config/deepspeed.json

{
    "train_micro_batch_size_per_gpu": 1,
    "gradient_accumulation_steps": 8,
    "steps_per_print": 1,
    "optimizer": {
        "type": "AdamW",
        "params": {
            "lr": 1e-4,
            "betas": [0.9, 0.95],
            "weight_decay": 0.05
        }
    },
    "scheduler": {
        "type": "WarmupLR",
        "params": {
            "warmup_min_lr": 0.0,
            "warmup_max_lr": 1e-4,
            "warmup_num_steps": 4000
        }
    },
    "gradient_clipping": 1.0,
    "zero_optimization": {
        "stage": 2,
        "offload_optimizer": {
            "device": "cpu",
            "pin_memory": true
        },
        "overlap_comm": true,
        "contiguous_gradients": true,
        "reduce_bucket_size": 5e7
    },
    "activation_checkpointing": {
        "partition_activations": true,
        "contiguous_memory_optimization": true,
        "cpu_checkpointing": true,
        "number_checkpoints": 2
    }
}