|
--- |
|
base_model: meta-llama/Llama-2-7b-chat-hf |
|
library_name: peft |
|
license: llama2 |
|
tags: |
|
- alignment-handbook |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: llama_2_unsafe_llama_2 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# llama_2_unsafe_llama_2 |
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1038 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- training_steps: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.6444 | 0.4 | 5 | 2.1252 | |
|
| 1.6642 | 0.8 | 10 | 1.4520 | |
|
| 1.29 | 1.2 | 15 | 1.2414 | |
|
| 1.151 | 1.6 | 20 | 1.1817 | |
|
| 1.0661 | 2.0 | 25 | 1.1291 | |
|
| 0.9829 | 2.4 | 30 | 1.1112 | |
|
| 0.9062 | 2.8 | 35 | 1.1073 | |
|
| 0.8685 | 3.2 | 40 | 1.1048 | |
|
| 0.8852 | 3.6 | 45 | 1.1038 | |
|
| 0.7973 | 4.0 | 50 | 1.1038 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.0 |
|
- Tokenizers 0.19.1 |
