update model card README.md

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4328
+- Loss: 0.2594
 
 ## Model description
 
@@ -32,29 +32,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 1.87e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
-- mixed_precision_training: Native AMP
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 67   | 0.2870          |
-| No log        | 2.0   | 134  | 0.2818          |
-| No log        | 3.0   | 201  | 0.2921          |
-| No log        | 4.0   | 268  | 0.3125          |
-| No log        | 5.0   | 335  | 0.3431          |
-| No log        | 6.0   | 402  | 0.3812          |
-| No log        | 7.0   | 469  | 0.3979          |
-| 0.3841        | 8.0   | 536  | 0.4125          |
-| 0.3841        | 9.0   | 603  | 0.4289          |
-| 0.3841        | 10.0  | 670  | 0.4328          |
+| 0.3776        | 1.0   | 809  | 0.2698          |
+| 0.27          | 2.0   | 1618 | 0.2615          |
+| 0.2557        | 3.0   | 2427 | 0.2594          |
 
 
 ### Framework versions