github
/
minimind-v
mirror of https://github.com/jingyaogong/minimind-v.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[update] num_workers=2

pull/120/head^2
jingyaogong 2026-05-12 09:54:46 +08:00
parent ee18831dce
commit 2b94dcb3d0
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
trainer/train_pretrain_vlm.py
View File

@ -95,7 +95,7 @@ if __name__ == "__main__":
parser.add_argument("--learning_rate", type=float, default=4e-4, help="初始学习率")
parser.add_argument("--device", type=str, default="cuda:0" if torch.cuda.is_available() else "cpu", help="训练设备")
parser.add_argument("--dtype", type=str, default="bfloat16", help="混合精度类型")
parser.add_argument("--num_workers", type=int, default=8, help="数据加载线程数")
parser.add_argument("--num_workers", type=int, default=2, help="数据加载线程数")
parser.add_argument("--accumulation_steps", type=int, default=1, help="梯度累积步数")
parser.add_argument("--grad_clip", type=float, default=1.0, help="梯度裁剪阈值")
parser.add_argument("--log_interval", type=int, default=100, help="日志打印间隔")

2
trainer/train_sft_vlm.py
View File

@ -95,7 +95,7 @@ if __name__ == "__main__":
parser.add_argument("--learning_rate", type=float, default=5e-6, help="初始学习率")
parser.add_argument("--device", type=str, default="cuda:0" if torch.cuda.is_available() else "cpu", help="训练设备")
parser.add_argument("--dtype", type=str, default="bfloat16", help="混合精度类型")
parser.add_argument("--num_workers", type=int, default=8, help="数据加载线程数")
parser.add_argument("--num_workers", type=int, default=2, help="数据加载线程数")
parser.add_argument("--accumulation_steps", type=int, default=1, help="梯度累积步数")
parser.add_argument("--grad_clip", type=float, default=1.0, help="梯度裁剪阈值")
parser.add_argument("--log_interval", type=int, default=100, help="日志打印间隔")