MiniCPM/finetune/configs/ds_config_zero3.json
2024-02-01 02:21:25 +08:00

38 lines
1.0 KiB
JSON

{
"fp16": {
"enabled": "auto",
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"bf16": {
"enabled": "auto"
},
"zero_optimization": {
"stage": 3,
"allgather_partitions": true,
"allgather_bucket_size": 5e8,
"reduce_scatter": true,
"contiguous_gradients": true,
"overlap_comm": true,
"reduce_bucket_size": "auto",
"stage3_prefetch_bucket_size": "auto",
"stage3_param_persistence_threshold": "auto",
"stage3_gather_16bit_weights_on_model_save": true
},
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"gradient_accumulation_steps": "auto",
"gradient_clipping": 1.0,
"wall_clock_breakdown": false,
"flops_profiler": {
"enabled": false,
"profile_step": 1,
"module_depth": -1,
"top_modules": 1,
"detailed": true,
"output_file": null
}
}