Hugging Face's logo

dkqjrm
/
20230826083404

Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
dkqjrm commited on
Commit
cf0b5ac
•
1 Parent(s): 738ddd0

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: '20230826083404'
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
+ # 20230826083404
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: 0.5588
22
+ - Accuracy: 0.56
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: 0.05
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 | 0.6769 | 0.61 |
54
+ | No log | 2.0 | 50 | 0.5349 | 0.59 |
55
+ | No log | 3.0 | 75 | 0.6615 | 0.58 |
56
+ | No log | 4.0 | 100 | 0.6596 | 0.64 |
57
+ | No log | 5.0 | 125 | 0.5523 | 0.71 |
58
+ | No log | 6.0 | 150 | 0.8447 | 0.67 |
59
+ | No log | 7.0 | 175 | 0.7506 | 0.66 |
60
+ | No log | 8.0 | 200 | 0.8463 | 0.68 |
61
+ | No log | 9.0 | 225 | 0.9064 | 0.56 |
62
+ | No log | 10.0 | 250 | 0.5533 | 0.58 |
63
+ | No log | 11.0 | 275 | 0.5701 | 0.41 |
64
+ | No log | 12.0 | 300 | 0.5593 | 0.51 |
65
+ | No log | 13.0 | 325 | 0.5599 | 0.52 |
66
+ | No log | 14.0 | 350 | 0.5619 | 0.37 |
67
+ | No log | 15.0 | 375 | 0.5591 | 0.56 |
68
+ | No log | 16.0 | 400 | 0.5569 | 0.55 |
69
+ | No log | 17.0 | 425 | 0.5511 | 0.56 |
70
+ | No log | 18.0 | 450 | 0.5599 | 0.52 |
71
+ | No log | 19.0 | 475 | 0.5561 | 0.59 |
72
+ | 1.4827 | 20.0 | 500 | 0.5577 | 0.57 |
73
+ | 1.4827 | 21.0 | 525 | 0.5537 | 0.58 |
74
+ | 1.4827 | 22.0 | 550 | 0.5616 | 0.43 |
75
+ | 1.4827 | 23.0 | 575 | 0.5607 | 0.34 |
76
+ | 1.4827 | 24.0 | 600 | 0.5616 | 0.39 |
77
+ | 1.4827 | 25.0 | 625 | 0.5597 | 0.56 |
78
+ | 1.4827 | 26.0 | 650 | 0.5623 | 0.41 |
79
+ | 1.4827 | 27.0 | 675 | 0.5612 | 0.43 |
80
+ | 1.4827 | 28.0 | 700 | 0.5573 | 0.57 |
81
+ | 1.4827 | 29.0 | 725 | 0.5631 | 0.42 |
82
+ | 1.4827 | 30.0 | 750 | 0.5594 | 0.51 |
83
+ | 1.4827 | 31.0 | 775 | 0.5593 | 0.56 |
84
+ | 1.4827 | 32.0 | 800 | 0.5646 | 0.43 |
85
+ | 1.4827 | 33.0 | 825 | 0.5664 | 0.44 |
86
+ | 1.4827 | 34.0 | 850 | 0.5597 | 0.56 |
87
+ | 1.4827 | 35.0 | 875 | 0.5629 | 0.41 |
88
+ | 1.4827 | 36.0 | 900 | 0.5610 | 0.43 |
89
+ | 1.4827 | 37.0 | 925 | 0.5572 | 0.58 |
90
+ | 1.4827 | 38.0 | 950 | 0.5592 | 0.6 |
91
+ | 1.4827 | 39.0 | 975 | 0.5553 | 0.59 |
92
+ | 1.1505 | 40.0 | 1000 | 0.5597 | 0.58 |
93
+ | 1.1505 | 41.0 | 1025 | 0.5570 | 0.62 |
94
+ | 1.1505 | 42.0 | 1050 | 0.5582 | 0.6 |
95
+ | 1.1505 | 43.0 | 1075 | 0.5601 | 0.46 |
96
+ | 1.1505 | 44.0 | 1100 | 0.5598 | 0.55 |
97
+ | 1.1505 | 45.0 | 1125 | 0.5574 | 0.59 |
98
+ | 1.1505 | 46.0 | 1150 | 0.5591 | 0.52 |
99
+ | 1.1505 | 47.0 | 1175 | 0.5601 | 0.5 |
100
+ | 1.1505 | 48.0 | 1200 | 0.5593 | 0.56 |
101
+ | 1.1505 | 49.0 | 1225 | 0.5600 | 0.48 |
102
+ | 1.1505 | 50.0 | 1250 | 0.5620 | 0.39 |
103
+ | 1.1505 | 51.0 | 1275 | 0.5598 | 0.51 |
104
+ | 1.1505 | 52.0 | 1300 | 0.5616 | 0.39 |
105
+ | 1.1505 | 53.0 | 1325 | 0.5601 | 0.43 |
106
+ | 1.1505 | 54.0 | 1350 | 0.5617 | 0.4 |
107
+ | 1.1505 | 55.0 | 1375 | 0.5619 | 0.41 |
108
+ | 1.1505 | 56.0 | 1400 | 0.5625 | 0.39 |
109
+ | 1.1505 | 57.0 | 1425 | 0.5591 | 0.56 |
110
+ | 1.1505 | 58.0 | 1450 | 0.5588 | 0.59 |
111
+ | 1.1505 | 59.0 | 1475 | 0.5580 | 0.59 |
112
+ | 0.9071 | 60.0 | 1500 | 0.5584 | 0.62 |
113
+ | 0.9071 | 61.0 | 1525 | 0.5590 | 0.58 |
114
+ | 0.9071 | 62.0 | 1550 | 0.5585 | 0.57 |
115
+ | 0.9071 | 63.0 | 1575 | 0.5586 | 0.59 |
116
+ | 0.9071 | 64.0 | 1600 | 0.5589 | 0.57 |
117
+ | 0.9071 | 65.0 | 1625 | 0.5587 | 0.59 |
118
+ | 0.9071 | 66.0 | 1650 | 0.5588 | 0.61 |
119
+ | 0.9071 | 67.0 | 1675 | 0.5592 | 0.57 |
120
+ | 0.9071 | 68.0 | 1700 | 0.5579 | 0.58 |
121
+ | 0.9071 | 69.0 | 1725 | 0.5586 | 0.56 |
122
+ | 0.9071 | 70.0 | 1750 | 0.5590 | 0.57 |
123
+ | 0.9071 | 71.0 | 1775 | 0.5590 | 0.57 |
124
+ | 0.9071 | 72.0 | 1800 | 0.5590 | 0.59 |
125
+ | 0.9071 | 73.0 | 1825 | 0.5591 | 0.56 |
126
+ | 0.9071 | 74.0 | 1850 | 0.5586 | 0.56 |
127
+ | 0.9071 | 75.0 | 1875 | 0.5590 | 0.56 |
128
+ | 0.9071 | 76.0 | 1900 | 0.5592 | 0.57 |
129
+ | 0.9071 | 77.0 | 1925 | 0.5587 | 0.53 |
130
+ | 0.9071 | 78.0 | 1950 | 0.5588 | 0.56 |
131
+ | 0.9071 | 79.0 | 1975 | 0.5589 | 0.58 |
132
+ | 0.7248 | 80.0 | 2000 | 0.5588 | 0.56 |
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