---
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-6.7b-base
tags:
- base_model:adapter:deepseek-ai/deepseek-coder-6.7b-base
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: lemexp-task1-v3-lemma_object_small_nodefs-deepseek-coder-6.7b-base
  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-v3-lemma_object_small_nodefs-deepseek-coder-6.7b-base

This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2294

## 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: 0.0004
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 16
- total_eval_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.4045        | 0.2001  | 720   | 0.3253          |
| 0.3156        | 0.4001  | 1440  | 0.2905          |
| 0.2636        | 0.6002  | 2160  | 0.2644          |
| 0.2455        | 0.8002  | 2880  | 0.2401          |
| 0.227         | 1.0003  | 3600  | 0.2328          |
| 0.1903        | 1.2003  | 4320  | 0.2267          |
| 0.1872        | 1.4004  | 5040  | 0.2187          |
| 0.1831        | 1.6004  | 5760  | 0.2105          |
| 0.1785        | 1.8005  | 6480  | 0.2082          |
| 0.1736        | 2.0006  | 7200  | 0.1973          |
| 0.1512        | 2.2006  | 7920  | 0.1999          |
| 0.1414        | 2.4007  | 8640  | 0.1973          |
| 0.1413        | 2.6007  | 9360  | 0.1891          |
| 0.1397        | 2.8008  | 10080 | 0.1857          |
| 0.1401        | 3.0008  | 10800 | 0.1840          |
| 0.1111        | 3.2009  | 11520 | 0.1837          |
| 0.1135        | 3.4009  | 12240 | 0.1819          |
| 0.1138        | 3.6010  | 12960 | 0.1821          |
| 0.1133        | 3.8011  | 13680 | 0.1799          |
| 0.1147        | 4.0011  | 14400 | 0.1769          |
| 0.0871        | 4.2012  | 15120 | 0.1822          |
| 0.0902        | 4.4012  | 15840 | 0.1860          |
| 0.0921        | 4.6013  | 16560 | 0.1809          |
| 0.0956        | 4.8013  | 17280 | 0.1696          |
| 0.0932        | 5.0014  | 18000 | 0.1711          |
| 0.0706        | 5.2014  | 18720 | 0.1792          |
| 0.0715        | 5.4015  | 19440 | 0.1803          |
| 0.075         | 5.6016  | 20160 | 0.1746          |
| 0.0775        | 5.8016  | 20880 | 0.1798          |
| 0.0759        | 6.0017  | 21600 | 0.1766          |
| 0.0604        | 6.2017  | 22320 | 0.1849          |
| 0.0608        | 6.4018  | 23040 | 0.1875          |
| 0.0626        | 6.6018  | 23760 | 0.1774          |
| 0.0614        | 6.8019  | 24480 | 0.1776          |
| 0.0622        | 7.0019  | 25200 | 0.1798          |
| 0.0505        | 7.2020  | 25920 | 0.1918          |
| 0.0475        | 7.4021  | 26640 | 0.1941          |
| 0.0487        | 7.6021  | 27360 | 0.1886          |
| 0.0507        | 7.8022  | 28080 | 0.1860          |
| 0.0507        | 8.0022  | 28800 | 0.1883          |
| 0.0372        | 8.2023  | 29520 | 0.2032          |
| 0.0368        | 8.4023  | 30240 | 0.1974          |
| 0.0383        | 8.6024  | 30960 | 0.1965          |
| 0.0387        | 8.8024  | 31680 | 0.1971          |
| 0.0395        | 9.0025  | 32400 | 0.1936          |
| 0.0277        | 9.2026  | 33120 | 0.2076          |
| 0.0287        | 9.4026  | 33840 | 0.1991          |
| 0.0305        | 9.6027  | 34560 | 0.2040          |
| 0.0315        | 9.8027  | 35280 | 0.2068          |
| 0.0305        | 10.0028 | 36000 | 0.1999          |
| 0.0228        | 10.2028 | 36720 | 0.2139          |
| 0.0226        | 10.4029 | 37440 | 0.2154          |
| 0.0237        | 10.6029 | 38160 | 0.2152          |
| 0.0236        | 10.8030 | 38880 | 0.2104          |
| 0.0236        | 11.0031 | 39600 | 0.2112          |
| 0.0192        | 11.2031 | 40320 | 0.2329          |
| 0.0186        | 11.4032 | 41040 | 0.2319          |
| 0.0184        | 11.6032 | 41760 | 0.2299          |
| 0.0189        | 11.8033 | 42480 | 0.2294          |


### Framework versions

- PEFT 0.17.1
- Transformers 4.55.4
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4