2023-10-17 10:32:40,008 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:40,009 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=25, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-17 10:32:40,009 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:40,009 MultiCorpus: 966 train + 219 dev + 204 test sentences - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator 2023-10-17 10:32:40,009 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:40,009 Train: 966 sentences 2023-10-17 10:32:40,009 (train_with_dev=False, train_with_test=False) 2023-10-17 10:32:40,009 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:40,009 Training Params: 2023-10-17 10:32:40,009 - learning_rate: "5e-05" 2023-10-17 10:32:40,009 - mini_batch_size: "8" 2023-10-17 10:32:40,009 - max_epochs: "10" 2023-10-17 10:32:40,009 - shuffle: "True" 2023-10-17 10:32:40,010 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:40,010 Plugins: 2023-10-17 10:32:40,010 - TensorboardLogger 2023-10-17 10:32:40,010 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 10:32:40,010 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:40,010 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 10:32:40,010 - metric: "('micro avg', 'f1-score')" 2023-10-17 10:32:40,010 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:40,010 Computation: 2023-10-17 10:32:40,010 - compute on device: cuda:0 2023-10-17 10:32:40,010 - embedding storage: none 2023-10-17 10:32:40,010 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:40,010 Model training base path: "hmbench-ajmc/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1" 2023-10-17 10:32:40,010 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:40,010 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:40,010 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 10:32:40,704 epoch 1 - iter 12/121 - loss 3.26006474 - time (sec): 0.69 - samples/sec: 3358.62 - lr: 0.000005 - momentum: 0.000000 2023-10-17 10:32:41,416 epoch 1 - iter 24/121 - loss 2.80714465 - time (sec): 1.41 - samples/sec: 3179.73 - lr: 0.000010 - momentum: 0.000000 2023-10-17 10:32:42,131 epoch 1 - iter 36/121 - loss 2.26357289 - time (sec): 2.12 - samples/sec: 3226.17 - lr: 0.000014 - momentum: 0.000000 2023-10-17 10:32:42,895 epoch 1 - iter 48/121 - loss 1.81294219 - time (sec): 2.88 - samples/sec: 3258.12 - lr: 0.000019 - momentum: 0.000000 2023-10-17 10:32:43,687 epoch 1 - iter 60/121 - loss 1.52221299 - time (sec): 3.68 - samples/sec: 3268.71 - lr: 0.000024 - momentum: 0.000000 2023-10-17 10:32:44,420 epoch 1 - iter 72/121 - loss 1.34077527 - time (sec): 4.41 - samples/sec: 3270.74 - lr: 0.000029 - momentum: 0.000000 2023-10-17 10:32:45,172 epoch 1 - iter 84/121 - loss 1.19489547 - time (sec): 5.16 - samples/sec: 3271.74 - lr: 0.000034 - momentum: 0.000000 2023-10-17 10:32:45,955 epoch 1 - iter 96/121 - loss 1.07021795 - time (sec): 5.94 - samples/sec: 3278.00 - lr: 0.000039 - momentum: 0.000000 2023-10-17 10:32:46,679 epoch 1 - iter 108/121 - loss 0.98756273 - time (sec): 6.67 - samples/sec: 3291.74 - lr: 0.000044 - momentum: 0.000000 2023-10-17 10:32:47,457 epoch 1 - iter 120/121 - loss 0.91125100 - time (sec): 7.45 - samples/sec: 3301.42 - lr: 0.000049 - momentum: 0.000000 2023-10-17 10:32:47,527 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:47,527 EPOCH 1 done: loss 0.9066 - lr: 0.000049 2023-10-17 10:32:48,393 DEV : loss 0.28961601853370667 - f1-score (micro avg) 0.5606 2023-10-17 10:32:48,400 saving best model 2023-10-17 10:32:48,825 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:49,560 epoch 2 - iter 12/121 - loss 0.22875945 - time (sec): 0.73 - samples/sec: 3357.71 - lr: 0.000049 - momentum: 0.000000 2023-10-17 10:32:50,258 epoch 2 - iter 24/121 - loss 0.22465711 - time (sec): 1.43 - samples/sec: 3181.20 - lr: 0.000049 - momentum: 0.000000 2023-10-17 10:32:50,958 epoch 2 - iter 36/121 - loss 0.21804974 - time (sec): 2.13 - samples/sec: 3256.77 - lr: 0.000048 - momentum: 0.000000 2023-10-17 10:32:51,716 epoch 2 - iter 48/121 - loss 0.20232516 - time (sec): 2.89 - samples/sec: 3363.68 - lr: 0.000048 - momentum: 0.000000 2023-10-17 10:32:52,516 epoch 2 - iter 60/121 - loss 0.19376496 - time (sec): 3.69 - samples/sec: 3323.26 - lr: 0.000047 - momentum: 0.000000 2023-10-17 10:32:53,255 epoch 2 - iter 72/121 - loss 0.19087101 - time (sec): 4.43 - samples/sec: 3345.29 - lr: 0.000047 - momentum: 0.000000 2023-10-17 10:32:54,009 epoch 2 - iter 84/121 - loss 0.18357053 - time (sec): 5.18 - samples/sec: 3309.54 - lr: 0.000046 - momentum: 0.000000 2023-10-17 10:32:54,817 epoch 2 - iter 96/121 - loss 0.18101522 - time (sec): 5.99 - samples/sec: 3292.67 - lr: 0.000046 - momentum: 0.000000 2023-10-17 10:32:55,656 epoch 2 - iter 108/121 - loss 0.17795186 - time (sec): 6.83 - samples/sec: 3254.49 - lr: 0.000045 - momentum: 0.000000 2023-10-17 10:32:56,429 epoch 2 - iter 120/121 - loss 0.17481566 - time (sec): 7.60 - samples/sec: 3230.58 - lr: 0.000045 - momentum: 0.000000 2023-10-17 10:32:56,482 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:56,482 EPOCH 2 done: loss 0.1739 - lr: 0.000045 2023-10-17 10:32:57,266 DEV : loss 0.13590769469738007 - f1-score (micro avg) 0.7866 2023-10-17 10:32:57,271 saving best model 2023-10-17 10:32:57,790 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:58,585 epoch 3 - iter 12/121 - loss 0.11327432 - time (sec): 0.79 - samples/sec: 3159.61 - lr: 0.000044 - momentum: 0.000000 2023-10-17 10:32:59,372 epoch 3 - iter 24/121 - loss 0.09727054 - time (sec): 1.58 - samples/sec: 3082.45 - lr: 0.000043 - momentum: 0.000000 2023-10-17 10:33:00,270 epoch 3 - iter 36/121 - loss 0.10169243 - time (sec): 2.48 - samples/sec: 3057.53 - lr: 0.000043 - momentum: 0.000000 2023-10-17 10:33:01,022 epoch 3 - iter 48/121 - loss 0.10278596 - time (sec): 3.23 - samples/sec: 3112.97 - lr: 0.000042 - momentum: 0.000000 2023-10-17 10:33:01,798 epoch 3 - iter 60/121 - loss 0.10669048 - time (sec): 4.00 - samples/sec: 3095.14 - lr: 0.000042 - momentum: 0.000000 2023-10-17 10:33:02,626 epoch 3 - iter 72/121 - loss 0.10457757 - time (sec): 4.83 - samples/sec: 3139.89 - lr: 0.000041 - momentum: 0.000000 2023-10-17 10:33:03,390 epoch 3 - iter 84/121 - loss 0.10430623 - time (sec): 5.60 - samples/sec: 3087.28 - lr: 0.000041 - momentum: 0.000000 2023-10-17 10:33:04,108 epoch 3 - iter 96/121 - loss 0.10325922 - time (sec): 6.31 - samples/sec: 3119.76 - lr: 0.000040 - momentum: 0.000000 2023-10-17 10:33:04,861 epoch 3 - iter 108/121 - loss 0.10206642 - time (sec): 7.07 - samples/sec: 3171.64 - lr: 0.000040 - momentum: 0.000000 2023-10-17 10:33:05,604 epoch 3 - iter 120/121 - loss 0.10270216 - time (sec): 7.81 - samples/sec: 3158.98 - lr: 0.000039 - momentum: 0.000000 2023-10-17 10:33:05,650 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:05,650 EPOCH 3 done: loss 0.1031 - lr: 0.000039 2023-10-17 10:33:06,430 DEV : loss 0.12963081896305084 - f1-score (micro avg) 0.8244 2023-10-17 10:33:06,436 saving best model 2023-10-17 10:33:06,980 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:07,716 epoch 4 - iter 12/121 - loss 0.10310305 - time (sec): 0.73 - samples/sec: 3448.31 - lr: 0.000038 - momentum: 0.000000 2023-10-17 10:33:08,423 epoch 4 - iter 24/121 - loss 0.07881906 - time (sec): 1.44 - samples/sec: 3412.90 - lr: 0.000038 - momentum: 0.000000 2023-10-17 10:33:09,156 epoch 4 - iter 36/121 - loss 0.06988981 - time (sec): 2.17 - samples/sec: 3421.12 - lr: 0.000037 - momentum: 0.000000 2023-10-17 10:33:09,918 epoch 4 - iter 48/121 - loss 0.08057507 - time (sec): 2.94 - samples/sec: 3305.58 - lr: 0.000037 - momentum: 0.000000 2023-10-17 10:33:10,641 epoch 4 - iter 60/121 - loss 0.07780496 - time (sec): 3.66 - samples/sec: 3399.05 - lr: 0.000036 - momentum: 0.000000 2023-10-17 10:33:11,431 epoch 4 - iter 72/121 - loss 0.06914986 - time (sec): 4.45 - samples/sec: 3354.70 - lr: 0.000036 - momentum: 0.000000 2023-10-17 10:33:12,226 epoch 4 - iter 84/121 - loss 0.06675876 - time (sec): 5.24 - samples/sec: 3323.77 - lr: 0.000035 - momentum: 0.000000 2023-10-17 10:33:12,958 epoch 4 - iter 96/121 - loss 0.07186866 - time (sec): 5.97 - samples/sec: 3319.67 - lr: 0.000035 - momentum: 0.000000 2023-10-17 10:33:13,732 epoch 4 - iter 108/121 - loss 0.07109931 - time (sec): 6.75 - samples/sec: 3281.32 - lr: 0.000034 - momentum: 0.000000 2023-10-17 10:33:14,537 epoch 4 - iter 120/121 - loss 0.06880122 - time (sec): 7.55 - samples/sec: 3250.67 - lr: 0.000034 - momentum: 0.000000 2023-10-17 10:33:14,587 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:14,587 EPOCH 4 done: loss 0.0683 - lr: 0.000034 2023-10-17 10:33:15,354 DEV : loss 0.15439237654209137 - f1-score (micro avg) 0.8221 2023-10-17 10:33:15,360 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:16,180 epoch 5 - iter 12/121 - loss 0.04724636 - time (sec): 0.82 - samples/sec: 3409.82 - lr: 0.000033 - momentum: 0.000000 2023-10-17 10:33:16,873 epoch 5 - iter 24/121 - loss 0.05331324 - time (sec): 1.51 - samples/sec: 3276.74 - lr: 0.000032 - momentum: 0.000000 2023-10-17 10:33:17,648 epoch 5 - iter 36/121 - loss 0.05313566 - time (sec): 2.29 - samples/sec: 3289.81 - lr: 0.000032 - momentum: 0.000000 2023-10-17 10:33:18,419 epoch 5 - iter 48/121 - loss 0.04906792 - time (sec): 3.06 - samples/sec: 3255.55 - lr: 0.000031 - momentum: 0.000000 2023-10-17 10:33:19,121 epoch 5 - iter 60/121 - loss 0.04719752 - time (sec): 3.76 - samples/sec: 3285.53 - lr: 0.000031 - momentum: 0.000000 2023-10-17 10:33:19,881 epoch 5 - iter 72/121 - loss 0.04375019 - time (sec): 4.52 - samples/sec: 3277.57 - lr: 0.000030 - momentum: 0.000000 2023-10-17 10:33:20,596 epoch 5 - iter 84/121 - loss 0.04656749 - time (sec): 5.23 - samples/sec: 3337.99 - lr: 0.000030 - momentum: 0.000000 2023-10-17 10:33:21,353 epoch 5 - iter 96/121 - loss 0.04663450 - time (sec): 5.99 - samples/sec: 3282.19 - lr: 0.000029 - momentum: 0.000000 2023-10-17 10:33:22,094 epoch 5 - iter 108/121 - loss 0.04648098 - time (sec): 6.73 - samples/sec: 3281.60 - lr: 0.000029 - momentum: 0.000000 2023-10-17 10:33:22,871 epoch 5 - iter 120/121 - loss 0.04818959 - time (sec): 7.51 - samples/sec: 3269.52 - lr: 0.000028 - momentum: 0.000000 2023-10-17 10:33:22,942 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:22,943 EPOCH 5 done: loss 0.0479 - lr: 0.000028 2023-10-17 10:33:23,707 DEV : loss 0.163357213139534 - f1-score (micro avg) 0.8361 2023-10-17 10:33:23,714 saving best model 2023-10-17 10:33:24,261 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:25,004 epoch 6 - iter 12/121 - loss 0.01706041 - time (sec): 0.74 - samples/sec: 3576.24 - lr: 0.000027 - momentum: 0.000000 2023-10-17 10:33:25,803 epoch 6 - iter 24/121 - loss 0.03413402 - time (sec): 1.54 - samples/sec: 3332.48 - lr: 0.000027 - momentum: 0.000000 2023-10-17 10:33:26,578 epoch 6 - iter 36/121 - loss 0.03081119 - time (sec): 2.32 - samples/sec: 3316.18 - lr: 0.000026 - momentum: 0.000000 2023-10-17 10:33:27,307 epoch 6 - iter 48/121 - loss 0.03234101 - time (sec): 3.04 - samples/sec: 3260.29 - lr: 0.000026 - momentum: 0.000000 2023-10-17 10:33:28,098 epoch 6 - iter 60/121 - loss 0.02974588 - time (sec): 3.84 - samples/sec: 3234.64 - lr: 0.000025 - momentum: 0.000000 2023-10-17 10:33:28,849 epoch 6 - iter 72/121 - loss 0.03224484 - time (sec): 4.59 - samples/sec: 3239.87 - lr: 0.000025 - momentum: 0.000000 2023-10-17 10:33:29,568 epoch 6 - iter 84/121 - loss 0.02986217 - time (sec): 5.31 - samples/sec: 3253.41 - lr: 0.000024 - momentum: 0.000000 2023-10-17 10:33:30,327 epoch 6 - iter 96/121 - loss 0.03273185 - time (sec): 6.06 - samples/sec: 3261.07 - lr: 0.000024 - momentum: 0.000000 2023-10-17 10:33:31,029 epoch 6 - iter 108/121 - loss 0.03525937 - time (sec): 6.77 - samples/sec: 3274.06 - lr: 0.000023 - momentum: 0.000000 2023-10-17 10:33:31,759 epoch 6 - iter 120/121 - loss 0.03648931 - time (sec): 7.50 - samples/sec: 3284.01 - lr: 0.000022 - momentum: 0.000000 2023-10-17 10:33:31,806 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:31,806 EPOCH 6 done: loss 0.0365 - lr: 0.000022 2023-10-17 10:33:32,581 DEV : loss 0.17233064770698547 - f1-score (micro avg) 0.821 2023-10-17 10:33:32,588 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:33,337 epoch 7 - iter 12/121 - loss 0.02404734 - time (sec): 0.75 - samples/sec: 3528.67 - lr: 0.000022 - momentum: 0.000000 2023-10-17 10:33:34,091 epoch 7 - iter 24/121 - loss 0.02779211 - time (sec): 1.50 - samples/sec: 3359.91 - lr: 0.000021 - momentum: 0.000000 2023-10-17 10:33:34,846 epoch 7 - iter 36/121 - loss 0.02659868 - time (sec): 2.26 - samples/sec: 3334.23 - lr: 0.000021 - momentum: 0.000000 2023-10-17 10:33:35,569 epoch 7 - iter 48/121 - loss 0.02679515 - time (sec): 2.98 - samples/sec: 3338.31 - lr: 0.000020 - momentum: 0.000000 2023-10-17 10:33:36,378 epoch 7 - iter 60/121 - loss 0.02553453 - time (sec): 3.79 - samples/sec: 3341.44 - lr: 0.000020 - momentum: 0.000000 2023-10-17 10:33:37,130 epoch 7 - iter 72/121 - loss 0.02409986 - time (sec): 4.54 - samples/sec: 3328.59 - lr: 0.000019 - momentum: 0.000000 2023-10-17 10:33:37,933 epoch 7 - iter 84/121 - loss 0.02334057 - time (sec): 5.34 - samples/sec: 3288.33 - lr: 0.000019 - momentum: 0.000000 2023-10-17 10:33:38,655 epoch 7 - iter 96/121 - loss 0.02309239 - time (sec): 6.07 - samples/sec: 3244.95 - lr: 0.000018 - momentum: 0.000000 2023-10-17 10:33:39,405 epoch 7 - iter 108/121 - loss 0.02399850 - time (sec): 6.82 - samples/sec: 3253.36 - lr: 0.000017 - momentum: 0.000000 2023-10-17 10:33:40,140 epoch 7 - iter 120/121 - loss 0.02302854 - time (sec): 7.55 - samples/sec: 3250.94 - lr: 0.000017 - momentum: 0.000000 2023-10-17 10:33:40,198 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:40,198 EPOCH 7 done: loss 0.0230 - lr: 0.000017 2023-10-17 10:33:41,033 DEV : loss 0.2143603265285492 - f1-score (micro avg) 0.825 2023-10-17 10:33:41,038 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:41,775 epoch 8 - iter 12/121 - loss 0.01577638 - time (sec): 0.74 - samples/sec: 3213.30 - lr: 0.000016 - momentum: 0.000000 2023-10-17 10:33:42,491 epoch 8 - iter 24/121 - loss 0.01178881 - time (sec): 1.45 - samples/sec: 3325.68 - lr: 0.000016 - momentum: 0.000000 2023-10-17 10:33:43,313 epoch 8 - iter 36/121 - loss 0.01688569 - time (sec): 2.27 - samples/sec: 3259.36 - lr: 0.000015 - momentum: 0.000000 2023-10-17 10:33:44,086 epoch 8 - iter 48/121 - loss 0.01747875 - time (sec): 3.05 - samples/sec: 3291.33 - lr: 0.000015 - momentum: 0.000000 2023-10-17 10:33:44,821 epoch 8 - iter 60/121 - loss 0.01973594 - time (sec): 3.78 - samples/sec: 3319.04 - lr: 0.000014 - momentum: 0.000000 2023-10-17 10:33:45,548 epoch 8 - iter 72/121 - loss 0.01860066 - time (sec): 4.51 - samples/sec: 3353.85 - lr: 0.000014 - momentum: 0.000000 2023-10-17 10:33:46,289 epoch 8 - iter 84/121 - loss 0.01781938 - time (sec): 5.25 - samples/sec: 3332.89 - lr: 0.000013 - momentum: 0.000000 2023-10-17 10:33:47,007 epoch 8 - iter 96/121 - loss 0.02044574 - time (sec): 5.97 - samples/sec: 3285.14 - lr: 0.000013 - momentum: 0.000000 2023-10-17 10:33:47,838 epoch 8 - iter 108/121 - loss 0.01883755 - time (sec): 6.80 - samples/sec: 3304.17 - lr: 0.000012 - momentum: 0.000000 2023-10-17 10:33:48,739 epoch 8 - iter 120/121 - loss 0.01804760 - time (sec): 7.70 - samples/sec: 3194.63 - lr: 0.000011 - momentum: 0.000000 2023-10-17 10:33:48,791 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:48,791 EPOCH 8 done: loss 0.0179 - lr: 0.000011 2023-10-17 10:33:49,588 DEV : loss 0.2186920940876007 - f1-score (micro avg) 0.8375 2023-10-17 10:33:49,593 saving best model 2023-10-17 10:33:50,089 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:50,818 epoch 9 - iter 12/121 - loss 0.01090955 - time (sec): 0.72 - samples/sec: 3218.18 - lr: 0.000011 - momentum: 0.000000 2023-10-17 10:33:51,572 epoch 9 - iter 24/121 - loss 0.01187864 - time (sec): 1.48 - samples/sec: 3083.15 - lr: 0.000010 - momentum: 0.000000 2023-10-17 10:33:52,357 epoch 9 - iter 36/121 - loss 0.01271093 - time (sec): 2.26 - samples/sec: 3149.15 - lr: 0.000010 - momentum: 0.000000 2023-10-17 10:33:53,127 epoch 9 - iter 48/121 - loss 0.01137607 - time (sec): 3.03 - samples/sec: 3211.30 - lr: 0.000009 - momentum: 0.000000 2023-10-17 10:33:53,911 epoch 9 - iter 60/121 - loss 0.01522958 - time (sec): 3.82 - samples/sec: 3160.21 - lr: 0.000009 - momentum: 0.000000 2023-10-17 10:33:54,709 epoch 9 - iter 72/121 - loss 0.01431421 - time (sec): 4.61 - samples/sec: 3156.82 - lr: 0.000008 - momentum: 0.000000 2023-10-17 10:33:55,437 epoch 9 - iter 84/121 - loss 0.01403599 - time (sec): 5.34 - samples/sec: 3161.08 - lr: 0.000008 - momentum: 0.000000 2023-10-17 10:33:56,197 epoch 9 - iter 96/121 - loss 0.01371746 - time (sec): 6.10 - samples/sec: 3194.06 - lr: 0.000007 - momentum: 0.000000 2023-10-17 10:33:56,952 epoch 9 - iter 108/121 - loss 0.01265669 - time (sec): 6.86 - samples/sec: 3215.69 - lr: 0.000006 - momentum: 0.000000 2023-10-17 10:33:57,739 epoch 9 - iter 120/121 - loss 0.01203950 - time (sec): 7.64 - samples/sec: 3210.74 - lr: 0.000006 - momentum: 0.000000 2023-10-17 10:33:57,802 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:57,802 EPOCH 9 done: loss 0.0120 - lr: 0.000006 2023-10-17 10:33:58,619 DEV : loss 0.22531166672706604 - f1-score (micro avg) 0.831 2023-10-17 10:33:58,625 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:59,359 epoch 10 - iter 12/121 - loss 0.00410764 - time (sec): 0.73 - samples/sec: 3231.86 - lr: 0.000005 - momentum: 0.000000 2023-10-17 10:34:00,117 epoch 10 - iter 24/121 - loss 0.00455508 - time (sec): 1.49 - samples/sec: 3295.25 - lr: 0.000005 - momentum: 0.000000 2023-10-17 10:34:00,855 epoch 10 - iter 36/121 - loss 0.00428222 - time (sec): 2.23 - samples/sec: 3295.81 - lr: 0.000004 - momentum: 0.000000 2023-10-17 10:34:01,694 epoch 10 - iter 48/121 - loss 0.00361187 - time (sec): 3.07 - samples/sec: 3229.25 - lr: 0.000004 - momentum: 0.000000 2023-10-17 10:34:02,545 epoch 10 - iter 60/121 - loss 0.00549113 - time (sec): 3.92 - samples/sec: 3181.74 - lr: 0.000003 - momentum: 0.000000 2023-10-17 10:34:03,295 epoch 10 - iter 72/121 - loss 0.00620171 - time (sec): 4.67 - samples/sec: 3192.91 - lr: 0.000003 - momentum: 0.000000 2023-10-17 10:34:04,040 epoch 10 - iter 84/121 - loss 0.00747202 - time (sec): 5.41 - samples/sec: 3206.36 - lr: 0.000002 - momentum: 0.000000 2023-10-17 10:34:04,836 epoch 10 - iter 96/121 - loss 0.00746805 - time (sec): 6.21 - samples/sec: 3222.04 - lr: 0.000001 - momentum: 0.000000 2023-10-17 10:34:05,588 epoch 10 - iter 108/121 - loss 0.00920783 - time (sec): 6.96 - samples/sec: 3215.46 - lr: 0.000001 - momentum: 0.000000 2023-10-17 10:34:06,319 epoch 10 - iter 120/121 - loss 0.00895767 - time (sec): 7.69 - samples/sec: 3205.43 - lr: 0.000000 - momentum: 0.000000 2023-10-17 10:34:06,366 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:34:06,366 EPOCH 10 done: loss 0.0089 - lr: 0.000000 2023-10-17 10:34:07,175 DEV : loss 0.23311887681484222 - f1-score (micro avg) 0.836 2023-10-17 10:34:07,605 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:34:07,606 Loading model from best epoch ... 2023-10-17 10:34:09,049 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date 2023-10-17 10:34:09,865 Results: - F-score (micro) 0.8081 - F-score (macro) 0.5805 - Accuracy 0.6952 By class: precision recall f1-score support pers 0.8367 0.8849 0.8601 139 scope 0.8099 0.8915 0.8487 129 work 0.6452 0.7500 0.6936 80 loc 1.0000 0.3333 0.5000 9 date 0.0000 0.0000 0.0000 3 micro avg 0.7818 0.8361 0.8081 360 macro avg 0.6584 0.5719 0.5805 360 weighted avg 0.7816 0.8361 0.8029 360 2023-10-17 10:34:09,865 ----------------------------------------------------------------------------------------------------