Hugging Face's logo

dkqjrm
/
20230826121217

Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
dkqjrm commited on
Commit
104d9a7
•
1 Parent(s): 885f566

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +140 -0
README.md ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - super_glue
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: '20230826121217'
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # 20230826121217
18
+
19
+ This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on the super_glue dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4150
22
+ - Accuracy: 0.63
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.001
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 8
44
+ - seed: 11
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 80.0
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 25 | 0.4146 | 0.66 |
54
+ | No log | 2.0 | 50 | 0.4116 | 0.66 |
55
+ | No log | 3.0 | 75 | 0.4139 | 0.66 |
56
+ | No log | 4.0 | 100 | 0.4170 | 0.64 |
57
+ | No log | 5.0 | 125 | 0.4182 | 0.65 |
58
+ | No log | 6.0 | 150 | 0.4208 | 0.57 |
59
+ | No log | 7.0 | 175 | 0.4115 | 0.66 |
60
+ | No log | 8.0 | 200 | 0.4157 | 0.66 |
61
+ | No log | 9.0 | 225 | 0.4229 | 0.64 |
62
+ | No log | 10.0 | 250 | 0.4205 | 0.65 |
63
+ | No log | 11.0 | 275 | 0.4178 | 0.64 |
64
+ | No log | 12.0 | 300 | 0.4131 | 0.67 |
65
+ | No log | 13.0 | 325 | 0.4146 | 0.65 |
66
+ | No log | 14.0 | 350 | 0.4202 | 0.63 |
67
+ | No log | 15.0 | 375 | 0.4331 | 0.62 |
68
+ | No log | 16.0 | 400 | 0.4120 | 0.66 |
69
+ | No log | 17.0 | 425 | 0.4144 | 0.63 |
70
+ | No log | 18.0 | 450 | 0.4182 | 0.64 |
71
+ | No log | 19.0 | 475 | 0.4184 | 0.59 |
72
+ | 0.5392 | 20.0 | 500 | 0.4161 | 0.65 |
73
+ | 0.5392 | 21.0 | 525 | 0.4185 | 0.64 |
74
+ | 0.5392 | 22.0 | 550 | 0.4187 | 0.59 |
75
+ | 0.5392 | 23.0 | 575 | 0.4186 | 0.62 |
76
+ | 0.5392 | 24.0 | 600 | 0.4159 | 0.65 |
77
+ | 0.5392 | 25.0 | 625 | 0.4152 | 0.64 |
78
+ | 0.5392 | 26.0 | 650 | 0.4151 | 0.62 |
79
+ | 0.5392 | 27.0 | 675 | 0.4136 | 0.63 |
80
+ | 0.5392 | 28.0 | 700 | 0.4190 | 0.65 |
81
+ | 0.5392 | 29.0 | 725 | 0.4225 | 0.61 |
82
+ | 0.5392 | 30.0 | 750 | 0.4209 | 0.57 |
83
+ | 0.5392 | 31.0 | 775 | 0.4167 | 0.63 |
84
+ | 0.5392 | 32.0 | 800 | 0.4153 | 0.62 |
85
+ | 0.5392 | 33.0 | 825 | 0.4236 | 0.6 |
86
+ | 0.5392 | 34.0 | 850 | 0.4191 | 0.58 |
87
+ | 0.5392 | 35.0 | 875 | 0.4160 | 0.61 |
88
+ | 0.5392 | 36.0 | 900 | 0.4163 | 0.62 |
89
+ | 0.5392 | 37.0 | 925 | 0.4193 | 0.59 |
90
+ | 0.5392 | 38.0 | 950 | 0.4208 | 0.62 |
91
+ | 0.5392 | 39.0 | 975 | 0.4163 | 0.6 |
92
+ | 0.5359 | 40.0 | 1000 | 0.4159 | 0.6 |
93
+ | 0.5359 | 41.0 | 1025 | 0.4146 | 0.62 |
94
+ | 0.5359 | 42.0 | 1050 | 0.4158 | 0.6 |
95
+ | 0.5359 | 43.0 | 1075 | 0.4211 | 0.59 |
96
+ | 0.5359 | 44.0 | 1100 | 0.4203 | 0.59 |
97
+ | 0.5359 | 45.0 | 1125 | 0.4217 | 0.57 |
98
+ | 0.5359 | 46.0 | 1150 | 0.4183 | 0.6 |
99
+ | 0.5359 | 47.0 | 1175 | 0.4138 | 0.63 |
100
+ | 0.5359 | 48.0 | 1200 | 0.4124 | 0.63 |
101
+ | 0.5359 | 49.0 | 1225 | 0.4140 | 0.63 |
102
+ | 0.5359 | 50.0 | 1250 | 0.4118 | 0.64 |
103
+ | 0.5359 | 51.0 | 1275 | 0.4137 | 0.62 |
104
+ | 0.5359 | 52.0 | 1300 | 0.4113 | 0.63 |
105
+ | 0.5359 | 53.0 | 1325 | 0.4112 | 0.62 |
106
+ | 0.5359 | 54.0 | 1350 | 0.4140 | 0.63 |
107
+ | 0.5359 | 55.0 | 1375 | 0.4129 | 0.64 |
108
+ | 0.5359 | 56.0 | 1400 | 0.4151 | 0.64 |
109
+ | 0.5359 | 57.0 | 1425 | 0.4155 | 0.63 |
110
+ | 0.5359 | 58.0 | 1450 | 0.4140 | 0.63 |
111
+ | 0.5359 | 59.0 | 1475 | 0.4145 | 0.64 |
112
+ | 0.5347 | 60.0 | 1500 | 0.4158 | 0.63 |
113
+ | 0.5347 | 61.0 | 1525 | 0.4148 | 0.62 |
114
+ | 0.5347 | 62.0 | 1550 | 0.4147 | 0.6 |
115
+ | 0.5347 | 63.0 | 1575 | 0.4153 | 0.64 |
116
+ | 0.5347 | 64.0 | 1600 | 0.4156 | 0.63 |
117
+ | 0.5347 | 65.0 | 1625 | 0.4152 | 0.64 |
118
+ | 0.5347 | 66.0 | 1650 | 0.4146 | 0.64 |
119
+ | 0.5347 | 67.0 | 1675 | 0.4151 | 0.64 |
120
+ | 0.5347 | 68.0 | 1700 | 0.4145 | 0.61 |
121
+ | 0.5347 | 69.0 | 1725 | 0.4153 | 0.61 |
122
+ | 0.5347 | 70.0 | 1750 | 0.4147 | 0.64 |
123
+ | 0.5347 | 71.0 | 1775 | 0.4146 | 0.64 |
124
+ | 0.5347 | 72.0 | 1800 | 0.4134 | 0.62 |
125
+ | 0.5347 | 73.0 | 1825 | 0.4140 | 0.63 |
126
+ | 0.5347 | 74.0 | 1850 | 0.4141 | 0.64 |
127
+ | 0.5347 | 75.0 | 1875 | 0.4151 | 0.63 |
128
+ | 0.5347 | 76.0 | 1900 | 0.4150 | 0.62 |
129
+ | 0.5347 | 77.0 | 1925 | 0.4148 | 0.61 |
130
+ | 0.5347 | 78.0 | 1950 | 0.4149 | 0.62 |
131
+ | 0.5347 | 79.0 | 1975 | 0.4150 | 0.63 |
132
+ | 0.5285 | 80.0 | 2000 | 0.4150 | 0.63 |
133
+
134
+
135
+ ### Framework versions
136
+
137
+ - Transformers 4.26.1
138
+ - Pytorch 2.0.1+cu118
139
+ - Datasets 2.12.0
140
+ - Tokenizers 0.13.3