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: 0.4852
- Rouge1: 0.2602
- Rouge2: 0.0661
- Rougel: 0.2363
- Bleu: 11.1005
- Meteor: 0.3527
- Codebleu: 0.1717
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: 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 | 1.0580 | 0.0867 | 0.0075 | 0.0826 | 0.3778 | 0.0859 | 0.0271 |
| No log | 2.0 | 8 | 0.7338 | 0.1628 | 0.0330 | 0.1493 | 1.7546 | 0.2224 | 0.0420 |
| No log | 3.0 | 12 | 0.6427 | 0.2150 | 0.0546 | 0.1959 | 3.3997 | 0.2411 | 0.0680 |
| No log | 4.0 | 16 | 0.5162 | 0.2598 | 0.0579 | 0.2303 | 5.3818 | 0.2805 | 0.1065 |
| No log | 5.0 | 20 | 0.4852 | 0.2578 | 0.0559 | 0.2346 | 6.1221 | 0.2829 | 0.1208 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1