| 2023-10-25 12:09:01,302 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:01,303 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 12:09:01,303 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:01,303 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 12:09:01,303 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:01,303 Train: 6183 sentences | |
| 2023-10-25 12:09:01,303 (train_with_dev=False, train_with_test=False) | |
| 2023-10-25 12:09:01,304 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:01,304 Training Params: | |
| 2023-10-25 12:09:01,304 - learning_rate: "3e-05" | |
| 2023-10-25 12:09:01,304 - mini_batch_size: "8" | |
| 2023-10-25 12:09:01,304 - max_epochs: "10" | |
| 2023-10-25 12:09:01,304 - shuffle: "True" | |
| 2023-10-25 12:09:01,304 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:01,304 Plugins: | |
| 2023-10-25 12:09:01,304 - TensorboardLogger | |
| 2023-10-25 12:09:01,304 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-25 12:09:01,304 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:01,304 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-25 12:09:01,304 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-25 12:09:01,304 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:01,304 Computation: | |
| 2023-10-25 12:09:01,304 - compute on device: cuda:0 | |
| 2023-10-25 12:09:01,304 - embedding storage: none | |
| 2023-10-25 12:09:01,304 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:01,304 Model training base path: "hmbench-topres19th/en-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-25 12:09:01,304 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:01,304 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:01,304 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-25 12:09:05,698 epoch 1 - iter 77/773 - loss 2.04935701 - time (sec): 4.39 - samples/sec: 2982.47 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 12:09:10,085 epoch 1 - iter 154/773 - loss 1.15224118 - time (sec): 8.78 - samples/sec: 2971.82 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 12:09:14,492 epoch 1 - iter 231/773 - loss 0.83962482 - time (sec): 13.19 - samples/sec: 2899.99 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 12:09:18,796 epoch 1 - iter 308/773 - loss 0.67002780 - time (sec): 17.49 - samples/sec: 2880.95 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 12:09:23,015 epoch 1 - iter 385/773 - loss 0.56132674 - time (sec): 21.71 - samples/sec: 2892.66 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 12:09:27,216 epoch 1 - iter 462/773 - loss 0.48308824 - time (sec): 25.91 - samples/sec: 2915.44 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 12:09:31,389 epoch 1 - iter 539/773 - loss 0.42824782 - time (sec): 30.08 - samples/sec: 2907.87 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 12:09:35,594 epoch 1 - iter 616/773 - loss 0.38904871 - time (sec): 34.29 - samples/sec: 2913.03 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 12:09:39,872 epoch 1 - iter 693/773 - loss 0.35655845 - time (sec): 38.57 - samples/sec: 2917.22 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 12:09:43,997 epoch 1 - iter 770/773 - loss 0.33228475 - time (sec): 42.69 - samples/sec: 2897.79 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 12:09:44,162 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:44,162 EPOCH 1 done: loss 0.3309 - lr: 0.000030 | |
| 2023-10-25 12:09:47,293 DEV : loss 0.049993742257356644 - f1-score (micro avg) 0.7523 | |
| 2023-10-25 12:09:47,319 saving best model | |
| 2023-10-25 12:09:47,898 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:52,486 epoch 2 - iter 77/773 - loss 0.05586007 - time (sec): 4.59 - samples/sec: 2762.10 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 12:09:57,004 epoch 2 - iter 154/773 - loss 0.06548935 - time (sec): 9.10 - samples/sec: 2828.81 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 12:10:01,297 epoch 2 - iter 231/773 - loss 0.06383761 - time (sec): 13.40 - samples/sec: 2888.10 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 12:10:05,751 epoch 2 - iter 308/773 - loss 0.06415157 - time (sec): 17.85 - samples/sec: 2910.03 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 12:10:10,194 epoch 2 - iter 385/773 - loss 0.07204142 - time (sec): 22.29 - samples/sec: 2908.49 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 12:10:14,677 epoch 2 - iter 462/773 - loss 0.07062633 - time (sec): 26.78 - samples/sec: 2864.21 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 12:10:18,899 epoch 2 - iter 539/773 - loss 0.07204287 - time (sec): 31.00 - samples/sec: 2857.66 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 12:10:23,280 epoch 2 - iter 616/773 - loss 0.07210437 - time (sec): 35.38 - samples/sec: 2818.57 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 12:10:27,601 epoch 2 - iter 693/773 - loss 0.07212975 - time (sec): 39.70 - samples/sec: 2803.29 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 12:10:32,010 epoch 2 - iter 770/773 - loss 0.07237257 - time (sec): 44.11 - samples/sec: 2809.61 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 12:10:32,167 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:10:32,168 EPOCH 2 done: loss 0.0723 - lr: 0.000027 | |
| 2023-10-25 12:10:34,902 DEV : loss 0.06731431186199188 - f1-score (micro avg) 0.6855 | |
| 2023-10-25 12:10:34,921 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:10:40,075 epoch 3 - iter 77/773 - loss 0.04149199 - time (sec): 5.15 - samples/sec: 2307.69 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 12:10:44,706 epoch 3 - iter 154/773 - loss 0.04585807 - time (sec): 9.78 - samples/sec: 2476.90 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 12:10:49,149 epoch 3 - iter 231/773 - loss 0.04473604 - time (sec): 14.23 - samples/sec: 2559.25 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 12:10:53,891 epoch 3 - iter 308/773 - loss 0.04580293 - time (sec): 18.97 - samples/sec: 2566.94 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 12:10:58,585 epoch 3 - iter 385/773 - loss 0.04415912 - time (sec): 23.66 - samples/sec: 2561.23 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 12:11:03,129 epoch 3 - iter 462/773 - loss 0.04458377 - time (sec): 28.21 - samples/sec: 2580.06 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 12:11:07,629 epoch 3 - iter 539/773 - loss 0.04465819 - time (sec): 32.71 - samples/sec: 2625.80 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 12:11:12,217 epoch 3 - iter 616/773 - loss 0.04392868 - time (sec): 37.29 - samples/sec: 2651.43 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 12:11:16,638 epoch 3 - iter 693/773 - loss 0.04295948 - time (sec): 41.72 - samples/sec: 2669.75 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 12:11:20,917 epoch 3 - iter 770/773 - loss 0.04338122 - time (sec): 45.99 - samples/sec: 2694.91 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 12:11:21,073 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:11:21,073 EPOCH 3 done: loss 0.0435 - lr: 0.000023 | |
| 2023-10-25 12:11:23,599 DEV : loss 0.06992863118648529 - f1-score (micro avg) 0.7865 | |
| 2023-10-25 12:11:23,617 saving best model | |
| 2023-10-25 12:11:24,310 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:11:28,634 epoch 4 - iter 77/773 - loss 0.03433423 - time (sec): 4.32 - samples/sec: 2690.37 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 12:11:33,053 epoch 4 - iter 154/773 - loss 0.02988579 - time (sec): 8.74 - samples/sec: 2771.11 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 12:11:37,747 epoch 4 - iter 231/773 - loss 0.03026380 - time (sec): 13.43 - samples/sec: 2748.66 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 12:11:42,346 epoch 4 - iter 308/773 - loss 0.03020876 - time (sec): 18.03 - samples/sec: 2694.06 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 12:11:47,174 epoch 4 - iter 385/773 - loss 0.03311283 - time (sec): 22.86 - samples/sec: 2724.08 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 12:11:51,918 epoch 4 - iter 462/773 - loss 0.03238387 - time (sec): 27.61 - samples/sec: 2694.60 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 12:11:56,468 epoch 4 - iter 539/773 - loss 0.03213652 - time (sec): 32.16 - samples/sec: 2705.37 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 12:12:00,887 epoch 4 - iter 616/773 - loss 0.03163816 - time (sec): 36.57 - samples/sec: 2678.18 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 12:12:05,429 epoch 4 - iter 693/773 - loss 0.03249376 - time (sec): 41.12 - samples/sec: 2700.12 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 12:12:09,862 epoch 4 - iter 770/773 - loss 0.03182826 - time (sec): 45.55 - samples/sec: 2714.95 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 12:12:10,038 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:12:10,039 EPOCH 4 done: loss 0.0318 - lr: 0.000020 | |
| 2023-10-25 12:12:12,691 DEV : loss 0.0831867977976799 - f1-score (micro avg) 0.7757 | |
| 2023-10-25 12:12:12,709 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:12:17,196 epoch 5 - iter 77/773 - loss 0.01118081 - time (sec): 4.49 - samples/sec: 2845.40 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 12:12:21,635 epoch 5 - iter 154/773 - loss 0.01225207 - time (sec): 8.92 - samples/sec: 2784.43 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 12:12:26,012 epoch 5 - iter 231/773 - loss 0.01513811 - time (sec): 13.30 - samples/sec: 2779.75 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 12:12:30,375 epoch 5 - iter 308/773 - loss 0.01783538 - time (sec): 17.66 - samples/sec: 2778.96 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 12:12:34,838 epoch 5 - iter 385/773 - loss 0.01923528 - time (sec): 22.13 - samples/sec: 2788.59 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 12:12:39,253 epoch 5 - iter 462/773 - loss 0.02067768 - time (sec): 26.54 - samples/sec: 2788.11 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 12:12:43,815 epoch 5 - iter 539/773 - loss 0.02178588 - time (sec): 31.10 - samples/sec: 2768.08 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 12:12:48,247 epoch 5 - iter 616/773 - loss 0.02202980 - time (sec): 35.54 - samples/sec: 2799.37 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 12:12:52,671 epoch 5 - iter 693/773 - loss 0.02206390 - time (sec): 39.96 - samples/sec: 2789.53 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 12:12:57,019 epoch 5 - iter 770/773 - loss 0.02268567 - time (sec): 44.31 - samples/sec: 2794.12 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 12:12:57,193 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:12:57,194 EPOCH 5 done: loss 0.0227 - lr: 0.000017 | |
| 2023-10-25 12:12:59,923 DEV : loss 0.10409079492092133 - f1-score (micro avg) 0.7599 | |
| 2023-10-25 12:12:59,941 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:13:04,359 epoch 6 - iter 77/773 - loss 0.01348224 - time (sec): 4.42 - samples/sec: 2675.10 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 12:13:08,929 epoch 6 - iter 154/773 - loss 0.01638656 - time (sec): 8.99 - samples/sec: 2724.77 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 12:13:13,271 epoch 6 - iter 231/773 - loss 0.01518915 - time (sec): 13.33 - samples/sec: 2699.04 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 12:13:17,554 epoch 6 - iter 308/773 - loss 0.01423275 - time (sec): 17.61 - samples/sec: 2715.12 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 12:13:21,948 epoch 6 - iter 385/773 - loss 0.01465336 - time (sec): 22.00 - samples/sec: 2719.42 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 12:13:26,275 epoch 6 - iter 462/773 - loss 0.01428615 - time (sec): 26.33 - samples/sec: 2755.48 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 12:13:30,650 epoch 6 - iter 539/773 - loss 0.01633936 - time (sec): 30.71 - samples/sec: 2796.82 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 12:13:34,925 epoch 6 - iter 616/773 - loss 0.01638676 - time (sec): 34.98 - samples/sec: 2821.52 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 12:13:39,145 epoch 6 - iter 693/773 - loss 0.01555940 - time (sec): 39.20 - samples/sec: 2844.70 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 12:13:43,632 epoch 6 - iter 770/773 - loss 0.01534485 - time (sec): 43.69 - samples/sec: 2830.40 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 12:13:43,817 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:13:43,818 EPOCH 6 done: loss 0.0153 - lr: 0.000013 | |
| 2023-10-25 12:13:47,014 DEV : loss 0.12169384211301804 - f1-score (micro avg) 0.7558 | |
| 2023-10-25 12:13:47,030 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:13:51,329 epoch 7 - iter 77/773 - loss 0.01436857 - time (sec): 4.30 - samples/sec: 2942.53 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 12:13:55,723 epoch 7 - iter 154/773 - loss 0.01141007 - time (sec): 8.69 - samples/sec: 2978.98 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 12:14:00,111 epoch 7 - iter 231/773 - loss 0.01256394 - time (sec): 13.08 - samples/sec: 2923.47 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 12:14:04,412 epoch 7 - iter 308/773 - loss 0.01155963 - time (sec): 17.38 - samples/sec: 2877.60 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 12:14:08,899 epoch 7 - iter 385/773 - loss 0.01165634 - time (sec): 21.87 - samples/sec: 2848.16 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 12:14:13,201 epoch 7 - iter 462/773 - loss 0.01214036 - time (sec): 26.17 - samples/sec: 2826.93 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 12:14:17,593 epoch 7 - iter 539/773 - loss 0.01164323 - time (sec): 30.56 - samples/sec: 2804.21 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 12:14:22,113 epoch 7 - iter 616/773 - loss 0.01236649 - time (sec): 35.08 - samples/sec: 2810.57 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 12:14:26,511 epoch 7 - iter 693/773 - loss 0.01338845 - time (sec): 39.48 - samples/sec: 2829.38 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 12:14:30,788 epoch 7 - iter 770/773 - loss 0.01263676 - time (sec): 43.76 - samples/sec: 2831.85 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 12:14:30,948 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:14:30,949 EPOCH 7 done: loss 0.0126 - lr: 0.000010 | |
| 2023-10-25 12:14:33,504 DEV : loss 0.12100550532341003 - f1-score (micro avg) 0.7798 | |
| 2023-10-25 12:14:33,521 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:14:38,008 epoch 8 - iter 77/773 - loss 0.00697278 - time (sec): 4.48 - samples/sec: 2710.94 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 12:14:42,374 epoch 8 - iter 154/773 - loss 0.00942980 - time (sec): 8.85 - samples/sec: 2728.78 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 12:14:47,348 epoch 8 - iter 231/773 - loss 0.00907831 - time (sec): 13.82 - samples/sec: 2680.93 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 12:14:52,128 epoch 8 - iter 308/773 - loss 0.00926748 - time (sec): 18.61 - samples/sec: 2648.71 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 12:14:56,906 epoch 8 - iter 385/773 - loss 0.00942620 - time (sec): 23.38 - samples/sec: 2667.48 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 12:15:01,658 epoch 8 - iter 462/773 - loss 0.00856654 - time (sec): 28.13 - samples/sec: 2670.62 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 12:15:06,213 epoch 8 - iter 539/773 - loss 0.00915887 - time (sec): 32.69 - samples/sec: 2686.56 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 12:15:10,739 epoch 8 - iter 616/773 - loss 0.00945267 - time (sec): 37.22 - samples/sec: 2687.82 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 12:15:15,239 epoch 8 - iter 693/773 - loss 0.00899884 - time (sec): 41.72 - samples/sec: 2683.48 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 12:15:19,697 epoch 8 - iter 770/773 - loss 0.00865270 - time (sec): 46.17 - samples/sec: 2684.25 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 12:15:19,865 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:15:19,865 EPOCH 8 done: loss 0.0086 - lr: 0.000007 | |
| 2023-10-25 12:15:22,716 DEV : loss 0.1208329051733017 - f1-score (micro avg) 0.7718 | |
| 2023-10-25 12:15:22,735 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:15:27,218 epoch 9 - iter 77/773 - loss 0.00207713 - time (sec): 4.48 - samples/sec: 2590.59 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 12:15:31,785 epoch 9 - iter 154/773 - loss 0.00299376 - time (sec): 9.05 - samples/sec: 2690.56 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 12:15:36,337 epoch 9 - iter 231/773 - loss 0.00439480 - time (sec): 13.60 - samples/sec: 2662.19 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 12:15:40,867 epoch 9 - iter 308/773 - loss 0.00427536 - time (sec): 18.13 - samples/sec: 2678.24 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 12:15:45,495 epoch 9 - iter 385/773 - loss 0.00426518 - time (sec): 22.76 - samples/sec: 2696.46 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 12:15:50,316 epoch 9 - iter 462/773 - loss 0.00496819 - time (sec): 27.58 - samples/sec: 2690.43 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 12:15:55,200 epoch 9 - iter 539/773 - loss 0.00520497 - time (sec): 32.46 - samples/sec: 2672.68 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 12:15:59,912 epoch 9 - iter 616/773 - loss 0.00510625 - time (sec): 37.17 - samples/sec: 2659.85 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 12:16:04,732 epoch 9 - iter 693/773 - loss 0.00494235 - time (sec): 41.99 - samples/sec: 2654.97 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 12:16:09,705 epoch 9 - iter 770/773 - loss 0.00530484 - time (sec): 46.97 - samples/sec: 2631.90 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 12:16:09,890 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:16:09,890 EPOCH 9 done: loss 0.0053 - lr: 0.000003 | |
| 2023-10-25 12:16:12,699 DEV : loss 0.12893347442150116 - f1-score (micro avg) 0.7771 | |
| 2023-10-25 12:16:12,715 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:16:17,489 epoch 10 - iter 77/773 - loss 0.00071556 - time (sec): 4.77 - samples/sec: 2666.44 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 12:16:22,187 epoch 10 - iter 154/773 - loss 0.00252394 - time (sec): 9.47 - samples/sec: 2581.74 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 12:16:26,865 epoch 10 - iter 231/773 - loss 0.00200991 - time (sec): 14.15 - samples/sec: 2640.64 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 12:16:31,612 epoch 10 - iter 308/773 - loss 0.00177058 - time (sec): 18.90 - samples/sec: 2657.01 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 12:16:36,407 epoch 10 - iter 385/773 - loss 0.00273068 - time (sec): 23.69 - samples/sec: 2650.98 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 12:16:41,225 epoch 10 - iter 462/773 - loss 0.00291902 - time (sec): 28.51 - samples/sec: 2655.16 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 12:16:45,670 epoch 10 - iter 539/773 - loss 0.00304957 - time (sec): 32.95 - samples/sec: 2675.25 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 12:16:50,087 epoch 10 - iter 616/773 - loss 0.00324520 - time (sec): 37.37 - samples/sec: 2666.88 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 12:16:54,512 epoch 10 - iter 693/773 - loss 0.00312779 - time (sec): 41.79 - samples/sec: 2683.66 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 12:16:58,780 epoch 10 - iter 770/773 - loss 0.00321731 - time (sec): 46.06 - samples/sec: 2688.80 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 12:16:58,943 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:16:58,944 EPOCH 10 done: loss 0.0032 - lr: 0.000000 | |
| 2023-10-25 12:17:01,521 DEV : loss 0.12955833971500397 - f1-score (micro avg) 0.7787 | |
| 2023-10-25 12:17:02,420 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:17:02,422 Loading model from best epoch ... | |
| 2023-10-25 12:17:04,237 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 12:17:12,614 | |
| Results: | |
| - F-score (micro) 0.7703 | |
| - F-score (macro) 0.606 | |
| - Accuracy 0.6435 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.8309 0.8414 0.8361 946 | |
| BUILDING 0.5915 0.2270 0.3281 185 | |
| STREET 0.7083 0.6071 0.6538 56 | |
| micro avg 0.8097 0.7346 0.7703 1187 | |
| macro avg 0.7103 0.5585 0.6060 1187 | |
| weighted avg 0.7878 0.7346 0.7484 1187 | |
| 2023-10-25 12:17:12,614 ---------------------------------------------------------------------------------------------------- | |