configuration-guide

Key Hyperparameters for Fine-Tuning Kronos on Custom Datasets: Configuration Guide

April 10, 2026 shiyu-coder/Kronos ↗

The key hyperparameters for fine-tuning Kronos on custom datasets include lookback_window and predict_window for temporal context, tokenizer_epochs and basemodel_epochs for training duration, and separate learning rates for the VQ-VAE tokenizer and Transformer predictor stages.

Kronos is a two-stage time-series foundation model from the shiyu-coder/Kronos repository that combines a quantized VQ-VAE tokenizer with a Transformer-based predictor. When adapting this architecture to your own CSV files, understanding

Have a question about this repo?

These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:

Share the following with your agent to get started:

curl -s "https://instagit.com/install.md"

Add to your MCP client configuration:

{
  "mcpServers": {
    "instagit": {
      "command": "npx",
      "args": ["-y", "instagit@latest"]
    }
  }
}

Ask your agent:

"Use Instagit MCP to understand how shiyu-coder/Kronos works."

Works with

Claude Codex Cursor VS Code OpenClaw Any MCP Client

Maintain an open-source project? Get it listed too →