metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-less_accuracy-action_detection
results: []
videomae-base-less_accuracy-action_detection
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: 1.8868
- Accuracy: 0.5391
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: 2
- eval_batch_size: 2
- 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: 1216
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2463 | 0.25 | 305 | 1.1609 | 0.6420 |
| 1.2048 | 1.25 | 610 | 2.4836 | 0.3210 |
| 0.9462 | 2.25 | 915 | 2.2188 | 0.5021 |
| 1.2819 | 3.25 | 1216 | 1.8868 | 0.5391 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1