| { | |
| "train_batch_size": 8, | |
| "gradient_accumulation_steps": 4, | |
| "gradient_clipping": 1.0, | |
| "fp16": { | |
| "enabled": true, | |
| "loss_scale": 0, | |
| "loss_scale_window": 1000, | |
| "initial_scale_power": 16, | |
| "hysteresis": 2, | |
| "min_loss_scale": 1 | |
| }, | |
| "zero_optimization": { | |
| "stage": 2, | |
| "allgather_partitions": true, | |
| "allgather_bucket_size": 5e8, | |
| "overlap_comm": true, | |
| "reduce_scatter": true, | |
| "reduce_bucket_size": 5e8, | |
| "contiguous_gradients": true, | |
| "cpu_offload": false | |
| }, | |
| "optimizer": { | |
| "type": "AdamW", | |
| "params": { | |
| "lr": 3e-4, | |
| "betas": [0.9, 0.95], | |
| "eps": 1e-8, | |
| "weight_decay": 0.1 | |
| } | |
| }, | |
| "scheduler": { | |
| "type": "WarmupDecayLR", | |
| "params": { | |
| "warmup_min_lr": 0, | |
| "warmup_max_lr": 3e-4, | |
| "warmup_num_steps": 2000, | |
| "total_num_steps": 100000 | |
| } | |
| }, | |
| "steps_per_print": 100, | |
| "wall_clock_breakdown": true, | |
| "dump_state": false | |
| } | |