README.md

---
license: apache-2.0
library_name: peft
tags:
- alignment-handbook
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrachat_200k
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: zephyr-7b-sft-qlora
  results: []
---

# zephyr-7b-sft-qlora

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4ultrachat_200k dataset.
It is the first step (Step 1 SFT, see below) of building Zephyr, i.e. before DPO.
It achieves the following results on the evaluation set:
- Loss: 0.9523

## Model description

QLoRA SFT via
```
# Step 1 - SFT
ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/multi_gpu.yaml --num_processes=1 scripts/run_sft.py recipes/zephyr-7b-beta/sft/config_qlora.yaml --load_in_4bit=true
```
see https://github.com/huggingface/alignment-handbook/blob/main/recipes/zephyr-7b-beta/README.md

## Intended uses & limitations

```
chat_template: "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}"
```

see https://github.com/huggingface/alignment-handbook/blob/main/recipes/zephyr-7b-beta/sft/config_qlora.yaml

## Training and evaluation data

```
dataset_mixer:
  HuggingFaceH4/ultrachat_200k: 1.0
dataset_splits:
- train_sft
- test_sft
```

see https://github.com/huggingface/alignment-handbook/blob/main/recipes/zephyr-7b-beta/sft/config_qlora.yaml

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- 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
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.913         | 1.0   | 17428 | 0.9523          |


### Framework versions

- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.0
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dball__zephyr-7b-sft-qlora)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |59.80|
|AI2 Reasoning Challenge (25-Shot)|59.73|
|HellaSwag (10-Shot)              |82.49|
|MMLU (5-Shot)                    |61.90|
|TruthfulQA (0-shot)              |42.32|
|Winogrande (5-shot)              |78.22|
|GSM8k (5-shot)                   |34.12|