|
|
--- |
|
|
library_name: peft |
|
|
license: other |
|
|
base_model: deepseek-ai/deepseek-coder-1.3b-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: lemexp-task3-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-task3-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: 0.1396 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-------:|:-----:|:---------------:| |
|
|
| 0.4251 | 0.2001 | 629 | 0.2945 | |
|
|
| 0.2993 | 0.4001 | 1258 | 0.2587 | |
|
|
| 0.2692 | 0.6002 | 1887 | 0.2363 | |
|
|
| 0.2389 | 0.8003 | 2516 | 0.2178 | |
|
|
| 0.2334 | 1.0003 | 3145 | 0.2135 | |
|
|
| 0.2119 | 1.2004 | 3774 | 0.2025 | |
|
|
| 0.2091 | 1.4004 | 4403 | 0.2047 | |
|
|
| 0.2026 | 1.6005 | 5032 | 0.1989 | |
|
|
| 0.2004 | 1.8006 | 5661 | 0.1933 | |
|
|
| 0.1976 | 2.0006 | 6290 | 0.1933 | |
|
|
| 0.1913 | 2.2007 | 6919 | 0.1899 | |
|
|
| 0.1821 | 2.4008 | 7548 | 0.1823 | |
|
|
| 0.1822 | 2.6008 | 8177 | 0.1871 | |
|
|
| 0.1825 | 2.8009 | 8806 | 0.1791 | |
|
|
| 0.1802 | 3.0010 | 9435 | 0.1806 | |
|
|
| 0.1659 | 3.2010 | 10064 | 0.1763 | |
|
|
| 0.1704 | 3.4011 | 10693 | 0.1771 | |
|
|
| 0.1655 | 3.6011 | 11322 | 0.1713 | |
|
|
| 0.1649 | 3.8012 | 11951 | 0.1692 | |
|
|
| 0.1641 | 4.0013 | 12580 | 0.1685 | |
|
|
| 0.1543 | 4.2013 | 13209 | 0.1706 | |
|
|
| 0.1532 | 4.4014 | 13838 | 0.1641 | |
|
|
| 0.1539 | 4.6015 | 14467 | 0.1616 | |
|
|
| 0.1513 | 4.8015 | 15096 | 0.1618 | |
|
|
| 0.1527 | 5.0016 | 15725 | 0.1629 | |
|
|
| 0.1436 | 5.2017 | 16354 | 0.1578 | |
|
|
| 0.14 | 5.4017 | 16983 | 0.1552 | |
|
|
| 0.1409 | 5.6018 | 17612 | 0.1557 | |
|
|
| 0.1408 | 5.8018 | 18241 | 0.1542 | |
|
|
| 0.1407 | 6.0019 | 18870 | 0.1519 | |
|
|
| 0.1338 | 6.2020 | 19499 | 0.1522 | |
|
|
| 0.1278 | 6.4020 | 20128 | 0.1498 | |
|
|
| 0.1305 | 6.6021 | 20757 | 0.1487 | |
|
|
| 0.127 | 6.8022 | 21386 | 0.1478 | |
|
|
| 0.1316 | 7.0022 | 22015 | 0.1451 | |
|
|
| 0.1159 | 7.2023 | 22644 | 0.1464 | |
|
|
| 0.1157 | 7.4024 | 23273 | 0.1445 | |
|
|
| 0.1198 | 7.6024 | 23902 | 0.1464 | |
|
|
| 0.1171 | 7.8025 | 24531 | 0.1426 | |
|
|
| 0.116 | 8.0025 | 25160 | 0.1395 | |
|
|
| 0.106 | 8.2026 | 25789 | 0.1414 | |
|
|
| 0.1051 | 8.4027 | 26418 | 0.1419 | |
|
|
| 0.1087 | 8.6027 | 27047 | 0.1403 | |
|
|
| 0.1073 | 8.8028 | 27676 | 0.1420 | |
|
|
| 0.1093 | 9.0029 | 28305 | 0.1403 | |
|
|
| 0.1027 | 9.2029 | 28934 | 0.1397 | |
|
|
| 0.0982 | 9.4030 | 29563 | 0.1386 | |
|
|
| 0.0968 | 9.6031 | 30192 | 0.1402 | |
|
|
| 0.0969 | 9.8031 | 30821 | 0.1380 | |
|
|
| 0.0972 | 10.0032 | 31450 | 0.1372 | |
|
|
| 0.0868 | 10.2032 | 32079 | 0.1404 | |
|
|
| 0.0893 | 10.4033 | 32708 | 0.1380 | |
|
|
| 0.0894 | 10.6034 | 33337 | 0.1363 | |
|
|
| 0.0883 | 10.8034 | 33966 | 0.1367 | |
|
|
| 0.0887 | 11.0035 | 34595 | 0.1388 | |
|
|
| 0.0831 | 11.2036 | 35224 | 0.1425 | |
|
|
| 0.0821 | 11.4036 | 35853 | 0.1399 | |
|
|
| 0.0822 | 11.6037 | 36482 | 0.1408 | |
|
|
| 0.0813 | 11.8038 | 37111 | 0.1396 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.14.0 |
|
|
- Transformers 4.47.0 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
