metadata
license: apache-2.0
base_model: Salesforce/codet5-base
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: v9.1-codet5-base-finetuned-code_function-to-test_case_function
results: []
v9.1-codet5-base-finetuned-code_function-to-test_case_function
This model is a fine-tuned version of Salesforce/codet5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6592
- Bleu: 0.0145
- Gen Len: 19.0
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: 2
- eval_batch_size: 2
- 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 | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 400 | 1.8713 | 0.0187 | 19.0 |
| 2.5133 | 2.0 | 800 | 1.7578 | 0.0149 | 19.0 |
| 1.9264 | 3.0 | 1200 | 1.7019 | 0.0161 | 19.0 |
| 1.7291 | 4.0 | 1600 | 1.6722 | 0.0165 | 19.0 |
| 1.5638 | 5.0 | 2000 | 1.6608 | 0.0149 | 19.0 |
| 1.5638 | 6.0 | 2400 | 1.6544 | 0.0146 | 19.0 |
| 1.4592 | 7.0 | 2800 | 1.6511 | 0.0139 | 19.0 |
| 1.3699 | 8.0 | 3200 | 1.6537 | 0.0148 | 19.0 |
| 1.3379 | 9.0 | 3600 | 1.6596 | 0.0145 | 19.0 |
| 1.2919 | 10.0 | 4000 | 1.6592 | 0.0145 | 19.0 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1