Hugging Face's logo

simonycl
/
bert-large-uncased-sst-2-32-13-smoothed

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
simonycl commited on
Commit
ac21521
•
1 Parent(s): 738fec8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +136 -0
README.md ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-large-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: bert-large-uncased-sst-2-32-13-smoothed
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # bert-large-uncased-sst-2-32-13-smoothed
17
+
18
+ This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6595
21
+ - Accuracy: 0.75
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 50
47
+ - num_epochs: 75
48
+ - label_smoothing_factor: 0.45
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | No log | 1.0 | 2 | 0.8178 | 0.5156 |
55
+ | No log | 2.0 | 4 | 0.8133 | 0.5156 |
56
+ | No log | 3.0 | 6 | 0.8065 | 0.5156 |
57
+ | No log | 4.0 | 8 | 0.7961 | 0.5156 |
58
+ | 0.8123 | 5.0 | 10 | 0.7821 | 0.5156 |
59
+ | 0.8123 | 6.0 | 12 | 0.7655 | 0.5 |
60
+ | 0.8123 | 7.0 | 14 | 0.7460 | 0.5 |
61
+ | 0.8123 | 8.0 | 16 | 0.7247 | 0.5 |
62
+ | 0.8123 | 9.0 | 18 | 0.7034 | 0.5312 |
63
+ | 0.751 | 10.0 | 20 | 0.6892 | 0.5938 |
64
+ | 0.751 | 11.0 | 22 | 0.6808 | 0.6094 |
65
+ | 0.751 | 12.0 | 24 | 0.6761 | 0.6719 |
66
+ | 0.751 | 13.0 | 26 | 0.6715 | 0.75 |
67
+ | 0.751 | 14.0 | 28 | 0.6665 | 0.7812 |
68
+ | 0.6479 | 15.0 | 30 | 0.6624 | 0.75 |
69
+ | 0.6479 | 16.0 | 32 | 0.6615 | 0.7344 |
70
+ | 0.6479 | 17.0 | 34 | 0.6572 | 0.7344 |
71
+ | 0.6479 | 18.0 | 36 | 0.6529 | 0.7656 |
72
+ | 0.6479 | 19.0 | 38 | 0.6503 | 0.7969 |
73
+ | 0.5876 | 20.0 | 40 | 0.6499 | 0.7812 |
74
+ | 0.5876 | 21.0 | 42 | 0.6496 | 0.7656 |
75
+ | 0.5876 | 22.0 | 44 | 0.6502 | 0.7344 |
76
+ | 0.5876 | 23.0 | 46 | 0.6536 | 0.75 |
77
+ | 0.5876 | 24.0 | 48 | 0.6593 | 0.7344 |
78
+ | 0.5439 | 25.0 | 50 | 0.6605 | 0.7344 |
79
+ | 0.5439 | 26.0 | 52 | 0.6592 | 0.7344 |
80
+ | 0.5439 | 27.0 | 54 | 0.6578 | 0.75 |
81
+ | 0.5439 | 28.0 | 56 | 0.6575 | 0.75 |
82
+ | 0.5439 | 29.0 | 58 | 0.6571 | 0.7344 |
83
+ | 0.5429 | 30.0 | 60 | 0.6575 | 0.75 |
84
+ | 0.5429 | 31.0 | 62 | 0.6635 | 0.75 |
85
+ | 0.5429 | 32.0 | 64 | 0.6681 | 0.7344 |
86
+ | 0.5429 | 33.0 | 66 | 0.6705 | 0.7188 |
87
+ | 0.5429 | 34.0 | 68 | 0.6701 | 0.6875 |
88
+ | 0.5404 | 35.0 | 70 | 0.6664 | 0.7188 |
89
+ | 0.5404 | 36.0 | 72 | 0.6621 | 0.7344 |
90
+ | 0.5404 | 37.0 | 74 | 0.6599 | 0.7344 |
91
+ | 0.5404 | 38.0 | 76 | 0.6604 | 0.7344 |
92
+ | 0.5404 | 39.0 | 78 | 0.6637 | 0.7344 |
93
+ | 0.5403 | 40.0 | 80 | 0.6647 | 0.7344 |
94
+ | 0.5403 | 41.0 | 82 | 0.6641 | 0.7344 |
95
+ | 0.5403 | 42.0 | 84 | 0.6633 | 0.7344 |
96
+ | 0.5403 | 43.0 | 86 | 0.6663 | 0.7344 |
97
+ | 0.5403 | 44.0 | 88 | 0.6699 | 0.7344 |
98
+ | 0.5406 | 45.0 | 90 | 0.6684 | 0.7344 |
99
+ | 0.5406 | 46.0 | 92 | 0.6625 | 0.7344 |
100
+ | 0.5406 | 47.0 | 94 | 0.6582 | 0.75 |
101
+ | 0.5406 | 48.0 | 96 | 0.6549 | 0.75 |
102
+ | 0.5406 | 49.0 | 98 | 0.6523 | 0.7656 |
103
+ | 0.54 | 50.0 | 100 | 0.6523 | 0.75 |
104
+ | 0.54 | 51.0 | 102 | 0.6525 | 0.75 |
105
+ | 0.54 | 52.0 | 104 | 0.6531 | 0.75 |
106
+ | 0.54 | 53.0 | 106 | 0.6534 | 0.75 |
107
+ | 0.54 | 54.0 | 108 | 0.6539 | 0.75 |
108
+ | 0.5396 | 55.0 | 110 | 0.6553 | 0.7656 |
109
+ | 0.5396 | 56.0 | 112 | 0.6540 | 0.75 |
110
+ | 0.5396 | 57.0 | 114 | 0.6555 | 0.7656 |
111
+ | 0.5396 | 58.0 | 116 | 0.6565 | 0.7656 |
112
+ | 0.5396 | 59.0 | 118 | 0.6588 | 0.7656 |
113
+ | 0.5403 | 60.0 | 120 | 0.6609 | 0.75 |
114
+ | 0.5403 | 61.0 | 122 | 0.6621 | 0.7344 |
115
+ | 0.5403 | 62.0 | 124 | 0.6619 | 0.7344 |
116
+ | 0.5403 | 63.0 | 126 | 0.6614 | 0.7344 |
117
+ | 0.5403 | 64.0 | 128 | 0.6599 | 0.7344 |
118
+ | 0.5405 | 65.0 | 130 | 0.6586 | 0.75 |
119
+ | 0.5405 | 66.0 | 132 | 0.6583 | 0.7656 |
120
+ | 0.5405 | 67.0 | 134 | 0.6580 | 0.7656 |
121
+ | 0.5405 | 68.0 | 136 | 0.6582 | 0.75 |
122
+ | 0.5405 | 69.0 | 138 | 0.6586 | 0.75 |
123
+ | 0.5399 | 70.0 | 140 | 0.6591 | 0.75 |
124
+ | 0.5399 | 71.0 | 142 | 0.6592 | 0.75 |
125
+ | 0.5399 | 72.0 | 144 | 0.6592 | 0.75 |
126
+ | 0.5399 | 73.0 | 146 | 0.6594 | 0.75 |
127
+ | 0.5399 | 74.0 | 148 | 0.6594 | 0.75 |
128
+ | 0.5403 | 75.0 | 150 | 0.6595 | 0.75 |
129
+
130
+
131
+ ### Framework versions
132
+
133
+ - Transformers 4.32.0.dev0
134
+ - Pytorch 2.0.1+cu118
135
+ - Datasets 2.4.0
136
+ - Tokenizers 0.13.3