End of training

README.md

@@ -17,8 +17,8 @@ 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: 1.4405
-- Accuracy: 0.5556
+- Loss: 1.6248
+- Accuracy: 0.4188
 
 ## Model description
 
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.6587        | 0.25  | 91   | 1.2941          | 0.4217   |
-| 1.6924        | 1.25  | 182  | 1.3867          | 0.4188   |
-| 1.7352        | 2.25  | 273  | 1.4279          | 0.4644   |
-| 1.8499        | 3.25  | 364  | 1.4405          | 0.5556   |
+| 2.7648        | 0.25  | 91   | 1.3670          | 0.4188   |
+| 1.5767        | 1.25  | 182  | 1.3835          | 0.4217   |
+| 1.8509        | 2.25  | 273  | 1.5909          | 0.4188   |
+| 1.5982        | 3.25  | 364  | 1.6248          | 0.4188   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:338e765c929e246071740ac2b71d0b80da1ae211a1b2fd37797faa3e9bf60974
+oid sha256:9fa7e82b94205b602da8ae6602757820ab3020e593514a75c672581a5c7cb2c2
 size 344943528