# The name of the model to pretrain. Choose from names in ``litgpt.config``. Mutually exclusive with
# ``model_config``. (type: Optional[str], default: null)
model_name: genomics-llama

# A ``litgpt.Config`` object to define the model architecture. Mutually exclusive with
# ``model_config``. (type: Optional[Config], default: null)
model_config:

# Directory in which to save checkpoints and logs. If running in a Lightning Studio Job, look for it in
# /teamspace/jobs/<job-name>/share. (type: <class 'Path'>, default: out/pretrain)
out_dir: out/pretrain/genomics-llama

# Optional path to a checkpoint directory to initialize the model from.
# Useful for continued pretraining. Mutually exclusive with ``resume``. (type: Optional[Path], default: null)
initial_checkpoint_dir:

# Path to a checkpoint directory to resume from in case training was interrupted, or ``True`` to resume
# from the latest checkpoint in ``out_dir``. (type: Union[bool, Path], default: False)
resume: false

# Data-related arguments. If not provided, the default is ``litgpt.data.TinyLlama``.
data: NAO

# Training-related arguments. See ``litgpt.args.TrainArgs`` for details
train:

  # Number of optimizer steps between saving checkpoints (type: Optional[int], default: 1000)
  save_interval: 1000

  # Number of iterations between logging calls (type: int, default: 1)
  log_interval: 1

  # Number of samples between optimizer steps across data-parallel ranks (type: int, default: 512)
  global_batch_size: 30720

  # Number of samples per data-parallel rank (type: int, default: 4)
  micro_batch_size: 48

  # Number of iterations with learning rate warmup active (type: int, default: 2000)
  lr_warmup_steps: 2000

  # Number of epochs to train on (type: Optional[int], default: null)
  epochs:

  # Total number of tokens to train on (type: Optional[int], default: 3000000000000)
  max_tokens: 1_000_000_000_000

  # Limits the number of optimizer steps to run. (type: Optional[int], default: null)
  max_steps:

  # Model sequence length. Limits the length of samples. Off by default (type: Optional[int], default: null)
  max_seq_length: 512

  # Sequence length for the dataloader
  seq_len_data: 128

  # Whether to tie the embedding weights with the language modeling head weights. (type: Optional[bool], default: False)
  tie_embeddings:

  #   (type: float, default: 0.0004)
  learning_rate: 6e-4

  #   (type: float, default: 0.1)
  weight_decay: 0.1

  #   (type: float, default: 0.9)
  beta1: 0.9

  #   (type: float, default: 0.95)
  beta2: 0.95

  #   (type: Optional[float], default: 1.0)
  max_norm: 1.0

  #   (type: float, default: 4e-05)
  min_lr: 4.0e-05

  log_stability_interval: 100

  z_loss: True

# Evaluation-related arguments. See ``litgpt.args.EvalArgs`` for details
eval:

  # Number of optimizer steps between evaluation calls (type: int, default: 1000)
  interval: 200

  # Number of tokens to generate (type: Optional[int], default: null)
  max_new_tokens:

  # Number of iterations (type: int, default: 100)
  max_iters: 100

# How many devices/GPUs to use. Uses all GPUs by default. (type: Union[int, str], default: auto)
devices: auto

# Optional path to the tokenizer dir that was used for preprocessing the dataset. Only some data
# module require this. (type: Optional[Path], default: null)
# tokenizer_dir: checkpoints/genomics-llama
tokenizer_dir: minbpe/mgfm-1024

# The name of the logger to send metrics to. (type: Literal['wandb', 'tensorboard', 'csv'], default: tensorboard)
logger_name: wandb

# The random seed to use for reproducibility. (type: int, default: 42)
seed: 42