---
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_lemma_command_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-task1-min_symbols_lemma_command_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: 0.5344

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.8566        | 0.2001  | 629   | 0.7667          |
| 0.7528        | 0.4001  | 1258  | 0.7298          |
| 0.7249        | 0.6002  | 1887  | 0.6923          |
| 0.6818        | 0.8003  | 2516  | 0.6711          |
| 0.6704        | 1.0003  | 3145  | 0.6628          |
| 0.634         | 1.2004  | 3774  | 0.6499          |
| 0.624         | 1.4004  | 4403  | 0.6382          |
| 0.6095        | 1.6005  | 5032  | 0.6322          |
| 0.6141        | 1.8006  | 5661  | 0.6245          |
| 0.6067        | 2.0006  | 6290  | 0.6177          |
| 0.5957        | 2.2007  | 6919  | 0.6074          |
| 0.5754        | 2.4008  | 7548  | 0.6158          |
| 0.5699        | 2.6008  | 8177  | 0.6045          |
| 0.576         | 2.8009  | 8806  | 0.6049          |
| 0.5713        | 3.0010  | 9435  | 0.5948          |
| 0.5298        | 3.2010  | 10064 | 0.5902          |
| 0.5411        | 3.4011  | 10693 | 0.5856          |
| 0.5377        | 3.6011  | 11322 | 0.5857          |
| 0.5387        | 3.8012  | 11951 | 0.5770          |
| 0.5334        | 4.0013  | 12580 | 0.5752          |
| 0.5052        | 4.2013  | 13209 | 0.5729          |
| 0.4976        | 4.4014  | 13838 | 0.5732          |
| 0.5091        | 4.6015  | 14467 | 0.5684          |
| 0.5019        | 4.8015  | 15096 | 0.5618          |
| 0.513         | 5.0016  | 15725 | 0.5605          |
| 0.4797        | 5.2017  | 16354 | 0.5728          |
| 0.4736        | 5.4017  | 16983 | 0.5593          |
| 0.4806        | 5.6018  | 17612 | 0.5633          |
| 0.4747        | 5.8018  | 18241 | 0.5611          |
| 0.4861        | 6.0019  | 18870 | 0.5459          |
| 0.4612        | 6.2020  | 19499 | 0.5555          |
| 0.444         | 6.4020  | 20128 | 0.5491          |
| 0.4413        | 6.6021  | 20757 | 0.5448          |
| 0.4481        | 6.8022  | 21386 | 0.5351          |
| 0.456         | 7.0022  | 22015 | 0.5412          |
| 0.4159        | 7.2023  | 22644 | 0.5415          |
| 0.4152        | 7.4024  | 23273 | 0.5381          |
| 0.422         | 7.6024  | 23902 | 0.5391          |
| 0.416         | 7.8025  | 24531 | 0.5359          |
| 0.4199        | 8.0025  | 25160 | 0.5295          |
| 0.3962        | 8.2026  | 25789 | 0.5408          |
| 0.3882        | 8.4027  | 26418 | 0.5318          |
| 0.3887        | 8.6027  | 27047 | 0.5306          |
| 0.3863        | 8.8028  | 27676 | 0.5246          |
| 0.3907        | 9.0029  | 28305 | 0.5309          |
| 0.3755        | 9.2029  | 28934 | 0.5318          |
| 0.3624        | 9.4030  | 29563 | 0.5293          |
| 0.359         | 9.6031  | 30192 | 0.5299          |
| 0.3612        | 9.8031  | 30821 | 0.5245          |
| 0.3612        | 10.0032 | 31450 | 0.5306          |
| 0.3345        | 10.2032 | 32079 | 0.5326          |
| 0.3327        | 10.4033 | 32708 | 0.5267          |
| 0.3369        | 10.6034 | 33337 | 0.5266          |
| 0.3353        | 10.8034 | 33966 | 0.5238          |
| 0.3304        | 11.0035 | 34595 | 0.5254          |
| 0.3132        | 11.2036 | 35224 | 0.5342          |
| 0.3082        | 11.4036 | 35853 | 0.5331          |
| 0.3088        | 11.6037 | 36482 | 0.5356          |
| 0.3125        | 11.8038 | 37111 | 0.5344          |


### Framework versions

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