Hugging Face's logo

simonycl
/
best_model-sst-2-16-100

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
simonycl commited on
Commit
00e7bb3
•
1 Parent(s): 0d15af9

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-sst-2-16-100
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-sst-2-16-100
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: 0.4760
21
+ - Accuracy: 0.9062
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 | 0.3957 | 0.875 |
54
+ | No log | 2.0 | 2 | 0.3958 | 0.875 |
55
+ | No log | 3.0 | 3 | 0.3961 | 0.875 |
56
+ | No log | 4.0 | 4 | 0.3964 | 0.875 |
57
+ | No log | 5.0 | 5 | 0.3968 | 0.875 |
58
+ | No log | 6.0 | 6 | 0.3971 | 0.875 |
59
+ | No log | 7.0 | 7 | 0.3974 | 0.875 |
60
+ | No log | 8.0 | 8 | 0.3976 | 0.875 |
61
+ | No log | 9.0 | 9 | 0.3978 | 0.875 |
62
+ | 0.2951 | 10.0 | 10 | 0.3979 | 0.875 |
63
+ | 0.2951 | 11.0 | 11 | 0.3977 | 0.875 |
64
+ | 0.2951 | 12.0 | 12 | 0.3971 | 0.875 |
65
+ | 0.2951 | 13.0 | 13 | 0.3963 | 0.875 |
66
+ | 0.2951 | 14.0 | 14 | 0.3954 | 0.875 |
67
+ | 0.2951 | 15.0 | 15 | 0.3943 | 0.875 |
68
+ | 0.2951 | 16.0 | 16 | 0.3929 | 0.875 |
69
+ | 0.2951 | 17.0 | 17 | 0.3912 | 0.875 |
70
+ | 0.2951 | 18.0 | 18 | 0.3895 | 0.875 |
71
+ | 0.2951 | 19.0 | 19 | 0.3876 | 0.875 |
72
+ | 0.2889 | 20.0 | 20 | 0.3854 | 0.875 |
73
+ | 0.2889 | 21.0 | 21 | 0.3830 | 0.875 |
74
+ | 0.2889 | 22.0 | 22 | 0.3806 | 0.875 |
75
+ | 0.2889 | 23.0 | 23 | 0.3789 | 0.875 |
76
+ | 0.2889 | 24.0 | 24 | 0.3770 | 0.875 |
77
+ | 0.2889 | 25.0 | 25 | 0.3755 | 0.9062 |
78
+ | 0.2889 | 26.0 | 26 | 0.3739 | 0.9062 |
79
+ | 0.2889 | 27.0 | 27 | 0.3728 | 0.9062 |
80
+ | 0.2889 | 28.0 | 28 | 0.3716 | 0.9062 |
81
+ | 0.2889 | 29.0 | 29 | 0.3704 | 0.9062 |
82
+ | 0.2147 | 30.0 | 30 | 0.3697 | 0.9062 |
83
+ | 0.2147 | 31.0 | 31 | 0.3692 | 0.9062 |
84
+ | 0.2147 | 32.0 | 32 | 0.3688 | 0.9062 |
85
+ | 0.2147 | 33.0 | 33 | 0.3686 | 0.9062 |
86
+ | 0.2147 | 34.0 | 34 | 0.3684 | 0.9062 |
87
+ | 0.2147 | 35.0 | 35 | 0.3683 | 0.9062 |
88
+ | 0.2147 | 36.0 | 36 | 0.3682 | 0.9062 |
89
+ | 0.2147 | 37.0 | 37 | 0.3684 | 0.9062 |
90
+ | 0.2147 | 38.0 | 38 | 0.3684 | 0.9062 |
91
+ | 0.2147 | 39.0 | 39 | 0.3685 | 0.9062 |
92
+ | 0.1272 | 40.0 | 40 | 0.3689 | 0.9062 |
93
+ | 0.1272 | 41.0 | 41 | 0.3693 | 0.9062 |
94
+ | 0.1272 | 42.0 | 42 | 0.3701 | 0.9062 |
95
+ | 0.1272 | 43.0 | 43 | 0.3709 | 0.875 |
96
+ | 0.1272 | 44.0 | 44 | 0.3719 | 0.875 |
97
+ | 0.1272 | 45.0 | 45 | 0.3728 | 0.875 |
98
+ | 0.1272 | 46.0 | 46 | 0.3731 | 0.875 |
99
+ | 0.1272 | 47.0 | 47 | 0.3728 | 0.875 |
100
+ | 0.1272 | 48.0 | 48 | 0.3729 | 0.875 |
101
+ | 0.1272 | 49.0 | 49 | 0.3726 | 0.875 |
102
+ | 0.0531 | 50.0 | 50 | 0.3726 | 0.875 |
103
+ | 0.0531 | 51.0 | 51 | 0.3721 | 0.875 |
104
+ | 0.0531 | 52.0 | 52 | 0.3716 | 0.875 |
105
+ | 0.0531 | 53.0 | 53 | 0.3715 | 0.875 |
106
+ | 0.0531 | 54.0 | 54 | 0.3707 | 0.875 |
107
+ | 0.0531 | 55.0 | 55 | 0.3706 | 0.875 |
108
+ | 0.0531 | 56.0 | 56 | 0.3702 | 0.875 |
109
+ | 0.0531 | 57.0 | 57 | 0.3707 | 0.875 |
110
+ | 0.0531 | 58.0 | 58 | 0.3716 | 0.875 |
111
+ | 0.0531 | 59.0 | 59 | 0.3735 | 0.875 |
112
+ | 0.0221 | 60.0 | 60 | 0.3754 | 0.875 |
113
+ | 0.0221 | 61.0 | 61 | 0.3775 | 0.875 |
114
+ | 0.0221 | 62.0 | 62 | 0.3801 | 0.875 |
115
+ | 0.0221 | 63.0 | 63 | 0.3824 | 0.875 |
116
+ | 0.0221 | 64.0 | 64 | 0.3847 | 0.875 |
117
+ | 0.0221 | 65.0 | 65 | 0.3871 | 0.875 |
118
+ | 0.0221 | 66.0 | 66 | 0.3883 | 0.875 |
119
+ | 0.0221 | 67.0 | 67 | 0.3885 | 0.875 |
120
+ | 0.0221 | 68.0 | 68 | 0.3886 | 0.875 |
121
+ | 0.0221 | 69.0 | 69 | 0.3876 | 0.875 |
122
+ | 0.0151 | 70.0 | 70 | 0.3869 | 0.875 |
123
+ | 0.0151 | 71.0 | 71 | 0.3869 | 0.875 |
124
+ | 0.0151 | 72.0 | 72 | 0.3871 | 0.875 |
125
+ | 0.0151 | 73.0 | 73 | 0.3875 | 0.875 |
126
+ | 0.0151 | 74.0 | 74 | 0.3872 | 0.875 |
127
+ | 0.0151 | 75.0 | 75 | 0.3873 | 0.875 |
128
+ | 0.0151 | 76.0 | 76 | 0.3869 | 0.875 |
129
+ | 0.0151 | 77.0 | 77 | 0.3868 | 0.875 |
130
+ | 0.0151 | 78.0 | 78 | 0.3876 | 0.9062 |
131
+ | 0.0151 | 79.0 | 79 | 0.3885 | 0.9062 |
132
+ | 0.0099 | 80.0 | 80 | 0.3896 | 0.9062 |
133
+ | 0.0099 | 81.0 | 81 | 0.3908 | 0.9062 |
134
+ | 0.0099 | 82.0 | 82 | 0.3921 | 0.9062 |
135
+ | 0.0099 | 83.0 | 83 | 0.3935 | 0.9062 |
136
+ | 0.0099 | 84.0 | 84 | 0.3952 | 0.9062 |
137
+ | 0.0099 | 85.0 | 85 | 0.3972 | 0.9062 |
138
+ | 0.0099 | 86.0 | 86 | 0.3992 | 0.9062 |
139
+ | 0.0099 | 87.0 | 87 | 0.4017 | 0.9062 |
140
+ | 0.0099 | 88.0 | 88 | 0.4042 | 0.9062 |
141
+ | 0.0099 | 89.0 | 89 | 0.4062 | 0.9062 |
142
+ | 0.0074 | 90.0 | 90 | 0.4082 | 0.9062 |
143
+ | 0.0074 | 91.0 | 91 | 0.4100 | 0.9062 |
144
+ | 0.0074 | 92.0 | 92 | 0.4118 | 0.9062 |
145
+ | 0.0074 | 93.0 | 93 | 0.4135 | 0.9062 |
146
+ | 0.0074 | 94.0 | 94 | 0.4152 | 0.9062 |
147
+ | 0.0074 | 95.0 | 95 | 0.4169 | 0.9062 |
148
+ | 0.0074 | 96.0 | 96 | 0.4185 | 0.9062 |
149
+ | 0.0074 | 97.0 | 97 | 0.4198 | 0.9062 |
150
+ | 0.0074 | 98.0 | 98 | 0.4211 | 0.9062 |
151
+ | 0.0074 | 99.0 | 99 | 0.4224 | 0.9062 |
152
+ | 0.006 | 100.0 | 100 | 0.4236 | 0.9062 |
153
+ | 0.006 | 101.0 | 101 | 0.4248 | 0.9062 |
154
+ | 0.006 | 102.0 | 102 | 0.4259 | 0.9062 |
155
+ | 0.006 | 103.0 | 103 | 0.4271 | 0.9062 |
156
+ | 0.006 | 104.0 | 104 | 0.4284 | 0.9062 |
157
+ | 0.006 | 105.0 | 105 | 0.4296 | 0.9062 |
158
+ | 0.006 | 106.0 | 106 | 0.4298 | 0.9062 |
159
+ | 0.006 | 107.0 | 107 | 0.4283 | 0.9062 |
160
+ | 0.006 | 108.0 | 108 | 0.4276 | 0.9062 |
161
+ | 0.006 | 109.0 | 109 | 0.4275 | 0.9062 |
162
+ | 0.0065 | 110.0 | 110 | 0.4280 | 0.9062 |
163
+ | 0.0065 | 111.0 | 111 | 0.4287 | 0.9062 |
164
+ | 0.0065 | 112.0 | 112 | 0.4297 | 0.9062 |
165
+ | 0.0065 | 113.0 | 113 | 0.4309 | 0.9062 |
166
+ | 0.0065 | 114.0 | 114 | 0.4322 | 0.9062 |
167
+ | 0.0065 | 115.0 | 115 | 0.4337 | 0.9062 |
168
+ | 0.0065 | 116.0 | 116 | 0.4352 | 0.9062 |
169
+ | 0.0065 | 117.0 | 117 | 0.4367 | 0.9062 |
170
+ | 0.0065 | 118.0 | 118 | 0.4383 | 0.9062 |
171
+ | 0.0065 | 119.0 | 119 | 0.4399 | 0.9062 |
172
+ | 0.0046 | 120.0 | 120 | 0.4413 | 0.9062 |
173
+ | 0.0046 | 121.0 | 121 | 0.4428 | 0.9062 |
174
+ | 0.0046 | 122.0 | 122 | 0.4443 | 0.9062 |
175
+ | 0.0046 | 123.0 | 123 | 0.4457 | 0.9062 |
176
+ | 0.0046 | 124.0 | 124 | 0.4470 | 0.9062 |
177
+ | 0.0046 | 125.0 | 125 | 0.4483 | 0.9062 |
178
+ | 0.0046 | 126.0 | 126 | 0.4495 | 0.9062 |
179
+ | 0.0046 | 127.0 | 127 | 0.4508 | 0.9062 |
180
+ | 0.0046 | 128.0 | 128 | 0.4520 | 0.9062 |
181
+ | 0.0046 | 129.0 | 129 | 0.4531 | 0.9062 |
182
+ | 0.0037 | 130.0 | 130 | 0.4543 | 0.9062 |
183
+ | 0.0037 | 131.0 | 131 | 0.4555 | 0.9062 |
184
+ | 0.0037 | 132.0 | 132 | 0.4566 | 0.9062 |
185
+ | 0.0037 | 133.0 | 133 | 0.4577 | 0.9062 |
186
+ | 0.0037 | 134.0 | 134 | 0.4588 | 0.9062 |
187
+ | 0.0037 | 135.0 | 135 | 0.4599 | 0.9062 |
188
+ | 0.0037 | 136.0 | 136 | 0.4610 | 0.9062 |
189
+ | 0.0037 | 137.0 | 137 | 0.4622 | 0.9062 |
190
+ | 0.0037 | 138.0 | 138 | 0.4633 | 0.9062 |
191
+ | 0.0037 | 139.0 | 139 | 0.4644 | 0.9062 |
192
+ | 0.0033 | 140.0 | 140 | 0.4655 | 0.9062 |
193
+ | 0.0033 | 141.0 | 141 | 0.4666 | 0.9062 |
194
+ | 0.0033 | 142.0 | 142 | 0.4677 | 0.9062 |
195
+ | 0.0033 | 143.0 | 143 | 0.4688 | 0.9062 |
196
+ | 0.0033 | 144.0 | 144 | 0.4700 | 0.9062 |
197
+ | 0.0033 | 145.0 | 145 | 0.4712 | 0.9062 |
198
+ | 0.0033 | 146.0 | 146 | 0.4725 | 0.9062 |
199
+ | 0.0033 | 147.0 | 147 | 0.4733 | 0.9062 |
200
+ | 0.0033 | 148.0 | 148 | 0.4742 | 0.9062 |
201
+ | 0.0033 | 149.0 | 149 | 0.4751 | 0.9062 |
202
+ | 0.0029 | 150.0 | 150 | 0.4760 | 0.9062 |
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