| { |
| "fold": 0, |
| "split_seed": 0, |
| "patch_size": 2, |
| "embed_dim": null, |
| "depth": null, |
| "num_heads": null, |
| "mlp_dim": null, |
| "hist_n": 3, |
| "epochs": 30, |
| "batch_size": 86, |
| "global_batch_size": 516, |
| "learning_rate": 0.0003, |
| "weight_decay": 0.0, |
| "max_grad_norm": 1.0, |
| "lr_scheduler": "cosine", |
| "seed": 42, |
| "num_workers": 8, |
| "optimizer": "muon", |
| "muon_lr": 0.0, |
| "muon_momentum": 0.95, |
| "muon_adjust_lr": "match_rms_adamw", |
| "gamma": 0.95, |
| "no_amp": false, |
| "amp_dtype": "bf16", |
| "no_compile": false, |
| "compile_mode": "reduce-overhead", |
| "distributed": true, |
| "disable_augment": false, |
| "num_color_permute": 9, |
| "eval_batch_size": null, |
| "eval_every": 1, |
| "max_train_batches": 0, |
| "arch": "unified_hist_cm", |
| "model_config": { |
| "embed_dim": 512, |
| "depth": 10, |
| "num_heads": 8, |
| "mlp_dim": 512, |
| "dropout": 0.1, |
| "num_actions": 8, |
| "arch": "unified_hist_cm", |
| "backbone": "unified_hist", |
| "click_embed": true, |
| "hist_n": 3, |
| "patch_size": 2, |
| "num_input_colors": 17, |
| "conditioning": "adaln_zero_all_layers + learned vector on the clicked patch token (zero-init)", |
| "norm": "pre", |
| "positional": "rope_only", |
| "task_token": false, |
| "attention": "sdpa" |
| }, |
| "world_size": 6, |
| "loss": "ffp_only", |
| "folds": { |
| "num_folds": 1, |
| "split_seed": 0, |
| "test_games_by_fold": { |
| "0": [] |
| } |
| } |
| } |
|
|
