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_old_defs-deepseek-coder-1.3b-base-ddp-8lr-v2
results: []
lemexp-task1-v2-template_small_old_defs-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: 0.1510
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 |
|---|---|---|---|
| 0.425 | 0.2002 | 721 | 0.3080 |
| 0.3071 | 0.4003 | 1442 | 0.2725 |
| 0.2669 | 0.6005 | 2163 | 0.2568 |
| 0.2608 | 0.8007 | 2884 | 0.2484 |
| 0.2484 | 1.0008 | 3605 | 0.2393 |
| 0.2343 | 1.2010 | 4326 | 0.2373 |
| 0.2334 | 1.4012 | 5047 | 0.2319 |
| 0.2262 | 1.6013 | 5768 | 0.2233 |
| 0.2229 | 1.8015 | 6489 | 0.2282 |
| 0.2196 | 2.0017 | 7210 | 0.2183 |
| 0.2102 | 2.2018 | 7931 | 0.2168 |
| 0.2097 | 2.4020 | 8652 | 0.2109 |
| 0.2046 | 2.6022 | 9373 | 0.2026 |
| 0.2034 | 2.8023 | 10094 | 0.2002 |
| 0.2023 | 3.0025 | 10815 | 0.2004 |
| 0.1906 | 3.2027 | 11536 | 0.1974 |
| 0.1905 | 3.4028 | 12257 | 0.1967 |
| 0.1875 | 3.6030 | 12978 | 0.1944 |
| 0.1852 | 3.8032 | 13699 | 0.1932 |
| 0.1875 | 4.0033 | 14420 | 0.1944 |
| 0.1754 | 4.2035 | 15141 | 0.1863 |
| 0.175 | 4.4037 | 15862 | 0.1834 |
| 0.1747 | 4.6038 | 16583 | 0.1904 |
| 0.175 | 4.8040 | 17304 | 0.1841 |
| 0.1739 | 5.0042 | 18025 | 0.1820 |
| 0.1604 | 5.2043 | 18746 | 0.1812 |
| 0.1628 | 5.4045 | 19467 | 0.1794 |
| 0.1608 | 5.6047 | 20188 | 0.1802 |
| 0.161 | 5.8048 | 20909 | 0.1737 |
| 0.1596 | 6.0050 | 21630 | 0.1763 |
| 0.151 | 6.2052 | 22351 | 0.1731 |
| 0.1501 | 6.4053 | 23072 | 0.1703 |
| 0.1487 | 6.6055 | 23793 | 0.1684 |
| 0.149 | 6.8057 | 24514 | 0.1654 |
| 0.1474 | 7.0058 | 25235 | 0.1642 |
| 0.1389 | 7.2060 | 25956 | 0.1641 |
| 0.1387 | 7.4062 | 26677 | 0.1635 |
| 0.1361 | 7.6063 | 27398 | 0.1637 |
| 0.1357 | 7.8065 | 28119 | 0.1627 |
| 0.1358 | 8.0067 | 28840 | 0.1605 |
| 0.1225 | 8.2068 | 29561 | 0.1575 |
| 0.1245 | 8.4070 | 30282 | 0.1540 |
| 0.1232 | 8.6072 | 31003 | 0.1558 |
| 0.1238 | 8.8073 | 31724 | 0.1539 |
| 0.1231 | 9.0075 | 32445 | 0.1525 |
| 0.1094 | 9.2077 | 33166 | 0.1560 |
| 0.1091 | 9.4078 | 33887 | 0.1528 |
| 0.1105 | 9.6080 | 34608 | 0.1505 |
| 0.1101 | 9.8082 | 35329 | 0.1523 |
| 0.1106 | 10.0083 | 36050 | 0.1537 |
| 0.0975 | 10.2085 | 36771 | 0.1569 |
| 0.0963 | 10.4087 | 37492 | 0.1513 |
| 0.0981 | 10.6088 | 38213 | 0.1516 |
| 0.0966 | 10.8090 | 38934 | 0.1507 |
| 0.0959 | 11.0092 | 39655 | 0.1513 |
| 0.089 | 11.2093 | 40376 | 0.1534 |
| 0.0866 | 11.4095 | 41097 | 0.1549 |
| 0.0871 | 11.6097 | 41818 | 0.1522 |
| 0.0866 | 11.8098 | 42539 | 0.1510 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0