NikhilSwami/qwen2.5-3b-instruct-R64-RIVERUSDT
06
1{2 "best_global_step": null,3 "best_metric": null,4 "best_model_checkpoint": null,5 "epoch": 1.0863531225905936,6 "eval_steps": 64,7 "global_step": 352,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.003108003108003108,14 "grad_norm": 10.027831077575684,15 "learning_rate": 0.0,16 "loss": 0.6767,17 "step": 118 },19 {20 "epoch": 0.006216006216006216,21 "grad_norm": 9.679778099060059,22 "learning_rate": 5.000000000000001e-07,23 "loss": 0.6644,24 "step": 225 },26 {27 "epoch": 0.009324009324009324,28 "grad_norm": 10.520271301269531,29 "learning_rate": 1.0000000000000002e-06,30 "loss": 0.6934,31 "step": 332 },33 {34 "epoch": 0.012432012432012432,35 "grad_norm": 8.677583694458008,36 "learning_rate": 1.5e-06,37 "loss": 0.6617,38 "step": 439 },40 {41 "epoch": 0.01554001554001554,42 "grad_norm": 6.502548694610596,43 "learning_rate": 2.0000000000000003e-06,44 "loss": 0.6509,45 "step": 546 },47 {48 "epoch": 0.018648018648018648,49 "grad_norm": 4.257171154022217,50 "learning_rate": 2.5e-06,51 "loss": 0.639,52 "step": 653 },54 {55 "epoch": 0.021756021756021756,56 "grad_norm": 3.460066556930542,57 "learning_rate": 3e-06,58 "loss": 0.6286,59 "step": 760 },61 {62 "epoch": 0.024864024864024864,63 "grad_norm": 3.0126283168792725,64 "learning_rate": 3.5e-06,65 "loss": 0.5948,66 "step": 867 },68 {69 "epoch": 0.027972027972027972,70 "grad_norm": 2.567995309829712,71 "learning_rate": 4.000000000000001e-06,72 "loss": 0.5744,73 "step": 974 },75 {76 "epoch": 0.03108003108003108,77 "grad_norm": 2.516597032546997,78 "learning_rate": 4.5e-06,79 "loss": 0.5496,80 "step": 1081 },82 {83 "epoch": 0.03418803418803419,84 "grad_norm": 1.8187586069107056,85 "learning_rate": 5e-06,86 "loss": 0.5397,87 "step": 1188 },89 {90 "epoch": 0.037296037296037296,91 "grad_norm": 1.7935529947280884,92 "learning_rate": 5.500000000000001e-06,93 "loss": 0.5229,94 "step": 1295 },96 {97 "epoch": 0.04040404040404041,98 "grad_norm": 1.8665963411331177,99 "learning_rate": 6e-06,100 "loss": 0.5227,101 "step": 13102 },103 {104 "epoch": 0.04351204351204351,105 "grad_norm": 2.0106680393218994,106 "learning_rate": 6.5000000000000004e-06,107 "loss": 0.4882,108 "step": 14109 },110 {111 "epoch": 0.046620046620046623,112 "grad_norm": 3.305211305618286,113 "learning_rate": 7e-06,114 "loss": 0.4772,115 "step": 15116 },117 {118 "epoch": 0.04972804972804973,119 "grad_norm": 3.047219753265381,120 "learning_rate": 7.500000000000001e-06,121 "loss": 0.452,122 "step": 16123 },124 {125 "epoch": 0.05283605283605284,126 "grad_norm": 2.5453591346740723,127 "learning_rate": 8.000000000000001e-06,128 "loss": 0.4138,129 "step": 17130 },131 {132 "epoch": 0.055944055944055944,133 "grad_norm": 5.414841175079346,134 "learning_rate": 8.5e-06,135 "loss": 0.4238,136 "step": 18137 },138 {139 "epoch": 0.059052059052059055,140 "grad_norm": 2.979440927505493,141 "learning_rate": 9e-06,142 "loss": 0.3987,143 "step": 19144 },145 {146 "epoch": 0.06216006216006216,147 "grad_norm": 1.981175422668457,148 "learning_rate": 9.5e-06,149 "loss": 0.3874,150 "step": 20151 },152 {153 "epoch": 0.06526806526806526,154 "grad_norm": 1.7793089151382446,155 "learning_rate": 1e-05,156 "loss": 0.3631,157 "step": 21158 },159 {160 "epoch": 0.06837606837606838,161 "grad_norm": 1.1854480504989624,162 "learning_rate": 9.989429175475688e-06,163 "loss": 0.3765,164 "step": 22165 },166 {167 "epoch": 0.07148407148407149,168 "grad_norm": 0.8928348422050476,169 "learning_rate": 9.978858350951375e-06,170 "loss": 0.3481,171 "step": 23172 },173 {174 "epoch": 0.07459207459207459,175 "grad_norm": 1.7531942129135132,176 "learning_rate": 9.968287526427062e-06,177 "loss": 0.3693,178 "step": 24179 },180 {181 "epoch": 0.0777000777000777,182 "grad_norm": 1.0829464197158813,183 "learning_rate": 9.957716701902749e-06,184 "loss": 0.3644,185 "step": 25186 },187 {188 "epoch": 0.08080808080808081,189 "grad_norm": 0.98089200258255,190 "learning_rate": 9.947145877378436e-06,191 "loss": 0.3616,192 "step": 26193 },194 {195 "epoch": 0.08391608391608392,196 "grad_norm": 0.795221745967865,197 "learning_rate": 9.936575052854123e-06,198 "loss": 0.3679,199 "step": 27200 },201 {202 "epoch": 0.08702408702408702,203 "grad_norm": 1.091843605041504,204 "learning_rate": 9.92600422832981e-06,205 "loss": 0.3439,206 "step": 28207 },208 {209 "epoch": 0.09013209013209013,210 "grad_norm": 0.8538377285003662,211 "learning_rate": 9.915433403805497e-06,212 "loss": 0.3401,213 "step": 29214 },215 {216 "epoch": 0.09324009324009325,217 "grad_norm": 0.9114591479301453,218 "learning_rate": 9.904862579281184e-06,219 "loss": 0.3515,220 "step": 30221 },222 {223 "epoch": 0.09634809634809635,224 "grad_norm": 0.9083001017570496,225 "learning_rate": 9.894291754756871e-06,226 "loss": 0.3449,227 "step": 31228 },229 {230 "epoch": 0.09945609945609946,231 "grad_norm": 0.9144365787506104,232 "learning_rate": 9.883720930232558e-06,233 "loss": 0.3393,234 "step": 32235 },236 {237 "epoch": 0.10256410256410256,238 "grad_norm": 1.0221809148788452,239 "learning_rate": 9.873150105708245e-06,240 "loss": 0.353,241 "step": 33242 },243 {244 "epoch": 0.10567210567210568,245 "grad_norm": 1.0219439268112183,246 "learning_rate": 9.862579281183932e-06,247 "loss": 0.3439,248 "step": 34249 },250 {251 "epoch": 0.10878010878010878,252 "grad_norm": 1.5430618524551392,253 "learning_rate": 9.852008456659621e-06,254 "loss": 0.3338,255 "step": 35256 },257 {258 "epoch": 0.11188811188811189,259 "grad_norm": 1.4754544496536255,260 "learning_rate": 9.841437632135308e-06,261 "loss": 0.3363,262 "step": 36263 },264 {265 "epoch": 0.11499611499611499,266 "grad_norm": 1.1298989057540894,267 "learning_rate": 9.830866807610995e-06,268 "loss": 0.3423,269 "step": 37270 },271 {272 "epoch": 0.11810411810411811,273 "grad_norm": 1.0130062103271484,274 "learning_rate": 9.820295983086682e-06,275 "loss": 0.3298,276 "step": 38277 },278 {279 "epoch": 0.12121212121212122,280 "grad_norm": 1.8003513813018799,281 "learning_rate": 9.80972515856237e-06,282 "loss": 0.3272,283 "step": 39284 },285 {286 "epoch": 0.12432012432012432,287 "grad_norm": 0.9532265067100525,288 "learning_rate": 9.799154334038056e-06,289 "loss": 0.3282,290 "step": 40291 },292 {293 "epoch": 0.12742812742812742,294 "grad_norm": 1.5232913494110107,295 "learning_rate": 9.788583509513743e-06,296 "loss": 0.3469,297 "step": 41298 },299 {300 "epoch": 0.13053613053613053,301 "grad_norm": 0.8918169736862183,302 "learning_rate": 9.77801268498943e-06,303 "loss": 0.326,304 "step": 42305 },306 {307 "epoch": 0.13364413364413363,308 "grad_norm": 0.8845950365066528,309 "learning_rate": 9.767441860465117e-06,310 "loss": 0.3313,311 "step": 43312 },313 {314 "epoch": 0.13675213675213677,315 "grad_norm": 0.8410794138908386,316 "learning_rate": 9.756871035940804e-06,317 "loss": 0.3318,318 "step": 44319 },320 {321 "epoch": 0.13986013986013987,322 "grad_norm": 0.7157808542251587,323 "learning_rate": 9.746300211416491e-06,324 "loss": 0.3381,325 "step": 45326 },327 {328 "epoch": 0.14296814296814297,329 "grad_norm": 1.1680670976638794,330 "learning_rate": 9.735729386892178e-06,331 "loss": 0.3281,332 "step": 46333 },334 {335 "epoch": 0.14607614607614608,336 "grad_norm": 0.9500836133956909,337 "learning_rate": 9.725158562367865e-06,338 "loss": 0.336,339 "step": 47340 },341 {342 "epoch": 0.14918414918414918,343 "grad_norm": 0.8565309643745422,344 "learning_rate": 9.714587737843552e-06,345 "loss": 0.3207,346 "step": 48347 },348 {349 "epoch": 0.1522921522921523,350 "grad_norm": 1.1311777830123901,351 "learning_rate": 9.70401691331924e-06,352 "loss": 0.3339,353 "step": 49354 },355 {356 "epoch": 0.1554001554001554,357 "grad_norm": 1.0368160009384155,358 "learning_rate": 9.693446088794927e-06,359 "loss": 0.3262,360 "step": 50361 },362 {363 "epoch": 0.1585081585081585,364 "grad_norm": 0.9648517370223999,365 "learning_rate": 9.682875264270614e-06,366 "loss": 0.3376,367 "step": 51368 },369 {370 "epoch": 0.16161616161616163,371 "grad_norm": 1.1039059162139893,372 "learning_rate": 9.6723044397463e-06,373 "loss": 0.3352,374 "step": 52375 },376 {377 "epoch": 0.16472416472416473,378 "grad_norm": 1.0544918775558472,379 "learning_rate": 9.661733615221988e-06,380 "loss": 0.3237,381 "step": 53382 },383 {384 "epoch": 0.16783216783216784,385 "grad_norm": 1.533158302307129,386 "learning_rate": 9.651162790697676e-06,387 "loss": 0.3287,388 "step": 54389 },390 {391 "epoch": 0.17094017094017094,392 "grad_norm": 1.2342826128005981,393 "learning_rate": 9.640591966173363e-06,394 "loss": 0.3162,395 "step": 55396 },397 {398 "epoch": 0.17404817404817405,399 "grad_norm": 1.0702942609786987,400 "learning_rate": 9.63002114164905e-06,401 "loss": 0.3143,402 "step": 56403 },404 {405 "epoch": 0.17715617715617715,406 "grad_norm": 1.02211594581604,407 "learning_rate": 9.619450317124736e-06,408 "loss": 0.3318,409 "step": 57410 },411 {412 "epoch": 0.18026418026418026,413 "grad_norm": 0.8379388451576233,414 "learning_rate": 9.608879492600423e-06,415 "loss": 0.3239,416 "step": 58417 },418 {419 "epoch": 0.18337218337218336,420 "grad_norm": 0.9620960354804993,421 "learning_rate": 9.59830866807611e-06,422 "loss": 0.3246,423 "step": 59424 },425 {426 "epoch": 0.1864801864801865,427 "grad_norm": 0.9239097833633423,428 "learning_rate": 9.587737843551797e-06,429 "loss": 0.3278,430 "step": 60431 },432 {433 "epoch": 0.1895881895881896,434 "grad_norm": 0.7097995281219482,435 "learning_rate": 9.577167019027484e-06,436 "loss": 0.3152,437 "step": 61438 },439 {440 "epoch": 0.1926961926961927,441 "grad_norm": 0.9077997803688049,442 "learning_rate": 9.566596194503171e-06,443 "loss": 0.3219,444 "step": 62445 },446 {447 "epoch": 0.1958041958041958,448 "grad_norm": 0.8704112768173218,449 "learning_rate": 9.55602536997886e-06,450 "loss": 0.3262,451 "step": 63452 },453 {454 "epoch": 0.1989121989121989,455 "grad_norm": 0.9264605641365051,456 "learning_rate": 9.545454545454547e-06,457 "loss": 0.3176,458 "step": 64459 },460 {461 "epoch": 0.1989121989121989,462 "eval_loss": 0.3377174139022827,463 "eval_runtime": 149.1316,464 "eval_samples_per_second": 1.911,465 "eval_steps_per_second": 0.959,466 "step": 64467 },468 {469 "epoch": 0.20202020202020202,470 "grad_norm": 0.9881049394607544,471 "learning_rate": 9.534883720930234e-06,472 "loss": 0.3312,473 "step": 65474 },475 {476 "epoch": 0.20512820512820512,477 "grad_norm": 1.1825007200241089,478 "learning_rate": 9.524312896405921e-06,479 "loss": 0.3189,480 "step": 66481 },482 {483 "epoch": 0.20823620823620823,484 "grad_norm": 0.8272495865821838,485 "learning_rate": 9.513742071881608e-06,486 "loss": 0.3293,487 "step": 67488 },489 {490 "epoch": 0.21134421134421136,491 "grad_norm": 1.0992769002914429,492 "learning_rate": 9.503171247357295e-06,493 "loss": 0.3119,494 "step": 68495 },496 {497 "epoch": 0.21445221445221446,498 "grad_norm": 0.9182390570640564,499 "learning_rate": 9.492600422832982e-06,500 "loss": 0.331,501 "step": 69502 },503 {504 "epoch": 0.21756021756021757,505 "grad_norm": 0.8677308559417725,506 "learning_rate": 9.482029598308669e-06,507 "loss": 0.3168,508 "step": 70509 },510 {511 "epoch": 0.22066822066822067,512 "grad_norm": 1.2915256023406982,513 "learning_rate": 9.471458773784356e-06,514 "loss": 0.3181,515 "step": 71516 },517 {518 "epoch": 0.22377622377622378,519 "grad_norm": 1.6176910400390625,520 "learning_rate": 9.460887949260043e-06,521 "loss": 0.3254,522 "step": 72523 },524 {525 "epoch": 0.22688422688422688,526 "grad_norm": 0.6357202529907227,527 "learning_rate": 9.45031712473573e-06,528 "loss": 0.3298,529 "step": 73530 },531 {532 "epoch": 0.22999222999222999,533 "grad_norm": 0.911662220954895,534 "learning_rate": 9.439746300211417e-06,535 "loss": 0.3248,536 "step": 74537 },538 {539 "epoch": 0.2331002331002331,540 "grad_norm": 0.7426556944847107,541 "learning_rate": 9.429175475687104e-06,542 "loss": 0.3301,543 "step": 75544 },545 {546 "epoch": 0.23620823620823622,547 "grad_norm": 0.7509779930114746,548 "learning_rate": 9.418604651162791e-06,549 "loss": 0.3209,550 "step": 76551 },552 {553 "epoch": 0.23931623931623933,554 "grad_norm": 0.7699870467185974,555 "learning_rate": 9.408033826638478e-06,556 "loss": 0.3171,557 "step": 77558 },559 {560 "epoch": 0.24242424242424243,561 "grad_norm": 0.7583193182945251,562 "learning_rate": 9.397463002114165e-06,563 "loss": 0.3128,564 "step": 78565 },566 {567 "epoch": 0.24553224553224554,568 "grad_norm": 0.968973696231842,569 "learning_rate": 9.386892177589852e-06,570 "loss": 0.3293,571 "step": 79572 },573 {574 "epoch": 0.24864024864024864,575 "grad_norm": 0.9967902302742004,576 "learning_rate": 9.37632135306554e-06,577 "loss": 0.3209,578 "step": 80579 },580 {581 "epoch": 0.2517482517482518,582 "grad_norm": 0.7837809920310974,583 "learning_rate": 9.365750528541226e-06,584 "loss": 0.3152,585 "step": 81586 },587 {588 "epoch": 0.25485625485625485,589 "grad_norm": 1.6905367374420166,590 "learning_rate": 9.355179704016915e-06,591 "loss": 0.3163,592 "step": 82593 },594 {595 "epoch": 0.257964257964258,596 "grad_norm": 0.8734452128410339,597 "learning_rate": 9.344608879492602e-06,598 "loss": 0.3306,599 "step": 83600 },601 {602 "epoch": 0.26107226107226106,603 "grad_norm": 3.6059653759002686,604 "learning_rate": 9.33403805496829e-06,605 "loss": 0.3104,606 "step": 84607 },608 {609 "epoch": 0.2641802641802642,610 "grad_norm": 1.1703656911849976,611 "learning_rate": 9.323467230443976e-06,612 "loss": 0.3071,613 "step": 85614 },615 {616 "epoch": 0.26728826728826727,617 "grad_norm": 0.8762909770011902,618 "learning_rate": 9.312896405919663e-06,619 "loss": 0.3022,620 "step": 86621 },622 {623 "epoch": 0.2703962703962704,624 "grad_norm": 2.158876419067383,625 "learning_rate": 9.30232558139535e-06,626 "loss": 0.3217,627 "step": 87628 },629 {630 "epoch": 0.27350427350427353,631 "grad_norm": 0.8010348081588745,632 "learning_rate": 9.291754756871036e-06,633 "loss": 0.322,634 "step": 88635 },636 {637 "epoch": 0.2766122766122766,638 "grad_norm": 1.119739055633545,639 "learning_rate": 9.281183932346723e-06,640 "loss": 0.3248,641 "step": 89642 },643 {644 "epoch": 0.27972027972027974,645 "grad_norm": 0.7900079488754272,646 "learning_rate": 9.27061310782241e-06,647 "loss": 0.3102,648 "step": 90649 },650 {651 "epoch": 0.2828282828282828,652 "grad_norm": 0.8093041181564331,653 "learning_rate": 9.260042283298098e-06,654 "loss": 0.3259,655 "step": 91656 },657 {658 "epoch": 0.28593628593628595,659 "grad_norm": 0.7240622043609619,660 "learning_rate": 9.249471458773785e-06,661 "loss": 0.3002,662 "step": 92663 },664 {665 "epoch": 0.289044289044289,666 "grad_norm": 0.9449782371520996,667 "learning_rate": 9.238900634249473e-06,668 "loss": 0.3076,669 "step": 93670 },671 {672 "epoch": 0.29215229215229216,673 "grad_norm": 0.9448596835136414,674 "learning_rate": 9.22832980972516e-06,675 "loss": 0.3012,676 "step": 94677 },678 {679 "epoch": 0.29526029526029524,680 "grad_norm": 0.9209067821502686,681 "learning_rate": 9.217758985200847e-06,682 "loss": 0.3131,683 "step": 95684 },685 {686 "epoch": 0.29836829836829837,687 "grad_norm": 0.878709614276886,688 "learning_rate": 9.207188160676534e-06,689 "loss": 0.3157,690 "step": 96691 },692 {693 "epoch": 0.3014763014763015,694 "grad_norm": 1.1178463697433472,695 "learning_rate": 9.19661733615222e-06,696 "loss": 0.3166,697 "step": 97698 },699 {700 "epoch": 0.3045843045843046,701 "grad_norm": 0.9717866778373718,702 "learning_rate": 9.186046511627908e-06,703 "loss": 0.3144,704 "step": 98705 },706 {707 "epoch": 0.3076923076923077,708 "grad_norm": 0.9905857443809509,709 "learning_rate": 9.175475687103595e-06,710 "loss": 0.3263,711 "step": 99712 },713 {714 "epoch": 0.3108003108003108,715 "grad_norm": 1.0447399616241455,716 "learning_rate": 9.164904862579282e-06,717 "loss": 0.3074,718 "step": 100719 },720 {721 "epoch": 0.3139083139083139,722 "grad_norm": 0.9876366853713989,723 "learning_rate": 9.154334038054969e-06,724 "loss": 0.3221,725 "step": 101726 },727 {728 "epoch": 0.317016317016317,729 "grad_norm": 1.3406106233596802,730 "learning_rate": 9.143763213530656e-06,731 "loss": 0.3209,732 "step": 102733 },734 {735 "epoch": 0.3201243201243201,736 "grad_norm": 1.1402978897094727,737 "learning_rate": 9.133192389006343e-06,738 "loss": 0.3181,739 "step": 103740 },741 {742 "epoch": 0.32323232323232326,743 "grad_norm": 1.0274314880371094,744 "learning_rate": 9.12262156448203e-06,745 "loss": 0.3179,746 "step": 104747 },748 {749 "epoch": 0.32634032634032634,750 "grad_norm": 1.0853135585784912,751 "learning_rate": 9.112050739957717e-06,752 "loss": 0.3068,753 "step": 105754 },755 {756 "epoch": 0.32944832944832947,757 "grad_norm": 0.9549627900123596,758 "learning_rate": 9.101479915433404e-06,759 "loss": 0.3058,760 "step": 106761 },762 {763 "epoch": 0.33255633255633255,764 "grad_norm": 0.9081363081932068,765 "learning_rate": 9.090909090909091e-06,766 "loss": 0.305,767 "step": 107768 },769 {770 "epoch": 0.3356643356643357,771 "grad_norm": 1.083267092704773,772 "learning_rate": 9.080338266384778e-06,773 "loss": 0.3293,774 "step": 108775 },776 {777 "epoch": 0.33877233877233875,778 "grad_norm": 0.9146764278411865,779 "learning_rate": 9.069767441860465e-06,780 "loss": 0.3308,781 "step": 109782 },783 {784 "epoch": 0.3418803418803419,785 "grad_norm": 0.8309290409088135,786 "learning_rate": 9.059196617336154e-06,787 "loss": 0.3219,788 "step": 110789 },790 {791 "epoch": 0.34498834498834496,792 "grad_norm": 0.7540556788444519,793 "learning_rate": 9.048625792811841e-06,794 "loss": 0.3165,795 "step": 111796 },797 {798 "epoch": 0.3480963480963481,799 "grad_norm": 0.7756165862083435,800 "learning_rate": 9.038054968287528e-06,801 "loss": 0.3201,802 "step": 112803 },804 {805 "epoch": 0.35120435120435123,806 "grad_norm": 1.016161561012268,807 "learning_rate": 9.027484143763215e-06,808 "loss": 0.318,809 "step": 113810 },811 {812 "epoch": 0.3543123543123543,813 "grad_norm": 1.1762275695800781,814 "learning_rate": 9.016913319238902e-06,815 "loss": 0.3071,816 "step": 114817 },818 {819 "epoch": 0.35742035742035744,820 "grad_norm": 1.0186941623687744,821 "learning_rate": 9.006342494714589e-06,822 "loss": 0.3094,823 "step": 115824 },825 {826 "epoch": 0.3605283605283605,827 "grad_norm": 1.3835426568984985,828 "learning_rate": 8.995771670190276e-06,829 "loss": 0.3203,830 "step": 116831 },832 {833 "epoch": 0.36363636363636365,834 "grad_norm": 0.9151639938354492,835 "learning_rate": 8.985200845665963e-06,836 "loss": 0.3075,837 "step": 117838 },839 {840 "epoch": 0.3667443667443667,841 "grad_norm": 0.9079708456993103,842 "learning_rate": 8.974630021141648e-06,843 "loss": 0.3111,844 "step": 118845 },846 {847 "epoch": 0.36985236985236986,848 "grad_norm": 0.7135366201400757,849 "learning_rate": 8.964059196617337e-06,850 "loss": 0.3131,851 "step": 119852 },853 {854 "epoch": 0.372960372960373,855 "grad_norm": 0.7310993671417236,856 "learning_rate": 8.953488372093024e-06,857 "loss": 0.3181,858 "step": 120859 },860 {861 "epoch": 0.37606837606837606,862 "grad_norm": 0.9562262296676636,863 "learning_rate": 8.942917547568711e-06,864 "loss": 0.3114,865 "step": 121866 },867 {868 "epoch": 0.3791763791763792,869 "grad_norm": 1.088692545890808,870 "learning_rate": 8.932346723044398e-06,871 "loss": 0.2985,872 "step": 122873 },874 {875 "epoch": 0.3822843822843823,876 "grad_norm": 1.3334287405014038,877 "learning_rate": 8.921775898520085e-06,878 "loss": 0.3198,879 "step": 123880 },881 {882 "epoch": 0.3853923853923854,883 "grad_norm": 1.1457082033157349,884 "learning_rate": 8.911205073995772e-06,885 "loss": 0.3027,886 "step": 124887 },888 {889 "epoch": 0.3885003885003885,890 "grad_norm": 1.0944201946258545,891 "learning_rate": 8.90063424947146e-06,892 "loss": 0.3195,893 "step": 125894 },895 {896 "epoch": 0.3916083916083916,897 "grad_norm": 1.679890513420105,898 "learning_rate": 8.890063424947146e-06,899 "loss": 0.3118,900 "step": 126901 },902 {903 "epoch": 0.3947163947163947,904 "grad_norm": 1.0934737920761108,905 "learning_rate": 8.879492600422833e-06,906 "loss": 0.3125,907 "step": 127908 },909 {910 "epoch": 0.3978243978243978,911 "grad_norm": 0.9423776865005493,912 "learning_rate": 8.86892177589852e-06,913 "loss": 0.3069,914 "step": 128915 },916 {917 "epoch": 0.3978243978243978,918 "eval_loss": 0.33542340993881226,919 "eval_runtime": 147.0915,920 "eval_samples_per_second": 1.938,921 "eval_steps_per_second": 0.972,922 "step": 128923 },924 {925 "epoch": 0.40093240093240096,926 "grad_norm": 1.373064637184143,927 "learning_rate": 8.858350951374208e-06,928 "loss": 0.3113,929 "step": 129930 },931 {932 "epoch": 0.40404040404040403,933 "grad_norm": 0.9782734513282776,934 "learning_rate": 8.847780126849895e-06,935 "loss": 0.3176,936 "step": 130937 },938 {939 "epoch": 0.40714840714840717,940 "grad_norm": 1.1988129615783691,941 "learning_rate": 8.837209302325582e-06,942 "loss": 0.3036,943 "step": 131944 },945 {946 "epoch": 0.41025641025641024,947 "grad_norm": 1.3978164196014404,948 "learning_rate": 8.826638477801269e-06,949 "loss": 0.3067,950 "step": 132951 },952 {953 "epoch": 0.4133644133644134,954 "grad_norm": 0.8266012072563171,955 "learning_rate": 8.816067653276956e-06,956 "loss": 0.3105,957 "step": 133958 },959 {960 "epoch": 0.41647241647241645,961 "grad_norm": 1.0358003377914429,962 "learning_rate": 8.805496828752643e-06,963 "loss": 0.3176,964 "step": 134965 },966 {967 "epoch": 0.4195804195804196,968 "grad_norm": 0.9363102316856384,969 "learning_rate": 8.79492600422833e-06,970 "loss": 0.3151,971 "step": 135972 },973 {974 "epoch": 0.4226884226884227,975 "grad_norm": 0.9805242419242859,976 "learning_rate": 8.784355179704017e-06,977 "loss": 0.3164,978 "step": 136979 },980 {981 "epoch": 0.4257964257964258,982 "grad_norm": 1.4923985004425049,983 "learning_rate": 8.773784355179706e-06,984 "loss": 0.3059,985 "step": 137986 },987 {988 "epoch": 0.4289044289044289,989 "grad_norm": 1.7009886503219604,990 "learning_rate": 8.763213530655393e-06,991 "loss": 0.2937,992 "step": 138993 },994 {995 "epoch": 0.432012432012432,996 "grad_norm": 0.8320425748825073,997 "learning_rate": 8.75264270613108e-06,998 "loss": 0.288,999 "step": 1391000 },1001 {1002 "epoch": 0.43512043512043513,1003 "grad_norm": 1.3431979417800903,1004 "learning_rate": 8.742071881606767e-06,1005 "loss": 0.3063,1006 "step": 1401007 },1008 {1009 "epoch": 0.4382284382284382,1010 "grad_norm": 1.0519447326660156,1011 "learning_rate": 8.731501057082454e-06,1012 "loss": 0.3043,1013 "step": 1411014 },1015 {1016 "epoch": 0.44133644133644134,1017 "grad_norm": 1.0041645765304565,1018 "learning_rate": 8.72093023255814e-06,1019 "loss": 0.3207,1020 "step": 1421021 },1022 {1023 "epoch": 0.4444444444444444,1024 "grad_norm": 1.176352620124817,1025 "learning_rate": 8.710359408033828e-06,1026 "loss": 0.3099,1027 "step": 1431028 },1029 {1030 "epoch": 0.44755244755244755,1031 "grad_norm": 0.8591434955596924,1032 "learning_rate": 8.699788583509515e-06,1033 "loss": 0.2913,1034 "step": 1441035 },1036 {1037 "epoch": 0.4471858134155744,1038 "grad_norm": 1.2351419925689697,1039 "learning_rate": 8.689217758985202e-06,1040 "loss": 0.3099,1041 "step": 1451042 },1043 {1044 "epoch": 0.4502698535080956,1045 "grad_norm": 1.8375589847564697,1046 "learning_rate": 8.691099476439791e-06,1047 "loss": 0.3092,1048 "step": 1461049 },1050 {1051 "epoch": 0.4533538936006168,1052 "grad_norm": 1.07125985622406,1053 "learning_rate": 8.680628272251308e-06,1054 "loss": 0.3016,1055 "step": 1471056 },1057 {1058 "epoch": 0.456437933693138,1059 "grad_norm": 1.1839478015899658,1060 "learning_rate": 8.670157068062827e-06,1061 "loss": 0.3003,1062 "step": 1481063 },1064 {1065 "epoch": 0.45952197378565923,1066 "grad_norm": 1.294833779335022,1067 "learning_rate": 8.659685863874346e-06,1068 "loss": 0.2972,1069 "step": 1491070 },1071 {1072 "epoch": 0.4626060138781804,1073 "grad_norm": 1.0540661811828613,1074 "learning_rate": 8.649214659685865e-06,1075 "loss": 0.2837,1076 "step": 1501077 },1078 {1079 "epoch": 0.4656900539707016,1080 "grad_norm": 1.1067568063735962,1081 "learning_rate": 8.638743455497383e-06,1082 "loss": 0.2966,1083 "step": 1511084 },1085 {1086 "epoch": 0.46877409406322285,1087 "grad_norm": 0.9972389340400696,1088 "learning_rate": 8.6282722513089e-06,1089 "loss": 0.2934,1090 "step": 1521091 },1092 {1093 "epoch": 0.471858134155744,1094 "grad_norm": 1.1589370965957642,1095 "learning_rate": 8.61780104712042e-06,1096 "loss": 0.3026,1097 "step": 1531098 },1099 {1100 "epoch": 0.47494217424826524,1101 "grad_norm": 1.1224210262298584,1102 "learning_rate": 8.607329842931938e-06,1103 "loss": 0.3042,1104 "step": 1541105 },1106 {1107 "epoch": 0.4780262143407864,1108 "grad_norm": 1.3200238943099976,1109 "learning_rate": 8.596858638743457e-06,1110 "loss": 0.3124,1111 "step": 1551112 },1113 {1114 "epoch": 0.4811102544333076,1115 "grad_norm": 1.1300067901611328,1116 "learning_rate": 8.586387434554974e-06,1117 "loss": 0.3167,1118 "step": 1561119 },1120 {1121 "epoch": 0.48419429452582885,1122 "grad_norm": 0.9678866863250732,1123 "learning_rate": 8.575916230366493e-06,1124 "loss": 0.3039,1125 "step": 1571126 },1127 {1128 "epoch": 0.48727833461835,1129 "grad_norm": 0.9656190872192383,1130 "learning_rate": 8.565445026178011e-06,1131 "loss": 0.3067,1132 "step": 1581133 },1134 {1135 "epoch": 0.49036237471087124,1136 "grad_norm": 0.9618685245513916,1137 "learning_rate": 8.55497382198953e-06,1138 "loss": 0.2992,1139 "step": 1591140 },1141 {1142 "epoch": 0.49344641480339246,1143 "grad_norm": 1.1055867671966553,1144 "learning_rate": 8.544502617801049e-06,1145 "loss": 0.2986,1146 "step": 1601147 },1148 {1149 "epoch": 0.49653045489591363,1150 "grad_norm": 0.8761485815048218,1151 "learning_rate": 8.534031413612566e-06,1152 "loss": 0.3071,1153 "step": 1611154 },1155 {1156 "epoch": 0.49961449498843485,1157 "grad_norm": 1.0709651708602905,1158 "learning_rate": 8.523560209424085e-06,1159 "loss": 0.2965,1160 "step": 1621161 },1162 {1163 "epoch": 0.5026985350809561,1164 "grad_norm": 1.2407382726669312,1165 "learning_rate": 8.513089005235604e-06,1166 "loss": 0.3134,1167 "step": 1631168 },1169 {1170 "epoch": 0.5057825751734772,1171 "grad_norm": 1.46315598487854,1172 "learning_rate": 8.502617801047122e-06,1173 "loss": 0.2886,1174 "step": 1641175 },1176 {1177 "epoch": 0.5088666152659984,1178 "grad_norm": 1.2314726114273071,1179 "learning_rate": 8.49214659685864e-06,1180 "loss": 0.2902,1181 "step": 1651182 },1183 {1184 "epoch": 0.5119506553585197,1185 "grad_norm": 1.223716378211975,1186 "learning_rate": 8.481675392670158e-06,1187 "loss": 0.3088,1188 "step": 1661189 },1190 {1191 "epoch": 0.5150346954510409,1192 "grad_norm": 1.1966098546981812,1193 "learning_rate": 8.471204188481677e-06,1194 "loss": 0.3139,1195 "step": 1671196 },1197 {1198 "epoch": 0.518118735543562,1199 "grad_norm": 1.1182276010513306,1200 "learning_rate": 8.460732984293194e-06,