Model save

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: 0.2350
-- Accuracy: 0.9161
+- Loss: 0.6944
+- Accuracy: 0.8205
 
 ## Model description
 
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.1547        | 0.5   | 75   | 0.3546          | 0.9143   |
-| 0.1088        | 1.5   | 150  | 0.1503          | 0.9571   |
+| 0.0433        | 0.5   | 75   | 0.3569          | 0.8857   |
+| 0.0047        | 1.5   | 150  | 0.3063          | 0.9429   |
 
 
 ### Framework versions

runs/May22_15-46-58_b08fa7a48520/events.out.tfevents.1716393129.b08fa7a48520.34.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e010ff645b41ba3d56da868c6fe62c1c19c151d94459fd20d163544e6e29f205
+size 411