End of training

README.md

@@ -2,9 +2,10 @@
 license: apache-2.0
 base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
 tags:
+- token-classification
 - generated_from_trainer
 datasets:
-- combined-train-drugtemist-dev-ner
+- Rodrigo1771/combined-train-drugtemist-dev-ner
 metrics:
 - precision
 - recall
@@ -17,24 +18,24 @@ model-index:
       name: Token Classification
       type: token-classification
     dataset:
-      name: combined-train-drugtemist-dev-ner
-      type: combined-train-drugtemist-dev-ner
+      name: Rodrigo1771/combined-train-drugtemist-dev-ner
+      type: Rodrigo1771/combined-train-drugtemist-dev-ner
       config: CombinedTrainDrugTEMISTDevNER
       split: validation
       args: CombinedTrainDrugTEMISTDevNER
     metrics:
     - name: Precision
       type: precision
-      value: 0.0914341567442687
+      value: 0.09532555790247038
     - name: Recall
       type: recall
-      value: 0.9457720588235294
+      value: 0.9540441176470589
     - name: F1
       type: f1
-      value: 0.16674769081186194
+      value: 0.17333222008850296
     - name: Accuracy
       type: accuracy
-      value: 0.7820794485561674
+      value: 0.7932840841995413
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,13 +43,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output
 
-This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the combined-train-drugtemist-dev-ner dataset.
+This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the Rodrigo1771/combined-train-drugtemist-dev-ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4862
-- Precision: 0.0914
-- Recall: 0.9458
-- F1: 0.1667
-- Accuracy: 0.7821
+- Loss: 1.0503
+- Precision: 0.0953
+- Recall: 0.9540
+- F1: 0.1733
+- Accuracy: 0.7933
 
 ## Model description
 

all_results.json

@@ -1,26 +1,26 @@
 {
     "epoch": 9.988249118683902,
-    "eval_accuracy": 0.8601754843670617,
-    "eval_f1": 0.4624414693662204,
-    "eval_loss": 0.6266195774078369,
-    "eval_precision": 0.32197630636422075,
-    "eval_recall": 0.8203088441740758,
-    "eval_runtime": 14.995,
+    "eval_accuracy": 0.7932840841995413,
+    "eval_f1": 0.17333222008850296,
+    "eval_loss": 1.0502684116363525,
+    "eval_precision": 0.09532555790247038,
+    "eval_recall": 0.9540441176470589,
+    "eval_runtime": 14.6851,
     "eval_samples": 6810,
-    "eval_samples_per_second": 454.15,
-    "eval_steps_per_second": 56.819,
-    "predict_accuracy": 0.9510588123763138,
-    "predict_f1": 0.6555634301913535,
-    "predict_loss": 0.18893657624721527,
-    "predict_precision": 0.5454009433962265,
-    "predict_recall": 0.8214920071047958,
-    "predict_runtime": 30.3218,
-    "predict_samples_per_second": 481.964,
-    "predict_steps_per_second": 60.254,
+    "eval_samples_per_second": 463.735,
+    "eval_steps_per_second": 58.018,
+    "predict_accuracy": 0.8808544760053879,
+    "predict_f1": 0.24078298623886968,
+    "predict_loss": 0.62894606590271,
+    "predict_precision": 0.1378032345013477,
+    "predict_recall": 0.9528246942341293,
+    "predict_runtime": 29.8715,
+    "predict_samples_per_second": 489.229,
+    "predict_steps_per_second": 61.162,
     "total_flos": 1.2649810588547778e+16,
     "train_loss": 0.10639642311544979,
-    "train_runtime": 1205.6346,
+    "train_runtime": 1208.2019,
     "train_samples": 27229,
-    "train_samples_per_second": 225.848,
-    "train_steps_per_second": 3.525
+    "train_samples_per_second": 225.368,
+    "train_steps_per_second": 3.518
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 9.988249118683902,
-    "eval_accuracy": 0.8601754843670617,
-    "eval_f1": 0.4624414693662204,
-    "eval_loss": 0.6266195774078369,
-    "eval_precision": 0.32197630636422075,
-    "eval_recall": 0.8203088441740758,
-    "eval_runtime": 14.995,
+    "eval_accuracy": 0.7932840841995413,
+    "eval_f1": 0.17333222008850296,
+    "eval_loss": 1.0502684116363525,
+    "eval_precision": 0.09532555790247038,
+    "eval_recall": 0.9540441176470589,
+    "eval_runtime": 14.6851,
     "eval_samples": 6810,
-    "eval_samples_per_second": 454.15,
-    "eval_steps_per_second": 56.819
+    "eval_samples_per_second": 463.735,
+    "eval_steps_per_second": 58.018
 }

predict_results.json

@@ -1,10 +1,10 @@
 {
-    "predict_accuracy": 0.9510588123763138,
-    "predict_f1": 0.6555634301913535,
-    "predict_loss": 0.18893657624721527,
-    "predict_precision": 0.5454009433962265,
-    "predict_recall": 0.8214920071047958,
-    "predict_runtime": 30.3218,
-    "predict_samples_per_second": 481.964,
-    "predict_steps_per_second": 60.254
+    "predict_accuracy": 0.8808544760053879,
+    "predict_f1": 0.24078298623886968,
+    "predict_loss": 0.62894606590271,
+    "predict_precision": 0.1378032345013477,
+    "predict_recall": 0.9528246942341293,
+    "predict_runtime": 29.8715,
+    "predict_samples_per_second": 489.229,
+    "predict_steps_per_second": 61.162
 }

tb/events.out.tfevents.1725049039.6b97e535edda.13440.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f105690f828d701992cc9bf50b2d6c540b9476f5cd4584b9d782e2db879b27e7
+size 560

train.log

@@ -1553,3 +1553,53 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 {'eval_loss': 1.4861844778060913, 'eval_precision': 0.0914341567442687, 'eval_recall': 0.9457720588235294, 'eval_f1': 0.16674769081186194, 'eval_accuracy': 0.7820794485561674, 'eval_runtime': 15.3988, 'eval_samples_per_second': 442.243, 'eval_steps_per_second': 55.329, 'epoch': 9.99}
 {'train_runtime': 1208.2019, 'train_samples_per_second': 225.368, 'train_steps_per_second': 3.518, 'train_loss': 0.10639642311544979, 'epoch': 9.99}
 
+***** train metrics *****
+  epoch                    =     9.9882
+  total_flos               = 11781054GF
+  train_loss               =     0.1064
+  train_runtime            = 0:20:08.20
+  train_samples            =      27229
+  train_samples_per_second =    225.368
+  train_steps_per_second   =      3.518
+08/30/2024 20:17:04 - INFO - __main__ -   *** Evaluate ***
+[INFO|trainer.py:805] 2024-08-30 20:17:04,325 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: id, ner_tags, tokens. If id, ner_tags, tokens are not expected by `RobertaForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3788] 2024-08-30 20:17:04,327 >> 
+***** Running Evaluation *****
+[INFO|trainer.py:3790] 2024-08-30 20:17:04,327 >>   Num examples = 6810
+[INFO|trainer.py:3793] 2024-08-30 20:17:04,327 >>   Batch size = 8
+
  0%|          | 0/852 [00:00<?, ?it/s]
  1%|          | 10/852 [00:00<00:09, 90.08it/s]
  2%|▏         | 20/852 [00:00<00:10, 78.76it/s]
  3%|▎         | 28/852 [00:00<00:10, 78.02it/s]
  4%|▍         | 36/852 [00:00<00:10, 78.47it/s]
  5%|▌         | 44/852 [00:00<00:10, 78.61it/s]
  6%|▌         | 53/852 [00:00<00:10, 79.34it/s]
  7%|▋         | 62/852 [00:00<00:09, 79.85it/s]
  8%|▊         | 70/852 [00:00<00:10, 77.38it/s]
  9%|▉         | 78/852 [00:00<00:09, 78.05it/s]
 10%|█         | 86/852 [00:01<00:09, 77.50it/s]
 11%|█         | 94/852 [00:01<00:09, 76.16it/s]
 12%|█▏        | 103/852 [00:01<00:09, 77.40it/s]
 13%|█▎        | 111/852 [00:01<00:09, 77.04it/s]
 14%|█▍        | 119/852 [00:01<00:09, 77.45it/s]
 15%|█▍        | 127/852 [00:01<00:09, 74.43it/s]
 16%|█▌        | 135/852 [00:01<00:09, 75.89it/s]
 17%|█▋        | 143/852 [00:01<00:09, 76.32it/s]
 18%|█▊        | 151/852 [00:01<00:09, 75.91it/s]
 19%|█▉        | 160/852 [00:02<00:08, 78.09it/s]
 20%|█▉        | 168/852 [00:02<00:08, 78.48it/s]
 21%|██        | 176/852 [00:02<00:08, 78.21it/s]
 22%|██▏       | 184/852 [00:02<00:08, 78.18it/s]
 23%|██▎       | 192/852 [00:02<00:08, 78.36it/s]
 24%|██▎       | 201/852 [00:02<00:08, 79.00it/s]
 25%|██▍       | 209/852 [00:02<00:08, 76.98it/s]
 25%|██▌       | 217/852 [00:02<00:08, 77.31it/s]
 26%|██▋       | 225/852 [00:02<00:08, 77.91it/s]
 27%|██▋       | 234/852 [00:03<00:07, 78.41it/s]
 28%|██▊       | 242/852 [00:03<00:08, 75.26it/s]
 29%|██▉       | 250/852 [00:03<00:07, 76.11it/s]
 30%|███       | 258/852 [00:03<00:07, 76.87it/s]
 31%|███       | 266/852 [00:03<00:07, 77.23it/s]
 32%|███▏      | 274/852 [00:03<00:07, 76.72it/s]
 33%|███▎      | 283/852 [00:03<00:07, 77.64it/s]
 34%|███▍      | 291/852 [00:03<00:07, 77.42it/s]
 35%|███▌      | 300/852 [00:03<00:07, 78.54it/s]
 36%|███▋      | 309/852 [00:03<00:06, 79.83it/s]
 37%|███▋      | 317/852 [00:04<00:06, 77.81it/s]
 38%|███▊      | 325/852 [00:04<00:06, 77.95it/s]
 39%|███▉      | 333/852 [00:04<00:06, 77.82it/s]
 40%|████      | 341/852 [00:04<00:06, 78.04it/s]
 41%|████      | 349/852 [00:04<00:06, 77.95it/s]
 42%|████▏     | 357/852 [00:04<00:06, 75.79it/s]
 43%|████▎     | 366/852 [00:04<00:06, 76.55it/s]
 44%|████▍     | 375/852 [00:04<00:06, 77.81it/s]
 45%|████▍     | 383/852 [00:04<00:06, 76.63it/s]
 46%|████▌     | 391/852 [00:05<00:05, 77.37it/s]
 47%|████▋     | 399/852 [00:05<00:05, 77.36it/s]
 48%|████▊     | 407/852 [00:05<00:05, 74.94it/s]
 49%|████▊     | 415/852 [00:05<00:05, 75.29it/s]
 50%|████▉     | 423/852 [00:05<00:05, 75.49it/s]
 51%|█████     | 431/852 [00:05<00:05, 75.09it/s]
 52%|█████▏    | 440/852 [00:05<00:05, 76.74it/s]
 53%|█████▎    | 448/852 [00:05<00:05, 76.92it/s]
 54%|█████▎    | 456/852 [00:05<00:05, 77.77it/s]
 54%|█████▍    | 464/852 [00:05<00:05, 76.63it/s]
 55%|█████▌    | 472/852 [00:06<00:05, 72.05it/s]
 56%|█████▋    | 480/852 [00:06<00:05, 73.97it/s]
 57%|█████▋    | 488/852 [00:06<00:04, 74.06it/s]
 58%|█████▊    | 496/852 [00:06<00:04, 75.08it/s]
 59%|█████▉    | 504/852 [00:06<00:04, 76.00it/s]
 60%|██████    | 512/852 [00:06<00:04, 76.30it/s]
 61%|██████    | 520/852 [00:06<00:04, 76.76it/s]
 62%|██████▏   | 528/852 [00:06<00:04, 74.32it/s]
 63%|██████▎   | 536/852 [00:06<00:04, 75.58it/s]
 64%|██████▍   | 544/852 [00:07<00:04, 76.71it/s]
 65%|██████▍   | 552/852 [00:07<00:04, 74.95it/s]
 66%|██████▌   | 560/852 [00:07<00:03, 75.87it/s]
 67%|██████▋   | 568/852 [00:07<00:03, 76.63it/s]
 68%|██████▊   | 576/852 [00:07<00:03, 76.40it/s]
 69%|██████▊   | 584/852 [00:07<00:03, 75.28it/s]
 69%|██████▉   | 592/852 [00:07<00:03, 75.66it/s]
 70%|███████   | 600/852 [00:07<00:03, 75.20it/s]
 71%|███████▏  | 608/852 [00:07<00:03, 74.78it/s]
 72%|███████▏  | 616/852 [00:08<00:03, 73.06it/s]
 73%|███████▎  | 624/852 [00:08<00:03, 74.76it/s]
 74%|███████▍  | 632/852 [00:08<00:03, 73.28it/s]
 75%|███████▌  | 640/852 [00:08<00:02, 73.23it/s]
 76%|███████▌  | 648/852 [00:08<00:02, 72.28it/s]
 77%|███████▋  | 656/852 [00:08<00:02, 74.30it/s]
 78%|███████▊  | 664/852 [00:08<00:02, 74.53it/s]
 79%|███████▉  | 672/852 [00:08<00:02, 74.57it/s]
 80%|███████▉  | 680/852 [00:08<00:02, 75.61it/s]
 81%|████████  | 689/852 [00:08<00:02, 77.74it/s]
 82%|████████▏ | 697/852 [00:09<00:02, 76.57it/s]
 83%|████████▎ | 706/852 [00:09<00:01, 77.79it/s]
 84%|████████▍ | 714/852 [00:09<00:01, 78.22it/s]
 85%|████████▍ | 722/852 [00:09<00:01, 77.26it/s]
 86%|████████▌ | 731/852 [00:09<00:01, 78.66it/s]
 87%|████████▋ | 740/852 [00:09<00:01, 79.91it/s]
 88%|████████▊ | 749/852 [00:09<00:01, 80.22it/s]
 89%|████████▉ | 758/852 [00:09<00:01, 80.35it/s]
 90%|█████████ | 767/852 [00:09<00:01, 79.25it/s]
 91%|█████████ | 776/852 [00:10<00:00, 79.74it/s]
 92%|█████████▏| 784/852 [00:10<00:00, 79.50it/s]
 93%|█████████▎| 792/852 [00:10<00:00, 79.31it/s]
 94%|█████████▍| 800/852 [00:10<00:00, 79.49it/s]
 95%|█████████▍| 809/852 [00:10<00:00, 81.08it/s]
 96%|█████████▌| 818/852 [00:10<00:00, 79.55it/s]
 97%|█████████▋| 827/852 [00:10<00:00, 81.06it/s]
 98%|█████████▊| 836/852 [00:10<00:00, 81.02it/s]
 99%|█████████▉| 845/852 [00:10<00:00, 79.78it/s]/usr/local/lib/python3.10/dist-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.
+  _warn_prf(average, modifier, msg_start, len(result))
+
+***** eval metrics *****
+  epoch                   =     9.9882
+  eval_accuracy           =     0.7933
+  eval_f1                 =     0.1733
+  eval_loss               =     1.0503
+  eval_precision          =     0.0953
+  eval_recall             =      0.954
+  eval_runtime            = 0:00:14.68
+  eval_samples            =       6810
+  eval_samples_per_second =    463.735
+  eval_steps_per_second   =     58.018
+08/30/2024 20:17:19 - INFO - __main__ -   *** Predict ***
+[INFO|trainer.py:805] 2024-08-30 20:17:19,020 >> The following columns in the test set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: id, ner_tags, tokens. If id, ner_tags, tokens are not expected by `RobertaForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3788] 2024-08-30 20:17:19,022 >> 
+***** Running Prediction *****
+[INFO|trainer.py:3790] 2024-08-30 20:17:19,022 >>   Num examples = 14614
+[INFO|trainer.py:3793] 2024-08-30 20:17:19,023 >>   Batch size = 8
+
  0%|          | 0/1827 [00:00<?, ?it/s]
  1%|          | 10/1827 [00:00<00:20, 87.94it/s]
  1%|          | 19/1827 [00:00<00:22, 79.79it/s]
  1%|▏         | 27/1827 [00:00<00:22, 79.33it/s]
  2%|▏         | 35/1827 [00:00<00:22, 78.11it/s]
  2%|▏         | 44/1827 [00:00<00:22, 80.08it/s]
  3%|▎         | 53/1827 [00:00<00:22, 79.80it/s]
  3%|▎         | 61/1827 [00:00<00:22, 77.38it/s]
  4%|▍         | 70/1827 [00:00<00:22, 77.96it/s]
  4%|▍         | 79/1827 [00:00<00:21, 80.62it/s]
  5%|▍         | 88/1827 [00:01<00:21, 79.62it/s]
  5%|▌         | 97/1827 [00:01<00:21, 81.19it/s]
  6%|▌         | 106/1827 [00:01<00:20, 82.65it/s]
  6%|▋         | 115/1827 [00:01<00:20, 82.97it/s]
  7%|▋         | 124/1827 [00:01<00:21, 79.65it/s]
  7%|▋         | 133/1827 [00:01<00:21, 79.51it/s]
  8%|▊         | 142/1827 [00:01<00:20, 80.61it/s]
  8%|▊         | 151/1827 [00:01<00:20, 81.06it/s]
  9%|▉         | 160/1827 [00:02<00:21, 77.41it/s]
  9%|▉         | 169/1827 [00:02<00:21, 78.59it/s]
 10%|▉         | 178/1827 [00:02<00:20, 79.54it/s]
 10%|█         | 187/1827 [00:02<00:20, 80.64it/s]
 11%|█         | 196/1827 [00:02<00:20, 80.28it/s]
 11%|█         | 205/1827 [00:02<00:20, 79.31it/s]
 12%|█▏        | 213/1827 [00:02<00:20, 78.96it/s]
 12%|█▏        | 222/1827 [00:02<00:20, 79.52it/s]
 13%|█▎        | 230/1827 [00:02<00:20, 78.22it/s]
 13%|█▎        | 238/1827 [00:02<00:20, 76.49it/s]
 14%|█▎        | 247/1827 [00:03<00:20, 78.15it/s]
 14%|█▍        | 256/1827 [00:03<00:19, 79.26it/s]
 14%|█▍        | 264/1827 [00:03<00:20, 77.90it/s]
 15%|█▍        | 273/1827 [00:03<00:19, 80.06it/s]
 15%|█▌        | 282/1827 [00:03<00:19, 81.15it/s]
 16%|█▌        | 291/1827 [00:03<00:19, 80.73it/s]
 16%|█▋        | 300/1827 [00:03<00:18, 81.69it/s]
 17%|█▋        | 309/1827 [00:03<00:18, 80.77it/s]
 17%|█▋        | 318/1827 [00:03<00:18, 80.07it/s]
 18%|█▊        | 327/1827 [00:04<00:18, 81.60it/s]
 18%|█▊        | 336/1827 [00:04<00:18, 80.47it/s]
 19%|█▉        | 345/1827 [00:04<00:18, 81.57it/s]
 19%|█▉        | 354/1827 [00:04<00:19, 76.57it/s]
 20%|█▉        | 362/1827 [00:04<00:19, 76.83it/s]
 20%|██        | 370/1827 [00:04<00:18, 77.31it/s]
 21%|██        | 378/1827 [00:04<00:18, 77.60it/s]
 21%|██        | 386/1827 [00:04<00:18, 77.53it/s]
 22%|██▏       | 394/1827 [00:04<00:18, 77.31it/s]
 22%|██▏       | 402/1827 [00:05<00:18, 77.04it/s]
 22%|██▏       | 410/1827 [00:05<00:18, 77.21it/s]
 23%|██▎       | 418/1827 [00:05<00:18, 74.60it/s]
 23%|██▎       | 426/1827 [00:05<00:18, 75.34it/s]
 24%|██▍       | 434/1827 [00:05<00:18, 75.76it/s]
 24%|██▍       | 442/1827 [00:05<00:18, 75.30it/s]
 25%|██▍       | 450/1827 [00:05<00:18, 76.15it/s]
 25%|██▌       | 459/1827 [00:05<00:17, 77.96it/s]
 26%|██▌       | 468/1827 [00:05<00:17, 78.69it/s]
 26%|██▌       | 476/1827 [00:06<00:17, 77.24it/s]
 26%|██▋       | 484/1827 [00:06<00:17, 77.34it/s]
 27%|██▋       | 492/1827 [00:06<00:17, 76.12it/s]
 27%|██▋       | 500/1827 [00:06<00:17, 77.21it/s]
 28%|██▊       | 508/1827 [00:06<00:16, 77.99it/s]
 28%|██▊       | 517/1827 [00:06<00:16, 78.96it/s]
 29%|██▉       | 526/1827 [00:06<00:16, 80.10it/s]
 29%|██▉       | 535/1827 [00:06<00:16, 78.94it/s]
 30%|██▉       | 544/1827 [00:06<00:16, 79.81it/s]
 30%|███       | 552/1827 [00:06<00:16, 79.35it/s]
 31%|███       | 560/1827 [00:07<00:15, 79.45it/s]
 31%|███       | 569/1827 [00:07<00:15, 80.99it/s]
 32%|███▏      | 578/1827 [00:07<00:15, 81.34it/s]
 32%|███▏      | 587/1827 [00:07<00:15, 80.67it/s]
 33%|███▎      | 596/1827 [00:07<00:15, 80.51it/s]
 33%|███▎      | 605/1827 [00:07<00:15, 80.13it/s]
 34%|███▎      | 614/1827 [00:07<00:15, 79.68it/s]
 34%|███▍      | 623/1827 [00:07<00:15, 80.12it/s]
 35%|███▍      | 632/1827 [00:07<00:14, 81.44it/s]
 35%|███▌      | 641/1827 [00:08<00:14, 82.11it/s]
 36%|███▌      | 650/1827 [00:08<00:15, 76.75it/s]
 36%|███▌      | 658/1827 [00:08<00:15, 76.92it/s]
 37%|███▋      | 667/1827 [00:08<00:14, 78.89it/s]
 37%|███▋      | 675/1827 [00:08<00:14, 78.89it/s]
 37%|███▋      | 684/1827 [00:08<00:14, 79.53it/s]
 38%|███▊      | 693/1827 [00:08<00:14, 80.94it/s]
 38%|███▊      | 702/1827 [00:08<00:14, 79.96it/s]
 39%|███▉      | 711/1827 [00:08<00:13, 80.90it/s]
 39%|███▉      | 720/1827 [00:09<00:13, 81.50it/s]
 40%|███▉      | 729/1827 [00:09<00:13, 81.53it/s]
 40%|████      | 738/1827 [00:09<00:13, 80.96it/s]
 41%|████      | 747/1827 [00:09<00:13, 80.92it/s]
 41%|████▏     | 756/1827 [00:09<00:13, 81.00it/s]
 42%|████▏     | 765/1827 [00:09<00:13, 80.78it/s]
 42%|████▏     | 774/1827 [00:09<00:13, 80.77it/s]
 43%|████▎     | 783/1827 [00:09<00:13, 78.74it/s]
 43%|████▎     | 792/1827 [00:09<00:13, 79.23it/s]
 44%|████▍     | 800/1827 [00:10<00:13, 78.17it/s]
 44%|████▍     | 809/1827 [00:10<00:12, 79.00it/s]
 45%|████▍     | 818/1827 [00:10<00:12, 79.52it/s]
 45%|████▌     | 827/1827 [00:10<00:12, 80.48it/s]
 46%|████▌     | 836/1827 [00:10<00:12, 78.98it/s]
 46%|████▋     | 845/1827 [00:10<00:12, 80.14it/s]
 47%|████▋     | 854/1827 [00:10<00:12, 80.46it/s]
 47%|████▋     | 863/1827 [00:10<00:11, 81.18it/s]
 48%|████▊     | 872/1827 [00:10<00:11, 81.19it/s]
 48%|████▊     | 881/1827 [00:11<00:11, 80.98it/s]
 49%|████▊     | 890/1827 [00:11<00:11, 81.37it/s]
 49%|████▉     | 899/1827 [00:11<00:11, 81.91it/s]
 50%|████▉     | 908/1827 [00:11<00:11, 81.97it/s]
 50%|█████     | 917/1827 [00:11<00:11, 82.23it/s]
 51%|█████     | 926/1827 [00:11<00:10, 82.15it/s]
 51%|█████     | 935/1827 [00:11<00:11, 80.10it/s]
 52%|█████▏    | 944/1827 [00:11<00:10, 80.66it/s]
 52%|█████▏    | 953/1827 [00:11<00:11, 79.31it/s]
 53%|█████▎    | 962/1827 [00:12<00:10, 79.70it/s]
 53%|█████▎    | 971/1827 [00:12<00:10, 80.87it/s]
 54%|█████▎    | 980/1827 [00:12<00:10, 79.74it/s]
 54%|█████▍    | 989/1827 [00:12<00:10, 80.80it/s]
 55%|█████▍    | 998/1827 [00:12<00:10, 80.66it/s]
 55%|█████▌    | 1007/1827 [00:12<00:10, 79.92it/s]
 56%|█████▌    | 1015/1827 [00:12<00:10, 79.86it/s]
 56%|█████▌    | 1024/1827 [00:12<00:09, 80.72it/s]
 57%|█████▋    | 1033/1827 [00:12<00:09, 81.65it/s]
 57%|█████▋    | 1042/1827 [00:13<00:09, 79.17it/s]
 58%|█████▊    | 1051/1827 [00:13<00:09, 79.75it/s]
 58%|█████▊    | 1060/1827 [00:13<00:09, 80.06it/s]
 59%|█████▊    | 1069/1827 [00:13<00:09, 79.66it/s]
 59%|█████▉    | 1078/1827 [00:13<00:09, 80.33it/s]
 59%|█████▉    | 1087/1827 [00:13<00:09, 80.70it/s]
 60%|█████▉    | 1096/1827 [00:13<00:09, 80.82it/s]
 60%|██████    | 1105/1827 [00:13<00:09, 79.90it/s]
 61%|██████    | 1113/1827 [00:13<00:08, 79.37it/s]
 61%|██████▏   | 1121/1827 [00:14<00:08, 78.82it/s]
 62%|██████▏   | 1129/1827 [00:14<00:08, 78.74it/s]
 62%|██████▏   | 1138/1827 [00:14<00:08, 79.54it/s]
 63%|██████▎   | 1146/1827 [00:14<00:08, 79.64it/s]
 63%|██████▎   | 1154/1827 [00:14<00:08, 78.95it/s]
 64%|██████▎   | 1162/1827 [00:14<00:08, 76.85it/s]
 64%|██████▍   | 1170/1827 [00:14<00:08, 77.11it/s]
 64%|██████▍   | 1178/1827 [00:14<00:08, 77.41it/s]
 65%|██████▍   | 1186/1827 [00:14<00:08, 76.41it/s]
 65%|██████▌   | 1195/1827 [00:15<00:08, 77.75it/s]
 66%|██████▌   | 1203/1827 [00:15<00:07, 78.33it/s]
 66%|██████▋   | 1211/1827 [00:15<00:07, 77.14it/s]
 67%|██████▋   | 1219/1827 [00:15<00:08, 75.69it/s]
 67%|██████▋   | 1227/1827 [00:15<00:07, 76.88it/s]
 68%|██████▊   | 1235/1827 [00:15<00:07, 77.28it/s]
 68%|██████▊   | 1243/1827 [00:15<00:07, 77.68it/s]
 68%|██████▊   | 1251/1827 [00:15<00:07, 77.84it/s]
 69%|██████▉   | 1259/1827 [00:15<00:07, 75.35it/s]
 69%|██████▉   | 1267/1827 [00:15<00:07, 76.47it/s]
 70%|██████▉   | 1276/1827 [00:16<00:07, 77.97it/s]
 70%|███████   | 1284/1827 [00:16<00:06, 78.01it/s]
 71%|███████   | 1292/1827 [00:16<00:06, 76.45it/s]
 71%|███████   | 1300/1827 [00:16<00:06, 77.46it/s]
 72%|███████▏  | 1308/1827 [00:16<00:06, 78.03it/s]
 72%|███████▏  | 1316/1827 [00:16<00:06, 77.74it/s]
 72%|███████▏  | 1324/1827 [00:16<00:06, 77.86it/s]
 73%|███████▎  | 1332/1827 [00:16<00:06, 77.96it/s]
 73%|███████▎  | 1340/1827 [00:16<00:06, 78.18it/s]
 74%|███████▍  | 1348/1827 [00:17<00:06, 76.62it/s]
 74%|███████▍  | 1356/1827 [00:17<00:06, 77.14it/s]
 75%|███████▍  | 1364/1827 [00:17<00:05, 77.97it/s]
 75%|███████▌  | 1372/1827 [00:17<00:05, 78.09it/s]
 76%|███████▌  | 1381/1827 [00:17<00:05, 79.48it/s]
 76%|███████▌  | 1389/1827 [00:17<00:05, 79.56it/s]
 77%|███████▋  | 1398/1827 [00:17<00:05, 80.37it/s]
 77%|███████▋  | 1407/1827 [00:17<00:05, 81.10it/s]
 78%|███████▊  | 1416/1827 [00:17<00:05, 81.80it/s]
 78%|███████▊  | 1425/1827 [00:17<00:04, 80.90it/s]
 78%|███████▊  | 1434/1827 [00:18<00:04, 79.95it/s]
 79%|███████▉  | 1442/1827 [00:18<00:04, 77.56it/s]
 79%|███████▉  | 1450/1827 [00:18<00:04, 77.58it/s]
 80%|███████▉  | 1459/1827 [00:18<00:04, 78.93it/s]
 80%|████████  | 1468/1827 [00:18<00:04, 79.42it/s]
 81%|████████  | 1476/1827 [00:18<00:04, 77.02it/s]
 81%|████████  | 1484/1827 [00:18<00:04, 77.76it/s]
 82%|████████▏ | 1492/1827 [00:18<00:04, 75.57it/s]
 82%|████████▏ | 1500/1827 [00:18<00:04, 76.23it/s]
 83%|████████▎ | 1508/1827 [00:19<00:04, 76.65it/s]
 83%|████████▎ | 1517/1827 [00:19<00:03, 78.09it/s]
 83%|████████▎ | 1525/1827 [00:19<00:03, 77.38it/s]
 84%|████████▍ | 1534/1827 [00:19<00:03, 78.28it/s]
 84%|████████▍ | 1542/1827 [00:19<00:03, 77.60it/s]
 85%|████████▍ | 1550/1827 [00:19<00:03, 77.22it/s]
 85%|████████▌ | 1558/1827 [00:19<00:03, 77.63it/s]
 86%|████████▌ | 1566/1827 [00:19<00:03, 77.77it/s]
 86%|████████▌ | 1574/1827 [00:19<00:03, 77.61it/s]
 87%|████████▋ | 1583/1827 [00:20<00:03, 78.96it/s]
 87%|████████▋ | 1591/1827 [00:20<00:02, 78.85it/s]
 88%|████████▊ | 1599/1827 [00:20<00:02, 78.83it/s]
 88%|████████▊ | 1608/1827 [00:20<00:02, 79.18it/s]
 88%|████████▊ | 1616/1827 [00:20<00:02, 78.24it/s]
 89%|████████▉ | 1624/1827 [00:20<00:02, 72.35it/s]
 89%|████████▉ | 1632/1827 [00:20<00:02, 73.13it/s]
 90%|████████▉ | 1640/1827 [00:20<00:02, 73.24it/s]
 90%|█████████ | 1649/1827 [00:20<00:02, 75.71it/s]
 91%|█████████ | 1658/1827 [00:21<00:02, 77.38it/s]
 91%|█████████ | 1666/1827 [00:21<00:02, 77.89it/s]
 92%|█████████▏| 1675/1827 [00:21<00:01, 79.27it/s]
 92%|█████████▏| 1684/1827 [00:21<00:01, 80.75it/s]
 93%|█████████▎| 1693/1827 [00:21<00:01, 79.27it/s]
 93%|█████████▎| 1702/1827 [00:21<00:01, 79.89it/s]
 94%|█████████▎| 1711/1827 [00:21<00:01, 80.41it/s]
 94%|█████████▍| 1720/1827 [00:21<00:01, 77.30it/s]
 95%|█████████▍| 1729/1827 [00:21<00:01, 78.18it/s]
 95%|█████████▌| 1738/1827 [00:22<00:01, 79.15it/s]
 96%|█████████▌| 1747/1827 [00:22<00:00, 80.30it/s]
 96%|█████████▌| 1756/1827 [00:22<00:00, 79.63it/s]
 97%|█████████▋| 1765/1827 [00:22<00:00, 80.54it/s]
 97%|█████████▋| 1774/1827 [00:22<00:00, 80.33it/s]
 98%|█████████▊| 1783/1827 [00:22<00:00, 81.23it/s]
 98%|█████████▊| 1792/1827 [00:22<00:00, 80.70it/s]
 99%|█████████▊| 1801/1827 [00:22<00:00, 77.42it/s]
 99%|█████████▉| 1810/1827 [00:22<00:00, 78.66it/s]
+[INFO|trainer.py:3478] 2024-08-30 20:17:49,537 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-08-30 20:17:49,539 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2690] 2024-08-30 20:17:50,922 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 20:17:50,923 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 20:17:50,923 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+***** predict metrics *****
+  predict_accuracy           =     0.8809
+  predict_f1                 =     0.2408
+  predict_loss               =     0.6289
+  predict_precision          =     0.1378
+  predict_recall             =     0.9528
+  predict_runtime            = 0:00:29.87
+  predict_samples_per_second =    489.229
+  predict_steps_per_second   =     61.162
+

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 9.988249118683902,
     "total_flos": 1.2649810588547778e+16,
     "train_loss": 0.10639642311544979,
-    "train_runtime": 1205.6346,
+    "train_runtime": 1208.2019,
     "train_samples": 27229,
-    "train_samples_per_second": 225.848,
-    "train_steps_per_second": 3.525
+    "train_samples_per_second": 225.368,
+    "train_steps_per_second": 3.518
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4624414693662204,
+  "best_metric": 0.17333222008850296,
   "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-2127",
   "epoch": 9.988249118683902,
   "eval_steps": 500,
@@ -10,14 +10,14 @@
   "log_history": [
     {
       "epoch": 0.9988249118683902,
-      "eval_accuracy": 0.8517239485355707,
-      "eval_f1": 0.4251637936518033,
-      "eval_loss": 0.3833567500114441,
-      "eval_precision": 0.29195422381409974,
-      "eval_recall": 0.7819372952737482,
-      "eval_runtime": 14.7317,
-      "eval_samples_per_second": 462.27,
-      "eval_steps_per_second": 57.835,
+      "eval_accuracy": 0.7849561289082346,
+      "eval_f1": 0.1613083366573594,
+      "eval_loss": 0.6610585451126099,
+      "eval_precision": 0.08832008386476806,
+      "eval_recall": 0.9292279411764706,
+      "eval_runtime": 14.7703,
+      "eval_samples_per_second": 461.06,
+      "eval_steps_per_second": 57.683,
       "step": 425
     },
     {
@@ -29,14 +29,14 @@
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.822140140332569,
-      "eval_f1": 0.40249737425603915,
-      "eval_loss": 0.5730458498001099,
-      "eval_precision": 0.2681125621890547,
-      "eval_recall": 0.8069723912026205,
-      "eval_runtime": 14.9036,
-      "eval_samples_per_second": 456.937,
-      "eval_steps_per_second": 57.167,
+      "eval_accuracy": 0.7551182940392986,
+      "eval_f1": 0.14506880733944952,
+      "eval_loss": 0.9204075932502747,
+      "eval_precision": 0.07866915422885572,
+      "eval_recall": 0.9301470588235294,
+      "eval_runtime": 14.7453,
+      "eval_samples_per_second": 461.844,
+      "eval_steps_per_second": 57.781,
       "step": 851
     },
     {
@@ -48,14 +48,14 @@
     },
     {
       "epoch": 2.99882491186839,
-      "eval_accuracy": 0.8338185013799827,
-      "eval_f1": 0.42018044559013074,
-      "eval_loss": 0.5796028971672058,
-      "eval_precision": 0.2847990681421083,
-      "eval_recall": 0.8008890968647637,
-      "eval_runtime": 14.7541,
-      "eval_samples_per_second": 461.567,
-      "eval_steps_per_second": 57.747,
+      "eval_accuracy": 0.7645035495077375,
+      "eval_f1": 0.15487907225146869,
+      "eval_loss": 0.9544711709022522,
+      "eval_precision": 0.0844496214327315,
+      "eval_recall": 0.9329044117647058,
+      "eval_runtime": 14.8107,
+      "eval_samples_per_second": 459.803,
+      "eval_steps_per_second": 57.526,
       "step": 1276
     },
     {
@@ -67,14 +67,14 @@
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8388097820863142,
-      "eval_f1": 0.43759863644971914,
-      "eval_loss": 0.6590859889984131,
-      "eval_precision": 0.2996455433560993,
-      "eval_recall": 0.8109499298081423,
-      "eval_runtime": 14.8634,
-      "eval_samples_per_second": 458.172,
-      "eval_steps_per_second": 57.322,
+      "eval_accuracy": 0.7692064756203056,
+      "eval_f1": 0.1618332674832082,
+      "eval_loss": 1.0923608541488647,
+      "eval_precision": 0.08852770813521224,
+      "eval_recall": 0.9411764705882353,
+      "eval_runtime": 14.8211,
+      "eval_samples_per_second": 459.48,
+      "eval_steps_per_second": 57.486,
       "step": 1702
     },
     {
@@ -86,14 +86,14 @@
     },
     {
       "epoch": 4.9988249118683905,
-      "eval_accuracy": 0.8601754843670617,
-      "eval_f1": 0.4624414693662204,
-      "eval_loss": 0.6266195774078369,
-      "eval_precision": 0.32197630636422075,
-      "eval_recall": 0.8203088441740758,
-      "eval_runtime": 14.7766,
-      "eval_samples_per_second": 460.863,
-      "eval_steps_per_second": 57.659,
+      "eval_accuracy": 0.7932840841995413,
+      "eval_f1": 0.17333222008850296,
+      "eval_loss": 1.0502684116363525,
+      "eval_precision": 0.09532555790247038,
+      "eval_recall": 0.9540441176470589,
+      "eval_runtime": 14.797,
+      "eval_samples_per_second": 460.229,
+      "eval_steps_per_second": 57.579,
       "step": 2127
     },
     {
@@ -105,26 +105,26 @@
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.8475977316105291,
-      "eval_f1": 0.44600244420145363,
-      "eval_loss": 0.7858611941337585,
-      "eval_precision": 0.3075490109110263,
-      "eval_recall": 0.8111839026672906,
-      "eval_runtime": 14.8163,
-      "eval_samples_per_second": 459.628,
-      "eval_steps_per_second": 57.504,
+      "eval_accuracy": 0.7787771018990209,
+      "eval_f1": 0.16632958498503356,
+      "eval_loss": 1.2641881704330444,
+      "eval_precision": 0.0911913421449481,
+      "eval_recall": 0.9448529411764706,
+      "eval_runtime": 14.5753,
+      "eval_samples_per_second": 467.228,
+      "eval_steps_per_second": 58.455,
       "step": 2553
     },
     {
       "epoch": 6.9988249118683905,
-      "eval_accuracy": 0.8507970944841886,
-      "eval_f1": 0.45324675324675323,
-      "eval_loss": 0.829707145690918,
-      "eval_precision": 0.3136796692432141,
-      "eval_recall": 0.8165652784277024,
-      "eval_runtime": 14.8867,
-      "eval_samples_per_second": 457.456,
-      "eval_steps_per_second": 57.232,
+      "eval_accuracy": 0.7828758564817994,
+      "eval_f1": 0.16898640903880793,
+      "eval_loss": 1.3261910676956177,
+      "eval_precision": 0.09275570735214812,
+      "eval_recall": 0.9485294117647058,
+      "eval_runtime": 14.5617,
+      "eval_samples_per_second": 467.665,
+      "eval_steps_per_second": 58.51,
       "step": 2978
     },
     {
@@ -136,14 +136,14 @@
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.8532206461889135,
-      "eval_f1": 0.453628249902988,
-      "eval_loss": 0.8468152284622192,
-      "eval_precision": 0.3134608509116911,
-      "eval_recall": 0.8205428170332242,
-      "eval_runtime": 15.05,
-      "eval_samples_per_second": 452.493,
-      "eval_steps_per_second": 56.611,
+      "eval_accuracy": 0.7848943386381424,
+      "eval_f1": 0.1687846203975236,
+      "eval_loss": 1.3697636127471924,
+      "eval_precision": 0.09259921344297461,
+      "eval_recall": 0.9522058823529411,
+      "eval_runtime": 14.6608,
+      "eval_samples_per_second": 464.504,
+      "eval_steps_per_second": 58.114,
       "step": 3404
     },
     {
@@ -155,14 +155,14 @@
     },
     {
       "epoch": 8.99882491186839,
-      "eval_accuracy": 0.8493827838576352,
-      "eval_f1": 0.44807482862451153,
-      "eval_loss": 0.9241161346435547,
-      "eval_precision": 0.30851345390383766,
-      "eval_recall": 0.8182030884417407,
-      "eval_runtime": 14.662,
-      "eval_samples_per_second": 464.465,
-      "eval_steps_per_second": 58.109,
+      "eval_accuracy": 0.782223625853049,
+      "eval_f1": 0.165499476776946,
+      "eval_loss": 1.4433350563049316,
+      "eval_precision": 0.09069254521393913,
+      "eval_recall": 0.9448529411764706,
+      "eval_runtime": 15.0504,
+      "eval_samples_per_second": 452.478,
+      "eval_steps_per_second": 56.61,
       "step": 3829
     },
     {
@@ -174,14 +174,14 @@
     },
     {
       "epoch": 9.988249118683902,
-      "eval_accuracy": 0.8498565092616749,
-      "eval_f1": 0.44938176197836166,
-      "eval_loss": 0.938378632068634,
-      "eval_precision": 0.31002310289674784,
-      "eval_recall": 0.816331305568554,
-      "eval_runtime": 15.4697,
-      "eval_samples_per_second": 440.215,
-      "eval_steps_per_second": 55.075,
+      "eval_accuracy": 0.7820794485561674,
+      "eval_f1": 0.16674769081186194,
+      "eval_loss": 1.4861844778060913,
+      "eval_precision": 0.0914341567442687,
+      "eval_recall": 0.9457720588235294,
+      "eval_runtime": 15.3988,
+      "eval_samples_per_second": 442.243,
+      "eval_steps_per_second": 55.329,
       "step": 4250
     },
     {
@@ -189,9 +189,9 @@
       "step": 4250,
       "total_flos": 1.2649810588547778e+16,
       "train_loss": 0.10639642311544979,
-      "train_runtime": 1205.6346,
-      "train_samples_per_second": 225.848,
-      "train_steps_per_second": 3.525
+      "train_runtime": 1208.2019,
+      "train_samples_per_second": 225.368,
+      "train_steps_per_second": 3.518
     }
   ],
   "logging_steps": 500,