|
|
--- |
|
|
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-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-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: 0.1445 |
|
|
|
|
|
## 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: 2 |
|
|
- eval_batch_size: 2 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 4 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- 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 | |
|
|
|:-------------:|:-------:|:-----:|:---------------:| |
|
|
| 0.6105 | 0.2001 | 720 | 0.1979 | |
|
|
| 0.3924 | 0.4002 | 1440 | 0.1762 | |
|
|
| 0.3264 | 0.6003 | 2160 | 0.1657 | |
|
|
| 0.3094 | 0.8003 | 2880 | 0.1514 | |
|
|
| 0.2879 | 1.0003 | 3600 | 0.1473 | |
|
|
| 0.2563 | 1.2004 | 4320 | 0.1422 | |
|
|
| 0.2479 | 1.4004 | 5040 | 0.1370 | |
|
|
| 0.2451 | 1.6005 | 5760 | 0.1394 | |
|
|
| 0.2413 | 1.8006 | 6480 | 0.1315 | |
|
|
| 0.2317 | 2.0006 | 7200 | 0.1288 | |
|
|
| 0.2101 | 2.2006 | 7920 | 0.1282 | |
|
|
| 0.2039 | 2.4007 | 8640 | 0.1231 | |
|
|
| 0.2006 | 2.6008 | 9360 | 0.1211 | |
|
|
| 0.2003 | 2.8009 | 10080 | 0.1172 | |
|
|
| 0.2044 | 3.0008 | 10800 | 0.1192 | |
|
|
| 0.1712 | 3.2009 | 11520 | 0.1202 | |
|
|
| 0.1762 | 3.4010 | 12240 | 0.1164 | |
|
|
| 0.1732 | 3.6011 | 12960 | 0.1136 | |
|
|
| 0.1731 | 3.8012 | 13680 | 0.1141 | |
|
|
| 0.1723 | 4.0011 | 14400 | 0.1121 | |
|
|
| 0.1466 | 4.2012 | 15120 | 0.1163 | |
|
|
| 0.1491 | 4.4013 | 15840 | 0.1121 | |
|
|
| 0.1485 | 4.6014 | 16560 | 0.1144 | |
|
|
| 0.1515 | 4.8014 | 17280 | 0.1088 | |
|
|
| 0.1496 | 5.0014 | 18000 | 0.1089 | |
|
|
| 0.1261 | 5.2015 | 18720 | 0.1125 | |
|
|
| 0.1281 | 5.4016 | 19440 | 0.1087 | |
|
|
| 0.1308 | 5.6016 | 20160 | 0.1090 | |
|
|
| 0.1319 | 5.8017 | 20880 | 0.1106 | |
|
|
| 0.13 | 6.0017 | 21600 | 0.1058 | |
|
|
| 0.1119 | 6.2018 | 22320 | 0.1176 | |
|
|
| 0.1134 | 6.4018 | 23040 | 0.1124 | |
|
|
| 0.1133 | 6.6019 | 23760 | 0.1133 | |
|
|
| 0.1141 | 6.8020 | 24480 | 0.1135 | |
|
|
| 0.1134 | 7.0019 | 25200 | 0.1110 | |
|
|
| 0.1 | 7.2020 | 25920 | 0.1170 | |
|
|
| 0.0964 | 7.4021 | 26640 | 0.1099 | |
|
|
| 0.0986 | 7.6022 | 27360 | 0.1141 | |
|
|
| 0.0984 | 7.8023 | 28080 | 0.1096 | |
|
|
| 0.0992 | 8.0022 | 28800 | 0.1101 | |
|
|
| 0.0832 | 8.2023 | 29520 | 0.1185 | |
|
|
| 0.0808 | 8.4024 | 30240 | 0.1157 | |
|
|
| 0.0837 | 8.6025 | 30960 | 0.1191 | |
|
|
| 0.0845 | 8.8026 | 31680 | 0.1213 | |
|
|
| 0.0834 | 9.0025 | 32400 | 0.1222 | |
|
|
| 0.0703 | 9.2026 | 33120 | 0.1285 | |
|
|
| 0.0714 | 9.4027 | 33840 | 0.1220 | |
|
|
| 0.0725 | 9.6028 | 34560 | 0.1245 | |
|
|
| 0.0742 | 9.8028 | 35280 | 0.1253 | |
|
|
| 0.0709 | 10.0028 | 36000 | 0.1231 | |
|
|
| 0.0618 | 10.2029 | 36720 | 0.1325 | |
|
|
| 0.0611 | 10.4029 | 37440 | 0.1318 | |
|
|
| 0.0621 | 10.6030 | 38160 | 0.1354 | |
|
|
| 0.062 | 10.8031 | 38880 | 0.1352 | |
|
|
| 0.063 | 11.0031 | 39600 | 0.1332 | |
|
|
| 0.0554 | 11.2031 | 40320 | 0.1455 | |
|
|
| 0.0552 | 11.4032 | 41040 | 0.1436 | |
|
|
| 0.0546 | 11.6033 | 41760 | 0.1423 | |
|
|
| 0.0552 | 11.8034 | 42480 | 0.1445 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.14.0 |
|
|
- Transformers 4.47.0 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.1 |
