| { |
| "base_model": "Qwen/Qwen2.5-0.5B-Instruct", |
| "revision": "7ae557604adf67be50417f59c2c2f167def9a775", |
| "recurrent_start": 6, |
| "recurrent_end": 18, |
| "lora_rank": 8, |
| "lora_alpha": 16, |
| "symbols": [ |
| "A", |
| "B", |
| "C", |
| "D", |
| "E", |
| "F", |
| "G", |
| "H", |
| "I", |
| "J", |
| "K", |
| "L", |
| "M", |
| "N", |
| "O", |
| "P", |
| "Q", |
| "R", |
| "S", |
| "T", |
| "U", |
| "V", |
| "W", |
| "X", |
| "Y", |
| "Z" |
| ], |
| "token_ids": [ |
| 362, |
| 425, |
| 356, |
| 422, |
| 468, |
| 434, |
| 479, |
| 472, |
| 358, |
| 619, |
| 730, |
| 444, |
| 386, |
| 451, |
| 506, |
| 393, |
| 1207, |
| 431, |
| 328, |
| 350, |
| 547, |
| 647, |
| 467, |
| 1599, |
| 809, |
| 1863 |
| ], |
| "prompt_format": "dataset_raw", |
| "loss_vocabulary": "symbols", |
| "train_max_depth": 12, |
| "train_depths": [ |
| 1, |
| 2, |
| 3, |
| 4, |
| 5, |
| 6, |
| 8, |
| 10, |
| 12 |
| ], |
| "recurrence_mode": "fixed_prompt", |
| "completion_head": { |
| "intermediate": 1 |
| }, |
| "completion_loss_weight": 0.1, |
| "training_compute": { |
| "precision": "bf16", |
| "attention": "sdpa" |
| }, |
| "executor": { |
| "train_scope": "recurrent", |
| "isolated": true, |
| "bridge": true, |
| "direct_readout": true, |
| "controller_size": 1, |
| "prefix_reuse": true, |
| "gradient_checkpointing": true, |
| "controller_kind": "shared_number" |
| }, |
| "format": "loopformer-executor-v2", |
| "controller_training": { |
| "source": "models/stage1_pointer/controller-shared-number-seed83/best", |
| "source_checkpoint_sha256": "42059fd6fd4cc1ffe05a705a99a7aba76d4e7e0d87933bad18c7adc4cdee1110", |
| "trained_depths": [ |
| 1, |
| 2, |
| 3, |
| 4, |
| 5, |
| 6, |
| 7, |
| 8, |
| 10, |
| 11, |
| 12, |
| 13, |
| 14, |
| 15, |
| 16, |
| 18, |
| 19, |
| 20, |
| 21, |
| 22, |
| 23, |
| 24, |
| 25, |
| 26, |
| 27, |
| 28, |
| 30, |
| 31, |
| 32, |
| 33, |
| 34, |
| 35, |
| 36, |
| 37, |
| 38, |
| 39, |
| 40, |
| 42, |
| 43, |
| 44, |
| 45, |
| 46, |
| 47, |
| 48, |
| 49, |
| 50, |
| 51, |
| 52, |
| 54, |
| 55, |
| 56, |
| 57, |
| 58, |
| 59, |
| 60, |
| 61, |
| 62, |
| 63 |
| ], |
| "training_loops": 12, |
| "optimization_scope": "countdown_cell_only", |
| "config": { |
| "source": "models/stage1_pointer/controller-shared-number-seed83/best", |
| "training_config": "configs/controller_affine.json", |
| "output": "models/stage1_pointer/controller-shared-number-precision-seed83" |
| }, |
| "fit": { |
| "method": "float64 L-BFGS on original free-running numerical prefix labels; float32 deployment", |
| "training_counts": [ |
| 1, |
| 2, |
| 3, |
| 4, |
| 5, |
| 6, |
| 7, |
| 8, |
| 10, |
| 11, |
| 12, |
| 13, |
| 14, |
| 15, |
| 16, |
| 18, |
| 19, |
| 20, |
| 21, |
| 22, |
| 23, |
| 24, |
| 25, |
| 26, |
| 27, |
| 28, |
| 30, |
| 31, |
| 32, |
| 33, |
| 34, |
| 35, |
| 36, |
| 37, |
| 38, |
| 39, |
| 40, |
| 42, |
| 43, |
| 44, |
| 45, |
| 46, |
| 47, |
| 48, |
| 49, |
| 50, |
| 51, |
| 52, |
| 54, |
| 55, |
| 56, |
| 57, |
| 58, |
| 59, |
| 60, |
| 61, |
| 62, |
| 63 |
| ], |
| "training_loops": 12, |
| "objective_evaluations": 10, |
| "before_mse": 4.1626904266916364e-09, |
| "fitted_mse": 2.002921115782509e-12, |
| "deployed_mse": 6.307695082326698e-12, |
| "learned_gain": 1.0, |
| "learned_offset": -0.9999999403953552, |
| "numeric_targets_are_inputs": false |
| }, |
| "selection": "One predetermined training-label fit; no stress/graph benchmark selection" |
| } |
| } |
|
|
