Hugging Face's logo

henryscheible
/
bert-large-uncased_stereoset_classifieronly

Text Classification
Transformers
PyTorch
bert
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Community
1
henryscheible commited on
Commit
af5986c
•
1 Parent(s): b337874

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +145 -0
README.md ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - stereoset
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: bert-large-uncased_stereoset_classifieronly
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: stereoset
17
+ type: stereoset
18
+ config: intersentence
19
+ split: validation
20
+ args: intersentence
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.5188383045525903
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # bert-large-uncased_stereoset_classifieronly
31
+
32
+ This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the stereoset dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.6912
35
+ - Accuracy: 0.5188
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 1e-05
55
+ - train_batch_size: 128
56
+ - eval_batch_size: 64
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 15
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | No log | 0.21 | 5 | 0.6983 | 0.5196 |
67
+ | No log | 0.42 | 10 | 0.6971 | 0.5228 |
68
+ | No log | 0.62 | 15 | 0.6962 | 0.5212 |
69
+ | No log | 0.83 | 20 | 0.6956 | 0.5196 |
70
+ | No log | 1.04 | 25 | 0.6947 | 0.5204 |
71
+ | No log | 1.25 | 30 | 0.6941 | 0.5243 |
72
+ | No log | 1.46 | 35 | 0.6938 | 0.5243 |
73
+ | No log | 1.67 | 40 | 0.6933 | 0.5181 |
74
+ | No log | 1.88 | 45 | 0.6932 | 0.5196 |
75
+ | No log | 2.08 | 50 | 0.6932 | 0.5188 |
76
+ | No log | 2.29 | 55 | 0.6930 | 0.5181 |
77
+ | No log | 2.5 | 60 | 0.6929 | 0.5181 |
78
+ | No log | 2.71 | 65 | 0.6929 | 0.5220 |
79
+ | No log | 2.92 | 70 | 0.6928 | 0.5196 |
80
+ | No log | 3.12 | 75 | 0.6927 | 0.5181 |
81
+ | No log | 3.33 | 80 | 0.6928 | 0.5243 |
82
+ | No log | 3.54 | 85 | 0.6930 | 0.5275 |
83
+ | No log | 3.75 | 90 | 0.6934 | 0.5243 |
84
+ | No log | 3.96 | 95 | 0.6932 | 0.5243 |
85
+ | No log | 4.17 | 100 | 0.6929 | 0.5259 |
86
+ | No log | 4.38 | 105 | 0.6927 | 0.5235 |
87
+ | No log | 4.58 | 110 | 0.6925 | 0.5204 |
88
+ | No log | 4.79 | 115 | 0.6923 | 0.5173 |
89
+ | No log | 5.0 | 120 | 0.6922 | 0.5173 |
90
+ | No log | 5.21 | 125 | 0.6921 | 0.5181 |
91
+ | No log | 5.42 | 130 | 0.6921 | 0.5173 |
92
+ | No log | 5.62 | 135 | 0.6921 | 0.5173 |
93
+ | No log | 5.83 | 140 | 0.6920 | 0.5173 |
94
+ | No log | 6.04 | 145 | 0.6921 | 0.5188 |
95
+ | No log | 6.25 | 150 | 0.6923 | 0.5220 |
96
+ | No log | 6.46 | 155 | 0.6925 | 0.5235 |
97
+ | No log | 6.67 | 160 | 0.6925 | 0.5235 |
98
+ | No log | 6.88 | 165 | 0.6923 | 0.5228 |
99
+ | No log | 7.08 | 170 | 0.6921 | 0.5204 |
100
+ | No log | 7.29 | 175 | 0.6918 | 0.5196 |
101
+ | No log | 7.5 | 180 | 0.6916 | 0.5188 |
102
+ | No log | 7.71 | 185 | 0.6914 | 0.5173 |
103
+ | No log | 7.92 | 190 | 0.6915 | 0.5204 |
104
+ | No log | 8.12 | 195 | 0.6916 | 0.5196 |
105
+ | No log | 8.33 | 200 | 0.6918 | 0.5204 |
106
+ | No log | 8.54 | 205 | 0.6917 | 0.5181 |
107
+ | No log | 8.75 | 210 | 0.6917 | 0.5204 |
108
+ | No log | 8.96 | 215 | 0.6919 | 0.5220 |
109
+ | No log | 9.17 | 220 | 0.6916 | 0.5212 |
110
+ | No log | 9.38 | 225 | 0.6914 | 0.5196 |
111
+ | No log | 9.58 | 230 | 0.6913 | 0.5173 |
112
+ | No log | 9.79 | 235 | 0.6913 | 0.5188 |
113
+ | No log | 10.0 | 240 | 0.6915 | 0.5188 |
114
+ | No log | 10.21 | 245 | 0.6916 | 0.5212 |
115
+ | No log | 10.42 | 250 | 0.6916 | 0.5212 |
116
+ | No log | 10.62 | 255 | 0.6915 | 0.5212 |
117
+ | No log | 10.83 | 260 | 0.6915 | 0.5188 |
118
+ | No log | 11.04 | 265 | 0.6914 | 0.5188 |
119
+ | No log | 11.25 | 270 | 0.6913 | 0.5188 |
120
+ | No log | 11.46 | 275 | 0.6913 | 0.5181 |
121
+ | No log | 11.67 | 280 | 0.6912 | 0.5173 |
122
+ | No log | 11.88 | 285 | 0.6912 | 0.5181 |
123
+ | No log | 12.08 | 290 | 0.6911 | 0.5188 |
124
+ | No log | 12.29 | 295 | 0.6911 | 0.5196 |
125
+ | No log | 12.5 | 300 | 0.6911 | 0.5204 |
126
+ | No log | 12.71 | 305 | 0.6911 | 0.5196 |
127
+ | No log | 12.92 | 310 | 0.6910 | 0.5196 |
128
+ | No log | 13.12 | 315 | 0.6911 | 0.5204 |
129
+ | No log | 13.33 | 320 | 0.6911 | 0.5196 |
130
+ | No log | 13.54 | 325 | 0.6911 | 0.5204 |
131
+ | No log | 13.75 | 330 | 0.6911 | 0.5188 |
132
+ | No log | 13.96 | 335 | 0.6912 | 0.5188 |
133
+ | No log | 14.17 | 340 | 0.6912 | 0.5188 |
134
+ | No log | 14.38 | 345 | 0.6912 | 0.5188 |
135
+ | No log | 14.58 | 350 | 0.6912 | 0.5188 |
136
+ | No log | 14.79 | 355 | 0.6912 | 0.5188 |
137
+ | No log | 15.0 | 360 | 0.6912 | 0.5188 |
138
+
139
+
140
+ ### Framework versions
141
+
142
+ - Transformers 4.26.1
143
+ - Pytorch 1.13.1
144
+ - Datasets 2.10.1
145
+ - Tokenizers 0.13.2