metadata
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: []
llama_2_unsafe_llama_2
This model is a fine-tuned version of 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