End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8276
+- Loss: 2.7109
 
 ## Model description
 
@@ -40,20 +40,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.0725        | 1.0   | 800  | 0.7177          |
-| 0.9696        | 2.0   | 1600 | 0.7636          |
-| 1.0935        | 3.0   | 2400 | 0.8900          |
-| 1.0146        | 4.0   | 3200 | 0.7952          |
-| 0.9994        | 5.0   | 4000 | 0.7545          |
-| 1.0023        | 6.0   | 4800 | 1.0007          |
-| 0.6994        | 7.0   | 5600 | 1.1323          |
-| 0.5347        | 8.0   | 6400 | 1.8276          |
+| 0.7865        | 1.0   | 800  | 1.1187          |
+| 0.6785        | 2.0   | 1600 | 1.2005          |
+| 0.774         | 3.0   | 2400 | 1.1685          |
+| 0.4621        | 4.0   | 3200 | 1.3130          |
+| 0.4138        | 5.0   | 4000 | 2.2119          |
+| 0.3162        | 6.0   | 4800 | 2.0261          |
+| 0.2778        | 7.0   | 5600 | 1.9403          |
+| 0.2476        | 8.0   | 6400 | 2.5232          |
+| 0.1718        | 9.0   | 7200 | 2.6737          |
+| 0.0869        | 10.0  | 8000 | 2.7109          |
 
 
 ### Framework versions