Hugging Face's logo

mamiksik
/
CodeBERTa-commit-message-autocomplete

Fill-Mask
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
2
mamiksik commited on
Commit
d3ff883
•
1 Parent(s): eb407e0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +38 -27
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: 1.7327
19
- - Accuracy: 0.6612
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: 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
@@ -51,27 +51,38 @@ The following hyperparameters were used during training:
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
 
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: 1.8796
19
+ - Accuracy: 0.6381
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 2e-05
39
+ - train_batch_size: 64
40
+ - eval_batch_size: 64
41
  - seed: 42
42
+ - gradient_accumulation_steps: 16
43
+ - total_train_batch_size: 1024
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 1000
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | No log | 1.0 | 40 | 4.5229 | 0.3460 |
55
+ | No log | 2.0 | 80 | 3.8419 | 0.3792 |
56
+ | No log | 3.0 | 120 | 3.1830 | 0.4538 |
57
+ | No log | 4.0 | 160 | 2.8435 | 0.5 |
58
+ | No log | 5.0 | 200 | 2.6741 | 0.5126 |
59
+ | No log | 6.0 | 240 | 2.6468 | 0.5211 |
60
+ | No log | 7.0 | 280 | 2.4902 | 0.5431 |
61
+ | No log | 8.0 | 320 | 2.4223 | 0.5590 |
62
+ | No log | 9.0 | 360 | 2.3677 | 0.5625 |
63
+ | No log | 10.0 | 400 | 2.3634 | 0.5654 |
64
+ | No log | 11.0 | 440 | 2.3334 | 0.5693 |
65
+ | No log | 12.0 | 480 | 2.1738 | 0.5963 |
66
+ | 3.0595 | 13.0 | 520 | 2.2148 | 0.5882 |
67
+ | 3.0595 | 14.0 | 560 | 2.2387 | 0.5878 |
68
+ | 3.0595 | 15.0 | 600 | 2.1472 | 0.5938 |
69
+ | 3.0595 | 16.0 | 640 | 2.1703 | 0.5963 |
70
+ | 3.0595 | 17.0 | 680 | 2.1183 | 0.5937 |
71
+ | 3.0595 | 18.0 | 720 | 2.1139 | 0.6035 |
72
+ | 3.0595 | 19.0 | 760 | 2.0543 | 0.6106 |
73
+ | 3.0595 | 20.0 | 800 | 2.0135 | 0.6148 |
74
+ | 3.0595 | 21.0 | 840 | 2.0445 | 0.6119 |
75
+ | 3.0595 | 22.0 | 880 | 1.9723 | 0.6221 |
76
+ | 3.0595 | 23.0 | 920 | 1.9972 | 0.6205 |
77
+ | 3.0595 | 24.0 | 960 | 1.9588 | 0.6280 |
78
+ | 2.1206 | 25.0 | 1000 | 1.9563 | 0.6280 |
79
+ | 2.1206 | 26.0 | 1040 | 1.9421 | 0.6254 |
80
+ | 2.1206 | 27.0 | 1080 | 1.9820 | 0.6291 |
81
+ | 2.1206 | 28.0 | 1120 | 1.8989 | 0.6315 |
82
+ | 2.1206 | 29.0 | 1160 | 1.8743 | 0.6330 |
83
+ | 2.1206 | 30.0 | 1200 | 1.8840 | 0.6389 |
84
+ | 2.1206 | 31.0 | 1240 | 1.9038 | 0.6325 |
85
+ | 2.1206 | 32.0 | 1280 | 1.8796 | 0.6381 |
86
 
87
 
88
  ### Framework versions