Model save

README.md

@@ -17,7 +17,7 @@ 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: 0.8817
+- Loss: 0.8993
 - Accuracy: 0.7633
 
 ## Model description
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.7968        | 0.2527 | 95   | 0.7985          | 0.7875   |
-| 0.8744        | 1.2527 | 190  | 0.7837          | 0.7875   |
-| 0.9479        | 2.2527 | 285  | 0.7812          | 0.7875   |
-| 0.8282        | 3.2420 | 376  | 0.7884          | 0.7875   |
+| 0.8086        | 0.2527 | 95   | 0.8059          | 0.7875   |
+| 0.8755        | 1.2527 | 190  | 0.7765          | 0.7875   |
+| 0.9334        | 2.2527 | 285  | 0.7846          | 0.7875   |
+| 0.8263        | 3.2420 | 376  | 0.7845          | 0.7875   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de948e9856555b259083b0a438f828372ba9ffecd5d52a2f105782c903a2b398
+oid sha256:a204470da53e1dfde725cb3015d524597f5067b1cfc3fd1cc4a3b6cffd1c5ceb
 size 344943528