deepspeed_config.json

{
    "train_micro_batch_size_per_gpu": 1,
    "gradient_accumulation_steps": 1,
    "optimizer": {
        "type": "Adam",
        "params": {
            "lr": 0.001,
            "betas": [
                0.8,
                0.999
            ],
            "eps": 1e-08,
            "weight_decay": 3e-07
        }
    },
    "scheduler": {
        "type": "WarmupLR",
        "params": {
            "warmup_min_lr": 0,
            "warmup_max_lr": 0.001,
            "warmup_num_steps": 1000
        }
    },
    "activation_checkpointing": {
        "partition_activations": true,
        "cpu_checkpointing": true,
        "contiguous_memory_optimization": false,
        "number_checkpoints": null,
        "synchronize_checkpoint_boundary": false,
        "profile": true
    },
    "fp16": {
        "enabled": true,
        "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": 3,
        "offload_param": {
            "device": "cpu",
            "pin_memory": true
        },
        "offload_optimizer": {
            "device": "cpu",
            "pin_memory": true
        },
        "contiguous_gradients": true,
        "overlap_comm": true
    }
}