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-lemma_object_small_nodefs-deepseek-coder-1.3b-base-ddp-8lr-v2
results: []
lemexp-task1-v2-lemma_object_small_nodefs-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: 0.2373
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 |
|---|---|---|---|
| 0.6444 | 0.2002 | 721 | 0.4798 |
| 0.4987 | 0.4003 | 1442 | 0.4339 |
| 0.4324 | 0.6005 | 2163 | 0.4100 |
| 0.4155 | 0.8007 | 2884 | 0.3960 |
| 0.3968 | 1.0008 | 3605 | 0.3739 |
| 0.3645 | 1.2010 | 4326 | 0.3639 |
| 0.3602 | 1.4012 | 5047 | 0.3606 |
| 0.3492 | 1.6013 | 5768 | 0.3542 |
| 0.35 | 1.8015 | 6489 | 0.3530 |
| 0.3443 | 2.0017 | 7210 | 0.3420 |
| 0.3249 | 2.2018 | 7931 | 0.3301 |
| 0.3189 | 2.4020 | 8652 | 0.3317 |
| 0.3161 | 2.6022 | 9373 | 0.3218 |
| 0.3131 | 2.8023 | 10094 | 0.3158 |
| 0.3138 | 3.0025 | 10815 | 0.3144 |
| 0.2886 | 3.2027 | 11536 | 0.3112 |
| 0.287 | 3.4028 | 12257 | 0.3085 |
| 0.2864 | 3.6030 | 12978 | 0.3042 |
| 0.2884 | 3.8032 | 13699 | 0.3027 |
| 0.2845 | 4.0033 | 14420 | 0.2965 |
| 0.263 | 4.2035 | 15141 | 0.3005 |
| 0.264 | 4.4037 | 15862 | 0.2947 |
| 0.2635 | 4.6038 | 16583 | 0.2897 |
| 0.2632 | 4.8040 | 17304 | 0.2893 |
| 0.2634 | 5.0042 | 18025 | 0.2822 |
| 0.2368 | 5.2043 | 18746 | 0.2793 |
| 0.2398 | 5.4045 | 19467 | 0.2769 |
| 0.2407 | 5.6047 | 20188 | 0.2768 |
| 0.2407 | 5.8048 | 20909 | 0.2750 |
| 0.2436 | 6.0050 | 21630 | 0.2741 |
| 0.2219 | 6.2052 | 22351 | 0.2738 |
| 0.2214 | 6.4053 | 23072 | 0.2717 |
| 0.2203 | 6.6055 | 23793 | 0.2673 |
| 0.2219 | 6.8057 | 24514 | 0.2632 |
| 0.2199 | 7.0058 | 25235 | 0.2589 |
| 0.206 | 7.2060 | 25956 | 0.2633 |
| 0.2011 | 7.4062 | 26677 | 0.2573 |
| 0.1998 | 7.6063 | 27398 | 0.2537 |
| 0.2006 | 7.8065 | 28119 | 0.2566 |
| 0.1998 | 8.0067 | 28840 | 0.2525 |
| 0.1772 | 8.2068 | 29561 | 0.2509 |
| 0.181 | 8.4070 | 30282 | 0.2532 |
| 0.1808 | 8.6072 | 31003 | 0.2462 |
| 0.1801 | 8.8073 | 31724 | 0.2481 |
| 0.1794 | 9.0075 | 32445 | 0.2442 |
| 0.1568 | 9.2077 | 33166 | 0.2456 |
| 0.1575 | 9.4078 | 33887 | 0.2464 |
| 0.1599 | 9.6080 | 34608 | 0.2442 |
| 0.1619 | 9.8082 | 35329 | 0.2387 |
| 0.1589 | 10.0083 | 36050 | 0.2361 |
| 0.1407 | 10.2085 | 36771 | 0.2423 |
| 0.1387 | 10.4087 | 37492 | 0.2410 |
| 0.1407 | 10.6088 | 38213 | 0.2356 |
| 0.1413 | 10.8090 | 38934 | 0.2370 |
| 0.1384 | 11.0092 | 39655 | 0.2396 |
| 0.1267 | 11.2093 | 40376 | 0.2388 |
| 0.1238 | 11.4095 | 41097 | 0.2397 |
| 0.1259 | 11.6097 | 41818 | 0.2361 |
| 0.1249 | 11.8098 | 42539 | 0.2373 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0