| { | |
| "train_batch_size": "auto", | |
| "train_micro_batch_size_per_gpu": "auto", | |
| "gradient_accumulation_steps": "auto", | |
| "gradient_clipping": "auto", | |
| "zero_allow_untested_optimizer": true, | |
| "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": 2, | |
| "allgather_partitions": true, | |
| "allgather_bucket_size": 500000000.0, | |
| "overlap_comm": true, | |
| "reduce_scatter": true, | |
| "reduce_bucket_size": 500000000.0, | |
| "contiguous_gradients": true, | |
| "round_robin_gradients": true | |
| } | |
| } |