[orena]

How many epochs did you train with ? 100k hours is not a lot for an LLM, Feels like bitter lesson

[vvolhejn]

I train for 1M steps (batch size 64, block size 2048), which is enough for the model to more-or-less converge.

It's also a tiny model for LLM standards, with 150M parameters. The goal wasn't really to reach state of the art but to show how the performance of a single language model architecture can be vastly different when you just change the tokenizer.

[singularfutur]

To get around state of the art, how many parameters would be needed with your approach?