| { | |
| "selected_config": { | |
| "name": "plain_l2_c0.25", | |
| "class_weight": null, | |
| "C": 0.25 | |
| }, | |
| "selection_metric": "macro_f1 then avg_excess_cost_tokens_vs_oracle after validation-based early stopping", | |
| "dev_metrics_before_refit": { | |
| "n_examples": 416, | |
| "accuracy": 0.569712, | |
| "macro_f1": 0.267917, | |
| "realized_solve_rate": 0.627404, | |
| "avg_total_tokens": 51731.351, | |
| "avg_model_calls": 15.312, | |
| "avg_wall_time_seconds": 89.666, | |
| "avg_excess_cost_tokens_vs_oracle": 19073.486, | |
| "missed_success_rate": 0.323834 | |
| }, | |
| "loss_history_epochs": 30, | |
| "early_stopping_metric": "dev_log_loss", | |
| "selected_epoch": 1, | |
| "best_dev_log_loss": 1.177944, | |
| "feature_dimensions": { | |
| "source_cardinality": 63, | |
| "domain_cardinality": 155, | |
| "total_feature_dim": 220 | |
| }, | |
| "label_counts_train": { | |
| "baseline_llm": 1898, | |
| "single_agent": 768, | |
| "none": 244, | |
| "per": 292, | |
| "broadcast": 140 | |
| }, | |
| "label_counts_dev": { | |
| "baseline_llm": 237, | |
| "single_agent": 96, | |
| "per": 36, | |
| "none": 30, | |
| "broadcast": 17 | |
| }, | |
| "label_counts_test": { | |
| "baseline_llm": 238, | |
| "none": 32, | |
| "single_agent": 97, | |
| "broadcast": 18, | |
| "per": 38 | |
| }, | |
| "features": [ | |
| "source", | |
| "domain", | |
| "difficulty", | |
| "difficulty_tier" | |
| ] | |
| } | |