rumike7/cadquery_create_basic_forms
03
1{2 "best_global_step": null,3 "best_metric": null,4 "best_model_checkpoint": null,5 "epoch": 9.547446153846154,6 "eval_steps": 500,7 "global_step": 19400,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.32,14 "grad_norm": 0.48755398392677307,15 "learning_rate": 9e-06,16 "loss": 2.9601,17 "mean_token_accuracy": 0.4284199851565063,18 "num_tokens": 15763.0,19 "step": 1020 },21 {22 "epoch": 0.64,23 "grad_norm": 0.7431631088256836,24 "learning_rate": 1.9e-05,25 "loss": 3.1197,26 "mean_token_accuracy": 0.42047689845785496,27 "num_tokens": 30510.0,28 "step": 2029 },30 {31 "epoch": 0.96,32 "grad_norm": 0.9281144142150879,33 "learning_rate": 1.9999959867760483e-05,34 "loss": 3.0392,35 "mean_token_accuracy": 0.41553077606949956,36 "num_tokens": 44066.0,37 "step": 3038 },39 {40 "epoch": 1.256,41 "grad_norm": 1.2322081327438354,42 "learning_rate": 1.999982113944484e-05,43 "loss": 3.3331,44 "mean_token_accuracy": 0.4135566469583962,45 "num_tokens": 58784.0,46 "step": 4047 },48 {49 "epoch": 1.576,50 "grad_norm": 7.1544270515441895,51 "learning_rate": 1.9999583320967683e-05,52 "loss": 3.092,53 "mean_token_accuracy": 0.42304785093292596,54 "num_tokens": 74305.0,55 "step": 5056 },57 {58 "epoch": 1.896,59 "grad_norm": 0.8600693345069885,60 "learning_rate": 1.99992464146856e-05,61 "loss": 2.8575,62 "mean_token_accuracy": 0.4428128655999899,63 "num_tokens": 88582.0,64 "step": 6065 },66 {67 "epoch": 2.192,68 "grad_norm": 1.3089476823806763,69 "learning_rate": 1.999881042393706e-05,70 "loss": 3.2266,71 "mean_token_accuracy": 0.43124929654437144,72 "num_tokens": 101701.0,73 "step": 7074 },75 {76 "epoch": 2.512,77 "grad_norm": 0.6948946714401245,78 "learning_rate": 1.9998275353042377e-05,79 "loss": 2.6626,80 "mean_token_accuracy": 0.45563504602760074,81 "num_tokens": 116845.0,82 "step": 8083 },84 {85 "epoch": 2.832,86 "grad_norm": 1.0951130390167236,87 "learning_rate": 1.999764120730368e-05,88 "loss": 2.6061,89 "mean_token_accuracy": 0.4799388902261853,90 "num_tokens": 131642.0,91 "step": 9092 },93 {94 "epoch": 3.128,95 "grad_norm": 2.2256667613983154,96 "learning_rate": 1.9996907993004836e-05,97 "loss": 2.5437,98 "mean_token_accuracy": 0.4792116602530351,99 "num_tokens": 144071.0,100 "step": 100101 },102 {103 "epoch": 3.448,104 "grad_norm": 1.3083274364471436,105 "learning_rate": 1.9996075717411405e-05,106 "loss": 2.3134,107 "mean_token_accuracy": 0.49251377964392307,108 "num_tokens": 160671.0,109 "step": 110110 },111 {112 "epoch": 3.768,113 "grad_norm": 1.0546499490737915,114 "learning_rate": 1.9995144388770577e-05,115 "loss": 2.5219,116 "mean_token_accuracy": 0.49237193521112205,117 "num_tokens": 174208.0,118 "step": 120119 },120 {121 "epoch": 4.064,122 "grad_norm": 1.3395127058029175,123 "learning_rate": 1.9994114016311053e-05,124 "loss": 2.6405,125 "mean_token_accuracy": 0.494740814977401,126 "num_tokens": 189174.0,127 "step": 130128 },129 {130 "epoch": 4.384,131 "grad_norm": 0.9926703572273254,132 "learning_rate": 1.9992984610243006e-05,133 "loss": 2.2636,134 "mean_token_accuracy": 0.5148700190708041,135 "num_tokens": 205614.0,136 "step": 140137 },138 {139 "epoch": 4.704,140 "grad_norm": 2.0030810832977295,141 "learning_rate": 1.9991756181757936e-05,142 "loss": 2.2209,143 "mean_token_accuracy": 0.5199183862656355,144 "num_tokens": 220053.0,145 "step": 150146 },147 {148 "epoch": 5.0,149 "grad_norm": 3.6073784828186035,150 "learning_rate": 1.999042874302857e-05,151 "loss": 2.3257,152 "mean_token_accuracy": 0.5087871091389978,153 "num_tokens": 232090.0,154 "step": 160155 },156 {157 "epoch": 5.32,158 "grad_norm": 0.9835549592971802,159 "learning_rate": 1.9989002307208767e-05,160 "loss": 2.0461,161 "mean_token_accuracy": 0.5411571308970451,162 "num_tokens": 247494.0,163 "step": 170164 },165 {166 "epoch": 5.64,167 "grad_norm": 1.3350774049758911,168 "learning_rate": 1.998747688843335e-05,169 "loss": 2.1222,170 "mean_token_accuracy": 0.5401662968099117,171 "num_tokens": 261394.0,172 "step": 180173 },174 {175 "epoch": 5.96,176 "grad_norm": 1.4606289863586426,177 "learning_rate": 1.9985852501817985e-05,178 "loss": 2.0423,179 "mean_token_accuracy": 0.5442505508661271,180 "num_tokens": 276061.0,181 "step": 190182 },183 {184 "epoch": 6.256,185 "grad_norm": 2.1242387294769287,186 "learning_rate": 1.998412916345904e-05,187 "loss": 2.1295,188 "mean_token_accuracy": 0.5391830210951535,189 "num_tokens": 289693.0,190 "step": 200191 },192 {193 "epoch": 6.576,194 "grad_norm": 1.4135829210281372,195 "learning_rate": 1.99823068904334e-05,196 "loss": 1.9505,197 "mean_token_accuracy": 0.5633615963160992,198 "num_tokens": 304290.0,199 "step": 210200 },201 {202 "epoch": 6.896,203 "grad_norm": 1.05637526512146,204 "learning_rate": 1.998038570079833e-05,205 "loss": 2.0059,206 "mean_token_accuracy": 0.569461640715599,207 "num_tokens": 319354.0,208 "step": 220209 },210 {211 "epoch": 7.192,212 "grad_norm": 1.409026026725769,213 "learning_rate": 1.9978365613591263e-05,214 "loss": 1.8998,215 "mean_token_accuracy": 0.5667525610408267,216 "num_tokens": 333444.0,217 "step": 230218 },219 {220 "epoch": 7.5120000000000005,221 "grad_norm": 0.9068111181259155,222 "learning_rate": 1.9976246648829636e-05,223 "loss": 1.6992,224 "mean_token_accuracy": 0.6070717331022024,225 "num_tokens": 349035.0,226 "step": 240227 },228 {229 "epoch": 7.832,230 "grad_norm": 1.7179079055786133,231 "learning_rate": 1.997402882751068e-05,232 "loss": 1.898,233 "mean_token_accuracy": 0.5741809576749801,234 "num_tokens": 363648.0,235 "step": 250236 },237 {238 "epoch": 8.128,239 "grad_norm": 2.5260181427001953,240 "learning_rate": 1.997171217161122e-05,241 "loss": 1.8262,242 "mean_token_accuracy": 0.6014102785973936,243 "num_tokens": 377215.0,244 "step": 260245 },246 {247 "epoch": 8.448,248 "grad_norm": 1.0469582080841064,249 "learning_rate": 1.996929670408744e-05,250 "loss": 1.7423,251 "mean_token_accuracy": 0.6009339291602374,252 "num_tokens": 394237.0,253 "step": 270254 },255 {256 "epoch": 8.768,257 "grad_norm": 2.0109641551971436,258 "learning_rate": 1.996678244887468e-05,259 "loss": 1.844,260 "mean_token_accuracy": 0.5853462919592858,261 "num_tokens": 407239.0,262 "step": 280263 },264 {265 "epoch": 9.064,266 "grad_norm": 2.3061084747314453,267 "learning_rate": 1.9964169430887174e-05,268 "loss": 1.7935,269 "mean_token_accuracy": 0.5961252535517151,270 "num_tokens": 420770.0,271 "step": 290272 },273 {274 "epoch": 9.384,275 "grad_norm": 1.5985437631607056,276 "learning_rate": 1.9961457676017833e-05,277 "loss": 1.703,278 "mean_token_accuracy": 0.6001830734312534,279 "num_tokens": 435005.0,280 "step": 300281 },282 {283 "epoch": 9.704,284 "grad_norm": 1.0775606632232666,285 "learning_rate": 1.9958647211137952e-05,286 "loss": 1.7104,287 "mean_token_accuracy": 0.6070772130973637,288 "num_tokens": 449192.0,289 "step": 310290 },291 {292 "epoch": 10.0,293 "grad_norm": 4.900282859802246,294 "learning_rate": 1.9955738064096975e-05,295 "loss": 1.7131,296 "mean_token_accuracy": 0.6122549969602276,297 "num_tokens": 464180.0,298 "step": 320299 },300 {301 "epoch": 10.32,302 "grad_norm": 4.266648769378662,303 "learning_rate": 1.9952730263722205e-05,304 "loss": 1.6526,305 "mean_token_accuracy": 0.6316778633743525,306 "num_tokens": 480765.0,307 "step": 330308 },309 {310 "epoch": 10.64,311 "grad_norm": 1.3835431337356567,312 "learning_rate": 1.994962383981851e-05,313 "loss": 1.5473,314 "mean_token_accuracy": 0.6267588481307029,315 "num_tokens": 495929.0,316 "step": 340317 },318 {319 "epoch": 10.96,320 "grad_norm": 0.9430285096168518,321 "learning_rate": 1.9946418823168053e-05,322 "loss": 1.7158,323 "mean_token_accuracy": 0.6107403030619025,324 "num_tokens": 508555.0,325 "step": 350326 },327 {328 "epoch": 11.256,329 "grad_norm": 1.7163220643997192,330 "learning_rate": 1.994311524552996e-05,331 "loss": 1.557,332 "mean_token_accuracy": 0.6259392479787002,333 "num_tokens": 522011.0,334 "step": 360335 },336 {337 "epoch": 11.576,338 "grad_norm": 1.8388807773590088,339 "learning_rate": 1.993971313964002e-05,340 "loss": 1.6451,341 "mean_token_accuracy": 0.6252246461808681,342 "num_tokens": 535811.0,343 "step": 370344 },345 {346 "epoch": 11.896,347 "grad_norm": 2.878235101699829,348 "learning_rate": 1.993621253921036e-05,349 "loss": 1.6015,350 "mean_token_accuracy": 0.6341628909111023,351 "num_tokens": 551848.0,352 "step": 380353 },354 {355 "epoch": 12.192,356 "grad_norm": 8.73257064819336,357 "learning_rate": 1.9932613478929103e-05,358 "loss": 1.6087,359 "mean_token_accuracy": 0.6341016663087381,360 "num_tokens": 566187.0,361 "step": 390362 },363 {364 "epoch": 12.512,365 "grad_norm": 1.6711736917495728,366 "learning_rate": 1.9928915994460037e-05,367 "loss": 1.4662,368 "mean_token_accuracy": 0.641170359775424,369 "num_tokens": 579340.0,370 "step": 400371 },372 {373 "epoch": 12.832,374 "grad_norm": 1.2355554103851318,375 "learning_rate": 1.9925120122442253e-05,376 "loss": 1.4234,377 "mean_token_accuracy": 0.6438105596229434,378 "num_tokens": 595449.0,379 "step": 410380 },381 {382 "epoch": 13.128,383 "grad_norm": 1.1492340564727783,384 "learning_rate": 1.9921225900489776e-05,385 "loss": 1.5106,386 "mean_token_accuracy": 0.6468948456081184,387 "num_tokens": 610726.0,388 "step": 420389 },390 {391 "epoch": 13.448,392 "grad_norm": 2.4454128742218018,393 "learning_rate": 1.9917233367191205e-05,394 "loss": 1.4301,395 "mean_token_accuracy": 0.6485198132693768,396 "num_tokens": 624770.0,397 "step": 430398 },399 {400 "epoch": 13.768,401 "grad_norm": 1.809606909751892,402 "learning_rate": 1.9913142562109328e-05,403 "loss": 1.4744,404 "mean_token_accuracy": 0.656716751307249,405 "num_tokens": 640635.0,406 "step": 440407 },408 {409 "epoch": 14.064,410 "grad_norm": 1.8572089672088623,411 "learning_rate": 1.990895352578072e-05,412 "loss": 1.4747,413 "mean_token_accuracy": 0.6568980690192532,414 "num_tokens": 652969.0,415 "step": 450416 },417 {418 "epoch": 14.384,419 "grad_norm": 1.4431779384613037,420 "learning_rate": 1.9904666299715357e-05,421 "loss": 1.3779,422 "mean_token_accuracy": 0.6651028156280517,423 "num_tokens": 667518.0,424 "step": 460425 },426 {427 "epoch": 14.704,428 "grad_norm": 1.1659435033798218,429 "learning_rate": 1.9900280926396186e-05,430 "loss": 1.4853,431 "mean_token_accuracy": 0.6542218446731567,432 "num_tokens": 682093.0,433 "step": 470434 },435 {436 "epoch": 15.0,437 "grad_norm": 2.4632649421691895,438 "learning_rate": 1.989579744927872e-05,439 "loss": 1.5292,440 "mean_token_accuracy": 0.6373760857292123,441 "num_tokens": 696270.0,442 "step": 480443 },444 {445 "epoch": 15.32,446 "grad_norm": 1.2648308277130127,447 "learning_rate": 1.98912159127906e-05,448 "loss": 1.5282,449 "mean_token_accuracy": 0.6369021199643612,450 "num_tokens": 711645.0,451 "step": 490452 },453 {454 "epoch": 15.64,455 "grad_norm": 1.6591901779174805,456 "learning_rate": 1.988653636233116e-05,457 "loss": 1.3674,458 "mean_token_accuracy": 0.6757966171950102,459 "num_tokens": 724986.0,460 "step": 500461 },462 {463 "epoch": 15.96,464 "grad_norm": 1.3664172887802124,465 "learning_rate": 1.988175884427097e-05,466 "loss": 1.3619,467 "mean_token_accuracy": 0.6697750940918923,468 "num_tokens": 740314.0,469 "step": 510470 },471 {472 "epoch": 16.256,473 "grad_norm": 1.3944075107574463,474 "learning_rate": 1.9876883405951378e-05,475 "loss": 1.4199,476 "mean_token_accuracy": 0.6569653801821373,477 "num_tokens": 754126.0,478 "step": 520479 },480 {481 "epoch": 16.576,482 "grad_norm": 1.846074104309082,483 "learning_rate": 1.987191009568405e-05,484 "loss": 1.3542,485 "mean_token_accuracy": 0.6702545773237943,486 "num_tokens": 770447.0,487 "step": 530488 },489 {490 "epoch": 16.896,491 "grad_norm": 1.4818017482757568,492 "learning_rate": 1.9866838962750473e-05,493 "loss": 1.3385,494 "mean_token_accuracy": 0.673089163005352,495 "num_tokens": 784145.0,496 "step": 540497 },498 {499 "epoch": 17.192,500 "grad_norm": 1.6503247022628784,501 "learning_rate": 1.986167005740149e-05,502 "loss": 1.4058,503 "mean_token_accuracy": 0.6697660020074329,504 "num_tokens": 797632.0,505 "step": 550506 },507 {508 "epoch": 17.512,509 "grad_norm": 1.7759121656417847,510 "learning_rate": 1.985640343085678e-05,511 "loss": 1.485,512 "mean_token_accuracy": 0.6630586348474026,513 "num_tokens": 812748.0,514 "step": 560515 },516 {517 "epoch": 17.832,518 "grad_norm": 1.6328964233398438,519 "learning_rate": 1.9851039135304366e-05,520 "loss": 1.3464,521 "mean_token_accuracy": 0.673164501786232,522 "num_tokens": 827388.0,523 "step": 570524 },525 {526 "epoch": 18.128,527 "grad_norm": 1.394505500793457,528 "learning_rate": 1.9845577223900087e-05,529 "loss": 1.3223,530 "mean_token_accuracy": 0.6847520865298606,531 "num_tokens": 842219.0,532 "step": 580533 },534 {535 "epoch": 18.448,536 "grad_norm": 1.541831374168396,537 "learning_rate": 1.984001775076708e-05,538 "loss": 1.3222,539 "mean_token_accuracy": 0.6771992217749357,540 "num_tokens": 857904.0,541 "step": 590542 },543 {544 "epoch": 18.768,545 "grad_norm": 1.4715123176574707,546 "learning_rate": 1.983436077099524e-05,547 "loss": 1.3623,548 "mean_token_accuracy": 0.6771474566310645,549 "num_tokens": 871758.0,550 "step": 600551 },552 {553 "epoch": 19.064,554 "grad_norm": 1.244395136833191,555 "learning_rate": 1.9828606340640678e-05,556 "loss": 1.3194,557 "mean_token_accuracy": 0.6701785076308895,558 "num_tokens": 885177.0,559 "step": 610560 },561 {562 "epoch": 19.384,563 "grad_norm": 3.2594940662384033,564 "learning_rate": 1.9822754516725148e-05,565 "loss": 1.3986,566 "mean_token_accuracy": 0.6804742000997066,567 "num_tokens": 900412.0,568 "step": 620569 },570 {571 "epoch": 19.704,572 "grad_norm": 1.9484755992889404,573 "learning_rate": 1.9816805357235512e-05,574 "loss": 1.3087,575 "mean_token_accuracy": 0.675427176989615,576 "num_tokens": 914923.0,577 "step": 630578 },579 {580 "epoch": 20.0,581 "grad_norm": 4.795617580413818,582 "learning_rate": 1.981075892112314e-05,583 "loss": 1.3261,584 "mean_token_accuracy": 0.6869603467954172,585 "num_tokens": 928360.0,586 "step": 640587 },588 {589 "epoch": 20.32,590 "grad_norm": 2.1296019554138184,591 "learning_rate": 1.980461526830334e-05,592 "loss": 1.3365,593 "mean_token_accuracy": 0.6707998286932707,594 "num_tokens": 942431.0,595 "step": 650596 },597 {598 "epoch": 20.64,599 "grad_norm": 2.041980743408203,600 "learning_rate": 1.979837445965475e-05,601 "loss": 1.4148,602 "mean_token_accuracy": 0.6774610493332147,603 "num_tokens": 957665.0,604 "step": 660605 },606 {607 "epoch": 20.96,608 "grad_norm": 2.0277955532073975,609 "learning_rate": 1.979203655701875e-05,610 "loss": 1.1934,611 "mean_token_accuracy": 0.7059706412255764,612 "num_tokens": 972341.0,613 "step": 670614 },615 {616 "epoch": 21.256,617 "grad_norm": 1.4342715740203857,618 "learning_rate": 1.978560162319885e-05,619 "loss": 1.2645,620 "mean_token_accuracy": 0.6948015895244237,621 "num_tokens": 987917.0,622 "step": 680623 },624 {625 "epoch": 21.576,626 "grad_norm": 2.365342140197754,627 "learning_rate": 1.9779069721960046e-05,628 "loss": 1.356,629 "mean_token_accuracy": 0.6770768724381924,630 "num_tokens": 1001846.0,631 "step": 690632 },633 {634 "epoch": 21.896,635 "grad_norm": 1.4183971881866455,636 "learning_rate": 1.9772440918028217e-05,637 "loss": 1.3372,638 "mean_token_accuracy": 0.6928307216614484,639 "num_tokens": 1016810.0,640 "step": 700641 },642 {643 "epoch": 22.192,644 "grad_norm": 1.5157005786895752,645 "learning_rate": 1.9765715277089458e-05,646 "loss": 1.2262,647 "mean_token_accuracy": 0.6972452486689026,648 "num_tokens": 1032507.0,649 "step": 710650 },651 {652 "epoch": 22.512,653 "grad_norm": 1.4448522329330444,654 "learning_rate": 1.9758892865789445e-05,655 "loss": 1.2261,656 "mean_token_accuracy": 0.6949771210551262,657 "num_tokens": 1047386.0,658 "step": 720659 },660 {661 "epoch": 22.832,662 "grad_norm": 2.33046817779541,663 "learning_rate": 1.9751973751732775e-05,664 "loss": 1.2348,665 "mean_token_accuracy": 0.6982233498245478,666 "num_tokens": 1061351.0,667 "step": 730668 },669 {670 "epoch": 23.128,671 "grad_norm": 1.8830664157867432,672 "learning_rate": 1.9744958003482285e-05,673 "loss": 1.2979,674 "mean_token_accuracy": 0.6971497769291336,675 "num_tokens": 1073148.0,676 "step": 740677 },678 {679 "epoch": 23.448,680 "grad_norm": 1.466878056526184,681 "learning_rate": 1.9737845690558385e-05,682 "loss": 1.3683,683 "mean_token_accuracy": 0.680212589353323,684 "num_tokens": 1088218.0,685 "step": 750686 },687 {688 "epoch": 23.768,689 "grad_norm": 1.5701245069503784,690 "learning_rate": 1.973063688343835e-05,691 "loss": 1.1505,692 "mean_token_accuracy": 0.7072769150137901,693 "num_tokens": 1102836.0,694 "step": 760695 },696 {697 "epoch": 24.064,698 "grad_norm": 1.6687356233596802,699 "learning_rate": 1.9723331653555653e-05,700 "loss": 1.2474,701 "mean_token_accuracy": 0.6967680285105834,702 "num_tokens": 1116942.0,703 "step": 770704 },705 {706 "epoch": 24.384,707 "grad_norm": 1.3728556632995605,708 "learning_rate": 1.9715930073299227e-05,709 "loss": 1.2448,710 "mean_token_accuracy": 0.7040290288627148,711 "num_tokens": 1132054.0,712 "step": 780713 },714 {715 "epoch": 24.704,716 "grad_norm": 1.4181838035583496,717 "learning_rate": 1.970843221601276e-05,718 "loss": 1.1969,719 "mean_token_accuracy": 0.6944498892873525,720 "num_tokens": 1148041.0,721 "step": 790722 },723 {724 "epoch": 25.0,725 "grad_norm": 4.3919596672058105,726 "learning_rate": 1.9700838155993972e-05,727 "loss": 1.1934,728 "mean_token_accuracy": 0.7042354522524653,729 "num_tokens": 1160450.0,730 "step": 800731 },732 {733 "epoch": 25.32,734 "grad_norm": 1.5123074054718018,735 "learning_rate": 1.9693147968493872e-05,736 "loss": 1.2369,737 "mean_token_accuracy": 0.692409698665142,738 "num_tokens": 1174351.0,739 "step": 810740 },741 {742 "epoch": 25.64,743 "grad_norm": 1.278221845626831,744 "learning_rate": 1.9685361729716014e-05,745 "loss": 1.1829,746 "mean_token_accuracy": 0.7174848213791847,747 "num_tokens": 1190213.0,748 "step": 820749 },750 {751 "epoch": 25.96,752 "grad_norm": 2.224332094192505,753 "learning_rate": 1.967747951681575e-05,754 "loss": 1.2224,755 "mean_token_accuracy": 0.7052119519561529,756 "num_tokens": 1205508.0,757 "step": 830758 },759 {760 "epoch": 26.256,761 "grad_norm": 1.548086166381836,762 "learning_rate": 1.966950140789944e-05,763 "loss": 1.2254,764 "mean_token_accuracy": 0.7041690679820808,765 "num_tokens": 1219047.0,766 "step": 840767 },768 {769 "epoch": 26.576,770 "grad_norm": 2.0900254249572754,771 "learning_rate": 1.9661427482023718e-05,772 "loss": 1.1557,773 "mean_token_accuracy": 0.7088660508394241,774 "num_tokens": 1231738.0,775 "step": 850776 },777 {778 "epoch": 26.896,779 "grad_norm": 1.9919354915618896,780 "learning_rate": 1.965325781919467e-05,781 "loss": 1.1962,782 "mean_token_accuracy": 0.7142665989696979,783 "num_tokens": 1248062.0,784 "step": 860785 },786 {787 "epoch": 27.192,788 "grad_norm": 2.2158303260803223,789 "learning_rate": 1.9644992500367072e-05,790 "loss": 1.2078,791 "mean_token_accuracy": 0.7049629523141964,792 "num_tokens": 1261738.0,793 "step": 870794 },795 {796 "epoch": 27.512,797 "grad_norm": 1.830531358718872,798 "learning_rate": 1.9636631607443565e-05,799 "loss": 1.2142,800 "mean_token_accuracy": 0.7097026702016592,801 "num_tokens": 1278012.0,802 "step": 880803 },804 {805 "epoch": 27.832,806 "grad_norm": 2.0944063663482666,807 "learning_rate": 1.9628175223273847e-05,808 "loss": 1.1368,809 "mean_token_accuracy": 0.7265028398483991,810 "num_tokens": 1292725.0,811 "step": 890812 },813 {814 "epoch": 28.128,815 "grad_norm": 1.4445384740829468,816 "learning_rate": 1.9619623431653872e-05,817 "loss": 1.2329,818 "mean_token_accuracy": 0.6941638359346906,819 "num_tokens": 1305912.0,820 "step": 900821 },822 {823 "epoch": 28.448,824 "grad_norm": 2.084064245223999,825 "learning_rate": 1.9610976317324993e-05,826 "loss": 1.1324,827 "mean_token_accuracy": 0.7086500860750675,828 "num_tokens": 1320269.0,829 "step": 910830 },831 {832 "epoch": 28.768,833 "grad_norm": 1.5166538953781128,834 "learning_rate": 1.9602233965973145e-05,835 "loss": 1.215,836 "mean_token_accuracy": 0.7056132420897484,837 "num_tokens": 1336877.0,838 "step": 920839 },840 {841 "epoch": 29.064,842 "grad_norm": 1.324559211730957,843 "learning_rate": 1.9593396464227964e-05,844 "loss": 1.1762,845 "mean_token_accuracy": 0.7244789052653957,846 "num_tokens": 1349855.0,847 "step": 930848 },849 {850 "epoch": 29.384,851 "grad_norm": 1.3715434074401855,852 "learning_rate": 1.9584463899661975e-05,853 "loss": 1.1323,854 "mean_token_accuracy": 0.7216422040015459,855 "num_tokens": 1364729.0,856 "step": 940857 },858 {859 "epoch": 29.704,860 "grad_norm": 1.782844066619873,861 "learning_rate": 1.9575436360789687e-05,862 "loss": 1.2588,863 "mean_token_accuracy": 0.7018849883228541,864 "num_tokens": 1378903.0,865 "step": 950866 },867 {868 "epoch": 30.0,869 "grad_norm": 3.4414260387420654,870 "learning_rate": 1.9566313937066727e-05,871 "loss": 1.1545,872 "mean_token_accuracy": 0.7196269961627754,873 "num_tokens": 1392540.0,874 "step": 960875 },876 {877 "epoch": 30.32,878 "grad_norm": 3.570629835128784,879 "learning_rate": 1.9557096718888956e-05,880 "loss": 1.1217,881 "mean_token_accuracy": 0.7212486552074552,882 "num_tokens": 1406295.0,883 "step": 970884 },885 {886 "epoch": 30.64,887 "grad_norm": 1.5852808952331543,888 "learning_rate": 1.9547784797591565e-05,889 "loss": 1.1959,890 "mean_token_accuracy": 0.7164284475147724,891 "num_tokens": 1422592.0,892 "step": 980893 },894 {895 "epoch": 30.96,896 "grad_norm": 1.5355671644210815,897 "learning_rate": 1.9538378265448195e-05,898 "loss": 1.1813,899 "mean_token_accuracy": 0.710675698518753,900 "num_tokens": 1437502.0,901 "step": 990902 },903 {904 "epoch": 31.256,905 "grad_norm": 1.5741212368011475,906 "learning_rate": 1.9528877215669983e-05,907 "loss": 1.1143,908 "mean_token_accuracy": 0.7233139457734855,909 "num_tokens": 1452056.0,910 "step": 1000911 },912 {913 "epoch": 32.576,914 "grad_norm": 1.7357654571533203,915 "learning_rate": 1.8116046949409032e-05,916 "loss": 1.2445,917 "mean_token_accuracy": 0.7005614548921585,918 "num_tokens": 14368.0,919 "step": 1010920 },921 {922 "epoch": 32.896,923 "grad_norm": 2.1830084323883057,924 "learning_rate": 1.807903147537074e-05,925 "loss": 1.1743,926 "mean_token_accuracy": 0.7173698712140322,927 "num_tokens": 31135.0,928 "step": 1020929 },930 {931 "epoch": 33.224,932 "grad_norm": 2.0015718936920166,933 "learning_rate": 1.8041694488049716e-05,934 "loss": 1.2619,935 "mean_token_accuracy": 0.715624163063561,936 "num_tokens": 46347.0,937 "step": 1030938 },939 {940 "epoch": 33.544,941 "grad_norm": 1.7311397790908813,942 "learning_rate": 1.8004037473309373e-05,943 "loss": 1.2331,944 "mean_token_accuracy": 0.7106888771057129,945 "num_tokens": 63240.0,946 "step": 1040947 },948 {949 "epoch": 33.864,950 "grad_norm": 1.8815584182739258,951 "learning_rate": 1.7966061929748968e-05,952 "loss": 1.2194,953 "mean_token_accuracy": 0.7109542470425367,954 "num_tokens": 79655.0,955 "step": 1050956 },957 {958 "epoch": 34.16,959 "grad_norm": 1.684423565864563,960 "learning_rate": 1.7927769368643904e-05,961 "loss": 1.0667,962 "mean_token_accuracy": 0.7348488770626687,963 "num_tokens": 95318.0,964 "step": 1060965 },966 {967 "epoch": 34.48,968 "grad_norm": 1.6687734127044678,969 "learning_rate": 1.788916131388564e-05,970 "loss": 1.1796,971 "mean_token_accuracy": 0.7278237771242857,972 "num_tokens": 111213.0,973 "step": 1070974 },975 {976 "epoch": 34.8,977 "grad_norm": 1.7268950939178467,978 "learning_rate": 1.785023930192103e-05,979 "loss": 1.1723,980 "mean_token_accuracy": 0.7138827528804541,981 "num_tokens": 126943.0,982 "step": 1080983 },984 {985 "epoch": 35.096,986 "grad_norm": 1.5416665077209473,987 "learning_rate": 1.781100488169115e-05,988 "loss": 1.0286,989 "mean_token_accuracy": 0.7333241834028347,990 "num_tokens": 142073.0,991 "step": 1090992 },993 {994 "epoch": 35.416,995 "grad_norm": 1.7402383089065552,996 "learning_rate": 1.777145961456971e-05,997 "loss": 1.0884,998 "mean_token_accuracy": 0.7265842445194721,999 "num_tokens": 158263.0,1000 "step": 11001001 },1002 {1003 "epoch": 35.736,1004 "grad_norm": 1.4736402034759521,1005 "learning_rate": 1.773160507430087e-05,1006 "loss": 1.1012,1007 "mean_token_accuracy": 0.727820971608162,1008 "num_tokens": 172637.0,1009 "step": 11101010 },1011 {1012 "epoch": 36.032,1013 "grad_norm": 2.027437448501587,1014 "learning_rate": 1.7691442846936643e-05,1015 "loss": 1.1525,1016 "mean_token_accuracy": 0.7281997264237017,1017 "num_tokens": 189288.0,1018 "step": 11201019 },1020 {1021 "epoch": 36.352,1022 "grad_norm": 2.058610439300537,1023 "learning_rate": 1.7650974530773745e-05,1024 "loss": 1.147,1025 "mean_token_accuracy": 0.7228171911090613,1026 "num_tokens": 204429.0,1027 "step": 11301028 },1029 {1030 "epoch": 36.672,1031 "grad_norm": 1.47328519821167,1032 "learning_rate": 1.7610201736290022e-05,1033 "loss": 1.1293,1034 "mean_token_accuracy": 0.7266111556440592,1035 "num_tokens": 220109.0,1036 "step": 11401037 },1038 {1039 "epoch": 36.992,1040 "grad_norm": 1.4244815111160278,1041 "learning_rate": 1.7569126086080342e-05,1042 "loss": 1.0312,1043 "mean_token_accuracy": 0.7415647856891155,1044 "num_tokens": 236961.0,1045 "step": 11501046 },1047 {1048 "epoch": 37.288,1049 "grad_norm": 1.6087596416473389,1050 "learning_rate": 1.7527749214792023e-05,1051 "loss": 1.1148,1052 "mean_token_accuracy": 0.722566624348228,1053 "num_tokens": 251116.0,1054 "step": 11601055 },1056 {1057 "epoch": 37.608,1058 "grad_norm": 1.6909428834915161,1059 "learning_rate": 1.7486072769059785e-05,1060 "loss": 1.1283,1061 "mean_token_accuracy": 0.7359607569873333,1062 "num_tokens": 267570.0,1063 "step": 11701064 },1065 {1066 "epoch": 37.928,1067 "grad_norm": 1.646548867225647,1068 "learning_rate": 1.7444098407440218e-05,1069 "loss": 1.0572,1070 "mean_token_accuracy": 0.7344494730234146,1071 "num_tokens": 282974.0,1072 "step": 11801073 },1074 {1075 "epoch": 38.224,1076 "grad_norm": 1.5249629020690918,1077 "learning_rate": 1.740182780034577e-05,1078 "loss": 0.9779,1079 "mean_token_accuracy": 0.7474351501142656,1080 "num_tokens": 298664.0,1081 "step": 11901082 },1083 {1084 "epoch": 38.544,1085 "grad_norm": 1.8203458786010742,1086 "learning_rate": 1.7359262629978286e-05,1087 "loss": 1.044,1088 "mean_token_accuracy": 0.7267404418438673,1089 "num_tokens": 313932.0,1090 "step": 12001091 },1092 {1093 "epoch": 38.864,1094 "grad_norm": 1.960335612297058,1095 "learning_rate": 1.731640459026206e-05,1096 "loss": 1.0537,1097 "mean_token_accuracy": 0.7449462197721004,1098 "num_tokens": 330427.0,1099 "step": 12101100 },1101 {1102 "epoch": 39.16,1103 "grad_norm": 2.152423620223999,1104 "learning_rate": 1.727325538677642e-05,1105 "loss": 1.1988,1106 "mean_token_accuracy": 0.7341888015334671,1107 "num_tokens": 344595.0,1108 "step": 12201109 },1110 {1111 "epoch": 39.48,1112 "grad_norm": 1.9269284009933472,1113 "learning_rate": 1.722981673668784e-05,1114 "loss": 1.0929,1115 "mean_token_accuracy": 0.7354621075093746,1116 "num_tokens": 361903.0,1117 "step": 12301118 },1119 {1120 "epoch": 39.8,1121 "grad_norm": 2.627488374710083,1122 "learning_rate": 1.7186090368681625e-05,1123 "loss": 1.0304,1124 "mean_token_accuracy": 0.7406851584091783,1125 "num_tokens": 378158.0,1126 "step": 12401127 },1128 {1129 "epoch": 40.096,1130 "grad_norm": 1.340135931968689,1131 "learning_rate": 1.714207802289311e-05,1132 "loss": 0.9831,1133 "mean_token_accuracy": 0.7508459779861811,1134 "num_tokens": 393086.0,1135 "step": 12501136 },1137 {1138 "epoch": 40.416,1139 "grad_norm": 1.5764344930648804,1140 "learning_rate": 1.7097781450838408e-05,1141 "loss": 1.0411,1142 "mean_token_accuracy": 0.7428241446614265,1143 "num_tokens": 408865.0,1144 "step": 12601145 },1146 {1147 "epoch": 40.736,1148 "grad_norm": 2.27480149269104,1149 "learning_rate": 1.7053202415344693e-05,1150 "loss": 1.1553,1151 "mean_token_accuracy": 0.7261891044676304,1152 "num_tokens": 422941.0,1153 "step": 12701154 },1155 {1156 "epoch": 41.032,1157 "grad_norm": 2.0869431495666504,1158 "learning_rate": 1.7008342690480075e-05,1159 "loss": 1.0776,1160 "mean_token_accuracy": 0.7442273002218556,1161 "num_tokens": 438615.0,1162 "step": 12801163 },1164 {1165 "epoch": 41.352,1166 "grad_norm": 1.6138980388641357,1167 "learning_rate": 1.6963204061482972e-05,1168 "loss": 0.9933,1169 "mean_token_accuracy": 0.7366263665258884,1170 "num_tokens": 454742.0,1171 "step": 12901172 },1173 {1174 "epoch": 41.672,1175 "grad_norm": 2.201198101043701,1176 "learning_rate": 1.6917788324691083e-05,1177 "loss": 1.12,1178 "mean_token_accuracy": 0.7349841587245465,1179 "num_tokens": 471732.0,1180 "step": 13001181 },1182 {1183 "epoch": 41.992,1184 "grad_norm": 2.3492226600646973,1185 "learning_rate": 1.687209728746989e-05,1186 "loss": 1.0594,1187 "mean_token_accuracy": 0.745047352835536,1188 "num_tokens": 487349.0,1189 "step": 13101190 },1191 {1192 "epoch": 42.288,1193 "grad_norm": 1.7862104177474976,1194 "learning_rate": 1.6826132768140735e-05,1195 "loss": 0.9756,1196 "mean_token_accuracy": 0.7570219249338717,1197 "num_tokens": 502115.0,1198 "step": 13201199 },1200 {