Hugging Face's logo

TehranNLP-org
/
xlnet-base-cased-avg-cola-2e-5-63

Text Classification
Transformers
PyTorch
xlnet
Inference Endpoints
Model card Files Community
1
xlnet-base-cased-avg-cola-2e-5-63
File size: 4,396 Bytes 
c765284
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.512192712055601,
  "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": 0.6242,
      "step": 268
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6478146314620972,
      "eval_matthews_correlation": 0.018148342420931135,
      "eval_runtime": 5.3259,
      "eval_samples_per_second": 195.835,
      "eval_steps_per_second": 24.597,
      "step": 268
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 0.5475,
      "step": 536
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5800684690475464,
      "eval_matthews_correlation": 0.3687428254676126,
      "eval_runtime": 5.3218,
      "eval_samples_per_second": 195.987,
      "eval_steps_per_second": 24.616,
      "step": 536
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.555555555555556e-05,
      "loss": 0.4228,
      "step": 804
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.518549382686615,
      "eval_matthews_correlation": 0.4729503605591106,
      "eval_runtime": 5.3206,
      "eval_samples_per_second": 196.031,
      "eval_steps_per_second": 24.621,
      "step": 804
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.3132,
      "step": 1072
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.7433116436004639,
      "eval_matthews_correlation": 0.4456190824541546,
      "eval_runtime": 5.2944,
      "eval_samples_per_second": 197.001,
      "eval_steps_per_second": 24.743,
      "step": 1072
    },
    {
      "epoch": 5.0,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 0.2426,
      "step": 1340
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.7162166833877563,
      "eval_matthews_correlation": 0.4729503605591106,
      "eval_runtime": 5.3233,
      "eval_samples_per_second": 195.929,
      "eval_steps_per_second": 24.609,
      "step": 1340
    },
    {
      "epoch": 6.0,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.1892,
      "step": 1608
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.7776421308517456,
      "eval_matthews_correlation": 0.48239382723457414,
      "eval_runtime": 5.3253,
      "eval_samples_per_second": 195.858,
      "eval_steps_per_second": 24.6,
      "step": 1608
    },
    {
      "epoch": 7.0,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1555,
      "step": 1876
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.855113685131073,
      "eval_matthews_correlation": 0.512192712055601,
      "eval_runtime": 5.304,
      "eval_samples_per_second": 196.642,
      "eval_steps_per_second": 24.698,
      "step": 1876
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.123,
      "step": 2144
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.1328730583190918,
      "eval_matthews_correlation": 0.47806047639386823,
      "eval_runtime": 5.3251,
      "eval_samples_per_second": 195.866,
      "eval_steps_per_second": 24.601,
      "step": 2144
    },
    {
      "epoch": 9.0,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.096,
      "step": 2412
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.1940616369247437,
      "eval_matthews_correlation": 0.47687961708523924,
      "eval_runtime": 5.3349,
      "eval_samples_per_second": 195.504,
      "eval_steps_per_second": 24.555,
      "step": 2412
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 0.0864,
      "step": 2680
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.3239350318908691,
      "eval_matthews_correlation": 0.45569507663230396,
      "eval_runtime": 5.3171,
      "eval_samples_per_second": 196.161,
      "eval_steps_per_second": 24.638,
      "step": 2680
    },
    {
      "epoch": 10.0,
      "step": 2680,
      "total_flos": 3851987691901440.0,
      "train_loss": 0.28002330011396265,
      "train_runtime": 1315.8713,
      "train_samples_per_second": 64.984,
      "train_steps_per_second": 2.037
    }
  ],
  "max_steps": 2680,
  "num_train_epochs": 10,
  "total_flos": 3851987691901440.0,
  "trial_name": null,
  "trial_params": null
}