| | --- |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - accuracy |
| | model-index: |
| | - name: CodeBERTa-commit-message-autocomplete |
| | 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. --> |
| |
|
| | # CodeBERTa-commit-message-autocomplete |
| |
|
| | 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: 1.8796 |
| | - Accuracy: 0.6381 |
| |
|
| | ## 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: 64 |
| | - eval_batch_size: 64 |
| | - seed: 42 |
| | - gradient_accumulation_steps: 16 |
| | - total_train_batch_size: 1024 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - lr_scheduler_warmup_steps: 1000 |
| | - num_epochs: 50 |
| | - mixed_precision_training: Native AMP |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| | |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | | No log | 1.0 | 40 | 4.5229 | 0.3460 | |
| | | No log | 2.0 | 80 | 3.8419 | 0.3792 | |
| | | No log | 3.0 | 120 | 3.1830 | 0.4538 | |
| | | No log | 4.0 | 160 | 2.8435 | 0.5 | |
| | | No log | 5.0 | 200 | 2.6741 | 0.5126 | |
| | | No log | 6.0 | 240 | 2.6468 | 0.5211 | |
| | | No log | 7.0 | 280 | 2.4902 | 0.5431 | |
| | | No log | 8.0 | 320 | 2.4223 | 0.5590 | |
| | | No log | 9.0 | 360 | 2.3677 | 0.5625 | |
| | | No log | 10.0 | 400 | 2.3634 | 0.5654 | |
| | | No log | 11.0 | 440 | 2.3334 | 0.5693 | |
| | | No log | 12.0 | 480 | 2.1738 | 0.5963 | |
| | | 3.0595 | 13.0 | 520 | 2.2148 | 0.5882 | |
| | | 3.0595 | 14.0 | 560 | 2.2387 | 0.5878 | |
| | | 3.0595 | 15.0 | 600 | 2.1472 | 0.5938 | |
| | | 3.0595 | 16.0 | 640 | 2.1703 | 0.5963 | |
| | | 3.0595 | 17.0 | 680 | 2.1183 | 0.5937 | |
| | | 3.0595 | 18.0 | 720 | 2.1139 | 0.6035 | |
| | | 3.0595 | 19.0 | 760 | 2.0543 | 0.6106 | |
| | | 3.0595 | 20.0 | 800 | 2.0135 | 0.6148 | |
| | | 3.0595 | 21.0 | 840 | 2.0445 | 0.6119 | |
| | | 3.0595 | 22.0 | 880 | 1.9723 | 0.6221 | |
| | | 3.0595 | 23.0 | 920 | 1.9972 | 0.6205 | |
| | | 3.0595 | 24.0 | 960 | 1.9588 | 0.6280 | |
| | | 2.1206 | 25.0 | 1000 | 1.9563 | 0.6280 | |
| | | 2.1206 | 26.0 | 1040 | 1.9421 | 0.6254 | |
| | | 2.1206 | 27.0 | 1080 | 1.9820 | 0.6291 | |
| | | 2.1206 | 28.0 | 1120 | 1.8989 | 0.6315 | |
| | | 2.1206 | 29.0 | 1160 | 1.8743 | 0.6330 | |
| | | 2.1206 | 30.0 | 1200 | 1.8840 | 0.6389 | |
| | | 2.1206 | 31.0 | 1240 | 1.9038 | 0.6325 | |
| | | 2.1206 | 32.0 | 1280 | 1.8796 | 0.6381 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.25.1 |
| | - Pytorch 1.13.0+cu117 |
| | - Datasets 2.7.1 |
| | - Tokenizers 0.13.2 |
| |
|
