Hugging Face's logo

simonycl
/
best_model-yelp_polarity-16-100

Text Classification
Transformers
PyTorch
albert
Generated from Trainer
Inference Endpoints
Model card Files Community
simonycl commited on
Commit
63aa1f8
•
1 Parent(s): 07c85dc

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +210 -0
README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: best_model-yelp_polarity-16-100
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
+ # best_model-yelp_polarity-16-100
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: 0.5412
21
+ - Accuracy: 0.8438
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: 500
47
+ - num_epochs: 150
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 1 | 0.6580 | 0.7812 |
54
+ | No log | 2.0 | 2 | 0.6573 | 0.7812 |
55
+ | No log | 3.0 | 3 | 0.6560 | 0.7812 |
56
+ | No log | 4.0 | 4 | 0.6540 | 0.7812 |
57
+ | No log | 5.0 | 5 | 0.6513 | 0.7812 |
58
+ | No log | 6.0 | 6 | 0.6477 | 0.7812 |
59
+ | No log | 7.0 | 7 | 0.6435 | 0.7812 |
60
+ | No log | 8.0 | 8 | 0.6384 | 0.7812 |
61
+ | No log | 9.0 | 9 | 0.6326 | 0.7812 |
62
+ | 0.1759 | 10.0 | 10 | 0.6262 | 0.7812 |
63
+ | 0.1759 | 11.0 | 11 | 0.6193 | 0.7812 |
64
+ | 0.1759 | 12.0 | 12 | 0.6120 | 0.7812 |
65
+ | 0.1759 | 13.0 | 13 | 0.6043 | 0.7812 |
66
+ | 0.1759 | 14.0 | 14 | 0.5961 | 0.7812 |
67
+ | 0.1759 | 15.0 | 15 | 0.5871 | 0.7812 |
68
+ | 0.1759 | 16.0 | 16 | 0.5777 | 0.7812 |
69
+ | 0.1759 | 17.0 | 17 | 0.5685 | 0.7812 |
70
+ | 0.1759 | 18.0 | 18 | 0.5589 | 0.7812 |
71
+ | 0.1759 | 19.0 | 19 | 0.5496 | 0.7812 |
72
+ | 0.1203 | 20.0 | 20 | 0.5396 | 0.7812 |
73
+ | 0.1203 | 21.0 | 21 | 0.5304 | 0.7812 |
74
+ | 0.1203 | 22.0 | 22 | 0.5207 | 0.7812 |
75
+ | 0.1203 | 23.0 | 23 | 0.5125 | 0.7812 |
76
+ | 0.1203 | 24.0 | 24 | 0.5041 | 0.7812 |
77
+ | 0.1203 | 25.0 | 25 | 0.4958 | 0.7812 |
78
+ | 0.1203 | 26.0 | 26 | 0.4893 | 0.7812 |
79
+ | 0.1203 | 27.0 | 27 | 0.4836 | 0.7812 |
80
+ | 0.1203 | 28.0 | 28 | 0.4770 | 0.7812 |
81
+ | 0.1203 | 29.0 | 29 | 0.4720 | 0.7812 |
82
+ | 0.0971 | 30.0 | 30 | 0.4676 | 0.7812 |
83
+ | 0.0971 | 31.0 | 31 | 0.4630 | 0.7812 |
84
+ | 0.0971 | 32.0 | 32 | 0.4597 | 0.7812 |
85
+ | 0.0971 | 33.0 | 33 | 0.4581 | 0.7812 |
86
+ | 0.0971 | 34.0 | 34 | 0.4584 | 0.7812 |
87
+ | 0.0971 | 35.0 | 35 | 0.4607 | 0.7812 |
88
+ | 0.0971 | 36.0 | 36 | 0.4643 | 0.7812 |
89
+ | 0.0971 | 37.0 | 37 | 0.4687 | 0.7812 |
90
+ | 0.0971 | 38.0 | 38 | 0.4721 | 0.7812 |
91
+ | 0.0971 | 39.0 | 39 | 0.4748 | 0.7812 |
92
+ | 0.0547 | 40.0 | 40 | 0.4764 | 0.7812 |
93
+ | 0.0547 | 41.0 | 41 | 0.4752 | 0.7812 |
94
+ | 0.0547 | 42.0 | 42 | 0.4749 | 0.7812 |
95
+ | 0.0547 | 43.0 | 43 | 0.4746 | 0.7812 |
96
+ | 0.0547 | 44.0 | 44 | 0.4754 | 0.7812 |
97
+ | 0.0547 | 45.0 | 45 | 0.4773 | 0.7812 |
98
+ | 0.0547 | 46.0 | 46 | 0.4760 | 0.8125 |
99
+ | 0.0547 | 47.0 | 47 | 0.4718 | 0.8125 |
100
+ | 0.0547 | 48.0 | 48 | 0.4653 | 0.8438 |
101
+ | 0.0547 | 49.0 | 49 | 0.4581 | 0.8438 |
102
+ | 0.0355 | 50.0 | 50 | 0.4521 | 0.8438 |
103
+ | 0.0355 | 51.0 | 51 | 0.4480 | 0.8438 |
104
+ | 0.0355 | 52.0 | 52 | 0.4458 | 0.8438 |
105
+ | 0.0355 | 53.0 | 53 | 0.4462 | 0.8438 |
106
+ | 0.0355 | 54.0 | 54 | 0.4464 | 0.8438 |
107
+ | 0.0355 | 55.0 | 55 | 0.4473 | 0.8438 |
108
+ | 0.0355 | 56.0 | 56 | 0.4505 | 0.8438 |
109
+ | 0.0355 | 57.0 | 57 | 0.4546 | 0.8438 |
110
+ | 0.0355 | 58.0 | 58 | 0.4587 | 0.8438 |
111
+ | 0.0355 | 59.0 | 59 | 0.4604 | 0.8438 |
112
+ | 0.0211 | 60.0 | 60 | 0.4608 | 0.8438 |
113
+ | 0.0211 | 61.0 | 61 | 0.4632 | 0.8438 |
114
+ | 0.0211 | 62.0 | 62 | 0.4666 | 0.8438 |
115
+ | 0.0211 | 63.0 | 63 | 0.4703 | 0.8438 |
116
+ | 0.0211 | 64.0 | 64 | 0.4767 | 0.8438 |
117
+ | 0.0211 | 65.0 | 65 | 0.4851 | 0.8438 |
118
+ | 0.0211 | 66.0 | 66 | 0.4901 | 0.8438 |
119
+ | 0.0211 | 67.0 | 67 | 0.4949 | 0.8438 |
120
+ | 0.0211 | 68.0 | 68 | 0.4973 | 0.8438 |
121
+ | 0.0211 | 69.0 | 69 | 0.5002 | 0.8438 |
122
+ | 0.0188 | 70.0 | 70 | 0.5022 | 0.8438 |
123
+ | 0.0188 | 71.0 | 71 | 0.5047 | 0.8438 |
124
+ | 0.0188 | 72.0 | 72 | 0.5076 | 0.8438 |
125
+ | 0.0188 | 73.0 | 73 | 0.5105 | 0.8438 |
126
+ | 0.0188 | 74.0 | 74 | 0.5129 | 0.8438 |
127
+ | 0.0188 | 75.0 | 75 | 0.5155 | 0.8438 |
128
+ | 0.0188 | 76.0 | 76 | 0.5167 | 0.8438 |
129
+ | 0.0188 | 77.0 | 77 | 0.5166 | 0.8438 |
130
+ | 0.0188 | 78.0 | 78 | 0.5165 | 0.8438 |
131
+ | 0.0188 | 79.0 | 79 | 0.5165 | 0.8438 |
132
+ | 0.0156 | 80.0 | 80 | 0.5167 | 0.8438 |
133
+ | 0.0156 | 81.0 | 81 | 0.5170 | 0.8438 |
134
+ | 0.0156 | 82.0 | 82 | 0.5172 | 0.8438 |
135
+ | 0.0156 | 83.0 | 83 | 0.5178 | 0.8438 |
136
+ | 0.0156 | 84.0 | 84 | 0.5185 | 0.8438 |
137
+ | 0.0156 | 85.0 | 85 | 0.5188 | 0.8438 |
138
+ | 0.0156 | 86.0 | 86 | 0.5199 | 0.8438 |
139
+ | 0.0156 | 87.0 | 87 | 0.5209 | 0.8438 |
140
+ | 0.0156 | 88.0 | 88 | 0.5220 | 0.8438 |
141
+ | 0.0156 | 89.0 | 89 | 0.5233 | 0.8438 |
142
+ | 0.0132 | 90.0 | 90 | 0.5246 | 0.8438 |
143
+ | 0.0132 | 91.0 | 91 | 0.5264 | 0.8438 |
144
+ | 0.0132 | 92.0 | 92 | 0.5281 | 0.8438 |
145
+ | 0.0132 | 93.0 | 93 | 0.5289 | 0.8438 |
146
+ | 0.0132 | 94.0 | 94 | 0.5289 | 0.8438 |
147
+ | 0.0132 | 95.0 | 95 | 0.5258 | 0.8438 |
148
+ | 0.0132 | 96.0 | 96 | 0.5209 | 0.8438 |
149
+ | 0.0132 | 97.0 | 97 | 0.5162 | 0.8438 |
150
+ | 0.0132 | 98.0 | 98 | 0.5120 | 0.8438 |
151
+ | 0.0132 | 99.0 | 99 | 0.5080 | 0.8438 |
152
+ | 0.0127 | 100.0 | 100 | 0.5050 | 0.8438 |
153
+ | 0.0127 | 101.0 | 101 | 0.5026 | 0.8438 |
154
+ | 0.0127 | 102.0 | 102 | 0.5008 | 0.8438 |
155
+ | 0.0127 | 103.0 | 103 | 0.4996 | 0.8438 |
156
+ | 0.0127 | 104.0 | 104 | 0.4990 | 0.8438 |
157
+ | 0.0127 | 105.0 | 105 | 0.4990 | 0.8438 |
158
+ | 0.0127 | 106.0 | 106 | 0.4997 | 0.8438 |
159
+ | 0.0127 | 107.0 | 107 | 0.4950 | 0.8438 |
160
+ | 0.0127 | 108.0 | 108 | 0.4918 | 0.8438 |
161
+ | 0.0127 | 109.0 | 109 | 0.4893 | 0.8438 |
162
+ | 0.0114 | 110.0 | 110 | 0.4883 | 0.8438 |
163
+ | 0.0114 | 111.0 | 111 | 0.4880 | 0.8438 |
164
+ | 0.0114 | 112.0 | 112 | 0.4881 | 0.8438 |
165
+ | 0.0114 | 113.0 | 113 | 0.4884 | 0.8438 |
166
+ | 0.0114 | 114.0 | 114 | 0.4891 | 0.8438 |
167
+ | 0.0114 | 115.0 | 115 | 0.4899 | 0.8438 |
168
+ | 0.0114 | 116.0 | 116 | 0.4914 | 0.8438 |
169
+ | 0.0114 | 117.0 | 117 | 0.4938 | 0.8438 |
170
+ | 0.0114 | 118.0 | 118 | 0.4966 | 0.8438 |
171
+ | 0.0114 | 119.0 | 119 | 0.4964 | 0.8438 |
172
+ | 0.0102 | 120.0 | 120 | 0.4966 | 0.8438 |
173
+ | 0.0102 | 121.0 | 121 | 0.4969 | 0.8438 |
174
+ | 0.0102 | 122.0 | 122 | 0.4975 | 0.8438 |
175
+ | 0.0102 | 123.0 | 123 | 0.4984 | 0.8438 |
176
+ | 0.0102 | 124.0 | 124 | 0.4986 | 0.8438 |
177
+ | 0.0102 | 125.0 | 125 | 0.4987 | 0.8438 |
178
+ | 0.0102 | 126.0 | 126 | 0.4990 | 0.8438 |
179
+ | 0.0102 | 127.0 | 127 | 0.4998 | 0.8438 |
180
+ | 0.0102 | 128.0 | 128 | 0.5001 | 0.8438 |
181
+ | 0.0102 | 129.0 | 129 | 0.5003 | 0.8438 |
182
+ | 0.009 | 130.0 | 130 | 0.5007 | 0.8438 |
183
+ | 0.009 | 131.0 | 131 | 0.5013 | 0.8438 |
184
+ | 0.009 | 132.0 | 132 | 0.5028 | 0.8438 |
185
+ | 0.009 | 133.0 | 133 | 0.5045 | 0.8438 |
186
+ | 0.009 | 134.0 | 134 | 0.5063 | 0.8438 |
187
+ | 0.009 | 135.0 | 135 | 0.5079 | 0.8438 |
188
+ | 0.009 | 136.0 | 136 | 0.5097 | 0.8438 |
189
+ | 0.009 | 137.0 | 137 | 0.5113 | 0.8438 |
190
+ | 0.009 | 138.0 | 138 | 0.5132 | 0.8438 |
191
+ | 0.009 | 139.0 | 139 | 0.5153 | 0.8438 |
192
+ | 0.0083 | 140.0 | 140 | 0.5179 | 0.8438 |
193
+ | 0.0083 | 141.0 | 141 | 0.5200 | 0.8438 |
194
+ | 0.0083 | 142.0 | 142 | 0.5226 | 0.8438 |
195
+ | 0.0083 | 143.0 | 143 | 0.5253 | 0.8438 |
196
+ | 0.0083 | 144.0 | 144 | 0.5278 | 0.8438 |
197
+ | 0.0083 | 145.0 | 145 | 0.5303 | 0.8438 |
198
+ | 0.0083 | 146.0 | 146 | 0.5326 | 0.8438 |
199
+ | 0.0083 | 147.0 | 147 | 0.5352 | 0.8438 |
200
+ | 0.0083 | 148.0 | 148 | 0.5378 | 0.8438 |
201
+ | 0.0083 | 149.0 | 149 | 0.5398 | 0.8438 |
202
+ | 0.0075 | 150.0 | 150 | 0.5412 | 0.8438 |
203
+
204
+
205
+ ### Framework versions
206
+
207
+ - Transformers 4.32.0.dev0
208
+ - Pytorch 2.0.1+cu118
209
+ - Datasets 2.4.0
210
+ - Tokenizers 0.13.3