FormlessAI/Qwen2.5-7B-Instruct-Reasoning-Unsloth
014
1{2 "best_global_step": null,3 "best_metric": null,4 "best_model_checkpoint": null,5 "epoch": 1.0,6 "eval_steps": 156,7 "global_step": 1556,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.0006428801028608164,14 "grad_norm": 1.4815346002578735,15 "learning_rate": 0.0,16 "loss": 3.0354,17 "num_input_tokens_seen": 58240,18 "step": 1,19 "train_runtime": 14.0904,20 "train_tokens_per_second": 4133.3121 },22 {23 "epoch": 0.0012857602057216328,24 "grad_norm": 1.3779746294021606,25 "learning_rate": 4e-05,26 "loss": 2.9584,27 "num_input_tokens_seen": 102384,28 "step": 2,29 "train_runtime": 20.0807,30 "train_tokens_per_second": 5098.63831 },32 {33 "epoch": 0.0019286403085824494,34 "grad_norm": 1.3874965906143188,35 "learning_rate": 8e-05,36 "loss": 3.1628,37 "num_input_tokens_seen": 164480,38 "step": 3,39 "train_runtime": 29.0202,40 "train_tokens_per_second": 5667.77441 },42 {43 "epoch": 0.0025715204114432656,44 "grad_norm": 1.467178225517273,45 "learning_rate": 0.00012,46 "loss": 2.8477,47 "num_input_tokens_seen": 227360,48 "step": 4,49 "train_runtime": 37.6089,50 "train_tokens_per_second": 6045.3751 },52 {53 "epoch": 0.0032144005143040825,54 "grad_norm": 1.5457735061645508,55 "learning_rate": 0.00016,56 "loss": 2.7233,57 "num_input_tokens_seen": 264512,58 "step": 5,59 "train_runtime": 42.7595,60 "train_tokens_per_second": 6186.03461 },62 {63 "epoch": 0.003857280617164899,64 "grad_norm": 1.178829312324524,65 "learning_rate": 0.0002,66 "loss": 2.1801,67 "num_input_tokens_seen": 309424,68 "step": 6,69 "train_runtime": 48.9842,70 "train_tokens_per_second": 6316.80971 },72 {73 "epoch": 0.004500160720025715,74 "grad_norm": 0.8789910078048706,75 "learning_rate": 0.00019987105093488073,76 "loss": 1.8974,77 "num_input_tokens_seen": 402160,78 "step": 7,79 "train_runtime": 61.7856,80 "train_tokens_per_second": 6508.9681 },82 {83 "epoch": 0.005143040822886531,84 "grad_norm": 0.673732578754425,85 "learning_rate": 0.00019974210186976145,86 "loss": 1.7119,87 "num_input_tokens_seen": 438624,88 "step": 8,89 "train_runtime": 66.8435,90 "train_tokens_per_second": 6561.95791 },92 {93 "epoch": 0.0057859209257473485,94 "grad_norm": 0.521441638469696,95 "learning_rate": 0.00019961315280464216,96 "loss": 1.4815,97 "num_input_tokens_seen": 486400,98 "step": 9,99 "train_runtime": 73.4648,100 "train_tokens_per_second": 6620.858101 },102 {103 "epoch": 0.006428801028608165,104 "grad_norm": 0.6127826571464539,105 "learning_rate": 0.0001994842037395229,106 "loss": 1.5544,107 "num_input_tokens_seen": 542512,108 "step": 10,109 "train_runtime": 81.1977,110 "train_tokens_per_second": 6681.374111 },112 {113 "epoch": 0.007071681131468981,114 "grad_norm": 0.640856146812439,115 "learning_rate": 0.0001993552546744036,116 "loss": 1.4353,117 "num_input_tokens_seen": 588752,118 "step": 11,119 "train_runtime": 87.6246,120 "train_tokens_per_second": 6719.029121 },122 {123 "epoch": 0.007714561234329798,124 "grad_norm": 0.48673883080482483,125 "learning_rate": 0.00019922630560928435,126 "loss": 1.3777,127 "num_input_tokens_seen": 652208,128 "step": 12,129 "train_runtime": 96.4514,130 "train_tokens_per_second": 6762.039131 },132 {133 "epoch": 0.008357441337190614,134 "grad_norm": 0.7254194021224976,135 "learning_rate": 0.00019909735654416506,136 "loss": 1.534,137 "num_input_tokens_seen": 713088,138 "step": 13,139 "train_runtime": 104.9169,140 "train_tokens_per_second": 6796.692141 },142 {143 "epoch": 0.00900032144005143,144 "grad_norm": 0.43824103474617004,145 "learning_rate": 0.00019896840747904578,146 "loss": 1.3674,147 "num_input_tokens_seen": 755024,148 "step": 14,149 "train_runtime": 110.719,150 "train_tokens_per_second": 6819.28151 },152 {153 "epoch": 0.009643201542912247,154 "grad_norm": 0.3844089210033417,155 "learning_rate": 0.0001988394584139265,156 "loss": 1.3111,157 "num_input_tokens_seen": 804912,158 "step": 15,159 "train_runtime": 117.6264,160 "train_tokens_per_second": 6842.954161 },162 {163 "epoch": 0.010286081645773062,164 "grad_norm": 0.35496699810028076,165 "learning_rate": 0.00019871050934880725,166 "loss": 1.2114,167 "num_input_tokens_seen": 873424,168 "step": 16,169 "train_runtime": 127.1638,170 "train_tokens_per_second": 6868.496171 },172 {173 "epoch": 0.01092896174863388,174 "grad_norm": 0.43963053822517395,175 "learning_rate": 0.00019858156028368796,176 "loss": 1.1994,177 "num_input_tokens_seen": 907520,178 "step": 17,179 "train_runtime": 131.9627,180 "train_tokens_per_second": 6877.095181 },182 {183 "epoch": 0.011571841851494697,184 "grad_norm": 0.33540457487106323,185 "learning_rate": 0.00019845261121856868,186 "loss": 1.254,187 "num_input_tokens_seen": 952896,188 "step": 18,189 "train_runtime": 138.2745,190 "train_tokens_per_second": 6891.337191 },192 {193 "epoch": 0.012214721954355513,194 "grad_norm": 0.2950117588043213,195 "learning_rate": 0.0001983236621534494,196 "loss": 1.1624,197 "num_input_tokens_seen": 1005344,198 "step": 19,199 "train_runtime": 145.6011,200 "train_tokens_per_second": 6904.781201 },202 {203 "epoch": 0.01285760205721633,204 "grad_norm": 0.2870226502418518,205 "learning_rate": 0.00019819471308833012,206 "loss": 1.1386,207 "num_input_tokens_seen": 1040544,208 "step": 20,209 "train_runtime": 150.5659,210 "train_tokens_per_second": 6910.886211 },212 {213 "epoch": 0.013500482160077145,214 "grad_norm": 0.27605196833610535,215 "learning_rate": 0.00019806576402321084,216 "loss": 1.2057,217 "num_input_tokens_seen": 1080432,218 "step": 21,219 "train_runtime": 156.1378,220 "train_tokens_per_second": 6919.735221 },222 {223 "epoch": 0.014143362262937963,224 "grad_norm": 0.29624828696250916,225 "learning_rate": 0.00019793681495809155,226 "loss": 1.2303,227 "num_input_tokens_seen": 1148496,228 "step": 22,229 "train_runtime": 165.7289,230 "train_tokens_per_second": 6929.969231 },232 {233 "epoch": 0.014786242365798778,234 "grad_norm": 0.2731878459453583,235 "learning_rate": 0.0001978078658929723,236 "loss": 1.0739,237 "num_input_tokens_seen": 1189760,238 "step": 23,239 "train_runtime": 171.4728,240 "train_tokens_per_second": 6938.478241 },242 {243 "epoch": 0.015429122468659595,244 "grad_norm": 0.33944907784461975,245 "learning_rate": 0.000197678916827853,246 "loss": 1.0303,247 "num_input_tokens_seen": 1226432,248 "step": 24,249 "train_runtime": 176.634,250 "train_tokens_per_second": 6943.352251 },252 {253 "epoch": 0.016072002571520413,254 "grad_norm": 0.2622462511062622,255 "learning_rate": 0.00019754996776273374,256 "loss": 1.3015,257 "num_input_tokens_seen": 1266848,258 "step": 25,259 "train_runtime": 182.3158,260 "train_tokens_per_second": 6948.647261 },262 {263 "epoch": 0.01671488267438123,264 "grad_norm": 0.24616512656211853,265 "learning_rate": 0.00019742101869761445,266 "loss": 1.1244,267 "num_input_tokens_seen": 1323584,268 "step": 26,269 "train_runtime": 190.2408,270 "train_tokens_per_second": 6957.415271 },272 {273 "epoch": 0.017357762777242044,274 "grad_norm": 0.23589050769805908,275 "learning_rate": 0.00019729206963249517,276 "loss": 1.1235,277 "num_input_tokens_seen": 1361104,278 "step": 27,279 "train_runtime": 195.5135,280 "train_tokens_per_second": 6961.687281 },282 {283 "epoch": 0.01800064288010286,284 "grad_norm": 0.23991915583610535,285 "learning_rate": 0.0001971631205673759,286 "loss": 1.1462,287 "num_input_tokens_seen": 1398528,288 "step": 28,289 "train_runtime": 200.794,290 "train_tokens_per_second": 6964.989291 },292 {293 "epoch": 0.01864352298296368,294 "grad_norm": 0.2634638547897339,295 "learning_rate": 0.00019703417150225663,296 "loss": 1.2721,297 "num_input_tokens_seen": 1435776,298 "step": 29,299 "train_runtime": 206.0467,300 "train_tokens_per_second": 6968.207301 },302 {303 "epoch": 0.019286403085824494,304 "grad_norm": 0.19377130270004272,305 "learning_rate": 0.00019690522243713733,306 "loss": 1.1832,307 "num_input_tokens_seen": 1478496,308 "step": 30,309 "train_runtime": 212.0993,310 "train_tokens_per_second": 6970.772311 },312 {313 "epoch": 0.01992928318868531,314 "grad_norm": 0.18850353360176086,315 "learning_rate": 0.00019677627337201807,316 "loss": 1.0619,317 "num_input_tokens_seen": 1532256,318 "step": 31,319 "train_runtime": 220.2613,320 "train_tokens_per_second": 6956.537321 },322 {323 "epoch": 0.020572163291546125,324 "grad_norm": 0.17500188946723938,325 "learning_rate": 0.0001966473243068988,326 "loss": 1.1776,327 "num_input_tokens_seen": 1579456,328 "step": 32,329 "train_runtime": 226.8725,330 "train_tokens_per_second": 6961.867331 },332 {333 "epoch": 0.021215043394406944,334 "grad_norm": 0.21095849573612213,335 "learning_rate": 0.0001965183752417795,336 "loss": 1.1431,337 "num_input_tokens_seen": 1624896,338 "step": 33,339 "train_runtime": 233.2234,340 "train_tokens_per_second": 6967.124341 },342 {343 "epoch": 0.02185792349726776,344 "grad_norm": 0.18223783373832703,345 "learning_rate": 0.00019638942617666023,346 "loss": 1.1791,347 "num_input_tokens_seen": 1669808,348 "step": 34,349 "train_runtime": 239.4782,350 "train_tokens_per_second": 6972.692351 },352 {353 "epoch": 0.022500803600128575,354 "grad_norm": 0.21014757454395294,355 "learning_rate": 0.00019626047711154094,356 "loss": 1.1142,357 "num_input_tokens_seen": 1738240,358 "step": 35,359 "train_runtime": 249.0199,360 "train_tokens_per_second": 6980.327361 },362 {363 "epoch": 0.023143683702989394,364 "grad_norm": 0.19807523488998413,365 "learning_rate": 0.0001961315280464217,366 "loss": 1.2255,367 "num_input_tokens_seen": 1788656,368 "step": 36,369 "train_runtime": 256.0945,370 "train_tokens_per_second": 6984.36371 },372 {373 "epoch": 0.02378656380585021,374 "grad_norm": 0.2257339507341385,375 "learning_rate": 0.00019600257898130238,376 "loss": 1.1833,377 "num_input_tokens_seen": 1830592,378 "step": 37,379 "train_runtime": 262.0096,380 "train_tokens_per_second": 6986.737381 },382 {383 "epoch": 0.024429443908711025,384 "grad_norm": 0.16706082224845886,385 "learning_rate": 0.00019587362991618313,386 "loss": 1.0836,387 "num_input_tokens_seen": 1889488,388 "step": 38,389 "train_runtime": 270.2441,390 "train_tokens_per_second": 6991.783391 },392 {393 "epoch": 0.02507232401157184,394 "grad_norm": 0.17788530886173248,395 "learning_rate": 0.00019574468085106384,396 "loss": 1.1416,397 "num_input_tokens_seen": 1926928,398 "step": 39,399 "train_runtime": 275.5398,400 "train_tokens_per_second": 6993.283401 },402 {403 "epoch": 0.02571520411443266,404 "grad_norm": 0.20560547709465027,405 "learning_rate": 0.00019561573178594456,406 "loss": 1.1354,407 "num_input_tokens_seen": 1975616,408 "step": 40,409 "train_runtime": 282.4472,410 "train_tokens_per_second": 6994.638411 },412 {413 "epoch": 0.026358084217293475,414 "grad_norm": 0.18634942173957825,415 "learning_rate": 0.00019548678272082528,416 "loss": 1.1416,417 "num_input_tokens_seen": 2020672,418 "step": 41,419 "train_runtime": 288.8056,420 "train_tokens_per_second": 6996.65421 },422 {423 "epoch": 0.02700096432015429,424 "grad_norm": 0.2036864012479782,425 "learning_rate": 0.00019535783365570602,426 "loss": 1.0778,427 "num_input_tokens_seen": 2059120,428 "step": 42,429 "train_runtime": 294.2046,430 "train_tokens_per_second": 6998.94431 },432 {433 "epoch": 0.027643844423015106,434 "grad_norm": 0.15779554843902588,435 "learning_rate": 0.00019522888459058672,436 "loss": 1.0298,437 "num_input_tokens_seen": 2113040,438 "step": 43,439 "train_runtime": 301.7907,440 "train_tokens_per_second": 7001.675441 },442 {443 "epoch": 0.028286724525875925,444 "grad_norm": 0.1940307766199112,445 "learning_rate": 0.00019509993552546746,446 "loss": 1.2145,447 "num_input_tokens_seen": 2168464,448 "step": 44,449 "train_runtime": 309.5156,450 "train_tokens_per_second": 7005.992451 },452 {453 "epoch": 0.02892960462873674,454 "grad_norm": 0.1537512242794037,455 "learning_rate": 0.00019497098646034818,456 "loss": 1.0519,457 "num_input_tokens_seen": 2221904,458 "step": 45,459 "train_runtime": 317.0459,460 "train_tokens_per_second": 7008.147461 },462 {463 "epoch": 0.029572484731597556,464 "grad_norm": 0.16348929703235626,465 "learning_rate": 0.0001948420373952289,466 "loss": 1.1651,467 "num_input_tokens_seen": 2261088,468 "step": 46,469 "train_runtime": 322.608,470 "train_tokens_per_second": 7008.778471 },472 {473 "epoch": 0.030215364834458372,474 "grad_norm": 0.1592399775981903,475 "learning_rate": 0.00019471308833010962,476 "loss": 1.0866,477 "num_input_tokens_seen": 2301040,478 "step": 47,479 "train_runtime": 328.2327,480 "train_tokens_per_second": 7010.392481 },482 {483 "epoch": 0.03085824493731919,484 "grad_norm": 0.15753492712974548,485 "learning_rate": 0.00019458413926499033,486 "loss": 1.2199,487 "num_input_tokens_seen": 2340080,488 "step": 48,489 "train_runtime": 333.7329,490 "train_tokens_per_second": 7011.835491 },492 {493 "epoch": 0.03150112504018,494 "grad_norm": 0.16081875562667847,495 "learning_rate": 0.00019445519019987105,496 "loss": 1.0763,497 "num_input_tokens_seen": 2385008,498 "step": 49,499 "train_runtime": 340.0525,500 "train_tokens_per_second": 7013.647501 },502 {503 "epoch": 0.032144005143040826,504 "grad_norm": 0.18117882311344147,505 "learning_rate": 0.00019432624113475177,506 "loss": 1.1252,507 "num_input_tokens_seen": 2424432,508 "step": 50,509 "train_runtime": 345.6231,510 "train_tokens_per_second": 7014.671511 },512 {513 "epoch": 0.03278688524590164,514 "grad_norm": 0.196014404296875,515 "learning_rate": 0.00019419729206963251,516 "loss": 1.1195,517 "num_input_tokens_seen": 2483664,518 "step": 51,519 "train_runtime": 353.9289,520 "train_tokens_per_second": 7017.409521 },522 {523 "epoch": 0.03342976534876246,524 "grad_norm": 0.17965562641620636,525 "learning_rate": 0.00019406834300451323,526 "loss": 1.1258,527 "num_input_tokens_seen": 2518352,528 "step": 52,529 "train_runtime": 358.8626,530 "train_tokens_per_second": 7017.594531 },532 {533 "epoch": 0.03407264545162327,534 "grad_norm": 0.1602979451417923,535 "learning_rate": 0.00019393939393939395,536 "loss": 1.0905,537 "num_input_tokens_seen": 2576704,538 "step": 53,539 "train_runtime": 367.0539,540 "train_tokens_per_second": 7019.961541 },542 {543 "epoch": 0.03471552555448409,544 "grad_norm": 0.17046068608760834,545 "learning_rate": 0.00019381044487427467,546 "loss": 1.1841,547 "num_input_tokens_seen": 2616624,548 "step": 54,549 "train_runtime": 372.6815,550 "train_tokens_per_second": 7021.074551 },552 {553 "epoch": 0.0353584056573449,554 "grad_norm": 0.15942060947418213,555 "learning_rate": 0.0001936814958091554,556 "loss": 1.0914,557 "num_input_tokens_seen": 2671344,558 "step": 55,559 "train_runtime": 380.3215,560 "train_tokens_per_second": 7023.911561 },562 {563 "epoch": 0.03600128576020572,564 "grad_norm": 0.17654664814472198,565 "learning_rate": 0.0001935525467440361,566 "loss": 1.0943,567 "num_input_tokens_seen": 2715520,568 "step": 56,569 "train_runtime": 386.5062,570 "train_tokens_per_second": 7025.813571 },572 {573 "epoch": 0.03664416586306654,574 "grad_norm": 0.23010510206222534,575 "learning_rate": 0.00019342359767891685,576 "loss": 1.1784,577 "num_input_tokens_seen": 2762960,578 "step": 57,579 "train_runtime": 393.1797,580 "train_tokens_per_second": 7027.219581 },582 {583 "epoch": 0.03728704596592736,584 "grad_norm": 0.17523719370365143,585 "learning_rate": 0.00019329464861379757,586 "loss": 1.1282,587 "num_input_tokens_seen": 2816064,588 "step": 58,589 "train_runtime": 400.6116,590 "train_tokens_per_second": 7029.413591 },592 {593 "epoch": 0.03792992606878817,594 "grad_norm": 0.21163171529769897,595 "learning_rate": 0.0001931656995486783,596 "loss": 1.0851,597 "num_input_tokens_seen": 2855264,598 "step": 59,599 "train_runtime": 406.1575,600 "train_tokens_per_second": 7029.942601 },602 {603 "epoch": 0.03857280617164899,604 "grad_norm": 0.25337469577789307,605 "learning_rate": 0.000193036750483559,606 "loss": 1.2117,607 "num_input_tokens_seen": 2904656,608 "step": 60,609 "train_runtime": 413.1009,610 "train_tokens_per_second": 7031.348611 },612 {613 "epoch": 0.0392156862745098,614 "grad_norm": 0.19712360203266144,615 "learning_rate": 0.00019290780141843972,616 "loss": 1.2204,617 "num_input_tokens_seen": 2971088,618 "step": 61,619 "train_runtime": 422.9897,620 "train_tokens_per_second": 7024.019621 },622 {623 "epoch": 0.03985856637737062,624 "grad_norm": 0.19821137189865112,625 "learning_rate": 0.00019277885235332044,626 "loss": 1.0626,627 "num_input_tokens_seen": 3013552,628 "step": 62,629 "train_runtime": 428.9561,630 "train_tokens_per_second": 7025.315631 },632 {633 "epoch": 0.040501446480231434,634 "grad_norm": 0.17856234312057495,635 "learning_rate": 0.00019264990328820116,636 "loss": 1.0619,637 "num_input_tokens_seen": 3059952,638 "step": 63,639 "train_runtime": 435.4318,640 "train_tokens_per_second": 7027.397641 },642 {643 "epoch": 0.04114432658309225,644 "grad_norm": 0.18660882115364075,645 "learning_rate": 0.0001925209542230819,646 "loss": 1.0679,647 "num_input_tokens_seen": 3107920,648 "step": 64,649 "train_runtime": 442.1457,650 "train_tokens_per_second": 7029.175651 },652 {653 "epoch": 0.04178720668595307,654 "grad_norm": 0.1943148672580719,655 "learning_rate": 0.0001923920051579626,656 "loss": 1.1859,657 "num_input_tokens_seen": 3155936,658 "step": 65,659 "train_runtime": 448.9004,660 "train_tokens_per_second": 7030.371661 },662 {663 "epoch": 0.04243008678881389,664 "grad_norm": 0.18507765233516693,665 "learning_rate": 0.00019226305609284334,666 "loss": 1.0599,667 "num_input_tokens_seen": 3190864,668 "step": 66,669 "train_runtime": 453.8531,670 "train_tokens_per_second": 7030.609671 },672 {673 "epoch": 0.043072966891674704,674 "grad_norm": 0.17876607179641724,675 "learning_rate": 0.00019213410702772406,676 "loss": 1.1394,677 "num_input_tokens_seen": 3233616,678 "step": 67,679 "train_runtime": 459.8348,680 "train_tokens_per_second": 7032.126681 },682 {683 "epoch": 0.04371584699453552,684 "grad_norm": 0.19422762095928192,685 "learning_rate": 0.00019200515796260478,686 "loss": 1.0683,687 "num_input_tokens_seen": 3303616,688 "step": 68,689 "train_runtime": 469.6416,690 "train_tokens_per_second": 7034.334691 },692 {693 "epoch": 0.044358727097396335,694 "grad_norm": 0.2042950987815857,695 "learning_rate": 0.0001918762088974855,696 "loss": 1.1002,697 "num_input_tokens_seen": 3353936,698 "step": 69,699 "train_runtime": 476.682,700 "train_tokens_per_second": 7036.003701 },702 {703 "epoch": 0.04500160720025715,704 "grad_norm": 0.18014422059059143,705 "learning_rate": 0.00019174725983236624,706 "loss": 0.9397,707 "num_input_tokens_seen": 3398368,708 "step": 70,709 "train_runtime": 482.9344,710 "train_tokens_per_second": 7036.915711 },712 {713 "epoch": 0.045644487303117966,714 "grad_norm": 0.16590985655784607,715 "learning_rate": 0.00019161831076724693,716 "loss": 1.0775,717 "num_input_tokens_seen": 3444640,718 "step": 71,719 "train_runtime": 489.4489,720 "train_tokens_per_second": 7037.793721 },722 {723 "epoch": 0.04628736740597879,724 "grad_norm": 0.19661296904087067,725 "learning_rate": 0.00019148936170212768,726 "loss": 1.1763,727 "num_input_tokens_seen": 3486768,728 "step": 72,729 "train_runtime": 495.3941,730 "train_tokens_per_second": 7038.372731 },732 {733 "epoch": 0.046930247508839604,734 "grad_norm": 0.18453364074230194,735 "learning_rate": 0.0001913604126370084,736 "loss": 1.0713,737 "num_input_tokens_seen": 3540944,738 "step": 73,739 "train_runtime": 502.9706,740 "train_tokens_per_second": 7040.062741 },742 {743 "epoch": 0.04757312761170042,744 "grad_norm": 0.1981048732995987,745 "learning_rate": 0.0001912314635718891,746 "loss": 1.1318,747 "num_input_tokens_seen": 3600416,748 "step": 74,749 "train_runtime": 511.3315,750 "train_tokens_per_second": 7041.255751 },752 {753 "epoch": 0.048216007714561235,754 "grad_norm": 0.19020932912826538,755 "learning_rate": 0.00019110251450676983,756 "loss": 1.1775,757 "num_input_tokens_seen": 3643216,758 "step": 75,759 "train_runtime": 517.3293,760 "train_tokens_per_second": 7042.354761 },762 {763 "epoch": 0.04885888781742205,764 "grad_norm": 0.19130156934261322,765 "learning_rate": 0.00019097356544165055,766 "loss": 1.0635,767 "num_input_tokens_seen": 3690592,768 "step": 76,769 "train_runtime": 523.9724,770 "train_tokens_per_second": 7043.485771 },772 {773 "epoch": 0.049501767920282866,774 "grad_norm": 0.191071018576622,775 "learning_rate": 0.0001908446163765313,776 "loss": 1.2032,777 "num_input_tokens_seen": 3743680,778 "step": 77,779 "train_runtime": 531.4274,780 "train_tokens_per_second": 7044.575781 },782 {783 "epoch": 0.05014464802314368,784 "grad_norm": 0.19254839420318604,785 "learning_rate": 0.00019071566731141199,786 "loss": 1.0561,787 "num_input_tokens_seen": 3788096,788 "step": 78,789 "train_runtime": 537.6994,790 "train_tokens_per_second": 7045.007791 },792 {793 "epoch": 0.0507875281260045,794 "grad_norm": 0.21967262029647827,795 "learning_rate": 0.00019058671824629273,796 "loss": 1.0789,797 "num_input_tokens_seen": 3824128,798 "step": 79,799 "train_runtime": 542.7932,800 "train_tokens_per_second": 7045.276801 },802 {803 "epoch": 0.05143040822886532,804 "grad_norm": 0.1794055998325348,805 "learning_rate": 0.00019045776918117345,806 "loss": 1.1144,807 "num_input_tokens_seen": 3869600,808 "step": 80,809 "train_runtime": 549.2268,810 "train_tokens_per_second": 7045.541811 },812 {813 "epoch": 0.052073288331726135,814 "grad_norm": 0.22182276844978333,815 "learning_rate": 0.00019032882011605417,816 "loss": 1.0452,817 "num_input_tokens_seen": 3930416,818 "step": 81,819 "train_runtime": 557.7179,820 "train_tokens_per_second": 7047.319821 },822 {823 "epoch": 0.05271616843458695,824 "grad_norm": 0.1964883953332901,825 "learning_rate": 0.00019019987105093489,826 "loss": 1.1264,827 "num_input_tokens_seen": 3994528,828 "step": 82,829 "train_runtime": 566.7719,830 "train_tokens_per_second": 7047.859831 },832 {833 "epoch": 0.053359048537447766,834 "grad_norm": 0.18389713764190674,835 "learning_rate": 0.00019007092198581563,836 "loss": 1.1044,837 "num_input_tokens_seen": 4025760,838 "step": 83,839 "train_runtime": 571.2105,840 "train_tokens_per_second": 7047.769841 },842 {843 "epoch": 0.05400192864030858,844 "grad_norm": 0.21487605571746826,845 "learning_rate": 0.00018994197292069632,846 "loss": 1.0369,847 "num_input_tokens_seen": 4073840,848 "step": 84,849 "train_runtime": 577.9687,850 "train_tokens_per_second": 7048.548851 },852 {853 "epoch": 0.0546448087431694,854 "grad_norm": 0.21032066643238068,855 "learning_rate": 0.00018981302385557707,856 "loss": 1.0615,857 "num_input_tokens_seen": 4108976,858 "step": 85,859 "train_runtime": 582.9533,860 "train_tokens_per_second": 7048.551861 },862 {863 "epoch": 0.05528768884603021,864 "grad_norm": 0.19567039608955383,865 "learning_rate": 0.00018968407479045778,866 "loss": 0.9216,867 "num_input_tokens_seen": 4164832,868 "step": 86,869 "train_runtime": 590.7405,870 "train_tokens_per_second": 7050.188871 },872 {873 "epoch": 0.055930568948891035,874 "grad_norm": 0.2140112817287445,875 "learning_rate": 0.00018955512572533848,876 "loss": 1.1268,877 "num_input_tokens_seen": 4223920,878 "step": 87,879 "train_runtime": 599.009,880 "train_tokens_per_second": 7051.513881 },882 {883 "epoch": 0.05657344905175185,884 "grad_norm": 0.2232234627008438,885 "learning_rate": 0.00018942617666021922,886 "loss": 1.1666,887 "num_input_tokens_seen": 4257440,888 "step": 88,889 "train_runtime": 603.7538,890 "train_tokens_per_second": 7051.616891 },892 {893 "epoch": 0.057216329154612666,894 "grad_norm": 0.20844654738903046,895 "learning_rate": 0.00018929722759509994,896 "loss": 0.9959,897 "num_input_tokens_seen": 4291488,898 "step": 89,899 "train_runtime": 608.6239,900 "train_tokens_per_second": 7051.133901 },902 {903 "epoch": 0.05785920925747348,904 "grad_norm": 0.21762102842330933,905 "learning_rate": 0.00018916827852998066,906 "loss": 1.0791,907 "num_input_tokens_seen": 4350704,908 "step": 90,909 "train_runtime": 616.9377,910 "train_tokens_per_second": 7052.097911 },912 {913 "epoch": 0.0585020893603343,914 "grad_norm": 0.2169635146856308,915 "learning_rate": 0.00018903932946486138,916 "loss": 1.169,917 "num_input_tokens_seen": 4390512,918 "step": 91,919 "train_runtime": 623.0766,920 "train_tokens_per_second": 7046.505921 },922 {923 "epoch": 0.05914496946319511,924 "grad_norm": 0.19721537828445435,925 "learning_rate": 0.00018891038039974212,926 "loss": 1.0508,927 "num_input_tokens_seen": 4441920,928 "step": 92,929 "train_runtime": 630.2606,930 "train_tokens_per_second": 7047.751931 },932 {933 "epoch": 0.05978784956605593,934 "grad_norm": 0.23010528087615967,935 "learning_rate": 0.00018878143133462284,936 "loss": 0.9817,937 "num_input_tokens_seen": 4486672,938 "step": 93,939 "train_runtime": 636.5612,940 "train_tokens_per_second": 7048.297941 },942 {943 "epoch": 0.060430729668916744,944 "grad_norm": 0.19669458270072937,945 "learning_rate": 0.00018865248226950356,946 "loss": 1.0702,947 "num_input_tokens_seen": 4538384,948 "step": 94,949 "train_runtime": 643.8004,950 "train_tokens_per_second": 7049.365951 },952 {953 "epoch": 0.061073609771777566,954 "grad_norm": 0.33032017946243286,955 "learning_rate": 0.00018852353320438427,956 "loss": 1.0299,957 "num_input_tokens_seen": 4589312,958 "step": 95,959 "train_runtime": 651.0321,960 "train_tokens_per_second": 7049.287961 },962 {963 "epoch": 0.06171648987463838,964 "grad_norm": 0.18110264837741852,965 "learning_rate": 0.00018839458413926502,966 "loss": 0.9553,967 "num_input_tokens_seen": 4626080,968 "step": 96,969 "train_runtime": 656.2234,970 "train_tokens_per_second": 7049.55971 },972 {973 "epoch": 0.0623593699774992,974 "grad_norm": 0.2149723619222641,975 "learning_rate": 0.0001882656350741457,976 "loss": 1.1532,977 "num_input_tokens_seen": 4668624,978 "step": 97,979 "train_runtime": 662.2157,980 "train_tokens_per_second": 7050.005981 },982 {983 "epoch": 0.06300225008036,984 "grad_norm": 0.21420878171920776,985 "learning_rate": 0.00018813668600902646,986 "loss": 1.1092,987 "num_input_tokens_seen": 4724240,988 "step": 98,989 "train_runtime": 670.094,990 "train_tokens_per_second": 7050.115991 },992 {993 "epoch": 0.06364513018322084,994 "grad_norm": 0.21070437133312225,995 "learning_rate": 0.00018800773694390717,996 "loss": 0.9589,997 "num_input_tokens_seen": 4795776,998 "step": 99,999 "train_runtime": 680.0991,1000 "train_tokens_per_second": 7051.5841001 },1002 {1003 "epoch": 0.06428801028608165,1004 "grad_norm": 0.19431836903095245,1005 "learning_rate": 0.0001878787878787879,1006 "loss": 1.0636,1007 "num_input_tokens_seen": 4851008,1008 "step": 100,1009 "train_runtime": 687.8429,1010 "train_tokens_per_second": 7052.4941011 },1012 {1013 "epoch": 0.06493089038894247,1014 "grad_norm": 0.20360679924488068,1015 "learning_rate": 0.0001877498388136686,1016 "loss": 1.1182,1017 "num_input_tokens_seen": 4891088,1018 "step": 101,1019 "train_runtime": 693.4719,1020 "train_tokens_per_second": 7053.0441021 },1022 {1023 "epoch": 0.06557377049180328,1024 "grad_norm": 0.21350686252117157,1025 "learning_rate": 0.00018762088974854933,1026 "loss": 1.0525,1027 "num_input_tokens_seen": 4952416,1028 "step": 102,1029 "train_runtime": 702.1041,1030 "train_tokens_per_second": 7053.6781031 },1032 {1033 "epoch": 0.0662166505946641,1034 "grad_norm": 0.2190914750099182,1035 "learning_rate": 0.00018749194068343005,1036 "loss": 1.0602,1037 "num_input_tokens_seen": 5000400,1038 "step": 103,1039 "train_runtime": 708.8252,1040 "train_tokens_per_second": 7054.4891041 },1042 {1043 "epoch": 0.06685953069752491,1044 "grad_norm": 0.21608233451843262,1045 "learning_rate": 0.00018736299161831077,1046 "loss": 1.1176,1047 "num_input_tokens_seen": 5048592,1048 "step": 104,1049 "train_runtime": 715.5961,1050 "train_tokens_per_second": 7055.0861051 },1052 {1053 "epoch": 0.06750241080038573,1054 "grad_norm": 0.21670708060264587,1055 "learning_rate": 0.0001872340425531915,1056 "loss": 1.1591,1057 "num_input_tokens_seen": 5081664,1058 "step": 105,1059 "train_runtime": 720.3252,1060 "train_tokens_per_second": 7054.681061 },1062 {1063 "epoch": 0.06814529090324654,1064 "grad_norm": 0.20723669230937958,1065 "learning_rate": 0.0001871050934880722,1066 "loss": 1.0741,1067 "num_input_tokens_seen": 5133264,1068 "step": 106,1069 "train_runtime": 727.5521,1070 "train_tokens_per_second": 7055.5281071 },1072 {1073 "epoch": 0.06878817100610736,1074 "grad_norm": 0.22334900498390198,1075 "learning_rate": 0.00018697614442295295,1076 "loss": 1.2012,1077 "num_input_tokens_seen": 5180464,1078 "step": 107,1079 "train_runtime": 734.1803,1080 "train_tokens_per_second": 7056.121081 },1082 {1083 "epoch": 0.06943105110896818,1084 "grad_norm": 0.19817394018173218,1085 "learning_rate": 0.00018684719535783366,1086 "loss": 1.0348,1087 "num_input_tokens_seen": 5227712,1088 "step": 108,1089 "train_runtime": 740.8405,1090 "train_tokens_per_second": 7056.4611091 },1092 {1093 "epoch": 0.07007393121182899,1094 "grad_norm": 0.22613032162189484,1095 "learning_rate": 0.00018671824629271438,1096 "loss": 1.0507,1097 "num_input_tokens_seen": 5297424,1098 "step": 109,1099 "train_runtime": 750.5378,1100 "train_tokens_per_second": 7058.1711101 },1102 {1103 "epoch": 0.0707168113146898,1104 "grad_norm": 0.19790789484977722,1105 "learning_rate": 0.0001865892972275951,1106 "loss": 1.1512,1107 "num_input_tokens_seen": 5353920,1108 "step": 110,1109 "train_runtime": 758.4763,1110 "train_tokens_per_second": 7058.7831111 },1112 {1113 "epoch": 0.07135969141755062,1114 "grad_norm": 0.19805489480495453,1115 "learning_rate": 0.00018646034816247585,1116 "loss": 1.0392,1117 "num_input_tokens_seen": 5387872,1118 "step": 111,1119 "train_runtime": 763.2666,1120 "train_tokens_per_second": 7058.9651121 },1122 {1123 "epoch": 0.07200257152041144,1124 "grad_norm": 0.21664251387119293,1125 "learning_rate": 0.00018633139909735656,1126 "loss": 1.0399,1127 "num_input_tokens_seen": 5431632,1128 "step": 112,1129 "train_runtime": 769.3579,1130 "train_tokens_per_second": 7059.9541131 },1132 {1133 "epoch": 0.07264545162327225,1134 "grad_norm": 0.21840597689151764,1135 "learning_rate": 0.00018620245003223728,1136 "loss": 1.0969,1137 "num_input_tokens_seen": 5478704,1138 "step": 113,1139 "train_runtime": 775.8252,1140 "train_tokens_per_second": 7061.7761141 },1142 {1143 "epoch": 0.07328833172613308,1144 "grad_norm": 0.1976010650396347,1145 "learning_rate": 0.000186073500967118,1146 "loss": 0.9954,1147 "num_input_tokens_seen": 5528176,1148 "step": 114,1149 "train_runtime": 782.6383,1150 "train_tokens_per_second": 7063.5131151 },1152 {1153 "epoch": 0.0739312118289939,1154 "grad_norm": 0.19003896415233612,1155 "learning_rate": 0.00018594455190199872,1156 "loss": 1.0055,1157 "num_input_tokens_seen": 5593040,1158 "step": 115,1159 "train_runtime": 791.6683,1160 "train_tokens_per_second": 7064.8781161 },1162 {1163 "epoch": 0.07457409193185471,1164 "grad_norm": 0.1933498978614807,1165 "learning_rate": 0.00018581560283687944,1166 "loss": 1.0906,1167 "num_input_tokens_seen": 5633680,1168 "step": 116,1169 "train_runtime": 797.3292,1170 "train_tokens_per_second": 7065.6891171 },1172 {1173 "epoch": 0.07521697203471553,1174 "grad_norm": 0.2050444781780243,1175 "learning_rate": 0.00018568665377176016,1176 "loss": 0.9672,1177 "num_input_tokens_seen": 5683744,1178 "step": 117,1179 "train_runtime": 804.286,1180 "train_tokens_per_second": 7066.8191181 },1182 {1183 "epoch": 0.07585985213757634,1184 "grad_norm": 0.20085984468460083,1185 "learning_rate": 0.0001855577047066409,1186 "loss": 1.0086,1187 "num_input_tokens_seen": 5718912,1188 "step": 118,1189 "train_runtime": 809.2226,1190 "train_tokens_per_second": 7067.1681191 },1192 {1193 "epoch": 0.07650273224043716,1194 "grad_norm": 0.2239076942205429,1195 "learning_rate": 0.0001854287556415216,1196 "loss": 1.0371,1197 "num_input_tokens_seen": 5787328,1198 "step": 119,1199 "train_runtime": 818.7746,1200 "train_tokens_per_second": 7068.28