---
library_name: peft
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-135M
tags:
- base_model:adapter:HuggingFaceTB/SmolLM2-135M
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: hausa_blend
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# hausa_blend

This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 9.6934

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.002
- train_batch_size: 64
- eval_batch_size: 64
- seed: 1652
- gradient_accumulation_steps: 5
- total_train_batch_size: 320
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 6
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 213.2576      | 1.0   | 201  | 22.5111         |
| 61.0713       | 2.0   | 402  | 11.1953         |
| 53.5773       | 3.0   | 603  | 10.4559         |
| 51.1444       | 4.0   | 804  | 10.0289         |
| 49.6945       | 5.0   | 1005 | 9.7750          |
| 48.9875       | 6.0   | 1206 | 9.6934          |


### Framework versions

- PEFT 0.16.0
- Transformers 4.54.1
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.2