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: 1.1355
-- Accuracy: 0.6458
+- Loss: 1.1351
+- Accuracy: 0.6508
 
 ## Model description
 
@@ -38,22 +38,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 6
+- eval_batch_size: 6
 - 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: 1252
+- training_steps: 184
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.2879        | 0.25  | 314  | 1.1342          | 0.6458   |
-| 0.8626        | 1.25  | 628  | 1.1139          | 0.6458   |
-| 1.6465        | 2.25  | 942  | 1.0998          | 0.6458   |
-| 1.0899        | 3.25  | 1252 | 1.0984          | 0.6458   |
+| 1.1087        | 0.26  | 47   | 1.0796          | 0.6667   |
+| 1.1741        | 1.26  | 94   | 1.0369          | 0.6667   |
+| 1.1019        | 2.26  | 141  | 1.0368          | 0.6667   |
+| 1.2164        | 3.23  | 184  | 1.0369          | 0.6667   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52604a95f763fa8a1dbe6bf0e883401c9e590edd774e0f3823ebd4d4688542b4
+oid sha256:aa2843b322ddf8b103147ebfa37c72d6ef3df1acc1b3a9267e0435af0a05e0b7
 size 344946604