---
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- generated_from_trainer
model-index:
- name: lemexp-task2-unordered_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-unordered_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: 0.3105

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.6401        | 0.2001  | 629   | 0.5142          |
| 0.5205        | 0.4001  | 1258  | 0.4704          |
| 0.4906        | 0.6002  | 1887  | 0.4461          |
| 0.4524        | 0.8003  | 2516  | 0.4227          |
| 0.4408        | 1.0003  | 3145  | 0.4169          |
| 0.4092        | 1.2004  | 3774  | 0.4022          |
| 0.4029        | 1.4004  | 4403  | 0.3971          |
| 0.3947        | 1.6005  | 5032  | 0.3918          |
| 0.3928        | 1.8006  | 5661  | 0.3805          |
| 0.3869        | 2.0006  | 6290  | 0.3856          |
| 0.3748        | 2.2007  | 6919  | 0.3751          |
| 0.3604        | 2.4008  | 7548  | 0.3739          |
| 0.3583        | 2.6008  | 8177  | 0.3759          |
| 0.3624        | 2.8009  | 8806  | 0.3687          |
| 0.3592        | 3.0010  | 9435  | 0.3655          |
| 0.3278        | 3.2010  | 10064 | 0.3649          |
| 0.3336        | 3.4011  | 10693 | 0.3591          |
| 0.3326        | 3.6011  | 11322 | 0.3517          |
| 0.3307        | 3.8012  | 11951 | 0.3525          |
| 0.3311        | 4.0013  | 12580 | 0.3459          |
| 0.3101        | 4.2013  | 13209 | 0.3513          |
| 0.3066        | 4.4014  | 13838 | 0.3417          |
| 0.3124        | 4.6015  | 14467 | 0.3340          |
| 0.3047        | 4.8015  | 15096 | 0.3364          |
| 0.3077        | 5.0016  | 15725 | 0.3315          |
| 0.2902        | 5.2017  | 16354 | 0.3371          |
| 0.2832        | 5.4017  | 16983 | 0.3275          |
| 0.2843        | 5.6018  | 17612 | 0.3241          |
| 0.2858        | 5.8018  | 18241 | 0.3213          |
| 0.2872        | 6.0019  | 18870 | 0.3226          |
| 0.2746        | 6.2020  | 19499 | 0.3203          |
| 0.2627        | 6.4020  | 20128 | 0.3212          |
| 0.2617        | 6.6021  | 20757 | 0.3182          |
| 0.2604        | 6.8022  | 21386 | 0.3146          |
| 0.2684        | 7.0022  | 22015 | 0.3094          |
| 0.2356        | 7.2023  | 22644 | 0.3170          |
| 0.2372        | 7.4024  | 23273 | 0.3104          |
| 0.2414        | 7.6024  | 23902 | 0.3101          |
| 0.2411        | 7.8025  | 24531 | 0.3112          |
| 0.2397        | 8.0025  | 25160 | 0.3114          |
| 0.2185        | 8.2026  | 25789 | 0.3119          |
| 0.2157        | 8.4027  | 26418 | 0.3083          |
| 0.2205        | 8.6027  | 27047 | 0.3015          |
| 0.2188        | 8.8028  | 27676 | 0.2993          |
| 0.2219        | 9.0029  | 28305 | 0.3015          |
| 0.2087        | 9.2029  | 28934 | 0.3043          |
| 0.1966        | 9.4030  | 29563 | 0.3016          |
| 0.1978        | 9.6031  | 30192 | 0.3075          |
| 0.1976        | 9.8031  | 30821 | 0.3023          |
| 0.1979        | 10.0032 | 31450 | 0.3014          |
| 0.1738        | 10.2032 | 32079 | 0.3083          |
| 0.1765        | 10.4033 | 32708 | 0.3082          |
| 0.1764        | 10.6034 | 33337 | 0.3063          |
| 0.1774        | 10.8034 | 33966 | 0.3065          |
| 0.1761        | 11.0035 | 34595 | 0.3052          |
| 0.161         | 11.2036 | 35224 | 0.3102          |
| 0.1584        | 11.4036 | 35853 | 0.3082          |
| 0.1583        | 11.6037 | 36482 | 0.3101          |
| 0.1573        | 11.8038 | 37111 | 0.3105          |


### Framework versions

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