Hugging Face's logo

simonycl
/
best_model-sst-2-32-42

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
simonycl commited on
Commit
17b08b8
•
1 Parent(s): c2d1128

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-2-32-42
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-2-32-42
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: 1.2575
21
+ - Accuracy: 0.8281
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 | 2 | 1.2950 | 0.8281 |
54
+ | No log | 2.0 | 4 | 1.2965 | 0.8281 |
55
+ | No log | 3.0 | 6 | 1.2971 | 0.8281 |
56
+ | No log | 4.0 | 8 | 1.2972 | 0.8281 |
57
+ | 0.3346 | 5.0 | 10 | 1.2994 | 0.8281 |
58
+ | 0.3346 | 6.0 | 12 | 1.3037 | 0.8281 |
59
+ | 0.3346 | 7.0 | 14 | 1.3082 | 0.8281 |
60
+ | 0.3346 | 8.0 | 16 | 1.3140 | 0.8281 |
61
+ | 0.3346 | 9.0 | 18 | 1.3212 | 0.8281 |
62
+ | 0.2586 | 10.0 | 20 | 1.3285 | 0.8281 |
63
+ | 0.2586 | 11.0 | 22 | 1.3346 | 0.8281 |
64
+ | 0.2586 | 12.0 | 24 | 1.3404 | 0.8281 |
65
+ | 0.2586 | 13.0 | 26 | 1.3443 | 0.8281 |
66
+ | 0.2586 | 14.0 | 28 | 1.3499 | 0.8281 |
67
+ | 0.2171 | 15.0 | 30 | 1.3534 | 0.8281 |
68
+ | 0.2171 | 16.0 | 32 | 1.3551 | 0.8281 |
69
+ | 0.2171 | 17.0 | 34 | 1.3544 | 0.8281 |
70
+ | 0.2171 | 18.0 | 36 | 1.3531 | 0.8281 |
71
+ | 0.2171 | 19.0 | 38 | 1.3516 | 0.8281 |
72
+ | 0.1549 | 20.0 | 40 | 1.3494 | 0.8281 |
73
+ | 0.1549 | 21.0 | 42 | 1.3471 | 0.8281 |
74
+ | 0.1549 | 22.0 | 44 | 1.3446 | 0.8281 |
75
+ | 0.1549 | 23.0 | 46 | 1.3414 | 0.8281 |
76
+ | 0.1549 | 24.0 | 48 | 1.3351 | 0.8281 |
77
+ | 0.0613 | 25.0 | 50 | 1.3277 | 0.8281 |
78
+ | 0.0613 | 26.0 | 52 | 1.3201 | 0.8281 |
79
+ | 0.0613 | 27.0 | 54 | 1.3110 | 0.8281 |
80
+ | 0.0613 | 28.0 | 56 | 1.2974 | 0.8281 |
81
+ | 0.0613 | 29.0 | 58 | 1.2847 | 0.8281 |
82
+ | 0.0094 | 30.0 | 60 | 1.2767 | 0.8281 |
83
+ | 0.0094 | 31.0 | 62 | 1.2697 | 0.8281 |
84
+ | 0.0094 | 32.0 | 64 | 1.2638 | 0.8281 |
85
+ | 0.0094 | 33.0 | 66 | 1.2625 | 0.8281 |
86
+ | 0.0094 | 34.0 | 68 | 1.2633 | 0.8281 |
87
+ | 0.0004 | 35.0 | 70 | 1.2642 | 0.8281 |
88
+ | 0.0004 | 36.0 | 72 | 1.2757 | 0.8281 |
89
+ | 0.0004 | 37.0 | 74 | 1.2783 | 0.8281 |
90
+ | 0.0004 | 38.0 | 76 | 1.2813 | 0.8281 |
91
+ | 0.0004 | 39.0 | 78 | 1.2892 | 0.8281 |
92
+ | 0.0074 | 40.0 | 80 | 1.2990 | 0.8281 |
93
+ | 0.0074 | 41.0 | 82 | 1.3111 | 0.8281 |
94
+ | 0.0074 | 42.0 | 84 | 1.3233 | 0.8281 |
95
+ | 0.0074 | 43.0 | 86 | 1.3317 | 0.8281 |
96
+ | 0.0074 | 44.0 | 88 | 1.3371 | 0.8281 |
97
+ | 0.0004 | 45.0 | 90 | 1.3410 | 0.8281 |
98
+ | 0.0004 | 46.0 | 92 | 1.3436 | 0.8281 |
99
+ | 0.0004 | 47.0 | 94 | 1.3456 | 0.8281 |
100
+ | 0.0004 | 48.0 | 96 | 1.3471 | 0.8281 |
101
+ | 0.0004 | 49.0 | 98 | 1.3489 | 0.8281 |
102
+ | 0.0005 | 50.0 | 100 | 1.3488 | 0.8281 |
103
+ | 0.0005 | 51.0 | 102 | 1.3429 | 0.8281 |
104
+ | 0.0005 | 52.0 | 104 | 1.3365 | 0.8281 |
105
+ | 0.0005 | 53.0 | 106 | 1.3305 | 0.8281 |
106
+ | 0.0005 | 54.0 | 108 | 1.3247 | 0.8281 |
107
+ | 0.0003 | 55.0 | 110 | 1.3195 | 0.8281 |
108
+ | 0.0003 | 56.0 | 112 | 1.3151 | 0.8281 |
109
+ | 0.0003 | 57.0 | 114 | 1.2921 | 0.8281 |
110
+ | 0.0003 | 58.0 | 116 | 1.2717 | 0.8281 |
111
+ | 0.0003 | 59.0 | 118 | 1.2551 | 0.8281 |
112
+ | 0.0166 | 60.0 | 120 | 1.2421 | 0.8281 |
113
+ | 0.0166 | 61.0 | 122 | 1.2590 | 0.8281 |
114
+ | 0.0166 | 62.0 | 124 | 1.2739 | 0.8281 |
115
+ | 0.0166 | 63.0 | 126 | 1.2861 | 0.8281 |
116
+ | 0.0166 | 64.0 | 128 | 1.2958 | 0.8281 |
117
+ | 0.0003 | 65.0 | 130 | 1.3039 | 0.8281 |
118
+ | 0.0003 | 66.0 | 132 | 1.3103 | 0.8281 |
119
+ | 0.0003 | 67.0 | 134 | 1.3126 | 0.8281 |
120
+ | 0.0003 | 68.0 | 136 | 1.3125 | 0.8281 |
121
+ | 0.0003 | 69.0 | 138 | 1.3125 | 0.8281 |
122
+ | 0.0002 | 70.0 | 140 | 1.3128 | 0.8281 |
123
+ | 0.0002 | 71.0 | 142 | 1.3131 | 0.8281 |
124
+ | 0.0002 | 72.0 | 144 | 1.3135 | 0.8281 |
125
+ | 0.0002 | 73.0 | 146 | 1.3141 | 0.8281 |
126
+ | 0.0002 | 74.0 | 148 | 1.3147 | 0.8281 |
127
+ | 0.0004 | 75.0 | 150 | 1.3289 | 0.8281 |
128
+ | 0.0004 | 76.0 | 152 | 1.3274 | 0.8281 |
129
+ | 0.0004 | 77.0 | 154 | 1.3260 | 0.8281 |
130
+ | 0.0004 | 78.0 | 156 | 1.3251 | 0.8281 |
131
+ | 0.0004 | 79.0 | 158 | 1.3523 | 0.8281 |
132
+ | 0.0008 | 80.0 | 160 | 1.3691 | 0.8281 |
133
+ | 0.0008 | 81.0 | 162 | 1.3789 | 0.8281 |
134
+ | 0.0008 | 82.0 | 164 | 1.3844 | 0.8281 |
135
+ | 0.0008 | 83.0 | 166 | 1.3873 | 0.8281 |
136
+ | 0.0008 | 84.0 | 168 | 1.3885 | 0.8281 |
137
+ | 0.0002 | 85.0 | 170 | 1.3889 | 0.8281 |
138
+ | 0.0002 | 86.0 | 172 | 1.3889 | 0.8281 |
139
+ | 0.0002 | 87.0 | 174 | 1.3888 | 0.8281 |
140
+ | 0.0002 | 88.0 | 176 | 1.3888 | 0.8281 |
141
+ | 0.0002 | 89.0 | 178 | 1.3890 | 0.8281 |
142
+ | 0.0002 | 90.0 | 180 | 1.3893 | 0.8281 |
143
+ | 0.0002 | 91.0 | 182 | 1.3898 | 0.8281 |
144
+ | 0.0002 | 92.0 | 184 | 1.3905 | 0.8281 |
145
+ | 0.0002 | 93.0 | 186 | 1.3913 | 0.8281 |
146
+ | 0.0002 | 94.0 | 188 | 1.3927 | 0.8281 |
147
+ | 0.0002 | 95.0 | 190 | 1.3938 | 0.8281 |
148
+ | 0.0002 | 96.0 | 192 | 1.3947 | 0.8281 |
149
+ | 0.0002 | 97.0 | 194 | 1.3954 | 0.8281 |
150
+ | 0.0002 | 98.0 | 196 | 1.3960 | 0.8281 |
151
+ | 0.0002 | 99.0 | 198 | 1.3967 | 0.8281 |
152
+ | 0.0002 | 100.0 | 200 | 1.3975 | 0.8281 |
153
+ | 0.0002 | 101.0 | 202 | 1.3984 | 0.8281 |
154
+ | 0.0002 | 102.0 | 204 | 1.3993 | 0.8281 |
155
+ | 0.0002 | 103.0 | 206 | 1.4001 | 0.8281 |
156
+ | 0.0002 | 104.0 | 208 | 1.4008 | 0.8281 |
157
+ | 0.0001 | 105.0 | 210 | 1.4014 | 0.8281 |
158
+ | 0.0001 | 106.0 | 212 | 1.4020 | 0.8281 |
159
+ | 0.0001 | 107.0 | 214 | 1.4026 | 0.8281 |
160
+ | 0.0001 | 108.0 | 216 | 1.4030 | 0.8281 |
161
+ | 0.0001 | 109.0 | 218 | 1.4035 | 0.8281 |
162
+ | 0.0001 | 110.0 | 220 | 1.4040 | 0.8281 |
163
+ | 0.0001 | 111.0 | 222 | 1.4046 | 0.8281 |
164
+ | 0.0001 | 112.0 | 224 | 1.4051 | 0.8281 |
165
+ | 0.0001 | 113.0 | 226 | 1.4057 | 0.8281 |
166
+ | 0.0001 | 114.0 | 228 | 1.4064 | 0.8281 |
167
+ | 0.0001 | 115.0 | 230 | 1.4071 | 0.8281 |
168
+ | 0.0001 | 116.0 | 232 | 1.4078 | 0.8281 |
169
+ | 0.0001 | 117.0 | 234 | 1.4085 | 0.8281 |
170
+ | 0.0001 | 118.0 | 236 | 1.4092 | 0.8281 |
171
+ | 0.0001 | 119.0 | 238 | 1.4099 | 0.8281 |
172
+ | 0.0001 | 120.0 | 240 | 1.4106 | 0.8281 |
173
+ | 0.0001 | 121.0 | 242 | 1.4108 | 0.8281 |
174
+ | 0.0001 | 122.0 | 244 | 1.4081 | 0.8281 |
175
+ | 0.0001 | 123.0 | 246 | 1.4055 | 0.8281 |
176
+ | 0.0001 | 124.0 | 248 | 1.4032 | 0.8281 |
177
+ | 0.0001 | 125.0 | 250 | 1.4011 | 0.8281 |
178
+ | 0.0001 | 126.0 | 252 | 1.3995 | 0.8281 |
179
+ | 0.0001 | 127.0 | 254 | 1.3982 | 0.8281 |
180
+ | 0.0001 | 128.0 | 256 | 1.3973 | 0.8281 |
181
+ | 0.0001 | 129.0 | 258 | 1.3967 | 0.8281 |
182
+ | 0.0001 | 130.0 | 260 | 1.3963 | 0.8281 |
183
+ | 0.0001 | 131.0 | 262 | 1.3962 | 0.8281 |
184
+ | 0.0001 | 132.0 | 264 | 1.3962 | 0.8281 |
185
+ | 0.0001 | 133.0 | 266 | 1.3965 | 0.8281 |
186
+ | 0.0001 | 134.0 | 268 | 1.3970 | 0.8281 |
187
+ | 0.0001 | 135.0 | 270 | 1.3989 | 0.8281 |
188
+ | 0.0001 | 136.0 | 272 | 1.4012 | 0.8281 |
189
+ | 0.0001 | 137.0 | 274 | 1.4035 | 0.8281 |
190
+ | 0.0001 | 138.0 | 276 | 1.4052 | 0.8281 |
191
+ | 0.0001 | 139.0 | 278 | 1.4064 | 0.8281 |
192
+ | 0.0002 | 140.0 | 280 | 1.3703 | 0.8281 |
193
+ | 0.0002 | 141.0 | 282 | 1.2995 | 0.8438 |
194
+ | 0.0002 | 142.0 | 284 | 1.2572 | 0.8281 |
195
+ | 0.0002 | 143.0 | 286 | 1.2224 | 0.8281 |
196
+ | 0.0002 | 144.0 | 288 | 1.2120 | 0.8438 |
197
+ | 0.0001 | 145.0 | 290 | 1.2242 | 0.8281 |
198
+ | 0.0001 | 146.0 | 292 | 1.2377 | 0.8281 |
199
+ | 0.0001 | 147.0 | 294 | 1.2477 | 0.8281 |
200
+ | 0.0001 | 148.0 | 296 | 1.2542 | 0.8281 |
201
+ | 0.0001 | 149.0 | 298 | 1.2575 | 0.8281 |
202
+ | 0.0002 | 150.0 | 300 | 1.2575 | 0.8281 |
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