| 2023-10-25 10:46:23,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:46:23,097 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=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-25 10:46:23,097 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:46:23,098 MultiCorpus: 6183 train + 680 dev + 2113 test sentences | |
| - NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator | |
| 2023-10-25 10:46:23,098 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:46:23,098 Train: 6183 sentences | |
| 2023-10-25 10:46:23,098 (train_with_dev=False, train_with_test=False) | |
| 2023-10-25 10:46:23,098 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:46:23,098 Training Params: | |
| 2023-10-25 10:46:23,098 - learning_rate: "5e-05" | |
| 2023-10-25 10:46:23,098 - mini_batch_size: "8" | |
| 2023-10-25 10:46:23,098 - max_epochs: "10" | |
| 2023-10-25 10:46:23,098 - shuffle: "True" | |
| 2023-10-25 10:46:23,098 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:46:23,098 Plugins: | |
| 2023-10-25 10:46:23,098 - TensorboardLogger | |
| 2023-10-25 10:46:23,098 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-25 10:46:23,098 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:46:23,098 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-25 10:46:23,098 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-25 10:46:23,098 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:46:23,098 Computation: | |
| 2023-10-25 10:46:23,098 - compute on device: cuda:0 | |
| 2023-10-25 10:46:23,098 - embedding storage: none | |
| 2023-10-25 10:46:23,098 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:46:23,098 Model training base path: "hmbench-topres19th/en-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-25 10:46:23,098 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:46:23,099 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:46:23,099 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-25 10:46:28,075 epoch 1 - iter 77/773 - loss 1.64952430 - time (sec): 4.97 - samples/sec: 2562.70 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 10:46:33,104 epoch 1 - iter 154/773 - loss 0.93337294 - time (sec): 10.00 - samples/sec: 2490.60 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 10:46:37,967 epoch 1 - iter 231/773 - loss 0.67782129 - time (sec): 14.87 - samples/sec: 2485.70 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 10:46:42,883 epoch 1 - iter 308/773 - loss 0.53205948 - time (sec): 19.78 - samples/sec: 2518.33 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 10:46:47,510 epoch 1 - iter 385/773 - loss 0.44635492 - time (sec): 24.41 - samples/sec: 2548.09 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 10:46:52,119 epoch 1 - iter 462/773 - loss 0.39431926 - time (sec): 29.02 - samples/sec: 2548.56 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 10:46:56,856 epoch 1 - iter 539/773 - loss 0.35292625 - time (sec): 33.76 - samples/sec: 2572.32 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 10:47:01,538 epoch 1 - iter 616/773 - loss 0.31935913 - time (sec): 38.44 - samples/sec: 2591.35 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 10:47:06,067 epoch 1 - iter 693/773 - loss 0.29408255 - time (sec): 42.97 - samples/sec: 2603.74 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 10:47:11,234 epoch 1 - iter 770/773 - loss 0.27440561 - time (sec): 48.13 - samples/sec: 2572.37 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-25 10:47:11,419 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:47:11,419 EPOCH 1 done: loss 0.2740 - lr: 0.000050 | |
| 2023-10-25 10:47:14,343 DEV : loss 0.06034430116415024 - f1-score (micro avg) 0.7484 | |
| 2023-10-25 10:47:14,361 saving best model | |
| 2023-10-25 10:47:14,855 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:47:19,548 epoch 2 - iter 77/773 - loss 0.07012990 - time (sec): 4.69 - samples/sec: 2619.54 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 10:47:24,265 epoch 2 - iter 154/773 - loss 0.07639423 - time (sec): 9.41 - samples/sec: 2633.95 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 10:47:28,908 epoch 2 - iter 231/773 - loss 0.07702505 - time (sec): 14.05 - samples/sec: 2566.17 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 10:47:33,737 epoch 2 - iter 308/773 - loss 0.07889340 - time (sec): 18.88 - samples/sec: 2592.89 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 10:47:38,654 epoch 2 - iter 385/773 - loss 0.07691864 - time (sec): 23.80 - samples/sec: 2589.87 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 10:47:43,488 epoch 2 - iter 462/773 - loss 0.07543602 - time (sec): 28.63 - samples/sec: 2594.69 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 10:47:48,286 epoch 2 - iter 539/773 - loss 0.07550983 - time (sec): 33.43 - samples/sec: 2604.25 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 10:47:52,924 epoch 2 - iter 616/773 - loss 0.07470403 - time (sec): 38.07 - samples/sec: 2593.52 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 10:47:57,364 epoch 2 - iter 693/773 - loss 0.07377788 - time (sec): 42.51 - samples/sec: 2598.85 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 10:48:02,105 epoch 2 - iter 770/773 - loss 0.07413970 - time (sec): 47.25 - samples/sec: 2619.42 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 10:48:02,274 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:48:02,274 EPOCH 2 done: loss 0.0739 - lr: 0.000044 | |
| 2023-10-25 10:48:05,217 DEV : loss 0.05858875438570976 - f1-score (micro avg) 0.7287 | |
| 2023-10-25 10:48:05,234 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:48:09,912 epoch 3 - iter 77/773 - loss 0.04462850 - time (sec): 4.68 - samples/sec: 2610.70 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 10:48:14,526 epoch 3 - iter 154/773 - loss 0.04609617 - time (sec): 9.29 - samples/sec: 2568.19 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 10:48:19,206 epoch 3 - iter 231/773 - loss 0.04727208 - time (sec): 13.97 - samples/sec: 2560.80 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 10:48:23,981 epoch 3 - iter 308/773 - loss 0.04497885 - time (sec): 18.75 - samples/sec: 2579.51 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 10:48:28,676 epoch 3 - iter 385/773 - loss 0.04572064 - time (sec): 23.44 - samples/sec: 2582.45 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 10:48:33,361 epoch 3 - iter 462/773 - loss 0.04619941 - time (sec): 28.12 - samples/sec: 2615.55 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 10:48:38,007 epoch 3 - iter 539/773 - loss 0.04607725 - time (sec): 32.77 - samples/sec: 2627.41 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 10:48:42,587 epoch 3 - iter 616/773 - loss 0.04767181 - time (sec): 37.35 - samples/sec: 2642.74 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 10:48:47,298 epoch 3 - iter 693/773 - loss 0.04860853 - time (sec): 42.06 - samples/sec: 2652.28 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 10:48:51,926 epoch 3 - iter 770/773 - loss 0.04752276 - time (sec): 46.69 - samples/sec: 2653.31 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 10:48:52,128 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:48:52,128 EPOCH 3 done: loss 0.0474 - lr: 0.000039 | |
| 2023-10-25 10:48:54,819 DEV : loss 0.07712458819150925 - f1-score (micro avg) 0.7984 | |
| 2023-10-25 10:48:54,837 saving best model | |
| 2023-10-25 10:48:55,493 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:49:00,161 epoch 4 - iter 77/773 - loss 0.03050623 - time (sec): 4.67 - samples/sec: 2675.26 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 10:49:04,947 epoch 4 - iter 154/773 - loss 0.02946324 - time (sec): 9.45 - samples/sec: 2673.61 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 10:49:09,646 epoch 4 - iter 231/773 - loss 0.02910360 - time (sec): 14.15 - samples/sec: 2668.78 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 10:49:14,475 epoch 4 - iter 308/773 - loss 0.03117292 - time (sec): 18.98 - samples/sec: 2650.63 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 10:49:19,063 epoch 4 - iter 385/773 - loss 0.03199838 - time (sec): 23.57 - samples/sec: 2641.28 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 10:49:23,661 epoch 4 - iter 462/773 - loss 0.03362317 - time (sec): 28.16 - samples/sec: 2632.01 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 10:49:28,433 epoch 4 - iter 539/773 - loss 0.03421957 - time (sec): 32.94 - samples/sec: 2636.66 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 10:49:33,019 epoch 4 - iter 616/773 - loss 0.03426652 - time (sec): 37.52 - samples/sec: 2654.08 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 10:49:37,742 epoch 4 - iter 693/773 - loss 0.03423819 - time (sec): 42.25 - samples/sec: 2659.12 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 10:49:42,356 epoch 4 - iter 770/773 - loss 0.03434937 - time (sec): 46.86 - samples/sec: 2642.18 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 10:49:42,527 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:49:42,527 EPOCH 4 done: loss 0.0345 - lr: 0.000033 | |
| 2023-10-25 10:49:45,313 DEV : loss 0.08568881452083588 - f1-score (micro avg) 0.7335 | |
| 2023-10-25 10:49:45,330 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:49:49,956 epoch 5 - iter 77/773 - loss 0.02456627 - time (sec): 4.62 - samples/sec: 2661.67 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 10:49:54,528 epoch 5 - iter 154/773 - loss 0.02402263 - time (sec): 9.20 - samples/sec: 2683.11 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 10:49:59,332 epoch 5 - iter 231/773 - loss 0.02135560 - time (sec): 14.00 - samples/sec: 2685.78 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 10:50:03,983 epoch 5 - iter 308/773 - loss 0.02453825 - time (sec): 18.65 - samples/sec: 2667.18 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 10:50:08,782 epoch 5 - iter 385/773 - loss 0.02274215 - time (sec): 23.45 - samples/sec: 2674.33 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 10:50:13,512 epoch 5 - iter 462/773 - loss 0.02118376 - time (sec): 28.18 - samples/sec: 2677.97 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 10:50:18,343 epoch 5 - iter 539/773 - loss 0.02077515 - time (sec): 33.01 - samples/sec: 2672.12 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 10:50:22,967 epoch 5 - iter 616/773 - loss 0.02113624 - time (sec): 37.64 - samples/sec: 2649.88 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 10:50:27,639 epoch 5 - iter 693/773 - loss 0.02125485 - time (sec): 42.31 - samples/sec: 2654.17 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 10:50:32,191 epoch 5 - iter 770/773 - loss 0.02224251 - time (sec): 46.86 - samples/sec: 2642.63 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 10:50:32,396 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:50:32,397 EPOCH 5 done: loss 0.0222 - lr: 0.000028 | |
| 2023-10-25 10:50:35,116 DEV : loss 0.0947536900639534 - f1-score (micro avg) 0.7796 | |
| 2023-10-25 10:50:35,134 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:50:39,949 epoch 6 - iter 77/773 - loss 0.01500115 - time (sec): 4.81 - samples/sec: 2626.09 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 10:50:44,800 epoch 6 - iter 154/773 - loss 0.01845212 - time (sec): 9.66 - samples/sec: 2601.14 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 10:50:49,370 epoch 6 - iter 231/773 - loss 0.01861329 - time (sec): 14.23 - samples/sec: 2594.22 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 10:50:54,061 epoch 6 - iter 308/773 - loss 0.01918329 - time (sec): 18.93 - samples/sec: 2630.47 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 10:50:58,683 epoch 6 - iter 385/773 - loss 0.01825918 - time (sec): 23.55 - samples/sec: 2678.01 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 10:51:03,288 epoch 6 - iter 462/773 - loss 0.01813405 - time (sec): 28.15 - samples/sec: 2692.93 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 10:51:07,966 epoch 6 - iter 539/773 - loss 0.01809914 - time (sec): 32.83 - samples/sec: 2676.28 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 10:51:12,563 epoch 6 - iter 616/773 - loss 0.01698338 - time (sec): 37.43 - samples/sec: 2660.98 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 10:51:17,016 epoch 6 - iter 693/773 - loss 0.01652935 - time (sec): 41.88 - samples/sec: 2668.09 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 10:51:21,606 epoch 6 - iter 770/773 - loss 0.01672796 - time (sec): 46.47 - samples/sec: 2666.18 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 10:51:21,789 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:51:21,790 EPOCH 6 done: loss 0.0169 - lr: 0.000022 | |
| 2023-10-25 10:51:24,542 DEV : loss 0.10434131324291229 - f1-score (micro avg) 0.7475 | |
| 2023-10-25 10:51:24,560 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:51:29,476 epoch 7 - iter 77/773 - loss 0.01488389 - time (sec): 4.91 - samples/sec: 2591.88 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 10:51:34,023 epoch 7 - iter 154/773 - loss 0.01287761 - time (sec): 9.46 - samples/sec: 2626.81 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 10:51:39,004 epoch 7 - iter 231/773 - loss 0.01049621 - time (sec): 14.44 - samples/sec: 2683.40 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 10:51:43,584 epoch 7 - iter 308/773 - loss 0.01009304 - time (sec): 19.02 - samples/sec: 2608.10 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 10:51:48,267 epoch 7 - iter 385/773 - loss 0.01061720 - time (sec): 23.70 - samples/sec: 2608.95 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 10:51:52,972 epoch 7 - iter 462/773 - loss 0.01079765 - time (sec): 28.41 - samples/sec: 2622.25 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 10:51:57,626 epoch 7 - iter 539/773 - loss 0.01022193 - time (sec): 33.06 - samples/sec: 2597.96 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 10:52:02,645 epoch 7 - iter 616/773 - loss 0.01026500 - time (sec): 38.08 - samples/sec: 2570.01 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 10:52:07,340 epoch 7 - iter 693/773 - loss 0.01015055 - time (sec): 42.78 - samples/sec: 2593.69 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 10:52:11,969 epoch 7 - iter 770/773 - loss 0.01047840 - time (sec): 47.41 - samples/sec: 2609.58 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 10:52:12,148 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:52:12,148 EPOCH 7 done: loss 0.0104 - lr: 0.000017 | |
| 2023-10-25 10:52:14,980 DEV : loss 0.12387851625680923 - f1-score (micro avg) 0.754 | |
| 2023-10-25 10:52:15,002 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:52:19,770 epoch 8 - iter 77/773 - loss 0.00559353 - time (sec): 4.77 - samples/sec: 2587.00 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 10:52:24,472 epoch 8 - iter 154/773 - loss 0.00716554 - time (sec): 9.47 - samples/sec: 2622.85 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 10:52:29,209 epoch 8 - iter 231/773 - loss 0.00969964 - time (sec): 14.21 - samples/sec: 2561.88 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 10:52:33,958 epoch 8 - iter 308/773 - loss 0.00787012 - time (sec): 18.95 - samples/sec: 2562.72 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 10:52:38,746 epoch 8 - iter 385/773 - loss 0.00822737 - time (sec): 23.74 - samples/sec: 2574.97 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 10:52:43,366 epoch 8 - iter 462/773 - loss 0.00949259 - time (sec): 28.36 - samples/sec: 2624.79 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 10:52:48,014 epoch 8 - iter 539/773 - loss 0.00909000 - time (sec): 33.01 - samples/sec: 2634.45 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 10:52:52,785 epoch 8 - iter 616/773 - loss 0.00910250 - time (sec): 37.78 - samples/sec: 2625.07 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 10:52:57,572 epoch 8 - iter 693/773 - loss 0.00897170 - time (sec): 42.57 - samples/sec: 2612.95 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 10:53:02,343 epoch 8 - iter 770/773 - loss 0.00836489 - time (sec): 47.34 - samples/sec: 2613.96 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 10:53:02,522 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:53:02,522 EPOCH 8 done: loss 0.0083 - lr: 0.000011 | |
| 2023-10-25 10:53:05,400 DEV : loss 0.13534879684448242 - f1-score (micro avg) 0.76 | |
| 2023-10-25 10:53:05,423 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:53:10,212 epoch 9 - iter 77/773 - loss 0.00267671 - time (sec): 4.79 - samples/sec: 2631.30 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 10:53:14,902 epoch 9 - iter 154/773 - loss 0.00629952 - time (sec): 9.48 - samples/sec: 2640.80 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 10:53:19,488 epoch 9 - iter 231/773 - loss 0.00639907 - time (sec): 14.06 - samples/sec: 2659.72 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 10:53:24,185 epoch 9 - iter 308/773 - loss 0.00529316 - time (sec): 18.76 - samples/sec: 2685.60 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 10:53:28,965 epoch 9 - iter 385/773 - loss 0.00507245 - time (sec): 23.54 - samples/sec: 2662.13 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 10:53:33,679 epoch 9 - iter 462/773 - loss 0.00499478 - time (sec): 28.25 - samples/sec: 2652.62 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 10:53:38,383 epoch 9 - iter 539/773 - loss 0.00530658 - time (sec): 32.96 - samples/sec: 2637.92 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 10:53:42,943 epoch 9 - iter 616/773 - loss 0.00494346 - time (sec): 37.52 - samples/sec: 2639.57 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 10:53:47,719 epoch 9 - iter 693/773 - loss 0.00479337 - time (sec): 42.29 - samples/sec: 2652.85 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 10:53:52,483 epoch 9 - iter 770/773 - loss 0.00475456 - time (sec): 47.06 - samples/sec: 2634.72 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 10:53:52,652 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:53:52,652 EPOCH 9 done: loss 0.0047 - lr: 0.000006 | |
| 2023-10-25 10:53:55,453 DEV : loss 0.13144543766975403 - f1-score (micro avg) 0.7613 | |
| 2023-10-25 10:53:55,471 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:54:00,257 epoch 10 - iter 77/773 - loss 0.00043461 - time (sec): 4.78 - samples/sec: 2475.21 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 10:54:04,904 epoch 10 - iter 154/773 - loss 0.00118691 - time (sec): 9.43 - samples/sec: 2492.59 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 10:54:09,501 epoch 10 - iter 231/773 - loss 0.00206157 - time (sec): 14.03 - samples/sec: 2527.22 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 10:54:14,081 epoch 10 - iter 308/773 - loss 0.00311004 - time (sec): 18.61 - samples/sec: 2565.03 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 10:54:18,614 epoch 10 - iter 385/773 - loss 0.00265094 - time (sec): 23.14 - samples/sec: 2560.55 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 10:54:23,379 epoch 10 - iter 462/773 - loss 0.00274512 - time (sec): 27.91 - samples/sec: 2585.42 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 10:54:28,186 epoch 10 - iter 539/773 - loss 0.00263932 - time (sec): 32.71 - samples/sec: 2601.23 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 10:54:33,072 epoch 10 - iter 616/773 - loss 0.00248618 - time (sec): 37.60 - samples/sec: 2613.44 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 10:54:37,776 epoch 10 - iter 693/773 - loss 0.00242872 - time (sec): 42.30 - samples/sec: 2631.20 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 10:54:42,474 epoch 10 - iter 770/773 - loss 0.00237640 - time (sec): 47.00 - samples/sec: 2629.04 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 10:54:42,664 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:54:42,664 EPOCH 10 done: loss 0.0025 - lr: 0.000000 | |
| 2023-10-25 10:54:45,907 DEV : loss 0.13963457942008972 - f1-score (micro avg) 0.7556 | |
| 2023-10-25 10:54:46,396 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:54:46,398 Loading model from best epoch ... | |
| 2023-10-25 10:54:48,450 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-BUILDING, B-BUILDING, E-BUILDING, I-BUILDING, S-STREET, B-STREET, E-STREET, I-STREET | |
| 2023-10-25 10:54:58,129 | |
| Results: | |
| - F-score (micro) 0.7752 | |
| - F-score (macro) 0.6601 | |
| - Accuracy 0.6529 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.7859 0.8573 0.8200 946 | |
| BUILDING 0.6454 0.4919 0.5583 185 | |
| STREET 0.6596 0.5536 0.6019 56 | |
| micro avg 0.7648 0.7860 0.7752 1187 | |
| macro avg 0.6969 0.6343 0.6601 1187 | |
| weighted avg 0.7580 0.7860 0.7689 1187 | |
| 2023-10-25 10:54:58,129 ---------------------------------------------------------------------------------------------------- | |