roneneldan

/

TinyStories-1M

like 61

Hi @roneneldan . Firstly, would like to say thank you for this model. It's truly cool for the people who are interested in trying to get small models to do interesting things.

However, I would really appreciate knowing exactly how many epochs through the dataset the 1M parameter model was trained for? From my understanding the 33M model was trained for 20 epochs right? Any more training details you could give us would be very much appreciated...

Thank you very much!