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_per_class_reflect
results: []
llama_2_unsafe_per_class_reflect
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: 0.8179
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
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 0.1
- training_steps: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3764 | 0.7692 | 5 | 1.8176 |
| 1.6306 | 1.5385 | 10 | 1.2812 |
| 1.2054 | 2.3077 | 15 | 0.9901 |
| 0.9679 | 3.0769 | 20 | 0.8995 |
| 0.8649 | 3.8462 | 25 | 0.8679 |
| 0.8062 | 4.6154 | 30 | 0.8346 |
| 0.8035 | 5.3846 | 35 | 0.8252 |
| 0.7083 | 6.1538 | 40 | 0.8200 |
| 0.703 | 6.9231 | 45 | 0.8188 |
| 0.6968 | 7.6923 | 50 | 0.8179 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1