Hugging Face's logo

azherali
/
CodeGenDetect-CodeBert_Lora

PEFT
Safetensors
Transformers
lora
Model card Files
xet
Community
azherali commited on
Commit
5e550bd
·
verified ·
1 Parent(s): 62beafe

Model save

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: microsoft/codebert-base
4
+ tags:
5
+ - base_model:adapter:microsoft/codebert-base
6
+ - lora
7
+ - transformers
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
+ - precision
12
+ - recall
13
+ model-index:
14
+ - name: CodeGenDetect-CodeBert_Lora
15
+ results: []
16
+ ---
17
+
18
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
19
+ should probably proofread and complete it, then remove this comment. -->
20
+
21
+ # CodeGenDetect-CodeBert_Lora
22
+
23
+ This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on the None dataset.
24
+ It achieves the following results on the evaluation set:
25
+ - Loss: 0.0384
26
+ - Accuracy: 0.9907
27
+ - F1: 0.9907
28
+ - Precision: 0.9907
29
+ - Recall: 0.9907
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 2e-05
49
+ - train_batch_size: 16
50
+ - eval_batch_size: 16
51
+ - seed: 42
52
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
53
+ - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_steps: 500
55
+ - num_epochs: 5
56
+ - mixed_precision_training: Native AMP
57
+
58
+ ### Training results
59
+
60
+ | Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall |
61
+ |:-------------:|:------:|:-----:|:--------:|:------:|:---------------:|:---------:|:------:|
62
+ | 0.1381 | 0.128 | 4000 | 0.9586 | 0.9586 | 0.1627 | 0.9599 | 0.9586 |
63
+ | 0.0821 | 0.256 | 8000 | 0.9761 | 0.9761 | 0.1081 | 0.9761 | 0.9761 |
64
+ | 0.0667 | 0.384 | 12000 | 0.9786 | 0.9786 | 0.1008 | 0.9787 | 0.9786 |
65
+ | 0.0754 | 0.512 | 16000 | 0.9820 | 0.9820 | 0.0779 | 0.9821 | 0.9820 |
66
+ | 0.0776 | 0.64 | 20000 | 0.9846 | 0.9846 | 0.0617 | 0.9847 | 0.9846 |
67
+ | 0.0643 | 0.768 | 24000 | 0.9831 | 0.9831 | 0.0761 | 0.9832 | 0.9831 |
68
+ | 0.064 | 0.896 | 28000 | 0.9878 | 0.9878 | 0.0495 | 0.9878 | 0.9878 |
69
+ | 0.0477 | 1.024 | 32000 | 0.9879 | 0.9879 | 0.0480 | 0.9880 | 0.9879 |
70
+ | 0.0427 | 1.152 | 36000 | 0.9894 | 0.9894 | 0.0424 | 0.9894 | 0.9894 |
71
+ | 0.0381 | 1.28 | 40000 | 0.9880 | 0.9880 | 0.0484 | 0.9880 | 0.9880 |
72
+ | 0.0423 | 1.408 | 44000 | 0.9901 | 0.9901 | 0.0399 | 0.9901 | 0.9901 |
73
+ | 0.0389 | 1.536 | 48000 | 0.9888 | 0.9888 | 0.0513 | 0.9889 | 0.9888 |
74
+ | 0.0416 | 1.6640 | 52000 | 0.9908 | 0.9908 | 0.0358 | 0.9908 | 0.9908 |
75
+ | 0.0374 | 1.792 | 56000 | 0.0370 | 0.9905 | 0.9905 | 0.9905 | 0.9905 |
76
+ | 0.0441 | 1.92 | 60000 | 0.0355 | 0.9905 | 0.9905 | 0.9905 | 0.9905 |
77
+ | 0.0358 | 2.048 | 64000 | 0.0384 | 0.9907 | 0.9907 | 0.9907 | 0.9907 |
78
+
79
+
80
+ ### Framework versions
81
+
82
+ - PEFT 0.18.0
83
+ - Transformers 4.57.3
84
+ - Pytorch 2.9.0+cu126
85
+ - Datasets 4.0.0
86
+ - Tokenizers 0.22.1