SYX/mistral_based_claim_extractor
2160
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 2.0,5 "eval_steps": 500,6 "global_step": 5914,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.0033818058843422386,13 "grad_norm": 1.5605809688568115,14 "learning_rate": 9.991538331358945e-05,15 "loss": 1.5931,16 "step": 1017 },18 {19 "epoch": 0.006763611768684477,20 "grad_norm": 0.2704204320907593,21 "learning_rate": 9.974614994076833e-05,22 "loss": 0.6298,23 "step": 2024 },25 {26 "epoch": 0.010145417653026716,27 "grad_norm": 0.20275332033634186,28 "learning_rate": 9.957691656794721e-05,29 "loss": 0.6147,30 "step": 3031 },32 {33 "epoch": 0.013527223537368955,34 "grad_norm": 0.1859731376171112,35 "learning_rate": 9.940768319512609e-05,36 "loss": 0.5784,37 "step": 4038 },39 {40 "epoch": 0.016909029421711193,41 "grad_norm": 0.20401914417743683,42 "learning_rate": 9.923844982230497e-05,43 "loss": 0.5696,44 "step": 5045 },46 {47 "epoch": 0.020290835306053433,48 "grad_norm": 0.21193653345108032,49 "learning_rate": 9.906921644948385e-05,50 "loss": 0.565,51 "step": 6052 },53 {54 "epoch": 0.023672641190395673,55 "grad_norm": 0.20135045051574707,56 "learning_rate": 9.889998307666272e-05,57 "loss": 0.5251,58 "step": 7059 },60 {61 "epoch": 0.02705444707473791,62 "grad_norm": 0.20686441659927368,63 "learning_rate": 9.873074970384161e-05,64 "loss": 0.5295,65 "step": 8066 },67 {68 "epoch": 0.03043625295908015,69 "grad_norm": 0.20559485256671906,70 "learning_rate": 9.856151633102048e-05,71 "loss": 0.5272,72 "step": 9073 },74 {75 "epoch": 0.033818058843422386,76 "grad_norm": 0.23076851665973663,77 "learning_rate": 9.839228295819937e-05,78 "loss": 0.5284,79 "step": 10080 },81 {82 "epoch": 0.037199864727764625,83 "grad_norm": 0.21439723670482635,84 "learning_rate": 9.822304958537824e-05,85 "loss": 0.5088,86 "step": 11087 },88 {89 "epoch": 0.040581670612106865,90 "grad_norm": 0.23800402879714966,91 "learning_rate": 9.805381621255713e-05,92 "loss": 0.5123,93 "step": 12094 },95 {96 "epoch": 0.043963476496449105,97 "grad_norm": 0.2768985629081726,98 "learning_rate": 9.7884582839736e-05,99 "loss": 0.4884,100 "step": 130101 },102 {103 "epoch": 0.047345282380791345,104 "grad_norm": 0.26437142491340637,105 "learning_rate": 9.771534946691489e-05,106 "loss": 0.4748,107 "step": 140108 },109 {110 "epoch": 0.05072708826513358,111 "grad_norm": 0.2534578740596771,112 "learning_rate": 9.754611609409376e-05,113 "loss": 0.4766,114 "step": 150115 },116 {117 "epoch": 0.05410889414947582,118 "grad_norm": 0.2550220787525177,119 "learning_rate": 9.737688272127265e-05,120 "loss": 0.4613,121 "step": 160122 },123 {124 "epoch": 0.05749070003381806,125 "grad_norm": 0.2937515377998352,126 "learning_rate": 9.720764934845152e-05,127 "loss": 0.4631,128 "step": 170129 },130 {131 "epoch": 0.0608725059181603,132 "grad_norm": 0.31693148612976074,133 "learning_rate": 9.703841597563041e-05,134 "loss": 0.4454,135 "step": 180136 },137 {138 "epoch": 0.06425431180250253,139 "grad_norm": 0.3209972679615021,140 "learning_rate": 9.686918260280928e-05,141 "loss": 0.4389,142 "step": 190143 },144 {145 "epoch": 0.06763611768684477,146 "grad_norm": 0.26218757033348083,147 "learning_rate": 9.669994922998817e-05,148 "loss": 0.4393,149 "step": 200150 },151 {152 "epoch": 0.07101792357118701,153 "grad_norm": 0.23638683557510376,154 "learning_rate": 9.653071585716704e-05,155 "loss": 0.393,156 "step": 210157 },158 {159 "epoch": 0.07439972945552925,160 "grad_norm": 0.2807103395462036,161 "learning_rate": 9.636148248434593e-05,162 "loss": 0.4012,163 "step": 220164 },165 {166 "epoch": 0.07778153533987149,167 "grad_norm": 0.29169249534606934,168 "learning_rate": 9.61922491115248e-05,169 "loss": 0.4146,170 "step": 230171 },172 {173 "epoch": 0.08116334122421373,174 "grad_norm": 0.26288753747940063,175 "learning_rate": 9.602301573870369e-05,176 "loss": 0.4185,177 "step": 240178 },179 {180 "epoch": 0.08454514710855597,181 "grad_norm": 0.2438131868839264,182 "learning_rate": 9.585378236588256e-05,183 "loss": 0.3786,184 "step": 250185 },186 {187 "epoch": 0.08792695299289821,188 "grad_norm": 0.2577499449253082,189 "learning_rate": 9.568454899306143e-05,190 "loss": 0.4075,191 "step": 260192 },193 {194 "epoch": 0.09130875887724045,195 "grad_norm": 0.2468397617340088,196 "learning_rate": 9.551531562024032e-05,197 "loss": 0.382,198 "step": 270199 },200 {201 "epoch": 0.09469056476158269,202 "grad_norm": 0.27210426330566406,203 "learning_rate": 9.53460822474192e-05,204 "loss": 0.3853,205 "step": 280206 },207 {208 "epoch": 0.09807237064592493,209 "grad_norm": 0.2579999566078186,210 "learning_rate": 9.517684887459808e-05,211 "loss": 0.3816,212 "step": 290213 },214 {215 "epoch": 0.10145417653026716,216 "grad_norm": 0.24862495064735413,217 "learning_rate": 9.500761550177695e-05,218 "loss": 0.3481,219 "step": 300220 },221 {222 "epoch": 0.1048359824146094,223 "grad_norm": 0.289042204618454,224 "learning_rate": 9.483838212895584e-05,225 "loss": 0.3961,226 "step": 310227 },228 {229 "epoch": 0.10821778829895164,230 "grad_norm": 0.2919853627681732,231 "learning_rate": 9.466914875613471e-05,232 "loss": 0.3332,233 "step": 320234 },235 {236 "epoch": 0.11159959418329388,237 "grad_norm": 0.25639480352401733,238 "learning_rate": 9.44999153833136e-05,239 "loss": 0.3644,240 "step": 330241 },242 {243 "epoch": 0.11498140006763612,244 "grad_norm": 0.26778921484947205,245 "learning_rate": 9.433068201049247e-05,246 "loss": 0.3695,247 "step": 340248 },249 {250 "epoch": 0.11836320595197836,251 "grad_norm": 0.24935244023799896,252 "learning_rate": 9.416144863767136e-05,253 "loss": 0.3433,254 "step": 350255 },256 {257 "epoch": 0.1217450118363206,258 "grad_norm": 0.2668505609035492,259 "learning_rate": 9.399221526485023e-05,260 "loss": 0.3689,261 "step": 360262 },263 {264 "epoch": 0.12512681772066284,265 "grad_norm": 0.2972855865955353,266 "learning_rate": 9.382298189202912e-05,267 "loss": 0.3153,268 "step": 370269 },270 {271 "epoch": 0.12850862360500506,272 "grad_norm": 0.2680118978023529,273 "learning_rate": 9.3653748519208e-05,274 "loss": 0.3332,275 "step": 380276 },277 {278 "epoch": 0.13189042948934732,279 "grad_norm": 0.28004977107048035,280 "learning_rate": 9.348451514638688e-05,281 "loss": 0.342,282 "step": 390283 },284 {285 "epoch": 0.13527223537368954,286 "grad_norm": 0.2519853115081787,287 "learning_rate": 9.331528177356575e-05,288 "loss": 0.3194,289 "step": 400290 },291 {292 "epoch": 0.1386540412580318,293 "grad_norm": 0.2775399386882782,294 "learning_rate": 9.314604840074464e-05,295 "loss": 0.3113,296 "step": 410297 },298 {299 "epoch": 0.14203584714237402,300 "grad_norm": 0.27479955554008484,301 "learning_rate": 9.297681502792351e-05,302 "loss": 0.3148,303 "step": 420304 },305 {306 "epoch": 0.14541765302671628,307 "grad_norm": 0.3637036681175232,308 "learning_rate": 9.28075816551024e-05,309 "loss": 0.3065,310 "step": 430311 },312 {313 "epoch": 0.1487994589110585,314 "grad_norm": 0.2898998260498047,315 "learning_rate": 9.263834828228127e-05,316 "loss": 0.2799,317 "step": 440318 },319 {320 "epoch": 0.15218126479540076,321 "grad_norm": 0.295907199382782,322 "learning_rate": 9.246911490946015e-05,323 "loss": 0.2984,324 "step": 450325 },326 {327 "epoch": 0.15556307067974298,328 "grad_norm": 0.3111323118209839,329 "learning_rate": 9.229988153663903e-05,330 "loss": 0.2854,331 "step": 460332 },333 {334 "epoch": 0.1589448765640852,335 "grad_norm": 0.2768048346042633,336 "learning_rate": 9.21306481638179e-05,337 "loss": 0.2895,338 "step": 470339 },340 {341 "epoch": 0.16232668244842746,342 "grad_norm": 0.34783947467803955,343 "learning_rate": 9.19614147909968e-05,344 "loss": 0.2686,345 "step": 480346 },347 {348 "epoch": 0.1657084883327697,349 "grad_norm": 0.3182440400123596,350 "learning_rate": 9.179218141817567e-05,351 "loss": 0.2603,352 "step": 490353 },354 {355 "epoch": 0.16909029421711194,356 "grad_norm": 0.3452625572681427,357 "learning_rate": 9.162294804535455e-05,358 "loss": 0.296,359 "step": 500360 },361 {362 "epoch": 0.17247210010145417,363 "grad_norm": 0.329106867313385,364 "learning_rate": 9.145371467253343e-05,365 "loss": 0.2665,366 "step": 510367 },368 {369 "epoch": 0.17585390598579642,370 "grad_norm": 0.3779897689819336,371 "learning_rate": 9.128448129971231e-05,372 "loss": 0.2545,373 "step": 520374 },375 {376 "epoch": 0.17923571187013865,377 "grad_norm": 0.33585628867149353,378 "learning_rate": 9.111524792689119e-05,379 "loss": 0.2683,380 "step": 530381 },382 {383 "epoch": 0.1826175177544809,384 "grad_norm": 0.27421489357948303,385 "learning_rate": 9.094601455407007e-05,386 "loss": 0.2585,387 "step": 540388 },389 {390 "epoch": 0.18599932363882313,391 "grad_norm": 0.37735405564308167,392 "learning_rate": 9.077678118124895e-05,393 "loss": 0.2676,394 "step": 550395 },396 {397 "epoch": 0.18938112952316538,398 "grad_norm": 0.30768734216690063,399 "learning_rate": 9.060754780842783e-05,400 "loss": 0.2543,401 "step": 560402 },403 {404 "epoch": 0.1927629354075076,405 "grad_norm": 0.3587827682495117,406 "learning_rate": 9.04383144356067e-05,407 "loss": 0.2249,408 "step": 570409 },410 {411 "epoch": 0.19614474129184986,412 "grad_norm": 0.3213902711868286,413 "learning_rate": 9.026908106278559e-05,414 "loss": 0.2443,415 "step": 580416 },417 {418 "epoch": 0.1995265471761921,419 "grad_norm": 0.4303820729255676,420 "learning_rate": 9.009984768996447e-05,421 "loss": 0.2256,422 "step": 590423 },424 {425 "epoch": 0.2029083530605343,426 "grad_norm": 0.2948843538761139,427 "learning_rate": 8.993061431714335e-05,428 "loss": 0.2295,429 "step": 600430 },431 {432 "epoch": 0.20629015894487657,433 "grad_norm": 0.3263229727745056,434 "learning_rate": 8.976138094432223e-05,435 "loss": 0.239,436 "step": 610437 },438 {439 "epoch": 0.2096719648292188,440 "grad_norm": 0.3471197783946991,441 "learning_rate": 8.95921475715011e-05,442 "loss": 0.2227,443 "step": 620444 },445 {446 "epoch": 0.21305377071356105,447 "grad_norm": 0.3152846693992615,448 "learning_rate": 8.942291419867999e-05,449 "loss": 0.2359,450 "step": 630451 },452 {453 "epoch": 0.21643557659790327,454 "grad_norm": 0.4284135401248932,455 "learning_rate": 8.925368082585886e-05,456 "loss": 0.2453,457 "step": 640458 },459 {460 "epoch": 0.21981738248224553,461 "grad_norm": 0.37850794196128845,462 "learning_rate": 8.908444745303775e-05,463 "loss": 0.2245,464 "step": 650465 },466 {467 "epoch": 0.22319918836658775,468 "grad_norm": 0.38802939653396606,469 "learning_rate": 8.891521408021662e-05,470 "loss": 0.2227,471 "step": 660472 },473 {474 "epoch": 0.22658099425093,475 "grad_norm": 0.32752034068107605,476 "learning_rate": 8.87459807073955e-05,477 "loss": 0.2008,478 "step": 670479 },480 {481 "epoch": 0.22996280013527223,482 "grad_norm": 0.3419714570045471,483 "learning_rate": 8.857674733457438e-05,484 "loss": 0.2049,485 "step": 680486 },487 {488 "epoch": 0.2333446060196145,489 "grad_norm": 0.3725152313709259,490 "learning_rate": 8.840751396175327e-05,491 "loss": 0.1922,492 "step": 690493 },494 {495 "epoch": 0.2367264119039567,496 "grad_norm": 0.3231143653392792,497 "learning_rate": 8.823828058893214e-05,498 "loss": 0.2094,499 "step": 700500 },501 {502 "epoch": 0.24010821778829894,503 "grad_norm": 0.3786492347717285,504 "learning_rate": 8.806904721611103e-05,505 "loss": 0.1917,506 "step": 710507 },508 {509 "epoch": 0.2434900236726412,510 "grad_norm": 0.3543280363082886,511 "learning_rate": 8.78998138432899e-05,512 "loss": 0.2005,513 "step": 720514 },515 {516 "epoch": 0.24687182955698342,517 "grad_norm": 0.336761474609375,518 "learning_rate": 8.773058047046879e-05,519 "loss": 0.174,520 "step": 730521 },522 {523 "epoch": 0.2502536354413257,524 "grad_norm": 0.3629204332828522,525 "learning_rate": 8.756134709764766e-05,526 "loss": 0.1851,527 "step": 740528 },529 {530 "epoch": 0.2536354413256679,531 "grad_norm": 0.3555070459842682,532 "learning_rate": 8.739211372482655e-05,533 "loss": 0.1832,534 "step": 750535 },536 {537 "epoch": 0.2570172472100101,538 "grad_norm": 0.41113823652267456,539 "learning_rate": 8.722288035200542e-05,540 "loss": 0.1772,541 "step": 760542 },543 {544 "epoch": 0.2603990530943524,545 "grad_norm": 0.32061767578125,546 "learning_rate": 8.70536469791843e-05,547 "loss": 0.1707,548 "step": 770549 },550 {551 "epoch": 0.26378085897869463,552 "grad_norm": 0.35991913080215454,553 "learning_rate": 8.688441360636318e-05,554 "loss": 0.1487,555 "step": 780556 },557 {558 "epoch": 0.26716266486303686,559 "grad_norm": 0.3859257102012634,560 "learning_rate": 8.671518023354207e-05,561 "loss": 0.1688,562 "step": 790563 },564 {565 "epoch": 0.2705444707473791,566 "grad_norm": 0.31017613410949707,567 "learning_rate": 8.654594686072094e-05,568 "loss": 0.1624,569 "step": 800570 },571 {572 "epoch": 0.27392627663172137,573 "grad_norm": 0.35503777861595154,574 "learning_rate": 8.637671348789981e-05,575 "loss": 0.1642,576 "step": 810577 },578 {579 "epoch": 0.2773080825160636,580 "grad_norm": 0.3433260917663574,581 "learning_rate": 8.62074801150787e-05,582 "loss": 0.1844,583 "step": 820584 },585 {586 "epoch": 0.2806898884004058,587 "grad_norm": 0.3865962624549866,588 "learning_rate": 8.603824674225757e-05,589 "loss": 0.1506,590 "step": 830591 },592 {593 "epoch": 0.28407169428474804,594 "grad_norm": 0.3324780762195587,595 "learning_rate": 8.586901336943646e-05,596 "loss": 0.1632,597 "step": 840598 },599 {600 "epoch": 0.28745350016909027,601 "grad_norm": 0.4064556062221527,602 "learning_rate": 8.569977999661533e-05,603 "loss": 0.1519,604 "step": 850605 },606 {607 "epoch": 0.29083530605343255,608 "grad_norm": 0.3946615159511566,609 "learning_rate": 8.553054662379422e-05,610 "loss": 0.157,611 "step": 860612 },613 {614 "epoch": 0.2942171119377748,615 "grad_norm": 0.3700334429740906,616 "learning_rate": 8.536131325097309e-05,617 "loss": 0.141,618 "step": 870619 },620 {621 "epoch": 0.297598917822117,622 "grad_norm": 0.420950710773468,623 "learning_rate": 8.519207987815198e-05,624 "loss": 0.1488,625 "step": 880626 },627 {628 "epoch": 0.30098072370645923,629 "grad_norm": 0.39633265137672424,630 "learning_rate": 8.502284650533085e-05,631 "loss": 0.1545,632 "step": 890633 },634 {635 "epoch": 0.3043625295908015,636 "grad_norm": 0.38442814350128174,637 "learning_rate": 8.485361313250974e-05,638 "loss": 0.141,639 "step": 900640 },641 {642 "epoch": 0.30774433547514374,643 "grad_norm": 0.41429537534713745,644 "learning_rate": 8.468437975968861e-05,645 "loss": 0.144,646 "step": 910647 },648 {649 "epoch": 0.31112614135948596,650 "grad_norm": 0.3561369478702545,651 "learning_rate": 8.45151463868675e-05,652 "loss": 0.134,653 "step": 920654 },655 {656 "epoch": 0.3145079472438282,657 "grad_norm": 0.3710062801837921,658 "learning_rate": 8.434591301404637e-05,659 "loss": 0.1457,660 "step": 930661 },662 {663 "epoch": 0.3178897531281704,664 "grad_norm": 0.3607446849346161,665 "learning_rate": 8.417667964122526e-05,666 "loss": 0.122,667 "step": 940668 },669 {670 "epoch": 0.3212715590125127,671 "grad_norm": 0.34604352712631226,672 "learning_rate": 8.400744626840413e-05,673 "loss": 0.1414,674 "step": 950675 },676 {677 "epoch": 0.3246533648968549,678 "grad_norm": 0.27822059392929077,679 "learning_rate": 8.383821289558302e-05,680 "loss": 0.1281,681 "step": 960682 },683 {684 "epoch": 0.32803517078119715,685 "grad_norm": 0.38080519437789917,686 "learning_rate": 8.366897952276189e-05,687 "loss": 0.1392,688 "step": 970689 },690 {691 "epoch": 0.3314169766655394,692 "grad_norm": 0.4061764180660248,693 "learning_rate": 8.349974614994078e-05,694 "loss": 0.1179,695 "step": 980696 },697 {698 "epoch": 0.33479878254988166,699 "grad_norm": 0.28504157066345215,700 "learning_rate": 8.333051277711965e-05,701 "loss": 0.1284,702 "step": 990703 },704 {705 "epoch": 0.3381805884342239,706 "grad_norm": 0.3242844343185425,707 "learning_rate": 8.316127940429852e-05,708 "loss": 0.1184,709 "step": 1000710 },711 {712 "epoch": 0.3415623943185661,713 "grad_norm": 0.3317604064941406,714 "learning_rate": 8.299204603147741e-05,715 "loss": 0.13,716 "step": 1010717 },718 {719 "epoch": 0.34494420020290834,720 "grad_norm": 0.39583227038383484,721 "learning_rate": 8.282281265865628e-05,722 "loss": 0.1146,723 "step": 1020724 },725 {726 "epoch": 0.3483260060872506,727 "grad_norm": 0.33169683814048767,728 "learning_rate": 8.265357928583517e-05,729 "loss": 0.1162,730 "step": 1030731 },732 {733 "epoch": 0.35170781197159284,734 "grad_norm": 0.38136041164398193,735 "learning_rate": 8.248434591301404e-05,736 "loss": 0.1268,737 "step": 1040738 },739 {740 "epoch": 0.35508961785593507,741 "grad_norm": 0.28301218152046204,742 "learning_rate": 8.231511254019293e-05,743 "loss": 0.1117,744 "step": 1050745 },746 {747 "epoch": 0.3584714237402773,748 "grad_norm": 0.3950181007385254,749 "learning_rate": 8.21458791673718e-05,750 "loss": 0.1172,751 "step": 1060752 },753 {754 "epoch": 0.3618532296246195,755 "grad_norm": 0.40106379985809326,756 "learning_rate": 8.197664579455069e-05,757 "loss": 0.1134,758 "step": 1070759 },760 {761 "epoch": 0.3652350355089618,762 "grad_norm": 0.3036629259586334,763 "learning_rate": 8.180741242172956e-05,764 "loss": 0.0977,765 "step": 1080766 },767 {768 "epoch": 0.36861684139330403,769 "grad_norm": 0.35834598541259766,770 "learning_rate": 8.163817904890845e-05,771 "loss": 0.1226,772 "step": 1090773 },774 {775 "epoch": 0.37199864727764625,776 "grad_norm": 0.3107944130897522,777 "learning_rate": 8.146894567608732e-05,778 "loss": 0.0932,779 "step": 1100780 },781 {782 "epoch": 0.3753804531619885,783 "grad_norm": 0.2708600163459778,784 "learning_rate": 8.129971230326621e-05,785 "loss": 0.1071,786 "step": 1110787 },788 {789 "epoch": 0.37876225904633076,790 "grad_norm": 0.3161390721797943,791 "learning_rate": 8.113047893044508e-05,792 "loss": 0.0951,793 "step": 1120794 },795 {796 "epoch": 0.382144064930673,797 "grad_norm": 0.2967537045478821,798 "learning_rate": 8.096124555762397e-05,799 "loss": 0.0961,800 "step": 1130801 },802 {803 "epoch": 0.3855258708150152,804 "grad_norm": 0.3615525960922241,805 "learning_rate": 8.079201218480284e-05,806 "loss": 0.0955,807 "step": 1140808 },809 {810 "epoch": 0.38890767669935744,811 "grad_norm": 0.33469459414482117,812 "learning_rate": 8.062277881198173e-05,813 "loss": 0.1028,814 "step": 1150815 },816 {817 "epoch": 0.3922894825836997,818 "grad_norm": 0.44299551844596863,819 "learning_rate": 8.04535454391606e-05,820 "loss": 0.1065,821 "step": 1160822 },823 {824 "epoch": 0.39567128846804195,825 "grad_norm": 0.3324688971042633,826 "learning_rate": 8.028431206633949e-05,827 "loss": 0.1026,828 "step": 1170829 },830 {831 "epoch": 0.3990530943523842,832 "grad_norm": 0.3845025599002838,833 "learning_rate": 8.011507869351836e-05,834 "loss": 0.1166,835 "step": 1180836 },837 {838 "epoch": 0.4024349002367264,839 "grad_norm": 0.36462751030921936,840 "learning_rate": 7.994584532069724e-05,841 "loss": 0.0955,842 "step": 1190843 },844 {845 "epoch": 0.4058167061210686,846 "grad_norm": 0.33478081226348877,847 "learning_rate": 7.977661194787612e-05,848 "loss": 0.0966,849 "step": 1200850 },851 {852 "epoch": 0.4091985120054109,853 "grad_norm": 0.3839697539806366,854 "learning_rate": 7.9607378575055e-05,855 "loss": 0.1011,856 "step": 1210857 },858 {859 "epoch": 0.41258031788975313,860 "grad_norm": 0.33828845620155334,861 "learning_rate": 7.943814520223388e-05,862 "loss": 0.094,863 "step": 1220864 },865 {866 "epoch": 0.41596212377409536,867 "grad_norm": 0.35532712936401367,868 "learning_rate": 7.926891182941276e-05,869 "loss": 0.0771,870 "step": 1230871 },872 {873 "epoch": 0.4193439296584376,874 "grad_norm": 0.32812246680259705,875 "learning_rate": 7.909967845659164e-05,876 "loss": 0.0931,877 "step": 1240878 },879 {880 "epoch": 0.42272573554277987,881 "grad_norm": 0.4312772750854492,882 "learning_rate": 7.893044508377052e-05,883 "loss": 0.091,884 "step": 1250885 },886 {887 "epoch": 0.4261075414271221,888 "grad_norm": 0.38822853565216064,889 "learning_rate": 7.87612117109494e-05,890 "loss": 0.0936,891 "step": 1260892 },893 {894 "epoch": 0.4294893473114643,895 "grad_norm": 0.30626174807548523,896 "learning_rate": 7.859197833812828e-05,897 "loss": 0.0773,898 "step": 1270899 },900 {901 "epoch": 0.43287115319580655,902 "grad_norm": 0.36472904682159424,903 "learning_rate": 7.842274496530716e-05,904 "loss": 0.0776,905 "step": 1280906 },907 {908 "epoch": 0.43625295908014877,909 "grad_norm": 0.312610000371933,910 "learning_rate": 7.825351159248604e-05,911 "loss": 0.0882,912 "step": 1290913 },914 {915 "epoch": 0.43963476496449105,916 "grad_norm": 0.34325119853019714,917 "learning_rate": 7.808427821966492e-05,918 "loss": 0.0836,919 "step": 1300920 },921 {922 "epoch": 0.4430165708488333,923 "grad_norm": 0.39519986510276794,924 "learning_rate": 7.79150448468438e-05,925 "loss": 0.084,926 "step": 1310927 },928 {929 "epoch": 0.4463983767331755,930 "grad_norm": 0.35263752937316895,931 "learning_rate": 7.774581147402268e-05,932 "loss": 0.0713,933 "step": 1320934 },935 {936 "epoch": 0.44978018261751773,937 "grad_norm": 0.36037376523017883,938 "learning_rate": 7.757657810120156e-05,939 "loss": 0.069,940 "step": 1330941 },942 {943 "epoch": 0.45316198850186,944 "grad_norm": 0.38161391019821167,945 "learning_rate": 7.740734472838044e-05,946 "loss": 0.0693,947 "step": 1340948 },949 {950 "epoch": 0.45654379438620224,951 "grad_norm": 0.3896481394767761,952 "learning_rate": 7.723811135555932e-05,953 "loss": 0.0793,954 "step": 1350955 },956 {957 "epoch": 0.45992560027054447,958 "grad_norm": 0.3284771740436554,959 "learning_rate": 7.70688779827382e-05,960 "loss": 0.0874,961 "step": 1360962 },963 {964 "epoch": 0.4633074061548867,965 "grad_norm": 0.3116714358329773,966 "learning_rate": 7.689964460991708e-05,967 "loss": 0.0734,968 "step": 1370969 },970 {971 "epoch": 0.466689212039229,972 "grad_norm": 0.29977601766586304,973 "learning_rate": 7.673041123709595e-05,974 "loss": 0.0696,975 "step": 1380976 },977 {978 "epoch": 0.4700710179235712,979 "grad_norm": 0.30298420786857605,980 "learning_rate": 7.656117786427484e-05,981 "loss": 0.0755,982 "step": 1390983 },984 {985 "epoch": 0.4734528238079134,986 "grad_norm": 0.3856925368309021,987 "learning_rate": 7.639194449145371e-05,988 "loss": 0.0791,989 "step": 1400990 },991 {992 "epoch": 0.47683462969225565,993 "grad_norm": 0.3421929180622101,994 "learning_rate": 7.62227111186326e-05,995 "loss": 0.0674,996 "step": 1410997 },998 {999 "epoch": 0.4802164355765979,1000 "grad_norm": 0.3304542899131775,1001 "learning_rate": 7.605347774581147e-05,1002 "loss": 0.076,1003 "step": 14201004 },1005 {1006 "epoch": 0.48359824146094016,1007 "grad_norm": 0.29870203137397766,1008 "learning_rate": 7.588424437299036e-05,1009 "loss": 0.0703,1010 "step": 14301011 },1012 {1013 "epoch": 0.4869800473452824,1014 "grad_norm": 0.2472551167011261,1015 "learning_rate": 7.571501100016923e-05,1016 "loss": 0.069,1017 "step": 14401018 },1019 {1020 "epoch": 0.4903618532296246,1021 "grad_norm": 0.2860611081123352,1022 "learning_rate": 7.554577762734812e-05,1023 "loss": 0.0667,1024 "step": 14501025 },1026 {1027 "epoch": 0.49374365911396684,1028 "grad_norm": 0.3618302345275879,1029 "learning_rate": 7.537654425452699e-05,1030 "loss": 0.0597,1031 "step": 14601032 },1033 {1034 "epoch": 0.4971254649983091,1035 "grad_norm": 0.34842416644096375,1036 "learning_rate": 7.520731088170588e-05,1037 "loss": 0.0715,1038 "step": 14701039 },1040 {1041 "epoch": 0.5005072708826513,1042 "grad_norm": 0.2862137258052826,1043 "learning_rate": 7.503807750888475e-05,1044 "loss": 0.0778,1045 "step": 14801046 },1047 {1048 "epoch": 0.5038890767669936,1049 "grad_norm": 0.3283160626888275,1050 "learning_rate": 7.486884413606364e-05,1051 "loss": 0.073,1052 "step": 14901053 },1054 {1055 "epoch": 0.5072708826513358,1056 "grad_norm": 0.2540145218372345,1057 "learning_rate": 7.469961076324251e-05,1058 "loss": 0.067,1059 "step": 15001060 },1061 {1062 "epoch": 0.510652688535678,1063 "grad_norm": 0.32044336199760437,1064 "learning_rate": 7.45303773904214e-05,1065 "loss": 0.063,1066 "step": 15101067 },1068 {1069 "epoch": 0.5140344944200202,1070 "grad_norm": 0.3898891508579254,1071 "learning_rate": 7.436114401760027e-05,1072 "loss": 0.0695,1073 "step": 15201074 },1075 {1076 "epoch": 0.5174163003043625,1077 "grad_norm": 0.30922603607177734,1078 "learning_rate": 7.419191064477916e-05,1079 "loss": 0.071,1080 "step": 15301081 },1082 {1083 "epoch": 0.5207981061887048,1084 "grad_norm": 0.3513735234737396,1085 "learning_rate": 7.402267727195803e-05,1086 "loss": 0.0722,1087 "step": 15401088 },1089 {1090 "epoch": 0.524179912073047,1091 "grad_norm": 0.2806611955165863,1092 "learning_rate": 7.38534438991369e-05,1093 "loss": 0.0662,1094 "step": 15501095 },1096 {1097 "epoch": 0.5275617179573893,1098 "grad_norm": 0.32641470432281494,1099 "learning_rate": 7.368421052631579e-05,1100 "loss": 0.0645,1101 "step": 15601102 },1103 {1104 "epoch": 0.5309435238417315,1105 "grad_norm": 0.2627265751361847,1106 "learning_rate": 7.351497715349466e-05,1107 "loss": 0.0594,1108 "step": 15701109 },1110 {1111 "epoch": 0.5343253297260737,1112 "grad_norm": 0.2586800158023834,1113 "learning_rate": 7.334574378067355e-05,1114 "loss": 0.0603,1115 "step": 15801116 },1117 {1118 "epoch": 0.5377071356104159,1119 "grad_norm": 0.24359896779060364,1120 "learning_rate": 7.317651040785242e-05,1121 "loss": 0.0638,1122 "step": 15901123 },1124 {1125 "epoch": 0.5410889414947582,1126 "grad_norm": 0.3084506392478943,1127 "learning_rate": 7.300727703503131e-05,1128 "loss": 0.0658,1129 "step": 16001130 },1131 {1132 "epoch": 0.5444707473791004,1133 "grad_norm": 0.29731103777885437,1134 "learning_rate": 7.283804366221018e-05,1135 "loss": 0.0548,1136 "step": 16101137 },1138 {1139 "epoch": 0.5478525532634427,1140 "grad_norm": 0.25320005416870117,1141 "learning_rate": 7.266881028938907e-05,1142 "loss": 0.0533,1143 "step": 16201144 },1145 {1146 "epoch": 0.551234359147785,1147 "grad_norm": 0.274166077375412,1148 "learning_rate": 7.249957691656794e-05,1149 "loss": 0.048,1150 "step": 16301151 },1152 {1153 "epoch": 0.5546161650321272,1154 "grad_norm": 0.29488497972488403,1155 "learning_rate": 7.233034354374683e-05,1156 "loss": 0.054,1157 "step": 16401158 },1159 {1160 "epoch": 0.5579979709164694,1161 "grad_norm": 0.2893562316894531,1162 "learning_rate": 7.21611101709257e-05,1163 "loss": 0.0589,1164 "step": 16501165 },1166 {1167 "epoch": 0.5613797768008116,1168 "grad_norm": 0.29615455865859985,1169 "learning_rate": 7.199187679810459e-05,1170 "loss": 0.0524,1171 "step": 16601172 },1173 {1174 "epoch": 0.5647615826851539,1175 "grad_norm": 0.3037727475166321,1176 "learning_rate": 7.182264342528346e-05,1177 "loss": 0.0486,1178 "step": 16701179 },1180 {1181 "epoch": 0.5681433885694961,1182 "grad_norm": 0.2997746765613556,1183 "learning_rate": 7.165341005246235e-05,1184 "loss": 0.047,1185 "step": 16801186 },1187 {1188 "epoch": 0.5715251944538383,1189 "grad_norm": 0.31440579891204834,1190 "learning_rate": 7.148417667964122e-05,1191 "loss": 0.0467,1192 "step": 16901193 },1194 {1195 "epoch": 0.5749070003381805,1196 "grad_norm": 0.345804363489151,1197 "learning_rate": 7.131494330682011e-05,1198 "loss": 0.0543,1199 "step": 17001200 },