| { | |
| "bf16": { | |
| "enabled": "auto" | |
| }, | |
| "zero_optimization": { | |
| "stage": 3, | |
| "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": false | |
| }, | |
| "gradient_accumulation_steps": "auto", | |
| "gradient_clipping": "auto", | |
| "steps_per_print": 2000, | |
| "train_batch_size": "auto", | |
| "train_micro_batch_size_per_gpu": "auto", | |
| "wall_clock_breakdown": false, | |
| "flops_profiler": { | |
| "enabled": true, | |
| "profile_step": 10, | |
| "module_depth": -1, | |
| "top_modules": 3, | |
| "detailed": true, | |
| "output_file": "flops_profiler.out" | |
| } | |
| } |