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: 0.6089
-- Accuracy: 0.6111
+- Loss: 0.7005
+- Accuracy: 0.5455
 
 ## 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: 48
+- training_steps: 32
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.1136        | 0.25  | 12   | 0.8848          | 0.5556   |
-| 0.8673        | 1.25  | 24   | 0.7142          | 0.7222   |
-| 0.7111        | 2.25  | 36   | 0.6508          | 0.5      |
-| 0.4491        | 3.25  | 48   | 0.6089          | 0.6111   |
+| No log        | 0.28  | 9    | 0.8633          | 0.4545   |
+| 0.8381        | 1.28  | 18   | 0.6962          | 0.5455   |
+| 0.6628        | 2.28  | 27   | 0.6852          | 0.5455   |
+| 0.6392        | 3.16  | 32   | 0.7005          | 0.5455   |
 
 
 ### Framework versions