Commit
•
09d6b7d
1
Parent(s):
71af103
End of training
Browse files- all_results.json +9 -9
- eval_results.json +5 -5
- runs/Mar16_07-56-12_9065e78e46e3/events.out.tfevents.1710579312.9065e78e46e3.418.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +459 -257
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
"total_flos": 2.0021605356722135e+19,
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.8732149076976663,
|
| 4 |
+
"eval_loss": 0.3263641893863678,
|
| 5 |
+
"eval_runtime": 15.9042,
|
| 6 |
+
"eval_samples_per_second": 180.518,
|
| 7 |
+
"eval_steps_per_second": 5.659,
|
| 8 |
"total_flos": 2.0021605356722135e+19,
|
| 9 |
+
"train_loss": 0.37925267927717454,
|
| 10 |
+
"train_runtime": 3266.1275,
|
| 11 |
+
"train_samples_per_second": 79.106,
|
| 12 |
+
"train_steps_per_second": 0.618
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.8732149076976663,
|
| 4 |
+
"eval_loss": 0.3263641893863678,
|
| 5 |
+
"eval_runtime": 15.9042,
|
| 6 |
+
"eval_samples_per_second": 180.518,
|
| 7 |
+
"eval_steps_per_second": 5.659
|
| 8 |
}
|
runs/Mar16_07-56-12_9065e78e46e3/events.out.tfevents.1710579312.9065e78e46e3.418.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:514b9e06e795d1a44bc748b203fb89bde681035259920a64218a64963429dd9a
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"total_flos": 2.0021605356722135e+19,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"total_flos": 2.0021605356722135e+19,
|
| 4 |
+
"train_loss": 0.37925267927717454,
|
| 5 |
+
"train_runtime": 3266.1275,
|
| 6 |
+
"train_samples_per_second": 79.106,
|
| 7 |
+
"train_steps_per_second": 0.618
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-FER2013/checkpoint-
|
| 4 |
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 2020,
|
|
@@ -10,1314 +10,1516 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.05,
|
|
|
|
| 13 |
"learning_rate": 2.4752475247524753e-06,
|
| 14 |
-
"loss": 0.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.1,
|
|
|
|
| 19 |
"learning_rate": 4.950495049504951e-06,
|
| 20 |
-
"loss": 0.
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.15,
|
|
|
|
| 25 |
"learning_rate": 7.4257425742574256e-06,
|
| 26 |
"loss": 0.6891,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.2,
|
|
|
|
| 31 |
"learning_rate": 9.900990099009901e-06,
|
| 32 |
-
"loss": 0.
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.25,
|
|
|
|
| 37 |
"learning_rate": 1.2376237623762377e-05,
|
| 38 |
-
"loss": 0.
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.3,
|
|
|
|
| 43 |
"learning_rate": 1.4851485148514851e-05,
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.35,
|
|
|
|
| 49 |
"learning_rate": 1.7326732673267325e-05,
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.4,
|
|
|
|
| 55 |
"learning_rate": 1.9801980198019803e-05,
|
| 56 |
-
"loss": 0.
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.45,
|
|
|
|
| 61 |
"learning_rate": 2.227722772277228e-05,
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.5,
|
|
|
|
| 67 |
"learning_rate": 2.4752475247524754e-05,
|
| 68 |
-
"loss": 0.
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.54,
|
|
|
|
| 73 |
"learning_rate": 2.722772277227723e-05,
|
| 74 |
-
"loss": 0.
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.59,
|
|
|
|
| 79 |
"learning_rate": 2.9702970297029702e-05,
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.64,
|
|
|
|
| 85 |
"learning_rate": 3.217821782178218e-05,
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.69,
|
|
|
|
| 91 |
"learning_rate": 3.465346534653465e-05,
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.74,
|
|
|
|
| 97 |
"learning_rate": 3.712871287128713e-05,
|
| 98 |
-
"loss": 0.
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.79,
|
|
|
|
| 103 |
"learning_rate": 3.9603960396039605e-05,
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 160
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.84,
|
|
|
|
| 109 |
"learning_rate": 4.207920792079208e-05,
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 170
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.89,
|
|
|
|
| 115 |
"learning_rate": 4.455445544554456e-05,
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 180
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.94,
|
|
|
|
| 121 |
"learning_rate": 4.702970297029703e-05,
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 190
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.99,
|
|
|
|
| 127 |
"learning_rate": 4.950495049504951e-05,
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 200
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 1.0,
|
| 133 |
-
"eval_accuracy": 0.
|
| 134 |
-
"eval_loss": 0.
|
| 135 |
-
"eval_runtime": 15.
|
| 136 |
-
"eval_samples_per_second":
|
| 137 |
-
"eval_steps_per_second": 5.
|
| 138 |
"step": 202
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 1.04,
|
|
|
|
| 142 |
"learning_rate": 4.977997799779978e-05,
|
| 143 |
-
"loss": 0.
|
| 144 |
"step": 210
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 1.09,
|
|
|
|
| 148 |
"learning_rate": 4.950495049504951e-05,
|
| 149 |
-
"loss": 0.
|
| 150 |
"step": 220
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 1.14,
|
|
|
|
| 154 |
"learning_rate": 4.9229922992299234e-05,
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 230
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 1.19,
|
|
|
|
| 160 |
"learning_rate": 4.895489548954896e-05,
|
| 161 |
-
"loss": 0.
|
| 162 |
"step": 240
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 1.24,
|
|
|
|
| 166 |
"learning_rate": 4.867986798679868e-05,
|
| 167 |
-
"loss": 0.
|
| 168 |
"step": 250
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 1.29,
|
|
|
|
| 172 |
"learning_rate": 4.8404840484048406e-05,
|
| 173 |
-
"loss": 0.
|
| 174 |
"step": 260
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 1.34,
|
|
|
|
| 178 |
"learning_rate": 4.812981298129813e-05,
|
| 179 |
-
"loss": 0.
|
| 180 |
"step": 270
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 1.39,
|
|
|
|
| 184 |
"learning_rate": 4.785478547854786e-05,
|
| 185 |
-
"loss": 0.
|
| 186 |
"step": 280
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 1.44,
|
|
|
|
| 190 |
"learning_rate": 4.7579757975797585e-05,
|
| 191 |
-
"loss": 0.
|
| 192 |
"step": 290
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 1.49,
|
|
|
|
| 196 |
"learning_rate": 4.730473047304731e-05,
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 300
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 1.53,
|
|
|
|
| 202 |
"learning_rate": 4.702970297029703e-05,
|
| 203 |
-
"loss": 0.
|
| 204 |
"step": 310
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 1.58,
|
|
|
|
| 208 |
"learning_rate": 4.675467546754676e-05,
|
| 209 |
-
"loss": 0.
|
| 210 |
"step": 320
|
| 211 |
},
|
| 212 |
{
|
| 213 |
"epoch": 1.63,
|
|
|
|
| 214 |
"learning_rate": 4.647964796479648e-05,
|
| 215 |
-
"loss": 0.
|
| 216 |
"step": 330
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 1.68,
|
|
|
|
| 220 |
"learning_rate": 4.62046204620462e-05,
|
| 221 |
-
"loss": 0.
|
| 222 |
"step": 340
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 1.73,
|
|
|
|
| 226 |
"learning_rate": 4.592959295929593e-05,
|
| 227 |
-
"loss": 0.
|
| 228 |
"step": 350
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 1.78,
|
|
|
|
| 232 |
"learning_rate": 4.5654565456545655e-05,
|
| 233 |
-
"loss": 0.
|
| 234 |
"step": 360
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 1.83,
|
|
|
|
| 238 |
"learning_rate": 4.537953795379538e-05,
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 370
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 1.88,
|
|
|
|
| 244 |
"learning_rate": 4.510451045104511e-05,
|
| 245 |
-
"loss": 0.
|
| 246 |
"step": 380
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 1.93,
|
|
|
|
| 250 |
"learning_rate": 4.4829482948294834e-05,
|
| 251 |
-
"loss": 0.
|
| 252 |
"step": 390
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 1.98,
|
|
|
|
| 256 |
"learning_rate": 4.455445544554456e-05,
|
| 257 |
-
"loss": 0.
|
| 258 |
"step": 400
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 2.0,
|
| 262 |
-
"eval_accuracy": 0.
|
| 263 |
-
"eval_loss": 0.
|
| 264 |
-
"eval_runtime": 15.
|
| 265 |
-
"eval_samples_per_second":
|
| 266 |
-
"eval_steps_per_second": 5.
|
| 267 |
"step": 404
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 2.03,
|
|
|
|
| 271 |
"learning_rate": 4.427942794279428e-05,
|
| 272 |
-
"loss": 0.
|
| 273 |
"step": 410
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 2.08,
|
|
|
|
| 277 |
"learning_rate": 4.4004400440044006e-05,
|
| 278 |
-
"loss": 0.
|
| 279 |
"step": 420
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 2.13,
|
|
|
|
| 283 |
"learning_rate": 4.372937293729373e-05,
|
| 284 |
-
"loss": 0.
|
| 285 |
"step": 430
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 2.18,
|
|
|
|
| 289 |
"learning_rate": 4.345434543454346e-05,
|
| 290 |
-
"loss": 0.
|
| 291 |
"step": 440
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 2.23,
|
|
|
|
| 295 |
"learning_rate": 4.3179317931793185e-05,
|
| 296 |
-
"loss": 0.
|
| 297 |
"step": 450
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 2.28,
|
|
|
|
| 301 |
"learning_rate": 4.2904290429042904e-05,
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 460
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 2.33,
|
|
|
|
| 307 |
"learning_rate": 4.262926292629263e-05,
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 470
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 2.38,
|
|
|
|
| 313 |
"learning_rate": 4.2354235423542356e-05,
|
| 314 |
-
"loss": 0.
|
| 315 |
"step": 480
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 2.43,
|
|
|
|
| 319 |
"learning_rate": 4.207920792079208e-05,
|
| 320 |
-
"loss": 0.
|
| 321 |
"step": 490
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 2.48,
|
|
|
|
| 325 |
"learning_rate": 4.18041804180418e-05,
|
| 326 |
-
"loss": 0.
|
| 327 |
"step": 500
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 2.52,
|
|
|
|
| 331 |
"learning_rate": 4.152915291529153e-05,
|
| 332 |
-
"loss": 0.
|
| 333 |
"step": 510
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 2.57,
|
|
|
|
| 337 |
"learning_rate": 4.1254125412541255e-05,
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 520
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 2.62,
|
|
|
|
| 343 |
"learning_rate": 4.097909790979098e-05,
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 530
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 2.67,
|
|
|
|
| 349 |
"learning_rate": 4.070407040704071e-05,
|
| 350 |
-
"loss": 0.
|
| 351 |
"step": 540
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 2.72,
|
|
|
|
| 355 |
"learning_rate": 4.042904290429043e-05,
|
| 356 |
-
"loss": 0.
|
| 357 |
"step": 550
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 2.77,
|
|
|
|
| 361 |
"learning_rate": 4.015401540154016e-05,
|
| 362 |
-
"loss": 0.
|
| 363 |
"step": 560
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 2.82,
|
|
|
|
| 367 |
"learning_rate": 3.987898789878988e-05,
|
| 368 |
-
"loss": 0.
|
| 369 |
"step": 570
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 2.87,
|
|
|
|
| 373 |
"learning_rate": 3.9603960396039605e-05,
|
| 374 |
-
"loss": 0.
|
| 375 |
"step": 580
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 2.92,
|
|
|
|
| 379 |
"learning_rate": 3.932893289328933e-05,
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 590
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 2.97,
|
|
|
|
| 385 |
"learning_rate": 3.905390539053906e-05,
|
| 386 |
-
"loss": 0.
|
| 387 |
"step": 600
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 3.0,
|
| 391 |
-
"eval_accuracy": 0.
|
| 392 |
-
"eval_loss": 0.
|
| 393 |
-
"eval_runtime":
|
| 394 |
-
"eval_samples_per_second":
|
| 395 |
-
"eval_steps_per_second": 5.
|
| 396 |
"step": 606
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 3.02,
|
|
|
|
| 400 |
"learning_rate": 3.877887788778878e-05,
|
| 401 |
-
"loss": 0.
|
| 402 |
"step": 610
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 3.07,
|
|
|
|
| 406 |
"learning_rate": 3.8503850385038503e-05,
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 620
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 3.12,
|
|
|
|
| 412 |
"learning_rate": 3.822882288228823e-05,
|
| 413 |
-
"loss": 0.
|
| 414 |
"step": 630
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 3.17,
|
|
|
|
| 418 |
"learning_rate": 3.7953795379537956e-05,
|
| 419 |
-
"loss": 0.
|
| 420 |
"step": 640
|
| 421 |
},
|
| 422 |
{
|
| 423 |
"epoch": 3.22,
|
|
|
|
| 424 |
"learning_rate": 3.767876787678768e-05,
|
| 425 |
-
"loss": 0.
|
| 426 |
"step": 650
|
| 427 |
},
|
| 428 |
{
|
| 429 |
"epoch": 3.27,
|
|
|
|
| 430 |
"learning_rate": 3.74037403740374e-05,
|
| 431 |
-
"loss": 0.
|
| 432 |
"step": 660
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 3.32,
|
|
|
|
| 436 |
"learning_rate": 3.712871287128713e-05,
|
| 437 |
-
"loss": 0.
|
| 438 |
"step": 670
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 3.37,
|
|
|
|
| 442 |
"learning_rate": 3.6853685368536854e-05,
|
| 443 |
-
"loss": 0.
|
| 444 |
"step": 680
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 3.42,
|
|
|
|
| 448 |
"learning_rate": 3.657865786578658e-05,
|
| 449 |
-
"loss": 0.
|
| 450 |
"step": 690
|
| 451 |
},
|
| 452 |
{
|
| 453 |
"epoch": 3.47,
|
|
|
|
| 454 |
"learning_rate": 3.6303630363036307e-05,
|
| 455 |
-
"loss": 0.
|
| 456 |
"step": 700
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 3.51,
|
|
|
|
| 460 |
"learning_rate": 3.602860286028603e-05,
|
| 461 |
-
"loss": 0.
|
| 462 |
"step": 710
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 3.56,
|
|
|
|
| 466 |
"learning_rate": 3.575357535753576e-05,
|
| 467 |
-
"loss": 0.
|
| 468 |
"step": 720
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 3.61,
|
|
|
|
| 472 |
"learning_rate": 3.5478547854785485e-05,
|
| 473 |
-
"loss": 0.
|
| 474 |
"step": 730
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 3.66,
|
|
|
|
| 478 |
"learning_rate": 3.5203520352035205e-05,
|
| 479 |
-
"loss": 0.
|
| 480 |
"step": 740
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 3.71,
|
|
|
|
| 484 |
"learning_rate": 3.492849284928493e-05,
|
| 485 |
-
"loss": 0.
|
| 486 |
"step": 750
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 3.76,
|
|
|
|
| 490 |
"learning_rate": 3.465346534653465e-05,
|
| 491 |
-
"loss": 0.
|
| 492 |
"step": 760
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 3.81,
|
|
|
|
| 496 |
"learning_rate": 3.4378437843784377e-05,
|
| 497 |
-
"loss": 0.
|
| 498 |
"step": 770
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 3.86,
|
|
|
|
| 502 |
"learning_rate": 3.41034103410341e-05,
|
| 503 |
-
"loss": 0.
|
| 504 |
"step": 780
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 3.91,
|
|
|
|
| 508 |
"learning_rate": 3.382838283828383e-05,
|
| 509 |
-
"loss": 0.
|
| 510 |
"step": 790
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 3.96,
|
|
|
|
| 514 |
"learning_rate": 3.3553355335533555e-05,
|
| 515 |
-
"loss": 0.
|
| 516 |
"step": 800
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 4.0,
|
| 520 |
-
"eval_accuracy": 0.
|
| 521 |
-
"eval_loss": 0.
|
| 522 |
-
"eval_runtime": 15.
|
| 523 |
-
"eval_samples_per_second":
|
| 524 |
-
"eval_steps_per_second": 5.
|
| 525 |
"step": 808
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 4.01,
|
|
|
|
| 529 |
"learning_rate": 3.327832783278328e-05,
|
| 530 |
-
"loss": 0.
|
| 531 |
"step": 810
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 4.06,
|
|
|
|
| 535 |
"learning_rate": 3.300330033003301e-05,
|
| 536 |
-
"loss": 0.
|
| 537 |
"step": 820
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 4.11,
|
|
|
|
| 541 |
"learning_rate": 3.272827282728273e-05,
|
| 542 |
-
"loss": 0.
|
| 543 |
"step": 830
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 4.16,
|
|
|
|
| 547 |
"learning_rate": 3.2453245324532453e-05,
|
| 548 |
-
"loss": 0.
|
| 549 |
"step": 840
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 4.21,
|
|
|
|
| 553 |
"learning_rate": 3.217821782178218e-05,
|
| 554 |
-
"loss": 0.
|
| 555 |
"step": 850
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 4.26,
|
|
|
|
| 559 |
"learning_rate": 3.1903190319031906e-05,
|
| 560 |
-
"loss": 0.
|
| 561 |
"step": 860
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 4.31,
|
|
|
|
| 565 |
"learning_rate": 3.162816281628163e-05,
|
| 566 |
-
"loss": 0.
|
| 567 |
"step": 870
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 4.36,
|
|
|
|
| 571 |
"learning_rate": 3.135313531353136e-05,
|
| 572 |
-
"loss": 0.
|
| 573 |
"step": 880
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 4.41,
|
|
|
|
| 577 |
"learning_rate": 3.1078107810781085e-05,
|
| 578 |
-
"loss": 0.
|
| 579 |
"step": 890
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 4.46,
|
|
|
|
| 583 |
"learning_rate": 3.0803080308030804e-05,
|
| 584 |
-
"loss": 0.
|
| 585 |
"step": 900
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 4.5,
|
|
|
|
| 589 |
"learning_rate": 3.052805280528053e-05,
|
| 590 |
-
"loss": 0.
|
| 591 |
"step": 910
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 4.55,
|
|
|
|
| 595 |
"learning_rate": 3.0253025302530253e-05,
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 920
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 4.6,
|
|
|
|
| 601 |
"learning_rate": 2.9977997799779976e-05,
|
| 602 |
-
"loss": 0.
|
| 603 |
"step": 930
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 4.65,
|
|
|
|
| 607 |
"learning_rate": 2.9702970297029702e-05,
|
| 608 |
-
"loss": 0.
|
| 609 |
"step": 940
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 4.7,
|
|
|
|
| 613 |
"learning_rate": 2.942794279427943e-05,
|
| 614 |
-
"loss": 0.
|
| 615 |
"step": 950
|
| 616 |
},
|
| 617 |
{
|
| 618 |
"epoch": 4.75,
|
|
|
|
| 619 |
"learning_rate": 2.9152915291529155e-05,
|
| 620 |
-
"loss": 0.
|
| 621 |
"step": 960
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 4.8,
|
|
|
|
| 625 |
"learning_rate": 2.8877887788778878e-05,
|
| 626 |
-
"loss": 0.
|
| 627 |
"step": 970
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 4.85,
|
|
|
|
| 631 |
"learning_rate": 2.8602860286028604e-05,
|
| 632 |
-
"loss": 0.
|
| 633 |
"step": 980
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 4.9,
|
|
|
|
| 637 |
"learning_rate": 2.832783278327833e-05,
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 990
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 4.95,
|
|
|
|
| 643 |
"learning_rate": 2.8052805280528056e-05,
|
| 644 |
-
"loss": 0.
|
| 645 |
"step": 1000
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 5.0,
|
|
|
|
| 649 |
"learning_rate": 2.777777777777778e-05,
|
| 650 |
-
"loss": 0.
|
| 651 |
"step": 1010
|
| 652 |
},
|
| 653 |
{
|
| 654 |
"epoch": 5.0,
|
| 655 |
-
"eval_accuracy": 0.
|
| 656 |
-
"eval_loss": 0.
|
| 657 |
-
"eval_runtime":
|
| 658 |
-
"eval_samples_per_second":
|
| 659 |
-
"eval_steps_per_second": 5.
|
| 660 |
"step": 1010
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 5.05,
|
|
|
|
| 664 |
"learning_rate": 2.7502750275027505e-05,
|
| 665 |
-
"loss": 0.
|
| 666 |
"step": 1020
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 5.1,
|
|
|
|
| 670 |
"learning_rate": 2.722772277227723e-05,
|
| 671 |
-
"loss": 0.
|
| 672 |
"step": 1030
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 5.15,
|
|
|
|
| 676 |
"learning_rate": 2.6952695269526958e-05,
|
| 677 |
-
"loss": 0.
|
| 678 |
"step": 1040
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 5.2,
|
|
|
|
| 682 |
"learning_rate": 2.667766776677668e-05,
|
| 683 |
-
"loss": 0.
|
| 684 |
"step": 1050
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 5.25,
|
|
|
|
| 688 |
"learning_rate": 2.64026402640264e-05,
|
| 689 |
-
"loss": 0.
|
| 690 |
"step": 1060
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 5.3,
|
|
|
|
| 694 |
"learning_rate": 2.6127612761276126e-05,
|
| 695 |
-
"loss": 0.
|
| 696 |
"step": 1070
|
| 697 |
},
|
| 698 |
{
|
| 699 |
"epoch": 5.35,
|
|
|
|
| 700 |
"learning_rate": 2.5852585258525853e-05,
|
| 701 |
-
"loss": 0.
|
| 702 |
"step": 1080
|
| 703 |
},
|
| 704 |
{
|
| 705 |
"epoch": 5.4,
|
|
|
|
| 706 |
"learning_rate": 2.557755775577558e-05,
|
| 707 |
-
"loss": 0.
|
| 708 |
"step": 1090
|
| 709 |
},
|
| 710 |
{
|
| 711 |
"epoch": 5.45,
|
|
|
|
| 712 |
"learning_rate": 2.53025302530253e-05,
|
| 713 |
-
"loss": 0.
|
| 714 |
"step": 1100
|
| 715 |
},
|
| 716 |
{
|
| 717 |
"epoch": 5.5,
|
|
|
|
| 718 |
"learning_rate": 2.5027502750275028e-05,
|
| 719 |
-
"loss": 0.
|
| 720 |
"step": 1110
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 5.54,
|
|
|
|
| 724 |
"learning_rate": 2.4752475247524754e-05,
|
| 725 |
-
"loss": 0.
|
| 726 |
"step": 1120
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 5.59,
|
|
|
|
| 730 |
"learning_rate": 2.447744774477448e-05,
|
| 731 |
-
"loss": 0.
|
| 732 |
"step": 1130
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 5.64,
|
|
|
|
| 736 |
"learning_rate": 2.4202420242024203e-05,
|
| 737 |
-
"loss": 0.
|
| 738 |
"step": 1140
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"epoch": 5.69,
|
|
|
|
| 742 |
"learning_rate": 2.392739273927393e-05,
|
| 743 |
-
"loss": 0.
|
| 744 |
"step": 1150
|
| 745 |
},
|
| 746 |
{
|
| 747 |
"epoch": 5.74,
|
|
|
|
| 748 |
"learning_rate": 2.3652365236523656e-05,
|
| 749 |
-
"loss": 0.
|
| 750 |
"step": 1160
|
| 751 |
},
|
| 752 |
{
|
| 753 |
"epoch": 5.79,
|
|
|
|
| 754 |
"learning_rate": 2.337733773377338e-05,
|
| 755 |
-
"loss": 0.
|
| 756 |
"step": 1170
|
| 757 |
},
|
| 758 |
{
|
| 759 |
"epoch": 5.84,
|
|
|
|
| 760 |
"learning_rate": 2.31023102310231e-05,
|
| 761 |
-
"loss": 0.
|
| 762 |
"step": 1180
|
| 763 |
},
|
| 764 |
{
|
| 765 |
"epoch": 5.89,
|
|
|
|
| 766 |
"learning_rate": 2.2827282728272828e-05,
|
| 767 |
-
"loss": 0.
|
| 768 |
"step": 1190
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 5.94,
|
|
|
|
| 772 |
"learning_rate": 2.2552255225522554e-05,
|
| 773 |
-
"loss": 0.
|
| 774 |
"step": 1200
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 5.99,
|
|
|
|
| 778 |
"learning_rate": 2.227722772277228e-05,
|
| 779 |
-
"loss": 0.
|
| 780 |
"step": 1210
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 6.0,
|
| 784 |
-
"eval_accuracy": 0.
|
| 785 |
-
"eval_loss": 0.
|
| 786 |
-
"eval_runtime": 15.
|
| 787 |
-
"eval_samples_per_second":
|
| 788 |
-
"eval_steps_per_second": 5.
|
| 789 |
"step": 1212
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 6.04,
|
|
|
|
| 793 |
"learning_rate": 2.2002200220022003e-05,
|
| 794 |
-
"loss": 0.
|
| 795 |
"step": 1220
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 6.09,
|
|
|
|
| 799 |
"learning_rate": 2.172717271727173e-05,
|
| 800 |
-
"loss": 0.
|
| 801 |
"step": 1230
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 6.14,
|
|
|
|
| 805 |
"learning_rate": 2.1452145214521452e-05,
|
| 806 |
-
"loss": 0.
|
| 807 |
"step": 1240
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 6.19,
|
|
|
|
| 811 |
"learning_rate": 2.1177117711771178e-05,
|
| 812 |
-
"loss": 0.
|
| 813 |
"step": 1250
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 6.24,
|
|
|
|
| 817 |
"learning_rate": 2.09020902090209e-05,
|
| 818 |
-
"loss": 0.
|
| 819 |
"step": 1260
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 6.29,
|
|
|
|
| 823 |
"learning_rate": 2.0627062706270627e-05,
|
| 824 |
-
"loss": 0.
|
| 825 |
"step": 1270
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 6.34,
|
|
|
|
| 829 |
"learning_rate": 2.0352035203520354e-05,
|
| 830 |
-
"loss": 0.
|
| 831 |
"step": 1280
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 6.39,
|
|
|
|
| 835 |
"learning_rate": 2.007700770077008e-05,
|
| 836 |
-
"loss": 0.
|
| 837 |
"step": 1290
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 6.44,
|
|
|
|
| 841 |
"learning_rate": 1.9801980198019803e-05,
|
| 842 |
-
"loss": 0.
|
| 843 |
"step": 1300
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 6.49,
|
|
|
|
| 847 |
"learning_rate": 1.952695269526953e-05,
|
| 848 |
-
"loss": 0.
|
| 849 |
"step": 1310
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 6.53,
|
|
|
|
| 853 |
"learning_rate": 1.9251925192519252e-05,
|
| 854 |
-
"loss": 0.
|
| 855 |
"step": 1320
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 6.58,
|
|
|
|
| 859 |
"learning_rate": 1.8976897689768978e-05,
|
| 860 |
-
"loss": 0.
|
| 861 |
"step": 1330
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 6.63,
|
|
|
|
| 865 |
"learning_rate": 1.87018701870187e-05,
|
| 866 |
-
"loss": 0.
|
| 867 |
"step": 1340
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 6.68,
|
|
|
|
| 871 |
"learning_rate": 1.8426842684268427e-05,
|
| 872 |
-
"loss": 0.
|
| 873 |
"step": 1350
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 6.73,
|
|
|
|
| 877 |
"learning_rate": 1.8151815181518153e-05,
|
| 878 |
-
"loss": 0.
|
| 879 |
"step": 1360
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 6.78,
|
|
|
|
| 883 |
"learning_rate": 1.787678767876788e-05,
|
| 884 |
-
"loss": 0.
|
| 885 |
"step": 1370
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 6.83,
|
|
|
|
| 889 |
"learning_rate": 1.7601760176017602e-05,
|
| 890 |
-
"loss": 0.
|
| 891 |
"step": 1380
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 6.88,
|
|
|
|
| 895 |
"learning_rate": 1.7326732673267325e-05,
|
| 896 |
-
"loss": 0.
|
| 897 |
"step": 1390
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 6.93,
|
|
|
|
| 901 |
"learning_rate": 1.705170517051705e-05,
|
| 902 |
-
"loss": 0.
|
| 903 |
"step": 1400
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 6.98,
|
|
|
|
| 907 |
"learning_rate": 1.6776677667766778e-05,
|
| 908 |
-
"loss": 0.
|
| 909 |
"step": 1410
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 7.0,
|
| 913 |
-
"eval_accuracy": 0.
|
| 914 |
-
"eval_loss": 0.
|
| 915 |
-
"eval_runtime": 15.
|
| 916 |
-
"eval_samples_per_second":
|
| 917 |
-
"eval_steps_per_second": 5.
|
| 918 |
"step": 1414
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 7.03,
|
|
|
|
| 922 |
"learning_rate": 1.6501650165016504e-05,
|
| 923 |
-
"loss": 0.
|
| 924 |
"step": 1420
|
| 925 |
},
|
| 926 |
{
|
| 927 |
"epoch": 7.08,
|
|
|
|
| 928 |
"learning_rate": 1.6226622662266227e-05,
|
| 929 |
-
"loss": 0.
|
| 930 |
"step": 1430
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 7.13,
|
|
|
|
| 934 |
"learning_rate": 1.5951595159515953e-05,
|
| 935 |
-
"loss": 0.
|
| 936 |
"step": 1440
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"epoch": 7.18,
|
|
|
|
| 940 |
"learning_rate": 1.567656765676568e-05,
|
| 941 |
-
"loss": 0.
|
| 942 |
"step": 1450
|
| 943 |
},
|
| 944 |
{
|
| 945 |
"epoch": 7.23,
|
|
|
|
| 946 |
"learning_rate": 1.5401540154015402e-05,
|
| 947 |
-
"loss": 0.
|
| 948 |
"step": 1460
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 7.28,
|
|
|
|
| 952 |
"learning_rate": 1.5126512651265127e-05,
|
| 953 |
-
"loss": 0.
|
| 954 |
"step": 1470
|
| 955 |
},
|
| 956 |
{
|
| 957 |
"epoch": 7.33,
|
|
|
|
| 958 |
"learning_rate": 1.4851485148514851e-05,
|
| 959 |
-
"loss": 0.
|
| 960 |
"step": 1480
|
| 961 |
},
|
| 962 |
{
|
| 963 |
"epoch": 7.38,
|
|
|
|
| 964 |
"learning_rate": 1.4576457645764577e-05,
|
| 965 |
-
"loss": 0.
|
| 966 |
"step": 1490
|
| 967 |
},
|
| 968 |
{
|
| 969 |
"epoch": 7.43,
|
|
|
|
| 970 |
"learning_rate": 1.4301430143014302e-05,
|
| 971 |
-
"loss": 0.
|
| 972 |
"step": 1500
|
| 973 |
},
|
| 974 |
{
|
| 975 |
"epoch": 7.48,
|
|
|
|
| 976 |
"learning_rate": 1.4026402640264028e-05,
|
| 977 |
-
"loss": 0.
|
| 978 |
"step": 1510
|
| 979 |
},
|
| 980 |
{
|
| 981 |
"epoch": 7.52,
|
|
|
|
| 982 |
"learning_rate": 1.3751375137513753e-05,
|
| 983 |
-
"loss": 0.
|
| 984 |
"step": 1520
|
| 985 |
},
|
| 986 |
{
|
| 987 |
"epoch": 7.57,
|
|
|
|
| 988 |
"learning_rate": 1.3476347634763479e-05,
|
| 989 |
-
"loss": 0.
|
| 990 |
"step": 1530
|
| 991 |
},
|
| 992 |
{
|
| 993 |
"epoch": 7.62,
|
|
|
|
| 994 |
"learning_rate": 1.32013201320132e-05,
|
| 995 |
-
"loss": 0.
|
| 996 |
"step": 1540
|
| 997 |
},
|
| 998 |
{
|
| 999 |
"epoch": 7.67,
|
|
|
|
| 1000 |
"learning_rate": 1.2926292629262926e-05,
|
| 1001 |
-
"loss": 0.
|
| 1002 |
"step": 1550
|
| 1003 |
},
|
| 1004 |
{
|
| 1005 |
"epoch": 7.72,
|
|
|
|
| 1006 |
"learning_rate": 1.265126512651265e-05,
|
| 1007 |
-
"loss": 0.
|
| 1008 |
"step": 1560
|
| 1009 |
},
|
| 1010 |
{
|
| 1011 |
"epoch": 7.77,
|
|
|
|
| 1012 |
"learning_rate": 1.2376237623762377e-05,
|
| 1013 |
-
"loss": 0.
|
| 1014 |
"step": 1570
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
"epoch": 7.82,
|
|
|
|
| 1018 |
"learning_rate": 1.2101210121012102e-05,
|
| 1019 |
-
"loss": 0.
|
| 1020 |
"step": 1580
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
"epoch": 7.87,
|
|
|
|
| 1024 |
"learning_rate": 1.1826182618261828e-05,
|
| 1025 |
-
"loss": 0.
|
| 1026 |
"step": 1590
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
"epoch": 7.92,
|
|
|
|
| 1030 |
"learning_rate": 1.155115511551155e-05,
|
| 1031 |
-
"loss": 0.
|
| 1032 |
"step": 1600
|
| 1033 |
},
|
| 1034 |
{
|
| 1035 |
"epoch": 7.97,
|
|
|
|
| 1036 |
"learning_rate": 1.1276127612761277e-05,
|
| 1037 |
-
"loss": 0.
|
| 1038 |
"step": 1610
|
| 1039 |
},
|
| 1040 |
{
|
| 1041 |
"epoch": 8.0,
|
| 1042 |
-
"eval_accuracy": 0.
|
| 1043 |
-
"eval_loss": 0.
|
| 1044 |
-
"eval_runtime": 15.
|
| 1045 |
-
"eval_samples_per_second":
|
| 1046 |
-
"eval_steps_per_second": 5.
|
| 1047 |
"step": 1616
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 8.02,
|
|
|
|
| 1051 |
"learning_rate": 1.1001100110011001e-05,
|
| 1052 |
-
"loss": 0.
|
| 1053 |
"step": 1620
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"epoch": 8.07,
|
|
|
|
| 1057 |
"learning_rate": 1.0726072607260726e-05,
|
| 1058 |
-
"loss": 0.
|
| 1059 |
"step": 1630
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
"epoch": 8.12,
|
|
|
|
| 1063 |
"learning_rate": 1.045104510451045e-05,
|
| 1064 |
-
"loss": 0.
|
| 1065 |
"step": 1640
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 8.17,
|
|
|
|
| 1069 |
"learning_rate": 1.0176017601760177e-05,
|
| 1070 |
-
"loss": 0.
|
| 1071 |
"step": 1650
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 8.22,
|
|
|
|
| 1075 |
"learning_rate": 9.900990099009901e-06,
|
| 1076 |
-
"loss": 0.
|
| 1077 |
"step": 1660
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
"epoch": 8.27,
|
|
|
|
| 1081 |
"learning_rate": 9.625962596259626e-06,
|
| 1082 |
-
"loss": 0.
|
| 1083 |
"step": 1670
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 8.32,
|
|
|
|
| 1087 |
"learning_rate": 9.35093509350935e-06,
|
| 1088 |
-
"loss": 0.
|
| 1089 |
"step": 1680
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
"epoch": 8.37,
|
|
|
|
| 1093 |
"learning_rate": 9.075907590759077e-06,
|
| 1094 |
-
"loss": 0.
|
| 1095 |
"step": 1690
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
"epoch": 8.42,
|
|
|
|
| 1099 |
"learning_rate": 8.800880088008801e-06,
|
| 1100 |
-
"loss": 0.
|
| 1101 |
"step": 1700
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 8.47,
|
|
|
|
| 1105 |
"learning_rate": 8.525852585258526e-06,
|
| 1106 |
-
"loss": 0.
|
| 1107 |
"step": 1710
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
"epoch": 8.51,
|
|
|
|
| 1111 |
"learning_rate": 8.250825082508252e-06,
|
| 1112 |
-
"loss": 0.
|
| 1113 |
"step": 1720
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 8.56,
|
|
|
|
| 1117 |
"learning_rate": 7.975797579757976e-06,
|
| 1118 |
-
"loss": 0.
|
| 1119 |
"step": 1730
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 8.61,
|
|
|
|
| 1123 |
"learning_rate": 7.700770077007701e-06,
|
| 1124 |
-
"loss": 0.
|
| 1125 |
"step": 1740
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 8.66,
|
|
|
|
| 1129 |
"learning_rate": 7.4257425742574256e-06,
|
| 1130 |
-
"loss": 0.
|
| 1131 |
"step": 1750
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 8.71,
|
|
|
|
| 1135 |
"learning_rate": 7.150715071507151e-06,
|
| 1136 |
-
"loss": 0.
|
| 1137 |
"step": 1760
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"epoch": 8.76,
|
|
|
|
| 1141 |
"learning_rate": 6.875687568756876e-06,
|
| 1142 |
-
"loss": 0.
|
| 1143 |
"step": 1770
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 8.81,
|
|
|
|
| 1147 |
"learning_rate": 6.6006600660066e-06,
|
| 1148 |
-
"loss": 0.
|
| 1149 |
"step": 1780
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"epoch": 8.86,
|
|
|
|
| 1153 |
"learning_rate": 6.325632563256325e-06,
|
| 1154 |
-
"loss": 0.
|
| 1155 |
"step": 1790
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 8.91,
|
|
|
|
| 1159 |
"learning_rate": 6.050605060506051e-06,
|
| 1160 |
-
"loss": 0.
|
| 1161 |
"step": 1800
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
"epoch": 8.96,
|
|
|
|
| 1165 |
"learning_rate": 5.775577557755775e-06,
|
| 1166 |
-
"loss": 0.
|
| 1167 |
"step": 1810
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 9.0,
|
| 1171 |
-
"eval_accuracy": 0.
|
| 1172 |
-
"eval_loss": 0.
|
| 1173 |
-
"eval_runtime":
|
| 1174 |
-
"eval_samples_per_second":
|
| 1175 |
-
"eval_steps_per_second": 5.
|
| 1176 |
"step": 1818
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 9.01,
|
|
|
|
| 1180 |
"learning_rate": 5.500550055005501e-06,
|
| 1181 |
-
"loss": 0.
|
| 1182 |
"step": 1820
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
"epoch": 9.06,
|
|
|
|
| 1186 |
"learning_rate": 5.225522552255225e-06,
|
| 1187 |
-
"loss": 0.
|
| 1188 |
"step": 1830
|
| 1189 |
},
|
| 1190 |
{
|
| 1191 |
"epoch": 9.11,
|
|
|
|
| 1192 |
"learning_rate": 4.950495049504951e-06,
|
| 1193 |
-
"loss": 0.
|
| 1194 |
"step": 1840
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
"epoch": 9.16,
|
|
|
|
| 1198 |
"learning_rate": 4.675467546754675e-06,
|
| 1199 |
-
"loss": 0.
|
| 1200 |
"step": 1850
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 9.21,
|
|
|
|
| 1204 |
"learning_rate": 4.400440044004401e-06,
|
| 1205 |
-
"loss": 0.
|
| 1206 |
"step": 1860
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 9.26,
|
|
|
|
| 1210 |
"learning_rate": 4.125412541254126e-06,
|
| 1211 |
-
"loss": 0.
|
| 1212 |
"step": 1870
|
| 1213 |
},
|
| 1214 |
{
|
| 1215 |
"epoch": 9.31,
|
|
|
|
| 1216 |
"learning_rate": 3.8503850385038505e-06,
|
| 1217 |
-
"loss": 0.
|
| 1218 |
"step": 1880
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 9.36,
|
|
|
|
| 1222 |
"learning_rate": 3.5753575357535755e-06,
|
| 1223 |
-
"loss": 0.
|
| 1224 |
"step": 1890
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 9.41,
|
|
|
|
| 1228 |
"learning_rate": 3.3003300330033e-06,
|
| 1229 |
-
"loss": 0.
|
| 1230 |
"step": 1900
|
| 1231 |
},
|
| 1232 |
{
|
| 1233 |
"epoch": 9.46,
|
|
|
|
| 1234 |
"learning_rate": 3.0253025302530254e-06,
|
| 1235 |
-
"loss": 0.
|
| 1236 |
"step": 1910
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
"epoch": 9.5,
|
|
|
|
| 1240 |
"learning_rate": 2.7502750275027504e-06,
|
| 1241 |
-
"loss": 0.
|
| 1242 |
"step": 1920
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
"epoch": 9.55,
|
|
|
|
| 1246 |
"learning_rate": 2.4752475247524753e-06,
|
| 1247 |
-
"loss": 0.
|
| 1248 |
"step": 1930
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
"epoch": 9.6,
|
|
|
|
| 1252 |
"learning_rate": 2.2002200220022003e-06,
|
| 1253 |
-
"loss": 0.
|
| 1254 |
"step": 1940
|
| 1255 |
},
|
| 1256 |
{
|
| 1257 |
"epoch": 9.65,
|
|
|
|
| 1258 |
"learning_rate": 1.9251925192519253e-06,
|
| 1259 |
-
"loss": 0.
|
| 1260 |
"step": 1950
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 9.7,
|
|
|
|
| 1264 |
"learning_rate": 1.65016501650165e-06,
|
| 1265 |
-
"loss": 0.
|
| 1266 |
"step": 1960
|
| 1267 |
},
|
| 1268 |
{
|
| 1269 |
"epoch": 9.75,
|
|
|
|
| 1270 |
"learning_rate": 1.3751375137513752e-06,
|
| 1271 |
-
"loss": 0.
|
| 1272 |
"step": 1970
|
| 1273 |
},
|
| 1274 |
{
|
| 1275 |
"epoch": 9.8,
|
|
|
|
| 1276 |
"learning_rate": 1.1001100110011001e-06,
|
| 1277 |
-
"loss": 0.
|
| 1278 |
"step": 1980
|
| 1279 |
},
|
| 1280 |
{
|
| 1281 |
"epoch": 9.85,
|
|
|
|
| 1282 |
"learning_rate": 8.25082508250825e-07,
|
| 1283 |
-
"loss": 0.
|
| 1284 |
"step": 1990
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
"epoch": 9.9,
|
|
|
|
| 1288 |
"learning_rate": 5.500550055005501e-07,
|
| 1289 |
-
"loss": 0.
|
| 1290 |
"step": 2000
|
| 1291 |
},
|
| 1292 |
{
|
| 1293 |
"epoch": 9.95,
|
|
|
|
| 1294 |
"learning_rate": 2.7502750275027504e-07,
|
| 1295 |
-
"loss": 0.
|
| 1296 |
"step": 2010
|
| 1297 |
},
|
| 1298 |
{
|
| 1299 |
"epoch": 10.0,
|
|
|
|
| 1300 |
"learning_rate": 0.0,
|
| 1301 |
-
"loss": 0.
|
| 1302 |
"step": 2020
|
| 1303 |
},
|
| 1304 |
{
|
| 1305 |
"epoch": 10.0,
|
| 1306 |
-
"eval_accuracy": 0.
|
| 1307 |
-
"eval_loss": 0.
|
| 1308 |
-
"eval_runtime": 15.
|
| 1309 |
-
"eval_samples_per_second":
|
| 1310 |
-
"eval_steps_per_second": 5.
|
| 1311 |
"step": 2020
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 10.0,
|
| 1315 |
"step": 2020,
|
| 1316 |
"total_flos": 2.0021605356722135e+19,
|
| 1317 |
-
"train_loss": 0.
|
| 1318 |
-
"train_runtime":
|
| 1319 |
-
"train_samples_per_second":
|
| 1320 |
-
"train_steps_per_second": 0.
|
| 1321 |
}
|
| 1322 |
],
|
| 1323 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8732149076976663,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-FER2013/checkpoint-2020",
|
| 4 |
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 2020,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 0.699901819229126,
|
| 14 |
"learning_rate": 2.4752475247524753e-06,
|
| 15 |
+
"loss": 0.7003,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 0.40010973811149597,
|
| 21 |
"learning_rate": 4.950495049504951e-06,
|
| 22 |
+
"loss": 0.6978,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 0.3860187530517578,
|
| 28 |
"learning_rate": 7.4257425742574256e-06,
|
| 29 |
"loss": 0.6891,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 0.38579830527305603,
|
| 35 |
"learning_rate": 9.900990099009901e-06,
|
| 36 |
+
"loss": 0.6837,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 0.5694485306739807,
|
| 42 |
"learning_rate": 1.2376237623762377e-05,
|
| 43 |
+
"loss": 0.6643,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 0.5950794816017151,
|
| 49 |
"learning_rate": 1.4851485148514851e-05,
|
| 50 |
+
"loss": 0.642,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.35,
|
| 55 |
+
"grad_norm": 0.7590372562408447,
|
| 56 |
"learning_rate": 1.7326732673267325e-05,
|
| 57 |
+
"loss": 0.6213,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.4,
|
| 62 |
+
"grad_norm": 0.7452055215835571,
|
| 63 |
"learning_rate": 1.9801980198019803e-05,
|
| 64 |
+
"loss": 0.6079,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.45,
|
| 69 |
+
"grad_norm": 1.1108556985855103,
|
| 70 |
"learning_rate": 2.227722772277228e-05,
|
| 71 |
+
"loss": 0.568,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.5,
|
| 76 |
+
"grad_norm": 2.0815961360931396,
|
| 77 |
"learning_rate": 2.4752475247524754e-05,
|
| 78 |
+
"loss": 0.5555,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.54,
|
| 83 |
+
"grad_norm": 2.206498146057129,
|
| 84 |
"learning_rate": 2.722772277227723e-05,
|
| 85 |
+
"loss": 0.5587,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.59,
|
| 90 |
+
"grad_norm": 0.8447802066802979,
|
| 91 |
"learning_rate": 2.9702970297029702e-05,
|
| 92 |
+
"loss": 0.5502,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.64,
|
| 97 |
+
"grad_norm": 0.9129859805107117,
|
| 98 |
"learning_rate": 3.217821782178218e-05,
|
| 99 |
+
"loss": 0.5442,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.69,
|
| 104 |
+
"grad_norm": 1.3158477544784546,
|
| 105 |
"learning_rate": 3.465346534653465e-05,
|
| 106 |
+
"loss": 0.509,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.74,
|
| 111 |
+
"grad_norm": 1.6786607503890991,
|
| 112 |
"learning_rate": 3.712871287128713e-05,
|
| 113 |
+
"loss": 0.5129,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.79,
|
| 118 |
+
"grad_norm": 1.0716958045959473,
|
| 119 |
"learning_rate": 3.9603960396039605e-05,
|
| 120 |
+
"loss": 0.5043,
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.84,
|
| 125 |
+
"grad_norm": 1.8416863679885864,
|
| 126 |
"learning_rate": 4.207920792079208e-05,
|
| 127 |
+
"loss": 0.4766,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.89,
|
| 132 |
+
"grad_norm": 2.109766721725464,
|
| 133 |
"learning_rate": 4.455445544554456e-05,
|
| 134 |
+
"loss": 0.4746,
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.94,
|
| 139 |
+
"grad_norm": 1.7481091022491455,
|
| 140 |
"learning_rate": 4.702970297029703e-05,
|
| 141 |
+
"loss": 0.5162,
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.99,
|
| 146 |
+
"grad_norm": 1.037062406539917,
|
| 147 |
"learning_rate": 4.950495049504951e-05,
|
| 148 |
+
"loss": 0.4811,
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.800417972831766,
|
| 154 |
+
"eval_loss": 0.43151769042015076,
|
| 155 |
+
"eval_runtime": 15.3075,
|
| 156 |
+
"eval_samples_per_second": 187.555,
|
| 157 |
+
"eval_steps_per_second": 5.879,
|
| 158 |
"step": 202
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 1.04,
|
| 162 |
+
"grad_norm": 1.0516308546066284,
|
| 163 |
"learning_rate": 4.977997799779978e-05,
|
| 164 |
+
"loss": 0.4625,
|
| 165 |
"step": 210
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 1.09,
|
| 169 |
+
"grad_norm": 1.0761890411376953,
|
| 170 |
"learning_rate": 4.950495049504951e-05,
|
| 171 |
+
"loss": 0.4659,
|
| 172 |
"step": 220
|
| 173 |
},
|
| 174 |
{
|
| 175 |
"epoch": 1.14,
|
| 176 |
+
"grad_norm": 1.9692820310592651,
|
| 177 |
"learning_rate": 4.9229922992299234e-05,
|
| 178 |
+
"loss": 0.4893,
|
| 179 |
"step": 230
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 1.19,
|
| 183 |
+
"grad_norm": 0.9031820893287659,
|
| 184 |
"learning_rate": 4.895489548954896e-05,
|
| 185 |
+
"loss": 0.4801,
|
| 186 |
"step": 240
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 1.24,
|
| 190 |
+
"grad_norm": 1.241443395614624,
|
| 191 |
"learning_rate": 4.867986798679868e-05,
|
| 192 |
+
"loss": 0.465,
|
| 193 |
"step": 250
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 1.29,
|
| 197 |
+
"grad_norm": 1.1679638624191284,
|
| 198 |
"learning_rate": 4.8404840484048406e-05,
|
| 199 |
+
"loss": 0.4396,
|
| 200 |
"step": 260
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 1.34,
|
| 204 |
+
"grad_norm": 1.4820034503936768,
|
| 205 |
"learning_rate": 4.812981298129813e-05,
|
| 206 |
+
"loss": 0.4573,
|
| 207 |
"step": 270
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 1.39,
|
| 211 |
+
"grad_norm": 1.0649698972702026,
|
| 212 |
"learning_rate": 4.785478547854786e-05,
|
| 213 |
+
"loss": 0.4616,
|
| 214 |
"step": 280
|
| 215 |
},
|
| 216 |
{
|
| 217 |
"epoch": 1.44,
|
| 218 |
+
"grad_norm": 1.2591346502304077,
|
| 219 |
"learning_rate": 4.7579757975797585e-05,
|
| 220 |
+
"loss": 0.4661,
|
| 221 |
"step": 290
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 1.49,
|
| 225 |
+
"grad_norm": 1.9309344291687012,
|
| 226 |
"learning_rate": 4.730473047304731e-05,
|
| 227 |
+
"loss": 0.4792,
|
| 228 |
"step": 300
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 1.53,
|
| 232 |
+
"grad_norm": 0.9727767109870911,
|
| 233 |
"learning_rate": 4.702970297029703e-05,
|
| 234 |
+
"loss": 0.471,
|
| 235 |
"step": 310
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 1.58,
|
| 239 |
+
"grad_norm": 1.0227768421173096,
|
| 240 |
"learning_rate": 4.675467546754676e-05,
|
| 241 |
+
"loss": 0.4779,
|
| 242 |
"step": 320
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 1.63,
|
| 246 |
+
"grad_norm": 1.7914155721664429,
|
| 247 |
"learning_rate": 4.647964796479648e-05,
|
| 248 |
+
"loss": 0.4552,
|
| 249 |
"step": 330
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 1.68,
|
| 253 |
+
"grad_norm": 1.1211057901382446,
|
| 254 |
"learning_rate": 4.62046204620462e-05,
|
| 255 |
+
"loss": 0.4542,
|
| 256 |
"step": 340
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 1.73,
|
| 260 |
+
"grad_norm": 0.8994653820991516,
|
| 261 |
"learning_rate": 4.592959295929593e-05,
|
| 262 |
+
"loss": 0.469,
|
| 263 |
"step": 350
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 1.78,
|
| 267 |
+
"grad_norm": 1.6254159212112427,
|
| 268 |
"learning_rate": 4.5654565456545655e-05,
|
| 269 |
+
"loss": 0.4209,
|
| 270 |
"step": 360
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 1.83,
|
| 274 |
+
"grad_norm": 1.175451397895813,
|
| 275 |
"learning_rate": 4.537953795379538e-05,
|
| 276 |
+
"loss": 0.4707,
|
| 277 |
"step": 370
|
| 278 |
},
|
| 279 |
{
|
| 280 |
"epoch": 1.88,
|
| 281 |
+
"grad_norm": 1.6570440530776978,
|
| 282 |
"learning_rate": 4.510451045104511e-05,
|
| 283 |
+
"loss": 0.4587,
|
| 284 |
"step": 380
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 1.93,
|
| 288 |
+
"grad_norm": 1.0916353464126587,
|
| 289 |
"learning_rate": 4.4829482948294834e-05,
|
| 290 |
+
"loss": 0.4507,
|
| 291 |
"step": 390
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 1.98,
|
| 295 |
+
"grad_norm": 1.0758109092712402,
|
| 296 |
"learning_rate": 4.455445544554456e-05,
|
| 297 |
+
"loss": 0.4287,
|
| 298 |
"step": 400
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 2.0,
|
| 302 |
+
"eval_accuracy": 0.8432601880877743,
|
| 303 |
+
"eval_loss": 0.357921838760376,
|
| 304 |
+
"eval_runtime": 15.3987,
|
| 305 |
+
"eval_samples_per_second": 186.444,
|
| 306 |
+
"eval_steps_per_second": 5.845,
|
| 307 |
"step": 404
|
| 308 |
},
|
| 309 |
{
|
| 310 |
"epoch": 2.03,
|
| 311 |
+
"grad_norm": 0.7765569686889648,
|
| 312 |
"learning_rate": 4.427942794279428e-05,
|
| 313 |
+
"loss": 0.4157,
|
| 314 |
"step": 410
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 2.08,
|
| 318 |
+
"grad_norm": 1.1473923921585083,
|
| 319 |
"learning_rate": 4.4004400440044006e-05,
|
| 320 |
+
"loss": 0.4227,
|
| 321 |
"step": 420
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 2.13,
|
| 325 |
+
"grad_norm": 7.452829837799072,
|
| 326 |
"learning_rate": 4.372937293729373e-05,
|
| 327 |
+
"loss": 0.4033,
|
| 328 |
"step": 430
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 2.18,
|
| 332 |
+
"grad_norm": 1.391101360321045,
|
| 333 |
"learning_rate": 4.345434543454346e-05,
|
| 334 |
+
"loss": 0.4563,
|
| 335 |
"step": 440
|
| 336 |
},
|
| 337 |
{
|
| 338 |
"epoch": 2.23,
|
| 339 |
+
"grad_norm": 1.0371557474136353,
|
| 340 |
"learning_rate": 4.3179317931793185e-05,
|
| 341 |
+
"loss": 0.4487,
|
| 342 |
"step": 450
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"epoch": 2.28,
|
| 346 |
+
"grad_norm": 0.998115062713623,
|
| 347 |
"learning_rate": 4.2904290429042904e-05,
|
| 348 |
+
"loss": 0.4178,
|
| 349 |
"step": 460
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 2.33,
|
| 353 |
+
"grad_norm": 1.1916583776474,
|
| 354 |
"learning_rate": 4.262926292629263e-05,
|
| 355 |
+
"loss": 0.4361,
|
| 356 |
"step": 470
|
| 357 |
},
|
| 358 |
{
|
| 359 |
"epoch": 2.38,
|
| 360 |
+
"grad_norm": 1.2483221292495728,
|
| 361 |
"learning_rate": 4.2354235423542356e-05,
|
| 362 |
+
"loss": 0.4317,
|
| 363 |
"step": 480
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 2.43,
|
| 367 |
+
"grad_norm": 1.2603436708450317,
|
| 368 |
"learning_rate": 4.207920792079208e-05,
|
| 369 |
+
"loss": 0.4252,
|
| 370 |
"step": 490
|
| 371 |
},
|
| 372 |
{
|
| 373 |
"epoch": 2.48,
|
| 374 |
+
"grad_norm": 1.614512324333191,
|
| 375 |
"learning_rate": 4.18041804180418e-05,
|
| 376 |
+
"loss": 0.4213,
|
| 377 |
"step": 500
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 2.52,
|
| 381 |
+
"grad_norm": 1.5845041275024414,
|
| 382 |
"learning_rate": 4.152915291529153e-05,
|
| 383 |
+
"loss": 0.4276,
|
| 384 |
"step": 510
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 2.57,
|
| 388 |
+
"grad_norm": 0.9629144072532654,
|
| 389 |
"learning_rate": 4.1254125412541255e-05,
|
| 390 |
+
"loss": 0.4168,
|
| 391 |
"step": 520
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"epoch": 2.62,
|
| 395 |
+
"grad_norm": 1.0476891994476318,
|
| 396 |
"learning_rate": 4.097909790979098e-05,
|
| 397 |
+
"loss": 0.4166,
|
| 398 |
"step": 530
|
| 399 |
},
|
| 400 |
{
|
| 401 |
"epoch": 2.67,
|
| 402 |
+
"grad_norm": 1.2000118494033813,
|
| 403 |
"learning_rate": 4.070407040704071e-05,
|
| 404 |
+
"loss": 0.4238,
|
| 405 |
"step": 540
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 2.72,
|
| 409 |
+
"grad_norm": 1.608628511428833,
|
| 410 |
"learning_rate": 4.042904290429043e-05,
|
| 411 |
+
"loss": 0.3974,
|
| 412 |
"step": 550
|
| 413 |
},
|
| 414 |
{
|
| 415 |
"epoch": 2.77,
|
| 416 |
+
"grad_norm": 2.0195207595825195,
|
| 417 |
"learning_rate": 4.015401540154016e-05,
|
| 418 |
+
"loss": 0.4087,
|
| 419 |
"step": 560
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 2.82,
|
| 423 |
+
"grad_norm": 1.2935571670532227,
|
| 424 |
"learning_rate": 3.987898789878988e-05,
|
| 425 |
+
"loss": 0.396,
|
| 426 |
"step": 570
|
| 427 |
},
|
| 428 |
{
|
| 429 |
"epoch": 2.87,
|
| 430 |
+
"grad_norm": 1.2056093215942383,
|
| 431 |
"learning_rate": 3.9603960396039605e-05,
|
| 432 |
+
"loss": 0.4191,
|
| 433 |
"step": 580
|
| 434 |
},
|
| 435 |
{
|
| 436 |
"epoch": 2.92,
|
| 437 |
+
"grad_norm": 0.9370687007904053,
|
| 438 |
"learning_rate": 3.932893289328933e-05,
|
| 439 |
+
"loss": 0.4323,
|
| 440 |
"step": 590
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"epoch": 2.97,
|
| 444 |
+
"grad_norm": 0.9331934452056885,
|
| 445 |
"learning_rate": 3.905390539053906e-05,
|
| 446 |
+
"loss": 0.4184,
|
| 447 |
"step": 600
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 3.0,
|
| 451 |
+
"eval_accuracy": 0.8467432950191571,
|
| 452 |
+
"eval_loss": 0.35166114568710327,
|
| 453 |
+
"eval_runtime": 15.3286,
|
| 454 |
+
"eval_samples_per_second": 187.297,
|
| 455 |
+
"eval_steps_per_second": 5.871,
|
| 456 |
"step": 606
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 3.02,
|
| 460 |
+
"grad_norm": 1.35804283618927,
|
| 461 |
"learning_rate": 3.877887788778878e-05,
|
| 462 |
+
"loss": 0.4034,
|
| 463 |
"step": 610
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"epoch": 3.07,
|
| 467 |
+
"grad_norm": 1.5728434324264526,
|
| 468 |
"learning_rate": 3.8503850385038503e-05,
|
| 469 |
+
"loss": 0.3917,
|
| 470 |
"step": 620
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 3.12,
|
| 474 |
+
"grad_norm": 1.0493104457855225,
|
| 475 |
"learning_rate": 3.822882288228823e-05,
|
| 476 |
+
"loss": 0.416,
|
| 477 |
"step": 630
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 3.17,
|
| 481 |
+
"grad_norm": 1.2043938636779785,
|
| 482 |
"learning_rate": 3.7953795379537956e-05,
|
| 483 |
+
"loss": 0.3913,
|
| 484 |
"step": 640
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 3.22,
|
| 488 |
+
"grad_norm": 1.6263302564620972,
|
| 489 |
"learning_rate": 3.767876787678768e-05,
|
| 490 |
+
"loss": 0.3815,
|
| 491 |
"step": 650
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 3.27,
|
| 495 |
+
"grad_norm": 1.8161449432373047,
|
| 496 |
"learning_rate": 3.74037403740374e-05,
|
| 497 |
+
"loss": 0.3802,
|
| 498 |
"step": 660
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 3.32,
|
| 502 |
+
"grad_norm": 1.2450302839279175,
|
| 503 |
"learning_rate": 3.712871287128713e-05,
|
| 504 |
+
"loss": 0.387,
|
| 505 |
"step": 670
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 3.37,
|
| 509 |
+
"grad_norm": 1.1230440139770508,
|
| 510 |
"learning_rate": 3.6853685368536854e-05,
|
| 511 |
+
"loss": 0.4023,
|
| 512 |
"step": 680
|
| 513 |
},
|
| 514 |
{
|
| 515 |
"epoch": 3.42,
|
| 516 |
+
"grad_norm": 1.3349334001541138,
|
| 517 |
"learning_rate": 3.657865786578658e-05,
|
| 518 |
+
"loss": 0.4092,
|
| 519 |
"step": 690
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 3.47,
|
| 523 |
+
"grad_norm": 1.1348090171813965,
|
| 524 |
"learning_rate": 3.6303630363036307e-05,
|
| 525 |
+
"loss": 0.3724,
|
| 526 |
"step": 700
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"epoch": 3.51,
|
| 530 |
+
"grad_norm": 1.1959893703460693,
|
| 531 |
"learning_rate": 3.602860286028603e-05,
|
| 532 |
+
"loss": 0.415,
|
| 533 |
"step": 710
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 3.56,
|
| 537 |
+
"grad_norm": 1.0938156843185425,
|
| 538 |
"learning_rate": 3.575357535753576e-05,
|
| 539 |
+
"loss": 0.3931,
|
| 540 |
"step": 720
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 3.61,
|
| 544 |
+
"grad_norm": 1.199876308441162,
|
| 545 |
"learning_rate": 3.5478547854785485e-05,
|
| 546 |
+
"loss": 0.3817,
|
| 547 |
"step": 730
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 3.66,
|
| 551 |
+
"grad_norm": 1.3452043533325195,
|
| 552 |
"learning_rate": 3.5203520352035205e-05,
|
| 553 |
+
"loss": 0.3897,
|
| 554 |
"step": 740
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 3.71,
|
| 558 |
+
"grad_norm": 1.3791470527648926,
|
| 559 |
"learning_rate": 3.492849284928493e-05,
|
| 560 |
+
"loss": 0.3828,
|
| 561 |
"step": 750
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 3.76,
|
| 565 |
+
"grad_norm": 1.7758994102478027,
|
| 566 |
"learning_rate": 3.465346534653465e-05,
|
| 567 |
+
"loss": 0.382,
|
| 568 |
"step": 760
|
| 569 |
},
|
| 570 |
{
|
| 571 |
"epoch": 3.81,
|
| 572 |
+
"grad_norm": 1.0924941301345825,
|
| 573 |
"learning_rate": 3.4378437843784377e-05,
|
| 574 |
+
"loss": 0.4048,
|
| 575 |
"step": 770
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 3.86,
|
| 579 |
+
"grad_norm": 1.1729379892349243,
|
| 580 |
"learning_rate": 3.41034103410341e-05,
|
| 581 |
+
"loss": 0.3716,
|
| 582 |
"step": 780
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 3.91,
|
| 586 |
+
"grad_norm": 1.1679847240447998,
|
| 587 |
"learning_rate": 3.382838283828383e-05,
|
| 588 |
+
"loss": 0.3726,
|
| 589 |
"step": 790
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"epoch": 3.96,
|
| 593 |
+
"grad_norm": 1.166401743888855,
|
| 594 |
"learning_rate": 3.3553355335533555e-05,
|
| 595 |
+
"loss": 0.3931,
|
| 596 |
"step": 800
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 4.0,
|
| 600 |
+
"eval_accuracy": 0.855451062347614,
|
| 601 |
+
"eval_loss": 0.33083683252334595,
|
| 602 |
+
"eval_runtime": 15.5188,
|
| 603 |
+
"eval_samples_per_second": 185.001,
|
| 604 |
+
"eval_steps_per_second": 5.799,
|
| 605 |
"step": 808
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 4.01,
|
| 609 |
+
"grad_norm": 1.225820541381836,
|
| 610 |
"learning_rate": 3.327832783278328e-05,
|
| 611 |
+
"loss": 0.3976,
|
| 612 |
"step": 810
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 4.06,
|
| 616 |
+
"grad_norm": 1.0681790113449097,
|
| 617 |
"learning_rate": 3.300330033003301e-05,
|
| 618 |
+
"loss": 0.3641,
|
| 619 |
"step": 820
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 4.11,
|
| 623 |
+
"grad_norm": 1.3162754774093628,
|
| 624 |
"learning_rate": 3.272827282728273e-05,
|
| 625 |
+
"loss": 0.3601,
|
| 626 |
"step": 830
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 4.16,
|
| 630 |
+
"grad_norm": 1.5509825944900513,
|
| 631 |
"learning_rate": 3.2453245324532453e-05,
|
| 632 |
+
"loss": 0.3777,
|
| 633 |
"step": 840
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 4.21,
|
| 637 |
+
"grad_norm": 1.4965535402297974,
|
| 638 |
"learning_rate": 3.217821782178218e-05,
|
| 639 |
+
"loss": 0.3662,
|
| 640 |
"step": 850
|
| 641 |
},
|
| 642 |
{
|
| 643 |
"epoch": 4.26,
|
| 644 |
+
"grad_norm": 1.846308946609497,
|
| 645 |
"learning_rate": 3.1903190319031906e-05,
|
| 646 |
+
"loss": 0.3755,
|
| 647 |
"step": 860
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 4.31,
|
| 651 |
+
"grad_norm": 1.008911371231079,
|
| 652 |
"learning_rate": 3.162816281628163e-05,
|
| 653 |
+
"loss": 0.3283,
|
| 654 |
"step": 870
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 4.36,
|
| 658 |
+
"grad_norm": 1.7026519775390625,
|
| 659 |
"learning_rate": 3.135313531353136e-05,
|
| 660 |
+
"loss": 0.3782,
|
| 661 |
"step": 880
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 4.41,
|
| 665 |
+
"grad_norm": 1.3682829141616821,
|
| 666 |
"learning_rate": 3.1078107810781085e-05,
|
| 667 |
+
"loss": 0.3943,
|
| 668 |
"step": 890
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 4.46,
|
| 672 |
+
"grad_norm": 1.2787247896194458,
|
| 673 |
"learning_rate": 3.0803080308030804e-05,
|
| 674 |
+
"loss": 0.3651,
|
| 675 |
"step": 900
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 4.5,
|
| 679 |
+
"grad_norm": 1.2230846881866455,
|
| 680 |
"learning_rate": 3.052805280528053e-05,
|
| 681 |
+
"loss": 0.3489,
|
| 682 |
"step": 910
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 4.55,
|
| 686 |
+
"grad_norm": 1.4894435405731201,
|
| 687 |
"learning_rate": 3.0253025302530253e-05,
|
| 688 |
+
"loss": 0.372,
|
| 689 |
"step": 920
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 4.6,
|
| 693 |
+
"grad_norm": 1.6204265356063843,
|
| 694 |
"learning_rate": 2.9977997799779976e-05,
|
| 695 |
+
"loss": 0.3637,
|
| 696 |
"step": 930
|
| 697 |
},
|
| 698 |
{
|
| 699 |
"epoch": 4.65,
|
| 700 |
+
"grad_norm": 1.4866546392440796,
|
| 701 |
"learning_rate": 2.9702970297029702e-05,
|
| 702 |
+
"loss": 0.3657,
|
| 703 |
"step": 940
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 4.7,
|
| 707 |
+
"grad_norm": 1.8092739582061768,
|
| 708 |
"learning_rate": 2.942794279427943e-05,
|
| 709 |
+
"loss": 0.375,
|
| 710 |
"step": 950
|
| 711 |
},
|
| 712 |
{
|
| 713 |
"epoch": 4.75,
|
| 714 |
+
"grad_norm": 1.3936327695846558,
|
| 715 |
"learning_rate": 2.9152915291529155e-05,
|
| 716 |
+
"loss": 0.3737,
|
| 717 |
"step": 960
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 4.8,
|
| 721 |
+
"grad_norm": 1.3176568746566772,
|
| 722 |
"learning_rate": 2.8877887788778878e-05,
|
| 723 |
+
"loss": 0.3565,
|
| 724 |
"step": 970
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"epoch": 4.85,
|
| 728 |
+
"grad_norm": 1.4575417041778564,
|
| 729 |
"learning_rate": 2.8602860286028604e-05,
|
| 730 |
+
"loss": 0.3611,
|
| 731 |
"step": 980
|
| 732 |
},
|
| 733 |
{
|
| 734 |
"epoch": 4.9,
|
| 735 |
+
"grad_norm": 1.5857540369033813,
|
| 736 |
"learning_rate": 2.832783278327833e-05,
|
| 737 |
+
"loss": 0.3656,
|
| 738 |
"step": 990
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"epoch": 4.95,
|
| 742 |
+
"grad_norm": 1.0636128187179565,
|
| 743 |
"learning_rate": 2.8052805280528056e-05,
|
| 744 |
+
"loss": 0.3396,
|
| 745 |
"step": 1000
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 5.0,
|
| 749 |
+
"grad_norm": 1.4022269248962402,
|
| 750 |
"learning_rate": 2.777777777777778e-05,
|
| 751 |
+
"loss": 0.3667,
|
| 752 |
"step": 1010
|
| 753 |
},
|
| 754 |
{
|
| 755 |
"epoch": 5.0,
|
| 756 |
+
"eval_accuracy": 0.8610240334378265,
|
| 757 |
+
"eval_loss": 0.3203551471233368,
|
| 758 |
+
"eval_runtime": 15.3956,
|
| 759 |
+
"eval_samples_per_second": 186.482,
|
| 760 |
+
"eval_steps_per_second": 5.846,
|
| 761 |
"step": 1010
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 5.05,
|
| 765 |
+
"grad_norm": 1.3242789506912231,
|
| 766 |
"learning_rate": 2.7502750275027505e-05,
|
| 767 |
+
"loss": 0.3563,
|
| 768 |
"step": 1020
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 5.1,
|
| 772 |
+
"grad_norm": 1.8484835624694824,
|
| 773 |
"learning_rate": 2.722772277227723e-05,
|
| 774 |
+
"loss": 0.3295,
|
| 775 |
"step": 1030
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 5.15,
|
| 779 |
+
"grad_norm": 1.2119253873825073,
|
| 780 |
"learning_rate": 2.6952695269526958e-05,
|
| 781 |
+
"loss": 0.3789,
|
| 782 |
"step": 1040
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 5.2,
|
| 786 |
+
"grad_norm": 1.6589637994766235,
|
| 787 |
"learning_rate": 2.667766776677668e-05,
|
| 788 |
+
"loss": 0.3379,
|
| 789 |
"step": 1050
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 5.25,
|
| 793 |
+
"grad_norm": 1.5714747905731201,
|
| 794 |
"learning_rate": 2.64026402640264e-05,
|
| 795 |
+
"loss": 0.3675,
|
| 796 |
"step": 1060
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"epoch": 5.3,
|
| 800 |
+
"grad_norm": 1.3527103662490845,
|
| 801 |
"learning_rate": 2.6127612761276126e-05,
|
| 802 |
+
"loss": 0.3573,
|
| 803 |
"step": 1070
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 5.35,
|
| 807 |
+
"grad_norm": 1.055513620376587,
|
| 808 |
"learning_rate": 2.5852585258525853e-05,
|
| 809 |
+
"loss": 0.3478,
|
| 810 |
"step": 1080
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 5.4,
|
| 814 |
+
"grad_norm": 1.6614227294921875,
|
| 815 |
"learning_rate": 2.557755775577558e-05,
|
| 816 |
+
"loss": 0.3692,
|
| 817 |
"step": 1090
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 5.45,
|
| 821 |
+
"grad_norm": 1.5745677947998047,
|
| 822 |
"learning_rate": 2.53025302530253e-05,
|
| 823 |
+
"loss": 0.331,
|
| 824 |
"step": 1100
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 5.5,
|
| 828 |
+
"grad_norm": 1.4897499084472656,
|
| 829 |
"learning_rate": 2.5027502750275028e-05,
|
| 830 |
+
"loss": 0.352,
|
| 831 |
"step": 1110
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 5.54,
|
| 835 |
+
"grad_norm": 1.4070786237716675,
|
| 836 |
"learning_rate": 2.4752475247524754e-05,
|
| 837 |
+
"loss": 0.345,
|
| 838 |
"step": 1120
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 5.59,
|
| 842 |
+
"grad_norm": 2.2010486125946045,
|
| 843 |
"learning_rate": 2.447744774477448e-05,
|
| 844 |
+
"loss": 0.3213,
|
| 845 |
"step": 1130
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 5.64,
|
| 849 |
+
"grad_norm": 1.4076497554779053,
|
| 850 |
"learning_rate": 2.4202420242024203e-05,
|
| 851 |
+
"loss": 0.3414,
|
| 852 |
"step": 1140
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 5.69,
|
| 856 |
+
"grad_norm": 1.168713092803955,
|
| 857 |
"learning_rate": 2.392739273927393e-05,
|
| 858 |
+
"loss": 0.3521,
|
| 859 |
"step": 1150
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"epoch": 5.74,
|
| 863 |
+
"grad_norm": 1.8131704330444336,
|
| 864 |
"learning_rate": 2.3652365236523656e-05,
|
| 865 |
+
"loss": 0.3576,
|
| 866 |
"step": 1160
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 5.79,
|
| 870 |
+
"grad_norm": 1.2432703971862793,
|
| 871 |
"learning_rate": 2.337733773377338e-05,
|
| 872 |
+
"loss": 0.3416,
|
| 873 |
"step": 1170
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 5.84,
|
| 877 |
+
"grad_norm": 2.248685598373413,
|
| 878 |
"learning_rate": 2.31023102310231e-05,
|
| 879 |
+
"loss": 0.3396,
|
| 880 |
"step": 1180
|
| 881 |
},
|
| 882 |
{
|
| 883 |
"epoch": 5.89,
|
| 884 |
+
"grad_norm": 1.8308826684951782,
|
| 885 |
"learning_rate": 2.2827282728272828e-05,
|
| 886 |
+
"loss": 0.3466,
|
| 887 |
"step": 1190
|
| 888 |
},
|
| 889 |
{
|
| 890 |
"epoch": 5.94,
|
| 891 |
+
"grad_norm": 2.5257883071899414,
|
| 892 |
"learning_rate": 2.2552255225522554e-05,
|
| 893 |
+
"loss": 0.3186,
|
| 894 |
"step": 1200
|
| 895 |
},
|
| 896 |
{
|
| 897 |
"epoch": 5.99,
|
| 898 |
+
"grad_norm": 1.7196460962295532,
|
| 899 |
"learning_rate": 2.227722772277228e-05,
|
| 900 |
+
"loss": 0.3545,
|
| 901 |
"step": 1210
|
| 902 |
},
|
| 903 |
{
|
| 904 |
"epoch": 6.0,
|
| 905 |
+
"eval_accuracy": 0.8659003831417624,
|
| 906 |
+
"eval_loss": 0.31437239050865173,
|
| 907 |
+
"eval_runtime": 15.7136,
|
| 908 |
+
"eval_samples_per_second": 182.707,
|
| 909 |
+
"eval_steps_per_second": 5.728,
|
| 910 |
"step": 1212
|
| 911 |
},
|
| 912 |
{
|
| 913 |
"epoch": 6.04,
|
| 914 |
+
"grad_norm": 1.643741250038147,
|
| 915 |
"learning_rate": 2.2002200220022003e-05,
|
| 916 |
+
"loss": 0.3356,
|
| 917 |
"step": 1220
|
| 918 |
},
|
| 919 |
{
|
| 920 |
"epoch": 6.09,
|
| 921 |
+
"grad_norm": 1.5010825395584106,
|
| 922 |
"learning_rate": 2.172717271727173e-05,
|
| 923 |
+
"loss": 0.3288,
|
| 924 |
"step": 1230
|
| 925 |
},
|
| 926 |
{
|
| 927 |
"epoch": 6.14,
|
| 928 |
+
"grad_norm": 1.2441235780715942,
|
| 929 |
"learning_rate": 2.1452145214521452e-05,
|
| 930 |
+
"loss": 0.3395,
|
| 931 |
"step": 1240
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"epoch": 6.19,
|
| 935 |
+
"grad_norm": 1.351552128791809,
|
| 936 |
"learning_rate": 2.1177117711771178e-05,
|
| 937 |
+
"loss": 0.3011,
|
| 938 |
"step": 1250
|
| 939 |
},
|
| 940 |
{
|
| 941 |
"epoch": 6.24,
|
| 942 |
+
"grad_norm": 1.3512260913848877,
|
| 943 |
"learning_rate": 2.09020902090209e-05,
|
| 944 |
+
"loss": 0.3416,
|
| 945 |
"step": 1260
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 6.29,
|
| 949 |
+
"grad_norm": 1.5813019275665283,
|
| 950 |
"learning_rate": 2.0627062706270627e-05,
|
| 951 |
+
"loss": 0.3523,
|
| 952 |
"step": 1270
|
| 953 |
},
|
| 954 |
{
|
| 955 |
"epoch": 6.34,
|
| 956 |
+
"grad_norm": 1.5249056816101074,
|
| 957 |
"learning_rate": 2.0352035203520354e-05,
|
| 958 |
+
"loss": 0.3288,
|
| 959 |
"step": 1280
|
| 960 |
},
|
| 961 |
{
|
| 962 |
"epoch": 6.39,
|
| 963 |
+
"grad_norm": 1.9175376892089844,
|
| 964 |
"learning_rate": 2.007700770077008e-05,
|
| 965 |
+
"loss": 0.3527,
|
| 966 |
"step": 1290
|
| 967 |
},
|
| 968 |
{
|
| 969 |
"epoch": 6.44,
|
| 970 |
+
"grad_norm": 1.5546538829803467,
|
| 971 |
"learning_rate": 1.9801980198019803e-05,
|
| 972 |
+
"loss": 0.3076,
|
| 973 |
"step": 1300
|
| 974 |
},
|
| 975 |
{
|
| 976 |
"epoch": 6.49,
|
| 977 |
+
"grad_norm": 1.5470608472824097,
|
| 978 |
"learning_rate": 1.952695269526953e-05,
|
| 979 |
+
"loss": 0.3303,
|
| 980 |
"step": 1310
|
| 981 |
},
|
| 982 |
{
|
| 983 |
"epoch": 6.53,
|
| 984 |
+
"grad_norm": 1.3036069869995117,
|
| 985 |
"learning_rate": 1.9251925192519252e-05,
|
| 986 |
+
"loss": 0.3527,
|
| 987 |
"step": 1320
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 6.58,
|
| 991 |
+
"grad_norm": 1.524294137954712,
|
| 992 |
"learning_rate": 1.8976897689768978e-05,
|
| 993 |
+
"loss": 0.3243,
|
| 994 |
"step": 1330
|
| 995 |
},
|
| 996 |
{
|
| 997 |
"epoch": 6.63,
|
| 998 |
+
"grad_norm": 1.5366973876953125,
|
| 999 |
"learning_rate": 1.87018701870187e-05,
|
| 1000 |
+
"loss": 0.3299,
|
| 1001 |
"step": 1340
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
"epoch": 6.68,
|
| 1005 |
+
"grad_norm": 1.2275673151016235,
|
| 1006 |
"learning_rate": 1.8426842684268427e-05,
|
| 1007 |
+
"loss": 0.2928,
|
| 1008 |
"step": 1350
|
| 1009 |
},
|
| 1010 |
{
|
| 1011 |
"epoch": 6.73,
|
| 1012 |
+
"grad_norm": 1.4205721616744995,
|
| 1013 |
"learning_rate": 1.8151815181518153e-05,
|
| 1014 |
+
"loss": 0.3215,
|
| 1015 |
"step": 1360
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
"epoch": 6.78,
|
| 1019 |
+
"grad_norm": 1.4984817504882812,
|
| 1020 |
"learning_rate": 1.787678767876788e-05,
|
| 1021 |
+
"loss": 0.3008,
|
| 1022 |
"step": 1370
|
| 1023 |
},
|
| 1024 |
{
|
| 1025 |
"epoch": 6.83,
|
| 1026 |
+
"grad_norm": 1.6792049407958984,
|
| 1027 |
"learning_rate": 1.7601760176017602e-05,
|
| 1028 |
+
"loss": 0.3403,
|
| 1029 |
"step": 1380
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 6.88,
|
| 1033 |
+
"grad_norm": 1.5373748540878296,
|
| 1034 |
"learning_rate": 1.7326732673267325e-05,
|
| 1035 |
+
"loss": 0.3353,
|
| 1036 |
"step": 1390
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
"epoch": 6.93,
|
| 1040 |
+
"grad_norm": 2.501495361328125,
|
| 1041 |
"learning_rate": 1.705170517051705e-05,
|
| 1042 |
+
"loss": 0.3219,
|
| 1043 |
"step": 1400
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
"epoch": 6.98,
|
| 1047 |
+
"grad_norm": 1.3856743574142456,
|
| 1048 |
"learning_rate": 1.6776677667766778e-05,
|
| 1049 |
+
"loss": 0.3137,
|
| 1050 |
"step": 1410
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
"epoch": 7.0,
|
| 1054 |
+
"eval_accuracy": 0.864158829676071,
|
| 1055 |
+
"eval_loss": 0.3307534158229828,
|
| 1056 |
+
"eval_runtime": 15.9606,
|
| 1057 |
+
"eval_samples_per_second": 179.88,
|
| 1058 |
+
"eval_steps_per_second": 5.639,
|
| 1059 |
"step": 1414
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
"epoch": 7.03,
|
| 1063 |
+
"grad_norm": 1.5321968793869019,
|
| 1064 |
"learning_rate": 1.6501650165016504e-05,
|
| 1065 |
+
"loss": 0.308,
|
| 1066 |
"step": 1420
|
| 1067 |
},
|
| 1068 |
{
|
| 1069 |
"epoch": 7.08,
|
| 1070 |
+
"grad_norm": 1.4582158327102661,
|
| 1071 |
"learning_rate": 1.6226622662266227e-05,
|
| 1072 |
+
"loss": 0.3168,
|
| 1073 |
"step": 1430
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
"epoch": 7.13,
|
| 1077 |
+
"grad_norm": 1.4425067901611328,
|
| 1078 |
"learning_rate": 1.5951595159515953e-05,
|
| 1079 |
+
"loss": 0.3213,
|
| 1080 |
"step": 1440
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 7.18,
|
| 1084 |
+
"grad_norm": 1.933104395866394,
|
| 1085 |
"learning_rate": 1.567656765676568e-05,
|
| 1086 |
+
"loss": 0.2978,
|
| 1087 |
"step": 1450
|
| 1088 |
},
|
| 1089 |
{
|
| 1090 |
"epoch": 7.23,
|
| 1091 |
+
"grad_norm": 1.5549027919769287,
|
| 1092 |
"learning_rate": 1.5401540154015402e-05,
|
| 1093 |
+
"loss": 0.3281,
|
| 1094 |
"step": 1460
|
| 1095 |
},
|
| 1096 |
{
|
| 1097 |
"epoch": 7.28,
|
| 1098 |
+
"grad_norm": 1.4376338720321655,
|
| 1099 |
"learning_rate": 1.5126512651265127e-05,
|
| 1100 |
+
"loss": 0.2896,
|
| 1101 |
"step": 1470
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 7.33,
|
| 1105 |
+
"grad_norm": 1.414781093597412,
|
| 1106 |
"learning_rate": 1.4851485148514851e-05,
|
| 1107 |
+
"loss": 0.3135,
|
| 1108 |
"step": 1480
|
| 1109 |
},
|
| 1110 |
{
|
| 1111 |
"epoch": 7.38,
|
| 1112 |
+
"grad_norm": 1.3260300159454346,
|
| 1113 |
"learning_rate": 1.4576457645764577e-05,
|
| 1114 |
+
"loss": 0.2991,
|
| 1115 |
"step": 1490
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 7.43,
|
| 1119 |
+
"grad_norm": 1.8632981777191162,
|
| 1120 |
"learning_rate": 1.4301430143014302e-05,
|
| 1121 |
+
"loss": 0.3135,
|
| 1122 |
"step": 1500
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 7.48,
|
| 1126 |
+
"grad_norm": 1.6400821208953857,
|
| 1127 |
"learning_rate": 1.4026402640264028e-05,
|
| 1128 |
+
"loss": 0.2882,
|
| 1129 |
"step": 1510
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 7.52,
|
| 1133 |
+
"grad_norm": 1.8777371644973755,
|
| 1134 |
"learning_rate": 1.3751375137513753e-05,
|
| 1135 |
+
"loss": 0.3539,
|
| 1136 |
"step": 1520
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 7.57,
|
| 1140 |
+
"grad_norm": 1.431818962097168,
|
| 1141 |
"learning_rate": 1.3476347634763479e-05,
|
| 1142 |
+
"loss": 0.3065,
|
| 1143 |
"step": 1530
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 7.62,
|
| 1147 |
+
"grad_norm": 2.002371311187744,
|
| 1148 |
"learning_rate": 1.32013201320132e-05,
|
| 1149 |
+
"loss": 0.3362,
|
| 1150 |
"step": 1540
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 7.67,
|
| 1154 |
+
"grad_norm": 1.3172950744628906,
|
| 1155 |
"learning_rate": 1.2926292629262926e-05,
|
| 1156 |
+
"loss": 0.3062,
|
| 1157 |
"step": 1550
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 7.72,
|
| 1161 |
+
"grad_norm": 2.155853271484375,
|
| 1162 |
"learning_rate": 1.265126512651265e-05,
|
| 1163 |
+
"loss": 0.3151,
|
| 1164 |
"step": 1560
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 7.77,
|
| 1168 |
+
"grad_norm": 1.8984310626983643,
|
| 1169 |
"learning_rate": 1.2376237623762377e-05,
|
| 1170 |
+
"loss": 0.3488,
|
| 1171 |
"step": 1570
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 7.82,
|
| 1175 |
+
"grad_norm": 1.3027973175048828,
|
| 1176 |
"learning_rate": 1.2101210121012102e-05,
|
| 1177 |
+
"loss": 0.3197,
|
| 1178 |
"step": 1580
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 7.87,
|
| 1182 |
+
"grad_norm": 1.9755516052246094,
|
| 1183 |
"learning_rate": 1.1826182618261828e-05,
|
| 1184 |
+
"loss": 0.3287,
|
| 1185 |
"step": 1590
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 7.92,
|
| 1189 |
+
"grad_norm": 1.6631439924240112,
|
| 1190 |
"learning_rate": 1.155115511551155e-05,
|
| 1191 |
+
"loss": 0.303,
|
| 1192 |
"step": 1600
|
| 1193 |
},
|
| 1194 |
{
|
| 1195 |
"epoch": 7.97,
|
| 1196 |
+
"grad_norm": 1.8642737865447998,
|
| 1197 |
"learning_rate": 1.1276127612761277e-05,
|
| 1198 |
+
"loss": 0.3178,
|
| 1199 |
"step": 1610
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
"epoch": 8.0,
|
| 1203 |
+
"eval_accuracy": 0.8645071403692093,
|
| 1204 |
+
"eval_loss": 0.32295528054237366,
|
| 1205 |
+
"eval_runtime": 15.3242,
|
| 1206 |
+
"eval_samples_per_second": 187.351,
|
| 1207 |
+
"eval_steps_per_second": 5.873,
|
| 1208 |
"step": 1616
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
"epoch": 8.02,
|
| 1212 |
+
"grad_norm": 1.4315767288208008,
|
| 1213 |
"learning_rate": 1.1001100110011001e-05,
|
| 1214 |
+
"loss": 0.3078,
|
| 1215 |
"step": 1620
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
"epoch": 8.07,
|
| 1219 |
+
"grad_norm": 1.6558310985565186,
|
| 1220 |
"learning_rate": 1.0726072607260726e-05,
|
| 1221 |
+
"loss": 0.2853,
|
| 1222 |
"step": 1630
|
| 1223 |
},
|
| 1224 |
{
|
| 1225 |
"epoch": 8.12,
|
| 1226 |
+
"grad_norm": 1.906076431274414,
|
| 1227 |
"learning_rate": 1.045104510451045e-05,
|
| 1228 |
+
"loss": 0.2814,
|
| 1229 |
"step": 1640
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
"epoch": 8.17,
|
| 1233 |
+
"grad_norm": 2.086242914199829,
|
| 1234 |
"learning_rate": 1.0176017601760177e-05,
|
| 1235 |
+
"loss": 0.2847,
|
| 1236 |
"step": 1650
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
"epoch": 8.22,
|
| 1240 |
+
"grad_norm": 1.793742299079895,
|
| 1241 |
"learning_rate": 9.900990099009901e-06,
|
| 1242 |
+
"loss": 0.2945,
|
| 1243 |
"step": 1660
|
| 1244 |
},
|
| 1245 |
{
|
| 1246 |
"epoch": 8.27,
|
| 1247 |
+
"grad_norm": 1.7942755222320557,
|
| 1248 |
"learning_rate": 9.625962596259626e-06,
|
| 1249 |
+
"loss": 0.296,
|
| 1250 |
"step": 1670
|
| 1251 |
},
|
| 1252 |
{
|
| 1253 |
"epoch": 8.32,
|
| 1254 |
+
"grad_norm": 1.7433489561080933,
|
| 1255 |
"learning_rate": 9.35093509350935e-06,
|
| 1256 |
+
"loss": 0.2885,
|
| 1257 |
"step": 1680
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 8.37,
|
| 1261 |
+
"grad_norm": 1.6308104991912842,
|
| 1262 |
"learning_rate": 9.075907590759077e-06,
|
| 1263 |
+
"loss": 0.3134,
|
| 1264 |
"step": 1690
|
| 1265 |
},
|
| 1266 |
{
|
| 1267 |
"epoch": 8.42,
|
| 1268 |
+
"grad_norm": 1.6005682945251465,
|
| 1269 |
"learning_rate": 8.800880088008801e-06,
|
| 1270 |
+
"loss": 0.3206,
|
| 1271 |
"step": 1700
|
| 1272 |
},
|
| 1273 |
{
|
| 1274 |
"epoch": 8.47,
|
| 1275 |
+
"grad_norm": 1.563693642616272,
|
| 1276 |
"learning_rate": 8.525852585258526e-06,
|
| 1277 |
+
"loss": 0.3112,
|
| 1278 |
"step": 1710
|
| 1279 |
},
|
| 1280 |
{
|
| 1281 |
"epoch": 8.51,
|
| 1282 |
+
"grad_norm": 1.796925663948059,
|
| 1283 |
"learning_rate": 8.250825082508252e-06,
|
| 1284 |
+
"loss": 0.3076,
|
| 1285 |
"step": 1720
|
| 1286 |
},
|
| 1287 |
{
|
| 1288 |
"epoch": 8.56,
|
| 1289 |
+
"grad_norm": 1.5874933004379272,
|
| 1290 |
"learning_rate": 7.975797579757976e-06,
|
| 1291 |
+
"loss": 0.3197,
|
| 1292 |
"step": 1730
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
"epoch": 8.61,
|
| 1296 |
+
"grad_norm": 1.5310964584350586,
|
| 1297 |
"learning_rate": 7.700770077007701e-06,
|
| 1298 |
+
"loss": 0.3026,
|
| 1299 |
"step": 1740
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 8.66,
|
| 1303 |
+
"grad_norm": 1.9441354274749756,
|
| 1304 |
"learning_rate": 7.4257425742574256e-06,
|
| 1305 |
+
"loss": 0.3051,
|
| 1306 |
"step": 1750
|
| 1307 |
},
|
| 1308 |
{
|
| 1309 |
"epoch": 8.71,
|
| 1310 |
+
"grad_norm": 1.8038005828857422,
|
| 1311 |
"learning_rate": 7.150715071507151e-06,
|
| 1312 |
+
"loss": 0.3107,
|
| 1313 |
"step": 1760
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 8.76,
|
| 1317 |
+
"grad_norm": 4.733364582061768,
|
| 1318 |
"learning_rate": 6.875687568756876e-06,
|
| 1319 |
+
"loss": 0.2939,
|
| 1320 |
"step": 1770
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
"epoch": 8.81,
|
| 1324 |
+
"grad_norm": 1.5854134559631348,
|
| 1325 |
"learning_rate": 6.6006600660066e-06,
|
| 1326 |
+
"loss": 0.3049,
|
| 1327 |
"step": 1780
|
| 1328 |
},
|
| 1329 |
{
|
| 1330 |
"epoch": 8.86,
|
| 1331 |
+
"grad_norm": 1.7545024156570435,
|
| 1332 |
"learning_rate": 6.325632563256325e-06,
|
| 1333 |
+
"loss": 0.2936,
|
| 1334 |
"step": 1790
|
| 1335 |
},
|
| 1336 |
{
|
| 1337 |
"epoch": 8.91,
|
| 1338 |
+
"grad_norm": 1.6307064294815063,
|
| 1339 |
"learning_rate": 6.050605060506051e-06,
|
| 1340 |
+
"loss": 0.2855,
|
| 1341 |
"step": 1800
|
| 1342 |
},
|
| 1343 |
{
|
| 1344 |
"epoch": 8.96,
|
| 1345 |
+
"grad_norm": 1.6208785772323608,
|
| 1346 |
"learning_rate": 5.775577557755775e-06,
|
| 1347 |
+
"loss": 0.2998,
|
| 1348 |
"step": 1810
|
| 1349 |
},
|
| 1350 |
{
|
| 1351 |
"epoch": 9.0,
|
| 1352 |
+
"eval_accuracy": 0.8707767328456983,
|
| 1353 |
+
"eval_loss": 0.32057538628578186,
|
| 1354 |
+
"eval_runtime": 15.4893,
|
| 1355 |
+
"eval_samples_per_second": 185.354,
|
| 1356 |
+
"eval_steps_per_second": 5.81,
|
| 1357 |
"step": 1818
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
"epoch": 9.01,
|
| 1361 |
+
"grad_norm": 1.7324903011322021,
|
| 1362 |
"learning_rate": 5.500550055005501e-06,
|
| 1363 |
+
"loss": 0.2916,
|
| 1364 |
"step": 1820
|
| 1365 |
},
|
| 1366 |
{
|
| 1367 |
"epoch": 9.06,
|
| 1368 |
+
"grad_norm": 1.4792495965957642,
|
| 1369 |
"learning_rate": 5.225522552255225e-06,
|
| 1370 |
+
"loss": 0.2771,
|
| 1371 |
"step": 1830
|
| 1372 |
},
|
| 1373 |
{
|
| 1374 |
"epoch": 9.11,
|
| 1375 |
+
"grad_norm": 2.207402229309082,
|
| 1376 |
"learning_rate": 4.950495049504951e-06,
|
| 1377 |
+
"loss": 0.2859,
|
| 1378 |
"step": 1840
|
| 1379 |
},
|
| 1380 |
{
|
| 1381 |
"epoch": 9.16,
|
| 1382 |
+
"grad_norm": 1.9077599048614502,
|
| 1383 |
"learning_rate": 4.675467546754675e-06,
|
| 1384 |
+
"loss": 0.2833,
|
| 1385 |
"step": 1850
|
| 1386 |
},
|
| 1387 |
{
|
| 1388 |
"epoch": 9.21,
|
| 1389 |
+
"grad_norm": 1.7705243825912476,
|
| 1390 |
"learning_rate": 4.400440044004401e-06,
|
| 1391 |
+
"loss": 0.3007,
|
| 1392 |
"step": 1860
|
| 1393 |
},
|
| 1394 |
{
|
| 1395 |
"epoch": 9.26,
|
| 1396 |
+
"grad_norm": 1.74075448513031,
|
| 1397 |
"learning_rate": 4.125412541254126e-06,
|
| 1398 |
+
"loss": 0.2912,
|
| 1399 |
"step": 1870
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 9.31,
|
| 1403 |
+
"grad_norm": 1.8058630228042603,
|
| 1404 |
"learning_rate": 3.8503850385038505e-06,
|
| 1405 |
+
"loss": 0.297,
|
| 1406 |
"step": 1880
|
| 1407 |
},
|
| 1408 |
{
|
| 1409 |
"epoch": 9.36,
|
| 1410 |
+
"grad_norm": 1.7161786556243896,
|
| 1411 |
"learning_rate": 3.5753575357535755e-06,
|
| 1412 |
+
"loss": 0.2789,
|
| 1413 |
"step": 1890
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 9.41,
|
| 1417 |
+
"grad_norm": 2.8628289699554443,
|
| 1418 |
"learning_rate": 3.3003300330033e-06,
|
| 1419 |
+
"loss": 0.3018,
|
| 1420 |
"step": 1900
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
"epoch": 9.46,
|
| 1424 |
+
"grad_norm": 1.9037891626358032,
|
| 1425 |
"learning_rate": 3.0253025302530254e-06,
|
| 1426 |
+
"loss": 0.3043,
|
| 1427 |
"step": 1910
|
| 1428 |
},
|
| 1429 |
{
|
| 1430 |
"epoch": 9.5,
|
| 1431 |
+
"grad_norm": 1.5443955659866333,
|
| 1432 |
"learning_rate": 2.7502750275027504e-06,
|
| 1433 |
+
"loss": 0.2813,
|
| 1434 |
"step": 1920
|
| 1435 |
},
|
| 1436 |
{
|
| 1437 |
"epoch": 9.55,
|
| 1438 |
+
"grad_norm": 1.6395975351333618,
|
| 1439 |
"learning_rate": 2.4752475247524753e-06,
|
| 1440 |
+
"loss": 0.2942,
|
| 1441 |
"step": 1930
|
| 1442 |
},
|
| 1443 |
{
|
| 1444 |
"epoch": 9.6,
|
| 1445 |
+
"grad_norm": 1.4861618280410767,
|
| 1446 |
"learning_rate": 2.2002200220022003e-06,
|
| 1447 |
+
"loss": 0.2769,
|
| 1448 |
"step": 1940
|
| 1449 |
},
|
| 1450 |
{
|
| 1451 |
"epoch": 9.65,
|
| 1452 |
+
"grad_norm": 1.9940297603607178,
|
| 1453 |
"learning_rate": 1.9251925192519253e-06,
|
| 1454 |
+
"loss": 0.2833,
|
| 1455 |
"step": 1950
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
"epoch": 9.7,
|
| 1459 |
+
"grad_norm": 1.800776720046997,
|
| 1460 |
"learning_rate": 1.65016501650165e-06,
|
| 1461 |
+
"loss": 0.2948,
|
| 1462 |
"step": 1960
|
| 1463 |
},
|
| 1464 |
{
|
| 1465 |
"epoch": 9.75,
|
| 1466 |
+
"grad_norm": 1.4160261154174805,
|
| 1467 |
"learning_rate": 1.3751375137513752e-06,
|
| 1468 |
+
"loss": 0.2932,
|
| 1469 |
"step": 1970
|
| 1470 |
},
|
| 1471 |
{
|
| 1472 |
"epoch": 9.8,
|
| 1473 |
+
"grad_norm": 1.8922903537750244,
|
| 1474 |
"learning_rate": 1.1001100110011001e-06,
|
| 1475 |
+
"loss": 0.3189,
|
| 1476 |
"step": 1980
|
| 1477 |
},
|
| 1478 |
{
|
| 1479 |
"epoch": 9.85,
|
| 1480 |
+
"grad_norm": 1.754544734954834,
|
| 1481 |
"learning_rate": 8.25082508250825e-07,
|
| 1482 |
+
"loss": 0.2907,
|
| 1483 |
"step": 1990
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
"epoch": 9.9,
|
| 1487 |
+
"grad_norm": 1.8808295726776123,
|
| 1488 |
"learning_rate": 5.500550055005501e-07,
|
| 1489 |
+
"loss": 0.2763,
|
| 1490 |
"step": 2000
|
| 1491 |
},
|
| 1492 |
{
|
| 1493 |
"epoch": 9.95,
|
| 1494 |
+
"grad_norm": 2.0124707221984863,
|
| 1495 |
"learning_rate": 2.7502750275027504e-07,
|
| 1496 |
+
"loss": 0.2611,
|
| 1497 |
"step": 2010
|
| 1498 |
},
|
| 1499 |
{
|
| 1500 |
"epoch": 10.0,
|
| 1501 |
+
"grad_norm": 1.8302078247070312,
|
| 1502 |
"learning_rate": 0.0,
|
| 1503 |
+
"loss": 0.2773,
|
| 1504 |
"step": 2020
|
| 1505 |
},
|
| 1506 |
{
|
| 1507 |
"epoch": 10.0,
|
| 1508 |
+
"eval_accuracy": 0.8732149076976663,
|
| 1509 |
+
"eval_loss": 0.3263641893863678,
|
| 1510 |
+
"eval_runtime": 15.9034,
|
| 1511 |
+
"eval_samples_per_second": 180.527,
|
| 1512 |
+
"eval_steps_per_second": 5.659,
|
| 1513 |
"step": 2020
|
| 1514 |
},
|
| 1515 |
{
|
| 1516 |
"epoch": 10.0,
|
| 1517 |
"step": 2020,
|
| 1518 |
"total_flos": 2.0021605356722135e+19,
|
| 1519 |
+
"train_loss": 0.37925267927717454,
|
| 1520 |
+
"train_runtime": 3266.1275,
|
| 1521 |
+
"train_samples_per_second": 79.106,
|
| 1522 |
+
"train_steps_per_second": 0.618
|
| 1523 |
}
|
| 1524 |
],
|
| 1525 |
"logging_steps": 10,
|