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: 2.5342
-- Accuracy: 0.75
+- Loss: 1.1101
+- Accuracy: 0.95
 
 ## Model description
 
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 3.5424        | 0.2586 | 30   | 3.2567          | 0.1      |
-| 3.291         | 1.2586 | 60   | 3.1067          | 0.2      |
-| 3.2726        | 2.2586 | 90   | 2.8033          | 0.7      |
-| 2.714         | 3.2241 | 116  | 2.5360          | 0.75     |
+| 3.1207        | 0.2586 | 30   | 2.6261          | 0.425    |
+| 2.6077        | 1.2586 | 60   | 1.8453          | 0.875    |
+| 2.1174        | 2.2586 | 90   | 1.3487          | 0.9      |
+| 1.6021        | 3.2241 | 116  | 1.1155          | 0.975    |
 
 
 ### Framework versions

runs/Sep08_17-25-35_7ad04907aae0/events.out.tfevents.1725826471.7ad04907aae0.36.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1281e582a2a768feff0933d045698f78fbc4e55bb0ecb152b50c8c30945cab
+size 405