---
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_nodefs-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_nodefs-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: 0.1548

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.3773        | 0.2001  | 720   | 0.2929          |
| 0.2804        | 0.4001  | 1440  | 0.2615          |
| 0.2488        | 0.6002  | 2160  | 0.2472          |
| 0.2405        | 0.8002  | 2880  | 0.2416          |
| 0.2302        | 1.0003  | 3600  | 0.2355          |
| 0.218         | 1.2003  | 4320  | 0.2305          |
| 0.2138        | 1.4004  | 5040  | 0.2205          |
| 0.2111        | 1.6004  | 5760  | 0.2150          |
| 0.2109        | 1.8005  | 6480  | 0.2147          |
| 0.2035        | 2.0006  | 7200  | 0.2091          |
| 0.1953        | 2.2006  | 7920  | 0.2103          |
| 0.1932        | 2.4007  | 8640  | 0.2053          |
| 0.1897        | 2.6007  | 9360  | 0.1994          |
| 0.1896        | 2.8008  | 10080 | 0.2000          |
| 0.1927        | 3.0008  | 10800 | 0.1980          |
| 0.1785        | 3.2009  | 11520 | 0.1952          |
| 0.18          | 3.4009  | 12240 | 0.1955          |
| 0.176         | 3.6010  | 12960 | 0.1882          |
| 0.1753        | 3.8011  | 13680 | 0.1899          |
| 0.1765        | 4.0011  | 14400 | 0.1840          |
| 0.165         | 4.2012  | 15120 | 0.1892          |
| 0.1653        | 4.4012  | 15840 | 0.1850          |
| 0.1645        | 4.6013  | 16560 | 0.1914          |
| 0.1656        | 4.8013  | 17280 | 0.1821          |
| 0.1607        | 5.0014  | 18000 | 0.1860          |
| 0.1524        | 5.2014  | 18720 | 0.1806          |
| 0.1523        | 5.4015  | 19440 | 0.1771          |
| 0.1529        | 5.6016  | 20160 | 0.1719          |
| 0.1524        | 5.8016  | 20880 | 0.1751          |
| 0.1491        | 6.0017  | 21600 | 0.1706          |
| 0.1412        | 6.2017  | 22320 | 0.1686          |
| 0.1419        | 6.4018  | 23040 | 0.1685          |
| 0.1408        | 6.6018  | 23760 | 0.1653          |
| 0.1413        | 6.8019  | 24480 | 0.1675          |
| 0.1385        | 7.0019  | 25200 | 0.1632          |
| 0.1306        | 7.2020  | 25920 | 0.1650          |
| 0.1286        | 7.4021  | 26640 | 0.1622          |
| 0.1291        | 7.6021  | 27360 | 0.1631          |
| 0.127         | 7.8022  | 28080 | 0.1580          |
| 0.1289        | 8.0022  | 28800 | 0.1584          |
| 0.1177        | 8.2023  | 29520 | 0.1576          |
| 0.1167        | 8.4023  | 30240 | 0.1564          |
| 0.1174        | 8.6024  | 30960 | 0.1550          |
| 0.1156        | 8.8024  | 31680 | 0.1543          |
| 0.1164        | 9.0025  | 32400 | 0.1531          |
| 0.105         | 9.2026  | 33120 | 0.1582          |
| 0.1045        | 9.4026  | 33840 | 0.1557          |
| 0.106         | 9.6027  | 34560 | 0.1534          |
| 0.1058        | 9.8027  | 35280 | 0.1500          |
| 0.1026        | 10.0028 | 36000 | 0.1499          |
| 0.0938        | 10.2028 | 36720 | 0.1540          |
| 0.0937        | 10.4029 | 37440 | 0.1522          |
| 0.0929        | 10.6029 | 38160 | 0.1542          |
| 0.0926        | 10.8030 | 38880 | 0.1537          |
| 0.0931        | 11.0031 | 39600 | 0.1518          |
| 0.0849        | 11.2031 | 40320 | 0.1579          |
| 0.0837        | 11.4032 | 41040 | 0.1560          |
| 0.0828        | 11.6032 | 41760 | 0.1548          |
| 0.0826        | 11.8033 | 42480 | 0.1548          |


### Framework versions

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