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: 0.2309
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 |
|---|---|---|---|
| 0.5603 | 0.2002 | 721 | 0.4280 |
| 0.4421 | 0.4003 | 1442 | 0.3964 |
| 0.3935 | 0.6005 | 2163 | 0.3718 |
| 0.3807 | 0.8007 | 2884 | 0.3598 |
| 0.3638 | 1.0008 | 3605 | 0.3509 |
| 0.3388 | 1.2010 | 4326 | 0.3377 |
| 0.3318 | 1.4012 | 5047 | 0.3292 |
| 0.3269 | 1.6013 | 5768 | 0.3266 |
| 0.3263 | 1.8015 | 6489 | 0.3187 |
| 0.321 | 2.0017 | 7210 | 0.3129 |
| 0.3035 | 2.2018 | 7931 | 0.3078 |
| 0.2986 | 2.4020 | 8652 | 0.3113 |
| 0.2983 | 2.6022 | 9373 | 0.3003 |
| 0.2932 | 2.8023 | 10094 | 0.2985 |
| 0.295 | 3.0025 | 10815 | 0.2942 |
| 0.2707 | 3.2027 | 11536 | 0.2922 |
| 0.2708 | 3.4028 | 12257 | 0.2888 |
| 0.2692 | 3.6030 | 12978 | 0.2862 |
| 0.2714 | 3.8032 | 13699 | 0.2828 |
| 0.2701 | 4.0033 | 14420 | 0.2790 |
| 0.2473 | 4.2035 | 15141 | 0.2722 |
| 0.2487 | 4.4037 | 15862 | 0.2764 |
| 0.2493 | 4.6038 | 16583 | 0.2731 |
| 0.2491 | 4.8040 | 17304 | 0.2675 |
| 0.2491 | 5.0042 | 18025 | 0.2660 |
| 0.2245 | 5.2043 | 18746 | 0.2611 |
| 0.2279 | 5.4045 | 19467 | 0.2609 |
| 0.2272 | 5.6047 | 20188 | 0.2658 |
| 0.2296 | 5.8048 | 20909 | 0.2536 |
| 0.2294 | 6.0050 | 21630 | 0.2581 |
| 0.2104 | 6.2052 | 22351 | 0.2542 |
| 0.2103 | 6.4053 | 23072 | 0.2537 |
| 0.2086 | 6.6055 | 23793 | 0.2543 |
| 0.2102 | 6.8057 | 24514 | 0.2465 |
| 0.209 | 7.0058 | 25235 | 0.2483 |
| 0.1947 | 7.2060 | 25956 | 0.2485 |
| 0.1927 | 7.4062 | 26677 | 0.2418 |
| 0.191 | 7.6063 | 27398 | 0.2384 |
| 0.1894 | 7.8065 | 28119 | 0.2394 |
| 0.1902 | 8.0067 | 28840 | 0.2380 |
| 0.1689 | 8.2068 | 29561 | 0.2367 |
| 0.1723 | 8.4070 | 30282 | 0.2346 |
| 0.1712 | 8.6072 | 31003 | 0.2330 |
| 0.1715 | 8.8073 | 31724 | 0.2308 |
| 0.1693 | 9.0075 | 32445 | 0.2356 |
| 0.1489 | 9.2077 | 33166 | 0.2351 |
| 0.15 | 9.4078 | 33887 | 0.2284 |
| 0.1519 | 9.6080 | 34608 | 0.2274 |
| 0.153 | 9.8082 | 35329 | 0.2283 |
| 0.1511 | 10.0083 | 36050 | 0.2318 |
| 0.1321 | 10.2085 | 36771 | 0.2320 |
| 0.1316 | 10.4087 | 37492 | 0.2287 |
| 0.1317 | 10.6088 | 38213 | 0.2290 |
| 0.1337 | 10.8090 | 38934 | 0.2251 |
| 0.1318 | 11.0092 | 39655 | 0.2285 |
| 0.1206 | 11.2093 | 40376 | 0.2307 |
| 0.1173 | 11.4095 | 41097 | 0.2312 |
| 0.1187 | 11.6097 | 41818 | 0.2321 |
| 0.1182 | 11.8098 | 42539 | 0.2309 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0