Training in progress, epoch 0
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +304 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.97,
|
| 3 |
+
"total_flos": 1.573510172037415e+18,
|
| 4 |
+
"train_loss": 1.3174563893732034,
|
| 5 |
+
"train_runtime": 880.088,
|
| 6 |
+
"train_samples_per_second": 23.261,
|
| 7 |
+
"train_steps_per_second": 0.181
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343290666
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc6c60fb9b9cd7b035c12b21ee73ee641d7d96247f9e9facae0c0d0eed950377
|
| 3 |
size 343290666
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.97,
|
| 3 |
+
"total_flos": 1.573510172037415e+18,
|
| 4 |
+
"train_loss": 1.3174563893732034,
|
| 5 |
+
"train_runtime": 880.088,
|
| 6 |
+
"train_samples_per_second": 23.261,
|
| 7 |
+
"train_steps_per_second": 0.181
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7335680751173709,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-type/checkpoint-372",
|
| 4 |
+
"epoch": 5.975903614457831,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 372,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.16,
|
| 13 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 14 |
+
"loss": 2.2533,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.32,
|
| 19 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 20 |
+
"loss": 2.0412,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.48,
|
| 25 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 26 |
+
"loss": 1.8051,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.64,
|
| 31 |
+
"learning_rate": 4.970059880239521e-05,
|
| 32 |
+
"loss": 1.5407,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.8,
|
| 37 |
+
"learning_rate": 4.820359281437126e-05,
|
| 38 |
+
"loss": 1.3111,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.96,
|
| 43 |
+
"learning_rate": 4.670658682634731e-05,
|
| 44 |
+
"loss": 1.1891,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.0,
|
| 49 |
+
"eval_accuracy": 0.6549295774647887,
|
| 50 |
+
"eval_loss": 1.0236921310424805,
|
| 51 |
+
"eval_runtime": 23.861,
|
| 52 |
+
"eval_samples_per_second": 71.414,
|
| 53 |
+
"eval_steps_per_second": 2.263,
|
| 54 |
+
"step": 62
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.12,
|
| 58 |
+
"learning_rate": 4.5209580838323355e-05,
|
| 59 |
+
"loss": 1.1132,
|
| 60 |
+
"step": 70
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.29,
|
| 64 |
+
"learning_rate": 4.3712574850299406e-05,
|
| 65 |
+
"loss": 1.0744,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.45,
|
| 70 |
+
"learning_rate": 4.221556886227545e-05,
|
| 71 |
+
"loss": 1.0471,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.61,
|
| 76 |
+
"learning_rate": 4.07185628742515e-05,
|
| 77 |
+
"loss": 1.0616,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.77,
|
| 82 |
+
"learning_rate": 3.9221556886227544e-05,
|
| 83 |
+
"loss": 0.9812,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.93,
|
| 88 |
+
"learning_rate": 3.7724550898203595e-05,
|
| 89 |
+
"loss": 0.9452,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.99,
|
| 94 |
+
"eval_accuracy": 0.6948356807511737,
|
| 95 |
+
"eval_loss": 0.8808437585830688,
|
| 96 |
+
"eval_runtime": 23.7153,
|
| 97 |
+
"eval_samples_per_second": 71.852,
|
| 98 |
+
"eval_steps_per_second": 2.277,
|
| 99 |
+
"step": 124
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.09,
|
| 103 |
+
"learning_rate": 3.6227544910179645e-05,
|
| 104 |
+
"loss": 0.9356,
|
| 105 |
+
"step": 130
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.25,
|
| 109 |
+
"learning_rate": 3.473053892215569e-05,
|
| 110 |
+
"loss": 0.906,
|
| 111 |
+
"step": 140
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.41,
|
| 115 |
+
"learning_rate": 3.323353293413174e-05,
|
| 116 |
+
"loss": 0.8799,
|
| 117 |
+
"step": 150
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.57,
|
| 121 |
+
"learning_rate": 3.1736526946107784e-05,
|
| 122 |
+
"loss": 0.9281,
|
| 123 |
+
"step": 160
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.73,
|
| 127 |
+
"learning_rate": 3.0239520958083834e-05,
|
| 128 |
+
"loss": 0.9325,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.89,
|
| 133 |
+
"learning_rate": 2.874251497005988e-05,
|
| 134 |
+
"loss": 0.8955,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.99,
|
| 139 |
+
"eval_accuracy": 0.7124413145539906,
|
| 140 |
+
"eval_loss": 0.8164246082305908,
|
| 141 |
+
"eval_runtime": 23.6115,
|
| 142 |
+
"eval_samples_per_second": 72.168,
|
| 143 |
+
"eval_steps_per_second": 2.287,
|
| 144 |
+
"step": 186
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.05,
|
| 148 |
+
"learning_rate": 2.724550898203593e-05,
|
| 149 |
+
"loss": 0.9305,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.21,
|
| 154 |
+
"learning_rate": 2.5748502994011976e-05,
|
| 155 |
+
"loss": 0.8252,
|
| 156 |
+
"step": 200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.37,
|
| 160 |
+
"learning_rate": 2.4251497005988023e-05,
|
| 161 |
+
"loss": 0.7959,
|
| 162 |
+
"step": 210
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.53,
|
| 166 |
+
"learning_rate": 2.275449101796407e-05,
|
| 167 |
+
"loss": 0.8614,
|
| 168 |
+
"step": 220
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.69,
|
| 172 |
+
"learning_rate": 2.125748502994012e-05,
|
| 173 |
+
"loss": 0.8008,
|
| 174 |
+
"step": 230
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.86,
|
| 178 |
+
"learning_rate": 1.9760479041916168e-05,
|
| 179 |
+
"loss": 0.8389,
|
| 180 |
+
"step": 240
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 4.0,
|
| 184 |
+
"eval_accuracy": 0.7282863849765259,
|
| 185 |
+
"eval_loss": 0.7755224108695984,
|
| 186 |
+
"eval_runtime": 23.4912,
|
| 187 |
+
"eval_samples_per_second": 72.538,
|
| 188 |
+
"eval_steps_per_second": 2.299,
|
| 189 |
+
"step": 249
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.02,
|
| 193 |
+
"learning_rate": 1.8263473053892215e-05,
|
| 194 |
+
"loss": 0.805,
|
| 195 |
+
"step": 250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.18,
|
| 199 |
+
"learning_rate": 1.6766467065868263e-05,
|
| 200 |
+
"loss": 0.7374,
|
| 201 |
+
"step": 260
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.34,
|
| 205 |
+
"learning_rate": 1.5269461077844313e-05,
|
| 206 |
+
"loss": 0.785,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.5,
|
| 211 |
+
"learning_rate": 1.377245508982036e-05,
|
| 212 |
+
"loss": 0.7534,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.66,
|
| 217 |
+
"learning_rate": 1.2275449101796408e-05,
|
| 218 |
+
"loss": 0.7473,
|
| 219 |
+
"step": 290
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.82,
|
| 223 |
+
"learning_rate": 1.0778443113772455e-05,
|
| 224 |
+
"loss": 0.7854,
|
| 225 |
+
"step": 300
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.98,
|
| 229 |
+
"learning_rate": 9.281437125748502e-06,
|
| 230 |
+
"loss": 0.8038,
|
| 231 |
+
"step": 310
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 5.0,
|
| 235 |
+
"eval_accuracy": 0.7306338028169014,
|
| 236 |
+
"eval_loss": 0.7651309370994568,
|
| 237 |
+
"eval_runtime": 23.7527,
|
| 238 |
+
"eval_samples_per_second": 71.739,
|
| 239 |
+
"eval_steps_per_second": 2.273,
|
| 240 |
+
"step": 311
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.14,
|
| 244 |
+
"learning_rate": 7.784431137724551e-06,
|
| 245 |
+
"loss": 0.7728,
|
| 246 |
+
"step": 320
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.3,
|
| 250 |
+
"learning_rate": 6.2874251497005985e-06,
|
| 251 |
+
"loss": 0.7011,
|
| 252 |
+
"step": 330
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.46,
|
| 256 |
+
"learning_rate": 4.7904191616766475e-06,
|
| 257 |
+
"loss": 0.7337,
|
| 258 |
+
"step": 340
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 5.62,
|
| 262 |
+
"learning_rate": 3.293413173652695e-06,
|
| 263 |
+
"loss": 0.7479,
|
| 264 |
+
"step": 350
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.78,
|
| 268 |
+
"learning_rate": 1.7964071856287426e-06,
|
| 269 |
+
"loss": 0.7345,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 5.94,
|
| 274 |
+
"learning_rate": 2.9940119760479047e-07,
|
| 275 |
+
"loss": 0.71,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 5.98,
|
| 280 |
+
"eval_accuracy": 0.7335680751173709,
|
| 281 |
+
"eval_loss": 0.7623339891433716,
|
| 282 |
+
"eval_runtime": 23.6551,
|
| 283 |
+
"eval_samples_per_second": 72.035,
|
| 284 |
+
"eval_steps_per_second": 2.283,
|
| 285 |
+
"step": 372
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 5.98,
|
| 289 |
+
"step": 372,
|
| 290 |
+
"total_flos": 3.6877651691946025e+18,
|
| 291 |
+
"train_loss": 0.9907107369233203,
|
| 292 |
+
"train_runtime": 1939.9637,
|
| 293 |
+
"train_samples_per_second": 24.625,
|
| 294 |
+
"train_steps_per_second": 0.192
|
| 295 |
+
}
|
| 296 |
+
],
|
| 297 |
+
"logging_steps": 10,
|
| 298 |
+
"max_steps": 372,
|
| 299 |
+
"num_train_epochs": 6,
|
| 300 |
+
"save_steps": 500,
|
| 301 |
+
"total_flos": 3.6877651691946025e+18,
|
| 302 |
+
"trial_name": null,
|
| 303 |
+
"trial_params": null
|
| 304 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b5f954316fc38b4a4f5d62a68a7490a1e2494c4dcb007244ea02ad9daf1c29d
|
| 3 |
size 4536
|