added reward function normalization, hidden eval set

fixing the reward tirage

Finetuning done GRPO

enhancing the reward function and inference

Finalized bulletproof inference.py with local/endpoint toggle

enhancing the reward function and inference

Finalized bulletproof inference.py with local/endpoint toggle

Inferencing improved, but not ready for GRPO

Added new tasks

Update codebase and ignore DIME.pdf and image_gen binaries

chore: update codebase and fix gitignore

updating inference

restructring logs

structured logs stroing

storing the logs

added alibaba trace data

adding ruberics,updating tasks,validators

debugging

check failure fixes

api key preference evaluation

added flash_crowd task

fixing task score reset

outputting logs in inference

fixing inference providers

updating inference openai client

refactoring file structure