| { | |
| "train_micro_batch_size_per_gpu": "auto", | |
| "train_batch_size": "auto", | |
| "gradient_accumulation_steps": "auto", | |
| "optimizer": { | |
| "type": "ZeroOneAdam", | |
| "params": { | |
| "lr": "auto", | |
| "weight_decay": "auto", | |
| "bias_correction": false, | |
| "var_freeze_step": 1000, | |
| "var_update_scaler": 16, | |
| "local_step_scaler": 1000, | |
| "local_step_clipper": 16, | |
| "cuda_aware": true, | |
| "comm_backend_name": "nccl" | |
| } | |
| }, | |
| "scheduler": { | |
| "type": "WarmupLR", | |
| "params": { | |
| "warmup_min_lr": 0, | |
| "warmup_max_lr": "auto", | |
| "warmup_num_steps": "auto" | |
| } | |
| }, | |
| "fp16": { | |
| "enabled": true | |
| }, | |
| "zero_optimization": { | |
| "stage": 0 | |
| } | |
| } | |