FreedomIntelligence/EchoX-8B
1076
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 1.0,5 "eval_steps": 500,6 "global_step": 420,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.002380952380952381,13 "grad_norm": 0.0,14 "learning_rate": 0,15 "loss": 0.5013,16 "step": 117 },18 {19 "epoch": 0.004761904761904762,20 "grad_norm": 1.2982189655303955,21 "learning_rate": 0.0,22 "loss": 0.4693,23 "step": 224 },25 {26 "epoch": 0.007142857142857143,27 "grad_norm": 1.3160841464996338,28 "learning_rate": 1.2920296742201791e-05,29 "loss": 0.4462,30 "step": 331 },32 {33 "epoch": 0.009523809523809525,34 "grad_norm": 1.3160841464996338,35 "learning_rate": 1.2920296742201791e-05,36 "loss": 0.8593,37 "step": 438 },39 {40 "epoch": 0.011904761904761904,41 "grad_norm": 1.3160841464996338,42 "learning_rate": 1.2920296742201791e-05,43 "loss": 0.8663,44 "step": 545 },46 {47 "epoch": 0.014285714285714285,48 "grad_norm": 1.0395259857177734,49 "learning_rate": 2.0478185834579563e-05,50 "loss": 0.5107,51 "step": 652 },53 {54 "epoch": 0.016666666666666666,55 "grad_norm": 1.0972439050674438,56 "learning_rate": 2.5840593484403582e-05,57 "loss": 0.5832,58 "step": 759 },60 {61 "epoch": 0.01904761904761905,62 "grad_norm": 1.2451457977294922,63 "learning_rate": 3e-05,64 "loss": 0.4994,65 "step": 866 },67 {68 "epoch": 0.02142857142857143,69 "grad_norm": 1.5299328565597534,70 "learning_rate": 3e-05,71 "loss": 0.5632,72 "step": 973 },74 {75 "epoch": 0.023809523809523808,76 "grad_norm": 1.456752061843872,77 "learning_rate": 3e-05,78 "loss": 0.5448,79 "step": 1080 },81 {82 "epoch": 0.02619047619047619,83 "grad_norm": 0.7797374725341797,84 "learning_rate": 3e-05,85 "loss": 0.4222,86 "step": 1187 },88 {89 "epoch": 0.02857142857142857,90 "grad_norm": 0.992181658744812,91 "learning_rate": 3e-05,92 "loss": 0.5173,93 "step": 1294 },95 {96 "epoch": 0.030952380952380953,97 "grad_norm": 1.0963839292526245,98 "learning_rate": 3e-05,99 "loss": 0.4048,100 "step": 13101 },102 {103 "epoch": 0.03333333333333333,104 "grad_norm": 1.3775476217269897,105 "learning_rate": 3e-05,106 "loss": 0.4774,107 "step": 14108 },109 {110 "epoch": 0.03571428571428571,111 "grad_norm": 1.551168441772461,112 "learning_rate": 3e-05,113 "loss": 0.5603,114 "step": 15115 },116 {117 "epoch": 0.0380952380952381,118 "grad_norm": 1.189092993736267,119 "learning_rate": 3e-05,120 "loss": 0.4756,121 "step": 16122 },123 {124 "epoch": 0.04047619047619048,125 "grad_norm": 1.0813432931900024,126 "learning_rate": 3e-05,127 "loss": 0.4955,128 "step": 17129 },130 {131 "epoch": 0.04285714285714286,132 "grad_norm": 1.224169373512268,133 "learning_rate": 3e-05,134 "loss": 0.4906,135 "step": 18136 },137 {138 "epoch": 0.04523809523809524,139 "grad_norm": 0.7351661324501038,140 "learning_rate": 3e-05,141 "loss": 0.4717,142 "step": 19143 },144 {145 "epoch": 0.047619047619047616,146 "grad_norm": 0.8378927707672119,147 "learning_rate": 3e-05,148 "loss": 0.4436,149 "step": 20150 },151 {152 "epoch": 0.05,153 "grad_norm": 1.2906426191329956,154 "learning_rate": 3e-05,155 "loss": 0.4294,156 "step": 21157 },158 {159 "epoch": 0.05238095238095238,160 "grad_norm": 0.9292688369750977,161 "learning_rate": 3e-05,162 "loss": 0.4252,163 "step": 22164 },165 {166 "epoch": 0.05476190476190476,167 "grad_norm": 0.757605254650116,168 "learning_rate": 3e-05,169 "loss": 0.4078,170 "step": 23171 },172 {173 "epoch": 0.05714285714285714,174 "grad_norm": 0.8978239893913269,175 "learning_rate": 3e-05,176 "loss": 0.4561,177 "step": 24178 },179 {180 "epoch": 0.05952380952380952,181 "grad_norm": 0.7445272207260132,182 "learning_rate": 3e-05,183 "loss": 0.4007,184 "step": 25185 },186 {187 "epoch": 0.06190476190476191,188 "grad_norm": 0.755946934223175,189 "learning_rate": 3e-05,190 "loss": 0.3974,191 "step": 26192 },193 {194 "epoch": 0.06428571428571428,195 "grad_norm": 1.2127957344055176,196 "learning_rate": 3e-05,197 "loss": 0.5496,198 "step": 27199 },200 {201 "epoch": 0.06666666666666667,202 "grad_norm": 1.2571460008621216,203 "learning_rate": 3e-05,204 "loss": 0.4526,205 "step": 28206 },207 {208 "epoch": 0.06904761904761905,209 "grad_norm": 0.9187604784965515,210 "learning_rate": 3e-05,211 "loss": 0.4042,212 "step": 29213 },214 {215 "epoch": 0.07142857142857142,216 "grad_norm": 0.990939736366272,217 "learning_rate": 3e-05,218 "loss": 0.4855,219 "step": 30220 },221 {222 "epoch": 0.07380952380952381,223 "grad_norm": 1.0081547498703003,224 "learning_rate": 3e-05,225 "loss": 0.5543,226 "step": 31227 },228 {229 "epoch": 0.0761904761904762,230 "grad_norm": 0.696738600730896,231 "learning_rate": 3e-05,232 "loss": 0.4036,233 "step": 32234 },235 {236 "epoch": 0.07857142857142857,237 "grad_norm": 1.7002297639846802,238 "learning_rate": 3e-05,239 "loss": 0.4686,240 "step": 33241 },242 {243 "epoch": 0.08095238095238096,244 "grad_norm": 0.8276028633117676,245 "learning_rate": 3e-05,246 "loss": 0.4009,247 "step": 34248 },249 {250 "epoch": 0.08333333333333333,251 "grad_norm": 1.270995020866394,252 "learning_rate": 3e-05,253 "loss": 0.4926,254 "step": 35255 },256 {257 "epoch": 0.08571428571428572,258 "grad_norm": 1.0746862888336182,259 "learning_rate": 3e-05,260 "loss": 0.4982,261 "step": 36262 },263 {264 "epoch": 0.0880952380952381,265 "grad_norm": 1.0116355419158936,266 "learning_rate": 3e-05,267 "loss": 0.3548,268 "step": 37269 },270 {271 "epoch": 0.09047619047619047,272 "grad_norm": 0.9556488394737244,273 "learning_rate": 3e-05,274 "loss": 0.4268,275 "step": 38276 },277 {278 "epoch": 0.09285714285714286,279 "grad_norm": 0.752404510974884,280 "learning_rate": 3e-05,281 "loss": 0.4496,282 "step": 39283 },284 {285 "epoch": 0.09523809523809523,286 "grad_norm": 0.7381091713905334,287 "learning_rate": 3e-05,288 "loss": 0.4412,289 "step": 40290 },291 {292 "epoch": 0.09761904761904762,293 "grad_norm": 1.2671267986297607,294 "learning_rate": 3e-05,295 "loss": 0.4382,296 "step": 41297 },298 {299 "epoch": 0.1,300 "grad_norm": 0.7863288521766663,301 "learning_rate": 3e-05,302 "loss": 0.4186,303 "step": 42304 },305 {306 "epoch": 0.10238095238095238,307 "grad_norm": 0.9142912030220032,308 "learning_rate": 3e-05,309 "loss": 0.442,310 "step": 43311 },312 {313 "epoch": 0.10476190476190476,314 "grad_norm": 0.9501491189002991,315 "learning_rate": 3e-05,316 "loss": 0.5339,317 "step": 44318 },319 {320 "epoch": 0.10714285714285714,321 "grad_norm": 0.888054609298706,322 "learning_rate": 3e-05,323 "loss": 0.4928,324 "step": 45325 },326 {327 "epoch": 0.10952380952380952,328 "grad_norm": 0.8860450983047485,329 "learning_rate": 3e-05,330 "loss": 0.4081,331 "step": 46332 },333 {334 "epoch": 0.11190476190476191,335 "grad_norm": 0.894538164138794,336 "learning_rate": 3e-05,337 "loss": 0.4213,338 "step": 47339 },340 {341 "epoch": 0.11428571428571428,342 "grad_norm": 1.657795786857605,343 "learning_rate": 3e-05,344 "loss": 0.4112,345 "step": 48346 },347 {348 "epoch": 0.11666666666666667,349 "grad_norm": 1.4137582778930664,350 "learning_rate": 3e-05,351 "loss": 0.5444,352 "step": 49353 },354 {355 "epoch": 0.11904761904761904,356 "grad_norm": 1.1915364265441895,357 "learning_rate": 3e-05,358 "loss": 0.4655,359 "step": 50360 },361 {362 "epoch": 0.12142857142857143,363 "grad_norm": 0.8001396059989929,364 "learning_rate": 3e-05,365 "loss": 0.4571,366 "step": 51367 },368 {369 "epoch": 0.12380952380952381,370 "grad_norm": 0.9784255623817444,371 "learning_rate": 3e-05,372 "loss": 0.4589,373 "step": 52374 },375 {376 "epoch": 0.1261904761904762,377 "grad_norm": 1.1923211812973022,378 "learning_rate": 3e-05,379 "loss": 0.5349,380 "step": 53381 },382 {383 "epoch": 0.12857142857142856,384 "grad_norm": 1.6921881437301636,385 "learning_rate": 3e-05,386 "loss": 0.5921,387 "step": 54388 },389 {390 "epoch": 0.13095238095238096,391 "grad_norm": 1.4049354791641235,392 "learning_rate": 3e-05,393 "loss": 0.3999,394 "step": 55395 },396 {397 "epoch": 0.13333333333333333,398 "grad_norm": 0.6025511026382446,399 "learning_rate": 3e-05,400 "loss": 0.3708,401 "step": 56402 },403 {404 "epoch": 0.1357142857142857,405 "grad_norm": 1.200055480003357,406 "learning_rate": 3e-05,407 "loss": 0.6888,408 "step": 57409 },410 {411 "epoch": 0.1380952380952381,412 "grad_norm": 0.9409858584403992,413 "learning_rate": 3e-05,414 "loss": 0.4722,415 "step": 58416 },417 {418 "epoch": 0.14047619047619048,419 "grad_norm": 1.47160804271698,420 "learning_rate": 3e-05,421 "loss": 1.0772,422 "step": 59423 },424 {425 "epoch": 0.14285714285714285,426 "grad_norm": 0.935752809047699,427 "learning_rate": 3e-05,428 "loss": 0.3725,429 "step": 60430 },431 {432 "epoch": 0.14523809523809525,433 "grad_norm": 0.8135111927986145,434 "learning_rate": 3e-05,435 "loss": 0.4312,436 "step": 61437 },438 {439 "epoch": 0.14761904761904762,440 "grad_norm": 1.1500678062438965,441 "learning_rate": 3e-05,442 "loss": 0.4317,443 "step": 62444 },445 {446 "epoch": 0.15,447 "grad_norm": 1.0388532876968384,448 "learning_rate": 3e-05,449 "loss": 0.5262,450 "step": 63451 },452 {453 "epoch": 0.1523809523809524,454 "grad_norm": 1.0478947162628174,455 "learning_rate": 3e-05,456 "loss": 0.5224,457 "step": 64458 },459 {460 "epoch": 0.15476190476190477,461 "grad_norm": 0.6370094418525696,462 "learning_rate": 3e-05,463 "loss": 0.4117,464 "step": 65465 },466 {467 "epoch": 0.15714285714285714,468 "grad_norm": 0.8117276430130005,469 "learning_rate": 3e-05,470 "loss": 0.4513,471 "step": 66472 },473 {474 "epoch": 0.1595238095238095,475 "grad_norm": 1.4209480285644531,476 "learning_rate": 3e-05,477 "loss": 0.419,478 "step": 67479 },480 {481 "epoch": 0.1619047619047619,482 "grad_norm": 1.3270151615142822,483 "learning_rate": 3e-05,484 "loss": 0.5064,485 "step": 68486 },487 {488 "epoch": 0.16428571428571428,489 "grad_norm": 1.4599213600158691,490 "learning_rate": 3e-05,491 "loss": 0.5342,492 "step": 69493 },494 {495 "epoch": 0.16666666666666666,496 "grad_norm": 0.7401596307754517,497 "learning_rate": 3e-05,498 "loss": 0.4609,499 "step": 70500 },501 {502 "epoch": 0.16904761904761906,503 "grad_norm": 0.6574556827545166,504 "learning_rate": 3e-05,505 "loss": 0.3689,506 "step": 71507 },508 {509 "epoch": 0.17142857142857143,510 "grad_norm": 1.6753238439559937,511 "learning_rate": 3e-05,512 "loss": 0.5226,513 "step": 72514 },515 {516 "epoch": 0.1738095238095238,517 "grad_norm": 0.8294124603271484,518 "learning_rate": 3e-05,519 "loss": 0.4176,520 "step": 73521 },522 {523 "epoch": 0.1761904761904762,524 "grad_norm": 0.9138219356536865,525 "learning_rate": 3e-05,526 "loss": 0.4123,527 "step": 74528 },529 {530 "epoch": 0.17857142857142858,531 "grad_norm": 0.8199627995491028,532 "learning_rate": 3e-05,533 "loss": 0.4374,534 "step": 75535 },536 {537 "epoch": 0.18095238095238095,538 "grad_norm": 0.7391550540924072,539 "learning_rate": 3e-05,540 "loss": 0.3825,541 "step": 76542 },543 {544 "epoch": 0.18333333333333332,545 "grad_norm": 0.729434609413147,546 "learning_rate": 3e-05,547 "loss": 0.4824,548 "step": 77549 },550 {551 "epoch": 0.18571428571428572,552 "grad_norm": 0.7266400456428528,553 "learning_rate": 3e-05,554 "loss": 0.3481,555 "step": 78556 },557 {558 "epoch": 0.1880952380952381,559 "grad_norm": 0.8050060272216797,560 "learning_rate": 3e-05,561 "loss": 0.4694,562 "step": 79563 },564 {565 "epoch": 0.19047619047619047,566 "grad_norm": 1.172167181968689,567 "learning_rate": 3e-05,568 "loss": 0.4291,569 "step": 80570 },571 {572 "epoch": 0.19285714285714287,573 "grad_norm": 1.1613800525665283,574 "learning_rate": 3e-05,575 "loss": 0.483,576 "step": 81577 },578 {579 "epoch": 0.19523809523809524,580 "grad_norm": 0.8675224184989929,581 "learning_rate": 3e-05,582 "loss": 0.4436,583 "step": 82584 },585 {586 "epoch": 0.1976190476190476,587 "grad_norm": 0.899101734161377,588 "learning_rate": 3e-05,589 "loss": 0.4858,590 "step": 83591 },592 {593 "epoch": 0.2,594 "grad_norm": 1.030885934829712,595 "learning_rate": 3e-05,596 "loss": 0.5346,597 "step": 84598 },599 {600 "epoch": 0.20238095238095238,601 "grad_norm": 0.9242229461669922,602 "learning_rate": 3e-05,603 "loss": 0.4349,604 "step": 85605 },606 {607 "epoch": 0.20476190476190476,608 "grad_norm": 0.7717217803001404,609 "learning_rate": 3e-05,610 "loss": 0.3759,611 "step": 86612 },613 {614 "epoch": 0.20714285714285716,615 "grad_norm": 1.2170741558074951,616 "learning_rate": 3e-05,617 "loss": 0.4937,618 "step": 87619 },620 {621 "epoch": 0.20952380952380953,622 "grad_norm": 1.2934021949768066,623 "learning_rate": 3e-05,624 "loss": 0.4993,625 "step": 88626 },627 {628 "epoch": 0.2119047619047619,629 "grad_norm": 1.3435097932815552,630 "learning_rate": 3e-05,631 "loss": 0.4603,632 "step": 89633 },634 {635 "epoch": 0.21428571428571427,636 "grad_norm": 0.8454081416130066,637 "learning_rate": 3e-05,638 "loss": 0.5203,639 "step": 90640 },641 {642 "epoch": 0.21666666666666667,643 "grad_norm": 0.8319071531295776,644 "learning_rate": 3e-05,645 "loss": 0.4997,646 "step": 91647 },648 {649 "epoch": 0.21904761904761905,650 "grad_norm": 0.6560430526733398,651 "learning_rate": 3e-05,652 "loss": 0.4763,653 "step": 92654 },655 {656 "epoch": 0.22142857142857142,657 "grad_norm": 2.126009941101074,658 "learning_rate": 3e-05,659 "loss": 0.7399,660 "step": 93661 },662 {663 "epoch": 0.22380952380952382,664 "grad_norm": 1.1273273229599,665 "learning_rate": 3e-05,666 "loss": 0.5303,667 "step": 94668 },669 {670 "epoch": 0.2261904761904762,671 "grad_norm": 0.9536347985267639,672 "learning_rate": 3e-05,673 "loss": 0.5147,674 "step": 95675 },676 {677 "epoch": 0.22857142857142856,678 "grad_norm": 0.6337579488754272,679 "learning_rate": 3e-05,680 "loss": 0.4474,681 "step": 96682 },683 {684 "epoch": 0.23095238095238096,685 "grad_norm": 0.6355674862861633,686 "learning_rate": 3e-05,687 "loss": 0.3958,688 "step": 97689 },690 {691 "epoch": 0.23333333333333334,692 "grad_norm": 0.9631844758987427,693 "learning_rate": 3e-05,694 "loss": 0.4463,695 "step": 98696 },697 {698 "epoch": 0.2357142857142857,699 "grad_norm": 0.7559183239936829,700 "learning_rate": 3e-05,701 "loss": 0.4952,702 "step": 99703 },704 {705 "epoch": 0.23809523809523808,706 "grad_norm": 0.926929771900177,707 "learning_rate": 3e-05,708 "loss": 0.5318,709 "step": 100710 },711 {712 "epoch": 0.24047619047619048,713 "grad_norm": 0.8441896438598633,714 "learning_rate": 3e-05,715 "loss": 0.4411,716 "step": 101717 },718 {719 "epoch": 0.24285714285714285,720 "grad_norm": 1.1027876138687134,721 "learning_rate": 3e-05,722 "loss": 0.5618,723 "step": 102724 },725 {726 "epoch": 0.24523809523809523,727 "grad_norm": 0.6018999814987183,728 "learning_rate": 3e-05,729 "loss": 0.4046,730 "step": 103731 },732 {733 "epoch": 0.24761904761904763,734 "grad_norm": 0.8065565228462219,735 "learning_rate": 3e-05,736 "loss": 0.4195,737 "step": 104738 },739 {740 "epoch": 0.25,741 "grad_norm": 0.6117183566093445,742 "learning_rate": 3e-05,743 "loss": 0.3556,744 "step": 105745 },746 {747 "epoch": 0.2523809523809524,748 "grad_norm": 1.0436320304870605,749 "learning_rate": 3e-05,750 "loss": 0.4699,751 "step": 106752 },753 {754 "epoch": 0.25476190476190474,755 "grad_norm": 1.1943013668060303,756 "learning_rate": 3e-05,757 "loss": 0.5636,758 "step": 107759 },760 {761 "epoch": 0.2571428571428571,762 "grad_norm": 0.8576936721801758,763 "learning_rate": 3e-05,764 "loss": 0.4178,765 "step": 108766 },767 {768 "epoch": 0.25952380952380955,769 "grad_norm": 0.7651050686836243,770 "learning_rate": 3e-05,771 "loss": 0.436,772 "step": 109773 },774 {775 "epoch": 0.2619047619047619,776 "grad_norm": 0.787661612033844,777 "learning_rate": 3e-05,778 "loss": 0.4378,779 "step": 110780 },781 {782 "epoch": 0.2642857142857143,783 "grad_norm": 0.961089551448822,784 "learning_rate": 3e-05,785 "loss": 0.4979,786 "step": 111787 },788 {789 "epoch": 0.26666666666666666,790 "grad_norm": 0.7426000833511353,791 "learning_rate": 3e-05,792 "loss": 0.4908,793 "step": 112794 },795 {796 "epoch": 0.26904761904761904,797 "grad_norm": 1.0738164186477661,798 "learning_rate": 3e-05,799 "loss": 0.5052,800 "step": 113801 },802 {803 "epoch": 0.2714285714285714,804 "grad_norm": 1.3592005968093872,805 "learning_rate": 3e-05,806 "loss": 0.5155,807 "step": 114808 },809 {810 "epoch": 0.27380952380952384,811 "grad_norm": 0.776147723197937,812 "learning_rate": 3e-05,813 "loss": 0.4199,814 "step": 115815 },816 {817 "epoch": 0.2761904761904762,818 "grad_norm": 1.184778094291687,819 "learning_rate": 3e-05,820 "loss": 0.4471,821 "step": 116822 },823 {824 "epoch": 0.2785714285714286,825 "grad_norm": 0.9415385127067566,826 "learning_rate": 3e-05,827 "loss": 0.4518,828 "step": 117829 },830 {831 "epoch": 0.28095238095238095,832 "grad_norm": 0.9082314372062683,833 "learning_rate": 3e-05,834 "loss": 0.4986,835 "step": 118836 },837 {838 "epoch": 0.2833333333333333,839 "grad_norm": 1.6528809070587158,840 "learning_rate": 3e-05,841 "loss": 0.6329,842 "step": 119843 },844 {845 "epoch": 0.2857142857142857,846 "grad_norm": 0.6157988905906677,847 "learning_rate": 3e-05,848 "loss": 0.346,849 "step": 120850 },851 {852 "epoch": 0.28809523809523807,853 "grad_norm": 1.335919737815857,854 "learning_rate": 3e-05,855 "loss": 0.5417,856 "step": 121857 },858 {859 "epoch": 0.2904761904761905,860 "grad_norm": 1.7414772510528564,861 "learning_rate": 3e-05,862 "loss": 0.513,863 "step": 122864 },865 {866 "epoch": 0.29285714285714287,867 "grad_norm": 1.0106985569000244,868 "learning_rate": 3e-05,869 "loss": 0.5358,870 "step": 123871 },872 {873 "epoch": 0.29523809523809524,874 "grad_norm": 0.8379469513893127,875 "learning_rate": 3e-05,876 "loss": 0.4548,877 "step": 124878 },879 {880 "epoch": 0.2976190476190476,881 "grad_norm": 0.8793790340423584,882 "learning_rate": 3e-05,883 "loss": 0.5191,884 "step": 125885 },886 {887 "epoch": 0.3,888 "grad_norm": 0.7612943053245544,889 "learning_rate": 3e-05,890 "loss": 0.4913,891 "step": 126892 },893 {894 "epoch": 0.30238095238095236,895 "grad_norm": 1.0233980417251587,896 "learning_rate": 3e-05,897 "loss": 0.5259,898 "step": 127899 },900 {901 "epoch": 0.3047619047619048,902 "grad_norm": 0.9049614071846008,903 "learning_rate": 3e-05,904 "loss": 0.4164,905 "step": 128906 },907 {908 "epoch": 0.30714285714285716,909 "grad_norm": 1.390436053276062,910 "learning_rate": 3e-05,911 "loss": 0.4505,912 "step": 129913 },914 {915 "epoch": 0.30952380952380953,916 "grad_norm": 0.705032229423523,917 "learning_rate": 3e-05,918 "loss": 0.4763,919 "step": 130920 },921 {922 "epoch": 0.3119047619047619,923 "grad_norm": 1.1658718585968018,924 "learning_rate": 3e-05,925 "loss": 0.4132,926 "step": 131927 },928 {929 "epoch": 0.3142857142857143,930 "grad_norm": 1.0997470617294312,931 "learning_rate": 3e-05,932 "loss": 0.4877,933 "step": 132934 },935 {936 "epoch": 0.31666666666666665,937 "grad_norm": 0.7365838885307312,938 "learning_rate": 3e-05,939 "loss": 0.3902,940 "step": 133941 },942 {943 "epoch": 0.319047619047619,944 "grad_norm": 1.0315278768539429,945 "learning_rate": 3e-05,946 "loss": 0.5093,947 "step": 134948 },949 {950 "epoch": 0.32142857142857145,951 "grad_norm": 0.8308622241020203,952 "learning_rate": 3e-05,953 "loss": 0.4309,954 "step": 135955 },956 {957 "epoch": 0.3238095238095238,958 "grad_norm": 0.8301631808280945,959 "learning_rate": 3e-05,960 "loss": 0.5057,961 "step": 136962 },963 {964 "epoch": 0.3261904761904762,965 "grad_norm": 0.6643893122673035,966 "learning_rate": 3e-05,967 "loss": 0.44,968 "step": 137969 },970 {971 "epoch": 0.32857142857142857,972 "grad_norm": 0.9323320984840393,973 "learning_rate": 3e-05,974 "loss": 0.4377,975 "step": 138976 },977 {978 "epoch": 0.33095238095238094,979 "grad_norm": 0.8339701294898987,980 "learning_rate": 3e-05,981 "loss": 0.4982,982 "step": 139983 },984 {985 "epoch": 0.3333333333333333,986 "grad_norm": 0.8500747680664062,987 "learning_rate": 3e-05,988 "loss": 0.4303,989 "step": 140990 },991 {992 "epoch": 0.3357142857142857,993 "grad_norm": 0.697967529296875,994 "learning_rate": 3e-05,995 "loss": 0.447,996 "step": 141997 },998 {999 "epoch": 0.3380952380952381,1000 "grad_norm": 1.1016360521316528,1001 "learning_rate": 3e-05,1002 "loss": 0.4827,1003 "step": 1421004 },1005 {1006 "epoch": 0.3404761904761905,1007 "grad_norm": 0.9719865918159485,1008 "learning_rate": 3e-05,1009 "loss": 0.4719,1010 "step": 1431011 },1012 {1013 "epoch": 0.34285714285714286,1014 "grad_norm": 0.8482648134231567,1015 "learning_rate": 3e-05,1016 "loss": 0.4171,1017 "step": 1441018 },1019 {1020 "epoch": 0.34523809523809523,1021 "grad_norm": 1.2719123363494873,1022 "learning_rate": 3e-05,1023 "loss": 0.4444,1024 "step": 1451025 },1026 {1027 "epoch": 0.3476190476190476,1028 "grad_norm": 1.1623255014419556,1029 "learning_rate": 3e-05,1030 "loss": 0.4033,1031 "step": 1461032 },1033 {1034 "epoch": 0.35,1035 "grad_norm": 0.7803097367286682,1036 "learning_rate": 3e-05,1037 "loss": 0.3299,1038 "step": 1471039 },1040 {1041 "epoch": 0.3523809523809524,1042 "grad_norm": 0.6812254786491394,1043 "learning_rate": 3e-05,1044 "loss": 0.3652,1045 "step": 1481046 },1047 {1048 "epoch": 0.3547619047619048,1049 "grad_norm": 1.0708630084991455,1050 "learning_rate": 3e-05,1051 "loss": 0.4121,1052 "step": 1491053 },1054 {1055 "epoch": 0.35714285714285715,1056 "grad_norm": 1.3431651592254639,1057 "learning_rate": 3e-05,1058 "loss": 0.4235,1059 "step": 1501060 },1061 {1062 "epoch": 0.3595238095238095,1063 "grad_norm": 0.779104471206665,1064 "learning_rate": 3e-05,1065 "loss": 0.3404,1066 "step": 1511067 },1068 {1069 "epoch": 0.3619047619047619,1070 "grad_norm": 0.6354933381080627,1071 "learning_rate": 3e-05,1072 "loss": 0.4572,1073 "step": 1521074 },1075 {1076 "epoch": 0.36428571428571427,1077 "grad_norm": 0.6587569117546082,1078 "learning_rate": 3e-05,1079 "loss": 0.3692,1080 "step": 1531081 },1082 {1083 "epoch": 0.36666666666666664,1084 "grad_norm": 1.0237056016921997,1085 "learning_rate": 3e-05,1086 "loss": 0.4356,1087 "step": 1541088 },1089 {1090 "epoch": 0.36904761904761907,1091 "grad_norm": 0.9965682625770569,1092 "learning_rate": 3e-05,1093 "loss": 0.4609,1094 "step": 1551095 },1096 {1097 "epoch": 0.37142857142857144,1098 "grad_norm": 0.9826563000679016,1099 "learning_rate": 3e-05,1100 "loss": 0.4502,1101 "step": 1561102 },1103 {1104 "epoch": 0.3738095238095238,1105 "grad_norm": 1.2390687465667725,1106 "learning_rate": 3e-05,1107 "loss": 0.4734,1108 "step": 1571109 },1110 {1111 "epoch": 0.3761904761904762,1112 "grad_norm": 0.7621622681617737,1113 "learning_rate": 3e-05,1114 "loss": 0.4267,1115 "step": 1581116 },1117 {1118 "epoch": 0.37857142857142856,1119 "grad_norm": 1.300564169883728,1120 "learning_rate": 3e-05,1121 "loss": 0.4018,1122 "step": 1591123 },1124 {1125 "epoch": 0.38095238095238093,1126 "grad_norm": 1.2761445045471191,1127 "learning_rate": 3e-05,1128 "loss": 0.5127,1129 "step": 1601130 },1131 {1132 "epoch": 0.38333333333333336,1133 "grad_norm": 0.933185875415802,1134 "learning_rate": 3e-05,1135 "loss": 0.5515,1136 "step": 1611137 },1138 {1139 "epoch": 0.38571428571428573,1140 "grad_norm": 1.3930639028549194,1141 "learning_rate": 3e-05,1142 "loss": 0.5837,1143 "step": 1621144 },1145 {1146 "epoch": 0.3880952380952381,1147 "grad_norm": 1.7598650455474854,1148 "learning_rate": 3e-05,1149 "loss": 0.6716,1150 "step": 1631151 },1152 {1153 "epoch": 0.3904761904761905,1154 "grad_norm": 0.9068734645843506,1155 "learning_rate": 3e-05,1156 "loss": 0.4984,1157 "step": 1641158 },1159 {1160 "epoch": 0.39285714285714285,1161 "grad_norm": 1.5030951499938965,1162 "learning_rate": 3e-05,1163 "loss": 0.4181,1164 "step": 1651165 },1166 {1167 "epoch": 0.3952380952380952,1168 "grad_norm": 0.6494777798652649,1169 "learning_rate": 3e-05,1170 "loss": 0.4,1171 "step": 1661172 },1173 {1174 "epoch": 0.3976190476190476,1175 "grad_norm": 0.7952489256858826,1176 "learning_rate": 3e-05,1177 "loss": 0.4569,1178 "step": 1671179 },1180 {1181 "epoch": 0.4,1182 "grad_norm": 1.175072193145752,1183 "learning_rate": 3e-05,1184 "loss": 0.4385,1185 "step": 1681186 },1187 {1188 "epoch": 0.4023809523809524,1189 "grad_norm": 0.8904735445976257,1190 "learning_rate": 3e-05,1191 "loss": 0.4107,1192 "step": 1691193 },1194 {1195 "epoch": 0.40476190476190477,1196 "grad_norm": 1.0196988582611084,1197 "learning_rate": 3e-05,1198 "loss": 0.3662,1199 "step": 1701200 },