Commit
•
3a834fe
1
Parent(s):
0c57bdd
End of training
Browse files
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second":
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.9022556390977443,
|
| 4 |
+
"eval_loss": 0.21882569789886475,
|
| 5 |
+
"eval_runtime": 0.8786,
|
| 6 |
+
"eval_samples_per_second": 151.372,
|
| 7 |
+
"eval_steps_per_second": 19.348,
|
| 8 |
+
"train_loss": 0.6012275494061984,
|
| 9 |
+
"train_runtime": 20.9633,
|
| 10 |
+
"train_samples_per_second": 49.324,
|
| 11 |
+
"train_steps_per_second": 6.201
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.9022556390977443,
|
| 4 |
+
"eval_loss": 0.21882569789886475,
|
| 5 |
+
"eval_runtime": 0.8786,
|
| 6 |
+
"eval_samples_per_second": 151.372,
|
| 7 |
+
"eval_steps_per_second": 19.348
|
| 8 |
}
|
runs/May31_10-43-13_ydupis-X570-AORUS-MASTER/events.out.tfevents.1654019265.ydupis-X570-AORUS-MASTER.15341.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57f21a9173f13accf0a2461e5325a23646ad76588fd81df085164be6ce634fbf
|
| 3 |
+
size 363
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.6012275494061984,
|
| 4 |
+
"train_runtime": 20.9633,
|
| 5 |
+
"train_samples_per_second": 49.324,
|
| 6 |
+
"train_steps_per_second": 6.201
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,460 +1,112 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./beans_outputs/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": 0.08,
|
| 12 |
-
"learning_rate": 0.
|
| 13 |
-
"loss": 1.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.15,
|
| 18 |
-
"learning_rate": 0.
|
| 19 |
-
"loss":
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.23,
|
| 24 |
-
"learning_rate": 0.
|
| 25 |
-
"loss":
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.31,
|
| 30 |
-
"learning_rate": 0.
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.38,
|
| 36 |
-
"learning_rate": 0.
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.46,
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.54,
|
| 48 |
-
"learning_rate": 0.
|
| 49 |
-
"loss": 0.
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.62,
|
| 54 |
-
"learning_rate": 0.
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.69,
|
| 60 |
-
"learning_rate": 0.
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.77,
|
| 66 |
-
"learning_rate": 0.
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.85,
|
| 72 |
-
"learning_rate": 0.
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.92,
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 120
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 1.0,
|
| 84 |
-
"learning_rate": 0.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 130
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 1.0,
|
| 90 |
-
"eval_accuracy": 0.8646616541353384,
|
| 91 |
-
"eval_loss": 0.28258681297302246,
|
| 92 |
-
"eval_runtime": 0.9861,
|
| 93 |
-
"eval_samples_per_second": 134.87,
|
| 94 |
-
"eval_steps_per_second": 17.239,
|
| 95 |
-
"step": 130
|
| 96 |
-
},
|
| 97 |
-
{
|
| 98 |
-
"epoch": 1.08,
|
| 99 |
-
"learning_rate": 0.0019199794436588243,
|
| 100 |
-
"loss": 0.5461,
|
| 101 |
-
"step": 140
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 1.15,
|
| 105 |
-
"learning_rate": 0.0018976137276390142,
|
| 106 |
-
"loss": 0.7203,
|
| 107 |
-
"step": 150
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 1.23,
|
| 111 |
-
"learning_rate": 0.0018726599588756144,
|
| 112 |
-
"loss": 0.4123,
|
| 113 |
-
"step": 160
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 1.31,
|
| 117 |
-
"learning_rate": 0.001845190085543795,
|
| 118 |
-
"loss": 0.5495,
|
| 119 |
-
"step": 170
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 1.38,
|
| 123 |
-
"learning_rate": 0.0018152833103995444,
|
| 124 |
-
"loss": 0.4613,
|
| 125 |
-
"step": 180
|
| 126 |
-
},
|
| 127 |
-
{
|
| 128 |
-
"epoch": 1.46,
|
| 129 |
-
"learning_rate": 0.0017830258624176223,
|
| 130 |
-
"loss": 0.4326,
|
| 131 |
-
"step": 190
|
| 132 |
-
},
|
| 133 |
-
{
|
| 134 |
-
"epoch": 1.54,
|
| 135 |
-
"learning_rate": 0.001748510748171101,
|
| 136 |
-
"loss": 0.3239,
|
| 137 |
-
"step": 200
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 1.62,
|
| 141 |
-
"learning_rate": 0.0017118374836693406,
|
| 142 |
-
"loss": 0.5905,
|
| 143 |
-
"step": 210
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 1.69,
|
| 147 |
-
"learning_rate": 0.0016731118074275702,
|
| 148 |
-
"loss": 0.5519,
|
| 149 |
-
"step": 220
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 1.77,
|
| 153 |
-
"learning_rate": 0.0016324453755953772,
|
| 154 |
-
"loss": 0.2935,
|
| 155 |
-
"step": 230
|
| 156 |
-
},
|
| 157 |
-
{
|
| 158 |
-
"epoch": 1.85,
|
| 159 |
-
"learning_rate": 0.001589955440023123,
|
| 160 |
-
"loss": 0.3501,
|
| 161 |
-
"step": 240
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"epoch": 1.92,
|
| 165 |
-
"learning_rate": 0.0015457645101945045,
|
| 166 |
-
"loss": 0.4842,
|
| 167 |
-
"step": 250
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 2.0,
|
| 171 |
-
"learning_rate": 0.0015,
|
| 172 |
-
"loss": 0.3596,
|
| 173 |
-
"step": 260
|
| 174 |
-
},
|
| 175 |
-
{
|
| 176 |
-
"epoch": 2.0,
|
| 177 |
"eval_accuracy": 0.9022556390977443,
|
| 178 |
-
"eval_loss": 0.
|
| 179 |
-
"eval_runtime": 0.
|
| 180 |
-
"eval_samples_per_second":
|
| 181 |
-
"eval_steps_per_second":
|
| 182 |
-
"step":
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 2.08,
|
| 186 |
-
"learning_rate": 0.0014527938603696375,
|
| 187 |
-
"loss": 0.578,
|
| 188 |
-
"step": 270
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 2.15,
|
| 192 |
-
"learning_rate": 0.0014042821988243049,
|
| 193 |
-
"loss": 0.3116,
|
| 194 |
-
"step": 280
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 2.23,
|
| 198 |
-
"learning_rate": 0.0013546048870425357,
|
| 199 |
-
"loss": 0.3378,
|
| 200 |
-
"step": 290
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 2.31,
|
| 204 |
-
"learning_rate": 0.0013039051575742468,
|
| 205 |
-
"loss": 0.3679,
|
| 206 |
-
"step": 300
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 2.38,
|
| 210 |
-
"learning_rate": 0.0012523291908642217,
|
| 211 |
-
"loss": 0.38,
|
| 212 |
-
"step": 310
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 2.46,
|
| 216 |
-
"learning_rate": 0.0012000256937760446,
|
| 217 |
-
"loss": 0.3309,
|
| 218 |
-
"step": 320
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 2.54,
|
| 222 |
-
"learning_rate": 0.001147145470831716,
|
| 223 |
-
"loss": 0.2248,
|
| 224 |
-
"step": 330
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 2.62,
|
| 228 |
-
"learning_rate": 0.0010938409894031794,
|
| 229 |
-
"loss": 0.3261,
|
| 230 |
-
"step": 340
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 2.69,
|
| 234 |
-
"learning_rate": 0.0010402659401094153,
|
| 235 |
-
"loss": 0.2697,
|
| 236 |
-
"step": 350
|
| 237 |
-
},
|
| 238 |
-
{
|
| 239 |
-
"epoch": 2.77,
|
| 240 |
-
"learning_rate": 0.0009865747936866028,
|
| 241 |
-
"loss": 0.3062,
|
| 242 |
-
"step": 360
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 2.85,
|
| 246 |
-
"learning_rate": 0.0009329223556089975,
|
| 247 |
-
"loss": 0.3551,
|
| 248 |
-
"step": 370
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 2.92,
|
| 252 |
-
"learning_rate": 0.0008794633197446771,
|
| 253 |
-
"loss": 0.2783,
|
| 254 |
-
"step": 380
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 3.0,
|
| 258 |
-
"learning_rate": 0.0008263518223330697,
|
| 259 |
-
"loss": 0.2419,
|
| 260 |
-
"step": 390
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 3.0,
|
| 264 |
-
"eval_accuracy": 0.9473684210526315,
|
| 265 |
-
"eval_loss": 0.13237899541854858,
|
| 266 |
-
"eval_runtime": 0.9783,
|
| 267 |
-
"eval_samples_per_second": 135.946,
|
| 268 |
-
"eval_steps_per_second": 17.377,
|
| 269 |
-
"step": 390
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 3.08,
|
| 273 |
-
"learning_rate": 0.0007737409975702781,
|
| 274 |
-
"loss": 0.2691,
|
| 275 |
-
"step": 400
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 3.15,
|
| 279 |
-
"learning_rate": 0.0007217825360835474,
|
| 280 |
-
"loss": 0.3115,
|
| 281 |
-
"step": 410
|
| 282 |
-
},
|
| 283 |
-
{
|
| 284 |
-
"epoch": 3.23,
|
| 285 |
-
"learning_rate": 0.0006706262475679205,
|
| 286 |
-
"loss": 0.2924,
|
| 287 |
-
"step": 420
|
| 288 |
-
},
|
| 289 |
-
{
|
| 290 |
-
"epoch": 3.31,
|
| 291 |
-
"learning_rate": 0.0006204196288461038,
|
| 292 |
-
"loss": 0.2037,
|
| 293 |
-
"step": 430
|
| 294 |
-
},
|
| 295 |
-
{
|
| 296 |
-
"epoch": 3.38,
|
| 297 |
-
"learning_rate": 0.0005713074385969457,
|
| 298 |
-
"loss": 0.2782,
|
| 299 |
-
"step": 440
|
| 300 |
-
},
|
| 301 |
-
{
|
| 302 |
-
"epoch": 3.46,
|
| 303 |
-
"learning_rate": 0.0005234312799786921,
|
| 304 |
-
"loss": 0.1141,
|
| 305 |
-
"step": 450
|
| 306 |
-
},
|
| 307 |
-
{
|
| 308 |
-
"epoch": 3.54,
|
| 309 |
-
"learning_rate": 0.00047692919235042255,
|
| 310 |
-
"loss": 0.504,
|
| 311 |
-
"step": 460
|
| 312 |
-
},
|
| 313 |
-
{
|
| 314 |
-
"epoch": 3.62,
|
| 315 |
-
"learning_rate": 0.0004319352532688443,
|
| 316 |
-
"loss": 0.1391,
|
| 317 |
-
"step": 470
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 3.69,
|
| 321 |
-
"learning_rate": 0.0003885791919079877,
|
| 322 |
-
"loss": 0.4455,
|
| 323 |
-
"step": 480
|
| 324 |
-
},
|
| 325 |
-
{
|
| 326 |
-
"epoch": 3.77,
|
| 327 |
-
"learning_rate": 0.0003469860150164151,
|
| 328 |
-
"loss": 0.1956,
|
| 329 |
-
"step": 490
|
| 330 |
-
},
|
| 331 |
-
{
|
| 332 |
-
"epoch": 3.85,
|
| 333 |
-
"learning_rate": 0.00030727564649040063,
|
| 334 |
-
"loss": 0.2292,
|
| 335 |
-
"step": 500
|
| 336 |
-
},
|
| 337 |
-
{
|
| 338 |
-
"epoch": 3.92,
|
| 339 |
-
"learning_rate": 0.00026956258160229697,
|
| 340 |
-
"loss": 0.2151,
|
| 341 |
-
"step": 510
|
| 342 |
-
},
|
| 343 |
-
{
|
| 344 |
-
"epoch": 4.0,
|
| 345 |
-
"learning_rate": 0.0002339555568810221,
|
| 346 |
-
"loss": 0.3248,
|
| 347 |
-
"step": 520
|
| 348 |
-
},
|
| 349 |
-
{
|
| 350 |
-
"epoch": 4.0,
|
| 351 |
-
"eval_accuracy": 0.9699248120300752,
|
| 352 |
-
"eval_loss": 0.11242649704217911,
|
| 353 |
-
"eval_runtime": 0.9749,
|
| 354 |
-
"eval_samples_per_second": 136.426,
|
| 355 |
-
"eval_steps_per_second": 17.438,
|
| 356 |
-
"step": 520
|
| 357 |
-
},
|
| 358 |
-
{
|
| 359 |
-
"epoch": 4.08,
|
| 360 |
-
"learning_rate": 0.00020055723659649904,
|
| 361 |
-
"loss": 0.0799,
|
| 362 |
-
"step": 530
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 4.15,
|
| 366 |
-
"learning_rate": 0.00016946391675198836,
|
| 367 |
-
"loss": 0.1854,
|
| 368 |
-
"step": 540
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 4.23,
|
| 372 |
-
"learning_rate": 0.00014076524743778318,
|
| 373 |
-
"loss": 0.2312,
|
| 374 |
-
"step": 550
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 4.31,
|
| 378 |
-
"learning_rate": 0.0001145439743467902,
|
| 379 |
-
"loss": 0.1739,
|
| 380 |
-
"step": 560
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 4.38,
|
| 384 |
-
"learning_rate": 9.08757001972762e-05,
|
| 385 |
-
"loss": 0.1797,
|
| 386 |
-
"step": 570
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 4.46,
|
| 390 |
-
"learning_rate": 6.98286667506618e-05,
|
| 391 |
-
"loss": 0.1376,
|
| 392 |
-
"step": 580
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 4.54,
|
| 396 |
-
"learning_rate": 5.146355805285452e-05,
|
| 397 |
-
"loss": 0.11,
|
| 398 |
-
"step": 590
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 4.62,
|
| 402 |
-
"learning_rate": 3.5833325466437696e-05,
|
| 403 |
-
"loss": 0.1737,
|
| 404 |
-
"step": 600
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 4.69,
|
| 408 |
-
"learning_rate": 2.2983034998182995e-05,
|
| 409 |
-
"loss": 0.1018,
|
| 410 |
-
"step": 610
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 4.77,
|
| 414 |
-
"learning_rate": 1.2949737362087154e-05,
|
| 415 |
-
"loss": 0.2031,
|
| 416 |
-
"step": 620
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 4.85,
|
| 420 |
-
"learning_rate": 5.7623611525721155e-06,
|
| 421 |
-
"loss": 0.1868,
|
| 422 |
-
"step": 630
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 4.92,
|
| 426 |
-
"learning_rate": 1.4416294358582382e-06,
|
| 427 |
-
"loss": 0.1781,
|
| 428 |
-
"step": 640
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 5.0,
|
| 432 |
-
"learning_rate": 0.0,
|
| 433 |
-
"loss": 0.1557,
|
| 434 |
-
"step": 650
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 5.0,
|
| 438 |
-
"eval_accuracy": 0.9699248120300752,
|
| 439 |
-
"eval_loss": 0.10140984505414963,
|
| 440 |
-
"eval_runtime": 1.0018,
|
| 441 |
-
"eval_samples_per_second": 132.757,
|
| 442 |
-
"eval_steps_per_second": 16.969,
|
| 443 |
-
"step": 650
|
| 444 |
},
|
| 445 |
{
|
| 446 |
-
"epoch":
|
| 447 |
-
"step":
|
| 448 |
-
"total_flos":
|
| 449 |
-
"train_loss": 0.
|
| 450 |
-
"train_runtime":
|
| 451 |
-
"train_samples_per_second":
|
| 452 |
-
"train_steps_per_second":
|
| 453 |
}
|
| 454 |
],
|
| 455 |
-
"max_steps":
|
| 456 |
-
"num_train_epochs":
|
| 457 |
-
"total_flos":
|
| 458 |
"trial_name": null,
|
| 459 |
"trial_params": null
|
| 460 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.21882569789886475,
|
| 3 |
+
"best_model_checkpoint": "./beans_outputs/checkpoint-130",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 130,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 0.0015384615384615387,
|
| 13 |
+
"loss": 1.0909,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.15,
|
| 18 |
+
"learning_rate": 0.0019823877374156645,
|
| 19 |
+
"loss": 0.9564,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.23,
|
| 24 |
+
"learning_rate": 0.0018976137276390142,
|
| 25 |
+
"loss": 0.8485,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.31,
|
| 30 |
+
"learning_rate": 0.001748510748171101,
|
| 31 |
+
"loss": 0.682,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.38,
|
| 36 |
+
"learning_rate": 0.0015457645101945045,
|
| 37 |
+
"loss": 0.7391,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.46,
|
| 42 |
+
"learning_rate": 0.0013039051575742468,
|
| 43 |
+
"loss": 0.3587,
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.54,
|
| 48 |
+
"learning_rate": 0.0010402659401094153,
|
| 49 |
+
"loss": 0.5773,
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.62,
|
| 54 |
+
"learning_rate": 0.0007737409975702781,
|
| 55 |
+
"loss": 0.507,
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.69,
|
| 60 |
+
"learning_rate": 0.0005234312799786921,
|
| 61 |
+
"loss": 0.4312,
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.77,
|
| 66 |
+
"learning_rate": 0.00030727564649040063,
|
| 67 |
+
"loss": 0.4067,
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.85,
|
| 72 |
+
"learning_rate": 0.00014076524743778318,
|
| 73 |
+
"loss": 0.3141,
|
| 74 |
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.92,
|
| 78 |
+
"learning_rate": 3.5833325466437696e-05,
|
| 79 |
+
"loss": 0.3359,
|
| 80 |
"step": 120
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 1.0,
|
| 84 |
+
"learning_rate": 0.0,
|
| 85 |
+
"loss": 0.5679,
|
| 86 |
"step": 130
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
"eval_accuracy": 0.9022556390977443,
|
| 91 |
+
"eval_loss": 0.21882569789886475,
|
| 92 |
+
"eval_runtime": 0.8027,
|
| 93 |
+
"eval_samples_per_second": 165.693,
|
| 94 |
+
"eval_steps_per_second": 21.179,
|
| 95 |
+
"step": 130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
},
|
| 97 |
{
|
| 98 |
+
"epoch": 1.0,
|
| 99 |
+
"step": 130,
|
| 100 |
+
"total_flos": 2.195932065572045e+16,
|
| 101 |
+
"train_loss": 0.6012275494061984,
|
| 102 |
+
"train_runtime": 20.9633,
|
| 103 |
+
"train_samples_per_second": 49.324,
|
| 104 |
+
"train_steps_per_second": 6.201
|
| 105 |
}
|
| 106 |
],
|
| 107 |
+
"max_steps": 130,
|
| 108 |
+
"num_train_epochs": 1,
|
| 109 |
+
"total_flos": 2.195932065572045e+16,
|
| 110 |
"trial_name": null,
|
| 111 |
"trial_params": null
|
| 112 |
}
|