swapnil7777/grpo-gxpo-qwen-1-5b-0-5-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260421-032-6c2559d4
This repo was uploaded from a local training checkpoint.
- Source run:
gxpo_qwen-1.5B_0.5_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032446
- Checkpoint:
checkpoint-396
- Local path:
/home/ismam/lookahead/lookahead_codes/checkpoints_hendrycks_math/gxpo_qwen-1.5B_0.5_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260421_032446/checkpoint-396
- Collection:
swapnil7777/grpo-69e9a184f1fa7f7aecb24d86
- Generated at: 2026-04-23 04:54:26 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-*
