From 0e082f25ef818eaeb5c8b6371a99559210e85afe Mon Sep 17 00:00:00 2001 From: Francesco Pham Date: Fri, 12 Mar 2021 16:01:09 +0100 Subject: [PATCH] remove redundant --skip-generation True (#3513) --- projects/recipes/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/projects/recipes/README.md b/projects/recipes/README.md index 20822e34be5..2b2010d5d0a 100644 --- a/projects/recipes/README.md +++ b/projects/recipes/README.md @@ -58,7 +58,7 @@ Commands for fine tuning the models on the [Blended Skill Talk](http://parl.ai/p **90M**. You may fine-tune your own 90M parameter model with: ``` -parlai train_model -t blended_skill_talk,wizard_of_wikipedia,convai2:normalized -m transformer/generator --multitask-weights 1,3,3,3 --init-model zoo:tutorial_transformer_generator/model --dict-file zoo:tutorial_transformer_generator/model.dict --embedding-size 512 --n-layers 8 --ffn-size 2048 --dropout 0.1 --n-heads 16 --learn-positional-embeddings True --n-positions 512 --variant xlm --activation gelu --skip-generation True --fp16 True --text-truncate 512 --label-truncate 128 --dict-tokenizer bpe --dict-lower True -lr 1e-06 --optimizer adamax --lr-scheduler reduceonplateau --gradient-clip 0.1 -veps 0.25 --betas 0.9,0.999 --update-freq 1 --attention-dropout 0.0 --relu-dropout 0.0 --skip-generation True -vp 15 -stim 60 -vme 20000 -bs 16 -vmt ppl -vmm min --save-after-valid True --model-file /tmp/test_train_90M +parlai train_model -t blended_skill_talk,wizard_of_wikipedia,convai2:normalized -m transformer/generator --multitask-weights 1,3,3,3 --init-model zoo:tutorial_transformer_generator/model --dict-file zoo:tutorial_transformer_generator/model.dict --embedding-size 512 --n-layers 8 --ffn-size 2048 --dropout 0.1 --n-heads 16 --learn-positional-embeddings True --n-positions 512 --variant xlm --activation gelu --fp16 True --text-truncate 512 --label-truncate 128 --dict-tokenizer bpe --dict-lower True -lr 1e-06 --optimizer adamax --lr-scheduler reduceonplateau --gradient-clip 0.1 -veps 0.25 --betas 0.9,0.999 --update-freq 1 --attention-dropout 0.0 --relu-dropout 0.0 --skip-generation True -vp 15 -stim 60 -vme 20000 -bs 16 -vmt ppl -vmm min --save-after-valid True --model-file /tmp/test_train_90M ``` **2.7B**. You may fine-tune your own 2.7B parameter model with: