metadata
tags:
- generated_from_trainer
model-index:
- name: codebert-python-custom-functions-dataset-python
results: []
codebert-python-custom-functions-dataset-python
This model is a fine-tuned version of neulab/codebert-python on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0151
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9043 | 1.0 | 43 | 1.5089 |
| 0.5831 | 2.0 | 86 | 0.4039 |
| 0.3148 | 3.0 | 129 | 0.1510 |
| 0.2251 | 4.0 | 172 | 0.0710 |
| 0.0766 | 5.0 | 215 | 0.0442 |
| 0.0884 | 6.0 | 258 | 0.0287 |
| 0.0975 | 7.0 | 301 | 0.0210 |
| 0.1113 | 8.0 | 344 | 0.0183 |
| 0.0448 | 9.0 | 387 | 0.0162 |
| 0.029 | 10.0 | 430 | 0.0151 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3