2023-11-09 09:46:45 -05:00
|
|
|
{
|
|
|
|
"bf16": {
|
|
|
|
"enabled": "auto"
|
|
|
|
},
|
|
|
|
"optimizer": {
|
|
|
|
"type": "AdamW",
|
|
|
|
"params": {
|
|
|
|
"lr": "auto",
|
|
|
|
"betas": "auto",
|
|
|
|
"eps": "auto",
|
|
|
|
"weight_decay": "auto"
|
|
|
|
}
|
|
|
|
},
|
|
|
|
|
|
|
|
"scheduler": {
|
2024-03-15 08:14:16 -04:00
|
|
|
"type": "WarmupCosineLR",
|
2023-11-09 09:46:45 -05:00
|
|
|
"params": {
|
2024-03-15 08:14:16 -04:00
|
|
|
"total_num_steps": "auto",
|
|
|
|
"warmup_num_steps": "auto",
|
2024-03-16 07:27:06 -04:00
|
|
|
"warmup_type": "linear"
|
2023-11-09 09:46:45 -05:00
|
|
|
}
|
|
|
|
},
|
|
|
|
|
|
|
|
"zero_optimization": {
|
|
|
|
"stage": 3,
|
|
|
|
"offload_optimizer": {
|
|
|
|
"device": "cpu",
|
|
|
|
"pin_memory": true
|
|
|
|
},
|
|
|
|
"offload_param": {
|
|
|
|
"device": "cpu",
|
|
|
|
"pin_memory": true
|
|
|
|
},
|
|
|
|
"overlap_comm": true,
|
|
|
|
"contiguous_gradients": true,
|
|
|
|
"sub_group_size": 1e9,
|
|
|
|
"reduce_bucket_size": "auto",
|
|
|
|
"stage3_prefetch_bucket_size": "auto",
|
|
|
|
"stage3_param_persistence_threshold": "auto",
|
|
|
|
"stage3_max_live_parameters": 1e9,
|
|
|
|
"stage3_max_reuse_distance": 1e9,
|
|
|
|
"stage3_gather_16bit_weights_on_model_save": true
|
|
|
|
},
|
|
|
|
|
|
|
|
"gradient_accumulation_steps": "auto",
|
|
|
|
"gradient_clipping": "auto",
|
|
|
|
"steps_per_print": 20,
|
|
|
|
"train_batch_size": "auto",
|
|
|
|
"train_micro_batch_size_per_gpu": "auto",
|
|
|
|
"wall_clock_breakdown": false
|
2024-03-16 07:27:06 -04:00
|
|
|
}
|