End of training
Browse files
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.25,
|
| 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": 3.25,
|
| 3 |
+
"eval_accuracy": 0.8284023668639053,
|
| 4 |
+
"eval_loss": 0.45989519357681274,
|
| 5 |
+
"eval_runtime": 94.1469,
|
| 6 |
+
"eval_samples_per_second": 1.795,
|
| 7 |
+
"eval_steps_per_second": 0.903
|
| 8 |
}
|
runs/May11_18-07-17_7ffe87b6d6e8/events.out.tfevents.1683829879.7ffe87b6d6e8.6406.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:432986d9b7a1a03f4af6f7b7c987efb96e6b53b13898824fdd0674920286b1ce
|
| 3 |
+
size 734
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.25,
|
| 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": 3.25,
|
| 3 |
+
"eval_accuracy": 0.8284023668639053,
|
| 4 |
+
"eval_loss": 0.45989519357681274,
|
| 5 |
+
"eval_runtime": 94.1469,
|
| 6 |
+
"eval_samples_per_second": 1.795,
|
| 7 |
+
"eval_steps_per_second": 0.903
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,439 +1,439 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-
|
| 4 |
"epoch": 3.25,
|
| 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": 0.02,
|
| 12 |
-
"learning_rate": 8.
|
| 13 |
-
"loss": 2.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.03,
|
| 18 |
-
"learning_rate": 1.
|
| 19 |
-
"loss": 2.
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.05,
|
| 24 |
-
"learning_rate": 2.
|
| 25 |
-
"loss": 2.
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.07,
|
| 30 |
-
"learning_rate": 3.
|
| 31 |
-
"loss": 2.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.08,
|
| 36 |
-
"learning_rate": 4.
|
| 37 |
-
"loss": 2.
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.1,
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 2.
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.12,
|
| 48 |
-
"learning_rate": 4.
|
| 49 |
-
"loss": 2.
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.13,
|
| 54 |
-
"learning_rate": 4.
|
| 55 |
-
"loss":
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.15,
|
| 60 |
-
"learning_rate": 4.
|
| 61 |
-
"loss": 1.
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.17,
|
| 66 |
-
"learning_rate": 4.
|
| 67 |
-
"loss": 1.
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.18,
|
| 72 |
-
"learning_rate": 4.
|
| 73 |
-
"loss": 1.
|
| 74 |
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.2,
|
| 78 |
-
"learning_rate": 4.
|
| 79 |
-
"loss": 1.
|
| 80 |
"step": 120
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.22,
|
| 84 |
-
"learning_rate": 4.
|
| 85 |
-
"loss": 1.
|
| 86 |
"step": 130
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.23,
|
| 90 |
-
"learning_rate": 4.
|
| 91 |
-
"loss": 1.
|
| 92 |
"step": 140
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.25,
|
| 96 |
-
"learning_rate": 4.
|
| 97 |
-
"loss": 1.
|
| 98 |
"step": 150
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.25,
|
| 102 |
-
"eval_accuracy": 0.
|
| 103 |
-
"eval_loss": 1.
|
| 104 |
-
"eval_runtime":
|
| 105 |
-
"eval_samples_per_second":
|
| 106 |
-
"eval_steps_per_second":
|
| 107 |
-
"step":
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 1.
|
| 111 |
-
"learning_rate": 4.
|
| 112 |
-
"loss": 1.
|
| 113 |
"step": 160
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 1.03,
|
| 117 |
-
"learning_rate": 3.
|
| 118 |
-
"loss": 1.
|
| 119 |
"step": 170
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 1.05,
|
| 123 |
-
"learning_rate": 3.
|
| 124 |
-
"loss": 0.
|
| 125 |
"step": 180
|
| 126 |
},
|
| 127 |
{
|
| 128 |
-
"epoch": 1.
|
| 129 |
-
"learning_rate": 3.
|
| 130 |
-
"loss": 0.
|
| 131 |
"step": 190
|
| 132 |
},
|
| 133 |
{
|
| 134 |
"epoch": 1.08,
|
| 135 |
-
"learning_rate": 3.
|
| 136 |
-
"loss": 0.
|
| 137 |
"step": 200
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.1,
|
| 141 |
-
"learning_rate": 3.
|
| 142 |
-
"loss":
|
| 143 |
"step": 210
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch": 1.
|
| 147 |
-
"learning_rate": 3.
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 220
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 1.13,
|
| 153 |
-
"learning_rate": 3.
|
| 154 |
-
"loss":
|
| 155 |
"step": 230
|
| 156 |
},
|
| 157 |
{
|
| 158 |
"epoch": 1.15,
|
| 159 |
-
"learning_rate": 3.
|
| 160 |
-
"loss":
|
| 161 |
"step": 240
|
| 162 |
},
|
| 163 |
{
|
| 164 |
-
"epoch": 1.
|
| 165 |
-
"learning_rate": 3.
|
| 166 |
-
"loss": 0.
|
| 167 |
"step": 250
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 1.18,
|
| 171 |
-
"learning_rate": 3.
|
| 172 |
-
"loss":
|
| 173 |
"step": 260
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 1.2,
|
| 177 |
-
"learning_rate": 3.
|
| 178 |
-
"loss":
|
| 179 |
"step": 270
|
| 180 |
},
|
| 181 |
{
|
| 182 |
-
"epoch": 1.
|
| 183 |
-
"learning_rate": 2.
|
| 184 |
-
"loss": 0.
|
| 185 |
"step": 280
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 1.23,
|
| 189 |
-
"learning_rate": 2.
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 290
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 1.25,
|
| 195 |
-
"learning_rate": 2.
|
| 196 |
-
"loss": 0.
|
| 197 |
"step": 300
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 1.25,
|
| 201 |
-
"eval_accuracy": 0.
|
| 202 |
-
"eval_loss": 0.
|
| 203 |
-
"eval_runtime":
|
| 204 |
-
"eval_samples_per_second":
|
| 205 |
-
"eval_steps_per_second":
|
| 206 |
-
"step":
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch": 2.
|
| 210 |
-
"learning_rate": 2.
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 310
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 2.03,
|
| 216 |
-
"learning_rate": 2.
|
| 217 |
-
"loss": 0.
|
| 218 |
"step": 320
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 2.05,
|
| 222 |
-
"learning_rate": 2.
|
| 223 |
-
"loss": 0.
|
| 224 |
"step": 330
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch": 2.
|
| 228 |
-
"learning_rate": 2.
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 340
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 2.08,
|
| 234 |
-
"learning_rate": 2.
|
| 235 |
-
"loss": 0.
|
| 236 |
"step": 350
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 2.1,
|
| 240 |
-
"learning_rate": 2.
|
| 241 |
-
"loss": 0.
|
| 242 |
"step": 360
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch": 2.
|
| 246 |
-
"learning_rate": 2.
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 370
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 2.13,
|
| 252 |
-
"learning_rate": 2.
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 380
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 2.15,
|
| 258 |
-
"learning_rate": 1.
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 390
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch": 2.
|
| 264 |
-
"learning_rate": 1.
|
| 265 |
-
"loss": 0.
|
| 266 |
"step": 400
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 2.18,
|
| 270 |
-
"learning_rate": 1.
|
| 271 |
-
"loss": 0.
|
| 272 |
"step": 410
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 2.2,
|
| 276 |
-
"learning_rate": 1.
|
| 277 |
-
"loss": 0.
|
| 278 |
"step": 420
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch": 2.
|
| 282 |
-
"learning_rate": 1.
|
| 283 |
-
"loss": 0.
|
| 284 |
"step": 430
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 2.23,
|
| 288 |
-
"learning_rate": 1.
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 440
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 2.25,
|
| 294 |
-
"learning_rate": 1.
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 450
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 2.25,
|
| 300 |
-
"eval_accuracy": 0.
|
| 301 |
-
"eval_loss": 0.
|
| 302 |
-
"eval_runtime":
|
| 303 |
-
"eval_samples_per_second":
|
| 304 |
-
"eval_steps_per_second":
|
| 305 |
-
"step":
|
| 306 |
},
|
| 307 |
{
|
| 308 |
-
"epoch": 3.
|
| 309 |
-
"learning_rate": 1.
|
| 310 |
-
"loss": 0.
|
| 311 |
"step": 460
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 3.03,
|
| 315 |
-
"learning_rate": 1.
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 470
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch": 3.
|
| 321 |
-
"learning_rate": 1.
|
| 322 |
-
"loss": 0.
|
| 323 |
"step": 480
|
| 324 |
},
|
| 325 |
{
|
| 326 |
-
"epoch": 3.
|
| 327 |
-
"learning_rate": 1.
|
| 328 |
-
"loss": 0.
|
| 329 |
"step": 490
|
| 330 |
},
|
| 331 |
{
|
| 332 |
"epoch": 3.08,
|
| 333 |
-
"learning_rate": 9.
|
| 334 |
-
"loss": 0.
|
| 335 |
"step": 500
|
| 336 |
},
|
| 337 |
{
|
| 338 |
-
"epoch": 3.
|
| 339 |
-
"learning_rate": 8.
|
| 340 |
-
"loss": 0.
|
| 341 |
"step": 510
|
| 342 |
},
|
| 343 |
{
|
| 344 |
-
"epoch": 3.
|
| 345 |
-
"learning_rate": 7.
|
| 346 |
-
"loss": 0.
|
| 347 |
"step": 520
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 3.13,
|
| 351 |
-
"learning_rate": 6.
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 530
|
| 354 |
},
|
| 355 |
{
|
| 356 |
-
"epoch": 3.
|
| 357 |
-
"learning_rate": 5.
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 540
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch": 3.
|
| 363 |
-
"learning_rate": 4.
|
| 364 |
-
"loss": 0.
|
| 365 |
"step": 550
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 3.18,
|
| 369 |
-
"learning_rate":
|
| 370 |
-
"loss": 0.
|
| 371 |
"step": 560
|
| 372 |
},
|
| 373 |
{
|
| 374 |
-
"epoch": 3.
|
| 375 |
-
"learning_rate":
|
| 376 |
-
"loss": 0.
|
| 377 |
"step": 570
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch": 3.
|
| 381 |
-
"learning_rate":
|
| 382 |
-
"loss": 0.
|
| 383 |
"step": 580
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 3.23,
|
| 387 |
-
"learning_rate":
|
| 388 |
-
"loss": 0.
|
| 389 |
"step": 590
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"epoch": 3.
|
| 393 |
-
"learning_rate":
|
| 394 |
-
"loss": 0.
|
| 395 |
"step": 600
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 3.25,
|
| 399 |
-
"eval_accuracy": 0.
|
| 400 |
-
"eval_loss": 0.
|
| 401 |
-
"eval_runtime":
|
| 402 |
-
"eval_samples_per_second":
|
| 403 |
-
"eval_steps_per_second":
|
| 404 |
-
"step":
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 3.25,
|
| 408 |
-
"step":
|
| 409 |
-
"total_flos": 1.
|
| 410 |
-
"train_loss": 0.
|
| 411 |
-
"train_runtime":
|
| 412 |
-
"train_samples_per_second": 1.
|
| 413 |
-
"train_steps_per_second": 0.
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 3.25,
|
| 417 |
-
"eval_accuracy": 0.
|
| 418 |
-
"eval_loss": 0.
|
| 419 |
-
"eval_runtime":
|
| 420 |
-
"eval_samples_per_second":
|
| 421 |
-
"eval_steps_per_second":
|
| 422 |
-
"step":
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 3.25,
|
| 426 |
-
"eval_accuracy": 0.
|
| 427 |
-
"eval_loss": 0.
|
| 428 |
-
"eval_runtime":
|
| 429 |
-
"eval_samples_per_second":
|
| 430 |
-
"eval_steps_per_second":
|
| 431 |
-
"step":
|
| 432 |
}
|
| 433 |
],
|
| 434 |
-
"max_steps":
|
| 435 |
"num_train_epochs": 9223372036854775807,
|
| 436 |
-
"total_flos": 1.
|
| 437 |
"trial_name": null,
|
| 438 |
"trial_params": null
|
| 439 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7738095238095238,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-604",
|
| 4 |
"epoch": 3.25,
|
| 5 |
+
"global_step": 604,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 8.196721311475409e-06,
|
| 13 |
+
"loss": 2.4329,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 1.6393442622950818e-05,
|
| 19 |
+
"loss": 2.4383,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.05,
|
| 24 |
+
"learning_rate": 2.459016393442623e-05,
|
| 25 |
+
"loss": 2.428,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.07,
|
| 30 |
+
"learning_rate": 3.2786885245901635e-05,
|
| 31 |
+
"loss": 2.3514,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.08,
|
| 36 |
+
"learning_rate": 4.098360655737705e-05,
|
| 37 |
+
"loss": 2.4083,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.1,
|
| 42 |
+
"learning_rate": 4.918032786885246e-05,
|
| 43 |
+
"loss": 2.2609,
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.12,
|
| 48 |
+
"learning_rate": 4.9171270718232046e-05,
|
| 49 |
+
"loss": 2.1355,
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.13,
|
| 54 |
+
"learning_rate": 4.825046040515654e-05,
|
| 55 |
+
"loss": 2.0781,
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.15,
|
| 60 |
+
"learning_rate": 4.732965009208104e-05,
|
| 61 |
+
"loss": 1.686,
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.17,
|
| 66 |
+
"learning_rate": 4.6408839779005524e-05,
|
| 67 |
+
"loss": 1.5192,
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.18,
|
| 72 |
+
"learning_rate": 4.5488029465930024e-05,
|
| 73 |
+
"loss": 1.7072,
|
| 74 |
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.2,
|
| 78 |
+
"learning_rate": 4.4567219152854516e-05,
|
| 79 |
+
"loss": 1.93,
|
| 80 |
"step": 120
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.22,
|
| 84 |
+
"learning_rate": 4.364640883977901e-05,
|
| 85 |
+
"loss": 1.4418,
|
| 86 |
"step": 130
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.23,
|
| 90 |
+
"learning_rate": 4.27255985267035e-05,
|
| 91 |
+
"loss": 1.6683,
|
| 92 |
"step": 140
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.25,
|
| 96 |
+
"learning_rate": 4.1804788213627995e-05,
|
| 97 |
+
"loss": 1.3861,
|
| 98 |
"step": 150
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.25,
|
| 102 |
+
"eval_accuracy": 0.40476190476190477,
|
| 103 |
+
"eval_loss": 1.518173336982727,
|
| 104 |
+
"eval_runtime": 74.2638,
|
| 105 |
+
"eval_samples_per_second": 1.131,
|
| 106 |
+
"eval_steps_per_second": 0.566,
|
| 107 |
+
"step": 151
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 1.01,
|
| 111 |
+
"learning_rate": 4.088397790055249e-05,
|
| 112 |
+
"loss": 1.1002,
|
| 113 |
"step": 160
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 1.03,
|
| 117 |
+
"learning_rate": 3.996316758747698e-05,
|
| 118 |
+
"loss": 1.0042,
|
| 119 |
"step": 170
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 1.05,
|
| 123 |
+
"learning_rate": 3.904235727440147e-05,
|
| 124 |
+
"loss": 0.6699,
|
| 125 |
"step": 180
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 1.06,
|
| 129 |
+
"learning_rate": 3.812154696132597e-05,
|
| 130 |
+
"loss": 0.7446,
|
| 131 |
"step": 190
|
| 132 |
},
|
| 133 |
{
|
| 134 |
"epoch": 1.08,
|
| 135 |
+
"learning_rate": 3.720073664825046e-05,
|
| 136 |
+
"loss": 0.575,
|
| 137 |
"step": 200
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.1,
|
| 141 |
+
"learning_rate": 3.627992633517496e-05,
|
| 142 |
+
"loss": 1.0777,
|
| 143 |
"step": 210
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 1.11,
|
| 147 |
+
"learning_rate": 3.535911602209945e-05,
|
| 148 |
+
"loss": 0.8046,
|
| 149 |
"step": 220
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 1.13,
|
| 153 |
+
"learning_rate": 3.4438305709023944e-05,
|
| 154 |
+
"loss": 1.3932,
|
| 155 |
"step": 230
|
| 156 |
},
|
| 157 |
{
|
| 158 |
"epoch": 1.15,
|
| 159 |
+
"learning_rate": 3.3517495395948436e-05,
|
| 160 |
+
"loss": 1.0903,
|
| 161 |
"step": 240
|
| 162 |
},
|
| 163 |
{
|
| 164 |
+
"epoch": 1.16,
|
| 165 |
+
"learning_rate": 3.259668508287293e-05,
|
| 166 |
+
"loss": 0.9612,
|
| 167 |
"step": 250
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 1.18,
|
| 171 |
+
"learning_rate": 3.167587476979743e-05,
|
| 172 |
+
"loss": 1.0058,
|
| 173 |
"step": 260
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 1.2,
|
| 177 |
+
"learning_rate": 3.0755064456721915e-05,
|
| 178 |
+
"loss": 1.0088,
|
| 179 |
"step": 270
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 1.21,
|
| 183 |
+
"learning_rate": 2.983425414364641e-05,
|
| 184 |
+
"loss": 0.5327,
|
| 185 |
"step": 280
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 1.23,
|
| 189 |
+
"learning_rate": 2.8913443830570904e-05,
|
| 190 |
+
"loss": 0.5463,
|
| 191 |
"step": 290
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 1.25,
|
| 195 |
+
"learning_rate": 2.7992633517495396e-05,
|
| 196 |
+
"loss": 0.6672,
|
| 197 |
"step": 300
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 1.25,
|
| 201 |
+
"eval_accuracy": 0.7023809523809523,
|
| 202 |
+
"eval_loss": 0.9395186901092529,
|
| 203 |
+
"eval_runtime": 73.8401,
|
| 204 |
+
"eval_samples_per_second": 1.138,
|
| 205 |
+
"eval_steps_per_second": 0.569,
|
| 206 |
+
"step": 302
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 2.01,
|
| 210 |
+
"learning_rate": 2.707182320441989e-05,
|
| 211 |
+
"loss": 0.1746,
|
| 212 |
"step": 310
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 2.03,
|
| 216 |
+
"learning_rate": 2.6151012891344385e-05,
|
| 217 |
+
"loss": 0.2385,
|
| 218 |
"step": 320
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 2.05,
|
| 222 |
+
"learning_rate": 2.523020257826888e-05,
|
| 223 |
+
"loss": 0.7082,
|
| 224 |
"step": 330
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 2.06,
|
| 228 |
+
"learning_rate": 2.430939226519337e-05,
|
| 229 |
+
"loss": 0.4966,
|
| 230 |
"step": 340
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 2.08,
|
| 234 |
+
"learning_rate": 2.3388581952117867e-05,
|
| 235 |
+
"loss": 0.74,
|
| 236 |
"step": 350
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 2.1,
|
| 240 |
+
"learning_rate": 2.246777163904236e-05,
|
| 241 |
+
"loss": 0.5615,
|
| 242 |
"step": 360
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 2.11,
|
| 246 |
+
"learning_rate": 2.1546961325966852e-05,
|
| 247 |
+
"loss": 0.406,
|
| 248 |
"step": 370
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 2.13,
|
| 252 |
+
"learning_rate": 2.0626151012891345e-05,
|
| 253 |
+
"loss": 0.2123,
|
| 254 |
"step": 380
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 2.15,
|
| 258 |
+
"learning_rate": 1.9705340699815838e-05,
|
| 259 |
+
"loss": 0.0971,
|
| 260 |
"step": 390
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 2.16,
|
| 264 |
+
"learning_rate": 1.878453038674033e-05,
|
| 265 |
+
"loss": 0.2095,
|
| 266 |
"step": 400
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 2.18,
|
| 270 |
+
"learning_rate": 1.7863720073664823e-05,
|
| 271 |
+
"loss": 0.0643,
|
| 272 |
"step": 410
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 2.2,
|
| 276 |
+
"learning_rate": 1.694290976058932e-05,
|
| 277 |
+
"loss": 0.1121,
|
| 278 |
"step": 420
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 2.21,
|
| 282 |
+
"learning_rate": 1.6022099447513812e-05,
|
| 283 |
+
"loss": 0.4411,
|
| 284 |
"step": 430
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 2.23,
|
| 288 |
+
"learning_rate": 1.5101289134438307e-05,
|
| 289 |
+
"loss": 0.2766,
|
| 290 |
"step": 440
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 2.25,
|
| 294 |
+
"learning_rate": 1.41804788213628e-05,
|
| 295 |
+
"loss": 0.1478,
|
| 296 |
"step": 450
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 2.25,
|
| 300 |
+
"eval_accuracy": 0.7380952380952381,
|
| 301 |
+
"eval_loss": 0.7313230633735657,
|
| 302 |
+
"eval_runtime": 75.0778,
|
| 303 |
+
"eval_samples_per_second": 1.119,
|
| 304 |
+
"eval_steps_per_second": 0.559,
|
| 305 |
+
"step": 453
|
| 306 |
},
|
| 307 |
{
|
| 308 |
+
"epoch": 3.01,
|
| 309 |
+
"learning_rate": 1.3259668508287292e-05,
|
| 310 |
+
"loss": 0.2004,
|
| 311 |
"step": 460
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 3.03,
|
| 315 |
+
"learning_rate": 1.2338858195211787e-05,
|
| 316 |
+
"loss": 0.0466,
|
| 317 |
"step": 470
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 3.04,
|
| 321 |
+
"learning_rate": 1.1418047882136281e-05,
|
| 322 |
+
"loss": 0.2506,
|
| 323 |
"step": 480
|
| 324 |
},
|
| 325 |
{
|
| 326 |
+
"epoch": 3.06,
|
| 327 |
+
"learning_rate": 1.0497237569060774e-05,
|
| 328 |
+
"loss": 0.2664,
|
| 329 |
"step": 490
|
| 330 |
},
|
| 331 |
{
|
| 332 |
"epoch": 3.08,
|
| 333 |
+
"learning_rate": 9.576427255985269e-06,
|
| 334 |
+
"loss": 0.3079,
|
| 335 |
"step": 500
|
| 336 |
},
|
| 337 |
{
|
| 338 |
+
"epoch": 3.09,
|
| 339 |
+
"learning_rate": 8.655616942909761e-06,
|
| 340 |
+
"loss": 0.3008,
|
| 341 |
"step": 510
|
| 342 |
},
|
| 343 |
{
|
| 344 |
+
"epoch": 3.11,
|
| 345 |
+
"learning_rate": 7.734806629834254e-06,
|
| 346 |
+
"loss": 0.1139,
|
| 347 |
"step": 520
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 3.13,
|
| 351 |
+
"learning_rate": 6.8139963167587485e-06,
|
| 352 |
+
"loss": 0.271,
|
| 353 |
"step": 530
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"epoch": 3.14,
|
| 357 |
+
"learning_rate": 5.893186003683242e-06,
|
| 358 |
+
"loss": 0.104,
|
| 359 |
"step": 540
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 3.16,
|
| 363 |
+
"learning_rate": 4.972375690607735e-06,
|
| 364 |
+
"loss": 0.191,
|
| 365 |
"step": 550
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 3.18,
|
| 369 |
+
"learning_rate": 4.0515653775322285e-06,
|
| 370 |
+
"loss": 0.1103,
|
| 371 |
"step": 560
|
| 372 |
},
|
| 373 |
{
|
| 374 |
+
"epoch": 3.19,
|
| 375 |
+
"learning_rate": 3.1307550644567225e-06,
|
| 376 |
+
"loss": 0.1846,
|
| 377 |
"step": 570
|
| 378 |
},
|
| 379 |
{
|
| 380 |
+
"epoch": 3.21,
|
| 381 |
+
"learning_rate": 2.2099447513812157e-06,
|
| 382 |
+
"loss": 0.1183,
|
| 383 |
"step": 580
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 3.23,
|
| 387 |
+
"learning_rate": 1.289134438305709e-06,
|
| 388 |
+
"loss": 0.0612,
|
| 389 |
"step": 590
|
| 390 |
},
|
| 391 |
{
|
| 392 |
+
"epoch": 3.24,
|
| 393 |
+
"learning_rate": 3.6832412523020263e-07,
|
| 394 |
+
"loss": 0.2596,
|
| 395 |
"step": 600
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 3.25,
|
| 399 |
+
"eval_accuracy": 0.7738095238095238,
|
| 400 |
+
"eval_loss": 0.543230414390564,
|
| 401 |
+
"eval_runtime": 74.0438,
|
| 402 |
+
"eval_samples_per_second": 1.134,
|
| 403 |
+
"eval_steps_per_second": 0.567,
|
| 404 |
+
"step": 604
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 3.25,
|
| 408 |
+
"step": 604,
|
| 409 |
+
"total_flos": 1.5053668400415375e+18,
|
| 410 |
+
"train_loss": 0.8410116481958636,
|
| 411 |
+
"train_runtime": 1073.1012,
|
| 412 |
+
"train_samples_per_second": 1.126,
|
| 413 |
+
"train_steps_per_second": 0.563
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 3.25,
|
| 417 |
+
"eval_accuracy": 0.8284023668639053,
|
| 418 |
+
"eval_loss": 0.4598952829837799,
|
| 419 |
+
"eval_runtime": 100.3611,
|
| 420 |
+
"eval_samples_per_second": 1.684,
|
| 421 |
+
"eval_steps_per_second": 0.847,
|
| 422 |
+
"step": 604
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 3.25,
|
| 426 |
+
"eval_accuracy": 0.8284023668639053,
|
| 427 |
+
"eval_loss": 0.45989519357681274,
|
| 428 |
+
"eval_runtime": 94.1469,
|
| 429 |
+
"eval_samples_per_second": 1.795,
|
| 430 |
+
"eval_steps_per_second": 0.903,
|
| 431 |
+
"step": 604
|
| 432 |
}
|
| 433 |
],
|
| 434 |
+
"max_steps": 604,
|
| 435 |
"num_train_epochs": 9223372036854775807,
|
| 436 |
+
"total_flos": 1.5053668400415375e+18,
|
| 437 |
"trial_name": null,
|
| 438 |
"trial_params": null
|
| 439 |
}
|