update model card README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,8 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_trainer
|
|
|
|
|
4 |
model-index:
|
5 |
- name: CommitPredictor
|
6 |
results: []
|
@@ -12,6 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
# CommitPredictor
|
13 |
|
14 |
This model is a fine-tuned version of [microsoft/codebert-base-mlm](https://huggingface.co/microsoft/codebert-base-mlm) on the None dataset.
|
|
|
|
|
|
|
15 |
|
16 |
## Model description
|
17 |
|
@@ -36,7 +41,18 @@ The following hyperparameters were used during training:
|
|
36 |
- seed: 42
|
37 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
38 |
- lr_scheduler_type: linear
|
39 |
-
- num_epochs:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
|
41 |
### Framework versions
|
42 |
|
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
model-index:
|
7 |
- name: CommitPredictor
|
8 |
results: []
|
|
|
14 |
# CommitPredictor
|
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: 0.5977
|
19 |
+
- Accuracy: 0.8787
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 5
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
50 |
+
| 0.8394 | 1.0 | 1373 | 0.6828 | 0.8590 |
|
51 |
+
| 0.6997 | 2.0 | 2746 | 0.6389 | 0.8685 |
|
52 |
+
| 0.6575 | 3.0 | 4119 | 0.6162 | 0.8752 |
|
53 |
+
| 0.6503 | 4.0 | 5492 | 0.6018 | 0.8783 |
|
54 |
+
| 0.6246 | 5.0 | 6865 | 0.5977 | 0.8787 |
|
55 |
+
|
56 |
|
57 |
### Framework versions
|
58 |
|