metadata
library_name: transformers
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-judo
results: []
videomae-small-finetuned-kinetics-finetuned-judo
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: 0.2644
- Accuracy: 0.8889
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.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: 130
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6846 | 0.1077 | 14 | 0.6309 | 0.6667 |
| 0.5857 | 1.1077 | 28 | 0.5324 | 0.7037 |
| 0.3921 | 2.1077 | 42 | 0.5325 | 0.6296 |
| 0.3011 | 3.1077 | 56 | 0.4113 | 0.8889 |
| 0.2184 | 4.1077 | 70 | 0.3408 | 0.8889 |
| 0.1523 | 5.1077 | 84 | 0.3739 | 0.8519 |
| 0.1197 | 6.1077 | 98 | 0.3697 | 0.7778 |
| 0.0763 | 7.1077 | 112 | 0.2562 | 0.8889 |
| 0.0724 | 8.1077 | 126 | 0.2623 | 0.8889 |
| 0.0685 | 9.0308 | 130 | 0.2644 | 0.8889 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0