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: 0.6831
-- Accuracy: 0.7714
+- Loss: 0.1994
+- Accuracy: 0.9290
 
 ## Model description
 
@@ -38,22 +38,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- train_batch_size: 2
+- eval_batch_size: 2
 - 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: 600
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.6613        | 0.25  | 300  | 1.1489          | 0.6      |
-| 1.0534        | 1.25  | 600  | 0.8595          | 0.6429   |
-| 0.5787        | 2.25  | 900  | 1.2630          | 0.7429   |
-| 0.326         | 3.25  | 1200 | 0.6831          | 0.7714   |
+| 1.199         | 0.25  | 150  | 1.1445          | 0.6      |
+| 0.9296        | 1.25  | 300  | 0.4473          | 0.8143   |
+| 0.0549        | 2.25  | 450  | 0.3688          | 0.8429   |
+| 0.4483        | 3.25  | 600  | 0.2308          | 0.9286   |
 
 
 ### Framework versions