{
    "train_micro_batch_size_per_gpu": 8,
    "gradient_accumulation_steps": 1,
    "optimizer":{
        "type": "Adam",
        "params": {
            "lr": 1e-4,
            "betas": [0.9, 0.999],
            "weight_decay": 0.02,
            "adam_w_mode": true
        }
    },
    "scheduler":{
        "type": "WarmupCosineLR",
        "params":{}
    },
    "fp16": {
        "enabled": false,
        "auto_cast": false,
        "loss_scale": 0,
        "initial_scale_power": 16,
        "loss_scale_window": 1000,
        "hysteresis": 2,
        "consecutive_hysteresis": false,
        "min_loss_scale": 1
    },
    "zero_optimization": {
        "stage": 0,
        "overlap_comm": true,
        "contiguous_gradients": true,
        "sub_group_size": 1e9,
        "reduce_bucket_size": "auto",
        "stage3_prefetch_bucket_size": "auto",
        "stage3_param_persistence_threshold": "auto",
        "stage3_max_live_parameters": 1e9,
        "stage3_max_reuse_distance": 1e9,
        "stage3_gather_16bit_weights_on_model_save": true
    },
    "wandb":{
        "enabled": true,
        "project": "V2Dial"
    }
}