update model card README.md

README.md

@@ -16,8 +16,8 @@ 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: 0.5278
-- Accuracy: 0.7935
+- Loss: 1.2120
+- Accuracy: 0.0
 
 ## Model description
 
@@ -37,22 +37,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- 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: 148
+- training_steps: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.1711        | 0.26  | 38   | 1.7583          | 0.5143   |
-| 0.8671        | 1.26  | 76   | 0.8746          | 0.7714   |
-| 0.5099        | 2.26  | 114  | 0.5396          | 0.8143   |
-| 0.3309        | 3.23  | 148  | 0.4273          | 0.8857   |
+| No log        | 0.5   | 1    | 1.2203          | 0.0      |
+| No log        | 1.5   | 2    | 1.0272          | 0.0      |
 
 
 ### Framework versions