Hugging Face's logo

simonycl
/
roberta-large-sst-2-64-13-smoothed

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
1
simonycl commited on
Commit
062215f
·
1 Parent(s): 1c0b2e3

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: mit
3
+ base_model: roberta-large
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: roberta-large-sst-2-64-13-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
+ # roberta-large-sst-2-64-13-smoothed
17
+
18
+ This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5741
21
+ - Accuracy: 0.9375
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 | 0.6932 | 0.5 |
55
+ | No log | 2.0 | 8 | 0.6930 | 0.5 |
56
+ | 0.6986 | 3.0 | 12 | 0.6928 | 0.5078 |
57
+ | 0.6986 | 4.0 | 16 | 0.6926 | 0.5078 |
58
+ | 0.7049 | 5.0 | 20 | 0.6926 | 0.5 |
59
+ | 0.7049 | 6.0 | 24 | 0.6924 | 0.5 |
60
+ | 0.7049 | 7.0 | 28 | 0.6922 | 0.5 |
61
+ | 0.6928 | 8.0 | 32 | 0.6918 | 0.5234 |
62
+ | 0.6928 | 9.0 | 36 | 0.6912 | 0.5312 |
63
+ | 0.6889 | 10.0 | 40 | 0.6905 | 0.5625 |
64
+ | 0.6889 | 11.0 | 44 | 0.6895 | 0.5078 |
65
+ | 0.6889 | 12.0 | 48 | 0.6880 | 0.5781 |
66
+ | 0.6855 | 13.0 | 52 | 0.6823 | 0.6875 |
67
+ | 0.6855 | 14.0 | 56 | 0.6590 | 0.8281 |
68
+ | 0.6346 | 15.0 | 60 | 0.6187 | 0.8672 |
69
+ | 0.6346 | 16.0 | 64 | 0.6192 | 0.8281 |
70
+ | 0.6346 | 17.0 | 68 | 0.5983 | 0.9062 |
71
+ | 0.5877 | 18.0 | 72 | 0.6030 | 0.875 |
72
+ | 0.5877 | 19.0 | 76 | 0.5942 | 0.9141 |
73
+ | 0.564 | 20.0 | 80 | 0.5918 | 0.8984 |
74
+ | 0.564 | 21.0 | 84 | 0.5860 | 0.9141 |
75
+ | 0.564 | 22.0 | 88 | 0.5761 | 0.9375 |
76
+ | 0.5505 | 23.0 | 92 | 0.5854 | 0.9297 |
77
+ | 0.5505 | 24.0 | 96 | 0.5750 | 0.9141 |
78
+ | 0.5462 | 25.0 | 100 | 0.5776 | 0.9141 |
79
+ | 0.5462 | 26.0 | 104 | 0.5713 | 0.9453 |
80
+ | 0.5462 | 27.0 | 108 | 0.5731 | 0.9375 |
81
+ | 0.5414 | 28.0 | 112 | 0.5770 | 0.9297 |
82
+ | 0.5414 | 29.0 | 116 | 0.5789 | 0.9141 |
83
+ | 0.5382 | 30.0 | 120 | 0.5871 | 0.9062 |
84
+ | 0.5382 | 31.0 | 124 | 0.5810 | 0.9141 |
85
+ | 0.5382 | 32.0 | 128 | 0.5765 | 0.9297 |
86
+ | 0.5383 | 33.0 | 132 | 0.5769 | 0.9297 |
87
+ | 0.5383 | 34.0 | 136 | 0.5718 | 0.9453 |
88
+ | 0.5385 | 35.0 | 140 | 0.5704 | 0.9453 |
89
+ | 0.5385 | 36.0 | 144 | 0.5728 | 0.9453 |
90
+ | 0.5385 | 37.0 | 148 | 0.5737 | 0.9297 |
91
+ | 0.5381 | 38.0 | 152 | 0.5749 | 0.9375 |
92
+ | 0.5381 | 39.0 | 156 | 0.5754 | 0.9375 |
93
+ | 0.5389 | 40.0 | 160 | 0.5742 | 0.9375 |
94
+ | 0.5389 | 41.0 | 164 | 0.5723 | 0.9375 |
95
+ | 0.5389 | 42.0 | 168 | 0.5720 | 0.9375 |
96
+ | 0.5372 | 43.0 | 172 | 0.5694 | 0.9453 |
97
+ | 0.5372 | 44.0 | 176 | 0.5723 | 0.9375 |
98
+ | 0.5384 | 45.0 | 180 | 0.5766 | 0.9375 |
99
+ | 0.5384 | 46.0 | 184 | 0.5715 | 0.9375 |
100
+ | 0.5384 | 47.0 | 188 | 0.5696 | 0.9453 |
101
+ | 0.5379 | 48.0 | 192 | 0.5709 | 0.9453 |
102
+ | 0.5379 | 49.0 | 196 | 0.5720 | 0.9453 |
103
+ | 0.5372 | 50.0 | 200 | 0.5717 | 0.9453 |
104
+ | 0.5372 | 51.0 | 204 | 0.5706 | 0.9453 |
105
+ | 0.5372 | 52.0 | 208 | 0.5697 | 0.9453 |
106
+ | 0.5371 | 53.0 | 212 | 0.5700 | 0.9453 |
107
+ | 0.5371 | 54.0 | 216 | 0.5706 | 0.9453 |
108
+ | 0.5368 | 55.0 | 220 | 0.5697 | 0.9453 |
109
+ | 0.5368 | 56.0 | 224 | 0.5702 | 0.9453 |
110
+ | 0.5368 | 57.0 | 228 | 0.5719 | 0.9453 |
111
+ | 0.5371 | 58.0 | 232 | 0.5728 | 0.9453 |
112
+ | 0.5371 | 59.0 | 236 | 0.5729 | 0.9375 |
113
+ | 0.5371 | 60.0 | 240 | 0.5734 | 0.9375 |
114
+ | 0.5371 | 61.0 | 244 | 0.5736 | 0.9375 |
115
+ | 0.5371 | 62.0 | 248 | 0.5745 | 0.9375 |
116
+ | 0.5369 | 63.0 | 252 | 0.5760 | 0.9375 |
117
+ | 0.5369 | 64.0 | 256 | 0.5772 | 0.9375 |
118
+ | 0.5365 | 65.0 | 260 | 0.5771 | 0.9375 |
119
+ | 0.5365 | 66.0 | 264 | 0.5763 | 0.9375 |
120
+ | 0.5365 | 67.0 | 268 | 0.5759 | 0.9375 |
121
+ | 0.5365 | 68.0 | 272 | 0.5753 | 0.9375 |
122
+ | 0.5365 | 69.0 | 276 | 0.5751 | 0.9375 |
123
+ | 0.5369 | 70.0 | 280 | 0.5746 | 0.9375 |
124
+ | 0.5369 | 71.0 | 284 | 0.5741 | 0.9375 |
125
+ | 0.5369 | 72.0 | 288 | 0.5742 | 0.9375 |
126
+ | 0.5367 | 73.0 | 292 | 0.5742 | 0.9375 |
127
+ | 0.5367 | 74.0 | 296 | 0.5741 | 0.9375 |
128
+ | 0.5368 | 75.0 | 300 | 0.5741 | 0.9375 |
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