Using AWS SageMaker to train a model to generate text (part 3): What I learned about Python AWS Lambdas this week

This is a follow-on from my investigation on how to use AWS SageMaker as an AWS replacement to my current approach to generate text from a Machine Learning model. Up until this point I’ve been running torch-rnn on a server locally. You can follow part 1 and part 2 of my progress so far.

In summary, here’s what I learned this week:

  • Some Python modules are OS platform specific. That means, if you install a module on MacOS, you can’t zip it up as a dependency in a .zip deployment for a Lambda which runs on Linux, as it won’t be OS compatible
  • The maximum size for an AWS Lambda deployment is 50MB. Zipping up what I’ve built so far (only a minimal script but relying on a number of modules) I’ve got a 500MB zip file. Clearly that’s too large to deploy as a Lambda
  • Following some suggestions here,  there are Python frameworks (such as Zappa) to help build Python based AWS Lambdas and address some of the issues with modules and deployment. Clearly I’ve got some learning here to get his to work 🙂

Using AWS SageMaker to train a model to generate text (part 2)

This is part 2 following on from my previous post, investigating how to take advantage of AWS SageMaker to train a model and use it to generate text for my Twitter bot, @kevinhookebot.

From the AWS SageMaker docs, in order to get the data in a supported format to use to train a model, it mentions “A script to convert data from tokenized text files to the protobuf format is included in the seq2seq example notebook”

Ok, so from the SageMaker Notebook I created in part 1, let’s start it up via the AWS console:

Once started, clicking the ‘Open’ link to open the Jupyter notebook, we can open the seq2seq example which is in the ‘SageMaker Examples’ section:

From looking at the steps in this example Notebook, it’s clear that this character2character algorithm is more focused on translating text from source to destination (such as translating text in one language to another, as shown in this example notebook).

Ok, so this isn’t what I was looking for so let’s change gears. My main objective is to be able to train a new model using AWS SageMaker service, and generate text from it. From what I understand so far, you have two options how you can use SageMaker. You can either use the AWS Console for SageMaker to create Training Jobs using the built in algorithms, or you can use a Juypter notebook and define the steps yourself using Python to retrieve your data source, prepare the data, and train a model.

At this point the easiest thing might be to look for another Recurrent Neural Net (RNN) to generate characters to replace the Lua Torch char-rnn approach I was previously running locally on an Ubuntu server. Doing some searching I found char-rnn.pytorch.

This is my first experience setting up a Juypter notebook, so at this point I’ve no idea if what I’ve doing is the right approach, but I’ve got something working.

On the righthand side of the notetbook I pressed the New button and selected a Python PyTorch notebook:

Next I added a step to clone the char-rnn.pytorch repo into my notebook:

Next I added a step to use the aws cli to copy my data file for training the model into my notebook:

Next, adding the config options to train a model using char-rnn.pytorch, I added a step to run the training, but it gave an error about some Python modules missing:

Adding an extra step to use pip to install the required modules:

The default number of epochs is 2,000 which takes a while to run, so decreasing this to something smaller with –n_epochs 100 we get a successful run, and calling the generate script, we have content!

I trained with an incredibly small file to get started, just 100 lines of text, for a very short time. So next steps I’m going to look at:

  • training with the full WordPress export of all my posts for a longer training time
  • training with a cleaned up export (remove URL links and other HTML markup)
  • automate the text generation from the model to feed my AWS Lambda based bot

I’ll share another update on these enhancements in my next upcoming post.


Using AWS Sagemaker to train a model to generate text (part 1)

If you’ve followed any of my recent posts, you’ll know I have been using RNN models to generate text from a model trained with my previous tweets, and the text from all of my previous blog posts, and feeding this into a Twitter bot: @kevinhookebot

The trouble I have right now is the scripts and generate models are running using Lua, and although I could install this to an EC2 instance, I don’t want to pay for an EC2 instance being up 100% of the time. Currently when I generate a new batch of text for my Twitter bot, I startup a local server running the scripts and the model, generate new text, and then stage it to DynamoDB to get picked up by the bot when it’s scheduled to next run. With the AWS provided Machine Learning services, there has to be something out of the box I can use on AWS that would automate these steps.

Let’s take a look at using AWS SageMaker.

First I created a SageMaker notebook with a new role, to access S3 buckets with ‘sagemaker’ in the name.

Then I created an S3 bucket – sagemaker-kevinhooke-ml – and uploaded a copy of my data file (all my previous posts from this blog, concatenated into a single file).

Next I created a new Training Job.

You need to pick an algorithm for the training and there’s a selection of provided algorithms for different purposes. To generate new text ‘in the style of’ the text that I’m going to training the model with, the ‘Sequence2Sequence’ looks like it does what I need.

On completing the Training Job, I got this error:

Ok, so let’s change the instance type. I picked the smallest of the instances before:

And it looks like you can’t change the type on the Notebook. So let’s create a new Notebook. Looking at the instance types, the ones with GPU support are on the large side, so let’s pick the smallest of the options and try again.

At this point I realized the instance type it’s talking about is for the training job not the notebook, and it’s specified here:

So let’s pick one of the GPU types and try again.

First training job is running:

Next error:

Hmm, off to do some reading in the docs to see what’s needed to run this training job. The docs here describe what’s needed for the sequence2sequence algorithm and I’m clearly missing some steps, so taking a pause here and will come back with an update later.