metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-good-gesturePhaseV12
results: []
videomae-base-finetuned-good-gesturePhaseV12
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.9544
- Loss: 0.2487
- Accuracy Hold: 1.0
- Accuracy Stroke: 0.4286
- Accuracy Recovery: 0.8947
- Accuracy Preparation: 0.9811
- Accuracy Unknown: 0.9286
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- 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: 630
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss | Accuracy Hold | Accuracy Stroke | Accuracy Recovery | Accuracy Preparation | Accuracy Unknown |
|---|---|---|---|---|---|---|---|---|---|
| 1.1508 | 0.2016 | 127 | 0.6900 | 1.0099 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0 |
| 0.7497 | 1.2016 | 254 | 0.7249 | 0.7448 | 0.3077 | 0.0 | 0.0 | 1.0 | 0.0 |
| 0.3044 | 2.2016 | 381 | 0.8603 | 0.4170 | 0.7692 | 0.0 | 0.5882 | 0.9620 | 0.6818 |
| 0.1617 | 3.2016 | 508 | 0.9127 | 0.3627 | 0.7308 | 0.1667 | 0.8824 | 0.9810 | 0.8636 |
| 0.0765 | 4.1937 | 630 | 0.9432 | 0.2175 | 0.8462 | 0.6667 | 0.8824 | 0.9747 | 0.9545 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1