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: 1.8301
-- Accuracy: 0.3677
+- Loss: 1.8583
+- Accuracy: 0.3226
 
 ## Model description
 
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.886         | 1.0   | 75   | 1.6964          | 0.3429   |
+| 1.8974        | 1.0   | 75   | 1.5608          | 0.5714   |
 
 
 ### Framework versions

runs/May24_14-33-48_4b27c78cc6c7/events.out.tfevents.1716561418.4b27c78cc6c7.35.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17489f31e866cf9957a2850abae7266377c6084c31b5131eab77e48295c781a1
+size 405