update model card README.md

README.md

@@ -2,6 +2,8 @@
 license: cc-by-nc-4.0
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: videomae-base-finetuned-ucf101-subset
   results: []
@@ -13,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 # videomae-base-finetuned-ucf101-subset
 
 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: 0.2630
+- Accuracy: 0.9032
 
 ## Model description
 
@@ -40,6 +45,20 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - training_steps: 300
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.7999        | 0.13  | 38   | 0.7968          | 0.7143   |
+| 0.3574        | 1.13  | 76   | 0.6632          | 0.7571   |
+| 0.1651        | 2.13  | 114  | 0.3926          | 0.8429   |
+| 0.0843        | 3.13  | 152  | 0.3751          | 0.8714   |
+| 0.1116        | 4.13  | 190  | 0.3232          | 0.9286   |
+| 0.0123        | 5.13  | 228  | 0.1498          | 0.9429   |
+| 0.0188        | 6.13  | 266  | 0.4283          | 0.9      |
+| 0.0146        | 7.11  | 300  | 0.4197          | 0.9      |
+
+
 ### Framework versions
 
 - Transformers 4.28.1