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: 0.5070
-- Accuracy: 0.8
+- Loss: 1.1199
+- Accuracy: 0.2669
 
 ## 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: 148
+- training_steps: 32
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.1013        | 0.26  | 38   | 1.6601          | 0.5429   |
-| 0.8317        | 1.26  | 76   | 1.0476          | 0.5429   |
-| 0.4313        | 2.26  | 114  | 0.5404          | 0.8143   |
-| 0.2871        | 3.23  | 148  | 0.4551          | 0.8143   |
+| No log        | 0.28  | 9    | 1.1095          | 0.3678   |
+| 1.1547        | 1.28  | 18   | 1.0840          | 0.2515   |
+| 1.0917        | 2.28  | 27   | 1.0370          | 0.4855   |
+| 1.0976        | 3.16  | 32   | 1.0296          | 0.4974   |
 
 
 ### Framework versions