Training complete

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [medicalai/ClinicalBERT](https://huggingface.co/medicalai/ClinicalBERT) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4264
-- Precision: 0.0
-- Recall: 0.0
-- F1: 0.0
-- Accuracy: 0.8504
+- Loss: 0.1567
+- Precision: 0.7118
+- Recall: 0.7328
+- F1: 0.7221
+- Accuracy: 0.9650
 
 ## Model description
 
@@ -56,10 +56,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
-| 216.5594      | 0.9996 | 652  | 1.4264          | 0.0       | 0.0    | 0.0 | 0.8504   |
-| 0.0           | 1.9992 | 1304 | 1.4264          | 0.0       | 0.0    | 0.0 | 0.8504   |
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.495         | 0.9996 | 652  | 0.3446          | 0.6425    | 0.6934 | 0.6670 | 0.9575   |
+| 0.3703        | 1.9992 | 1304 | 0.1567          | 0.7118    | 0.7328 | 0.7221 | 0.9650   |
 
 
 ### Framework versions