2023-04-04 16:58:08 -04:00
|
|
|
{
|
|
|
|
|
"train_batch_size": "auto",
|
2023-04-04 22:52:44 -04:00
|
|
|
"gradient_accumulation_steps": "auto",
|
2023-04-04 16:58:08 -04:00
|
|
|
"train_micro_batch_size_per_gpu": "auto",
|
|
|
|
|
"fp16": {
|
|
|
|
|
"enabled": "auto",
|
|
|
|
|
"min_loss_scale": 1,
|
|
|
|
|
"loss_scale_window": 1000,
|
|
|
|
|
"hysteresis": 2,
|
|
|
|
|
"initial_scale_power": 32
|
|
|
|
|
},
|
|
|
|
|
"bf16": {
|
|
|
|
|
"enabled": "auto"
|
|
|
|
|
},
|
|
|
|
|
"gradient_clipping": 1.0,
|
|
|
|
|
"zero_optimization": {
|
|
|
|
|
"stage": 2,
|
|
|
|
|
"offload_param": {
|
|
|
|
|
"device": "none"
|
|
|
|
|
},
|
|
|
|
|
"offload_optimizer": {
|
2023-04-05 16:42:35 -04:00
|
|
|
"device": "none"
|
2023-04-04 16:58:08 -04:00
|
|
|
},
|
|
|
|
|
"allgather_partitions": true,
|
|
|
|
|
"allgather_bucket_size": 5e8,
|
|
|
|
|
"contiguous_gradients": true
|
2023-04-13 13:58:59 -04:00
|
|
|
},
|
|
|
|
|
"optimizer": {
|
|
|
|
|
"type": "AdamW",
|
|
|
|
|
"params": {
|
|
|
|
|
"lr": "auto",
|
|
|
|
|
"betas": [
|
|
|
|
|
0.9,
|
|
|
|
|
0.999
|
|
|
|
|
],
|
|
|
|
|
"eps": 1e-08
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
"scheduler": {
|
|
|
|
|
"type": "WarmupLR",
|
|
|
|
|
"params": {
|
|
|
|
|
"warmup_min_lr": 0,
|
|
|
|
|
"warmup_max_lr": "auto",
|
|
|
|
|
"warmup_num_steps": "auto",
|
|
|
|
|
"warmup_type": "linear"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
