2023-10-25 21:28:09,101 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:09,102 Model: "SequenceTagger( (embeddings): TransformerWordEmbeddings( (model): BertModel( (embeddings): BertEmbeddings( (word_embeddings): Embedding(64001, 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): BertEncoder( (layer): ModuleList( (0-11): 12 x BertLayer( (attention): BertAttention( (self): BertSelfAttention( (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): BertSelfOutput( (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): BertIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): BertOutput( (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) ) ) ) ) (pooler): BertPooler( (dense): Linear(in_features=768, out_features=768, bias=True) (activation): Tanh() ) ) ) (locked_dropout): LockedDropout(p=0.5) (linear): Linear(in_features=768, out_features=17, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-25 21:28:09,102 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:09,102 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 2023-10-25 21:28:09,102 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:09,103 Train: 1085 sentences 2023-10-25 21:28:09,103 (train_with_dev=False, train_with_test=False) 2023-10-25 21:28:09,103 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:09,103 Training Params: 2023-10-25 21:28:09,103 - learning_rate: "5e-05" 2023-10-25 21:28:09,103 - mini_batch_size: "4" 2023-10-25 21:28:09,103 - max_epochs: "10" 2023-10-25 21:28:09,103 - shuffle: "True" 2023-10-25 21:28:09,103 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:09,103 Plugins: 2023-10-25 21:28:09,103 - TensorboardLogger 2023-10-25 21:28:09,103 - LinearScheduler | warmup_fraction: '0.1' 2023-10-25 21:28:09,103 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:09,103 Final evaluation on model from best epoch (best-model.pt) 2023-10-25 21:28:09,103 - metric: "('micro avg', 'f1-score')" 2023-10-25 21:28:09,103 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:09,103 Computation: 2023-10-25 21:28:09,103 - compute on device: cuda:0 2023-10-25 21:28:09,103 - embedding storage: none 2023-10-25 21:28:09,103 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:09,103 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" 2023-10-25 21:28:09,103 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:09,103 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:09,103 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-25 21:28:10,568 epoch 1 - iter 27/272 - loss 2.78765850 - time (sec): 1.46 - samples/sec: 3749.30 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:28:12,027 epoch 1 - iter 54/272 - loss 2.00101582 - time (sec): 2.92 - samples/sec: 3713.94 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:28:13,451 epoch 1 - iter 81/272 - loss 1.57394260 - time (sec): 4.35 - samples/sec: 3560.78 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:28:14,978 epoch 1 - iter 108/272 - loss 1.25429045 - time (sec): 5.87 - samples/sec: 3555.28 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:28:16,446 epoch 1 - iter 135/272 - loss 1.07013551 - time (sec): 7.34 - samples/sec: 3469.41 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:28:17,961 epoch 1 - iter 162/272 - loss 0.92511254 - time (sec): 8.86 - samples/sec: 3510.43 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:28:19,538 epoch 1 - iter 189/272 - loss 0.82909206 - time (sec): 10.43 - samples/sec: 3458.10 - lr: 0.000035 - momentum: 0.000000 2023-10-25 21:28:21,053 epoch 1 - iter 216/272 - loss 0.74558155 - time (sec): 11.95 - samples/sec: 3467.28 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:28:22,540 epoch 1 - iter 243/272 - loss 0.68899771 - time (sec): 13.44 - samples/sec: 3437.71 - lr: 0.000044 - momentum: 0.000000 2023-10-25 21:28:24,103 epoch 1 - iter 270/272 - loss 0.64040727 - time (sec): 15.00 - samples/sec: 3450.74 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:28:24,209 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:24,209 EPOCH 1 done: loss 0.6380 - lr: 0.000049 2023-10-25 21:28:24,928 DEV : loss 0.14035949110984802 - f1-score (micro avg) 0.6881 2023-10-25 21:28:24,934 saving best model 2023-10-25 21:28:25,364 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:26,882 epoch 2 - iter 27/272 - loss 0.09840230 - time (sec): 1.52 - samples/sec: 3106.26 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:28:28,448 epoch 2 - iter 54/272 - loss 0.09235375 - time (sec): 3.08 - samples/sec: 3434.25 - lr: 0.000049 - momentum: 0.000000 2023-10-25 21:28:30,007 epoch 2 - iter 81/272 - loss 0.11428755 - time (sec): 4.64 - samples/sec: 3233.28 - lr: 0.000048 - momentum: 0.000000 2023-10-25 21:28:31,513 epoch 2 - iter 108/272 - loss 0.11632033 - time (sec): 6.15 - samples/sec: 3451.06 - lr: 0.000048 - momentum: 0.000000 2023-10-25 21:28:33,039 epoch 2 - iter 135/272 - loss 0.11619477 - time (sec): 7.67 - samples/sec: 3453.70 - lr: 0.000047 - momentum: 0.000000 2023-10-25 21:28:34,571 epoch 2 - iter 162/272 - loss 0.11865776 - time (sec): 9.21 - samples/sec: 3407.72 - lr: 0.000047 - momentum: 0.000000 2023-10-25 21:28:36,059 epoch 2 - iter 189/272 - loss 0.11920523 - time (sec): 10.69 - samples/sec: 3470.34 - lr: 0.000046 - momentum: 0.000000 2023-10-25 21:28:37,574 epoch 2 - iter 216/272 - loss 0.11666654 - time (sec): 12.21 - samples/sec: 3540.98 - lr: 0.000046 - momentum: 0.000000 2023-10-25 21:28:39,053 epoch 2 - iter 243/272 - loss 0.11787206 - time (sec): 13.69 - samples/sec: 3477.79 - lr: 0.000045 - momentum: 0.000000 2023-10-25 21:28:40,560 epoch 2 - iter 270/272 - loss 0.12009223 - time (sec): 15.19 - samples/sec: 3412.65 - lr: 0.000045 - momentum: 0.000000 2023-10-25 21:28:40,657 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:40,657 EPOCH 2 done: loss 0.1202 - lr: 0.000045 2023-10-25 21:28:41,905 DEV : loss 0.12892909348011017 - f1-score (micro avg) 0.7395 2023-10-25 21:28:41,911 saving best model 2023-10-25 21:28:42,606 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:44,437 epoch 3 - iter 27/272 - loss 0.09342546 - time (sec): 1.82 - samples/sec: 2742.45 - lr: 0.000044 - momentum: 0.000000 2023-10-25 21:28:45,908 epoch 3 - iter 54/272 - loss 0.07117048 - time (sec): 3.29 - samples/sec: 3278.77 - lr: 0.000043 - momentum: 0.000000 2023-10-25 21:28:47,432 epoch 3 - iter 81/272 - loss 0.06750136 - time (sec): 4.81 - samples/sec: 3238.86 - lr: 0.000043 - momentum: 0.000000 2023-10-25 21:28:48,965 epoch 3 - iter 108/272 - loss 0.06927074 - time (sec): 6.34 - samples/sec: 3317.73 - lr: 0.000042 - momentum: 0.000000 2023-10-25 21:28:50,533 epoch 3 - iter 135/272 - loss 0.06639235 - time (sec): 7.91 - samples/sec: 3380.15 - lr: 0.000042 - momentum: 0.000000 2023-10-25 21:28:52,011 epoch 3 - iter 162/272 - loss 0.06610577 - time (sec): 9.39 - samples/sec: 3350.69 - lr: 0.000041 - momentum: 0.000000 2023-10-25 21:28:53,559 epoch 3 - iter 189/272 - loss 0.07007724 - time (sec): 10.94 - samples/sec: 3314.61 - lr: 0.000041 - momentum: 0.000000 2023-10-25 21:28:55,123 epoch 3 - iter 216/272 - loss 0.06922837 - time (sec): 12.50 - samples/sec: 3315.90 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:28:56,720 epoch 3 - iter 243/272 - loss 0.06963662 - time (sec): 14.10 - samples/sec: 3284.26 - lr: 0.000040 - momentum: 0.000000 2023-10-25 21:28:58,265 epoch 3 - iter 270/272 - loss 0.06919947 - time (sec): 15.64 - samples/sec: 3310.51 - lr: 0.000039 - momentum: 0.000000 2023-10-25 21:28:58,371 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:28:58,371 EPOCH 3 done: loss 0.0690 - lr: 0.000039 2023-10-25 21:28:59,614 DEV : loss 0.1450655460357666 - f1-score (micro avg) 0.7698 2023-10-25 21:28:59,620 saving best model 2023-10-25 21:29:00,271 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:29:01,797 epoch 4 - iter 27/272 - loss 0.03839164 - time (sec): 1.52 - samples/sec: 3389.43 - lr: 0.000038 - momentum: 0.000000 2023-10-25 21:29:03,246 epoch 4 - iter 54/272 - loss 0.05836842 - time (sec): 2.97 - samples/sec: 3375.16 - lr: 0.000038 - momentum: 0.000000 2023-10-25 21:29:04,837 epoch 4 - iter 81/272 - loss 0.05467419 - time (sec): 4.56 - samples/sec: 3543.96 - lr: 0.000037 - momentum: 0.000000 2023-10-25 21:29:06,369 epoch 4 - iter 108/272 - loss 0.05545031 - time (sec): 6.09 - samples/sec: 3456.12 - lr: 0.000037 - momentum: 0.000000 2023-10-25 21:29:07,934 epoch 4 - iter 135/272 - loss 0.05172334 - time (sec): 7.66 - samples/sec: 3437.62 - lr: 0.000036 - momentum: 0.000000 2023-10-25 21:29:09,467 epoch 4 - iter 162/272 - loss 0.05002860 - time (sec): 9.19 - samples/sec: 3467.60 - lr: 0.000036 - momentum: 0.000000 2023-10-25 21:29:10,944 epoch 4 - iter 189/272 - loss 0.04822871 - time (sec): 10.67 - samples/sec: 3465.66 - lr: 0.000035 - momentum: 0.000000 2023-10-25 21:29:12,476 epoch 4 - iter 216/272 - loss 0.04524283 - time (sec): 12.20 - samples/sec: 3457.22 - lr: 0.000034 - momentum: 0.000000 2023-10-25 21:29:13,983 epoch 4 - iter 243/272 - loss 0.04533348 - time (sec): 13.71 - samples/sec: 3443.64 - lr: 0.000034 - momentum: 0.000000 2023-10-25 21:29:15,536 epoch 4 - iter 270/272 - loss 0.04712815 - time (sec): 15.26 - samples/sec: 3395.72 - lr: 0.000033 - momentum: 0.000000 2023-10-25 21:29:15,635 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:29:15,636 EPOCH 4 done: loss 0.0470 - lr: 0.000033 2023-10-25 21:29:16,808 DEV : loss 0.14436790347099304 - f1-score (micro avg) 0.7925 2023-10-25 21:29:16,814 saving best model 2023-10-25 21:29:17,460 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:29:19,028 epoch 5 - iter 27/272 - loss 0.02507648 - time (sec): 1.56 - samples/sec: 3238.49 - lr: 0.000033 - momentum: 0.000000 2023-10-25 21:29:20,566 epoch 5 - iter 54/272 - loss 0.03155307 - time (sec): 3.10 - samples/sec: 3166.66 - lr: 0.000032 - momentum: 0.000000 2023-10-25 21:29:22,132 epoch 5 - iter 81/272 - loss 0.02739434 - time (sec): 4.67 - samples/sec: 3166.84 - lr: 0.000032 - momentum: 0.000000 2023-10-25 21:29:23,726 epoch 5 - iter 108/272 - loss 0.02941651 - time (sec): 6.26 - samples/sec: 3191.64 - lr: 0.000031 - momentum: 0.000000 2023-10-25 21:29:25,199 epoch 5 - iter 135/272 - loss 0.02739614 - time (sec): 7.74 - samples/sec: 3135.22 - lr: 0.000031 - momentum: 0.000000 2023-10-25 21:29:26,698 epoch 5 - iter 162/272 - loss 0.03066702 - time (sec): 9.23 - samples/sec: 3237.55 - lr: 0.000030 - momentum: 0.000000 2023-10-25 21:29:28,219 epoch 5 - iter 189/272 - loss 0.03167286 - time (sec): 10.76 - samples/sec: 3268.30 - lr: 0.000029 - momentum: 0.000000 2023-10-25 21:29:29,737 epoch 5 - iter 216/272 - loss 0.03130840 - time (sec): 12.27 - samples/sec: 3274.44 - lr: 0.000029 - momentum: 0.000000 2023-10-25 21:29:31,274 epoch 5 - iter 243/272 - loss 0.03201179 - time (sec): 13.81 - samples/sec: 3346.11 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:29:32,794 epoch 5 - iter 270/272 - loss 0.03426102 - time (sec): 15.33 - samples/sec: 3380.00 - lr: 0.000028 - momentum: 0.000000 2023-10-25 21:29:32,902 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:29:32,902 EPOCH 5 done: loss 0.0342 - lr: 0.000028 2023-10-25 21:29:34,118 DEV : loss 0.1501101553440094 - f1-score (micro avg) 0.7964 2023-10-25 21:29:34,124 saving best model 2023-10-25 21:29:34,805 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:29:36,368 epoch 6 - iter 27/272 - loss 0.01909779 - time (sec): 1.56 - samples/sec: 3493.85 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:29:37,843 epoch 6 - iter 54/272 - loss 0.01727977 - time (sec): 3.04 - samples/sec: 3533.53 - lr: 0.000027 - momentum: 0.000000 2023-10-25 21:29:39,322 epoch 6 - iter 81/272 - loss 0.01553708 - time (sec): 4.51 - samples/sec: 3427.14 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:29:40,841 epoch 6 - iter 108/272 - loss 0.01998247 - time (sec): 6.03 - samples/sec: 3439.13 - lr: 0.000026 - momentum: 0.000000 2023-10-25 21:29:42,736 epoch 6 - iter 135/272 - loss 0.01744104 - time (sec): 7.93 - samples/sec: 3234.22 - lr: 0.000025 - momentum: 0.000000 2023-10-25 21:29:44,174 epoch 6 - iter 162/272 - loss 0.01847424 - time (sec): 9.37 - samples/sec: 3320.47 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:29:45,642 epoch 6 - iter 189/272 - loss 0.01935988 - time (sec): 10.83 - samples/sec: 3383.82 - lr: 0.000024 - momentum: 0.000000 2023-10-25 21:29:47,102 epoch 6 - iter 216/272 - loss 0.01931684 - time (sec): 12.29 - samples/sec: 3326.04 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:29:48,602 epoch 6 - iter 243/272 - loss 0.01934257 - time (sec): 13.79 - samples/sec: 3372.67 - lr: 0.000023 - momentum: 0.000000 2023-10-25 21:29:50,066 epoch 6 - iter 270/272 - loss 0.02070140 - time (sec): 15.26 - samples/sec: 3379.89 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:29:50,171 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:29:50,172 EPOCH 6 done: loss 0.0205 - lr: 0.000022 2023-10-25 21:29:51,433 DEV : loss 0.165546253323555 - f1-score (micro avg) 0.8066 2023-10-25 21:29:51,440 saving best model 2023-10-25 21:29:54,714 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:29:56,247 epoch 7 - iter 27/272 - loss 0.00697830 - time (sec): 1.53 - samples/sec: 3623.25 - lr: 0.000022 - momentum: 0.000000 2023-10-25 21:29:57,777 epoch 7 - iter 54/272 - loss 0.00914022 - time (sec): 3.06 - samples/sec: 3451.66 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:29:59,278 epoch 7 - iter 81/272 - loss 0.00936467 - time (sec): 4.56 - samples/sec: 3464.62 - lr: 0.000021 - momentum: 0.000000 2023-10-25 21:30:00,780 epoch 7 - iter 108/272 - loss 0.00900487 - time (sec): 6.06 - samples/sec: 3543.39 - lr: 0.000020 - momentum: 0.000000 2023-10-25 21:30:02,352 epoch 7 - iter 135/272 - loss 0.01188333 - time (sec): 7.64 - samples/sec: 3443.14 - lr: 0.000019 - momentum: 0.000000 2023-10-25 21:30:03,855 epoch 7 - iter 162/272 - loss 0.01348404 - time (sec): 9.14 - samples/sec: 3432.95 - lr: 0.000019 - momentum: 0.000000 2023-10-25 21:30:05,413 epoch 7 - iter 189/272 - loss 0.01577447 - time (sec): 10.70 - samples/sec: 3464.67 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:30:06,948 epoch 7 - iter 216/272 - loss 0.01509764 - time (sec): 12.23 - samples/sec: 3455.51 - lr: 0.000018 - momentum: 0.000000 2023-10-25 21:30:08,406 epoch 7 - iter 243/272 - loss 0.01702924 - time (sec): 13.69 - samples/sec: 3423.92 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:30:09,929 epoch 7 - iter 270/272 - loss 0.01657090 - time (sec): 15.21 - samples/sec: 3393.89 - lr: 0.000017 - momentum: 0.000000 2023-10-25 21:30:10,042 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:30:10,042 EPOCH 7 done: loss 0.0165 - lr: 0.000017 2023-10-25 21:30:11,380 DEV : loss 0.18749994039535522 - f1-score (micro avg) 0.8036 2023-10-25 21:30:11,386 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:30:12,890 epoch 8 - iter 27/272 - loss 0.01739788 - time (sec): 1.50 - samples/sec: 4044.12 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:30:14,357 epoch 8 - iter 54/272 - loss 0.01871958 - time (sec): 2.97 - samples/sec: 3716.48 - lr: 0.000016 - momentum: 0.000000 2023-10-25 21:30:15,894 epoch 8 - iter 81/272 - loss 0.01462857 - time (sec): 4.51 - samples/sec: 3692.83 - lr: 0.000015 - momentum: 0.000000 2023-10-25 21:30:17,387 epoch 8 - iter 108/272 - loss 0.01387024 - time (sec): 6.00 - samples/sec: 3631.22 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:30:18,930 epoch 8 - iter 135/272 - loss 0.01409383 - time (sec): 7.54 - samples/sec: 3613.71 - lr: 0.000014 - momentum: 0.000000 2023-10-25 21:30:20,417 epoch 8 - iter 162/272 - loss 0.01425509 - time (sec): 9.03 - samples/sec: 3556.26 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:30:21,950 epoch 8 - iter 189/272 - loss 0.01373470 - time (sec): 10.56 - samples/sec: 3529.86 - lr: 0.000013 - momentum: 0.000000 2023-10-25 21:30:23,498 epoch 8 - iter 216/272 - loss 0.01224350 - time (sec): 12.11 - samples/sec: 3512.96 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:30:25,052 epoch 8 - iter 243/272 - loss 0.01131915 - time (sec): 13.67 - samples/sec: 3470.03 - lr: 0.000012 - momentum: 0.000000 2023-10-25 21:30:26,502 epoch 8 - iter 270/272 - loss 0.01157460 - time (sec): 15.12 - samples/sec: 3431.48 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:30:26,605 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:30:26,605 EPOCH 8 done: loss 0.0115 - lr: 0.000011 2023-10-25 21:30:27,835 DEV : loss 0.17698289453983307 - f1-score (micro avg) 0.8266 2023-10-25 21:30:27,841 saving best model 2023-10-25 21:30:28,465 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:30:30,036 epoch 9 - iter 27/272 - loss 0.00058588 - time (sec): 1.57 - samples/sec: 3749.18 - lr: 0.000011 - momentum: 0.000000 2023-10-25 21:30:31,531 epoch 9 - iter 54/272 - loss 0.00623629 - time (sec): 3.06 - samples/sec: 3569.82 - lr: 0.000010 - momentum: 0.000000 2023-10-25 21:30:33,037 epoch 9 - iter 81/272 - loss 0.00539403 - time (sec): 4.57 - samples/sec: 3400.69 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:30:34,548 epoch 9 - iter 108/272 - loss 0.00741251 - time (sec): 6.08 - samples/sec: 3341.22 - lr: 0.000009 - momentum: 0.000000 2023-10-25 21:30:36,038 epoch 9 - iter 135/272 - loss 0.00926729 - time (sec): 7.57 - samples/sec: 3391.09 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:30:37,554 epoch 9 - iter 162/272 - loss 0.00852067 - time (sec): 9.09 - samples/sec: 3414.77 - lr: 0.000008 - momentum: 0.000000 2023-10-25 21:30:39,074 epoch 9 - iter 189/272 - loss 0.00788998 - time (sec): 10.61 - samples/sec: 3466.92 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:30:40,588 epoch 9 - iter 216/272 - loss 0.00711701 - time (sec): 12.12 - samples/sec: 3418.25 - lr: 0.000007 - momentum: 0.000000 2023-10-25 21:30:42,061 epoch 9 - iter 243/272 - loss 0.00659543 - time (sec): 13.59 - samples/sec: 3439.13 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:30:43,592 epoch 9 - iter 270/272 - loss 0.00744715 - time (sec): 15.13 - samples/sec: 3427.52 - lr: 0.000006 - momentum: 0.000000 2023-10-25 21:30:43,695 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:30:43,696 EPOCH 9 done: loss 0.0074 - lr: 0.000006 2023-10-25 21:30:45,471 DEV : loss 0.1907862275838852 - f1-score (micro avg) 0.822 2023-10-25 21:30:45,478 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:30:46,944 epoch 10 - iter 27/272 - loss 0.00585267 - time (sec): 1.47 - samples/sec: 3723.63 - lr: 0.000005 - momentum: 0.000000 2023-10-25 21:30:48,393 epoch 10 - iter 54/272 - loss 0.00495959 - time (sec): 2.91 - samples/sec: 3508.61 - lr: 0.000004 - momentum: 0.000000 2023-10-25 21:30:49,885 epoch 10 - iter 81/272 - loss 0.00450007 - time (sec): 4.41 - samples/sec: 3559.91 - lr: 0.000004 - momentum: 0.000000 2023-10-25 21:30:51,343 epoch 10 - iter 108/272 - loss 0.00425761 - time (sec): 5.86 - samples/sec: 3633.67 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:30:52,829 epoch 10 - iter 135/272 - loss 0.00470265 - time (sec): 7.35 - samples/sec: 3550.95 - lr: 0.000003 - momentum: 0.000000 2023-10-25 21:30:54,275 epoch 10 - iter 162/272 - loss 0.00419178 - time (sec): 8.80 - samples/sec: 3540.66 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:30:55,718 epoch 10 - iter 189/272 - loss 0.00450719 - time (sec): 10.24 - samples/sec: 3586.16 - lr: 0.000002 - momentum: 0.000000 2023-10-25 21:30:57,167 epoch 10 - iter 216/272 - loss 0.00419873 - time (sec): 11.69 - samples/sec: 3564.16 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:30:58,628 epoch 10 - iter 243/272 - loss 0.00473732 - time (sec): 13.15 - samples/sec: 3537.51 - lr: 0.000001 - momentum: 0.000000 2023-10-25 21:31:00,035 epoch 10 - iter 270/272 - loss 0.00519675 - time (sec): 14.56 - samples/sec: 3555.18 - lr: 0.000000 - momentum: 0.000000 2023-10-25 21:31:00,128 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:00,128 EPOCH 10 done: loss 0.0052 - lr: 0.000000 2023-10-25 21:31:01,313 DEV : loss 0.19103476405143738 - f1-score (micro avg) 0.8205 2023-10-25 21:31:01,785 ---------------------------------------------------------------------------------------------------- 2023-10-25 21:31:01,786 Loading model from best epoch ... 2023-10-25 21:31:03,678 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 2023-10-25 21:31:05,500 Results: - F-score (micro) 0.7823 - F-score (macro) 0.7373 - Accuracy 0.664 By class: precision recall f1-score support LOC 0.8000 0.8718 0.8344 312 PER 0.6947 0.8750 0.7745 208 ORG 0.4545 0.3636 0.4040 55 HumanProd 0.8800 1.0000 0.9362 22 micro avg 0.7392 0.8308 0.7823 597 macro avg 0.7073 0.7776 0.7373 597 weighted avg 0.7344 0.8308 0.7776 597 2023-10-25 21:31:05,500 ----------------------------------------------------------------------------------------------------