run_name: loracle_cispo_v9
checkpoint_dir: checkpoints/loracle_k16_uber_v3_sft
base_model: /workspace/models/Qwen3-14B
d_model: 5120
token_dir_kind: svd_fixed_k16_mag7_rankfirst
n_direction_tokens: 4480
prefix_mode: rank_tagged
training_lora_dir: data/unified_mag7_k16/tokens
prompts_path: data/uber_v3/prompts.parquet
loraqa_path: data/uber_v3/qa.parquet
holdout_ids_path: data/v2_splits/train_holdout.json
interpreter_rank: 256
lora_alpha: 32
batch_size: 2
lr: 3.0e-05
warmup_steps: 2000
weight_decay: 0.01
max_grad_norm: 1.0
epochs: 1
max_length: 5500
bf16: true
tasks:
- loraqa
task_weights: natural
eval_every_epochs: 0.33
cross_lora_eval_every_epochs: 0.33
early_stop_patience: 0
early_stop_min_delta: 0.0
judge_evals:
- enabled: true
  eval_set: configs/eval_sets/auditbench.yaml
  eval_every_epochs: 0.33
- enabled: true
  eval_set: configs/eval_sets/heldout_ia_v2.yaml
  eval_every_epochs: 0.33
- enabled: true
  eval_set: configs/eval_sets/heldout_gradients_k16_v2.yaml
  eval_every_epochs: 0.33
- enabled: true
  eval_set: configs/eval_sets/heldout_multidoc_k16_v2.yaml
  eval_every_epochs: 0.33
- enabled: true
  eval_set: configs/eval_sets/ood_models.yaml
  eval_every_epochs: 0.33
judge:
  model: anthropic/claude-sonnet-4.6
  max_workers: 16
  request_timeout_s: 60
wandb_project: lora-oracles
wandb_entity: null
fineweb_lora_dir: null
fineweb_summaries_path: null
fineweb_holdout_ids_path: null
fineweb_max_train_items: null
encoder_type: ao
encoder_top_k: 16
per_k_affines: false
learned_scale_layout: all14_rankfirst
learned_scale_init: 2.0
learned_scale_lr_mult: 50.0
learned_scale_hook_mode: modulated
hook_op: add
hook_layer: 1
typed_slots: false
instruction_preamble: null
use_system_prompt: false
lr_schedule: linear
note: "CISPO v9 \u2014 trained on IA+MD+FW combined K=8 DPO-holdout rollouts. Hypers:\
  \ lr=5e-6, eps_low=1.0, eps_high=1.0, grad_accum=4, shuffle=True, filter max>=5,\
  \ 1 epoch = 194 opt steps."