From 53ddbbe0b1d734e6e7720920fb05217c642d088a Mon Sep 17 00:00:00 2001 From: Bryan McCann Date: Wed, 27 Jun 2018 13:53:15 -0700 Subject: [PATCH] Update README.md --- README.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 33ed8969..70ce11ec 100644 --- a/README.md +++ b/README.md @@ -37,17 +37,17 @@ nvidia-docker run -it --rm -v `pwd`:/decaNLP/ -u $(id -u):$(id -g) decanlp bash For example, to train a Multitask Question Answering Network (MQAN) on the Stanford Question Answering Dataset (SQuAD): ```bash -nvidia-docker run -it --rm -v `pwd`:/decaNLP/ -u $(id -u):$(id -g) decanlp bash -c "python /decaNLP/train.py --train_tasks squad --gpus DEVICE_ID" +nvidia-docker run -it --rm -v `pwd`:/decaNLP/ -u $(id -u):$(id -g) decanlp bash -c "python /decaNLP/train.py --train_tasks squad --gpu DEVICE_ID" ``` To multitask with the fully joint, round-robin training described in the paper, you can add multiple tasks: ```bash -nvidia-docker run -it --rm -v `pwd`:/decaNLP/ -u $(id -u):$(id -g) decanlp bash -c "python /decaNLP/train.py --train_tasks squad iwslt.en.de --train_iterations 1 --gpus DEVICE_ID" +nvidia-docker run -it --rm -v `pwd`:/decaNLP/ -u $(id -u):$(id -g) decanlp bash -c "python /decaNLP/train.py --train_tasks squad iwslt.en.de --train_iterations 1 --gpu DEVICE_ID" ``` To train on the entire Natural Language Decathlon: ```bash -nvidia-docker run -it --rm -v `pwd`:/decaNLP/ -u $(id -u):$(id -g) decanlp bash -c "python /decaNLP/train.py --train_tasks squad iwslt.en.de cnn_dailymail multinli.in.out sst srl zre woz.en wikisql schema --train_iterations 1 --gpus DEVICE_ID" +nvidia-docker run -it --rm -v `pwd`:/decaNLP/ -u $(id -u):$(id -g) decanlp bash -c "python /decaNLP/train.py --train_tasks squad iwslt.en.de cnn_dailymail multinli.in.out sst srl zre woz.en wikisql schema --train_iterations 1 --gpu DEVICE_ID" ``` You can find a list of commands in `experiments.sh` that correspond to each trained model that we used to report validation results comparing models and training strategies in the paper. @@ -83,12 +83,12 @@ If you are having trouble with the specified port on either machine, run `lsof - You can evaluate a model for a specific task with `EVALUATION_TYPE` as `validation` or `test`: ```bash -nvidia-docker run -it --rm -v `pwd`:/decaNLP/ -u $(id -u):$(id -g) decanlp bash -c "python /decaNLP/predict.py --evaluate EVALUATION_TYPE --path PATH_TO_CHECKPOINT_DIRECTORY --gpus DEVICE_ID --tasks squad" +nvidia-docker run -it --rm -v `pwd`:/decaNLP/ -u $(id -u):$(id -g) decanlp bash -c "python /decaNLP/predict.py --evaluate EVALUATION_TYPE --path PATH_TO_CHECKPOINT_DIRECTORY --gpu DEVICE_ID --tasks squad" ``` or evaluate on the entire decathlon by removing any task specification: ```bash -nvidia-docker run -it --rm -v `pwd`:/decaNLP/ -u $(id -u):$(id -g) decanlp bash -c "python /decaNLP/predict.py --evaluate EVALUATION_TYPE --path PATH_TO_CHECKPOINT_DIRECTORY --gpus DEVICE_ID" +nvidia-docker run -it --rm -v `pwd`:/decaNLP/ -u $(id -u):$(id -g) decanlp bash -c "python /decaNLP/predict.py --evaluate EVALUATION_TYPE --path PATH_TO_CHECKPOINT_DIRECTORY --gpu DEVICE_ID" ``` For test performance, please use the original [SQuAD](https://rajpurkar.github.io/SQuAD-explorer/), [MultiNLI](https://www.nyu.edu/projects/bowman/multinli/), and [WikiSQL](https://github.com/salesforce/WikiSQL) evaluation systems.