| { | |
| "args": { | |
| "base": "Qwen/Qwen3.5-4B-Base", | |
| "n_per_source": 1000, | |
| "epochs": 5, | |
| "lr": 1e-05, | |
| "head_lr": 0.0, | |
| "weight_decay": 0.01, | |
| "lora": 16, | |
| "accum": 2, | |
| "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": "/root/evals/sev/response-policy-html-contrast-v1", | |
| "train_sources": "", | |
| "device": "cuda", | |
| "batch": 4, | |
| "dtype": "bf16", | |
| "weights_dtype": "fp32", | |
| "checkpointing": 1, | |
| "option_isolation": 0, | |
| "special_embeddings": 0, | |
| "head_dim": 256, | |
| "lora_targets": "all", | |
| "base_revision": "1001bb4d826a52d1f399e183466143f4da7b741b", | |
| "p_none": 0.0, | |
| "p_none_distract": 0.0, | |
| "p_distract": 0.0, | |
| "p_none_pair": 0.0, | |
| "synthetic_repeat": 1, | |
| "public_frac": 1.0, | |
| "anchor": "", | |
| "anchor_w": 0.0, | |
| "anchor_sources": "", | |
| "out": "/runs/sev-html-contrast-4b-v1/00-trial-0/checkpoint", | |
| "data": "", | |
| "replay": 0, | |
| "init_from": "macmacmacmac/Sev-4B@v0.3.0-response-policy-research", | |
| "seed": 4 | |
| }, | |
| "suite_sha256": "40d3a8b3bd416a3754ecc30e9791a9ebb14a26c8f2a4422057f769a2dbce4dee", | |
| "base_revision": "1001bb4d826a52d1f399e183466143f4da7b741b", | |
| "init_source": { | |
| "init_from": "macmacmacmac/Sev-4B@v0.3.0-response-policy-research", | |
| "resolved": "/__modal/volumes/vo-RociVuGycNGtzvUcdOqecz/hub/models--macmacmacmac--Sev-4B/snapshots/da0a131c2636b06c16bbca7d8ae84f0dc1e90b7e", | |
| "adapter_sha256": "fa1916b34fe1eeb10d15c36927c225df43115407d7c97b4f879bba3102c3ed21", | |
| "head_sha256": "12112262e1822fa4ab2981650bd10ceac46929bb29fbbdd843a39ec9de7dbe82", | |
| "adapter_tensors": 496 | |
| }, | |
| "ordinal_objective": "ranked_probability_score", | |
| "holdout": [] | |
| } | |