|
|
--- |
|
|
library_name: peft |
|
|
license: other |
|
|
base_model: deepseek-ai/deepseek-coder-6.7b-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: lemexp-task1-v3-template_small_nodefs-deepseek-coder-6.7b-base |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# lemexp-task1-v3-template_small_nodefs-deepseek-coder-6.7b-base |
|
|
|
|
|
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1322 |
|
|
|
|
|
## 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 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 | |
|
|
|:-------------:|:-------:|:-----:|:---------------:| |
|
|
| 0.2967 | 0.2001 | 720 | 0.1984 | |
|
|
| 0.1959 | 0.4001 | 1440 | 0.1738 | |
|
|
| 0.1636 | 0.6002 | 2160 | 0.1623 | |
|
|
| 0.1539 | 0.8002 | 2880 | 0.1537 | |
|
|
| 0.1384 | 1.0003 | 3600 | 0.1512 | |
|
|
| 0.1317 | 1.2003 | 4320 | 0.1433 | |
|
|
| 0.1237 | 1.4004 | 5040 | 0.1368 | |
|
|
| 0.1174 | 1.6004 | 5760 | 0.1396 | |
|
|
| 0.1178 | 1.8005 | 6480 | 0.1316 | |
|
|
| 0.1134 | 2.0006 | 7200 | 0.1312 | |
|
|
| 0.1075 | 2.2006 | 7920 | 0.1269 | |
|
|
| 0.1018 | 2.4007 | 8640 | 0.1254 | |
|
|
| 0.1018 | 2.6007 | 9360 | 0.1270 | |
|
|
| 0.0931 | 2.8008 | 10080 | 0.1249 | |
|
|
| 0.0924 | 3.0008 | 10800 | 0.1218 | |
|
|
| 0.0897 | 3.2009 | 11520 | 0.1216 | |
|
|
| 0.0868 | 3.4009 | 12240 | 0.1241 | |
|
|
| 0.0865 | 3.6010 | 12960 | 0.1148 | |
|
|
| 0.084 | 3.8011 | 13680 | 0.1159 | |
|
|
| 0.0815 | 4.0011 | 14400 | 0.1176 | |
|
|
| 0.0753 | 4.2012 | 15120 | 0.1139 | |
|
|
| 0.0762 | 4.4012 | 15840 | 0.1140 | |
|
|
| 0.074 | 4.6013 | 16560 | 0.1131 | |
|
|
| 0.0732 | 4.8013 | 17280 | 0.1108 | |
|
|
| 0.0685 | 5.0014 | 18000 | 0.1152 | |
|
|
| 0.0655 | 5.2014 | 18720 | 0.1140 | |
|
|
| 0.0664 | 5.4015 | 19440 | 0.1120 | |
|
|
| 0.0648 | 5.6016 | 20160 | 0.1131 | |
|
|
| 0.063 | 5.8016 | 20880 | 0.1125 | |
|
|
| 0.0609 | 6.0017 | 21600 | 0.1141 | |
|
|
| 0.0576 | 6.2017 | 22320 | 0.1105 | |
|
|
| 0.0572 | 6.4018 | 23040 | 0.1143 | |
|
|
| 0.0554 | 6.6018 | 23760 | 0.1115 | |
|
|
| 0.0538 | 6.8019 | 24480 | 0.1113 | |
|
|
| 0.052 | 7.0019 | 25200 | 0.1132 | |
|
|
| 0.0498 | 7.2020 | 25920 | 0.1132 | |
|
|
| 0.0485 | 7.4021 | 26640 | 0.1115 | |
|
|
| 0.0483 | 7.6021 | 27360 | 0.1115 | |
|
|
| 0.0469 | 7.8022 | 28080 | 0.1126 | |
|
|
| 0.0443 | 8.0022 | 28800 | 0.1134 | |
|
|
| 0.0421 | 8.2023 | 29520 | 0.1150 | |
|
|
| 0.0411 | 8.4023 | 30240 | 0.1144 | |
|
|
| 0.0412 | 8.6024 | 30960 | 0.1117 | |
|
|
| 0.0391 | 8.8024 | 31680 | 0.1127 | |
|
|
| 0.0403 | 9.0025 | 32400 | 0.1162 | |
|
|
| 0.0354 | 9.2026 | 33120 | 0.1193 | |
|
|
| 0.0354 | 9.4026 | 33840 | 0.1218 | |
|
|
| 0.0352 | 9.6027 | 34560 | 0.1196 | |
|
|
| 0.0356 | 9.8027 | 35280 | 0.1236 | |
|
|
| 0.0331 | 10.0028 | 36000 | 0.1234 | |
|
|
| 0.032 | 10.2028 | 36720 | 0.1265 | |
|
|
| 0.0302 | 10.4029 | 37440 | 0.1289 | |
|
|
| 0.0301 | 10.6029 | 38160 | 0.1280 | |
|
|
| 0.0295 | 10.8030 | 38880 | 0.1259 | |
|
|
| 0.028 | 11.0031 | 39600 | 0.1295 | |
|
|
| 0.0274 | 11.2031 | 40320 | 0.1308 | |
|
|
| 0.0271 | 11.4032 | 41040 | 0.1309 | |
|
|
| 0.0267 | 11.6032 | 41760 | 0.1339 | |
|
|
| 0.0259 | 11.8033 | 42480 | 0.1322 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.14.0 |
|
|
- Transformers 4.47.0 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.1 |
