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: 2.1076
- Accuracy: 0.7284
- F1: 0.7284
- Bleu4: 0.7262
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 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 1 | 2.4321 | 0.7137 | 0.7137 | 0.5207 |
| No log | 2.0 | 2 | 2.2808 | 0.7186 | 0.7186 | 0.6834 |
| No log | 3.0 | 3 | 2.1813 | 0.7273 | 0.7273 | 0.6974 |
| No log | 4.0 | 4 | 2.2816 | 0.7316 | 0.7316 | 0.6591 |
| No log | 5.0 | 5 | 2.1076 | 0.7284 | 0.7284 | 0.7262 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2