Hugging Face's logo

TehranNLP-org
/
electra-base-avg-cola-2e-5-21

Text Classification
Transformers
PyTorch
electra
Inference Endpoints
Model card Files Community
electra-base-avg-cola-2e-5-21
File size: 4,393 Bytes 
70c82c2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.7068649074843276,
  "best_model_checkpoint": "./bert-base-uncased/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": 0.4974,
      "step": 268
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.3856096863746643,
      "eval_matthews_correlation": 0.6039307167689609,
      "eval_runtime": 4.0975,
      "eval_samples_per_second": 254.544,
      "eval_steps_per_second": 31.971,
      "step": 268
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 0.3024,
      "step": 536
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.3309681713581085,
      "eval_matthews_correlation": 0.6557131266546689,
      "eval_runtime": 4.2881,
      "eval_samples_per_second": 243.234,
      "eval_steps_per_second": 30.55,
      "step": 536
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.555555555555556e-05,
      "loss": 0.1855,
      "step": 804
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.3909442722797394,
      "eval_matthews_correlation": 0.6679153499290561,
      "eval_runtime": 4.2794,
      "eval_samples_per_second": 243.728,
      "eval_steps_per_second": 30.612,
      "step": 804
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.1278,
      "step": 1072
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.4562387764453888,
      "eval_matthews_correlation": 0.6657078975506158,
      "eval_runtime": 4.2964,
      "eval_samples_per_second": 242.759,
      "eval_steps_per_second": 30.49,
      "step": 1072
    },
    {
      "epoch": 5.0,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 0.094,
      "step": 1340
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.634463906288147,
      "eval_matthews_correlation": 0.6304318137769176,
      "eval_runtime": 4.2802,
      "eval_samples_per_second": 243.682,
      "eval_steps_per_second": 30.606,
      "step": 1340
    },
    {
      "epoch": 6.0,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.0685,
      "step": 1608
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6211329698562622,
      "eval_matthews_correlation": 0.6700089525749314,
      "eval_runtime": 4.2939,
      "eval_samples_per_second": 242.905,
      "eval_steps_per_second": 30.509,
      "step": 1608
    },
    {
      "epoch": 7.0,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.048,
      "step": 1876
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.580573558807373,
      "eval_matthews_correlation": 0.7068649074843276,
      "eval_runtime": 4.3122,
      "eval_samples_per_second": 241.873,
      "eval_steps_per_second": 30.379,
      "step": 1876
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.0352,
      "step": 2144
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.6809670329093933,
      "eval_matthews_correlation": 0.6773861896003048,
      "eval_runtime": 4.3021,
      "eval_samples_per_second": 242.442,
      "eval_steps_per_second": 30.451,
      "step": 2144
    },
    {
      "epoch": 9.0,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.0253,
      "step": 2412
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.7312929034233093,
      "eval_matthews_correlation": 0.6850707271866645,
      "eval_runtime": 4.3106,
      "eval_samples_per_second": 241.961,
      "eval_steps_per_second": 30.39,
      "step": 2412
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 0.0181,
      "step": 2680
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.7737548351287842,
      "eval_matthews_correlation": 0.6578435355005723,
      "eval_runtime": 4.3001,
      "eval_samples_per_second": 242.555,
      "eval_steps_per_second": 30.465,
      "step": 2680
    },
    {
      "epoch": 10.0,
      "step": 2680,
      "total_flos": 3594991817003520.0,
      "train_loss": 0.14022661696619063,
      "train_runtime": 1094.6693,
      "train_samples_per_second": 78.115,
      "train_steps_per_second": 2.448
    }
  ],
  "max_steps": 2680,
  "num_train_epochs": 10,
  "total_flos": 3594991817003520.0,
  "trial_name": null,
  "trial_params": null
}