trainer_state.json
| 1 | { |
| 2 | "best_metric": null, |
| 3 | "best_model_checkpoint": null, |
| 4 | "epoch": 50.0, |
| 5 | "global_step": 34800, |
| 6 | "is_hyper_param_search": false, |
| 7 | "is_local_process_zero": true, |
| 8 | "is_world_process_zero": true, |
| 9 | "log_history": [ |
| 10 | { |
| 11 | "epoch": 0.01, |
| 12 | "learning_rate": 5.999999999999999e-06, |
| 13 | "loss": 0.0495, |
| 14 | "step": 10 |
| 15 | }, |
| 16 | { |
| 17 | "epoch": 0.03, |
| 18 | "learning_rate": 1.1999999999999999e-05, |
| 19 | "loss": 0.044, |
| 20 | "step": 20 |
| 21 | }, |
| 22 | { |
| 23 | "epoch": 0.04, |
| 24 | "learning_rate": 1.7999999999999997e-05, |
| 25 | "loss": 0.0557, |
| 26 | "step": 30 |
| 27 | }, |
| 28 | { |
| 29 | "epoch": 0.06, |
| 30 | "learning_rate": 2.3999999999999997e-05, |
| 31 | "loss": 0.0405, |
| 32 | "step": 40 |
| 33 | }, |
| 34 | { |
| 35 | "epoch": 0.07, |
| 36 | "learning_rate": 2.9999999999999997e-05, |
| 37 | "loss": 0.0389, |
| 38 | "step": 50 |
| 39 | }, |
| 40 | { |
| 41 | "epoch": 0.09, |
| 42 | "learning_rate": 3.5999999999999994e-05, |
| 43 | "loss": 0.0497, |
| 44 | "step": 60 |
| 45 | }, |
| 46 | { |
| 47 | "epoch": 0.1, |
| 48 | "learning_rate": 4.2e-05, |
| 49 | "loss": 0.0358, |
| 50 | "step": 70 |
| 51 | }, |
| 52 | { |
| 53 | "epoch": 0.11, |
| 54 | "learning_rate": 4.7999999999999994e-05, |
| 55 | "loss": 0.0594, |
| 56 | "step": 80 |
| 57 | }, |
| 58 | { |
| 59 | "epoch": 0.13, |
| 60 | "learning_rate": 5.399999999999999e-05, |
| 61 | "loss": 0.0458, |
| 62 | "step": 90 |
| 63 | }, |
| 64 | { |
| 65 | "epoch": 0.14, |
| 66 | "learning_rate": 5.9999999999999995e-05, |
| 67 | "loss": 0.0433, |
| 68 | "step": 100 |
| 69 | }, |
| 70 | { |
| 71 | "epoch": 0.14, |
| 72 | "eval_loss": 0.14026756584644318, |
| 73 | "eval_runtime": 39.7591, |
| 74 | "eval_samples_per_second": 11.494, |
| 75 | "eval_steps_per_second": 1.459, |
| 76 | "eval_wer": 0.1454600210811625, |
| 77 | "step": 100 |
| 78 | }, |
| 79 | { |
| 80 | "epoch": 0.16, |
| 81 | "learning_rate": 6.599999999999999e-05, |
| 82 | "loss": 0.0569, |
| 83 | "step": 110 |
| 84 | }, |
| 85 | { |
| 86 | "epoch": 0.17, |
| 87 | "learning_rate": 7.199999999999999e-05, |
| 88 | "loss": 0.0497, |
| 89 | "step": 120 |
| 90 | }, |
| 91 | { |
| 92 | "epoch": 0.19, |
| 93 | "learning_rate": 7.8e-05, |
| 94 | "loss": 0.0426, |
| 95 | "step": 130 |
| 96 | }, |
| 97 | { |
| 98 | "epoch": 0.2, |
| 99 | "learning_rate": 8.4e-05, |
| 100 | "loss": 0.0521, |
| 101 | "step": 140 |
| 102 | }, |
| 103 | { |
| 104 | "epoch": 0.22, |
| 105 | "learning_rate": 8.999999999999999e-05, |
| 106 | "loss": 0.0375, |
| 107 | "step": 150 |
| 108 | }, |
| 109 | { |
| 110 | "epoch": 0.23, |
| 111 | "learning_rate": 9.599999999999999e-05, |
| 112 | "loss": 0.0505, |
| 113 | "step": 160 |
| 114 | }, |
| 115 | { |
| 116 | "epoch": 0.24, |
| 117 | "learning_rate": 0.000102, |
| 118 | "loss": 0.042, |
| 119 | "step": 170 |
| 120 | }, |
| 121 | { |
| 122 | "epoch": 0.26, |
| 123 | "learning_rate": 0.00010799999999999998, |
| 124 | "loss": 0.0549, |
| 125 | "step": 180 |
| 126 | }, |
| 127 | { |
| 128 | "epoch": 0.27, |
| 129 | "learning_rate": 0.00011399999999999999, |
| 130 | "loss": 0.0558, |
| 131 | "step": 190 |
| 132 | }, |
| 133 | { |
| 134 | "epoch": 0.29, |
| 135 | "learning_rate": 0.00011999999999999999, |
| 136 | "loss": 0.0423, |
| 137 | "step": 200 |
| 138 | }, |
| 139 | { |
| 140 | "epoch": 0.29, |
| 141 | "eval_loss": 0.14491483569145203, |
| 142 | "eval_runtime": 39.8939, |
| 143 | "eval_samples_per_second": 11.455, |
| 144 | "eval_steps_per_second": 1.454, |
| 145 | "eval_wer": 0.14756813732871554, |
| 146 | "step": 200 |
| 147 | }, |
| 148 | { |
| 149 | "epoch": 0.3, |
| 150 | "learning_rate": 0.00012599999999999997, |
| 151 | "loss": 0.0706, |
| 152 | "step": 210 |
| 153 | }, |
| 154 | { |
| 155 | "epoch": 0.32, |
| 156 | "learning_rate": 0.00013199999999999998, |
| 157 | "loss": 0.0403, |
| 158 | "step": 220 |
| 159 | }, |
| 160 | { |
| 161 | "epoch": 0.33, |
| 162 | "learning_rate": 0.000138, |
| 163 | "loss": 0.0578, |
| 164 | "step": 230 |
| 165 | }, |
| 166 | { |
| 167 | "epoch": 0.34, |
| 168 | "learning_rate": 0.00014399999999999998, |
| 169 | "loss": 0.0642, |
| 170 | "step": 240 |
| 171 | }, |
| 172 | { |
| 173 | "epoch": 0.36, |
| 174 | "learning_rate": 0.00015, |
| 175 | "loss": 0.054, |
| 176 | "step": 250 |
| 177 | }, |
| 178 | { |
| 179 | "epoch": 0.37, |
| 180 | "learning_rate": 0.000156, |
| 181 | "loss": 0.0576, |
| 182 | "step": 260 |
| 183 | }, |
| 184 | { |
| 185 | "epoch": 0.39, |
| 186 | "learning_rate": 0.000162, |
| 187 | "loss": 0.0668, |
| 188 | "step": 270 |
| 189 | }, |
| 190 | { |
| 191 | "epoch": 0.4, |
| 192 | "learning_rate": 0.000168, |
| 193 | "loss": 0.057, |
| 194 | "step": 280 |
| 195 | }, |
| 196 | { |
| 197 | "epoch": 0.42, |
| 198 | "learning_rate": 0.00017399999999999997, |
| 199 | "loss": 0.05, |
| 200 | "step": 290 |
| 201 | }, |
| 202 | { |
| 203 | "epoch": 0.43, |
| 204 | "learning_rate": 0.00017999999999999998, |
| 205 | "loss": 0.0603, |
| 206 | "step": 300 |
| 207 | }, |
| 208 | { |
| 209 | "epoch": 0.43, |
| 210 | "eval_loss": 0.15721559524536133, |
| 211 | "eval_runtime": 39.6461, |
| 212 | "eval_samples_per_second": 11.527, |
| 213 | "eval_steps_per_second": 1.463, |
| 214 | "eval_wer": 0.15163379009185363, |
| 215 | "step": 300 |
| 216 | }, |
| 217 | { |
| 218 | "epoch": 0.45, |
| 219 | "learning_rate": 0.000186, |
| 220 | "loss": 0.0903, |
| 221 | "step": 310 |
| 222 | }, |
| 223 | { |
| 224 | "epoch": 0.46, |
| 225 | "learning_rate": 0.00019199999999999998, |
| 226 | "loss": 0.0532, |
| 227 | "step": 320 |
| 228 | }, |
| 229 | { |
| 230 | "epoch": 0.47, |
| 231 | "learning_rate": 0.000198, |
| 232 | "loss": 0.079, |
| 233 | "step": 330 |
| 234 | }, |
| 235 | { |
| 236 | "epoch": 0.49, |
| 237 | "learning_rate": 0.000204, |
| 238 | "loss": 0.0732, |
| 239 | "step": 340 |
| 240 | }, |
| 241 | { |
| 242 | "epoch": 0.5, |
| 243 | "learning_rate": 0.00020999999999999998, |
| 244 | "loss": 0.0617, |
| 245 | "step": 350 |
| 246 | }, |
| 247 | { |
| 248 | "epoch": 0.52, |
| 249 | "learning_rate": 0.00021599999999999996, |
| 250 | "loss": 0.0848, |
| 251 | "step": 360 |
| 252 | }, |
| 253 | { |
| 254 | "epoch": 0.53, |
| 255 | "learning_rate": 0.00022199999999999998, |
| 256 | "loss": 0.0599, |
| 257 | "step": 370 |
| 258 | }, |
| 259 | { |
| 260 | "epoch": 0.55, |
| 261 | "learning_rate": 0.00022799999999999999, |
| 262 | "loss": 0.0706, |
| 263 | "step": 380 |
| 264 | }, |
| 265 | { |
| 266 | "epoch": 0.56, |
| 267 | "learning_rate": 0.000234, |
| 268 | "loss": 0.058, |
| 269 | "step": 390 |
| 270 | }, |
| 271 | { |
| 272 | "epoch": 0.57, |
| 273 | "learning_rate": 0.00023999999999999998, |
| 274 | "loss": 0.0691, |
| 275 | "step": 400 |
| 276 | }, |
| 277 | { |
| 278 | "epoch": 0.57, |
| 279 | "eval_loss": 0.16631954908370972, |
| 280 | "eval_runtime": 39.7215, |
| 281 | "eval_samples_per_second": 11.505, |
| 282 | "eval_steps_per_second": 1.46, |
| 283 | "eval_wer": 0.1669929227525975, |
| 284 | "step": 400 |
| 285 | }, |
| 286 | { |
| 287 | "epoch": 0.59, |
| 288 | "learning_rate": 0.00024599999999999996, |
| 289 | "loss": 0.0786, |
| 290 | "step": 410 |
| 291 | }, |
| 292 | { |
| 293 | "epoch": 0.6, |
| 294 | "learning_rate": 0.00025199999999999995, |
| 295 | "loss": 0.0908, |
| 296 | "step": 420 |
| 297 | }, |
| 298 | { |
| 299 | "epoch": 0.62, |
| 300 | "learning_rate": 0.000258, |
| 301 | "loss": 0.0918, |
| 302 | "step": 430 |
| 303 | }, |
| 304 | { |
| 305 | "epoch": 0.63, |
| 306 | "learning_rate": 0.00026399999999999997, |
| 307 | "loss": 0.0768, |
| 308 | "step": 440 |
| 309 | }, |
| 310 | { |
| 311 | "epoch": 0.65, |
| 312 | "learning_rate": 0.00027, |
| 313 | "loss": 0.0976, |
| 314 | "step": 450 |
| 315 | }, |
| 316 | { |
| 317 | "epoch": 0.66, |
| 318 | "learning_rate": 0.000276, |
| 319 | "loss": 0.1104, |
| 320 | "step": 460 |
| 321 | }, |
| 322 | { |
| 323 | "epoch": 0.68, |
| 324 | "learning_rate": 0.00028199999999999997, |
| 325 | "loss": 0.0866, |
| 326 | "step": 470 |
| 327 | }, |
| 328 | { |
| 329 | "epoch": 0.69, |
| 330 | "learning_rate": 0.00028799999999999995, |
| 331 | "loss": 0.1069, |
| 332 | "step": 480 |
| 333 | }, |
| 334 | { |
| 335 | "epoch": 0.7, |
| 336 | "learning_rate": 0.000294, |
| 337 | "loss": 0.0814, |
| 338 | "step": 490 |
| 339 | }, |
| 340 | { |
| 341 | "epoch": 0.72, |
| 342 | "learning_rate": 0.0003, |
| 343 | "loss": 0.087, |
| 344 | "step": 500 |
| 345 | }, |
| 346 | { |
| 347 | "epoch": 0.72, |
| 348 | "eval_loss": 0.19561158120632172, |
| 349 | "eval_runtime": 39.5545, |
| 350 | "eval_samples_per_second": 11.554, |
| 351 | "eval_steps_per_second": 1.466, |
| 352 | "eval_wer": 0.18732118656828792, |
| 353 | "step": 500 |
| 354 | }, |
| 355 | { |
| 356 | "epoch": 0.73, |
| 357 | "learning_rate": 0.0002999125364431487, |
| 358 | "loss": 0.1204, |
| 359 | "step": 510 |
| 360 | }, |
| 361 | { |
| 362 | "epoch": 0.75, |
| 363 | "learning_rate": 0.00029982507288629735, |
| 364 | "loss": 0.0861, |
| 365 | "step": 520 |
| 366 | }, |
| 367 | { |
| 368 | "epoch": 0.76, |
| 369 | "learning_rate": 0.00029973760932944606, |
| 370 | "loss": 0.1073, |
| 371 | "step": 530 |
| 372 | }, |
| 373 | { |
| 374 | "epoch": 0.78, |
| 375 | "learning_rate": 0.0002996501457725947, |
| 376 | "loss": 0.1028, |
| 377 | "step": 540 |
| 378 | }, |
| 379 | { |
| 380 | "epoch": 0.79, |
| 381 | "learning_rate": 0.0002995626822157434, |
| 382 | "loss": 0.087, |
| 383 | "step": 550 |
| 384 | }, |
| 385 | { |
| 386 | "epoch": 0.8, |
| 387 | "learning_rate": 0.0002994752186588921, |
| 388 | "loss": 0.1206, |
| 389 | "step": 560 |
| 390 | }, |
| 391 | { |
| 392 | "epoch": 0.82, |
| 393 | "learning_rate": 0.00029938775510204076, |
| 394 | "loss": 0.0949, |
| 395 | "step": 570 |
| 396 | }, |
| 397 | { |
| 398 | "epoch": 0.83, |
| 399 | "learning_rate": 0.0002993002915451895, |
| 400 | "loss": 0.1248, |
| 401 | "step": 580 |
| 402 | }, |
| 403 | { |
| 404 | "epoch": 0.85, |
| 405 | "learning_rate": 0.0002992128279883382, |
| 406 | "loss": 0.115, |
| 407 | "step": 590 |
| 408 | }, |
| 409 | { |
| 410 | "epoch": 0.86, |
| 411 | "learning_rate": 0.00029912536443148685, |
| 412 | "loss": 0.1038, |
| 413 | "step": 600 |
| 414 | }, |
| 415 | { |
| 416 | "epoch": 0.86, |
| 417 | "eval_loss": 0.2007717341184616, |
| 418 | "eval_runtime": 39.645, |
| 419 | "eval_samples_per_second": 11.527, |
| 420 | "eval_steps_per_second": 1.463, |
| 421 | "eval_wer": 0.18882698388796867, |
| 422 | "step": 600 |
| 423 | }, |
| 424 | { |
| 425 | "epoch": 0.88, |
| 426 | "learning_rate": 0.00029903790087463557, |
| 427 | "loss": 0.1188, |
| 428 | "step": 610 |
| 429 | }, |
| 430 | { |
| 431 | "epoch": 0.89, |
| 432 | "learning_rate": 0.00029895043731778423, |
| 433 | "loss": 0.097, |
| 434 | "step": 620 |
| 435 | }, |
| 436 | { |
| 437 | "epoch": 0.91, |
| 438 | "learning_rate": 0.00029886297376093294, |
| 439 | "loss": 0.097, |
| 440 | "step": 630 |
| 441 | }, |
| 442 | { |
| 443 | "epoch": 0.92, |
| 444 | "learning_rate": 0.0002987755102040816, |
| 445 | "loss": 0.1028, |
| 446 | "step": 640 |
| 447 | }, |
| 448 | { |
| 449 | "epoch": 0.93, |
| 450 | "learning_rate": 0.00029868804664723027, |
| 451 | "loss": 0.0929, |
| 452 | "step": 650 |
| 453 | }, |
| 454 | { |
| 455 | "epoch": 0.95, |
| 456 | "learning_rate": 0.000298600583090379, |
| 457 | "loss": 0.1155, |
| 458 | "step": 660 |
| 459 | }, |
| 460 | { |
| 461 | "epoch": 0.96, |
| 462 | "learning_rate": 0.00029851311953352764, |
| 463 | "loss": 0.1659, |
| 464 | "step": 670 |
| 465 | }, |
| 466 | { |
| 467 | "epoch": 0.98, |
| 468 | "learning_rate": 0.00029842565597667636, |
| 469 | "loss": 0.1001, |
| 470 | "step": 680 |
| 471 | }, |
| 472 | { |
| 473 | "epoch": 0.99, |
| 474 | "learning_rate": 0.00029833819241982507, |
| 475 | "loss": 0.1038, |
| 476 | "step": 690 |
| 477 | }, |
| 478 | { |
| 479 | "epoch": 1.01, |
| 480 | "learning_rate": 0.00029825072886297373, |
| 481 | "loss": 0.1149, |
| 482 | "step": 700 |
| 483 | }, |
| 484 | { |
| 485 | "epoch": 1.01, |
| 486 | "eval_loss": 0.21170839667320251, |
| 487 | "eval_runtime": 39.8933, |
| 488 | "eval_samples_per_second": 11.456, |
| 489 | "eval_steps_per_second": 1.454, |
| 490 | "eval_wer": 0.19876524619786176, |
| 491 | "step": 700 |
| 492 | }, |
| 493 | { |
| 494 | "epoch": 1.02, |
| 495 | "learning_rate": 0.00029816326530612245, |
| 496 | "loss": 0.1066, |
| 497 | "step": 710 |
| 498 | }, |
| 499 | { |
| 500 | "epoch": 1.03, |
| 501 | "learning_rate": 0.0002980758017492711, |
| 502 | "loss": 0.118, |
| 503 | "step": 720 |
| 504 | }, |
| 505 | { |
| 506 | "epoch": 1.05, |
| 507 | "learning_rate": 0.00029798833819241977, |
| 508 | "loss": 0.1548, |
| 509 | "step": 730 |
| 510 | }, |
| 511 | { |
| 512 | "epoch": 1.06, |
| 513 | "learning_rate": 0.0002979008746355685, |
| 514 | "loss": 0.1112, |
| 515 | "step": 740 |
| 516 | }, |
| 517 | { |
| 518 | "epoch": 1.08, |
| 519 | "learning_rate": 0.00029781341107871714, |
| 520 | "loss": 0.1176, |
| 521 | "step": 750 |
| 522 | }, |
| 523 | { |
| 524 | "epoch": 1.09, |
| 525 | "learning_rate": 0.00029772594752186586, |
| 526 | "loss": 0.1084, |
| 527 | "step": 760 |
| 528 | }, |
| 529 | { |
| 530 | "epoch": 1.11, |
| 531 | "learning_rate": 0.0002976384839650146, |
| 532 | "loss": 0.1014, |
| 533 | "step": 770 |
| 534 | }, |
| 535 | { |
| 536 | "epoch": 1.12, |
| 537 | "learning_rate": 0.00029755102040816323, |
| 538 | "loss": 0.1117, |
| 539 | "step": 780 |
| 540 | }, |
| 541 | { |
| 542 | "epoch": 1.14, |
| 543 | "learning_rate": 0.00029746355685131195, |
| 544 | "loss": 0.1001, |
| 545 | "step": 790 |
| 546 | }, |
| 547 | { |
| 548 | "epoch": 1.15, |
| 549 | "learning_rate": 0.0002973760932944606, |
| 550 | "loss": 0.1031, |
| 551 | "step": 800 |
| 552 | }, |
| 553 | { |
| 554 | "epoch": 1.15, |
| 555 | "eval_loss": 0.18768654763698578, |
| 556 | "eval_runtime": 39.7924, |
| 557 | "eval_samples_per_second": 11.485, |
| 558 | "eval_steps_per_second": 1.458, |
| 559 | "eval_wer": 0.18822466496009638, |
| 560 | "step": 800 |
| 561 | }, |
| 562 | { |
| 563 | "epoch": 1.16, |
| 564 | "learning_rate": 0.0002972886297376093, |
| 565 | "loss": 0.0994, |
| 566 | "step": 810 |
| 567 | }, |
| 568 | { |
| 569 | "epoch": 1.18, |
| 570 | "learning_rate": 0.000297201166180758, |
| 571 | "loss": 0.0947, |
| 572 | "step": 820 |
| 573 | }, |
| 574 | { |
| 575 | "epoch": 1.19, |
| 576 | "learning_rate": 0.00029711370262390665, |
| 577 | "loss": 0.1321, |
| 578 | "step": 830 |
| 579 | }, |
| 580 | { |
| 581 | "epoch": 1.21, |
| 582 | "learning_rate": 0.00029702623906705536, |
| 583 | "loss": 0.1205, |
| 584 | "step": 840 |
| 585 | }, |
| 586 | { |
| 587 | "epoch": 1.22, |
| 588 | "learning_rate": 0.0002969387755102041, |
| 589 | "loss": 0.1585, |
| 590 | "step": 850 |
| 591 | }, |
| 592 | { |
| 593 | "epoch": 1.24, |
| 594 | "learning_rate": 0.00029685131195335274, |
| 595 | "loss": 0.106, |
| 596 | "step": 860 |
| 597 | }, |
| 598 | { |
| 599 | "epoch": 1.25, |
| 600 | "learning_rate": 0.00029676384839650145, |
| 601 | "loss": 0.1093, |
| 602 | "step": 870 |
| 603 | }, |
| 604 | { |
| 605 | "epoch": 1.26, |
| 606 | "learning_rate": 0.0002966763848396501, |
| 607 | "loss": 0.1274, |
| 608 | "step": 880 |
| 609 | }, |
| 610 | { |
| 611 | "epoch": 1.28, |
| 612 | "learning_rate": 0.00029658892128279883, |
| 613 | "loss": 0.1058, |
| 614 | "step": 890 |
| 615 | }, |
| 616 | { |
| 617 | "epoch": 1.29, |
| 618 | "learning_rate": 0.0002965014577259475, |
| 619 | "loss": 0.1333, |
| 620 | "step": 900 |
| 621 | }, |
| 622 | { |
| 623 | "epoch": 1.29, |
| 624 | "eval_loss": 0.1909557580947876, |
| 625 | "eval_runtime": 39.5497, |
| 626 | "eval_samples_per_second": 11.555, |
| 627 | "eval_steps_per_second": 1.467, |
| 628 | "eval_wer": 0.19500075289865984, |
| 629 | "step": 900 |
| 630 | }, |
| 631 | { |
| 632 | "epoch": 1.31, |
| 633 | "learning_rate": 0.00029641399416909615, |
| 634 | "loss": 0.1212, |
| 635 | "step": 910 |
| 636 | }, |
| 637 | { |
| 638 | "epoch": 1.32, |
| 639 | "learning_rate": 0.00029632653061224487, |
| 640 | "loss": 0.1079, |
| 641 | "step": 920 |
| 642 | }, |
| 643 | { |
| 644 | "epoch": 1.34, |
| 645 | "learning_rate": 0.0002962390670553935, |
| 646 | "loss": 0.1354, |
| 647 | "step": 930 |
| 648 | }, |
| 649 | { |
| 650 | "epoch": 1.35, |
| 651 | "learning_rate": 0.00029615160349854224, |
| 652 | "loss": 0.0998, |
| 653 | "step": 940 |
| 654 | }, |
| 655 | { |
| 656 | "epoch": 1.36, |
| 657 | "learning_rate": 0.00029606413994169096, |
| 658 | "loss": 0.105, |
| 659 | "step": 950 |
| 660 | }, |
| 661 | { |
| 662 | "epoch": 1.38, |
| 663 | "learning_rate": 0.0002959766763848396, |
| 664 | "loss": 0.1337, |
| 665 | "step": 960 |
| 666 | }, |
| 667 | { |
| 668 | "epoch": 1.39, |
| 669 | "learning_rate": 0.00029588921282798833, |
| 670 | "loss": 0.0865, |
| 671 | "step": 970 |
| 672 | }, |
| 673 | { |
| 674 | "epoch": 1.41, |
| 675 | "learning_rate": 0.000295801749271137, |
| 676 | "loss": 0.1259, |
| 677 | "step": 980 |
| 678 | }, |
| 679 | { |
| 680 | "epoch": 1.42, |
| 681 | "learning_rate": 0.0002957142857142857, |
| 682 | "loss": 0.1159, |
| 683 | "step": 990 |
| 684 | }, |
| 685 | { |
| 686 | "epoch": 1.44, |
| 687 | "learning_rate": 0.00029562682215743437, |
| 688 | "loss": 0.1086, |
| 689 | "step": 1000 |
| 690 | }, |
| 691 | { |
| 692 | "epoch": 1.44, |
| 693 | "eval_loss": 0.19512739777565002, |
| 694 | "eval_runtime": 39.4175, |
| 695 | "eval_samples_per_second": 11.594, |
| 696 | "eval_steps_per_second": 1.471, |
| 697 | "eval_wer": 0.2017768408372233, |
| 698 | "step": 1000 |
| 699 | }, |
| 700 | { |
| 701 | "epoch": 1.45, |
| 702 | "learning_rate": 0.00029553935860058303, |
| 703 | "loss": 0.119, |
| 704 | "step": 1010 |
| 705 | }, |
| 706 | { |
| 707 | "epoch": 1.47, |
| 708 | "learning_rate": 0.00029545189504373174, |
| 709 | "loss": 0.1213, |
| 710 | "step": 1020 |
| 711 | }, |
| 712 | { |
| 713 | "epoch": 1.48, |
| 714 | "learning_rate": 0.00029536443148688046, |
| 715 | "loss": 0.1069, |
| 716 | "step": 1030 |
| 717 | }, |
| 718 | { |
| 719 | "epoch": 1.49, |
| 720 | "learning_rate": 0.0002952769679300291, |
| 721 | "loss": 0.1051, |
| 722 | "step": 1040 |
| 723 | }, |
| 724 | { |
| 725 | "epoch": 1.51, |
| 726 | "learning_rate": 0.00029518950437317784, |
| 727 | "loss": 0.1337, |
| 728 | "step": 1050 |
| 729 | }, |
| 730 | { |
| 731 | "epoch": 1.52, |
| 732 | "learning_rate": 0.0002951020408163265, |
| 733 | "loss": 0.1232, |
| 734 | "step": 1060 |
| 735 | }, |
| 736 | { |
| 737 | "epoch": 1.54, |
| 738 | "learning_rate": 0.0002950145772594752, |
| 739 | "loss": 0.1016, |
| 740 | "step": 1070 |
| 741 | }, |
| 742 | { |
| 743 | "epoch": 1.55, |
| 744 | "learning_rate": 0.00029492711370262387, |
| 745 | "loss": 0.1196, |
| 746 | "step": 1080 |
| 747 | }, |
| 748 | { |
| 749 | "epoch": 1.57, |
| 750 | "learning_rate": 0.00029483965014577253, |
| 751 | "loss": 0.1081, |
| 752 | "step": 1090 |
| 753 | }, |
| 754 | { |
| 755 | "epoch": 1.58, |
| 756 | "learning_rate": 0.00029475218658892125, |
| 757 | "loss": 0.1025, |
| 758 | "step": 1100 |
| 759 | }, |
| 760 | { |
| 761 | "epoch": 1.58, |
| 762 | "eval_loss": 0.1834399253129959, |
| 763 | "eval_runtime": 39.434, |
| 764 | "eval_samples_per_second": 11.589, |
| 765 | "eval_steps_per_second": 1.471, |
| 766 | "eval_wer": 0.19469959343472368, |
| 767 | "step": 1100 |
| 768 | }, |
| 769 | { |
| 770 | "epoch": 1.59, |
| 771 | "learning_rate": 0.00029466472303206996, |
| 772 | "loss": 0.1053, |
| 773 | "step": 1110 |
| 774 | }, |
| 775 | { |
| 776 | "epoch": 1.61, |
| 777 | "learning_rate": 0.0002945772594752186, |
| 778 | "loss": 0.0881, |
| 779 | "step": 1120 |
| 780 | }, |
| 781 | { |
| 782 | "epoch": 1.62, |
| 783 | "learning_rate": 0.00029448979591836734, |
| 784 | "loss": 0.129, |
| 785 | "step": 1130 |
| 786 | }, |
| 787 | { |
| 788 | "epoch": 1.64, |
| 789 | "learning_rate": 0.000294402332361516, |
| 790 | "loss": 0.0928, |
| 791 | "step": 1140 |
| 792 | }, |
| 793 | { |
| 794 | "epoch": 1.65, |
| 795 | "learning_rate": 0.0002943148688046647, |
| 796 | "loss": 0.1065, |
| 797 | "step": 1150 |
| 798 | }, |
| 799 | { |
| 800 | "epoch": 1.67, |
| 801 | "learning_rate": 0.0002942274052478134, |
| 802 | "loss": 0.1062, |
| 803 | "step": 1160 |
| 804 | }, |
| 805 | { |
| 806 | "epoch": 1.68, |
| 807 | "learning_rate": 0.0002941399416909621, |
| 808 | "loss": 0.0941, |
| 809 | "step": 1170 |
| 810 | }, |
| 811 | { |
| 812 | "epoch": 1.7, |
| 813 | "learning_rate": 0.00029405247813411075, |
| 814 | "loss": 0.1117, |
| 815 | "step": 1180 |
| 816 | }, |
| 817 | { |
| 818 | "epoch": 1.71, |
| 819 | "learning_rate": 0.00029396501457725947, |
| 820 | "loss": 0.087, |
| 821 | "step": 1190 |
| 822 | }, |
| 823 | { |
| 824 | "epoch": 1.72, |
| 825 | "learning_rate": 0.0002938775510204081, |
| 826 | "loss": 0.137, |
| 827 | "step": 1200 |
| 828 | }, |
| 829 | { |
| 830 | "epoch": 1.72, |
| 831 | "eval_loss": 0.18502399325370789, |
| 832 | "eval_runtime": 39.3835, |
| 833 | "eval_samples_per_second": 11.604, |
| 834 | "eval_steps_per_second": 1.473, |
| 835 | "eval_wer": 0.1925914771871706, |
| 836 | "step": 1200 |
| 837 | }, |
| 838 | { |
| 839 | "epoch": 1.74, |
| 840 | "learning_rate": 0.00029379008746355684, |
| 841 | "loss": 0.1106, |
| 842 | "step": 1210 |
| 843 | }, |
| 844 | { |
| 845 | "epoch": 1.75, |
| 846 | "learning_rate": 0.0002937026239067055, |
| 847 | "loss": 0.0867, |
| 848 | "step": 1220 |
| 849 | }, |
| 850 | { |
| 851 | "epoch": 1.77, |
| 852 | "learning_rate": 0.0002936151603498542, |
| 853 | "loss": 0.1207, |
| 854 | "step": 1230 |
| 855 | }, |
| 856 | { |
| 857 | "epoch": 1.78, |
| 858 | "learning_rate": 0.0002935276967930029, |
| 859 | "loss": 0.1277, |
| 860 | "step": 1240 |
| 861 | }, |
| 862 | { |
| 863 | "epoch": 1.8, |
| 864 | "learning_rate": 0.0002934402332361516, |
| 865 | "loss": 0.1125, |
| 866 | "step": 1250 |
| 867 | }, |
| 868 | { |
| 869 | "epoch": 1.81, |
| 870 | "learning_rate": 0.0002933527696793003, |
| 871 | "loss": 0.1062, |
| 872 | "step": 1260 |
| 873 | }, |
| 874 | { |
| 875 | "epoch": 1.82, |
| 876 | "learning_rate": 0.0002932653061224489, |
| 877 | "loss": 0.0973, |
| 878 | "step": 1270 |
| 879 | }, |
| 880 | { |
| 881 | "epoch": 1.84, |
| 882 | "learning_rate": 0.00029317784256559763, |
| 883 | "loss": 0.124, |
| 884 | "step": 1280 |
| 885 | }, |
| 886 | { |
| 887 | "epoch": 1.85, |
| 888 | "learning_rate": 0.00029309037900874634, |
| 889 | "loss": 0.0987, |
| 890 | "step": 1290 |
| 891 | }, |
| 892 | { |
| 893 | "epoch": 1.87, |
| 894 | "learning_rate": 0.000293002915451895, |
| 895 | "loss": 0.1062, |
| 896 | "step": 1300 |
| 897 | }, |
| 898 | { |
| 899 | "epoch": 1.87, |
| 900 | "eval_loss": 0.17643560469150543, |
| 901 | "eval_runtime": 39.5145, |
| 902 | "eval_samples_per_second": 11.565, |
| 903 | "eval_steps_per_second": 1.468, |
| 904 | "eval_wer": 0.18837524469206446, |
| 905 | "step": 1300 |
| 906 | }, |
| 907 | { |
| 908 | "epoch": 1.88, |
| 909 | "learning_rate": 0.0002929154518950437, |
| 910 | "loss": 0.1073, |
| 911 | "step": 1310 |
| 912 | }, |
| 913 | { |
| 914 | "epoch": 1.9, |
| 915 | "learning_rate": 0.0002928279883381924, |
| 916 | "loss": 0.0911, |
| 917 | "step": 1320 |
| 918 | }, |
| 919 | { |
| 920 | "epoch": 1.91, |
| 921 | "learning_rate": 0.0002927405247813411, |
| 922 | "loss": 0.1032, |
| 923 | "step": 1330 |
| 924 | }, |
| 925 | { |
| 926 | "epoch": 1.93, |
| 927 | "learning_rate": 0.00029265306122448976, |
| 928 | "loss": 0.1205, |
| 929 | "step": 1340 |
| 930 | }, |
| 931 | { |
| 932 | "epoch": 1.94, |
| 933 | "learning_rate": 0.00029256559766763847, |
| 934 | "loss": 0.1096, |
| 935 | "step": 1350 |
| 936 | }, |
| 937 | { |
| 938 | "epoch": 1.95, |
| 939 | "learning_rate": 0.00029247813411078713, |
| 940 | "loss": 0.11, |
| 941 | "step": 1360 |
| 942 | }, |
| 943 | { |
| 944 | "epoch": 1.97, |
| 945 | "learning_rate": 0.00029239067055393585, |
| 946 | "loss": 0.1194, |
| 947 | "step": 1370 |
| 948 | }, |
| 949 | { |
| 950 | "epoch": 1.98, |
| 951 | "learning_rate": 0.0002923032069970845, |
| 952 | "loss": 0.1052, |
| 953 | "step": 1380 |
| 954 | }, |
| 955 | { |
| 956 | "epoch": 2.0, |
| 957 | "learning_rate": 0.0002922157434402332, |
| 958 | "loss": 0.1039, |
| 959 | "step": 1390 |
| 960 | }, |
| 961 | { |
| 962 | "epoch": 2.01, |
| 963 | "learning_rate": 0.0002921282798833819, |
| 964 | "loss": 0.1321, |
| 965 | "step": 1400 |
| 966 | }, |
| 967 | { |
| 968 | "epoch": 2.01, |
| 969 | "eval_loss": 0.1891152262687683, |
| 970 | "eval_runtime": 39.7053, |
| 971 | "eval_samples_per_second": 11.51, |
| 972 | "eval_steps_per_second": 1.461, |
| 973 | "eval_wer": 0.18912814335190484, |
| 974 | "step": 1400 |
| 975 | }, |
| 976 | { |
| 977 | "epoch": 2.03, |
| 978 | "learning_rate": 0.0002920408163265306, |
| 979 | "loss": 0.1047, |
| 980 | "step": 1410 |
| 981 | }, |
| 982 | { |
| 983 | "epoch": 2.04, |
| 984 | "learning_rate": 0.00029195335276967926, |
| 985 | "loss": 0.1019, |
| 986 | "step": 1420 |
| 987 | }, |
| 988 | { |
| 989 | "epoch": 2.05, |
| 990 | "learning_rate": 0.000291865889212828, |
| 991 | "loss": 0.1235, |
| 992 | "step": 1430 |
| 993 | }, |
| 994 | { |
| 995 | "epoch": 2.07, |
| 996 | "learning_rate": 0.0002917784256559767, |
| 997 | "loss": 0.1034, |
| 998 | "step": 1440 |
| 999 | }, |
| 1000 | { |
| 1001 | "epoch": 2.08, |
| 1002 | "learning_rate": 0.00029169096209912535, |
| 1003 | "loss": 0.1205, |
| 1004 | "step": 1450 |
| 1005 | }, |
| 1006 | { |
| 1007 | "epoch": 2.1, |
| 1008 | "learning_rate": 0.000291603498542274, |
| 1009 | "loss": 0.1044, |
| 1010 | "step": 1460 |
| 1011 | }, |
| 1012 | { |
| 1013 | "epoch": 2.11, |
| 1014 | "learning_rate": 0.0002915160349854227, |
| 1015 | "loss": 0.0894, |
| 1016 | "step": 1470 |
| 1017 | }, |
| 1018 | { |
| 1019 | "epoch": 2.13, |
| 1020 | "learning_rate": 0.00029143731778425656, |
| 1021 | "loss": 0.1223, |
| 1022 | "step": 1480 |
| 1023 | }, |
| 1024 | { |
| 1025 | "epoch": 2.14, |
| 1026 | "learning_rate": 0.0002913498542274052, |
| 1027 | "loss": 0.0766, |
| 1028 | "step": 1490 |
| 1029 | }, |
| 1030 | { |
| 1031 | "epoch": 2.16, |
| 1032 | "learning_rate": 0.00029126239067055394, |
| 1033 | "loss": 0.1328, |
| 1034 | "step": 1500 |
| 1035 | }, |
| 1036 | { |
| 1037 | "epoch": 2.16, |
| 1038 | "eval_loss": 0.1817779541015625, |
| 1039 | "eval_runtime": 39.602, |
| 1040 | "eval_samples_per_second": 11.54, |
| 1041 | "eval_steps_per_second": 1.465, |
| 1042 | "eval_wer": 0.18717060683631984, |
| 1043 | "step": 1500 |
| 1044 | }, |
| 1045 | { |
| 1046 | "epoch": 2.17, |
| 1047 | "learning_rate": 0.0002911749271137026, |
| 1048 | "loss": 0.0977, |
| 1049 | "step": 1510 |
| 1050 | }, |
| 1051 | { |
| 1052 | "epoch": 2.18, |
| 1053 | "learning_rate": 0.00029108746355685126, |
| 1054 | "loss": 0.0956, |
| 1055 | "step": 1520 |
| 1056 | }, |
| 1057 | { |
| 1058 | "epoch": 2.2, |
| 1059 | "learning_rate": 0.00029099999999999997, |
| 1060 | "loss": 0.1013, |
| 1061 | "step": 1530 |
| 1062 | }, |
| 1063 | { |
| 1064 | "epoch": 2.21, |
| 1065 | "learning_rate": 0.00029091253644314863, |
| 1066 | "loss": 0.0918, |
| 1067 | "step": 1540 |
| 1068 | }, |
| 1069 | { |
| 1070 | "epoch": 2.23, |
| 1071 | "learning_rate": 0.00029082507288629735, |
| 1072 | "loss": 0.1058, |
| 1073 | "step": 1550 |
| 1074 | }, |
| 1075 | { |
| 1076 | "epoch": 2.24, |
| 1077 | "learning_rate": 0.00029073760932944606, |
| 1078 | "loss": 0.0987, |
| 1079 | "step": 1560 |
| 1080 | }, |
| 1081 | { |
| 1082 | "epoch": 2.26, |
| 1083 | "learning_rate": 0.0002906501457725947, |
| 1084 | "loss": 0.0973, |
| 1085 | "step": 1570 |
| 1086 | }, |
| 1087 | { |
| 1088 | "epoch": 2.27, |
| 1089 | "learning_rate": 0.00029056268221574344, |
| 1090 | "loss": 0.0959, |
| 1091 | "step": 1580 |
| 1092 | }, |
| 1093 | { |
| 1094 | "epoch": 2.28, |
| 1095 | "learning_rate": 0.0002904752186588921, |
| 1096 | "loss": 0.0975, |
| 1097 | "step": 1590 |
| 1098 | }, |
| 1099 | { |
| 1100 | "epoch": 2.3, |
| 1101 | "learning_rate": 0.00029038775510204076, |
| 1102 | "loss": 0.1008, |
| 1103 | "step": 1600 |
| 1104 | }, |
| 1105 | { |
| 1106 | "epoch": 2.3, |
| 1107 | "eval_loss": 0.172745481133461, |
| 1108 | "eval_runtime": 39.676, |
| 1109 | "eval_samples_per_second": 11.518, |
| 1110 | "eval_steps_per_second": 1.462, |
| 1111 | "eval_wer": 0.18988104201174522, |
| 1112 | "step": 1600 |
| 1113 | }, |
| 1114 | { |
| 1115 | "epoch": 2.31, |
| 1116 | "learning_rate": 0.0002903002915451895, |
| 1117 | "loss": 0.0855, |
| 1118 | "step": 1610 |
| 1119 | }, |
| 1120 | { |
| 1121 | "epoch": 2.33, |
| 1122 | "learning_rate": 0.00029021282798833814, |
| 1123 | "loss": 0.098, |
| 1124 | "step": 1620 |
| 1125 | }, |
| 1126 | { |
| 1127 | "epoch": 2.34, |
| 1128 | "learning_rate": 0.00029012536443148685, |
| 1129 | "loss": 0.0943, |
| 1130 | "step": 1630 |
| 1131 | }, |
| 1132 | { |
| 1133 | "epoch": 2.36, |
| 1134 | "learning_rate": 0.00029003790087463557, |
| 1135 | "loss": 0.0767, |
| 1136 | "step": 1640 |
| 1137 | }, |
| 1138 | { |
| 1139 | "epoch": 2.37, |
| 1140 | "learning_rate": 0.0002899504373177842, |
| 1141 | "loss": 0.1074, |
| 1142 | "step": 1650 |
| 1143 | }, |
| 1144 | { |
| 1145 | "epoch": 2.39, |
| 1146 | "learning_rate": 0.00028986297376093294, |
| 1147 | "loss": 0.103, |
| 1148 | "step": 1660 |
| 1149 | }, |
| 1150 | { |
| 1151 | "epoch": 2.4, |
| 1152 | "learning_rate": 0.0002897755102040816, |
| 1153 | "loss": 0.1019, |
| 1154 | "step": 1670 |
| 1155 | }, |
| 1156 | { |
| 1157 | "epoch": 2.41, |
| 1158 | "learning_rate": 0.0002896880466472303, |
| 1159 | "loss": 0.1072, |
| 1160 | "step": 1680 |
| 1161 | }, |
| 1162 | { |
| 1163 | "epoch": 2.43, |
| 1164 | "learning_rate": 0.000289600583090379, |
| 1165 | "loss": 0.1117, |
| 1166 | "step": 1690 |
| 1167 | }, |
| 1168 | { |
| 1169 | "epoch": 2.44, |
| 1170 | "learning_rate": 0.00028951311953352764, |
| 1171 | "loss": 0.1097, |
| 1172 | "step": 1700 |
| 1173 | }, |
| 1174 | { |
| 1175 | "epoch": 2.44, |
| 1176 | "eval_loss": 0.17900413274765015, |
| 1177 | "eval_runtime": 39.672, |
| 1178 | "eval_samples_per_second": 11.519, |
| 1179 | "eval_steps_per_second": 1.462, |
| 1180 | "eval_wer": 0.19153741906339405, |
| 1181 | "step": 1700 |
| 1182 | }, |
| 1183 | { |
| 1184 | "epoch": 2.46, |
| 1185 | "learning_rate": 0.00028942565597667635, |
| 1186 | "loss": 0.086, |
| 1187 | "step": 1710 |
| 1188 | }, |
| 1189 | { |
| 1190 | "epoch": 2.47, |
| 1191 | "learning_rate": 0.00028933819241982507, |
| 1192 | "loss": 0.0891, |
| 1193 | "step": 1720 |
| 1194 | }, |
| 1195 | { |
| 1196 | "epoch": 2.49, |
| 1197 | "learning_rate": 0.00028925072886297373, |
| 1198 | "loss": 0.0871, |
| 1199 | "step": 1730 |
| 1200 | }, |
| 1201 | { |
| 1202 | "epoch": 2.5, |
| 1203 | "learning_rate": 0.00028916326530612244, |
| 1204 | "loss": 0.0927, |
| 1205 | "step": 1740 |
| 1206 | }, |
| 1207 | { |
| 1208 | "epoch": 2.51, |
| 1209 | "learning_rate": 0.0002890758017492711, |
| 1210 | "loss": 0.1066, |
| 1211 | "step": 1750 |
| 1212 | }, |
| 1213 | { |
| 1214 | "epoch": 2.53, |
| 1215 | "learning_rate": 0.0002889883381924198, |
| 1216 | "loss": 0.0864, |
| 1217 | "step": 1760 |
| 1218 | }, |
| 1219 | { |
| 1220 | "epoch": 2.54, |
| 1221 | "learning_rate": 0.0002889008746355685, |
| 1222 | "loss": 0.0953, |
| 1223 | "step": 1770 |
| 1224 | }, |
| 1225 | { |
| 1226 | "epoch": 2.56, |
| 1227 | "learning_rate": 0.00028881341107871714, |
| 1228 | "loss": 0.0818, |
| 1229 | "step": 1780 |
| 1230 | }, |
| 1231 | { |
| 1232 | "epoch": 2.57, |
| 1233 | "learning_rate": 0.00028872594752186586, |
| 1234 | "loss": 0.0872, |
| 1235 | "step": 1790 |
| 1236 | }, |
| 1237 | { |
| 1238 | "epoch": 2.59, |
| 1239 | "learning_rate": 0.0002886384839650145, |
| 1240 | "loss": 0.1117, |
| 1241 | "step": 1800 |
| 1242 | }, |
| 1243 | { |
| 1244 | "epoch": 2.59, |
| 1245 | "eval_loss": 0.17877764999866486, |
| 1246 | "eval_runtime": 39.5526, |
| 1247 | "eval_samples_per_second": 11.554, |
| 1248 | "eval_steps_per_second": 1.466, |
| 1249 | "eval_wer": 0.1925914771871706, |
| 1250 | "step": 1800 |
| 1251 | }, |
| 1252 | { |
| 1253 | "epoch": 2.6, |
| 1254 | "learning_rate": 0.00028855102040816323, |
| 1255 | "loss": 0.0963, |
| 1256 | "step": 1810 |
| 1257 | }, |
| 1258 | { |
| 1259 | "epoch": 2.61, |
| 1260 | "learning_rate": 0.00028846355685131195, |
| 1261 | "loss": 0.1027, |
| 1262 | "step": 1820 |
| 1263 | }, |
| 1264 | { |
| 1265 | "epoch": 2.63, |
| 1266 | "learning_rate": 0.0002883760932944606, |
| 1267 | "loss": 0.1048, |
| 1268 | "step": 1830 |
| 1269 | }, |
| 1270 | { |
| 1271 | "epoch": 2.64, |
| 1272 | "learning_rate": 0.0002882886297376093, |
| 1273 | "loss": 0.0812, |
| 1274 | "step": 1840 |
| 1275 | }, |
| 1276 | { |
| 1277 | "epoch": 2.66, |
| 1278 | "learning_rate": 0.000288201166180758, |
| 1279 | "loss": 0.1138, |
| 1280 | "step": 1850 |
| 1281 | }, |
| 1282 | { |
| 1283 | "epoch": 2.67, |
| 1284 | "learning_rate": 0.0002881137026239067, |
| 1285 | "loss": 0.0991, |
| 1286 | "step": 1860 |
| 1287 | }, |
| 1288 | { |
| 1289 | "epoch": 2.69, |
| 1290 | "learning_rate": 0.00028802623906705536, |
| 1291 | "loss": 0.11, |
| 1292 | "step": 1870 |
| 1293 | }, |
| 1294 | { |
| 1295 | "epoch": 2.7, |
| 1296 | "learning_rate": 0.000287938775510204, |
| 1297 | "loss": 0.1228, |
| 1298 | "step": 1880 |
| 1299 | }, |
| 1300 | { |
| 1301 | "epoch": 2.72, |
| 1302 | "learning_rate": 0.00028785131195335274, |
| 1303 | "loss": 0.0913, |
| 1304 | "step": 1890 |
| 1305 | }, |
| 1306 | { |
| 1307 | "epoch": 2.73, |
| 1308 | "learning_rate": 0.00028776384839650145, |
| 1309 | "loss": 0.1088, |
| 1310 | "step": 1900 |
| 1311 | }, |
| 1312 | { |
| 1313 | "epoch": 2.73, |
| 1314 | "eval_loss": 0.17957444489002228, |
| 1315 | "eval_runtime": 39.6133, |
| 1316 | "eval_samples_per_second": 11.537, |
| 1317 | "eval_steps_per_second": 1.464, |
| 1318 | "eval_wer": 0.17918988104201175, |
| 1319 | "step": 1900 |
| 1320 | }, |
| 1321 | { |
| 1322 | "epoch": 2.74, |
| 1323 | "learning_rate": 0.0002876763848396501, |
| 1324 | "loss": 0.0987, |
| 1325 | "step": 1910 |
| 1326 | }, |
| 1327 | { |
| 1328 | "epoch": 2.76, |
| 1329 | "learning_rate": 0.0002875889212827988, |
| 1330 | "loss": 0.1139, |
| 1331 | "step": 1920 |
| 1332 | }, |
| 1333 | { |
| 1334 | "epoch": 2.77, |
| 1335 | "learning_rate": 0.0002875014577259475, |
| 1336 | "loss": 0.1016, |
| 1337 | "step": 1930 |
| 1338 | }, |
| 1339 | { |
| 1340 | "epoch": 2.79, |
| 1341 | "learning_rate": 0.0002874139941690962, |
| 1342 | "loss": 0.0882, |
| 1343 | "step": 1940 |
| 1344 | }, |
| 1345 | { |
| 1346 | "epoch": 2.8, |
| 1347 | "learning_rate": 0.00028732653061224486, |
| 1348 | "loss": 0.1073, |
| 1349 | "step": 1950 |
| 1350 | }, |
| 1351 | { |
| 1352 | "epoch": 2.82, |
| 1353 | "learning_rate": 0.0002872390670553935, |
| 1354 | "loss": 0.0956, |
| 1355 | "step": 1960 |
| 1356 | }, |
| 1357 | { |
| 1358 | "epoch": 2.83, |
| 1359 | "learning_rate": 0.00028715160349854224, |
| 1360 | "loss": 0.0834, |
| 1361 | "step": 1970 |
| 1362 | }, |
| 1363 | { |
| 1364 | "epoch": 2.84, |
| 1365 | "learning_rate": 0.00028706413994169095, |
| 1366 | "loss": 0.1044, |
| 1367 | "step": 1980 |
| 1368 | }, |
| 1369 | { |
| 1370 | "epoch": 2.86, |
| 1371 | "learning_rate": 0.0002869766763848396, |
| 1372 | "loss": 0.0842, |
| 1373 | "step": 1990 |
| 1374 | }, |
| 1375 | { |
| 1376 | "epoch": 2.87, |
| 1377 | "learning_rate": 0.00028688921282798833, |
| 1378 | "loss": 0.1192, |
| 1379 | "step": 2000 |
| 1380 | }, |
| 1381 | { |
| 1382 | "epoch": 2.87, |
| 1383 | "eval_loss": 0.17964738607406616, |
| 1384 | "eval_runtime": 39.5923, |
| 1385 | "eval_samples_per_second": 11.543, |
| 1386 | "eval_steps_per_second": 1.465, |
| 1387 | "eval_wer": 0.1900316217437133, |
| 1388 | "step": 2000 |
| 1389 | }, |
| 1390 | { |
| 1391 | "epoch": 2.89, |
| 1392 | "learning_rate": 0.000286801749271137, |
| 1393 | "loss": 0.0993, |
| 1394 | "step": 2010 |
| 1395 | }, |
| 1396 | { |
| 1397 | "epoch": 2.9, |
| 1398 | "learning_rate": 0.0002867142857142857, |
| 1399 | "loss": 0.0792, |
| 1400 | "step": 2020 |
| 1401 | }, |
| 1402 | { |
| 1403 | "epoch": 2.92, |
| 1404 | "learning_rate": 0.00028662682215743437, |
| 1405 | "loss": 0.0904, |
| 1406 | "step": 2030 |
| 1407 | }, |
| 1408 | { |
| 1409 | "epoch": 2.93, |
| 1410 | "learning_rate": 0.0002865393586005831, |
| 1411 | "loss": 0.0849, |
| 1412 | "step": 2040 |
| 1413 | }, |
| 1414 | { |
| 1415 | "epoch": 2.95, |
| 1416 | "learning_rate": 0.00028645189504373174, |
| 1417 | "loss": 0.109, |
| 1418 | "step": 2050 |
| 1419 | }, |
| 1420 | { |
| 1421 | "epoch": 2.96, |
| 1422 | "learning_rate": 0.0002863644314868804, |
| 1423 | "loss": 0.0976, |
| 1424 | "step": 2060 |
| 1425 | }, |
| 1426 | { |
| 1427 | "epoch": 2.97, |
| 1428 | "learning_rate": 0.0002862769679300291, |
| 1429 | "loss": 0.1072, |
| 1430 | "step": 2070 |
| 1431 | }, |
| 1432 | { |
| 1433 | "epoch": 2.99, |
| 1434 | "learning_rate": 0.00028618950437317783, |
| 1435 | "loss": 0.0885, |
| 1436 | "step": 2080 |
| 1437 | }, |
| 1438 | { |
| 1439 | "epoch": 3.0, |
| 1440 | "learning_rate": 0.0002861020408163265, |
| 1441 | "loss": 0.0931, |
| 1442 | "step": 2090 |
| 1443 | }, |
| 1444 | { |
| 1445 | "epoch": 3.02, |
| 1446 | "learning_rate": 0.0002860145772594752, |
| 1447 | "loss": 0.1131, |
| 1448 | "step": 2100 |
| 1449 | }, |
| 1450 | { |
| 1451 | "epoch": 3.02, |
| 1452 | "eval_loss": 0.1814257949590683, |
| 1453 | "eval_runtime": 39.7474, |
| 1454 | "eval_samples_per_second": 11.498, |
| 1455 | "eval_steps_per_second": 1.459, |
| 1456 | "eval_wer": 0.18355669326908597, |
| 1457 | "step": 2100 |
| 1458 | }, |
| 1459 | { |
| 1460 | "epoch": 3.03, |
| 1461 | "learning_rate": 0.00028592711370262387, |
| 1462 | "loss": 0.0937, |
| 1463 | "step": 2110 |
| 1464 | }, |
| 1465 | { |
| 1466 | "epoch": 3.05, |
| 1467 | "learning_rate": 0.0002858396501457726, |
| 1468 | "loss": 0.126, |
| 1469 | "step": 2120 |
| 1470 | }, |
| 1471 | { |
| 1472 | "epoch": 3.06, |
| 1473 | "learning_rate": 0.00028575218658892125, |
| 1474 | "loss": 0.0868, |
| 1475 | "step": 2130 |
| 1476 | }, |
| 1477 | { |
| 1478 | "epoch": 3.07, |
| 1479 | "learning_rate": 0.0002856647230320699, |
| 1480 | "loss": 0.0902, |
| 1481 | "step": 2140 |
| 1482 | }, |
| 1483 | { |
| 1484 | "epoch": 3.09, |
| 1485 | "learning_rate": 0.0002855772594752186, |
| 1486 | "loss": 0.0938, |
| 1487 | "step": 2150 |
| 1488 | }, |
| 1489 | { |
| 1490 | "epoch": 3.1, |
| 1491 | "learning_rate": 0.00028548979591836734, |
| 1492 | "loss": 0.0834, |
| 1493 | "step": 2160 |
| 1494 | }, |
| 1495 | { |
| 1496 | "epoch": 3.12, |
| 1497 | "learning_rate": 0.000285402332361516, |
| 1498 | "loss": 0.1019, |
| 1499 | "step": 2170 |
| 1500 | }, |
| 1501 | { |
| 1502 | "epoch": 3.13, |
| 1503 | "learning_rate": 0.0002853148688046647, |
| 1504 | "loss": 0.0826, |
| 1505 | "step": 2180 |
| 1506 | }, |
| 1507 | { |
| 1508 | "epoch": 3.15, |
| 1509 | "learning_rate": 0.0002852274052478134, |
| 1510 | "loss": 0.0969, |
| 1511 | "step": 2190 |
| 1512 | }, |
| 1513 | { |
| 1514 | "epoch": 3.16, |
| 1515 | "learning_rate": 0.0002851399416909621, |
| 1516 | "loss": 0.1054, |
| 1517 | "step": 2200 |
| 1518 | }, |
| 1519 | { |
| 1520 | "epoch": 3.16, |
| 1521 | "eval_loss": 0.1734437644481659, |
| 1522 | "eval_runtime": 39.7519, |
| 1523 | "eval_samples_per_second": 11.496, |
| 1524 | "eval_steps_per_second": 1.459, |
| 1525 | "eval_wer": 0.1794910405059479, |
| 1526 | "step": 2200 |
| 1527 | }, |
| 1528 | { |
| 1529 | "epoch": 3.18, |
| 1530 | "learning_rate": 0.00028505247813411075, |
| 1531 | "loss": 0.0836, |
| 1532 | "step": 2210 |
| 1533 | }, |
| 1534 | { |
| 1535 | "epoch": 3.19, |
| 1536 | "learning_rate": 0.00028496501457725946, |
| 1537 | "loss": 0.1054, |
| 1538 | "step": 2220 |
| 1539 | }, |
| 1540 | { |
| 1541 | "epoch": 3.2, |
| 1542 | "learning_rate": 0.0002848775510204081, |
| 1543 | "loss": 0.0864, |
| 1544 | "step": 2230 |
| 1545 | }, |
| 1546 | { |
| 1547 | "epoch": 3.22, |
| 1548 | "learning_rate": 0.00028479008746355684, |
| 1549 | "loss": 0.105, |
| 1550 | "step": 2240 |
| 1551 | }, |
| 1552 | { |
| 1553 | "epoch": 3.23, |
| 1554 | "learning_rate": 0.0002847026239067055, |
| 1555 | "loss": 0.104, |
| 1556 | "step": 2250 |
| 1557 | }, |
| 1558 | { |
| 1559 | "epoch": 3.25, |
| 1560 | "learning_rate": 0.0002846151603498542, |
| 1561 | "loss": 0.1042, |
| 1562 | "step": 2260 |
| 1563 | }, |
| 1564 | { |
| 1565 | "epoch": 3.26, |
| 1566 | "learning_rate": 0.0002845276967930029, |
| 1567 | "loss": 0.1108, |
| 1568 | "step": 2270 |
| 1569 | }, |
| 1570 | { |
| 1571 | "epoch": 3.28, |
| 1572 | "learning_rate": 0.0002844402332361516, |
| 1573 | "loss": 0.1239, |
| 1574 | "step": 2280 |
| 1575 | }, |
| 1576 | { |
| 1577 | "epoch": 3.29, |
| 1578 | "learning_rate": 0.00028435276967930025, |
| 1579 | "loss": 0.0847, |
| 1580 | "step": 2290 |
| 1581 | }, |
| 1582 | { |
| 1583 | "epoch": 3.3, |
| 1584 | "learning_rate": 0.00028426530612244897, |
| 1585 | "loss": 0.1043, |
| 1586 | "step": 2300 |
| 1587 | }, |
| 1588 | { |
| 1589 | "epoch": 3.3, |
| 1590 | "eval_loss": 0.19418245553970337, |
| 1591 | "eval_runtime": 39.5906, |
| 1592 | "eval_samples_per_second": 11.543, |
| 1593 | "eval_steps_per_second": 1.465, |
| 1594 | "eval_wer": 0.18566480951663905, |
| 1595 | "step": 2300 |
| 1596 | }, |
| 1597 | { |
| 1598 | "epoch": 3.32, |
| 1599 | "learning_rate": 0.0002841778425655977, |
| 1600 | "loss": 0.1004, |
| 1601 | "step": 2310 |
| 1602 | }, |
| 1603 | { |
| 1604 | "epoch": 3.33, |
| 1605 | "learning_rate": 0.00028409037900874634, |
| 1606 | "loss": 0.1123, |
| 1607 | "step": 2320 |
| 1608 | }, |
| 1609 | { |
| 1610 | "epoch": 3.35, |
| 1611 | "learning_rate": 0.000284002915451895, |
| 1612 | "loss": 0.0911, |
| 1613 | "step": 2330 |
| 1614 | }, |
| 1615 | { |
| 1616 | "epoch": 3.36, |
| 1617 | "learning_rate": 0.0002839154518950437, |
| 1618 | "loss": 0.0987, |
| 1619 | "step": 2340 |
| 1620 | }, |
| 1621 | { |
| 1622 | "epoch": 3.38, |
| 1623 | "learning_rate": 0.0002838279883381924, |
| 1624 | "loss": 0.0928, |
| 1625 | "step": 2350 |
| 1626 | }, |
| 1627 | { |
| 1628 | "epoch": 3.39, |
| 1629 | "learning_rate": 0.0002837405247813411, |
| 1630 | "loss": 0.0861, |
| 1631 | "step": 2360 |
| 1632 | }, |
| 1633 | { |
| 1634 | "epoch": 3.41, |
| 1635 | "learning_rate": 0.00028365306122448976, |
| 1636 | "loss": 0.1137, |
| 1637 | "step": 2370 |
| 1638 | }, |
| 1639 | { |
| 1640 | "epoch": 3.42, |
| 1641 | "learning_rate": 0.00028356559766763847, |
| 1642 | "loss": 0.0811, |
| 1643 | "step": 2380 |
| 1644 | }, |
| 1645 | { |
| 1646 | "epoch": 3.43, |
| 1647 | "learning_rate": 0.0002834781341107872, |
| 1648 | "loss": 0.0924, |
| 1649 | "step": 2390 |
| 1650 | }, |
| 1651 | { |
| 1652 | "epoch": 3.45, |
| 1653 | "learning_rate": 0.00028339067055393585, |
| 1654 | "loss": 0.1117, |
| 1655 | "step": 2400 |
| 1656 | }, |
| 1657 | { |
| 1658 | "epoch": 3.45, |
| 1659 | "eval_loss": 0.18514806032180786, |
| 1660 | "eval_runtime": 39.8212, |
| 1661 | "eval_samples_per_second": 11.476, |
| 1662 | "eval_steps_per_second": 1.457, |
| 1663 | "eval_wer": 0.19183857852733022, |
| 1664 | "step": 2400 |
| 1665 | }, |
| 1666 | { |
| 1667 | "epoch": 3.46, |
| 1668 | "learning_rate": 0.0002833032069970845, |
| 1669 | "loss": 0.0852, |
| 1670 | "step": 2410 |
| 1671 | }, |
| 1672 | { |
| 1673 | "epoch": 3.48, |
| 1674 | "learning_rate": 0.0002832157434402332, |
| 1675 | "loss": 0.1054, |
| 1676 | "step": 2420 |
| 1677 | }, |
| 1678 | { |
| 1679 | "epoch": 3.49, |
| 1680 | "learning_rate": 0.0002831282798833819, |
| 1681 | "loss": 0.1085, |
| 1682 | "step": 2430 |
| 1683 | }, |
| 1684 | { |
| 1685 | "epoch": 3.51, |
| 1686 | "learning_rate": 0.0002830408163265306, |
| 1687 | "loss": 0.0801, |
| 1688 | "step": 2440 |
| 1689 | }, |
| 1690 | { |
| 1691 | "epoch": 3.52, |
| 1692 | "learning_rate": 0.00028295335276967926, |
| 1693 | "loss": 0.0959, |
| 1694 | "step": 2450 |
| 1695 | }, |
| 1696 | { |
| 1697 | "epoch": 3.53, |
| 1698 | "learning_rate": 0.000282865889212828, |
| 1699 | "loss": 0.0874, |
| 1700 | "step": 2460 |
| 1701 | }, |
| 1702 | { |
| 1703 | "epoch": 3.55, |
| 1704 | "learning_rate": 0.00028277842565597663, |
| 1705 | "loss": 0.1038, |
| 1706 | "step": 2470 |
| 1707 | }, |
| 1708 | { |
| 1709 | "epoch": 3.56, |
| 1710 | "learning_rate": 0.00028269096209912535, |
| 1711 | "loss": 0.1012, |
| 1712 | "step": 2480 |
| 1713 | }, |
| 1714 | { |
| 1715 | "epoch": 3.58, |
| 1716 | "learning_rate": 0.00028260349854227406, |
| 1717 | "loss": 0.0862, |
| 1718 | "step": 2490 |
| 1719 | }, |
| 1720 | { |
| 1721 | "epoch": 3.59, |
| 1722 | "learning_rate": 0.0002825160349854227, |
| 1723 | "loss": 0.0922, |
| 1724 | "step": 2500 |
| 1725 | }, |
| 1726 | { |
| 1727 | "epoch": 3.59, |
| 1728 | "eval_loss": 0.18909135460853577, |
| 1729 | "eval_runtime": 39.6765, |
| 1730 | "eval_samples_per_second": 11.518, |
| 1731 | "eval_steps_per_second": 1.462, |
| 1732 | "eval_wer": 0.1846107513928625, |
| 1733 | "step": 2500 |
| 1734 | }, |
| 1735 | { |
| 1736 | "epoch": 3.61, |
| 1737 | "learning_rate": 0.0002824285714285714, |
| 1738 | "loss": 0.0741, |
| 1739 | "step": 2510 |
| 1740 | }, |
| 1741 | { |
| 1742 | "epoch": 3.62, |
| 1743 | "learning_rate": 0.0002823411078717201, |
| 1744 | "loss": 0.0942, |
| 1745 | "step": 2520 |
| 1746 | }, |
| 1747 | { |
| 1748 | "epoch": 3.64, |
| 1749 | "learning_rate": 0.00028225364431486876, |
| 1750 | "loss": 0.089, |
| 1751 | "step": 2530 |
| 1752 | }, |
| 1753 | { |
| 1754 | "epoch": 3.65, |
| 1755 | "learning_rate": 0.0002821661807580175, |
| 1756 | "loss": 0.0882, |
| 1757 | "step": 2540 |
| 1758 | }, |
| 1759 | { |
| 1760 | "epoch": 3.66, |
| 1761 | "learning_rate": 0.00028207871720116614, |
| 1762 | "loss": 0.092, |
| 1763 | "step": 2550 |
| 1764 | }, |
| 1765 | { |
| 1766 | "epoch": 3.68, |
| 1767 | "learning_rate": 0.00028199125364431485, |
| 1768 | "loss": 0.0834, |
| 1769 | "step": 2560 |
| 1770 | }, |
| 1771 | { |
| 1772 | "epoch": 3.69, |
| 1773 | "learning_rate": 0.00028190379008746357, |
| 1774 | "loss": 0.1412, |
| 1775 | "step": 2570 |
| 1776 | }, |
| 1777 | { |
| 1778 | "epoch": 3.71, |
| 1779 | "learning_rate": 0.00028181632653061223, |
| 1780 | "loss": 0.0847, |
| 1781 | "step": 2580 |
| 1782 | }, |
| 1783 | { |
| 1784 | "epoch": 3.72, |
| 1785 | "learning_rate": 0.0002817288629737609, |
| 1786 | "loss": 0.089, |
| 1787 | "step": 2590 |
| 1788 | }, |
| 1789 | { |
| 1790 | "epoch": 3.74, |
| 1791 | "learning_rate": 0.0002816413994169096, |
| 1792 | "loss": 0.1084, |
| 1793 | "step": 2600 |
| 1794 | }, |
| 1795 | { |
| 1796 | "epoch": 3.74, |
| 1797 | "eval_loss": 0.18555234372615814, |
| 1798 | "eval_runtime": 39.7139, |
| 1799 | "eval_samples_per_second": 11.507, |
| 1800 | "eval_steps_per_second": 1.46, |
| 1801 | "eval_wer": 0.18536365005270292, |
| 1802 | "step": 2600 |
| 1803 | }, |
| 1804 | { |
| 1805 | "epoch": 3.75, |
| 1806 | "learning_rate": 0.00028155393586005826, |
| 1807 | "loss": 0.0743, |
| 1808 | "step": 2610 |
| 1809 | }, |
| 1810 | { |
| 1811 | "epoch": 3.76, |
| 1812 | "learning_rate": 0.000281466472303207, |
| 1813 | "loss": 0.1098, |
| 1814 | "step": 2620 |
| 1815 | }, |
| 1816 | { |
| 1817 | "epoch": 3.78, |
| 1818 | "learning_rate": 0.00028137900874635564, |
| 1819 | "loss": 0.0825, |
| 1820 | "step": 2630 |
| 1821 | }, |
| 1822 | { |
| 1823 | "epoch": 3.79, |
| 1824 | "learning_rate": 0.00028129154518950436, |
| 1825 | "loss": 0.1, |
| 1826 | "step": 2640 |
| 1827 | }, |
| 1828 | { |
| 1829 | "epoch": 3.81, |
| 1830 | "learning_rate": 0.00028120408163265307, |
| 1831 | "loss": 0.0886, |
| 1832 | "step": 2650 |
| 1833 | }, |
| 1834 | { |
| 1835 | "epoch": 3.82, |
| 1836 | "learning_rate": 0.00028111661807580173, |
| 1837 | "loss": 0.0783, |
| 1838 | "step": 2660 |
| 1839 | }, |
| 1840 | { |
| 1841 | "epoch": 3.84, |
| 1842 | "learning_rate": 0.00028102915451895045, |
| 1843 | "loss": 0.1155, |
| 1844 | "step": 2670 |
| 1845 | }, |
| 1846 | { |
| 1847 | "epoch": 3.85, |
| 1848 | "learning_rate": 0.0002809416909620991, |
| 1849 | "loss": 0.0977, |
| 1850 | "step": 2680 |
| 1851 | }, |
| 1852 | { |
| 1853 | "epoch": 3.86, |
| 1854 | "learning_rate": 0.00028085422740524777, |
| 1855 | "loss": 0.0882, |
| 1856 | "step": 2690 |
| 1857 | }, |
| 1858 | { |
| 1859 | "epoch": 3.88, |
| 1860 | "learning_rate": 0.0002807667638483965, |
| 1861 | "loss": 0.1132, |
| 1862 | "step": 2700 |
| 1863 | }, |
| 1864 | { |
| 1865 | "epoch": 3.88, |
| 1866 | "eval_loss": 0.1814679652452469, |
| 1867 | "eval_runtime": 39.8894, |
| 1868 | "eval_samples_per_second": 11.457, |
| 1869 | "eval_steps_per_second": 1.454, |
| 1870 | "eval_wer": 0.19018220147568138, |
| 1871 | "step": 2700 |
| 1872 | }, |
| 1873 | { |
| 1874 | "epoch": 3.89, |
| 1875 | "learning_rate": 0.00028067930029154514, |
| 1876 | "loss": 0.0943, |
| 1877 | "step": 2710 |
| 1878 | }, |
| 1879 | { |
| 1880 | "epoch": 3.91, |
| 1881 | "learning_rate": 0.00028059183673469386, |
| 1882 | "loss": 0.1055, |
| 1883 | "step": 2720 |
| 1884 | }, |
| 1885 | { |
| 1886 | "epoch": 3.92, |
| 1887 | "learning_rate": 0.0002805043731778425, |
| 1888 | "loss": 0.0958, |
| 1889 | "step": 2730 |
| 1890 | }, |
| 1891 | { |
| 1892 | "epoch": 3.94, |
| 1893 | "learning_rate": 0.00028041690962099123, |
| 1894 | "loss": 0.1021, |
| 1895 | "step": 2740 |
| 1896 | }, |
| 1897 | { |
| 1898 | "epoch": 3.95, |
| 1899 | "learning_rate": 0.00028032944606413995, |
| 1900 | "loss": 0.1098, |
| 1901 | "step": 2750 |
| 1902 | }, |
| 1903 | { |
| 1904 | "epoch": 3.97, |
| 1905 | "learning_rate": 0.0002802419825072886, |
| 1906 | "loss": 0.0958, |
| 1907 | "step": 2760 |
| 1908 | }, |
| 1909 | { |
| 1910 | "epoch": 3.98, |
| 1911 | "learning_rate": 0.00028015451895043727, |
| 1912 | "loss": 0.0834, |
| 1913 | "step": 2770 |
| 1914 | }, |
| 1915 | { |
| 1916 | "epoch": 3.99, |
| 1917 | "learning_rate": 0.000280067055393586, |
| 1918 | "loss": 0.0845, |
| 1919 | "step": 2780 |
| 1920 | }, |
| 1921 | { |
| 1922 | "epoch": 4.01, |
| 1923 | "learning_rate": 0.00027997959183673465, |
| 1924 | "loss": 0.0859, |
| 1925 | "step": 2790 |
| 1926 | }, |
| 1927 | { |
| 1928 | "epoch": 4.02, |
| 1929 | "learning_rate": 0.00027989212827988336, |
| 1930 | "loss": 0.0979, |
| 1931 | "step": 2800 |
| 1932 | }, |
| 1933 | { |
| 1934 | "epoch": 4.02, |
| 1935 | "eval_loss": 0.17596615850925446, |
| 1936 | "eval_runtime": 39.7684, |
| 1937 | "eval_samples_per_second": 11.492, |
| 1938 | "eval_steps_per_second": 1.458, |
| 1939 | "eval_wer": 0.18039451889775637, |
| 1940 | "step": 2800 |
| 1941 | }, |
| 1942 | { |
| 1943 | "epoch": 4.04, |
| 1944 | "learning_rate": 0.000279804664723032, |
| 1945 | "loss": 0.0867, |
| 1946 | "step": 2810 |
| 1947 | }, |
| 1948 | { |
| 1949 | "epoch": 4.05, |
| 1950 | "learning_rate": 0.00027971720116618074, |
| 1951 | "loss": 0.0853, |
| 1952 | "step": 2820 |
| 1953 | }, |
| 1954 | { |
| 1955 | "epoch": 4.07, |
| 1956 | "learning_rate": 0.00027962973760932945, |
| 1957 | "loss": 0.0766, |
| 1958 | "step": 2830 |
| 1959 | }, |
| 1960 | { |
| 1961 | "epoch": 4.08, |
| 1962 | "learning_rate": 0.0002795422740524781, |
| 1963 | "loss": 0.0863, |
| 1964 | "step": 2840 |
| 1965 | }, |
| 1966 | { |
| 1967 | "epoch": 4.09, |
| 1968 | "learning_rate": 0.00027945481049562683, |
| 1969 | "loss": 0.0715, |
| 1970 | "step": 2850 |
| 1971 | }, |
| 1972 | { |
| 1973 | "epoch": 4.11, |
| 1974 | "learning_rate": 0.0002793673469387755, |
| 1975 | "loss": 0.0864, |
| 1976 | "step": 2860 |
| 1977 | }, |
| 1978 | { |
| 1979 | "epoch": 4.12, |
| 1980 | "learning_rate": 0.00027927988338192415, |
| 1981 | "loss": 0.0931, |
| 1982 | "step": 2870 |
| 1983 | }, |
| 1984 | { |
| 1985 | "epoch": 4.14, |
| 1986 | "learning_rate": 0.00027919241982507286, |
| 1987 | "loss": 0.0739, |
| 1988 | "step": 2880 |
| 1989 | }, |
| 1990 | { |
| 1991 | "epoch": 4.15, |
| 1992 | "learning_rate": 0.0002791049562682215, |
| 1993 | "loss": 0.0761, |
| 1994 | "step": 2890 |
| 1995 | }, |
| 1996 | { |
| 1997 | "epoch": 4.17, |
| 1998 | "learning_rate": 0.00027901749271137024, |
| 1999 | "loss": 0.0698, |
| 2000 | "step": 2900 |
| 2001 | }, |
| 2002 | { |
| 2003 | "epoch": 4.17, |
| 2004 | "eval_loss": 0.1889517903327942, |
| 2005 | "eval_runtime": 39.7733, |
| 2006 | "eval_samples_per_second": 11.49, |
| 2007 | "eval_steps_per_second": 1.458, |
| 2008 | "eval_wer": 0.1826532148772775, |
| 2009 | "step": 2900 |
| 2010 | }, |
| 2011 | { |
| 2012 | "epoch": 4.18, |
| 2013 | "learning_rate": 0.00027893002915451896, |
| 2014 | "loss": 0.1061, |
| 2015 | "step": 2910 |
| 2016 | }, |
| 2017 | { |
| 2018 | "epoch": 4.2, |
| 2019 | "learning_rate": 0.0002788425655976676, |
| 2020 | "loss": 0.1011, |
| 2021 | "step": 2920 |
| 2022 | }, |
| 2023 | { |
| 2024 | "epoch": 4.21, |
| 2025 | "learning_rate": 0.00027875510204081633, |
| 2026 | "loss": 0.0772, |
| 2027 | "step": 2930 |
| 2028 | }, |
| 2029 | { |
| 2030 | "epoch": 4.22, |
| 2031 | "learning_rate": 0.000278667638483965, |
| 2032 | "loss": 0.0964, |
| 2033 | "step": 2940 |
| 2034 | }, |
| 2035 | { |
| 2036 | "epoch": 4.24, |
| 2037 | "learning_rate": 0.00027858017492711365, |
| 2038 | "loss": 0.0824, |
| 2039 | "step": 2950 |
| 2040 | }, |
| 2041 | { |
| 2042 | "epoch": 4.25, |
| 2043 | "learning_rate": 0.00027849271137026237, |
| 2044 | "loss": 0.0788, |
| 2045 | "step": 2960 |
| 2046 | }, |
| 2047 | { |
| 2048 | "epoch": 4.27, |
| 2049 | "learning_rate": 0.00027840524781341103, |
| 2050 | "loss": 0.1011, |
| 2051 | "step": 2970 |
| 2052 | }, |
| 2053 | { |
| 2054 | "epoch": 4.28, |
| 2055 | "learning_rate": 0.00027831778425655974, |
| 2056 | "loss": 0.0775, |
| 2057 | "step": 2980 |
| 2058 | }, |
| 2059 | { |
| 2060 | "epoch": 4.3, |
| 2061 | "learning_rate": 0.0002782303206997084, |
| 2062 | "loss": 0.0912, |
| 2063 | "step": 2990 |
| 2064 | }, |
| 2065 | { |
| 2066 | "epoch": 4.31, |
| 2067 | "learning_rate": 0.0002781428571428571, |
| 2068 | "loss": 0.0862, |
| 2069 | "step": 3000 |
| 2070 | }, |
| 2071 | { |
| 2072 | "epoch": 4.31, |
| 2073 | "eval_loss": 0.17421171069145203, |
| 2074 | "eval_runtime": 40.0805, |
| 2075 | "eval_samples_per_second": 11.402, |
| 2076 | "eval_steps_per_second": 1.447, |
| 2077 | "eval_wer": 0.1715103147116398, |
| 2078 | "step": 3000 |
| 2079 | }, |
| 2080 | { |
| 2081 | "epoch": 4.32, |
| 2082 | "learning_rate": 0.00027805539358600583, |
| 2083 | "loss": 0.1038, |
| 2084 | "step": 3010 |
| 2085 | }, |
| 2086 | { |
| 2087 | "epoch": 4.34, |
| 2088 | "learning_rate": 0.0002779679300291545, |
| 2089 | "loss": 0.0934, |
| 2090 | "step": 3020 |
| 2091 | }, |
| 2092 | { |
| 2093 | "epoch": 4.35, |
| 2094 | "learning_rate": 0.0002778804664723032, |
| 2095 | "loss": 0.0597, |
| 2096 | "step": 3030 |
| 2097 | }, |
| 2098 | { |
| 2099 | "epoch": 4.37, |
| 2100 | "learning_rate": 0.00027779300291545187, |
| 2101 | "loss": 0.1031, |
| 2102 | "step": 3040 |
| 2103 | }, |
| 2104 | { |
| 2105 | "epoch": 4.38, |
| 2106 | "learning_rate": 0.00027770553935860053, |
| 2107 | "loss": 0.073, |
| 2108 | "step": 3050 |
| 2109 | }, |
| 2110 | { |
| 2111 | "epoch": 4.4, |
| 2112 | "learning_rate": 0.00027761807580174925, |
| 2113 | "loss": 0.0767, |
| 2114 | "step": 3060 |
| 2115 | }, |
| 2116 | { |
| 2117 | "epoch": 4.41, |
| 2118 | "learning_rate": 0.0002775306122448979, |
| 2119 | "loss": 0.0834, |
| 2120 | "step": 3070 |
| 2121 | }, |
| 2122 | { |
| 2123 | "epoch": 4.43, |
| 2124 | "learning_rate": 0.0002774431486880466, |
| 2125 | "loss": 0.0829, |
| 2126 | "step": 3080 |
| 2127 | }, |
| 2128 | { |
| 2129 | "epoch": 4.44, |
| 2130 | "learning_rate": 0.00027735568513119534, |
| 2131 | "loss": 0.0804, |
| 2132 | "step": 3090 |
| 2133 | }, |
| 2134 | { |
| 2135 | "epoch": 4.45, |
| 2136 | "learning_rate": 0.000277268221574344, |
| 2137 | "loss": 0.0833, |
| 2138 | "step": 3100 |
| 2139 | }, |
| 2140 | { |
| 2141 | "epoch": 4.45, |
| 2142 | "eval_loss": 0.17197643220424652, |
| 2143 | "eval_runtime": 39.7627, |
| 2144 | "eval_samples_per_second": 11.493, |
| 2145 | "eval_steps_per_second": 1.459, |
| 2146 | "eval_wer": 0.1794910405059479, |
| 2147 | "step": 3100 |
| 2148 | }, |
| 2149 | { |
| 2150 | "epoch": 4.47, |
| 2151 | "learning_rate": 0.0002771807580174927, |
| 2152 | "loss": 0.0851, |
| 2153 | "step": 3110 |
| 2154 | }, |
| 2155 | { |
| 2156 | "epoch": 4.48, |
| 2157 | "learning_rate": 0.0002770932944606414, |
| 2158 | "loss": 0.0938, |
| 2159 | "step": 3120 |
| 2160 | }, |
| 2161 | { |
| 2162 | "epoch": 4.5, |
| 2163 | "learning_rate": 0.00027700583090379004, |
| 2164 | "loss": 0.093, |
| 2165 | "step": 3130 |
| 2166 | }, |
| 2167 | { |
| 2168 | "epoch": 4.51, |
| 2169 | "learning_rate": 0.00027691836734693875, |
| 2170 | "loss": 0.0975, |
| 2171 | "step": 3140 |
| 2172 | }, |
| 2173 | { |
| 2174 | "epoch": 4.53, |
| 2175 | "learning_rate": 0.0002768309037900874, |
| 2176 | "loss": 0.0825, |
| 2177 | "step": 3150 |
| 2178 | }, |
| 2179 | { |
| 2180 | "epoch": 4.54, |
| 2181 | "learning_rate": 0.0002767434402332361, |
| 2182 | "loss": 0.075, |
| 2183 | "step": 3160 |
| 2184 | }, |
| 2185 | { |
| 2186 | "epoch": 4.55, |
| 2187 | "learning_rate": 0.00027665597667638484, |
| 2188 | "loss": 0.119, |
| 2189 | "step": 3170 |
| 2190 | }, |
| 2191 | { |
| 2192 | "epoch": 4.57, |
| 2193 | "learning_rate": 0.0002765685131195335, |
| 2194 | "loss": 0.0823, |
| 2195 | "step": 3180 |
| 2196 | }, |
| 2197 | { |
| 2198 | "epoch": 4.58, |
| 2199 | "learning_rate": 0.0002764810495626822, |
| 2200 | "loss": 0.0881, |
| 2201 | "step": 3190 |
| 2202 | }, |
| 2203 | { |
| 2204 | "epoch": 4.6, |
| 2205 | "learning_rate": 0.0002763935860058309, |
| 2206 | "loss": 0.0781, |
| 2207 | "step": 3200 |
| 2208 | }, |
| 2209 | { |
| 2210 | "epoch": 4.6, |
| 2211 | "eval_loss": 0.18404971063137054, |
| 2212 | "eval_runtime": 39.7696, |
| 2213 | "eval_samples_per_second": 11.491, |
| 2214 | "eval_steps_per_second": 1.458, |
| 2215 | "eval_wer": 0.18551422978467097, |
| 2216 | "step": 3200 |
| 2217 | }, |
| 2218 | { |
| 2219 | "epoch": 4.61, |
| 2220 | "learning_rate": 0.0002763061224489796, |
| 2221 | "loss": 0.0898, |
| 2222 | "step": 3210 |
| 2223 | }, |
| 2224 | { |
| 2225 | "epoch": 4.63, |
| 2226 | "learning_rate": 0.00027621865889212825, |
| 2227 | "loss": 0.0843, |
| 2228 | "step": 3220 |
| 2229 | }, |
| 2230 | { |
| 2231 | "epoch": 4.64, |
| 2232 | "learning_rate": 0.0002761311953352769, |
| 2233 | "loss": 0.0868, |
| 2234 | "step": 3230 |
| 2235 | }, |
| 2236 | { |
| 2237 | "epoch": 4.66, |
| 2238 | "learning_rate": 0.00027604373177842563, |
| 2239 | "loss": 0.1109, |
| 2240 | "step": 3240 |
| 2241 | }, |
| 2242 | { |
| 2243 | "epoch": 4.67, |
| 2244 | "learning_rate": 0.0002759562682215743, |
| 2245 | "loss": 0.1084, |
| 2246 | "step": 3250 |
| 2247 | }, |
| 2248 | { |
| 2249 | "epoch": 4.68, |
| 2250 | "learning_rate": 0.000275868804664723, |
| 2251 | "loss": 0.0948, |
| 2252 | "step": 3260 |
| 2253 | }, |
| 2254 | { |
| 2255 | "epoch": 4.7, |
| 2256 | "learning_rate": 0.0002757813411078717, |
| 2257 | "loss": 0.106, |
| 2258 | "step": 3270 |
| 2259 | }, |
| 2260 | { |
| 2261 | "epoch": 4.71, |
| 2262 | "learning_rate": 0.0002756938775510204, |
| 2263 | "loss": 0.0703, |
| 2264 | "step": 3280 |
| 2265 | }, |
| 2266 | { |
| 2267 | "epoch": 4.73, |
| 2268 | "learning_rate": 0.0002756064139941691, |
| 2269 | "loss": 0.1003, |
| 2270 | "step": 3290 |
| 2271 | }, |
| 2272 | { |
| 2273 | "epoch": 4.74, |
| 2274 | "learning_rate": 0.00027551895043731776, |
| 2275 | "loss": 0.0907, |
| 2276 | "step": 3300 |
| 2277 | }, |
| 2278 | { |
| 2279 | "epoch": 4.74, |
| 2280 | "eval_loss": 0.16755123436450958, |
| 2281 | "eval_runtime": 40.1876, |
| 2282 | "eval_samples_per_second": 11.372, |
| 2283 | "eval_steps_per_second": 1.443, |
| 2284 | "eval_wer": 0.17903930131004367, |
| 2285 | "step": 3300 |
| 2286 | }, |
| 2287 | { |
| 2288 | "epoch": 4.76, |
| 2289 | "learning_rate": 0.0002754314868804664, |
| 2290 | "loss": 0.0845, |
| 2291 | "step": 3310 |
| 2292 | }, |
| 2293 | { |
| 2294 | "epoch": 4.77, |
| 2295 | "learning_rate": 0.00027534402332361513, |
| 2296 | "loss": 0.0957, |
| 2297 | "step": 3320 |
| 2298 | }, |
| 2299 | { |
| 2300 | "epoch": 4.78, |
| 2301 | "learning_rate": 0.0002752565597667638, |
| 2302 | "loss": 0.0825, |
| 2303 | "step": 3330 |
| 2304 | }, |
| 2305 | { |
| 2306 | "epoch": 4.8, |
| 2307 | "learning_rate": 0.0002751690962099125, |
| 2308 | "loss": 0.1048, |
| 2309 | "step": 3340 |
| 2310 | }, |
| 2311 | { |
| 2312 | "epoch": 4.81, |
| 2313 | "learning_rate": 0.0002750816326530612, |
| 2314 | "loss": 0.0857, |
| 2315 | "step": 3350 |
| 2316 | }, |
| 2317 | { |
| 2318 | "epoch": 4.83, |
| 2319 | "learning_rate": 0.0002749941690962099, |
| 2320 | "loss": 0.0704, |
| 2321 | "step": 3360 |
| 2322 | }, |
| 2323 | { |
| 2324 | "epoch": 4.84, |
| 2325 | "learning_rate": 0.0002749067055393586, |
| 2326 | "loss": 0.0895, |
| 2327 | "step": 3370 |
| 2328 | }, |
| 2329 | { |
| 2330 | "epoch": 4.86, |
| 2331 | "learning_rate": 0.00027481924198250726, |
| 2332 | "loss": 0.0637, |
| 2333 | "step": 3380 |
| 2334 | }, |
| 2335 | { |
| 2336 | "epoch": 4.87, |
| 2337 | "learning_rate": 0.000274731778425656, |
| 2338 | "loss": 0.0972, |
| 2339 | "step": 3390 |
| 2340 | }, |
| 2341 | { |
| 2342 | "epoch": 4.89, |
| 2343 | "learning_rate": 0.00027464431486880464, |
| 2344 | "loss": 0.0998, |
| 2345 | "step": 3400 |
| 2346 | }, |
| 2347 | { |
| 2348 | "epoch": 4.89, |
| 2349 | "eval_loss": 0.18358713388442993, |
| 2350 | "eval_runtime": 39.8198, |
| 2351 | "eval_samples_per_second": 11.477, |
| 2352 | "eval_steps_per_second": 1.457, |
| 2353 | "eval_wer": 0.1847613311248306, |
| 2354 | "step": 3400 |
| 2355 | }, |
| 2356 | { |
| 2357 | "epoch": 4.9, |
| 2358 | "learning_rate": 0.0002745568513119533, |
| 2359 | "loss": 0.0758, |
| 2360 | "step": 3410 |
| 2361 | }, |
| 2362 | { |
| 2363 | "epoch": 4.91, |
| 2364 | "learning_rate": 0.000274469387755102, |
| 2365 | "loss": 0.0953, |
| 2366 | "step": 3420 |
| 2367 | }, |
| 2368 | { |
| 2369 | "epoch": 4.93, |
| 2370 | "learning_rate": 0.0002743819241982507, |
| 2371 | "loss": 0.0848, |
| 2372 | "step": 3430 |
| 2373 | }, |
| 2374 | { |
| 2375 | "epoch": 4.94, |
| 2376 | "learning_rate": 0.0002742944606413994, |
| 2377 | "loss": 0.1245, |
| 2378 | "step": 3440 |
| 2379 | }, |
| 2380 | { |
| 2381 | "epoch": 4.96, |
| 2382 | "learning_rate": 0.0002742069970845481, |
| 2383 | "loss": 0.0751, |
| 2384 | "step": 3450 |
| 2385 | }, |
| 2386 | { |
| 2387 | "epoch": 4.97, |
| 2388 | "learning_rate": 0.00027411953352769676, |
| 2389 | "loss": 0.0844, |
| 2390 | "step": 3460 |
| 2391 | }, |
| 2392 | { |
| 2393 | "epoch": 4.99, |
| 2394 | "learning_rate": 0.0002740320699708455, |
| 2395 | "loss": 0.1096, |
| 2396 | "step": 3470 |
| 2397 | }, |
| 2398 | { |
| 2399 | "epoch": 5.0, |
| 2400 | "learning_rate": 0.00027394460641399414, |
| 2401 | "loss": 0.0643, |
| 2402 | "step": 3480 |
| 2403 | }, |
| 2404 | { |
| 2405 | "epoch": 5.01, |
| 2406 | "learning_rate": 0.0002738571428571428, |
| 2407 | "loss": 0.1243, |
| 2408 | "step": 3490 |
| 2409 | }, |
| 2410 | { |
| 2411 | "epoch": 5.03, |
| 2412 | "learning_rate": 0.0002737696793002915, |
| 2413 | "loss": 0.0886, |
| 2414 | "step": 3500 |
| 2415 | }, |
| 2416 | { |
| 2417 | "epoch": 5.03, |
| 2418 | "eval_loss": 0.17481039464473724, |
| 2419 | "eval_runtime": 39.889, |
| 2420 | "eval_samples_per_second": 11.457, |
| 2421 | "eval_steps_per_second": 1.454, |
| 2422 | "eval_wer": 0.18039451889775637, |
| 2423 | "step": 3500 |
| 2424 | }, |
| 2425 | { |
| 2426 | "epoch": 5.04, |
| 2427 | "learning_rate": 0.00027368221574344023, |
| 2428 | "loss": 0.1015, |
| 2429 | "step": 3510 |
| 2430 | }, |
| 2431 | { |
| 2432 | "epoch": 5.06, |
| 2433 | "learning_rate": 0.0002735947521865889, |
| 2434 | "loss": 0.0802, |
| 2435 | "step": 3520 |
| 2436 | }, |
| 2437 | { |
| 2438 | "epoch": 5.07, |
| 2439 | "learning_rate": 0.0002735072886297376, |
| 2440 | "loss": 0.0888, |
| 2441 | "step": 3530 |
| 2442 | }, |
| 2443 | { |
| 2444 | "epoch": 5.09, |
| 2445 | "learning_rate": 0.00027341982507288627, |
| 2446 | "loss": 0.0844, |
| 2447 | "step": 3540 |
| 2448 | }, |
| 2449 | { |
| 2450 | "epoch": 5.1, |
| 2451 | "learning_rate": 0.000273332361516035, |
| 2452 | "loss": 0.0687, |
| 2453 | "step": 3550 |
| 2454 | }, |
| 2455 | { |
| 2456 | "epoch": 5.11, |
| 2457 | "learning_rate": 0.00027324489795918364, |
| 2458 | "loss": 0.0928, |
| 2459 | "step": 3560 |
| 2460 | }, |
| 2461 | { |
| 2462 | "epoch": 5.13, |
| 2463 | "learning_rate": 0.00027315743440233236, |
| 2464 | "loss": 0.0816, |
| 2465 | "step": 3570 |
| 2466 | }, |
| 2467 | { |
| 2468 | "epoch": 5.14, |
| 2469 | "learning_rate": 0.000273069970845481, |
| 2470 | "loss": 0.0643, |
| 2471 | "step": 3580 |
| 2472 | }, |
| 2473 | { |
| 2474 | "epoch": 5.16, |
| 2475 | "learning_rate": 0.0002729825072886297, |
| 2476 | "loss": 0.0854, |
| 2477 | "step": 3590 |
| 2478 | }, |
| 2479 | { |
| 2480 | "epoch": 5.17, |
| 2481 | "learning_rate": 0.0002728950437317784, |
| 2482 | "loss": 0.0798, |
| 2483 | "step": 3600 |
| 2484 | }, |
| 2485 | { |
| 2486 | "epoch": 5.17, |
| 2487 | "eval_loss": 0.18081925809383392, |
| 2488 | "eval_runtime": 39.9753, |
| 2489 | "eval_samples_per_second": 11.432, |
| 2490 | "eval_steps_per_second": 1.451, |
| 2491 | "eval_wer": 0.19153741906339405, |
| 2492 | "step": 3600 |
| 2493 | }, |
| 2494 | { |
| 2495 | "epoch": 5.19, |
| 2496 | "learning_rate": 0.0002728075801749271, |
| 2497 | "loss": 0.0843, |
| 2498 | "step": 3610 |
| 2499 | }, |
| 2500 | { |
| 2501 | "epoch": 5.2, |
| 2502 | "learning_rate": 0.00027272011661807577, |
| 2503 | "loss": 0.0814, |
| 2504 | "step": 3620 |
| 2505 | }, |
| 2506 | { |
| 2507 | "epoch": 5.22, |
| 2508 | "learning_rate": 0.0002726326530612245, |
| 2509 | "loss": 0.0706, |
| 2510 | "step": 3630 |
| 2511 | }, |
| 2512 | { |
| 2513 | "epoch": 5.23, |
| 2514 | "learning_rate": 0.00027254518950437315, |
| 2515 | "loss": 0.099, |
| 2516 | "step": 3640 |
| 2517 | }, |
| 2518 | { |
| 2519 | "epoch": 5.24, |
| 2520 | "learning_rate": 0.00027245772594752186, |
| 2521 | "loss": 0.0597, |
| 2522 | "step": 3650 |
| 2523 | }, |
| 2524 | { |
| 2525 | "epoch": 5.26, |
| 2526 | "learning_rate": 0.0002723702623906705, |
| 2527 | "loss": 0.085, |
| 2528 | "step": 3660 |
| 2529 | }, |
| 2530 | { |
| 2531 | "epoch": 5.27, |
| 2532 | "learning_rate": 0.0002722827988338192, |
| 2533 | "loss": 0.0802, |
| 2534 | "step": 3670 |
| 2535 | }, |
| 2536 | { |
| 2537 | "epoch": 5.29, |
| 2538 | "learning_rate": 0.0002721953352769679, |
| 2539 | "loss": 0.0664, |
| 2540 | "step": 3680 |
| 2541 | }, |
| 2542 | { |
| 2543 | "epoch": 5.3, |
| 2544 | "learning_rate": 0.0002721078717201166, |
| 2545 | "loss": 0.0971, |
| 2546 | "step": 3690 |
| 2547 | }, |
| 2548 | { |
| 2549 | "epoch": 5.32, |
| 2550 | "learning_rate": 0.00027202040816326527, |
| 2551 | "loss": 0.065, |
| 2552 | "step": 3700 |
| 2553 | }, |
| 2554 | { |
| 2555 | "epoch": 5.32, |
| 2556 | "eval_loss": 0.1817695051431656, |
| 2557 | "eval_runtime": 39.9937, |
| 2558 | "eval_samples_per_second": 11.427, |
| 2559 | "eval_steps_per_second": 1.45, |
| 2560 | "eval_wer": 0.1841590121969583, |
| 2561 | "step": 3700 |
| 2562 | }, |
| 2563 | { |
| 2564 | "epoch": 5.33, |
| 2565 | "learning_rate": 0.000271932944606414, |
| 2566 | "loss": 0.0862, |
| 2567 | "step": 3710 |
| 2568 | }, |
| 2569 | { |
| 2570 | "epoch": 5.34, |
| 2571 | "learning_rate": 0.00027184548104956265, |
| 2572 | "loss": 0.0886, |
| 2573 | "step": 3720 |
| 2574 | }, |
| 2575 | { |
| 2576 | "epoch": 5.36, |
| 2577 | "learning_rate": 0.00027175801749271136, |
| 2578 | "loss": 0.0663, |
| 2579 | "step": 3730 |
| 2580 | }, |
| 2581 | { |
| 2582 | "epoch": 5.37, |
| 2583 | "learning_rate": 0.00027167055393586, |
| 2584 | "loss": 0.0857, |
| 2585 | "step": 3740 |
| 2586 | }, |
| 2587 | { |
| 2588 | "epoch": 5.39, |
| 2589 | "learning_rate": 0.00027158309037900874, |
| 2590 | "loss": 0.0826, |
| 2591 | "step": 3750 |
| 2592 | }, |
| 2593 | { |
| 2594 | "epoch": 5.4, |
| 2595 | "learning_rate": 0.0002714956268221574, |
| 2596 | "loss": 0.0862, |
| 2597 | "step": 3760 |
| 2598 | }, |
| 2599 | { |
| 2600 | "epoch": 5.42, |
| 2601 | "learning_rate": 0.0002714081632653061, |
| 2602 | "loss": 0.0865, |
| 2603 | "step": 3770 |
| 2604 | }, |
| 2605 | { |
| 2606 | "epoch": 5.43, |
| 2607 | "learning_rate": 0.0002713206997084548, |
| 2608 | "loss": 0.0731, |
| 2609 | "step": 3780 |
| 2610 | }, |
| 2611 | { |
| 2612 | "epoch": 5.45, |
| 2613 | "learning_rate": 0.0002712332361516035, |
| 2614 | "loss": 0.0986, |
| 2615 | "step": 3790 |
| 2616 | }, |
| 2617 | { |
| 2618 | "epoch": 5.46, |
| 2619 | "learning_rate": 0.00027114577259475215, |
| 2620 | "loss": 0.0854, |
| 2621 | "step": 3800 |
| 2622 | }, |
| 2623 | { |
| 2624 | "epoch": 5.46, |
| 2625 | "eval_loss": 0.16976070404052734, |
| 2626 | "eval_runtime": 39.7742, |
| 2627 | "eval_samples_per_second": 11.49, |
| 2628 | "eval_steps_per_second": 1.458, |
| 2629 | "eval_wer": 0.1840084324649902, |
| 2630 | "step": 3800 |
| 2631 | }, |
| 2632 | { |
| 2633 | "epoch": 5.47, |
| 2634 | "learning_rate": 0.00027105830903790087, |
| 2635 | "loss": 0.0984, |
| 2636 | "step": 3810 |
| 2637 | }, |
| 2638 | { |
| 2639 | "epoch": 5.49, |
| 2640 | "learning_rate": 0.00027097084548104953, |
| 2641 | "loss": 0.0782, |
| 2642 | "step": 3820 |
| 2643 | }, |
| 2644 | { |
| 2645 | "epoch": 5.5, |
| 2646 | "learning_rate": 0.00027088338192419824, |
| 2647 | "loss": 0.0754, |
| 2648 | "step": 3830 |
| 2649 | }, |
| 2650 | { |
| 2651 | "epoch": 5.52, |
| 2652 | "learning_rate": 0.00027079591836734696, |
| 2653 | "loss": 0.0915, |
| 2654 | "step": 3840 |
| 2655 | }, |
| 2656 | { |
| 2657 | "epoch": 5.53, |
| 2658 | "learning_rate": 0.00027070845481049556, |
| 2659 | "loss": 0.0784, |
| 2660 | "step": 3850 |
| 2661 | }, |
| 2662 | { |
| 2663 | "epoch": 5.55, |
| 2664 | "learning_rate": 0.0002706209912536443, |
| 2665 | "loss": 0.1126, |
| 2666 | "step": 3860 |
| 2667 | }, |
| 2668 | { |
| 2669 | "epoch": 5.56, |
| 2670 | "learning_rate": 0.000270533527696793, |
| 2671 | "loss": 0.0727, |
| 2672 | "step": 3870 |
| 2673 | }, |
| 2674 | { |
| 2675 | "epoch": 5.57, |
| 2676 | "learning_rate": 0.00027044606413994165, |
| 2677 | "loss": 0.0842, |
| 2678 | "step": 3880 |
| 2679 | }, |
| 2680 | { |
| 2681 | "epoch": 5.59, |
| 2682 | "learning_rate": 0.00027035860058309037, |
| 2683 | "loss": 0.0961, |
| 2684 | "step": 3890 |
| 2685 | }, |
| 2686 | { |
| 2687 | "epoch": 5.6, |
| 2688 | "learning_rate": 0.00027027113702623903, |
| 2689 | "loss": 0.0745, |
| 2690 | "step": 3900 |
| 2691 | }, |
| 2692 | { |
| 2693 | "epoch": 5.6, |
| 2694 | "eval_loss": 0.17608921229839325, |
| 2695 | "eval_runtime": 39.9521, |
| 2696 | "eval_samples_per_second": 11.439, |
| 2697 | "eval_steps_per_second": 1.452, |
| 2698 | "eval_wer": 0.18114741755759675, |
| 2699 | "step": 3900 |
| 2700 | }, |
| 2701 | { |
| 2702 | "epoch": 5.62, |
| 2703 | "learning_rate": 0.00027018367346938775, |
| 2704 | "loss": 0.0905, |
| 2705 | "step": 3910 |
| 2706 | }, |
| 2707 | { |
| 2708 | "epoch": 5.63, |
| 2709 | "learning_rate": 0.0002700962099125364, |
| 2710 | "loss": 0.0842, |
| 2711 | "step": 3920 |
| 2712 | }, |
| 2713 | { |
| 2714 | "epoch": 5.65, |
| 2715 | "learning_rate": 0.0002700087463556851, |
| 2716 | "loss": 0.0843, |
| 2717 | "step": 3930 |
| 2718 | }, |
| 2719 | { |
| 2720 | "epoch": 5.66, |
| 2721 | "learning_rate": 0.0002699212827988338, |
| 2722 | "loss": 0.0955, |
| 2723 | "step": 3940 |
| 2724 | }, |
| 2725 | { |
| 2726 | "epoch": 5.68, |
| 2727 | "learning_rate": 0.0002698338192419825, |
| 2728 | "loss": 0.0784, |
| 2729 | "step": 3950 |
| 2730 | }, |
| 2731 | { |
| 2732 | "epoch": 5.69, |
| 2733 | "learning_rate": 0.00026974635568513116, |
| 2734 | "loss": 0.0801, |
| 2735 | "step": 3960 |
| 2736 | }, |
| 2737 | { |
| 2738 | "epoch": 5.7, |
| 2739 | "learning_rate": 0.00026965889212827987, |
| 2740 | "loss": 0.0815, |
| 2741 | "step": 3970 |
| 2742 | }, |
| 2743 | { |
| 2744 | "epoch": 5.72, |
| 2745 | "learning_rate": 0.00026957142857142853, |
| 2746 | "loss": 0.0825, |
| 2747 | "step": 3980 |
| 2748 | }, |
| 2749 | { |
| 2750 | "epoch": 5.73, |
| 2751 | "learning_rate": 0.00026948396501457725, |
| 2752 | "loss": 0.0836, |
| 2753 | "step": 3990 |
| 2754 | }, |
| 2755 | { |
| 2756 | "epoch": 5.75, |
| 2757 | "learning_rate": 0.0002693965014577259, |
| 2758 | "loss": 0.0789, |
| 2759 | "step": 4000 |
| 2760 | }, |
| 2761 | { |
| 2762 | "epoch": 5.75, |
| 2763 | "eval_loss": 0.17331229150295258, |
| 2764 | "eval_runtime": 40.1008, |
| 2765 | "eval_samples_per_second": 11.396, |
| 2766 | "eval_steps_per_second": 1.446, |
| 2767 | "eval_wer": 0.1840084324649902, |
| 2768 | "step": 4000 |
| 2769 | }, |
| 2770 | { |
| 2771 | "epoch": 5.76, |
| 2772 | "learning_rate": 0.0002693090379008746, |
| 2773 | "loss": 0.0866, |
| 2774 | "step": 4010 |
| 2775 | }, |
| 2776 | { |
| 2777 | "epoch": 5.78, |
| 2778 | "learning_rate": 0.00026922157434402334, |
| 2779 | "loss": 0.0779, |
| 2780 | "step": 4020 |
| 2781 | }, |
| 2782 | { |
| 2783 | "epoch": 5.79, |
| 2784 | "learning_rate": 0.000269134110787172, |
| 2785 | "loss": 0.0789, |
| 2786 | "step": 4030 |
| 2787 | }, |
| 2788 | { |
| 2789 | "epoch": 5.8, |
| 2790 | "learning_rate": 0.00026904664723032066, |
| 2791 | "loss": 0.0841, |
| 2792 | "step": 4040 |
| 2793 | }, |
| 2794 | { |
| 2795 | "epoch": 5.82, |
| 2796 | "learning_rate": 0.0002689591836734694, |
| 2797 | "loss": 0.0677, |
| 2798 | "step": 4050 |
| 2799 | }, |
| 2800 | { |
| 2801 | "epoch": 5.83, |
| 2802 | "learning_rate": 0.00026887172011661804, |
| 2803 | "loss": 0.096, |
| 2804 | "step": 4060 |
| 2805 | }, |
| 2806 | { |
| 2807 | "epoch": 5.85, |
| 2808 | "learning_rate": 0.00026878425655976675, |
| 2809 | "loss": 0.0854, |
| 2810 | "step": 4070 |
| 2811 | }, |
| 2812 | { |
| 2813 | "epoch": 5.86, |
| 2814 | "learning_rate": 0.0002686967930029154, |
| 2815 | "loss": 0.0847, |
| 2816 | "step": 4080 |
| 2817 | }, |
| 2818 | { |
| 2819 | "epoch": 5.88, |
| 2820 | "learning_rate": 0.00026860932944606413, |
| 2821 | "loss": 0.0986, |
| 2822 | "step": 4090 |
| 2823 | }, |
| 2824 | { |
| 2825 | "epoch": 5.89, |
| 2826 | "learning_rate": 0.00026852186588921284, |
| 2827 | "loss": 0.0903, |
| 2828 | "step": 4100 |
| 2829 | }, |
| 2830 | { |
| 2831 | "epoch": 5.89, |
| 2832 | "eval_loss": 0.17269666492938995, |
| 2833 | "eval_runtime": 39.8943, |
| 2834 | "eval_samples_per_second": 11.455, |
| 2835 | "eval_steps_per_second": 1.454, |
| 2836 | "eval_wer": 0.18370727300105405, |
| 2837 | "step": 4100 |
| 2838 | }, |
| 2839 | { |
| 2840 | "epoch": 5.91, |
| 2841 | "learning_rate": 0.0002684344023323615, |
| 2842 | "loss": 0.079, |
| 2843 | "step": 4110 |
| 2844 | }, |
| 2845 | { |
| 2846 | "epoch": 5.92, |
| 2847 | "learning_rate": 0.00026834693877551016, |
| 2848 | "loss": 0.1023, |
| 2849 | "step": 4120 |
| 2850 | }, |
| 2851 | { |
| 2852 | "epoch": 5.93, |
| 2853 | "learning_rate": 0.0002682594752186589, |
| 2854 | "loss": 0.0685, |
| 2855 | "step": 4130 |
| 2856 | }, |
| 2857 | { |
| 2858 | "epoch": 5.95, |
| 2859 | "learning_rate": 0.00026817201166180754, |
| 2860 | "loss": 0.1132, |
| 2861 | "step": 4140 |
| 2862 | }, |
| 2863 | { |
| 2864 | "epoch": 5.96, |
| 2865 | "learning_rate": 0.00026808454810495625, |
| 2866 | "loss": 0.0695, |
| 2867 | "step": 4150 |
| 2868 | }, |
| 2869 | { |
| 2870 | "epoch": 5.98, |
| 2871 | "learning_rate": 0.0002679970845481049, |
| 2872 | "loss": 0.0909, |
| 2873 | "step": 4160 |
| 2874 | }, |
| 2875 | { |
| 2876 | "epoch": 5.99, |
| 2877 | "learning_rate": 0.00026790962099125363, |
| 2878 | "loss": 0.0826, |
| 2879 | "step": 4170 |
| 2880 | }, |
| 2881 | { |
| 2882 | "epoch": 6.01, |
| 2883 | "learning_rate": 0.0002678221574344023, |
| 2884 | "loss": 0.0844, |
| 2885 | "step": 4180 |
| 2886 | }, |
| 2887 | { |
| 2888 | "epoch": 6.02, |
| 2889 | "learning_rate": 0.000267734693877551, |
| 2890 | "loss": 0.0805, |
| 2891 | "step": 4190 |
| 2892 | }, |
| 2893 | { |
| 2894 | "epoch": 6.03, |
| 2895 | "learning_rate": 0.0002676472303206997, |
| 2896 | "loss": 0.0774, |
| 2897 | "step": 4200 |
| 2898 | }, |
| 2899 | { |
| 2900 | "epoch": 6.03, |
| 2901 | "eval_loss": 0.19473043084144592, |
| 2902 | "eval_runtime": 39.8592, |
| 2903 | "eval_samples_per_second": 11.465, |
| 2904 | "eval_steps_per_second": 1.455, |
| 2905 | "eval_wer": 0.18686944737238367, |
| 2906 | "step": 4200 |
| 2907 | }, |
| 2908 | { |
| 2909 | "epoch": 6.05, |
| 2910 | "learning_rate": 0.0002675597667638484, |
| 2911 | "loss": 0.0907, |
| 2912 | "step": 4210 |
| 2913 | }, |
| 2914 | { |
| 2915 | "epoch": 6.06, |
| 2916 | "learning_rate": 0.00026747230320699704, |
| 2917 | "loss": 0.0737, |
| 2918 | "step": 4220 |
| 2919 | }, |
| 2920 | { |
| 2921 | "epoch": 6.08, |
| 2922 | "learning_rate": 0.00026738483965014576, |
| 2923 | "loss": 0.0701, |
| 2924 | "step": 4230 |
| 2925 | }, |
| 2926 | { |
| 2927 | "epoch": 6.09, |
| 2928 | "learning_rate": 0.0002672973760932944, |
| 2929 | "loss": 0.0774, |
| 2930 | "step": 4240 |
| 2931 | }, |
| 2932 | { |
| 2933 | "epoch": 6.11, |
| 2934 | "learning_rate": 0.00026720991253644313, |
| 2935 | "loss": 0.075, |
| 2936 | "step": 4250 |
| 2937 | }, |
| 2938 | { |
| 2939 | "epoch": 6.12, |
| 2940 | "learning_rate": 0.0002671224489795918, |
| 2941 | "loss": 0.102, |
| 2942 | "step": 4260 |
| 2943 | }, |
| 2944 | { |
| 2945 | "epoch": 6.14, |
| 2946 | "learning_rate": 0.0002670349854227405, |
| 2947 | "loss": 0.0744, |
| 2948 | "step": 4270 |
| 2949 | }, |
| 2950 | { |
| 2951 | "epoch": 6.15, |
| 2952 | "learning_rate": 0.0002669475218658892, |
| 2953 | "loss": 0.085, |
| 2954 | "step": 4280 |
| 2955 | }, |
| 2956 | { |
| 2957 | "epoch": 6.16, |
| 2958 | "learning_rate": 0.0002668600583090379, |
| 2959 | "loss": 0.0779, |
| 2960 | "step": 4290 |
| 2961 | }, |
| 2962 | { |
| 2963 | "epoch": 6.18, |
| 2964 | "learning_rate": 0.00026677259475218655, |
| 2965 | "loss": 0.0697, |
| 2966 | "step": 4300 |
| 2967 | }, |
| 2968 | { |
| 2969 | "epoch": 6.18, |
| 2970 | "eval_loss": 0.18682928383350372, |
| 2971 | "eval_runtime": 39.9127, |
| 2972 | "eval_samples_per_second": 11.45, |
| 2973 | "eval_steps_per_second": 1.453, |
| 2974 | "eval_wer": 0.18129799728956483, |
| 2975 | "step": 4300 |
| 2976 | }, |
| 2977 | { |
| 2978 | "epoch": 6.19, |
| 2979 | "learning_rate": 0.00026668513119533526, |
| 2980 | "loss": 0.1041, |
| 2981 | "step": 4310 |
| 2982 | }, |
| 2983 | { |
| 2984 | "epoch": 6.21, |
| 2985 | "learning_rate": 0.0002665976676384839, |
| 2986 | "loss": 0.0732, |
| 2987 | "step": 4320 |
| 2988 | }, |
| 2989 | { |
| 2990 | "epoch": 6.22, |
| 2991 | "learning_rate": 0.00026651020408163264, |
| 2992 | "loss": 0.0875, |
| 2993 | "step": 4330 |
| 2994 | }, |
| 2995 | { |
| 2996 | "epoch": 6.24, |
| 2997 | "learning_rate": 0.0002664227405247813, |
| 2998 | "loss": 0.0816, |
| 2999 | "step": 4340 |
| 3000 | }, |
| 3001 | { |
| 3002 | "epoch": 6.25, |
| 3003 | "learning_rate": 0.00026633527696793, |
| 3004 | "loss": 0.0722, |
| 3005 | "step": 4350 |
| 3006 | }, |
| 3007 | { |
| 3008 | "epoch": 6.26, |
| 3009 | "learning_rate": 0.00026624781341107873, |
| 3010 | "loss": 0.0973, |
| 3011 | "step": 4360 |
| 3012 | }, |
| 3013 | { |
| 3014 | "epoch": 6.28, |
| 3015 | "learning_rate": 0.0002661603498542274, |
| 3016 | "loss": 0.0724, |
| 3017 | "step": 4370 |
| 3018 | }, |
| 3019 | { |
| 3020 | "epoch": 6.29, |
| 3021 | "learning_rate": 0.0002660816326530612, |
| 3022 | "loss": 0.0795, |
| 3023 | "step": 4380 |
| 3024 | }, |
| 3025 | { |
| 3026 | "epoch": 6.31, |
| 3027 | "learning_rate": 0.0002659941690962099, |
| 3028 | "loss": 0.0762, |
| 3029 | "step": 4390 |
| 3030 | }, |
| 3031 | { |
| 3032 | "epoch": 6.32, |
| 3033 | "learning_rate": 0.0002659067055393586, |
| 3034 | "loss": 0.0778, |
| 3035 | "step": 4400 |
| 3036 | }, |
| 3037 | { |
| 3038 | "epoch": 6.32, |
| 3039 | "eval_loss": 0.1720825582742691, |
| 3040 | "eval_runtime": 39.8776, |
| 3041 | "eval_samples_per_second": 11.46, |
| 3042 | "eval_steps_per_second": 1.454, |
| 3043 | "eval_wer": 0.18114741755759675, |
| 3044 | "step": 4400 |
| 3045 | }, |
| 3046 | { |
| 3047 | "epoch": 6.34, |
| 3048 | "learning_rate": 0.00026581924198250726, |
| 3049 | "loss": 0.0782, |
| 3050 | "step": 4410 |
| 3051 | }, |
| 3052 | { |
| 3053 | "epoch": 6.35, |
| 3054 | "learning_rate": 0.00026573177842565597, |
| 3055 | "loss": 0.0822, |
| 3056 | "step": 4420 |
| 3057 | }, |
| 3058 | { |
| 3059 | "epoch": 6.36, |
| 3060 | "learning_rate": 0.00026564431486880463, |
| 3061 | "loss": 0.0935, |
| 3062 | "step": 4430 |
| 3063 | }, |
| 3064 | { |
| 3065 | "epoch": 6.38, |
| 3066 | "learning_rate": 0.00026555685131195335, |
| 3067 | "loss": 0.0818, |
| 3068 | "step": 4440 |
| 3069 | }, |
| 3070 | { |
| 3071 | "epoch": 6.39, |
| 3072 | "learning_rate": 0.000265469387755102, |
| 3073 | "loss": 0.0758, |
| 3074 | "step": 4450 |
| 3075 | }, |
| 3076 | { |
| 3077 | "epoch": 6.41, |
| 3078 | "learning_rate": 0.00026538192419825067, |
| 3079 | "loss": 0.0805, |
| 3080 | "step": 4460 |
| 3081 | }, |
| 3082 | { |
| 3083 | "epoch": 6.42, |
| 3084 | "learning_rate": 0.0002652944606413994, |
| 3085 | "loss": 0.0667, |
| 3086 | "step": 4470 |
| 3087 | }, |
| 3088 | { |
| 3089 | "epoch": 6.44, |
| 3090 | "learning_rate": 0.0002652069970845481, |
| 3091 | "loss": 0.0728, |
| 3092 | "step": 4480 |
| 3093 | }, |
| 3094 | { |
| 3095 | "epoch": 6.45, |
| 3096 | "learning_rate": 0.00026511953352769676, |
| 3097 | "loss": 0.0813, |
| 3098 | "step": 4490 |
| 3099 | }, |
| 3100 | { |
| 3101 | "epoch": 6.47, |
| 3102 | "learning_rate": 0.0002650320699708455, |
| 3103 | "loss": 0.0771, |
| 3104 | "step": 4500 |
| 3105 | }, |
| 3106 | { |
| 3107 | "epoch": 6.47, |
| 3108 | "eval_loss": 0.1848333477973938, |
| 3109 | "eval_runtime": 39.9888, |
| 3110 | "eval_samples_per_second": 11.428, |
| 3111 | "eval_steps_per_second": 1.45, |
| 3112 | "eval_wer": 0.199216985393766, |
| 3113 | "step": 4500 |
| 3114 | }, |
| 3115 | { |
| 3116 | "epoch": 6.48, |
| 3117 | "learning_rate": 0.00026494460641399414, |
| 3118 | "loss": 0.0893, |
| 3119 | "step": 4510 |
| 3120 | }, |
| 3121 | { |
| 3122 | "epoch": 6.49, |
| 3123 | "learning_rate": 0.00026485714285714285, |
| 3124 | "loss": 0.083, |
| 3125 | "step": 4520 |
| 3126 | }, |
| 3127 | { |
| 3128 | "epoch": 6.51, |
| 3129 | "learning_rate": 0.0002647696793002915, |
| 3130 | "loss": 0.0837, |
| 3131 | "step": 4530 |
| 3132 | }, |
| 3133 | { |
| 3134 | "epoch": 6.52, |
| 3135 | "learning_rate": 0.0002646822157434402, |
| 3136 | "loss": 0.0827, |
| 3137 | "step": 4540 |
| 3138 | }, |
| 3139 | { |
| 3140 | "epoch": 6.54, |
| 3141 | "learning_rate": 0.0002645947521865889, |
| 3142 | "loss": 0.0708, |
| 3143 | "step": 4550 |
| 3144 | }, |
| 3145 | { |
| 3146 | "epoch": 6.55, |
| 3147 | "learning_rate": 0.0002645072886297376, |
| 3148 | "loss": 0.0849, |
| 3149 | "step": 4560 |
| 3150 | }, |
| 3151 | { |
| 3152 | "epoch": 6.57, |
| 3153 | "learning_rate": 0.00026441982507288626, |
| 3154 | "loss": 0.0738, |
| 3155 | "step": 4570 |
| 3156 | }, |
| 3157 | { |
| 3158 | "epoch": 6.58, |
| 3159 | "learning_rate": 0.000264332361516035, |
| 3160 | "loss": 0.0838, |
| 3161 | "step": 4580 |
| 3162 | }, |
| 3163 | { |
| 3164 | "epoch": 6.59, |
| 3165 | "learning_rate": 0.00026424489795918364, |
| 3166 | "loss": 0.0758, |
| 3167 | "step": 4590 |
| 3168 | }, |
| 3169 | { |
| 3170 | "epoch": 6.61, |
| 3171 | "learning_rate": 0.00026415743440233235, |
| 3172 | "loss": 0.0717, |
| 3173 | "step": 4600 |
| 3174 | }, |
| 3175 | { |
| 3176 | "epoch": 6.61, |
| 3177 | "eval_loss": 0.17897100746631622, |
| 3178 | "eval_runtime": 39.9583, |
| 3179 | "eval_samples_per_second": 11.437, |
| 3180 | "eval_steps_per_second": 1.452, |
| 3181 | "eval_wer": 0.1919891582592983, |
| 3182 | "step": 4600 |
| 3183 | }, |
| 3184 | { |
| 3185 | "epoch": 6.62, |
| 3186 | "learning_rate": 0.000264069970845481, |
| 3187 | "loss": 0.0982, |
| 3188 | "step": 4610 |
| 3189 | }, |
| 3190 | { |
| 3191 | "epoch": 6.64, |
| 3192 | "learning_rate": 0.00026398250728862973, |
| 3193 | "loss": 0.09, |
| 3194 | "step": 4620 |
| 3195 | }, |
| 3196 | { |
| 3197 | "epoch": 6.65, |
| 3198 | "learning_rate": 0.0002638950437317784, |
| 3199 | "loss": 0.0911, |
| 3200 | "step": 4630 |
| 3201 | }, |
| 3202 | { |
| 3203 | "epoch": 6.67, |
| 3204 | "learning_rate": 0.0002638075801749271, |
| 3205 | "loss": 0.0833, |
| 3206 | "step": 4640 |
| 3207 | }, |
| 3208 | { |
| 3209 | "epoch": 6.68, |
| 3210 | "learning_rate": 0.00026372011661807577, |
| 3211 | "loss": 0.0892, |
| 3212 | "step": 4650 |
| 3213 | }, |
| 3214 | { |
| 3215 | "epoch": 6.7, |
| 3216 | "learning_rate": 0.0002636326530612245, |
| 3217 | "loss": 0.0936, |
| 3218 | "step": 4660 |
| 3219 | }, |
| 3220 | { |
| 3221 | "epoch": 6.71, |
| 3222 | "learning_rate": 0.00026354518950437314, |
| 3223 | "loss": 0.0812, |
| 3224 | "step": 4670 |
| 3225 | }, |
| 3226 | { |
| 3227 | "epoch": 6.72, |
| 3228 | "learning_rate": 0.00026345772594752186, |
| 3229 | "loss": 0.0823, |
| 3230 | "step": 4680 |
| 3231 | }, |
| 3232 | { |
| 3233 | "epoch": 6.74, |
| 3234 | "learning_rate": 0.0002633702623906705, |
| 3235 | "loss": 0.0896, |
| 3236 | "step": 4690 |
| 3237 | }, |
| 3238 | { |
| 3239 | "epoch": 6.75, |
| 3240 | "learning_rate": 0.00026328279883381923, |
| 3241 | "loss": 0.0772, |
| 3242 | "step": 4700 |
| 3243 | }, |
| 3244 | { |
| 3245 | "epoch": 6.75, |
| 3246 | "eval_loss": 0.1973699927330017, |
| 3247 | "eval_runtime": 39.8929, |
| 3248 | "eval_samples_per_second": 11.456, |
| 3249 | "eval_steps_per_second": 1.454, |
| 3250 | "eval_wer": 0.19274205691913868, |
| 3251 | "step": 4700 |
| 3252 | }, |
| 3253 | { |
| 3254 | "epoch": 6.77, |
| 3255 | "learning_rate": 0.00026319533527696795, |
| 3256 | "loss": 0.0983, |
| 3257 | "step": 4710 |
| 3258 | }, |
| 3259 | { |
| 3260 | "epoch": 6.78, |
| 3261 | "learning_rate": 0.00026310787172011656, |
| 3262 | "loss": 0.0822, |
| 3263 | "step": 4720 |
| 3264 | }, |
| 3265 | { |
| 3266 | "epoch": 6.8, |
| 3267 | "learning_rate": 0.00026302040816326527, |
| 3268 | "loss": 0.0826, |
| 3269 | "step": 4730 |
| 3270 | }, |
| 3271 | { |
| 3272 | "epoch": 6.81, |
| 3273 | "learning_rate": 0.000262932944606414, |
| 3274 | "loss": 0.0938, |
| 3275 | "step": 4740 |
| 3276 | }, |
| 3277 | { |
| 3278 | "epoch": 6.82, |
| 3279 | "learning_rate": 0.00026284548104956265, |
| 3280 | "loss": 0.0796, |
| 3281 | "step": 4750 |
| 3282 | }, |
| 3283 | { |
| 3284 | "epoch": 6.84, |
| 3285 | "learning_rate": 0.00026275801749271136, |
| 3286 | "loss": 0.1045, |
| 3287 | "step": 4760 |
| 3288 | }, |
| 3289 | { |
| 3290 | "epoch": 6.85, |
| 3291 | "learning_rate": 0.00026267055393586, |
| 3292 | "loss": 0.0803, |
| 3293 | "step": 4770 |
| 3294 | }, |
| 3295 | { |
| 3296 | "epoch": 6.87, |
| 3297 | "learning_rate": 0.00026258309037900874, |
| 3298 | "loss": 0.0886, |
| 3299 | "step": 4780 |
| 3300 | }, |
| 3301 | { |
| 3302 | "epoch": 6.88, |
| 3303 | "learning_rate": 0.0002624956268221574, |
| 3304 | "loss": 0.0872, |
| 3305 | "step": 4790 |
| 3306 | }, |
| 3307 | { |
| 3308 | "epoch": 6.9, |
| 3309 | "learning_rate": 0.0002624081632653061, |
| 3310 | "loss": 0.0721, |
| 3311 | "step": 4800 |
| 3312 | }, |
| 3313 | { |
| 3314 | "epoch": 6.9, |
| 3315 | "eval_loss": 0.19075419008731842, |
| 3316 | "eval_runtime": 39.9033, |
| 3317 | "eval_samples_per_second": 11.453, |
| 3318 | "eval_steps_per_second": 1.454, |
| 3319 | "eval_wer": 0.19364553531094714, |
| 3320 | "step": 4800 |
| 3321 | }, |
| 3322 | { |
| 3323 | "epoch": 6.91, |
| 3324 | "learning_rate": 0.0002623206997084548, |
| 3325 | "loss": 0.0853, |
| 3326 | "step": 4810 |
| 3327 | }, |
| 3328 | { |
| 3329 | "epoch": 6.93, |
| 3330 | "learning_rate": 0.0002622332361516035, |
| 3331 | "loss": 0.0657, |
| 3332 | "step": 4820 |
| 3333 | }, |
| 3334 | { |
| 3335 | "epoch": 6.94, |
| 3336 | "learning_rate": 0.00026214577259475215, |
| 3337 | "loss": 0.0864, |
| 3338 | "step": 4830 |
| 3339 | }, |
| 3340 | { |
| 3341 | "epoch": 6.95, |
| 3342 | "learning_rate": 0.00026205830903790086, |
| 3343 | "loss": 0.0914, |
| 3344 | "step": 4840 |
| 3345 | }, |
| 3346 | { |
| 3347 | "epoch": 6.97, |
| 3348 | "learning_rate": 0.0002619708454810495, |
| 3349 | "loss": 0.0767, |
| 3350 | "step": 4850 |
| 3351 | }, |
| 3352 | { |
| 3353 | "epoch": 6.98, |
| 3354 | "learning_rate": 0.00026188338192419824, |
| 3355 | "loss": 0.0872, |
| 3356 | "step": 4860 |
| 3357 | }, |
| 3358 | { |
| 3359 | "epoch": 7.0, |
| 3360 | "learning_rate": 0.0002617959183673469, |
| 3361 | "loss": 0.0734, |
| 3362 | "step": 4870 |
| 3363 | }, |
| 3364 | { |
| 3365 | "epoch": 7.01, |
| 3366 | "learning_rate": 0.0002617084548104956, |
| 3367 | "loss": 0.1009, |
| 3368 | "step": 4880 |
| 3369 | }, |
| 3370 | { |
| 3371 | "epoch": 7.03, |
| 3372 | "learning_rate": 0.00026162099125364433, |
| 3373 | "loss": 0.0684, |
| 3374 | "step": 4890 |
| 3375 | }, |
| 3376 | { |
| 3377 | "epoch": 7.04, |
| 3378 | "learning_rate": 0.000261533527696793, |
| 3379 | "loss": 0.0736, |
| 3380 | "step": 4900 |
| 3381 | }, |
| 3382 | { |
| 3383 | "epoch": 7.04, |
| 3384 | "eval_loss": 0.1875203400850296, |
| 3385 | "eval_runtime": 39.8411, |
| 3386 | "eval_samples_per_second": 11.471, |
| 3387 | "eval_steps_per_second": 1.456, |
| 3388 | "eval_wer": 0.18506249058876675, |
| 3389 | "step": 4900 |
| 3390 | }, |
| 3391 | { |
| 3392 | "epoch": 7.05, |
| 3393 | "learning_rate": 0.00026144606413994165, |
| 3394 | "loss": 0.0692, |
| 3395 | "step": 4910 |
| 3396 | }, |
| 3397 | { |
| 3398 | "epoch": 7.07, |
| 3399 | "learning_rate": 0.00026135860058309037, |
| 3400 | "loss": 0.0701, |
| 3401 | "step": 4920 |
| 3402 | }, |
| 3403 | { |
| 3404 | "epoch": 7.08, |
| 3405 | "learning_rate": 0.00026127113702623903, |
| 3406 | "loss": 0.0786, |
| 3407 | "step": 4930 |
| 3408 | }, |
| 3409 | { |
| 3410 | "epoch": 7.1, |
| 3411 | "learning_rate": 0.00026118367346938774, |
| 3412 | "loss": 0.0796, |
| 3413 | "step": 4940 |
| 3414 | }, |
| 3415 | { |
| 3416 | "epoch": 7.11, |
| 3417 | "learning_rate": 0.0002610962099125364, |
| 3418 | "loss": 0.0654, |
| 3419 | "step": 4950 |
| 3420 | }, |
| 3421 | { |
| 3422 | "epoch": 7.13, |
| 3423 | "learning_rate": 0.0002610087463556851, |
| 3424 | "loss": 0.0765, |
| 3425 | "step": 4960 |
| 3426 | }, |
| 3427 | { |
| 3428 | "epoch": 7.14, |
| 3429 | "learning_rate": 0.00026092128279883383, |
| 3430 | "loss": 0.0696, |
| 3431 | "step": 4970 |
| 3432 | }, |
| 3433 | { |
| 3434 | "epoch": 7.16, |
| 3435 | "learning_rate": 0.0002608338192419825, |
| 3436 | "loss": 0.0723, |
| 3437 | "step": 4980 |
| 3438 | }, |
| 3439 | { |
| 3440 | "epoch": 7.17, |
| 3441 | "learning_rate": 0.00026074635568513116, |
| 3442 | "loss": 0.0664, |
| 3443 | "step": 4990 |
| 3444 | }, |
| 3445 | { |
| 3446 | "epoch": 7.18, |
| 3447 | "learning_rate": 0.00026065889212827987, |
| 3448 | "loss": 0.0779, |
| 3449 | "step": 5000 |
| 3450 | }, |
| 3451 | { |
| 3452 | "epoch": 7.18, |
| 3453 | "eval_loss": 0.182932049036026, |
| 3454 | "eval_runtime": 39.8597, |
| 3455 | "eval_samples_per_second": 11.465, |
| 3456 | "eval_steps_per_second": 1.455, |
| 3457 | "eval_wer": 0.18325553380514983, |
| 3458 | "step": 5000 |
| 3459 | }, |
| 3460 | { |
| 3461 | "epoch": 7.2, |
| 3462 | "learning_rate": 0.00026057142857142853, |
| 3463 | "loss": 0.0822, |
| 3464 | "step": 5010 |
| 3465 | }, |
| 3466 | { |
| 3467 | "epoch": 7.21, |
| 3468 | "learning_rate": 0.00026048396501457725, |
| 3469 | "loss": 0.0723, |
| 3470 | "step": 5020 |
| 3471 | }, |
| 3472 | { |
| 3473 | "epoch": 7.23, |
| 3474 | "learning_rate": 0.0002603965014577259, |
| 3475 | "loss": 0.0802, |
| 3476 | "step": 5030 |
| 3477 | }, |
| 3478 | { |
| 3479 | "epoch": 7.24, |
| 3480 | "learning_rate": 0.0002603090379008746, |
| 3481 | "loss": 0.0725, |
| 3482 | "step": 5040 |
| 3483 | }, |
| 3484 | { |
| 3485 | "epoch": 7.26, |
| 3486 | "learning_rate": 0.0002602215743440233, |
| 3487 | "loss": 0.083, |
| 3488 | "step": 5050 |
| 3489 | }, |
| 3490 | { |
| 3491 | "epoch": 7.27, |
| 3492 | "learning_rate": 0.000260134110787172, |
| 3493 | "loss": 0.0941, |
| 3494 | "step": 5060 |
| 3495 | }, |
| 3496 | { |
| 3497 | "epoch": 7.28, |
| 3498 | "learning_rate": 0.0002600466472303207, |
| 3499 | "loss": 0.0617, |
| 3500 | "step": 5070 |
| 3501 | }, |
| 3502 | { |
| 3503 | "epoch": 7.3, |
| 3504 | "learning_rate": 0.0002599591836734694, |
| 3505 | "loss": 0.07, |
| 3506 | "step": 5080 |
| 3507 | }, |
| 3508 | { |
| 3509 | "epoch": 7.31, |
| 3510 | "learning_rate": 0.00025987172011661803, |
| 3511 | "loss": 0.0673, |
| 3512 | "step": 5090 |
| 3513 | }, |
| 3514 | { |
| 3515 | "epoch": 7.33, |
| 3516 | "learning_rate": 0.00025978425655976675, |
| 3517 | "loss": 0.0738, |
| 3518 | "step": 5100 |
| 3519 | }, |
| 3520 | { |
| 3521 | "epoch": 7.33, |
| 3522 | "eval_loss": 0.1895502805709839, |
| 3523 | "eval_runtime": 39.9633, |
| 3524 | "eval_samples_per_second": 11.435, |
| 3525 | "eval_steps_per_second": 1.451, |
| 3526 | "eval_wer": 0.18521307032073484, |
| 3527 | "step": 5100 |
| 3528 | }, |
| 3529 | { |
| 3530 | "epoch": 7.34, |
| 3531 | "learning_rate": 0.0002596967930029154, |
| 3532 | "loss": 0.0739, |
| 3533 | "step": 5110 |
| 3534 | }, |
| 3535 | { |
| 3536 | "epoch": 7.36, |
| 3537 | "learning_rate": 0.0002596093294460641, |
| 3538 | "loss": 0.0779, |
| 3539 | "step": 5120 |
| 3540 | }, |
| 3541 | { |
| 3542 | "epoch": 7.37, |
| 3543 | "learning_rate": 0.0002595218658892128, |
| 3544 | "loss": 0.0878, |
| 3545 | "step": 5130 |
| 3546 | }, |
| 3547 | { |
| 3548 | "epoch": 7.39, |
| 3549 | "learning_rate": 0.0002594344023323615, |
| 3550 | "loss": 0.0739, |
| 3551 | "step": 5140 |
| 3552 | }, |
| 3553 | { |
| 3554 | "epoch": 7.4, |
| 3555 | "learning_rate": 0.0002593469387755102, |
| 3556 | "loss": 0.0836, |
| 3557 | "step": 5150 |
| 3558 | }, |
| 3559 | { |
| 3560 | "epoch": 7.41, |
| 3561 | "learning_rate": 0.0002592594752186589, |
| 3562 | "loss": 0.073, |
| 3563 | "step": 5160 |
| 3564 | }, |
| 3565 | { |
| 3566 | "epoch": 7.43, |
| 3567 | "learning_rate": 0.00025917201166180754, |
| 3568 | "loss": 0.064, |
| 3569 | "step": 5170 |
| 3570 | }, |
| 3571 | { |
| 3572 | "epoch": 7.44, |
| 3573 | "learning_rate": 0.00025908454810495625, |
| 3574 | "loss": 0.0852, |
| 3575 | "step": 5180 |
| 3576 | }, |
| 3577 | { |
| 3578 | "epoch": 7.46, |
| 3579 | "learning_rate": 0.0002589970845481049, |
| 3580 | "loss": 0.0673, |
| 3581 | "step": 5190 |
| 3582 | }, |
| 3583 | { |
| 3584 | "epoch": 7.47, |
| 3585 | "learning_rate": 0.00025890962099125363, |
| 3586 | "loss": 0.0799, |
| 3587 | "step": 5200 |
| 3588 | }, |
| 3589 | { |
| 3590 | "epoch": 7.47, |
| 3591 | "eval_loss": 0.1826663762331009, |
| 3592 | "eval_runtime": 39.9859, |
| 3593 | "eval_samples_per_second": 11.429, |
| 3594 | "eval_steps_per_second": 1.451, |
| 3595 | "eval_wer": 0.19244089745520254, |
| 3596 | "step": 5200 |
| 3597 | }, |
| 3598 | { |
| 3599 | "epoch": 7.49, |
| 3600 | "learning_rate": 0.0002588221574344023, |
| 3601 | "loss": 0.0698, |
| 3602 | "step": 5210 |
| 3603 | }, |
| 3604 | { |
| 3605 | "epoch": 7.5, |
| 3606 | "learning_rate": 0.000258734693877551, |
| 3607 | "loss": 0.0658, |
| 3608 | "step": 5220 |
| 3609 | }, |
| 3610 | { |
| 3611 | "epoch": 7.51, |
| 3612 | "learning_rate": 0.0002586472303206997, |
| 3613 | "loss": 0.081, |
| 3614 | "step": 5230 |
| 3615 | }, |
| 3616 | { |
| 3617 | "epoch": 7.53, |
| 3618 | "learning_rate": 0.0002585597667638484, |
| 3619 | "loss": 0.0755, |
| 3620 | "step": 5240 |
| 3621 | }, |
| 3622 | { |
| 3623 | "epoch": 7.54, |
| 3624 | "learning_rate": 0.0002584723032069971, |
| 3625 | "loss": 0.0824, |
| 3626 | "step": 5250 |
| 3627 | }, |
| 3628 | { |
| 3629 | "epoch": 7.56, |
| 3630 | "learning_rate": 0.00025838483965014576, |
| 3631 | "loss": 0.0666, |
| 3632 | "step": 5260 |
| 3633 | }, |
| 3634 | { |
| 3635 | "epoch": 7.57, |
| 3636 | "learning_rate": 0.0002582973760932944, |
| 3637 | "loss": 0.0679, |
| 3638 | "step": 5270 |
| 3639 | }, |
| 3640 | { |
| 3641 | "epoch": 7.59, |
| 3642 | "learning_rate": 0.00025820991253644313, |
| 3643 | "loss": 0.0774, |
| 3644 | "step": 5280 |
| 3645 | }, |
| 3646 | { |
| 3647 | "epoch": 7.6, |
| 3648 | "learning_rate": 0.0002581224489795918, |
| 3649 | "loss": 0.0699, |
| 3650 | "step": 5290 |
| 3651 | }, |
| 3652 | { |
| 3653 | "epoch": 7.61, |
| 3654 | "learning_rate": 0.0002580349854227405, |
| 3655 | "loss": 0.0682, |
| 3656 | "step": 5300 |
| 3657 | }, |
| 3658 | { |
| 3659 | "epoch": 7.61, |
| 3660 | "eval_loss": 0.1933245211839676, |
| 3661 | "eval_runtime": 40.0463, |
| 3662 | "eval_samples_per_second": 11.412, |
| 3663 | "eval_steps_per_second": 1.448, |
| 3664 | "eval_wer": 0.19575365155850022, |
| 3665 | "step": 5300 |
| 3666 | }, |
| 3667 | { |
| 3668 | "epoch": 7.63, |
| 3669 | "learning_rate": 0.00025794752186588917, |
| 3670 | "loss": 0.0878, |
| 3671 | "step": 5310 |
| 3672 | }, |
| 3673 | { |
| 3674 | "epoch": 7.64, |
| 3675 | "learning_rate": 0.0002578600583090379, |
| 3676 | "loss": 0.0668, |
| 3677 | "step": 5320 |
| 3678 | }, |
| 3679 | { |
| 3680 | "epoch": 7.66, |
| 3681 | "learning_rate": 0.0002577725947521866, |
| 3682 | "loss": 0.0886, |
| 3683 | "step": 5330 |
| 3684 | }, |
| 3685 | { |
| 3686 | "epoch": 7.67, |
| 3687 | "learning_rate": 0.00025768513119533526, |
| 3688 | "loss": 0.0625, |
| 3689 | "step": 5340 |
| 3690 | }, |
| 3691 | { |
| 3692 | "epoch": 7.69, |
| 3693 | "learning_rate": 0.0002575976676384839, |
| 3694 | "loss": 0.0748, |
| 3695 | "step": 5350 |
| 3696 | }, |
| 3697 | { |
| 3698 | "epoch": 7.7, |
| 3699 | "learning_rate": 0.00025751020408163264, |
| 3700 | "loss": 0.0811, |
| 3701 | "step": 5360 |
| 3702 | }, |
| 3703 | { |
| 3704 | "epoch": 7.72, |
| 3705 | "learning_rate": 0.0002574227405247813, |
| 3706 | "loss": 0.0765, |
| 3707 | "step": 5370 |
| 3708 | }, |
| 3709 | { |
| 3710 | "epoch": 7.73, |
| 3711 | "learning_rate": 0.00025733527696793, |
| 3712 | "loss": 0.0797, |
| 3713 | "step": 5380 |
| 3714 | }, |
| 3715 | { |
| 3716 | "epoch": 7.74, |
| 3717 | "learning_rate": 0.00025724781341107867, |
| 3718 | "loss": 0.0728, |
| 3719 | "step": 5390 |
| 3720 | }, |
| 3721 | { |
| 3722 | "epoch": 7.76, |
| 3723 | "learning_rate": 0.0002571603498542274, |
| 3724 | "loss": 0.0702, |
| 3725 | "step": 5400 |
| 3726 | }, |
| 3727 | { |
| 3728 | "epoch": 7.76, |
| 3729 | "eval_loss": 0.16960883140563965, |
| 3730 | "eval_runtime": 40.0131, |
| 3731 | "eval_samples_per_second": 11.421, |
| 3732 | "eval_steps_per_second": 1.45, |
| 3733 | "eval_wer": 0.17723234452642675, |
| 3734 | "step": 5400 |
| 3735 | }, |
| 3736 | { |
| 3737 | "epoch": 7.77, |
| 3738 | "learning_rate": 0.0002570728862973761, |
| 3739 | "loss": 0.0755, |
| 3740 | "step": 5410 |
| 3741 | }, |
| 3742 | { |
| 3743 | "epoch": 7.79, |
| 3744 | "learning_rate": 0.00025698542274052476, |
| 3745 | "loss": 0.0628, |
| 3746 | "step": 5420 |
| 3747 | }, |
| 3748 | { |
| 3749 | "epoch": 7.8, |
| 3750 | "learning_rate": 0.0002568979591836735, |
| 3751 | "loss": 0.0693, |
| 3752 | "step": 5430 |
| 3753 | }, |
| 3754 | { |
| 3755 | "epoch": 7.82, |
| 3756 | "learning_rate": 0.00025681049562682214, |
| 3757 | "loss": 0.0673, |
| 3758 | "step": 5440 |
| 3759 | }, |
| 3760 | { |
| 3761 | "epoch": 7.83, |
| 3762 | "learning_rate": 0.0002567230320699708, |
| 3763 | "loss": 0.0816, |
| 3764 | "step": 5450 |
| 3765 | }, |
| 3766 | { |
| 3767 | "epoch": 7.84, |
| 3768 | "learning_rate": 0.0002566355685131195, |
| 3769 | "loss": 0.0656, |
| 3770 | "step": 5460 |
| 3771 | }, |
| 3772 | { |
| 3773 | "epoch": 7.86, |
| 3774 | "learning_rate": 0.0002565481049562682, |
| 3775 | "loss": 0.0686, |
| 3776 | "step": 5470 |
| 3777 | }, |
| 3778 | { |
| 3779 | "epoch": 7.87, |
| 3780 | "learning_rate": 0.0002564606413994169, |
| 3781 | "loss": 0.0899, |
| 3782 | "step": 5480 |
| 3783 | }, |
| 3784 | { |
| 3785 | "epoch": 7.89, |
| 3786 | "learning_rate": 0.0002563731778425656, |
| 3787 | "loss": 0.0673, |
| 3788 | "step": 5490 |
| 3789 | }, |
| 3790 | { |
| 3791 | "epoch": 7.9, |
| 3792 | "learning_rate": 0.00025628571428571427, |
| 3793 | "loss": 0.0784, |
| 3794 | "step": 5500 |
| 3795 | }, |
| 3796 | { |
| 3797 | "epoch": 7.9, |
| 3798 | "eval_loss": 0.17280295491218567, |
| 3799 | "eval_runtime": 39.9805, |
| 3800 | "eval_samples_per_second": 11.431, |
| 3801 | "eval_steps_per_second": 1.451, |
| 3802 | "eval_wer": 0.1846107513928625, |
| 3803 | "step": 5500 |
| 3804 | }, |
| 3805 | { |
| 3806 | "epoch": 7.92, |
| 3807 | "learning_rate": 0.000256198250728863, |
| 3808 | "loss": 0.0795, |
| 3809 | "step": 5510 |
| 3810 | }, |
| 3811 | { |
| 3812 | "epoch": 7.93, |
| 3813 | "learning_rate": 0.00025611078717201164, |
| 3814 | "loss": 0.0675, |
| 3815 | "step": 5520 |
| 3816 | }, |
| 3817 | { |
| 3818 | "epoch": 7.95, |
| 3819 | "learning_rate": 0.0002560233236151603, |
| 3820 | "loss": 0.0959, |
| 3821 | "step": 5530 |
| 3822 | }, |
| 3823 | { |
| 3824 | "epoch": 7.96, |
| 3825 | "learning_rate": 0.000255935860058309, |
| 3826 | "loss": 0.0652, |
| 3827 | "step": 5540 |
| 3828 | }, |
| 3829 | { |
| 3830 | "epoch": 7.97, |
| 3831 | "learning_rate": 0.0002558483965014577, |
| 3832 | "loss": 0.0707, |
| 3833 | "step": 5550 |
| 3834 | }, |
| 3835 | { |
| 3836 | "epoch": 7.99, |
| 3837 | "learning_rate": 0.0002557609329446064, |
| 3838 | "loss": 0.0832, |
| 3839 | "step": 5560 |
| 3840 | }, |
| 3841 | { |
| 3842 | "epoch": 8.0, |
| 3843 | "learning_rate": 0.0002556734693877551, |
| 3844 | "loss": 0.0724, |
| 3845 | "step": 5570 |
| 3846 | }, |
| 3847 | { |
| 3848 | "epoch": 8.02, |
| 3849 | "learning_rate": 0.00025558600583090377, |
| 3850 | "loss": 0.0819, |
| 3851 | "step": 5580 |
| 3852 | }, |
| 3853 | { |
| 3854 | "epoch": 8.03, |
| 3855 | "learning_rate": 0.0002554985422740525, |
| 3856 | "loss": 0.0677, |
| 3857 | "step": 5590 |
| 3858 | }, |
| 3859 | { |
| 3860 | "epoch": 8.05, |
| 3861 | "learning_rate": 0.00025541107871720114, |
| 3862 | "loss": 0.0778, |
| 3863 | "step": 5600 |
| 3864 | }, |
| 3865 | { |
| 3866 | "epoch": 8.05, |
| 3867 | "eval_loss": 0.1783214509487152, |
| 3868 | "eval_runtime": 39.8325, |
| 3869 | "eval_samples_per_second": 11.473, |
| 3870 | "eval_steps_per_second": 1.456, |
| 3871 | "eval_wer": 0.1808462580936606, |
| 3872 | "step": 5600 |
| 3873 | }, |
| 3874 | { |
| 3875 | "epoch": 8.06, |
| 3876 | "learning_rate": 0.00025532361516034986, |
| 3877 | "loss": 0.0661, |
| 3878 | "step": 5610 |
| 3879 | }, |
| 3880 | { |
| 3881 | "epoch": 8.07, |
| 3882 | "learning_rate": 0.0002552361516034985, |
| 3883 | "loss": 0.0588, |
| 3884 | "step": 5620 |
| 3885 | }, |
| 3886 | { |
| 3887 | "epoch": 8.09, |
| 3888 | "learning_rate": 0.0002551486880466472, |
| 3889 | "loss": 0.0762, |
| 3890 | "step": 5630 |
| 3891 | }, |
| 3892 | { |
| 3893 | "epoch": 8.1, |
| 3894 | "learning_rate": 0.0002550612244897959, |
| 3895 | "loss": 0.0714, |
| 3896 | "step": 5640 |
| 3897 | }, |
| 3898 | { |
| 3899 | "epoch": 8.12, |
| 3900 | "learning_rate": 0.00025497376093294456, |
| 3901 | "loss": 0.0757, |
| 3902 | "step": 5650 |
| 3903 | }, |
| 3904 | { |
| 3905 | "epoch": 8.13, |
| 3906 | "learning_rate": 0.00025488629737609327, |
| 3907 | "loss": 0.0614, |
| 3908 | "step": 5660 |
| 3909 | }, |
| 3910 | { |
| 3911 | "epoch": 8.15, |
| 3912 | "learning_rate": 0.000254798833819242, |
| 3913 | "loss": 0.0774, |
| 3914 | "step": 5670 |
| 3915 | }, |
| 3916 | { |
| 3917 | "epoch": 8.16, |
| 3918 | "learning_rate": 0.00025471137026239065, |
| 3919 | "loss": 0.0766, |
| 3920 | "step": 5680 |
| 3921 | }, |
| 3922 | { |
| 3923 | "epoch": 8.18, |
| 3924 | "learning_rate": 0.00025462390670553936, |
| 3925 | "loss": 0.0722, |
| 3926 | "step": 5690 |
| 3927 | }, |
| 3928 | { |
| 3929 | "epoch": 8.19, |
| 3930 | "learning_rate": 0.000254536443148688, |
| 3931 | "loss": 0.0906, |
| 3932 | "step": 5700 |
| 3933 | }, |
| 3934 | { |
| 3935 | "epoch": 8.19, |
| 3936 | "eval_loss": 0.1898173987865448, |
| 3937 | "eval_runtime": 40.2295, |
| 3938 | "eval_samples_per_second": 11.36, |
| 3939 | "eval_steps_per_second": 1.442, |
| 3940 | "eval_wer": 0.197259448878181, |
| 3941 | "step": 5700 |
| 3942 | }, |
| 3943 | { |
| 3944 | "epoch": 8.2, |
| 3945 | "learning_rate": 0.0002544489795918367, |
| 3946 | "loss": 0.0685, |
| 3947 | "step": 5710 |
| 3948 | }, |
| 3949 | { |
| 3950 | "epoch": 8.22, |
| 3951 | "learning_rate": 0.0002543615160349854, |
| 3952 | "loss": 0.0812, |
| 3953 | "step": 5720 |
| 3954 | }, |
| 3955 | { |
| 3956 | "epoch": 8.23, |
| 3957 | "learning_rate": 0.00025427405247813406, |
| 3958 | "loss": 0.0798, |
| 3959 | "step": 5730 |
| 3960 | }, |
| 3961 | { |
| 3962 | "epoch": 8.25, |
| 3963 | "learning_rate": 0.0002541865889212828, |
| 3964 | "loss": 0.0655, |
| 3965 | "step": 5740 |
| 3966 | }, |
| 3967 | { |
| 3968 | "epoch": 8.26, |
| 3969 | "learning_rate": 0.0002540991253644315, |
| 3970 | "loss": 0.0838, |
| 3971 | "step": 5750 |
| 3972 | }, |
| 3973 | { |
| 3974 | "epoch": 8.28, |
| 3975 | "learning_rate": 0.00025401166180758015, |
| 3976 | "loss": 0.0831, |
| 3977 | "step": 5760 |
| 3978 | }, |
| 3979 | { |
| 3980 | "epoch": 8.29, |
| 3981 | "learning_rate": 0.00025392419825072887, |
| 3982 | "loss": 0.0761, |
| 3983 | "step": 5770 |
| 3984 | }, |
| 3985 | { |
| 3986 | "epoch": 8.3, |
| 3987 | "learning_rate": 0.0002538367346938775, |
| 3988 | "loss": 0.0653, |
| 3989 | "step": 5780 |
| 3990 | }, |
| 3991 | { |
| 3992 | "epoch": 8.32, |
| 3993 | "learning_rate": 0.00025374927113702624, |
| 3994 | "loss": 0.0701, |
| 3995 | "step": 5790 |
| 3996 | }, |
| 3997 | { |
| 3998 | "epoch": 8.33, |
| 3999 | "learning_rate": 0.0002536618075801749, |
| 4000 | "loss": 0.0842, |
| 4001 | "step": 5800 |
| 4002 | }, |
| 4003 | { |
| 4004 | "epoch": 8.33, |
| 4005 | "eval_loss": 0.17102932929992676, |
| 4006 | "eval_runtime": 40.0617, |
| 4007 | "eval_samples_per_second": 11.407, |
| 4008 | "eval_steps_per_second": 1.448, |
| 4009 | "eval_wer": 0.17934046077397983, |
| 4010 | "step": 5800 |
| 4011 | }, |
| 4012 | { |
| 4013 | "epoch": 8.35, |
| 4014 | "learning_rate": 0.00025357434402332356, |
| 4015 | "loss": 0.0707, |
| 4016 | "step": 5810 |
| 4017 | }, |
| 4018 | { |
| 4019 | "epoch": 8.36, |
| 4020 | "learning_rate": 0.0002534868804664723, |
| 4021 | "loss": 0.0625, |
| 4022 | "step": 5820 |
| 4023 | }, |
| 4024 | { |
| 4025 | "epoch": 8.38, |
| 4026 | "learning_rate": 0.000253399416909621, |
| 4027 | "loss": 0.0818, |
| 4028 | "step": 5830 |
| 4029 | }, |
| 4030 | { |
| 4031 | "epoch": 8.39, |
| 4032 | "learning_rate": 0.00025331195335276965, |
| 4033 | "loss": 0.0644, |
| 4034 | "step": 5840 |
| 4035 | }, |
| 4036 | { |
| 4037 | "epoch": 8.41, |
| 4038 | "learning_rate": 0.00025322448979591837, |
| 4039 | "loss": 0.1082, |
| 4040 | "step": 5850 |
| 4041 | }, |
| 4042 | { |
| 4043 | "epoch": 8.42, |
| 4044 | "learning_rate": 0.00025313702623906703, |
| 4045 | "loss": 0.0661, |
| 4046 | "step": 5860 |
| 4047 | }, |
| 4048 | { |
| 4049 | "epoch": 8.43, |
| 4050 | "learning_rate": 0.00025304956268221574, |
| 4051 | "loss": 0.0726, |
| 4052 | "step": 5870 |
| 4053 | }, |
| 4054 | { |
| 4055 | "epoch": 8.45, |
| 4056 | "learning_rate": 0.0002529620991253644, |
| 4057 | "loss": 0.0922, |
| 4058 | "step": 5880 |
| 4059 | }, |
| 4060 | { |
| 4061 | "epoch": 8.46, |
| 4062 | "learning_rate": 0.00025287463556851307, |
| 4063 | "loss": 0.0689, |
| 4064 | "step": 5890 |
| 4065 | }, |
| 4066 | { |
| 4067 | "epoch": 8.48, |
| 4068 | "learning_rate": 0.0002527871720116618, |
| 4069 | "loss": 0.0701, |
| 4070 | "step": 5900 |
| 4071 | }, |
| 4072 | { |
| 4073 | "epoch": 8.48, |
| 4074 | "eval_loss": 0.18022069334983826, |
| 4075 | "eval_runtime": 39.8801, |
| 4076 | "eval_samples_per_second": 11.459, |
| 4077 | "eval_steps_per_second": 1.454, |
| 4078 | "eval_wer": 0.17918988104201175, |
| 4079 | "step": 5900 |
| 4080 | }, |
| 4081 | { |
| 4082 | "epoch": 8.49, |
| 4083 | "learning_rate": 0.00025269970845481044, |
| 4084 | "loss": 0.0709, |
| 4085 | "step": 5910 |
| 4086 | }, |
| 4087 | { |
| 4088 | "epoch": 8.51, |
| 4089 | "learning_rate": 0.00025261224489795916, |
| 4090 | "loss": 0.0679, |
| 4091 | "step": 5920 |
| 4092 | }, |
| 4093 | { |
| 4094 | "epoch": 8.52, |
| 4095 | "learning_rate": 0.00025252478134110787, |
| 4096 | "loss": 0.0898, |
| 4097 | "step": 5930 |
| 4098 | }, |
| 4099 | { |
| 4100 | "epoch": 8.53, |
| 4101 | "learning_rate": 0.00025243731778425653, |
| 4102 | "loss": 0.0816, |
| 4103 | "step": 5940 |
| 4104 | }, |
| 4105 | { |
| 4106 | "epoch": 8.55, |
| 4107 | "learning_rate": 0.00025234985422740525, |
| 4108 | "loss": 0.0832, |
| 4109 | "step": 5950 |
| 4110 | }, |
| 4111 | { |
| 4112 | "epoch": 8.56, |
| 4113 | "learning_rate": 0.0002522623906705539, |
| 4114 | "loss": 0.0701, |
| 4115 | "step": 5960 |
| 4116 | }, |
| 4117 | { |
| 4118 | "epoch": 8.58, |
| 4119 | "learning_rate": 0.0002521749271137026, |
| 4120 | "loss": 0.0605, |
| 4121 | "step": 5970 |
| 4122 | }, |
| 4123 | { |
| 4124 | "epoch": 8.59, |
| 4125 | "learning_rate": 0.0002520874635568513, |
| 4126 | "loss": 0.0796, |
| 4127 | "step": 5980 |
| 4128 | }, |
| 4129 | { |
| 4130 | "epoch": 8.61, |
| 4131 | "learning_rate": 0.00025199999999999995, |
| 4132 | "loss": 0.0542, |
| 4133 | "step": 5990 |
| 4134 | }, |
| 4135 | { |
| 4136 | "epoch": 8.62, |
| 4137 | "learning_rate": 0.00025191253644314866, |
| 4138 | "loss": 0.0758, |
| 4139 | "step": 6000 |
| 4140 | }, |
| 4141 | { |
| 4142 | "epoch": 8.62, |
| 4143 | "eval_loss": 0.18393321335315704, |
| 4144 | "eval_runtime": 39.9261, |
| 4145 | "eval_samples_per_second": 11.446, |
| 4146 | "eval_steps_per_second": 1.453, |
| 4147 | "eval_wer": 0.18099683782562867, |
| 4148 | "step": 6000 |
| 4149 | }, |
| 4150 | { |
| 4151 | "epoch": 8.64, |
| 4152 | "learning_rate": 0.0002518250728862974, |
| 4153 | "loss": 0.075, |
| 4154 | "step": 6010 |
| 4155 | }, |
| 4156 | { |
| 4157 | "epoch": 8.65, |
| 4158 | "learning_rate": 0.00025173760932944604, |
| 4159 | "loss": 0.0671, |
| 4160 | "step": 6020 |
| 4161 | }, |
| 4162 | { |
| 4163 | "epoch": 8.66, |
| 4164 | "learning_rate": 0.00025165014577259475, |
| 4165 | "loss": 0.0867, |
| 4166 | "step": 6030 |
| 4167 | }, |
| 4168 | { |
| 4169 | "epoch": 8.68, |
| 4170 | "learning_rate": 0.0002515626822157434, |
| 4171 | "loss": 0.0804, |
| 4172 | "step": 6040 |
| 4173 | }, |
| 4174 | { |
| 4175 | "epoch": 8.69, |
| 4176 | "learning_rate": 0.0002514752186588921, |
| 4177 | "loss": 0.0806, |
| 4178 | "step": 6050 |
| 4179 | }, |
| 4180 | { |
| 4181 | "epoch": 8.71, |
| 4182 | "learning_rate": 0.0002513877551020408, |
| 4183 | "loss": 0.0708, |
| 4184 | "step": 6060 |
| 4185 | }, |
| 4186 | { |
| 4187 | "epoch": 8.72, |
| 4188 | "learning_rate": 0.00025130029154518945, |
| 4189 | "loss": 0.0759, |
| 4190 | "step": 6070 |
| 4191 | }, |
| 4192 | { |
| 4193 | "epoch": 8.74, |
| 4194 | "learning_rate": 0.00025121282798833816, |
| 4195 | "loss": 0.0626, |
| 4196 | "step": 6080 |
| 4197 | }, |
| 4198 | { |
| 4199 | "epoch": 8.75, |
| 4200 | "learning_rate": 0.0002511253644314869, |
| 4201 | "loss": 0.0645, |
| 4202 | "step": 6090 |
| 4203 | }, |
| 4204 | { |
| 4205 | "epoch": 8.76, |
| 4206 | "learning_rate": 0.00025103790087463554, |
| 4207 | "loss": 0.0751, |
| 4208 | "step": 6100 |
| 4209 | }, |
| 4210 | { |
| 4211 | "epoch": 8.76, |
| 4212 | "eval_loss": 0.18380357325077057, |
| 4213 | "eval_runtime": 39.9599, |
| 4214 | "eval_samples_per_second": 11.436, |
| 4215 | "eval_steps_per_second": 1.451, |
| 4216 | "eval_wer": 0.1840084324649902, |
| 4217 | "step": 6100 |
| 4218 | }, |
| 4219 | { |
| 4220 | "epoch": 8.78, |
| 4221 | "learning_rate": 0.00025095043731778425, |
| 4222 | "loss": 0.0868, |
| 4223 | "step": 6110 |
| 4224 | }, |
| 4225 | { |
| 4226 | "epoch": 8.79, |
| 4227 | "learning_rate": 0.0002508629737609329, |
| 4228 | "loss": 0.07, |
| 4229 | "step": 6120 |
| 4230 | }, |
| 4231 | { |
| 4232 | "epoch": 8.81, |
| 4233 | "learning_rate": 0.00025077551020408163, |
| 4234 | "loss": 0.0913, |
| 4235 | "step": 6130 |
| 4236 | }, |
| 4237 | { |
| 4238 | "epoch": 8.82, |
| 4239 | "learning_rate": 0.0002506880466472303, |
| 4240 | "loss": 0.0712, |
| 4241 | "step": 6140 |
| 4242 | }, |
| 4243 | { |
| 4244 | "epoch": 8.84, |
| 4245 | "learning_rate": 0.00025060058309037895, |
| 4246 | "loss": 0.0836, |
| 4247 | "step": 6150 |
| 4248 | }, |
| 4249 | { |
| 4250 | "epoch": 8.85, |
| 4251 | "learning_rate": 0.00025051311953352767, |
| 4252 | "loss": 0.074, |
| 4253 | "step": 6160 |
| 4254 | }, |
| 4255 | { |
| 4256 | "epoch": 8.86, |
| 4257 | "learning_rate": 0.00025042565597667633, |
| 4258 | "loss": 0.0745, |
| 4259 | "step": 6170 |
| 4260 | }, |
| 4261 | { |
| 4262 | "epoch": 8.88, |
| 4263 | "learning_rate": 0.00025033819241982504, |
| 4264 | "loss": 0.0895, |
| 4265 | "step": 6180 |
| 4266 | }, |
| 4267 | { |
| 4268 | "epoch": 8.89, |
| 4269 | "learning_rate": 0.00025025072886297376, |
| 4270 | "loss": 0.0674, |
| 4271 | "step": 6190 |
| 4272 | }, |
| 4273 | { |
| 4274 | "epoch": 8.91, |
| 4275 | "learning_rate": 0.0002501632653061224, |
| 4276 | "loss": 0.0773, |
| 4277 | "step": 6200 |
| 4278 | }, |
| 4279 | { |
| 4280 | "epoch": 8.91, |
| 4281 | "eval_loss": 0.187347874045372, |
| 4282 | "eval_runtime": 40.007, |
| 4283 | "eval_samples_per_second": 11.423, |
| 4284 | "eval_steps_per_second": 1.45, |
| 4285 | "eval_wer": 0.1886764041560006, |
| 4286 | "step": 6200 |
| 4287 | }, |
| 4288 | { |
| 4289 | "epoch": 8.92, |
| 4290 | "learning_rate": 0.00025007580174927113, |
| 4291 | "loss": 0.0648, |
| 4292 | "step": 6210 |
| 4293 | }, |
| 4294 | { |
| 4295 | "epoch": 8.94, |
| 4296 | "learning_rate": 0.0002499883381924198, |
| 4297 | "loss": 0.0906, |
| 4298 | "step": 6220 |
| 4299 | }, |
| 4300 | { |
| 4301 | "epoch": 8.95, |
| 4302 | "learning_rate": 0.0002499008746355685, |
| 4303 | "loss": 0.0673, |
| 4304 | "step": 6230 |
| 4305 | }, |
| 4306 | { |
| 4307 | "epoch": 8.97, |
| 4308 | "learning_rate": 0.00024981341107871717, |
| 4309 | "loss": 0.0498, |
| 4310 | "step": 6240 |
| 4311 | }, |
| 4312 | { |
| 4313 | "epoch": 8.98, |
| 4314 | "learning_rate": 0.00024972594752186583, |
| 4315 | "loss": 0.0808, |
| 4316 | "step": 6250 |
| 4317 | }, |
| 4318 | { |
| 4319 | "epoch": 8.99, |
| 4320 | "learning_rate": 0.00024963848396501455, |
| 4321 | "loss": 0.0661, |
| 4322 | "step": 6260 |
| 4323 | }, |
| 4324 | { |
| 4325 | "epoch": 9.01, |
| 4326 | "learning_rate": 0.00024955102040816326, |
| 4327 | "loss": 0.0707, |
| 4328 | "step": 6270 |
| 4329 | }, |
| 4330 | { |
| 4331 | "epoch": 9.02, |
| 4332 | "learning_rate": 0.0002494635568513119, |
| 4333 | "loss": 0.0672, |
| 4334 | "step": 6280 |
| 4335 | }, |
| 4336 | { |
| 4337 | "epoch": 9.04, |
| 4338 | "learning_rate": 0.00024937609329446064, |
| 4339 | "loss": 0.0678, |
| 4340 | "step": 6290 |
| 4341 | }, |
| 4342 | { |
| 4343 | "epoch": 9.05, |
| 4344 | "learning_rate": 0.0002492886297376093, |
| 4345 | "loss": 0.0735, |
| 4346 | "step": 6300 |
| 4347 | }, |
| 4348 | { |
| 4349 | "epoch": 9.05, |
| 4350 | "eval_loss": 0.18213719129562378, |
| 4351 | "eval_runtime": 40.0397, |
| 4352 | "eval_samples_per_second": 11.414, |
| 4353 | "eval_steps_per_second": 1.449, |
| 4354 | "eval_wer": 0.16789640114440596, |
| 4355 | "step": 6300 |
| 4356 | }, |
| 4357 | { |
| 4358 | "epoch": 9.07, |
| 4359 | "learning_rate": 0.000249201166180758, |
| 4360 | "loss": 0.0521, |
| 4361 | "step": 6310 |
| 4362 | }, |
| 4363 | { |
| 4364 | "epoch": 9.08, |
| 4365 | "learning_rate": 0.0002491137026239067, |
| 4366 | "loss": 0.0594, |
| 4367 | "step": 6320 |
| 4368 | }, |
| 4369 | { |
| 4370 | "epoch": 9.09, |
| 4371 | "learning_rate": 0.00024902623906705533, |
| 4372 | "loss": 0.068, |
| 4373 | "step": 6330 |
| 4374 | }, |
| 4375 | { |
| 4376 | "epoch": 9.11, |
| 4377 | "learning_rate": 0.00024893877551020405, |
| 4378 | "loss": 0.0625, |
| 4379 | "step": 6340 |
| 4380 | }, |
| 4381 | { |
| 4382 | "epoch": 9.12, |
| 4383 | "learning_rate": 0.00024885131195335276, |
| 4384 | "loss": 0.088, |
| 4385 | "step": 6350 |
| 4386 | }, |
| 4387 | { |
| 4388 | "epoch": 9.14, |
| 4389 | "learning_rate": 0.0002487638483965014, |
| 4390 | "loss": 0.0838, |
| 4391 | "step": 6360 |
| 4392 | }, |
| 4393 | { |
| 4394 | "epoch": 9.15, |
| 4395 | "learning_rate": 0.00024867638483965014, |
| 4396 | "loss": 0.062, |
| 4397 | "step": 6370 |
| 4398 | }, |
| 4399 | { |
| 4400 | "epoch": 9.17, |
| 4401 | "learning_rate": 0.0002485889212827988, |
| 4402 | "loss": 0.0583, |
| 4403 | "step": 6380 |
| 4404 | }, |
| 4405 | { |
| 4406 | "epoch": 9.18, |
| 4407 | "learning_rate": 0.0002485014577259475, |
| 4408 | "loss": 0.057, |
| 4409 | "step": 6390 |
| 4410 | }, |
| 4411 | { |
| 4412 | "epoch": 9.2, |
| 4413 | "learning_rate": 0.0002484139941690962, |
| 4414 | "loss": 0.0779, |
| 4415 | "step": 6400 |
| 4416 | }, |
| 4417 | { |
| 4418 | "epoch": 9.2, |
| 4419 | "eval_loss": 0.165808767080307, |
| 4420 | "eval_runtime": 39.9557, |
| 4421 | "eval_samples_per_second": 11.438, |
| 4422 | "eval_steps_per_second": 1.452, |
| 4423 | "eval_wer": 0.17060683631983134, |
| 4424 | "step": 6400 |
| 4425 | }, |
| 4426 | { |
| 4427 | "epoch": 9.21, |
| 4428 | "learning_rate": 0.0002483265306122449, |
| 4429 | "loss": 0.0522, |
| 4430 | "step": 6410 |
| 4431 | }, |
| 4432 | { |
| 4433 | "epoch": 9.22, |
| 4434 | "learning_rate": 0.00024823906705539355, |
| 4435 | "loss": 0.0686, |
| 4436 | "step": 6420 |
| 4437 | }, |
| 4438 | { |
| 4439 | "epoch": 9.24, |
| 4440 | "learning_rate": 0.0002481516034985422, |
| 4441 | "loss": 0.0545, |
| 4442 | "step": 6430 |
| 4443 | }, |
| 4444 | { |
| 4445 | "epoch": 9.25, |
| 4446 | "learning_rate": 0.00024806413994169093, |
| 4447 | "loss": 0.0709, |
| 4448 | "step": 6440 |
| 4449 | }, |
| 4450 | { |
| 4451 | "epoch": 9.27, |
| 4452 | "learning_rate": 0.00024797667638483964, |
| 4453 | "loss": 0.0623, |
| 4454 | "step": 6450 |
| 4455 | }, |
| 4456 | { |
| 4457 | "epoch": 9.28, |
| 4458 | "learning_rate": 0.0002478892128279883, |
| 4459 | "loss": 0.0681, |
| 4460 | "step": 6460 |
| 4461 | }, |
| 4462 | { |
| 4463 | "epoch": 9.3, |
| 4464 | "learning_rate": 0.000247801749271137, |
| 4465 | "loss": 0.0617, |
| 4466 | "step": 6470 |
| 4467 | }, |
| 4468 | { |
| 4469 | "epoch": 9.31, |
| 4470 | "learning_rate": 0.0002477142857142857, |
| 4471 | "loss": 0.0659, |
| 4472 | "step": 6480 |
| 4473 | }, |
| 4474 | { |
| 4475 | "epoch": 9.32, |
| 4476 | "learning_rate": 0.0002476268221574344, |
| 4477 | "loss": 0.0674, |
| 4478 | "step": 6490 |
| 4479 | }, |
| 4480 | { |
| 4481 | "epoch": 9.34, |
| 4482 | "learning_rate": 0.00024753935860058306, |
| 4483 | "loss": 0.0655, |
| 4484 | "step": 6500 |
| 4485 | }, |
| 4486 | { |
| 4487 | "epoch": 9.34, |
| 4488 | "eval_loss": 0.16366757452487946, |
| 4489 | "eval_runtime": 39.9847, |
| 4490 | "eval_samples_per_second": 11.429, |
| 4491 | "eval_steps_per_second": 1.451, |
| 4492 | "eval_wer": 0.1683481403403102, |
| 4493 | "step": 6500 |
| 4494 | }, |
| 4495 | { |
| 4496 | "epoch": 9.35, |
| 4497 | "learning_rate": 0.0002474518950437317, |
| 4498 | "loss": 0.0694, |
| 4499 | "step": 6510 |
| 4500 | }, |
| 4501 | { |
| 4502 | "epoch": 9.37, |
| 4503 | "learning_rate": 0.00024736443148688043, |
| 4504 | "loss": 0.073, |
| 4505 | "step": 6520 |
| 4506 | }, |
| 4507 | { |
| 4508 | "epoch": 9.38, |
| 4509 | "learning_rate": 0.00024727696793002915, |
| 4510 | "loss": 0.0614, |
| 4511 | "step": 6530 |
| 4512 | }, |
| 4513 | { |
| 4514 | "epoch": 9.4, |
| 4515 | "learning_rate": 0.0002471895043731778, |
| 4516 | "loss": 0.0538, |
| 4517 | "step": 6540 |
| 4518 | }, |
| 4519 | { |
| 4520 | "epoch": 9.41, |
| 4521 | "learning_rate": 0.0002471020408163265, |
| 4522 | "loss": 0.0779, |
| 4523 | "step": 6550 |
| 4524 | }, |
| 4525 | { |
| 4526 | "epoch": 9.43, |
| 4527 | "learning_rate": 0.0002470145772594752, |
| 4528 | "loss": 0.0556, |
| 4529 | "step": 6560 |
| 4530 | }, |
| 4531 | { |
| 4532 | "epoch": 9.44, |
| 4533 | "learning_rate": 0.0002469271137026239, |
| 4534 | "loss": 0.0848, |
| 4535 | "step": 6570 |
| 4536 | }, |
| 4537 | { |
| 4538 | "epoch": 9.45, |
| 4539 | "learning_rate": 0.00024683965014577256, |
| 4540 | "loss": 0.0705, |
| 4541 | "step": 6580 |
| 4542 | }, |
| 4543 | { |
| 4544 | "epoch": 9.47, |
| 4545 | "learning_rate": 0.0002467521865889213, |
| 4546 | "loss": 0.0638, |
| 4547 | "step": 6590 |
| 4548 | }, |
| 4549 | { |
| 4550 | "epoch": 9.48, |
| 4551 | "learning_rate": 0.00024666472303206993, |
| 4552 | "loss": 0.0651, |
| 4553 | "step": 6600 |
| 4554 | }, |
| 4555 | { |
| 4556 | "epoch": 9.48, |
| 4557 | "eval_loss": 0.16613377630710602, |
| 4558 | "eval_runtime": 40.0138, |
| 4559 | "eval_samples_per_second": 11.421, |
| 4560 | "eval_steps_per_second": 1.449, |
| 4561 | "eval_wer": 0.16940219846408675, |
| 4562 | "step": 6600 |
| 4563 | }, |
| 4564 | { |
| 4565 | "epoch": 9.5, |
| 4566 | "learning_rate": 0.00024657725947521865, |
| 4567 | "loss": 0.055, |
| 4568 | "step": 6610 |
| 4569 | }, |
| 4570 | { |
| 4571 | "epoch": 9.51, |
| 4572 | "learning_rate": 0.0002464897959183673, |
| 4573 | "loss": 0.0659, |
| 4574 | "step": 6620 |
| 4575 | }, |
| 4576 | { |
| 4577 | "epoch": 9.53, |
| 4578 | "learning_rate": 0.000246402332361516, |
| 4579 | "loss": 0.0704, |
| 4580 | "step": 6630 |
| 4581 | }, |
| 4582 | { |
| 4583 | "epoch": 9.54, |
| 4584 | "learning_rate": 0.0002463148688046647, |
| 4585 | "loss": 0.0488, |
| 4586 | "step": 6640 |
| 4587 | }, |
| 4588 | { |
| 4589 | "epoch": 9.55, |
| 4590 | "learning_rate": 0.0002462274052478134, |
| 4591 | "loss": 0.0831, |
| 4592 | "step": 6650 |
| 4593 | }, |
| 4594 | { |
| 4595 | "epoch": 9.57, |
| 4596 | "learning_rate": 0.00024613994169096206, |
| 4597 | "loss": 0.0603, |
| 4598 | "step": 6660 |
| 4599 | }, |
| 4600 | { |
| 4601 | "epoch": 9.58, |
| 4602 | "learning_rate": 0.0002460524781341108, |
| 4603 | "loss": 0.0739, |
| 4604 | "step": 6670 |
| 4605 | }, |
| 4606 | { |
| 4607 | "epoch": 9.6, |
| 4608 | "learning_rate": 0.0002459650145772595, |
| 4609 | "loss": 0.0708, |
| 4610 | "step": 6680 |
| 4611 | }, |
| 4612 | { |
| 4613 | "epoch": 9.61, |
| 4614 | "learning_rate": 0.00024587755102040815, |
| 4615 | "loss": 0.0579, |
| 4616 | "step": 6690 |
| 4617 | }, |
| 4618 | { |
| 4619 | "epoch": 9.63, |
| 4620 | "learning_rate": 0.0002457900874635568, |
| 4621 | "loss": 0.0806, |
| 4622 | "step": 6700 |
| 4623 | }, |
| 4624 | { |
| 4625 | "epoch": 9.63, |
| 4626 | "eval_loss": 0.16738936305046082, |
| 4627 | "eval_runtime": 39.7838, |
| 4628 | "eval_samples_per_second": 11.487, |
| 4629 | "eval_steps_per_second": 1.458, |
| 4630 | "eval_wer": 0.17467248908296942, |
| 4631 | "step": 6700 |
| 4632 | }, |
| 4633 | { |
| 4634 | "epoch": 9.64, |
| 4635 | "learning_rate": 0.00024570262390670553, |
| 4636 | "loss": 0.0572, |
| 4637 | "step": 6710 |
| 4638 | }, |
| 4639 | { |
| 4640 | "epoch": 9.66, |
| 4641 | "learning_rate": 0.0002456151603498542, |
| 4642 | "loss": 0.0713, |
| 4643 | "step": 6720 |
| 4644 | }, |
| 4645 | { |
| 4646 | "epoch": 9.67, |
| 4647 | "learning_rate": 0.0002455276967930029, |
| 4648 | "loss": 0.0787, |
| 4649 | "step": 6730 |
| 4650 | }, |
| 4651 | { |
| 4652 | "epoch": 9.68, |
| 4653 | "learning_rate": 0.00024544023323615156, |
| 4654 | "loss": 0.0651, |
| 4655 | "step": 6740 |
| 4656 | }, |
| 4657 | { |
| 4658 | "epoch": 9.7, |
| 4659 | "learning_rate": 0.0002453527696793003, |
| 4660 | "loss": 0.0677, |
| 4661 | "step": 6750 |
| 4662 | }, |
| 4663 | { |
| 4664 | "epoch": 9.71, |
| 4665 | "learning_rate": 0.000245265306122449, |
| 4666 | "loss": 0.0641, |
| 4667 | "step": 6760 |
| 4668 | }, |
| 4669 | { |
| 4670 | "epoch": 9.73, |
| 4671 | "learning_rate": 0.00024517784256559766, |
| 4672 | "loss": 0.0768, |
| 4673 | "step": 6770 |
| 4674 | }, |
| 4675 | { |
| 4676 | "epoch": 9.74, |
| 4677 | "learning_rate": 0.0002450903790087463, |
| 4678 | "loss": 0.0651, |
| 4679 | "step": 6780 |
| 4680 | }, |
| 4681 | { |
| 4682 | "epoch": 9.76, |
| 4683 | "learning_rate": 0.00024500291545189503, |
| 4684 | "loss": 0.0676, |
| 4685 | "step": 6790 |
| 4686 | }, |
| 4687 | { |
| 4688 | "epoch": 9.77, |
| 4689 | "learning_rate": 0.0002449154518950437, |
| 4690 | "loss": 0.065, |
| 4691 | "step": 6800 |
| 4692 | }, |
| 4693 | { |
| 4694 | "epoch": 9.77, |
| 4695 | "eval_loss": 0.17342041432857513, |
| 4696 | "eval_runtime": 39.9722, |
| 4697 | "eval_samples_per_second": 11.433, |
| 4698 | "eval_steps_per_second": 1.451, |
| 4699 | "eval_wer": 0.17271495256738442, |
| 4700 | "step": 6800 |
| 4701 | }, |
| 4702 | { |
| 4703 | "epoch": 9.78, |
| 4704 | "learning_rate": 0.0002448279883381924, |
| 4705 | "loss": 0.0582, |
| 4706 | "step": 6810 |
| 4707 | }, |
| 4708 | { |
| 4709 | "epoch": 9.8, |
| 4710 | "learning_rate": 0.00024474052478134107, |
| 4711 | "loss": 0.0798, |
| 4712 | "step": 6820 |
| 4713 | }, |
| 4714 | { |
| 4715 | "epoch": 9.81, |
| 4716 | "learning_rate": 0.0002446530612244898, |
| 4717 | "loss": 0.0757, |
| 4718 | "step": 6830 |
| 4719 | }, |
| 4720 | { |
| 4721 | "epoch": 9.83, |
| 4722 | "learning_rate": 0.00024456559766763844, |
| 4723 | "loss": 0.0672, |
| 4724 | "step": 6840 |
| 4725 | }, |
| 4726 | { |
| 4727 | "epoch": 9.84, |
| 4728 | "learning_rate": 0.00024447813411078716, |
| 4729 | "loss": 0.0694, |
| 4730 | "step": 6850 |
| 4731 | }, |
| 4732 | { |
| 4733 | "epoch": 9.86, |
| 4734 | "learning_rate": 0.0002443906705539359, |
| 4735 | "loss": 0.0722, |
| 4736 | "step": 6860 |
| 4737 | }, |
| 4738 | { |
| 4739 | "epoch": 9.87, |
| 4740 | "learning_rate": 0.00024430320699708453, |
| 4741 | "loss": 0.0676, |
| 4742 | "step": 6870 |
| 4743 | }, |
| 4744 | { |
| 4745 | "epoch": 9.89, |
| 4746 | "learning_rate": 0.0002442157434402332, |
| 4747 | "loss": 0.071, |
| 4748 | "step": 6880 |
| 4749 | }, |
| 4750 | { |
| 4751 | "epoch": 9.9, |
| 4752 | "learning_rate": 0.00024412827988338188, |
| 4753 | "loss": 0.0635, |
| 4754 | "step": 6890 |
| 4755 | }, |
| 4756 | { |
| 4757 | "epoch": 9.91, |
| 4758 | "learning_rate": 0.0002440408163265306, |
| 4759 | "loss": 0.0719, |
| 4760 | "step": 6900 |
| 4761 | }, |
| 4762 | { |
| 4763 | "epoch": 9.91, |
| 4764 | "eval_loss": 0.1549205482006073, |
| 4765 | "eval_runtime": 39.9005, |
| 4766 | "eval_samples_per_second": 11.453, |
| 4767 | "eval_steps_per_second": 1.454, |
| 4768 | "eval_wer": 0.1615720524017467, |
| 4769 | "step": 6900 |
| 4770 | }, |
| 4771 | { |
| 4772 | "epoch": 9.93, |
| 4773 | "learning_rate": 0.00024395335276967929, |
| 4774 | "loss": 0.0605, |
| 4775 | "step": 6910 |
| 4776 | }, |
| 4777 | { |
| 4778 | "epoch": 9.94, |
| 4779 | "learning_rate": 0.00024386588921282797, |
| 4780 | "loss": 0.0661, |
| 4781 | "step": 6920 |
| 4782 | }, |
| 4783 | { |
| 4784 | "epoch": 9.96, |
| 4785 | "learning_rate": 0.00024377842565597666, |
| 4786 | "loss": 0.0729, |
| 4787 | "step": 6930 |
| 4788 | }, |
| 4789 | { |
| 4790 | "epoch": 9.97, |
| 4791 | "learning_rate": 0.00024369096209912535, |
| 4792 | "loss": 0.0594, |
| 4793 | "step": 6940 |
| 4794 | }, |
| 4795 | { |
| 4796 | "epoch": 9.99, |
| 4797 | "learning_rate": 0.00024360349854227404, |
| 4798 | "loss": 0.0677, |
| 4799 | "step": 6950 |
| 4800 | }, |
| 4801 | { |
| 4802 | "epoch": 10.0, |
| 4803 | "learning_rate": 0.0002435160349854227, |
| 4804 | "loss": 0.0626, |
| 4805 | "step": 6960 |
| 4806 | }, |
| 4807 | { |
| 4808 | "epoch": 10.01, |
| 4809 | "learning_rate": 0.00024342857142857139, |
| 4810 | "loss": 0.0754, |
| 4811 | "step": 6970 |
| 4812 | }, |
| 4813 | { |
| 4814 | "epoch": 10.03, |
| 4815 | "learning_rate": 0.00024334110787172007, |
| 4816 | "loss": 0.0585, |
| 4817 | "step": 6980 |
| 4818 | }, |
| 4819 | { |
| 4820 | "epoch": 10.04, |
| 4821 | "learning_rate": 0.0002432536443148688, |
| 4822 | "loss": 0.0591, |
| 4823 | "step": 6990 |
| 4824 | }, |
| 4825 | { |
| 4826 | "epoch": 10.06, |
| 4827 | "learning_rate": 0.00024316618075801748, |
| 4828 | "loss": 0.0672, |
| 4829 | "step": 7000 |
| 4830 | }, |
| 4831 | { |
| 4832 | "epoch": 10.06, |
| 4833 | "eval_loss": 0.1598873883485794, |
| 4834 | "eval_runtime": 39.9955, |
| 4835 | "eval_samples_per_second": 11.426, |
| 4836 | "eval_steps_per_second": 1.45, |
| 4837 | "eval_wer": 0.16292726998945942, |
| 4838 | "step": 7000 |
| 4839 | }, |
| 4840 | { |
| 4841 | "epoch": 10.07, |
| 4842 | "learning_rate": 0.00024307871720116617, |
| 4843 | "loss": 0.0445, |
| 4844 | "step": 7010 |
| 4845 | }, |
| 4846 | { |
| 4847 | "epoch": 10.09, |
| 4848 | "learning_rate": 0.00024299125364431485, |
| 4849 | "loss": 0.075, |
| 4850 | "step": 7020 |
| 4851 | }, |
| 4852 | { |
| 4853 | "epoch": 10.1, |
| 4854 | "learning_rate": 0.00024290379008746354, |
| 4855 | "loss": 0.067, |
| 4856 | "step": 7030 |
| 4857 | }, |
| 4858 | { |
| 4859 | "epoch": 10.11, |
| 4860 | "learning_rate": 0.00024281632653061223, |
| 4861 | "loss": 0.0765, |
| 4862 | "step": 7040 |
| 4863 | }, |
| 4864 | { |
| 4865 | "epoch": 10.13, |
| 4866 | "learning_rate": 0.0002427288629737609, |
| 4867 | "loss": 0.0614, |
| 4868 | "step": 7050 |
| 4869 | }, |
| 4870 | { |
| 4871 | "epoch": 10.14, |
| 4872 | "learning_rate": 0.00024264139941690958, |
| 4873 | "loss": 0.0541, |
| 4874 | "step": 7060 |
| 4875 | }, |
| 4876 | { |
| 4877 | "epoch": 10.16, |
| 4878 | "learning_rate": 0.0002425539358600583, |
| 4879 | "loss": 0.076, |
| 4880 | "step": 7070 |
| 4881 | }, |
| 4882 | { |
| 4883 | "epoch": 10.17, |
| 4884 | "learning_rate": 0.00024246647230320698, |
| 4885 | "loss": 0.0833, |
| 4886 | "step": 7080 |
| 4887 | }, |
| 4888 | { |
| 4889 | "epoch": 10.19, |
| 4890 | "learning_rate": 0.00024237900874635567, |
| 4891 | "loss": 0.069, |
| 4892 | "step": 7090 |
| 4893 | }, |
| 4894 | { |
| 4895 | "epoch": 10.2, |
| 4896 | "learning_rate": 0.00024229154518950436, |
| 4897 | "loss": 0.0712, |
| 4898 | "step": 7100 |
| 4899 | }, |
| 4900 | { |
| 4901 | "epoch": 10.2, |
| 4902 | "eval_loss": 0.1684901863336563, |
| 4903 | "eval_runtime": 40.0595, |
| 4904 | "eval_samples_per_second": 11.408, |
| 4905 | "eval_steps_per_second": 1.448, |
| 4906 | "eval_wer": 0.16654118355669326, |
| 4907 | "step": 7100 |
| 4908 | }, |
| 4909 | { |
| 4910 | "epoch": 10.22, |
| 4911 | "learning_rate": 0.00024220408163265304, |
| 4912 | "loss": 0.0585, |
| 4913 | "step": 7110 |
| 4914 | }, |
| 4915 | { |
| 4916 | "epoch": 10.23, |
| 4917 | "learning_rate": 0.00024211661807580173, |
| 4918 | "loss": 0.0802, |
| 4919 | "step": 7120 |
| 4920 | }, |
| 4921 | { |
| 4922 | "epoch": 10.24, |
| 4923 | "learning_rate": 0.00024202915451895042, |
| 4924 | "loss": 0.0573, |
| 4925 | "step": 7130 |
| 4926 | }, |
| 4927 | { |
| 4928 | "epoch": 10.26, |
| 4929 | "learning_rate": 0.00024194169096209908, |
| 4930 | "loss": 0.0692, |
| 4931 | "step": 7140 |
| 4932 | }, |
| 4933 | { |
| 4934 | "epoch": 10.27, |
| 4935 | "learning_rate": 0.00024185422740524777, |
| 4936 | "loss": 0.0664, |
| 4937 | "step": 7150 |
| 4938 | }, |
| 4939 | { |
| 4940 | "epoch": 10.29, |
| 4941 | "learning_rate": 0.00024176676384839648, |
| 4942 | "loss": 0.0585, |
| 4943 | "step": 7160 |
| 4944 | }, |
| 4945 | { |
| 4946 | "epoch": 10.3, |
| 4947 | "learning_rate": 0.00024167930029154517, |
| 4948 | "loss": 0.0776, |
| 4949 | "step": 7170 |
| 4950 | }, |
| 4951 | { |
| 4952 | "epoch": 10.32, |
| 4953 | "learning_rate": 0.00024159183673469386, |
| 4954 | "loss": 0.0606, |
| 4955 | "step": 7180 |
| 4956 | }, |
| 4957 | { |
| 4958 | "epoch": 10.33, |
| 4959 | "learning_rate": 0.00024150437317784255, |
| 4960 | "loss": 0.073, |
| 4961 | "step": 7190 |
| 4962 | }, |
| 4963 | { |
| 4964 | "epoch": 10.34, |
| 4965 | "learning_rate": 0.00024141690962099124, |
| 4966 | "loss": 0.0687, |
| 4967 | "step": 7200 |
| 4968 | }, |
| 4969 | { |
| 4970 | "epoch": 10.34, |
| 4971 | "eval_loss": 0.16169100999832153, |
| 4972 | "eval_runtime": 39.9721, |
| 4973 | "eval_samples_per_second": 11.433, |
| 4974 | "eval_steps_per_second": 1.451, |
| 4975 | "eval_wer": 0.1644330673091402, |
| 4976 | "step": 7200 |
| 4977 | }, |
| 4978 | { |
| 4979 | "epoch": 10.36, |
| 4980 | "learning_rate": 0.00024132944606413992, |
| 4981 | "loss": 0.0499, |
| 4982 | "step": 7210 |
| 4983 | }, |
| 4984 | { |
| 4985 | "epoch": 10.37, |
| 4986 | "learning_rate": 0.0002412419825072886, |
| 4987 | "loss": 0.0765, |
| 4988 | "step": 7220 |
| 4989 | }, |
| 4990 | { |
| 4991 | "epoch": 10.39, |
| 4992 | "learning_rate": 0.00024115451895043727, |
| 4993 | "loss": 0.0591, |
| 4994 | "step": 7230 |
| 4995 | }, |
| 4996 | { |
| 4997 | "epoch": 10.4, |
| 4998 | "learning_rate": 0.00024106705539358596, |
| 4999 | "loss": 0.074, |
| 5000 | "step": 7240 |
| 5001 | }, |
| 5002 | { |
| 5003 | "epoch": 10.42, |
| 5004 | "learning_rate": 0.00024097959183673467, |
| 5005 | "loss": 0.0747, |
| 5006 | "step": 7250 |
| 5007 | }, |
| 5008 | { |
| 5009 | "epoch": 10.43, |
| 5010 | "learning_rate": 0.00024089212827988336, |
| 5011 | "loss": 0.0677, |
| 5012 | "step": 7260 |
| 5013 | }, |
| 5014 | { |
| 5015 | "epoch": 10.45, |
| 5016 | "learning_rate": 0.00024080466472303205, |
| 5017 | "loss": 0.075, |
| 5018 | "step": 7270 |
| 5019 | }, |
| 5020 | { |
| 5021 | "epoch": 10.46, |
| 5022 | "learning_rate": 0.00024071720116618074, |
| 5023 | "loss": 0.0523, |
| 5024 | "step": 7280 |
| 5025 | }, |
| 5026 | { |
| 5027 | "epoch": 10.47, |
| 5028 | "learning_rate": 0.00024062973760932943, |
| 5029 | "loss": 0.0693, |
| 5030 | "step": 7290 |
| 5031 | }, |
| 5032 | { |
| 5033 | "epoch": 10.49, |
| 5034 | "learning_rate": 0.00024054227405247811, |
| 5035 | "loss": 0.0586, |
| 5036 | "step": 7300 |
| 5037 | }, |
| 5038 | { |
| 5039 | "epoch": 10.49, |
| 5040 | "eval_loss": 0.1741245537996292, |
| 5041 | "eval_runtime": 39.8869, |
| 5042 | "eval_samples_per_second": 11.457, |
| 5043 | "eval_steps_per_second": 1.454, |
| 5044 | "eval_wer": 0.17000451739195904, |
| 5045 | "step": 7300 |
| 5046 | }, |
| 5047 | { |
| 5048 | "epoch": 10.5, |
| 5049 | "learning_rate": 0.0002404548104956268, |
| 5050 | "loss": 0.059, |
| 5051 | "step": 7310 |
| 5052 | }, |
| 5053 | { |
| 5054 | "epoch": 10.52, |
| 5055 | "learning_rate": 0.00024036734693877546, |
| 5056 | "loss": 0.0691, |
| 5057 | "step": 7320 |
| 5058 | }, |
| 5059 | { |
| 5060 | "epoch": 10.53, |
| 5061 | "learning_rate": 0.00024027988338192418, |
| 5062 | "loss": 0.0508, |
| 5063 | "step": 7330 |
| 5064 | }, |
| 5065 | { |
| 5066 | "epoch": 10.55, |
| 5067 | "learning_rate": 0.00024019241982507287, |
| 5068 | "loss": 0.0682, |
| 5069 | "step": 7340 |
| 5070 | }, |
| 5071 | { |
| 5072 | "epoch": 10.56, |
| 5073 | "learning_rate": 0.00024010495626822155, |
| 5074 | "loss": 0.0682, |
| 5075 | "step": 7350 |
| 5076 | }, |
| 5077 | { |
| 5078 | "epoch": 10.57, |
| 5079 | "learning_rate": 0.00024001749271137024, |
| 5080 | "loss": 0.0532, |
| 5081 | "step": 7360 |
| 5082 | }, |
| 5083 | { |
| 5084 | "epoch": 10.59, |
| 5085 | "learning_rate": 0.00023993002915451893, |
| 5086 | "loss": 0.0629, |
| 5087 | "step": 7370 |
| 5088 | }, |
| 5089 | { |
| 5090 | "epoch": 10.6, |
| 5091 | "learning_rate": 0.00023984256559766762, |
| 5092 | "loss": 0.064, |
| 5093 | "step": 7380 |
| 5094 | }, |
| 5095 | { |
| 5096 | "epoch": 10.62, |
| 5097 | "learning_rate": 0.0002397551020408163, |
| 5098 | "loss": 0.0692, |
| 5099 | "step": 7390 |
| 5100 | }, |
| 5101 | { |
| 5102 | "epoch": 10.63, |
| 5103 | "learning_rate": 0.00023966763848396502, |
| 5104 | "loss": 0.0628, |
| 5105 | "step": 7400 |
| 5106 | }, |
| 5107 | { |
| 5108 | "epoch": 10.63, |
| 5109 | "eval_loss": 0.175329327583313, |
| 5110 | "eval_runtime": 40.1747, |
| 5111 | "eval_samples_per_second": 11.375, |
| 5112 | "eval_steps_per_second": 1.444, |
| 5113 | "eval_wer": 0.1675952416804698, |
| 5114 | "step": 7400 |
| 5115 | }, |
| 5116 | { |
| 5117 | "epoch": 10.65, |
| 5118 | "learning_rate": 0.00023958017492711365, |
| 5119 | "loss": 0.0557, |
| 5120 | "step": 7410 |
| 5121 | }, |
| 5122 | { |
| 5123 | "epoch": 10.66, |
| 5124 | "learning_rate": 0.00023949271137026237, |
| 5125 | "loss": 0.0771, |
| 5126 | "step": 7420 |
| 5127 | }, |
| 5128 | { |
| 5129 | "epoch": 10.68, |
| 5130 | "learning_rate": 0.00023940524781341106, |
| 5131 | "loss": 0.0599, |
| 5132 | "step": 7430 |
| 5133 | }, |
| 5134 | { |
| 5135 | "epoch": 10.69, |
| 5136 | "learning_rate": 0.00023931778425655974, |
| 5137 | "loss": 0.0782, |
| 5138 | "step": 7440 |
| 5139 | }, |
| 5140 | { |
| 5141 | "epoch": 10.7, |
| 5142 | "learning_rate": 0.00023923032069970843, |
| 5143 | "loss": 0.0611, |
| 5144 | "step": 7450 |
| 5145 | }, |
| 5146 | { |
| 5147 | "epoch": 10.72, |
| 5148 | "learning_rate": 0.00023914285714285712, |
| 5149 | "loss": 0.0488, |
| 5150 | "step": 7460 |
| 5151 | }, |
| 5152 | { |
| 5153 | "epoch": 10.73, |
| 5154 | "learning_rate": 0.0002390553935860058, |
| 5155 | "loss": 0.072, |
| 5156 | "step": 7470 |
| 5157 | }, |
| 5158 | { |
| 5159 | "epoch": 10.75, |
| 5160 | "learning_rate": 0.0002389679300291545, |
| 5161 | "loss": 0.0644, |
| 5162 | "step": 7480 |
| 5163 | }, |
| 5164 | { |
| 5165 | "epoch": 10.76, |
| 5166 | "learning_rate": 0.0002388804664723032, |
| 5167 | "loss": 0.0577, |
| 5168 | "step": 7490 |
| 5169 | }, |
| 5170 | { |
| 5171 | "epoch": 10.78, |
| 5172 | "learning_rate": 0.00023879300291545187, |
| 5173 | "loss": 0.0644, |
| 5174 | "step": 7500 |
| 5175 | }, |
| 5176 | { |
| 5177 | "epoch": 10.78, |
| 5178 | "eval_loss": 0.18111708760261536, |
| 5179 | "eval_runtime": 40.0144, |
| 5180 | "eval_samples_per_second": 11.421, |
| 5181 | "eval_steps_per_second": 1.449, |
| 5182 | "eval_wer": 0.17542538774280983, |
| 5183 | "step": 7500 |
| 5184 | }, |
| 5185 | { |
| 5186 | "epoch": 10.79, |
| 5187 | "learning_rate": 0.00023870553935860056, |
| 5188 | "loss": 0.0564, |
| 5189 | "step": 7510 |
| 5190 | }, |
| 5191 | { |
| 5192 | "epoch": 10.8, |
| 5193 | "learning_rate": 0.00023861807580174925, |
| 5194 | "loss": 0.0675, |
| 5195 | "step": 7520 |
| 5196 | }, |
| 5197 | { |
| 5198 | "epoch": 10.82, |
| 5199 | "learning_rate": 0.00023853061224489794, |
| 5200 | "loss": 0.0585, |
| 5201 | "step": 7530 |
| 5202 | }, |
| 5203 | { |
| 5204 | "epoch": 10.83, |
| 5205 | "learning_rate": 0.00023844314868804662, |
| 5206 | "loss": 0.0811, |
| 5207 | "step": 7540 |
| 5208 | }, |
| 5209 | { |
| 5210 | "epoch": 10.85, |
| 5211 | "learning_rate": 0.0002383556851311953, |
| 5212 | "loss": 0.0647, |
| 5213 | "step": 7550 |
| 5214 | }, |
| 5215 | { |
| 5216 | "epoch": 10.86, |
| 5217 | "learning_rate": 0.000238268221574344, |
| 5218 | "loss": 0.0447, |
| 5219 | "step": 7560 |
| 5220 | }, |
| 5221 | { |
| 5222 | "epoch": 10.88, |
| 5223 | "learning_rate": 0.00023818075801749271, |
| 5224 | "loss": 0.0748, |
| 5225 | "step": 7570 |
| 5226 | }, |
| 5227 | { |
| 5228 | "epoch": 10.89, |
| 5229 | "learning_rate": 0.0002380932944606414, |
| 5230 | "loss": 0.0535, |
| 5231 | "step": 7580 |
| 5232 | }, |
| 5233 | { |
| 5234 | "epoch": 10.91, |
| 5235 | "learning_rate": 0.00023800583090379006, |
| 5236 | "loss": 0.0638, |
| 5237 | "step": 7590 |
| 5238 | }, |
| 5239 | { |
| 5240 | "epoch": 10.92, |
| 5241 | "learning_rate": 0.00023791836734693875, |
| 5242 | "loss": 0.0583, |
| 5243 | "step": 7600 |
| 5244 | }, |
| 5245 | { |
| 5246 | "epoch": 10.92, |
| 5247 | "eval_loss": 0.16907170414924622, |
| 5248 | "eval_runtime": 39.9078, |
| 5249 | "eval_samples_per_second": 11.451, |
| 5250 | "eval_steps_per_second": 1.453, |
| 5251 | "eval_wer": 0.17647944586658637, |
| 5252 | "step": 7600 |
| 5253 | }, |
| 5254 | { |
| 5255 | "epoch": 10.93, |
| 5256 | "learning_rate": 0.00023783090379008744, |
| 5257 | "loss": 0.053, |
| 5258 | "step": 7610 |
| 5259 | }, |
| 5260 | { |
| 5261 | "epoch": 10.95, |
| 5262 | "learning_rate": 0.00023774344023323613, |
| 5263 | "loss": 0.0822, |
| 5264 | "step": 7620 |
| 5265 | }, |
| 5266 | { |
| 5267 | "epoch": 10.96, |
| 5268 | "learning_rate": 0.00023765597667638481, |
| 5269 | "loss": 0.0535, |
| 5270 | "step": 7630 |
| 5271 | }, |
| 5272 | { |
| 5273 | "epoch": 10.98, |
| 5274 | "learning_rate": 0.0002375685131195335, |
| 5275 | "loss": 0.0611, |
| 5276 | "step": 7640 |
| 5277 | }, |
| 5278 | { |
| 5279 | "epoch": 10.99, |
| 5280 | "learning_rate": 0.0002374810495626822, |
| 5281 | "loss": 0.0452, |
| 5282 | "step": 7650 |
| 5283 | }, |
| 5284 | { |
| 5285 | "epoch": 11.01, |
| 5286 | "learning_rate": 0.0002373935860058309, |
| 5287 | "loss": 0.0676, |
| 5288 | "step": 7660 |
| 5289 | }, |
| 5290 | { |
| 5291 | "epoch": 11.02, |
| 5292 | "learning_rate": 0.0002373061224489796, |
| 5293 | "loss": 0.0563, |
| 5294 | "step": 7670 |
| 5295 | }, |
| 5296 | { |
| 5297 | "epoch": 11.03, |
| 5298 | "learning_rate": 0.00023721865889212825, |
| 5299 | "loss": 0.0537, |
| 5300 | "step": 7680 |
| 5301 | }, |
| 5302 | { |
| 5303 | "epoch": 11.05, |
| 5304 | "learning_rate": 0.00023713119533527694, |
| 5305 | "loss": 0.0702, |
| 5306 | "step": 7690 |
| 5307 | }, |
| 5308 | { |
| 5309 | "epoch": 11.06, |
| 5310 | "learning_rate": 0.00023704373177842563, |
| 5311 | "loss": 0.0645, |
| 5312 | "step": 7700 |
| 5313 | }, |
| 5314 | { |
| 5315 | "epoch": 11.06, |
| 5316 | "eval_loss": 0.16939429938793182, |
| 5317 | "eval_runtime": 39.8761, |
| 5318 | "eval_samples_per_second": 11.461, |
| 5319 | "eval_steps_per_second": 1.455, |
| 5320 | "eval_wer": 0.16684234302062942, |
| 5321 | "step": 7700 |
| 5322 | }, |
| 5323 | { |
| 5324 | "epoch": 11.08, |
| 5325 | "learning_rate": 0.00023695626822157432, |
| 5326 | "loss": 0.0638, |
| 5327 | "step": 7710 |
| 5328 | }, |
| 5329 | { |
| 5330 | "epoch": 11.09, |
| 5331 | "learning_rate": 0.000236868804664723, |
| 5332 | "loss": 0.0513, |
| 5333 | "step": 7720 |
| 5334 | }, |
| 5335 | { |
| 5336 | "epoch": 11.11, |
| 5337 | "learning_rate": 0.0002367813411078717, |
| 5338 | "loss": 0.0416, |
| 5339 | "step": 7730 |
| 5340 | }, |
| 5341 | { |
| 5342 | "epoch": 11.12, |
| 5343 | "learning_rate": 0.00023669387755102038, |
| 5344 | "loss": 0.0846, |
| 5345 | "step": 7740 |
| 5346 | }, |
| 5347 | { |
| 5348 | "epoch": 11.14, |
| 5349 | "learning_rate": 0.0002366064139941691, |
| 5350 | "loss": 0.0552, |
| 5351 | "step": 7750 |
| 5352 | }, |
| 5353 | { |
| 5354 | "epoch": 11.15, |
| 5355 | "learning_rate": 0.00023651895043731778, |
| 5356 | "loss": 0.061, |
| 5357 | "step": 7760 |
| 5358 | }, |
| 5359 | { |
| 5360 | "epoch": 11.16, |
| 5361 | "learning_rate": 0.00023643148688046645, |
| 5362 | "loss": 0.0928, |
| 5363 | "step": 7770 |
| 5364 | }, |
| 5365 | { |
| 5366 | "epoch": 11.18, |
| 5367 | "learning_rate": 0.00023634402332361513, |
| 5368 | "loss": 0.0694, |
| 5369 | "step": 7780 |
| 5370 | }, |
| 5371 | { |
| 5372 | "epoch": 11.19, |
| 5373 | "learning_rate": 0.00023625655976676382, |
| 5374 | "loss": 0.0618, |
| 5375 | "step": 7790 |
| 5376 | }, |
| 5377 | { |
| 5378 | "epoch": 11.21, |
| 5379 | "learning_rate": 0.0002361690962099125, |
| 5380 | "loss": 0.0608, |
| 5381 | "step": 7800 |
| 5382 | }, |
| 5383 | { |
| 5384 | "epoch": 11.21, |
| 5385 | "eval_loss": 0.17372234165668488, |
| 5386 | "eval_runtime": 40.0285, |
| 5387 | "eval_samples_per_second": 11.417, |
| 5388 | "eval_steps_per_second": 1.449, |
| 5389 | "eval_wer": 0.16488480650504442, |
| 5390 | "step": 7800 |
| 5391 | }, |
| 5392 | { |
| 5393 | "epoch": 11.22, |
| 5394 | "learning_rate": 0.0002360816326530612, |
| 5395 | "loss": 0.067, |
| 5396 | "step": 7810 |
| 5397 | }, |
| 5398 | { |
| 5399 | "epoch": 11.24, |
| 5400 | "learning_rate": 0.00023599416909620988, |
| 5401 | "loss": 0.0566, |
| 5402 | "step": 7820 |
| 5403 | }, |
| 5404 | { |
| 5405 | "epoch": 11.25, |
| 5406 | "learning_rate": 0.0002359067055393586, |
| 5407 | "loss": 0.0471, |
| 5408 | "step": 7830 |
| 5409 | }, |
| 5410 | { |
| 5411 | "epoch": 11.26, |
| 5412 | "learning_rate": 0.0002358192419825073, |
| 5413 | "loss": 0.0689, |
| 5414 | "step": 7840 |
| 5415 | }, |
| 5416 | { |
| 5417 | "epoch": 11.28, |
| 5418 | "learning_rate": 0.00023573177842565598, |
| 5419 | "loss": 0.0483, |
| 5420 | "step": 7850 |
| 5421 | }, |
| 5422 | { |
| 5423 | "epoch": 11.29, |
| 5424 | "learning_rate": 0.00023564431486880464, |
| 5425 | "loss": 0.07, |
| 5426 | "step": 7860 |
| 5427 | }, |
| 5428 | { |
| 5429 | "epoch": 11.31, |
| 5430 | "learning_rate": 0.00023555685131195332, |
| 5431 | "loss": 0.0636, |
| 5432 | "step": 7870 |
| 5433 | }, |
| 5434 | { |
| 5435 | "epoch": 11.32, |
| 5436 | "learning_rate": 0.000235469387755102, |
| 5437 | "loss": 0.0522, |
| 5438 | "step": 7880 |
| 5439 | }, |
| 5440 | { |
| 5441 | "epoch": 11.34, |
| 5442 | "learning_rate": 0.0002353819241982507, |
| 5443 | "loss": 0.0678, |
| 5444 | "step": 7890 |
| 5445 | }, |
| 5446 | { |
| 5447 | "epoch": 11.35, |
| 5448 | "learning_rate": 0.0002352944606413994, |
| 5449 | "loss": 0.0532, |
| 5450 | "step": 7900 |
| 5451 | }, |
| 5452 | { |
| 5453 | "epoch": 11.35, |
| 5454 | "eval_loss": 0.17522485554218292, |
| 5455 | "eval_runtime": 39.7919, |
| 5456 | "eval_samples_per_second": 11.485, |
| 5457 | "eval_steps_per_second": 1.458, |
| 5458 | "eval_wer": 0.17000451739195904, |
| 5459 | "step": 7900 |
| 5460 | }, |
| 5461 | { |
| 5462 | "epoch": 11.36, |
| 5463 | "learning_rate": 0.00023520699708454808, |
| 5464 | "loss": 0.0525, |
| 5465 | "step": 7910 |
| 5466 | }, |
| 5467 | { |
| 5468 | "epoch": 11.38, |
| 5469 | "learning_rate": 0.0002351195335276968, |
| 5470 | "loss": 0.0693, |
| 5471 | "step": 7920 |
| 5472 | }, |
| 5473 | { |
| 5474 | "epoch": 11.39, |
| 5475 | "learning_rate": 0.00023503206997084548, |
| 5476 | "loss": 0.0508, |
| 5477 | "step": 7930 |
| 5478 | }, |
| 5479 | { |
| 5480 | "epoch": 11.41, |
| 5481 | "learning_rate": 0.00023494460641399417, |
| 5482 | "loss": 0.0626, |
| 5483 | "step": 7940 |
| 5484 | }, |
| 5485 | { |
| 5486 | "epoch": 11.42, |
| 5487 | "learning_rate": 0.00023485714285714283, |
| 5488 | "loss": 0.06, |
| 5489 | "step": 7950 |
| 5490 | }, |
| 5491 | { |
| 5492 | "epoch": 11.44, |
| 5493 | "learning_rate": 0.00023476967930029152, |
| 5494 | "loss": 0.0545, |
| 5495 | "step": 7960 |
| 5496 | }, |
| 5497 | { |
| 5498 | "epoch": 11.45, |
| 5499 | "learning_rate": 0.0002346822157434402, |
| 5500 | "loss": 0.0621, |
| 5501 | "step": 7970 |
| 5502 | }, |
| 5503 | { |
| 5504 | "epoch": 11.47, |
| 5505 | "learning_rate": 0.0002345947521865889, |
| 5506 | "loss": 0.0467, |
| 5507 | "step": 7980 |
| 5508 | }, |
| 5509 | { |
| 5510 | "epoch": 11.48, |
| 5511 | "learning_rate": 0.00023450728862973758, |
| 5512 | "loss": 0.0839, |
| 5513 | "step": 7990 |
| 5514 | }, |
| 5515 | { |
| 5516 | "epoch": 11.49, |
| 5517 | "learning_rate": 0.0002344198250728863, |
| 5518 | "loss": 0.0557, |
| 5519 | "step": 8000 |
| 5520 | }, |
| 5521 | { |
| 5522 | "epoch": 11.49, |
| 5523 | "eval_loss": 0.18215720355510712, |
| 5524 | "eval_runtime": 39.894, |
| 5525 | "eval_samples_per_second": 11.455, |
| 5526 | "eval_steps_per_second": 1.454, |
| 5527 | "eval_wer": 0.1724137931034483, |
| 5528 | "step": 8000 |
| 5529 | }, |
| 5530 | { |
| 5531 | "epoch": 11.51, |
| 5532 | "learning_rate": 0.00023433236151603498, |
| 5533 | "loss": 0.0648, |
| 5534 | "step": 8010 |
| 5535 | }, |
| 5536 | { |
| 5537 | "epoch": 11.52, |
| 5538 | "learning_rate": 0.00023424489795918367, |
| 5539 | "loss": 0.0612, |
| 5540 | "step": 8020 |
| 5541 | }, |
| 5542 | { |
| 5543 | "epoch": 11.54, |
| 5544 | "learning_rate": 0.00023415743440233236, |
| 5545 | "loss": 0.0621, |
| 5546 | "step": 8030 |
| 5547 | }, |
| 5548 | { |
| 5549 | "epoch": 11.55, |
| 5550 | "learning_rate": 0.00023406997084548102, |
| 5551 | "loss": 0.065, |
| 5552 | "step": 8040 |
| 5553 | }, |
| 5554 | { |
| 5555 | "epoch": 11.57, |
| 5556 | "learning_rate": 0.0002339825072886297, |
| 5557 | "loss": 0.0541, |
| 5558 | "step": 8050 |
| 5559 | }, |
| 5560 | { |
| 5561 | "epoch": 11.58, |
| 5562 | "learning_rate": 0.0002338950437317784, |
| 5563 | "loss": 0.0633, |
| 5564 | "step": 8060 |
| 5565 | }, |
| 5566 | { |
| 5567 | "epoch": 11.59, |
| 5568 | "learning_rate": 0.00023380758017492708, |
| 5569 | "loss": 0.0753, |
| 5570 | "step": 8070 |
| 5571 | }, |
| 5572 | { |
| 5573 | "epoch": 11.61, |
| 5574 | "learning_rate": 0.00023372011661807577, |
| 5575 | "loss": 0.0683, |
| 5576 | "step": 8080 |
| 5577 | }, |
| 5578 | { |
| 5579 | "epoch": 11.62, |
| 5580 | "learning_rate": 0.00023363265306122448, |
| 5581 | "loss": 0.0608, |
| 5582 | "step": 8090 |
| 5583 | }, |
| 5584 | { |
| 5585 | "epoch": 11.64, |
| 5586 | "learning_rate": 0.00023354518950437317, |
| 5587 | "loss": 0.0532, |
| 5588 | "step": 8100 |
| 5589 | }, |
| 5590 | { |
| 5591 | "epoch": 11.64, |
| 5592 | "eval_loss": 0.17462661862373352, |
| 5593 | "eval_runtime": 39.9062, |
| 5594 | "eval_samples_per_second": 11.452, |
| 5595 | "eval_steps_per_second": 1.453, |
| 5596 | "eval_wer": 0.16202379159765096, |
| 5597 | "step": 8100 |
| 5598 | }, |
| 5599 | { |
| 5600 | "epoch": 11.65, |
| 5601 | "learning_rate": 0.00023345772594752186, |
| 5602 | "loss": 0.0574, |
| 5603 | "step": 8110 |
| 5604 | }, |
| 5605 | { |
| 5606 | "epoch": 11.67, |
| 5607 | "learning_rate": 0.00023337026239067055, |
| 5608 | "loss": 0.0694, |
| 5609 | "step": 8120 |
| 5610 | }, |
| 5611 | { |
| 5612 | "epoch": 11.68, |
| 5613 | "learning_rate": 0.0002332827988338192, |
| 5614 | "loss": 0.0531, |
| 5615 | "step": 8130 |
| 5616 | }, |
| 5617 | { |
| 5618 | "epoch": 11.7, |
| 5619 | "learning_rate": 0.0002331953352769679, |
| 5620 | "loss": 0.0761, |
| 5621 | "step": 8140 |
| 5622 | }, |
| 5623 | { |
| 5624 | "epoch": 11.71, |
| 5625 | "learning_rate": 0.00023310787172011659, |
| 5626 | "loss": 0.06, |
| 5627 | "step": 8150 |
| 5628 | }, |
| 5629 | { |
| 5630 | "epoch": 11.72, |
| 5631 | "learning_rate": 0.00023302040816326527, |
| 5632 | "loss": 0.0786, |
| 5633 | "step": 8160 |
| 5634 | }, |
| 5635 | { |
| 5636 | "epoch": 11.74, |
| 5637 | "learning_rate": 0.00023293294460641396, |
| 5638 | "loss": 0.0744, |
| 5639 | "step": 8170 |
| 5640 | }, |
| 5641 | { |
| 5642 | "epoch": 11.75, |
| 5643 | "learning_rate": 0.00023284548104956268, |
| 5644 | "loss": 0.0621, |
| 5645 | "step": 8180 |
| 5646 | }, |
| 5647 | { |
| 5648 | "epoch": 11.77, |
| 5649 | "learning_rate": 0.00023275801749271136, |
| 5650 | "loss": 0.0738, |
| 5651 | "step": 8190 |
| 5652 | }, |
| 5653 | { |
| 5654 | "epoch": 11.78, |
| 5655 | "learning_rate": 0.00023267055393586005, |
| 5656 | "loss": 0.0492, |
| 5657 | "step": 8200 |
| 5658 | }, |
| 5659 | { |
| 5660 | "epoch": 11.78, |
| 5661 | "eval_loss": 0.17493364214897156, |
| 5662 | "eval_runtime": 39.8456, |
| 5663 | "eval_samples_per_second": 11.469, |
| 5664 | "eval_steps_per_second": 1.456, |
| 5665 | "eval_wer": 0.1630778497214275, |
| 5666 | "step": 8200 |
| 5667 | }, |
| 5668 | { |
| 5669 | "epoch": 11.8, |
| 5670 | "learning_rate": 0.00023258309037900874, |
| 5671 | "loss": 0.0569, |
| 5672 | "step": 8210 |
| 5673 | }, |
| 5674 | { |
| 5675 | "epoch": 11.81, |
| 5676 | "learning_rate": 0.0002324956268221574, |
| 5677 | "loss": 0.0762, |
| 5678 | "step": 8220 |
| 5679 | }, |
| 5680 | { |
| 5681 | "epoch": 11.82, |
| 5682 | "learning_rate": 0.0002324081632653061, |
| 5683 | "loss": 0.0511, |
| 5684 | "step": 8230 |
| 5685 | }, |
| 5686 | { |
| 5687 | "epoch": 11.84, |
| 5688 | "learning_rate": 0.00023232069970845478, |
| 5689 | "loss": 0.0685, |
| 5690 | "step": 8240 |
| 5691 | }, |
| 5692 | { |
| 5693 | "epoch": 11.85, |
| 5694 | "learning_rate": 0.00023223323615160346, |
| 5695 | "loss": 0.0643, |
| 5696 | "step": 8250 |
| 5697 | }, |
| 5698 | { |
| 5699 | "epoch": 11.87, |
| 5700 | "learning_rate": 0.00023214577259475218, |
| 5701 | "loss": 0.0654, |
| 5702 | "step": 8260 |
| 5703 | }, |
| 5704 | { |
| 5705 | "epoch": 11.88, |
| 5706 | "learning_rate": 0.00023205830903790087, |
| 5707 | "loss": 0.0624, |
| 5708 | "step": 8270 |
| 5709 | }, |
| 5710 | { |
| 5711 | "epoch": 11.9, |
| 5712 | "learning_rate": 0.00023197084548104955, |
| 5713 | "loss": 0.0555, |
| 5714 | "step": 8280 |
| 5715 | }, |
| 5716 | { |
| 5717 | "epoch": 11.91, |
| 5718 | "learning_rate": 0.00023188338192419824, |
| 5719 | "loss": 0.0715, |
| 5720 | "step": 8290 |
| 5721 | }, |
| 5722 | { |
| 5723 | "epoch": 11.93, |
| 5724 | "learning_rate": 0.00023179591836734693, |
| 5725 | "loss": 0.0606, |
| 5726 | "step": 8300 |
| 5727 | }, |
| 5728 | { |
| 5729 | "epoch": 11.93, |
| 5730 | "eval_loss": 0.1753462255001068, |
| 5731 | "eval_runtime": 39.9815, |
| 5732 | "eval_samples_per_second": 11.43, |
| 5733 | "eval_steps_per_second": 1.451, |
| 5734 | "eval_wer": 0.1683481403403102, |
| 5735 | "step": 8300 |
| 5736 | }, |
| 5737 | { |
| 5738 | "epoch": 11.94, |
| 5739 | "learning_rate": 0.0002317084548104956, |
| 5740 | "loss": 0.0608, |
| 5741 | "step": 8310 |
| 5742 | }, |
| 5743 | { |
| 5744 | "epoch": 11.95, |
| 5745 | "learning_rate": 0.00023162099125364428, |
| 5746 | "loss": 0.062, |
| 5747 | "step": 8320 |
| 5748 | }, |
| 5749 | { |
| 5750 | "epoch": 11.97, |
| 5751 | "learning_rate": 0.00023153352769679297, |
| 5752 | "loss": 0.0617, |
| 5753 | "step": 8330 |
| 5754 | }, |
| 5755 | { |
| 5756 | "epoch": 11.98, |
| 5757 | "learning_rate": 0.00023144606413994166, |
| 5758 | "loss": 0.0719, |
| 5759 | "step": 8340 |
| 5760 | }, |
| 5761 | { |
| 5762 | "epoch": 12.0, |
| 5763 | "learning_rate": 0.00023135860058309037, |
| 5764 | "loss": 0.0741, |
| 5765 | "step": 8350 |
| 5766 | }, |
| 5767 | { |
| 5768 | "epoch": 12.01, |
| 5769 | "learning_rate": 0.00023127113702623906, |
| 5770 | "loss": 0.0808, |
| 5771 | "step": 8360 |
| 5772 | }, |
| 5773 | { |
| 5774 | "epoch": 12.03, |
| 5775 | "learning_rate": 0.00023118367346938775, |
| 5776 | "loss": 0.062, |
| 5777 | "step": 8370 |
| 5778 | }, |
| 5779 | { |
| 5780 | "epoch": 12.04, |
| 5781 | "learning_rate": 0.00023109620991253643, |
| 5782 | "loss": 0.0636, |
| 5783 | "step": 8380 |
| 5784 | }, |
| 5785 | { |
| 5786 | "epoch": 12.05, |
| 5787 | "learning_rate": 0.00023100874635568512, |
| 5788 | "loss": 0.0585, |
| 5789 | "step": 8390 |
| 5790 | }, |
| 5791 | { |
| 5792 | "epoch": 12.07, |
| 5793 | "learning_rate": 0.00023092128279883378, |
| 5794 | "loss": 0.0523, |
| 5795 | "step": 8400 |
| 5796 | }, |
| 5797 | { |
| 5798 | "epoch": 12.07, |
| 5799 | "eval_loss": 0.17258815467357635, |
| 5800 | "eval_runtime": 39.8367, |
| 5801 | "eval_samples_per_second": 11.472, |
| 5802 | "eval_steps_per_second": 1.456, |
| 5803 | "eval_wer": 0.1624755307935552, |
| 5804 | "step": 8400 |
| 5805 | }, |
| 5806 | { |
| 5807 | "epoch": 12.08, |
| 5808 | "learning_rate": 0.00023083381924198247, |
| 5809 | "loss": 0.064, |
| 5810 | "step": 8410 |
| 5811 | }, |
| 5812 | { |
| 5813 | "epoch": 12.1, |
| 5814 | "learning_rate": 0.00023074635568513116, |
| 5815 | "loss": 0.0615, |
| 5816 | "step": 8420 |
| 5817 | }, |
| 5818 | { |
| 5819 | "epoch": 12.11, |
| 5820 | "learning_rate": 0.00023065889212827985, |
| 5821 | "loss": 0.0614, |
| 5822 | "step": 8430 |
| 5823 | }, |
| 5824 | { |
| 5825 | "epoch": 12.13, |
| 5826 | "learning_rate": 0.00023057142857142856, |
| 5827 | "loss": 0.0811, |
| 5828 | "step": 8440 |
| 5829 | }, |
| 5830 | { |
| 5831 | "epoch": 12.14, |
| 5832 | "learning_rate": 0.00023048396501457725, |
| 5833 | "loss": 0.0522, |
| 5834 | "step": 8450 |
| 5835 | }, |
| 5836 | { |
| 5837 | "epoch": 12.16, |
| 5838 | "learning_rate": 0.00023039650145772594, |
| 5839 | "loss": 0.0809, |
| 5840 | "step": 8460 |
| 5841 | }, |
| 5842 | { |
| 5843 | "epoch": 12.17, |
| 5844 | "learning_rate": 0.00023030903790087462, |
| 5845 | "loss": 0.0437, |
| 5846 | "step": 8470 |
| 5847 | }, |
| 5848 | { |
| 5849 | "epoch": 12.18, |
| 5850 | "learning_rate": 0.0002302215743440233, |
| 5851 | "loss": 0.0546, |
| 5852 | "step": 8480 |
| 5853 | }, |
| 5854 | { |
| 5855 | "epoch": 12.2, |
| 5856 | "learning_rate": 0.00023013411078717197, |
| 5857 | "loss": 0.0621, |
| 5858 | "step": 8490 |
| 5859 | }, |
| 5860 | { |
| 5861 | "epoch": 12.21, |
| 5862 | "learning_rate": 0.00023004664723032066, |
| 5863 | "loss": 0.0577, |
| 5864 | "step": 8500 |
| 5865 | }, |
| 5866 | { |
| 5867 | "epoch": 12.21, |
| 5868 | "eval_loss": 0.17561942338943481, |
| 5869 | "eval_runtime": 39.9824, |
| 5870 | "eval_samples_per_second": 11.43, |
| 5871 | "eval_steps_per_second": 1.451, |
| 5872 | "eval_wer": 0.17015509712392712, |
| 5873 | "step": 8500 |
| 5874 | }, |
| 5875 | { |
| 5876 | "epoch": 12.23, |
| 5877 | "learning_rate": 0.00022995918367346935, |
| 5878 | "loss": 0.07, |
| 5879 | "step": 8510 |
| 5880 | }, |
| 5881 | { |
| 5882 | "epoch": 12.24, |
| 5883 | "learning_rate": 0.00022987172011661806, |
| 5884 | "loss": 0.0501, |
| 5885 | "step": 8520 |
| 5886 | }, |
| 5887 | { |
| 5888 | "epoch": 12.26, |
| 5889 | "learning_rate": 0.00022978425655976675, |
| 5890 | "loss": 0.0515, |
| 5891 | "step": 8530 |
| 5892 | }, |
| 5893 | { |
| 5894 | "epoch": 12.27, |
| 5895 | "learning_rate": 0.00022969679300291544, |
| 5896 | "loss": 0.0658, |
| 5897 | "step": 8540 |
| 5898 | }, |
| 5899 | { |
| 5900 | "epoch": 12.28, |
| 5901 | "learning_rate": 0.00022960932944606413, |
| 5902 | "loss": 0.05, |
| 5903 | "step": 8550 |
| 5904 | }, |
| 5905 | { |
| 5906 | "epoch": 12.3, |
| 5907 | "learning_rate": 0.00022952186588921282, |
| 5908 | "loss": 0.0559, |
| 5909 | "step": 8560 |
| 5910 | }, |
| 5911 | { |
| 5912 | "epoch": 12.31, |
| 5913 | "learning_rate": 0.0002294344023323615, |
| 5914 | "loss": 0.0461, |
| 5915 | "step": 8570 |
| 5916 | }, |
| 5917 | { |
| 5918 | "epoch": 12.33, |
| 5919 | "learning_rate": 0.00022934693877551016, |
| 5920 | "loss": 0.0654, |
| 5921 | "step": 8580 |
| 5922 | }, |
| 5923 | { |
| 5924 | "epoch": 12.34, |
| 5925 | "learning_rate": 0.00022925947521865885, |
| 5926 | "loss": 0.0583, |
| 5927 | "step": 8590 |
| 5928 | }, |
| 5929 | { |
| 5930 | "epoch": 12.36, |
| 5931 | "learning_rate": 0.00022917201166180754, |
| 5932 | "loss": 0.061, |
| 5933 | "step": 8600 |
| 5934 | }, |
| 5935 | { |
| 5936 | "epoch": 12.36, |
| 5937 | "eval_loss": 0.16998374462127686, |
| 5938 | "eval_runtime": 39.9068, |
| 5939 | "eval_samples_per_second": 11.452, |
| 5940 | "eval_steps_per_second": 1.453, |
| 5941 | "eval_wer": 0.16578828489685288, |
| 5942 | "step": 8600 |
| 5943 | }, |
| 5944 | { |
| 5945 | "epoch": 12.37, |
| 5946 | "learning_rate": 0.00022908454810495626, |
| 5947 | "loss": 0.067, |
| 5948 | "step": 8610 |
| 5949 | }, |
| 5950 | { |
| 5951 | "epoch": 12.39, |
| 5952 | "learning_rate": 0.00022899708454810494, |
| 5953 | "loss": 0.0637, |
| 5954 | "step": 8620 |
| 5955 | }, |
| 5956 | { |
| 5957 | "epoch": 12.4, |
| 5958 | "learning_rate": 0.00022890962099125363, |
| 5959 | "loss": 0.0517, |
| 5960 | "step": 8630 |
| 5961 | }, |
| 5962 | { |
| 5963 | "epoch": 12.41, |
| 5964 | "learning_rate": 0.00022882215743440232, |
| 5965 | "loss": 0.0598, |
| 5966 | "step": 8640 |
| 5967 | }, |
| 5968 | { |
| 5969 | "epoch": 12.43, |
| 5970 | "learning_rate": 0.000228734693877551, |
| 5971 | "loss": 0.0598, |
| 5972 | "step": 8650 |
| 5973 | }, |
| 5974 | { |
| 5975 | "epoch": 12.44, |
| 5976 | "learning_rate": 0.0002286472303206997, |
| 5977 | "loss": 0.0656, |
| 5978 | "step": 8660 |
| 5979 | }, |
| 5980 | { |
| 5981 | "epoch": 12.46, |
| 5982 | "learning_rate": 0.00022855976676384836, |
| 5983 | "loss": 0.0699, |
| 5984 | "step": 8670 |
| 5985 | }, |
| 5986 | { |
| 5987 | "epoch": 12.47, |
| 5988 | "learning_rate": 0.00022847230320699704, |
| 5989 | "loss": 0.0524, |
| 5990 | "step": 8680 |
| 5991 | }, |
| 5992 | { |
| 5993 | "epoch": 12.49, |
| 5994 | "learning_rate": 0.00022838483965014576, |
| 5995 | "loss": 0.0557, |
| 5996 | "step": 8690 |
| 5997 | }, |
| 5998 | { |
| 5999 | "epoch": 12.5, |
| 6000 | "learning_rate": 0.00022829737609329445, |
| 6001 | "loss": 0.0546, |
| 6002 | "step": 8700 |
| 6003 | }, |
| 6004 | { |
| 6005 | "epoch": 12.5, |
| 6006 | "eval_loss": 0.16951903700828552, |
| 6007 | "eval_runtime": 39.9127, |
| 6008 | "eval_samples_per_second": 11.45, |
| 6009 | "eval_steps_per_second": 1.453, |
| 6010 | "eval_wer": 0.15750639963860863, |
| 6011 | "step": 8700 |
| 6012 | }, |
| 6013 | { |
| 6014 | "epoch": 12.51, |
| 6015 | "learning_rate": 0.00022820991253644313, |
| 6016 | "loss": 0.0841, |
| 6017 | "step": 8710 |
| 6018 | }, |
| 6019 | { |
| 6020 | "epoch": 12.53, |
| 6021 | "learning_rate": 0.00022812244897959182, |
| 6022 | "loss": 0.0452, |
| 6023 | "step": 8720 |
| 6024 | }, |
| 6025 | { |
| 6026 | "epoch": 12.54, |
| 6027 | "learning_rate": 0.0002280349854227405, |
| 6028 | "loss": 0.0674, |
| 6029 | "step": 8730 |
| 6030 | }, |
| 6031 | { |
| 6032 | "epoch": 12.56, |
| 6033 | "learning_rate": 0.0002279475218658892, |
| 6034 | "loss": 0.0652, |
| 6035 | "step": 8740 |
| 6036 | }, |
| 6037 | { |
| 6038 | "epoch": 12.57, |
| 6039 | "learning_rate": 0.00022786005830903789, |
| 6040 | "loss": 0.0592, |
| 6041 | "step": 8750 |
| 6042 | }, |
| 6043 | { |
| 6044 | "epoch": 12.59, |
| 6045 | "learning_rate": 0.00022777259475218655, |
| 6046 | "loss": 0.0628, |
| 6047 | "step": 8760 |
| 6048 | }, |
| 6049 | { |
| 6050 | "epoch": 12.6, |
| 6051 | "learning_rate": 0.00022768513119533523, |
| 6052 | "loss": 0.0595, |
| 6053 | "step": 8770 |
| 6054 | }, |
| 6055 | { |
| 6056 | "epoch": 12.61, |
| 6057 | "learning_rate": 0.00022759766763848395, |
| 6058 | "loss": 0.0718, |
| 6059 | "step": 8780 |
| 6060 | }, |
| 6061 | { |
| 6062 | "epoch": 12.63, |
| 6063 | "learning_rate": 0.00022751020408163264, |
| 6064 | "loss": 0.0636, |
| 6065 | "step": 8790 |
| 6066 | }, |
| 6067 | { |
| 6068 | "epoch": 12.64, |
| 6069 | "learning_rate": 0.00022742274052478133, |
| 6070 | "loss": 0.0692, |
| 6071 | "step": 8800 |
| 6072 | }, |
| 6073 | { |
| 6074 | "epoch": 12.64, |
| 6075 | "eval_loss": 0.16482137143611908, |
| 6076 | "eval_runtime": 39.9004, |
| 6077 | "eval_samples_per_second": 11.454, |
| 6078 | "eval_steps_per_second": 1.454, |
| 6079 | "eval_wer": 0.1644330673091402, |
| 6080 | "step": 8800 |
| 6081 | }, |
| 6082 | { |
| 6083 | "epoch": 12.66, |
| 6084 | "learning_rate": 0.00022733527696793, |
| 6085 | "loss": 0.0734, |
| 6086 | "step": 8810 |
| 6087 | }, |
| 6088 | { |
| 6089 | "epoch": 12.67, |
| 6090 | "learning_rate": 0.0002272478134110787, |
| 6091 | "loss": 0.0566, |
| 6092 | "step": 8820 |
| 6093 | }, |
| 6094 | { |
| 6095 | "epoch": 12.69, |
| 6096 | "learning_rate": 0.0002271603498542274, |
| 6097 | "loss": 0.0693, |
| 6098 | "step": 8830 |
| 6099 | }, |
| 6100 | { |
| 6101 | "epoch": 12.7, |
| 6102 | "learning_rate": 0.00022707288629737608, |
| 6103 | "loss": 0.057, |
| 6104 | "step": 8840 |
| 6105 | }, |
| 6106 | { |
| 6107 | "epoch": 12.72, |
| 6108 | "learning_rate": 0.00022698542274052474, |
| 6109 | "loss": 0.0512, |
| 6110 | "step": 8850 |
| 6111 | }, |
| 6112 | { |
| 6113 | "epoch": 12.73, |
| 6114 | "learning_rate": 0.00022689795918367343, |
| 6115 | "loss": 0.0698, |
| 6116 | "step": 8860 |
| 6117 | }, |
| 6118 | { |
| 6119 | "epoch": 12.74, |
| 6120 | "learning_rate": 0.00022681049562682214, |
| 6121 | "loss": 0.0621, |
| 6122 | "step": 8870 |
| 6123 | }, |
| 6124 | { |
| 6125 | "epoch": 12.76, |
| 6126 | "learning_rate": 0.00022672303206997083, |
| 6127 | "loss": 0.0553, |
| 6128 | "step": 8880 |
| 6129 | }, |
| 6130 | { |
| 6131 | "epoch": 12.77, |
| 6132 | "learning_rate": 0.00022663556851311952, |
| 6133 | "loss": 0.058, |
| 6134 | "step": 8890 |
| 6135 | }, |
| 6136 | { |
| 6137 | "epoch": 12.79, |
| 6138 | "learning_rate": 0.0002265481049562682, |
| 6139 | "loss": 0.0497, |
| 6140 | "step": 8900 |
| 6141 | }, |
| 6142 | { |
| 6143 | "epoch": 12.79, |
| 6144 | "eval_loss": 0.15961284935474396, |
| 6145 | "eval_runtime": 39.8903, |
| 6146 | "eval_samples_per_second": 11.456, |
| 6147 | "eval_steps_per_second": 1.454, |
| 6148 | "eval_wer": 0.16187321186568288, |
| 6149 | "step": 8900 |
| 6150 | }, |
| 6151 | { |
| 6152 | "epoch": 12.8, |
| 6153 | "learning_rate": 0.0002264606413994169, |
| 6154 | "loss": 0.0633, |
| 6155 | "step": 8910 |
| 6156 | }, |
| 6157 | { |
| 6158 | "epoch": 12.82, |
| 6159 | "learning_rate": 0.00022637317784256558, |
| 6160 | "loss": 0.0585, |
| 6161 | "step": 8920 |
| 6162 | }, |
| 6163 | { |
| 6164 | "epoch": 12.83, |
| 6165 | "learning_rate": 0.00022628571428571427, |
| 6166 | "loss": 0.0719, |
| 6167 | "step": 8930 |
| 6168 | }, |
| 6169 | { |
| 6170 | "epoch": 12.84, |
| 6171 | "learning_rate": 0.00022619825072886293, |
| 6172 | "loss": 0.056, |
| 6173 | "step": 8940 |
| 6174 | }, |
| 6175 | { |
| 6176 | "epoch": 12.86, |
| 6177 | "learning_rate": 0.00022611078717201164, |
| 6178 | "loss": 0.0473, |
| 6179 | "step": 8950 |
| 6180 | }, |
| 6181 | { |
| 6182 | "epoch": 12.87, |
| 6183 | "learning_rate": 0.00022602332361516033, |
| 6184 | "loss": 0.066, |
| 6185 | "step": 8960 |
| 6186 | }, |
| 6187 | { |
| 6188 | "epoch": 12.89, |
| 6189 | "learning_rate": 0.00022593586005830902, |
| 6190 | "loss": 0.058, |
| 6191 | "step": 8970 |
| 6192 | }, |
| 6193 | { |
| 6194 | "epoch": 12.9, |
| 6195 | "learning_rate": 0.0002258483965014577, |
| 6196 | "loss": 0.059, |
| 6197 | "step": 8980 |
| 6198 | }, |
| 6199 | { |
| 6200 | "epoch": 12.92, |
| 6201 | "learning_rate": 0.0002257609329446064, |
| 6202 | "loss": 0.0628, |
| 6203 | "step": 8990 |
| 6204 | }, |
| 6205 | { |
| 6206 | "epoch": 12.93, |
| 6207 | "learning_rate": 0.00022567346938775508, |
| 6208 | "loss": 0.0524, |
| 6209 | "step": 9000 |
| 6210 | }, |
| 6211 | { |
| 6212 | "epoch": 12.93, |
| 6213 | "eval_loss": 0.1611989289522171, |
| 6214 | "eval_runtime": 39.9555, |
| 6215 | "eval_samples_per_second": 11.438, |
| 6216 | "eval_steps_per_second": 1.452, |
| 6217 | "eval_wer": 0.15946393615419366, |
| 6218 | "step": 9000 |
| 6219 | }, |
| 6220 | { |
| 6221 | "epoch": 12.95, |
| 6222 | "learning_rate": 0.00022558600583090377, |
| 6223 | "loss": 0.0705, |
| 6224 | "step": 9010 |
| 6225 | }, |
| 6226 | { |
| 6227 | "epoch": 12.96, |
| 6228 | "learning_rate": 0.00022549854227405249, |
| 6229 | "loss": 0.0483, |
| 6230 | "step": 9020 |
| 6231 | }, |
| 6232 | { |
| 6233 | "epoch": 12.97, |
| 6234 | "learning_rate": 0.00022541107871720112, |
| 6235 | "loss": 0.0626, |
| 6236 | "step": 9030 |
| 6237 | }, |
| 6238 | { |
| 6239 | "epoch": 12.99, |
| 6240 | "learning_rate": 0.00022532361516034984, |
| 6241 | "loss": 0.0555, |
| 6242 | "step": 9040 |
| 6243 | }, |
| 6244 | { |
| 6245 | "epoch": 13.0, |
| 6246 | "learning_rate": 0.00022524489795918367, |
| 6247 | "loss": 0.057, |
| 6248 | "step": 9050 |
| 6249 | }, |
| 6250 | { |
| 6251 | "epoch": 13.02, |
| 6252 | "learning_rate": 0.00022515743440233236, |
| 6253 | "loss": 0.075, |
| 6254 | "step": 9060 |
| 6255 | }, |
| 6256 | { |
| 6257 | "epoch": 13.03, |
| 6258 | "learning_rate": 0.00022506997084548104, |
| 6259 | "loss": 0.0543, |
| 6260 | "step": 9070 |
| 6261 | }, |
| 6262 | { |
| 6263 | "epoch": 13.05, |
| 6264 | "learning_rate": 0.00022498250728862973, |
| 6265 | "loss": 0.0728, |
| 6266 | "step": 9080 |
| 6267 | }, |
| 6268 | { |
| 6269 | "epoch": 13.06, |
| 6270 | "learning_rate": 0.0002248950437317784, |
| 6271 | "loss": 0.0522, |
| 6272 | "step": 9090 |
| 6273 | }, |
| 6274 | { |
| 6275 | "epoch": 13.07, |
| 6276 | "learning_rate": 0.00022480758017492708, |
| 6277 | "loss": 0.0501, |
| 6278 | "step": 9100 |
| 6279 | }, |
| 6280 | { |
| 6281 | "epoch": 13.07, |
| 6282 | "eval_loss": 0.1783318668603897, |
| 6283 | "eval_runtime": 39.9433, |
| 6284 | "eval_samples_per_second": 11.441, |
| 6285 | "eval_steps_per_second": 1.452, |
| 6286 | "eval_wer": 0.16413190784520404, |
| 6287 | "step": 9100 |
| 6288 | }, |
| 6289 | { |
| 6290 | "epoch": 13.09, |
| 6291 | "learning_rate": 0.00022472011661807577, |
| 6292 | "loss": 0.0597, |
| 6293 | "step": 9110 |
| 6294 | }, |
| 6295 | { |
| 6296 | "epoch": 13.1, |
| 6297 | "learning_rate": 0.00022463265306122446, |
| 6298 | "loss": 0.0493, |
| 6299 | "step": 9120 |
| 6300 | }, |
| 6301 | { |
| 6302 | "epoch": 13.12, |
| 6303 | "learning_rate": 0.00022454518950437317, |
| 6304 | "loss": 0.0622, |
| 6305 | "step": 9130 |
| 6306 | }, |
| 6307 | { |
| 6308 | "epoch": 13.13, |
| 6309 | "learning_rate": 0.00022445772594752186, |
| 6310 | "loss": 0.0528, |
| 6311 | "step": 9140 |
| 6312 | }, |
| 6313 | { |
| 6314 | "epoch": 13.15, |
| 6315 | "learning_rate": 0.00022437026239067055, |
| 6316 | "loss": 0.0592, |
| 6317 | "step": 9150 |
| 6318 | }, |
| 6319 | { |
| 6320 | "epoch": 13.16, |
| 6321 | "learning_rate": 0.00022428279883381923, |
| 6322 | "loss": 0.066, |
| 6323 | "step": 9160 |
| 6324 | }, |
| 6325 | { |
| 6326 | "epoch": 13.18, |
| 6327 | "learning_rate": 0.00022419533527696792, |
| 6328 | "loss": 0.0549, |
| 6329 | "step": 9170 |
| 6330 | }, |
| 6331 | { |
| 6332 | "epoch": 13.19, |
| 6333 | "learning_rate": 0.00022410787172011658, |
| 6334 | "loss": 0.0652, |
| 6335 | "step": 9180 |
| 6336 | }, |
| 6337 | { |
| 6338 | "epoch": 13.2, |
| 6339 | "learning_rate": 0.00022402040816326527, |
| 6340 | "loss": 0.0613, |
| 6341 | "step": 9190 |
| 6342 | }, |
| 6343 | { |
| 6344 | "epoch": 13.22, |
| 6345 | "learning_rate": 0.00022393294460641396, |
| 6346 | "loss": 0.0539, |
| 6347 | "step": 9200 |
| 6348 | }, |
| 6349 | { |
| 6350 | "epoch": 13.22, |
| 6351 | "eval_loss": 0.16895711421966553, |
| 6352 | "eval_runtime": 39.9239, |
| 6353 | "eval_samples_per_second": 11.447, |
| 6354 | "eval_steps_per_second": 1.453, |
| 6355 | "eval_wer": 0.16217437132961904, |
| 6356 | "step": 9200 |
| 6357 | }, |
| 6358 | { |
| 6359 | "epoch": 13.23, |
| 6360 | "learning_rate": 0.00022384548104956265, |
| 6361 | "loss": 0.057, |
| 6362 | "step": 9210 |
| 6363 | }, |
| 6364 | { |
| 6365 | "epoch": 13.25, |
| 6366 | "learning_rate": 0.00022375801749271136, |
| 6367 | "loss": 0.0491, |
| 6368 | "step": 9220 |
| 6369 | }, |
| 6370 | { |
| 6371 | "epoch": 13.26, |
| 6372 | "learning_rate": 0.00022367055393586005, |
| 6373 | "loss": 0.0761, |
| 6374 | "step": 9230 |
| 6375 | }, |
| 6376 | { |
| 6377 | "epoch": 13.28, |
| 6378 | "learning_rate": 0.00022358309037900874, |
| 6379 | "loss": 0.063, |
| 6380 | "step": 9240 |
| 6381 | }, |
| 6382 | { |
| 6383 | "epoch": 13.29, |
| 6384 | "learning_rate": 0.00022349562682215743, |
| 6385 | "loss": 0.0537, |
| 6386 | "step": 9250 |
| 6387 | }, |
| 6388 | { |
| 6389 | "epoch": 13.3, |
| 6390 | "learning_rate": 0.00022340816326530611, |
| 6391 | "loss": 0.0535, |
| 6392 | "step": 9260 |
| 6393 | }, |
| 6394 | { |
| 6395 | "epoch": 13.32, |
| 6396 | "learning_rate": 0.00022332069970845477, |
| 6397 | "loss": 0.0475, |
| 6398 | "step": 9270 |
| 6399 | }, |
| 6400 | { |
| 6401 | "epoch": 13.33, |
| 6402 | "learning_rate": 0.00022323323615160346, |
| 6403 | "loss": 0.0702, |
| 6404 | "step": 9280 |
| 6405 | }, |
| 6406 | { |
| 6407 | "epoch": 13.35, |
| 6408 | "learning_rate": 0.00022314577259475215, |
| 6409 | "loss": 0.0617, |
| 6410 | "step": 9290 |
| 6411 | }, |
| 6412 | { |
| 6413 | "epoch": 13.36, |
| 6414 | "learning_rate": 0.00022305830903790084, |
| 6415 | "loss": 0.0608, |
| 6416 | "step": 9300 |
| 6417 | }, |
| 6418 | { |
| 6419 | "epoch": 13.36, |
| 6420 | "eval_loss": 0.1596861034631729, |
| 6421 | "eval_runtime": 40.0878, |
| 6422 | "eval_samples_per_second": 11.4, |
| 6423 | "eval_steps_per_second": 1.447, |
| 6424 | "eval_wer": 0.1597650956181298, |
| 6425 | "step": 9300 |
| 6426 | }, |
| 6427 | { |
| 6428 | "epoch": 13.38, |
| 6429 | "learning_rate": 0.00022297084548104955, |
| 6430 | "loss": 0.0602, |
| 6431 | "step": 9310 |
| 6432 | }, |
| 6433 | { |
| 6434 | "epoch": 13.39, |
| 6435 | "learning_rate": 0.00022288338192419824, |
| 6436 | "loss": 0.0474, |
| 6437 | "step": 9320 |
| 6438 | }, |
| 6439 | { |
| 6440 | "epoch": 13.41, |
| 6441 | "learning_rate": 0.00022279591836734693, |
| 6442 | "loss": 0.053, |
| 6443 | "step": 9330 |
| 6444 | }, |
| 6445 | { |
| 6446 | "epoch": 13.42, |
| 6447 | "learning_rate": 0.00022270845481049562, |
| 6448 | "loss": 0.0465, |
| 6449 | "step": 9340 |
| 6450 | }, |
| 6451 | { |
| 6452 | "epoch": 13.43, |
| 6453 | "learning_rate": 0.0002226209912536443, |
| 6454 | "loss": 0.0632, |
| 6455 | "step": 9350 |
| 6456 | }, |
| 6457 | { |
| 6458 | "epoch": 13.45, |
| 6459 | "learning_rate": 0.00022253352769679297, |
| 6460 | "loss": 0.0514, |
| 6461 | "step": 9360 |
| 6462 | }, |
| 6463 | { |
| 6464 | "epoch": 13.46, |
| 6465 | "learning_rate": 0.00022244606413994165, |
| 6466 | "loss": 0.0538, |
| 6467 | "step": 9370 |
| 6468 | }, |
| 6469 | { |
| 6470 | "epoch": 13.48, |
| 6471 | "learning_rate": 0.00022235860058309034, |
| 6472 | "loss": 0.0593, |
| 6473 | "step": 9380 |
| 6474 | }, |
| 6475 | { |
| 6476 | "epoch": 13.49, |
| 6477 | "learning_rate": 0.00022227113702623906, |
| 6478 | "loss": 0.0609, |
| 6479 | "step": 9390 |
| 6480 | }, |
| 6481 | { |
| 6482 | "epoch": 13.51, |
| 6483 | "learning_rate": 0.00022218367346938774, |
| 6484 | "loss": 0.0627, |
| 6485 | "step": 9400 |
| 6486 | }, |
| 6487 | { |
| 6488 | "epoch": 13.51, |
| 6489 | "eval_loss": 0.16226713359355927, |
| 6490 | "eval_runtime": 40.1172, |
| 6491 | "eval_samples_per_second": 11.392, |
| 6492 | "eval_steps_per_second": 1.446, |
| 6493 | "eval_wer": 0.16262611052552325, |
| 6494 | "step": 9400 |
| 6495 | }, |
| 6496 | { |
| 6497 | "epoch": 13.52, |
| 6498 | "learning_rate": 0.00022209620991253643, |
| 6499 | "loss": 0.0696, |
| 6500 | "step": 9410 |
| 6501 | }, |
| 6502 | { |
| 6503 | "epoch": 13.53, |
| 6504 | "learning_rate": 0.00022200874635568512, |
| 6505 | "loss": 0.048, |
| 6506 | "step": 9420 |
| 6507 | }, |
| 6508 | { |
| 6509 | "epoch": 13.55, |
| 6510 | "learning_rate": 0.0002219212827988338, |
| 6511 | "loss": 0.0624, |
| 6512 | "step": 9430 |
| 6513 | }, |
| 6514 | { |
| 6515 | "epoch": 13.56, |
| 6516 | "learning_rate": 0.0002218338192419825, |
| 6517 | "loss": 0.0595, |
| 6518 | "step": 9440 |
| 6519 | }, |
| 6520 | { |
| 6521 | "epoch": 13.58, |
| 6522 | "learning_rate": 0.00022174635568513116, |
| 6523 | "loss": 0.0583, |
| 6524 | "step": 9450 |
| 6525 | }, |
| 6526 | { |
| 6527 | "epoch": 13.59, |
| 6528 | "learning_rate": 0.00022165889212827984, |
| 6529 | "loss": 0.0607, |
| 6530 | "step": 9460 |
| 6531 | }, |
| 6532 | { |
| 6533 | "epoch": 13.61, |
| 6534 | "learning_rate": 0.00022157142857142853, |
| 6535 | "loss": 0.0548, |
| 6536 | "step": 9470 |
| 6537 | }, |
| 6538 | { |
| 6539 | "epoch": 13.62, |
| 6540 | "learning_rate": 0.00022148396501457725, |
| 6541 | "loss": 0.0647, |
| 6542 | "step": 9480 |
| 6543 | }, |
| 6544 | { |
| 6545 | "epoch": 13.64, |
| 6546 | "learning_rate": 0.00022139650145772594, |
| 6547 | "loss": 0.0683, |
| 6548 | "step": 9490 |
| 6549 | }, |
| 6550 | { |
| 6551 | "epoch": 13.65, |
| 6552 | "learning_rate": 0.00022130903790087462, |
| 6553 | "loss": 0.0456, |
| 6554 | "step": 9500 |
| 6555 | }, |
| 6556 | { |
| 6557 | "epoch": 13.65, |
| 6558 | "eval_loss": 0.16573207080364227, |
| 6559 | "eval_runtime": 40.0704, |
| 6560 | "eval_samples_per_second": 11.405, |
| 6561 | "eval_steps_per_second": 1.447, |
| 6562 | "eval_wer": 0.16217437132961904, |
| 6563 | "step": 9500 |
| 6564 | }, |
| 6565 | { |
| 6566 | "epoch": 13.66, |
| 6567 | "learning_rate": 0.0002212215743440233, |
| 6568 | "loss": 0.0506, |
| 6569 | "step": 9510 |
| 6570 | }, |
| 6571 | { |
| 6572 | "epoch": 13.68, |
| 6573 | "learning_rate": 0.000221134110787172, |
| 6574 | "loss": 0.0557, |
| 6575 | "step": 9520 |
| 6576 | }, |
| 6577 | { |
| 6578 | "epoch": 13.69, |
| 6579 | "learning_rate": 0.0002210466472303207, |
| 6580 | "loss": 0.0558, |
| 6581 | "step": 9530 |
| 6582 | }, |
| 6583 | { |
| 6584 | "epoch": 13.71, |
| 6585 | "learning_rate": 0.00022095918367346935, |
| 6586 | "loss": 0.0598, |
| 6587 | "step": 9540 |
| 6588 | }, |
| 6589 | { |
| 6590 | "epoch": 13.72, |
| 6591 | "learning_rate": 0.00022087172011661804, |
| 6592 | "loss": 0.0459, |
| 6593 | "step": 9550 |
| 6594 | }, |
| 6595 | { |
| 6596 | "epoch": 13.74, |
| 6597 | "learning_rate": 0.00022078425655976672, |
| 6598 | "loss": 0.0708, |
| 6599 | "step": 9560 |
| 6600 | }, |
| 6601 | { |
| 6602 | "epoch": 13.75, |
| 6603 | "learning_rate": 0.00022069679300291544, |
| 6604 | "loss": 0.0507, |
| 6605 | "step": 9570 |
| 6606 | }, |
| 6607 | { |
| 6608 | "epoch": 13.76, |
| 6609 | "learning_rate": 0.00022060932944606413, |
| 6610 | "loss": 0.0741, |
| 6611 | "step": 9580 |
| 6612 | }, |
| 6613 | { |
| 6614 | "epoch": 13.78, |
| 6615 | "learning_rate": 0.00022052186588921281, |
| 6616 | "loss": 0.0534, |
| 6617 | "step": 9590 |
| 6618 | }, |
| 6619 | { |
| 6620 | "epoch": 13.79, |
| 6621 | "learning_rate": 0.0002204344023323615, |
| 6622 | "loss": 0.0563, |
| 6623 | "step": 9600 |
| 6624 | }, |
| 6625 | { |
| 6626 | "epoch": 13.79, |
| 6627 | "eval_loss": 0.1635971963405609, |
| 6628 | "eval_runtime": 40.1592, |
| 6629 | "eval_samples_per_second": 11.38, |
| 6630 | "eval_steps_per_second": 1.444, |
| 6631 | "eval_wer": 0.16398132811323596, |
| 6632 | "step": 9600 |
| 6633 | }, |
| 6634 | { |
| 6635 | "epoch": 13.81, |
| 6636 | "learning_rate": 0.0002203469387755102, |
| 6637 | "loss": 0.0676, |
| 6638 | "step": 9610 |
| 6639 | }, |
| 6640 | { |
| 6641 | "epoch": 13.82, |
| 6642 | "learning_rate": 0.00022025947521865888, |
| 6643 | "loss": 0.044, |
| 6644 | "step": 9620 |
| 6645 | }, |
| 6646 | { |
| 6647 | "epoch": 13.84, |
| 6648 | "learning_rate": 0.00022017201166180754, |
| 6649 | "loss": 0.0634, |
| 6650 | "step": 9630 |
| 6651 | }, |
| 6652 | { |
| 6653 | "epoch": 13.85, |
| 6654 | "learning_rate": 0.00022008454810495623, |
| 6655 | "loss": 0.0501, |
| 6656 | "step": 9640 |
| 6657 | }, |
| 6658 | { |
| 6659 | "epoch": 13.86, |
| 6660 | "learning_rate": 0.00021999708454810494, |
| 6661 | "loss": 0.0556, |
| 6662 | "step": 9650 |
| 6663 | }, |
| 6664 | { |
| 6665 | "epoch": 13.88, |
| 6666 | "learning_rate": 0.00021990962099125363, |
| 6667 | "loss": 0.0659, |
| 6668 | "step": 9660 |
| 6669 | }, |
| 6670 | { |
| 6671 | "epoch": 13.89, |
| 6672 | "learning_rate": 0.00021982215743440232, |
| 6673 | "loss": 0.0587, |
| 6674 | "step": 9670 |
| 6675 | }, |
| 6676 | { |
| 6677 | "epoch": 13.91, |
| 6678 | "learning_rate": 0.000219734693877551, |
| 6679 | "loss": 0.0671, |
| 6680 | "step": 9680 |
| 6681 | }, |
| 6682 | { |
| 6683 | "epoch": 13.92, |
| 6684 | "learning_rate": 0.0002196472303206997, |
| 6685 | "loss": 0.056, |
| 6686 | "step": 9690 |
| 6687 | }, |
| 6688 | { |
| 6689 | "epoch": 13.94, |
| 6690 | "learning_rate": 0.00021955976676384838, |
| 6691 | "loss": 0.0533, |
| 6692 | "step": 9700 |
| 6693 | }, |
| 6694 | { |
| 6695 | "epoch": 13.94, |
| 6696 | "eval_loss": 0.15973329544067383, |
| 6697 | "eval_runtime": 39.8632, |
| 6698 | "eval_samples_per_second": 11.464, |
| 6699 | "eval_steps_per_second": 1.455, |
| 6700 | "eval_wer": 0.1630778497214275, |
| 6701 | "step": 9700 |
| 6702 | }, |
| 6703 | { |
| 6704 | "epoch": 13.95, |
| 6705 | "learning_rate": 0.00021947230320699707, |
| 6706 | "loss": 0.0615, |
| 6707 | "step": 9710 |
| 6708 | }, |
| 6709 | { |
| 6710 | "epoch": 13.97, |
| 6711 | "learning_rate": 0.00021938483965014573, |
| 6712 | "loss": 0.0534, |
| 6713 | "step": 9720 |
| 6714 | }, |
| 6715 | { |
| 6716 | "epoch": 13.98, |
| 6717 | "learning_rate": 0.00021929737609329442, |
| 6718 | "loss": 0.0592, |
| 6719 | "step": 9730 |
| 6720 | }, |
| 6721 | { |
| 6722 | "epoch": 13.99, |
| 6723 | "learning_rate": 0.00021920991253644313, |
| 6724 | "loss": 0.0595, |
| 6725 | "step": 9740 |
| 6726 | }, |
| 6727 | { |
| 6728 | "epoch": 14.01, |
| 6729 | "learning_rate": 0.00021912244897959182, |
| 6730 | "loss": 0.0589, |
| 6731 | "step": 9750 |
| 6732 | }, |
| 6733 | { |
| 6734 | "epoch": 14.02, |
| 6735 | "learning_rate": 0.0002190349854227405, |
| 6736 | "loss": 0.0605, |
| 6737 | "step": 9760 |
| 6738 | }, |
| 6739 | { |
| 6740 | "epoch": 14.04, |
| 6741 | "learning_rate": 0.0002189475218658892, |
| 6742 | "loss": 0.0444, |
| 6743 | "step": 9770 |
| 6744 | }, |
| 6745 | { |
| 6746 | "epoch": 14.05, |
| 6747 | "learning_rate": 0.00021886005830903788, |
| 6748 | "loss": 0.0612, |
| 6749 | "step": 9780 |
| 6750 | }, |
| 6751 | { |
| 6752 | "epoch": 14.07, |
| 6753 | "learning_rate": 0.00021877259475218657, |
| 6754 | "loss": 0.045, |
| 6755 | "step": 9790 |
| 6756 | }, |
| 6757 | { |
| 6758 | "epoch": 14.08, |
| 6759 | "learning_rate": 0.00021868513119533526, |
| 6760 | "loss": 0.0733, |
| 6761 | "step": 9800 |
| 6762 | }, |
| 6763 | { |
| 6764 | "epoch": 14.08, |
| 6765 | "eval_loss": 0.16077786684036255, |
| 6766 | "eval_runtime": 39.8765, |
| 6767 | "eval_samples_per_second": 11.46, |
| 6768 | "eval_steps_per_second": 1.454, |
| 6769 | "eval_wer": 0.1715103147116398, |
| 6770 | "step": 9800 |
| 6771 | }, |
| 6772 | { |
| 6773 | "epoch": 14.09, |
| 6774 | "learning_rate": 0.00021859766763848392, |
| 6775 | "loss": 0.0694, |
| 6776 | "step": 9810 |
| 6777 | }, |
| 6778 | { |
| 6779 | "epoch": 14.11, |
| 6780 | "learning_rate": 0.00021851020408163264, |
| 6781 | "loss": 0.0599, |
| 6782 | "step": 9820 |
| 6783 | }, |
| 6784 | { |
| 6785 | "epoch": 14.12, |
| 6786 | "learning_rate": 0.00021842274052478132, |
| 6787 | "loss": 0.0685, |
| 6788 | "step": 9830 |
| 6789 | }, |
| 6790 | { |
| 6791 | "epoch": 14.14, |
| 6792 | "learning_rate": 0.00021833527696793, |
| 6793 | "loss": 0.0596, |
| 6794 | "step": 9840 |
| 6795 | }, |
| 6796 | { |
| 6797 | "epoch": 14.15, |
| 6798 | "learning_rate": 0.0002182478134110787, |
| 6799 | "loss": 0.063, |
| 6800 | "step": 9850 |
| 6801 | }, |
| 6802 | { |
| 6803 | "epoch": 14.17, |
| 6804 | "learning_rate": 0.0002181603498542274, |
| 6805 | "loss": 0.0602, |
| 6806 | "step": 9860 |
| 6807 | }, |
| 6808 | { |
| 6809 | "epoch": 14.18, |
| 6810 | "learning_rate": 0.00021807288629737608, |
| 6811 | "loss": 0.0547, |
| 6812 | "step": 9870 |
| 6813 | }, |
| 6814 | { |
| 6815 | "epoch": 14.2, |
| 6816 | "learning_rate": 0.00021798542274052476, |
| 6817 | "loss": 0.0622, |
| 6818 | "step": 9880 |
| 6819 | }, |
| 6820 | { |
| 6821 | "epoch": 14.21, |
| 6822 | "learning_rate": 0.00021789795918367348, |
| 6823 | "loss": 0.0522, |
| 6824 | "step": 9890 |
| 6825 | }, |
| 6826 | { |
| 6827 | "epoch": 14.22, |
| 6828 | "learning_rate": 0.0002178104956268221, |
| 6829 | "loss": 0.0635, |
| 6830 | "step": 9900 |
| 6831 | }, |
| 6832 | { |
| 6833 | "epoch": 14.22, |
| 6834 | "eval_loss": 0.16328591108322144, |
| 6835 | "eval_runtime": 40.0655, |
| 6836 | "eval_samples_per_second": 11.406, |
| 6837 | "eval_steps_per_second": 1.448, |
| 6838 | "eval_wer": 0.1615720524017467, |
| 6839 | "step": 9900 |
| 6840 | }, |
| 6841 | { |
| 6842 | "epoch": 14.24, |
| 6843 | "learning_rate": 0.00021772303206997083, |
| 6844 | "loss": 0.0453, |
| 6845 | "step": 9910 |
| 6846 | }, |
| 6847 | { |
| 6848 | "epoch": 14.25, |
| 6849 | "learning_rate": 0.00021763556851311951, |
| 6850 | "loss": 0.0531, |
| 6851 | "step": 9920 |
| 6852 | }, |
| 6853 | { |
| 6854 | "epoch": 14.27, |
| 6855 | "learning_rate": 0.0002175481049562682, |
| 6856 | "loss": 0.0613, |
| 6857 | "step": 9930 |
| 6858 | }, |
| 6859 | { |
| 6860 | "epoch": 14.28, |
| 6861 | "learning_rate": 0.0002174606413994169, |
| 6862 | "loss": 0.0579, |
| 6863 | "step": 9940 |
| 6864 | }, |
| 6865 | { |
| 6866 | "epoch": 14.3, |
| 6867 | "learning_rate": 0.00021737317784256558, |
| 6868 | "loss": 0.0544, |
| 6869 | "step": 9950 |
| 6870 | }, |
| 6871 | { |
| 6872 | "epoch": 14.31, |
| 6873 | "learning_rate": 0.00021728571428571427, |
| 6874 | "loss": 0.0568, |
| 6875 | "step": 9960 |
| 6876 | }, |
| 6877 | { |
| 6878 | "epoch": 14.32, |
| 6879 | "learning_rate": 0.00021719825072886295, |
| 6880 | "loss": 0.0503, |
| 6881 | "step": 9970 |
| 6882 | }, |
| 6883 | { |
| 6884 | "epoch": 14.34, |
| 6885 | "learning_rate": 0.00021711078717201167, |
| 6886 | "loss": 0.0666, |
| 6887 | "step": 9980 |
| 6888 | }, |
| 6889 | { |
| 6890 | "epoch": 14.35, |
| 6891 | "learning_rate": 0.0002170233236151603, |
| 6892 | "loss": 0.0674, |
| 6893 | "step": 9990 |
| 6894 | }, |
| 6895 | { |
| 6896 | "epoch": 14.37, |
| 6897 | "learning_rate": 0.00021693586005830902, |
| 6898 | "loss": 0.0515, |
| 6899 | "step": 10000 |
| 6900 | }, |
| 6901 | { |
| 6902 | "epoch": 14.37, |
| 6903 | "eval_loss": 0.16031676530838013, |
| 6904 | "eval_runtime": 40.2452, |
| 6905 | "eval_samples_per_second": 11.355, |
| 6906 | "eval_steps_per_second": 1.441, |
| 6907 | "eval_wer": 0.16428248757717212, |
| 6908 | "step": 10000 |
| 6909 | }, |
| 6910 | { |
| 6911 | "epoch": 14.38, |
| 6912 | "learning_rate": 0.0002168483965014577, |
| 6913 | "loss": 0.0453, |
| 6914 | "step": 10010 |
| 6915 | }, |
| 6916 | { |
| 6917 | "epoch": 14.4, |
| 6918 | "learning_rate": 0.0002167609329446064, |
| 6919 | "loss": 0.0383, |
| 6920 | "step": 10020 |
| 6921 | }, |
| 6922 | { |
| 6923 | "epoch": 14.41, |
| 6924 | "learning_rate": 0.00021667346938775508, |
| 6925 | "loss": 0.0582, |
| 6926 | "step": 10030 |
| 6927 | }, |
| 6928 | { |
| 6929 | "epoch": 14.43, |
| 6930 | "learning_rate": 0.00021658600583090377, |
| 6931 | "loss": 0.0521, |
| 6932 | "step": 10040 |
| 6933 | }, |
| 6934 | { |
| 6935 | "epoch": 14.44, |
| 6936 | "learning_rate": 0.00021649854227405246, |
| 6937 | "loss": 0.0611, |
| 6938 | "step": 10050 |
| 6939 | }, |
| 6940 | { |
| 6941 | "epoch": 14.45, |
| 6942 | "learning_rate": 0.00021641107871720115, |
| 6943 | "loss": 0.0555, |
| 6944 | "step": 10060 |
| 6945 | }, |
| 6946 | { |
| 6947 | "epoch": 14.47, |
| 6948 | "learning_rate": 0.00021632361516034986, |
| 6949 | "loss": 0.0571, |
| 6950 | "step": 10070 |
| 6951 | }, |
| 6952 | { |
| 6953 | "epoch": 14.48, |
| 6954 | "learning_rate": 0.00021623615160349852, |
| 6955 | "loss": 0.0673, |
| 6956 | "step": 10080 |
| 6957 | }, |
| 6958 | { |
| 6959 | "epoch": 14.5, |
| 6960 | "learning_rate": 0.0002161486880466472, |
| 6961 | "loss": 0.0461, |
| 6962 | "step": 10090 |
| 6963 | }, |
| 6964 | { |
| 6965 | "epoch": 14.51, |
| 6966 | "learning_rate": 0.0002160612244897959, |
| 6967 | "loss": 0.0653, |
| 6968 | "step": 10100 |
| 6969 | }, |
| 6970 | { |
| 6971 | "epoch": 14.51, |
| 6972 | "eval_loss": 0.16045616567134857, |
| 6973 | "eval_runtime": 39.9395, |
| 6974 | "eval_samples_per_second": 11.442, |
| 6975 | "eval_steps_per_second": 1.452, |
| 6976 | "eval_wer": 0.15840987803041712, |
| 6977 | "step": 10100 |
| 6978 | }, |
| 6979 | { |
| 6980 | "epoch": 14.53, |
| 6981 | "learning_rate": 0.00021597376093294458, |
| 6982 | "loss": 0.0555, |
| 6983 | "step": 10110 |
| 6984 | }, |
| 6985 | { |
| 6986 | "epoch": 14.54, |
| 6987 | "learning_rate": 0.00021588629737609327, |
| 6988 | "loss": 0.0591, |
| 6989 | "step": 10120 |
| 6990 | }, |
| 6991 | { |
| 6992 | "epoch": 14.55, |
| 6993 | "learning_rate": 0.00021579883381924196, |
| 6994 | "loss": 0.0639, |
| 6995 | "step": 10130 |
| 6996 | }, |
| 6997 | { |
| 6998 | "epoch": 14.57, |
| 6999 | "learning_rate": 0.00021571137026239065, |
| 7000 | "loss": 0.0507, |
| 7001 | "step": 10140 |
| 7002 | }, |
| 7003 | { |
| 7004 | "epoch": 14.58, |
| 7005 | "learning_rate": 0.00021562390670553936, |
| 7006 | "loss": 0.0744, |
| 7007 | "step": 10150 |
| 7008 | }, |
| 7009 | { |
| 7010 | "epoch": 14.6, |
| 7011 | "learning_rate": 0.00021553644314868805, |
| 7012 | "loss": 0.0596, |
| 7013 | "step": 10160 |
| 7014 | }, |
| 7015 | { |
| 7016 | "epoch": 14.61, |
| 7017 | "learning_rate": 0.0002154489795918367, |
| 7018 | "loss": 0.0447, |
| 7019 | "step": 10170 |
| 7020 | }, |
| 7021 | { |
| 7022 | "epoch": 14.63, |
| 7023 | "learning_rate": 0.0002153615160349854, |
| 7024 | "loss": 0.0632, |
| 7025 | "step": 10180 |
| 7026 | }, |
| 7027 | { |
| 7028 | "epoch": 14.64, |
| 7029 | "learning_rate": 0.0002152740524781341, |
| 7030 | "loss": 0.0488, |
| 7031 | "step": 10190 |
| 7032 | }, |
| 7033 | { |
| 7034 | "epoch": 14.66, |
| 7035 | "learning_rate": 0.00021518658892128278, |
| 7036 | "loss": 0.0565, |
| 7037 | "step": 10200 |
| 7038 | }, |
| 7039 | { |
| 7040 | "epoch": 14.66, |
| 7041 | "eval_loss": 0.1643233746290207, |
| 7042 | "eval_runtime": 40.486, |
| 7043 | "eval_samples_per_second": 11.288, |
| 7044 | "eval_steps_per_second": 1.433, |
| 7045 | "eval_wer": 0.15810871856648095, |
| 7046 | "step": 10200 |
| 7047 | }, |
| 7048 | { |
| 7049 | "epoch": 14.67, |
| 7050 | "learning_rate": 0.00021509912536443146, |
| 7051 | "loss": 0.0521, |
| 7052 | "step": 10210 |
| 7053 | }, |
| 7054 | { |
| 7055 | "epoch": 14.68, |
| 7056 | "learning_rate": 0.00021501166180758015, |
| 7057 | "loss": 0.0523, |
| 7058 | "step": 10220 |
| 7059 | }, |
| 7060 | { |
| 7061 | "epoch": 14.7, |
| 7062 | "learning_rate": 0.00021492419825072884, |
| 7063 | "loss": 0.0711, |
| 7064 | "step": 10230 |
| 7065 | }, |
| 7066 | { |
| 7067 | "epoch": 14.71, |
| 7068 | "learning_rate": 0.00021483673469387755, |
| 7069 | "loss": 0.051, |
| 7070 | "step": 10240 |
| 7071 | }, |
| 7072 | { |
| 7073 | "epoch": 14.73, |
| 7074 | "learning_rate": 0.00021474927113702624, |
| 7075 | "loss": 0.063, |
| 7076 | "step": 10250 |
| 7077 | }, |
| 7078 | { |
| 7079 | "epoch": 14.74, |
| 7080 | "learning_rate": 0.0002146618075801749, |
| 7081 | "loss": 0.0521, |
| 7082 | "step": 10260 |
| 7083 | }, |
| 7084 | { |
| 7085 | "epoch": 14.76, |
| 7086 | "learning_rate": 0.0002145743440233236, |
| 7087 | "loss": 0.0573, |
| 7088 | "step": 10270 |
| 7089 | }, |
| 7090 | { |
| 7091 | "epoch": 14.77, |
| 7092 | "learning_rate": 0.00021448688046647228, |
| 7093 | "loss": 0.0668, |
| 7094 | "step": 10280 |
| 7095 | }, |
| 7096 | { |
| 7097 | "epoch": 14.78, |
| 7098 | "learning_rate": 0.00021439941690962097, |
| 7099 | "loss": 0.0523, |
| 7100 | "step": 10290 |
| 7101 | }, |
| 7102 | { |
| 7103 | "epoch": 14.8, |
| 7104 | "learning_rate": 0.00021431195335276965, |
| 7105 | "loss": 0.0576, |
| 7106 | "step": 10300 |
| 7107 | }, |
| 7108 | { |
| 7109 | "epoch": 14.8, |
| 7110 | "eval_loss": 0.15989667177200317, |
| 7111 | "eval_runtime": 39.8824, |
| 7112 | "eval_samples_per_second": 11.459, |
| 7113 | "eval_steps_per_second": 1.454, |
| 7114 | "eval_wer": 0.16081915374190633, |
| 7115 | "step": 10300 |
| 7116 | }, |
| 7117 | { |
| 7118 | "epoch": 14.81, |
| 7119 | "learning_rate": 0.00021422448979591834, |
| 7120 | "loss": 0.0478, |
| 7121 | "step": 10310 |
| 7122 | }, |
| 7123 | { |
| 7124 | "epoch": 14.83, |
| 7125 | "learning_rate": 0.00021413702623906706, |
| 7126 | "loss": 0.0601, |
| 7127 | "step": 10320 |
| 7128 | }, |
| 7129 | { |
| 7130 | "epoch": 14.84, |
| 7131 | "learning_rate": 0.00021404956268221575, |
| 7132 | "loss": 0.0628, |
| 7133 | "step": 10330 |
| 7134 | }, |
| 7135 | { |
| 7136 | "epoch": 14.86, |
| 7137 | "learning_rate": 0.00021396209912536443, |
| 7138 | "loss": 0.0493, |
| 7139 | "step": 10340 |
| 7140 | }, |
| 7141 | { |
| 7142 | "epoch": 14.87, |
| 7143 | "learning_rate": 0.0002138746355685131, |
| 7144 | "loss": 0.0654, |
| 7145 | "step": 10350 |
| 7146 | }, |
| 7147 | { |
| 7148 | "epoch": 14.89, |
| 7149 | "learning_rate": 0.00021378717201166178, |
| 7150 | "loss": 0.05, |
| 7151 | "step": 10360 |
| 7152 | }, |
| 7153 | { |
| 7154 | "epoch": 14.9, |
| 7155 | "learning_rate": 0.00021369970845481047, |
| 7156 | "loss": 0.0567, |
| 7157 | "step": 10370 |
| 7158 | }, |
| 7159 | { |
| 7160 | "epoch": 14.91, |
| 7161 | "learning_rate": 0.00021361224489795916, |
| 7162 | "loss": 0.0642, |
| 7163 | "step": 10380 |
| 7164 | }, |
| 7165 | { |
| 7166 | "epoch": 14.93, |
| 7167 | "learning_rate": 0.00021352478134110785, |
| 7168 | "loss": 0.0493, |
| 7169 | "step": 10390 |
| 7170 | }, |
| 7171 | { |
| 7172 | "epoch": 14.94, |
| 7173 | "learning_rate": 0.00021343731778425653, |
| 7174 | "loss": 0.0593, |
| 7175 | "step": 10400 |
| 7176 | }, |
| 7177 | { |
| 7178 | "epoch": 14.94, |
| 7179 | "eval_loss": 0.15803176164627075, |
| 7180 | "eval_runtime": 40.0466, |
| 7181 | "eval_samples_per_second": 11.412, |
| 7182 | "eval_steps_per_second": 1.448, |
| 7183 | "eval_wer": 0.1552477036590875, |
| 7184 | "step": 10400 |
| 7185 | }, |
| 7186 | { |
| 7187 | "epoch": 14.96, |
| 7188 | "learning_rate": 0.00021334985422740525, |
| 7189 | "loss": 0.0594, |
| 7190 | "step": 10410 |
| 7191 | }, |
| 7192 | { |
| 7193 | "epoch": 14.97, |
| 7194 | "learning_rate": 0.00021326239067055394, |
| 7195 | "loss": 0.0525, |
| 7196 | "step": 10420 |
| 7197 | }, |
| 7198 | { |
| 7199 | "epoch": 14.99, |
| 7200 | "learning_rate": 0.00021317492711370262, |
| 7201 | "loss": 0.0546, |
| 7202 | "step": 10430 |
| 7203 | }, |
| 7204 | { |
| 7205 | "epoch": 15.0, |
| 7206 | "learning_rate": 0.00021308746355685129, |
| 7207 | "loss": 0.065, |
| 7208 | "step": 10440 |
| 7209 | }, |
| 7210 | { |
| 7211 | "epoch": 15.01, |
| 7212 | "learning_rate": 0.00021299999999999997, |
| 7213 | "loss": 0.0553, |
| 7214 | "step": 10450 |
| 7215 | }, |
| 7216 | { |
| 7217 | "epoch": 15.03, |
| 7218 | "learning_rate": 0.00021291253644314866, |
| 7219 | "loss": 0.0502, |
| 7220 | "step": 10460 |
| 7221 | }, |
| 7222 | { |
| 7223 | "epoch": 15.04, |
| 7224 | "learning_rate": 0.00021282507288629735, |
| 7225 | "loss": 0.0518, |
| 7226 | "step": 10470 |
| 7227 | }, |
| 7228 | { |
| 7229 | "epoch": 15.06, |
| 7230 | "learning_rate": 0.00021273760932944604, |
| 7231 | "loss": 0.0533, |
| 7232 | "step": 10480 |
| 7233 | }, |
| 7234 | { |
| 7235 | "epoch": 15.07, |
| 7236 | "learning_rate": 0.00021265014577259472, |
| 7237 | "loss": 0.0534, |
| 7238 | "step": 10490 |
| 7239 | }, |
| 7240 | { |
| 7241 | "epoch": 15.09, |
| 7242 | "learning_rate": 0.00021256268221574344, |
| 7243 | "loss": 0.0624, |
| 7244 | "step": 10500 |
| 7245 | }, |
| 7246 | { |
| 7247 | "epoch": 15.09, |
| 7248 | "eval_loss": 0.16080322861671448, |
| 7249 | "eval_runtime": 39.9501, |
| 7250 | "eval_samples_per_second": 11.439, |
| 7251 | "eval_steps_per_second": 1.452, |
| 7252 | "eval_wer": 0.15946393615419366, |
| 7253 | "step": 10500 |
| 7254 | }, |
| 7255 | { |
| 7256 | "epoch": 15.1, |
| 7257 | "learning_rate": 0.00021247521865889213, |
| 7258 | "loss": 0.0495, |
| 7259 | "step": 10510 |
| 7260 | }, |
| 7261 | { |
| 7262 | "epoch": 15.11, |
| 7263 | "learning_rate": 0.00021238775510204082, |
| 7264 | "loss": 0.062, |
| 7265 | "step": 10520 |
| 7266 | }, |
| 7267 | { |
| 7268 | "epoch": 15.13, |
| 7269 | "learning_rate": 0.00021230029154518948, |
| 7270 | "loss": 0.0617, |
| 7271 | "step": 10530 |
| 7272 | }, |
| 7273 | { |
| 7274 | "epoch": 15.14, |
| 7275 | "learning_rate": 0.00021221282798833816, |
| 7276 | "loss": 0.0541, |
| 7277 | "step": 10540 |
| 7278 | }, |
| 7279 | { |
| 7280 | "epoch": 15.16, |
| 7281 | "learning_rate": 0.00021212536443148685, |
| 7282 | "loss": 0.0574, |
| 7283 | "step": 10550 |
| 7284 | }, |
| 7285 | { |
| 7286 | "epoch": 15.17, |
| 7287 | "learning_rate": 0.00021203790087463554, |
| 7288 | "loss": 0.0396, |
| 7289 | "step": 10560 |
| 7290 | }, |
| 7291 | { |
| 7292 | "epoch": 15.19, |
| 7293 | "learning_rate": 0.00021195043731778423, |
| 7294 | "loss": 0.0522, |
| 7295 | "step": 10570 |
| 7296 | }, |
| 7297 | { |
| 7298 | "epoch": 15.2, |
| 7299 | "learning_rate": 0.00021186297376093294, |
| 7300 | "loss": 0.0602, |
| 7301 | "step": 10580 |
| 7302 | }, |
| 7303 | { |
| 7304 | "epoch": 15.22, |
| 7305 | "learning_rate": 0.00021177551020408163, |
| 7306 | "loss": 0.0383, |
| 7307 | "step": 10590 |
| 7308 | }, |
| 7309 | { |
| 7310 | "epoch": 15.23, |
| 7311 | "learning_rate": 0.00021168804664723032, |
| 7312 | "loss": 0.0544, |
| 7313 | "step": 10600 |
| 7314 | }, |
| 7315 | { |
| 7316 | "epoch": 15.23, |
| 7317 | "eval_loss": 0.1565014123916626, |
| 7318 | "eval_runtime": 39.9025, |
| 7319 | "eval_samples_per_second": 11.453, |
| 7320 | "eval_steps_per_second": 1.454, |
| 7321 | "eval_wer": 0.16066857400993825, |
| 7322 | "step": 10600 |
| 7323 | }, |
| 7324 | { |
| 7325 | "epoch": 15.24, |
| 7326 | "learning_rate": 0.000211600583090379, |
| 7327 | "loss": 0.0482, |
| 7328 | "step": 10610 |
| 7329 | }, |
| 7330 | { |
| 7331 | "epoch": 15.26, |
| 7332 | "learning_rate": 0.00021151311953352767, |
| 7333 | "loss": 0.0644, |
| 7334 | "step": 10620 |
| 7335 | }, |
| 7336 | { |
| 7337 | "epoch": 15.27, |
| 7338 | "learning_rate": 0.00021142565597667636, |
| 7339 | "loss": 0.0465, |
| 7340 | "step": 10630 |
| 7341 | }, |
| 7342 | { |
| 7343 | "epoch": 15.29, |
| 7344 | "learning_rate": 0.00021133819241982504, |
| 7345 | "loss": 0.0482, |
| 7346 | "step": 10640 |
| 7347 | }, |
| 7348 | { |
| 7349 | "epoch": 15.3, |
| 7350 | "learning_rate": 0.00021125072886297373, |
| 7351 | "loss": 0.069, |
| 7352 | "step": 10650 |
| 7353 | }, |
| 7354 | { |
| 7355 | "epoch": 15.32, |
| 7356 | "learning_rate": 0.00021116326530612242, |
| 7357 | "loss": 0.0537, |
| 7358 | "step": 10660 |
| 7359 | }, |
| 7360 | { |
| 7361 | "epoch": 15.33, |
| 7362 | "learning_rate": 0.00021107580174927113, |
| 7363 | "loss": 0.053, |
| 7364 | "step": 10670 |
| 7365 | }, |
| 7366 | { |
| 7367 | "epoch": 15.34, |
| 7368 | "learning_rate": 0.00021098833819241982, |
| 7369 | "loss": 0.0516, |
| 7370 | "step": 10680 |
| 7371 | }, |
| 7372 | { |
| 7373 | "epoch": 15.36, |
| 7374 | "learning_rate": 0.0002109008746355685, |
| 7375 | "loss": 0.0402, |
| 7376 | "step": 10690 |
| 7377 | }, |
| 7378 | { |
| 7379 | "epoch": 15.37, |
| 7380 | "learning_rate": 0.0002108134110787172, |
| 7381 | "loss": 0.052, |
| 7382 | "step": 10700 |
| 7383 | }, |
| 7384 | { |
| 7385 | "epoch": 15.37, |
| 7386 | "eval_loss": 0.16009217500686646, |
| 7387 | "eval_runtime": 40.0212, |
| 7388 | "eval_samples_per_second": 11.419, |
| 7389 | "eval_steps_per_second": 1.449, |
| 7390 | "eval_wer": 0.15931335642222558, |
| 7391 | "step": 10700 |
| 7392 | }, |
| 7393 | { |
| 7394 | "epoch": 15.39, |
| 7395 | "learning_rate": 0.00021072594752186586, |
| 7396 | "loss": 0.0464, |
| 7397 | "step": 10710 |
| 7398 | }, |
| 7399 | { |
| 7400 | "epoch": 15.4, |
| 7401 | "learning_rate": 0.00021063848396501455, |
| 7402 | "loss": 0.0603, |
| 7403 | "step": 10720 |
| 7404 | }, |
| 7405 | { |
| 7406 | "epoch": 15.42, |
| 7407 | "learning_rate": 0.00021055102040816323, |
| 7408 | "loss": 0.0535, |
| 7409 | "step": 10730 |
| 7410 | }, |
| 7411 | { |
| 7412 | "epoch": 15.43, |
| 7413 | "learning_rate": 0.00021046355685131192, |
| 7414 | "loss": 0.0583, |
| 7415 | "step": 10740 |
| 7416 | }, |
| 7417 | { |
| 7418 | "epoch": 15.45, |
| 7419 | "learning_rate": 0.00021037609329446064, |
| 7420 | "loss": 0.0628, |
| 7421 | "step": 10750 |
| 7422 | }, |
| 7423 | { |
| 7424 | "epoch": 15.46, |
| 7425 | "learning_rate": 0.00021028862973760933, |
| 7426 | "loss": 0.0553, |
| 7427 | "step": 10760 |
| 7428 | }, |
| 7429 | { |
| 7430 | "epoch": 15.47, |
| 7431 | "learning_rate": 0.000210201166180758, |
| 7432 | "loss": 0.0526, |
| 7433 | "step": 10770 |
| 7434 | }, |
| 7435 | { |
| 7436 | "epoch": 15.49, |
| 7437 | "learning_rate": 0.0002101137026239067, |
| 7438 | "loss": 0.0417, |
| 7439 | "step": 10780 |
| 7440 | }, |
| 7441 | { |
| 7442 | "epoch": 15.5, |
| 7443 | "learning_rate": 0.0002100262390670554, |
| 7444 | "loss": 0.0498, |
| 7445 | "step": 10790 |
| 7446 | }, |
| 7447 | { |
| 7448 | "epoch": 15.52, |
| 7449 | "learning_rate": 0.00020993877551020405, |
| 7450 | "loss": 0.0577, |
| 7451 | "step": 10800 |
| 7452 | }, |
| 7453 | { |
| 7454 | "epoch": 15.52, |
| 7455 | "eval_loss": 0.1494068205356598, |
| 7456 | "eval_runtime": 40.6793, |
| 7457 | "eval_samples_per_second": 11.234, |
| 7458 | "eval_steps_per_second": 1.426, |
| 7459 | "eval_wer": 0.1552477036590875, |
| 7460 | "step": 10800 |
| 7461 | }, |
| 7462 | { |
| 7463 | "epoch": 15.53, |
| 7464 | "learning_rate": 0.00020985131195335274, |
| 7465 | "loss": 0.047, |
| 7466 | "step": 10810 |
| 7467 | }, |
| 7468 | { |
| 7469 | "epoch": 15.55, |
| 7470 | "learning_rate": 0.00020976384839650143, |
| 7471 | "loss": 0.0467, |
| 7472 | "step": 10820 |
| 7473 | }, |
| 7474 | { |
| 7475 | "epoch": 15.56, |
| 7476 | "learning_rate": 0.0002096763848396501, |
| 7477 | "loss": 0.0468, |
| 7478 | "step": 10830 |
| 7479 | }, |
| 7480 | { |
| 7481 | "epoch": 15.57, |
| 7482 | "learning_rate": 0.00020958892128279883, |
| 7483 | "loss": 0.0484, |
| 7484 | "step": 10840 |
| 7485 | }, |
| 7486 | { |
| 7487 | "epoch": 15.59, |
| 7488 | "learning_rate": 0.00020950145772594752, |
| 7489 | "loss": 0.0553, |
| 7490 | "step": 10850 |
| 7491 | }, |
| 7492 | { |
| 7493 | "epoch": 15.6, |
| 7494 | "learning_rate": 0.0002094139941690962, |
| 7495 | "loss": 0.0478, |
| 7496 | "step": 10860 |
| 7497 | }, |
| 7498 | { |
| 7499 | "epoch": 15.62, |
| 7500 | "learning_rate": 0.0002093265306122449, |
| 7501 | "loss": 0.061, |
| 7502 | "step": 10870 |
| 7503 | }, |
| 7504 | { |
| 7505 | "epoch": 15.63, |
| 7506 | "learning_rate": 0.00020923906705539358, |
| 7507 | "loss": 0.0492, |
| 7508 | "step": 10880 |
| 7509 | }, |
| 7510 | { |
| 7511 | "epoch": 15.65, |
| 7512 | "learning_rate": 0.00020915160349854224, |
| 7513 | "loss": 0.0462, |
| 7514 | "step": 10890 |
| 7515 | }, |
| 7516 | { |
| 7517 | "epoch": 15.66, |
| 7518 | "learning_rate": 0.00020906413994169093, |
| 7519 | "loss": 0.0762, |
| 7520 | "step": 10900 |
| 7521 | }, |
| 7522 | { |
| 7523 | "epoch": 15.66, |
| 7524 | "eval_loss": 0.1616104245185852, |
| 7525 | "eval_runtime": 40.2584, |
| 7526 | "eval_samples_per_second": 11.352, |
| 7527 | "eval_steps_per_second": 1.441, |
| 7528 | "eval_wer": 0.15991567535009787, |
| 7529 | "step": 10900 |
| 7530 | }, |
| 7531 | { |
| 7532 | "epoch": 15.68, |
| 7533 | "learning_rate": 0.00020897667638483962, |
| 7534 | "loss": 0.0435, |
| 7535 | "step": 10910 |
| 7536 | }, |
| 7537 | { |
| 7538 | "epoch": 15.69, |
| 7539 | "learning_rate": 0.0002088892128279883, |
| 7540 | "loss": 0.0551, |
| 7541 | "step": 10920 |
| 7542 | }, |
| 7543 | { |
| 7544 | "epoch": 15.7, |
| 7545 | "learning_rate": 0.00020880174927113702, |
| 7546 | "loss": 0.0621, |
| 7547 | "step": 10930 |
| 7548 | }, |
| 7549 | { |
| 7550 | "epoch": 15.72, |
| 7551 | "learning_rate": 0.0002087142857142857, |
| 7552 | "loss": 0.0501, |
| 7553 | "step": 10940 |
| 7554 | }, |
| 7555 | { |
| 7556 | "epoch": 15.73, |
| 7557 | "learning_rate": 0.0002086268221574344, |
| 7558 | "loss": 0.0519, |
| 7559 | "step": 10950 |
| 7560 | }, |
| 7561 | { |
| 7562 | "epoch": 15.75, |
| 7563 | "learning_rate": 0.00020853935860058308, |
| 7564 | "loss": 0.0415, |
| 7565 | "step": 10960 |
| 7566 | }, |
| 7567 | { |
| 7568 | "epoch": 15.76, |
| 7569 | "learning_rate": 0.00020845189504373177, |
| 7570 | "loss": 0.0717, |
| 7571 | "step": 10970 |
| 7572 | }, |
| 7573 | { |
| 7574 | "epoch": 15.78, |
| 7575 | "learning_rate": 0.00020836443148688043, |
| 7576 | "loss": 0.0691, |
| 7577 | "step": 10980 |
| 7578 | }, |
| 7579 | { |
| 7580 | "epoch": 15.79, |
| 7581 | "learning_rate": 0.00020827696793002912, |
| 7582 | "loss": 0.0477, |
| 7583 | "step": 10990 |
| 7584 | }, |
| 7585 | { |
| 7586 | "epoch": 15.8, |
| 7587 | "learning_rate": 0.0002081895043731778, |
| 7588 | "loss": 0.0509, |
| 7589 | "step": 11000 |
| 7590 | }, |
| 7591 | { |
| 7592 | "epoch": 15.8, |
| 7593 | "eval_loss": 0.1517663598060608, |
| 7594 | "eval_runtime": 39.8657, |
| 7595 | "eval_samples_per_second": 11.463, |
| 7596 | "eval_steps_per_second": 1.455, |
| 7597 | "eval_wer": 0.15359132660743863, |
| 7598 | "step": 11000 |
| 7599 | }, |
| 7600 | { |
| 7601 | "epoch": 15.82, |
| 7602 | "learning_rate": 0.00020810204081632652, |
| 7603 | "loss": 0.0382, |
| 7604 | "step": 11010 |
| 7605 | }, |
| 7606 | { |
| 7607 | "epoch": 15.83, |
| 7608 | "learning_rate": 0.0002080145772594752, |
| 7609 | "loss": 0.0558, |
| 7610 | "step": 11020 |
| 7611 | }, |
| 7612 | { |
| 7613 | "epoch": 15.85, |
| 7614 | "learning_rate": 0.0002079271137026239, |
| 7615 | "loss": 0.0464, |
| 7616 | "step": 11030 |
| 7617 | }, |
| 7618 | { |
| 7619 | "epoch": 15.86, |
| 7620 | "learning_rate": 0.00020783965014577259, |
| 7621 | "loss": 0.0541, |
| 7622 | "step": 11040 |
| 7623 | }, |
| 7624 | { |
| 7625 | "epoch": 15.88, |
| 7626 | "learning_rate": 0.00020775218658892127, |
| 7627 | "loss": 0.067, |
| 7628 | "step": 11050 |
| 7629 | }, |
| 7630 | { |
| 7631 | "epoch": 15.89, |
| 7632 | "learning_rate": 0.00020766472303206996, |
| 7633 | "loss": 0.0431, |
| 7634 | "step": 11060 |
| 7635 | }, |
| 7636 | { |
| 7637 | "epoch": 15.91, |
| 7638 | "learning_rate": 0.00020758600583090377, |
| 7639 | "loss": 0.0541, |
| 7640 | "step": 11070 |
| 7641 | }, |
| 7642 | { |
| 7643 | "epoch": 15.92, |
| 7644 | "learning_rate": 0.00020749854227405246, |
| 7645 | "loss": 0.0622, |
| 7646 | "step": 11080 |
| 7647 | }, |
| 7648 | { |
| 7649 | "epoch": 15.93, |
| 7650 | "learning_rate": 0.00020741107871720114, |
| 7651 | "loss": 0.0577, |
| 7652 | "step": 11090 |
| 7653 | }, |
| 7654 | { |
| 7655 | "epoch": 15.95, |
| 7656 | "learning_rate": 0.00020732361516034983, |
| 7657 | "loss": 0.0542, |
| 7658 | "step": 11100 |
| 7659 | }, |
| 7660 | { |
| 7661 | "epoch": 15.95, |
| 7662 | "eval_loss": 0.15586353838443756, |
| 7663 | "eval_runtime": 39.8742, |
| 7664 | "eval_samples_per_second": 11.461, |
| 7665 | "eval_steps_per_second": 1.455, |
| 7666 | "eval_wer": 0.15645234151483212, |
| 7667 | "step": 11100 |
| 7668 | }, |
| 7669 | { |
| 7670 | "epoch": 15.96, |
| 7671 | "learning_rate": 0.00020723615160349855, |
| 7672 | "loss": 0.0576, |
| 7673 | "step": 11110 |
| 7674 | }, |
| 7675 | { |
| 7676 | "epoch": 15.98, |
| 7677 | "learning_rate": 0.00020714868804664723, |
| 7678 | "loss": 0.0741, |
| 7679 | "step": 11120 |
| 7680 | }, |
| 7681 | { |
| 7682 | "epoch": 15.99, |
| 7683 | "learning_rate": 0.0002070612244897959, |
| 7684 | "loss": 0.0568, |
| 7685 | "step": 11130 |
| 7686 | }, |
| 7687 | { |
| 7688 | "epoch": 16.01, |
| 7689 | "learning_rate": 0.00020697376093294458, |
| 7690 | "loss": 0.0524, |
| 7691 | "step": 11140 |
| 7692 | }, |
| 7693 | { |
| 7694 | "epoch": 16.02, |
| 7695 | "learning_rate": 0.00020688629737609327, |
| 7696 | "loss": 0.0527, |
| 7697 | "step": 11150 |
| 7698 | }, |
| 7699 | { |
| 7700 | "epoch": 16.03, |
| 7701 | "learning_rate": 0.00020679883381924196, |
| 7702 | "loss": 0.047, |
| 7703 | "step": 11160 |
| 7704 | }, |
| 7705 | { |
| 7706 | "epoch": 16.05, |
| 7707 | "learning_rate": 0.00020671137026239065, |
| 7708 | "loss": 0.0621, |
| 7709 | "step": 11170 |
| 7710 | }, |
| 7711 | { |
| 7712 | "epoch": 16.06, |
| 7713 | "learning_rate": 0.00020662390670553933, |
| 7714 | "loss": 0.0552, |
| 7715 | "step": 11180 |
| 7716 | }, |
| 7717 | { |
| 7718 | "epoch": 16.08, |
| 7719 | "learning_rate": 0.00020653644314868802, |
| 7720 | "loss": 0.0441, |
| 7721 | "step": 11190 |
| 7722 | }, |
| 7723 | { |
| 7724 | "epoch": 16.09, |
| 7725 | "learning_rate": 0.00020644897959183674, |
| 7726 | "loss": 0.041, |
| 7727 | "step": 11200 |
| 7728 | }, |
| 7729 | { |
| 7730 | "epoch": 16.09, |
| 7731 | "eval_loss": 0.16197079420089722, |
| 7732 | "eval_runtime": 40.3539, |
| 7733 | "eval_samples_per_second": 11.325, |
| 7734 | "eval_steps_per_second": 1.437, |
| 7735 | "eval_wer": 0.15840987803041712, |
| 7736 | "step": 11200 |
| 7737 | }, |
| 7738 | { |
| 7739 | "epoch": 16.11, |
| 7740 | "learning_rate": 0.00020636151603498543, |
| 7741 | "loss": 0.0362, |
| 7742 | "step": 11210 |
| 7743 | }, |
| 7744 | { |
| 7745 | "epoch": 16.12, |
| 7746 | "learning_rate": 0.00020627405247813409, |
| 7747 | "loss": 0.0615, |
| 7748 | "step": 11220 |
| 7749 | }, |
| 7750 | { |
| 7751 | "epoch": 16.14, |
| 7752 | "learning_rate": 0.00020618658892128277, |
| 7753 | "loss": 0.0602, |
| 7754 | "step": 11230 |
| 7755 | }, |
| 7756 | { |
| 7757 | "epoch": 16.15, |
| 7758 | "learning_rate": 0.00020609912536443146, |
| 7759 | "loss": 0.0569, |
| 7760 | "step": 11240 |
| 7761 | }, |
| 7762 | { |
| 7763 | "epoch": 16.16, |
| 7764 | "learning_rate": 0.00020601166180758015, |
| 7765 | "loss": 0.0459, |
| 7766 | "step": 11250 |
| 7767 | }, |
| 7768 | { |
| 7769 | "epoch": 16.18, |
| 7770 | "learning_rate": 0.00020592419825072884, |
| 7771 | "loss": 0.0427, |
| 7772 | "step": 11260 |
| 7773 | }, |
| 7774 | { |
| 7775 | "epoch": 16.19, |
| 7776 | "learning_rate": 0.00020583673469387753, |
| 7777 | "loss": 0.0593, |
| 7778 | "step": 11270 |
| 7779 | }, |
| 7780 | { |
| 7781 | "epoch": 16.21, |
| 7782 | "learning_rate": 0.00020574927113702624, |
| 7783 | "loss": 0.056, |
| 7784 | "step": 11280 |
| 7785 | }, |
| 7786 | { |
| 7787 | "epoch": 16.22, |
| 7788 | "learning_rate": 0.00020566180758017493, |
| 7789 | "loss": 0.0566, |
| 7790 | "step": 11290 |
| 7791 | }, |
| 7792 | { |
| 7793 | "epoch": 16.24, |
| 7794 | "learning_rate": 0.00020557434402332362, |
| 7795 | "loss": 0.0449, |
| 7796 | "step": 11300 |
| 7797 | }, |
| 7798 | { |
| 7799 | "epoch": 16.24, |
| 7800 | "eval_loss": 0.15112736821174622, |
| 7801 | "eval_runtime": 39.9719, |
| 7802 | "eval_samples_per_second": 11.433, |
| 7803 | "eval_steps_per_second": 1.451, |
| 7804 | "eval_wer": 0.15298900767956633, |
| 7805 | "step": 11300 |
| 7806 | }, |
| 7807 | { |
| 7808 | "epoch": 16.25, |
| 7809 | "learning_rate": 0.00020548688046647228, |
| 7810 | "loss": 0.052, |
| 7811 | "step": 11310 |
| 7812 | }, |
| 7813 | { |
| 7814 | "epoch": 16.26, |
| 7815 | "learning_rate": 0.00020539941690962096, |
| 7816 | "loss": 0.0581, |
| 7817 | "step": 11320 |
| 7818 | }, |
| 7819 | { |
| 7820 | "epoch": 16.28, |
| 7821 | "learning_rate": 0.00020531195335276965, |
| 7822 | "loss": 0.0511, |
| 7823 | "step": 11330 |
| 7824 | }, |
| 7825 | { |
| 7826 | "epoch": 16.29, |
| 7827 | "learning_rate": 0.00020522448979591834, |
| 7828 | "loss": 0.0511, |
| 7829 | "step": 11340 |
| 7830 | }, |
| 7831 | { |
| 7832 | "epoch": 16.31, |
| 7833 | "learning_rate": 0.00020513702623906703, |
| 7834 | "loss": 0.056, |
| 7835 | "step": 11350 |
| 7836 | }, |
| 7837 | { |
| 7838 | "epoch": 16.32, |
| 7839 | "learning_rate": 0.00020504956268221572, |
| 7840 | "loss": 0.0385, |
| 7841 | "step": 11360 |
| 7842 | }, |
| 7843 | { |
| 7844 | "epoch": 16.34, |
| 7845 | "learning_rate": 0.00020496209912536443, |
| 7846 | "loss": 0.0542, |
| 7847 | "step": 11370 |
| 7848 | }, |
| 7849 | { |
| 7850 | "epoch": 16.35, |
| 7851 | "learning_rate": 0.00020487463556851312, |
| 7852 | "loss": 0.0441, |
| 7853 | "step": 11380 |
| 7854 | }, |
| 7855 | { |
| 7856 | "epoch": 16.36, |
| 7857 | "learning_rate": 0.0002047871720116618, |
| 7858 | "loss": 0.056, |
| 7859 | "step": 11390 |
| 7860 | }, |
| 7861 | { |
| 7862 | "epoch": 16.38, |
| 7863 | "learning_rate": 0.00020469970845481047, |
| 7864 | "loss": 0.0541, |
| 7865 | "step": 11400 |
| 7866 | }, |
| 7867 | { |
| 7868 | "epoch": 16.38, |
| 7869 | "eval_loss": 0.16502057015895844, |
| 7870 | "eval_runtime": 39.9246, |
| 7871 | "eval_samples_per_second": 11.447, |
| 7872 | "eval_steps_per_second": 1.453, |
| 7873 | "eval_wer": 0.16036741454600212, |
| 7874 | "step": 11400 |
| 7875 | }, |
| 7876 | { |
| 7877 | "epoch": 16.39, |
| 7878 | "learning_rate": 0.00020461224489795916, |
| 7879 | "loss": 0.052, |
| 7880 | "step": 11410 |
| 7881 | }, |
| 7882 | { |
| 7883 | "epoch": 16.41, |
| 7884 | "learning_rate": 0.00020452478134110784, |
| 7885 | "loss": 0.055, |
| 7886 | "step": 11420 |
| 7887 | }, |
| 7888 | { |
| 7889 | "epoch": 16.42, |
| 7890 | "learning_rate": 0.00020443731778425653, |
| 7891 | "loss": 0.0402, |
| 7892 | "step": 11430 |
| 7893 | }, |
| 7894 | { |
| 7895 | "epoch": 16.44, |
| 7896 | "learning_rate": 0.00020434985422740522, |
| 7897 | "loss": 0.0544, |
| 7898 | "step": 11440 |
| 7899 | }, |
| 7900 | { |
| 7901 | "epoch": 16.45, |
| 7902 | "learning_rate": 0.00020426239067055393, |
| 7903 | "loss": 0.0474, |
| 7904 | "step": 11450 |
| 7905 | }, |
| 7906 | { |
| 7907 | "epoch": 16.47, |
| 7908 | "learning_rate": 0.00020417492711370262, |
| 7909 | "loss": 0.0534, |
| 7910 | "step": 11460 |
| 7911 | }, |
| 7912 | { |
| 7913 | "epoch": 16.48, |
| 7914 | "learning_rate": 0.0002040874635568513, |
| 7915 | "loss": 0.0624, |
| 7916 | "step": 11470 |
| 7917 | }, |
| 7918 | { |
| 7919 | "epoch": 16.49, |
| 7920 | "learning_rate": 0.000204, |
| 7921 | "loss": 0.0476, |
| 7922 | "step": 11480 |
| 7923 | }, |
| 7924 | { |
| 7925 | "epoch": 16.51, |
| 7926 | "learning_rate": 0.00020391253644314866, |
| 7927 | "loss": 0.0496, |
| 7928 | "step": 11490 |
| 7929 | }, |
| 7930 | { |
| 7931 | "epoch": 16.52, |
| 7932 | "learning_rate": 0.00020382507288629735, |
| 7933 | "loss": 0.0467, |
| 7934 | "step": 11500 |
| 7935 | }, |
| 7936 | { |
| 7937 | "epoch": 16.52, |
| 7938 | "eval_loss": 0.1587601602077484, |
| 7939 | "eval_runtime": 40.0875, |
| 7940 | "eval_samples_per_second": 11.4, |
| 7941 | "eval_steps_per_second": 1.447, |
| 7942 | "eval_wer": 0.1572052401746725, |
| 7943 | "step": 11500 |
| 7944 | }, |
| 7945 | { |
| 7946 | "epoch": 16.54, |
| 7947 | "learning_rate": 0.00020373760932944603, |
| 7948 | "loss": 0.0546, |
| 7949 | "step": 11510 |
| 7950 | }, |
| 7951 | { |
| 7952 | "epoch": 16.55, |
| 7953 | "learning_rate": 0.00020365014577259472, |
| 7954 | "loss": 0.0515, |
| 7955 | "step": 11520 |
| 7956 | }, |
| 7957 | { |
| 7958 | "epoch": 16.57, |
| 7959 | "learning_rate": 0.0002035626822157434, |
| 7960 | "loss": 0.0493, |
| 7961 | "step": 11530 |
| 7962 | }, |
| 7963 | { |
| 7964 | "epoch": 16.58, |
| 7965 | "learning_rate": 0.00020347521865889213, |
| 7966 | "loss": 0.0529, |
| 7967 | "step": 11540 |
| 7968 | }, |
| 7969 | { |
| 7970 | "epoch": 16.59, |
| 7971 | "learning_rate": 0.00020338775510204081, |
| 7972 | "loss": 0.0473, |
| 7973 | "step": 11550 |
| 7974 | }, |
| 7975 | { |
| 7976 | "epoch": 16.61, |
| 7977 | "learning_rate": 0.0002033002915451895, |
| 7978 | "loss": 0.0439, |
| 7979 | "step": 11560 |
| 7980 | }, |
| 7981 | { |
| 7982 | "epoch": 16.62, |
| 7983 | "learning_rate": 0.0002032128279883382, |
| 7984 | "loss": 0.0563, |
| 7985 | "step": 11570 |
| 7986 | }, |
| 7987 | { |
| 7988 | "epoch": 16.64, |
| 7989 | "learning_rate": 0.00020312536443148685, |
| 7990 | "loss": 0.0501, |
| 7991 | "step": 11580 |
| 7992 | }, |
| 7993 | { |
| 7994 | "epoch": 16.65, |
| 7995 | "learning_rate": 0.00020303790087463554, |
| 7996 | "loss": 0.0624, |
| 7997 | "step": 11590 |
| 7998 | }, |
| 7999 | { |
| 8000 | "epoch": 16.67, |
| 8001 | "learning_rate": 0.00020295043731778423, |
| 8002 | "loss": 0.0507, |
| 8003 | "step": 11600 |
| 8004 | }, |
| 8005 | { |
| 8006 | "epoch": 16.67, |
| 8007 | "eval_loss": 0.16117839515209198, |
| 8008 | "eval_runtime": 39.882, |
| 8009 | "eval_samples_per_second": 11.459, |
| 8010 | "eval_steps_per_second": 1.454, |
| 8011 | "eval_wer": 0.16262611052552325, |
| 8012 | "step": 11600 |
| 8013 | }, |
| 8014 | { |
| 8015 | "epoch": 16.68, |
| 8016 | "learning_rate": 0.00020286297376093291, |
| 8017 | "loss": 0.0458, |
| 8018 | "step": 11610 |
| 8019 | }, |
| 8020 | { |
| 8021 | "epoch": 16.7, |
| 8022 | "learning_rate": 0.0002027755102040816, |
| 8023 | "loss": 0.0498, |
| 8024 | "step": 11620 |
| 8025 | }, |
| 8026 | { |
| 8027 | "epoch": 16.71, |
| 8028 | "learning_rate": 0.00020268804664723032, |
| 8029 | "loss": 0.0548, |
| 8030 | "step": 11630 |
| 8031 | }, |
| 8032 | { |
| 8033 | "epoch": 16.72, |
| 8034 | "learning_rate": 0.000202600583090379, |
| 8035 | "loss": 0.0446, |
| 8036 | "step": 11640 |
| 8037 | }, |
| 8038 | { |
| 8039 | "epoch": 16.74, |
| 8040 | "learning_rate": 0.0002025131195335277, |
| 8041 | "loss": 0.0469, |
| 8042 | "step": 11650 |
| 8043 | }, |
| 8044 | { |
| 8045 | "epoch": 16.75, |
| 8046 | "learning_rate": 0.00020242565597667638, |
| 8047 | "loss": 0.0471, |
| 8048 | "step": 11660 |
| 8049 | }, |
| 8050 | { |
| 8051 | "epoch": 16.77, |
| 8052 | "learning_rate": 0.00020233819241982504, |
| 8053 | "loss": 0.0673, |
| 8054 | "step": 11670 |
| 8055 | }, |
| 8056 | { |
| 8057 | "epoch": 16.78, |
| 8058 | "learning_rate": 0.00020225072886297373, |
| 8059 | "loss": 0.0393, |
| 8060 | "step": 11680 |
| 8061 | }, |
| 8062 | { |
| 8063 | "epoch": 16.8, |
| 8064 | "learning_rate": 0.00020216326530612242, |
| 8065 | "loss": 0.0569, |
| 8066 | "step": 11690 |
| 8067 | }, |
| 8068 | { |
| 8069 | "epoch": 16.81, |
| 8070 | "learning_rate": 0.0002020758017492711, |
| 8071 | "loss": 0.0558, |
| 8072 | "step": 11700 |
| 8073 | }, |
| 8074 | { |
| 8075 | "epoch": 16.81, |
| 8076 | "eval_loss": 0.16593004763126373, |
| 8077 | "eval_runtime": 39.9159, |
| 8078 | "eval_samples_per_second": 11.449, |
| 8079 | "eval_steps_per_second": 1.453, |
| 8080 | "eval_wer": 0.16096973347387442, |
| 8081 | "step": 11700 |
| 8082 | }, |
| 8083 | { |
| 8084 | "epoch": 16.82, |
| 8085 | "learning_rate": 0.00020198833819241982, |
| 8086 | "loss": 0.0504, |
| 8087 | "step": 11710 |
| 8088 | }, |
| 8089 | { |
| 8090 | "epoch": 16.84, |
| 8091 | "learning_rate": 0.0002019008746355685, |
| 8092 | "loss": 0.0514, |
| 8093 | "step": 11720 |
| 8094 | }, |
| 8095 | { |
| 8096 | "epoch": 16.85, |
| 8097 | "learning_rate": 0.0002018134110787172, |
| 8098 | "loss": 0.0549, |
| 8099 | "step": 11730 |
| 8100 | }, |
| 8101 | { |
| 8102 | "epoch": 16.87, |
| 8103 | "learning_rate": 0.00020172594752186588, |
| 8104 | "loss": 0.0633, |
| 8105 | "step": 11740 |
| 8106 | }, |
| 8107 | { |
| 8108 | "epoch": 16.88, |
| 8109 | "learning_rate": 0.00020163848396501457, |
| 8110 | "loss": 0.0622, |
| 8111 | "step": 11750 |
| 8112 | }, |
| 8113 | { |
| 8114 | "epoch": 16.9, |
| 8115 | "learning_rate": 0.00020155102040816323, |
| 8116 | "loss": 0.041, |
| 8117 | "step": 11760 |
| 8118 | }, |
| 8119 | { |
| 8120 | "epoch": 16.91, |
| 8121 | "learning_rate": 0.00020146355685131192, |
| 8122 | "loss": 0.0537, |
| 8123 | "step": 11770 |
| 8124 | }, |
| 8125 | { |
| 8126 | "epoch": 16.93, |
| 8127 | "learning_rate": 0.0002013760932944606, |
| 8128 | "loss": 0.0601, |
| 8129 | "step": 11780 |
| 8130 | }, |
| 8131 | { |
| 8132 | "epoch": 16.94, |
| 8133 | "learning_rate": 0.0002012886297376093, |
| 8134 | "loss": 0.0484, |
| 8135 | "step": 11790 |
| 8136 | }, |
| 8137 | { |
| 8138 | "epoch": 16.95, |
| 8139 | "learning_rate": 0.000201201166180758, |
| 8140 | "loss": 0.0538, |
| 8141 | "step": 11800 |
| 8142 | }, |
| 8143 | { |
| 8144 | "epoch": 16.95, |
| 8145 | "eval_loss": 0.16603288054466248, |
| 8146 | "eval_runtime": 39.9783, |
| 8147 | "eval_samples_per_second": 11.431, |
| 8148 | "eval_steps_per_second": 1.451, |
| 8149 | "eval_wer": 0.15901219695828941, |
| 8150 | "step": 11800 |
| 8151 | }, |
| 8152 | { |
| 8153 | "epoch": 16.97, |
| 8154 | "learning_rate": 0.0002011137026239067, |
| 8155 | "loss": 0.045, |
| 8156 | "step": 11810 |
| 8157 | }, |
| 8158 | { |
| 8159 | "epoch": 16.98, |
| 8160 | "learning_rate": 0.0002010262390670554, |
| 8161 | "loss": 0.0527, |
| 8162 | "step": 11820 |
| 8163 | }, |
| 8164 | { |
| 8165 | "epoch": 17.0, |
| 8166 | "learning_rate": 0.00020093877551020407, |
| 8167 | "loss": 0.0446, |
| 8168 | "step": 11830 |
| 8169 | }, |
| 8170 | { |
| 8171 | "epoch": 17.01, |
| 8172 | "learning_rate": 0.00020085131195335276, |
| 8173 | "loss": 0.0503, |
| 8174 | "step": 11840 |
| 8175 | }, |
| 8176 | { |
| 8177 | "epoch": 17.03, |
| 8178 | "learning_rate": 0.00020076384839650142, |
| 8179 | "loss": 0.0435, |
| 8180 | "step": 11850 |
| 8181 | }, |
| 8182 | { |
| 8183 | "epoch": 17.04, |
| 8184 | "learning_rate": 0.0002006763848396501, |
| 8185 | "loss": 0.0375, |
| 8186 | "step": 11860 |
| 8187 | }, |
| 8188 | { |
| 8189 | "epoch": 17.05, |
| 8190 | "learning_rate": 0.0002005889212827988, |
| 8191 | "loss": 0.0511, |
| 8192 | "step": 11870 |
| 8193 | }, |
| 8194 | { |
| 8195 | "epoch": 17.07, |
| 8196 | "learning_rate": 0.00020050145772594751, |
| 8197 | "loss": 0.0388, |
| 8198 | "step": 11880 |
| 8199 | }, |
| 8200 | { |
| 8201 | "epoch": 17.08, |
| 8202 | "learning_rate": 0.0002004139941690962, |
| 8203 | "loss": 0.0468, |
| 8204 | "step": 11890 |
| 8205 | }, |
| 8206 | { |
| 8207 | "epoch": 17.1, |
| 8208 | "learning_rate": 0.0002003265306122449, |
| 8209 | "loss": 0.0465, |
| 8210 | "step": 11900 |
| 8211 | }, |
| 8212 | { |
| 8213 | "epoch": 17.1, |
| 8214 | "eval_loss": 0.16712433099746704, |
| 8215 | "eval_runtime": 39.8942, |
| 8216 | "eval_samples_per_second": 11.455, |
| 8217 | "eval_steps_per_second": 1.454, |
| 8218 | "eval_wer": 0.15359132660743863, |
| 8219 | "step": 11900 |
| 8220 | }, |
| 8221 | { |
| 8222 | "epoch": 17.11, |
| 8223 | "learning_rate": 0.00020023906705539358, |
| 8224 | "loss": 0.0585, |
| 8225 | "step": 11910 |
| 8226 | }, |
| 8227 | { |
| 8228 | "epoch": 17.13, |
| 8229 | "learning_rate": 0.00020015160349854227, |
| 8230 | "loss": 0.0591, |
| 8231 | "step": 11920 |
| 8232 | }, |
| 8233 | { |
| 8234 | "epoch": 17.14, |
| 8235 | "learning_rate": 0.00020006413994169095, |
| 8236 | "loss": 0.0358, |
| 8237 | "step": 11930 |
| 8238 | }, |
| 8239 | { |
| 8240 | "epoch": 17.16, |
| 8241 | "learning_rate": 0.00019997667638483961, |
| 8242 | "loss": 0.0715, |
| 8243 | "step": 11940 |
| 8244 | }, |
| 8245 | { |
| 8246 | "epoch": 17.17, |
| 8247 | "learning_rate": 0.0001998892128279883, |
| 8248 | "loss": 0.0445, |
| 8249 | "step": 11950 |
| 8250 | }, |
| 8251 | { |
| 8252 | "epoch": 17.18, |
| 8253 | "learning_rate": 0.000199801749271137, |
| 8254 | "loss": 0.0582, |
| 8255 | "step": 11960 |
| 8256 | }, |
| 8257 | { |
| 8258 | "epoch": 17.2, |
| 8259 | "learning_rate": 0.0001997142857142857, |
| 8260 | "loss": 0.0634, |
| 8261 | "step": 11970 |
| 8262 | }, |
| 8263 | { |
| 8264 | "epoch": 17.21, |
| 8265 | "learning_rate": 0.0001996268221574344, |
| 8266 | "loss": 0.0422, |
| 8267 | "step": 11980 |
| 8268 | }, |
| 8269 | { |
| 8270 | "epoch": 17.23, |
| 8271 | "learning_rate": 0.00019953935860058308, |
| 8272 | "loss": 0.0569, |
| 8273 | "step": 11990 |
| 8274 | }, |
| 8275 | { |
| 8276 | "epoch": 17.24, |
| 8277 | "learning_rate": 0.00019945189504373177, |
| 8278 | "loss": 0.0453, |
| 8279 | "step": 12000 |
| 8280 | }, |
| 8281 | { |
| 8282 | "epoch": 17.24, |
| 8283 | "eval_loss": 0.16343770921230316, |
| 8284 | "eval_runtime": 40.2019, |
| 8285 | "eval_samples_per_second": 11.368, |
| 8286 | "eval_steps_per_second": 1.443, |
| 8287 | "eval_wer": 0.15359132660743863, |
| 8288 | "step": 12000 |
| 8289 | }, |
| 8290 | { |
| 8291 | "epoch": 17.26, |
| 8292 | "learning_rate": 0.00019936443148688046, |
| 8293 | "loss": 0.0483, |
| 8294 | "step": 12010 |
| 8295 | }, |
| 8296 | { |
| 8297 | "epoch": 17.27, |
| 8298 | "learning_rate": 0.00019927696793002914, |
| 8299 | "loss": 0.0479, |
| 8300 | "step": 12020 |
| 8301 | }, |
| 8302 | { |
| 8303 | "epoch": 17.28, |
| 8304 | "learning_rate": 0.0001991895043731778, |
| 8305 | "loss": 0.0434, |
| 8306 | "step": 12030 |
| 8307 | }, |
| 8308 | { |
| 8309 | "epoch": 17.3, |
| 8310 | "learning_rate": 0.0001991020408163265, |
| 8311 | "loss": 0.0618, |
| 8312 | "step": 12040 |
| 8313 | }, |
| 8314 | { |
| 8315 | "epoch": 17.31, |
| 8316 | "learning_rate": 0.00019901457725947518, |
| 8317 | "loss": 0.0422, |
| 8318 | "step": 12050 |
| 8319 | }, |
| 8320 | { |
| 8321 | "epoch": 17.33, |
| 8322 | "learning_rate": 0.0001989271137026239, |
| 8323 | "loss": 0.0444, |
| 8324 | "step": 12060 |
| 8325 | }, |
| 8326 | { |
| 8327 | "epoch": 17.34, |
| 8328 | "learning_rate": 0.00019883965014577258, |
| 8329 | "loss": 0.0555, |
| 8330 | "step": 12070 |
| 8331 | }, |
| 8332 | { |
| 8333 | "epoch": 17.36, |
| 8334 | "learning_rate": 0.00019876093294460642, |
| 8335 | "loss": 0.0392, |
| 8336 | "step": 12080 |
| 8337 | }, |
| 8338 | { |
| 8339 | "epoch": 17.37, |
| 8340 | "learning_rate": 0.00019867346938775508, |
| 8341 | "loss": 0.0604, |
| 8342 | "step": 12090 |
| 8343 | }, |
| 8344 | { |
| 8345 | "epoch": 17.39, |
| 8346 | "learning_rate": 0.00019858600583090377, |
| 8347 | "loss": 0.0459, |
| 8348 | "step": 12100 |
| 8349 | }, |
| 8350 | { |
| 8351 | "epoch": 17.39, |
| 8352 | "eval_loss": 0.16481797397136688, |
| 8353 | "eval_runtime": 39.9889, |
| 8354 | "eval_samples_per_second": 11.428, |
| 8355 | "eval_steps_per_second": 1.45, |
| 8356 | "eval_wer": 0.15856045776238517, |
| 8357 | "step": 12100 |
| 8358 | }, |
| 8359 | { |
| 8360 | "epoch": 17.4, |
| 8361 | "learning_rate": 0.00019849854227405245, |
| 8362 | "loss": 0.0508, |
| 8363 | "step": 12110 |
| 8364 | }, |
| 8365 | { |
| 8366 | "epoch": 17.41, |
| 8367 | "learning_rate": 0.00019841107871720114, |
| 8368 | "loss": 0.0506, |
| 8369 | "step": 12120 |
| 8370 | }, |
| 8371 | { |
| 8372 | "epoch": 17.43, |
| 8373 | "learning_rate": 0.00019832361516034983, |
| 8374 | "loss": 0.0386, |
| 8375 | "step": 12130 |
| 8376 | }, |
| 8377 | { |
| 8378 | "epoch": 17.44, |
| 8379 | "learning_rate": 0.00019823615160349852, |
| 8380 | "loss": 0.0586, |
| 8381 | "step": 12140 |
| 8382 | }, |
| 8383 | { |
| 8384 | "epoch": 17.46, |
| 8385 | "learning_rate": 0.00019814868804664723, |
| 8386 | "loss": 0.0486, |
| 8387 | "step": 12150 |
| 8388 | }, |
| 8389 | { |
| 8390 | "epoch": 17.47, |
| 8391 | "learning_rate": 0.00019806122448979592, |
| 8392 | "loss": 0.0655, |
| 8393 | "step": 12160 |
| 8394 | }, |
| 8395 | { |
| 8396 | "epoch": 17.49, |
| 8397 | "learning_rate": 0.0001979737609329446, |
| 8398 | "loss": 0.052, |
| 8399 | "step": 12170 |
| 8400 | }, |
| 8401 | { |
| 8402 | "epoch": 17.5, |
| 8403 | "learning_rate": 0.00019788629737609327, |
| 8404 | "loss": 0.0415, |
| 8405 | "step": 12180 |
| 8406 | }, |
| 8407 | { |
| 8408 | "epoch": 17.51, |
| 8409 | "learning_rate": 0.00019779883381924196, |
| 8410 | "loss": 0.0468, |
| 8411 | "step": 12190 |
| 8412 | }, |
| 8413 | { |
| 8414 | "epoch": 17.53, |
| 8415 | "learning_rate": 0.00019771137026239064, |
| 8416 | "loss": 0.0481, |
| 8417 | "step": 12200 |
| 8418 | }, |
| 8419 | { |
| 8420 | "epoch": 17.53, |
| 8421 | "eval_loss": 0.16811503469944, |
| 8422 | "eval_runtime": 39.855, |
| 8423 | "eval_samples_per_second": 11.467, |
| 8424 | "eval_steps_per_second": 1.455, |
| 8425 | "eval_wer": 0.1537419063394067, |
| 8426 | "step": 12200 |
| 8427 | }, |
| 8428 | { |
| 8429 | "epoch": 17.54, |
| 8430 | "learning_rate": 0.00019762390670553933, |
| 8431 | "loss": 0.0529, |
| 8432 | "step": 12210 |
| 8433 | }, |
| 8434 | { |
| 8435 | "epoch": 17.56, |
| 8436 | "learning_rate": 0.00019753644314868802, |
| 8437 | "loss": 0.0568, |
| 8438 | "step": 12220 |
| 8439 | }, |
| 8440 | { |
| 8441 | "epoch": 17.57, |
| 8442 | "learning_rate": 0.0001974489795918367, |
| 8443 | "loss": 0.0454, |
| 8444 | "step": 12230 |
| 8445 | }, |
| 8446 | { |
| 8447 | "epoch": 17.59, |
| 8448 | "learning_rate": 0.00019736151603498542, |
| 8449 | "loss": 0.0558, |
| 8450 | "step": 12240 |
| 8451 | }, |
| 8452 | { |
| 8453 | "epoch": 17.6, |
| 8454 | "learning_rate": 0.0001972740524781341, |
| 8455 | "loss": 0.0351, |
| 8456 | "step": 12250 |
| 8457 | }, |
| 8458 | { |
| 8459 | "epoch": 17.61, |
| 8460 | "learning_rate": 0.0001971865889212828, |
| 8461 | "loss": 0.0534, |
| 8462 | "step": 12260 |
| 8463 | }, |
| 8464 | { |
| 8465 | "epoch": 17.63, |
| 8466 | "learning_rate": 0.00019709912536443146, |
| 8467 | "loss": 0.0451, |
| 8468 | "step": 12270 |
| 8469 | }, |
| 8470 | { |
| 8471 | "epoch": 17.64, |
| 8472 | "learning_rate": 0.00019701166180758015, |
| 8473 | "loss": 0.0438, |
| 8474 | "step": 12280 |
| 8475 | }, |
| 8476 | { |
| 8477 | "epoch": 17.66, |
| 8478 | "learning_rate": 0.00019692419825072884, |
| 8479 | "loss": 0.055, |
| 8480 | "step": 12290 |
| 8481 | }, |
| 8482 | { |
| 8483 | "epoch": 17.67, |
| 8484 | "learning_rate": 0.00019683673469387752, |
| 8485 | "loss": 0.0506, |
| 8486 | "step": 12300 |
| 8487 | }, |
| 8488 | { |
| 8489 | "epoch": 17.67, |
| 8490 | "eval_loss": 0.16215792298316956, |
| 8491 | "eval_runtime": 40.1021, |
| 8492 | "eval_samples_per_second": 11.396, |
| 8493 | "eval_steps_per_second": 1.446, |
| 8494 | "eval_wer": 0.15750639963860863, |
| 8495 | "step": 12300 |
| 8496 | }, |
| 8497 | { |
| 8498 | "epoch": 17.69, |
| 8499 | "learning_rate": 0.0001967492711370262, |
| 8500 | "loss": 0.0472, |
| 8501 | "step": 12310 |
| 8502 | }, |
| 8503 | { |
| 8504 | "epoch": 17.7, |
| 8505 | "learning_rate": 0.0001966618075801749, |
| 8506 | "loss": 0.0624, |
| 8507 | "step": 12320 |
| 8508 | }, |
| 8509 | { |
| 8510 | "epoch": 17.72, |
| 8511 | "learning_rate": 0.00019657434402332361, |
| 8512 | "loss": 0.0492, |
| 8513 | "step": 12330 |
| 8514 | }, |
| 8515 | { |
| 8516 | "epoch": 17.73, |
| 8517 | "learning_rate": 0.0001964868804664723, |
| 8518 | "loss": 0.0607, |
| 8519 | "step": 12340 |
| 8520 | }, |
| 8521 | { |
| 8522 | "epoch": 17.74, |
| 8523 | "learning_rate": 0.000196399416909621, |
| 8524 | "loss": 0.0454, |
| 8525 | "step": 12350 |
| 8526 | }, |
| 8527 | { |
| 8528 | "epoch": 17.76, |
| 8529 | "learning_rate": 0.00019631195335276965, |
| 8530 | "loss": 0.0457, |
| 8531 | "step": 12360 |
| 8532 | }, |
| 8533 | { |
| 8534 | "epoch": 17.77, |
| 8535 | "learning_rate": 0.00019622448979591834, |
| 8536 | "loss": 0.0618, |
| 8537 | "step": 12370 |
| 8538 | }, |
| 8539 | { |
| 8540 | "epoch": 17.79, |
| 8541 | "learning_rate": 0.00019613702623906703, |
| 8542 | "loss": 0.034, |
| 8543 | "step": 12380 |
| 8544 | }, |
| 8545 | { |
| 8546 | "epoch": 17.8, |
| 8547 | "learning_rate": 0.00019604956268221571, |
| 8548 | "loss": 0.0467, |
| 8549 | "step": 12390 |
| 8550 | }, |
| 8551 | { |
| 8552 | "epoch": 17.82, |
| 8553 | "learning_rate": 0.0001959620991253644, |
| 8554 | "loss": 0.057, |
| 8555 | "step": 12400 |
| 8556 | }, |
| 8557 | { |
| 8558 | "epoch": 17.82, |
| 8559 | "eval_loss": 0.15522630512714386, |
| 8560 | "eval_runtime": 39.9906, |
| 8561 | "eval_samples_per_second": 11.428, |
| 8562 | "eval_steps_per_second": 1.45, |
| 8563 | "eval_wer": 0.15298900767956633, |
| 8564 | "step": 12400 |
| 8565 | }, |
| 8566 | { |
| 8567 | "epoch": 17.83, |
| 8568 | "learning_rate": 0.00019587463556851312, |
| 8569 | "loss": 0.0523, |
| 8570 | "step": 12410 |
| 8571 | }, |
| 8572 | { |
| 8573 | "epoch": 17.84, |
| 8574 | "learning_rate": 0.0001957871720116618, |
| 8575 | "loss": 0.0505, |
| 8576 | "step": 12420 |
| 8577 | }, |
| 8578 | { |
| 8579 | "epoch": 17.86, |
| 8580 | "learning_rate": 0.0001956997084548105, |
| 8581 | "loss": 0.0351, |
| 8582 | "step": 12430 |
| 8583 | }, |
| 8584 | { |
| 8585 | "epoch": 17.87, |
| 8586 | "learning_rate": 0.00019561224489795918, |
| 8587 | "loss": 0.0668, |
| 8588 | "step": 12440 |
| 8589 | }, |
| 8590 | { |
| 8591 | "epoch": 17.89, |
| 8592 | "learning_rate": 0.00019552478134110784, |
| 8593 | "loss": 0.053, |
| 8594 | "step": 12450 |
| 8595 | }, |
| 8596 | { |
| 8597 | "epoch": 17.9, |
| 8598 | "learning_rate": 0.00019543731778425653, |
| 8599 | "loss": 0.0562, |
| 8600 | "step": 12460 |
| 8601 | }, |
| 8602 | { |
| 8603 | "epoch": 17.92, |
| 8604 | "learning_rate": 0.00019534985422740522, |
| 8605 | "loss": 0.0597, |
| 8606 | "step": 12470 |
| 8607 | }, |
| 8608 | { |
| 8609 | "epoch": 17.93, |
| 8610 | "learning_rate": 0.0001952623906705539, |
| 8611 | "loss": 0.06, |
| 8612 | "step": 12480 |
| 8613 | }, |
| 8614 | { |
| 8615 | "epoch": 17.95, |
| 8616 | "learning_rate": 0.0001951749271137026, |
| 8617 | "loss": 0.0595, |
| 8618 | "step": 12490 |
| 8619 | }, |
| 8620 | { |
| 8621 | "epoch": 17.96, |
| 8622 | "learning_rate": 0.0001950874635568513, |
| 8623 | "loss": 0.0492, |
| 8624 | "step": 12500 |
| 8625 | }, |
| 8626 | { |
| 8627 | "epoch": 17.96, |
| 8628 | "eval_loss": 0.15482190251350403, |
| 8629 | "eval_runtime": 39.803, |
| 8630 | "eval_samples_per_second": 11.482, |
| 8631 | "eval_steps_per_second": 1.457, |
| 8632 | "eval_wer": 0.15148321035988557, |
| 8633 | "step": 12500 |
| 8634 | }, |
| 8635 | { |
| 8636 | "epoch": 17.97, |
| 8637 | "learning_rate": 0.000195, |
| 8638 | "loss": 0.0518, |
| 8639 | "step": 12510 |
| 8640 | }, |
| 8641 | { |
| 8642 | "epoch": 17.99, |
| 8643 | "learning_rate": 0.00019491253644314868, |
| 8644 | "loss": 0.0581, |
| 8645 | "step": 12520 |
| 8646 | }, |
| 8647 | { |
| 8648 | "epoch": 18.0, |
| 8649 | "learning_rate": 0.00019482507288629737, |
| 8650 | "loss": 0.0601, |
| 8651 | "step": 12530 |
| 8652 | }, |
| 8653 | { |
| 8654 | "epoch": 18.02, |
| 8655 | "learning_rate": 0.00019473760932944603, |
| 8656 | "loss": 0.0456, |
| 8657 | "step": 12540 |
| 8658 | }, |
| 8659 | { |
| 8660 | "epoch": 18.03, |
| 8661 | "learning_rate": 0.00019465014577259472, |
| 8662 | "loss": 0.039, |
| 8663 | "step": 12550 |
| 8664 | }, |
| 8665 | { |
| 8666 | "epoch": 18.05, |
| 8667 | "learning_rate": 0.0001945626822157434, |
| 8668 | "loss": 0.0476, |
| 8669 | "step": 12560 |
| 8670 | }, |
| 8671 | { |
| 8672 | "epoch": 18.06, |
| 8673 | "learning_rate": 0.0001944752186588921, |
| 8674 | "loss": 0.0403, |
| 8675 | "step": 12570 |
| 8676 | }, |
| 8677 | { |
| 8678 | "epoch": 18.07, |
| 8679 | "learning_rate": 0.0001943877551020408, |
| 8680 | "loss": 0.0417, |
| 8681 | "step": 12580 |
| 8682 | }, |
| 8683 | { |
| 8684 | "epoch": 18.09, |
| 8685 | "learning_rate": 0.0001943002915451895, |
| 8686 | "loss": 0.0489, |
| 8687 | "step": 12590 |
| 8688 | }, |
| 8689 | { |
| 8690 | "epoch": 18.1, |
| 8691 | "learning_rate": 0.0001942128279883382, |
| 8692 | "loss": 0.0555, |
| 8693 | "step": 12600 |
| 8694 | }, |
| 8695 | { |
| 8696 | "epoch": 18.1, |
| 8697 | "eval_loss": 0.1575390100479126, |
| 8698 | "eval_runtime": 39.9057, |
| 8699 | "eval_samples_per_second": 11.452, |
| 8700 | "eval_steps_per_second": 1.453, |
| 8701 | "eval_wer": 0.1532901671435025, |
| 8702 | "step": 12600 |
| 8703 | }, |
| 8704 | { |
| 8705 | "epoch": 18.12, |
| 8706 | "learning_rate": 0.00019412536443148688, |
| 8707 | "loss": 0.0471, |
| 8708 | "step": 12610 |
| 8709 | }, |
| 8710 | { |
| 8711 | "epoch": 18.13, |
| 8712 | "learning_rate": 0.00019403790087463556, |
| 8713 | "loss": 0.0501, |
| 8714 | "step": 12620 |
| 8715 | }, |
| 8716 | { |
| 8717 | "epoch": 18.15, |
| 8718 | "learning_rate": 0.00019395043731778422, |
| 8719 | "loss": 0.0415, |
| 8720 | "step": 12630 |
| 8721 | }, |
| 8722 | { |
| 8723 | "epoch": 18.16, |
| 8724 | "learning_rate": 0.0001938629737609329, |
| 8725 | "loss": 0.0538, |
| 8726 | "step": 12640 |
| 8727 | }, |
| 8728 | { |
| 8729 | "epoch": 18.18, |
| 8730 | "learning_rate": 0.0001937755102040816, |
| 8731 | "loss": 0.052, |
| 8732 | "step": 12650 |
| 8733 | }, |
| 8734 | { |
| 8735 | "epoch": 18.19, |
| 8736 | "learning_rate": 0.0001936880466472303, |
| 8737 | "loss": 0.0515, |
| 8738 | "step": 12660 |
| 8739 | }, |
| 8740 | { |
| 8741 | "epoch": 18.2, |
| 8742 | "learning_rate": 0.000193600583090379, |
| 8743 | "loss": 0.0416, |
| 8744 | "step": 12670 |
| 8745 | }, |
| 8746 | { |
| 8747 | "epoch": 18.22, |
| 8748 | "learning_rate": 0.0001935131195335277, |
| 8749 | "loss": 0.0406, |
| 8750 | "step": 12680 |
| 8751 | }, |
| 8752 | { |
| 8753 | "epoch": 18.23, |
| 8754 | "learning_rate": 0.00019342565597667638, |
| 8755 | "loss": 0.0448, |
| 8756 | "step": 12690 |
| 8757 | }, |
| 8758 | { |
| 8759 | "epoch": 18.25, |
| 8760 | "learning_rate": 0.00019333819241982507, |
| 8761 | "loss": 0.0364, |
| 8762 | "step": 12700 |
| 8763 | }, |
| 8764 | { |
| 8765 | "epoch": 18.25, |
| 8766 | "eval_loss": 0.1611556112766266, |
| 8767 | "eval_runtime": 39.9322, |
| 8768 | "eval_samples_per_second": 11.444, |
| 8769 | "eval_steps_per_second": 1.452, |
| 8770 | "eval_wer": 0.1492245143803644, |
| 8771 | "step": 12700 |
| 8772 | }, |
| 8773 | { |
| 8774 | "epoch": 18.26, |
| 8775 | "learning_rate": 0.00019325072886297375, |
| 8776 | "loss": 0.0508, |
| 8777 | "step": 12710 |
| 8778 | }, |
| 8779 | { |
| 8780 | "epoch": 18.28, |
| 8781 | "learning_rate": 0.00019316326530612242, |
| 8782 | "loss": 0.0462, |
| 8783 | "step": 12720 |
| 8784 | }, |
| 8785 | { |
| 8786 | "epoch": 18.29, |
| 8787 | "learning_rate": 0.0001930758017492711, |
| 8788 | "loss": 0.0587, |
| 8789 | "step": 12730 |
| 8790 | }, |
| 8791 | { |
| 8792 | "epoch": 18.3, |
| 8793 | "learning_rate": 0.0001929883381924198, |
| 8794 | "loss": 0.05, |
| 8795 | "step": 12740 |
| 8796 | }, |
| 8797 | { |
| 8798 | "epoch": 18.32, |
| 8799 | "learning_rate": 0.00019290087463556848, |
| 8800 | "loss": 0.0434, |
| 8801 | "step": 12750 |
| 8802 | }, |
| 8803 | { |
| 8804 | "epoch": 18.33, |
| 8805 | "learning_rate": 0.0001928134110787172, |
| 8806 | "loss": 0.0483, |
| 8807 | "step": 12760 |
| 8808 | }, |
| 8809 | { |
| 8810 | "epoch": 18.35, |
| 8811 | "learning_rate": 0.00019272594752186588, |
| 8812 | "loss": 0.0404, |
| 8813 | "step": 12770 |
| 8814 | }, |
| 8815 | { |
| 8816 | "epoch": 18.36, |
| 8817 | "learning_rate": 0.00019263848396501457, |
| 8818 | "loss": 0.0468, |
| 8819 | "step": 12780 |
| 8820 | }, |
| 8821 | { |
| 8822 | "epoch": 18.38, |
| 8823 | "learning_rate": 0.00019255102040816326, |
| 8824 | "loss": 0.0445, |
| 8825 | "step": 12790 |
| 8826 | }, |
| 8827 | { |
| 8828 | "epoch": 18.39, |
| 8829 | "learning_rate": 0.00019246355685131195, |
| 8830 | "loss": 0.0517, |
| 8831 | "step": 12800 |
| 8832 | }, |
| 8833 | { |
| 8834 | "epoch": 18.39, |
| 8835 | "eval_loss": 0.1672176569700241, |
| 8836 | "eval_runtime": 39.9361, |
| 8837 | "eval_samples_per_second": 11.443, |
| 8838 | "eval_steps_per_second": 1.452, |
| 8839 | "eval_wer": 0.1511820508959494, |
| 8840 | "step": 12800 |
| 8841 | }, |
| 8842 | { |
| 8843 | "epoch": 18.41, |
| 8844 | "learning_rate": 0.0001923760932944606, |
| 8845 | "loss": 0.0504, |
| 8846 | "step": 12810 |
| 8847 | }, |
| 8848 | { |
| 8849 | "epoch": 18.42, |
| 8850 | "learning_rate": 0.0001922886297376093, |
| 8851 | "loss": 0.0403, |
| 8852 | "step": 12820 |
| 8853 | }, |
| 8854 | { |
| 8855 | "epoch": 18.43, |
| 8856 | "learning_rate": 0.00019220116618075798, |
| 8857 | "loss": 0.042, |
| 8858 | "step": 12830 |
| 8859 | }, |
| 8860 | { |
| 8861 | "epoch": 18.45, |
| 8862 | "learning_rate": 0.0001921137026239067, |
| 8863 | "loss": 0.0442, |
| 8864 | "step": 12840 |
| 8865 | }, |
| 8866 | { |
| 8867 | "epoch": 18.46, |
| 8868 | "learning_rate": 0.00019202623906705538, |
| 8869 | "loss": 0.0394, |
| 8870 | "step": 12850 |
| 8871 | }, |
| 8872 | { |
| 8873 | "epoch": 18.48, |
| 8874 | "learning_rate": 0.00019193877551020407, |
| 8875 | "loss": 0.0494, |
| 8876 | "step": 12860 |
| 8877 | }, |
| 8878 | { |
| 8879 | "epoch": 18.49, |
| 8880 | "learning_rate": 0.00019185131195335276, |
| 8881 | "loss": 0.0417, |
| 8882 | "step": 12870 |
| 8883 | }, |
| 8884 | { |
| 8885 | "epoch": 18.51, |
| 8886 | "learning_rate": 0.00019176384839650145, |
| 8887 | "loss": 0.0476, |
| 8888 | "step": 12880 |
| 8889 | }, |
| 8890 | { |
| 8891 | "epoch": 18.52, |
| 8892 | "learning_rate": 0.00019167638483965014, |
| 8893 | "loss": 0.0571, |
| 8894 | "step": 12890 |
| 8895 | }, |
| 8896 | { |
| 8897 | "epoch": 18.53, |
| 8898 | "learning_rate": 0.0001915889212827988, |
| 8899 | "loss": 0.0444, |
| 8900 | "step": 12900 |
| 8901 | }, |
| 8902 | { |
| 8903 | "epoch": 18.53, |
| 8904 | "eval_loss": 0.15720723569393158, |
| 8905 | "eval_runtime": 39.8966, |
| 8906 | "eval_samples_per_second": 11.455, |
| 8907 | "eval_steps_per_second": 1.454, |
| 8908 | "eval_wer": 0.15163379009185363, |
| 8909 | "step": 12900 |
| 8910 | }, |
| 8911 | { |
| 8912 | "epoch": 18.55, |
| 8913 | "learning_rate": 0.00019150145772594749, |
| 8914 | "loss": 0.0466, |
| 8915 | "step": 12910 |
| 8916 | }, |
| 8917 | { |
| 8918 | "epoch": 18.56, |
| 8919 | "learning_rate": 0.00019141399416909617, |
| 8920 | "loss": 0.0483, |
| 8921 | "step": 12920 |
| 8922 | }, |
| 8923 | { |
| 8924 | "epoch": 18.58, |
| 8925 | "learning_rate": 0.0001913265306122449, |
| 8926 | "loss": 0.0495, |
| 8927 | "step": 12930 |
| 8928 | }, |
| 8929 | { |
| 8930 | "epoch": 18.59, |
| 8931 | "learning_rate": 0.00019123906705539358, |
| 8932 | "loss": 0.0393, |
| 8933 | "step": 12940 |
| 8934 | }, |
| 8935 | { |
| 8936 | "epoch": 18.61, |
| 8937 | "learning_rate": 0.00019115160349854226, |
| 8938 | "loss": 0.0394, |
| 8939 | "step": 12950 |
| 8940 | }, |
| 8941 | { |
| 8942 | "epoch": 18.62, |
| 8943 | "learning_rate": 0.00019106413994169095, |
| 8944 | "loss": 0.0639, |
| 8945 | "step": 12960 |
| 8946 | }, |
| 8947 | { |
| 8948 | "epoch": 18.64, |
| 8949 | "learning_rate": 0.00019097667638483964, |
| 8950 | "loss": 0.0442, |
| 8951 | "step": 12970 |
| 8952 | }, |
| 8953 | { |
| 8954 | "epoch": 18.65, |
| 8955 | "learning_rate": 0.00019088921282798833, |
| 8956 | "loss": 0.0807, |
| 8957 | "step": 12980 |
| 8958 | }, |
| 8959 | { |
| 8960 | "epoch": 18.66, |
| 8961 | "learning_rate": 0.000190801749271137, |
| 8962 | "loss": 0.0581, |
| 8963 | "step": 12990 |
| 8964 | }, |
| 8965 | { |
| 8966 | "epoch": 18.68, |
| 8967 | "learning_rate": 0.00019071428571428568, |
| 8968 | "loss": 0.0413, |
| 8969 | "step": 13000 |
| 8970 | }, |
| 8971 | { |
| 8972 | "epoch": 18.68, |
| 8973 | "eval_loss": 0.1595200002193451, |
| 8974 | "eval_runtime": 39.866, |
| 8975 | "eval_samples_per_second": 11.463, |
| 8976 | "eval_steps_per_second": 1.455, |
| 8977 | "eval_wer": 0.14877277518446017, |
| 8978 | "step": 13000 |
| 8979 | }, |
| 8980 | { |
| 8981 | "epoch": 18.69, |
| 8982 | "learning_rate": 0.0001906268221574344, |
| 8983 | "loss": 0.0487, |
| 8984 | "step": 13010 |
| 8985 | }, |
| 8986 | { |
| 8987 | "epoch": 18.71, |
| 8988 | "learning_rate": 0.00019053935860058308, |
| 8989 | "loss": 0.0526, |
| 8990 | "step": 13020 |
| 8991 | }, |
| 8992 | { |
| 8993 | "epoch": 18.72, |
| 8994 | "learning_rate": 0.00019045189504373177, |
| 8995 | "loss": 0.0432, |
| 8996 | "step": 13030 |
| 8997 | }, |
| 8998 | { |
| 8999 | "epoch": 18.74, |
| 9000 | "learning_rate": 0.00019036443148688045, |
| 9001 | "loss": 0.0537, |
| 9002 | "step": 13040 |
| 9003 | }, |
| 9004 | { |
| 9005 | "epoch": 18.75, |
| 9006 | "learning_rate": 0.00019027696793002914, |
| 9007 | "loss": 0.0455, |
| 9008 | "step": 13050 |
| 9009 | }, |
| 9010 | { |
| 9011 | "epoch": 18.76, |
| 9012 | "learning_rate": 0.00019018950437317783, |
| 9013 | "loss": 0.051, |
| 9014 | "step": 13060 |
| 9015 | }, |
| 9016 | { |
| 9017 | "epoch": 18.78, |
| 9018 | "learning_rate": 0.00019010204081632652, |
| 9019 | "loss": 0.05, |
| 9020 | "step": 13070 |
| 9021 | }, |
| 9022 | { |
| 9023 | "epoch": 18.79, |
| 9024 | "learning_rate": 0.00019001457725947518, |
| 9025 | "loss": 0.0452, |
| 9026 | "step": 13080 |
| 9027 | }, |
| 9028 | { |
| 9029 | "epoch": 18.81, |
| 9030 | "learning_rate": 0.00018992711370262387, |
| 9031 | "loss": 0.0445, |
| 9032 | "step": 13090 |
| 9033 | }, |
| 9034 | { |
| 9035 | "epoch": 18.82, |
| 9036 | "learning_rate": 0.00018983965014577258, |
| 9037 | "loss": 0.0621, |
| 9038 | "step": 13100 |
| 9039 | }, |
| 9040 | { |
| 9041 | "epoch": 18.82, |
| 9042 | "eval_loss": 0.15519918501377106, |
| 9043 | "eval_runtime": 40.5387, |
| 9044 | "eval_samples_per_second": 11.273, |
| 9045 | "eval_steps_per_second": 1.431, |
| 9046 | "eval_wer": 0.14817045625658787, |
| 9047 | "step": 13100 |
| 9048 | }, |
| 9049 | { |
| 9050 | "epoch": 18.84, |
| 9051 | "learning_rate": 0.00018975218658892127, |
| 9052 | "loss": 0.0501, |
| 9053 | "step": 13110 |
| 9054 | }, |
| 9055 | { |
| 9056 | "epoch": 18.85, |
| 9057 | "learning_rate": 0.00018966472303206996, |
| 9058 | "loss": 0.049, |
| 9059 | "step": 13120 |
| 9060 | }, |
| 9061 | { |
| 9062 | "epoch": 18.86, |
| 9063 | "learning_rate": 0.00018957725947521865, |
| 9064 | "loss": 0.039, |
| 9065 | "step": 13130 |
| 9066 | }, |
| 9067 | { |
| 9068 | "epoch": 18.88, |
| 9069 | "learning_rate": 0.00018948979591836733, |
| 9070 | "loss": 0.0542, |
| 9071 | "step": 13140 |
| 9072 | }, |
| 9073 | { |
| 9074 | "epoch": 18.89, |
| 9075 | "learning_rate": 0.00018940233236151602, |
| 9076 | "loss": 0.0485, |
| 9077 | "step": 13150 |
| 9078 | }, |
| 9079 | { |
| 9080 | "epoch": 18.91, |
| 9081 | "learning_rate": 0.0001893148688046647, |
| 9082 | "loss": 0.0452, |
| 9083 | "step": 13160 |
| 9084 | }, |
| 9085 | { |
| 9086 | "epoch": 18.92, |
| 9087 | "learning_rate": 0.00018922740524781337, |
| 9088 | "loss": 0.0457, |
| 9089 | "step": 13170 |
| 9090 | }, |
| 9091 | { |
| 9092 | "epoch": 18.94, |
| 9093 | "learning_rate": 0.00018913994169096206, |
| 9094 | "loss": 0.0465, |
| 9095 | "step": 13180 |
| 9096 | }, |
| 9097 | { |
| 9098 | "epoch": 18.95, |
| 9099 | "learning_rate": 0.00018905247813411077, |
| 9100 | "loss": 0.0556, |
| 9101 | "step": 13190 |
| 9102 | }, |
| 9103 | { |
| 9104 | "epoch": 18.97, |
| 9105 | "learning_rate": 0.00018896501457725946, |
| 9106 | "loss": 0.04, |
| 9107 | "step": 13200 |
| 9108 | }, |
| 9109 | { |
| 9110 | "epoch": 18.97, |
| 9111 | "eval_loss": 0.15459690988063812, |
| 9112 | "eval_runtime": 39.9064, |
| 9113 | "eval_samples_per_second": 11.452, |
| 9114 | "eval_steps_per_second": 1.453, |
| 9115 | "eval_wer": 0.14696581840084325, |
| 9116 | "step": 13200 |
| 9117 | }, |
| 9118 | { |
| 9119 | "epoch": 18.98, |
| 9120 | "learning_rate": 0.00018887755102040815, |
| 9121 | "loss": 0.0382, |
| 9122 | "step": 13210 |
| 9123 | }, |
| 9124 | { |
| 9125 | "epoch": 18.99, |
| 9126 | "learning_rate": 0.00018879008746355684, |
| 9127 | "loss": 0.0354, |
| 9128 | "step": 13220 |
| 9129 | }, |
| 9130 | { |
| 9131 | "epoch": 19.01, |
| 9132 | "learning_rate": 0.00018870262390670553, |
| 9133 | "loss": 0.0414, |
| 9134 | "step": 13230 |
| 9135 | }, |
| 9136 | { |
| 9137 | "epoch": 19.02, |
| 9138 | "learning_rate": 0.0001886151603498542, |
| 9139 | "loss": 0.0463, |
| 9140 | "step": 13240 |
| 9141 | }, |
| 9142 | { |
| 9143 | "epoch": 19.04, |
| 9144 | "learning_rate": 0.0001885276967930029, |
| 9145 | "loss": 0.0497, |
| 9146 | "step": 13250 |
| 9147 | }, |
| 9148 | { |
| 9149 | "epoch": 19.05, |
| 9150 | "learning_rate": 0.00018844023323615156, |
| 9151 | "loss": 0.0504, |
| 9152 | "step": 13260 |
| 9153 | }, |
| 9154 | { |
| 9155 | "epoch": 19.07, |
| 9156 | "learning_rate": 0.00018835276967930028, |
| 9157 | "loss": 0.0424, |
| 9158 | "step": 13270 |
| 9159 | }, |
| 9160 | { |
| 9161 | "epoch": 19.08, |
| 9162 | "learning_rate": 0.00018826530612244896, |
| 9163 | "loss": 0.0491, |
| 9164 | "step": 13280 |
| 9165 | }, |
| 9166 | { |
| 9167 | "epoch": 19.09, |
| 9168 | "learning_rate": 0.00018817784256559765, |
| 9169 | "loss": 0.0485, |
| 9170 | "step": 13290 |
| 9171 | }, |
| 9172 | { |
| 9173 | "epoch": 19.11, |
| 9174 | "learning_rate": 0.00018809037900874634, |
| 9175 | "loss": 0.0394, |
| 9176 | "step": 13300 |
| 9177 | }, |
| 9178 | { |
| 9179 | "epoch": 19.11, |
| 9180 | "eval_loss": 0.16309237480163574, |
| 9181 | "eval_runtime": 39.9257, |
| 9182 | "eval_samples_per_second": 11.446, |
| 9183 | "eval_steps_per_second": 1.453, |
| 9184 | "eval_wer": 0.15283842794759825, |
| 9185 | "step": 13300 |
| 9186 | }, |
| 9187 | { |
| 9188 | "epoch": 19.12, |
| 9189 | "learning_rate": 0.00018800291545189503, |
| 9190 | "loss": 0.0537, |
| 9191 | "step": 13310 |
| 9192 | }, |
| 9193 | { |
| 9194 | "epoch": 19.14, |
| 9195 | "learning_rate": 0.00018791545189504372, |
| 9196 | "loss": 0.0444, |
| 9197 | "step": 13320 |
| 9198 | }, |
| 9199 | { |
| 9200 | "epoch": 19.15, |
| 9201 | "learning_rate": 0.0001878279883381924, |
| 9202 | "loss": 0.0577, |
| 9203 | "step": 13330 |
| 9204 | }, |
| 9205 | { |
| 9206 | "epoch": 19.17, |
| 9207 | "learning_rate": 0.00018774052478134112, |
| 9208 | "loss": 0.056, |
| 9209 | "step": 13340 |
| 9210 | }, |
| 9211 | { |
| 9212 | "epoch": 19.18, |
| 9213 | "learning_rate": 0.00018765306122448975, |
| 9214 | "loss": 0.0365, |
| 9215 | "step": 13350 |
| 9216 | }, |
| 9217 | { |
| 9218 | "epoch": 19.2, |
| 9219 | "learning_rate": 0.00018756559766763847, |
| 9220 | "loss": 0.048, |
| 9221 | "step": 13360 |
| 9222 | }, |
| 9223 | { |
| 9224 | "epoch": 19.21, |
| 9225 | "learning_rate": 0.00018747813411078716, |
| 9226 | "loss": 0.0582, |
| 9227 | "step": 13370 |
| 9228 | }, |
| 9229 | { |
| 9230 | "epoch": 19.22, |
| 9231 | "learning_rate": 0.00018739067055393584, |
| 9232 | "loss": 0.056, |
| 9233 | "step": 13380 |
| 9234 | }, |
| 9235 | { |
| 9236 | "epoch": 19.24, |
| 9237 | "learning_rate": 0.00018730320699708453, |
| 9238 | "loss": 0.0473, |
| 9239 | "step": 13390 |
| 9240 | }, |
| 9241 | { |
| 9242 | "epoch": 19.25, |
| 9243 | "learning_rate": 0.00018721574344023322, |
| 9244 | "loss": 0.0465, |
| 9245 | "step": 13400 |
| 9246 | }, |
| 9247 | { |
| 9248 | "epoch": 19.25, |
| 9249 | "eval_loss": 0.16543611884117126, |
| 9250 | "eval_runtime": 40.0496, |
| 9251 | "eval_samples_per_second": 11.411, |
| 9252 | "eval_steps_per_second": 1.448, |
| 9253 | "eval_wer": 0.14967625357626863, |
| 9254 | "step": 13400 |
| 9255 | }, |
| 9256 | { |
| 9257 | "epoch": 19.27, |
| 9258 | "learning_rate": 0.0001871282798833819, |
| 9259 | "loss": 0.0526, |
| 9260 | "step": 13410 |
| 9261 | }, |
| 9262 | { |
| 9263 | "epoch": 19.28, |
| 9264 | "learning_rate": 0.0001870408163265306, |
| 9265 | "loss": 0.0448, |
| 9266 | "step": 13420 |
| 9267 | }, |
| 9268 | { |
| 9269 | "epoch": 19.3, |
| 9270 | "learning_rate": 0.0001869533527696793, |
| 9271 | "loss": 0.0571, |
| 9272 | "step": 13430 |
| 9273 | }, |
| 9274 | { |
| 9275 | "epoch": 19.31, |
| 9276 | "learning_rate": 0.00018686588921282794, |
| 9277 | "loss": 0.0514, |
| 9278 | "step": 13440 |
| 9279 | }, |
| 9280 | { |
| 9281 | "epoch": 19.32, |
| 9282 | "learning_rate": 0.00018677842565597666, |
| 9283 | "loss": 0.0644, |
| 9284 | "step": 13450 |
| 9285 | }, |
| 9286 | { |
| 9287 | "epoch": 19.34, |
| 9288 | "learning_rate": 0.00018669096209912535, |
| 9289 | "loss": 0.0626, |
| 9290 | "step": 13460 |
| 9291 | }, |
| 9292 | { |
| 9293 | "epoch": 19.35, |
| 9294 | "learning_rate": 0.00018660349854227403, |
| 9295 | "loss": 0.0391, |
| 9296 | "step": 13470 |
| 9297 | }, |
| 9298 | { |
| 9299 | "epoch": 19.37, |
| 9300 | "learning_rate": 0.00018651603498542272, |
| 9301 | "loss": 0.0568, |
| 9302 | "step": 13480 |
| 9303 | }, |
| 9304 | { |
| 9305 | "epoch": 19.38, |
| 9306 | "learning_rate": 0.0001864285714285714, |
| 9307 | "loss": 0.0375, |
| 9308 | "step": 13490 |
| 9309 | }, |
| 9310 | { |
| 9311 | "epoch": 19.4, |
| 9312 | "learning_rate": 0.0001863411078717201, |
| 9313 | "loss": 0.0529, |
| 9314 | "step": 13500 |
| 9315 | }, |
| 9316 | { |
| 9317 | "epoch": 19.4, |
| 9318 | "eval_loss": 0.16998930275440216, |
| 9319 | "eval_runtime": 40.128, |
| 9320 | "eval_samples_per_second": 11.389, |
| 9321 | "eval_steps_per_second": 1.445, |
| 9322 | "eval_wer": 0.15268784821563017, |
| 9323 | "step": 13500 |
| 9324 | }, |
| 9325 | { |
| 9326 | "epoch": 19.41, |
| 9327 | "learning_rate": 0.00018625364431486879, |
| 9328 | "loss": 0.0572, |
| 9329 | "step": 13510 |
| 9330 | }, |
| 9331 | { |
| 9332 | "epoch": 19.43, |
| 9333 | "learning_rate": 0.0001861661807580175, |
| 9334 | "loss": 0.0376, |
| 9335 | "step": 13520 |
| 9336 | }, |
| 9337 | { |
| 9338 | "epoch": 19.44, |
| 9339 | "learning_rate": 0.00018607871720116616, |
| 9340 | "loss": 0.0473, |
| 9341 | "step": 13530 |
| 9342 | }, |
| 9343 | { |
| 9344 | "epoch": 19.45, |
| 9345 | "learning_rate": 0.00018599125364431485, |
| 9346 | "loss": 0.0473, |
| 9347 | "step": 13540 |
| 9348 | }, |
| 9349 | { |
| 9350 | "epoch": 19.47, |
| 9351 | "learning_rate": 0.00018590379008746354, |
| 9352 | "loss": 0.0561, |
| 9353 | "step": 13550 |
| 9354 | }, |
| 9355 | { |
| 9356 | "epoch": 19.48, |
| 9357 | "learning_rate": 0.00018581632653061223, |
| 9358 | "loss": 0.0615, |
| 9359 | "step": 13560 |
| 9360 | }, |
| 9361 | { |
| 9362 | "epoch": 19.5, |
| 9363 | "learning_rate": 0.0001857288629737609, |
| 9364 | "loss": 0.0379, |
| 9365 | "step": 13570 |
| 9366 | }, |
| 9367 | { |
| 9368 | "epoch": 19.51, |
| 9369 | "learning_rate": 0.0001856413994169096, |
| 9370 | "loss": 0.0445, |
| 9371 | "step": 13580 |
| 9372 | }, |
| 9373 | { |
| 9374 | "epoch": 19.53, |
| 9375 | "learning_rate": 0.0001855539358600583, |
| 9376 | "loss": 0.0518, |
| 9377 | "step": 13590 |
| 9378 | }, |
| 9379 | { |
| 9380 | "epoch": 19.54, |
| 9381 | "learning_rate": 0.000185466472303207, |
| 9382 | "loss": 0.0432, |
| 9383 | "step": 13600 |
| 9384 | }, |
| 9385 | { |
| 9386 | "epoch": 19.54, |
| 9387 | "eval_loss": 0.15767106413841248, |
| 9388 | "eval_runtime": 39.8653, |
| 9389 | "eval_samples_per_second": 11.464, |
| 9390 | "eval_steps_per_second": 1.455, |
| 9391 | "eval_wer": 0.14696581840084325, |
| 9392 | "step": 13600 |
| 9393 | }, |
| 9394 | { |
| 9395 | "epoch": 19.55, |
| 9396 | "learning_rate": 0.0001853790087463557, |
| 9397 | "loss": 0.0629, |
| 9398 | "step": 13610 |
| 9399 | }, |
| 9400 | { |
| 9401 | "epoch": 19.57, |
| 9402 | "learning_rate": 0.00018529154518950435, |
| 9403 | "loss": 0.0393, |
| 9404 | "step": 13620 |
| 9405 | }, |
| 9406 | { |
| 9407 | "epoch": 19.58, |
| 9408 | "learning_rate": 0.00018520408163265304, |
| 9409 | "loss": 0.0519, |
| 9410 | "step": 13630 |
| 9411 | }, |
| 9412 | { |
| 9413 | "epoch": 19.6, |
| 9414 | "learning_rate": 0.00018511661807580173, |
| 9415 | "loss": 0.0367, |
| 9416 | "step": 13640 |
| 9417 | }, |
| 9418 | { |
| 9419 | "epoch": 19.61, |
| 9420 | "learning_rate": 0.00018502915451895042, |
| 9421 | "loss": 0.0431, |
| 9422 | "step": 13650 |
| 9423 | }, |
| 9424 | { |
| 9425 | "epoch": 19.63, |
| 9426 | "learning_rate": 0.0001849416909620991, |
| 9427 | "loss": 0.0576, |
| 9428 | "step": 13660 |
| 9429 | }, |
| 9430 | { |
| 9431 | "epoch": 19.64, |
| 9432 | "learning_rate": 0.0001848542274052478, |
| 9433 | "loss": 0.0461, |
| 9434 | "step": 13670 |
| 9435 | }, |
| 9436 | { |
| 9437 | "epoch": 19.66, |
| 9438 | "learning_rate": 0.00018476676384839648, |
| 9439 | "loss": 0.045, |
| 9440 | "step": 13680 |
| 9441 | }, |
| 9442 | { |
| 9443 | "epoch": 19.67, |
| 9444 | "learning_rate": 0.0001846793002915452, |
| 9445 | "loss": 0.0508, |
| 9446 | "step": 13690 |
| 9447 | }, |
| 9448 | { |
| 9449 | "epoch": 19.68, |
| 9450 | "learning_rate": 0.00018459183673469388, |
| 9451 | "loss": 0.0459, |
| 9452 | "step": 13700 |
| 9453 | }, |
| 9454 | { |
| 9455 | "epoch": 19.68, |
| 9456 | "eval_loss": 0.158447265625, |
| 9457 | "eval_runtime": 40.1118, |
| 9458 | "eval_samples_per_second": 11.393, |
| 9459 | "eval_steps_per_second": 1.446, |
| 9460 | "eval_wer": 0.1525372684836621, |
| 9461 | "step": 13700 |
| 9462 | }, |
| 9463 | { |
| 9464 | "epoch": 19.7, |
| 9465 | "learning_rate": 0.00018450437317784254, |
| 9466 | "loss": 0.057, |
| 9467 | "step": 13710 |
| 9468 | }, |
| 9469 | { |
| 9470 | "epoch": 19.71, |
| 9471 | "learning_rate": 0.00018441690962099123, |
| 9472 | "loss": 0.0471, |
| 9473 | "step": 13720 |
| 9474 | }, |
| 9475 | { |
| 9476 | "epoch": 19.73, |
| 9477 | "learning_rate": 0.00018432944606413992, |
| 9478 | "loss": 0.0489, |
| 9479 | "step": 13730 |
| 9480 | }, |
| 9481 | { |
| 9482 | "epoch": 19.74, |
| 9483 | "learning_rate": 0.0001842419825072886, |
| 9484 | "loss": 0.0507, |
| 9485 | "step": 13740 |
| 9486 | }, |
| 9487 | { |
| 9488 | "epoch": 19.76, |
| 9489 | "learning_rate": 0.0001841545189504373, |
| 9490 | "loss": 0.0386, |
| 9491 | "step": 13750 |
| 9492 | }, |
| 9493 | { |
| 9494 | "epoch": 19.77, |
| 9495 | "learning_rate": 0.00018406705539358598, |
| 9496 | "loss": 0.0393, |
| 9497 | "step": 13760 |
| 9498 | }, |
| 9499 | { |
| 9500 | "epoch": 19.78, |
| 9501 | "learning_rate": 0.0001839795918367347, |
| 9502 | "loss": 0.0411, |
| 9503 | "step": 13770 |
| 9504 | }, |
| 9505 | { |
| 9506 | "epoch": 19.8, |
| 9507 | "learning_rate": 0.00018389212827988339, |
| 9508 | "loss": 0.056, |
| 9509 | "step": 13780 |
| 9510 | }, |
| 9511 | { |
| 9512 | "epoch": 19.81, |
| 9513 | "learning_rate": 0.00018380466472303207, |
| 9514 | "loss": 0.0394, |
| 9515 | "step": 13790 |
| 9516 | }, |
| 9517 | { |
| 9518 | "epoch": 19.83, |
| 9519 | "learning_rate": 0.00018371720116618074, |
| 9520 | "loss": 0.0529, |
| 9521 | "step": 13800 |
| 9522 | }, |
| 9523 | { |
| 9524 | "epoch": 19.83, |
| 9525 | "eval_loss": 0.1573006957769394, |
| 9526 | "eval_runtime": 39.8821, |
| 9527 | "eval_samples_per_second": 11.459, |
| 9528 | "eval_steps_per_second": 1.454, |
| 9529 | "eval_wer": 0.14967625357626863, |
| 9530 | "step": 13800 |
| 9531 | }, |
| 9532 | { |
| 9533 | "epoch": 19.84, |
| 9534 | "learning_rate": 0.00018362973760932942, |
| 9535 | "loss": 0.0512, |
| 9536 | "step": 13810 |
| 9537 | }, |
| 9538 | { |
| 9539 | "epoch": 19.86, |
| 9540 | "learning_rate": 0.0001835422740524781, |
| 9541 | "loss": 0.05, |
| 9542 | "step": 13820 |
| 9543 | }, |
| 9544 | { |
| 9545 | "epoch": 19.87, |
| 9546 | "learning_rate": 0.0001834548104956268, |
| 9547 | "loss": 0.0485, |
| 9548 | "step": 13830 |
| 9549 | }, |
| 9550 | { |
| 9551 | "epoch": 19.89, |
| 9552 | "learning_rate": 0.0001833673469387755, |
| 9553 | "loss": 0.0368, |
| 9554 | "step": 13840 |
| 9555 | }, |
| 9556 | { |
| 9557 | "epoch": 19.9, |
| 9558 | "learning_rate": 0.00018327988338192417, |
| 9559 | "loss": 0.0512, |
| 9560 | "step": 13850 |
| 9561 | }, |
| 9562 | { |
| 9563 | "epoch": 19.91, |
| 9564 | "learning_rate": 0.0001831924198250729, |
| 9565 | "loss": 0.05, |
| 9566 | "step": 13860 |
| 9567 | }, |
| 9568 | { |
| 9569 | "epoch": 19.93, |
| 9570 | "learning_rate": 0.00018310495626822158, |
| 9571 | "loss": 0.0443, |
| 9572 | "step": 13870 |
| 9573 | }, |
| 9574 | { |
| 9575 | "epoch": 19.94, |
| 9576 | "learning_rate": 0.00018301749271137027, |
| 9577 | "loss": 0.0381, |
| 9578 | "step": 13880 |
| 9579 | }, |
| 9580 | { |
| 9581 | "epoch": 19.96, |
| 9582 | "learning_rate": 0.00018293002915451893, |
| 9583 | "loss": 0.0396, |
| 9584 | "step": 13890 |
| 9585 | }, |
| 9586 | { |
| 9587 | "epoch": 19.97, |
| 9588 | "learning_rate": 0.00018284256559766761, |
| 9589 | "loss": 0.0467, |
| 9590 | "step": 13900 |
| 9591 | }, |
| 9592 | { |
| 9593 | "epoch": 19.97, |
| 9594 | "eval_loss": 0.1563096046447754, |
| 9595 | "eval_runtime": 39.8443, |
| 9596 | "eval_samples_per_second": 11.47, |
| 9597 | "eval_steps_per_second": 1.456, |
| 9598 | "eval_wer": 0.15208552928775787, |
| 9599 | "step": 13900 |
| 9600 | }, |
| 9601 | { |
| 9602 | "epoch": 19.99, |
| 9603 | "learning_rate": 0.0001827551020408163, |
| 9604 | "loss": 0.0617, |
| 9605 | "step": 13910 |
| 9606 | }, |
| 9607 | { |
| 9608 | "epoch": 20.0, |
| 9609 | "learning_rate": 0.000182667638483965, |
| 9610 | "loss": 0.0334, |
| 9611 | "step": 13920 |
| 9612 | }, |
| 9613 | { |
| 9614 | "epoch": 20.01, |
| 9615 | "learning_rate": 0.00018258017492711368, |
| 9616 | "loss": 0.0511, |
| 9617 | "step": 13930 |
| 9618 | }, |
| 9619 | { |
| 9620 | "epoch": 20.03, |
| 9621 | "learning_rate": 0.00018249271137026237, |
| 9622 | "loss": 0.0419, |
| 9623 | "step": 13940 |
| 9624 | }, |
| 9625 | { |
| 9626 | "epoch": 20.04, |
| 9627 | "learning_rate": 0.00018240524781341108, |
| 9628 | "loss": 0.0376, |
| 9629 | "step": 13950 |
| 9630 | }, |
| 9631 | { |
| 9632 | "epoch": 20.06, |
| 9633 | "learning_rate": 0.00018231778425655977, |
| 9634 | "loss": 0.0431, |
| 9635 | "step": 13960 |
| 9636 | }, |
| 9637 | { |
| 9638 | "epoch": 20.07, |
| 9639 | "learning_rate": 0.00018223032069970846, |
| 9640 | "loss": 0.0356, |
| 9641 | "step": 13970 |
| 9642 | }, |
| 9643 | { |
| 9644 | "epoch": 20.09, |
| 9645 | "learning_rate": 0.00018214285714285712, |
| 9646 | "loss": 0.0566, |
| 9647 | "step": 13980 |
| 9648 | }, |
| 9649 | { |
| 9650 | "epoch": 20.1, |
| 9651 | "learning_rate": 0.0001820553935860058, |
| 9652 | "loss": 0.0478, |
| 9653 | "step": 13990 |
| 9654 | }, |
| 9655 | { |
| 9656 | "epoch": 20.11, |
| 9657 | "learning_rate": 0.0001819679300291545, |
| 9658 | "loss": 0.0516, |
| 9659 | "step": 14000 |
| 9660 | }, |
| 9661 | { |
| 9662 | "epoch": 20.11, |
| 9663 | "eval_loss": 0.15548963844776154, |
| 9664 | "eval_runtime": 40.0025, |
| 9665 | "eval_samples_per_second": 11.424, |
| 9666 | "eval_steps_per_second": 1.45, |
| 9667 | "eval_wer": 0.15268784821563017, |
| 9668 | "step": 14000 |
| 9669 | }, |
| 9670 | { |
| 9671 | "epoch": 20.13, |
| 9672 | "learning_rate": 0.00018188046647230318, |
| 9673 | "loss": 0.0554, |
| 9674 | "step": 14010 |
| 9675 | }, |
| 9676 | { |
| 9677 | "epoch": 20.14, |
| 9678 | "learning_rate": 0.00018179300291545187, |
| 9679 | "loss": 0.0498, |
| 9680 | "step": 14020 |
| 9681 | }, |
| 9682 | { |
| 9683 | "epoch": 20.16, |
| 9684 | "learning_rate": 0.00018170553935860058, |
| 9685 | "loss": 0.0542, |
| 9686 | "step": 14030 |
| 9687 | }, |
| 9688 | { |
| 9689 | "epoch": 20.17, |
| 9690 | "learning_rate": 0.00018161807580174927, |
| 9691 | "loss": 0.043, |
| 9692 | "step": 14040 |
| 9693 | }, |
| 9694 | { |
| 9695 | "epoch": 20.19, |
| 9696 | "learning_rate": 0.00018153061224489796, |
| 9697 | "loss": 0.0511, |
| 9698 | "step": 14050 |
| 9699 | }, |
| 9700 | { |
| 9701 | "epoch": 20.2, |
| 9702 | "learning_rate": 0.00018144314868804665, |
| 9703 | "loss": 0.0495, |
| 9704 | "step": 14060 |
| 9705 | }, |
| 9706 | { |
| 9707 | "epoch": 20.22, |
| 9708 | "learning_rate": 0.0001813556851311953, |
| 9709 | "loss": 0.0342, |
| 9710 | "step": 14070 |
| 9711 | }, |
| 9712 | { |
| 9713 | "epoch": 20.23, |
| 9714 | "learning_rate": 0.000181268221574344, |
| 9715 | "loss": 0.056, |
| 9716 | "step": 14080 |
| 9717 | }, |
| 9718 | { |
| 9719 | "epoch": 20.24, |
| 9720 | "learning_rate": 0.00018118075801749268, |
| 9721 | "loss": 0.0438, |
| 9722 | "step": 14090 |
| 9723 | }, |
| 9724 | { |
| 9725 | "epoch": 20.26, |
| 9726 | "learning_rate": 0.00018109329446064137, |
| 9727 | "loss": 0.0506, |
| 9728 | "step": 14100 |
| 9729 | }, |
| 9730 | { |
| 9731 | "epoch": 20.26, |
| 9732 | "eval_loss": 0.15269336104393005, |
| 9733 | "eval_runtime": 39.9095, |
| 9734 | "eval_samples_per_second": 11.451, |
| 9735 | "eval_steps_per_second": 1.453, |
| 9736 | "eval_wer": 0.14681523866887516, |
| 9737 | "step": 14100 |
| 9738 | }, |
| 9739 | { |
| 9740 | "epoch": 20.27, |
| 9741 | "learning_rate": 0.00018100583090379006, |
| 9742 | "loss": 0.0443, |
| 9743 | "step": 14110 |
| 9744 | }, |
| 9745 | { |
| 9746 | "epoch": 20.29, |
| 9747 | "learning_rate": 0.00018091836734693877, |
| 9748 | "loss": 0.04, |
| 9749 | "step": 14120 |
| 9750 | }, |
| 9751 | { |
| 9752 | "epoch": 20.3, |
| 9753 | "learning_rate": 0.00018083090379008746, |
| 9754 | "loss": 0.046, |
| 9755 | "step": 14130 |
| 9756 | }, |
| 9757 | { |
| 9758 | "epoch": 20.32, |
| 9759 | "learning_rate": 0.00018074344023323615, |
| 9760 | "loss": 0.0455, |
| 9761 | "step": 14140 |
| 9762 | }, |
| 9763 | { |
| 9764 | "epoch": 20.33, |
| 9765 | "learning_rate": 0.00018065597667638484, |
| 9766 | "loss": 0.0471, |
| 9767 | "step": 14150 |
| 9768 | }, |
| 9769 | { |
| 9770 | "epoch": 20.34, |
| 9771 | "learning_rate": 0.0001805685131195335, |
| 9772 | "loss": 0.0436, |
| 9773 | "step": 14160 |
| 9774 | }, |
| 9775 | { |
| 9776 | "epoch": 20.36, |
| 9777 | "learning_rate": 0.0001804810495626822, |
| 9778 | "loss": 0.0417, |
| 9779 | "step": 14170 |
| 9780 | }, |
| 9781 | { |
| 9782 | "epoch": 20.37, |
| 9783 | "learning_rate": 0.00018039358600583088, |
| 9784 | "loss": 0.0517, |
| 9785 | "step": 14180 |
| 9786 | }, |
| 9787 | { |
| 9788 | "epoch": 20.39, |
| 9789 | "learning_rate": 0.00018030612244897956, |
| 9790 | "loss": 0.0492, |
| 9791 | "step": 14190 |
| 9792 | }, |
| 9793 | { |
| 9794 | "epoch": 20.4, |
| 9795 | "learning_rate": 0.00018021865889212828, |
| 9796 | "loss": 0.0445, |
| 9797 | "step": 14200 |
| 9798 | }, |
| 9799 | { |
| 9800 | "epoch": 20.4, |
| 9801 | "eval_loss": 0.15262174606323242, |
| 9802 | "eval_runtime": 40.2286, |
| 9803 | "eval_samples_per_second": 11.36, |
| 9804 | "eval_steps_per_second": 1.442, |
| 9805 | "eval_wer": 0.15027857250414095, |
| 9806 | "step": 14200 |
| 9807 | }, |
| 9808 | { |
| 9809 | "epoch": 20.42, |
| 9810 | "learning_rate": 0.00018013119533527697, |
| 9811 | "loss": 0.0505, |
| 9812 | "step": 14210 |
| 9813 | }, |
| 9814 | { |
| 9815 | "epoch": 20.43, |
| 9816 | "learning_rate": 0.00018004373177842565, |
| 9817 | "loss": 0.0436, |
| 9818 | "step": 14220 |
| 9819 | }, |
| 9820 | { |
| 9821 | "epoch": 20.45, |
| 9822 | "learning_rate": 0.00017995626822157434, |
| 9823 | "loss": 0.046, |
| 9824 | "step": 14230 |
| 9825 | }, |
| 9826 | { |
| 9827 | "epoch": 20.46, |
| 9828 | "learning_rate": 0.00017986880466472303, |
| 9829 | "loss": 0.0341, |
| 9830 | "step": 14240 |
| 9831 | }, |
| 9832 | { |
| 9833 | "epoch": 20.47, |
| 9834 | "learning_rate": 0.0001797813411078717, |
| 9835 | "loss": 0.0454, |
| 9836 | "step": 14250 |
| 9837 | }, |
| 9838 | { |
| 9839 | "epoch": 20.49, |
| 9840 | "learning_rate": 0.00017969387755102038, |
| 9841 | "loss": 0.046, |
| 9842 | "step": 14260 |
| 9843 | }, |
| 9844 | { |
| 9845 | "epoch": 20.5, |
| 9846 | "learning_rate": 0.00017960641399416907, |
| 9847 | "loss": 0.0421, |
| 9848 | "step": 14270 |
| 9849 | }, |
| 9850 | { |
| 9851 | "epoch": 20.52, |
| 9852 | "learning_rate": 0.00017951895043731775, |
| 9853 | "loss": 0.048, |
| 9854 | "step": 14280 |
| 9855 | }, |
| 9856 | { |
| 9857 | "epoch": 20.53, |
| 9858 | "learning_rate": 0.00017943148688046647, |
| 9859 | "loss": 0.0355, |
| 9860 | "step": 14290 |
| 9861 | }, |
| 9862 | { |
| 9863 | "epoch": 20.55, |
| 9864 | "learning_rate": 0.00017934402332361516, |
| 9865 | "loss": 0.0467, |
| 9866 | "step": 14300 |
| 9867 | }, |
| 9868 | { |
| 9869 | "epoch": 20.55, |
| 9870 | "eval_loss": 0.14778903126716614, |
| 9871 | "eval_runtime": 40.0483, |
| 9872 | "eval_samples_per_second": 11.411, |
| 9873 | "eval_steps_per_second": 1.448, |
| 9874 | "eval_wer": 0.14907393464839633, |
| 9875 | "step": 14300 |
| 9876 | }, |
| 9877 | { |
| 9878 | "epoch": 20.56, |
| 9879 | "learning_rate": 0.00017925655976676384, |
| 9880 | "loss": 0.0495, |
| 9881 | "step": 14310 |
| 9882 | }, |
| 9883 | { |
| 9884 | "epoch": 20.57, |
| 9885 | "learning_rate": 0.00017916909620991253, |
| 9886 | "loss": 0.0415, |
| 9887 | "step": 14320 |
| 9888 | }, |
| 9889 | { |
| 9890 | "epoch": 20.59, |
| 9891 | "learning_rate": 0.00017908163265306122, |
| 9892 | "loss": 0.0429, |
| 9893 | "step": 14330 |
| 9894 | }, |
| 9895 | { |
| 9896 | "epoch": 20.6, |
| 9897 | "learning_rate": 0.00017899416909620988, |
| 9898 | "loss": 0.0447, |
| 9899 | "step": 14340 |
| 9900 | }, |
| 9901 | { |
| 9902 | "epoch": 20.62, |
| 9903 | "learning_rate": 0.00017890670553935857, |
| 9904 | "loss": 0.0496, |
| 9905 | "step": 14350 |
| 9906 | }, |
| 9907 | { |
| 9908 | "epoch": 20.63, |
| 9909 | "learning_rate": 0.00017881924198250726, |
| 9910 | "loss": 0.0504, |
| 9911 | "step": 14360 |
| 9912 | }, |
| 9913 | { |
| 9914 | "epoch": 20.65, |
| 9915 | "learning_rate": 0.00017873177842565595, |
| 9916 | "loss": 0.053, |
| 9917 | "step": 14370 |
| 9918 | }, |
| 9919 | { |
| 9920 | "epoch": 20.66, |
| 9921 | "learning_rate": 0.00017864431486880466, |
| 9922 | "loss": 0.0482, |
| 9923 | "step": 14380 |
| 9924 | }, |
| 9925 | { |
| 9926 | "epoch": 20.68, |
| 9927 | "learning_rate": 0.00017855685131195335, |
| 9928 | "loss": 0.0393, |
| 9929 | "step": 14390 |
| 9930 | }, |
| 9931 | { |
| 9932 | "epoch": 20.69, |
| 9933 | "learning_rate": 0.00017846938775510204, |
| 9934 | "loss": 0.0475, |
| 9935 | "step": 14400 |
| 9936 | }, |
| 9937 | { |
| 9938 | "epoch": 20.69, |
| 9939 | "eval_loss": 0.1577850878238678, |
| 9940 | "eval_runtime": 40.5152, |
| 9941 | "eval_samples_per_second": 11.28, |
| 9942 | "eval_steps_per_second": 1.432, |
| 9943 | "eval_wer": 0.15057973196807709, |
| 9944 | "step": 14400 |
| 9945 | }, |
| 9946 | { |
| 9947 | "epoch": 20.7, |
| 9948 | "learning_rate": 0.00017838192419825072, |
| 9949 | "loss": 0.0475, |
| 9950 | "step": 14410 |
| 9951 | }, |
| 9952 | { |
| 9953 | "epoch": 20.72, |
| 9954 | "learning_rate": 0.0001782944606413994, |
| 9955 | "loss": 0.04, |
| 9956 | "step": 14420 |
| 9957 | }, |
| 9958 | { |
| 9959 | "epoch": 20.73, |
| 9960 | "learning_rate": 0.00017820699708454807, |
| 9961 | "loss": 0.0525, |
| 9962 | "step": 14430 |
| 9963 | }, |
| 9964 | { |
| 9965 | "epoch": 20.75, |
| 9966 | "learning_rate": 0.00017811953352769676, |
| 9967 | "loss": 0.0412, |
| 9968 | "step": 14440 |
| 9969 | }, |
| 9970 | { |
| 9971 | "epoch": 20.76, |
| 9972 | "learning_rate": 0.00017803206997084545, |
| 9973 | "loss": 0.0376, |
| 9974 | "step": 14450 |
| 9975 | }, |
| 9976 | { |
| 9977 | "epoch": 20.78, |
| 9978 | "learning_rate": 0.00017794460641399416, |
| 9979 | "loss": 0.0419, |
| 9980 | "step": 14460 |
| 9981 | }, |
| 9982 | { |
| 9983 | "epoch": 20.79, |
| 9984 | "learning_rate": 0.00017785714285714285, |
| 9985 | "loss": 0.0365, |
| 9986 | "step": 14470 |
| 9987 | }, |
| 9988 | { |
| 9989 | "epoch": 20.8, |
| 9990 | "learning_rate": 0.00017776967930029154, |
| 9991 | "loss": 0.0439, |
| 9992 | "step": 14480 |
| 9993 | }, |
| 9994 | { |
| 9995 | "epoch": 20.82, |
| 9996 | "learning_rate": 0.00017768221574344023, |
| 9997 | "loss": 0.038, |
| 9998 | "step": 14490 |
| 9999 | }, |
| 10000 | { |
| 10001 | "epoch": 20.83, |
| 10002 | "learning_rate": 0.00017759475218658891, |
| 10003 | "loss": 0.0416, |
| 10004 | "step": 14500 |
| 10005 | }, |
| 10006 | { |
| 10007 | "epoch": 20.83, |
| 10008 | "eval_loss": 0.14831580221652985, |
| 10009 | "eval_runtime": 39.9501, |
| 10010 | "eval_samples_per_second": 11.439, |
| 10011 | "eval_steps_per_second": 1.452, |
| 10012 | "eval_wer": 0.15148321035988557, |
| 10013 | "step": 14500 |
| 10014 | }, |
| 10015 | { |
| 10016 | "epoch": 20.85, |
| 10017 | "learning_rate": 0.0001775072886297376, |
| 10018 | "loss": 0.0488, |
| 10019 | "step": 14510 |
| 10020 | }, |
| 10021 | { |
| 10022 | "epoch": 20.86, |
| 10023 | "learning_rate": 0.00017741982507288626, |
| 10024 | "loss": 0.0511, |
| 10025 | "step": 14520 |
| 10026 | }, |
| 10027 | { |
| 10028 | "epoch": 20.88, |
| 10029 | "learning_rate": 0.00017733236151603495, |
| 10030 | "loss": 0.0605, |
| 10031 | "step": 14530 |
| 10032 | }, |
| 10033 | { |
| 10034 | "epoch": 20.89, |
| 10035 | "learning_rate": 0.00017724489795918364, |
| 10036 | "loss": 0.027, |
| 10037 | "step": 14540 |
| 10038 | }, |
| 10039 | { |
| 10040 | "epoch": 20.91, |
| 10041 | "learning_rate": 0.00017715743440233235, |
| 10042 | "loss": 0.0499, |
| 10043 | "step": 14550 |
| 10044 | }, |
| 10045 | { |
| 10046 | "epoch": 20.92, |
| 10047 | "learning_rate": 0.00017706997084548104, |
| 10048 | "loss": 0.0462, |
| 10049 | "step": 14560 |
| 10050 | }, |
| 10051 | { |
| 10052 | "epoch": 20.93, |
| 10053 | "learning_rate": 0.00017698250728862973, |
| 10054 | "loss": 0.0376, |
| 10055 | "step": 14570 |
| 10056 | }, |
| 10057 | { |
| 10058 | "epoch": 20.95, |
| 10059 | "learning_rate": 0.00017689504373177842, |
| 10060 | "loss": 0.0632, |
| 10061 | "step": 14580 |
| 10062 | }, |
| 10063 | { |
| 10064 | "epoch": 20.96, |
| 10065 | "learning_rate": 0.0001768075801749271, |
| 10066 | "loss": 0.0459, |
| 10067 | "step": 14590 |
| 10068 | }, |
| 10069 | { |
| 10070 | "epoch": 20.98, |
| 10071 | "learning_rate": 0.0001767201166180758, |
| 10072 | "loss": 0.0467, |
| 10073 | "step": 14600 |
| 10074 | }, |
| 10075 | { |
| 10076 | "epoch": 20.98, |
| 10077 | "eval_loss": 0.14795160293579102, |
| 10078 | "eval_runtime": 40.0839, |
| 10079 | "eval_samples_per_second": 11.401, |
| 10080 | "eval_steps_per_second": 1.447, |
| 10081 | "eval_wer": 0.1519349495557898, |
| 10082 | "step": 14600 |
| 10083 | }, |
| 10084 | { |
| 10085 | "epoch": 20.99, |
| 10086 | "learning_rate": 0.00017663265306122445, |
| 10087 | "loss": 0.0478, |
| 10088 | "step": 14610 |
| 10089 | }, |
| 10090 | { |
| 10091 | "epoch": 21.01, |
| 10092 | "learning_rate": 0.00017654518950437314, |
| 10093 | "loss": 0.0346, |
| 10094 | "step": 14620 |
| 10095 | }, |
| 10096 | { |
| 10097 | "epoch": 21.02, |
| 10098 | "learning_rate": 0.00017645772594752186, |
| 10099 | "loss": 0.0437, |
| 10100 | "step": 14630 |
| 10101 | }, |
| 10102 | { |
| 10103 | "epoch": 21.03, |
| 10104 | "learning_rate": 0.00017637026239067055, |
| 10105 | "loss": 0.0533, |
| 10106 | "step": 14640 |
| 10107 | }, |
| 10108 | { |
| 10109 | "epoch": 21.05, |
| 10110 | "learning_rate": 0.00017628279883381923, |
| 10111 | "loss": 0.0414, |
| 10112 | "step": 14650 |
| 10113 | }, |
| 10114 | { |
| 10115 | "epoch": 21.06, |
| 10116 | "learning_rate": 0.00017619533527696792, |
| 10117 | "loss": 0.033, |
| 10118 | "step": 14660 |
| 10119 | }, |
| 10120 | { |
| 10121 | "epoch": 21.08, |
| 10122 | "learning_rate": 0.0001761078717201166, |
| 10123 | "loss": 0.0384, |
| 10124 | "step": 14670 |
| 10125 | }, |
| 10126 | { |
| 10127 | "epoch": 21.09, |
| 10128 | "learning_rate": 0.0001760204081632653, |
| 10129 | "loss": 0.0456, |
| 10130 | "step": 14680 |
| 10131 | }, |
| 10132 | { |
| 10133 | "epoch": 21.11, |
| 10134 | "learning_rate": 0.00017593294460641398, |
| 10135 | "loss": 0.0376, |
| 10136 | "step": 14690 |
| 10137 | }, |
| 10138 | { |
| 10139 | "epoch": 21.12, |
| 10140 | "learning_rate": 0.00017584548104956265, |
| 10141 | "loss": 0.0527, |
| 10142 | "step": 14700 |
| 10143 | }, |
| 10144 | { |
| 10145 | "epoch": 21.12, |
| 10146 | "eval_loss": 0.152811199426651, |
| 10147 | "eval_runtime": 39.8549, |
| 10148 | "eval_samples_per_second": 11.467, |
| 10149 | "eval_steps_per_second": 1.455, |
| 10150 | "eval_wer": 0.14907393464839633, |
| 10151 | "step": 14700 |
| 10152 | }, |
| 10153 | { |
| 10154 | "epoch": 21.14, |
| 10155 | "learning_rate": 0.00017575801749271133, |
| 10156 | "loss": 0.0395, |
| 10157 | "step": 14710 |
| 10158 | }, |
| 10159 | { |
| 10160 | "epoch": 21.15, |
| 10161 | "learning_rate": 0.00017567055393586005, |
| 10162 | "loss": 0.0435, |
| 10163 | "step": 14720 |
| 10164 | }, |
| 10165 | { |
| 10166 | "epoch": 21.16, |
| 10167 | "learning_rate": 0.00017558309037900874, |
| 10168 | "loss": 0.0414, |
| 10169 | "step": 14730 |
| 10170 | }, |
| 10171 | { |
| 10172 | "epoch": 21.18, |
| 10173 | "learning_rate": 0.00017549562682215742, |
| 10174 | "loss": 0.0364, |
| 10175 | "step": 14740 |
| 10176 | }, |
| 10177 | { |
| 10178 | "epoch": 21.19, |
| 10179 | "learning_rate": 0.0001754081632653061, |
| 10180 | "loss": 0.0349, |
| 10181 | "step": 14750 |
| 10182 | }, |
| 10183 | { |
| 10184 | "epoch": 21.21, |
| 10185 | "learning_rate": 0.0001753206997084548, |
| 10186 | "loss": 0.0436, |
| 10187 | "step": 14760 |
| 10188 | }, |
| 10189 | { |
| 10190 | "epoch": 21.22, |
| 10191 | "learning_rate": 0.0001752332361516035, |
| 10192 | "loss": 0.0513, |
| 10193 | "step": 14770 |
| 10194 | }, |
| 10195 | { |
| 10196 | "epoch": 21.24, |
| 10197 | "learning_rate": 0.00017514577259475218, |
| 10198 | "loss": 0.0489, |
| 10199 | "step": 14780 |
| 10200 | }, |
| 10201 | { |
| 10202 | "epoch": 21.25, |
| 10203 | "learning_rate": 0.00017505830903790084, |
| 10204 | "loss": 0.0302, |
| 10205 | "step": 14790 |
| 10206 | }, |
| 10207 | { |
| 10208 | "epoch": 21.26, |
| 10209 | "learning_rate": 0.00017497084548104952, |
| 10210 | "loss": 0.0625, |
| 10211 | "step": 14800 |
| 10212 | }, |
| 10213 | { |
| 10214 | "epoch": 21.26, |
| 10215 | "eval_loss": 0.1483238786458969, |
| 10216 | "eval_runtime": 40.1794, |
| 10217 | "eval_samples_per_second": 11.374, |
| 10218 | "eval_steps_per_second": 1.444, |
| 10219 | "eval_wer": 0.14907393464839633, |
| 10220 | "step": 14800 |
| 10221 | }, |
| 10222 | { |
| 10223 | "epoch": 21.28, |
| 10224 | "learning_rate": 0.00017488338192419824, |
| 10225 | "loss": 0.0435, |
| 10226 | "step": 14810 |
| 10227 | }, |
| 10228 | { |
| 10229 | "epoch": 21.29, |
| 10230 | "learning_rate": 0.00017479591836734693, |
| 10231 | "loss": 0.0369, |
| 10232 | "step": 14820 |
| 10233 | }, |
| 10234 | { |
| 10235 | "epoch": 21.31, |
| 10236 | "learning_rate": 0.00017470845481049562, |
| 10237 | "loss": 0.0447, |
| 10238 | "step": 14830 |
| 10239 | }, |
| 10240 | { |
| 10241 | "epoch": 21.32, |
| 10242 | "learning_rate": 0.0001746209912536443, |
| 10243 | "loss": 0.0332, |
| 10244 | "step": 14840 |
| 10245 | }, |
| 10246 | { |
| 10247 | "epoch": 21.34, |
| 10248 | "learning_rate": 0.000174533527696793, |
| 10249 | "loss": 0.0375, |
| 10250 | "step": 14850 |
| 10251 | }, |
| 10252 | { |
| 10253 | "epoch": 21.35, |
| 10254 | "learning_rate": 0.00017444606413994168, |
| 10255 | "loss": 0.0468, |
| 10256 | "step": 14860 |
| 10257 | }, |
| 10258 | { |
| 10259 | "epoch": 21.36, |
| 10260 | "learning_rate": 0.00017435860058309037, |
| 10261 | "loss": 0.0434, |
| 10262 | "step": 14870 |
| 10263 | }, |
| 10264 | { |
| 10265 | "epoch": 21.38, |
| 10266 | "learning_rate": 0.00017427113702623903, |
| 10267 | "loss": 0.047, |
| 10268 | "step": 14880 |
| 10269 | }, |
| 10270 | { |
| 10271 | "epoch": 21.39, |
| 10272 | "learning_rate": 0.00017418367346938774, |
| 10273 | "loss": 0.0402, |
| 10274 | "step": 14890 |
| 10275 | }, |
| 10276 | { |
| 10277 | "epoch": 21.41, |
| 10278 | "learning_rate": 0.00017409620991253643, |
| 10279 | "loss": 0.043, |
| 10280 | "step": 14900 |
| 10281 | }, |
| 10282 | { |
| 10283 | "epoch": 21.41, |
| 10284 | "eval_loss": 0.15278911590576172, |
| 10285 | "eval_runtime": 40.0861, |
| 10286 | "eval_samples_per_second": 11.4, |
| 10287 | "eval_steps_per_second": 1.447, |
| 10288 | "eval_wer": 0.14862219545249208, |
| 10289 | "step": 14900 |
| 10290 | }, |
| 10291 | { |
| 10292 | "epoch": 21.42, |
| 10293 | "learning_rate": 0.00017400874635568512, |
| 10294 | "loss": 0.0458, |
| 10295 | "step": 14910 |
| 10296 | }, |
| 10297 | { |
| 10298 | "epoch": 21.44, |
| 10299 | "learning_rate": 0.0001739212827988338, |
| 10300 | "loss": 0.0451, |
| 10301 | "step": 14920 |
| 10302 | }, |
| 10303 | { |
| 10304 | "epoch": 21.45, |
| 10305 | "learning_rate": 0.0001738338192419825, |
| 10306 | "loss": 0.0435, |
| 10307 | "step": 14930 |
| 10308 | }, |
| 10309 | { |
| 10310 | "epoch": 21.47, |
| 10311 | "learning_rate": 0.00017374635568513118, |
| 10312 | "loss": 0.043, |
| 10313 | "step": 14940 |
| 10314 | }, |
| 10315 | { |
| 10316 | "epoch": 21.48, |
| 10317 | "learning_rate": 0.00017365889212827987, |
| 10318 | "loss": 0.0461, |
| 10319 | "step": 14950 |
| 10320 | }, |
| 10321 | { |
| 10322 | "epoch": 21.49, |
| 10323 | "learning_rate": 0.00017357142857142859, |
| 10324 | "loss": 0.0498, |
| 10325 | "step": 14960 |
| 10326 | }, |
| 10327 | { |
| 10328 | "epoch": 21.51, |
| 10329 | "learning_rate": 0.00017348396501457722, |
| 10330 | "loss": 0.0465, |
| 10331 | "step": 14970 |
| 10332 | }, |
| 10333 | { |
| 10334 | "epoch": 21.52, |
| 10335 | "learning_rate": 0.00017339650145772593, |
| 10336 | "loss": 0.0386, |
| 10337 | "step": 14980 |
| 10338 | }, |
| 10339 | { |
| 10340 | "epoch": 21.54, |
| 10341 | "learning_rate": 0.00017330903790087462, |
| 10342 | "loss": 0.0388, |
| 10343 | "step": 14990 |
| 10344 | }, |
| 10345 | { |
| 10346 | "epoch": 21.55, |
| 10347 | "learning_rate": 0.0001732215743440233, |
| 10348 | "loss": 0.0362, |
| 10349 | "step": 15000 |
| 10350 | }, |
| 10351 | { |
| 10352 | "epoch": 21.55, |
| 10353 | "eval_loss": 0.15051406621932983, |
| 10354 | "eval_runtime": 40.2706, |
| 10355 | "eval_samples_per_second": 11.348, |
| 10356 | "eval_steps_per_second": 1.44, |
| 10357 | "eval_wer": 0.15283842794759825, |
| 10358 | "step": 15000 |
| 10359 | }, |
| 10360 | { |
| 10361 | "epoch": 21.57, |
| 10362 | "learning_rate": 0.000173134110787172, |
| 10363 | "loss": 0.0421, |
| 10364 | "step": 15010 |
| 10365 | }, |
| 10366 | { |
| 10367 | "epoch": 21.58, |
| 10368 | "learning_rate": 0.00017304664723032069, |
| 10369 | "loss": 0.0505, |
| 10370 | "step": 15020 |
| 10371 | }, |
| 10372 | { |
| 10373 | "epoch": 21.59, |
| 10374 | "learning_rate": 0.00017295918367346937, |
| 10375 | "loss": 0.0425, |
| 10376 | "step": 15030 |
| 10377 | }, |
| 10378 | { |
| 10379 | "epoch": 21.61, |
| 10380 | "learning_rate": 0.00017287172011661806, |
| 10381 | "loss": 0.0369, |
| 10382 | "step": 15040 |
| 10383 | }, |
| 10384 | { |
| 10385 | "epoch": 21.62, |
| 10386 | "learning_rate": 0.00017278425655976678, |
| 10387 | "loss": 0.0457, |
| 10388 | "step": 15050 |
| 10389 | }, |
| 10390 | { |
| 10391 | "epoch": 21.64, |
| 10392 | "learning_rate": 0.0001726967930029154, |
| 10393 | "loss": 0.0358, |
| 10394 | "step": 15060 |
| 10395 | }, |
| 10396 | { |
| 10397 | "epoch": 21.65, |
| 10398 | "learning_rate": 0.00017260932944606413, |
| 10399 | "loss": 0.0433, |
| 10400 | "step": 15070 |
| 10401 | }, |
| 10402 | { |
| 10403 | "epoch": 21.67, |
| 10404 | "learning_rate": 0.0001725218658892128, |
| 10405 | "loss": 0.0411, |
| 10406 | "step": 15080 |
| 10407 | }, |
| 10408 | { |
| 10409 | "epoch": 21.68, |
| 10410 | "learning_rate": 0.0001724344023323615, |
| 10411 | "loss": 0.0382, |
| 10412 | "step": 15090 |
| 10413 | }, |
| 10414 | { |
| 10415 | "epoch": 21.7, |
| 10416 | "learning_rate": 0.0001723469387755102, |
| 10417 | "loss": 0.0418, |
| 10418 | "step": 15100 |
| 10419 | }, |
| 10420 | { |
| 10421 | "epoch": 21.7, |
| 10422 | "eval_loss": 0.16807501018047333, |
| 10423 | "eval_runtime": 40.3622, |
| 10424 | "eval_samples_per_second": 11.322, |
| 10425 | "eval_steps_per_second": 1.437, |
| 10426 | "eval_wer": 0.15404306580334287, |
| 10427 | "step": 15100 |
| 10428 | }, |
| 10429 | { |
| 10430 | "epoch": 21.71, |
| 10431 | "learning_rate": 0.00017225947521865888, |
| 10432 | "loss": 0.043, |
| 10433 | "step": 15110 |
| 10434 | }, |
| 10435 | { |
| 10436 | "epoch": 21.72, |
| 10437 | "learning_rate": 0.00017217201166180756, |
| 10438 | "loss": 0.0402, |
| 10439 | "step": 15120 |
| 10440 | }, |
| 10441 | { |
| 10442 | "epoch": 21.74, |
| 10443 | "learning_rate": 0.00017208454810495625, |
| 10444 | "loss": 0.059, |
| 10445 | "step": 15130 |
| 10446 | }, |
| 10447 | { |
| 10448 | "epoch": 21.75, |
| 10449 | "learning_rate": 0.00017199708454810497, |
| 10450 | "loss": 0.039, |
| 10451 | "step": 15140 |
| 10452 | }, |
| 10453 | { |
| 10454 | "epoch": 21.77, |
| 10455 | "learning_rate": 0.00017190962099125363, |
| 10456 | "loss": 0.049, |
| 10457 | "step": 15150 |
| 10458 | }, |
| 10459 | { |
| 10460 | "epoch": 21.78, |
| 10461 | "learning_rate": 0.00017182215743440232, |
| 10462 | "loss": 0.047, |
| 10463 | "step": 15160 |
| 10464 | }, |
| 10465 | { |
| 10466 | "epoch": 21.8, |
| 10467 | "learning_rate": 0.000171734693877551, |
| 10468 | "loss": 0.0545, |
| 10469 | "step": 15170 |
| 10470 | }, |
| 10471 | { |
| 10472 | "epoch": 21.81, |
| 10473 | "learning_rate": 0.0001716472303206997, |
| 10474 | "loss": 0.0409, |
| 10475 | "step": 15180 |
| 10476 | }, |
| 10477 | { |
| 10478 | "epoch": 21.82, |
| 10479 | "learning_rate": 0.00017155976676384838, |
| 10480 | "loss": 0.0512, |
| 10481 | "step": 15190 |
| 10482 | }, |
| 10483 | { |
| 10484 | "epoch": 21.84, |
| 10485 | "learning_rate": 0.00017147230320699707, |
| 10486 | "loss": 0.0521, |
| 10487 | "step": 15200 |
| 10488 | }, |
| 10489 | { |
| 10490 | "epoch": 21.84, |
| 10491 | "eval_loss": 0.1461421400308609, |
| 10492 | "eval_runtime": 39.9835, |
| 10493 | "eval_samples_per_second": 11.43, |
| 10494 | "eval_steps_per_second": 1.451, |
| 10495 | "eval_wer": 0.1472669778647794, |
| 10496 | "step": 15200 |
| 10497 | }, |
| 10498 | { |
| 10499 | "epoch": 21.85, |
| 10500 | "learning_rate": 0.00017138483965014576, |
| 10501 | "loss": 0.0358, |
| 10502 | "step": 15210 |
| 10503 | }, |
| 10504 | { |
| 10505 | "epoch": 21.87, |
| 10506 | "learning_rate": 0.00017129737609329447, |
| 10507 | "loss": 0.0419, |
| 10508 | "step": 15220 |
| 10509 | }, |
| 10510 | { |
| 10511 | "epoch": 21.88, |
| 10512 | "learning_rate": 0.00017120991253644316, |
| 10513 | "loss": 0.0488, |
| 10514 | "step": 15230 |
| 10515 | }, |
| 10516 | { |
| 10517 | "epoch": 21.9, |
| 10518 | "learning_rate": 0.00017112244897959182, |
| 10519 | "loss": 0.0375, |
| 10520 | "step": 15240 |
| 10521 | }, |
| 10522 | { |
| 10523 | "epoch": 21.91, |
| 10524 | "learning_rate": 0.0001710349854227405, |
| 10525 | "loss": 0.0492, |
| 10526 | "step": 15250 |
| 10527 | }, |
| 10528 | { |
| 10529 | "epoch": 21.93, |
| 10530 | "learning_rate": 0.0001709475218658892, |
| 10531 | "loss": 0.045, |
| 10532 | "step": 15260 |
| 10533 | }, |
| 10534 | { |
| 10535 | "epoch": 21.94, |
| 10536 | "learning_rate": 0.00017086005830903788, |
| 10537 | "loss": 0.0392, |
| 10538 | "step": 15270 |
| 10539 | }, |
| 10540 | { |
| 10541 | "epoch": 21.95, |
| 10542 | "learning_rate": 0.00017077259475218657, |
| 10543 | "loss": 0.0451, |
| 10544 | "step": 15280 |
| 10545 | }, |
| 10546 | { |
| 10547 | "epoch": 21.97, |
| 10548 | "learning_rate": 0.00017068513119533526, |
| 10549 | "loss": 0.0383, |
| 10550 | "step": 15290 |
| 10551 | }, |
| 10552 | { |
| 10553 | "epoch": 21.98, |
| 10554 | "learning_rate": 0.00017059766763848395, |
| 10555 | "loss": 0.0437, |
| 10556 | "step": 15300 |
| 10557 | }, |
| 10558 | { |
| 10559 | "epoch": 21.98, |
| 10560 | "eval_loss": 0.14696332812309265, |
| 10561 | "eval_runtime": 40.0769, |
| 10562 | "eval_samples_per_second": 11.403, |
| 10563 | "eval_steps_per_second": 1.447, |
| 10564 | "eval_wer": 0.14425538322541787, |
| 10565 | "step": 15300 |
| 10566 | }, |
| 10567 | { |
| 10568 | "epoch": 22.0, |
| 10569 | "learning_rate": 0.00017051020408163266, |
| 10570 | "loss": 0.0477, |
| 10571 | "step": 15310 |
| 10572 | }, |
| 10573 | { |
| 10574 | "epoch": 22.01, |
| 10575 | "learning_rate": 0.00017042274052478135, |
| 10576 | "loss": 0.0389, |
| 10577 | "step": 15320 |
| 10578 | }, |
| 10579 | { |
| 10580 | "epoch": 22.03, |
| 10581 | "learning_rate": 0.00017033527696793, |
| 10582 | "loss": 0.0445, |
| 10583 | "step": 15330 |
| 10584 | }, |
| 10585 | { |
| 10586 | "epoch": 22.04, |
| 10587 | "learning_rate": 0.0001702478134110787, |
| 10588 | "loss": 0.0441, |
| 10589 | "step": 15340 |
| 10590 | }, |
| 10591 | { |
| 10592 | "epoch": 22.05, |
| 10593 | "learning_rate": 0.00017016034985422739, |
| 10594 | "loss": 0.0376, |
| 10595 | "step": 15350 |
| 10596 | }, |
| 10597 | { |
| 10598 | "epoch": 22.07, |
| 10599 | "learning_rate": 0.00017007288629737607, |
| 10600 | "loss": 0.0399, |
| 10601 | "step": 15360 |
| 10602 | }, |
| 10603 | { |
| 10604 | "epoch": 22.08, |
| 10605 | "learning_rate": 0.00016998542274052476, |
| 10606 | "loss": 0.047, |
| 10607 | "step": 15370 |
| 10608 | }, |
| 10609 | { |
| 10610 | "epoch": 22.1, |
| 10611 | "learning_rate": 0.00016989795918367345, |
| 10612 | "loss": 0.0426, |
| 10613 | "step": 15380 |
| 10614 | }, |
| 10615 | { |
| 10616 | "epoch": 22.11, |
| 10617 | "learning_rate": 0.00016981049562682216, |
| 10618 | "loss": 0.0458, |
| 10619 | "step": 15390 |
| 10620 | }, |
| 10621 | { |
| 10622 | "epoch": 22.13, |
| 10623 | "learning_rate": 0.00016972303206997085, |
| 10624 | "loss": 0.0432, |
| 10625 | "step": 15400 |
| 10626 | }, |
| 10627 | { |
| 10628 | "epoch": 22.13, |
| 10629 | "eval_loss": 0.15462301671504974, |
| 10630 | "eval_runtime": 40.0637, |
| 10631 | "eval_samples_per_second": 11.407, |
| 10632 | "eval_steps_per_second": 1.448, |
| 10633 | "eval_wer": 0.1525372684836621, |
| 10634 | "step": 15400 |
| 10635 | }, |
| 10636 | { |
| 10637 | "epoch": 22.14, |
| 10638 | "learning_rate": 0.00016963556851311954, |
| 10639 | "loss": 0.0564, |
| 10640 | "step": 15410 |
| 10641 | }, |
| 10642 | { |
| 10643 | "epoch": 22.16, |
| 10644 | "learning_rate": 0.0001695481049562682, |
| 10645 | "loss": 0.0718, |
| 10646 | "step": 15420 |
| 10647 | }, |
| 10648 | { |
| 10649 | "epoch": 22.17, |
| 10650 | "learning_rate": 0.0001694606413994169, |
| 10651 | "loss": 0.0464, |
| 10652 | "step": 15430 |
| 10653 | }, |
| 10654 | { |
| 10655 | "epoch": 22.18, |
| 10656 | "learning_rate": 0.00016937317784256558, |
| 10657 | "loss": 0.0498, |
| 10658 | "step": 15440 |
| 10659 | }, |
| 10660 | { |
| 10661 | "epoch": 22.2, |
| 10662 | "learning_rate": 0.00016928571428571427, |
| 10663 | "loss": 0.0444, |
| 10664 | "step": 15450 |
| 10665 | }, |
| 10666 | { |
| 10667 | "epoch": 22.21, |
| 10668 | "learning_rate": 0.00016919825072886295, |
| 10669 | "loss": 0.0321, |
| 10670 | "step": 15460 |
| 10671 | }, |
| 10672 | { |
| 10673 | "epoch": 22.23, |
| 10674 | "learning_rate": 0.00016911078717201164, |
| 10675 | "loss": 0.0566, |
| 10676 | "step": 15470 |
| 10677 | }, |
| 10678 | { |
| 10679 | "epoch": 22.24, |
| 10680 | "learning_rate": 0.00016902332361516036, |
| 10681 | "loss": 0.0392, |
| 10682 | "step": 15480 |
| 10683 | }, |
| 10684 | { |
| 10685 | "epoch": 22.26, |
| 10686 | "learning_rate": 0.00016893586005830904, |
| 10687 | "loss": 0.052, |
| 10688 | "step": 15490 |
| 10689 | }, |
| 10690 | { |
| 10691 | "epoch": 22.27, |
| 10692 | "learning_rate": 0.00016884839650145773, |
| 10693 | "loss": 0.04, |
| 10694 | "step": 15500 |
| 10695 | }, |
| 10696 | { |
| 10697 | "epoch": 22.27, |
| 10698 | "eval_loss": 0.16076627373695374, |
| 10699 | "eval_runtime": 40.1413, |
| 10700 | "eval_samples_per_second": 11.385, |
| 10701 | "eval_steps_per_second": 1.445, |
| 10702 | "eval_wer": 0.15464538473121517, |
| 10703 | "step": 15500 |
| 10704 | }, |
| 10705 | { |
| 10706 | "epoch": 22.28, |
| 10707 | "learning_rate": 0.0001687609329446064, |
| 10708 | "loss": 0.0389, |
| 10709 | "step": 15510 |
| 10710 | }, |
| 10711 | { |
| 10712 | "epoch": 22.3, |
| 10713 | "learning_rate": 0.00016867346938775508, |
| 10714 | "loss": 0.0462, |
| 10715 | "step": 15520 |
| 10716 | }, |
| 10717 | { |
| 10718 | "epoch": 22.31, |
| 10719 | "learning_rate": 0.00016858600583090377, |
| 10720 | "loss": 0.0418, |
| 10721 | "step": 15530 |
| 10722 | }, |
| 10723 | { |
| 10724 | "epoch": 22.33, |
| 10725 | "learning_rate": 0.00016849854227405246, |
| 10726 | "loss": 0.0472, |
| 10727 | "step": 15540 |
| 10728 | }, |
| 10729 | { |
| 10730 | "epoch": 22.34, |
| 10731 | "learning_rate": 0.00016841107871720114, |
| 10732 | "loss": 0.0482, |
| 10733 | "step": 15550 |
| 10734 | }, |
| 10735 | { |
| 10736 | "epoch": 22.36, |
| 10737 | "learning_rate": 0.00016832361516034983, |
| 10738 | "loss": 0.0414, |
| 10739 | "step": 15560 |
| 10740 | }, |
| 10741 | { |
| 10742 | "epoch": 22.37, |
| 10743 | "learning_rate": 0.00016823615160349855, |
| 10744 | "loss": 0.0522, |
| 10745 | "step": 15570 |
| 10746 | }, |
| 10747 | { |
| 10748 | "epoch": 22.39, |
| 10749 | "learning_rate": 0.00016814868804664723, |
| 10750 | "loss": 0.0446, |
| 10751 | "step": 15580 |
| 10752 | }, |
| 10753 | { |
| 10754 | "epoch": 22.4, |
| 10755 | "learning_rate": 0.0001680612244897959, |
| 10756 | "loss": 0.0412, |
| 10757 | "step": 15590 |
| 10758 | }, |
| 10759 | { |
| 10760 | "epoch": 22.41, |
| 10761 | "learning_rate": 0.00016797376093294458, |
| 10762 | "loss": 0.0489, |
| 10763 | "step": 15600 |
| 10764 | }, |
| 10765 | { |
| 10766 | "epoch": 22.41, |
| 10767 | "eval_loss": 0.15332674980163574, |
| 10768 | "eval_runtime": 40.0542, |
| 10769 | "eval_samples_per_second": 11.41, |
| 10770 | "eval_steps_per_second": 1.448, |
| 10771 | "eval_wer": 0.15042915223610903, |
| 10772 | "step": 15600 |
| 10773 | }, |
| 10774 | { |
| 10775 | "epoch": 22.43, |
| 10776 | "learning_rate": 0.00016788629737609327, |
| 10777 | "loss": 0.0315, |
| 10778 | "step": 15610 |
| 10779 | }, |
| 10780 | { |
| 10781 | "epoch": 22.44, |
| 10782 | "learning_rate": 0.00016779883381924196, |
| 10783 | "loss": 0.0503, |
| 10784 | "step": 15620 |
| 10785 | }, |
| 10786 | { |
| 10787 | "epoch": 22.46, |
| 10788 | "learning_rate": 0.00016771137026239065, |
| 10789 | "loss": 0.0387, |
| 10790 | "step": 15630 |
| 10791 | }, |
| 10792 | { |
| 10793 | "epoch": 22.47, |
| 10794 | "learning_rate": 0.00016762390670553934, |
| 10795 | "loss": 0.0459, |
| 10796 | "step": 15640 |
| 10797 | }, |
| 10798 | { |
| 10799 | "epoch": 22.49, |
| 10800 | "learning_rate": 0.00016753644314868805, |
| 10801 | "loss": 0.0387, |
| 10802 | "step": 15650 |
| 10803 | }, |
| 10804 | { |
| 10805 | "epoch": 22.5, |
| 10806 | "learning_rate": 0.00016744897959183674, |
| 10807 | "loss": 0.0415, |
| 10808 | "step": 15660 |
| 10809 | }, |
| 10810 | { |
| 10811 | "epoch": 22.51, |
| 10812 | "learning_rate": 0.00016736151603498543, |
| 10813 | "loss": 0.0416, |
| 10814 | "step": 15670 |
| 10815 | }, |
| 10816 | { |
| 10817 | "epoch": 22.53, |
| 10818 | "learning_rate": 0.0001672740524781341, |
| 10819 | "loss": 0.0442, |
| 10820 | "step": 15680 |
| 10821 | }, |
| 10822 | { |
| 10823 | "epoch": 22.54, |
| 10824 | "learning_rate": 0.00016718658892128277, |
| 10825 | "loss": 0.0342, |
| 10826 | "step": 15690 |
| 10827 | }, |
| 10828 | { |
| 10829 | "epoch": 22.56, |
| 10830 | "learning_rate": 0.00016709912536443146, |
| 10831 | "loss": 0.047, |
| 10832 | "step": 15700 |
| 10833 | }, |
| 10834 | { |
| 10835 | "epoch": 22.56, |
| 10836 | "eval_loss": 0.14910167455673218, |
| 10837 | "eval_runtime": 39.949, |
| 10838 | "eval_samples_per_second": 11.44, |
| 10839 | "eval_steps_per_second": 1.452, |
| 10840 | "eval_wer": 0.1453094413491944, |
| 10841 | "step": 15700 |
| 10842 | }, |
| 10843 | { |
| 10844 | "epoch": 22.57, |
| 10845 | "learning_rate": 0.00016701166180758015, |
| 10846 | "loss": 0.0468, |
| 10847 | "step": 15710 |
| 10848 | }, |
| 10849 | { |
| 10850 | "epoch": 22.59, |
| 10851 | "learning_rate": 0.00016692419825072884, |
| 10852 | "loss": 0.0461, |
| 10853 | "step": 15720 |
| 10854 | }, |
| 10855 | { |
| 10856 | "epoch": 22.6, |
| 10857 | "learning_rate": 0.00016683673469387753, |
| 10858 | "loss": 0.0453, |
| 10859 | "step": 15730 |
| 10860 | }, |
| 10861 | { |
| 10862 | "epoch": 22.61, |
| 10863 | "learning_rate": 0.00016674927113702624, |
| 10864 | "loss": 0.0559, |
| 10865 | "step": 15740 |
| 10866 | }, |
| 10867 | { |
| 10868 | "epoch": 22.63, |
| 10869 | "learning_rate": 0.00016666180758017493, |
| 10870 | "loss": 0.0422, |
| 10871 | "step": 15750 |
| 10872 | }, |
| 10873 | { |
| 10874 | "epoch": 22.64, |
| 10875 | "learning_rate": 0.00016657434402332362, |
| 10876 | "loss": 0.0367, |
| 10877 | "step": 15760 |
| 10878 | }, |
| 10879 | { |
| 10880 | "epoch": 22.66, |
| 10881 | "learning_rate": 0.00016648688046647228, |
| 10882 | "loss": 0.0499, |
| 10883 | "step": 15770 |
| 10884 | }, |
| 10885 | { |
| 10886 | "epoch": 22.67, |
| 10887 | "learning_rate": 0.00016639941690962097, |
| 10888 | "loss": 0.0454, |
| 10889 | "step": 15780 |
| 10890 | }, |
| 10891 | { |
| 10892 | "epoch": 22.69, |
| 10893 | "learning_rate": 0.00016631195335276965, |
| 10894 | "loss": 0.043, |
| 10895 | "step": 15790 |
| 10896 | }, |
| 10897 | { |
| 10898 | "epoch": 22.7, |
| 10899 | "learning_rate": 0.00016622448979591834, |
| 10900 | "loss": 0.0571, |
| 10901 | "step": 15800 |
| 10902 | }, |
| 10903 | { |
| 10904 | "epoch": 22.7, |
| 10905 | "eval_loss": 0.1495945006608963, |
| 10906 | "eval_runtime": 40.0515, |
| 10907 | "eval_samples_per_second": 11.41, |
| 10908 | "eval_steps_per_second": 1.448, |
| 10909 | "eval_wer": 0.15148321035988557, |
| 10910 | "step": 15800 |
| 10911 | }, |
| 10912 | { |
| 10913 | "epoch": 22.72, |
| 10914 | "learning_rate": 0.00016613702623906703, |
| 10915 | "loss": 0.0405, |
| 10916 | "step": 15810 |
| 10917 | }, |
| 10918 | { |
| 10919 | "epoch": 22.73, |
| 10920 | "learning_rate": 0.00016604956268221574, |
| 10921 | "loss": 0.0594, |
| 10922 | "step": 15820 |
| 10923 | }, |
| 10924 | { |
| 10925 | "epoch": 22.74, |
| 10926 | "learning_rate": 0.00016596209912536443, |
| 10927 | "loss": 0.049, |
| 10928 | "step": 15830 |
| 10929 | }, |
| 10930 | { |
| 10931 | "epoch": 22.76, |
| 10932 | "learning_rate": 0.00016587463556851312, |
| 10933 | "loss": 0.031, |
| 10934 | "step": 15840 |
| 10935 | }, |
| 10936 | { |
| 10937 | "epoch": 22.77, |
| 10938 | "learning_rate": 0.0001657871720116618, |
| 10939 | "loss": 0.0434, |
| 10940 | "step": 15850 |
| 10941 | }, |
| 10942 | { |
| 10943 | "epoch": 22.79, |
| 10944 | "learning_rate": 0.00016569970845481047, |
| 10945 | "loss": 0.0462, |
| 10946 | "step": 15860 |
| 10947 | }, |
| 10948 | { |
| 10949 | "epoch": 22.8, |
| 10950 | "learning_rate": 0.00016561224489795916, |
| 10951 | "loss": 0.0427, |
| 10952 | "step": 15870 |
| 10953 | }, |
| 10954 | { |
| 10955 | "epoch": 22.82, |
| 10956 | "learning_rate": 0.00016552478134110784, |
| 10957 | "loss": 0.0335, |
| 10958 | "step": 15880 |
| 10959 | }, |
| 10960 | { |
| 10961 | "epoch": 22.83, |
| 10962 | "learning_rate": 0.00016543731778425653, |
| 10963 | "loss": 0.0445, |
| 10964 | "step": 15890 |
| 10965 | }, |
| 10966 | { |
| 10967 | "epoch": 22.84, |
| 10968 | "learning_rate": 0.00016534985422740522, |
| 10969 | "loss": 0.0415, |
| 10970 | "step": 15900 |
| 10971 | }, |
| 10972 | { |
| 10973 | "epoch": 22.84, |
| 10974 | "eval_loss": 0.14830708503723145, |
| 10975 | "eval_runtime": 40.0588, |
| 10976 | "eval_samples_per_second": 11.408, |
| 10977 | "eval_steps_per_second": 1.448, |
| 10978 | "eval_wer": 0.15268784821563017, |
| 10979 | "step": 15900 |
| 10980 | }, |
| 10981 | { |
| 10982 | "epoch": 22.86, |
| 10983 | "learning_rate": 0.00016526239067055394, |
| 10984 | "loss": 0.0393, |
| 10985 | "step": 15910 |
| 10986 | }, |
| 10987 | { |
| 10988 | "epoch": 22.87, |
| 10989 | "learning_rate": 0.00016517492711370262, |
| 10990 | "loss": 0.0525, |
| 10991 | "step": 15920 |
| 10992 | }, |
| 10993 | { |
| 10994 | "epoch": 22.89, |
| 10995 | "learning_rate": 0.0001650874635568513, |
| 10996 | "loss": 0.0349, |
| 10997 | "step": 15930 |
| 10998 | }, |
| 10999 | { |
| 11000 | "epoch": 22.9, |
| 11001 | "learning_rate": 0.000165, |
| 11002 | "loss": 0.0378, |
| 11003 | "step": 15940 |
| 11004 | }, |
| 11005 | { |
| 11006 | "epoch": 22.92, |
| 11007 | "learning_rate": 0.00016491253644314866, |
| 11008 | "loss": 0.0474, |
| 11009 | "step": 15950 |
| 11010 | }, |
| 11011 | { |
| 11012 | "epoch": 22.93, |
| 11013 | "learning_rate": 0.00016482507288629735, |
| 11014 | "loss": 0.0412, |
| 11015 | "step": 15960 |
| 11016 | }, |
| 11017 | { |
| 11018 | "epoch": 22.95, |
| 11019 | "learning_rate": 0.00016473760932944604, |
| 11020 | "loss": 0.0456, |
| 11021 | "step": 15970 |
| 11022 | }, |
| 11023 | { |
| 11024 | "epoch": 22.96, |
| 11025 | "learning_rate": 0.00016465014577259472, |
| 11026 | "loss": 0.0391, |
| 11027 | "step": 15980 |
| 11028 | }, |
| 11029 | { |
| 11030 | "epoch": 22.97, |
| 11031 | "learning_rate": 0.0001645626822157434, |
| 11032 | "loss": 0.0386, |
| 11033 | "step": 15990 |
| 11034 | }, |
| 11035 | { |
| 11036 | "epoch": 22.99, |
| 11037 | "learning_rate": 0.00016447521865889213, |
| 11038 | "loss": 0.0429, |
| 11039 | "step": 16000 |
| 11040 | }, |
| 11041 | { |
| 11042 | "epoch": 22.99, |
| 11043 | "eval_loss": 0.152438685297966, |
| 11044 | "eval_runtime": 39.9987, |
| 11045 | "eval_samples_per_second": 11.425, |
| 11046 | "eval_steps_per_second": 1.45, |
| 11047 | "eval_wer": 0.14696581840084325, |
| 11048 | "step": 16000 |
| 11049 | }, |
| 11050 | { |
| 11051 | "epoch": 23.0, |
| 11052 | "learning_rate": 0.00016438775510204081, |
| 11053 | "loss": 0.0516, |
| 11054 | "step": 16010 |
| 11055 | }, |
| 11056 | { |
| 11057 | "epoch": 23.02, |
| 11058 | "learning_rate": 0.0001643002915451895, |
| 11059 | "loss": 0.0391, |
| 11060 | "step": 16020 |
| 11061 | }, |
| 11062 | { |
| 11063 | "epoch": 23.03, |
| 11064 | "learning_rate": 0.0001642128279883382, |
| 11065 | "loss": 0.0378, |
| 11066 | "step": 16030 |
| 11067 | }, |
| 11068 | { |
| 11069 | "epoch": 23.05, |
| 11070 | "learning_rate": 0.00016412536443148685, |
| 11071 | "loss": 0.0431, |
| 11072 | "step": 16040 |
| 11073 | }, |
| 11074 | { |
| 11075 | "epoch": 23.06, |
| 11076 | "learning_rate": 0.00016403790087463554, |
| 11077 | "loss": 0.0377, |
| 11078 | "step": 16050 |
| 11079 | }, |
| 11080 | { |
| 11081 | "epoch": 23.07, |
| 11082 | "learning_rate": 0.00016395043731778423, |
| 11083 | "loss": 0.0399, |
| 11084 | "step": 16060 |
| 11085 | }, |
| 11086 | { |
| 11087 | "epoch": 23.09, |
| 11088 | "learning_rate": 0.00016386297376093291, |
| 11089 | "loss": 0.0415, |
| 11090 | "step": 16070 |
| 11091 | }, |
| 11092 | { |
| 11093 | "epoch": 23.1, |
| 11094 | "learning_rate": 0.00016377551020408163, |
| 11095 | "loss": 0.0387, |
| 11096 | "step": 16080 |
| 11097 | }, |
| 11098 | { |
| 11099 | "epoch": 23.12, |
| 11100 | "learning_rate": 0.00016368804664723032, |
| 11101 | "loss": 0.0465, |
| 11102 | "step": 16090 |
| 11103 | }, |
| 11104 | { |
| 11105 | "epoch": 23.13, |
| 11106 | "learning_rate": 0.000163600583090379, |
| 11107 | "loss": 0.0379, |
| 11108 | "step": 16100 |
| 11109 | }, |
| 11110 | { |
| 11111 | "epoch": 23.13, |
| 11112 | "eval_loss": 0.14876484870910645, |
| 11113 | "eval_runtime": 39.9457, |
| 11114 | "eval_samples_per_second": 11.441, |
| 11115 | "eval_steps_per_second": 1.452, |
| 11116 | "eval_wer": 0.1498268333082367, |
| 11117 | "step": 16100 |
| 11118 | }, |
| 11119 | { |
| 11120 | "epoch": 23.15, |
| 11121 | "learning_rate": 0.0001635131195335277, |
| 11122 | "loss": 0.0488, |
| 11123 | "step": 16110 |
| 11124 | }, |
| 11125 | { |
| 11126 | "epoch": 23.16, |
| 11127 | "learning_rate": 0.00016342565597667638, |
| 11128 | "loss": 0.0456, |
| 11129 | "step": 16120 |
| 11130 | }, |
| 11131 | { |
| 11132 | "epoch": 23.18, |
| 11133 | "learning_rate": 0.00016333819241982504, |
| 11134 | "loss": 0.0353, |
| 11135 | "step": 16130 |
| 11136 | }, |
| 11137 | { |
| 11138 | "epoch": 23.19, |
| 11139 | "learning_rate": 0.00016325072886297373, |
| 11140 | "loss": 0.0409, |
| 11141 | "step": 16140 |
| 11142 | }, |
| 11143 | { |
| 11144 | "epoch": 23.2, |
| 11145 | "learning_rate": 0.00016316326530612242, |
| 11146 | "loss": 0.0443, |
| 11147 | "step": 16150 |
| 11148 | }, |
| 11149 | { |
| 11150 | "epoch": 23.22, |
| 11151 | "learning_rate": 0.0001630758017492711, |
| 11152 | "loss": 0.0501, |
| 11153 | "step": 16160 |
| 11154 | }, |
| 11155 | { |
| 11156 | "epoch": 23.23, |
| 11157 | "learning_rate": 0.00016298833819241982, |
| 11158 | "loss": 0.0419, |
| 11159 | "step": 16170 |
| 11160 | }, |
| 11161 | { |
| 11162 | "epoch": 23.25, |
| 11163 | "learning_rate": 0.0001629008746355685, |
| 11164 | "loss": 0.0354, |
| 11165 | "step": 16180 |
| 11166 | }, |
| 11167 | { |
| 11168 | "epoch": 23.26, |
| 11169 | "learning_rate": 0.0001628134110787172, |
| 11170 | "loss": 0.0392, |
| 11171 | "step": 16190 |
| 11172 | }, |
| 11173 | { |
| 11174 | "epoch": 23.28, |
| 11175 | "learning_rate": 0.00016272594752186588, |
| 11176 | "loss": 0.0433, |
| 11177 | "step": 16200 |
| 11178 | }, |
| 11179 | { |
| 11180 | "epoch": 23.28, |
| 11181 | "eval_loss": 0.1418367326259613, |
| 11182 | "eval_runtime": 39.9209, |
| 11183 | "eval_samples_per_second": 11.448, |
| 11184 | "eval_steps_per_second": 1.453, |
| 11185 | "eval_wer": 0.14561060081313054, |
| 11186 | "step": 16200 |
| 11187 | }, |
| 11188 | { |
| 11189 | "epoch": 23.29, |
| 11190 | "learning_rate": 0.00016263848396501457, |
| 11191 | "loss": 0.0432, |
| 11192 | "step": 16210 |
| 11193 | }, |
| 11194 | { |
| 11195 | "epoch": 23.3, |
| 11196 | "learning_rate": 0.00016255102040816323, |
| 11197 | "loss": 0.05, |
| 11198 | "step": 16220 |
| 11199 | }, |
| 11200 | { |
| 11201 | "epoch": 23.32, |
| 11202 | "learning_rate": 0.00016246355685131192, |
| 11203 | "loss": 0.0386, |
| 11204 | "step": 16230 |
| 11205 | }, |
| 11206 | { |
| 11207 | "epoch": 23.33, |
| 11208 | "learning_rate": 0.0001623760932944606, |
| 11209 | "loss": 0.0439, |
| 11210 | "step": 16240 |
| 11211 | }, |
| 11212 | { |
| 11213 | "epoch": 23.35, |
| 11214 | "learning_rate": 0.0001622886297376093, |
| 11215 | "loss": 0.0391, |
| 11216 | "step": 16250 |
| 11217 | }, |
| 11218 | { |
| 11219 | "epoch": 23.36, |
| 11220 | "learning_rate": 0.000162201166180758, |
| 11221 | "loss": 0.0307, |
| 11222 | "step": 16260 |
| 11223 | }, |
| 11224 | { |
| 11225 | "epoch": 23.38, |
| 11226 | "learning_rate": 0.0001621137026239067, |
| 11227 | "loss": 0.0466, |
| 11228 | "step": 16270 |
| 11229 | }, |
| 11230 | { |
| 11231 | "epoch": 23.39, |
| 11232 | "learning_rate": 0.0001620262390670554, |
| 11233 | "loss": 0.0401, |
| 11234 | "step": 16280 |
| 11235 | }, |
| 11236 | { |
| 11237 | "epoch": 23.41, |
| 11238 | "learning_rate": 0.00016193877551020408, |
| 11239 | "loss": 0.0395, |
| 11240 | "step": 16290 |
| 11241 | }, |
| 11242 | { |
| 11243 | "epoch": 23.42, |
| 11244 | "learning_rate": 0.00016185131195335276, |
| 11245 | "loss": 0.0336, |
| 11246 | "step": 16300 |
| 11247 | }, |
| 11248 | { |
| 11249 | "epoch": 23.42, |
| 11250 | "eval_loss": 0.14791372418403625, |
| 11251 | "eval_runtime": 40.2525, |
| 11252 | "eval_samples_per_second": 11.353, |
| 11253 | "eval_steps_per_second": 1.441, |
| 11254 | "eval_wer": 0.15088089143201325, |
| 11255 | "step": 16300 |
| 11256 | }, |
| 11257 | { |
| 11258 | "epoch": 23.43, |
| 11259 | "learning_rate": 0.00016176384839650142, |
| 11260 | "loss": 0.0371, |
| 11261 | "step": 16310 |
| 11262 | }, |
| 11263 | { |
| 11264 | "epoch": 23.45, |
| 11265 | "learning_rate": 0.0001616763848396501, |
| 11266 | "loss": 0.0456, |
| 11267 | "step": 16320 |
| 11268 | }, |
| 11269 | { |
| 11270 | "epoch": 23.46, |
| 11271 | "learning_rate": 0.0001615889212827988, |
| 11272 | "loss": 0.0356, |
| 11273 | "step": 16330 |
| 11274 | }, |
| 11275 | { |
| 11276 | "epoch": 23.48, |
| 11277 | "learning_rate": 0.00016150145772594751, |
| 11278 | "loss": 0.0459, |
| 11279 | "step": 16340 |
| 11280 | }, |
| 11281 | { |
| 11282 | "epoch": 23.49, |
| 11283 | "learning_rate": 0.0001614139941690962, |
| 11284 | "loss": 0.038, |
| 11285 | "step": 16350 |
| 11286 | }, |
| 11287 | { |
| 11288 | "epoch": 23.51, |
| 11289 | "learning_rate": 0.0001613265306122449, |
| 11290 | "loss": 0.0395, |
| 11291 | "step": 16360 |
| 11292 | }, |
| 11293 | { |
| 11294 | "epoch": 23.52, |
| 11295 | "learning_rate": 0.00016123906705539358, |
| 11296 | "loss": 0.0395, |
| 11297 | "step": 16370 |
| 11298 | }, |
| 11299 | { |
| 11300 | "epoch": 23.53, |
| 11301 | "learning_rate": 0.00016115160349854227, |
| 11302 | "loss": 0.0286, |
| 11303 | "step": 16380 |
| 11304 | }, |
| 11305 | { |
| 11306 | "epoch": 23.55, |
| 11307 | "learning_rate": 0.00016106413994169095, |
| 11308 | "loss": 0.0518, |
| 11309 | "step": 16390 |
| 11310 | }, |
| 11311 | { |
| 11312 | "epoch": 23.56, |
| 11313 | "learning_rate": 0.00016097667638483962, |
| 11314 | "loss": 0.037, |
| 11315 | "step": 16400 |
| 11316 | }, |
| 11317 | { |
| 11318 | "epoch": 23.56, |
| 11319 | "eval_loss": 0.14310529828071594, |
| 11320 | "eval_runtime": 40.01, |
| 11321 | "eval_samples_per_second": 11.422, |
| 11322 | "eval_steps_per_second": 1.45, |
| 11323 | "eval_wer": 0.14621291974100287, |
| 11324 | "step": 16400 |
| 11325 | }, |
| 11326 | { |
| 11327 | "epoch": 23.58, |
| 11328 | "learning_rate": 0.0001608892128279883, |
| 11329 | "loss": 0.0287, |
| 11330 | "step": 16410 |
| 11331 | }, |
| 11332 | { |
| 11333 | "epoch": 23.59, |
| 11334 | "learning_rate": 0.000160801749271137, |
| 11335 | "loss": 0.0442, |
| 11336 | "step": 16420 |
| 11337 | }, |
| 11338 | { |
| 11339 | "epoch": 23.61, |
| 11340 | "learning_rate": 0.0001607142857142857, |
| 11341 | "loss": 0.0421, |
| 11342 | "step": 16430 |
| 11343 | }, |
| 11344 | { |
| 11345 | "epoch": 23.62, |
| 11346 | "learning_rate": 0.0001606268221574344, |
| 11347 | "loss": 0.0384, |
| 11348 | "step": 16440 |
| 11349 | }, |
| 11350 | { |
| 11351 | "epoch": 23.64, |
| 11352 | "learning_rate": 0.00016053935860058308, |
| 11353 | "loss": 0.0328, |
| 11354 | "step": 16450 |
| 11355 | }, |
| 11356 | { |
| 11357 | "epoch": 23.65, |
| 11358 | "learning_rate": 0.00016045189504373177, |
| 11359 | "loss": 0.0388, |
| 11360 | "step": 16460 |
| 11361 | }, |
| 11362 | { |
| 11363 | "epoch": 23.66, |
| 11364 | "learning_rate": 0.00016036443148688046, |
| 11365 | "loss": 0.0414, |
| 11366 | "step": 16470 |
| 11367 | }, |
| 11368 | { |
| 11369 | "epoch": 23.68, |
| 11370 | "learning_rate": 0.00016027696793002915, |
| 11371 | "loss": 0.039, |
| 11372 | "step": 16480 |
| 11373 | }, |
| 11374 | { |
| 11375 | "epoch": 23.69, |
| 11376 | "learning_rate": 0.0001601895043731778, |
| 11377 | "loss": 0.0477, |
| 11378 | "step": 16490 |
| 11379 | }, |
| 11380 | { |
| 11381 | "epoch": 23.71, |
| 11382 | "learning_rate": 0.0001601020408163265, |
| 11383 | "loss": 0.0379, |
| 11384 | "step": 16500 |
| 11385 | }, |
| 11386 | { |
| 11387 | "epoch": 23.71, |
| 11388 | "eval_loss": 0.14307264983654022, |
| 11389 | "eval_runtime": 39.9826, |
| 11390 | "eval_samples_per_second": 11.43, |
| 11391 | "eval_steps_per_second": 1.451, |
| 11392 | "eval_wer": 0.15208552928775787, |
| 11393 | "step": 16500 |
| 11394 | }, |
| 11395 | { |
| 11396 | "epoch": 23.72, |
| 11397 | "learning_rate": 0.0001600145772594752, |
| 11398 | "loss": 0.0455, |
| 11399 | "step": 16510 |
| 11400 | }, |
| 11401 | { |
| 11402 | "epoch": 23.74, |
| 11403 | "learning_rate": 0.0001599271137026239, |
| 11404 | "loss": 0.0479, |
| 11405 | "step": 16520 |
| 11406 | }, |
| 11407 | { |
| 11408 | "epoch": 23.75, |
| 11409 | "learning_rate": 0.00015983965014577258, |
| 11410 | "loss": 0.0348, |
| 11411 | "step": 16530 |
| 11412 | }, |
| 11413 | { |
| 11414 | "epoch": 23.76, |
| 11415 | "learning_rate": 0.00015975218658892127, |
| 11416 | "loss": 0.0486, |
| 11417 | "step": 16540 |
| 11418 | }, |
| 11419 | { |
| 11420 | "epoch": 23.78, |
| 11421 | "learning_rate": 0.00015966472303206996, |
| 11422 | "loss": 0.0372, |
| 11423 | "step": 16550 |
| 11424 | }, |
| 11425 | { |
| 11426 | "epoch": 23.79, |
| 11427 | "learning_rate": 0.00015957725947521865, |
| 11428 | "loss": 0.0494, |
| 11429 | "step": 16560 |
| 11430 | }, |
| 11431 | { |
| 11432 | "epoch": 23.81, |
| 11433 | "learning_rate": 0.00015948979591836734, |
| 11434 | "loss": 0.0484, |
| 11435 | "step": 16570 |
| 11436 | }, |
| 11437 | { |
| 11438 | "epoch": 23.82, |
| 11439 | "learning_rate": 0.000159402332361516, |
| 11440 | "loss": 0.0376, |
| 11441 | "step": 16580 |
| 11442 | }, |
| 11443 | { |
| 11444 | "epoch": 23.84, |
| 11445 | "learning_rate": 0.00015931486880466469, |
| 11446 | "loss": 0.0504, |
| 11447 | "step": 16590 |
| 11448 | }, |
| 11449 | { |
| 11450 | "epoch": 23.85, |
| 11451 | "learning_rate": 0.0001592274052478134, |
| 11452 | "loss": 0.0368, |
| 11453 | "step": 16600 |
| 11454 | }, |
| 11455 | { |
| 11456 | "epoch": 23.85, |
| 11457 | "eval_loss": 0.1425299048423767, |
| 11458 | "eval_runtime": 40.0088, |
| 11459 | "eval_samples_per_second": 11.422, |
| 11460 | "eval_steps_per_second": 1.45, |
| 11461 | "eval_wer": 0.14636349947297095, |
| 11462 | "step": 16600 |
| 11463 | }, |
| 11464 | { |
| 11465 | "epoch": 23.86, |
| 11466 | "learning_rate": 0.0001591399416909621, |
| 11467 | "loss": 0.0306, |
| 11468 | "step": 16610 |
| 11469 | }, |
| 11470 | { |
| 11471 | "epoch": 23.88, |
| 11472 | "learning_rate": 0.00015905247813411078, |
| 11473 | "loss": 0.052, |
| 11474 | "step": 16620 |
| 11475 | }, |
| 11476 | { |
| 11477 | "epoch": 23.89, |
| 11478 | "learning_rate": 0.00015896501457725946, |
| 11479 | "loss": 0.0363, |
| 11480 | "step": 16630 |
| 11481 | }, |
| 11482 | { |
| 11483 | "epoch": 23.91, |
| 11484 | "learning_rate": 0.00015887755102040815, |
| 11485 | "loss": 0.0448, |
| 11486 | "step": 16640 |
| 11487 | }, |
| 11488 | { |
| 11489 | "epoch": 23.92, |
| 11490 | "learning_rate": 0.00015879008746355684, |
| 11491 | "loss": 0.0367, |
| 11492 | "step": 16650 |
| 11493 | }, |
| 11494 | { |
| 11495 | "epoch": 23.94, |
| 11496 | "learning_rate": 0.00015870262390670553, |
| 11497 | "loss": 0.0334, |
| 11498 | "step": 16660 |
| 11499 | }, |
| 11500 | { |
| 11501 | "epoch": 23.95, |
| 11502 | "learning_rate": 0.0001586151603498542, |
| 11503 | "loss": 0.0391, |
| 11504 | "step": 16670 |
| 11505 | }, |
| 11506 | { |
| 11507 | "epoch": 23.97, |
| 11508 | "learning_rate": 0.00015852769679300288, |
| 11509 | "loss": 0.0355, |
| 11510 | "step": 16680 |
| 11511 | }, |
| 11512 | { |
| 11513 | "epoch": 23.98, |
| 11514 | "learning_rate": 0.0001584402332361516, |
| 11515 | "loss": 0.0497, |
| 11516 | "step": 16690 |
| 11517 | }, |
| 11518 | { |
| 11519 | "epoch": 23.99, |
| 11520 | "learning_rate": 0.00015835276967930028, |
| 11521 | "loss": 0.063, |
| 11522 | "step": 16700 |
| 11523 | }, |
| 11524 | { |
| 11525 | "epoch": 23.99, |
| 11526 | "eval_loss": 0.14010843634605408, |
| 11527 | "eval_runtime": 40.037, |
| 11528 | "eval_samples_per_second": 11.414, |
| 11529 | "eval_steps_per_second": 1.449, |
| 11530 | "eval_wer": 0.14305074536967324, |
| 11531 | "step": 16700 |
| 11532 | }, |
| 11533 | { |
| 11534 | "epoch": 24.01, |
| 11535 | "learning_rate": 0.00015826530612244897, |
| 11536 | "loss": 0.0439, |
| 11537 | "step": 16710 |
| 11538 | }, |
| 11539 | { |
| 11540 | "epoch": 24.02, |
| 11541 | "learning_rate": 0.00015817784256559766, |
| 11542 | "loss": 0.0418, |
| 11543 | "step": 16720 |
| 11544 | }, |
| 11545 | { |
| 11546 | "epoch": 24.04, |
| 11547 | "learning_rate": 0.00015809037900874634, |
| 11548 | "loss": 0.043, |
| 11549 | "step": 16730 |
| 11550 | }, |
| 11551 | { |
| 11552 | "epoch": 24.05, |
| 11553 | "learning_rate": 0.00015800291545189503, |
| 11554 | "loss": 0.0454, |
| 11555 | "step": 16740 |
| 11556 | }, |
| 11557 | { |
| 11558 | "epoch": 24.07, |
| 11559 | "learning_rate": 0.00015791545189504372, |
| 11560 | "loss": 0.0428, |
| 11561 | "step": 16750 |
| 11562 | }, |
| 11563 | { |
| 11564 | "epoch": 24.08, |
| 11565 | "learning_rate": 0.00015782798833819238, |
| 11566 | "loss": 0.0446, |
| 11567 | "step": 16760 |
| 11568 | }, |
| 11569 | { |
| 11570 | "epoch": 24.09, |
| 11571 | "learning_rate": 0.0001577405247813411, |
| 11572 | "loss": 0.0352, |
| 11573 | "step": 16770 |
| 11574 | }, |
| 11575 | { |
| 11576 | "epoch": 24.11, |
| 11577 | "learning_rate": 0.00015765306122448978, |
| 11578 | "loss": 0.0412, |
| 11579 | "step": 16780 |
| 11580 | }, |
| 11581 | { |
| 11582 | "epoch": 24.12, |
| 11583 | "learning_rate": 0.00015756559766763847, |
| 11584 | "loss": 0.0537, |
| 11585 | "step": 16790 |
| 11586 | }, |
| 11587 | { |
| 11588 | "epoch": 24.14, |
| 11589 | "learning_rate": 0.00015747813411078716, |
| 11590 | "loss": 0.0392, |
| 11591 | "step": 16800 |
| 11592 | }, |
| 11593 | { |
| 11594 | "epoch": 24.14, |
| 11595 | "eval_loss": 0.14533428847789764, |
| 11596 | "eval_runtime": 40.1832, |
| 11597 | "eval_samples_per_second": 11.373, |
| 11598 | "eval_steps_per_second": 1.443, |
| 11599 | "eval_wer": 0.15268784821563017, |
| 11600 | "step": 16800 |
| 11601 | }, |
| 11602 | { |
| 11603 | "epoch": 24.15, |
| 11604 | "learning_rate": 0.00015739067055393585, |
| 11605 | "loss": 0.0407, |
| 11606 | "step": 16810 |
| 11607 | }, |
| 11608 | { |
| 11609 | "epoch": 24.17, |
| 11610 | "learning_rate": 0.00015730320699708453, |
| 11611 | "loss": 0.0379, |
| 11612 | "step": 16820 |
| 11613 | }, |
| 11614 | { |
| 11615 | "epoch": 24.18, |
| 11616 | "learning_rate": 0.00015721574344023322, |
| 11617 | "loss": 0.0382, |
| 11618 | "step": 16830 |
| 11619 | }, |
| 11620 | { |
| 11621 | "epoch": 24.2, |
| 11622 | "learning_rate": 0.00015712827988338194, |
| 11623 | "loss": 0.0577, |
| 11624 | "step": 16840 |
| 11625 | }, |
| 11626 | { |
| 11627 | "epoch": 24.21, |
| 11628 | "learning_rate": 0.00015704081632653057, |
| 11629 | "loss": 0.0334, |
| 11630 | "step": 16850 |
| 11631 | }, |
| 11632 | { |
| 11633 | "epoch": 24.22, |
| 11634 | "learning_rate": 0.00015695335276967929, |
| 11635 | "loss": 0.0414, |
| 11636 | "step": 16860 |
| 11637 | }, |
| 11638 | { |
| 11639 | "epoch": 24.24, |
| 11640 | "learning_rate": 0.00015686588921282797, |
| 11641 | "loss": 0.0406, |
| 11642 | "step": 16870 |
| 11643 | }, |
| 11644 | { |
| 11645 | "epoch": 24.25, |
| 11646 | "learning_rate": 0.0001567871720116618, |
| 11647 | "loss": 0.0475, |
| 11648 | "step": 16880 |
| 11649 | }, |
| 11650 | { |
| 11651 | "epoch": 24.27, |
| 11652 | "learning_rate": 0.0001566997084548105, |
| 11653 | "loss": 0.0404, |
| 11654 | "step": 16890 |
| 11655 | }, |
| 11656 | { |
| 11657 | "epoch": 24.28, |
| 11658 | "learning_rate": 0.00015661224489795918, |
| 11659 | "loss": 0.0415, |
| 11660 | "step": 16900 |
| 11661 | }, |
| 11662 | { |
| 11663 | "epoch": 24.28, |
| 11664 | "eval_loss": 0.14745640754699707, |
| 11665 | "eval_runtime": 40.0707, |
| 11666 | "eval_samples_per_second": 11.405, |
| 11667 | "eval_steps_per_second": 1.447, |
| 11668 | "eval_wer": 0.1499774130402048, |
| 11669 | "step": 16900 |
| 11670 | }, |
| 11671 | { |
| 11672 | "epoch": 24.3, |
| 11673 | "learning_rate": 0.00015652478134110787, |
| 11674 | "loss": 0.0534, |
| 11675 | "step": 16910 |
| 11676 | }, |
| 11677 | { |
| 11678 | "epoch": 24.31, |
| 11679 | "learning_rate": 0.00015643731778425653, |
| 11680 | "loss": 0.0391, |
| 11681 | "step": 16920 |
| 11682 | }, |
| 11683 | { |
| 11684 | "epoch": 24.32, |
| 11685 | "learning_rate": 0.00015634985422740522, |
| 11686 | "loss": 0.043, |
| 11687 | "step": 16930 |
| 11688 | }, |
| 11689 | { |
| 11690 | "epoch": 24.34, |
| 11691 | "learning_rate": 0.0001562623906705539, |
| 11692 | "loss": 0.0499, |
| 11693 | "step": 16940 |
| 11694 | }, |
| 11695 | { |
| 11696 | "epoch": 24.35, |
| 11697 | "learning_rate": 0.00015617492711370262, |
| 11698 | "loss": 0.0401, |
| 11699 | "step": 16950 |
| 11700 | }, |
| 11701 | { |
| 11702 | "epoch": 24.37, |
| 11703 | "learning_rate": 0.0001560874635568513, |
| 11704 | "loss": 0.0477, |
| 11705 | "step": 16960 |
| 11706 | }, |
| 11707 | { |
| 11708 | "epoch": 24.38, |
| 11709 | "learning_rate": 0.000156, |
| 11710 | "loss": 0.0407, |
| 11711 | "step": 16970 |
| 11712 | }, |
| 11713 | { |
| 11714 | "epoch": 24.4, |
| 11715 | "learning_rate": 0.00015591253644314869, |
| 11716 | "loss": 0.0388, |
| 11717 | "step": 16980 |
| 11718 | }, |
| 11719 | { |
| 11720 | "epoch": 24.41, |
| 11721 | "learning_rate": 0.00015582507288629737, |
| 11722 | "loss": 0.0602, |
| 11723 | "step": 16990 |
| 11724 | }, |
| 11725 | { |
| 11726 | "epoch": 24.43, |
| 11727 | "learning_rate": 0.00015573760932944606, |
| 11728 | "loss": 0.0437, |
| 11729 | "step": 17000 |
| 11730 | }, |
| 11731 | { |
| 11732 | "epoch": 24.43, |
| 11733 | "eval_loss": 0.1374850571155548, |
| 11734 | "eval_runtime": 40.0686, |
| 11735 | "eval_samples_per_second": 11.405, |
| 11736 | "eval_steps_per_second": 1.448, |
| 11737 | "eval_wer": 0.1433519048336094, |
| 11738 | "step": 17000 |
| 11739 | }, |
| 11740 | { |
| 11741 | "epoch": 24.44, |
| 11742 | "learning_rate": 0.00015565014577259472, |
| 11743 | "loss": 0.0511, |
| 11744 | "step": 17010 |
| 11745 | }, |
| 11746 | { |
| 11747 | "epoch": 24.45, |
| 11748 | "learning_rate": 0.0001555626822157434, |
| 11749 | "loss": 0.0409, |
| 11750 | "step": 17020 |
| 11751 | }, |
| 11752 | { |
| 11753 | "epoch": 24.47, |
| 11754 | "learning_rate": 0.0001554752186588921, |
| 11755 | "loss": 0.0416, |
| 11756 | "step": 17030 |
| 11757 | }, |
| 11758 | { |
| 11759 | "epoch": 24.48, |
| 11760 | "learning_rate": 0.0001553877551020408, |
| 11761 | "loss": 0.0463, |
| 11762 | "step": 17040 |
| 11763 | }, |
| 11764 | { |
| 11765 | "epoch": 24.5, |
| 11766 | "learning_rate": 0.0001553002915451895, |
| 11767 | "loss": 0.0344, |
| 11768 | "step": 17050 |
| 11769 | }, |
| 11770 | { |
| 11771 | "epoch": 24.51, |
| 11772 | "learning_rate": 0.0001552128279883382, |
| 11773 | "loss": 0.0474, |
| 11774 | "step": 17060 |
| 11775 | }, |
| 11776 | { |
| 11777 | "epoch": 24.53, |
| 11778 | "learning_rate": 0.00015512536443148688, |
| 11779 | "loss": 0.0418, |
| 11780 | "step": 17070 |
| 11781 | }, |
| 11782 | { |
| 11783 | "epoch": 24.54, |
| 11784 | "learning_rate": 0.00015503790087463556, |
| 11785 | "loss": 0.0429, |
| 11786 | "step": 17080 |
| 11787 | }, |
| 11788 | { |
| 11789 | "epoch": 24.55, |
| 11790 | "learning_rate": 0.00015495043731778425, |
| 11791 | "loss": 0.0468, |
| 11792 | "step": 17090 |
| 11793 | }, |
| 11794 | { |
| 11795 | "epoch": 24.57, |
| 11796 | "learning_rate": 0.0001548629737609329, |
| 11797 | "loss": 0.0409, |
| 11798 | "step": 17100 |
| 11799 | }, |
| 11800 | { |
| 11801 | "epoch": 24.57, |
| 11802 | "eval_loss": 0.13606612384319305, |
| 11803 | "eval_runtime": 39.9263, |
| 11804 | "eval_samples_per_second": 11.446, |
| 11805 | "eval_steps_per_second": 1.453, |
| 11806 | "eval_wer": 0.14711639813281133, |
| 11807 | "step": 17100 |
| 11808 | }, |
| 11809 | { |
| 11810 | "epoch": 24.58, |
| 11811 | "learning_rate": 0.0001547755102040816, |
| 11812 | "loss": 0.0513, |
| 11813 | "step": 17110 |
| 11814 | }, |
| 11815 | { |
| 11816 | "epoch": 24.6, |
| 11817 | "learning_rate": 0.0001546880466472303, |
| 11818 | "loss": 0.0425, |
| 11819 | "step": 17120 |
| 11820 | }, |
| 11821 | { |
| 11822 | "epoch": 24.61, |
| 11823 | "learning_rate": 0.000154600583090379, |
| 11824 | "loss": 0.0397, |
| 11825 | "step": 17130 |
| 11826 | }, |
| 11827 | { |
| 11828 | "epoch": 24.63, |
| 11829 | "learning_rate": 0.0001545131195335277, |
| 11830 | "loss": 0.0447, |
| 11831 | "step": 17140 |
| 11832 | }, |
| 11833 | { |
| 11834 | "epoch": 24.64, |
| 11835 | "learning_rate": 0.00015442565597667638, |
| 11836 | "loss": 0.0375, |
| 11837 | "step": 17150 |
| 11838 | }, |
| 11839 | { |
| 11840 | "epoch": 24.66, |
| 11841 | "learning_rate": 0.00015433819241982507, |
| 11842 | "loss": 0.0448, |
| 11843 | "step": 17160 |
| 11844 | }, |
| 11845 | { |
| 11846 | "epoch": 24.67, |
| 11847 | "learning_rate": 0.00015425072886297376, |
| 11848 | "loss": 0.0401, |
| 11849 | "step": 17170 |
| 11850 | }, |
| 11851 | { |
| 11852 | "epoch": 24.68, |
| 11853 | "learning_rate": 0.00015416326530612244, |
| 11854 | "loss": 0.0365, |
| 11855 | "step": 17180 |
| 11856 | }, |
| 11857 | { |
| 11858 | "epoch": 24.7, |
| 11859 | "learning_rate": 0.0001540758017492711, |
| 11860 | "loss": 0.0542, |
| 11861 | "step": 17190 |
| 11862 | }, |
| 11863 | { |
| 11864 | "epoch": 24.71, |
| 11865 | "learning_rate": 0.0001539883381924198, |
| 11866 | "loss": 0.0345, |
| 11867 | "step": 17200 |
| 11868 | }, |
| 11869 | { |
| 11870 | "epoch": 24.71, |
| 11871 | "eval_loss": 0.147772416472435, |
| 11872 | "eval_runtime": 39.9882, |
| 11873 | "eval_samples_per_second": 11.428, |
| 11874 | "eval_steps_per_second": 1.45, |
| 11875 | "eval_wer": 0.14711639813281133, |
| 11876 | "step": 17200 |
| 11877 | }, |
| 11878 | { |
| 11879 | "epoch": 24.73, |
| 11880 | "learning_rate": 0.0001539008746355685, |
| 11881 | "loss": 0.0431, |
| 11882 | "step": 17210 |
| 11883 | }, |
| 11884 | { |
| 11885 | "epoch": 24.74, |
| 11886 | "learning_rate": 0.0001538134110787172, |
| 11887 | "loss": 0.0456, |
| 11888 | "step": 17220 |
| 11889 | }, |
| 11890 | { |
| 11891 | "epoch": 24.76, |
| 11892 | "learning_rate": 0.00015372594752186588, |
| 11893 | "loss": 0.0338, |
| 11894 | "step": 17230 |
| 11895 | }, |
| 11896 | { |
| 11897 | "epoch": 24.77, |
| 11898 | "learning_rate": 0.00015363848396501457, |
| 11899 | "loss": 0.0447, |
| 11900 | "step": 17240 |
| 11901 | }, |
| 11902 | { |
| 11903 | "epoch": 24.78, |
| 11904 | "learning_rate": 0.00015355102040816326, |
| 11905 | "loss": 0.0334, |
| 11906 | "step": 17250 |
| 11907 | }, |
| 11908 | { |
| 11909 | "epoch": 24.8, |
| 11910 | "learning_rate": 0.00015346355685131195, |
| 11911 | "loss": 0.0523, |
| 11912 | "step": 17260 |
| 11913 | }, |
| 11914 | { |
| 11915 | "epoch": 24.81, |
| 11916 | "learning_rate": 0.0001533760932944606, |
| 11917 | "loss": 0.0383, |
| 11918 | "step": 17270 |
| 11919 | }, |
| 11920 | { |
| 11921 | "epoch": 24.83, |
| 11922 | "learning_rate": 0.0001532886297376093, |
| 11923 | "loss": 0.0372, |
| 11924 | "step": 17280 |
| 11925 | }, |
| 11926 | { |
| 11927 | "epoch": 24.84, |
| 11928 | "learning_rate": 0.00015320116618075798, |
| 11929 | "loss": 0.0465, |
| 11930 | "step": 17290 |
| 11931 | }, |
| 11932 | { |
| 11933 | "epoch": 24.86, |
| 11934 | "learning_rate": 0.0001531137026239067, |
| 11935 | "loss": 0.0344, |
| 11936 | "step": 17300 |
| 11937 | }, |
| 11938 | { |
| 11939 | "epoch": 24.86, |
| 11940 | "eval_loss": 0.1439347267150879, |
| 11941 | "eval_runtime": 40.2695, |
| 11942 | "eval_samples_per_second": 11.349, |
| 11943 | "eval_steps_per_second": 1.44, |
| 11944 | "eval_wer": 0.14756813732871554, |
| 11945 | "step": 17300 |
| 11946 | }, |
| 11947 | { |
| 11948 | "epoch": 24.87, |
| 11949 | "learning_rate": 0.00015302623906705539, |
| 11950 | "loss": 0.0427, |
| 11951 | "step": 17310 |
| 11952 | }, |
| 11953 | { |
| 11954 | "epoch": 24.89, |
| 11955 | "learning_rate": 0.00015293877551020407, |
| 11956 | "loss": 0.0384, |
| 11957 | "step": 17320 |
| 11958 | }, |
| 11959 | { |
| 11960 | "epoch": 24.9, |
| 11961 | "learning_rate": 0.00015285131195335276, |
| 11962 | "loss": 0.0364, |
| 11963 | "step": 17330 |
| 11964 | }, |
| 11965 | { |
| 11966 | "epoch": 24.91, |
| 11967 | "learning_rate": 0.00015276384839650145, |
| 11968 | "loss": 0.04, |
| 11969 | "step": 17340 |
| 11970 | }, |
| 11971 | { |
| 11972 | "epoch": 24.93, |
| 11973 | "learning_rate": 0.00015267638483965014, |
| 11974 | "loss": 0.0469, |
| 11975 | "step": 17350 |
| 11976 | }, |
| 11977 | { |
| 11978 | "epoch": 24.94, |
| 11979 | "learning_rate": 0.0001525889212827988, |
| 11980 | "loss": 0.0425, |
| 11981 | "step": 17360 |
| 11982 | }, |
| 11983 | { |
| 11984 | "epoch": 24.96, |
| 11985 | "learning_rate": 0.00015250145772594749, |
| 11986 | "loss": 0.0441, |
| 11987 | "step": 17370 |
| 11988 | }, |
| 11989 | { |
| 11990 | "epoch": 24.97, |
| 11991 | "learning_rate": 0.0001524139941690962, |
| 11992 | "loss": 0.034, |
| 11993 | "step": 17380 |
| 11994 | }, |
| 11995 | { |
| 11996 | "epoch": 24.99, |
| 11997 | "learning_rate": 0.0001523265306122449, |
| 11998 | "loss": 0.0459, |
| 11999 | "step": 17390 |
| 12000 | }, |
| 12001 | { |
| 12002 | "epoch": 25.0, |
| 12003 | "learning_rate": 0.00015223906705539358, |
| 12004 | "loss": 0.0328, |
| 12005 | "step": 17400 |
| 12006 | }, |
| 12007 | { |
| 12008 | "epoch": 25.0, |
| 12009 | "eval_loss": 0.14581048488616943, |
| 12010 | "eval_runtime": 40.0126, |
| 12011 | "eval_samples_per_second": 11.421, |
| 12012 | "eval_steps_per_second": 1.45, |
| 12013 | "eval_wer": 0.15057973196807709, |
| 12014 | "step": 17400 |
| 12015 | }, |
| 12016 | { |
| 12017 | "epoch": 25.01, |
| 12018 | "learning_rate": 0.00015215160349854226, |
| 12019 | "loss": 0.043, |
| 12020 | "step": 17410 |
| 12021 | }, |
| 12022 | { |
| 12023 | "epoch": 25.03, |
| 12024 | "learning_rate": 0.00015206413994169095, |
| 12025 | "loss": 0.0414, |
| 12026 | "step": 17420 |
| 12027 | }, |
| 12028 | { |
| 12029 | "epoch": 25.04, |
| 12030 | "learning_rate": 0.00015197667638483964, |
| 12031 | "loss": 0.0402, |
| 12032 | "step": 17430 |
| 12033 | }, |
| 12034 | { |
| 12035 | "epoch": 25.06, |
| 12036 | "learning_rate": 0.00015188921282798833, |
| 12037 | "loss": 0.0372, |
| 12038 | "step": 17440 |
| 12039 | }, |
| 12040 | { |
| 12041 | "epoch": 25.07, |
| 12042 | "learning_rate": 0.000151801749271137, |
| 12043 | "loss": 0.0334, |
| 12044 | "step": 17450 |
| 12045 | }, |
| 12046 | { |
| 12047 | "epoch": 25.09, |
| 12048 | "learning_rate": 0.00015171428571428568, |
| 12049 | "loss": 0.0458, |
| 12050 | "step": 17460 |
| 12051 | }, |
| 12052 | { |
| 12053 | "epoch": 25.1, |
| 12054 | "learning_rate": 0.0001516268221574344, |
| 12055 | "loss": 0.0364, |
| 12056 | "step": 17470 |
| 12057 | }, |
| 12058 | { |
| 12059 | "epoch": 25.11, |
| 12060 | "learning_rate": 0.00015153935860058308, |
| 12061 | "loss": 0.0401, |
| 12062 | "step": 17480 |
| 12063 | }, |
| 12064 | { |
| 12065 | "epoch": 25.13, |
| 12066 | "learning_rate": 0.00015145189504373177, |
| 12067 | "loss": 0.0359, |
| 12068 | "step": 17490 |
| 12069 | }, |
| 12070 | { |
| 12071 | "epoch": 25.14, |
| 12072 | "learning_rate": 0.00015136443148688046, |
| 12073 | "loss": 0.0548, |
| 12074 | "step": 17500 |
| 12075 | }, |
| 12076 | { |
| 12077 | "epoch": 25.14, |
| 12078 | "eval_loss": 0.14898838102817535, |
| 12079 | "eval_runtime": 39.994, |
| 12080 | "eval_samples_per_second": 11.427, |
| 12081 | "eval_steps_per_second": 1.45, |
| 12082 | "eval_wer": 0.14410480349344978, |
| 12083 | "step": 17500 |
| 12084 | }, |
| 12085 | { |
| 12086 | "epoch": 25.16, |
| 12087 | "learning_rate": 0.00015127696793002914, |
| 12088 | "loss": 0.05, |
| 12089 | "step": 17510 |
| 12090 | }, |
| 12091 | { |
| 12092 | "epoch": 25.17, |
| 12093 | "learning_rate": 0.00015118950437317783, |
| 12094 | "loss": 0.0342, |
| 12095 | "step": 17520 |
| 12096 | }, |
| 12097 | { |
| 12098 | "epoch": 25.19, |
| 12099 | "learning_rate": 0.00015110204081632652, |
| 12100 | "loss": 0.0462, |
| 12101 | "step": 17530 |
| 12102 | }, |
| 12103 | { |
| 12104 | "epoch": 25.2, |
| 12105 | "learning_rate": 0.00015101457725947518, |
| 12106 | "loss": 0.0478, |
| 12107 | "step": 17540 |
| 12108 | }, |
| 12109 | { |
| 12110 | "epoch": 25.22, |
| 12111 | "learning_rate": 0.00015092711370262387, |
| 12112 | "loss": 0.0361, |
| 12113 | "step": 17550 |
| 12114 | }, |
| 12115 | { |
| 12116 | "epoch": 25.23, |
| 12117 | "learning_rate": 0.00015083965014577258, |
| 12118 | "loss": 0.0399, |
| 12119 | "step": 17560 |
| 12120 | }, |
| 12121 | { |
| 12122 | "epoch": 25.24, |
| 12123 | "learning_rate": 0.00015075218658892127, |
| 12124 | "loss": 0.0403, |
| 12125 | "step": 17570 |
| 12126 | }, |
| 12127 | { |
| 12128 | "epoch": 25.26, |
| 12129 | "learning_rate": 0.00015066472303206996, |
| 12130 | "loss": 0.0442, |
| 12131 | "step": 17580 |
| 12132 | }, |
| 12133 | { |
| 12134 | "epoch": 25.27, |
| 12135 | "learning_rate": 0.00015057725947521865, |
| 12136 | "loss": 0.0401, |
| 12137 | "step": 17590 |
| 12138 | }, |
| 12139 | { |
| 12140 | "epoch": 25.29, |
| 12141 | "learning_rate": 0.00015048979591836733, |
| 12142 | "loss": 0.0335, |
| 12143 | "step": 17600 |
| 12144 | }, |
| 12145 | { |
| 12146 | "epoch": 25.29, |
| 12147 | "eval_loss": 0.14889946579933167, |
| 12148 | "eval_runtime": 40.0346, |
| 12149 | "eval_samples_per_second": 11.415, |
| 12150 | "eval_steps_per_second": 1.449, |
| 12151 | "eval_wer": 0.14636349947297095, |
| 12152 | "step": 17600 |
| 12153 | }, |
| 12154 | { |
| 12155 | "epoch": 25.3, |
| 12156 | "learning_rate": 0.00015040233236151602, |
| 12157 | "loss": 0.0489, |
| 12158 | "step": 17610 |
| 12159 | }, |
| 12160 | { |
| 12161 | "epoch": 25.32, |
| 12162 | "learning_rate": 0.0001503148688046647, |
| 12163 | "loss": 0.0495, |
| 12164 | "step": 17620 |
| 12165 | }, |
| 12166 | { |
| 12167 | "epoch": 25.33, |
| 12168 | "learning_rate": 0.00015022740524781337, |
| 12169 | "loss": 0.0428, |
| 12170 | "step": 17630 |
| 12171 | }, |
| 12172 | { |
| 12173 | "epoch": 25.34, |
| 12174 | "learning_rate": 0.00015013994169096209, |
| 12175 | "loss": 0.0444, |
| 12176 | "step": 17640 |
| 12177 | }, |
| 12178 | { |
| 12179 | "epoch": 25.36, |
| 12180 | "learning_rate": 0.00015005247813411077, |
| 12181 | "loss": 0.0428, |
| 12182 | "step": 17650 |
| 12183 | }, |
| 12184 | { |
| 12185 | "epoch": 25.37, |
| 12186 | "learning_rate": 0.00014996501457725946, |
| 12187 | "loss": 0.0403, |
| 12188 | "step": 17660 |
| 12189 | }, |
| 12190 | { |
| 12191 | "epoch": 25.39, |
| 12192 | "learning_rate": 0.00014987755102040815, |
| 12193 | "loss": 0.0379, |
| 12194 | "step": 17670 |
| 12195 | }, |
| 12196 | { |
| 12197 | "epoch": 25.4, |
| 12198 | "learning_rate": 0.00014979008746355684, |
| 12199 | "loss": 0.0447, |
| 12200 | "step": 17680 |
| 12201 | }, |
| 12202 | { |
| 12203 | "epoch": 25.42, |
| 12204 | "learning_rate": 0.00014970262390670553, |
| 12205 | "loss": 0.0449, |
| 12206 | "step": 17690 |
| 12207 | }, |
| 12208 | { |
| 12209 | "epoch": 25.43, |
| 12210 | "learning_rate": 0.00014961516034985421, |
| 12211 | "loss": 0.0312, |
| 12212 | "step": 17700 |
| 12213 | }, |
| 12214 | { |
| 12215 | "epoch": 25.43, |
| 12216 | "eval_loss": 0.1425950974225998, |
| 12217 | "eval_runtime": 40.0419, |
| 12218 | "eval_samples_per_second": 11.413, |
| 12219 | "eval_steps_per_second": 1.448, |
| 12220 | "eval_wer": 0.13762987501882246, |
| 12221 | "step": 17700 |
| 12222 | }, |
| 12223 | { |
| 12224 | "epoch": 25.45, |
| 12225 | "learning_rate": 0.0001495276967930029, |
| 12226 | "loss": 0.0418, |
| 12227 | "step": 17710 |
| 12228 | }, |
| 12229 | { |
| 12230 | "epoch": 25.46, |
| 12231 | "learning_rate": 0.0001494402332361516, |
| 12232 | "loss": 0.0387, |
| 12233 | "step": 17720 |
| 12234 | }, |
| 12235 | { |
| 12236 | "epoch": 25.47, |
| 12237 | "learning_rate": 0.00014935276967930028, |
| 12238 | "loss": 0.0375, |
| 12239 | "step": 17730 |
| 12240 | }, |
| 12241 | { |
| 12242 | "epoch": 25.49, |
| 12243 | "learning_rate": 0.00014926530612244897, |
| 12244 | "loss": 0.0329, |
| 12245 | "step": 17740 |
| 12246 | }, |
| 12247 | { |
| 12248 | "epoch": 25.5, |
| 12249 | "learning_rate": 0.00014917784256559765, |
| 12250 | "loss": 0.0336, |
| 12251 | "step": 17750 |
| 12252 | }, |
| 12253 | { |
| 12254 | "epoch": 25.52, |
| 12255 | "learning_rate": 0.00014909037900874634, |
| 12256 | "loss": 0.0401, |
| 12257 | "step": 17760 |
| 12258 | }, |
| 12259 | { |
| 12260 | "epoch": 25.53, |
| 12261 | "learning_rate": 0.00014900291545189503, |
| 12262 | "loss": 0.0386, |
| 12263 | "step": 17770 |
| 12264 | }, |
| 12265 | { |
| 12266 | "epoch": 25.55, |
| 12267 | "learning_rate": 0.00014891545189504372, |
| 12268 | "loss": 0.0308, |
| 12269 | "step": 17780 |
| 12270 | }, |
| 12271 | { |
| 12272 | "epoch": 25.56, |
| 12273 | "learning_rate": 0.0001488279883381924, |
| 12274 | "loss": 0.0355, |
| 12275 | "step": 17790 |
| 12276 | }, |
| 12277 | { |
| 12278 | "epoch": 25.57, |
| 12279 | "learning_rate": 0.0001487405247813411, |
| 12280 | "loss": 0.039, |
| 12281 | "step": 17800 |
| 12282 | }, |
| 12283 | { |
| 12284 | "epoch": 25.57, |
| 12285 | "eval_loss": 0.14126811921596527, |
| 12286 | "eval_runtime": 39.9334, |
| 12287 | "eval_samples_per_second": 11.444, |
| 12288 | "eval_steps_per_second": 1.452, |
| 12289 | "eval_wer": 0.14094262912212016, |
| 12290 | "step": 17800 |
| 12291 | }, |
| 12292 | { |
| 12293 | "epoch": 25.59, |
| 12294 | "learning_rate": 0.00014865306122448978, |
| 12295 | "loss": 0.0416, |
| 12296 | "step": 17810 |
| 12297 | }, |
| 12298 | { |
| 12299 | "epoch": 25.6, |
| 12300 | "learning_rate": 0.00014856559766763847, |
| 12301 | "loss": 0.0464, |
| 12302 | "step": 17820 |
| 12303 | }, |
| 12304 | { |
| 12305 | "epoch": 25.62, |
| 12306 | "learning_rate": 0.00014847813411078716, |
| 12307 | "loss": 0.0431, |
| 12308 | "step": 17830 |
| 12309 | }, |
| 12310 | { |
| 12311 | "epoch": 25.63, |
| 12312 | "learning_rate": 0.00014839067055393584, |
| 12313 | "loss": 0.0362, |
| 12314 | "step": 17840 |
| 12315 | }, |
| 12316 | { |
| 12317 | "epoch": 25.65, |
| 12318 | "learning_rate": 0.00014830320699708453, |
| 12319 | "loss": 0.0383, |
| 12320 | "step": 17850 |
| 12321 | }, |
| 12322 | { |
| 12323 | "epoch": 25.66, |
| 12324 | "learning_rate": 0.00014821574344023322, |
| 12325 | "loss": 0.0416, |
| 12326 | "step": 17860 |
| 12327 | }, |
| 12328 | { |
| 12329 | "epoch": 25.68, |
| 12330 | "learning_rate": 0.0001481282798833819, |
| 12331 | "loss": 0.0374, |
| 12332 | "step": 17870 |
| 12333 | }, |
| 12334 | { |
| 12335 | "epoch": 25.69, |
| 12336 | "learning_rate": 0.0001480408163265306, |
| 12337 | "loss": 0.0384, |
| 12338 | "step": 17880 |
| 12339 | }, |
| 12340 | { |
| 12341 | "epoch": 25.7, |
| 12342 | "learning_rate": 0.00014795335276967928, |
| 12343 | "loss": 0.0486, |
| 12344 | "step": 17890 |
| 12345 | }, |
| 12346 | { |
| 12347 | "epoch": 25.72, |
| 12348 | "learning_rate": 0.00014786588921282797, |
| 12349 | "loss": 0.0316, |
| 12350 | "step": 17900 |
| 12351 | }, |
| 12352 | { |
| 12353 | "epoch": 25.72, |
| 12354 | "eval_loss": 0.1351412832736969, |
| 12355 | "eval_runtime": 40.4468, |
| 12356 | "eval_samples_per_second": 11.299, |
| 12357 | "eval_steps_per_second": 1.434, |
| 12358 | "eval_wer": 0.13853335341063092, |
| 12359 | "step": 17900 |
| 12360 | }, |
| 12361 | { |
| 12362 | "epoch": 25.73, |
| 12363 | "learning_rate": 0.00014777842565597666, |
| 12364 | "loss": 0.0483, |
| 12365 | "step": 17910 |
| 12366 | }, |
| 12367 | { |
| 12368 | "epoch": 25.75, |
| 12369 | "learning_rate": 0.00014769096209912535, |
| 12370 | "loss": 0.0343, |
| 12371 | "step": 17920 |
| 12372 | }, |
| 12373 | { |
| 12374 | "epoch": 25.76, |
| 12375 | "learning_rate": 0.00014760349854227404, |
| 12376 | "loss": 0.0353, |
| 12377 | "step": 17930 |
| 12378 | }, |
| 12379 | { |
| 12380 | "epoch": 25.78, |
| 12381 | "learning_rate": 0.00014751603498542272, |
| 12382 | "loss": 0.0314, |
| 12383 | "step": 17940 |
| 12384 | }, |
| 12385 | { |
| 12386 | "epoch": 25.79, |
| 12387 | "learning_rate": 0.0001474285714285714, |
| 12388 | "loss": 0.0325, |
| 12389 | "step": 17950 |
| 12390 | }, |
| 12391 | { |
| 12392 | "epoch": 25.8, |
| 12393 | "learning_rate": 0.0001473411078717201, |
| 12394 | "loss": 0.0502, |
| 12395 | "step": 17960 |
| 12396 | }, |
| 12397 | { |
| 12398 | "epoch": 25.82, |
| 12399 | "learning_rate": 0.0001472536443148688, |
| 12400 | "loss": 0.0355, |
| 12401 | "step": 17970 |
| 12402 | }, |
| 12403 | { |
| 12404 | "epoch": 25.83, |
| 12405 | "learning_rate": 0.00014716618075801747, |
| 12406 | "loss": 0.0504, |
| 12407 | "step": 17980 |
| 12408 | }, |
| 12409 | { |
| 12410 | "epoch": 25.85, |
| 12411 | "learning_rate": 0.00014707871720116616, |
| 12412 | "loss": 0.0347, |
| 12413 | "step": 17990 |
| 12414 | }, |
| 12415 | { |
| 12416 | "epoch": 25.86, |
| 12417 | "learning_rate": 0.00014699125364431485, |
| 12418 | "loss": 0.0414, |
| 12419 | "step": 18000 |
| 12420 | }, |
| 12421 | { |
| 12422 | "epoch": 25.86, |
| 12423 | "eval_loss": 0.14004768431186676, |
| 12424 | "eval_runtime": 40.0192, |
| 12425 | "eval_samples_per_second": 11.42, |
| 12426 | "eval_steps_per_second": 1.449, |
| 12427 | "eval_wer": 0.14410480349344978, |
| 12428 | "step": 18000 |
| 12429 | }, |
| 12430 | { |
| 12431 | "epoch": 25.88, |
| 12432 | "learning_rate": 0.00014690379008746357, |
| 12433 | "loss": 0.0441, |
| 12434 | "step": 18010 |
| 12435 | }, |
| 12436 | { |
| 12437 | "epoch": 25.89, |
| 12438 | "learning_rate": 0.00014681632653061223, |
| 12439 | "loss": 0.0397, |
| 12440 | "step": 18020 |
| 12441 | }, |
| 12442 | { |
| 12443 | "epoch": 25.91, |
| 12444 | "learning_rate": 0.00014672886297376091, |
| 12445 | "loss": 0.0396, |
| 12446 | "step": 18030 |
| 12447 | }, |
| 12448 | { |
| 12449 | "epoch": 25.92, |
| 12450 | "learning_rate": 0.0001466413994169096, |
| 12451 | "loss": 0.033, |
| 12452 | "step": 18040 |
| 12453 | }, |
| 12454 | { |
| 12455 | "epoch": 25.93, |
| 12456 | "learning_rate": 0.0001465539358600583, |
| 12457 | "loss": 0.037, |
| 12458 | "step": 18050 |
| 12459 | }, |
| 12460 | { |
| 12461 | "epoch": 25.95, |
| 12462 | "learning_rate": 0.00014646647230320698, |
| 12463 | "loss": 0.047, |
| 12464 | "step": 18060 |
| 12465 | }, |
| 12466 | { |
| 12467 | "epoch": 25.96, |
| 12468 | "learning_rate": 0.00014637900874635567, |
| 12469 | "loss": 0.0302, |
| 12470 | "step": 18070 |
| 12471 | }, |
| 12472 | { |
| 12473 | "epoch": 25.98, |
| 12474 | "learning_rate": 0.00014629154518950435, |
| 12475 | "loss": 0.0434, |
| 12476 | "step": 18080 |
| 12477 | }, |
| 12478 | { |
| 12479 | "epoch": 25.99, |
| 12480 | "learning_rate": 0.00014620408163265304, |
| 12481 | "loss": 0.0376, |
| 12482 | "step": 18090 |
| 12483 | }, |
| 12484 | { |
| 12485 | "epoch": 26.01, |
| 12486 | "learning_rate": 0.00014611661807580176, |
| 12487 | "loss": 0.053, |
| 12488 | "step": 18100 |
| 12489 | }, |
| 12490 | { |
| 12491 | "epoch": 26.01, |
| 12492 | "eval_loss": 0.1369037628173828, |
| 12493 | "eval_runtime": 40.0603, |
| 12494 | "eval_samples_per_second": 11.408, |
| 12495 | "eval_steps_per_second": 1.448, |
| 12496 | "eval_wer": 0.13657581689504592, |
| 12497 | "step": 18100 |
| 12498 | }, |
| 12499 | { |
| 12500 | "epoch": 26.02, |
| 12501 | "learning_rate": 0.00014602915451895042, |
| 12502 | "loss": 0.039, |
| 12503 | "step": 18110 |
| 12504 | }, |
| 12505 | { |
| 12506 | "epoch": 26.03, |
| 12507 | "learning_rate": 0.0001459416909620991, |
| 12508 | "loss": 0.0339, |
| 12509 | "step": 18120 |
| 12510 | }, |
| 12511 | { |
| 12512 | "epoch": 26.05, |
| 12513 | "learning_rate": 0.0001458542274052478, |
| 12514 | "loss": 0.0373, |
| 12515 | "step": 18130 |
| 12516 | }, |
| 12517 | { |
| 12518 | "epoch": 26.06, |
| 12519 | "learning_rate": 0.0001457667638483965, |
| 12520 | "loss": 0.0338, |
| 12521 | "step": 18140 |
| 12522 | }, |
| 12523 | { |
| 12524 | "epoch": 26.08, |
| 12525 | "learning_rate": 0.00014567930029154517, |
| 12526 | "loss": 0.0325, |
| 12527 | "step": 18150 |
| 12528 | }, |
| 12529 | { |
| 12530 | "epoch": 26.09, |
| 12531 | "learning_rate": 0.00014559183673469386, |
| 12532 | "loss": 0.0351, |
| 12533 | "step": 18160 |
| 12534 | }, |
| 12535 | { |
| 12536 | "epoch": 26.11, |
| 12537 | "learning_rate": 0.00014550437317784254, |
| 12538 | "loss": 0.0372, |
| 12539 | "step": 18170 |
| 12540 | }, |
| 12541 | { |
| 12542 | "epoch": 26.12, |
| 12543 | "learning_rate": 0.00014541690962099123, |
| 12544 | "loss": 0.0431, |
| 12545 | "step": 18180 |
| 12546 | }, |
| 12547 | { |
| 12548 | "epoch": 26.14, |
| 12549 | "learning_rate": 0.00014532944606413995, |
| 12550 | "loss": 0.033, |
| 12551 | "step": 18190 |
| 12552 | }, |
| 12553 | { |
| 12554 | "epoch": 26.15, |
| 12555 | "learning_rate": 0.0001452419825072886, |
| 12556 | "loss": 0.0461, |
| 12557 | "step": 18200 |
| 12558 | }, |
| 12559 | { |
| 12560 | "epoch": 26.15, |
| 12561 | "eval_loss": 0.14241348206996918, |
| 12562 | "eval_runtime": 40.4143, |
| 12563 | "eval_samples_per_second": 11.308, |
| 12564 | "eval_steps_per_second": 1.435, |
| 12565 | "eval_wer": 0.140641469658184, |
| 12566 | "step": 18200 |
| 12567 | }, |
| 12568 | { |
| 12569 | "epoch": 26.16, |
| 12570 | "learning_rate": 0.0001451545189504373, |
| 12571 | "loss": 0.0428, |
| 12572 | "step": 18210 |
| 12573 | }, |
| 12574 | { |
| 12575 | "epoch": 26.18, |
| 12576 | "learning_rate": 0.00014506705539358598, |
| 12577 | "loss": 0.0327, |
| 12578 | "step": 18220 |
| 12579 | }, |
| 12580 | { |
| 12581 | "epoch": 26.19, |
| 12582 | "learning_rate": 0.0001449795918367347, |
| 12583 | "loss": 0.0456, |
| 12584 | "step": 18230 |
| 12585 | }, |
| 12586 | { |
| 12587 | "epoch": 26.21, |
| 12588 | "learning_rate": 0.00014489212827988336, |
| 12589 | "loss": 0.0344, |
| 12590 | "step": 18240 |
| 12591 | }, |
| 12592 | { |
| 12593 | "epoch": 26.22, |
| 12594 | "learning_rate": 0.00014480466472303205, |
| 12595 | "loss": 0.0359, |
| 12596 | "step": 18250 |
| 12597 | }, |
| 12598 | { |
| 12599 | "epoch": 26.24, |
| 12600 | "learning_rate": 0.00014471720116618074, |
| 12601 | "loss": 0.0399, |
| 12602 | "step": 18260 |
| 12603 | }, |
| 12604 | { |
| 12605 | "epoch": 26.25, |
| 12606 | "learning_rate": 0.00014462973760932945, |
| 12607 | "loss": 0.0359, |
| 12608 | "step": 18270 |
| 12609 | }, |
| 12610 | { |
| 12611 | "epoch": 26.26, |
| 12612 | "learning_rate": 0.00014454227405247814, |
| 12613 | "loss": 0.0427, |
| 12614 | "step": 18280 |
| 12615 | }, |
| 12616 | { |
| 12617 | "epoch": 26.28, |
| 12618 | "learning_rate": 0.0001444548104956268, |
| 12619 | "loss": 0.0387, |
| 12620 | "step": 18290 |
| 12621 | }, |
| 12622 | { |
| 12623 | "epoch": 26.29, |
| 12624 | "learning_rate": 0.0001443673469387755, |
| 12625 | "loss": 0.0442, |
| 12626 | "step": 18300 |
| 12627 | }, |
| 12628 | { |
| 12629 | "epoch": 26.29, |
| 12630 | "eval_loss": 0.14577917754650116, |
| 12631 | "eval_runtime": 40.0268, |
| 12632 | "eval_samples_per_second": 11.417, |
| 12633 | "eval_steps_per_second": 1.449, |
| 12634 | "eval_wer": 0.142599006173769, |
| 12635 | "step": 18300 |
| 12636 | }, |
| 12637 | { |
| 12638 | "epoch": 26.31, |
| 12639 | "learning_rate": 0.00014427988338192418, |
| 12640 | "loss": 0.043, |
| 12641 | "step": 18310 |
| 12642 | }, |
| 12643 | { |
| 12644 | "epoch": 26.32, |
| 12645 | "learning_rate": 0.0001441924198250729, |
| 12646 | "loss": 0.0449, |
| 12647 | "step": 18320 |
| 12648 | }, |
| 12649 | { |
| 12650 | "epoch": 26.34, |
| 12651 | "learning_rate": 0.00014410495626822155, |
| 12652 | "loss": 0.0458, |
| 12653 | "step": 18330 |
| 12654 | }, |
| 12655 | { |
| 12656 | "epoch": 26.35, |
| 12657 | "learning_rate": 0.00014401749271137024, |
| 12658 | "loss": 0.0335, |
| 12659 | "step": 18340 |
| 12660 | }, |
| 12661 | { |
| 12662 | "epoch": 26.36, |
| 12663 | "learning_rate": 0.00014393002915451893, |
| 12664 | "loss": 0.0378, |
| 12665 | "step": 18350 |
| 12666 | }, |
| 12667 | { |
| 12668 | "epoch": 26.38, |
| 12669 | "learning_rate": 0.00014384256559766764, |
| 12670 | "loss": 0.0458, |
| 12671 | "step": 18360 |
| 12672 | }, |
| 12673 | { |
| 12674 | "epoch": 26.39, |
| 12675 | "learning_rate": 0.0001437551020408163, |
| 12676 | "loss": 0.0329, |
| 12677 | "step": 18370 |
| 12678 | }, |
| 12679 | { |
| 12680 | "epoch": 26.41, |
| 12681 | "learning_rate": 0.000143667638483965, |
| 12682 | "loss": 0.0468, |
| 12683 | "step": 18380 |
| 12684 | }, |
| 12685 | { |
| 12686 | "epoch": 26.42, |
| 12687 | "learning_rate": 0.00014358017492711368, |
| 12688 | "loss": 0.0324, |
| 12689 | "step": 18390 |
| 12690 | }, |
| 12691 | { |
| 12692 | "epoch": 26.44, |
| 12693 | "learning_rate": 0.0001434927113702624, |
| 12694 | "loss": 0.0407, |
| 12695 | "step": 18400 |
| 12696 | }, |
| 12697 | { |
| 12698 | "epoch": 26.44, |
| 12699 | "eval_loss": 0.14220750331878662, |
| 12700 | "eval_runtime": 40.1386, |
| 12701 | "eval_samples_per_second": 11.386, |
| 12702 | "eval_steps_per_second": 1.445, |
| 12703 | "eval_wer": 0.13988857099834362, |
| 12704 | "step": 18400 |
| 12705 | }, |
| 12706 | { |
| 12707 | "epoch": 26.45, |
| 12708 | "learning_rate": 0.00014340524781341108, |
| 12709 | "loss": 0.0483, |
| 12710 | "step": 18410 |
| 12711 | }, |
| 12712 | { |
| 12713 | "epoch": 26.47, |
| 12714 | "learning_rate": 0.00014331778425655974, |
| 12715 | "loss": 0.0292, |
| 12716 | "step": 18420 |
| 12717 | }, |
| 12718 | { |
| 12719 | "epoch": 26.48, |
| 12720 | "learning_rate": 0.00014323032069970843, |
| 12721 | "loss": 0.0394, |
| 12722 | "step": 18430 |
| 12723 | }, |
| 12724 | { |
| 12725 | "epoch": 26.49, |
| 12726 | "learning_rate": 0.00014314285714285712, |
| 12727 | "loss": 0.0318, |
| 12728 | "step": 18440 |
| 12729 | }, |
| 12730 | { |
| 12731 | "epoch": 26.51, |
| 12732 | "learning_rate": 0.00014305539358600583, |
| 12733 | "loss": 0.0401, |
| 12734 | "step": 18450 |
| 12735 | }, |
| 12736 | { |
| 12737 | "epoch": 26.52, |
| 12738 | "learning_rate": 0.0001429679300291545, |
| 12739 | "loss": 0.0361, |
| 12740 | "step": 18460 |
| 12741 | }, |
| 12742 | { |
| 12743 | "epoch": 26.54, |
| 12744 | "learning_rate": 0.00014288046647230318, |
| 12745 | "loss": 0.0359, |
| 12746 | "step": 18470 |
| 12747 | }, |
| 12748 | { |
| 12749 | "epoch": 26.55, |
| 12750 | "learning_rate": 0.00014279300291545187, |
| 12751 | "loss": 0.0395, |
| 12752 | "step": 18480 |
| 12753 | }, |
| 12754 | { |
| 12755 | "epoch": 26.57, |
| 12756 | "learning_rate": 0.00014270553935860058, |
| 12757 | "loss": 0.0381, |
| 12758 | "step": 18490 |
| 12759 | }, |
| 12760 | { |
| 12761 | "epoch": 26.58, |
| 12762 | "learning_rate": 0.00014261807580174927, |
| 12763 | "loss": 0.0346, |
| 12764 | "step": 18500 |
| 12765 | }, |
| 12766 | { |
| 12767 | "epoch": 26.58, |
| 12768 | "eval_loss": 0.1381981372833252, |
| 12769 | "eval_runtime": 40.4312, |
| 12770 | "eval_samples_per_second": 11.303, |
| 12771 | "eval_steps_per_second": 1.435, |
| 12772 | "eval_wer": 0.13627465743110978, |
| 12773 | "step": 18500 |
| 12774 | }, |
| 12775 | { |
| 12776 | "epoch": 26.59, |
| 12777 | "learning_rate": 0.00014253061224489793, |
| 12778 | "loss": 0.0421, |
| 12779 | "step": 18510 |
| 12780 | }, |
| 12781 | { |
| 12782 | "epoch": 26.61, |
| 12783 | "learning_rate": 0.00014244314868804662, |
| 12784 | "loss": 0.0403, |
| 12785 | "step": 18520 |
| 12786 | }, |
| 12787 | { |
| 12788 | "epoch": 26.62, |
| 12789 | "learning_rate": 0.00014235568513119534, |
| 12790 | "loss": 0.0424, |
| 12791 | "step": 18530 |
| 12792 | }, |
| 12793 | { |
| 12794 | "epoch": 26.64, |
| 12795 | "learning_rate": 0.00014226822157434402, |
| 12796 | "loss": 0.036, |
| 12797 | "step": 18540 |
| 12798 | }, |
| 12799 | { |
| 12800 | "epoch": 26.65, |
| 12801 | "learning_rate": 0.00014218075801749268, |
| 12802 | "loss": 0.0376, |
| 12803 | "step": 18550 |
| 12804 | }, |
| 12805 | { |
| 12806 | "epoch": 26.67, |
| 12807 | "learning_rate": 0.00014209329446064137, |
| 12808 | "loss": 0.0429, |
| 12809 | "step": 18560 |
| 12810 | }, |
| 12811 | { |
| 12812 | "epoch": 26.68, |
| 12813 | "learning_rate": 0.0001420058309037901, |
| 12814 | "loss": 0.0338, |
| 12815 | "step": 18570 |
| 12816 | }, |
| 12817 | { |
| 12818 | "epoch": 26.7, |
| 12819 | "learning_rate": 0.00014191836734693878, |
| 12820 | "loss": 0.0379, |
| 12821 | "step": 18580 |
| 12822 | }, |
| 12823 | { |
| 12824 | "epoch": 26.71, |
| 12825 | "learning_rate": 0.00014183090379008746, |
| 12826 | "loss": 0.0286, |
| 12827 | "step": 18590 |
| 12828 | }, |
| 12829 | { |
| 12830 | "epoch": 26.72, |
| 12831 | "learning_rate": 0.00014174344023323612, |
| 12832 | "loss": 0.0483, |
| 12833 | "step": 18600 |
| 12834 | }, |
| 12835 | { |
| 12836 | "epoch": 26.72, |
| 12837 | "eval_loss": 0.13980348408222198, |
| 12838 | "eval_runtime": 40.3916, |
| 12839 | "eval_samples_per_second": 11.314, |
| 12840 | "eval_steps_per_second": 1.436, |
| 12841 | "eval_wer": 0.14018973046227978, |
| 12842 | "step": 18600 |
| 12843 | }, |
| 12844 | { |
| 12845 | "epoch": 26.74, |
| 12846 | "learning_rate": 0.0001416559766763848, |
| 12847 | "loss": 0.0362, |
| 12848 | "step": 18610 |
| 12849 | }, |
| 12850 | { |
| 12851 | "epoch": 26.75, |
| 12852 | "learning_rate": 0.00014156851311953353, |
| 12853 | "loss": 0.0378, |
| 12854 | "step": 18620 |
| 12855 | }, |
| 12856 | { |
| 12857 | "epoch": 26.77, |
| 12858 | "learning_rate": 0.00014148104956268222, |
| 12859 | "loss": 0.0406, |
| 12860 | "step": 18630 |
| 12861 | }, |
| 12862 | { |
| 12863 | "epoch": 26.78, |
| 12864 | "learning_rate": 0.00014139358600583088, |
| 12865 | "loss": 0.0332, |
| 12866 | "step": 18640 |
| 12867 | }, |
| 12868 | { |
| 12869 | "epoch": 26.8, |
| 12870 | "learning_rate": 0.00014130612244897956, |
| 12871 | "loss": 0.0361, |
| 12872 | "step": 18650 |
| 12873 | }, |
| 12874 | { |
| 12875 | "epoch": 26.81, |
| 12876 | "learning_rate": 0.00014121865889212828, |
| 12877 | "loss": 0.0279, |
| 12878 | "step": 18660 |
| 12879 | }, |
| 12880 | { |
| 12881 | "epoch": 26.82, |
| 12882 | "learning_rate": 0.00014113119533527697, |
| 12883 | "loss": 0.025, |
| 12884 | "step": 18670 |
| 12885 | }, |
| 12886 | { |
| 12887 | "epoch": 26.84, |
| 12888 | "learning_rate": 0.00014104373177842565, |
| 12889 | "loss": 0.0405, |
| 12890 | "step": 18680 |
| 12891 | }, |
| 12892 | { |
| 12893 | "epoch": 26.85, |
| 12894 | "learning_rate": 0.00014095626822157432, |
| 12895 | "loss": 0.04, |
| 12896 | "step": 18690 |
| 12897 | }, |
| 12898 | { |
| 12899 | "epoch": 26.87, |
| 12900 | "learning_rate": 0.00014086880466472303, |
| 12901 | "loss": 0.0377, |
| 12902 | "step": 18700 |
| 12903 | }, |
| 12904 | { |
| 12905 | "epoch": 26.87, |
| 12906 | "eval_loss": 0.13871943950653076, |
| 12907 | "eval_runtime": 40.3957, |
| 12908 | "eval_samples_per_second": 11.313, |
| 12909 | "eval_steps_per_second": 1.436, |
| 12910 | "eval_wer": 0.14034031019424786, |
| 12911 | "step": 18700 |
| 12912 | }, |
| 12913 | { |
| 12914 | "epoch": 26.88, |
| 12915 | "learning_rate": 0.00014078134110787172, |
| 12916 | "loss": 0.0424, |
| 12917 | "step": 18710 |
| 12918 | }, |
| 12919 | { |
| 12920 | "epoch": 26.9, |
| 12921 | "learning_rate": 0.0001406938775510204, |
| 12922 | "loss": 0.0277, |
| 12923 | "step": 18720 |
| 12924 | }, |
| 12925 | { |
| 12926 | "epoch": 26.91, |
| 12927 | "learning_rate": 0.00014060641399416907, |
| 12928 | "loss": 0.0386, |
| 12929 | "step": 18730 |
| 12930 | }, |
| 12931 | { |
| 12932 | "epoch": 26.93, |
| 12933 | "learning_rate": 0.00014051895043731775, |
| 12934 | "loss": 0.0378, |
| 12935 | "step": 18740 |
| 12936 | }, |
| 12937 | { |
| 12938 | "epoch": 26.94, |
| 12939 | "learning_rate": 0.00014043148688046647, |
| 12940 | "loss": 0.0342, |
| 12941 | "step": 18750 |
| 12942 | }, |
| 12943 | { |
| 12944 | "epoch": 26.95, |
| 12945 | "learning_rate": 0.00014034402332361516, |
| 12946 | "loss": 0.0389, |
| 12947 | "step": 18760 |
| 12948 | }, |
| 12949 | { |
| 12950 | "epoch": 26.97, |
| 12951 | "learning_rate": 0.00014025655976676385, |
| 12952 | "loss": 0.0339, |
| 12953 | "step": 18770 |
| 12954 | }, |
| 12955 | { |
| 12956 | "epoch": 26.98, |
| 12957 | "learning_rate": 0.0001401690962099125, |
| 12958 | "loss": 0.0336, |
| 12959 | "step": 18780 |
| 12960 | }, |
| 12961 | { |
| 12962 | "epoch": 27.0, |
| 12963 | "learning_rate": 0.00014008163265306122, |
| 12964 | "loss": 0.0383, |
| 12965 | "step": 18790 |
| 12966 | }, |
| 12967 | { |
| 12968 | "epoch": 27.01, |
| 12969 | "learning_rate": 0.0001399941690962099, |
| 12970 | "loss": 0.0322, |
| 12971 | "step": 18800 |
| 12972 | }, |
| 12973 | { |
| 12974 | "epoch": 27.01, |
| 12975 | "eval_loss": 0.1367408037185669, |
| 12976 | "eval_runtime": 40.3646, |
| 12977 | "eval_samples_per_second": 11.322, |
| 12978 | "eval_steps_per_second": 1.437, |
| 12979 | "eval_wer": 0.13371480198765245, |
| 12980 | "step": 18800 |
| 12981 | }, |
| 12982 | { |
| 12983 | "epoch": 27.03, |
| 12984 | "learning_rate": 0.0001399067055393586, |
| 12985 | "loss": 0.0354, |
| 12986 | "step": 18810 |
| 12987 | }, |
| 12988 | { |
| 12989 | "epoch": 27.04, |
| 12990 | "learning_rate": 0.00013981924198250726, |
| 12991 | "loss": 0.0372, |
| 12992 | "step": 18820 |
| 12993 | }, |
| 12994 | { |
| 12995 | "epoch": 27.05, |
| 12996 | "learning_rate": 0.00013973177842565597, |
| 12997 | "loss": 0.0382, |
| 12998 | "step": 18830 |
| 12999 | }, |
| 13000 | { |
| 13001 | "epoch": 27.07, |
| 13002 | "learning_rate": 0.00013964431486880466, |
| 13003 | "loss": 0.0437, |
| 13004 | "step": 18840 |
| 13005 | }, |
| 13006 | { |
| 13007 | "epoch": 27.08, |
| 13008 | "learning_rate": 0.00013955685131195335, |
| 13009 | "loss": 0.0413, |
| 13010 | "step": 18850 |
| 13011 | }, |
| 13012 | { |
| 13013 | "epoch": 27.1, |
| 13014 | "learning_rate": 0.00013946938775510204, |
| 13015 | "loss": 0.0347, |
| 13016 | "step": 18860 |
| 13017 | }, |
| 13018 | { |
| 13019 | "epoch": 27.11, |
| 13020 | "learning_rate": 0.0001393819241982507, |
| 13021 | "loss": 0.0434, |
| 13022 | "step": 18870 |
| 13023 | }, |
| 13024 | { |
| 13025 | "epoch": 27.13, |
| 13026 | "learning_rate": 0.0001392944606413994, |
| 13027 | "loss": 0.037, |
| 13028 | "step": 18880 |
| 13029 | }, |
| 13030 | { |
| 13031 | "epoch": 27.14, |
| 13032 | "learning_rate": 0.0001392069970845481, |
| 13033 | "loss": 0.0355, |
| 13034 | "step": 18890 |
| 13035 | }, |
| 13036 | { |
| 13037 | "epoch": 27.16, |
| 13038 | "learning_rate": 0.0001391195335276968, |
| 13039 | "loss": 0.0487, |
| 13040 | "step": 18900 |
| 13041 | }, |
| 13042 | { |
| 13043 | "epoch": 27.16, |
| 13044 | "eval_loss": 0.13838794827461243, |
| 13045 | "eval_runtime": 40.1371, |
| 13046 | "eval_samples_per_second": 11.386, |
| 13047 | "eval_steps_per_second": 1.445, |
| 13048 | "eval_wer": 0.140641469658184, |
| 13049 | "step": 18900 |
| 13050 | }, |
| 13051 | { |
| 13052 | "epoch": 27.17, |
| 13053 | "learning_rate": 0.00013903206997084545, |
| 13054 | "loss": 0.0444, |
| 13055 | "step": 18910 |
| 13056 | }, |
| 13057 | { |
| 13058 | "epoch": 27.18, |
| 13059 | "learning_rate": 0.00013894460641399416, |
| 13060 | "loss": 0.0459, |
| 13061 | "step": 18920 |
| 13062 | }, |
| 13063 | { |
| 13064 | "epoch": 27.2, |
| 13065 | "learning_rate": 0.00013885714285714285, |
| 13066 | "loss": 0.0453, |
| 13067 | "step": 18930 |
| 13068 | }, |
| 13069 | { |
| 13070 | "epoch": 27.21, |
| 13071 | "learning_rate": 0.00013876967930029154, |
| 13072 | "loss": 0.0403, |
| 13073 | "step": 18940 |
| 13074 | }, |
| 13075 | { |
| 13076 | "epoch": 27.23, |
| 13077 | "learning_rate": 0.00013869096209912535, |
| 13078 | "loss": 0.0487, |
| 13079 | "step": 18950 |
| 13080 | }, |
| 13081 | { |
| 13082 | "epoch": 27.24, |
| 13083 | "learning_rate": 0.00013860349854227403, |
| 13084 | "loss": 0.0404, |
| 13085 | "step": 18960 |
| 13086 | }, |
| 13087 | { |
| 13088 | "epoch": 27.26, |
| 13089 | "learning_rate": 0.00013851603498542275, |
| 13090 | "loss": 0.0355, |
| 13091 | "step": 18970 |
| 13092 | }, |
| 13093 | { |
| 13094 | "epoch": 27.27, |
| 13095 | "learning_rate": 0.0001384285714285714, |
| 13096 | "loss": 0.0371, |
| 13097 | "step": 18980 |
| 13098 | }, |
| 13099 | { |
| 13100 | "epoch": 27.28, |
| 13101 | "learning_rate": 0.0001383411078717201, |
| 13102 | "loss": 0.03, |
| 13103 | "step": 18990 |
| 13104 | }, |
| 13105 | { |
| 13106 | "epoch": 27.3, |
| 13107 | "learning_rate": 0.00013825364431486878, |
| 13108 | "loss": 0.0368, |
| 13109 | "step": 19000 |
| 13110 | }, |
| 13111 | { |
| 13112 | "epoch": 27.3, |
| 13113 | "eval_loss": 0.14037658274173737, |
| 13114 | "eval_runtime": 40.5049, |
| 13115 | "eval_samples_per_second": 11.283, |
| 13116 | "eval_steps_per_second": 1.432, |
| 13117 | "eval_wer": 0.14034031019424786, |
| 13118 | "step": 19000 |
| 13119 | }, |
| 13120 | { |
| 13121 | "epoch": 27.31, |
| 13122 | "learning_rate": 0.00013816618075801747, |
| 13123 | "loss": 0.0412, |
| 13124 | "step": 19010 |
| 13125 | }, |
| 13126 | { |
| 13127 | "epoch": 27.33, |
| 13128 | "learning_rate": 0.00013807871720116616, |
| 13129 | "loss": 0.0392, |
| 13130 | "step": 19020 |
| 13131 | }, |
| 13132 | { |
| 13133 | "epoch": 27.34, |
| 13134 | "learning_rate": 0.00013799125364431485, |
| 13135 | "loss": 0.0418, |
| 13136 | "step": 19030 |
| 13137 | }, |
| 13138 | { |
| 13139 | "epoch": 27.36, |
| 13140 | "learning_rate": 0.00013790379008746354, |
| 13141 | "loss": 0.0365, |
| 13142 | "step": 19040 |
| 13143 | }, |
| 13144 | { |
| 13145 | "epoch": 27.37, |
| 13146 | "learning_rate": 0.00013781632653061222, |
| 13147 | "loss": 0.0397, |
| 13148 | "step": 19050 |
| 13149 | }, |
| 13150 | { |
| 13151 | "epoch": 27.39, |
| 13152 | "learning_rate": 0.00013772886297376094, |
| 13153 | "loss": 0.039, |
| 13154 | "step": 19060 |
| 13155 | }, |
| 13156 | { |
| 13157 | "epoch": 27.4, |
| 13158 | "learning_rate": 0.0001376413994169096, |
| 13159 | "loss": 0.0391, |
| 13160 | "step": 19070 |
| 13161 | }, |
| 13162 | { |
| 13163 | "epoch": 27.41, |
| 13164 | "learning_rate": 0.0001375539358600583, |
| 13165 | "loss": 0.0402, |
| 13166 | "step": 19080 |
| 13167 | }, |
| 13168 | { |
| 13169 | "epoch": 27.43, |
| 13170 | "learning_rate": 0.00013746647230320698, |
| 13171 | "loss": 0.0334, |
| 13172 | "step": 19090 |
| 13173 | }, |
| 13174 | { |
| 13175 | "epoch": 27.44, |
| 13176 | "learning_rate": 0.0001373790087463557, |
| 13177 | "loss": 0.0418, |
| 13178 | "step": 19100 |
| 13179 | }, |
| 13180 | { |
| 13181 | "epoch": 27.44, |
| 13182 | "eval_loss": 0.13838353753089905, |
| 13183 | "eval_runtime": 40.2187, |
| 13184 | "eval_samples_per_second": 11.363, |
| 13185 | "eval_steps_per_second": 1.442, |
| 13186 | "eval_wer": 0.14079204939015208, |
| 13187 | "step": 19100 |
| 13188 | }, |
| 13189 | { |
| 13190 | "epoch": 27.46, |
| 13191 | "learning_rate": 0.00013729154518950435, |
| 13192 | "loss": 0.0298, |
| 13193 | "step": 19110 |
| 13194 | }, |
| 13195 | { |
| 13196 | "epoch": 27.47, |
| 13197 | "learning_rate": 0.00013720408163265304, |
| 13198 | "loss": 0.0382, |
| 13199 | "step": 19120 |
| 13200 | }, |
| 13201 | { |
| 13202 | "epoch": 27.49, |
| 13203 | "learning_rate": 0.00013711661807580173, |
| 13204 | "loss": 0.0394, |
| 13205 | "step": 19130 |
| 13206 | }, |
| 13207 | { |
| 13208 | "epoch": 27.5, |
| 13209 | "learning_rate": 0.00013702915451895044, |
| 13210 | "loss": 0.0341, |
| 13211 | "step": 19140 |
| 13212 | }, |
| 13213 | { |
| 13214 | "epoch": 27.51, |
| 13215 | "learning_rate": 0.00013694169096209913, |
| 13216 | "loss": 0.0382, |
| 13217 | "step": 19150 |
| 13218 | }, |
| 13219 | { |
| 13220 | "epoch": 27.53, |
| 13221 | "learning_rate": 0.0001368542274052478, |
| 13222 | "loss": 0.0379, |
| 13223 | "step": 19160 |
| 13224 | }, |
| 13225 | { |
| 13226 | "epoch": 27.54, |
| 13227 | "learning_rate": 0.00013676676384839648, |
| 13228 | "loss": 0.0357, |
| 13229 | "step": 19170 |
| 13230 | }, |
| 13231 | { |
| 13232 | "epoch": 27.56, |
| 13233 | "learning_rate": 0.00013667930029154517, |
| 13234 | "loss": 0.0358, |
| 13235 | "step": 19180 |
| 13236 | }, |
| 13237 | { |
| 13238 | "epoch": 27.57, |
| 13239 | "learning_rate": 0.00013659183673469388, |
| 13240 | "loss": 0.031, |
| 13241 | "step": 19190 |
| 13242 | }, |
| 13243 | { |
| 13244 | "epoch": 27.59, |
| 13245 | "learning_rate": 0.00013650437317784254, |
| 13246 | "loss": 0.0332, |
| 13247 | "step": 19200 |
| 13248 | }, |
| 13249 | { |
| 13250 | "epoch": 27.59, |
| 13251 | "eval_loss": 0.14226850867271423, |
| 13252 | "eval_runtime": 40.214, |
| 13253 | "eval_samples_per_second": 11.364, |
| 13254 | "eval_steps_per_second": 1.442, |
| 13255 | "eval_wer": 0.14154494804999246, |
| 13256 | "step": 19200 |
| 13257 | }, |
| 13258 | { |
| 13259 | "epoch": 27.6, |
| 13260 | "learning_rate": 0.00013641690962099123, |
| 13261 | "loss": 0.0347, |
| 13262 | "step": 19210 |
| 13263 | }, |
| 13264 | { |
| 13265 | "epoch": 27.61, |
| 13266 | "learning_rate": 0.00013632944606413992, |
| 13267 | "loss": 0.0392, |
| 13268 | "step": 19220 |
| 13269 | }, |
| 13270 | { |
| 13271 | "epoch": 27.63, |
| 13272 | "learning_rate": 0.00013624198250728863, |
| 13273 | "loss": 0.0424, |
| 13274 | "step": 19230 |
| 13275 | }, |
| 13276 | { |
| 13277 | "epoch": 27.64, |
| 13278 | "learning_rate": 0.00013615451895043732, |
| 13279 | "loss": 0.0322, |
| 13280 | "step": 19240 |
| 13281 | }, |
| 13282 | { |
| 13283 | "epoch": 27.66, |
| 13284 | "learning_rate": 0.00013606705539358598, |
| 13285 | "loss": 0.0395, |
| 13286 | "step": 19250 |
| 13287 | }, |
| 13288 | { |
| 13289 | "epoch": 27.67, |
| 13290 | "learning_rate": 0.00013597959183673467, |
| 13291 | "loss": 0.0338, |
| 13292 | "step": 19260 |
| 13293 | }, |
| 13294 | { |
| 13295 | "epoch": 27.69, |
| 13296 | "learning_rate": 0.00013589212827988339, |
| 13297 | "loss": 0.0334, |
| 13298 | "step": 19270 |
| 13299 | }, |
| 13300 | { |
| 13301 | "epoch": 27.7, |
| 13302 | "learning_rate": 0.00013580466472303207, |
| 13303 | "loss": 0.0409, |
| 13304 | "step": 19280 |
| 13305 | }, |
| 13306 | { |
| 13307 | "epoch": 27.72, |
| 13308 | "learning_rate": 0.00013571720116618073, |
| 13309 | "loss": 0.0358, |
| 13310 | "step": 19290 |
| 13311 | }, |
| 13312 | { |
| 13313 | "epoch": 27.73, |
| 13314 | "learning_rate": 0.00013562973760932942, |
| 13315 | "loss": 0.046, |
| 13316 | "step": 19300 |
| 13317 | }, |
| 13318 | { |
| 13319 | "epoch": 27.73, |
| 13320 | "eval_loss": 0.13767357170581818, |
| 13321 | "eval_runtime": 40.1195, |
| 13322 | "eval_samples_per_second": 11.391, |
| 13323 | "eval_steps_per_second": 1.446, |
| 13324 | "eval_wer": 0.13657581689504592, |
| 13325 | "step": 19300 |
| 13326 | }, |
| 13327 | { |
| 13328 | "epoch": 27.74, |
| 13329 | "learning_rate": 0.0001355422740524781, |
| 13330 | "loss": 0.039, |
| 13331 | "step": 19310 |
| 13332 | }, |
| 13333 | { |
| 13334 | "epoch": 27.76, |
| 13335 | "learning_rate": 0.00013545481049562682, |
| 13336 | "loss": 0.034, |
| 13337 | "step": 19320 |
| 13338 | }, |
| 13339 | { |
| 13340 | "epoch": 27.77, |
| 13341 | "learning_rate": 0.0001353673469387755, |
| 13342 | "loss": 0.0393, |
| 13343 | "step": 19330 |
| 13344 | }, |
| 13345 | { |
| 13346 | "epoch": 27.79, |
| 13347 | "learning_rate": 0.00013527988338192417, |
| 13348 | "loss": 0.0351, |
| 13349 | "step": 19340 |
| 13350 | }, |
| 13351 | { |
| 13352 | "epoch": 27.8, |
| 13353 | "learning_rate": 0.00013519241982507286, |
| 13354 | "loss": 0.0412, |
| 13355 | "step": 19350 |
| 13356 | }, |
| 13357 | { |
| 13358 | "epoch": 27.82, |
| 13359 | "learning_rate": 0.00013510495626822158, |
| 13360 | "loss": 0.03, |
| 13361 | "step": 19360 |
| 13362 | }, |
| 13363 | { |
| 13364 | "epoch": 27.83, |
| 13365 | "learning_rate": 0.00013501749271137026, |
| 13366 | "loss": 0.0443, |
| 13367 | "step": 19370 |
| 13368 | }, |
| 13369 | { |
| 13370 | "epoch": 27.84, |
| 13371 | "learning_rate": 0.00013493002915451892, |
| 13372 | "loss": 0.0352, |
| 13373 | "step": 19380 |
| 13374 | }, |
| 13375 | { |
| 13376 | "epoch": 27.86, |
| 13377 | "learning_rate": 0.0001348425655976676, |
| 13378 | "loss": 0.0307, |
| 13379 | "step": 19390 |
| 13380 | }, |
| 13381 | { |
| 13382 | "epoch": 27.87, |
| 13383 | "learning_rate": 0.00013475510204081633, |
| 13384 | "loss": 0.0525, |
| 13385 | "step": 19400 |
| 13386 | }, |
| 13387 | { |
| 13388 | "epoch": 27.87, |
| 13389 | "eval_loss": 0.13637852668762207, |
| 13390 | "eval_runtime": 40.0608, |
| 13391 | "eval_samples_per_second": 11.408, |
| 13392 | "eval_steps_per_second": 1.448, |
| 13393 | "eval_wer": 0.13657581689504592, |
| 13394 | "step": 19400 |
| 13395 | }, |
| 13396 | { |
| 13397 | "epoch": 27.89, |
| 13398 | "learning_rate": 0.00013467638483965013, |
| 13399 | "loss": 0.0328, |
| 13400 | "step": 19410 |
| 13401 | }, |
| 13402 | { |
| 13403 | "epoch": 27.9, |
| 13404 | "learning_rate": 0.00013458892128279882, |
| 13405 | "loss": 0.0347, |
| 13406 | "step": 19420 |
| 13407 | }, |
| 13408 | { |
| 13409 | "epoch": 27.92, |
| 13410 | "learning_rate": 0.0001345014577259475, |
| 13411 | "loss": 0.0349, |
| 13412 | "step": 19430 |
| 13413 | }, |
| 13414 | { |
| 13415 | "epoch": 27.93, |
| 13416 | "learning_rate": 0.0001344139941690962, |
| 13417 | "loss": 0.0373, |
| 13418 | "step": 19440 |
| 13419 | }, |
| 13420 | { |
| 13421 | "epoch": 27.95, |
| 13422 | "learning_rate": 0.00013432653061224488, |
| 13423 | "loss": 0.0393, |
| 13424 | "step": 19450 |
| 13425 | }, |
| 13426 | { |
| 13427 | "epoch": 27.96, |
| 13428 | "learning_rate": 0.00013423906705539357, |
| 13429 | "loss": 0.0351, |
| 13430 | "step": 19460 |
| 13431 | }, |
| 13432 | { |
| 13433 | "epoch": 27.97, |
| 13434 | "learning_rate": 0.00013415160349854226, |
| 13435 | "loss": 0.0375, |
| 13436 | "step": 19470 |
| 13437 | }, |
| 13438 | { |
| 13439 | "epoch": 27.99, |
| 13440 | "learning_rate": 0.00013406413994169095, |
| 13441 | "loss": 0.0385, |
| 13442 | "step": 19480 |
| 13443 | }, |
| 13444 | { |
| 13445 | "epoch": 28.0, |
| 13446 | "learning_rate": 0.00013397667638483964, |
| 13447 | "loss": 0.0372, |
| 13448 | "step": 19490 |
| 13449 | }, |
| 13450 | { |
| 13451 | "epoch": 28.02, |
| 13452 | "learning_rate": 0.00013388921282798832, |
| 13453 | "loss": 0.0349, |
| 13454 | "step": 19500 |
| 13455 | }, |
| 13456 | { |
| 13457 | "epoch": 28.02, |
| 13458 | "eval_loss": 0.1400323212146759, |
| 13459 | "eval_runtime": 40.3762, |
| 13460 | "eval_samples_per_second": 11.319, |
| 13461 | "eval_steps_per_second": 1.436, |
| 13462 | "eval_wer": 0.13627465743110978, |
| 13463 | "step": 19500 |
| 13464 | }, |
| 13465 | { |
| 13466 | "epoch": 28.03, |
| 13467 | "learning_rate": 0.000133801749271137, |
| 13468 | "loss": 0.0333, |
| 13469 | "step": 19510 |
| 13470 | }, |
| 13471 | { |
| 13472 | "epoch": 28.05, |
| 13473 | "learning_rate": 0.0001337142857142857, |
| 13474 | "loss": 0.0414, |
| 13475 | "step": 19520 |
| 13476 | }, |
| 13477 | { |
| 13478 | "epoch": 28.06, |
| 13479 | "learning_rate": 0.0001336268221574344, |
| 13480 | "loss": 0.037, |
| 13481 | "step": 19530 |
| 13482 | }, |
| 13483 | { |
| 13484 | "epoch": 28.07, |
| 13485 | "learning_rate": 0.00013353935860058308, |
| 13486 | "loss": 0.0319, |
| 13487 | "step": 19540 |
| 13488 | }, |
| 13489 | { |
| 13490 | "epoch": 28.09, |
| 13491 | "learning_rate": 0.00013345189504373176, |
| 13492 | "loss": 0.0366, |
| 13493 | "step": 19550 |
| 13494 | }, |
| 13495 | { |
| 13496 | "epoch": 28.1, |
| 13497 | "learning_rate": 0.00013336443148688045, |
| 13498 | "loss": 0.0377, |
| 13499 | "step": 19560 |
| 13500 | }, |
| 13501 | { |
| 13502 | "epoch": 28.12, |
| 13503 | "learning_rate": 0.00013327696793002914, |
| 13504 | "loss": 0.0317, |
| 13505 | "step": 19570 |
| 13506 | }, |
| 13507 | { |
| 13508 | "epoch": 28.13, |
| 13509 | "learning_rate": 0.00013318950437317783, |
| 13510 | "loss": 0.0347, |
| 13511 | "step": 19580 |
| 13512 | }, |
| 13513 | { |
| 13514 | "epoch": 28.15, |
| 13515 | "learning_rate": 0.00013310204081632652, |
| 13516 | "loss": 0.0322, |
| 13517 | "step": 19590 |
| 13518 | }, |
| 13519 | { |
| 13520 | "epoch": 28.16, |
| 13521 | "learning_rate": 0.0001330145772594752, |
| 13522 | "loss": 0.0375, |
| 13523 | "step": 19600 |
| 13524 | }, |
| 13525 | { |
| 13526 | "epoch": 28.16, |
| 13527 | "eval_loss": 0.14294388890266418, |
| 13528 | "eval_runtime": 40.0691, |
| 13529 | "eval_samples_per_second": 11.405, |
| 13530 | "eval_steps_per_second": 1.447, |
| 13531 | "eval_wer": 0.13793103448275862, |
| 13532 | "step": 19600 |
| 13533 | }, |
| 13534 | { |
| 13535 | "epoch": 28.18, |
| 13536 | "learning_rate": 0.0001329271137026239, |
| 13537 | "loss": 0.0404, |
| 13538 | "step": 19610 |
| 13539 | }, |
| 13540 | { |
| 13541 | "epoch": 28.19, |
| 13542 | "learning_rate": 0.00013283965014577258, |
| 13543 | "loss": 0.0446, |
| 13544 | "step": 19620 |
| 13545 | }, |
| 13546 | { |
| 13547 | "epoch": 28.2, |
| 13548 | "learning_rate": 0.00013275218658892127, |
| 13549 | "loss": 0.0307, |
| 13550 | "step": 19630 |
| 13551 | }, |
| 13552 | { |
| 13553 | "epoch": 28.22, |
| 13554 | "learning_rate": 0.00013266472303206996, |
| 13555 | "loss": 0.0413, |
| 13556 | "step": 19640 |
| 13557 | }, |
| 13558 | { |
| 13559 | "epoch": 28.23, |
| 13560 | "learning_rate": 0.00013257725947521864, |
| 13561 | "loss": 0.043, |
| 13562 | "step": 19650 |
| 13563 | }, |
| 13564 | { |
| 13565 | "epoch": 28.25, |
| 13566 | "learning_rate": 0.00013248979591836733, |
| 13567 | "loss": 0.0303, |
| 13568 | "step": 19660 |
| 13569 | }, |
| 13570 | { |
| 13571 | "epoch": 28.26, |
| 13572 | "learning_rate": 0.00013240233236151602, |
| 13573 | "loss": 0.0339, |
| 13574 | "step": 19670 |
| 13575 | }, |
| 13576 | { |
| 13577 | "epoch": 28.28, |
| 13578 | "learning_rate": 0.0001323148688046647, |
| 13579 | "loss": 0.032, |
| 13580 | "step": 19680 |
| 13581 | }, |
| 13582 | { |
| 13583 | "epoch": 28.29, |
| 13584 | "learning_rate": 0.0001322274052478134, |
| 13585 | "loss": 0.0403, |
| 13586 | "step": 19690 |
| 13587 | }, |
| 13588 | { |
| 13589 | "epoch": 28.3, |
| 13590 | "learning_rate": 0.00013213994169096208, |
| 13591 | "loss": 0.0315, |
| 13592 | "step": 19700 |
| 13593 | }, |
| 13594 | { |
| 13595 | "epoch": 28.3, |
| 13596 | "eval_loss": 0.134770467877388, |
| 13597 | "eval_runtime": 40.3128, |
| 13598 | "eval_samples_per_second": 11.336, |
| 13599 | "eval_steps_per_second": 1.439, |
| 13600 | "eval_wer": 0.13401596145158862, |
| 13601 | "step": 19700 |
| 13602 | }, |
| 13603 | { |
| 13604 | "epoch": 28.32, |
| 13605 | "learning_rate": 0.00013205247813411077, |
| 13606 | "loss": 0.0327, |
| 13607 | "step": 19710 |
| 13608 | }, |
| 13609 | { |
| 13610 | "epoch": 28.33, |
| 13611 | "learning_rate": 0.00013196501457725946, |
| 13612 | "loss": 0.0407, |
| 13613 | "step": 19720 |
| 13614 | }, |
| 13615 | { |
| 13616 | "epoch": 28.35, |
| 13617 | "learning_rate": 0.00013187755102040815, |
| 13618 | "loss": 0.0304, |
| 13619 | "step": 19730 |
| 13620 | }, |
| 13621 | { |
| 13622 | "epoch": 28.36, |
| 13623 | "learning_rate": 0.00013179008746355683, |
| 13624 | "loss": 0.0445, |
| 13625 | "step": 19740 |
| 13626 | }, |
| 13627 | { |
| 13628 | "epoch": 28.38, |
| 13629 | "learning_rate": 0.00013170262390670552, |
| 13630 | "loss": 0.0361, |
| 13631 | "step": 19750 |
| 13632 | }, |
| 13633 | { |
| 13634 | "epoch": 28.39, |
| 13635 | "learning_rate": 0.0001316151603498542, |
| 13636 | "loss": 0.0341, |
| 13637 | "step": 19760 |
| 13638 | }, |
| 13639 | { |
| 13640 | "epoch": 28.41, |
| 13641 | "learning_rate": 0.0001315276967930029, |
| 13642 | "loss": 0.0342, |
| 13643 | "step": 19770 |
| 13644 | }, |
| 13645 | { |
| 13646 | "epoch": 28.42, |
| 13647 | "learning_rate": 0.00013144023323615159, |
| 13648 | "loss": 0.0297, |
| 13649 | "step": 19780 |
| 13650 | }, |
| 13651 | { |
| 13652 | "epoch": 28.43, |
| 13653 | "learning_rate": 0.00013135276967930027, |
| 13654 | "loss": 0.0251, |
| 13655 | "step": 19790 |
| 13656 | }, |
| 13657 | { |
| 13658 | "epoch": 28.45, |
| 13659 | "learning_rate": 0.00013126530612244896, |
| 13660 | "loss": 0.0329, |
| 13661 | "step": 19800 |
| 13662 | }, |
| 13663 | { |
| 13664 | "epoch": 28.45, |
| 13665 | "eval_loss": 0.13576379418373108, |
| 13666 | "eval_runtime": 40.3207, |
| 13667 | "eval_samples_per_second": 11.334, |
| 13668 | "eval_steps_per_second": 1.438, |
| 13669 | "eval_wer": 0.13296190332781208, |
| 13670 | "step": 19800 |
| 13671 | }, |
| 13672 | { |
| 13673 | "epoch": 28.46, |
| 13674 | "learning_rate": 0.00013117784256559765, |
| 13675 | "loss": 0.0331, |
| 13676 | "step": 19810 |
| 13677 | }, |
| 13678 | { |
| 13679 | "epoch": 28.48, |
| 13680 | "learning_rate": 0.00013109037900874634, |
| 13681 | "loss": 0.0456, |
| 13682 | "step": 19820 |
| 13683 | }, |
| 13684 | { |
| 13685 | "epoch": 28.49, |
| 13686 | "learning_rate": 0.00013100291545189503, |
| 13687 | "loss": 0.0336, |
| 13688 | "step": 19830 |
| 13689 | }, |
| 13690 | { |
| 13691 | "epoch": 28.51, |
| 13692 | "learning_rate": 0.00013091545189504374, |
| 13693 | "loss": 0.0333, |
| 13694 | "step": 19840 |
| 13695 | }, |
| 13696 | { |
| 13697 | "epoch": 28.52, |
| 13698 | "learning_rate": 0.0001308279883381924, |
| 13699 | "loss": 0.0321, |
| 13700 | "step": 19850 |
| 13701 | }, |
| 13702 | { |
| 13703 | "epoch": 28.53, |
| 13704 | "learning_rate": 0.0001307405247813411, |
| 13705 | "loss": 0.0279, |
| 13706 | "step": 19860 |
| 13707 | }, |
| 13708 | { |
| 13709 | "epoch": 28.55, |
| 13710 | "learning_rate": 0.00013065306122448978, |
| 13711 | "loss": 0.0321, |
| 13712 | "step": 19870 |
| 13713 | }, |
| 13714 | { |
| 13715 | "epoch": 28.56, |
| 13716 | "learning_rate": 0.00013056559766763846, |
| 13717 | "loss": 0.0329, |
| 13718 | "step": 19880 |
| 13719 | }, |
| 13720 | { |
| 13721 | "epoch": 28.58, |
| 13722 | "learning_rate": 0.00013047813411078715, |
| 13723 | "loss": 0.0339, |
| 13724 | "step": 19890 |
| 13725 | }, |
| 13726 | { |
| 13727 | "epoch": 28.59, |
| 13728 | "learning_rate": 0.00013039067055393584, |
| 13729 | "loss": 0.0388, |
| 13730 | "step": 19900 |
| 13731 | }, |
| 13732 | { |
| 13733 | "epoch": 28.59, |
| 13734 | "eval_loss": 0.13492873311042786, |
| 13735 | "eval_runtime": 40.1943, |
| 13736 | "eval_samples_per_second": 11.37, |
| 13737 | "eval_steps_per_second": 1.443, |
| 13738 | "eval_wer": 0.13883451287456708, |
| 13739 | "step": 19900 |
| 13740 | }, |
| 13741 | { |
| 13742 | "epoch": 28.61, |
| 13743 | "learning_rate": 0.00013030320699708453, |
| 13744 | "loss": 0.029, |
| 13745 | "step": 19910 |
| 13746 | }, |
| 13747 | { |
| 13748 | "epoch": 28.62, |
| 13749 | "learning_rate": 0.00013021574344023322, |
| 13750 | "loss": 0.0425, |
| 13751 | "step": 19920 |
| 13752 | }, |
| 13753 | { |
| 13754 | "epoch": 28.64, |
| 13755 | "learning_rate": 0.00013012827988338193, |
| 13756 | "loss": 0.0335, |
| 13757 | "step": 19930 |
| 13758 | }, |
| 13759 | { |
| 13760 | "epoch": 28.65, |
| 13761 | "learning_rate": 0.0001300408163265306, |
| 13762 | "loss": 0.0396, |
| 13763 | "step": 19940 |
| 13764 | }, |
| 13765 | { |
| 13766 | "epoch": 28.66, |
| 13767 | "learning_rate": 0.00012995335276967928, |
| 13768 | "loss": 0.0384, |
| 13769 | "step": 19950 |
| 13770 | }, |
| 13771 | { |
| 13772 | "epoch": 28.68, |
| 13773 | "learning_rate": 0.00012986588921282797, |
| 13774 | "loss": 0.0332, |
| 13775 | "step": 19960 |
| 13776 | }, |
| 13777 | { |
| 13778 | "epoch": 28.69, |
| 13779 | "learning_rate": 0.00012977842565597668, |
| 13780 | "loss": 0.0479, |
| 13781 | "step": 19970 |
| 13782 | }, |
| 13783 | { |
| 13784 | "epoch": 28.71, |
| 13785 | "learning_rate": 0.00012969096209912534, |
| 13786 | "loss": 0.0391, |
| 13787 | "step": 19980 |
| 13788 | }, |
| 13789 | { |
| 13790 | "epoch": 28.72, |
| 13791 | "learning_rate": 0.00012960349854227403, |
| 13792 | "loss": 0.0411, |
| 13793 | "step": 19990 |
| 13794 | }, |
| 13795 | { |
| 13796 | "epoch": 28.74, |
| 13797 | "learning_rate": 0.00012951603498542272, |
| 13798 | "loss": 0.0337, |
| 13799 | "step": 20000 |
| 13800 | }, |
| 13801 | { |
| 13802 | "epoch": 28.74, |
| 13803 | "eval_loss": 0.1368357241153717, |
| 13804 | "eval_runtime": 40.167, |
| 13805 | "eval_samples_per_second": 11.378, |
| 13806 | "eval_steps_per_second": 1.444, |
| 13807 | "eval_wer": 0.136726396627014, |
| 13808 | "step": 20000 |
| 13809 | }, |
| 13810 | { |
| 13811 | "epoch": 28.75, |
| 13812 | "learning_rate": 0.0001294285714285714, |
| 13813 | "loss": 0.0295, |
| 13814 | "step": 20010 |
| 13815 | }, |
| 13816 | { |
| 13817 | "epoch": 28.76, |
| 13818 | "learning_rate": 0.00012934110787172012, |
| 13819 | "loss": 0.0394, |
| 13820 | "step": 20020 |
| 13821 | }, |
| 13822 | { |
| 13823 | "epoch": 28.78, |
| 13824 | "learning_rate": 0.00012925364431486878, |
| 13825 | "loss": 0.0262, |
| 13826 | "step": 20030 |
| 13827 | }, |
| 13828 | { |
| 13829 | "epoch": 28.79, |
| 13830 | "learning_rate": 0.00012916618075801747, |
| 13831 | "loss": 0.0351, |
| 13832 | "step": 20040 |
| 13833 | }, |
| 13834 | { |
| 13835 | "epoch": 28.81, |
| 13836 | "learning_rate": 0.00012907871720116616, |
| 13837 | "loss": 0.0354, |
| 13838 | "step": 20050 |
| 13839 | }, |
| 13840 | { |
| 13841 | "epoch": 28.82, |
| 13842 | "learning_rate": 0.00012899125364431487, |
| 13843 | "loss": 0.0332, |
| 13844 | "step": 20060 |
| 13845 | }, |
| 13846 | { |
| 13847 | "epoch": 28.84, |
| 13848 | "learning_rate": 0.00012890379008746353, |
| 13849 | "loss": 0.0349, |
| 13850 | "step": 20070 |
| 13851 | }, |
| 13852 | { |
| 13853 | "epoch": 28.85, |
| 13854 | "learning_rate": 0.00012881632653061222, |
| 13855 | "loss": 0.0518, |
| 13856 | "step": 20080 |
| 13857 | }, |
| 13858 | { |
| 13859 | "epoch": 28.86, |
| 13860 | "learning_rate": 0.0001287288629737609, |
| 13861 | "loss": 0.0388, |
| 13862 | "step": 20090 |
| 13863 | }, |
| 13864 | { |
| 13865 | "epoch": 28.88, |
| 13866 | "learning_rate": 0.00012864139941690963, |
| 13867 | "loss": 0.0363, |
| 13868 | "step": 20100 |
| 13869 | }, |
| 13870 | { |
| 13871 | "epoch": 28.88, |
| 13872 | "eval_loss": 0.13563397526741028, |
| 13873 | "eval_runtime": 40.5164, |
| 13874 | "eval_samples_per_second": 11.279, |
| 13875 | "eval_steps_per_second": 1.432, |
| 13876 | "eval_wer": 0.13717813582291824, |
| 13877 | "step": 20100 |
| 13878 | }, |
| 13879 | { |
| 13880 | "epoch": 28.89, |
| 13881 | "learning_rate": 0.0001285539358600583, |
| 13882 | "loss": 0.0339, |
| 13883 | "step": 20110 |
| 13884 | }, |
| 13885 | { |
| 13886 | "epoch": 28.91, |
| 13887 | "learning_rate": 0.00012846647230320697, |
| 13888 | "loss": 0.0446, |
| 13889 | "step": 20120 |
| 13890 | }, |
| 13891 | { |
| 13892 | "epoch": 28.92, |
| 13893 | "learning_rate": 0.00012837900874635566, |
| 13894 | "loss": 0.0373, |
| 13895 | "step": 20130 |
| 13896 | }, |
| 13897 | { |
| 13898 | "epoch": 28.94, |
| 13899 | "learning_rate": 0.00012829154518950435, |
| 13900 | "loss": 0.0337, |
| 13901 | "step": 20140 |
| 13902 | }, |
| 13903 | { |
| 13904 | "epoch": 28.95, |
| 13905 | "learning_rate": 0.00012820408163265306, |
| 13906 | "loss": 0.0361, |
| 13907 | "step": 20150 |
| 13908 | }, |
| 13909 | { |
| 13910 | "epoch": 28.97, |
| 13911 | "learning_rate": 0.00012811661807580173, |
| 13912 | "loss": 0.0359, |
| 13913 | "step": 20160 |
| 13914 | }, |
| 13915 | { |
| 13916 | "epoch": 28.98, |
| 13917 | "learning_rate": 0.0001280291545189504, |
| 13918 | "loss": 0.0392, |
| 13919 | "step": 20170 |
| 13920 | }, |
| 13921 | { |
| 13922 | "epoch": 28.99, |
| 13923 | "learning_rate": 0.0001279416909620991, |
| 13924 | "loss": 0.0352, |
| 13925 | "step": 20180 |
| 13926 | }, |
| 13927 | { |
| 13928 | "epoch": 29.01, |
| 13929 | "learning_rate": 0.00012785422740524782, |
| 13930 | "loss": 0.0446, |
| 13931 | "step": 20190 |
| 13932 | }, |
| 13933 | { |
| 13934 | "epoch": 29.02, |
| 13935 | "learning_rate": 0.0001277667638483965, |
| 13936 | "loss": 0.0353, |
| 13937 | "step": 20200 |
| 13938 | }, |
| 13939 | { |
| 13940 | "epoch": 29.02, |
| 13941 | "eval_loss": 0.13083459436893463, |
| 13942 | "eval_runtime": 40.1834, |
| 13943 | "eval_samples_per_second": 11.373, |
| 13944 | "eval_steps_per_second": 1.443, |
| 13945 | "eval_wer": 0.13386538171962054, |
| 13946 | "step": 20200 |
| 13947 | }, |
| 13948 | { |
| 13949 | "epoch": 29.04, |
| 13950 | "learning_rate": 0.00012767930029154517, |
| 13951 | "loss": 0.0378, |
| 13952 | "step": 20210 |
| 13953 | }, |
| 13954 | { |
| 13955 | "epoch": 29.05, |
| 13956 | "learning_rate": 0.00012759183673469385, |
| 13957 | "loss": 0.0341, |
| 13958 | "step": 20220 |
| 13959 | }, |
| 13960 | { |
| 13961 | "epoch": 29.07, |
| 13962 | "learning_rate": 0.00012750437317784257, |
| 13963 | "loss": 0.0314, |
| 13964 | "step": 20230 |
| 13965 | }, |
| 13966 | { |
| 13967 | "epoch": 29.08, |
| 13968 | "learning_rate": 0.00012741690962099126, |
| 13969 | "loss": 0.0382, |
| 13970 | "step": 20240 |
| 13971 | }, |
| 13972 | { |
| 13973 | "epoch": 29.09, |
| 13974 | "learning_rate": 0.00012732944606413992, |
| 13975 | "loss": 0.0338, |
| 13976 | "step": 20250 |
| 13977 | }, |
| 13978 | { |
| 13979 | "epoch": 29.11, |
| 13980 | "learning_rate": 0.0001272419825072886, |
| 13981 | "loss": 0.0278, |
| 13982 | "step": 20260 |
| 13983 | }, |
| 13984 | { |
| 13985 | "epoch": 29.12, |
| 13986 | "learning_rate": 0.00012715451895043732, |
| 13987 | "loss": 0.032, |
| 13988 | "step": 20270 |
| 13989 | }, |
| 13990 | { |
| 13991 | "epoch": 29.14, |
| 13992 | "learning_rate": 0.000127067055393586, |
| 13993 | "loss": 0.0379, |
| 13994 | "step": 20280 |
| 13995 | }, |
| 13996 | { |
| 13997 | "epoch": 29.15, |
| 13998 | "learning_rate": 0.0001269795918367347, |
| 13999 | "loss": 0.0429, |
| 14000 | "step": 20290 |
| 14001 | }, |
| 14002 | { |
| 14003 | "epoch": 29.17, |
| 14004 | "learning_rate": 0.00012689212827988336, |
| 14005 | "loss": 0.0457, |
| 14006 | "step": 20300 |
| 14007 | }, |
| 14008 | { |
| 14009 | "epoch": 29.17, |
| 14010 | "eval_loss": 0.13166461884975433, |
| 14011 | "eval_runtime": 40.2261, |
| 14012 | "eval_samples_per_second": 11.361, |
| 14013 | "eval_steps_per_second": 1.442, |
| 14014 | "eval_wer": 0.13537117903930132, |
| 14015 | "step": 20300 |
| 14016 | }, |
| 14017 | { |
| 14018 | "epoch": 29.18, |
| 14019 | "learning_rate": 0.00012680466472303204, |
| 14020 | "loss": 0.0394, |
| 14021 | "step": 20310 |
| 14022 | }, |
| 14023 | { |
| 14024 | "epoch": 29.2, |
| 14025 | "learning_rate": 0.00012671720116618076, |
| 14026 | "loss": 0.0358, |
| 14027 | "step": 20320 |
| 14028 | }, |
| 14029 | { |
| 14030 | "epoch": 29.21, |
| 14031 | "learning_rate": 0.00012662973760932945, |
| 14032 | "loss": 0.029, |
| 14033 | "step": 20330 |
| 14034 | }, |
| 14035 | { |
| 14036 | "epoch": 29.22, |
| 14037 | "learning_rate": 0.0001265422740524781, |
| 14038 | "loss": 0.0356, |
| 14039 | "step": 20340 |
| 14040 | }, |
| 14041 | { |
| 14042 | "epoch": 29.24, |
| 14043 | "learning_rate": 0.0001264548104956268, |
| 14044 | "loss": 0.0298, |
| 14045 | "step": 20350 |
| 14046 | }, |
| 14047 | { |
| 14048 | "epoch": 29.25, |
| 14049 | "learning_rate": 0.0001263673469387755, |
| 14050 | "loss": 0.0255, |
| 14051 | "step": 20360 |
| 14052 | }, |
| 14053 | { |
| 14054 | "epoch": 29.27, |
| 14055 | "learning_rate": 0.0001262798833819242, |
| 14056 | "loss": 0.0427, |
| 14057 | "step": 20370 |
| 14058 | }, |
| 14059 | { |
| 14060 | "epoch": 29.28, |
| 14061 | "learning_rate": 0.00012619241982507289, |
| 14062 | "loss": 0.0296, |
| 14063 | "step": 20380 |
| 14064 | }, |
| 14065 | { |
| 14066 | "epoch": 29.3, |
| 14067 | "learning_rate": 0.00012610495626822155, |
| 14068 | "loss": 0.0307, |
| 14069 | "step": 20390 |
| 14070 | }, |
| 14071 | { |
| 14072 | "epoch": 29.31, |
| 14073 | "learning_rate": 0.00012601749271137026, |
| 14074 | "loss": 0.0338, |
| 14075 | "step": 20400 |
| 14076 | }, |
| 14077 | { |
| 14078 | "epoch": 29.31, |
| 14079 | "eval_loss": 0.12933945655822754, |
| 14080 | "eval_runtime": 40.0847, |
| 14081 | "eval_samples_per_second": 11.401, |
| 14082 | "eval_steps_per_second": 1.447, |
| 14083 | "eval_wer": 0.13552175877126937, |
| 14084 | "step": 20400 |
| 14085 | }, |
| 14086 | { |
| 14087 | "epoch": 29.32, |
| 14088 | "learning_rate": 0.00012593002915451895, |
| 14089 | "loss": 0.0313, |
| 14090 | "step": 20410 |
| 14091 | }, |
| 14092 | { |
| 14093 | "epoch": 29.34, |
| 14094 | "learning_rate": 0.00012584256559766764, |
| 14095 | "loss": 0.04, |
| 14096 | "step": 20420 |
| 14097 | }, |
| 14098 | { |
| 14099 | "epoch": 29.35, |
| 14100 | "learning_rate": 0.0001257551020408163, |
| 14101 | "loss": 0.0357, |
| 14102 | "step": 20430 |
| 14103 | }, |
| 14104 | { |
| 14105 | "epoch": 29.37, |
| 14106 | "learning_rate": 0.000125667638483965, |
| 14107 | "loss": 0.0279, |
| 14108 | "step": 20440 |
| 14109 | }, |
| 14110 | { |
| 14111 | "epoch": 29.38, |
| 14112 | "learning_rate": 0.0001255801749271137, |
| 14113 | "loss": 0.0315, |
| 14114 | "step": 20450 |
| 14115 | }, |
| 14116 | { |
| 14117 | "epoch": 29.4, |
| 14118 | "learning_rate": 0.0001254927113702624, |
| 14119 | "loss": 0.0286, |
| 14120 | "step": 20460 |
| 14121 | }, |
| 14122 | { |
| 14123 | "epoch": 29.41, |
| 14124 | "learning_rate": 0.00012540524781341108, |
| 14125 | "loss": 0.0405, |
| 14126 | "step": 20470 |
| 14127 | }, |
| 14128 | { |
| 14129 | "epoch": 29.43, |
| 14130 | "learning_rate": 0.00012531778425655974, |
| 14131 | "loss": 0.0317, |
| 14132 | "step": 20480 |
| 14133 | }, |
| 14134 | { |
| 14135 | "epoch": 29.44, |
| 14136 | "learning_rate": 0.00012523032069970845, |
| 14137 | "loss": 0.0394, |
| 14138 | "step": 20490 |
| 14139 | }, |
| 14140 | { |
| 14141 | "epoch": 29.45, |
| 14142 | "learning_rate": 0.00012514285714285714, |
| 14143 | "loss": 0.0355, |
| 14144 | "step": 20500 |
| 14145 | }, |
| 14146 | { |
| 14147 | "epoch": 29.45, |
| 14148 | "eval_loss": 0.13684523105621338, |
| 14149 | "eval_runtime": 40.2263, |
| 14150 | "eval_samples_per_second": 11.361, |
| 14151 | "eval_steps_per_second": 1.442, |
| 14152 | "eval_wer": 0.12979972895648245, |
| 14153 | "step": 20500 |
| 14154 | }, |
| 14155 | { |
| 14156 | "epoch": 29.47, |
| 14157 | "learning_rate": 0.00012505539358600583, |
| 14158 | "loss": 0.0354, |
| 14159 | "step": 20510 |
| 14160 | }, |
| 14161 | { |
| 14162 | "epoch": 29.48, |
| 14163 | "learning_rate": 0.0001249679300291545, |
| 14164 | "loss": 0.0322, |
| 14165 | "step": 20520 |
| 14166 | }, |
| 14167 | { |
| 14168 | "epoch": 29.5, |
| 14169 | "learning_rate": 0.0001248804664723032, |
| 14170 | "loss": 0.0346, |
| 14171 | "step": 20530 |
| 14172 | }, |
| 14173 | { |
| 14174 | "epoch": 29.51, |
| 14175 | "learning_rate": 0.0001247930029154519, |
| 14176 | "loss": 0.0439, |
| 14177 | "step": 20540 |
| 14178 | }, |
| 14179 | { |
| 14180 | "epoch": 29.53, |
| 14181 | "learning_rate": 0.00012470553935860058, |
| 14182 | "loss": 0.0402, |
| 14183 | "step": 20550 |
| 14184 | }, |
| 14185 | { |
| 14186 | "epoch": 29.54, |
| 14187 | "learning_rate": 0.00012461807580174927, |
| 14188 | "loss": 0.0325, |
| 14189 | "step": 20560 |
| 14190 | }, |
| 14191 | { |
| 14192 | "epoch": 29.55, |
| 14193 | "learning_rate": 0.00012453061224489793, |
| 14194 | "loss": 0.0358, |
| 14195 | "step": 20570 |
| 14196 | }, |
| 14197 | { |
| 14198 | "epoch": 29.57, |
| 14199 | "learning_rate": 0.00012444314868804664, |
| 14200 | "loss": 0.0349, |
| 14201 | "step": 20580 |
| 14202 | }, |
| 14203 | { |
| 14204 | "epoch": 29.58, |
| 14205 | "learning_rate": 0.00012435568513119533, |
| 14206 | "loss": 0.0391, |
| 14207 | "step": 20590 |
| 14208 | }, |
| 14209 | { |
| 14210 | "epoch": 29.6, |
| 14211 | "learning_rate": 0.00012426822157434402, |
| 14212 | "loss": 0.0339, |
| 14213 | "step": 20600 |
| 14214 | }, |
| 14215 | { |
| 14216 | "epoch": 29.6, |
| 14217 | "eval_loss": 0.13588006794452667, |
| 14218 | "eval_runtime": 40.1534, |
| 14219 | "eval_samples_per_second": 11.381, |
| 14220 | "eval_steps_per_second": 1.444, |
| 14221 | "eval_wer": 0.13311248305978016, |
| 14222 | "step": 20600 |
| 14223 | }, |
| 14224 | { |
| 14225 | "epoch": 29.61, |
| 14226 | "learning_rate": 0.00012418075801749268, |
| 14227 | "loss": 0.0418, |
| 14228 | "step": 20610 |
| 14229 | }, |
| 14230 | { |
| 14231 | "epoch": 29.63, |
| 14232 | "learning_rate": 0.0001240932944606414, |
| 14233 | "loss": 0.0374, |
| 14234 | "step": 20620 |
| 14235 | }, |
| 14236 | { |
| 14237 | "epoch": 29.64, |
| 14238 | "learning_rate": 0.00012400583090379008, |
| 14239 | "loss": 0.0358, |
| 14240 | "step": 20630 |
| 14241 | }, |
| 14242 | { |
| 14243 | "epoch": 29.66, |
| 14244 | "learning_rate": 0.00012391836734693877, |
| 14245 | "loss": 0.0438, |
| 14246 | "step": 20640 |
| 14247 | }, |
| 14248 | { |
| 14249 | "epoch": 29.67, |
| 14250 | "learning_rate": 0.00012383090379008746, |
| 14251 | "loss": 0.0319, |
| 14252 | "step": 20650 |
| 14253 | }, |
| 14254 | { |
| 14255 | "epoch": 29.68, |
| 14256 | "learning_rate": 0.00012374344023323615, |
| 14257 | "loss": 0.0266, |
| 14258 | "step": 20660 |
| 14259 | }, |
| 14260 | { |
| 14261 | "epoch": 29.7, |
| 14262 | "learning_rate": 0.00012365597667638484, |
| 14263 | "loss": 0.035, |
| 14264 | "step": 20670 |
| 14265 | }, |
| 14266 | { |
| 14267 | "epoch": 29.71, |
| 14268 | "learning_rate": 0.00012356851311953352, |
| 14269 | "loss": 0.045, |
| 14270 | "step": 20680 |
| 14271 | }, |
| 14272 | { |
| 14273 | "epoch": 29.73, |
| 14274 | "learning_rate": 0.0001234810495626822, |
| 14275 | "loss": 0.0471, |
| 14276 | "step": 20690 |
| 14277 | }, |
| 14278 | { |
| 14279 | "epoch": 29.74, |
| 14280 | "learning_rate": 0.0001233935860058309, |
| 14281 | "loss": 0.0374, |
| 14282 | "step": 20700 |
| 14283 | }, |
| 14284 | { |
| 14285 | "epoch": 29.74, |
| 14286 | "eval_loss": 0.13162796199321747, |
| 14287 | "eval_runtime": 40.4509, |
| 14288 | "eval_samples_per_second": 11.298, |
| 14289 | "eval_steps_per_second": 1.434, |
| 14290 | "eval_wer": 0.12995030868845053, |
| 14291 | "step": 20700 |
| 14292 | }, |
| 14293 | { |
| 14294 | "epoch": 29.76, |
| 14295 | "learning_rate": 0.0001233061224489796, |
| 14296 | "loss": 0.0285, |
| 14297 | "step": 20710 |
| 14298 | }, |
| 14299 | { |
| 14300 | "epoch": 29.77, |
| 14301 | "learning_rate": 0.00012321865889212827, |
| 14302 | "loss": 0.0359, |
| 14303 | "step": 20720 |
| 14304 | }, |
| 14305 | { |
| 14306 | "epoch": 29.78, |
| 14307 | "learning_rate": 0.00012313119533527696, |
| 14308 | "loss": 0.0284, |
| 14309 | "step": 20730 |
| 14310 | }, |
| 14311 | { |
| 14312 | "epoch": 29.8, |
| 14313 | "learning_rate": 0.00012304373177842565, |
| 14314 | "loss": 0.0243, |
| 14315 | "step": 20740 |
| 14316 | }, |
| 14317 | { |
| 14318 | "epoch": 29.81, |
| 14319 | "learning_rate": 0.00012295626822157434, |
| 14320 | "loss": 0.0306, |
| 14321 | "step": 20750 |
| 14322 | }, |
| 14323 | { |
| 14324 | "epoch": 29.83, |
| 14325 | "learning_rate": 0.00012286880466472303, |
| 14326 | "loss": 0.038, |
| 14327 | "step": 20760 |
| 14328 | }, |
| 14329 | { |
| 14330 | "epoch": 29.84, |
| 14331 | "learning_rate": 0.00012278134110787171, |
| 14332 | "loss": 0.0338, |
| 14333 | "step": 20770 |
| 14334 | }, |
| 14335 | { |
| 14336 | "epoch": 29.86, |
| 14337 | "learning_rate": 0.0001226938775510204, |
| 14338 | "loss": 0.0304, |
| 14339 | "step": 20780 |
| 14340 | }, |
| 14341 | { |
| 14342 | "epoch": 29.87, |
| 14343 | "learning_rate": 0.0001226064139941691, |
| 14344 | "loss": 0.0361, |
| 14345 | "step": 20790 |
| 14346 | }, |
| 14347 | { |
| 14348 | "epoch": 29.89, |
| 14349 | "learning_rate": 0.00012251895043731778, |
| 14350 | "loss": 0.0358, |
| 14351 | "step": 20800 |
| 14352 | }, |
| 14353 | { |
| 14354 | "epoch": 29.89, |
| 14355 | "eval_loss": 0.13410452008247375, |
| 14356 | "eval_runtime": 40.2318, |
| 14357 | "eval_samples_per_second": 11.359, |
| 14358 | "eval_steps_per_second": 1.442, |
| 14359 | "eval_wer": 0.13507001957536516, |
| 14360 | "step": 20800 |
| 14361 | }, |
| 14362 | { |
| 14363 | "epoch": 29.9, |
| 14364 | "learning_rate": 0.00012243148688046647, |
| 14365 | "loss": 0.0341, |
| 14366 | "step": 20810 |
| 14367 | }, |
| 14368 | { |
| 14369 | "epoch": 29.91, |
| 14370 | "learning_rate": 0.00012234402332361515, |
| 14371 | "loss": 0.0434, |
| 14372 | "step": 20820 |
| 14373 | }, |
| 14374 | { |
| 14375 | "epoch": 29.93, |
| 14376 | "learning_rate": 0.00012225655976676384, |
| 14377 | "loss": 0.0317, |
| 14378 | "step": 20830 |
| 14379 | }, |
| 14380 | { |
| 14381 | "epoch": 29.94, |
| 14382 | "learning_rate": 0.00012216909620991253, |
| 14383 | "loss": 0.0415, |
| 14384 | "step": 20840 |
| 14385 | }, |
| 14386 | { |
| 14387 | "epoch": 29.96, |
| 14388 | "learning_rate": 0.00012208163265306122, |
| 14389 | "loss": 0.0355, |
| 14390 | "step": 20850 |
| 14391 | }, |
| 14392 | { |
| 14393 | "epoch": 29.97, |
| 14394 | "learning_rate": 0.0001219941690962099, |
| 14395 | "loss": 0.0376, |
| 14396 | "step": 20860 |
| 14397 | }, |
| 14398 | { |
| 14399 | "epoch": 29.99, |
| 14400 | "learning_rate": 0.0001219067055393586, |
| 14401 | "loss": 0.0373, |
| 14402 | "step": 20870 |
| 14403 | }, |
| 14404 | { |
| 14405 | "epoch": 30.0, |
| 14406 | "learning_rate": 0.00012181924198250727, |
| 14407 | "loss": 0.0283, |
| 14408 | "step": 20880 |
| 14409 | }, |
| 14410 | { |
| 14411 | "epoch": 30.01, |
| 14412 | "learning_rate": 0.00012173177842565597, |
| 14413 | "loss": 0.0411, |
| 14414 | "step": 20890 |
| 14415 | }, |
| 14416 | { |
| 14417 | "epoch": 30.03, |
| 14418 | "learning_rate": 0.00012164431486880466, |
| 14419 | "loss": 0.0336, |
| 14420 | "step": 20900 |
| 14421 | }, |
| 14422 | { |
| 14423 | "epoch": 30.03, |
| 14424 | "eval_loss": 0.1340400129556656, |
| 14425 | "eval_runtime": 40.2902, |
| 14426 | "eval_samples_per_second": 11.343, |
| 14427 | "eval_steps_per_second": 1.44, |
| 14428 | "eval_wer": 0.13205842493600362, |
| 14429 | "step": 20900 |
| 14430 | }, |
| 14431 | { |
| 14432 | "epoch": 30.04, |
| 14433 | "learning_rate": 0.00012155685131195334, |
| 14434 | "loss": 0.0405, |
| 14435 | "step": 20910 |
| 14436 | }, |
| 14437 | { |
| 14438 | "epoch": 30.06, |
| 14439 | "learning_rate": 0.00012146938775510203, |
| 14440 | "loss": 0.0406, |
| 14441 | "step": 20920 |
| 14442 | }, |
| 14443 | { |
| 14444 | "epoch": 30.07, |
| 14445 | "learning_rate": 0.00012138192419825071, |
| 14446 | "loss": 0.0304, |
| 14447 | "step": 20930 |
| 14448 | }, |
| 14449 | { |
| 14450 | "epoch": 30.09, |
| 14451 | "learning_rate": 0.00012129446064139941, |
| 14452 | "loss": 0.0366, |
| 14453 | "step": 20940 |
| 14454 | }, |
| 14455 | { |
| 14456 | "epoch": 30.1, |
| 14457 | "learning_rate": 0.0001212069970845481, |
| 14458 | "loss": 0.0356, |
| 14459 | "step": 20950 |
| 14460 | }, |
| 14461 | { |
| 14462 | "epoch": 30.11, |
| 14463 | "learning_rate": 0.00012111953352769678, |
| 14464 | "loss": 0.0369, |
| 14465 | "step": 20960 |
| 14466 | }, |
| 14467 | { |
| 14468 | "epoch": 30.13, |
| 14469 | "learning_rate": 0.00012103206997084546, |
| 14470 | "loss": 0.034, |
| 14471 | "step": 20970 |
| 14472 | }, |
| 14473 | { |
| 14474 | "epoch": 30.14, |
| 14475 | "learning_rate": 0.00012094460641399416, |
| 14476 | "loss": 0.0273, |
| 14477 | "step": 20980 |
| 14478 | }, |
| 14479 | { |
| 14480 | "epoch": 30.16, |
| 14481 | "learning_rate": 0.00012085714285714285, |
| 14482 | "loss": 0.0409, |
| 14483 | "step": 20990 |
| 14484 | }, |
| 14485 | { |
| 14486 | "epoch": 30.17, |
| 14487 | "learning_rate": 0.00012076967930029154, |
| 14488 | "loss": 0.0393, |
| 14489 | "step": 21000 |
| 14490 | }, |
| 14491 | { |
| 14492 | "epoch": 30.17, |
| 14493 | "eval_loss": 0.13167157769203186, |
| 14494 | "eval_runtime": 40.4932, |
| 14495 | "eval_samples_per_second": 11.286, |
| 14496 | "eval_steps_per_second": 1.432, |
| 14497 | "eval_wer": 0.13461828037946091, |
| 14498 | "step": 21000 |
| 14499 | }, |
| 14500 | { |
| 14501 | "epoch": 30.19, |
| 14502 | "learning_rate": 0.00012068221574344022, |
| 14503 | "loss": 0.0313, |
| 14504 | "step": 21010 |
| 14505 | }, |
| 14506 | { |
| 14507 | "epoch": 30.2, |
| 14508 | "learning_rate": 0.00012059475218658891, |
| 14509 | "loss": 0.0302, |
| 14510 | "step": 21020 |
| 14511 | }, |
| 14512 | { |
| 14513 | "epoch": 30.22, |
| 14514 | "learning_rate": 0.0001205072886297376, |
| 14515 | "loss": 0.0266, |
| 14516 | "step": 21030 |
| 14517 | }, |
| 14518 | { |
| 14519 | "epoch": 30.23, |
| 14520 | "learning_rate": 0.00012041982507288629, |
| 14521 | "loss": 0.0415, |
| 14522 | "step": 21040 |
| 14523 | }, |
| 14524 | { |
| 14525 | "epoch": 30.24, |
| 14526 | "learning_rate": 0.00012033236151603498, |
| 14527 | "loss": 0.0286, |
| 14528 | "step": 21050 |
| 14529 | }, |
| 14530 | { |
| 14531 | "epoch": 30.26, |
| 14532 | "learning_rate": 0.00012024489795918365, |
| 14533 | "loss": 0.0344, |
| 14534 | "step": 21060 |
| 14535 | }, |
| 14536 | { |
| 14537 | "epoch": 30.27, |
| 14538 | "learning_rate": 0.00012015743440233235, |
| 14539 | "loss": 0.0317, |
| 14540 | "step": 21070 |
| 14541 | }, |
| 14542 | { |
| 14543 | "epoch": 30.29, |
| 14544 | "learning_rate": 0.00012006997084548104, |
| 14545 | "loss": 0.0271, |
| 14546 | "step": 21080 |
| 14547 | }, |
| 14548 | { |
| 14549 | "epoch": 30.3, |
| 14550 | "learning_rate": 0.00011998250728862973, |
| 14551 | "loss": 0.0418, |
| 14552 | "step": 21090 |
| 14553 | }, |
| 14554 | { |
| 14555 | "epoch": 30.32, |
| 14556 | "learning_rate": 0.00011989504373177843, |
| 14557 | "loss": 0.0383, |
| 14558 | "step": 21100 |
| 14559 | }, |
| 14560 | { |
| 14561 | "epoch": 30.32, |
| 14562 | "eval_loss": 0.12635038793087006, |
| 14563 | "eval_runtime": 40.1747, |
| 14564 | "eval_samples_per_second": 11.375, |
| 14565 | "eval_steps_per_second": 1.444, |
| 14566 | "eval_wer": 0.13627465743110978, |
| 14567 | "step": 21100 |
| 14568 | }, |
| 14569 | { |
| 14570 | "epoch": 30.33, |
| 14571 | "learning_rate": 0.0001198075801749271, |
| 14572 | "loss": 0.0352, |
| 14573 | "step": 21110 |
| 14574 | }, |
| 14575 | { |
| 14576 | "epoch": 30.34, |
| 14577 | "learning_rate": 0.00011972011661807579, |
| 14578 | "loss": 0.0324, |
| 14579 | "step": 21120 |
| 14580 | }, |
| 14581 | { |
| 14582 | "epoch": 30.36, |
| 14583 | "learning_rate": 0.00011963265306122448, |
| 14584 | "loss": 0.0326, |
| 14585 | "step": 21130 |
| 14586 | }, |
| 14587 | { |
| 14588 | "epoch": 30.37, |
| 14589 | "learning_rate": 0.00011954518950437318, |
| 14590 | "loss": 0.0368, |
| 14591 | "step": 21140 |
| 14592 | }, |
| 14593 | { |
| 14594 | "epoch": 30.39, |
| 14595 | "learning_rate": 0.00011945772594752185, |
| 14596 | "loss": 0.0299, |
| 14597 | "step": 21150 |
| 14598 | }, |
| 14599 | { |
| 14600 | "epoch": 30.4, |
| 14601 | "learning_rate": 0.00011937026239067054, |
| 14602 | "loss": 0.0316, |
| 14603 | "step": 21160 |
| 14604 | }, |
| 14605 | { |
| 14606 | "epoch": 30.42, |
| 14607 | "learning_rate": 0.00011928279883381923, |
| 14608 | "loss": 0.0304, |
| 14609 | "step": 21170 |
| 14610 | }, |
| 14611 | { |
| 14612 | "epoch": 30.43, |
| 14613 | "learning_rate": 0.00011919533527696792, |
| 14614 | "loss": 0.0307, |
| 14615 | "step": 21180 |
| 14616 | }, |
| 14617 | { |
| 14618 | "epoch": 30.45, |
| 14619 | "learning_rate": 0.00011910787172011662, |
| 14620 | "loss": 0.0369, |
| 14621 | "step": 21190 |
| 14622 | }, |
| 14623 | { |
| 14624 | "epoch": 30.46, |
| 14625 | "learning_rate": 0.0001190204081632653, |
| 14626 | "loss": 0.0353, |
| 14627 | "step": 21200 |
| 14628 | }, |
| 14629 | { |
| 14630 | "epoch": 30.46, |
| 14631 | "eval_loss": 0.1339302957057953, |
| 14632 | "eval_runtime": 40.1253, |
| 14633 | "eval_samples_per_second": 11.389, |
| 14634 | "eval_steps_per_second": 1.445, |
| 14635 | "eval_wer": 0.13642523716307786, |
| 14636 | "step": 21200 |
| 14637 | }, |
| 14638 | { |
| 14639 | "epoch": 30.47, |
| 14640 | "learning_rate": 0.00011893294460641398, |
| 14641 | "loss": 0.039, |
| 14642 | "step": 21210 |
| 14643 | }, |
| 14644 | { |
| 14645 | "epoch": 30.49, |
| 14646 | "learning_rate": 0.00011884548104956267, |
| 14647 | "loss": 0.0304, |
| 14648 | "step": 21220 |
| 14649 | }, |
| 14650 | { |
| 14651 | "epoch": 30.5, |
| 14652 | "learning_rate": 0.00011875801749271137, |
| 14653 | "loss": 0.0294, |
| 14654 | "step": 21230 |
| 14655 | }, |
| 14656 | { |
| 14657 | "epoch": 30.52, |
| 14658 | "learning_rate": 0.00011867055393586005, |
| 14659 | "loss": 0.0529, |
| 14660 | "step": 21240 |
| 14661 | }, |
| 14662 | { |
| 14663 | "epoch": 30.53, |
| 14664 | "learning_rate": 0.00011858309037900873, |
| 14665 | "loss": 0.028, |
| 14666 | "step": 21250 |
| 14667 | }, |
| 14668 | { |
| 14669 | "epoch": 30.55, |
| 14670 | "learning_rate": 0.00011849562682215742, |
| 14671 | "loss": 0.0378, |
| 14672 | "step": 21260 |
| 14673 | }, |
| 14674 | { |
| 14675 | "epoch": 30.56, |
| 14676 | "learning_rate": 0.00011840816326530612, |
| 14677 | "loss": 0.0351, |
| 14678 | "step": 21270 |
| 14679 | }, |
| 14680 | { |
| 14681 | "epoch": 30.57, |
| 14682 | "learning_rate": 0.00011832069970845481, |
| 14683 | "loss": 0.0325, |
| 14684 | "step": 21280 |
| 14685 | }, |
| 14686 | { |
| 14687 | "epoch": 30.59, |
| 14688 | "learning_rate": 0.00011823323615160348, |
| 14689 | "loss": 0.0425, |
| 14690 | "step": 21290 |
| 14691 | }, |
| 14692 | { |
| 14693 | "epoch": 30.6, |
| 14694 | "learning_rate": 0.00011814577259475217, |
| 14695 | "loss": 0.0254, |
| 14696 | "step": 21300 |
| 14697 | }, |
| 14698 | { |
| 14699 | "epoch": 30.6, |
| 14700 | "eval_loss": 0.13099804520606995, |
| 14701 | "eval_runtime": 40.1721, |
| 14702 | "eval_samples_per_second": 11.376, |
| 14703 | "eval_steps_per_second": 1.444, |
| 14704 | "eval_wer": 0.13702755609095016, |
| 14705 | "step": 21300 |
| 14706 | }, |
| 14707 | { |
| 14708 | "epoch": 30.62, |
| 14709 | "learning_rate": 0.00011805830903790086, |
| 14710 | "loss": 0.0342, |
| 14711 | "step": 21310 |
| 14712 | }, |
| 14713 | { |
| 14714 | "epoch": 30.63, |
| 14715 | "learning_rate": 0.00011797084548104956, |
| 14716 | "loss": 0.044, |
| 14717 | "step": 21320 |
| 14718 | }, |
| 14719 | { |
| 14720 | "epoch": 30.65, |
| 14721 | "learning_rate": 0.00011788338192419824, |
| 14722 | "loss": 0.0278, |
| 14723 | "step": 21330 |
| 14724 | }, |
| 14725 | { |
| 14726 | "epoch": 30.66, |
| 14727 | "learning_rate": 0.00011779591836734692, |
| 14728 | "loss": 0.0322, |
| 14729 | "step": 21340 |
| 14730 | }, |
| 14731 | { |
| 14732 | "epoch": 30.68, |
| 14733 | "learning_rate": 0.00011770845481049561, |
| 14734 | "loss": 0.0468, |
| 14735 | "step": 21350 |
| 14736 | }, |
| 14737 | { |
| 14738 | "epoch": 30.69, |
| 14739 | "learning_rate": 0.00011762099125364431, |
| 14740 | "loss": 0.0375, |
| 14741 | "step": 21360 |
| 14742 | }, |
| 14743 | { |
| 14744 | "epoch": 30.7, |
| 14745 | "learning_rate": 0.000117533527696793, |
| 14746 | "loss": 0.0311, |
| 14747 | "step": 21370 |
| 14748 | }, |
| 14749 | { |
| 14750 | "epoch": 30.72, |
| 14751 | "learning_rate": 0.00011744606413994168, |
| 14752 | "loss": 0.026, |
| 14753 | "step": 21380 |
| 14754 | }, |
| 14755 | { |
| 14756 | "epoch": 30.73, |
| 14757 | "learning_rate": 0.00011735860058309036, |
| 14758 | "loss": 0.0439, |
| 14759 | "step": 21390 |
| 14760 | }, |
| 14761 | { |
| 14762 | "epoch": 30.75, |
| 14763 | "learning_rate": 0.00011727113702623907, |
| 14764 | "loss": 0.0341, |
| 14765 | "step": 21400 |
| 14766 | }, |
| 14767 | { |
| 14768 | "epoch": 30.75, |
| 14769 | "eval_loss": 0.1271417737007141, |
| 14770 | "eval_runtime": 40.1531, |
| 14771 | "eval_samples_per_second": 11.381, |
| 14772 | "eval_steps_per_second": 1.444, |
| 14773 | "eval_wer": 0.13883451287456708, |
| 14774 | "step": 21400 |
| 14775 | }, |
| 14776 | { |
| 14777 | "epoch": 30.76, |
| 14778 | "learning_rate": 0.00011718367346938775, |
| 14779 | "loss": 0.044, |
| 14780 | "step": 21410 |
| 14781 | }, |
| 14782 | { |
| 14783 | "epoch": 30.78, |
| 14784 | "learning_rate": 0.00011709620991253643, |
| 14785 | "loss": 0.0266, |
| 14786 | "step": 21420 |
| 14787 | }, |
| 14788 | { |
| 14789 | "epoch": 30.79, |
| 14790 | "learning_rate": 0.00011700874635568512, |
| 14791 | "loss": 0.0301, |
| 14792 | "step": 21430 |
| 14793 | }, |
| 14794 | { |
| 14795 | "epoch": 30.8, |
| 14796 | "learning_rate": 0.00011693002915451893, |
| 14797 | "loss": 0.0308, |
| 14798 | "step": 21440 |
| 14799 | }, |
| 14800 | { |
| 14801 | "epoch": 30.82, |
| 14802 | "learning_rate": 0.00011684256559766762, |
| 14803 | "loss": 0.0251, |
| 14804 | "step": 21450 |
| 14805 | }, |
| 14806 | { |
| 14807 | "epoch": 30.83, |
| 14808 | "learning_rate": 0.00011675510204081632, |
| 14809 | "loss": 0.0336, |
| 14810 | "step": 21460 |
| 14811 | }, |
| 14812 | { |
| 14813 | "epoch": 30.85, |
| 14814 | "learning_rate": 0.00011666763848396501, |
| 14815 | "loss": 0.0348, |
| 14816 | "step": 21470 |
| 14817 | }, |
| 14818 | { |
| 14819 | "epoch": 30.86, |
| 14820 | "learning_rate": 0.00011658017492711369, |
| 14821 | "loss": 0.0274, |
| 14822 | "step": 21480 |
| 14823 | }, |
| 14824 | { |
| 14825 | "epoch": 30.88, |
| 14826 | "learning_rate": 0.00011649271137026237, |
| 14827 | "loss": 0.0361, |
| 14828 | "step": 21490 |
| 14829 | }, |
| 14830 | { |
| 14831 | "epoch": 30.89, |
| 14832 | "learning_rate": 0.00011640524781341106, |
| 14833 | "loss": 0.0337, |
| 14834 | "step": 21500 |
| 14835 | }, |
| 14836 | { |
| 14837 | "epoch": 30.89, |
| 14838 | "eval_loss": 0.1293652504682541, |
| 14839 | "eval_runtime": 40.341, |
| 14840 | "eval_samples_per_second": 11.328, |
| 14841 | "eval_steps_per_second": 1.438, |
| 14842 | "eval_wer": 0.1380816142147267, |
| 14843 | "step": 21500 |
| 14844 | }, |
| 14845 | { |
| 14846 | "epoch": 30.91, |
| 14847 | "learning_rate": 0.00011631778425655976, |
| 14848 | "loss": 0.0439, |
| 14849 | "step": 21510 |
| 14850 | }, |
| 14851 | { |
| 14852 | "epoch": 30.92, |
| 14853 | "learning_rate": 0.00011623032069970845, |
| 14854 | "loss": 0.0347, |
| 14855 | "step": 21520 |
| 14856 | }, |
| 14857 | { |
| 14858 | "epoch": 30.93, |
| 14859 | "learning_rate": 0.00011614285714285713, |
| 14860 | "loss": 0.0281, |
| 14861 | "step": 21530 |
| 14862 | }, |
| 14863 | { |
| 14864 | "epoch": 30.95, |
| 14865 | "learning_rate": 0.00011605539358600581, |
| 14866 | "loss": 0.0493, |
| 14867 | "step": 21540 |
| 14868 | }, |
| 14869 | { |
| 14870 | "epoch": 30.96, |
| 14871 | "learning_rate": 0.00011596793002915452, |
| 14872 | "loss": 0.0321, |
| 14873 | "step": 21550 |
| 14874 | }, |
| 14875 | { |
| 14876 | "epoch": 30.98, |
| 14877 | "learning_rate": 0.0001158804664723032, |
| 14878 | "loss": 0.0409, |
| 14879 | "step": 21560 |
| 14880 | }, |
| 14881 | { |
| 14882 | "epoch": 30.99, |
| 14883 | "learning_rate": 0.00011579300291545188, |
| 14884 | "loss": 0.048, |
| 14885 | "step": 21570 |
| 14886 | }, |
| 14887 | { |
| 14888 | "epoch": 31.01, |
| 14889 | "learning_rate": 0.00011570553935860057, |
| 14890 | "loss": 0.0271, |
| 14891 | "step": 21580 |
| 14892 | }, |
| 14893 | { |
| 14894 | "epoch": 31.02, |
| 14895 | "learning_rate": 0.00011561807580174927, |
| 14896 | "loss": 0.0318, |
| 14897 | "step": 21590 |
| 14898 | }, |
| 14899 | { |
| 14900 | "epoch": 31.03, |
| 14901 | "learning_rate": 0.00011553061224489795, |
| 14902 | "loss": 0.0261, |
| 14903 | "step": 21600 |
| 14904 | }, |
| 14905 | { |
| 14906 | "epoch": 31.03, |
| 14907 | "eval_loss": 0.1307568997144699, |
| 14908 | "eval_runtime": 40.326, |
| 14909 | "eval_samples_per_second": 11.333, |
| 14910 | "eval_steps_per_second": 1.438, |
| 14911 | "eval_wer": 0.13552175877126937, |
| 14912 | "step": 21600 |
| 14913 | }, |
| 14914 | { |
| 14915 | "epoch": 31.05, |
| 14916 | "learning_rate": 0.00011544314868804664, |
| 14917 | "loss": 0.0325, |
| 14918 | "step": 21610 |
| 14919 | }, |
| 14920 | { |
| 14921 | "epoch": 31.06, |
| 14922 | "learning_rate": 0.00011535568513119532, |
| 14923 | "loss": 0.0298, |
| 14924 | "step": 21620 |
| 14925 | }, |
| 14926 | { |
| 14927 | "epoch": 31.08, |
| 14928 | "learning_rate": 0.000115268221574344, |
| 14929 | "loss": 0.0292, |
| 14930 | "step": 21630 |
| 14931 | }, |
| 14932 | { |
| 14933 | "epoch": 31.09, |
| 14934 | "learning_rate": 0.0001151807580174927, |
| 14935 | "loss": 0.0315, |
| 14936 | "step": 21640 |
| 14937 | }, |
| 14938 | { |
| 14939 | "epoch": 31.11, |
| 14940 | "learning_rate": 0.0001150932944606414, |
| 14941 | "loss": 0.0319, |
| 14942 | "step": 21650 |
| 14943 | }, |
| 14944 | { |
| 14945 | "epoch": 31.12, |
| 14946 | "learning_rate": 0.00011500583090379007, |
| 14947 | "loss": 0.0301, |
| 14948 | "step": 21660 |
| 14949 | }, |
| 14950 | { |
| 14951 | "epoch": 31.14, |
| 14952 | "learning_rate": 0.00011491836734693876, |
| 14953 | "loss": 0.0399, |
| 14954 | "step": 21670 |
| 14955 | }, |
| 14956 | { |
| 14957 | "epoch": 31.15, |
| 14958 | "learning_rate": 0.00011483090379008746, |
| 14959 | "loss": 0.033, |
| 14960 | "step": 21680 |
| 14961 | }, |
| 14962 | { |
| 14963 | "epoch": 31.16, |
| 14964 | "learning_rate": 0.00011474344023323615, |
| 14965 | "loss": 0.0348, |
| 14966 | "step": 21690 |
| 14967 | }, |
| 14968 | { |
| 14969 | "epoch": 31.18, |
| 14970 | "learning_rate": 0.00011465597667638483, |
| 14971 | "loss": 0.0276, |
| 14972 | "step": 21700 |
| 14973 | }, |
| 14974 | { |
| 14975 | "epoch": 31.18, |
| 14976 | "eval_loss": 0.12548431754112244, |
| 14977 | "eval_runtime": 40.1766, |
| 14978 | "eval_samples_per_second": 11.375, |
| 14979 | "eval_steps_per_second": 1.444, |
| 14980 | "eval_wer": 0.13793103448275862, |
| 14981 | "step": 21700 |
| 14982 | }, |
| 14983 | { |
| 14984 | "epoch": 31.19, |
| 14985 | "learning_rate": 0.00011456851311953351, |
| 14986 | "loss": 0.0376, |
| 14987 | "step": 21710 |
| 14988 | }, |
| 14989 | { |
| 14990 | "epoch": 31.21, |
| 14991 | "learning_rate": 0.00011448104956268221, |
| 14992 | "loss": 0.0291, |
| 14993 | "step": 21720 |
| 14994 | }, |
| 14995 | { |
| 14996 | "epoch": 31.22, |
| 14997 | "learning_rate": 0.0001143935860058309, |
| 14998 | "loss": 0.0276, |
| 14999 | "step": 21730 |
| 15000 | }, |
| 15001 | { |
| 15002 | "epoch": 31.24, |
| 15003 | "learning_rate": 0.00011430612244897959, |
| 15004 | "loss": 0.0343, |
| 15005 | "step": 21740 |
| 15006 | }, |
| 15007 | { |
| 15008 | "epoch": 31.25, |
| 15009 | "learning_rate": 0.00011421865889212826, |
| 15010 | "loss": 0.0292, |
| 15011 | "step": 21750 |
| 15012 | }, |
| 15013 | { |
| 15014 | "epoch": 31.26, |
| 15015 | "learning_rate": 0.00011413119533527695, |
| 15016 | "loss": 0.0313, |
| 15017 | "step": 21760 |
| 15018 | }, |
| 15019 | { |
| 15020 | "epoch": 31.28, |
| 15021 | "learning_rate": 0.00011404373177842565, |
| 15022 | "loss": 0.0306, |
| 15023 | "step": 21770 |
| 15024 | }, |
| 15025 | { |
| 15026 | "epoch": 31.29, |
| 15027 | "learning_rate": 0.00011395626822157434, |
| 15028 | "loss": 0.0362, |
| 15029 | "step": 21780 |
| 15030 | }, |
| 15031 | { |
| 15032 | "epoch": 31.31, |
| 15033 | "learning_rate": 0.00011386880466472302, |
| 15034 | "loss": 0.04, |
| 15035 | "step": 21790 |
| 15036 | }, |
| 15037 | { |
| 15038 | "epoch": 31.32, |
| 15039 | "learning_rate": 0.0001137813411078717, |
| 15040 | "loss": 0.0316, |
| 15041 | "step": 21800 |
| 15042 | }, |
| 15043 | { |
| 15044 | "epoch": 31.32, |
| 15045 | "eval_loss": 0.13308794796466827, |
| 15046 | "eval_runtime": 40.3702, |
| 15047 | "eval_samples_per_second": 11.32, |
| 15048 | "eval_steps_per_second": 1.437, |
| 15049 | "eval_wer": 0.13823219394669478, |
| 15050 | "step": 21800 |
| 15051 | }, |
| 15052 | { |
| 15053 | "epoch": 31.34, |
| 15054 | "learning_rate": 0.0001136938775510204, |
| 15055 | "loss": 0.0391, |
| 15056 | "step": 21810 |
| 15057 | }, |
| 15058 | { |
| 15059 | "epoch": 31.35, |
| 15060 | "learning_rate": 0.00011360641399416909, |
| 15061 | "loss": 0.032, |
| 15062 | "step": 21820 |
| 15063 | }, |
| 15064 | { |
| 15065 | "epoch": 31.36, |
| 15066 | "learning_rate": 0.00011351895043731778, |
| 15067 | "loss": 0.0261, |
| 15068 | "step": 21830 |
| 15069 | }, |
| 15070 | { |
| 15071 | "epoch": 31.38, |
| 15072 | "learning_rate": 0.00011343148688046645, |
| 15073 | "loss": 0.0276, |
| 15074 | "step": 21840 |
| 15075 | }, |
| 15076 | { |
| 15077 | "epoch": 31.39, |
| 15078 | "learning_rate": 0.00011334402332361515, |
| 15079 | "loss": 0.0348, |
| 15080 | "step": 21850 |
| 15081 | }, |
| 15082 | { |
| 15083 | "epoch": 31.41, |
| 15084 | "learning_rate": 0.00011325655976676384, |
| 15085 | "loss": 0.0352, |
| 15086 | "step": 21860 |
| 15087 | }, |
| 15088 | { |
| 15089 | "epoch": 31.42, |
| 15090 | "learning_rate": 0.00011316909620991253, |
| 15091 | "loss": 0.0249, |
| 15092 | "step": 21870 |
| 15093 | }, |
| 15094 | { |
| 15095 | "epoch": 31.44, |
| 15096 | "learning_rate": 0.00011308163265306122, |
| 15097 | "loss": 0.0339, |
| 15098 | "step": 21880 |
| 15099 | }, |
| 15100 | { |
| 15101 | "epoch": 31.45, |
| 15102 | "learning_rate": 0.00011299416909620989, |
| 15103 | "loss": 0.0358, |
| 15104 | "step": 21890 |
| 15105 | }, |
| 15106 | { |
| 15107 | "epoch": 31.47, |
| 15108 | "learning_rate": 0.00011290670553935859, |
| 15109 | "loss": 0.0274, |
| 15110 | "step": 21900 |
| 15111 | }, |
| 15112 | { |
| 15113 | "epoch": 31.47, |
| 15114 | "eval_loss": 0.13432462513446808, |
| 15115 | "eval_runtime": 40.5527, |
| 15116 | "eval_samples_per_second": 11.269, |
| 15117 | "eval_steps_per_second": 1.43, |
| 15118 | "eval_wer": 0.13311248305978016, |
| 15119 | "step": 21900 |
| 15120 | }, |
| 15121 | { |
| 15122 | "epoch": 31.48, |
| 15123 | "learning_rate": 0.00011281924198250728, |
| 15124 | "loss": 0.0294, |
| 15125 | "step": 21910 |
| 15126 | }, |
| 15127 | { |
| 15128 | "epoch": 31.49, |
| 15129 | "learning_rate": 0.00011273177842565597, |
| 15130 | "loss": 0.0273, |
| 15131 | "step": 21920 |
| 15132 | }, |
| 15133 | { |
| 15134 | "epoch": 31.51, |
| 15135 | "learning_rate": 0.00011264431486880464, |
| 15136 | "loss": 0.0275, |
| 15137 | "step": 21930 |
| 15138 | }, |
| 15139 | { |
| 15140 | "epoch": 31.52, |
| 15141 | "learning_rate": 0.00011255685131195334, |
| 15142 | "loss": 0.0301, |
| 15143 | "step": 21940 |
| 15144 | }, |
| 15145 | { |
| 15146 | "epoch": 31.54, |
| 15147 | "learning_rate": 0.00011246938775510203, |
| 15148 | "loss": 0.0265, |
| 15149 | "step": 21950 |
| 15150 | }, |
| 15151 | { |
| 15152 | "epoch": 31.55, |
| 15153 | "learning_rate": 0.00011238192419825072, |
| 15154 | "loss": 0.0343, |
| 15155 | "step": 21960 |
| 15156 | }, |
| 15157 | { |
| 15158 | "epoch": 31.57, |
| 15159 | "learning_rate": 0.00011229446064139942, |
| 15160 | "loss": 0.0278, |
| 15161 | "step": 21970 |
| 15162 | }, |
| 15163 | { |
| 15164 | "epoch": 31.58, |
| 15165 | "learning_rate": 0.0001122069970845481, |
| 15166 | "loss": 0.0347, |
| 15167 | "step": 21980 |
| 15168 | }, |
| 15169 | { |
| 15170 | "epoch": 31.59, |
| 15171 | "learning_rate": 0.00011211953352769678, |
| 15172 | "loss": 0.0329, |
| 15173 | "step": 21990 |
| 15174 | }, |
| 15175 | { |
| 15176 | "epoch": 31.61, |
| 15177 | "learning_rate": 0.00011203206997084547, |
| 15178 | "loss": 0.0317, |
| 15179 | "step": 22000 |
| 15180 | }, |
| 15181 | { |
| 15182 | "epoch": 31.61, |
| 15183 | "eval_loss": 0.129713773727417, |
| 15184 | "eval_runtime": 40.2564, |
| 15185 | "eval_samples_per_second": 11.352, |
| 15186 | "eval_steps_per_second": 1.441, |
| 15187 | "eval_wer": 0.13341364252371632, |
| 15188 | "step": 22000 |
| 15189 | }, |
| 15190 | { |
| 15191 | "epoch": 31.62, |
| 15192 | "learning_rate": 0.00011194460641399416, |
| 15193 | "loss": 0.0409, |
| 15194 | "step": 22010 |
| 15195 | }, |
| 15196 | { |
| 15197 | "epoch": 31.64, |
| 15198 | "learning_rate": 0.00011185714285714285, |
| 15199 | "loss": 0.0268, |
| 15200 | "step": 22020 |
| 15201 | }, |
| 15202 | { |
| 15203 | "epoch": 31.65, |
| 15204 | "learning_rate": 0.00011176967930029153, |
| 15205 | "loss": 0.0461, |
| 15206 | "step": 22030 |
| 15207 | }, |
| 15208 | { |
| 15209 | "epoch": 31.67, |
| 15210 | "learning_rate": 0.00011168221574344022, |
| 15211 | "loss": 0.0362, |
| 15212 | "step": 22040 |
| 15213 | }, |
| 15214 | { |
| 15215 | "epoch": 31.68, |
| 15216 | "learning_rate": 0.00011159475218658891, |
| 15217 | "loss": 0.0282, |
| 15218 | "step": 22050 |
| 15219 | }, |
| 15220 | { |
| 15221 | "epoch": 31.7, |
| 15222 | "learning_rate": 0.00011150728862973761, |
| 15223 | "loss": 0.0447, |
| 15224 | "step": 22060 |
| 15225 | }, |
| 15226 | { |
| 15227 | "epoch": 31.71, |
| 15228 | "learning_rate": 0.00011141982507288629, |
| 15229 | "loss": 0.0306, |
| 15230 | "step": 22070 |
| 15231 | }, |
| 15232 | { |
| 15233 | "epoch": 31.72, |
| 15234 | "learning_rate": 0.00011133236151603497, |
| 15235 | "loss": 0.0367, |
| 15236 | "step": 22080 |
| 15237 | }, |
| 15238 | { |
| 15239 | "epoch": 31.74, |
| 15240 | "learning_rate": 0.00011124489795918366, |
| 15241 | "loss": 0.0244, |
| 15242 | "step": 22090 |
| 15243 | }, |
| 15244 | { |
| 15245 | "epoch": 31.75, |
| 15246 | "learning_rate": 0.00011115743440233236, |
| 15247 | "loss": 0.029, |
| 15248 | "step": 22100 |
| 15249 | }, |
| 15250 | { |
| 15251 | "epoch": 31.75, |
| 15252 | "eval_loss": 0.1280178278684616, |
| 15253 | "eval_runtime": 40.1733, |
| 15254 | "eval_samples_per_second": 11.376, |
| 15255 | "eval_steps_per_second": 1.444, |
| 15256 | "eval_wer": 0.13130552627616324, |
| 15257 | "step": 22100 |
| 15258 | }, |
| 15259 | { |
| 15260 | "epoch": 31.77, |
| 15261 | "learning_rate": 0.00011106997084548104, |
| 15262 | "loss": 0.0368, |
| 15263 | "step": 22110 |
| 15264 | }, |
| 15265 | { |
| 15266 | "epoch": 31.78, |
| 15267 | "learning_rate": 0.00011098250728862973, |
| 15268 | "loss": 0.0244, |
| 15269 | "step": 22120 |
| 15270 | }, |
| 15271 | { |
| 15272 | "epoch": 31.8, |
| 15273 | "learning_rate": 0.00011089504373177841, |
| 15274 | "loss": 0.0295, |
| 15275 | "step": 22130 |
| 15276 | }, |
| 15277 | { |
| 15278 | "epoch": 31.81, |
| 15279 | "learning_rate": 0.0001108075801749271, |
| 15280 | "loss": 0.0315, |
| 15281 | "step": 22140 |
| 15282 | }, |
| 15283 | { |
| 15284 | "epoch": 31.82, |
| 15285 | "learning_rate": 0.0001107201166180758, |
| 15286 | "loss": 0.0213, |
| 15287 | "step": 22150 |
| 15288 | }, |
| 15289 | { |
| 15290 | "epoch": 31.84, |
| 15291 | "learning_rate": 0.00011063265306122448, |
| 15292 | "loss": 0.0409, |
| 15293 | "step": 22160 |
| 15294 | }, |
| 15295 | { |
| 15296 | "epoch": 31.85, |
| 15297 | "learning_rate": 0.00011054518950437316, |
| 15298 | "loss": 0.0407, |
| 15299 | "step": 22170 |
| 15300 | }, |
| 15301 | { |
| 15302 | "epoch": 31.87, |
| 15303 | "learning_rate": 0.00011045772594752185, |
| 15304 | "loss": 0.0375, |
| 15305 | "step": 22180 |
| 15306 | }, |
| 15307 | { |
| 15308 | "epoch": 31.88, |
| 15309 | "learning_rate": 0.00011037026239067055, |
| 15310 | "loss": 0.0301, |
| 15311 | "step": 22190 |
| 15312 | }, |
| 15313 | { |
| 15314 | "epoch": 31.9, |
| 15315 | "learning_rate": 0.00011028279883381923, |
| 15316 | "loss": 0.0243, |
| 15317 | "step": 22200 |
| 15318 | }, |
| 15319 | { |
| 15320 | "epoch": 31.9, |
| 15321 | "eval_loss": 0.13117167353630066, |
| 15322 | "eval_runtime": 40.1562, |
| 15323 | "eval_samples_per_second": 11.381, |
| 15324 | "eval_steps_per_second": 1.444, |
| 15325 | "eval_wer": 0.13130552627616324, |
| 15326 | "step": 22200 |
| 15327 | }, |
| 15328 | { |
| 15329 | "epoch": 31.91, |
| 15330 | "learning_rate": 0.00011019533527696792, |
| 15331 | "loss": 0.0305, |
| 15332 | "step": 22210 |
| 15333 | }, |
| 15334 | { |
| 15335 | "epoch": 31.93, |
| 15336 | "learning_rate": 0.0001101078717201166, |
| 15337 | "loss": 0.0302, |
| 15338 | "step": 22220 |
| 15339 | }, |
| 15340 | { |
| 15341 | "epoch": 31.94, |
| 15342 | "learning_rate": 0.0001100204081632653, |
| 15343 | "loss": 0.0364, |
| 15344 | "step": 22230 |
| 15345 | }, |
| 15346 | { |
| 15347 | "epoch": 31.95, |
| 15348 | "learning_rate": 0.000109932944606414, |
| 15349 | "loss": 0.0331, |
| 15350 | "step": 22240 |
| 15351 | }, |
| 15352 | { |
| 15353 | "epoch": 31.97, |
| 15354 | "learning_rate": 0.00010984548104956267, |
| 15355 | "loss": 0.0286, |
| 15356 | "step": 22250 |
| 15357 | }, |
| 15358 | { |
| 15359 | "epoch": 31.98, |
| 15360 | "learning_rate": 0.00010975801749271136, |
| 15361 | "loss": 0.0303, |
| 15362 | "step": 22260 |
| 15363 | }, |
| 15364 | { |
| 15365 | "epoch": 32.0, |
| 15366 | "learning_rate": 0.00010967055393586006, |
| 15367 | "loss": 0.0318, |
| 15368 | "step": 22270 |
| 15369 | }, |
| 15370 | { |
| 15371 | "epoch": 32.01, |
| 15372 | "learning_rate": 0.00010958309037900875, |
| 15373 | "loss": 0.0431, |
| 15374 | "step": 22280 |
| 15375 | }, |
| 15376 | { |
| 15377 | "epoch": 32.03, |
| 15378 | "learning_rate": 0.00010949562682215742, |
| 15379 | "loss": 0.0271, |
| 15380 | "step": 22290 |
| 15381 | }, |
| 15382 | { |
| 15383 | "epoch": 32.04, |
| 15384 | "learning_rate": 0.00010940816326530611, |
| 15385 | "loss": 0.0298, |
| 15386 | "step": 22300 |
| 15387 | }, |
| 15388 | { |
| 15389 | "epoch": 32.04, |
| 15390 | "eval_loss": 0.1335451751947403, |
| 15391 | "eval_runtime": 40.2607, |
| 15392 | "eval_samples_per_second": 11.351, |
| 15393 | "eval_steps_per_second": 1.441, |
| 15394 | "eval_wer": 0.13251016413190783, |
| 15395 | "step": 22300 |
| 15396 | }, |
| 15397 | { |
| 15398 | "epoch": 32.05, |
| 15399 | "learning_rate": 0.0001093206997084548, |
| 15400 | "loss": 0.0277, |
| 15401 | "step": 22310 |
| 15402 | }, |
| 15403 | { |
| 15404 | "epoch": 32.07, |
| 15405 | "learning_rate": 0.0001092332361516035, |
| 15406 | "loss": 0.0312, |
| 15407 | "step": 22320 |
| 15408 | }, |
| 15409 | { |
| 15410 | "epoch": 32.08, |
| 15411 | "learning_rate": 0.00010914577259475218, |
| 15412 | "loss": 0.0444, |
| 15413 | "step": 22330 |
| 15414 | }, |
| 15415 | { |
| 15416 | "epoch": 32.1, |
| 15417 | "learning_rate": 0.00010905830903790086, |
| 15418 | "loss": 0.0323, |
| 15419 | "step": 22340 |
| 15420 | }, |
| 15421 | { |
| 15422 | "epoch": 32.11, |
| 15423 | "learning_rate": 0.00010897084548104955, |
| 15424 | "loss": 0.0309, |
| 15425 | "step": 22350 |
| 15426 | }, |
| 15427 | { |
| 15428 | "epoch": 32.13, |
| 15429 | "learning_rate": 0.00010888338192419825, |
| 15430 | "loss": 0.0302, |
| 15431 | "step": 22360 |
| 15432 | }, |
| 15433 | { |
| 15434 | "epoch": 32.14, |
| 15435 | "learning_rate": 0.00010879591836734694, |
| 15436 | "loss": 0.0257, |
| 15437 | "step": 22370 |
| 15438 | }, |
| 15439 | { |
| 15440 | "epoch": 32.16, |
| 15441 | "learning_rate": 0.00010870845481049561, |
| 15442 | "loss": 0.0451, |
| 15443 | "step": 22380 |
| 15444 | }, |
| 15445 | { |
| 15446 | "epoch": 32.17, |
| 15447 | "learning_rate": 0.0001086209912536443, |
| 15448 | "loss": 0.0345, |
| 15449 | "step": 22390 |
| 15450 | }, |
| 15451 | { |
| 15452 | "epoch": 32.18, |
| 15453 | "learning_rate": 0.000108533527696793, |
| 15454 | "loss": 0.0251, |
| 15455 | "step": 22400 |
| 15456 | }, |
| 15457 | { |
| 15458 | "epoch": 32.18, |
| 15459 | "eval_loss": 0.133877694606781, |
| 15460 | "eval_runtime": 40.4225, |
| 15461 | "eval_samples_per_second": 11.306, |
| 15462 | "eval_steps_per_second": 1.435, |
| 15463 | "eval_wer": 0.134768860111429, |
| 15464 | "step": 22400 |
| 15465 | }, |
| 15466 | { |
| 15467 | "epoch": 32.2, |
| 15468 | "learning_rate": 0.00010844606413994169, |
| 15469 | "loss": 0.0355, |
| 15470 | "step": 22410 |
| 15471 | }, |
| 15472 | { |
| 15473 | "epoch": 32.21, |
| 15474 | "learning_rate": 0.00010835860058309038, |
| 15475 | "loss": 0.0202, |
| 15476 | "step": 22420 |
| 15477 | }, |
| 15478 | { |
| 15479 | "epoch": 32.23, |
| 15480 | "learning_rate": 0.00010827113702623905, |
| 15481 | "loss": 0.0383, |
| 15482 | "step": 22430 |
| 15483 | }, |
| 15484 | { |
| 15485 | "epoch": 32.24, |
| 15486 | "learning_rate": 0.00010818367346938774, |
| 15487 | "loss": 0.0391, |
| 15488 | "step": 22440 |
| 15489 | }, |
| 15490 | { |
| 15491 | "epoch": 32.26, |
| 15492 | "learning_rate": 0.00010809620991253644, |
| 15493 | "loss": 0.0356, |
| 15494 | "step": 22450 |
| 15495 | }, |
| 15496 | { |
| 15497 | "epoch": 32.27, |
| 15498 | "learning_rate": 0.00010800874635568513, |
| 15499 | "loss": 0.0307, |
| 15500 | "step": 22460 |
| 15501 | }, |
| 15502 | { |
| 15503 | "epoch": 32.28, |
| 15504 | "learning_rate": 0.0001079212827988338, |
| 15505 | "loss": 0.0267, |
| 15506 | "step": 22470 |
| 15507 | }, |
| 15508 | { |
| 15509 | "epoch": 32.3, |
| 15510 | "learning_rate": 0.00010783381924198249, |
| 15511 | "loss": 0.0341, |
| 15512 | "step": 22480 |
| 15513 | }, |
| 15514 | { |
| 15515 | "epoch": 32.31, |
| 15516 | "learning_rate": 0.00010774635568513119, |
| 15517 | "loss": 0.026, |
| 15518 | "step": 22490 |
| 15519 | }, |
| 15520 | { |
| 15521 | "epoch": 32.33, |
| 15522 | "learning_rate": 0.00010765889212827988, |
| 15523 | "loss": 0.0287, |
| 15524 | "step": 22500 |
| 15525 | }, |
| 15526 | { |
| 15527 | "epoch": 32.33, |
| 15528 | "eval_loss": 0.14132900536060333, |
| 15529 | "eval_runtime": 40.4253, |
| 15530 | "eval_samples_per_second": 11.305, |
| 15531 | "eval_steps_per_second": 1.435, |
| 15532 | "eval_wer": 0.13371480198765245, |
| 15533 | "step": 22500 |
| 15534 | }, |
| 15535 | { |
| 15536 | "epoch": 32.34, |
| 15537 | "learning_rate": 0.00010757142857142857, |
| 15538 | "loss": 0.0334, |
| 15539 | "step": 22510 |
| 15540 | }, |
| 15541 | { |
| 15542 | "epoch": 32.36, |
| 15543 | "learning_rate": 0.00010748396501457724, |
| 15544 | "loss": 0.0309, |
| 15545 | "step": 22520 |
| 15546 | }, |
| 15547 | { |
| 15548 | "epoch": 32.37, |
| 15549 | "learning_rate": 0.00010739650145772594, |
| 15550 | "loss": 0.0347, |
| 15551 | "step": 22530 |
| 15552 | }, |
| 15553 | { |
| 15554 | "epoch": 32.39, |
| 15555 | "learning_rate": 0.00010730903790087463, |
| 15556 | "loss": 0.0392, |
| 15557 | "step": 22540 |
| 15558 | }, |
| 15559 | { |
| 15560 | "epoch": 32.4, |
| 15561 | "learning_rate": 0.00010722157434402332, |
| 15562 | "loss": 0.0311, |
| 15563 | "step": 22550 |
| 15564 | }, |
| 15565 | { |
| 15566 | "epoch": 32.41, |
| 15567 | "learning_rate": 0.00010713411078717199, |
| 15568 | "loss": 0.0363, |
| 15569 | "step": 22560 |
| 15570 | }, |
| 15571 | { |
| 15572 | "epoch": 32.43, |
| 15573 | "learning_rate": 0.00010704664723032068, |
| 15574 | "loss": 0.0336, |
| 15575 | "step": 22570 |
| 15576 | }, |
| 15577 | { |
| 15578 | "epoch": 32.44, |
| 15579 | "learning_rate": 0.00010695918367346938, |
| 15580 | "loss": 0.0425, |
| 15581 | "step": 22580 |
| 15582 | }, |
| 15583 | { |
| 15584 | "epoch": 32.46, |
| 15585 | "learning_rate": 0.00010687172011661807, |
| 15586 | "loss": 0.0257, |
| 15587 | "step": 22590 |
| 15588 | }, |
| 15589 | { |
| 15590 | "epoch": 32.47, |
| 15591 | "learning_rate": 0.00010678425655976676, |
| 15592 | "loss": 0.0322, |
| 15593 | "step": 22600 |
| 15594 | }, |
| 15595 | { |
| 15596 | "epoch": 32.47, |
| 15597 | "eval_loss": 0.1421317458152771, |
| 15598 | "eval_runtime": 40.1693, |
| 15599 | "eval_samples_per_second": 11.377, |
| 15600 | "eval_steps_per_second": 1.444, |
| 15601 | "eval_wer": 0.13461828037946091, |
| 15602 | "step": 22600 |
| 15603 | }, |
| 15604 | { |
| 15605 | "epoch": 32.49, |
| 15606 | "learning_rate": 0.00010669679300291543, |
| 15607 | "loss": 0.0385, |
| 15608 | "step": 22610 |
| 15609 | }, |
| 15610 | { |
| 15611 | "epoch": 32.5, |
| 15612 | "learning_rate": 0.00010660932944606413, |
| 15613 | "loss": 0.0222, |
| 15614 | "step": 22620 |
| 15615 | }, |
| 15616 | { |
| 15617 | "epoch": 32.51, |
| 15618 | "learning_rate": 0.00010652186588921282, |
| 15619 | "loss": 0.0464, |
| 15620 | "step": 22630 |
| 15621 | }, |
| 15622 | { |
| 15623 | "epoch": 32.53, |
| 15624 | "learning_rate": 0.00010643440233236151, |
| 15625 | "loss": 0.0272, |
| 15626 | "step": 22640 |
| 15627 | }, |
| 15628 | { |
| 15629 | "epoch": 32.54, |
| 15630 | "learning_rate": 0.00010634693877551018, |
| 15631 | "loss": 0.0287, |
| 15632 | "step": 22650 |
| 15633 | }, |
| 15634 | { |
| 15635 | "epoch": 32.56, |
| 15636 | "learning_rate": 0.00010625947521865889, |
| 15637 | "loss": 0.0261, |
| 15638 | "step": 22660 |
| 15639 | }, |
| 15640 | { |
| 15641 | "epoch": 32.57, |
| 15642 | "learning_rate": 0.00010617201166180757, |
| 15643 | "loss": 0.0238, |
| 15644 | "step": 22670 |
| 15645 | }, |
| 15646 | { |
| 15647 | "epoch": 32.59, |
| 15648 | "learning_rate": 0.00010608454810495626, |
| 15649 | "loss": 0.0369, |
| 15650 | "step": 22680 |
| 15651 | }, |
| 15652 | { |
| 15653 | "epoch": 32.6, |
| 15654 | "learning_rate": 0.00010599708454810495, |
| 15655 | "loss": 0.0292, |
| 15656 | "step": 22690 |
| 15657 | }, |
| 15658 | { |
| 15659 | "epoch": 32.61, |
| 15660 | "learning_rate": 0.00010590962099125362, |
| 15661 | "loss": 0.0274, |
| 15662 | "step": 22700 |
| 15663 | }, |
| 15664 | { |
| 15665 | "epoch": 32.61, |
| 15666 | "eval_loss": 0.1342337280511856, |
| 15667 | "eval_runtime": 40.3469, |
| 15668 | "eval_samples_per_second": 11.327, |
| 15669 | "eval_steps_per_second": 1.438, |
| 15670 | "eval_wer": 0.13145610600813132, |
| 15671 | "step": 22700 |
| 15672 | }, |
| 15673 | { |
| 15674 | "epoch": 32.63, |
| 15675 | "learning_rate": 0.00010582215743440232, |
| 15676 | "loss": 0.0285, |
| 15677 | "step": 22710 |
| 15678 | }, |
| 15679 | { |
| 15680 | "epoch": 32.64, |
| 15681 | "learning_rate": 0.00010573469387755101, |
| 15682 | "loss": 0.0391, |
| 15683 | "step": 22720 |
| 15684 | }, |
| 15685 | { |
| 15686 | "epoch": 32.66, |
| 15687 | "learning_rate": 0.0001056472303206997, |
| 15688 | "loss": 0.0394, |
| 15689 | "step": 22730 |
| 15690 | }, |
| 15691 | { |
| 15692 | "epoch": 32.67, |
| 15693 | "learning_rate": 0.00010555976676384837, |
| 15694 | "loss": 0.0302, |
| 15695 | "step": 22740 |
| 15696 | }, |
| 15697 | { |
| 15698 | "epoch": 32.69, |
| 15699 | "learning_rate": 0.00010547230320699708, |
| 15700 | "loss": 0.0268, |
| 15701 | "step": 22750 |
| 15702 | }, |
| 15703 | { |
| 15704 | "epoch": 32.7, |
| 15705 | "learning_rate": 0.00010538483965014576, |
| 15706 | "loss": 0.034, |
| 15707 | "step": 22760 |
| 15708 | }, |
| 15709 | { |
| 15710 | "epoch": 32.72, |
| 15711 | "learning_rate": 0.00010529737609329445, |
| 15712 | "loss": 0.0301, |
| 15713 | "step": 22770 |
| 15714 | }, |
| 15715 | { |
| 15716 | "epoch": 32.73, |
| 15717 | "learning_rate": 0.00010520991253644315, |
| 15718 | "loss": 0.0293, |
| 15719 | "step": 22780 |
| 15720 | }, |
| 15721 | { |
| 15722 | "epoch": 32.74, |
| 15723 | "learning_rate": 0.00010512244897959183, |
| 15724 | "loss": 0.0378, |
| 15725 | "step": 22790 |
| 15726 | }, |
| 15727 | { |
| 15728 | "epoch": 32.76, |
| 15729 | "learning_rate": 0.00010503498542274052, |
| 15730 | "loss": 0.0307, |
| 15731 | "step": 22800 |
| 15732 | }, |
| 15733 | { |
| 15734 | "epoch": 32.76, |
| 15735 | "eval_loss": 0.1377181112766266, |
| 15736 | "eval_runtime": 40.1267, |
| 15737 | "eval_samples_per_second": 11.389, |
| 15738 | "eval_steps_per_second": 1.445, |
| 15739 | "eval_wer": 0.13160668574009937, |
| 15740 | "step": 22800 |
| 15741 | }, |
| 15742 | { |
| 15743 | "epoch": 32.77, |
| 15744 | "learning_rate": 0.0001049475218658892, |
| 15745 | "loss": 0.034, |
| 15746 | "step": 22810 |
| 15747 | }, |
| 15748 | { |
| 15749 | "epoch": 32.79, |
| 15750 | "learning_rate": 0.00010486005830903789, |
| 15751 | "loss": 0.0302, |
| 15752 | "step": 22820 |
| 15753 | }, |
| 15754 | { |
| 15755 | "epoch": 32.8, |
| 15756 | "learning_rate": 0.00010477259475218658, |
| 15757 | "loss": 0.0349, |
| 15758 | "step": 22830 |
| 15759 | }, |
| 15760 | { |
| 15761 | "epoch": 32.82, |
| 15762 | "learning_rate": 0.00010468513119533527, |
| 15763 | "loss": 0.0373, |
| 15764 | "step": 22840 |
| 15765 | }, |
| 15766 | { |
| 15767 | "epoch": 32.83, |
| 15768 | "learning_rate": 0.00010459766763848396, |
| 15769 | "loss": 0.0304, |
| 15770 | "step": 22850 |
| 15771 | }, |
| 15772 | { |
| 15773 | "epoch": 32.84, |
| 15774 | "learning_rate": 0.00010451020408163264, |
| 15775 | "loss": 0.0311, |
| 15776 | "step": 22860 |
| 15777 | }, |
| 15778 | { |
| 15779 | "epoch": 32.86, |
| 15780 | "learning_rate": 0.00010442274052478134, |
| 15781 | "loss": 0.0352, |
| 15782 | "step": 22870 |
| 15783 | }, |
| 15784 | { |
| 15785 | "epoch": 32.87, |
| 15786 | "learning_rate": 0.00010433527696793002, |
| 15787 | "loss": 0.0306, |
| 15788 | "step": 22880 |
| 15789 | }, |
| 15790 | { |
| 15791 | "epoch": 32.89, |
| 15792 | "learning_rate": 0.0001042478134110787, |
| 15793 | "loss": 0.0288, |
| 15794 | "step": 22890 |
| 15795 | }, |
| 15796 | { |
| 15797 | "epoch": 32.9, |
| 15798 | "learning_rate": 0.0001041603498542274, |
| 15799 | "loss": 0.0297, |
| 15800 | "step": 22900 |
| 15801 | }, |
| 15802 | { |
| 15803 | "epoch": 32.9, |
| 15804 | "eval_loss": 0.13861913979053497, |
| 15805 | "eval_runtime": 40.2824, |
| 15806 | "eval_samples_per_second": 11.345, |
| 15807 | "eval_steps_per_second": 1.44, |
| 15808 | "eval_wer": 0.1322090046679717, |
| 15809 | "step": 22900 |
| 15810 | }, |
| 15811 | { |
| 15812 | "epoch": 32.92, |
| 15813 | "learning_rate": 0.0001040728862973761, |
| 15814 | "loss": 0.0379, |
| 15815 | "step": 22910 |
| 15816 | }, |
| 15817 | { |
| 15818 | "epoch": 32.93, |
| 15819 | "learning_rate": 0.00010398542274052477, |
| 15820 | "loss": 0.0299, |
| 15821 | "step": 22920 |
| 15822 | }, |
| 15823 | { |
| 15824 | "epoch": 32.95, |
| 15825 | "learning_rate": 0.00010389795918367346, |
| 15826 | "loss": 0.0483, |
| 15827 | "step": 22930 |
| 15828 | }, |
| 15829 | { |
| 15830 | "epoch": 32.96, |
| 15831 | "learning_rate": 0.00010381049562682215, |
| 15832 | "loss": 0.0323, |
| 15833 | "step": 22940 |
| 15834 | }, |
| 15835 | { |
| 15836 | "epoch": 32.97, |
| 15837 | "learning_rate": 0.00010372303206997083, |
| 15838 | "loss": 0.0406, |
| 15839 | "step": 22950 |
| 15840 | }, |
| 15841 | { |
| 15842 | "epoch": 32.99, |
| 15843 | "learning_rate": 0.00010363556851311954, |
| 15844 | "loss": 0.0332, |
| 15845 | "step": 22960 |
| 15846 | }, |
| 15847 | { |
| 15848 | "epoch": 33.0, |
| 15849 | "learning_rate": 0.00010354810495626821, |
| 15850 | "loss": 0.0298, |
| 15851 | "step": 22970 |
| 15852 | }, |
| 15853 | { |
| 15854 | "epoch": 33.02, |
| 15855 | "learning_rate": 0.0001034606413994169, |
| 15856 | "loss": 0.0409, |
| 15857 | "step": 22980 |
| 15858 | }, |
| 15859 | { |
| 15860 | "epoch": 33.03, |
| 15861 | "learning_rate": 0.00010337317784256559, |
| 15862 | "loss": 0.0228, |
| 15863 | "step": 22990 |
| 15864 | }, |
| 15865 | { |
| 15866 | "epoch": 33.05, |
| 15867 | "learning_rate": 0.00010328571428571429, |
| 15868 | "loss": 0.0311, |
| 15869 | "step": 23000 |
| 15870 | }, |
| 15871 | { |
| 15872 | "epoch": 33.05, |
| 15873 | "eval_loss": 0.13526782393455505, |
| 15874 | "eval_runtime": 40.1803, |
| 15875 | "eval_samples_per_second": 11.374, |
| 15876 | "eval_steps_per_second": 1.443, |
| 15877 | "eval_wer": 0.13175726547206745, |
| 15878 | "step": 23000 |
| 15879 | }, |
| 15880 | { |
| 15881 | "epoch": 33.06, |
| 15882 | "learning_rate": 0.00010319825072886296, |
| 15883 | "loss": 0.0345, |
| 15884 | "step": 23010 |
| 15885 | }, |
| 15886 | { |
| 15887 | "epoch": 33.07, |
| 15888 | "learning_rate": 0.00010311078717201165, |
| 15889 | "loss": 0.0289, |
| 15890 | "step": 23020 |
| 15891 | }, |
| 15892 | { |
| 15893 | "epoch": 33.09, |
| 15894 | "learning_rate": 0.00010302332361516034, |
| 15895 | "loss": 0.0321, |
| 15896 | "step": 23030 |
| 15897 | }, |
| 15898 | { |
| 15899 | "epoch": 33.1, |
| 15900 | "learning_rate": 0.00010293586005830904, |
| 15901 | "loss": 0.0231, |
| 15902 | "step": 23040 |
| 15903 | }, |
| 15904 | { |
| 15905 | "epoch": 33.12, |
| 15906 | "learning_rate": 0.00010284839650145773, |
| 15907 | "loss": 0.0366, |
| 15908 | "step": 23050 |
| 15909 | }, |
| 15910 | { |
| 15911 | "epoch": 33.13, |
| 15912 | "learning_rate": 0.0001027609329446064, |
| 15913 | "loss": 0.0343, |
| 15914 | "step": 23060 |
| 15915 | }, |
| 15916 | { |
| 15917 | "epoch": 33.15, |
| 15918 | "learning_rate": 0.00010267346938775509, |
| 15919 | "loss": 0.0263, |
| 15920 | "step": 23070 |
| 15921 | }, |
| 15922 | { |
| 15923 | "epoch": 33.16, |
| 15924 | "learning_rate": 0.00010258600583090379, |
| 15925 | "loss": 0.0291, |
| 15926 | "step": 23080 |
| 15927 | }, |
| 15928 | { |
| 15929 | "epoch": 33.18, |
| 15930 | "learning_rate": 0.00010249854227405248, |
| 15931 | "loss": 0.0263, |
| 15932 | "step": 23090 |
| 15933 | }, |
| 15934 | { |
| 15935 | "epoch": 33.19, |
| 15936 | "learning_rate": 0.00010241107871720115, |
| 15937 | "loss": 0.0402, |
| 15938 | "step": 23100 |
| 15939 | }, |
| 15940 | { |
| 15941 | "epoch": 33.19, |
| 15942 | "eval_loss": 0.1352507621049881, |
| 15943 | "eval_runtime": 40.2484, |
| 15944 | "eval_samples_per_second": 11.354, |
| 15945 | "eval_steps_per_second": 1.441, |
| 15946 | "eval_wer": 0.13130552627616324, |
| 15947 | "step": 23100 |
| 15948 | }, |
| 15949 | { |
| 15950 | "epoch": 33.2, |
| 15951 | "learning_rate": 0.00010232361516034984, |
| 15952 | "loss": 0.0336, |
| 15953 | "step": 23110 |
| 15954 | }, |
| 15955 | { |
| 15956 | "epoch": 33.22, |
| 15957 | "learning_rate": 0.00010223615160349853, |
| 15958 | "loss": 0.0223, |
| 15959 | "step": 23120 |
| 15960 | }, |
| 15961 | { |
| 15962 | "epoch": 33.23, |
| 15963 | "learning_rate": 0.00010214868804664723, |
| 15964 | "loss": 0.0308, |
| 15965 | "step": 23130 |
| 15966 | }, |
| 15967 | { |
| 15968 | "epoch": 33.25, |
| 15969 | "learning_rate": 0.00010206122448979592, |
| 15970 | "loss": 0.0265, |
| 15971 | "step": 23140 |
| 15972 | }, |
| 15973 | { |
| 15974 | "epoch": 33.26, |
| 15975 | "learning_rate": 0.00010197376093294459, |
| 15976 | "loss": 0.0335, |
| 15977 | "step": 23150 |
| 15978 | }, |
| 15979 | { |
| 15980 | "epoch": 33.28, |
| 15981 | "learning_rate": 0.00010188629737609328, |
| 15982 | "loss": 0.0282, |
| 15983 | "step": 23160 |
| 15984 | }, |
| 15985 | { |
| 15986 | "epoch": 33.29, |
| 15987 | "learning_rate": 0.00010179883381924198, |
| 15988 | "loss": 0.0322, |
| 15989 | "step": 23170 |
| 15990 | }, |
| 15991 | { |
| 15992 | "epoch": 33.3, |
| 15993 | "learning_rate": 0.00010171137026239067, |
| 15994 | "loss": 0.0352, |
| 15995 | "step": 23180 |
| 15996 | }, |
| 15997 | { |
| 15998 | "epoch": 33.32, |
| 15999 | "learning_rate": 0.00010162390670553934, |
| 16000 | "loss": 0.0235, |
| 16001 | "step": 23190 |
| 16002 | }, |
| 16003 | { |
| 16004 | "epoch": 33.33, |
| 16005 | "learning_rate": 0.00010153644314868803, |
| 16006 | "loss": 0.0327, |
| 16007 | "step": 23200 |
| 16008 | }, |
| 16009 | { |
| 16010 | "epoch": 33.33, |
| 16011 | "eval_loss": 0.13268069922924042, |
| 16012 | "eval_runtime": 40.328, |
| 16013 | "eval_samples_per_second": 11.332, |
| 16014 | "eval_steps_per_second": 1.438, |
| 16015 | "eval_wer": 0.1341665411835567, |
| 16016 | "step": 23200 |
| 16017 | }, |
| 16018 | { |
| 16019 | "epoch": 33.35, |
| 16020 | "learning_rate": 0.00010144897959183673, |
| 16021 | "loss": 0.0308, |
| 16022 | "step": 23210 |
| 16023 | }, |
| 16024 | { |
| 16025 | "epoch": 33.36, |
| 16026 | "learning_rate": 0.00010136151603498542, |
| 16027 | "loss": 0.032, |
| 16028 | "step": 23220 |
| 16029 | }, |
| 16030 | { |
| 16031 | "epoch": 33.38, |
| 16032 | "learning_rate": 0.00010127405247813411, |
| 16033 | "loss": 0.0361, |
| 16034 | "step": 23230 |
| 16035 | }, |
| 16036 | { |
| 16037 | "epoch": 33.39, |
| 16038 | "learning_rate": 0.00010118658892128278, |
| 16039 | "loss": 0.0276, |
| 16040 | "step": 23240 |
| 16041 | }, |
| 16042 | { |
| 16043 | "epoch": 33.41, |
| 16044 | "learning_rate": 0.00010109912536443147, |
| 16045 | "loss": 0.0325, |
| 16046 | "step": 23250 |
| 16047 | }, |
| 16048 | { |
| 16049 | "epoch": 33.42, |
| 16050 | "learning_rate": 0.00010101166180758017, |
| 16051 | "loss": 0.0301, |
| 16052 | "step": 23260 |
| 16053 | }, |
| 16054 | { |
| 16055 | "epoch": 33.43, |
| 16056 | "learning_rate": 0.00010092419825072886, |
| 16057 | "loss": 0.0376, |
| 16058 | "step": 23270 |
| 16059 | }, |
| 16060 | { |
| 16061 | "epoch": 33.45, |
| 16062 | "learning_rate": 0.00010083673469387753, |
| 16063 | "loss": 0.0297, |
| 16064 | "step": 23280 |
| 16065 | }, |
| 16066 | { |
| 16067 | "epoch": 33.46, |
| 16068 | "learning_rate": 0.00010074927113702622, |
| 16069 | "loss": 0.028, |
| 16070 | "step": 23290 |
| 16071 | }, |
| 16072 | { |
| 16073 | "epoch": 33.48, |
| 16074 | "learning_rate": 0.00010066180758017492, |
| 16075 | "loss": 0.0249, |
| 16076 | "step": 23300 |
| 16077 | }, |
| 16078 | { |
| 16079 | "epoch": 33.48, |
| 16080 | "eval_loss": 0.13825057446956635, |
| 16081 | "eval_runtime": 40.2776, |
| 16082 | "eval_samples_per_second": 11.346, |
| 16083 | "eval_steps_per_second": 1.44, |
| 16084 | "eval_wer": 0.13687697635898208, |
| 16085 | "step": 23300 |
| 16086 | }, |
| 16087 | { |
| 16088 | "epoch": 33.49, |
| 16089 | "learning_rate": 0.00010057434402332361, |
| 16090 | "loss": 0.0319, |
| 16091 | "step": 23310 |
| 16092 | }, |
| 16093 | { |
| 16094 | "epoch": 33.51, |
| 16095 | "learning_rate": 0.0001004868804664723, |
| 16096 | "loss": 0.0353, |
| 16097 | "step": 23320 |
| 16098 | }, |
| 16099 | { |
| 16100 | "epoch": 33.52, |
| 16101 | "learning_rate": 0.00010039941690962097, |
| 16102 | "loss": 0.0345, |
| 16103 | "step": 23330 |
| 16104 | }, |
| 16105 | { |
| 16106 | "epoch": 33.53, |
| 16107 | "learning_rate": 0.00010031195335276968, |
| 16108 | "loss": 0.0312, |
| 16109 | "step": 23340 |
| 16110 | }, |
| 16111 | { |
| 16112 | "epoch": 33.55, |
| 16113 | "learning_rate": 0.00010022448979591836, |
| 16114 | "loss": 0.0414, |
| 16115 | "step": 23350 |
| 16116 | }, |
| 16117 | { |
| 16118 | "epoch": 33.56, |
| 16119 | "learning_rate": 0.00010013702623906705, |
| 16120 | "loss": 0.027, |
| 16121 | "step": 23360 |
| 16122 | }, |
| 16123 | { |
| 16124 | "epoch": 33.58, |
| 16125 | "learning_rate": 0.00010004956268221573, |
| 16126 | "loss": 0.0313, |
| 16127 | "step": 23370 |
| 16128 | }, |
| 16129 | { |
| 16130 | "epoch": 33.59, |
| 16131 | "learning_rate": 9.996209912536441e-05, |
| 16132 | "loss": 0.0367, |
| 16133 | "step": 23380 |
| 16134 | }, |
| 16135 | { |
| 16136 | "epoch": 33.61, |
| 16137 | "learning_rate": 9.987463556851312e-05, |
| 16138 | "loss": 0.0298, |
| 16139 | "step": 23390 |
| 16140 | }, |
| 16141 | { |
| 16142 | "epoch": 33.62, |
| 16143 | "learning_rate": 9.97871720116618e-05, |
| 16144 | "loss": 0.0331, |
| 16145 | "step": 23400 |
| 16146 | }, |
| 16147 | { |
| 16148 | "epoch": 33.62, |
| 16149 | "eval_loss": 0.13275952637195587, |
| 16150 | "eval_runtime": 40.5257, |
| 16151 | "eval_samples_per_second": 11.277, |
| 16152 | "eval_steps_per_second": 1.431, |
| 16153 | "eval_wer": 0.13356422225568437, |
| 16154 | "step": 23400 |
| 16155 | }, |
| 16156 | { |
| 16157 | "epoch": 33.64, |
| 16158 | "learning_rate": 9.969970845481049e-05, |
| 16159 | "loss": 0.0283, |
| 16160 | "step": 23410 |
| 16161 | }, |
| 16162 | { |
| 16163 | "epoch": 33.65, |
| 16164 | "learning_rate": 9.961224489795917e-05, |
| 16165 | "loss": 0.0227, |
| 16166 | "step": 23420 |
| 16167 | }, |
| 16168 | { |
| 16169 | "epoch": 33.66, |
| 16170 | "learning_rate": 9.952478134110787e-05, |
| 16171 | "loss": 0.0382, |
| 16172 | "step": 23430 |
| 16173 | }, |
| 16174 | { |
| 16175 | "epoch": 33.68, |
| 16176 | "learning_rate": 9.943731778425655e-05, |
| 16177 | "loss": 0.0297, |
| 16178 | "step": 23440 |
| 16179 | }, |
| 16180 | { |
| 16181 | "epoch": 33.69, |
| 16182 | "learning_rate": 9.934985422740524e-05, |
| 16183 | "loss": 0.0435, |
| 16184 | "step": 23450 |
| 16185 | }, |
| 16186 | { |
| 16187 | "epoch": 33.71, |
| 16188 | "learning_rate": 9.926239067055392e-05, |
| 16189 | "loss": 0.0277, |
| 16190 | "step": 23460 |
| 16191 | }, |
| 16192 | { |
| 16193 | "epoch": 33.72, |
| 16194 | "learning_rate": 9.917492711370262e-05, |
| 16195 | "loss": 0.0277, |
| 16196 | "step": 23470 |
| 16197 | }, |
| 16198 | { |
| 16199 | "epoch": 33.74, |
| 16200 | "learning_rate": 9.90874635568513e-05, |
| 16201 | "loss": 0.0335, |
| 16202 | "step": 23480 |
| 16203 | }, |
| 16204 | { |
| 16205 | "epoch": 33.75, |
| 16206 | "learning_rate": 9.9e-05, |
| 16207 | "loss": 0.0244, |
| 16208 | "step": 23490 |
| 16209 | }, |
| 16210 | { |
| 16211 | "epoch": 33.76, |
| 16212 | "learning_rate": 9.891253644314867e-05, |
| 16213 | "loss": 0.0249, |
| 16214 | "step": 23500 |
| 16215 | }, |
| 16216 | { |
| 16217 | "epoch": 33.76, |
| 16218 | "eval_loss": 0.13773199915885925, |
| 16219 | "eval_runtime": 40.1237, |
| 16220 | "eval_samples_per_second": 11.39, |
| 16221 | "eval_steps_per_second": 1.446, |
| 16222 | "eval_wer": 0.13296190332781208, |
| 16223 | "step": 23500 |
| 16224 | }, |
| 16225 | { |
| 16226 | "epoch": 33.78, |
| 16227 | "learning_rate": 9.882507288629736e-05, |
| 16228 | "loss": 0.0326, |
| 16229 | "step": 23510 |
| 16230 | }, |
| 16231 | { |
| 16232 | "epoch": 33.79, |
| 16233 | "learning_rate": 9.873760932944606e-05, |
| 16234 | "loss": 0.0273, |
| 16235 | "step": 23520 |
| 16236 | }, |
| 16237 | { |
| 16238 | "epoch": 33.81, |
| 16239 | "learning_rate": 9.865014577259475e-05, |
| 16240 | "loss": 0.033, |
| 16241 | "step": 23530 |
| 16242 | }, |
| 16243 | { |
| 16244 | "epoch": 33.82, |
| 16245 | "learning_rate": 9.856268221574343e-05, |
| 16246 | "loss": 0.0273, |
| 16247 | "step": 23540 |
| 16248 | }, |
| 16249 | { |
| 16250 | "epoch": 33.84, |
| 16251 | "learning_rate": 9.847521865889211e-05, |
| 16252 | "loss": 0.0266, |
| 16253 | "step": 23550 |
| 16254 | }, |
| 16255 | { |
| 16256 | "epoch": 33.85, |
| 16257 | "learning_rate": 9.838775510204081e-05, |
| 16258 | "loss": 0.0297, |
| 16259 | "step": 23560 |
| 16260 | }, |
| 16261 | { |
| 16262 | "epoch": 33.86, |
| 16263 | "learning_rate": 9.83002915451895e-05, |
| 16264 | "loss": 0.033, |
| 16265 | "step": 23570 |
| 16266 | }, |
| 16267 | { |
| 16268 | "epoch": 33.88, |
| 16269 | "learning_rate": 9.821282798833819e-05, |
| 16270 | "loss": 0.0366, |
| 16271 | "step": 23580 |
| 16272 | }, |
| 16273 | { |
| 16274 | "epoch": 33.89, |
| 16275 | "learning_rate": 9.812536443148686e-05, |
| 16276 | "loss": 0.0279, |
| 16277 | "step": 23590 |
| 16278 | }, |
| 16279 | { |
| 16280 | "epoch": 33.91, |
| 16281 | "learning_rate": 9.803790087463556e-05, |
| 16282 | "loss": 0.0374, |
| 16283 | "step": 23600 |
| 16284 | }, |
| 16285 | { |
| 16286 | "epoch": 33.91, |
| 16287 | "eval_loss": 0.13894473016262054, |
| 16288 | "eval_runtime": 40.1032, |
| 16289 | "eval_samples_per_second": 11.396, |
| 16290 | "eval_steps_per_second": 1.446, |
| 16291 | "eval_wer": 0.1287456708327059, |
| 16292 | "step": 23600 |
| 16293 | }, |
| 16294 | { |
| 16295 | "epoch": 33.92, |
| 16296 | "learning_rate": 9.795043731778425e-05, |
| 16297 | "loss": 0.0311, |
| 16298 | "step": 23610 |
| 16299 | }, |
| 16300 | { |
| 16301 | "epoch": 33.94, |
| 16302 | "learning_rate": 9.786297376093294e-05, |
| 16303 | "loss": 0.0306, |
| 16304 | "step": 23620 |
| 16305 | }, |
| 16306 | { |
| 16307 | "epoch": 33.95, |
| 16308 | "learning_rate": 9.777551020408162e-05, |
| 16309 | "loss": 0.0286, |
| 16310 | "step": 23630 |
| 16311 | }, |
| 16312 | { |
| 16313 | "epoch": 33.97, |
| 16314 | "learning_rate": 9.768804664723031e-05, |
| 16315 | "loss": 0.0365, |
| 16316 | "step": 23640 |
| 16317 | }, |
| 16318 | { |
| 16319 | "epoch": 33.98, |
| 16320 | "learning_rate": 9.7600583090379e-05, |
| 16321 | "loss": 0.0326, |
| 16322 | "step": 23650 |
| 16323 | }, |
| 16324 | { |
| 16325 | "epoch": 33.99, |
| 16326 | "learning_rate": 9.751311953352769e-05, |
| 16327 | "loss": 0.0268, |
| 16328 | "step": 23660 |
| 16329 | }, |
| 16330 | { |
| 16331 | "epoch": 34.01, |
| 16332 | "learning_rate": 9.742565597667638e-05, |
| 16333 | "loss": 0.0312, |
| 16334 | "step": 23670 |
| 16335 | }, |
| 16336 | { |
| 16337 | "epoch": 34.02, |
| 16338 | "learning_rate": 9.733819241982505e-05, |
| 16339 | "loss": 0.0326, |
| 16340 | "step": 23680 |
| 16341 | }, |
| 16342 | { |
| 16343 | "epoch": 34.04, |
| 16344 | "learning_rate": 9.725072886297375e-05, |
| 16345 | "loss": 0.0228, |
| 16346 | "step": 23690 |
| 16347 | }, |
| 16348 | { |
| 16349 | "epoch": 34.05, |
| 16350 | "learning_rate": 9.716326530612244e-05, |
| 16351 | "loss": 0.0356, |
| 16352 | "step": 23700 |
| 16353 | }, |
| 16354 | { |
| 16355 | "epoch": 34.05, |
| 16356 | "eval_loss": 0.13883648812770844, |
| 16357 | "eval_runtime": 40.284, |
| 16358 | "eval_samples_per_second": 11.344, |
| 16359 | "eval_steps_per_second": 1.44, |
| 16360 | "eval_wer": 0.12964914922451437, |
| 16361 | "step": 23700 |
| 16362 | }, |
| 16363 | { |
| 16364 | "epoch": 34.07, |
| 16365 | "learning_rate": 9.707580174927113e-05, |
| 16366 | "loss": 0.0236, |
| 16367 | "step": 23710 |
| 16368 | }, |
| 16369 | { |
| 16370 | "epoch": 34.08, |
| 16371 | "learning_rate": 9.698833819241983e-05, |
| 16372 | "loss": 0.0282, |
| 16373 | "step": 23720 |
| 16374 | }, |
| 16375 | { |
| 16376 | "epoch": 34.09, |
| 16377 | "learning_rate": 9.69008746355685e-05, |
| 16378 | "loss": 0.0319, |
| 16379 | "step": 23730 |
| 16380 | }, |
| 16381 | { |
| 16382 | "epoch": 34.11, |
| 16383 | "learning_rate": 9.681341107871719e-05, |
| 16384 | "loss": 0.0324, |
| 16385 | "step": 23740 |
| 16386 | }, |
| 16387 | { |
| 16388 | "epoch": 34.12, |
| 16389 | "learning_rate": 9.672594752186588e-05, |
| 16390 | "loss": 0.0314, |
| 16391 | "step": 23750 |
| 16392 | }, |
| 16393 | { |
| 16394 | "epoch": 34.14, |
| 16395 | "learning_rate": 9.663848396501457e-05, |
| 16396 | "loss": 0.0232, |
| 16397 | "step": 23760 |
| 16398 | }, |
| 16399 | { |
| 16400 | "epoch": 34.15, |
| 16401 | "learning_rate": 9.655102040816326e-05, |
| 16402 | "loss": 0.028, |
| 16403 | "step": 23770 |
| 16404 | }, |
| 16405 | { |
| 16406 | "epoch": 34.17, |
| 16407 | "learning_rate": 9.646355685131194e-05, |
| 16408 | "loss": 0.0244, |
| 16409 | "step": 23780 |
| 16410 | }, |
| 16411 | { |
| 16412 | "epoch": 34.18, |
| 16413 | "learning_rate": 9.637609329446063e-05, |
| 16414 | "loss": 0.0243, |
| 16415 | "step": 23790 |
| 16416 | }, |
| 16417 | { |
| 16418 | "epoch": 34.2, |
| 16419 | "learning_rate": 9.628862973760932e-05, |
| 16420 | "loss": 0.0337, |
| 16421 | "step": 23800 |
| 16422 | }, |
| 16423 | { |
| 16424 | "epoch": 34.2, |
| 16425 | "eval_loss": 0.13111823797225952, |
| 16426 | "eval_runtime": 40.2412, |
| 16427 | "eval_samples_per_second": 11.357, |
| 16428 | "eval_steps_per_second": 1.441, |
| 16429 | "eval_wer": 0.1287456708327059, |
| 16430 | "step": 23800 |
| 16431 | }, |
| 16432 | { |
| 16433 | "epoch": 34.21, |
| 16434 | "learning_rate": 9.620116618075802e-05, |
| 16435 | "loss": 0.0394, |
| 16436 | "step": 23810 |
| 16437 | }, |
| 16438 | { |
| 16439 | "epoch": 34.22, |
| 16440 | "learning_rate": 9.61137026239067e-05, |
| 16441 | "loss": 0.0362, |
| 16442 | "step": 23820 |
| 16443 | }, |
| 16444 | { |
| 16445 | "epoch": 34.24, |
| 16446 | "learning_rate": 9.602623906705538e-05, |
| 16447 | "loss": 0.0246, |
| 16448 | "step": 23830 |
| 16449 | }, |
| 16450 | { |
| 16451 | "epoch": 34.25, |
| 16452 | "learning_rate": 9.593877551020407e-05, |
| 16453 | "loss": 0.025, |
| 16454 | "step": 23840 |
| 16455 | }, |
| 16456 | { |
| 16457 | "epoch": 34.27, |
| 16458 | "learning_rate": 9.585131195335277e-05, |
| 16459 | "loss": 0.0399, |
| 16460 | "step": 23850 |
| 16461 | }, |
| 16462 | { |
| 16463 | "epoch": 34.28, |
| 16464 | "learning_rate": 9.576384839650145e-05, |
| 16465 | "loss": 0.0253, |
| 16466 | "step": 23860 |
| 16467 | }, |
| 16468 | { |
| 16469 | "epoch": 34.3, |
| 16470 | "learning_rate": 9.567638483965013e-05, |
| 16471 | "loss": 0.0316, |
| 16472 | "step": 23870 |
| 16473 | }, |
| 16474 | { |
| 16475 | "epoch": 34.31, |
| 16476 | "learning_rate": 9.558892128279882e-05, |
| 16477 | "loss": 0.0288, |
| 16478 | "step": 23880 |
| 16479 | }, |
| 16480 | { |
| 16481 | "epoch": 34.32, |
| 16482 | "learning_rate": 9.550145772594751e-05, |
| 16483 | "loss": 0.0204, |
| 16484 | "step": 23890 |
| 16485 | }, |
| 16486 | { |
| 16487 | "epoch": 34.34, |
| 16488 | "learning_rate": 9.541399416909621e-05, |
| 16489 | "loss": 0.026, |
| 16490 | "step": 23900 |
| 16491 | }, |
| 16492 | { |
| 16493 | "epoch": 34.34, |
| 16494 | "eval_loss": 0.1346319168806076, |
| 16495 | "eval_runtime": 40.2297, |
| 16496 | "eval_samples_per_second": 11.36, |
| 16497 | "eval_steps_per_second": 1.442, |
| 16498 | "eval_wer": 0.1275410329769613, |
| 16499 | "step": 23900 |
| 16500 | }, |
| 16501 | { |
| 16502 | "epoch": 34.35, |
| 16503 | "learning_rate": 9.532653061224489e-05, |
| 16504 | "loss": 0.0241, |
| 16505 | "step": 23910 |
| 16506 | }, |
| 16507 | { |
| 16508 | "epoch": 34.37, |
| 16509 | "learning_rate": 9.523906705539357e-05, |
| 16510 | "loss": 0.0293, |
| 16511 | "step": 23920 |
| 16512 | }, |
| 16513 | { |
| 16514 | "epoch": 34.38, |
| 16515 | "learning_rate": 9.515160349854226e-05, |
| 16516 | "loss": 0.0265, |
| 16517 | "step": 23930 |
| 16518 | }, |
| 16519 | { |
| 16520 | "epoch": 34.4, |
| 16521 | "learning_rate": 9.506413994169096e-05, |
| 16522 | "loss": 0.0344, |
| 16523 | "step": 23940 |
| 16524 | }, |
| 16525 | { |
| 16526 | "epoch": 34.41, |
| 16527 | "learning_rate": 9.497667638483964e-05, |
| 16528 | "loss": 0.0308, |
| 16529 | "step": 23950 |
| 16530 | }, |
| 16531 | { |
| 16532 | "epoch": 34.43, |
| 16533 | "learning_rate": 9.488921282798833e-05, |
| 16534 | "loss": 0.0256, |
| 16535 | "step": 23960 |
| 16536 | }, |
| 16537 | { |
| 16538 | "epoch": 34.44, |
| 16539 | "learning_rate": 9.480174927113701e-05, |
| 16540 | "loss": 0.0286, |
| 16541 | "step": 23970 |
| 16542 | }, |
| 16543 | { |
| 16544 | "epoch": 34.45, |
| 16545 | "learning_rate": 9.471428571428571e-05, |
| 16546 | "loss": 0.0393, |
| 16547 | "step": 23980 |
| 16548 | }, |
| 16549 | { |
| 16550 | "epoch": 34.47, |
| 16551 | "learning_rate": 9.46268221574344e-05, |
| 16552 | "loss": 0.0203, |
| 16553 | "step": 23990 |
| 16554 | }, |
| 16555 | { |
| 16556 | "epoch": 34.48, |
| 16557 | "learning_rate": 9.453935860058308e-05, |
| 16558 | "loss": 0.0312, |
| 16559 | "step": 24000 |
| 16560 | }, |
| 16561 | { |
| 16562 | "epoch": 34.48, |
| 16563 | "eval_loss": 0.1321752965450287, |
| 16564 | "eval_runtime": 40.3973, |
| 16565 | "eval_samples_per_second": 11.313, |
| 16566 | "eval_steps_per_second": 1.436, |
| 16567 | "eval_wer": 0.12919741002861015, |
| 16568 | "step": 24000 |
| 16569 | }, |
| 16570 | { |
| 16571 | "epoch": 34.5, |
| 16572 | "learning_rate": 9.445189504373176e-05, |
| 16573 | "loss": 0.0277, |
| 16574 | "step": 24010 |
| 16575 | }, |
| 16576 | { |
| 16577 | "epoch": 34.51, |
| 16578 | "learning_rate": 9.436443148688047e-05, |
| 16579 | "loss": 0.0386, |
| 16580 | "step": 24020 |
| 16581 | }, |
| 16582 | { |
| 16583 | "epoch": 34.53, |
| 16584 | "learning_rate": 9.427696793002915e-05, |
| 16585 | "loss": 0.0385, |
| 16586 | "step": 24030 |
| 16587 | }, |
| 16588 | { |
| 16589 | "epoch": 34.54, |
| 16590 | "learning_rate": 9.418950437317783e-05, |
| 16591 | "loss": 0.0285, |
| 16592 | "step": 24040 |
| 16593 | }, |
| 16594 | { |
| 16595 | "epoch": 34.55, |
| 16596 | "learning_rate": 9.410204081632652e-05, |
| 16597 | "loss": 0.0305, |
| 16598 | "step": 24050 |
| 16599 | }, |
| 16600 | { |
| 16601 | "epoch": 34.57, |
| 16602 | "learning_rate": 9.40145772594752e-05, |
| 16603 | "loss": 0.0206, |
| 16604 | "step": 24060 |
| 16605 | }, |
| 16606 | { |
| 16607 | "epoch": 34.58, |
| 16608 | "learning_rate": 9.39271137026239e-05, |
| 16609 | "loss": 0.0479, |
| 16610 | "step": 24070 |
| 16611 | }, |
| 16612 | { |
| 16613 | "epoch": 34.6, |
| 16614 | "learning_rate": 9.38396501457726e-05, |
| 16615 | "loss": 0.0314, |
| 16616 | "step": 24080 |
| 16617 | }, |
| 16618 | { |
| 16619 | "epoch": 34.61, |
| 16620 | "learning_rate": 9.375218658892127e-05, |
| 16621 | "loss": 0.0233, |
| 16622 | "step": 24090 |
| 16623 | }, |
| 16624 | { |
| 16625 | "epoch": 34.63, |
| 16626 | "learning_rate": 9.366472303206996e-05, |
| 16627 | "loss": 0.0285, |
| 16628 | "step": 24100 |
| 16629 | }, |
| 16630 | { |
| 16631 | "epoch": 34.63, |
| 16632 | "eval_loss": 0.13412344455718994, |
| 16633 | "eval_runtime": 40.2936, |
| 16634 | "eval_samples_per_second": 11.342, |
| 16635 | "eval_steps_per_second": 1.439, |
| 16636 | "eval_wer": 0.13100436681222707, |
| 16637 | "step": 24100 |
| 16638 | }, |
| 16639 | { |
| 16640 | "epoch": 34.64, |
| 16641 | "learning_rate": 9.357725947521866e-05, |
| 16642 | "loss": 0.0229, |
| 16643 | "step": 24110 |
| 16644 | }, |
| 16645 | { |
| 16646 | "epoch": 34.66, |
| 16647 | "learning_rate": 9.348979591836735e-05, |
| 16648 | "loss": 0.0386, |
| 16649 | "step": 24120 |
| 16650 | }, |
| 16651 | { |
| 16652 | "epoch": 34.67, |
| 16653 | "learning_rate": 9.340233236151602e-05, |
| 16654 | "loss": 0.0386, |
| 16655 | "step": 24130 |
| 16656 | }, |
| 16657 | { |
| 16658 | "epoch": 34.68, |
| 16659 | "learning_rate": 9.331486880466471e-05, |
| 16660 | "loss": 0.0278, |
| 16661 | "step": 24140 |
| 16662 | }, |
| 16663 | { |
| 16664 | "epoch": 34.7, |
| 16665 | "learning_rate": 9.322740524781341e-05, |
| 16666 | "loss": 0.0295, |
| 16667 | "step": 24150 |
| 16668 | }, |
| 16669 | { |
| 16670 | "epoch": 34.71, |
| 16671 | "learning_rate": 9.31399416909621e-05, |
| 16672 | "loss": 0.019, |
| 16673 | "step": 24160 |
| 16674 | }, |
| 16675 | { |
| 16676 | "epoch": 34.73, |
| 16677 | "learning_rate": 9.305247813411078e-05, |
| 16678 | "loss": 0.031, |
| 16679 | "step": 24170 |
| 16680 | }, |
| 16681 | { |
| 16682 | "epoch": 34.74, |
| 16683 | "learning_rate": 9.296501457725946e-05, |
| 16684 | "loss": 0.0325, |
| 16685 | "step": 24180 |
| 16686 | }, |
| 16687 | { |
| 16688 | "epoch": 34.76, |
| 16689 | "learning_rate": 9.287755102040815e-05, |
| 16690 | "loss": 0.0343, |
| 16691 | "step": 24190 |
| 16692 | }, |
| 16693 | { |
| 16694 | "epoch": 34.77, |
| 16695 | "learning_rate": 9.279008746355685e-05, |
| 16696 | "loss": 0.0314, |
| 16697 | "step": 24200 |
| 16698 | }, |
| 16699 | { |
| 16700 | "epoch": 34.77, |
| 16701 | "eval_loss": 0.1259945183992386, |
| 16702 | "eval_runtime": 40.0768, |
| 16703 | "eval_samples_per_second": 11.403, |
| 16704 | "eval_steps_per_second": 1.447, |
| 16705 | "eval_wer": 0.130853787080259, |
| 16706 | "step": 24200 |
| 16707 | }, |
| 16708 | { |
| 16709 | "epoch": 34.78, |
| 16710 | "learning_rate": 9.270262390670554e-05, |
| 16711 | "loss": 0.0263, |
| 16712 | "step": 24210 |
| 16713 | }, |
| 16714 | { |
| 16715 | "epoch": 34.8, |
| 16716 | "learning_rate": 9.261516034985421e-05, |
| 16717 | "loss": 0.026, |
| 16718 | "step": 24220 |
| 16719 | }, |
| 16720 | { |
| 16721 | "epoch": 34.81, |
| 16722 | "learning_rate": 9.25276967930029e-05, |
| 16723 | "loss": 0.0285, |
| 16724 | "step": 24230 |
| 16725 | }, |
| 16726 | { |
| 16727 | "epoch": 34.83, |
| 16728 | "learning_rate": 9.24402332361516e-05, |
| 16729 | "loss": 0.0262, |
| 16730 | "step": 24240 |
| 16731 | }, |
| 16732 | { |
| 16733 | "epoch": 34.84, |
| 16734 | "learning_rate": 9.235276967930029e-05, |
| 16735 | "loss": 0.0253, |
| 16736 | "step": 24250 |
| 16737 | }, |
| 16738 | { |
| 16739 | "epoch": 34.86, |
| 16740 | "learning_rate": 9.226530612244898e-05, |
| 16741 | "loss": 0.0243, |
| 16742 | "step": 24260 |
| 16743 | }, |
| 16744 | { |
| 16745 | "epoch": 34.87, |
| 16746 | "learning_rate": 9.217784256559765e-05, |
| 16747 | "loss": 0.0215, |
| 16748 | "step": 24270 |
| 16749 | }, |
| 16750 | { |
| 16751 | "epoch": 34.89, |
| 16752 | "learning_rate": 9.209037900874635e-05, |
| 16753 | "loss": 0.035, |
| 16754 | "step": 24280 |
| 16755 | }, |
| 16756 | { |
| 16757 | "epoch": 34.9, |
| 16758 | "learning_rate": 9.200291545189504e-05, |
| 16759 | "loss": 0.0308, |
| 16760 | "step": 24290 |
| 16761 | }, |
| 16762 | { |
| 16763 | "epoch": 34.91, |
| 16764 | "learning_rate": 9.191545189504373e-05, |
| 16765 | "loss": 0.0318, |
| 16766 | "step": 24300 |
| 16767 | }, |
| 16768 | { |
| 16769 | "epoch": 34.91, |
| 16770 | "eval_loss": 0.13191795349121094, |
| 16771 | "eval_runtime": 40.2331, |
| 16772 | "eval_samples_per_second": 11.359, |
| 16773 | "eval_steps_per_second": 1.442, |
| 16774 | "eval_wer": 0.12995030868845053, |
| 16775 | "step": 24300 |
| 16776 | }, |
| 16777 | { |
| 16778 | "epoch": 34.93, |
| 16779 | "learning_rate": 9.18279883381924e-05, |
| 16780 | "loss": 0.0287, |
| 16781 | "step": 24310 |
| 16782 | }, |
| 16783 | { |
| 16784 | "epoch": 34.94, |
| 16785 | "learning_rate": 9.174052478134109e-05, |
| 16786 | "loss": 0.0317, |
| 16787 | "step": 24320 |
| 16788 | }, |
| 16789 | { |
| 16790 | "epoch": 34.96, |
| 16791 | "learning_rate": 9.165306122448979e-05, |
| 16792 | "loss": 0.0226, |
| 16793 | "step": 24330 |
| 16794 | }, |
| 16795 | { |
| 16796 | "epoch": 34.97, |
| 16797 | "learning_rate": 9.156559766763848e-05, |
| 16798 | "loss": 0.0232, |
| 16799 | "step": 24340 |
| 16800 | }, |
| 16801 | { |
| 16802 | "epoch": 34.99, |
| 16803 | "learning_rate": 9.147813411078717e-05, |
| 16804 | "loss": 0.0355, |
| 16805 | "step": 24350 |
| 16806 | }, |
| 16807 | { |
| 16808 | "epoch": 35.0, |
| 16809 | "learning_rate": 9.139067055393584e-05, |
| 16810 | "loss": 0.032, |
| 16811 | "step": 24360 |
| 16812 | }, |
| 16813 | { |
| 16814 | "epoch": 35.01, |
| 16815 | "learning_rate": 9.130320699708454e-05, |
| 16816 | "loss": 0.0381, |
| 16817 | "step": 24370 |
| 16818 | }, |
| 16819 | { |
| 16820 | "epoch": 35.03, |
| 16821 | "learning_rate": 9.121574344023323e-05, |
| 16822 | "loss": 0.0248, |
| 16823 | "step": 24380 |
| 16824 | }, |
| 16825 | { |
| 16826 | "epoch": 35.04, |
| 16827 | "learning_rate": 9.112827988338192e-05, |
| 16828 | "loss": 0.0202, |
| 16829 | "step": 24390 |
| 16830 | }, |
| 16831 | { |
| 16832 | "epoch": 35.06, |
| 16833 | "learning_rate": 9.104081632653059e-05, |
| 16834 | "loss": 0.0238, |
| 16835 | "step": 24400 |
| 16836 | }, |
| 16837 | { |
| 16838 | "epoch": 35.06, |
| 16839 | "eval_loss": 0.13871027529239655, |
| 16840 | "eval_runtime": 40.2335, |
| 16841 | "eval_samples_per_second": 11.359, |
| 16842 | "eval_steps_per_second": 1.442, |
| 16843 | "eval_wer": 0.13010088842041861, |
| 16844 | "step": 24400 |
| 16845 | }, |
| 16846 | { |
| 16847 | "epoch": 35.07, |
| 16848 | "learning_rate": 9.09533527696793e-05, |
| 16849 | "loss": 0.0209, |
| 16850 | "step": 24410 |
| 16851 | }, |
| 16852 | { |
| 16853 | "epoch": 35.09, |
| 16854 | "learning_rate": 9.086588921282798e-05, |
| 16855 | "loss": 0.0266, |
| 16856 | "step": 24420 |
| 16857 | }, |
| 16858 | { |
| 16859 | "epoch": 35.1, |
| 16860 | "learning_rate": 9.077842565597667e-05, |
| 16861 | "loss": 0.0217, |
| 16862 | "step": 24430 |
| 16863 | }, |
| 16864 | { |
| 16865 | "epoch": 35.11, |
| 16866 | "learning_rate": 9.069096209912536e-05, |
| 16867 | "loss": 0.034, |
| 16868 | "step": 24440 |
| 16869 | }, |
| 16870 | { |
| 16871 | "epoch": 35.13, |
| 16872 | "learning_rate": 9.060349854227405e-05, |
| 16873 | "loss": 0.0335, |
| 16874 | "step": 24450 |
| 16875 | }, |
| 16876 | { |
| 16877 | "epoch": 35.14, |
| 16878 | "learning_rate": 9.051603498542273e-05, |
| 16879 | "loss": 0.0352, |
| 16880 | "step": 24460 |
| 16881 | }, |
| 16882 | { |
| 16883 | "epoch": 35.16, |
| 16884 | "learning_rate": 9.042857142857142e-05, |
| 16885 | "loss": 0.027, |
| 16886 | "step": 24470 |
| 16887 | }, |
| 16888 | { |
| 16889 | "epoch": 35.17, |
| 16890 | "learning_rate": 9.034110787172011e-05, |
| 16891 | "loss": 0.0254, |
| 16892 | "step": 24480 |
| 16893 | }, |
| 16894 | { |
| 16895 | "epoch": 35.19, |
| 16896 | "learning_rate": 9.025364431486878e-05, |
| 16897 | "loss": 0.0319, |
| 16898 | "step": 24490 |
| 16899 | }, |
| 16900 | { |
| 16901 | "epoch": 35.2, |
| 16902 | "learning_rate": 9.016618075801749e-05, |
| 16903 | "loss": 0.0213, |
| 16904 | "step": 24500 |
| 16905 | }, |
| 16906 | { |
| 16907 | "epoch": 35.2, |
| 16908 | "eval_loss": 0.13293719291687012, |
| 16909 | "eval_runtime": 40.6113, |
| 16910 | "eval_samples_per_second": 11.253, |
| 16911 | "eval_steps_per_second": 1.428, |
| 16912 | "eval_wer": 0.1326607438638759, |
| 16913 | "step": 24500 |
| 16914 | }, |
| 16915 | { |
| 16916 | "epoch": 35.22, |
| 16917 | "learning_rate": 9.007871720116617e-05, |
| 16918 | "loss": 0.0234, |
| 16919 | "step": 24510 |
| 16920 | }, |
| 16921 | { |
| 16922 | "epoch": 35.23, |
| 16923 | "learning_rate": 8.999125364431486e-05, |
| 16924 | "loss": 0.029, |
| 16925 | "step": 24520 |
| 16926 | }, |
| 16927 | { |
| 16928 | "epoch": 35.24, |
| 16929 | "learning_rate": 8.990379008746356e-05, |
| 16930 | "loss": 0.0278, |
| 16931 | "step": 24530 |
| 16932 | }, |
| 16933 | { |
| 16934 | "epoch": 35.26, |
| 16935 | "learning_rate": 8.981632653061224e-05, |
| 16936 | "loss": 0.0288, |
| 16937 | "step": 24540 |
| 16938 | }, |
| 16939 | { |
| 16940 | "epoch": 35.27, |
| 16941 | "learning_rate": 8.972886297376092e-05, |
| 16942 | "loss": 0.0223, |
| 16943 | "step": 24550 |
| 16944 | }, |
| 16945 | { |
| 16946 | "epoch": 35.29, |
| 16947 | "learning_rate": 8.964139941690961e-05, |
| 16948 | "loss": 0.0208, |
| 16949 | "step": 24560 |
| 16950 | }, |
| 16951 | { |
| 16952 | "epoch": 35.3, |
| 16953 | "learning_rate": 8.95539358600583e-05, |
| 16954 | "loss": 0.0356, |
| 16955 | "step": 24570 |
| 16956 | }, |
| 16957 | { |
| 16958 | "epoch": 35.32, |
| 16959 | "learning_rate": 8.946647230320699e-05, |
| 16960 | "loss": 0.0262, |
| 16961 | "step": 24580 |
| 16962 | }, |
| 16963 | { |
| 16964 | "epoch": 35.33, |
| 16965 | "learning_rate": 8.937900874635568e-05, |
| 16966 | "loss": 0.0324, |
| 16967 | "step": 24590 |
| 16968 | }, |
| 16969 | { |
| 16970 | "epoch": 35.34, |
| 16971 | "learning_rate": 8.929154518950436e-05, |
| 16972 | "loss": 0.0261, |
| 16973 | "step": 24600 |
| 16974 | }, |
| 16975 | { |
| 16976 | "epoch": 35.34, |
| 16977 | "eval_loss": 0.1314808577299118, |
| 16978 | "eval_runtime": 40.3503, |
| 16979 | "eval_samples_per_second": 11.326, |
| 16980 | "eval_steps_per_second": 1.437, |
| 16981 | "eval_wer": 0.12949856949254632, |
| 16982 | "step": 24600 |
| 16983 | }, |
| 16984 | { |
| 16985 | "epoch": 35.36, |
| 16986 | "learning_rate": 8.920408163265305e-05, |
| 16987 | "loss": 0.0216, |
| 16988 | "step": 24610 |
| 16989 | }, |
| 16990 | { |
| 16991 | "epoch": 35.37, |
| 16992 | "learning_rate": 8.911661807580175e-05, |
| 16993 | "loss": 0.0416, |
| 16994 | "step": 24620 |
| 16995 | }, |
| 16996 | { |
| 16997 | "epoch": 35.39, |
| 16998 | "learning_rate": 8.902915451895043e-05, |
| 16999 | "loss": 0.0351, |
| 17000 | "step": 24630 |
| 17001 | }, |
| 17002 | { |
| 17003 | "epoch": 35.4, |
| 17004 | "learning_rate": 8.894169096209912e-05, |
| 17005 | "loss": 0.029, |
| 17006 | "step": 24640 |
| 17007 | }, |
| 17008 | { |
| 17009 | "epoch": 35.42, |
| 17010 | "learning_rate": 8.88542274052478e-05, |
| 17011 | "loss": 0.0291, |
| 17012 | "step": 24650 |
| 17013 | }, |
| 17014 | { |
| 17015 | "epoch": 35.43, |
| 17016 | "learning_rate": 8.87667638483965e-05, |
| 17017 | "loss": 0.0255, |
| 17018 | "step": 24660 |
| 17019 | }, |
| 17020 | { |
| 17021 | "epoch": 35.45, |
| 17022 | "learning_rate": 8.867930029154518e-05, |
| 17023 | "loss": 0.0305, |
| 17024 | "step": 24670 |
| 17025 | }, |
| 17026 | { |
| 17027 | "epoch": 35.46, |
| 17028 | "learning_rate": 8.859183673469387e-05, |
| 17029 | "loss": 0.0222, |
| 17030 | "step": 24680 |
| 17031 | }, |
| 17032 | { |
| 17033 | "epoch": 35.47, |
| 17034 | "learning_rate": 8.850437317784256e-05, |
| 17035 | "loss": 0.0319, |
| 17036 | "step": 24690 |
| 17037 | }, |
| 17038 | { |
| 17039 | "epoch": 35.49, |
| 17040 | "learning_rate": 8.841690962099124e-05, |
| 17041 | "loss": 0.0289, |
| 17042 | "step": 24700 |
| 17043 | }, |
| 17044 | { |
| 17045 | "epoch": 35.49, |
| 17046 | "eval_loss": 0.13069851696491241, |
| 17047 | "eval_runtime": 40.6111, |
| 17048 | "eval_samples_per_second": 11.253, |
| 17049 | "eval_steps_per_second": 1.428, |
| 17050 | "eval_wer": 0.1322090046679717, |
| 17051 | "step": 24700 |
| 17052 | }, |
| 17053 | { |
| 17054 | "epoch": 35.5, |
| 17055 | "learning_rate": 8.832944606413994e-05, |
| 17056 | "loss": 0.0261, |
| 17057 | "step": 24710 |
| 17058 | }, |
| 17059 | { |
| 17060 | "epoch": 35.52, |
| 17061 | "learning_rate": 8.824198250728862e-05, |
| 17062 | "loss": 0.0288, |
| 17063 | "step": 24720 |
| 17064 | }, |
| 17065 | { |
| 17066 | "epoch": 35.53, |
| 17067 | "learning_rate": 8.81545189504373e-05, |
| 17068 | "loss": 0.0295, |
| 17069 | "step": 24730 |
| 17070 | }, |
| 17071 | { |
| 17072 | "epoch": 35.55, |
| 17073 | "learning_rate": 8.8067055393586e-05, |
| 17074 | "loss": 0.0246, |
| 17075 | "step": 24740 |
| 17076 | }, |
| 17077 | { |
| 17078 | "epoch": 35.56, |
| 17079 | "learning_rate": 8.79795918367347e-05, |
| 17080 | "loss": 0.0296, |
| 17081 | "step": 24750 |
| 17082 | }, |
| 17083 | { |
| 17084 | "epoch": 35.57, |
| 17085 | "learning_rate": 8.789212827988337e-05, |
| 17086 | "loss": 0.0251, |
| 17087 | "step": 24760 |
| 17088 | }, |
| 17089 | { |
| 17090 | "epoch": 35.59, |
| 17091 | "learning_rate": 8.780466472303206e-05, |
| 17092 | "loss": 0.0357, |
| 17093 | "step": 24770 |
| 17094 | }, |
| 17095 | { |
| 17096 | "epoch": 35.6, |
| 17097 | "learning_rate": 8.771720116618075e-05, |
| 17098 | "loss": 0.0235, |
| 17099 | "step": 24780 |
| 17100 | }, |
| 17101 | { |
| 17102 | "epoch": 35.62, |
| 17103 | "learning_rate": 8.762973760932945e-05, |
| 17104 | "loss": 0.028, |
| 17105 | "step": 24790 |
| 17106 | }, |
| 17107 | { |
| 17108 | "epoch": 35.63, |
| 17109 | "learning_rate": 8.754227405247814e-05, |
| 17110 | "loss": 0.0204, |
| 17111 | "step": 24800 |
| 17112 | }, |
| 17113 | { |
| 17114 | "epoch": 35.63, |
| 17115 | "eval_loss": 0.12542444467544556, |
| 17116 | "eval_runtime": 40.1226, |
| 17117 | "eval_samples_per_second": 11.39, |
| 17118 | "eval_steps_per_second": 1.446, |
| 17119 | "eval_wer": 0.13115494654419516, |
| 17120 | "step": 24800 |
| 17121 | }, |
| 17122 | { |
| 17123 | "epoch": 35.65, |
| 17124 | "learning_rate": 8.745481049562681e-05, |
| 17125 | "loss": 0.0211, |
| 17126 | "step": 24810 |
| 17127 | }, |
| 17128 | { |
| 17129 | "epoch": 35.66, |
| 17130 | "learning_rate": 8.73673469387755e-05, |
| 17131 | "loss": 0.0259, |
| 17132 | "step": 24820 |
| 17133 | }, |
| 17134 | { |
| 17135 | "epoch": 35.68, |
| 17136 | "learning_rate": 8.72798833819242e-05, |
| 17137 | "loss": 0.0275, |
| 17138 | "step": 24830 |
| 17139 | }, |
| 17140 | { |
| 17141 | "epoch": 35.69, |
| 17142 | "learning_rate": 8.719241982507289e-05, |
| 17143 | "loss": 0.024, |
| 17144 | "step": 24840 |
| 17145 | }, |
| 17146 | { |
| 17147 | "epoch": 35.7, |
| 17148 | "learning_rate": 8.710495626822156e-05, |
| 17149 | "loss": 0.0257, |
| 17150 | "step": 24850 |
| 17151 | }, |
| 17152 | { |
| 17153 | "epoch": 35.72, |
| 17154 | "learning_rate": 8.701749271137025e-05, |
| 17155 | "loss": 0.0225, |
| 17156 | "step": 24860 |
| 17157 | }, |
| 17158 | { |
| 17159 | "epoch": 35.73, |
| 17160 | "learning_rate": 8.693002915451894e-05, |
| 17161 | "loss": 0.0375, |
| 17162 | "step": 24870 |
| 17163 | }, |
| 17164 | { |
| 17165 | "epoch": 35.75, |
| 17166 | "learning_rate": 8.684256559766764e-05, |
| 17167 | "loss": 0.0252, |
| 17168 | "step": 24880 |
| 17169 | }, |
| 17170 | { |
| 17171 | "epoch": 35.76, |
| 17172 | "learning_rate": 8.675510204081633e-05, |
| 17173 | "loss": 0.0298, |
| 17174 | "step": 24890 |
| 17175 | }, |
| 17176 | { |
| 17177 | "epoch": 35.78, |
| 17178 | "learning_rate": 8.6667638483965e-05, |
| 17179 | "loss": 0.0266, |
| 17180 | "step": 24900 |
| 17181 | }, |
| 17182 | { |
| 17183 | "epoch": 35.78, |
| 17184 | "eval_loss": 0.1274455338716507, |
| 17185 | "eval_runtime": 40.3501, |
| 17186 | "eval_samples_per_second": 11.326, |
| 17187 | "eval_steps_per_second": 1.437, |
| 17188 | "eval_wer": 0.128896250564674, |
| 17189 | "step": 24900 |
| 17190 | }, |
| 17191 | { |
| 17192 | "epoch": 35.79, |
| 17193 | "learning_rate": 8.658017492711369e-05, |
| 17194 | "loss": 0.0278, |
| 17195 | "step": 24910 |
| 17196 | }, |
| 17197 | { |
| 17198 | "epoch": 35.8, |
| 17199 | "learning_rate": 8.649271137026239e-05, |
| 17200 | "loss": 0.0288, |
| 17201 | "step": 24920 |
| 17202 | }, |
| 17203 | { |
| 17204 | "epoch": 35.82, |
| 17205 | "learning_rate": 8.640524781341108e-05, |
| 17206 | "loss": 0.0205, |
| 17207 | "step": 24930 |
| 17208 | }, |
| 17209 | { |
| 17210 | "epoch": 35.83, |
| 17211 | "learning_rate": 8.631778425655975e-05, |
| 17212 | "loss": 0.0247, |
| 17213 | "step": 24940 |
| 17214 | }, |
| 17215 | { |
| 17216 | "epoch": 35.85, |
| 17217 | "learning_rate": 8.623032069970844e-05, |
| 17218 | "loss": 0.0282, |
| 17219 | "step": 24950 |
| 17220 | }, |
| 17221 | { |
| 17222 | "epoch": 35.86, |
| 17223 | "learning_rate": 8.614285714285714e-05, |
| 17224 | "loss": 0.0243, |
| 17225 | "step": 24960 |
| 17226 | }, |
| 17227 | { |
| 17228 | "epoch": 35.88, |
| 17229 | "learning_rate": 8.605539358600583e-05, |
| 17230 | "loss": 0.0311, |
| 17231 | "step": 24970 |
| 17232 | }, |
| 17233 | { |
| 17234 | "epoch": 35.89, |
| 17235 | "learning_rate": 8.596793002915452e-05, |
| 17236 | "loss": 0.0327, |
| 17237 | "step": 24980 |
| 17238 | }, |
| 17239 | { |
| 17240 | "epoch": 35.91, |
| 17241 | "learning_rate": 8.588046647230319e-05, |
| 17242 | "loss": 0.0361, |
| 17243 | "step": 24990 |
| 17244 | }, |
| 17245 | { |
| 17246 | "epoch": 35.92, |
| 17247 | "learning_rate": 8.579300291545188e-05, |
| 17248 | "loss": 0.0287, |
| 17249 | "step": 25000 |
| 17250 | }, |
| 17251 | { |
| 17252 | "epoch": 35.92, |
| 17253 | "eval_loss": 0.12421078979969025, |
| 17254 | "eval_runtime": 40.3244, |
| 17255 | "eval_samples_per_second": 11.333, |
| 17256 | "eval_steps_per_second": 1.438, |
| 17257 | "eval_wer": 0.12422827887366361, |
| 17258 | "step": 25000 |
| 17259 | }, |
| 17260 | { |
| 17261 | "epoch": 35.93, |
| 17262 | "learning_rate": 8.570553935860058e-05, |
| 17263 | "loss": 0.0287, |
| 17264 | "step": 25010 |
| 17265 | }, |
| 17266 | { |
| 17267 | "epoch": 35.95, |
| 17268 | "learning_rate": 8.561807580174927e-05, |
| 17269 | "loss": 0.031, |
| 17270 | "step": 25020 |
| 17271 | }, |
| 17272 | { |
| 17273 | "epoch": 35.96, |
| 17274 | "learning_rate": 8.553061224489794e-05, |
| 17275 | "loss": 0.0313, |
| 17276 | "step": 25030 |
| 17277 | }, |
| 17278 | { |
| 17279 | "epoch": 35.98, |
| 17280 | "learning_rate": 8.544314868804663e-05, |
| 17281 | "loss": 0.0255, |
| 17282 | "step": 25040 |
| 17283 | }, |
| 17284 | { |
| 17285 | "epoch": 35.99, |
| 17286 | "learning_rate": 8.535568513119533e-05, |
| 17287 | "loss": 0.0262, |
| 17288 | "step": 25050 |
| 17289 | }, |
| 17290 | { |
| 17291 | "epoch": 36.01, |
| 17292 | "learning_rate": 8.526822157434402e-05, |
| 17293 | "loss": 0.0238, |
| 17294 | "step": 25060 |
| 17295 | }, |
| 17296 | { |
| 17297 | "epoch": 36.02, |
| 17298 | "learning_rate": 8.518075801749271e-05, |
| 17299 | "loss": 0.0263, |
| 17300 | "step": 25070 |
| 17301 | }, |
| 17302 | { |
| 17303 | "epoch": 36.03, |
| 17304 | "learning_rate": 8.509329446064138e-05, |
| 17305 | "loss": 0.0324, |
| 17306 | "step": 25080 |
| 17307 | }, |
| 17308 | { |
| 17309 | "epoch": 36.05, |
| 17310 | "learning_rate": 8.500583090379008e-05, |
| 17311 | "loss": 0.0249, |
| 17312 | "step": 25090 |
| 17313 | }, |
| 17314 | { |
| 17315 | "epoch": 36.06, |
| 17316 | "learning_rate": 8.491836734693877e-05, |
| 17317 | "loss": 0.0208, |
| 17318 | "step": 25100 |
| 17319 | }, |
| 17320 | { |
| 17321 | "epoch": 36.06, |
| 17322 | "eval_loss": 0.13018617033958435, |
| 17323 | "eval_runtime": 40.7248, |
| 17324 | "eval_samples_per_second": 11.222, |
| 17325 | "eval_steps_per_second": 1.424, |
| 17326 | "eval_wer": 0.12769161270892937, |
| 17327 | "step": 25100 |
| 17328 | }, |
| 17329 | { |
| 17330 | "epoch": 36.08, |
| 17331 | "learning_rate": 8.483090379008746e-05, |
| 17332 | "loss": 0.0227, |
| 17333 | "step": 25110 |
| 17334 | }, |
| 17335 | { |
| 17336 | "epoch": 36.09, |
| 17337 | "learning_rate": 8.474344023323613e-05, |
| 17338 | "loss": 0.0232, |
| 17339 | "step": 25120 |
| 17340 | }, |
| 17341 | { |
| 17342 | "epoch": 36.11, |
| 17343 | "learning_rate": 8.465597667638482e-05, |
| 17344 | "loss": 0.0199, |
| 17345 | "step": 25130 |
| 17346 | }, |
| 17347 | { |
| 17348 | "epoch": 36.12, |
| 17349 | "learning_rate": 8.456851311953352e-05, |
| 17350 | "loss": 0.0356, |
| 17351 | "step": 25140 |
| 17352 | }, |
| 17353 | { |
| 17354 | "epoch": 36.14, |
| 17355 | "learning_rate": 8.448104956268221e-05, |
| 17356 | "loss": 0.0257, |
| 17357 | "step": 25150 |
| 17358 | }, |
| 17359 | { |
| 17360 | "epoch": 36.15, |
| 17361 | "learning_rate": 8.43935860058309e-05, |
| 17362 | "loss": 0.0306, |
| 17363 | "step": 25160 |
| 17364 | }, |
| 17365 | { |
| 17366 | "epoch": 36.16, |
| 17367 | "learning_rate": 8.430612244897957e-05, |
| 17368 | "loss": 0.0214, |
| 17369 | "step": 25170 |
| 17370 | }, |
| 17371 | { |
| 17372 | "epoch": 36.18, |
| 17373 | "learning_rate": 8.421865889212828e-05, |
| 17374 | "loss": 0.0245, |
| 17375 | "step": 25180 |
| 17376 | }, |
| 17377 | { |
| 17378 | "epoch": 36.19, |
| 17379 | "learning_rate": 8.413119533527696e-05, |
| 17380 | "loss": 0.0287, |
| 17381 | "step": 25190 |
| 17382 | }, |
| 17383 | { |
| 17384 | "epoch": 36.21, |
| 17385 | "learning_rate": 8.404373177842565e-05, |
| 17386 | "loss": 0.0258, |
| 17387 | "step": 25200 |
| 17388 | }, |
| 17389 | { |
| 17390 | "epoch": 36.21, |
| 17391 | "eval_loss": 0.13101942837238312, |
| 17392 | "eval_runtime": 40.0217, |
| 17393 | "eval_samples_per_second": 11.419, |
| 17394 | "eval_steps_per_second": 1.449, |
| 17395 | "eval_wer": 0.1307032073482909, |
| 17396 | "step": 25200 |
| 17397 | }, |
| 17398 | { |
| 17399 | "epoch": 36.22, |
| 17400 | "learning_rate": 8.395626822157433e-05, |
| 17401 | "loss": 0.0289, |
| 17402 | "step": 25210 |
| 17403 | }, |
| 17404 | { |
| 17405 | "epoch": 36.24, |
| 17406 | "learning_rate": 8.386880466472303e-05, |
| 17407 | "loss": 0.0227, |
| 17408 | "step": 25220 |
| 17409 | }, |
| 17410 | { |
| 17411 | "epoch": 36.25, |
| 17412 | "learning_rate": 8.378134110787172e-05, |
| 17413 | "loss": 0.0181, |
| 17414 | "step": 25230 |
| 17415 | }, |
| 17416 | { |
| 17417 | "epoch": 36.26, |
| 17418 | "learning_rate": 8.36938775510204e-05, |
| 17419 | "loss": 0.0276, |
| 17420 | "step": 25240 |
| 17421 | }, |
| 17422 | { |
| 17423 | "epoch": 36.28, |
| 17424 | "learning_rate": 8.360641399416909e-05, |
| 17425 | "loss": 0.0324, |
| 17426 | "step": 25250 |
| 17427 | }, |
| 17428 | { |
| 17429 | "epoch": 36.29, |
| 17430 | "learning_rate": 8.351895043731778e-05, |
| 17431 | "loss": 0.0306, |
| 17432 | "step": 25260 |
| 17433 | }, |
| 17434 | { |
| 17435 | "epoch": 36.31, |
| 17436 | "learning_rate": 8.343148688046647e-05, |
| 17437 | "loss": 0.0247, |
| 17438 | "step": 25270 |
| 17439 | }, |
| 17440 | { |
| 17441 | "epoch": 36.32, |
| 17442 | "learning_rate": 8.334402332361515e-05, |
| 17443 | "loss": 0.0293, |
| 17444 | "step": 25280 |
| 17445 | }, |
| 17446 | { |
| 17447 | "epoch": 36.34, |
| 17448 | "learning_rate": 8.325655976676384e-05, |
| 17449 | "loss": 0.0303, |
| 17450 | "step": 25290 |
| 17451 | }, |
| 17452 | { |
| 17453 | "epoch": 36.35, |
| 17454 | "learning_rate": 8.316909620991252e-05, |
| 17455 | "loss": 0.0222, |
| 17456 | "step": 25300 |
| 17457 | }, |
| 17458 | { |
| 17459 | "epoch": 36.35, |
| 17460 | "eval_loss": 0.12964005768299103, |
| 17461 | "eval_runtime": 40.3469, |
| 17462 | "eval_samples_per_second": 11.327, |
| 17463 | "eval_steps_per_second": 1.438, |
| 17464 | "eval_wer": 0.1287456708327059, |
| 17465 | "step": 25300 |
| 17466 | }, |
| 17467 | { |
| 17468 | "epoch": 36.36, |
| 17469 | "learning_rate": 8.308163265306122e-05, |
| 17470 | "loss": 0.0316, |
| 17471 | "step": 25310 |
| 17472 | }, |
| 17473 | { |
| 17474 | "epoch": 36.38, |
| 17475 | "learning_rate": 8.29941690962099e-05, |
| 17476 | "loss": 0.032, |
| 17477 | "step": 25320 |
| 17478 | }, |
| 17479 | { |
| 17480 | "epoch": 36.39, |
| 17481 | "learning_rate": 8.29067055393586e-05, |
| 17482 | "loss": 0.0185, |
| 17483 | "step": 25330 |
| 17484 | }, |
| 17485 | { |
| 17486 | "epoch": 36.41, |
| 17487 | "learning_rate": 8.28192419825073e-05, |
| 17488 | "loss": 0.0351, |
| 17489 | "step": 25340 |
| 17490 | }, |
| 17491 | { |
| 17492 | "epoch": 36.42, |
| 17493 | "learning_rate": 8.273177842565597e-05, |
| 17494 | "loss": 0.0242, |
| 17495 | "step": 25350 |
| 17496 | }, |
| 17497 | { |
| 17498 | "epoch": 36.44, |
| 17499 | "learning_rate": 8.264431486880466e-05, |
| 17500 | "loss": 0.0205, |
| 17501 | "step": 25360 |
| 17502 | }, |
| 17503 | { |
| 17504 | "epoch": 36.45, |
| 17505 | "learning_rate": 8.255685131195335e-05, |
| 17506 | "loss": 0.0269, |
| 17507 | "step": 25370 |
| 17508 | }, |
| 17509 | { |
| 17510 | "epoch": 36.47, |
| 17511 | "learning_rate": 8.246938775510203e-05, |
| 17512 | "loss": 0.0199, |
| 17513 | "step": 25380 |
| 17514 | }, |
| 17515 | { |
| 17516 | "epoch": 36.48, |
| 17517 | "learning_rate": 8.238192419825072e-05, |
| 17518 | "loss": 0.0291, |
| 17519 | "step": 25390 |
| 17520 | }, |
| 17521 | { |
| 17522 | "epoch": 36.49, |
| 17523 | "learning_rate": 8.229446064139941e-05, |
| 17524 | "loss": 0.0219, |
| 17525 | "step": 25400 |
| 17526 | }, |
| 17527 | { |
| 17528 | "epoch": 36.49, |
| 17529 | "eval_loss": 0.13100750744342804, |
| 17530 | "eval_runtime": 40.0869, |
| 17531 | "eval_samples_per_second": 11.4, |
| 17532 | "eval_steps_per_second": 1.447, |
| 17533 | "eval_wer": 0.12784219244089745, |
| 17534 | "step": 25400 |
| 17535 | }, |
| 17536 | { |
| 17537 | "epoch": 36.51, |
| 17538 | "learning_rate": 8.22069970845481e-05, |
| 17539 | "loss": 0.0358, |
| 17540 | "step": 25410 |
| 17541 | }, |
| 17542 | { |
| 17543 | "epoch": 36.52, |
| 17544 | "learning_rate": 8.211953352769679e-05, |
| 17545 | "loss": 0.0206, |
| 17546 | "step": 25420 |
| 17547 | }, |
| 17548 | { |
| 17549 | "epoch": 36.54, |
| 17550 | "learning_rate": 8.203206997084549e-05, |
| 17551 | "loss": 0.0204, |
| 17552 | "step": 25430 |
| 17553 | }, |
| 17554 | { |
| 17555 | "epoch": 36.55, |
| 17556 | "learning_rate": 8.194460641399416e-05, |
| 17557 | "loss": 0.0332, |
| 17558 | "step": 25440 |
| 17559 | }, |
| 17560 | { |
| 17561 | "epoch": 36.57, |
| 17562 | "learning_rate": 8.185714285714285e-05, |
| 17563 | "loss": 0.0256, |
| 17564 | "step": 25450 |
| 17565 | }, |
| 17566 | { |
| 17567 | "epoch": 36.58, |
| 17568 | "learning_rate": 8.177842565597667e-05, |
| 17569 | "loss": 0.025, |
| 17570 | "step": 25460 |
| 17571 | }, |
| 17572 | { |
| 17573 | "epoch": 36.59, |
| 17574 | "learning_rate": 8.169096209912536e-05, |
| 17575 | "loss": 0.0284, |
| 17576 | "step": 25470 |
| 17577 | }, |
| 17578 | { |
| 17579 | "epoch": 36.61, |
| 17580 | "learning_rate": 8.160349854227404e-05, |
| 17581 | "loss": 0.0213, |
| 17582 | "step": 25480 |
| 17583 | }, |
| 17584 | { |
| 17585 | "epoch": 36.62, |
| 17586 | "learning_rate": 8.151603498542275e-05, |
| 17587 | "loss": 0.0368, |
| 17588 | "step": 25490 |
| 17589 | }, |
| 17590 | { |
| 17591 | "epoch": 36.64, |
| 17592 | "learning_rate": 8.142857142857142e-05, |
| 17593 | "loss": 0.0221, |
| 17594 | "step": 25500 |
| 17595 | }, |
| 17596 | { |
| 17597 | "epoch": 36.64, |
| 17598 | "eval_loss": 0.1341370940208435, |
| 17599 | "eval_runtime": 40.1907, |
| 17600 | "eval_samples_per_second": 11.371, |
| 17601 | "eval_steps_per_second": 1.443, |
| 17602 | "eval_wer": 0.12934798976057824, |
| 17603 | "step": 25500 |
| 17604 | }, |
| 17605 | { |
| 17606 | "epoch": 36.65, |
| 17607 | "learning_rate": 8.134110787172011e-05, |
| 17608 | "loss": 0.0307, |
| 17609 | "step": 25510 |
| 17610 | }, |
| 17611 | { |
| 17612 | "epoch": 36.67, |
| 17613 | "learning_rate": 8.12536443148688e-05, |
| 17614 | "loss": 0.0182, |
| 17615 | "step": 25520 |
| 17616 | }, |
| 17617 | { |
| 17618 | "epoch": 36.68, |
| 17619 | "learning_rate": 8.11661807580175e-05, |
| 17620 | "loss": 0.0293, |
| 17621 | "step": 25530 |
| 17622 | }, |
| 17623 | { |
| 17624 | "epoch": 36.7, |
| 17625 | "learning_rate": 8.107871720116617e-05, |
| 17626 | "loss": 0.026, |
| 17627 | "step": 25540 |
| 17628 | }, |
| 17629 | { |
| 17630 | "epoch": 36.71, |
| 17631 | "learning_rate": 8.099125364431486e-05, |
| 17632 | "loss": 0.0252, |
| 17633 | "step": 25550 |
| 17634 | }, |
| 17635 | { |
| 17636 | "epoch": 36.72, |
| 17637 | "learning_rate": 8.090379008746355e-05, |
| 17638 | "loss": 0.0259, |
| 17639 | "step": 25560 |
| 17640 | }, |
| 17641 | { |
| 17642 | "epoch": 36.74, |
| 17643 | "learning_rate": 8.081632653061223e-05, |
| 17644 | "loss": 0.0219, |
| 17645 | "step": 25570 |
| 17646 | }, |
| 17647 | { |
| 17648 | "epoch": 36.75, |
| 17649 | "learning_rate": 8.072886297376094e-05, |
| 17650 | "loss": 0.0239, |
| 17651 | "step": 25580 |
| 17652 | }, |
| 17653 | { |
| 17654 | "epoch": 36.77, |
| 17655 | "learning_rate": 8.064139941690961e-05, |
| 17656 | "loss": 0.0336, |
| 17657 | "step": 25590 |
| 17658 | }, |
| 17659 | { |
| 17660 | "epoch": 36.78, |
| 17661 | "learning_rate": 8.05539358600583e-05, |
| 17662 | "loss": 0.0182, |
| 17663 | "step": 25600 |
| 17664 | }, |
| 17665 | { |
| 17666 | "epoch": 36.78, |
| 17667 | "eval_loss": 0.13404802978038788, |
| 17668 | "eval_runtime": 40.1153, |
| 17669 | "eval_samples_per_second": 11.392, |
| 17670 | "eval_steps_per_second": 1.446, |
| 17671 | "eval_wer": 0.126938714049089, |
| 17672 | "step": 25600 |
| 17673 | }, |
| 17674 | { |
| 17675 | "epoch": 36.8, |
| 17676 | "learning_rate": 8.046647230320699e-05, |
| 17677 | "loss": 0.0247, |
| 17678 | "step": 25610 |
| 17679 | }, |
| 17680 | { |
| 17681 | "epoch": 36.81, |
| 17682 | "learning_rate": 8.037900874635569e-05, |
| 17683 | "loss": 0.0214, |
| 17684 | "step": 25620 |
| 17685 | }, |
| 17686 | { |
| 17687 | "epoch": 36.82, |
| 17688 | "learning_rate": 8.029154518950436e-05, |
| 17689 | "loss": 0.0266, |
| 17690 | "step": 25630 |
| 17691 | }, |
| 17692 | { |
| 17693 | "epoch": 36.84, |
| 17694 | "learning_rate": 8.020408163265305e-05, |
| 17695 | "loss": 0.0301, |
| 17696 | "step": 25640 |
| 17697 | }, |
| 17698 | { |
| 17699 | "epoch": 36.85, |
| 17700 | "learning_rate": 8.011661807580174e-05, |
| 17701 | "loss": 0.0188, |
| 17702 | "step": 25650 |
| 17703 | }, |
| 17704 | { |
| 17705 | "epoch": 36.87, |
| 17706 | "learning_rate": 8.002915451895044e-05, |
| 17707 | "loss": 0.0229, |
| 17708 | "step": 25660 |
| 17709 | }, |
| 17710 | { |
| 17711 | "epoch": 36.88, |
| 17712 | "learning_rate": 7.994169096209913e-05, |
| 17713 | "loss": 0.0237, |
| 17714 | "step": 25670 |
| 17715 | }, |
| 17716 | { |
| 17717 | "epoch": 36.9, |
| 17718 | "learning_rate": 7.98542274052478e-05, |
| 17719 | "loss": 0.0203, |
| 17720 | "step": 25680 |
| 17721 | }, |
| 17722 | { |
| 17723 | "epoch": 36.91, |
| 17724 | "learning_rate": 7.976676384839649e-05, |
| 17725 | "loss": 0.0262, |
| 17726 | "step": 25690 |
| 17727 | }, |
| 17728 | { |
| 17729 | "epoch": 36.93, |
| 17730 | "learning_rate": 7.967930029154518e-05, |
| 17731 | "loss": 0.0176, |
| 17732 | "step": 25700 |
| 17733 | }, |
| 17734 | { |
| 17735 | "epoch": 36.93, |
| 17736 | "eval_loss": 0.13346485793590546, |
| 17737 | "eval_runtime": 40.5735, |
| 17738 | "eval_samples_per_second": 11.264, |
| 17739 | "eval_steps_per_second": 1.43, |
| 17740 | "eval_wer": 0.12769161270892937, |
| 17741 | "step": 25700 |
| 17742 | }, |
| 17743 | { |
| 17744 | "epoch": 36.94, |
| 17745 | "learning_rate": 7.959183673469388e-05, |
| 17746 | "loss": 0.0291, |
| 17747 | "step": 25710 |
| 17748 | }, |
| 17749 | { |
| 17750 | "epoch": 36.95, |
| 17751 | "learning_rate": 7.950437317784255e-05, |
| 17752 | "loss": 0.0327, |
| 17753 | "step": 25720 |
| 17754 | }, |
| 17755 | { |
| 17756 | "epoch": 36.97, |
| 17757 | "learning_rate": 7.941690962099124e-05, |
| 17758 | "loss": 0.0228, |
| 17759 | "step": 25730 |
| 17760 | }, |
| 17761 | { |
| 17762 | "epoch": 36.98, |
| 17763 | "learning_rate": 7.932944606413993e-05, |
| 17764 | "loss": 0.0276, |
| 17765 | "step": 25740 |
| 17766 | }, |
| 17767 | { |
| 17768 | "epoch": 37.0, |
| 17769 | "learning_rate": 7.924198250728863e-05, |
| 17770 | "loss": 0.025, |
| 17771 | "step": 25750 |
| 17772 | }, |
| 17773 | { |
| 17774 | "epoch": 37.01, |
| 17775 | "learning_rate": 7.915451895043732e-05, |
| 17776 | "loss": 0.0251, |
| 17777 | "step": 25760 |
| 17778 | }, |
| 17779 | { |
| 17780 | "epoch": 37.03, |
| 17781 | "learning_rate": 7.906705539358599e-05, |
| 17782 | "loss": 0.0258, |
| 17783 | "step": 25770 |
| 17784 | }, |
| 17785 | { |
| 17786 | "epoch": 37.04, |
| 17787 | "learning_rate": 7.897959183673468e-05, |
| 17788 | "loss": 0.0209, |
| 17789 | "step": 25780 |
| 17790 | }, |
| 17791 | { |
| 17792 | "epoch": 37.05, |
| 17793 | "learning_rate": 7.889212827988338e-05, |
| 17794 | "loss": 0.0242, |
| 17795 | "step": 25790 |
| 17796 | }, |
| 17797 | { |
| 17798 | "epoch": 37.07, |
| 17799 | "learning_rate": 7.880466472303207e-05, |
| 17800 | "loss": 0.0301, |
| 17801 | "step": 25800 |
| 17802 | }, |
| 17803 | { |
| 17804 | "epoch": 37.07, |
| 17805 | "eval_loss": 0.13566622138023376, |
| 17806 | "eval_runtime": 40.4741, |
| 17807 | "eval_samples_per_second": 11.291, |
| 17808 | "eval_steps_per_second": 1.433, |
| 17809 | "eval_wer": 0.12844451136876978, |
| 17810 | "step": 25800 |
| 17811 | }, |
| 17812 | { |
| 17813 | "epoch": 37.08, |
| 17814 | "learning_rate": 7.871720116618074e-05, |
| 17815 | "loss": 0.03, |
| 17816 | "step": 25810 |
| 17817 | }, |
| 17818 | { |
| 17819 | "epoch": 37.1, |
| 17820 | "learning_rate": 7.862973760932943e-05, |
| 17821 | "loss": 0.0265, |
| 17822 | "step": 25820 |
| 17823 | }, |
| 17824 | { |
| 17825 | "epoch": 37.11, |
| 17826 | "learning_rate": 7.854227405247813e-05, |
| 17827 | "loss": 0.0225, |
| 17828 | "step": 25830 |
| 17829 | }, |
| 17830 | { |
| 17831 | "epoch": 37.13, |
| 17832 | "learning_rate": 7.845481049562682e-05, |
| 17833 | "loss": 0.0234, |
| 17834 | "step": 25840 |
| 17835 | }, |
| 17836 | { |
| 17837 | "epoch": 37.14, |
| 17838 | "learning_rate": 7.836734693877551e-05, |
| 17839 | "loss": 0.028, |
| 17840 | "step": 25850 |
| 17841 | }, |
| 17842 | { |
| 17843 | "epoch": 37.16, |
| 17844 | "learning_rate": 7.827988338192418e-05, |
| 17845 | "loss": 0.0323, |
| 17846 | "step": 25860 |
| 17847 | }, |
| 17848 | { |
| 17849 | "epoch": 37.17, |
| 17850 | "learning_rate": 7.819241982507287e-05, |
| 17851 | "loss": 0.0207, |
| 17852 | "step": 25870 |
| 17853 | }, |
| 17854 | { |
| 17855 | "epoch": 37.18, |
| 17856 | "learning_rate": 7.810495626822157e-05, |
| 17857 | "loss": 0.0262, |
| 17858 | "step": 25880 |
| 17859 | }, |
| 17860 | { |
| 17861 | "epoch": 37.2, |
| 17862 | "learning_rate": 7.801749271137026e-05, |
| 17863 | "loss": 0.0247, |
| 17864 | "step": 25890 |
| 17865 | }, |
| 17866 | { |
| 17867 | "epoch": 37.21, |
| 17868 | "learning_rate": 7.793002915451894e-05, |
| 17869 | "loss": 0.0205, |
| 17870 | "step": 25900 |
| 17871 | }, |
| 17872 | { |
| 17873 | "epoch": 37.21, |
| 17874 | "eval_loss": 0.1321299970149994, |
| 17875 | "eval_runtime": 40.1895, |
| 17876 | "eval_samples_per_second": 11.371, |
| 17877 | "eval_steps_per_second": 1.443, |
| 17878 | "eval_wer": 0.12919741002861015, |
| 17879 | "step": 25900 |
| 17880 | }, |
| 17881 | { |
| 17882 | "epoch": 37.23, |
| 17883 | "learning_rate": 7.784256559766762e-05, |
| 17884 | "loss": 0.0258, |
| 17885 | "step": 25910 |
| 17886 | }, |
| 17887 | { |
| 17888 | "epoch": 37.24, |
| 17889 | "learning_rate": 7.775510204081632e-05, |
| 17890 | "loss": 0.018, |
| 17891 | "step": 25920 |
| 17892 | }, |
| 17893 | { |
| 17894 | "epoch": 37.26, |
| 17895 | "learning_rate": 7.766763848396501e-05, |
| 17896 | "loss": 0.0195, |
| 17897 | "step": 25930 |
| 17898 | }, |
| 17899 | { |
| 17900 | "epoch": 37.27, |
| 17901 | "learning_rate": 7.75801749271137e-05, |
| 17902 | "loss": 0.0229, |
| 17903 | "step": 25940 |
| 17904 | }, |
| 17905 | { |
| 17906 | "epoch": 37.28, |
| 17907 | "learning_rate": 7.749271137026237e-05, |
| 17908 | "loss": 0.0225, |
| 17909 | "step": 25950 |
| 17910 | }, |
| 17911 | { |
| 17912 | "epoch": 37.3, |
| 17913 | "learning_rate": 7.740524781341108e-05, |
| 17914 | "loss": 0.0288, |
| 17915 | "step": 25960 |
| 17916 | }, |
| 17917 | { |
| 17918 | "epoch": 37.31, |
| 17919 | "learning_rate": 7.731778425655976e-05, |
| 17920 | "loss": 0.0283, |
| 17921 | "step": 25970 |
| 17922 | }, |
| 17923 | { |
| 17924 | "epoch": 37.33, |
| 17925 | "learning_rate": 7.723032069970845e-05, |
| 17926 | "loss": 0.0255, |
| 17927 | "step": 25980 |
| 17928 | }, |
| 17929 | { |
| 17930 | "epoch": 37.34, |
| 17931 | "learning_rate": 7.714285714285713e-05, |
| 17932 | "loss": 0.027, |
| 17933 | "step": 25990 |
| 17934 | }, |
| 17935 | { |
| 17936 | "epoch": 37.36, |
| 17937 | "learning_rate": 7.705539358600581e-05, |
| 17938 | "loss": 0.0193, |
| 17939 | "step": 26000 |
| 17940 | }, |
| 17941 | { |
| 17942 | "epoch": 37.36, |
| 17943 | "eval_loss": 0.1375712752342224, |
| 17944 | "eval_runtime": 40.3298, |
| 17945 | "eval_samples_per_second": 11.332, |
| 17946 | "eval_steps_per_second": 1.438, |
| 17947 | "eval_wer": 0.12844451136876978, |
| 17948 | "step": 26000 |
| 17949 | }, |
| 17950 | { |
| 17951 | "epoch": 37.37, |
| 17952 | "learning_rate": 7.696793002915452e-05, |
| 17953 | "loss": 0.0275, |
| 17954 | "step": 26010 |
| 17955 | }, |
| 17956 | { |
| 17957 | "epoch": 37.39, |
| 17958 | "learning_rate": 7.68804664723032e-05, |
| 17959 | "loss": 0.0196, |
| 17960 | "step": 26020 |
| 17961 | }, |
| 17962 | { |
| 17963 | "epoch": 37.4, |
| 17964 | "learning_rate": 7.679300291545189e-05, |
| 17965 | "loss": 0.0192, |
| 17966 | "step": 26030 |
| 17967 | }, |
| 17968 | { |
| 17969 | "epoch": 37.41, |
| 17970 | "learning_rate": 7.670553935860057e-05, |
| 17971 | "loss": 0.0291, |
| 17972 | "step": 26040 |
| 17973 | }, |
| 17974 | { |
| 17975 | "epoch": 37.43, |
| 17976 | "learning_rate": 7.661807580174927e-05, |
| 17977 | "loss": 0.0179, |
| 17978 | "step": 26050 |
| 17979 | }, |
| 17980 | { |
| 17981 | "epoch": 37.44, |
| 17982 | "learning_rate": 7.653061224489796e-05, |
| 17983 | "loss": 0.0249, |
| 17984 | "step": 26060 |
| 17985 | }, |
| 17986 | { |
| 17987 | "epoch": 37.46, |
| 17988 | "learning_rate": 7.644314868804664e-05, |
| 17989 | "loss": 0.0202, |
| 17990 | "step": 26070 |
| 17991 | }, |
| 17992 | { |
| 17993 | "epoch": 37.47, |
| 17994 | "learning_rate": 7.635568513119532e-05, |
| 17995 | "loss": 0.0212, |
| 17996 | "step": 26080 |
| 17997 | }, |
| 17998 | { |
| 17999 | "epoch": 37.49, |
| 18000 | "learning_rate": 7.626822157434402e-05, |
| 18001 | "loss": 0.0258, |
| 18002 | "step": 26090 |
| 18003 | }, |
| 18004 | { |
| 18005 | "epoch": 37.5, |
| 18006 | "learning_rate": 7.618075801749271e-05, |
| 18007 | "loss": 0.019, |
| 18008 | "step": 26100 |
| 18009 | }, |
| 18010 | { |
| 18011 | "epoch": 37.5, |
| 18012 | "eval_loss": 0.13397379219532013, |
| 18013 | "eval_runtime": 40.1527, |
| 18014 | "eval_samples_per_second": 11.382, |
| 18015 | "eval_steps_per_second": 1.444, |
| 18016 | "eval_wer": 0.13100436681222707, |
| 18017 | "step": 26100 |
| 18018 | }, |
| 18019 | { |
| 18020 | "epoch": 37.51, |
| 18021 | "learning_rate": 7.60932944606414e-05, |
| 18022 | "loss": 0.0264, |
| 18023 | "step": 26110 |
| 18024 | }, |
| 18025 | { |
| 18026 | "epoch": 37.53, |
| 18027 | "learning_rate": 7.600583090379008e-05, |
| 18028 | "loss": 0.0243, |
| 18029 | "step": 26120 |
| 18030 | }, |
| 18031 | { |
| 18032 | "epoch": 37.54, |
| 18033 | "learning_rate": 7.591836734693876e-05, |
| 18034 | "loss": 0.0252, |
| 18035 | "step": 26130 |
| 18036 | }, |
| 18037 | { |
| 18038 | "epoch": 37.56, |
| 18039 | "learning_rate": 7.583090379008746e-05, |
| 18040 | "loss": 0.0325, |
| 18041 | "step": 26140 |
| 18042 | }, |
| 18043 | { |
| 18044 | "epoch": 37.57, |
| 18045 | "learning_rate": 7.574344023323615e-05, |
| 18046 | "loss": 0.0228, |
| 18047 | "step": 26150 |
| 18048 | }, |
| 18049 | { |
| 18050 | "epoch": 37.59, |
| 18051 | "learning_rate": 7.565597667638483e-05, |
| 18052 | "loss": 0.028, |
| 18053 | "step": 26160 |
| 18054 | }, |
| 18055 | { |
| 18056 | "epoch": 37.6, |
| 18057 | "learning_rate": 7.556851311953351e-05, |
| 18058 | "loss": 0.0175, |
| 18059 | "step": 26170 |
| 18060 | }, |
| 18061 | { |
| 18062 | "epoch": 37.61, |
| 18063 | "learning_rate": 7.548104956268221e-05, |
| 18064 | "loss": 0.0315, |
| 18065 | "step": 26180 |
| 18066 | }, |
| 18067 | { |
| 18068 | "epoch": 37.63, |
| 18069 | "learning_rate": 7.53935860058309e-05, |
| 18070 | "loss": 0.0335, |
| 18071 | "step": 26190 |
| 18072 | }, |
| 18073 | { |
| 18074 | "epoch": 37.64, |
| 18075 | "learning_rate": 7.530612244897959e-05, |
| 18076 | "loss": 0.018, |
| 18077 | "step": 26200 |
| 18078 | }, |
| 18079 | { |
| 18080 | "epoch": 37.64, |
| 18081 | "eval_loss": 0.13758954405784607, |
| 18082 | "eval_runtime": 40.5804, |
| 18083 | "eval_samples_per_second": 11.262, |
| 18084 | "eval_steps_per_second": 1.429, |
| 18085 | "eval_wer": 0.13326306279174824, |
| 18086 | "step": 26200 |
| 18087 | }, |
| 18088 | { |
| 18089 | "epoch": 37.66, |
| 18090 | "learning_rate": 7.521865889212829e-05, |
| 18091 | "loss": 0.0352, |
| 18092 | "step": 26210 |
| 18093 | }, |
| 18094 | { |
| 18095 | "epoch": 37.67, |
| 18096 | "learning_rate": 7.513119533527696e-05, |
| 18097 | "loss": 0.0237, |
| 18098 | "step": 26220 |
| 18099 | }, |
| 18100 | { |
| 18101 | "epoch": 37.69, |
| 18102 | "learning_rate": 7.504373177842565e-05, |
| 18103 | "loss": 0.0214, |
| 18104 | "step": 26230 |
| 18105 | }, |
| 18106 | { |
| 18107 | "epoch": 37.7, |
| 18108 | "learning_rate": 7.495626822157434e-05, |
| 18109 | "loss": 0.0237, |
| 18110 | "step": 26240 |
| 18111 | }, |
| 18112 | { |
| 18113 | "epoch": 37.72, |
| 18114 | "learning_rate": 7.486880466472303e-05, |
| 18115 | "loss": 0.0248, |
| 18116 | "step": 26250 |
| 18117 | }, |
| 18118 | { |
| 18119 | "epoch": 37.73, |
| 18120 | "learning_rate": 7.478134110787171e-05, |
| 18121 | "loss": 0.0333, |
| 18122 | "step": 26260 |
| 18123 | }, |
| 18124 | { |
| 18125 | "epoch": 37.74, |
| 18126 | "learning_rate": 7.46938775510204e-05, |
| 18127 | "loss": 0.0279, |
| 18128 | "step": 26270 |
| 18129 | }, |
| 18130 | { |
| 18131 | "epoch": 37.76, |
| 18132 | "learning_rate": 7.460641399416909e-05, |
| 18133 | "loss": 0.0245, |
| 18134 | "step": 26280 |
| 18135 | }, |
| 18136 | { |
| 18137 | "epoch": 37.77, |
| 18138 | "learning_rate": 7.451895043731778e-05, |
| 18139 | "loss": 0.0281, |
| 18140 | "step": 26290 |
| 18141 | }, |
| 18142 | { |
| 18143 | "epoch": 37.79, |
| 18144 | "learning_rate": 7.443148688046646e-05, |
| 18145 | "loss": 0.0254, |
| 18146 | "step": 26300 |
| 18147 | }, |
| 18148 | { |
| 18149 | "epoch": 37.79, |
| 18150 | "eval_loss": 0.13217325508594513, |
| 18151 | "eval_runtime": 40.6524, |
| 18152 | "eval_samples_per_second": 11.242, |
| 18153 | "eval_steps_per_second": 1.427, |
| 18154 | "eval_wer": 0.13175726547206745, |
| 18155 | "step": 26300 |
| 18156 | }, |
| 18157 | { |
| 18158 | "epoch": 37.8, |
| 18159 | "learning_rate": 7.434402332361515e-05, |
| 18160 | "loss": 0.0281, |
| 18161 | "step": 26310 |
| 18162 | }, |
| 18163 | { |
| 18164 | "epoch": 37.82, |
| 18165 | "learning_rate": 7.425655976676384e-05, |
| 18166 | "loss": 0.0175, |
| 18167 | "step": 26320 |
| 18168 | }, |
| 18169 | { |
| 18170 | "epoch": 37.83, |
| 18171 | "learning_rate": 7.416909620991253e-05, |
| 18172 | "loss": 0.0375, |
| 18173 | "step": 26330 |
| 18174 | }, |
| 18175 | { |
| 18176 | "epoch": 37.84, |
| 18177 | "learning_rate": 7.408163265306122e-05, |
| 18178 | "loss": 0.0229, |
| 18179 | "step": 26340 |
| 18180 | }, |
| 18181 | { |
| 18182 | "epoch": 37.86, |
| 18183 | "learning_rate": 7.39941690962099e-05, |
| 18184 | "loss": 0.0193, |
| 18185 | "step": 26350 |
| 18186 | }, |
| 18187 | { |
| 18188 | "epoch": 37.87, |
| 18189 | "learning_rate": 7.390670553935859e-05, |
| 18190 | "loss": 0.0269, |
| 18191 | "step": 26360 |
| 18192 | }, |
| 18193 | { |
| 18194 | "epoch": 37.89, |
| 18195 | "learning_rate": 7.381924198250728e-05, |
| 18196 | "loss": 0.0233, |
| 18197 | "step": 26370 |
| 18198 | }, |
| 18199 | { |
| 18200 | "epoch": 37.9, |
| 18201 | "learning_rate": 7.373177842565597e-05, |
| 18202 | "loss": 0.0209, |
| 18203 | "step": 26380 |
| 18204 | }, |
| 18205 | { |
| 18206 | "epoch": 37.92, |
| 18207 | "learning_rate": 7.364431486880466e-05, |
| 18208 | "loss": 0.0232, |
| 18209 | "step": 26390 |
| 18210 | }, |
| 18211 | { |
| 18212 | "epoch": 37.93, |
| 18213 | "learning_rate": 7.355685131195334e-05, |
| 18214 | "loss": 0.0188, |
| 18215 | "step": 26400 |
| 18216 | }, |
| 18217 | { |
| 18218 | "epoch": 37.93, |
| 18219 | "eval_loss": 0.1334916353225708, |
| 18220 | "eval_runtime": 40.3434, |
| 18221 | "eval_samples_per_second": 11.328, |
| 18222 | "eval_steps_per_second": 1.438, |
| 18223 | "eval_wer": 0.1263363951212167, |
| 18224 | "step": 26400 |
| 18225 | }, |
| 18226 | { |
| 18227 | "epoch": 37.95, |
| 18228 | "learning_rate": 7.346938775510203e-05, |
| 18229 | "loss": 0.0282, |
| 18230 | "step": 26410 |
| 18231 | }, |
| 18232 | { |
| 18233 | "epoch": 37.96, |
| 18234 | "learning_rate": 7.338192419825072e-05, |
| 18235 | "loss": 0.0246, |
| 18236 | "step": 26420 |
| 18237 | }, |
| 18238 | { |
| 18239 | "epoch": 37.97, |
| 18240 | "learning_rate": 7.329446064139941e-05, |
| 18241 | "loss": 0.0293, |
| 18242 | "step": 26430 |
| 18243 | }, |
| 18244 | { |
| 18245 | "epoch": 37.99, |
| 18246 | "learning_rate": 7.32069970845481e-05, |
| 18247 | "loss": 0.0206, |
| 18248 | "step": 26440 |
| 18249 | }, |
| 18250 | { |
| 18251 | "epoch": 38.0, |
| 18252 | "learning_rate": 7.311953352769678e-05, |
| 18253 | "loss": 0.0228, |
| 18254 | "step": 26450 |
| 18255 | }, |
| 18256 | { |
| 18257 | "epoch": 38.02, |
| 18258 | "learning_rate": 7.303206997084547e-05, |
| 18259 | "loss": 0.0207, |
| 18260 | "step": 26460 |
| 18261 | }, |
| 18262 | { |
| 18263 | "epoch": 38.03, |
| 18264 | "learning_rate": 7.294460641399417e-05, |
| 18265 | "loss": 0.0213, |
| 18266 | "step": 26470 |
| 18267 | }, |
| 18268 | { |
| 18269 | "epoch": 38.05, |
| 18270 | "learning_rate": 7.285714285714285e-05, |
| 18271 | "loss": 0.0211, |
| 18272 | "step": 26480 |
| 18273 | }, |
| 18274 | { |
| 18275 | "epoch": 38.06, |
| 18276 | "learning_rate": 7.276967930029155e-05, |
| 18277 | "loss": 0.029, |
| 18278 | "step": 26490 |
| 18279 | }, |
| 18280 | { |
| 18281 | "epoch": 38.07, |
| 18282 | "learning_rate": 7.268221574344022e-05, |
| 18283 | "loss": 0.023, |
| 18284 | "step": 26500 |
| 18285 | }, |
| 18286 | { |
| 18287 | "epoch": 38.07, |
| 18288 | "eval_loss": 0.13524821400642395, |
| 18289 | "eval_runtime": 40.7993, |
| 18290 | "eval_samples_per_second": 11.201, |
| 18291 | "eval_steps_per_second": 1.422, |
| 18292 | "eval_wer": 0.1281433519048336, |
| 18293 | "step": 26500 |
| 18294 | }, |
| 18295 | { |
| 18296 | "epoch": 38.09, |
| 18297 | "learning_rate": 7.259475218658891e-05, |
| 18298 | "loss": 0.026, |
| 18299 | "step": 26510 |
| 18300 | }, |
| 18301 | { |
| 18302 | "epoch": 38.1, |
| 18303 | "learning_rate": 7.25072886297376e-05, |
| 18304 | "loss": 0.0165, |
| 18305 | "step": 26520 |
| 18306 | }, |
| 18307 | { |
| 18308 | "epoch": 38.12, |
| 18309 | "learning_rate": 7.241982507288629e-05, |
| 18310 | "loss": 0.03, |
| 18311 | "step": 26530 |
| 18312 | }, |
| 18313 | { |
| 18314 | "epoch": 38.13, |
| 18315 | "learning_rate": 7.233236151603497e-05, |
| 18316 | "loss": 0.0252, |
| 18317 | "step": 26540 |
| 18318 | }, |
| 18319 | { |
| 18320 | "epoch": 38.15, |
| 18321 | "learning_rate": 7.224489795918366e-05, |
| 18322 | "loss": 0.0309, |
| 18323 | "step": 26550 |
| 18324 | }, |
| 18325 | { |
| 18326 | "epoch": 38.16, |
| 18327 | "learning_rate": 7.215743440233236e-05, |
| 18328 | "loss": 0.0275, |
| 18329 | "step": 26560 |
| 18330 | }, |
| 18331 | { |
| 18332 | "epoch": 38.18, |
| 18333 | "learning_rate": 7.206997084548104e-05, |
| 18334 | "loss": 0.0196, |
| 18335 | "step": 26570 |
| 18336 | }, |
| 18337 | { |
| 18338 | "epoch": 38.19, |
| 18339 | "learning_rate": 7.198250728862974e-05, |
| 18340 | "loss": 0.0357, |
| 18341 | "step": 26580 |
| 18342 | }, |
| 18343 | { |
| 18344 | "epoch": 38.2, |
| 18345 | "learning_rate": 7.189504373177841e-05, |
| 18346 | "loss": 0.0248, |
| 18347 | "step": 26590 |
| 18348 | }, |
| 18349 | { |
| 18350 | "epoch": 38.22, |
| 18351 | "learning_rate": 7.180758017492712e-05, |
| 18352 | "loss": 0.0198, |
| 18353 | "step": 26600 |
| 18354 | }, |
| 18355 | { |
| 18356 | "epoch": 38.22, |
| 18357 | "eval_loss": 0.12783843278884888, |
| 18358 | "eval_runtime": 40.4736, |
| 18359 | "eval_samples_per_second": 11.291, |
| 18360 | "eval_steps_per_second": 1.433, |
| 18361 | "eval_wer": 0.12513175726547207, |
| 18362 | "step": 26600 |
| 18363 | }, |
| 18364 | { |
| 18365 | "epoch": 38.23, |
| 18366 | "learning_rate": 7.172011661807579e-05, |
| 18367 | "loss": 0.0328, |
| 18368 | "step": 26610 |
| 18369 | }, |
| 18370 | { |
| 18371 | "epoch": 38.25, |
| 18372 | "learning_rate": 7.163265306122449e-05, |
| 18373 | "loss": 0.0212, |
| 18374 | "step": 26620 |
| 18375 | }, |
| 18376 | { |
| 18377 | "epoch": 38.26, |
| 18378 | "learning_rate": 7.154518950437317e-05, |
| 18379 | "loss": 0.0277, |
| 18380 | "step": 26630 |
| 18381 | }, |
| 18382 | { |
| 18383 | "epoch": 38.28, |
| 18384 | "learning_rate": 7.145772594752185e-05, |
| 18385 | "loss": 0.0255, |
| 18386 | "step": 26640 |
| 18387 | }, |
| 18388 | { |
| 18389 | "epoch": 38.29, |
| 18390 | "learning_rate": 7.137026239067055e-05, |
| 18391 | "loss": 0.0212, |
| 18392 | "step": 26650 |
| 18393 | }, |
| 18394 | { |
| 18395 | "epoch": 38.3, |
| 18396 | "learning_rate": 7.128279883381923e-05, |
| 18397 | "loss": 0.0313, |
| 18398 | "step": 26660 |
| 18399 | }, |
| 18400 | { |
| 18401 | "epoch": 38.32, |
| 18402 | "learning_rate": 7.119533527696793e-05, |
| 18403 | "loss": 0.0216, |
| 18404 | "step": 26670 |
| 18405 | }, |
| 18406 | { |
| 18407 | "epoch": 38.33, |
| 18408 | "learning_rate": 7.11078717201166e-05, |
| 18409 | "loss": 0.0226, |
| 18410 | "step": 26680 |
| 18411 | }, |
| 18412 | { |
| 18413 | "epoch": 38.35, |
| 18414 | "learning_rate": 7.10204081632653e-05, |
| 18415 | "loss": 0.0209, |
| 18416 | "step": 26690 |
| 18417 | }, |
| 18418 | { |
| 18419 | "epoch": 38.36, |
| 18420 | "learning_rate": 7.093294460641398e-05, |
| 18421 | "loss": 0.0182, |
| 18422 | "step": 26700 |
| 18423 | }, |
| 18424 | { |
| 18425 | "epoch": 38.36, |
| 18426 | "eval_loss": 0.13292567431926727, |
| 18427 | "eval_runtime": 40.4251, |
| 18428 | "eval_samples_per_second": 11.305, |
| 18429 | "eval_steps_per_second": 1.435, |
| 18430 | "eval_wer": 0.12769161270892937, |
| 18431 | "step": 26700 |
| 18432 | }, |
| 18433 | { |
| 18434 | "epoch": 38.38, |
| 18435 | "learning_rate": 7.084548104956268e-05, |
| 18436 | "loss": 0.0236, |
| 18437 | "step": 26710 |
| 18438 | }, |
| 18439 | { |
| 18440 | "epoch": 38.39, |
| 18441 | "learning_rate": 7.075801749271136e-05, |
| 18442 | "loss": 0.0209, |
| 18443 | "step": 26720 |
| 18444 | }, |
| 18445 | { |
| 18446 | "epoch": 38.41, |
| 18447 | "learning_rate": 7.067055393586006e-05, |
| 18448 | "loss": 0.026, |
| 18449 | "step": 26730 |
| 18450 | }, |
| 18451 | { |
| 18452 | "epoch": 38.42, |
| 18453 | "learning_rate": 7.058309037900875e-05, |
| 18454 | "loss": 0.0235, |
| 18455 | "step": 26740 |
| 18456 | }, |
| 18457 | { |
| 18458 | "epoch": 38.43, |
| 18459 | "learning_rate": 7.049562682215743e-05, |
| 18460 | "loss": 0.0405, |
| 18461 | "step": 26750 |
| 18462 | }, |
| 18463 | { |
| 18464 | "epoch": 38.45, |
| 18465 | "learning_rate": 7.040816326530612e-05, |
| 18466 | "loss": 0.0295, |
| 18467 | "step": 26760 |
| 18468 | }, |
| 18469 | { |
| 18470 | "epoch": 38.46, |
| 18471 | "learning_rate": 7.032069970845481e-05, |
| 18472 | "loss": 0.0203, |
| 18473 | "step": 26770 |
| 18474 | }, |
| 18475 | { |
| 18476 | "epoch": 38.48, |
| 18477 | "learning_rate": 7.02332361516035e-05, |
| 18478 | "loss": 0.0207, |
| 18479 | "step": 26780 |
| 18480 | }, |
| 18481 | { |
| 18482 | "epoch": 38.49, |
| 18483 | "learning_rate": 7.014577259475217e-05, |
| 18484 | "loss": 0.0239, |
| 18485 | "step": 26790 |
| 18486 | }, |
| 18487 | { |
| 18488 | "epoch": 38.51, |
| 18489 | "learning_rate": 7.005830903790087e-05, |
| 18490 | "loss": 0.0257, |
| 18491 | "step": 26800 |
| 18492 | }, |
| 18493 | { |
| 18494 | "epoch": 38.51, |
| 18495 | "eval_loss": 0.1308964639902115, |
| 18496 | "eval_runtime": 40.3719, |
| 18497 | "eval_samples_per_second": 11.32, |
| 18498 | "eval_steps_per_second": 1.437, |
| 18499 | "eval_wer": 0.1281433519048336, |
| 18500 | "step": 26800 |
| 18501 | }, |
| 18502 | { |
| 18503 | "epoch": 38.52, |
| 18504 | "learning_rate": 6.997084548104955e-05, |
| 18505 | "loss": 0.0285, |
| 18506 | "step": 26810 |
| 18507 | }, |
| 18508 | { |
| 18509 | "epoch": 38.53, |
| 18510 | "learning_rate": 6.988338192419825e-05, |
| 18511 | "loss": 0.0245, |
| 18512 | "step": 26820 |
| 18513 | }, |
| 18514 | { |
| 18515 | "epoch": 38.55, |
| 18516 | "learning_rate": 6.979591836734692e-05, |
| 18517 | "loss": 0.0231, |
| 18518 | "step": 26830 |
| 18519 | }, |
| 18520 | { |
| 18521 | "epoch": 38.56, |
| 18522 | "learning_rate": 6.970845481049562e-05, |
| 18523 | "loss": 0.032, |
| 18524 | "step": 26840 |
| 18525 | }, |
| 18526 | { |
| 18527 | "epoch": 38.58, |
| 18528 | "learning_rate": 6.962099125364431e-05, |
| 18529 | "loss": 0.0209, |
| 18530 | "step": 26850 |
| 18531 | }, |
| 18532 | { |
| 18533 | "epoch": 38.59, |
| 18534 | "learning_rate": 6.9533527696793e-05, |
| 18535 | "loss": 0.0254, |
| 18536 | "step": 26860 |
| 18537 | }, |
| 18538 | { |
| 18539 | "epoch": 38.61, |
| 18540 | "learning_rate": 6.944606413994169e-05, |
| 18541 | "loss": 0.022, |
| 18542 | "step": 26870 |
| 18543 | }, |
| 18544 | { |
| 18545 | "epoch": 38.62, |
| 18546 | "learning_rate": 6.935860058309038e-05, |
| 18547 | "loss": 0.022, |
| 18548 | "step": 26880 |
| 18549 | }, |
| 18550 | { |
| 18551 | "epoch": 38.64, |
| 18552 | "learning_rate": 6.927113702623906e-05, |
| 18553 | "loss": 0.0182, |
| 18554 | "step": 26890 |
| 18555 | }, |
| 18556 | { |
| 18557 | "epoch": 38.65, |
| 18558 | "learning_rate": 6.918367346938775e-05, |
| 18559 | "loss": 0.0259, |
| 18560 | "step": 26900 |
| 18561 | }, |
| 18562 | { |
| 18563 | "epoch": 38.65, |
| 18564 | "eval_loss": 0.1267746239900589, |
| 18565 | "eval_runtime": 40.23, |
| 18566 | "eval_samples_per_second": 11.36, |
| 18567 | "eval_steps_per_second": 1.442, |
| 18568 | "eval_wer": 0.1281433519048336, |
| 18569 | "step": 26900 |
| 18570 | }, |
| 18571 | { |
| 18572 | "epoch": 38.66, |
| 18573 | "learning_rate": 6.909620991253644e-05, |
| 18574 | "loss": 0.034, |
| 18575 | "step": 26910 |
| 18576 | }, |
| 18577 | { |
| 18578 | "epoch": 38.68, |
| 18579 | "learning_rate": 6.900874635568513e-05, |
| 18580 | "loss": 0.0205, |
| 18581 | "step": 26920 |
| 18582 | }, |
| 18583 | { |
| 18584 | "epoch": 38.69, |
| 18585 | "learning_rate": 6.892128279883382e-05, |
| 18586 | "loss": 0.0194, |
| 18587 | "step": 26930 |
| 18588 | }, |
| 18589 | { |
| 18590 | "epoch": 38.71, |
| 18591 | "learning_rate": 6.88338192419825e-05, |
| 18592 | "loss": 0.0293, |
| 18593 | "step": 26940 |
| 18594 | }, |
| 18595 | { |
| 18596 | "epoch": 38.72, |
| 18597 | "learning_rate": 6.874635568513119e-05, |
| 18598 | "loss": 0.0194, |
| 18599 | "step": 26950 |
| 18600 | }, |
| 18601 | { |
| 18602 | "epoch": 38.74, |
| 18603 | "learning_rate": 6.865889212827988e-05, |
| 18604 | "loss": 0.026, |
| 18605 | "step": 26960 |
| 18606 | }, |
| 18607 | { |
| 18608 | "epoch": 38.75, |
| 18609 | "learning_rate": 6.857142857142857e-05, |
| 18610 | "loss": 0.0182, |
| 18611 | "step": 26970 |
| 18612 | }, |
| 18613 | { |
| 18614 | "epoch": 38.76, |
| 18615 | "learning_rate": 6.848396501457726e-05, |
| 18616 | "loss": 0.0279, |
| 18617 | "step": 26980 |
| 18618 | }, |
| 18619 | { |
| 18620 | "epoch": 38.78, |
| 18621 | "learning_rate": 6.839650145772594e-05, |
| 18622 | "loss": 0.0234, |
| 18623 | "step": 26990 |
| 18624 | }, |
| 18625 | { |
| 18626 | "epoch": 38.79, |
| 18627 | "learning_rate": 6.830903790087463e-05, |
| 18628 | "loss": 0.0306, |
| 18629 | "step": 27000 |
| 18630 | }, |
| 18631 | { |
| 18632 | "epoch": 38.79, |
| 18633 | "eval_loss": 0.13185811042785645, |
| 18634 | "eval_runtime": 40.2584, |
| 18635 | "eval_samples_per_second": 11.352, |
| 18636 | "eval_steps_per_second": 1.441, |
| 18637 | "eval_wer": 0.12964914922451437, |
| 18638 | "step": 27000 |
| 18639 | }, |
| 18640 | { |
| 18641 | "epoch": 38.81, |
| 18642 | "learning_rate": 6.822157434402332e-05, |
| 18643 | "loss": 0.0247, |
| 18644 | "step": 27010 |
| 18645 | }, |
| 18646 | { |
| 18647 | "epoch": 38.82, |
| 18648 | "learning_rate": 6.813411078717201e-05, |
| 18649 | "loss": 0.018, |
| 18650 | "step": 27020 |
| 18651 | }, |
| 18652 | { |
| 18653 | "epoch": 38.84, |
| 18654 | "learning_rate": 6.80466472303207e-05, |
| 18655 | "loss": 0.022, |
| 18656 | "step": 27030 |
| 18657 | }, |
| 18658 | { |
| 18659 | "epoch": 38.85, |
| 18660 | "learning_rate": 6.795918367346938e-05, |
| 18661 | "loss": 0.0232, |
| 18662 | "step": 27040 |
| 18663 | }, |
| 18664 | { |
| 18665 | "epoch": 38.86, |
| 18666 | "learning_rate": 6.787172011661807e-05, |
| 18667 | "loss": 0.0234, |
| 18668 | "step": 27050 |
| 18669 | }, |
| 18670 | { |
| 18671 | "epoch": 38.88, |
| 18672 | "learning_rate": 6.778425655976676e-05, |
| 18673 | "loss": 0.0329, |
| 18674 | "step": 27060 |
| 18675 | }, |
| 18676 | { |
| 18677 | "epoch": 38.89, |
| 18678 | "learning_rate": 6.769679300291545e-05, |
| 18679 | "loss": 0.0216, |
| 18680 | "step": 27070 |
| 18681 | }, |
| 18682 | { |
| 18683 | "epoch": 38.91, |
| 18684 | "learning_rate": 6.760932944606413e-05, |
| 18685 | "loss": 0.0252, |
| 18686 | "step": 27080 |
| 18687 | }, |
| 18688 | { |
| 18689 | "epoch": 38.92, |
| 18690 | "learning_rate": 6.752186588921282e-05, |
| 18691 | "loss": 0.022, |
| 18692 | "step": 27090 |
| 18693 | }, |
| 18694 | { |
| 18695 | "epoch": 38.94, |
| 18696 | "learning_rate": 6.743440233236151e-05, |
| 18697 | "loss": 0.0212, |
| 18698 | "step": 27100 |
| 18699 | }, |
| 18700 | { |
| 18701 | "epoch": 38.94, |
| 18702 | "eval_loss": 0.12713249027729034, |
| 18703 | "eval_runtime": 40.5764, |
| 18704 | "eval_samples_per_second": 11.263, |
| 18705 | "eval_steps_per_second": 1.429, |
| 18706 | "eval_wer": 0.1275410329769613, |
| 18707 | "step": 27100 |
| 18708 | }, |
| 18709 | { |
| 18710 | "epoch": 38.95, |
| 18711 | "learning_rate": 6.73469387755102e-05, |
| 18712 | "loss": 0.0213, |
| 18713 | "step": 27110 |
| 18714 | }, |
| 18715 | { |
| 18716 | "epoch": 38.97, |
| 18717 | "learning_rate": 6.725947521865889e-05, |
| 18718 | "loss": 0.0196, |
| 18719 | "step": 27120 |
| 18720 | }, |
| 18721 | { |
| 18722 | "epoch": 38.98, |
| 18723 | "learning_rate": 6.717201166180757e-05, |
| 18724 | "loss": 0.0269, |
| 18725 | "step": 27130 |
| 18726 | }, |
| 18727 | { |
| 18728 | "epoch": 38.99, |
| 18729 | "learning_rate": 6.708454810495626e-05, |
| 18730 | "loss": 0.0212, |
| 18731 | "step": 27140 |
| 18732 | }, |
| 18733 | { |
| 18734 | "epoch": 39.01, |
| 18735 | "learning_rate": 6.699708454810495e-05, |
| 18736 | "loss": 0.0208, |
| 18737 | "step": 27150 |
| 18738 | }, |
| 18739 | { |
| 18740 | "epoch": 39.02, |
| 18741 | "learning_rate": 6.690962099125364e-05, |
| 18742 | "loss": 0.0191, |
| 18743 | "step": 27160 |
| 18744 | }, |
| 18745 | { |
| 18746 | "epoch": 39.04, |
| 18747 | "learning_rate": 6.682215743440233e-05, |
| 18748 | "loss": 0.02, |
| 18749 | "step": 27170 |
| 18750 | }, |
| 18751 | { |
| 18752 | "epoch": 39.05, |
| 18753 | "learning_rate": 6.673469387755101e-05, |
| 18754 | "loss": 0.0265, |
| 18755 | "step": 27180 |
| 18756 | }, |
| 18757 | { |
| 18758 | "epoch": 39.07, |
| 18759 | "learning_rate": 6.66472303206997e-05, |
| 18760 | "loss": 0.0179, |
| 18761 | "step": 27190 |
| 18762 | }, |
| 18763 | { |
| 18764 | "epoch": 39.08, |
| 18765 | "learning_rate": 6.655976676384839e-05, |
| 18766 | "loss": 0.0214, |
| 18767 | "step": 27200 |
| 18768 | }, |
| 18769 | { |
| 18770 | "epoch": 39.08, |
| 18771 | "eval_loss": 0.13211554288864136, |
| 18772 | "eval_runtime": 40.5187, |
| 18773 | "eval_samples_per_second": 11.279, |
| 18774 | "eval_steps_per_second": 1.431, |
| 18775 | "eval_wer": 0.12739045324499323, |
| 18776 | "step": 27200 |
| 18777 | }, |
| 18778 | { |
| 18779 | "epoch": 39.09, |
| 18780 | "learning_rate": 6.647230320699708e-05, |
| 18781 | "loss": 0.0229, |
| 18782 | "step": 27210 |
| 18783 | }, |
| 18784 | { |
| 18785 | "epoch": 39.11, |
| 18786 | "learning_rate": 6.638483965014576e-05, |
| 18787 | "loss": 0.0187, |
| 18788 | "step": 27220 |
| 18789 | }, |
| 18790 | { |
| 18791 | "epoch": 39.12, |
| 18792 | "learning_rate": 6.629737609329445e-05, |
| 18793 | "loss": 0.0347, |
| 18794 | "step": 27230 |
| 18795 | }, |
| 18796 | { |
| 18797 | "epoch": 39.14, |
| 18798 | "learning_rate": 6.620991253644314e-05, |
| 18799 | "loss": 0.0202, |
| 18800 | "step": 27240 |
| 18801 | }, |
| 18802 | { |
| 18803 | "epoch": 39.15, |
| 18804 | "learning_rate": 6.612244897959183e-05, |
| 18805 | "loss": 0.0274, |
| 18806 | "step": 27250 |
| 18807 | }, |
| 18808 | { |
| 18809 | "epoch": 39.17, |
| 18810 | "learning_rate": 6.603498542274052e-05, |
| 18811 | "loss": 0.0294, |
| 18812 | "step": 27260 |
| 18813 | }, |
| 18814 | { |
| 18815 | "epoch": 39.18, |
| 18816 | "learning_rate": 6.59475218658892e-05, |
| 18817 | "loss": 0.0238, |
| 18818 | "step": 27270 |
| 18819 | }, |
| 18820 | { |
| 18821 | "epoch": 39.2, |
| 18822 | "learning_rate": 6.586005830903789e-05, |
| 18823 | "loss": 0.0228, |
| 18824 | "step": 27280 |
| 18825 | }, |
| 18826 | { |
| 18827 | "epoch": 39.21, |
| 18828 | "learning_rate": 6.577259475218658e-05, |
| 18829 | "loss": 0.0224, |
| 18830 | "step": 27290 |
| 18831 | }, |
| 18832 | { |
| 18833 | "epoch": 39.22, |
| 18834 | "learning_rate": 6.568513119533528e-05, |
| 18835 | "loss": 0.0385, |
| 18836 | "step": 27300 |
| 18837 | }, |
| 18838 | { |
| 18839 | "epoch": 39.22, |
| 18840 | "eval_loss": 0.13131336867809296, |
| 18841 | "eval_runtime": 40.7082, |
| 18842 | "eval_samples_per_second": 11.226, |
| 18843 | "eval_steps_per_second": 1.425, |
| 18844 | "eval_wer": 0.128896250564674, |
| 18845 | "step": 27300 |
| 18846 | }, |
| 18847 | { |
| 18848 | "epoch": 39.24, |
| 18849 | "learning_rate": 6.559766763848396e-05, |
| 18850 | "loss": 0.0241, |
| 18851 | "step": 27310 |
| 18852 | }, |
| 18853 | { |
| 18854 | "epoch": 39.25, |
| 18855 | "learning_rate": 6.551020408163264e-05, |
| 18856 | "loss": 0.0323, |
| 18857 | "step": 27320 |
| 18858 | }, |
| 18859 | { |
| 18860 | "epoch": 39.27, |
| 18861 | "learning_rate": 6.542274052478133e-05, |
| 18862 | "loss": 0.0283, |
| 18863 | "step": 27330 |
| 18864 | }, |
| 18865 | { |
| 18866 | "epoch": 39.28, |
| 18867 | "learning_rate": 6.533527696793002e-05, |
| 18868 | "loss": 0.0223, |
| 18869 | "step": 27340 |
| 18870 | }, |
| 18871 | { |
| 18872 | "epoch": 39.3, |
| 18873 | "learning_rate": 6.524781341107871e-05, |
| 18874 | "loss": 0.023, |
| 18875 | "step": 27350 |
| 18876 | }, |
| 18877 | { |
| 18878 | "epoch": 39.31, |
| 18879 | "learning_rate": 6.51603498542274e-05, |
| 18880 | "loss": 0.0232, |
| 18881 | "step": 27360 |
| 18882 | }, |
| 18883 | { |
| 18884 | "epoch": 39.32, |
| 18885 | "learning_rate": 6.507288629737608e-05, |
| 18886 | "loss": 0.0214, |
| 18887 | "step": 27370 |
| 18888 | }, |
| 18889 | { |
| 18890 | "epoch": 39.34, |
| 18891 | "learning_rate": 6.498542274052477e-05, |
| 18892 | "loss": 0.0239, |
| 18893 | "step": 27380 |
| 18894 | }, |
| 18895 | { |
| 18896 | "epoch": 39.35, |
| 18897 | "learning_rate": 6.489795918367347e-05, |
| 18898 | "loss": 0.0254, |
| 18899 | "step": 27390 |
| 18900 | }, |
| 18901 | { |
| 18902 | "epoch": 39.37, |
| 18903 | "learning_rate": 6.481049562682215e-05, |
| 18904 | "loss": 0.0315, |
| 18905 | "step": 27400 |
| 18906 | }, |
| 18907 | { |
| 18908 | "epoch": 39.37, |
| 18909 | "eval_loss": 0.1282867193222046, |
| 18910 | "eval_runtime": 40.3945, |
| 18911 | "eval_samples_per_second": 11.313, |
| 18912 | "eval_steps_per_second": 1.436, |
| 18913 | "eval_wer": 0.12904683029664207, |
| 18914 | "step": 27400 |
| 18915 | }, |
| 18916 | { |
| 18917 | "epoch": 39.38, |
| 18918 | "learning_rate": 6.472303206997085e-05, |
| 18919 | "loss": 0.0206, |
| 18920 | "step": 27410 |
| 18921 | }, |
| 18922 | { |
| 18923 | "epoch": 39.4, |
| 18924 | "learning_rate": 6.463556851311952e-05, |
| 18925 | "loss": 0.0206, |
| 18926 | "step": 27420 |
| 18927 | }, |
| 18928 | { |
| 18929 | "epoch": 39.41, |
| 18930 | "learning_rate": 6.454810495626822e-05, |
| 18931 | "loss": 0.0248, |
| 18932 | "step": 27430 |
| 18933 | }, |
| 18934 | { |
| 18935 | "epoch": 39.43, |
| 18936 | "learning_rate": 6.44606413994169e-05, |
| 18937 | "loss": 0.0141, |
| 18938 | "step": 27440 |
| 18939 | }, |
| 18940 | { |
| 18941 | "epoch": 39.44, |
| 18942 | "learning_rate": 6.437317784256559e-05, |
| 18943 | "loss": 0.0348, |
| 18944 | "step": 27450 |
| 18945 | }, |
| 18946 | { |
| 18947 | "epoch": 39.45, |
| 18948 | "learning_rate": 6.428571428571427e-05, |
| 18949 | "loss": 0.0207, |
| 18950 | "step": 27460 |
| 18951 | }, |
| 18952 | { |
| 18953 | "epoch": 39.47, |
| 18954 | "learning_rate": 6.419825072886296e-05, |
| 18955 | "loss": 0.0248, |
| 18956 | "step": 27470 |
| 18957 | }, |
| 18958 | { |
| 18959 | "epoch": 39.48, |
| 18960 | "learning_rate": 6.411078717201166e-05, |
| 18961 | "loss": 0.0209, |
| 18962 | "step": 27480 |
| 18963 | }, |
| 18964 | { |
| 18965 | "epoch": 39.5, |
| 18966 | "learning_rate": 6.402332361516034e-05, |
| 18967 | "loss": 0.0215, |
| 18968 | "step": 27490 |
| 18969 | }, |
| 18970 | { |
| 18971 | "epoch": 39.51, |
| 18972 | "learning_rate": 6.393586005830904e-05, |
| 18973 | "loss": 0.0208, |
| 18974 | "step": 27500 |
| 18975 | }, |
| 18976 | { |
| 18977 | "epoch": 39.51, |
| 18978 | "eval_loss": 0.1325148493051529, |
| 18979 | "eval_runtime": 40.3921, |
| 18980 | "eval_samples_per_second": 11.314, |
| 18981 | "eval_steps_per_second": 1.436, |
| 18982 | "eval_wer": 0.1263363951212167, |
| 18983 | "step": 27500 |
| 18984 | }, |
| 18985 | { |
| 18986 | "epoch": 39.53, |
| 18987 | "learning_rate": 6.384839650145771e-05, |
| 18988 | "loss": 0.0152, |
| 18989 | "step": 27510 |
| 18990 | }, |
| 18991 | { |
| 18992 | "epoch": 39.54, |
| 18993 | "learning_rate": 6.376093294460642e-05, |
| 18994 | "loss": 0.0182, |
| 18995 | "step": 27520 |
| 18996 | }, |
| 18997 | { |
| 18998 | "epoch": 39.55, |
| 18999 | "learning_rate": 6.367346938775509e-05, |
| 19000 | "loss": 0.0226, |
| 19001 | "step": 27530 |
| 19002 | }, |
| 19003 | { |
| 19004 | "epoch": 39.57, |
| 19005 | "learning_rate": 6.358600583090379e-05, |
| 19006 | "loss": 0.0204, |
| 19007 | "step": 27540 |
| 19008 | }, |
| 19009 | { |
| 19010 | "epoch": 39.58, |
| 19011 | "learning_rate": 6.349854227405247e-05, |
| 19012 | "loss": 0.024, |
| 19013 | "step": 27550 |
| 19014 | }, |
| 19015 | { |
| 19016 | "epoch": 39.6, |
| 19017 | "learning_rate": 6.341107871720117e-05, |
| 19018 | "loss": 0.0212, |
| 19019 | "step": 27560 |
| 19020 | }, |
| 19021 | { |
| 19022 | "epoch": 39.61, |
| 19023 | "learning_rate": 6.332361516034985e-05, |
| 19024 | "loss": 0.0247, |
| 19025 | "step": 27570 |
| 19026 | }, |
| 19027 | { |
| 19028 | "epoch": 39.63, |
| 19029 | "learning_rate": 6.323615160349854e-05, |
| 19030 | "loss": 0.0294, |
| 19031 | "step": 27580 |
| 19032 | }, |
| 19033 | { |
| 19034 | "epoch": 39.64, |
| 19035 | "learning_rate": 6.314868804664723e-05, |
| 19036 | "loss": 0.0198, |
| 19037 | "step": 27590 |
| 19038 | }, |
| 19039 | { |
| 19040 | "epoch": 39.66, |
| 19041 | "learning_rate": 6.30612244897959e-05, |
| 19042 | "loss": 0.029, |
| 19043 | "step": 27600 |
| 19044 | }, |
| 19045 | { |
| 19046 | "epoch": 39.66, |
| 19047 | "eval_loss": 0.12957048416137695, |
| 19048 | "eval_runtime": 40.5377, |
| 19049 | "eval_samples_per_second": 11.273, |
| 19050 | "eval_steps_per_second": 1.431, |
| 19051 | "eval_wer": 0.12919741002861015, |
| 19052 | "step": 27600 |
| 19053 | }, |
| 19054 | { |
| 19055 | "epoch": 39.67, |
| 19056 | "learning_rate": 6.29737609329446e-05, |
| 19057 | "loss": 0.0228, |
| 19058 | "step": 27610 |
| 19059 | }, |
| 19060 | { |
| 19061 | "epoch": 39.68, |
| 19062 | "learning_rate": 6.288629737609328e-05, |
| 19063 | "loss": 0.0301, |
| 19064 | "step": 27620 |
| 19065 | }, |
| 19066 | { |
| 19067 | "epoch": 39.7, |
| 19068 | "learning_rate": 6.279883381924198e-05, |
| 19069 | "loss": 0.0275, |
| 19070 | "step": 27630 |
| 19071 | }, |
| 19072 | { |
| 19073 | "epoch": 39.71, |
| 19074 | "learning_rate": 6.271137026239066e-05, |
| 19075 | "loss": 0.0215, |
| 19076 | "step": 27640 |
| 19077 | }, |
| 19078 | { |
| 19079 | "epoch": 39.73, |
| 19080 | "learning_rate": 6.262390670553936e-05, |
| 19081 | "loss": 0.0207, |
| 19082 | "step": 27650 |
| 19083 | }, |
| 19084 | { |
| 19085 | "epoch": 39.74, |
| 19086 | "learning_rate": 6.253644314868805e-05, |
| 19087 | "loss": 0.0204, |
| 19088 | "step": 27660 |
| 19089 | }, |
| 19090 | { |
| 19091 | "epoch": 39.76, |
| 19092 | "learning_rate": 6.244897959183673e-05, |
| 19093 | "loss": 0.0222, |
| 19094 | "step": 27670 |
| 19095 | }, |
| 19096 | { |
| 19097 | "epoch": 39.77, |
| 19098 | "learning_rate": 6.236151603498542e-05, |
| 19099 | "loss": 0.0264, |
| 19100 | "step": 27680 |
| 19101 | }, |
| 19102 | { |
| 19103 | "epoch": 39.78, |
| 19104 | "learning_rate": 6.227405247813411e-05, |
| 19105 | "loss": 0.0174, |
| 19106 | "step": 27690 |
| 19107 | }, |
| 19108 | { |
| 19109 | "epoch": 39.8, |
| 19110 | "learning_rate": 6.21865889212828e-05, |
| 19111 | "loss": 0.0263, |
| 19112 | "step": 27700 |
| 19113 | }, |
| 19114 | { |
| 19115 | "epoch": 39.8, |
| 19116 | "eval_loss": 0.12812817096710205, |
| 19117 | "eval_runtime": 41.192, |
| 19118 | "eval_samples_per_second": 11.094, |
| 19119 | "eval_steps_per_second": 1.408, |
| 19120 | "eval_wer": 0.12723987351302515, |
| 19121 | "step": 27700 |
| 19122 | }, |
| 19123 | { |
| 19124 | "epoch": 39.81, |
| 19125 | "learning_rate": 6.209912536443149e-05, |
| 19126 | "loss": 0.0186, |
| 19127 | "step": 27710 |
| 19128 | }, |
| 19129 | { |
| 19130 | "epoch": 39.83, |
| 19131 | "learning_rate": 6.201166180758017e-05, |
| 19132 | "loss": 0.0252, |
| 19133 | "step": 27720 |
| 19134 | }, |
| 19135 | { |
| 19136 | "epoch": 39.84, |
| 19137 | "learning_rate": 6.192419825072885e-05, |
| 19138 | "loss": 0.0235, |
| 19139 | "step": 27730 |
| 19140 | }, |
| 19141 | { |
| 19142 | "epoch": 39.86, |
| 19143 | "learning_rate": 6.183673469387755e-05, |
| 19144 | "loss": 0.0255, |
| 19145 | "step": 27740 |
| 19146 | }, |
| 19147 | { |
| 19148 | "epoch": 39.87, |
| 19149 | "learning_rate": 6.174927113702624e-05, |
| 19150 | "loss": 0.0327, |
| 19151 | "step": 27750 |
| 19152 | }, |
| 19153 | { |
| 19154 | "epoch": 39.89, |
| 19155 | "learning_rate": 6.166180758017492e-05, |
| 19156 | "loss": 0.0238, |
| 19157 | "step": 27760 |
| 19158 | }, |
| 19159 | { |
| 19160 | "epoch": 39.9, |
| 19161 | "learning_rate": 6.157434402332361e-05, |
| 19162 | "loss": 0.0144, |
| 19163 | "step": 27770 |
| 19164 | }, |
| 19165 | { |
| 19166 | "epoch": 39.91, |
| 19167 | "learning_rate": 6.14868804664723e-05, |
| 19168 | "loss": 0.0244, |
| 19169 | "step": 27780 |
| 19170 | }, |
| 19171 | { |
| 19172 | "epoch": 39.93, |
| 19173 | "learning_rate": 6.139941690962099e-05, |
| 19174 | "loss": 0.0205, |
| 19175 | "step": 27790 |
| 19176 | }, |
| 19177 | { |
| 19178 | "epoch": 39.94, |
| 19179 | "learning_rate": 6.131195335276968e-05, |
| 19180 | "loss": 0.0234, |
| 19181 | "step": 27800 |
| 19182 | }, |
| 19183 | { |
| 19184 | "epoch": 39.94, |
| 19185 | "eval_loss": 0.12909665703773499, |
| 19186 | "eval_runtime": 40.2598, |
| 19187 | "eval_samples_per_second": 11.351, |
| 19188 | "eval_steps_per_second": 1.441, |
| 19189 | "eval_wer": 0.12498117753350399, |
| 19190 | "step": 27800 |
| 19191 | }, |
| 19192 | { |
| 19193 | "epoch": 39.96, |
| 19194 | "learning_rate": 6.122448979591836e-05, |
| 19195 | "loss": 0.0253, |
| 19196 | "step": 27810 |
| 19197 | }, |
| 19198 | { |
| 19199 | "epoch": 39.97, |
| 19200 | "learning_rate": 6.113702623906705e-05, |
| 19201 | "loss": 0.0199, |
| 19202 | "step": 27820 |
| 19203 | }, |
| 19204 | { |
| 19205 | "epoch": 39.99, |
| 19206 | "learning_rate": 6.104956268221574e-05, |
| 19207 | "loss": 0.0212, |
| 19208 | "step": 27830 |
| 19209 | }, |
| 19210 | { |
| 19211 | "epoch": 40.0, |
| 19212 | "learning_rate": 6.096209912536443e-05, |
| 19213 | "loss": 0.0206, |
| 19214 | "step": 27840 |
| 19215 | }, |
| 19216 | { |
| 19217 | "epoch": 40.01, |
| 19218 | "learning_rate": 6.0874635568513116e-05, |
| 19219 | "loss": 0.0249, |
| 19220 | "step": 27850 |
| 19221 | }, |
| 19222 | { |
| 19223 | "epoch": 40.03, |
| 19224 | "learning_rate": 6.0787172011661804e-05, |
| 19225 | "loss": 0.021, |
| 19226 | "step": 27860 |
| 19227 | }, |
| 19228 | { |
| 19229 | "epoch": 40.04, |
| 19230 | "learning_rate": 6.069970845481049e-05, |
| 19231 | "loss": 0.027, |
| 19232 | "step": 27870 |
| 19233 | }, |
| 19234 | { |
| 19235 | "epoch": 40.06, |
| 19236 | "learning_rate": 6.061224489795918e-05, |
| 19237 | "loss": 0.0231, |
| 19238 | "step": 27880 |
| 19239 | }, |
| 19240 | { |
| 19241 | "epoch": 40.07, |
| 19242 | "learning_rate": 6.052478134110787e-05, |
| 19243 | "loss": 0.0224, |
| 19244 | "step": 27890 |
| 19245 | }, |
| 19246 | { |
| 19247 | "epoch": 40.09, |
| 19248 | "learning_rate": 6.0437317784256555e-05, |
| 19249 | "loss": 0.0229, |
| 19250 | "step": 27900 |
| 19251 | }, |
| 19252 | { |
| 19253 | "epoch": 40.09, |
| 19254 | "eval_loss": 0.13076798617839813, |
| 19255 | "eval_runtime": 40.4671, |
| 19256 | "eval_samples_per_second": 11.293, |
| 19257 | "eval_steps_per_second": 1.433, |
| 19258 | "eval_wer": 0.1287456708327059, |
| 19259 | "step": 27900 |
| 19260 | }, |
| 19261 | { |
| 19262 | "epoch": 40.1, |
| 19263 | "learning_rate": 6.0349854227405236e-05, |
| 19264 | "loss": 0.0167, |
| 19265 | "step": 27910 |
| 19266 | }, |
| 19267 | { |
| 19268 | "epoch": 40.11, |
| 19269 | "learning_rate": 6.026239067055393e-05, |
| 19270 | "loss": 0.0221, |
| 19271 | "step": 27920 |
| 19272 | }, |
| 19273 | { |
| 19274 | "epoch": 40.13, |
| 19275 | "learning_rate": 6.017492711370261e-05, |
| 19276 | "loss": 0.0211, |
| 19277 | "step": 27930 |
| 19278 | }, |
| 19279 | { |
| 19280 | "epoch": 40.14, |
| 19281 | "learning_rate": 6.008746355685131e-05, |
| 19282 | "loss": 0.0211, |
| 19283 | "step": 27940 |
| 19284 | }, |
| 19285 | { |
| 19286 | "epoch": 40.16, |
| 19287 | "learning_rate": 5.9999999999999995e-05, |
| 19288 | "loss": 0.0239, |
| 19289 | "step": 27950 |
| 19290 | }, |
| 19291 | { |
| 19292 | "epoch": 40.17, |
| 19293 | "learning_rate": 5.991253644314868e-05, |
| 19294 | "loss": 0.0241, |
| 19295 | "step": 27960 |
| 19296 | }, |
| 19297 | { |
| 19298 | "epoch": 40.19, |
| 19299 | "learning_rate": 5.982507288629737e-05, |
| 19300 | "loss": 0.029, |
| 19301 | "step": 27970 |
| 19302 | }, |
| 19303 | { |
| 19304 | "epoch": 40.2, |
| 19305 | "learning_rate": 5.973760932944606e-05, |
| 19306 | "loss": 0.0173, |
| 19307 | "step": 27980 |
| 19308 | }, |
| 19309 | { |
| 19310 | "epoch": 40.22, |
| 19311 | "learning_rate": 5.9650145772594746e-05, |
| 19312 | "loss": 0.019, |
| 19313 | "step": 27990 |
| 19314 | }, |
| 19315 | { |
| 19316 | "epoch": 40.23, |
| 19317 | "learning_rate": 5.9562682215743434e-05, |
| 19318 | "loss": 0.0254, |
| 19319 | "step": 28000 |
| 19320 | }, |
| 19321 | { |
| 19322 | "epoch": 40.23, |
| 19323 | "eval_loss": 0.13149315118789673, |
| 19324 | "eval_runtime": 40.5502, |
| 19325 | "eval_samples_per_second": 11.27, |
| 19326 | "eval_steps_per_second": 1.43, |
| 19327 | "eval_wer": 0.12573407619334437, |
| 19328 | "step": 28000 |
| 19329 | }, |
| 19330 | { |
| 19331 | "epoch": 40.24, |
| 19332 | "learning_rate": 5.947521865889212e-05, |
| 19333 | "loss": 0.0205, |
| 19334 | "step": 28010 |
| 19335 | }, |
| 19336 | { |
| 19337 | "epoch": 40.26, |
| 19338 | "learning_rate": 5.938775510204081e-05, |
| 19339 | "loss": 0.0242, |
| 19340 | "step": 28020 |
| 19341 | }, |
| 19342 | { |
| 19343 | "epoch": 40.27, |
| 19344 | "learning_rate": 5.93002915451895e-05, |
| 19345 | "loss": 0.0186, |
| 19346 | "step": 28030 |
| 19347 | }, |
| 19348 | { |
| 19349 | "epoch": 40.29, |
| 19350 | "learning_rate": 5.921282798833819e-05, |
| 19351 | "loss": 0.0153, |
| 19352 | "step": 28040 |
| 19353 | }, |
| 19354 | { |
| 19355 | "epoch": 40.3, |
| 19356 | "learning_rate": 5.9125364431486874e-05, |
| 19357 | "loss": 0.0259, |
| 19358 | "step": 28050 |
| 19359 | }, |
| 19360 | { |
| 19361 | "epoch": 40.32, |
| 19362 | "learning_rate": 5.903790087463557e-05, |
| 19363 | "loss": 0.0264, |
| 19364 | "step": 28060 |
| 19365 | }, |
| 19366 | { |
| 19367 | "epoch": 40.33, |
| 19368 | "learning_rate": 5.895043731778425e-05, |
| 19369 | "loss": 0.0212, |
| 19370 | "step": 28070 |
| 19371 | }, |
| 19372 | { |
| 19373 | "epoch": 40.34, |
| 19374 | "learning_rate": 5.8862973760932944e-05, |
| 19375 | "loss": 0.0212, |
| 19376 | "step": 28080 |
| 19377 | }, |
| 19378 | { |
| 19379 | "epoch": 40.36, |
| 19380 | "learning_rate": 5.8775510204081625e-05, |
| 19381 | "loss": 0.0189, |
| 19382 | "step": 28090 |
| 19383 | }, |
| 19384 | { |
| 19385 | "epoch": 40.37, |
| 19386 | "learning_rate": 5.868804664723031e-05, |
| 19387 | "loss": 0.0266, |
| 19388 | "step": 28100 |
| 19389 | }, |
| 19390 | { |
| 19391 | "epoch": 40.37, |
| 19392 | "eval_loss": 0.132347971200943, |
| 19393 | "eval_runtime": 40.6163, |
| 19394 | "eval_samples_per_second": 11.252, |
| 19395 | "eval_steps_per_second": 1.428, |
| 19396 | "eval_wer": 0.12498117753350399, |
| 19397 | "step": 28100 |
| 19398 | }, |
| 19399 | { |
| 19400 | "epoch": 40.39, |
| 19401 | "learning_rate": 5.8600583090379e-05, |
| 19402 | "loss": 0.0224, |
| 19403 | "step": 28110 |
| 19404 | }, |
| 19405 | { |
| 19406 | "epoch": 40.4, |
| 19407 | "learning_rate": 5.851311953352769e-05, |
| 19408 | "loss": 0.0255, |
| 19409 | "step": 28120 |
| 19410 | }, |
| 19411 | { |
| 19412 | "epoch": 40.42, |
| 19413 | "learning_rate": 5.8425655976676384e-05, |
| 19414 | "loss": 0.027, |
| 19415 | "step": 28130 |
| 19416 | }, |
| 19417 | { |
| 19418 | "epoch": 40.43, |
| 19419 | "learning_rate": 5.8338192419825065e-05, |
| 19420 | "loss": 0.022, |
| 19421 | "step": 28140 |
| 19422 | }, |
| 19423 | { |
| 19424 | "epoch": 40.45, |
| 19425 | "learning_rate": 5.825072886297376e-05, |
| 19426 | "loss": 0.0227, |
| 19427 | "step": 28150 |
| 19428 | }, |
| 19429 | { |
| 19430 | "epoch": 40.46, |
| 19431 | "learning_rate": 5.816326530612244e-05, |
| 19432 | "loss": 0.0202, |
| 19433 | "step": 28160 |
| 19434 | }, |
| 19435 | { |
| 19436 | "epoch": 40.47, |
| 19437 | "learning_rate": 5.8075801749271135e-05, |
| 19438 | "loss": 0.0226, |
| 19439 | "step": 28170 |
| 19440 | }, |
| 19441 | { |
| 19442 | "epoch": 40.49, |
| 19443 | "learning_rate": 5.7988338192419816e-05, |
| 19444 | "loss": 0.0195, |
| 19445 | "step": 28180 |
| 19446 | }, |
| 19447 | { |
| 19448 | "epoch": 40.5, |
| 19449 | "learning_rate": 5.790087463556851e-05, |
| 19450 | "loss": 0.0167, |
| 19451 | "step": 28190 |
| 19452 | }, |
| 19453 | { |
| 19454 | "epoch": 40.52, |
| 19455 | "learning_rate": 5.781341107871719e-05, |
| 19456 | "loss": 0.0275, |
| 19457 | "step": 28200 |
| 19458 | }, |
| 19459 | { |
| 19460 | "epoch": 40.52, |
| 19461 | "eval_loss": 0.12815876305103302, |
| 19462 | "eval_runtime": 40.653, |
| 19463 | "eval_samples_per_second": 11.241, |
| 19464 | "eval_steps_per_second": 1.427, |
| 19465 | "eval_wer": 0.12422827887366361, |
| 19466 | "step": 28200 |
| 19467 | }, |
| 19468 | { |
| 19469 | "epoch": 40.53, |
| 19470 | "learning_rate": 5.772594752186589e-05, |
| 19471 | "loss": 0.0188, |
| 19472 | "step": 28210 |
| 19473 | }, |
| 19474 | { |
| 19475 | "epoch": 40.55, |
| 19476 | "learning_rate": 5.7638483965014575e-05, |
| 19477 | "loss": 0.0204, |
| 19478 | "step": 28220 |
| 19479 | }, |
| 19480 | { |
| 19481 | "epoch": 40.56, |
| 19482 | "learning_rate": 5.7551020408163256e-05, |
| 19483 | "loss": 0.0216, |
| 19484 | "step": 28230 |
| 19485 | }, |
| 19486 | { |
| 19487 | "epoch": 40.57, |
| 19488 | "learning_rate": 5.746355685131195e-05, |
| 19489 | "loss": 0.0156, |
| 19490 | "step": 28240 |
| 19491 | }, |
| 19492 | { |
| 19493 | "epoch": 40.59, |
| 19494 | "learning_rate": 5.737609329446063e-05, |
| 19495 | "loss": 0.0211, |
| 19496 | "step": 28250 |
| 19497 | }, |
| 19498 | { |
| 19499 | "epoch": 40.6, |
| 19500 | "learning_rate": 5.7288629737609326e-05, |
| 19501 | "loss": 0.0167, |
| 19502 | "step": 28260 |
| 19503 | }, |
| 19504 | { |
| 19505 | "epoch": 40.62, |
| 19506 | "learning_rate": 5.720116618075801e-05, |
| 19507 | "loss": 0.0221, |
| 19508 | "step": 28270 |
| 19509 | }, |
| 19510 | { |
| 19511 | "epoch": 40.63, |
| 19512 | "learning_rate": 5.71137026239067e-05, |
| 19513 | "loss": 0.0177, |
| 19514 | "step": 28280 |
| 19515 | }, |
| 19516 | { |
| 19517 | "epoch": 40.65, |
| 19518 | "learning_rate": 5.702623906705538e-05, |
| 19519 | "loss": 0.015, |
| 19520 | "step": 28290 |
| 19521 | }, |
| 19522 | { |
| 19523 | "epoch": 40.66, |
| 19524 | "learning_rate": 5.693877551020408e-05, |
| 19525 | "loss": 0.0266, |
| 19526 | "step": 28300 |
| 19527 | }, |
| 19528 | { |
| 19529 | "epoch": 40.66, |
| 19530 | "eval_loss": 0.1275702863931656, |
| 19531 | "eval_runtime": 40.6042, |
| 19532 | "eval_samples_per_second": 11.255, |
| 19533 | "eval_steps_per_second": 1.428, |
| 19534 | "eval_wer": 0.12543291672940823, |
| 19535 | "step": 28300 |
| 19536 | }, |
| 19537 | { |
| 19538 | "epoch": 40.68, |
| 19539 | "learning_rate": 5.6851311953352766e-05, |
| 19540 | "loss": 0.0201, |
| 19541 | "step": 28310 |
| 19542 | }, |
| 19543 | { |
| 19544 | "epoch": 40.69, |
| 19545 | "learning_rate": 5.6763848396501454e-05, |
| 19546 | "loss": 0.0284, |
| 19547 | "step": 28320 |
| 19548 | }, |
| 19549 | { |
| 19550 | "epoch": 40.7, |
| 19551 | "learning_rate": 5.667638483965014e-05, |
| 19552 | "loss": 0.0228, |
| 19553 | "step": 28330 |
| 19554 | }, |
| 19555 | { |
| 19556 | "epoch": 40.72, |
| 19557 | "learning_rate": 5.658892128279883e-05, |
| 19558 | "loss": 0.0192, |
| 19559 | "step": 28340 |
| 19560 | }, |
| 19561 | { |
| 19562 | "epoch": 40.73, |
| 19563 | "learning_rate": 5.650145772594752e-05, |
| 19564 | "loss": 0.0214, |
| 19565 | "step": 28350 |
| 19566 | }, |
| 19567 | { |
| 19568 | "epoch": 40.75, |
| 19569 | "learning_rate": 5.6413994169096205e-05, |
| 19570 | "loss": 0.0156, |
| 19571 | "step": 28360 |
| 19572 | }, |
| 19573 | { |
| 19574 | "epoch": 40.76, |
| 19575 | "learning_rate": 5.632653061224489e-05, |
| 19576 | "loss": 0.0229, |
| 19577 | "step": 28370 |
| 19578 | }, |
| 19579 | { |
| 19580 | "epoch": 40.78, |
| 19581 | "learning_rate": 5.6239067055393574e-05, |
| 19582 | "loss": 0.0287, |
| 19583 | "step": 28380 |
| 19584 | }, |
| 19585 | { |
| 19586 | "epoch": 40.79, |
| 19587 | "learning_rate": 5.615160349854227e-05, |
| 19588 | "loss": 0.0176, |
| 19589 | "step": 28390 |
| 19590 | }, |
| 19591 | { |
| 19592 | "epoch": 40.8, |
| 19593 | "learning_rate": 5.6064139941690964e-05, |
| 19594 | "loss": 0.0237, |
| 19595 | "step": 28400 |
| 19596 | }, |
| 19597 | { |
| 19598 | "epoch": 40.8, |
| 19599 | "eval_loss": 0.13049447536468506, |
| 19600 | "eval_runtime": 40.609, |
| 19601 | "eval_samples_per_second": 11.254, |
| 19602 | "eval_steps_per_second": 1.428, |
| 19603 | "eval_wer": 0.12543291672940823, |
| 19604 | "step": 28400 |
| 19605 | }, |
| 19606 | { |
| 19607 | "epoch": 40.82, |
| 19608 | "learning_rate": 5.5976676384839645e-05, |
| 19609 | "loss": 0.022, |
| 19610 | "step": 28410 |
| 19611 | }, |
| 19612 | { |
| 19613 | "epoch": 40.83, |
| 19614 | "learning_rate": 5.588921282798834e-05, |
| 19615 | "loss": 0.03, |
| 19616 | "step": 28420 |
| 19617 | }, |
| 19618 | { |
| 19619 | "epoch": 40.85, |
| 19620 | "learning_rate": 5.580174927113702e-05, |
| 19621 | "loss": 0.0224, |
| 19622 | "step": 28430 |
| 19623 | }, |
| 19624 | { |
| 19625 | "epoch": 40.86, |
| 19626 | "learning_rate": 5.571428571428571e-05, |
| 19627 | "loss": 0.0192, |
| 19628 | "step": 28440 |
| 19629 | }, |
| 19630 | { |
| 19631 | "epoch": 40.88, |
| 19632 | "learning_rate": 5.5626822157434396e-05, |
| 19633 | "loss": 0.0267, |
| 19634 | "step": 28450 |
| 19635 | }, |
| 19636 | { |
| 19637 | "epoch": 40.89, |
| 19638 | "learning_rate": 5.5539358600583084e-05, |
| 19639 | "loss": 0.0171, |
| 19640 | "step": 28460 |
| 19641 | }, |
| 19642 | { |
| 19643 | "epoch": 40.91, |
| 19644 | "learning_rate": 5.545189504373177e-05, |
| 19645 | "loss": 0.019, |
| 19646 | "step": 28470 |
| 19647 | }, |
| 19648 | { |
| 19649 | "epoch": 40.92, |
| 19650 | "learning_rate": 5.536443148688046e-05, |
| 19651 | "loss": 0.0261, |
| 19652 | "step": 28480 |
| 19653 | }, |
| 19654 | { |
| 19655 | "epoch": 40.93, |
| 19656 | "learning_rate": 5.5276967930029155e-05, |
| 19657 | "loss": 0.0168, |
| 19658 | "step": 28490 |
| 19659 | }, |
| 19660 | { |
| 19661 | "epoch": 40.95, |
| 19662 | "learning_rate": 5.5189504373177836e-05, |
| 19663 | "loss": 0.0229, |
| 19664 | "step": 28500 |
| 19665 | }, |
| 19666 | { |
| 19667 | "epoch": 40.95, |
| 19668 | "eval_loss": 0.1289079487323761, |
| 19669 | "eval_runtime": 40.595, |
| 19670 | "eval_samples_per_second": 11.258, |
| 19671 | "eval_steps_per_second": 1.429, |
| 19672 | "eval_wer": 0.12588465592531245, |
| 19673 | "step": 28500 |
| 19674 | }, |
| 19675 | { |
| 19676 | "epoch": 40.96, |
| 19677 | "learning_rate": 5.510204081632653e-05, |
| 19678 | "loss": 0.0198, |
| 19679 | "step": 28510 |
| 19680 | }, |
| 19681 | { |
| 19682 | "epoch": 40.98, |
| 19683 | "learning_rate": 5.501457725947521e-05, |
| 19684 | "loss": 0.0157, |
| 19685 | "step": 28520 |
| 19686 | }, |
| 19687 | { |
| 19688 | "epoch": 40.99, |
| 19689 | "learning_rate": 5.4927113702623906e-05, |
| 19690 | "loss": 0.022, |
| 19691 | "step": 28530 |
| 19692 | }, |
| 19693 | { |
| 19694 | "epoch": 41.01, |
| 19695 | "learning_rate": 5.483965014577259e-05, |
| 19696 | "loss": 0.0195, |
| 19697 | "step": 28540 |
| 19698 | }, |
| 19699 | { |
| 19700 | "epoch": 41.02, |
| 19701 | "learning_rate": 5.475218658892128e-05, |
| 19702 | "loss": 0.0206, |
| 19703 | "step": 28550 |
| 19704 | }, |
| 19705 | { |
| 19706 | "epoch": 41.03, |
| 19707 | "learning_rate": 5.466472303206996e-05, |
| 19708 | "loss": 0.0188, |
| 19709 | "step": 28560 |
| 19710 | }, |
| 19711 | { |
| 19712 | "epoch": 41.05, |
| 19713 | "learning_rate": 5.457725947521865e-05, |
| 19714 | "loss": 0.0226, |
| 19715 | "step": 28570 |
| 19716 | }, |
| 19717 | { |
| 19718 | "epoch": 41.06, |
| 19719 | "learning_rate": 5.4489795918367346e-05, |
| 19720 | "loss": 0.0208, |
| 19721 | "step": 28580 |
| 19722 | }, |
| 19723 | { |
| 19724 | "epoch": 41.08, |
| 19725 | "learning_rate": 5.440233236151603e-05, |
| 19726 | "loss": 0.0192, |
| 19727 | "step": 28590 |
| 19728 | }, |
| 19729 | { |
| 19730 | "epoch": 41.09, |
| 19731 | "learning_rate": 5.431486880466472e-05, |
| 19732 | "loss": 0.0194, |
| 19733 | "step": 28600 |
| 19734 | }, |
| 19735 | { |
| 19736 | "epoch": 41.09, |
| 19737 | "eval_loss": 0.12941156327724457, |
| 19738 | "eval_runtime": 40.6472, |
| 19739 | "eval_samples_per_second": 11.243, |
| 19740 | "eval_steps_per_second": 1.427, |
| 19741 | "eval_wer": 0.12377653967775937, |
| 19742 | "step": 28600 |
| 19743 | }, |
| 19744 | { |
| 19745 | "epoch": 41.11, |
| 19746 | "learning_rate": 5.42274052478134e-05, |
| 19747 | "loss": 0.0246, |
| 19748 | "step": 28610 |
| 19749 | }, |
| 19750 | { |
| 19751 | "epoch": 41.12, |
| 19752 | "learning_rate": 5.41399416909621e-05, |
| 19753 | "loss": 0.0232, |
| 19754 | "step": 28620 |
| 19755 | }, |
| 19756 | { |
| 19757 | "epoch": 41.14, |
| 19758 | "learning_rate": 5.405247813411078e-05, |
| 19759 | "loss": 0.0203, |
| 19760 | "step": 28630 |
| 19761 | }, |
| 19762 | { |
| 19763 | "epoch": 41.15, |
| 19764 | "learning_rate": 5.396501457725947e-05, |
| 19765 | "loss": 0.0203, |
| 19766 | "step": 28640 |
| 19767 | }, |
| 19768 | { |
| 19769 | "epoch": 41.16, |
| 19770 | "learning_rate": 5.3877551020408154e-05, |
| 19771 | "loss": 0.0254, |
| 19772 | "step": 28650 |
| 19773 | }, |
| 19774 | { |
| 19775 | "epoch": 41.18, |
| 19776 | "learning_rate": 5.379008746355685e-05, |
| 19777 | "loss": 0.0217, |
| 19778 | "step": 28660 |
| 19779 | }, |
| 19780 | { |
| 19781 | "epoch": 41.19, |
| 19782 | "learning_rate": 5.370262390670554e-05, |
| 19783 | "loss": 0.0227, |
| 19784 | "step": 28670 |
| 19785 | }, |
| 19786 | { |
| 19787 | "epoch": 41.21, |
| 19788 | "learning_rate": 5.3615160349854225e-05, |
| 19789 | "loss": 0.0204, |
| 19790 | "step": 28680 |
| 19791 | }, |
| 19792 | { |
| 19793 | "epoch": 41.22, |
| 19794 | "learning_rate": 5.352769679300291e-05, |
| 19795 | "loss": 0.0185, |
| 19796 | "step": 28690 |
| 19797 | }, |
| 19798 | { |
| 19799 | "epoch": 41.24, |
| 19800 | "learning_rate": 5.34402332361516e-05, |
| 19801 | "loss": 0.0222, |
| 19802 | "step": 28700 |
| 19803 | }, |
| 19804 | { |
| 19805 | "epoch": 41.24, |
| 19806 | "eval_loss": 0.12966987490653992, |
| 19807 | "eval_runtime": 41.1373, |
| 19808 | "eval_samples_per_second": 11.109, |
| 19809 | "eval_steps_per_second": 1.41, |
| 19810 | "eval_wer": 0.12046378557446168, |
| 19811 | "step": 28700 |
| 19812 | }, |
| 19813 | { |
| 19814 | "epoch": 41.25, |
| 19815 | "learning_rate": 5.335276967930029e-05, |
| 19816 | "loss": 0.0133, |
| 19817 | "step": 28710 |
| 19818 | }, |
| 19819 | { |
| 19820 | "epoch": 41.26, |
| 19821 | "learning_rate": 5.326530612244897e-05, |
| 19822 | "loss": 0.0226, |
| 19823 | "step": 28720 |
| 19824 | }, |
| 19825 | { |
| 19826 | "epoch": 41.28, |
| 19827 | "learning_rate": 5.3177842565597664e-05, |
| 19828 | "loss": 0.0225, |
| 19829 | "step": 28730 |
| 19830 | }, |
| 19831 | { |
| 19832 | "epoch": 41.29, |
| 19833 | "learning_rate": 5.3090379008746345e-05, |
| 19834 | "loss": 0.0152, |
| 19835 | "step": 28740 |
| 19836 | }, |
| 19837 | { |
| 19838 | "epoch": 41.31, |
| 19839 | "learning_rate": 5.300291545189504e-05, |
| 19840 | "loss": 0.0199, |
| 19841 | "step": 28750 |
| 19842 | }, |
| 19843 | { |
| 19844 | "epoch": 41.32, |
| 19845 | "learning_rate": 5.291545189504373e-05, |
| 19846 | "loss": 0.0216, |
| 19847 | "step": 28760 |
| 19848 | }, |
| 19849 | { |
| 19850 | "epoch": 41.34, |
| 19851 | "learning_rate": 5.2827988338192416e-05, |
| 19852 | "loss": 0.0309, |
| 19853 | "step": 28770 |
| 19854 | }, |
| 19855 | { |
| 19856 | "epoch": 41.35, |
| 19857 | "learning_rate": 5.2740524781341104e-05, |
| 19858 | "loss": 0.0205, |
| 19859 | "step": 28780 |
| 19860 | }, |
| 19861 | { |
| 19862 | "epoch": 41.36, |
| 19863 | "learning_rate": 5.265306122448979e-05, |
| 19864 | "loss": 0.0252, |
| 19865 | "step": 28790 |
| 19866 | }, |
| 19867 | { |
| 19868 | "epoch": 41.38, |
| 19869 | "learning_rate": 5.256559766763848e-05, |
| 19870 | "loss": 0.024, |
| 19871 | "step": 28800 |
| 19872 | }, |
| 19873 | { |
| 19874 | "epoch": 41.38, |
| 19875 | "eval_loss": 0.12944242358207703, |
| 19876 | "eval_runtime": 40.5436, |
| 19877 | "eval_samples_per_second": 11.272, |
| 19878 | "eval_steps_per_second": 1.431, |
| 19879 | "eval_wer": 0.11910856798674899, |
| 19880 | "step": 28800 |
| 19881 | }, |
| 19882 | { |
| 19883 | "epoch": 41.39, |
| 19884 | "learning_rate": 5.247813411078717e-05, |
| 19885 | "loss": 0.022, |
| 19886 | "step": 28810 |
| 19887 | }, |
| 19888 | { |
| 19889 | "epoch": 41.41, |
| 19890 | "learning_rate": 5.2390670553935855e-05, |
| 19891 | "loss": 0.0296, |
| 19892 | "step": 28820 |
| 19893 | }, |
| 19894 | { |
| 19895 | "epoch": 41.42, |
| 19896 | "learning_rate": 5.230320699708454e-05, |
| 19897 | "loss": 0.015, |
| 19898 | "step": 28830 |
| 19899 | }, |
| 19900 | { |
| 19901 | "epoch": 41.44, |
| 19902 | "learning_rate": 5.221574344023323e-05, |
| 19903 | "loss": 0.0226, |
| 19904 | "step": 28840 |
| 19905 | }, |
| 19906 | { |
| 19907 | "epoch": 41.45, |
| 19908 | "learning_rate": 5.2128279883381926e-05, |
| 19909 | "loss": 0.0188, |
| 19910 | "step": 28850 |
| 19911 | }, |
| 19912 | { |
| 19913 | "epoch": 41.47, |
| 19914 | "learning_rate": 5.204081632653061e-05, |
| 19915 | "loss": 0.0173, |
| 19916 | "step": 28860 |
| 19917 | }, |
| 19918 | { |
| 19919 | "epoch": 41.48, |
| 19920 | "learning_rate": 5.19533527696793e-05, |
| 19921 | "loss": 0.0203, |
| 19922 | "step": 28870 |
| 19923 | }, |
| 19924 | { |
| 19925 | "epoch": 41.49, |
| 19926 | "learning_rate": 5.186588921282798e-05, |
| 19927 | "loss": 0.0209, |
| 19928 | "step": 28880 |
| 19929 | }, |
| 19930 | { |
| 19931 | "epoch": 41.51, |
| 19932 | "learning_rate": 5.177842565597668e-05, |
| 19933 | "loss": 0.0245, |
| 19934 | "step": 28890 |
| 19935 | }, |
| 19936 | { |
| 19937 | "epoch": 41.52, |
| 19938 | "learning_rate": 5.169096209912536e-05, |
| 19939 | "loss": 0.0185, |
| 19940 | "step": 28900 |
| 19941 | }, |
| 19942 | { |
| 19943 | "epoch": 41.52, |
| 19944 | "eval_loss": 0.13065434992313385, |
| 19945 | "eval_runtime": 40.6007, |
| 19946 | "eval_samples_per_second": 11.256, |
| 19947 | "eval_steps_per_second": 1.429, |
| 19948 | "eval_wer": 0.12121668423430207, |
| 19949 | "step": 28900 |
| 19950 | }, |
| 19951 | { |
| 19952 | "epoch": 41.54, |
| 19953 | "learning_rate": 5.1603498542274046e-05, |
| 19954 | "loss": 0.0172, |
| 19955 | "step": 28910 |
| 19956 | }, |
| 19957 | { |
| 19958 | "epoch": 41.55, |
| 19959 | "learning_rate": 5.1516034985422734e-05, |
| 19960 | "loss": 0.0213, |
| 19961 | "step": 28920 |
| 19962 | }, |
| 19963 | { |
| 19964 | "epoch": 41.57, |
| 19965 | "learning_rate": 5.142857142857142e-05, |
| 19966 | "loss": 0.0175, |
| 19967 | "step": 28930 |
| 19968 | }, |
| 19969 | { |
| 19970 | "epoch": 41.58, |
| 19971 | "learning_rate": 5.134110787172011e-05, |
| 19972 | "loss": 0.0166, |
| 19973 | "step": 28940 |
| 19974 | }, |
| 19975 | { |
| 19976 | "epoch": 41.59, |
| 19977 | "learning_rate": 5.12536443148688e-05, |
| 19978 | "loss": 0.0285, |
| 19979 | "step": 28950 |
| 19980 | }, |
| 19981 | { |
| 19982 | "epoch": 41.61, |
| 19983 | "learning_rate": 5.117492711370262e-05, |
| 19984 | "loss": 0.0188, |
| 19985 | "step": 28960 |
| 19986 | }, |
| 19987 | { |
| 19988 | "epoch": 41.62, |
| 19989 | "learning_rate": 5.1087463556851305e-05, |
| 19990 | "loss": 0.0234, |
| 19991 | "step": 28970 |
| 19992 | }, |
| 19993 | { |
| 19994 | "epoch": 41.64, |
| 19995 | "learning_rate": 5.1e-05, |
| 19996 | "loss": 0.0206, |
| 19997 | "step": 28980 |
| 19998 | }, |
| 19999 | { |
| 20000 | "epoch": 41.65, |
| 20001 | "learning_rate": 5.091253644314868e-05, |
| 20002 | "loss": 0.0241, |
| 20003 | "step": 28990 |
| 20004 | }, |
| 20005 | { |
| 20006 | "epoch": 41.67, |
| 20007 | "learning_rate": 5.0825072886297375e-05, |
| 20008 | "loss": 0.0199, |
| 20009 | "step": 29000 |
| 20010 | }, |
| 20011 | { |
| 20012 | "epoch": 41.67, |
| 20013 | "eval_loss": 0.1251639872789383, |
| 20014 | "eval_runtime": 40.5816, |
| 20015 | "eval_samples_per_second": 11.261, |
| 20016 | "eval_steps_per_second": 1.429, |
| 20017 | "eval_wer": 0.12181900316217437, |
| 20018 | "step": 29000 |
| 20019 | }, |
| 20020 | { |
| 20021 | "epoch": 41.68, |
| 20022 | "learning_rate": 5.0737609329446057e-05, |
| 20023 | "loss": 0.0231, |
| 20024 | "step": 29010 |
| 20025 | }, |
| 20026 | { |
| 20027 | "epoch": 41.7, |
| 20028 | "learning_rate": 5.065014577259475e-05, |
| 20029 | "loss": 0.0183, |
| 20030 | "step": 29020 |
| 20031 | }, |
| 20032 | { |
| 20033 | "epoch": 41.71, |
| 20034 | "learning_rate": 5.056268221574343e-05, |
| 20035 | "loss": 0.0179, |
| 20036 | "step": 29030 |
| 20037 | }, |
| 20038 | { |
| 20039 | "epoch": 41.72, |
| 20040 | "learning_rate": 5.047521865889213e-05, |
| 20041 | "loss": 0.0214, |
| 20042 | "step": 29040 |
| 20043 | }, |
| 20044 | { |
| 20045 | "epoch": 41.74, |
| 20046 | "learning_rate": 5.038775510204081e-05, |
| 20047 | "loss": 0.0223, |
| 20048 | "step": 29050 |
| 20049 | }, |
| 20050 | { |
| 20051 | "epoch": 41.75, |
| 20052 | "learning_rate": 5.03002915451895e-05, |
| 20053 | "loss": 0.0151, |
| 20054 | "step": 29060 |
| 20055 | }, |
| 20056 | { |
| 20057 | "epoch": 41.77, |
| 20058 | "learning_rate": 5.021282798833819e-05, |
| 20059 | "loss": 0.0207, |
| 20060 | "step": 29070 |
| 20061 | }, |
| 20062 | { |
| 20063 | "epoch": 41.78, |
| 20064 | "learning_rate": 5.012536443148688e-05, |
| 20065 | "loss": 0.0217, |
| 20066 | "step": 29080 |
| 20067 | }, |
| 20068 | { |
| 20069 | "epoch": 41.8, |
| 20070 | "learning_rate": 5.0037900874635566e-05, |
| 20071 | "loss": 0.0185, |
| 20072 | "step": 29090 |
| 20073 | }, |
| 20074 | { |
| 20075 | "epoch": 41.81, |
| 20076 | "learning_rate": 4.995043731778425e-05, |
| 20077 | "loss": 0.0311, |
| 20078 | "step": 29100 |
| 20079 | }, |
| 20080 | { |
| 20081 | "epoch": 41.81, |
| 20082 | "eval_loss": 0.12811152637004852, |
| 20083 | "eval_runtime": 40.4122, |
| 20084 | "eval_samples_per_second": 11.308, |
| 20085 | "eval_steps_per_second": 1.435, |
| 20086 | "eval_wer": 0.1236259599457913, |
| 20087 | "step": 29100 |
| 20088 | }, |
| 20089 | { |
| 20090 | "epoch": 41.82, |
| 20091 | "learning_rate": 4.986297376093294e-05, |
| 20092 | "loss": 0.0205, |
| 20093 | "step": 29110 |
| 20094 | }, |
| 20095 | { |
| 20096 | "epoch": 41.84, |
| 20097 | "learning_rate": 4.977551020408162e-05, |
| 20098 | "loss": 0.0294, |
| 20099 | "step": 29120 |
| 20100 | }, |
| 20101 | { |
| 20102 | "epoch": 41.85, |
| 20103 | "learning_rate": 4.968804664723032e-05, |
| 20104 | "loss": 0.0138, |
| 20105 | "step": 29130 |
| 20106 | }, |
| 20107 | { |
| 20108 | "epoch": 41.87, |
| 20109 | "learning_rate": 4.9600583090379e-05, |
| 20110 | "loss": 0.0263, |
| 20111 | "step": 29140 |
| 20112 | }, |
| 20113 | { |
| 20114 | "epoch": 41.88, |
| 20115 | "learning_rate": 4.9513119533527694e-05, |
| 20116 | "loss": 0.0214, |
| 20117 | "step": 29150 |
| 20118 | }, |
| 20119 | { |
| 20120 | "epoch": 41.9, |
| 20121 | "learning_rate": 4.942565597667638e-05, |
| 20122 | "loss": 0.0162, |
| 20123 | "step": 29160 |
| 20124 | }, |
| 20125 | { |
| 20126 | "epoch": 41.91, |
| 20127 | "learning_rate": 4.933819241982507e-05, |
| 20128 | "loss": 0.0251, |
| 20129 | "step": 29170 |
| 20130 | }, |
| 20131 | { |
| 20132 | "epoch": 41.93, |
| 20133 | "learning_rate": 4.925072886297376e-05, |
| 20134 | "loss": 0.0186, |
| 20135 | "step": 29180 |
| 20136 | }, |
| 20137 | { |
| 20138 | "epoch": 41.94, |
| 20139 | "learning_rate": 4.9163265306122445e-05, |
| 20140 | "loss": 0.0242, |
| 20141 | "step": 29190 |
| 20142 | }, |
| 20143 | { |
| 20144 | "epoch": 41.95, |
| 20145 | "learning_rate": 4.907580174927113e-05, |
| 20146 | "loss": 0.0235, |
| 20147 | "step": 29200 |
| 20148 | }, |
| 20149 | { |
| 20150 | "epoch": 41.95, |
| 20151 | "eval_loss": 0.12631256878376007, |
| 20152 | "eval_runtime": 41.101, |
| 20153 | "eval_samples_per_second": 11.119, |
| 20154 | "eval_steps_per_second": 1.411, |
| 20155 | "eval_wer": 0.1267881343171209, |
| 20156 | "step": 29200 |
| 20157 | }, |
| 20158 | { |
| 20159 | "epoch": 41.97, |
| 20160 | "learning_rate": 4.898833819241982e-05, |
| 20161 | "loss": 0.0178, |
| 20162 | "step": 29210 |
| 20163 | }, |
| 20164 | { |
| 20165 | "epoch": 41.98, |
| 20166 | "learning_rate": 4.890087463556851e-05, |
| 20167 | "loss": 0.0259, |
| 20168 | "step": 29220 |
| 20169 | }, |
| 20170 | { |
| 20171 | "epoch": 42.0, |
| 20172 | "learning_rate": 4.881341107871719e-05, |
| 20173 | "loss": 0.019, |
| 20174 | "step": 29230 |
| 20175 | }, |
| 20176 | { |
| 20177 | "epoch": 42.01, |
| 20178 | "learning_rate": 4.8725947521865885e-05, |
| 20179 | "loss": 0.0196, |
| 20180 | "step": 29240 |
| 20181 | }, |
| 20182 | { |
| 20183 | "epoch": 42.03, |
| 20184 | "learning_rate": 4.863848396501458e-05, |
| 20185 | "loss": 0.0212, |
| 20186 | "step": 29250 |
| 20187 | }, |
| 20188 | { |
| 20189 | "epoch": 42.04, |
| 20190 | "learning_rate": 4.855102040816326e-05, |
| 20191 | "loss": 0.0214, |
| 20192 | "step": 29260 |
| 20193 | }, |
| 20194 | { |
| 20195 | "epoch": 42.05, |
| 20196 | "learning_rate": 4.8463556851311955e-05, |
| 20197 | "loss": 0.0219, |
| 20198 | "step": 29270 |
| 20199 | }, |
| 20200 | { |
| 20201 | "epoch": 42.07, |
| 20202 | "learning_rate": 4.8376093294460636e-05, |
| 20203 | "loss": 0.027, |
| 20204 | "step": 29280 |
| 20205 | }, |
| 20206 | { |
| 20207 | "epoch": 42.08, |
| 20208 | "learning_rate": 4.8288629737609324e-05, |
| 20209 | "loss": 0.0186, |
| 20210 | "step": 29290 |
| 20211 | }, |
| 20212 | { |
| 20213 | "epoch": 42.1, |
| 20214 | "learning_rate": 4.820116618075801e-05, |
| 20215 | "loss": 0.0175, |
| 20216 | "step": 29300 |
| 20217 | }, |
| 20218 | { |
| 20219 | "epoch": 42.1, |
| 20220 | "eval_loss": 0.12914027273654938, |
| 20221 | "eval_runtime": 40.8425, |
| 20222 | "eval_samples_per_second": 11.189, |
| 20223 | "eval_steps_per_second": 1.42, |
| 20224 | "eval_wer": 0.1255834964613763, |
| 20225 | "step": 29300 |
| 20226 | }, |
| 20227 | { |
| 20228 | "epoch": 42.11, |
| 20229 | "learning_rate": 4.81137026239067e-05, |
| 20230 | "loss": 0.0227, |
| 20231 | "step": 29310 |
| 20232 | }, |
| 20233 | { |
| 20234 | "epoch": 42.13, |
| 20235 | "learning_rate": 4.802623906705539e-05, |
| 20236 | "loss": 0.0246, |
| 20237 | "step": 29320 |
| 20238 | }, |
| 20239 | { |
| 20240 | "epoch": 42.14, |
| 20241 | "learning_rate": 4.7938775510204076e-05, |
| 20242 | "loss": 0.0188, |
| 20243 | "step": 29330 |
| 20244 | }, |
| 20245 | { |
| 20246 | "epoch": 42.16, |
| 20247 | "learning_rate": 4.785131195335277e-05, |
| 20248 | "loss": 0.0217, |
| 20249 | "step": 29340 |
| 20250 | }, |
| 20251 | { |
| 20252 | "epoch": 42.17, |
| 20253 | "learning_rate": 4.776384839650145e-05, |
| 20254 | "loss": 0.0219, |
| 20255 | "step": 29350 |
| 20256 | }, |
| 20257 | { |
| 20258 | "epoch": 42.18, |
| 20259 | "learning_rate": 4.7676384839650146e-05, |
| 20260 | "loss": 0.019, |
| 20261 | "step": 29360 |
| 20262 | }, |
| 20263 | { |
| 20264 | "epoch": 42.2, |
| 20265 | "learning_rate": 4.758892128279883e-05, |
| 20266 | "loss": 0.0241, |
| 20267 | "step": 29370 |
| 20268 | }, |
| 20269 | { |
| 20270 | "epoch": 42.21, |
| 20271 | "learning_rate": 4.750145772594752e-05, |
| 20272 | "loss": 0.016, |
| 20273 | "step": 29380 |
| 20274 | }, |
| 20275 | { |
| 20276 | "epoch": 42.23, |
| 20277 | "learning_rate": 4.74139941690962e-05, |
| 20278 | "loss": 0.0277, |
| 20279 | "step": 29390 |
| 20280 | }, |
| 20281 | { |
| 20282 | "epoch": 42.24, |
| 20283 | "learning_rate": 4.73265306122449e-05, |
| 20284 | "loss": 0.0188, |
| 20285 | "step": 29400 |
| 20286 | }, |
| 20287 | { |
| 20288 | "epoch": 42.24, |
| 20289 | "eval_loss": 0.12900404632091522, |
| 20290 | "eval_runtime": 40.6753, |
| 20291 | "eval_samples_per_second": 11.235, |
| 20292 | "eval_steps_per_second": 1.426, |
| 20293 | "eval_wer": 0.12573407619334437, |
| 20294 | "step": 29400 |
| 20295 | }, |
| 20296 | { |
| 20297 | "epoch": 42.26, |
| 20298 | "learning_rate": 4.723906705539358e-05, |
| 20299 | "loss": 0.0176, |
| 20300 | "step": 29410 |
| 20301 | }, |
| 20302 | { |
| 20303 | "epoch": 42.27, |
| 20304 | "learning_rate": 4.715160349854227e-05, |
| 20305 | "loss": 0.021, |
| 20306 | "step": 29420 |
| 20307 | }, |
| 20308 | { |
| 20309 | "epoch": 42.28, |
| 20310 | "learning_rate": 4.706413994169096e-05, |
| 20311 | "loss": 0.0168, |
| 20312 | "step": 29430 |
| 20313 | }, |
| 20314 | { |
| 20315 | "epoch": 42.3, |
| 20316 | "learning_rate": 4.697667638483964e-05, |
| 20317 | "loss": 0.0258, |
| 20318 | "step": 29440 |
| 20319 | }, |
| 20320 | { |
| 20321 | "epoch": 42.31, |
| 20322 | "learning_rate": 4.688921282798834e-05, |
| 20323 | "loss": 0.0234, |
| 20324 | "step": 29450 |
| 20325 | }, |
| 20326 | { |
| 20327 | "epoch": 42.33, |
| 20328 | "learning_rate": 4.680174927113702e-05, |
| 20329 | "loss": 0.0248, |
| 20330 | "step": 29460 |
| 20331 | }, |
| 20332 | { |
| 20333 | "epoch": 42.34, |
| 20334 | "learning_rate": 4.671428571428571e-05, |
| 20335 | "loss": 0.0213, |
| 20336 | "step": 29470 |
| 20337 | }, |
| 20338 | { |
| 20339 | "epoch": 42.36, |
| 20340 | "learning_rate": 4.6626822157434394e-05, |
| 20341 | "loss": 0.0246, |
| 20342 | "step": 29480 |
| 20343 | }, |
| 20344 | { |
| 20345 | "epoch": 42.37, |
| 20346 | "learning_rate": 4.653935860058309e-05, |
| 20347 | "loss": 0.0244, |
| 20348 | "step": 29490 |
| 20349 | }, |
| 20350 | { |
| 20351 | "epoch": 42.39, |
| 20352 | "learning_rate": 4.645189504373177e-05, |
| 20353 | "loss": 0.0288, |
| 20354 | "step": 29500 |
| 20355 | }, |
| 20356 | { |
| 20357 | "epoch": 42.39, |
| 20358 | "eval_loss": 0.12424959987401962, |
| 20359 | "eval_runtime": 40.6911, |
| 20360 | "eval_samples_per_second": 11.231, |
| 20361 | "eval_steps_per_second": 1.425, |
| 20362 | "eval_wer": 0.1261858153892486, |
| 20363 | "step": 29500 |
| 20364 | }, |
| 20365 | { |
| 20366 | "epoch": 42.4, |
| 20367 | "learning_rate": 4.6364431486880465e-05, |
| 20368 | "loss": 0.0208, |
| 20369 | "step": 29510 |
| 20370 | }, |
| 20371 | { |
| 20372 | "epoch": 42.41, |
| 20373 | "learning_rate": 4.627696793002915e-05, |
| 20374 | "loss": 0.0203, |
| 20375 | "step": 29520 |
| 20376 | }, |
| 20377 | { |
| 20378 | "epoch": 42.43, |
| 20379 | "learning_rate": 4.618950437317784e-05, |
| 20380 | "loss": 0.0182, |
| 20381 | "step": 29530 |
| 20382 | }, |
| 20383 | { |
| 20384 | "epoch": 42.44, |
| 20385 | "learning_rate": 4.610204081632653e-05, |
| 20386 | "loss": 0.0262, |
| 20387 | "step": 29540 |
| 20388 | }, |
| 20389 | { |
| 20390 | "epoch": 42.46, |
| 20391 | "learning_rate": 4.6014577259475216e-05, |
| 20392 | "loss": 0.0173, |
| 20393 | "step": 29550 |
| 20394 | }, |
| 20395 | { |
| 20396 | "epoch": 42.47, |
| 20397 | "learning_rate": 4.5927113702623904e-05, |
| 20398 | "loss": 0.0202, |
| 20399 | "step": 29560 |
| 20400 | }, |
| 20401 | { |
| 20402 | "epoch": 42.49, |
| 20403 | "learning_rate": 4.5839650145772585e-05, |
| 20404 | "loss": 0.0233, |
| 20405 | "step": 29570 |
| 20406 | }, |
| 20407 | { |
| 20408 | "epoch": 42.5, |
| 20409 | "learning_rate": 4.575218658892128e-05, |
| 20410 | "loss": 0.0164, |
| 20411 | "step": 29580 |
| 20412 | }, |
| 20413 | { |
| 20414 | "epoch": 42.51, |
| 20415 | "learning_rate": 4.566472303206996e-05, |
| 20416 | "loss": 0.0245, |
| 20417 | "step": 29590 |
| 20418 | }, |
| 20419 | { |
| 20420 | "epoch": 42.53, |
| 20421 | "learning_rate": 4.5577259475218656e-05, |
| 20422 | "loss": 0.0223, |
| 20423 | "step": 29600 |
| 20424 | }, |
| 20425 | { |
| 20426 | "epoch": 42.53, |
| 20427 | "eval_loss": 0.12688687443733215, |
| 20428 | "eval_runtime": 40.9929, |
| 20429 | "eval_samples_per_second": 11.148, |
| 20430 | "eval_steps_per_second": 1.415, |
| 20431 | "eval_wer": 0.12663755458515283, |
| 20432 | "step": 29600 |
| 20433 | }, |
| 20434 | { |
| 20435 | "epoch": 42.54, |
| 20436 | "learning_rate": 4.548979591836734e-05, |
| 20437 | "loss": 0.0254, |
| 20438 | "step": 29610 |
| 20439 | }, |
| 20440 | { |
| 20441 | "epoch": 42.56, |
| 20442 | "learning_rate": 4.540233236151603e-05, |
| 20443 | "loss": 0.0263, |
| 20444 | "step": 29620 |
| 20445 | }, |
| 20446 | { |
| 20447 | "epoch": 42.57, |
| 20448 | "learning_rate": 4.531486880466472e-05, |
| 20449 | "loss": 0.024, |
| 20450 | "step": 29630 |
| 20451 | }, |
| 20452 | { |
| 20453 | "epoch": 42.59, |
| 20454 | "learning_rate": 4.522740524781341e-05, |
| 20455 | "loss": 0.0236, |
| 20456 | "step": 29640 |
| 20457 | }, |
| 20458 | { |
| 20459 | "epoch": 42.6, |
| 20460 | "learning_rate": 4.5139941690962095e-05, |
| 20461 | "loss": 0.0223, |
| 20462 | "step": 29650 |
| 20463 | }, |
| 20464 | { |
| 20465 | "epoch": 42.61, |
| 20466 | "learning_rate": 4.505247813411078e-05, |
| 20467 | "loss": 0.0233, |
| 20468 | "step": 29660 |
| 20469 | }, |
| 20470 | { |
| 20471 | "epoch": 42.63, |
| 20472 | "learning_rate": 4.496501457725947e-05, |
| 20473 | "loss": 0.027, |
| 20474 | "step": 29670 |
| 20475 | }, |
| 20476 | { |
| 20477 | "epoch": 42.64, |
| 20478 | "learning_rate": 4.487755102040816e-05, |
| 20479 | "loss": 0.0146, |
| 20480 | "step": 29680 |
| 20481 | }, |
| 20482 | { |
| 20483 | "epoch": 42.66, |
| 20484 | "learning_rate": 4.479008746355685e-05, |
| 20485 | "loss": 0.0316, |
| 20486 | "step": 29690 |
| 20487 | }, |
| 20488 | { |
| 20489 | "epoch": 42.67, |
| 20490 | "learning_rate": 4.470262390670553e-05, |
| 20491 | "loss": 0.0125, |
| 20492 | "step": 29700 |
| 20493 | }, |
| 20494 | { |
| 20495 | "epoch": 42.67, |
| 20496 | "eval_loss": 0.13046014308929443, |
| 20497 | "eval_runtime": 40.7681, |
| 20498 | "eval_samples_per_second": 11.21, |
| 20499 | "eval_steps_per_second": 1.423, |
| 20500 | "eval_wer": 0.12302364101791899, |
| 20501 | "step": 29700 |
| 20502 | }, |
| 20503 | { |
| 20504 | "epoch": 42.69, |
| 20505 | "learning_rate": 4.461516034985422e-05, |
| 20506 | "loss": 0.0232, |
| 20507 | "step": 29710 |
| 20508 | }, |
| 20509 | { |
| 20510 | "epoch": 42.7, |
| 20511 | "learning_rate": 4.452769679300292e-05, |
| 20512 | "loss": 0.0207, |
| 20513 | "step": 29720 |
| 20514 | }, |
| 20515 | { |
| 20516 | "epoch": 42.72, |
| 20517 | "learning_rate": 4.44402332361516e-05, |
| 20518 | "loss": 0.0174, |
| 20519 | "step": 29730 |
| 20520 | }, |
| 20521 | { |
| 20522 | "epoch": 42.73, |
| 20523 | "learning_rate": 4.435276967930029e-05, |
| 20524 | "loss": 0.0201, |
| 20525 | "step": 29740 |
| 20526 | }, |
| 20527 | { |
| 20528 | "epoch": 42.74, |
| 20529 | "learning_rate": 4.4265306122448974e-05, |
| 20530 | "loss": 0.022, |
| 20531 | "step": 29750 |
| 20532 | }, |
| 20533 | { |
| 20534 | "epoch": 42.76, |
| 20535 | "learning_rate": 4.417784256559766e-05, |
| 20536 | "loss": 0.0154, |
| 20537 | "step": 29760 |
| 20538 | }, |
| 20539 | { |
| 20540 | "epoch": 42.77, |
| 20541 | "learning_rate": 4.409037900874635e-05, |
| 20542 | "loss": 0.0194, |
| 20543 | "step": 29770 |
| 20544 | }, |
| 20545 | { |
| 20546 | "epoch": 42.79, |
| 20547 | "learning_rate": 4.400291545189504e-05, |
| 20548 | "loss": 0.0198, |
| 20549 | "step": 29780 |
| 20550 | }, |
| 20551 | { |
| 20552 | "epoch": 42.8, |
| 20553 | "learning_rate": 4.3915451895043726e-05, |
| 20554 | "loss": 0.0199, |
| 20555 | "step": 29790 |
| 20556 | }, |
| 20557 | { |
| 20558 | "epoch": 42.82, |
| 20559 | "learning_rate": 4.3827988338192414e-05, |
| 20560 | "loss": 0.0182, |
| 20561 | "step": 29800 |
| 20562 | }, |
| 20563 | { |
| 20564 | "epoch": 42.82, |
| 20565 | "eval_loss": 0.131119966506958, |
| 20566 | "eval_runtime": 41.0012, |
| 20567 | "eval_samples_per_second": 11.146, |
| 20568 | "eval_steps_per_second": 1.415, |
| 20569 | "eval_wer": 0.1222707423580786, |
| 20570 | "step": 29800 |
| 20571 | }, |
| 20572 | { |
| 20573 | "epoch": 42.83, |
| 20574 | "learning_rate": 4.374052478134111e-05, |
| 20575 | "loss": 0.0175, |
| 20576 | "step": 29810 |
| 20577 | }, |
| 20578 | { |
| 20579 | "epoch": 42.84, |
| 20580 | "learning_rate": 4.365306122448979e-05, |
| 20581 | "loss": 0.0252, |
| 20582 | "step": 29820 |
| 20583 | }, |
| 20584 | { |
| 20585 | "epoch": 42.86, |
| 20586 | "learning_rate": 4.3565597667638484e-05, |
| 20587 | "loss": 0.0176, |
| 20588 | "step": 29830 |
| 20589 | }, |
| 20590 | { |
| 20591 | "epoch": 42.87, |
| 20592 | "learning_rate": 4.3478134110787165e-05, |
| 20593 | "loss": 0.0397, |
| 20594 | "step": 29840 |
| 20595 | }, |
| 20596 | { |
| 20597 | "epoch": 42.89, |
| 20598 | "learning_rate": 4.339067055393586e-05, |
| 20599 | "loss": 0.0147, |
| 20600 | "step": 29850 |
| 20601 | }, |
| 20602 | { |
| 20603 | "epoch": 42.9, |
| 20604 | "learning_rate": 4.330320699708454e-05, |
| 20605 | "loss": 0.0154, |
| 20606 | "step": 29860 |
| 20607 | }, |
| 20608 | { |
| 20609 | "epoch": 42.92, |
| 20610 | "learning_rate": 4.3215743440233236e-05, |
| 20611 | "loss": 0.0181, |
| 20612 | "step": 29870 |
| 20613 | }, |
| 20614 | { |
| 20615 | "epoch": 42.93, |
| 20616 | "learning_rate": 4.312827988338192e-05, |
| 20617 | "loss": 0.0121, |
| 20618 | "step": 29880 |
| 20619 | }, |
| 20620 | { |
| 20621 | "epoch": 42.95, |
| 20622 | "learning_rate": 4.3040816326530605e-05, |
| 20623 | "loss": 0.0298, |
| 20624 | "step": 29890 |
| 20625 | }, |
| 20626 | { |
| 20627 | "epoch": 42.96, |
| 20628 | "learning_rate": 4.29533527696793e-05, |
| 20629 | "loss": 0.0194, |
| 20630 | "step": 29900 |
| 20631 | }, |
| 20632 | { |
| 20633 | "epoch": 42.96, |
| 20634 | "eval_loss": 0.131606325507164, |
| 20635 | "eval_runtime": 40.5304, |
| 20636 | "eval_samples_per_second": 11.275, |
| 20637 | "eval_steps_per_second": 1.431, |
| 20638 | "eval_wer": 0.12708929378105707, |
| 20639 | "step": 29900 |
| 20640 | }, |
| 20641 | { |
| 20642 | "epoch": 42.97, |
| 20643 | "learning_rate": 4.286588921282798e-05, |
| 20644 | "loss": 0.019, |
| 20645 | "step": 29910 |
| 20646 | }, |
| 20647 | { |
| 20648 | "epoch": 42.99, |
| 20649 | "learning_rate": 4.2778425655976675e-05, |
| 20650 | "loss": 0.0251, |
| 20651 | "step": 29920 |
| 20652 | }, |
| 20653 | { |
| 20654 | "epoch": 43.0, |
| 20655 | "learning_rate": 4.2690962099125357e-05, |
| 20656 | "loss": 0.0166, |
| 20657 | "step": 29930 |
| 20658 | }, |
| 20659 | { |
| 20660 | "epoch": 43.02, |
| 20661 | "learning_rate": 4.260349854227405e-05, |
| 20662 | "loss": 0.0201, |
| 20663 | "step": 29940 |
| 20664 | }, |
| 20665 | { |
| 20666 | "epoch": 43.03, |
| 20667 | "learning_rate": 4.251603498542273e-05, |
| 20668 | "loss": 0.0187, |
| 20669 | "step": 29950 |
| 20670 | }, |
| 20671 | { |
| 20672 | "epoch": 43.05, |
| 20673 | "learning_rate": 4.242857142857143e-05, |
| 20674 | "loss": 0.0256, |
| 20675 | "step": 29960 |
| 20676 | }, |
| 20677 | { |
| 20678 | "epoch": 43.06, |
| 20679 | "learning_rate": 4.234110787172011e-05, |
| 20680 | "loss": 0.0249, |
| 20681 | "step": 29970 |
| 20682 | }, |
| 20683 | { |
| 20684 | "epoch": 43.07, |
| 20685 | "learning_rate": 4.22536443148688e-05, |
| 20686 | "loss": 0.0209, |
| 20687 | "step": 29980 |
| 20688 | }, |
| 20689 | { |
| 20690 | "epoch": 43.09, |
| 20691 | "learning_rate": 4.216618075801749e-05, |
| 20692 | "loss": 0.0222, |
| 20693 | "step": 29990 |
| 20694 | }, |
| 20695 | { |
| 20696 | "epoch": 43.1, |
| 20697 | "learning_rate": 4.208746355685131e-05, |
| 20698 | "loss": 0.0148, |
| 20699 | "step": 30000 |
| 20700 | }, |
| 20701 | { |
| 20702 | "epoch": 43.1, |
| 20703 | "eval_loss": 0.1303335726261139, |
| 20704 | "eval_runtime": 40.5862, |
| 20705 | "eval_samples_per_second": 11.26, |
| 20706 | "eval_steps_per_second": 1.429, |
| 20707 | "eval_wer": 0.12708929378105707, |
| 20708 | "step": 30000 |
| 20709 | }, |
| 20710 | { |
| 20711 | "epoch": 43.12, |
| 20712 | "learning_rate": 4.2e-05, |
| 20713 | "loss": 0.0199, |
| 20714 | "step": 30010 |
| 20715 | }, |
| 20716 | { |
| 20717 | "epoch": 43.13, |
| 20718 | "learning_rate": 4.1912536443148686e-05, |
| 20719 | "loss": 0.0153, |
| 20720 | "step": 30020 |
| 20721 | }, |
| 20722 | { |
| 20723 | "epoch": 43.15, |
| 20724 | "learning_rate": 4.1825072886297373e-05, |
| 20725 | "loss": 0.0187, |
| 20726 | "step": 30030 |
| 20727 | }, |
| 20728 | { |
| 20729 | "epoch": 43.16, |
| 20730 | "learning_rate": 4.173760932944606e-05, |
| 20731 | "loss": 0.0203, |
| 20732 | "step": 30040 |
| 20733 | }, |
| 20734 | { |
| 20735 | "epoch": 43.18, |
| 20736 | "learning_rate": 4.165014577259475e-05, |
| 20737 | "loss": 0.0207, |
| 20738 | "step": 30050 |
| 20739 | }, |
| 20740 | { |
| 20741 | "epoch": 43.19, |
| 20742 | "learning_rate": 4.156268221574344e-05, |
| 20743 | "loss": 0.0232, |
| 20744 | "step": 30060 |
| 20745 | }, |
| 20746 | { |
| 20747 | "epoch": 43.2, |
| 20748 | "learning_rate": 4.1475218658892125e-05, |
| 20749 | "loss": 0.0217, |
| 20750 | "step": 30070 |
| 20751 | }, |
| 20752 | { |
| 20753 | "epoch": 43.22, |
| 20754 | "learning_rate": 4.1387755102040806e-05, |
| 20755 | "loss": 0.0182, |
| 20756 | "step": 30080 |
| 20757 | }, |
| 20758 | { |
| 20759 | "epoch": 43.23, |
| 20760 | "learning_rate": 4.13002915451895e-05, |
| 20761 | "loss": 0.0257, |
| 20762 | "step": 30090 |
| 20763 | }, |
| 20764 | { |
| 20765 | "epoch": 43.25, |
| 20766 | "learning_rate": 4.1212827988338196e-05, |
| 20767 | "loss": 0.0125, |
| 20768 | "step": 30100 |
| 20769 | }, |
| 20770 | { |
| 20771 | "epoch": 43.25, |
| 20772 | "eval_loss": 0.12872837483882904, |
| 20773 | "eval_runtime": 40.7552, |
| 20774 | "eval_samples_per_second": 11.213, |
| 20775 | "eval_steps_per_second": 1.423, |
| 20776 | "eval_wer": 0.12468001806956784, |
| 20777 | "step": 30100 |
| 20778 | }, |
| 20779 | { |
| 20780 | "epoch": 43.26, |
| 20781 | "learning_rate": 4.112536443148688e-05, |
| 20782 | "loss": 0.0231, |
| 20783 | "step": 30110 |
| 20784 | }, |
| 20785 | { |
| 20786 | "epoch": 43.28, |
| 20787 | "learning_rate": 4.103790087463557e-05, |
| 20788 | "loss": 0.0132, |
| 20789 | "step": 30120 |
| 20790 | }, |
| 20791 | { |
| 20792 | "epoch": 43.29, |
| 20793 | "learning_rate": 4.095043731778425e-05, |
| 20794 | "loss": 0.0208, |
| 20795 | "step": 30130 |
| 20796 | }, |
| 20797 | { |
| 20798 | "epoch": 43.3, |
| 20799 | "learning_rate": 4.086297376093294e-05, |
| 20800 | "loss": 0.0193, |
| 20801 | "step": 30140 |
| 20802 | }, |
| 20803 | { |
| 20804 | "epoch": 43.32, |
| 20805 | "learning_rate": 4.077551020408163e-05, |
| 20806 | "loss": 0.0142, |
| 20807 | "step": 30150 |
| 20808 | }, |
| 20809 | { |
| 20810 | "epoch": 43.33, |
| 20811 | "learning_rate": 4.0688046647230316e-05, |
| 20812 | "loss": 0.0343, |
| 20813 | "step": 30160 |
| 20814 | }, |
| 20815 | { |
| 20816 | "epoch": 43.35, |
| 20817 | "learning_rate": 4.0600583090379004e-05, |
| 20818 | "loss": 0.0209, |
| 20819 | "step": 30170 |
| 20820 | }, |
| 20821 | { |
| 20822 | "epoch": 43.36, |
| 20823 | "learning_rate": 4.051311953352769e-05, |
| 20824 | "loss": 0.0164, |
| 20825 | "step": 30180 |
| 20826 | }, |
| 20827 | { |
| 20828 | "epoch": 43.38, |
| 20829 | "learning_rate": 4.0425655976676387e-05, |
| 20830 | "loss": 0.026, |
| 20831 | "step": 30190 |
| 20832 | }, |
| 20833 | { |
| 20834 | "epoch": 43.39, |
| 20835 | "learning_rate": 4.033819241982507e-05, |
| 20836 | "loss": 0.0197, |
| 20837 | "step": 30200 |
| 20838 | }, |
| 20839 | { |
| 20840 | "epoch": 43.39, |
| 20841 | "eval_loss": 0.12666457891464233, |
| 20842 | "eval_runtime": 40.7476, |
| 20843 | "eval_samples_per_second": 11.215, |
| 20844 | "eval_steps_per_second": 1.423, |
| 20845 | "eval_wer": 0.12287306128595091, |
| 20846 | "step": 30200 |
| 20847 | }, |
| 20848 | { |
| 20849 | "epoch": 43.41, |
| 20850 | "learning_rate": 4.025072886297376e-05, |
| 20851 | "loss": 0.0222, |
| 20852 | "step": 30210 |
| 20853 | }, |
| 20854 | { |
| 20855 | "epoch": 43.42, |
| 20856 | "learning_rate": 4.0163265306122443e-05, |
| 20857 | "loss": 0.0146, |
| 20858 | "step": 30220 |
| 20859 | }, |
| 20860 | { |
| 20861 | "epoch": 43.43, |
| 20862 | "learning_rate": 4.007580174927114e-05, |
| 20863 | "loss": 0.0144, |
| 20864 | "step": 30230 |
| 20865 | }, |
| 20866 | { |
| 20867 | "epoch": 43.45, |
| 20868 | "learning_rate": 3.998833819241982e-05, |
| 20869 | "loss": 0.0253, |
| 20870 | "step": 30240 |
| 20871 | }, |
| 20872 | { |
| 20873 | "epoch": 43.46, |
| 20874 | "learning_rate": 3.9900874635568514e-05, |
| 20875 | "loss": 0.0207, |
| 20876 | "step": 30250 |
| 20877 | }, |
| 20878 | { |
| 20879 | "epoch": 43.48, |
| 20880 | "learning_rate": 3.9813411078717195e-05, |
| 20881 | "loss": 0.0235, |
| 20882 | "step": 30260 |
| 20883 | }, |
| 20884 | { |
| 20885 | "epoch": 43.49, |
| 20886 | "learning_rate": 3.972594752186588e-05, |
| 20887 | "loss": 0.0147, |
| 20888 | "step": 30270 |
| 20889 | }, |
| 20890 | { |
| 20891 | "epoch": 43.51, |
| 20892 | "learning_rate": 3.963848396501457e-05, |
| 20893 | "loss": 0.0172, |
| 20894 | "step": 30280 |
| 20895 | }, |
| 20896 | { |
| 20897 | "epoch": 43.52, |
| 20898 | "learning_rate": 3.955102040816326e-05, |
| 20899 | "loss": 0.0248, |
| 20900 | "step": 30290 |
| 20901 | }, |
| 20902 | { |
| 20903 | "epoch": 43.53, |
| 20904 | "learning_rate": 3.9463556851311953e-05, |
| 20905 | "loss": 0.0149, |
| 20906 | "step": 30300 |
| 20907 | }, |
| 20908 | { |
| 20909 | "epoch": 43.53, |
| 20910 | "eval_loss": 0.12862493097782135, |
| 20911 | "eval_runtime": 40.7412, |
| 20912 | "eval_samples_per_second": 11.217, |
| 20913 | "eval_steps_per_second": 1.424, |
| 20914 | "eval_wer": 0.12212016262611053, |
| 20915 | "step": 30300 |
| 20916 | }, |
| 20917 | { |
| 20918 | "epoch": 43.55, |
| 20919 | "learning_rate": 3.9376093294460635e-05, |
| 20920 | "loss": 0.0221, |
| 20921 | "step": 30310 |
| 20922 | }, |
| 20923 | { |
| 20924 | "epoch": 43.56, |
| 20925 | "learning_rate": 3.928862973760933e-05, |
| 20926 | "loss": 0.0152, |
| 20927 | "step": 30320 |
| 20928 | }, |
| 20929 | { |
| 20930 | "epoch": 43.58, |
| 20931 | "learning_rate": 3.920116618075801e-05, |
| 20932 | "loss": 0.0186, |
| 20933 | "step": 30330 |
| 20934 | }, |
| 20935 | { |
| 20936 | "epoch": 43.59, |
| 20937 | "learning_rate": 3.9113702623906705e-05, |
| 20938 | "loss": 0.0161, |
| 20939 | "step": 30340 |
| 20940 | }, |
| 20941 | { |
| 20942 | "epoch": 43.61, |
| 20943 | "learning_rate": 3.9026239067055386e-05, |
| 20944 | "loss": 0.0157, |
| 20945 | "step": 30350 |
| 20946 | }, |
| 20947 | { |
| 20948 | "epoch": 43.62, |
| 20949 | "learning_rate": 3.893877551020408e-05, |
| 20950 | "loss": 0.0231, |
| 20951 | "step": 30360 |
| 20952 | }, |
| 20953 | { |
| 20954 | "epoch": 43.64, |
| 20955 | "learning_rate": 3.885131195335276e-05, |
| 20956 | "loss": 0.0174, |
| 20957 | "step": 30370 |
| 20958 | }, |
| 20959 | { |
| 20960 | "epoch": 43.65, |
| 20961 | "learning_rate": 3.876384839650146e-05, |
| 20962 | "loss": 0.0181, |
| 20963 | "step": 30380 |
| 20964 | }, |
| 20965 | { |
| 20966 | "epoch": 43.66, |
| 20967 | "learning_rate": 3.8676384839650145e-05, |
| 20968 | "loss": 0.021, |
| 20969 | "step": 30390 |
| 20970 | }, |
| 20971 | { |
| 20972 | "epoch": 43.68, |
| 20973 | "learning_rate": 3.858892128279883e-05, |
| 20974 | "loss": 0.0268, |
| 20975 | "step": 30400 |
| 20976 | }, |
| 20977 | { |
| 20978 | "epoch": 43.68, |
| 20979 | "eval_loss": 0.1292026787996292, |
| 20980 | "eval_runtime": 40.6933, |
| 20981 | "eval_samples_per_second": 11.23, |
| 20982 | "eval_steps_per_second": 1.425, |
| 20983 | "eval_wer": 0.12272248155398284, |
| 20984 | "step": 30400 |
| 20985 | }, |
| 20986 | { |
| 20987 | "epoch": 43.69, |
| 20988 | "learning_rate": 3.850145772594752e-05, |
| 20989 | "loss": 0.0213, |
| 20990 | "step": 30410 |
| 20991 | }, |
| 20992 | { |
| 20993 | "epoch": 43.71, |
| 20994 | "learning_rate": 3.84139941690962e-05, |
| 20995 | "loss": 0.0202, |
| 20996 | "step": 30420 |
| 20997 | }, |
| 20998 | { |
| 20999 | "epoch": 43.72, |
| 21000 | "learning_rate": 3.8326530612244896e-05, |
| 21001 | "loss": 0.0204, |
| 21002 | "step": 30430 |
| 21003 | }, |
| 21004 | { |
| 21005 | "epoch": 43.74, |
| 21006 | "learning_rate": 3.823906705539358e-05, |
| 21007 | "loss": 0.0215, |
| 21008 | "step": 30440 |
| 21009 | }, |
| 21010 | { |
| 21011 | "epoch": 43.75, |
| 21012 | "learning_rate": 3.815160349854227e-05, |
| 21013 | "loss": 0.0113, |
| 21014 | "step": 30450 |
| 21015 | }, |
| 21016 | { |
| 21017 | "epoch": 43.76, |
| 21018 | "learning_rate": 3.806413994169095e-05, |
| 21019 | "loss": 0.0184, |
| 21020 | "step": 30460 |
| 21021 | }, |
| 21022 | { |
| 21023 | "epoch": 43.78, |
| 21024 | "learning_rate": 3.797667638483965e-05, |
| 21025 | "loss": 0.0226, |
| 21026 | "step": 30470 |
| 21027 | }, |
| 21028 | { |
| 21029 | "epoch": 43.79, |
| 21030 | "learning_rate": 3.7889212827988336e-05, |
| 21031 | "loss": 0.0262, |
| 21032 | "step": 30480 |
| 21033 | }, |
| 21034 | { |
| 21035 | "epoch": 43.81, |
| 21036 | "learning_rate": 3.7801749271137023e-05, |
| 21037 | "loss": 0.018, |
| 21038 | "step": 30490 |
| 21039 | }, |
| 21040 | { |
| 21041 | "epoch": 43.82, |
| 21042 | "learning_rate": 3.771428571428571e-05, |
| 21043 | "loss": 0.0173, |
| 21044 | "step": 30500 |
| 21045 | }, |
| 21046 | { |
| 21047 | "epoch": 43.82, |
| 21048 | "eval_loss": 0.1283373236656189, |
| 21049 | "eval_runtime": 40.7197, |
| 21050 | "eval_samples_per_second": 11.223, |
| 21051 | "eval_steps_per_second": 1.424, |
| 21052 | "eval_wer": 0.1216684234302063, |
| 21053 | "step": 30500 |
| 21054 | }, |
| 21055 | { |
| 21056 | "epoch": 43.84, |
| 21057 | "learning_rate": 3.76268221574344e-05, |
| 21058 | "loss": 0.0201, |
| 21059 | "step": 30510 |
| 21060 | }, |
| 21061 | { |
| 21062 | "epoch": 43.85, |
| 21063 | "learning_rate": 3.753935860058309e-05, |
| 21064 | "loss": 0.0161, |
| 21065 | "step": 30520 |
| 21066 | }, |
| 21067 | { |
| 21068 | "epoch": 43.86, |
| 21069 | "learning_rate": 3.7451895043731775e-05, |
| 21070 | "loss": 0.0172, |
| 21071 | "step": 30530 |
| 21072 | }, |
| 21073 | { |
| 21074 | "epoch": 43.88, |
| 21075 | "learning_rate": 3.736443148688046e-05, |
| 21076 | "loss": 0.0206, |
| 21077 | "step": 30540 |
| 21078 | }, |
| 21079 | { |
| 21080 | "epoch": 43.89, |
| 21081 | "learning_rate": 3.727696793002915e-05, |
| 21082 | "loss": 0.0183, |
| 21083 | "step": 30550 |
| 21084 | }, |
| 21085 | { |
| 21086 | "epoch": 43.91, |
| 21087 | "learning_rate": 3.718950437317784e-05, |
| 21088 | "loss": 0.0198, |
| 21089 | "step": 30560 |
| 21090 | }, |
| 21091 | { |
| 21092 | "epoch": 43.92, |
| 21093 | "learning_rate": 3.710204081632653e-05, |
| 21094 | "loss": 0.0176, |
| 21095 | "step": 30570 |
| 21096 | }, |
| 21097 | { |
| 21098 | "epoch": 43.94, |
| 21099 | "learning_rate": 3.7014577259475215e-05, |
| 21100 | "loss": 0.0174, |
| 21101 | "step": 30580 |
| 21102 | }, |
| 21103 | { |
| 21104 | "epoch": 43.95, |
| 21105 | "learning_rate": 3.69271137026239e-05, |
| 21106 | "loss": 0.0219, |
| 21107 | "step": 30590 |
| 21108 | }, |
| 21109 | { |
| 21110 | "epoch": 43.97, |
| 21111 | "learning_rate": 3.683965014577259e-05, |
| 21112 | "loss": 0.0171, |
| 21113 | "step": 30600 |
| 21114 | }, |
| 21115 | { |
| 21116 | "epoch": 43.97, |
| 21117 | "eval_loss": 0.12676407396793365, |
| 21118 | "eval_runtime": 40.7159, |
| 21119 | "eval_samples_per_second": 11.224, |
| 21120 | "eval_steps_per_second": 1.425, |
| 21121 | "eval_wer": 0.11986146664658937, |
| 21122 | "step": 30600 |
| 21123 | }, |
| 21124 | { |
| 21125 | "epoch": 43.98, |
| 21126 | "learning_rate": 3.675218658892128e-05, |
| 21127 | "loss": 0.0201, |
| 21128 | "step": 30610 |
| 21129 | }, |
| 21130 | { |
| 21131 | "epoch": 43.99, |
| 21132 | "learning_rate": 3.6664723032069966e-05, |
| 21133 | "loss": 0.0183, |
| 21134 | "step": 30620 |
| 21135 | }, |
| 21136 | { |
| 21137 | "epoch": 44.01, |
| 21138 | "learning_rate": 3.6577259475218654e-05, |
| 21139 | "loss": 0.0218, |
| 21140 | "step": 30630 |
| 21141 | }, |
| 21142 | { |
| 21143 | "epoch": 44.02, |
| 21144 | "learning_rate": 3.648979591836734e-05, |
| 21145 | "loss": 0.0207, |
| 21146 | "step": 30640 |
| 21147 | }, |
| 21148 | { |
| 21149 | "epoch": 44.04, |
| 21150 | "learning_rate": 3.640233236151603e-05, |
| 21151 | "loss": 0.0164, |
| 21152 | "step": 30650 |
| 21153 | }, |
| 21154 | { |
| 21155 | "epoch": 44.05, |
| 21156 | "learning_rate": 3.631486880466472e-05, |
| 21157 | "loss": 0.0188, |
| 21158 | "step": 30660 |
| 21159 | }, |
| 21160 | { |
| 21161 | "epoch": 44.07, |
| 21162 | "learning_rate": 3.6227405247813406e-05, |
| 21163 | "loss": 0.022, |
| 21164 | "step": 30670 |
| 21165 | }, |
| 21166 | { |
| 21167 | "epoch": 44.08, |
| 21168 | "learning_rate": 3.6139941690962094e-05, |
| 21169 | "loss": 0.0192, |
| 21170 | "step": 30680 |
| 21171 | }, |
| 21172 | { |
| 21173 | "epoch": 44.09, |
| 21174 | "learning_rate": 3.605247813411078e-05, |
| 21175 | "loss": 0.0197, |
| 21176 | "step": 30690 |
| 21177 | }, |
| 21178 | { |
| 21179 | "epoch": 44.11, |
| 21180 | "learning_rate": 3.5965014577259476e-05, |
| 21181 | "loss": 0.0184, |
| 21182 | "step": 30700 |
| 21183 | }, |
| 21184 | { |
| 21185 | "epoch": 44.11, |
| 21186 | "eval_loss": 0.12772968411445618, |
| 21187 | "eval_runtime": 40.7769, |
| 21188 | "eval_samples_per_second": 11.207, |
| 21189 | "eval_steps_per_second": 1.422, |
| 21190 | "eval_wer": 0.12121668423430207, |
| 21191 | "step": 30700 |
| 21192 | }, |
| 21193 | { |
| 21194 | "epoch": 44.12, |
| 21195 | "learning_rate": 3.5877551020408164e-05, |
| 21196 | "loss": 0.0306, |
| 21197 | "step": 30710 |
| 21198 | }, |
| 21199 | { |
| 21200 | "epoch": 44.14, |
| 21201 | "learning_rate": 3.579008746355685e-05, |
| 21202 | "loss": 0.0197, |
| 21203 | "step": 30720 |
| 21204 | }, |
| 21205 | { |
| 21206 | "epoch": 44.15, |
| 21207 | "learning_rate": 3.570262390670554e-05, |
| 21208 | "loss": 0.0297, |
| 21209 | "step": 30730 |
| 21210 | }, |
| 21211 | { |
| 21212 | "epoch": 44.17, |
| 21213 | "learning_rate": 3.561516034985423e-05, |
| 21214 | "loss": 0.0166, |
| 21215 | "step": 30740 |
| 21216 | }, |
| 21217 | { |
| 21218 | "epoch": 44.18, |
| 21219 | "learning_rate": 3.552769679300291e-05, |
| 21220 | "loss": 0.0183, |
| 21221 | "step": 30750 |
| 21222 | }, |
| 21223 | { |
| 21224 | "epoch": 44.2, |
| 21225 | "learning_rate": 3.54402332361516e-05, |
| 21226 | "loss": 0.0208, |
| 21227 | "step": 30760 |
| 21228 | }, |
| 21229 | { |
| 21230 | "epoch": 44.21, |
| 21231 | "learning_rate": 3.5352769679300285e-05, |
| 21232 | "loss": 0.0184, |
| 21233 | "step": 30770 |
| 21234 | }, |
| 21235 | { |
| 21236 | "epoch": 44.22, |
| 21237 | "learning_rate": 3.526530612244897e-05, |
| 21238 | "loss": 0.0181, |
| 21239 | "step": 30780 |
| 21240 | }, |
| 21241 | { |
| 21242 | "epoch": 44.24, |
| 21243 | "learning_rate": 3.517784256559767e-05, |
| 21244 | "loss": 0.017, |
| 21245 | "step": 30790 |
| 21246 | }, |
| 21247 | { |
| 21248 | "epoch": 44.25, |
| 21249 | "learning_rate": 3.5090379008746355e-05, |
| 21250 | "loss": 0.0176, |
| 21251 | "step": 30800 |
| 21252 | }, |
| 21253 | { |
| 21254 | "epoch": 44.25, |
| 21255 | "eval_loss": 0.1296500861644745, |
| 21256 | "eval_runtime": 40.688, |
| 21257 | "eval_samples_per_second": 11.232, |
| 21258 | "eval_steps_per_second": 1.425, |
| 21259 | "eval_wer": 0.1203132058424936, |
| 21260 | "step": 30800 |
| 21261 | }, |
| 21262 | { |
| 21263 | "epoch": 44.27, |
| 21264 | "learning_rate": 3.500291545189504e-05, |
| 21265 | "loss": 0.0158, |
| 21266 | "step": 30810 |
| 21267 | }, |
| 21268 | { |
| 21269 | "epoch": 44.28, |
| 21270 | "learning_rate": 3.491545189504373e-05, |
| 21271 | "loss": 0.0138, |
| 21272 | "step": 30820 |
| 21273 | }, |
| 21274 | { |
| 21275 | "epoch": 44.3, |
| 21276 | "learning_rate": 3.482798833819242e-05, |
| 21277 | "loss": 0.0197, |
| 21278 | "step": 30830 |
| 21279 | }, |
| 21280 | { |
| 21281 | "epoch": 44.31, |
| 21282 | "learning_rate": 3.474052478134111e-05, |
| 21283 | "loss": 0.0173, |
| 21284 | "step": 30840 |
| 21285 | }, |
| 21286 | { |
| 21287 | "epoch": 44.32, |
| 21288 | "learning_rate": 3.4653061224489795e-05, |
| 21289 | "loss": 0.0138, |
| 21290 | "step": 30850 |
| 21291 | }, |
| 21292 | { |
| 21293 | "epoch": 44.34, |
| 21294 | "learning_rate": 3.456559766763848e-05, |
| 21295 | "loss": 0.0177, |
| 21296 | "step": 30860 |
| 21297 | }, |
| 21298 | { |
| 21299 | "epoch": 44.35, |
| 21300 | "learning_rate": 3.447813411078717e-05, |
| 21301 | "loss": 0.0153, |
| 21302 | "step": 30870 |
| 21303 | }, |
| 21304 | { |
| 21305 | "epoch": 44.37, |
| 21306 | "learning_rate": 3.439067055393586e-05, |
| 21307 | "loss": 0.0169, |
| 21308 | "step": 30880 |
| 21309 | }, |
| 21310 | { |
| 21311 | "epoch": 44.38, |
| 21312 | "learning_rate": 3.4303206997084546e-05, |
| 21313 | "loss": 0.0168, |
| 21314 | "step": 30890 |
| 21315 | }, |
| 21316 | { |
| 21317 | "epoch": 44.4, |
| 21318 | "learning_rate": 3.4215743440233234e-05, |
| 21319 | "loss": 0.0172, |
| 21320 | "step": 30900 |
| 21321 | }, |
| 21322 | { |
| 21323 | "epoch": 44.4, |
| 21324 | "eval_loss": 0.12854306399822235, |
| 21325 | "eval_runtime": 41.8837, |
| 21326 | "eval_samples_per_second": 10.911, |
| 21327 | "eval_steps_per_second": 1.385, |
| 21328 | "eval_wer": 0.12106610450233399, |
| 21329 | "step": 30900 |
| 21330 | }, |
| 21331 | { |
| 21332 | "epoch": 44.41, |
| 21333 | "learning_rate": 3.412827988338192e-05, |
| 21334 | "loss": 0.0215, |
| 21335 | "step": 30910 |
| 21336 | }, |
| 21337 | { |
| 21338 | "epoch": 44.43, |
| 21339 | "learning_rate": 3.404081632653061e-05, |
| 21340 | "loss": 0.0137, |
| 21341 | "step": 30920 |
| 21342 | }, |
| 21343 | { |
| 21344 | "epoch": 44.44, |
| 21345 | "learning_rate": 3.39533527696793e-05, |
| 21346 | "loss": 0.0201, |
| 21347 | "step": 30930 |
| 21348 | }, |
| 21349 | { |
| 21350 | "epoch": 44.45, |
| 21351 | "learning_rate": 3.3865889212827986e-05, |
| 21352 | "loss": 0.0171, |
| 21353 | "step": 30940 |
| 21354 | }, |
| 21355 | { |
| 21356 | "epoch": 44.47, |
| 21357 | "learning_rate": 3.3778425655976673e-05, |
| 21358 | "loss": 0.0164, |
| 21359 | "step": 30950 |
| 21360 | }, |
| 21361 | { |
| 21362 | "epoch": 44.48, |
| 21363 | "learning_rate": 3.369096209912536e-05, |
| 21364 | "loss": 0.0221, |
| 21365 | "step": 30960 |
| 21366 | }, |
| 21367 | { |
| 21368 | "epoch": 44.5, |
| 21369 | "learning_rate": 3.360349854227405e-05, |
| 21370 | "loss": 0.013, |
| 21371 | "step": 30970 |
| 21372 | }, |
| 21373 | { |
| 21374 | "epoch": 44.51, |
| 21375 | "learning_rate": 3.351603498542274e-05, |
| 21376 | "loss": 0.0203, |
| 21377 | "step": 30980 |
| 21378 | }, |
| 21379 | { |
| 21380 | "epoch": 44.53, |
| 21381 | "learning_rate": 3.3428571428571425e-05, |
| 21382 | "loss": 0.0196, |
| 21383 | "step": 30990 |
| 21384 | }, |
| 21385 | { |
| 21386 | "epoch": 44.54, |
| 21387 | "learning_rate": 3.334110787172011e-05, |
| 21388 | "loss": 0.0155, |
| 21389 | "step": 31000 |
| 21390 | }, |
| 21391 | { |
| 21392 | "epoch": 44.54, |
| 21393 | "eval_loss": 0.12705247104167938, |
| 21394 | "eval_runtime": 40.7901, |
| 21395 | "eval_samples_per_second": 11.204, |
| 21396 | "eval_steps_per_second": 1.422, |
| 21397 | "eval_wer": 0.12212016262611053, |
| 21398 | "step": 31000 |
| 21399 | }, |
| 21400 | { |
| 21401 | "epoch": 44.55, |
| 21402 | "learning_rate": 3.32536443148688e-05, |
| 21403 | "loss": 0.0255, |
| 21404 | "step": 31010 |
| 21405 | }, |
| 21406 | { |
| 21407 | "epoch": 44.57, |
| 21408 | "learning_rate": 3.316618075801749e-05, |
| 21409 | "loss": 0.0139, |
| 21410 | "step": 31020 |
| 21411 | }, |
| 21412 | { |
| 21413 | "epoch": 44.58, |
| 21414 | "learning_rate": 3.307871720116618e-05, |
| 21415 | "loss": 0.0225, |
| 21416 | "step": 31030 |
| 21417 | }, |
| 21418 | { |
| 21419 | "epoch": 44.6, |
| 21420 | "learning_rate": 3.2991253644314865e-05, |
| 21421 | "loss": 0.0192, |
| 21422 | "step": 31040 |
| 21423 | }, |
| 21424 | { |
| 21425 | "epoch": 44.61, |
| 21426 | "learning_rate": 3.290379008746355e-05, |
| 21427 | "loss": 0.0167, |
| 21428 | "step": 31050 |
| 21429 | }, |
| 21430 | { |
| 21431 | "epoch": 44.63, |
| 21432 | "learning_rate": 3.281632653061224e-05, |
| 21433 | "loss": 0.0159, |
| 21434 | "step": 31060 |
| 21435 | }, |
| 21436 | { |
| 21437 | "epoch": 44.64, |
| 21438 | "learning_rate": 3.2728862973760935e-05, |
| 21439 | "loss": 0.017, |
| 21440 | "step": 31070 |
| 21441 | }, |
| 21442 | { |
| 21443 | "epoch": 44.66, |
| 21444 | "learning_rate": 3.2641399416909616e-05, |
| 21445 | "loss": 0.0287, |
| 21446 | "step": 31080 |
| 21447 | }, |
| 21448 | { |
| 21449 | "epoch": 44.67, |
| 21450 | "learning_rate": 3.2553935860058304e-05, |
| 21451 | "loss": 0.0176, |
| 21452 | "step": 31090 |
| 21453 | }, |
| 21454 | { |
| 21455 | "epoch": 44.68, |
| 21456 | "learning_rate": 3.246647230320699e-05, |
| 21457 | "loss": 0.0195, |
| 21458 | "step": 31100 |
| 21459 | }, |
| 21460 | { |
| 21461 | "epoch": 44.68, |
| 21462 | "eval_loss": 0.12698258459568024, |
| 21463 | "eval_runtime": 40.4576, |
| 21464 | "eval_samples_per_second": 11.296, |
| 21465 | "eval_steps_per_second": 1.434, |
| 21466 | "eval_wer": 0.12076494503839783, |
| 21467 | "step": 31100 |
| 21468 | }, |
| 21469 | { |
| 21470 | "epoch": 44.7, |
| 21471 | "learning_rate": 3.237900874635568e-05, |
| 21472 | "loss": 0.0197, |
| 21473 | "step": 31110 |
| 21474 | }, |
| 21475 | { |
| 21476 | "epoch": 44.71, |
| 21477 | "learning_rate": 3.229154518950437e-05, |
| 21478 | "loss": 0.0102, |
| 21479 | "step": 31120 |
| 21480 | }, |
| 21481 | { |
| 21482 | "epoch": 44.73, |
| 21483 | "learning_rate": 3.2204081632653056e-05, |
| 21484 | "loss": 0.0215, |
| 21485 | "step": 31130 |
| 21486 | }, |
| 21487 | { |
| 21488 | "epoch": 44.74, |
| 21489 | "learning_rate": 3.2116618075801744e-05, |
| 21490 | "loss": 0.0217, |
| 21491 | "step": 31140 |
| 21492 | }, |
| 21493 | { |
| 21494 | "epoch": 44.76, |
| 21495 | "learning_rate": 3.202915451895043e-05, |
| 21496 | "loss": 0.0167, |
| 21497 | "step": 31150 |
| 21498 | }, |
| 21499 | { |
| 21500 | "epoch": 44.77, |
| 21501 | "learning_rate": 3.1941690962099126e-05, |
| 21502 | "loss": 0.0266, |
| 21503 | "step": 31160 |
| 21504 | }, |
| 21505 | { |
| 21506 | "epoch": 44.78, |
| 21507 | "learning_rate": 3.1854227405247814e-05, |
| 21508 | "loss": 0.0148, |
| 21509 | "step": 31170 |
| 21510 | }, |
| 21511 | { |
| 21512 | "epoch": 44.8, |
| 21513 | "learning_rate": 3.17667638483965e-05, |
| 21514 | "loss": 0.0191, |
| 21515 | "step": 31180 |
| 21516 | }, |
| 21517 | { |
| 21518 | "epoch": 44.81, |
| 21519 | "learning_rate": 3.167930029154519e-05, |
| 21520 | "loss": 0.019, |
| 21521 | "step": 31190 |
| 21522 | }, |
| 21523 | { |
| 21524 | "epoch": 44.83, |
| 21525 | "learning_rate": 3.159183673469388e-05, |
| 21526 | "loss": 0.0179, |
| 21527 | "step": 31200 |
| 21528 | }, |
| 21529 | { |
| 21530 | "epoch": 44.83, |
| 21531 | "eval_loss": 0.12674599885940552, |
| 21532 | "eval_runtime": 40.9642, |
| 21533 | "eval_samples_per_second": 11.156, |
| 21534 | "eval_steps_per_second": 1.416, |
| 21535 | "eval_wer": 0.11925914771871705, |
| 21536 | "step": 31200 |
| 21537 | }, |
| 21538 | { |
| 21539 | "epoch": 44.84, |
| 21540 | "learning_rate": 3.1504373177842566e-05, |
| 21541 | "loss": 0.0213, |
| 21542 | "step": 31210 |
| 21543 | }, |
| 21544 | { |
| 21545 | "epoch": 44.86, |
| 21546 | "learning_rate": 3.141690962099125e-05, |
| 21547 | "loss": 0.0187, |
| 21548 | "step": 31220 |
| 21549 | }, |
| 21550 | { |
| 21551 | "epoch": 44.87, |
| 21552 | "learning_rate": 3.1329446064139935e-05, |
| 21553 | "loss": 0.0268, |
| 21554 | "step": 31230 |
| 21555 | }, |
| 21556 | { |
| 21557 | "epoch": 44.89, |
| 21558 | "learning_rate": 3.124198250728862e-05, |
| 21559 | "loss": 0.0225, |
| 21560 | "step": 31240 |
| 21561 | }, |
| 21562 | { |
| 21563 | "epoch": 44.9, |
| 21564 | "learning_rate": 3.115451895043732e-05, |
| 21565 | "loss": 0.0183, |
| 21566 | "step": 31250 |
| 21567 | }, |
| 21568 | { |
| 21569 | "epoch": 44.91, |
| 21570 | "learning_rate": 3.1067055393586005e-05, |
| 21571 | "loss": 0.0191, |
| 21572 | "step": 31260 |
| 21573 | }, |
| 21574 | { |
| 21575 | "epoch": 44.93, |
| 21576 | "learning_rate": 3.097959183673469e-05, |
| 21577 | "loss": 0.0206, |
| 21578 | "step": 31270 |
| 21579 | }, |
| 21580 | { |
| 21581 | "epoch": 44.94, |
| 21582 | "learning_rate": 3.089212827988338e-05, |
| 21583 | "loss": 0.0163, |
| 21584 | "step": 31280 |
| 21585 | }, |
| 21586 | { |
| 21587 | "epoch": 44.96, |
| 21588 | "learning_rate": 3.080466472303207e-05, |
| 21589 | "loss": 0.0181, |
| 21590 | "step": 31290 |
| 21591 | }, |
| 21592 | { |
| 21593 | "epoch": 44.97, |
| 21594 | "learning_rate": 3.071720116618076e-05, |
| 21595 | "loss": 0.0171, |
| 21596 | "step": 31300 |
| 21597 | }, |
| 21598 | { |
| 21599 | "epoch": 44.97, |
| 21600 | "eval_loss": 0.1255967915058136, |
| 21601 | "eval_runtime": 40.8446, |
| 21602 | "eval_samples_per_second": 11.189, |
| 21603 | "eval_steps_per_second": 1.42, |
| 21604 | "eval_wer": 0.11850624905887668, |
| 21605 | "step": 31300 |
| 21606 | }, |
| 21607 | { |
| 21608 | "epoch": 44.99, |
| 21609 | "learning_rate": 3.0629737609329445e-05, |
| 21610 | "loss": 0.0236, |
| 21611 | "step": 31310 |
| 21612 | }, |
| 21613 | { |
| 21614 | "epoch": 45.0, |
| 21615 | "learning_rate": 3.054227405247813e-05, |
| 21616 | "loss": 0.0213, |
| 21617 | "step": 31320 |
| 21618 | }, |
| 21619 | { |
| 21620 | "epoch": 45.01, |
| 21621 | "learning_rate": 3.0454810495626817e-05, |
| 21622 | "loss": 0.0203, |
| 21623 | "step": 31330 |
| 21624 | }, |
| 21625 | { |
| 21626 | "epoch": 45.03, |
| 21627 | "learning_rate": 3.0367346938775508e-05, |
| 21628 | "loss": 0.0158, |
| 21629 | "step": 31340 |
| 21630 | }, |
| 21631 | { |
| 21632 | "epoch": 45.04, |
| 21633 | "learning_rate": 3.0279883381924196e-05, |
| 21634 | "loss": 0.028, |
| 21635 | "step": 31350 |
| 21636 | }, |
| 21637 | { |
| 21638 | "epoch": 45.06, |
| 21639 | "learning_rate": 3.0192419825072884e-05, |
| 21640 | "loss": 0.0196, |
| 21641 | "step": 31360 |
| 21642 | }, |
| 21643 | { |
| 21644 | "epoch": 45.07, |
| 21645 | "learning_rate": 3.0104956268221572e-05, |
| 21646 | "loss": 0.0144, |
| 21647 | "step": 31370 |
| 21648 | }, |
| 21649 | { |
| 21650 | "epoch": 45.09, |
| 21651 | "learning_rate": 3.001749271137026e-05, |
| 21652 | "loss": 0.0283, |
| 21653 | "step": 31380 |
| 21654 | }, |
| 21655 | { |
| 21656 | "epoch": 45.1, |
| 21657 | "learning_rate": 2.9930029154518948e-05, |
| 21658 | "loss": 0.0167, |
| 21659 | "step": 31390 |
| 21660 | }, |
| 21661 | { |
| 21662 | "epoch": 45.11, |
| 21663 | "learning_rate": 2.9842565597667636e-05, |
| 21664 | "loss": 0.0221, |
| 21665 | "step": 31400 |
| 21666 | }, |
| 21667 | { |
| 21668 | "epoch": 45.11, |
| 21669 | "eval_loss": 0.1247408539056778, |
| 21670 | "eval_runtime": 40.8758, |
| 21671 | "eval_samples_per_second": 11.18, |
| 21672 | "eval_steps_per_second": 1.419, |
| 21673 | "eval_wer": 0.1183556693269086, |
| 21674 | "step": 31400 |
| 21675 | }, |
| 21676 | { |
| 21677 | "epoch": 45.13, |
| 21678 | "learning_rate": 2.9755102040816323e-05, |
| 21679 | "loss": 0.0251, |
| 21680 | "step": 31410 |
| 21681 | }, |
| 21682 | { |
| 21683 | "epoch": 45.14, |
| 21684 | "learning_rate": 2.966763848396501e-05, |
| 21685 | "loss": 0.0201, |
| 21686 | "step": 31420 |
| 21687 | }, |
| 21688 | { |
| 21689 | "epoch": 45.16, |
| 21690 | "learning_rate": 2.9580174927113703e-05, |
| 21691 | "loss": 0.0254, |
| 21692 | "step": 31430 |
| 21693 | }, |
| 21694 | { |
| 21695 | "epoch": 45.17, |
| 21696 | "learning_rate": 2.949271137026239e-05, |
| 21697 | "loss": 0.0194, |
| 21698 | "step": 31440 |
| 21699 | }, |
| 21700 | { |
| 21701 | "epoch": 45.19, |
| 21702 | "learning_rate": 2.940524781341108e-05, |
| 21703 | "loss": 0.0157, |
| 21704 | "step": 31450 |
| 21705 | }, |
| 21706 | { |
| 21707 | "epoch": 45.2, |
| 21708 | "learning_rate": 2.9317784256559766e-05, |
| 21709 | "loss": 0.0162, |
| 21710 | "step": 31460 |
| 21711 | }, |
| 21712 | { |
| 21713 | "epoch": 45.22, |
| 21714 | "learning_rate": 2.923032069970845e-05, |
| 21715 | "loss": 0.0142, |
| 21716 | "step": 31470 |
| 21717 | }, |
| 21718 | { |
| 21719 | "epoch": 45.23, |
| 21720 | "learning_rate": 2.914285714285714e-05, |
| 21721 | "loss": 0.0222, |
| 21722 | "step": 31480 |
| 21723 | }, |
| 21724 | { |
| 21725 | "epoch": 45.24, |
| 21726 | "learning_rate": 2.9055393586005827e-05, |
| 21727 | "loss": 0.0183, |
| 21728 | "step": 31490 |
| 21729 | }, |
| 21730 | { |
| 21731 | "epoch": 45.26, |
| 21732 | "learning_rate": 2.8967930029154515e-05, |
| 21733 | "loss": 0.0177, |
| 21734 | "step": 31500 |
| 21735 | }, |
| 21736 | { |
| 21737 | "epoch": 45.26, |
| 21738 | "eval_loss": 0.1244613528251648, |
| 21739 | "eval_runtime": 41.3124, |
| 21740 | "eval_samples_per_second": 11.062, |
| 21741 | "eval_steps_per_second": 1.404, |
| 21742 | "eval_wer": 0.11925914771871705, |
| 21743 | "step": 31500 |
| 21744 | }, |
| 21745 | { |
| 21746 | "epoch": 45.27, |
| 21747 | "learning_rate": 2.8880466472303202e-05, |
| 21748 | "loss": 0.0196, |
| 21749 | "step": 31510 |
| 21750 | }, |
| 21751 | { |
| 21752 | "epoch": 45.29, |
| 21753 | "learning_rate": 2.8793002915451894e-05, |
| 21754 | "loss": 0.0131, |
| 21755 | "step": 31520 |
| 21756 | }, |
| 21757 | { |
| 21758 | "epoch": 45.3, |
| 21759 | "learning_rate": 2.870553935860058e-05, |
| 21760 | "loss": 0.0242, |
| 21761 | "step": 31530 |
| 21762 | }, |
| 21763 | { |
| 21764 | "epoch": 45.32, |
| 21765 | "learning_rate": 2.861807580174927e-05, |
| 21766 | "loss": 0.0172, |
| 21767 | "step": 31540 |
| 21768 | }, |
| 21769 | { |
| 21770 | "epoch": 45.33, |
| 21771 | "learning_rate": 2.8530612244897957e-05, |
| 21772 | "loss": 0.0177, |
| 21773 | "step": 31550 |
| 21774 | }, |
| 21775 | { |
| 21776 | "epoch": 45.34, |
| 21777 | "learning_rate": 2.8443148688046645e-05, |
| 21778 | "loss": 0.023, |
| 21779 | "step": 31560 |
| 21780 | }, |
| 21781 | { |
| 21782 | "epoch": 45.36, |
| 21783 | "learning_rate": 2.8355685131195333e-05, |
| 21784 | "loss": 0.0157, |
| 21785 | "step": 31570 |
| 21786 | }, |
| 21787 | { |
| 21788 | "epoch": 45.37, |
| 21789 | "learning_rate": 2.826822157434402e-05, |
| 21790 | "loss": 0.0215, |
| 21791 | "step": 31580 |
| 21792 | }, |
| 21793 | { |
| 21794 | "epoch": 45.39, |
| 21795 | "learning_rate": 2.818075801749271e-05, |
| 21796 | "loss": 0.017, |
| 21797 | "step": 31590 |
| 21798 | }, |
| 21799 | { |
| 21800 | "epoch": 45.4, |
| 21801 | "learning_rate": 2.8093294460641397e-05, |
| 21802 | "loss": 0.0174, |
| 21803 | "step": 31600 |
| 21804 | }, |
| 21805 | { |
| 21806 | "epoch": 45.4, |
| 21807 | "eval_loss": 0.12396515160799026, |
| 21808 | "eval_runtime": 40.8394, |
| 21809 | "eval_samples_per_second": 11.19, |
| 21810 | "eval_steps_per_second": 1.42, |
| 21811 | "eval_wer": 0.11850624905887668, |
| 21812 | "step": 31600 |
| 21813 | }, |
| 21814 | { |
| 21815 | "epoch": 45.42, |
| 21816 | "learning_rate": 2.800583090379008e-05, |
| 21817 | "loss": 0.0211, |
| 21818 | "step": 31610 |
| 21819 | }, |
| 21820 | { |
| 21821 | "epoch": 45.43, |
| 21822 | "learning_rate": 2.7918367346938776e-05, |
| 21823 | "loss": 0.0171, |
| 21824 | "step": 31620 |
| 21825 | }, |
| 21826 | { |
| 21827 | "epoch": 45.45, |
| 21828 | "learning_rate": 2.7830903790087464e-05, |
| 21829 | "loss": 0.0171, |
| 21830 | "step": 31630 |
| 21831 | }, |
| 21832 | { |
| 21833 | "epoch": 45.46, |
| 21834 | "learning_rate": 2.774344023323615e-05, |
| 21835 | "loss": 0.0188, |
| 21836 | "step": 31640 |
| 21837 | }, |
| 21838 | { |
| 21839 | "epoch": 45.47, |
| 21840 | "learning_rate": 2.7655976676384836e-05, |
| 21841 | "loss": 0.023, |
| 21842 | "step": 31650 |
| 21843 | }, |
| 21844 | { |
| 21845 | "epoch": 45.49, |
| 21846 | "learning_rate": 2.7568513119533524e-05, |
| 21847 | "loss": 0.0168, |
| 21848 | "step": 31660 |
| 21849 | }, |
| 21850 | { |
| 21851 | "epoch": 45.5, |
| 21852 | "learning_rate": 2.7481049562682212e-05, |
| 21853 | "loss": 0.0179, |
| 21854 | "step": 31670 |
| 21855 | }, |
| 21856 | { |
| 21857 | "epoch": 45.52, |
| 21858 | "learning_rate": 2.73935860058309e-05, |
| 21859 | "loss": 0.0195, |
| 21860 | "step": 31680 |
| 21861 | }, |
| 21862 | { |
| 21863 | "epoch": 45.53, |
| 21864 | "learning_rate": 2.7306122448979588e-05, |
| 21865 | "loss": 0.017, |
| 21866 | "step": 31690 |
| 21867 | }, |
| 21868 | { |
| 21869 | "epoch": 45.55, |
| 21870 | "learning_rate": 2.7218658892128276e-05, |
| 21871 | "loss": 0.0149, |
| 21872 | "step": 31700 |
| 21873 | }, |
| 21874 | { |
| 21875 | "epoch": 45.55, |
| 21876 | "eval_loss": 0.12391093373298645, |
| 21877 | "eval_runtime": 40.7869, |
| 21878 | "eval_samples_per_second": 11.205, |
| 21879 | "eval_steps_per_second": 1.422, |
| 21880 | "eval_wer": 0.1189579882547809, |
| 21881 | "step": 31700 |
| 21882 | }, |
| 21883 | { |
| 21884 | "epoch": 45.56, |
| 21885 | "learning_rate": 2.7131195335276967e-05, |
| 21886 | "loss": 0.0149, |
| 21887 | "step": 31710 |
| 21888 | }, |
| 21889 | { |
| 21890 | "epoch": 45.57, |
| 21891 | "learning_rate": 2.7043731778425655e-05, |
| 21892 | "loss": 0.0146, |
| 21893 | "step": 31720 |
| 21894 | }, |
| 21895 | { |
| 21896 | "epoch": 45.59, |
| 21897 | "learning_rate": 2.6956268221574343e-05, |
| 21898 | "loss": 0.0257, |
| 21899 | "step": 31730 |
| 21900 | }, |
| 21901 | { |
| 21902 | "epoch": 45.6, |
| 21903 | "learning_rate": 2.686880466472303e-05, |
| 21904 | "loss": 0.0181, |
| 21905 | "step": 31740 |
| 21906 | }, |
| 21907 | { |
| 21908 | "epoch": 45.62, |
| 21909 | "learning_rate": 2.678134110787172e-05, |
| 21910 | "loss": 0.0266, |
| 21911 | "step": 31750 |
| 21912 | }, |
| 21913 | { |
| 21914 | "epoch": 45.63, |
| 21915 | "learning_rate": 2.6693877551020407e-05, |
| 21916 | "loss": 0.0197, |
| 21917 | "step": 31760 |
| 21918 | }, |
| 21919 | { |
| 21920 | "epoch": 45.65, |
| 21921 | "learning_rate": 2.6606413994169095e-05, |
| 21922 | "loss": 0.0158, |
| 21923 | "step": 31770 |
| 21924 | }, |
| 21925 | { |
| 21926 | "epoch": 45.66, |
| 21927 | "learning_rate": 2.651895043731778e-05, |
| 21928 | "loss": 0.0191, |
| 21929 | "step": 31780 |
| 21930 | }, |
| 21931 | { |
| 21932 | "epoch": 45.68, |
| 21933 | "learning_rate": 2.6431486880466467e-05, |
| 21934 | "loss": 0.0206, |
| 21935 | "step": 31790 |
| 21936 | }, |
| 21937 | { |
| 21938 | "epoch": 45.69, |
| 21939 | "learning_rate": 2.6344023323615158e-05, |
| 21940 | "loss": 0.0156, |
| 21941 | "step": 31800 |
| 21942 | }, |
| 21943 | { |
| 21944 | "epoch": 45.69, |
| 21945 | "eval_loss": 0.12179351598024368, |
| 21946 | "eval_runtime": 40.676, |
| 21947 | "eval_samples_per_second": 11.235, |
| 21948 | "eval_steps_per_second": 1.426, |
| 21949 | "eval_wer": 0.11910856798674899, |
| 21950 | "step": 31800 |
| 21951 | }, |
| 21952 | { |
| 21953 | "epoch": 45.7, |
| 21954 | "learning_rate": 2.6256559766763846e-05, |
| 21955 | "loss": 0.0167, |
| 21956 | "step": 31810 |
| 21957 | }, |
| 21958 | { |
| 21959 | "epoch": 45.72, |
| 21960 | "learning_rate": 2.6169096209912534e-05, |
| 21961 | "loss": 0.0165, |
| 21962 | "step": 31820 |
| 21963 | }, |
| 21964 | { |
| 21965 | "epoch": 45.73, |
| 21966 | "learning_rate": 2.6081632653061222e-05, |
| 21967 | "loss": 0.0179, |
| 21968 | "step": 31830 |
| 21969 | }, |
| 21970 | { |
| 21971 | "epoch": 45.75, |
| 21972 | "learning_rate": 2.599416909620991e-05, |
| 21973 | "loss": 0.0183, |
| 21974 | "step": 31840 |
| 21975 | }, |
| 21976 | { |
| 21977 | "epoch": 45.76, |
| 21978 | "learning_rate": 2.5906705539358598e-05, |
| 21979 | "loss": 0.0241, |
| 21980 | "step": 31850 |
| 21981 | }, |
| 21982 | { |
| 21983 | "epoch": 45.78, |
| 21984 | "learning_rate": 2.5819241982507286e-05, |
| 21985 | "loss": 0.0191, |
| 21986 | "step": 31860 |
| 21987 | }, |
| 21988 | { |
| 21989 | "epoch": 45.79, |
| 21990 | "learning_rate": 2.5731778425655973e-05, |
| 21991 | "loss": 0.0159, |
| 21992 | "step": 31870 |
| 21993 | }, |
| 21994 | { |
| 21995 | "epoch": 45.8, |
| 21996 | "learning_rate": 2.564431486880466e-05, |
| 21997 | "loss": 0.021, |
| 21998 | "step": 31880 |
| 21999 | }, |
| 22000 | { |
| 22001 | "epoch": 45.82, |
| 22002 | "learning_rate": 2.5556851311953353e-05, |
| 22003 | "loss": 0.0194, |
| 22004 | "step": 31890 |
| 22005 | }, |
| 22006 | { |
| 22007 | "epoch": 45.83, |
| 22008 | "learning_rate": 2.546938775510204e-05, |
| 22009 | "loss": 0.0276, |
| 22010 | "step": 31900 |
| 22011 | }, |
| 22012 | { |
| 22013 | "epoch": 45.83, |
| 22014 | "eval_loss": 0.12291625887155533, |
| 22015 | "eval_runtime": 40.8657, |
| 22016 | "eval_samples_per_second": 11.183, |
| 22017 | "eval_steps_per_second": 1.419, |
| 22018 | "eval_wer": 0.11986146664658937, |
| 22019 | "step": 31900 |
| 22020 | }, |
| 22021 | { |
| 22022 | "epoch": 45.85, |
| 22023 | "learning_rate": 2.538192419825073e-05, |
| 22024 | "loss": 0.0214, |
| 22025 | "step": 31910 |
| 22026 | }, |
| 22027 | { |
| 22028 | "epoch": 45.86, |
| 22029 | "learning_rate": 2.5294460641399416e-05, |
| 22030 | "loss": 0.0105, |
| 22031 | "step": 31920 |
| 22032 | }, |
| 22033 | { |
| 22034 | "epoch": 45.88, |
| 22035 | "learning_rate": 2.5206997084548104e-05, |
| 22036 | "loss": 0.0221, |
| 22037 | "step": 31930 |
| 22038 | }, |
| 22039 | { |
| 22040 | "epoch": 45.89, |
| 22041 | "learning_rate": 2.511953352769679e-05, |
| 22042 | "loss": 0.0202, |
| 22043 | "step": 31940 |
| 22044 | }, |
| 22045 | { |
| 22046 | "epoch": 45.91, |
| 22047 | "learning_rate": 2.5032069970845477e-05, |
| 22048 | "loss": 0.0197, |
| 22049 | "step": 31950 |
| 22050 | }, |
| 22051 | { |
| 22052 | "epoch": 45.92, |
| 22053 | "learning_rate": 2.4944606413994165e-05, |
| 22054 | "loss": 0.0204, |
| 22055 | "step": 31960 |
| 22056 | }, |
| 22057 | { |
| 22058 | "epoch": 45.93, |
| 22059 | "learning_rate": 2.4857142857142852e-05, |
| 22060 | "loss": 0.0206, |
| 22061 | "step": 31970 |
| 22062 | }, |
| 22063 | { |
| 22064 | "epoch": 45.95, |
| 22065 | "learning_rate": 2.4769679300291544e-05, |
| 22066 | "loss": 0.0172, |
| 22067 | "step": 31980 |
| 22068 | }, |
| 22069 | { |
| 22070 | "epoch": 45.96, |
| 22071 | "learning_rate": 2.468221574344023e-05, |
| 22072 | "loss": 0.0149, |
| 22073 | "step": 31990 |
| 22074 | }, |
| 22075 | { |
| 22076 | "epoch": 45.98, |
| 22077 | "learning_rate": 2.459475218658892e-05, |
| 22078 | "loss": 0.0178, |
| 22079 | "step": 32000 |
| 22080 | }, |
| 22081 | { |
| 22082 | "epoch": 45.98, |
| 22083 | "eval_loss": 0.12346994876861572, |
| 22084 | "eval_runtime": 42.8222, |
| 22085 | "eval_samples_per_second": 10.672, |
| 22086 | "eval_steps_per_second": 1.354, |
| 22087 | "eval_wer": 0.1189579882547809, |
| 22088 | "step": 32000 |
| 22089 | }, |
| 22090 | { |
| 22091 | "epoch": 45.99, |
| 22092 | "learning_rate": 2.4507288629737607e-05, |
| 22093 | "loss": 0.0166, |
| 22094 | "step": 32010 |
| 22095 | }, |
| 22096 | { |
| 22097 | "epoch": 46.01, |
| 22098 | "learning_rate": 2.4419825072886295e-05, |
| 22099 | "loss": 0.0176, |
| 22100 | "step": 32020 |
| 22101 | }, |
| 22102 | { |
| 22103 | "epoch": 46.02, |
| 22104 | "learning_rate": 2.4332361516034983e-05, |
| 22105 | "loss": 0.0188, |
| 22106 | "step": 32030 |
| 22107 | }, |
| 22108 | { |
| 22109 | "epoch": 46.03, |
| 22110 | "learning_rate": 2.424489795918367e-05, |
| 22111 | "loss": 0.0142, |
| 22112 | "step": 32040 |
| 22113 | }, |
| 22114 | { |
| 22115 | "epoch": 46.05, |
| 22116 | "learning_rate": 2.415743440233236e-05, |
| 22117 | "loss": 0.0315, |
| 22118 | "step": 32050 |
| 22119 | }, |
| 22120 | { |
| 22121 | "epoch": 46.06, |
| 22122 | "learning_rate": 2.4069970845481047e-05, |
| 22123 | "loss": 0.0154, |
| 22124 | "step": 32060 |
| 22125 | }, |
| 22126 | { |
| 22127 | "epoch": 46.08, |
| 22128 | "learning_rate": 2.3982507288629738e-05, |
| 22129 | "loss": 0.0166, |
| 22130 | "step": 32070 |
| 22131 | }, |
| 22132 | { |
| 22133 | "epoch": 46.09, |
| 22134 | "learning_rate": 2.3895043731778426e-05, |
| 22135 | "loss": 0.0164, |
| 22136 | "step": 32080 |
| 22137 | }, |
| 22138 | { |
| 22139 | "epoch": 46.11, |
| 22140 | "learning_rate": 2.3807580174927114e-05, |
| 22141 | "loss": 0.0166, |
| 22142 | "step": 32090 |
| 22143 | }, |
| 22144 | { |
| 22145 | "epoch": 46.12, |
| 22146 | "learning_rate": 2.3720116618075802e-05, |
| 22147 | "loss": 0.0171, |
| 22148 | "step": 32100 |
| 22149 | }, |
| 22150 | { |
| 22151 | "epoch": 46.12, |
| 22152 | "eval_loss": 0.12300096452236176, |
| 22153 | "eval_runtime": 40.7996, |
| 22154 | "eval_samples_per_second": 11.201, |
| 22155 | "eval_steps_per_second": 1.422, |
| 22156 | "eval_wer": 0.11956030718265322, |
| 22157 | "step": 32100 |
| 22158 | }, |
| 22159 | { |
| 22160 | "epoch": 46.14, |
| 22161 | "learning_rate": 2.3632653061224486e-05, |
| 22162 | "loss": 0.0176, |
| 22163 | "step": 32110 |
| 22164 | }, |
| 22165 | { |
| 22166 | "epoch": 46.15, |
| 22167 | "learning_rate": 2.3545189504373174e-05, |
| 22168 | "loss": 0.0163, |
| 22169 | "step": 32120 |
| 22170 | }, |
| 22171 | { |
| 22172 | "epoch": 46.16, |
| 22173 | "learning_rate": 2.3457725947521862e-05, |
| 22174 | "loss": 0.0188, |
| 22175 | "step": 32130 |
| 22176 | }, |
| 22177 | { |
| 22178 | "epoch": 46.18, |
| 22179 | "learning_rate": 2.337026239067055e-05, |
| 22180 | "loss": 0.0153, |
| 22181 | "step": 32140 |
| 22182 | }, |
| 22183 | { |
| 22184 | "epoch": 46.19, |
| 22185 | "learning_rate": 2.3282798833819238e-05, |
| 22186 | "loss": 0.0167, |
| 22187 | "step": 32150 |
| 22188 | }, |
| 22189 | { |
| 22190 | "epoch": 46.21, |
| 22191 | "learning_rate": 2.3195335276967926e-05, |
| 22192 | "loss": 0.0179, |
| 22193 | "step": 32160 |
| 22194 | }, |
| 22195 | { |
| 22196 | "epoch": 46.22, |
| 22197 | "learning_rate": 2.3107871720116617e-05, |
| 22198 | "loss": 0.0158, |
| 22199 | "step": 32170 |
| 22200 | }, |
| 22201 | { |
| 22202 | "epoch": 46.24, |
| 22203 | "learning_rate": 2.3020408163265305e-05, |
| 22204 | "loss": 0.0192, |
| 22205 | "step": 32180 |
| 22206 | }, |
| 22207 | { |
| 22208 | "epoch": 46.25, |
| 22209 | "learning_rate": 2.2932944606413993e-05, |
| 22210 | "loss": 0.0139, |
| 22211 | "step": 32190 |
| 22212 | }, |
| 22213 | { |
| 22214 | "epoch": 46.26, |
| 22215 | "learning_rate": 2.284548104956268e-05, |
| 22216 | "loss": 0.0226, |
| 22217 | "step": 32200 |
| 22218 | }, |
| 22219 | { |
| 22220 | "epoch": 46.26, |
| 22221 | "eval_loss": 0.1228545680642128, |
| 22222 | "eval_runtime": 41.5098, |
| 22223 | "eval_samples_per_second": 11.009, |
| 22224 | "eval_steps_per_second": 1.397, |
| 22225 | "eval_wer": 0.11925914771871705, |
| 22226 | "step": 32200 |
| 22227 | }, |
| 22228 | { |
| 22229 | "epoch": 46.28, |
| 22230 | "learning_rate": 2.275801749271137e-05, |
| 22231 | "loss": 0.0159, |
| 22232 | "step": 32210 |
| 22233 | }, |
| 22234 | { |
| 22235 | "epoch": 46.29, |
| 22236 | "learning_rate": 2.2670553935860057e-05, |
| 22237 | "loss": 0.0174, |
| 22238 | "step": 32220 |
| 22239 | }, |
| 22240 | { |
| 22241 | "epoch": 46.31, |
| 22242 | "learning_rate": 2.2583090379008745e-05, |
| 22243 | "loss": 0.0213, |
| 22244 | "step": 32230 |
| 22245 | }, |
| 22246 | { |
| 22247 | "epoch": 46.32, |
| 22248 | "learning_rate": 2.2495626822157432e-05, |
| 22249 | "loss": 0.0167, |
| 22250 | "step": 32240 |
| 22251 | }, |
| 22252 | { |
| 22253 | "epoch": 46.34, |
| 22254 | "learning_rate": 2.2408163265306117e-05, |
| 22255 | "loss": 0.0219, |
| 22256 | "step": 32250 |
| 22257 | }, |
| 22258 | { |
| 22259 | "epoch": 46.35, |
| 22260 | "learning_rate": 2.232069970845481e-05, |
| 22261 | "loss": 0.0137, |
| 22262 | "step": 32260 |
| 22263 | }, |
| 22264 | { |
| 22265 | "epoch": 46.36, |
| 22266 | "learning_rate": 2.22332361516035e-05, |
| 22267 | "loss": 0.0177, |
| 22268 | "step": 32270 |
| 22269 | }, |
| 22270 | { |
| 22271 | "epoch": 46.38, |
| 22272 | "learning_rate": 2.2145772594752184e-05, |
| 22273 | "loss": 0.0201, |
| 22274 | "step": 32280 |
| 22275 | }, |
| 22276 | { |
| 22277 | "epoch": 46.39, |
| 22278 | "learning_rate": 2.2058309037900872e-05, |
| 22279 | "loss": 0.0156, |
| 22280 | "step": 32290 |
| 22281 | }, |
| 22282 | { |
| 22283 | "epoch": 46.41, |
| 22284 | "learning_rate": 2.197084548104956e-05, |
| 22285 | "loss": 0.0222, |
| 22286 | "step": 32300 |
| 22287 | }, |
| 22288 | { |
| 22289 | "epoch": 46.41, |
| 22290 | "eval_loss": 0.12293291836977005, |
| 22291 | "eval_runtime": 40.8016, |
| 22292 | "eval_samples_per_second": 11.201, |
| 22293 | "eval_steps_per_second": 1.422, |
| 22294 | "eval_wer": 0.1189579882547809, |
| 22295 | "step": 32300 |
| 22296 | }, |
| 22297 | { |
| 22298 | "epoch": 46.42, |
| 22299 | "learning_rate": 2.1883381924198248e-05, |
| 22300 | "loss": 0.0194, |
| 22301 | "step": 32310 |
| 22302 | }, |
| 22303 | { |
| 22304 | "epoch": 46.44, |
| 22305 | "learning_rate": 2.1795918367346936e-05, |
| 22306 | "loss": 0.0132, |
| 22307 | "step": 32320 |
| 22308 | }, |
| 22309 | { |
| 22310 | "epoch": 46.45, |
| 22311 | "learning_rate": 2.1708454810495623e-05, |
| 22312 | "loss": 0.0185, |
| 22313 | "step": 32330 |
| 22314 | }, |
| 22315 | { |
| 22316 | "epoch": 46.47, |
| 22317 | "learning_rate": 2.162099125364431e-05, |
| 22318 | "loss": 0.0228, |
| 22319 | "step": 32340 |
| 22320 | }, |
| 22321 | { |
| 22322 | "epoch": 46.48, |
| 22323 | "learning_rate": 2.1533527696793003e-05, |
| 22324 | "loss": 0.0249, |
| 22325 | "step": 32350 |
| 22326 | }, |
| 22327 | { |
| 22328 | "epoch": 46.49, |
| 22329 | "learning_rate": 2.144606413994169e-05, |
| 22330 | "loss": 0.0166, |
| 22331 | "step": 32360 |
| 22332 | }, |
| 22333 | { |
| 22334 | "epoch": 46.51, |
| 22335 | "learning_rate": 2.135860058309038e-05, |
| 22336 | "loss": 0.0187, |
| 22337 | "step": 32370 |
| 22338 | }, |
| 22339 | { |
| 22340 | "epoch": 46.52, |
| 22341 | "learning_rate": 2.1271137026239066e-05, |
| 22342 | "loss": 0.0215, |
| 22343 | "step": 32380 |
| 22344 | }, |
| 22345 | { |
| 22346 | "epoch": 46.54, |
| 22347 | "learning_rate": 2.1183673469387754e-05, |
| 22348 | "loss": 0.0113, |
| 22349 | "step": 32390 |
| 22350 | }, |
| 22351 | { |
| 22352 | "epoch": 46.55, |
| 22353 | "learning_rate": 2.1096209912536442e-05, |
| 22354 | "loss": 0.0208, |
| 22355 | "step": 32400 |
| 22356 | }, |
| 22357 | { |
| 22358 | "epoch": 46.55, |
| 22359 | "eval_loss": 0.12255549430847168, |
| 22360 | "eval_runtime": 41.0134, |
| 22361 | "eval_samples_per_second": 11.143, |
| 22362 | "eval_steps_per_second": 1.414, |
| 22363 | "eval_wer": 0.11820508959494053, |
| 22364 | "step": 32400 |
| 22365 | }, |
| 22366 | { |
| 22367 | "epoch": 46.57, |
| 22368 | "learning_rate": 2.100874635568513e-05, |
| 22369 | "loss": 0.0179, |
| 22370 | "step": 32410 |
| 22371 | }, |
| 22372 | { |
| 22373 | "epoch": 46.58, |
| 22374 | "learning_rate": 2.0921282798833815e-05, |
| 22375 | "loss": 0.0192, |
| 22376 | "step": 32420 |
| 22377 | }, |
| 22378 | { |
| 22379 | "epoch": 46.59, |
| 22380 | "learning_rate": 2.0833819241982502e-05, |
| 22381 | "loss": 0.0183, |
| 22382 | "step": 32430 |
| 22383 | }, |
| 22384 | { |
| 22385 | "epoch": 46.61, |
| 22386 | "learning_rate": 2.0746355685131197e-05, |
| 22387 | "loss": 0.0142, |
| 22388 | "step": 32440 |
| 22389 | }, |
| 22390 | { |
| 22391 | "epoch": 46.62, |
| 22392 | "learning_rate": 2.065889212827988e-05, |
| 22393 | "loss": 0.021, |
| 22394 | "step": 32450 |
| 22395 | }, |
| 22396 | { |
| 22397 | "epoch": 46.64, |
| 22398 | "learning_rate": 2.057142857142857e-05, |
| 22399 | "loss": 0.0161, |
| 22400 | "step": 32460 |
| 22401 | }, |
| 22402 | { |
| 22403 | "epoch": 46.65, |
| 22404 | "learning_rate": 2.0483965014577257e-05, |
| 22405 | "loss": 0.0138, |
| 22406 | "step": 32470 |
| 22407 | }, |
| 22408 | { |
| 22409 | "epoch": 46.67, |
| 22410 | "learning_rate": 2.0396501457725945e-05, |
| 22411 | "loss": 0.0183, |
| 22412 | "step": 32480 |
| 22413 | }, |
| 22414 | { |
| 22415 | "epoch": 46.68, |
| 22416 | "learning_rate": 2.0309037900874633e-05, |
| 22417 | "loss": 0.0184, |
| 22418 | "step": 32490 |
| 22419 | }, |
| 22420 | { |
| 22421 | "epoch": 46.7, |
| 22422 | "learning_rate": 2.022157434402332e-05, |
| 22423 | "loss": 0.0176, |
| 22424 | "step": 32500 |
| 22425 | }, |
| 22426 | { |
| 22427 | "epoch": 46.7, |
| 22428 | "eval_loss": 0.12446217983961105, |
| 22429 | "eval_runtime": 40.8413, |
| 22430 | "eval_samples_per_second": 11.19, |
| 22431 | "eval_steps_per_second": 1.42, |
| 22432 | "eval_wer": 0.11850624905887668, |
| 22433 | "step": 32500 |
| 22434 | }, |
| 22435 | { |
| 22436 | "epoch": 46.71, |
| 22437 | "learning_rate": 2.013411078717201e-05, |
| 22438 | "loss": 0.019, |
| 22439 | "step": 32510 |
| 22440 | }, |
| 22441 | { |
| 22442 | "epoch": 46.72, |
| 22443 | "learning_rate": 2.0046647230320697e-05, |
| 22444 | "loss": 0.0198, |
| 22445 | "step": 32520 |
| 22446 | }, |
| 22447 | { |
| 22448 | "epoch": 46.74, |
| 22449 | "learning_rate": 1.9959183673469388e-05, |
| 22450 | "loss": 0.0139, |
| 22451 | "step": 32530 |
| 22452 | }, |
| 22453 | { |
| 22454 | "epoch": 46.75, |
| 22455 | "learning_rate": 1.9871720116618076e-05, |
| 22456 | "loss": 0.0155, |
| 22457 | "step": 32540 |
| 22458 | }, |
| 22459 | { |
| 22460 | "epoch": 46.77, |
| 22461 | "learning_rate": 1.9784256559766764e-05, |
| 22462 | "loss": 0.0259, |
| 22463 | "step": 32550 |
| 22464 | }, |
| 22465 | { |
| 22466 | "epoch": 46.78, |
| 22467 | "learning_rate": 1.9696793002915452e-05, |
| 22468 | "loss": 0.017, |
| 22469 | "step": 32560 |
| 22470 | }, |
| 22471 | { |
| 22472 | "epoch": 46.8, |
| 22473 | "learning_rate": 1.960932944606414e-05, |
| 22474 | "loss": 0.0182, |
| 22475 | "step": 32570 |
| 22476 | }, |
| 22477 | { |
| 22478 | "epoch": 46.81, |
| 22479 | "learning_rate": 1.9521865889212828e-05, |
| 22480 | "loss": 0.0195, |
| 22481 | "step": 32580 |
| 22482 | }, |
| 22483 | { |
| 22484 | "epoch": 46.82, |
| 22485 | "learning_rate": 1.9434402332361512e-05, |
| 22486 | "loss": 0.0172, |
| 22487 | "step": 32590 |
| 22488 | }, |
| 22489 | { |
| 22490 | "epoch": 46.84, |
| 22491 | "learning_rate": 1.93469387755102e-05, |
| 22492 | "loss": 0.0202, |
| 22493 | "step": 32600 |
| 22494 | }, |
| 22495 | { |
| 22496 | "epoch": 46.84, |
| 22497 | "eval_loss": 0.12425705790519714, |
| 22498 | "eval_runtime": 42.4199, |
| 22499 | "eval_samples_per_second": 10.773, |
| 22500 | "eval_steps_per_second": 1.367, |
| 22501 | "eval_wer": 0.11956030718265322, |
| 22502 | "step": 32600 |
| 22503 | }, |
| 22504 | { |
| 22505 | "epoch": 46.85, |
| 22506 | "learning_rate": 1.9259475218658888e-05, |
| 22507 | "loss": 0.0155, |
| 22508 | "step": 32610 |
| 22509 | }, |
| 22510 | { |
| 22511 | "epoch": 46.87, |
| 22512 | "learning_rate": 1.9172011661807576e-05, |
| 22513 | "loss": 0.0186, |
| 22514 | "step": 32620 |
| 22515 | }, |
| 22516 | { |
| 22517 | "epoch": 46.88, |
| 22518 | "learning_rate": 1.9084548104956267e-05, |
| 22519 | "loss": 0.0262, |
| 22520 | "step": 32630 |
| 22521 | }, |
| 22522 | { |
| 22523 | "epoch": 46.9, |
| 22524 | "learning_rate": 1.8997084548104955e-05, |
| 22525 | "loss": 0.0176, |
| 22526 | "step": 32640 |
| 22527 | }, |
| 22528 | { |
| 22529 | "epoch": 46.91, |
| 22530 | "learning_rate": 1.8909620991253643e-05, |
| 22531 | "loss": 0.0215, |
| 22532 | "step": 32650 |
| 22533 | }, |
| 22534 | { |
| 22535 | "epoch": 46.93, |
| 22536 | "learning_rate": 1.882215743440233e-05, |
| 22537 | "loss": 0.0141, |
| 22538 | "step": 32660 |
| 22539 | }, |
| 22540 | { |
| 22541 | "epoch": 46.94, |
| 22542 | "learning_rate": 1.873469387755102e-05, |
| 22543 | "loss": 0.0224, |
| 22544 | "step": 32670 |
| 22545 | }, |
| 22546 | { |
| 22547 | "epoch": 46.95, |
| 22548 | "learning_rate": 1.8647230320699707e-05, |
| 22549 | "loss": 0.0199, |
| 22550 | "step": 32680 |
| 22551 | }, |
| 22552 | { |
| 22553 | "epoch": 46.97, |
| 22554 | "learning_rate": 1.8559766763848395e-05, |
| 22555 | "loss": 0.0129, |
| 22556 | "step": 32690 |
| 22557 | }, |
| 22558 | { |
| 22559 | "epoch": 46.98, |
| 22560 | "learning_rate": 1.8472303206997082e-05, |
| 22561 | "loss": 0.0176, |
| 22562 | "step": 32700 |
| 22563 | }, |
| 22564 | { |
| 22565 | "epoch": 46.98, |
| 22566 | "eval_loss": 0.12350737303495407, |
| 22567 | "eval_runtime": 40.9221, |
| 22568 | "eval_samples_per_second": 11.168, |
| 22569 | "eval_steps_per_second": 1.417, |
| 22570 | "eval_wer": 0.11956030718265322, |
| 22571 | "step": 32700 |
| 22572 | }, |
| 22573 | { |
| 22574 | "epoch": 47.0, |
| 22575 | "learning_rate": 1.838483965014577e-05, |
| 22576 | "loss": 0.017, |
| 22577 | "step": 32710 |
| 22578 | }, |
| 22579 | { |
| 22580 | "epoch": 47.01, |
| 22581 | "learning_rate": 1.8297376093294458e-05, |
| 22582 | "loss": 0.0208, |
| 22583 | "step": 32720 |
| 22584 | }, |
| 22585 | { |
| 22586 | "epoch": 47.03, |
| 22587 | "learning_rate": 1.8209912536443146e-05, |
| 22588 | "loss": 0.0144, |
| 22589 | "step": 32730 |
| 22590 | }, |
| 22591 | { |
| 22592 | "epoch": 47.04, |
| 22593 | "learning_rate": 1.8122448979591837e-05, |
| 22594 | "loss": 0.0164, |
| 22595 | "step": 32740 |
| 22596 | }, |
| 22597 | { |
| 22598 | "epoch": 47.05, |
| 22599 | "learning_rate": 1.8034985422740522e-05, |
| 22600 | "loss": 0.0174, |
| 22601 | "step": 32750 |
| 22602 | }, |
| 22603 | { |
| 22604 | "epoch": 47.07, |
| 22605 | "learning_rate": 1.794752186588921e-05, |
| 22606 | "loss": 0.0194, |
| 22607 | "step": 32760 |
| 22608 | }, |
| 22609 | { |
| 22610 | "epoch": 47.08, |
| 22611 | "learning_rate": 1.7860058309037898e-05, |
| 22612 | "loss": 0.0219, |
| 22613 | "step": 32770 |
| 22614 | }, |
| 22615 | { |
| 22616 | "epoch": 47.1, |
| 22617 | "learning_rate": 1.7772594752186586e-05, |
| 22618 | "loss": 0.0143, |
| 22619 | "step": 32780 |
| 22620 | }, |
| 22621 | { |
| 22622 | "epoch": 47.11, |
| 22623 | "learning_rate": 1.7685131195335277e-05, |
| 22624 | "loss": 0.0125, |
| 22625 | "step": 32790 |
| 22626 | }, |
| 22627 | { |
| 22628 | "epoch": 47.13, |
| 22629 | "learning_rate": 1.7597667638483965e-05, |
| 22630 | "loss": 0.0226, |
| 22631 | "step": 32800 |
| 22632 | }, |
| 22633 | { |
| 22634 | "epoch": 47.13, |
| 22635 | "eval_loss": 0.12387290596961975, |
| 22636 | "eval_runtime": 40.9699, |
| 22637 | "eval_samples_per_second": 11.155, |
| 22638 | "eval_steps_per_second": 1.416, |
| 22639 | "eval_wer": 0.12001204637855745, |
| 22640 | "step": 32800 |
| 22641 | }, |
| 22642 | { |
| 22643 | "epoch": 47.14, |
| 22644 | "learning_rate": 1.7510204081632653e-05, |
| 22645 | "loss": 0.0169, |
| 22646 | "step": 32810 |
| 22647 | }, |
| 22648 | { |
| 22649 | "epoch": 47.16, |
| 22650 | "learning_rate": 1.7422740524781337e-05, |
| 22651 | "loss": 0.0186, |
| 22652 | "step": 32820 |
| 22653 | }, |
| 22654 | { |
| 22655 | "epoch": 47.17, |
| 22656 | "learning_rate": 1.733527696793003e-05, |
| 22657 | "loss": 0.0147, |
| 22658 | "step": 32830 |
| 22659 | }, |
| 22660 | { |
| 22661 | "epoch": 47.18, |
| 22662 | "learning_rate": 1.7247813411078716e-05, |
| 22663 | "loss": 0.0132, |
| 22664 | "step": 32840 |
| 22665 | }, |
| 22666 | { |
| 22667 | "epoch": 47.2, |
| 22668 | "learning_rate": 1.7160349854227404e-05, |
| 22669 | "loss": 0.0159, |
| 22670 | "step": 32850 |
| 22671 | }, |
| 22672 | { |
| 22673 | "epoch": 47.21, |
| 22674 | "learning_rate": 1.7072886297376092e-05, |
| 22675 | "loss": 0.0161, |
| 22676 | "step": 32860 |
| 22677 | }, |
| 22678 | { |
| 22679 | "epoch": 47.23, |
| 22680 | "learning_rate": 1.698542274052478e-05, |
| 22681 | "loss": 0.0151, |
| 22682 | "step": 32870 |
| 22683 | }, |
| 22684 | { |
| 22685 | "epoch": 47.24, |
| 22686 | "learning_rate": 1.6897959183673468e-05, |
| 22687 | "loss": 0.013, |
| 22688 | "step": 32880 |
| 22689 | }, |
| 22690 | { |
| 22691 | "epoch": 47.26, |
| 22692 | "learning_rate": 1.6810495626822156e-05, |
| 22693 | "loss": 0.0146, |
| 22694 | "step": 32890 |
| 22695 | }, |
| 22696 | { |
| 22697 | "epoch": 47.27, |
| 22698 | "learning_rate": 1.6723032069970844e-05, |
| 22699 | "loss": 0.0122, |
| 22700 | "step": 32900 |
| 22701 | }, |
| 22702 | { |
| 22703 | "epoch": 47.27, |
| 22704 | "eval_loss": 0.12316489219665527, |
| 22705 | "eval_runtime": 42.0627, |
| 22706 | "eval_samples_per_second": 10.865, |
| 22707 | "eval_steps_per_second": 1.379, |
| 22708 | "eval_wer": 0.11940972745068514, |
| 22709 | "step": 32900 |
| 22710 | }, |
| 22711 | { |
| 22712 | "epoch": 47.28, |
| 22713 | "learning_rate": 1.663556851311953e-05, |
| 22714 | "loss": 0.0185, |
| 22715 | "step": 32910 |
| 22716 | }, |
| 22717 | { |
| 22718 | "epoch": 47.3, |
| 22719 | "learning_rate": 1.654810495626822e-05, |
| 22720 | "loss": 0.0215, |
| 22721 | "step": 32920 |
| 22722 | }, |
| 22723 | { |
| 22724 | "epoch": 47.31, |
| 22725 | "learning_rate": 1.6460641399416907e-05, |
| 22726 | "loss": 0.0183, |
| 22727 | "step": 32930 |
| 22728 | }, |
| 22729 | { |
| 22730 | "epoch": 47.33, |
| 22731 | "learning_rate": 1.6373177842565595e-05, |
| 22732 | "loss": 0.0147, |
| 22733 | "step": 32940 |
| 22734 | }, |
| 22735 | { |
| 22736 | "epoch": 47.34, |
| 22737 | "learning_rate": 1.6285714285714283e-05, |
| 22738 | "loss": 0.0171, |
| 22739 | "step": 32950 |
| 22740 | }, |
| 22741 | { |
| 22742 | "epoch": 47.36, |
| 22743 | "learning_rate": 1.619825072886297e-05, |
| 22744 | "loss": 0.0137, |
| 22745 | "step": 32960 |
| 22746 | }, |
| 22747 | { |
| 22748 | "epoch": 47.37, |
| 22749 | "learning_rate": 1.6110787172011662e-05, |
| 22750 | "loss": 0.0158, |
| 22751 | "step": 32970 |
| 22752 | }, |
| 22753 | { |
| 22754 | "epoch": 47.39, |
| 22755 | "learning_rate": 1.602332361516035e-05, |
| 22756 | "loss": 0.0102, |
| 22757 | "step": 32980 |
| 22758 | }, |
| 22759 | { |
| 22760 | "epoch": 47.4, |
| 22761 | "learning_rate": 1.5935860058309035e-05, |
| 22762 | "loss": 0.0119, |
| 22763 | "step": 32990 |
| 22764 | }, |
| 22765 | { |
| 22766 | "epoch": 47.41, |
| 22767 | "learning_rate": 1.5848396501457723e-05, |
| 22768 | "loss": 0.0185, |
| 22769 | "step": 33000 |
| 22770 | }, |
| 22771 | { |
| 22772 | "epoch": 47.41, |
| 22773 | "eval_loss": 0.12409212440252304, |
| 22774 | "eval_runtime": 41.2942, |
| 22775 | "eval_samples_per_second": 11.067, |
| 22776 | "eval_steps_per_second": 1.405, |
| 22777 | "eval_wer": 0.11880740852281282, |
| 22778 | "step": 33000 |
| 22779 | }, |
| 22780 | { |
| 22781 | "epoch": 47.43, |
| 22782 | "learning_rate": 1.5760932944606414e-05, |
| 22783 | "loss": 0.0144, |
| 22784 | "step": 33010 |
| 22785 | }, |
| 22786 | { |
| 22787 | "epoch": 47.44, |
| 22788 | "learning_rate": 1.5673469387755102e-05, |
| 22789 | "loss": 0.0204, |
| 22790 | "step": 33020 |
| 22791 | }, |
| 22792 | { |
| 22793 | "epoch": 47.46, |
| 22794 | "learning_rate": 1.558600583090379e-05, |
| 22795 | "loss": 0.0172, |
| 22796 | "step": 33030 |
| 22797 | }, |
| 22798 | { |
| 22799 | "epoch": 47.47, |
| 22800 | "learning_rate": 1.5498542274052478e-05, |
| 22801 | "loss": 0.0179, |
| 22802 | "step": 33040 |
| 22803 | }, |
| 22804 | { |
| 22805 | "epoch": 47.49, |
| 22806 | "learning_rate": 1.5411078717201166e-05, |
| 22807 | "loss": 0.0153, |
| 22808 | "step": 33050 |
| 22809 | }, |
| 22810 | { |
| 22811 | "epoch": 47.5, |
| 22812 | "learning_rate": 1.5323615160349853e-05, |
| 22813 | "loss": 0.0206, |
| 22814 | "step": 33060 |
| 22815 | }, |
| 22816 | { |
| 22817 | "epoch": 47.51, |
| 22818 | "learning_rate": 1.5236151603498541e-05, |
| 22819 | "loss": 0.0158, |
| 22820 | "step": 33070 |
| 22821 | }, |
| 22822 | { |
| 22823 | "epoch": 47.53, |
| 22824 | "learning_rate": 1.514868804664723e-05, |
| 22825 | "loss": 0.0187, |
| 22826 | "step": 33080 |
| 22827 | }, |
| 22828 | { |
| 22829 | "epoch": 47.54, |
| 22830 | "learning_rate": 1.5061224489795917e-05, |
| 22831 | "loss": 0.0162, |
| 22832 | "step": 33090 |
| 22833 | }, |
| 22834 | { |
| 22835 | "epoch": 47.56, |
| 22836 | "learning_rate": 1.4973760932944603e-05, |
| 22837 | "loss": 0.0198, |
| 22838 | "step": 33100 |
| 22839 | }, |
| 22840 | { |
| 22841 | "epoch": 47.56, |
| 22842 | "eval_loss": 0.12408657371997833, |
| 22843 | "eval_runtime": 41.0394, |
| 22844 | "eval_samples_per_second": 11.136, |
| 22845 | "eval_steps_per_second": 1.413, |
| 22846 | "eval_wer": 0.11925914771871705, |
| 22847 | "step": 33100 |
| 22848 | }, |
| 22849 | { |
| 22850 | "epoch": 47.57, |
| 22851 | "learning_rate": 1.4886297376093295e-05, |
| 22852 | "loss": 0.016, |
| 22853 | "step": 33110 |
| 22854 | }, |
| 22855 | { |
| 22856 | "epoch": 47.59, |
| 22857 | "learning_rate": 1.4798833819241981e-05, |
| 22858 | "loss": 0.0162, |
| 22859 | "step": 33120 |
| 22860 | }, |
| 22861 | { |
| 22862 | "epoch": 47.6, |
| 22863 | "learning_rate": 1.4711370262390669e-05, |
| 22864 | "loss": 0.0177, |
| 22865 | "step": 33130 |
| 22866 | }, |
| 22867 | { |
| 22868 | "epoch": 47.61, |
| 22869 | "learning_rate": 1.4623906705539357e-05, |
| 22870 | "loss": 0.0133, |
| 22871 | "step": 33140 |
| 22872 | }, |
| 22873 | { |
| 22874 | "epoch": 47.63, |
| 22875 | "learning_rate": 1.4536443148688046e-05, |
| 22876 | "loss": 0.0181, |
| 22877 | "step": 33150 |
| 22878 | }, |
| 22879 | { |
| 22880 | "epoch": 47.64, |
| 22881 | "learning_rate": 1.4448979591836734e-05, |
| 22882 | "loss": 0.0191, |
| 22883 | "step": 33160 |
| 22884 | }, |
| 22885 | { |
| 22886 | "epoch": 47.66, |
| 22887 | "learning_rate": 1.4361516034985422e-05, |
| 22888 | "loss": 0.0241, |
| 22889 | "step": 33170 |
| 22890 | }, |
| 22891 | { |
| 22892 | "epoch": 47.67, |
| 22893 | "learning_rate": 1.427405247813411e-05, |
| 22894 | "loss": 0.0197, |
| 22895 | "step": 33180 |
| 22896 | }, |
| 22897 | { |
| 22898 | "epoch": 47.69, |
| 22899 | "learning_rate": 1.4186588921282796e-05, |
| 22900 | "loss": 0.0198, |
| 22901 | "step": 33190 |
| 22902 | }, |
| 22903 | { |
| 22904 | "epoch": 47.7, |
| 22905 | "learning_rate": 1.4099125364431486e-05, |
| 22906 | "loss": 0.0184, |
| 22907 | "step": 33200 |
| 22908 | }, |
| 22909 | { |
| 22910 | "epoch": 47.7, |
| 22911 | "eval_loss": 0.12426743656396866, |
| 22912 | "eval_runtime": 41.2473, |
| 22913 | "eval_samples_per_second": 11.08, |
| 22914 | "eval_steps_per_second": 1.406, |
| 22915 | "eval_wer": 0.11820508959494053, |
| 22916 | "step": 33200 |
| 22917 | }, |
| 22918 | { |
| 22919 | "epoch": 47.72, |
| 22920 | "learning_rate": 1.4011661807580174e-05, |
| 22921 | "loss": 0.0178, |
| 22922 | "step": 33210 |
| 22923 | }, |
| 22924 | { |
| 22925 | "epoch": 47.73, |
| 22926 | "learning_rate": 1.3924198250728862e-05, |
| 22927 | "loss": 0.0225, |
| 22928 | "step": 33220 |
| 22929 | }, |
| 22930 | { |
| 22931 | "epoch": 47.74, |
| 22932 | "learning_rate": 1.383673469387755e-05, |
| 22933 | "loss": 0.013, |
| 22934 | "step": 33230 |
| 22935 | }, |
| 22936 | { |
| 22937 | "epoch": 47.76, |
| 22938 | "learning_rate": 1.3749271137026239e-05, |
| 22939 | "loss": 0.0106, |
| 22940 | "step": 33240 |
| 22941 | }, |
| 22942 | { |
| 22943 | "epoch": 47.77, |
| 22944 | "learning_rate": 1.3661807580174927e-05, |
| 22945 | "loss": 0.0202, |
| 22946 | "step": 33250 |
| 22947 | }, |
| 22948 | { |
| 22949 | "epoch": 47.79, |
| 22950 | "learning_rate": 1.3574344023323615e-05, |
| 22951 | "loss": 0.015, |
| 22952 | "step": 33260 |
| 22953 | }, |
| 22954 | { |
| 22955 | "epoch": 47.8, |
| 22956 | "learning_rate": 1.3486880466472301e-05, |
| 22957 | "loss": 0.0233, |
| 22958 | "step": 33270 |
| 22959 | }, |
| 22960 | { |
| 22961 | "epoch": 47.82, |
| 22962 | "learning_rate": 1.3399416909620989e-05, |
| 22963 | "loss": 0.0155, |
| 22964 | "step": 33280 |
| 22965 | }, |
| 22966 | { |
| 22967 | "epoch": 47.83, |
| 22968 | "learning_rate": 1.3311953352769678e-05, |
| 22969 | "loss": 0.0182, |
| 22970 | "step": 33290 |
| 22971 | }, |
| 22972 | { |
| 22973 | "epoch": 47.84, |
| 22974 | "learning_rate": 1.3224489795918366e-05, |
| 22975 | "loss": 0.0233, |
| 22976 | "step": 33300 |
| 22977 | }, |
| 22978 | { |
| 22979 | "epoch": 47.84, |
| 22980 | "eval_loss": 0.12506160140037537, |
| 22981 | "eval_runtime": 41.1898, |
| 22982 | "eval_samples_per_second": 11.095, |
| 22983 | "eval_steps_per_second": 1.408, |
| 22984 | "eval_wer": 0.11745219093510013, |
| 22985 | "step": 33300 |
| 22986 | }, |
| 22987 | { |
| 22988 | "epoch": 47.86, |
| 22989 | "learning_rate": 1.3137026239067054e-05, |
| 22990 | "loss": 0.0202, |
| 22991 | "step": 33310 |
| 22992 | }, |
| 22993 | { |
| 22994 | "epoch": 47.87, |
| 22995 | "learning_rate": 1.3049562682215742e-05, |
| 22996 | "loss": 0.0223, |
| 22997 | "step": 33320 |
| 22998 | }, |
| 22999 | { |
| 23000 | "epoch": 47.89, |
| 23001 | "learning_rate": 1.296209912536443e-05, |
| 23002 | "loss": 0.0122, |
| 23003 | "step": 33330 |
| 23004 | }, |
| 23005 | { |
| 23006 | "epoch": 47.9, |
| 23007 | "learning_rate": 1.287463556851312e-05, |
| 23008 | "loss": 0.0144, |
| 23009 | "step": 33340 |
| 23010 | }, |
| 23011 | { |
| 23012 | "epoch": 47.92, |
| 23013 | "learning_rate": 1.2787172011661806e-05, |
| 23014 | "loss": 0.0169, |
| 23015 | "step": 33350 |
| 23016 | }, |
| 23017 | { |
| 23018 | "epoch": 47.93, |
| 23019 | "learning_rate": 1.2699708454810494e-05, |
| 23020 | "loss": 0.0131, |
| 23021 | "step": 33360 |
| 23022 | }, |
| 23023 | { |
| 23024 | "epoch": 47.95, |
| 23025 | "learning_rate": 1.2612244897959182e-05, |
| 23026 | "loss": 0.021, |
| 23027 | "step": 33370 |
| 23028 | }, |
| 23029 | { |
| 23030 | "epoch": 47.96, |
| 23031 | "learning_rate": 1.2524781341107871e-05, |
| 23032 | "loss": 0.0194, |
| 23033 | "step": 33380 |
| 23034 | }, |
| 23035 | { |
| 23036 | "epoch": 47.97, |
| 23037 | "learning_rate": 1.2437317784256559e-05, |
| 23038 | "loss": 0.0174, |
| 23039 | "step": 33390 |
| 23040 | }, |
| 23041 | { |
| 23042 | "epoch": 47.99, |
| 23043 | "learning_rate": 1.2349854227405247e-05, |
| 23044 | "loss": 0.0137, |
| 23045 | "step": 33400 |
| 23046 | }, |
| 23047 | { |
| 23048 | "epoch": 47.99, |
| 23049 | "eval_loss": 0.12359973043203354, |
| 23050 | "eval_runtime": 40.9137, |
| 23051 | "eval_samples_per_second": 11.17, |
| 23052 | "eval_steps_per_second": 1.418, |
| 23053 | "eval_wer": 0.11669929227525976, |
| 23054 | "step": 33400 |
| 23055 | }, |
| 23056 | { |
| 23057 | "epoch": 48.0, |
| 23058 | "learning_rate": 1.2262390670553935e-05, |
| 23059 | "loss": 0.0138, |
| 23060 | "step": 33410 |
| 23061 | }, |
| 23062 | { |
| 23063 | "epoch": 48.02, |
| 23064 | "learning_rate": 1.2174927113702621e-05, |
| 23065 | "loss": 0.0119, |
| 23066 | "step": 33420 |
| 23067 | }, |
| 23068 | { |
| 23069 | "epoch": 48.03, |
| 23070 | "learning_rate": 1.2087463556851312e-05, |
| 23071 | "loss": 0.014, |
| 23072 | "step": 33430 |
| 23073 | }, |
| 23074 | { |
| 23075 | "epoch": 48.05, |
| 23076 | "learning_rate": 1.1999999999999999e-05, |
| 23077 | "loss": 0.0235, |
| 23078 | "step": 33440 |
| 23079 | }, |
| 23080 | { |
| 23081 | "epoch": 48.06, |
| 23082 | "learning_rate": 1.1912536443148687e-05, |
| 23083 | "loss": 0.0219, |
| 23084 | "step": 33450 |
| 23085 | }, |
| 23086 | { |
| 23087 | "epoch": 48.07, |
| 23088 | "learning_rate": 1.1825072886297374e-05, |
| 23089 | "loss": 0.014, |
| 23090 | "step": 33460 |
| 23091 | }, |
| 23092 | { |
| 23093 | "epoch": 48.09, |
| 23094 | "learning_rate": 1.1737609329446064e-05, |
| 23095 | "loss": 0.0245, |
| 23096 | "step": 33470 |
| 23097 | }, |
| 23098 | { |
| 23099 | "epoch": 48.1, |
| 23100 | "learning_rate": 1.1650145772594752e-05, |
| 23101 | "loss": 0.0179, |
| 23102 | "step": 33480 |
| 23103 | }, |
| 23104 | { |
| 23105 | "epoch": 48.12, |
| 23106 | "learning_rate": 1.156268221574344e-05, |
| 23107 | "loss": 0.0327, |
| 23108 | "step": 33490 |
| 23109 | }, |
| 23110 | { |
| 23111 | "epoch": 48.13, |
| 23112 | "learning_rate": 1.1475218658892128e-05, |
| 23113 | "loss": 0.0149, |
| 23114 | "step": 33500 |
| 23115 | }, |
| 23116 | { |
| 23117 | "epoch": 48.13, |
| 23118 | "eval_loss": 0.12391505390405655, |
| 23119 | "eval_runtime": 40.4562, |
| 23120 | "eval_samples_per_second": 11.296, |
| 23121 | "eval_steps_per_second": 1.434, |
| 23122 | "eval_wer": 0.11654871254329167, |
| 23123 | "step": 33500 |
| 23124 | }, |
| 23125 | { |
| 23126 | "epoch": 48.15, |
| 23127 | "learning_rate": 1.1387755102040814e-05, |
| 23128 | "loss": 0.0124, |
| 23129 | "step": 33510 |
| 23130 | }, |
| 23131 | { |
| 23132 | "epoch": 48.16, |
| 23133 | "learning_rate": 1.1300291545189503e-05, |
| 23134 | "loss": 0.0215, |
| 23135 | "step": 33520 |
| 23136 | }, |
| 23137 | { |
| 23138 | "epoch": 48.18, |
| 23139 | "learning_rate": 1.1212827988338191e-05, |
| 23140 | "loss": 0.0111, |
| 23141 | "step": 33530 |
| 23142 | }, |
| 23143 | { |
| 23144 | "epoch": 48.19, |
| 23145 | "learning_rate": 1.112536443148688e-05, |
| 23146 | "loss": 0.0195, |
| 23147 | "step": 33540 |
| 23148 | }, |
| 23149 | { |
| 23150 | "epoch": 48.2, |
| 23151 | "learning_rate": 1.1037900874635567e-05, |
| 23152 | "loss": 0.0186, |
| 23153 | "step": 33550 |
| 23154 | }, |
| 23155 | { |
| 23156 | "epoch": 48.22, |
| 23157 | "learning_rate": 1.0950437317784255e-05, |
| 23158 | "loss": 0.0154, |
| 23159 | "step": 33560 |
| 23160 | }, |
| 23161 | { |
| 23162 | "epoch": 48.23, |
| 23163 | "learning_rate": 1.0862973760932945e-05, |
| 23164 | "loss": 0.0162, |
| 23165 | "step": 33570 |
| 23166 | }, |
| 23167 | { |
| 23168 | "epoch": 48.25, |
| 23169 | "learning_rate": 1.0775510204081633e-05, |
| 23170 | "loss": 0.0134, |
| 23171 | "step": 33580 |
| 23172 | }, |
| 23173 | { |
| 23174 | "epoch": 48.26, |
| 23175 | "learning_rate": 1.0688046647230319e-05, |
| 23176 | "loss": 0.022, |
| 23177 | "step": 33590 |
| 23178 | }, |
| 23179 | { |
| 23180 | "epoch": 48.28, |
| 23181 | "learning_rate": 1.0600583090379007e-05, |
| 23182 | "loss": 0.0129, |
| 23183 | "step": 33600 |
| 23184 | }, |
| 23185 | { |
| 23186 | "epoch": 48.28, |
| 23187 | "eval_loss": 0.12475401163101196, |
| 23188 | "eval_runtime": 40.7809, |
| 23189 | "eval_samples_per_second": 11.206, |
| 23190 | "eval_steps_per_second": 1.422, |
| 23191 | "eval_wer": 0.11624755307935553, |
| 23192 | "step": 33600 |
| 23193 | }, |
| 23194 | { |
| 23195 | "epoch": 48.29, |
| 23196 | "learning_rate": 1.0513119533527696e-05, |
| 23197 | "loss": 0.0161, |
| 23198 | "step": 33610 |
| 23199 | }, |
| 23200 | { |
| 23201 | "epoch": 48.3, |
| 23202 | "learning_rate": 1.0425655976676384e-05, |
| 23203 | "loss": 0.0174, |
| 23204 | "step": 33620 |
| 23205 | }, |
| 23206 | { |
| 23207 | "epoch": 48.32, |
| 23208 | "learning_rate": 1.0338192419825072e-05, |
| 23209 | "loss": 0.0114, |
| 23210 | "step": 33630 |
| 23211 | }, |
| 23212 | { |
| 23213 | "epoch": 48.33, |
| 23214 | "learning_rate": 1.025072886297376e-05, |
| 23215 | "loss": 0.0237, |
| 23216 | "step": 33640 |
| 23217 | }, |
| 23218 | { |
| 23219 | "epoch": 48.35, |
| 23220 | "learning_rate": 1.0163265306122448e-05, |
| 23221 | "loss": 0.0142, |
| 23222 | "step": 33650 |
| 23223 | }, |
| 23224 | { |
| 23225 | "epoch": 48.36, |
| 23226 | "learning_rate": 1.0075801749271137e-05, |
| 23227 | "loss": 0.0162, |
| 23228 | "step": 33660 |
| 23229 | }, |
| 23230 | { |
| 23231 | "epoch": 48.38, |
| 23232 | "learning_rate": 9.988338192419824e-06, |
| 23233 | "loss": 0.0225, |
| 23234 | "step": 33670 |
| 23235 | }, |
| 23236 | { |
| 23237 | "epoch": 48.39, |
| 23238 | "learning_rate": 9.900874635568512e-06, |
| 23239 | "loss": 0.0172, |
| 23240 | "step": 33680 |
| 23241 | }, |
| 23242 | { |
| 23243 | "epoch": 48.41, |
| 23244 | "learning_rate": 9.8134110787172e-06, |
| 23245 | "loss": 0.0178, |
| 23246 | "step": 33690 |
| 23247 | }, |
| 23248 | { |
| 23249 | "epoch": 48.42, |
| 23250 | "learning_rate": 9.725947521865889e-06, |
| 23251 | "loss": 0.0162, |
| 23252 | "step": 33700 |
| 23253 | }, |
| 23254 | { |
| 23255 | "epoch": 48.42, |
| 23256 | "eval_loss": 0.12392963469028473, |
| 23257 | "eval_runtime": 40.7699, |
| 23258 | "eval_samples_per_second": 11.209, |
| 23259 | "eval_steps_per_second": 1.423, |
| 23260 | "eval_wer": 0.11624755307935553, |
| 23261 | "step": 33700 |
| 23262 | }, |
| 23263 | { |
| 23264 | "epoch": 48.43, |
| 23265 | "learning_rate": 9.638483965014577e-06, |
| 23266 | "loss": 0.0156, |
| 23267 | "step": 33710 |
| 23268 | }, |
| 23269 | { |
| 23270 | "epoch": 48.45, |
| 23271 | "learning_rate": 9.551020408163265e-06, |
| 23272 | "loss": 0.0183, |
| 23273 | "step": 33720 |
| 23274 | }, |
| 23275 | { |
| 23276 | "epoch": 48.46, |
| 23277 | "learning_rate": 9.463556851311953e-06, |
| 23278 | "loss": 0.013, |
| 23279 | "step": 33730 |
| 23280 | }, |
| 23281 | { |
| 23282 | "epoch": 48.48, |
| 23283 | "learning_rate": 9.376093294460639e-06, |
| 23284 | "loss": 0.0163, |
| 23285 | "step": 33740 |
| 23286 | }, |
| 23287 | { |
| 23288 | "epoch": 48.49, |
| 23289 | "learning_rate": 9.288629737609328e-06, |
| 23290 | "loss": 0.017, |
| 23291 | "step": 33750 |
| 23292 | }, |
| 23293 | { |
| 23294 | "epoch": 48.51, |
| 23295 | "learning_rate": 9.201166180758016e-06, |
| 23296 | "loss": 0.0142, |
| 23297 | "step": 33760 |
| 23298 | }, |
| 23299 | { |
| 23300 | "epoch": 48.52, |
| 23301 | "learning_rate": 9.113702623906704e-06, |
| 23302 | "loss": 0.0212, |
| 23303 | "step": 33770 |
| 23304 | }, |
| 23305 | { |
| 23306 | "epoch": 48.53, |
| 23307 | "learning_rate": 9.026239067055394e-06, |
| 23308 | "loss": 0.0181, |
| 23309 | "step": 33780 |
| 23310 | }, |
| 23311 | { |
| 23312 | "epoch": 48.55, |
| 23313 | "learning_rate": 8.93877551020408e-06, |
| 23314 | "loss": 0.0258, |
| 23315 | "step": 33790 |
| 23316 | }, |
| 23317 | { |
| 23318 | "epoch": 48.56, |
| 23319 | "learning_rate": 8.851311953352768e-06, |
| 23320 | "loss": 0.0173, |
| 23321 | "step": 33800 |
| 23322 | }, |
| 23323 | { |
| 23324 | "epoch": 48.56, |
| 23325 | "eval_loss": 0.12351784110069275, |
| 23326 | "eval_runtime": 40.8564, |
| 23327 | "eval_samples_per_second": 11.186, |
| 23328 | "eval_steps_per_second": 1.42, |
| 23329 | "eval_wer": 0.11669929227525976, |
| 23330 | "step": 33800 |
| 23331 | }, |
| 23332 | { |
| 23333 | "epoch": 48.58, |
| 23334 | "learning_rate": 8.763848396501458e-06, |
| 23335 | "loss": 0.0156, |
| 23336 | "step": 33810 |
| 23337 | }, |
| 23338 | { |
| 23339 | "epoch": 48.59, |
| 23340 | "learning_rate": 8.676384839650145e-06, |
| 23341 | "loss": 0.0223, |
| 23342 | "step": 33820 |
| 23343 | }, |
| 23344 | { |
| 23345 | "epoch": 48.61, |
| 23346 | "learning_rate": 8.588921282798833e-06, |
| 23347 | "loss": 0.0157, |
| 23348 | "step": 33830 |
| 23349 | }, |
| 23350 | { |
| 23351 | "epoch": 48.62, |
| 23352 | "learning_rate": 8.501457725947521e-06, |
| 23353 | "loss": 0.0158, |
| 23354 | "step": 33840 |
| 23355 | }, |
| 23356 | { |
| 23357 | "epoch": 48.64, |
| 23358 | "learning_rate": 8.413994169096209e-06, |
| 23359 | "loss": 0.0166, |
| 23360 | "step": 33850 |
| 23361 | }, |
| 23362 | { |
| 23363 | "epoch": 48.65, |
| 23364 | "learning_rate": 8.326530612244897e-06, |
| 23365 | "loss": 0.0195, |
| 23366 | "step": 33860 |
| 23367 | }, |
| 23368 | { |
| 23369 | "epoch": 48.66, |
| 23370 | "learning_rate": 8.239067055393587e-06, |
| 23371 | "loss": 0.0182, |
| 23372 | "step": 33870 |
| 23373 | }, |
| 23374 | { |
| 23375 | "epoch": 48.68, |
| 23376 | "learning_rate": 8.151603498542273e-06, |
| 23377 | "loss": 0.0131, |
| 23378 | "step": 33880 |
| 23379 | }, |
| 23380 | { |
| 23381 | "epoch": 48.69, |
| 23382 | "learning_rate": 8.06413994169096e-06, |
| 23383 | "loss": 0.0186, |
| 23384 | "step": 33890 |
| 23385 | }, |
| 23386 | { |
| 23387 | "epoch": 48.71, |
| 23388 | "learning_rate": 7.97667638483965e-06, |
| 23389 | "loss": 0.0144, |
| 23390 | "step": 33900 |
| 23391 | }, |
| 23392 | { |
| 23393 | "epoch": 48.71, |
| 23394 | "eval_loss": 0.12300607562065125, |
| 23395 | "eval_runtime": 40.8193, |
| 23396 | "eval_samples_per_second": 11.196, |
| 23397 | "eval_steps_per_second": 1.421, |
| 23398 | "eval_wer": 0.11624755307935553, |
| 23399 | "step": 33900 |
| 23400 | }, |
| 23401 | { |
| 23402 | "epoch": 48.72, |
| 23403 | "learning_rate": 7.889212827988337e-06, |
| 23404 | "loss": 0.0113, |
| 23405 | "step": 33910 |
| 23406 | }, |
| 23407 | { |
| 23408 | "epoch": 48.74, |
| 23409 | "learning_rate": 7.801749271137026e-06, |
| 23410 | "loss": 0.0163, |
| 23411 | "step": 33920 |
| 23412 | }, |
| 23413 | { |
| 23414 | "epoch": 48.75, |
| 23415 | "learning_rate": 7.714285714285714e-06, |
| 23416 | "loss": 0.0146, |
| 23417 | "step": 33930 |
| 23418 | }, |
| 23419 | { |
| 23420 | "epoch": 48.76, |
| 23421 | "learning_rate": 7.626822157434402e-06, |
| 23422 | "loss": 0.0151, |
| 23423 | "step": 33940 |
| 23424 | }, |
| 23425 | { |
| 23426 | "epoch": 48.78, |
| 23427 | "learning_rate": 7.53935860058309e-06, |
| 23428 | "loss": 0.0229, |
| 23429 | "step": 33950 |
| 23430 | }, |
| 23431 | { |
| 23432 | "epoch": 48.79, |
| 23433 | "learning_rate": 7.451895043731778e-06, |
| 23434 | "loss": 0.0155, |
| 23435 | "step": 33960 |
| 23436 | }, |
| 23437 | { |
| 23438 | "epoch": 48.81, |
| 23439 | "learning_rate": 7.364431486880466e-06, |
| 23440 | "loss": 0.0226, |
| 23441 | "step": 33970 |
| 23442 | }, |
| 23443 | { |
| 23444 | "epoch": 48.82, |
| 23445 | "learning_rate": 7.2769679300291535e-06, |
| 23446 | "loss": 0.0172, |
| 23447 | "step": 33980 |
| 23448 | }, |
| 23449 | { |
| 23450 | "epoch": 48.84, |
| 23451 | "learning_rate": 7.189504373177842e-06, |
| 23452 | "loss": 0.0254, |
| 23453 | "step": 33990 |
| 23454 | }, |
| 23455 | { |
| 23456 | "epoch": 48.85, |
| 23457 | "learning_rate": 7.10204081632653e-06, |
| 23458 | "loss": 0.0194, |
| 23459 | "step": 34000 |
| 23460 | }, |
| 23461 | { |
| 23462 | "epoch": 48.85, |
| 23463 | "eval_loss": 0.12407871335744858, |
| 23464 | "eval_runtime": 40.7097, |
| 23465 | "eval_samples_per_second": 11.226, |
| 23466 | "eval_steps_per_second": 1.425, |
| 23467 | "eval_wer": 0.1170004517391959, |
| 23468 | "step": 34000 |
| 23469 | }, |
| 23470 | { |
| 23471 | "epoch": 48.86, |
| 23472 | "learning_rate": 7.014577259475219e-06, |
| 23473 | "loss": 0.0179, |
| 23474 | "step": 34010 |
| 23475 | }, |
| 23476 | { |
| 23477 | "epoch": 48.88, |
| 23478 | "learning_rate": 6.927113702623906e-06, |
| 23479 | "loss": 0.0244, |
| 23480 | "step": 34020 |
| 23481 | }, |
| 23482 | { |
| 23483 | "epoch": 48.89, |
| 23484 | "learning_rate": 6.839650145772594e-06, |
| 23485 | "loss": 0.0152, |
| 23486 | "step": 34030 |
| 23487 | }, |
| 23488 | { |
| 23489 | "epoch": 48.91, |
| 23490 | "learning_rate": 6.7521865889212826e-06, |
| 23491 | "loss": 0.0178, |
| 23492 | "step": 34040 |
| 23493 | }, |
| 23494 | { |
| 23495 | "epoch": 48.92, |
| 23496 | "learning_rate": 6.66472303206997e-06, |
| 23497 | "loss": 0.0164, |
| 23498 | "step": 34050 |
| 23499 | }, |
| 23500 | { |
| 23501 | "epoch": 48.94, |
| 23502 | "learning_rate": 6.577259475218658e-06, |
| 23503 | "loss": 0.0145, |
| 23504 | "step": 34060 |
| 23505 | }, |
| 23506 | { |
| 23507 | "epoch": 48.95, |
| 23508 | "learning_rate": 6.489795918367346e-06, |
| 23509 | "loss": 0.015, |
| 23510 | "step": 34070 |
| 23511 | }, |
| 23512 | { |
| 23513 | "epoch": 48.97, |
| 23514 | "learning_rate": 6.402332361516035e-06, |
| 23515 | "loss": 0.0096, |
| 23516 | "step": 34080 |
| 23517 | }, |
| 23518 | { |
| 23519 | "epoch": 48.98, |
| 23520 | "learning_rate": 6.314868804664722e-06, |
| 23521 | "loss": 0.0191, |
| 23522 | "step": 34090 |
| 23523 | }, |
| 23524 | { |
| 23525 | "epoch": 48.99, |
| 23526 | "learning_rate": 6.227405247813411e-06, |
| 23527 | "loss": 0.0164, |
| 23528 | "step": 34100 |
| 23529 | }, |
| 23530 | { |
| 23531 | "epoch": 48.99, |
| 23532 | "eval_loss": 0.12447045743465424, |
| 23533 | "eval_runtime": 40.8776, |
| 23534 | "eval_samples_per_second": 11.18, |
| 23535 | "eval_steps_per_second": 1.419, |
| 23536 | "eval_wer": 0.11745219093510013, |
| 23537 | "step": 34100 |
| 23538 | }, |
| 23539 | { |
| 23540 | "epoch": 49.01, |
| 23541 | "learning_rate": 6.139941690962099e-06, |
| 23542 | "loss": 0.0251, |
| 23543 | "step": 34110 |
| 23544 | }, |
| 23545 | { |
| 23546 | "epoch": 49.02, |
| 23547 | "learning_rate": 6.0524781341107866e-06, |
| 23548 | "loss": 0.0203, |
| 23549 | "step": 34120 |
| 23550 | }, |
| 23551 | { |
| 23552 | "epoch": 49.04, |
| 23553 | "learning_rate": 5.9650145772594745e-06, |
| 23554 | "loss": 0.0193, |
| 23555 | "step": 34130 |
| 23556 | }, |
| 23557 | { |
| 23558 | "epoch": 49.05, |
| 23559 | "learning_rate": 5.877551020408162e-06, |
| 23560 | "loss": 0.0195, |
| 23561 | "step": 34140 |
| 23562 | }, |
| 23563 | { |
| 23564 | "epoch": 49.07, |
| 23565 | "learning_rate": 5.790087463556851e-06, |
| 23566 | "loss": 0.0194, |
| 23567 | "step": 34150 |
| 23568 | }, |
| 23569 | { |
| 23570 | "epoch": 49.08, |
| 23571 | "learning_rate": 5.702623906705539e-06, |
| 23572 | "loss": 0.0212, |
| 23573 | "step": 34160 |
| 23574 | }, |
| 23575 | { |
| 23576 | "epoch": 49.09, |
| 23577 | "learning_rate": 5.615160349854228e-06, |
| 23578 | "loss": 0.0183, |
| 23579 | "step": 34170 |
| 23580 | }, |
| 23581 | { |
| 23582 | "epoch": 49.11, |
| 23583 | "learning_rate": 5.527696793002915e-06, |
| 23584 | "loss": 0.0129, |
| 23585 | "step": 34180 |
| 23586 | }, |
| 23587 | { |
| 23588 | "epoch": 49.12, |
| 23589 | "learning_rate": 5.440233236151603e-06, |
| 23590 | "loss": 0.018, |
| 23591 | "step": 34190 |
| 23592 | }, |
| 23593 | { |
| 23594 | "epoch": 49.14, |
| 23595 | "learning_rate": 5.3527696793002914e-06, |
| 23596 | "loss": 0.0144, |
| 23597 | "step": 34200 |
| 23598 | }, |
| 23599 | { |
| 23600 | "epoch": 49.14, |
| 23601 | "eval_loss": 0.1245112419128418, |
| 23602 | "eval_runtime": 41.1029, |
| 23603 | "eval_samples_per_second": 11.118, |
| 23604 | "eval_steps_per_second": 1.411, |
| 23605 | "eval_wer": 0.11609697334738744, |
| 23606 | "step": 34200 |
| 23607 | }, |
| 23608 | { |
| 23609 | "epoch": 49.15, |
| 23610 | "learning_rate": 5.2653061224489785e-06, |
| 23611 | "loss": 0.0193, |
| 23612 | "step": 34210 |
| 23613 | }, |
| 23614 | { |
| 23615 | "epoch": 49.17, |
| 23616 | "learning_rate": 5.177842565597667e-06, |
| 23617 | "loss": 0.0215, |
| 23618 | "step": 34220 |
| 23619 | }, |
| 23620 | { |
| 23621 | "epoch": 49.18, |
| 23622 | "learning_rate": 5.090379008746355e-06, |
| 23623 | "loss": 0.0131, |
| 23624 | "step": 34230 |
| 23625 | }, |
| 23626 | { |
| 23627 | "epoch": 49.2, |
| 23628 | "learning_rate": 5.002915451895044e-06, |
| 23629 | "loss": 0.0222, |
| 23630 | "step": 34240 |
| 23631 | }, |
| 23632 | { |
| 23633 | "epoch": 49.21, |
| 23634 | "learning_rate": 4.915451895043731e-06, |
| 23635 | "loss": 0.0166, |
| 23636 | "step": 34250 |
| 23637 | }, |
| 23638 | { |
| 23639 | "epoch": 49.22, |
| 23640 | "learning_rate": 4.82798833819242e-06, |
| 23641 | "loss": 0.0215, |
| 23642 | "step": 34260 |
| 23643 | }, |
| 23644 | { |
| 23645 | "epoch": 49.24, |
| 23646 | "learning_rate": 4.7405247813411076e-06, |
| 23647 | "loss": 0.014, |
| 23648 | "step": 34270 |
| 23649 | }, |
| 23650 | { |
| 23651 | "epoch": 49.25, |
| 23652 | "learning_rate": 4.6530612244897954e-06, |
| 23653 | "loss": 0.0125, |
| 23654 | "step": 34280 |
| 23655 | }, |
| 23656 | { |
| 23657 | "epoch": 49.27, |
| 23658 | "learning_rate": 4.565597667638483e-06, |
| 23659 | "loss": 0.0168, |
| 23660 | "step": 34290 |
| 23661 | }, |
| 23662 | { |
| 23663 | "epoch": 49.28, |
| 23664 | "learning_rate": 4.478134110787172e-06, |
| 23665 | "loss": 0.0209, |
| 23666 | "step": 34300 |
| 23667 | }, |
| 23668 | { |
| 23669 | "epoch": 49.28, |
| 23670 | "eval_loss": 0.12437942624092102, |
| 23671 | "eval_runtime": 40.865, |
| 23672 | "eval_samples_per_second": 11.183, |
| 23673 | "eval_steps_per_second": 1.419, |
| 23674 | "eval_wer": 0.11609697334738744, |
| 23675 | "step": 34300 |
| 23676 | }, |
| 23677 | { |
| 23678 | "epoch": 49.3, |
| 23679 | "learning_rate": 4.390670553935859e-06, |
| 23680 | "loss": 0.0158, |
| 23681 | "step": 34310 |
| 23682 | }, |
| 23683 | { |
| 23684 | "epoch": 49.31, |
| 23685 | "learning_rate": 4.303206997084548e-06, |
| 23686 | "loss": 0.0141, |
| 23687 | "step": 34320 |
| 23688 | }, |
| 23689 | { |
| 23690 | "epoch": 49.32, |
| 23691 | "learning_rate": 4.215743440233236e-06, |
| 23692 | "loss": 0.0186, |
| 23693 | "step": 34330 |
| 23694 | }, |
| 23695 | { |
| 23696 | "epoch": 49.34, |
| 23697 | "learning_rate": 4.128279883381924e-06, |
| 23698 | "loss": 0.0244, |
| 23699 | "step": 34340 |
| 23700 | }, |
| 23701 | { |
| 23702 | "epoch": 49.35, |
| 23703 | "learning_rate": 4.0408163265306116e-06, |
| 23704 | "loss": 0.0122, |
| 23705 | "step": 34350 |
| 23706 | }, |
| 23707 | { |
| 23708 | "epoch": 49.37, |
| 23709 | "learning_rate": 3.9533527696793e-06, |
| 23710 | "loss": 0.0155, |
| 23711 | "step": 34360 |
| 23712 | }, |
| 23713 | { |
| 23714 | "epoch": 49.38, |
| 23715 | "learning_rate": 3.865889212827988e-06, |
| 23716 | "loss": 0.0133, |
| 23717 | "step": 34370 |
| 23718 | }, |
| 23719 | { |
| 23720 | "epoch": 49.4, |
| 23721 | "learning_rate": 3.778425655976676e-06, |
| 23722 | "loss": 0.0131, |
| 23723 | "step": 34380 |
| 23724 | }, |
| 23725 | { |
| 23726 | "epoch": 49.41, |
| 23727 | "learning_rate": 3.690962099125364e-06, |
| 23728 | "loss": 0.0167, |
| 23729 | "step": 34390 |
| 23730 | }, |
| 23731 | { |
| 23732 | "epoch": 49.43, |
| 23733 | "learning_rate": 3.603498542274052e-06, |
| 23734 | "loss": 0.0168, |
| 23735 | "step": 34400 |
| 23736 | }, |
| 23737 | { |
| 23738 | "epoch": 49.43, |
| 23739 | "eval_loss": 0.12430938333272934, |
| 23740 | "eval_runtime": 40.7925, |
| 23741 | "eval_samples_per_second": 11.203, |
| 23742 | "eval_steps_per_second": 1.422, |
| 23743 | "eval_wer": 0.11639813281132359, |
| 23744 | "step": 34400 |
| 23745 | }, |
| 23746 | { |
| 23747 | "epoch": 49.44, |
| 23748 | "learning_rate": 3.5160349854227402e-06, |
| 23749 | "loss": 0.0211, |
| 23750 | "step": 34410 |
| 23751 | }, |
| 23752 | { |
| 23753 | "epoch": 49.45, |
| 23754 | "learning_rate": 3.428571428571428e-06, |
| 23755 | "loss": 0.0123, |
| 23756 | "step": 34420 |
| 23757 | }, |
| 23758 | { |
| 23759 | "epoch": 49.47, |
| 23760 | "learning_rate": 3.3411078717201164e-06, |
| 23761 | "loss": 0.0147, |
| 23762 | "step": 34430 |
| 23763 | }, |
| 23764 | { |
| 23765 | "epoch": 49.48, |
| 23766 | "learning_rate": 3.2536443148688043e-06, |
| 23767 | "loss": 0.0174, |
| 23768 | "step": 34440 |
| 23769 | }, |
| 23770 | { |
| 23771 | "epoch": 49.5, |
| 23772 | "learning_rate": 3.1661807580174926e-06, |
| 23773 | "loss": 0.0128, |
| 23774 | "step": 34450 |
| 23775 | }, |
| 23776 | { |
| 23777 | "epoch": 49.51, |
| 23778 | "learning_rate": 3.07871720116618e-06, |
| 23779 | "loss": 0.0208, |
| 23780 | "step": 34460 |
| 23781 | }, |
| 23782 | { |
| 23783 | "epoch": 49.53, |
| 23784 | "learning_rate": 2.9912536443148684e-06, |
| 23785 | "loss": 0.017, |
| 23786 | "step": 34470 |
| 23787 | }, |
| 23788 | { |
| 23789 | "epoch": 49.54, |
| 23790 | "learning_rate": 2.9037900874635563e-06, |
| 23791 | "loss": 0.0192, |
| 23792 | "step": 34480 |
| 23793 | }, |
| 23794 | { |
| 23795 | "epoch": 49.55, |
| 23796 | "learning_rate": 2.8163265306122447e-06, |
| 23797 | "loss": 0.0182, |
| 23798 | "step": 34490 |
| 23799 | }, |
| 23800 | { |
| 23801 | "epoch": 49.57, |
| 23802 | "learning_rate": 2.7288629737609326e-06, |
| 23803 | "loss": 0.0163, |
| 23804 | "step": 34500 |
| 23805 | }, |
| 23806 | { |
| 23807 | "epoch": 49.57, |
| 23808 | "eval_loss": 0.12417034804821014, |
| 23809 | "eval_runtime": 40.9643, |
| 23810 | "eval_samples_per_second": 11.156, |
| 23811 | "eval_steps_per_second": 1.416, |
| 23812 | "eval_wer": 0.11654871254329167, |
| 23813 | "step": 34500 |
| 23814 | }, |
| 23815 | { |
| 23816 | "epoch": 49.58, |
| 23817 | "learning_rate": 2.641399416909621e-06, |
| 23818 | "loss": 0.0283, |
| 23819 | "step": 34510 |
| 23820 | }, |
| 23821 | { |
| 23822 | "epoch": 49.6, |
| 23823 | "learning_rate": 2.5539358600583088e-06, |
| 23824 | "loss": 0.0136, |
| 23825 | "step": 34520 |
| 23826 | }, |
| 23827 | { |
| 23828 | "epoch": 49.61, |
| 23829 | "learning_rate": 2.466472303206997e-06, |
| 23830 | "loss": 0.0163, |
| 23831 | "step": 34530 |
| 23832 | }, |
| 23833 | { |
| 23834 | "epoch": 49.63, |
| 23835 | "learning_rate": 2.3790087463556846e-06, |
| 23836 | "loss": 0.0204, |
| 23837 | "step": 34540 |
| 23838 | }, |
| 23839 | { |
| 23840 | "epoch": 49.64, |
| 23841 | "learning_rate": 2.291545189504373e-06, |
| 23842 | "loss": 0.0119, |
| 23843 | "step": 34550 |
| 23844 | }, |
| 23845 | { |
| 23846 | "epoch": 49.66, |
| 23847 | "learning_rate": 2.2040816326530608e-06, |
| 23848 | "loss": 0.0162, |
| 23849 | "step": 34560 |
| 23850 | }, |
| 23851 | { |
| 23852 | "epoch": 49.67, |
| 23853 | "learning_rate": 2.116618075801749e-06, |
| 23854 | "loss": 0.0153, |
| 23855 | "step": 34570 |
| 23856 | }, |
| 23857 | { |
| 23858 | "epoch": 49.68, |
| 23859 | "learning_rate": 2.029154518950437e-06, |
| 23860 | "loss": 0.0156, |
| 23861 | "step": 34580 |
| 23862 | }, |
| 23863 | { |
| 23864 | "epoch": 49.7, |
| 23865 | "learning_rate": 1.9416909620991253e-06, |
| 23866 | "loss": 0.0153, |
| 23867 | "step": 34590 |
| 23868 | }, |
| 23869 | { |
| 23870 | "epoch": 49.71, |
| 23871 | "learning_rate": 1.8542274052478132e-06, |
| 23872 | "loss": 0.0128, |
| 23873 | "step": 34600 |
| 23874 | }, |
| 23875 | { |
| 23876 | "epoch": 49.71, |
| 23877 | "eval_loss": 0.12449096143245697, |
| 23878 | "eval_runtime": 40.8869, |
| 23879 | "eval_samples_per_second": 11.177, |
| 23880 | "eval_steps_per_second": 1.419, |
| 23881 | "eval_wer": 0.11624755307935553, |
| 23882 | "step": 34600 |
| 23883 | }, |
| 23884 | { |
| 23885 | "epoch": 49.73, |
| 23886 | "learning_rate": 1.7667638483965013e-06, |
| 23887 | "loss": 0.0219, |
| 23888 | "step": 34610 |
| 23889 | }, |
| 23890 | { |
| 23891 | "epoch": 49.74, |
| 23892 | "learning_rate": 1.6793002915451894e-06, |
| 23893 | "loss": 0.0164, |
| 23894 | "step": 34620 |
| 23895 | }, |
| 23896 | { |
| 23897 | "epoch": 49.76, |
| 23898 | "learning_rate": 1.5918367346938775e-06, |
| 23899 | "loss": 0.0118, |
| 23900 | "step": 34630 |
| 23901 | }, |
| 23902 | { |
| 23903 | "epoch": 49.77, |
| 23904 | "learning_rate": 1.5043731778425654e-06, |
| 23905 | "loss": 0.0197, |
| 23906 | "step": 34640 |
| 23907 | }, |
| 23908 | { |
| 23909 | "epoch": 49.78, |
| 23910 | "learning_rate": 1.4169096209912535e-06, |
| 23911 | "loss": 0.017, |
| 23912 | "step": 34650 |
| 23913 | }, |
| 23914 | { |
| 23915 | "epoch": 49.8, |
| 23916 | "learning_rate": 1.3294460641399416e-06, |
| 23917 | "loss": 0.0192, |
| 23918 | "step": 34660 |
| 23919 | }, |
| 23920 | { |
| 23921 | "epoch": 49.81, |
| 23922 | "learning_rate": 1.2419825072886298e-06, |
| 23923 | "loss": 0.0164, |
| 23924 | "step": 34670 |
| 23925 | }, |
| 23926 | { |
| 23927 | "epoch": 49.83, |
| 23928 | "learning_rate": 1.1545189504373177e-06, |
| 23929 | "loss": 0.0093, |
| 23930 | "step": 34680 |
| 23931 | }, |
| 23932 | { |
| 23933 | "epoch": 49.84, |
| 23934 | "learning_rate": 1.0670553935860058e-06, |
| 23935 | "loss": 0.018, |
| 23936 | "step": 34690 |
| 23937 | }, |
| 23938 | { |
| 23939 | "epoch": 49.86, |
| 23940 | "learning_rate": 9.795918367346939e-07, |
| 23941 | "loss": 0.0179, |
| 23942 | "step": 34700 |
| 23943 | }, |
| 23944 | { |
| 23945 | "epoch": 49.86, |
| 23946 | "eval_loss": 0.12448325753211975, |
| 23947 | "eval_runtime": 40.9585, |
| 23948 | "eval_samples_per_second": 11.158, |
| 23949 | "eval_steps_per_second": 1.416, |
| 23950 | "eval_wer": 0.11639813281132359, |
| 23951 | "step": 34700 |
| 23952 | }, |
| 23953 | { |
| 23954 | "epoch": 49.87, |
| 23955 | "learning_rate": 8.921282798833819e-07, |
| 23956 | "loss": 0.0174, |
| 23957 | "step": 34710 |
| 23958 | }, |
| 23959 | { |
| 23960 | "epoch": 49.89, |
| 23961 | "learning_rate": 8.0466472303207e-07, |
| 23962 | "loss": 0.0132, |
| 23963 | "step": 34720 |
| 23964 | }, |
| 23965 | { |
| 23966 | "epoch": 49.9, |
| 23967 | "learning_rate": 7.17201166180758e-07, |
| 23968 | "loss": 0.014, |
| 23969 | "step": 34730 |
| 23970 | }, |
| 23971 | { |
| 23972 | "epoch": 49.91, |
| 23973 | "learning_rate": 6.297376093294461e-07, |
| 23974 | "loss": 0.0153, |
| 23975 | "step": 34740 |
| 23976 | }, |
| 23977 | { |
| 23978 | "epoch": 49.93, |
| 23979 | "learning_rate": 5.422740524781341e-07, |
| 23980 | "loss": 0.0108, |
| 23981 | "step": 34750 |
| 23982 | }, |
| 23983 | { |
| 23984 | "epoch": 49.94, |
| 23985 | "learning_rate": 4.548104956268221e-07, |
| 23986 | "loss": 0.015, |
| 23987 | "step": 34760 |
| 23988 | }, |
| 23989 | { |
| 23990 | "epoch": 49.96, |
| 23991 | "learning_rate": 3.6734693877551015e-07, |
| 23992 | "loss": 0.0158, |
| 23993 | "step": 34770 |
| 23994 | }, |
| 23995 | { |
| 23996 | "epoch": 49.97, |
| 23997 | "learning_rate": 2.7988338192419826e-07, |
| 23998 | "loss": 0.0174, |
| 23999 | "step": 34780 |
| 24000 | }, |
| 24001 | { |
| 24002 | "epoch": 49.99, |
| 24003 | "learning_rate": 1.9241982507288626e-07, |
| 24004 | "loss": 0.0182, |
| 24005 | "step": 34790 |
| 24006 | }, |
| 24007 | { |
| 24008 | "epoch": 50.0, |
| 24009 | "learning_rate": 1.0495626822157434e-07, |
| 24010 | "loss": 0.0137, |
| 24011 | "step": 34800 |
| 24012 | }, |
| 24013 | { |
| 24014 | "epoch": 50.0, |
| 24015 | "eval_loss": 0.1244998648762703, |
| 24016 | "eval_runtime": 41.0501, |
| 24017 | "eval_samples_per_second": 11.133, |
| 24018 | "eval_steps_per_second": 1.413, |
| 24019 | "eval_wer": 0.11639813281132359, |
| 24020 | "step": 34800 |
| 24021 | } |
| 24022 | ], |
| 24023 | "max_steps": 34800, |
| 24024 | "num_train_epochs": 50, |
| 24025 | "total_flos": 2.8774580960101165e+20, |
| 24026 | "trial_name": null, |
| 24027 | "trial_params": null |
| 24028 | } |
| 24029 | |