| 2023-10-17 16:05:51,820 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:05:51,821 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 16:05:51,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:05:51,822 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 16:05:51,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:05:51,822 Train: 5777 sentences | |
| 2023-10-17 16:05:51,822 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 16:05:51,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:05:51,822 Training Params: | |
| 2023-10-17 16:05:51,822 - learning_rate: "3e-05" | |
| 2023-10-17 16:05:51,822 - mini_batch_size: "4" | |
| 2023-10-17 16:05:51,822 - max_epochs: "10" | |
| 2023-10-17 16:05:51,822 - shuffle: "True" | |
| 2023-10-17 16:05:51,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:05:51,822 Plugins: | |
| 2023-10-17 16:05:51,822 - TensorboardLogger | |
| 2023-10-17 16:05:51,822 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 16:05:51,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:05:51,822 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 16:05:51,822 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 16:05:51,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:05:51,822 Computation: | |
| 2023-10-17 16:05:51,822 - compute on device: cuda:0 | |
| 2023-10-17 16:05:51,822 - embedding storage: none | |
| 2023-10-17 16:05:51,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:05:51,822 Model training base path: "hmbench-icdar/nl-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-17 16:05:51,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:05:51,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:05:51,823 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 16:05:58,938 epoch 1 - iter 144/1445 - loss 2.61442915 - time (sec): 7.11 - samples/sec: 2565.02 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 16:06:05,920 epoch 1 - iter 288/1445 - loss 1.48508856 - time (sec): 14.10 - samples/sec: 2529.03 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 16:06:13,014 epoch 1 - iter 432/1445 - loss 1.10139561 - time (sec): 21.19 - samples/sec: 2472.30 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 16:06:20,202 epoch 1 - iter 576/1445 - loss 0.86933963 - time (sec): 28.38 - samples/sec: 2469.61 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 16:06:27,561 epoch 1 - iter 720/1445 - loss 0.72081647 - time (sec): 35.74 - samples/sec: 2474.93 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 16:06:34,978 epoch 1 - iter 864/1445 - loss 0.62859943 - time (sec): 43.15 - samples/sec: 2450.29 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 16:06:42,071 epoch 1 - iter 1008/1445 - loss 0.55956683 - time (sec): 50.25 - samples/sec: 2459.27 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 16:06:49,693 epoch 1 - iter 1152/1445 - loss 0.50313260 - time (sec): 57.87 - samples/sec: 2441.54 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 16:06:56,773 epoch 1 - iter 1296/1445 - loss 0.46190545 - time (sec): 64.95 - samples/sec: 2435.48 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 16:07:04,076 epoch 1 - iter 1440/1445 - loss 0.42817614 - time (sec): 72.25 - samples/sec: 2432.73 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 16:07:04,322 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:07:04,323 EPOCH 1 done: loss 0.4276 - lr: 0.000030 | |
| 2023-10-17 16:07:07,040 DEV : loss 0.08966663479804993 - f1-score (micro avg) 0.8004 | |
| 2023-10-17 16:07:07,056 saving best model | |
| 2023-10-17 16:07:07,420 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:07:14,351 epoch 2 - iter 144/1445 - loss 0.13373991 - time (sec): 6.93 - samples/sec: 2388.36 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 16:07:21,190 epoch 2 - iter 288/1445 - loss 0.12005429 - time (sec): 13.77 - samples/sec: 2433.94 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 16:07:28,283 epoch 2 - iter 432/1445 - loss 0.10977419 - time (sec): 20.86 - samples/sec: 2444.98 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 16:07:35,769 epoch 2 - iter 576/1445 - loss 0.10492325 - time (sec): 28.35 - samples/sec: 2432.19 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 16:07:42,654 epoch 2 - iter 720/1445 - loss 0.10061786 - time (sec): 35.23 - samples/sec: 2439.70 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 16:07:49,741 epoch 2 - iter 864/1445 - loss 0.09806729 - time (sec): 42.32 - samples/sec: 2485.05 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 16:07:56,799 epoch 2 - iter 1008/1445 - loss 0.09598940 - time (sec): 49.38 - samples/sec: 2492.22 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 16:08:03,879 epoch 2 - iter 1152/1445 - loss 0.09402430 - time (sec): 56.46 - samples/sec: 2480.00 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 16:08:11,024 epoch 2 - iter 1296/1445 - loss 0.09410389 - time (sec): 63.60 - samples/sec: 2487.14 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 16:08:18,116 epoch 2 - iter 1440/1445 - loss 0.09305196 - time (sec): 70.69 - samples/sec: 2486.04 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 16:08:18,336 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:08:18,336 EPOCH 2 done: loss 0.0932 - lr: 0.000027 | |
| 2023-10-17 16:08:21,685 DEV : loss 0.09091634303331375 - f1-score (micro avg) 0.8244 | |
| 2023-10-17 16:08:21,701 saving best model | |
| 2023-10-17 16:08:22,149 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:08:29,534 epoch 3 - iter 144/1445 - loss 0.06992594 - time (sec): 7.38 - samples/sec: 2466.82 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 16:08:36,552 epoch 3 - iter 288/1445 - loss 0.06304889 - time (sec): 14.40 - samples/sec: 2457.36 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 16:08:43,801 epoch 3 - iter 432/1445 - loss 0.06653206 - time (sec): 21.65 - samples/sec: 2514.49 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 16:08:50,910 epoch 3 - iter 576/1445 - loss 0.06750477 - time (sec): 28.76 - samples/sec: 2479.06 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 16:08:58,054 epoch 3 - iter 720/1445 - loss 0.06590474 - time (sec): 35.90 - samples/sec: 2471.29 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 16:09:05,405 epoch 3 - iter 864/1445 - loss 0.06338105 - time (sec): 43.25 - samples/sec: 2473.63 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 16:09:12,492 epoch 3 - iter 1008/1445 - loss 0.06397475 - time (sec): 50.34 - samples/sec: 2451.70 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 16:09:19,380 epoch 3 - iter 1152/1445 - loss 0.06368394 - time (sec): 57.23 - samples/sec: 2443.68 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 16:09:26,479 epoch 3 - iter 1296/1445 - loss 0.06411821 - time (sec): 64.32 - samples/sec: 2452.52 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 16:09:33,742 epoch 3 - iter 1440/1445 - loss 0.06471648 - time (sec): 71.59 - samples/sec: 2452.06 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 16:09:34,000 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:09:34,001 EPOCH 3 done: loss 0.0647 - lr: 0.000023 | |
| 2023-10-17 16:09:37,163 DEV : loss 0.08195469528436661 - f1-score (micro avg) 0.8681 | |
| 2023-10-17 16:09:37,180 saving best model | |
| 2023-10-17 16:09:37,649 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:09:44,774 epoch 4 - iter 144/1445 - loss 0.03793689 - time (sec): 7.12 - samples/sec: 2500.53 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 16:09:51,815 epoch 4 - iter 288/1445 - loss 0.04584517 - time (sec): 14.16 - samples/sec: 2460.92 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 16:09:58,809 epoch 4 - iter 432/1445 - loss 0.04581201 - time (sec): 21.16 - samples/sec: 2439.30 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 16:10:05,955 epoch 4 - iter 576/1445 - loss 0.04818147 - time (sec): 28.30 - samples/sec: 2427.68 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 16:10:13,182 epoch 4 - iter 720/1445 - loss 0.05102175 - time (sec): 35.53 - samples/sec: 2440.70 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 16:10:20,228 epoch 4 - iter 864/1445 - loss 0.05185422 - time (sec): 42.58 - samples/sec: 2465.40 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 16:10:27,265 epoch 4 - iter 1008/1445 - loss 0.05102231 - time (sec): 49.61 - samples/sec: 2473.93 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 16:10:34,786 epoch 4 - iter 1152/1445 - loss 0.04988097 - time (sec): 57.14 - samples/sec: 2457.91 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 16:10:41,874 epoch 4 - iter 1296/1445 - loss 0.04932647 - time (sec): 64.22 - samples/sec: 2460.98 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 16:10:49,054 epoch 4 - iter 1440/1445 - loss 0.04942813 - time (sec): 71.40 - samples/sec: 2461.23 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 16:10:49,309 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:10:49,309 EPOCH 4 done: loss 0.0494 - lr: 0.000020 | |
| 2023-10-17 16:10:52,521 DEV : loss 0.10280071198940277 - f1-score (micro avg) 0.8594 | |
| 2023-10-17 16:10:52,537 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:10:59,669 epoch 5 - iter 144/1445 - loss 0.05086725 - time (sec): 7.13 - samples/sec: 2306.72 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 16:11:06,676 epoch 5 - iter 288/1445 - loss 0.03847390 - time (sec): 14.14 - samples/sec: 2406.40 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 16:11:13,729 epoch 5 - iter 432/1445 - loss 0.03722457 - time (sec): 21.19 - samples/sec: 2437.47 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 16:11:20,636 epoch 5 - iter 576/1445 - loss 0.03791969 - time (sec): 28.10 - samples/sec: 2413.95 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 16:11:27,649 epoch 5 - iter 720/1445 - loss 0.03762962 - time (sec): 35.11 - samples/sec: 2451.19 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 16:11:34,669 epoch 5 - iter 864/1445 - loss 0.03832143 - time (sec): 42.13 - samples/sec: 2458.12 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 16:11:41,965 epoch 5 - iter 1008/1445 - loss 0.03898272 - time (sec): 49.43 - samples/sec: 2477.51 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 16:11:49,173 epoch 5 - iter 1152/1445 - loss 0.03774384 - time (sec): 56.63 - samples/sec: 2497.13 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 16:11:56,200 epoch 5 - iter 1296/1445 - loss 0.03646897 - time (sec): 63.66 - samples/sec: 2499.37 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 16:12:03,012 epoch 5 - iter 1440/1445 - loss 0.03614791 - time (sec): 70.47 - samples/sec: 2491.29 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 16:12:03,244 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:12:03,244 EPOCH 5 done: loss 0.0361 - lr: 0.000017 | |
| 2023-10-17 16:12:06,435 DEV : loss 0.10241829603910446 - f1-score (micro avg) 0.8564 | |
| 2023-10-17 16:12:06,451 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:12:13,704 epoch 6 - iter 144/1445 - loss 0.04938968 - time (sec): 7.25 - samples/sec: 2536.58 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 16:12:20,795 epoch 6 - iter 288/1445 - loss 0.03451984 - time (sec): 14.34 - samples/sec: 2478.84 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 16:12:27,672 epoch 6 - iter 432/1445 - loss 0.03115367 - time (sec): 21.22 - samples/sec: 2492.77 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 16:12:34,599 epoch 6 - iter 576/1445 - loss 0.02804596 - time (sec): 28.15 - samples/sec: 2497.72 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 16:12:41,827 epoch 6 - iter 720/1445 - loss 0.02653754 - time (sec): 35.37 - samples/sec: 2500.60 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 16:12:48,924 epoch 6 - iter 864/1445 - loss 0.02661037 - time (sec): 42.47 - samples/sec: 2513.53 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 16:12:56,046 epoch 6 - iter 1008/1445 - loss 0.02512559 - time (sec): 49.59 - samples/sec: 2514.30 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 16:13:03,060 epoch 6 - iter 1152/1445 - loss 0.02561509 - time (sec): 56.61 - samples/sec: 2493.42 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 16:13:09,934 epoch 6 - iter 1296/1445 - loss 0.02667536 - time (sec): 63.48 - samples/sec: 2489.39 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 16:13:16,851 epoch 6 - iter 1440/1445 - loss 0.02699248 - time (sec): 70.40 - samples/sec: 2493.45 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 16:13:17,148 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:13:17,149 EPOCH 6 done: loss 0.0269 - lr: 0.000013 | |
| 2023-10-17 16:13:20,688 DEV : loss 0.12599067389965057 - f1-score (micro avg) 0.8492 | |
| 2023-10-17 16:13:20,704 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:13:27,879 epoch 7 - iter 144/1445 - loss 0.01798898 - time (sec): 7.17 - samples/sec: 2565.89 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 16:13:34,920 epoch 7 - iter 288/1445 - loss 0.01577177 - time (sec): 14.22 - samples/sec: 2547.63 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 16:13:41,963 epoch 7 - iter 432/1445 - loss 0.01581476 - time (sec): 21.26 - samples/sec: 2502.35 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 16:13:49,180 epoch 7 - iter 576/1445 - loss 0.01575283 - time (sec): 28.47 - samples/sec: 2493.63 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 16:13:56,308 epoch 7 - iter 720/1445 - loss 0.01733916 - time (sec): 35.60 - samples/sec: 2499.92 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 16:14:03,346 epoch 7 - iter 864/1445 - loss 0.01744267 - time (sec): 42.64 - samples/sec: 2486.88 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 16:14:10,369 epoch 7 - iter 1008/1445 - loss 0.01855480 - time (sec): 49.66 - samples/sec: 2474.02 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 16:14:17,360 epoch 7 - iter 1152/1445 - loss 0.01883145 - time (sec): 56.65 - samples/sec: 2473.49 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 16:14:24,443 epoch 7 - iter 1296/1445 - loss 0.01853015 - time (sec): 63.74 - samples/sec: 2467.26 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 16:14:31,615 epoch 7 - iter 1440/1445 - loss 0.01913705 - time (sec): 70.91 - samples/sec: 2476.79 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 16:14:31,850 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:14:31,850 EPOCH 7 done: loss 0.0192 - lr: 0.000010 | |
| 2023-10-17 16:14:35,121 DEV : loss 0.12630820274353027 - f1-score (micro avg) 0.8673 | |
| 2023-10-17 16:14:35,139 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:14:42,235 epoch 8 - iter 144/1445 - loss 0.01838052 - time (sec): 7.09 - samples/sec: 2411.28 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 16:14:49,383 epoch 8 - iter 288/1445 - loss 0.01367032 - time (sec): 14.24 - samples/sec: 2402.76 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 16:14:56,511 epoch 8 - iter 432/1445 - loss 0.01331123 - time (sec): 21.37 - samples/sec: 2435.34 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 16:15:03,633 epoch 8 - iter 576/1445 - loss 0.01435875 - time (sec): 28.49 - samples/sec: 2432.92 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 16:15:10,448 epoch 8 - iter 720/1445 - loss 0.01281387 - time (sec): 35.31 - samples/sec: 2421.01 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 16:15:17,642 epoch 8 - iter 864/1445 - loss 0.01215775 - time (sec): 42.50 - samples/sec: 2445.73 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 16:15:24,878 epoch 8 - iter 1008/1445 - loss 0.01228586 - time (sec): 49.74 - samples/sec: 2457.97 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 16:15:32,003 epoch 8 - iter 1152/1445 - loss 0.01409772 - time (sec): 56.86 - samples/sec: 2453.22 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 16:15:39,161 epoch 8 - iter 1296/1445 - loss 0.01486635 - time (sec): 64.02 - samples/sec: 2465.22 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 16:15:46,199 epoch 8 - iter 1440/1445 - loss 0.01428808 - time (sec): 71.06 - samples/sec: 2471.79 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 16:15:46,432 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:15:46,433 EPOCH 8 done: loss 0.0143 - lr: 0.000007 | |
| 2023-10-17 16:15:49,712 DEV : loss 0.147283136844635 - f1-score (micro avg) 0.8614 | |
| 2023-10-17 16:15:49,727 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:15:56,769 epoch 9 - iter 144/1445 - loss 0.01334705 - time (sec): 7.04 - samples/sec: 2570.34 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 16:16:04,493 epoch 9 - iter 288/1445 - loss 0.01614528 - time (sec): 14.76 - samples/sec: 2495.81 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 16:16:11,470 epoch 9 - iter 432/1445 - loss 0.01383466 - time (sec): 21.74 - samples/sec: 2484.14 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 16:16:18,444 epoch 9 - iter 576/1445 - loss 0.01256669 - time (sec): 28.72 - samples/sec: 2482.26 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 16:16:25,416 epoch 9 - iter 720/1445 - loss 0.01229858 - time (sec): 35.69 - samples/sec: 2506.55 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 16:16:32,172 epoch 9 - iter 864/1445 - loss 0.01145068 - time (sec): 42.44 - samples/sec: 2524.48 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 16:16:39,190 epoch 9 - iter 1008/1445 - loss 0.01150023 - time (sec): 49.46 - samples/sec: 2506.71 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 16:16:46,049 epoch 9 - iter 1152/1445 - loss 0.01113663 - time (sec): 56.32 - samples/sec: 2506.36 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 16:16:53,266 epoch 9 - iter 1296/1445 - loss 0.01096505 - time (sec): 63.54 - samples/sec: 2492.67 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 16:17:00,355 epoch 9 - iter 1440/1445 - loss 0.01055015 - time (sec): 70.63 - samples/sec: 2485.57 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 16:17:00,582 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:17:00,582 EPOCH 9 done: loss 0.0105 - lr: 0.000003 | |
| 2023-10-17 16:17:03,819 DEV : loss 0.13861502707004547 - f1-score (micro avg) 0.8674 | |
| 2023-10-17 16:17:03,835 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:17:10,875 epoch 10 - iter 144/1445 - loss 0.00264139 - time (sec): 7.04 - samples/sec: 2578.53 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 16:17:17,605 epoch 10 - iter 288/1445 - loss 0.00303990 - time (sec): 13.77 - samples/sec: 2533.99 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 16:17:24,447 epoch 10 - iter 432/1445 - loss 0.00328206 - time (sec): 20.61 - samples/sec: 2433.78 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 16:17:31,703 epoch 10 - iter 576/1445 - loss 0.00421475 - time (sec): 27.87 - samples/sec: 2431.67 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 16:17:38,866 epoch 10 - iter 720/1445 - loss 0.00504231 - time (sec): 35.03 - samples/sec: 2448.92 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 16:17:45,871 epoch 10 - iter 864/1445 - loss 0.00543516 - time (sec): 42.03 - samples/sec: 2446.74 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 16:17:52,967 epoch 10 - iter 1008/1445 - loss 0.00520470 - time (sec): 49.13 - samples/sec: 2457.22 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 16:18:00,019 epoch 10 - iter 1152/1445 - loss 0.00518206 - time (sec): 56.18 - samples/sec: 2464.51 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 16:18:07,103 epoch 10 - iter 1296/1445 - loss 0.00570006 - time (sec): 63.27 - samples/sec: 2479.72 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 16:18:14,425 epoch 10 - iter 1440/1445 - loss 0.00595358 - time (sec): 70.59 - samples/sec: 2488.80 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 16:18:14,655 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:18:14,656 EPOCH 10 done: loss 0.0060 - lr: 0.000000 | |
| 2023-10-17 16:18:17,857 DEV : loss 0.150188148021698 - f1-score (micro avg) 0.8647 | |
| 2023-10-17 16:18:18,219 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:18:18,220 Loading model from best epoch ... | |
| 2023-10-17 16:18:19,595 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 16:18:22,388 | |
| Results: | |
| - F-score (micro) 0.8422 | |
| - F-score (macro) 0.7199 | |
| - Accuracy 0.7358 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.8524 0.8506 0.8515 482 | |
| LOC 0.9390 0.8406 0.8871 458 | |
| ORG 0.5333 0.3478 0.4211 69 | |
| micro avg 0.8750 0.8117 0.8422 1009 | |
| macro avg 0.7749 0.6797 0.7199 1009 | |
| weighted avg 0.8699 0.8117 0.8382 1009 | |
| 2023-10-17 16:18:22,388 ---------------------------------------------------------------------------------------------------- | |