Model save

README.md

@@ -18,8 +18,8 @@ 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: 0.7028
-- Accuracy: 0.5
+- Loss: 0.7032
+- Accuracy: 0.6667
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.25  | 1    | 0.7028          | 0.5      |
-| No log        | 1.25  | 2    | 0.7072          | 0.5      |
-| No log        | 2.25  | 3    | 0.7156          | 0.5      |
-| No log        | 3.25  | 4    | 0.7224          | 0.5      |
+| No log        | 0.25  | 1    | 0.7032          | 0.6667   |
+| No log        | 1.25  | 2    | 0.5820          | 0.6667   |
+| No log        | 2.25  | 3    | 0.5235          | 0.6667   |
+| No log        | 3.25  | 4    | 0.4957          | 0.6667   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c74a2263dc29d8d34e608f20da41149d97cfd81a3fddbfd149258cd18860621d
+oid sha256:f72dd143ecffd5001bb20bd9c1c6cd4146bfb717ceba061e00bb858a4c11e11c
 size 344937368