swapnil7777/GRPO_hendrycks_math_qwen_1.5B_20260316_222238
08
Add W&B metadata for GRPO_hendrycks_math_qwen_1.5B_20260316_222238
Sanitize adapter config for GRPO_hendrycks_math_qwen_1.5B_20260316_222238
Sanitize model card for GRPO_hendrycks_math_qwen_1.5B_20260316_222238
Upload best checkpoint for GRPO_hendrycks_math_qwen_1.5B_20260316_222238 (step 396)
initial commit
