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: 1.2503
-- Accuracy: 0.4839
+- Loss: 1.1078
+- Accuracy: 0.5806
 
 ## Model description
 
@@ -38,22 +38,26 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 4
+- eval_batch_size: 4
 - 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: 90
+- training_steps: 88
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.3818        | 0.26  | 23   | 1.2466          | 0.4      |
-| 1.3807        | 1.26  | 46   | 1.1977          | 0.44     |
-| 1.3333        | 2.26  | 69   | 1.2033          | 0.52     |
-| 1.1941        | 3.23  | 90   | 1.1854          | 0.52     |
+| 1.5179        | 0.14  | 12   | 1.2395          | 0.48     |
+| 1.1924        | 1.14  | 24   | 1.1857          | 0.52     |
+| 1.3708        | 2.14  | 36   | 1.1845          | 0.48     |
+| 1.1118        | 3.14  | 48   | 1.0907          | 0.44     |
+| 1.1829        | 4.14  | 60   | 1.1010          | 0.6      |
+| 1.2004        | 5.14  | 72   | 1.0521          | 0.56     |
+| 1.0309        | 6.14  | 84   | 1.0305          | 0.56     |
+| 1.0309        | 7.05  | 88   | 1.0280          | 0.6      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:053c821382727ebc173c1ea5672dd632c2a72e22d49fdacb9452306c93f631a1
+oid sha256:cb505f13a3f8f46fd1ecc91d890966c5fb4e052e71f7b64687c6bbe74c6cef83
 size 344946604