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: 0.3850
-- Accuracy: 0.8395
+- Loss: 0.5372
+- Accuracy: 0.7978
 
 ## Model description
 
@@ -45,17 +45,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 210
+- training_steps: 265
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.0368        | 0.2048 | 43   | 2.0273          | 0.2933   |
-| 1.1679        | 1.2048 | 86   | 1.0919          | 0.56     |
-| 0.5097        | 2.2048 | 129  | 0.5804          | 0.8267   |
-| 0.2293        | 3.2048 | 172  | 0.4855          | 0.8267   |
-| 0.1882        | 4.1810 | 210  | 0.3435          | 0.9067   |
+| 2.2682        | 0.2038 | 54   | 2.0374          | 0.3214   |
+| 1.0997        | 1.2038 | 108  | 1.0029          | 0.6667   |
+| 0.6996        | 2.2038 | 162  | 0.7633          | 0.7857   |
+| 0.7031        | 3.2038 | 216  | 0.5940          | 0.7857   |
+| 0.4078        | 4.1849 | 265  | 0.5297          | 0.8452   |
 
 
 ### Framework versions

runs/Oct29_18-26-07_7c56bb07786b/events.out.tfevents.1730226387.7c56bb07786b.1505.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8af652cf9fae209590c4dad84dea750bc85fb4175a920d298228ed7fc6f1322
-size 12518
+oid sha256:f124c1836d11a295c5121460ef8150c1f25fc3c1e9d50d025e121532a214839d
+size 13195

runs/Oct29_18-26-07_7c56bb07786b/events.out.tfevents.1730227090.7c56bb07786b.1505.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6690d3d3d8135b37dc4a7d03b3914f43d99d258eb1e258b70f5a5832c983c991
+size 411