{
 "system": "p4v2_dense_s3",
 "split": "test_template",
 "checkpoint": "experiments/runs/p4v2_dense_seed03_20261030004544/checkpoint",
 "checkpoint_sha256": "ad0aff87189cbcd49c815e59f0adc835f1b576d111a7b0d60b7332142b4382da",
 "config_sha256": "c4e269d3e05ff208da6fe05ce1c72b11c3c69353f7d124cde990da4ff785b9ba",
 "code_commit": "unknown",
 "device": "mps",
 "precision": "fp32",
 "evaluated_at": "2026-10-30T04:06:42-0400",
 "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": 0.249,
   "n": 1000,
   "by_family": {
    "fsm": 0.4530386740331492,
    "arith": 0.024875621890547265,
    "bind": 0.07281553398058252,
    "sched": 0.49029126213592233,
    "excl": 0.22330097087378642
   },
   "edits_per_token": 2.0
  }
 },
 "seconds": 11.4
}