|
|
--- |
|
|
{} |
|
|
--- |
|
|
# Model with No Refusal Messages From CoCoNoT |
|
|
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on UltraChat SFT. |
|
|
|
|
|
## Suggusted Method For Generations |
|
|
|
|
|
For this model, `model.generate` or `pipeline` are sufficient. |
|
|
|
|
|
<!-- ### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 2e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 8 |
|
|
- total_train_batch_size: 128 |
|
|
- total_eval_batch_size: 64 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 1.1131 | 1.0 | 1871 | 1.1339 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.45.2 |
|
|
- Pytorch 2.3.0.dev20240111+rocm5.6 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.20.1 --> |
|
|
|
