decider_config.json

{
 "temperature": 2.173,
 "temperature_by_type": {
  "choice": 2.098,
  "noul": 0.05,
  "score": 3.152
 },
 "neutralize_none": false,
 "version": "4b-v2.1",
 "base": "Mapika/decider-4b v1 + LoRA (merged); v1 is Qwen/Qwen3.5-4B-Base + one supervised pass over mixture v2",
 "layout": "plain",
 "max_options": 255,
 "max_state_tokens": 32768,
 "schema_first": false,
 "schema_first_trained": false,
 "isolated_levels": true,
 "release_date": "2026-09-24",
 "requires": "decider-ai>=1.4.0 for temperature_by_type; older versions serve every answer at temperature",
 "stage": "decider-4b v1 + LoRA rank 64 (alpha 128) on attention and MLP, LR 1e-4, 2 epochs (1,518 steps of 65,536 tokens) over v2's 29,325-row mix in the plain state-first layout (generated decision families with code-computed answers, Qwen3.6-27B-written document questions kept when two independent answers agreed, human-labelled public sets, replay of v1's mixture v2), with the replay rows trained toward v1's own answer distribution (KL to v1) instead of their labels, merged into the bf16 weights; no RL stage; temperature fitted by NLL on 61 in-task regression tasks (the 67 in-task tasks without banking77, clinc_oos, mmlu, arc, winogrande, hellaswag); temperature_by_type fitted with decider.calibrate.fit_by_type on the same regression rows plus our own validation rows (choice, noul and score answers)",
 "parent_temperature": 1.099,
 "parent_temperature_by_type": {
  "choice": 1.11,
  "noul": 1.56,
  "score": 1.287
 },
 "temperature_fit": {
  "rows": {
   "choice": 1307,
   "noul": 228,
   "score": 65
  },
  "nll": {
   "choice": {
    "T=1": 0.7488,
    "fitted": 0.5396
   },
   "noul": {
    "T=1": 0.4073,
    "fitted": 0.2428
   },
   "score": {
    "T=1": 1.3384,
    "fitted": 0.7943
   }
  },
  "sets": "jbmax_v2 val_jb/val_teacher/cal_human/guard, 400 each"
 },
 "noul_temperature_note": "Noul T 0.05 for JevBench's 0.2-0.8 band rule; calibrated Noul probabilities: noul T fitted on own rows = 2.795",
 "images": true
}