{
    "train_batch_size": 64,
    "train_micro_batch_size_per_gpu": 1,
    "gradient_accumulation_steps": 16,
    "optimizer": {
        "type": "Adam",
        "params": {
            "lr": 3e-05,
            "betas": [
                0.9,
                0.999
            ],
            "eps": 1e-8,
            "weight_decay": 0.01
        }
    },
    "gradient_clipping": 0.1,
    "scheduler": {
        "type": "OneCycle",
        "params": {
            "cycle_first_step_size": 16000,
            "cycle_first_stair_count": 8000,
            "decay_step_size": 16000,
            "cycle_min_lr": 1e-06,
            "cycle_max_lr": 3e-05,
            "decay_lr_rate": 1e-07,
            "cycle_min_mom": 0.85,
            "cycle_max_mom": 0.99,
            "decay_mom_rate": 0.0
        }
    },
    "zero_optimization": true,
    "disable_allgather": true,
    "fp16": {
        "enabled": true,
        "loss_scale": 0,
        "min_loss_scale": 1
    }
}