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: 1.4937
-- Accuracy: 0.5325
+- Loss: 0.4584
+- Accuracy: 0.8323
 
 ## Model description
 
@@ -43,14 +43,14 @@ 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: 144
+- training_steps: 300
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.51  | 73   | 1.8364          | 0.5676   |
-| 2.1369        | 1.49  | 144  | 1.3739          | 0.6486   |
+| 2.0705        | 0.5   | 150  | 1.0644          | 0.6286   |
+| 0.555         | 1.5   | 300  | 0.4974          | 0.7571   |
 
 
 ### Framework versions