End of training

README.md

@@ -18,8 +18,8 @@ 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: 0.3360
-- Accuracy: 0.8143
+- Loss: 0.2697
+- Accuracy: 0.9429
 
 ## Model description
 
@@ -51,14 +51,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.6246        | 0.25  | 75   | 1.5693          | 0.4286   |
-| 0.7032        | 1.25  | 150  | 0.7640          | 0.7      |
-| 0.321         | 2.25  | 225  | 0.3456          | 0.8      |
-| 0.1922        | 3.25  | 300  | 0.3360          | 0.8143   |
+| 1.8661        | 0.25  | 75   | 1.7027          | 0.3429   |
+| 0.7817        | 1.25  | 150  | 0.7355          | 0.7571   |
+| 0.4118        | 2.25  | 225  | 0.4649          | 0.8571   |
+| 0.2132        | 3.25  | 300  | 0.2697          | 0.9429   |
 
 
 ### Framework versions
 
-- Transformers 4.47.0.dev0
+- Transformers 4.46.3
 - Pytorch 2.1.1+cu121
+- Datasets 3.1.0
 - Tokenizers 0.20.3