lemexp-task1-v3-template_small_notypes-deepseek-coder-1.3b-base-8lr-12epochs-special-eos
This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1759
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_FUSED 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 |
|---|---|---|---|
| 0.4261 | 0.2001 | 720 | 0.3401 |
| 0.3251 | 0.4001 | 1440 | 0.3158 |
| 0.2838 | 0.6002 | 2160 | 0.2862 |
| 0.2739 | 0.8002 | 2880 | 0.2687 |
| 0.2594 | 1.0003 | 3600 | 0.2624 |
| 0.247 | 1.2003 | 4320 | 0.2717 |
| 0.2419 | 1.4004 | 5040 | 0.2542 |
| 0.2364 | 1.6004 | 5760 | 0.2456 |
| 0.2368 | 1.8005 | 6480 | 0.2427 |
| 0.2307 | 2.0006 | 7200 | 0.2357 |
| 0.2187 | 2.2006 | 7920 | 0.2322 |
| 0.216 | 2.4007 | 8640 | 0.2319 |
| 0.211 | 2.6007 | 9360 | 0.2258 |
| 0.2109 | 2.8008 | 10080 | 0.2254 |
| 0.2133 | 3.0008 | 10800 | 0.2257 |
| 0.1972 | 3.2009 | 11520 | 0.2263 |
| 0.1984 | 3.4009 | 12240 | 0.2151 |
| 0.1941 | 3.6010 | 12960 | 0.2183 |
| 0.193 | 3.8011 | 13680 | 0.2138 |
| 0.194 | 4.0011 | 14400 | 0.2209 |
| 0.1792 | 4.2012 | 15120 | 0.2142 |
| 0.1812 | 4.4012 | 15840 | 0.2011 |
| 0.1777 | 4.6013 | 16560 | 0.2070 |
| 0.1785 | 4.8013 | 17280 | 0.1996 |
| 0.1736 | 5.0014 | 18000 | 0.1980 |
| 0.1651 | 5.2014 | 18720 | 0.2003 |
| 0.1645 | 5.4015 | 19440 | 0.1971 |
| 0.1656 | 5.6016 | 20160 | 0.1949 |
| 0.1653 | 5.8016 | 20880 | 0.1935 |
| 0.1602 | 6.0017 | 21600 | 0.1880 |
| 0.1523 | 6.2017 | 22320 | 0.1892 |
| 0.1516 | 6.4018 | 23040 | 0.1893 |
| 0.1501 | 6.6018 | 23760 | 0.1860 |
| 0.1493 | 6.8019 | 24480 | 0.1836 |
| 0.1476 | 7.0019 | 25200 | 0.1772 |
| 0.137 | 7.2020 | 25920 | 0.1853 |
| 0.136 | 7.4021 | 26640 | 0.1819 |
| 0.1375 | 7.6021 | 27360 | 0.1782 |
| 0.1338 | 7.8022 | 28080 | 0.1764 |
| 0.1352 | 8.0022 | 28800 | 0.1740 |
| 0.1215 | 8.2023 | 29520 | 0.1781 |
| 0.1198 | 8.4023 | 30240 | 0.1706 |
| 0.122 | 8.6024 | 30960 | 0.1725 |
| 0.1208 | 8.8024 | 31680 | 0.1693 |
| 0.1206 | 9.0025 | 32400 | 0.1683 |
| 0.1061 | 9.2026 | 33120 | 0.1691 |
| 0.1077 | 9.4026 | 33840 | 0.1681 |
| 0.108 | 9.6027 | 34560 | 0.1714 |
| 0.1074 | 9.8027 | 35280 | 0.1656 |
| 0.1027 | 10.0028 | 36000 | 0.1707 |
| 0.092 | 10.2028 | 36720 | 0.1745 |
| 0.0915 | 10.4029 | 37440 | 0.1685 |
| 0.0921 | 10.6029 | 38160 | 0.1727 |
| 0.0914 | 10.8030 | 38880 | 0.1704 |
| 0.0916 | 11.0031 | 39600 | 0.1681 |
| 0.0819 | 11.2031 | 40320 | 0.1754 |
| 0.081 | 11.4032 | 41040 | 0.1750 |
| 0.0797 | 11.6032 | 41760 | 0.1753 |
| 0.0794 | 11.8033 | 42480 | 0.1759 |
Framework versions
- PEFT 0.14.0
- Transformers 4.57.0
- Pytorch 2.8.0+cu128
- Datasets 4.2.0
- Tokenizers 0.22.1
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for yalhessi/lemexp-task1-v3-template_small_notypes-deepseek-coder-1.3b-base-8lr-12epochs-special-eos
Base model
deepseek-ai/deepseek-coder-1.3b-base