add model
Browse files- README.md +201 -201
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -13,7 +13,7 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [MJ199999/gpt3_model](https://huggingface.co/MJ199999/gpt3_model) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Train Loss: 0.
|
| 17 |
- Train Lr: 0.0009999999
|
| 18 |
- Epoch: 199
|
| 19 |
|
|
@@ -41,206 +41,206 @@ The following hyperparameters were used during training:
|
|
| 41 |
|
| 42 |
| Train Loss | Train Lr | Epoch |
|
| 43 |
|:----------:|:------------:|:-----:|
|
| 44 |
-
| 5.
|
| 45 |
-
|
|
| 46 |
-
|
|
| 47 |
-
| 2.
|
| 48 |
-
| 1.
|
| 49 |
-
| 1.
|
| 50 |
-
| 1.
|
| 51 |
-
| 1.
|
| 52 |
-
| 1.
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
| 133 |
-
| 0.
|
| 134 |
-
| 0.
|
| 135 |
-
| 0.
|
| 136 |
-
| 0.
|
| 137 |
-
| 0.
|
| 138 |
-
| 0.
|
| 139 |
-
| 0.
|
| 140 |
-
| 0.
|
| 141 |
-
| 0.
|
| 142 |
-
| 0.
|
| 143 |
-
| 0.
|
| 144 |
-
| 0.
|
| 145 |
-
| 0.
|
| 146 |
-
| 0.
|
| 147 |
-
| 0.
|
| 148 |
-
| 0.
|
| 149 |
-
| 0.
|
| 150 |
-
| 0.
|
| 151 |
-
| 0.
|
| 152 |
-
| 0.
|
| 153 |
-
| 0.
|
| 154 |
-
| 0.
|
| 155 |
-
| 0.
|
| 156 |
-
| 0.
|
| 157 |
-
| 0.
|
| 158 |
-
| 0.
|
| 159 |
-
| 0.
|
| 160 |
-
| 0.
|
| 161 |
-
| 0.
|
| 162 |
-
| 0.
|
| 163 |
-
| 0.
|
| 164 |
-
| 0.
|
| 165 |
-
| 0.
|
| 166 |
-
| 0.
|
| 167 |
-
| 0.
|
| 168 |
-
| 0.
|
| 169 |
-
| 0.
|
| 170 |
-
| 0.
|
| 171 |
-
| 0.
|
| 172 |
-
| 0.
|
| 173 |
-
| 0.
|
| 174 |
-
| 0.
|
| 175 |
-
| 0.
|
| 176 |
-
| 0.
|
| 177 |
-
| 0.
|
| 178 |
-
| 0.
|
| 179 |
-
| 0.
|
| 180 |
-
| 0.
|
| 181 |
-
| 0.
|
| 182 |
-
| 0.
|
| 183 |
-
| 0.
|
| 184 |
-
| 0.
|
| 185 |
-
| 0.
|
| 186 |
-
| 0.
|
| 187 |
-
| 0.
|
| 188 |
-
| 0.
|
| 189 |
-
| 0.
|
| 190 |
-
| 0.
|
| 191 |
-
| 0.
|
| 192 |
-
| 0.
|
| 193 |
-
| 0.
|
| 194 |
-
| 0.
|
| 195 |
-
| 0.
|
| 196 |
-
| 0.
|
| 197 |
-
| 0.
|
| 198 |
-
| 0.
|
| 199 |
-
| 0.
|
| 200 |
-
| 0.
|
| 201 |
-
| 0.
|
| 202 |
-
| 0.
|
| 203 |
-
| 0.
|
| 204 |
-
| 0.
|
| 205 |
-
| 0.
|
| 206 |
-
| 0.
|
| 207 |
-
| 0.
|
| 208 |
-
| 0.
|
| 209 |
-
| 0.
|
| 210 |
-
| 0.
|
| 211 |
-
| 0.
|
| 212 |
-
| 0.
|
| 213 |
-
| 0.
|
| 214 |
-
| 0.
|
| 215 |
-
| 0.
|
| 216 |
-
| 0.
|
| 217 |
-
| 0.
|
| 218 |
-
| 0.
|
| 219 |
-
| 0.
|
| 220 |
-
| 0.
|
| 221 |
-
| 0.
|
| 222 |
-
| 0.
|
| 223 |
-
| 0.
|
| 224 |
-
| 0.
|
| 225 |
-
| 0.
|
| 226 |
-
| 0.
|
| 227 |
-
| 0.
|
| 228 |
-
| 0.
|
| 229 |
-
| 0.
|
| 230 |
-
| 0.
|
| 231 |
-
| 0.
|
| 232 |
-
| 0.
|
| 233 |
-
| 0.
|
| 234 |
-
| 0.
|
| 235 |
-
| 0.
|
| 236 |
-
| 0.
|
| 237 |
-
| 0.
|
| 238 |
-
| 0.
|
| 239 |
-
| 0.
|
| 240 |
-
| 0.
|
| 241 |
-
| 0.
|
| 242 |
-
| 0.
|
| 243 |
-
| 0.
|
| 244 |
|
| 245 |
|
| 246 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [MJ199999/gpt3_model](https://huggingface.co/MJ199999/gpt3_model) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Train Loss: 0.4905
|
| 17 |
- Train Lr: 0.0009999999
|
| 18 |
- Epoch: 199
|
| 19 |
|
|
|
|
| 41 |
|
| 42 |
| Train Loss | Train Lr | Epoch |
|
| 43 |
|:----------:|:------------:|:-----:|
|
| 44 |
+
| 5.1583 | 0.01 | 0 |
|
| 45 |
+
| 3.9477 | 0.01 | 1 |
|
| 46 |
+
| 2.9332 | 0.01 | 2 |
|
| 47 |
+
| 2.1581 | 0.01 | 3 |
|
| 48 |
+
| 1.6918 | 0.01 | 4 |
|
| 49 |
+
| 1.3929 | 0.01 | 5 |
|
| 50 |
+
| 1.2062 | 0.01 | 6 |
|
| 51 |
+
| 1.0955 | 0.01 | 7 |
|
| 52 |
+
| 1.0068 | 0.01 | 8 |
|
| 53 |
+
| 0.9528 | 0.01 | 9 |
|
| 54 |
+
| 0.9051 | 0.01 | 10 |
|
| 55 |
+
| 0.8710 | 0.01 | 11 |
|
| 56 |
+
| 0.8564 | 0.01 | 12 |
|
| 57 |
+
| 0.8094 | 0.01 | 13 |
|
| 58 |
+
| 0.8143 | 0.01 | 14 |
|
| 59 |
+
| 0.7853 | 0.01 | 15 |
|
| 60 |
+
| 0.7625 | 0.01 | 16 |
|
| 61 |
+
| 0.7508 | 0.01 | 17 |
|
| 62 |
+
| 0.7449 | 0.01 | 18 |
|
| 63 |
+
| 0.7319 | 0.01 | 19 |
|
| 64 |
+
| 0.7144 | 0.01 | 20 |
|
| 65 |
+
| 0.7045 | 0.01 | 21 |
|
| 66 |
+
| 0.7029 | 0.01 | 22 |
|
| 67 |
+
| 0.6937 | 0.01 | 23 |
|
| 68 |
+
| 0.6898 | 0.01 | 24 |
|
| 69 |
+
| 0.6745 | 0.01 | 25 |
|
| 70 |
+
| 0.6767 | 0.01 | 26 |
|
| 71 |
+
| 0.6692 | 0.01 | 27 |
|
| 72 |
+
| 0.6604 | 0.01 | 28 |
|
| 73 |
+
| 0.6573 | 0.01 | 29 |
|
| 74 |
+
| 0.6524 | 0.01 | 30 |
|
| 75 |
+
| 0.6508 | 0.01 | 31 |
|
| 76 |
+
| 0.6443 | 0.01 | 32 |
|
| 77 |
+
| 0.6452 | 0.01 | 33 |
|
| 78 |
+
| 0.6371 | 0.01 | 34 |
|
| 79 |
+
| 0.6362 | 0.01 | 35 |
|
| 80 |
+
| 0.6304 | 0.01 | 36 |
|
| 81 |
+
| 0.6317 | 0.01 | 37 |
|
| 82 |
+
| 0.6270 | 0.01 | 38 |
|
| 83 |
+
| 0.6257 | 0.01 | 39 |
|
| 84 |
+
| 0.6208 | 0.01 | 40 |
|
| 85 |
+
| 0.6227 | 0.01 | 41 |
|
| 86 |
+
| 0.6154 | 0.01 | 42 |
|
| 87 |
+
| 0.6126 | 0.01 | 43 |
|
| 88 |
+
| 0.6149 | 0.01 | 44 |
|
| 89 |
+
| 0.6075 | 0.01 | 45 |
|
| 90 |
+
| 0.6084 | 0.01 | 46 |
|
| 91 |
+
| 0.6078 | 0.01 | 47 |
|
| 92 |
+
| 0.6057 | 0.01 | 48 |
|
| 93 |
+
| 0.6033 | 0.01 | 49 |
|
| 94 |
+
| 0.6040 | 0.01 | 50 |
|
| 95 |
+
| 0.5989 | 0.01 | 51 |
|
| 96 |
+
| 0.5967 | 0.01 | 52 |
|
| 97 |
+
| 0.5952 | 0.01 | 53 |
|
| 98 |
+
| 0.5911 | 0.01 | 54 |
|
| 99 |
+
| 0.5904 | 0.01 | 55 |
|
| 100 |
+
| 0.5888 | 0.01 | 56 |
|
| 101 |
+
| 0.5886 | 0.01 | 57 |
|
| 102 |
+
| 0.5883 | 0.01 | 58 |
|
| 103 |
+
| 0.5838 | 0.01 | 59 |
|
| 104 |
+
| 0.5856 | 0.01 | 60 |
|
| 105 |
+
| 0.5850 | 0.01 | 61 |
|
| 106 |
+
| 0.5801 | 0.01 | 62 |
|
| 107 |
+
| 0.5821 | 0.01 | 63 |
|
| 108 |
+
| 0.5781 | 0.01 | 64 |
|
| 109 |
+
| 0.5786 | 0.01 | 65 |
|
| 110 |
+
| 0.5835 | 0.01 | 66 |
|
| 111 |
+
| 0.5808 | 0.01 | 67 |
|
| 112 |
+
| 0.5754 | 0.01 | 68 |
|
| 113 |
+
| 0.5742 | 0.01 | 69 |
|
| 114 |
+
| 0.5733 | 0.01 | 70 |
|
| 115 |
+
| 0.5700 | 0.01 | 71 |
|
| 116 |
+
| 0.5738 | 0.01 | 72 |
|
| 117 |
+
| 0.5678 | 0.01 | 73 |
|
| 118 |
+
| 0.5695 | 0.01 | 74 |
|
| 119 |
+
| 0.5684 | 0.01 | 75 |
|
| 120 |
+
| 0.5696 | 0.01 | 76 |
|
| 121 |
+
| 0.5688 | 0.01 | 77 |
|
| 122 |
+
| 0.5648 | 0.01 | 78 |
|
| 123 |
+
| 0.5592 | 0.01 | 79 |
|
| 124 |
+
| 0.5622 | 0.01 | 80 |
|
| 125 |
+
| 0.5660 | 0.01 | 81 |
|
| 126 |
+
| 0.5636 | 0.01 | 82 |
|
| 127 |
+
| 0.5602 | 0.01 | 83 |
|
| 128 |
+
| 0.5613 | 0.01 | 84 |
|
| 129 |
+
| 0.5608 | 0.01 | 85 |
|
| 130 |
+
| 0.5589 | 0.01 | 86 |
|
| 131 |
+
| 0.5580 | 0.01 | 87 |
|
| 132 |
+
| 0.5566 | 0.01 | 88 |
|
| 133 |
+
| 0.5531 | 0.01 | 89 |
|
| 134 |
+
| 0.5571 | 0.01 | 90 |
|
| 135 |
+
| 0.5541 | 0.01 | 91 |
|
| 136 |
+
| 0.5576 | 0.01 | 92 |
|
| 137 |
+
| 0.5560 | 0.01 | 93 |
|
| 138 |
+
| 0.5517 | 0.01 | 94 |
|
| 139 |
+
| 0.5508 | 0.01 | 95 |
|
| 140 |
+
| 0.5554 | 0.01 | 96 |
|
| 141 |
+
| 0.5539 | 0.01 | 97 |
|
| 142 |
+
| 0.5493 | 0.01 | 98 |
|
| 143 |
+
| 0.5499 | 0.01 | 99 |
|
| 144 |
+
| 0.4999 | 0.0009999999 | 100 |
|
| 145 |
+
| 0.4981 | 0.0009999999 | 101 |
|
| 146 |
+
| 0.4983 | 0.0009999999 | 102 |
|
| 147 |
+
| 0.4984 | 0.0009999999 | 103 |
|
| 148 |
+
| 0.4974 | 0.0009999999 | 104 |
|
| 149 |
+
| 0.4957 | 0.0009999999 | 105 |
|
| 150 |
+
| 0.4966 | 0.0009999999 | 106 |
|
| 151 |
+
| 0.4975 | 0.0009999999 | 107 |
|
| 152 |
+
| 0.4962 | 0.0009999999 | 108 |
|
| 153 |
+
| 0.4932 | 0.0009999999 | 109 |
|
| 154 |
+
| 0.4983 | 0.0009999999 | 110 |
|
| 155 |
+
| 0.4937 | 0.0009999999 | 111 |
|
| 156 |
+
| 0.4926 | 0.0009999999 | 112 |
|
| 157 |
+
| 0.4944 | 0.0009999999 | 113 |
|
| 158 |
+
| 0.4947 | 0.0009999999 | 114 |
|
| 159 |
+
| 0.4953 | 0.0009999999 | 115 |
|
| 160 |
+
| 0.4934 | 0.0009999999 | 116 |
|
| 161 |
+
| 0.4929 | 0.0009999999 | 117 |
|
| 162 |
+
| 0.4925 | 0.0009999999 | 118 |
|
| 163 |
+
| 0.4948 | 0.0009999999 | 119 |
|
| 164 |
+
| 0.4947 | 0.0009999999 | 120 |
|
| 165 |
+
| 0.4936 | 0.0009999999 | 121 |
|
| 166 |
+
| 0.4909 | 0.0009999999 | 122 |
|
| 167 |
+
| 0.4960 | 0.0009999999 | 123 |
|
| 168 |
+
| 0.4952 | 0.0009999999 | 124 |
|
| 169 |
+
| 0.4923 | 0.0009999999 | 125 |
|
| 170 |
+
| 0.4930 | 0.0009999999 | 126 |
|
| 171 |
+
| 0.4942 | 0.0009999999 | 127 |
|
| 172 |
+
| 0.4927 | 0.0009999999 | 128 |
|
| 173 |
+
| 0.4917 | 0.0009999999 | 129 |
|
| 174 |
+
| 0.4926 | 0.0009999999 | 130 |
|
| 175 |
+
| 0.4927 | 0.0009999999 | 131 |
|
| 176 |
+
| 0.4932 | 0.0009999999 | 132 |
|
| 177 |
+
| 0.4925 | 0.0009999999 | 133 |
|
| 178 |
+
| 0.4928 | 0.0009999999 | 134 |
|
| 179 |
+
| 0.4936 | 0.0009999999 | 135 |
|
| 180 |
+
| 0.4908 | 0.0009999999 | 136 |
|
| 181 |
+
| 0.4936 | 0.0009999999 | 137 |
|
| 182 |
+
| 0.4916 | 0.0009999999 | 138 |
|
| 183 |
+
| 0.4906 | 0.0009999999 | 139 |
|
| 184 |
+
| 0.4904 | 0.0009999999 | 140 |
|
| 185 |
+
| 0.4920 | 0.0009999999 | 141 |
|
| 186 |
+
| 0.4924 | 0.0009999999 | 142 |
|
| 187 |
+
| 0.4902 | 0.0009999999 | 143 |
|
| 188 |
+
| 0.4903 | 0.0009999999 | 144 |
|
| 189 |
+
| 0.4903 | 0.0009999999 | 145 |
|
| 190 |
+
| 0.4924 | 0.0009999999 | 146 |
|
| 191 |
+
| 0.4889 | 0.0009999999 | 147 |
|
| 192 |
+
| 0.4896 | 0.0009999999 | 148 |
|
| 193 |
+
| 0.4919 | 0.0009999999 | 149 |
|
| 194 |
+
| 0.4896 | 0.0009999999 | 150 |
|
| 195 |
+
| 0.4906 | 0.0009999999 | 151 |
|
| 196 |
+
| 0.4923 | 0.0009999999 | 152 |
|
| 197 |
+
| 0.4899 | 0.0009999999 | 153 |
|
| 198 |
+
| 0.4925 | 0.0009999999 | 154 |
|
| 199 |
+
| 0.4901 | 0.0009999999 | 155 |
|
| 200 |
+
| 0.4910 | 0.0009999999 | 156 |
|
| 201 |
+
| 0.4904 | 0.0009999999 | 157 |
|
| 202 |
+
| 0.4912 | 0.0009999999 | 158 |
|
| 203 |
+
| 0.4937 | 0.0009999999 | 159 |
|
| 204 |
+
| 0.4894 | 0.0009999999 | 160 |
|
| 205 |
+
| 0.4913 | 0.0009999999 | 161 |
|
| 206 |
+
| 0.4899 | 0.0009999999 | 162 |
|
| 207 |
+
| 0.4894 | 0.0009999999 | 163 |
|
| 208 |
+
| 0.4904 | 0.0009999999 | 164 |
|
| 209 |
+
| 0.4900 | 0.0009999999 | 165 |
|
| 210 |
+
| 0.4890 | 0.0009999999 | 166 |
|
| 211 |
+
| 0.4919 | 0.0009999999 | 167 |
|
| 212 |
+
| 0.4909 | 0.0009999999 | 168 |
|
| 213 |
+
| 0.4891 | 0.0009999999 | 169 |
|
| 214 |
+
| 0.4900 | 0.0009999999 | 170 |
|
| 215 |
+
| 0.4910 | 0.0009999999 | 171 |
|
| 216 |
+
| 0.4901 | 0.0009999999 | 172 |
|
| 217 |
+
| 0.4914 | 0.0009999999 | 173 |
|
| 218 |
+
| 0.4913 | 0.0009999999 | 174 |
|
| 219 |
+
| 0.4897 | 0.0009999999 | 175 |
|
| 220 |
+
| 0.4892 | 0.0009999999 | 176 |
|
| 221 |
+
| 0.4929 | 0.0009999999 | 177 |
|
| 222 |
+
| 0.4881 | 0.0009999999 | 178 |
|
| 223 |
+
| 0.4920 | 0.0009999999 | 179 |
|
| 224 |
+
| 0.4888 | 0.0009999999 | 180 |
|
| 225 |
+
| 0.4901 | 0.0009999999 | 181 |
|
| 226 |
+
| 0.4875 | 0.0009999999 | 182 |
|
| 227 |
+
| 0.4930 | 0.0009999999 | 183 |
|
| 228 |
+
| 0.4867 | 0.0009999999 | 184 |
|
| 229 |
+
| 0.4890 | 0.0009999999 | 185 |
|
| 230 |
+
| 0.4898 | 0.0009999999 | 186 |
|
| 231 |
+
| 0.4880 | 0.0009999999 | 187 |
|
| 232 |
+
| 0.4899 | 0.0009999999 | 188 |
|
| 233 |
+
| 0.4881 | 0.0009999999 | 189 |
|
| 234 |
+
| 0.4897 | 0.0009999999 | 190 |
|
| 235 |
+
| 0.4876 | 0.0009999999 | 191 |
|
| 236 |
+
| 0.4873 | 0.0009999999 | 192 |
|
| 237 |
+
| 0.4901 | 0.0009999999 | 193 |
|
| 238 |
+
| 0.4898 | 0.0009999999 | 194 |
|
| 239 |
+
| 0.4898 | 0.0009999999 | 195 |
|
| 240 |
+
| 0.4861 | 0.0009999999 | 196 |
|
| 241 |
+
| 0.4878 | 0.0009999999 | 197 |
|
| 242 |
+
| 0.4880 | 0.0009999999 | 198 |
|
| 243 |
+
| 0.4905 | 0.0009999999 | 199 |
|
| 244 |
|
| 245 |
|
| 246 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4650595440
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da0b1727ba706417e6a685d7101e9e1a77adcf26f2b35ca2fa3cb6c39234d403
|
| 3 |
size 4650595440
|