End of training

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: 0.0597
-- Accuracy: 0.9857
+- Loss: 0.5329
+- Accuracy: 0.8
 
 ## Model description
 
@@ -50,14 +50,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.994         | 0.12  | 75   | 1.7537          | 0.4429   |
-| 1.1229        | 1.12  | 150  | 0.6333          | 0.7714   |
-| 0.4459        | 2.12  | 225  | 0.5334          | 0.7429   |
-| 0.4052        | 3.12  | 300  | 0.4663          | 0.8429   |
-| 0.2089        | 4.12  | 375  | 0.4041          | 0.9      |
-| 0.0095        | 5.12  | 450  | 0.0874          | 0.9857   |
-| 0.0059        | 6.12  | 525  | 0.0583          | 0.9857   |
-| 0.0053        | 7.12  | 600  | 0.0597          | 0.9857   |
+| 1.2256        | 0.12  | 75   | 1.1427          | 0.6143   |
+| 0.6761        | 1.12  | 150  | 0.7566          | 0.6857   |
+| 0.7232        | 2.12  | 225  | 0.7386          | 0.6857   |
+| 0.1706        | 3.12  | 300  | 0.6110          | 0.8429   |
+| 0.0644        | 4.12  | 375  | 0.3533          | 0.8429   |
+| 0.456         | 5.12  | 450  | 0.4699          | 0.8286   |
+| 0.1312        | 6.12  | 525  | 0.5655          | 0.8286   |
+| 0.0827        | 7.12  | 600  | 0.5329          | 0.8      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a5dc792be2b5950e811c97cfe527e26e58f920938b44c3b6ec0553855f40ce8
+oid sha256:6e646f84683acd75473a8ae23b22d99713d29be6031b457908074a23d660a406
 size 344961984