Fine Tuning

Llama fine tuning

This examples fine-tunes Llama 2 on a Q&A list.

Problem

• Name: Llama Finetuning
• Problem Type: text_causal_classification_modeling
• Model Source: HF
• Model Name: meta-llama/Llama-2-7b-hf
• Secrets Blueprint: HF Meta
  • A token with access to meta-llama/Llama-2-7b-hf

Dataset

• Train dataframe: finetune_train.csv
• Validation dataframe: finetune_validation.csv
• Answer column: output
• Prompt column: instruction
• Validation size: 0.01

Output storage

• Model Storage: HF
• Model Name: llama-finetuned
• Store only the LoRA Adapters: true
• Secrets Blueprint: Write Token
  • A token with write access to HF

Run

• Run Title: Run 01
• Resources
  • Accelerator: A10G
  • GPU Count: 1
  • Memory: 64
• Tracking
  • Experiment name: Llama Finetuning
  • API key: API key generated from User > API Keys dropdown
  • Tracking mode: after_epoch