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

[feat] update sft

pull/107/head
jingyaogong 2025-10-26 21:24:19 +08:00
parent c2bfead000
commit 2ce5c31170
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
trainer/train_sft_vlm.py
View File

@ -95,8 +95,8 @@ if __name__ == "__main__":
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=8, 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("--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("--grad_clip", type=float, default=1.0, help="梯度裁剪阈值")
parser.add_argument("--log_interval", type=int, default=10, help="日志打印间隔") parser.add_argument("--log_interval", type=int, default=100, help="日志打印间隔")
parser.add_argument("--save_interval", type=int, default=10, help="模型保存间隔") parser.add_argument("--save_interval", type=int, default=100, help="模型保存间隔")
parser.add_argument('--hidden_size', default=512, type=int, help="隐藏层维度") parser.add_argument('--hidden_size', default=512, type=int, help="隐藏层维度")
parser.add_argument('--num_hidden_layers', default=8, type=int, help="隐藏层数量") parser.add_argument('--num_hidden_layers', default=8, type=int, help="隐藏层数量")
parser.add_argument('--max_seq_len', default=1536, type=int, help="训练的最大截断长度") parser.add_argument('--max_seq_len', default=1536, type=int, help="训练的最大截断长度")