| 2023-10-13 09:14:37,108 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:37,109 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (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): 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=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-13 09:14:37,109 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:37,109 MultiCorpus: 1214 train + 266 dev + 251 test sentences | |
| - NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator | |
| 2023-10-13 09:14:37,109 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:37,109 Train: 1214 sentences | |
| 2023-10-13 09:14:37,109 (train_with_dev=False, train_with_test=False) | |
| 2023-10-13 09:14:37,109 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:37,109 Training Params: | |
| 2023-10-13 09:14:37,109 - learning_rate: "5e-05" | |
| 2023-10-13 09:14:37,109 - mini_batch_size: "4" | |
| 2023-10-13 09:14:37,109 - max_epochs: "10" | |
| 2023-10-13 09:14:37,109 - shuffle: "True" | |
| 2023-10-13 09:14:37,109 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:37,109 Plugins: | |
| 2023-10-13 09:14:37,110 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-13 09:14:37,110 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:37,110 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-13 09:14:37,110 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-13 09:14:37,110 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:37,110 Computation: | |
| 2023-10-13 09:14:37,110 - compute on device: cuda:0 | |
| 2023-10-13 09:14:37,110 - embedding storage: none | |
| 2023-10-13 09:14:37,110 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:37,110 Model training base path: "hmbench-ajmc/en-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-13 09:14:37,110 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:37,110 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:38,509 epoch 1 - iter 30/304 - loss 3.26533625 - time (sec): 1.40 - samples/sec: 2197.51 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 09:14:39,836 epoch 1 - iter 60/304 - loss 2.52396187 - time (sec): 2.72 - samples/sec: 2320.21 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 09:14:41,149 epoch 1 - iter 90/304 - loss 1.91225369 - time (sec): 4.04 - samples/sec: 2332.45 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 09:14:42,473 epoch 1 - iter 120/304 - loss 1.62800576 - time (sec): 5.36 - samples/sec: 2289.23 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 09:14:43,787 epoch 1 - iter 150/304 - loss 1.40639103 - time (sec): 6.68 - samples/sec: 2323.03 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 09:14:45,092 epoch 1 - iter 180/304 - loss 1.24597081 - time (sec): 7.98 - samples/sec: 2308.19 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 09:14:46,371 epoch 1 - iter 210/304 - loss 1.11152874 - time (sec): 9.26 - samples/sec: 2307.15 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-13 09:14:47,653 epoch 1 - iter 240/304 - loss 1.01243221 - time (sec): 10.54 - samples/sec: 2314.74 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-13 09:14:48,928 epoch 1 - iter 270/304 - loss 0.92964922 - time (sec): 11.82 - samples/sec: 2314.61 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-13 09:14:50,206 epoch 1 - iter 300/304 - loss 0.85739553 - time (sec): 13.10 - samples/sec: 2335.91 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-13 09:14:50,371 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:50,371 EPOCH 1 done: loss 0.8496 - lr: 0.000049 | |
| 2023-10-13 09:14:51,338 DEV : loss 0.201650470495224 - f1-score (micro avg) 0.6265 | |
| 2023-10-13 09:14:51,344 saving best model | |
| 2023-10-13 09:14:51,717 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:14:53,016 epoch 2 - iter 30/304 - loss 0.23233354 - time (sec): 1.30 - samples/sec: 2297.90 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-13 09:14:54,307 epoch 2 - iter 60/304 - loss 0.21378074 - time (sec): 2.59 - samples/sec: 2329.36 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-13 09:14:55,597 epoch 2 - iter 90/304 - loss 0.17494250 - time (sec): 3.88 - samples/sec: 2341.26 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-13 09:14:56,972 epoch 2 - iter 120/304 - loss 0.17535025 - time (sec): 5.25 - samples/sec: 2311.31 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-13 09:14:58,290 epoch 2 - iter 150/304 - loss 0.16287909 - time (sec): 6.57 - samples/sec: 2336.25 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-13 09:14:59,611 epoch 2 - iter 180/304 - loss 0.15875884 - time (sec): 7.89 - samples/sec: 2313.94 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-13 09:15:00,959 epoch 2 - iter 210/304 - loss 0.15246544 - time (sec): 9.24 - samples/sec: 2332.32 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-13 09:15:02,299 epoch 2 - iter 240/304 - loss 0.14503716 - time (sec): 10.58 - samples/sec: 2337.19 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-13 09:15:03,694 epoch 2 - iter 270/304 - loss 0.14762009 - time (sec): 11.97 - samples/sec: 2322.14 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-13 09:15:05,009 epoch 2 - iter 300/304 - loss 0.14227592 - time (sec): 13.29 - samples/sec: 2316.86 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-13 09:15:05,182 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:15:05,183 EPOCH 2 done: loss 0.1428 - lr: 0.000045 | |
| 2023-10-13 09:15:06,187 DEV : loss 0.15195277333259583 - f1-score (micro avg) 0.8133 | |
| 2023-10-13 09:15:06,194 saving best model | |
| 2023-10-13 09:15:06,662 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:15:08,063 epoch 3 - iter 30/304 - loss 0.05676444 - time (sec): 1.40 - samples/sec: 2173.93 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-13 09:15:09,462 epoch 3 - iter 60/304 - loss 0.06761027 - time (sec): 2.80 - samples/sec: 2176.58 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-13 09:15:10,961 epoch 3 - iter 90/304 - loss 0.06873990 - time (sec): 4.30 - samples/sec: 2184.72 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-13 09:15:12,476 epoch 3 - iter 120/304 - loss 0.06757685 - time (sec): 5.81 - samples/sec: 2118.45 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-13 09:15:13,823 epoch 3 - iter 150/304 - loss 0.06996653 - time (sec): 7.16 - samples/sec: 2139.39 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-13 09:15:15,154 epoch 3 - iter 180/304 - loss 0.07913479 - time (sec): 8.49 - samples/sec: 2141.81 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-13 09:15:16,481 epoch 3 - iter 210/304 - loss 0.08228924 - time (sec): 9.82 - samples/sec: 2174.93 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-13 09:15:17,803 epoch 3 - iter 240/304 - loss 0.08984783 - time (sec): 11.14 - samples/sec: 2186.18 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-13 09:15:19,160 epoch 3 - iter 270/304 - loss 0.08913348 - time (sec): 12.50 - samples/sec: 2221.62 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-13 09:15:20,497 epoch 3 - iter 300/304 - loss 0.09116194 - time (sec): 13.83 - samples/sec: 2208.35 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-13 09:15:20,681 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:15:20,681 EPOCH 3 done: loss 0.0903 - lr: 0.000039 | |
| 2023-10-13 09:15:21,660 DEV : loss 0.15804360806941986 - f1-score (micro avg) 0.8216 | |
| 2023-10-13 09:15:21,666 saving best model | |
| 2023-10-13 09:15:22,186 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:15:23,555 epoch 4 - iter 30/304 - loss 0.03604401 - time (sec): 1.37 - samples/sec: 2347.09 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-13 09:15:24,927 epoch 4 - iter 60/304 - loss 0.02876844 - time (sec): 2.74 - samples/sec: 2293.45 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-13 09:15:26,280 epoch 4 - iter 90/304 - loss 0.04362614 - time (sec): 4.09 - samples/sec: 2262.63 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-13 09:15:27,621 epoch 4 - iter 120/304 - loss 0.04360443 - time (sec): 5.43 - samples/sec: 2240.24 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-13 09:15:28,956 epoch 4 - iter 150/304 - loss 0.04145059 - time (sec): 6.77 - samples/sec: 2268.73 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-13 09:15:30,287 epoch 4 - iter 180/304 - loss 0.04960702 - time (sec): 8.10 - samples/sec: 2265.92 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-13 09:15:31,640 epoch 4 - iter 210/304 - loss 0.05541308 - time (sec): 9.45 - samples/sec: 2266.11 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-13 09:15:33,000 epoch 4 - iter 240/304 - loss 0.06095762 - time (sec): 10.81 - samples/sec: 2274.36 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-13 09:15:34,357 epoch 4 - iter 270/304 - loss 0.05985542 - time (sec): 12.17 - samples/sec: 2275.80 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-13 09:15:35,691 epoch 4 - iter 300/304 - loss 0.06489252 - time (sec): 13.50 - samples/sec: 2265.80 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-13 09:15:35,870 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:15:35,870 EPOCH 4 done: loss 0.0641 - lr: 0.000033 | |
| 2023-10-13 09:15:37,238 DEV : loss 0.2069637030363083 - f1-score (micro avg) 0.8019 | |
| 2023-10-13 09:15:37,247 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:15:38,839 epoch 5 - iter 30/304 - loss 0.04191437 - time (sec): 1.59 - samples/sec: 1998.89 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-13 09:15:40,396 epoch 5 - iter 60/304 - loss 0.03204806 - time (sec): 3.15 - samples/sec: 2031.74 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-13 09:15:41,713 epoch 5 - iter 90/304 - loss 0.03275413 - time (sec): 4.46 - samples/sec: 2113.80 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-13 09:15:42,991 epoch 5 - iter 120/304 - loss 0.04056152 - time (sec): 5.74 - samples/sec: 2171.53 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-13 09:15:44,285 epoch 5 - iter 150/304 - loss 0.05389375 - time (sec): 7.04 - samples/sec: 2205.77 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-13 09:15:45,574 epoch 5 - iter 180/304 - loss 0.05150614 - time (sec): 8.33 - samples/sec: 2232.06 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 09:15:46,848 epoch 5 - iter 210/304 - loss 0.05150225 - time (sec): 9.60 - samples/sec: 2242.98 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 09:15:48,151 epoch 5 - iter 240/304 - loss 0.05217181 - time (sec): 10.90 - samples/sec: 2259.05 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 09:15:49,483 epoch 5 - iter 270/304 - loss 0.05447614 - time (sec): 12.23 - samples/sec: 2256.83 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 09:15:50,806 epoch 5 - iter 300/304 - loss 0.05138325 - time (sec): 13.56 - samples/sec: 2261.82 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 09:15:50,979 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:15:50,979 EPOCH 5 done: loss 0.0516 - lr: 0.000028 | |
| 2023-10-13 09:15:51,943 DEV : loss 0.2098654955625534 - f1-score (micro avg) 0.8198 | |
| 2023-10-13 09:15:51,948 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:15:53,206 epoch 6 - iter 30/304 - loss 0.05555524 - time (sec): 1.26 - samples/sec: 2228.63 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 09:15:54,494 epoch 6 - iter 60/304 - loss 0.05040596 - time (sec): 2.54 - samples/sec: 2381.04 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 09:15:55,812 epoch 6 - iter 90/304 - loss 0.03898913 - time (sec): 3.86 - samples/sec: 2358.92 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 09:15:57,152 epoch 6 - iter 120/304 - loss 0.03712618 - time (sec): 5.20 - samples/sec: 2343.91 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 09:15:58,457 epoch 6 - iter 150/304 - loss 0.03224463 - time (sec): 6.51 - samples/sec: 2301.40 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 09:15:59,782 epoch 6 - iter 180/304 - loss 0.03203376 - time (sec): 7.83 - samples/sec: 2309.02 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 09:16:01,115 epoch 6 - iter 210/304 - loss 0.03430597 - time (sec): 9.17 - samples/sec: 2320.87 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 09:16:02,446 epoch 6 - iter 240/304 - loss 0.03929362 - time (sec): 10.50 - samples/sec: 2317.97 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 09:16:03,775 epoch 6 - iter 270/304 - loss 0.03687403 - time (sec): 11.83 - samples/sec: 2311.64 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 09:16:05,087 epoch 6 - iter 300/304 - loss 0.03657846 - time (sec): 13.14 - samples/sec: 2331.31 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 09:16:05,266 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:16:05,267 EPOCH 6 done: loss 0.0368 - lr: 0.000022 | |
| 2023-10-13 09:16:06,246 DEV : loss 0.22034451365470886 - f1-score (micro avg) 0.8221 | |
| 2023-10-13 09:16:06,252 saving best model | |
| 2023-10-13 09:16:06,730 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:16:08,099 epoch 7 - iter 30/304 - loss 0.02239979 - time (sec): 1.36 - samples/sec: 2260.37 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 09:16:09,399 epoch 7 - iter 60/304 - loss 0.03115877 - time (sec): 2.66 - samples/sec: 2298.72 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 09:16:10,685 epoch 7 - iter 90/304 - loss 0.03771206 - time (sec): 3.95 - samples/sec: 2299.27 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 09:16:12,011 epoch 7 - iter 120/304 - loss 0.03515986 - time (sec): 5.28 - samples/sec: 2373.43 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 09:16:13,437 epoch 7 - iter 150/304 - loss 0.03089837 - time (sec): 6.70 - samples/sec: 2309.39 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 09:16:14,917 epoch 7 - iter 180/304 - loss 0.02684988 - time (sec): 8.18 - samples/sec: 2276.56 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 09:16:16,275 epoch 7 - iter 210/304 - loss 0.02627693 - time (sec): 9.54 - samples/sec: 2278.53 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 09:16:17,630 epoch 7 - iter 240/304 - loss 0.03001494 - time (sec): 10.90 - samples/sec: 2303.15 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 09:16:18,969 epoch 7 - iter 270/304 - loss 0.02826276 - time (sec): 12.23 - samples/sec: 2273.72 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 09:16:20,296 epoch 7 - iter 300/304 - loss 0.02865291 - time (sec): 13.56 - samples/sec: 2264.87 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 09:16:20,474 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:16:20,474 EPOCH 7 done: loss 0.0288 - lr: 0.000017 | |
| 2023-10-13 09:16:21,466 DEV : loss 0.23426471650600433 - f1-score (micro avg) 0.8168 | |
| 2023-10-13 09:16:21,473 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:16:22,877 epoch 8 - iter 30/304 - loss 0.02224755 - time (sec): 1.40 - samples/sec: 2401.89 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 09:16:24,263 epoch 8 - iter 60/304 - loss 0.01525236 - time (sec): 2.79 - samples/sec: 2263.66 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 09:16:25,635 epoch 8 - iter 90/304 - loss 0.02329187 - time (sec): 4.16 - samples/sec: 2258.57 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 09:16:26,976 epoch 8 - iter 120/304 - loss 0.02334889 - time (sec): 5.50 - samples/sec: 2257.54 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 09:16:28,374 epoch 8 - iter 150/304 - loss 0.02386948 - time (sec): 6.90 - samples/sec: 2262.04 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 09:16:29,758 epoch 8 - iter 180/304 - loss 0.02048026 - time (sec): 8.28 - samples/sec: 2259.77 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 09:16:31,110 epoch 8 - iter 210/304 - loss 0.02097907 - time (sec): 9.64 - samples/sec: 2249.01 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 09:16:32,423 epoch 8 - iter 240/304 - loss 0.02088416 - time (sec): 10.95 - samples/sec: 2260.29 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 09:16:33,741 epoch 8 - iter 270/304 - loss 0.02000901 - time (sec): 12.27 - samples/sec: 2255.30 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 09:16:35,084 epoch 8 - iter 300/304 - loss 0.02079615 - time (sec): 13.61 - samples/sec: 2248.16 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 09:16:35,257 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:16:35,257 EPOCH 8 done: loss 0.0205 - lr: 0.000011 | |
| 2023-10-13 09:16:36,170 DEV : loss 0.2336961030960083 - f1-score (micro avg) 0.8088 | |
| 2023-10-13 09:16:36,176 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:16:37,480 epoch 9 - iter 30/304 - loss 0.03185151 - time (sec): 1.30 - samples/sec: 2118.20 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 09:16:38,805 epoch 9 - iter 60/304 - loss 0.01941022 - time (sec): 2.63 - samples/sec: 2248.26 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 09:16:40,114 epoch 9 - iter 90/304 - loss 0.02418827 - time (sec): 3.94 - samples/sec: 2338.22 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 09:16:41,423 epoch 9 - iter 120/304 - loss 0.02236864 - time (sec): 5.25 - samples/sec: 2360.29 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 09:16:42,747 epoch 9 - iter 150/304 - loss 0.01936117 - time (sec): 6.57 - samples/sec: 2338.84 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 09:16:44,042 epoch 9 - iter 180/304 - loss 0.02011720 - time (sec): 7.86 - samples/sec: 2336.05 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 09:16:45,349 epoch 9 - iter 210/304 - loss 0.01822278 - time (sec): 9.17 - samples/sec: 2312.70 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 09:16:46,676 epoch 9 - iter 240/304 - loss 0.01633974 - time (sec): 10.50 - samples/sec: 2343.24 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 09:16:47,986 epoch 9 - iter 270/304 - loss 0.01538783 - time (sec): 11.81 - samples/sec: 2337.67 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 09:16:49,306 epoch 9 - iter 300/304 - loss 0.01441047 - time (sec): 13.13 - samples/sec: 2332.01 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 09:16:49,476 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:16:49,476 EPOCH 9 done: loss 0.0142 - lr: 0.000006 | |
| 2023-10-13 09:16:50,451 DEV : loss 0.23067596554756165 - f1-score (micro avg) 0.8341 | |
| 2023-10-13 09:16:50,457 saving best model | |
| 2023-10-13 09:16:50,946 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:16:52,223 epoch 10 - iter 30/304 - loss 0.00042546 - time (sec): 1.28 - samples/sec: 2287.84 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 09:16:53,505 epoch 10 - iter 60/304 - loss 0.00653303 - time (sec): 2.56 - samples/sec: 2398.84 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 09:16:54,777 epoch 10 - iter 90/304 - loss 0.00676046 - time (sec): 3.83 - samples/sec: 2481.73 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 09:16:56,053 epoch 10 - iter 120/304 - loss 0.01082980 - time (sec): 5.11 - samples/sec: 2451.59 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 09:16:57,352 epoch 10 - iter 150/304 - loss 0.01160425 - time (sec): 6.40 - samples/sec: 2397.63 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 09:16:58,713 epoch 10 - iter 180/304 - loss 0.00964747 - time (sec): 7.76 - samples/sec: 2406.44 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 09:17:00,034 epoch 10 - iter 210/304 - loss 0.01238947 - time (sec): 9.09 - samples/sec: 2398.10 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 09:17:01,355 epoch 10 - iter 240/304 - loss 0.01215384 - time (sec): 10.41 - samples/sec: 2363.73 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 09:17:02,681 epoch 10 - iter 270/304 - loss 0.01161439 - time (sec): 11.73 - samples/sec: 2360.65 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 09:17:04,067 epoch 10 - iter 300/304 - loss 0.01123309 - time (sec): 13.12 - samples/sec: 2346.33 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-13 09:17:04,242 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:17:04,242 EPOCH 10 done: loss 0.0112 - lr: 0.000000 | |
| 2023-10-13 09:17:05,216 DEV : loss 0.22761297225952148 - f1-score (micro avg) 0.8253 | |
| 2023-10-13 09:17:05,622 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:17:05,624 Loading model from best epoch ... | |
| 2023-10-13 09:17:07,074 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object | |
| 2023-10-13 09:17:08,140 | |
| Results: | |
| - F-score (micro) 0.7847 | |
| - F-score (macro) 0.6101 | |
| - Accuracy 0.6556 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.7278 0.8146 0.7687 151 | |
| pers 0.7607 0.9271 0.8357 96 | |
| work 0.7034 0.8737 0.7793 95 | |
| loc 0.6667 0.6667 0.6667 3 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.7262 0.8534 0.7847 348 | |
| macro avg 0.5717 0.6564 0.6101 348 | |
| weighted avg 0.7234 0.8534 0.7826 348 | |
| 2023-10-13 09:17:08,140 ---------------------------------------------------------------------------------------------------- | |