Model save

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: 0.3937
-- Accuracy: 0.9355
+- Loss: 0.5380
+- Accuracy: 0.8258
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.1381        | 0.2568 | 38   | 1.8478          | 0.5429   |
-| 0.9543        | 1.2568 | 76   | 0.9674          | 0.6571   |
-| 0.4914        | 2.2568 | 114  | 0.6266          | 0.7429   |
-| 0.3415        | 3.2297 | 148  | 0.4506          | 0.8429   |
+| 2.1259        | 0.2568 | 38   | 1.9268          | 0.2714   |
+| 1.0429        | 1.2568 | 76   | 1.0447          | 0.6429   |
+| 0.5065        | 2.2568 | 114  | 0.6279          | 0.7714   |
+| 0.3014        | 3.2297 | 148  | 0.4685          | 0.8857   |
 
 
 ### Framework versions

runs/Dec13_14-41-40_2fa76351bb1a/events.out.tfevents.1734102613.2fa76351bb1a.6043.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c111e1884498fcdcf153ff9a636dc17533a2fe24e0accb42f3d79e80eb9bed
+size 411