ds_config_zero3.json 1.15 KB
Newer Older
1
2
3
4
5
{
    "fp16": {
        "enabled": true,
        "loss_scale": 0,
        "loss_scale_window": 1000,
6
        "initial_scale_power": 16,
7
8
9
10
        "hysteresis": 2,
        "min_loss_scale": 1
    },

11
    "zero_optimization": {
12
13
14
15
        "stage": 3,
        "cpu_offload": true,
        "cpu_offload_params": true,
        "cpu_offload_use_pin_memory" : true,
16
17
        "overlap_comm": true,
        "contiguous_gradients": true,
18
19
20
21
22
23
24
        "sub_group_size": 1e14,
        "reduce_bucket_size": 0,
        "stage3_prefetch_bucket_size": 0,
        "stage3_param_persistence_threshold": 0,
        "stage3_max_live_parameters": 1e9,
        "stage3_max_reuse_distance": 1e9,
        "stage3_gather_fp16_weights_on_model_save": true
25
    },
26

27
28
29
30
31
32
33
34
35
    "optimizer": {
        "type": "AdamW",
        "params": {
            "lr": 3e-5,
            "betas": [0.8, 0.999],
            "eps": 1e-8,
            "weight_decay": 3e-7
        }
    },
36

37
38
39
40
41
42
43
44
    "scheduler": {
        "type": "WarmupLR",
        "params": {
            "warmup_min_lr": 0,
            "warmup_max_lr": 3e-5,
            "warmup_num_steps": 500
        }
    },
45
46
47
48

    "steps_per_print": 2000,
    "wall_clock_breakdown": false
}