Giorgio Gilestro
84124de143
Clarity pass over the main text (36-item audit), Discussion rewrite and cut, acknowledgements, Souly et al. as ref 62, lettered SI panels, model section moved under Results; plus the untracked curriculum/society/compose/smol configs, runners, figures, stats and tests that the SI already cites. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm
25 lines
813 B
YAML
25 lines
813 B
YAML
# Stage B (prereg v4 §5 G2, v5 families): does forgetting occur, and is it general rather than one pair?
|
|
# One lineage, zero replay, all six selected families in sequence at the founder budget that passed C1.
|
|
# Pass: mean drop across families learned before the last >= 0.15, with no single family carrying
|
|
# more than 50% of the total drop (the v4 failure mode: one pair at +0.65, the rest ~0).
|
|
experiment: llm_curriculum_v5_g2
|
|
kind: llm_curriculum
|
|
base_model: Qwen/Qwen2.5-1.5B
|
|
seed: 1
|
|
families: [mnli, arc, hellaswag, squad, boolq, winogrande]
|
|
lineages: 1
|
|
generations: 6
|
|
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
|
|
batch_size: 24
|
|
train_batch_size: 2
|
|
train_max_len: 512
|
|
lora: {r: 16, alpha: 32}
|
|
output: {dir: results/llm_curriculum_v5_g2}
|