End of training

README.md

@@ -18,9 +18,9 @@ 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: 0.6389
-- Accuracy: 0.8145
-- F1: 0.8152
+- Loss: 0.7573
+- Accuracy: 0.82
+- F1: 0.8207
 
 ## Model description
 
@@ -40,22 +40,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 32
+- train_batch_size: 8
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 4
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 375  | 1.1511          | 0.5755   | 0.5607 |
-| 1.4974        | 2.0   | 750  | 0.7869          | 0.7535   | 0.7525 |
-| 0.7908        | 3.0   | 1125 | 0.6635          | 0.8      | 0.8024 |
-| 0.5067        | 4.0   | 1500 | 0.6389          | 0.8145   | 0.8152 |
+| 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 |
 
 
 ### Framework versions