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: 0.3167
-- Accuracy: 0.9032
+- Loss: 0.3532
+- Accuracy: 0.8903
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.3516        | 0.25  | 150  | 1.3336          | 0.5571   |
-| 1.0445        | 1.25  | 300  | 0.8041          | 0.7714   |
-| 0.1752        | 2.25  | 450  | 0.7214          | 0.7286   |
-| 0.1347        | 3.25  | 600  | 0.2863          | 0.9143   |
+| 1.2945        | 0.25  | 150  | 1.1367          | 0.5143   |
+| 0.8621        | 1.25  | 300  | 0.7921          | 0.7857   |
+| 0.2108        | 2.25  | 450  | 0.5836          | 0.7857   |
+| 0.0447        | 3.25  | 600  | 0.3807          | 0.8714   |
 
 
 ### Framework versions

runs/Nov30_08-17-15_4a534e3efb22/events.out.tfevents.1732955614.4a534e3efb22.2277.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d281512f3ed3599dfe022520b5dc10c2cb3c6c975f009679933bdbc51588da1d
+size 411