Training in progress, epoch 0
Browse files- all_results.json +6 -6
- pytorch_model.bin +1 -1
- train_results.json +6 -5
- trainer_state.json +416 -1874
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 29.
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 29.57,
|
| 3 |
+
"total_flos": 1.2835906128174883e+19,
|
| 4 |
+
"train_loss": 0.46080853518317727,
|
| 5 |
+
"train_runtime": 3932.5078,
|
| 6 |
+
"train_samples_per_second": 133.22,
|
| 7 |
+
"train_steps_per_second": 0.13
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110394865
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95d775242790b26922a803a30e3e6e6002ff27ae00b7347e1cdabf391f374a77
|
| 3 |
size 110394865
|
train_results.json
CHANGED
|
@@ -1,7 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 29.
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 29.57,
|
| 3 |
+
"total_flos": 1.2835906128174883e+19,
|
| 4 |
+
"train_loss": 0.46080853518317727,
|
| 5 |
+
"train_runtime": 3932.5078,
|
| 6 |
+
"train_samples_per_second": 133.22,
|
| 7 |
+
"train_steps_per_second": 0.13
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,2059 +1,601 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-
|
| 4 |
-
"epoch": 29.
|
| 5 |
-
"global_step":
|
| 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.
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
"
|
| 24 |
-
"learning_rate": 5.102040816326531e-06,
|
| 25 |
-
"loss": 0.6747,
|
| 26 |
-
"step": 30
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 0.41,
|
| 30 |
-
"learning_rate": 6.802721088435375e-06,
|
| 31 |
-
"loss": 0.6626,
|
| 32 |
-
"step": 40
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 0.51,
|
| 36 |
-
"learning_rate": 8.503401360544217e-06,
|
| 37 |
-
"loss": 0.645,
|
| 38 |
-
"step": 50
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.61,
|
| 42 |
-
"learning_rate": 1.0204081632653061e-05,
|
| 43 |
-
"loss": 0.643,
|
| 44 |
-
"step": 60
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.71,
|
| 48 |
-
"learning_rate": 1.1904761904761905e-05,
|
| 49 |
-
"loss": 0.6353,
|
| 50 |
-
"step": 70
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 0.81,
|
| 54 |
-
"learning_rate": 1.360544217687075e-05,
|
| 55 |
-
"loss": 0.6242,
|
| 56 |
-
"step": 80
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.91,
|
| 60 |
-
"learning_rate": 1.5306122448979594e-05,
|
| 61 |
-
"loss": 0.6271,
|
| 62 |
-
"step": 90
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.99,
|
| 66 |
-
"eval_accuracy": 0.6925615412058509,
|
| 67 |
-
"eval_loss": 0.6034993529319763,
|
| 68 |
-
"eval_runtime": 291.7633,
|
| 69 |
-
"eval_samples_per_second": 38.428,
|
| 70 |
-
"eval_steps_per_second": 0.151,
|
| 71 |
-
"step": 98
|
| 72 |
-
},
|
| 73 |
-
{
|
| 74 |
-
"epoch": 1.01,
|
| 75 |
-
"learning_rate": 1.7006802721088435e-05,
|
| 76 |
-
"loss": 0.625,
|
| 77 |
-
"step": 100
|
| 78 |
-
},
|
| 79 |
-
{
|
| 80 |
-
"epoch": 1.11,
|
| 81 |
-
"learning_rate": 1.8707482993197282e-05,
|
| 82 |
-
"loss": 0.6206,
|
| 83 |
-
"step": 110
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 1.22,
|
| 87 |
-
"learning_rate": 2.0408163265306123e-05,
|
| 88 |
-
"loss": 0.6208,
|
| 89 |
-
"step": 120
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 1.32,
|
| 93 |
-
"learning_rate": 2.2108843537414966e-05,
|
| 94 |
-
"loss": 0.625,
|
| 95 |
-
"step": 130
|
| 96 |
-
},
|
| 97 |
-
{
|
| 98 |
-
"epoch": 1.42,
|
| 99 |
-
"learning_rate": 2.380952380952381e-05,
|
| 100 |
-
"loss": 0.6198,
|
| 101 |
-
"step": 140
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 1.52,
|
| 105 |
-
"learning_rate": 2.5510204081632654e-05,
|
| 106 |
-
"loss": 0.613,
|
| 107 |
-
"step": 150
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 1.62,
|
| 111 |
-
"learning_rate": 2.72108843537415e-05,
|
| 112 |
-
"loss": 0.6242,
|
| 113 |
-
"step": 160
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 1.72,
|
| 117 |
-
"learning_rate": 2.891156462585034e-05,
|
| 118 |
-
"loss": 0.616,
|
| 119 |
-
"step": 170
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 1.82,
|
| 123 |
-
"learning_rate": 3.061224489795919e-05,
|
| 124 |
-
"loss": 0.6145,
|
| 125 |
-
"step": 180
|
| 126 |
-
},
|
| 127 |
-
{
|
| 128 |
-
"epoch": 1.92,
|
| 129 |
-
"learning_rate": 3.231292517006803e-05,
|
| 130 |
-
"loss": 0.6156,
|
| 131 |
-
"step": 190
|
| 132 |
-
},
|
| 133 |
-
{
|
| 134 |
-
"epoch": 1.99,
|
| 135 |
-
"eval_accuracy": 0.7005886550124866,
|
| 136 |
-
"eval_loss": 0.5843892097473145,
|
| 137 |
-
"eval_runtime": 301.4707,
|
| 138 |
-
"eval_samples_per_second": 37.191,
|
| 139 |
-
"eval_steps_per_second": 0.146,
|
| 140 |
-
"step": 197
|
| 141 |
-
},
|
| 142 |
-
{
|
| 143 |
-
"epoch": 2.03,
|
| 144 |
-
"learning_rate": 3.401360544217687e-05,
|
| 145 |
-
"loss": 0.6069,
|
| 146 |
-
"step": 200
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 2.13,
|
| 150 |
-
"learning_rate": 3.571428571428572e-05,
|
| 151 |
-
"loss": 0.6087,
|
| 152 |
-
"step": 210
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 2.23,
|
| 156 |
-
"learning_rate": 3.7414965986394564e-05,
|
| 157 |
-
"loss": 0.6116,
|
| 158 |
-
"step": 220
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 2.33,
|
| 162 |
-
"learning_rate": 3.9115646258503405e-05,
|
| 163 |
-
"loss": 0.6085,
|
| 164 |
-
"step": 230
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 2.43,
|
| 168 |
-
"learning_rate": 4.0816326530612245e-05,
|
| 169 |
-
"loss": 0.6049,
|
| 170 |
-
"step": 240
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 2.53,
|
| 174 |
-
"learning_rate": 4.2517006802721085e-05,
|
| 175 |
-
"loss": 0.6013,
|
| 176 |
-
"step": 250
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 2.63,
|
| 180 |
-
"learning_rate": 4.421768707482993e-05,
|
| 181 |
-
"loss": 0.6009,
|
| 182 |
-
"step": 260
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 2.73,
|
| 186 |
-
"learning_rate": 4.591836734693878e-05,
|
| 187 |
-
"loss": 0.608,
|
| 188 |
-
"step": 270
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 2.84,
|
| 192 |
-
"learning_rate": 4.761904761904762e-05,
|
| 193 |
-
"loss": 0.6145,
|
| 194 |
-
"step": 280
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 2.94,
|
| 198 |
-
"learning_rate": 4.931972789115647e-05,
|
| 199 |
-
"loss": 0.6148,
|
| 200 |
-
"step": 290
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 3.0,
|
| 204 |
-
"eval_accuracy": 0.7103995718872637,
|
| 205 |
-
"eval_loss": 0.5758489966392517,
|
| 206 |
-
"eval_runtime": 290.2528,
|
| 207 |
-
"eval_samples_per_second": 38.628,
|
| 208 |
-
"eval_steps_per_second": 0.152,
|
| 209 |
-
"step": 296
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 3.04,
|
| 213 |
-
"learning_rate": 4.9886621315192745e-05,
|
| 214 |
-
"loss": 0.5965,
|
| 215 |
-
"step": 300
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 3.14,
|
| 219 |
-
"learning_rate": 4.969765684051398e-05,
|
| 220 |
-
"loss": 0.601,
|
| 221 |
-
"step": 310
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 3.24,
|
| 225 |
-
"learning_rate": 4.9508692365835225e-05,
|
| 226 |
-
"loss": 0.6087,
|
| 227 |
-
"step": 320
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 3.34,
|
| 231 |
-
"learning_rate": 4.931972789115647e-05,
|
| 232 |
-
"loss": 0.6063,
|
| 233 |
-
"step": 330
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 3.44,
|
| 237 |
-
"learning_rate": 4.9130763416477704e-05,
|
| 238 |
-
"loss": 0.6034,
|
| 239 |
-
"step": 340
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 3.54,
|
| 243 |
-
"learning_rate": 4.894179894179895e-05,
|
| 244 |
-
"loss": 0.5962,
|
| 245 |
-
"step": 350
|
| 246 |
-
},
|
| 247 |
-
{
|
| 248 |
-
"epoch": 3.65,
|
| 249 |
-
"learning_rate": 4.875283446712018e-05,
|
| 250 |
-
"loss": 0.605,
|
| 251 |
-
"step": 360
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 3.75,
|
| 255 |
-
"learning_rate": 4.8563869992441426e-05,
|
| 256 |
-
"loss": 0.5962,
|
| 257 |
-
"step": 370
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 3.85,
|
| 261 |
-
"learning_rate": 4.837490551776266e-05,
|
| 262 |
-
"loss": 0.5986,
|
| 263 |
-
"step": 380
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 3.95,
|
| 267 |
-
"learning_rate": 4.8185941043083905e-05,
|
| 268 |
-
"loss": 0.6055,
|
| 269 |
-
"step": 390
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 4.0,
|
| 273 |
-
"eval_accuracy": 0.7014805565465573,
|
| 274 |
-
"eval_loss": 0.5852587819099426,
|
| 275 |
-
"eval_runtime": 287.2656,
|
| 276 |
-
"eval_samples_per_second": 39.03,
|
| 277 |
-
"eval_steps_per_second": 0.153,
|
| 278 |
-
"step": 395
|
| 279 |
-
},
|
| 280 |
-
{
|
| 281 |
-
"epoch": 4.05,
|
| 282 |
-
"learning_rate": 4.799697656840514e-05,
|
| 283 |
-
"loss": 0.597,
|
| 284 |
-
"step": 400
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 4.15,
|
| 288 |
-
"learning_rate": 4.7808012093726384e-05,
|
| 289 |
-
"loss": 0.5931,
|
| 290 |
-
"step": 410
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 4.25,
|
| 294 |
-
"learning_rate": 4.761904761904762e-05,
|
| 295 |
-
"loss": 0.5942,
|
| 296 |
-
"step": 420
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 4.35,
|
| 300 |
-
"learning_rate": 4.7430083144368857e-05,
|
| 301 |
-
"loss": 0.5989,
|
| 302 |
-
"step": 430
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 4.46,
|
| 306 |
-
"learning_rate": 4.72411186696901e-05,
|
| 307 |
-
"loss": 0.5947,
|
| 308 |
-
"step": 440
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 4.56,
|
| 312 |
-
"learning_rate": 4.7052154195011336e-05,
|
| 313 |
-
"loss": 0.5972,
|
| 314 |
-
"step": 450
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 4.66,
|
| 318 |
-
"learning_rate": 4.686318972033258e-05,
|
| 319 |
-
"loss": 0.5864,
|
| 320 |
-
"step": 460
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 4.76,
|
| 324 |
-
"learning_rate": 4.667422524565382e-05,
|
| 325 |
-
"loss": 0.5975,
|
| 326 |
-
"step": 470
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 4.86,
|
| 330 |
-
"learning_rate": 4.648526077097506e-05,
|
| 331 |
-
"loss": 0.598,
|
| 332 |
-
"step": 480
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 4.96,
|
| 336 |
-
"learning_rate": 4.62962962962963e-05,
|
| 337 |
-
"loss": 0.5938,
|
| 338 |
-
"step": 490
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 4.99,
|
| 342 |
-
"eval_accuracy": 0.7103995718872637,
|
| 343 |
-
"eval_loss": 0.5857925415039062,
|
| 344 |
-
"eval_runtime": 270.8215,
|
| 345 |
-
"eval_samples_per_second": 41.4,
|
| 346 |
-
"eval_steps_per_second": 0.162,
|
| 347 |
-
"step": 493
|
| 348 |
-
},
|
| 349 |
-
{
|
| 350 |
-
"epoch": 5.06,
|
| 351 |
-
"learning_rate": 4.610733182161754e-05,
|
| 352 |
-
"loss": 0.5987,
|
| 353 |
-
"step": 500
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 5.16,
|
| 357 |
-
"learning_rate": 4.591836734693878e-05,
|
| 358 |
-
"loss": 0.5889,
|
| 359 |
-
"step": 510
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 5.27,
|
| 363 |
-
"learning_rate": 4.5729402872260016e-05,
|
| 364 |
-
"loss": 0.5908,
|
| 365 |
-
"step": 520
|
| 366 |
-
},
|
| 367 |
-
{
|
| 368 |
-
"epoch": 5.37,
|
| 369 |
-
"learning_rate": 4.554043839758126e-05,
|
| 370 |
-
"loss": 0.5908,
|
| 371 |
-
"step": 530
|
| 372 |
-
},
|
| 373 |
-
{
|
| 374 |
-
"epoch": 5.47,
|
| 375 |
-
"learning_rate": 4.53514739229025e-05,
|
| 376 |
-
"loss": 0.5871,
|
| 377 |
-
"step": 540
|
| 378 |
-
},
|
| 379 |
-
{
|
| 380 |
-
"epoch": 5.57,
|
| 381 |
-
"learning_rate": 4.516250944822374e-05,
|
| 382 |
-
"loss": 0.593,
|
| 383 |
-
"step": 550
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 5.67,
|
| 387 |
-
"learning_rate": 4.4973544973544974e-05,
|
| 388 |
-
"loss": 0.5891,
|
| 389 |
-
"step": 560
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 5.77,
|
| 393 |
-
"learning_rate": 4.478458049886621e-05,
|
| 394 |
-
"loss": 0.594,
|
| 395 |
-
"step": 570
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 5.87,
|
| 399 |
-
"learning_rate": 4.4595616024187454e-05,
|
| 400 |
-
"loss": 0.5924,
|
| 401 |
-
"step": 580
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 5.97,
|
| 405 |
-
"learning_rate": 4.4406651549508697e-05,
|
| 406 |
-
"loss": 0.5878,
|
| 407 |
-
"step": 590
|
| 408 |
-
},
|
| 409 |
-
{
|
| 410 |
-
"epoch": 5.99,
|
| 411 |
-
"eval_accuracy": 0.7210132001427042,
|
| 412 |
-
"eval_loss": 0.5630102753639221,
|
| 413 |
-
"eval_runtime": 271.5122,
|
| 414 |
-
"eval_samples_per_second": 41.295,
|
| 415 |
-
"eval_steps_per_second": 0.162,
|
| 416 |
-
"step": 592
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 6.08,
|
| 420 |
-
"learning_rate": 4.421768707482993e-05,
|
| 421 |
-
"loss": 0.5898,
|
| 422 |
-
"step": 600
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 6.18,
|
| 426 |
-
"learning_rate": 4.4028722600151176e-05,
|
| 427 |
-
"loss": 0.5872,
|
| 428 |
-
"step": 610
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 6.28,
|
| 432 |
-
"learning_rate": 4.383975812547241e-05,
|
| 433 |
-
"loss": 0.5885,
|
| 434 |
-
"step": 620
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 6.38,
|
| 438 |
-
"learning_rate": 4.3650793650793655e-05,
|
| 439 |
-
"loss": 0.5811,
|
| 440 |
-
"step": 630
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 6.48,
|
| 444 |
-
"learning_rate": 4.346182917611489e-05,
|
| 445 |
-
"loss": 0.5859,
|
| 446 |
-
"step": 640
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 6.58,
|
| 450 |
-
"learning_rate": 4.3272864701436134e-05,
|
| 451 |
-
"loss": 0.5914,
|
| 452 |
-
"step": 650
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch": 6.68,
|
| 456 |
-
"learning_rate": 4.308390022675737e-05,
|
| 457 |
-
"loss": 0.5867,
|
| 458 |
-
"step": 660
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 6.78,
|
| 462 |
-
"learning_rate": 4.289493575207861e-05,
|
| 463 |
-
"loss": 0.5865,
|
| 464 |
-
"step": 670
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 6.89,
|
| 468 |
-
"learning_rate": 4.2705971277399856e-05,
|
| 469 |
-
"loss": 0.5881,
|
| 470 |
-
"step": 680
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 6.99,
|
| 474 |
-
"learning_rate": 4.2517006802721085e-05,
|
| 475 |
-
"loss": 0.5873,
|
| 476 |
-
"step": 690
|
| 477 |
-
},
|
| 478 |
-
{
|
| 479 |
-
"epoch": 7.0,
|
| 480 |
-
"eval_accuracy": 0.7235997145915091,
|
| 481 |
-
"eval_loss": 0.5619792938232422,
|
| 482 |
-
"eval_runtime": 267.8238,
|
| 483 |
-
"eval_samples_per_second": 41.863,
|
| 484 |
-
"eval_steps_per_second": 0.164,
|
| 485 |
-
"step": 691
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 7.09,
|
| 489 |
-
"learning_rate": 4.232804232804233e-05,
|
| 490 |
-
"loss": 0.5803,
|
| 491 |
-
"step": 700
|
| 492 |
-
},
|
| 493 |
-
{
|
| 494 |
-
"epoch": 7.19,
|
| 495 |
-
"learning_rate": 4.2139077853363565e-05,
|
| 496 |
-
"loss": 0.5775,
|
| 497 |
-
"step": 710
|
| 498 |
-
},
|
| 499 |
-
{
|
| 500 |
-
"epoch": 7.29,
|
| 501 |
-
"learning_rate": 4.195011337868481e-05,
|
| 502 |
-
"loss": 0.5849,
|
| 503 |
-
"step": 720
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 7.39,
|
| 507 |
-
"learning_rate": 4.176114890400605e-05,
|
| 508 |
-
"loss": 0.5856,
|
| 509 |
-
"step": 730
|
| 510 |
-
},
|
| 511 |
-
{
|
| 512 |
-
"epoch": 7.49,
|
| 513 |
-
"learning_rate": 4.157218442932729e-05,
|
| 514 |
-
"loss": 0.5843,
|
| 515 |
-
"step": 740
|
| 516 |
-
},
|
| 517 |
-
{
|
| 518 |
-
"epoch": 7.59,
|
| 519 |
-
"learning_rate": 4.138321995464853e-05,
|
| 520 |
-
"loss": 0.5889,
|
| 521 |
-
"step": 750
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 7.7,
|
| 525 |
-
"learning_rate": 4.1194255479969766e-05,
|
| 526 |
-
"loss": 0.5763,
|
| 527 |
-
"step": 760
|
| 528 |
-
},
|
| 529 |
-
{
|
| 530 |
-
"epoch": 7.8,
|
| 531 |
-
"learning_rate": 4.100529100529101e-05,
|
| 532 |
-
"loss": 0.5833,
|
| 533 |
-
"step": 770
|
| 534 |
-
},
|
| 535 |
-
{
|
| 536 |
-
"epoch": 7.9,
|
| 537 |
-
"learning_rate": 4.0816326530612245e-05,
|
| 538 |
-
"loss": 0.5781,
|
| 539 |
-
"step": 780
|
| 540 |
-
},
|
| 541 |
-
{
|
| 542 |
-
"epoch": 8.0,
|
| 543 |
-
"learning_rate": 4.062736205593349e-05,
|
| 544 |
-
"loss": 0.5947,
|
| 545 |
-
"step": 790
|
| 546 |
-
},
|
| 547 |
-
{
|
| 548 |
-
"epoch": 8.0,
|
| 549 |
-
"eval_accuracy": 0.7195861576881912,
|
| 550 |
-
"eval_loss": 0.5669898390769958,
|
| 551 |
-
"eval_runtime": 271.8958,
|
| 552 |
-
"eval_samples_per_second": 41.236,
|
| 553 |
-
"eval_steps_per_second": 0.162,
|
| 554 |
-
"step": 790
|
| 555 |
-
},
|
| 556 |
-
{
|
| 557 |
-
"epoch": 8.1,
|
| 558 |
-
"learning_rate": 4.043839758125473e-05,
|
| 559 |
-
"loss": 0.5784,
|
| 560 |
-
"step": 800
|
| 561 |
-
},
|
| 562 |
-
{
|
| 563 |
-
"epoch": 8.2,
|
| 564 |
-
"learning_rate": 4.024943310657597e-05,
|
| 565 |
-
"loss": 0.578,
|
| 566 |
-
"step": 810
|
| 567 |
-
},
|
| 568 |
-
{
|
| 569 |
-
"epoch": 8.3,
|
| 570 |
-
"learning_rate": 4.006046863189721e-05,
|
| 571 |
-
"loss": 0.5888,
|
| 572 |
-
"step": 820
|
| 573 |
-
},
|
| 574 |
-
{
|
| 575 |
-
"epoch": 8.41,
|
| 576 |
-
"learning_rate": 3.987150415721844e-05,
|
| 577 |
-
"loss": 0.5828,
|
| 578 |
-
"step": 830
|
| 579 |
-
},
|
| 580 |
-
{
|
| 581 |
-
"epoch": 8.51,
|
| 582 |
-
"learning_rate": 3.968253968253968e-05,
|
| 583 |
-
"loss": 0.582,
|
| 584 |
-
"step": 840
|
| 585 |
-
},
|
| 586 |
-
{
|
| 587 |
-
"epoch": 8.61,
|
| 588 |
-
"learning_rate": 3.9493575207860925e-05,
|
| 589 |
-
"loss": 0.5817,
|
| 590 |
-
"step": 850
|
| 591 |
-
},
|
| 592 |
-
{
|
| 593 |
-
"epoch": 8.71,
|
| 594 |
-
"learning_rate": 3.930461073318216e-05,
|
| 595 |
-
"loss": 0.5729,
|
| 596 |
-
"step": 860
|
| 597 |
-
},
|
| 598 |
-
{
|
| 599 |
-
"epoch": 8.81,
|
| 600 |
-
"learning_rate": 3.9115646258503405e-05,
|
| 601 |
-
"loss": 0.5831,
|
| 602 |
-
"step": 870
|
| 603 |
-
},
|
| 604 |
-
{
|
| 605 |
-
"epoch": 8.91,
|
| 606 |
-
"learning_rate": 3.892668178382464e-05,
|
| 607 |
-
"loss": 0.5866,
|
| 608 |
-
"step": 880
|
| 609 |
-
},
|
| 610 |
-
{
|
| 611 |
-
"epoch": 8.99,
|
| 612 |
-
"eval_accuracy": 0.7265429896539422,
|
| 613 |
-
"eval_loss": 0.5592203736305237,
|
| 614 |
-
"eval_runtime": 270.4426,
|
| 615 |
-
"eval_samples_per_second": 41.458,
|
| 616 |
-
"eval_steps_per_second": 0.163,
|
| 617 |
-
"step": 888
|
| 618 |
-
},
|
| 619 |
-
{
|
| 620 |
-
"epoch": 9.01,
|
| 621 |
-
"learning_rate": 3.8737717309145884e-05,
|
| 622 |
-
"loss": 0.5808,
|
| 623 |
-
"step": 890
|
| 624 |
-
},
|
| 625 |
-
{
|
| 626 |
-
"epoch": 9.11,
|
| 627 |
-
"learning_rate": 3.854875283446712e-05,
|
| 628 |
-
"loss": 0.5863,
|
| 629 |
-
"step": 900
|
| 630 |
-
},
|
| 631 |
-
{
|
| 632 |
-
"epoch": 9.22,
|
| 633 |
-
"learning_rate": 3.835978835978836e-05,
|
| 634 |
-
"loss": 0.5783,
|
| 635 |
-
"step": 910
|
| 636 |
-
},
|
| 637 |
-
{
|
| 638 |
-
"epoch": 9.32,
|
| 639 |
-
"learning_rate": 3.81708238851096e-05,
|
| 640 |
-
"loss": 0.578,
|
| 641 |
-
"step": 920
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 9.42,
|
| 645 |
-
"learning_rate": 3.798185941043084e-05,
|
| 646 |
-
"loss": 0.569,
|
| 647 |
-
"step": 930
|
| 648 |
-
},
|
| 649 |
-
{
|
| 650 |
-
"epoch": 9.52,
|
| 651 |
-
"learning_rate": 3.7792894935752085e-05,
|
| 652 |
-
"loss": 0.5821,
|
| 653 |
-
"step": 940
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 9.62,
|
| 657 |
-
"learning_rate": 3.760393046107332e-05,
|
| 658 |
-
"loss": 0.5827,
|
| 659 |
-
"step": 950
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 9.72,
|
| 663 |
-
"learning_rate": 3.7414965986394564e-05,
|
| 664 |
-
"loss": 0.5817,
|
| 665 |
-
"step": 960
|
| 666 |
-
},
|
| 667 |
-
{
|
| 668 |
-
"epoch": 9.82,
|
| 669 |
-
"learning_rate": 3.7226001511715794e-05,
|
| 670 |
-
"loss": 0.5774,
|
| 671 |
-
"step": 970
|
| 672 |
-
},
|
| 673 |
-
{
|
| 674 |
-
"epoch": 9.92,
|
| 675 |
-
"learning_rate": 3.7037037037037037e-05,
|
| 676 |
-
"loss": 0.5807,
|
| 677 |
-
"step": 980
|
| 678 |
-
},
|
| 679 |
-
{
|
| 680 |
-
"epoch": 9.99,
|
| 681 |
-
"eval_accuracy": 0.7253835176596504,
|
| 682 |
-
"eval_loss": 0.557357132434845,
|
| 683 |
-
"eval_runtime": 270.5413,
|
| 684 |
-
"eval_samples_per_second": 41.443,
|
| 685 |
-
"eval_steps_per_second": 0.163,
|
| 686 |
-
"step": 987
|
| 687 |
-
},
|
| 688 |
-
{
|
| 689 |
-
"epoch": 10.03,
|
| 690 |
-
"learning_rate": 3.684807256235828e-05,
|
| 691 |
-
"loss": 0.5883,
|
| 692 |
-
"step": 990
|
| 693 |
-
},
|
| 694 |
-
{
|
| 695 |
-
"epoch": 10.13,
|
| 696 |
-
"learning_rate": 3.6659108087679516e-05,
|
| 697 |
-
"loss": 0.5711,
|
| 698 |
-
"step": 1000
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 10.23,
|
| 702 |
-
"learning_rate": 3.647014361300076e-05,
|
| 703 |
-
"loss": 0.5794,
|
| 704 |
-
"step": 1010
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 10.33,
|
| 708 |
-
"learning_rate": 3.6281179138321995e-05,
|
| 709 |
-
"loss": 0.5869,
|
| 710 |
-
"step": 1020
|
| 711 |
-
},
|
| 712 |
-
{
|
| 713 |
-
"epoch": 10.43,
|
| 714 |
-
"learning_rate": 3.609221466364324e-05,
|
| 715 |
-
"loss": 0.584,
|
| 716 |
-
"step": 1030
|
| 717 |
-
},
|
| 718 |
-
{
|
| 719 |
-
"epoch": 10.53,
|
| 720 |
-
"learning_rate": 3.5903250188964474e-05,
|
| 721 |
-
"loss": 0.5716,
|
| 722 |
-
"step": 1040
|
| 723 |
-
},
|
| 724 |
-
{
|
| 725 |
-
"epoch": 10.63,
|
| 726 |
-
"learning_rate": 3.571428571428572e-05,
|
| 727 |
-
"loss": 0.5783,
|
| 728 |
-
"step": 1050
|
| 729 |
-
},
|
| 730 |
-
{
|
| 731 |
-
"epoch": 10.73,
|
| 732 |
-
"learning_rate": 3.552532123960696e-05,
|
| 733 |
-
"loss": 0.577,
|
| 734 |
-
"step": 1060
|
| 735 |
-
},
|
| 736 |
-
{
|
| 737 |
-
"epoch": 10.84,
|
| 738 |
-
"learning_rate": 3.5336356764928196e-05,
|
| 739 |
-
"loss": 0.5779,
|
| 740 |
-
"step": 1070
|
| 741 |
-
},
|
| 742 |
-
{
|
| 743 |
-
"epoch": 10.94,
|
| 744 |
-
"learning_rate": 3.514739229024944e-05,
|
| 745 |
-
"loss": 0.5764,
|
| 746 |
-
"step": 1080
|
| 747 |
-
},
|
| 748 |
-
{
|
| 749 |
-
"epoch": 11.0,
|
| 750 |
-
"eval_accuracy": 0.7244916161255798,
|
| 751 |
-
"eval_loss": 0.565514862537384,
|
| 752 |
-
"eval_runtime": 273.5069,
|
| 753 |
-
"eval_samples_per_second": 40.993,
|
| 754 |
-
"eval_steps_per_second": 0.161,
|
| 755 |
-
"step": 1086
|
| 756 |
-
},
|
| 757 |
-
{
|
| 758 |
-
"epoch": 11.04,
|
| 759 |
-
"learning_rate": 3.4958427815570675e-05,
|
| 760 |
-
"loss": 0.5806,
|
| 761 |
-
"step": 1090
|
| 762 |
-
},
|
| 763 |
-
{
|
| 764 |
-
"epoch": 11.14,
|
| 765 |
-
"learning_rate": 3.476946334089191e-05,
|
| 766 |
-
"loss": 0.5779,
|
| 767 |
-
"step": 1100
|
| 768 |
-
},
|
| 769 |
-
{
|
| 770 |
-
"epoch": 11.24,
|
| 771 |
-
"learning_rate": 3.4580498866213154e-05,
|
| 772 |
-
"loss": 0.5799,
|
| 773 |
-
"step": 1110
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"epoch": 11.34,
|
| 777 |
-
"learning_rate": 3.439153439153439e-05,
|
| 778 |
-
"loss": 0.5844,
|
| 779 |
-
"step": 1120
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 11.44,
|
| 783 |
-
"learning_rate": 3.4202569916855634e-05,
|
| 784 |
-
"loss": 0.5715,
|
| 785 |
-
"step": 1130
|
| 786 |
-
},
|
| 787 |
-
{
|
| 788 |
-
"epoch": 11.54,
|
| 789 |
-
"learning_rate": 3.401360544217687e-05,
|
| 790 |
-
"loss": 0.5809,
|
| 791 |
-
"step": 1140
|
| 792 |
-
},
|
| 793 |
-
{
|
| 794 |
-
"epoch": 11.65,
|
| 795 |
-
"learning_rate": 3.382464096749811e-05,
|
| 796 |
-
"loss": 0.5695,
|
| 797 |
-
"step": 1150
|
| 798 |
-
},
|
| 799 |
-
{
|
| 800 |
-
"epoch": 11.75,
|
| 801 |
-
"learning_rate": 3.363567649281935e-05,
|
| 802 |
-
"loss": 0.576,
|
| 803 |
-
"step": 1160
|
| 804 |
-
},
|
| 805 |
-
{
|
| 806 |
-
"epoch": 11.85,
|
| 807 |
-
"learning_rate": 3.344671201814059e-05,
|
| 808 |
-
"loss": 0.5736,
|
| 809 |
-
"step": 1170
|
| 810 |
-
},
|
| 811 |
-
{
|
| 812 |
-
"epoch": 11.95,
|
| 813 |
-
"learning_rate": 3.325774754346183e-05,
|
| 814 |
-
"loss": 0.5729,
|
| 815 |
-
"step": 1180
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 12.0,
|
| 819 |
-
"eval_accuracy": 0.7236889047449162,
|
| 820 |
-
"eval_loss": 0.5611264109611511,
|
| 821 |
-
"eval_runtime": 268.1746,
|
| 822 |
-
"eval_samples_per_second": 41.809,
|
| 823 |
-
"eval_steps_per_second": 0.164,
|
| 824 |
-
"step": 1185
|
| 825 |
-
},
|
| 826 |
-
{
|
| 827 |
-
"epoch": 12.05,
|
| 828 |
-
"learning_rate": 3.306878306878307e-05,
|
| 829 |
-
"loss": 0.5775,
|
| 830 |
-
"step": 1190
|
| 831 |
-
},
|
| 832 |
-
{
|
| 833 |
-
"epoch": 12.15,
|
| 834 |
-
"learning_rate": 3.2879818594104314e-05,
|
| 835 |
-
"loss": 0.5774,
|
| 836 |
-
"step": 1200
|
| 837 |
-
},
|
| 838 |
-
{
|
| 839 |
-
"epoch": 12.25,
|
| 840 |
-
"learning_rate": 3.269085411942555e-05,
|
| 841 |
-
"loss": 0.5751,
|
| 842 |
-
"step": 1210
|
| 843 |
-
},
|
| 844 |
-
{
|
| 845 |
-
"epoch": 12.35,
|
| 846 |
-
"learning_rate": 3.250188964474679e-05,
|
| 847 |
-
"loss": 0.5767,
|
| 848 |
-
"step": 1220
|
| 849 |
-
},
|
| 850 |
-
{
|
| 851 |
-
"epoch": 12.46,
|
| 852 |
-
"learning_rate": 3.231292517006803e-05,
|
| 853 |
-
"loss": 0.5717,
|
| 854 |
-
"step": 1230
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 12.56,
|
| 858 |
-
"learning_rate": 3.2123960695389265e-05,
|
| 859 |
-
"loss": 0.5738,
|
| 860 |
-
"step": 1240
|
| 861 |
-
},
|
| 862 |
-
{
|
| 863 |
-
"epoch": 12.66,
|
| 864 |
-
"learning_rate": 3.193499622071051e-05,
|
| 865 |
-
"loss": 0.5749,
|
| 866 |
-
"step": 1250
|
| 867 |
-
},
|
| 868 |
-
{
|
| 869 |
-
"epoch": 12.76,
|
| 870 |
-
"learning_rate": 3.1746031746031745e-05,
|
| 871 |
-
"loss": 0.5741,
|
| 872 |
-
"step": 1260
|
| 873 |
-
},
|
| 874 |
-
{
|
| 875 |
-
"epoch": 12.86,
|
| 876 |
-
"learning_rate": 3.155706727135299e-05,
|
| 877 |
-
"loss": 0.5789,
|
| 878 |
-
"step": 1270
|
| 879 |
-
},
|
| 880 |
-
{
|
| 881 |
-
"epoch": 12.96,
|
| 882 |
-
"learning_rate": 3.1368102796674224e-05,
|
| 883 |
-
"loss": 0.577,
|
| 884 |
-
"step": 1280
|
| 885 |
-
},
|
| 886 |
-
{
|
| 887 |
-
"epoch": 12.99,
|
| 888 |
-
"eval_accuracy": 0.7188726364609347,
|
| 889 |
-
"eval_loss": 0.5702112913131714,
|
| 890 |
-
"eval_runtime": 267.6574,
|
| 891 |
-
"eval_samples_per_second": 41.889,
|
| 892 |
-
"eval_steps_per_second": 0.164,
|
| 893 |
-
"step": 1283
|
| 894 |
-
},
|
| 895 |
-
{
|
| 896 |
-
"epoch": 13.06,
|
| 897 |
-
"learning_rate": 3.117913832199547e-05,
|
| 898 |
-
"loss": 0.5767,
|
| 899 |
-
"step": 1290
|
| 900 |
-
},
|
| 901 |
-
{
|
| 902 |
-
"epoch": 13.16,
|
| 903 |
-
"learning_rate": 3.09901738473167e-05,
|
| 904 |
-
"loss": 0.5727,
|
| 905 |
-
"step": 1300
|
| 906 |
-
},
|
| 907 |
-
{
|
| 908 |
-
"epoch": 13.27,
|
| 909 |
-
"learning_rate": 3.0801209372637946e-05,
|
| 910 |
-
"loss": 0.5702,
|
| 911 |
-
"step": 1310
|
| 912 |
-
},
|
| 913 |
-
{
|
| 914 |
-
"epoch": 13.37,
|
| 915 |
-
"learning_rate": 3.061224489795919e-05,
|
| 916 |
-
"loss": 0.5768,
|
| 917 |
-
"step": 1320
|
| 918 |
-
},
|
| 919 |
-
{
|
| 920 |
-
"epoch": 13.47,
|
| 921 |
-
"learning_rate": 3.0423280423280425e-05,
|
| 922 |
-
"loss": 0.5708,
|
| 923 |
-
"step": 1330
|
| 924 |
-
},
|
| 925 |
-
{
|
| 926 |
-
"epoch": 13.57,
|
| 927 |
-
"learning_rate": 3.0234315948601665e-05,
|
| 928 |
-
"loss": 0.5708,
|
| 929 |
-
"step": 1340
|
| 930 |
-
},
|
| 931 |
-
{
|
| 932 |
-
"epoch": 13.67,
|
| 933 |
-
"learning_rate": 3.0045351473922904e-05,
|
| 934 |
-
"loss": 0.5677,
|
| 935 |
-
"step": 1350
|
| 936 |
-
},
|
| 937 |
-
{
|
| 938 |
-
"epoch": 13.77,
|
| 939 |
-
"learning_rate": 2.9856386999244147e-05,
|
| 940 |
-
"loss": 0.5755,
|
| 941 |
-
"step": 1360
|
| 942 |
-
},
|
| 943 |
-
{
|
| 944 |
-
"epoch": 13.87,
|
| 945 |
-
"learning_rate": 2.9667422524565387e-05,
|
| 946 |
-
"loss": 0.5731,
|
| 947 |
-
"step": 1370
|
| 948 |
-
},
|
| 949 |
-
{
|
| 950 |
-
"epoch": 13.97,
|
| 951 |
-
"learning_rate": 2.947845804988662e-05,
|
| 952 |
-
"loss": 0.5702,
|
| 953 |
-
"step": 1380
|
| 954 |
-
},
|
| 955 |
-
{
|
| 956 |
-
"epoch": 13.99,
|
| 957 |
-
"eval_accuracy": 0.7259186585800927,
|
| 958 |
-
"eval_loss": 0.5587979555130005,
|
| 959 |
-
"eval_runtime": 267.9851,
|
| 960 |
-
"eval_samples_per_second": 41.838,
|
| 961 |
-
"eval_steps_per_second": 0.164,
|
| 962 |
-
"step": 1382
|
| 963 |
-
},
|
| 964 |
-
{
|
| 965 |
-
"epoch": 14.08,
|
| 966 |
-
"learning_rate": 2.928949357520786e-05,
|
| 967 |
-
"loss": 0.5713,
|
| 968 |
-
"step": 1390
|
| 969 |
-
},
|
| 970 |
-
{
|
| 971 |
-
"epoch": 14.18,
|
| 972 |
-
"learning_rate": 2.91005291005291e-05,
|
| 973 |
-
"loss": 0.5648,
|
| 974 |
-
"step": 1400
|
| 975 |
-
},
|
| 976 |
-
{
|
| 977 |
-
"epoch": 14.28,
|
| 978 |
-
"learning_rate": 2.891156462585034e-05,
|
| 979 |
-
"loss": 0.5715,
|
| 980 |
-
"step": 1410
|
| 981 |
-
},
|
| 982 |
-
{
|
| 983 |
-
"epoch": 14.38,
|
| 984 |
-
"learning_rate": 2.872260015117158e-05,
|
| 985 |
-
"loss": 0.5711,
|
| 986 |
-
"step": 1420
|
| 987 |
-
},
|
| 988 |
-
{
|
| 989 |
-
"epoch": 14.48,
|
| 990 |
-
"learning_rate": 2.853363567649282e-05,
|
| 991 |
-
"loss": 0.5598,
|
| 992 |
-
"step": 1430
|
| 993 |
-
},
|
| 994 |
-
{
|
| 995 |
-
"epoch": 14.58,
|
| 996 |
-
"learning_rate": 2.834467120181406e-05,
|
| 997 |
-
"loss": 0.5746,
|
| 998 |
-
"step": 1440
|
| 999 |
-
},
|
| 1000 |
-
{
|
| 1001 |
-
"epoch": 14.68,
|
| 1002 |
-
"learning_rate": 2.81557067271353e-05,
|
| 1003 |
-
"loss": 0.5702,
|
| 1004 |
-
"step": 1450
|
| 1005 |
-
},
|
| 1006 |
-
{
|
| 1007 |
-
"epoch": 14.78,
|
| 1008 |
-
"learning_rate": 2.796674225245654e-05,
|
| 1009 |
-
"loss": 0.58,
|
| 1010 |
-
"step": 1460
|
| 1011 |
-
},
|
| 1012 |
-
{
|
| 1013 |
-
"epoch": 14.89,
|
| 1014 |
-
"learning_rate": 2.777777777777778e-05,
|
| 1015 |
-
"loss": 0.5706,
|
| 1016 |
-
"step": 1470
|
| 1017 |
-
},
|
| 1018 |
-
{
|
| 1019 |
-
"epoch": 14.99,
|
| 1020 |
-
"learning_rate": 2.758881330309902e-05,
|
| 1021 |
-
"loss": 0.5717,
|
| 1022 |
-
"step": 1480
|
| 1023 |
-
},
|
| 1024 |
-
{
|
| 1025 |
-
"epoch": 15.0,
|
| 1026 |
-
"eval_accuracy": 0.7244024259721726,
|
| 1027 |
-
"eval_loss": 0.5564510226249695,
|
| 1028 |
-
"eval_runtime": 273.2108,
|
| 1029 |
-
"eval_samples_per_second": 41.038,
|
| 1030 |
-
"eval_steps_per_second": 0.161,
|
| 1031 |
-
"step": 1481
|
| 1032 |
-
},
|
| 1033 |
-
{
|
| 1034 |
-
"epoch": 15.09,
|
| 1035 |
-
"learning_rate": 2.739984882842026e-05,
|
| 1036 |
-
"loss": 0.5678,
|
| 1037 |
-
"step": 1490
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
-
"epoch":
|
| 1041 |
-
"learning_rate":
|
| 1042 |
-
"loss": 0.
|
| 1043 |
-
"step":
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
-
"epoch":
|
| 1047 |
-
"learning_rate": 2.
|
| 1048 |
-
"loss": 0.
|
| 1049 |
-
"step":
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
-
"epoch":
|
| 1053 |
-
"
|
| 1054 |
-
"
|
| 1055 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
-
"epoch":
|
| 1059 |
-
"learning_rate":
|
| 1060 |
-
"loss": 0.
|
| 1061 |
-
"step":
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
-
"epoch":
|
| 1065 |
-
"learning_rate":
|
| 1066 |
-
"loss": 0.
|
| 1067 |
-
"step":
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
-
"epoch":
|
| 1071 |
-
"
|
| 1072 |
-
"
|
| 1073 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
-
"epoch":
|
| 1077 |
-
"learning_rate":
|
| 1078 |
-
"loss": 0.
|
| 1079 |
-
"step":
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
-
"epoch":
|
| 1083 |
-
"
|
| 1084 |
-
"
|
| 1085 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
-
"epoch":
|
| 1089 |
-
"learning_rate":
|
| 1090 |
-
"loss": 0.
|
| 1091 |
-
"step":
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
-
"epoch":
|
| 1095 |
-
"
|
| 1096 |
-
"
|
| 1097 |
-
"
|
| 1098 |
-
"eval_samples_per_second": 41.459,
|
| 1099 |
-
"eval_steps_per_second": 0.163,
|
| 1100 |
-
"step": 1580
|
| 1101 |
},
|
| 1102 |
{
|
| 1103 |
-
"epoch":
|
| 1104 |
-
"
|
| 1105 |
-
"
|
| 1106 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
-
"epoch":
|
| 1110 |
-
"learning_rate":
|
| 1111 |
-
"loss": 0.
|
| 1112 |
-
"step":
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
-
"epoch":
|
| 1116 |
-
"learning_rate":
|
| 1117 |
-
"loss": 0.
|
| 1118 |
-
"step":
|
| 1119 |
},
|
| 1120 |
{
|
| 1121 |
-
"epoch":
|
| 1122 |
-
"
|
| 1123 |
-
"
|
| 1124 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1125 |
},
|
| 1126 |
{
|
| 1127 |
-
"epoch":
|
| 1128 |
-
"learning_rate":
|
| 1129 |
-
"loss": 0.
|
| 1130 |
-
"step":
|
| 1131 |
},
|
| 1132 |
{
|
| 1133 |
-
"epoch":
|
| 1134 |
-
"learning_rate":
|
| 1135 |
-
"loss": 0.
|
| 1136 |
-
"step":
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
-
"epoch":
|
| 1140 |
-
"
|
| 1141 |
-
"
|
| 1142 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1143 |
},
|
| 1144 |
{
|
| 1145 |
-
"epoch":
|
| 1146 |
-
"learning_rate":
|
| 1147 |
-
"loss": 0.
|
| 1148 |
-
"step":
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
-
"epoch":
|
| 1152 |
-
"
|
| 1153 |
-
"
|
| 1154 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1155 |
},
|
| 1156 |
{
|
| 1157 |
-
"epoch":
|
| 1158 |
-
"
|
| 1159 |
-
"
|
| 1160 |
-
"
|
| 1161 |
-
"eval_samples_per_second": 41.53,
|
| 1162 |
-
"eval_steps_per_second": 0.163,
|
| 1163 |
-
"step": 1678
|
| 1164 |
},
|
| 1165 |
{
|
| 1166 |
-
"epoch":
|
| 1167 |
-
"learning_rate":
|
| 1168 |
-
"loss": 0.
|
| 1169 |
-
"step":
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
-
"epoch":
|
| 1173 |
-
"
|
| 1174 |
-
"
|
| 1175 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1176 |
},
|
| 1177 |
{
|
| 1178 |
-
"epoch":
|
| 1179 |
-
"learning_rate":
|
| 1180 |
-
"loss": 0.
|
| 1181 |
-
"step":
|
| 1182 |
},
|
| 1183 |
{
|
| 1184 |
-
"epoch":
|
| 1185 |
-
"learning_rate":
|
| 1186 |
-
"loss": 0.
|
| 1187 |
-
"step":
|
| 1188 |
},
|
| 1189 |
{
|
| 1190 |
-
"epoch":
|
| 1191 |
-
"
|
| 1192 |
-
"
|
| 1193 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
-
"epoch":
|
| 1197 |
-
"learning_rate":
|
| 1198 |
-
"loss": 0.
|
| 1199 |
-
"step":
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
-
"epoch":
|
| 1203 |
-
"
|
| 1204 |
-
"
|
| 1205 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
-
"epoch":
|
| 1209 |
-
"learning_rate":
|
| 1210 |
-
"loss": 0.
|
| 1211 |
-
"step":
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
-
"epoch":
|
| 1215 |
-
"learning_rate":
|
| 1216 |
-
"loss": 0.
|
| 1217 |
-
"step":
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
-
"epoch":
|
| 1221 |
-
"
|
| 1222 |
-
"
|
| 1223 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
-
"epoch": 17
|
| 1227 |
-
"
|
| 1228 |
-
"
|
| 1229 |
-
"
|
| 1230 |
-
"eval_samples_per_second": 41.984,
|
| 1231 |
-
"eval_steps_per_second": 0.165,
|
| 1232 |
-
"step": 1777
|
| 1233 |
},
|
| 1234 |
{
|
| 1235 |
-
"epoch":
|
| 1236 |
-
"learning_rate":
|
| 1237 |
-
"loss": 0.
|
| 1238 |
-
"step":
|
| 1239 |
},
|
| 1240 |
{
|
| 1241 |
-
"epoch":
|
| 1242 |
-
"
|
| 1243 |
-
"
|
| 1244 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1245 |
},
|
| 1246 |
{
|
| 1247 |
-
"epoch":
|
| 1248 |
-
"learning_rate":
|
| 1249 |
-
"loss": 0.
|
| 1250 |
-
"step":
|
| 1251 |
},
|
| 1252 |
{
|
| 1253 |
-
"epoch":
|
| 1254 |
-
"learning_rate": 2.
|
| 1255 |
-
"loss": 0.
|
| 1256 |
-
"step":
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
-
"epoch":
|
| 1260 |
-
"
|
| 1261 |
-
"
|
| 1262 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1263 |
},
|
| 1264 |
{
|
| 1265 |
-
"epoch":
|
| 1266 |
-
"learning_rate": 2.
|
| 1267 |
-
"loss": 0.
|
| 1268 |
-
"step":
|
| 1269 |
},
|
| 1270 |
{
|
| 1271 |
-
"epoch":
|
| 1272 |
-
"
|
| 1273 |
-
"
|
| 1274 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
-
"epoch":
|
| 1278 |
-
"learning_rate": 2.
|
| 1279 |
-
"loss": 0.
|
| 1280 |
-
"step":
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
-
"epoch":
|
| 1284 |
-
"learning_rate": 2.
|
| 1285 |
-
"loss": 0.
|
| 1286 |
-
"step":
|
| 1287 |
},
|
| 1288 |
{
|
| 1289 |
-
"epoch":
|
| 1290 |
-
"
|
| 1291 |
-
"
|
| 1292 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
-
"epoch":
|
| 1296 |
-
"
|
| 1297 |
-
"
|
| 1298 |
-
"
|
| 1299 |
-
"eval_samples_per_second": 41.079,
|
| 1300 |
-
"eval_steps_per_second": 0.161,
|
| 1301 |
-
"step": 1876
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
-
"epoch":
|
| 1305 |
-
"learning_rate": 2.
|
| 1306 |
-
"loss": 0.
|
| 1307 |
-
"step":
|
| 1308 |
},
|
| 1309 |
{
|
| 1310 |
-
"epoch":
|
| 1311 |
-
"
|
| 1312 |
-
"
|
| 1313 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
-
"epoch":
|
| 1317 |
-
"learning_rate":
|
| 1318 |
-
"loss": 0.
|
| 1319 |
-
"step":
|
| 1320 |
},
|
| 1321 |
{
|
| 1322 |
-
"epoch":
|
| 1323 |
-
"learning_rate":
|
| 1324 |
-
"loss": 0.
|
| 1325 |
-
"step":
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
-
"epoch":
|
| 1329 |
-
"
|
| 1330 |
-
"
|
| 1331 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
-
"epoch":
|
| 1335 |
-
"learning_rate":
|
| 1336 |
-
"loss": 0.
|
| 1337 |
-
"step":
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
-
"epoch":
|
| 1341 |
-
"
|
| 1342 |
-
"
|
| 1343 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
-
"epoch": 19.
|
| 1347 |
-
"learning_rate": 1.
|
| 1348 |
-
"loss": 0.
|
| 1349 |
-
"step":
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
-
"epoch": 19.
|
| 1353 |
"learning_rate": 1.8518518518518518e-05,
|
| 1354 |
-
"loss": 0.
|
| 1355 |
-
"step":
|
| 1356 |
-
},
|
| 1357 |
-
{
|
| 1358 |
-
"epoch": 19.95,
|
| 1359 |
-
"learning_rate": 1.8329554043839758e-05,
|
| 1360 |
-
"loss": 0.5617,
|
| 1361 |
-
"step": 1970
|
| 1362 |
},
|
| 1363 |
{
|
| 1364 |
"epoch": 20.0,
|
| 1365 |
-
"eval_accuracy": 0.
|
| 1366 |
-
"eval_loss": 0.
|
| 1367 |
-
"eval_runtime":
|
| 1368 |
-
"eval_samples_per_second":
|
| 1369 |
-
"eval_steps_per_second": 0.
|
| 1370 |
-
"step":
|
| 1371 |
-
},
|
| 1372 |
-
{
|
| 1373 |
-
"epoch": 20.05,
|
| 1374 |
-
"learning_rate": 1.8140589569160997e-05,
|
| 1375 |
-
"loss": 0.5541,
|
| 1376 |
-
"step": 1980
|
| 1377 |
-
},
|
| 1378 |
-
{
|
| 1379 |
-
"epoch": 20.15,
|
| 1380 |
-
"learning_rate": 1.7951625094482237e-05,
|
| 1381 |
-
"loss": 0.5693,
|
| 1382 |
-
"step": 1990
|
| 1383 |
-
},
|
| 1384 |
-
{
|
| 1385 |
-
"epoch": 20.25,
|
| 1386 |
-
"learning_rate": 1.776266061980348e-05,
|
| 1387 |
-
"loss": 0.5652,
|
| 1388 |
-
"step": 2000
|
| 1389 |
},
|
| 1390 |
{
|
| 1391 |
-
"epoch": 20.
|
| 1392 |
-
"learning_rate": 1.
|
| 1393 |
-
"loss": 0.
|
| 1394 |
-
"step":
|
| 1395 |
-
},
|
| 1396 |
-
{
|
| 1397 |
-
"epoch": 20.46,
|
| 1398 |
-
"learning_rate": 1.7384731670445956e-05,
|
| 1399 |
-
"loss": 0.5597,
|
| 1400 |
-
"step": 2020
|
| 1401 |
-
},
|
| 1402 |
-
{
|
| 1403 |
-
"epoch": 20.56,
|
| 1404 |
-
"learning_rate": 1.7195767195767195e-05,
|
| 1405 |
-
"loss": 0.5674,
|
| 1406 |
-
"step": 2030
|
| 1407 |
-
},
|
| 1408 |
-
{
|
| 1409 |
-
"epoch": 20.66,
|
| 1410 |
-
"learning_rate": 1.7006802721088435e-05,
|
| 1411 |
-
"loss": 0.5634,
|
| 1412 |
-
"step": 2040
|
| 1413 |
-
},
|
| 1414 |
-
{
|
| 1415 |
-
"epoch": 20.76,
|
| 1416 |
-
"learning_rate": 1.6817838246409674e-05,
|
| 1417 |
-
"loss": 0.567,
|
| 1418 |
-
"step": 2050
|
| 1419 |
-
},
|
| 1420 |
-
{
|
| 1421 |
-
"epoch": 20.86,
|
| 1422 |
-
"learning_rate": 1.6628873771730914e-05,
|
| 1423 |
-
"loss": 0.5571,
|
| 1424 |
-
"step": 2060
|
| 1425 |
},
|
| 1426 |
{
|
| 1427 |
-
"epoch": 20.
|
| 1428 |
-
"learning_rate": 1.
|
| 1429 |
-
"loss": 0.
|
| 1430 |
-
"step":
|
| 1431 |
},
|
| 1432 |
{
|
| 1433 |
"epoch": 20.99,
|
| 1434 |
-
"eval_accuracy": 0.
|
| 1435 |
-
"eval_loss": 0.
|
| 1436 |
-
"eval_runtime":
|
| 1437 |
-
"eval_samples_per_second":
|
| 1438 |
-
"eval_steps_per_second": 0.
|
| 1439 |
-
"step":
|
| 1440 |
-
},
|
| 1441 |
-
{
|
| 1442 |
-
"epoch": 21.06,
|
| 1443 |
-
"learning_rate": 1.6250944822373397e-05,
|
| 1444 |
-
"loss": 0.5589,
|
| 1445 |
-
"step": 2080
|
| 1446 |
-
},
|
| 1447 |
-
{
|
| 1448 |
-
"epoch": 21.16,
|
| 1449 |
-
"learning_rate": 1.6061980347694633e-05,
|
| 1450 |
-
"loss": 0.5658,
|
| 1451 |
-
"step": 2090
|
| 1452 |
},
|
| 1453 |
{
|
| 1454 |
-
"epoch": 21.
|
| 1455 |
-
"learning_rate": 1.
|
| 1456 |
-
"loss": 0.
|
| 1457 |
-
"step":
|
| 1458 |
-
},
|
| 1459 |
-
{
|
| 1460 |
-
"epoch": 21.37,
|
| 1461 |
-
"learning_rate": 1.5684051398337112e-05,
|
| 1462 |
-
"loss": 0.5618,
|
| 1463 |
-
"step": 2110
|
| 1464 |
-
},
|
| 1465 |
-
{
|
| 1466 |
-
"epoch": 21.47,
|
| 1467 |
-
"learning_rate": 1.549508692365835e-05,
|
| 1468 |
-
"loss": 0.5624,
|
| 1469 |
-
"step": 2120
|
| 1470 |
-
},
|
| 1471 |
-
{
|
| 1472 |
-
"epoch": 21.57,
|
| 1473 |
-
"learning_rate": 1.5306122448979594e-05,
|
| 1474 |
-
"loss": 0.5619,
|
| 1475 |
-
"step": 2130
|
| 1476 |
-
},
|
| 1477 |
-
{
|
| 1478 |
-
"epoch": 21.67,
|
| 1479 |
-
"learning_rate": 1.5117157974300832e-05,
|
| 1480 |
-
"loss": 0.5554,
|
| 1481 |
-
"step": 2140
|
| 1482 |
-
},
|
| 1483 |
-
{
|
| 1484 |
-
"epoch": 21.77,
|
| 1485 |
-
"learning_rate": 1.4928193499622074e-05,
|
| 1486 |
-
"loss": 0.5539,
|
| 1487 |
-
"step": 2150
|
| 1488 |
-
},
|
| 1489 |
-
{
|
| 1490 |
-
"epoch": 21.87,
|
| 1491 |
-
"learning_rate": 1.473922902494331e-05,
|
| 1492 |
-
"loss": 0.5657,
|
| 1493 |
-
"step": 2160
|
| 1494 |
},
|
| 1495 |
{
|
| 1496 |
"epoch": 21.97,
|
| 1497 |
-
"
|
| 1498 |
-
"
|
| 1499 |
-
"
|
| 1500 |
-
|
| 1501 |
-
|
| 1502 |
-
"
|
| 1503 |
-
"eval_accuracy": 0.7314484480913307,
|
| 1504 |
-
"eval_loss": 0.5537222623825073,
|
| 1505 |
-
"eval_runtime": 267.4411,
|
| 1506 |
-
"eval_samples_per_second": 41.923,
|
| 1507 |
-
"eval_steps_per_second": 0.165,
|
| 1508 |
-
"step": 2172
|
| 1509 |
-
},
|
| 1510 |
-
{
|
| 1511 |
-
"epoch": 22.08,
|
| 1512 |
-
"learning_rate": 1.436130007558579e-05,
|
| 1513 |
-
"loss": 0.554,
|
| 1514 |
-
"step": 2180
|
| 1515 |
-
},
|
| 1516 |
-
{
|
| 1517 |
-
"epoch": 22.18,
|
| 1518 |
-
"learning_rate": 1.417233560090703e-05,
|
| 1519 |
-
"loss": 0.569,
|
| 1520 |
-
"step": 2190
|
| 1521 |
-
},
|
| 1522 |
-
{
|
| 1523 |
-
"epoch": 22.28,
|
| 1524 |
-
"learning_rate": 1.398337112622827e-05,
|
| 1525 |
-
"loss": 0.5528,
|
| 1526 |
-
"step": 2200
|
| 1527 |
-
},
|
| 1528 |
-
{
|
| 1529 |
-
"epoch": 22.38,
|
| 1530 |
-
"learning_rate": 1.379440665154951e-05,
|
| 1531 |
-
"loss": 0.5649,
|
| 1532 |
-
"step": 2210
|
| 1533 |
-
},
|
| 1534 |
-
{
|
| 1535 |
-
"epoch": 22.48,
|
| 1536 |
-
"learning_rate": 1.360544217687075e-05,
|
| 1537 |
-
"loss": 0.5586,
|
| 1538 |
-
"step": 2220
|
| 1539 |
-
},
|
| 1540 |
-
{
|
| 1541 |
-
"epoch": 22.58,
|
| 1542 |
-
"learning_rate": 1.3416477702191987e-05,
|
| 1543 |
-
"loss": 0.5606,
|
| 1544 |
-
"step": 2230
|
| 1545 |
-
},
|
| 1546 |
-
{
|
| 1547 |
-
"epoch": 22.68,
|
| 1548 |
-
"learning_rate": 1.3227513227513228e-05,
|
| 1549 |
-
"loss": 0.5551,
|
| 1550 |
-
"step": 2240
|
| 1551 |
-
},
|
| 1552 |
-
{
|
| 1553 |
-
"epoch": 22.78,
|
| 1554 |
-
"learning_rate": 1.3038548752834468e-05,
|
| 1555 |
-
"loss": 0.5588,
|
| 1556 |
-
"step": 2250
|
| 1557 |
-
},
|
| 1558 |
-
{
|
| 1559 |
-
"epoch": 22.89,
|
| 1560 |
-
"learning_rate": 1.2849584278155707e-05,
|
| 1561 |
-
"loss": 0.5591,
|
| 1562 |
-
"step": 2260
|
| 1563 |
},
|
| 1564 |
{
|
| 1565 |
-
"epoch": 22.
|
| 1566 |
-
"learning_rate": 1.
|
| 1567 |
-
"loss": 0.
|
| 1568 |
-
"step":
|
| 1569 |
},
|
| 1570 |
{
|
| 1571 |
-
"epoch":
|
| 1572 |
-
"
|
| 1573 |
-
"
|
| 1574 |
-
"
|
| 1575 |
-
"eval_samples_per_second": 41.485,
|
| 1576 |
-
"eval_steps_per_second": 0.163,
|
| 1577 |
-
"step": 2271
|
| 1578 |
},
|
| 1579 |
{
|
| 1580 |
-
"epoch":
|
| 1581 |
-
"
|
| 1582 |
-
"
|
| 1583 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1584 |
},
|
| 1585 |
{
|
| 1586 |
"epoch": 23.19,
|
| 1587 |
-
"learning_rate": 1.
|
| 1588 |
-
"loss": 0.
|
| 1589 |
-
"step":
|
| 1590 |
-
},
|
| 1591 |
-
{
|
| 1592 |
-
"epoch": 23.29,
|
| 1593 |
-
"learning_rate": 1.2093726379440666e-05,
|
| 1594 |
-
"loss": 0.5495,
|
| 1595 |
-
"step": 2300
|
| 1596 |
-
},
|
| 1597 |
-
{
|
| 1598 |
-
"epoch": 23.39,
|
| 1599 |
-
"learning_rate": 1.1904761904761905e-05,
|
| 1600 |
-
"loss": 0.5571,
|
| 1601 |
-
"step": 2310
|
| 1602 |
-
},
|
| 1603 |
-
{
|
| 1604 |
-
"epoch": 23.49,
|
| 1605 |
-
"learning_rate": 1.1715797430083145e-05,
|
| 1606 |
-
"loss": 0.5545,
|
| 1607 |
-
"step": 2320
|
| 1608 |
-
},
|
| 1609 |
-
{
|
| 1610 |
-
"epoch": 23.59,
|
| 1611 |
-
"learning_rate": 1.1526832955404384e-05,
|
| 1612 |
-
"loss": 0.5625,
|
| 1613 |
-
"step": 2330
|
| 1614 |
-
},
|
| 1615 |
-
{
|
| 1616 |
-
"epoch": 23.7,
|
| 1617 |
-
"learning_rate": 1.1337868480725626e-05,
|
| 1618 |
-
"loss": 0.5573,
|
| 1619 |
-
"step": 2340
|
| 1620 |
-
},
|
| 1621 |
-
{
|
| 1622 |
-
"epoch": 23.8,
|
| 1623 |
-
"learning_rate": 1.1148904006046863e-05,
|
| 1624 |
-
"loss": 0.5623,
|
| 1625 |
-
"step": 2350
|
| 1626 |
-
},
|
| 1627 |
-
{
|
| 1628 |
-
"epoch": 23.9,
|
| 1629 |
-
"learning_rate": 1.0959939531368103e-05,
|
| 1630 |
-
"loss": 0.5527,
|
| 1631 |
-
"step": 2360
|
| 1632 |
},
|
| 1633 |
{
|
| 1634 |
-
"epoch":
|
| 1635 |
-
"learning_rate": 1.
|
| 1636 |
-
"loss": 0.
|
| 1637 |
-
"step":
|
| 1638 |
},
|
| 1639 |
{
|
| 1640 |
"epoch": 24.0,
|
| 1641 |
-
"eval_accuracy": 0.
|
| 1642 |
-
"eval_loss": 0.
|
| 1643 |
-
"eval_runtime":
|
| 1644 |
-
"eval_samples_per_second":
|
| 1645 |
-
"eval_steps_per_second": 0.
|
| 1646 |
-
"step":
|
| 1647 |
-
},
|
| 1648 |
-
{
|
| 1649 |
-
"epoch": 24.1,
|
| 1650 |
-
"learning_rate": 1.0582010582010582e-05,
|
| 1651 |
-
"loss": 0.5586,
|
| 1652 |
-
"step": 2380
|
| 1653 |
-
},
|
| 1654 |
-
{
|
| 1655 |
-
"epoch": 24.2,
|
| 1656 |
-
"learning_rate": 1.0393046107331822e-05,
|
| 1657 |
-
"loss": 0.5424,
|
| 1658 |
-
"step": 2390
|
| 1659 |
-
},
|
| 1660 |
-
{
|
| 1661 |
-
"epoch": 24.3,
|
| 1662 |
-
"learning_rate": 1.0204081632653061e-05,
|
| 1663 |
-
"loss": 0.5598,
|
| 1664 |
-
"step": 2400
|
| 1665 |
-
},
|
| 1666 |
-
{
|
| 1667 |
-
"epoch": 24.41,
|
| 1668 |
-
"learning_rate": 1.0015117157974303e-05,
|
| 1669 |
-
"loss": 0.5528,
|
| 1670 |
-
"step": 2410
|
| 1671 |
-
},
|
| 1672 |
-
{
|
| 1673 |
-
"epoch": 24.51,
|
| 1674 |
-
"learning_rate": 9.82615268329554e-06,
|
| 1675 |
-
"loss": 0.5521,
|
| 1676 |
-
"step": 2420
|
| 1677 |
-
},
|
| 1678 |
-
{
|
| 1679 |
-
"epoch": 24.61,
|
| 1680 |
-
"learning_rate": 9.63718820861678e-06,
|
| 1681 |
-
"loss": 0.5524,
|
| 1682 |
-
"step": 2430
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
-
"epoch": 24.
|
| 1686 |
-
"learning_rate": 9.
|
| 1687 |
-
"loss": 0.
|
| 1688 |
-
"step":
|
| 1689 |
-
},
|
| 1690 |
-
{
|
| 1691 |
-
"epoch": 24.81,
|
| 1692 |
-
"learning_rate": 9.259259259259259e-06,
|
| 1693 |
-
"loss": 0.5608,
|
| 1694 |
-
"step": 2450
|
| 1695 |
},
|
| 1696 |
{
|
| 1697 |
-
"epoch": 24.
|
| 1698 |
-
"learning_rate":
|
| 1699 |
-
"loss": 0.
|
| 1700 |
-
"step":
|
| 1701 |
},
|
| 1702 |
{
|
| 1703 |
"epoch": 24.99,
|
| 1704 |
-
"eval_accuracy": 0.
|
| 1705 |
-
"eval_loss": 0.
|
| 1706 |
-
"eval_runtime":
|
| 1707 |
-
"eval_samples_per_second":
|
| 1708 |
-
"eval_steps_per_second": 0.
|
| 1709 |
-
"step":
|
| 1710 |
-
},
|
| 1711 |
-
{
|
| 1712 |
-
"epoch": 25.01,
|
| 1713 |
-
"learning_rate": 8.88133030990174e-06,
|
| 1714 |
-
"loss": 0.5516,
|
| 1715 |
-
"step": 2470
|
| 1716 |
-
},
|
| 1717 |
-
{
|
| 1718 |
-
"epoch": 25.11,
|
| 1719 |
-
"learning_rate": 8.692365835222978e-06,
|
| 1720 |
-
"loss": 0.5489,
|
| 1721 |
-
"step": 2480
|
| 1722 |
-
},
|
| 1723 |
-
{
|
| 1724 |
-
"epoch": 25.22,
|
| 1725 |
-
"learning_rate": 8.503401360544217e-06,
|
| 1726 |
-
"loss": 0.5562,
|
| 1727 |
-
"step": 2490
|
| 1728 |
-
},
|
| 1729 |
-
{
|
| 1730 |
-
"epoch": 25.32,
|
| 1731 |
-
"learning_rate": 8.314436885865457e-06,
|
| 1732 |
-
"loss": 0.5498,
|
| 1733 |
-
"step": 2500
|
| 1734 |
-
},
|
| 1735 |
-
{
|
| 1736 |
-
"epoch": 25.42,
|
| 1737 |
-
"learning_rate": 8.125472411186698e-06,
|
| 1738 |
-
"loss": 0.5578,
|
| 1739 |
-
"step": 2510
|
| 1740 |
-
},
|
| 1741 |
-
{
|
| 1742 |
-
"epoch": 25.52,
|
| 1743 |
-
"learning_rate": 7.936507936507936e-06,
|
| 1744 |
-
"loss": 0.551,
|
| 1745 |
-
"step": 2520
|
| 1746 |
-
},
|
| 1747 |
-
{
|
| 1748 |
-
"epoch": 25.62,
|
| 1749 |
-
"learning_rate": 7.747543461829176e-06,
|
| 1750 |
-
"loss": 0.5572,
|
| 1751 |
-
"step": 2530
|
| 1752 |
-
},
|
| 1753 |
-
{
|
| 1754 |
-
"epoch": 25.72,
|
| 1755 |
-
"learning_rate": 7.558578987150416e-06,
|
| 1756 |
-
"loss": 0.5523,
|
| 1757 |
-
"step": 2540
|
| 1758 |
-
},
|
| 1759 |
-
{
|
| 1760 |
-
"epoch": 25.82,
|
| 1761 |
-
"learning_rate": 7.369614512471655e-06,
|
| 1762 |
-
"loss": 0.5525,
|
| 1763 |
-
"step": 2550
|
| 1764 |
-
},
|
| 1765 |
-
{
|
| 1766 |
-
"epoch": 25.92,
|
| 1767 |
-
"learning_rate": 7.180650037792895e-06,
|
| 1768 |
-
"loss": 0.5563,
|
| 1769 |
-
"step": 2560
|
| 1770 |
-
},
|
| 1771 |
-
{
|
| 1772 |
-
"epoch": 25.99,
|
| 1773 |
-
"eval_accuracy": 0.7302889760970389,
|
| 1774 |
-
"eval_loss": 0.5556601285934448,
|
| 1775 |
-
"eval_runtime": 270.2761,
|
| 1776 |
-
"eval_samples_per_second": 41.484,
|
| 1777 |
-
"eval_steps_per_second": 0.163,
|
| 1778 |
-
"step": 2567
|
| 1779 |
-
},
|
| 1780 |
-
{
|
| 1781 |
-
"epoch": 26.03,
|
| 1782 |
-
"learning_rate": 6.991685563114135e-06,
|
| 1783 |
-
"loss": 0.5607,
|
| 1784 |
-
"step": 2570
|
| 1785 |
-
},
|
| 1786 |
-
{
|
| 1787 |
-
"epoch": 26.13,
|
| 1788 |
-
"learning_rate": 6.802721088435375e-06,
|
| 1789 |
-
"loss": 0.5555,
|
| 1790 |
-
"step": 2580
|
| 1791 |
-
},
|
| 1792 |
-
{
|
| 1793 |
-
"epoch": 26.23,
|
| 1794 |
-
"learning_rate": 6.613756613756614e-06,
|
| 1795 |
-
"loss": 0.5527,
|
| 1796 |
-
"step": 2590
|
| 1797 |
-
},
|
| 1798 |
-
{
|
| 1799 |
-
"epoch": 26.33,
|
| 1800 |
-
"learning_rate": 6.424792139077854e-06,
|
| 1801 |
-
"loss": 0.5549,
|
| 1802 |
-
"step": 2600
|
| 1803 |
-
},
|
| 1804 |
-
{
|
| 1805 |
-
"epoch": 26.43,
|
| 1806 |
-
"learning_rate": 6.235827664399093e-06,
|
| 1807 |
-
"loss": 0.5435,
|
| 1808 |
-
"step": 2610
|
| 1809 |
-
},
|
| 1810 |
-
{
|
| 1811 |
-
"epoch": 26.53,
|
| 1812 |
-
"learning_rate": 6.046863189720333e-06,
|
| 1813 |
-
"loss": 0.5511,
|
| 1814 |
-
"step": 2620
|
| 1815 |
-
},
|
| 1816 |
-
{
|
| 1817 |
-
"epoch": 26.63,
|
| 1818 |
-
"learning_rate": 5.857898715041572e-06,
|
| 1819 |
-
"loss": 0.5629,
|
| 1820 |
-
"step": 2630
|
| 1821 |
-
},
|
| 1822 |
-
{
|
| 1823 |
-
"epoch": 26.73,
|
| 1824 |
-
"learning_rate": 5.668934240362813e-06,
|
| 1825 |
-
"loss": 0.5527,
|
| 1826 |
-
"step": 2640
|
| 1827 |
-
},
|
| 1828 |
-
{
|
| 1829 |
-
"epoch": 26.84,
|
| 1830 |
-
"learning_rate": 5.4799697656840515e-06,
|
| 1831 |
-
"loss": 0.5541,
|
| 1832 |
-
"step": 2650
|
| 1833 |
-
},
|
| 1834 |
-
{
|
| 1835 |
-
"epoch": 26.94,
|
| 1836 |
-
"learning_rate": 5.291005291005291e-06,
|
| 1837 |
-
"loss": 0.5563,
|
| 1838 |
-
"step": 2660
|
| 1839 |
-
},
|
| 1840 |
-
{
|
| 1841 |
-
"epoch": 27.0,
|
| 1842 |
-
"eval_accuracy": 0.727613271494827,
|
| 1843 |
-
"eval_loss": 0.5571199655532837,
|
| 1844 |
-
"eval_runtime": 269.8955,
|
| 1845 |
-
"eval_samples_per_second": 41.542,
|
| 1846 |
-
"eval_steps_per_second": 0.163,
|
| 1847 |
-
"step": 2666
|
| 1848 |
-
},
|
| 1849 |
-
{
|
| 1850 |
-
"epoch": 27.04,
|
| 1851 |
-
"learning_rate": 5.102040816326531e-06,
|
| 1852 |
-
"loss": 0.553,
|
| 1853 |
-
"step": 2670
|
| 1854 |
-
},
|
| 1855 |
-
{
|
| 1856 |
-
"epoch": 27.14,
|
| 1857 |
-
"learning_rate": 4.91307634164777e-06,
|
| 1858 |
-
"loss": 0.5502,
|
| 1859 |
-
"step": 2680
|
| 1860 |
-
},
|
| 1861 |
-
{
|
| 1862 |
-
"epoch": 27.24,
|
| 1863 |
-
"learning_rate": 4.724111866969011e-06,
|
| 1864 |
-
"loss": 0.55,
|
| 1865 |
-
"step": 2690
|
| 1866 |
},
|
| 1867 |
{
|
| 1868 |
-
"epoch":
|
| 1869 |
-
"learning_rate":
|
| 1870 |
-
"loss": 0.
|
| 1871 |
-
"step":
|
| 1872 |
},
|
| 1873 |
{
|
| 1874 |
-
"epoch":
|
| 1875 |
-
"
|
| 1876 |
-
"
|
| 1877 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1878 |
},
|
| 1879 |
{
|
| 1880 |
-
"epoch":
|
| 1881 |
-
"learning_rate":
|
| 1882 |
-
"loss": 0.
|
| 1883 |
-
"step":
|
| 1884 |
},
|
| 1885 |
{
|
| 1886 |
-
"epoch":
|
| 1887 |
-
"learning_rate":
|
| 1888 |
-
"loss": 0.
|
| 1889 |
-
"step":
|
| 1890 |
},
|
| 1891 |
{
|
| 1892 |
-
"epoch":
|
| 1893 |
-
"
|
| 1894 |
-
"
|
| 1895 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1896 |
},
|
| 1897 |
{
|
| 1898 |
-
"epoch": 27.
|
| 1899 |
-
"learning_rate":
|
| 1900 |
-
"loss": 0.
|
| 1901 |
-
"step":
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
-
"epoch": 27.
|
| 1905 |
-
"learning_rate": 3.
|
| 1906 |
-
"loss": 0.
|
| 1907 |
-
"step":
|
| 1908 |
},
|
| 1909 |
{
|
| 1910 |
"epoch": 28.0,
|
| 1911 |
-
"eval_accuracy": 0.
|
| 1912 |
-
"eval_loss": 0.
|
| 1913 |
-
"eval_runtime":
|
| 1914 |
-
"eval_samples_per_second":
|
| 1915 |
-
"eval_steps_per_second": 0.
|
| 1916 |
-
"step":
|
| 1917 |
-
},
|
| 1918 |
-
{
|
| 1919 |
-
"epoch": 28.05,
|
| 1920 |
-
"learning_rate": 3.212396069538927e-06,
|
| 1921 |
-
"loss": 0.553,
|
| 1922 |
-
"step": 2770
|
| 1923 |
-
},
|
| 1924 |
-
{
|
| 1925 |
-
"epoch": 28.15,
|
| 1926 |
-
"learning_rate": 3.0234315948601664e-06,
|
| 1927 |
-
"loss": 0.5534,
|
| 1928 |
-
"step": 2780
|
| 1929 |
},
|
| 1930 |
{
|
| 1931 |
-
"epoch": 28.
|
| 1932 |
-
"learning_rate": 2.
|
| 1933 |
-
"loss": 0.
|
| 1934 |
-
"step":
|
| 1935 |
-
},
|
| 1936 |
-
{
|
| 1937 |
-
"epoch": 28.35,
|
| 1938 |
-
"learning_rate": 2.6455026455026455e-06,
|
| 1939 |
-
"loss": 0.5553,
|
| 1940 |
-
"step": 2800
|
| 1941 |
-
},
|
| 1942 |
-
{
|
| 1943 |
-
"epoch": 28.46,
|
| 1944 |
-
"learning_rate": 2.456538170823885e-06,
|
| 1945 |
-
"loss": 0.5503,
|
| 1946 |
-
"step": 2810
|
| 1947 |
-
},
|
| 1948 |
-
{
|
| 1949 |
-
"epoch": 28.56,
|
| 1950 |
-
"learning_rate": 2.2675736961451247e-06,
|
| 1951 |
-
"loss": 0.5493,
|
| 1952 |
-
"step": 2820
|
| 1953 |
-
},
|
| 1954 |
-
{
|
| 1955 |
-
"epoch": 28.66,
|
| 1956 |
-
"learning_rate": 2.0786092214663643e-06,
|
| 1957 |
-
"loss": 0.5474,
|
| 1958 |
-
"step": 2830
|
| 1959 |
-
},
|
| 1960 |
-
{
|
| 1961 |
-
"epoch": 28.76,
|
| 1962 |
-
"learning_rate": 1.889644746787604e-06,
|
| 1963 |
-
"loss": 0.5477,
|
| 1964 |
-
"step": 2840
|
| 1965 |
-
},
|
| 1966 |
-
{
|
| 1967 |
-
"epoch": 28.86,
|
| 1968 |
-
"learning_rate": 1.7006802721088438e-06,
|
| 1969 |
-
"loss": 0.5565,
|
| 1970 |
-
"step": 2850
|
| 1971 |
-
},
|
| 1972 |
-
{
|
| 1973 |
-
"epoch": 28.96,
|
| 1974 |
-
"learning_rate": 1.5117157974300832e-06,
|
| 1975 |
-
"loss": 0.5491,
|
| 1976 |
-
"step": 2860
|
| 1977 |
},
|
| 1978 |
{
|
| 1979 |
"epoch": 28.99,
|
| 1980 |
-
"
|
| 1981 |
-
"
|
| 1982 |
-
"
|
| 1983 |
-
"eval_samples_per_second": 41.411,
|
| 1984 |
-
"eval_steps_per_second": 0.163,
|
| 1985 |
-
"step": 2863
|
| 1986 |
-
},
|
| 1987 |
-
{
|
| 1988 |
-
"epoch": 29.06,
|
| 1989 |
-
"learning_rate": 1.3227513227513228e-06,
|
| 1990 |
-
"loss": 0.5508,
|
| 1991 |
-
"step": 2870
|
| 1992 |
-
},
|
| 1993 |
-
{
|
| 1994 |
-
"epoch": 29.16,
|
| 1995 |
-
"learning_rate": 1.1337868480725623e-06,
|
| 1996 |
-
"loss": 0.5513,
|
| 1997 |
-
"step": 2880
|
| 1998 |
-
},
|
| 1999 |
-
{
|
| 2000 |
-
"epoch": 29.27,
|
| 2001 |
-
"learning_rate": 9.44822373393802e-07,
|
| 2002 |
-
"loss": 0.5517,
|
| 2003 |
-
"step": 2890
|
| 2004 |
-
},
|
| 2005 |
-
{
|
| 2006 |
-
"epoch": 29.37,
|
| 2007 |
-
"learning_rate": 7.558578987150416e-07,
|
| 2008 |
-
"loss": 0.5575,
|
| 2009 |
-
"step": 2900
|
| 2010 |
},
|
| 2011 |
{
|
| 2012 |
-
"epoch":
|
| 2013 |
-
"
|
| 2014 |
-
"
|
| 2015 |
-
"
|
|
|
|
|
|
|
|
|
|
| 2016 |
},
|
| 2017 |
{
|
| 2018 |
"epoch": 29.57,
|
| 2019 |
-
"learning_rate":
|
| 2020 |
-
"loss": 0.
|
| 2021 |
-
"step":
|
| 2022 |
},
|
| 2023 |
{
|
| 2024 |
-
"epoch": 29.
|
| 2025 |
-
"
|
| 2026 |
-
"
|
| 2027 |
-
"
|
|
|
|
|
|
|
|
|
|
| 2028 |
},
|
| 2029 |
{
|
| 2030 |
-
"epoch": 29.
|
| 2031 |
-
"
|
| 2032 |
-
"
|
| 2033 |
-
"
|
| 2034 |
-
|
| 2035 |
-
|
| 2036 |
-
"
|
| 2037 |
-
"eval_accuracy": 0.7302889760970389,
|
| 2038 |
-
"eval_loss": 0.5574254989624023,
|
| 2039 |
-
"eval_runtime": 267.0764,
|
| 2040 |
-
"eval_samples_per_second": 41.98,
|
| 2041 |
-
"eval_steps_per_second": 0.165,
|
| 2042 |
-
"step": 2940
|
| 2043 |
-
},
|
| 2044 |
-
{
|
| 2045 |
-
"epoch": 29.77,
|
| 2046 |
-
"step": 2940,
|
| 2047 |
-
"total_flos": 7.46776315809736e+19,
|
| 2048 |
-
"train_loss": 0.5755378539870385,
|
| 2049 |
-
"train_runtime": 78104.0618,
|
| 2050 |
-
"train_samples_per_second": 38.759,
|
| 2051 |
-
"train_steps_per_second": 0.038
|
| 2052 |
}
|
| 2053 |
],
|
| 2054 |
-
"max_steps":
|
| 2055 |
"num_train_epochs": 30,
|
| 2056 |
-
"total_flos":
|
| 2057 |
"trial_name": null,
|
| 2058 |
"trial_params": null
|
| 2059 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8001030396702731,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-310",
|
| 4 |
+
"epoch": 29.565217391304348,
|
| 5 |
+
"global_step": 510,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.58,
|
| 12 |
+
"learning_rate": 9.803921568627451e-06,
|
| 13 |
+
"loss": 0.6794,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.99,
|
| 18 |
+
"eval_accuracy": 0.7047913446676971,
|
| 19 |
+
"eval_loss": 0.5848240256309509,
|
| 20 |
+
"eval_runtime": 9.3525,
|
| 21 |
+
"eval_samples_per_second": 207.538,
|
| 22 |
+
"eval_steps_per_second": 0.855,
|
| 23 |
+
"step": 17
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 1.16,
|
| 27 |
+
"learning_rate": 1.9607843137254903e-05,
|
| 28 |
+
"loss": 0.6308,
|
| 29 |
+
"step": 20
|
| 30 |
},
|
| 31 |
{
|
| 32 |
+
"epoch": 1.74,
|
| 33 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 34 |
+
"loss": 0.5835,
|
| 35 |
+
"step": 30
|
| 36 |
},
|
| 37 |
{
|
| 38 |
+
"epoch": 1.97,
|
| 39 |
+
"eval_accuracy": 0.7429160226687275,
|
| 40 |
+
"eval_loss": 0.5206928253173828,
|
| 41 |
+
"eval_runtime": 9.455,
|
| 42 |
+
"eval_samples_per_second": 205.288,
|
| 43 |
+
"eval_steps_per_second": 0.846,
|
| 44 |
+
"step": 34
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 2.32,
|
| 48 |
+
"learning_rate": 3.9215686274509805e-05,
|
| 49 |
+
"loss": 0.5523,
|
| 50 |
+
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 2.9,
|
| 54 |
+
"learning_rate": 4.901960784313725e-05,
|
| 55 |
+
"loss": 0.5257,
|
| 56 |
+
"step": 50
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 2.96,
|
| 60 |
+
"eval_accuracy": 0.7640391550747038,
|
| 61 |
+
"eval_loss": 0.4912124574184418,
|
| 62 |
+
"eval_runtime": 9.367,
|
| 63 |
+
"eval_samples_per_second": 207.218,
|
| 64 |
+
"eval_steps_per_second": 0.854,
|
| 65 |
+
"step": 51
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 3.48,
|
| 69 |
+
"learning_rate": 4.901960784313725e-05,
|
| 70 |
+
"loss": 0.5128,
|
| 71 |
+
"step": 60
|
| 72 |
},
|
| 73 |
{
|
| 74 |
+
"epoch": 4.0,
|
| 75 |
+
"eval_accuracy": 0.7743431221020093,
|
| 76 |
+
"eval_loss": 0.46713554859161377,
|
| 77 |
+
"eval_runtime": 9.3663,
|
| 78 |
+
"eval_samples_per_second": 207.232,
|
| 79 |
+
"eval_steps_per_second": 0.854,
|
| 80 |
+
"step": 69
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 4.06,
|
| 84 |
+
"learning_rate": 4.793028322440087e-05,
|
| 85 |
+
"loss": 0.5028,
|
| 86 |
+
"step": 70
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 4.64,
|
| 90 |
+
"learning_rate": 4.684095860566449e-05,
|
| 91 |
+
"loss": 0.4963,
|
| 92 |
+
"step": 80
|
|
|
|
|
|
|
|
|
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 4.99,
|
| 96 |
+
"eval_accuracy": 0.7599175682637815,
|
| 97 |
+
"eval_loss": 0.479315847158432,
|
| 98 |
+
"eval_runtime": 9.3717,
|
| 99 |
+
"eval_samples_per_second": 207.114,
|
| 100 |
+
"eval_steps_per_second": 0.854,
|
| 101 |
+
"step": 86
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 5.22,
|
| 105 |
+
"learning_rate": 4.5751633986928104e-05,
|
| 106 |
+
"loss": 0.4965,
|
| 107 |
+
"step": 90
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 5.8,
|
| 111 |
+
"learning_rate": 4.466230936819172e-05,
|
| 112 |
+
"loss": 0.5005,
|
| 113 |
+
"step": 100
|
| 114 |
},
|
| 115 |
{
|
| 116 |
+
"epoch": 5.97,
|
| 117 |
+
"eval_accuracy": 0.7650695517774343,
|
| 118 |
+
"eval_loss": 0.485215961933136,
|
| 119 |
+
"eval_runtime": 9.3698,
|
| 120 |
+
"eval_samples_per_second": 207.154,
|
| 121 |
+
"eval_steps_per_second": 0.854,
|
| 122 |
+
"step": 103
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 6.38,
|
| 126 |
+
"learning_rate": 4.357298474945534e-05,
|
| 127 |
+
"loss": 0.4963,
|
| 128 |
+
"step": 110
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 6.96,
|
| 132 |
+
"learning_rate": 4.2483660130718954e-05,
|
| 133 |
+
"loss": 0.4748,
|
| 134 |
+
"step": 120
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 6.96,
|
| 138 |
+
"eval_accuracy": 0.768160741885626,
|
| 139 |
+
"eval_loss": 0.4841272234916687,
|
| 140 |
+
"eval_runtime": 9.371,
|
| 141 |
+
"eval_samples_per_second": 207.128,
|
| 142 |
+
"eval_steps_per_second": 0.854,
|
| 143 |
+
"step": 120
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 7.54,
|
| 147 |
+
"learning_rate": 4.1394335511982573e-05,
|
| 148 |
+
"loss": 0.4732,
|
| 149 |
+
"step": 130
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.7748583204533745,
|
| 154 |
+
"eval_loss": 0.4430771768093109,
|
| 155 |
+
"eval_runtime": 9.3845,
|
| 156 |
+
"eval_samples_per_second": 206.83,
|
| 157 |
+
"eval_steps_per_second": 0.852,
|
| 158 |
+
"step": 138
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 8.12,
|
| 162 |
+
"learning_rate": 4.0305010893246186e-05,
|
| 163 |
+
"loss": 0.4842,
|
| 164 |
+
"step": 140
|
|
|
|
|
|
|
|
|
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 8.7,
|
| 168 |
+
"learning_rate": 3.9215686274509805e-05,
|
| 169 |
+
"loss": 0.4614,
|
| 170 |
+
"step": 150
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 8.99,
|
| 174 |
+
"eval_accuracy": 0.7856774858320453,
|
| 175 |
+
"eval_loss": 0.4429071843624115,
|
| 176 |
+
"eval_runtime": 9.3915,
|
| 177 |
+
"eval_samples_per_second": 206.677,
|
| 178 |
+
"eval_steps_per_second": 0.852,
|
| 179 |
+
"step": 155
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 9.28,
|
| 183 |
+
"learning_rate": 3.8126361655773424e-05,
|
| 184 |
+
"loss": 0.4645,
|
| 185 |
+
"step": 160
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 9.86,
|
| 189 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 190 |
+
"loss": 0.4647,
|
| 191 |
+
"step": 170
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 9.97,
|
| 195 |
+
"eval_accuracy": 0.7717671303451829,
|
| 196 |
+
"eval_loss": 0.4715192914009094,
|
| 197 |
+
"eval_runtime": 9.3758,
|
| 198 |
+
"eval_samples_per_second": 207.023,
|
| 199 |
+
"eval_steps_per_second": 0.853,
|
| 200 |
+
"step": 172
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"epoch": 10.43,
|
| 204 |
+
"learning_rate": 3.5947712418300656e-05,
|
| 205 |
+
"loss": 0.4601,
|
| 206 |
+
"step": 180
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 10.96,
|
| 210 |
+
"eval_accuracy": 0.7753735188047398,
|
| 211 |
+
"eval_loss": 0.4722177982330322,
|
| 212 |
+
"eval_runtime": 9.3838,
|
| 213 |
+
"eval_samples_per_second": 206.847,
|
| 214 |
+
"eval_steps_per_second": 0.853,
|
| 215 |
+
"step": 189
|
| 216 |
},
|
| 217 |
{
|
| 218 |
+
"epoch": 11.01,
|
| 219 |
+
"learning_rate": 3.4858387799564275e-05,
|
| 220 |
+
"loss": 0.4496,
|
| 221 |
+
"step": 190
|
| 222 |
},
|
| 223 |
{
|
| 224 |
+
"epoch": 11.59,
|
| 225 |
+
"learning_rate": 3.376906318082789e-05,
|
| 226 |
+
"loss": 0.4626,
|
| 227 |
+
"step": 200
|
| 228 |
},
|
| 229 |
{
|
| 230 |
+
"epoch": 12.0,
|
| 231 |
+
"eval_accuracy": 0.7872230808861411,
|
| 232 |
+
"eval_loss": 0.44434165954589844,
|
| 233 |
+
"eval_runtime": 9.3667,
|
| 234 |
+
"eval_samples_per_second": 207.223,
|
| 235 |
+
"eval_steps_per_second": 0.854,
|
| 236 |
+
"step": 207
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 12.17,
|
| 240 |
+
"learning_rate": 3.2679738562091506e-05,
|
| 241 |
+
"loss": 0.4447,
|
| 242 |
+
"step": 210
|
|
|
|
|
|
|
|
|
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 12.75,
|
| 246 |
+
"learning_rate": 3.1590413943355126e-05,
|
| 247 |
+
"loss": 0.4526,
|
| 248 |
+
"step": 220
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 12.99,
|
| 252 |
+
"eval_accuracy": 0.7908294693456981,
|
| 253 |
+
"eval_loss": 0.4368865489959717,
|
| 254 |
+
"eval_runtime": 9.3607,
|
| 255 |
+
"eval_samples_per_second": 207.356,
|
| 256 |
+
"eval_steps_per_second": 0.855,
|
| 257 |
+
"step": 224
|
| 258 |
},
|
| 259 |
{
|
| 260 |
+
"epoch": 13.33,
|
| 261 |
+
"learning_rate": 3.0501089324618738e-05,
|
| 262 |
+
"loss": 0.447,
|
| 263 |
+
"step": 230
|
| 264 |
},
|
| 265 |
{
|
| 266 |
+
"epoch": 13.91,
|
| 267 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 268 |
+
"loss": 0.4494,
|
| 269 |
+
"step": 240
|
| 270 |
},
|
| 271 |
{
|
| 272 |
+
"epoch": 13.97,
|
| 273 |
+
"eval_accuracy": 0.7970118495620814,
|
| 274 |
+
"eval_loss": 0.42481139302253723,
|
| 275 |
+
"eval_runtime": 9.3639,
|
| 276 |
+
"eval_samples_per_second": 207.286,
|
| 277 |
+
"eval_steps_per_second": 0.854,
|
| 278 |
+
"step": 241
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 14.49,
|
| 282 |
+
"learning_rate": 2.832244008714597e-05,
|
| 283 |
+
"loss": 0.458,
|
| 284 |
+
"step": 250
|
| 285 |
},
|
| 286 |
{
|
| 287 |
+
"epoch": 14.96,
|
| 288 |
+
"eval_accuracy": 0.7867078825347759,
|
| 289 |
+
"eval_loss": 0.4402971863746643,
|
| 290 |
+
"eval_runtime": 9.4177,
|
| 291 |
+
"eval_samples_per_second": 206.101,
|
| 292 |
+
"eval_steps_per_second": 0.849,
|
| 293 |
+
"step": 258
|
| 294 |
},
|
| 295 |
{
|
| 296 |
+
"epoch": 15.07,
|
| 297 |
+
"learning_rate": 2.7233115468409585e-05,
|
| 298 |
+
"loss": 0.4501,
|
| 299 |
+
"step": 260
|
| 300 |
},
|
| 301 |
{
|
| 302 |
+
"epoch": 15.65,
|
| 303 |
+
"learning_rate": 2.6143790849673204e-05,
|
| 304 |
+
"loss": 0.4387,
|
| 305 |
+
"step": 270
|
| 306 |
},
|
| 307 |
{
|
| 308 |
+
"epoch": 16.0,
|
| 309 |
+
"eval_accuracy": 0.7964966512107161,
|
| 310 |
+
"eval_loss": 0.4251194894313812,
|
| 311 |
+
"eval_runtime": 9.3671,
|
| 312 |
+
"eval_samples_per_second": 207.214,
|
| 313 |
+
"eval_steps_per_second": 0.854,
|
| 314 |
+
"step": 276
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 16.23,
|
| 318 |
+
"learning_rate": 2.5054466230936817e-05,
|
| 319 |
+
"loss": 0.4448,
|
| 320 |
+
"step": 280
|
|
|
|
|
|
|
|
|
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"epoch": 16.81,
|
| 324 |
+
"learning_rate": 2.3965141612200436e-05,
|
| 325 |
+
"loss": 0.4314,
|
| 326 |
+
"step": 290
|
| 327 |
},
|
| 328 |
{
|
| 329 |
+
"epoch": 16.99,
|
| 330 |
+
"eval_accuracy": 0.7980422462648119,
|
| 331 |
+
"eval_loss": 0.4256560206413269,
|
| 332 |
+
"eval_runtime": 9.3785,
|
| 333 |
+
"eval_samples_per_second": 206.963,
|
| 334 |
+
"eval_steps_per_second": 0.853,
|
| 335 |
+
"step": 293
|
| 336 |
},
|
| 337 |
{
|
| 338 |
+
"epoch": 17.39,
|
| 339 |
+
"learning_rate": 2.2875816993464052e-05,
|
| 340 |
+
"loss": 0.4354,
|
| 341 |
+
"step": 300
|
| 342 |
},
|
| 343 |
{
|
| 344 |
+
"epoch": 17.97,
|
| 345 |
+
"learning_rate": 2.178649237472767e-05,
|
| 346 |
+
"loss": 0.432,
|
| 347 |
+
"step": 310
|
| 348 |
},
|
| 349 |
{
|
| 350 |
+
"epoch": 17.97,
|
| 351 |
+
"eval_accuracy": 0.8001030396702731,
|
| 352 |
+
"eval_loss": 0.42466819286346436,
|
| 353 |
+
"eval_runtime": 9.3749,
|
| 354 |
+
"eval_samples_per_second": 207.041,
|
| 355 |
+
"eval_steps_per_second": 0.853,
|
| 356 |
+
"step": 310
|
| 357 |
},
|
| 358 |
{
|
| 359 |
+
"epoch": 18.55,
|
| 360 |
+
"learning_rate": 2.0697167755991287e-05,
|
| 361 |
+
"loss": 0.4372,
|
| 362 |
+
"step": 320
|
| 363 |
},
|
| 364 |
{
|
| 365 |
+
"epoch": 18.96,
|
| 366 |
+
"eval_accuracy": 0.7856774858320453,
|
| 367 |
+
"eval_loss": 0.44541600346565247,
|
| 368 |
+
"eval_runtime": 9.3667,
|
| 369 |
+
"eval_samples_per_second": 207.222,
|
| 370 |
+
"eval_steps_per_second": 0.854,
|
| 371 |
+
"step": 327
|
| 372 |
},
|
| 373 |
{
|
| 374 |
+
"epoch": 19.13,
|
| 375 |
+
"learning_rate": 1.9607843137254903e-05,
|
| 376 |
+
"loss": 0.4298,
|
| 377 |
+
"step": 330
|
| 378 |
},
|
| 379 |
{
|
| 380 |
+
"epoch": 19.71,
|
| 381 |
"learning_rate": 1.8518518518518518e-05,
|
| 382 |
+
"loss": 0.434,
|
| 383 |
+
"step": 340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 20.0,
|
| 387 |
+
"eval_accuracy": 0.7903142709943328,
|
| 388 |
+
"eval_loss": 0.43263283371925354,
|
| 389 |
+
"eval_runtime": 9.367,
|
| 390 |
+
"eval_samples_per_second": 207.217,
|
| 391 |
+
"eval_steps_per_second": 0.854,
|
| 392 |
+
"step": 345
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 393 |
},
|
| 394 |
{
|
| 395 |
+
"epoch": 20.29,
|
| 396 |
+
"learning_rate": 1.7429193899782137e-05,
|
| 397 |
+
"loss": 0.4257,
|
| 398 |
+
"step": 350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 399 |
},
|
| 400 |
{
|
| 401 |
+
"epoch": 20.87,
|
| 402 |
+
"learning_rate": 1.6339869281045753e-05,
|
| 403 |
+
"loss": 0.4313,
|
| 404 |
+
"step": 360
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 20.99,
|
| 408 |
+
"eval_accuracy": 0.7959814528593508,
|
| 409 |
+
"eval_loss": 0.4253856837749481,
|
| 410 |
+
"eval_runtime": 9.3553,
|
| 411 |
+
"eval_samples_per_second": 207.475,
|
| 412 |
+
"eval_steps_per_second": 0.855,
|
| 413 |
+
"step": 362
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 414 |
},
|
| 415 |
{
|
| 416 |
+
"epoch": 21.45,
|
| 417 |
+
"learning_rate": 1.5250544662309369e-05,
|
| 418 |
+
"loss": 0.421,
|
| 419 |
+
"step": 370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 21.97,
|
| 423 |
+
"eval_accuracy": 0.7970118495620814,
|
| 424 |
+
"eval_loss": 0.42772090435028076,
|
| 425 |
+
"eval_runtime": 9.3638,
|
| 426 |
+
"eval_samples_per_second": 207.288,
|
| 427 |
+
"eval_steps_per_second": 0.854,
|
| 428 |
+
"step": 379
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 429 |
},
|
| 430 |
{
|
| 431 |
+
"epoch": 22.03,
|
| 432 |
+
"learning_rate": 1.4161220043572985e-05,
|
| 433 |
+
"loss": 0.4207,
|
| 434 |
+
"step": 380
|
| 435 |
},
|
| 436 |
{
|
| 437 |
+
"epoch": 22.61,
|
| 438 |
+
"learning_rate": 1.3071895424836602e-05,
|
| 439 |
+
"loss": 0.4272,
|
| 440 |
+
"step": 390
|
|
|
|
|
|
|
|
|
|
| 441 |
},
|
| 442 |
{
|
| 443 |
+
"epoch": 22.96,
|
| 444 |
+
"eval_accuracy": 0.7980422462648119,
|
| 445 |
+
"eval_loss": 0.4280939996242523,
|
| 446 |
+
"eval_runtime": 9.3579,
|
| 447 |
+
"eval_samples_per_second": 207.419,
|
| 448 |
+
"eval_steps_per_second": 0.855,
|
| 449 |
+
"step": 396
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 23.19,
|
| 453 |
+
"learning_rate": 1.1982570806100218e-05,
|
| 454 |
+
"loss": 0.4185,
|
| 455 |
+
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 456 |
},
|
| 457 |
{
|
| 458 |
+
"epoch": 23.77,
|
| 459 |
+
"learning_rate": 1.0893246187363835e-05,
|
| 460 |
+
"loss": 0.4245,
|
| 461 |
+
"step": 410
|
| 462 |
},
|
| 463 |
{
|
| 464 |
"epoch": 24.0,
|
| 465 |
+
"eval_accuracy": 0.7959814528593508,
|
| 466 |
+
"eval_loss": 0.4282556176185608,
|
| 467 |
+
"eval_runtime": 9.3525,
|
| 468 |
+
"eval_samples_per_second": 207.539,
|
| 469 |
+
"eval_steps_per_second": 0.855,
|
| 470 |
+
"step": 414
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 471 |
},
|
| 472 |
{
|
| 473 |
+
"epoch": 24.35,
|
| 474 |
+
"learning_rate": 9.803921568627451e-06,
|
| 475 |
+
"loss": 0.4179,
|
| 476 |
+
"step": 420
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 477 |
},
|
| 478 |
{
|
| 479 |
+
"epoch": 24.93,
|
| 480 |
+
"learning_rate": 8.714596949891069e-06,
|
| 481 |
+
"loss": 0.4207,
|
| 482 |
+
"step": 430
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 24.99,
|
| 486 |
+
"eval_accuracy": 0.7892838742916023,
|
| 487 |
+
"eval_loss": 0.4409063458442688,
|
| 488 |
+
"eval_runtime": 9.3603,
|
| 489 |
+
"eval_samples_per_second": 207.365,
|
| 490 |
+
"eval_steps_per_second": 0.855,
|
| 491 |
+
"step": 431
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 492 |
},
|
| 493 |
{
|
| 494 |
+
"epoch": 25.51,
|
| 495 |
+
"learning_rate": 7.6252723311546845e-06,
|
| 496 |
+
"loss": 0.4134,
|
| 497 |
+
"step": 440
|
| 498 |
},
|
| 499 |
{
|
| 500 |
+
"epoch": 25.97,
|
| 501 |
+
"eval_accuracy": 0.7964966512107161,
|
| 502 |
+
"eval_loss": 0.43111562728881836,
|
| 503 |
+
"eval_runtime": 9.3664,
|
| 504 |
+
"eval_samples_per_second": 207.229,
|
| 505 |
+
"eval_steps_per_second": 0.854,
|
| 506 |
+
"step": 448
|
| 507 |
},
|
| 508 |
{
|
| 509 |
+
"epoch": 26.09,
|
| 510 |
+
"learning_rate": 6.535947712418301e-06,
|
| 511 |
+
"loss": 0.4216,
|
| 512 |
+
"step": 450
|
| 513 |
},
|
| 514 |
{
|
| 515 |
+
"epoch": 26.67,
|
| 516 |
+
"learning_rate": 5.446623093681918e-06,
|
| 517 |
+
"loss": 0.4157,
|
| 518 |
+
"step": 460
|
| 519 |
},
|
| 520 |
{
|
| 521 |
+
"epoch": 26.96,
|
| 522 |
+
"eval_accuracy": 0.794435857805255,
|
| 523 |
+
"eval_loss": 0.43559595942497253,
|
| 524 |
+
"eval_runtime": 9.3485,
|
| 525 |
+
"eval_samples_per_second": 207.628,
|
| 526 |
+
"eval_steps_per_second": 0.856,
|
| 527 |
+
"step": 465
|
| 528 |
},
|
| 529 |
{
|
| 530 |
+
"epoch": 27.25,
|
| 531 |
+
"learning_rate": 4.357298474945534e-06,
|
| 532 |
+
"loss": 0.4235,
|
| 533 |
+
"step": 470
|
| 534 |
},
|
| 535 |
{
|
| 536 |
+
"epoch": 27.83,
|
| 537 |
+
"learning_rate": 3.2679738562091506e-06,
|
| 538 |
+
"loss": 0.4207,
|
| 539 |
+
"step": 480
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 28.0,
|
| 543 |
+
"eval_accuracy": 0.7980422462648119,
|
| 544 |
+
"eval_loss": 0.4301479756832123,
|
| 545 |
+
"eval_runtime": 9.3663,
|
| 546 |
+
"eval_samples_per_second": 207.233,
|
| 547 |
+
"eval_steps_per_second": 0.854,
|
| 548 |
+
"step": 483
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 549 |
},
|
| 550 |
{
|
| 551 |
+
"epoch": 28.41,
|
| 552 |
+
"learning_rate": 2.178649237472767e-06,
|
| 553 |
+
"loss": 0.4128,
|
| 554 |
+
"step": 490
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 28.99,
|
| 558 |
+
"learning_rate": 1.0893246187363836e-06,
|
| 559 |
+
"loss": 0.4104,
|
| 560 |
+
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 561 |
},
|
| 562 |
{
|
| 563 |
+
"epoch": 28.99,
|
| 564 |
+
"eval_accuracy": 0.7954662545079856,
|
| 565 |
+
"eval_loss": 0.4339882433414459,
|
| 566 |
+
"eval_runtime": 9.3665,
|
| 567 |
+
"eval_samples_per_second": 207.228,
|
| 568 |
+
"eval_steps_per_second": 0.854,
|
| 569 |
+
"step": 500
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 29.57,
|
| 573 |
+
"learning_rate": 0.0,
|
| 574 |
+
"loss": 0.4187,
|
| 575 |
+
"step": 510
|
| 576 |
},
|
| 577 |
{
|
| 578 |
+
"epoch": 29.57,
|
| 579 |
+
"eval_accuracy": 0.7954662545079856,
|
| 580 |
+
"eval_loss": 0.4336837828159332,
|
| 581 |
+
"eval_runtime": 9.3744,
|
| 582 |
+
"eval_samples_per_second": 207.053,
|
| 583 |
+
"eval_steps_per_second": 0.853,
|
| 584 |
+
"step": 510
|
| 585 |
},
|
| 586 |
{
|
| 587 |
+
"epoch": 29.57,
|
| 588 |
+
"step": 510,
|
| 589 |
+
"total_flos": 1.2835906128174883e+19,
|
| 590 |
+
"train_loss": 0.46080853518317727,
|
| 591 |
+
"train_runtime": 3932.5078,
|
| 592 |
+
"train_samples_per_second": 133.22,
|
| 593 |
+
"train_steps_per_second": 0.13
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 594 |
}
|
| 595 |
],
|
| 596 |
+
"max_steps": 510,
|
| 597 |
"num_train_epochs": 30,
|
| 598 |
+
"total_flos": 1.2835906128174883e+19,
|
| 599 |
"trial_name": null,
|
| 600 |
"trial_params": null
|
| 601 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef939cd59d81be9f37bfadc055ef8cab25db668087412c32c6927dcb41799913
|
| 3 |
size 4027
|