|
--- |
|
base_model: meta-llama/Meta-Llama-3-8B-Instruct |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Meta-Llama-3-8B_derta |
|
results: [] |
|
license: apache-2.0 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# Meta-Llama-3-8B-Instruct_derta_100step |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the [Evol-Instruct](https://huggingface.co/datasets/WizardLMTeam/WizardLM_evol_instruct_70k) and [BeaverTails](https://huggingface.co/datasets/PKU-Alignment/BeaverTails) dataset. |
|
The model is continued to train 100 steps with DeRTa on LLaMA3-8B-Instruct. |
|
|
|
## Model description |
|
|
|
Please refer to the paper [Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training](https://arxiv.org/abs/2407.09121) and GitHub [DeRTa](https://github.com/RobustNLP/DeRTa). |
|
|
|
Input format: |
|
``` |
|
[INST] Your Instruction [\INST] |
|
``` |
|
## Intended uses & limitations |
|
|
|
The model is trained with DeRTa, showing a high safety performance. |
|
|
|
## 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: 16 |
|
- weight_decay: 2e-5 |
|
- eval_batch_size: 1 |
|
- seed: 1 |
|
- distributed_type: multi-GPU |
|
- num_devices: 8 |
|
- total_train_batch_size: 128 |
|
- total_eval_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 2.0 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.0 |
|
- Pytorch 2.2.0+cu118 |
|
- Datasets 2.10.0 |
|
- Tokenizers 0.19.1 |
