End of training

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: 0.1923
-- Accuracy: 0.9286
+- Loss: 0.2729
+- Accuracy: 0.8429
 
 ## Model description
 
@@ -50,15 +50,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.4714        | 0.25  | 150  | 1.3539          | 0.4429   |
-| 0.6439        | 1.25  | 300  | 0.9757          | 0.5857   |
-| 0.2072        | 2.25  | 450  | 0.2924          | 0.9286   |
-| 0.1924        | 3.25  | 600  | 0.1923          | 0.9286   |
+| 1.4161        | 0.25  | 150  | 1.2126          | 0.5      |
+| 0.3558        | 1.25  | 300  | 0.5057          | 0.7714   |
+| 0.2107        | 2.25  | 450  | 0.3836          | 0.8143   |
+| 0.3386        | 3.25  | 600  | 0.2729          | 0.8429   |
 
 
 ### Framework versions
 
-- Transformers 4.32.1
+- Transformers 4.33.0
 - Pytorch 1.10.0+cu113
 - Datasets 2.14.4
 - Tokenizers 0.13.3