---
library_name: peft
license: other
base_model: Qwen/Qwen2.5-3B
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: sms_adapter
  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. -->

# sms_adapter

This model is a fine-tuned version of [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3455
- Accuracy: 0.923

## 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 0.7771        | 0.8881 | 500  | 0.3763          | 0.871    |
| 0.2888        | 1.7762 | 1000 | 0.3110          | 0.897    |
| 0.1767        | 2.6643 | 1500 | 0.3098          | 0.922    |
| 0.1337        | 3.5524 | 2000 | 0.3240          | 0.93     |
| 0.0885        | 4.4405 | 2500 | 0.3455          | 0.923    |


### Framework versions

- PEFT 0.13.2
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3