add model
Browse files- README.md +202 -202
- config.json +1 -1
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -11,9 +11,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 11 |
|
| 12 |
# gpt3_model
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [/
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Train Loss: 0.
|
| 17 |
- Train Lr: 9.999999e-05
|
| 18 |
- Epoch: 199
|
| 19 |
|
|
@@ -41,206 +41,206 @@ The following hyperparameters were used during training:
|
|
| 41 |
|
| 42 |
| Train Loss | Train Lr | Epoch |
|
| 43 |
|:----------:|:------------:|:-----:|
|
| 44 |
-
|
|
| 45 |
-
|
|
| 46 |
-
|
|
| 47 |
-
|
|
| 48 |
-
|
|
| 49 |
-
|
|
| 50 |
-
|
|
| 51 |
-
|
|
| 52 |
-
|
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
|
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
|
|
| 69 |
-
|
|
| 70 |
-
|
|
| 71 |
-
|
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
-
|
|
| 75 |
-
|
|
| 76 |
-
|
|
| 77 |
-
|
|
| 78 |
-
|
|
| 79 |
-
|
|
| 80 |
-
|
|
| 81 |
-
|
|
| 82 |
-
|
|
| 83 |
-
|
|
| 84 |
-
|
|
| 85 |
-
|
|
| 86 |
-
|
|
| 87 |
-
|
|
| 88 |
-
|
|
| 89 |
-
|
|
| 90 |
-
|
|
| 91 |
-
|
|
| 92 |
-
|
|
| 93 |
-
|
|
| 94 |
-
|
|
| 95 |
-
|
|
| 96 |
-
|
|
| 97 |
-
|
|
| 98 |
-
|
|
| 99 |
-
|
|
| 100 |
-
|
|
| 101 |
-
|
|
| 102 |
-
|
|
| 103 |
-
|
|
| 104 |
-
|
|
| 105 |
-
|
|
| 106 |
-
|
|
| 107 |
-
|
|
| 108 |
-
|
|
| 109 |
-
|
|
| 110 |
-
|
|
| 111 |
-
|
|
| 112 |
-
|
|
| 113 |
-
|
|
| 114 |
-
|
|
| 115 |
-
|
|
| 116 |
-
|
|
| 117 |
-
|
|
| 118 |
-
|
|
| 119 |
-
|
|
| 120 |
-
|
|
| 121 |
-
|
|
| 122 |
-
|
|
| 123 |
-
|
|
| 124 |
-
|
|
| 125 |
-
|
|
| 126 |
-
|
|
| 127 |
-
|
|
| 128 |
-
|
|
| 129 |
-
|
|
| 130 |
-
|
|
| 131 |
-
|
|
| 132 |
-
|
|
| 133 |
-
|
|
| 134 |
-
|
|
| 135 |
-
|
|
| 136 |
-
|
|
| 137 |
-
|
|
| 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
|
|
|
|
| 11 |
|
| 12 |
# gpt3_model
|
| 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: 0.4635
|
| 17 |
- Train Lr: 9.999999e-05
|
| 18 |
- Epoch: 199
|
| 19 |
|
|
|
|
| 41 |
|
| 42 |
| Train Loss | Train Lr | Epoch |
|
| 43 |
|:----------:|:------------:|:-----:|
|
| 44 |
+
| 5.9839 | 0.01 | 0 |
|
| 45 |
+
| 5.3590 | 0.01 | 1 |
|
| 46 |
+
| 4.8662 | 0.01 | 2 |
|
| 47 |
+
| 4.2878 | 0.01 | 3 |
|
| 48 |
+
| 3.6482 | 0.01 | 4 |
|
| 49 |
+
| 3.0220 | 0.01 | 5 |
|
| 50 |
+
| 2.5057 | 0.01 | 6 |
|
| 51 |
+
| 2.1530 | 0.01 | 7 |
|
| 52 |
+
| 1.8817 | 0.01 | 8 |
|
| 53 |
+
| 1.6666 | 0.01 | 9 |
|
| 54 |
+
| 1.5034 | 0.01 | 10 |
|
| 55 |
+
| 1.3592 | 0.01 | 11 |
|
| 56 |
+
| 1.2743 | 0.01 | 12 |
|
| 57 |
+
| 1.1953 | 0.01 | 13 |
|
| 58 |
+
| 1.1265 | 0.01 | 14 |
|
| 59 |
+
| 1.0642 | 0.01 | 15 |
|
| 60 |
+
| 1.0352 | 0.01 | 16 |
|
| 61 |
+
| 0.9863 | 0.01 | 17 |
|
| 62 |
+
| 0.9612 | 0.01 | 18 |
|
| 63 |
+
| 0.9259 | 0.01 | 19 |
|
| 64 |
+
| 0.9051 | 0.01 | 20 |
|
| 65 |
+
| 0.8740 | 0.01 | 21 |
|
| 66 |
+
| 0.8529 | 0.01 | 22 |
|
| 67 |
+
| 0.8360 | 0.01 | 23 |
|
| 68 |
+
| 0.8209 | 0.01 | 24 |
|
| 69 |
+
| 0.8083 | 0.01 | 25 |
|
| 70 |
+
| 0.7941 | 0.01 | 26 |
|
| 71 |
+
| 0.7916 | 0.01 | 27 |
|
| 72 |
+
| 0.7688 | 0.01 | 28 |
|
| 73 |
+
| 0.7597 | 0.01 | 29 |
|
| 74 |
+
| 0.7603 | 0.01 | 30 |
|
| 75 |
+
| 0.7446 | 0.01 | 31 |
|
| 76 |
+
| 0.7324 | 0.01 | 32 |
|
| 77 |
+
| 0.7274 | 0.01 | 33 |
|
| 78 |
+
| 0.7141 | 0.01 | 34 |
|
| 79 |
+
| 0.7124 | 0.01 | 35 |
|
| 80 |
+
| 0.7075 | 0.01 | 36 |
|
| 81 |
+
| 0.7004 | 0.01 | 37 |
|
| 82 |
+
| 0.6949 | 0.01 | 38 |
|
| 83 |
+
| 0.6931 | 0.01 | 39 |
|
| 84 |
+
| 0.6841 | 0.01 | 40 |
|
| 85 |
+
| 0.6827 | 0.01 | 41 |
|
| 86 |
+
| 0.6889 | 0.01 | 42 |
|
| 87 |
+
| 0.6760 | 0.01 | 43 |
|
| 88 |
+
| 0.6752 | 0.01 | 44 |
|
| 89 |
+
| 0.6692 | 0.01 | 45 |
|
| 90 |
+
| 0.6636 | 0.01 | 46 |
|
| 91 |
+
| 0.6556 | 0.01 | 47 |
|
| 92 |
+
| 0.6486 | 0.01 | 48 |
|
| 93 |
+
| 0.6441 | 0.01 | 49 |
|
| 94 |
+
| 0.6493 | 0.01 | 50 |
|
| 95 |
+
| 0.6385 | 0.01 | 51 |
|
| 96 |
+
| 0.6426 | 0.01 | 52 |
|
| 97 |
+
| 0.6368 | 0.01 | 53 |
|
| 98 |
+
| 0.6285 | 0.01 | 54 |
|
| 99 |
+
| 0.6315 | 0.01 | 55 |
|
| 100 |
+
| 0.6246 | 0.01 | 56 |
|
| 101 |
+
| 0.6191 | 0.01 | 57 |
|
| 102 |
+
| 0.6242 | 0.01 | 58 |
|
| 103 |
+
| 0.6235 | 0.01 | 59 |
|
| 104 |
+
| 0.6205 | 0.01 | 60 |
|
| 105 |
+
| 0.6229 | 0.01 | 61 |
|
| 106 |
+
| 0.6108 | 0.01 | 62 |
|
| 107 |
+
| 0.6071 | 0.01 | 63 |
|
| 108 |
+
| 0.6030 | 0.01 | 64 |
|
| 109 |
+
| 0.6057 | 0.01 | 65 |
|
| 110 |
+
| 0.6052 | 0.01 | 66 |
|
| 111 |
+
| 0.6016 | 0.01 | 67 |
|
| 112 |
+
| 0.5998 | 0.01 | 68 |
|
| 113 |
+
| 0.5987 | 0.01 | 69 |
|
| 114 |
+
| 0.5992 | 0.01 | 70 |
|
| 115 |
+
| 0.5996 | 0.01 | 71 |
|
| 116 |
+
| 0.5941 | 0.01 | 72 |
|
| 117 |
+
| 0.5882 | 0.01 | 73 |
|
| 118 |
+
| 0.5949 | 0.01 | 74 |
|
| 119 |
+
| 0.5836 | 0.01 | 75 |
|
| 120 |
+
| 0.5891 | 0.01 | 76 |
|
| 121 |
+
| 0.5824 | 0.01 | 77 |
|
| 122 |
+
| 0.5845 | 0.01 | 78 |
|
| 123 |
+
| 0.5785 | 0.01 | 79 |
|
| 124 |
+
| 0.5775 | 0.01 | 80 |
|
| 125 |
+
| 0.5837 | 0.01 | 81 |
|
| 126 |
+
| 0.5836 | 0.01 | 82 |
|
| 127 |
+
| 0.5795 | 0.01 | 83 |
|
| 128 |
+
| 0.5801 | 0.01 | 84 |
|
| 129 |
+
| 0.5785 | 0.01 | 85 |
|
| 130 |
+
| 0.5778 | 0.01 | 86 |
|
| 131 |
+
| 0.5713 | 0.01 | 87 |
|
| 132 |
+
| 0.5703 | 0.01 | 88 |
|
| 133 |
+
| 0.5754 | 0.01 | 89 |
|
| 134 |
+
| 0.5681 | 0.01 | 90 |
|
| 135 |
+
| 0.5669 | 0.01 | 91 |
|
| 136 |
+
| 0.5663 | 0.01 | 92 |
|
| 137 |
+
| 0.5647 | 0.01 | 93 |
|
| 138 |
+
| 0.5684 | 0.01 | 94 |
|
| 139 |
+
| 0.5623 | 0.01 | 95 |
|
| 140 |
+
| 0.5622 | 0.01 | 96 |
|
| 141 |
+
| 0.5597 | 0.01 | 97 |
|
| 142 |
+
| 0.5592 | 0.01 | 98 |
|
| 143 |
+
| 0.5586 | 0.01 | 99 |
|
| 144 |
+
| 0.4859 | 0.0009999999 | 100 |
|
| 145 |
+
| 0.4874 | 0.0009999999 | 101 |
|
| 146 |
+
| 0.4794 | 0.0009999999 | 102 |
|
| 147 |
+
| 0.4802 | 0.0009999999 | 103 |
|
| 148 |
+
| 0.4763 | 0.0009999999 | 104 |
|
| 149 |
+
| 0.4776 | 0.0009999999 | 105 |
|
| 150 |
+
| 0.4758 | 0.0009999999 | 106 |
|
| 151 |
+
| 0.4751 | 0.0009999999 | 107 |
|
| 152 |
+
| 0.4785 | 0.0009999999 | 108 |
|
| 153 |
+
| 0.4766 | 0.0009999999 | 109 |
|
| 154 |
+
| 0.4741 | 0.0009999999 | 110 |
|
| 155 |
+
| 0.4739 | 0.0009999999 | 111 |
|
| 156 |
+
| 0.4756 | 0.0009999999 | 112 |
|
| 157 |
+
| 0.4697 | 0.0009999999 | 113 |
|
| 158 |
+
| 0.4733 | 0.0009999999 | 114 |
|
| 159 |
+
| 0.4746 | 0.0009999999 | 115 |
|
| 160 |
+
| 0.4733 | 0.0009999999 | 116 |
|
| 161 |
+
| 0.4749 | 0.0009999999 | 117 |
|
| 162 |
+
| 0.4767 | 0.0009999999 | 118 |
|
| 163 |
+
| 0.4721 | 0.0009999999 | 119 |
|
| 164 |
+
| 0.4697 | 0.0009999999 | 120 |
|
| 165 |
+
| 0.4709 | 0.0009999999 | 121 |
|
| 166 |
+
| 0.4709 | 0.0009999999 | 122 |
|
| 167 |
+
| 0.4699 | 0.0009999999 | 123 |
|
| 168 |
+
| 0.4731 | 0.0009999999 | 124 |
|
| 169 |
+
| 0.4708 | 0.0009999999 | 125 |
|
| 170 |
+
| 0.4728 | 0.0009999999 | 126 |
|
| 171 |
+
| 0.4678 | 0.0009999999 | 127 |
|
| 172 |
+
| 0.4699 | 0.0009999999 | 128 |
|
| 173 |
+
| 0.4706 | 0.0009999999 | 129 |
|
| 174 |
+
| 0.4703 | 0.0009999999 | 130 |
|
| 175 |
+
| 0.4691 | 0.0009999999 | 131 |
|
| 176 |
+
| 0.4701 | 0.0009999999 | 132 |
|
| 177 |
+
| 0.4680 | 0.0009999999 | 133 |
|
| 178 |
+
| 0.4666 | 0.0009999999 | 134 |
|
| 179 |
+
| 0.4701 | 0.0009999999 | 135 |
|
| 180 |
+
| 0.4690 | 0.0009999999 | 136 |
|
| 181 |
+
| 0.4703 | 0.0009999999 | 137 |
|
| 182 |
+
| 0.4712 | 0.0009999999 | 138 |
|
| 183 |
+
| 0.4753 | 0.0009999999 | 139 |
|
| 184 |
+
| 0.4694 | 0.0009999999 | 140 |
|
| 185 |
+
| 0.4702 | 0.0009999999 | 141 |
|
| 186 |
+
| 0.4653 | 0.0009999999 | 142 |
|
| 187 |
+
| 0.4687 | 0.0009999999 | 143 |
|
| 188 |
+
| 0.4706 | 0.0009999999 | 144 |
|
| 189 |
+
| 0.4649 | 0.0009999999 | 145 |
|
| 190 |
+
| 0.4659 | 0.0009999999 | 146 |
|
| 191 |
+
| 0.4685 | 0.0009999999 | 147 |
|
| 192 |
+
| 0.4702 | 0.0009999999 | 148 |
|
| 193 |
+
| 0.4674 | 0.0009999999 | 149 |
|
| 194 |
+
| 0.4623 | 9.999999e-05 | 150 |
|
| 195 |
+
| 0.4661 | 9.999999e-05 | 151 |
|
| 196 |
+
| 0.4614 | 9.999999e-05 | 152 |
|
| 197 |
+
| 0.4638 | 9.999999e-05 | 153 |
|
| 198 |
+
| 0.4625 | 9.999999e-05 | 154 |
|
| 199 |
+
| 0.4602 | 9.999999e-05 | 155 |
|
| 200 |
+
| 0.4661 | 9.999999e-05 | 156 |
|
| 201 |
+
| 0.4643 | 9.999999e-05 | 157 |
|
| 202 |
+
| 0.4629 | 9.999999e-05 | 158 |
|
| 203 |
+
| 0.4647 | 9.999999e-05 | 159 |
|
| 204 |
+
| 0.4642 | 9.999999e-05 | 160 |
|
| 205 |
+
| 0.4649 | 9.999999e-05 | 161 |
|
| 206 |
+
| 0.4609 | 9.999999e-05 | 162 |
|
| 207 |
+
| 0.4631 | 9.999999e-05 | 163 |
|
| 208 |
+
| 0.4663 | 9.999999e-05 | 164 |
|
| 209 |
+
| 0.4625 | 9.999999e-05 | 165 |
|
| 210 |
+
| 0.4616 | 9.999999e-05 | 166 |
|
| 211 |
+
| 0.4567 | 9.999999e-05 | 167 |
|
| 212 |
+
| 0.4567 | 9.999999e-05 | 168 |
|
| 213 |
+
| 0.4625 | 9.999999e-05 | 169 |
|
| 214 |
+
| 0.4639 | 9.999999e-05 | 170 |
|
| 215 |
+
| 0.4632 | 9.999999e-05 | 171 |
|
| 216 |
+
| 0.4606 | 9.999999e-05 | 172 |
|
| 217 |
+
| 0.4622 | 9.999999e-05 | 173 |
|
| 218 |
+
| 0.4621 | 9.999999e-05 | 174 |
|
| 219 |
+
| 0.4583 | 9.999999e-05 | 175 |
|
| 220 |
+
| 0.4586 | 9.999999e-05 | 176 |
|
| 221 |
+
| 0.4589 | 9.999999e-05 | 177 |
|
| 222 |
+
| 0.4568 | 9.999999e-05 | 178 |
|
| 223 |
+
| 0.4579 | 9.999999e-05 | 179 |
|
| 224 |
+
| 0.4634 | 9.999999e-05 | 180 |
|
| 225 |
+
| 0.4623 | 9.999999e-05 | 181 |
|
| 226 |
+
| 0.4645 | 9.999999e-05 | 182 |
|
| 227 |
+
| 0.4638 | 9.999999e-05 | 183 |
|
| 228 |
+
| 0.4610 | 9.999999e-05 | 184 |
|
| 229 |
+
| 0.4605 | 9.999999e-05 | 185 |
|
| 230 |
+
| 0.4636 | 9.999999e-05 | 186 |
|
| 231 |
+
| 0.4619 | 9.999999e-05 | 187 |
|
| 232 |
+
| 0.4627 | 9.999999e-05 | 188 |
|
| 233 |
+
| 0.4617 | 9.999999e-05 | 189 |
|
| 234 |
+
| 0.4607 | 9.999999e-05 | 190 |
|
| 235 |
+
| 0.4649 | 9.999999e-05 | 191 |
|
| 236 |
+
| 0.4601 | 9.999999e-05 | 192 |
|
| 237 |
+
| 0.4613 | 9.999999e-05 | 193 |
|
| 238 |
+
| 0.4608 | 9.999999e-05 | 194 |
|
| 239 |
+
| 0.4618 | 9.999999e-05 | 195 |
|
| 240 |
+
| 0.4593 | 9.999999e-05 | 196 |
|
| 241 |
+
| 0.4600 | 9.999999e-05 | 197 |
|
| 242 |
+
| 0.4580 | 9.999999e-05 | 198 |
|
| 243 |
+
| 0.4635 | 9.999999e-05 | 199 |
|
| 244 |
|
| 245 |
|
| 246 |
### Framework versions
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "MJ199999/gpt3_model",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4650580080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adf8569da5cc0e501fb144939133818d0b808b50f62074bbeb81fdd71cd7bf24
|
| 3 |
size 4650580080
|