Model save

README.md

@@ -18,9 +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: 0.3756
-- Model Preparation Time: 0.0017
-- Accuracy: 0.9161
+- Loss: 1.4163
+- Accuracy: 0.2368
 
 ## Model description
 
@@ -46,21 +45,21 @@ 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: 148
+- training_steps: 96
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Model Preparation Time | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:----------------------:|:--------:|
-| 2.1284        | 0.2568 | 38   | 1.8426          | 0.0017                 | 0.4286   |
-| 0.8904        | 1.2568 | 76   | 0.7788          | 0.0017                 | 0.7429   |
-| 0.3888        | 2.2568 | 114  | 0.4578          | 0.0017                 | 0.7714   |
-| 0.2734        | 3.2297 | 148  | 0.3996          | 0.0017                 | 0.7571   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.4528        | 1.0   | 25   | 1.4396          | 0.2625   |
+| 1.4244        | 2.0   | 50   | 1.4033          | 0.25     |
+| 1.4495        | 3.0   | 75   | 1.3919          | 0.25     |
+| 1.3912        | 3.84  | 96   | 1.3885          | 0.25     |
 
 
 ### Framework versions
 
 - Transformers 4.44.1
-- Pytorch 2.2.2
-- Datasets 2.21.0
+- Pytorch 2.4.0
+- Datasets 2.19.1
 - Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65075debdecc9e839e978690049134982dec88fc45777dafb21566f8a02e9b80
+oid sha256:cee842c76ef3cbbb4e60494aafec758ad2206efd09bac5f8737c0986aa958715
 size 344943528