update model card README.md

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9602
+- Loss: 0.6465
 
 ## Model description
 
@@ -35,23 +35,24 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
 - train_batch_size: 16
-- eval_batch_size: 64
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.9434        | 1.0   | 2812 | 0.9601          |
-| 0.9429        | 2.0   | 5624 | 0.9602          |
+| 0.6363        | 1.0   | 2812 | 0.6465          |
+| 0.6361        | 2.0   | 5624 | 0.6465          |
+| 0.6358        | 3.0   | 8436 | 0.6465          |
 
 
 ### Framework versions
 
 - Transformers 4.24.0
 - Pytorch 1.12.1+cu113
-- Datasets 2.6.1
-- Tokenizers 0.13.1
+- Datasets 2.7.0
+- Tokenizers 0.13.2