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](https://huggingface.co/facebook/bart-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7520
+- Loss: 0.4084
 
 ## Model description
 
@@ -35,8 +35,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8703        | 1.0   | 125  | 0.7690          |
-| 0.7928        | 2.0   | 250  | 0.7561          |
-| 0.8007        | 3.0   | 375  | 0.7520          |
+| 0.5513        | 1.0   | 1000 | 0.4476          |
+| 0.4666        | 2.0   | 2000 | 0.4170          |
+| 0.412         | 3.0   | 3000 | 0.4084          |
 
 
 ### Framework versions