---
library_name: peft
license: mit
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
tags:
- generated_from_trainer
model-index:
- name: DeepSeek-R1-Distill-Qwen-1.5B-xlangai-spider-text-2-SQL-5-train-epochs
  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. -->

# DeepSeek-R1-Distill-Qwen-1.5B-xlangai-spider-text-2-SQL-5-train-epochs

This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co./deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on xlangai/spider text-to-SQL dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2901

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

Fine-tuning dataset: https://huggingface.co./datasets/xlangai/spider

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.235         | 1.0   | 1750 | 0.2988          |
| 1.1652        | 2.0   | 3500 | 0.2931          |
| 1.1291        | 3.0   | 5250 | 0.2912          |
| 0.9951        | 4.0   | 7000 | 0.2909          |
| 0.8963        | 5.0   | 8750 | 0.2901          |


### Framework versions

- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0