End of training

README.md

@@ -18,9 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli](https://huggingface.co/MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7573
-- Accuracy: 0.82
-- F1: 0.8207
+- Loss: 0.6329
+- Accuracy: 0.8235
+- F1: 0.8241
+- Log Loss: 0.6329
 
 ## Model description
 
@@ -40,8 +41,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 16
+- train_batch_size: 16
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -50,13 +51,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 1.6738        | 1.0   | 750  | 0.8938          | 0.712    | 0.7142 |
-| 0.7626        | 2.0   | 1500 | 0.8021          | 0.7645   | 0.7633 |
-| 0.6333        | 3.0   | 2250 | 0.7307          | 0.7965   | 0.7997 |
-| 0.5001        | 4.0   | 3000 | 0.6905          | 0.817    | 0.8181 |
-| 0.3686        | 5.0   | 3750 | 0.7573          | 0.82     | 0.8207 |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Log Loss |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|
+| No log        | 1.0   | 375  | 1.1586          | 0.5505   | 0.5121 | 1.1586   |
+| 1.4748        | 2.0   | 750  | 0.7917          | 0.7495   | 0.7506 | 0.7917   |
+| 0.7813        | 3.0   | 1125 | 0.6692          | 0.798    | 0.7989 | 0.6692   |
+| 0.5346        | 4.0   | 1500 | 0.6359          | 0.811    | 0.8105 | 0.6359   |
+| 0.5346        | 5.0   | 1875 | 0.6329          | 0.8235   | 0.8241 | 0.6329   |
 
 
 ### Framework versions