Hugging Face's logo

mamiksik
/
CommitPredictor

Fill-Mask
Transformers
PyTorch
roberta
Generated from Trainer
Model card Files
xet
Community
1
mamiksik commited on
Commit
eb05084
·
1 Parent(s): 96211b4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.5238
19
- - Accuracy: 0.8925
20
 
21
  ## Model description
22
 
@@ -35,7 +35,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 1.7636624471082695e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
49
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
50
- | 0.7781 | 1.0 | 2440 | 0.6600 | 0.8638 |
51
- | 0.6881 | 2.0 | 4880 | 0.6070 | 0.8760 |
52
- | 0.6493 | 3.0 | 7320 | 0.5903 | 0.8794 |
53
- | 0.6173 | 4.0 | 9760 | 0.5597 | 0.8849 |
54
- | 0.5803 | 5.0 | 12200 | 0.5430 | 0.8888 |
55
- | 0.5735 | 6.0 | 14640 | 0.5380 | 0.8891 |
56
- | 0.575 | 7.0 | 17080 | 0.5392 | 0.8892 |
57
- | 0.5517 | 8.0 | 19520 | 0.5279 | 0.8912 |
58
- | 0.5552 | 9.0 | 21960 | 0.5283 | 0.8912 |
59
- | 0.5542 | 10.0 | 24400 | 0.5238 | 0.8925 |
60
 
61
 
62
  ### Framework versions
 
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: 0.5166
19
+ - Accuracy: 0.8940
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 2.0426643720739023e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
49
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
50
+ | 0.7655 | 1.0 | 2440 | 0.6519 | 0.8661 |
51
+ | 0.6784 | 2.0 | 4880 | 0.5992 | 0.8772 |
52
+ | 0.6391 | 3.0 | 7320 | 0.5835 | 0.8811 |
53
+ | 0.6067 | 4.0 | 9760 | 0.5530 | 0.8861 |
54
+ | 0.5707 | 5.0 | 12200 | 0.5377 | 0.8899 |
55
+ | 0.5631 | 6.0 | 14640 | 0.5304 | 0.8911 |
56
+ | 0.5632 | 7.0 | 17080 | 0.5317 | 0.8908 |
57
+ | 0.5394 | 8.0 | 19520 | 0.5208 | 0.8927 |
58
+ | 0.5417 | 9.0 | 21960 | 0.5204 | 0.8925 |
59
+ | 0.5419 | 10.0 | 24400 | 0.5166 | 0.8940 |
60
 
61
 
62
  ### Framework versions