LASR-Callum/qwen3.6-27b-lora-t2-9284-chunk-only-702-answeronly-r64

LoRA SFT adapter — lora_qwen36_t2_9284_da_chunk_only_702_answeronly_dynbatch_2xh200

field	value
experiment	LoRA SFT adapter — lora_qwen36_t2_9284_da_chunk_only_702_answeronly_dynbatch_2xh200
date_generated	20260901
constitution	inherited from the training data (LASR-Callum/2026-09-01-answer-only-supervision-chunk-only-702); not declared in this train config
source_repo	https://github.com/Matthew-Bozoukov/teaching_claude_why_replication.git @ 7137baea6e1f33c182908af6bfba29634d87c9e8
models	base: Qwen/Qwen3.6-27B
generation_config	{"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 + training_meta.json {thinking, train_config, base_model, dataset{repo,file,revision}, git_sha, timestamp}
provenance	uv run train --config configs/train/lora_qwen36_t2_9284_da_chunk_only_702_answeronly_dynbatch_2xh200.yaml
dataset	hf.co/datasets/LASR-Callum/2026-09-01-answer-only-supervision-chunk-only-702@044e3b315a5384b7151f1f6b719934a7b9305c2b (mixture_think_cotonly.jsonl)