README.md

---
library_name: transformers
license: apache-2.0
datasets:
- gretelai/synthetic_text_to_sql
- NickyNicky/synthetic_text_to_sql_format_chatML_gemma
language:
- en

widget:
- text: |
    <bos><start_of_turn>system
    You are a helpful AI assistant.
    you are a sql expert who responds in json format.<end_of_turn>
    <start_of_turn>user
    ## prompt:
    What is the total gold production by 'Site B' in the 'production' table?
    
    ## sql context:
    CREATE TABLE production (id INT, site VARCHAR(50), year INT, gold_production INT, silver_production INT);<end_of_turn>
    <start_of_turn>model
---


<p align="center">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/641b435ba5f876fe30c5ae0a/Fy2GvAheKCnd3Jj3TbrPG.png" alt="" style="width: 95%; max-height: 750px;">
</p>

## Metrics.
```
TrainOutput(global_step=2509,
  training_loss=0.2509715025906736,
  metrics={'train_runtime': 22783.0743,
    'train_samples_per_second': 8.81,
    'train_steps_per_second': 0.11,
    'total_flos': 1.820581902144553e+18,
    'train_loss': 0.2509715025906736,
    'epoch': 2.01
    }
)
```

## Take dataset.
```
gretelai/synthetic_text_to_sql
```

## Dataset format gemma fine tune.
```
NickyNicky/synthetic_text_to_sql_format_chatML_gemma
```

## colab examples and Gradio.
```
https://colab.research.google.com/drive/1-0PsRAqTum2UuvsXb9JtXxLISIUWd8zv?usp=sharing
```

## gradio colab.
<p align="center">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/641b435ba5f876fe30c5ae0a/X2rf3Z7jJ2WUI7LANw4IH.png" alt="" style="width: 95%; max-height: 750px;">
</p>

## $ train
<p align="center">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/641b435ba5f876fe30c5ae0a/tLhUyV2uW44-Cf0vwXFbd.png" alt="" style="width: 95%; max-height: 750px;">
</p>