swapnil7777/gxpo-gxpo-llama-iso-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260413-1610-2a9f5222
07
swapnil7777/gxpo-gxpo-llama-iso-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260413-1610-2a9f5222
This repo was uploaded from a local training checkpoint.
- Source run:
gxpo_llama_iso_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260413_161029 - Checkpoint:
best_checkpoint - Local path:
/home/ismam/lookahead/lookahead_codes/checkpoints_hendrycks_math/gxpo_llama_iso_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260413_161029/best_checkpoint - Collection:
swapnil7777/gxpo-math-llama-69df23c9c96e90c788264f8f - Generated at: 2026-04-15 05:36:43 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_*, orcheckpoint-*
