{
  "babylm_checkpoints": true,
  "babylm_ckpt_dir": null,
  "beta1": 0.9,
  "beta2": 0.98,
  "causal_per_masked": 1,
  "dev_dir": "/home/sid/sidBabyLM/nanochat/data/dev",
  "eps": 1e-08,
  "full_dev": false,
  "grad_clip": 2.0,
  "hub_repo": "svsatheesh/BabySteps_ChadBert-100M-mixed",
  "keep_ratio": 0.1,
  "lr": 0.007,
  "mask_end": 0.15,
  "mask_start": 0.3,
  "masked_per_causal": 0,
  "micro_batch": 8,
  "muon_aux_lr": 0.007,
  "muon_aux_weight_decay": null,
  "muon_batch_updates": true,
  "muon_beta2": 0.95,
  "muon_eps2": 1e-08,
  "muon_lr": 0.005,
  "muon_momentum": 0.95,
  "muon_nesterov": true,
  "muon_ns_steps": 5,
  "muon_split_qkv": true,
  "muon_weight_decay": 0.1,
  "optimizer": "muon",
  "output_dir": "/home/sid/sidBabyLM/gptbert/runs/sweep100m/muon-100m-legacyCK-mixed-lr0.005-aux0.007-s42",
  "phase1_frac": 0.6,
  "phase2_frac": 0.8,
  "precision": "bf16",
  "push_to_hub": false,
  "random_ratio": 0.1,
  "repo": "BabyLM-community/babylm-baseline-100m-gpt-bert-mixed",
  "retokenize": false,
  "save_every": 0,
  "seed": 42,
  "tail_avg_every": 10,
  "tail_avg_frac": 0.0,
  "tokens_per_step": 131072,
  "total_steps": 12330,
  "track": "strict",
  "train_dir": "/home/sid/sidBabyLM/nanochat/data/strict",
  "val_every": 1000,
  "val_seq_len": 128,
  "val_words": 1000000,
  "warmup_frac": 0.016,
  "weight_decay": 0.1,
  "z_loss": 0.0001
}