update model card README.md

README.md

@@ -16,8 +16,8 @@ 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: 0.5838
-- Accuracy: 0.8194
+- Loss: 0.4559
+- Accuracy: 0.8698
 
 ## Model description
 
@@ -43,15 +43,16 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 111
+- training_steps: 148
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.1044        | 0.34  | 38   | 1.7608          | 0.4915   |
-| 0.875         | 1.34  | 76   | 0.7820          | 0.7350   |
-| 0.5103        | 2.32  | 111  | 0.6441          | 0.8248   |
+| 2.1321        | 0.26  | 38   | 1.7063          | 0.5      |
+| 0.7513        | 1.26  | 76   | 0.8875          | 0.6757   |
+| 0.3882        | 2.26  | 114  | 0.4695          | 0.8243   |
+| 0.2671        | 3.23  | 148  | 0.3920          | 0.8243   |
 
 
 ### Framework versions