risk-kd
Collection
data: https://www.kaggle.com/datasets/warkingleo2000/RISK-KD/
kaggle datasets download warkingleo2000/risk-kd • 8 items • Updated
student_sft_init
This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set:
- Loss: 1.1767
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 4
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1293 | 1.0 | 571 | 1.1598 |
| 0.9276 | 2.0 | 1142 | 1.1511 |
| 0.8279 | 3.0 | 1713 | 1.1767 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.10.0+cu126
- Datasets 4.8.4
- Tokenizers 0.21.4
- Downloads last month
- 166
Model tree for phanviethoang1512/llama3.2-1b-deita-dpo-student_sft_init
Base model
meta-llama/Llama-3.2-1B