metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base-finetuned-kinetics
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: VideoMAE_4_CLASS_QUALITY_CHECK
results: []
VideoMAE_4_CLASS_QUALITY_CHECK
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0015
- Accuracy: 1.0
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use 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: 350
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.0723 | 0.02 | 7 | 1.3154 | 0.4286 |
| 4.5479 | 1.0214 | 15 | 1.0319 | 0.8571 |
| 3.6957 | 2.02 | 22 | 0.6454 | 0.8571 |
| 1.7212 | 3.0214 | 30 | 0.2796 | 1.0 |
| 0.6321 | 4.02 | 37 | 0.0587 | 1.0 |
| 0.0861 | 5.0214 | 45 | 0.0120 | 1.0 |
| 0.0166 | 6.02 | 52 | 0.0029 | 1.0 |
| 0.0047 | 7.0214 | 60 | 0.0018 | 1.0 |
| 0.0029 | 8.02 | 67 | 0.0015 | 1.0 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.1