araft_trained_sft

<!-- 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 on the Araft dataset.

Model description

This model has been generated in the context of the Araft project. The Araft project consists in fine-tuning a Llama2-7B model to enable the use of the ReAct 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 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.

For further information, please see the 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