Hugging Face's logo

TehranNLP-org
/
xlnet-base-cased-avg-cola-2e-5-42

Text Classification
Transformers
PyTorch
xlnet
Model card Files Community
1
xlnet-base-cased-avg-cola-2e-5-42
File size: 4,379 Bytes 
708878a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.49369621090355154,
  "best_model_checkpoint": "./xlnet-base-cased/fine_tuned_models/checkpoint-1876",
  "epoch": 10.0,
  "global_step": 2680,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 2e-05,
      "loss": 0.6214,
      "step": 268
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8445629477500916,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 5.2858,
      "eval_samples_per_second": 197.321,
      "eval_steps_per_second": 24.783,
      "step": 268
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 0.5559,
      "step": 536
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.807519257068634,
      "eval_matthews_correlation": 0.21580374087877008,
      "eval_runtime": 5.302,
      "eval_samples_per_second": 196.72,
      "eval_steps_per_second": 24.708,
      "step": 536
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.555555555555556e-05,
      "loss": 0.4284,
      "step": 804
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6560272574424744,
      "eval_matthews_correlation": 0.4538429410217894,
      "eval_runtime": 5.3043,
      "eval_samples_per_second": 196.635,
      "eval_steps_per_second": 24.697,
      "step": 804
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.3259,
      "step": 1072
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.7219155430793762,
      "eval_matthews_correlation": 0.4369166632963792,
      "eval_runtime": 5.3104,
      "eval_samples_per_second": 196.406,
      "eval_steps_per_second": 24.668,
      "step": 1072
    },
    {
      "epoch": 5.0,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 0.248,
      "step": 1340
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.856024980545044,
      "eval_matthews_correlation": 0.43655986862605256,
      "eval_runtime": 5.2976,
      "eval_samples_per_second": 196.881,
      "eval_steps_per_second": 24.728,
      "step": 1340
    },
    {
      "epoch": 6.0,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.1894,
      "step": 1608
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.9414917826652527,
      "eval_matthews_correlation": 0.45061623518481686,
      "eval_runtime": 5.2949,
      "eval_samples_per_second": 196.983,
      "eval_steps_per_second": 24.741,
      "step": 1608
    },
    {
      "epoch": 7.0,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1492,
      "step": 1876
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.9454582333564758,
      "eval_matthews_correlation": 0.49369621090355154,
      "eval_runtime": 5.2965,
      "eval_samples_per_second": 196.921,
      "eval_steps_per_second": 24.733,
      "step": 1876
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.1223,
      "step": 2144
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.105307936668396,
      "eval_matthews_correlation": 0.4859069062313801,
      "eval_runtime": 5.2949,
      "eval_samples_per_second": 196.982,
      "eval_steps_per_second": 24.741,
      "step": 2144
    },
    {
      "epoch": 9.0,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.1115,
      "step": 2412
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.2678706645965576,
      "eval_matthews_correlation": 0.4829638975063273,
      "eval_runtime": 5.3057,
      "eval_samples_per_second": 196.58,
      "eval_steps_per_second": 24.69,
      "step": 2412
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 0.0913,
      "step": 2680
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.2386504411697388,
      "eval_matthews_correlation": 0.4787316411367127,
      "eval_runtime": 5.3037,
      "eval_samples_per_second": 196.655,
      "eval_steps_per_second": 24.7,
      "step": 2680
    },
    {
      "epoch": 10.0,
      "step": 2680,
      "total_flos": 3851987691901440.0,
      "train_loss": 0.28432635905137704,
      "train_runtime": 1347.9437,
      "train_samples_per_second": 63.437,
      "train_steps_per_second": 1.988
    }
  ],
  "max_steps": 2680,
  "num_train_epochs": 10,
  "total_flos": 3851987691901440.0,
  "trial_name": null,
  "trial_params": null
}