| 2023-10-17 18:24:39,029 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:39,030 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): ElectraModel( | |
| (embeddings): ElectraEmbeddings( | |
| (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): ElectraEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x ElectraLayer( | |
| (attention): ElectraAttention( | |
| (self): ElectraSelfAttention( | |
| (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): ElectraSelfOutput( | |
| (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): ElectraIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): ElectraOutput( | |
| (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) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 18:24:39,030 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:39,030 MultiCorpus: 5777 train + 722 dev + 723 test sentences | |
| - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl | |
| 2023-10-17 18:24:39,030 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:39,030 Train: 5777 sentences | |
| 2023-10-17 18:24:39,030 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 18:24:39,030 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:39,030 Training Params: | |
| 2023-10-17 18:24:39,030 - learning_rate: "3e-05" | |
| 2023-10-17 18:24:39,030 - mini_batch_size: "4" | |
| 2023-10-17 18:24:39,030 - max_epochs: "10" | |
| 2023-10-17 18:24:39,030 - shuffle: "True" | |
| 2023-10-17 18:24:39,030 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:39,030 Plugins: | |
| 2023-10-17 18:24:39,030 - TensorboardLogger | |
| 2023-10-17 18:24:39,030 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 18:24:39,030 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:39,030 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 18:24:39,030 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 18:24:39,030 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:39,030 Computation: | |
| 2023-10-17 18:24:39,030 - compute on device: cuda:0 | |
| 2023-10-17 18:24:39,031 - embedding storage: none | |
| 2023-10-17 18:24:39,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:39,031 Model training base path: "hmbench-icdar/nl-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 18:24:39,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:39,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:39,031 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 18:24:46,064 epoch 1 - iter 144/1445 - loss 2.40249140 - time (sec): 7.03 - samples/sec: 2391.55 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:24:53,424 epoch 1 - iter 288/1445 - loss 1.36473047 - time (sec): 14.39 - samples/sec: 2360.01 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:25:00,668 epoch 1 - iter 432/1445 - loss 0.96670832 - time (sec): 21.64 - samples/sec: 2368.22 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:25:07,775 epoch 1 - iter 576/1445 - loss 0.75923383 - time (sec): 28.74 - samples/sec: 2399.17 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:25:14,606 epoch 1 - iter 720/1445 - loss 0.63444395 - time (sec): 35.57 - samples/sec: 2424.50 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:25:21,617 epoch 1 - iter 864/1445 - loss 0.54802313 - time (sec): 42.59 - samples/sec: 2450.41 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:25:28,797 epoch 1 - iter 1008/1445 - loss 0.49139637 - time (sec): 49.77 - samples/sec: 2451.68 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:25:35,915 epoch 1 - iter 1152/1445 - loss 0.44471338 - time (sec): 56.88 - samples/sec: 2457.05 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:25:42,772 epoch 1 - iter 1296/1445 - loss 0.40703382 - time (sec): 63.74 - samples/sec: 2471.56 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:25:50,326 epoch 1 - iter 1440/1445 - loss 0.37927457 - time (sec): 71.29 - samples/sec: 2461.52 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:25:50,587 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:50,587 EPOCH 1 done: loss 0.3781 - lr: 0.000030 | |
| 2023-10-17 18:25:53,549 DEV : loss 0.08337056636810303 - f1-score (micro avg) 0.7966 | |
| 2023-10-17 18:25:53,568 saving best model | |
| 2023-10-17 18:25:53,937 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:26:01,081 epoch 2 - iter 144/1445 - loss 0.09997945 - time (sec): 7.14 - samples/sec: 2323.79 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:26:08,349 epoch 2 - iter 288/1445 - loss 0.10050675 - time (sec): 14.41 - samples/sec: 2377.08 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:26:15,230 epoch 2 - iter 432/1445 - loss 0.09758629 - time (sec): 21.29 - samples/sec: 2429.50 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:26:22,200 epoch 2 - iter 576/1445 - loss 0.10550488 - time (sec): 28.26 - samples/sec: 2439.70 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:26:29,525 epoch 2 - iter 720/1445 - loss 0.09799138 - time (sec): 35.58 - samples/sec: 2465.77 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:26:36,921 epoch 2 - iter 864/1445 - loss 0.09518587 - time (sec): 42.98 - samples/sec: 2494.97 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:26:43,832 epoch 2 - iter 1008/1445 - loss 0.09965579 - time (sec): 49.89 - samples/sec: 2465.33 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:26:50,996 epoch 2 - iter 1152/1445 - loss 0.09757907 - time (sec): 57.05 - samples/sec: 2484.80 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:26:58,119 epoch 2 - iter 1296/1445 - loss 0.09642403 - time (sec): 64.18 - samples/sec: 2466.31 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:27:05,384 epoch 2 - iter 1440/1445 - loss 0.09419689 - time (sec): 71.44 - samples/sec: 2457.35 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:27:05,610 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:27:05,610 EPOCH 2 done: loss 0.0941 - lr: 0.000027 | |
| 2023-10-17 18:27:09,438 DEV : loss 0.059414949268102646 - f1-score (micro avg) 0.8677 | |
| 2023-10-17 18:27:09,455 saving best model | |
| 2023-10-17 18:27:09,918 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:27:16,714 epoch 3 - iter 144/1445 - loss 0.05939246 - time (sec): 6.79 - samples/sec: 2548.39 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:27:24,383 epoch 3 - iter 288/1445 - loss 0.06503883 - time (sec): 14.46 - samples/sec: 2347.37 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:27:31,793 epoch 3 - iter 432/1445 - loss 0.07206773 - time (sec): 21.87 - samples/sec: 2381.75 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:27:38,996 epoch 3 - iter 576/1445 - loss 0.06976120 - time (sec): 29.07 - samples/sec: 2410.64 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:27:46,120 epoch 3 - iter 720/1445 - loss 0.06784493 - time (sec): 36.20 - samples/sec: 2440.24 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:27:53,122 epoch 3 - iter 864/1445 - loss 0.07022398 - time (sec): 43.20 - samples/sec: 2446.68 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:28:00,718 epoch 3 - iter 1008/1445 - loss 0.07026795 - time (sec): 50.80 - samples/sec: 2419.53 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:28:08,051 epoch 3 - iter 1152/1445 - loss 0.06785824 - time (sec): 58.13 - samples/sec: 2435.02 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:28:15,597 epoch 3 - iter 1296/1445 - loss 0.06757860 - time (sec): 65.67 - samples/sec: 2414.48 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:28:23,280 epoch 3 - iter 1440/1445 - loss 0.06798115 - time (sec): 73.36 - samples/sec: 2393.59 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:28:23,534 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:28:23,534 EPOCH 3 done: loss 0.0679 - lr: 0.000023 | |
| 2023-10-17 18:28:26,900 DEV : loss 0.07125767320394516 - f1-score (micro avg) 0.8778 | |
| 2023-10-17 18:28:26,918 saving best model | |
| 2023-10-17 18:28:27,479 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:28:34,657 epoch 4 - iter 144/1445 - loss 0.03823889 - time (sec): 7.17 - samples/sec: 2571.13 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:28:42,028 epoch 4 - iter 288/1445 - loss 0.04172689 - time (sec): 14.54 - samples/sec: 2513.34 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:28:48,844 epoch 4 - iter 432/1445 - loss 0.04752585 - time (sec): 21.35 - samples/sec: 2481.42 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:28:55,928 epoch 4 - iter 576/1445 - loss 0.05232222 - time (sec): 28.44 - samples/sec: 2491.59 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:29:02,810 epoch 4 - iter 720/1445 - loss 0.05199722 - time (sec): 35.32 - samples/sec: 2472.85 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:29:09,858 epoch 4 - iter 864/1445 - loss 0.05516103 - time (sec): 42.37 - samples/sec: 2472.30 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:29:16,970 epoch 4 - iter 1008/1445 - loss 0.05469799 - time (sec): 49.48 - samples/sec: 2479.29 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:29:24,308 epoch 4 - iter 1152/1445 - loss 0.05442157 - time (sec): 56.82 - samples/sec: 2468.09 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:29:31,541 epoch 4 - iter 1296/1445 - loss 0.05372314 - time (sec): 64.05 - samples/sec: 2458.54 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:29:38,985 epoch 4 - iter 1440/1445 - loss 0.05417645 - time (sec): 71.49 - samples/sec: 2457.99 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:29:39,246 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:29:39,247 EPOCH 4 done: loss 0.0541 - lr: 0.000020 | |
| 2023-10-17 18:29:42,664 DEV : loss 0.10595724731683731 - f1-score (micro avg) 0.8568 | |
| 2023-10-17 18:29:42,685 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:29:50,238 epoch 5 - iter 144/1445 - loss 0.03925321 - time (sec): 7.55 - samples/sec: 2234.30 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:29:57,133 epoch 5 - iter 288/1445 - loss 0.03820912 - time (sec): 14.45 - samples/sec: 2291.33 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:30:04,590 epoch 5 - iter 432/1445 - loss 0.03770167 - time (sec): 21.90 - samples/sec: 2391.99 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:30:11,483 epoch 5 - iter 576/1445 - loss 0.03620886 - time (sec): 28.80 - samples/sec: 2405.91 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:30:18,766 epoch 5 - iter 720/1445 - loss 0.03355020 - time (sec): 36.08 - samples/sec: 2403.33 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:30:25,813 epoch 5 - iter 864/1445 - loss 0.03410430 - time (sec): 43.13 - samples/sec: 2426.47 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:30:33,029 epoch 5 - iter 1008/1445 - loss 0.03521635 - time (sec): 50.34 - samples/sec: 2439.19 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:30:39,998 epoch 5 - iter 1152/1445 - loss 0.03751550 - time (sec): 57.31 - samples/sec: 2448.07 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:30:46,953 epoch 5 - iter 1296/1445 - loss 0.03804211 - time (sec): 64.27 - samples/sec: 2447.82 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:30:53,948 epoch 5 - iter 1440/1445 - loss 0.03773588 - time (sec): 71.26 - samples/sec: 2467.64 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:30:54,165 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:30:54,165 EPOCH 5 done: loss 0.0378 - lr: 0.000017 | |
| 2023-10-17 18:30:57,498 DEV : loss 0.1191408783197403 - f1-score (micro avg) 0.8652 | |
| 2023-10-17 18:30:57,516 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:31:04,570 epoch 6 - iter 144/1445 - loss 0.01536583 - time (sec): 7.05 - samples/sec: 2581.94 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:31:11,647 epoch 6 - iter 288/1445 - loss 0.01909159 - time (sec): 14.13 - samples/sec: 2539.44 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:31:18,546 epoch 6 - iter 432/1445 - loss 0.02633944 - time (sec): 21.03 - samples/sec: 2550.13 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:31:25,686 epoch 6 - iter 576/1445 - loss 0.02999207 - time (sec): 28.17 - samples/sec: 2528.23 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:31:32,920 epoch 6 - iter 720/1445 - loss 0.03103521 - time (sec): 35.40 - samples/sec: 2533.15 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:31:40,138 epoch 6 - iter 864/1445 - loss 0.03041336 - time (sec): 42.62 - samples/sec: 2521.88 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:31:47,125 epoch 6 - iter 1008/1445 - loss 0.03013301 - time (sec): 49.61 - samples/sec: 2514.36 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:31:54,126 epoch 6 - iter 1152/1445 - loss 0.02977871 - time (sec): 56.61 - samples/sec: 2495.66 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:32:01,353 epoch 6 - iter 1296/1445 - loss 0.02885957 - time (sec): 63.84 - samples/sec: 2485.56 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:32:08,036 epoch 6 - iter 1440/1445 - loss 0.02830552 - time (sec): 70.52 - samples/sec: 2492.18 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:32:08,274 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:08,275 EPOCH 6 done: loss 0.0283 - lr: 0.000013 | |
| 2023-10-17 18:32:11,731 DEV : loss 0.1016329899430275 - f1-score (micro avg) 0.8851 | |
| 2023-10-17 18:32:11,750 saving best model | |
| 2023-10-17 18:32:12,213 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:19,813 epoch 7 - iter 144/1445 - loss 0.01283763 - time (sec): 7.60 - samples/sec: 2326.72 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:32:27,511 epoch 7 - iter 288/1445 - loss 0.02088703 - time (sec): 15.30 - samples/sec: 2243.04 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:32:35,883 epoch 7 - iter 432/1445 - loss 0.02183665 - time (sec): 23.67 - samples/sec: 2242.34 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:32:43,093 epoch 7 - iter 576/1445 - loss 0.02240611 - time (sec): 30.88 - samples/sec: 2318.86 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:32:50,374 epoch 7 - iter 720/1445 - loss 0.02292437 - time (sec): 38.16 - samples/sec: 2347.37 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:32:57,550 epoch 7 - iter 864/1445 - loss 0.02185865 - time (sec): 45.34 - samples/sec: 2364.34 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:33:04,627 epoch 7 - iter 1008/1445 - loss 0.02156408 - time (sec): 52.41 - samples/sec: 2375.00 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:33:11,457 epoch 7 - iter 1152/1445 - loss 0.02042531 - time (sec): 59.24 - samples/sec: 2390.81 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:33:18,355 epoch 7 - iter 1296/1445 - loss 0.02042436 - time (sec): 66.14 - samples/sec: 2396.48 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:33:25,535 epoch 7 - iter 1440/1445 - loss 0.02033836 - time (sec): 73.32 - samples/sec: 2396.58 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:33:25,757 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:33:25,757 EPOCH 7 done: loss 0.0204 - lr: 0.000010 | |
| 2023-10-17 18:33:29,168 DEV : loss 0.1190648004412651 - f1-score (micro avg) 0.8655 | |
| 2023-10-17 18:33:29,188 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:33:36,420 epoch 8 - iter 144/1445 - loss 0.00857818 - time (sec): 7.23 - samples/sec: 2455.99 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:33:43,376 epoch 8 - iter 288/1445 - loss 0.01132420 - time (sec): 14.19 - samples/sec: 2487.91 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:33:50,188 epoch 8 - iter 432/1445 - loss 0.01072450 - time (sec): 21.00 - samples/sec: 2477.46 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:33:57,282 epoch 8 - iter 576/1445 - loss 0.01112080 - time (sec): 28.09 - samples/sec: 2474.40 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:34:04,320 epoch 8 - iter 720/1445 - loss 0.01113390 - time (sec): 35.13 - samples/sec: 2453.70 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:34:11,554 epoch 8 - iter 864/1445 - loss 0.01168471 - time (sec): 42.37 - samples/sec: 2449.12 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:34:18,690 epoch 8 - iter 1008/1445 - loss 0.01211707 - time (sec): 49.50 - samples/sec: 2443.14 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:34:26,217 epoch 8 - iter 1152/1445 - loss 0.01308008 - time (sec): 57.03 - samples/sec: 2458.92 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:34:33,244 epoch 8 - iter 1296/1445 - loss 0.01348119 - time (sec): 64.06 - samples/sec: 2458.87 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:34:40,430 epoch 8 - iter 1440/1445 - loss 0.01338325 - time (sec): 71.24 - samples/sec: 2464.52 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:34:40,677 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:34:40,678 EPOCH 8 done: loss 0.0134 - lr: 0.000007 | |
| 2023-10-17 18:34:44,135 DEV : loss 0.1326545625925064 - f1-score (micro avg) 0.8661 | |
| 2023-10-17 18:34:44,159 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:34:51,536 epoch 9 - iter 144/1445 - loss 0.00677100 - time (sec): 7.37 - samples/sec: 2388.08 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:34:58,666 epoch 9 - iter 288/1445 - loss 0.00589925 - time (sec): 14.51 - samples/sec: 2496.19 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:35:05,566 epoch 9 - iter 432/1445 - loss 0.00710020 - time (sec): 21.40 - samples/sec: 2473.34 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:35:12,669 epoch 9 - iter 576/1445 - loss 0.00726776 - time (sec): 28.51 - samples/sec: 2472.61 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:35:19,808 epoch 9 - iter 720/1445 - loss 0.00665823 - time (sec): 35.65 - samples/sec: 2484.41 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:35:27,339 epoch 9 - iter 864/1445 - loss 0.00694911 - time (sec): 43.18 - samples/sec: 2452.15 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:35:34,823 epoch 9 - iter 1008/1445 - loss 0.00785515 - time (sec): 50.66 - samples/sec: 2461.29 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:35:41,857 epoch 9 - iter 1152/1445 - loss 0.00791889 - time (sec): 57.70 - samples/sec: 2456.03 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:35:48,930 epoch 9 - iter 1296/1445 - loss 0.00819709 - time (sec): 64.77 - samples/sec: 2468.17 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:35:55,665 epoch 9 - iter 1440/1445 - loss 0.00824064 - time (sec): 71.50 - samples/sec: 2458.58 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:35:55,884 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:35:55,885 EPOCH 9 done: loss 0.0082 - lr: 0.000003 | |
| 2023-10-17 18:35:59,265 DEV : loss 0.13092152774333954 - f1-score (micro avg) 0.8755 | |
| 2023-10-17 18:35:59,283 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:36:06,634 epoch 10 - iter 144/1445 - loss 0.00800238 - time (sec): 7.35 - samples/sec: 2446.53 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:36:13,521 epoch 10 - iter 288/1445 - loss 0.00496623 - time (sec): 14.24 - samples/sec: 2460.81 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:36:20,659 epoch 10 - iter 432/1445 - loss 0.00568248 - time (sec): 21.37 - samples/sec: 2474.86 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:36:27,805 epoch 10 - iter 576/1445 - loss 0.00602579 - time (sec): 28.52 - samples/sec: 2476.23 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:36:34,747 epoch 10 - iter 720/1445 - loss 0.00617050 - time (sec): 35.46 - samples/sec: 2477.34 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:36:41,884 epoch 10 - iter 864/1445 - loss 0.00622325 - time (sec): 42.60 - samples/sec: 2489.90 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:36:48,941 epoch 10 - iter 1008/1445 - loss 0.00593060 - time (sec): 49.66 - samples/sec: 2477.93 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:36:55,998 epoch 10 - iter 1152/1445 - loss 0.00607493 - time (sec): 56.71 - samples/sec: 2466.32 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:37:02,996 epoch 10 - iter 1296/1445 - loss 0.00609370 - time (sec): 63.71 - samples/sec: 2476.51 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:37:09,948 epoch 10 - iter 1440/1445 - loss 0.00604769 - time (sec): 70.66 - samples/sec: 2488.21 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:37:10,161 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:37:10,162 EPOCH 10 done: loss 0.0060 - lr: 0.000000 | |
| 2023-10-17 18:37:13,655 DEV : loss 0.1363741010427475 - f1-score (micro avg) 0.877 | |
| 2023-10-17 18:37:14,123 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:37:14,124 Loading model from best epoch ... | |
| 2023-10-17 18:37:15,533 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG | |
| 2023-10-17 18:37:18,597 | |
| Results: | |
| - F-score (micro) 0.8566 | |
| - F-score (macro) 0.7724 | |
| - Accuracy 0.7604 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.8104 0.8693 0.8388 482 | |
| LOC 0.9320 0.8974 0.9143 458 | |
| ORG 0.6875 0.4783 0.5641 69 | |
| micro avg 0.8579 0.8553 0.8566 1009 | |
| macro avg 0.8100 0.7483 0.7724 1009 | |
| weighted avg 0.8572 0.8553 0.8543 1009 | |
| 2023-10-17 18:37:18,597 ---------------------------------------------------------------------------------------------------- | |