update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: CodeBERTa-commit-message-autocomplete
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# CodeBERTa-commit-message-autocomplete
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [microsoft/codebert-base-mlm](https://huggingface.co/microsoft/codebert-base-mlm) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.7327
|
| 19 |
+
- Accuracy: 0.6612
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 42
|
| 40 |
+
- eval_batch_size: 42
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 3
|
| 43 |
+
- total_train_batch_size: 126
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 1000
|
| 47 |
+
- num_epochs: 50
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| No log | 1.0 | 325 | 2.6847 | 0.5185 |
|
| 55 |
+
| 3.367 | 2.0 | 650 | 2.4055 | 0.5573 |
|
| 56 |
+
| 3.367 | 3.0 | 975 | 2.2742 | 0.5766 |
|
| 57 |
+
| 2.4354 | 4.0 | 1300 | 2.1065 | 0.6057 |
|
| 58 |
+
| 2.1925 | 5.0 | 1625 | 2.0764 | 0.6053 |
|
| 59 |
+
| 2.1925 | 6.0 | 1950 | 2.0169 | 0.6172 |
|
| 60 |
+
| 2.0217 | 7.0 | 2275 | 1.9270 | 0.6209 |
|
| 61 |
+
| 1.9424 | 8.0 | 2600 | 1.9326 | 0.6318 |
|
| 62 |
+
| 1.9424 | 9.0 | 2925 | 1.8849 | 0.6321 |
|
| 63 |
+
| 1.8485 | 10.0 | 3250 | 1.8834 | 0.6422 |
|
| 64 |
+
| 1.7847 | 11.0 | 3575 | 1.8213 | 0.6481 |
|
| 65 |
+
| 1.7847 | 12.0 | 3900 | 1.8674 | 0.6374 |
|
| 66 |
+
| 1.719 | 13.0 | 4225 | 1.7865 | 0.6473 |
|
| 67 |
+
| 1.6847 | 14.0 | 4550 | 1.8005 | 0.6523 |
|
| 68 |
+
| 1.6847 | 15.0 | 4875 | 1.8039 | 0.6516 |
|
| 69 |
+
| 1.6274 | 16.0 | 5200 | 1.7457 | 0.6617 |
|
| 70 |
+
| 1.5833 | 17.0 | 5525 | 1.7456 | 0.6526 |
|
| 71 |
+
| 1.5833 | 18.0 | 5850 | 1.7314 | 0.6626 |
|
| 72 |
+
| 1.5485 | 19.0 | 6175 | 1.7605 | 0.6590 |
|
| 73 |
+
| 1.5448 | 20.0 | 6500 | 1.7694 | 0.6592 |
|
| 74 |
+
| 1.5448 | 21.0 | 6825 | 1.7327 | 0.6612 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.25.1
|
| 80 |
+
- Pytorch 1.13.0+cu117
|
| 81 |
+
- Datasets 2.7.1
|
| 82 |
+
- Tokenizers 0.13.2
|