metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: CommitPredictor
results: []
CommitPredictor
This model is a fine-tuned version of microsoft/codebert-base-mlm on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5977
- Accuracy: 0.8793
- F1: 0.8793
- Bleu4: 0.8016
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Bleu4 |
|---|---|---|---|---|---|---|
| 0.8373 | 1.0 | 1373 | 0.6817 | 0.8587 | 0.8587 | 0.8615 |
| 0.6984 | 2.0 | 2746 | 0.6406 | 0.8685 | 0.8685 | 0.9062 |
| 0.6587 | 3.0 | 4119 | 0.6172 | 0.8748 | 0.8748 | 0.9067 |
| 0.6514 | 4.0 | 5492 | 0.6017 | 0.8783 | 0.8783 | 0.9198 |
| 0.6263 | 5.0 | 6865 | 0.5977 | 0.8793 | 0.8793 | 0.8016 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2