2023-10-17 21:48:44,320 ----------------------------------------------------------------------------------------------------
2023-10-17 21:48:44,321 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=21, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2023-10-17 21:48:44,321 ----------------------------------------------------------------------------------------------------
2023-10-17 21:48:44,321 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences
 - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator
2023-10-17 21:48:44,321 ----------------------------------------------------------------------------------------------------
2023-10-17 21:48:44,321 Train:  5901 sentences
2023-10-17 21:48:44,321         (train_with_dev=False, train_with_test=False)
2023-10-17 21:48:44,321 ----------------------------------------------------------------------------------------------------
2023-10-17 21:48:44,322 Training Params:
2023-10-17 21:48:44,322  - learning_rate: "3e-05" 
2023-10-17 21:48:44,322  - mini_batch_size: "4"
2023-10-17 21:48:44,322  - max_epochs: "10"
2023-10-17 21:48:44,322  - shuffle: "True"
2023-10-17 21:48:44,322 ----------------------------------------------------------------------------------------------------
2023-10-17 21:48:44,322 Plugins:
2023-10-17 21:48:44,322  - TensorboardLogger
2023-10-17 21:48:44,322  - LinearScheduler | warmup_fraction: '0.1'
2023-10-17 21:48:44,322 ----------------------------------------------------------------------------------------------------
2023-10-17 21:48:44,322 Final evaluation on model from best epoch (best-model.pt)
2023-10-17 21:48:44,322  - metric: "('micro avg', 'f1-score')"
2023-10-17 21:48:44,322 ----------------------------------------------------------------------------------------------------
2023-10-17 21:48:44,322 Computation:
2023-10-17 21:48:44,322  - compute on device: cuda:0
2023-10-17 21:48:44,322  - embedding storage: none
2023-10-17 21:48:44,322 ----------------------------------------------------------------------------------------------------
2023-10-17 21:48:44,322 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-17 21:48:44,322 ----------------------------------------------------------------------------------------------------
2023-10-17 21:48:44,322 ----------------------------------------------------------------------------------------------------
2023-10-17 21:48:44,322 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-17 21:48:52,215 epoch 1 - iter 147/1476 - loss 3.21553891 - time (sec): 7.89 - samples/sec: 2054.82 - lr: 0.000003 - momentum: 0.000000
2023-10-17 21:49:00,069 epoch 1 - iter 294/1476 - loss 1.82928163 - time (sec): 15.75 - samples/sec: 2288.06 - lr: 0.000006 - momentum: 0.000000
2023-10-17 21:49:07,291 epoch 1 - iter 441/1476 - loss 1.40421229 - time (sec): 22.97 - samples/sec: 2268.93 - lr: 0.000009 - momentum: 0.000000
2023-10-17 21:49:14,183 epoch 1 - iter 588/1476 - loss 1.17671724 - time (sec): 29.86 - samples/sec: 2242.25 - lr: 0.000012 - momentum: 0.000000
2023-10-17 21:49:21,418 epoch 1 - iter 735/1476 - loss 1.00461301 - time (sec): 37.09 - samples/sec: 2239.65 - lr: 0.000015 - momentum: 0.000000
2023-10-17 21:49:29,052 epoch 1 - iter 882/1476 - loss 0.87623716 - time (sec): 44.73 - samples/sec: 2269.88 - lr: 0.000018 - momentum: 0.000000
2023-10-17 21:49:36,057 epoch 1 - iter 1029/1476 - loss 0.78397459 - time (sec): 51.73 - samples/sec: 2267.14 - lr: 0.000021 - momentum: 0.000000
2023-10-17 21:49:43,075 epoch 1 - iter 1176/1476 - loss 0.71570404 - time (sec): 58.75 - samples/sec: 2262.64 - lr: 0.000024 - momentum: 0.000000
2023-10-17 21:49:49,813 epoch 1 - iter 1323/1476 - loss 0.65939395 - time (sec): 65.49 - samples/sec: 2273.76 - lr: 0.000027 - momentum: 0.000000
2023-10-17 21:49:56,543 epoch 1 - iter 1470/1476 - loss 0.61090665 - time (sec): 72.22 - samples/sec: 2292.81 - lr: 0.000030 - momentum: 0.000000
2023-10-17 21:49:56,815 ----------------------------------------------------------------------------------------------------
2023-10-17 21:49:56,815 EPOCH 1 done: loss 0.6087 - lr: 0.000030
2023-10-17 21:50:03,163 DEV : loss 0.11746251583099365 - f1-score (micro avg)  0.7497
2023-10-17 21:50:03,193 saving best model
2023-10-17 21:50:03,639 ----------------------------------------------------------------------------------------------------
2023-10-17 21:50:10,801 epoch 2 - iter 147/1476 - loss 0.15813511 - time (sec): 7.16 - samples/sec: 2256.78 - lr: 0.000030 - momentum: 0.000000
2023-10-17 21:50:18,227 epoch 2 - iter 294/1476 - loss 0.15426334 - time (sec): 14.59 - samples/sec: 2368.85 - lr: 0.000029 - momentum: 0.000000
2023-10-17 21:50:25,596 epoch 2 - iter 441/1476 - loss 0.14926787 - time (sec): 21.95 - samples/sec: 2327.63 - lr: 0.000029 - momentum: 0.000000
2023-10-17 21:50:32,544 epoch 2 - iter 588/1476 - loss 0.14462305 - time (sec): 28.90 - samples/sec: 2312.96 - lr: 0.000029 - momentum: 0.000000
2023-10-17 21:50:39,870 epoch 2 - iter 735/1476 - loss 0.13899207 - time (sec): 36.23 - samples/sec: 2322.65 - lr: 0.000028 - momentum: 0.000000
2023-10-17 21:50:47,131 epoch 2 - iter 882/1476 - loss 0.13780348 - time (sec): 43.49 - samples/sec: 2327.09 - lr: 0.000028 - momentum: 0.000000
2023-10-17 21:50:54,421 epoch 2 - iter 1029/1476 - loss 0.13394971 - time (sec): 50.78 - samples/sec: 2333.26 - lr: 0.000028 - momentum: 0.000000
2023-10-17 21:51:01,785 epoch 2 - iter 1176/1476 - loss 0.13121195 - time (sec): 58.14 - samples/sec: 2317.18 - lr: 0.000027 - momentum: 0.000000
2023-10-17 21:51:08,880 epoch 2 - iter 1323/1476 - loss 0.13009309 - time (sec): 65.24 - samples/sec: 2309.28 - lr: 0.000027 - momentum: 0.000000
2023-10-17 21:51:16,070 epoch 2 - iter 1470/1476 - loss 0.12888252 - time (sec): 72.43 - samples/sec: 2289.73 - lr: 0.000027 - momentum: 0.000000
2023-10-17 21:51:16,340 ----------------------------------------------------------------------------------------------------
2023-10-17 21:51:16,341 EPOCH 2 done: loss 0.1290 - lr: 0.000027
2023-10-17 21:51:27,700 DEV : loss 0.13118185102939606 - f1-score (micro avg)  0.8205
2023-10-17 21:51:27,731 saving best model
2023-10-17 21:51:28,302 ----------------------------------------------------------------------------------------------------
2023-10-17 21:51:35,230 epoch 3 - iter 147/1476 - loss 0.08428630 - time (sec): 6.93 - samples/sec: 2348.59 - lr: 0.000026 - momentum: 0.000000
2023-10-17 21:51:42,235 epoch 3 - iter 294/1476 - loss 0.09269462 - time (sec): 13.93 - samples/sec: 2356.80 - lr: 0.000026 - momentum: 0.000000
2023-10-17 21:51:49,369 epoch 3 - iter 441/1476 - loss 0.09367626 - time (sec): 21.07 - samples/sec: 2351.19 - lr: 0.000026 - momentum: 0.000000
2023-10-17 21:51:56,599 epoch 3 - iter 588/1476 - loss 0.09126280 - time (sec): 28.29 - samples/sec: 2348.58 - lr: 0.000025 - momentum: 0.000000
2023-10-17 21:52:03,877 epoch 3 - iter 735/1476 - loss 0.08799231 - time (sec): 35.57 - samples/sec: 2365.87 - lr: 0.000025 - momentum: 0.000000
2023-10-17 21:52:11,036 epoch 3 - iter 882/1476 - loss 0.09015570 - time (sec): 42.73 - samples/sec: 2357.46 - lr: 0.000025 - momentum: 0.000000
2023-10-17 21:52:18,050 epoch 3 - iter 1029/1476 - loss 0.08819344 - time (sec): 49.75 - samples/sec: 2327.38 - lr: 0.000024 - momentum: 0.000000
2023-10-17 21:52:25,561 epoch 3 - iter 1176/1476 - loss 0.08449557 - time (sec): 57.26 - samples/sec: 2335.19 - lr: 0.000024 - momentum: 0.000000
2023-10-17 21:52:32,715 epoch 3 - iter 1323/1476 - loss 0.08531470 - time (sec): 64.41 - samples/sec: 2330.10 - lr: 0.000024 - momentum: 0.000000
2023-10-17 21:52:39,597 epoch 3 - iter 1470/1476 - loss 0.08419234 - time (sec): 71.29 - samples/sec: 2325.31 - lr: 0.000023 - momentum: 0.000000
2023-10-17 21:52:39,874 ----------------------------------------------------------------------------------------------------
2023-10-17 21:52:39,874 EPOCH 3 done: loss 0.0843 - lr: 0.000023
2023-10-17 21:52:51,115 DEV : loss 0.16755998134613037 - f1-score (micro avg)  0.8279
2023-10-17 21:52:51,145 saving best model
2023-10-17 21:52:51,681 ----------------------------------------------------------------------------------------------------
2023-10-17 21:52:58,821 epoch 4 - iter 147/1476 - loss 0.04505536 - time (sec): 7.14 - samples/sec: 2204.94 - lr: 0.000023 - momentum: 0.000000
2023-10-17 21:53:05,784 epoch 4 - iter 294/1476 - loss 0.05272174 - time (sec): 14.10 - samples/sec: 2309.05 - lr: 0.000023 - momentum: 0.000000
2023-10-17 21:53:13,188 epoch 4 - iter 441/1476 - loss 0.04762974 - time (sec): 21.50 - samples/sec: 2351.47 - lr: 0.000022 - momentum: 0.000000
2023-10-17 21:53:20,374 epoch 4 - iter 588/1476 - loss 0.04819030 - time (sec): 28.69 - samples/sec: 2305.59 - lr: 0.000022 - momentum: 0.000000
2023-10-17 21:53:27,155 epoch 4 - iter 735/1476 - loss 0.04871004 - time (sec): 35.47 - samples/sec: 2273.30 - lr: 0.000022 - momentum: 0.000000
2023-10-17 21:53:34,314 epoch 4 - iter 882/1476 - loss 0.05424007 - time (sec): 42.63 - samples/sec: 2263.05 - lr: 0.000021 - momentum: 0.000000
2023-10-17 21:53:42,060 epoch 4 - iter 1029/1476 - loss 0.05865699 - time (sec): 50.38 - samples/sec: 2308.28 - lr: 0.000021 - momentum: 0.000000
2023-10-17 21:53:49,002 epoch 4 - iter 1176/1476 - loss 0.05889975 - time (sec): 57.32 - samples/sec: 2287.65 - lr: 0.000021 - momentum: 0.000000
2023-10-17 21:53:56,692 epoch 4 - iter 1323/1476 - loss 0.05913293 - time (sec): 65.01 - samples/sec: 2290.30 - lr: 0.000020 - momentum: 0.000000
2023-10-17 21:54:03,864 epoch 4 - iter 1470/1476 - loss 0.05991994 - time (sec): 72.18 - samples/sec: 2298.06 - lr: 0.000020 - momentum: 0.000000
2023-10-17 21:54:04,127 ----------------------------------------------------------------------------------------------------
2023-10-17 21:54:04,127 EPOCH 4 done: loss 0.0598 - lr: 0.000020
2023-10-17 21:54:15,616 DEV : loss 0.17331284284591675 - f1-score (micro avg)  0.8302
2023-10-17 21:54:15,670 saving best model
2023-10-17 21:54:16,260 ----------------------------------------------------------------------------------------------------
2023-10-17 21:54:23,152 epoch 5 - iter 147/1476 - loss 0.03359008 - time (sec): 6.89 - samples/sec: 2257.85 - lr: 0.000020 - momentum: 0.000000
2023-10-17 21:54:30,014 epoch 5 - iter 294/1476 - loss 0.03632772 - time (sec): 13.75 - samples/sec: 2278.23 - lr: 0.000019 - momentum: 0.000000
2023-10-17 21:54:37,186 epoch 5 - iter 441/1476 - loss 0.03568507 - time (sec): 20.92 - samples/sec: 2316.55 - lr: 0.000019 - momentum: 0.000000
2023-10-17 21:54:44,249 epoch 5 - iter 588/1476 - loss 0.03760278 - time (sec): 27.99 - samples/sec: 2266.87 - lr: 0.000019 - momentum: 0.000000
2023-10-17 21:54:51,594 epoch 5 - iter 735/1476 - loss 0.04078622 - time (sec): 35.33 - samples/sec: 2287.15 - lr: 0.000018 - momentum: 0.000000
2023-10-17 21:54:59,589 epoch 5 - iter 882/1476 - loss 0.04255157 - time (sec): 43.33 - samples/sec: 2336.51 - lr: 0.000018 - momentum: 0.000000
2023-10-17 21:55:06,590 epoch 5 - iter 1029/1476 - loss 0.04205174 - time (sec): 50.33 - samples/sec: 2312.12 - lr: 0.000018 - momentum: 0.000000
2023-10-17 21:55:13,557 epoch 5 - iter 1176/1476 - loss 0.04118599 - time (sec): 57.29 - samples/sec: 2318.35 - lr: 0.000017 - momentum: 0.000000
2023-10-17 21:55:20,931 epoch 5 - iter 1323/1476 - loss 0.04130013 - time (sec): 64.67 - samples/sec: 2321.54 - lr: 0.000017 - momentum: 0.000000
2023-10-17 21:55:27,776 epoch 5 - iter 1470/1476 - loss 0.04011977 - time (sec): 71.51 - samples/sec: 2319.72 - lr: 0.000017 - momentum: 0.000000
2023-10-17 21:55:28,042 ----------------------------------------------------------------------------------------------------
2023-10-17 21:55:28,042 EPOCH 5 done: loss 0.0401 - lr: 0.000017
2023-10-17 21:55:39,436 DEV : loss 0.20299148559570312 - f1-score (micro avg)  0.8369
2023-10-17 21:55:39,472 saving best model
2023-10-17 21:55:40,011 ----------------------------------------------------------------------------------------------------
2023-10-17 21:55:47,241 epoch 6 - iter 147/1476 - loss 0.02601882 - time (sec): 7.22 - samples/sec: 2381.67 - lr: 0.000016 - momentum: 0.000000
2023-10-17 21:55:54,128 epoch 6 - iter 294/1476 - loss 0.02904149 - time (sec): 14.11 - samples/sec: 2285.03 - lr: 0.000016 - momentum: 0.000000
2023-10-17 21:56:01,426 epoch 6 - iter 441/1476 - loss 0.02853494 - time (sec): 21.41 - samples/sec: 2257.19 - lr: 0.000016 - momentum: 0.000000
2023-10-17 21:56:08,396 epoch 6 - iter 588/1476 - loss 0.02496954 - time (sec): 28.38 - samples/sec: 2243.92 - lr: 0.000015 - momentum: 0.000000
2023-10-17 21:56:15,336 epoch 6 - iter 735/1476 - loss 0.02547030 - time (sec): 35.32 - samples/sec: 2262.51 - lr: 0.000015 - momentum: 0.000000
2023-10-17 21:56:22,689 epoch 6 - iter 882/1476 - loss 0.02698140 - time (sec): 42.67 - samples/sec: 2278.19 - lr: 0.000015 - momentum: 0.000000
2023-10-17 21:56:30,040 epoch 6 - iter 1029/1476 - loss 0.02674758 - time (sec): 50.02 - samples/sec: 2278.13 - lr: 0.000014 - momentum: 0.000000
2023-10-17 21:56:37,097 epoch 6 - iter 1176/1476 - loss 0.02770049 - time (sec): 57.08 - samples/sec: 2283.56 - lr: 0.000014 - momentum: 0.000000
2023-10-17 21:56:44,374 epoch 6 - iter 1323/1476 - loss 0.02898319 - time (sec): 64.36 - samples/sec: 2291.76 - lr: 0.000014 - momentum: 0.000000
2023-10-17 21:56:51,525 epoch 6 - iter 1470/1476 - loss 0.02874026 - time (sec): 71.51 - samples/sec: 2288.88 - lr: 0.000013 - momentum: 0.000000
2023-10-17 21:56:52,143 ----------------------------------------------------------------------------------------------------
2023-10-17 21:56:52,144 EPOCH 6 done: loss 0.0305 - lr: 0.000013
2023-10-17 21:57:03,761 DEV : loss 0.20546814799308777 - f1-score (micro avg)  0.8283
2023-10-17 21:57:03,799 ----------------------------------------------------------------------------------------------------
2023-10-17 21:57:11,091 epoch 7 - iter 147/1476 - loss 0.01863009 - time (sec): 7.29 - samples/sec: 2273.51 - lr: 0.000013 - momentum: 0.000000
2023-10-17 21:57:18,293 epoch 7 - iter 294/1476 - loss 0.01506715 - time (sec): 14.49 - samples/sec: 2309.46 - lr: 0.000013 - momentum: 0.000000
2023-10-17 21:57:25,362 epoch 7 - iter 441/1476 - loss 0.01637533 - time (sec): 21.56 - samples/sec: 2274.18 - lr: 0.000012 - momentum: 0.000000
2023-10-17 21:57:32,712 epoch 7 - iter 588/1476 - loss 0.01718266 - time (sec): 28.91 - samples/sec: 2305.57 - lr: 0.000012 - momentum: 0.000000
2023-10-17 21:57:39,788 epoch 7 - iter 735/1476 - loss 0.01626465 - time (sec): 35.99 - samples/sec: 2311.05 - lr: 0.000012 - momentum: 0.000000
2023-10-17 21:57:47,342 epoch 7 - iter 882/1476 - loss 0.01727661 - time (sec): 43.54 - samples/sec: 2277.66 - lr: 0.000011 - momentum: 0.000000
2023-10-17 21:57:54,472 epoch 7 - iter 1029/1476 - loss 0.01684576 - time (sec): 50.67 - samples/sec: 2294.87 - lr: 0.000011 - momentum: 0.000000
2023-10-17 21:58:01,562 epoch 7 - iter 1176/1476 - loss 0.01900031 - time (sec): 57.76 - samples/sec: 2293.35 - lr: 0.000011 - momentum: 0.000000
2023-10-17 21:58:09,016 epoch 7 - iter 1323/1476 - loss 0.01887086 - time (sec): 65.22 - samples/sec: 2305.29 - lr: 0.000010 - momentum: 0.000000
2023-10-17 21:58:16,034 epoch 7 - iter 1470/1476 - loss 0.01884465 - time (sec): 72.23 - samples/sec: 2292.59 - lr: 0.000010 - momentum: 0.000000
2023-10-17 21:58:16,349 ----------------------------------------------------------------------------------------------------
2023-10-17 21:58:16,349 EPOCH 7 done: loss 0.0188 - lr: 0.000010
2023-10-17 21:58:28,137 DEV : loss 0.20466740429401398 - f1-score (micro avg)  0.8393
2023-10-17 21:58:28,183 saving best model
2023-10-17 21:58:28,790 ----------------------------------------------------------------------------------------------------
2023-10-17 21:58:36,102 epoch 8 - iter 147/1476 - loss 0.01243626 - time (sec): 7.31 - samples/sec: 2301.24 - lr: 0.000010 - momentum: 0.000000
2023-10-17 21:58:43,165 epoch 8 - iter 294/1476 - loss 0.01391050 - time (sec): 14.37 - samples/sec: 2379.34 - lr: 0.000009 - momentum: 0.000000
2023-10-17 21:58:50,392 epoch 8 - iter 441/1476 - loss 0.01500665 - time (sec): 21.60 - samples/sec: 2397.81 - lr: 0.000009 - momentum: 0.000000
2023-10-17 21:58:57,536 epoch 8 - iter 588/1476 - loss 0.01378980 - time (sec): 28.74 - samples/sec: 2400.67 - lr: 0.000009 - momentum: 0.000000
2023-10-17 21:59:04,538 epoch 8 - iter 735/1476 - loss 0.01391589 - time (sec): 35.75 - samples/sec: 2360.66 - lr: 0.000008 - momentum: 0.000000
2023-10-17 21:59:11,626 epoch 8 - iter 882/1476 - loss 0.01343908 - time (sec): 42.83 - samples/sec: 2330.48 - lr: 0.000008 - momentum: 0.000000
2023-10-17 21:59:18,850 epoch 8 - iter 1029/1476 - loss 0.01351983 - time (sec): 50.06 - samples/sec: 2331.07 - lr: 0.000008 - momentum: 0.000000
2023-10-17 21:59:25,750 epoch 8 - iter 1176/1476 - loss 0.01341649 - time (sec): 56.96 - samples/sec: 2314.96 - lr: 0.000007 - momentum: 0.000000
2023-10-17 21:59:32,657 epoch 8 - iter 1323/1476 - loss 0.01314697 - time (sec): 63.87 - samples/sec: 2309.97 - lr: 0.000007 - momentum: 0.000000
2023-10-17 21:59:40,165 epoch 8 - iter 1470/1476 - loss 0.01308090 - time (sec): 71.37 - samples/sec: 2324.00 - lr: 0.000007 - momentum: 0.000000
2023-10-17 21:59:40,440 ----------------------------------------------------------------------------------------------------
2023-10-17 21:59:40,440 EPOCH 8 done: loss 0.0130 - lr: 0.000007
2023-10-17 21:59:52,612 DEV : loss 0.20943744480609894 - f1-score (micro avg)  0.8488
2023-10-17 21:59:52,650 saving best model
2023-10-17 21:59:53,234 ----------------------------------------------------------------------------------------------------
2023-10-17 22:00:00,328 epoch 9 - iter 147/1476 - loss 0.00953557 - time (sec): 7.09 - samples/sec: 2370.87 - lr: 0.000006 - momentum: 0.000000
2023-10-17 22:00:08,201 epoch 9 - iter 294/1476 - loss 0.00763867 - time (sec): 14.96 - samples/sec: 2348.79 - lr: 0.000006 - momentum: 0.000000
2023-10-17 22:00:15,710 epoch 9 - iter 441/1476 - loss 0.01052035 - time (sec): 22.47 - samples/sec: 2390.84 - lr: 0.000006 - momentum: 0.000000
2023-10-17 22:00:23,177 epoch 9 - iter 588/1476 - loss 0.01054438 - time (sec): 29.94 - samples/sec: 2405.81 - lr: 0.000005 - momentum: 0.000000
2023-10-17 22:00:30,492 epoch 9 - iter 735/1476 - loss 0.01163723 - time (sec): 37.26 - samples/sec: 2371.56 - lr: 0.000005 - momentum: 0.000000
2023-10-17 22:00:37,497 epoch 9 - iter 882/1476 - loss 0.01067846 - time (sec): 44.26 - samples/sec: 2352.64 - lr: 0.000005 - momentum: 0.000000
2023-10-17 22:00:44,690 epoch 9 - iter 1029/1476 - loss 0.00995912 - time (sec): 51.45 - samples/sec: 2338.83 - lr: 0.000004 - momentum: 0.000000
2023-10-17 22:00:52,032 epoch 9 - iter 1176/1476 - loss 0.00976714 - time (sec): 58.79 - samples/sec: 2306.27 - lr: 0.000004 - momentum: 0.000000
2023-10-17 22:00:59,128 epoch 9 - iter 1323/1476 - loss 0.00967883 - time (sec): 65.89 - samples/sec: 2286.15 - lr: 0.000004 - momentum: 0.000000
2023-10-17 22:01:05,985 epoch 9 - iter 1470/1476 - loss 0.00946124 - time (sec): 72.75 - samples/sec: 2279.57 - lr: 0.000003 - momentum: 0.000000
2023-10-17 22:01:06,248 ----------------------------------------------------------------------------------------------------
2023-10-17 22:01:06,248 EPOCH 9 done: loss 0.0094 - lr: 0.000003
2023-10-17 22:01:17,704 DEV : loss 0.21988801658153534 - f1-score (micro avg)  0.8454
2023-10-17 22:01:17,736 ----------------------------------------------------------------------------------------------------
2023-10-17 22:01:24,951 epoch 10 - iter 147/1476 - loss 0.00447608 - time (sec): 7.21 - samples/sec: 2374.08 - lr: 0.000003 - momentum: 0.000000
2023-10-17 22:01:32,255 epoch 10 - iter 294/1476 - loss 0.00883325 - time (sec): 14.52 - samples/sec: 2369.45 - lr: 0.000003 - momentum: 0.000000
2023-10-17 22:01:39,367 epoch 10 - iter 441/1476 - loss 0.00766936 - time (sec): 21.63 - samples/sec: 2332.40 - lr: 0.000002 - momentum: 0.000000
2023-10-17 22:01:46,573 epoch 10 - iter 588/1476 - loss 0.00647105 - time (sec): 28.84 - samples/sec: 2299.01 - lr: 0.000002 - momentum: 0.000000
2023-10-17 22:01:53,832 epoch 10 - iter 735/1476 - loss 0.00639483 - time (sec): 36.10 - samples/sec: 2309.00 - lr: 0.000002 - momentum: 0.000000
2023-10-17 22:02:00,794 epoch 10 - iter 882/1476 - loss 0.00613195 - time (sec): 43.06 - samples/sec: 2293.47 - lr: 0.000001 - momentum: 0.000000
2023-10-17 22:02:07,987 epoch 10 - iter 1029/1476 - loss 0.00564404 - time (sec): 50.25 - samples/sec: 2298.22 - lr: 0.000001 - momentum: 0.000000
2023-10-17 22:02:15,173 epoch 10 - iter 1176/1476 - loss 0.00570421 - time (sec): 57.44 - samples/sec: 2280.26 - lr: 0.000001 - momentum: 0.000000
2023-10-17 22:02:22,909 epoch 10 - iter 1323/1476 - loss 0.00608918 - time (sec): 65.17 - samples/sec: 2317.76 - lr: 0.000000 - momentum: 0.000000
2023-10-17 22:02:29,700 epoch 10 - iter 1470/1476 - loss 0.00720383 - time (sec): 71.96 - samples/sec: 2304.00 - lr: 0.000000 - momentum: 0.000000
2023-10-17 22:02:29,971 ----------------------------------------------------------------------------------------------------
2023-10-17 22:02:29,971 EPOCH 10 done: loss 0.0072 - lr: 0.000000
2023-10-17 22:02:41,352 DEV : loss 0.2181602418422699 - f1-score (micro avg)  0.8512
2023-10-17 22:02:41,382 saving best model
2023-10-17 22:02:42,401 ----------------------------------------------------------------------------------------------------
2023-10-17 22:02:42,402 Loading model from best epoch ...
2023-10-17 22:02:43,873 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod
2023-10-17 22:02:50,897 
Results:
- F-score (micro) 0.816
- F-score (macro) 0.7265
- Accuracy 0.7086

By class:
              precision    recall  f1-score   support

         loc     0.8704    0.8846    0.8775       858
        pers     0.7743    0.8305    0.8014       537
         org     0.6000    0.5909    0.5954       132
        prod     0.7377    0.7377    0.7377        61
        time     0.5806    0.6667    0.6207        54

   micro avg     0.8019    0.8307    0.8160      1642
   macro avg     0.7126    0.7421    0.7265      1642
weighted avg     0.8028    0.8307    0.8163      1642

2023-10-17 22:02:50,897 ----------------------------------------------------------------------------------------------------