---
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-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-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: 0.2634

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.5858        | 0.2001  | 720   | 0.4896          |
| 0.4652        | 0.4001  | 1440  | 0.4362          |
| 0.4072        | 0.6002  | 2160  | 0.4134          |
| 0.3941        | 0.8002  | 2880  | 0.3971          |
| 0.3765        | 1.0003  | 3600  | 0.3855          |
| 0.3457        | 1.2003  | 4320  | 0.3746          |
| 0.3401        | 1.4004  | 5040  | 0.3664          |
| 0.3392        | 1.6004  | 5760  | 0.3655          |
| 0.3354        | 1.8005  | 6480  | 0.3511          |
| 0.3286        | 2.0006  | 7200  | 0.3507          |
| 0.3095        | 2.2006  | 7920  | 0.3500          |
| 0.3046        | 2.4007  | 8640  | 0.3373          |
| 0.3004        | 2.6007  | 9360  | 0.3278          |
| 0.2993        | 2.8008  | 10080 | 0.3210          |
| 0.3009        | 3.0008  | 10800 | 0.3270          |
| 0.2759        | 3.2009  | 11520 | 0.3232          |
| 0.2782        | 3.4009  | 12240 | 0.3173          |
| 0.2768        | 3.6010  | 12960 | 0.3180          |
| 0.276         | 3.8011  | 13680 | 0.3124          |
| 0.2772        | 4.0011  | 14400 | 0.3027          |
| 0.2495        | 4.2012  | 15120 | 0.3122          |
| 0.2575        | 4.4012  | 15840 | 0.3063          |
| 0.2525        | 4.6013  | 16560 | 0.2970          |
| 0.2586        | 4.8013  | 17280 | 0.3007          |
| 0.2518        | 5.0014  | 18000 | 0.3017          |
| 0.2297        | 5.2014  | 18720 | 0.2969          |
| 0.2316        | 5.4015  | 19440 | 0.2911          |
| 0.2355        | 5.6016  | 20160 | 0.2951          |
| 0.2358        | 5.8016  | 20880 | 0.2850          |
| 0.2308        | 6.0017  | 21600 | 0.2823          |
| 0.2135        | 6.2017  | 22320 | 0.2825          |
| 0.2151        | 6.4018  | 23040 | 0.2798          |
| 0.2143        | 6.6018  | 23760 | 0.2780          |
| 0.2131        | 6.8019  | 24480 | 0.2756          |
| 0.2126        | 7.0019  | 25200 | 0.2703          |
| 0.1967        | 7.2020  | 25920 | 0.2741          |
| 0.1922        | 7.4021  | 26640 | 0.2734          |
| 0.1928        | 7.6021  | 27360 | 0.2694          |
| 0.1931        | 7.8022  | 28080 | 0.2635          |
| 0.1958        | 8.0022  | 28800 | 0.2680          |
| 0.1732        | 8.2023  | 29520 | 0.2659          |
| 0.1711        | 8.4023  | 30240 | 0.2651          |
| 0.1736        | 8.6024  | 30960 | 0.2650          |
| 0.172         | 8.8024  | 31680 | 0.2565          |
| 0.1752        | 9.0025  | 32400 | 0.2579          |
| 0.1521        | 9.2026  | 33120 | 0.2709          |
| 0.1519        | 9.4026  | 33840 | 0.2620          |
| 0.1569        | 9.6027  | 34560 | 0.2624          |
| 0.1548        | 9.8027  | 35280 | 0.2566          |
| 0.152         | 10.0028 | 36000 | 0.2577          |
| 0.1338        | 10.2028 | 36720 | 0.2610          |
| 0.1353        | 10.4029 | 37440 | 0.2582          |
| 0.1346        | 10.6029 | 38160 | 0.2583          |
| 0.1347        | 10.8030 | 38880 | 0.2576          |
| 0.1361        | 11.0031 | 39600 | 0.2593          |
| 0.1219        | 11.2031 | 40320 | 0.2644          |
| 0.1203        | 11.4032 | 41040 | 0.2636          |
| 0.1188        | 11.6032 | 41760 | 0.2645          |
| 0.1186        | 11.8033 | 42480 | 0.2634          |


### Framework versions

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