|
|
--- |
|
|
library_name: peft |
|
|
license: other |
|
|
base_model: deepseek-ai/deepseek-coder-1.3b-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: lemexp-task4-v2-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-task4-v2-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: 0.0416 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-------:|:-----:|:---------------:| |
|
|
| 0.1561 | 0.2001 | 720 | 0.0861 | |
|
|
| 0.0845 | 0.4001 | 1440 | 0.0716 | |
|
|
| 0.0724 | 0.6002 | 2160 | 0.0636 | |
|
|
| 0.07 | 0.8002 | 2880 | 0.0615 | |
|
|
| 0.0654 | 1.0003 | 3600 | 0.0629 | |
|
|
| 0.0636 | 1.2003 | 4320 | 0.0623 | |
|
|
| 0.0631 | 1.4004 | 5040 | 0.0600 | |
|
|
| 0.0626 | 1.6004 | 5760 | 0.0609 | |
|
|
| 0.0631 | 1.8005 | 6480 | 0.0562 | |
|
|
| 0.061 | 2.0006 | 7200 | 0.0559 | |
|
|
| 0.0597 | 2.2006 | 7920 | 0.0585 | |
|
|
| 0.0591 | 2.4007 | 8640 | 0.0543 | |
|
|
| 0.0553 | 2.6007 | 9360 | 0.0566 | |
|
|
| 0.0572 | 2.8008 | 10080 | 0.0528 | |
|
|
| 0.058 | 3.0008 | 10800 | 0.0504 | |
|
|
| 0.0543 | 3.2009 | 11520 | 0.0512 | |
|
|
| 0.054 | 3.4009 | 12240 | 0.0537 | |
|
|
| 0.0554 | 3.6010 | 12960 | 0.0520 | |
|
|
| 0.0532 | 3.8011 | 13680 | 0.0520 | |
|
|
| 0.0551 | 4.0011 | 14400 | 0.0513 | |
|
|
| 0.0514 | 4.2012 | 15120 | 0.0527 | |
|
|
| 0.0525 | 4.4012 | 15840 | 0.0498 | |
|
|
| 0.0509 | 4.6013 | 16560 | 0.0491 | |
|
|
| 0.0519 | 4.8013 | 17280 | 0.0501 | |
|
|
| 0.0519 | 5.0014 | 18000 | 0.0497 | |
|
|
| 0.0503 | 5.2014 | 18720 | 0.0496 | |
|
|
| 0.0489 | 5.4015 | 19440 | 0.0523 | |
|
|
| 0.05 | 5.6016 | 20160 | 0.0478 | |
|
|
| 0.0508 | 5.8016 | 20880 | 0.0467 | |
|
|
| 0.047 | 6.0017 | 21600 | 0.0471 | |
|
|
| 0.0477 | 6.2017 | 22320 | 0.0472 | |
|
|
| 0.0469 | 6.4018 | 23040 | 0.0474 | |
|
|
| 0.0484 | 6.6018 | 23760 | 0.0459 | |
|
|
| 0.0478 | 6.8019 | 24480 | 0.0453 | |
|
|
| 0.0472 | 7.0019 | 25200 | 0.0460 | |
|
|
| 0.0459 | 7.2020 | 25920 | 0.0446 | |
|
|
| 0.0454 | 7.4021 | 26640 | 0.0443 | |
|
|
| 0.0454 | 7.6021 | 27360 | 0.0461 | |
|
|
| 0.0453 | 7.8022 | 28080 | 0.0455 | |
|
|
| 0.0453 | 8.0022 | 28800 | 0.0439 | |
|
|
| 0.0449 | 8.2023 | 29520 | 0.0437 | |
|
|
| 0.0447 | 8.4023 | 30240 | 0.0429 | |
|
|
| 0.0446 | 8.6024 | 30960 | 0.0427 | |
|
|
| 0.0437 | 8.8024 | 31680 | 0.0441 | |
|
|
| 0.0437 | 9.0025 | 32400 | 0.0434 | |
|
|
| 0.0428 | 9.2026 | 33120 | 0.0426 | |
|
|
| 0.0431 | 9.4026 | 33840 | 0.0417 | |
|
|
| 0.0428 | 9.6027 | 34560 | 0.0421 | |
|
|
| 0.0428 | 9.8027 | 35280 | 0.0422 | |
|
|
| 0.0424 | 10.0028 | 36000 | 0.0425 | |
|
|
| 0.0422 | 10.2028 | 36720 | 0.0423 | |
|
|
| 0.042 | 10.4029 | 37440 | 0.0424 | |
|
|
| 0.0417 | 10.6029 | 38160 | 0.0419 | |
|
|
| 0.0414 | 10.8030 | 38880 | 0.0424 | |
|
|
| 0.0413 | 11.0031 | 39600 | 0.0417 | |
|
|
| 0.0415 | 11.2031 | 40320 | 0.0415 | |
|
|
| 0.0413 | 11.4032 | 41040 | 0.0418 | |
|
|
| 0.0412 | 11.6032 | 41760 | 0.0418 | |
|
|
| 0.0412 | 11.8033 | 42480 | 0.0416 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.14.0 |
|
|
- Transformers 4.47.0 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
