Hugging Face's logo

henryscheible
/
bert-large-uncased_winobias_classifieronly

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
2
henryscheible commited on
Commit
a088947
·
1 Parent(s): ccab5d9

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +97 -0
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: bert-large-uncased_winobias_classifieronly
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # bert-large-uncased_winobias_classifieronly
16
+
17
+ This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.6934
20
+ - Accuracy: 0.5095
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
+ - train_batch_size: 128
41
+ - eval_batch_size: 64
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 15
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | No log | 0.38 | 5 | 0.8249 | 0.4987 |
52
+ | No log | 0.77 | 10 | 0.8058 | 0.4987 |
53
+ | No log | 1.15 | 15 | 0.7886 | 0.4987 |
54
+ | No log | 1.54 | 20 | 0.7731 | 0.4987 |
55
+ | No log | 1.92 | 25 | 0.7593 | 0.4981 |
56
+ | No log | 2.31 | 30 | 0.7470 | 0.4987 |
57
+ | No log | 2.69 | 35 | 0.7363 | 0.4994 |
58
+ | No log | 3.08 | 40 | 0.7276 | 0.4994 |
59
+ | No log | 3.46 | 45 | 0.7205 | 0.4994 |
60
+ | No log | 3.85 | 50 | 0.7142 | 0.5 |
61
+ | No log | 4.23 | 55 | 0.7088 | 0.5 |
62
+ | No log | 4.62 | 60 | 0.7044 | 0.4994 |
63
+ | No log | 5.0 | 65 | 0.7009 | 0.5 |
64
+ | No log | 5.38 | 70 | 0.6983 | 0.5013 |
65
+ | No log | 5.77 | 75 | 0.6966 | 0.5006 |
66
+ | No log | 6.15 | 80 | 0.6955 | 0.4994 |
67
+ | No log | 6.54 | 85 | 0.6948 | 0.5032 |
68
+ | No log | 6.92 | 90 | 0.6943 | 0.5158 |
69
+ | No log | 7.31 | 95 | 0.6940 | 0.5114 |
70
+ | No log | 7.69 | 100 | 0.6938 | 0.5120 |
71
+ | No log | 8.08 | 105 | 0.6936 | 0.5088 |
72
+ | No log | 8.46 | 110 | 0.6936 | 0.5101 |
73
+ | No log | 8.85 | 115 | 0.6935 | 0.5101 |
74
+ | No log | 9.23 | 120 | 0.6935 | 0.5107 |
75
+ | No log | 9.62 | 125 | 0.6934 | 0.5120 |
76
+ | No log | 10.0 | 130 | 0.6934 | 0.5107 |
77
+ | No log | 10.38 | 135 | 0.6934 | 0.5126 |
78
+ | No log | 10.77 | 140 | 0.6934 | 0.5133 |
79
+ | No log | 11.15 | 145 | 0.6934 | 0.5139 |
80
+ | No log | 11.54 | 150 | 0.6934 | 0.5114 |
81
+ | No log | 11.92 | 155 | 0.6934 | 0.5088 |
82
+ | No log | 12.31 | 160 | 0.6934 | 0.5076 |
83
+ | No log | 12.69 | 165 | 0.6934 | 0.5063 |
84
+ | No log | 13.08 | 170 | 0.6934 | 0.5101 |
85
+ | No log | 13.46 | 175 | 0.6934 | 0.5107 |
86
+ | No log | 13.85 | 180 | 0.6934 | 0.5101 |
87
+ | No log | 14.23 | 185 | 0.6934 | 0.5095 |
88
+ | No log | 14.62 | 190 | 0.6934 | 0.5095 |
89
+ | No log | 15.0 | 195 | 0.6934 | 0.5095 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - Transformers 4.26.1
95
+ - Pytorch 1.13.1
96
+ - Datasets 2.10.1
97
+ - Tokenizers 0.13.2