---
license: apache-2.0
datasets:
- HuggingFaceFW/fineweb-2
language:
- sv
base_model:
- HuggingFaceTB/SmolLM2-360M-Instruct
pipeline_tag: text-generation
library_name: transformers
---
Work in progress! This model has been trained on about 15% of Swedish Fineweb-2 so far. It is intended for my research and has not been evaluated more broadly yet.

Training parameters:

* Learning rate: 5e-4
* LR scheduler: Cosine
* Warmup ratio: 0.05
* Batch size: 1
* 8 A100 (40GB) GPUs
* Gradient accumulation steps: 32
* Effective batch size: 256
* Max. context length: 8192 tokens