A fine-tune of unsloth/gemma-3-270m-it on the 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 and Prohibited Use Policy regarding the use of Gemma-generated content.
- Downloads last month
- 284