Modelpublic

swapnil7777/grpo-grpo-llama-3b-iso-hendrycks-math-seed42-20260414-174423-checkpoint-4

sourceHugging Faceupdated 6mo agoView on Hugging Face

0likes5downloads

Model Card

This repo was uploaded from a local training checkpoint.

—Source run: grpo_llama_3B_iso_hendrycks_math_seed42_20260414_174423
—Checkpoint: checkpoint-4
—Local path: /home/ismam/lookahead/lookahead_codes/checkpoints_hendrycks_math/grpo_llama_3B_iso_hendrycks_math_seed42_20260414_174423/checkpoint-4
—Collection: swapnil7777/grpo-math-llama-plot-gen-69dfb3d18bfa89259a41a96a
—Generated at: 2026-04-15 15:51:06 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-*