---
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- generated_from_trainer
model-index:
- name: lemexp-task1-v2-template_small_notypes-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-task1-v2-template_small_notypes-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: 0.1711

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.4293        | 0.2001  | 720   | 0.3388          |
| 0.324         | 0.4001  | 1440  | 0.2977          |
| 0.282         | 0.6002  | 2160  | 0.2814          |
| 0.2707        | 0.8002  | 2880  | 0.2713          |
| 0.2595        | 1.0003  | 3600  | 0.2822          |
| 0.2434        | 1.2003  | 4320  | 0.2586          |
| 0.2403        | 1.4004  | 5040  | 0.2458          |
| 0.2355        | 1.6004  | 5760  | 0.2513          |
| 0.2342        | 1.8005  | 6480  | 0.2404          |
| 0.2284        | 2.0006  | 7200  | 0.2346          |
| 0.2176        | 2.2006  | 7920  | 0.2339          |
| 0.2148        | 2.4007  | 8640  | 0.2315          |
| 0.2127        | 2.6007  | 9360  | 0.2236          |
| 0.2108        | 2.8008  | 10080 | 0.2300          |
| 0.2124        | 3.0008  | 10800 | 0.2186          |
| 0.1962        | 3.2009  | 11520 | 0.2232          |
| 0.1993        | 3.4009  | 12240 | 0.2160          |
| 0.1944        | 3.6010  | 12960 | 0.2141          |
| 0.1945        | 3.8011  | 13680 | 0.2150          |
| 0.1934        | 4.0011  | 14400 | 0.2132          |
| 0.182         | 4.2012  | 15120 | 0.2050          |
| 0.1817        | 4.4012  | 15840 | 0.2079          |
| 0.1809        | 4.6013  | 16560 | 0.2013          |
| 0.1805        | 4.8013  | 17280 | 0.2045          |
| 0.1768        | 5.0014  | 18000 | 0.1979          |
| 0.1661        | 5.2014  | 18720 | 0.1919          |
| 0.1673        | 5.4015  | 19440 | 0.1962          |
| 0.1679        | 5.6016  | 20160 | 0.1925          |
| 0.168         | 5.8016  | 20880 | 0.1873          |
| 0.1623        | 6.0017  | 21600 | 0.1869          |
| 0.155         | 6.2017  | 22320 | 0.1875          |
| 0.1551        | 6.4018  | 23040 | 0.1869          |
| 0.1521        | 6.6018  | 23760 | 0.1870          |
| 0.1536        | 6.8019  | 24480 | 0.1816          |
| 0.1506        | 7.0019  | 25200 | 0.1825          |
| 0.1417        | 7.2020  | 25920 | 0.1867          |
| 0.1405        | 7.4021  | 26640 | 0.1795          |
| 0.1409        | 7.6021  | 27360 | 0.1808          |
| 0.1384        | 7.8022  | 28080 | 0.1754          |
| 0.1409        | 8.0022  | 28800 | 0.1767          |
| 0.1271        | 8.2023  | 29520 | 0.1753          |
| 0.1258        | 8.4023  | 30240 | 0.1742          |
| 0.1279        | 8.6024  | 30960 | 0.1737          |
| 0.126         | 8.8024  | 31680 | 0.1709          |
| 0.1255        | 9.0025  | 32400 | 0.1688          |
| 0.1138        | 9.2026  | 33120 | 0.1734          |
| 0.1134        | 9.4026  | 33840 | 0.1709          |
| 0.1149        | 9.6027  | 34560 | 0.1697          |
| 0.1143        | 9.8027  | 35280 | 0.1681          |
| 0.1106        | 10.0028 | 36000 | 0.1651          |
| 0.1011        | 10.2028 | 36720 | 0.1698          |
| 0.1004        | 10.4029 | 37440 | 0.1672          |
| 0.1003        | 10.6029 | 38160 | 0.1698          |
| 0.1004        | 10.8030 | 38880 | 0.1681          |
| 0.0999        | 11.0031 | 39600 | 0.1660          |
| 0.091         | 11.2031 | 40320 | 0.1721          |
| 0.0901        | 11.4032 | 41040 | 0.1714          |
| 0.0886        | 11.6032 | 41760 | 0.1719          |
| 0.0885        | 11.8033 | 42480 | 0.1711          |


### Framework versions

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