Hugging Face's logo

dzungpham
/
graphcodebert-code-classification

Transformers
Safetensors
detection
AI-generated
bert
Model card Files
xet
 Community
graphcodebert-code-classification
File size: 4,981 Bytes
aae9944
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
2026-04-23 14:52:26,578 - INFO - ===== Training Configuration =====
2026-04-23 14:52:26,580 - INFO - model_name           : microsoft/unixcoder-base
2026-04-23 14:52:26,582 - INFO - output_dir           : output_checkpoints/unixcoder-base/
2026-04-23 14:52:26,583 - INFO - num_epochs           : 0.5
2026-04-23 14:52:26,584 - INFO - max_steps            : 50
2026-04-23 14:52:26,585 - INFO - batch_size           : 32
2026-04-23 14:52:26,587 - INFO - learning_rate        : 1e-06
2026-04-23 14:52:26,588 - INFO - max_length           : 512
2026-04-23 14:52:26,589 - INFO - num_labels           : 2
2026-04-23 14:52:26,591 - INFO - use_wandb            : True
2026-04-23 14:52:26,592 - INFO - freeze_base          : True
2026-04-23 14:52:26,593 - INFO - loss_type            : r-drop
2026-04-23 14:52:26,594 - INFO - focal_alpha          : 1.0
2026-04-23 14:52:26,595 - INFO - focal_gamma          : 2.0
2026-04-23 14:52:26,596 - INFO - r_drop_alpha         : 6.0
2026-04-23 14:52:26,597 - INFO - infonce_temperature  : 0.07
2026-04-23 14:52:26,598 - INFO - infonce_weight       : 0.5
2026-04-23 14:52:26,599 - INFO - seed                 : 42
2026-04-23 14:52:26,600 - INFO - resume_from_checkpoint : None
2026-04-23 14:52:26,601 - INFO - label_smoothing      : 0.3
2026-04-23 14:52:26,602 - INFO - adversarial_epsilon  : 0.5
2026-04-23 14:52:26,604 - INFO - use_swa              : False
2026-04-23 14:52:26,606 - INFO - swa_start_epoch      : 0
2026-04-23 14:52:26,606 - INFO - swa_lr               : 1e-05
2026-04-23 14:52:26,607 - INFO - data_augmentation    : True
2026-04-23 14:52:26,609 - INFO - aug_rename_prob      : 0.6
2026-04-23 14:52:26,610 - INFO - aug_format_prob      : 0.6
2026-04-23 14:52:26,612 - INFO - mixup_alpha          : 1.0
2026-04-23 14:52:26,613 - INFO - low_pass_keep_ratio  : 0.5
2026-04-23 14:52:26,614 - INFO - freq_consistency_weight : 0.2
2026-04-23 14:52:26,615 - INFO - hidden_dropout_prob  : 0.3
2026-04-23 14:52:26,616 - INFO - attention_probs_dropout_prob : 0.3
2026-04-23 14:52:26,618 - INFO - classifier_dropout   : 0.3
2026-04-23 14:52:26,619 - INFO - =================================
2026-04-23 14:52:27,631 - INFO - Model placed on cuda
2026-04-23 14:52:27,635 - INFO - ===== Model Architecture =====
2026-04-23 14:52:27,638 - INFO - 
RobertaForSequenceClassification(
  (roberta): RobertaModel(
    (embeddings): RobertaEmbeddings(
      (word_embeddings): Embedding(51416, 768, padding_idx=1)
      (position_embeddings): Embedding(1026, 768, padding_idx=1)
      (token_type_embeddings): Embedding(10, 768)
      (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      (dropout): Dropout(p=0.3, inplace=False)
    )
    (encoder): RobertaEncoder(
      (layer): ModuleList(
        (0-11): 12 x RobertaLayer(
          (attention): RobertaAttention(
            (self): RobertaSdpaSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.3, inplace=False)
            )
            (output): RobertaSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.3, inplace=False)
            )
          )
          (intermediate): RobertaIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
            (intermediate_act_fn): GELUActivation()
          )
          (output): RobertaOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
            (dropout): Dropout(p=0.3, inplace=False)
          )
        )
      )
    )
  )
  (classifier): RobertaClassificationHead(
    (dense): Linear(in_features=768, out_features=768, bias=True)
    (dropout): Dropout(p=0.3, inplace=False)
    (out_proj): Linear(in_features=768, out_features=2, bias=True)
  )
)
2026-04-23 14:52:27,640 - INFO - ===== Parameter Summary =====
2026-04-23 14:52:27,642 - INFO - Total Parameters:         125,931,266
2026-04-23 14:52:27,643 - INFO - Trainable Parameters:     592,130
2026-04-23 14:52:27,646 - INFO - Non-trainable Parameters: 125,339,136
2026-04-23 14:52:27,647 - INFO - ===== Tokenizer Summary =====
2026-04-23 14:52:27,663 - INFO - Vocab size: 51416 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
2026-04-23 14:52:27,665 - INFO - ===== End of Architecture Log =====
2026-04-23 14:52:27,666 - INFO - Data augmentation enabled (rename=0.6, format=0.6)
2026-04-23 14:52:28,797 - INFO - === Starting training with MixCode + FFT low-pass consistency ===
2026-04-23 14:54:25,677 - INFO - Training complete!
2026-04-23 14:54:26,437 - INFO - Final model saved to output_checkpoints/unixcoder-base/final_model