Fix: Fixed again again

Fix: Fixed again

Fix: Fixing Again

Fix: Fixing

Fix: Trying to fix dependency issues

Fix: Fixed file

fix: serialize bug_metadata as JSON to fix pyarrow mixed-type error

fix: upgrade bitsandbytes>=0.49.0 (triton.ops), switch to Qwen2.5-Coder-3B

fix: torch at build time, remove mergekit (conflicts accelerate/peft/trl)

fix: empty requirements.txt, install training deps at runtime

fix: remove wandb - click conflict with gradio causes resolution-too-deep

fix: resolve pip dependency conflicts for HF Spaces build

Fix: loosen strict dependencies to prevent pip backtracking

fix: remove hardcoded torch from requirements for HF space

chore: normalize dataset inputs and fix mergekit dependency for TRL 0.14.0

Add HANDOVER.md: full project state, deps, training instructions, known fixes

Auto-detect GPU: bfloat16+batch2+gen8 on A100, float16+batch1+gen4 on T4 — same script works on both

Reduce max_completion_length to 160 for T4 speed: target 1000 steps in <8hrs

Fix: bump bitsandbytes to 0.45.3 for CUDA 12.x support on Kaggle T4

Optimize for Kaggle P100: float16, batch=1, grad_accum=8, num_gen=4, max_completion=256, lora_r=8

Fix GRPOConfig: rename max_new_tokens to max_completion_length for trl==0.14.0

Update: Added testing

Align gradio version with Hugging Face Space builder2

Add dockerignore to reduce Space build context

Stabilize Space runtime: pin ML deps and disable runtime package drift

Pin torch to cu121 build + use model.device instead of hardcoded cuda string

Replace unsloth with bitsandbytes+peft: fixes CUDA driver incompatibility on HF A100

Fix Gradio 4.x every= deprecation: use gr.Timer for auto-refresh

Reduce training to 500 steps with tightened curriculum for A10G budget

Add Gradio training monitor and fix subprocess python path

Fix eval device selection with CUDA-safe fallback

Add interactive Gradio demo at /demo in env Space

Optimize for A100 80GB: 8 generations, batch 4, lr 2e-5, dense logging

Restore full 1000-step training with original curriculum

Reduce training to 500 steps with tightened curriculum for A10G budget

"Update: Minor fixes"

Add Gradio training monitor and fix subprocess python path

Curated the bugs dataset

Resolved README Merge conflicts

Update: Started making changes for the hackathon

Updated README.md

Update: Refined and validated values

Update: Even more Final README.md update

Update: Final README.md update

Update: Final README.md update

Fix: Changed environment variables and added validator

Fix: Final submission cleanup, unified identity and integrity markers

Update: Made refinements to the project

Fix: Revise README for improved clarity and detail

Update: README