swapnil7777/gxpo-gxpo-qwen-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114637-ch-33191273

swapnil7777/gxpo-gxpo-qwen-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260411-114637-ch-33191273

This repo was uploaded from a local training checkpoint.

• —Source run: gxpo_qwen_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114637
• —Checkpoint: checkpoint-352
• —Local path: /home/ismam/lookahead/lookahead_codes/checkpoints_hendrycks_math/gxpo_qwen_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260411_114637/checkpoint-352
• —Collection: swapnil7777/gxpo-math-seed-42-69db67e297388ce31fb3d68a
• —Generated at: 2026-04-12 14:40:38 UTC

This checkpoint name is designed to stay readable:

• —run name preserves method, model, K, dataset, seed, and run timestamp
• —checkpoint suffix preserves whether this is best_checkpoint, bp_budget_*, or checkpoint-*