Model save

README.md

@@ -18,8 +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: 1.9573
-- Accuracy: 0.6321
+- Loss: 2.0503
+- Accuracy: 0.6439
 
 ## Model description
 
@@ -38,23 +38,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 5e-06
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
-- training_steps: 520
+- lr_scheduler_warmup_ratio: 0.2
+- training_steps: 390
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.1315        | 0.2519 | 131  | 2.2071          | 0.3857   |
-| 1.1581        | 1.2519 | 262  | 1.1586          | 0.6547   |
-| 0.6854        | 2.2519 | 393  | 0.8164          | 0.7623   |
-| 0.3349        | 3.2442 | 520  | 0.6746          | 0.8206   |
+| 0.1658        | 0.3359 | 131  | 0.5805          | 0.8251   |
+| 0.1039        | 1.3359 | 262  | 0.5685          | 0.8251   |
+| 0.0832        | 2.3282 | 390  | 0.5565          | 0.8475   |
 
 
 ### Framework versions

runs/Jan08_20-28-15_5a3016f64bbf/events.out.tfevents.1736370286.5a3016f64bbf.332.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8da9ed9c73210f936b2678c82a6f6f55bea6a60ff4c717f06a4dc1419425a65
+size 411