metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-0.5B
tags:
- generated_from_trainer
model-index:
- name: sparql-qwen
results: []
sparql-qwen
This model is a fine-tuned version of Qwen/Qwen2.5-Coder-0.5B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6232
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7485 | 0.1048 | 500 | 0.8336 |
| 0.7336 | 0.2096 | 1000 | 0.7696 |
| 0.6787 | 0.3143 | 1500 | 0.7376 |
| 0.6756 | 0.4191 | 2000 | 0.7190 |
| 0.6651 | 0.5239 | 2500 | 0.7038 |
| 0.6835 | 0.6287 | 3000 | 0.6932 |
| 0.6572 | 0.7334 | 3500 | 0.6810 |
| 0.6664 | 0.8382 | 4000 | 0.6773 |
| 0.6304 | 0.9430 | 4500 | 0.6675 |
| 0.7408 | 1.0478 | 5000 | 0.6648 |
| 0.7004 | 1.1526 | 5500 | 0.6616 |
| 0.6466 | 1.2573 | 6000 | 0.6579 |
| 0.6914 | 1.3621 | 6500 | 0.6543 |
| 0.6885 | 1.4669 | 7000 | 0.6507 |
| 0.6508 | 1.5717 | 7500 | 0.6478 |
| 0.7039 | 1.6764 | 8000 | 0.6442 |
| 0.665 | 1.7812 | 8500 | 0.6436 |
| 0.6483 | 1.8860 | 9000 | 0.6405 |
| 0.699 | 1.9908 | 9500 | 0.6373 |
| 0.4961 | 2.0956 | 10000 | 0.6380 |
| 0.5103 | 2.2003 | 10500 | 0.6367 |
| 0.5443 | 2.3051 | 11000 | 0.6349 |
| 0.4813 | 2.4099 | 11500 | 0.6340 |
| 0.5555 | 2.5147 | 12000 | 0.6324 |
| 0.5711 | 2.6194 | 12500 | 0.6313 |
| 0.5088 | 2.7242 | 13000 | 0.6309 |
| 0.492 | 2.8290 | 13500 | 0.6297 |
| 0.4936 | 2.9338 | 14000 | 0.6267 |
| 0.6411 | 3.0386 | 14500 | 0.6271 |
| 0.6618 | 3.1433 | 15000 | 0.6267 |
| 0.6212 | 3.2481 | 15500 | 0.6260 |
| 0.6337 | 3.3529 | 16000 | 0.6253 |
| 0.6412 | 3.4577 | 16500 | 0.6234 |
| 0.6208 | 3.5624 | 17000 | 0.6232 |
| 0.676 | 3.6672 | 17500 | 0.6226 |
| 0.6465 | 3.7720 | 18000 | 0.6217 |
| 0.6157 | 3.8768 | 18500 | 0.6210 |
| 0.6622 | 3.9816 | 19000 | 0.6200 |
| 0.4811 | 4.0863 | 19500 | 0.6219 |
| 0.5264 | 4.1911 | 20000 | 0.6213 |
| 0.4738 | 4.2959 | 20500 | 0.6232 |
Framework versions
- PEFT 0.14.0
- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3