From f60ab499ebd9a1347650e3531e766eae7106e054 Mon Sep 17 00:00:00 2001
From: thinhlpg <thinhlpg@gmail.com>
Date: Mon, 24 Mar 2025 06:02:13 +0700
Subject: [PATCH] chore: update worklog

---
 docs/00_worklog.md | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/docs/00_worklog.md b/docs/00_worklog.md
index 0e8a3cc..3b15ca6 100644
--- a/docs/00_worklog.md
+++ b/docs/00_worklog.md
@@ -2,6 +2,7 @@
 
 ## Backlog
 
+- [ ] @thinhlpg transfers the project to @bachvudinh
 - [ ] Modify `generate_dataset.py` (**ONLY AFTER** the simple training and benchmark works):
     - [ ] As a data dataset maker, I want to change from LLama 3.1 8B to API call, like claude, gemini or openai. Originally they use 3.1 8B for `Self-Bootstrapping` demonstration, but the dataset quality is low, for sure.
     - [ ] Experimenting with different chunking strategies
@@ -19,17 +20,17 @@
 
 ## 250324
 
-- [ ] @thinhlpg transfers the project to @bachvudinh
-
-## 250323
-
-- [ ] Train the model
-- [ ] Make the dataset
-- [ ] Upload datasets to HF Hub
+- [ ] Train the model v0
+- [ ] Make the dataset v0
+- [ ] Upload dataset v0 to HF Hub
       - Initial dataset from AutoDidact
       - Paraphrased sdataset
 - [ ] Make a simple gradio demo app
 
+## 250323
+
+- brain.exe and back.exe refused to work 😭
+
 ## 250322
 
 - [x] Moving all the scattered and disorganized stuffs that've been working on for the past week into this repo.