lemexp-task1-v3-lemma_object_full_nodefs-deepseek-coder-6.7b-base
This model is a fine-tuned version of deepseek-ai/deepseek-coder-6.7b-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1302
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: 0.0004
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 16
- total_eval_batch_size: 8
- 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 |
|---|---|---|---|
| 0.3108 | 0.2000 | 3114 | 0.3017 |
| 0.2685 | 0.4000 | 6228 | 0.2551 |
| 0.2493 | 0.6000 | 9342 | 0.2313 |
| 0.2335 | 0.8001 | 12456 | 0.2242 |
| 0.2223 | 1.0001 | 15570 | 0.2162 |
| 0.2042 | 1.2001 | 18684 | 0.2044 |
| 0.1984 | 1.4001 | 21798 | 0.1986 |
| 0.1993 | 1.6001 | 24912 | 0.1940 |
| 0.1931 | 1.8001 | 28026 | 0.1886 |
| 0.1887 | 2.0001 | 31140 | 0.1876 |
| 0.1712 | 2.2001 | 34254 | 0.1830 |
| 0.1751 | 2.4002 | 37368 | 0.1793 |
| 0.1714 | 2.6002 | 40482 | 0.1794 |
| 0.1736 | 2.8002 | 43596 | 0.1795 |
| 0.168 | 3.0002 | 46710 | 0.1722 |
| 0.1564 | 3.2002 | 49824 | 0.1717 |
| 0.156 | 3.4002 | 52938 | 0.1695 |
| 0.154 | 3.6002 | 56052 | 0.1673 |
| 0.1538 | 3.8002 | 59166 | 0.1666 |
| 0.1539 | 4.0003 | 62280 | 0.1657 |
| 0.1388 | 4.2003 | 65394 | 0.1624 |
| 0.1406 | 4.4003 | 68508 | 0.1634 |
| 0.1379 | 4.6003 | 71622 | 0.1573 |
| 0.1407 | 4.8003 | 74736 | 0.1580 |
| 0.1395 | 5.0003 | 77850 | 0.1577 |
| 0.1245 | 5.2003 | 80964 | 0.1550 |
| 0.1286 | 5.4003 | 84078 | 0.1559 |
| 0.1283 | 5.6004 | 87192 | 0.1521 |
| 0.1254 | 5.8004 | 90306 | 0.1480 |
| 0.1254 | 6.0004 | 93420 | 0.1445 |
| 0.1129 | 6.2004 | 96534 | 0.1441 |
| 0.1146 | 6.4004 | 99648 | 0.1441 |
| 0.1166 | 6.6004 | 102762 | 0.1420 |
| 0.1159 | 6.8004 | 105876 | 0.1436 |
| 0.1155 | 7.0004 | 108990 | 0.1407 |
| 0.1012 | 7.2005 | 112104 | 0.1419 |
| 0.0994 | 7.4005 | 115218 | 0.1419 |
| 0.1012 | 7.6005 | 118332 | 0.1383 |
| 0.1027 | 7.8005 | 121446 | 0.1381 |
| 0.1014 | 8.0005 | 124560 | 0.1354 |
| 0.0896 | 8.2005 | 127674 | 0.1385 |
| 0.0893 | 8.4005 | 130788 | 0.1377 |
| 0.0918 | 8.6006 | 133902 | 0.1349 |
| 0.0915 | 8.8006 | 137016 | 0.1312 |
| 0.0878 | 9.0006 | 140130 | 0.1323 |
| 0.0757 | 9.2006 | 143244 | 0.1349 |
| 0.0772 | 9.4006 | 146358 | 0.1326 |
| 0.0779 | 9.6006 | 149472 | 0.1308 |
| 0.0757 | 9.8006 | 152586 | 0.1293 |
| 0.0768 | 10.0006 | 155700 | 0.1298 |
| 0.0661 | 10.2007 | 158814 | 0.1355 |
| 0.0648 | 10.4007 | 161928 | 0.1330 |
| 0.0661 | 10.6007 | 165042 | 0.1313 |
| 0.0643 | 10.8007 | 168156 | 0.1283 |
| 0.0627 | 11.0007 | 171270 | 0.1300 |
| 0.0567 | 11.2007 | 174384 | 0.1335 |
| 0.0569 | 11.4007 | 177498 | 0.1327 |
| 0.0553 | 11.6007 | 180612 | 0.1323 |
| 0.0558 | 11.8008 | 183726 | 0.1302 |
Framework versions
- PEFT 0.17.1
- Transformers 4.55.4
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4
- Downloads last month
- 89
Model tree for yalhessi/lemexp-task1-v3-lemma_object_full_nodefs-deepseek-coder-6.7b-base
Base model
deepseek-ai/deepseek-coder-6.7b-base