mamiksik commited on
Commit
8554d5d
1 Parent(s): a3cf483

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -9
README.md CHANGED
@@ -16,10 +16,10 @@ 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: 2.1076
20
- - Accuracy: 0.7284
21
- - F1: 0.7284
22
- - Bleu4: 0.7262
23
 
24
  ## Model description
25
 
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Bleu4 |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|
53
- | No log | 1.0 | 1 | 2.4321 | 0.7137 | 0.7137 | 0.5207 |
54
- | No log | 2.0 | 2 | 2.2808 | 0.7186 | 0.7186 | 0.6834 |
55
- | No log | 3.0 | 3 | 2.1813 | 0.7273 | 0.7273 | 0.6974 |
56
- | No log | 4.0 | 4 | 2.2816 | 0.7316 | 0.7316 | 0.6591 |
57
- | No log | 5.0 | 5 | 2.1076 | 0.7284 | 0.7284 | 0.7262 |
58
 
59
 
60
  ### Framework versions
 
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: 0.5977
20
+ - Accuracy: 0.8793
21
+ - F1: 0.8793
22
+ - Bleu4: 0.8016
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Bleu4 |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|
53
+ | 0.8373 | 1.0 | 1373 | 0.6817 | 0.8587 | 0.8587 | 0.8615 |
54
+ | 0.6984 | 2.0 | 2746 | 0.6406 | 0.8685 | 0.8685 | 0.9062 |
55
+ | 0.6587 | 3.0 | 4119 | 0.6172 | 0.8748 | 0.8748 | 0.9067 |
56
+ | 0.6514 | 4.0 | 5492 | 0.6017 | 0.8783 | 0.8783 | 0.9198 |
57
+ | 0.6263 | 5.0 | 6865 | 0.5977 | 0.8793 | 0.8793 | 0.8016 |
58
 
59
 
60
  ### Framework versions