Skip to content

Added how to use commit0 for sampling during STAR training#105

Draft
wenting-zhao wants to merge 18 commits intomainfrom
star
Draft

Added how to use commit0 for sampling during STAR training#105
wenting-zhao wants to merge 18 commits intomainfrom
star

Conversation

@wenting-zhao
Copy link
Collaborator

@wenting-zhao wenting-zhao commented Dec 8, 2024

python examples/star/star.py --model_name_or_path meta-llama/Llama-3.1-8B-Instruct --dataset_name commit0/mbpp -n 10 --output_dir outputs --low_cpu_mem_usage --with_tracking --report_to wandb --iteration 5 --per_device_train_batch_size 1 --gradient_accumulation_steps 8

TODOs:

  • Extend STAR to multiple iterations (Done)
  • Align the code with the formalism of STaR

@wenting-zhao wenting-zhao marked this pull request as draft December 8, 2024 18:34
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant