Hugging Face's logo

mamiksik
/
CommitPredictor

Fill-Mask
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
mamiksik commited on
Commit
498dfdb
·
1 Parent(s): cadc651

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -58
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: 1.9935
19
- - Accuracy: 0.6325
20
 
21
  ## Model description
22
 
@@ -36,11 +36,11 @@ More information needed
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
@@ -48,58 +48,21 @@ The following hyperparameters were used during training:
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
- | No log | 1.0 | 448 | 2.4744 | 0.5376 |
54
- | 2.9007 | 2.0 | 896 | 2.4149 | 0.5473 |
55
- | 2.5284 | 3.0 | 1344 | 2.3077 | 0.5639 |
56
- | 2.3292 | 4.0 | 1792 | 2.2617 | 0.5640 |
57
- | 2.2692 | 5.0 | 2240 | 2.2155 | 0.5719 |
58
- | 2.1766 | 6.0 | 2688 | 2.1555 | 0.5792 |
59
- | 2.0842 | 7.0 | 3136 | 2.0758 | 0.6030 |
60
- | 2.0268 | 8.0 | 3584 | 2.1446 | 0.5942 |
61
- | 1.9416 | 9.0 | 4032 | 2.1110 | 0.5840 |
62
- | 1.9416 | 10.0 | 4480 | 2.1379 | 0.5888 |
63
- | 1.8969 | 11.0 | 4928 | 2.0461 | 0.6082 |
64
- | 1.8247 | 12.0 | 5376 | 2.0585 | 0.6007 |
65
- | 1.8038 | 13.0 | 5824 | 2.0541 | 0.6022 |
66
- | 1.7601 | 14.0 | 6272 | 2.0832 | 0.6043 |
67
- | 1.7086 | 15.0 | 6720 | 2.0224 | 0.6096 |
68
- | 1.7087 | 16.0 | 7168 | 2.0853 | 0.6057 |
69
- | 1.653 | 17.0 | 7616 | 2.0259 | 0.6124 |
70
- | 1.5953 | 18.0 | 8064 | 1.9913 | 0.6207 |
71
- | 1.6074 | 19.0 | 8512 | 1.9798 | 0.6157 |
72
- | 1.6074 | 20.0 | 8960 | 2.0234 | 0.6033 |
73
- | 1.5749 | 21.0 | 9408 | 1.9686 | 0.6197 |
74
- | 1.535 | 22.0 | 9856 | 2.0068 | 0.6163 |
75
- | 1.4942 | 23.0 | 10304 | 1.9486 | 0.6310 |
76
- | 1.4765 | 24.0 | 10752 | 1.9502 | 0.6304 |
77
- | 1.4558 | 25.0 | 11200 | 1.9509 | 0.6328 |
78
- | 1.4617 | 26.0 | 11648 | 1.9903 | 0.6196 |
79
- | 1.4224 | 27.0 | 12096 | 1.9849 | 0.6321 |
80
- | 1.4019 | 28.0 | 12544 | 1.9781 | 0.6193 |
81
- | 1.4019 | 29.0 | 12992 | 2.0661 | 0.6145 |
82
- | 1.3624 | 30.0 | 13440 | 1.9948 | 0.6191 |
83
- | 1.3517 | 31.0 | 13888 | 1.9117 | 0.6392 |
84
- | 1.3613 | 32.0 | 14336 | 2.0300 | 0.6176 |
85
- | 1.3428 | 33.0 | 14784 | 2.0005 | 0.6226 |
86
- | 1.3257 | 34.0 | 15232 | 2.0079 | 0.6149 |
87
- | 1.3127 | 35.0 | 15680 | 2.0231 | 0.6213 |
88
- | 1.289 | 36.0 | 16128 | 1.9961 | 0.6296 |
89
- | 1.2689 | 37.0 | 16576 | 1.9930 | 0.6221 |
90
- | 1.2651 | 38.0 | 17024 | 1.9675 | 0.6314 |
91
- | 1.2651 | 39.0 | 17472 | 1.9835 | 0.6220 |
92
- | 1.2638 | 40.0 | 17920 | nan | 0.6275 |
93
- | 1.235 | 41.0 | 18368 | 2.0100 | 0.6299 |
94
- | 1.2239 | 42.0 | 18816 | 2.0384 | 0.6152 |
95
- | 1.2147 | 43.0 | 19264 | 2.0421 | 0.6209 |
96
- | 1.1961 | 44.0 | 19712 | 2.0041 | 0.6212 |
97
- | 1.1988 | 45.0 | 20160 | 1.9905 | 0.6230 |
98
- | 1.2007 | 46.0 | 20608 | 2.0222 | 0.6275 |
99
- | 1.2029 | 47.0 | 21056 | 1.9856 | 0.6361 |
100
- | 1.1779 | 48.0 | 21504 | 2.0348 | 0.6184 |
101
- | 1.1779 | 49.0 | 21952 | 1.9196 | 0.6324 |
102
- | 1.1973 | 50.0 | 22400 | 1.9935 | 0.6325 |
103
 
104
 
105
  ### 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: 1.8427
19
+ - Accuracy: 0.6409
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 2e-05
39
+ - train_batch_size: 32
40
+ - eval_batch_size: 32
41
  - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 128
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
+ | No log | 1.0 | 292 | 2.2754 | 0.5767 |
54
+ | 2.5787 | 2.0 | 584 | 2.2006 | 0.5877 |
55
+ | 2.5787 | 3.0 | 876 | 2.0851 | 0.5953 |
56
+ | 2.2167 | 4.0 | 1168 | 2.0148 | 0.6142 |
57
+ | 2.2167 | 5.0 | 1460 | 1.9583 | 0.6144 |
58
+ | 2.064 | 6.0 | 1752 | 1.8846 | 0.6309 |
59
+ | 1.9626 | 7.0 | 2044 | 1.9399 | 0.6247 |
60
+ | 1.9626 | 8.0 | 2336 | 1.8423 | 0.6401 |
61
+ | 1.8671 | 9.0 | 2628 | 1.8065 | 0.6407 |
62
+ | 1.8671 | 10.0 | 2920 | 1.7582 | 0.6507 |
63
+ | 1.7957 | 11.0 | 3212 | 1.7978 | 0.6479 |
64
+ | 1.7226 | 12.0 | 3504 | 1.8058 | 0.6521 |
65
+ | 1.7226 | 13.0 | 3796 | 1.8427 | 0.6409 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions