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: 1.8751
-- Accuracy: 0.4127
+- Loss: 0.3194
+- Accuracy: 0.8571
 
 ## Model description
 
@@ -43,13 +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: 75
+- training_steps: 300
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.916         | 1.0   | 75   | 1.8321          | 0.4038   |
+| 1.8741        | 0.25  | 75   | 1.5246          | 0.5769   |
+| 0.958         | 1.25  | 150  | 0.4663          | 0.8654   |
+| 0.2844        | 2.25  | 225  | 0.1899          | 0.9615   |
+| 0.1966        | 3.25  | 300  | 0.1445          | 0.9615   |
 
 
 ### Framework versions