|
|
--- |
|
|
library_name: peft |
|
|
license: other |
|
|
base_model: deepseek-ai/deepseek-coder-1.3b-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: lemexp-task1-v2-template_small-deepseek-coder-1.3b-base-ddp-12lr-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-template_small-deepseek-coder-1.3b-base-ddp-12lr-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: 0.1541 |
|
|
|
|
|
## 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: 0.0012 |
|
|
- 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 | |
|
|
|:-------------:|:-------:|:-----:|:---------------:| |
|
|
| 0.3986 | 0.2001 | 720 | 0.3279 | |
|
|
| 0.3106 | 0.4001 | 1440 | 0.2887 | |
|
|
| 0.2816 | 0.6002 | 2160 | 0.2783 | |
|
|
| 0.2741 | 0.8002 | 2880 | 0.2706 | |
|
|
| 0.2644 | 1.0003 | 3600 | 0.2729 | |
|
|
| 0.2559 | 1.2003 | 4320 | 0.2616 | |
|
|
| 0.2526 | 1.4004 | 5040 | 0.2572 | |
|
|
| 0.248 | 1.6004 | 5760 | 0.2575 | |
|
|
| 0.2467 | 1.8005 | 6480 | 0.2575 | |
|
|
| 0.2414 | 2.0006 | 7200 | 0.2458 | |
|
|
| 0.2347 | 2.2006 | 7920 | 0.2465 | |
|
|
| 0.2335 | 2.4007 | 8640 | 0.2434 | |
|
|
| 0.2304 | 2.6007 | 9360 | 0.2338 | |
|
|
| 0.2273 | 2.8008 | 10080 | 0.2284 | |
|
|
| 0.2272 | 3.0008 | 10800 | 0.2300 | |
|
|
| 0.2176 | 3.2009 | 11520 | 0.2303 | |
|
|
| 0.2208 | 3.4009 | 12240 | 0.2261 | |
|
|
| 0.2142 | 3.6010 | 12960 | 0.2264 | |
|
|
| 0.2121 | 3.8011 | 13680 | 0.2194 | |
|
|
| 0.2111 | 4.0011 | 14400 | 0.2199 | |
|
|
| 0.203 | 4.2012 | 15120 | 0.2156 | |
|
|
| 0.2029 | 4.4012 | 15840 | 0.2122 | |
|
|
| 0.1986 | 4.6013 | 16560 | 0.2297 | |
|
|
| 0.1994 | 4.8013 | 17280 | 0.2142 | |
|
|
| 0.1958 | 5.0014 | 18000 | 0.2057 | |
|
|
| 0.1865 | 5.2014 | 18720 | 0.2046 | |
|
|
| 0.1858 | 5.4015 | 19440 | 0.2081 | |
|
|
| 0.1862 | 5.6016 | 20160 | 0.2052 | |
|
|
| 0.1864 | 5.8016 | 20880 | 0.1912 | |
|
|
| 0.1798 | 6.0017 | 21600 | 0.1945 | |
|
|
| 0.173 | 6.2017 | 22320 | 0.1919 | |
|
|
| 0.1732 | 6.4018 | 23040 | 0.1874 | |
|
|
| 0.1704 | 6.6018 | 23760 | 0.1858 | |
|
|
| 0.1704 | 6.8019 | 24480 | 0.1879 | |
|
|
| 0.1669 | 7.0019 | 25200 | 0.1847 | |
|
|
| 0.1602 | 7.2020 | 25920 | 0.1802 | |
|
|
| 0.1575 | 7.4021 | 26640 | 0.1825 | |
|
|
| 0.1568 | 7.6021 | 27360 | 0.1821 | |
|
|
| 0.154 | 7.8022 | 28080 | 0.1738 | |
|
|
| 0.1547 | 8.0022 | 28800 | 0.1749 | |
|
|
| 0.144 | 8.2023 | 29520 | 0.1749 | |
|
|
| 0.1413 | 8.4023 | 30240 | 0.1703 | |
|
|
| 0.143 | 8.6024 | 30960 | 0.1714 | |
|
|
| 0.1396 | 8.8024 | 31680 | 0.1650 | |
|
|
| 0.1398 | 9.0025 | 32400 | 0.1690 | |
|
|
| 0.1274 | 9.2026 | 33120 | 0.1676 | |
|
|
| 0.1261 | 9.4026 | 33840 | 0.1638 | |
|
|
| 0.1274 | 9.6027 | 34560 | 0.1662 | |
|
|
| 0.1263 | 9.8027 | 35280 | 0.1579 | |
|
|
| 0.1224 | 10.0028 | 36000 | 0.1585 | |
|
|
| 0.1123 | 10.2028 | 36720 | 0.1597 | |
|
|
| 0.1114 | 10.4029 | 37440 | 0.1561 | |
|
|
| 0.1102 | 10.6029 | 38160 | 0.1574 | |
|
|
| 0.1095 | 10.8030 | 38880 | 0.1542 | |
|
|
| 0.1101 | 11.0031 | 39600 | 0.1520 | |
|
|
| 0.0992 | 11.2031 | 40320 | 0.1565 | |
|
|
| 0.0972 | 11.4032 | 41040 | 0.1554 | |
|
|
| 0.0957 | 11.6032 | 41760 | 0.1548 | |
|
|
| 0.0955 | 11.8033 | 42480 | 0.1541 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.14.0 |
|
|
- Transformers 4.47.0 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
