Hugging Face's logo

TehranNLP-org
/
electra-base-avg-sst2-2e-5-42

Text Classification
Transformers
PyTorch
electra
Inference Endpoints
Model card Files Community
electra-base-avg-sst2-2e-5-42
File size: 4,334 Bytes 
c432906
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9541284403669725,
  "best_model_checkpoint": "./electra-base-discriminator/fine_tuned_models/checkpoint-8420",
  "epoch": 10.0,
  "global_step": 21050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 1.8398562688161604e-05,
      "loss": 0.228,
      "step": 2105
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9426605504587156,
      "eval_loss": 0.19972862303256989,
      "eval_runtime": 3.5276,
      "eval_samples_per_second": 247.196,
      "eval_steps_per_second": 30.9,
      "step": 2105
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.6354277945032536e-05,
      "loss": 0.1181,
      "step": 4210
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.948394495412844,
      "eval_loss": 0.19976772367954254,
      "eval_runtime": 3.5381,
      "eval_samples_per_second": 246.462,
      "eval_steps_per_second": 30.808,
      "step": 4210
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.4309993201903469e-05,
      "loss": 0.0879,
      "step": 6315
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9461009174311926,
      "eval_loss": 0.2184586375951767,
      "eval_runtime": 3.5293,
      "eval_samples_per_second": 247.074,
      "eval_steps_per_second": 30.884,
      "step": 6315
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.2265708458774402e-05,
      "loss": 0.0671,
      "step": 8420
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9541284403669725,
      "eval_loss": 0.18563394248485565,
      "eval_runtime": 3.533,
      "eval_samples_per_second": 246.815,
      "eval_steps_per_second": 30.852,
      "step": 8420
    },
    {
      "epoch": 5.0,
      "learning_rate": 1.0221423715645335e-05,
      "loss": 0.0512,
      "step": 10525
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9472477064220184,
      "eval_loss": 0.24747443199157715,
      "eval_runtime": 3.5309,
      "eval_samples_per_second": 246.965,
      "eval_steps_per_second": 30.871,
      "step": 10525
    },
    {
      "epoch": 6.0,
      "learning_rate": 8.177138972516268e-06,
      "loss": 0.0396,
      "step": 12630
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.948394495412844,
      "eval_loss": 0.20705512166023254,
      "eval_runtime": 3.5235,
      "eval_samples_per_second": 247.482,
      "eval_steps_per_second": 30.935,
      "step": 12630
    },
    {
      "epoch": 7.0,
      "learning_rate": 6.132854229387201e-06,
      "loss": 0.0303,
      "step": 14735
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9461009174311926,
      "eval_loss": 0.25413599610328674,
      "eval_runtime": 3.5256,
      "eval_samples_per_second": 247.331,
      "eval_steps_per_second": 30.916,
      "step": 14735
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.088569486258134e-06,
      "loss": 0.0221,
      "step": 16840
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9380733944954128,
      "eval_loss": 0.29228484630584717,
      "eval_runtime": 3.5294,
      "eval_samples_per_second": 247.067,
      "eval_steps_per_second": 30.883,
      "step": 16840
    },
    {
      "epoch": 9.0,
      "learning_rate": 2.044284743129067e-06,
      "loss": 0.0173,
      "step": 18945
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9426605504587156,
      "eval_loss": 0.32282954454421997,
      "eval_runtime": 3.5271,
      "eval_samples_per_second": 247.23,
      "eval_steps_per_second": 30.904,
      "step": 18945
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 0.0117,
      "step": 21050
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9461009174311926,
      "eval_loss": 0.3563162386417389,
      "eval_runtime": 3.5159,
      "eval_samples_per_second": 248.017,
      "eval_steps_per_second": 31.002,
      "step": 21050
    },
    {
      "epoch": 10.0,
      "step": 21050,
      "total_flos": 2.831471218376448e+16,
      "train_loss": 0.06732057612185807,
      "train_runtime": 7753.7046,
      "train_samples_per_second": 86.86,
      "train_steps_per_second": 2.715
    }
  ],
  "max_steps": 21050,
  "num_train_epochs": 10,
  "total_flos": 2.831471218376448e+16,
  "trial_name": null,
  "trial_params": null
}