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: 0.6237
-- Accuracy: 0.8114
+- Loss: 0.6163
+- Accuracy: 0.7898
 
 ## Model description
 
@@ -43,16 +43,22 @@ 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: 1460
+- training_steps: 3650
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.0135        | 0.25  | 365  | 2.1088          | 0.1443   |
-| 1.6817        | 1.25  | 730  | 2.0997          | 0.3918   |
-| 0.1918        | 2.25  | 1095 | 1.2655          | 0.6186   |
-| 0.4802        | 3.25  | 1460 | 1.1125          | 0.7423   |
+| 1.1996        | 0.1   | 365  | 2.4460          | 0.5567   |
+| 1.4174        | 1.1   | 730  | 0.6252          | 0.8041   |
+| 0.0092        | 2.1   | 1095 | 1.2255          | 0.7629   |
+| 0.765         | 3.1   | 1460 | 0.9238          | 0.7732   |
+| 0.1714        | 4.1   | 1825 | 1.0449          | 0.7938   |
+| 0.09          | 5.1   | 2190 | 1.4747          | 0.7629   |
+| 0.0006        | 6.1   | 2555 | 1.3157          | 0.7835   |
+| 0.0004        | 7.1   | 2920 | 1.6183          | 0.7216   |
+| 0.0012        | 8.1   | 3285 | 1.5373          | 0.7732   |
+| 0.0005        | 9.1   | 3650 | 1.6775          | 0.7629   |
 
 
 ### Framework versions