Model save

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: 0.7916
-- Accuracy: 0.7972
+- Loss: 0.9940
+- Accuracy: 0.5408
 
 ## Model description
 
@@ -39,8 +39,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -51,14 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 1.6087        | 0.1316 | 10   | 1.8483          | 0.2597   |
-| 1.3273        | 1.1316 | 20   | 1.4452          | 0.2983   |
-| 1.2351        | 2.1316 | 30   | 1.5890          | 0.2799   |
-| 1.1635        | 3.1316 | 40   | 1.3830          | 0.2910   |
-| 1.0374        | 4.1316 | 50   | 1.3682          | 0.3002   |
-| 0.9699        | 5.1316 | 60   | 1.2128          | 0.5322   |
-| 0.8748        | 6.1316 | 70   | 1.0850          | 0.5562   |
-| 0.8748        | 7.0789 | 76   | 1.0721          | 0.5599   |
+| 1.5445        | 0.2632 | 20   | 1.6095          | 0.1123   |
+| 1.2942        | 1.2632 | 40   | 1.2199          | 0.5120   |
+| 1.2008        | 2.2632 | 60   | 1.1847          | 0.5267   |
+| 1.0759        | 3.2105 | 76   | 1.0455          | 0.5525   |
 
 
 ### Framework versions