metadata
license: bsd-3-clause
base_model: Salesforce/codet5p-220m-py
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-py on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1679
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.99 | 56 | 0.1700 |
| 0.1837 | 1.99 | 113 | 0.1634 |
| 0.1837 | 3.0 | 170 | 0.1658 |
| 0.1277 | 3.95 | 224 | 0.1679 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.15.2