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: 0.4980
-- Accuracy: 0.8129
+- Loss: 0.6321
+- Accuracy: 0.7642
 
 ## Model description
 
@@ -42,24 +42,24 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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: 148
+- training_steps: 132
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.1431        | 0.2568 | 38   | 1.8763          | 0.4571   |
-| 0.8765        | 1.2568 | 76   | 0.8873          | 0.7571   |
-| 0.4523        | 2.2568 | 114  | 0.5120          | 0.8714   |
-| 0.3402        | 3.2297 | 148  | 0.3611          | 0.8571   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.0105        | 0.25  | 33   | 0.8727          | 0.75     |
+| 0.6753        | 1.25  | 66   | 0.5264          | 0.9062   |
+| 0.3198        | 2.25  | 99   | 0.4118          | 0.875    |
+| 0.2581        | 3.25  | 132  | 0.3522          | 0.9375   |
 
 
 ### Framework versions
 
-- Transformers 4.45.2
-- Pytorch 2.5.0+cu124
-- Datasets 3.0.1
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu121
+- Datasets 3.0.2
 - Tokenizers 0.20.1

runs/Oct27_18-20-03_9aab03d2776c/events.out.tfevents.1730054197.9aab03d2776c.6648.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43eb9a4313e9143879ccd4a09d537431095ef72b8546f288f3ab864e19d5ec4
+size 411