| { | |
| "architecture": "PCRClassifier (phase-coherent linear recurrence + non-competing complex screening attention hybrid)", | |
| "task": "pathx", | |
| "seq_len": 16384, | |
| "vocab_size": 256, | |
| "n_params": 2011660, | |
| "training_steps": 250000, | |
| "pcr_config": { | |
| "d_model": 128, | |
| "n_layers": 6, | |
| "d_state": 256, | |
| "norm": "batch", | |
| "block": "s5", | |
| "encoder": "linear", | |
| "dropout": 0.0, | |
| "r_min": 0.999, | |
| "r_max": 0.9999, | |
| "max_phase": 0.31416, | |
| "lr_rec_factor": 0.3333, | |
| "lr_bc_factor": 0.3333, | |
| "screen_layers": [ | |
| 2, | |
| 4 | |
| ], | |
| "screen_heads": 4, | |
| "screen_dim_head": 32, | |
| "screen_chunk": 1024 | |
| }, | |
| "optimizer": { | |
| "lr": 0.00045, | |
| "weight_decay": 0.05, | |
| "warmup": 2500, | |
| "lr_scheduler": "hold_then_linear", | |
| "lr_decay_start": 200000, | |
| "lr_final_ratio": 0.1, | |
| "clip_grad": 1.0, | |
| "batch_size": 32 | |
| }, | |
| "seed": 0 | |
| } |