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: 0.7333
-- Accuracy: 0.4706
+- Loss: 0.8504
+- Accuracy: 0.7059
 
 ## Model description
 
@@ -37,25 +37,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- learning_rate: 3e-05
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 136
+- training_steps: 68
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6509        | 0.19  | 26   | 0.7615          | 0.4706   |
-| 0.7591        | 1.19  | 52   | 0.7596          | 0.5294   |
-| 0.8024        | 2.19  | 78   | 0.7129          | 0.4706   |
-| 0.7443        | 3.19  | 104  | 0.7310          | 0.4706   |
-| 0.7078        | 4.19  | 130  | 0.7323          | 0.4706   |
-| 0.7078        | 5.04  | 136  | 0.7333          | 0.4706   |
+| 0.4845        | 0.19  | 13   | 0.6341          | 0.5294   |
+| 0.6466        | 1.19  | 26   | 0.9443          | 0.4706   |
+| 0.3798        | 2.19  | 39   | 0.9459          | 0.6471   |
+| 0.3392        | 3.19  | 52   | 1.1101          | 0.6471   |
+| 0.191         | 4.19  | 65   | 0.8548          | 0.6471   |
+| 0.191         | 5.04  | 68   | 0.8504          | 0.7059   |
 
 
 ### Framework versions