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: 0.2753
-- Accuracy: 0.9097
+- Loss: 0.4599
+- Accuracy: 0.8284
 
 ## Model description
 
@@ -43,16 +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: 600
+- training_steps: 604
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.5351        | 0.25  | 150  | 1.7104          | 0.5286   |
-| 0.8621        | 1.25  | 300  | 0.7072          | 0.7429   |
-| 0.2002        | 2.25  | 450  | 0.5906          | 0.8286   |
-| 0.4786        | 3.25  | 600  | 0.2855          | 0.9      |
+| 1.3861        | 0.25  | 151  | 1.5182          | 0.4048   |
+| 0.6672        | 1.25  | 302  | 0.9395          | 0.7024   |
+| 0.1478        | 2.25  | 453  | 0.7313          | 0.7381   |
+| 0.2596        | 3.25  | 604  | 0.5432          | 0.7738   |
 
 
 ### Framework versions