X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=README.txt;h=d4cb93d405a81f0d3d3b6118ab06860f2953cb68;hb=2175a87ad4304a97c63ac9cca6224d0c0b74c64e;hp=bf6180a1c5b3edbacc5da38493528b921bdcd871;hpb=45f841397dd6f8fb163f2c5b0793cdc250072c73;p=picoclvr.git diff --git a/README.txt b/README.txt index bf6180a..d4cb93d 100644 --- a/README.txt +++ b/README.txt @@ -11,6 +11,7 @@ For the arithmetic expressions experiments ./main.py --task=expr -# 352M parameters / 2.5M samples +# 352M parameters / 2.5M samples, reaches 99.80% after 12 epochs, the + learning rate schedule is obviously terrible -./main.py --task=expr --nb_blocks=48 --result_dir=results_expr_48b_d1024_2.5M --dim_model=1024 --nb_train_samples=2500000 --learning_rate_schedule="1:2e-5,3:4e-6" +./main.py --task=expr --nb_blocks=48 --dim_model=1024 --nb_train_samples=2500000 --result_dir=results_expr_48b_d1024_2.5M