---
library_name: transformers
license: apache-2.0
datasets:
- NickyNicky/oasst2_clusters
- OpenAssistant/oasst2
model:
- google/gemma-1.1-2b-it
language:
- bg
- ca
- cs
- da
- de
- en
- es
- fr
- hr
- hu
- it
- nl
- pl
- pt
- ro
- ru
- sl
- sr
- sv
- uk

widget:
- text: |
    <bos><start_of_turn>system
    You are a helpful AI assistant.<end_of_turn>
    <start_of_turn>user
    {question}<end_of_turn>
    <start_of_turn>model

---


<p align="center">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/641b435ba5f876fe30c5ae0a/YXqUXFjX8uIJT-mdOnM1h.png" alt="" style="width: 95%; max-height: 750px;">
</p>

## Metrics.

<p align="center">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/641b435ba5f876fe30c5ae0a/g7YbkdYm6G4dUdWGRa0nG.png" alt="" style="width: 95%; max-height: 750px;">
</p>

<p align="center">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/641b435ba5f876fe30c5ae0a/CN4dNjrvbvwOZqjrCWT7_.png" alt="" style="width: 95%; max-height: 750px;">
</p>


```
TrainOutput(global_step=1390,
  training_loss=1.0502444919064748,
  metrics={
    'train_runtime': 22700.8355,
    'train_samples_per_second': 2.449,
    'train_steps_per_second': 0.061,
    'total_flos': 1.2395973405265306e+18,
    'train_loss': 1.0502444919064748,
    'epoch': 4.05
})

```

## Take dataset.
```
OpenAssistant/oasst2
```

## Dataset format gemma fine tune.
```
NickyNicky/oasst2_clusters
```

## colab examples.
```
https://colab.research.google.com/drive/16qS7NMSu20LzcwvYCrBGVI7rd9Hr-vpN?usp=sharing
```