Model save

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8320
+- Loss: 2.9093
 - Accuracy: 0.2
 
 ## Model description
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 3.4164        | 0.33  | 20   | 2.9580          | 0.1      |
-| 3.1344        | 1.33  | 40   | 2.8666          | 0.2      |
-| 2.7856        | 2.33  | 60   | 2.8320          | 0.2      |
+| 3.4345        | 0.33  | 20   | 2.9824          | 0.05     |
+| 3.3011        | 1.33  | 40   | 2.9158          | 0.15     |
+| 3.0027        | 2.33  | 60   | 2.9093          | 0.2      |
 
 
 ### Framework versions