cuong1692001/Terminal-debugging
013
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": 8692,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.001150483202945237,14 "grad_norm": 1.766325007533239,15 "learning_rate": 9.999994774591762e-06,16 "loss": 0.909,17 "num_input_tokens_seen": 284352,18 "step": 5,19 "train_runtime": 31.8621,20 "train_tokens_per_second": 8924.46721 },22 {23 "epoch": 0.002300966405890474,24 "grad_norm": 1.4977177815945257,25 "learning_rate": 9.999973546389506e-06,26 "loss": 0.7805,27 "num_input_tokens_seen": 581176,28 "step": 10,29 "train_runtime": 59.5781,30 "train_tokens_per_second": 9754.86431 },32 {33 "epoch": 0.003451449608835711,34 "grad_norm": 1.0829632671990435,35 "learning_rate": 9.999935988874494e-06,36 "loss": 0.7063,37 "num_input_tokens_seen": 866224,38 "step": 15,39 "train_runtime": 95.5027,40 "train_tokens_per_second": 9070.14941 },42 {43 "epoch": 0.004601932811780948,44 "grad_norm": 0.9748199320947489,45 "learning_rate": 9.999882102169385e-06,46 "loss": 0.6595,47 "num_input_tokens_seen": 1158400,48 "step": 20,49 "train_runtime": 129.0961,50 "train_tokens_per_second": 8973.16251 },52 {53 "epoch": 0.005752416014726185,54 "grad_norm": 1.2093320932662874,55 "learning_rate": 9.999811886450166e-06,56 "loss": 0.6575,57 "num_input_tokens_seen": 1463096,58 "step": 25,59 "train_runtime": 150.0408,60 "train_tokens_per_second": 9751.32361 },62 {63 "epoch": 0.006902899217671422,64 "grad_norm": 0.9828100334290493,65 "learning_rate": 9.999725341946154e-06,66 "loss": 0.658,67 "num_input_tokens_seen": 1758224,68 "step": 30,69 "train_runtime": 176.7733,70 "train_tokens_per_second": 9946.20871 },72 {73 "epoch": 0.008053382420616659,74 "grad_norm": 0.9382389824038813,75 "learning_rate": 9.999622468939991e-06,76 "loss": 0.6512,77 "num_input_tokens_seen": 2042552,78 "step": 35,79 "train_runtime": 198.0886,80 "train_tokens_per_second": 10311.30681 },82 {83 "epoch": 0.009203865623561895,84 "grad_norm": 1.0289259709553886,85 "learning_rate": 9.999503267767651e-06,86 "loss": 0.6327,87 "num_input_tokens_seen": 2347032,88 "step": 40,89 "train_runtime": 223.1623,90 "train_tokens_per_second": 10517.15591 },92 {93 "epoch": 0.010354348826507133,94 "grad_norm": 1.1816159841971012,95 "learning_rate": 9.999367738818428e-06,96 "loss": 0.6656,97 "num_input_tokens_seen": 2594752,98 "step": 45,99 "train_runtime": 251.4412,100 "train_tokens_per_second": 10319.516101 },102 {103 "epoch": 0.01150483202945237,104 "grad_norm": 1.0940534462802884,105 "learning_rate": 9.999215882534944e-06,106 "loss": 0.6404,107 "num_input_tokens_seen": 2893800,108 "step": 50,109 "train_runtime": 287.4078,110 "train_tokens_per_second": 10068.619111 },112 {113 "epoch": 0.012655315232397607,114 "grad_norm": 1.0086989065703342,115 "learning_rate": 9.999047699413145e-06,116 "loss": 0.6297,117 "num_input_tokens_seen": 3210000,118 "step": 55,119 "train_runtime": 313.5712,120 "train_tokens_per_second": 10236.911121 },122 {123 "epoch": 0.013805798435342844,124 "grad_norm": 1.0251171653500366,125 "learning_rate": 9.998863190002293e-06,126 "loss": 0.6326,127 "num_input_tokens_seen": 3500424,128 "step": 60,129 "train_runtime": 347.0606,130 "train_tokens_per_second": 10085.916131 },132 {133 "epoch": 0.01495628163828808,134 "grad_norm": 0.9196778163732294,135 "learning_rate": 9.998662354904978e-06,136 "loss": 0.6206,137 "num_input_tokens_seen": 3781008,138 "step": 65,139 "train_runtime": 377.0088,140 "train_tokens_per_second": 10028.965141 },142 {143 "epoch": 0.016106764841233318,144 "grad_norm": 1.104080574342752,145 "learning_rate": 9.9984451947771e-06,146 "loss": 0.5788,147 "num_input_tokens_seen": 4055520,148 "step": 70,149 "train_runtime": 403.5576,150 "train_tokens_per_second": 10049.421151 },152 {153 "epoch": 0.017257248044178556,154 "grad_norm": 1.0385273575353133,155 "learning_rate": 9.99821171032788e-06,156 "loss": 0.5984,157 "num_input_tokens_seen": 4364144,158 "step": 75,159 "train_runtime": 424.762,160 "train_tokens_per_second": 10274.328161 },162 {163 "epoch": 0.01840773124712379,164 "grad_norm": 1.066202873643926,165 "learning_rate": 9.997961902319848e-06,166 "loss": 0.6195,167 "num_input_tokens_seen": 4676760,168 "step": 80,169 "train_runtime": 450.8342,170 "train_tokens_per_second": 10373.569171 },172 {173 "epoch": 0.019558214450069028,174 "grad_norm": 1.012668713401408,175 "learning_rate": 9.997695771568848e-06,176 "loss": 0.595,177 "num_input_tokens_seen": 4966944,178 "step": 85,179 "train_runtime": 475.4493,180 "train_tokens_per_second": 10446.842181 },182 {183 "epoch": 0.020708697653014266,184 "grad_norm": 1.193830281082122,185 "learning_rate": 9.997413318944033e-06,186 "loss": 0.6066,187 "num_input_tokens_seen": 5240672,188 "step": 90,189 "train_runtime": 502.9857,190 "train_tokens_per_second": 10419.127191 },192 {193 "epoch": 0.021859180855959504,194 "grad_norm": 2.0956209535412063,195 "learning_rate": 9.997114545367856e-06,196 "loss": 0.5713,197 "num_input_tokens_seen": 5529784,198 "step": 95,199 "train_runtime": 535.9077,200 "train_tokens_per_second": 10318.538201 },202 {203 "epoch": 0.02300966405890474,204 "grad_norm": 0.9018337526368458,205 "learning_rate": 9.996799451816078e-06,206 "loss": 0.5942,207 "num_input_tokens_seen": 5817360,208 "step": 100,209 "train_runtime": 563.1315,210 "train_tokens_per_second": 10330.375211 },212 {213 "epoch": 0.024160147261849976,214 "grad_norm": 1.1880000462108928,215 "learning_rate": 9.996468039317756e-06,216 "loss": 0.5891,217 "num_input_tokens_seen": 6100040,218 "step": 105,219 "train_runtime": 589.9606,220 "train_tokens_per_second": 10339.742221 },222 {223 "epoch": 0.025310630464795213,224 "grad_norm": 1.0080850299533164,225 "learning_rate": 9.996120308955243e-06,226 "loss": 0.5686,227 "num_input_tokens_seen": 6372616,228 "step": 110,229 "train_runtime": 617.0443,230 "train_tokens_per_second": 10327.648231 },232 {233 "epoch": 0.02646111366774045,234 "grad_norm": 0.9918805875206164,235 "learning_rate": 9.995756261864184e-06,236 "loss": 0.5667,237 "num_input_tokens_seen": 6662664,238 "step": 115,239 "train_runtime": 648.8213,240 "train_tokens_per_second": 10268.874241 },242 {243 "epoch": 0.02761159687068569,244 "grad_norm": 1.0576316511920598,245 "learning_rate": 9.995375899233515e-06,246 "loss": 0.5739,247 "num_input_tokens_seen": 6956296,248 "step": 120,249 "train_runtime": 667.2231,250 "train_tokens_per_second": 10425.743251 },252 {253 "epoch": 0.028762080073630927,254 "grad_norm": 0.9691694911320798,255 "learning_rate": 9.994979222305453e-06,256 "loss": 0.5808,257 "num_input_tokens_seen": 7253584,258 "step": 125,259 "train_runtime": 693.7493,260 "train_tokens_per_second": 10455.627261 },262 {263 "epoch": 0.02991256327657616,264 "grad_norm": 1.3106007861799989,265 "learning_rate": 9.994566232375498e-06,266 "loss": 0.5744,267 "num_input_tokens_seen": 7525768,268 "step": 130,269 "train_runtime": 721.004,270 "train_tokens_per_second": 10437.901271 },272 {273 "epoch": 0.0310630464795214,274 "grad_norm": 0.9771512086576776,275 "learning_rate": 9.994136930792425e-06,276 "loss": 0.6382,277 "num_input_tokens_seen": 7805496,278 "step": 135,279 "train_runtime": 747.2073,280 "train_tokens_per_second": 10446.226281 },282 {283 "epoch": 0.032213529682466636,284 "grad_norm": 1.1108336391930276,285 "learning_rate": 9.993691318958282e-06,286 "loss": 0.5925,287 "num_input_tokens_seen": 8088080,288 "step": 140,289 "train_runtime": 769.5601,290 "train_tokens_per_second": 10510.005291 },292 {293 "epoch": 0.033364012885411874,294 "grad_norm": 1.3412472988209507,295 "learning_rate": 9.993229398328382e-06,296 "loss": 0.5801,297 "num_input_tokens_seen": 8379744,298 "step": 145,299 "train_runtime": 797.736,300 "train_tokens_per_second": 10504.407301 },302 {303 "epoch": 0.03451449608835711,304 "grad_norm": 1.1964882303243665,305 "learning_rate": 9.992751170411306e-06,306 "loss": 0.5853,307 "num_input_tokens_seen": 8678464,308 "step": 150,309 "train_runtime": 826.7935,310 "train_tokens_per_second": 10496.531311 },312 {313 "epoch": 0.03566497929130235,314 "grad_norm": 1.0278764880484794,315 "learning_rate": 9.992256636768884e-06,316 "loss": 0.5896,317 "num_input_tokens_seen": 8982064,318 "step": 155,319 "train_runtime": 856.6555,320 "train_tokens_per_second": 10485.037321 },322 {323 "epoch": 0.03681546249424758,324 "grad_norm": 1.071254429302389,325 "learning_rate": 9.991745799016206e-06,326 "loss": 0.5829,327 "num_input_tokens_seen": 9262432,328 "step": 160,329 "train_runtime": 891.8273,330 "train_tokens_per_second": 10385.903331 },332 {333 "epoch": 0.03796594569719282,334 "grad_norm": 1.0691648184325047,335 "learning_rate": 9.991218658821609e-06,336 "loss": 0.6314,337 "num_input_tokens_seen": 9517952,338 "step": 165,339 "train_runtime": 917.441,340 "train_tokens_per_second": 10374.457341 },342 {343 "epoch": 0.039116428900138056,344 "grad_norm": 0.9273755042376516,345 "learning_rate": 9.990675217906665e-06,346 "loss": 0.5316,347 "num_input_tokens_seen": 9818952,348 "step": 170,349 "train_runtime": 948.3611,350 "train_tokens_per_second": 10353.601351 },352 {353 "epoch": 0.040266912103083294,354 "grad_norm": 0.9904068681419756,355 "learning_rate": 9.990115478046189e-06,356 "loss": 0.5686,357 "num_input_tokens_seen": 10103144,358 "step": 175,359 "train_runtime": 974.2285,360 "train_tokens_per_second": 10370.405361 },362 {363 "epoch": 0.04141739530602853,364 "grad_norm": 0.9288190784163819,365 "learning_rate": 9.989539441068223e-06,366 "loss": 0.5753,367 "num_input_tokens_seen": 10404968,368 "step": 180,369 "train_runtime": 998.2122,370 "train_tokens_per_second": 10423.603371 },372 {373 "epoch": 0.04256787850897377,374 "grad_norm": 1.1200237777337045,375 "learning_rate": 9.988947108854037e-06,376 "loss": 0.6008,377 "num_input_tokens_seen": 10699984,378 "step": 185,379 "train_runtime": 1028.4739,380 "train_tokens_per_second": 10403.749381 },382 {383 "epoch": 0.04371836171191901,384 "grad_norm": 1.118565286047391,385 "learning_rate": 9.988338483338116e-06,386 "loss": 0.5398,387 "num_input_tokens_seen": 11011088,388 "step": 190,389 "train_runtime": 1050.4787,390 "train_tokens_per_second": 10481.971391 },392 {393 "epoch": 0.044868844914864245,394 "grad_norm": 0.8817271642109321,395 "learning_rate": 9.987713566508156e-06,396 "loss": 0.5305,397 "num_input_tokens_seen": 11312176,398 "step": 195,399 "train_runtime": 1080.8153,400 "train_tokens_per_second": 10466.336401 },402 {403 "epoch": 0.04601932811780948,404 "grad_norm": 1.255494172726284,405 "learning_rate": 9.987072360405061e-06,406 "loss": 0.5585,407 "num_input_tokens_seen": 11565944,408 "step": 200,409 "train_runtime": 1108.9369,410 "train_tokens_per_second": 10429.758411 },412 {413 "epoch": 0.04716981132075472,414 "grad_norm": 0.9772429802936903,415 "learning_rate": 9.986414867122935e-06,416 "loss": 0.5766,417 "num_input_tokens_seen": 11853880,418 "step": 205,419 "train_runtime": 1134.9374,420 "train_tokens_per_second": 10444.523421 },422 {423 "epoch": 0.04832029452369995,424 "grad_norm": 1.0695339316876415,425 "learning_rate": 9.98574108880907e-06,426 "loss": 0.5334,427 "num_input_tokens_seen": 12116936,428 "step": 210,429 "train_runtime": 1161.7404,430 "train_tokens_per_second": 10429.986431 },432 {433 "epoch": 0.04947077772664519,434 "grad_norm": 0.9195037498512013,435 "learning_rate": 9.985051027663945e-06,436 "loss": 0.5518,437 "num_input_tokens_seen": 12418528,438 "step": 215,439 "train_runtime": 1192.4275,440 "train_tokens_per_second": 10414.494441 },442 {443 "epoch": 0.05062126092959043,444 "grad_norm": 1.0662779613209175,445 "learning_rate": 9.984344685941217e-06,446 "loss": 0.5567,447 "num_input_tokens_seen": 12697288,448 "step": 220,449 "train_runtime": 1222.9874,450 "train_tokens_per_second": 10382.191451 },452 {453 "epoch": 0.051771744132535664,454 "grad_norm": 0.9734149773108488,455 "learning_rate": 9.983622065947714e-06,456 "loss": 0.5364,457 "num_input_tokens_seen": 12984792,458 "step": 225,459 "train_runtime": 1251.4028,460 "train_tokens_per_second": 10376.189461 },462 {463 "epoch": 0.0529222273354809,464 "grad_norm": 0.8982545540145891,465 "learning_rate": 9.982883170043427e-06,466 "loss": 0.5636,467 "num_input_tokens_seen": 13245176,468 "step": 230,469 "train_runtime": 1278.6588,470 "train_tokens_per_second": 10358.648471 },472 {473 "epoch": 0.05407271053842614,474 "grad_norm": 0.8897518831605272,475 "learning_rate": 9.982128000641497e-06,476 "loss": 0.5721,477 "num_input_tokens_seen": 13530616,478 "step": 235,479 "train_runtime": 1304.7999,480 "train_tokens_per_second": 10369.878481 },482 {483 "epoch": 0.05522319374137138,484 "grad_norm": 0.9607187232316375,485 "learning_rate": 9.981356560208222e-06,486 "loss": 0.5558,487 "num_input_tokens_seen": 13825816,488 "step": 240,489 "train_runtime": 1330.206,490 "train_tokens_per_second": 10393.74491 },492 {493 "epoch": 0.056373676944316616,494 "grad_norm": 0.8575267448085204,495 "learning_rate": 9.98056885126303e-06,496 "loss": 0.5254,497 "num_input_tokens_seen": 14122792,498 "step": 245,499 "train_runtime": 1356.6815,500 "train_tokens_per_second": 10409.807501 },502 {503 "epoch": 0.05752416014726185,504 "grad_norm": 0.9608955416662621,505 "learning_rate": 9.979764876378484e-06,506 "loss": 0.5769,507 "num_input_tokens_seen": 14423112,508 "step": 250,509 "train_runtime": 1390.6529,510 "train_tokens_per_second": 10371.468511 },512 {513 "epoch": 0.058674643350207084,514 "grad_norm": 0.9768421398121152,515 "learning_rate": 9.978944638180271e-06,516 "loss": 0.5385,517 "num_input_tokens_seen": 14734024,518 "step": 255,519 "train_runtime": 1422.7513,520 "train_tokens_per_second": 10356.008521 },522 {523 "epoch": 0.05982512655315232,524 "grad_norm": 1.169476358539382,525 "learning_rate": 9.97810813934719e-06,526 "loss": 0.5779,527 "num_input_tokens_seen": 15016184,528 "step": 260,529 "train_runtime": 1452.7422,530 "train_tokens_per_second": 10336.441531 },532 {533 "epoch": 0.06097560975609756,534 "grad_norm": 1.196714112519288,535 "learning_rate": 9.977255382611144e-06,536 "loss": 0.5521,537 "num_input_tokens_seen": 15320184,538 "step": 265,539 "train_runtime": 1478.8566,540 "train_tokens_per_second": 10359.479541 },542 {543 "epoch": 0.0621260929590428,544 "grad_norm": 1.0003269070465257,545 "learning_rate": 9.976386370757136e-06,546 "loss": 0.5625,547 "num_input_tokens_seen": 15626896,548 "step": 270,549 "train_runtime": 1506.8821,550 "train_tokens_per_second": 10370.351551 },552 {553 "epoch": 0.06327657616198804,554 "grad_norm": 0.7872853414934483,555 "learning_rate": 9.975501106623253e-06,556 "loss": 0.5501,557 "num_input_tokens_seen": 15947392,558 "step": 275,559 "train_runtime": 1545.8634,560 "train_tokens_per_second": 10316.171561 },562 {563 "epoch": 0.06442705936493327,564 "grad_norm": 1.0130639433922382,565 "learning_rate": 9.974599593100664e-06,566 "loss": 0.562,567 "num_input_tokens_seen": 16241840,568 "step": 280,569 "train_runtime": 1577.6089,570 "train_tokens_per_second": 10295.226571 },572 {573 "epoch": 0.06557754256787851,574 "grad_norm": 0.9982978729720613,575 "learning_rate": 9.9736818331336e-06,576 "loss": 0.5631,577 "num_input_tokens_seen": 16541464,578 "step": 285,579 "train_runtime": 1601.9517,580 "train_tokens_per_second": 10325.82581 },582 {583 "epoch": 0.06672802577082375,584 "grad_norm": 1.016015970892931,585 "learning_rate": 9.972747829719355e-06,586 "loss": 0.548,587 "num_input_tokens_seen": 16821552,588 "step": 290,589 "train_runtime": 1626.6357,590 "train_tokens_per_second": 10341.315591 },592 {593 "epoch": 0.06787850897376899,594 "grad_norm": 0.8613258143359411,595 "learning_rate": 9.971797585908277e-06,596 "loss": 0.5364,597 "num_input_tokens_seen": 17104560,598 "step": 295,599 "train_runtime": 1657.4111,600 "train_tokens_per_second": 10320.047601 },602 {603 "epoch": 0.06902899217671422,604 "grad_norm": 1.1507039450592036,605 "learning_rate": 9.970831104803742e-06,606 "loss": 0.6015,607 "num_input_tokens_seen": 17368896,608 "step": 300,609 "train_runtime": 1686.2216,610 "train_tokens_per_second": 10300.482611 },612 {613 "epoch": 0.07017947537965946,614 "grad_norm": 1.086809604655306,615 "learning_rate": 9.969848389562162e-06,616 "loss": 0.5456,617 "num_input_tokens_seen": 17630184,618 "step": 305,619 "train_runtime": 1716.0138,620 "train_tokens_per_second": 10273.917621 },622 {623 "epoch": 0.0713299585826047,624 "grad_norm": 1.1941199818069477,625 "learning_rate": 9.968849443392972e-06,626 "loss": 0.55,627 "num_input_tokens_seen": 17920776,628 "step": 310,629 "train_runtime": 1738.7959,630 "train_tokens_per_second": 10306.429631 },632 {633 "epoch": 0.07248044178554994,634 "grad_norm": 0.8336846595195279,635 "learning_rate": 9.967834269558604e-06,636 "loss": 0.5234,637 "num_input_tokens_seen": 18202152,638 "step": 315,639 "train_runtime": 1768.6705,640 "train_tokens_per_second": 10291.432641 },642 {643 "epoch": 0.07363092498849516,644 "grad_norm": 0.9281786875387816,645 "learning_rate": 9.966802871374497e-06,646 "loss": 0.5662,647 "num_input_tokens_seen": 18465944,648 "step": 320,649 "train_runtime": 1790.2205,650 "train_tokens_per_second": 10314.899651 },652 {653 "epoch": 0.0747814081914404,654 "grad_norm": 1.0455199298076596,655 "learning_rate": 9.965755252209073e-06,656 "loss": 0.5516,657 "num_input_tokens_seen": 18760320,658 "step": 325,659 "train_runtime": 1822.0113,660 "train_tokens_per_second": 10296.49661 },662 {663 "epoch": 0.07593189139438564,664 "grad_norm": 0.9289305777270558,665 "learning_rate": 9.96469141548373e-06,666 "loss": 0.5709,667 "num_input_tokens_seen": 19050304,668 "step": 330,669 "train_runtime": 1849.3434,670 "train_tokens_per_second": 10301.118671 },672 {673 "epoch": 0.07708237459733087,674 "grad_norm": 0.9784627057003694,675 "learning_rate": 9.963611364672831e-06,676 "loss": 0.544,677 "num_input_tokens_seen": 19317816,678 "step": 335,679 "train_runtime": 1875.7962,680 "train_tokens_per_second": 10298.462681 },682 {683 "epoch": 0.07823285780027611,684 "grad_norm": 6.088806899922095,685 "learning_rate": 9.962515103303694e-06,686 "loss": 0.5318,687 "num_input_tokens_seen": 19588960,688 "step": 340,689 "train_runtime": 1904.7419,690 "train_tokens_per_second": 10284.312691 },692 {693 "epoch": 0.07938334100322135,694 "grad_norm": 1.1571082102262917,695 "learning_rate": 9.961402634956575e-06,696 "loss": 0.518,697 "num_input_tokens_seen": 19882032,698 "step": 345,699 "train_runtime": 1929.4507,700 "train_tokens_per_second": 10304.504701 },702 {703 "epoch": 0.08053382420616659,704 "grad_norm": 0.8761677171112716,705 "learning_rate": 9.96027396326466e-06,706 "loss": 0.5416,707 "num_input_tokens_seen": 20166528,708 "step": 350,709 "train_runtime": 1960.0909,710 "train_tokens_per_second": 10288.568711 },712 {713 "epoch": 0.08168430740911183,714 "grad_norm": 1.0659126887122947,715 "learning_rate": 9.959129091914058e-06,716 "loss": 0.5246,717 "num_input_tokens_seen": 20442152,718 "step": 355,719 "train_runtime": 1988.8978,720 "train_tokens_per_second": 10278.131721 },722 {723 "epoch": 0.08283479061205706,724 "grad_norm": 1.064296509118394,725 "learning_rate": 9.957968024643781e-06,726 "loss": 0.5448,727 "num_input_tokens_seen": 20752112,728 "step": 360,729 "train_runtime": 2014.342,730 "train_tokens_per_second": 10302.179731 },732 {733 "epoch": 0.0839852738150023,734 "grad_norm": 0.8506445344617584,735 "learning_rate": 9.956790765245733e-06,736 "loss": 0.5319,737 "num_input_tokens_seen": 21029760,738 "step": 365,739 "train_runtime": 2041.1344,740 "train_tokens_per_second": 10302.977741 },742 {743 "epoch": 0.08513575701794754,744 "grad_norm": 1.032001373361533,745 "learning_rate": 9.955597317564705e-06,746 "loss": 0.5422,747 "num_input_tokens_seen": 21309112,748 "step": 370,749 "train_runtime": 2065.9088,750 "train_tokens_per_second": 10314.643751 },752 {753 "epoch": 0.08628624022089278,754 "grad_norm": 0.9840747877199333,755 "learning_rate": 9.95438768549835e-06,756 "loss": 0.5619,757 "num_input_tokens_seen": 21578216,758 "step": 375,759 "train_runtime": 2096.2264,760 "train_tokens_per_second": 10293.839761 },762 {763 "epoch": 0.08743672342383801,764 "grad_norm": 0.8861730249408858,765 "learning_rate": 9.953161872997185e-06,766 "loss": 0.5396,767 "num_input_tokens_seen": 21839432,768 "step": 380,769 "train_runtime": 2123.9678,770 "train_tokens_per_second": 10282.374771 },772 {773 "epoch": 0.08858720662678325,774 "grad_norm": 1.1236998152097732,775 "learning_rate": 9.951919884064564e-06,776 "loss": 0.5263,777 "num_input_tokens_seen": 22120760,778 "step": 385,779 "train_runtime": 2155.8674,780 "train_tokens_per_second": 10260.724781 },782 {783 "epoch": 0.08973768982972849,784 "grad_norm": 0.8211935509162231,785 "learning_rate": 9.950661722756674e-06,786 "loss": 0.5293,787 "num_input_tokens_seen": 22395664,788 "step": 390,789 "train_runtime": 2194.2169,790 "train_tokens_per_second": 10206.677791 },792 {793 "epoch": 0.09088817303267373,794 "grad_norm": 0.9524622981909562,795 "learning_rate": 9.949387393182519e-06,796 "loss": 0.5251,797 "num_input_tokens_seen": 22667224,798 "step": 395,799 "train_runtime": 2227.1816,800 "train_tokens_per_second": 10177.537801 },802 {803 "epoch": 0.09203865623561897,804 "grad_norm": 1.0644210310913742,805 "learning_rate": 9.948096899503905e-06,806 "loss": 0.5423,807 "num_input_tokens_seen": 22964224,808 "step": 400,809 "train_runtime": 2255.507,810 "train_tokens_per_second": 10181.402811 },812 {813 "epoch": 0.0931891394385642,814 "grad_norm": 0.7871290726495593,815 "learning_rate": 9.946790245935429e-06,816 "loss": 0.519,817 "num_input_tokens_seen": 23273560,818 "step": 405,819 "train_runtime": 2283.8081,820 "train_tokens_per_second": 10190.681821 },822 {823 "epoch": 0.09433962264150944,824 "grad_norm": 1.044026828487096,825 "learning_rate": 9.945467436744468e-06,826 "loss": 0.5468,827 "num_input_tokens_seen": 23528880,828 "step": 410,829 "train_runtime": 2316.2188,830 "train_tokens_per_second": 10158.315831 },832 {833 "epoch": 0.09549010584445466,834 "grad_norm": 1.0902623094209076,835 "learning_rate": 9.944128476251154e-06,836 "loss": 0.5117,837 "num_input_tokens_seen": 23799000,838 "step": 415,839 "train_runtime": 2343.0969,840 "train_tokens_per_second": 10157.07841 },842 {843 "epoch": 0.0966405890473999,844 "grad_norm": 1.018862344685691,845 "learning_rate": 9.942773368828373e-06,846 "loss": 0.5145,847 "num_input_tokens_seen": 24069432,848 "step": 420,849 "train_runtime": 2372.5444,850 "train_tokens_per_second": 10144.987851 },852 {853 "epoch": 0.09779107225034514,854 "grad_norm": 0.8955069553709278,855 "learning_rate": 9.941402118901743e-06,856 "loss": 0.528,857 "num_input_tokens_seen": 24361648,858 "step": 425,859 "train_runtime": 2399.7621,860 "train_tokens_per_second": 10151.693861 },862 {863 "epoch": 0.09894155545329038,864 "grad_norm": 0.8955055015179952,865 "learning_rate": 9.9400147309496e-06,866 "loss": 0.5352,867 "num_input_tokens_seen": 24625328,868 "step": 430,869 "train_runtime": 2430.0546,870 "train_tokens_per_second": 10133.652871 },872 {873 "epoch": 0.10009203865623562,874 "grad_norm": 0.8142807480260092,875 "learning_rate": 9.938611209502988e-06,876 "loss": 0.5607,877 "num_input_tokens_seen": 24922168,878 "step": 435,879 "train_runtime": 2452.9371,880 "train_tokens_per_second": 10160.133881 },882 {883 "epoch": 0.10124252185918085,884 "grad_norm": 0.9583067011721819,885 "learning_rate": 9.93719155914564e-06,886 "loss": 0.517,887 "num_input_tokens_seen": 25199496,888 "step": 440,889 "train_runtime": 2481.6913,890 "train_tokens_per_second": 10154.162891 },892 {893 "epoch": 0.10239300506212609,894 "grad_norm": 0.877165179724369,895 "learning_rate": 9.935755784513961e-06,896 "loss": 0.5467,897 "num_input_tokens_seen": 25474376,898 "step": 445,899 "train_runtime": 2514.3133,900 "train_tokens_per_second": 10131.743901 },902 {903 "epoch": 0.10354348826507133,904 "grad_norm": 1.033730847295833,905 "learning_rate": 9.93430389029702e-06,906 "loss": 0.5279,907 "num_input_tokens_seen": 25756816,908 "step": 450,909 "train_runtime": 2546.7348,910 "train_tokens_per_second": 10113.663911 },912 {913 "epoch": 0.10469397146801657,914 "grad_norm": 0.8807888279332817,915 "learning_rate": 9.932835881236529e-06,916 "loss": 0.5182,917 "num_input_tokens_seen": 26046896,918 "step": 455,919 "train_runtime": 2570.0847,920 "train_tokens_per_second": 10134.645921 },922 {923 "epoch": 0.1058444546709618,924 "grad_norm": 0.8709703069126551,925 "learning_rate": 9.93135176212683e-06,926 "loss": 0.5625,927 "num_input_tokens_seen": 26355088,928 "step": 460,929 "train_runtime": 2594.2446,930 "train_tokens_per_second": 10159.06931 },932 {933 "epoch": 0.10699493787390704,934 "grad_norm": 1.0813952755458804,935 "learning_rate": 9.929851537814871e-06,936 "loss": 0.545,937 "num_input_tokens_seen": 26650264,938 "step": 465,939 "train_runtime": 2618.5204,940 "train_tokens_per_second": 10177.604941 },942 {943 "epoch": 0.10814542107685228,944 "grad_norm": 0.9977898945576259,945 "learning_rate": 9.928335213200216e-06,946 "loss": 0.5324,947 "num_input_tokens_seen": 26954128,948 "step": 470,949 "train_runtime": 2642.8792,950 "train_tokens_per_second": 10198.774951 },952 {953 "epoch": 0.10929590427979752,954 "grad_norm": 1.006734536570242,955 "learning_rate": 9.92680279323499e-06,956 "loss": 0.5482,957 "num_input_tokens_seen": 27266312,958 "step": 475,959 "train_runtime": 2662.9671,960 "train_tokens_per_second": 10239.072961 },962 {963 "epoch": 0.11044638748274276,964 "grad_norm": 0.9419359743879657,965 "learning_rate": 9.925254282923896e-06,966 "loss": 0.5716,967 "num_input_tokens_seen": 27560256,968 "step": 480,969 "train_runtime": 2691.8246,970 "train_tokens_per_second": 10238.503971 },972 {973 "epoch": 0.111596870685688,974 "grad_norm": 0.7732134565976387,975 "learning_rate": 9.92368968732418e-06,976 "loss": 0.5479,977 "num_input_tokens_seen": 27864632,978 "step": 485,979 "train_runtime": 2718.8595,980 "train_tokens_per_second": 10248.647981 },982 {983 "epoch": 0.11274735388863323,984 "grad_norm": 0.7907335986065439,985 "learning_rate": 9.922109011545629e-06,986 "loss": 0.5408,987 "num_input_tokens_seen": 28152424,988 "step": 490,989 "train_runtime": 2750.0189,990 "train_tokens_per_second": 10237.175991 },992 {993 "epoch": 0.11389783709157847,994 "grad_norm": 0.9177923239631248,995 "learning_rate": 9.920512260750533e-06,996 "loss": 0.5213,997 "num_input_tokens_seen": 28424168,998 "step": 495,999 "train_runtime": 2777.9806,1000 "train_tokens_per_second": 10231.9531001 },1002 {1003 "epoch": 0.1150483202945237,1004 "grad_norm": 0.810363781899224,1005 "learning_rate": 9.918899440153693e-06,1006 "loss": 0.5327,1007 "num_input_tokens_seen": 28728744,1008 "step": 500,1009 "train_runtime": 2811.5996,1010 "train_tokens_per_second": 10217.9361011 },1012 {1013 "epoch": 0.11619880349746893,1014 "grad_norm": 0.8273259840752242,1015 "learning_rate": 9.917270555022384e-06,1016 "loss": 0.5445,1017 "num_input_tokens_seen": 29020200,1018 "step": 505,1019 "train_runtime": 2842.2302,1020 "train_tokens_per_second": 10210.3621021 },1022 {1023 "epoch": 0.11734928670041417,1024 "grad_norm": 0.8743501554990264,1025 "learning_rate": 9.915625610676352e-06,1026 "loss": 0.5142,1027 "num_input_tokens_seen": 29318576,1028 "step": 510,1029 "train_runtime": 2874.7685,1030 "train_tokens_per_second": 10198.5871031 },1032 {1033 "epoch": 0.1184997699033594,1034 "grad_norm": 1.0362492966915384,1035 "learning_rate": 9.913964612487786e-06,1036 "loss": 0.5378,1037 "num_input_tokens_seen": 29605832,1038 "step": 515,1039 "train_runtime": 2897.1651,1040 "train_tokens_per_second": 10218.8971041 },1042 {1043 "epoch": 0.11965025310630464,1044 "grad_norm": 0.9445286539997724,1045 "learning_rate": 9.912287565881309e-06,1046 "loss": 0.5416,1047 "num_input_tokens_seen": 29897040,1048 "step": 520,1049 "train_runtime": 2923.3717,1050 "train_tokens_per_second": 10226.9031051 },1052 {1053 "epoch": 0.12080073630924988,1054 "grad_norm": 1.2184416084495149,1055 "learning_rate": 9.910594476333948e-06,1056 "loss": 0.5139,1057 "num_input_tokens_seen": 30202456,1058 "step": 525,1059 "train_runtime": 2957.9452,1060 "train_tokens_per_second": 10210.621061 },1062 {1063 "epoch": 0.12195121951219512,1064 "grad_norm": 0.899487961407593,1065 "learning_rate": 9.908885349375134e-06,1066 "loss": 0.5275,1067 "num_input_tokens_seen": 30480312,1068 "step": 530,1069 "train_runtime": 2989.7734,1070 "train_tokens_per_second": 10194.8571071 },1072 {1073 "epoch": 0.12310170271514036,1074 "grad_norm": 0.884663011836274,1075 "learning_rate": 9.907160190586672e-06,1076 "loss": 0.5484,1077 "num_input_tokens_seen": 30753776,1078 "step": 535,1079 "train_runtime": 3017.3488,1080 "train_tokens_per_second": 10192.3171081 },1082 {1083 "epoch": 0.1242521859180856,1084 "grad_norm": 0.8189189114343147,1085 "learning_rate": 9.905419005602722e-06,1086 "loss": 0.5192,1087 "num_input_tokens_seen": 31059160,1088 "step": 540,1089 "train_runtime": 3041.7403,1090 "train_tokens_per_second": 10210.9841091 },1092 {1093 "epoch": 0.12540266912103085,1094 "grad_norm": 0.9536943662035456,1095 "learning_rate": 9.903661800109781e-06,1096 "loss": 0.5218,1097 "num_input_tokens_seen": 31355496,1098 "step": 545,1099 "train_runtime": 3074.1292,1100 "train_tokens_per_second": 10199.7981101 },1102 {1103 "epoch": 0.12655315232397607,1104 "grad_norm": 0.8772730840776594,1105 "learning_rate": 9.901888579846675e-06,1106 "loss": 0.5546,1107 "num_input_tokens_seen": 31639080,1108 "step": 550,1109 "train_runtime": 3099.4811,1110 "train_tokens_per_second": 10207.8641111 },1112 {1113 "epoch": 0.1277036355269213,1114 "grad_norm": 0.7834258454271067,1115 "learning_rate": 9.900099350604526e-06,1116 "loss": 0.5542,1117 "num_input_tokens_seen": 31917480,1118 "step": 555,1119 "train_runtime": 3125.6019,1120 "train_tokens_per_second": 10211.6271121 },1122 {1123 "epoch": 0.12885411872986655,1124 "grad_norm": 0.8703404368890796,1125 "learning_rate": 9.898294118226745e-06,1126 "loss": 0.5174,1127 "num_input_tokens_seen": 32206480,1128 "step": 560,1129 "train_runtime": 3155.9154,1130 "train_tokens_per_second": 10205.1151131 },1132 {1133 "epoch": 0.13000460193281177,1134 "grad_norm": 0.9505220431522421,1135 "learning_rate": 9.896472888609001e-06,1136 "loss": 0.535,1137 "num_input_tokens_seen": 32485928,1138 "step": 565,1139 "train_runtime": 3179.0395,1140 "train_tokens_per_second": 10218.7871141 },1142 {1143 "epoch": 0.13115508513575702,1144 "grad_norm": 0.9252931343781008,1145 "learning_rate": 9.894635667699212e-06,1146 "loss": 0.5378,1147 "num_input_tokens_seen": 32786264,1148 "step": 570,1149 "train_runtime": 3210.3412,1150 "train_tokens_per_second": 10212.7041151 },1152 {1153 "epoch": 0.13230556833870225,1154 "grad_norm": 0.9774445789504773,1155 "learning_rate": 9.892782461497521e-06,1156 "loss": 0.5294,1157 "num_input_tokens_seen": 33065936,1158 "step": 575,1159 "train_runtime": 3237.4802,1160 "train_tokens_per_second": 10213.4791161 },1162 {1163 "epoch": 0.1334560515416475,1164 "grad_norm": 0.8356052100744731,1165 "learning_rate": 9.890913276056277e-06,1166 "loss": 0.5236,1167 "num_input_tokens_seen": 33338616,1168 "step": 580,1169 "train_runtime": 3265.1369,1170 "train_tokens_per_second": 10210.481171 },1172 {1173 "epoch": 0.13460653474459272,1174 "grad_norm": 0.9076754443737494,1175 "learning_rate": 9.889028117480013e-06,1176 "loss": 0.5284,1177 "num_input_tokens_seen": 33631240,1178 "step": 585,1179 "train_runtime": 3296.2439,1180 "train_tokens_per_second": 10202.8981181 },1182 {1183 "epoch": 0.13575701794753797,1184 "grad_norm": 0.8333609620536444,1185 "learning_rate": 9.887126991925433e-06,1186 "loss": 0.538,1187 "num_input_tokens_seen": 33911824,1188 "step": 590,1189 "train_runtime": 3324.1737,1190 "train_tokens_per_second": 10201.581191 },1192 {1193 "epoch": 0.1369075011504832,1194 "grad_norm": 0.8067824652891697,1195 "learning_rate": 9.885209905601382e-06,1196 "loss": 0.5064,1197 "num_input_tokens_seen": 34212416,1198 "step": 595,1199 "train_runtime": 3348.7537,1200 "train_tokens_per_second": 10216.462