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-deepseek-coder-1.3b-base-ddp-8lr-v2
results: []
lemexp-task1-v2-lemma_object_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: 0.2306
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 |
|---|---|---|---|
| 0.5613 | 0.2002 | 721 | 0.4284 |
| 0.44 | 0.4003 | 1442 | 0.3884 |
| 0.3929 | 0.6005 | 2163 | 0.3794 |
| 0.3803 | 0.8007 | 2884 | 0.3589 |
| 0.3646 | 1.0008 | 3605 | 0.3492 |
| 0.3378 | 1.2010 | 4326 | 0.3442 |
| 0.3317 | 1.4012 | 5047 | 0.3342 |
| 0.3256 | 1.6013 | 5768 | 0.3264 |
| 0.3268 | 1.8015 | 6489 | 0.3211 |
| 0.321 | 2.0017 | 7210 | 0.3174 |
| 0.3037 | 2.2018 | 7931 | 0.3149 |
| 0.2988 | 2.4020 | 8652 | 0.3114 |
| 0.2979 | 2.6022 | 9373 | 0.3003 |
| 0.2939 | 2.8023 | 10094 | 0.2976 |
| 0.2943 | 3.0025 | 10815 | 0.2961 |
| 0.2702 | 3.2027 | 11536 | 0.2882 |
| 0.2703 | 3.4028 | 12257 | 0.2930 |
| 0.2699 | 3.6030 | 12978 | 0.2876 |
| 0.2723 | 3.8032 | 13699 | 0.2836 |
| 0.2698 | 4.0033 | 14420 | 0.2837 |
| 0.2479 | 4.2035 | 15141 | 0.2796 |
| 0.2487 | 4.4037 | 15862 | 0.2793 |
| 0.2482 | 4.6038 | 16583 | 0.2768 |
| 0.2501 | 4.8040 | 17304 | 0.2705 |
| 0.2494 | 5.0042 | 18025 | 0.2723 |
| 0.2255 | 5.2043 | 18746 | 0.2666 |
| 0.2274 | 5.4045 | 19467 | 0.2644 |
| 0.2272 | 5.6047 | 20188 | 0.2639 |
| 0.2293 | 5.8048 | 20909 | 0.2590 |
| 0.2301 | 6.0050 | 21630 | 0.2586 |
| 0.2099 | 6.2052 | 22351 | 0.2625 |
| 0.2087 | 6.4053 | 23072 | 0.2579 |
| 0.2085 | 6.6055 | 23793 | 0.2506 |
| 0.2106 | 6.8057 | 24514 | 0.2453 |
| 0.2088 | 7.0058 | 25235 | 0.2545 |
| 0.1949 | 7.2060 | 25956 | 0.2471 |
| 0.1912 | 7.4062 | 26677 | 0.2481 |
| 0.1906 | 7.6063 | 27398 | 0.2416 |
| 0.1885 | 7.8065 | 28119 | 0.2388 |
| 0.1882 | 8.0067 | 28840 | 0.2396 |
| 0.1676 | 8.2068 | 29561 | 0.2385 |
| 0.1707 | 8.4070 | 30282 | 0.2383 |
| 0.1715 | 8.6072 | 31003 | 0.2320 |
| 0.1717 | 8.8073 | 31724 | 0.2337 |
| 0.1679 | 9.0075 | 32445 | 0.2362 |
| 0.1484 | 9.2077 | 33166 | 0.2344 |
| 0.1492 | 9.4078 | 33887 | 0.2308 |
| 0.1513 | 9.6080 | 34608 | 0.2321 |
| 0.1528 | 9.8082 | 35329 | 0.2307 |
| 0.1507 | 10.0083 | 36050 | 0.2289 |
| 0.1319 | 10.2085 | 36771 | 0.2332 |
| 0.131 | 10.4087 | 37492 | 0.2262 |
| 0.1328 | 10.6088 | 38213 | 0.2263 |
| 0.1333 | 10.8090 | 38934 | 0.2260 |
| 0.1311 | 11.0092 | 39655 | 0.2293 |
| 0.1207 | 11.2093 | 40376 | 0.2344 |
| 0.1169 | 11.4095 | 41097 | 0.2312 |
| 0.1184 | 11.6097 | 41818 | 0.2318 |
| 0.1175 | 11.8098 | 42539 | 0.2306 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0