ToBeWithYou/ABSA-Multi_Label_Classification
03
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 3.984819734345351,5 "eval_steps": 500,6 "global_step": 10500,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.003795066413662239,13 "grad_norm": 1.7131669521331787,14 "learning_rate": 1.6666666666666667e-06,15 "loss": 0.6804,16 "step": 1017 },18 {19 "epoch": 0.007590132827324478,20 "grad_norm": 1.7053213119506836,21 "learning_rate": 3.3333333333333333e-06,22 "loss": 0.6854,23 "step": 2024 },25 {26 "epoch": 0.011385199240986717,27 "grad_norm": 1.8932372331619263,28 "learning_rate": 5e-06,29 "loss": 0.6597,30 "step": 3031 },32 {33 "epoch": 0.015180265654648957,34 "grad_norm": 1.516872763633728,35 "learning_rate": 6.666666666666667e-06,36 "loss": 0.6243,37 "step": 4038 },39 {40 "epoch": 0.018975332068311195,41 "grad_norm": 1.5149081945419312,42 "learning_rate": 8.333333333333334e-06,43 "loss": 0.5632,44 "step": 5045 },46 {47 "epoch": 0.022770398481973434,48 "grad_norm": 1.0706552267074585,49 "learning_rate": 1e-05,50 "loss": 0.5289,51 "step": 6052 },53 {54 "epoch": 0.026565464895635674,55 "grad_norm": 1.102160930633545,56 "learning_rate": 1.1666666666666668e-05,57 "loss": 0.5263,58 "step": 7059 },60 {61 "epoch": 0.030360531309297913,62 "grad_norm": 1.2059059143066406,63 "learning_rate": 1.3333333333333333e-05,64 "loss": 0.5466,65 "step": 8066 },67 {68 "epoch": 0.03415559772296015,69 "grad_norm": 1.0622307062149048,70 "learning_rate": 1.5e-05,71 "loss": 0.4918,72 "step": 9073 },74 {75 "epoch": 0.03795066413662239,76 "grad_norm": 1.5696407556533813,77 "learning_rate": 1.6666666666666667e-05,78 "loss": 0.516,79 "step": 10080 },81 {82 "epoch": 0.04174573055028463,83 "grad_norm": 1.49858820438385,84 "learning_rate": 1.8333333333333333e-05,85 "loss": 0.5024,86 "step": 11087 },88 {89 "epoch": 0.04554079696394687,90 "grad_norm": 1.5996527671813965,91 "learning_rate": 2e-05,92 "loss": 0.4775,93 "step": 12094 },95 {96 "epoch": 0.04933586337760911,97 "grad_norm": 1.6391699314117432,98 "learning_rate": 2.1666666666666667e-05,99 "loss": 0.5028,100 "step": 130101 },102 {103 "epoch": 0.05313092979127135,104 "grad_norm": 1.5045441389083862,105 "learning_rate": 2.3333333333333336e-05,106 "loss": 0.472,107 "step": 140108 },109 {110 "epoch": 0.056925996204933584,111 "grad_norm": 1.1791646480560303,112 "learning_rate": 2.5e-05,113 "loss": 0.4606,114 "step": 150115 },116 {117 "epoch": 0.06072106261859583,118 "grad_norm": 1.3659300804138184,119 "learning_rate": 2.6666666666666667e-05,120 "loss": 0.527,121 "step": 160122 },123 {124 "epoch": 0.06451612903225806,125 "grad_norm": 0.9830155968666077,126 "learning_rate": 2.8333333333333335e-05,127 "loss": 0.458,128 "step": 170129 },130 {131 "epoch": 0.0683111954459203,132 "grad_norm": 1.6211776733398438,133 "learning_rate": 3e-05,134 "loss": 0.4613,135 "step": 180136 },137 {138 "epoch": 0.07210626185958255,139 "grad_norm": 1.9507710933685303,140 "learning_rate": 3.1666666666666666e-05,141 "loss": 0.4531,142 "step": 190143 },144 {145 "epoch": 0.07590132827324478,146 "grad_norm": 1.312615156173706,147 "learning_rate": 3.3333333333333335e-05,148 "loss": 0.4384,149 "step": 200150 },151 {152 "epoch": 0.07969639468690702,153 "grad_norm": 2.034919261932373,154 "learning_rate": 3.5e-05,155 "loss": 0.4747,156 "step": 210157 },158 {159 "epoch": 0.08349146110056926,160 "grad_norm": 2.045759677886963,161 "learning_rate": 3.6666666666666666e-05,162 "loss": 0.4153,163 "step": 220164 },165 {166 "epoch": 0.0872865275142315,167 "grad_norm": 2.0934813022613525,168 "learning_rate": 3.8333333333333334e-05,169 "loss": 0.3829,170 "step": 230171 },172 {173 "epoch": 0.09108159392789374,174 "grad_norm": 2.4255552291870117,175 "learning_rate": 4e-05,176 "loss": 0.3816,177 "step": 240178 },179 {180 "epoch": 0.09487666034155598,181 "grad_norm": 1.42184579372406,182 "learning_rate": 4.166666666666667e-05,183 "loss": 0.3948,184 "step": 250185 },186 {187 "epoch": 0.09867172675521822,188 "grad_norm": 1.6787000894546509,189 "learning_rate": 4.3333333333333334e-05,190 "loss": 0.3877,191 "step": 260192 },193 {194 "epoch": 0.10246679316888045,195 "grad_norm": 2.121290445327759,196 "learning_rate": 4.5e-05,197 "loss": 0.3732,198 "step": 270199 },200 {201 "epoch": 0.1062618595825427,202 "grad_norm": 1.5,203 "learning_rate": 4.666666666666667e-05,204 "loss": 0.3567,205 "step": 280206 },207 {208 "epoch": 0.11005692599620494,209 "grad_norm": 3.0193252563476562,210 "learning_rate": 4.8333333333333334e-05,211 "loss": 0.3916,212 "step": 290213 },214 {215 "epoch": 0.11385199240986717,216 "grad_norm": 2.7301666736602783,217 "learning_rate": 5e-05,218 "loss": 0.3723,219 "step": 300220 },221 {222 "epoch": 0.11764705882352941,223 "grad_norm": 1.8423070907592773,224 "learning_rate": 4.9951171875e-05,225 "loss": 0.3214,226 "step": 310227 },228 {229 "epoch": 0.12144212523719165,230 "grad_norm": 1.204102873802185,231 "learning_rate": 4.990234375e-05,232 "loss": 0.3251,233 "step": 320234 },235 {236 "epoch": 0.1252371916508539,237 "grad_norm": 1.803913950920105,238 "learning_rate": 4.9853515625000005e-05,239 "loss": 0.3942,240 "step": 330241 },242 {243 "epoch": 0.12903225806451613,244 "grad_norm": 3.175114154815674,245 "learning_rate": 4.9804687500000004e-05,246 "loss": 0.39,247 "step": 340248 },249 {250 "epoch": 0.13282732447817835,251 "grad_norm": 2.4476590156555176,252 "learning_rate": 4.9755859375e-05,253 "loss": 0.349,254 "step": 350255 },256 {257 "epoch": 0.1366223908918406,258 "grad_norm": 1.2592339515686035,259 "learning_rate": 4.970703125e-05,260 "loss": 0.3315,261 "step": 360262 },263 {264 "epoch": 0.14041745730550284,265 "grad_norm": 1.6238622665405273,266 "learning_rate": 4.9658203125e-05,267 "loss": 0.3307,268 "step": 370269 },270 {271 "epoch": 0.1442125237191651,272 "grad_norm": 1.3984373807907104,273 "learning_rate": 4.9609375000000005e-05,274 "loss": 0.294,275 "step": 380276 },277 {278 "epoch": 0.14800759013282733,279 "grad_norm": 3.1960623264312744,280 "learning_rate": 4.9560546875e-05,281 "loss": 0.3314,282 "step": 390283 },284 {285 "epoch": 0.15180265654648956,286 "grad_norm": 1.5345971584320068,287 "learning_rate": 4.951171875e-05,288 "loss": 0.3438,289 "step": 400290 },291 {292 "epoch": 0.1555977229601518,293 "grad_norm": 3.1037323474884033,294 "learning_rate": 4.9462890625e-05,295 "loss": 0.3246,296 "step": 410297 },298 {299 "epoch": 0.15939278937381404,300 "grad_norm": 3.519519805908203,301 "learning_rate": 4.94140625e-05,302 "loss": 0.3087,303 "step": 420304 },305 {306 "epoch": 0.16318785578747627,307 "grad_norm": 1.347273826599121,308 "learning_rate": 4.9365234375000005e-05,309 "loss": 0.3303,310 "step": 430311 },312 {313 "epoch": 0.16698292220113853,314 "grad_norm": 1.2372374534606934,315 "learning_rate": 4.931640625e-05,316 "loss": 0.3225,317 "step": 440318 },319 {320 "epoch": 0.17077798861480076,321 "grad_norm": 0.9122889637947083,322 "learning_rate": 4.9267578125e-05,323 "loss": 0.3081,324 "step": 450325 },326 {327 "epoch": 0.174573055028463,328 "grad_norm": 3.7750535011291504,329 "learning_rate": 4.921875e-05,330 "loss": 0.2785,331 "step": 460332 },333 {334 "epoch": 0.17836812144212524,335 "grad_norm": 1.0529924631118774,336 "learning_rate": 4.9169921875000006e-05,337 "loss": 0.283,338 "step": 470339 },340 {341 "epoch": 0.18216318785578747,342 "grad_norm": 1.5323132276535034,343 "learning_rate": 4.9121093750000004e-05,344 "loss": 0.2982,345 "step": 480346 },347 {348 "epoch": 0.1859582542694497,349 "grad_norm": 1.1751055717468262,350 "learning_rate": 4.9072265625e-05,351 "loss": 0.2639,352 "step": 490353 },354 {355 "epoch": 0.18975332068311196,356 "grad_norm": 1.0208653211593628,357 "learning_rate": 4.90234375e-05,358 "loss": 0.2651,359 "step": 500360 },361 {362 "epoch": 0.1935483870967742,363 "grad_norm": 1.7089987993240356,364 "learning_rate": 4.8974609375e-05,365 "loss": 0.2572,366 "step": 510367 },368 {369 "epoch": 0.19734345351043645,370 "grad_norm": 4.918070316314697,371 "learning_rate": 4.8925781250000006e-05,372 "loss": 0.299,373 "step": 520374 },375 {376 "epoch": 0.20113851992409867,377 "grad_norm": 1.117162823677063,378 "learning_rate": 4.8876953125000004e-05,379 "loss": 0.2699,380 "step": 530381 },382 {383 "epoch": 0.2049335863377609,384 "grad_norm": 1.813411831855774,385 "learning_rate": 4.8828125e-05,386 "loss": 0.2391,387 "step": 540388 },389 {390 "epoch": 0.20872865275142316,391 "grad_norm": 3.368643283843994,392 "learning_rate": 4.8779296875e-05,393 "loss": 0.3022,394 "step": 550395 },396 {397 "epoch": 0.2125237191650854,398 "grad_norm": 16.486289978027344,399 "learning_rate": 4.873046875e-05,400 "loss": 0.2837,401 "step": 560402 },403 {404 "epoch": 0.21631878557874762,405 "grad_norm": 1.3590037822723389,406 "learning_rate": 4.8681640625000005e-05,407 "loss": 0.2182,408 "step": 570409 },410 {411 "epoch": 0.22011385199240988,412 "grad_norm": 1.8672986030578613,413 "learning_rate": 4.8632812500000004e-05,414 "loss": 0.2925,415 "step": 580416 },417 {418 "epoch": 0.2239089184060721,419 "grad_norm": 2.350752592086792,420 "learning_rate": 4.8583984375e-05,421 "loss": 0.2585,422 "step": 590423 },424 {425 "epoch": 0.22770398481973433,426 "grad_norm": 2.4918649196624756,427 "learning_rate": 4.853515625e-05,428 "loss": 0.2824,429 "step": 600430 },431 {432 "epoch": 0.2314990512333966,433 "grad_norm": 2.4856553077697754,434 "learning_rate": 4.8486328125e-05,435 "loss": 0.2444,436 "step": 610437 },438 {439 "epoch": 0.23529411764705882,440 "grad_norm": 1.87199866771698,441 "learning_rate": 4.8437500000000005e-05,442 "loss": 0.256,443 "step": 620444 },445 {446 "epoch": 0.23908918406072105,447 "grad_norm": 1.0694291591644287,448 "learning_rate": 4.8388671875000004e-05,449 "loss": 0.245,450 "step": 630451 },452 {453 "epoch": 0.2428842504743833,454 "grad_norm": 0.7904035449028015,455 "learning_rate": 4.833984375e-05,456 "loss": 0.2588,457 "step": 640458 },459 {460 "epoch": 0.24667931688804554,461 "grad_norm": 2.714871883392334,462 "learning_rate": 4.8291015625e-05,463 "loss": 0.2741,464 "step": 650465 },466 {467 "epoch": 0.2504743833017078,468 "grad_norm": 3.948547124862671,469 "learning_rate": 4.82421875e-05,470 "loss": 0.2335,471 "step": 660472 },473 {474 "epoch": 0.25426944971537,475 "grad_norm": 1.6354694366455078,476 "learning_rate": 4.8193359375000005e-05,477 "loss": 0.2298,478 "step": 670479 },480 {481 "epoch": 0.25806451612903225,482 "grad_norm": 1.1305994987487793,483 "learning_rate": 4.8144531250000003e-05,484 "loss": 0.2279,485 "step": 680486 },487 {488 "epoch": 0.2618595825426945,489 "grad_norm": 1.804825782775879,490 "learning_rate": 4.8095703125e-05,491 "loss": 0.2401,492 "step": 690493 },494 {495 "epoch": 0.2656546489563567,496 "grad_norm": 1.0778950452804565,497 "learning_rate": 4.8046875e-05,498 "loss": 0.2498,499 "step": 700500 },501 {502 "epoch": 0.269449715370019,503 "grad_norm": 2.672403335571289,504 "learning_rate": 4.7998046875e-05,505 "loss": 0.2521,506 "step": 710507 },508 {509 "epoch": 0.2732447817836812,510 "grad_norm": 1.0559144020080566,511 "learning_rate": 4.7949218750000005e-05,512 "loss": 0.1855,513 "step": 720514 },515 {516 "epoch": 0.27703984819734345,517 "grad_norm": 1.3226491212844849,518 "learning_rate": 4.7900390625e-05,519 "loss": 0.21,520 "step": 730521 },522 {523 "epoch": 0.2808349146110057,524 "grad_norm": 2.1266074180603027,525 "learning_rate": 4.78515625e-05,526 "loss": 0.2232,527 "step": 740528 },529 {530 "epoch": 0.2846299810246679,531 "grad_norm": 2.9967539310455322,532 "learning_rate": 4.7802734375e-05,533 "loss": 0.2554,534 "step": 750535 },536 {537 "epoch": 0.2884250474383302,538 "grad_norm": 2.6614627838134766,539 "learning_rate": 4.775390625e-05,540 "loss": 0.2811,541 "step": 760542 },543 {544 "epoch": 0.2922201138519924,545 "grad_norm": 1.64667546749115,546 "learning_rate": 4.7705078125000004e-05,547 "loss": 0.2102,548 "step": 770549 },550 {551 "epoch": 0.29601518026565465,552 "grad_norm": 2.339608669281006,553 "learning_rate": 4.765625e-05,554 "loss": 0.2125,555 "step": 780556 },557 {558 "epoch": 0.2998102466793169,559 "grad_norm": 1.6804083585739136,560 "learning_rate": 4.7607421875e-05,561 "loss": 0.2722,562 "step": 790563 },564 {565 "epoch": 0.3036053130929791,566 "grad_norm": 2.6005263328552246,567 "learning_rate": 4.755859375e-05,568 "loss": 0.2067,569 "step": 800570 },571 {572 "epoch": 0.30740037950664134,573 "grad_norm": 5.113396167755127,574 "learning_rate": 4.7509765625000006e-05,575 "loss": 0.1988,576 "step": 810577 },578 {579 "epoch": 0.3111954459203036,580 "grad_norm": 1.9176031351089478,581 "learning_rate": 4.7460937500000004e-05,582 "loss": 0.2416,583 "step": 820584 },585 {586 "epoch": 0.31499051233396586,587 "grad_norm": 1.5946362018585205,588 "learning_rate": 4.7412109375e-05,589 "loss": 0.2416,590 "step": 830591 },592 {593 "epoch": 0.3187855787476281,594 "grad_norm": 1.6692804098129272,595 "learning_rate": 4.736328125e-05,596 "loss": 0.2139,597 "step": 840598 },599 {600 "epoch": 0.3225806451612903,601 "grad_norm": 4.5298285484313965,602 "learning_rate": 4.7314453125e-05,603 "loss": 0.2285,604 "step": 850605 },606 {607 "epoch": 0.32637571157495254,608 "grad_norm": 1.9948817491531372,609 "learning_rate": 4.7265625000000005e-05,610 "loss": 0.2453,611 "step": 860612 },613 {614 "epoch": 0.3301707779886148,615 "grad_norm": 2.5353565216064453,616 "learning_rate": 4.7216796875000004e-05,617 "loss": 0.2259,618 "step": 870619 },620 {621 "epoch": 0.33396584440227706,622 "grad_norm": 5.23643684387207,623 "learning_rate": 4.716796875e-05,624 "loss": 0.2318,625 "step": 880626 },627 {628 "epoch": 0.3377609108159393,629 "grad_norm": 3.062701463699341,630 "learning_rate": 4.7119140625e-05,631 "loss": 0.1835,632 "step": 890633 },634 {635 "epoch": 0.3415559772296015,636 "grad_norm": 1.5771597623825073,637 "learning_rate": 4.70703125e-05,638 "loss": 0.2195,639 "step": 900640 },641 {642 "epoch": 0.34535104364326374,643 "grad_norm": 0.9039077162742615,644 "learning_rate": 4.7021484375000005e-05,645 "loss": 0.1545,646 "step": 910647 },648 {649 "epoch": 0.349146110056926,650 "grad_norm": 2.7035298347473145,651 "learning_rate": 4.6972656250000004e-05,652 "loss": 0.2221,653 "step": 920654 },655 {656 "epoch": 0.35294117647058826,657 "grad_norm": 2.3225386142730713,658 "learning_rate": 4.6923828125e-05,659 "loss": 0.1912,660 "step": 930661 },662 {663 "epoch": 0.3567362428842505,664 "grad_norm": 1.1066793203353882,665 "learning_rate": 4.6875e-05,666 "loss": 0.2003,667 "step": 940668 },669 {670 "epoch": 0.3605313092979127,671 "grad_norm": 1.2358715534210205,672 "learning_rate": 4.6826171875e-05,673 "loss": 0.1944,674 "step": 950675 },676 {677 "epoch": 0.36432637571157495,678 "grad_norm": 0.5866732001304626,679 "learning_rate": 4.6777343750000005e-05,680 "loss": 0.1885,681 "step": 960682 },683 {684 "epoch": 0.3681214421252372,685 "grad_norm": 1.436168909072876,686 "learning_rate": 4.6728515625000004e-05,687 "loss": 0.182,688 "step": 970689 },690 {691 "epoch": 0.3719165085388994,692 "grad_norm": 1.5037955045700073,693 "learning_rate": 4.66796875e-05,694 "loss": 0.2024,695 "step": 980696 },697 {698 "epoch": 0.3757115749525617,699 "grad_norm": 1.4837393760681152,700 "learning_rate": 4.6630859375e-05,701 "loss": 0.2249,702 "step": 990703 },704 {705 "epoch": 0.3795066413662239,706 "grad_norm": 12.082221031188965,707 "learning_rate": 4.658203125e-05,708 "loss": 0.2191,709 "step": 1000710 },711 {712 "epoch": 0.38330170777988615,713 "grad_norm": 0.7743262648582458,714 "learning_rate": 4.6533203125000005e-05,715 "loss": 0.1654,716 "step": 1010717 },718 {719 "epoch": 0.3870967741935484,720 "grad_norm": 3.7393670082092285,721 "learning_rate": 4.6484375e-05,722 "loss": 0.1595,723 "step": 1020724 },725 {726 "epoch": 0.3908918406072106,727 "grad_norm": 1.2153229713439941,728 "learning_rate": 4.6435546875e-05,729 "loss": 0.2276,730 "step": 1030731 },732 {733 "epoch": 0.3946869070208729,734 "grad_norm": 0.9271629452705383,735 "learning_rate": 4.638671875e-05,736 "loss": 0.2039,737 "step": 1040738 },739 {740 "epoch": 0.3984819734345351,741 "grad_norm": 1.0829685926437378,742 "learning_rate": 4.6337890625e-05,743 "loss": 0.1731,744 "step": 1050745 },746 {747 "epoch": 0.40227703984819735,748 "grad_norm": 1.2705596685409546,749 "learning_rate": 4.6289062500000005e-05,750 "loss": 0.1359,751 "step": 1060752 },753 {754 "epoch": 0.4060721062618596,755 "grad_norm": 4.376911163330078,756 "learning_rate": 4.6240234375e-05,757 "loss": 0.2095,758 "step": 1070759 },760 {761 "epoch": 0.4098671726755218,762 "grad_norm": 2.1292335987091064,763 "learning_rate": 4.619140625e-05,764 "loss": 0.1916,765 "step": 1080766 },767 {768 "epoch": 0.41366223908918404,769 "grad_norm": 1.6525979042053223,770 "learning_rate": 4.6142578125e-05,771 "loss": 0.173,772 "step": 1090773 },774 {775 "epoch": 0.4174573055028463,776 "grad_norm": 4.228000164031982,777 "learning_rate": 4.609375e-05,778 "loss": 0.2117,779 "step": 1100780 },781 {782 "epoch": 0.42125237191650855,783 "grad_norm": 5.334222316741943,784 "learning_rate": 4.6044921875000004e-05,785 "loss": 0.185,786 "step": 1110787 },788 {789 "epoch": 0.4250474383301708,790 "grad_norm": 1.7326403856277466,791 "learning_rate": 4.599609375e-05,792 "loss": 0.1875,793 "step": 1120794 },795 {796 "epoch": 0.428842504743833,797 "grad_norm": 2.4292402267456055,798 "learning_rate": 4.5947265625e-05,799 "loss": 0.1747,800 "step": 1130801 },802 {803 "epoch": 0.43263757115749524,804 "grad_norm": 1.6561298370361328,805 "learning_rate": 4.58984375e-05,806 "loss": 0.2017,807 "step": 1140808 },809 {810 "epoch": 0.4364326375711575,811 "grad_norm": 2.659874439239502,812 "learning_rate": 4.5849609375000005e-05,813 "loss": 0.2415,814 "step": 1150815 },816 {817 "epoch": 0.44022770398481975,818 "grad_norm": 2.743425130844116,819 "learning_rate": 4.5800781250000004e-05,820 "loss": 0.2332,821 "step": 1160822 },823 {824 "epoch": 0.444022770398482,825 "grad_norm": 2.3197848796844482,826 "learning_rate": 4.5751953125e-05,827 "loss": 0.1946,828 "step": 1170829 },830 {831 "epoch": 0.4478178368121442,832 "grad_norm": 2.110534191131592,833 "learning_rate": 4.5703125e-05,834 "loss": 0.1948,835 "step": 1180836 },837 {838 "epoch": 0.45161290322580644,839 "grad_norm": 1.3609685897827148,840 "learning_rate": 4.5654296875e-05,841 "loss": 0.1801,842 "step": 1190843 },844 {845 "epoch": 0.45540796963946867,846 "grad_norm": 3.159426689147949,847 "learning_rate": 4.5605468750000005e-05,848 "loss": 0.2184,849 "step": 1200850 },851 {852 "epoch": 0.45920303605313095,853 "grad_norm": 1.7927987575531006,854 "learning_rate": 4.5556640625000004e-05,855 "loss": 0.1604,856 "step": 1210857 },858 {859 "epoch": 0.4629981024667932,860 "grad_norm": 1.5928328037261963,861 "learning_rate": 4.55078125e-05,862 "loss": 0.1693,863 "step": 1220864 },865 {866 "epoch": 0.4667931688804554,867 "grad_norm": 0.8145284056663513,868 "learning_rate": 4.5458984375e-05,869 "loss": 0.1761,870 "step": 1230871 },872 {873 "epoch": 0.47058823529411764,874 "grad_norm": 0.7765156030654907,875 "learning_rate": 4.541015625e-05,876 "loss": 0.1799,877 "step": 1240878 },879 {880 "epoch": 0.47438330170777987,881 "grad_norm": 1.8456169366836548,882 "learning_rate": 4.5361328125000005e-05,883 "loss": 0.168,884 "step": 1250885 },886 {887 "epoch": 0.4781783681214421,888 "grad_norm": 1.6953251361846924,889 "learning_rate": 4.5312500000000004e-05,890 "loss": 0.1945,891 "step": 1260892 },893 {894 "epoch": 0.4819734345351044,895 "grad_norm": 1.5285083055496216,896 "learning_rate": 4.5263671875e-05,897 "loss": 0.2075,898 "step": 1270899 },900 {901 "epoch": 0.4857685009487666,902 "grad_norm": 2.95650577545166,903 "learning_rate": 4.521484375e-05,904 "loss": 0.1601,905 "step": 1280906 },907 {908 "epoch": 0.48956356736242884,909 "grad_norm": 0.7677034735679626,910 "learning_rate": 4.5166015625e-05,911 "loss": 0.1695,912 "step": 1290913 },914 {915 "epoch": 0.49335863377609107,916 "grad_norm": 1.9959975481033325,917 "learning_rate": 4.5117187500000005e-05,918 "loss": 0.2183,919 "step": 1300920 },921 {922 "epoch": 0.4971537001897533,923 "grad_norm": 1.8000417947769165,924 "learning_rate": 4.5068359375000003e-05,925 "loss": 0.175,926 "step": 1310927 },928 {929 "epoch": 0.5009487666034156,930 "grad_norm": 1.400612473487854,931 "learning_rate": 4.501953125e-05,932 "loss": 0.2085,933 "step": 1320934 },935 {936 "epoch": 0.5047438330170778,937 "grad_norm": 1.6406989097595215,938 "learning_rate": 4.4970703125e-05,939 "loss": 0.1537,940 "step": 1330941 },942 {943 "epoch": 0.50853889943074,944 "grad_norm": 2.0849852561950684,945 "learning_rate": 4.4921875e-05,946 "loss": 0.1579,947 "step": 1340948 },949 {950 "epoch": 0.5123339658444023,951 "grad_norm": 2.6497225761413574,952 "learning_rate": 4.4873046875000005e-05,953 "loss": 0.1888,954 "step": 1350955 },956 {957 "epoch": 0.5161290322580645,958 "grad_norm": 2.2594399452209473,959 "learning_rate": 4.482421875e-05,960 "loss": 0.1645,961 "step": 1360962 },963 {964 "epoch": 0.5199240986717267,965 "grad_norm": 1.3591111898422241,966 "learning_rate": 4.4775390625e-05,967 "loss": 0.1876,968 "step": 1370969 },970 {971 "epoch": 0.523719165085389,972 "grad_norm": 5.060487747192383,973 "learning_rate": 4.47265625e-05,974 "loss": 0.1946,975 "step": 1380976 },977 {978 "epoch": 0.5275142314990512,979 "grad_norm": 1.7694716453552246,980 "learning_rate": 4.4677734375e-05,981 "loss": 0.0966,982 "step": 1390983 },984 {985 "epoch": 0.5313092979127134,986 "grad_norm": 2.8661625385284424,987 "learning_rate": 4.4628906250000004e-05,988 "loss": 0.1614,989 "step": 1400990 },991 {992 "epoch": 0.5351043643263758,993 "grad_norm": 2.2955727577209473,994 "learning_rate": 4.4580078125e-05,995 "loss": 0.193,996 "step": 1410997 },998 {999 "epoch": 0.538899430740038,1000 "grad_norm": 1.4596924781799316,1001 "learning_rate": 4.453125e-05,1002 "loss": 0.1971,1003 "step": 14201004 },1005 {1006 "epoch": 0.5426944971537002,1007 "grad_norm": 1.039890170097351,1008 "learning_rate": 4.4482421875e-05,1009 "loss": 0.1909,1010 "step": 14301011 },1012 {1013 "epoch": 0.5464895635673624,1014 "grad_norm": 1.433979868888855,1015 "learning_rate": 4.443359375e-05,1016 "loss": 0.1832,1017 "step": 14401018 },1019 {1020 "epoch": 0.5502846299810247,1021 "grad_norm": 1.306391954421997,1022 "learning_rate": 4.4384765625000004e-05,1023 "loss": 0.1867,1024 "step": 14501025 },1026 {1027 "epoch": 0.5540796963946869,1028 "grad_norm": 1.2681069374084473,1029 "learning_rate": 4.43359375e-05,1030 "loss": 0.1506,1031 "step": 14601032 },1033 {1034 "epoch": 0.5578747628083491,1035 "grad_norm": 3.947502613067627,1036 "learning_rate": 4.4287109375e-05,1037 "loss": 0.1343,1038 "step": 14701039 },1040 {1041 "epoch": 0.5616698292220114,1042 "grad_norm": 4.928821563720703,1043 "learning_rate": 4.423828125e-05,1044 "loss": 0.2057,1045 "step": 14801046 },1047 {1048 "epoch": 0.5654648956356736,1049 "grad_norm": 2.162473201751709,1050 "learning_rate": 4.4189453125000005e-05,1051 "loss": 0.1942,1052 "step": 14901053 },1054 {1055 "epoch": 0.5692599620493358,1056 "grad_norm": 5.402246475219727,1057 "learning_rate": 4.4140625000000004e-05,1058 "loss": 0.1727,1059 "step": 15001060 },1061 {1062 "epoch": 0.573055028462998,1063 "grad_norm": 0.2728889286518097,1064 "learning_rate": 4.4091796875e-05,1065 "loss": 0.1345,1066 "step": 15101067 },1068 {1069 "epoch": 0.5768500948766604,1070 "grad_norm": 2.027841567993164,1071 "learning_rate": 4.404296875e-05,1072 "loss": 0.213,1073 "step": 15201074 },1075 {1076 "epoch": 0.5806451612903226,1077 "grad_norm": 1.3224737644195557,1078 "learning_rate": 4.3994140625e-05,1079 "loss": 0.1735,1080 "step": 15301081 },1082 {1083 "epoch": 0.5844402277039848,1084 "grad_norm": 2.3124992847442627,1085 "learning_rate": 4.3945312500000005e-05,1086 "loss": 0.2177,1087 "step": 15401088 },1089 {1090 "epoch": 0.5882352941176471,1091 "grad_norm": 1.2521787881851196,1092 "learning_rate": 4.3896484375000004e-05,1093 "loss": 0.1332,1094 "step": 15501095 },1096 {1097 "epoch": 0.5920303605313093,1098 "grad_norm": 2.5216283798217773,1099 "learning_rate": 4.384765625e-05,1100 "loss": 0.1318,1101 "step": 15601102 },1103 {1104 "epoch": 0.5958254269449715,1105 "grad_norm": 1.8268439769744873,1106 "learning_rate": 4.3798828125e-05,1107 "loss": 0.1269,1108 "step": 15701109 },1110 {1111 "epoch": 0.5996204933586338,1112 "grad_norm": 0.6268766522407532,1113 "learning_rate": 4.375e-05,1114 "loss": 0.1381,1115 "step": 15801116 },1117 {1118 "epoch": 0.603415559772296,1119 "grad_norm": 1.979546308517456,1120 "learning_rate": 4.3701171875000005e-05,1121 "loss": 0.1351,1122 "step": 15901123 },1124 {1125 "epoch": 0.6072106261859582,1126 "grad_norm": 1.5526436567306519,1127 "learning_rate": 4.3652343750000004e-05,1128 "loss": 0.2163,1129 "step": 16001130 },1131 {1132 "epoch": 0.6110056925996205,1133 "grad_norm": 0.9428083896636963,1134 "learning_rate": 4.3603515625e-05,1135 "loss": 0.1398,1136 "step": 16101137 },1138 {1139 "epoch": 0.6148007590132827,1140 "grad_norm": 2.1224870681762695,1141 "learning_rate": 4.35546875e-05,1142 "loss": 0.1891,1143 "step": 16201144 },1145 {1146 "epoch": 0.618595825426945,1147 "grad_norm": 0.3401525914669037,1148 "learning_rate": 4.3505859375e-05,1149 "loss": 0.1068,1150 "step": 16301151 },1152 {1153 "epoch": 0.6223908918406073,1154 "grad_norm": 1.1070092916488647,1155 "learning_rate": 4.3457031250000005e-05,1156 "loss": 0.1407,1157 "step": 16401158 },1159 {1160 "epoch": 0.6261859582542695,1161 "grad_norm": 1.1588579416275024,1162 "learning_rate": 4.3408203125e-05,1163 "loss": 0.2238,1164 "step": 16501165 },1166 {1167 "epoch": 0.6299810246679317,1168 "grad_norm": 1.3201090097427368,1169 "learning_rate": 4.3359375e-05,1170 "loss": 0.2135,1171 "step": 16601172 },1173 {1174 "epoch": 0.6337760910815939,1175 "grad_norm": 1.2257441282272339,1176 "learning_rate": 4.3310546875e-05,1177 "loss": 0.1261,1178 "step": 16701179 },1180 {1181 "epoch": 0.6375711574952562,1182 "grad_norm": 1.4213567972183228,1183 "learning_rate": 4.326171875e-05,1184 "loss": 0.1439,1185 "step": 16801186 },1187 {1188 "epoch": 0.6413662239089184,1189 "grad_norm": 1.0983916521072388,1190 "learning_rate": 4.3212890625000004e-05,1191 "loss": 0.1356,1192 "step": 16901193 },1194 {1195 "epoch": 0.6451612903225806,1196 "grad_norm": 1.6485854387283325,1197 "learning_rate": 4.31640625e-05,1198 "loss": 0.1549,1199 "step": 17001200 },