Model save

README.md

@@ -1,5 +1,6 @@
 ---
 license: cc-by-nc-4.0
+base_model: MCG-NJU/videomae-base
 tags:
 - generated_from_trainer
 metrics:
@@ -16,8 +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: 0.5036
-- Accuracy: 0.8581
+- Loss: 0.4451
+- Accuracy: 0.8452
 
 ## Model description
 
@@ -47,17 +48,17 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.0323        | 0.26  | 38   | 1.6402          | 0.5571   |
-| 0.8081        | 1.26  | 76   | 0.8534          | 0.6857   |
-| 0.4099        | 2.26  | 114  | 0.5761          | 0.8429   |
-| 0.255         | 3.23  | 148  | 0.3967          | 0.9      |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 1.0504        | 0.2568 | 38   | 0.9655          | 0.7286   |
+| 0.5387        | 1.2568 | 76   | 0.5637          | 0.7571   |
+| 0.2298        | 2.2568 | 114  | 0.4616          | 0.8286   |
+| 0.13          | 3.2297 | 148  | 0.4940          | 0.8429   |
 
 
 ### Framework versions
 
-- Transformers 4.29.0
-- Pytorch 2.2.2
-- Datasets 2.13.2
-- Tokenizers 0.13.3
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu118
+- Datasets 2.19.0
+- Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7889ad298cc0b88e49c0245ec89e9a0de00236f4e55ea79694030c83fc029f8
+oid sha256:3969cb9b6b9c1fa1e9bae622aa9175b97512c83304e662053e029a78f80a514f
 size 344961984