As we entered June, the Maeumjigi team completed the major developments of the 1st semester Capstone project and focused entirely on building safety nets and preparing for the final presentation.
In the final week of May (27th-30th), we dedicated our efforts to wrapping up the results of the highly anticipated 4th Fine-Tuning (fine_tuning_4) and solidifying the system's framework.
On May 21st and 22nd, the Maeumjigi Capstone team embarked on massive data generation and preparation for the 4th Fine-Tuning (fine_tuning_4).
Over the two days of May 19th and 20th, the automation of evaluation for the 3rd fine-tuning (fine_tuning_3) and the enhancement of backend/frontend features for building the actual app service proceeded in parallel.
I must correct my previous assumption that "May 13th was the last of Maeumjigi's May development"! On May 17th, a massive wave of backend integration testing and report drafting hit us.
On May 13th, after fixing the hardcoding bugs discovered yesterday, we finally resumed proper inference testing for the 2nd round fine-tuned models.
The 2nd round of fine-tuning (fine_tuning_2) parallel training, which was ambitiously started to correct the LoRA hyperparameter mistake (alpha/rank setup error), finally ended on May 12th!
May 7th was the day we synthesized the fine-tuning results of our 5 models (Llama3.3-70B, DSR1-70B, HCX-Omni-8B, Qwen35-9B, HCX-Text-1.5B) and proceeded with full-scale visualization and local environment setup.
April 5th marks the day we wrapped up the arduous data preprocessing journey (v1~v4) by generating a final report, while simultaneously kicking off the frontend project that will become the face of the Maeumjigi web service.
This is the record of April 1, when we began processing a massive amount of conversation data into a format suitable for training the Llama 3.1 model, which will become the core engine of the Maeumjigi project.
This is the record of March 31, when we conducted the Android build test of the MND Convention reservation alarm app, which was the initial direction of the Maeumjigi project, while simultaneously starting the Llama 3.1 fine-tuning data preprocessing, hinting at a full transition into an AI-based project.
This is the record of March 30, when we officially started developing the 'MND Convention Reservation Alarm' application, which was the initial idea for the Maeumjigi project. Based on the coding rules we set last time, we established a detailed project plan and laid the foundation for Test-Driven Development (TDD).
This is the record of March 26, 2026, the very first day of the grand journey of the "Maeumjigi" capstone project. At that time, instead of the current AI-based "Maeumjigi", the project took its first steps simply as an Android alarm application.