wehub-resource-sync
43 lines
990 B
JSON
43 lines
990 B
JSON
{
|
|
"train_micro_batch_size_per_gpu": 1,
|
|
"gradient_accumulation_steps": 1,
|
|
"steps_per_print": 10,
|
|
"optimizer": {
|
|
"type": "AdamW",
|
|
"params": {
|
|
"lr": 1e-5,
|
|
"betas": [0.9, 0.999],
|
|
"eps": 1e-8,
|
|
"weight_decay": 0.01
|
|
}
|
|
},
|
|
"scheduler": {
|
|
"type": "WarmupLR",
|
|
"params": {
|
|
"warmup_min_lr": 0,
|
|
"warmup_max_lr": 1e-5,
|
|
"warmup_num_steps": 10
|
|
}
|
|
},
|
|
"gradient_clipping": 1.0,
|
|
"bf16": {
|
|
"enabled": true
|
|
},
|
|
"zero_optimization": {
|
|
"stage": 3,
|
|
"allgather_partitions": true,
|
|
"allgather_bucket_size": 5e7,
|
|
"overlap_comm": true,
|
|
"reduce_scatter": true,
|
|
"reduce_bucket_size": 5e7,
|
|
"contiguous_gradients": true,
|
|
"stage3_max_live_parameters": 1e9,
|
|
"stage3_max_reuse_distance": 1e9,
|
|
"stage3_prefetch_bucket_size": 5e7,
|
|
"stage3_param_persistence_threshold": 1e5,
|
|
"stage3_gather_16bit_weights_on_model_save": true,
|
|
"sub_group_size": 1e12
|
|
},
|
|
"wall_clock_breakdown": false
|
|
}
|