{
  "pipe-parallel-size": 1,
  "model-parallel-size": 1,

  # model settings
  "num-layers": 16,
  "hidden-size": 2048,
  "num-attention-heads": 8,
  "seq-length": 2048,
  "max-position-embeddings": 2048,
  "pos-emb": "rotary",
  "no-weight-tying": true,
  "gpt-j-residual": false,
  "output-layer-parallelism": "column",

  "scaled-upper-triang-masked-softmax-fusion": false,
  "bias-gelu-fusion": false,

  # init methods
  "init_method": "small_init",
  "output_layer_init_method": "wang_init",

  "optimizer": {
    "type": "Adam",
    "params": {
      "lr": 0.00025,
      "betas": [0.9, 0.95],
      "eps": 1.0e-8,
    }
  },
  "min_lr": 0.000025,

  # 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": 500000000,
    "overlap_comm": True,
    "reduce_scatter": True,
    "reduce_bucket_size": 500000000,
    "contiguous_gradients": True,
  },

  "train_micro_batch_size_per_gpu": 16,
  "gas": 1,
  "data-impl": "mmap",
  "num_workers": 1,

  # activation checkpointing
  "checkpoint-activations": true,
  "checkpoint-num-layers": 1,
  "partition-activations": true,
  "synchronize-each-layer": true,

  # regularization
  "gradient_clipping": 1.0,
  "weight-decay": 0.1,
  "hidden-dropout": 0,
  "attention-dropout": 0,

  # precision settings
  "fp16": {
    "fp16": true,
    "enabled": true,
    "loss_scale": 0,
    "loss_scale_window": 1000,
    "initial_scale_power": 12,
    "hysteresis": 2,
    "min_loss_scale": 1,
  },

  "train-iters": 143000,
  "lr-decay-iters": 143000,
  "distributed-backend": "nccl",
  "lr-decay-style": "cosine",
  "warmup": 0.01,
  "checkpoint-factor": 1000,
  "eval-interval": 40000,
  "eval-iters": 10,

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