🍻 cheers
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Aug06_22-45-08_a3e0ec26426d/events.out.tfevents.1659828394.a3e0ec26426d.71.18 +3 -0
- test_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +2153 -578
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 1.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 13.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 2.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_accuracy": 0.7471264367816092,
|
| 4 |
+
"eval_loss": 0.847703754901886,
|
| 5 |
+
"eval_runtime": 1.6712,
|
| 6 |
+
"eval_samples_per_second": 104.114,
|
| 7 |
+
"eval_steps_per_second": 13.164,
|
| 8 |
+
"total_flos": 5.622144623740109e+18,
|
| 9 |
+
"train_loss": 0.2358846340533141,
|
| 10 |
+
"train_runtime": 1979.1189,
|
| 11 |
+
"train_samples_per_second": 36.658,
|
| 12 |
+
"train_steps_per_second": 2.299
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 1.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 13.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_accuracy": 0.7470588235294118,
|
| 4 |
+
"eval_loss": 0.7239104509353638,
|
| 5 |
+
"eval_runtime": 1.5971,
|
| 6 |
+
"eval_samples_per_second": 106.444,
|
| 7 |
+
"eval_steps_per_second": 13.775
|
| 8 |
}
|
runs/Aug06_22-45-08_a3e0ec26426d/events.out.tfevents.1659828394.a3e0ec26426d.71.18
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6b9f5654c4e0fa78cb3d60e5b5dfbe4004df50154dc337900c535690f6d6525
|
| 3 |
+
size 686
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 1.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 13.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_accuracy": 0.7471264367816092,
|
| 4 |
+
"eval_loss": 0.847703754901886,
|
| 5 |
+
"eval_runtime": 1.6712,
|
| 6 |
+
"eval_samples_per_second": 104.114,
|
| 7 |
+
"eval_steps_per_second": 13.164
|
| 8 |
}
|
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": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"total_flos": 5.622144623740109e+18,
|
| 4 |
+
"train_loss": 0.2358846340533141,
|
| 5 |
+
"train_runtime": 1979.1189,
|
| 6 |
+
"train_samples_per_second": 36.658,
|
| 7 |
+
"train_steps_per_second": 2.299
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1585 +1,3160 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./croupier-creature-classifier/checkpoint-
|
| 4 |
-
"epoch":
|
| 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": 0.11,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 1.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.22,
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 1.
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.33,
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 1.
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.44,
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 1.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.55,
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 1.
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.66,
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.77,
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 1.
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.88,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 1.
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.99,
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 1.
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 1.1,
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 1.
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 1.1,
|
| 72 |
-
"eval_accuracy": 0.
|
| 73 |
-
"eval_loss": 1.
|
| 74 |
-
"eval_runtime": 1.
|
| 75 |
-
"eval_samples_per_second": 111.
|
| 76 |
-
"eval_steps_per_second": 14.
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 1.21,
|
| 81 |
-
"learning_rate":
|
| 82 |
-
"loss": 1.
|
| 83 |
"step": 110
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 1.32,
|
| 87 |
-
"learning_rate":
|
| 88 |
-
"loss": 1.
|
| 89 |
"step": 120
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 1.43,
|
| 93 |
-
"learning_rate":
|
| 94 |
-
"loss":
|
| 95 |
"step": 130
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 1.54,
|
| 99 |
-
"learning_rate":
|
| 100 |
-
"loss":
|
| 101 |
"step": 140
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 1.65,
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss":
|
| 107 |
"step": 150
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 1.76,
|
| 111 |
-
"learning_rate":
|
| 112 |
-
"loss": 0.
|
| 113 |
"step": 160
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 1.87,
|
| 117 |
-
"learning_rate":
|
| 118 |
-
"loss":
|
| 119 |
"step": 170
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 1.98,
|
| 123 |
-
"learning_rate":
|
| 124 |
-
"loss":
|
| 125 |
"step": 180
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"epoch": 2.09,
|
| 129 |
-
"learning_rate":
|
| 130 |
-
"loss": 0.
|
| 131 |
"step": 190
|
| 132 |
},
|
| 133 |
{
|
| 134 |
"epoch": 2.2,
|
| 135 |
-
"learning_rate":
|
| 136 |
-
"loss": 0.
|
| 137 |
"step": 200
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 2.2,
|
| 141 |
-
"eval_accuracy": 0.
|
| 142 |
-
"eval_loss": 0.
|
| 143 |
-
"eval_runtime": 1.
|
| 144 |
-
"eval_samples_per_second": 105.
|
| 145 |
-
"eval_steps_per_second": 13.
|
| 146 |
"step": 200
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 2.31,
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 210
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 2.42,
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 220
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 2.53,
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss":
|
| 164 |
"step": 230
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 2.64,
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 240
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 2.75,
|
| 174 |
-
"learning_rate":
|
| 175 |
-
"loss": 0.
|
| 176 |
"step": 250
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 2.86,
|
| 180 |
-
"learning_rate":
|
| 181 |
-
"loss": 0.
|
| 182 |
"step": 260
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 2.97,
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 270
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 3.08,
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss": 0.
|
| 194 |
"step": 280
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 3.19,
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss": 0.
|
| 200 |
"step": 290
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 3.3,
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 300
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 3.3,
|
| 210 |
-
"eval_accuracy": 0.
|
| 211 |
-
"eval_loss": 0.
|
| 212 |
-
"eval_runtime":
|
| 213 |
-
"eval_samples_per_second":
|
| 214 |
-
"eval_steps_per_second":
|
| 215 |
"step": 300
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 3.41,
|
| 219 |
-
"learning_rate":
|
| 220 |
-
"loss": 0.
|
| 221 |
"step": 310
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 3.52,
|
| 225 |
-
"learning_rate":
|
| 226 |
-
"loss": 0.
|
| 227 |
"step": 320
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 3.63,
|
| 231 |
-
"learning_rate":
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 330
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 3.74,
|
| 237 |
-
"learning_rate":
|
| 238 |
-
"loss": 0.
|
| 239 |
"step": 340
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 3.85,
|
| 243 |
-
"learning_rate":
|
| 244 |
-
"loss": 0.
|
| 245 |
"step": 350
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 3.96,
|
| 249 |
-
"learning_rate":
|
| 250 |
-
"loss": 0.
|
| 251 |
"step": 360
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 4.07,
|
| 255 |
-
"learning_rate":
|
| 256 |
-
"loss": 0.
|
| 257 |
"step": 370
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 4.18,
|
| 261 |
-
"learning_rate":
|
| 262 |
-
"loss": 0.
|
| 263 |
"step": 380
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 4.29,
|
| 267 |
-
"learning_rate":
|
| 268 |
-
"loss": 0.
|
| 269 |
"step": 390
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 4.4,
|
| 273 |
-
"learning_rate":
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 400
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 4.4,
|
| 279 |
-
"eval_accuracy": 0.
|
| 280 |
-
"eval_loss": 0.
|
| 281 |
-
"eval_runtime": 1.
|
| 282 |
-
"eval_samples_per_second":
|
| 283 |
-
"eval_steps_per_second": 13.
|
| 284 |
"step": 400
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 4.51,
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 410
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 4.62,
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 420
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 4.73,
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 430
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 4.84,
|
| 306 |
-
"learning_rate":
|
| 307 |
-
"loss": 0.
|
| 308 |
"step": 440
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 4.95,
|
| 312 |
-
"learning_rate":
|
| 313 |
-
"loss": 0.
|
| 314 |
"step": 450
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 5.05,
|
| 318 |
-
"learning_rate":
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 460
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 5.16,
|
| 324 |
-
"learning_rate":
|
| 325 |
-
"loss": 0.
|
| 326 |
"step": 470
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 5.27,
|
| 330 |
-
"learning_rate":
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 480
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 5.38,
|
| 336 |
-
"learning_rate":
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 490
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 5.49,
|
| 342 |
-
"learning_rate":
|
| 343 |
-
"loss": 0.
|
| 344 |
"step": 500
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 5.49,
|
| 348 |
-
"eval_accuracy": 0.
|
| 349 |
-
"eval_loss": 0.
|
| 350 |
-
"eval_runtime": 1.
|
| 351 |
-
"eval_samples_per_second":
|
| 352 |
-
"eval_steps_per_second": 13.
|
| 353 |
"step": 500
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 5.6,
|
| 357 |
-
"learning_rate":
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 510
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 5.71,
|
| 363 |
-
"learning_rate":
|
| 364 |
-
"loss": 0.
|
| 365 |
"step": 520
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 5.82,
|
| 369 |
-
"learning_rate":
|
| 370 |
-
"loss": 0.
|
| 371 |
"step": 530
|
| 372 |
},
|
| 373 |
{
|
| 374 |
"epoch": 5.93,
|
| 375 |
-
"learning_rate":
|
| 376 |
-
"loss": 0.
|
| 377 |
"step": 540
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 6.04,
|
| 381 |
-
"learning_rate":
|
| 382 |
-
"loss": 0.
|
| 383 |
"step": 550
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 6.15,
|
| 387 |
-
"learning_rate":
|
| 388 |
-
"loss": 0.
|
| 389 |
"step": 560
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 6.26,
|
| 393 |
-
"learning_rate":
|
| 394 |
-
"loss": 0.
|
| 395 |
"step": 570
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 6.37,
|
| 399 |
-
"learning_rate":
|
| 400 |
-
"loss": 0.
|
| 401 |
"step": 580
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 6.48,
|
| 405 |
-
"learning_rate":
|
| 406 |
-
"loss": 0.
|
| 407 |
"step": 590
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 6.59,
|
| 411 |
-
"learning_rate":
|
| 412 |
-
"loss": 0.
|
| 413 |
"step": 600
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 6.59,
|
| 417 |
-
"eval_accuracy": 0.
|
| 418 |
-
"eval_loss": 0.
|
| 419 |
-
"eval_runtime": 1.
|
| 420 |
-
"eval_samples_per_second":
|
| 421 |
-
"eval_steps_per_second":
|
| 422 |
"step": 600
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 6.7,
|
| 426 |
-
"learning_rate":
|
| 427 |
-
"loss": 0.
|
| 428 |
"step": 610
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 6.81,
|
| 432 |
-
"learning_rate":
|
| 433 |
-
"loss": 0.
|
| 434 |
"step": 620
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 6.92,
|
| 438 |
-
"learning_rate":
|
| 439 |
-
"loss": 0.
|
| 440 |
"step": 630
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"epoch": 7.03,
|
| 444 |
-
"learning_rate":
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 640
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 7.14,
|
| 450 |
-
"learning_rate":
|
| 451 |
-
"loss": 0.
|
| 452 |
"step": 650
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 7.25,
|
| 456 |
-
"learning_rate":
|
| 457 |
-
"loss": 0.
|
| 458 |
"step": 660
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 7.36,
|
| 462 |
-
"learning_rate":
|
| 463 |
-
"loss": 0.
|
| 464 |
"step": 670
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 7.47,
|
| 468 |
-
"learning_rate":
|
| 469 |
-
"loss": 0.
|
| 470 |
"step": 680
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 7.58,
|
| 474 |
-
"learning_rate":
|
| 475 |
-
"loss": 0.
|
| 476 |
"step": 690
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 7.69,
|
| 480 |
-
"learning_rate":
|
| 481 |
-
"loss": 0.
|
| 482 |
"step": 700
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 7.69,
|
| 486 |
-
"eval_accuracy": 0.
|
| 487 |
-
"eval_loss": 0.
|
| 488 |
-
"eval_runtime":
|
| 489 |
-
"eval_samples_per_second":
|
| 490 |
-
"eval_steps_per_second":
|
| 491 |
"step": 700
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 7.8,
|
| 495 |
-
"learning_rate":
|
| 496 |
-
"loss": 0.
|
| 497 |
"step": 710
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 7.91,
|
| 501 |
-
"learning_rate":
|
| 502 |
-
"loss": 0.
|
| 503 |
"step": 720
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 8.02,
|
| 507 |
-
"learning_rate":
|
| 508 |
-
"loss": 0.
|
| 509 |
"step": 730
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 8.13,
|
| 513 |
-
"learning_rate":
|
| 514 |
-
"loss": 0.
|
| 515 |
"step": 740
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 8.24,
|
| 519 |
-
"learning_rate":
|
| 520 |
-
"loss": 0.
|
| 521 |
"step": 750
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 8.35,
|
| 525 |
-
"learning_rate":
|
| 526 |
-
"loss": 0.
|
| 527 |
"step": 760
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 8.46,
|
| 531 |
-
"learning_rate":
|
| 532 |
-
"loss": 0.
|
| 533 |
"step": 770
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 8.57,
|
| 537 |
-
"learning_rate":
|
| 538 |
-
"loss": 0.
|
| 539 |
"step": 780
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 8.68,
|
| 543 |
-
"learning_rate":
|
| 544 |
-
"loss": 0.
|
| 545 |
"step": 790
|
| 546 |
},
|
| 547 |
{
|
| 548 |
"epoch": 8.79,
|
| 549 |
-
"learning_rate":
|
| 550 |
-
"loss": 0.
|
| 551 |
"step": 800
|
| 552 |
},
|
| 553 |
{
|
| 554 |
"epoch": 8.79,
|
| 555 |
-
"eval_accuracy": 0.
|
| 556 |
-
"eval_loss": 0.
|
| 557 |
-
"eval_runtime": 1.
|
| 558 |
-
"eval_samples_per_second":
|
| 559 |
-
"eval_steps_per_second":
|
| 560 |
"step": 800
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 8.9,
|
| 564 |
-
"learning_rate":
|
| 565 |
-
"loss": 0.
|
| 566 |
"step": 810
|
| 567 |
},
|
| 568 |
{
|
| 569 |
"epoch": 9.01,
|
| 570 |
-
"learning_rate":
|
| 571 |
-
"loss": 0.
|
| 572 |
"step": 820
|
| 573 |
},
|
| 574 |
{
|
| 575 |
"epoch": 9.12,
|
| 576 |
-
"learning_rate":
|
| 577 |
-
"loss": 0.
|
| 578 |
"step": 830
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 9.23,
|
| 582 |
-
"learning_rate":
|
| 583 |
-
"loss": 0.
|
| 584 |
"step": 840
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 9.34,
|
| 588 |
-
"learning_rate":
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 850
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 9.45,
|
| 594 |
-
"learning_rate":
|
| 595 |
-
"loss": 0.
|
| 596 |
"step": 860
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 9.56,
|
| 600 |
-
"learning_rate":
|
| 601 |
-
"loss": 0.
|
| 602 |
"step": 870
|
| 603 |
},
|
| 604 |
{
|
| 605 |
"epoch": 9.67,
|
| 606 |
-
"learning_rate":
|
| 607 |
-
"loss": 0.
|
| 608 |
"step": 880
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 9.78,
|
| 612 |
-
"learning_rate":
|
| 613 |
-
"loss": 0.
|
| 614 |
"step": 890
|
| 615 |
},
|
| 616 |
{
|
| 617 |
"epoch": 9.89,
|
| 618 |
-
"learning_rate":
|
| 619 |
-
"loss": 0.
|
| 620 |
"step": 900
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 9.89,
|
| 624 |
-
"eval_accuracy": 0.
|
| 625 |
-
"eval_loss": 0.
|
| 626 |
-
"eval_runtime": 1.
|
| 627 |
-
"eval_samples_per_second":
|
| 628 |
-
"eval_steps_per_second":
|
| 629 |
"step": 900
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 10.0,
|
| 633 |
-
"learning_rate":
|
| 634 |
-
"loss": 0.
|
| 635 |
"step": 910
|
| 636 |
},
|
| 637 |
{
|
| 638 |
"epoch": 10.11,
|
| 639 |
-
"learning_rate":
|
| 640 |
-
"loss": 0.
|
| 641 |
"step": 920
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 10.22,
|
| 645 |
-
"learning_rate":
|
| 646 |
-
"loss": 0.
|
| 647 |
"step": 930
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 10.33,
|
| 651 |
-
"learning_rate":
|
| 652 |
-
"loss": 0.
|
| 653 |
"step": 940
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 10.44,
|
| 657 |
-
"learning_rate":
|
| 658 |
-
"loss": 0.
|
| 659 |
"step": 950
|
| 660 |
},
|
| 661 |
{
|
| 662 |
"epoch": 10.55,
|
| 663 |
-
"learning_rate":
|
| 664 |
-
"loss": 0.
|
| 665 |
"step": 960
|
| 666 |
},
|
| 667 |
{
|
| 668 |
"epoch": 10.66,
|
| 669 |
-
"learning_rate":
|
| 670 |
-
"loss": 0.
|
| 671 |
"step": 970
|
| 672 |
},
|
| 673 |
{
|
| 674 |
"epoch": 10.77,
|
| 675 |
-
"learning_rate":
|
| 676 |
-
"loss": 0.
|
| 677 |
"step": 980
|
| 678 |
},
|
| 679 |
{
|
| 680 |
"epoch": 10.88,
|
| 681 |
-
"learning_rate":
|
| 682 |
-
"loss": 0.
|
| 683 |
"step": 990
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 10.99,
|
| 687 |
-
"learning_rate":
|
| 688 |
-
"loss": 0.
|
| 689 |
"step": 1000
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 10.99,
|
| 693 |
-
"eval_accuracy": 0.
|
| 694 |
-
"eval_loss": 0.
|
| 695 |
-
"eval_runtime": 1.
|
| 696 |
-
"eval_samples_per_second":
|
| 697 |
-
"eval_steps_per_second":
|
| 698 |
"step": 1000
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 11.1,
|
| 702 |
-
"learning_rate":
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 1010
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 11.21,
|
| 708 |
-
"learning_rate":
|
| 709 |
-
"loss": 0.
|
| 710 |
"step": 1020
|
| 711 |
},
|
| 712 |
{
|
| 713 |
"epoch": 11.32,
|
| 714 |
-
"learning_rate":
|
| 715 |
-
"loss": 0.
|
| 716 |
"step": 1030
|
| 717 |
},
|
| 718 |
{
|
| 719 |
"epoch": 11.43,
|
| 720 |
-
"learning_rate":
|
| 721 |
-
"loss": 0.
|
| 722 |
"step": 1040
|
| 723 |
},
|
| 724 |
{
|
| 725 |
"epoch": 11.54,
|
| 726 |
-
"learning_rate":
|
| 727 |
-
"loss": 0.
|
| 728 |
"step": 1050
|
| 729 |
},
|
| 730 |
{
|
| 731 |
"epoch": 11.65,
|
| 732 |
-
"learning_rate":
|
| 733 |
-
"loss": 0.
|
| 734 |
"step": 1060
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 11.76,
|
| 738 |
-
"learning_rate":
|
| 739 |
-
"loss": 0.
|
| 740 |
"step": 1070
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 11.87,
|
| 744 |
-
"learning_rate":
|
| 745 |
-
"loss": 0.
|
| 746 |
"step": 1080
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 11.98,
|
| 750 |
-
"learning_rate":
|
| 751 |
-
"loss": 0.
|
| 752 |
"step": 1090
|
| 753 |
},
|
| 754 |
{
|
| 755 |
"epoch": 12.09,
|
| 756 |
-
"learning_rate":
|
| 757 |
-
"loss": 0.
|
| 758 |
"step": 1100
|
| 759 |
},
|
| 760 |
{
|
| 761 |
"epoch": 12.09,
|
| 762 |
-
"eval_accuracy": 0.
|
| 763 |
-
"eval_loss": 0.
|
| 764 |
-
"eval_runtime": 1.
|
| 765 |
-
"eval_samples_per_second":
|
| 766 |
-
"eval_steps_per_second":
|
| 767 |
"step": 1100
|
| 768 |
},
|
| 769 |
{
|
| 770 |
"epoch": 12.2,
|
| 771 |
-
"learning_rate":
|
| 772 |
-
"loss": 0.
|
| 773 |
"step": 1110
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 12.31,
|
| 777 |
-
"learning_rate":
|
| 778 |
-
"loss": 0.
|
| 779 |
"step": 1120
|
| 780 |
},
|
| 781 |
{
|
| 782 |
"epoch": 12.42,
|
| 783 |
-
"learning_rate":
|
| 784 |
-
"loss": 0.
|
| 785 |
"step": 1130
|
| 786 |
},
|
| 787 |
{
|
| 788 |
"epoch": 12.53,
|
| 789 |
-
"learning_rate":
|
| 790 |
-
"loss": 0.
|
| 791 |
"step": 1140
|
| 792 |
},
|
| 793 |
{
|
| 794 |
"epoch": 12.64,
|
| 795 |
-
"learning_rate":
|
| 796 |
-
"loss": 0.
|
| 797 |
"step": 1150
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 12.75,
|
| 801 |
-
"learning_rate":
|
| 802 |
-
"loss": 0.
|
| 803 |
"step": 1160
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 12.86,
|
| 807 |
-
"learning_rate":
|
| 808 |
-
"loss": 0.
|
| 809 |
"step": 1170
|
| 810 |
},
|
| 811 |
{
|
| 812 |
"epoch": 12.97,
|
| 813 |
-
"learning_rate":
|
| 814 |
-
"loss": 0.
|
| 815 |
"step": 1180
|
| 816 |
},
|
| 817 |
{
|
| 818 |
"epoch": 13.08,
|
| 819 |
-
"learning_rate":
|
| 820 |
-
"loss": 0.
|
| 821 |
"step": 1190
|
| 822 |
},
|
| 823 |
{
|
| 824 |
"epoch": 13.19,
|
| 825 |
-
"learning_rate":
|
| 826 |
-
"loss": 0.
|
| 827 |
"step": 1200
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 13.19,
|
| 831 |
-
"eval_accuracy": 0.
|
| 832 |
-
"eval_loss": 0.
|
| 833 |
-
"eval_runtime": 1.
|
| 834 |
-
"eval_samples_per_second":
|
| 835 |
-
"eval_steps_per_second":
|
| 836 |
"step": 1200
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 13.3,
|
| 840 |
-
"learning_rate":
|
| 841 |
-
"loss": 0.
|
| 842 |
"step": 1210
|
| 843 |
},
|
| 844 |
{
|
| 845 |
"epoch": 13.41,
|
| 846 |
-
"learning_rate":
|
| 847 |
-
"loss": 0.
|
| 848 |
"step": 1220
|
| 849 |
},
|
| 850 |
{
|
| 851 |
"epoch": 13.52,
|
| 852 |
-
"learning_rate":
|
| 853 |
-
"loss": 0.
|
| 854 |
"step": 1230
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 13.63,
|
| 858 |
-
"learning_rate":
|
| 859 |
-
"loss": 0.
|
| 860 |
"step": 1240
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 13.74,
|
| 864 |
-
"learning_rate":
|
| 865 |
-
"loss": 0.
|
| 866 |
"step": 1250
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 13.85,
|
| 870 |
-
"learning_rate":
|
| 871 |
-
"loss": 0.
|
| 872 |
"step": 1260
|
| 873 |
},
|
| 874 |
{
|
| 875 |
"epoch": 13.96,
|
| 876 |
-
"learning_rate":
|
| 877 |
-
"loss": 0.
|
| 878 |
"step": 1270
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 14.07,
|
| 882 |
-
"learning_rate":
|
| 883 |
-
"loss": 0.
|
| 884 |
"step": 1280
|
| 885 |
},
|
| 886 |
{
|
| 887 |
"epoch": 14.18,
|
| 888 |
-
"learning_rate":
|
| 889 |
-
"loss": 0.
|
| 890 |
"step": 1290
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 14.29,
|
| 894 |
-
"learning_rate":
|
| 895 |
-
"loss": 0.
|
| 896 |
"step": 1300
|
| 897 |
},
|
| 898 |
{
|
| 899 |
"epoch": 14.29,
|
| 900 |
-
"eval_accuracy": 0.
|
| 901 |
-
"eval_loss":
|
| 902 |
-
"eval_runtime": 1.
|
| 903 |
-
"eval_samples_per_second":
|
| 904 |
-
"eval_steps_per_second":
|
| 905 |
"step": 1300
|
| 906 |
},
|
| 907 |
{
|
| 908 |
"epoch": 14.4,
|
| 909 |
-
"learning_rate":
|
| 910 |
-
"loss": 0.
|
| 911 |
"step": 1310
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 14.51,
|
| 915 |
-
"learning_rate":
|
| 916 |
-
"loss": 0.
|
| 917 |
"step": 1320
|
| 918 |
},
|
| 919 |
{
|
| 920 |
"epoch": 14.62,
|
| 921 |
-
"learning_rate":
|
| 922 |
-
"loss": 0.
|
| 923 |
"step": 1330
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 14.73,
|
| 927 |
-
"learning_rate":
|
| 928 |
-
"loss": 0.
|
| 929 |
"step": 1340
|
| 930 |
},
|
| 931 |
{
|
| 932 |
"epoch": 14.84,
|
| 933 |
-
"learning_rate":
|
| 934 |
-
"loss": 0.
|
| 935 |
"step": 1350
|
| 936 |
},
|
| 937 |
{
|
| 938 |
"epoch": 14.95,
|
| 939 |
-
"learning_rate":
|
| 940 |
-
"loss": 0.
|
| 941 |
"step": 1360
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 15.05,
|
| 945 |
-
"learning_rate":
|
| 946 |
-
"loss": 0.
|
| 947 |
"step": 1370
|
| 948 |
},
|
| 949 |
{
|
| 950 |
"epoch": 15.16,
|
| 951 |
-
"learning_rate":
|
| 952 |
-
"loss": 0.
|
| 953 |
"step": 1380
|
| 954 |
},
|
| 955 |
{
|
| 956 |
"epoch": 15.27,
|
| 957 |
-
"learning_rate":
|
| 958 |
-
"loss": 0.
|
| 959 |
"step": 1390
|
| 960 |
},
|
| 961 |
{
|
| 962 |
"epoch": 15.38,
|
| 963 |
-
"learning_rate":
|
| 964 |
-
"loss": 0.
|
| 965 |
"step": 1400
|
| 966 |
},
|
| 967 |
{
|
| 968 |
"epoch": 15.38,
|
| 969 |
-
"eval_accuracy": 0.
|
| 970 |
-
"eval_loss": 0.
|
| 971 |
-
"eval_runtime": 1.
|
| 972 |
-
"eval_samples_per_second":
|
| 973 |
-
"eval_steps_per_second":
|
| 974 |
"step": 1400
|
| 975 |
},
|
| 976 |
{
|
| 977 |
"epoch": 15.49,
|
| 978 |
-
"learning_rate":
|
| 979 |
-
"loss": 0.
|
| 980 |
"step": 1410
|
| 981 |
},
|
| 982 |
{
|
| 983 |
"epoch": 15.6,
|
| 984 |
-
"learning_rate":
|
| 985 |
-
"loss": 0.
|
| 986 |
"step": 1420
|
| 987 |
},
|
| 988 |
{
|
| 989 |
"epoch": 15.71,
|
| 990 |
-
"learning_rate":
|
| 991 |
-
"loss": 0.
|
| 992 |
"step": 1430
|
| 993 |
},
|
| 994 |
{
|
| 995 |
"epoch": 15.82,
|
| 996 |
-
"learning_rate":
|
| 997 |
-
"loss": 0.
|
| 998 |
"step": 1440
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 15.93,
|
| 1002 |
-
"learning_rate":
|
| 1003 |
-
"loss": 0.
|
| 1004 |
"step": 1450
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
"epoch": 16.04,
|
| 1008 |
-
"learning_rate":
|
| 1009 |
-
"loss": 0.
|
| 1010 |
"step": 1460
|
| 1011 |
},
|
| 1012 |
{
|
| 1013 |
"epoch": 16.15,
|
| 1014 |
-
"learning_rate":
|
| 1015 |
-
"loss": 0.
|
| 1016 |
"step": 1470
|
| 1017 |
},
|
| 1018 |
{
|
| 1019 |
"epoch": 16.26,
|
| 1020 |
-
"learning_rate":
|
| 1021 |
-
"loss": 0.
|
| 1022 |
"step": 1480
|
| 1023 |
},
|
| 1024 |
{
|
| 1025 |
"epoch": 16.37,
|
| 1026 |
-
"learning_rate":
|
| 1027 |
-
"loss": 0.
|
| 1028 |
"step": 1490
|
| 1029 |
},
|
| 1030 |
{
|
| 1031 |
"epoch": 16.48,
|
| 1032 |
-
"learning_rate":
|
| 1033 |
-
"loss": 0.
|
| 1034 |
"step": 1500
|
| 1035 |
},
|
| 1036 |
{
|
| 1037 |
"epoch": 16.48,
|
| 1038 |
-
"eval_accuracy": 0.
|
| 1039 |
-
"eval_loss": 0.
|
| 1040 |
-
"eval_runtime": 1.
|
| 1041 |
-
"eval_samples_per_second":
|
| 1042 |
-
"eval_steps_per_second":
|
| 1043 |
"step": 1500
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
"epoch": 16.59,
|
| 1047 |
-
"learning_rate":
|
| 1048 |
-
"loss": 0.
|
| 1049 |
"step": 1510
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 16.7,
|
| 1053 |
-
"learning_rate":
|
| 1054 |
-
"loss": 0.
|
| 1055 |
"step": 1520
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 16.81,
|
| 1059 |
-
"learning_rate":
|
| 1060 |
-
"loss": 0.
|
| 1061 |
"step": 1530
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
"epoch": 16.92,
|
| 1065 |
-
"learning_rate":
|
| 1066 |
-
"loss": 0.
|
| 1067 |
"step": 1540
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
"epoch": 17.03,
|
| 1071 |
-
"learning_rate":
|
| 1072 |
-
"loss": 0.
|
| 1073 |
"step": 1550
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
"epoch": 17.14,
|
| 1077 |
-
"learning_rate":
|
| 1078 |
-
"loss": 0.
|
| 1079 |
"step": 1560
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
"epoch": 17.25,
|
| 1083 |
-
"learning_rate":
|
| 1084 |
-
"loss": 0.
|
| 1085 |
"step": 1570
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 17.36,
|
| 1089 |
-
"learning_rate":
|
| 1090 |
-
"loss": 0.
|
| 1091 |
"step": 1580
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
"epoch": 17.47,
|
| 1095 |
-
"learning_rate":
|
| 1096 |
-
"loss": 0.
|
| 1097 |
"step": 1590
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
"epoch": 17.58,
|
| 1101 |
-
"learning_rate":
|
| 1102 |
-
"loss": 0.
|
| 1103 |
"step": 1600
|
| 1104 |
},
|
| 1105 |
{
|
| 1106 |
"epoch": 17.58,
|
| 1107 |
-
"eval_accuracy": 0.
|
| 1108 |
-
"eval_loss": 0.
|
| 1109 |
-
"eval_runtime": 1.
|
| 1110 |
-
"eval_samples_per_second":
|
| 1111 |
-
"eval_steps_per_second":
|
| 1112 |
"step": 1600
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
"epoch": 17.69,
|
| 1116 |
-
"learning_rate":
|
| 1117 |
-
"loss": 0.
|
| 1118 |
"step": 1610
|
| 1119 |
},
|
| 1120 |
{
|
| 1121 |
"epoch": 17.8,
|
| 1122 |
-
"learning_rate":
|
| 1123 |
-
"loss": 0.
|
| 1124 |
"step": 1620
|
| 1125 |
},
|
| 1126 |
{
|
| 1127 |
"epoch": 17.91,
|
| 1128 |
-
"learning_rate":
|
| 1129 |
-
"loss": 0.
|
| 1130 |
"step": 1630
|
| 1131 |
},
|
| 1132 |
{
|
| 1133 |
"epoch": 18.02,
|
| 1134 |
-
"learning_rate":
|
| 1135 |
-
"loss": 0.
|
| 1136 |
"step": 1640
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 18.13,
|
| 1140 |
-
"learning_rate":
|
| 1141 |
-
"loss": 0.
|
| 1142 |
"step": 1650
|
| 1143 |
},
|
| 1144 |
{
|
| 1145 |
"epoch": 18.24,
|
| 1146 |
-
"learning_rate":
|
| 1147 |
-
"loss": 0.
|
| 1148 |
"step": 1660
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 18.35,
|
| 1152 |
-
"learning_rate":
|
| 1153 |
-
"loss": 0.
|
| 1154 |
"step": 1670
|
| 1155 |
},
|
| 1156 |
{
|
| 1157 |
"epoch": 18.46,
|
| 1158 |
-
"learning_rate":
|
| 1159 |
-
"loss": 0.
|
| 1160 |
"step": 1680
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
"epoch": 18.57,
|
| 1164 |
-
"learning_rate":
|
| 1165 |
-
"loss": 0.
|
| 1166 |
"step": 1690
|
| 1167 |
},
|
| 1168 |
{
|
| 1169 |
"epoch": 18.68,
|
| 1170 |
-
"learning_rate":
|
| 1171 |
-
"loss": 0.
|
| 1172 |
"step": 1700
|
| 1173 |
},
|
| 1174 |
{
|
| 1175 |
"epoch": 18.68,
|
| 1176 |
-
"eval_accuracy": 0.
|
| 1177 |
-
"eval_loss": 0.
|
| 1178 |
-
"eval_runtime": 1.
|
| 1179 |
-
"eval_samples_per_second":
|
| 1180 |
-
"eval_steps_per_second":
|
| 1181 |
"step": 1700
|
| 1182 |
},
|
| 1183 |
{
|
| 1184 |
"epoch": 18.79,
|
| 1185 |
-
"learning_rate":
|
| 1186 |
-
"loss": 0.
|
| 1187 |
"step": 1710
|
| 1188 |
},
|
| 1189 |
{
|
| 1190 |
"epoch": 18.9,
|
| 1191 |
-
"learning_rate":
|
| 1192 |
-
"loss": 0.
|
| 1193 |
"step": 1720
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
"epoch": 19.01,
|
| 1197 |
-
"learning_rate":
|
| 1198 |
-
"loss": 0.
|
| 1199 |
"step": 1730
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
"epoch": 19.12,
|
| 1203 |
-
"learning_rate":
|
| 1204 |
-
"loss": 0.
|
| 1205 |
"step": 1740
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
"epoch": 19.23,
|
| 1209 |
-
"learning_rate":
|
| 1210 |
-
"loss": 0.
|
| 1211 |
"step": 1750
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
"epoch": 19.34,
|
| 1215 |
-
"learning_rate":
|
| 1216 |
-
"loss": 0.
|
| 1217 |
"step": 1760
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
"epoch": 19.45,
|
| 1221 |
-
"learning_rate":
|
| 1222 |
-
"loss": 0.
|
| 1223 |
"step": 1770
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
"epoch": 19.56,
|
| 1227 |
-
"learning_rate":
|
| 1228 |
-
"loss": 0.
|
| 1229 |
"step": 1780
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
"epoch": 19.67,
|
| 1233 |
-
"learning_rate":
|
| 1234 |
-
"loss": 0.
|
| 1235 |
"step": 1790
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
"epoch": 19.78,
|
| 1239 |
-
"learning_rate":
|
| 1240 |
-
"loss": 0.
|
| 1241 |
"step": 1800
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 19.78,
|
| 1245 |
-
"eval_accuracy": 0.
|
| 1246 |
-
"eval_loss": 0.
|
| 1247 |
-
"eval_runtime": 1.
|
| 1248 |
-
"eval_samples_per_second":
|
| 1249 |
-
"eval_steps_per_second":
|
| 1250 |
"step": 1800
|
| 1251 |
},
|
| 1252 |
{
|
| 1253 |
"epoch": 19.89,
|
| 1254 |
-
"learning_rate":
|
| 1255 |
-
"loss": 0.
|
| 1256 |
"step": 1810
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
"epoch": 20.0,
|
| 1260 |
-
"learning_rate":
|
| 1261 |
-
"loss": 0.
|
| 1262 |
"step": 1820
|
| 1263 |
},
|
| 1264 |
{
|
| 1265 |
"epoch": 20.11,
|
| 1266 |
-
"learning_rate":
|
| 1267 |
-
"loss": 0.
|
| 1268 |
"step": 1830
|
| 1269 |
},
|
| 1270 |
{
|
| 1271 |
"epoch": 20.22,
|
| 1272 |
-
"learning_rate":
|
| 1273 |
-
"loss": 0.
|
| 1274 |
"step": 1840
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 20.33,
|
| 1278 |
-
"learning_rate":
|
| 1279 |
-
"loss": 0.
|
| 1280 |
"step": 1850
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
"epoch": 20.44,
|
| 1284 |
-
"learning_rate":
|
| 1285 |
-
"loss": 0.
|
| 1286 |
"step": 1860
|
| 1287 |
},
|
| 1288 |
{
|
| 1289 |
"epoch": 20.55,
|
| 1290 |
-
"learning_rate":
|
| 1291 |
-
"loss": 0.
|
| 1292 |
"step": 1870
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
"epoch": 20.66,
|
| 1296 |
-
"learning_rate":
|
| 1297 |
-
"loss": 0.
|
| 1298 |
"step": 1880
|
| 1299 |
},
|
| 1300 |
{
|
| 1301 |
"epoch": 20.77,
|
| 1302 |
-
"learning_rate":
|
| 1303 |
-
"loss": 0.
|
| 1304 |
"step": 1890
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
"epoch": 20.88,
|
| 1308 |
-
"learning_rate":
|
| 1309 |
-
"loss": 0.
|
| 1310 |
"step": 1900
|
| 1311 |
},
|
| 1312 |
{
|
| 1313 |
"epoch": 20.88,
|
| 1314 |
-
"eval_accuracy": 0.
|
| 1315 |
-
"eval_loss": 0.
|
| 1316 |
-
"eval_runtime": 1.
|
| 1317 |
-
"eval_samples_per_second":
|
| 1318 |
-
"eval_steps_per_second":
|
| 1319 |
"step": 1900
|
| 1320 |
},
|
| 1321 |
{
|
| 1322 |
"epoch": 20.99,
|
| 1323 |
-
"learning_rate":
|
| 1324 |
-
"loss": 0.
|
| 1325 |
"step": 1910
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
"epoch": 21.1,
|
| 1329 |
-
"learning_rate":
|
| 1330 |
-
"loss": 0.
|
| 1331 |
"step": 1920
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
"epoch": 21.21,
|
| 1335 |
-
"learning_rate":
|
| 1336 |
-
"loss": 0.
|
| 1337 |
"step": 1930
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
"epoch": 21.32,
|
| 1341 |
-
"learning_rate":
|
| 1342 |
-
"loss": 0.
|
| 1343 |
"step": 1940
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
"epoch": 21.43,
|
| 1347 |
-
"learning_rate":
|
| 1348 |
-
"loss": 0.
|
| 1349 |
"step": 1950
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 21.54,
|
| 1353 |
-
"learning_rate":
|
| 1354 |
-
"loss": 0.
|
| 1355 |
"step": 1960
|
| 1356 |
},
|
| 1357 |
{
|
| 1358 |
"epoch": 21.65,
|
| 1359 |
-
"learning_rate":
|
| 1360 |
-
"loss": 0.
|
| 1361 |
"step": 1970
|
| 1362 |
},
|
| 1363 |
{
|
| 1364 |
"epoch": 21.76,
|
| 1365 |
-
"learning_rate":
|
| 1366 |
-
"loss": 0.
|
| 1367 |
"step": 1980
|
| 1368 |
},
|
| 1369 |
{
|
| 1370 |
"epoch": 21.87,
|
| 1371 |
-
"learning_rate":
|
| 1372 |
-
"loss": 0.
|
| 1373 |
"step": 1990
|
| 1374 |
},
|
| 1375 |
{
|
| 1376 |
"epoch": 21.98,
|
| 1377 |
-
"learning_rate":
|
| 1378 |
-
"loss": 0.
|
| 1379 |
"step": 2000
|
| 1380 |
},
|
| 1381 |
{
|
| 1382 |
"epoch": 21.98,
|
| 1383 |
-
"eval_accuracy": 0.
|
| 1384 |
-
"eval_loss": 0.
|
| 1385 |
-
"eval_runtime": 1.
|
| 1386 |
-
"eval_samples_per_second":
|
| 1387 |
-
"eval_steps_per_second":
|
| 1388 |
"step": 2000
|
| 1389 |
},
|
| 1390 |
{
|
| 1391 |
"epoch": 22.09,
|
| 1392 |
-
"learning_rate":
|
| 1393 |
-
"loss": 0.
|
| 1394 |
"step": 2010
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 22.2,
|
| 1398 |
-
"learning_rate":
|
| 1399 |
-
"loss": 0.
|
| 1400 |
"step": 2020
|
| 1401 |
},
|
| 1402 |
{
|
| 1403 |
"epoch": 22.31,
|
| 1404 |
-
"learning_rate":
|
| 1405 |
-
"loss": 0.
|
| 1406 |
"step": 2030
|
| 1407 |
},
|
| 1408 |
{
|
| 1409 |
"epoch": 22.42,
|
| 1410 |
-
"learning_rate":
|
| 1411 |
-
"loss": 0.
|
| 1412 |
"step": 2040
|
| 1413 |
},
|
| 1414 |
{
|
| 1415 |
"epoch": 22.53,
|
| 1416 |
-
"learning_rate": 1.
|
| 1417 |
-
"loss": 0.
|
| 1418 |
"step": 2050
|
| 1419 |
},
|
| 1420 |
{
|
| 1421 |
"epoch": 22.64,
|
| 1422 |
-
"learning_rate": 1.
|
| 1423 |
-
"loss": 0.
|
| 1424 |
"step": 2060
|
| 1425 |
},
|
| 1426 |
{
|
| 1427 |
"epoch": 22.75,
|
| 1428 |
-
"learning_rate": 1.
|
| 1429 |
-
"loss": 0.
|
| 1430 |
"step": 2070
|
| 1431 |
},
|
| 1432 |
{
|
| 1433 |
"epoch": 22.86,
|
| 1434 |
-
"learning_rate": 1.
|
| 1435 |
-
"loss": 0.
|
| 1436 |
"step": 2080
|
| 1437 |
},
|
| 1438 |
{
|
| 1439 |
"epoch": 22.97,
|
| 1440 |
-
"learning_rate": 1.
|
| 1441 |
-
"loss": 0.
|
| 1442 |
"step": 2090
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
"epoch": 23.08,
|
| 1446 |
-
"learning_rate": 1.
|
| 1447 |
-
"loss": 0.
|
| 1448 |
"step": 2100
|
| 1449 |
},
|
| 1450 |
{
|
| 1451 |
"epoch": 23.08,
|
| 1452 |
-
"eval_accuracy": 0.
|
| 1453 |
-
"eval_loss": 0.
|
| 1454 |
-
"eval_runtime": 1.
|
| 1455 |
-
"eval_samples_per_second":
|
| 1456 |
-
"eval_steps_per_second":
|
| 1457 |
"step": 2100
|
| 1458 |
},
|
| 1459 |
{
|
| 1460 |
"epoch": 23.19,
|
| 1461 |
-
"learning_rate": 1.
|
| 1462 |
-
"loss": 0.
|
| 1463 |
"step": 2110
|
| 1464 |
},
|
| 1465 |
{
|
| 1466 |
"epoch": 23.3,
|
| 1467 |
-
"learning_rate": 1.
|
| 1468 |
-
"loss": 0.
|
| 1469 |
"step": 2120
|
| 1470 |
},
|
| 1471 |
{
|
| 1472 |
"epoch": 23.41,
|
| 1473 |
-
"learning_rate": 1.
|
| 1474 |
-
"loss": 0.
|
| 1475 |
"step": 2130
|
| 1476 |
},
|
| 1477 |
{
|
| 1478 |
"epoch": 23.52,
|
| 1479 |
-
"learning_rate": 1.
|
| 1480 |
-
"loss": 0.
|
| 1481 |
"step": 2140
|
| 1482 |
},
|
| 1483 |
{
|
| 1484 |
"epoch": 23.63,
|
| 1485 |
-
"learning_rate": 1.
|
| 1486 |
-
"loss": 0.
|
| 1487 |
"step": 2150
|
| 1488 |
},
|
| 1489 |
{
|
| 1490 |
"epoch": 23.74,
|
| 1491 |
-
"learning_rate": 1.
|
| 1492 |
-
"loss": 0.
|
| 1493 |
"step": 2160
|
| 1494 |
},
|
| 1495 |
{
|
| 1496 |
"epoch": 23.85,
|
| 1497 |
-
"learning_rate":
|
| 1498 |
-
"loss": 0.
|
| 1499 |
"step": 2170
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
"epoch": 23.96,
|
| 1503 |
-
"learning_rate":
|
| 1504 |
-
"loss": 0.
|
| 1505 |
"step": 2180
|
| 1506 |
},
|
| 1507 |
{
|
| 1508 |
"epoch": 24.07,
|
| 1509 |
-
"learning_rate":
|
| 1510 |
-
"loss": 0.
|
| 1511 |
"step": 2190
|
| 1512 |
},
|
| 1513 |
{
|
| 1514 |
"epoch": 24.18,
|
| 1515 |
-
"learning_rate":
|
| 1516 |
-
"loss": 0.
|
| 1517 |
"step": 2200
|
| 1518 |
},
|
| 1519 |
{
|
| 1520 |
"epoch": 24.18,
|
| 1521 |
-
"eval_accuracy": 0.
|
| 1522 |
-
"eval_loss": 0.
|
| 1523 |
-
"eval_runtime": 1.
|
| 1524 |
-
"eval_samples_per_second":
|
| 1525 |
-
"eval_steps_per_second":
|
| 1526 |
"step": 2200
|
| 1527 |
},
|
| 1528 |
{
|
| 1529 |
"epoch": 24.29,
|
| 1530 |
-
"learning_rate":
|
| 1531 |
-
"loss": 0.
|
| 1532 |
"step": 2210
|
| 1533 |
},
|
| 1534 |
{
|
| 1535 |
"epoch": 24.4,
|
| 1536 |
-
"learning_rate":
|
| 1537 |
-
"loss": 0.
|
| 1538 |
"step": 2220
|
| 1539 |
},
|
| 1540 |
{
|
| 1541 |
"epoch": 24.51,
|
| 1542 |
-
"learning_rate":
|
| 1543 |
-
"loss": 0.
|
| 1544 |
"step": 2230
|
| 1545 |
},
|
| 1546 |
{
|
| 1547 |
"epoch": 24.62,
|
| 1548 |
-
"learning_rate":
|
| 1549 |
-
"loss": 0.
|
| 1550 |
"step": 2240
|
| 1551 |
},
|
| 1552 |
{
|
| 1553 |
"epoch": 24.73,
|
| 1554 |
-
"learning_rate":
|
| 1555 |
-
"loss": 0.
|
| 1556 |
"step": 2250
|
| 1557 |
},
|
| 1558 |
{
|
| 1559 |
"epoch": 24.84,
|
| 1560 |
-
"learning_rate": 1.
|
| 1561 |
-
"loss": 0.
|
| 1562 |
"step": 2260
|
| 1563 |
},
|
| 1564 |
{
|
| 1565 |
"epoch": 24.95,
|
| 1566 |
-
"learning_rate":
|
| 1567 |
-
"loss": 0.
|
| 1568 |
"step": 2270
|
| 1569 |
},
|
| 1570 |
{
|
| 1571 |
-
"epoch": 25.
|
| 1572 |
-
"
|
| 1573 |
-
"
|
| 1574 |
-
"
|
| 1575 |
-
|
| 1576 |
-
|
| 1577 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1578 |
}
|
| 1579 |
],
|
| 1580 |
-
"max_steps":
|
| 1581 |
-
"num_train_epochs":
|
| 1582 |
-
"total_flos":
|
| 1583 |
"trial_name": null,
|
| 1584 |
"trial_params": null
|
| 1585 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6692019104957581,
|
| 3 |
+
"best_model_checkpoint": "./croupier-creature-classifier/checkpoint-2000",
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 4550,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 2.9934065934065934e-05,
|
| 13 |
+
"loss": 1.3796,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.22,
|
| 18 |
+
"learning_rate": 2.9868131868131868e-05,
|
| 19 |
+
"loss": 1.3597,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.33,
|
| 24 |
+
"learning_rate": 2.9802197802197805e-05,
|
| 25 |
+
"loss": 1.3427,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.44,
|
| 30 |
+
"learning_rate": 2.973626373626374e-05,
|
| 31 |
+
"loss": 1.3331,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.55,
|
| 36 |
+
"learning_rate": 2.9670329670329673e-05,
|
| 37 |
+
"loss": 1.275,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.66,
|
| 42 |
+
"learning_rate": 2.9604395604395606e-05,
|
| 43 |
+
"loss": 1.2765,
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.77,
|
| 48 |
+
"learning_rate": 2.953846153846154e-05,
|
| 49 |
+
"loss": 1.2306,
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.88,
|
| 54 |
+
"learning_rate": 2.947252747252747e-05,
|
| 55 |
+
"loss": 1.2621,
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.99,
|
| 60 |
+
"learning_rate": 2.9406593406593407e-05,
|
| 61 |
+
"loss": 1.1997,
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 1.1,
|
| 66 |
+
"learning_rate": 2.934065934065934e-05,
|
| 67 |
+
"loss": 1.1159,
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 1.1,
|
| 72 |
+
"eval_accuracy": 0.611764705882353,
|
| 73 |
+
"eval_loss": 1.1144014596939087,
|
| 74 |
+
"eval_runtime": 1.5221,
|
| 75 |
+
"eval_samples_per_second": 111.687,
|
| 76 |
+
"eval_steps_per_second": 14.454,
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 1.21,
|
| 81 |
+
"learning_rate": 2.9274725274725275e-05,
|
| 82 |
+
"loss": 1.0839,
|
| 83 |
"step": 110
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 1.32,
|
| 87 |
+
"learning_rate": 2.920879120879121e-05,
|
| 88 |
+
"loss": 1.0689,
|
| 89 |
"step": 120
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 1.43,
|
| 93 |
+
"learning_rate": 2.9142857142857142e-05,
|
| 94 |
+
"loss": 0.9898,
|
| 95 |
"step": 130
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 1.54,
|
| 99 |
+
"learning_rate": 2.907692307692308e-05,
|
| 100 |
+
"loss": 0.9495,
|
| 101 |
"step": 140
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 1.65,
|
| 105 |
+
"learning_rate": 2.9010989010989013e-05,
|
| 106 |
+
"loss": 0.9943,
|
| 107 |
"step": 150
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 1.76,
|
| 111 |
+
"learning_rate": 2.8945054945054947e-05,
|
| 112 |
+
"loss": 0.98,
|
| 113 |
"step": 160
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 1.87,
|
| 117 |
+
"learning_rate": 2.887912087912088e-05,
|
| 118 |
+
"loss": 0.9986,
|
| 119 |
"step": 170
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 1.98,
|
| 123 |
+
"learning_rate": 2.8813186813186814e-05,
|
| 124 |
+
"loss": 0.9522,
|
| 125 |
"step": 180
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"epoch": 2.09,
|
| 129 |
+
"learning_rate": 2.8747252747252748e-05,
|
| 130 |
+
"loss": 0.8533,
|
| 131 |
"step": 190
|
| 132 |
},
|
| 133 |
{
|
| 134 |
"epoch": 2.2,
|
| 135 |
+
"learning_rate": 2.8681318681318685e-05,
|
| 136 |
+
"loss": 0.8183,
|
| 137 |
"step": 200
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 2.2,
|
| 141 |
+
"eval_accuracy": 0.6882352941176471,
|
| 142 |
+
"eval_loss": 0.9109101891517639,
|
| 143 |
+
"eval_runtime": 1.6142,
|
| 144 |
+
"eval_samples_per_second": 105.317,
|
| 145 |
+
"eval_steps_per_second": 13.629,
|
| 146 |
"step": 200
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 2.31,
|
| 150 |
+
"learning_rate": 2.861538461538462e-05,
|
| 151 |
+
"loss": 0.7843,
|
| 152 |
"step": 210
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 2.42,
|
| 156 |
+
"learning_rate": 2.854945054945055e-05,
|
| 157 |
+
"loss": 0.8093,
|
| 158 |
"step": 220
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 2.53,
|
| 162 |
+
"learning_rate": 2.8483516483516482e-05,
|
| 163 |
+
"loss": 0.8541,
|
| 164 |
"step": 230
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 2.64,
|
| 168 |
+
"learning_rate": 2.8417582417582416e-05,
|
| 169 |
+
"loss": 0.7405,
|
| 170 |
"step": 240
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 2.75,
|
| 174 |
+
"learning_rate": 2.8351648351648353e-05,
|
| 175 |
+
"loss": 0.7858,
|
| 176 |
"step": 250
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 2.86,
|
| 180 |
+
"learning_rate": 2.8285714285714287e-05,
|
| 181 |
+
"loss": 0.7966,
|
| 182 |
"step": 260
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 2.97,
|
| 186 |
+
"learning_rate": 2.821978021978022e-05,
|
| 187 |
+
"loss": 0.695,
|
| 188 |
"step": 270
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 3.08,
|
| 192 |
+
"learning_rate": 2.8153846153846154e-05,
|
| 193 |
+
"loss": 0.6649,
|
| 194 |
"step": 280
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 3.19,
|
| 198 |
+
"learning_rate": 2.8087912087912088e-05,
|
| 199 |
+
"loss": 0.605,
|
| 200 |
"step": 290
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 3.3,
|
| 204 |
+
"learning_rate": 2.802197802197802e-05,
|
| 205 |
+
"loss": 0.6829,
|
| 206 |
"step": 300
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 3.3,
|
| 210 |
+
"eval_accuracy": 0.7235294117647059,
|
| 211 |
+
"eval_loss": 0.7676671743392944,
|
| 212 |
+
"eval_runtime": 1.6247,
|
| 213 |
+
"eval_samples_per_second": 104.633,
|
| 214 |
+
"eval_steps_per_second": 13.541,
|
| 215 |
"step": 300
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 3.41,
|
| 219 |
+
"learning_rate": 2.795604395604396e-05,
|
| 220 |
+
"loss": 0.5722,
|
| 221 |
"step": 310
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 3.52,
|
| 225 |
+
"learning_rate": 2.7890109890109892e-05,
|
| 226 |
+
"loss": 0.654,
|
| 227 |
"step": 320
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 3.63,
|
| 231 |
+
"learning_rate": 2.7824175824175826e-05,
|
| 232 |
+
"loss": 0.7001,
|
| 233 |
"step": 330
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 3.74,
|
| 237 |
+
"learning_rate": 2.775824175824176e-05,
|
| 238 |
+
"loss": 0.5804,
|
| 239 |
"step": 340
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 3.85,
|
| 243 |
+
"learning_rate": 2.7692307692307694e-05,
|
| 244 |
+
"loss": 0.6638,
|
| 245 |
"step": 350
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 3.96,
|
| 249 |
+
"learning_rate": 2.7626373626373624e-05,
|
| 250 |
+
"loss": 0.6668,
|
| 251 |
"step": 360
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 4.07,
|
| 255 |
+
"learning_rate": 2.756043956043956e-05,
|
| 256 |
+
"loss": 0.5599,
|
| 257 |
"step": 370
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 4.18,
|
| 261 |
+
"learning_rate": 2.7494505494505495e-05,
|
| 262 |
+
"loss": 0.5317,
|
| 263 |
"step": 380
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 4.29,
|
| 267 |
+
"learning_rate": 2.7428571428571428e-05,
|
| 268 |
+
"loss": 0.5403,
|
| 269 |
"step": 390
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 4.4,
|
| 273 |
+
"learning_rate": 2.7362637362637362e-05,
|
| 274 |
+
"loss": 0.5575,
|
| 275 |
"step": 400
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 4.4,
|
| 279 |
+
"eval_accuracy": 0.6764705882352942,
|
| 280 |
+
"eval_loss": 0.7670463919639587,
|
| 281 |
+
"eval_runtime": 1.6237,
|
| 282 |
+
"eval_samples_per_second": 104.698,
|
| 283 |
+
"eval_steps_per_second": 13.549,
|
| 284 |
"step": 400
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 4.51,
|
| 288 |
+
"learning_rate": 2.7296703296703296e-05,
|
| 289 |
+
"loss": 0.5018,
|
| 290 |
"step": 410
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 4.62,
|
| 294 |
+
"learning_rate": 2.7230769230769233e-05,
|
| 295 |
+
"loss": 0.5715,
|
| 296 |
"step": 420
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 4.73,
|
| 300 |
+
"learning_rate": 2.7164835164835166e-05,
|
| 301 |
+
"loss": 0.4884,
|
| 302 |
"step": 430
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 4.84,
|
| 306 |
+
"learning_rate": 2.7105494505494504e-05,
|
| 307 |
+
"loss": 0.5533,
|
| 308 |
"step": 440
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 4.95,
|
| 312 |
+
"learning_rate": 2.703956043956044e-05,
|
| 313 |
+
"loss": 0.5183,
|
| 314 |
"step": 450
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 5.05,
|
| 318 |
+
"learning_rate": 2.6973626373626375e-05,
|
| 319 |
+
"loss": 0.4451,
|
| 320 |
"step": 460
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 5.16,
|
| 324 |
+
"learning_rate": 2.690769230769231e-05,
|
| 325 |
+
"loss": 0.4605,
|
| 326 |
"step": 470
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 5.27,
|
| 330 |
+
"learning_rate": 2.6841758241758243e-05,
|
| 331 |
+
"loss": 0.4289,
|
| 332 |
"step": 480
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 5.38,
|
| 336 |
+
"learning_rate": 2.6775824175824176e-05,
|
| 337 |
+
"loss": 0.4433,
|
| 338 |
"step": 490
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 5.49,
|
| 342 |
+
"learning_rate": 2.670989010989011e-05,
|
| 343 |
+
"loss": 0.4644,
|
| 344 |
"step": 500
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 5.49,
|
| 348 |
+
"eval_accuracy": 0.6647058823529411,
|
| 349 |
+
"eval_loss": 0.8459996581077576,
|
| 350 |
+
"eval_runtime": 1.6386,
|
| 351 |
+
"eval_samples_per_second": 103.747,
|
| 352 |
+
"eval_steps_per_second": 13.426,
|
| 353 |
"step": 500
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 5.6,
|
| 357 |
+
"learning_rate": 2.6643956043956047e-05,
|
| 358 |
+
"loss": 0.4732,
|
| 359 |
"step": 510
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 5.71,
|
| 363 |
+
"learning_rate": 2.657802197802198e-05,
|
| 364 |
+
"loss": 0.4939,
|
| 365 |
"step": 520
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 5.82,
|
| 369 |
+
"learning_rate": 2.651208791208791e-05,
|
| 370 |
+
"loss": 0.4209,
|
| 371 |
"step": 530
|
| 372 |
},
|
| 373 |
{
|
| 374 |
"epoch": 5.93,
|
| 375 |
+
"learning_rate": 2.6446153846153845e-05,
|
| 376 |
+
"loss": 0.3783,
|
| 377 |
"step": 540
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 6.04,
|
| 381 |
+
"learning_rate": 2.638021978021978e-05,
|
| 382 |
+
"loss": 0.4665,
|
| 383 |
"step": 550
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 6.15,
|
| 387 |
+
"learning_rate": 2.6314285714285715e-05,
|
| 388 |
+
"loss": 0.2572,
|
| 389 |
"step": 560
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 6.26,
|
| 393 |
+
"learning_rate": 2.624835164835165e-05,
|
| 394 |
+
"loss": 0.3752,
|
| 395 |
"step": 570
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 6.37,
|
| 399 |
+
"learning_rate": 2.6182417582417583e-05,
|
| 400 |
+
"loss": 0.2943,
|
| 401 |
"step": 580
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 6.48,
|
| 405 |
+
"learning_rate": 2.6116483516483517e-05,
|
| 406 |
+
"loss": 0.3949,
|
| 407 |
"step": 590
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 6.59,
|
| 411 |
+
"learning_rate": 2.605054945054945e-05,
|
| 412 |
+
"loss": 0.3096,
|
| 413 |
"step": 600
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 6.59,
|
| 417 |
+
"eval_accuracy": 0.7529411764705882,
|
| 418 |
+
"eval_loss": 0.7081632614135742,
|
| 419 |
+
"eval_runtime": 1.6198,
|
| 420 |
+
"eval_samples_per_second": 104.953,
|
| 421 |
+
"eval_steps_per_second": 13.582,
|
| 422 |
"step": 600
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 6.7,
|
| 426 |
+
"learning_rate": 2.5984615384615384e-05,
|
| 427 |
+
"loss": 0.4314,
|
| 428 |
"step": 610
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 6.81,
|
| 432 |
+
"learning_rate": 2.591868131868132e-05,
|
| 433 |
+
"loss": 0.3389,
|
| 434 |
"step": 620
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 6.92,
|
| 438 |
+
"learning_rate": 2.5852747252747255e-05,
|
| 439 |
+
"loss": 0.399,
|
| 440 |
"step": 630
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"epoch": 7.03,
|
| 444 |
+
"learning_rate": 2.578681318681319e-05,
|
| 445 |
+
"loss": 0.3425,
|
| 446 |
"step": 640
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 7.14,
|
| 450 |
+
"learning_rate": 2.5720879120879122e-05,
|
| 451 |
+
"loss": 0.3395,
|
| 452 |
"step": 650
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 7.25,
|
| 456 |
+
"learning_rate": 2.5654945054945056e-05,
|
| 457 |
+
"loss": 0.3558,
|
| 458 |
"step": 660
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 7.36,
|
| 462 |
+
"learning_rate": 2.558901098901099e-05,
|
| 463 |
+
"loss": 0.3773,
|
| 464 |
"step": 670
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 7.47,
|
| 468 |
+
"learning_rate": 2.5523076923076923e-05,
|
| 469 |
+
"loss": 0.3493,
|
| 470 |
"step": 680
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 7.58,
|
| 474 |
+
"learning_rate": 2.5457142857142857e-05,
|
| 475 |
+
"loss": 0.402,
|
| 476 |
"step": 690
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 7.69,
|
| 480 |
+
"learning_rate": 2.539120879120879e-05,
|
| 481 |
+
"loss": 0.305,
|
| 482 |
"step": 700
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 7.69,
|
| 486 |
+
"eval_accuracy": 0.7647058823529411,
|
| 487 |
+
"eval_loss": 0.693938136100769,
|
| 488 |
+
"eval_runtime": 1.7847,
|
| 489 |
+
"eval_samples_per_second": 95.254,
|
| 490 |
+
"eval_steps_per_second": 12.327,
|
| 491 |
"step": 700
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 7.8,
|
| 495 |
+
"learning_rate": 2.5325274725274724e-05,
|
| 496 |
+
"loss": 0.3702,
|
| 497 |
"step": 710
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 7.91,
|
| 501 |
+
"learning_rate": 2.5259340659340658e-05,
|
| 502 |
+
"loss": 0.374,
|
| 503 |
"step": 720
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 8.02,
|
| 507 |
+
"learning_rate": 2.5193406593406595e-05,
|
| 508 |
+
"loss": 0.3374,
|
| 509 |
"step": 730
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 8.13,
|
| 513 |
+
"learning_rate": 2.512747252747253e-05,
|
| 514 |
+
"loss": 0.2479,
|
| 515 |
"step": 740
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 8.24,
|
| 519 |
+
"learning_rate": 2.5061538461538462e-05,
|
| 520 |
+
"loss": 0.3161,
|
| 521 |
"step": 750
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 8.35,
|
| 525 |
+
"learning_rate": 2.4995604395604396e-05,
|
| 526 |
+
"loss": 0.3229,
|
| 527 |
"step": 760
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 8.46,
|
| 531 |
+
"learning_rate": 2.492967032967033e-05,
|
| 532 |
+
"loss": 0.2871,
|
| 533 |
"step": 770
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 8.57,
|
| 537 |
+
"learning_rate": 2.4863736263736267e-05,
|
| 538 |
+
"loss": 0.3116,
|
| 539 |
"step": 780
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 8.68,
|
| 543 |
+
"learning_rate": 2.47978021978022e-05,
|
| 544 |
+
"loss": 0.3632,
|
| 545 |
"step": 790
|
| 546 |
},
|
| 547 |
{
|
| 548 |
"epoch": 8.79,
|
| 549 |
+
"learning_rate": 2.4731868131868134e-05,
|
| 550 |
+
"loss": 0.3349,
|
| 551 |
"step": 800
|
| 552 |
},
|
| 553 |
{
|
| 554 |
"epoch": 8.79,
|
| 555 |
+
"eval_accuracy": 0.7235294117647059,
|
| 556 |
+
"eval_loss": 0.7285170555114746,
|
| 557 |
+
"eval_runtime": 1.7358,
|
| 558 |
+
"eval_samples_per_second": 97.94,
|
| 559 |
+
"eval_steps_per_second": 12.675,
|
| 560 |
"step": 800
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 8.9,
|
| 564 |
+
"learning_rate": 2.4665934065934068e-05,
|
| 565 |
+
"loss": 0.3465,
|
| 566 |
"step": 810
|
| 567 |
},
|
| 568 |
{
|
| 569 |
"epoch": 9.01,
|
| 570 |
+
"learning_rate": 2.4599999999999998e-05,
|
| 571 |
+
"loss": 0.2579,
|
| 572 |
"step": 820
|
| 573 |
},
|
| 574 |
{
|
| 575 |
"epoch": 9.12,
|
| 576 |
+
"learning_rate": 2.4534065934065932e-05,
|
| 577 |
+
"loss": 0.324,
|
| 578 |
"step": 830
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 9.23,
|
| 582 |
+
"learning_rate": 2.446813186813187e-05,
|
| 583 |
+
"loss": 0.3192,
|
| 584 |
"step": 840
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 9.34,
|
| 588 |
+
"learning_rate": 2.4402197802197803e-05,
|
| 589 |
+
"loss": 0.2076,
|
| 590 |
"step": 850
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 9.45,
|
| 594 |
+
"learning_rate": 2.4336263736263736e-05,
|
| 595 |
+
"loss": 0.2456,
|
| 596 |
"step": 860
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 9.56,
|
| 600 |
+
"learning_rate": 2.427032967032967e-05,
|
| 601 |
+
"loss": 0.3255,
|
| 602 |
"step": 870
|
| 603 |
},
|
| 604 |
{
|
| 605 |
"epoch": 9.67,
|
| 606 |
+
"learning_rate": 2.4204395604395604e-05,
|
| 607 |
+
"loss": 0.3601,
|
| 608 |
"step": 880
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 9.78,
|
| 612 |
+
"learning_rate": 2.413846153846154e-05,
|
| 613 |
+
"loss": 0.1986,
|
| 614 |
"step": 890
|
| 615 |
},
|
| 616 |
{
|
| 617 |
"epoch": 9.89,
|
| 618 |
+
"learning_rate": 2.4072527472527475e-05,
|
| 619 |
+
"loss": 0.36,
|
| 620 |
"step": 900
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 9.89,
|
| 624 |
+
"eval_accuracy": 0.7294117647058823,
|
| 625 |
+
"eval_loss": 0.7664376497268677,
|
| 626 |
+
"eval_runtime": 1.6387,
|
| 627 |
+
"eval_samples_per_second": 103.742,
|
| 628 |
+
"eval_steps_per_second": 13.425,
|
| 629 |
"step": 900
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 10.0,
|
| 633 |
+
"learning_rate": 2.4006593406593408e-05,
|
| 634 |
+
"loss": 0.259,
|
| 635 |
"step": 910
|
| 636 |
},
|
| 637 |
{
|
| 638 |
"epoch": 10.11,
|
| 639 |
+
"learning_rate": 2.3940659340659342e-05,
|
| 640 |
+
"loss": 0.2984,
|
| 641 |
"step": 920
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 10.22,
|
| 645 |
+
"learning_rate": 2.3874725274725276e-05,
|
| 646 |
+
"loss": 0.2073,
|
| 647 |
"step": 930
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 10.33,
|
| 651 |
+
"learning_rate": 2.380879120879121e-05,
|
| 652 |
+
"loss": 0.3265,
|
| 653 |
"step": 940
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 10.44,
|
| 657 |
+
"learning_rate": 2.3742857142857146e-05,
|
| 658 |
+
"loss": 0.3372,
|
| 659 |
"step": 950
|
| 660 |
},
|
| 661 |
{
|
| 662 |
"epoch": 10.55,
|
| 663 |
+
"learning_rate": 2.3676923076923077e-05,
|
| 664 |
+
"loss": 0.3518,
|
| 665 |
"step": 960
|
| 666 |
},
|
| 667 |
{
|
| 668 |
"epoch": 10.66,
|
| 669 |
+
"learning_rate": 2.361098901098901e-05,
|
| 670 |
+
"loss": 0.2707,
|
| 671 |
"step": 970
|
| 672 |
},
|
| 673 |
{
|
| 674 |
"epoch": 10.77,
|
| 675 |
+
"learning_rate": 2.3545054945054944e-05,
|
| 676 |
+
"loss": 0.2529,
|
| 677 |
"step": 980
|
| 678 |
},
|
| 679 |
{
|
| 680 |
"epoch": 10.88,
|
| 681 |
+
"learning_rate": 2.3479120879120878e-05,
|
| 682 |
+
"loss": 0.258,
|
| 683 |
"step": 990
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 10.99,
|
| 687 |
+
"learning_rate": 2.341978021978022e-05,
|
| 688 |
+
"loss": 0.3184,
|
| 689 |
"step": 1000
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 10.99,
|
| 693 |
+
"eval_accuracy": 0.7588235294117647,
|
| 694 |
+
"eval_loss": 0.6806656718254089,
|
| 695 |
+
"eval_runtime": 1.6209,
|
| 696 |
+
"eval_samples_per_second": 104.882,
|
| 697 |
+
"eval_steps_per_second": 13.573,
|
| 698 |
"step": 1000
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 11.1,
|
| 702 |
+
"learning_rate": 2.3353846153846153e-05,
|
| 703 |
+
"loss": 0.2439,
|
| 704 |
"step": 1010
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 11.21,
|
| 708 |
+
"learning_rate": 2.3287912087912087e-05,
|
| 709 |
+
"loss": 0.1827,
|
| 710 |
"step": 1020
|
| 711 |
},
|
| 712 |
{
|
| 713 |
"epoch": 11.32,
|
| 714 |
+
"learning_rate": 2.3221978021978024e-05,
|
| 715 |
+
"loss": 0.2845,
|
| 716 |
"step": 1030
|
| 717 |
},
|
| 718 |
{
|
| 719 |
"epoch": 11.43,
|
| 720 |
+
"learning_rate": 2.3156043956043957e-05,
|
| 721 |
+
"loss": 0.2503,
|
| 722 |
"step": 1040
|
| 723 |
},
|
| 724 |
{
|
| 725 |
"epoch": 11.54,
|
| 726 |
+
"learning_rate": 2.309010989010989e-05,
|
| 727 |
+
"loss": 0.2009,
|
| 728 |
"step": 1050
|
| 729 |
},
|
| 730 |
{
|
| 731 |
"epoch": 11.65,
|
| 732 |
+
"learning_rate": 2.3024175824175825e-05,
|
| 733 |
+
"loss": 0.2486,
|
| 734 |
"step": 1060
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 11.76,
|
| 738 |
+
"learning_rate": 2.295824175824176e-05,
|
| 739 |
+
"loss": 0.1877,
|
| 740 |
"step": 1070
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 11.87,
|
| 744 |
+
"learning_rate": 2.2892307692307692e-05,
|
| 745 |
+
"loss": 0.3497,
|
| 746 |
"step": 1080
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 11.98,
|
| 750 |
+
"learning_rate": 2.282637362637363e-05,
|
| 751 |
+
"loss": 0.2559,
|
| 752 |
"step": 1090
|
| 753 |
},
|
| 754 |
{
|
| 755 |
"epoch": 12.09,
|
| 756 |
+
"learning_rate": 2.2760439560439563e-05,
|
| 757 |
+
"loss": 0.2815,
|
| 758 |
"step": 1100
|
| 759 |
},
|
| 760 |
{
|
| 761 |
"epoch": 12.09,
|
| 762 |
+
"eval_accuracy": 0.7352941176470589,
|
| 763 |
+
"eval_loss": 0.7407693266868591,
|
| 764 |
+
"eval_runtime": 1.6974,
|
| 765 |
+
"eval_samples_per_second": 100.156,
|
| 766 |
+
"eval_steps_per_second": 12.961,
|
| 767 |
"step": 1100
|
| 768 |
},
|
| 769 |
{
|
| 770 |
"epoch": 12.2,
|
| 771 |
+
"learning_rate": 2.2694505494505497e-05,
|
| 772 |
+
"loss": 0.2352,
|
| 773 |
"step": 1110
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 12.31,
|
| 777 |
+
"learning_rate": 2.262857142857143e-05,
|
| 778 |
+
"loss": 0.2422,
|
| 779 |
"step": 1120
|
| 780 |
},
|
| 781 |
{
|
| 782 |
"epoch": 12.42,
|
| 783 |
+
"learning_rate": 2.256263736263736e-05,
|
| 784 |
+
"loss": 0.2287,
|
| 785 |
"step": 1130
|
| 786 |
},
|
| 787 |
{
|
| 788 |
"epoch": 12.53,
|
| 789 |
+
"learning_rate": 2.2496703296703298e-05,
|
| 790 |
+
"loss": 0.282,
|
| 791 |
"step": 1140
|
| 792 |
},
|
| 793 |
{
|
| 794 |
"epoch": 12.64,
|
| 795 |
+
"learning_rate": 2.243076923076923e-05,
|
| 796 |
+
"loss": 0.2579,
|
| 797 |
"step": 1150
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 12.75,
|
| 801 |
+
"learning_rate": 2.2364835164835165e-05,
|
| 802 |
+
"loss": 0.2907,
|
| 803 |
"step": 1160
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 12.86,
|
| 807 |
+
"learning_rate": 2.22989010989011e-05,
|
| 808 |
+
"loss": 0.3221,
|
| 809 |
"step": 1170
|
| 810 |
},
|
| 811 |
{
|
| 812 |
"epoch": 12.97,
|
| 813 |
+
"learning_rate": 2.2232967032967032e-05,
|
| 814 |
+
"loss": 0.2657,
|
| 815 |
"step": 1180
|
| 816 |
},
|
| 817 |
{
|
| 818 |
"epoch": 13.08,
|
| 819 |
+
"learning_rate": 2.2167032967032966e-05,
|
| 820 |
+
"loss": 0.2456,
|
| 821 |
"step": 1190
|
| 822 |
},
|
| 823 |
{
|
| 824 |
"epoch": 13.19,
|
| 825 |
+
"learning_rate": 2.2101098901098903e-05,
|
| 826 |
+
"loss": 0.1745,
|
| 827 |
"step": 1200
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 13.19,
|
| 831 |
+
"eval_accuracy": 0.7294117647058823,
|
| 832 |
+
"eval_loss": 0.7527948617935181,
|
| 833 |
+
"eval_runtime": 1.6243,
|
| 834 |
+
"eval_samples_per_second": 104.661,
|
| 835 |
+
"eval_steps_per_second": 13.544,
|
| 836 |
"step": 1200
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 13.3,
|
| 840 |
+
"learning_rate": 2.2035164835164837e-05,
|
| 841 |
+
"loss": 0.202,
|
| 842 |
"step": 1210
|
| 843 |
},
|
| 844 |
{
|
| 845 |
"epoch": 13.41,
|
| 846 |
+
"learning_rate": 2.196923076923077e-05,
|
| 847 |
+
"loss": 0.1601,
|
| 848 |
"step": 1220
|
| 849 |
},
|
| 850 |
{
|
| 851 |
"epoch": 13.52,
|
| 852 |
+
"learning_rate": 2.1903296703296704e-05,
|
| 853 |
+
"loss": 0.1467,
|
| 854 |
"step": 1230
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 13.63,
|
| 858 |
+
"learning_rate": 2.1837362637362638e-05,
|
| 859 |
+
"loss": 0.287,
|
| 860 |
"step": 1240
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 13.74,
|
| 864 |
+
"learning_rate": 2.177142857142857e-05,
|
| 865 |
+
"loss": 0.2805,
|
| 866 |
"step": 1250
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 13.85,
|
| 870 |
+
"learning_rate": 2.170549450549451e-05,
|
| 871 |
+
"loss": 0.2405,
|
| 872 |
"step": 1260
|
| 873 |
},
|
| 874 |
{
|
| 875 |
"epoch": 13.96,
|
| 876 |
+
"learning_rate": 2.163956043956044e-05,
|
| 877 |
+
"loss": 0.3035,
|
| 878 |
"step": 1270
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 14.07,
|
| 882 |
+
"learning_rate": 2.1573626373626373e-05,
|
| 883 |
+
"loss": 0.2273,
|
| 884 |
"step": 1280
|
| 885 |
},
|
| 886 |
{
|
| 887 |
"epoch": 14.18,
|
| 888 |
+
"learning_rate": 2.1507692307692306e-05,
|
| 889 |
+
"loss": 0.1933,
|
| 890 |
"step": 1290
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 14.29,
|
| 894 |
+
"learning_rate": 2.144175824175824e-05,
|
| 895 |
+
"loss": 0.1894,
|
| 896 |
"step": 1300
|
| 897 |
},
|
| 898 |
{
|
| 899 |
"epoch": 14.29,
|
| 900 |
+
"eval_accuracy": 0.7470588235294118,
|
| 901 |
+
"eval_loss": 0.7634099721908569,
|
| 902 |
+
"eval_runtime": 1.6355,
|
| 903 |
+
"eval_samples_per_second": 103.947,
|
| 904 |
+
"eval_steps_per_second": 13.452,
|
| 905 |
"step": 1300
|
| 906 |
},
|
| 907 |
{
|
| 908 |
"epoch": 14.4,
|
| 909 |
+
"learning_rate": 2.1375824175824177e-05,
|
| 910 |
+
"loss": 0.1862,
|
| 911 |
"step": 1310
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 14.51,
|
| 915 |
+
"learning_rate": 2.130989010989011e-05,
|
| 916 |
+
"loss": 0.258,
|
| 917 |
"step": 1320
|
| 918 |
},
|
| 919 |
{
|
| 920 |
"epoch": 14.62,
|
| 921 |
+
"learning_rate": 2.1243956043956045e-05,
|
| 922 |
+
"loss": 0.231,
|
| 923 |
"step": 1330
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 14.73,
|
| 927 |
+
"learning_rate": 2.1178021978021978e-05,
|
| 928 |
+
"loss": 0.2558,
|
| 929 |
"step": 1340
|
| 930 |
},
|
| 931 |
{
|
| 932 |
"epoch": 14.84,
|
| 933 |
+
"learning_rate": 2.1112087912087912e-05,
|
| 934 |
+
"loss": 0.1848,
|
| 935 |
"step": 1350
|
| 936 |
},
|
| 937 |
{
|
| 938 |
"epoch": 14.95,
|
| 939 |
+
"learning_rate": 2.1046153846153846e-05,
|
| 940 |
+
"loss": 0.2495,
|
| 941 |
"step": 1360
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 15.05,
|
| 945 |
+
"learning_rate": 2.0980219780219783e-05,
|
| 946 |
+
"loss": 0.2079,
|
| 947 |
"step": 1370
|
| 948 |
},
|
| 949 |
{
|
| 950 |
"epoch": 15.16,
|
| 951 |
+
"learning_rate": 2.0914285714285716e-05,
|
| 952 |
+
"loss": 0.1803,
|
| 953 |
"step": 1380
|
| 954 |
},
|
| 955 |
{
|
| 956 |
"epoch": 15.27,
|
| 957 |
+
"learning_rate": 2.084835164835165e-05,
|
| 958 |
+
"loss": 0.2434,
|
| 959 |
"step": 1390
|
| 960 |
},
|
| 961 |
{
|
| 962 |
"epoch": 15.38,
|
| 963 |
+
"learning_rate": 2.0782417582417584e-05,
|
| 964 |
+
"loss": 0.1641,
|
| 965 |
"step": 1400
|
| 966 |
},
|
| 967 |
{
|
| 968 |
"epoch": 15.38,
|
| 969 |
+
"eval_accuracy": 0.7647058823529411,
|
| 970 |
+
"eval_loss": 0.7208631634712219,
|
| 971 |
+
"eval_runtime": 1.7468,
|
| 972 |
+
"eval_samples_per_second": 97.323,
|
| 973 |
+
"eval_steps_per_second": 12.595,
|
| 974 |
"step": 1400
|
| 975 |
},
|
| 976 |
{
|
| 977 |
"epoch": 15.49,
|
| 978 |
+
"learning_rate": 2.0716483516483514e-05,
|
| 979 |
+
"loss": 0.2347,
|
| 980 |
"step": 1410
|
| 981 |
},
|
| 982 |
{
|
| 983 |
"epoch": 15.6,
|
| 984 |
+
"learning_rate": 2.065054945054945e-05,
|
| 985 |
+
"loss": 0.1929,
|
| 986 |
"step": 1420
|
| 987 |
},
|
| 988 |
{
|
| 989 |
"epoch": 15.71,
|
| 990 |
+
"learning_rate": 2.0584615384615385e-05,
|
| 991 |
+
"loss": 0.1588,
|
| 992 |
"step": 1430
|
| 993 |
},
|
| 994 |
{
|
| 995 |
"epoch": 15.82,
|
| 996 |
+
"learning_rate": 2.051868131868132e-05,
|
| 997 |
+
"loss": 0.2216,
|
| 998 |
"step": 1440
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 15.93,
|
| 1002 |
+
"learning_rate": 2.0452747252747252e-05,
|
| 1003 |
+
"loss": 0.1755,
|
| 1004 |
"step": 1450
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
"epoch": 16.04,
|
| 1008 |
+
"learning_rate": 2.0386813186813186e-05,
|
| 1009 |
+
"loss": 0.2623,
|
| 1010 |
"step": 1460
|
| 1011 |
},
|
| 1012 |
{
|
| 1013 |
"epoch": 16.15,
|
| 1014 |
+
"learning_rate": 2.032087912087912e-05,
|
| 1015 |
+
"loss": 0.2498,
|
| 1016 |
"step": 1470
|
| 1017 |
},
|
| 1018 |
{
|
| 1019 |
"epoch": 16.26,
|
| 1020 |
+
"learning_rate": 2.0254945054945057e-05,
|
| 1021 |
+
"loss": 0.2103,
|
| 1022 |
"step": 1480
|
| 1023 |
},
|
| 1024 |
{
|
| 1025 |
"epoch": 16.37,
|
| 1026 |
+
"learning_rate": 2.018901098901099e-05,
|
| 1027 |
+
"loss": 0.1713,
|
| 1028 |
"step": 1490
|
| 1029 |
},
|
| 1030 |
{
|
| 1031 |
"epoch": 16.48,
|
| 1032 |
+
"learning_rate": 2.0123076923076924e-05,
|
| 1033 |
+
"loss": 0.1932,
|
| 1034 |
"step": 1500
|
| 1035 |
},
|
| 1036 |
{
|
| 1037 |
"epoch": 16.48,
|
| 1038 |
+
"eval_accuracy": 0.7,
|
| 1039 |
+
"eval_loss": 0.9090902805328369,
|
| 1040 |
+
"eval_runtime": 1.6369,
|
| 1041 |
+
"eval_samples_per_second": 103.854,
|
| 1042 |
+
"eval_steps_per_second": 13.44,
|
| 1043 |
"step": 1500
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
"epoch": 16.59,
|
| 1047 |
+
"learning_rate": 2.0057142857142858e-05,
|
| 1048 |
+
"loss": 0.256,
|
| 1049 |
"step": 1510
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 16.7,
|
| 1053 |
+
"learning_rate": 1.999120879120879e-05,
|
| 1054 |
+
"loss": 0.1954,
|
| 1055 |
"step": 1520
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 16.81,
|
| 1059 |
+
"learning_rate": 1.992527472527473e-05,
|
| 1060 |
+
"loss": 0.2644,
|
| 1061 |
"step": 1530
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
"epoch": 16.92,
|
| 1065 |
+
"learning_rate": 1.9859340659340662e-05,
|
| 1066 |
+
"loss": 0.2049,
|
| 1067 |
"step": 1540
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
"epoch": 17.03,
|
| 1071 |
+
"learning_rate": 1.9793406593406596e-05,
|
| 1072 |
+
"loss": 0.1822,
|
| 1073 |
"step": 1550
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
"epoch": 17.14,
|
| 1077 |
+
"learning_rate": 1.9727472527472526e-05,
|
| 1078 |
+
"loss": 0.1925,
|
| 1079 |
"step": 1560
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
"epoch": 17.25,
|
| 1083 |
+
"learning_rate": 1.966153846153846e-05,
|
| 1084 |
+
"loss": 0.2075,
|
| 1085 |
"step": 1570
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 17.36,
|
| 1089 |
+
"learning_rate": 1.9595604395604394e-05,
|
| 1090 |
+
"loss": 0.2604,
|
| 1091 |
"step": 1580
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
"epoch": 17.47,
|
| 1095 |
+
"learning_rate": 1.952967032967033e-05,
|
| 1096 |
+
"loss": 0.1662,
|
| 1097 |
"step": 1590
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
"epoch": 17.58,
|
| 1101 |
+
"learning_rate": 1.9463736263736264e-05,
|
| 1102 |
+
"loss": 0.1609,
|
| 1103 |
"step": 1600
|
| 1104 |
},
|
| 1105 |
{
|
| 1106 |
"epoch": 17.58,
|
| 1107 |
+
"eval_accuracy": 0.7588235294117647,
|
| 1108 |
+
"eval_loss": 0.7208409309387207,
|
| 1109 |
+
"eval_runtime": 1.6376,
|
| 1110 |
+
"eval_samples_per_second": 103.809,
|
| 1111 |
+
"eval_steps_per_second": 13.434,
|
| 1112 |
"step": 1600
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
"epoch": 17.69,
|
| 1116 |
+
"learning_rate": 1.9397802197802198e-05,
|
| 1117 |
+
"loss": 0.1817,
|
| 1118 |
"step": 1610
|
| 1119 |
},
|
| 1120 |
{
|
| 1121 |
"epoch": 17.8,
|
| 1122 |
+
"learning_rate": 1.9331868131868132e-05,
|
| 1123 |
+
"loss": 0.2423,
|
| 1124 |
"step": 1620
|
| 1125 |
},
|
| 1126 |
{
|
| 1127 |
"epoch": 17.91,
|
| 1128 |
+
"learning_rate": 1.9265934065934065e-05,
|
| 1129 |
+
"loss": 0.1722,
|
| 1130 |
"step": 1630
|
| 1131 |
},
|
| 1132 |
{
|
| 1133 |
"epoch": 18.02,
|
| 1134 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 1135 |
+
"loss": 0.1544,
|
| 1136 |
"step": 1640
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 18.13,
|
| 1140 |
+
"learning_rate": 1.9134065934065936e-05,
|
| 1141 |
+
"loss": 0.1976,
|
| 1142 |
"step": 1650
|
| 1143 |
},
|
| 1144 |
{
|
| 1145 |
"epoch": 18.24,
|
| 1146 |
+
"learning_rate": 1.906813186813187e-05,
|
| 1147 |
+
"loss": 0.2191,
|
| 1148 |
"step": 1660
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 18.35,
|
| 1152 |
+
"learning_rate": 1.9002197802197804e-05,
|
| 1153 |
+
"loss": 0.1458,
|
| 1154 |
"step": 1670
|
| 1155 |
},
|
| 1156 |
{
|
| 1157 |
"epoch": 18.46,
|
| 1158 |
+
"learning_rate": 1.8936263736263737e-05,
|
| 1159 |
+
"loss": 0.2027,
|
| 1160 |
"step": 1680
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
"epoch": 18.57,
|
| 1164 |
+
"learning_rate": 1.887032967032967e-05,
|
| 1165 |
+
"loss": 0.1637,
|
| 1166 |
"step": 1690
|
| 1167 |
},
|
| 1168 |
{
|
| 1169 |
"epoch": 18.68,
|
| 1170 |
+
"learning_rate": 1.8804395604395605e-05,
|
| 1171 |
+
"loss": 0.132,
|
| 1172 |
"step": 1700
|
| 1173 |
},
|
| 1174 |
{
|
| 1175 |
"epoch": 18.68,
|
| 1176 |
+
"eval_accuracy": 0.7588235294117647,
|
| 1177 |
+
"eval_loss": 0.8486713171005249,
|
| 1178 |
+
"eval_runtime": 1.6357,
|
| 1179 |
+
"eval_samples_per_second": 103.93,
|
| 1180 |
+
"eval_steps_per_second": 13.45,
|
| 1181 |
"step": 1700
|
| 1182 |
},
|
| 1183 |
{
|
| 1184 |
"epoch": 18.79,
|
| 1185 |
+
"learning_rate": 1.873846153846154e-05,
|
| 1186 |
+
"loss": 0.1319,
|
| 1187 |
"step": 1710
|
| 1188 |
},
|
| 1189 |
{
|
| 1190 |
"epoch": 18.9,
|
| 1191 |
+
"learning_rate": 1.8672527472527472e-05,
|
| 1192 |
+
"loss": 0.2005,
|
| 1193 |
"step": 1720
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
"epoch": 19.01,
|
| 1197 |
+
"learning_rate": 1.8606593406593406e-05,
|
| 1198 |
+
"loss": 0.2234,
|
| 1199 |
"step": 1730
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
"epoch": 19.12,
|
| 1203 |
+
"learning_rate": 1.854065934065934e-05,
|
| 1204 |
+
"loss": 0.188,
|
| 1205 |
"step": 1740
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
"epoch": 19.23,
|
| 1209 |
+
"learning_rate": 1.8474725274725277e-05,
|
| 1210 |
+
"loss": 0.1322,
|
| 1211 |
"step": 1750
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
"epoch": 19.34,
|
| 1215 |
+
"learning_rate": 1.840879120879121e-05,
|
| 1216 |
+
"loss": 0.2137,
|
| 1217 |
"step": 1760
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
"epoch": 19.45,
|
| 1221 |
+
"learning_rate": 1.8342857142857144e-05,
|
| 1222 |
+
"loss": 0.2314,
|
| 1223 |
"step": 1770
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
"epoch": 19.56,
|
| 1227 |
+
"learning_rate": 1.8276923076923078e-05,
|
| 1228 |
+
"loss": 0.1987,
|
| 1229 |
"step": 1780
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
"epoch": 19.67,
|
| 1233 |
+
"learning_rate": 1.821098901098901e-05,
|
| 1234 |
+
"loss": 0.1955,
|
| 1235 |
"step": 1790
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
"epoch": 19.78,
|
| 1239 |
+
"learning_rate": 1.8145054945054945e-05,
|
| 1240 |
+
"loss": 0.1903,
|
| 1241 |
"step": 1800
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 19.78,
|
| 1245 |
+
"eval_accuracy": 0.7470588235294118,
|
| 1246 |
+
"eval_loss": 0.7911531329154968,
|
| 1247 |
+
"eval_runtime": 1.6371,
|
| 1248 |
+
"eval_samples_per_second": 103.842,
|
| 1249 |
+
"eval_steps_per_second": 13.438,
|
| 1250 |
"step": 1800
|
| 1251 |
},
|
| 1252 |
{
|
| 1253 |
"epoch": 19.89,
|
| 1254 |
+
"learning_rate": 1.8079120879120882e-05,
|
| 1255 |
+
"loss": 0.1333,
|
| 1256 |
"step": 1810
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
"epoch": 20.0,
|
| 1260 |
+
"learning_rate": 1.8013186813186816e-05,
|
| 1261 |
+
"loss": 0.2119,
|
| 1262 |
"step": 1820
|
| 1263 |
},
|
| 1264 |
{
|
| 1265 |
"epoch": 20.11,
|
| 1266 |
+
"learning_rate": 1.794725274725275e-05,
|
| 1267 |
+
"loss": 0.1784,
|
| 1268 |
"step": 1830
|
| 1269 |
},
|
| 1270 |
{
|
| 1271 |
"epoch": 20.22,
|
| 1272 |
+
"learning_rate": 1.788131868131868e-05,
|
| 1273 |
+
"loss": 0.1821,
|
| 1274 |
"step": 1840
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 20.33,
|
| 1278 |
+
"learning_rate": 1.7815384615384613e-05,
|
| 1279 |
+
"loss": 0.2508,
|
| 1280 |
"step": 1850
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
"epoch": 20.44,
|
| 1284 |
+
"learning_rate": 1.7749450549450547e-05,
|
| 1285 |
+
"loss": 0.1599,
|
| 1286 |
"step": 1860
|
| 1287 |
},
|
| 1288 |
{
|
| 1289 |
"epoch": 20.55,
|
| 1290 |
+
"learning_rate": 1.7683516483516484e-05,
|
| 1291 |
+
"loss": 0.133,
|
| 1292 |
"step": 1870
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
"epoch": 20.66,
|
| 1296 |
+
"learning_rate": 1.7617582417582418e-05,
|
| 1297 |
+
"loss": 0.1344,
|
| 1298 |
"step": 1880
|
| 1299 |
},
|
| 1300 |
{
|
| 1301 |
"epoch": 20.77,
|
| 1302 |
+
"learning_rate": 1.755164835164835e-05,
|
| 1303 |
+
"loss": 0.163,
|
| 1304 |
"step": 1890
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
"epoch": 20.88,
|
| 1308 |
+
"learning_rate": 1.7485714285714285e-05,
|
| 1309 |
+
"loss": 0.121,
|
| 1310 |
"step": 1900
|
| 1311 |
},
|
| 1312 |
{
|
| 1313 |
"epoch": 20.88,
|
| 1314 |
+
"eval_accuracy": 0.7470588235294118,
|
| 1315 |
+
"eval_loss": 0.6734881401062012,
|
| 1316 |
+
"eval_runtime": 1.6331,
|
| 1317 |
+
"eval_samples_per_second": 104.095,
|
| 1318 |
+
"eval_steps_per_second": 13.471,
|
| 1319 |
"step": 1900
|
| 1320 |
},
|
| 1321 |
{
|
| 1322 |
"epoch": 20.99,
|
| 1323 |
+
"learning_rate": 1.741978021978022e-05,
|
| 1324 |
+
"loss": 0.1984,
|
| 1325 |
"step": 1910
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
"epoch": 21.1,
|
| 1329 |
+
"learning_rate": 1.7353846153846156e-05,
|
| 1330 |
+
"loss": 0.15,
|
| 1331 |
"step": 1920
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
"epoch": 21.21,
|
| 1335 |
+
"learning_rate": 1.728791208791209e-05,
|
| 1336 |
+
"loss": 0.11,
|
| 1337 |
"step": 1930
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
"epoch": 21.32,
|
| 1341 |
+
"learning_rate": 1.7221978021978023e-05,
|
| 1342 |
+
"loss": 0.1753,
|
| 1343 |
"step": 1940
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
"epoch": 21.43,
|
| 1347 |
+
"learning_rate": 1.7156043956043957e-05,
|
| 1348 |
+
"loss": 0.1535,
|
| 1349 |
"step": 1950
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 21.54,
|
| 1353 |
+
"learning_rate": 1.709010989010989e-05,
|
| 1354 |
+
"loss": 0.1269,
|
| 1355 |
"step": 1960
|
| 1356 |
},
|
| 1357 |
{
|
| 1358 |
"epoch": 21.65,
|
| 1359 |
+
"learning_rate": 1.7024175824175825e-05,
|
| 1360 |
+
"loss": 0.1711,
|
| 1361 |
"step": 1970
|
| 1362 |
},
|
| 1363 |
{
|
| 1364 |
"epoch": 21.76,
|
| 1365 |
+
"learning_rate": 1.6958241758241758e-05,
|
| 1366 |
+
"loss": 0.1871,
|
| 1367 |
"step": 1980
|
| 1368 |
},
|
| 1369 |
{
|
| 1370 |
"epoch": 21.87,
|
| 1371 |
+
"learning_rate": 1.6892307692307692e-05,
|
| 1372 |
+
"loss": 0.1544,
|
| 1373 |
"step": 1990
|
| 1374 |
},
|
| 1375 |
{
|
| 1376 |
"epoch": 21.98,
|
| 1377 |
+
"learning_rate": 1.6826373626373626e-05,
|
| 1378 |
+
"loss": 0.1903,
|
| 1379 |
"step": 2000
|
| 1380 |
},
|
| 1381 |
{
|
| 1382 |
"epoch": 21.98,
|
| 1383 |
+
"eval_accuracy": 0.7823529411764706,
|
| 1384 |
+
"eval_loss": 0.6692019104957581,
|
| 1385 |
+
"eval_runtime": 1.6545,
|
| 1386 |
+
"eval_samples_per_second": 102.753,
|
| 1387 |
+
"eval_steps_per_second": 13.297,
|
| 1388 |
"step": 2000
|
| 1389 |
},
|
| 1390 |
{
|
| 1391 |
"epoch": 22.09,
|
| 1392 |
+
"learning_rate": 1.676043956043956e-05,
|
| 1393 |
+
"loss": 0.1258,
|
| 1394 |
"step": 2010
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 22.2,
|
| 1398 |
+
"learning_rate": 1.6694505494505493e-05,
|
| 1399 |
+
"loss": 0.1057,
|
| 1400 |
"step": 2020
|
| 1401 |
},
|
| 1402 |
{
|
| 1403 |
"epoch": 22.31,
|
| 1404 |
+
"learning_rate": 1.662857142857143e-05,
|
| 1405 |
+
"loss": 0.0954,
|
| 1406 |
"step": 2030
|
| 1407 |
},
|
| 1408 |
{
|
| 1409 |
"epoch": 22.42,
|
| 1410 |
+
"learning_rate": 1.6562637362637364e-05,
|
| 1411 |
+
"loss": 0.2413,
|
| 1412 |
"step": 2040
|
| 1413 |
},
|
| 1414 |
{
|
| 1415 |
"epoch": 22.53,
|
| 1416 |
+
"learning_rate": 1.6496703296703297e-05,
|
| 1417 |
+
"loss": 0.1073,
|
| 1418 |
"step": 2050
|
| 1419 |
},
|
| 1420 |
{
|
| 1421 |
"epoch": 22.64,
|
| 1422 |
+
"learning_rate": 1.643076923076923e-05,
|
| 1423 |
+
"loss": 0.2491,
|
| 1424 |
"step": 2060
|
| 1425 |
},
|
| 1426 |
{
|
| 1427 |
"epoch": 22.75,
|
| 1428 |
+
"learning_rate": 1.6364835164835165e-05,
|
| 1429 |
+
"loss": 0.1972,
|
| 1430 |
"step": 2070
|
| 1431 |
},
|
| 1432 |
{
|
| 1433 |
"epoch": 22.86,
|
| 1434 |
+
"learning_rate": 1.62989010989011e-05,
|
| 1435 |
+
"loss": 0.1852,
|
| 1436 |
"step": 2080
|
| 1437 |
},
|
| 1438 |
{
|
| 1439 |
"epoch": 22.97,
|
| 1440 |
+
"learning_rate": 1.6232967032967036e-05,
|
| 1441 |
+
"loss": 0.135,
|
| 1442 |
"step": 2090
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
"epoch": 23.08,
|
| 1446 |
+
"learning_rate": 1.616703296703297e-05,
|
| 1447 |
+
"loss": 0.176,
|
| 1448 |
"step": 2100
|
| 1449 |
},
|
| 1450 |
{
|
| 1451 |
"epoch": 23.08,
|
| 1452 |
+
"eval_accuracy": 0.7176470588235294,
|
| 1453 |
+
"eval_loss": 0.8350964784622192,
|
| 1454 |
+
"eval_runtime": 1.6244,
|
| 1455 |
+
"eval_samples_per_second": 104.652,
|
| 1456 |
+
"eval_steps_per_second": 13.543,
|
| 1457 |
"step": 2100
|
| 1458 |
},
|
| 1459 |
{
|
| 1460 |
"epoch": 23.19,
|
| 1461 |
+
"learning_rate": 1.6101098901098903e-05,
|
| 1462 |
+
"loss": 0.1485,
|
| 1463 |
"step": 2110
|
| 1464 |
},
|
| 1465 |
{
|
| 1466 |
"epoch": 23.3,
|
| 1467 |
+
"learning_rate": 1.6035164835164837e-05,
|
| 1468 |
+
"loss": 0.1436,
|
| 1469 |
"step": 2120
|
| 1470 |
},
|
| 1471 |
{
|
| 1472 |
"epoch": 23.41,
|
| 1473 |
+
"learning_rate": 1.5969230769230767e-05,
|
| 1474 |
+
"loss": 0.1783,
|
| 1475 |
"step": 2130
|
| 1476 |
},
|
| 1477 |
{
|
| 1478 |
"epoch": 23.52,
|
| 1479 |
+
"learning_rate": 1.5903296703296704e-05,
|
| 1480 |
+
"loss": 0.1655,
|
| 1481 |
"step": 2140
|
| 1482 |
},
|
| 1483 |
{
|
| 1484 |
"epoch": 23.63,
|
| 1485 |
+
"learning_rate": 1.5837362637362638e-05,
|
| 1486 |
+
"loss": 0.1274,
|
| 1487 |
"step": 2150
|
| 1488 |
},
|
| 1489 |
{
|
| 1490 |
"epoch": 23.74,
|
| 1491 |
+
"learning_rate": 1.577142857142857e-05,
|
| 1492 |
+
"loss": 0.1261,
|
| 1493 |
"step": 2160
|
| 1494 |
},
|
| 1495 |
{
|
| 1496 |
"epoch": 23.85,
|
| 1497 |
+
"learning_rate": 1.5705494505494505e-05,
|
| 1498 |
+
"loss": 0.2141,
|
| 1499 |
"step": 2170
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
"epoch": 23.96,
|
| 1503 |
+
"learning_rate": 1.563956043956044e-05,
|
| 1504 |
+
"loss": 0.2215,
|
| 1505 |
"step": 2180
|
| 1506 |
},
|
| 1507 |
{
|
| 1508 |
"epoch": 24.07,
|
| 1509 |
+
"learning_rate": 1.5573626373626373e-05,
|
| 1510 |
+
"loss": 0.2243,
|
| 1511 |
"step": 2190
|
| 1512 |
},
|
| 1513 |
{
|
| 1514 |
"epoch": 24.18,
|
| 1515 |
+
"learning_rate": 1.550769230769231e-05,
|
| 1516 |
+
"loss": 0.1186,
|
| 1517 |
"step": 2200
|
| 1518 |
},
|
| 1519 |
{
|
| 1520 |
"epoch": 24.18,
|
| 1521 |
+
"eval_accuracy": 0.7470588235294118,
|
| 1522 |
+
"eval_loss": 0.7317846417427063,
|
| 1523 |
+
"eval_runtime": 1.63,
|
| 1524 |
+
"eval_samples_per_second": 104.295,
|
| 1525 |
+
"eval_steps_per_second": 13.497,
|
| 1526 |
"step": 2200
|
| 1527 |
},
|
| 1528 |
{
|
| 1529 |
"epoch": 24.29,
|
| 1530 |
+
"learning_rate": 1.5441758241758243e-05,
|
| 1531 |
+
"loss": 0.2046,
|
| 1532 |
"step": 2210
|
| 1533 |
},
|
| 1534 |
{
|
| 1535 |
"epoch": 24.4,
|
| 1536 |
+
"learning_rate": 1.5375824175824177e-05,
|
| 1537 |
+
"loss": 0.1992,
|
| 1538 |
"step": 2220
|
| 1539 |
},
|
| 1540 |
{
|
| 1541 |
"epoch": 24.51,
|
| 1542 |
+
"learning_rate": 1.530989010989011e-05,
|
| 1543 |
+
"loss": 0.1289,
|
| 1544 |
"step": 2230
|
| 1545 |
},
|
| 1546 |
{
|
| 1547 |
"epoch": 24.62,
|
| 1548 |
+
"learning_rate": 1.5243956043956046e-05,
|
| 1549 |
+
"loss": 0.1033,
|
| 1550 |
"step": 2240
|
| 1551 |
},
|
| 1552 |
{
|
| 1553 |
"epoch": 24.73,
|
| 1554 |
+
"learning_rate": 1.517802197802198e-05,
|
| 1555 |
+
"loss": 0.2098,
|
| 1556 |
"step": 2250
|
| 1557 |
},
|
| 1558 |
{
|
| 1559 |
"epoch": 24.84,
|
| 1560 |
+
"learning_rate": 1.5112087912087913e-05,
|
| 1561 |
+
"loss": 0.0928,
|
| 1562 |
"step": 2260
|
| 1563 |
},
|
| 1564 |
{
|
| 1565 |
"epoch": 24.95,
|
| 1566 |
+
"learning_rate": 1.5046153846153845e-05,
|
| 1567 |
+
"loss": 0.1469,
|
| 1568 |
"step": 2270
|
| 1569 |
},
|
| 1570 |
{
|
| 1571 |
+
"epoch": 25.05,
|
| 1572 |
+
"learning_rate": 1.498021978021978e-05,
|
| 1573 |
+
"loss": 0.0645,
|
| 1574 |
+
"step": 2280
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 25.16,
|
| 1578 |
+
"learning_rate": 1.4914285714285715e-05,
|
| 1579 |
+
"loss": 0.1786,
|
| 1580 |
+
"step": 2290
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 25.27,
|
| 1584 |
+
"learning_rate": 1.4848351648351648e-05,
|
| 1585 |
+
"loss": 0.1424,
|
| 1586 |
+
"step": 2300
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 25.27,
|
| 1590 |
+
"eval_accuracy": 0.7588235294117647,
|
| 1591 |
+
"eval_loss": 0.7859658598899841,
|
| 1592 |
+
"eval_runtime": 1.6259,
|
| 1593 |
+
"eval_samples_per_second": 104.556,
|
| 1594 |
+
"eval_steps_per_second": 13.531,
|
| 1595 |
+
"step": 2300
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 25.38,
|
| 1599 |
+
"learning_rate": 1.4782417582417582e-05,
|
| 1600 |
+
"loss": 0.0742,
|
| 1601 |
+
"step": 2310
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 25.49,
|
| 1605 |
+
"learning_rate": 1.4716483516483517e-05,
|
| 1606 |
+
"loss": 0.1224,
|
| 1607 |
+
"step": 2320
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 25.6,
|
| 1611 |
+
"learning_rate": 1.4650549450549451e-05,
|
| 1612 |
+
"loss": 0.1334,
|
| 1613 |
+
"step": 2330
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 25.71,
|
| 1617 |
+
"learning_rate": 1.4584615384615385e-05,
|
| 1618 |
+
"loss": 0.1924,
|
| 1619 |
+
"step": 2340
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 25.82,
|
| 1623 |
+
"learning_rate": 1.451868131868132e-05,
|
| 1624 |
+
"loss": 0.1386,
|
| 1625 |
+
"step": 2350
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 25.93,
|
| 1629 |
+
"learning_rate": 1.4452747252747254e-05,
|
| 1630 |
+
"loss": 0.1982,
|
| 1631 |
+
"step": 2360
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 26.04,
|
| 1635 |
+
"learning_rate": 1.4386813186813186e-05,
|
| 1636 |
+
"loss": 0.1341,
|
| 1637 |
+
"step": 2370
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 26.15,
|
| 1641 |
+
"learning_rate": 1.4320879120879121e-05,
|
| 1642 |
+
"loss": 0.1664,
|
| 1643 |
+
"step": 2380
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 26.26,
|
| 1647 |
+
"learning_rate": 1.4254945054945055e-05,
|
| 1648 |
+
"loss": 0.0903,
|
| 1649 |
+
"step": 2390
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 26.37,
|
| 1653 |
+
"learning_rate": 1.4189010989010989e-05,
|
| 1654 |
+
"loss": 0.144,
|
| 1655 |
+
"step": 2400
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 26.37,
|
| 1659 |
+
"eval_accuracy": 0.788235294117647,
|
| 1660 |
+
"eval_loss": 0.7021328806877136,
|
| 1661 |
+
"eval_runtime": 1.618,
|
| 1662 |
+
"eval_samples_per_second": 105.065,
|
| 1663 |
+
"eval_steps_per_second": 13.597,
|
| 1664 |
+
"step": 2400
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 26.48,
|
| 1668 |
+
"learning_rate": 1.4123076923076924e-05,
|
| 1669 |
+
"loss": 0.1747,
|
| 1670 |
+
"step": 2410
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 26.59,
|
| 1674 |
+
"learning_rate": 1.4057142857142858e-05,
|
| 1675 |
+
"loss": 0.1655,
|
| 1676 |
+
"step": 2420
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 26.7,
|
| 1680 |
+
"learning_rate": 1.3991208791208793e-05,
|
| 1681 |
+
"loss": 0.1003,
|
| 1682 |
+
"step": 2430
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 26.81,
|
| 1686 |
+
"learning_rate": 1.3925274725274727e-05,
|
| 1687 |
+
"loss": 0.142,
|
| 1688 |
+
"step": 2440
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 26.92,
|
| 1692 |
+
"learning_rate": 1.3859340659340659e-05,
|
| 1693 |
+
"loss": 0.089,
|
| 1694 |
+
"step": 2450
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 27.03,
|
| 1698 |
+
"learning_rate": 1.3793406593406594e-05,
|
| 1699 |
+
"loss": 0.2091,
|
| 1700 |
+
"step": 2460
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 27.14,
|
| 1704 |
+
"learning_rate": 1.3727472527472528e-05,
|
| 1705 |
+
"loss": 0.1794,
|
| 1706 |
+
"step": 2470
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 27.25,
|
| 1710 |
+
"learning_rate": 1.3661538461538461e-05,
|
| 1711 |
+
"loss": 0.133,
|
| 1712 |
+
"step": 2480
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 27.36,
|
| 1716 |
+
"learning_rate": 1.3595604395604397e-05,
|
| 1717 |
+
"loss": 0.1039,
|
| 1718 |
+
"step": 2490
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 27.47,
|
| 1722 |
+
"learning_rate": 1.352967032967033e-05,
|
| 1723 |
+
"loss": 0.1088,
|
| 1724 |
+
"step": 2500
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 27.47,
|
| 1728 |
+
"eval_accuracy": 0.7470588235294118,
|
| 1729 |
+
"eval_loss": 0.8109354972839355,
|
| 1730 |
+
"eval_runtime": 1.7131,
|
| 1731 |
+
"eval_samples_per_second": 99.233,
|
| 1732 |
+
"eval_steps_per_second": 12.842,
|
| 1733 |
+
"step": 2500
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 27.58,
|
| 1737 |
+
"learning_rate": 1.3463736263736264e-05,
|
| 1738 |
+
"loss": 0.1443,
|
| 1739 |
+
"step": 2510
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 27.69,
|
| 1743 |
+
"learning_rate": 1.3397802197802198e-05,
|
| 1744 |
+
"loss": 0.1106,
|
| 1745 |
+
"step": 2520
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 27.8,
|
| 1749 |
+
"learning_rate": 1.3331868131868132e-05,
|
| 1750 |
+
"loss": 0.0908,
|
| 1751 |
+
"step": 2530
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 27.91,
|
| 1755 |
+
"learning_rate": 1.3265934065934065e-05,
|
| 1756 |
+
"loss": 0.1268,
|
| 1757 |
+
"step": 2540
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 28.02,
|
| 1761 |
+
"learning_rate": 1.32e-05,
|
| 1762 |
+
"loss": 0.194,
|
| 1763 |
+
"step": 2550
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 28.13,
|
| 1767 |
+
"learning_rate": 1.3134065934065934e-05,
|
| 1768 |
+
"loss": 0.1085,
|
| 1769 |
+
"step": 2560
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 28.24,
|
| 1773 |
+
"learning_rate": 1.306813186813187e-05,
|
| 1774 |
+
"loss": 0.0856,
|
| 1775 |
+
"step": 2570
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 28.35,
|
| 1779 |
+
"learning_rate": 1.3002197802197803e-05,
|
| 1780 |
+
"loss": 0.1157,
|
| 1781 |
+
"step": 2580
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 28.46,
|
| 1785 |
+
"learning_rate": 1.2936263736263735e-05,
|
| 1786 |
+
"loss": 0.0941,
|
| 1787 |
+
"step": 2590
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 28.57,
|
| 1791 |
+
"learning_rate": 1.287032967032967e-05,
|
| 1792 |
+
"loss": 0.1019,
|
| 1793 |
+
"step": 2600
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 28.57,
|
| 1797 |
+
"eval_accuracy": 0.7470588235294118,
|
| 1798 |
+
"eval_loss": 0.8157252669334412,
|
| 1799 |
+
"eval_runtime": 1.6087,
|
| 1800 |
+
"eval_samples_per_second": 105.676,
|
| 1801 |
+
"eval_steps_per_second": 13.676,
|
| 1802 |
+
"step": 2600
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 28.68,
|
| 1806 |
+
"learning_rate": 1.2804395604395605e-05,
|
| 1807 |
+
"loss": 0.1466,
|
| 1808 |
+
"step": 2610
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 28.79,
|
| 1812 |
+
"learning_rate": 1.2738461538461538e-05,
|
| 1813 |
+
"loss": 0.0661,
|
| 1814 |
+
"step": 2620
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 28.9,
|
| 1818 |
+
"learning_rate": 1.2672527472527474e-05,
|
| 1819 |
+
"loss": 0.2147,
|
| 1820 |
+
"step": 2630
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 29.01,
|
| 1824 |
+
"learning_rate": 1.2606593406593407e-05,
|
| 1825 |
+
"loss": 0.2561,
|
| 1826 |
+
"step": 2640
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 29.12,
|
| 1830 |
+
"learning_rate": 1.2540659340659341e-05,
|
| 1831 |
+
"loss": 0.1408,
|
| 1832 |
+
"step": 2650
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 29.23,
|
| 1836 |
+
"learning_rate": 1.2474725274725275e-05,
|
| 1837 |
+
"loss": 0.0896,
|
| 1838 |
+
"step": 2660
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 29.34,
|
| 1842 |
+
"learning_rate": 1.2408791208791208e-05,
|
| 1843 |
+
"loss": 0.1356,
|
| 1844 |
+
"step": 2670
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 29.45,
|
| 1848 |
+
"learning_rate": 1.2342857142857144e-05,
|
| 1849 |
+
"loss": 0.0914,
|
| 1850 |
+
"step": 2680
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 29.56,
|
| 1854 |
+
"learning_rate": 1.2276923076923077e-05,
|
| 1855 |
+
"loss": 0.1355,
|
| 1856 |
+
"step": 2690
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 29.67,
|
| 1860 |
+
"learning_rate": 1.2210989010989011e-05,
|
| 1861 |
+
"loss": 0.0947,
|
| 1862 |
+
"step": 2700
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 29.67,
|
| 1866 |
+
"eval_accuracy": 0.7588235294117647,
|
| 1867 |
+
"eval_loss": 0.8027762174606323,
|
| 1868 |
+
"eval_runtime": 1.6188,
|
| 1869 |
+
"eval_samples_per_second": 105.014,
|
| 1870 |
+
"eval_steps_per_second": 13.59,
|
| 1871 |
+
"step": 2700
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 29.78,
|
| 1875 |
+
"learning_rate": 1.2145054945054947e-05,
|
| 1876 |
+
"loss": 0.0745,
|
| 1877 |
+
"step": 2710
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 29.89,
|
| 1881 |
+
"learning_rate": 1.207912087912088e-05,
|
| 1882 |
+
"loss": 0.172,
|
| 1883 |
+
"step": 2720
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 30.0,
|
| 1887 |
+
"learning_rate": 1.2013186813186812e-05,
|
| 1888 |
+
"loss": 0.1363,
|
| 1889 |
+
"step": 2730
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 30.11,
|
| 1893 |
+
"learning_rate": 1.1947252747252748e-05,
|
| 1894 |
+
"loss": 0.1109,
|
| 1895 |
+
"step": 2740
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 30.22,
|
| 1899 |
+
"learning_rate": 1.1881318681318681e-05,
|
| 1900 |
+
"loss": 0.0705,
|
| 1901 |
+
"step": 2750
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 30.33,
|
| 1905 |
+
"learning_rate": 1.1815384615384615e-05,
|
| 1906 |
+
"loss": 0.1153,
|
| 1907 |
+
"step": 2760
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 30.44,
|
| 1911 |
+
"learning_rate": 1.174945054945055e-05,
|
| 1912 |
+
"loss": 0.0552,
|
| 1913 |
+
"step": 2770
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 30.55,
|
| 1917 |
+
"learning_rate": 1.1683516483516484e-05,
|
| 1918 |
+
"loss": 0.1828,
|
| 1919 |
+
"step": 2780
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 30.66,
|
| 1923 |
+
"learning_rate": 1.1617582417582418e-05,
|
| 1924 |
+
"loss": 0.1159,
|
| 1925 |
+
"step": 2790
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 30.77,
|
| 1929 |
+
"learning_rate": 1.1551648351648351e-05,
|
| 1930 |
+
"loss": 0.1715,
|
| 1931 |
+
"step": 2800
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 30.77,
|
| 1935 |
+
"eval_accuracy": 0.7470588235294118,
|
| 1936 |
+
"eval_loss": 0.8344667553901672,
|
| 1937 |
+
"eval_runtime": 1.6594,
|
| 1938 |
+
"eval_samples_per_second": 102.448,
|
| 1939 |
+
"eval_steps_per_second": 13.258,
|
| 1940 |
+
"step": 2800
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 30.88,
|
| 1944 |
+
"learning_rate": 1.1485714285714285e-05,
|
| 1945 |
+
"loss": 0.2173,
|
| 1946 |
+
"step": 2810
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 30.99,
|
| 1950 |
+
"learning_rate": 1.141978021978022e-05,
|
| 1951 |
+
"loss": 0.0776,
|
| 1952 |
+
"step": 2820
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 31.1,
|
| 1956 |
+
"learning_rate": 1.1353846153846154e-05,
|
| 1957 |
+
"loss": 0.0849,
|
| 1958 |
+
"step": 2830
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 31.21,
|
| 1962 |
+
"learning_rate": 1.1287912087912088e-05,
|
| 1963 |
+
"loss": 0.1367,
|
| 1964 |
+
"step": 2840
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 31.32,
|
| 1968 |
+
"learning_rate": 1.1221978021978023e-05,
|
| 1969 |
+
"loss": 0.1146,
|
| 1970 |
+
"step": 2850
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 31.43,
|
| 1974 |
+
"learning_rate": 1.1156043956043957e-05,
|
| 1975 |
+
"loss": 0.2185,
|
| 1976 |
+
"step": 2860
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 31.54,
|
| 1980 |
+
"learning_rate": 1.1090109890109889e-05,
|
| 1981 |
+
"loss": 0.1426,
|
| 1982 |
+
"step": 2870
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 31.65,
|
| 1986 |
+
"learning_rate": 1.1024175824175824e-05,
|
| 1987 |
+
"loss": 0.1934,
|
| 1988 |
+
"step": 2880
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 31.76,
|
| 1992 |
+
"learning_rate": 1.0958241758241758e-05,
|
| 1993 |
+
"loss": 0.1535,
|
| 1994 |
+
"step": 2890
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 31.87,
|
| 1998 |
+
"learning_rate": 1.0892307692307692e-05,
|
| 1999 |
+
"loss": 0.1046,
|
| 2000 |
+
"step": 2900
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 31.87,
|
| 2004 |
+
"eval_accuracy": 0.7411764705882353,
|
| 2005 |
+
"eval_loss": 0.8577510118484497,
|
| 2006 |
+
"eval_runtime": 1.6297,
|
| 2007 |
+
"eval_samples_per_second": 104.313,
|
| 2008 |
+
"eval_steps_per_second": 13.499,
|
| 2009 |
+
"step": 2900
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 31.98,
|
| 2013 |
+
"learning_rate": 1.0826373626373627e-05,
|
| 2014 |
+
"loss": 0.1664,
|
| 2015 |
+
"step": 2910
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 32.09,
|
| 2019 |
+
"learning_rate": 1.076043956043956e-05,
|
| 2020 |
+
"loss": 0.1792,
|
| 2021 |
+
"step": 2920
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 32.2,
|
| 2025 |
+
"learning_rate": 1.0694505494505496e-05,
|
| 2026 |
+
"loss": 0.1166,
|
| 2027 |
+
"step": 2930
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 32.31,
|
| 2031 |
+
"learning_rate": 1.0628571428571428e-05,
|
| 2032 |
+
"loss": 0.078,
|
| 2033 |
+
"step": 2940
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 32.42,
|
| 2037 |
+
"learning_rate": 1.0562637362637362e-05,
|
| 2038 |
+
"loss": 0.0868,
|
| 2039 |
+
"step": 2950
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 32.53,
|
| 2043 |
+
"learning_rate": 1.0496703296703297e-05,
|
| 2044 |
+
"loss": 0.0976,
|
| 2045 |
+
"step": 2960
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 32.64,
|
| 2049 |
+
"learning_rate": 1.0430769230769231e-05,
|
| 2050 |
+
"loss": 0.2388,
|
| 2051 |
+
"step": 2970
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 32.75,
|
| 2055 |
+
"learning_rate": 1.0364835164835165e-05,
|
| 2056 |
+
"loss": 0.1135,
|
| 2057 |
+
"step": 2980
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 32.86,
|
| 2061 |
+
"learning_rate": 1.02989010989011e-05,
|
| 2062 |
+
"loss": 0.1377,
|
| 2063 |
+
"step": 2990
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 32.97,
|
| 2067 |
+
"learning_rate": 1.0232967032967034e-05,
|
| 2068 |
+
"loss": 0.1367,
|
| 2069 |
+
"step": 3000
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 32.97,
|
| 2073 |
+
"eval_accuracy": 0.788235294117647,
|
| 2074 |
+
"eval_loss": 0.7669554948806763,
|
| 2075 |
+
"eval_runtime": 1.6159,
|
| 2076 |
+
"eval_samples_per_second": 105.202,
|
| 2077 |
+
"eval_steps_per_second": 13.614,
|
| 2078 |
+
"step": 3000
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 33.08,
|
| 2082 |
+
"learning_rate": 1.0167032967032966e-05,
|
| 2083 |
+
"loss": 0.1076,
|
| 2084 |
+
"step": 3010
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 33.19,
|
| 2088 |
+
"learning_rate": 1.0101098901098901e-05,
|
| 2089 |
+
"loss": 0.1596,
|
| 2090 |
+
"step": 3020
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 33.3,
|
| 2094 |
+
"learning_rate": 1.0035164835164835e-05,
|
| 2095 |
+
"loss": 0.1152,
|
| 2096 |
+
"step": 3030
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 33.41,
|
| 2100 |
+
"learning_rate": 9.96923076923077e-06,
|
| 2101 |
+
"loss": 0.1093,
|
| 2102 |
+
"step": 3040
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 33.52,
|
| 2106 |
+
"learning_rate": 9.903296703296704e-06,
|
| 2107 |
+
"loss": 0.1465,
|
| 2108 |
+
"step": 3050
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 33.63,
|
| 2112 |
+
"learning_rate": 9.843956043956044e-06,
|
| 2113 |
+
"loss": 0.1281,
|
| 2114 |
+
"step": 3060
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 33.74,
|
| 2118 |
+
"learning_rate": 9.778021978021979e-06,
|
| 2119 |
+
"loss": 0.0871,
|
| 2120 |
+
"step": 3070
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 33.85,
|
| 2124 |
+
"learning_rate": 9.712087912087913e-06,
|
| 2125 |
+
"loss": 0.0713,
|
| 2126 |
+
"step": 3080
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 33.96,
|
| 2130 |
+
"learning_rate": 9.646153846153846e-06,
|
| 2131 |
+
"loss": 0.0605,
|
| 2132 |
+
"step": 3090
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 34.07,
|
| 2136 |
+
"learning_rate": 9.580219780219782e-06,
|
| 2137 |
+
"loss": 0.1339,
|
| 2138 |
+
"step": 3100
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 34.07,
|
| 2142 |
+
"eval_accuracy": 0.7647058823529411,
|
| 2143 |
+
"eval_loss": 0.776252269744873,
|
| 2144 |
+
"eval_runtime": 1.6196,
|
| 2145 |
+
"eval_samples_per_second": 104.967,
|
| 2146 |
+
"eval_steps_per_second": 13.584,
|
| 2147 |
+
"step": 3100
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 34.18,
|
| 2151 |
+
"learning_rate": 9.514285714285714e-06,
|
| 2152 |
+
"loss": 0.1543,
|
| 2153 |
+
"step": 3110
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 34.29,
|
| 2157 |
+
"learning_rate": 9.448351648351647e-06,
|
| 2158 |
+
"loss": 0.0526,
|
| 2159 |
+
"step": 3120
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 34.4,
|
| 2163 |
+
"learning_rate": 9.382417582417583e-06,
|
| 2164 |
+
"loss": 0.1342,
|
| 2165 |
+
"step": 3130
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 34.51,
|
| 2169 |
+
"learning_rate": 9.316483516483516e-06,
|
| 2170 |
+
"loss": 0.0849,
|
| 2171 |
+
"step": 3140
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 34.62,
|
| 2175 |
+
"learning_rate": 9.25054945054945e-06,
|
| 2176 |
+
"loss": 0.0898,
|
| 2177 |
+
"step": 3150
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 34.73,
|
| 2181 |
+
"learning_rate": 9.184615384615386e-06,
|
| 2182 |
+
"loss": 0.1102,
|
| 2183 |
+
"step": 3160
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 34.84,
|
| 2187 |
+
"learning_rate": 9.11868131868132e-06,
|
| 2188 |
+
"loss": 0.1245,
|
| 2189 |
+
"step": 3170
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 34.95,
|
| 2193 |
+
"learning_rate": 9.052747252747255e-06,
|
| 2194 |
+
"loss": 0.1517,
|
| 2195 |
+
"step": 3180
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 35.05,
|
| 2199 |
+
"learning_rate": 8.986813186813187e-06,
|
| 2200 |
+
"loss": 0.15,
|
| 2201 |
+
"step": 3190
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 35.16,
|
| 2205 |
+
"learning_rate": 8.92087912087912e-06,
|
| 2206 |
+
"loss": 0.1194,
|
| 2207 |
+
"step": 3200
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 35.16,
|
| 2211 |
+
"eval_accuracy": 0.7705882352941177,
|
| 2212 |
+
"eval_loss": 0.7726542949676514,
|
| 2213 |
+
"eval_runtime": 1.6435,
|
| 2214 |
+
"eval_samples_per_second": 103.438,
|
| 2215 |
+
"eval_steps_per_second": 13.386,
|
| 2216 |
+
"step": 3200
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 35.27,
|
| 2220 |
+
"learning_rate": 8.854945054945056e-06,
|
| 2221 |
+
"loss": 0.0909,
|
| 2222 |
+
"step": 3210
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 35.38,
|
| 2226 |
+
"learning_rate": 8.78901098901099e-06,
|
| 2227 |
+
"loss": 0.0842,
|
| 2228 |
+
"step": 3220
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 35.49,
|
| 2232 |
+
"learning_rate": 8.723076923076923e-06,
|
| 2233 |
+
"loss": 0.1693,
|
| 2234 |
+
"step": 3230
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 35.6,
|
| 2238 |
+
"learning_rate": 8.657142857142858e-06,
|
| 2239 |
+
"loss": 0.1059,
|
| 2240 |
+
"step": 3240
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 35.71,
|
| 2244 |
+
"learning_rate": 8.591208791208792e-06,
|
| 2245 |
+
"loss": 0.1426,
|
| 2246 |
+
"step": 3250
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 35.82,
|
| 2250 |
+
"learning_rate": 8.525274725274724e-06,
|
| 2251 |
+
"loss": 0.1127,
|
| 2252 |
+
"step": 3260
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 35.93,
|
| 2256 |
+
"learning_rate": 8.45934065934066e-06,
|
| 2257 |
+
"loss": 0.0513,
|
| 2258 |
+
"step": 3270
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 36.04,
|
| 2262 |
+
"learning_rate": 8.393406593406593e-06,
|
| 2263 |
+
"loss": 0.1005,
|
| 2264 |
+
"step": 3280
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 36.15,
|
| 2268 |
+
"learning_rate": 8.327472527472527e-06,
|
| 2269 |
+
"loss": 0.0906,
|
| 2270 |
+
"step": 3290
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 36.26,
|
| 2274 |
+
"learning_rate": 8.261538461538462e-06,
|
| 2275 |
+
"loss": 0.151,
|
| 2276 |
+
"step": 3300
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 36.26,
|
| 2280 |
+
"eval_accuracy": 0.7470588235294118,
|
| 2281 |
+
"eval_loss": 0.8271679878234863,
|
| 2282 |
+
"eval_runtime": 1.8428,
|
| 2283 |
+
"eval_samples_per_second": 92.249,
|
| 2284 |
+
"eval_steps_per_second": 11.938,
|
| 2285 |
+
"step": 3300
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 36.37,
|
| 2289 |
+
"learning_rate": 8.195604395604396e-06,
|
| 2290 |
+
"loss": 0.0569,
|
| 2291 |
+
"step": 3310
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 36.48,
|
| 2295 |
+
"learning_rate": 8.129670329670331e-06,
|
| 2296 |
+
"loss": 0.1806,
|
| 2297 |
+
"step": 3320
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 36.59,
|
| 2301 |
+
"learning_rate": 8.063736263736263e-06,
|
| 2302 |
+
"loss": 0.1399,
|
| 2303 |
+
"step": 3330
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 36.7,
|
| 2307 |
+
"learning_rate": 7.997802197802197e-06,
|
| 2308 |
+
"loss": 0.1186,
|
| 2309 |
+
"step": 3340
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 36.81,
|
| 2313 |
+
"learning_rate": 7.931868131868132e-06,
|
| 2314 |
+
"loss": 0.0971,
|
| 2315 |
+
"step": 3350
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 36.92,
|
| 2319 |
+
"learning_rate": 7.865934065934066e-06,
|
| 2320 |
+
"loss": 0.1759,
|
| 2321 |
+
"step": 3360
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 37.03,
|
| 2325 |
+
"learning_rate": 7.8e-06,
|
| 2326 |
+
"loss": 0.0609,
|
| 2327 |
+
"step": 3370
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 37.14,
|
| 2331 |
+
"learning_rate": 7.734065934065935e-06,
|
| 2332 |
+
"loss": 0.101,
|
| 2333 |
+
"step": 3380
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 37.25,
|
| 2337 |
+
"learning_rate": 7.668131868131869e-06,
|
| 2338 |
+
"loss": 0.0826,
|
| 2339 |
+
"step": 3390
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 37.36,
|
| 2343 |
+
"learning_rate": 7.602197802197802e-06,
|
| 2344 |
+
"loss": 0.0646,
|
| 2345 |
+
"step": 3400
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 37.36,
|
| 2349 |
+
"eval_accuracy": 0.7764705882352941,
|
| 2350 |
+
"eval_loss": 0.7721197009086609,
|
| 2351 |
+
"eval_runtime": 1.6753,
|
| 2352 |
+
"eval_samples_per_second": 101.472,
|
| 2353 |
+
"eval_steps_per_second": 13.132,
|
| 2354 |
+
"step": 3400
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 37.47,
|
| 2358 |
+
"learning_rate": 7.536263736263736e-06,
|
| 2359 |
+
"loss": 0.1707,
|
| 2360 |
+
"step": 3410
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 37.58,
|
| 2364 |
+
"learning_rate": 7.47032967032967e-06,
|
| 2365 |
+
"loss": 0.114,
|
| 2366 |
+
"step": 3420
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 37.69,
|
| 2370 |
+
"learning_rate": 7.4043956043956046e-06,
|
| 2371 |
+
"loss": 0.1188,
|
| 2372 |
+
"step": 3430
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 37.8,
|
| 2376 |
+
"learning_rate": 7.338461538461539e-06,
|
| 2377 |
+
"loss": 0.1788,
|
| 2378 |
+
"step": 3440
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 37.91,
|
| 2382 |
+
"learning_rate": 7.272527472527472e-06,
|
| 2383 |
+
"loss": 0.1241,
|
| 2384 |
+
"step": 3450
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 38.02,
|
| 2388 |
+
"learning_rate": 7.2065934065934065e-06,
|
| 2389 |
+
"loss": 0.1308,
|
| 2390 |
+
"step": 3460
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 38.13,
|
| 2394 |
+
"learning_rate": 7.140659340659341e-06,
|
| 2395 |
+
"loss": 0.1154,
|
| 2396 |
+
"step": 3470
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 38.24,
|
| 2400 |
+
"learning_rate": 7.0747252747252756e-06,
|
| 2401 |
+
"loss": 0.1787,
|
| 2402 |
+
"step": 3480
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 38.35,
|
| 2406 |
+
"learning_rate": 7.008791208791208e-06,
|
| 2407 |
+
"loss": 0.1262,
|
| 2408 |
+
"step": 3490
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 38.46,
|
| 2412 |
+
"learning_rate": 6.942857142857143e-06,
|
| 2413 |
+
"loss": 0.0801,
|
| 2414 |
+
"step": 3500
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 38.46,
|
| 2418 |
+
"eval_accuracy": 0.7529411764705882,
|
| 2419 |
+
"eval_loss": 0.8170506358146667,
|
| 2420 |
+
"eval_runtime": 1.6607,
|
| 2421 |
+
"eval_samples_per_second": 102.365,
|
| 2422 |
+
"eval_steps_per_second": 13.247,
|
| 2423 |
+
"step": 3500
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 38.57,
|
| 2427 |
+
"learning_rate": 6.8769230769230775e-06,
|
| 2428 |
+
"loss": 0.098,
|
| 2429 |
+
"step": 3510
|
| 2430 |
+
},
|
| 2431 |
+
{
|
| 2432 |
+
"epoch": 38.68,
|
| 2433 |
+
"learning_rate": 6.810989010989011e-06,
|
| 2434 |
+
"loss": 0.1109,
|
| 2435 |
+
"step": 3520
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 38.79,
|
| 2439 |
+
"learning_rate": 6.745054945054945e-06,
|
| 2440 |
+
"loss": 0.1078,
|
| 2441 |
+
"step": 3530
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 38.9,
|
| 2445 |
+
"learning_rate": 6.679120879120879e-06,
|
| 2446 |
+
"loss": 0.0767,
|
| 2447 |
+
"step": 3540
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 39.01,
|
| 2451 |
+
"learning_rate": 6.613186813186814e-06,
|
| 2452 |
+
"loss": 0.0886,
|
| 2453 |
+
"step": 3550
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 39.12,
|
| 2457 |
+
"learning_rate": 6.547252747252747e-06,
|
| 2458 |
+
"loss": 0.0631,
|
| 2459 |
+
"step": 3560
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 39.23,
|
| 2463 |
+
"learning_rate": 6.481318681318681e-06,
|
| 2464 |
+
"loss": 0.0737,
|
| 2465 |
+
"step": 3570
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 39.34,
|
| 2469 |
+
"learning_rate": 6.415384615384616e-06,
|
| 2470 |
+
"loss": 0.1207,
|
| 2471 |
+
"step": 3580
|
| 2472 |
+
},
|
| 2473 |
+
{
|
| 2474 |
+
"epoch": 39.45,
|
| 2475 |
+
"learning_rate": 6.3494505494505496e-06,
|
| 2476 |
+
"loss": 0.0831,
|
| 2477 |
+
"step": 3590
|
| 2478 |
+
},
|
| 2479 |
+
{
|
| 2480 |
+
"epoch": 39.56,
|
| 2481 |
+
"learning_rate": 6.283516483516483e-06,
|
| 2482 |
+
"loss": 0.1038,
|
| 2483 |
+
"step": 3600
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 39.56,
|
| 2487 |
+
"eval_accuracy": 0.7058823529411765,
|
| 2488 |
+
"eval_loss": 0.9464375376701355,
|
| 2489 |
+
"eval_runtime": 1.6231,
|
| 2490 |
+
"eval_samples_per_second": 104.738,
|
| 2491 |
+
"eval_steps_per_second": 13.554,
|
| 2492 |
+
"step": 3600
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 39.67,
|
| 2496 |
+
"learning_rate": 6.217582417582418e-06,
|
| 2497 |
+
"loss": 0.1151,
|
| 2498 |
+
"step": 3610
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 39.78,
|
| 2502 |
+
"learning_rate": 6.151648351648352e-06,
|
| 2503 |
+
"loss": 0.113,
|
| 2504 |
+
"step": 3620
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 39.89,
|
| 2508 |
+
"learning_rate": 6.085714285714285e-06,
|
| 2509 |
+
"loss": 0.1226,
|
| 2510 |
+
"step": 3630
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 40.0,
|
| 2514 |
+
"learning_rate": 6.01978021978022e-06,
|
| 2515 |
+
"loss": 0.0645,
|
| 2516 |
+
"step": 3640
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 40.11,
|
| 2520 |
+
"learning_rate": 5.953846153846154e-06,
|
| 2521 |
+
"loss": 0.1398,
|
| 2522 |
+
"step": 3650
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 40.22,
|
| 2526 |
+
"learning_rate": 5.887912087912089e-06,
|
| 2527 |
+
"loss": 0.0801,
|
| 2528 |
+
"step": 3660
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 40.33,
|
| 2532 |
+
"learning_rate": 5.821978021978022e-06,
|
| 2533 |
+
"loss": 0.0787,
|
| 2534 |
+
"step": 3670
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 40.44,
|
| 2538 |
+
"learning_rate": 5.756043956043956e-06,
|
| 2539 |
+
"loss": 0.1388,
|
| 2540 |
+
"step": 3680
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 40.55,
|
| 2544 |
+
"learning_rate": 5.690109890109891e-06,
|
| 2545 |
+
"loss": 0.0356,
|
| 2546 |
+
"step": 3690
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 40.66,
|
| 2550 |
+
"learning_rate": 5.624175824175824e-06,
|
| 2551 |
+
"loss": 0.16,
|
| 2552 |
+
"step": 3700
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 40.66,
|
| 2556 |
+
"eval_accuracy": 0.7705882352941177,
|
| 2557 |
+
"eval_loss": 0.8004665374755859,
|
| 2558 |
+
"eval_runtime": 1.6262,
|
| 2559 |
+
"eval_samples_per_second": 104.537,
|
| 2560 |
+
"eval_steps_per_second": 13.528,
|
| 2561 |
+
"step": 3700
|
| 2562 |
+
},
|
| 2563 |
+
{
|
| 2564 |
+
"epoch": 40.77,
|
| 2565 |
+
"learning_rate": 5.558241758241758e-06,
|
| 2566 |
+
"loss": 0.1363,
|
| 2567 |
+
"step": 3710
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 40.88,
|
| 2571 |
+
"learning_rate": 5.492307692307693e-06,
|
| 2572 |
+
"loss": 0.0803,
|
| 2573 |
+
"step": 3720
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 40.99,
|
| 2577 |
+
"learning_rate": 5.426373626373627e-06,
|
| 2578 |
+
"loss": 0.077,
|
| 2579 |
+
"step": 3730
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 41.1,
|
| 2583 |
+
"learning_rate": 5.36043956043956e-06,
|
| 2584 |
+
"loss": 0.0912,
|
| 2585 |
+
"step": 3740
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 41.21,
|
| 2589 |
+
"learning_rate": 5.2945054945054946e-06,
|
| 2590 |
+
"loss": 0.1425,
|
| 2591 |
+
"step": 3750
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 41.32,
|
| 2595 |
+
"learning_rate": 5.228571428571429e-06,
|
| 2596 |
+
"loss": 0.0815,
|
| 2597 |
+
"step": 3760
|
| 2598 |
+
},
|
| 2599 |
+
{
|
| 2600 |
+
"epoch": 41.43,
|
| 2601 |
+
"learning_rate": 5.162637362637363e-06,
|
| 2602 |
+
"loss": 0.0987,
|
| 2603 |
+
"step": 3770
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 41.54,
|
| 2607 |
+
"learning_rate": 5.0967032967032965e-06,
|
| 2608 |
+
"loss": 0.0457,
|
| 2609 |
+
"step": 3780
|
| 2610 |
+
},
|
| 2611 |
+
{
|
| 2612 |
+
"epoch": 41.65,
|
| 2613 |
+
"learning_rate": 5.030769230769231e-06,
|
| 2614 |
+
"loss": 0.1181,
|
| 2615 |
+
"step": 3790
|
| 2616 |
+
},
|
| 2617 |
+
{
|
| 2618 |
+
"epoch": 41.76,
|
| 2619 |
+
"learning_rate": 4.9648351648351656e-06,
|
| 2620 |
+
"loss": 0.1151,
|
| 2621 |
+
"step": 3800
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 41.76,
|
| 2625 |
+
"eval_accuracy": 0.7470588235294118,
|
| 2626 |
+
"eval_loss": 0.8784206509590149,
|
| 2627 |
+
"eval_runtime": 1.6555,
|
| 2628 |
+
"eval_samples_per_second": 102.688,
|
| 2629 |
+
"eval_steps_per_second": 13.289,
|
| 2630 |
+
"step": 3800
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 41.87,
|
| 2634 |
+
"learning_rate": 4.898901098901098e-06,
|
| 2635 |
+
"loss": 0.1219,
|
| 2636 |
+
"step": 3810
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 41.98,
|
| 2640 |
+
"learning_rate": 4.832967032967033e-06,
|
| 2641 |
+
"loss": 0.0719,
|
| 2642 |
+
"step": 3820
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 42.09,
|
| 2646 |
+
"learning_rate": 4.7670329670329675e-06,
|
| 2647 |
+
"loss": 0.0647,
|
| 2648 |
+
"step": 3830
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 42.2,
|
| 2652 |
+
"learning_rate": 4.701098901098901e-06,
|
| 2653 |
+
"loss": 0.1066,
|
| 2654 |
+
"step": 3840
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 42.31,
|
| 2658 |
+
"learning_rate": 4.635164835164835e-06,
|
| 2659 |
+
"loss": 0.052,
|
| 2660 |
+
"step": 3850
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 42.42,
|
| 2664 |
+
"learning_rate": 4.569230769230769e-06,
|
| 2665 |
+
"loss": 0.0658,
|
| 2666 |
+
"step": 3860
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 42.53,
|
| 2670 |
+
"learning_rate": 4.503296703296704e-06,
|
| 2671 |
+
"loss": 0.0851,
|
| 2672 |
+
"step": 3870
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 42.64,
|
| 2676 |
+
"learning_rate": 4.437362637362637e-06,
|
| 2677 |
+
"loss": 0.071,
|
| 2678 |
+
"step": 3880
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 42.75,
|
| 2682 |
+
"learning_rate": 4.371428571428571e-06,
|
| 2683 |
+
"loss": 0.0922,
|
| 2684 |
+
"step": 3890
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 42.86,
|
| 2688 |
+
"learning_rate": 4.305494505494506e-06,
|
| 2689 |
+
"loss": 0.1159,
|
| 2690 |
+
"step": 3900
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 42.86,
|
| 2694 |
+
"eval_accuracy": 0.7470588235294118,
|
| 2695 |
+
"eval_loss": 0.85979163646698,
|
| 2696 |
+
"eval_runtime": 1.6327,
|
| 2697 |
+
"eval_samples_per_second": 104.124,
|
| 2698 |
+
"eval_steps_per_second": 13.475,
|
| 2699 |
+
"step": 3900
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 42.97,
|
| 2703 |
+
"learning_rate": 4.2395604395604396e-06,
|
| 2704 |
+
"loss": 0.1347,
|
| 2705 |
+
"step": 3910
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 43.08,
|
| 2709 |
+
"learning_rate": 4.173626373626373e-06,
|
| 2710 |
+
"loss": 0.0455,
|
| 2711 |
+
"step": 3920
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 43.19,
|
| 2715 |
+
"learning_rate": 4.107692307692308e-06,
|
| 2716 |
+
"loss": 0.054,
|
| 2717 |
+
"step": 3930
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 43.3,
|
| 2721 |
+
"learning_rate": 4.041758241758242e-06,
|
| 2722 |
+
"loss": 0.1078,
|
| 2723 |
+
"step": 3940
|
| 2724 |
+
},
|
| 2725 |
+
{
|
| 2726 |
+
"epoch": 43.41,
|
| 2727 |
+
"learning_rate": 3.975824175824176e-06,
|
| 2728 |
+
"loss": 0.0738,
|
| 2729 |
+
"step": 3950
|
| 2730 |
+
},
|
| 2731 |
+
{
|
| 2732 |
+
"epoch": 43.52,
|
| 2733 |
+
"learning_rate": 3.90989010989011e-06,
|
| 2734 |
+
"loss": 0.0672,
|
| 2735 |
+
"step": 3960
|
| 2736 |
+
},
|
| 2737 |
+
{
|
| 2738 |
+
"epoch": 43.63,
|
| 2739 |
+
"learning_rate": 3.843956043956044e-06,
|
| 2740 |
+
"loss": 0.0476,
|
| 2741 |
+
"step": 3970
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 43.74,
|
| 2745 |
+
"learning_rate": 3.7780219780219784e-06,
|
| 2746 |
+
"loss": 0.1283,
|
| 2747 |
+
"step": 3980
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 43.85,
|
| 2751 |
+
"learning_rate": 3.712087912087912e-06,
|
| 2752 |
+
"loss": 0.1116,
|
| 2753 |
+
"step": 3990
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 43.96,
|
| 2757 |
+
"learning_rate": 3.646153846153846e-06,
|
| 2758 |
+
"loss": 0.0575,
|
| 2759 |
+
"step": 4000
|
| 2760 |
+
},
|
| 2761 |
+
{
|
| 2762 |
+
"epoch": 43.96,
|
| 2763 |
+
"eval_accuracy": 0.7529411764705882,
|
| 2764 |
+
"eval_loss": 0.8543334007263184,
|
| 2765 |
+
"eval_runtime": 1.6405,
|
| 2766 |
+
"eval_samples_per_second": 103.629,
|
| 2767 |
+
"eval_steps_per_second": 13.411,
|
| 2768 |
+
"step": 4000
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 44.07,
|
| 2772 |
+
"learning_rate": 3.5802197802197803e-06,
|
| 2773 |
+
"loss": 0.079,
|
| 2774 |
+
"step": 4010
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 44.18,
|
| 2778 |
+
"learning_rate": 3.5142857142857144e-06,
|
| 2779 |
+
"loss": 0.0763,
|
| 2780 |
+
"step": 4020
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 44.29,
|
| 2784 |
+
"learning_rate": 3.4483516483516485e-06,
|
| 2785 |
+
"loss": 0.0445,
|
| 2786 |
+
"step": 4030
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 44.4,
|
| 2790 |
+
"learning_rate": 3.3824175824175826e-06,
|
| 2791 |
+
"loss": 0.0939,
|
| 2792 |
+
"step": 4040
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 44.51,
|
| 2796 |
+
"learning_rate": 3.3164835164835163e-06,
|
| 2797 |
+
"loss": 0.1475,
|
| 2798 |
+
"step": 4050
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 44.62,
|
| 2802 |
+
"learning_rate": 3.250549450549451e-06,
|
| 2803 |
+
"loss": 0.1596,
|
| 2804 |
+
"step": 4060
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 44.73,
|
| 2808 |
+
"learning_rate": 3.1846153846153846e-06,
|
| 2809 |
+
"loss": 0.1322,
|
| 2810 |
+
"step": 4070
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 44.84,
|
| 2814 |
+
"learning_rate": 3.1186813186813187e-06,
|
| 2815 |
+
"loss": 0.1158,
|
| 2816 |
+
"step": 4080
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 44.95,
|
| 2820 |
+
"learning_rate": 3.0527472527472528e-06,
|
| 2821 |
+
"loss": 0.075,
|
| 2822 |
+
"step": 4090
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 45.05,
|
| 2826 |
+
"learning_rate": 2.986813186813187e-06,
|
| 2827 |
+
"loss": 0.164,
|
| 2828 |
+
"step": 4100
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 45.05,
|
| 2832 |
+
"eval_accuracy": 0.7588235294117647,
|
| 2833 |
+
"eval_loss": 0.8658636808395386,
|
| 2834 |
+
"eval_runtime": 1.518,
|
| 2835 |
+
"eval_samples_per_second": 111.989,
|
| 2836 |
+
"eval_steps_per_second": 14.493,
|
| 2837 |
+
"step": 4100
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 45.16,
|
| 2841 |
+
"learning_rate": 2.920879120879121e-06,
|
| 2842 |
+
"loss": 0.0847,
|
| 2843 |
+
"step": 4110
|
| 2844 |
+
},
|
| 2845 |
+
{
|
| 2846 |
+
"epoch": 45.27,
|
| 2847 |
+
"learning_rate": 2.854945054945055e-06,
|
| 2848 |
+
"loss": 0.1098,
|
| 2849 |
+
"step": 4120
|
| 2850 |
+
},
|
| 2851 |
+
{
|
| 2852 |
+
"epoch": 45.38,
|
| 2853 |
+
"learning_rate": 2.7890109890109892e-06,
|
| 2854 |
+
"loss": 0.1282,
|
| 2855 |
+
"step": 4130
|
| 2856 |
+
},
|
| 2857 |
+
{
|
| 2858 |
+
"epoch": 45.49,
|
| 2859 |
+
"learning_rate": 2.723076923076923e-06,
|
| 2860 |
+
"loss": 0.0736,
|
| 2861 |
+
"step": 4140
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 45.6,
|
| 2865 |
+
"learning_rate": 2.657142857142857e-06,
|
| 2866 |
+
"loss": 0.1344,
|
| 2867 |
+
"step": 4150
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 45.71,
|
| 2871 |
+
"learning_rate": 2.591208791208791e-06,
|
| 2872 |
+
"loss": 0.1191,
|
| 2873 |
+
"step": 4160
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 45.82,
|
| 2877 |
+
"learning_rate": 2.5252747252747253e-06,
|
| 2878 |
+
"loss": 0.0721,
|
| 2879 |
+
"step": 4170
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 45.93,
|
| 2883 |
+
"learning_rate": 2.4593406593406594e-06,
|
| 2884 |
+
"loss": 0.0371,
|
| 2885 |
+
"step": 4180
|
| 2886 |
+
},
|
| 2887 |
+
{
|
| 2888 |
+
"epoch": 46.04,
|
| 2889 |
+
"learning_rate": 2.3934065934065935e-06,
|
| 2890 |
+
"loss": 0.0407,
|
| 2891 |
+
"step": 4190
|
| 2892 |
+
},
|
| 2893 |
+
{
|
| 2894 |
+
"epoch": 46.15,
|
| 2895 |
+
"learning_rate": 2.3274725274725276e-06,
|
| 2896 |
+
"loss": 0.1319,
|
| 2897 |
+
"step": 4200
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 46.15,
|
| 2901 |
+
"eval_accuracy": 0.7411764705882353,
|
| 2902 |
+
"eval_loss": 0.885351300239563,
|
| 2903 |
+
"eval_runtime": 1.4998,
|
| 2904 |
+
"eval_samples_per_second": 113.347,
|
| 2905 |
+
"eval_steps_per_second": 14.668,
|
| 2906 |
+
"step": 4200
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 46.26,
|
| 2910 |
+
"learning_rate": 2.2615384615384617e-06,
|
| 2911 |
+
"loss": 0.1159,
|
| 2912 |
+
"step": 4210
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 46.37,
|
| 2916 |
+
"learning_rate": 2.195604395604396e-06,
|
| 2917 |
+
"loss": 0.0659,
|
| 2918 |
+
"step": 4220
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 46.48,
|
| 2922 |
+
"learning_rate": 2.1296703296703296e-06,
|
| 2923 |
+
"loss": 0.0948,
|
| 2924 |
+
"step": 4230
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 46.59,
|
| 2928 |
+
"learning_rate": 2.0637362637362637e-06,
|
| 2929 |
+
"loss": 0.0886,
|
| 2930 |
+
"step": 4240
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 46.7,
|
| 2934 |
+
"learning_rate": 1.9978021978021978e-06,
|
| 2935 |
+
"loss": 0.0889,
|
| 2936 |
+
"step": 4250
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 46.81,
|
| 2940 |
+
"learning_rate": 1.931868131868132e-06,
|
| 2941 |
+
"loss": 0.0339,
|
| 2942 |
+
"step": 4260
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 46.92,
|
| 2946 |
+
"learning_rate": 1.8659340659340658e-06,
|
| 2947 |
+
"loss": 0.0697,
|
| 2948 |
+
"step": 4270
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 47.03,
|
| 2952 |
+
"learning_rate": 1.8e-06,
|
| 2953 |
+
"loss": 0.0777,
|
| 2954 |
+
"step": 4280
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 47.14,
|
| 2958 |
+
"learning_rate": 1.734065934065934e-06,
|
| 2959 |
+
"loss": 0.0546,
|
| 2960 |
+
"step": 4290
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 47.25,
|
| 2964 |
+
"learning_rate": 1.6681318681318681e-06,
|
| 2965 |
+
"loss": 0.0489,
|
| 2966 |
+
"step": 4300
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 47.25,
|
| 2970 |
+
"eval_accuracy": 0.7588235294117647,
|
| 2971 |
+
"eval_loss": 0.7507675886154175,
|
| 2972 |
+
"eval_runtime": 1.5139,
|
| 2973 |
+
"eval_samples_per_second": 112.29,
|
| 2974 |
+
"eval_steps_per_second": 14.532,
|
| 2975 |
+
"step": 4300
|
| 2976 |
+
},
|
| 2977 |
+
{
|
| 2978 |
+
"epoch": 47.36,
|
| 2979 |
+
"learning_rate": 1.6021978021978023e-06,
|
| 2980 |
+
"loss": 0.087,
|
| 2981 |
+
"step": 4310
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 47.47,
|
| 2985 |
+
"learning_rate": 1.5362637362637364e-06,
|
| 2986 |
+
"loss": 0.0452,
|
| 2987 |
+
"step": 4320
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 47.58,
|
| 2991 |
+
"learning_rate": 1.4703296703296705e-06,
|
| 2992 |
+
"loss": 0.0508,
|
| 2993 |
+
"step": 4330
|
| 2994 |
+
},
|
| 2995 |
+
{
|
| 2996 |
+
"epoch": 47.69,
|
| 2997 |
+
"learning_rate": 1.4043956043956046e-06,
|
| 2998 |
+
"loss": 0.0812,
|
| 2999 |
+
"step": 4340
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 47.8,
|
| 3003 |
+
"learning_rate": 1.3384615384615383e-06,
|
| 3004 |
+
"loss": 0.0721,
|
| 3005 |
+
"step": 4350
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 47.91,
|
| 3009 |
+
"learning_rate": 1.2725274725274724e-06,
|
| 3010 |
+
"loss": 0.0835,
|
| 3011 |
+
"step": 4360
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 48.02,
|
| 3015 |
+
"learning_rate": 1.2065934065934065e-06,
|
| 3016 |
+
"loss": 0.1077,
|
| 3017 |
+
"step": 4370
|
| 3018 |
+
},
|
| 3019 |
+
{
|
| 3020 |
+
"epoch": 48.13,
|
| 3021 |
+
"learning_rate": 1.1406593406593406e-06,
|
| 3022 |
+
"loss": 0.0636,
|
| 3023 |
+
"step": 4380
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 48.24,
|
| 3027 |
+
"learning_rate": 1.0747252747252748e-06,
|
| 3028 |
+
"loss": 0.1026,
|
| 3029 |
+
"step": 4390
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 48.35,
|
| 3033 |
+
"learning_rate": 1.0087912087912089e-06,
|
| 3034 |
+
"loss": 0.0678,
|
| 3035 |
+
"step": 4400
|
| 3036 |
+
},
|
| 3037 |
+
{
|
| 3038 |
+
"epoch": 48.35,
|
| 3039 |
+
"eval_accuracy": 0.7352941176470589,
|
| 3040 |
+
"eval_loss": 0.8784447312355042,
|
| 3041 |
+
"eval_runtime": 1.5075,
|
| 3042 |
+
"eval_samples_per_second": 112.768,
|
| 3043 |
+
"eval_steps_per_second": 14.594,
|
| 3044 |
+
"step": 4400
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 48.46,
|
| 3048 |
+
"learning_rate": 9.42857142857143e-07,
|
| 3049 |
+
"loss": 0.072,
|
| 3050 |
+
"step": 4410
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 48.57,
|
| 3054 |
+
"learning_rate": 8.769230769230769e-07,
|
| 3055 |
+
"loss": 0.0526,
|
| 3056 |
+
"step": 4420
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 48.68,
|
| 3060 |
+
"learning_rate": 8.10989010989011e-07,
|
| 3061 |
+
"loss": 0.0802,
|
| 3062 |
+
"step": 4430
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 48.79,
|
| 3066 |
+
"learning_rate": 7.450549450549451e-07,
|
| 3067 |
+
"loss": 0.046,
|
| 3068 |
+
"step": 4440
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 48.9,
|
| 3072 |
+
"learning_rate": 6.791208791208791e-07,
|
| 3073 |
+
"loss": 0.0656,
|
| 3074 |
+
"step": 4450
|
| 3075 |
+
},
|
| 3076 |
+
{
|
| 3077 |
+
"epoch": 49.01,
|
| 3078 |
+
"learning_rate": 6.131868131868131e-07,
|
| 3079 |
+
"loss": 0.139,
|
| 3080 |
+
"step": 4460
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 49.12,
|
| 3084 |
+
"learning_rate": 5.472527472527473e-07,
|
| 3085 |
+
"loss": 0.0576,
|
| 3086 |
+
"step": 4470
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 49.23,
|
| 3090 |
+
"learning_rate": 4.813186813186814e-07,
|
| 3091 |
+
"loss": 0.0686,
|
| 3092 |
+
"step": 4480
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 49.34,
|
| 3096 |
+
"learning_rate": 4.153846153846154e-07,
|
| 3097 |
+
"loss": 0.0658,
|
| 3098 |
+
"step": 4490
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 49.45,
|
| 3102 |
+
"learning_rate": 3.4945054945054945e-07,
|
| 3103 |
+
"loss": 0.0832,
|
| 3104 |
+
"step": 4500
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 49.45,
|
| 3108 |
+
"eval_accuracy": 0.7764705882352941,
|
| 3109 |
+
"eval_loss": 0.7247602343559265,
|
| 3110 |
+
"eval_runtime": 1.5084,
|
| 3111 |
+
"eval_samples_per_second": 112.699,
|
| 3112 |
+
"eval_steps_per_second": 14.585,
|
| 3113 |
+
"step": 4500
|
| 3114 |
+
},
|
| 3115 |
+
{
|
| 3116 |
+
"epoch": 49.56,
|
| 3117 |
+
"learning_rate": 2.835164835164835e-07,
|
| 3118 |
+
"loss": 0.0692,
|
| 3119 |
+
"step": 4510
|
| 3120 |
+
},
|
| 3121 |
+
{
|
| 3122 |
+
"epoch": 49.67,
|
| 3123 |
+
"learning_rate": 2.175824175824176e-07,
|
| 3124 |
+
"loss": 0.1135,
|
| 3125 |
+
"step": 4520
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 49.78,
|
| 3129 |
+
"learning_rate": 1.5164835164835167e-07,
|
| 3130 |
+
"loss": 0.1512,
|
| 3131 |
+
"step": 4530
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 49.89,
|
| 3135 |
+
"learning_rate": 8.571428571428572e-08,
|
| 3136 |
+
"loss": 0.1339,
|
| 3137 |
+
"step": 4540
|
| 3138 |
+
},
|
| 3139 |
+
{
|
| 3140 |
+
"epoch": 50.0,
|
| 3141 |
+
"learning_rate": 1.9780219780219782e-08,
|
| 3142 |
+
"loss": 0.1045,
|
| 3143 |
+
"step": 4550
|
| 3144 |
+
},
|
| 3145 |
+
{
|
| 3146 |
+
"epoch": 50.0,
|
| 3147 |
+
"step": 4550,
|
| 3148 |
+
"total_flos": 5.622144623740109e+18,
|
| 3149 |
+
"train_loss": 0.2358846340533141,
|
| 3150 |
+
"train_runtime": 1979.1189,
|
| 3151 |
+
"train_samples_per_second": 36.658,
|
| 3152 |
+
"train_steps_per_second": 2.299
|
| 3153 |
}
|
| 3154 |
],
|
| 3155 |
+
"max_steps": 4550,
|
| 3156 |
+
"num_train_epochs": 50,
|
| 3157 |
+
"total_flos": 5.622144623740109e+18,
|
| 3158 |
"trial_name": null,
|
| 3159 |
"trial_params": null
|
| 3160 |
}
|