---
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- generated_from_trainer
model-index:
- name: lemexp-task3-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-task3-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: 0.1245

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.4237        | 0.2001  | 720   | 0.2939          |
| 0.2873        | 0.4001  | 1440  | 0.2619          |
| 0.2345        | 0.6002  | 2160  | 0.2396          |
| 0.2212        | 0.8002  | 2880  | 0.2263          |
| 0.2041        | 1.0003  | 3600  | 0.2142          |
| 0.1872        | 1.2003  | 4320  | 0.2103          |
| 0.1829        | 1.4004  | 5040  | 0.1951          |
| 0.1807        | 1.6004  | 5760  | 0.1921          |
| 0.1776        | 1.8005  | 6480  | 0.1884          |
| 0.1759        | 2.0006  | 7200  | 0.1840          |
| 0.1658        | 2.2006  | 7920  | 0.1791          |
| 0.1627        | 2.4007  | 8640  | 0.1727          |
| 0.1574        | 2.6007  | 9360  | 0.1716          |
| 0.1571        | 2.8008  | 10080 | 0.1727          |
| 0.1549        | 3.0008  | 10800 | 0.1675          |
| 0.1441        | 3.2009  | 11520 | 0.1620          |
| 0.1447        | 3.4009  | 12240 | 0.1606          |
| 0.1433        | 3.6010  | 12960 | 0.1668          |
| 0.1409        | 3.8011  | 13680 | 0.1674          |
| 0.1415        | 4.0011  | 14400 | 0.1585          |
| 0.1282        | 4.2012  | 15120 | 0.1583          |
| 0.1332        | 4.4012  | 15840 | 0.1567          |
| 0.1296        | 4.6013  | 16560 | 0.1559          |
| 0.1332        | 4.8013  | 17280 | 0.1477          |
| 0.1268        | 5.0014  | 18000 | 0.1507          |
| 0.1176        | 5.2014  | 18720 | 0.1490          |
| 0.1166        | 5.4015  | 19440 | 0.1494          |
| 0.1196        | 5.6016  | 20160 | 0.1442          |
| 0.1193        | 5.8016  | 20880 | 0.1416          |
| 0.1156        | 6.0017  | 21600 | 0.1390          |
| 0.1067        | 6.2017  | 22320 | 0.1446          |
| 0.1069        | 6.4018  | 23040 | 0.1418          |
| 0.1085        | 6.6018  | 23760 | 0.1385          |
| 0.1062        | 6.8019  | 24480 | 0.1312          |
| 0.1074        | 7.0019  | 25200 | 0.1343          |
| 0.0986        | 7.2020  | 25920 | 0.1362          |
| 0.0965        | 7.4021  | 26640 | 0.1360          |
| 0.0967        | 7.6021  | 27360 | 0.1335          |
| 0.0955        | 7.8022  | 28080 | 0.1275          |
| 0.0986        | 8.0022  | 28800 | 0.1328          |
| 0.0876        | 8.2023  | 29520 | 0.1348          |
| 0.0867        | 8.4023  | 30240 | 0.1314          |
| 0.087         | 8.6024  | 30960 | 0.1290          |
| 0.0863        | 8.8024  | 31680 | 0.1261          |
| 0.087         | 9.0025  | 32400 | 0.1244          |
| 0.0775        | 9.2026  | 33120 | 0.1293          |
| 0.0768        | 9.4026  | 33840 | 0.1260          |
| 0.0797        | 9.6027  | 34560 | 0.1277          |
| 0.0779        | 9.8027  | 35280 | 0.1234          |
| 0.0765        | 10.0028 | 36000 | 0.1230          |
| 0.0692        | 10.2028 | 36720 | 0.1267          |
| 0.0697        | 10.4029 | 37440 | 0.1259          |
| 0.0691        | 10.6029 | 38160 | 0.1263          |
| 0.0692        | 10.8030 | 38880 | 0.1229          |
| 0.0694        | 11.0031 | 39600 | 0.1227          |
| 0.0647        | 11.2031 | 40320 | 0.1255          |
| 0.0632        | 11.4032 | 41040 | 0.1250          |
| 0.0636        | 11.6032 | 41760 | 0.1260          |
| 0.0626        | 11.8033 | 42480 | 0.1245          |


### Framework versions

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