| { | |
| "bf16": { | |
| "enabled": true | |
| }, | |
| "optimizer": { | |
| "type": "AdamW", | |
| "params": { | |
| "lr": "auto", | |
| "weight_decay": "auto", | |
| "torch_adam": true, | |
| "adam_w_mode": true | |
| } | |
| }, | |
| "scheduler": { | |
| "type": "WarmupCosineLR", | |
| "params": { | |
| "warmup_min_ratio": 0.0, | |
| "cos_min_ratio": 0.0001, | |
| "warmup_num_steps": 250, | |
| "total_num_steps": "auto" | |
| } | |
| }, | |
| "zero_optimization": { | |
| "stage": 2, | |
| "allgather_partitions": true, | |
| "allgather_bucket_size": 2e8, | |
| "overlap_comm": true, | |
| "reduce_scatter": true, | |
| "reduce_bucket_size": 5e8, | |
| "contiguous_gradients": true | |
| }, | |
| "gradient_accumulation_steps": 1, | |
| "train_micro_batch_size_per_gpu": 1, | |
| "train_batch_size": "auto", | |
| "gradient_clipping": "auto", | |
| "steps_per_print": 2000, | |
| "wall_clock_breakdown": false | |
| } |