SCD/stage6alt_eval.json

{
  "acc_norm_sum_gap": -0.025000000000000133,
  "bpt_gap": 0.18680916770453448,
  "corpus": {
    "dataset": "wikitext",
    "name": "wikitext",
    "num_sequences": 64,
    "sequence_length": 2048,
    "split": "test",
    "subset": "wikitext-2-raw-v1"
  },
  "lm_eval": {
    "arc_easy_limit": 100,
    "hellaswag_limit": 200
  },
  "mode": "thermometer",
  "stage": "6alt",
  "student_acc_norm_sum": 1.4649999999999999,
  "student_arc_easy_acc_norm": 0.74,
  "student_bpt": 2.911000749244174,
  "student_hellaswag_acc_norm": 0.725,
  "teacher_acc_norm_sum": 1.49,
  "teacher_arc_easy_acc_norm": 0.75,
  "teacher_bpt": 2.7241915815396394,
  "teacher_cache": {
    "hit": false,
    "key": "c213c7c5d390ac8b236729041eb77281f074e112f36690b6120fd47042106f28",
    "path": "/cache/ablations/_shared/thermometer_teacher_cache.json"
  },
  "teacher_hellaswag_acc_norm": 0.74,
  "top1_agreement": 0.8253312706947327
}