Training in progress, epoch 0
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Jan09_16-59-27_315083aa3976/events.out.tfevents.1704819633.315083aa3976.4375.3 +3 -0
- runs/Jan09_17-01-19_315083aa3976/events.out.tfevents.1704819695.315083aa3976.4375.4 +3 -0
- train_results.json +6 -6
- trainer_state.json +25 -376
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 3.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.7727272727272727,
|
| 4 |
+
"eval_loss": 0.5183508396148682,
|
| 5 |
+
"eval_runtime": 0.2754,
|
| 6 |
+
"eval_samples_per_second": 79.874,
|
| 7 |
+
"eval_steps_per_second": 3.631,
|
| 8 |
+
"total_flos": 9395563836653568.0,
|
| 9 |
+
"train_loss": 0.6626813014348348,
|
| 10 |
+
"train_runtime": 16.1154,
|
| 11 |
+
"train_samples_per_second": 35.184,
|
| 12 |
+
"train_steps_per_second": 0.186
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 3.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.7727272727272727,
|
| 4 |
+
"eval_loss": 0.5183508396148682,
|
| 5 |
+
"eval_runtime": 0.2754,
|
| 6 |
+
"eval_samples_per_second": 79.874,
|
| 7 |
+
"eval_steps_per_second": 3.631
|
| 8 |
}
|
runs/Jan09_16-59-27_315083aa3976/events.out.tfevents.1704819633.315083aa3976.4375.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ee6d45e6241026b97467a8a6322f16418348a974efe7716705de75a07a2b8fb
|
| 3 |
+
size 405
|
runs/Jan09_17-01-19_315083aa3976/events.out.tfevents.1704819695.315083aa3976.4375.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14f02194ed0f63833689f4f6f5d855f810cb9e21558a9f009c70cd44f72cde20
|
| 3 |
+
size 5084
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 9395563836653568.0,
|
| 4 |
+
"train_loss": 0.6626813014348348,
|
| 5 |
+
"train_runtime": 16.1154,
|
| 6 |
+
"train_samples_per_second": 35.184,
|
| 7 |
+
"train_steps_per_second": 0.186
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,397 +1,46 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat-kornia/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
"
|
| 19 |
-
"learning_rate": 1.7543859649122806e-05,
|
| 20 |
-
"loss": 2.1353,
|
| 21 |
-
"step": 20
|
| 22 |
-
},
|
| 23 |
-
{
|
| 24 |
-
"epoch": 0.16,
|
| 25 |
-
"learning_rate": 2.6315789473684212e-05,
|
| 26 |
-
"loss": 1.675,
|
| 27 |
-
"step": 30
|
| 28 |
-
},
|
| 29 |
-
{
|
| 30 |
-
"epoch": 0.21,
|
| 31 |
-
"learning_rate": 3.508771929824561e-05,
|
| 32 |
-
"loss": 0.9284,
|
| 33 |
-
"step": 40
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 0.26,
|
| 37 |
-
"learning_rate": 4.3859649122807014e-05,
|
| 38 |
-
"loss": 0.4401,
|
| 39 |
-
"step": 50
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 0.32,
|
| 43 |
-
"learning_rate": 4.970760233918128e-05,
|
| 44 |
-
"loss": 0.298,
|
| 45 |
-
"step": 60
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.37,
|
| 49 |
-
"learning_rate": 4.8732943469785574e-05,
|
| 50 |
-
"loss": 0.2324,
|
| 51 |
-
"step": 70
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.42,
|
| 55 |
-
"learning_rate": 4.7758284600389865e-05,
|
| 56 |
-
"loss": 0.197,
|
| 57 |
-
"step": 80
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"epoch": 0.47,
|
| 61 |
-
"learning_rate": 4.678362573099415e-05,
|
| 62 |
-
"loss": 0.1968,
|
| 63 |
-
"step": 90
|
| 64 |
-
},
|
| 65 |
-
{
|
| 66 |
-
"epoch": 0.53,
|
| 67 |
-
"learning_rate": 4.580896686159844e-05,
|
| 68 |
-
"loss": 0.1871,
|
| 69 |
-
"step": 100
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 0.58,
|
| 73 |
-
"learning_rate": 4.483430799220273e-05,
|
| 74 |
-
"loss": 0.1575,
|
| 75 |
-
"step": 110
|
| 76 |
-
},
|
| 77 |
-
{
|
| 78 |
-
"epoch": 0.63,
|
| 79 |
-
"learning_rate": 4.3859649122807014e-05,
|
| 80 |
-
"loss": 0.1613,
|
| 81 |
-
"step": 120
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 0.68,
|
| 85 |
-
"learning_rate": 4.2884990253411305e-05,
|
| 86 |
-
"loss": 0.1312,
|
| 87 |
-
"step": 130
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.74,
|
| 91 |
-
"learning_rate": 4.1910331384015596e-05,
|
| 92 |
-
"loss": 0.1433,
|
| 93 |
-
"step": 140
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.79,
|
| 97 |
-
"learning_rate": 4.093567251461988e-05,
|
| 98 |
-
"loss": 0.1181,
|
| 99 |
-
"step": 150
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 0.84,
|
| 103 |
-
"learning_rate": 3.996101364522417e-05,
|
| 104 |
-
"loss": 0.1127,
|
| 105 |
-
"step": 160
|
| 106 |
-
},
|
| 107 |
-
{
|
| 108 |
-
"epoch": 0.89,
|
| 109 |
-
"learning_rate": 3.898635477582846e-05,
|
| 110 |
-
"loss": 0.1241,
|
| 111 |
-
"step": 170
|
| 112 |
-
},
|
| 113 |
-
{
|
| 114 |
-
"epoch": 0.95,
|
| 115 |
-
"learning_rate": 3.8011695906432746e-05,
|
| 116 |
-
"loss": 0.0925,
|
| 117 |
-
"step": 180
|
| 118 |
-
},
|
| 119 |
-
{
|
| 120 |
-
"epoch": 1.0,
|
| 121 |
-
"learning_rate": 3.7037037037037037e-05,
|
| 122 |
-
"loss": 0.1099,
|
| 123 |
-
"step": 190
|
| 124 |
-
},
|
| 125 |
-
{
|
| 126 |
-
"epoch": 1.0,
|
| 127 |
-
"eval_accuracy": 0.9607407407407408,
|
| 128 |
-
"eval_loss": 0.132521852850914,
|
| 129 |
-
"eval_runtime": 28.1721,
|
| 130 |
-
"eval_samples_per_second": 95.84,
|
| 131 |
-
"eval_steps_per_second": 3.017,
|
| 132 |
-
"step": 190
|
| 133 |
-
},
|
| 134 |
-
{
|
| 135 |
-
"epoch": 1.05,
|
| 136 |
-
"learning_rate": 3.606237816764133e-05,
|
| 137 |
-
"loss": 0.0904,
|
| 138 |
-
"step": 200
|
| 139 |
-
},
|
| 140 |
-
{
|
| 141 |
-
"epoch": 1.11,
|
| 142 |
-
"learning_rate": 3.508771929824561e-05,
|
| 143 |
-
"loss": 0.0863,
|
| 144 |
-
"step": 210
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"epoch": 1.16,
|
| 148 |
-
"learning_rate": 3.41130604288499e-05,
|
| 149 |
-
"loss": 0.0928,
|
| 150 |
-
"step": 220
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 1.21,
|
| 154 |
-
"learning_rate": 3.313840155945419e-05,
|
| 155 |
-
"loss": 0.0582,
|
| 156 |
-
"step": 230
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 1.26,
|
| 160 |
-
"learning_rate": 3.216374269005848e-05,
|
| 161 |
-
"loss": 0.1032,
|
| 162 |
-
"step": 240
|
| 163 |
-
},
|
| 164 |
-
{
|
| 165 |
-
"epoch": 1.32,
|
| 166 |
-
"learning_rate": 3.118908382066277e-05,
|
| 167 |
-
"loss": 0.0785,
|
| 168 |
-
"step": 250
|
| 169 |
-
},
|
| 170 |
-
{
|
| 171 |
-
"epoch": 1.37,
|
| 172 |
-
"learning_rate": 3.0214424951267055e-05,
|
| 173 |
-
"loss": 0.0761,
|
| 174 |
-
"step": 260
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 1.42,
|
| 178 |
-
"learning_rate": 2.9239766081871346e-05,
|
| 179 |
-
"loss": 0.1002,
|
| 180 |
-
"step": 270
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"epoch": 1.47,
|
| 184 |
-
"learning_rate": 2.8265107212475634e-05,
|
| 185 |
-
"loss": 0.0582,
|
| 186 |
-
"step": 280
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 1.53,
|
| 190 |
-
"learning_rate": 2.729044834307992e-05,
|
| 191 |
-
"loss": 0.0695,
|
| 192 |
-
"step": 290
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 1.58,
|
| 196 |
-
"learning_rate": 2.6315789473684212e-05,
|
| 197 |
-
"loss": 0.0636,
|
| 198 |
-
"step": 300
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"epoch": 1.63,
|
| 202 |
-
"learning_rate": 2.53411306042885e-05,
|
| 203 |
-
"loss": 0.0729,
|
| 204 |
-
"step": 310
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 1.68,
|
| 208 |
-
"learning_rate": 2.4366471734892787e-05,
|
| 209 |
-
"loss": 0.0728,
|
| 210 |
-
"step": 320
|
| 211 |
-
},
|
| 212 |
-
{
|
| 213 |
-
"epoch": 1.74,
|
| 214 |
-
"learning_rate": 2.3391812865497074e-05,
|
| 215 |
-
"loss": 0.0722,
|
| 216 |
-
"step": 330
|
| 217 |
-
},
|
| 218 |
-
{
|
| 219 |
-
"epoch": 1.79,
|
| 220 |
-
"learning_rate": 2.2417153996101365e-05,
|
| 221 |
-
"loss": 0.0682,
|
| 222 |
-
"step": 340
|
| 223 |
-
},
|
| 224 |
-
{
|
| 225 |
-
"epoch": 1.84,
|
| 226 |
-
"learning_rate": 2.1442495126705653e-05,
|
| 227 |
-
"loss": 0.0789,
|
| 228 |
-
"step": 350
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"epoch": 1.89,
|
| 232 |
-
"learning_rate": 2.046783625730994e-05,
|
| 233 |
-
"loss": 0.068,
|
| 234 |
-
"step": 360
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 1.95,
|
| 238 |
-
"learning_rate": 1.949317738791423e-05,
|
| 239 |
-
"loss": 0.0631,
|
| 240 |
-
"step": 370
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 2.0,
|
| 244 |
-
"
|
| 245 |
-
"
|
| 246 |
-
"
|
|
|
|
|
|
|
|
|
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 2.0,
|
| 250 |
-
"
|
| 251 |
-
"
|
| 252 |
-
"
|
| 253 |
-
"
|
| 254 |
-
"
|
| 255 |
-
"
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 2.05,
|
| 259 |
-
"learning_rate": 1.7543859649122806e-05,
|
| 260 |
-
"loss": 0.0488,
|
| 261 |
-
"step": 390
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 2.11,
|
| 265 |
-
"learning_rate": 1.6569200779727097e-05,
|
| 266 |
-
"loss": 0.0588,
|
| 267 |
-
"step": 400
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 2.16,
|
| 271 |
-
"learning_rate": 1.5594541910331384e-05,
|
| 272 |
-
"loss": 0.0472,
|
| 273 |
-
"step": 410
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 2.21,
|
| 277 |
-
"learning_rate": 1.4619883040935673e-05,
|
| 278 |
-
"loss": 0.0391,
|
| 279 |
-
"step": 420
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 2.26,
|
| 283 |
-
"learning_rate": 1.364522417153996e-05,
|
| 284 |
-
"loss": 0.0475,
|
| 285 |
-
"step": 430
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 2.32,
|
| 289 |
-
"learning_rate": 1.267056530214425e-05,
|
| 290 |
-
"loss": 0.0448,
|
| 291 |
-
"step": 440
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 2.37,
|
| 295 |
-
"learning_rate": 1.1695906432748537e-05,
|
| 296 |
-
"loss": 0.0357,
|
| 297 |
-
"step": 450
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 2.42,
|
| 301 |
-
"learning_rate": 1.0721247563352826e-05,
|
| 302 |
-
"loss": 0.0408,
|
| 303 |
-
"step": 460
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 2.47,
|
| 307 |
-
"learning_rate": 9.746588693957115e-06,
|
| 308 |
-
"loss": 0.0549,
|
| 309 |
-
"step": 470
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 2.53,
|
| 313 |
-
"learning_rate": 8.771929824561403e-06,
|
| 314 |
-
"loss": 0.0442,
|
| 315 |
-
"step": 480
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 2.58,
|
| 319 |
-
"learning_rate": 7.797270955165692e-06,
|
| 320 |
-
"loss": 0.0403,
|
| 321 |
-
"step": 490
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.63,
|
| 325 |
-
"learning_rate": 6.82261208576998e-06,
|
| 326 |
-
"loss": 0.0413,
|
| 327 |
-
"step": 500
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 2.68,
|
| 331 |
-
"learning_rate": 5.8479532163742686e-06,
|
| 332 |
-
"loss": 0.0495,
|
| 333 |
-
"step": 510
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 2.74,
|
| 337 |
-
"learning_rate": 4.873294346978558e-06,
|
| 338 |
-
"loss": 0.0456,
|
| 339 |
-
"step": 520
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 2.79,
|
| 343 |
-
"learning_rate": 3.898635477582846e-06,
|
| 344 |
-
"loss": 0.0263,
|
| 345 |
-
"step": 530
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 2.84,
|
| 349 |
-
"learning_rate": 2.9239766081871343e-06,
|
| 350 |
-
"loss": 0.0301,
|
| 351 |
-
"step": 540
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"epoch": 2.89,
|
| 355 |
-
"learning_rate": 1.949317738791423e-06,
|
| 356 |
-
"loss": 0.0239,
|
| 357 |
-
"step": 550
|
| 358 |
-
},
|
| 359 |
-
{
|
| 360 |
-
"epoch": 2.95,
|
| 361 |
-
"learning_rate": 9.746588693957115e-07,
|
| 362 |
-
"loss": 0.0293,
|
| 363 |
-
"step": 560
|
| 364 |
-
},
|
| 365 |
-
{
|
| 366 |
-
"epoch": 3.0,
|
| 367 |
-
"learning_rate": 0.0,
|
| 368 |
-
"loss": 0.0319,
|
| 369 |
-
"step": 570
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 3.0,
|
| 373 |
-
"eval_accuracy": 0.9859259259259259,
|
| 374 |
-
"eval_loss": 0.04464924708008766,
|
| 375 |
-
"eval_runtime": 27.6917,
|
| 376 |
-
"eval_samples_per_second": 97.502,
|
| 377 |
-
"eval_steps_per_second": 3.07,
|
| 378 |
-
"step": 570
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 3.0,
|
| 382 |
-
"step": 570,
|
| 383 |
-
"total_flos": 1.8124066505760768e+18,
|
| 384 |
-
"train_loss": 0.2106599067386828,
|
| 385 |
-
"train_runtime": 2165.214,
|
| 386 |
-
"train_samples_per_second": 33.669,
|
| 387 |
-
"train_steps_per_second": 0.263
|
| 388 |
}
|
| 389 |
],
|
| 390 |
"logging_steps": 10,
|
| 391 |
-
"max_steps":
|
| 392 |
"num_train_epochs": 3,
|
| 393 |
"save_steps": 500,
|
| 394 |
-
"total_flos":
|
| 395 |
"trial_name": null,
|
| 396 |
"trial_params": null
|
| 397 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7727272727272727,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat-kornia/checkpoint-3",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.67,
|
| 13 |
+
"eval_accuracy": 0.5,
|
| 14 |
+
"eval_loss": 0.6792736649513245,
|
| 15 |
+
"eval_runtime": 0.244,
|
| 16 |
+
"eval_samples_per_second": 90.155,
|
| 17 |
+
"eval_steps_per_second": 4.098,
|
| 18 |
+
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.7727272727272727,
|
| 23 |
+
"eval_loss": 0.5183508396148682,
|
| 24 |
+
"eval_runtime": 0.251,
|
| 25 |
+
"eval_samples_per_second": 87.662,
|
| 26 |
+
"eval_steps_per_second": 3.985,
|
| 27 |
+
"step": 3
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 2.0,
|
| 31 |
+
"step": 3,
|
| 32 |
+
"total_flos": 9395563836653568.0,
|
| 33 |
+
"train_loss": 0.6626813014348348,
|
| 34 |
+
"train_runtime": 16.1154,
|
| 35 |
+
"train_samples_per_second": 35.184,
|
| 36 |
+
"train_steps_per_second": 0.186
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
}
|
| 38 |
],
|
| 39 |
"logging_steps": 10,
|
| 40 |
+
"max_steps": 3,
|
| 41 |
"num_train_epochs": 3,
|
| 42 |
"save_steps": 500,
|
| 43 |
+
"total_flos": 9395563836653568.0,
|
| 44 |
"trial_name": null,
|
| 45 |
"trial_params": null
|
| 46 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa50120f4373e50a41297d075a830ebaacc0fbc77a8eccca0709a18d6dd371b5
|
| 3 |
size 4664
|