Files

36 lines
760 B
JSON

{
"fp16": {
"enabled": true,
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"optimizer": {
"type": "AdamW",
"params": {
"lr": 0.0001,
"betas": [
0.9,
0.999
],
"eps": 1e-8,
"weight_decay": 0
}
},
"bf16": {
"enabled": false
},
"train_micro_batch_size_per_gpu": 32,
"train_batch_size": 256,
"gradient_accumulation_steps": 1,
"zero_optimization": {
"stage": 2,
"overlap_comm": true,
"contiguous_gradients": true,
"sub_group_size": 1e9
},
"steps_per_print": 10000,
}