In this section, you'll find information on how to fine-tune Cohere's generative models on AWS Sagemaker.

Sagemaker customers can fine-tune Cohere’s Command R model for their use cases.

Customers can kick off fine-tuning jobs by completing the data preparation and validation steps through the AWS Console. This is useful for customers who don't need or don't want to create a fine-tuning job programmatically via the Cohere AWS SDK, preferring to opt for the ease and simplicity of a web interface instead.

Please see our jupyter notebook for step by step instructions.

Before a fine-tuning job can be started, users must upload a dataset with training and (optionally) evaluation data. The structure of the data for fine-tuning on Amazon Sagemaker should be jsonl. Read more about preparing the training data for chat fine-tuning in our docs: Preparing the Chat Fine-tuning Data.

You'll need your input data to be in jsonl file, in our chat format. Please see Preparing the Chat Fine-tuning Data for more details.

{
  "messages": [
    {
      "role": "System",
      "content": "You are a large language model trained by Cohere."
    },
    {
      "role": "User",
      "content": "Hi! What were Time magazines top 10 cover stories in the last 10 years?"
    },
    {
      "role": "Chatbot",
      "content": "Time magazines top 10 cover stories in the last 10 years were:\\n\\n1. Volodymyr Zelenskyy\\n2. Elon Musk\\n3. Martin Luther King Jr.\\n4. How Earth Survived\\n5. Her Lasting Impact\\n6. Nothing to See Here\\n7. Meltdown\\n8. Deal With It\\n9. The Top of America\\n10. Bitter Pill"
    },
    {
      "role": "User",
      "content": "Who is Volodymyr Zelenskyy?"
    },
    {
      "role": "Chatbot",
      "content": "Volodymyr Zelenskyy is a Ukrainian politician who was elected President of Ukraine in 2019. He previously served as the Minister of Internal Affairs in the government of Prime Minister Volodymyr Groysman."
    },
    {
      "role": "User",
      "content": "Thank you!"
    }
  ]
}

After uploading the dataset, the fine-tuning job can begin.

The Sagemaker fine-tuning job requires:

• an s3 path to the uploaded train dataset
• an optional s3 path to the eval dataset

In this section, we will walk through how you can start training a fine-tuned model for Generate with both the AWS Console and the Cohere AWS SDK.

Creating a fine-tuned model for Generate via the AWS Console consists of a few simple steps, discussed below.

In the Input your data section, you can provide the S3 link to the training dataset file and, optionally, the validation dataset file. Your data should be in jsonl format. You can also set the following hyperparameters to use in training.

We allow you to specify the following hyperparameters for Command-R.

We suggest starting your training without setting any specific parameters. That said, here are some guidelines for resolving certain issues you might encounter:

• If the model outputs are too similar or lack diversity, reduce the epoch number by 1 or 2.
• If the model does not appear to be converging, increase the learning rate.
• If you want to change your batch size, you can use 8, 16 or 24 for Command Light. Command has a batch size of 8.

In the Output data section, enter the Amazon S3 location in which Amazon Sagemaker should save the output of the job. Amazon Sagemaker stores the training loss metrics and validation loss metrics for each epoch in separate files in the location that you specify.

Choose 'Create Fine-tuning job' to begin the job.

You will be able to see your training job overview as illustrated below.

You will receive an email notification when the fine-tuning job has completed training. You can explore the evaluation metrics using the AWS Console. Learn more here.

As your fine-tuning job runs, it will progress through various stages. The following table describes the meaning of the various status messages you might encounter. You can also stop your fine-tuning job while it is in progress.

In addition to the Sagemaker UI, customers are also able to create programatic fine-tuning job using the Cohere AWS SDK. The SDK exposes methods to create fine-tuning jobs, monitor progress, and invoke the fine-tuned model. Please see the following ipython notebooks:

• Command finetuning jupyter notebook

Please see the notebooks above for full import paths, arns, and explanations.