feat: add T4-optimized SFT and RLVR training scripts, evaluation utilities, and updated documentation

feat: add training pipeline with SFT and RLVR support for Qwen 2.5-3B-Instruct

feat: enhance training environment and documentation for CORP-ENV models

chore: increase max prompt and sequence lengths in training scripts

feat: add new training jobs and scripts for DeepSeek and Nemotron models

refactor: update training scripts and environment setup for Qwen3 model

refactor: update training scripts and documentation for SFT and RLVR processes

feat: add environment setup and requirements for Lightning AI H100 training

feat: update README and runbook for SFT and GRPO training enhancements

feat: update evaluation results and training scripts for Qwen2.5-7B-Instruct

comm

feat: update training scripts and add judge-rerunnable notebook for CORP-ENV

feat: add evaluation and plotting scripts for CORP-ENV