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: 0.3160
-- Accuracy: 0.8968
+- Loss: 0.5739
+- Accuracy: 0.8
 
 ## Model description
 
@@ -44,17 +44,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 750
+- training_steps: 300
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.5236        | 0.2   | 150  | 1.5999          | 0.3143   |
-| 0.7562        | 1.2   | 300  | 0.7772          | 0.7571   |
-| 0.1744        | 2.2   | 450  | 0.6027          | 0.8286   |
-| 0.6707        | 3.2   | 600  | 0.4752          | 0.8286   |
-| 0.0057        | 4.2   | 750  | 0.0703          | 0.9714   |
+| 1.1326        | 0.5   | 150  | 1.2260          | 0.5714   |
+| 0.9273        | 1.5   | 300  | 0.5721          | 0.8286   |
 
 
 ### Framework versions