-
-
Save moyix/3182dc46afd15e75a7b34cf6bf574fbd to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
fairseq-train \ | |
--valid-subset valid --train-subset train \ | |
--lr 0.01 --clip-norm 0.1 --dropout 0.0 --max-tokens 8192 --arch transformer \ | |
--max-source-positions 4096 --max-target-positions 2048 \ | |
--encoder-embed-dim 1024 --decoder-embed-dim 1024 \ | |
--encoder-attention-heads 16 --decoder-attention-heads 16 \ | |
--amp --model-parallel-size 2 --lr-scheduler cosine \ | |
--validate-interval-updates 25000 --max-update 1000000 \ | |
--save-dir checkpoints --optimizer adam \ | |
--tensorboard-logdir tlogz ghdis_dbg | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment