Valohai CLI installation and Valohai project setup

Ensure you have opened an account on https://valohai.com, see https://app.valohai.com/accounts/signup/
Install Valohai CLI - it’s easy to install and get started with the CLI tool, see Command-line Usage.

After install the Valohai CLI, we will have to do the below:

clone this repo

  $ git clone https://github.com:valohai/dl4j-nlp-cuda-example.git
  $ cd dl4j-nlp-cuda-example

create a new Valohai project (requires an account on https://valohai.com)

$ vh project create

  (Resolved create to project create.)
  Project name: dl4j-nlp-cuda-example
  😄  Success! Project dl4j-nlp-cuda-example created.

Go back to your account on https://valohai.com to find this project present:

$ vh project open

Once in your Valohai project, add this git repo (https://github.com/neomatrix369/dl4j-nlp-cuda-example) to the project, under the Repository tab in the Settings page (https://app.valohai.com/p/[your-user-id]/dl4j-nlp-cuda-example/settings/repository/).

viewing Valohai cloud environments (optional)

$ vh env

shortlisting GPU based environments (optional)

$ vh env -price --queue --gpu

List all environments that support GPUs with their price tag and their queue status.

getting familiar with the CLI tool

$ vh lint
$ vh exec list
$ vh exec run --help

watch an execution in process using it's counter number

$ vh watch 1

show all the outputs (end-results) of an execution

$ vh outputs 1

and download the one's of your choice

$ vh outputs --download . --filter *.logs 1

run a step but override one of the step variables

$ vh exec run train-gpu-linux \
     --gpu-linux-uberjar=datum://016dff00-2095-4df7-5d9e-02cb7cd009bb [--adhoc]

### Overrides the gpu-linux-uberjar variable in the train-gpu-linux step

stop a running or queue execution

$ vh stop 2

Return to main README.md