dougalldeepmind/2026-09-15-qwen36-0-nonmoral-advice-7

LoRA SFT adapter — recipe sft on mixture nonmoral-advice-7 (qwen36, seed 0)

field	value
experiment	LoRA SFT adapter — recipe sft on mixture nonmoral-advice-7 (qwen36, seed 0)
date_generated	20260915
constitution	preferences/craft_tensions_09_grounded/preferences.md (author target); constitutions/claude_distilled_09_principles/constitution.md (compatibility review only)
source_repo	https://github.com/Matthew-Bozoukov/teaching_claude_why_replication.git @ fd63ca8b83a5ea4127b015ed3034045afc0802ba
models	base: Qwen/Qwen3.6-27B@6a9e13bd6fc8f0983b9b99948120bc37f49c13e9
generation_config	{"recipe": "sft", "seed": 0, "thinking": true, "epochs": 1.0, "lr": 0.0001, "batch_size": 1, "grad_accum": 16, "max_seq_len": 8192, "lora": {"r": 64, "alpha": 128, "dropout": 0.05}, "dynamic_batching": {"token_budget": 8000, "loss_agg": "seq-mean-token-mean"}}
schema	PEFT LoRA adapter (safetensors) + tokenizer + train_config.yaml (the resolved config that ran, every launch argument and pin written back: uv run train --config train_config.yaml re-runs it) + training_meta.json {organism, thinking, recipe, mix_subject, train_config, base_model, base_model_revision, model_profile, dataset{repo,file,revision}, git_sha, timestamp}
provenance	scripts/train/train_lora.py --config configs/train/sft.yaml model=qwen36 seed=0 wandb=false constitution=preferences/craft_tensions_09_grounded/preferences.md (author target); constitutions/claude_distilled_09_principles/constitution.md (compatibility review only) data_repo=dougalldeepmind/2026-09-15-nonmoral-advice-7-mix data_revision=588783fb079d0bbe5c9eb568418fcff2aad4cecb base_model_revision=6a9e13bd6fc8f0983b9b99948120bc37f49c13e9 allow_default_supervise=true
dataset	hf.co/datasets/dougalldeepmind/2026-09-15-nonmoral-advice-7-mix@588783fb079d0bbe5c9eb568418fcff2aad4cecb (mixture.jsonl)