Hugging Face's logo

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

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
simonycl commited on
Commit
fb58b0f
•
1 Parent(s): 236a662

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-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: roberta-base-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-base-sst-2-64-13-smoothed
17
+
18
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6071
21
+ - Accuracy: 0.8672
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 | 0.6941 | 0.5 |
55
+ | No log | 2.0 | 8 | 0.6939 | 0.5 |
56
+ | 0.694 | 3.0 | 12 | 0.6936 | 0.5 |
57
+ | 0.694 | 4.0 | 16 | 0.6932 | 0.5 |
58
+ | 0.6948 | 5.0 | 20 | 0.6929 | 0.5 |
59
+ | 0.6948 | 6.0 | 24 | 0.6925 | 0.5 |
60
+ | 0.6948 | 7.0 | 28 | 0.6922 | 0.5469 |
61
+ | 0.6948 | 8.0 | 32 | 0.6919 | 0.6719 |
62
+ | 0.6948 | 9.0 | 36 | 0.6914 | 0.7266 |
63
+ | 0.6908 | 10.0 | 40 | 0.6907 | 0.75 |
64
+ | 0.6908 | 11.0 | 44 | 0.6894 | 0.6719 |
65
+ | 0.6908 | 12.0 | 48 | 0.6866 | 0.6328 |
66
+ | 0.6835 | 13.0 | 52 | 0.6789 | 0.7891 |
67
+ | 0.6835 | 14.0 | 56 | 0.6514 | 0.8828 |
68
+ | 0.637 | 15.0 | 60 | 0.6004 | 0.875 |
69
+ | 0.637 | 16.0 | 64 | 0.6097 | 0.8984 |
70
+ | 0.637 | 17.0 | 68 | 0.6147 | 0.8516 |
71
+ | 0.5653 | 18.0 | 72 | 0.5973 | 0.8672 |
72
+ | 0.5653 | 19.0 | 76 | 0.6056 | 0.875 |
73
+ | 0.544 | 20.0 | 80 | 0.6077 | 0.875 |
74
+ | 0.544 | 21.0 | 84 | 0.5947 | 0.8672 |
75
+ | 0.544 | 22.0 | 88 | 0.6029 | 0.8828 |
76
+ | 0.5384 | 23.0 | 92 | 0.6067 | 0.8828 |
77
+ | 0.5384 | 24.0 | 96 | 0.5998 | 0.8828 |
78
+ | 0.5361 | 25.0 | 100 | 0.5978 | 0.8906 |
79
+ | 0.5361 | 26.0 | 104 | 0.6004 | 0.875 |
80
+ | 0.5361 | 27.0 | 108 | 0.6055 | 0.8672 |
81
+ | 0.5364 | 28.0 | 112 | 0.6064 | 0.8672 |
82
+ | 0.5364 | 29.0 | 116 | 0.5991 | 0.8906 |
83
+ | 0.5364 | 30.0 | 120 | 0.5973 | 0.8906 |
84
+ | 0.5364 | 31.0 | 124 | 0.6019 | 0.8828 |
85
+ | 0.5364 | 32.0 | 128 | 0.6085 | 0.8594 |
86
+ | 0.5358 | 33.0 | 132 | 0.6069 | 0.8672 |
87
+ | 0.5358 | 34.0 | 136 | 0.6075 | 0.8594 |
88
+ | 0.5357 | 35.0 | 140 | 0.6022 | 0.8828 |
89
+ | 0.5357 | 36.0 | 144 | 0.5980 | 0.8906 |
90
+ | 0.5357 | 37.0 | 148 | 0.5983 | 0.8984 |
91
+ | 0.5359 | 38.0 | 152 | 0.5962 | 0.8984 |
92
+ | 0.5359 | 39.0 | 156 | 0.5965 | 0.8984 |
93
+ | 0.5358 | 40.0 | 160 | 0.6007 | 0.8984 |
94
+ | 0.5358 | 41.0 | 164 | 0.6010 | 0.8984 |
95
+ | 0.5358 | 42.0 | 168 | 0.5975 | 0.8984 |
96
+ | 0.5355 | 43.0 | 172 | 0.5975 | 0.8906 |
97
+ | 0.5355 | 44.0 | 176 | 0.6012 | 0.8906 |
98
+ | 0.5354 | 45.0 | 180 | 0.6027 | 0.8828 |
99
+ | 0.5354 | 46.0 | 184 | 0.6027 | 0.8828 |
100
+ | 0.5354 | 47.0 | 188 | 0.6018 | 0.8828 |
101
+ | 0.5355 | 48.0 | 192 | 0.6070 | 0.875 |
102
+ | 0.5355 | 49.0 | 196 | 0.6090 | 0.8672 |
103
+ | 0.5352 | 50.0 | 200 | 0.6090 | 0.8672 |
104
+ | 0.5352 | 51.0 | 204 | 0.6079 | 0.8672 |
105
+ | 0.5352 | 52.0 | 208 | 0.6072 | 0.8906 |
106
+ | 0.5354 | 53.0 | 212 | 0.6063 | 0.8906 |
107
+ | 0.5354 | 54.0 | 216 | 0.6045 | 0.8672 |
108
+ | 0.5353 | 55.0 | 220 | 0.6094 | 0.8672 |
109
+ | 0.5353 | 56.0 | 224 | 0.6167 | 0.8438 |
110
+ | 0.5353 | 57.0 | 228 | 0.6176 | 0.8516 |
111
+ | 0.5353 | 58.0 | 232 | 0.6188 | 0.8516 |
112
+ | 0.5353 | 59.0 | 236 | 0.6204 | 0.8516 |
113
+ | 0.5353 | 60.0 | 240 | 0.6218 | 0.8438 |
114
+ | 0.5353 | 61.0 | 244 | 0.6222 | 0.8516 |
115
+ | 0.5353 | 62.0 | 248 | 0.6208 | 0.8516 |
116
+ | 0.5352 | 63.0 | 252 | 0.6194 | 0.8516 |
117
+ | 0.5352 | 64.0 | 256 | 0.6167 | 0.8438 |
118
+ | 0.5351 | 65.0 | 260 | 0.6144 | 0.8438 |
119
+ | 0.5351 | 66.0 | 264 | 0.6128 | 0.8516 |
120
+ | 0.5351 | 67.0 | 268 | 0.6117 | 0.8594 |
121
+ | 0.5349 | 68.0 | 272 | 0.6112 | 0.8594 |
122
+ | 0.5349 | 69.0 | 276 | 0.6114 | 0.8672 |
123
+ | 0.5351 | 70.0 | 280 | 0.6089 | 0.8672 |
124
+ | 0.5351 | 71.0 | 284 | 0.6077 | 0.875 |
125
+ | 0.5351 | 72.0 | 288 | 0.6073 | 0.875 |
126
+ | 0.5352 | 73.0 | 292 | 0.6072 | 0.8672 |
127
+ | 0.5352 | 74.0 | 296 | 0.6071 | 0.8672 |
128
+ | 0.5355 | 75.0 | 300 | 0.6071 | 0.8672 |
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