Model save

README.md

@@ -3,6 +3,8 @@ license: cc-by-nc-4.0
 base_model: MCG-NJU/videomae-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: videomae-base-finetuned-ucf101-subset
   results: []
@@ -15,12 +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:
-- eval_loss: 2.2843
-- eval_accuracy: 0.0839
-- eval_runtime: 16.8711
-- eval_samples_per_second: 9.187
-- eval_steps_per_second: 1.185
-- step: 0
+- Loss: 0.4353
+- Accuracy: 0.8581
 
 ## Model description
 
@@ -48,6 +46,16 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - training_steps: 148
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 2.16          | 0.2568 | 38   | 1.7993          | 0.5      |
+| 0.8394        | 1.2568 | 76   | 0.8820          | 0.7      |
+| 0.4228        | 2.2568 | 114  | 0.5060          | 0.8429   |
+| 0.3029        | 3.2297 | 148  | 0.3845          | 0.8857   |
+
+
 ### Framework versions
 
 - Transformers 4.41.0

runs/May18_20-17-26_DESKTOP-SGO0ICV/events.out.tfevents.1716035095.DESKTOP-SGO0ICV.14384.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a78ecc30cc65cdd25286f42704e4cf05611cfb97b20ad00838a424007df449
+size 411