Model save

README.md

@@ -1,4 +1,5 @@
 ---
+license: cc-by-nc-4.0
 base_model: MCG-NJU/videomae-base
 tags:
 - generated_from_trainer
@@ -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: 1.4122
-- Accuracy: 0.4259
+- Loss: 1.4876
+- Accuracy: 0.3623
 
 ## Model description
 
@@ -37,22 +38,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 108
+- training_steps: 28
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.5888        | 0.25  | 27   | 1.5160          | 0.3519   |
-| 1.6285        | 1.25  | 54   | 1.4788          | 0.3333   |
-| 1.6013        | 2.25  | 81   | 1.4498          | 0.3704   |
-| 1.5937        | 3.25  | 108  | 1.4122          | 0.4259   |
+| No log        | 0.29  | 8    | 1.5153          | 0.3043   |
+| 1.6246        | 1.29  | 16   | 1.4876          | 0.3623   |
+| 1.3937        | 2.29  | 24   | 1.4613          | 0.3333   |
+| 1.3937        | 3.14  | 28   | 1.4523          | 0.3333   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef61151ba7f300d2c4e9a1d81dc896067c9c9e830e9b70d27fcb118b1d4d8246
+oid sha256:9b7bb3477f24034d7dd325b30e31bb8cbbba01933a2f695421c6331ca4c890dd
 size 344988594