Model save

README.md

@@ -3,10 +3,9 @@ library_name: transformers
 license: apache-2.0
 base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
 tags:
-- token-classification
 - generated_from_trainer
 datasets:
-- Rodrigo1771/distemist-85-ner
+- drugtemist-85-ner
 metrics:
 - precision
 - recall
@@ -19,24 +18,24 @@ model-index:
       name: Token Classification
       type: token-classification
     dataset:
-      name: Rodrigo1771/distemist-85-ner
-      type: Rodrigo1771/distemist-85-ner
-      config: DisTEMIST NER
+      name: drugtemist-85-ner
+      type: drugtemist-85-ner
+      config: DrugTEMIST NER
       split: validation
-      args: DisTEMIST NER
+      args: DrugTEMIST NER
     metrics:
     - name: Precision
       type: precision
-      value: 0.803175344384777
+      value: 0.9347826086956522
     - name: Recall
       type: recall
-      value: 0.8048666354702855
+      value: 0.9485294117647058
     - name: F1
       type: f1
-      value: 0.8040201005025126
+      value: 0.9416058394160585
     - name: Accuracy
       type: accuracy
-      value: 0.9764853694371592
+      value: 0.9989083718950389
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,13 +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 Rodrigo1771/distemist-85-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 drugtemist-85-ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1424
-- Precision: 0.8032
-- Recall: 0.8049
-- F1: 0.8040
-- Accuracy: 0.9765
+- Loss: 0.0058
+- Precision: 0.9348
+- Recall: 0.9485
+- F1: 0.9416
+- Accuracy: 0.9989
 
 ## Model description
 
@@ -81,18 +80,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 0.9990 | 499  | 0.0739          | 0.7271    | 0.7953 | 0.7596 | 0.9731   |
-| 0.105         | 2.0    | 999  | 0.0908          | 0.7436    | 0.7890 | 0.7656 | 0.9729   |
-| 0.0448        | 2.9990 | 1498 | 0.0930          | 0.7676    | 0.7990 | 0.7830 | 0.9744   |
-| 0.0255        | 4.0    | 1998 | 0.1052          | 0.7806    | 0.7983 | 0.7894 | 0.9757   |
-| 0.0164        | 4.9990 | 2497 | 0.1100          | 0.7756    | 0.8007 | 0.7879 | 0.9750   |
-| 0.0112        | 6.0    | 2997 | 0.1266          | 0.7869    | 0.8124 | 0.7994 | 0.9768   |
-| 0.0073        | 6.9990 | 3496 | 0.1288          | 0.7929    | 0.8009 | 0.7969 | 0.9763   |
-| 0.0054        | 8.0    | 3996 | 0.1424          | 0.8032    | 0.8049 | 0.8040 | 0.9765   |
-| 0.0038        | 8.9990 | 4495 | 0.1455          | 0.7901    | 0.8042 | 0.7971 | 0.9765   |
-| 0.0028        | 9.9900 | 4990 | 0.1497          | 0.7898    | 0.8072 | 0.7984 | 0.9768   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 466  | 0.0031          | 0.9292    | 0.9412 | 0.9352 | 0.9989   |
+| 0.0199        | 2.0   | 932  | 0.0031          | 0.9212    | 0.9568 | 0.9387 | 0.9989   |
+| 0.0026        | 3.0   | 1398 | 0.0040          | 0.9365    | 0.9357 | 0.9361 | 0.9989   |
+| 0.0011        | 4.0   | 1864 | 0.0052          | 0.9400    | 0.9219 | 0.9309 | 0.9987   |
+| 0.001         | 5.0   | 2330 | 0.0048          | 0.9461    | 0.9522 | 0.9492 | 0.9989   |
+| 0.0005        | 6.0   | 2796 | 0.0046          | 0.9376    | 0.9522 | 0.9448 | 0.9989   |
+| 0.0004        | 7.0   | 3262 | 0.0050          | 0.9328    | 0.9568 | 0.9446 | 0.9990   |
+| 0.0002        | 8.0   | 3728 | 0.0055          | 0.9423    | 0.9449 | 0.9436 | 0.9989   |
+| 0.0001        | 9.0   | 4194 | 0.0057          | 0.9399    | 0.9485 | 0.9442 | 0.9989   |
+| 0.0001        | 10.0  | 4660 | 0.0058          | 0.9348    | 0.9485 | 0.9416 | 0.9989   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e399e6af42ef4ecdb60ff9e1b060521b37b4bc5e506b3f1161be2a8586ca1f
+oid sha256:8ffb52a560270ca01c848053ce5081195b99ce3022deb83a8d0d15a9c351568f
 size 496244100

tb/events.out.tfevents.1725577909.2a66098fac87.9264.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f6260e869742047a3377dfa6864252ec79b1694042c0ddc87051efbe5d1e54e
-size 11320
+oid sha256:78b123fe2690b4ef8daee19df1596f88d3d9902ee0a7e2e67195ebf39fc38893
+size 12146

train.log

@@ -1437,3 +1437,16 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|trainer.py:2632] 2024-09-05 23:34:18,337 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-2330 (score: 0.9491525423728814).
 
                                                   
 [INFO|trainer.py:4283] 2024-09-05 23:34:18,533 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+[INFO|trainer.py:3503] 2024-09-05 23:34:40,390 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-05 23:34:40,392 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-05 23:34:41,886 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-05 23:34:41,887 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-05 23:34:41,888 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+[INFO|trainer.py:3503] 2024-09-05 23:34:41,936 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-05 23:34:41,937 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-05 23:34:43,193 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-05 23:34:43,194 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-05 23:34:43,194 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+{'eval_loss': 0.005793666001409292, 'eval_precision': 0.9347826086956522, 'eval_recall': 0.9485294117647058, 'eval_f1': 0.9416058394160585, 'eval_accuracy': 0.9989083718950389, 'eval_runtime': 14.4595, 'eval_samples_per_second': 470.971, 'eval_steps_per_second': 58.923, 'epoch': 10.0}
+{'train_runtime': 1349.0548, 'train_samples_per_second': 220.873, 'train_steps_per_second': 3.454, 'train_loss': 0.002772659832779558, 'epoch': 10.0}
+