Model save

README.md

@@ -1,10 +1,10 @@
 ---
-base_model: IVN-RIN/bioBIT
+license: apache-2.0
+base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
 tags:
-- token-classification
 - generated_from_trainer
 datasets:
-- Rodrigo1771/drugtemist-it-ner
+- symptemist-ner
 metrics:
 - precision
 - recall
@@ -17,24 +17,24 @@ model-index:
       name: Token Classification
       type: token-classification
     dataset:
-      name: Rodrigo1771/drugtemist-it-ner
-      type: Rodrigo1771/drugtemist-it-ner
-      config: DrugTEMIST Italian NER
+      name: symptemist-ner
+      type: symptemist-ner
+      config: SympTEMIST NER
       split: validation
-      args: DrugTEMIST Italian NER
+      args: SympTEMIST NER
     metrics:
     - name: Precision
       type: precision
-      value: 0.9328214971209213
+      value: 0.6594676042189854
     - name: Recall
       type: recall
-      value: 0.9409486931268151
+      value: 0.7186644772851669
     - name: F1
       type: f1
-      value: 0.936867469879518
+      value: 0.6877946568884233
     - name: Accuracy
       type: accuracy
-      value: 0.9988184887042326
+      value: 0.9487631941993647
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,13 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output
 
-This model is a fine-tuned version of [IVN-RIN/bioBIT](https://huggingface.co/IVN-RIN/bioBIT) on the Rodrigo1771/drugtemist-it-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 symptemist-ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0067
-- Precision: 0.9328
-- Recall: 0.9409
-- F1: 0.9369
-- Accuracy: 0.9988
+- Loss: 0.2767
+- Precision: 0.6595
+- Recall: 0.7187
+- F1: 0.6878
+- Accuracy: 0.9488
 
 ## Model description
 
@@ -81,16 +81,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 425  | 0.0056          | 0.8672    | 0.9226 | 0.8940 | 0.9981   |
-| 0.0104        | 2.0   | 850  | 0.0042          | 0.9151    | 0.9284 | 0.9217 | 0.9986   |
-| 0.0034        | 3.0   | 1275 | 0.0043          | 0.9182    | 0.9129 | 0.9155 | 0.9985   |
-| 0.0022        | 4.0   | 1700 | 0.0044          | 0.9365    | 0.9138 | 0.9250 | 0.9986   |
-| 0.0012        | 5.0   | 2125 | 0.0061          | 0.9107    | 0.9284 | 0.9195 | 0.9985   |
-| 0.0009        | 6.0   | 2550 | 0.0060          | 0.9104    | 0.9342 | 0.9221 | 0.9987   |
-| 0.0009        | 7.0   | 2975 | 0.0065          | 0.9230    | 0.9400 | 0.9314 | 0.9987   |
-| 0.0005        | 8.0   | 3400 | 0.0059          | 0.9258    | 0.9303 | 0.9281 | 0.9987   |
-| 0.0004        | 9.0   | 3825 | 0.0066          | 0.9255    | 0.9380 | 0.9317 | 0.9987   |
-| 0.0001        | 10.0  | 4250 | 0.0067          | 0.9328    | 0.9409 | 0.9369 | 0.9988   |
+| No log        | 1.0   | 150  | 0.1504          | 0.5091    | 0.6409 | 0.5675 | 0.9456   |
+| No log        | 2.0   | 300  | 0.1547          | 0.5881    | 0.6995 | 0.639  | 0.9462   |
+| No log        | 3.0   | 450  | 0.1618          | 0.6237    | 0.6984 | 0.6589 | 0.9476   |
+| 0.126         | 4.0   | 600  | 0.1920          | 0.6154    | 0.7181 | 0.6628 | 0.9451   |
+| 0.126         | 5.0   | 750  | 0.2102          | 0.6561    | 0.7028 | 0.6786 | 0.9488   |
+| 0.126         | 6.0   | 900  | 0.2414          | 0.6443    | 0.7088 | 0.6750 | 0.9467   |
+| 0.0251        | 7.0   | 1050 | 0.2500          | 0.6588    | 0.7061 | 0.6816 | 0.9492   |
+| 0.0251        | 8.0   | 1200 | 0.2642          | 0.6440    | 0.7307 | 0.6846 | 0.9474   |
+| 0.0251        | 9.0   | 1350 | 0.2747          | 0.6675    | 0.7187 | 0.6921 | 0.9483   |
+| 0.0091        | 10.0  | 1500 | 0.2767          | 0.6595    | 0.7187 | 0.6878 | 0.9488   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6017fad51f5dc5737798ff6d9fd9fbfbc1d8d5e8c58fda4e121890b2bd69b001
+oid sha256:3c0cc86344025d3d9ad816c10866b7af4bb1e9ae5a0fd5c4e9e2a0bfde337257
 size 496244100

tb/events.out.tfevents.1725056887.6b97e535edda.51600.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b64cb2bd4ea4ebc30acb43ec3597dee9e97889efa2097df4b63784bd9dd34ba
-size 9984
+oid sha256:828d0da32d0107678e9d0aa2a710b0216207647fa04be0e03222be8b137b81af
+size 10810

train.log

@@ -844,3 +844,16 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|trainer.py:2621] 2024-08-30 22:35:40,063 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-1350 (score: 0.6921454928835002).
 
                                                   
 [INFO|trainer.py:4239] 2024-08-30 22:35:40,264 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+[INFO|trainer.py:3478] 2024-08-30 22:35:51,472 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-08-30 22:35:51,473 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2690] 2024-08-30 22:35:52,914 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 22:35:52,915 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 22:35:52,916 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+[INFO|trainer.py:3478] 2024-08-30 22:35:52,965 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-08-30 22:35:52,967 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2690] 2024-08-30 22:35:55,047 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 22:35:55,048 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 22:35:55,048 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+{'eval_loss': 0.27674129605293274, 'eval_precision': 0.6594676042189854, 'eval_recall': 0.7186644772851669, 'eval_f1': 0.6877946568884233, 'eval_accuracy': 0.9487631941993647, 'eval_runtime': 6.0833, 'eval_samples_per_second': 414.082, 'eval_steps_per_second': 51.781, 'epoch': 10.0}
+{'train_runtime': 453.0745, 'train_samples_per_second': 211.819, 'train_steps_per_second': 3.311, 'train_loss': 0.05337127685546875, 'epoch': 10.0}
+