Skywork/train/ds_config/zero3_offload.json

27 lines
705 B
JSON

{
"train_batch_size" : "auto",
"train_micro_batch_size_per_gpu": "auto",
"steps_per_print": 10,
"gradient_accumulation_steps": "auto",
"wall_clock_breakdown": false,
"zero_optimization": {
"stage": 3,
"contiguous_gradients": true,
"stage3_max_live_parameters": 1e9,
"stage3_max_reuse_distance": 1e9,
"stage3_prefetch_bucket_size": 1e7,
"stage3_param_persistence_threshold": 1e5,
"reduce_bucket_size": 1e7,
"sub_group_size": 1e9,
"offload_optimizer": {
"device": "cpu"
},
"offload_param": {
"device": "cpu"
}
},
"bf16": {
"enabled": true
}
}