experiments/ptv3/train_args.json

{
  "activation": "gelu",
  "adam_betas": "0.9,0.95",
  "arch": "ptv3",
  "aug_drop": 0.0,
  "aug_flip": true,
  "aug_jitter": 0.0,
  "aug_rotate": true,
  "batch_size": 32,
  "behind_emb_dim": 8,
  "cache_dir": "hf://usm3d/s23dr-2026-sampled_8192_v3:train",
  "conf_clamp_min": null,
  "conf_head_wd": 0.1,
  "conf_mode": "sinkhorn",
  "conf_weight": 0.1,
  "cooldown_start": 195000,
  "cooldown_steps": 5000,
  "cosine_decay": false,
  "cpu": false,
  "cross_attn_interval": 4,
  "decoder_input_xattn": false,
  "decoder_layers": 3,
  "deterministic": false,
  "dropout": 0.1,
  "ema_decay": 0.0,
  "encoder_layers": 4,
  "endpoint_warmup": 0,
  "endpoint_weight": 0.1,
  "ff": 1024,
  "hidden": 256,
  "kv_heads_cross": 2,
  "kv_heads_self": 2,
  "latent_layers": 7,
  "latent_tokens": 256,
  "learnable_fourier": false,
  "length_floor": 0.0,
  "lr": 0.00015,
  "num_heads": 4,
  "out_dir": "runs/step3b_8192",
  "pre_encoder_layers": 0,
  "qk_norm": true,
  "qk_norm_type": "l2",
  "rms_norm": true,
  "seed": 353,
  "segment_conf": true,
  "segment_param": "midpoint_dir_len",
  "segments": 64,
  "seq_len": 8192,
  "sinkhorn_dustbin": 0.3,
  "sinkhorn_eps": 0.1,
  "sinkhorn_eps_schedule": "none",
  "sinkhorn_eps_start": null,
  "sinkhorn_iters": 20,
  "sinkhorn_weight": 1.0,
  "steps": 200000,
  "val_cache_dir": "",
  "varifold_cross_only": false,
  "varifold_weight": 0.0,
  "vote_features": true,
  "warmup": 1000,
  "weight_decay": 0.01
}