| { |
| "args": { |
| "base": "empero-ai/Qwen3.8-2B-Distill", |
| "n_per_source": 1000, |
| "epochs": 1, |
| "lr": 3e-05, |
| "head_lr": 0.0, |
| "weight_decay": 0.01, |
| "lora": 16, |
| "accum": 4, |
| "holdout": "", |
| "perm_kl": 0.0, |
| "perm_frac": 0.3, |
| "ord_w": 0.0, |
| "label_smoothing": 0.0, |
| "brier_w": 0.0, |
| "focal_gamma": 0.0, |
| "suite": "evals/v7/decision-v7", |
| "train_sources": "", |
| "device": "cuda", |
| "batch": 8, |
| "dtype": "bf16", |
| "weights_dtype": "fp32", |
| "checkpointing": 1, |
| "option_isolation": 0, |
| "special_embeddings": 0, |
| "head_dim": 256, |
| "lora_targets": "all", |
| "base_revision": "e37a2dc4acc68ad75a91e07e63168cb04cc06345", |
| "p_none": 0.1, |
| "p_none_distract": 0.12, |
| "p_distract": 0.15, |
| "p_none_pair": 0.25, |
| "synthetic_repeat": 1, |
| "public_frac": 1.0, |
| "anchor": "", |
| "anchor_w": 0.0, |
| "anchor_sources": "", |
| "out": "runs/d2b-mix4", |
| "data": "../data/train_mix_v4delta/train.jsonl", |
| "max_state": 1024, |
| "replay": 3000, |
| "init_from": "runs/d2b-mix2", |
| "seed": 0, |
| "save_every": 400 |
| }, |
| "suite_sha256": "a8f50e481b7d90b97da049e0ff6a01cee2f1ed204aed61a8265af0edbb5514d2", |
| "base_revision": "e37a2dc4acc68ad75a91e07e63168cb04cc06345", |
| "init_source": { |
| "init_from": "runs/d2b-mix2", |
| "resolved": "runs/d2b-mix2", |
| "adapter_sha256": "1eedf217220328f8c57dad184988cc5792dc101dbc794bf674ee861913806fc6", |
| "head_sha256": "c617dacf28ba0819cc141328d502ea49d16a7aefde3edc9a5091c42ce0211938", |
| "adapter_tensors": 372 |
| }, |
| "ordinal_objective": "ranked_probability_score", |
| "holdout": [] |
| } |
|
|
