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: RALL_RGBCROP_Aug16F-cosine_with_restarts
results: []
RALL_RGBCROP_Aug16F-cosine_with_restarts
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: 0.4225
- Accuracy: 0.8494
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
- 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: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 3462
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4395 | 0.0835 | 289 | 0.5305 | 0.7239 |
| 0.2409 | 1.0835 | 578 | 0.5012 | 0.8016 |
| 0.0269 | 2.0835 | 867 | 0.6809 | 0.8160 |
| 0.0086 | 3.0835 | 1156 | 0.8971 | 0.7894 |
| 0.0008 | 4.0835 | 1445 | 0.9614 | 0.8160 |
| 0.0004 | 5.0835 | 1734 | 1.0207 | 0.8160 |
| 0.0004 | 6.0835 | 2023 | 1.0934 | 0.8139 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1