---
license: gemma
language:
- en
base_model: unsloth/gemma-3-270m-it
datasets:
- marksverdhei/clickbait_title_classification
pipeline_tag: text-generation
library_name: transformers
tags:
- sft
- trl
- unsloth
- google
- gemma
- gemma3
- gemma3_text
---
![logo](https://storage.googleapis.com/gweb-developer-goog-blog-assets/images/gemma-3_2.original.png)
A fine-tune of [unsloth/gemma-3-270m-it](https://huggingface.co/unsloth/gemma-3-270m-it) on the [marksverdhei/clickbait_title_classification](https://huggingface.co/datasets/marksverdhei/clickbait_title_classification) dataset.

## Usage example
**System prompt**
```
You are a clickbait detector. Carefully anaylze the provided text then respond with True or False on whether it could be considered clickbait in JSON format.
```
**User prompt**
```
€8bn bank bailout in Ireland
```
**Assistant response**
```
{"clickbait": false}
```
## Model Details
- Base Model: `unsloth/gemma-3-270m-it`
- Parameter Count: 268,098,176
- Precision: torch.bfloat16

## Hardware
- GPU: NVIDIA A100-SXM4-40GB

## Training Settings
### PEFT
- Rank: 32
- LoRA alpha: 64
- Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
- Gradient checkpointing: unsloth

### SFT
- Epoch: 2
- Batch size: 32
- Gradient Accumulation steps: 1
- Warmup ratio: 0.05
- Learning rate: 0.0002
- Optimizer: adamw_torch_fused
- Learning rate scheduler: cosine

## Training stats
- Date: 2026-03-25T14:04:25.345010
- Peak VRAM usage: 3.354 GB
- Global step: 1900
- Training runtime (seconds): 988.9368
- Average training loss: 0.07525361977750436
- Final validation loss: 0.0014968806644901633

## Framework versions
- Unsloth: 2026.3.11
- TRL: 0.22.2
- Transformers: 4.56.2
- Pytorch: 2.10.0+cu128
- Datasets: 4.8.4
- Tokenizers: 0.22.2

## License
This model is released under the Gemma license. See the [Gemma Terms of Use](https://ai.google.dev/gemma/terms) and [Prohibited Use Policy](https://policies.google.com/terms/generative-ai/use-policy) regarding the use of Gemma-generated content.