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: 0.8304
-- Accuracy: 0.7548
+- Loss: 0.5110
+- Accuracy: 0.8129
 
 ## Model description
 
@@ -44,14 +44,13 @@ 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: 150
+- training_steps: 75
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.8113        | 0.5   | 75   | 1.5966          | 0.3857   |
-| 0.895         | 1.5   | 150  | 0.9440          | 0.6429   |
+| 0.4871        | 1.0   | 75   | 0.7370          | 0.7143   |
 
 
 ### Framework versions

runs/May22_12-56-09_940520f3922b/events.out.tfevents.1716382778.940520f3922b.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002442083b589f464caeb8fdd4480c214698a1bdc75c3e36c9da95aceeef99e6
+size 405