Views
No views yet
| field | value |
|---|---|
experiment | LoRA SFT adapter — lora_qwen36_less_random220_control_r64. THE CONTROL ARM: base Qwen3.6-27B trained on 220 rows drawn at random (seed 1) from the same 2,203-row pool. The two arms differ only in which 220 rows they saw; every hyperparameter, the batching protocol and the loss path are identical, so a difference between them is attributable to the selection. Trained one arm per GPU on a single pod so both share one base-model download. |
date_generated | 2026-08-19 |
constitution | constitutions/claude_distilled_12_principles_mid/constitution.md — inherited from the training data (LASR-Callum/2026-08-19-random-220-difficult-advice-control-train) |
source_repo | https://github.com/Matthew-Bozoukov/teaching_claude_why_replication.git @ 4078304ba62de85cca9e4c1d9347c4d88c95d52b |
models | base: Qwen/Qwen3.6-27B |
generation_config | {"seed": 0, "thinking": true, "epochs": 4, "lr": 0.0001, "batch_size": 1, "grad_accum": 16, "max_seq_len": 8192, "lora": {"r": 64, "alpha": 128, "dropout": 0.05}} |
schema | PEFT LoRA adapter (safetensors) + tokenizer + training_meta.json {thinking, train_config, base_model, dataset{repo,file,revision}, git_sha, timestamp} |
provenance | uv run train --config configs/train/2026-08-19_lora_qwen36_less_random_220_control_rank64.yaml push=false (on pod), then uv run python scratch/less/train_arms.py push |
dataset | hf.co/datasets/LASR-Callum/2026-08-19-random-220-difficult-advice-control-train@5ede5bc026bab7a83ff635d5bcf301a12b8822d3 (mixture.jsonl) |
paired_arm | LASR-Callum/2026-08-19-qwen36-lora-less-top10-220-rank-64 |