2023-10-17 20:02:07,718 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:07,719 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 20:02:07,719 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:07,719 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 20:02:07,719 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:07,719 Train: 1085 sentences 2023-10-17 20:02:07,719 (train_with_dev=False, train_with_test=False) 2023-10-17 20:02:07,719 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:07,719 Training Params: 2023-10-17 20:02:07,719 - learning_rate: "5e-05" 2023-10-17 20:02:07,719 - mini_batch_size: "8" 2023-10-17 20:02:07,719 - max_epochs: "10" 2023-10-17 20:02:07,719 - shuffle: "True" 2023-10-17 20:02:07,719 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:07,719 Plugins: 2023-10-17 20:02:07,720 - TensorboardLogger 2023-10-17 20:02:07,720 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 20:02:07,720 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:07,720 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 20:02:07,720 - metric: "('micro avg', 'f1-score')" 2023-10-17 20:02:07,720 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:07,720 Computation: 2023-10-17 20:02:07,720 - compute on device: cuda:0 2023-10-17 20:02:07,720 - embedding storage: none 2023-10-17 20:02:07,720 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:07,720 Model training base path: "hmbench-newseye/sv-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" 2023-10-17 20:02:07,720 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:07,720 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:07,720 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 20:02:09,052 epoch 1 - iter 13/136 - loss 3.90680085 - time (sec): 1.33 - samples/sec: 3528.83 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:02:10,322 epoch 1 - iter 26/136 - loss 3.55895351 - time (sec): 2.60 - samples/sec: 3430.69 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:02:11,749 epoch 1 - iter 39/136 - loss 2.74126999 - time (sec): 4.03 - samples/sec: 3594.16 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:02:13,066 epoch 1 - iter 52/136 - loss 2.17219974 - time (sec): 5.35 - samples/sec: 3639.45 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:02:14,451 epoch 1 - iter 65/136 - loss 1.87047412 - time (sec): 6.73 - samples/sec: 3551.62 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:02:15,833 epoch 1 - iter 78/136 - loss 1.60103945 - time (sec): 8.11 - samples/sec: 3604.49 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:02:17,294 epoch 1 - iter 91/136 - loss 1.41316409 - time (sec): 9.57 - samples/sec: 3599.18 - lr: 0.000033 - momentum: 0.000000 2023-10-17 20:02:18,721 epoch 1 - iter 104/136 - loss 1.25997927 - time (sec): 11.00 - samples/sec: 3626.72 - lr: 0.000038 - momentum: 0.000000 2023-10-17 20:02:20,174 epoch 1 - iter 117/136 - loss 1.14147820 - time (sec): 12.45 - samples/sec: 3637.12 - lr: 0.000043 - momentum: 0.000000 2023-10-17 20:02:21,708 epoch 1 - iter 130/136 - loss 1.05471195 - time (sec): 13.99 - samples/sec: 3567.84 - lr: 0.000047 - momentum: 0.000000 2023-10-17 20:02:22,347 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:22,348 EPOCH 1 done: loss 1.0206 - lr: 0.000047 2023-10-17 20:02:23,475 DEV : loss 0.1729203313589096 - f1-score (micro avg) 0.6042 2023-10-17 20:02:23,480 saving best model 2023-10-17 20:02:23,882 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:25,325 epoch 2 - iter 13/136 - loss 0.14807463 - time (sec): 1.44 - samples/sec: 3461.82 - lr: 0.000050 - momentum: 0.000000 2023-10-17 20:02:26,662 epoch 2 - iter 26/136 - loss 0.15887359 - time (sec): 2.78 - samples/sec: 3620.58 - lr: 0.000049 - momentum: 0.000000 2023-10-17 20:02:28,031 epoch 2 - iter 39/136 - loss 0.16702427 - time (sec): 4.15 - samples/sec: 3613.56 - lr: 0.000048 - momentum: 0.000000 2023-10-17 20:02:29,731 epoch 2 - iter 52/136 - loss 0.16318825 - time (sec): 5.85 - samples/sec: 3524.72 - lr: 0.000048 - momentum: 0.000000 2023-10-17 20:02:30,932 epoch 2 - iter 65/136 - loss 0.16136772 - time (sec): 7.05 - samples/sec: 3570.87 - lr: 0.000047 - momentum: 0.000000 2023-10-17 20:02:32,381 epoch 2 - iter 78/136 - loss 0.16561702 - time (sec): 8.50 - samples/sec: 3496.40 - lr: 0.000047 - momentum: 0.000000 2023-10-17 20:02:33,674 epoch 2 - iter 91/136 - loss 0.16472638 - time (sec): 9.79 - samples/sec: 3496.53 - lr: 0.000046 - momentum: 0.000000 2023-10-17 20:02:35,123 epoch 2 - iter 104/136 - loss 0.15378818 - time (sec): 11.24 - samples/sec: 3543.22 - lr: 0.000046 - momentum: 0.000000 2023-10-17 20:02:36,492 epoch 2 - iter 117/136 - loss 0.15058060 - time (sec): 12.61 - samples/sec: 3498.24 - lr: 0.000045 - momentum: 0.000000 2023-10-17 20:02:37,954 epoch 2 - iter 130/136 - loss 0.14512488 - time (sec): 14.07 - samples/sec: 3536.68 - lr: 0.000045 - momentum: 0.000000 2023-10-17 20:02:38,493 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:38,494 EPOCH 2 done: loss 0.1436 - lr: 0.000045 2023-10-17 20:02:39,948 DEV : loss 0.10842905938625336 - f1-score (micro avg) 0.7751 2023-10-17 20:02:39,954 saving best model 2023-10-17 20:02:40,491 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:42,041 epoch 3 - iter 13/136 - loss 0.07133591 - time (sec): 1.54 - samples/sec: 3401.08 - lr: 0.000044 - momentum: 0.000000 2023-10-17 20:02:43,550 epoch 3 - iter 26/136 - loss 0.08050463 - time (sec): 3.05 - samples/sec: 3625.60 - lr: 0.000043 - momentum: 0.000000 2023-10-17 20:02:44,850 epoch 3 - iter 39/136 - loss 0.07549434 - time (sec): 4.35 - samples/sec: 3638.66 - lr: 0.000043 - momentum: 0.000000 2023-10-17 20:02:46,389 epoch 3 - iter 52/136 - loss 0.07539455 - time (sec): 5.89 - samples/sec: 3583.23 - lr: 0.000042 - momentum: 0.000000 2023-10-17 20:02:47,824 epoch 3 - iter 65/136 - loss 0.07284452 - time (sec): 7.32 - samples/sec: 3546.17 - lr: 0.000042 - momentum: 0.000000 2023-10-17 20:02:49,109 epoch 3 - iter 78/136 - loss 0.07551226 - time (sec): 8.61 - samples/sec: 3584.68 - lr: 0.000041 - momentum: 0.000000 2023-10-17 20:02:50,507 epoch 3 - iter 91/136 - loss 0.08313272 - time (sec): 10.01 - samples/sec: 3547.32 - lr: 0.000041 - momentum: 0.000000 2023-10-17 20:02:51,670 epoch 3 - iter 104/136 - loss 0.08415168 - time (sec): 11.17 - samples/sec: 3576.19 - lr: 0.000040 - momentum: 0.000000 2023-10-17 20:02:53,075 epoch 3 - iter 117/136 - loss 0.08122647 - time (sec): 12.58 - samples/sec: 3597.21 - lr: 0.000040 - momentum: 0.000000 2023-10-17 20:02:54,397 epoch 3 - iter 130/136 - loss 0.08038663 - time (sec): 13.90 - samples/sec: 3598.01 - lr: 0.000039 - momentum: 0.000000 2023-10-17 20:02:54,935 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:54,935 EPOCH 3 done: loss 0.0800 - lr: 0.000039 2023-10-17 20:02:56,467 DEV : loss 0.12283124774694443 - f1-score (micro avg) 0.7792 2023-10-17 20:02:56,473 saving best model 2023-10-17 20:02:56,981 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:02:58,359 epoch 4 - iter 13/136 - loss 0.04451944 - time (sec): 1.38 - samples/sec: 3361.74 - lr: 0.000038 - momentum: 0.000000 2023-10-17 20:03:00,015 epoch 4 - iter 26/136 - loss 0.03568214 - time (sec): 3.03 - samples/sec: 3180.10 - lr: 0.000038 - momentum: 0.000000 2023-10-17 20:03:01,549 epoch 4 - iter 39/136 - loss 0.04359458 - time (sec): 4.57 - samples/sec: 3335.54 - lr: 0.000037 - momentum: 0.000000 2023-10-17 20:03:02,824 epoch 4 - iter 52/136 - loss 0.04163316 - time (sec): 5.84 - samples/sec: 3370.12 - lr: 0.000037 - momentum: 0.000000 2023-10-17 20:03:04,009 epoch 4 - iter 65/136 - loss 0.04418803 - time (sec): 7.03 - samples/sec: 3383.09 - lr: 0.000036 - momentum: 0.000000 2023-10-17 20:03:05,626 epoch 4 - iter 78/136 - loss 0.04593159 - time (sec): 8.64 - samples/sec: 3444.03 - lr: 0.000036 - momentum: 0.000000 2023-10-17 20:03:07,242 epoch 4 - iter 91/136 - loss 0.04579649 - time (sec): 10.26 - samples/sec: 3411.15 - lr: 0.000035 - momentum: 0.000000 2023-10-17 20:03:08,671 epoch 4 - iter 104/136 - loss 0.04668489 - time (sec): 11.69 - samples/sec: 3408.71 - lr: 0.000035 - momentum: 0.000000 2023-10-17 20:03:09,931 epoch 4 - iter 117/136 - loss 0.04644160 - time (sec): 12.95 - samples/sec: 3470.46 - lr: 0.000034 - momentum: 0.000000 2023-10-17 20:03:11,202 epoch 4 - iter 130/136 - loss 0.04726019 - time (sec): 14.22 - samples/sec: 3452.42 - lr: 0.000034 - momentum: 0.000000 2023-10-17 20:03:11,829 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:03:11,830 EPOCH 4 done: loss 0.0486 - lr: 0.000034 2023-10-17 20:03:13,341 DEV : loss 0.10291425883769989 - f1-score (micro avg) 0.7812 2023-10-17 20:03:13,348 saving best model 2023-10-17 20:03:13,865 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:03:15,205 epoch 5 - iter 13/136 - loss 0.03258676 - time (sec): 1.33 - samples/sec: 3792.78 - lr: 0.000033 - momentum: 0.000000 2023-10-17 20:03:16,642 epoch 5 - iter 26/136 - loss 0.03067879 - time (sec): 2.77 - samples/sec: 3721.20 - lr: 0.000032 - momentum: 0.000000 2023-10-17 20:03:18,006 epoch 5 - iter 39/136 - loss 0.03276621 - time (sec): 4.13 - samples/sec: 3770.05 - lr: 0.000032 - momentum: 0.000000 2023-10-17 20:03:19,436 epoch 5 - iter 52/136 - loss 0.03765332 - time (sec): 5.56 - samples/sec: 3678.39 - lr: 0.000031 - momentum: 0.000000 2023-10-17 20:03:21,046 epoch 5 - iter 65/136 - loss 0.03607231 - time (sec): 7.18 - samples/sec: 3570.71 - lr: 0.000031 - momentum: 0.000000 2023-10-17 20:03:22,456 epoch 5 - iter 78/136 - loss 0.03339675 - time (sec): 8.59 - samples/sec: 3564.67 - lr: 0.000030 - momentum: 0.000000 2023-10-17 20:03:23,830 epoch 5 - iter 91/136 - loss 0.03650890 - time (sec): 9.96 - samples/sec: 3557.82 - lr: 0.000030 - momentum: 0.000000 2023-10-17 20:03:25,217 epoch 5 - iter 104/136 - loss 0.03442960 - time (sec): 11.35 - samples/sec: 3562.26 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:03:26,500 epoch 5 - iter 117/136 - loss 0.03459512 - time (sec): 12.63 - samples/sec: 3533.11 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:03:27,877 epoch 5 - iter 130/136 - loss 0.03444956 - time (sec): 14.01 - samples/sec: 3536.40 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:03:28,518 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:03:28,518 EPOCH 5 done: loss 0.0340 - lr: 0.000028 2023-10-17 20:03:29,983 DEV : loss 0.11607682704925537 - f1-score (micro avg) 0.7934 2023-10-17 20:03:29,989 saving best model 2023-10-17 20:03:30,726 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:03:31,877 epoch 6 - iter 13/136 - loss 0.01514382 - time (sec): 1.15 - samples/sec: 3999.40 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:03:33,319 epoch 6 - iter 26/136 - loss 0.02288618 - time (sec): 2.59 - samples/sec: 3691.16 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:03:34,661 epoch 6 - iter 39/136 - loss 0.02429339 - time (sec): 3.93 - samples/sec: 3697.51 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:03:36,064 epoch 6 - iter 52/136 - loss 0.02463788 - time (sec): 5.34 - samples/sec: 3650.79 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:03:37,426 epoch 6 - iter 65/136 - loss 0.02298716 - time (sec): 6.70 - samples/sec: 3683.08 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:03:38,843 epoch 6 - iter 78/136 - loss 0.02247348 - time (sec): 8.12 - samples/sec: 3754.68 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:03:40,196 epoch 6 - iter 91/136 - loss 0.02314909 - time (sec): 9.47 - samples/sec: 3748.25 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:03:41,642 epoch 6 - iter 104/136 - loss 0.02276842 - time (sec): 10.91 - samples/sec: 3682.51 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:03:43,003 epoch 6 - iter 117/136 - loss 0.02092841 - time (sec): 12.28 - samples/sec: 3662.64 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:03:44,335 epoch 6 - iter 130/136 - loss 0.02176745 - time (sec): 13.61 - samples/sec: 3636.94 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:03:44,970 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:03:44,970 EPOCH 6 done: loss 0.0221 - lr: 0.000023 2023-10-17 20:03:46,513 DEV : loss 0.1339295357465744 - f1-score (micro avg) 0.8155 2023-10-17 20:03:46,521 saving best model 2023-10-17 20:03:47,019 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:03:48,905 epoch 7 - iter 13/136 - loss 0.02470688 - time (sec): 1.88 - samples/sec: 3215.00 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:03:50,305 epoch 7 - iter 26/136 - loss 0.01909740 - time (sec): 3.28 - samples/sec: 3374.16 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:03:51,503 epoch 7 - iter 39/136 - loss 0.01699709 - time (sec): 4.48 - samples/sec: 3470.03 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:03:52,802 epoch 7 - iter 52/136 - loss 0.01571998 - time (sec): 5.78 - samples/sec: 3403.29 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:03:54,275 epoch 7 - iter 65/136 - loss 0.01520591 - time (sec): 7.25 - samples/sec: 3387.89 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:03:55,529 epoch 7 - iter 78/136 - loss 0.01504275 - time (sec): 8.51 - samples/sec: 3398.14 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:03:56,914 epoch 7 - iter 91/136 - loss 0.01386626 - time (sec): 9.89 - samples/sec: 3452.43 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:03:58,403 epoch 7 - iter 104/136 - loss 0.01333893 - time (sec): 11.38 - samples/sec: 3487.81 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:03:59,839 epoch 7 - iter 117/136 - loss 0.01428210 - time (sec): 12.82 - samples/sec: 3486.38 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:04:01,239 epoch 7 - iter 130/136 - loss 0.01389741 - time (sec): 14.22 - samples/sec: 3477.85 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:04:02,009 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:04:02,009 EPOCH 7 done: loss 0.0150 - lr: 0.000017 2023-10-17 20:04:03,491 DEV : loss 0.1483554244041443 - f1-score (micro avg) 0.8101 2023-10-17 20:04:03,497 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:04:04,888 epoch 8 - iter 13/136 - loss 0.01313850 - time (sec): 1.39 - samples/sec: 3546.31 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:04:06,855 epoch 8 - iter 26/136 - loss 0.00694009 - time (sec): 3.36 - samples/sec: 3079.49 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:04:08,190 epoch 8 - iter 39/136 - loss 0.00596193 - time (sec): 4.69 - samples/sec: 3339.91 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:04:09,645 epoch 8 - iter 52/136 - loss 0.00751512 - time (sec): 6.15 - samples/sec: 3288.52 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:04:11,049 epoch 8 - iter 65/136 - loss 0.00859132 - time (sec): 7.55 - samples/sec: 3348.21 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:04:12,587 epoch 8 - iter 78/136 - loss 0.00954904 - time (sec): 9.09 - samples/sec: 3331.65 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:04:14,359 epoch 8 - iter 91/136 - loss 0.01015131 - time (sec): 10.86 - samples/sec: 3336.20 - lr: 0.000013 - momentum: 0.000000 2023-10-17 20:04:15,628 epoch 8 - iter 104/136 - loss 0.01038419 - time (sec): 12.13 - samples/sec: 3364.49 - lr: 0.000013 - momentum: 0.000000 2023-10-17 20:04:16,838 epoch 8 - iter 117/136 - loss 0.01034903 - time (sec): 13.34 - samples/sec: 3327.07 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:04:18,376 epoch 8 - iter 130/136 - loss 0.01005288 - time (sec): 14.88 - samples/sec: 3340.23 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:04:19,027 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:04:19,027 EPOCH 8 done: loss 0.0103 - lr: 0.000012 2023-10-17 20:04:20,496 DEV : loss 0.15991544723510742 - f1-score (micro avg) 0.8199 2023-10-17 20:04:20,502 saving best model 2023-10-17 20:04:21,106 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:04:22,433 epoch 9 - iter 13/136 - loss 0.00224882 - time (sec): 1.32 - samples/sec: 3563.19 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:04:23,917 epoch 9 - iter 26/136 - loss 0.00183179 - time (sec): 2.81 - samples/sec: 3419.00 - lr: 0.000010 - momentum: 0.000000 2023-10-17 20:04:25,133 epoch 9 - iter 39/136 - loss 0.00194506 - time (sec): 4.03 - samples/sec: 3360.84 - lr: 0.000010 - momentum: 0.000000 2023-10-17 20:04:26,792 epoch 9 - iter 52/136 - loss 0.00308254 - time (sec): 5.68 - samples/sec: 3396.35 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:04:28,070 epoch 9 - iter 65/136 - loss 0.01003080 - time (sec): 6.96 - samples/sec: 3442.17 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:04:29,442 epoch 9 - iter 78/136 - loss 0.01082740 - time (sec): 8.33 - samples/sec: 3427.57 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:04:31,187 epoch 9 - iter 91/136 - loss 0.00961569 - time (sec): 10.08 - samples/sec: 3468.68 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:04:32,615 epoch 9 - iter 104/136 - loss 0.01034925 - time (sec): 11.51 - samples/sec: 3533.01 - lr: 0.000007 - momentum: 0.000000 2023-10-17 20:04:33,821 epoch 9 - iter 117/136 - loss 0.00979864 - time (sec): 12.71 - samples/sec: 3507.74 - lr: 0.000007 - momentum: 0.000000 2023-10-17 20:04:35,280 epoch 9 - iter 130/136 - loss 0.00932433 - time (sec): 14.17 - samples/sec: 3496.43 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:04:35,947 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:04:35,947 EPOCH 9 done: loss 0.0090 - lr: 0.000006 2023-10-17 20:04:37,520 DEV : loss 0.16742360591888428 - f1-score (micro avg) 0.8066 2023-10-17 20:04:37,530 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:04:39,101 epoch 10 - iter 13/136 - loss 0.00275634 - time (sec): 1.57 - samples/sec: 3043.58 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:04:40,427 epoch 10 - iter 26/136 - loss 0.00255019 - time (sec): 2.90 - samples/sec: 3219.14 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:04:41,754 epoch 10 - iter 39/136 - loss 0.00297794 - time (sec): 4.22 - samples/sec: 3334.06 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:04:43,057 epoch 10 - iter 52/136 - loss 0.00301243 - time (sec): 5.53 - samples/sec: 3515.85 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:04:44,654 epoch 10 - iter 65/136 - loss 0.00244713 - time (sec): 7.12 - samples/sec: 3482.34 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:04:46,218 epoch 10 - iter 78/136 - loss 0.00342059 - time (sec): 8.69 - samples/sec: 3477.13 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:04:47,740 epoch 10 - iter 91/136 - loss 0.00341841 - time (sec): 10.21 - samples/sec: 3447.75 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:04:49,055 epoch 10 - iter 104/136 - loss 0.00409207 - time (sec): 11.52 - samples/sec: 3433.47 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:04:50,709 epoch 10 - iter 117/136 - loss 0.00660157 - time (sec): 13.18 - samples/sec: 3456.80 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:04:51,941 epoch 10 - iter 130/136 - loss 0.00640003 - time (sec): 14.41 - samples/sec: 3456.15 - lr: 0.000000 - momentum: 0.000000 2023-10-17 20:04:52,544 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:04:52,544 EPOCH 10 done: loss 0.0063 - lr: 0.000000 2023-10-17 20:04:54,087 DEV : loss 0.1717977672815323 - f1-score (micro avg) 0.8051 2023-10-17 20:04:54,476 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:04:54,477 Loading model from best epoch ... 2023-10-17 20:04:56,043 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 20:04:58,126 Results: - F-score (micro) 0.7891 - F-score (macro) 0.7256 - Accuracy 0.6694 By class: precision recall f1-score support LOC 0.8171 0.8590 0.8375 312 PER 0.7258 0.8654 0.7895 208 ORG 0.5217 0.4364 0.4752 55 HumanProd 0.7143 0.9091 0.8000 22 micro avg 0.7569 0.8241 0.7891 597 macro avg 0.6947 0.7675 0.7256 597 weighted avg 0.7543 0.8241 0.7860 597 2023-10-17 20:04:58,126 ----------------------------------------------------------------------------------------------------