---
base_model: deepseek-ai/deepseek-coder-1.3b-base
datasets:
- generator
library_name: peft
license: other
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: sft_small
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/stojchets/huggingface/runs/sft_small)
# sft_small

This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 3.9430

## 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: 1.41e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.437         | 0.1   | 1    | 3.9886          |
| 4.2418        | 0.2   | 2    | 3.9798          |
| 4.3555        | 0.3   | 3    | 3.9724          |
| 3.1845        | 0.4   | 4    | 3.9651          |
| 3.0337        | 0.5   | 5    | 3.9591          |
| 4.6927        | 0.6   | 6    | 3.9539          |
| 4.5557        | 0.7   | 7    | 3.9497          |
| 3.9312        | 0.8   | 8    | 3.9464          |
| 4.0857        | 0.9   | 9    | 3.9441          |
| 4.1279        | 1.0   | 10   | 3.9430          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.43.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1