删除多余的图像文件并调整训练脚本中的批量大小

2025-06-27 01:00:33 +08:00 · 2025-06-27 01:00:33 +08:00 · feba9a930e
parent 561979c7e3
commit feba9a930e
20 changed files with 1 additions and 1 deletions
--- a/images/1-wiki.png
+++ b/images/1-wiki.png
--- a/images/2-wiki.png
+++ b/images/2-wiki.png
--- a/images/3-wiki.png
+++ b/images/3-wiki.png
--- a/images/4-wiki.png
+++ b/images/4-wiki.png
--- a/images/5-wiki.png
+++ b/images/5-wiki.png
--- a/images/LLM-structure-moe.png
+++ b/images/LLM-structure-moe.png
--- a/images/LLM-structure.png
+++ b/images/LLM-structure.png
--- a/images/and_huggingface.png
+++ b/images/and_huggingface.png
--- a/images/and_modelscope.png
+++ b/images/and_modelscope.png
--- a/images/compare_radar.png
+++ b/images/compare_radar.png
--- a/images/dataset.jpg
+++ b/images/dataset.jpg
--- a/images/gpt3_config.png
+++ b/images/gpt3_config.png
--- a/images/logo.png
+++ b/images/logo.png
--- a/images/logo2.png
+++ b/images/logo2.png
--- a/images/minimind2.gif
+++ b/images/minimind2.gif
--- a/images/pre_512_loss.png
+++ b/images/pre_512_loss.png
--- a/images/pre_768_loss.png
+++ b/images/pre_768_loss.png
--- a/images/sft_512_loss.png
+++ b/images/sft_512_loss.png
--- a/images/sft_768_loss.png
+++ b/images/sft_768_loss.png
--- a/trainer/train_pretrain.py
+++ b/trainer/train_pretrain.py
@ -119,7 +119,7 @@ if __name__ == "__main__":
    parser.add_argument("--out_dir", type=str, default="../out")
    # 若要以最快速度实现zero则epochs设置为1轮；否则应当利用有限的数据训练2~6个epochs。
    parser.add_argument("--epochs", type=int, default=1)
-    parser.add_argument("--batch_size", type=int, default=32)
+    parser.add_argument("--batch_size", type=int, default=16)
    parser.add_argument("--learning_rate", type=float, default=5e-4)
    parser.add_argument("--device", type=str, default="cuda:0" if torch.cuda.is_available() else "cpu")
    parser.add_argument("--dtype", type=str, default="bfloat16")