Hugging Face's logo

TehranNLP-org
/
electra-base-avg-cola

Text Classification
Transformers
PyTorch
electra
Inference Endpoints
Model card Files Community
electra-base-avg-cola
File size: 3,779 Bytes 
627b641
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.667660908939119,
  "best_model_checkpoint": "/content/output_dir/checkpoint-2412",
  "epoch": 9.0,
  "global_step": 2412,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 9.280492497114274e-05,
      "loss": 0.4622,
      "step": 268
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5115634202957153,
      "eval_matthews_correlation": 0.5385290213636863,
      "eval_runtime": 7.985,
      "eval_samples_per_second": 130.62,
      "eval_steps_per_second": 16.406,
      "step": 268
    },
    {
      "epoch": 2.0,
      "learning_rate": 8.249326664101577e-05,
      "loss": 0.2823,
      "step": 536
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.4201788902282715,
      "eval_matthews_correlation": 0.6035894895952164,
      "eval_runtime": 8.0283,
      "eval_samples_per_second": 129.916,
      "eval_steps_per_second": 16.317,
      "step": 536
    },
    {
      "epoch": 3.0,
      "learning_rate": 7.218160831088881e-05,
      "loss": 0.1804,
      "step": 804
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.580650806427002,
      "eval_matthews_correlation": 0.5574138665741355,
      "eval_runtime": 8.1314,
      "eval_samples_per_second": 128.268,
      "eval_steps_per_second": 16.11,
      "step": 804
    },
    {
      "epoch": 4.0,
      "learning_rate": 6.186994998076183e-05,
      "loss": 0.1357,
      "step": 1072
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.4439031779766083,
      "eval_matthews_correlation": 0.6557697896854868,
      "eval_runtime": 8.1435,
      "eval_samples_per_second": 128.078,
      "eval_steps_per_second": 16.087,
      "step": 1072
    },
    {
      "epoch": 5.0,
      "learning_rate": 5.155829165063486e-05,
      "loss": 0.0913,
      "step": 1340
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.5736830830574036,
      "eval_matthews_correlation": 0.6249925495853809,
      "eval_runtime": 8.0533,
      "eval_samples_per_second": 129.512,
      "eval_steps_per_second": 16.267,
      "step": 1340
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.1246633320507885e-05,
      "loss": 0.065,
      "step": 1608
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.7729296684265137,
      "eval_matthews_correlation": 0.6188970025554703,
      "eval_runtime": 8.081,
      "eval_samples_per_second": 129.068,
      "eval_steps_per_second": 16.211,
      "step": 1608
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.093497499038092e-05,
      "loss": 0.0433,
      "step": 1876
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.7351673245429993,
      "eval_matthews_correlation": 0.6405767700619004,
      "eval_runtime": 8.1372,
      "eval_samples_per_second": 128.176,
      "eval_steps_per_second": 16.099,
      "step": 1876
    },
    {
      "epoch": 8.0,
      "learning_rate": 2.0623316660253942e-05,
      "loss": 0.0199,
      "step": 2144
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.7900031208992004,
      "eval_matthews_correlation": 0.6565021466238845,
      "eval_runtime": 8.1095,
      "eval_samples_per_second": 128.615,
      "eval_steps_per_second": 16.154,
      "step": 2144
    },
    {
      "epoch": 9.0,
      "learning_rate": 1.0311658330126971e-05,
      "loss": 0.0114,
      "step": 2412
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.8539554476737976,
      "eval_matthews_correlation": 0.667660908939119,
      "eval_runtime": 8.1204,
      "eval_samples_per_second": 128.442,
      "eval_steps_per_second": 16.132,
      "step": 2412
    }
  ],
  "max_steps": 2680,
  "num_train_epochs": 10,
  "total_flos": 6470985270606336.0,
  "trial_name": null,
  "trial_params": null
}