| 2023-10-13 10:32:44,163 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:44,164 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 10:32:44,164 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:44,164 MultiCorpus: 966 train + 219 dev + 204 test sentences | |
| - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator | |
| 2023-10-13 10:32:44,164 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:44,164 Train: 966 sentences | |
| 2023-10-13 10:32:44,164 (train_with_dev=False, train_with_test=False) | |
| 2023-10-13 10:32:44,164 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:44,164 Training Params: | |
| 2023-10-13 10:32:44,164 - learning_rate: "5e-05" | |
| 2023-10-13 10:32:44,164 - mini_batch_size: "4" | |
| 2023-10-13 10:32:44,164 - max_epochs: "10" | |
| 2023-10-13 10:32:44,164 - shuffle: "True" | |
| 2023-10-13 10:32:44,164 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:44,164 Plugins: | |
| 2023-10-13 10:32:44,165 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-13 10:32:44,165 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:44,165 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-13 10:32:44,165 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-13 10:32:44,165 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:44,165 Computation: | |
| 2023-10-13 10:32:44,165 - compute on device: cuda:0 | |
| 2023-10-13 10:32:44,165 - embedding storage: none | |
| 2023-10-13 10:32:44,165 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:44,165 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-13 10:32:44,165 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:44,165 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:45,262 epoch 1 - iter 24/242 - loss 3.25335328 - time (sec): 1.10 - samples/sec: 2127.85 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 10:32:46,382 epoch 1 - iter 48/242 - loss 2.59177701 - time (sec): 2.22 - samples/sec: 2263.16 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 10:32:47,458 epoch 1 - iter 72/242 - loss 1.97195814 - time (sec): 3.29 - samples/sec: 2324.93 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 10:32:48,517 epoch 1 - iter 96/242 - loss 1.65768289 - time (sec): 4.35 - samples/sec: 2312.60 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 10:32:49,556 epoch 1 - iter 120/242 - loss 1.48583439 - time (sec): 5.39 - samples/sec: 2266.92 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 10:32:50,650 epoch 1 - iter 144/242 - loss 1.32044676 - time (sec): 6.48 - samples/sec: 2292.38 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 10:32:51,703 epoch 1 - iter 168/242 - loss 1.20028931 - time (sec): 7.54 - samples/sec: 2295.04 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-13 10:32:52,776 epoch 1 - iter 192/242 - loss 1.09544768 - time (sec): 8.61 - samples/sec: 2310.77 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-13 10:32:53,819 epoch 1 - iter 216/242 - loss 1.00812496 - time (sec): 9.65 - samples/sec: 2298.61 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-13 10:32:54,860 epoch 1 - iter 240/242 - loss 0.93777178 - time (sec): 10.69 - samples/sec: 2296.00 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-13 10:32:54,945 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:54,945 EPOCH 1 done: loss 0.9330 - lr: 0.000049 | |
| 2023-10-13 10:32:55,762 DEV : loss 0.2682833671569824 - f1-score (micro avg) 0.5051 | |
| 2023-10-13 10:32:55,767 saving best model | |
| 2023-10-13 10:32:56,104 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:32:57,193 epoch 2 - iter 24/242 - loss 0.24233411 - time (sec): 1.09 - samples/sec: 2243.39 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-13 10:32:58,283 epoch 2 - iter 48/242 - loss 0.27352313 - time (sec): 2.18 - samples/sec: 2189.77 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-13 10:32:59,390 epoch 2 - iter 72/242 - loss 0.24957463 - time (sec): 3.29 - samples/sec: 2247.67 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-13 10:33:00,494 epoch 2 - iter 96/242 - loss 0.23339870 - time (sec): 4.39 - samples/sec: 2265.45 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-13 10:33:01,581 epoch 2 - iter 120/242 - loss 0.22873479 - time (sec): 5.48 - samples/sec: 2252.38 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-13 10:33:02,678 epoch 2 - iter 144/242 - loss 0.22253268 - time (sec): 6.57 - samples/sec: 2211.42 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-13 10:33:03,862 epoch 2 - iter 168/242 - loss 0.21054077 - time (sec): 7.76 - samples/sec: 2198.09 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-13 10:33:05,229 epoch 2 - iter 192/242 - loss 0.20798788 - time (sec): 9.12 - samples/sec: 2150.53 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-13 10:33:06,579 epoch 2 - iter 216/242 - loss 0.20068830 - time (sec): 10.47 - samples/sec: 2148.17 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-13 10:33:07,843 epoch 2 - iter 240/242 - loss 0.19864246 - time (sec): 11.74 - samples/sec: 2098.23 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-13 10:33:07,933 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:33:07,933 EPOCH 2 done: loss 0.1980 - lr: 0.000045 | |
| 2023-10-13 10:33:08,766 DEV : loss 0.1464683562517166 - f1-score (micro avg) 0.7949 | |
| 2023-10-13 10:33:08,770 saving best model | |
| 2023-10-13 10:33:09,214 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:33:10,364 epoch 3 - iter 24/242 - loss 0.16091341 - time (sec): 1.14 - samples/sec: 2146.61 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-13 10:33:11,455 epoch 3 - iter 48/242 - loss 0.13751572 - time (sec): 2.23 - samples/sec: 2236.48 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-13 10:33:12,584 epoch 3 - iter 72/242 - loss 0.11751205 - time (sec): 3.36 - samples/sec: 2201.37 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-13 10:33:13,647 epoch 3 - iter 96/242 - loss 0.11286946 - time (sec): 4.42 - samples/sec: 2196.68 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-13 10:33:14,718 epoch 3 - iter 120/242 - loss 0.10884545 - time (sec): 5.49 - samples/sec: 2219.49 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-13 10:33:15,830 epoch 3 - iter 144/242 - loss 0.10288949 - time (sec): 6.61 - samples/sec: 2221.59 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-13 10:33:16,938 epoch 3 - iter 168/242 - loss 0.11086947 - time (sec): 7.72 - samples/sec: 2216.44 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-13 10:33:18,055 epoch 3 - iter 192/242 - loss 0.10661603 - time (sec): 8.83 - samples/sec: 2228.89 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-13 10:33:19,170 epoch 3 - iter 216/242 - loss 0.10394865 - time (sec): 9.95 - samples/sec: 2229.00 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-13 10:33:20,280 epoch 3 - iter 240/242 - loss 0.10619255 - time (sec): 11.06 - samples/sec: 2224.34 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-13 10:33:20,371 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:33:20,371 EPOCH 3 done: loss 0.1071 - lr: 0.000039 | |
| 2023-10-13 10:33:21,258 DEV : loss 0.1535373479127884 - f1-score (micro avg) 0.7959 | |
| 2023-10-13 10:33:21,264 saving best model | |
| 2023-10-13 10:33:21,740 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:33:22,935 epoch 4 - iter 24/242 - loss 0.10320247 - time (sec): 1.19 - samples/sec: 2115.41 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-13 10:33:24,123 epoch 4 - iter 48/242 - loss 0.07939513 - time (sec): 2.38 - samples/sec: 2168.31 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-13 10:33:25,269 epoch 4 - iter 72/242 - loss 0.07554641 - time (sec): 3.53 - samples/sec: 2172.48 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-13 10:33:26,430 epoch 4 - iter 96/242 - loss 0.07777123 - time (sec): 4.69 - samples/sec: 2083.03 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-13 10:33:27,627 epoch 4 - iter 120/242 - loss 0.07377281 - time (sec): 5.89 - samples/sec: 2129.40 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-13 10:33:28,783 epoch 4 - iter 144/242 - loss 0.07660214 - time (sec): 7.04 - samples/sec: 2119.85 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-13 10:33:29,980 epoch 4 - iter 168/242 - loss 0.08008651 - time (sec): 8.24 - samples/sec: 2108.89 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-13 10:33:31,164 epoch 4 - iter 192/242 - loss 0.08165757 - time (sec): 9.42 - samples/sec: 2094.57 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-13 10:33:32,266 epoch 4 - iter 216/242 - loss 0.08032315 - time (sec): 10.52 - samples/sec: 2090.79 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-13 10:33:33,424 epoch 4 - iter 240/242 - loss 0.08061572 - time (sec): 11.68 - samples/sec: 2101.47 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-13 10:33:33,517 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:33:33,517 EPOCH 4 done: loss 0.0804 - lr: 0.000033 | |
| 2023-10-13 10:33:34,327 DEV : loss 0.15460173785686493 - f1-score (micro avg) 0.8302 | |
| 2023-10-13 10:33:34,332 saving best model | |
| 2023-10-13 10:33:34,775 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:33:35,871 epoch 5 - iter 24/242 - loss 0.04333528 - time (sec): 1.09 - samples/sec: 2314.58 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-13 10:33:37,067 epoch 5 - iter 48/242 - loss 0.06041197 - time (sec): 2.29 - samples/sec: 2102.58 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-13 10:33:38,239 epoch 5 - iter 72/242 - loss 0.06194261 - time (sec): 3.46 - samples/sec: 2108.92 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-13 10:33:39,370 epoch 5 - iter 96/242 - loss 0.06264413 - time (sec): 4.59 - samples/sec: 2097.63 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-13 10:33:40,495 epoch 5 - iter 120/242 - loss 0.06599964 - time (sec): 5.72 - samples/sec: 2160.83 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-13 10:33:41,629 epoch 5 - iter 144/242 - loss 0.06705809 - time (sec): 6.85 - samples/sec: 2202.73 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 10:33:42,738 epoch 5 - iter 168/242 - loss 0.06296828 - time (sec): 7.96 - samples/sec: 2218.31 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 10:33:43,893 epoch 5 - iter 192/242 - loss 0.05987115 - time (sec): 9.11 - samples/sec: 2191.20 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 10:33:44,938 epoch 5 - iter 216/242 - loss 0.05813650 - time (sec): 10.16 - samples/sec: 2166.44 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 10:33:46,028 epoch 5 - iter 240/242 - loss 0.05890973 - time (sec): 11.25 - samples/sec: 2178.60 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 10:33:46,119 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:33:46,120 EPOCH 5 done: loss 0.0590 - lr: 0.000028 | |
| 2023-10-13 10:33:46,939 DEV : loss 0.1725456714630127 - f1-score (micro avg) 0.8177 | |
| 2023-10-13 10:33:46,947 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:33:48,203 epoch 6 - iter 24/242 - loss 0.02517752 - time (sec): 1.25 - samples/sec: 2032.34 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 10:33:49,443 epoch 6 - iter 48/242 - loss 0.03321135 - time (sec): 2.49 - samples/sec: 1871.41 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 10:33:50,688 epoch 6 - iter 72/242 - loss 0.04604501 - time (sec): 3.74 - samples/sec: 1880.33 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 10:33:51,917 epoch 6 - iter 96/242 - loss 0.03998321 - time (sec): 4.97 - samples/sec: 1881.91 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 10:33:53,174 epoch 6 - iter 120/242 - loss 0.03952014 - time (sec): 6.23 - samples/sec: 1935.57 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 10:33:54,356 epoch 6 - iter 144/242 - loss 0.03847568 - time (sec): 7.41 - samples/sec: 1961.77 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 10:33:55,495 epoch 6 - iter 168/242 - loss 0.03897755 - time (sec): 8.55 - samples/sec: 2013.94 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 10:33:56,597 epoch 6 - iter 192/242 - loss 0.03778722 - time (sec): 9.65 - samples/sec: 2067.25 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 10:33:57,712 epoch 6 - iter 216/242 - loss 0.03937553 - time (sec): 10.76 - samples/sec: 2087.39 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 10:33:58,811 epoch 6 - iter 240/242 - loss 0.03932459 - time (sec): 11.86 - samples/sec: 2075.58 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 10:33:58,896 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:33:58,896 EPOCH 6 done: loss 0.0394 - lr: 0.000022 | |
| 2023-10-13 10:33:59,715 DEV : loss 0.1740647554397583 - f1-score (micro avg) 0.835 | |
| 2023-10-13 10:33:59,721 saving best model | |
| 2023-10-13 10:34:00,174 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:34:01,314 epoch 7 - iter 24/242 - loss 0.02318180 - time (sec): 1.14 - samples/sec: 1941.79 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 10:34:02,453 epoch 7 - iter 48/242 - loss 0.01729606 - time (sec): 2.28 - samples/sec: 2027.22 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 10:34:03,566 epoch 7 - iter 72/242 - loss 0.02262438 - time (sec): 3.39 - samples/sec: 2119.19 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 10:34:04,733 epoch 7 - iter 96/242 - loss 0.02501738 - time (sec): 4.56 - samples/sec: 2104.79 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 10:34:05,820 epoch 7 - iter 120/242 - loss 0.02919611 - time (sec): 5.64 - samples/sec: 2135.37 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 10:34:06,957 epoch 7 - iter 144/242 - loss 0.03130738 - time (sec): 6.78 - samples/sec: 2163.14 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 10:34:08,076 epoch 7 - iter 168/242 - loss 0.03134948 - time (sec): 7.90 - samples/sec: 2192.84 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 10:34:09,207 epoch 7 - iter 192/242 - loss 0.02926383 - time (sec): 9.03 - samples/sec: 2192.87 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 10:34:10,327 epoch 7 - iter 216/242 - loss 0.02796656 - time (sec): 10.15 - samples/sec: 2170.75 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 10:34:11,483 epoch 7 - iter 240/242 - loss 0.02857407 - time (sec): 11.31 - samples/sec: 2182.12 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 10:34:11,570 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:34:11,570 EPOCH 7 done: loss 0.0285 - lr: 0.000017 | |
| 2023-10-13 10:34:12,571 DEV : loss 0.1742168813943863 - f1-score (micro avg) 0.8436 | |
| 2023-10-13 10:34:12,577 saving best model | |
| 2023-10-13 10:34:13,076 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:34:14,247 epoch 8 - iter 24/242 - loss 0.01086829 - time (sec): 1.17 - samples/sec: 2085.56 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 10:34:15,436 epoch 8 - iter 48/242 - loss 0.00806217 - time (sec): 2.36 - samples/sec: 1953.97 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 10:34:16,577 epoch 8 - iter 72/242 - loss 0.00829654 - time (sec): 3.50 - samples/sec: 2019.32 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 10:34:17,772 epoch 8 - iter 96/242 - loss 0.00824662 - time (sec): 4.69 - samples/sec: 1981.51 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 10:34:18,939 epoch 8 - iter 120/242 - loss 0.00880508 - time (sec): 5.86 - samples/sec: 2075.73 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 10:34:20,023 epoch 8 - iter 144/242 - loss 0.00918007 - time (sec): 6.94 - samples/sec: 2107.49 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 10:34:21,102 epoch 8 - iter 168/242 - loss 0.00857383 - time (sec): 8.02 - samples/sec: 2111.73 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 10:34:22,202 epoch 8 - iter 192/242 - loss 0.01312391 - time (sec): 9.12 - samples/sec: 2143.89 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 10:34:23,318 epoch 8 - iter 216/242 - loss 0.01720811 - time (sec): 10.24 - samples/sec: 2159.18 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 10:34:24,458 epoch 8 - iter 240/242 - loss 0.01847871 - time (sec): 11.38 - samples/sec: 2162.33 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 10:34:24,544 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:34:24,544 EPOCH 8 done: loss 0.0185 - lr: 0.000011 | |
| 2023-10-13 10:34:25,331 DEV : loss 0.17900130152702332 - f1-score (micro avg) 0.8434 | |
| 2023-10-13 10:34:25,336 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:34:26,415 epoch 9 - iter 24/242 - loss 0.00595388 - time (sec): 1.08 - samples/sec: 2519.91 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 10:34:27,469 epoch 9 - iter 48/242 - loss 0.00471831 - time (sec): 2.13 - samples/sec: 2478.86 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 10:34:28,511 epoch 9 - iter 72/242 - loss 0.00922085 - time (sec): 3.17 - samples/sec: 2342.05 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 10:34:29,549 epoch 9 - iter 96/242 - loss 0.01347132 - time (sec): 4.21 - samples/sec: 2368.10 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 10:34:30,584 epoch 9 - iter 120/242 - loss 0.01224917 - time (sec): 5.25 - samples/sec: 2381.62 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 10:34:31,657 epoch 9 - iter 144/242 - loss 0.01652466 - time (sec): 6.32 - samples/sec: 2414.38 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 10:34:32,721 epoch 9 - iter 168/242 - loss 0.01464413 - time (sec): 7.38 - samples/sec: 2389.55 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 10:34:33,814 epoch 9 - iter 192/242 - loss 0.01535698 - time (sec): 8.48 - samples/sec: 2344.80 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 10:34:34,911 epoch 9 - iter 216/242 - loss 0.01385580 - time (sec): 9.57 - samples/sec: 2351.88 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 10:34:36,023 epoch 9 - iter 240/242 - loss 0.01300705 - time (sec): 10.69 - samples/sec: 2304.96 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 10:34:36,109 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:34:36,110 EPOCH 9 done: loss 0.0130 - lr: 0.000006 | |
| 2023-10-13 10:34:36,922 DEV : loss 0.1945873200893402 - f1-score (micro avg) 0.8369 | |
| 2023-10-13 10:34:36,927 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:34:37,946 epoch 10 - iter 24/242 - loss 0.01355820 - time (sec): 1.02 - samples/sec: 2221.61 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 10:34:39,054 epoch 10 - iter 48/242 - loss 0.01940785 - time (sec): 2.13 - samples/sec: 2207.82 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 10:34:40,179 epoch 10 - iter 72/242 - loss 0.01796443 - time (sec): 3.25 - samples/sec: 2238.97 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 10:34:41,320 epoch 10 - iter 96/242 - loss 0.01644088 - time (sec): 4.39 - samples/sec: 2255.07 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 10:34:42,434 epoch 10 - iter 120/242 - loss 0.01442045 - time (sec): 5.51 - samples/sec: 2254.63 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 10:34:43,525 epoch 10 - iter 144/242 - loss 0.01289671 - time (sec): 6.60 - samples/sec: 2211.56 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 10:34:44,619 epoch 10 - iter 168/242 - loss 0.01144991 - time (sec): 7.69 - samples/sec: 2191.41 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 10:34:45,745 epoch 10 - iter 192/242 - loss 0.01126744 - time (sec): 8.82 - samples/sec: 2169.01 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 10:34:46,848 epoch 10 - iter 216/242 - loss 0.00993734 - time (sec): 9.92 - samples/sec: 2193.79 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 10:34:48,012 epoch 10 - iter 240/242 - loss 0.00912108 - time (sec): 11.08 - samples/sec: 2214.01 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-13 10:34:48,101 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:34:48,101 EPOCH 10 done: loss 0.0090 - lr: 0.000000 | |
| 2023-10-13 10:34:48,908 DEV : loss 0.19059312343597412 - f1-score (micro avg) 0.8364 | |
| 2023-10-13 10:34:49,260 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 10:34:49,261 Loading model from best epoch ... | |
| 2023-10-13 10:34:50,661 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-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date | |
| 2023-10-13 10:34:51,558 | |
| Results: | |
| - F-score (micro) 0.8301 | |
| - F-score (macro) 0.5879 | |
| - Accuracy 0.7232 | |
| By class: | |
| precision recall f1-score support | |
| pers 0.8514 0.9065 0.8780 139 | |
| scope 0.8444 0.8837 0.8636 129 | |
| work 0.7229 0.7500 0.7362 80 | |
| loc 0.7500 0.3333 0.4615 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.8189 0.8417 0.8301 360 | |
| macro avg 0.6337 0.5747 0.5879 360 | |
| weighted avg 0.8107 0.8417 0.8236 360 | |
| 2023-10-13 10:34:51,558 ---------------------------------------------------------------------------------------------------- | |