---
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- generated_from_trainer
model-index:
- name: lemexp-task1-template_small-deepseek-coder-1.3b-base-ddp-8lr
  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-template_small-deepseek-coder-1.3b-base-ddp-8lr

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: 0.1898

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.4568        | 0.2001  | 629   | 0.3546          |
| 0.3564        | 0.4001  | 1258  | 0.3166          |
| 0.3295        | 0.6002  | 1887  | 0.2969          |
| 0.3013        | 0.8003  | 2516  | 0.2892          |
| 0.2925        | 1.0003  | 3145  | 0.2887          |
| 0.2786        | 1.2004  | 3774  | 0.2703          |
| 0.2723        | 1.4004  | 4403  | 0.2618          |
| 0.2636        | 1.6005  | 5032  | 0.2608          |
| 0.2645        | 1.8006  | 5661  | 0.2529          |
| 0.2559        | 2.0006  | 6290  | 0.2550          |
| 0.2525        | 2.2007  | 6919  | 0.2538          |
| 0.245         | 2.4008  | 7548  | 0.2488          |
| 0.2429        | 2.6008  | 8177  | 0.2453          |
| 0.2427        | 2.8009  | 8806  | 0.2432          |
| 0.2384        | 3.0010  | 9435  | 0.2353          |
| 0.2223        | 3.2010  | 10064 | 0.2349          |
| 0.225         | 3.4011  | 10693 | 0.2328          |
| 0.2231        | 3.6011  | 11322 | 0.2276          |
| 0.2231        | 3.8012  | 11951 | 0.2231          |
| 0.221         | 4.0013  | 12580 | 0.2249          |
| 0.2079        | 4.2013  | 13209 | 0.2228          |
| 0.2065        | 4.4014  | 13838 | 0.2215          |
| 0.2115        | 4.6015  | 14467 | 0.2197          |
| 0.2057        | 4.8015  | 15096 | 0.2177          |
| 0.207         | 5.0016  | 15725 | 0.2157          |
| 0.1966        | 5.2017  | 16354 | 0.2147          |
| 0.194         | 5.4017  | 16983 | 0.2137          |
| 0.1925        | 5.6018  | 17612 | 0.2077          |
| 0.1919        | 5.8018  | 18241 | 0.2063          |
| 0.1916        | 6.0019  | 18870 | 0.2064          |
| 0.1857        | 6.2020  | 19499 | 0.2039          |
| 0.177         | 6.4020  | 20128 | 0.2025          |
| 0.1767        | 6.6021  | 20757 | 0.2024          |
| 0.1765        | 6.8022  | 21386 | 0.1962          |
| 0.1782        | 7.0022  | 22015 | 0.1961          |
| 0.161         | 7.2023  | 22644 | 0.1980          |
| 0.1625        | 7.4024  | 23273 | 0.1941          |
| 0.1642        | 7.6024  | 23902 | 0.1966          |
| 0.1625        | 7.8025  | 24531 | 0.1893          |
| 0.161         | 8.0025  | 25160 | 0.1886          |
| 0.1485        | 8.2026  | 25789 | 0.1979          |
| 0.149         | 8.4027  | 26418 | 0.1910          |
| 0.1501        | 8.6027  | 27047 | 0.1879          |
| 0.148         | 8.8028  | 27676 | 0.1857          |
| 0.1501        | 9.0029  | 28305 | 0.1850          |
| 0.1414        | 9.2029  | 28934 | 0.1927          |
| 0.1338        | 9.4030  | 29563 | 0.1879          |
| 0.1342        | 9.6031  | 30192 | 0.1865          |
| 0.1348        | 9.8031  | 30821 | 0.1849          |
| 0.1337        | 10.0032 | 31450 | 0.1834          |
| 0.1202        | 10.2032 | 32079 | 0.1903          |
| 0.1208        | 10.4033 | 32708 | 0.1895          |
| 0.1199        | 10.6034 | 33337 | 0.1878          |
| 0.1213        | 10.8034 | 33966 | 0.1855          |
| 0.1187        | 11.0035 | 34595 | 0.1859          |
| 0.111         | 11.2036 | 35224 | 0.1903          |
| 0.1084        | 11.4036 | 35853 | 0.1884          |
| 0.1079        | 11.6037 | 36482 | 0.1905          |
| 0.1069        | 11.8038 | 37111 | 0.1898          |


### Framework versions

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