revert(training): temporarily revert dataset bounds back to 10 for complete trial confirmation before scaling

feat(training): scale dataset to 500 prompts and add hub export cell for full hackathon training run

fix(trl): inject warnings_issued dict into unsloth model to prevent TRL GRPO init crash on PeftModels

fix(trl): force hardware-specific fp16/bf16 flags to prevent TRL from crashing on T4 GPU

fix(trl): mock weave.trace to complete package bypass

fix(trl): add weave to the magic mock bypass list for cell 5

fix(trl): inject magicmock bypass into cell 5 to squash TRL 0.24.0 import crash

feat: complete rewrite of grpo training script using Unsloth optimized pathway

chore: test trial run for colab script with 10 dataset size and fixed dependencies

fix: downgrade TRL to 0.15.0 and nuke ghost vLLM install to prevent import crashes

fix: correct trl version pin to 0.17.0

fix: vLLM/TRL version conflict in Colab Cell 1

fix: training reward bounds to (0.01, 0.99) — prevents loss=0 from zero variance

fix: increase num_generations=6, temperature=0.9, lr=2e-5 to fix zero-loss GRPO

fix: remove fp16=True, use paged_adamw_8bit for QLoRA BFloat16 compatibility

fix: add 4-bit quantization + LoRA to fit GRPO training in T4 15GB VRAM

refactor: rewrite training script - remove rollout_func, use inline reward evaluation

fix: remove deprecated GRPOConfig params for latest TRL compatibility

fix: set live HF Space URL in training script and demo app

feat: CodeSensei - GRPO-trained LLM code debugger on OpenEnv