trlx/examples/summarize_rlhf/sft/ds_config_gptj.json

{
  "train_batch_size": 128,
  "fp16": {
    "enabled": true,
    "min_loss_scale": 1,
    "opt_level": "O2"
  },
  "zero_optimization": {
    "stage": 2,
    "offload_param": {
      "device": "cpu"
    },
    "offload_optimizer": {
      "device": "cpu"
    },
    "allgather_partitions": true,
    "allgather_bucket_size": 5e8,
    "contiguous_gradients": true
  },
  "optimizer": {
    "type": "AdamW",
    "params": {
      "lr": 1e-05,
      "betas": [
        0.9,
        0.95
      ],
      "eps": 1e-08
    }
  },
  "scheduler": {
    "type": "WarmupLR",
    "params": {
      "warmup_min_lr": 0,
      "warmup_max_lr": 1e-05,
      "warmup_num_steps": "auto"
    }
  }
}