| { | |
| "bf16": { | |
| "enabled": true | |
| }, | |
| "train_micro_batch_size_per_gpu": 1, | |
| "train_batch_size": "auto", | |
| "gradient_accumulation_steps": 1, | |
| "gradient_clipping": 0.05, | |
| "zero_optimization": { | |
| "stage": 2, | |
| "offload_optimizer": { | |
| "device": "none" | |
| }, | |
| "overlap_comm": true, | |
| "contiguous_gradients": true, | |
| "sub_group_size": 1e9, | |
| "reduce_bucket_size": 5e8, | |
| "allgather_partitions": true, | |
| "allgather_bucket_size": 2e8, | |
| "reduce_scatter": true | |
| }, | |
| "steps_per_print": 100, | |
| "wall_clock_breakdown": false | |
| } |