Hugging Face's logo

mamiksik
/
CommitPredictor

Fill-Mask
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
mamiksik commited on
Commit
c3c1a85
·
1 Parent(s): 5cc9e35

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +57 -20
README.md CHANGED
@@ -3,7 +3,6 @@ tags:
3
  - generated_from_trainer
4
  metrics:
5
  - accuracy
6
- - f1
7
  model-index:
8
  - name: CommitPredictor
9
  results: []
@@ -16,10 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/codebert-base-mlm](https://huggingface.co/microsoft/codebert-base-mlm) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5888
20
- - Accuracy: 0.8783
21
- - F1: 0.8783
22
- - Bleu4: 0.8598
23
 
24
  ## Model description
25
 
@@ -39,11 +36,11 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 2e-05
42
- - train_batch_size: 42
43
- - eval_batch_size: 42
44
  - seed: 42
45
  - gradient_accumulation_steps: 3
46
- - total_train_batch_size: 126
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - num_epochs: 50
@@ -51,18 +48,58 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Bleu4 |
55
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|
56
- | No log | 1.0 | 236 | 0.8706 | 0.8253 | 0.8253 | 0.7764 |
57
- | No log | 2.0 | 472 | 0.7296 | 0.8503 | 0.8503 | 0.8287 |
58
- | 1.0825 | 3.0 | 708 | 0.6826 | 0.8594 | 0.8594 | 0.8123 |
59
- | 1.0825 | 4.0 | 944 | 0.6655 | 0.8645 | 0.8645 | 0.8480 |
60
- | 0.755 | 5.0 | 1180 | 0.6317 | 0.8696 | 0.8696 | 0.9028 |
61
- | 0.755 | 6.0 | 1416 | 0.6333 | 0.8699 | 0.8699 | 0.8870 |
62
- | 0.6948 | 7.0 | 1652 | 0.6147 | 0.8738 | 0.8738 | 0.9187 |
63
- | 0.6948 | 8.0 | 1888 | 0.6110 | 0.8738 | 0.8738 | 0.8080 |
64
- | 0.6633 | 9.0 | 2124 | 0.5987 | 0.8770 | 0.8770 | 0.8903 |
65
- | 0.6633 | 10.0 | 2360 | 0.5888 | 0.8783 | 0.8783 | 0.8598 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
3
  - generated_from_trainer
4
  metrics:
5
  - accuracy
 
6
  model-index:
7
  - name: CommitPredictor
8
  results: []
 
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: 0.5096
19
+ - Accuracy: 0.8933
 
 
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 2e-05
39
+ - train_batch_size: 21
40
+ - eval_batch_size: 21
41
  - seed: 42
42
  - gradient_accumulation_steps: 3
43
+ - total_train_batch_size: 63
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - num_epochs: 50
 
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
+ | 1.1808 | 1.0 | 599 | 0.7826 | 0.8420 |
54
+ | 0.8381 | 2.0 | 1198 | 0.7008 | 0.8581 |
55
+ | 0.7733 | 3.0 | 1797 | 0.6717 | 0.8639 |
56
+ | 0.7416 | 4.0 | 2396 | 0.6460 | 0.8682 |
57
+ | 0.7143 | 5.0 | 2995 | 0.6331 | 0.8708 |
58
+ | 0.683 | 6.0 | 3594 | 0.6243 | 0.8723 |
59
+ | 0.6609 | 7.0 | 4193 | 0.6151 | 0.8744 |
60
+ | 0.6547 | 8.0 | 4792 | 0.5987 | 0.8765 |
61
+ | 0.6467 | 9.0 | 5391 | 0.5969 | 0.8776 |
62
+ | 0.6366 | 10.0 | 5990 | 0.5890 | 0.8786 |
63
+ | 0.6176 | 11.0 | 6589 | 0.5785 | 0.8801 |
64
+ | 0.6106 | 12.0 | 7188 | 0.5813 | 0.8803 |
65
+ | 0.6026 | 13.0 | 7787 | 0.5644 | 0.8834 |
66
+ | 0.6005 | 14.0 | 8386 | 0.5600 | 0.8841 |
67
+ | 0.5965 | 15.0 | 8985 | 0.5653 | 0.8832 |
68
+ | 0.5851 | 16.0 | 9584 | 0.5544 | 0.8850 |
69
+ | 0.5781 | 17.0 | 10183 | 0.5543 | 0.8849 |
70
+ | 0.5732 | 18.0 | 10782 | 0.5464 | 0.8862 |
71
+ | 0.5713 | 19.0 | 11381 | 0.5448 | 0.8860 |
72
+ | 0.5678 | 20.0 | 11980 | 0.5452 | 0.8869 |
73
+ | 0.5615 | 21.0 | 12579 | 0.5395 | 0.8883 |
74
+ | 0.5543 | 22.0 | 13178 | 0.5383 | 0.8881 |
75
+ | 0.555 | 23.0 | 13777 | 0.5456 | 0.8870 |
76
+ | 0.5517 | 24.0 | 14376 | 0.5314 | 0.8890 |
77
+ | 0.5478 | 25.0 | 14975 | 0.5355 | 0.8878 |
78
+ | 0.5423 | 26.0 | 15574 | 0.5316 | 0.8892 |
79
+ | 0.5402 | 27.0 | 16173 | 0.5261 | 0.8903 |
80
+ | 0.5385 | 28.0 | 16772 | 0.5343 | 0.8884 |
81
+ | 0.5358 | 29.0 | 17371 | 0.5288 | 0.8894 |
82
+ | 0.5319 | 30.0 | 17970 | 0.5200 | 0.8912 |
83
+ | 0.5292 | 31.0 | 18569 | 0.5142 | 0.8923 |
84
+ | 0.529 | 32.0 | 19168 | 0.5174 | 0.8915 |
85
+ | 0.5233 | 33.0 | 19767 | 0.5253 | 0.8905 |
86
+ | 0.5236 | 34.0 | 20366 | 0.5135 | 0.8917 |
87
+ | 0.5269 | 35.0 | 20965 | 0.5127 | 0.8931 |
88
+ | 0.5145 | 36.0 | 21564 | 0.5182 | 0.8909 |
89
+ | 0.5192 | 37.0 | 22163 | 0.5185 | 0.8912 |
90
+ | 0.5154 | 38.0 | 22762 | 0.5160 | 0.8927 |
91
+ | 0.5131 | 39.0 | 23361 | 0.5135 | 0.8926 |
92
+ | 0.513 | 40.0 | 23960 | 0.5125 | 0.8924 |
93
+ | 0.5106 | 41.0 | 24559 | 0.5137 | 0.8919 |
94
+ | 0.5079 | 42.0 | 25158 | 0.5052 | 0.8935 |
95
+ | 0.508 | 43.0 | 25757 | 0.5172 | 0.8926 |
96
+ | 0.5104 | 44.0 | 26356 | 0.5062 | 0.8933 |
97
+ | 0.5066 | 45.0 | 26955 | 0.5076 | 0.8933 |
98
+ | 0.5085 | 46.0 | 27554 | 0.5123 | 0.8922 |
99
+ | 0.5064 | 47.0 | 28153 | 0.5102 | 0.8937 |
100
+ | 0.5058 | 48.0 | 28752 | 0.5127 | 0.8929 |
101
+ | 0.5028 | 49.0 | 29351 | 0.5164 | 0.8930 |
102
+ | 0.5036 | 50.0 | 29950 | 0.5096 | 0.8933 |
103
 
104
 
105
  ### Framework versions