---
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-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-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: 0.1304

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.382         | 0.2001  | 720   | 0.2739          |
| 0.2596        | 0.4001  | 1440  | 0.2392          |
| 0.2144        | 0.6002  | 2160  | 0.2247          |
| 0.2056        | 0.8002  | 2880  | 0.2076          |
| 0.1927        | 1.0003  | 3600  | 0.1997          |
| 0.1783        | 1.2003  | 4320  | 0.1963          |
| 0.1726        | 1.4004  | 5040  | 0.1855          |
| 0.1733        | 1.6004  | 5760  | 0.1810          |
| 0.1697        | 1.8005  | 6480  | 0.1782          |
| 0.1666        | 2.0006  | 7200  | 0.1705          |
| 0.1581        | 2.2006  | 7920  | 0.1725          |
| 0.1562        | 2.4007  | 8640  | 0.1662          |
| 0.1509        | 2.6007  | 9360  | 0.1702          |
| 0.1502        | 2.8008  | 10080 | 0.1607          |
| 0.1493        | 3.0008  | 10800 | 0.1635          |
| 0.1381        | 3.2009  | 11520 | 0.1604          |
| 0.139         | 3.4009  | 12240 | 0.1577          |
| 0.1388        | 3.6010  | 12960 | 0.1559          |
| 0.1353        | 3.8011  | 13680 | 0.1573          |
| 0.1375        | 4.0011  | 14400 | 0.1531          |
| 0.1231        | 4.2012  | 15120 | 0.1536          |
| 0.1277        | 4.4012  | 15840 | 0.1542          |
| 0.127         | 4.6013  | 16560 | 0.1529          |
| 0.1289        | 4.8013  | 17280 | 0.1467          |
| 0.1242        | 5.0014  | 18000 | 0.1439          |
| 0.1138        | 5.2014  | 18720 | 0.1419          |
| 0.1153        | 5.4015  | 19440 | 0.1431          |
| 0.1154        | 5.6016  | 20160 | 0.1398          |
| 0.1159        | 5.8016  | 20880 | 0.1434          |
| 0.1132        | 6.0017  | 21600 | 0.1394          |
| 0.1052        | 6.2017  | 22320 | 0.1361          |
| 0.1041        | 6.4018  | 23040 | 0.1401          |
| 0.1061        | 6.6018  | 23760 | 0.1355          |
| 0.105         | 6.8019  | 24480 | 0.1376          |
| 0.106         | 7.0019  | 25200 | 0.1322          |
| 0.0966        | 7.2020  | 25920 | 0.1357          |
| 0.0947        | 7.4021  | 26640 | 0.1322          |
| 0.0954        | 7.6021  | 27360 | 0.1341          |
| 0.0949        | 7.8022  | 28080 | 0.1329          |
| 0.097         | 8.0022  | 28800 | 0.1294          |
| 0.0857        | 8.2023  | 29520 | 0.1291          |
| 0.0852        | 8.4023  | 30240 | 0.1263          |
| 0.0859        | 8.6024  | 30960 | 0.1289          |
| 0.0843        | 8.8024  | 31680 | 0.1281          |
| 0.0853        | 9.0025  | 32400 | 0.1254          |
| 0.0755        | 9.2026  | 33120 | 0.1295          |
| 0.0753        | 9.4026  | 33840 | 0.1253          |
| 0.0776        | 9.6027  | 34560 | 0.1284          |
| 0.0762        | 9.8027  | 35280 | 0.1220          |
| 0.0757        | 10.0028 | 36000 | 0.1223          |
| 0.0679        | 10.2028 | 36720 | 0.1242          |
| 0.0687        | 10.4029 | 37440 | 0.1263          |
| 0.0678        | 10.6029 | 38160 | 0.1281          |
| 0.0678        | 10.8030 | 38880 | 0.1266          |
| 0.068         | 11.0031 | 39600 | 0.1266          |
| 0.0636        | 11.2031 | 40320 | 0.1287          |
| 0.0624        | 11.4032 | 41040 | 0.1280          |
| 0.0623        | 11.6032 | 41760 | 0.1303          |
| 0.0613        | 11.8033 | 42480 | 0.1304          |


### Framework versions

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