swapnil7777/sfpo-gxpo-qwen-3b-k-5-hendrycks-math-seed42-20260410-184131-checkpoint-228
This repo was uploaded from a local training checkpoint.
- Source run:
gxpo_qwen_3B_k_5_hendrycks_math_seed42_20260410_184131
- Checkpoint:
checkpoint-228
- Local path:
/home/ismam/lookahead/lookahead_codes/checkpoints_hendrycks_math/gxpo_qwen_3B_k_5_hendrycks_math_seed42_20260410_184131/checkpoint-228
- Collection:
swapnil7777/sfpo-math-k-3-isobp-69da41d2c75a8c6ca4453cf2
- Generated at: 2026-04-11 12:47:11 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-*
