---
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_full-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_full-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: 0.1529

## 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: 6
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.2779        | 0.2   | 3094  | 0.2787          |
| 0.2568        | 0.4   | 6188  | 0.2658          |
| 0.2493        | 0.6   | 9282  | 0.2520          |
| 0.2413        | 0.8   | 12376 | 0.2400          |
| 0.2362        | 1.0   | 15470 | 0.2373          |
| 0.2298        | 1.2   | 18564 | 0.2296          |
| 0.2272        | 1.4   | 21658 | 0.2256          |
| 0.2194        | 1.6   | 24752 | 0.2186          |
| 0.2189        | 1.8   | 27846 | 0.2178          |
| 0.212         | 2.0   | 30940 | 0.2128          |
| 0.206         | 2.2   | 34034 | 0.2165          |
| 0.2037        | 2.4   | 37128 | 0.2034          |
| 0.199         | 2.6   | 40222 | 0.2056          |
| 0.1963        | 2.8   | 43316 | 0.2008          |
| 0.1942        | 3.0   | 46410 | 0.1971          |
| 0.1858        | 3.2   | 49504 | 0.1919          |
| 0.1851        | 3.4   | 52598 | 0.1906          |
| 0.1791        | 3.6   | 55692 | 0.1837          |
| 0.1776        | 3.8   | 58786 | 0.1813          |
| 0.1758        | 4.0   | 61880 | 0.1761          |
| 0.166         | 4.2   | 64974 | 0.1732          |
| 0.1633        | 4.4   | 68068 | 0.1701          |
| 0.1593        | 4.6   | 71162 | 0.1687          |
| 0.1541        | 4.8   | 74256 | 0.1683          |
| 0.1525        | 5.0   | 77350 | 0.1623          |
| 0.1445        | 5.2   | 80444 | 0.1623          |
| 0.143         | 5.4   | 83538 | 0.1601          |
| 0.1409        | 5.6   | 86632 | 0.1567          |
| 0.1386        | 5.8   | 89726 | 0.1537          |
| 0.1358        | 6.0   | 92820 | 0.1529          |


### Framework versions

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