{ "model": "sphere-ff", "dim": 512, "depth": 8, "heads": 8, "seq_len": 512, "batch_size": 32, "steps": 60000, "warmup": 1000, "lr": 0.0006, "solver_iters": 4, "solver_tol": 0.001, "eval_every": 1000, "seed": 0, "grad_accum": 2, "no_bf16": false, "r_init": 0.7, "logit_scale": 10.0, "tag": "1b", "save_checkpoint": true, "checkpoint_every": 0, "s3_prefix": "", "data_dir": "data1b", "wandb": false, "wandb_project": "spherical-attention", "wandb_entity": null, "cloudwatch": false, "cloudwatch_region": "us-east-2", "resume": "", "ngpt": true, "selective_wd": true, "grad_steps": 1, "ema": 0.999, "abort_divergence": 1.5 }