Updated the training notebook to improve compatibility with Google Colab by defining paths based on the environment. Added absolute paths for data and results, ensuring seamless execution both in Colab and local environments. Enhanced print statements to include the CORP_GYM path for better clarity.
feat: add T4-optimized SFT and RLVR training scripts, evaluation utilities, and updated documentation
Updated the Dockerfile to include additional directories for data and scripts, ensuring a more organized structure. Added new training notebooks for DeepSeek-R1 and Nemotron-3 models, providing end-to-end reproducibility for SFT and RLVR training processes. Revised the README.md to include links to the new notebooks and improved clarity on model training and evaluation steps. Enhanced the .gitignore file to exclude unnecessary files and directories, streamlining the project structure.
feat: update README and runbook for SFT and GRPO training enhancements
Revised the README.md and runbook to reflect changes in the SFT and GRPO training processes, including default input/output paths and parameters. Updated example commands for data preparation and training scripts to incorporate new defaults for merging datasets. Added details on the new `e1_m1_h1_examples.jsonl` file and clarified the training steps for improved user guidance. Introduced new JSONL files for verification results and summaries to enhance tracking of model performance.
feat: update training scripts and add judge-rerunnable notebook for CORP-ENV
Enhanced training scripts for SFT and GRPO to utilize Unsloth and Hugging Face TRL, including new parameters for max steps. Introduced a judge-rerunnable notebook for streamlined training and evaluation processes. Updated README.md and runbook to reflect these changes and provide clearer instructions for users.
