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: 0.2233
-- Accuracy: 0.9226
+- Loss: 0.3907
+- Accuracy: 0.8903
 
 ## Model description
 
@@ -49,15 +49,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.8073        | 0.25  | 75   | 1.3999          | 0.6857   |
-| 0.9688        | 1.25  | 150  | 0.6959          | 0.7286   |
-| 0.266         | 2.25  | 225  | 0.4545          | 0.7714   |
-| 0.2419        | 3.25  | 300  | 0.2742          | 0.9      |
+| 1.897         | 0.25  | 75   | 1.4589          | 0.6      |
+| 0.949         | 1.25  | 150  | 0.6212          | 0.8      |
+| 0.3123        | 2.25  | 225  | 0.3480          | 0.8714   |
+| 0.3394        | 3.25  | 300  | 0.1887          | 0.9143   |
 
 
 ### Framework versions
 
-- Transformers 4.30.1
+- Transformers 4.30.2
 - Pytorch 2.0.1+cu118
-- Datasets 2.12.0
+- Datasets 2.13.1
 - Tokenizers 0.13.3