Hugging Face's logo

simonycl
/
roberta-base-sst-2-16-42-smoothed

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
simonycl commited on
Commit
59c6c35
·
1 Parent(s): bc2d3d5

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-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: bert-base-uncased-sst-2-16-42-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-base-uncased-sst-2-16-42-smoothed
17
+
18
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6339
21
+ - Accuracy: 0.7812
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 | 4 | 0.7048 | 0.5 |
55
+ | No log | 2.0 | 8 | 0.7021 | 0.5 |
56
+ | 0.7078 | 3.0 | 12 | 0.6982 | 0.5 |
57
+ | 0.7078 | 4.0 | 16 | 0.6936 | 0.4922 |
58
+ | 0.6935 | 5.0 | 20 | 0.6898 | 0.5625 |
59
+ | 0.6935 | 6.0 | 24 | 0.6878 | 0.625 |
60
+ | 0.6935 | 7.0 | 28 | 0.6856 | 0.6484 |
61
+ | 0.682 | 8.0 | 32 | 0.6818 | 0.6797 |
62
+ | 0.682 | 9.0 | 36 | 0.6759 | 0.7109 |
63
+ | 0.6567 | 10.0 | 40 | 0.6692 | 0.6562 |
64
+ | 0.6567 | 11.0 | 44 | 0.6662 | 0.6562 |
65
+ | 0.6567 | 12.0 | 48 | 0.6669 | 0.6484 |
66
+ | 0.6177 | 13.0 | 52 | 0.6612 | 0.6719 |
67
+ | 0.6177 | 14.0 | 56 | 0.6589 | 0.6641 |
68
+ | 0.5787 | 15.0 | 60 | 0.6565 | 0.6797 |
69
+ | 0.5787 | 16.0 | 64 | 0.6519 | 0.7109 |
70
+ | 0.5787 | 17.0 | 68 | 0.6506 | 0.7266 |
71
+ | 0.5487 | 18.0 | 72 | 0.6496 | 0.75 |
72
+ | 0.5487 | 19.0 | 76 | 0.6489 | 0.7344 |
73
+ | 0.5398 | 20.0 | 80 | 0.6492 | 0.75 |
74
+ | 0.5398 | 21.0 | 84 | 0.6467 | 0.7578 |
75
+ | 0.5398 | 22.0 | 88 | 0.6439 | 0.75 |
76
+ | 0.5384 | 23.0 | 92 | 0.6419 | 0.75 |
77
+ | 0.5384 | 24.0 | 96 | 0.6442 | 0.75 |
78
+ | 0.5389 | 25.0 | 100 | 0.6442 | 0.7422 |
79
+ | 0.5389 | 26.0 | 104 | 0.6391 | 0.75 |
80
+ | 0.5389 | 27.0 | 108 | 0.6428 | 0.7734 |
81
+ | 0.5373 | 28.0 | 112 | 0.6449 | 0.7656 |
82
+ | 0.5373 | 29.0 | 116 | 0.6412 | 0.7812 |
83
+ | 0.5379 | 30.0 | 120 | 0.6359 | 0.7578 |
84
+ | 0.5379 | 31.0 | 124 | 0.6348 | 0.7734 |
85
+ | 0.5379 | 32.0 | 128 | 0.6343 | 0.7891 |
86
+ | 0.5366 | 33.0 | 132 | 0.6340 | 0.7969 |
87
+ | 0.5366 | 34.0 | 136 | 0.6340 | 0.7891 |
88
+ | 0.5366 | 35.0 | 140 | 0.6339 | 0.7734 |
89
+ | 0.5366 | 36.0 | 144 | 0.6337 | 0.7734 |
90
+ | 0.5366 | 37.0 | 148 | 0.6335 | 0.7734 |
91
+ | 0.5363 | 38.0 | 152 | 0.6334 | 0.7969 |
92
+ | 0.5363 | 39.0 | 156 | 0.6347 | 0.7734 |
93
+ | 0.5367 | 40.0 | 160 | 0.6355 | 0.7656 |
94
+ | 0.5367 | 41.0 | 164 | 0.6363 | 0.7578 |
95
+ | 0.5367 | 42.0 | 168 | 0.6374 | 0.7656 |
96
+ | 0.5359 | 43.0 | 172 | 0.6375 | 0.7656 |
97
+ | 0.5359 | 44.0 | 176 | 0.6357 | 0.7578 |
98
+ | 0.5358 | 45.0 | 180 | 0.6351 | 0.7656 |
99
+ | 0.5358 | 46.0 | 184 | 0.6339 | 0.7734 |
100
+ | 0.5358 | 47.0 | 188 | 0.6334 | 0.7812 |
101
+ | 0.5362 | 48.0 | 192 | 0.6330 | 0.7891 |
102
+ | 0.5362 | 49.0 | 196 | 0.6327 | 0.7891 |
103
+ | 0.5364 | 50.0 | 200 | 0.6329 | 0.7891 |
104
+ | 0.5364 | 51.0 | 204 | 0.6341 | 0.7734 |
105
+ | 0.5364 | 52.0 | 208 | 0.6337 | 0.7734 |
106
+ | 0.5365 | 53.0 | 212 | 0.6326 | 0.7891 |
107
+ | 0.5365 | 54.0 | 216 | 0.6325 | 0.7891 |
108
+ | 0.5361 | 55.0 | 220 | 0.6326 | 0.7969 |
109
+ | 0.5361 | 56.0 | 224 | 0.6328 | 0.7891 |
110
+ | 0.5361 | 57.0 | 228 | 0.6328 | 0.7891 |
111
+ | 0.5361 | 58.0 | 232 | 0.6330 | 0.7891 |
112
+ | 0.5361 | 59.0 | 236 | 0.6335 | 0.7812 |
113
+ | 0.5363 | 60.0 | 240 | 0.6340 | 0.7812 |
114
+ | 0.5363 | 61.0 | 244 | 0.6343 | 0.7812 |
115
+ | 0.5363 | 62.0 | 248 | 0.6346 | 0.7734 |
116
+ | 0.536 | 63.0 | 252 | 0.6348 | 0.7734 |
117
+ | 0.536 | 64.0 | 256 | 0.6349 | 0.7734 |
118
+ | 0.5362 | 65.0 | 260 | 0.6353 | 0.7656 |
119
+ | 0.5362 | 66.0 | 264 | 0.6358 | 0.7656 |
120
+ | 0.5362 | 67.0 | 268 | 0.6361 | 0.7578 |
121
+ | 0.536 | 68.0 | 272 | 0.6355 | 0.7656 |
122
+ | 0.536 | 69.0 | 276 | 0.6349 | 0.7734 |
123
+ | 0.5358 | 70.0 | 280 | 0.6344 | 0.7734 |
124
+ | 0.5358 | 71.0 | 284 | 0.6342 | 0.7812 |
125
+ | 0.5358 | 72.0 | 288 | 0.6340 | 0.7812 |
126
+ | 0.5357 | 73.0 | 292 | 0.6340 | 0.7812 |
127
+ | 0.5357 | 74.0 | 296 | 0.6339 | 0.7812 |
128
+ | 0.5358 | 75.0 | 300 | 0.6339 | 0.7812 |
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