metadata
license: apache-2.0
base_model: Salesforce/codet5-base
tags:
- code-generation
- generated_from_trainer
metrics:
- rouge
- bleu
model-index:
- name: codeT5-finetuned-cXg-nl-to-code
results: []
codeT5-finetuned-cXg-nl-to-code
This model is a fine-tuned version of Salesforce/codet5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8873
- Rouge1: 0.1077
- Rouge2: 0.0133
- Rougel: 0.1043
- Bleu: 3.0765
- Meteor: 0.1706
- Codebleu: 0.0498
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Bleu | Meteor | Codebleu |
|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 4 | 2.1149 | 0.0415 | 0.0010 | 0.0417 | 0.0629 | 0.0236 | 0.0177 |
| No log | 2.0 | 8 | 1.5027 | 0.0719 | 0.0028 | 0.0709 | 0.0682 | 0.0383 | 0.0201 |
| No log | 3.0 | 12 | 1.0964 | 0.0913 | 0.0106 | 0.0916 | 0.3613 | 0.1050 | 0.0267 |
| No log | 4.0 | 16 | 0.9316 | 0.1012 | 0.012 | 0.0979 | 0.6845 | 0.1369 | 0.0317 |
| No log | 5.0 | 20 | 0.8873 | 0.1058 | 0.012 | 0.1007 | 0.7454 | 0.1497 | 0.0338 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1