End of training

README.md

@@ -16,7 +16,7 @@ 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: 0.5036
+- Loss: 0.4682
 
 ## Model description
 
@@ -48,10 +48,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.2077        | 0.2568 | 38   | 1.9686          |
-| 1.2212        | 1.2568 | 76   | 1.1918          |
-| 0.5977        | 2.2568 | 114  | 0.6955          |
-| 0.3278        | 3.2297 | 148  | 0.5036          |
+| 2.1119        | 0.2568 | 38   | 1.9120          |
+| 1.1109        | 1.2568 | 76   | 0.9462          |
+| 0.5405        | 2.2568 | 114  | 0.6334          |
+| 0.3395        | 3.2297 | 148  | 0.4682          |
 
 
 ### Framework versions

runs/Sep24_19-36-42_f4ed9dfa5b88/events.out.tfevents.1727206602.f4ed9dfa5b88.22998.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78961e458ec790653c7049ea6b80fa1e830e63b578f482bdc1b726a1e5fcef4f
-size 9301
+oid sha256:70fa0a9d2b41ae57c889cd6460b2d5efafd542b96b12a1cd5eb3b1bf2bf59c14
+size 9926