End of training

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: 0.9609
-- Accuracy: 0.6571
+- Loss: 0.8340
+- Accuracy: 0.7571
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.2979        | 0.2639 | 19   | 2.0789          | 0.2429   |
-| 1.8145        | 1.2639 | 38   | 1.5275          | 0.4714   |
-| 1.1183        | 2.2639 | 57   | 1.0960          | 0.5714   |
-| 0.7046        | 3.2083 | 72   | 0.9609          | 0.6571   |
+| 2.3005        | 0.2639 | 19   | 2.0589          | 0.4286   |
+| 1.7915        | 1.2639 | 38   | 1.3942          | 0.5      |
+| 0.9689        | 2.2639 | 57   | 0.9386          | 0.6571   |
+| 0.6231        | 3.2083 | 72   | 0.8340          | 0.7571   |
 
 
 ### Framework versions