Model save

README.md

@@ -18,7 +18,7 @@ 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: 0.4523
+- Loss: 0.5559
 - Accuracy: 0.8529
 
 ## Model description
@@ -39,24 +39,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 3
+- eval_batch_size: 3
 - 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: 1200
+- training_steps: 1600
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
-|:-------------:|:-------:|:----:|:---------------:|:--------:|
-| 1.6881        | 15.0042 | 200  | 1.6327          | 0.1765   |
-| 1.6118        | 30.0083 | 400  | 1.6022          | 0.2353   |
-| 1.3647        | 46.0017 | 600  | 1.3752          | 0.3824   |
-| 0.6254        | 61.0058 | 800  | 1.4182          | 0.3529   |
-| 0.4048        | 76.01   | 1000 | 0.6370          | 0.8235   |
-| 0.1016        | 92.0033 | 1200 | 0.4523          | 0.8529   |
+| Training Loss | Epoch    | Step | Validation Loss | Accuracy |
+|:-------------:|:--------:|:----:|:---------------:|:--------:|
+| 0.9168        | 55.0031  | 500  | 1.1491          | 0.5294   |
+| 0.3827        | 111.0006 | 1000 | 0.7479          | 0.8235   |
+| 0.0043        | 166.0037 | 1500 | 0.5559          | 0.8529   |
 
 
 ### Framework versions