{ "seed": 42, "output_dir": "./codenames_complete", "vocab_size": 500, "max_clue_number": 9, "hidden": 192, "gnn_layers": 3, "gnn_heads": 6, "n_strat": 6, "ppo": { "episodes": 1000, "update_steps": 512, "batch_size": 128, "epochs": 4, "clip": 0.2, "vf_coef": 0.5, "ent_coef": 0.01, "gamma": 0.99, "gae_lambda": 0.95, "lr_slow": 3e-05, "lr_fast": 0.0006, "opponent_hist_len": 16, "log_every": 50, "eval_every": 250, "eval_games": 200, "meta_every": 4, "meta_lr": 0.001 }, "pref_states": 800, "pref_rollouts_per_pair": 4, "do_sft": 1, "do_dpo": 1, "sft_steps": 150, "dpo_steps": 200, "distill_dataset_size": 2000, "distill_steps": 400, "distill_batch_size": 64, "eval_games": 200 }