17000 into 30 dimensions is quite a bit of space - eg, if each dimension is only 2 values, 30 dimensions gives you a billion unuique locations (2^30)     See Less

Andrey thank you for this great series of lectures. you are a great Educator! 100% GOLD Material to Learn     See Less

I'm confused at 56:17 why care must be taking with how many times you can use the test dataset as the model will lear     See More Is this because there is no equivalent of 'torch.no_grad()' for LLMs - will the LLM always update the weights when given data?    See Less

i love u     See Less

at 21:24 I think it's supposed to be first letter not first word. It's first word in the paper but first letter i     See More ple    See Less

Love all the tips and explanations on pytorch, training efficiency, and educational purposed errors. I was writing both code and notes and rewatching and enjoyed it and felt having a fruitfu     See More r finished. It's like I was learning with a kind and insightful mentor sitting next to me. Thanks so much Andrej.    See Less

It is an absolute honor to learn from the very best. Thanks Andrej.     See Less

thank you andrej     See Less

Can't thank you enough. It's such a satisfying feeling to understand the logic under the ML models clearly. Thank you!     See Less

This is amazing. Using just a little bit of what I was able to learn from part 3, namely the Kaiming init, and turning back on the learning rate decay, I was able to achieve 2.03 and 2.04 in     See More nd validation with a 1.89 in my training loss with just 300k iterations and 23k parameters. I set my block size to 4 and my embeddings to 12 and increased my hidden layer to 300 while decaying my learning rate exponent from -1 to -3 linear space over the 300k steps. All that without even using batch normalization yet. After applying batch norm, was able to get these down to 1.99 and 1.98 with training loss in the 1.7s after a little more tweaking. Really good content in this lecture, it really has me feeling like a chef in the kitchen almost, cooking up a model with a few turns of the knobs...This sounds like a game or a problem that can be solved with an AI trained on turning knobs.    See Less