Hugging Face's logo

henryscheible
/
bert-base-uncased_stereoset_finetuned

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
2
henryscheible commited on
Commit
2f97ee7
·
1 Parent(s): 3f4de64

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +121 -0
README.md ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-base-uncased_stereoset_finetuned
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: 0.7260596546310832
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-base-uncased_stereoset_finetuned
31
+
32
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the stereoset dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 1.3464
35
+ - Accuracy: 0.7261
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: 5e-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: 10
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | No log | 0.21 | 5 | 0.6832 | 0.5565 |
67
+ | No log | 0.42 | 10 | 0.6945 | 0.4741 |
68
+ | No log | 0.62 | 15 | 0.6659 | 0.6224 |
69
+ | No log | 0.83 | 20 | 0.6337 | 0.6758 |
70
+ | No log | 1.04 | 25 | 0.6019 | 0.6695 |
71
+ | No log | 1.25 | 30 | 0.5797 | 0.7096 |
72
+ | No log | 1.46 | 35 | 0.5562 | 0.7166 |
73
+ | No log | 1.67 | 40 | 0.5497 | 0.7363 |
74
+ | No log | 1.88 | 45 | 0.5382 | 0.7418 |
75
+ | No log | 2.08 | 50 | 0.5356 | 0.7418 |
76
+ | No log | 2.29 | 55 | 0.5690 | 0.7316 |
77
+ | No log | 2.5 | 60 | 0.5778 | 0.7418 |
78
+ | No log | 2.71 | 65 | 0.5695 | 0.7386 |
79
+ | No log | 2.92 | 70 | 0.5765 | 0.7386 |
80
+ | No log | 3.12 | 75 | 0.6079 | 0.7363 |
81
+ | No log | 3.33 | 80 | 0.6919 | 0.7370 |
82
+ | No log | 3.54 | 85 | 0.7396 | 0.7339 |
83
+ | No log | 3.75 | 90 | 0.7109 | 0.7339 |
84
+ | No log | 3.96 | 95 | 0.7246 | 0.7308 |
85
+ | No log | 4.17 | 100 | 0.7502 | 0.7292 |
86
+ | No log | 4.38 | 105 | 0.8222 | 0.7331 |
87
+ | No log | 4.58 | 110 | 0.8508 | 0.7268 |
88
+ | No log | 4.79 | 115 | 0.8995 | 0.7378 |
89
+ | No log | 5.0 | 120 | 0.8797 | 0.7323 |
90
+ | No log | 5.21 | 125 | 0.9254 | 0.7370 |
91
+ | No log | 5.42 | 130 | 0.9863 | 0.7292 |
92
+ | No log | 5.62 | 135 | 1.0044 | 0.7198 |
93
+ | No log | 5.83 | 140 | 1.0236 | 0.7339 |
94
+ | No log | 6.04 | 145 | 1.0705 | 0.7355 |
95
+ | No log | 6.25 | 150 | 1.0734 | 0.7323 |
96
+ | No log | 6.46 | 155 | 1.1066 | 0.7300 |
97
+ | No log | 6.67 | 160 | 1.1166 | 0.7292 |
98
+ | No log | 6.88 | 165 | 1.1258 | 0.7370 |
99
+ | No log | 7.08 | 170 | 1.1972 | 0.7300 |
100
+ | No log | 7.29 | 175 | 1.1682 | 0.7268 |
101
+ | No log | 7.5 | 180 | 1.2221 | 0.7166 |
102
+ | No log | 7.71 | 185 | 1.2813 | 0.7151 |
103
+ | No log | 7.92 | 190 | 1.3180 | 0.7214 |
104
+ | No log | 8.12 | 195 | 1.3224 | 0.7166 |
105
+ | No log | 8.33 | 200 | 1.3252 | 0.7135 |
106
+ | No log | 8.54 | 205 | 1.3205 | 0.7221 |
107
+ | No log | 8.75 | 210 | 1.3266 | 0.7245 |
108
+ | No log | 8.96 | 215 | 1.3318 | 0.7206 |
109
+ | No log | 9.17 | 220 | 1.3345 | 0.7237 |
110
+ | No log | 9.38 | 225 | 1.3378 | 0.7245 |
111
+ | No log | 9.58 | 230 | 1.3422 | 0.7261 |
112
+ | No log | 9.79 | 235 | 1.3453 | 0.7261 |
113
+ | No log | 10.0 | 240 | 1.3464 | 0.7261 |
114
+
115
+
116
+ ### Framework versions
117
+
118
+ - Transformers 4.26.1
119
+ - Pytorch 1.13.1
120
+ - Datasets 2.9.0
121
+ - Tokenizers 0.13.2