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: 0.2849
-- Accuracy: 0.9111
+- Loss: 0.8458
+- Accuracy: 0.7364
 
 ## Model description
 
@@ -39,27 +39,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 3
-- eval_batch_size: 3
+- train_batch_size: 10
+- eval_batch_size: 10
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 200
+- training_steps: 480
+- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.188         | 0.25  | 50   | 0.9450          | 0.6222   |
-| 0.6172        | 1.25  | 100  | 0.4384          | 0.8222   |
-| 0.325         | 2.25  | 150  | 0.2533          | 0.8889   |
-| 0.1939        | 3.25  | 200  | 0.2849          | 0.9111   |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.5803        | 0.2521 | 121  | 0.8145          | 0.6059   |
+| 0.4256        | 1.2521 | 242  | 0.8485          | 0.6580   |
+| 0.3913        | 2.2521 | 363  | 0.9005          | 0.7110   |
+| 0.3751        | 3.2437 | 480  | 0.8458          | 0.7364   |
 
 
 ### Framework versions
 
 - Transformers 4.46.2
 - Pytorch 2.5.1+cu124
-- Datasets 2.21.0
+- Datasets 3.1.0
 - Tokenizers 0.20.3