---
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_notypes-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_notypes-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: 0.1620

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.4455        | 0.2002  | 721   | 0.3234          |
| 0.3298        | 0.4003  | 1442  | 0.2983          |
| 0.2882        | 0.6005  | 2163  | 0.2751          |
| 0.279         | 0.8007  | 2884  | 0.2731          |
| 0.2666        | 1.0008  | 3605  | 0.2549          |
| 0.2514        | 1.2010  | 4326  | 0.2510          |
| 0.2473        | 1.4012  | 5047  | 0.2483          |
| 0.2414        | 1.6013  | 5768  | 0.2416          |
| 0.2392        | 1.8015  | 6489  | 0.2338          |
| 0.2344        | 2.0017  | 7210  | 0.2286          |
| 0.2249        | 2.2018  | 7931  | 0.2262          |
| 0.224         | 2.4020  | 8652  | 0.2282          |
| 0.2187        | 2.6022  | 9373  | 0.2221          |
| 0.2177        | 2.8023  | 10094 | 0.2160          |
| 0.2143        | 3.0025  | 10815 | 0.2136          |
| 0.2044        | 3.2027  | 11536 | 0.2131          |
| 0.2015        | 3.4028  | 12257 | 0.2073          |
| 0.2011        | 3.6030  | 12978 | 0.2110          |
| 0.1995        | 3.8032  | 13699 | 0.2024          |
| 0.1987        | 4.0033  | 14420 | 0.2046          |
| 0.187         | 4.2035  | 15141 | 0.2017          |
| 0.1858        | 4.4037  | 15862 | 0.1998          |
| 0.1859        | 4.6038  | 16583 | 0.1967          |
| 0.1859        | 4.8040  | 17304 | 0.1975          |
| 0.1851        | 5.0042  | 18025 | 0.1986          |
| 0.1708        | 5.2043  | 18746 | 0.1932          |
| 0.1723        | 5.4045  | 19467 | 0.1874          |
| 0.1708        | 5.6047  | 20188 | 0.1921          |
| 0.1727        | 5.8048  | 20909 | 0.1852          |
| 0.1709        | 6.0050  | 21630 | 0.1836          |
| 0.1594        | 6.2052  | 22351 | 0.1884          |
| 0.1589        | 6.4053  | 23072 | 0.1809          |
| 0.1576        | 6.6055  | 23793 | 0.1775          |
| 0.1585        | 6.8057  | 24514 | 0.1792          |
| 0.1558        | 7.0058  | 25235 | 0.1747          |
| 0.1488        | 7.2060  | 25956 | 0.1727          |
| 0.1464        | 7.4062  | 26677 | 0.1730          |
| 0.1451        | 7.6063  | 27398 | 0.1713          |
| 0.1432        | 7.8065  | 28119 | 0.1728          |
| 0.1431        | 8.0067  | 28840 | 0.1742          |
| 0.1307        | 8.2068  | 29561 | 0.1686          |
| 0.1315        | 8.4070  | 30282 | 0.1660          |
| 0.1308        | 8.6072  | 31003 | 0.1652          |
| 0.1308        | 8.8073  | 31724 | 0.1646          |
| 0.1305        | 9.0075  | 32445 | 0.1673          |
| 0.117         | 9.2077  | 33166 | 0.1676          |
| 0.1163        | 9.4078  | 33887 | 0.1640          |
| 0.1179        | 9.6080  | 34608 | 0.1595          |
| 0.1167        | 9.8082  | 35329 | 0.1601          |
| 0.1175        | 10.0083 | 36050 | 0.1644          |
| 0.1032        | 10.2085 | 36771 | 0.1647          |
| 0.103         | 10.4087 | 37492 | 0.1598          |
| 0.1039        | 10.6088 | 38213 | 0.1613          |
| 0.1042        | 10.8090 | 38934 | 0.1584          |
| 0.1022        | 11.0092 | 39655 | 0.1607          |
| 0.0948        | 11.2093 | 40376 | 0.1620          |
| 0.0925        | 11.4095 | 41097 | 0.1628          |
| 0.093         | 11.6097 | 41818 | 0.1623          |
| 0.0926        | 11.8098 | 42539 | 0.1620          |


### Framework versions

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