---
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Llama-2-7b-chat-hf
model-index:
- name: '20240328_1004'
  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. -->

# araft_trained_sft

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 [Araft dataset](https://huggingface.co/datasets/FDeRubeis/araft).

## Model description

This model has been generated in the context of the [Araft](https://github.com/FDeRubeis/Araft) project. The Araft project consists in fine-tuning a Llama2-7B model to enable the use of the [ReAct](https://arxiv.org/abs/2210.03629) pattern for Wikipedia-augmented question-answering. This model is the product of the first training step: SFT training.

In the SFT training step, the trajectories from the [Araft dataset](https://huggingface.co/datasets/FDeRubeis/araft) have been used to fine-tune the model, using each step as a desired output for the previous part of the trajectory. The model achieves a 16% performace (f1 score) on the [HotpotQA dataset](https://hotpotqa.github.io/).

For further information, please see the [Araft](https://github.com/FDeRubeis/Araft) github repo.

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP


### Framework versions

- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2