metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-small-finetuned-kinetics
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-small-finetuned-kinetics-finetuned-ucf101-subset
results: []
videomae-small-finetuned-kinetics-finetuned-ucf101-subset
This model is a fine-tuned version of MCG-NJU/videomae-small-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1171
- Accuracy: 0.9677
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: 1
- eval_batch_size: 1
- 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: 1200
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7637 | 0.25 | 300 | 0.6597 | 0.9286 |
| 0.512 | 1.25 | 600 | 0.2801 | 0.9143 |
| 0.0404 | 2.25 | 900 | 0.4797 | 0.8571 |
| 0.4026 | 3.25 | 1200 | 0.1202 | 0.9714 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2