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 3, having gained enough experience with the 8B models, our team finally challenged the ultimate kings of performance: fine-tuning massive 70B (70 billion parameters) models. We attempted to train both Llama 3.3 70B and DeepSeek-R1 70B, but as expected, we hit a massive hardware resource wall.
April 14 is the day we resumed the synthetic data (v5) generation work, which had been temporarily halted since the bill bomb incident. We increased the API billing limit (lifted the restriction) and ran the system, but once again, it didn't go smoothly.
On April 9, using the Colab notebook we ambitiously completed yesterday, we finally attempted the first training (fine-tuning) of our artificial intelligence model (Llama 3.1). However, reality was not that easy, and we had to face numerous errors. It was also a tough day as we had to simultaneously create the presentation materials for the 6th week of the Capstone Design project.