2023-10-17 20:12:25,534 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:25,535 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 20:12:25,535 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:25,535 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 2023-10-17 20:12:25,535 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:25,535 Train: 1085 sentences 2023-10-17 20:12:25,536 (train_with_dev=False, train_with_test=False) 2023-10-17 20:12:25,536 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:25,536 Training Params: 2023-10-17 20:12:25,536 - learning_rate: "3e-05" 2023-10-17 20:12:25,536 - mini_batch_size: "8" 2023-10-17 20:12:25,536 - max_epochs: "10" 2023-10-17 20:12:25,536 - shuffle: "True" 2023-10-17 20:12:25,536 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:25,536 Plugins: 2023-10-17 20:12:25,536 - TensorboardLogger 2023-10-17 20:12:25,536 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 20:12:25,536 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:25,536 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 20:12:25,536 - metric: "('micro avg', 'f1-score')" 2023-10-17 20:12:25,536 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:25,536 Computation: 2023-10-17 20:12:25,536 - compute on device: cuda:0 2023-10-17 20:12:25,536 - embedding storage: none 2023-10-17 20:12:25,536 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:25,536 Model training base path: "hmbench-newseye/sv-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" 2023-10-17 20:12:25,536 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:25,536 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:25,536 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 20:12:26,980 epoch 1 - iter 13/136 - loss 3.56469652 - time (sec): 1.44 - samples/sec: 3585.96 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:12:28,536 epoch 1 - iter 26/136 - loss 3.33018314 - time (sec): 3.00 - samples/sec: 3781.08 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:12:30,021 epoch 1 - iter 39/136 - loss 2.95543144 - time (sec): 4.48 - samples/sec: 3735.60 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:12:31,254 epoch 1 - iter 52/136 - loss 2.55098163 - time (sec): 5.72 - samples/sec: 3716.28 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:12:32,731 epoch 1 - iter 65/136 - loss 2.16561603 - time (sec): 7.19 - samples/sec: 3665.22 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:12:33,786 epoch 1 - iter 78/136 - loss 1.95630135 - time (sec): 8.25 - samples/sec: 3676.32 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:12:35,197 epoch 1 - iter 91/136 - loss 1.74967521 - time (sec): 9.66 - samples/sec: 3616.63 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:12:36,561 epoch 1 - iter 104/136 - loss 1.55037843 - time (sec): 11.02 - samples/sec: 3669.59 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:12:37,858 epoch 1 - iter 117/136 - loss 1.41500927 - time (sec): 12.32 - samples/sec: 3698.94 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:12:39,033 epoch 1 - iter 130/136 - loss 1.31279338 - time (sec): 13.50 - samples/sec: 3697.45 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:12:39,636 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:39,636 EPOCH 1 done: loss 1.2734 - lr: 0.000028 2023-10-17 20:12:40,860 DEV : loss 0.17920981347560883 - f1-score (micro avg) 0.6068 2023-10-17 20:12:40,865 saving best model 2023-10-17 20:12:41,222 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:42,459 epoch 2 - iter 13/136 - loss 0.23296681 - time (sec): 1.24 - samples/sec: 3765.35 - lr: 0.000030 - momentum: 0.000000 2023-10-17 20:12:43,820 epoch 2 - iter 26/136 - loss 0.24799180 - time (sec): 2.60 - samples/sec: 3732.19 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:12:44,999 epoch 2 - iter 39/136 - loss 0.22292966 - time (sec): 3.78 - samples/sec: 3845.54 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:12:46,415 epoch 2 - iter 52/136 - loss 0.21149373 - time (sec): 5.19 - samples/sec: 3724.35 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:12:47,777 epoch 2 - iter 65/136 - loss 0.20240517 - time (sec): 6.55 - samples/sec: 3700.29 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:12:49,399 epoch 2 - iter 78/136 - loss 0.19342818 - time (sec): 8.18 - samples/sec: 3600.69 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:12:50,745 epoch 2 - iter 91/136 - loss 0.18557542 - time (sec): 9.52 - samples/sec: 3600.10 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:12:52,371 epoch 2 - iter 104/136 - loss 0.18162443 - time (sec): 11.15 - samples/sec: 3578.27 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:12:53,841 epoch 2 - iter 117/136 - loss 0.17641577 - time (sec): 12.62 - samples/sec: 3601.85 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:12:55,198 epoch 2 - iter 130/136 - loss 0.16835610 - time (sec): 13.97 - samples/sec: 3576.06 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:12:55,859 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:55,860 EPOCH 2 done: loss 0.1664 - lr: 0.000027 2023-10-17 20:12:57,380 DEV : loss 0.12096702307462692 - f1-score (micro avg) 0.7178 2023-10-17 20:12:57,385 saving best model 2023-10-17 20:12:57,885 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:12:59,565 epoch 3 - iter 13/136 - loss 0.10688261 - time (sec): 1.68 - samples/sec: 2818.79 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:13:00,706 epoch 3 - iter 26/136 - loss 0.11348635 - time (sec): 2.82 - samples/sec: 3122.93 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:13:02,144 epoch 3 - iter 39/136 - loss 0.10946288 - time (sec): 4.26 - samples/sec: 3337.16 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:13:03,448 epoch 3 - iter 52/136 - loss 0.09875128 - time (sec): 5.56 - samples/sec: 3419.92 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:13:04,795 epoch 3 - iter 65/136 - loss 0.10238528 - time (sec): 6.91 - samples/sec: 3496.81 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:13:06,069 epoch 3 - iter 78/136 - loss 0.09890742 - time (sec): 8.18 - samples/sec: 3529.37 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:13:07,400 epoch 3 - iter 91/136 - loss 0.09927605 - time (sec): 9.51 - samples/sec: 3489.99 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:13:09,059 epoch 3 - iter 104/136 - loss 0.10213739 - time (sec): 11.17 - samples/sec: 3465.90 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:13:10,483 epoch 3 - iter 117/136 - loss 0.10125728 - time (sec): 12.60 - samples/sec: 3489.58 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:13:12,174 epoch 3 - iter 130/136 - loss 0.09993701 - time (sec): 14.29 - samples/sec: 3467.14 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:13:12,782 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:13:12,782 EPOCH 3 done: loss 0.0986 - lr: 0.000024 2023-10-17 20:13:14,255 DEV : loss 0.08591549098491669 - f1-score (micro avg) 0.7942 2023-10-17 20:13:14,260 saving best model 2023-10-17 20:13:14,727 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:13:15,913 epoch 4 - iter 13/136 - loss 0.06018926 - time (sec): 1.18 - samples/sec: 3558.55 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:13:17,244 epoch 4 - iter 26/136 - loss 0.06085278 - time (sec): 2.51 - samples/sec: 3578.74 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:13:18,689 epoch 4 - iter 39/136 - loss 0.06043327 - time (sec): 3.96 - samples/sec: 3479.26 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:13:20,225 epoch 4 - iter 52/136 - loss 0.06185287 - time (sec): 5.49 - samples/sec: 3426.97 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:13:21,401 epoch 4 - iter 65/136 - loss 0.05755276 - time (sec): 6.67 - samples/sec: 3537.79 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:13:23,133 epoch 4 - iter 78/136 - loss 0.06276857 - time (sec): 8.40 - samples/sec: 3485.61 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:13:24,317 epoch 4 - iter 91/136 - loss 0.06484688 - time (sec): 9.59 - samples/sec: 3540.53 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:13:25,962 epoch 4 - iter 104/136 - loss 0.06068370 - time (sec): 11.23 - samples/sec: 3532.08 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:13:27,379 epoch 4 - iter 117/136 - loss 0.06208566 - time (sec): 12.65 - samples/sec: 3578.80 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:13:28,583 epoch 4 - iter 130/136 - loss 0.06298638 - time (sec): 13.85 - samples/sec: 3603.24 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:13:29,189 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:13:29,189 EPOCH 4 done: loss 0.0615 - lr: 0.000020 2023-10-17 20:13:30,692 DEV : loss 0.10039487481117249 - f1-score (micro avg) 0.7971 2023-10-17 20:13:30,697 saving best model 2023-10-17 20:13:31,165 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:13:32,955 epoch 5 - iter 13/136 - loss 0.03987252 - time (sec): 1.79 - samples/sec: 3074.23 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:13:34,130 epoch 5 - iter 26/136 - loss 0.03912310 - time (sec): 2.96 - samples/sec: 3323.99 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:13:35,468 epoch 5 - iter 39/136 - loss 0.03863979 - time (sec): 4.30 - samples/sec: 3262.17 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:13:36,801 epoch 5 - iter 52/136 - loss 0.03622420 - time (sec): 5.63 - samples/sec: 3478.53 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:13:38,388 epoch 5 - iter 65/136 - loss 0.03387900 - time (sec): 7.22 - samples/sec: 3483.48 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:13:39,949 epoch 5 - iter 78/136 - loss 0.03469888 - time (sec): 8.78 - samples/sec: 3504.32 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:13:41,157 epoch 5 - iter 91/136 - loss 0.03515893 - time (sec): 9.99 - samples/sec: 3502.52 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:13:42,657 epoch 5 - iter 104/136 - loss 0.03745754 - time (sec): 11.49 - samples/sec: 3501.30 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:13:44,109 epoch 5 - iter 117/136 - loss 0.03876292 - time (sec): 12.94 - samples/sec: 3462.10 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:13:45,464 epoch 5 - iter 130/136 - loss 0.03993650 - time (sec): 14.30 - samples/sec: 3492.18 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:13:46,046 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:13:46,047 EPOCH 5 done: loss 0.0401 - lr: 0.000017 2023-10-17 20:13:47,576 DEV : loss 0.11180326342582703 - f1-score (micro avg) 0.7904 2023-10-17 20:13:47,582 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:13:49,187 epoch 6 - iter 13/136 - loss 0.02256178 - time (sec): 1.60 - samples/sec: 3203.98 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:13:50,516 epoch 6 - iter 26/136 - loss 0.02483432 - time (sec): 2.93 - samples/sec: 3436.08 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:13:51,729 epoch 6 - iter 39/136 - loss 0.02830385 - time (sec): 4.15 - samples/sec: 3482.11 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:13:53,135 epoch 6 - iter 52/136 - loss 0.02444290 - time (sec): 5.55 - samples/sec: 3479.67 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:13:54,664 epoch 6 - iter 65/136 - loss 0.02307868 - time (sec): 7.08 - samples/sec: 3515.74 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:13:55,765 epoch 6 - iter 78/136 - loss 0.02339547 - time (sec): 8.18 - samples/sec: 3541.86 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:13:57,053 epoch 6 - iter 91/136 - loss 0.02421288 - time (sec): 9.47 - samples/sec: 3540.14 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:13:58,360 epoch 6 - iter 104/136 - loss 0.02596671 - time (sec): 10.78 - samples/sec: 3563.87 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:13:59,837 epoch 6 - iter 117/136 - loss 0.02545975 - time (sec): 12.25 - samples/sec: 3577.26 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:14:01,410 epoch 6 - iter 130/136 - loss 0.02737841 - time (sec): 13.83 - samples/sec: 3566.42 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:14:02,079 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:14:02,080 EPOCH 6 done: loss 0.0269 - lr: 0.000014 2023-10-17 20:14:03,594 DEV : loss 0.11931055039167404 - f1-score (micro avg) 0.7906 2023-10-17 20:14:03,599 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:14:05,036 epoch 7 - iter 13/136 - loss 0.02728369 - time (sec): 1.44 - samples/sec: 3647.55 - lr: 0.000013 - momentum: 0.000000 2023-10-17 20:14:06,754 epoch 7 - iter 26/136 - loss 0.02508212 - time (sec): 3.15 - samples/sec: 3243.52 - lr: 0.000013 - momentum: 0.000000 2023-10-17 20:14:07,977 epoch 7 - iter 39/136 - loss 0.01944223 - time (sec): 4.38 - samples/sec: 3359.95 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:14:09,367 epoch 7 - iter 52/136 - loss 0.01891054 - time (sec): 5.77 - samples/sec: 3445.16 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:14:10,931 epoch 7 - iter 65/136 - loss 0.01886752 - time (sec): 7.33 - samples/sec: 3414.88 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:14:12,273 epoch 7 - iter 78/136 - loss 0.02600379 - time (sec): 8.67 - samples/sec: 3438.12 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:14:13,711 epoch 7 - iter 91/136 - loss 0.02405010 - time (sec): 10.11 - samples/sec: 3474.80 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:14:15,069 epoch 7 - iter 104/136 - loss 0.02314826 - time (sec): 11.47 - samples/sec: 3458.49 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:14:16,353 epoch 7 - iter 117/136 - loss 0.02220090 - time (sec): 12.75 - samples/sec: 3495.04 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:14:17,726 epoch 7 - iter 130/136 - loss 0.02185557 - time (sec): 14.13 - samples/sec: 3499.49 - lr: 0.000010 - momentum: 0.000000 2023-10-17 20:14:18,387 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:14:18,387 EPOCH 7 done: loss 0.0216 - lr: 0.000010 2023-10-17 20:14:19,971 DEV : loss 0.1356595754623413 - f1-score (micro avg) 0.7842 2023-10-17 20:14:19,978 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:14:21,419 epoch 8 - iter 13/136 - loss 0.01459122 - time (sec): 1.44 - samples/sec: 3223.63 - lr: 0.000010 - momentum: 0.000000 2023-10-17 20:14:22,884 epoch 8 - iter 26/136 - loss 0.01524438 - time (sec): 2.91 - samples/sec: 3345.87 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:14:24,288 epoch 8 - iter 39/136 - loss 0.01681237 - time (sec): 4.31 - samples/sec: 3506.61 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:14:25,632 epoch 8 - iter 52/136 - loss 0.01579062 - time (sec): 5.65 - samples/sec: 3488.23 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:14:27,289 epoch 8 - iter 65/136 - loss 0.01850053 - time (sec): 7.31 - samples/sec: 3476.24 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:14:28,856 epoch 8 - iter 78/136 - loss 0.01750239 - time (sec): 8.88 - samples/sec: 3400.75 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:14:30,174 epoch 8 - iter 91/136 - loss 0.01679539 - time (sec): 10.20 - samples/sec: 3458.71 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:14:31,621 epoch 8 - iter 104/136 - loss 0.01636561 - time (sec): 11.64 - samples/sec: 3460.03 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:14:32,839 epoch 8 - iter 117/136 - loss 0.01625463 - time (sec): 12.86 - samples/sec: 3488.55 - lr: 0.000007 - momentum: 0.000000 2023-10-17 20:14:34,305 epoch 8 - iter 130/136 - loss 0.01599673 - time (sec): 14.33 - samples/sec: 3475.87 - lr: 0.000007 - momentum: 0.000000 2023-10-17 20:14:34,871 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:14:34,872 EPOCH 8 done: loss 0.0155 - lr: 0.000007 2023-10-17 20:14:36,374 DEV : loss 0.13436543941497803 - f1-score (micro avg) 0.8051 2023-10-17 20:14:36,378 saving best model 2023-10-17 20:14:36,851 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:14:38,467 epoch 9 - iter 13/136 - loss 0.01017808 - time (sec): 1.61 - samples/sec: 3125.28 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:14:39,861 epoch 9 - iter 26/136 - loss 0.00781613 - time (sec): 3.01 - samples/sec: 3384.75 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:14:41,513 epoch 9 - iter 39/136 - loss 0.00860655 - time (sec): 4.66 - samples/sec: 3275.36 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:14:42,651 epoch 9 - iter 52/136 - loss 0.00830057 - time (sec): 5.80 - samples/sec: 3299.77 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:14:43,851 epoch 9 - iter 65/136 - loss 0.00782478 - time (sec): 7.00 - samples/sec: 3391.09 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:14:45,388 epoch 9 - iter 78/136 - loss 0.00919217 - time (sec): 8.53 - samples/sec: 3393.01 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:14:46,901 epoch 9 - iter 91/136 - loss 0.01018609 - time (sec): 10.05 - samples/sec: 3385.34 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:14:48,204 epoch 9 - iter 104/136 - loss 0.01072845 - time (sec): 11.35 - samples/sec: 3442.69 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:14:49,825 epoch 9 - iter 117/136 - loss 0.01148823 - time (sec): 12.97 - samples/sec: 3450.66 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:14:51,005 epoch 9 - iter 130/136 - loss 0.01159600 - time (sec): 14.15 - samples/sec: 3492.50 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:14:51,676 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:14:51,676 EPOCH 9 done: loss 0.0114 - lr: 0.000004 2023-10-17 20:14:53,187 DEV : loss 0.14552520215511322 - f1-score (micro avg) 0.8183 2023-10-17 20:14:53,191 saving best model 2023-10-17 20:14:53,662 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:14:54,950 epoch 10 - iter 13/136 - loss 0.01469245 - time (sec): 1.29 - samples/sec: 3230.38 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:14:56,089 epoch 10 - iter 26/136 - loss 0.02040672 - time (sec): 2.42 - samples/sec: 3368.12 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:14:57,468 epoch 10 - iter 39/136 - loss 0.01427909 - time (sec): 3.80 - samples/sec: 3452.11 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:14:58,855 epoch 10 - iter 52/136 - loss 0.01331876 - time (sec): 5.19 - samples/sec: 3514.99 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:15:00,113 epoch 10 - iter 65/136 - loss 0.01438903 - time (sec): 6.45 - samples/sec: 3491.61 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:15:01,548 epoch 10 - iter 78/136 - loss 0.01258656 - time (sec): 7.88 - samples/sec: 3591.51 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:15:03,037 epoch 10 - iter 91/136 - loss 0.01300637 - time (sec): 9.37 - samples/sec: 3576.70 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:15:04,424 epoch 10 - iter 104/136 - loss 0.01261802 - time (sec): 10.76 - samples/sec: 3624.70 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:15:05,828 epoch 10 - iter 117/136 - loss 0.01157527 - time (sec): 12.16 - samples/sec: 3630.39 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:15:07,223 epoch 10 - iter 130/136 - loss 0.01084597 - time (sec): 13.56 - samples/sec: 3632.39 - lr: 0.000000 - momentum: 0.000000 2023-10-17 20:15:08,084 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:15:08,084 EPOCH 10 done: loss 0.0107 - lr: 0.000000 2023-10-17 20:15:09,555 DEV : loss 0.15006117522716522 - f1-score (micro avg) 0.8132 2023-10-17 20:15:09,926 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:15:09,928 Loading model from best epoch ... 2023-10-17 20:15:11,517 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 2023-10-17 20:15:13,740 Results: - F-score (micro) 0.7926 - F-score (macro) 0.7586 - Accuracy 0.6716 By class: precision recall f1-score support LOC 0.8479 0.8397 0.8438 312 PER 0.7121 0.8798 0.7871 208 ORG 0.4667 0.5091 0.4870 55 HumanProd 0.8462 1.0000 0.9167 22 micro avg 0.7592 0.8291 0.7926 597 macro avg 0.7182 0.8072 0.7586 597 weighted avg 0.7654 0.8291 0.7939 597 2023-10-17 20:15:13,740 ----------------------------------------------------------------------------------------------------