---
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- generated_from_trainer
model-index:
- name: lemexp-task1-v2-lemma_object_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-lemma_object_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: 0.2817

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.6176        | 0.2001  | 720   | 0.5116          |
| 0.4965        | 0.4001  | 1440  | 0.4646          |
| 0.4307        | 0.6002  | 2160  | 0.4362          |
| 0.4144        | 0.8002  | 2880  | 0.4168          |
| 0.3977        | 1.0003  | 3600  | 0.4030          |
| 0.3632        | 1.2003  | 4320  | 0.3949          |
| 0.3596        | 1.4004  | 5040  | 0.3871          |
| 0.3571        | 1.6004  | 5760  | 0.3772          |
| 0.3509        | 1.8005  | 6480  | 0.3702          |
| 0.3437        | 2.0006  | 7200  | 0.3618          |
| 0.3249        | 2.2006  | 7920  | 0.3660          |
| 0.3214        | 2.4007  | 8640  | 0.3525          |
| 0.3149        | 2.6007  | 9360  | 0.3490          |
| 0.316         | 2.8008  | 10080 | 0.3403          |
| 0.315         | 3.0008  | 10800 | 0.3452          |
| 0.288         | 3.2009  | 11520 | 0.3454          |
| 0.2919        | 3.4009  | 12240 | 0.3368          |
| 0.2907        | 3.6010  | 12960 | 0.3342          |
| 0.2876        | 3.8011  | 13680 | 0.3282          |
| 0.2898        | 4.0011  | 14400 | 0.3280          |
| 0.2606        | 4.2012  | 15120 | 0.3285          |
| 0.2691        | 4.4012  | 15840 | 0.3259          |
| 0.2646        | 4.6013  | 16560 | 0.3245          |
| 0.2695        | 4.8013  | 17280 | 0.3110          |
| 0.263         | 5.0014  | 18000 | 0.3142          |
| 0.2415        | 5.2014  | 18720 | 0.3215          |
| 0.2428        | 5.4015  | 19440 | 0.3047          |
| 0.2448        | 5.6016  | 20160 | 0.3056          |
| 0.2458        | 5.8016  | 20880 | 0.3039          |
| 0.2416        | 6.0017  | 21600 | 0.3001          |
| 0.2236        | 6.2017  | 22320 | 0.3052          |
| 0.2247        | 6.4018  | 23040 | 0.2968          |
| 0.2232        | 6.6018  | 23760 | 0.2951          |
| 0.2231        | 6.8019  | 24480 | 0.2924          |
| 0.2207        | 7.0019  | 25200 | 0.2878          |
| 0.2058        | 7.2020  | 25920 | 0.2924          |
| 0.201         | 7.4021  | 26640 | 0.2952          |
| 0.2004        | 7.6021  | 27360 | 0.2898          |
| 0.2016        | 7.8022  | 28080 | 0.2772          |
| 0.205         | 8.0022  | 28800 | 0.2871          |
| 0.1808        | 8.2023  | 29520 | 0.2853          |
| 0.179         | 8.4023  | 30240 | 0.2801          |
| 0.1819        | 8.6024  | 30960 | 0.2835          |
| 0.1791        | 8.8024  | 31680 | 0.2744          |
| 0.1821        | 9.0025  | 32400 | 0.2749          |
| 0.1582        | 9.2026  | 33120 | 0.2867          |
| 0.1587        | 9.4026  | 33840 | 0.2798          |
| 0.1632        | 9.6027  | 34560 | 0.2796          |
| 0.161         | 9.8027  | 35280 | 0.2744          |
| 0.1586        | 10.0028 | 36000 | 0.2733          |
| 0.1397        | 10.2028 | 36720 | 0.2841          |
| 0.1411        | 10.4029 | 37440 | 0.2834          |
| 0.1411        | 10.6029 | 38160 | 0.2785          |
| 0.1419        | 10.8030 | 38880 | 0.2800          |
| 0.1425        | 11.0031 | 39600 | 0.2796          |
| 0.1274        | 11.2031 | 40320 | 0.2845          |
| 0.1258        | 11.4032 | 41040 | 0.2793          |
| 0.1244        | 11.6032 | 41760 | 0.2816          |
| 0.1229        | 11.8033 | 42480 | 0.2817          |


### Framework versions

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