mode: cd n_probes: 16 probe: rademacher eps: 0.1 probe_chunk: 8 measure_fp32: true tokens: 2e9 global_batch_tokens: 524288 lr: 6e-4 warmup: 2000 optimizer: adamw wd: 0.1 betas: [0.9, 0.95] grad_clip: 1.0 eval_every: 500 seed: 0