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-gesturePhasev2
results: []
videomae-base-finetuned-gesturePhasev2
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:
- Loss: 0.8172
- Accuracy: 0.7633
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- training_steps: 376
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1665 | 0.125 | 47 | 1.0642 | 0.775 |
| 0.7316 | 1.1263 | 95 | 0.7826 | 0.7875 |
| 0.7259 | 2.125 | 142 | 0.8042 | 0.7875 |
| 0.6643 | 3.1263 | 190 | 0.8023 | 0.7875 |
| 0.761 | 4.125 | 237 | 0.8077 | 0.7875 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1