Views
No views yet
| field | value |
|---|---|
experiment | LoRA SFT adapter — lora_qwen36_t2_9284_synthdoc716_lessswap_dynbatch_2xh200 |
date_generated | 20260817 |
constitution | inherited from the training data (LASR-Callum/2026-08-17-table2-9284-synthdoc-716-less-swap-bests-for-traits); not declared in this train config |
source_repo | this repository @ nogit |
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/2026-08-16_lora_qwen36_table2_9284_synthdoc_716_less_swap_dynbatch.yaml |
dataset | hf.co/datasets/LASR-Callum/2026-08-17-table2-9284-synthdoc-716-less-swap-bests-for-traits@be616c483e3f5129698203340d969db7ca7a76e0 (mixture_think.jsonl) |