End of training

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9131274131274131
+      value: 0.9089615931721194
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the snli dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2615
-- Accuracy: 0.9131
+- Loss: 0.2600
+- Accuracy: 0.9090
 
 ## Model description
 
@@ -50,25 +50,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 64
-- eval_batch_size: 32
-- seed: 75
+- train_batch_size: 256
+- eval_batch_size: 128
+- seed: 30
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.3449        | 1.0   | 8584  | 0.2785          | 0.9046   |
-| 0.2964        | 2.0   | 17168 | 0.2619          | 0.9096   |
-| 0.2557        | 3.0   | 25752 | 0.2615          | 0.9131   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.369         | 1.0   | 2146 | 0.2819          | 0.9007   |
+| 0.3179        | 2.0   | 4292 | 0.2659          | 0.9067   |
+| 0.2931        | 3.0   | 6438 | 0.2600          | 0.9090   |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
-- Pytorch 2.0.1+cu118
+- Pytorch 2.1.1+cu121
 - Datasets 2.15.0
 - Tokenizers 0.15.0