cuong1692001/Terminal-dependency_management
08
1{2 "best_global_step": null,3 "best_metric": null,4 "best_model_checkpoint": null,5 "epoch": 2.0,6 "eval_steps": 500,7 "global_step": 4968,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.002012882447665056,14 "grad_norm": 2.297874630841598,15 "learning_rate": 9.999984004554854e-06,16 "loss": 0.867,17 "num_input_tokens_seen": 292832,18 "step": 5,19 "train_runtime": 39.7021,20 "train_tokens_per_second": 7375.73821 },22 {23 "epoch": 0.004025764895330112,24 "grad_norm": 1.5412972986291504,25 "learning_rate": 9.999919023234347e-06,26 "loss": 0.7277,27 "num_input_tokens_seen": 564944,28 "step": 10,29 "train_runtime": 66.4419,30 "train_tokens_per_second": 8502.8331 },32 {33 "epoch": 0.006038647342995169,34 "grad_norm": 1.3285416449380885,35 "learning_rate": 9.999804056972284e-06,36 "loss": 0.6583,37 "num_input_tokens_seen": 816128,38 "step": 15,39 "train_runtime": 95.0256,40 "train_tokens_per_second": 8588.50441 },42 {43 "epoch": 0.008051529790660225,44 "grad_norm": 0.9814892211337461,45 "learning_rate": 9.999639106918003e-06,46 "loss": 0.6616,47 "num_input_tokens_seen": 1099328,48 "step": 20,49 "train_runtime": 127.2285,50 "train_tokens_per_second": 8640.58351 },52 {53 "epoch": 0.010064412238325281,54 "grad_norm": 1.0896984128385303,55 "learning_rate": 9.99942417472053e-06,56 "loss": 0.5853,57 "num_input_tokens_seen": 1374032,58 "step": 25,59 "train_runtime": 153.9678,60 "train_tokens_per_second": 8924.15261 },62 {63 "epoch": 0.012077294685990338,64 "grad_norm": 1.0662278961026128,65 "learning_rate": 9.999159262528582e-06,66 "loss": 0.604,67 "num_input_tokens_seen": 1636080,68 "step": 30,69 "train_runtime": 178.3494,70 "train_tokens_per_second": 9173.45471 },72 {73 "epoch": 0.014090177133655395,74 "grad_norm": 0.9930923199663517,75 "learning_rate": 9.99884437299052e-06,76 "loss": 0.5905,77 "num_input_tokens_seen": 1900688,78 "step": 35,79 "train_runtime": 201.2774,80 "train_tokens_per_second": 9443.12981 },82 {83 "epoch": 0.01610305958132045,84 "grad_norm": 0.9690627403707294,85 "learning_rate": 9.998479509254341e-06,86 "loss": 0.575,87 "num_input_tokens_seen": 2199616,88 "step": 40,89 "train_runtime": 235.7208,90 "train_tokens_per_second": 9331.44891 },92 {93 "epoch": 0.018115942028985508,94 "grad_norm": 1.0729878367285486,95 "learning_rate": 9.998064674967647e-06,96 "loss": 0.5676,97 "num_input_tokens_seen": 2476496,98 "step": 45,99 "train_runtime": 270.2691,100 "train_tokens_per_second": 9163.074101 },102 {103 "epoch": 0.020128824476650563,104 "grad_norm": 1.0319800558502288,105 "learning_rate": 9.997599874277596e-06,106 "loss": 0.5935,107 "num_input_tokens_seen": 2761112,108 "step": 50,109 "train_runtime": 303.6384,110 "train_tokens_per_second": 9093.42111 },112 {113 "epoch": 0.02214170692431562,114 "grad_norm": 1.0330630133831564,115 "learning_rate": 9.99708511183087e-06,116 "loss": 0.5641,117 "num_input_tokens_seen": 3062000,118 "step": 55,119 "train_runtime": 332.92,120 "train_tokens_per_second": 9197.405121 },122 {123 "epoch": 0.024154589371980676,124 "grad_norm": 1.024063001375934,125 "learning_rate": 9.99652039277363e-06,126 "loss": 0.5104,127 "num_input_tokens_seen": 3329408,128 "step": 60,129 "train_runtime": 364.1266,130 "train_tokens_per_second": 9143.545131 },132 {133 "epoch": 0.026167471819645734,134 "grad_norm": 1.0403150394762068,135 "learning_rate": 9.995905722751453e-06,136 "loss": 0.554,137 "num_input_tokens_seen": 3591352,138 "step": 65,139 "train_runtime": 396.3182,140 "train_tokens_per_second": 9061.789141 },142 {143 "epoch": 0.02818035426731079,144 "grad_norm": 0.989881460344966,145 "learning_rate": 9.99524110790929e-06,146 "loss": 0.5112,147 "num_input_tokens_seen": 3864640,148 "step": 70,149 "train_runtime": 422.9422,150 "train_tokens_per_second": 9137.514151 },152 {153 "epoch": 0.030193236714975844,154 "grad_norm": 1.0121773824486404,155 "learning_rate": 9.994526554891394e-06,156 "loss": 0.5092,157 "num_input_tokens_seen": 4118608,158 "step": 75,159 "train_runtime": 455.3539,160 "train_tokens_per_second": 9044.85161 },162 {163 "epoch": 0.0322061191626409,164 "grad_norm": 1.0623009014957763,165 "learning_rate": 9.99376207084126e-06,166 "loss": 0.5149,167 "num_input_tokens_seen": 4397920,168 "step": 80,169 "train_runtime": 480.756,170 "train_tokens_per_second": 9147.926171 },172 {173 "epoch": 0.03421900161030596,174 "grad_norm": 0.9593445283598526,175 "learning_rate": 9.992947663401548e-06,176 "loss": 0.5463,177 "num_input_tokens_seen": 4693768,178 "step": 85,179 "train_runtime": 512.7989,180 "train_tokens_per_second": 9153.233181 },182 {183 "epoch": 0.036231884057971016,184 "grad_norm": 1.0508704978399308,185 "learning_rate": 9.992083340714016e-06,186 "loss": 0.5106,187 "num_input_tokens_seen": 4961600,188 "step": 90,189 "train_runtime": 544.8363,190 "train_tokens_per_second": 9106.588191 },192 {193 "epoch": 0.038244766505636074,194 "grad_norm": 1.1518906280289636,195 "learning_rate": 9.991169111419422e-06,196 "loss": 0.5364,197 "num_input_tokens_seen": 5248632,198 "step": 95,199 "train_runtime": 582.7007,200 "train_tokens_per_second": 9007.424201 },202 {203 "epoch": 0.040257648953301126,204 "grad_norm": 1.0455583857626112,205 "learning_rate": 9.990204984657458e-06,206 "loss": 0.5126,207 "num_input_tokens_seen": 5535592,208 "step": 100,209 "train_runtime": 613.3673,210 "train_tokens_per_second": 9024.922211 },212 {213 "epoch": 0.042270531400966184,214 "grad_norm": 0.9647063794409773,215 "learning_rate": 9.989190970066643e-06,216 "loss": 0.4907,217 "num_input_tokens_seen": 5825616,218 "step": 105,219 "train_runtime": 648.4131,220 "train_tokens_per_second": 8984.421221 },222 {223 "epoch": 0.04428341384863124,224 "grad_norm": 1.025853461617905,225 "learning_rate": 9.98812707778423e-06,226 "loss": 0.5066,227 "num_input_tokens_seen": 6096520,228 "step": 110,229 "train_runtime": 677.1808,230 "train_tokens_per_second": 9002.795231 },232 {233 "epoch": 0.046296296296296294,234 "grad_norm": 0.9941746624599364,235 "learning_rate": 9.987013318446114e-06,236 "loss": 0.5259,237 "num_input_tokens_seen": 6388368,238 "step": 115,239 "train_runtime": 703.6922,240 "train_tokens_per_second": 9078.355241 },242 {243 "epoch": 0.04830917874396135,244 "grad_norm": 1.005276106932477,245 "learning_rate": 9.985849703186711e-06,246 "loss": 0.5149,247 "num_input_tokens_seen": 6666624,248 "step": 120,249 "train_runtime": 737.6899,250 "train_tokens_per_second": 9037.163251 },252 {253 "epoch": 0.05032206119162641,254 "grad_norm": 1.0054534660231844,255 "learning_rate": 9.984636243638864e-06,256 "loss": 0.5026,257 "num_input_tokens_seen": 6936568,258 "step": 125,259 "train_runtime": 765.4033,260 "train_tokens_per_second": 9062.631261 },262 {263 "epoch": 0.05233494363929147,264 "grad_norm": 0.9649854296642881,265 "learning_rate": 9.983372951933702e-06,266 "loss": 0.4955,267 "num_input_tokens_seen": 7206584,268 "step": 130,269 "train_runtime": 796.5003,270 "train_tokens_per_second": 9047.811271 },272 {273 "epoch": 0.05434782608695652,274 "grad_norm": 1.0014564760412348,275 "learning_rate": 9.982059840700546e-06,276 "loss": 0.4968,277 "num_input_tokens_seen": 7475776,278 "step": 135,279 "train_runtime": 828.7164,280 "train_tokens_per_second": 9020.91281 },282 {283 "epoch": 0.05636070853462158,284 "grad_norm": 0.9385880473188393,285 "learning_rate": 9.980696923066768e-06,286 "loss": 0.4931,287 "num_input_tokens_seen": 7731464,288 "step": 140,289 "train_runtime": 861.9344,290 "train_tokens_per_second": 8969.898291 },292 {293 "epoch": 0.05837359098228664,294 "grad_norm": 1.029261356856895,295 "learning_rate": 9.979284212657658e-06,296 "loss": 0.5025,297 "num_input_tokens_seen": 8017968,298 "step": 145,299 "train_runtime": 884.1322,300 "train_tokens_per_second": 9068.743301 },302 {303 "epoch": 0.06038647342995169,304 "grad_norm": 0.9568689832650803,305 "learning_rate": 9.977821723596293e-06,306 "loss": 0.5134,307 "num_input_tokens_seen": 8291456,308 "step": 150,309 "train_runtime": 908.7213,310 "train_tokens_per_second": 9124.312311 },312 {313 "epoch": 0.06239935587761675,314 "grad_norm": 1.0073839022410702,315 "learning_rate": 9.976309470503398e-06,316 "loss": 0.4773,317 "num_input_tokens_seen": 8578792,318 "step": 155,319 "train_runtime": 944.0011,320 "train_tokens_per_second": 9087.693321 },322 {323 "epoch": 0.0644122383252818,324 "grad_norm": 0.9920386431386734,325 "learning_rate": 9.974747468497194e-06,326 "loss": 0.5019,327 "num_input_tokens_seen": 8890568,328 "step": 160,329 "train_runtime": 971.9993,330 "train_tokens_per_second": 9146.682331 },332 {333 "epoch": 0.06642512077294686,334 "grad_norm": 0.9884792357109632,335 "learning_rate": 9.973135733193249e-06,336 "loss": 0.4943,337 "num_input_tokens_seen": 9179704,338 "step": 165,339 "train_runtime": 1001.0592,340 "train_tokens_per_second": 9169.991341 },342 {343 "epoch": 0.06843800322061191,344 "grad_norm": 1.092841343494877,345 "learning_rate": 9.971474280704325e-06,346 "loss": 0.4921,347 "num_input_tokens_seen": 9461368,348 "step": 170,349 "train_runtime": 1027.2,350 "train_tokens_per_second": 9210.833351 },352 {353 "epoch": 0.07045088566827697,354 "grad_norm": 1.2286594209419102,355 "learning_rate": 9.969763127640209e-06,356 "loss": 0.4741,357 "num_input_tokens_seen": 9713984,358 "step": 175,359 "train_runtime": 1056.8353,360 "train_tokens_per_second": 9191.577361 },362 {363 "epoch": 0.07246376811594203,364 "grad_norm": 0.8373313585482862,365 "learning_rate": 9.968002291107557e-06,366 "loss": 0.4759,367 "num_input_tokens_seen": 10012384,368 "step": 180,369 "train_runtime": 1086.8129,370 "train_tokens_per_second": 9212.61371 },372 {373 "epoch": 0.07447665056360708,374 "grad_norm": 1.0232386757931464,375 "learning_rate": 9.966191788709716e-06,376 "loss": 0.4987,377 "num_input_tokens_seen": 10309304,378 "step": 185,379 "train_runtime": 1124.6164,380 "train_tokens_per_second": 9166.952381 },382 {383 "epoch": 0.07648953301127215,384 "grad_norm": 1.0192498037984576,385 "learning_rate": 9.96433163854655e-06,386 "loss": 0.5044,387 "num_input_tokens_seen": 10601024,388 "step": 190,389 "train_runtime": 1154.457,390 "train_tokens_per_second": 9182.693391 },392 {393 "epoch": 0.0785024154589372,394 "grad_norm": 0.8967750445238334,395 "learning_rate": 9.96242185921426e-06,396 "loss": 0.4963,397 "num_input_tokens_seen": 10843288,398 "step": 195,399 "train_runtime": 1184.9067,400 "train_tokens_per_second": 9151.174401 },402 {403 "epoch": 0.08051529790660225,404 "grad_norm": 0.913336553563134,405 "learning_rate": 9.9604624698052e-06,406 "loss": 0.4897,407 "num_input_tokens_seen": 11122280,408 "step": 200,409 "train_runtime": 1215.3143,410 "train_tokens_per_second": 9151.772411 },412 {413 "epoch": 0.08252818035426732,414 "grad_norm": 1.0051464363210705,415 "learning_rate": 9.958453489907673e-06,416 "loss": 0.4868,417 "num_input_tokens_seen": 11398920,418 "step": 205,419 "train_runtime": 1247.2302,420 "train_tokens_per_second": 9139.388421 },422 {423 "epoch": 0.08454106280193237,424 "grad_norm": 0.9520523183963829,425 "learning_rate": 9.95639493960576e-06,426 "loss": 0.4624,427 "num_input_tokens_seen": 11687640,428 "step": 210,429 "train_runtime": 1281.9313,430 "train_tokens_per_second": 9117.213431 },432 {433 "epoch": 0.08655394524959742,434 "grad_norm": 1.004052413112944,435 "learning_rate": 9.954286839479093e-06,436 "loss": 0.4623,437 "num_input_tokens_seen": 11963376,438 "step": 215,439 "train_runtime": 1310.3705,440 "train_tokens_per_second": 9129.766441 },442 {443 "epoch": 0.08856682769726248,444 "grad_norm": 0.9695102563911814,445 "learning_rate": 9.952129210602667e-06,446 "loss": 0.5101,447 "num_input_tokens_seen": 12245024,448 "step": 220,449 "train_runtime": 1343.393,450 "train_tokens_per_second": 9114.997451 },452 {453 "epoch": 0.09057971014492754,454 "grad_norm": 0.962229278452791,455 "learning_rate": 9.949922074546622e-06,456 "loss": 0.4567,457 "num_input_tokens_seen": 12524040,458 "step": 225,459 "train_runtime": 1369.1511,460 "train_tokens_per_second": 9147.303461 },462 {463 "epoch": 0.09259259259259259,464 "grad_norm": 0.9824369554443164,465 "learning_rate": 9.947665453376032e-06,466 "loss": 0.4815,467 "num_input_tokens_seen": 12785280,468 "step": 230,469 "train_runtime": 1400.5983,470 "train_tokens_per_second": 9128.442471 },472 {473 "epoch": 0.09460547504025765,474 "grad_norm": 0.85368460319332,475 "learning_rate": 9.945359369650673e-06,476 "loss": 0.4564,477 "num_input_tokens_seen": 13058144,478 "step": 235,479 "train_runtime": 1434.6051,480 "train_tokens_per_second": 9102.257481 },482 {483 "epoch": 0.0966183574879227,484 "grad_norm": 0.8997471128244209,485 "learning_rate": 9.943003846424811e-06,486 "loss": 0.4618,487 "num_input_tokens_seen": 13344560,488 "step": 240,489 "train_runtime": 1465.1679,490 "train_tokens_per_second": 9107.871491 },492 {493 "epoch": 0.09863123993558776,494 "grad_norm": 0.9464056047380616,495 "learning_rate": 9.940598907246968e-06,496 "loss": 0.48,497 "num_input_tokens_seen": 13615896,498 "step": 245,499 "train_runtime": 1501.0603,500 "train_tokens_per_second": 9070.852501 },502 {503 "epoch": 0.10064412238325282,504 "grad_norm": 0.8962483000661939,505 "learning_rate": 9.93814457615968e-06,506 "loss": 0.4692,507 "num_input_tokens_seen": 13907312,508 "step": 250,509 "train_runtime": 1529.34,510 "train_tokens_per_second": 9093.669511 },512 {513 "epoch": 0.10265700483091787,514 "grad_norm": 0.8970724655525292,515 "learning_rate": 9.935640877699267e-06,516 "loss": 0.4603,517 "num_input_tokens_seen": 14164552,518 "step": 255,519 "train_runtime": 1560.4007,520 "train_tokens_per_second": 9077.51521 },522 {523 "epoch": 0.10466988727858294,524 "grad_norm": 0.9285997033654927,525 "learning_rate": 9.933087836895575e-06,526 "loss": 0.4722,527 "num_input_tokens_seen": 14443752,528 "step": 260,529 "train_runtime": 1587.6033,530 "train_tokens_per_second": 9097.835531 },532 {533 "epoch": 0.10668276972624799,534 "grad_norm": 0.9859648420826093,535 "learning_rate": 9.930485479271735e-06,536 "loss": 0.4877,537 "num_input_tokens_seen": 14736200,538 "step": 265,539 "train_runtime": 1620.9205,540 "train_tokens_per_second": 9091.254541 },542 {543 "epoch": 0.10869565217391304,544 "grad_norm": 0.8933935555310302,545 "learning_rate": 9.927833830843912e-06,546 "loss": 0.466,547 "num_input_tokens_seen": 15016808,548 "step": 270,549 "train_runtime": 1657.4694,550 "train_tokens_per_second": 9060.081551 },552 {553 "epoch": 0.1107085346215781,554 "grad_norm": 0.901422608365093,555 "learning_rate": 9.925132918121031e-06,556 "loss": 0.4919,557 "num_input_tokens_seen": 15308392,558 "step": 275,559 "train_runtime": 1687.0118,560 "train_tokens_per_second": 9074.265561 },562 {563 "epoch": 0.11272141706924316,564 "grad_norm": 1.0917968989269704,565 "learning_rate": 9.922382768104522e-06,566 "loss": 0.4688,567 "num_input_tokens_seen": 15559416,568 "step": 280,569 "train_runtime": 1714.5165,570 "train_tokens_per_second": 9075.104571 },572 {573 "epoch": 0.11473429951690821,574 "grad_norm": 1.061812935108647,575 "learning_rate": 9.919583408288049e-06,576 "loss": 0.4684,577 "num_input_tokens_seen": 15836040,578 "step": 285,579 "train_runtime": 1744.45,580 "train_tokens_per_second": 9077.956581 },582 {583 "epoch": 0.11674718196457327,584 "grad_norm": 0.9537165872143243,585 "learning_rate": 9.916734866657233e-06,586 "loss": 0.4808,587 "num_input_tokens_seen": 16110584,588 "step": 290,589 "train_runtime": 1775.4645,590 "train_tokens_per_second": 9074.011591 },592 {593 "epoch": 0.11876006441223833,594 "grad_norm": 0.916650519501917,595 "learning_rate": 9.913837171689371e-06,596 "loss": 0.4565,597 "num_input_tokens_seen": 16386896,598 "step": 295,599 "train_runtime": 1800.6521,600 "train_tokens_per_second": 9100.534601 },602 {603 "epoch": 0.12077294685990338,604 "grad_norm": 0.8896413097983231,605 "learning_rate": 9.910890352353154e-06,606 "loss": 0.4622,607 "num_input_tokens_seen": 16681768,608 "step": 300,609 "train_runtime": 1826.484,610 "train_tokens_per_second": 9133.268611 },612 {613 "epoch": 0.12278582930756844,614 "grad_norm": 1.047536047835029,615 "learning_rate": 9.90789443810838e-06,616 "loss": 0.4496,617 "num_input_tokens_seen": 16957488,618 "step": 305,619 "train_runtime": 1852.5616,620 "train_tokens_per_second": 9153.535621 },622 {623 "epoch": 0.1247987117552335,624 "grad_norm": 0.8071488982140137,625 "learning_rate": 9.904849458905654e-06,626 "loss": 0.486,627 "num_input_tokens_seen": 17260552,628 "step": 310,629 "train_runtime": 1890.3429,630 "train_tokens_per_second": 9130.91631 },632 {633 "epoch": 0.12681159420289856,634 "grad_norm": 0.9224613988609329,635 "learning_rate": 9.901755445186088e-06,636 "loss": 0.4643,637 "num_input_tokens_seen": 17526528,638 "step": 315,639 "train_runtime": 1919.1621,640 "train_tokens_per_second": 9132.385641 },642 {643 "epoch": 0.1288244766505636,644 "grad_norm": 0.8816714224692683,645 "learning_rate": 9.898612427881002e-06,646 "loss": 0.4747,647 "num_input_tokens_seen": 17801096,648 "step": 320,649 "train_runtime": 1951.7409,650 "train_tokens_per_second": 9120.625651 },652 {653 "epoch": 0.13083735909822866,654 "grad_norm": 1.013524769504045,655 "learning_rate": 9.895420438411616e-06,656 "loss": 0.5203,657 "num_input_tokens_seen": 18086600,658 "step": 325,659 "train_runtime": 1979.6703,660 "train_tokens_per_second": 9136.168661 },662 {663 "epoch": 0.13285024154589373,664 "grad_norm": 0.9633152341610259,665 "learning_rate": 9.892179508688724e-06,666 "loss": 0.4754,667 "num_input_tokens_seen": 18348912,668 "step": 330,669 "train_runtime": 2010.2191,670 "train_tokens_per_second": 9127.817671 },672 {673 "epoch": 0.13486312399355876,674 "grad_norm": 1.0039963734989743,675 "learning_rate": 9.888889671112388e-06,676 "loss": 0.445,677 "num_input_tokens_seen": 18619192,678 "step": 335,679 "train_runtime": 2036.4325,680 "train_tokens_per_second": 9143.044681 },682 {683 "epoch": 0.13687600644122383,684 "grad_norm": 1.0832401853018647,685 "learning_rate": 9.88555095857161e-06,686 "loss": 0.4669,687 "num_input_tokens_seen": 18905056,688 "step": 340,689 "train_runtime": 2068.8702,690 "train_tokens_per_second": 9137.865691 },692 {693 "epoch": 0.1388888888888889,694 "grad_norm": 0.862382244963817,695 "learning_rate": 9.882163404444001e-06,696 "loss": 0.4782,697 "num_input_tokens_seen": 19184608,698 "step": 345,699 "train_runtime": 2098.8762,700 "train_tokens_per_second": 9140.419701 },702 {703 "epoch": 0.14090177133655393,704 "grad_norm": 0.864044298283736,705 "learning_rate": 9.878727042595447e-06,706 "loss": 0.4543,707 "num_input_tokens_seen": 19461712,708 "step": 350,709 "train_runtime": 2128.7935,710 "train_tokens_per_second": 9142.132711 },712 {713 "epoch": 0.142914653784219,714 "grad_norm": 0.9320696362077064,715 "learning_rate": 9.875241907379774e-06,716 "loss": 0.4441,717 "num_input_tokens_seen": 19740152,718 "step": 355,719 "train_runtime": 2160.5367,720 "train_tokens_per_second": 9136.689721 },722 {723 "epoch": 0.14492753623188406,724 "grad_norm": 0.8487837648535018,725 "learning_rate": 9.871708033638403e-06,726 "loss": 0.4712,727 "num_input_tokens_seen": 20008048,728 "step": 360,729 "train_runtime": 2188.3335,730 "train_tokens_per_second": 9143.053731 },732 {733 "epoch": 0.1469404186795491,734 "grad_norm": 0.8449813828387256,735 "learning_rate": 9.8681254567e-06,736 "loss": 0.461,737 "num_input_tokens_seen": 20280608,738 "step": 365,739 "train_runtime": 2212.8748,740 "train_tokens_per_second": 9164.824741 },742 {743 "epoch": 0.14895330112721417,744 "grad_norm": 0.9446992309876536,745 "learning_rate": 9.864494212380125e-06,746 "loss": 0.4195,747 "num_input_tokens_seen": 20529280,748 "step": 370,749 "train_runtime": 2239.8901,750 "train_tokens_per_second": 9165.307751 },752 {753 "epoch": 0.15096618357487923,754 "grad_norm": 0.8916069751957232,755 "learning_rate": 9.860814336980873e-06,756 "loss": 0.4436,757 "num_input_tokens_seen": 20811944,758 "step": 375,759 "train_runtime": 2269.4774,760 "train_tokens_per_second": 9170.369761 },762 {763 "epoch": 0.1529790660225443,764 "grad_norm": 0.902573279691924,765 "learning_rate": 9.85708586729051e-06,766 "loss": 0.4566,767 "num_input_tokens_seen": 21099408,768 "step": 380,769 "train_runtime": 2303.2507,770 "train_tokens_per_second": 9160.708771 },772 {773 "epoch": 0.15499194847020933,774 "grad_norm": 0.8867322843522712,775 "learning_rate": 9.85330884058311e-06,776 "loss": 0.4646,777 "num_input_tokens_seen": 21383888,778 "step": 385,779 "train_runtime": 2332.8596,780 "train_tokens_per_second": 9166.385781 },782 {783 "epoch": 0.1570048309178744,784 "grad_norm": 0.8675325974577762,785 "learning_rate": 9.849483294618174e-06,786 "loss": 0.4672,787 "num_input_tokens_seen": 21649424,788 "step": 390,789 "train_runtime": 2357.814,790 "train_tokens_per_second": 9181.99791 },792 {793 "epoch": 0.15901771336553946,794 "grad_norm": 0.8905402068232048,795 "learning_rate": 9.84560926764026e-06,796 "loss": 0.4698,797 "num_input_tokens_seen": 21936800,798 "step": 395,799 "train_runtime": 2388.2232,800 "train_tokens_per_second": 9185.406801 },802 {803 "epoch": 0.1610305958132045,804 "grad_norm": 1.7325432324949936,805 "learning_rate": 9.8416867983786e-06,806 "loss": 0.4787,807 "num_input_tokens_seen": 22236592,808 "step": 400,809 "train_runtime": 2415.6416,810 "train_tokens_per_second": 9205.253811 },812 {813 "epoch": 0.16304347826086957,814 "grad_norm": 0.8270328203472112,815 "learning_rate": 9.837715926046705e-06,816 "loss": 0.4563,817 "num_input_tokens_seen": 22511304,818 "step": 405,819 "train_runtime": 2443.4163,820 "train_tokens_per_second": 9213.045821 },822 {823 "epoch": 0.16505636070853463,824 "grad_norm": 0.9386742183347965,825 "learning_rate": 9.833696690341985e-06,826 "loss": 0.4427,827 "num_input_tokens_seen": 22789600,828 "step": 410,829 "train_runtime": 2473.4378,830 "train_tokens_per_second": 9213.735831 },832 {833 "epoch": 0.16706924315619967,834 "grad_norm": 0.823193403541499,835 "learning_rate": 9.829629131445342e-06,836 "loss": 0.4448,837 "num_input_tokens_seen": 23057896,838 "step": 415,839 "train_runtime": 2499.8246,840 "train_tokens_per_second": 9223.806841 },842 {843 "epoch": 0.16908212560386474,844 "grad_norm": 1.0759155560083942,845 "learning_rate": 9.825513290020774e-06,846 "loss": 0.4716,847 "num_input_tokens_seen": 23322920,848 "step": 420,849 "train_runtime": 2524.8992,850 "train_tokens_per_second": 9237.169851 },852 {853 "epoch": 0.1710950080515298,854 "grad_norm": 1.2895244102227148,855 "learning_rate": 9.821349207214965e-06,856 "loss": 0.4635,857 "num_input_tokens_seen": 23607720,858 "step": 425,859 "train_runtime": 2555.2346,860 "train_tokens_per_second": 9238.964861 },862 {863 "epoch": 0.17310789049919484,864 "grad_norm": 1.0077840856078137,865 "learning_rate": 9.817136924656876e-06,866 "loss": 0.4601,867 "num_input_tokens_seen": 23878208,868 "step": 430,869 "train_runtime": 2582.5663,870 "train_tokens_per_second": 9245.923871 },872 {873 "epoch": 0.1751207729468599,874 "grad_norm": 0.9407880632968855,875 "learning_rate": 9.81287648445733e-06,876 "loss": 0.4771,877 "num_input_tokens_seen": 24132696,878 "step": 435,879 "train_runtime": 2610.4406,880 "train_tokens_per_second": 9244.683881 },882 {883 "epoch": 0.17713365539452497,884 "grad_norm": 0.9053142341505027,885 "learning_rate": 9.808567929208585e-06,886 "loss": 0.5071,887 "num_input_tokens_seen": 24370704,888 "step": 440,889 "train_runtime": 2635.5968,890 "train_tokens_per_second": 9246.75891 },892 {893 "epoch": 0.17914653784219,894 "grad_norm": 0.9661909090080892,895 "learning_rate": 9.804211301983919e-06,896 "loss": 0.4677,897 "num_input_tokens_seen": 24646976,898 "step": 445,899 "train_runtime": 2664.2255,900 "train_tokens_per_second": 9251.085901 },902 {903 "epoch": 0.18115942028985507,904 "grad_norm": 0.8394811999152494,905 "learning_rate": 9.799806646337186e-06,906 "loss": 0.4412,907 "num_input_tokens_seen": 24928696,908 "step": 450,909 "train_runtime": 2692.6558,910 "train_tokens_per_second": 9258.033911 },912 {913 "epoch": 0.18317230273752014,914 "grad_norm": 0.8442351104000755,915 "learning_rate": 9.795354006302391e-06,916 "loss": 0.4778,917 "num_input_tokens_seen": 25219216,918 "step": 455,919 "train_runtime": 2716.0677,920 "train_tokens_per_second": 9285.194921 },922 {923 "epoch": 0.18518518518518517,924 "grad_norm": 0.8146128583546326,925 "learning_rate": 9.790853426393246e-06,926 "loss": 0.4418,927 "num_input_tokens_seen": 25478368,928 "step": 460,929 "train_runtime": 2745.2859,930 "train_tokens_per_second": 9280.77931 },932 {933 "epoch": 0.18719806763285024,934 "grad_norm": 0.8503603324829592,935 "learning_rate": 9.786304951602721e-06,936 "loss": 0.4505,937 "num_input_tokens_seen": 25769232,938 "step": 465,939 "train_runtime": 2776.8307,940 "train_tokens_per_second": 9280.088941 },942 {943 "epoch": 0.1892109500805153,944 "grad_norm": 0.8906558768292534,945 "learning_rate": 9.781708627402607e-06,946 "loss": 0.4682,947 "num_input_tokens_seen": 26048576,948 "step": 470,949 "train_runtime": 2815.5419,950 "train_tokens_per_second": 9251.71951 },952 {953 "epoch": 0.19122383252818034,954 "grad_norm": 0.8560769187270413,955 "learning_rate": 9.777064499743044e-06,956 "loss": 0.4755,957 "num_input_tokens_seen": 26328000,958 "step": 475,959 "train_runtime": 2848.0769,960 "train_tokens_per_second": 9244.133961 },962 {963 "epoch": 0.1932367149758454,964 "grad_norm": 0.9460611498214977,965 "learning_rate": 9.772372615052073e-06,966 "loss": 0.4521,967 "num_input_tokens_seen": 26625520,968 "step": 480,969 "train_runtime": 2871.8286,970 "train_tokens_per_second": 9271.278971 },972 {973 "epoch": 0.19524959742351047,974 "grad_norm": 0.9498293368473315,975 "learning_rate": 9.767633020235175e-06,976 "loss": 0.4664,977 "num_input_tokens_seen": 26912912,978 "step": 485,979 "train_runtime": 2905.6311,980 "train_tokens_per_second": 9262.329981 },982 {983 "epoch": 0.1972624798711755,984 "grad_norm": 0.880158192459652,985 "learning_rate": 9.762845762674783e-06,986 "loss": 0.4483,987 "num_input_tokens_seen": 27186112,988 "step": 490,989 "train_runtime": 2933.3314,990 "train_tokens_per_second": 9267.999991 },992 {993 "epoch": 0.19927536231884058,994 "grad_norm": 0.9087010500522344,995 "learning_rate": 9.758010890229841e-06,996 "loss": 0.4425,997 "num_input_tokens_seen": 27458000,998 "step": 495,999 "train_runtime": 2958.1078,1000 "train_tokens_per_second": 9282.2851001 },1002 {1003 "epoch": 0.20128824476650564,1004 "grad_norm": 0.9534094173539439,1005 "learning_rate": 9.753128451235286e-06,1006 "loss": 0.4376,1007 "num_input_tokens_seen": 27728384,1008 "step": 500,1009 "train_runtime": 2984.0872,1010 "train_tokens_per_second": 9292.0821011 },1012 {1013 "epoch": 0.20330112721417068,1014 "grad_norm": 0.8811629303030996,1015 "learning_rate": 9.748198494501598e-06,1016 "loss": 0.4464,1017 "num_input_tokens_seen": 27995208,1018 "step": 505,1019 "train_runtime": 3012.725,1020 "train_tokens_per_second": 9292.3211021 },1022 {1023 "epoch": 0.20531400966183574,1024 "grad_norm": 0.8332138484162837,1025 "learning_rate": 9.743221069314293e-06,1026 "loss": 0.4636,1027 "num_input_tokens_seen": 28282768,1028 "step": 510,1029 "train_runtime": 3050.6012,1030 "train_tokens_per_second": 9271.2111031 },1032 {1033 "epoch": 0.2073268921095008,1034 "grad_norm": 1.0108628601807634,1035 "learning_rate": 9.73819622543344e-06,1036 "loss": 0.4625,1037 "num_input_tokens_seen": 28551128,1038 "step": 515,1039 "train_runtime": 3085.8372,1040 "train_tokens_per_second": 9252.3121041 },1042 {1043 "epoch": 0.20933977455716588,1044 "grad_norm": 0.8787448272227463,1045 "learning_rate": 9.733124013093158e-06,1046 "loss": 0.4933,1047 "num_input_tokens_seen": 28811192,1048 "step": 520,1049 "train_runtime": 3119.0151,1050 "train_tokens_per_second": 9237.2721051 },1052 {1053 "epoch": 0.2113526570048309,1054 "grad_norm": 0.9083794945005091,1055 "learning_rate": 9.728004483001117e-06,1056 "loss": 0.4467,1057 "num_input_tokens_seen": 29059944,1058 "step": 525,1059 "train_runtime": 3148.6589,1060 "train_tokens_per_second": 9229.3081061 },1062 {1063 "epoch": 0.21336553945249598,1064 "grad_norm": 0.9675936515894851,1065 "learning_rate": 9.722837686338025e-06,1066 "loss": 0.4537,1067 "num_input_tokens_seen": 29359232,1068 "step": 530,1069 "train_runtime": 3177.5706,1070 "train_tokens_per_second": 9239.5221071 },1072 {1073 "epoch": 0.21537842190016104,1074 "grad_norm": 0.8837171449614337,1075 "learning_rate": 9.717623674757126e-06,1076 "loss": 0.4708,1077 "num_input_tokens_seen": 29641328,1078 "step": 535,1079 "train_runtime": 3209.9208,1080 "train_tokens_per_second": 9234.2861081 },1082 {1083 "epoch": 0.21739130434782608,1084 "grad_norm": 0.7986281586917634,1085 "learning_rate": 9.712362500383678e-06,1086 "loss": 0.4612,1087 "num_input_tokens_seen": 29911064,1088 "step": 540,1089 "train_runtime": 3238.9396,1090 "train_tokens_per_second": 9234.8321091 },1092 {1093 "epoch": 0.21940418679549115,1094 "grad_norm": 0.8703945257775082,1095 "learning_rate": 9.707054215814428e-06,1096 "loss": 0.4375,1097 "num_input_tokens_seen": 30189032,1098 "step": 545,1099 "train_runtime": 3272.7725,1100 "train_tokens_per_second": 9224.2991101 },1102 {1103 "epoch": 0.2214170692431562,1104 "grad_norm": 0.8211355084617955,1105 "learning_rate": 9.7016988741171e-06,1106 "loss": 0.4562,1107 "num_input_tokens_seen": 30489720,1108 "step": 550,1109 "train_runtime": 3306.9035,1110 "train_tokens_per_second": 9220.0211111 },1112 {1113 "epoch": 0.22342995169082125,1114 "grad_norm": 0.8200822471994678,1115 "learning_rate": 9.696296528829847e-06,1116 "loss": 0.4629,1117 "num_input_tokens_seen": 30755376,1118 "step": 555,1119 "train_runtime": 3326.6834,1120 "train_tokens_per_second": 9245.0571121 },1122 {1123 "epoch": 0.22544283413848631,1124 "grad_norm": 0.8793668514223952,1125 "learning_rate": 9.690847233960723e-06,1126 "loss": 0.4438,1127 "num_input_tokens_seen": 31000552,1128 "step": 560,1129 "train_runtime": 3356.3594,1130 "train_tokens_per_second": 9236.3621131 },1132 {1133 "epoch": 0.22745571658615138,1134 "grad_norm": 0.8181596604472655,1135 "learning_rate": 9.685351043987151e-06,1136 "loss": 0.455,1137 "num_input_tokens_seen": 31284360,1138 "step": 565,1139 "train_runtime": 3385.453,1140 "train_tokens_per_second": 9240.8191141 },1142 {1143 "epoch": 0.22946859903381642,1144 "grad_norm": 0.8709313822510947,1145 "learning_rate": 9.679808013855367e-06,1146 "loss": 0.4755,1147 "num_input_tokens_seen": 31590160,1148 "step": 570,1149 "train_runtime": 3420.896,1150 "train_tokens_per_second": 9234.471151 },1152 {1153 "epoch": 0.23148148148148148,1154 "grad_norm": 0.8219481315168611,1155 "learning_rate": 9.674218198979876e-06,1156 "loss": 0.4564,1157 "num_input_tokens_seen": 31891040,1158 "step": 575,1159 "train_runtime": 3453.0585,1160 "train_tokens_per_second": 9235.5921161 },1162 {1163 "epoch": 0.23349436392914655,1164 "grad_norm": 0.7890669251783218,1165 "learning_rate": 9.668581655242896e-06,1166 "loss": 0.4195,1167 "num_input_tokens_seen": 32172592,1168 "step": 580,1169 "train_runtime": 3478.2807,1170 "train_tokens_per_second": 9249.5671171 },1172 {1173 "epoch": 0.23550724637681159,1174 "grad_norm": 0.7996915699369995,1175 "learning_rate": 9.662898438993803e-06,1176 "loss": 0.4326,1177 "num_input_tokens_seen": 32453192,1178 "step": 585,1179 "train_runtime": 3513.1942,1180 "train_tokens_per_second": 9237.5171181 },1182 {1183 "epoch": 0.23752012882447665,1184 "grad_norm": 0.8486263117718159,1185 "learning_rate": 9.657168607048564e-06,1186 "loss": 0.4261,1187 "num_input_tokens_seen": 32734816,1188 "step": 590,1189 "train_runtime": 3535.6832,1190 "train_tokens_per_second": 9258.4131191 },1192 {1193 "epoch": 0.23953301127214172,1194 "grad_norm": 0.8253459827233957,1195 "learning_rate": 9.651392216689167e-06,1196 "loss": 0.4395,1197 "num_input_tokens_seen": 33026104,1198 "step": 595,1199 "train_runtime": 3564.8102,1200 "train_tokens_per_second": 9264.477