roscazo
/

CTEBMSP_ANAT_DISO

@@ -12,21 +12,21 @@ should probably proofread and complete it, then remove this comment. -->
 # CTEBMSP_ANAT_DISO
-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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0625
-- Anat Precision: 0.6977
-- Anat Recall: 0.6648
-- Anat F1: 0.6809
 - Anat Number: 361
-- Diso Precision: 0.8914
-- Diso Recall: 0.8972
-- Diso F1: 0.8943
 - Diso Number: 2645
-- Overall Precision: 0.8693
-- Overall Recall: 0.8693
-- Overall F1: 0.8693
-- Overall Accuracy: 0.9869
 ## Model description
@@ -45,22 +45,26 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss | Anat Precision | Anat Recall | Anat F1 | Anat Number | Diso Precision | Diso Recall | Diso F1 | Diso Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------------:|:-----------:|:-------:|:-----------:|:--------------:|:-----------:|:-------:|:-----------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 0.0541        | 1.0   | 1570 | 0.0541          | 0.6821         | 0.5291      | 0.5959  | 361         | 0.8545         | 0.8949      | 0.8742  | 2645        | 0.8387            | 0.8510         | 0.8448     | 0.9850           |
-| 0.0281        | 2.0   | 3140 | 0.0520          | 0.6339         | 0.7147      | 0.6719  | 361         | 0.8683         | 0.8998      | 0.8838  | 2645        | 0.8380            | 0.8776         | 0.8573     | 0.9860           |
-| 0.0148        | 3.0   | 4710 | 0.0573          | 0.7188         | 0.6371      | 0.6755  | 361         | 0.8882         | 0.8983      | 0.8932  | 2645        | 0.8701            | 0.8669         | 0.8685     | 0.9868           |
-| 0.0081        | 4.0   | 6280 | 0.0625          | 0.6977         | 0.6648      | 0.6809  | 361         | 0.8914         | 0.8972      | 0.8943  | 2645        | 0.8693            | 0.8693         | 0.8693     | 0.9869           |
 ### Framework versions

 # CTEBMSP_ANAT_DISO
+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 None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0909
+- Anat Precision: 0.7522
+- Anat Recall: 0.7147
+- Anat F1: 0.7330
 - Anat Number: 361
+- Diso Precision: 0.8915
+- Diso Recall: 0.8919
+- Diso F1: 0.8917
 - Diso Number: 2645
+- Overall Precision: 0.8755
+- Overall Recall: 0.8706
+- Overall F1: 0.8731
+- Overall Accuracy: 0.9873
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 8e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 8
 ### Training results
+| Training Loss | Epoch | Step  | Validation Loss | Anat Precision | Anat Recall | Anat F1 | Anat Number | Diso Precision | Diso Recall | Diso F1 | Diso Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------------:|:-----------:|:-------:|:-----------:|:--------------:|:-----------:|:-------:|:-----------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.0592        | 1.0   | 2133  | 0.0506          | 0.6950         | 0.4986      | 0.5806  | 361         | 0.8635         | 0.8609      | 0.8622  | 2645        | 0.8484            | 0.8174         | 0.8326     | 0.9843           |
+| 0.0323        | 2.0   | 4266  | 0.0583          | 0.7899         | 0.6039      | 0.6845  | 361         | 0.8780         | 0.8817      | 0.8798  | 2645        | 0.8697            | 0.8483         | 0.8589     | 0.9858           |
+| 0.0201        | 3.0   | 6399  | 0.0580          | 0.6565         | 0.7147      | 0.6844  | 361         | 0.8598         | 0.8764      | 0.8680  | 2645        | 0.8339            | 0.8570         | 0.8453     | 0.9851           |
+| 0.0121        | 4.0   | 8532  | 0.0758          | 0.7240         | 0.6759      | 0.6991  | 361         | 0.8976         | 0.8752      | 0.8863  | 2645        | 0.8776            | 0.8513         | 0.8642     | 0.9863           |
+| 0.0078        | 5.0   | 10665 | 0.0814          | 0.7219         | 0.7119      | 0.7169  | 361         | 0.8776         | 0.8975      | 0.8875  | 2645        | 0.8595            | 0.8752         | 0.8673     | 0.9862           |
+| 0.0031        | 6.0   | 12798 | 0.0974          | 0.7599         | 0.6399      | 0.6947  | 361         | 0.8895         | 0.8915      | 0.8905  | 2645        | 0.8761            | 0.8613         | 0.8686     | 0.9867           |
+| 0.002         | 7.0   | 14931 | 0.0980          | 0.7143         | 0.6787      | 0.6960  | 361         | 0.8813         | 0.8957      | 0.8884  | 2645        | 0.8624            | 0.8696         | 0.8660     | 0.9860           |
+| 0.0005        | 8.0   | 17064 | 0.0909          | 0.7522         | 0.7147      | 0.7330  | 361         | 0.8915         | 0.8919      | 0.8917  | 2645        | 0.8755            | 0.8706         | 0.8731     | 0.9873           |
 ### Framework versions