ds_config_zero2.json 943 Bytes
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
12
13
14
15
16
17
18
19
20
    "zero_optimization": {
        "stage": 2,
        "allgather_partitions": true,
        "allgather_bucket_size": 2e8,
        "overlap_comm": true,
        "reduce_scatter": true,
        "reduce_bucket_size": 2e8,
        "contiguous_gradients": true,
        "cpu_offload": true
    },
21

22
23
24
25
26
27
28
29
30
    "optimizer": {
        "type": "AdamW",
        "params": {
            "lr": 3e-5,
            "betas": [0.8, 0.999],
            "eps": 1e-8,
            "weight_decay": 3e-7
        }
    },
31

32
33
34
35
36
37
38
39
    "scheduler": {
        "type": "WarmupLR",
        "params": {
            "warmup_min_lr": 0,
            "warmup_max_lr": 3e-5,
            "warmup_num_steps": 500
        }
    },
40
41
42
43

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