d97e47c408
day01: 学习笔记 + 调试配置 + batch_size 默认值调整
...
- learning/day01/04_qa_notes.md: 第一天实操问答笔记（环境搭建、虚拟环境、
数据流与打点、数据清洗流水线、nvidia-smi 解读、batch/LR 缩放）
- .vscode/launch.json: VSCode 调试配置（train_pretrain + 当前文件）
- train_pretrain.py: batch_size 默认值 32 -> 128
- .gitignore: 忽略 checkpoints/ 和 dataset/*.jsonl 大文件
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-02 00:51:12 -04:00
b23a05868d
Add Day 1 learning notes and model Chinese comments
...
- learning/day01: prereading, deep dive, and exam notes
- model_minimind.py: added comprehensive Chinese comments for study
- .gitignore: minor update
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-06-01 21:33:23 -04:00
101d7df2da
[update] minimind-3
2026-03-25 23:57:45 +08:00
ce693f8e7f
[fix] git track
2025-10-21 23:09:00 +08:00
b60fd11f85
update track
2025-02-10 00:32:33 +08:00
06a66d88c9
添加了wandb
2024-09-23 20:11:45 +08:00
0fa4d17d26
更新了忽视列表
2024-09-23 18:36:04 +08:00
QiaohuiGao
jingyaogong
gongjy
Yu Chengzhang