Hugging Face's logo

HID-APP
/
script-detector-microsoft-codebert-base

Safetensors
roberta
Model card Files
xet
 Community
script-detector-microsoft-codebert-base
File size: 5,147 Bytes
f59e019
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
{
  "best_global_step": 373,
  "best_metric": 0.8898085876875323,
  "best_model_checkpoint": "/kaggle/working/outputs/codebert-all-combined/microsoft-codebert-base/checkpoint-373",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2984,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 8.451900482177734,
      "learning_rate": 1.3351206434316355e-05,
      "loss": 3.253069430190181,
      "step": 373
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8352668213457076,
      "eval_f1": 0.8898085876875323,
      "eval_loss": 0.5276884436607361,
      "eval_precision": 0.8143939393939394,
      "eval_recall": 0.9806157354618016,
      "eval_runtime": 26.2521,
      "eval_samples_per_second": 49.253,
      "eval_steps_per_second": 3.085,
      "step": 373
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.377457141876221,
      "learning_rate": 6.684539767649688e-06,
      "loss": 2.735222946862433,
      "step": 746
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8290796597061099,
      "eval_f1": 0.8875318066157761,
      "eval_loss": 0.5213587880134583,
      "eval_precision": 0.8014705882352942,
      "eval_recall": 0.9942987457240593,
      "eval_runtime": 26.0805,
      "eval_samples_per_second": 49.577,
      "eval_steps_per_second": 3.106,
      "step": 746
    },
    {
      "epoch": 3.0,
      "grad_norm": 8.425128936767578,
      "learning_rate": 1.7873100983020556e-08,
      "loss": 2.6189828826658847,
      "step": 1119
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8360402165506574,
      "eval_f1": 0.886021505376344,
      "eval_loss": 0.5193805694580078,
      "eval_precision": 0.8382502543234995,
      "eval_recall": 0.9395667046750285,
      "eval_runtime": 25.9863,
      "eval_samples_per_second": 49.757,
      "eval_steps_per_second": 3.117,
      "step": 1119
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.492631912231445,
      "learning_rate": 1.1117068811438785e-05,
      "loss": 2.643136932127597,
      "step": 1492
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8283062645011601,
      "eval_f1": 0.8875379939209727,
      "eval_loss": 0.5421428680419922,
      "eval_precision": 0.7985414767547858,
      "eval_recall": 0.9988597491448119,
      "eval_runtime": 26.1276,
      "eval_samples_per_second": 49.488,
      "eval_steps_per_second": 3.1,
      "step": 1492
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.1199772357940674,
      "learning_rate": 8.894846589216563e-06,
      "loss": 2.5547156448977884,
      "step": 1865
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8267594740912606,
      "eval_f1": 0.885480572597137,
      "eval_loss": 0.5424710512161255,
      "eval_precision": 0.8025949953660797,
      "eval_recall": 0.9874572405929305,
      "eval_runtime": 25.9539,
      "eval_samples_per_second": 49.819,
      "eval_steps_per_second": 3.121,
      "step": 1865
    },
    {
      "epoch": 6.0,
      "grad_norm": 3.1183524131774902,
      "learning_rate": 6.67262436699434e-06,
      "loss": 2.5014848069914546,
      "step": 2238
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8290796597061099,
      "eval_f1": 0.8868407578084997,
      "eval_loss": 0.5805880427360535,
      "eval_precision": 0.8048327137546468,
      "eval_recall": 0.9874572405929305,
      "eval_runtime": 26.5677,
      "eval_samples_per_second": 48.668,
      "eval_steps_per_second": 3.049,
      "step": 2238
    },
    {
      "epoch": 7.0,
      "grad_norm": 25.385547637939453,
      "learning_rate": 4.450402144772119e-06,
      "loss": 2.44378613019437,
      "step": 2611
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.851508120649652,
      "eval_f1": 0.883495145631068,
      "eval_loss": 0.6349141001701355,
      "eval_precision": 0.9442282749675746,
      "eval_recall": 0.830102622576967,
      "eval_runtime": 27.4334,
      "eval_samples_per_second": 47.132,
      "eval_steps_per_second": 2.953,
      "step": 2611
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.2667272090911865,
      "learning_rate": 2.228179922549896e-06,
      "loss": 2.413644417361344,
      "step": 2984
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.848414539829853,
      "eval_f1": 0.8852459016393442,
      "eval_loss": 0.6463340520858765,
      "eval_precision": 0.9097472924187726,
      "eval_recall": 0.8620296465222349,
      "eval_runtime": 26.2292,
      "eval_samples_per_second": 49.296,
      "eval_steps_per_second": 3.088,
      "step": 2984
    }
  ],
  "logging_steps": 500,
  "max_steps": 3357,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.507302824278304e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}