---
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- generated_from_trainer
model-index:
- name: lemexp-task4-v2-small_no_symbols-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-task4-v2-small_no_symbols-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: 0.0427

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.1596        | 0.2001  | 720   | 0.0929          |
| 0.0915        | 0.4001  | 1440  | 0.0789          |
| 0.0761        | 0.6002  | 2160  | 0.0721          |
| 0.073         | 0.8002  | 2880  | 0.0659          |
| 0.0693        | 1.0003  | 3600  | 0.0646          |
| 0.067         | 1.2003  | 4320  | 0.0617          |
| 0.066         | 1.4004  | 5040  | 0.0618          |
| 0.0652        | 1.6004  | 5760  | 0.0624          |
| 0.0663        | 1.8005  | 6480  | 0.0611          |
| 0.0645        | 2.0006  | 7200  | 0.0610          |
| 0.0612        | 2.2006  | 7920  | 0.0605          |
| 0.0599        | 2.4007  | 8640  | 0.0583          |
| 0.0586        | 2.6007  | 9360  | 0.0555          |
| 0.0586        | 2.8008  | 10080 | 0.0561          |
| 0.0589        | 3.0008  | 10800 | 0.0564          |
| 0.0576        | 3.2009  | 11520 | 0.0545          |
| 0.0566        | 3.4009  | 12240 | 0.0560          |
| 0.0574        | 3.6010  | 12960 | 0.0523          |
| 0.0547        | 3.8011  | 13680 | 0.0623          |
| 0.0565        | 4.0011  | 14400 | 0.0518          |
| 0.0524        | 4.2012  | 15120 | 0.0513          |
| 0.0537        | 4.4012  | 15840 | 0.0494          |
| 0.0527        | 4.6013  | 16560 | 0.0483          |
| 0.054         | 4.8013  | 17280 | 0.0492          |
| 0.0527        | 5.0014  | 18000 | 0.0503          |
| 0.0509        | 5.2014  | 18720 | 0.0483          |
| 0.0502        | 5.4015  | 19440 | 0.0515          |
| 0.0518        | 5.6016  | 20160 | 0.0481          |
| 0.0507        | 5.8016  | 20880 | 0.0496          |
| 0.0495        | 6.0017  | 21600 | 0.0484          |
| 0.0483        | 6.2017  | 22320 | 0.0504          |
| 0.0485        | 6.4018  | 23040 | 0.0466          |
| 0.0485        | 6.6018  | 23760 | 0.0462          |
| 0.0482        | 6.8019  | 24480 | 0.0486          |
| 0.0467        | 7.0019  | 25200 | 0.0459          |
| 0.0465        | 7.2020  | 25920 | 0.0461          |
| 0.0461        | 7.4021  | 26640 | 0.0476          |
| 0.0471        | 7.6021  | 27360 | 0.0460          |
| 0.046         | 7.8022  | 28080 | 0.0439          |
| 0.0455        | 8.0022  | 28800 | 0.0458          |
| 0.0458        | 8.2023  | 29520 | 0.0454          |
| 0.0451        | 8.4023  | 30240 | 0.0444          |
| 0.0445        | 8.6024  | 30960 | 0.0444          |
| 0.0437        | 8.8024  | 31680 | 0.0435          |
| 0.0442        | 9.0025  | 32400 | 0.0436          |
| 0.0433        | 9.2026  | 33120 | 0.0432          |
| 0.0434        | 9.4026  | 33840 | 0.0433          |
| 0.0435        | 9.6027  | 34560 | 0.0433          |
| 0.043         | 9.8027  | 35280 | 0.0433          |
| 0.0427        | 10.0028 | 36000 | 0.0430          |
| 0.0427        | 10.2028 | 36720 | 0.0426          |
| 0.0419        | 10.4029 | 37440 | 0.0423          |
| 0.0419        | 10.6029 | 38160 | 0.0424          |
| 0.0417        | 10.8030 | 38880 | 0.0426          |
| 0.0415        | 11.0031 | 39600 | 0.0422          |
| 0.0415        | 11.2031 | 40320 | 0.0427          |
| 0.0414        | 11.4032 | 41040 | 0.0425          |
| 0.0414        | 11.6032 | 41760 | 0.0425          |
| 0.0413        | 11.8033 | 42480 | 0.0427          |


### Framework versions

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