End of training

README.md

@@ -3,9 +3,10 @@ library_name: transformers
 license: apache-2.0
 base_model: michiyasunaga/BioLinkBERT-base
 tags:
+- token-classification
 - generated_from_trainer
 datasets:
-- drugtemist-en-9-ner
+- Rodrigo1771/drugtemist-en-9-ner
 metrics:
 - precision
 - recall
@@ -18,24 +19,24 @@ model-index:
       name: Token Classification
       type: token-classification
     dataset:
-      name: drugtemist-en-9-ner
-      type: drugtemist-en-9-ner
+      name: Rodrigo1771/drugtemist-en-9-ner
+      type: Rodrigo1771/drugtemist-en-9-ner
       config: DrugTEMIST English NER
       split: validation
       args: DrugTEMIST English NER
     metrics:
     - name: Precision
       type: precision
-      value: 0.924860853432282
+      value: 0.9297597042513863
     - name: Recall
       type: recall
-      value: 0.9291705498602051
+      value: 0.9375582479030755
     - name: F1
       type: f1
-      value: 0.9270106927010694
+      value: 0.9336426914153132
     - name: Accuracy
       type: accuracy
-      value: 0.9986534758462869
+      value: 0.9987999888371054
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,13 +44,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output
 
-This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on the drugtemist-en-9-ner dataset.
+This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on the Rodrigo1771/drugtemist-en-9-ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0071
-- Precision: 0.9249
-- Recall: 0.9292
-- F1: 0.9270
-- Accuracy: 0.9987
+- Loss: 0.0046
+- Precision: 0.9298
+- Recall: 0.9376
+- F1: 0.9336
+- Accuracy: 0.9988
 
 ## Model description
 

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9987999888371054,
+    "eval_f1": 0.9336426914153132,
+    "eval_loss": 0.004605981521308422,
+    "eval_precision": 0.9297597042513863,
+    "eval_recall": 0.9375582479030755,
+    "eval_runtime": 13.2724,
+    "eval_samples": 6946,
+    "eval_samples_per_second": 523.342,
+    "eval_steps_per_second": 65.474,
+    "predict_accuracy": 0.9986882326988529,
+    "predict_f1": 0.9205633802816902,
+    "predict_loss": 0.004973105154931545,
+    "predict_precision": 0.8938730853391685,
+    "predict_recall": 0.9488966318234611,
+    "predict_runtime": 25.752,
+    "predict_samples_per_second": 571.412,
+    "predict_steps_per_second": 71.451,
+    "total_flos": 1.1151464037050934e+16,
+    "train_loss": 0.002938754050150616,
+    "train_runtime": 1039.0289,
+    "train_samples": 27967,
+    "train_samples_per_second": 269.165,
+    "train_steps_per_second": 4.206
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9987999888371054,
+    "eval_f1": 0.9336426914153132,
+    "eval_loss": 0.004605981521308422,
+    "eval_precision": 0.9297597042513863,
+    "eval_recall": 0.9375582479030755,
+    "eval_runtime": 13.2724,
+    "eval_samples": 6946,
+    "eval_samples_per_second": 523.342,
+    "eval_steps_per_second": 65.474
+}

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_accuracy": 0.9986882326988529,
+    "predict_f1": 0.9205633802816902,
+    "predict_loss": 0.004973105154931545,
+    "predict_precision": 0.8938730853391685,
+    "predict_recall": 0.9488966318234611,
+    "predict_runtime": 25.752,
+    "predict_samples_per_second": 571.412,
+    "predict_steps_per_second": 71.451
+}

tb/events.out.tfevents.1725570294.c3806e32a2f8.1237.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8921f39abba2cbc517633b1fc318ac0654a4e096e416d5ce4dde888385d854c5
+size 560

train.log

@@ -1280,3 +1280,51 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 {'eval_loss': 0.00707679707556963, 'eval_precision': 0.924860853432282, 'eval_recall': 0.9291705498602051, 'eval_f1': 0.9270106927010694, 'eval_accuracy': 0.9986534758462869, 'eval_runtime': 13.4189, 'eval_samples_per_second': 517.629, 'eval_steps_per_second': 64.76, 'epoch': 10.0}
 {'train_runtime': 1039.0289, 'train_samples_per_second': 269.165, 'train_steps_per_second': 4.206, 'train_loss': 0.002938754050150616, 'epoch': 10.0}
 
+***** train metrics *****
+  epoch                    =       10.0
+  total_flos               = 10385610GF
+  train_loss               =     0.0029
+  train_runtime            = 0:17:19.02
+  train_samples            =      27967
+  train_samples_per_second =    269.165
+  train_steps_per_second   =      4.206
+09/05/2024 21:04:40 - INFO - __main__ -   *** Evaluate ***
+[INFO|trainer.py:811] 2024-09-05 21:04:40,816 >> The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: id, tokens, ner_tags. If id, tokens, ner_tags are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3819] 2024-09-05 21:04:40,819 >> 
+***** Running Evaluation *****
+[INFO|trainer.py:3821] 2024-09-05 21:04:40,819 >>   Num examples = 6946
+[INFO|trainer.py:3824] 2024-09-05 21:04:40,819 >>   Batch size = 8
+
  0%|          | 0/869 [00:00<?, ?it/s]
  1%|          | 10/869 [00:00<00:08, 98.30it/s]
  2%|▏         | 20/869 [00:00<00:09, 88.58it/s]
  3%|▎         | 29/869 [00:00<00:09, 88.26it/s]
  4%|▍         | 38/869 [00:00<00:09, 88.48it/s]
  6%|▌         | 48/869 [00:00<00:09, 90.80it/s]
  7%|▋         | 58/869 [00:00<00:08, 91.97it/s]
  8%|▊         | 68/869 [00:00<00:08, 90.67it/s]
  9%|▉         | 78/869 [00:00<00:08, 90.51it/s]
 10%|█         | 89/869 [00:00<00:08, 93.51it/s]
 12%|█▏        | 100/869 [00:01<00:08, 95.79it/s]
 13%|█▎        | 110/869 [00:01<00:08, 94.19it/s]
 14%|█▍        | 120/869 [00:01<00:07, 94.41it/s]
 15%|█▍        | 130/869 [00:01<00:07, 93.70it/s]
 16%|█▌        | 140/869 [00:01<00:07, 94.25it/s]
 17%|█▋        | 150/869 [00:01<00:07, 91.67it/s]
 18%|█▊        | 160/869 [00:01<00:07, 90.44it/s]
 20%|█▉        | 170/869 [00:01<00:07, 88.93it/s]
 21%|██        | 179/869 [00:01<00:07, 88.51it/s]
 22%|██▏       | 189/869 [00:02<00:07, 90.19it/s]
 23%|██▎       | 199/869 [00:02<00:07, 89.37it/s]
 24%|██▍       | 209/869 [00:02<00:07, 90.40it/s]
 25%|██▌       | 219/869 [00:02<00:07, 92.85it/s]
 26%|██▋       | 229/869 [00:02<00:07, 90.28it/s]
 28%|██▊       | 239/869 [00:02<00:07, 87.08it/s]
 29%|██▊       | 248/869 [00:02<00:07, 82.72it/s]
 30%|██▉       | 258/869 [00:02<00:07, 86.16it/s]
 31%|███       | 267/869 [00:02<00:06, 86.93it/s]
 32%|███▏      | 276/869 [00:03<00:06, 87.45it/s]
 33%|███▎      | 285/869 [00:03<00:06, 87.83it/s]
 34%|███▍      | 295/869 [00:03<00:06, 88.99it/s]
 35%|███▍      | 304/869 [00:03<00:06, 87.61it/s]
 36%|███▌      | 313/869 [00:03<00:06, 86.93it/s]
 37%|███▋      | 322/869 [00:03<00:06, 85.96it/s]
 38%|███▊      | 332/869 [00:03<00:06, 88.73it/s]
 39%|███▉      | 341/869 [00:03<00:05, 88.78it/s]
 40%|████      | 350/869 [00:03<00:05, 87.18it/s]
 41%|████▏     | 360/869 [00:04<00:05, 90.49it/s]
 43%|████▎     | 370/869 [00:04<00:05, 92.05it/s]
 44%|████▎     | 380/869 [00:04<00:05, 89.42it/s]
 45%|████▍     | 389/869 [00:04<00:05, 86.57it/s]
 46%|████▌     | 399/869 [00:04<00:05, 89.33it/s]
 47%|████▋     | 409/869 [00:04<00:05, 91.90it/s]
 48%|████▊     | 419/869 [00:04<00:04, 92.49it/s]
 49%|████▉     | 429/869 [00:04<00:04, 92.52it/s]
 51%|█████     | 439/869 [00:04<00:04, 90.46it/s]
 52%|█████▏    | 449/869 [00:04<00:04, 90.02it/s]
 53%|█████▎    | 459/869 [00:05<00:04, 90.68it/s]
 54%|█████▍    | 469/869 [00:05<00:04, 91.56it/s]
 55%|█████▌    | 480/869 [00:05<00:04, 94.03it/s]
 56%|█████▋    | 490/869 [00:05<00:04, 91.51it/s]
 58%|█████▊    | 500/869 [00:05<00:03, 92.57it/s]
 59%|█████▊    | 510/869 [00:05<00:03, 90.78it/s]
 60%|█████▉    | 520/869 [00:05<00:03, 93.29it/s]
 61%|██████    | 530/869 [00:05<00:03, 88.69it/s]
 62%|██████▏   | 539/869 [00:05<00:03, 88.40it/s]
 63%|██████▎   | 549/869 [00:06<00:03, 90.30it/s]
 64%|██████▍   | 559/869 [00:06<00:03, 90.75it/s]
 65%|██████▌   | 569/869 [00:06<00:03, 90.68it/s]
 67%|██████▋   | 579/869 [00:06<00:03, 92.01it/s]
 68%|██████▊   | 589/869 [00:06<00:03, 90.49it/s]
 69%|██████▉   | 599/869 [00:06<00:02, 92.77it/s]
 70%|███████   | 609/869 [00:06<00:02, 93.32it/s]
 71%|███████   | 619/869 [00:06<00:02, 92.00it/s]
 72%|███████▏  | 629/869 [00:06<00:02, 92.91it/s]
 74%|███████▎  | 639/869 [00:07<00:02, 91.85it/s]
 75%|███████▍  | 649/869 [00:07<00:02, 93.27it/s]
 76%|███████▌  | 659/869 [00:07<00:02, 92.46it/s]
 77%|███████▋  | 670/869 [00:07<00:02, 94.83it/s]
 78%|███████▊  | 680/869 [00:07<00:01, 95.72it/s]
 79%|███████▉  | 690/869 [00:07<00:02, 88.88it/s]
 81%|████████  | 700/869 [00:07<00:01, 90.68it/s]
 82%|████████▏ | 710/869 [00:07<00:01, 91.37it/s]
 83%|████████▎ | 720/869 [00:07<00:01, 90.58it/s]
 84%|████████▍ | 730/869 [00:08<00:01, 92.01it/s]
 85%|████████▌ | 740/869 [00:08<00:01, 91.19it/s]
 86%|████████▋ | 750/869 [00:08<00:01, 91.65it/s]
 87%|████████▋ | 760/869 [00:08<00:01, 92.57it/s]
 89%|████████▊ | 770/869 [00:08<00:01, 90.79it/s]
 90%|████████▉ | 780/869 [00:08<00:01, 85.70it/s]
 91%|█████████ | 790/869 [00:08<00:00, 89.02it/s]
 92%|█████████▏| 800/869 [00:08<00:00, 90.94it/s]
 93%|█████████▎| 810/869 [00:08<00:00, 92.20it/s]
 94%|█████████▍| 820/869 [00:09<00:00, 92.22it/s]
 96%|█████████▌| 830/869 [00:09<00:00, 93.70it/s]
 97%|█████████▋| 840/869 [00:09<00:00, 93.56it/s]
 98%|█████████▊| 850/869 [00:09<00:00, 95.06it/s]
 99%|█████████▉| 860/869 [00:09<00:00, 92.13it/s]
+***** eval metrics *****
+  epoch                   =       10.0
+  eval_accuracy           =     0.9988
+  eval_f1                 =     0.9336
+  eval_loss               =     0.0046
+  eval_precision          =     0.9298
+  eval_recall             =     0.9376
+  eval_runtime            = 0:00:13.27
+  eval_samples            =       6946
+  eval_samples_per_second =    523.342
+  eval_steps_per_second   =     65.474
+09/05/2024 21:04:54 - INFO - __main__ -   *** Predict ***
+[INFO|trainer.py:811] 2024-09-05 21:04:54,097 >> The following columns in the test set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: id, tokens, ner_tags. If id, tokens, ner_tags are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3819] 2024-09-05 21:04:54,099 >> 
+***** Running Prediction *****
+[INFO|trainer.py:3821] 2024-09-05 21:04:54,099 >>   Num examples = 14715
+[INFO|trainer.py:3824] 2024-09-05 21:04:54,099 >>   Batch size = 8
+
  0%|          | 0/1840 [00:00<?, ?it/s]
  1%|          | 11/1840 [00:00<00:18, 100.66it/s]
  1%|          | 22/1840 [00:00<00:20, 87.32it/s] 
  2%|▏         | 32/1840 [00:00<00:20, 89.81it/s]
  2%|▏         | 42/1840 [00:00<00:19, 91.46it/s]
  3%|▎         | 52/1840 [00:00<00:19, 92.87it/s]
  3%|▎         | 62/1840 [00:00<00:19, 90.69it/s]
  4%|▍         | 72/1840 [00:00<00:19, 91.57it/s]
  4%|▍         | 82/1840 [00:00<00:18, 92.80it/s]
  5%|▌         | 92/1840 [00:01<00:19, 91.99it/s]
  6%|▌         | 102/1840 [00:01<00:18, 93.57it/s]
  6%|▌         | 112/1840 [00:01<00:18, 93.70it/s]
  7%|▋         | 122/1840 [00:01<00:18, 92.44it/s]
  7%|▋         | 132/1840 [00:01<00:18, 91.33it/s]
  8%|▊         | 142/1840 [00:01<00:18, 91.08it/s]
  8%|▊         | 152/1840 [00:01<00:18, 92.76it/s]
  9%|▉         | 162/1840 [00:01<00:18, 89.12it/s]
  9%|▉         | 172/1840 [00:01<00:18, 91.00it/s]
 10%|▉         | 182/1840 [00:01<00:17, 93.30it/s]
 10%|█         | 192/1840 [00:02<00:17, 93.99it/s]
 11%|█         | 202/1840 [00:02<00:17, 92.71it/s]
 12%|█▏        | 212/1840 [00:02<00:17, 92.90it/s]
 12%|█▏        | 222/1840 [00:02<00:17, 93.02it/s]
 13%|█▎        | 232/1840 [00:02<00:17, 90.92it/s]
 13%|█▎        | 242/1840 [00:02<00:17, 89.04it/s]
 14%|█▎        | 251/1840 [00:02<00:17, 89.29it/s]
 14%|█▍        | 261/1840 [00:02<00:17, 90.53it/s]
 15%|█▍        | 271/1840 [00:02<00:17, 92.01it/s]
 15%|█▌        | 282/1840 [00:03<00:16, 94.95it/s]
 16%|█▌        | 292/1840 [00:03<00:16, 94.44it/s]
 16%|█▋        | 302/1840 [00:03<00:16, 95.06it/s]
 17%|█▋        | 312/1840 [00:03<00:16, 94.21it/s]
 18%|█▊        | 322/1840 [00:03<00:16, 94.83it/s]
 18%|█▊        | 332/1840 [00:03<00:15, 95.15it/s]
 19%|█▊        | 343/1840 [00:03<00:15, 96.70it/s]
 19%|█▉        | 353/1840 [00:03<00:15, 93.88it/s]
 20%|█▉        | 363/1840 [00:03<00:15, 94.46it/s]
 20%|██        | 374/1840 [00:04<00:15, 96.46it/s]
 21%|██        | 384/1840 [00:04<00:15, 96.58it/s]
 21%|██▏       | 394/1840 [00:04<00:15, 94.52it/s]
 22%|██▏       | 404/1840 [00:04<00:15, 93.54it/s]
 22%|██▎       | 414/1840 [00:04<00:15, 91.33it/s]
 23%|██▎       | 424/1840 [00:04<00:15, 90.95it/s]
 24%|██▎       | 434/1840 [00:04<00:15, 90.46it/s]
 24%|██▍       | 444/1840 [00:04<00:15, 92.37it/s]
 25%|██▍       | 454/1840 [00:04<00:14, 92.51it/s]
 25%|██▌       | 464/1840 [00:05<00:14, 93.47it/s]
 26%|██▌       | 474/1840 [00:05<00:14, 92.31it/s]
 26%|██▋       | 484/1840 [00:05<00:14, 90.63it/s]
 27%|██▋       | 494/1840 [00:05<00:14, 90.70it/s]
 27%|██▋       | 504/1840 [00:05<00:14, 91.02it/s]
 28%|██▊       | 514/1840 [00:05<00:14, 93.08it/s]
 28%|██▊       | 524/1840 [00:05<00:13, 94.07it/s]
 29%|██▉       | 534/1840 [00:05<00:13, 94.78it/s]
 30%|██▉       | 544/1840 [00:05<00:13, 93.68it/s]
 30%|███       | 554/1840 [00:05<00:13, 94.96it/s]
 31%|███       | 564/1840 [00:06<00:13, 94.31it/s]
 31%|███       | 574/1840 [00:06<00:13, 95.70it/s]
 32%|███▏      | 584/1840 [00:06<00:13, 96.46it/s]
 32%|███▏      | 594/1840 [00:06<00:13, 93.35it/s]
 33%|███▎      | 604/1840 [00:06<00:13, 91.14it/s]
 33%|███▎      | 614/1840 [00:06<00:13, 92.08it/s]
 34%|███▍      | 624/1840 [00:06<00:13, 90.07it/s]
 34%|███▍      | 634/1840 [00:06<00:13, 92.36it/s]
 35%|███▌      | 644/1840 [00:06<00:12, 94.27it/s]
 36%|███▌      | 654/1840 [00:07<00:12, 95.15it/s]
 36%|███▌      | 664/1840 [00:07<00:12, 91.92it/s]
 37%|███▋      | 675/1840 [00:07<00:12, 94.52it/s]
 37%|███▋      | 685/1840 [00:07<00:12, 93.52it/s]
 38%|███▊      | 695/1840 [00:07<00:12, 94.01it/s]
 38%|███▊      | 705/1840 [00:07<00:11, 95.00it/s]
 39%|███▉      | 715/1840 [00:07<00:11, 95.08it/s]
 39%|███▉      | 726/1840 [00:07<00:11, 97.47it/s]
 40%|████      | 737/1840 [00:07<00:11, 98.74it/s]
 41%|████      | 747/1840 [00:08<00:11, 97.58it/s]
 41%|████      | 758/1840 [00:08<00:10, 99.05it/s]
 42%|████▏     | 768/1840 [00:08<00:10, 98.35it/s]
 42%|████▏     | 778/1840 [00:08<00:10, 97.78it/s]
 43%|████▎     | 788/1840 [00:08<00:10, 96.12it/s]
 43%|████▎     | 798/1840 [00:08<00:10, 96.37it/s]
 44%|████▍     | 808/1840 [00:08<00:10, 94.99it/s]
 44%|████▍     | 818/1840 [00:08<00:10, 95.70it/s]
 45%|████▌     | 828/1840 [00:08<00:10, 95.46it/s]
 46%|████▌     | 838/1840 [00:08<00:10, 96.12it/s]
 46%|████▌     | 848/1840 [00:09<00:10, 94.62it/s]
 47%|████▋     | 859/1840 [00:09<00:10, 96.32it/s]
 47%|████▋     | 869/1840 [00:09<00:10, 96.37it/s]
 48%|████▊     | 879/1840 [00:09<00:10, 94.02it/s]
 48%|████▊     | 889/1840 [00:09<00:10, 93.01it/s]
 49%|████▉     | 899/1840 [00:09<00:10, 93.14it/s]
 49%|████▉     | 910/1840 [00:09<00:09, 95.61it/s]
 50%|█████     | 920/1840 [00:09<00:09, 96.63it/s]
 51%|█████     | 930/1840 [00:09<00:09, 96.96it/s]
 51%|█████     | 940/1840 [00:10<00:09, 94.21it/s]
 52%|█████▏    | 950/1840 [00:10<00:09, 91.67it/s]
 52%|█████▏    | 960/1840 [00:10<00:10, 86.59it/s]
 53%|█████▎    | 970/1840 [00:10<00:09, 89.43it/s]
 53%|█████▎    | 980/1840 [00:10<00:09, 91.22it/s]
 54%|█████▍    | 990/1840 [00:10<00:09, 92.21it/s]
 54%|█████▍    | 1000/1840 [00:10<00:09, 92.68it/s]
 55%|█████▍    | 1010/1840 [00:10<00:08, 93.86it/s]
 55%|█████▌    | 1020/1840 [00:10<00:08, 95.17it/s]
 56%|█████▌    | 1031/1840 [00:11<00:08, 96.74it/s]
 57%|█████▋    | 1041/1840 [00:11<00:08, 94.91it/s]
 57%|█████▋    | 1051/1840 [00:11<00:08, 95.37it/s]
 58%|█████▊    | 1061/1840 [00:11<00:08, 94.87it/s]
 58%|█████▊    | 1071/1840 [00:11<00:08, 95.93it/s]
 59%|█████▉    | 1082/1840 [00:11<00:07, 97.63it/s]
 59%|█████▉    | 1092/1840 [00:11<00:07, 96.67it/s]
 60%|█████▉    | 1102/1840 [00:11<00:07, 95.77it/s]
 60%|██████    | 1112/1840 [00:11<00:07, 95.81it/s]
 61%|██████    | 1122/1840 [00:11<00:07, 95.09it/s]
 62%|██████▏   | 1132/1840 [00:12<00:07, 94.79it/s]
 62%|██████▏   | 1142/1840 [00:12<00:07, 94.93it/s]
 63%|██████▎   | 1152/1840 [00:12<00:07, 95.37it/s]
 63%|██████▎   | 1162/1840 [00:12<00:07, 95.48it/s]
 64%|██████▎   | 1172/1840 [00:12<00:07, 92.83it/s]
 64%|██████▍   | 1182/1840 [00:12<00:07, 93.70it/s]
 65%|██████▍   | 1192/1840 [00:12<00:07, 91.77it/s]
 65%|██████▌   | 1202/1840 [00:12<00:06, 93.80it/s]
 66%|██████▌   | 1212/1840 [00:12<00:06, 93.86it/s]
 66%|██████▋   | 1222/1840 [00:13<00:06, 92.60it/s]
 67%|██████▋   | 1232/1840 [00:13<00:06, 92.08it/s]
 68%|██████▊   | 1242/1840 [00:13<00:06, 93.89it/s]
 68%|██████▊   | 1252/1840 [00:13<00:06, 94.06it/s]
 69%|██████▊   | 1262/1840 [00:13<00:06, 92.09it/s]
 69%|██████▉   | 1272/1840 [00:13<00:06, 92.27it/s]
 70%|██████▉   | 1282/1840 [00:13<00:06, 92.93it/s]
 70%|███████   | 1292/1840 [00:13<00:05, 93.23it/s]
 71%|███████   | 1302/1840 [00:13<00:05, 94.53it/s]
 71%|███████▏  | 1313/1840 [00:14<00:05, 96.30it/s]
 72%|███████▏  | 1324/1840 [00:14<00:05, 97.65it/s]
 72%|███████▎  | 1334/1840 [00:14<00:05, 96.65it/s]
 73%|███████▎  | 1344/1840 [00:14<00:05, 96.78it/s]
 74%|███████▎  | 1354/1840 [00:14<00:05, 96.36it/s]
 74%|███████▍  | 1364/1840 [00:14<00:04, 96.05it/s]
 75%|███████▍  | 1374/1840 [00:14<00:04, 96.54it/s]
 75%|███████▌  | 1384/1840 [00:14<00:04, 95.78it/s]
 76%|███████▌  | 1394/1840 [00:14<00:04, 96.55it/s]
 76%|███████▋  | 1404/1840 [00:14<00:04, 96.13it/s]
 77%|███████▋  | 1415/1840 [00:15<00:04, 97.23it/s]
 78%|███████▊  | 1426/1840 [00:15<00:04, 98.32it/s]
 78%|███████▊  | 1436/1840 [00:15<00:04, 95.65it/s]
 79%|███████▊  | 1446/1840 [00:15<00:04, 92.20it/s]
 79%|███████▉  | 1456/1840 [00:15<00:04, 92.15it/s]
 80%|███████▉  | 1466/1840 [00:15<00:03, 93.93it/s]
 80%|████████  | 1476/1840 [00:15<00:03, 94.96it/s]
 81%|████████  | 1486/1840 [00:15<00:03, 92.39it/s]
 81%|████████▏ | 1496/1840 [00:15<00:03, 92.62it/s]
 82%|████████▏ | 1506/1840 [00:16<00:03, 90.94it/s]
 82%|████████▏ | 1516/1840 [00:16<00:03, 89.76it/s]
 83%|████████▎ | 1526/1840 [00:16<00:03, 92.31it/s]
 83%|████████▎ | 1536/1840 [00:16<00:03, 91.36it/s]
 84%|████████▍ | 1546/1840 [00:16<00:03, 91.31it/s]
 85%|████████▍ | 1556/1840 [00:16<00:03, 91.22it/s]
 85%|████████▌ | 1566/1840 [00:16<00:03, 90.24it/s]
 86%|████████▌ | 1576/1840 [00:16<00:02, 89.47it/s]
 86%|████████▌ | 1586/1840 [00:16<00:02, 90.91it/s]
 87%|████████▋ | 1596/1840 [00:17<00:02, 91.45it/s]
 87%|████████▋ | 1606/1840 [00:17<00:02, 92.23it/s]
 88%|████████▊ | 1616/1840 [00:17<00:02, 93.15it/s]
 88%|████████▊ | 1626/1840 [00:17<00:02, 92.75it/s]
 89%|████████▉ | 1636/1840 [00:17<00:02, 86.16it/s]
 89%|████████▉ | 1645/1840 [00:17<00:02, 86.13it/s]
 90%|████████▉ | 1655/1840 [00:17<00:02, 88.10it/s]
 90%|█████████ | 1665/1840 [00:17<00:01, 91.07it/s]
 91%|█████████ | 1675/1840 [00:17<00:01, 91.32it/s]
 92%|█████████▏| 1685/1840 [00:18<00:01, 92.00it/s]
 92%|█████████▏| 1695/1840 [00:18<00:01, 94.04it/s]
 93%|█████████▎| 1705/1840 [00:18<00:01, 92.60it/s]
 93%|█████████▎| 1715/1840 [00:18<00:01, 93.06it/s]
 94%|█████████▍| 1725/1840 [00:18<00:01, 94.15it/s]
 94%|█████████▍| 1735/1840 [00:18<00:01, 91.69it/s]
 95%|█████████▍| 1745/1840 [00:18<00:01, 93.98it/s]
 95%|█████████▌| 1755/1840 [00:18<00:00, 95.51it/s]
 96%|█████████▌| 1765/1840 [00:18<00:00, 96.50it/s]
 96%|█████████▋| 1775/1840 [00:18<00:00, 96.16it/s]
 97%|█████████▋| 1785/1840 [00:19<00:00, 95.98it/s]
 98%|█████████▊| 1795/1840 [00:19<00:00, 96.85it/s]
 98%|█████████▊| 1805/1840 [00:19<00:00, 96.83it/s]
 99%|█████████▊| 1815/1840 [00:19<00:00, 93.07it/s]
 99%|█████████▉| 1825/1840 [00:19<00:00, 94.73it/s]
+[INFO|trainer.py:3503] 2024-09-05 21:05:20,650 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-05 21:05:20,652 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-05 21:05:21,937 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-05 21:05:21,938 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-05 21:05:21,939 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+***** predict metrics *****
+  predict_accuracy           =     0.9987
+  predict_f1                 =     0.9206
+  predict_loss               =      0.005
+  predict_precision          =     0.8939
+  predict_recall             =     0.9489
+  predict_runtime            = 0:00:25.75
+  predict_samples_per_second =    571.412
+  predict_steps_per_second   =     71.451
+

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 1.1151464037050934e+16,
+    "train_loss": 0.002938754050150616,
+    "train_runtime": 1039.0289,
+    "train_samples": 27967,
+    "train_samples_per_second": 269.165,
+    "train_steps_per_second": 4.206
+}

trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.9336426914153132,
+  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-1311",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 4370,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9984720788100354,
+      "eval_f1": 0.9122645842903078,
+      "eval_loss": 0.004654619377106428,
+      "eval_precision": 0.8994565217391305,
+      "eval_recall": 0.9254426840633737,
+      "eval_runtime": 13.3719,
+      "eval_samples_per_second": 519.448,
+      "eval_steps_per_second": 64.987,
+      "step": 437
+    },
+    {
+      "epoch": 1.1441647597254005,
+      "grad_norm": 0.35407835245132446,
+      "learning_rate": 4.4279176201373e-05,
+      "loss": 0.0144,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9984511483827756,
+      "eval_f1": 0.9131627056672761,
+      "eval_loss": 0.005305842496454716,
+      "eval_precision": 0.8959641255605382,
+      "eval_recall": 0.9310344827586207,
+      "eval_runtime": 13.2738,
+      "eval_samples_per_second": 523.286,
+      "eval_steps_per_second": 65.467,
+      "step": 874
+    },
+    {
+      "epoch": 2.288329519450801,
+      "grad_norm": 0.008026196621358395,
+      "learning_rate": 3.8558352402745995e-05,
+      "loss": 0.0038,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9987999888371054,
+      "eval_f1": 0.9336426914153132,
+      "eval_loss": 0.004605981521308422,
+      "eval_precision": 0.9297597042513863,
+      "eval_recall": 0.9375582479030755,
+      "eval_runtime": 13.2443,
+      "eval_samples_per_second": 524.45,
+      "eval_steps_per_second": 65.613,
+      "step": 1311
+    },
+    {
+      "epoch": 3.4324942791762014,
+      "grad_norm": 0.13839516043663025,
+      "learning_rate": 3.2837528604119e-05,
+      "loss": 0.0022,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9985627773281612,
+      "eval_f1": 0.9223616922361693,
+      "eval_loss": 0.005482749082148075,
+      "eval_precision": 0.9202226345083488,
+      "eval_recall": 0.9245107176141659,
+      "eval_runtime": 13.4564,
+      "eval_samples_per_second": 516.186,
+      "eval_steps_per_second": 64.579,
+      "step": 1748
+    },
+    {
+      "epoch": 4.576659038901602,
+      "grad_norm": 0.01504958514124155,
+      "learning_rate": 2.7116704805491993e-05,
+      "loss": 0.0019,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9985627773281612,
+      "eval_f1": 0.9231477220432582,
+      "eval_loss": 0.005268561653792858,
+      "eval_precision": 0.9118181818181819,
+      "eval_recall": 0.934762348555452,
+      "eval_runtime": 13.2814,
+      "eval_samples_per_second": 522.986,
+      "eval_steps_per_second": 65.43,
+      "step": 2185
+    },
+    {
+      "epoch": 5.720823798627002,
+      "grad_norm": 0.11815565079450607,
+      "learning_rate": 2.139588100686499e-05,
+      "loss": 0.0014,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.998618591800854,
+      "eval_f1": 0.92243381328379,
+      "eval_loss": 0.005419280380010605,
+      "eval_precision": 0.9194444444444444,
+      "eval_recall": 0.9254426840633737,
+      "eval_runtime": 13.1103,
+      "eval_samples_per_second": 529.811,
+      "eval_steps_per_second": 66.284,
+      "step": 2622
+    },
+    {
+      "epoch": 6.864988558352403,
+      "grad_norm": 0.012974879704415798,
+      "learning_rate": 1.5675057208237986e-05,
+      "loss": 0.0009,
+      "step": 3000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9986255686099406,
+      "eval_f1": 0.9289055191768008,
+      "eval_loss": 0.007274709176272154,
+      "eval_precision": 0.9323943661971831,
+      "eval_recall": 0.9254426840633737,
+      "eval_runtime": 13.1693,
+      "eval_samples_per_second": 527.439,
+      "eval_steps_per_second": 65.987,
+      "step": 3059
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9986604526553735,
+      "eval_f1": 0.9297752808988765,
+      "eval_loss": 0.006545887794345617,
+      "eval_precision": 0.9341486359360301,
+      "eval_recall": 0.9254426840633737,
+      "eval_runtime": 13.1956,
+      "eval_samples_per_second": 526.386,
+      "eval_steps_per_second": 65.855,
+      "step": 3496
+    },
+    {
+      "epoch": 8.009153318077804,
+      "grad_norm": 0.0015736627392470837,
+      "learning_rate": 9.954233409610985e-06,
+      "loss": 0.0005,
+      "step": 3500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9986674294644602,
+      "eval_f1": 0.930905695611578,
+      "eval_loss": 0.006908744107931852,
+      "eval_precision": 0.9326473339569691,
+      "eval_recall": 0.9291705498602051,
+      "eval_runtime": 13.5052,
+      "eval_samples_per_second": 514.321,
+      "eval_steps_per_second": 64.346,
+      "step": 3933
+    },
+    {
+      "epoch": 9.153318077803204,
+      "grad_norm": 0.0005491800257004797,
+      "learning_rate": 4.233409610983982e-06,
+      "loss": 0.0004,
+      "step": 4000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9986534758462869,
+      "eval_f1": 0.9270106927010694,
+      "eval_loss": 0.00707679707556963,
+      "eval_precision": 0.924860853432282,
+      "eval_recall": 0.9291705498602051,
+      "eval_runtime": 13.4189,
+      "eval_samples_per_second": 517.629,
+      "eval_steps_per_second": 64.76,
+      "step": 4370
+    },
+    {
+      "epoch": 10.0,
+      "step": 4370,
+      "total_flos": 1.1151464037050934e+16,
+      "train_loss": 0.002938754050150616,
+      "train_runtime": 1039.0289,
+      "train_samples_per_second": 269.165,
+      "train_steps_per_second": 4.206
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4370,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1151464037050934e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}