---
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- generated_from_trainer
model-index:
- name: lemexp-task2-ordered_lemma_object_small-deepseek-coder-1.3b-base-ddp-8lr
  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-task2-ordered_lemma_object_small-deepseek-coder-1.3b-base-ddp-8lr

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: 0.2732

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.6215        | 0.2001  | 629   | 0.4887          |
| 0.4954        | 0.4001  | 1258  | 0.4381          |
| 0.4617        | 0.6002  | 1887  | 0.4172          |
| 0.4239        | 0.8003  | 2516  | 0.3932          |
| 0.4128        | 1.0003  | 3145  | 0.3909          |
| 0.382         | 1.2004  | 3774  | 0.3691          |
| 0.3743        | 1.4004  | 4403  | 0.3694          |
| 0.3669        | 1.6005  | 5032  | 0.3574          |
| 0.3634        | 1.8006  | 5661  | 0.3510          |
| 0.3576        | 2.0006  | 6290  | 0.3507          |
| 0.3458        | 2.2007  | 6919  | 0.3425          |
| 0.3341        | 2.4008  | 7548  | 0.3494          |
| 0.3296        | 2.6008  | 8177  | 0.3409          |
| 0.3346        | 2.8009  | 8806  | 0.3339          |
| 0.33          | 3.0010  | 9435  | 0.3290          |
| 0.3022        | 3.2010  | 10064 | 0.3255          |
| 0.3072        | 3.4011  | 10693 | 0.3205          |
| 0.3033        | 3.6011  | 11322 | 0.3182          |
| 0.3026        | 3.8012  | 11951 | 0.3111          |
| 0.3019        | 4.0013  | 12580 | 0.3120          |
| 0.2831        | 4.2013  | 13209 | 0.3150          |
| 0.2789        | 4.4014  | 13838 | 0.3042          |
| 0.2851        | 4.6015  | 14467 | 0.3077          |
| 0.2786        | 4.8015  | 15096 | 0.3038          |
| 0.2795        | 5.0016  | 15725 | 0.3018          |
| 0.2639        | 5.2017  | 16354 | 0.2993          |
| 0.2581        | 5.4017  | 16983 | 0.2924          |
| 0.2577        | 5.6018  | 17612 | 0.2991          |
| 0.2578        | 5.8018  | 18241 | 0.2903          |
| 0.2619        | 6.0019  | 18870 | 0.2895          |
| 0.2476        | 6.2020  | 19499 | 0.2867          |
| 0.2371        | 6.4020  | 20128 | 0.2940          |
| 0.2371        | 6.6021  | 20757 | 0.2874          |
| 0.2352        | 6.8022  | 21386 | 0.2805          |
| 0.2413        | 7.0022  | 22015 | 0.2776          |
| 0.2107        | 7.2023  | 22644 | 0.2818          |
| 0.2128        | 7.4024  | 23273 | 0.2817          |
| 0.2174        | 7.6024  | 23902 | 0.2784          |
| 0.2172        | 7.8025  | 24531 | 0.2779          |
| 0.2139        | 8.0025  | 25160 | 0.2776          |
| 0.1954        | 8.2026  | 25789 | 0.2799          |
| 0.1922        | 8.4027  | 26418 | 0.2754          |
| 0.1978        | 8.6027  | 27047 | 0.2698          |
| 0.1946        | 8.8028  | 27676 | 0.2726          |
| 0.1978        | 9.0029  | 28305 | 0.2704          |
| 0.1856        | 9.2029  | 28934 | 0.2747          |
| 0.175         | 9.4030  | 29563 | 0.2691          |
| 0.1764        | 9.6031  | 30192 | 0.2721          |
| 0.176         | 9.8031  | 30821 | 0.2651          |
| 0.1757        | 10.0032 | 31450 | 0.2630          |
| 0.1525        | 10.2032 | 32079 | 0.2743          |
| 0.1562        | 10.4033 | 32708 | 0.2736          |
| 0.1554        | 10.6034 | 33337 | 0.2675          |
| 0.1565        | 10.8034 | 33966 | 0.2664          |
| 0.1557        | 11.0035 | 34595 | 0.2665          |
| 0.1424        | 11.2036 | 35224 | 0.2709          |
| 0.1394        | 11.4036 | 35853 | 0.2727          |
| 0.1393        | 11.6037 | 36482 | 0.2740          |
| 0.1387        | 11.8038 | 37111 | 0.2732          |


### Framework versions

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