metadata
license: bsd-3-clause
base_model: Salesforce/codet5p-220m
tags:
- generated_from_trainer
model-index:
- name: codet5-fine-tuned
results: []
codet5-fine-tuned
This model is a fine-tuned version of Salesforce/codet5p-220m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0916
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: 5e-05
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.99 | 56 | 0.0720 |
| 0.0898 | 1.99 | 113 | 0.0694 |
| 0.0898 | 3.0 | 170 | 0.0682 |
| 0.0509 | 4.0 | 227 | 0.0693 |
| 0.0509 | 4.99 | 283 | 0.0699 |
| 0.0384 | 5.99 | 340 | 0.0725 |
| 0.0384 | 7.0 | 397 | 0.0729 |
| 0.0295 | 8.0 | 454 | 0.0758 |
| 0.0224 | 8.99 | 510 | 0.0785 |
| 0.0224 | 9.99 | 567 | 0.0806 |
| 0.0177 | 11.0 | 624 | 0.0799 |
| 0.0177 | 12.0 | 681 | 0.0835 |
| 0.0136 | 12.99 | 737 | 0.0873 |
| 0.0136 | 13.99 | 794 | 0.0881 |
| 0.0116 | 15.0 | 851 | 0.0887 |
| 0.0095 | 16.0 | 908 | 0.0899 |
| 0.0095 | 16.99 | 964 | 0.0910 |
| 0.0082 | 17.99 | 1021 | 0.0916 |
| 0.0082 | 19.0 | 1078 | 0.0912 |
| 0.0072 | 19.74 | 1120 | 0.0916 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.15.2