Files
axolotl/deepspeed_configs/zero3_bf16.json
2024-10-28 07:32:49 -04:00

23 lines
604 B
JSON

{
"zero_optimization": {
"stage": 3,
"overlap_comm": true,
"contiguous_gradients": true,
"sub_group_size": 0,
"reduce_bucket_size": "auto",
"stage3_prefetch_bucket_size": "auto",
"stage3_param_persistence_threshold": "auto",
"stage3_max_live_parameters": 0,
"stage3_max_reuse_distance": 0,
"stage3_gather_16bit_weights_on_model_save": true
},
"bf16": {
"enabled": true
},
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"wall_clock_breakdown": false
}