End of training
Browse files- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +364 -0
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9674,
|
| 4 |
+
"eval_loss": 0.09441738575696945,
|
| 5 |
+
"eval_runtime": 9.1116,
|
| 6 |
+
"eval_samples_per_second": 548.751,
|
| 7 |
+
"eval_steps_per_second": 8.67,
|
| 8 |
+
"train_loss": 0.5967143625020981,
|
| 9 |
+
"train_runtime": 629.905,
|
| 10 |
+
"train_samples_per_second": 214.318,
|
| 11 |
+
"train_steps_per_second": 0.838
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9674,
|
| 4 |
+
"eval_loss": 0.09441738575696945,
|
| 5 |
+
"eval_runtime": 9.1116,
|
| 6 |
+
"eval_samples_per_second": 548.751,
|
| 7 |
+
"eval_steps_per_second": 8.67
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.5967143625020981,
|
| 4 |
+
"train_runtime": 629.905,
|
| 5 |
+
"train_samples_per_second": 214.318,
|
| 6 |
+
"train_steps_per_second": 0.838
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,364 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9674,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-528",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 528,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 9.433962264150944e-06,
|
| 13 |
+
"loss": 2.3257,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"learning_rate": 1.8867924528301888e-05,
|
| 19 |
+
"loss": 2.167,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.17,
|
| 24 |
+
"learning_rate": 2.830188679245283e-05,
|
| 25 |
+
"loss": 1.8935,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.23,
|
| 30 |
+
"learning_rate": 3.7735849056603776e-05,
|
| 31 |
+
"loss": 1.4622,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.28,
|
| 36 |
+
"learning_rate": 4.716981132075472e-05,
|
| 37 |
+
"loss": 1.1314,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.34,
|
| 42 |
+
"learning_rate": 4.926315789473684e-05,
|
| 43 |
+
"loss": 0.8737,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.4,
|
| 48 |
+
"learning_rate": 4.821052631578948e-05,
|
| 49 |
+
"loss": 0.7787,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.45,
|
| 54 |
+
"learning_rate": 4.715789473684211e-05,
|
| 55 |
+
"loss": 0.7031,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.51,
|
| 60 |
+
"learning_rate": 4.610526315789474e-05,
|
| 61 |
+
"loss": 0.6667,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.57,
|
| 66 |
+
"learning_rate": 4.5052631578947366e-05,
|
| 67 |
+
"loss": 0.6549,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.62,
|
| 72 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 73 |
+
"loss": 0.5933,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.68,
|
| 78 |
+
"learning_rate": 4.294736842105264e-05,
|
| 79 |
+
"loss": 0.5883,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.74,
|
| 84 |
+
"learning_rate": 4.1894736842105264e-05,
|
| 85 |
+
"loss": 0.5463,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.8,
|
| 90 |
+
"learning_rate": 4.08421052631579e-05,
|
| 91 |
+
"loss": 0.5061,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.85,
|
| 96 |
+
"learning_rate": 3.978947368421053e-05,
|
| 97 |
+
"loss": 0.5435,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.91,
|
| 102 |
+
"learning_rate": 3.873684210526316e-05,
|
| 103 |
+
"loss": 0.507,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.97,
|
| 108 |
+
"learning_rate": 3.768421052631579e-05,
|
| 109 |
+
"loss": 0.5329,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.0,
|
| 114 |
+
"eval_accuracy": 0.9512,
|
| 115 |
+
"eval_loss": 0.15013164281845093,
|
| 116 |
+
"eval_runtime": 9.3339,
|
| 117 |
+
"eval_samples_per_second": 535.679,
|
| 118 |
+
"eval_steps_per_second": 8.464,
|
| 119 |
+
"step": 176
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.02,
|
| 123 |
+
"learning_rate": 3.663157894736842e-05,
|
| 124 |
+
"loss": 0.5219,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.08,
|
| 129 |
+
"learning_rate": 3.5578947368421054e-05,
|
| 130 |
+
"loss": 0.4953,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.14,
|
| 135 |
+
"learning_rate": 3.452631578947369e-05,
|
| 136 |
+
"loss": 0.5238,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.19,
|
| 141 |
+
"learning_rate": 3.347368421052632e-05,
|
| 142 |
+
"loss": 0.464,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.25,
|
| 147 |
+
"learning_rate": 3.2421052631578945e-05,
|
| 148 |
+
"loss": 0.4815,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.31,
|
| 153 |
+
"learning_rate": 3.136842105263158e-05,
|
| 154 |
+
"loss": 0.4669,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.36,
|
| 159 |
+
"learning_rate": 3.0315789473684214e-05,
|
| 160 |
+
"loss": 0.4785,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.42,
|
| 165 |
+
"learning_rate": 2.9263157894736844e-05,
|
| 166 |
+
"loss": 0.46,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.48,
|
| 171 |
+
"learning_rate": 2.8210526315789476e-05,
|
| 172 |
+
"loss": 0.4394,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.53,
|
| 177 |
+
"learning_rate": 2.7157894736842106e-05,
|
| 178 |
+
"loss": 0.4578,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.59,
|
| 183 |
+
"learning_rate": 2.610526315789474e-05,
|
| 184 |
+
"loss": 0.4589,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.65,
|
| 189 |
+
"learning_rate": 2.505263157894737e-05,
|
| 190 |
+
"loss": 0.4082,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.7,
|
| 195 |
+
"learning_rate": 2.4e-05,
|
| 196 |
+
"loss": 0.4365,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.76,
|
| 201 |
+
"learning_rate": 2.294736842105263e-05,
|
| 202 |
+
"loss": 0.4381,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.82,
|
| 207 |
+
"learning_rate": 2.1894736842105266e-05,
|
| 208 |
+
"loss": 0.4151,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.88,
|
| 213 |
+
"learning_rate": 2.0842105263157895e-05,
|
| 214 |
+
"loss": 0.4214,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.93,
|
| 219 |
+
"learning_rate": 1.9789473684210528e-05,
|
| 220 |
+
"loss": 0.4351,
|
| 221 |
+
"step": 340
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.99,
|
| 225 |
+
"learning_rate": 1.8736842105263158e-05,
|
| 226 |
+
"loss": 0.3966,
|
| 227 |
+
"step": 350
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.0,
|
| 231 |
+
"eval_accuracy": 0.9636,
|
| 232 |
+
"eval_loss": 0.10934372246265411,
|
| 233 |
+
"eval_runtime": 9.2925,
|
| 234 |
+
"eval_samples_per_second": 538.07,
|
| 235 |
+
"eval_steps_per_second": 8.502,
|
| 236 |
+
"step": 352
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.05,
|
| 240 |
+
"learning_rate": 1.768421052631579e-05,
|
| 241 |
+
"loss": 0.4426,
|
| 242 |
+
"step": 360
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.1,
|
| 246 |
+
"learning_rate": 1.6631578947368423e-05,
|
| 247 |
+
"loss": 0.3918,
|
| 248 |
+
"step": 370
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.16,
|
| 252 |
+
"learning_rate": 1.5578947368421056e-05,
|
| 253 |
+
"loss": 0.3932,
|
| 254 |
+
"step": 380
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.22,
|
| 258 |
+
"learning_rate": 1.4526315789473685e-05,
|
| 259 |
+
"loss": 0.3756,
|
| 260 |
+
"step": 390
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.27,
|
| 264 |
+
"learning_rate": 1.3473684210526316e-05,
|
| 265 |
+
"loss": 0.3903,
|
| 266 |
+
"step": 400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.33,
|
| 270 |
+
"learning_rate": 1.2421052631578949e-05,
|
| 271 |
+
"loss": 0.379,
|
| 272 |
+
"step": 410
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.39,
|
| 276 |
+
"learning_rate": 1.136842105263158e-05,
|
| 277 |
+
"loss": 0.4059,
|
| 278 |
+
"step": 420
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.44,
|
| 282 |
+
"learning_rate": 1.0315789473684211e-05,
|
| 283 |
+
"loss": 0.3891,
|
| 284 |
+
"step": 430
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.5,
|
| 288 |
+
"learning_rate": 9.263157894736844e-06,
|
| 289 |
+
"loss": 0.3666,
|
| 290 |
+
"step": 440
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.56,
|
| 294 |
+
"learning_rate": 8.210526315789475e-06,
|
| 295 |
+
"loss": 0.4086,
|
| 296 |
+
"step": 450
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.61,
|
| 300 |
+
"learning_rate": 7.157894736842105e-06,
|
| 301 |
+
"loss": 0.3723,
|
| 302 |
+
"step": 460
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.67,
|
| 306 |
+
"learning_rate": 6.105263157894737e-06,
|
| 307 |
+
"loss": 0.3698,
|
| 308 |
+
"step": 470
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.73,
|
| 312 |
+
"learning_rate": 5.052631578947369e-06,
|
| 313 |
+
"loss": 0.373,
|
| 314 |
+
"step": 480
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.78,
|
| 318 |
+
"learning_rate": 4.000000000000001e-06,
|
| 319 |
+
"loss": 0.3636,
|
| 320 |
+
"step": 490
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.84,
|
| 324 |
+
"learning_rate": 2.9473684210526317e-06,
|
| 325 |
+
"loss": 0.3787,
|
| 326 |
+
"step": 500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.9,
|
| 330 |
+
"learning_rate": 1.8947368421052634e-06,
|
| 331 |
+
"loss": 0.3554,
|
| 332 |
+
"step": 510
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.95,
|
| 336 |
+
"learning_rate": 8.421052631578948e-07,
|
| 337 |
+
"loss": 0.3778,
|
| 338 |
+
"step": 520
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.0,
|
| 342 |
+
"eval_accuracy": 0.9674,
|
| 343 |
+
"eval_loss": 0.09441738575696945,
|
| 344 |
+
"eval_runtime": 9.2622,
|
| 345 |
+
"eval_samples_per_second": 539.827,
|
| 346 |
+
"eval_steps_per_second": 8.529,
|
| 347 |
+
"step": 528
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.0,
|
| 351 |
+
"step": 528,
|
| 352 |
+
"total_flos": 3.35630861217792e+18,
|
| 353 |
+
"train_loss": 0.5967143625020981,
|
| 354 |
+
"train_runtime": 629.905,
|
| 355 |
+
"train_samples_per_second": 214.318,
|
| 356 |
+
"train_steps_per_second": 0.838
|
| 357 |
+
}
|
| 358 |
+
],
|
| 359 |
+
"max_steps": 528,
|
| 360 |
+
"num_train_epochs": 3,
|
| 361 |
+
"total_flos": 3.35630861217792e+18,
|
| 362 |
+
"trial_name": null,
|
| 363 |
+
"trial_params": null
|
| 364 |
+
}
|