Delta-Vector/Pascal-Base-Lora
112
1{2 "best_global_step": null,3 "best_metric": null,4 "best_model_checkpoint": null,5 "epoch": 1.0,6 "eval_steps": 500,7 "global_step": 1004,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.00099601593625498,14 "grad_norm": 0.4463295638561249,15 "learning_rate": 9.900990099009901e-08,16 "loss": 2.6197,17 "step": 118 },19 {20 "epoch": 0.00199203187250996,21 "grad_norm": 0.8444207906723022,22 "learning_rate": 1.9801980198019803e-07,23 "loss": 2.7588,24 "step": 225 },26 {27 "epoch": 0.00298804780876494,28 "grad_norm": 0.6591606140136719,29 "learning_rate": 2.9702970297029703e-07,30 "loss": 2.9263,31 "step": 332 },33 {34 "epoch": 0.00398406374501992,35 "grad_norm": 0.5656299591064453,36 "learning_rate": 3.9603960396039606e-07,37 "loss": 2.4296,38 "step": 439 },40 {41 "epoch": 0.0049800796812749,42 "grad_norm": 0.5051721930503845,43 "learning_rate": 4.950495049504951e-07,44 "loss": 2.3939,45 "step": 546 },47 {48 "epoch": 0.00597609561752988,49 "grad_norm": 0.7762399911880493,50 "learning_rate": 5.940594059405941e-07,51 "loss": 2.6638,52 "step": 653 },54 {55 "epoch": 0.0069721115537848604,56 "grad_norm": 0.5301679968833923,57 "learning_rate": 6.930693069306931e-07,58 "loss": 2.2199,59 "step": 760 },61 {62 "epoch": 0.00796812749003984,63 "grad_norm": 0.6617525219917297,64 "learning_rate": 7.920792079207921e-07,65 "loss": 2.8019,66 "step": 867 },68 {69 "epoch": 0.008964143426294821,70 "grad_norm": 0.7944237589836121,71 "learning_rate": 8.910891089108911e-07,72 "loss": 2.7146,73 "step": 974 },75 {76 "epoch": 0.0099601593625498,77 "grad_norm": 0.6918312907218933,78 "learning_rate": 9.900990099009902e-07,79 "loss": 2.6128,80 "step": 1081 },82 {83 "epoch": 0.010956175298804782,84 "grad_norm": 0.550072193145752,85 "learning_rate": 1.0891089108910893e-06,86 "loss": 2.5252,87 "step": 1188 },89 {90 "epoch": 0.01195219123505976,91 "grad_norm": 0.4420550763607025,92 "learning_rate": 1.1881188118811881e-06,93 "loss": 2.6964,94 "step": 1295 },96 {97 "epoch": 0.012948207171314742,98 "grad_norm": 0.4683515429496765,99 "learning_rate": 1.2871287128712872e-06,100 "loss": 2.6433,101 "step": 13102 },103 {104 "epoch": 0.013944223107569721,105 "grad_norm": 0.5689812898635864,106 "learning_rate": 1.3861386138613863e-06,107 "loss": 2.3309,108 "step": 14109 },110 {111 "epoch": 0.014940239043824702,112 "grad_norm": 0.5711223483085632,113 "learning_rate": 1.4851485148514852e-06,114 "loss": 2.4396,115 "step": 15116 },117 {118 "epoch": 0.01593625498007968,119 "grad_norm": 0.4562544822692871,120 "learning_rate": 1.5841584158415842e-06,121 "loss": 2.234,122 "step": 16123 },124 {125 "epoch": 0.01693227091633466,126 "grad_norm": 0.33882570266723633,127 "learning_rate": 1.6831683168316833e-06,128 "loss": 2.5468,129 "step": 17130 },131 {132 "epoch": 0.017928286852589643,133 "grad_norm": 0.46446338295936584,134 "learning_rate": 1.7821782178217822e-06,135 "loss": 2.6143,136 "step": 18137 },138 {139 "epoch": 0.018924302788844622,140 "grad_norm": 0.625619649887085,141 "learning_rate": 1.8811881188118813e-06,142 "loss": 2.5565,143 "step": 19144 },145 {146 "epoch": 0.0199203187250996,147 "grad_norm": 0.5139931440353394,148 "learning_rate": 1.9801980198019803e-06,149 "loss": 2.8371,150 "step": 20151 },152 {153 "epoch": 0.02091633466135458,154 "grad_norm": 0.45826011896133423,155 "learning_rate": 2.0792079207920794e-06,156 "loss": 2.5883,157 "step": 21158 },159 {160 "epoch": 0.021912350597609563,161 "grad_norm": 0.5945838093757629,162 "learning_rate": 2.1782178217821785e-06,163 "loss": 2.6956,164 "step": 22165 },166 {167 "epoch": 0.022908366533864542,168 "grad_norm": 0.6705940961837769,169 "learning_rate": 2.2772277227722776e-06,170 "loss": 3.1889,171 "step": 23172 },173 {174 "epoch": 0.02390438247011952,175 "grad_norm": 0.489014208316803,176 "learning_rate": 2.3762376237623762e-06,177 "loss": 2.646,178 "step": 24179 },180 {181 "epoch": 0.0249003984063745,182 "grad_norm": 0.5540168285369873,183 "learning_rate": 2.4752475247524753e-06,184 "loss": 2.6909,185 "step": 25186 },187 {188 "epoch": 0.025896414342629483,189 "grad_norm": 0.34993091225624084,190 "learning_rate": 2.5742574257425744e-06,191 "loss": 2.5703,192 "step": 26193 },194 {195 "epoch": 0.026892430278884463,196 "grad_norm": 0.6204649209976196,197 "learning_rate": 2.6732673267326735e-06,198 "loss": 2.6973,199 "step": 27200 },201 {202 "epoch": 0.027888446215139442,203 "grad_norm": 0.6948006749153137,204 "learning_rate": 2.7722772277227726e-06,205 "loss": 2.8826,206 "step": 28207 },208 {209 "epoch": 0.02888446215139442,210 "grad_norm": 0.4865665137767792,211 "learning_rate": 2.8712871287128712e-06,212 "loss": 2.6566,213 "step": 29214 },215 {216 "epoch": 0.029880478087649404,217 "grad_norm": 0.7654755711555481,218 "learning_rate": 2.9702970297029703e-06,219 "loss": 2.9627,220 "step": 30221 },222 {223 "epoch": 0.030876494023904383,224 "grad_norm": 0.636715829372406,225 "learning_rate": 3.0693069306930694e-06,226 "loss": 2.3846,227 "step": 31228 },229 {230 "epoch": 0.03187250996015936,231 "grad_norm": 0.3698335289955139,232 "learning_rate": 3.1683168316831685e-06,233 "loss": 2.6724,234 "step": 32235 },236 {237 "epoch": 0.03286852589641434,238 "grad_norm": 0.7592146396636963,239 "learning_rate": 3.2673267326732676e-06,240 "loss": 2.9239,241 "step": 33242 },243 {244 "epoch": 0.03386454183266932,245 "grad_norm": 0.7194887399673462,246 "learning_rate": 3.3663366336633666e-06,247 "loss": 2.4727,248 "step": 34249 },250 {251 "epoch": 0.0348605577689243,252 "grad_norm": 0.4150688350200653,253 "learning_rate": 3.4653465346534653e-06,254 "loss": 2.6407,255 "step": 35256 },257 {258 "epoch": 0.035856573705179286,259 "grad_norm": 0.4450097382068634,260 "learning_rate": 3.5643564356435644e-06,261 "loss": 2.6709,262 "step": 36263 },264 {265 "epoch": 0.036852589641434265,266 "grad_norm": 0.4754781424999237,267 "learning_rate": 3.6633663366336635e-06,268 "loss": 2.6848,269 "step": 37270 },271 {272 "epoch": 0.037848605577689244,273 "grad_norm": 0.41208407282829285,274 "learning_rate": 3.7623762376237625e-06,275 "loss": 2.5176,276 "step": 38277 },278 {279 "epoch": 0.03884462151394422,280 "grad_norm": 0.41328731179237366,281 "learning_rate": 3.861386138613862e-06,282 "loss": 2.3275,283 "step": 39284 },285 {286 "epoch": 0.0398406374501992,287 "grad_norm": 0.5368106365203857,288 "learning_rate": 3.960396039603961e-06,289 "loss": 2.4877,290 "step": 40291 },292 {293 "epoch": 0.04083665338645418,294 "grad_norm": 0.37100547552108765,295 "learning_rate": 4.05940594059406e-06,296 "loss": 2.5933,297 "step": 41298 },299 {300 "epoch": 0.04183266932270916,301 "grad_norm": 0.4816776216030121,302 "learning_rate": 4.158415841584159e-06,303 "loss": 2.844,304 "step": 42305 },306 {307 "epoch": 0.04282868525896414,308 "grad_norm": 0.4209342896938324,309 "learning_rate": 4.2574257425742575e-06,310 "loss": 2.5422,311 "step": 43312 },313 {314 "epoch": 0.043824701195219126,315 "grad_norm": 0.6714078783988953,316 "learning_rate": 4.356435643564357e-06,317 "loss": 2.7081,318 "step": 44319 },320 {321 "epoch": 0.044820717131474105,322 "grad_norm": 0.26568883657455444,323 "learning_rate": 4.455445544554456e-06,324 "loss": 2.9217,325 "step": 45326 },327 {328 "epoch": 0.045816733067729085,329 "grad_norm": 0.37946802377700806,330 "learning_rate": 4.554455445544555e-06,331 "loss": 2.4118,332 "step": 46333 },334 {335 "epoch": 0.046812749003984064,336 "grad_norm": 0.6484291553497314,337 "learning_rate": 4.653465346534654e-06,338 "loss": 2.547,339 "step": 47340 },341 {342 "epoch": 0.04780876494023904,343 "grad_norm": 0.29198533296585083,344 "learning_rate": 4.7524752475247525e-06,345 "loss": 2.519,346 "step": 48347 },348 {349 "epoch": 0.04880478087649402,350 "grad_norm": 0.7583147883415222,351 "learning_rate": 4.851485148514852e-06,352 "loss": 2.9767,353 "step": 49354 },355 {356 "epoch": 0.049800796812749,357 "grad_norm": 0.5130609273910522,358 "learning_rate": 4.950495049504951e-06,359 "loss": 2.7004,360 "step": 50361 },362 {363 "epoch": 0.05079681274900399,364 "grad_norm": 0.31620916724205017,365 "learning_rate": 5.04950495049505e-06,366 "loss": 2.4462,367 "step": 51368 },369 {370 "epoch": 0.05179282868525897,371 "grad_norm": 0.8395189046859741,372 "learning_rate": 5.148514851485149e-06,373 "loss": 2.5588,374 "step": 52375 },376 {377 "epoch": 0.052788844621513946,378 "grad_norm": 0.387138307094574,379 "learning_rate": 5.247524752475248e-06,380 "loss": 2.1448,381 "step": 53382 },383 {384 "epoch": 0.053784860557768925,385 "grad_norm": 1.2158163785934448,386 "learning_rate": 5.346534653465347e-06,387 "loss": 2.3136,388 "step": 54389 },390 {391 "epoch": 0.054780876494023904,392 "grad_norm": 0.2387009710073471,393 "learning_rate": 5.4455445544554465e-06,394 "loss": 2.1985,395 "step": 55396 },397 {398 "epoch": 0.055776892430278883,399 "grad_norm": 0.3181290924549103,400 "learning_rate": 5.544554455445545e-06,401 "loss": 2.3419,402 "step": 56403 },404 {405 "epoch": 0.05677290836653386,406 "grad_norm": 0.37027299404144287,407 "learning_rate": 5.643564356435644e-06,408 "loss": 2.6245,409 "step": 57410 },411 {412 "epoch": 0.05776892430278884,413 "grad_norm": 1.2025309801101685,414 "learning_rate": 5.7425742574257425e-06,415 "loss": 3.9658,416 "step": 58417 },418 {419 "epoch": 0.05876494023904383,420 "grad_norm": 0.2420024573802948,421 "learning_rate": 5.841584158415842e-06,422 "loss": 2.6491,423 "step": 59424 },425 {426 "epoch": 0.05976095617529881,427 "grad_norm": 0.5019764304161072,428 "learning_rate": 5.940594059405941e-06,429 "loss": 2.5349,430 "step": 60431 },432 {433 "epoch": 0.060756972111553786,434 "grad_norm": 0.42150792479515076,435 "learning_rate": 6.03960396039604e-06,436 "loss": 3.0192,437 "step": 61438 },439 {440 "epoch": 0.061752988047808766,441 "grad_norm": 0.21461670100688934,442 "learning_rate": 6.138613861386139e-06,443 "loss": 2.4131,444 "step": 62445 },446 {447 "epoch": 0.06274900398406374,448 "grad_norm": 0.27715393900871277,449 "learning_rate": 6.237623762376238e-06,450 "loss": 2.0699,451 "step": 63452 },453 {454 "epoch": 0.06374501992031872,455 "grad_norm": 0.23175019025802612,456 "learning_rate": 6.336633663366337e-06,457 "loss": 2.454,458 "step": 64459 },460 {461 "epoch": 0.0647410358565737,462 "grad_norm": 1.4909917116165161,463 "learning_rate": 6.4356435643564364e-06,464 "loss": 2.394,465 "step": 65466 },467 {468 "epoch": 0.06573705179282868,469 "grad_norm": 0.25836002826690674,470 "learning_rate": 6.534653465346535e-06,471 "loss": 2.1991,472 "step": 66473 },474 {475 "epoch": 0.06673306772908366,476 "grad_norm": 0.24367666244506836,477 "learning_rate": 6.633663366336635e-06,478 "loss": 2.1038,479 "step": 67480 },481 {482 "epoch": 0.06772908366533864,483 "grad_norm": 0.2366018295288086,484 "learning_rate": 6.732673267326733e-06,485 "loss": 2.4102,486 "step": 68487 },488 {489 "epoch": 0.06872509960159362,490 "grad_norm": 0.2741665542125702,491 "learning_rate": 6.831683168316833e-06,492 "loss": 2.4163,493 "step": 69494 },495 {496 "epoch": 0.0697211155378486,497 "grad_norm": 1.1350017786026,498 "learning_rate": 6.930693069306931e-06,499 "loss": 3.1909,500 "step": 70501 },502 {503 "epoch": 0.07071713147410359,504 "grad_norm": 0.7466657161712646,505 "learning_rate": 7.02970297029703e-06,506 "loss": 3.0505,507 "step": 71508 },509 {510 "epoch": 0.07171314741035857,511 "grad_norm": 0.6016573309898376,512 "learning_rate": 7.128712871287129e-06,513 "loss": 2.523,514 "step": 72515 },516 {517 "epoch": 0.07270916334661355,518 "grad_norm": 0.29950985312461853,519 "learning_rate": 7.227722772277228e-06,520 "loss": 2.2338,521 "step": 73522 },523 {524 "epoch": 0.07370517928286853,525 "grad_norm": 0.3367365598678589,526 "learning_rate": 7.326732673267327e-06,527 "loss": 2.3668,528 "step": 74529 },530 {531 "epoch": 0.07470119521912351,532 "grad_norm": 0.23957543075084686,533 "learning_rate": 7.425742574257426e-06,534 "loss": 2.3929,535 "step": 75536 },537 {538 "epoch": 0.07569721115537849,539 "grad_norm": 0.2996574342250824,540 "learning_rate": 7.524752475247525e-06,541 "loss": 2.4929,542 "step": 76543 },544 {545 "epoch": 0.07669322709163347,546 "grad_norm": 1.1166422367095947,547 "learning_rate": 7.6237623762376246e-06,548 "loss": 2.2256,549 "step": 77550 },551 {552 "epoch": 0.07768924302788845,553 "grad_norm": 0.3733150362968445,554 "learning_rate": 7.722772277227724e-06,555 "loss": 2.4912,556 "step": 78557 },558 {559 "epoch": 0.07868525896414343,560 "grad_norm": 0.3624296486377716,561 "learning_rate": 7.821782178217822e-06,562 "loss": 2.7605,563 "step": 79564 },565 {566 "epoch": 0.0796812749003984,567 "grad_norm": 0.47846829891204834,568 "learning_rate": 7.920792079207921e-06,569 "loss": 2.7636,570 "step": 80571 },572 {573 "epoch": 0.08067729083665338,574 "grad_norm": 0.3782709836959839,575 "learning_rate": 8.019801980198021e-06,576 "loss": 2.4481,577 "step": 81578 },579 {580 "epoch": 0.08167330677290836,581 "grad_norm": 0.5004844665527344,582 "learning_rate": 8.11881188118812e-06,583 "loss": 2.4166,584 "step": 82585 },586 {587 "epoch": 0.08266932270916334,588 "grad_norm": 0.20830737054347992,589 "learning_rate": 8.217821782178218e-06,590 "loss": 2.4728,591 "step": 83592 },593 {594 "epoch": 0.08366533864541832,595 "grad_norm": 0.2479114830493927,596 "learning_rate": 8.316831683168318e-06,597 "loss": 2.2449,598 "step": 84599 },600 {601 "epoch": 0.0846613545816733,602 "grad_norm": 0.42911332845687866,603 "learning_rate": 8.415841584158416e-06,604 "loss": 2.2295,605 "step": 85606 },607 {608 "epoch": 0.08565737051792828,609 "grad_norm": 0.44220131635665894,610 "learning_rate": 8.514851485148515e-06,611 "loss": 2.4495,612 "step": 86613 },614 {615 "epoch": 0.08665338645418327,616 "grad_norm": 0.23947738111019135,617 "learning_rate": 8.613861386138615e-06,618 "loss": 2.1415,619 "step": 87620 },621 {622 "epoch": 0.08764940239043825,623 "grad_norm": 0.42801541090011597,624 "learning_rate": 8.712871287128714e-06,625 "loss": 2.3226,626 "step": 88627 },628 {629 "epoch": 0.08864541832669323,630 "grad_norm": 0.39098042249679565,631 "learning_rate": 8.811881188118812e-06,632 "loss": 2.3063,633 "step": 89634 },635 {636 "epoch": 0.08964143426294821,637 "grad_norm": 0.29923197627067566,638 "learning_rate": 8.910891089108911e-06,639 "loss": 2.6163,640 "step": 90641 },642 {643 "epoch": 0.09063745019920319,644 "grad_norm": 0.2684191167354584,645 "learning_rate": 9.009900990099011e-06,646 "loss": 2.6845,647 "step": 91648 },649 {650 "epoch": 0.09163346613545817,651 "grad_norm": 0.27097082138061523,652 "learning_rate": 9.10891089108911e-06,653 "loss": 2.598,654 "step": 92655 },656 {657 "epoch": 0.09262948207171315,658 "grad_norm": 0.2647894024848938,659 "learning_rate": 9.20792079207921e-06,660 "loss": 2.2659,661 "step": 93662 },663 {664 "epoch": 0.09362549800796813,665 "grad_norm": 0.38580745458602905,666 "learning_rate": 9.306930693069308e-06,667 "loss": 2.5818,668 "step": 94669 },670 {671 "epoch": 0.0946215139442231,672 "grad_norm": 0.23376502096652985,673 "learning_rate": 9.405940594059405e-06,674 "loss": 2.207,675 "step": 95676 },677 {678 "epoch": 0.09561752988047809,679 "grad_norm": 0.7030872702598572,680 "learning_rate": 9.504950495049505e-06,681 "loss": 2.1312,682 "step": 96683 },684 {685 "epoch": 0.09661354581673307,686 "grad_norm": 0.23579809069633484,687 "learning_rate": 9.603960396039604e-06,688 "loss": 2.0685,689 "step": 97690 },691 {692 "epoch": 0.09760956175298804,693 "grad_norm": 0.3901154100894928,694 "learning_rate": 9.702970297029704e-06,695 "loss": 2.662,696 "step": 98697 },698 {699 "epoch": 0.09860557768924302,700 "grad_norm": 0.2687411606311798,701 "learning_rate": 9.801980198019802e-06,702 "loss": 2.9062,703 "step": 99704 },705 {706 "epoch": 0.099601593625498,707 "grad_norm": 0.1916651427745819,708 "learning_rate": 9.900990099009901e-06,709 "loss": 2.1874,710 "step": 100711 },712 {713 "epoch": 0.10059760956175298,714 "grad_norm": 0.3915342688560486,715 "learning_rate": 1e-05,716 "loss": 2.4196,717 "step": 101718 },719 {720 "epoch": 0.10159362549800798,721 "grad_norm": 0.4256736636161804,722 "learning_rate": 9.999969740355927e-06,723 "loss": 2.3229,724 "step": 102725 },726 {727 "epoch": 0.10258964143426295,728 "grad_norm": 0.24454592168331146,729 "learning_rate": 9.999878961789962e-06,730 "loss": 2.4725,731 "step": 103732 },733 {734 "epoch": 0.10358565737051793,735 "grad_norm": 0.4549209475517273,736 "learning_rate": 9.999727665400876e-06,737 "loss": 2.6802,738 "step": 104739 },740 {741 "epoch": 0.10458167330677291,742 "grad_norm": 0.27968448400497437,743 "learning_rate": 9.999515853019941e-06,744 "loss": 2.154,745 "step": 105746 },747 {748 "epoch": 0.10557768924302789,749 "grad_norm": 0.30781856179237366,750 "learning_rate": 9.999243527210904e-06,751 "loss": 2.1358,752 "step": 106753 },754 {755 "epoch": 0.10657370517928287,756 "grad_norm": 0.22190262377262115,757 "learning_rate": 9.998910691269957e-06,758 "loss": 2.1951,759 "step": 107760 },761 {762 "epoch": 0.10756972111553785,763 "grad_norm": 0.36984801292419434,764 "learning_rate": 9.998517349225698e-06,765 "loss": 2.2283,766 "step": 108767 },768 {769 "epoch": 0.10856573705179283,770 "grad_norm": 0.24837668240070343,771 "learning_rate": 9.998063505839084e-06,772 "loss": 2.4556,773 "step": 109774 },775 {776 "epoch": 0.10956175298804781,777 "grad_norm": 0.17527616024017334,778 "learning_rate": 9.99754916660337e-06,779 "loss": 2.2414,780 "step": 110781 },782 {783 "epoch": 0.11055776892430279,784 "grad_norm": 0.2681446969509125,785 "learning_rate": 9.996974337744047e-06,786 "loss": 2.6504,787 "step": 111788 },789 {790 "epoch": 0.11155378486055777,791 "grad_norm": 0.41997164487838745,792 "learning_rate": 9.99633902621876e-06,793 "loss": 2.4704,794 "step": 112795 },796 {797 "epoch": 0.11254980079681275,798 "grad_norm": 0.43319636583328247,799 "learning_rate": 9.995643239717228e-06,800 "loss": 2.4391,801 "step": 113802 },803 {804 "epoch": 0.11354581673306773,805 "grad_norm": 0.3344462811946869,806 "learning_rate": 9.994886986661155e-06,807 "loss": 2.4113,808 "step": 114809 },810 {811 "epoch": 0.1145418326693227,812 "grad_norm": 0.2086816132068634,813 "learning_rate": 9.994070276204115e-06,814 "loss": 2.1469,815 "step": 115816 },817 {818 "epoch": 0.11553784860557768,819 "grad_norm": 0.35499969124794006,820 "learning_rate": 9.993193118231463e-06,821 "loss": 2.6212,822 "step": 116823 },824 {825 "epoch": 0.11653386454183266,826 "grad_norm": 0.4640713036060333,827 "learning_rate": 9.992255523360187e-06,828 "loss": 2.5926,829 "step": 117830 },831 {832 "epoch": 0.11752988047808766,833 "grad_norm": 0.3302168548107147,834 "learning_rate": 9.991257502938805e-06,835 "loss": 2.0769,836 "step": 118837 },838 {839 "epoch": 0.11852589641434264,840 "grad_norm": 0.4918990135192871,841 "learning_rate": 9.990199069047216e-06,842 "loss": 2.4818,843 "step": 119844 },845 {846 "epoch": 0.11952191235059761,847 "grad_norm": 0.25973260402679443,848 "learning_rate": 9.989080234496548e-06,849 "loss": 2.3236,850 "step": 120851 },852 {853 "epoch": 0.1205179282868526,854 "grad_norm": 0.26280921697616577,855 "learning_rate": 9.98790101282902e-06,856 "loss": 2.4276,857 "step": 121858 },859 {860 "epoch": 0.12151394422310757,861 "grad_norm": 0.21018964052200317,862 "learning_rate": 9.986661418317759e-06,863 "loss": 2.3006,864 "step": 122865 },866 {867 "epoch": 0.12250996015936255,868 "grad_norm": 0.30688363313674927,869 "learning_rate": 9.985361465966644e-06,870 "loss": 2.3402,871 "step": 123872 },873 {874 "epoch": 0.12350597609561753,875 "grad_norm": 0.27469494938850403,876 "learning_rate": 9.984001171510112e-06,877 "loss": 2.7987,878 "step": 124879 },880 {881 "epoch": 0.12450199203187251,882 "grad_norm": 0.2825527489185333,883 "learning_rate": 9.982580551412972e-06,884 "loss": 2.4642,885 "step": 125886 },887 {888 "epoch": 0.1254980079681275,889 "grad_norm": 0.6109227538108826,890 "learning_rate": 9.98109962287021e-06,891 "loss": 2.6041,892 "step": 126893 },894 {895 "epoch": 0.12649402390438247,896 "grad_norm": 0.3983345031738281,897 "learning_rate": 9.979558403806773e-06,898 "loss": 2.4599,899 "step": 127900 },901 {902 "epoch": 0.12749003984063745,903 "grad_norm": 0.3466341495513916,904 "learning_rate": 9.977956912877356e-06,905 "loss": 2.1902,906 "step": 128907 },908 {909 "epoch": 0.12848605577689243,910 "grad_norm": 0.3762282729148865,911 "learning_rate": 9.97629516946618e-06,912 "loss": 2.2643,913 "step": 129914 },915 {916 "epoch": 0.1294820717131474,917 "grad_norm": 0.523991048336029,918 "learning_rate": 9.974573193686747e-06,919 "loss": 2.196,920 "step": 130921 },922 {923 "epoch": 0.13047808764940239,924 "grad_norm": 0.23254041373729706,925 "learning_rate": 9.97279100638161e-06,926 "loss": 2.4402,927 "step": 131928 },929 {930 "epoch": 0.13147410358565736,931 "grad_norm": 0.3137255311012268,932 "learning_rate": 9.970948629122108e-06,933 "loss": 2.5905,934 "step": 132935 },936 {937 "epoch": 0.13247011952191234,938 "grad_norm": 0.21106691658496857,939 "learning_rate": 9.969046084208116e-06,940 "loss": 2.3683,941 "step": 133942 },943 {944 "epoch": 0.13346613545816732,945 "grad_norm": 0.4183836877346039,946 "learning_rate": 9.967083394667763e-06,947 "loss": 2.0614,948 "step": 134949 },950 {951 "epoch": 0.1344621513944223,952 "grad_norm": 0.4468408226966858,953 "learning_rate": 9.965060584257165e-06,954 "loss": 2.4639,955 "step": 135956 },957 {958 "epoch": 0.13545816733067728,959 "grad_norm": 0.22207094728946686,960 "learning_rate": 9.962977677460132e-06,961 "loss": 2.2261,962 "step": 136963 },964 {965 "epoch": 0.13645418326693226,966 "grad_norm": 0.2465856373310089,967 "learning_rate": 9.960834699487873e-06,968 "loss": 2.2444,969 "step": 137970 },971 {972 "epoch": 0.13745019920318724,973 "grad_norm": 0.3648821711540222,974 "learning_rate": 9.958631676278686e-06,975 "loss": 2.6132,976 "step": 138977 },978 {979 "epoch": 0.13844621513944222,980 "grad_norm": 0.21419532597064972,981 "learning_rate": 9.956368634497648e-06,982 "loss": 2.4863,983 "step": 139984 },985 {986 "epoch": 0.1394422310756972,987 "grad_norm": 0.5358874797821045,988 "learning_rate": 9.9540456015363e-06,989 "loss": 2.401,990 "step": 140991 },992 {993 "epoch": 0.14043824701195218,994 "grad_norm": 0.25208160281181335,995 "learning_rate": 9.951662605512298e-06,996 "loss": 2.5901,997 "step": 141998 },999 {1000 "epoch": 0.14143426294820718,1001 "grad_norm": 0.2659305930137634,1002 "learning_rate": 9.949219675269089e-06,1003 "loss": 2.3229,1004 "step": 1421005 },1006 {1007 "epoch": 0.14243027888446216,1008 "grad_norm": 0.5667638778686523,1009 "learning_rate": 9.946716840375552e-06,1010 "loss": 2.4998,1011 "step": 1431012 },1013 {1014 "epoch": 0.14342629482071714,1015 "grad_norm": 0.315893292427063,1016 "learning_rate": 9.944154131125643e-06,1017 "loss": 2.4017,1018 "step": 1441019 },1020 {1021 "epoch": 0.14442231075697212,1022 "grad_norm": 0.43832895159721375,1023 "learning_rate": 9.941531578538032e-06,1024 "loss": 2.473,1025 "step": 1451026 },1027 {1028 "epoch": 0.1454183266932271,1029 "grad_norm": 0.2750052511692047,1030 "learning_rate": 9.938849214355722e-06,1031 "loss": 2.3208,1032 "step": 1461033 },1034 {1035 "epoch": 0.14641434262948208,1036 "grad_norm": 0.26100143790245056,1037 "learning_rate": 9.936107071045665e-06,1038 "loss": 2.2151,1039 "step": 1471040 },1041 {1042 "epoch": 0.14741035856573706,1043 "grad_norm": 0.3080121576786041,1044 "learning_rate": 9.933305181798374e-06,1045 "loss": 2.0868,1046 "step": 1481047 },1048 {1049 "epoch": 0.14840637450199204,1050 "grad_norm": 0.24721984565258026,1051 "learning_rate": 9.93044358052752e-06,1052 "loss": 2.3312,1053 "step": 1491054 },1055 {1056 "epoch": 0.14940239043824702,1057 "grad_norm": 0.5916289687156677,1058 "learning_rate": 9.927522301869515e-06,1059 "loss": 2.6542,1060 "step": 1501061 },1062 {1063 "epoch": 0.150398406374502,1064 "grad_norm": 0.22790588438510895,1065 "learning_rate": 9.924541381183099e-06,1066 "loss": 2.3121,1067 "step": 1511068 },1069 {1070 "epoch": 0.15139442231075698,1071 "grad_norm": 0.3201110064983368,1072 "learning_rate": 9.921500854548916e-06,1073 "loss": 2.8776,1074 "step": 1521075 },1076 {1077 "epoch": 0.15239043824701196,1078 "grad_norm": 0.3063032627105713,1079 "learning_rate": 9.918400758769063e-06,1080 "loss": 2.3604,1081 "step": 1531082 },1083 {1084 "epoch": 0.15338645418326693,1085 "grad_norm": 0.41891732811927795,1086 "learning_rate": 9.915241131366657e-06,1087 "loss": 2.1036,1088 "step": 1541089 },1090 {1091 "epoch": 0.15438247011952191,1092 "grad_norm": 1.0909143686294556,1093 "learning_rate": 9.912022010585385e-06,1094 "loss": 2.5247,1095 "step": 1551096 },1097 {1098 "epoch": 0.1553784860557769,1099 "grad_norm": 0.26673582196235657,1100 "learning_rate": 9.90874343538902e-06,1101 "loss": 2.159,1102 "step": 1561103 },1104 {1105 "epoch": 0.15637450199203187,1106 "grad_norm": 0.3614170551300049,1107 "learning_rate": 9.905405445460972e-06,1108 "loss": 2.4383,1109 "step": 1571110 },1111 {1112 "epoch": 0.15737051792828685,1113 "grad_norm": 0.5078898668289185,1114 "learning_rate": 9.902008081203796e-06,1115 "loss": 2.2543,1116 "step": 1581117 },1118 {1119 "epoch": 0.15836653386454183,1120 "grad_norm": 0.3936934769153595,1121 "learning_rate": 9.898551383738707e-06,1122 "loss": 2.538,1123 "step": 1591124 },1125 {1126 "epoch": 0.1593625498007968,1127 "grad_norm": 0.6516975164413452,1128 "learning_rate": 9.895035394905073e-06,1129 "loss": 2.5301,1130 "step": 1601131 },1132 {1133 "epoch": 0.1603585657370518,1134 "grad_norm": 0.26518794894218445,1135 "learning_rate": 9.89146015725993e-06,1136 "loss": 2.2118,1137 "step": 1611138 },1139 {1140 "epoch": 0.16135458167330677,1141 "grad_norm": 0.41366127133369446,1142 "learning_rate": 9.887825714077439e-06,1143 "loss": 2.4799,1144 "step": 1621145 },1146 {1147 "epoch": 0.16235059760956175,1148 "grad_norm": 0.5400006771087646,1149 "learning_rate": 9.884132109348386e-06,1150 "loss": 2.5019,1151 "step": 1631152 },1153 {1154 "epoch": 0.16334661354581673,1155 "grad_norm": 0.36508408188819885,1156 "learning_rate": 9.880379387779637e-06,1157 "loss": 2.7938,1158 "step": 1641159 },1160 {1161 "epoch": 0.1643426294820717,1162 "grad_norm": 0.4240388572216034,1163 "learning_rate": 9.876567594793597e-06,1164 "loss": 2.5002,1165 "step": 1651166 },1167 {1168 "epoch": 0.16533864541832669,1169 "grad_norm": 0.277864933013916,1170 "learning_rate": 9.87269677652767e-06,1171 "loss": 2.5436,1172 "step": 1661173 },1174 {1175 "epoch": 0.16633466135458166,1176 "grad_norm": 0.25840163230895996,1177 "learning_rate": 9.868766979833686e-06,1178 "loss": 2.2811,1179 "step": 1671180 },1181 {1182 "epoch": 0.16733067729083664,1183 "grad_norm": 0.32198214530944824,1184 "learning_rate": 9.864778252277344e-06,1185 "loss": 2.3215,1186 "step": 1681187 },1188 {1189 "epoch": 0.16832669322709162,1190 "grad_norm": 0.613046407699585,1191 "learning_rate": 9.86073064213764e-06,1192 "loss": 2.8133,1193 "step": 1691194 },1195 {1196 "epoch": 0.1693227091633466,1197 "grad_norm": 0.38470038771629333,1198 "learning_rate": 9.856624198406262e-06,1199 "loss": 2.4133,1200 "step": 170