minimind/trainer/ds_config_pretrain.json

38 lines
932 B
JSON

{
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"gradient_accumulation_steps": "auto",
"gradient_clipping": 1.0,
"zero_optimization": {
"stage": 2,
"allgather_partitions": true,
"allgather_bucket_size": 5e6,
"reduce_scatter": true,
"reduce_bucket_size": 5e6,
"overlap_comm": true,
"contiguous_gradients": true
},
"bf16": {
"enabled": true
},
"optimizer": {
"type": "AdamW",
"params": {
"lr": "auto",
"betas": [0.9, 0.95],
"eps": 1e-8,
"weight_decay": 0.1
}
},
"scheduler": {
"type": "WarmupDecayLR",
"params": {
"warmup_min_lr": 0,
"warmup_max_lr": "auto",
"warmup_num_steps": "auto",
"total_num_steps": "auto"
}
},
"wall_clock_breakdown": false
}