| { | |
| "cache_dir": "hf://usm3d/s23dr-2026-sampled_2048_v2:train", | |
| "val_cache_dir": "", | |
| "arch": "perceiver", | |
| "segments": 64, | |
| "hidden": 256, | |
| "ff": 1024, | |
| "latent_tokens": 256, | |
| "latent_layers": 7, | |
| "encoder_layers": 4, | |
| "pre_encoder_layers": 0, | |
| "decoder_layers": 3, | |
| "decoder_input_xattn": false, | |
| "qk_norm": true, | |
| "qk_norm_type": "l2", | |
| "learnable_fourier": false, | |
| "num_heads": 4, | |
| "kv_heads_cross": 2, | |
| "kv_heads_self": 2, | |
| "cross_attn_interval": 4, | |
| "dropout": 0.1, | |
| "steps": 160000, | |
| "batch_size": 32, | |
| "lr": 3e-05, | |
| "muon_lr": null, | |
| "adam_betas": "0.9,0.95", | |
| "warmup": 10000, | |
| "cosine_decay": false, | |
| "cooldown_start": 140000, | |
| "cooldown_steps": 20000, | |
| "mup": false, | |
| "mup_base_width": 128, | |
| "seed": 353, | |
| "varifold_weight": 0.0, | |
| "varifold_cross_only": false, | |
| "sinkhorn_weight": 1.0, | |
| "sinkhorn_eps": 0.1, | |
| "sinkhorn_eps_start": null, | |
| "sinkhorn_iters": 20, | |
| "sinkhorn_dustbin": 0.3, | |
| "vertex_f1_weight": 0.0, | |
| "soft_hss_weight": 0.0, | |
| "endpoint_weight": 0.1, | |
| "endpoint_warmup": 0, | |
| "aug_rotate": true, | |
| "aug_jitter": 0.0, | |
| "aug_drop": 0.0, | |
| "aug_flip": true, | |
| "gpu_dataset": false, | |
| "stored_seq_len": 8192, | |
| "rms_norm": true, | |
| "activation": "gelu", | |
| "behind_emb_dim": 8, | |
| "vote_features": true, | |
| "segment_param": "midpoint_dir_len", | |
| "length_floor": 0.0, | |
| "segment_conf": true, | |
| "conf_weight": 0.1, | |
| "conf_mode": "sinkhorn", | |
| "conf_clamp_min": null, | |
| "conf_head_wd": 0.1, | |
| "optimizer": "adamw", | |
| "out_dir": "/workspace/s23dr_2026_example/runs", | |
| "resume": "runs/20260322_085443/checkpoints/step125000.pt", | |
| "cpu": false, | |
| "args_from": "runs/20260322_085443/args.json" | |
| } |