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: 0.5521
-- Accuracy: 0.8601
+- Loss: 1.1702
+- Accuracy: 0.7817
 
 ## Model description
 
@@ -50,12 +50,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.6087        | 0.17  | 270  | 1.6756          | 0.3720   |
-| 1.1954        | 1.17  | 540  | 1.1006          | 0.5990   |
-| 0.9847        | 2.17  | 810  | 0.9660          | 0.6715   |
-| 0.0737        | 3.17  | 1080 | 0.6722          | 0.8309   |
-| 0.0054        | 4.17  | 1350 | 0.5286          | 0.8502   |
-| 0.1586        | 5.17  | 1620 | 0.5369          | 0.8696   |
+| 2.4355        | 0.17  | 270  | 2.3796          | 0.4879   |
+| 0.8776        | 1.17  | 540  | 1.4838          | 0.6812   |
+| 0.0146        | 2.17  | 810  | 1.0878          | 0.7391   |
+| 2.1899        | 3.17  | 1080 | 1.3479          | 0.7295   |
+| 0.0019        | 4.17  | 1350 | 0.8615          | 0.8261   |
+| 0.0021        | 5.17  | 1620 | 0.6128          | 0.8551   |
 
 
 ### Framework versions

runs/Dec04_18-06-44_ff076e552dd6/events.out.tfevents.1701714429.ff076e552dd6.1376.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:779a74ebad21733c3852a2e14ef741e397edcada15f6e65029347142a8d7a770
+size 411