CoolFace
Modelpublic

swapnil7777/gxpo-gxpo-llama-iso-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260413-1610-707e7dca

sourceHugging Faceupdated 6mo agoView on Hugging Face
0likes4downloads
Model Card

swapnil7777/gxpo-gxpo-llama-iso-3b-k-5-shutoff-trajectory-aware-hendrycks-math-seed42-20260413-1610-707e7dca

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: checkpoint-378
  • —Local path: /home/ismam/lookahead/lookahead_codes/checkpoints_hendrycks_math/gxpo_llama_iso_3B_k_5_shutoff_trajectory_aware_hendrycks_math_seed42_20260413_161029/checkpoint-378
  • —Collection: swapnil7777/gxpo-math-llama-69df23c9c96e90c788264f8f
  • —Generated at: 2026-04-15 05:39:50 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-*