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: 0.3493
-- Accuracy: 0.9161
+- Loss: 0.4043
+- Accuracy: 0.8968
 
 ## Model description
 
@@ -50,15 +50,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.8486        | 0.25  | 75   | 1.5844          | 0.4571   |
-| 0.9248        | 1.25  | 150  | 0.8662          | 0.7143   |
-| 0.3441        | 2.25  | 225  | 0.3369          | 0.8857   |
-| 0.2896        | 3.25  | 300  | 0.1827          | 0.9714   |
+| 1.835         | 0.25  | 75   | 1.5384          | 0.4143   |
+| 0.5822        | 1.25  | 150  | 0.6968          | 0.8      |
+| 0.2967        | 2.25  | 225  | 0.3601          | 0.9143   |
+| 0.0952        | 3.25  | 300  | 0.2773          | 0.9      |
 
 
 ### Framework versions
 
-- Transformers 4.32.1
+- Transformers 4.33.2
 - Pytorch 2.0.1+cu118
-- Datasets 2.14.4
+- Datasets 2.14.5
 - Tokenizers 0.13.3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffbe1ac69a3d44a33dc39e3ddf6f8f30611a2d6e88d0f6d660820a64c129c7b7
+oid sha256:c0b6492e5e50cb4f9c413b73830ff0bec4f449f1d0dbb252dee8f7ef381ff406
 size 345003509