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: 0.5838
-- Accuracy: 0.7677
+- Loss: 0.3045
+- Accuracy: 0.9226
 
 ## Model description
 
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.7455        | 0.25  | 75   | 1.3021          | 0.5857   |
-| 0.9476        | 1.25  | 150  | 0.5081          | 0.8429   |
-| 0.3926        | 2.25  | 225  | 0.3852          | 0.7714   |
-| 0.2059        | 3.25  | 300  | 0.3989          | 0.8429   |
+| 1.7867        | 0.25  | 75   | 1.3081          | 0.5429   |
+| 0.7871        | 1.25  | 150  | 0.5381          | 0.7857   |
+| 0.2923        | 2.25  | 225  | 0.4681          | 0.7571   |
+| 0.2033        | 3.25  | 300  | 0.2787          | 0.9      |
 
 
 ### Framework versions

runs/May12_18-11-57_gcp/events.out.tfevents.1715538234.gcp.1903.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08856973faf170e6a22240d6c0b2f1ab41b6e78dd87851ec5f789df1298d44e
+size 411