---
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- generated_from_trainer
model-index:
- name: lemexp-task4-v2-small_no_defs-deepseek-coder-1.3b-base-ddp-8lr-v2
  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. -->

# lemexp-task4-v2-small_no_defs-deepseek-coder-1.3b-base-ddp-8lr-v2

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 an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0415

## 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: 0.0008
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 16
- total_eval_batch_size: 16
- 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: 12
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.1511        | 0.2001  | 720   | 0.0814          |
| 0.0835        | 0.4001  | 1440  | 0.0725          |
| 0.0719        | 0.6002  | 2160  | 0.0638          |
| 0.0679        | 0.8002  | 2880  | 0.0652          |
| 0.0648        | 1.0003  | 3600  | 0.0642          |
| 0.0634        | 1.2003  | 4320  | 0.0593          |
| 0.0622        | 1.4004  | 5040  | 0.0651          |
| 0.0642        | 1.6004  | 5760  | 0.0634          |
| 0.0621        | 1.8005  | 6480  | 0.0603          |
| 0.062         | 2.0006  | 7200  | 0.0602          |
| 0.0588        | 2.2006  | 7920  | 0.0534          |
| 0.0576        | 2.4007  | 8640  | 0.0630          |
| 0.0581        | 2.6007  | 9360  | 0.0595          |
| 0.0572        | 2.8008  | 10080 | 0.0538          |
| 0.0561        | 3.0008  | 10800 | 0.0541          |
| 0.0545        | 3.2009  | 11520 | 0.0555          |
| 0.0538        | 3.4009  | 12240 | 0.0558          |
| 0.0557        | 3.6010  | 12960 | 0.0519          |
| 0.0532        | 3.8011  | 13680 | 0.0610          |
| 0.054         | 4.0011  | 14400 | 0.0527          |
| 0.0518        | 4.2012  | 15120 | 0.0515          |
| 0.0537        | 4.4012  | 15840 | 0.0516          |
| 0.0509        | 4.6013  | 16560 | 0.0509          |
| 0.0512        | 4.8013  | 17280 | 0.0486          |
| 0.051         | 5.0014  | 18000 | 0.0491          |
| 0.0499        | 5.2014  | 18720 | 0.0491          |
| 0.0491        | 5.4015  | 19440 | 0.0488          |
| 0.0497        | 5.6016  | 20160 | 0.0468          |
| 0.05          | 5.8016  | 20880 | 0.0468          |
| 0.0481        | 6.0017  | 21600 | 0.0509          |
| 0.048         | 6.2017  | 22320 | 0.0470          |
| 0.047         | 6.4018  | 23040 | 0.0459          |
| 0.0479        | 6.6018  | 23760 | 0.0464          |
| 0.0479        | 6.8019  | 24480 | 0.0467          |
| 0.0462        | 7.0019  | 25200 | 0.0458          |
| 0.0456        | 7.2020  | 25920 | 0.0446          |
| 0.0456        | 7.4021  | 26640 | 0.0449          |
| 0.0458        | 7.6021  | 27360 | 0.0431          |
| 0.0454        | 7.8022  | 28080 | 0.0447          |
| 0.0456        | 8.0022  | 28800 | 0.0428          |
| 0.0447        | 8.2023  | 29520 | 0.0446          |
| 0.0441        | 8.4023  | 30240 | 0.0422          |
| 0.0437        | 8.6024  | 30960 | 0.0425          |
| 0.0432        | 8.8024  | 31680 | 0.0431          |
| 0.0443        | 9.0025  | 32400 | 0.0421          |
| 0.0428        | 9.2026  | 33120 | 0.0418          |
| 0.0432        | 9.4026  | 33840 | 0.0423          |
| 0.043         | 9.6027  | 34560 | 0.0421          |
| 0.0426        | 9.8027  | 35280 | 0.0427          |
| 0.0421        | 10.0028 | 36000 | 0.0423          |
| 0.0425        | 10.2028 | 36720 | 0.0413          |
| 0.0418        | 10.4029 | 37440 | 0.0420          |
| 0.0418        | 10.6029 | 38160 | 0.0417          |
| 0.0415        | 10.8030 | 38880 | 0.0419          |
| 0.0412        | 11.0031 | 39600 | 0.0423          |
| 0.0414        | 11.2031 | 40320 | 0.0416          |
| 0.0412        | 11.4032 | 41040 | 0.0417          |
| 0.0412        | 11.6032 | 41760 | 0.0416          |
| 0.0412        | 11.8033 | 42480 | 0.0415          |


### Framework versions

- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0