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: 0.5470
-- Accuracy: 0.8129
+- Loss: 0.4497
+- Accuracy: 0.8774
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.109         | 0.2568 | 38   | 1.8529          | 0.6      |
-| 0.9259        | 1.2568 | 76   | 1.2052          | 0.5      |
-| 0.4802        | 2.2568 | 114  | 0.6029          | 0.8571   |
-| 0.3519        | 3.2297 | 148  | 0.4827          | 0.8714   |
+| 2.1243        | 0.2568 | 38   | 1.8105          | 0.3857   |
+| 0.9539        | 1.2568 | 76   | 0.9815          | 0.5857   |
+| 0.4701        | 2.2568 | 114  | 0.4805          | 0.8571   |
+| 0.2869        | 3.2297 | 148  | 0.3917          | 0.8714   |
 
 
 ### Framework versions

runs/Oct14_13-48-17_dc6088e9f91b/events.out.tfevents.1728913699.dc6088e9f91b.3595.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d3022f697f1545cb62a625e1a5b088f3bd74fe9bf9ba42d266e65d26a655e7a
-size 9462
+oid sha256:4e1bfc6c233dbfc865c328e19942cfb00d36d6b20f56a1ab0c6a724ce40de1e3
+size 10139

runs/Oct14_13-48-17_dc6088e9f91b/events.out.tfevents.1728913945.dc6088e9f91b.3595.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29740312ac3114f4330945689b71d7f47ca17aa25fe564f86bcb35fcfb0571ff
+size 411