metadata
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-8lr-v2
results: []
lemexp-task1-v2-template_small-deepseek-coder-1.3b-base-ddp-8lr-v2
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: 0.1536
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 |
|---|---|---|---|
| 0.4023 | 0.2002 | 721 | 0.2979 |
| 0.2974 | 0.4003 | 1442 | 0.2705 |
| 0.2625 | 0.6005 | 2163 | 0.2579 |
| 0.2578 | 0.8007 | 2884 | 0.2518 |
| 0.2454 | 1.0008 | 3605 | 0.2368 |
| 0.2309 | 1.2010 | 4326 | 0.2288 |
| 0.228 | 1.4012 | 5047 | 0.2253 |
| 0.223 | 1.6013 | 5768 | 0.2217 |
| 0.2221 | 1.8015 | 6489 | 0.2268 |
| 0.2181 | 2.0017 | 7210 | 0.2157 |
| 0.2081 | 2.2018 | 7931 | 0.2147 |
| 0.2079 | 2.4020 | 8652 | 0.2112 |
| 0.204 | 2.6022 | 9373 | 0.2052 |
| 0.2019 | 2.8023 | 10094 | 0.2038 |
| 0.2002 | 3.0025 | 10815 | 0.2045 |
| 0.1909 | 3.2027 | 11536 | 0.1983 |
| 0.1883 | 3.4028 | 12257 | 0.1964 |
| 0.1874 | 3.6030 | 12978 | 0.2010 |
| 0.1858 | 3.8032 | 13699 | 0.1928 |
| 0.1859 | 4.0033 | 14420 | 0.1917 |
| 0.1738 | 4.2035 | 15141 | 0.1931 |
| 0.1734 | 4.4037 | 15862 | 0.1876 |
| 0.1738 | 4.6038 | 16583 | 0.1848 |
| 0.1746 | 4.8040 | 17304 | 0.1816 |
| 0.1728 | 5.0042 | 18025 | 0.1800 |
| 0.1601 | 5.2043 | 18746 | 0.1832 |
| 0.1612 | 5.4045 | 19467 | 0.1799 |
| 0.1594 | 5.6047 | 20188 | 0.1806 |
| 0.1598 | 5.8048 | 20909 | 0.1768 |
| 0.1595 | 6.0050 | 21630 | 0.1819 |
| 0.15 | 6.2052 | 22351 | 0.1725 |
| 0.1488 | 6.4053 | 23072 | 0.1727 |
| 0.1489 | 6.6055 | 23793 | 0.1706 |
| 0.1487 | 6.8057 | 24514 | 0.1700 |
| 0.1475 | 7.0058 | 25235 | 0.1676 |
| 0.1392 | 7.2060 | 25956 | 0.1658 |
| 0.1375 | 7.4062 | 26677 | 0.1641 |
| 0.1358 | 7.6063 | 27398 | 0.1639 |
| 0.1347 | 7.8065 | 28119 | 0.1613 |
| 0.135 | 8.0067 | 28840 | 0.1595 |
| 0.1223 | 8.2068 | 29561 | 0.1608 |
| 0.1239 | 8.4070 | 30282 | 0.1580 |
| 0.1224 | 8.6072 | 31003 | 0.1562 |
| 0.1234 | 8.8073 | 31724 | 0.1570 |
| 0.1224 | 9.0075 | 32445 | 0.1555 |
| 0.1094 | 9.2077 | 33166 | 0.1561 |
| 0.1088 | 9.4078 | 33887 | 0.1552 |
| 0.1106 | 9.6080 | 34608 | 0.1528 |
| 0.1097 | 9.8082 | 35329 | 0.1520 |
| 0.1101 | 10.0083 | 36050 | 0.1533 |
| 0.0971 | 10.2085 | 36771 | 0.1566 |
| 0.0965 | 10.4087 | 37492 | 0.1528 |
| 0.0975 | 10.6088 | 38213 | 0.1529 |
| 0.0975 | 10.8090 | 38934 | 0.1517 |
| 0.0963 | 11.0092 | 39655 | 0.1528 |
| 0.0887 | 11.2093 | 40376 | 0.1550 |
| 0.0868 | 11.4095 | 41097 | 0.1550 |
| 0.0874 | 11.6097 | 41818 | 0.1542 |
| 0.087 | 11.8098 | 42539 | 0.1536 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0