X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=README.txt;h=d4740f386def252fb3b3229bcb97ba95b40fb3dc;hb=f44ab6863f93ae348e66ffbf52251d96d3b5453c;hp=d4cb93d405a81f0d3d3b6118ab06860f2953cb68;hpb=2175a87ad4304a97c63ac9cca6224d0c0b74c64e;p=picoclvr.git diff --git a/README.txt b/README.txt index d4cb93d..d4740f3 100644 --- a/README.txt +++ b/README.txt @@ -1,10 +1,12 @@ +====================================================================== For the stack experiment: ./main.py --task=stack Takes ~1h10min on a 4090. +====================================================================== For the arithmetic expressions experiments # 38M parameters / 250k samples @@ -15,3 +17,7 @@ For the arithmetic expressions experiments learning rate schedule is obviously terrible ./main.py --task=expr --nb_blocks=48 --dim_model=1024 --nb_train_samples=2500000 --result_dir=results_expr_48b_d1024_2.5M +====================================================================== +25.07.2023 + +./main.py --task=sandbox --nb_train_samples=10000 --nb_test_samples=1000 --nb_blocks=4 --nb_heads=1 --nb_epochs=20