{
 "system": "p4v2_gr_s1",
 "split": "test_template",
 "checkpoint": "experiments/runs/p4v2_gr_seed01_20261030001749/checkpoint",
 "checkpoint_sha256": "597a91e3beb1daea126d7c5b2ecd2bac327eb323b55cebe57a153e1f27b95f80",
 "config_sha256": "0b796604197779959d0bcdc2c38bdf81a3d839c7f9ecbd53dd757def310268bc",
 "code_commit": "unknown",
 "device": "mps",
 "precision": "fp32",
 "evaluated_at": "2026-10-30T04:06:23-0400",
 "data_sha256": "06620e1cf60b7250aac71f4fb5ee74e3705f4b9aab102e22b5c5bdbed76c4ae2",
 "exact_match": {
  "budget0": {
   "accuracy": 0.254,
   "n": 1000,
   "by_family": {
    "fsm": 0.430939226519337,
    "arith": 0.024875621890547265,
    "bind": 0.10679611650485436,
    "sched": 0.4854368932038835,
    "excl": 0.23786407766990292
   },
   "edits_per_token": 0.0
  },
  "forced_b2": {
   "accuracy": 0.259,
   "n": 1000,
   "by_family": {
    "fsm": 0.46408839779005523,
    "arith": 0.014925373134328358,
    "bind": 0.11165048543689321,
    "sched": 0.48058252427184467,
    "excl": 0.24271844660194175
   },
   "edits_per_token": 2.0
  }
 },
 "seconds": 18.0
}