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: 1.8708
-- Accuracy: 0.3806
+- Loss: 0.1057
+- Accuracy: 0.9677
 
 ## Model description
 
@@ -44,13 +44,17 @@ 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: 75
+- training_steps: 375
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.9035        | 1.0   | 75   | 1.7250          | 0.3429   |
+| 0.9101        | 0.2   | 75   | 0.8777          | 0.6286   |
+| 0.2332        | 1.2   | 150  | 0.3905          | 0.8286   |
+| 0.1484        | 2.2   | 225  | 0.2272          | 0.9429   |
+| 0.0183        | 3.2   | 300  | 0.0616          | 0.9857   |
+| 0.0393        | 4.2   | 375  | 0.0391          | 1.0      |
 
 
 ### Framework versions

runs/May21_00-58-36_8696136f2511/events.out.tfevents.1716253831.8696136f2511.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd81480f44738874df1f027b189ae9166ea4de3b63e58de88e521b2de57e2dc3
+size 734