| { | |
| "bf16": { | |
| "enabled": false | |
| }, | |
| "zero_optimization": { | |
| "stage": 3, | |
| "offload_optimizer": { | |
| "device": "cpu" | |
| }, | |
| "offload_param": { | |
| "device": "cpu" | |
| }, | |
| "overlap_comm": true, | |
| "contiguous_gradients": true, | |
| "reduce_bucket_size": "auto", | |
| "stage3_prefetch_bucket_size": "auto", | |
| "stage3_param_persistence_threshold": "auto", | |
| "sub_group_size": 1e9, | |
| "stage3_max_live_parameters": 1e9, | |
| "stage3_max_reuse_distance": 1e9, | |
| "stage3_gather_16bit_weights_on_model_save": true | |
| }, | |
| "gradient_accumulation_steps": 4, | |
| "gradient_clipping": "auto", | |
| "steps_per_print": 2000, | |
| "train_batch_size": "auto", | |
| "train_micro_batch_size_per_gpu": "auto", | |
| "wall_clock_breakdown": false | |
| } | |