{
 "system": "p4v2_dense_s2",
 "split": "test_template",
 "checkpoint": "experiments/runs/p4v2_dense_seed02_20261030004544/checkpoint",
 "checkpoint_sha256": "a7371f8c402f8a7fd98f784bb1c6750d70ccb46f53060656ba762df1166582b0",
 "config_sha256": "dbf7526c8c09e5cb0257a92cb81256910e8697c6a3507f64b37a3af184e37f46",
 "code_commit": "unknown",
 "device": "mps",
 "precision": "fp32",
 "evaluated_at": "2026-10-30T04:06:37-0400",
 "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": 0.44751381215469616,
    "arith": 0.03980099502487562,
    "bind": 0.07766990291262135,
    "sched": 0.5097087378640777,
    "excl": 0.23786407766990292
   },
   "edits_per_token": 2.0
  }
 },
 "seconds": 11.5
}