{ "model_name": "/root/garble_runs/gq1_lr5e6/step_6", "full_ft": true, "use_vllm": false, "base_model": false, "grad_ckpt": true, "env": "state_track_q", "curriculum": [ { "r_min": 4, "r_max": 4, "t_min": 6, "t_max": 8, "val_max": 30, "k_max": 9, "mod": 97, "n_queries": 3 }, { "r_min": 4, "r_max": 4, "t_min": 9, "t_max": 11, "val_max": 30, "k_max": 9, "mod": 97, "n_queries": 3 }, { "r_min": 4, "r_max": 4, "t_min": 12, "t_max": 14, "val_max": 30, "k_max": 9, "mod": 97, "n_queries": 3 }, { "r_min": 4, "r_max": 4, "t_min": 16, "t_max": 18, "val_max": 30, "k_max": 9, "mod": 97, "n_queries": 3 }, { "r_min": 4, "r_max": 4, "t_min": 20, "t_max": 22, "val_max": 30, "k_max": 9, "mod": 97, "n_queries": 3 }, { "r_min": 4, "r_max": 4, "t_min": 24, "t_max": 26, "val_max": 30, "k_max": 9, "mod": 97, "n_queries": 3 }, { "r_min": 4, "r_max": 4, "t_min": 28, "t_max": 30, "val_max": 30, "k_max": 9, "mod": 97, "n_queries": 3 }, { "r_min": 4, "r_max": 4, "t_min": 34, "t_max": 36, "val_max": 30, "k_max": 9, "mod": 97, "n_queries": 3 }, { "r_min": 4, "r_max": 4, "t_min": 40, "t_max": 42, "val_max": 30, "k_max": 9, "mod": 97, "n_queries": 3 }, { "r_min": 4, "r_max": 4, "t_min": 48, "t_max": 50, "val_max": 30, "k_max": 9, "mod": 97, "n_queries": 3 } ], "auto_curriculum": true, "start_tier": 0, "tier_advance_thresh": 0.75, "tier_min_dwell": 8, "lr": 5e-06, "warmup_ratio": 0.02, "max_grad_norm": 1.0, "max_steps": 600, "batch_problems": 8, "group_size": 12, "pg_microbatch": 2, "gen_chunk": 48, "temperature": 1.0, "top_p": 1.0, "think_temperature": 1.1, "out_temperature": 0.6, "max_think": 512, "max_out": 64, "max_seq_length": 8192, "correct_thresh": 0.99, "rank_bonus": 0.25, "adaptive_lambda": true, "lambda_target": 0.6, "lambda_lr": 0.02, "lambda_ema_alpha": 0.9, "lambda_init": 0.0, "lambda_max": 0.4, "lambda_penalty": 0.3, "length_penalty_mode": "linear", "length_target": null, "length_floor": null, "length_anneal_steps": 0, "penalty_signal": "length", "penalty_on_correct_only": true, "w_len": 0.5, "w_leg": 1.0, "normalize_advantages": true, "eval_every": 10, "eval_problems": 16, "seed": 42, "n_checkpoints": 12, "keep_ckpts": 2, "latest_optimizer": 0, "save_dir": "/root/garble_runs", "wandb_project": "cot-oracle", "wandb_entity": "MATS10-CS-JB", "wandb_group": "gq1", "run_name": "gq1_lr5e6", "console_every": 1, "table_every": 10, "save_every": 25, "resume_from": "/root/garble_runs/gq1_lr5e6/step_6", "lora_r": 0, "lora_alpha": 0, "lora_dropout": 0.0 }