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: 0.3661
-- Accuracy: 0.8452
+- Loss: 0.3216
+- Accuracy: 0.8839
 
 ## Model description
 
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.0257        | 0.25  | 75   | 1.4214          | 0.6143   |
-| 1.0258        | 1.25  | 150  | 0.6302          | 0.8      |
-| 0.3566        | 2.25  | 225  | 0.3157          | 0.9286   |
-| 0.3042        | 3.25  | 300  | 0.2149          | 0.9286   |
+| 1.725         | 0.25  | 75   | 1.4550          | 0.5857   |
+| 0.9129        | 1.25  | 150  | 0.6065          | 0.8      |
+| 0.2847        | 2.25  | 225  | 0.3712          | 0.8429   |
+| 0.1871        | 3.25  | 300  | 0.2804          | 0.9      |
 
 
 ### Framework versions

runs/May11_05-13-35_416a2f8f7915/events.out.tfevents.1715405313.416a2f8f7915.5049.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017603fb785cb703282acd833994ba3544f7724afa620e59cde20d7d1d26f147
+size 411