Lie24/FuLinNa_GLM4-9B-Chat
013
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 15.0,5 "eval_steps": 500,6 "global_step": 840,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.017857142857142856,13 "learning_rate": 7.142857142857143e-07,14 "loss": 6.1665,15 "step": 116 },17 {18 "epoch": 0.03571428571428571,19 "learning_rate": 1.4285714285714286e-06,20 "loss": 6.3965,21 "step": 222 },23 {24 "epoch": 0.05357142857142857,25 "learning_rate": 2.1428571428571427e-06,26 "loss": 6.5581,27 "step": 328 },29 {30 "epoch": 0.07142857142857142,31 "grad_norm": 0.0,32 "learning_rate": 2.1428571428571427e-06,33 "loss": 6.5117,34 "step": 435 },36 {37 "epoch": 0.08928571428571429,38 "grad_norm": 0.0,39 "learning_rate": 2.1428571428571427e-06,40 "loss": 6.5869,41 "step": 542 },43 {44 "epoch": 0.10714285714285714,45 "grad_norm": 0.0,46 "learning_rate": 2.1428571428571427e-06,47 "loss": 6.3418,48 "step": 649 },50 {51 "epoch": 0.125,52 "grad_norm": 0.0,53 "learning_rate": 2.1428571428571427e-06,54 "loss": 6.208,55 "step": 756 },57 {58 "epoch": 0.14285714285714285,59 "grad_norm": 0.0,60 "learning_rate": 2.1428571428571427e-06,61 "loss": 6.3003,62 "step": 863 },64 {65 "epoch": 0.16071428571428573,66 "grad_norm": 0.0,67 "learning_rate": 2.1428571428571427e-06,68 "loss": 6.4839,69 "step": 970 },71 {72 "epoch": 0.17857142857142858,73 "grad_norm": 0.0,74 "learning_rate": 2.1428571428571427e-06,75 "loss": 6.1602,76 "step": 1077 },78 {79 "epoch": 0.19642857142857142,80 "grad_norm": 0.0,81 "learning_rate": 2.1428571428571427e-06,82 "loss": 6.3042,83 "step": 1184 },85 {86 "epoch": 0.21428571428571427,87 "grad_norm": 0.0,88 "learning_rate": 2.1428571428571427e-06,89 "loss": 6.0332,90 "step": 1291 },92 {93 "epoch": 0.23214285714285715,94 "grad_norm": 0.0,95 "learning_rate": 2.1428571428571427e-06,96 "loss": 6.5386,97 "step": 1398 },99 {100 "epoch": 0.25,101 "grad_norm": 0.0,102 "learning_rate": 2.1428571428571427e-06,103 "loss": 6.2471,104 "step": 14105 },106 {107 "epoch": 0.26785714285714285,108 "grad_norm": 0.0,109 "learning_rate": 2.1428571428571427e-06,110 "loss": 6.5361,111 "step": 15112 },113 {114 "epoch": 0.2857142857142857,115 "grad_norm": 0.0,116 "learning_rate": 2.1428571428571427e-06,117 "loss": 6.9404,118 "step": 16119 },120 {121 "epoch": 0.30357142857142855,122 "grad_norm": 0.0,123 "learning_rate": 2.1428571428571427e-06,124 "loss": 6.4058,125 "step": 17126 },127 {128 "epoch": 0.32142857142857145,129 "grad_norm": 0.0,130 "learning_rate": 2.1428571428571427e-06,131 "loss": 6.2627,132 "step": 18133 },134 {135 "epoch": 0.3392857142857143,136 "grad_norm": 0.0,137 "learning_rate": 2.1428571428571427e-06,138 "loss": 6.272,139 "step": 19140 },141 {142 "epoch": 0.35714285714285715,143 "grad_norm": 0.0,144 "learning_rate": 2.1428571428571427e-06,145 "loss": 6.4814,146 "step": 20147 },148 {149 "epoch": 0.375,150 "grad_norm": 0.0,151 "learning_rate": 2.1428571428571427e-06,152 "loss": 6.2671,153 "step": 21154 },155 {156 "epoch": 0.39285714285714285,157 "grad_norm": 0.0,158 "learning_rate": 2.1428571428571427e-06,159 "loss": 6.1455,160 "step": 22161 },162 {163 "epoch": 0.4107142857142857,164 "grad_norm": 0.0,165 "learning_rate": 2.1428571428571427e-06,166 "loss": 6.1328,167 "step": 23168 },169 {170 "epoch": 0.42857142857142855,171 "grad_norm": 230.8024139404297,172 "learning_rate": 2.8571428571428573e-06,173 "loss": 6.2754,174 "step": 24175 },176 {177 "epoch": 0.44642857142857145,178 "grad_norm": 230.8024139404297,179 "learning_rate": 3.5714285714285714e-06,180 "loss": 4.6094,181 "step": 25182 },183 {184 "epoch": 0.4642857142857143,185 "grad_norm": 230.8024139404297,186 "learning_rate": 4.2857142857142855e-06,187 "loss": 4.4473,188 "step": 26189 },190 {191 "epoch": 0.48214285714285715,192 "grad_norm": 230.8024139404297,193 "learning_rate": 4.9999999999999996e-06,194 "loss": 4.6074,195 "step": 27196 },197 {198 "epoch": 0.5,199 "grad_norm": 104.01466369628906,200 "learning_rate": 5.7142857142857145e-06,201 "loss": 4.8125,202 "step": 28203 },204 {205 "epoch": 0.5178571428571429,206 "grad_norm": 104.01466369628906,207 "learning_rate": 6.428571428571429e-06,208 "loss": 3.7014,209 "step": 29210 },211 {212 "epoch": 0.5357142857142857,213 "grad_norm": 104.01466369628906,214 "learning_rate": 7.142857142857143e-06,215 "loss": 3.8691,216 "step": 30217 },218 {219 "epoch": 0.5535714285714286,220 "grad_norm": 104.01466369628906,221 "learning_rate": 7.857142857142858e-06,222 "loss": 3.6411,223 "step": 31224 },225 {226 "epoch": 0.5714285714285714,227 "grad_norm": 38.60957336425781,228 "learning_rate": 8.571428571428571e-06,229 "loss": 3.7668,230 "step": 32231 },232 {233 "epoch": 0.5892857142857143,234 "grad_norm": 38.60957336425781,235 "learning_rate": 9.285714285714286e-06,236 "loss": 3.115,237 "step": 33238 },239 {240 "epoch": 0.6071428571428571,241 "grad_norm": 38.60957336425781,242 "learning_rate": 9.999999999999999e-06,243 "loss": 3.1592,244 "step": 34245 },246 {247 "epoch": 0.625,248 "grad_norm": 38.60957336425781,249 "learning_rate": 1.0714285714285714e-05,250 "loss": 3.2053,251 "step": 35252 },253 {254 "epoch": 0.6428571428571429,255 "grad_norm": 29.317277908325195,256 "learning_rate": 1.1428571428571429e-05,257 "loss": 3.1006,258 "step": 36259 },260 {261 "epoch": 0.6607142857142857,262 "grad_norm": 29.317277908325195,263 "learning_rate": 1.2142857142857144e-05,264 "loss": 2.7161,265 "step": 37266 },267 {268 "epoch": 0.6785714285714286,269 "grad_norm": 29.317277908325195,270 "learning_rate": 1.2857142857142857e-05,271 "loss": 2.6982,272 "step": 38273 },274 {275 "epoch": 0.6964285714285714,276 "grad_norm": 29.317277908325195,277 "learning_rate": 1.3571428571428572e-05,278 "loss": 2.6333,279 "step": 39280 },281 {282 "epoch": 0.7142857142857143,283 "grad_norm": 24.417295455932617,284 "learning_rate": 1.4285714285714285e-05,285 "loss": 2.7019,286 "step": 40287 },288 {289 "epoch": 0.7321428571428571,290 "grad_norm": 24.417295455932617,291 "learning_rate": 1.5e-05,292 "loss": 2.3599,293 "step": 41294 },295 {296 "epoch": 0.75,297 "grad_norm": 24.417295455932617,298 "learning_rate": 1.5714285714285715e-05,299 "loss": 2.3931,300 "step": 42301 },302 {303 "epoch": 0.7678571428571429,304 "grad_norm": 24.417295455932617,305 "learning_rate": 1.6428571428571432e-05,306 "loss": 2.2354,307 "step": 43308 },309 {310 "epoch": 0.7857142857142857,311 "grad_norm": 22.96832847595215,312 "learning_rate": 1.7142857142857142e-05,313 "loss": 2.5569,314 "step": 44315 },316 {317 "epoch": 0.8035714285714286,318 "grad_norm": 22.96832847595215,319 "learning_rate": 1.785714285714286e-05,320 "loss": 2.1937,321 "step": 45322 },323 {324 "epoch": 0.8214285714285714,325 "grad_norm": 22.96832847595215,326 "learning_rate": 1.8571428571428572e-05,327 "loss": 2.199,328 "step": 46329 },330 {331 "epoch": 0.8392857142857143,332 "grad_norm": 22.96832847595215,333 "learning_rate": 1.928571428571429e-05,334 "loss": 2.2279,335 "step": 47336 },337 {338 "epoch": 0.8571428571428571,339 "grad_norm": 18.068286895751953,340 "learning_rate": 1.9999999999999998e-05,341 "loss": 2.2932,342 "step": 48343 },344 {345 "epoch": 0.875,346 "grad_norm": 18.068286895751953,347 "learning_rate": 2.0714285714285715e-05,348 "loss": 2.1881,349 "step": 49350 },351 {352 "epoch": 0.8928571428571429,353 "grad_norm": 18.068286895751953,354 "learning_rate": 2.1428571428571428e-05,355 "loss": 2.1971,356 "step": 50357 },358 {359 "epoch": 0.9107142857142857,360 "grad_norm": 18.068286895751953,361 "learning_rate": 2.2142857142857145e-05,362 "loss": 2.0692,363 "step": 51364 },365 {366 "epoch": 0.9285714285714286,367 "grad_norm": 19.364484786987305,368 "learning_rate": 2.2857142857142858e-05,369 "loss": 2.1223,370 "step": 52371 },372 {373 "epoch": 0.9464285714285714,374 "grad_norm": 19.364484786987305,375 "learning_rate": 2.357142857142857e-05,376 "loss": 2.0865,377 "step": 53378 },379 {380 "epoch": 0.9642857142857143,381 "grad_norm": 19.364484786987305,382 "learning_rate": 2.4285714285714288e-05,383 "loss": 2.1046,384 "step": 54385 },386 {387 "epoch": 0.9821428571428571,388 "grad_norm": 19.364484786987305,389 "learning_rate": 2.5e-05,390 "loss": 2.0803,391 "step": 55392 },393 {394 "epoch": 1.0,395 "grad_norm": 15.066437721252441,396 "learning_rate": 2.5714285714285714e-05,397 "loss": 2.0692,398 "step": 56399 },400 {401 "epoch": 1.0178571428571428,402 "grad_norm": 15.066437721252441,403 "learning_rate": 2.6428571428571428e-05,404 "loss": 2.0048,405 "step": 57406 },407 {408 "epoch": 1.0357142857142858,409 "grad_norm": 15.066437721252441,410 "learning_rate": 2.7142857142857144e-05,411 "loss": 1.9008,412 "step": 58413 },414 {415 "epoch": 1.0535714285714286,416 "grad_norm": 15.066437721252441,417 "learning_rate": 2.7857142857142858e-05,418 "loss": 1.8903,419 "step": 59420 },421 {422 "epoch": 1.0714285714285714,423 "grad_norm": 13.632275581359863,424 "learning_rate": 2.857142857142857e-05,425 "loss": 1.9506,426 "step": 60427 },428 {429 "epoch": 1.0892857142857142,430 "grad_norm": 13.632275581359863,431 "learning_rate": 2.9285714285714284e-05,432 "loss": 1.7871,433 "step": 61434 },435 {436 "epoch": 1.1071428571428572,437 "grad_norm": 13.632275581359863,438 "learning_rate": 3e-05,439 "loss": 1.7432,440 "step": 62441 },442 {443 "epoch": 1.125,444 "grad_norm": 13.632275581359863,445 "learning_rate": 2.9962406015037596e-05,446 "loss": 1.7252,447 "step": 63448 },449 {450 "epoch": 1.1428571428571428,451 "grad_norm": 14.228506088256836,452 "learning_rate": 2.9924812030075187e-05,453 "loss": 1.8796,454 "step": 64455 },456 {457 "epoch": 1.1607142857142858,458 "grad_norm": 14.228506088256836,459 "learning_rate": 2.988721804511278e-05,460 "loss": 1.8615,461 "step": 65462 },463 {464 "epoch": 1.1785714285714286,465 "grad_norm": 14.228506088256836,466 "learning_rate": 2.9849624060150376e-05,467 "loss": 1.7247,468 "step": 66469 },470 {471 "epoch": 1.1964285714285714,472 "grad_norm": 14.228506088256836,473 "learning_rate": 2.981203007518797e-05,474 "loss": 1.7633,475 "step": 67476 },477 {478 "epoch": 1.2142857142857142,479 "grad_norm": 15.551071166992188,480 "learning_rate": 2.9774436090225562e-05,481 "loss": 1.873,482 "step": 68483 },484 {485 "epoch": 1.2321428571428572,486 "grad_norm": 15.551071166992188,487 "learning_rate": 2.9736842105263157e-05,488 "loss": 1.8282,489 "step": 69490 },491 {492 "epoch": 1.25,493 "grad_norm": 15.551071166992188,494 "learning_rate": 2.9699248120300752e-05,495 "loss": 1.6896,496 "step": 70497 },498 {499 "epoch": 1.2678571428571428,500 "grad_norm": 15.551071166992188,501 "learning_rate": 2.9661654135338347e-05,502 "loss": 1.7615,503 "step": 71504 },505 {506 "epoch": 1.2857142857142856,507 "grad_norm": 14.377410888671875,508 "learning_rate": 2.9624060150375938e-05,509 "loss": 1.7761,510 "step": 72511 },512 {513 "epoch": 1.3035714285714286,514 "grad_norm": 14.377410888671875,515 "learning_rate": 2.9586466165413533e-05,516 "loss": 1.7222,517 "step": 73518 },519 {520 "epoch": 1.3214285714285714,521 "grad_norm": 14.377410888671875,522 "learning_rate": 2.9548872180451128e-05,523 "loss": 1.8105,524 "step": 74525 },526 {527 "epoch": 1.3392857142857144,528 "grad_norm": 14.377410888671875,529 "learning_rate": 2.9511278195488722e-05,530 "loss": 1.7357,531 "step": 75532 },533 {534 "epoch": 1.3571428571428572,535 "grad_norm": 15.64229965209961,536 "learning_rate": 2.9473684210526314e-05,537 "loss": 1.6945,538 "step": 76539 },540 {541 "epoch": 1.375,542 "grad_norm": 15.64229965209961,543 "learning_rate": 2.943609022556391e-05,544 "loss": 1.7681,545 "step": 77546 },547 {548 "epoch": 1.3928571428571428,549 "grad_norm": 15.64229965209961,550 "learning_rate": 2.9398496240601503e-05,551 "loss": 1.6145,552 "step": 78553 },554 {555 "epoch": 1.4107142857142856,556 "grad_norm": 15.64229965209961,557 "learning_rate": 2.9360902255639098e-05,558 "loss": 1.7286,559 "step": 79560 },561 {562 "epoch": 1.4285714285714286,563 "grad_norm": 15.191073417663574,564 "learning_rate": 2.932330827067669e-05,565 "loss": 1.5326,566 "step": 80567 },568 {569 "epoch": 1.4464285714285714,570 "grad_norm": 15.191073417663574,571 "learning_rate": 2.9285714285714284e-05,572 "loss": 1.7954,573 "step": 81574 },575 {576 "epoch": 1.4642857142857144,577 "grad_norm": 15.191073417663574,578 "learning_rate": 2.924812030075188e-05,579 "loss": 1.6355,580 "step": 82581 },582 {583 "epoch": 1.4821428571428572,584 "grad_norm": 15.191073417663574,585 "learning_rate": 2.9210526315789474e-05,586 "loss": 1.666,587 "step": 83588 },589 {590 "epoch": 1.5,591 "grad_norm": 15.714180946350098,592 "learning_rate": 2.917293233082707e-05,593 "loss": 1.5962,594 "step": 84595 },596 {597 "epoch": 1.5178571428571428,598 "grad_norm": 15.714180946350098,599 "learning_rate": 2.9135338345864663e-05,600 "loss": 1.7747,601 "step": 85602 },603 {604 "epoch": 1.5357142857142856,605 "grad_norm": 15.714180946350098,606 "learning_rate": 2.9097744360902258e-05,607 "loss": 1.6663,608 "step": 86609 },610 {611 "epoch": 1.5535714285714286,612 "grad_norm": 15.714180946350098,613 "learning_rate": 2.9060150375939853e-05,614 "loss": 1.7379,615 "step": 87616 },617 {618 "epoch": 1.5714285714285714,619 "grad_norm": 14.792555809020996,620 "learning_rate": 2.9022556390977444e-05,621 "loss": 1.6414,622 "step": 88623 },624 {625 "epoch": 1.5892857142857144,626 "grad_norm": 14.792555809020996,627 "learning_rate": 2.898496240601504e-05,628 "loss": 1.6715,629 "step": 89630 },631 {632 "epoch": 1.6071428571428572,633 "grad_norm": 14.792555809020996,634 "learning_rate": 2.8947368421052634e-05,635 "loss": 1.7252,636 "step": 90637 },638 {639 "epoch": 1.625,640 "grad_norm": 14.792555809020996,641 "learning_rate": 2.8909774436090228e-05,642 "loss": 1.4945,643 "step": 91644 },645 {646 "epoch": 1.6428571428571428,647 "grad_norm": 14.602505683898926,648 "learning_rate": 2.887218045112782e-05,649 "loss": 1.819,650 "step": 92651 },652 {653 "epoch": 1.6607142857142856,654 "grad_norm": 14.602505683898926,655 "learning_rate": 2.8834586466165414e-05,656 "loss": 1.5228,657 "step": 93658 },659 {660 "epoch": 1.6785714285714286,661 "grad_norm": 14.602505683898926,662 "learning_rate": 2.879699248120301e-05,663 "loss": 1.6512,664 "step": 94665 },666 {667 "epoch": 1.6964285714285714,668 "grad_norm": 14.602505683898926,669 "learning_rate": 2.8759398496240604e-05,670 "loss": 1.6498,671 "step": 95672 },673 {674 "epoch": 1.7142857142857144,675 "grad_norm": 14.357579231262207,676 "learning_rate": 2.8721804511278195e-05,677 "loss": 1.7876,678 "step": 96679 },680 {681 "epoch": 1.7321428571428572,682 "grad_norm": 14.357579231262207,683 "learning_rate": 2.868421052631579e-05,684 "loss": 1.6372,685 "step": 97686 },687 {688 "epoch": 1.75,689 "grad_norm": 14.357579231262207,690 "learning_rate": 2.8646616541353385e-05,691 "loss": 1.5226,692 "step": 98693 },694 {695 "epoch": 1.7678571428571428,696 "grad_norm": 14.357579231262207,697 "learning_rate": 2.860902255639098e-05,698 "loss": 1.6523,699 "step": 99700 },701 {702 "epoch": 1.7857142857142856,703 "grad_norm": 12.28958797454834,704 "learning_rate": 2.857142857142857e-05,705 "loss": 1.4866,706 "step": 100707 },708 {709 "epoch": 1.8035714285714286,710 "grad_norm": 12.28958797454834,711 "learning_rate": 2.8533834586466166e-05,712 "loss": 1.4967,713 "step": 101714 },715 {716 "epoch": 1.8214285714285714,717 "grad_norm": 12.28958797454834,718 "learning_rate": 2.849624060150376e-05,719 "loss": 1.6534,720 "step": 102721 },722 {723 "epoch": 1.8392857142857144,724 "grad_norm": 12.28958797454834,725 "learning_rate": 2.8458646616541355e-05,726 "loss": 1.4913,727 "step": 103728 },729 {730 "epoch": 1.8571428571428572,731 "grad_norm": 11.686190605163574,732 "learning_rate": 2.8421052631578946e-05,733 "loss": 1.5909,734 "step": 104735 },736 {737 "epoch": 1.875,738 "grad_norm": 11.686190605163574,739 "learning_rate": 2.838345864661654e-05,740 "loss": 1.6018,741 "step": 105742 },743 {744 "epoch": 1.8928571428571428,745 "grad_norm": 11.686190605163574,746 "learning_rate": 2.8345864661654136e-05,747 "loss": 1.4518,748 "step": 106749 },750 {751 "epoch": 1.9107142857142856,752 "grad_norm": 11.686190605163574,753 "learning_rate": 2.830827067669173e-05,754 "loss": 1.7177,755 "step": 107756 },757 {758 "epoch": 1.9285714285714286,759 "grad_norm": 13.209571838378906,760 "learning_rate": 2.8270676691729322e-05,761 "loss": 1.5298,762 "step": 108763 },764 {765 "epoch": 1.9464285714285714,766 "grad_norm": 13.209571838378906,767 "learning_rate": 2.8233082706766917e-05,768 "loss": 1.5328,769 "step": 109770 },771 {772 "epoch": 1.9642857142857144,773 "grad_norm": 13.209571838378906,774 "learning_rate": 2.819548872180451e-05,775 "loss": 1.5262,776 "step": 110777 },778 {779 "epoch": 1.9821428571428572,780 "grad_norm": 13.209571838378906,781 "learning_rate": 2.8157894736842106e-05,782 "loss": 1.5762,783 "step": 111784 },785 {786 "epoch": 2.0,787 "grad_norm": 10.644370079040527,788 "learning_rate": 2.8120300751879698e-05,789 "loss": 1.4681,790 "step": 112791 },792 {793 "epoch": 2.017857142857143,794 "grad_norm": 10.644370079040527,795 "learning_rate": 2.8082706766917292e-05,796 "loss": 1.3092,797 "step": 113798 },799 {800 "epoch": 2.0357142857142856,801 "grad_norm": 10.644370079040527,802 "learning_rate": 2.8045112781954887e-05,803 "loss": 1.3781,804 "step": 114805 },806 {807 "epoch": 2.0535714285714284,808 "grad_norm": 10.644370079040527,809 "learning_rate": 2.8007518796992482e-05,810 "loss": 1.328,811 "step": 115812 },813 {814 "epoch": 2.0714285714285716,815 "grad_norm": 10.72980785369873,816 "learning_rate": 2.7969924812030073e-05,817 "loss": 1.4338,818 "step": 116819 },820 {821 "epoch": 2.0892857142857144,822 "grad_norm": 10.72980785369873,823 "learning_rate": 2.7932330827067668e-05,824 "loss": 1.2646,825 "step": 117826 },827 {828 "epoch": 2.107142857142857,829 "grad_norm": 10.72980785369873,830 "learning_rate": 2.7894736842105263e-05,831 "loss": 1.4899,832 "step": 118833 },834 {835 "epoch": 2.125,836 "grad_norm": 10.72980785369873,837 "learning_rate": 2.7857142857142858e-05,838 "loss": 1.2913,839 "step": 119840 },841 {842 "epoch": 2.142857142857143,843 "grad_norm": 12.673820495605469,844 "learning_rate": 2.781954887218045e-05,845 "loss": 1.3636,846 "step": 120847 },848 {849 "epoch": 2.1607142857142856,850 "grad_norm": 12.673820495605469,851 "learning_rate": 2.7781954887218044e-05,852 "loss": 1.272,853 "step": 121854 },855 {856 "epoch": 2.1785714285714284,857 "grad_norm": 12.673820495605469,858 "learning_rate": 2.774436090225564e-05,859 "loss": 1.2552,860 "step": 122861 },862 {863 "epoch": 2.1964285714285716,864 "grad_norm": 12.673820495605469,865 "learning_rate": 2.7706766917293233e-05,866 "loss": 1.1824,867 "step": 123868 },869 {870 "epoch": 2.2142857142857144,871 "grad_norm": 11.79961109161377,872 "learning_rate": 2.7669172932330825e-05,873 "loss": 1.276,874 "step": 124875 },876 {877 "epoch": 2.232142857142857,878 "grad_norm": 11.79961109161377,879 "learning_rate": 2.7631578947368423e-05,880 "loss": 1.2714,881 "step": 125882 },883 {884 "epoch": 2.25,885 "grad_norm": 11.79961109161377,886 "learning_rate": 2.7593984962406017e-05,887 "loss": 1.288,888 "step": 126889 },890 {891 "epoch": 2.267857142857143,892 "grad_norm": 11.79961109161377,893 "learning_rate": 2.7556390977443612e-05,894 "loss": 1.3359,895 "step": 127896 },897 {898 "epoch": 2.2857142857142856,899 "grad_norm": 14.634297370910645,900 "learning_rate": 2.7518796992481204e-05,901 "loss": 1.2911,902 "step": 128903 },904 {905 "epoch": 2.3035714285714284,906 "grad_norm": 14.634297370910645,907 "learning_rate": 2.74812030075188e-05,908 "loss": 1.1898,909 "step": 129910 },911 {912 "epoch": 2.3214285714285716,913 "grad_norm": 14.634297370910645,914 "learning_rate": 2.7443609022556393e-05,915 "loss": 1.2327,916 "step": 130917 },918 {919 "epoch": 2.3392857142857144,920 "grad_norm": 14.634297370910645,921 "learning_rate": 2.7406015037593988e-05,922 "loss": 1.405,923 "step": 131924 },925 {926 "epoch": 2.357142857142857,927 "grad_norm": 16.606494903564453,928 "learning_rate": 2.736842105263158e-05,929 "loss": 1.2003,930 "step": 132931 },932 {933 "epoch": 2.375,934 "grad_norm": 16.606494903564453,935 "learning_rate": 2.7330827067669174e-05,936 "loss": 1.4715,937 "step": 133938 },939 {940 "epoch": 2.392857142857143,941 "grad_norm": 16.606494903564453,942 "learning_rate": 2.729323308270677e-05,943 "loss": 1.3771,944 "step": 134945 },946 {947 "epoch": 2.4107142857142856,948 "grad_norm": 16.606494903564453,949 "learning_rate": 2.7255639097744363e-05,950 "loss": 1.165,951 "step": 135952 },953 {954 "epoch": 2.4285714285714284,955 "grad_norm": 15.750870704650879,956 "learning_rate": 2.7218045112781955e-05,957 "loss": 1.3275,958 "step": 136959 },960 {961 "epoch": 2.4464285714285716,962 "grad_norm": 15.750870704650879,963 "learning_rate": 2.718045112781955e-05,964 "loss": 1.3169,965 "step": 137966 },967 {968 "epoch": 2.4642857142857144,969 "grad_norm": 15.750870704650879,970 "learning_rate": 2.7142857142857144e-05,971 "loss": 1.2426,972 "step": 138973 },974 {975 "epoch": 2.482142857142857,976 "grad_norm": 15.750870704650879,977 "learning_rate": 2.710526315789474e-05,978 "loss": 1.2549,979 "step": 139980 },981 {982 "epoch": 2.5,983 "grad_norm": 16.149423599243164,984 "learning_rate": 2.706766917293233e-05,985 "loss": 1.3336,986 "step": 140987 },988 {989 "epoch": 2.517857142857143,990 "grad_norm": 16.149423599243164,991 "learning_rate": 2.7030075187969925e-05,992 "loss": 1.2404,993 "step": 141994 },995 {996 "epoch": 2.5357142857142856,997 "grad_norm": 16.149423599243164,998 "learning_rate": 2.699248120300752e-05,999 "loss": 1.2969,1000 "step": 1421001 },1002 {1003 "epoch": 2.553571428571429,1004 "grad_norm": 16.149423599243164,1005 "learning_rate": 2.6954887218045115e-05,1006 "loss": 1.1973,1007 "step": 1431008 },1009 {1010 "epoch": 2.571428571428571,1011 "grad_norm": 13.522272109985352,1012 "learning_rate": 2.6917293233082706e-05,1013 "loss": 1.1382,1014 "step": 1441015 },1016 {1017 "epoch": 2.5892857142857144,1018 "grad_norm": 13.522272109985352,1019 "learning_rate": 2.68796992481203e-05,1020 "loss": 1.2349,1021 "step": 1451022 },1023 {1024 "epoch": 2.607142857142857,1025 "grad_norm": 13.522272109985352,1026 "learning_rate": 2.6842105263157896e-05,1027 "loss": 1.1815,1028 "step": 1461029 },1030 {1031 "epoch": 2.625,1032 "grad_norm": 13.522272109985352,1033 "learning_rate": 2.680451127819549e-05,1034 "loss": 1.0928,1035 "step": 1471036 },1037 {1038 "epoch": 2.642857142857143,1039 "grad_norm": 11.987059593200684,1040 "learning_rate": 2.6766917293233082e-05,1041 "loss": 1.3141,1042 "step": 1481043 },1044 {1045 "epoch": 2.6607142857142856,1046 "grad_norm": 11.987059593200684,1047 "learning_rate": 2.6729323308270676e-05,1048 "loss": 1.2795,1049 "step": 1491050 },1051 {1052 "epoch": 2.678571428571429,1053 "grad_norm": 11.987059593200684,1054 "learning_rate": 2.669172932330827e-05,1055 "loss": 1.0408,1056 "step": 1501057 },1058 {1059 "epoch": 2.696428571428571,1060 "grad_norm": 11.987059593200684,1061 "learning_rate": 2.6654135338345866e-05,1062 "loss": 1.2148,1063 "step": 1511064 },1065 {1066 "epoch": 2.7142857142857144,1067 "grad_norm": 11.788473129272461,1068 "learning_rate": 2.6616541353383457e-05,1069 "loss": 1.2111,1070 "step": 1521071 },1072 {1073 "epoch": 2.732142857142857,1074 "grad_norm": 11.788473129272461,1075 "learning_rate": 2.6578947368421052e-05,1076 "loss": 1.2054,1077 "step": 1531078 },1079 {1080 "epoch": 2.75,1081 "grad_norm": 11.788473129272461,1082 "learning_rate": 2.6541353383458647e-05,1083 "loss": 1.2268,1084 "step": 1541085 },1086 {1087 "epoch": 2.767857142857143,1088 "grad_norm": 11.788473129272461,1089 "learning_rate": 2.650375939849624e-05,1090 "loss": 1.1021,1091 "step": 1551092 },1093 {1094 "epoch": 2.7857142857142856,1095 "grad_norm": 11.825960159301758,1096 "learning_rate": 2.6466165413533833e-05,1097 "loss": 1.2378,1098 "step": 1561099 },1100 {1101 "epoch": 2.803571428571429,1102 "grad_norm": 11.825960159301758,1103 "learning_rate": 2.6428571428571428e-05,1104 "loss": 1.097,1105 "step": 1571106 },1107 {1108 "epoch": 2.821428571428571,1109 "grad_norm": 11.825960159301758,1110 "learning_rate": 2.6390977443609022e-05,1111 "loss": 1.2128,1112 "step": 1581113 },1114 {1115 "epoch": 2.8392857142857144,1116 "grad_norm": 11.825960159301758,1117 "learning_rate": 2.6353383458646617e-05,1118 "loss": 1.1729,1119 "step": 1591120 },1121 {1122 "epoch": 2.857142857142857,1123 "grad_norm": 12.994108200073242,1124 "learning_rate": 2.631578947368421e-05,1125 "loss": 1.3422,1126 "step": 1601127 },1128 {1129 "epoch": 2.875,1130 "grad_norm": 12.994108200073242,1131 "learning_rate": 2.6278195488721803e-05,1132 "loss": 1.1797,1133 "step": 1611134 },1135 {1136 "epoch": 2.892857142857143,1137 "grad_norm": 12.994108200073242,1138 "learning_rate": 2.6240601503759398e-05,1139 "loss": 1.205,1140 "step": 1621141 },1142 {1143 "epoch": 2.9107142857142856,1144 "grad_norm": 12.994108200073242,1145 "learning_rate": 2.6203007518796993e-05,1146 "loss": 1.1354,1147 "step": 1631148 },1149 {1150 "epoch": 2.928571428571429,1151 "grad_norm": 13.220701217651367,1152 "learning_rate": 2.6165413533834584e-05,1153 "loss": 1.1998,1154 "step": 1641155 },1156 {1157 "epoch": 2.946428571428571,1158 "grad_norm": 13.220701217651367,1159 "learning_rate": 2.612781954887218e-05,1160 "loss": 1.0995,1161 "step": 1651162 },1163 {1164 "epoch": 2.9642857142857144,1165 "grad_norm": 13.220701217651367,1166 "learning_rate": 2.6090225563909774e-05,1167 "loss": 1.1673,1168 "step": 1661169 },1170 {1171 "epoch": 2.982142857142857,1172 "grad_norm": 13.220701217651367,1173 "learning_rate": 2.605263157894737e-05,1174 "loss": 1.0815,1175 "step": 1671176 },1177 {1178 "epoch": 3.0,1179 "grad_norm": 12.115779876708984,1180 "learning_rate": 2.6015037593984963e-05,1181 "loss": 1.1843,1182 "step": 1681183 },1184 {1185 "epoch": 3.017857142857143,1186 "grad_norm": 12.115779876708984,1187 "learning_rate": 2.5977443609022558e-05,1188 "loss": 0.926,1189 "step": 1691190 },1191 {1192 "epoch": 3.0357142857142856,1193 "grad_norm": 12.115779876708984,1194 "learning_rate": 2.5939849624060153e-05,1195 "loss": 1.0279,1196 "step": 1701197 },1198 {1199 "epoch": 3.0535714285714284,1200 "grad_norm": 12.115779876708984,