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: 0.3910
-- Accuracy: 0.8839
+- Loss: 1.4294
+- Accuracy: 0.5290
 
 ## Model description
 
@@ -44,21 +44,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 600
+- training_steps: 150
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.2544        | 0.25  | 150  | 1.3703          | 0.4429   |
-| 1.0825        | 1.25  | 300  | 0.6761          | 0.7429   |
-| 0.2885        | 2.25  | 450  | 0.6104          | 0.8286   |
-| 0.262         | 3.25  | 600  | 0.0935          | 0.9857   |
+| 1.3265        | 1.0   | 150  | 1.2609          | 0.6286   |
 
 
 ### Framework versions
 
-- Transformers 4.33.2
+- Transformers 4.34.0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
-- Tokenizers 0.13.3
+- Tokenizers 0.14.1