From 2ce5c31170609dc68b2387d6bd88d287645bedbb Mon Sep 17 00:00:00 2001 From: jingyaogong Date: Sun, 26 Oct 2025 21:24:19 +0800 Subject: [PATCH] [feat] update sft --- trainer/train_sft_vlm.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/trainer/train_sft_vlm.py b/trainer/train_sft_vlm.py index 98f8d1f..f9f6ac4 100644 --- a/trainer/train_sft_vlm.py +++ b/trainer/train_sft_vlm.py @@ -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("--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=10, 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("--log_interval", type=int, default=100, help="日志打印间隔") + 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('--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")