---
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- generated_from_trainer
model-index:
- name: lemexp-task1-min_symbols_template_small-deepseek-coder-1.3b-base-ddp-4lr
  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-min_symbols_template_small-deepseek-coder-1.3b-base-ddp-4lr

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: 0.2117

## 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: 0.0004
- 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.4738        | 0.2001  | 629   | 0.3492          |
| 0.3491        | 0.4001  | 1258  | 0.3134          |
| 0.321         | 0.6002  | 1887  | 0.2880          |
| 0.287         | 0.8003  | 2516  | 0.2711          |
| 0.276         | 1.0003  | 3145  | 0.2664          |
| 0.2593        | 1.2004  | 3774  | 0.2559          |
| 0.251         | 1.4004  | 4403  | 0.2481          |
| 0.2416        | 1.6005  | 5032  | 0.2442          |
| 0.2407        | 1.8006  | 5661  | 0.2368          |
| 0.2331        | 2.0006  | 6290  | 0.2340          |
| 0.2278        | 2.2007  | 6919  | 0.2319          |
| 0.2181        | 2.4008  | 7548  | 0.2328          |
| 0.2146        | 2.6008  | 8177  | 0.2237          |
| 0.2153        | 2.8009  | 8806  | 0.2197          |
| 0.2119        | 3.0010  | 9435  | 0.2208          |
| 0.1936        | 3.2010  | 10064 | 0.2153          |
| 0.1946        | 3.4011  | 10693 | 0.2160          |
| 0.1954        | 3.6011  | 11322 | 0.2106          |
| 0.1942        | 3.8012  | 11951 | 0.2122          |
| 0.1931        | 4.0013  | 12580 | 0.2097          |
| 0.179         | 4.2013  | 13209 | 0.2099          |
| 0.1772        | 4.4014  | 13838 | 0.2088          |
| 0.1807        | 4.6015  | 14467 | 0.2066          |
| 0.1765        | 4.8015  | 15096 | 0.2026          |
| 0.1784        | 5.0016  | 15725 | 0.2022          |
| 0.168         | 5.2017  | 16354 | 0.2046          |
| 0.164         | 5.4017  | 16983 | 0.2010          |
| 0.164         | 5.6018  | 17612 | 0.1976          |
| 0.1637        | 5.8018  | 18241 | 0.2014          |
| 0.1647        | 6.0019  | 18870 | 0.1973          |
| 0.1583        | 6.2020  | 19499 | 0.2000          |
| 0.1498        | 6.4020  | 20128 | 0.1980          |
| 0.1509        | 6.6021  | 20757 | 0.1972          |
| 0.1497        | 6.8022  | 21386 | 0.1975          |
| 0.1527        | 7.0022  | 22015 | 0.1957          |
| 0.1365        | 7.2023  | 22644 | 0.1993          |
| 0.1379        | 7.4024  | 23273 | 0.1952          |
| 0.1398        | 7.6024  | 23902 | 0.1962          |
| 0.1399        | 7.8025  | 24531 | 0.1938          |
| 0.1382        | 8.0025  | 25160 | 0.1973          |
| 0.1274        | 8.2026  | 25789 | 0.2003          |
| 0.1279        | 8.4027  | 26418 | 0.1976          |
| 0.1292        | 8.6027  | 27047 | 0.1949          |
| 0.1272        | 8.8028  | 27676 | 0.1933          |
| 0.1293        | 9.0029  | 28305 | 0.1934          |
| 0.123         | 9.2029  | 28934 | 0.2014          |
| 0.117         | 9.4030  | 29563 | 0.2006          |
| 0.1174        | 9.6031  | 30192 | 0.1991          |
| 0.1185        | 9.8031  | 30821 | 0.1996          |
| 0.1176        | 10.0032 | 31450 | 0.1987          |
| 0.1075        | 10.2032 | 32079 | 0.2035          |
| 0.109         | 10.4033 | 32708 | 0.2077          |
| 0.1081        | 10.6034 | 33337 | 0.2042          |
| 0.1087        | 10.8034 | 33966 | 0.2038          |
| 0.1077        | 11.0035 | 34595 | 0.2064          |
| 0.1027        | 11.2036 | 35224 | 0.2117          |
| 0.1003        | 11.4036 | 35853 | 0.2089          |
| 0.1002        | 11.6037 | 36482 | 0.2108          |
| 0.0994        | 11.8038 | 37111 | 0.2117          |


### Framework versions

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