Hugging Face's logo

dzungpham
/
SLA-SemEval-challenge

Transformers
Safetensors
detection
AI-generated
bert
Model card Files
xet
 Community
SLA-SemEval-challenge
File size: 4,105 Bytes
218aef1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0128,
  "eval_steps": 1000,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00064,
      "grad_norm": 1.6144306659698486,
      "learning_rate": 1.1520000000000002e-08,
      "loss": 0.729,
      "step": 10
    },
    {
      "epoch": 0.00128,
      "grad_norm": 2.0952296257019043,
      "learning_rate": 2.4320000000000002e-08,
      "loss": 0.7295,
      "step": 20
    },
    {
      "epoch": 0.00192,
      "grad_norm": 1.3587689399719238,
      "learning_rate": 3.7120000000000004e-08,
      "loss": 0.73,
      "step": 30
    },
    {
      "epoch": 0.00256,
      "grad_norm": 1.2531732320785522,
      "learning_rate": 4.9920000000000006e-08,
      "loss": 0.7221,
      "step": 40
    },
    {
      "epoch": 0.0032,
      "grad_norm": 1.437932014465332,
      "learning_rate": 6.272000000000001e-08,
      "loss": 0.7209,
      "step": 50
    },
    {
      "epoch": 0.00384,
      "grad_norm": 1.418426752090454,
      "learning_rate": 7.552e-08,
      "loss": 0.729,
      "step": 60
    },
    {
      "epoch": 0.00448,
      "grad_norm": 1.9476298093795776,
      "learning_rate": 8.832e-08,
      "loss": 0.7242,
      "step": 70
    },
    {
      "epoch": 0.00512,
      "grad_norm": 1.7948051691055298,
      "learning_rate": 1.0112000000000001e-07,
      "loss": 0.7227,
      "step": 80
    },
    {
      "epoch": 0.00576,
      "grad_norm": 1.6534360647201538,
      "learning_rate": 1.1392e-07,
      "loss": 0.7234,
      "step": 90
    },
    {
      "epoch": 0.0064,
      "grad_norm": 1.0920158624649048,
      "learning_rate": 1.2672e-07,
      "loss": 0.7328,
      "step": 100
    },
    {
      "epoch": 0.00704,
      "grad_norm": 1.977837085723877,
      "learning_rate": 1.3952000000000002e-07,
      "loss": 0.7263,
      "step": 110
    },
    {
      "epoch": 0.00768,
      "grad_norm": 1.388983130455017,
      "learning_rate": 1.5232000000000003e-07,
      "loss": 0.7286,
      "step": 120
    },
    {
      "epoch": 0.00832,
      "grad_norm": 1.2956682443618774,
      "learning_rate": 1.6512e-07,
      "loss": 0.7251,
      "step": 130
    },
    {
      "epoch": 0.00896,
      "grad_norm": 1.8125052452087402,
      "learning_rate": 1.7792e-07,
      "loss": 0.7251,
      "step": 140
    },
    {
      "epoch": 0.0096,
      "grad_norm": 1.626846194267273,
      "learning_rate": 1.9072e-07,
      "loss": 0.727,
      "step": 150
    },
    {
      "epoch": 0.01024,
      "grad_norm": 2.3243086338043213,
      "learning_rate": 2.0352e-07,
      "loss": 0.726,
      "step": 160
    },
    {
      "epoch": 0.01088,
      "grad_norm": 1.4734737873077393,
      "learning_rate": 2.1632e-07,
      "loss": 0.7252,
      "step": 170
    },
    {
      "epoch": 0.01152,
      "grad_norm": 2.090498685836792,
      "learning_rate": 2.2912e-07,
      "loss": 0.7273,
      "step": 180
    },
    {
      "epoch": 0.01216,
      "grad_norm": 1.7563093900680542,
      "learning_rate": 2.4192000000000004e-07,
      "loss": 0.719,
      "step": 190
    },
    {
      "epoch": 0.0128,
      "grad_norm": 1.449843168258667,
      "learning_rate": 2.5472000000000005e-07,
      "loss": 0.7237,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 156250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1683910754304000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}