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: 0.4003
-- Accuracy: 0.8516
+- Loss: 0.3660
+- Accuracy: 0.9032
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.1814        | 0.2568 | 38   | 1.8574          | 0.4714   |
-| 0.8234        | 1.2568 | 76   | 0.9412          | 0.7      |
-| 0.467         | 2.2568 | 114  | 0.5704          | 0.7571   |
-| 0.3374        | 3.2297 | 148  | 0.4216          | 0.8714   |
+| 2.0976        | 0.2568 | 38   | 1.6405          | 0.6429   |
+| 0.682         | 1.2568 | 76   | 0.7726          | 0.8      |
+| 0.4104        | 2.2568 | 114  | 0.4206          | 0.8571   |
+| 0.2605        | 3.2297 | 148  | 0.3388          | 0.9      |
 
 
 ### Framework versions

runs/Oct14_15-11-34_71fb6b0700bc/events.out.tfevents.1728918696.71fb6b0700bc.15107.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b65c793e99026cec3004a02b24c4613c81722e4136661facd21579d5bc285c
-size 9462
+oid sha256:5ff62ba09609919c48275ab9a42c35c9c7a0911b88784e9b5da86bc23895cb74
+size 10139

runs/Oct14_15-11-34_71fb6b0700bc/events.out.tfevents.1728918935.71fb6b0700bc.15107.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce284a92b40765bea808299d6056894738f48e8a2387e585aea40879203250ae
+size 411