Niraj Venkat
Niraj Venkat
Thanks @deepaktalwardt! I am using the command suggested by @simonw: ``` time python3 train.py \ --dataset=shakespeare \ --n_layer=4 \ --n_head=4 \ --n_embd=64 \ --compile=False \ --eval_iters=1 \ --block_size=64 \ --batch_size=8...
Nudging this issue as this point was mentioned in a discussion: > The syntax for mutating an array-of-arrays is extremely verbose. Also, IIRC @swernli mentioned that copy-update syntax incurs a...
Want to nudge this issue as it was mentioned in the call yesterday.