global_step420000/config.yml

{
  # parallelism settings
  "pipe-parallel-size": 0,
  "model-parallel-size": 1,

  # model settings
  "num-layers": 24,
  "hidden-size": 2048,
  "num-attention-heads": 32,
  "seq-length": 4096,
  "max-position-embeddings": 4096,

  # architecture design
  "attention_head_type": "multihead",
  "norm": "layernorm",
  "pos-emb": "rotary",
  "rotary_pct": 0.25,
  "rotary_interleaved": false,  # GPT-NeoX style
  "mlp_multiple_of": 256,
  "mlp_type": "gated",
  "activation": "silu",
  "no-weight-tying": true,
  "gpt_j_residual": false,
  "gpt_j_tied": false,
  "output_layer_parallelism": "column",

  # init methods
  "init_method": "normal",
  "output_layer_init_method": "scaled_normal",
  "init_method_std": 0.02,

  # biases
  # NOTE: QKV projections were hard-coded with bias=True
  "use_bias_in_norms": false,
  "use_bias_in_attn_linear": false,
  "use_bias_in_mlp": false,

  # fused ops
  "use_flash_cross_entropy": true,
  "bias-gelu-fusion": false,
  "scaled-upper-triang-masked-softmax-fusion": false,
  "attention-config": [[["flash"], 24]],

  # optimizer settings
  "optimizer": {
    "type": "Adam",
    "params": {
      "lr": 0.001,
      "betas": [0.9, 0.95],
      "eps": 1.0e-8,
    }
  },
  "min_lr": 0.0001,
  "train-iters": 540_000,
  "lr-decay-iters": 540_000,
  "lr-decay-style": "hybrid_cosine_inv_sqrt_2",
  "warmup": 0.018,
  "cooldown": 0.,

  "reset_attention_mask": true,
  "reset_position_ids": true,

  # for all zero_optimization options, see https://www.deepspeed.ai/docs/config-json/#zero-optimizations-for-fp16-training
  "zero_optimization": {
    "stage": 1,
    "allgather_partitions": true,
    "allgather_bucket_size": 1260000000,
    "overlap_comm": true,
    "reduce_scatter": true,
    "reduce_bucket_size": 1260000000,
    "contiguous_gradients": true,
    "cpu_offload": false,
  },

  # batch / data settings
  "train_micro_batch_size_per_gpu": 2,
  "gradient_accumulation_steps": 2,
  "data-impl": "mmap",
  "eval-interval": 500_000,
  "eval-iters": 1,
  "eval_batch_size": 1,
  "eval_tasks": [],

  # activation checkpointing
  "checkpoint-activations": true,
  "checkpoint-num-layers": 24,
  "partition-activations": true,
  "synchronize-each-layer": true,

  # regularization
  "gradient_clipping": 1,
  "weight-decay": 0.1,
  "hidden-dropout": 0.,
  "attention-dropout": 0.,

  # precision settings
  "bf16": { "enabled": true },
  "precision": "bfloat16",
  "full_precision_lm_cross_entropy": true,
  "fp32_allreduce": true,

  # misc. training settings
  "num-workers": 2,
  "distributed-backend": "nccl",

  # checkpoint settings
  "checkpoint-factor": 10_000,
  #"s3_sync_interval": 20_000,
  "extra-save-iters": [230_001],
  "save": "",
  "load": "",
  #"s3_path": "",

  "train_data_paths": [],
  "valid-data-paths": [],
  "test-data-paths": [],

  # tokenizer settings
  "tokenizer-type": "TiktokenTokenizer",
  "vocab-file": "arcade100k.tiktoken",

  "log-interval": 10,
  "steps_per_print": 10,
  "wall_clock_breakdown": true,

  "use_wandb": true,
  "wandb_host": "",
  "wandb_team": "",
  "wandb_project": "",
  "wandb_group": "",
  "wandb_name": "",
  #"wandb_resume": "must",

  # multi-node launcher
  "launcher": "slurm",
  "deepspeed_slurm": true,

  "seed": 1234
}