---
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-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-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: 0.1520

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.428         | 0.2002  | 721   | 0.3134          |
| 0.308         | 0.4003  | 1442  | 0.2745          |
| 0.2674        | 0.6005  | 2163  | 0.2665          |
| 0.2618        | 0.8007  | 2884  | 0.2526          |
| 0.2488        | 1.0008  | 3605  | 0.2386          |
| 0.2333        | 1.2010  | 4326  | 0.2362          |
| 0.2308        | 1.4012  | 5047  | 0.2231          |
| 0.2254        | 1.6013  | 5768  | 0.2292          |
| 0.2238        | 1.8015  | 6489  | 0.2197          |
| 0.219         | 2.0017  | 7210  | 0.2146          |
| 0.2096        | 2.2018  | 7931  | 0.2149          |
| 0.2078        | 2.4020  | 8652  | 0.2135          |
| 0.2047        | 2.6022  | 9373  | 0.2064          |
| 0.2033        | 2.8023  | 10094 | 0.2077          |
| 0.2016        | 3.0025  | 10815 | 0.1990          |
| 0.1912        | 3.2027  | 11536 | 0.2029          |
| 0.1889        | 3.4028  | 12257 | 0.1974          |
| 0.187         | 3.6030  | 12978 | 0.1986          |
| 0.1861        | 3.8032  | 13699 | 0.1946          |
| 0.1854        | 4.0033  | 14420 | 0.1931          |
| 0.1754        | 4.2035  | 15141 | 0.1851          |
| 0.1752        | 4.4037  | 15862 | 0.1863          |
| 0.1731        | 4.6038  | 16583 | 0.1875          |
| 0.1747        | 4.8040  | 17304 | 0.1848          |
| 0.1725        | 5.0042  | 18025 | 0.1823          |
| 0.1606        | 5.2043  | 18746 | 0.1818          |
| 0.1606        | 5.4045  | 19467 | 0.1817          |
| 0.1599        | 5.6047  | 20188 | 0.1791          |
| 0.1609        | 5.8048  | 20909 | 0.1759          |
| 0.1583        | 6.0050  | 21630 | 0.1764          |
| 0.1507        | 6.2052  | 22351 | 0.1741          |
| 0.1489        | 6.4053  | 23072 | 0.1730          |
| 0.1479        | 6.6055  | 23793 | 0.1693          |
| 0.148         | 6.8057  | 24514 | 0.1691          |
| 0.1472        | 7.0058  | 25235 | 0.1664          |
| 0.139         | 7.2060  | 25956 | 0.1653          |
| 0.1376        | 7.4062  | 26677 | 0.1633          |
| 0.1358        | 7.6063  | 27398 | 0.1627          |
| 0.134         | 7.8065  | 28119 | 0.1625          |
| 0.1341        | 8.0067  | 28840 | 0.1630          |
| 0.1212        | 8.2068  | 29561 | 0.1612          |
| 0.1235        | 8.4070  | 30282 | 0.1598          |
| 0.1227        | 8.6072  | 31003 | 0.1568          |
| 0.1224        | 8.8073  | 31724 | 0.1543          |
| 0.122         | 9.0075  | 32445 | 0.1548          |
| 0.1094        | 9.2077  | 33166 | 0.1557          |
| 0.1087        | 9.4078  | 33887 | 0.1512          |
| 0.1095        | 9.6080  | 34608 | 0.1530          |
| 0.1088        | 9.8082  | 35329 | 0.1516          |
| 0.1103        | 10.0083 | 36050 | 0.1523          |
| 0.0967        | 10.2085 | 36771 | 0.1581          |
| 0.0958        | 10.4087 | 37492 | 0.1528          |
| 0.0969        | 10.6088 | 38213 | 0.1526          |
| 0.0964        | 10.8090 | 38934 | 0.1526          |
| 0.0953        | 11.0092 | 39655 | 0.1528          |
| 0.088         | 11.2093 | 40376 | 0.1560          |
| 0.0857        | 11.4095 | 41097 | 0.1546          |
| 0.0862        | 11.6097 | 41818 | 0.1547          |
| 0.0864        | 11.8098 | 42539 | 0.1520          |


### Framework versions

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