---
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-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-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: 0.2308

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.376         | 0.2001  | 720   | 0.3061          |
| 0.2956        | 0.4001  | 1440  | 0.2719          |
| 0.2461        | 0.6002  | 2160  | 0.2516          |
| 0.2307        | 0.8002  | 2880  | 0.2278          |
| 0.2154        | 1.0003  | 3600  | 0.2175          |
| 0.1815        | 1.2003  | 4320  | 0.2159          |
| 0.1785        | 1.4004  | 5040  | 0.2063          |
| 0.1748        | 1.6004  | 5760  | 0.2053          |
| 0.1715        | 1.8005  | 6480  | 0.1971          |
| 0.1664        | 2.0006  | 7200  | 0.1899          |
| 0.1452        | 2.2006  | 7920  | 0.1971          |
| 0.1363        | 2.4007  | 8640  | 0.1878          |
| 0.1345        | 2.6007  | 9360  | 0.1852          |
| 0.1345        | 2.8008  | 10080 | 0.1804          |
| 0.1355        | 3.0008  | 10800 | 0.1782          |
| 0.1072        | 3.2009  | 11520 | 0.1811          |
| 0.1086        | 3.4009  | 12240 | 0.1772          |
| 0.109         | 3.6010  | 12960 | 0.1782          |
| 0.1084        | 3.8011  | 13680 | 0.1748          |
| 0.1114        | 4.0011  | 14400 | 0.1665          |
| 0.0839        | 4.2012  | 15120 | 0.1762          |
| 0.0878        | 4.4012  | 15840 | 0.1742          |
| 0.0887        | 4.6013  | 16560 | 0.1814          |
| 0.0928        | 4.8013  | 17280 | 0.1696          |
| 0.0888        | 5.0014  | 18000 | 0.1723          |
| 0.067         | 5.2014  | 18720 | 0.1807          |
| 0.0696        | 5.4015  | 19440 | 0.1794          |
| 0.0724        | 5.6016  | 20160 | 0.1767          |
| 0.0748        | 5.8016  | 20880 | 0.1777          |
| 0.0731        | 6.0017  | 21600 | 0.1753          |
| 0.0579        | 6.2017  | 22320 | 0.1856          |
| 0.0582        | 6.4018  | 23040 | 0.1760          |
| 0.0597        | 6.6018  | 23760 | 0.1775          |
| 0.0591        | 6.8019  | 24480 | 0.1827          |
| 0.0591        | 7.0019  | 25200 | 0.1757          |
| 0.0479        | 7.2020  | 25920 | 0.1938          |
| 0.0457        | 7.4021  | 26640 | 0.1841          |
| 0.0463        | 7.6021  | 27360 | 0.1897          |
| 0.0482        | 7.8022  | 28080 | 0.1827          |
| 0.0483        | 8.0022  | 28800 | 0.1814          |
| 0.0353        | 8.2023  | 29520 | 0.1986          |
| 0.0346        | 8.4023  | 30240 | 0.2028          |
| 0.0358        | 8.6024  | 30960 | 0.1992          |
| 0.0374        | 8.8024  | 31680 | 0.2005          |
| 0.0373        | 9.0025  | 32400 | 0.1997          |
| 0.026         | 9.2026  | 33120 | 0.2042          |
| 0.0273        | 9.4026  | 33840 | 0.1999          |
| 0.0289        | 9.6027  | 34560 | 0.2058          |
| 0.0302        | 9.8027  | 35280 | 0.2088          |
| 0.0287        | 10.0028 | 36000 | 0.2023          |
| 0.0213        | 10.2028 | 36720 | 0.2204          |
| 0.0214        | 10.4029 | 37440 | 0.2143          |
| 0.0226        | 10.6029 | 38160 | 0.2182          |
| 0.0222        | 10.8030 | 38880 | 0.2174          |
| 0.0224        | 11.0031 | 39600 | 0.2165          |
| 0.0182        | 11.2031 | 40320 | 0.2343          |
| 0.0178        | 11.4032 | 41040 | 0.2309          |
| 0.0174        | 11.6032 | 41760 | 0.2295          |
| 0.0181        | 11.8033 | 42480 | 0.2308          |


### Framework versions

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