 57.55 - samples/sec: 2319.55 - lr: 0.000007 - momentum: 0.000000 2023-10-17 20:16:50,451 epoch 8 - iter 1323/1476 - loss 0.01429358 - time (sec): 64.77 - samples/sec: 2320.02 - lr: 0.000007 - momentum: 0.000000 2023-10-17 20:16:57,506 epoch 8 - iter 1470/1476 - loss 0.01418919 - time (sec): 71.83 - samples/sec: 2303.65 - lr: 0.000007 - momentum: 0.000000 2023-10-17 20:16:57,853 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:16:57,853 EPOCH 8 done: loss 0.0141 - lr: 0.000007 2023-10-17 20:17:09,346 DEV : loss 0.20007802546024323 - f1-score (micro avg) 0.8496 2023-10-17 20:17:09,379 saving best model 2023-10-17 20:17:09,862 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:17:17,475 epoch 9 - iter 147/1476 - loss 0.00436533 - time (sec): 7.61 - samples/sec: 2367.42 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:17:24,847 epoch 9 - iter 294/1476 - loss 0.00510740 - time (sec): 14.98 - samples/sec: 2429.53 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:17:32,428 epoch 9 - iter 441/1476 - loss 0.00763822 - time (sec): 22.56 - samples/sec: 2423.43 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:17:39,465 epoch 9 - iter 588/1476 - loss 0.00743456 - time (sec): 29.60 - samples/sec: 2361.44 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:17:47,117 epoch 9 - iter 735/1476 - loss 0.00689757 - time (sec): 37.25 - samples/sec: 2308.36 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:17:54,005 epoch 9 - iter 882/1476 - loss 0.00620989 - time (sec): 44.14 - samples/sec: 2316.95 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:18:00,853 epoch 9 - iter 1029/1476 - loss 0.00730072 - time (sec): 50.99 - samples/sec: 2301.79 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:18:07,914 epoch 9 - iter 1176/1476 - loss 0.00714572 - time (sec): 58.05 - samples/sec: 2289.46 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:18:15,625 epoch 9 - iter 1323/1476 - loss 0.00707158 - time (sec): 65.76 - samples/sec: 2299.61 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:18:22,423 epoch 9 - iter 1470/1476 - loss 0.00773284 - time (sec): 72.56 - samples/sec: 2283.54 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:18:22,726 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:18:22,726 EPOCH 9 done: loss 0.0078 - lr: 0.000003 2023-10-17 20:18:34,319 DEV : loss 0.2041151374578476 - f1-score (micro avg) 0.8596 2023-10-17 20:18:34,349 saving best model 2023-10-17 20:18:34,828 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:18:42,621 epoch 10 - iter 147/1476 - loss 0.00709689 - time (sec): 7.79 - samples/sec: 2535.00 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:18:50,003 epoch 10 - iter 294/1476 - loss 0.00608595 - time (sec): 15.17 - samples/sec: 2439.34 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:18:57,062 epoch 10 - iter 441/1476 - loss 0.00472843 - time (sec): 22.23 - samples/sec: 2396.12 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:19:04,224 epoch 10 - iter 588/1476 - loss 0.00501675 - time (sec): 29.39 - samples/sec: 2314.37 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:19:11,140 epoch 10 - iter 735/1476 - loss 0.00493818 - time (sec): 36.31 - samples/sec: 2306.06 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:19:18,274 epoch 10 - iter 882/1476 - loss 0.00479554 - time (sec): 43.44 - samples/sec: 2297.04 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:19:25,625 epoch 10 - iter 1029/1476 - loss 0.00501958 - time (sec): 50.79 - samples/sec: 2305.35 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:19:32,682 epoch 10 - iter 1176/1476 - loss 0.00595793 - time (sec): 57.85 - samples/sec: 2291.26 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:19:39,780 epoch 10 - iter 1323/1476 - loss 0.00561353 - time (sec): 64.95 - samples/sec: 2284.04 - lr: 0.000000 - momentum: 0.000000 2023-10-17 20:19:47,478 epoch 10 - iter 1470/1476 - loss 0.00566830 - time (sec): 72.65 - samples/sec: 2283.76 - lr: 0.000000 - momentum: 0.000000 2023-10-17 20:19:47,747 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:19:47,748 EPOCH 10 done: loss 0.0057 - lr: 0.000000 2023-10-17 20:19:59,001 DEV : loss 0.2035822868347168 - f1-score (micro avg) 0.8602 2023-10-17 20:19:59,031 saving best model 2023-10-17 20:19:59,889 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:19:59,891 Loading model from best epoch ... 2023-10-17 20:20:01,237 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod 2023-10-17 20:20:07,284 Results: - F-score (micro) 0.7934 - F-score (macro) 0.7114 - Accuracy 0.6758 By class: precision recall f1-score support loc 0.8474 0.8671 0.8571 858 pers 0.7487 0.8045 0.7756 537 org 0.5329 0.6136 0.5704 132 prod 0.7500 0.7377 0.7438 61 time 0.5625 0.6667 0.6102 54 micro avg 0.7730 0.8149 0.7934 1642 macro avg 0.6883 0.7379 0.7114 1642 weighted avg 0.7768 0.8149 0.7951 1642 2023-10-17 20:20:07,284 ----------------------------------------------------------------------------------------------------