# Calibration for the real-dataset curriculum (prereg v4 §5 gates, re-run on the new families).
# Stage A (this config): base accuracy on every candidate, and one specialist per candidate trained
# from the base on its train split — the C1 band is base <= 0.40 and specialist >= 0.60.
# Stage B (curriculum_v5_g2.yaml, after selection): one lineage, zero replay, all chosen families in
# sequence — the forgetting probe; mean drop across families learned before the last must be >= 0.15,
# and it must not be carried by a single family (the v4 failure: one pair at +0.65, the rest ~0).
experiment: llm_curriculum_v5_calib
kind: llm_curriculum
base_model: Qwen/Qwen2.5-1.5B
seed: 1
families: [gsm8k, mbpp, boolq, mnli, sst2, csqa, arc, winogrande, squad, nq_open, hellaswag]
lineages: 11              # one lineage per candidate = each trains only its own family at gen 0
generations: 1            # gen 0 only: founders; the recorded acc_* rows ARE the specialist table
arms: [isolated]
baselines: []
n_new: 300
n_replay: 0
n_test: 60
n_val: 20
epochs: 3
lr: 1.0e-4
max_new_tokens: 48        # spans / short text need more room than a label
batch_size: 24
train_batch_size: 2
train_max_len: 512
lora: {r: 16, alpha: 32}
output: {dir: results/llm_curriculum_v5_calib}