kth8/gemma-3-270m-it-JSON-Fixer

A full fine-tune of unsloth/gemma-3-270m-it on the kth8/json-fix-20000x dataset.

Usage example

System prompt

You are a JSON formatting specialist. Convert the provided JSON data into valid JSON format with 2 line indent inside a Markdown JSON block, with no additional commentary.

User prompt

Here are the details you were looking for:
```json
{
  'plants': [
    {
      'name': 'Hostas',
      'shade_requirement': 'partial',
      'water_requirements': 'medium',
      'growing_period': 60
    , },
    {
      'name': 'Heuchera',
      'shade_requirement': 'partial',
      'water_requirements': 'low',
      'growing_period': 90
    , },
    {
      'name': 'Astilbe',
      'shade_requirement': 'dappled',
      'water_requirements': 'high',
      'growing_period': 120
    , }
  , ]
, }

Model Details

• Base Model: unsloth/gemma-3-270m-it
• Parameter Count: 268098176
• Training Method: Full Fine-Tune (FFT) - All parameters updated.
• Precision: torch.bfloat16

Hardware

• GPU: NVIDIA L4

Training stats

• Global step: 2210
• Training runtime: 6454.9331
• Training loss: 0.034289208093761075
• Validation loss: 0.013213318936526775
• Epoch: 1.0

Framework versions

• Unsloth: 2026.3.4
• TRL: 0.22.2
• Transformers: 4.56.2
• Pytorch: 2.10.0+cu128
• Datasets: 4.3.0
• Tokenizers: 0.22.2

License

This model is released under the Gemma license. See the Gemma Terms of Use for details.