Model save

README.md

@@ -14,7 +14,7 @@ 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: 3.5407
+- Loss: 3.2885
 
 ## Model description
 
@@ -41,16 +41,17 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 5
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 491  | 4.0977          |
-| No log        | 2.0   | 982  | 3.7601          |
-| No log        | 3.0   | 1473 | 3.6330          |
-| No log        | 4.0   | 1964 | 3.5690          |
-| No log        | 5.0   | 2455 | 3.5407          |
+| 4.8834        | 1.0   | 501  | 3.9087          |
+| 3.6523        | 2.0   | 1002 | 3.5352          |
+| 3.3936        | 3.0   | 1503 | 3.3920          |
+| 3.2593        | 4.0   | 2004 | 3.3206          |
+| 3.1806        | 5.0   | 2505 | 3.2885          |
 
 
 ### Framework versions