|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: CommitPredictor |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# CommitPredictor |
|
|
|
This model is a fine-tuned version of [microsoft/codebert-base-mlm](https://huggingface.co/microsoft/codebert-base-mlm) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.6621 |
|
- Accuracy: 0.6851 |
|
|
|
## 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: 42 |
|
- eval_batch_size: 42 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 3 |
|
- total_train_batch_size: 126 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 50 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| No log | 1.0 | 299 | 2.2298 | 0.5874 | |
|
| 2.5371 | 2.0 | 598 | 2.1358 | 0.6110 | |
|
| 2.5371 | 3.0 | 897 | 2.0865 | 0.6056 | |
|
| 2.1935 | 4.0 | 1196 | 2.0596 | 0.6179 | |
|
| 2.1935 | 5.0 | 1495 | 1.9902 | 0.6305 | |
|
| 2.0549 | 6.0 | 1794 | 1.9647 | 0.6274 | |
|
| 1.9558 | 7.0 | 2093 | 1.9462 | 0.6290 | |
|
| 1.9558 | 8.0 | 2392 | 1.9443 | 0.6261 | |
|
| 1.8732 | 9.0 | 2691 | 1.9241 | 0.6317 | |
|
| 1.8732 | 10.0 | 2990 | 1.8810 | 0.6461 | |
|
| 1.798 | 11.0 | 3289 | 1.8232 | 0.6434 | |
|
| 1.7427 | 12.0 | 3588 | 1.8621 | 0.6452 | |
|
| 1.7427 | 13.0 | 3887 | 1.7853 | 0.6596 | |
|
| 1.7124 | 14.0 | 4186 | 1.8741 | 0.6451 | |
|
| 1.7124 | 15.0 | 4485 | 1.7989 | 0.6536 | |
|
| 1.6683 | 16.0 | 4784 | 1.7783 | 0.6582 | |
|
| 1.59 | 17.0 | 5083 | 1.7738 | 0.6642 | |
|
| 1.59 | 18.0 | 5382 | 1.8241 | 0.6534 | |
|
| 1.5773 | 19.0 | 5681 | 1.8739 | 0.6547 | |
|
| 1.5773 | 20.0 | 5980 | 1.7439 | 0.6695 | |
|
| 1.532 | 21.0 | 6279 | 1.7081 | 0.6705 | |
|
| 1.4875 | 22.0 | 6578 | 1.7486 | 0.6662 | |
|
| 1.4875 | 23.0 | 6877 | 1.7568 | 0.6656 | |
|
| 1.466 | 24.0 | 7176 | 1.8062 | 0.6658 | |
|
| 1.466 | 25.0 | 7475 | 1.7666 | 0.6704 | |
|
| 1.448 | 26.0 | 7774 | 1.7219 | 0.6670 | |
|
| 1.4121 | 27.0 | 8073 | 1.6704 | 0.6745 | |
|
| 1.4121 | 28.0 | 8372 | 1.6966 | 0.6719 | |
|
| 1.3984 | 29.0 | 8671 | 1.6789 | 0.6825 | |
|
| 1.3984 | 30.0 | 8970 | 1.7001 | 0.6797 | |
|
| 1.3586 | 31.0 | 9269 | 1.7262 | 0.6712 | |
|
| 1.3433 | 32.0 | 9568 | 1.7446 | 0.6744 | |
|
| 1.3433 | 33.0 | 9867 | 1.6961 | 0.6752 | |
|
| 1.3366 | 34.0 | 10166 | 1.7180 | 0.6729 | |
|
| 1.3366 | 35.0 | 10465 | 1.6608 | 0.6773 | |
|
| 1.3227 | 36.0 | 10764 | 1.6820 | 0.6814 | |
|
| 1.3025 | 37.0 | 11063 | 1.7324 | 0.6727 | |
|
| 1.3025 | 38.0 | 11362 | 1.6705 | 0.6882 | |
|
| 1.2933 | 39.0 | 11661 | 1.6891 | 0.6742 | |
|
| 1.2933 | 40.0 | 11960 | 1.6533 | 0.6797 | |
|
| 1.2826 | 41.0 | 12259 | 1.6851 | 0.6770 | |
|
| 1.2784 | 42.0 | 12558 | 1.7140 | 0.6806 | |
|
| 1.2784 | 43.0 | 12857 | 1.6869 | 0.6769 | |
|
| 1.2703 | 44.0 | 13156 | 1.7068 | 0.6730 | |
|
| 1.2703 | 45.0 | 13455 | 1.7376 | 0.6681 | |
|
| 1.2492 | 46.0 | 13754 | 1.6944 | 0.6751 | |
|
| 1.2619 | 47.0 | 14053 | 1.8112 | 0.6644 | |
|
| 1.2619 | 48.0 | 14352 | 1.7553 | 0.6721 | |
|
| 1.2465 | 49.0 | 14651 | 1.7040 | 0.6713 | |
|
| 1.2465 | 50.0 | 14950 | 1.6621 | 0.6851 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.13.0+cu117 |
|
- Datasets 2.7.1 |
|
- Tokenizers 0.13.2 |
|
|
