| { | |
| "bf16": { | |
| "enabled": "auto" | |
| }, | |
| "optimizer": { | |
| "type": "AdamW", | |
| "params": { | |
| "lr": "auto", | |
| "betas": "auto", | |
| "eps": "auto", | |
| "weight_decay": "auto", | |
| "torch_adam": true, | |
| "adam_w_mode": true | |
| } | |
| }, | |
| "scheduler": { | |
| "type": "WarmupDecayLR", | |
| "params": { | |
| "warmup_min_lr": "auto", | |
| "warmup_max_lr": "auto", | |
| "warmup_num_steps": "auto", | |
| "total_num_steps": "auto" | |
| } | |
| }, | |
| "zero_optimization": { | |
| "stage": 2, | |
| "allgather_partitions": true, | |
| "allgather_bucket_size": 200000000.0, | |
| "overlap_comm": true, | |
| "reduce_scatter": true, | |
| "reduce_bucket_size": "auto", | |
| "contiguous_gradients": true | |
| }, | |
| "gradient_accumulation_steps": "auto", | |
| "gradient_clipping": "auto", | |
| "train_batch_size": "auto", | |
| "train_micro_batch_size_per_gpu": "auto", | |
| "steps_per_print": 2000, | |
| "wall_clock_breakdown": false | |
| } | |