End of training
Browse files- README.md +203 -203
- all_results.json +9 -9
- eval_results.json +5 -5
- pytorch_model.bin +1 -1
- train_results.json +4 -4
- trainer_state.json +1035 -1035
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -67,206 +67,206 @@ The following hyperparameters were used during training:
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
-
| No log | 1.0 | 2 |
|
| 71 |
-
| No log | 2.0 | 4 |
|
| 72 |
-
| No log | 3.0 | 6 |
|
| 73 |
-
| No log | 4.0 | 8 |
|
| 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 |
-
| 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 |
-
| 0.
|
| 245 |
-
| 0.
|
| 246 |
-
| 0.
|
| 247 |
-
| 0.
|
| 248 |
-
| 0.
|
| 249 |
-
| 0.
|
| 250 |
-
| 0.
|
| 251 |
-
| 0.
|
| 252 |
-
| 0.
|
| 253 |
-
| 0.
|
| 254 |
-
| 0.
|
| 255 |
-
| 0.
|
| 256 |
-
| 0.
|
| 257 |
-
| 0.
|
| 258 |
-
| 0.
|
| 259 |
-
| 0.
|
| 260 |
-
| 0.
|
| 261 |
-
| 0.
|
| 262 |
-
| 0.
|
| 263 |
-
| 0.
|
| 264 |
-
| 0.
|
| 265 |
-
| 0.
|
| 266 |
-
| 0.
|
| 267 |
-
| 0.
|
| 268 |
-
| 0.
|
| 269 |
-
| 0.
|
| 270 |
|
| 271 |
|
| 272 |
### Framework versions
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.8285714285714286
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.6771
|
| 36 |
+
- Accuracy: 0.8286
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 1.0 | 2 | 0.6875 | 0.8143 |
|
| 71 |
+
| No log | 2.0 | 4 | 0.6874 | 0.8143 |
|
| 72 |
+
| No log | 3.0 | 6 | 0.6873 | 0.8143 |
|
| 73 |
+
| No log | 4.0 | 8 | 0.6871 | 0.8143 |
|
| 74 |
+
| 0.7555 | 5.0 | 10 | 0.6869 | 0.8143 |
|
| 75 |
+
| 0.7555 | 6.0 | 12 | 0.6866 | 0.8143 |
|
| 76 |
+
| 0.7555 | 7.0 | 14 | 0.6862 | 0.8143 |
|
| 77 |
+
| 0.7555 | 8.0 | 16 | 0.6858 | 0.8143 |
|
| 78 |
+
| 0.7555 | 9.0 | 18 | 0.6853 | 0.8143 |
|
| 79 |
+
| 0.7576 | 10.0 | 20 | 0.6848 | 0.8143 |
|
| 80 |
+
| 0.7576 | 11.0 | 22 | 0.6842 | 0.8143 |
|
| 81 |
+
| 0.7576 | 12.0 | 24 | 0.6836 | 0.8143 |
|
| 82 |
+
| 0.7576 | 13.0 | 26 | 0.6830 | 0.8143 |
|
| 83 |
+
| 0.7576 | 14.0 | 28 | 0.6823 | 0.8143 |
|
| 84 |
+
| 0.769 | 15.0 | 30 | 0.6816 | 0.8 |
|
| 85 |
+
| 0.769 | 16.0 | 32 | 0.6808 | 0.8 |
|
| 86 |
+
| 0.769 | 17.0 | 34 | 0.6800 | 0.8143 |
|
| 87 |
+
| 0.769 | 18.0 | 36 | 0.6791 | 0.8143 |
|
| 88 |
+
| 0.769 | 19.0 | 38 | 0.6781 | 0.8143 |
|
| 89 |
+
| 0.7564 | 20.0 | 40 | 0.6771 | 0.8286 |
|
| 90 |
+
| 0.7564 | 21.0 | 42 | 0.6760 | 0.8143 |
|
| 91 |
+
| 0.7564 | 22.0 | 44 | 0.6748 | 0.8143 |
|
| 92 |
+
| 0.7564 | 23.0 | 46 | 0.6737 | 0.8 |
|
| 93 |
+
| 0.7564 | 24.0 | 48 | 0.6725 | 0.8 |
|
| 94 |
+
| 0.7508 | 25.0 | 50 | 0.6713 | 0.8143 |
|
| 95 |
+
| 0.7508 | 26.0 | 52 | 0.6701 | 0.8143 |
|
| 96 |
+
| 0.7508 | 27.0 | 54 | 0.6689 | 0.8143 |
|
| 97 |
+
| 0.7508 | 28.0 | 56 | 0.6674 | 0.8143 |
|
| 98 |
+
| 0.7508 | 29.0 | 58 | 0.6660 | 0.8143 |
|
| 99 |
+
| 0.747 | 30.0 | 60 | 0.6646 | 0.8143 |
|
| 100 |
+
| 0.747 | 31.0 | 62 | 0.6631 | 0.8143 |
|
| 101 |
+
| 0.747 | 32.0 | 64 | 0.6616 | 0.8143 |
|
| 102 |
+
| 0.747 | 33.0 | 66 | 0.6601 | 0.8143 |
|
| 103 |
+
| 0.747 | 34.0 | 68 | 0.6586 | 0.8143 |
|
| 104 |
+
| 0.7343 | 35.0 | 70 | 0.6570 | 0.8143 |
|
| 105 |
+
| 0.7343 | 36.0 | 72 | 0.6553 | 0.8143 |
|
| 106 |
+
| 0.7343 | 37.0 | 74 | 0.6536 | 0.8143 |
|
| 107 |
+
| 0.7343 | 38.0 | 76 | 0.6517 | 0.8143 |
|
| 108 |
+
| 0.7343 | 39.0 | 78 | 0.6499 | 0.8143 |
|
| 109 |
+
| 0.7532 | 40.0 | 80 | 0.6480 | 0.8143 |
|
| 110 |
+
| 0.7532 | 41.0 | 82 | 0.6461 | 0.8143 |
|
| 111 |
+
| 0.7532 | 42.0 | 84 | 0.6442 | 0.8143 |
|
| 112 |
+
| 0.7532 | 43.0 | 86 | 0.6423 | 0.8143 |
|
| 113 |
+
| 0.7532 | 44.0 | 88 | 0.6405 | 0.8143 |
|
| 114 |
+
| 0.7239 | 45.0 | 90 | 0.6387 | 0.8143 |
|
| 115 |
+
| 0.7239 | 46.0 | 92 | 0.6368 | 0.8143 |
|
| 116 |
+
| 0.7239 | 47.0 | 94 | 0.6352 | 0.8143 |
|
| 117 |
+
| 0.7239 | 48.0 | 96 | 0.6337 | 0.8143 |
|
| 118 |
+
| 0.7239 | 49.0 | 98 | 0.6321 | 0.8286 |
|
| 119 |
+
| 0.7085 | 50.0 | 100 | 0.6307 | 0.8286 |
|
| 120 |
+
| 0.7085 | 51.0 | 102 | 0.6294 | 0.8286 |
|
| 121 |
+
| 0.7085 | 52.0 | 104 | 0.6278 | 0.8286 |
|
| 122 |
+
| 0.7085 | 53.0 | 106 | 0.6263 | 0.8286 |
|
| 123 |
+
| 0.7085 | 54.0 | 108 | 0.6248 | 0.8143 |
|
| 124 |
+
| 0.7203 | 55.0 | 110 | 0.6233 | 0.8143 |
|
| 125 |
+
| 0.7203 | 56.0 | 112 | 0.6219 | 0.8143 |
|
| 126 |
+
| 0.7203 | 57.0 | 114 | 0.6205 | 0.8143 |
|
| 127 |
+
| 0.7203 | 58.0 | 116 | 0.6191 | 0.8143 |
|
| 128 |
+
| 0.7203 | 59.0 | 118 | 0.6179 | 0.8143 |
|
| 129 |
+
| 0.7136 | 60.0 | 120 | 0.6167 | 0.8143 |
|
| 130 |
+
| 0.7136 | 61.0 | 122 | 0.6157 | 0.8143 |
|
| 131 |
+
| 0.7136 | 62.0 | 124 | 0.6148 | 0.8 |
|
| 132 |
+
| 0.7136 | 63.0 | 126 | 0.6138 | 0.8 |
|
| 133 |
+
| 0.7136 | 64.0 | 128 | 0.6125 | 0.8 |
|
| 134 |
+
| 0.7123 | 65.0 | 130 | 0.6111 | 0.8 |
|
| 135 |
+
| 0.7123 | 66.0 | 132 | 0.6096 | 0.8143 |
|
| 136 |
+
| 0.7123 | 67.0 | 134 | 0.6083 | 0.8143 |
|
| 137 |
+
| 0.7123 | 68.0 | 136 | 0.6070 | 0.8143 |
|
| 138 |
+
| 0.7123 | 69.0 | 138 | 0.6057 | 0.8143 |
|
| 139 |
+
| 0.7076 | 70.0 | 140 | 0.6046 | 0.8143 |
|
| 140 |
+
| 0.7076 | 71.0 | 142 | 0.6035 | 0.8143 |
|
| 141 |
+
| 0.7076 | 72.0 | 144 | 0.6023 | 0.8143 |
|
| 142 |
+
| 0.7076 | 73.0 | 146 | 0.6011 | 0.8143 |
|
| 143 |
+
| 0.7076 | 74.0 | 148 | 0.5999 | 0.8143 |
|
| 144 |
+
| 0.6878 | 75.0 | 150 | 0.5988 | 0.8143 |
|
| 145 |
+
| 0.6878 | 76.0 | 152 | 0.5975 | 0.8143 |
|
| 146 |
+
| 0.6878 | 77.0 | 154 | 0.5964 | 0.8143 |
|
| 147 |
+
| 0.6878 | 78.0 | 156 | 0.5953 | 0.8143 |
|
| 148 |
+
| 0.6878 | 79.0 | 158 | 0.5942 | 0.8143 |
|
| 149 |
+
| 0.6657 | 80.0 | 160 | 0.5932 | 0.8143 |
|
| 150 |
+
| 0.6657 | 81.0 | 162 | 0.5923 | 0.8143 |
|
| 151 |
+
| 0.6657 | 82.0 | 164 | 0.5914 | 0.8143 |
|
| 152 |
+
| 0.6657 | 83.0 | 166 | 0.5906 | 0.8143 |
|
| 153 |
+
| 0.6657 | 84.0 | 168 | 0.5897 | 0.8143 |
|
| 154 |
+
| 0.6434 | 85.0 | 170 | 0.5888 | 0.8143 |
|
| 155 |
+
| 0.6434 | 86.0 | 172 | 0.5878 | 0.8143 |
|
| 156 |
+
| 0.6434 | 87.0 | 174 | 0.5868 | 0.8143 |
|
| 157 |
+
| 0.6434 | 88.0 | 176 | 0.5859 | 0.8143 |
|
| 158 |
+
| 0.6434 | 89.0 | 178 | 0.5851 | 0.8143 |
|
| 159 |
+
| 0.6825 | 90.0 | 180 | 0.5843 | 0.8143 |
|
| 160 |
+
| 0.6825 | 91.0 | 182 | 0.5836 | 0.8143 |
|
| 161 |
+
| 0.6825 | 92.0 | 184 | 0.5828 | 0.8143 |
|
| 162 |
+
| 0.6825 | 93.0 | 186 | 0.5823 | 0.8143 |
|
| 163 |
+
| 0.6825 | 94.0 | 188 | 0.5817 | 0.8286 |
|
| 164 |
+
| 0.6695 | 95.0 | 190 | 0.5809 | 0.8143 |
|
| 165 |
+
| 0.6695 | 96.0 | 192 | 0.5801 | 0.8143 |
|
| 166 |
+
| 0.6695 | 97.0 | 194 | 0.5793 | 0.8143 |
|
| 167 |
+
| 0.6695 | 98.0 | 196 | 0.5787 | 0.8143 |
|
| 168 |
+
| 0.6695 | 99.0 | 198 | 0.5780 | 0.8143 |
|
| 169 |
+
| 0.6672 | 100.0 | 200 | 0.5772 | 0.8143 |
|
| 170 |
+
| 0.6672 | 101.0 | 202 | 0.5762 | 0.8143 |
|
| 171 |
+
| 0.6672 | 102.0 | 204 | 0.5754 | 0.8143 |
|
| 172 |
+
| 0.6672 | 103.0 | 206 | 0.5746 | 0.8143 |
|
| 173 |
+
| 0.6672 | 104.0 | 208 | 0.5738 | 0.8143 |
|
| 174 |
+
| 0.6569 | 105.0 | 210 | 0.5731 | 0.8143 |
|
| 175 |
+
| 0.6569 | 106.0 | 212 | 0.5724 | 0.8143 |
|
| 176 |
+
| 0.6569 | 107.0 | 214 | 0.5716 | 0.8143 |
|
| 177 |
+
| 0.6569 | 108.0 | 216 | 0.5708 | 0.8143 |
|
| 178 |
+
| 0.6569 | 109.0 | 218 | 0.5701 | 0.8143 |
|
| 179 |
+
| 0.6748 | 110.0 | 220 | 0.5694 | 0.8143 |
|
| 180 |
+
| 0.6748 | 111.0 | 222 | 0.5687 | 0.8143 |
|
| 181 |
+
| 0.6748 | 112.0 | 224 | 0.5680 | 0.8143 |
|
| 182 |
+
| 0.6748 | 113.0 | 226 | 0.5674 | 0.8143 |
|
| 183 |
+
| 0.6748 | 114.0 | 228 | 0.5668 | 0.8143 |
|
| 184 |
+
| 0.6388 | 115.0 | 230 | 0.5662 | 0.8143 |
|
| 185 |
+
| 0.6388 | 116.0 | 232 | 0.5657 | 0.8143 |
|
| 186 |
+
| 0.6388 | 117.0 | 234 | 0.5652 | 0.8143 |
|
| 187 |
+
| 0.6388 | 118.0 | 236 | 0.5648 | 0.8286 |
|
| 188 |
+
| 0.6388 | 119.0 | 238 | 0.5645 | 0.8286 |
|
| 189 |
+
| 0.6551 | 120.0 | 240 | 0.5641 | 0.8286 |
|
| 190 |
+
| 0.6551 | 121.0 | 242 | 0.5636 | 0.8143 |
|
| 191 |
+
| 0.6551 | 122.0 | 244 | 0.5631 | 0.8143 |
|
| 192 |
+
| 0.6551 | 123.0 | 246 | 0.5627 | 0.8143 |
|
| 193 |
+
| 0.6551 | 124.0 | 248 | 0.5624 | 0.8143 |
|
| 194 |
+
| 0.6452 | 125.0 | 250 | 0.5622 | 0.8143 |
|
| 195 |
+
| 0.6452 | 126.0 | 252 | 0.5620 | 0.8143 |
|
| 196 |
+
| 0.6452 | 127.0 | 254 | 0.5618 | 0.8143 |
|
| 197 |
+
| 0.6452 | 128.0 | 256 | 0.5615 | 0.8143 |
|
| 198 |
+
| 0.6452 | 129.0 | 258 | 0.5613 | 0.8143 |
|
| 199 |
+
| 0.645 | 130.0 | 260 | 0.5611 | 0.8143 |
|
| 200 |
+
| 0.645 | 131.0 | 262 | 0.5608 | 0.8143 |
|
| 201 |
+
| 0.645 | 132.0 | 264 | 0.5606 | 0.8143 |
|
| 202 |
+
| 0.645 | 133.0 | 266 | 0.5602 | 0.8143 |
|
| 203 |
+
| 0.645 | 134.0 | 268 | 0.5596 | 0.8143 |
|
| 204 |
+
| 0.629 | 135.0 | 270 | 0.5590 | 0.8143 |
|
| 205 |
+
| 0.629 | 136.0 | 272 | 0.5582 | 0.8143 |
|
| 206 |
+
| 0.629 | 137.0 | 274 | 0.5576 | 0.8143 |
|
| 207 |
+
| 0.629 | 138.0 | 276 | 0.5571 | 0.8143 |
|
| 208 |
+
| 0.629 | 139.0 | 278 | 0.5568 | 0.8143 |
|
| 209 |
+
| 0.7126 | 140.0 | 280 | 0.5565 | 0.8143 |
|
| 210 |
+
| 0.7126 | 141.0 | 282 | 0.5563 | 0.8143 |
|
| 211 |
+
| 0.7126 | 142.0 | 284 | 0.5561 | 0.8143 |
|
| 212 |
+
| 0.7126 | 143.0 | 286 | 0.5559 | 0.8143 |
|
| 213 |
+
| 0.7126 | 144.0 | 288 | 0.5555 | 0.8143 |
|
| 214 |
+
| 0.669 | 145.0 | 290 | 0.5552 | 0.8143 |
|
| 215 |
+
| 0.669 | 146.0 | 292 | 0.5547 | 0.8143 |
|
| 216 |
+
| 0.669 | 147.0 | 294 | 0.5542 | 0.8143 |
|
| 217 |
+
| 0.669 | 148.0 | 296 | 0.5538 | 0.8143 |
|
| 218 |
+
| 0.669 | 149.0 | 298 | 0.5534 | 0.8143 |
|
| 219 |
+
| 0.6481 | 150.0 | 300 | 0.5530 | 0.8143 |
|
| 220 |
+
| 0.6481 | 151.0 | 302 | 0.5526 | 0.8143 |
|
| 221 |
+
| 0.6481 | 152.0 | 304 | 0.5522 | 0.8143 |
|
| 222 |
+
| 0.6481 | 153.0 | 306 | 0.5519 | 0.8143 |
|
| 223 |
+
| 0.6481 | 154.0 | 308 | 0.5515 | 0.8143 |
|
| 224 |
+
| 0.6211 | 155.0 | 310 | 0.5510 | 0.8143 |
|
| 225 |
+
| 0.6211 | 156.0 | 312 | 0.5506 | 0.8143 |
|
| 226 |
+
| 0.6211 | 157.0 | 314 | 0.5502 | 0.8143 |
|
| 227 |
+
| 0.6211 | 158.0 | 316 | 0.5499 | 0.8143 |
|
| 228 |
+
| 0.6211 | 159.0 | 318 | 0.5496 | 0.8143 |
|
| 229 |
+
| 0.6458 | 160.0 | 320 | 0.5492 | 0.8286 |
|
| 230 |
+
| 0.6458 | 161.0 | 322 | 0.5490 | 0.8143 |
|
| 231 |
+
| 0.6458 | 162.0 | 324 | 0.5488 | 0.8143 |
|
| 232 |
+
| 0.6458 | 163.0 | 326 | 0.5486 | 0.8143 |
|
| 233 |
+
| 0.6458 | 164.0 | 328 | 0.5484 | 0.8143 |
|
| 234 |
+
| 0.6317 | 165.0 | 330 | 0.5481 | 0.8143 |
|
| 235 |
+
| 0.6317 | 166.0 | 332 | 0.5479 | 0.8286 |
|
| 236 |
+
| 0.6317 | 167.0 | 334 | 0.5476 | 0.8286 |
|
| 237 |
+
| 0.6317 | 168.0 | 336 | 0.5473 | 0.8286 |
|
| 238 |
+
| 0.6317 | 169.0 | 338 | 0.5471 | 0.8286 |
|
| 239 |
+
| 0.6154 | 170.0 | 340 | 0.5470 | 0.8286 |
|
| 240 |
+
| 0.6154 | 171.0 | 342 | 0.5468 | 0.8286 |
|
| 241 |
+
| 0.6154 | 172.0 | 344 | 0.5466 | 0.8286 |
|
| 242 |
+
| 0.6154 | 173.0 | 346 | 0.5464 | 0.8286 |
|
| 243 |
+
| 0.6154 | 174.0 | 348 | 0.5462 | 0.8286 |
|
| 244 |
+
| 0.6323 | 175.0 | 350 | 0.5460 | 0.8286 |
|
| 245 |
+
| 0.6323 | 176.0 | 352 | 0.5459 | 0.8286 |
|
| 246 |
+
| 0.6323 | 177.0 | 354 | 0.5457 | 0.8286 |
|
| 247 |
+
| 0.6323 | 178.0 | 356 | 0.5456 | 0.8286 |
|
| 248 |
+
| 0.6323 | 179.0 | 358 | 0.5455 | 0.8286 |
|
| 249 |
+
| 0.6331 | 180.0 | 360 | 0.5453 | 0.8286 |
|
| 250 |
+
| 0.6331 | 181.0 | 362 | 0.5452 | 0.8286 |
|
| 251 |
+
| 0.6331 | 182.0 | 364 | 0.5451 | 0.8286 |
|
| 252 |
+
| 0.6331 | 183.0 | 366 | 0.5449 | 0.8286 |
|
| 253 |
+
| 0.6331 | 184.0 | 368 | 0.5448 | 0.8286 |
|
| 254 |
+
| 0.6333 | 185.0 | 370 | 0.5447 | 0.8286 |
|
| 255 |
+
| 0.6333 | 186.0 | 372 | 0.5447 | 0.8286 |
|
| 256 |
+
| 0.6333 | 187.0 | 374 | 0.5446 | 0.8286 |
|
| 257 |
+
| 0.6333 | 188.0 | 376 | 0.5445 | 0.8286 |
|
| 258 |
+
| 0.6333 | 189.0 | 378 | 0.5445 | 0.8286 |
|
| 259 |
+
| 0.608 | 190.0 | 380 | 0.5444 | 0.8286 |
|
| 260 |
+
| 0.608 | 191.0 | 382 | 0.5444 | 0.8286 |
|
| 261 |
+
| 0.608 | 192.0 | 384 | 0.5443 | 0.8286 |
|
| 262 |
+
| 0.608 | 193.0 | 386 | 0.5443 | 0.8286 |
|
| 263 |
+
| 0.608 | 194.0 | 388 | 0.5442 | 0.8286 |
|
| 264 |
+
| 0.6155 | 195.0 | 390 | 0.5442 | 0.8286 |
|
| 265 |
+
| 0.6155 | 196.0 | 392 | 0.5442 | 0.8286 |
|
| 266 |
+
| 0.6155 | 197.0 | 394 | 0.5442 | 0.8286 |
|
| 267 |
+
| 0.6155 | 198.0 | 396 | 0.5441 | 0.8286 |
|
| 268 |
+
| 0.6155 | 199.0 | 398 | 0.5441 | 0.8286 |
|
| 269 |
+
| 0.6272 | 200.0 | 400 | 0.5441 | 0.8286 |
|
| 270 |
|
| 271 |
|
| 272 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 200.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 2.
|
| 8 |
"total_flos": 2.23710151698432e+18,
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 200.0,
|
| 3 |
+
"eval_accuracy": 0.8285714285714286,
|
| 4 |
+
"eval_loss": 0.6770716309547424,
|
| 5 |
+
"eval_runtime": 0.6932,
|
| 6 |
+
"eval_samples_per_second": 100.985,
|
| 7 |
+
"eval_steps_per_second": 2.885,
|
| 8 |
"total_flos": 2.23710151698432e+18,
|
| 9 |
+
"train_loss": 0.6791047298908234,
|
| 10 |
+
"train_runtime": 1022.1437,
|
| 11 |
+
"train_samples_per_second": 88.05,
|
| 12 |
+
"train_steps_per_second": 0.391
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 200.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 200.0,
|
| 3 |
+
"eval_accuracy": 0.8285714285714286,
|
| 4 |
+
"eval_loss": 0.6770716309547424,
|
| 5 |
+
"eval_runtime": 0.6932,
|
| 6 |
+
"eval_samples_per_second": 100.985,
|
| 7 |
+
"eval_steps_per_second": 2.885
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110397937
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3948bfd3caacca713d9cd1f9c0bcc4bab7d1122e553b8f0d46454329a59a0401
|
| 3 |
size 110397937
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 200.0,
|
| 3 |
"total_flos": 2.23710151698432e+18,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 200.0,
|
| 3 |
"total_flos": 2.23710151698432e+18,
|
| 4 |
+
"train_loss": 0.6791047298908234,
|
| 5 |
+
"train_runtime": 1022.1437,
|
| 6 |
+
"train_samples_per_second": 88.05,
|
| 7 |
+
"train_steps_per_second": 0.391
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-ADC-3cls-0922/checkpoint-
|
| 4 |
"epoch": 200.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 400,
|
|
@@ -10,2052 +10,2052 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"eval_accuracy": 0.
|
| 14 |
-
"eval_loss":
|
| 15 |
-
"eval_runtime":
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second":
|
| 18 |
"step": 2
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 2.0,
|
| 22 |
-
"eval_accuracy": 0.
|
| 23 |
-
"eval_loss":
|
| 24 |
-
"eval_runtime":
|
| 25 |
-
"eval_samples_per_second":
|
| 26 |
-
"eval_steps_per_second":
|
| 27 |
"step": 4
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 3.0,
|
| 31 |
-
"eval_accuracy": 0.
|
| 32 |
-
"eval_loss":
|
| 33 |
-
"eval_runtime": 0.
|
| 34 |
-
"eval_samples_per_second":
|
| 35 |
-
"eval_steps_per_second":
|
| 36 |
"step": 6
|
| 37 |
},
|
| 38 |
{
|
| 39 |
"epoch": 4.0,
|
| 40 |
-
"eval_accuracy": 0.
|
| 41 |
-
"eval_loss":
|
| 42 |
-
"eval_runtime":
|
| 43 |
-
"eval_samples_per_second":
|
| 44 |
-
"eval_steps_per_second":
|
| 45 |
"step": 8
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 5.0,
|
| 49 |
"learning_rate": 1.25e-05,
|
| 50 |
-
"loss":
|
| 51 |
"step": 10
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 5.0,
|
| 55 |
-
"eval_accuracy": 0.
|
| 56 |
-
"eval_loss":
|
| 57 |
-
"eval_runtime": 0.
|
| 58 |
-
"eval_samples_per_second":
|
| 59 |
-
"eval_steps_per_second": 3.
|
| 60 |
"step": 10
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 6.0,
|
| 64 |
-
"eval_accuracy": 0.
|
| 65 |
-
"eval_loss":
|
| 66 |
-
"eval_runtime": 0.
|
| 67 |
-
"eval_samples_per_second":
|
| 68 |
-
"eval_steps_per_second": 3.
|
| 69 |
"step": 12
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 7.0,
|
| 73 |
-
"eval_accuracy": 0.
|
| 74 |
-
"eval_loss":
|
| 75 |
-
"eval_runtime": 0.
|
| 76 |
-
"eval_samples_per_second":
|
| 77 |
-
"eval_steps_per_second": 2.
|
| 78 |
"step": 14
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 8.0,
|
| 82 |
-
"eval_accuracy": 0.
|
| 83 |
-
"eval_loss":
|
| 84 |
-
"eval_runtime": 0.
|
| 85 |
-
"eval_samples_per_second": 109.
|
| 86 |
-
"eval_steps_per_second": 3.
|
| 87 |
"step": 16
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 9.0,
|
| 91 |
-
"eval_accuracy": 0.
|
| 92 |
-
"eval_loss":
|
| 93 |
-
"eval_runtime": 0.
|
| 94 |
-
"eval_samples_per_second":
|
| 95 |
-
"eval_steps_per_second": 3.
|
| 96 |
"step": 18
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 10.0,
|
| 100 |
"learning_rate": 2.5e-05,
|
| 101 |
-
"loss":
|
| 102 |
"step": 20
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 10.0,
|
| 106 |
-
"eval_accuracy": 0.
|
| 107 |
-
"eval_loss":
|
| 108 |
-
"eval_runtime": 0.
|
| 109 |
-
"eval_samples_per_second":
|
| 110 |
-
"eval_steps_per_second": 2.
|
| 111 |
"step": 20
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 11.0,
|
| 115 |
-
"eval_accuracy": 0.
|
| 116 |
-
"eval_loss":
|
| 117 |
-
"eval_runtime": 0.
|
| 118 |
-
"eval_samples_per_second": 109.
|
| 119 |
-
"eval_steps_per_second": 3.
|
| 120 |
"step": 22
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 12.0,
|
| 124 |
-
"eval_accuracy": 0.
|
| 125 |
-
"eval_loss":
|
| 126 |
-
"eval_runtime": 0.
|
| 127 |
-
"eval_samples_per_second":
|
| 128 |
-
"eval_steps_per_second": 3.
|
| 129 |
"step": 24
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 13.0,
|
| 133 |
-
"eval_accuracy": 0.
|
| 134 |
-
"eval_loss":
|
| 135 |
-
"eval_runtime": 0.
|
| 136 |
-
"eval_samples_per_second":
|
| 137 |
-
"eval_steps_per_second": 2.
|
| 138 |
"step": 26
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 14.0,
|
| 142 |
-
"eval_accuracy": 0.
|
| 143 |
-
"eval_loss":
|
| 144 |
-
"eval_runtime": 0.
|
| 145 |
-
"eval_samples_per_second":
|
| 146 |
-
"eval_steps_per_second": 3.
|
| 147 |
"step": 28
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 15.0,
|
| 151 |
"learning_rate": 3.7500000000000003e-05,
|
| 152 |
-
"loss":
|
| 153 |
"step": 30
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 15.0,
|
| 157 |
-
"eval_accuracy": 0.
|
| 158 |
-
"eval_loss":
|
| 159 |
-
"eval_runtime": 0.
|
| 160 |
-
"eval_samples_per_second":
|
| 161 |
-
"eval_steps_per_second": 3.
|
| 162 |
"step": 30
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 16.0,
|
| 166 |
-
"eval_accuracy": 0.
|
| 167 |
-
"eval_loss":
|
| 168 |
-
"eval_runtime": 0.
|
| 169 |
-
"eval_samples_per_second": 84.
|
| 170 |
-
"eval_steps_per_second": 2.
|
| 171 |
"step": 32
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 17.0,
|
| 175 |
-
"eval_accuracy": 0.
|
| 176 |
-
"eval_loss":
|
| 177 |
-
"eval_runtime": 0.
|
| 178 |
-
"eval_samples_per_second":
|
| 179 |
-
"eval_steps_per_second": 3.
|
| 180 |
"step": 34
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 18.0,
|
| 184 |
-
"eval_accuracy": 0.
|
| 185 |
-
"eval_loss":
|
| 186 |
-
"eval_runtime": 0.
|
| 187 |
-
"eval_samples_per_second": 110.
|
| 188 |
-
"eval_steps_per_second": 3.
|
| 189 |
"step": 36
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 19.0,
|
| 193 |
-
"eval_accuracy": 0.
|
| 194 |
-
"eval_loss":
|
| 195 |
-
"eval_runtime":
|
| 196 |
-
"eval_samples_per_second":
|
| 197 |
-
"eval_steps_per_second":
|
| 198 |
"step": 38
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 20.0,
|
| 202 |
"learning_rate": 5e-05,
|
| 203 |
-
"loss":
|
| 204 |
"step": 40
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 20.0,
|
| 208 |
-
"eval_accuracy": 0.
|
| 209 |
-
"eval_loss":
|
| 210 |
-
"eval_runtime": 0.
|
| 211 |
-
"eval_samples_per_second":
|
| 212 |
-
"eval_steps_per_second": 3.
|
| 213 |
"step": 40
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 21.0,
|
| 217 |
-
"eval_accuracy": 0.
|
| 218 |
-
"eval_loss":
|
| 219 |
-
"eval_runtime": 0.
|
| 220 |
-
"eval_samples_per_second":
|
| 221 |
-
"eval_steps_per_second": 3.
|
| 222 |
"step": 42
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 22.0,
|
| 226 |
-
"eval_accuracy": 0.
|
| 227 |
-
"eval_loss":
|
| 228 |
-
"eval_runtime": 0.
|
| 229 |
-
"eval_samples_per_second":
|
| 230 |
-
"eval_steps_per_second": 2.
|
| 231 |
"step": 44
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 23.0,
|
| 235 |
-
"eval_accuracy": 0.
|
| 236 |
-
"eval_loss":
|
| 237 |
-
"eval_runtime": 0.
|
| 238 |
-
"eval_samples_per_second":
|
| 239 |
-
"eval_steps_per_second": 3.
|
| 240 |
"step": 46
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 24.0,
|
| 244 |
-
"eval_accuracy": 0.
|
| 245 |
-
"eval_loss":
|
| 246 |
-
"eval_runtime": 0.
|
| 247 |
-
"eval_samples_per_second":
|
| 248 |
-
"eval_steps_per_second": 3.
|
| 249 |
"step": 48
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 25.0,
|
| 253 |
"learning_rate": 6.25e-05,
|
| 254 |
-
"loss":
|
| 255 |
"step": 50
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 25.0,
|
| 259 |
-
"eval_accuracy": 0.
|
| 260 |
-
"eval_loss":
|
| 261 |
-
"eval_runtime": 0.
|
| 262 |
-
"eval_samples_per_second":
|
| 263 |
-
"eval_steps_per_second":
|
| 264 |
"step": 50
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 26.0,
|
| 268 |
-
"eval_accuracy": 0.
|
| 269 |
-
"eval_loss": 0.
|
| 270 |
-
"eval_runtime": 0.
|
| 271 |
-
"eval_samples_per_second":
|
| 272 |
-
"eval_steps_per_second":
|
| 273 |
"step": 52
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 27.0,
|
| 277 |
-
"eval_accuracy": 0.
|
| 278 |
-
"eval_loss": 0.
|
| 279 |
-
"eval_runtime": 0.
|
| 280 |
-
"eval_samples_per_second":
|
| 281 |
-
"eval_steps_per_second": 3.
|
| 282 |
"step": 54
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 28.0,
|
| 286 |
-
"eval_accuracy": 0.
|
| 287 |
-
"eval_loss": 0.
|
| 288 |
-
"eval_runtime": 0.
|
| 289 |
-
"eval_samples_per_second":
|
| 290 |
-
"eval_steps_per_second":
|
| 291 |
"step": 56
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 29.0,
|
| 295 |
-
"eval_accuracy": 0.
|
| 296 |
-
"eval_loss": 0.
|
| 297 |
-
"eval_runtime": 0.
|
| 298 |
-
"eval_samples_per_second":
|
| 299 |
-
"eval_steps_per_second":
|
| 300 |
"step": 58
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 30.0,
|
| 304 |
"learning_rate": 7.500000000000001e-05,
|
| 305 |
-
"loss":
|
| 306 |
"step": 60
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 30.0,
|
| 310 |
-
"eval_accuracy": 0.
|
| 311 |
-
"eval_loss": 0.
|
| 312 |
-
"eval_runtime": 0.
|
| 313 |
-
"eval_samples_per_second":
|
| 314 |
-
"eval_steps_per_second": 3.
|
| 315 |
"step": 60
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 31.0,
|
| 319 |
-
"eval_accuracy": 0.
|
| 320 |
-
"eval_loss": 0.
|
| 321 |
-
"eval_runtime": 0.
|
| 322 |
-
"eval_samples_per_second":
|
| 323 |
-
"eval_steps_per_second":
|
| 324 |
"step": 62
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 32.0,
|
| 328 |
-
"eval_accuracy": 0.
|
| 329 |
-
"eval_loss": 0.
|
| 330 |
-
"eval_runtime": 0.
|
| 331 |
-
"eval_samples_per_second":
|
| 332 |
-
"eval_steps_per_second":
|
| 333 |
"step": 64
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 33.0,
|
| 337 |
-
"eval_accuracy": 0.
|
| 338 |
-
"eval_loss": 0.
|
| 339 |
-
"eval_runtime": 0.
|
| 340 |
-
"eval_samples_per_second": 109.
|
| 341 |
-
"eval_steps_per_second": 3.
|
| 342 |
"step": 66
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"epoch": 34.0,
|
| 346 |
-
"eval_accuracy": 0.
|
| 347 |
-
"eval_loss": 0.
|
| 348 |
-
"eval_runtime": 0.
|
| 349 |
-
"eval_samples_per_second":
|
| 350 |
-
"eval_steps_per_second":
|
| 351 |
"step": 68
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 35.0,
|
| 355 |
"learning_rate": 8.75e-05,
|
| 356 |
-
"loss":
|
| 357 |
"step": 70
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 35.0,
|
| 361 |
-
"eval_accuracy": 0.
|
| 362 |
-
"eval_loss": 0.
|
| 363 |
-
"eval_runtime": 0.
|
| 364 |
-
"eval_samples_per_second":
|
| 365 |
-
"eval_steps_per_second":
|
| 366 |
"step": 70
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 36.0,
|
| 370 |
-
"eval_accuracy": 0.
|
| 371 |
-
"eval_loss": 0.
|
| 372 |
-
"eval_runtime": 0.
|
| 373 |
-
"eval_samples_per_second":
|
| 374 |
-
"eval_steps_per_second": 3.
|
| 375 |
"step": 72
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 37.0,
|
| 379 |
-
"eval_accuracy": 0.
|
| 380 |
-
"eval_loss": 0.
|
| 381 |
-
"eval_runtime": 0.
|
| 382 |
-
"eval_samples_per_second":
|
| 383 |
-
"eval_steps_per_second":
|
| 384 |
"step": 74
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 38.0,
|
| 388 |
-
"eval_accuracy": 0.
|
| 389 |
-
"eval_loss": 0.
|
| 390 |
-
"eval_runtime": 0.
|
| 391 |
-
"eval_samples_per_second":
|
| 392 |
-
"eval_steps_per_second":
|
| 393 |
"step": 76
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 39.0,
|
| 397 |
-
"eval_accuracy": 0.
|
| 398 |
-
"eval_loss": 0.
|
| 399 |
-
"eval_runtime": 0.
|
| 400 |
-
"eval_samples_per_second":
|
| 401 |
-
"eval_steps_per_second":
|
| 402 |
"step": 78
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 40.0,
|
| 406 |
"learning_rate": 0.0001,
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 80
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 40.0,
|
| 412 |
-
"eval_accuracy": 0.
|
| 413 |
-
"eval_loss": 0.
|
| 414 |
-
"eval_runtime": 0.
|
| 415 |
-
"eval_samples_per_second":
|
| 416 |
-
"eval_steps_per_second":
|
| 417 |
"step": 80
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 41.0,
|
| 421 |
-
"eval_accuracy": 0.
|
| 422 |
-
"eval_loss": 0.
|
| 423 |
-
"eval_runtime": 0.
|
| 424 |
-
"eval_samples_per_second":
|
| 425 |
-
"eval_steps_per_second":
|
| 426 |
"step": 82
|
| 427 |
},
|
| 428 |
{
|
| 429 |
"epoch": 42.0,
|
| 430 |
-
"eval_accuracy": 0.
|
| 431 |
-
"eval_loss": 0.
|
| 432 |
-
"eval_runtime": 0.
|
| 433 |
-
"eval_samples_per_second":
|
| 434 |
-
"eval_steps_per_second": 3.
|
| 435 |
"step": 84
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 43.0,
|
| 439 |
-
"eval_accuracy": 0.
|
| 440 |
-
"eval_loss": 0.
|
| 441 |
-
"eval_runtime": 0.
|
| 442 |
-
"eval_samples_per_second":
|
| 443 |
-
"eval_steps_per_second":
|
| 444 |
"step": 86
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 44.0,
|
| 448 |
-
"eval_accuracy": 0.
|
| 449 |
-
"eval_loss": 0.
|
| 450 |
-
"eval_runtime": 0.
|
| 451 |
-
"eval_samples_per_second":
|
| 452 |
-
"eval_steps_per_second":
|
| 453 |
"step": 88
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 45.0,
|
| 457 |
"learning_rate": 9.687500000000001e-05,
|
| 458 |
-
"loss": 0.
|
| 459 |
"step": 90
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 45.0,
|
| 463 |
-
"eval_accuracy": 0.
|
| 464 |
-
"eval_loss": 0.
|
| 465 |
-
"eval_runtime": 0.
|
| 466 |
-
"eval_samples_per_second":
|
| 467 |
-
"eval_steps_per_second": 3.
|
| 468 |
"step": 90
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 46.0,
|
| 472 |
-
"eval_accuracy": 0.
|
| 473 |
-
"eval_loss": 0.
|
| 474 |
-
"eval_runtime": 0.
|
| 475 |
-
"eval_samples_per_second":
|
| 476 |
-
"eval_steps_per_second":
|
| 477 |
"step": 92
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 47.0,
|
| 481 |
-
"eval_accuracy": 0.
|
| 482 |
-
"eval_loss": 0.
|
| 483 |
-
"eval_runtime": 0.
|
| 484 |
-
"eval_samples_per_second":
|
| 485 |
-
"eval_steps_per_second":
|
| 486 |
"step": 94
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 48.0,
|
| 490 |
-
"eval_accuracy": 0.
|
| 491 |
-
"eval_loss": 0.
|
| 492 |
-
"eval_runtime": 0.
|
| 493 |
-
"eval_samples_per_second":
|
| 494 |
-
"eval_steps_per_second": 3.
|
| 495 |
"step": 96
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 49.0,
|
| 499 |
-
"eval_accuracy": 0.
|
| 500 |
-
"eval_loss": 0.
|
| 501 |
-
"eval_runtime": 0.
|
| 502 |
-
"eval_samples_per_second":
|
| 503 |
-
"eval_steps_per_second":
|
| 504 |
"step": 98
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 50.0,
|
| 508 |
"learning_rate": 9.375e-05,
|
| 509 |
-
"loss": 0.
|
| 510 |
"step": 100
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 50.0,
|
| 514 |
-
"eval_accuracy": 0.
|
| 515 |
-
"eval_loss": 0.
|
| 516 |
-
"eval_runtime": 0.
|
| 517 |
-
"eval_samples_per_second":
|
| 518 |
-
"eval_steps_per_second":
|
| 519 |
"step": 100
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 51.0,
|
| 523 |
-
"eval_accuracy": 0.
|
| 524 |
-
"eval_loss": 0.
|
| 525 |
-
"eval_runtime": 0.
|
| 526 |
-
"eval_samples_per_second":
|
| 527 |
-
"eval_steps_per_second": 3.
|
| 528 |
"step": 102
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 52.0,
|
| 532 |
-
"eval_accuracy": 0.
|
| 533 |
-
"eval_loss": 0.
|
| 534 |
-
"eval_runtime": 0.
|
| 535 |
-
"eval_samples_per_second":
|
| 536 |
-
"eval_steps_per_second":
|
| 537 |
"step": 104
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 53.0,
|
| 541 |
-
"eval_accuracy": 0.
|
| 542 |
-
"eval_loss": 0.
|
| 543 |
-
"eval_runtime": 0.
|
| 544 |
-
"eval_samples_per_second":
|
| 545 |
-
"eval_steps_per_second":
|
| 546 |
"step": 106
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 54.0,
|
| 550 |
-
"eval_accuracy": 0.
|
| 551 |
-
"eval_loss": 0.
|
| 552 |
-
"eval_runtime": 0.
|
| 553 |
-
"eval_samples_per_second":
|
| 554 |
-
"eval_steps_per_second": 3.
|
| 555 |
"step": 108
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 55.0,
|
| 559 |
"learning_rate": 9.062500000000001e-05,
|
| 560 |
-
"loss": 0.
|
| 561 |
"step": 110
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 55.0,
|
| 565 |
-
"eval_accuracy": 0.
|
| 566 |
-
"eval_loss": 0.
|
| 567 |
-
"eval_runtime": 0.
|
| 568 |
-
"eval_samples_per_second":
|
| 569 |
-
"eval_steps_per_second":
|
| 570 |
"step": 110
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 56.0,
|
| 574 |
-
"eval_accuracy": 0.
|
| 575 |
-
"eval_loss": 0.
|
| 576 |
-
"eval_runtime": 0.
|
| 577 |
-
"eval_samples_per_second":
|
| 578 |
-
"eval_steps_per_second":
|
| 579 |
"step": 112
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 57.0,
|
| 583 |
-
"eval_accuracy": 0.
|
| 584 |
-
"eval_loss": 0.
|
| 585 |
-
"eval_runtime": 0.
|
| 586 |
-
"eval_samples_per_second":
|
| 587 |
-
"eval_steps_per_second": 3.
|
| 588 |
"step": 114
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 58.0,
|
| 592 |
-
"eval_accuracy": 0.
|
| 593 |
-
"eval_loss": 0.
|
| 594 |
-
"eval_runtime": 0.
|
| 595 |
-
"eval_samples_per_second":
|
| 596 |
-
"eval_steps_per_second": 3.
|
| 597 |
"step": 116
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 59.0,
|
| 601 |
-
"eval_accuracy": 0.
|
| 602 |
-
"eval_loss": 0.
|
| 603 |
-
"eval_runtime": 0.
|
| 604 |
-
"eval_samples_per_second":
|
| 605 |
-
"eval_steps_per_second": 2.
|
| 606 |
"step": 118
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 60.0,
|
| 610 |
"learning_rate": 8.75e-05,
|
| 611 |
-
"loss": 0.
|
| 612 |
"step": 120
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 60.0,
|
| 616 |
-
"eval_accuracy": 0.
|
| 617 |
-
"eval_loss": 0.
|
| 618 |
-
"eval_runtime": 0.
|
| 619 |
-
"eval_samples_per_second":
|
| 620 |
-
"eval_steps_per_second": 3.
|
| 621 |
"step": 120
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 61.0,
|
| 625 |
-
"eval_accuracy": 0.
|
| 626 |
-
"eval_loss": 0.
|
| 627 |
-
"eval_runtime": 0.
|
| 628 |
-
"eval_samples_per_second":
|
| 629 |
-
"eval_steps_per_second": 3.
|
| 630 |
"step": 122
|
| 631 |
},
|
| 632 |
{
|
| 633 |
"epoch": 62.0,
|
| 634 |
-
"eval_accuracy": 0.
|
| 635 |
-
"eval_loss": 0.
|
| 636 |
-
"eval_runtime": 0.
|
| 637 |
-
"eval_samples_per_second":
|
| 638 |
-
"eval_steps_per_second": 2.
|
| 639 |
"step": 124
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 63.0,
|
| 643 |
-
"eval_accuracy": 0.
|
| 644 |
-
"eval_loss": 0.
|
| 645 |
-
"eval_runtime": 0.
|
| 646 |
-
"eval_samples_per_second": 110.
|
| 647 |
-
"eval_steps_per_second": 3.
|
| 648 |
"step": 126
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 64.0,
|
| 652 |
-
"eval_accuracy": 0.
|
| 653 |
-
"eval_loss": 0.
|
| 654 |
-
"eval_runtime": 0.
|
| 655 |
-
"eval_samples_per_second":
|
| 656 |
-
"eval_steps_per_second": 3.
|
| 657 |
"step": 128
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 65.0,
|
| 661 |
"learning_rate": 8.4375e-05,
|
| 662 |
-
"loss": 0.
|
| 663 |
"step": 130
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 65.0,
|
| 667 |
-
"eval_accuracy": 0.
|
| 668 |
-
"eval_loss": 0.
|
| 669 |
-
"eval_runtime": 0.
|
| 670 |
-
"eval_samples_per_second":
|
| 671 |
-
"eval_steps_per_second": 2.
|
| 672 |
"step": 130
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 66.0,
|
| 676 |
-
"eval_accuracy": 0.
|
| 677 |
-
"eval_loss": 0.
|
| 678 |
-
"eval_runtime": 0.
|
| 679 |
-
"eval_samples_per_second": 109.
|
| 680 |
-
"eval_steps_per_second": 3.
|
| 681 |
"step": 132
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 67.0,
|
| 685 |
-
"eval_accuracy": 0.
|
| 686 |
-
"eval_loss": 0.
|
| 687 |
-
"eval_runtime": 0.
|
| 688 |
-
"eval_samples_per_second":
|
| 689 |
-
"eval_steps_per_second":
|
| 690 |
"step": 134
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 68.0,
|
| 694 |
-
"eval_accuracy": 0.
|
| 695 |
-
"eval_loss": 0.
|
| 696 |
-
"eval_runtime": 0.
|
| 697 |
-
"eval_samples_per_second": 85.
|
| 698 |
-
"eval_steps_per_second": 2.
|
| 699 |
"step": 136
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 69.0,
|
| 703 |
-
"eval_accuracy": 0.
|
| 704 |
-
"eval_loss": 0.
|
| 705 |
-
"eval_runtime": 0.
|
| 706 |
-
"eval_samples_per_second":
|
| 707 |
-
"eval_steps_per_second": 3.
|
| 708 |
"step": 138
|
| 709 |
},
|
| 710 |
{
|
| 711 |
"epoch": 70.0,
|
| 712 |
"learning_rate": 8.125000000000001e-05,
|
| 713 |
-
"loss": 0.
|
| 714 |
"step": 140
|
| 715 |
},
|
| 716 |
{
|
| 717 |
"epoch": 70.0,
|
| 718 |
-
"eval_accuracy": 0.
|
| 719 |
-
"eval_loss": 0.
|
| 720 |
-
"eval_runtime": 0.
|
| 721 |
-
"eval_samples_per_second":
|
| 722 |
-
"eval_steps_per_second": 3.
|
| 723 |
"step": 140
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 71.0,
|
| 727 |
-
"eval_accuracy": 0.
|
| 728 |
-
"eval_loss": 0.
|
| 729 |
-
"eval_runtime": 0.
|
| 730 |
-
"eval_samples_per_second":
|
| 731 |
-
"eval_steps_per_second": 2.
|
| 732 |
"step": 142
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 72.0,
|
| 736 |
-
"eval_accuracy": 0.
|
| 737 |
-
"eval_loss": 0.
|
| 738 |
-
"eval_runtime": 0.
|
| 739 |
-
"eval_samples_per_second":
|
| 740 |
-
"eval_steps_per_second": 3.
|
| 741 |
"step": 144
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 73.0,
|
| 745 |
-
"eval_accuracy": 0.
|
| 746 |
-
"eval_loss": 0.
|
| 747 |
-
"eval_runtime": 0.
|
| 748 |
-
"eval_samples_per_second":
|
| 749 |
-
"eval_steps_per_second": 3.
|
| 750 |
"step": 146
|
| 751 |
},
|
| 752 |
{
|
| 753 |
"epoch": 74.0,
|
| 754 |
-
"eval_accuracy": 0.
|
| 755 |
-
"eval_loss": 0.
|
| 756 |
-
"eval_runtime": 0.
|
| 757 |
-
"eval_samples_per_second":
|
| 758 |
-
"eval_steps_per_second": 2.
|
| 759 |
"step": 148
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 75.0,
|
| 763 |
"learning_rate": 7.8125e-05,
|
| 764 |
-
"loss": 0.
|
| 765 |
"step": 150
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 75.0,
|
| 769 |
-
"eval_accuracy": 0.
|
| 770 |
-
"eval_loss": 0.
|
| 771 |
-
"eval_runtime": 0.
|
| 772 |
-
"eval_samples_per_second": 111.
|
| 773 |
-
"eval_steps_per_second": 3.
|
| 774 |
"step": 150
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 76.0,
|
| 778 |
-
"eval_accuracy": 0.
|
| 779 |
-
"eval_loss": 0.
|
| 780 |
-
"eval_runtime": 0.
|
| 781 |
-
"eval_samples_per_second":
|
| 782 |
-
"eval_steps_per_second": 3.
|
| 783 |
"step": 152
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 77.0,
|
| 787 |
-
"eval_accuracy": 0.
|
| 788 |
-
"eval_loss": 0.
|
| 789 |
-
"eval_runtime": 0.
|
| 790 |
-
"eval_samples_per_second": 87.
|
| 791 |
-
"eval_steps_per_second": 2.
|
| 792 |
"step": 154
|
| 793 |
},
|
| 794 |
{
|
| 795 |
"epoch": 78.0,
|
| 796 |
-
"eval_accuracy": 0.
|
| 797 |
-
"eval_loss": 0.
|
| 798 |
-
"eval_runtime": 0.
|
| 799 |
-
"eval_samples_per_second":
|
| 800 |
-
"eval_steps_per_second": 3.
|
| 801 |
"step": 156
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 79.0,
|
| 805 |
-
"eval_accuracy": 0.
|
| 806 |
-
"eval_loss": 0.
|
| 807 |
-
"eval_runtime": 0.
|
| 808 |
-
"eval_samples_per_second":
|
| 809 |
-
"eval_steps_per_second": 3.
|
| 810 |
"step": 158
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 80.0,
|
| 814 |
"learning_rate": 7.500000000000001e-05,
|
| 815 |
-
"loss": 0.
|
| 816 |
"step": 160
|
| 817 |
},
|
| 818 |
{
|
| 819 |
"epoch": 80.0,
|
| 820 |
-
"eval_accuracy": 0.
|
| 821 |
-
"eval_loss": 0.
|
| 822 |
-
"eval_runtime": 0.
|
| 823 |
-
"eval_samples_per_second":
|
| 824 |
-
"eval_steps_per_second": 2.
|
| 825 |
"step": 160
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 81.0,
|
| 829 |
-
"eval_accuracy": 0.
|
| 830 |
-
"eval_loss": 0.
|
| 831 |
-
"eval_runtime": 0.
|
| 832 |
-
"eval_samples_per_second":
|
| 833 |
-
"eval_steps_per_second": 3.
|
| 834 |
"step": 162
|
| 835 |
},
|
| 836 |
{
|
| 837 |
"epoch": 82.0,
|
| 838 |
-
"eval_accuracy": 0.
|
| 839 |
-
"eval_loss": 0.
|
| 840 |
-
"eval_runtime": 0.
|
| 841 |
-
"eval_samples_per_second":
|
| 842 |
-
"eval_steps_per_second": 3.
|
| 843 |
"step": 164
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 83.0,
|
| 847 |
-
"eval_accuracy": 0.
|
| 848 |
-
"eval_loss": 0.
|
| 849 |
-
"eval_runtime": 0.
|
| 850 |
-
"eval_samples_per_second":
|
| 851 |
-
"eval_steps_per_second": 2.
|
| 852 |
"step": 166
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 84.0,
|
| 856 |
-
"eval_accuracy": 0.
|
| 857 |
-
"eval_loss": 0.
|
| 858 |
-
"eval_runtime": 0.
|
| 859 |
-
"eval_samples_per_second":
|
| 860 |
-
"eval_steps_per_second": 3.
|
| 861 |
"step": 168
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 85.0,
|
| 865 |
"learning_rate": 7.1875e-05,
|
| 866 |
-
"loss": 0.
|
| 867 |
"step": 170
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 85.0,
|
| 871 |
-
"eval_accuracy": 0.
|
| 872 |
-
"eval_loss": 0.
|
| 873 |
-
"eval_runtime": 0.
|
| 874 |
-
"eval_samples_per_second":
|
| 875 |
-
"eval_steps_per_second": 3.
|
| 876 |
"step": 170
|
| 877 |
},
|
| 878 |
{
|
| 879 |
"epoch": 86.0,
|
| 880 |
-
"eval_accuracy": 0.
|
| 881 |
-
"eval_loss": 0.
|
| 882 |
-
"eval_runtime": 0.
|
| 883 |
-
"eval_samples_per_second":
|
| 884 |
-
"eval_steps_per_second": 2.
|
| 885 |
"step": 172
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 87.0,
|
| 889 |
-
"eval_accuracy": 0.
|
| 890 |
-
"eval_loss": 0.
|
| 891 |
-
"eval_runtime": 0.
|
| 892 |
-
"eval_samples_per_second":
|
| 893 |
-
"eval_steps_per_second": 3.
|
| 894 |
"step": 174
|
| 895 |
},
|
| 896 |
{
|
| 897 |
"epoch": 88.0,
|
| 898 |
-
"eval_accuracy": 0.
|
| 899 |
-
"eval_loss": 0.
|
| 900 |
-
"eval_runtime": 0.
|
| 901 |
-
"eval_samples_per_second":
|
| 902 |
-
"eval_steps_per_second": 3.
|
| 903 |
"step": 176
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 89.0,
|
| 907 |
-
"eval_accuracy": 0.
|
| 908 |
-
"eval_loss": 0.
|
| 909 |
-
"eval_runtime": 0.
|
| 910 |
-
"eval_samples_per_second":
|
| 911 |
-
"eval_steps_per_second": 2.
|
| 912 |
"step": 178
|
| 913 |
},
|
| 914 |
{
|
| 915 |
"epoch": 90.0,
|
| 916 |
"learning_rate": 6.875e-05,
|
| 917 |
-
"loss": 0.
|
| 918 |
"step": 180
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 90.0,
|
| 922 |
-
"eval_accuracy": 0.
|
| 923 |
-
"eval_loss": 0.
|
| 924 |
-
"eval_runtime": 0.
|
| 925 |
-
"eval_samples_per_second": 110.
|
| 926 |
-
"eval_steps_per_second": 3.
|
| 927 |
"step": 180
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 91.0,
|
| 931 |
-
"eval_accuracy": 0.
|
| 932 |
-
"eval_loss": 0.
|
| 933 |
-
"eval_runtime": 0.
|
| 934 |
-
"eval_samples_per_second":
|
| 935 |
-
"eval_steps_per_second": 3.
|
| 936 |
"step": 182
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"epoch": 92.0,
|
| 940 |
-
"eval_accuracy": 0.
|
| 941 |
-
"eval_loss": 0.
|
| 942 |
-
"eval_runtime": 0.
|
| 943 |
-
"eval_samples_per_second":
|
| 944 |
-
"eval_steps_per_second":
|
| 945 |
"step": 184
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 93.0,
|
| 949 |
-
"eval_accuracy": 0.
|
| 950 |
-
"eval_loss": 0.
|
| 951 |
-
"eval_runtime": 0.
|
| 952 |
-
"eval_samples_per_second":
|
| 953 |
-
"eval_steps_per_second": 3.
|
| 954 |
"step": 186
|
| 955 |
},
|
| 956 |
{
|
| 957 |
"epoch": 94.0,
|
| 958 |
-
"eval_accuracy": 0.
|
| 959 |
-
"eval_loss": 0.
|
| 960 |
-
"eval_runtime": 0.
|
| 961 |
-
"eval_samples_per_second":
|
| 962 |
-
"eval_steps_per_second": 3.
|
| 963 |
"step": 188
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 95.0,
|
| 967 |
"learning_rate": 6.562500000000001e-05,
|
| 968 |
-
"loss": 0.
|
| 969 |
"step": 190
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 95.0,
|
| 973 |
-
"eval_accuracy": 0.
|
| 974 |
-
"eval_loss": 0.
|
| 975 |
-
"eval_runtime": 0.
|
| 976 |
-
"eval_samples_per_second":
|
| 977 |
-
"eval_steps_per_second":
|
| 978 |
"step": 190
|
| 979 |
},
|
| 980 |
{
|
| 981 |
"epoch": 96.0,
|
| 982 |
-
"eval_accuracy": 0.
|
| 983 |
-
"eval_loss": 0.
|
| 984 |
-
"eval_runtime": 0.
|
| 985 |
-
"eval_samples_per_second":
|
| 986 |
-
"eval_steps_per_second":
|
| 987 |
"step": 192
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 97.0,
|
| 991 |
-
"eval_accuracy": 0.
|
| 992 |
-
"eval_loss": 0.
|
| 993 |
-
"eval_runtime": 0.
|
| 994 |
-
"eval_samples_per_second": 110.
|
| 995 |
-
"eval_steps_per_second": 3.
|
| 996 |
"step": 194
|
| 997 |
},
|
| 998 |
{
|
| 999 |
"epoch": 98.0,
|
| 1000 |
-
"eval_accuracy": 0.
|
| 1001 |
-
"eval_loss": 0.
|
| 1002 |
-
"eval_runtime": 0.
|
| 1003 |
-
"eval_samples_per_second":
|
| 1004 |
-
"eval_steps_per_second":
|
| 1005 |
"step": 196
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 99.0,
|
| 1009 |
-
"eval_accuracy": 0.
|
| 1010 |
-
"eval_loss": 0.
|
| 1011 |
-
"eval_runtime": 0.
|
| 1012 |
-
"eval_samples_per_second":
|
| 1013 |
-
"eval_steps_per_second":
|
| 1014 |
"step": 198
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
"epoch": 100.0,
|
| 1018 |
"learning_rate": 6.25e-05,
|
| 1019 |
-
"loss": 0.
|
| 1020 |
"step": 200
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
"epoch": 100.0,
|
| 1024 |
-
"eval_accuracy": 0.
|
| 1025 |
-
"eval_loss": 0.
|
| 1026 |
-
"eval_runtime": 0.
|
| 1027 |
-
"eval_samples_per_second":
|
| 1028 |
-
"eval_steps_per_second": 3.
|
| 1029 |
"step": 200
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 101.0,
|
| 1033 |
-
"eval_accuracy": 0.
|
| 1034 |
-
"eval_loss": 0.
|
| 1035 |
-
"eval_runtime": 0.
|
| 1036 |
-
"eval_samples_per_second":
|
| 1037 |
-
"eval_steps_per_second":
|
| 1038 |
"step": 202
|
| 1039 |
},
|
| 1040 |
{
|
| 1041 |
"epoch": 102.0,
|
| 1042 |
-
"eval_accuracy": 0.
|
| 1043 |
-
"eval_loss": 0.
|
| 1044 |
-
"eval_runtime": 0.
|
| 1045 |
-
"eval_samples_per_second":
|
| 1046 |
-
"eval_steps_per_second":
|
| 1047 |
"step": 204
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 103.0,
|
| 1051 |
-
"eval_accuracy": 0.
|
| 1052 |
-
"eval_loss": 0.
|
| 1053 |
-
"eval_runtime": 0.
|
| 1054 |
-
"eval_samples_per_second": 109.
|
| 1055 |
-
"eval_steps_per_second": 3.
|
| 1056 |
"step": 206
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 104.0,
|
| 1060 |
-
"eval_accuracy": 0.
|
| 1061 |
-
"eval_loss": 0.
|
| 1062 |
-
"eval_runtime": 0.
|
| 1063 |
-
"eval_samples_per_second":
|
| 1064 |
-
"eval_steps_per_second":
|
| 1065 |
"step": 208
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 105.0,
|
| 1069 |
"learning_rate": 5.9375e-05,
|
| 1070 |
-
"loss": 0.
|
| 1071 |
"step": 210
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 105.0,
|
| 1075 |
-
"eval_accuracy": 0.
|
| 1076 |
-
"eval_loss": 0.
|
| 1077 |
-
"eval_runtime": 0.
|
| 1078 |
-
"eval_samples_per_second":
|
| 1079 |
-
"eval_steps_per_second":
|
| 1080 |
"step": 210
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 106.0,
|
| 1084 |
-
"eval_accuracy": 0.
|
| 1085 |
-
"eval_loss": 0.
|
| 1086 |
-
"eval_runtime": 0.
|
| 1087 |
-
"eval_samples_per_second":
|
| 1088 |
-
"eval_steps_per_second": 3.
|
| 1089 |
"step": 212
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
"epoch": 107.0,
|
| 1093 |
-
"eval_accuracy": 0.
|
| 1094 |
-
"eval_loss": 0.
|
| 1095 |
-
"eval_runtime": 0.
|
| 1096 |
-
"eval_samples_per_second":
|
| 1097 |
-
"eval_steps_per_second":
|
| 1098 |
"step": 214
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
"epoch": 108.0,
|
| 1102 |
-
"eval_accuracy": 0.
|
| 1103 |
-
"eval_loss": 0.
|
| 1104 |
-
"eval_runtime": 0.
|
| 1105 |
-
"eval_samples_per_second":
|
| 1106 |
-
"eval_steps_per_second":
|
| 1107 |
"step": 216
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
"epoch": 109.0,
|
| 1111 |
-
"eval_accuracy": 0.
|
| 1112 |
-
"eval_loss": 0.
|
| 1113 |
-
"eval_runtime": 0.
|
| 1114 |
-
"eval_samples_per_second":
|
| 1115 |
-
"eval_steps_per_second": 3.
|
| 1116 |
"step": 218
|
| 1117 |
},
|
| 1118 |
{
|
| 1119 |
"epoch": 110.0,
|
| 1120 |
"learning_rate": 5.6250000000000005e-05,
|
| 1121 |
-
"loss": 0.
|
| 1122 |
"step": 220
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 110.0,
|
| 1126 |
-
"eval_accuracy": 0.
|
| 1127 |
-
"eval_loss": 0.
|
| 1128 |
-
"eval_runtime": 0.
|
| 1129 |
-
"eval_samples_per_second":
|
| 1130 |
-
"eval_steps_per_second":
|
| 1131 |
"step": 220
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 111.0,
|
| 1135 |
-
"eval_accuracy": 0.
|
| 1136 |
-
"eval_loss": 0.
|
| 1137 |
-
"eval_runtime": 0.
|
| 1138 |
-
"eval_samples_per_second":
|
| 1139 |
-
"eval_steps_per_second":
|
| 1140 |
"step": 222
|
| 1141 |
},
|
| 1142 |
{
|
| 1143 |
"epoch": 112.0,
|
| 1144 |
-
"eval_accuracy": 0.
|
| 1145 |
-
"eval_loss": 0.
|
| 1146 |
-
"eval_runtime": 0.
|
| 1147 |
-
"eval_samples_per_second":
|
| 1148 |
-
"eval_steps_per_second": 3.
|
| 1149 |
"step": 224
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"epoch": 113.0,
|
| 1153 |
-
"eval_accuracy": 0.
|
| 1154 |
-
"eval_loss": 0.
|
| 1155 |
-
"eval_runtime": 0.
|
| 1156 |
-
"eval_samples_per_second":
|
| 1157 |
-
"eval_steps_per_second": 2.
|
| 1158 |
"step": 226
|
| 1159 |
},
|
| 1160 |
{
|
| 1161 |
"epoch": 114.0,
|
| 1162 |
-
"eval_accuracy": 0.
|
| 1163 |
-
"eval_loss": 0.
|
| 1164 |
-
"eval_runtime": 0.
|
| 1165 |
-
"eval_samples_per_second":
|
| 1166 |
-
"eval_steps_per_second":
|
| 1167 |
"step": 228
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 115.0,
|
| 1171 |
"learning_rate": 5.3125000000000004e-05,
|
| 1172 |
-
"loss": 0.
|
| 1173 |
"step": 230
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 115.0,
|
| 1177 |
-
"eval_accuracy": 0.
|
| 1178 |
-
"eval_loss": 0.
|
| 1179 |
-
"eval_runtime": 0.
|
| 1180 |
-
"eval_samples_per_second": 109.
|
| 1181 |
-
"eval_steps_per_second": 3.
|
| 1182 |
"step": 230
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
"epoch": 116.0,
|
| 1186 |
-
"eval_accuracy": 0.
|
| 1187 |
-
"eval_loss": 0.
|
| 1188 |
-
"eval_runtime": 0.
|
| 1189 |
-
"eval_samples_per_second":
|
| 1190 |
-
"eval_steps_per_second":
|
| 1191 |
"step": 232
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
"epoch": 117.0,
|
| 1195 |
-
"eval_accuracy": 0.
|
| 1196 |
-
"eval_loss": 0.
|
| 1197 |
-
"eval_runtime": 0.
|
| 1198 |
-
"eval_samples_per_second":
|
| 1199 |
-
"eval_steps_per_second":
|
| 1200 |
"step": 234
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 118.0,
|
| 1204 |
-
"eval_accuracy": 0.
|
| 1205 |
-
"eval_loss": 0.
|
| 1206 |
-
"eval_runtime": 0.
|
| 1207 |
-
"eval_samples_per_second":
|
| 1208 |
-
"eval_steps_per_second": 3.
|
| 1209 |
"step": 236
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
"epoch": 119.0,
|
| 1213 |
-
"eval_accuracy": 0.
|
| 1214 |
-
"eval_loss": 0.
|
| 1215 |
-
"eval_runtime": 0.
|
| 1216 |
-
"eval_samples_per_second":
|
| 1217 |
-
"eval_steps_per_second":
|
| 1218 |
"step": 238
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 120.0,
|
| 1222 |
"learning_rate": 5e-05,
|
| 1223 |
-
"loss": 0.
|
| 1224 |
"step": 240
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 120.0,
|
| 1228 |
-
"eval_accuracy": 0.
|
| 1229 |
-
"eval_loss": 0.
|
| 1230 |
-
"eval_runtime": 0.
|
| 1231 |
-
"eval_samples_per_second":
|
| 1232 |
-
"eval_steps_per_second":
|
| 1233 |
"step": 240
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
"epoch": 121.0,
|
| 1237 |
-
"eval_accuracy": 0.
|
| 1238 |
-
"eval_loss": 0.
|
| 1239 |
-
"eval_runtime": 0.
|
| 1240 |
-
"eval_samples_per_second":
|
| 1241 |
-
"eval_steps_per_second": 3.
|
| 1242 |
"step": 242
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
"epoch": 122.0,
|
| 1246 |
-
"eval_accuracy": 0.
|
| 1247 |
-
"eval_loss": 0.
|
| 1248 |
-
"eval_runtime": 0.
|
| 1249 |
-
"eval_samples_per_second":
|
| 1250 |
-
"eval_steps_per_second":
|
| 1251 |
"step": 244
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
"epoch": 123.0,
|
| 1255 |
-
"eval_accuracy": 0.
|
| 1256 |
-
"eval_loss": 0.
|
| 1257 |
-
"eval_runtime": 0.
|
| 1258 |
-
"eval_samples_per_second":
|
| 1259 |
-
"eval_steps_per_second":
|
| 1260 |
"step": 246
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 124.0,
|
| 1264 |
-
"eval_accuracy": 0.
|
| 1265 |
-
"eval_loss": 0.
|
| 1266 |
-
"eval_runtime": 0.
|
| 1267 |
-
"eval_samples_per_second":
|
| 1268 |
-
"eval_steps_per_second": 3.
|
| 1269 |
"step": 248
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 125.0,
|
| 1273 |
"learning_rate": 4.6875e-05,
|
| 1274 |
-
"loss": 0.
|
| 1275 |
"step": 250
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
"epoch": 125.0,
|
| 1279 |
-
"eval_accuracy": 0.
|
| 1280 |
-
"eval_loss": 0.
|
| 1281 |
-
"eval_runtime": 0.
|
| 1282 |
-
"eval_samples_per_second":
|
| 1283 |
-
"eval_steps_per_second":
|
| 1284 |
"step": 250
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
"epoch": 126.0,
|
| 1288 |
-
"eval_accuracy": 0.
|
| 1289 |
-
"eval_loss": 0.
|
| 1290 |
-
"eval_runtime": 0.
|
| 1291 |
-
"eval_samples_per_second":
|
| 1292 |
-
"eval_steps_per_second":
|
| 1293 |
"step": 252
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
"epoch": 127.0,
|
| 1297 |
-
"eval_accuracy": 0.
|
| 1298 |
-
"eval_loss": 0.
|
| 1299 |
-
"eval_runtime": 0.
|
| 1300 |
-
"eval_samples_per_second":
|
| 1301 |
-
"eval_steps_per_second": 3.
|
| 1302 |
"step": 254
|
| 1303 |
},
|
| 1304 |
{
|
| 1305 |
"epoch": 128.0,
|
| 1306 |
-
"eval_accuracy": 0.
|
| 1307 |
-
"eval_loss": 0.
|
| 1308 |
-
"eval_runtime": 0.
|
| 1309 |
-
"eval_samples_per_second":
|
| 1310 |
-
"eval_steps_per_second":
|
| 1311 |
"step": 256
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 129.0,
|
| 1315 |
-
"eval_accuracy": 0.
|
| 1316 |
-
"eval_loss": 0.
|
| 1317 |
-
"eval_runtime": 0.
|
| 1318 |
-
"eval_samples_per_second":
|
| 1319 |
-
"eval_steps_per_second": 2.
|
| 1320 |
"step": 258
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
"epoch": 130.0,
|
| 1324 |
"learning_rate": 4.375e-05,
|
| 1325 |
-
"loss": 0.
|
| 1326 |
"step": 260
|
| 1327 |
},
|
| 1328 |
{
|
| 1329 |
"epoch": 130.0,
|
| 1330 |
-
"eval_accuracy": 0.
|
| 1331 |
-
"eval_loss": 0.
|
| 1332 |
-
"eval_runtime": 0.
|
| 1333 |
-
"eval_samples_per_second":
|
| 1334 |
-
"eval_steps_per_second": 3.
|
| 1335 |
"step": 260
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
"epoch": 131.0,
|
| 1339 |
-
"eval_accuracy": 0.
|
| 1340 |
-
"eval_loss": 0.
|
| 1341 |
-
"eval_runtime": 0.
|
| 1342 |
-
"eval_samples_per_second": 110.
|
| 1343 |
-
"eval_steps_per_second": 3.
|
| 1344 |
"step": 262
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 132.0,
|
| 1348 |
-
"eval_accuracy": 0.
|
| 1349 |
-
"eval_loss": 0.
|
| 1350 |
-
"eval_runtime": 0.
|
| 1351 |
-
"eval_samples_per_second":
|
| 1352 |
-
"eval_steps_per_second": 2.
|
| 1353 |
"step": 264
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 133.0,
|
| 1357 |
-
"eval_accuracy": 0.
|
| 1358 |
-
"eval_loss": 0.
|
| 1359 |
-
"eval_runtime": 0.
|
| 1360 |
-
"eval_samples_per_second":
|
| 1361 |
-
"eval_steps_per_second": 3.
|
| 1362 |
"step": 266
|
| 1363 |
},
|
| 1364 |
{
|
| 1365 |
"epoch": 134.0,
|
| 1366 |
-
"eval_accuracy": 0.
|
| 1367 |
-
"eval_loss": 0.
|
| 1368 |
-
"eval_runtime": 0.
|
| 1369 |
-
"eval_samples_per_second":
|
| 1370 |
-
"eval_steps_per_second": 3.
|
| 1371 |
"step": 268
|
| 1372 |
},
|
| 1373 |
{
|
| 1374 |
"epoch": 135.0,
|
| 1375 |
"learning_rate": 4.0625000000000005e-05,
|
| 1376 |
-
"loss": 0.
|
| 1377 |
"step": 270
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 135.0,
|
| 1381 |
-
"eval_accuracy": 0.
|
| 1382 |
-
"eval_loss": 0.
|
| 1383 |
-
"eval_runtime": 0.
|
| 1384 |
-
"eval_samples_per_second":
|
| 1385 |
-
"eval_steps_per_second": 2.
|
| 1386 |
"step": 270
|
| 1387 |
},
|
| 1388 |
{
|
| 1389 |
"epoch": 136.0,
|
| 1390 |
-
"eval_accuracy": 0.
|
| 1391 |
-
"eval_loss": 0.
|
| 1392 |
-
"eval_runtime": 0.
|
| 1393 |
-
"eval_samples_per_second":
|
| 1394 |
-
"eval_steps_per_second": 3.
|
| 1395 |
"step": 272
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 137.0,
|
| 1399 |
-
"eval_accuracy": 0.
|
| 1400 |
-
"eval_loss": 0.
|
| 1401 |
-
"eval_runtime": 0.
|
| 1402 |
-
"eval_samples_per_second":
|
| 1403 |
-
"eval_steps_per_second": 3.
|
| 1404 |
"step": 274
|
| 1405 |
},
|
| 1406 |
{
|
| 1407 |
"epoch": 138.0,
|
| 1408 |
-
"eval_accuracy": 0.
|
| 1409 |
-
"eval_loss": 0.
|
| 1410 |
-
"eval_runtime": 0.
|
| 1411 |
-
"eval_samples_per_second":
|
| 1412 |
-
"eval_steps_per_second": 2.
|
| 1413 |
"step": 276
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 139.0,
|
| 1417 |
-
"eval_accuracy": 0.
|
| 1418 |
-
"eval_loss": 0.
|
| 1419 |
-
"eval_runtime": 0.
|
| 1420 |
-
"eval_samples_per_second":
|
| 1421 |
-
"eval_steps_per_second": 3.
|
| 1422 |
"step": 278
|
| 1423 |
},
|
| 1424 |
{
|
| 1425 |
"epoch": 140.0,
|
| 1426 |
"learning_rate": 3.7500000000000003e-05,
|
| 1427 |
-
"loss": 0.
|
| 1428 |
"step": 280
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
"epoch": 140.0,
|
| 1432 |
-
"eval_accuracy": 0.
|
| 1433 |
-
"eval_loss": 0.
|
| 1434 |
-
"eval_runtime": 0.
|
| 1435 |
-
"eval_samples_per_second": 109.
|
| 1436 |
-
"eval_steps_per_second": 3.
|
| 1437 |
"step": 280
|
| 1438 |
},
|
| 1439 |
{
|
| 1440 |
"epoch": 141.0,
|
| 1441 |
-
"eval_accuracy": 0.
|
| 1442 |
-
"eval_loss": 0.
|
| 1443 |
-
"eval_runtime": 0.
|
| 1444 |
-
"eval_samples_per_second":
|
| 1445 |
-
"eval_steps_per_second": 2.
|
| 1446 |
"step": 282
|
| 1447 |
},
|
| 1448 |
{
|
| 1449 |
"epoch": 142.0,
|
| 1450 |
-
"eval_accuracy": 0.
|
| 1451 |
-
"eval_loss": 0.
|
| 1452 |
"eval_runtime": 0.6382,
|
| 1453 |
-
"eval_samples_per_second": 109.
|
| 1454 |
"eval_steps_per_second": 3.134,
|
| 1455 |
"step": 284
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
"epoch": 143.0,
|
| 1459 |
-
"eval_accuracy": 0.
|
| 1460 |
-
"eval_loss": 0.
|
| 1461 |
-
"eval_runtime": 0.
|
| 1462 |
-
"eval_samples_per_second":
|
| 1463 |
-
"eval_steps_per_second": 3.
|
| 1464 |
"step": 286
|
| 1465 |
},
|
| 1466 |
{
|
| 1467 |
"epoch": 144.0,
|
| 1468 |
-
"eval_accuracy": 0.
|
| 1469 |
-
"eval_loss": 0.
|
| 1470 |
-
"eval_runtime": 0.
|
| 1471 |
-
"eval_samples_per_second":
|
| 1472 |
-
"eval_steps_per_second": 2.
|
| 1473 |
"step": 288
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
"epoch": 145.0,
|
| 1477 |
"learning_rate": 3.4375e-05,
|
| 1478 |
-
"loss": 0.
|
| 1479 |
"step": 290
|
| 1480 |
},
|
| 1481 |
{
|
| 1482 |
"epoch": 145.0,
|
| 1483 |
-
"eval_accuracy": 0.
|
| 1484 |
-
"eval_loss": 0.
|
| 1485 |
-
"eval_runtime": 0.
|
| 1486 |
-
"eval_samples_per_second":
|
| 1487 |
-
"eval_steps_per_second": 3.
|
| 1488 |
"step": 290
|
| 1489 |
},
|
| 1490 |
{
|
| 1491 |
"epoch": 146.0,
|
| 1492 |
-
"eval_accuracy": 0.
|
| 1493 |
-
"eval_loss": 0.
|
| 1494 |
-
"eval_runtime": 0.
|
| 1495 |
-
"eval_samples_per_second":
|
| 1496 |
-
"eval_steps_per_second": 3.
|
| 1497 |
"step": 292
|
| 1498 |
},
|
| 1499 |
{
|
| 1500 |
"epoch": 147.0,
|
| 1501 |
-
"eval_accuracy": 0.
|
| 1502 |
-
"eval_loss": 0.
|
| 1503 |
-
"eval_runtime": 0.
|
| 1504 |
-
"eval_samples_per_second":
|
| 1505 |
-
"eval_steps_per_second": 2.
|
| 1506 |
"step": 294
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 148.0,
|
| 1510 |
-
"eval_accuracy": 0.
|
| 1511 |
-
"eval_loss": 0.
|
| 1512 |
-
"eval_runtime": 0.
|
| 1513 |
-
"eval_samples_per_second":
|
| 1514 |
-
"eval_steps_per_second": 3.
|
| 1515 |
"step": 296
|
| 1516 |
},
|
| 1517 |
{
|
| 1518 |
"epoch": 149.0,
|
| 1519 |
-
"eval_accuracy": 0.
|
| 1520 |
-
"eval_loss": 0.
|
| 1521 |
-
"eval_runtime": 0.
|
| 1522 |
-
"eval_samples_per_second":
|
| 1523 |
-
"eval_steps_per_second": 3.
|
| 1524 |
"step": 298
|
| 1525 |
},
|
| 1526 |
{
|
| 1527 |
"epoch": 150.0,
|
| 1528 |
"learning_rate": 3.125e-05,
|
| 1529 |
-
"loss": 0.
|
| 1530 |
"step": 300
|
| 1531 |
},
|
| 1532 |
{
|
| 1533 |
"epoch": 150.0,
|
| 1534 |
-
"eval_accuracy": 0.
|
| 1535 |
-
"eval_loss": 0.
|
| 1536 |
-
"eval_runtime": 0.
|
| 1537 |
-
"eval_samples_per_second":
|
| 1538 |
-
"eval_steps_per_second": 2.
|
| 1539 |
"step": 300
|
| 1540 |
},
|
| 1541 |
{
|
| 1542 |
"epoch": 151.0,
|
| 1543 |
-
"eval_accuracy": 0.
|
| 1544 |
-
"eval_loss": 0.
|
| 1545 |
-
"eval_runtime": 0.
|
| 1546 |
-
"eval_samples_per_second":
|
| 1547 |
-
"eval_steps_per_second": 3.
|
| 1548 |
"step": 302
|
| 1549 |
},
|
| 1550 |
{
|
| 1551 |
"epoch": 152.0,
|
| 1552 |
-
"eval_accuracy": 0.
|
| 1553 |
-
"eval_loss": 0.
|
| 1554 |
-
"eval_runtime": 0.
|
| 1555 |
-
"eval_samples_per_second":
|
| 1556 |
-
"eval_steps_per_second": 3.
|
| 1557 |
"step": 304
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
"epoch": 153.0,
|
| 1561 |
-
"eval_accuracy": 0.
|
| 1562 |
-
"eval_loss": 0.
|
| 1563 |
-
"eval_runtime": 0.
|
| 1564 |
-
"eval_samples_per_second":
|
| 1565 |
-
"eval_steps_per_second": 2.
|
| 1566 |
"step": 306
|
| 1567 |
},
|
| 1568 |
{
|
| 1569 |
"epoch": 154.0,
|
| 1570 |
-
"eval_accuracy": 0.
|
| 1571 |
-
"eval_loss": 0.
|
| 1572 |
-
"eval_runtime": 0.
|
| 1573 |
-
"eval_samples_per_second":
|
| 1574 |
-
"eval_steps_per_second": 3.
|
| 1575 |
"step": 308
|
| 1576 |
},
|
| 1577 |
{
|
| 1578 |
"epoch": 155.0,
|
| 1579 |
"learning_rate": 2.8125000000000003e-05,
|
| 1580 |
-
"loss": 0.
|
| 1581 |
"step": 310
|
| 1582 |
},
|
| 1583 |
{
|
| 1584 |
"epoch": 155.0,
|
| 1585 |
"eval_accuracy": 0.8142857142857143,
|
| 1586 |
-
"eval_loss": 0.
|
| 1587 |
-
"eval_runtime": 0.
|
| 1588 |
-
"eval_samples_per_second":
|
| 1589 |
-
"eval_steps_per_second": 3.
|
| 1590 |
"step": 310
|
| 1591 |
},
|
| 1592 |
{
|
| 1593 |
"epoch": 156.0,
|
| 1594 |
"eval_accuracy": 0.8142857142857143,
|
| 1595 |
-
"eval_loss": 0.
|
| 1596 |
-
"eval_runtime": 0.
|
| 1597 |
-
"eval_samples_per_second":
|
| 1598 |
-
"eval_steps_per_second":
|
| 1599 |
"step": 312
|
| 1600 |
},
|
| 1601 |
{
|
| 1602 |
"epoch": 157.0,
|
| 1603 |
"eval_accuracy": 0.8142857142857143,
|
| 1604 |
-
"eval_loss": 0.
|
| 1605 |
-
"eval_runtime": 0.
|
| 1606 |
-
"eval_samples_per_second":
|
| 1607 |
-
"eval_steps_per_second":
|
| 1608 |
"step": 314
|
| 1609 |
},
|
| 1610 |
{
|
| 1611 |
"epoch": 158.0,
|
| 1612 |
"eval_accuracy": 0.8142857142857143,
|
| 1613 |
-
"eval_loss": 0.
|
| 1614 |
-
"eval_runtime": 0.
|
| 1615 |
-
"eval_samples_per_second":
|
| 1616 |
-
"eval_steps_per_second": 3.
|
| 1617 |
"step": 316
|
| 1618 |
},
|
| 1619 |
{
|
| 1620 |
"epoch": 159.0,
|
| 1621 |
"eval_accuracy": 0.8142857142857143,
|
| 1622 |
-
"eval_loss": 0.
|
| 1623 |
-
"eval_runtime": 0.
|
| 1624 |
-
"eval_samples_per_second":
|
| 1625 |
-
"eval_steps_per_second":
|
| 1626 |
"step": 318
|
| 1627 |
},
|
| 1628 |
{
|
| 1629 |
"epoch": 160.0,
|
| 1630 |
"learning_rate": 2.5e-05,
|
| 1631 |
-
"loss": 0.
|
| 1632 |
"step": 320
|
| 1633 |
},
|
| 1634 |
{
|
| 1635 |
"epoch": 160.0,
|
| 1636 |
-
"eval_accuracy": 0.
|
| 1637 |
-
"eval_loss": 0.
|
| 1638 |
-
"eval_runtime": 0.
|
| 1639 |
-
"eval_samples_per_second":
|
| 1640 |
-
"eval_steps_per_second":
|
| 1641 |
"step": 320
|
| 1642 |
},
|
| 1643 |
{
|
| 1644 |
"epoch": 161.0,
|
| 1645 |
"eval_accuracy": 0.8142857142857143,
|
| 1646 |
-
"eval_loss": 0.
|
| 1647 |
-
"eval_runtime": 0.
|
| 1648 |
-
"eval_samples_per_second":
|
| 1649 |
-
"eval_steps_per_second": 3.
|
| 1650 |
"step": 322
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
"epoch": 162.0,
|
| 1654 |
"eval_accuracy": 0.8142857142857143,
|
| 1655 |
-
"eval_loss": 0.
|
| 1656 |
-
"eval_runtime": 0.
|
| 1657 |
-
"eval_samples_per_second":
|
| 1658 |
-
"eval_steps_per_second":
|
| 1659 |
"step": 324
|
| 1660 |
},
|
| 1661 |
{
|
| 1662 |
"epoch": 163.0,
|
| 1663 |
"eval_accuracy": 0.8142857142857143,
|
| 1664 |
-
"eval_loss": 0.
|
| 1665 |
-
"eval_runtime": 0.
|
| 1666 |
-
"eval_samples_per_second":
|
| 1667 |
-
"eval_steps_per_second":
|
| 1668 |
"step": 326
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
"epoch": 164.0,
|
| 1672 |
"eval_accuracy": 0.8142857142857143,
|
| 1673 |
-
"eval_loss": 0.
|
| 1674 |
-
"eval_runtime": 0.
|
| 1675 |
-
"eval_samples_per_second":
|
| 1676 |
-
"eval_steps_per_second": 3.
|
| 1677 |
"step": 328
|
| 1678 |
},
|
| 1679 |
{
|
| 1680 |
"epoch": 165.0,
|
| 1681 |
"learning_rate": 2.1875e-05,
|
| 1682 |
-
"loss": 0.
|
| 1683 |
"step": 330
|
| 1684 |
},
|
| 1685 |
{
|
| 1686 |
"epoch": 165.0,
|
| 1687 |
-
"eval_accuracy": 0.
|
| 1688 |
-
"eval_loss": 0.
|
| 1689 |
-
"eval_runtime": 0.
|
| 1690 |
-
"eval_samples_per_second":
|
| 1691 |
-
"eval_steps_per_second":
|
| 1692 |
"step": 330
|
| 1693 |
},
|
| 1694 |
{
|
| 1695 |
"epoch": 166.0,
|
| 1696 |
-
"eval_accuracy": 0.
|
| 1697 |
-
"eval_loss": 0.
|
| 1698 |
-
"eval_runtime": 0.
|
| 1699 |
-
"eval_samples_per_second":
|
| 1700 |
-
"eval_steps_per_second":
|
| 1701 |
"step": 332
|
| 1702 |
},
|
| 1703 |
{
|
| 1704 |
"epoch": 167.0,
|
| 1705 |
-
"eval_accuracy": 0.
|
| 1706 |
-
"eval_loss": 0.
|
| 1707 |
-
"eval_runtime": 0.
|
| 1708 |
-
"eval_samples_per_second":
|
| 1709 |
-
"eval_steps_per_second":
|
| 1710 |
"step": 334
|
| 1711 |
},
|
| 1712 |
{
|
| 1713 |
"epoch": 168.0,
|
| 1714 |
-
"eval_accuracy": 0.
|
| 1715 |
-
"eval_loss": 0.
|
| 1716 |
-
"eval_runtime": 0.
|
| 1717 |
-
"eval_samples_per_second":
|
| 1718 |
-
"eval_steps_per_second":
|
| 1719 |
"step": 336
|
| 1720 |
},
|
| 1721 |
{
|
| 1722 |
"epoch": 169.0,
|
| 1723 |
-
"eval_accuracy": 0.
|
| 1724 |
-
"eval_loss": 0.
|
| 1725 |
-
"eval_runtime": 0.
|
| 1726 |
-
"eval_samples_per_second":
|
| 1727 |
-
"eval_steps_per_second":
|
| 1728 |
"step": 338
|
| 1729 |
},
|
| 1730 |
{
|
| 1731 |
"epoch": 170.0,
|
| 1732 |
"learning_rate": 1.8750000000000002e-05,
|
| 1733 |
-
"loss": 0.
|
| 1734 |
"step": 340
|
| 1735 |
},
|
| 1736 |
{
|
| 1737 |
"epoch": 170.0,
|
| 1738 |
-
"eval_accuracy": 0.
|
| 1739 |
-
"eval_loss": 0.
|
| 1740 |
-
"eval_runtime": 0.
|
| 1741 |
-
"eval_samples_per_second":
|
| 1742 |
-
"eval_steps_per_second": 3.
|
| 1743 |
"step": 340
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
"epoch": 171.0,
|
| 1747 |
-
"eval_accuracy": 0.
|
| 1748 |
-
"eval_loss": 0.
|
| 1749 |
-
"eval_runtime": 0.
|
| 1750 |
-
"eval_samples_per_second":
|
| 1751 |
-
"eval_steps_per_second":
|
| 1752 |
"step": 342
|
| 1753 |
},
|
| 1754 |
{
|
| 1755 |
"epoch": 172.0,
|
| 1756 |
-
"eval_accuracy": 0.
|
| 1757 |
-
"eval_loss": 0.
|
| 1758 |
-
"eval_runtime": 0.
|
| 1759 |
-
"eval_samples_per_second":
|
| 1760 |
-
"eval_steps_per_second":
|
| 1761 |
"step": 344
|
| 1762 |
},
|
| 1763 |
{
|
| 1764 |
"epoch": 173.0,
|
| 1765 |
-
"eval_accuracy": 0.
|
| 1766 |
-
"eval_loss": 0.
|
| 1767 |
-
"eval_runtime": 0.
|
| 1768 |
-
"eval_samples_per_second":
|
| 1769 |
-
"eval_steps_per_second":
|
| 1770 |
"step": 346
|
| 1771 |
},
|
| 1772 |
{
|
| 1773 |
"epoch": 174.0,
|
| 1774 |
-
"eval_accuracy": 0.
|
| 1775 |
-
"eval_loss": 0.
|
| 1776 |
-
"eval_runtime": 0.
|
| 1777 |
-
"eval_samples_per_second":
|
| 1778 |
-
"eval_steps_per_second":
|
| 1779 |
"step": 348
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
"epoch": 175.0,
|
| 1783 |
"learning_rate": 1.5625e-05,
|
| 1784 |
-
"loss": 0.
|
| 1785 |
"step": 350
|
| 1786 |
},
|
| 1787 |
{
|
| 1788 |
"epoch": 175.0,
|
| 1789 |
-
"eval_accuracy": 0.
|
| 1790 |
-
"eval_loss": 0.
|
| 1791 |
-
"eval_runtime": 0.
|
| 1792 |
-
"eval_samples_per_second":
|
| 1793 |
-
"eval_steps_per_second":
|
| 1794 |
"step": 350
|
| 1795 |
},
|
| 1796 |
{
|
| 1797 |
"epoch": 176.0,
|
| 1798 |
-
"eval_accuracy": 0.
|
| 1799 |
-
"eval_loss": 0.
|
| 1800 |
-
"eval_runtime": 0.
|
| 1801 |
-
"eval_samples_per_second":
|
| 1802 |
-
"eval_steps_per_second":
|
| 1803 |
"step": 352
|
| 1804 |
},
|
| 1805 |
{
|
| 1806 |
"epoch": 177.0,
|
| 1807 |
-
"eval_accuracy": 0.
|
| 1808 |
-
"eval_loss": 0.
|
| 1809 |
-
"eval_runtime": 0.
|
| 1810 |
-
"eval_samples_per_second":
|
| 1811 |
-
"eval_steps_per_second":
|
| 1812 |
"step": 354
|
| 1813 |
},
|
| 1814 |
{
|
| 1815 |
"epoch": 178.0,
|
| 1816 |
-
"eval_accuracy": 0.
|
| 1817 |
-
"eval_loss": 0.
|
| 1818 |
-
"eval_runtime": 0.
|
| 1819 |
-
"eval_samples_per_second":
|
| 1820 |
-
"eval_steps_per_second":
|
| 1821 |
"step": 356
|
| 1822 |
},
|
| 1823 |
{
|
| 1824 |
"epoch": 179.0,
|
| 1825 |
-
"eval_accuracy": 0.
|
| 1826 |
-
"eval_loss": 0.
|
| 1827 |
-
"eval_runtime": 0.
|
| 1828 |
-
"eval_samples_per_second":
|
| 1829 |
-
"eval_steps_per_second": 3.
|
| 1830 |
"step": 358
|
| 1831 |
},
|
| 1832 |
{
|
| 1833 |
"epoch": 180.0,
|
| 1834 |
"learning_rate": 1.25e-05,
|
| 1835 |
-
"loss": 0.
|
| 1836 |
"step": 360
|
| 1837 |
},
|
| 1838 |
{
|
| 1839 |
"epoch": 180.0,
|
| 1840 |
-
"eval_accuracy": 0.
|
| 1841 |
-
"eval_loss": 0.
|
| 1842 |
-
"eval_runtime": 0.
|
| 1843 |
-
"eval_samples_per_second":
|
| 1844 |
-
"eval_steps_per_second":
|
| 1845 |
"step": 360
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
"epoch": 181.0,
|
| 1849 |
-
"eval_accuracy": 0.
|
| 1850 |
-
"eval_loss": 0.
|
| 1851 |
-
"eval_runtime": 0.
|
| 1852 |
-
"eval_samples_per_second":
|
| 1853 |
-
"eval_steps_per_second":
|
| 1854 |
"step": 362
|
| 1855 |
},
|
| 1856 |
{
|
| 1857 |
"epoch": 182.0,
|
| 1858 |
-
"eval_accuracy": 0.
|
| 1859 |
-
"eval_loss": 0.
|
| 1860 |
-
"eval_runtime": 0.
|
| 1861 |
-
"eval_samples_per_second":
|
| 1862 |
-
"eval_steps_per_second": 3.
|
| 1863 |
"step": 364
|
| 1864 |
},
|
| 1865 |
{
|
| 1866 |
"epoch": 183.0,
|
| 1867 |
-
"eval_accuracy": 0.
|
| 1868 |
-
"eval_loss": 0.
|
| 1869 |
-
"eval_runtime": 0.
|
| 1870 |
-
"eval_samples_per_second":
|
| 1871 |
-
"eval_steps_per_second":
|
| 1872 |
"step": 366
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
"epoch": 184.0,
|
| 1876 |
-
"eval_accuracy": 0.
|
| 1877 |
-
"eval_loss": 0.
|
| 1878 |
-
"eval_runtime": 0.
|
| 1879 |
-
"eval_samples_per_second":
|
| 1880 |
-
"eval_steps_per_second":
|
| 1881 |
"step": 368
|
| 1882 |
},
|
| 1883 |
{
|
| 1884 |
"epoch": 185.0,
|
| 1885 |
"learning_rate": 9.375000000000001e-06,
|
| 1886 |
-
"loss": 0.
|
| 1887 |
"step": 370
|
| 1888 |
},
|
| 1889 |
{
|
| 1890 |
"epoch": 185.0,
|
| 1891 |
-
"eval_accuracy": 0.
|
| 1892 |
-
"eval_loss": 0.
|
| 1893 |
-
"eval_runtime": 0.
|
| 1894 |
-
"eval_samples_per_second":
|
| 1895 |
-
"eval_steps_per_second": 3.
|
| 1896 |
"step": 370
|
| 1897 |
},
|
| 1898 |
{
|
| 1899 |
"epoch": 186.0,
|
| 1900 |
-
"eval_accuracy": 0.
|
| 1901 |
-
"eval_loss": 0.
|
| 1902 |
-
"eval_runtime": 0.
|
| 1903 |
-
"eval_samples_per_second":
|
| 1904 |
-
"eval_steps_per_second":
|
| 1905 |
"step": 372
|
| 1906 |
},
|
| 1907 |
{
|
| 1908 |
"epoch": 187.0,
|
| 1909 |
-
"eval_accuracy": 0.
|
| 1910 |
-
"eval_loss": 0.
|
| 1911 |
-
"eval_runtime": 0.
|
| 1912 |
-
"eval_samples_per_second":
|
| 1913 |
-
"eval_steps_per_second":
|
| 1914 |
"step": 374
|
| 1915 |
},
|
| 1916 |
{
|
| 1917 |
"epoch": 188.0,
|
| 1918 |
-
"eval_accuracy": 0.
|
| 1919 |
-
"eval_loss": 0.
|
| 1920 |
-
"eval_runtime": 0.
|
| 1921 |
-
"eval_samples_per_second":
|
| 1922 |
-
"eval_steps_per_second": 3.
|
| 1923 |
"step": 376
|
| 1924 |
},
|
| 1925 |
{
|
| 1926 |
"epoch": 189.0,
|
| 1927 |
-
"eval_accuracy": 0.
|
| 1928 |
-
"eval_loss": 0.
|
| 1929 |
-
"eval_runtime": 0.
|
| 1930 |
-
"eval_samples_per_second":
|
| 1931 |
-
"eval_steps_per_second": 2.
|
| 1932 |
"step": 378
|
| 1933 |
},
|
| 1934 |
{
|
| 1935 |
"epoch": 190.0,
|
| 1936 |
"learning_rate": 6.25e-06,
|
| 1937 |
-
"loss": 0.
|
| 1938 |
"step": 380
|
| 1939 |
},
|
| 1940 |
{
|
| 1941 |
"epoch": 190.0,
|
| 1942 |
-
"eval_accuracy": 0.
|
| 1943 |
-
"eval_loss": 0.
|
| 1944 |
-
"eval_runtime": 0.
|
| 1945 |
-
"eval_samples_per_second":
|
| 1946 |
-
"eval_steps_per_second":
|
| 1947 |
"step": 380
|
| 1948 |
},
|
| 1949 |
{
|
| 1950 |
"epoch": 191.0,
|
| 1951 |
-
"eval_accuracy": 0.
|
| 1952 |
-
"eval_loss": 0.
|
| 1953 |
-
"eval_runtime": 0.
|
| 1954 |
-
"eval_samples_per_second":
|
| 1955 |
-
"eval_steps_per_second": 3.
|
| 1956 |
"step": 382
|
| 1957 |
},
|
| 1958 |
{
|
| 1959 |
"epoch": 192.0,
|
| 1960 |
-
"eval_accuracy": 0.
|
| 1961 |
-
"eval_loss": 0.
|
| 1962 |
-
"eval_runtime": 0.
|
| 1963 |
-
"eval_samples_per_second":
|
| 1964 |
-
"eval_steps_per_second":
|
| 1965 |
"step": 384
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 193.0,
|
| 1969 |
-
"eval_accuracy": 0.
|
| 1970 |
-
"eval_loss": 0.
|
| 1971 |
-
"eval_runtime": 0.
|
| 1972 |
-
"eval_samples_per_second":
|
| 1973 |
-
"eval_steps_per_second":
|
| 1974 |
"step": 386
|
| 1975 |
},
|
| 1976 |
{
|
| 1977 |
"epoch": 194.0,
|
| 1978 |
-
"eval_accuracy": 0.
|
| 1979 |
-
"eval_loss": 0.
|
| 1980 |
-
"eval_runtime": 0.
|
| 1981 |
-
"eval_samples_per_second":
|
| 1982 |
-
"eval_steps_per_second": 3.
|
| 1983 |
"step": 388
|
| 1984 |
},
|
| 1985 |
{
|
| 1986 |
"epoch": 195.0,
|
| 1987 |
"learning_rate": 3.125e-06,
|
| 1988 |
-
"loss": 0.
|
| 1989 |
"step": 390
|
| 1990 |
},
|
| 1991 |
{
|
| 1992 |
"epoch": 195.0,
|
| 1993 |
-
"eval_accuracy": 0.
|
| 1994 |
-
"eval_loss": 0.
|
| 1995 |
-
"eval_runtime": 0.
|
| 1996 |
-
"eval_samples_per_second":
|
| 1997 |
-
"eval_steps_per_second":
|
| 1998 |
"step": 390
|
| 1999 |
},
|
| 2000 |
{
|
| 2001 |
"epoch": 196.0,
|
| 2002 |
-
"eval_accuracy": 0.
|
| 2003 |
-
"eval_loss": 0.
|
| 2004 |
-
"eval_runtime": 0.
|
| 2005 |
-
"eval_samples_per_second":
|
| 2006 |
-
"eval_steps_per_second":
|
| 2007 |
"step": 392
|
| 2008 |
},
|
| 2009 |
{
|
| 2010 |
"epoch": 197.0,
|
| 2011 |
-
"eval_accuracy": 0.
|
| 2012 |
-
"eval_loss": 0.
|
| 2013 |
-
"eval_runtime": 0.
|
| 2014 |
-
"eval_samples_per_second":
|
| 2015 |
-
"eval_steps_per_second": 3.
|
| 2016 |
"step": 394
|
| 2017 |
},
|
| 2018 |
{
|
| 2019 |
"epoch": 198.0,
|
| 2020 |
-
"eval_accuracy": 0.
|
| 2021 |
-
"eval_loss": 0.
|
| 2022 |
-
"eval_runtime": 0.
|
| 2023 |
-
"eval_samples_per_second":
|
| 2024 |
-
"eval_steps_per_second":
|
| 2025 |
"step": 396
|
| 2026 |
},
|
| 2027 |
{
|
| 2028 |
"epoch": 199.0,
|
| 2029 |
-
"eval_accuracy": 0.
|
| 2030 |
-
"eval_loss": 0.
|
| 2031 |
-
"eval_runtime": 0.
|
| 2032 |
-
"eval_samples_per_second":
|
| 2033 |
-
"eval_steps_per_second":
|
| 2034 |
"step": 398
|
| 2035 |
},
|
| 2036 |
{
|
| 2037 |
"epoch": 200.0,
|
| 2038 |
"learning_rate": 0.0,
|
| 2039 |
-
"loss": 0.
|
| 2040 |
"step": 400
|
| 2041 |
},
|
| 2042 |
{
|
| 2043 |
"epoch": 200.0,
|
| 2044 |
-
"eval_accuracy": 0.
|
| 2045 |
-
"eval_loss": 0.
|
| 2046 |
-
"eval_runtime": 0.
|
| 2047 |
-
"eval_samples_per_second":
|
| 2048 |
-
"eval_steps_per_second": 3.
|
| 2049 |
"step": 400
|
| 2050 |
},
|
| 2051 |
{
|
| 2052 |
"epoch": 200.0,
|
| 2053 |
"step": 400,
|
| 2054 |
"total_flos": 2.23710151698432e+18,
|
| 2055 |
-
"train_loss": 0.
|
| 2056 |
-
"train_runtime":
|
| 2057 |
-
"train_samples_per_second":
|
| 2058 |
-
"train_steps_per_second": 0.
|
| 2059 |
}
|
| 2060 |
],
|
| 2061 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8285714285714286,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-ADC-3cls-0922/checkpoint-40",
|
| 4 |
"epoch": 200.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 400,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.8142857142857143,
|
| 14 |
+
"eval_loss": 0.6875032186508179,
|
| 15 |
+
"eval_runtime": 0.8381,
|
| 16 |
+
"eval_samples_per_second": 83.526,
|
| 17 |
+
"eval_steps_per_second": 2.386,
|
| 18 |
"step": 2
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.8142857142857143,
|
| 23 |
+
"eval_loss": 0.6874324083328247,
|
| 24 |
+
"eval_runtime": 0.6285,
|
| 25 |
+
"eval_samples_per_second": 111.384,
|
| 26 |
+
"eval_steps_per_second": 3.182,
|
| 27 |
"step": 4
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.8142857142857143,
|
| 32 |
+
"eval_loss": 0.6873045563697815,
|
| 33 |
+
"eval_runtime": 0.6533,
|
| 34 |
+
"eval_samples_per_second": 107.153,
|
| 35 |
+
"eval_steps_per_second": 3.062,
|
| 36 |
"step": 6
|
| 37 |
},
|
| 38 |
{
|
| 39 |
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.8142857142857143,
|
| 41 |
+
"eval_loss": 0.687107264995575,
|
| 42 |
+
"eval_runtime": 0.8041,
|
| 43 |
+
"eval_samples_per_second": 87.057,
|
| 44 |
+
"eval_steps_per_second": 2.487,
|
| 45 |
"step": 8
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 5.0,
|
| 49 |
"learning_rate": 1.25e-05,
|
| 50 |
+
"loss": 0.7555,
|
| 51 |
"step": 10
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 5.0,
|
| 55 |
+
"eval_accuracy": 0.8142857142857143,
|
| 56 |
+
"eval_loss": 0.6868652701377869,
|
| 57 |
+
"eval_runtime": 0.6585,
|
| 58 |
+
"eval_samples_per_second": 106.309,
|
| 59 |
+
"eval_steps_per_second": 3.037,
|
| 60 |
"step": 10
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 6.0,
|
| 64 |
+
"eval_accuracy": 0.8142857142857143,
|
| 65 |
+
"eval_loss": 0.686565101146698,
|
| 66 |
+
"eval_runtime": 0.6372,
|
| 67 |
+
"eval_samples_per_second": 109.86,
|
| 68 |
+
"eval_steps_per_second": 3.139,
|
| 69 |
"step": 12
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 7.0,
|
| 73 |
+
"eval_accuracy": 0.8142857142857143,
|
| 74 |
+
"eval_loss": 0.6861968636512756,
|
| 75 |
+
"eval_runtime": 0.8401,
|
| 76 |
+
"eval_samples_per_second": 83.326,
|
| 77 |
+
"eval_steps_per_second": 2.381,
|
| 78 |
"step": 14
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 8.0,
|
| 82 |
+
"eval_accuracy": 0.8142857142857143,
|
| 83 |
+
"eval_loss": 0.685771644115448,
|
| 84 |
+
"eval_runtime": 0.6402,
|
| 85 |
+
"eval_samples_per_second": 109.344,
|
| 86 |
+
"eval_steps_per_second": 3.124,
|
| 87 |
"step": 16
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 9.0,
|
| 91 |
+
"eval_accuracy": 0.8142857142857143,
|
| 92 |
+
"eval_loss": 0.6853042244911194,
|
| 93 |
+
"eval_runtime": 0.638,
|
| 94 |
+
"eval_samples_per_second": 109.711,
|
| 95 |
+
"eval_steps_per_second": 3.135,
|
| 96 |
"step": 18
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 10.0,
|
| 100 |
"learning_rate": 2.5e-05,
|
| 101 |
+
"loss": 0.7576,
|
| 102 |
"step": 20
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 10.0,
|
| 106 |
+
"eval_accuracy": 0.8142857142857143,
|
| 107 |
+
"eval_loss": 0.6847913861274719,
|
| 108 |
+
"eval_runtime": 0.8284,
|
| 109 |
+
"eval_samples_per_second": 84.496,
|
| 110 |
+
"eval_steps_per_second": 2.414,
|
| 111 |
"step": 20
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 11.0,
|
| 115 |
+
"eval_accuracy": 0.8142857142857143,
|
| 116 |
+
"eval_loss": 0.6842377185821533,
|
| 117 |
+
"eval_runtime": 0.6408,
|
| 118 |
+
"eval_samples_per_second": 109.237,
|
| 119 |
+
"eval_steps_per_second": 3.121,
|
| 120 |
"step": 22
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 12.0,
|
| 124 |
+
"eval_accuracy": 0.8142857142857143,
|
| 125 |
+
"eval_loss": 0.6836268901824951,
|
| 126 |
+
"eval_runtime": 0.6496,
|
| 127 |
+
"eval_samples_per_second": 107.755,
|
| 128 |
+
"eval_steps_per_second": 3.079,
|
| 129 |
"step": 24
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 13.0,
|
| 133 |
+
"eval_accuracy": 0.8142857142857143,
|
| 134 |
+
"eval_loss": 0.6829591393470764,
|
| 135 |
+
"eval_runtime": 0.8145,
|
| 136 |
+
"eval_samples_per_second": 85.938,
|
| 137 |
+
"eval_steps_per_second": 2.455,
|
| 138 |
"step": 26
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 14.0,
|
| 142 |
+
"eval_accuracy": 0.8142857142857143,
|
| 143 |
+
"eval_loss": 0.6822755336761475,
|
| 144 |
+
"eval_runtime": 0.6641,
|
| 145 |
+
"eval_samples_per_second": 105.412,
|
| 146 |
+
"eval_steps_per_second": 3.012,
|
| 147 |
"step": 28
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 15.0,
|
| 151 |
"learning_rate": 3.7500000000000003e-05,
|
| 152 |
+
"loss": 0.769,
|
| 153 |
"step": 30
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 15.0,
|
| 157 |
+
"eval_accuracy": 0.8,
|
| 158 |
+
"eval_loss": 0.6815804839134216,
|
| 159 |
+
"eval_runtime": 0.6278,
|
| 160 |
+
"eval_samples_per_second": 111.502,
|
| 161 |
+
"eval_steps_per_second": 3.186,
|
| 162 |
"step": 30
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 16.0,
|
| 166 |
+
"eval_accuracy": 0.8,
|
| 167 |
+
"eval_loss": 0.6808401346206665,
|
| 168 |
+
"eval_runtime": 0.8247,
|
| 169 |
+
"eval_samples_per_second": 84.88,
|
| 170 |
+
"eval_steps_per_second": 2.425,
|
| 171 |
"step": 32
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 17.0,
|
| 175 |
+
"eval_accuracy": 0.8142857142857143,
|
| 176 |
+
"eval_loss": 0.6800239086151123,
|
| 177 |
+
"eval_runtime": 0.6376,
|
| 178 |
+
"eval_samples_per_second": 109.794,
|
| 179 |
+
"eval_steps_per_second": 3.137,
|
| 180 |
"step": 34
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 18.0,
|
| 184 |
+
"eval_accuracy": 0.8142857142857143,
|
| 185 |
+
"eval_loss": 0.679133951663971,
|
| 186 |
+
"eval_runtime": 0.6356,
|
| 187 |
+
"eval_samples_per_second": 110.128,
|
| 188 |
+
"eval_steps_per_second": 3.147,
|
| 189 |
"step": 36
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 19.0,
|
| 193 |
+
"eval_accuracy": 0.8142857142857143,
|
| 194 |
+
"eval_loss": 0.6781331896781921,
|
| 195 |
+
"eval_runtime": 0.8136,
|
| 196 |
+
"eval_samples_per_second": 86.039,
|
| 197 |
+
"eval_steps_per_second": 2.458,
|
| 198 |
"step": 38
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 20.0,
|
| 202 |
"learning_rate": 5e-05,
|
| 203 |
+
"loss": 0.7564,
|
| 204 |
"step": 40
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 20.0,
|
| 208 |
+
"eval_accuracy": 0.8285714285714286,
|
| 209 |
+
"eval_loss": 0.6770716309547424,
|
| 210 |
+
"eval_runtime": 0.627,
|
| 211 |
+
"eval_samples_per_second": 111.643,
|
| 212 |
+
"eval_steps_per_second": 3.19,
|
| 213 |
"step": 40
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 21.0,
|
| 217 |
+
"eval_accuracy": 0.8142857142857143,
|
| 218 |
+
"eval_loss": 0.6759592294692993,
|
| 219 |
+
"eval_runtime": 0.6244,
|
| 220 |
+
"eval_samples_per_second": 112.113,
|
| 221 |
+
"eval_steps_per_second": 3.203,
|
| 222 |
"step": 42
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 22.0,
|
| 226 |
+
"eval_accuracy": 0.8142857142857143,
|
| 227 |
+
"eval_loss": 0.674824059009552,
|
| 228 |
+
"eval_runtime": 0.72,
|
| 229 |
+
"eval_samples_per_second": 97.226,
|
| 230 |
+
"eval_steps_per_second": 2.778,
|
| 231 |
"step": 44
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 23.0,
|
| 235 |
+
"eval_accuracy": 0.8,
|
| 236 |
+
"eval_loss": 0.6736522912979126,
|
| 237 |
+
"eval_runtime": 0.6356,
|
| 238 |
+
"eval_samples_per_second": 110.125,
|
| 239 |
+
"eval_steps_per_second": 3.146,
|
| 240 |
"step": 46
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 24.0,
|
| 244 |
+
"eval_accuracy": 0.8,
|
| 245 |
+
"eval_loss": 0.6724562644958496,
|
| 246 |
+
"eval_runtime": 0.6465,
|
| 247 |
+
"eval_samples_per_second": 108.268,
|
| 248 |
+
"eval_steps_per_second": 3.093,
|
| 249 |
"step": 48
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 25.0,
|
| 253 |
"learning_rate": 6.25e-05,
|
| 254 |
+
"loss": 0.7508,
|
| 255 |
"step": 50
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 25.0,
|
| 259 |
+
"eval_accuracy": 0.8142857142857143,
|
| 260 |
+
"eval_loss": 0.6713314056396484,
|
| 261 |
+
"eval_runtime": 0.6458,
|
| 262 |
+
"eval_samples_per_second": 108.385,
|
| 263 |
+
"eval_steps_per_second": 3.097,
|
| 264 |
"step": 50
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 26.0,
|
| 268 |
+
"eval_accuracy": 0.8142857142857143,
|
| 269 |
+
"eval_loss": 0.6701393723487854,
|
| 270 |
+
"eval_runtime": 0.7532,
|
| 271 |
+
"eval_samples_per_second": 92.934,
|
| 272 |
+
"eval_steps_per_second": 2.655,
|
| 273 |
"step": 52
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 27.0,
|
| 277 |
+
"eval_accuracy": 0.8142857142857143,
|
| 278 |
+
"eval_loss": 0.6688514947891235,
|
| 279 |
+
"eval_runtime": 0.6275,
|
| 280 |
+
"eval_samples_per_second": 111.546,
|
| 281 |
+
"eval_steps_per_second": 3.187,
|
| 282 |
"step": 54
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 28.0,
|
| 286 |
+
"eval_accuracy": 0.8142857142857143,
|
| 287 |
+
"eval_loss": 0.6674489378929138,
|
| 288 |
+
"eval_runtime": 0.6455,
|
| 289 |
+
"eval_samples_per_second": 108.446,
|
| 290 |
+
"eval_steps_per_second": 3.098,
|
| 291 |
"step": 56
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 29.0,
|
| 295 |
+
"eval_accuracy": 0.8142857142857143,
|
| 296 |
+
"eval_loss": 0.6660061478614807,
|
| 297 |
+
"eval_runtime": 0.7926,
|
| 298 |
+
"eval_samples_per_second": 88.312,
|
| 299 |
+
"eval_steps_per_second": 2.523,
|
| 300 |
"step": 58
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 30.0,
|
| 304 |
"learning_rate": 7.500000000000001e-05,
|
| 305 |
+
"loss": 0.747,
|
| 306 |
"step": 60
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 30.0,
|
| 310 |
+
"eval_accuracy": 0.8142857142857143,
|
| 311 |
+
"eval_loss": 0.6645620465278625,
|
| 312 |
+
"eval_runtime": 0.6238,
|
| 313 |
+
"eval_samples_per_second": 112.214,
|
| 314 |
+
"eval_steps_per_second": 3.206,
|
| 315 |
"step": 60
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 31.0,
|
| 319 |
+
"eval_accuracy": 0.8142857142857143,
|
| 320 |
+
"eval_loss": 0.6631242632865906,
|
| 321 |
+
"eval_runtime": 0.651,
|
| 322 |
+
"eval_samples_per_second": 107.52,
|
| 323 |
+
"eval_steps_per_second": 3.072,
|
| 324 |
"step": 62
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 32.0,
|
| 328 |
+
"eval_accuracy": 0.8142857142857143,
|
| 329 |
+
"eval_loss": 0.6616196036338806,
|
| 330 |
+
"eval_runtime": 0.8036,
|
| 331 |
+
"eval_samples_per_second": 87.111,
|
| 332 |
+
"eval_steps_per_second": 2.489,
|
| 333 |
"step": 64
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 33.0,
|
| 337 |
+
"eval_accuracy": 0.8142857142857143,
|
| 338 |
+
"eval_loss": 0.6600926518440247,
|
| 339 |
+
"eval_runtime": 0.638,
|
| 340 |
+
"eval_samples_per_second": 109.722,
|
| 341 |
+
"eval_steps_per_second": 3.135,
|
| 342 |
"step": 66
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"epoch": 34.0,
|
| 346 |
+
"eval_accuracy": 0.8142857142857143,
|
| 347 |
+
"eval_loss": 0.6585766673088074,
|
| 348 |
+
"eval_runtime": 0.6365,
|
| 349 |
+
"eval_samples_per_second": 109.973,
|
| 350 |
+
"eval_steps_per_second": 3.142,
|
| 351 |
"step": 68
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 35.0,
|
| 355 |
"learning_rate": 8.75e-05,
|
| 356 |
+
"loss": 0.7343,
|
| 357 |
"step": 70
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 35.0,
|
| 361 |
+
"eval_accuracy": 0.8142857142857143,
|
| 362 |
+
"eval_loss": 0.6569960117340088,
|
| 363 |
+
"eval_runtime": 0.7913,
|
| 364 |
+
"eval_samples_per_second": 88.467,
|
| 365 |
+
"eval_steps_per_second": 2.528,
|
| 366 |
"step": 70
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 36.0,
|
| 370 |
+
"eval_accuracy": 0.8142857142857143,
|
| 371 |
+
"eval_loss": 0.6553293466567993,
|
| 372 |
+
"eval_runtime": 0.6317,
|
| 373 |
+
"eval_samples_per_second": 110.815,
|
| 374 |
+
"eval_steps_per_second": 3.166,
|
| 375 |
"step": 72
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 37.0,
|
| 379 |
+
"eval_accuracy": 0.8142857142857143,
|
| 380 |
+
"eval_loss": 0.6535871028900146,
|
| 381 |
+
"eval_runtime": 0.6261,
|
| 382 |
+
"eval_samples_per_second": 111.81,
|
| 383 |
+
"eval_steps_per_second": 3.195,
|
| 384 |
"step": 74
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 38.0,
|
| 388 |
+
"eval_accuracy": 0.8142857142857143,
|
| 389 |
+
"eval_loss": 0.6517333388328552,
|
| 390 |
+
"eval_runtime": 0.7801,
|
| 391 |
+
"eval_samples_per_second": 89.727,
|
| 392 |
+
"eval_steps_per_second": 2.564,
|
| 393 |
"step": 76
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 39.0,
|
| 397 |
+
"eval_accuracy": 0.8142857142857143,
|
| 398 |
+
"eval_loss": 0.6498710513114929,
|
| 399 |
+
"eval_runtime": 0.6688,
|
| 400 |
+
"eval_samples_per_second": 104.667,
|
| 401 |
+
"eval_steps_per_second": 2.99,
|
| 402 |
"step": 78
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 40.0,
|
| 406 |
"learning_rate": 0.0001,
|
| 407 |
+
"loss": 0.7532,
|
| 408 |
"step": 80
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 40.0,
|
| 412 |
+
"eval_accuracy": 0.8142857142857143,
|
| 413 |
+
"eval_loss": 0.6480462551116943,
|
| 414 |
+
"eval_runtime": 0.6422,
|
| 415 |
+
"eval_samples_per_second": 108.998,
|
| 416 |
+
"eval_steps_per_second": 3.114,
|
| 417 |
"step": 80
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 41.0,
|
| 421 |
+
"eval_accuracy": 0.8142857142857143,
|
| 422 |
+
"eval_loss": 0.6461040377616882,
|
| 423 |
+
"eval_runtime": 0.7878,
|
| 424 |
+
"eval_samples_per_second": 88.86,
|
| 425 |
+
"eval_steps_per_second": 2.539,
|
| 426 |
"step": 82
|
| 427 |
},
|
| 428 |
{
|
| 429 |
"epoch": 42.0,
|
| 430 |
+
"eval_accuracy": 0.8142857142857143,
|
| 431 |
+
"eval_loss": 0.6441839337348938,
|
| 432 |
+
"eval_runtime": 0.6221,
|
| 433 |
+
"eval_samples_per_second": 112.518,
|
| 434 |
+
"eval_steps_per_second": 3.215,
|
| 435 |
"step": 84
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 43.0,
|
| 439 |
+
"eval_accuracy": 0.8142857142857143,
|
| 440 |
+
"eval_loss": 0.6423068046569824,
|
| 441 |
+
"eval_runtime": 0.6404,
|
| 442 |
+
"eval_samples_per_second": 109.306,
|
| 443 |
+
"eval_steps_per_second": 3.123,
|
| 444 |
"step": 86
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 44.0,
|
| 448 |
+
"eval_accuracy": 0.8142857142857143,
|
| 449 |
+
"eval_loss": 0.6404834985733032,
|
| 450 |
+
"eval_runtime": 0.8194,
|
| 451 |
+
"eval_samples_per_second": 85.431,
|
| 452 |
+
"eval_steps_per_second": 2.441,
|
| 453 |
"step": 88
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 45.0,
|
| 457 |
"learning_rate": 9.687500000000001e-05,
|
| 458 |
+
"loss": 0.7239,
|
| 459 |
"step": 90
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 45.0,
|
| 463 |
+
"eval_accuracy": 0.8142857142857143,
|
| 464 |
+
"eval_loss": 0.638668417930603,
|
| 465 |
+
"eval_runtime": 0.6293,
|
| 466 |
+
"eval_samples_per_second": 111.227,
|
| 467 |
+
"eval_steps_per_second": 3.178,
|
| 468 |
"step": 90
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 46.0,
|
| 472 |
+
"eval_accuracy": 0.8142857142857143,
|
| 473 |
+
"eval_loss": 0.6368482112884521,
|
| 474 |
+
"eval_runtime": 0.6307,
|
| 475 |
+
"eval_samples_per_second": 110.981,
|
| 476 |
+
"eval_steps_per_second": 3.171,
|
| 477 |
"step": 92
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 47.0,
|
| 481 |
+
"eval_accuracy": 0.8142857142857143,
|
| 482 |
+
"eval_loss": 0.6351889967918396,
|
| 483 |
+
"eval_runtime": 0.8243,
|
| 484 |
+
"eval_samples_per_second": 84.921,
|
| 485 |
+
"eval_steps_per_second": 2.426,
|
| 486 |
"step": 94
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 48.0,
|
| 490 |
+
"eval_accuracy": 0.8142857142857143,
|
| 491 |
+
"eval_loss": 0.6336590051651001,
|
| 492 |
+
"eval_runtime": 0.6325,
|
| 493 |
+
"eval_samples_per_second": 110.664,
|
| 494 |
+
"eval_steps_per_second": 3.162,
|
| 495 |
"step": 96
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 49.0,
|
| 499 |
+
"eval_accuracy": 0.8285714285714286,
|
| 500 |
+
"eval_loss": 0.6321325302124023,
|
| 501 |
+
"eval_runtime": 0.6292,
|
| 502 |
+
"eval_samples_per_second": 111.258,
|
| 503 |
+
"eval_steps_per_second": 3.179,
|
| 504 |
"step": 98
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 50.0,
|
| 508 |
"learning_rate": 9.375e-05,
|
| 509 |
+
"loss": 0.7085,
|
| 510 |
"step": 100
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 50.0,
|
| 514 |
+
"eval_accuracy": 0.8285714285714286,
|
| 515 |
+
"eval_loss": 0.6307134628295898,
|
| 516 |
+
"eval_runtime": 0.8147,
|
| 517 |
+
"eval_samples_per_second": 85.924,
|
| 518 |
+
"eval_steps_per_second": 2.455,
|
| 519 |
"step": 100
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 51.0,
|
| 523 |
+
"eval_accuracy": 0.8285714285714286,
|
| 524 |
+
"eval_loss": 0.6293519139289856,
|
| 525 |
+
"eval_runtime": 0.6273,
|
| 526 |
+
"eval_samples_per_second": 111.588,
|
| 527 |
+
"eval_steps_per_second": 3.188,
|
| 528 |
"step": 102
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 52.0,
|
| 532 |
+
"eval_accuracy": 0.8285714285714286,
|
| 533 |
+
"eval_loss": 0.6278188228607178,
|
| 534 |
+
"eval_runtime": 0.6366,
|
| 535 |
+
"eval_samples_per_second": 109.96,
|
| 536 |
+
"eval_steps_per_second": 3.142,
|
| 537 |
"step": 104
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 53.0,
|
| 541 |
+
"eval_accuracy": 0.8285714285714286,
|
| 542 |
+
"eval_loss": 0.6263061165809631,
|
| 543 |
+
"eval_runtime": 0.8106,
|
| 544 |
+
"eval_samples_per_second": 86.353,
|
| 545 |
+
"eval_steps_per_second": 2.467,
|
| 546 |
"step": 106
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 54.0,
|
| 550 |
+
"eval_accuracy": 0.8142857142857143,
|
| 551 |
+
"eval_loss": 0.6247809529304504,
|
| 552 |
+
"eval_runtime": 0.637,
|
| 553 |
+
"eval_samples_per_second": 109.885,
|
| 554 |
+
"eval_steps_per_second": 3.14,
|
| 555 |
"step": 108
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 55.0,
|
| 559 |
"learning_rate": 9.062500000000001e-05,
|
| 560 |
+
"loss": 0.7203,
|
| 561 |
"step": 110
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 55.0,
|
| 565 |
+
"eval_accuracy": 0.8142857142857143,
|
| 566 |
+
"eval_loss": 0.6232935190200806,
|
| 567 |
+
"eval_runtime": 0.6312,
|
| 568 |
+
"eval_samples_per_second": 110.901,
|
| 569 |
+
"eval_steps_per_second": 3.169,
|
| 570 |
"step": 110
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 56.0,
|
| 574 |
+
"eval_accuracy": 0.8142857142857143,
|
| 575 |
+
"eval_loss": 0.6218679547309875,
|
| 576 |
+
"eval_runtime": 0.8253,
|
| 577 |
+
"eval_samples_per_second": 84.819,
|
| 578 |
+
"eval_steps_per_second": 2.423,
|
| 579 |
"step": 112
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 57.0,
|
| 583 |
+
"eval_accuracy": 0.8142857142857143,
|
| 584 |
+
"eval_loss": 0.6204643845558167,
|
| 585 |
+
"eval_runtime": 0.6393,
|
| 586 |
+
"eval_samples_per_second": 109.495,
|
| 587 |
+
"eval_steps_per_second": 3.128,
|
| 588 |
"step": 114
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 58.0,
|
| 592 |
+
"eval_accuracy": 0.8142857142857143,
|
| 593 |
+
"eval_loss": 0.6191075444221497,
|
| 594 |
+
"eval_runtime": 0.6278,
|
| 595 |
+
"eval_samples_per_second": 111.495,
|
| 596 |
+
"eval_steps_per_second": 3.186,
|
| 597 |
"step": 116
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 59.0,
|
| 601 |
+
"eval_accuracy": 0.8142857142857143,
|
| 602 |
+
"eval_loss": 0.6178752779960632,
|
| 603 |
+
"eval_runtime": 0.8233,
|
| 604 |
+
"eval_samples_per_second": 85.027,
|
| 605 |
+
"eval_steps_per_second": 2.429,
|
| 606 |
"step": 118
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 60.0,
|
| 610 |
"learning_rate": 8.75e-05,
|
| 611 |
+
"loss": 0.7136,
|
| 612 |
"step": 120
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 60.0,
|
| 616 |
+
"eval_accuracy": 0.8142857142857143,
|
| 617 |
+
"eval_loss": 0.6167242527008057,
|
| 618 |
+
"eval_runtime": 0.6489,
|
| 619 |
+
"eval_samples_per_second": 107.881,
|
| 620 |
+
"eval_steps_per_second": 3.082,
|
| 621 |
"step": 120
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 61.0,
|
| 625 |
+
"eval_accuracy": 0.8142857142857143,
|
| 626 |
+
"eval_loss": 0.6156985759735107,
|
| 627 |
+
"eval_runtime": 0.6472,
|
| 628 |
+
"eval_samples_per_second": 108.154,
|
| 629 |
+
"eval_steps_per_second": 3.09,
|
| 630 |
"step": 122
|
| 631 |
},
|
| 632 |
{
|
| 633 |
"epoch": 62.0,
|
| 634 |
+
"eval_accuracy": 0.8,
|
| 635 |
+
"eval_loss": 0.61481112241745,
|
| 636 |
+
"eval_runtime": 0.8228,
|
| 637 |
+
"eval_samples_per_second": 85.073,
|
| 638 |
+
"eval_steps_per_second": 2.431,
|
| 639 |
"step": 124
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 63.0,
|
| 643 |
+
"eval_accuracy": 0.8,
|
| 644 |
+
"eval_loss": 0.6138356328010559,
|
| 645 |
+
"eval_runtime": 0.6327,
|
| 646 |
+
"eval_samples_per_second": 110.64,
|
| 647 |
+
"eval_steps_per_second": 3.161,
|
| 648 |
"step": 126
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 64.0,
|
| 652 |
+
"eval_accuracy": 0.8,
|
| 653 |
+
"eval_loss": 0.6125301122665405,
|
| 654 |
+
"eval_runtime": 0.6379,
|
| 655 |
+
"eval_samples_per_second": 109.736,
|
| 656 |
+
"eval_steps_per_second": 3.135,
|
| 657 |
"step": 128
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 65.0,
|
| 661 |
"learning_rate": 8.4375e-05,
|
| 662 |
+
"loss": 0.7123,
|
| 663 |
"step": 130
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 65.0,
|
| 667 |
+
"eval_accuracy": 0.8,
|
| 668 |
+
"eval_loss": 0.6110576391220093,
|
| 669 |
+
"eval_runtime": 0.825,
|
| 670 |
+
"eval_samples_per_second": 84.849,
|
| 671 |
+
"eval_steps_per_second": 2.424,
|
| 672 |
"step": 130
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 66.0,
|
| 676 |
+
"eval_accuracy": 0.8142857142857143,
|
| 677 |
+
"eval_loss": 0.6096405982971191,
|
| 678 |
+
"eval_runtime": 0.6376,
|
| 679 |
+
"eval_samples_per_second": 109.782,
|
| 680 |
+
"eval_steps_per_second": 3.137,
|
| 681 |
"step": 132
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 67.0,
|
| 685 |
+
"eval_accuracy": 0.8142857142857143,
|
| 686 |
+
"eval_loss": 0.6083278656005859,
|
| 687 |
+
"eval_runtime": 0.8232,
|
| 688 |
+
"eval_samples_per_second": 85.037,
|
| 689 |
+
"eval_steps_per_second": 2.43,
|
| 690 |
"step": 134
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 68.0,
|
| 694 |
+
"eval_accuracy": 0.8142857142857143,
|
| 695 |
+
"eval_loss": 0.6069909930229187,
|
| 696 |
+
"eval_runtime": 0.8193,
|
| 697 |
+
"eval_samples_per_second": 85.437,
|
| 698 |
+
"eval_steps_per_second": 2.441,
|
| 699 |
"step": 136
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 69.0,
|
| 703 |
+
"eval_accuracy": 0.8142857142857143,
|
| 704 |
+
"eval_loss": 0.6057179570198059,
|
| 705 |
+
"eval_runtime": 0.6486,
|
| 706 |
+
"eval_samples_per_second": 107.925,
|
| 707 |
+
"eval_steps_per_second": 3.084,
|
| 708 |
"step": 138
|
| 709 |
},
|
| 710 |
{
|
| 711 |
"epoch": 70.0,
|
| 712 |
"learning_rate": 8.125000000000001e-05,
|
| 713 |
+
"loss": 0.7076,
|
| 714 |
"step": 140
|
| 715 |
},
|
| 716 |
{
|
| 717 |
"epoch": 70.0,
|
| 718 |
+
"eval_accuracy": 0.8142857142857143,
|
| 719 |
+
"eval_loss": 0.604619562625885,
|
| 720 |
+
"eval_runtime": 0.6358,
|
| 721 |
+
"eval_samples_per_second": 110.095,
|
| 722 |
+
"eval_steps_per_second": 3.146,
|
| 723 |
"step": 140
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 71.0,
|
| 727 |
+
"eval_accuracy": 0.8142857142857143,
|
| 728 |
+
"eval_loss": 0.6034784913063049,
|
| 729 |
+
"eval_runtime": 0.8201,
|
| 730 |
+
"eval_samples_per_second": 85.352,
|
| 731 |
+
"eval_steps_per_second": 2.439,
|
| 732 |
"step": 142
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 72.0,
|
| 736 |
+
"eval_accuracy": 0.8142857142857143,
|
| 737 |
+
"eval_loss": 0.6022736430168152,
|
| 738 |
+
"eval_runtime": 0.6311,
|
| 739 |
+
"eval_samples_per_second": 110.91,
|
| 740 |
+
"eval_steps_per_second": 3.169,
|
| 741 |
"step": 144
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 73.0,
|
| 745 |
+
"eval_accuracy": 0.8142857142857143,
|
| 746 |
+
"eval_loss": 0.6011058688163757,
|
| 747 |
+
"eval_runtime": 0.6566,
|
| 748 |
+
"eval_samples_per_second": 106.607,
|
| 749 |
+
"eval_steps_per_second": 3.046,
|
| 750 |
"step": 146
|
| 751 |
},
|
| 752 |
{
|
| 753 |
"epoch": 74.0,
|
| 754 |
+
"eval_accuracy": 0.8142857142857143,
|
| 755 |
+
"eval_loss": 0.5999324917793274,
|
| 756 |
+
"eval_runtime": 0.8174,
|
| 757 |
+
"eval_samples_per_second": 85.64,
|
| 758 |
+
"eval_steps_per_second": 2.447,
|
| 759 |
"step": 148
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 75.0,
|
| 763 |
"learning_rate": 7.8125e-05,
|
| 764 |
+
"loss": 0.6878,
|
| 765 |
"step": 150
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 75.0,
|
| 769 |
+
"eval_accuracy": 0.8142857142857143,
|
| 770 |
+
"eval_loss": 0.5987647175788879,
|
| 771 |
+
"eval_runtime": 0.6275,
|
| 772 |
+
"eval_samples_per_second": 111.562,
|
| 773 |
+
"eval_steps_per_second": 3.187,
|
| 774 |
"step": 150
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 76.0,
|
| 778 |
+
"eval_accuracy": 0.8142857142857143,
|
| 779 |
+
"eval_loss": 0.5975351333618164,
|
| 780 |
+
"eval_runtime": 0.6296,
|
| 781 |
+
"eval_samples_per_second": 111.178,
|
| 782 |
+
"eval_steps_per_second": 3.177,
|
| 783 |
"step": 152
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 77.0,
|
| 787 |
+
"eval_accuracy": 0.8142857142857143,
|
| 788 |
+
"eval_loss": 0.5963953137397766,
|
| 789 |
+
"eval_runtime": 0.8044,
|
| 790 |
+
"eval_samples_per_second": 87.018,
|
| 791 |
+
"eval_steps_per_second": 2.486,
|
| 792 |
"step": 154
|
| 793 |
},
|
| 794 |
{
|
| 795 |
"epoch": 78.0,
|
| 796 |
+
"eval_accuracy": 0.8142857142857143,
|
| 797 |
+
"eval_loss": 0.5952684879302979,
|
| 798 |
+
"eval_runtime": 0.6501,
|
| 799 |
+
"eval_samples_per_second": 107.669,
|
| 800 |
+
"eval_steps_per_second": 3.076,
|
| 801 |
"step": 156
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 79.0,
|
| 805 |
+
"eval_accuracy": 0.8142857142857143,
|
| 806 |
+
"eval_loss": 0.5942099094390869,
|
| 807 |
+
"eval_runtime": 0.6469,
|
| 808 |
+
"eval_samples_per_second": 108.203,
|
| 809 |
+
"eval_steps_per_second": 3.092,
|
| 810 |
"step": 158
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 80.0,
|
| 814 |
"learning_rate": 7.500000000000001e-05,
|
| 815 |
+
"loss": 0.6657,
|
| 816 |
"step": 160
|
| 817 |
},
|
| 818 |
{
|
| 819 |
"epoch": 80.0,
|
| 820 |
+
"eval_accuracy": 0.8142857142857143,
|
| 821 |
+
"eval_loss": 0.5932222008705139,
|
| 822 |
+
"eval_runtime": 0.8259,
|
| 823 |
+
"eval_samples_per_second": 84.754,
|
| 824 |
+
"eval_steps_per_second": 2.422,
|
| 825 |
"step": 160
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 81.0,
|
| 829 |
+
"eval_accuracy": 0.8142857142857143,
|
| 830 |
+
"eval_loss": 0.5923032760620117,
|
| 831 |
+
"eval_runtime": 0.6393,
|
| 832 |
+
"eval_samples_per_second": 109.49,
|
| 833 |
+
"eval_steps_per_second": 3.128,
|
| 834 |
"step": 162
|
| 835 |
},
|
| 836 |
{
|
| 837 |
"epoch": 82.0,
|
| 838 |
+
"eval_accuracy": 0.8142857142857143,
|
| 839 |
+
"eval_loss": 0.5914328098297119,
|
| 840 |
+
"eval_runtime": 0.6466,
|
| 841 |
+
"eval_samples_per_second": 108.262,
|
| 842 |
+
"eval_steps_per_second": 3.093,
|
| 843 |
"step": 164
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 83.0,
|
| 847 |
+
"eval_accuracy": 0.8142857142857143,
|
| 848 |
+
"eval_loss": 0.5905909538269043,
|
| 849 |
+
"eval_runtime": 0.8278,
|
| 850 |
+
"eval_samples_per_second": 84.56,
|
| 851 |
+
"eval_steps_per_second": 2.416,
|
| 852 |
"step": 166
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 84.0,
|
| 856 |
+
"eval_accuracy": 0.8142857142857143,
|
| 857 |
+
"eval_loss": 0.5897351503372192,
|
| 858 |
+
"eval_runtime": 0.6485,
|
| 859 |
+
"eval_samples_per_second": 107.935,
|
| 860 |
+
"eval_steps_per_second": 3.084,
|
| 861 |
"step": 168
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 85.0,
|
| 865 |
"learning_rate": 7.1875e-05,
|
| 866 |
+
"loss": 0.6434,
|
| 867 |
"step": 170
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 85.0,
|
| 871 |
+
"eval_accuracy": 0.8142857142857143,
|
| 872 |
+
"eval_loss": 0.588803768157959,
|
| 873 |
+
"eval_runtime": 0.6407,
|
| 874 |
+
"eval_samples_per_second": 109.255,
|
| 875 |
+
"eval_steps_per_second": 3.122,
|
| 876 |
"step": 170
|
| 877 |
},
|
| 878 |
{
|
| 879 |
"epoch": 86.0,
|
| 880 |
+
"eval_accuracy": 0.8142857142857143,
|
| 881 |
+
"eval_loss": 0.5878075361251831,
|
| 882 |
+
"eval_runtime": 0.7846,
|
| 883 |
+
"eval_samples_per_second": 89.216,
|
| 884 |
+
"eval_steps_per_second": 2.549,
|
| 885 |
"step": 172
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 87.0,
|
| 889 |
+
"eval_accuracy": 0.8142857142857143,
|
| 890 |
+
"eval_loss": 0.5868256688117981,
|
| 891 |
+
"eval_runtime": 0.6427,
|
| 892 |
+
"eval_samples_per_second": 108.917,
|
| 893 |
+
"eval_steps_per_second": 3.112,
|
| 894 |
"step": 174
|
| 895 |
},
|
| 896 |
{
|
| 897 |
"epoch": 88.0,
|
| 898 |
+
"eval_accuracy": 0.8142857142857143,
|
| 899 |
+
"eval_loss": 0.5859082341194153,
|
| 900 |
+
"eval_runtime": 0.6384,
|
| 901 |
+
"eval_samples_per_second": 109.65,
|
| 902 |
+
"eval_steps_per_second": 3.133,
|
| 903 |
"step": 176
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 89.0,
|
| 907 |
+
"eval_accuracy": 0.8142857142857143,
|
| 908 |
+
"eval_loss": 0.5850787162780762,
|
| 909 |
+
"eval_runtime": 0.7009,
|
| 910 |
+
"eval_samples_per_second": 99.878,
|
| 911 |
+
"eval_steps_per_second": 2.854,
|
| 912 |
"step": 178
|
| 913 |
},
|
| 914 |
{
|
| 915 |
"epoch": 90.0,
|
| 916 |
"learning_rate": 6.875e-05,
|
| 917 |
+
"loss": 0.6825,
|
| 918 |
"step": 180
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 90.0,
|
| 922 |
+
"eval_accuracy": 0.8142857142857143,
|
| 923 |
+
"eval_loss": 0.5843265652656555,
|
| 924 |
+
"eval_runtime": 0.6343,
|
| 925 |
+
"eval_samples_per_second": 110.361,
|
| 926 |
+
"eval_steps_per_second": 3.153,
|
| 927 |
"step": 180
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 91.0,
|
| 931 |
+
"eval_accuracy": 0.8142857142857143,
|
| 932 |
+
"eval_loss": 0.5835766792297363,
|
| 933 |
+
"eval_runtime": 0.645,
|
| 934 |
+
"eval_samples_per_second": 108.529,
|
| 935 |
+
"eval_steps_per_second": 3.101,
|
| 936 |
"step": 182
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"epoch": 92.0,
|
| 940 |
+
"eval_accuracy": 0.8142857142857143,
|
| 941 |
+
"eval_loss": 0.5828419923782349,
|
| 942 |
+
"eval_runtime": 0.6414,
|
| 943 |
+
"eval_samples_per_second": 109.129,
|
| 944 |
+
"eval_steps_per_second": 3.118,
|
| 945 |
"step": 184
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 93.0,
|
| 949 |
+
"eval_accuracy": 0.8142857142857143,
|
| 950 |
+
"eval_loss": 0.5822591781616211,
|
| 951 |
+
"eval_runtime": 0.6506,
|
| 952 |
+
"eval_samples_per_second": 107.585,
|
| 953 |
+
"eval_steps_per_second": 3.074,
|
| 954 |
"step": 186
|
| 955 |
},
|
| 956 |
{
|
| 957 |
"epoch": 94.0,
|
| 958 |
+
"eval_accuracy": 0.8285714285714286,
|
| 959 |
+
"eval_loss": 0.5817149877548218,
|
| 960 |
+
"eval_runtime": 0.6481,
|
| 961 |
+
"eval_samples_per_second": 108.003,
|
| 962 |
+
"eval_steps_per_second": 3.086,
|
| 963 |
"step": 188
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 95.0,
|
| 967 |
"learning_rate": 6.562500000000001e-05,
|
| 968 |
+
"loss": 0.6695,
|
| 969 |
"step": 190
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 95.0,
|
| 973 |
+
"eval_accuracy": 0.8142857142857143,
|
| 974 |
+
"eval_loss": 0.5809342265129089,
|
| 975 |
+
"eval_runtime": 0.6426,
|
| 976 |
+
"eval_samples_per_second": 108.939,
|
| 977 |
+
"eval_steps_per_second": 3.113,
|
| 978 |
"step": 190
|
| 979 |
},
|
| 980 |
{
|
| 981 |
"epoch": 96.0,
|
| 982 |
+
"eval_accuracy": 0.8142857142857143,
|
| 983 |
+
"eval_loss": 0.5801157355308533,
|
| 984 |
+
"eval_runtime": 0.7408,
|
| 985 |
+
"eval_samples_per_second": 94.487,
|
| 986 |
+
"eval_steps_per_second": 2.7,
|
| 987 |
"step": 192
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 97.0,
|
| 991 |
+
"eval_accuracy": 0.8142857142857143,
|
| 992 |
+
"eval_loss": 0.5793442130088806,
|
| 993 |
+
"eval_runtime": 0.6328,
|
| 994 |
+
"eval_samples_per_second": 110.628,
|
| 995 |
+
"eval_steps_per_second": 3.161,
|
| 996 |
"step": 194
|
| 997 |
},
|
| 998 |
{
|
| 999 |
"epoch": 98.0,
|
| 1000 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1001 |
+
"eval_loss": 0.5787318348884583,
|
| 1002 |
+
"eval_runtime": 0.6404,
|
| 1003 |
+
"eval_samples_per_second": 109.309,
|
| 1004 |
+
"eval_steps_per_second": 3.123,
|
| 1005 |
"step": 196
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 99.0,
|
| 1009 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1010 |
+
"eval_loss": 0.5780039429664612,
|
| 1011 |
+
"eval_runtime": 0.7894,
|
| 1012 |
+
"eval_samples_per_second": 88.678,
|
| 1013 |
+
"eval_steps_per_second": 2.534,
|
| 1014 |
"step": 198
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
"epoch": 100.0,
|
| 1018 |
"learning_rate": 6.25e-05,
|
| 1019 |
+
"loss": 0.6672,
|
| 1020 |
"step": 200
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
"epoch": 100.0,
|
| 1024 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1025 |
+
"eval_loss": 0.5772114992141724,
|
| 1026 |
+
"eval_runtime": 0.6485,
|
| 1027 |
+
"eval_samples_per_second": 107.942,
|
| 1028 |
+
"eval_steps_per_second": 3.084,
|
| 1029 |
"step": 200
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 101.0,
|
| 1033 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1034 |
+
"eval_loss": 0.5762485265731812,
|
| 1035 |
+
"eval_runtime": 0.632,
|
| 1036 |
+
"eval_samples_per_second": 110.757,
|
| 1037 |
+
"eval_steps_per_second": 3.164,
|
| 1038 |
"step": 202
|
| 1039 |
},
|
| 1040 |
{
|
| 1041 |
"epoch": 102.0,
|
| 1042 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1043 |
+
"eval_loss": 0.5753609538078308,
|
| 1044 |
+
"eval_runtime": 0.8156,
|
| 1045 |
+
"eval_samples_per_second": 85.824,
|
| 1046 |
+
"eval_steps_per_second": 2.452,
|
| 1047 |
"step": 204
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 103.0,
|
| 1051 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1052 |
+
"eval_loss": 0.5745884776115417,
|
| 1053 |
+
"eval_runtime": 0.641,
|
| 1054 |
+
"eval_samples_per_second": 109.197,
|
| 1055 |
+
"eval_steps_per_second": 3.12,
|
| 1056 |
"step": 206
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 104.0,
|
| 1060 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1061 |
+
"eval_loss": 0.573843777179718,
|
| 1062 |
+
"eval_runtime": 0.64,
|
| 1063 |
+
"eval_samples_per_second": 109.374,
|
| 1064 |
+
"eval_steps_per_second": 3.125,
|
| 1065 |
"step": 208
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 105.0,
|
| 1069 |
"learning_rate": 5.9375e-05,
|
| 1070 |
+
"loss": 0.6569,
|
| 1071 |
"step": 210
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 105.0,
|
| 1075 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1076 |
+
"eval_loss": 0.5731338858604431,
|
| 1077 |
+
"eval_runtime": 0.8165,
|
| 1078 |
+
"eval_samples_per_second": 85.735,
|
| 1079 |
+
"eval_steps_per_second": 2.45,
|
| 1080 |
"step": 210
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 106.0,
|
| 1084 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1085 |
+
"eval_loss": 0.5723776817321777,
|
| 1086 |
+
"eval_runtime": 0.6448,
|
| 1087 |
+
"eval_samples_per_second": 108.558,
|
| 1088 |
+
"eval_steps_per_second": 3.102,
|
| 1089 |
"step": 212
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
"epoch": 107.0,
|
| 1093 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1094 |
+
"eval_loss": 0.5715596675872803,
|
| 1095 |
+
"eval_runtime": 0.6552,
|
| 1096 |
+
"eval_samples_per_second": 106.837,
|
| 1097 |
+
"eval_steps_per_second": 3.052,
|
| 1098 |
"step": 214
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
"epoch": 108.0,
|
| 1102 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1103 |
+
"eval_loss": 0.5707866549491882,
|
| 1104 |
+
"eval_runtime": 0.7955,
|
| 1105 |
+
"eval_samples_per_second": 87.991,
|
| 1106 |
+
"eval_steps_per_second": 2.514,
|
| 1107 |
"step": 216
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
"epoch": 109.0,
|
| 1111 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1112 |
+
"eval_loss": 0.570074737071991,
|
| 1113 |
+
"eval_runtime": 0.6364,
|
| 1114 |
+
"eval_samples_per_second": 109.993,
|
| 1115 |
+
"eval_steps_per_second": 3.143,
|
| 1116 |
"step": 218
|
| 1117 |
},
|
| 1118 |
{
|
| 1119 |
"epoch": 110.0,
|
| 1120 |
"learning_rate": 5.6250000000000005e-05,
|
| 1121 |
+
"loss": 0.6748,
|
| 1122 |
"step": 220
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 110.0,
|
| 1126 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1127 |
+
"eval_loss": 0.5693923830986023,
|
| 1128 |
+
"eval_runtime": 0.6356,
|
| 1129 |
+
"eval_samples_per_second": 110.138,
|
| 1130 |
+
"eval_steps_per_second": 3.147,
|
| 1131 |
"step": 220
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 111.0,
|
| 1135 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1136 |
+
"eval_loss": 0.5686994791030884,
|
| 1137 |
+
"eval_runtime": 0.8207,
|
| 1138 |
+
"eval_samples_per_second": 85.298,
|
| 1139 |
+
"eval_steps_per_second": 2.437,
|
| 1140 |
"step": 222
|
| 1141 |
},
|
| 1142 |
{
|
| 1143 |
"epoch": 112.0,
|
| 1144 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1145 |
+
"eval_loss": 0.5680269598960876,
|
| 1146 |
+
"eval_runtime": 0.6498,
|
| 1147 |
+
"eval_samples_per_second": 107.722,
|
| 1148 |
+
"eval_steps_per_second": 3.078,
|
| 1149 |
"step": 224
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"epoch": 113.0,
|
| 1153 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1154 |
+
"eval_loss": 0.5673888325691223,
|
| 1155 |
+
"eval_runtime": 0.6711,
|
| 1156 |
+
"eval_samples_per_second": 104.299,
|
| 1157 |
+
"eval_steps_per_second": 2.98,
|
| 1158 |
"step": 226
|
| 1159 |
},
|
| 1160 |
{
|
| 1161 |
"epoch": 114.0,
|
| 1162 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1163 |
+
"eval_loss": 0.5668244957923889,
|
| 1164 |
+
"eval_runtime": 0.8599,
|
| 1165 |
+
"eval_samples_per_second": 81.4,
|
| 1166 |
+
"eval_steps_per_second": 2.326,
|
| 1167 |
"step": 228
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 115.0,
|
| 1171 |
"learning_rate": 5.3125000000000004e-05,
|
| 1172 |
+
"loss": 0.6388,
|
| 1173 |
"step": 230
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 115.0,
|
| 1177 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1178 |
+
"eval_loss": 0.56624835729599,
|
| 1179 |
+
"eval_runtime": 0.639,
|
| 1180 |
+
"eval_samples_per_second": 109.549,
|
| 1181 |
+
"eval_steps_per_second": 3.13,
|
| 1182 |
"step": 230
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
"epoch": 116.0,
|
| 1186 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1187 |
+
"eval_loss": 0.5657045841217041,
|
| 1188 |
+
"eval_runtime": 0.6452,
|
| 1189 |
+
"eval_samples_per_second": 108.495,
|
| 1190 |
+
"eval_steps_per_second": 3.1,
|
| 1191 |
"step": 232
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
"epoch": 117.0,
|
| 1195 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1196 |
+
"eval_loss": 0.5652384757995605,
|
| 1197 |
+
"eval_runtime": 0.8319,
|
| 1198 |
+
"eval_samples_per_second": 84.146,
|
| 1199 |
+
"eval_steps_per_second": 2.404,
|
| 1200 |
"step": 234
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 118.0,
|
| 1204 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1205 |
+
"eval_loss": 0.5648259520530701,
|
| 1206 |
+
"eval_runtime": 0.6475,
|
| 1207 |
+
"eval_samples_per_second": 108.103,
|
| 1208 |
+
"eval_steps_per_second": 3.089,
|
| 1209 |
"step": 236
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
"epoch": 119.0,
|
| 1213 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1214 |
+
"eval_loss": 0.5644696354866028,
|
| 1215 |
+
"eval_runtime": 0.6531,
|
| 1216 |
+
"eval_samples_per_second": 107.184,
|
| 1217 |
+
"eval_steps_per_second": 3.062,
|
| 1218 |
"step": 238
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 120.0,
|
| 1222 |
"learning_rate": 5e-05,
|
| 1223 |
+
"loss": 0.6551,
|
| 1224 |
"step": 240
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 120.0,
|
| 1228 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1229 |
+
"eval_loss": 0.5640624165534973,
|
| 1230 |
+
"eval_runtime": 0.8277,
|
| 1231 |
+
"eval_samples_per_second": 84.574,
|
| 1232 |
+
"eval_steps_per_second": 2.416,
|
| 1233 |
"step": 240
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
"epoch": 121.0,
|
| 1237 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1238 |
+
"eval_loss": 0.5636399388313293,
|
| 1239 |
+
"eval_runtime": 0.6478,
|
| 1240 |
+
"eval_samples_per_second": 108.056,
|
| 1241 |
+
"eval_steps_per_second": 3.087,
|
| 1242 |
"step": 242
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
"epoch": 122.0,
|
| 1246 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1247 |
+
"eval_loss": 0.563149094581604,
|
| 1248 |
+
"eval_runtime": 0.6338,
|
| 1249 |
+
"eval_samples_per_second": 110.453,
|
| 1250 |
+
"eval_steps_per_second": 3.156,
|
| 1251 |
"step": 244
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
"epoch": 123.0,
|
| 1255 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1256 |
+
"eval_loss": 0.5627174973487854,
|
| 1257 |
+
"eval_runtime": 0.8111,
|
| 1258 |
+
"eval_samples_per_second": 86.304,
|
| 1259 |
+
"eval_steps_per_second": 2.466,
|
| 1260 |
"step": 246
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 124.0,
|
| 1264 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1265 |
+
"eval_loss": 0.562400221824646,
|
| 1266 |
+
"eval_runtime": 0.649,
|
| 1267 |
+
"eval_samples_per_second": 107.86,
|
| 1268 |
+
"eval_steps_per_second": 3.082,
|
| 1269 |
"step": 248
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 125.0,
|
| 1273 |
"learning_rate": 4.6875e-05,
|
| 1274 |
+
"loss": 0.6452,
|
| 1275 |
"step": 250
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
"epoch": 125.0,
|
| 1279 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1280 |
+
"eval_loss": 0.5621911287307739,
|
| 1281 |
+
"eval_runtime": 0.6465,
|
| 1282 |
+
"eval_samples_per_second": 108.279,
|
| 1283 |
+
"eval_steps_per_second": 3.094,
|
| 1284 |
"step": 250
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
"epoch": 126.0,
|
| 1288 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1289 |
+
"eval_loss": 0.5620221495628357,
|
| 1290 |
+
"eval_runtime": 0.827,
|
| 1291 |
+
"eval_samples_per_second": 84.639,
|
| 1292 |
+
"eval_steps_per_second": 2.418,
|
| 1293 |
"step": 252
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
"epoch": 127.0,
|
| 1297 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1298 |
+
"eval_loss": 0.5617978572845459,
|
| 1299 |
+
"eval_runtime": 0.6221,
|
| 1300 |
+
"eval_samples_per_second": 112.525,
|
| 1301 |
+
"eval_steps_per_second": 3.215,
|
| 1302 |
"step": 254
|
| 1303 |
},
|
| 1304 |
{
|
| 1305 |
"epoch": 128.0,
|
| 1306 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1307 |
+
"eval_loss": 0.5614616870880127,
|
| 1308 |
+
"eval_runtime": 0.6384,
|
| 1309 |
+
"eval_samples_per_second": 109.65,
|
| 1310 |
+
"eval_steps_per_second": 3.133,
|
| 1311 |
"step": 256
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 129.0,
|
| 1315 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1316 |
+
"eval_loss": 0.5612771511077881,
|
| 1317 |
+
"eval_runtime": 0.8188,
|
| 1318 |
+
"eval_samples_per_second": 85.487,
|
| 1319 |
+
"eval_steps_per_second": 2.442,
|
| 1320 |
"step": 258
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
"epoch": 130.0,
|
| 1324 |
"learning_rate": 4.375e-05,
|
| 1325 |
+
"loss": 0.645,
|
| 1326 |
"step": 260
|
| 1327 |
},
|
| 1328 |
{
|
| 1329 |
"epoch": 130.0,
|
| 1330 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1331 |
+
"eval_loss": 0.5610944032669067,
|
| 1332 |
+
"eval_runtime": 0.6274,
|
| 1333 |
+
"eval_samples_per_second": 111.57,
|
| 1334 |
+
"eval_steps_per_second": 3.188,
|
| 1335 |
"step": 260
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
"epoch": 131.0,
|
| 1339 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1340 |
+
"eval_loss": 0.5608205199241638,
|
| 1341 |
+
"eval_runtime": 0.6351,
|
| 1342 |
+
"eval_samples_per_second": 110.223,
|
| 1343 |
+
"eval_steps_per_second": 3.149,
|
| 1344 |
"step": 262
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 132.0,
|
| 1348 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1349 |
+
"eval_loss": 0.5606086254119873,
|
| 1350 |
+
"eval_runtime": 0.8451,
|
| 1351 |
+
"eval_samples_per_second": 82.832,
|
| 1352 |
+
"eval_steps_per_second": 2.367,
|
| 1353 |
"step": 264
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 133.0,
|
| 1357 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1358 |
+
"eval_loss": 0.5602155923843384,
|
| 1359 |
+
"eval_runtime": 0.6314,
|
| 1360 |
+
"eval_samples_per_second": 110.864,
|
| 1361 |
+
"eval_steps_per_second": 3.168,
|
| 1362 |
"step": 266
|
| 1363 |
},
|
| 1364 |
{
|
| 1365 |
"epoch": 134.0,
|
| 1366 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1367 |
+
"eval_loss": 0.5596277713775635,
|
| 1368 |
+
"eval_runtime": 0.6347,
|
| 1369 |
+
"eval_samples_per_second": 110.28,
|
| 1370 |
+
"eval_steps_per_second": 3.151,
|
| 1371 |
"step": 268
|
| 1372 |
},
|
| 1373 |
{
|
| 1374 |
"epoch": 135.0,
|
| 1375 |
"learning_rate": 4.0625000000000005e-05,
|
| 1376 |
+
"loss": 0.629,
|
| 1377 |
"step": 270
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 135.0,
|
| 1381 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1382 |
+
"eval_loss": 0.558956503868103,
|
| 1383 |
+
"eval_runtime": 0.8112,
|
| 1384 |
+
"eval_samples_per_second": 86.289,
|
| 1385 |
+
"eval_steps_per_second": 2.465,
|
| 1386 |
"step": 270
|
| 1387 |
},
|
| 1388 |
{
|
| 1389 |
"epoch": 136.0,
|
| 1390 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1391 |
+
"eval_loss": 0.5582412481307983,
|
| 1392 |
+
"eval_runtime": 0.6394,
|
| 1393 |
+
"eval_samples_per_second": 109.485,
|
| 1394 |
+
"eval_steps_per_second": 3.128,
|
| 1395 |
"step": 272
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 137.0,
|
| 1399 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1400 |
+
"eval_loss": 0.5576009750366211,
|
| 1401 |
+
"eval_runtime": 0.6293,
|
| 1402 |
+
"eval_samples_per_second": 111.232,
|
| 1403 |
+
"eval_steps_per_second": 3.178,
|
| 1404 |
"step": 274
|
| 1405 |
},
|
| 1406 |
{
|
| 1407 |
"epoch": 138.0,
|
| 1408 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1409 |
+
"eval_loss": 0.5571399927139282,
|
| 1410 |
+
"eval_runtime": 0.8108,
|
| 1411 |
+
"eval_samples_per_second": 86.33,
|
| 1412 |
+
"eval_steps_per_second": 2.467,
|
| 1413 |
"step": 276
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 139.0,
|
| 1417 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1418 |
+
"eval_loss": 0.5567926168441772,
|
| 1419 |
+
"eval_runtime": 0.6262,
|
| 1420 |
+
"eval_samples_per_second": 111.788,
|
| 1421 |
+
"eval_steps_per_second": 3.194,
|
| 1422 |
"step": 278
|
| 1423 |
},
|
| 1424 |
{
|
| 1425 |
"epoch": 140.0,
|
| 1426 |
"learning_rate": 3.7500000000000003e-05,
|
| 1427 |
+
"loss": 0.7126,
|
| 1428 |
"step": 280
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
"epoch": 140.0,
|
| 1432 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1433 |
+
"eval_loss": 0.556534469127655,
|
| 1434 |
+
"eval_runtime": 0.6392,
|
| 1435 |
+
"eval_samples_per_second": 109.51,
|
| 1436 |
+
"eval_steps_per_second": 3.129,
|
| 1437 |
"step": 280
|
| 1438 |
},
|
| 1439 |
{
|
| 1440 |
"epoch": 141.0,
|
| 1441 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1442 |
+
"eval_loss": 0.5563255548477173,
|
| 1443 |
+
"eval_runtime": 0.8384,
|
| 1444 |
+
"eval_samples_per_second": 83.488,
|
| 1445 |
+
"eval_steps_per_second": 2.385,
|
| 1446 |
"step": 282
|
| 1447 |
},
|
| 1448 |
{
|
| 1449 |
"epoch": 142.0,
|
| 1450 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1451 |
+
"eval_loss": 0.5561147928237915,
|
| 1452 |
"eval_runtime": 0.6382,
|
| 1453 |
+
"eval_samples_per_second": 109.687,
|
| 1454 |
"eval_steps_per_second": 3.134,
|
| 1455 |
"step": 284
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
"epoch": 143.0,
|
| 1459 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1460 |
+
"eval_loss": 0.5559044480323792,
|
| 1461 |
+
"eval_runtime": 0.647,
|
| 1462 |
+
"eval_samples_per_second": 108.191,
|
| 1463 |
+
"eval_steps_per_second": 3.091,
|
| 1464 |
"step": 286
|
| 1465 |
},
|
| 1466 |
{
|
| 1467 |
"epoch": 144.0,
|
| 1468 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1469 |
+
"eval_loss": 0.555549681186676,
|
| 1470 |
+
"eval_runtime": 0.8257,
|
| 1471 |
+
"eval_samples_per_second": 84.779,
|
| 1472 |
+
"eval_steps_per_second": 2.422,
|
| 1473 |
"step": 288
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
"epoch": 145.0,
|
| 1477 |
"learning_rate": 3.4375e-05,
|
| 1478 |
+
"loss": 0.669,
|
| 1479 |
"step": 290
|
| 1480 |
},
|
| 1481 |
{
|
| 1482 |
"epoch": 145.0,
|
| 1483 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1484 |
+
"eval_loss": 0.5551820397377014,
|
| 1485 |
+
"eval_runtime": 0.6311,
|
| 1486 |
+
"eval_samples_per_second": 110.921,
|
| 1487 |
+
"eval_steps_per_second": 3.169,
|
| 1488 |
"step": 290
|
| 1489 |
},
|
| 1490 |
{
|
| 1491 |
"epoch": 146.0,
|
| 1492 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1493 |
+
"eval_loss": 0.55474454164505,
|
| 1494 |
+
"eval_runtime": 0.653,
|
| 1495 |
+
"eval_samples_per_second": 107.193,
|
| 1496 |
+
"eval_steps_per_second": 3.063,
|
| 1497 |
"step": 292
|
| 1498 |
},
|
| 1499 |
{
|
| 1500 |
"epoch": 147.0,
|
| 1501 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1502 |
+
"eval_loss": 0.5542392134666443,
|
| 1503 |
+
"eval_runtime": 0.8093,
|
| 1504 |
+
"eval_samples_per_second": 86.493,
|
| 1505 |
+
"eval_steps_per_second": 2.471,
|
| 1506 |
"step": 294
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 148.0,
|
| 1510 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1511 |
+
"eval_loss": 0.5537976622581482,
|
| 1512 |
+
"eval_runtime": 0.6472,
|
| 1513 |
+
"eval_samples_per_second": 108.161,
|
| 1514 |
+
"eval_steps_per_second": 3.09,
|
| 1515 |
"step": 296
|
| 1516 |
},
|
| 1517 |
{
|
| 1518 |
"epoch": 149.0,
|
| 1519 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1520 |
+
"eval_loss": 0.5534089803695679,
|
| 1521 |
+
"eval_runtime": 0.6283,
|
| 1522 |
+
"eval_samples_per_second": 111.403,
|
| 1523 |
+
"eval_steps_per_second": 3.183,
|
| 1524 |
"step": 298
|
| 1525 |
},
|
| 1526 |
{
|
| 1527 |
"epoch": 150.0,
|
| 1528 |
"learning_rate": 3.125e-05,
|
| 1529 |
+
"loss": 0.6481,
|
| 1530 |
"step": 300
|
| 1531 |
},
|
| 1532 |
{
|
| 1533 |
"epoch": 150.0,
|
| 1534 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1535 |
+
"eval_loss": 0.5530030727386475,
|
| 1536 |
+
"eval_runtime": 0.8284,
|
| 1537 |
+
"eval_samples_per_second": 84.505,
|
| 1538 |
+
"eval_steps_per_second": 2.414,
|
| 1539 |
"step": 300
|
| 1540 |
},
|
| 1541 |
{
|
| 1542 |
"epoch": 151.0,
|
| 1543 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1544 |
+
"eval_loss": 0.5526387095451355,
|
| 1545 |
+
"eval_runtime": 0.6358,
|
| 1546 |
+
"eval_samples_per_second": 110.105,
|
| 1547 |
+
"eval_steps_per_second": 3.146,
|
| 1548 |
"step": 302
|
| 1549 |
},
|
| 1550 |
{
|
| 1551 |
"epoch": 152.0,
|
| 1552 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1553 |
+
"eval_loss": 0.5522416830062866,
|
| 1554 |
+
"eval_runtime": 0.6285,
|
| 1555 |
+
"eval_samples_per_second": 111.384,
|
| 1556 |
+
"eval_steps_per_second": 3.182,
|
| 1557 |
"step": 304
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
"epoch": 153.0,
|
| 1561 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1562 |
+
"eval_loss": 0.5518553853034973,
|
| 1563 |
+
"eval_runtime": 0.7207,
|
| 1564 |
+
"eval_samples_per_second": 97.122,
|
| 1565 |
+
"eval_steps_per_second": 2.775,
|
| 1566 |
"step": 306
|
| 1567 |
},
|
| 1568 |
{
|
| 1569 |
"epoch": 154.0,
|
| 1570 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1571 |
+
"eval_loss": 0.5514690279960632,
|
| 1572 |
+
"eval_runtime": 0.6359,
|
| 1573 |
+
"eval_samples_per_second": 110.085,
|
| 1574 |
+
"eval_steps_per_second": 3.145,
|
| 1575 |
"step": 308
|
| 1576 |
},
|
| 1577 |
{
|
| 1578 |
"epoch": 155.0,
|
| 1579 |
"learning_rate": 2.8125000000000003e-05,
|
| 1580 |
+
"loss": 0.6211,
|
| 1581 |
"step": 310
|
| 1582 |
},
|
| 1583 |
{
|
| 1584 |
"epoch": 155.0,
|
| 1585 |
"eval_accuracy": 0.8142857142857143,
|
| 1586 |
+
"eval_loss": 0.5510378479957581,
|
| 1587 |
+
"eval_runtime": 0.636,
|
| 1588 |
+
"eval_samples_per_second": 110.056,
|
| 1589 |
+
"eval_steps_per_second": 3.144,
|
| 1590 |
"step": 310
|
| 1591 |
},
|
| 1592 |
{
|
| 1593 |
"epoch": 156.0,
|
| 1594 |
"eval_accuracy": 0.8142857142857143,
|
| 1595 |
+
"eval_loss": 0.5506120920181274,
|
| 1596 |
+
"eval_runtime": 0.6297,
|
| 1597 |
+
"eval_samples_per_second": 111.157,
|
| 1598 |
+
"eval_steps_per_second": 3.176,
|
| 1599 |
"step": 312
|
| 1600 |
},
|
| 1601 |
{
|
| 1602 |
"epoch": 157.0,
|
| 1603 |
"eval_accuracy": 0.8142857142857143,
|
| 1604 |
+
"eval_loss": 0.5502142906188965,
|
| 1605 |
+
"eval_runtime": 0.6795,
|
| 1606 |
+
"eval_samples_per_second": 103.02,
|
| 1607 |
+
"eval_steps_per_second": 2.943,
|
| 1608 |
"step": 314
|
| 1609 |
},
|
| 1610 |
{
|
| 1611 |
"epoch": 158.0,
|
| 1612 |
"eval_accuracy": 0.8142857142857143,
|
| 1613 |
+
"eval_loss": 0.5498998761177063,
|
| 1614 |
+
"eval_runtime": 0.6321,
|
| 1615 |
+
"eval_samples_per_second": 110.745,
|
| 1616 |
+
"eval_steps_per_second": 3.164,
|
| 1617 |
"step": 316
|
| 1618 |
},
|
| 1619 |
{
|
| 1620 |
"epoch": 159.0,
|
| 1621 |
"eval_accuracy": 0.8142857142857143,
|
| 1622 |
+
"eval_loss": 0.5495581030845642,
|
| 1623 |
+
"eval_runtime": 0.6392,
|
| 1624 |
+
"eval_samples_per_second": 109.52,
|
| 1625 |
+
"eval_steps_per_second": 3.129,
|
| 1626 |
"step": 318
|
| 1627 |
},
|
| 1628 |
{
|
| 1629 |
"epoch": 160.0,
|
| 1630 |
"learning_rate": 2.5e-05,
|
| 1631 |
+
"loss": 0.6458,
|
| 1632 |
"step": 320
|
| 1633 |
},
|
| 1634 |
{
|
| 1635 |
"epoch": 160.0,
|
| 1636 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1637 |
+
"eval_loss": 0.5492438077926636,
|
| 1638 |
+
"eval_runtime": 0.8024,
|
| 1639 |
+
"eval_samples_per_second": 87.237,
|
| 1640 |
+
"eval_steps_per_second": 2.492,
|
| 1641 |
"step": 320
|
| 1642 |
},
|
| 1643 |
{
|
| 1644 |
"epoch": 161.0,
|
| 1645 |
"eval_accuracy": 0.8142857142857143,
|
| 1646 |
+
"eval_loss": 0.5489979982376099,
|
| 1647 |
+
"eval_runtime": 0.6575,
|
| 1648 |
+
"eval_samples_per_second": 106.471,
|
| 1649 |
+
"eval_steps_per_second": 3.042,
|
| 1650 |
"step": 322
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
"epoch": 162.0,
|
| 1654 |
"eval_accuracy": 0.8142857142857143,
|
| 1655 |
+
"eval_loss": 0.5487762689590454,
|
| 1656 |
+
"eval_runtime": 0.6515,
|
| 1657 |
+
"eval_samples_per_second": 107.45,
|
| 1658 |
+
"eval_steps_per_second": 3.07,
|
| 1659 |
"step": 324
|
| 1660 |
},
|
| 1661 |
{
|
| 1662 |
"epoch": 163.0,
|
| 1663 |
"eval_accuracy": 0.8142857142857143,
|
| 1664 |
+
"eval_loss": 0.548595130443573,
|
| 1665 |
+
"eval_runtime": 0.8069,
|
| 1666 |
+
"eval_samples_per_second": 86.752,
|
| 1667 |
+
"eval_steps_per_second": 2.479,
|
| 1668 |
"step": 326
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
"epoch": 164.0,
|
| 1672 |
"eval_accuracy": 0.8142857142857143,
|
| 1673 |
+
"eval_loss": 0.5483713746070862,
|
| 1674 |
+
"eval_runtime": 0.6447,
|
| 1675 |
+
"eval_samples_per_second": 108.582,
|
| 1676 |
+
"eval_steps_per_second": 3.102,
|
| 1677 |
"step": 328
|
| 1678 |
},
|
| 1679 |
{
|
| 1680 |
"epoch": 165.0,
|
| 1681 |
"learning_rate": 2.1875e-05,
|
| 1682 |
+
"loss": 0.6317,
|
| 1683 |
"step": 330
|
| 1684 |
},
|
| 1685 |
{
|
| 1686 |
"epoch": 165.0,
|
| 1687 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1688 |
+
"eval_loss": 0.5481104254722595,
|
| 1689 |
+
"eval_runtime": 0.6486,
|
| 1690 |
+
"eval_samples_per_second": 107.926,
|
| 1691 |
+
"eval_steps_per_second": 3.084,
|
| 1692 |
"step": 330
|
| 1693 |
},
|
| 1694 |
{
|
| 1695 |
"epoch": 166.0,
|
| 1696 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1697 |
+
"eval_loss": 0.5478586554527283,
|
| 1698 |
+
"eval_runtime": 0.8209,
|
| 1699 |
+
"eval_samples_per_second": 85.268,
|
| 1700 |
+
"eval_steps_per_second": 2.436,
|
| 1701 |
"step": 332
|
| 1702 |
},
|
| 1703 |
{
|
| 1704 |
"epoch": 167.0,
|
| 1705 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1706 |
+
"eval_loss": 0.5475797653198242,
|
| 1707 |
+
"eval_runtime": 0.7417,
|
| 1708 |
+
"eval_samples_per_second": 94.381,
|
| 1709 |
+
"eval_steps_per_second": 2.697,
|
| 1710 |
"step": 334
|
| 1711 |
},
|
| 1712 |
{
|
| 1713 |
"epoch": 168.0,
|
| 1714 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1715 |
+
"eval_loss": 0.5473471879959106,
|
| 1716 |
+
"eval_runtime": 0.6501,
|
| 1717 |
+
"eval_samples_per_second": 107.671,
|
| 1718 |
+
"eval_steps_per_second": 3.076,
|
| 1719 |
"step": 336
|
| 1720 |
},
|
| 1721 |
{
|
| 1722 |
"epoch": 169.0,
|
| 1723 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1724 |
+
"eval_loss": 0.5471236705780029,
|
| 1725 |
+
"eval_runtime": 0.7944,
|
| 1726 |
+
"eval_samples_per_second": 88.115,
|
| 1727 |
+
"eval_steps_per_second": 2.518,
|
| 1728 |
"step": 338
|
| 1729 |
},
|
| 1730 |
{
|
| 1731 |
"epoch": 170.0,
|
| 1732 |
"learning_rate": 1.8750000000000002e-05,
|
| 1733 |
+
"loss": 0.6154,
|
| 1734 |
"step": 340
|
| 1735 |
},
|
| 1736 |
{
|
| 1737 |
"epoch": 170.0,
|
| 1738 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1739 |
+
"eval_loss": 0.5469514727592468,
|
| 1740 |
+
"eval_runtime": 0.6378,
|
| 1741 |
+
"eval_samples_per_second": 109.76,
|
| 1742 |
+
"eval_steps_per_second": 3.136,
|
| 1743 |
"step": 340
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
"epoch": 171.0,
|
| 1747 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1748 |
+
"eval_loss": 0.5467889308929443,
|
| 1749 |
+
"eval_runtime": 0.6433,
|
| 1750 |
+
"eval_samples_per_second": 108.819,
|
| 1751 |
+
"eval_steps_per_second": 3.109,
|
| 1752 |
"step": 342
|
| 1753 |
},
|
| 1754 |
{
|
| 1755 |
"epoch": 172.0,
|
| 1756 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1757 |
+
"eval_loss": 0.5466357469558716,
|
| 1758 |
+
"eval_runtime": 0.8146,
|
| 1759 |
+
"eval_samples_per_second": 85.93,
|
| 1760 |
+
"eval_steps_per_second": 2.455,
|
| 1761 |
"step": 344
|
| 1762 |
},
|
| 1763 |
{
|
| 1764 |
"epoch": 173.0,
|
| 1765 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1766 |
+
"eval_loss": 0.5464411973953247,
|
| 1767 |
+
"eval_runtime": 0.6826,
|
| 1768 |
+
"eval_samples_per_second": 102.554,
|
| 1769 |
+
"eval_steps_per_second": 2.93,
|
| 1770 |
"step": 346
|
| 1771 |
},
|
| 1772 |
{
|
| 1773 |
"epoch": 174.0,
|
| 1774 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1775 |
+
"eval_loss": 0.5462457537651062,
|
| 1776 |
+
"eval_runtime": 0.6413,
|
| 1777 |
+
"eval_samples_per_second": 109.146,
|
| 1778 |
+
"eval_steps_per_second": 3.118,
|
| 1779 |
"step": 348
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
"epoch": 175.0,
|
| 1783 |
"learning_rate": 1.5625e-05,
|
| 1784 |
+
"loss": 0.6323,
|
| 1785 |
"step": 350
|
| 1786 |
},
|
| 1787 |
{
|
| 1788 |
"epoch": 175.0,
|
| 1789 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1790 |
+
"eval_loss": 0.5460384488105774,
|
| 1791 |
+
"eval_runtime": 0.8055,
|
| 1792 |
+
"eval_samples_per_second": 86.906,
|
| 1793 |
+
"eval_steps_per_second": 2.483,
|
| 1794 |
"step": 350
|
| 1795 |
},
|
| 1796 |
{
|
| 1797 |
"epoch": 176.0,
|
| 1798 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1799 |
+
"eval_loss": 0.545864999294281,
|
| 1800 |
+
"eval_runtime": 0.635,
|
| 1801 |
+
"eval_samples_per_second": 110.23,
|
| 1802 |
+
"eval_steps_per_second": 3.149,
|
| 1803 |
"step": 352
|
| 1804 |
},
|
| 1805 |
{
|
| 1806 |
"epoch": 177.0,
|
| 1807 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1808 |
+
"eval_loss": 0.54571932554245,
|
| 1809 |
+
"eval_runtime": 0.6362,
|
| 1810 |
+
"eval_samples_per_second": 110.035,
|
| 1811 |
+
"eval_steps_per_second": 3.144,
|
| 1812 |
"step": 354
|
| 1813 |
},
|
| 1814 |
{
|
| 1815 |
"epoch": 178.0,
|
| 1816 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1817 |
+
"eval_loss": 0.5455992817878723,
|
| 1818 |
+
"eval_runtime": 0.8155,
|
| 1819 |
+
"eval_samples_per_second": 85.839,
|
| 1820 |
+
"eval_steps_per_second": 2.453,
|
| 1821 |
"step": 356
|
| 1822 |
},
|
| 1823 |
{
|
| 1824 |
"epoch": 179.0,
|
| 1825 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1826 |
+
"eval_loss": 0.5454698801040649,
|
| 1827 |
+
"eval_runtime": 0.6543,
|
| 1828 |
+
"eval_samples_per_second": 106.992,
|
| 1829 |
+
"eval_steps_per_second": 3.057,
|
| 1830 |
"step": 358
|
| 1831 |
},
|
| 1832 |
{
|
| 1833 |
"epoch": 180.0,
|
| 1834 |
"learning_rate": 1.25e-05,
|
| 1835 |
+
"loss": 0.6331,
|
| 1836 |
"step": 360
|
| 1837 |
},
|
| 1838 |
{
|
| 1839 |
"epoch": 180.0,
|
| 1840 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1841 |
+
"eval_loss": 0.5453290343284607,
|
| 1842 |
+
"eval_runtime": 0.6499,
|
| 1843 |
+
"eval_samples_per_second": 107.716,
|
| 1844 |
+
"eval_steps_per_second": 3.078,
|
| 1845 |
"step": 360
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
"epoch": 181.0,
|
| 1849 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1850 |
+
"eval_loss": 0.5451884865760803,
|
| 1851 |
+
"eval_runtime": 0.8265,
|
| 1852 |
+
"eval_samples_per_second": 84.691,
|
| 1853 |
+
"eval_steps_per_second": 2.42,
|
| 1854 |
"step": 362
|
| 1855 |
},
|
| 1856 |
{
|
| 1857 |
"epoch": 182.0,
|
| 1858 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1859 |
+
"eval_loss": 0.5450613498687744,
|
| 1860 |
+
"eval_runtime": 0.6389,
|
| 1861 |
+
"eval_samples_per_second": 109.556,
|
| 1862 |
+
"eval_steps_per_second": 3.13,
|
| 1863 |
"step": 364
|
| 1864 |
},
|
| 1865 |
{
|
| 1866 |
"epoch": 183.0,
|
| 1867 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1868 |
+
"eval_loss": 0.5449284911155701,
|
| 1869 |
+
"eval_runtime": 0.6467,
|
| 1870 |
+
"eval_samples_per_second": 108.243,
|
| 1871 |
+
"eval_steps_per_second": 3.093,
|
| 1872 |
"step": 366
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
"epoch": 184.0,
|
| 1876 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1877 |
+
"eval_loss": 0.5448177456855774,
|
| 1878 |
+
"eval_runtime": 0.825,
|
| 1879 |
+
"eval_samples_per_second": 84.846,
|
| 1880 |
+
"eval_steps_per_second": 2.424,
|
| 1881 |
"step": 368
|
| 1882 |
},
|
| 1883 |
{
|
| 1884 |
"epoch": 185.0,
|
| 1885 |
"learning_rate": 9.375000000000001e-06,
|
| 1886 |
+
"loss": 0.6333,
|
| 1887 |
"step": 370
|
| 1888 |
},
|
| 1889 |
{
|
| 1890 |
"epoch": 185.0,
|
| 1891 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1892 |
+
"eval_loss": 0.544733464717865,
|
| 1893 |
+
"eval_runtime": 0.6541,
|
| 1894 |
+
"eval_samples_per_second": 107.012,
|
| 1895 |
+
"eval_steps_per_second": 3.057,
|
| 1896 |
"step": 370
|
| 1897 |
},
|
| 1898 |
{
|
| 1899 |
"epoch": 186.0,
|
| 1900 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1901 |
+
"eval_loss": 0.5446553230285645,
|
| 1902 |
+
"eval_runtime": 0.6491,
|
| 1903 |
+
"eval_samples_per_second": 107.838,
|
| 1904 |
+
"eval_steps_per_second": 3.081,
|
| 1905 |
"step": 372
|
| 1906 |
},
|
| 1907 |
{
|
| 1908 |
"epoch": 187.0,
|
| 1909 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1910 |
+
"eval_loss": 0.5445802211761475,
|
| 1911 |
+
"eval_runtime": 0.8184,
|
| 1912 |
+
"eval_samples_per_second": 85.533,
|
| 1913 |
+
"eval_steps_per_second": 2.444,
|
| 1914 |
"step": 374
|
| 1915 |
},
|
| 1916 |
{
|
| 1917 |
"epoch": 188.0,
|
| 1918 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1919 |
+
"eval_loss": 0.5445207357406616,
|
| 1920 |
+
"eval_runtime": 0.6378,
|
| 1921 |
+
"eval_samples_per_second": 109.754,
|
| 1922 |
+
"eval_steps_per_second": 3.136,
|
| 1923 |
"step": 376
|
| 1924 |
},
|
| 1925 |
{
|
| 1926 |
"epoch": 189.0,
|
| 1927 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1928 |
+
"eval_loss": 0.5444640517234802,
|
| 1929 |
+
"eval_runtime": 0.6708,
|
| 1930 |
+
"eval_samples_per_second": 104.36,
|
| 1931 |
+
"eval_steps_per_second": 2.982,
|
| 1932 |
"step": 378
|
| 1933 |
},
|
| 1934 |
{
|
| 1935 |
"epoch": 190.0,
|
| 1936 |
"learning_rate": 6.25e-06,
|
| 1937 |
+
"loss": 0.608,
|
| 1938 |
"step": 380
|
| 1939 |
},
|
| 1940 |
{
|
| 1941 |
"epoch": 190.0,
|
| 1942 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1943 |
+
"eval_loss": 0.544407069683075,
|
| 1944 |
+
"eval_runtime": 0.8392,
|
| 1945 |
+
"eval_samples_per_second": 83.416,
|
| 1946 |
+
"eval_steps_per_second": 2.383,
|
| 1947 |
"step": 380
|
| 1948 |
},
|
| 1949 |
{
|
| 1950 |
"epoch": 191.0,
|
| 1951 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1952 |
+
"eval_loss": 0.5443536043167114,
|
| 1953 |
+
"eval_runtime": 0.6405,
|
| 1954 |
+
"eval_samples_per_second": 109.293,
|
| 1955 |
+
"eval_steps_per_second": 3.123,
|
| 1956 |
"step": 382
|
| 1957 |
},
|
| 1958 |
{
|
| 1959 |
"epoch": 192.0,
|
| 1960 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1961 |
+
"eval_loss": 0.5443087816238403,
|
| 1962 |
+
"eval_runtime": 0.6431,
|
| 1963 |
+
"eval_samples_per_second": 108.85,
|
| 1964 |
+
"eval_steps_per_second": 3.11,
|
| 1965 |
"step": 384
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 193.0,
|
| 1969 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1970 |
+
"eval_loss": 0.5442724823951721,
|
| 1971 |
+
"eval_runtime": 0.8311,
|
| 1972 |
+
"eval_samples_per_second": 84.221,
|
| 1973 |
+
"eval_steps_per_second": 2.406,
|
| 1974 |
"step": 386
|
| 1975 |
},
|
| 1976 |
{
|
| 1977 |
"epoch": 194.0,
|
| 1978 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1979 |
+
"eval_loss": 0.5442416667938232,
|
| 1980 |
+
"eval_runtime": 0.6416,
|
| 1981 |
+
"eval_samples_per_second": 109.095,
|
| 1982 |
+
"eval_steps_per_second": 3.117,
|
| 1983 |
"step": 388
|
| 1984 |
},
|
| 1985 |
{
|
| 1986 |
"epoch": 195.0,
|
| 1987 |
"learning_rate": 3.125e-06,
|
| 1988 |
+
"loss": 0.6155,
|
| 1989 |
"step": 390
|
| 1990 |
},
|
| 1991 |
{
|
| 1992 |
"epoch": 195.0,
|
| 1993 |
+
"eval_accuracy": 0.8285714285714286,
|
| 1994 |
+
"eval_loss": 0.5442100763320923,
|
| 1995 |
+
"eval_runtime": 0.6472,
|
| 1996 |
+
"eval_samples_per_second": 108.158,
|
| 1997 |
+
"eval_steps_per_second": 3.09,
|
| 1998 |
"step": 390
|
| 1999 |
},
|
| 2000 |
{
|
| 2001 |
"epoch": 196.0,
|
| 2002 |
+
"eval_accuracy": 0.8285714285714286,
|
| 2003 |
+
"eval_loss": 0.5441816449165344,
|
| 2004 |
+
"eval_runtime": 0.8234,
|
| 2005 |
+
"eval_samples_per_second": 85.016,
|
| 2006 |
+
"eval_steps_per_second": 2.429,
|
| 2007 |
"step": 392
|
| 2008 |
},
|
| 2009 |
{
|
| 2010 |
"epoch": 197.0,
|
| 2011 |
+
"eval_accuracy": 0.8285714285714286,
|
| 2012 |
+
"eval_loss": 0.5441582202911377,
|
| 2013 |
+
"eval_runtime": 0.6411,
|
| 2014 |
+
"eval_samples_per_second": 109.183,
|
| 2015 |
+
"eval_steps_per_second": 3.12,
|
| 2016 |
"step": 394
|
| 2017 |
},
|
| 2018 |
{
|
| 2019 |
"epoch": 198.0,
|
| 2020 |
+
"eval_accuracy": 0.8285714285714286,
|
| 2021 |
+
"eval_loss": 0.5441429615020752,
|
| 2022 |
+
"eval_runtime": 0.6367,
|
| 2023 |
+
"eval_samples_per_second": 109.941,
|
| 2024 |
+
"eval_steps_per_second": 3.141,
|
| 2025 |
"step": 396
|
| 2026 |
},
|
| 2027 |
{
|
| 2028 |
"epoch": 199.0,
|
| 2029 |
+
"eval_accuracy": 0.8285714285714286,
|
| 2030 |
+
"eval_loss": 0.5441319346427917,
|
| 2031 |
+
"eval_runtime": 0.8204,
|
| 2032 |
+
"eval_samples_per_second": 85.32,
|
| 2033 |
+
"eval_steps_per_second": 2.438,
|
| 2034 |
"step": 398
|
| 2035 |
},
|
| 2036 |
{
|
| 2037 |
"epoch": 200.0,
|
| 2038 |
"learning_rate": 0.0,
|
| 2039 |
+
"loss": 0.6272,
|
| 2040 |
"step": 400
|
| 2041 |
},
|
| 2042 |
{
|
| 2043 |
"epoch": 200.0,
|
| 2044 |
+
"eval_accuracy": 0.8285714285714286,
|
| 2045 |
+
"eval_loss": 0.5441268086433411,
|
| 2046 |
+
"eval_runtime": 0.646,
|
| 2047 |
+
"eval_samples_per_second": 108.365,
|
| 2048 |
+
"eval_steps_per_second": 3.096,
|
| 2049 |
"step": 400
|
| 2050 |
},
|
| 2051 |
{
|
| 2052 |
"epoch": 200.0,
|
| 2053 |
"step": 400,
|
| 2054 |
"total_flos": 2.23710151698432e+18,
|
| 2055 |
+
"train_loss": 0.6791047298908234,
|
| 2056 |
+
"train_runtime": 1022.1437,
|
| 2057 |
+
"train_samples_per_second": 88.05,
|
| 2058 |
+
"train_steps_per_second": 0.391
|
| 2059 |
}
|
| 2060 |
],
|
| 2061 |
"logging_steps": 10,
|