devolvedLLM / mixtral2 /trainer_state.json
JayKimDevolved's picture
Upload 66 files
f3ccbc5 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 79.43793911007026,
"eval_steps": 500,
"global_step": 4240,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1873536299765808,
"grad_norm": 5.991908550262451,
"learning_rate": 4.9999313759953484e-05,
"loss": 6.4768,
"step": 10
},
{
"epoch": 0.3747072599531616,
"grad_norm": 8.760614395141602,
"learning_rate": 4.999725507748798e-05,
"loss": 5.0186,
"step": 20
},
{
"epoch": 0.5620608899297423,
"grad_norm": 4.322343826293945,
"learning_rate": 4.999382406562349e-05,
"loss": 3.1088,
"step": 30
},
{
"epoch": 0.7494145199063232,
"grad_norm": 1.4796526432037354,
"learning_rate": 4.9989020912719864e-05,
"loss": 2.2997,
"step": 40
},
{
"epoch": 0.936768149882904,
"grad_norm": 0.8381783962249756,
"learning_rate": 4.998284588246634e-05,
"loss": 1.9748,
"step": 50
},
{
"epoch": 1.1241217798594847,
"grad_norm": 0.6073408722877502,
"learning_rate": 4.99752993138672e-05,
"loss": 1.8716,
"step": 60
},
{
"epoch": 1.3114754098360657,
"grad_norm": 0.5777516961097717,
"learning_rate": 4.996638162122302e-05,
"loss": 1.7803,
"step": 70
},
{
"epoch": 1.4988290398126463,
"grad_norm": 0.5658383369445801,
"learning_rate": 4.995609329410804e-05,
"loss": 1.7585,
"step": 80
},
{
"epoch": 1.6861826697892273,
"grad_norm": 0.6109507083892822,
"learning_rate": 4.994443489734322e-05,
"loss": 1.6902,
"step": 90
},
{
"epoch": 1.8735362997658078,
"grad_norm": 0.6710304021835327,
"learning_rate": 4.9931407070965254e-05,
"loss": 1.675,
"step": 100
},
{
"epoch": 2.060889929742389,
"grad_norm": 0.6605099439620972,
"learning_rate": 4.9917010530191455e-05,
"loss": 1.5914,
"step": 110
},
{
"epoch": 2.2482435597189694,
"grad_norm": 0.8813541531562805,
"learning_rate": 4.990124606538042e-05,
"loss": 1.5681,
"step": 120
},
{
"epoch": 2.4355971896955504,
"grad_norm": 0.9561053514480591,
"learning_rate": 4.9884114541988747e-05,
"loss": 1.4891,
"step": 130
},
{
"epoch": 2.6229508196721314,
"grad_norm": 1.0302178859710693,
"learning_rate": 4.9865616900523406e-05,
"loss": 1.4524,
"step": 140
},
{
"epoch": 2.810304449648712,
"grad_norm": 1.114527940750122,
"learning_rate": 4.984575415649019e-05,
"loss": 1.3666,
"step": 150
},
{
"epoch": 2.9976580796252925,
"grad_norm": 1.1488112211227417,
"learning_rate": 4.982452740033793e-05,
"loss": 1.3581,
"step": 160
},
{
"epoch": 3.1850117096018735,
"grad_norm": 1.3187187910079956,
"learning_rate": 4.9801937797398636e-05,
"loss": 1.2926,
"step": 170
},
{
"epoch": 3.3723653395784545,
"grad_norm": 1.4319546222686768,
"learning_rate": 4.9777986587823523e-05,
"loss": 1.2463,
"step": 180
},
{
"epoch": 3.559718969555035,
"grad_norm": 1.4622282981872559,
"learning_rate": 4.975267508651492e-05,
"loss": 1.2304,
"step": 190
},
{
"epoch": 3.747072599531616,
"grad_norm": 2.000797748565674,
"learning_rate": 4.97260046830541e-05,
"loss": 1.2252,
"step": 200
},
{
"epoch": 3.9344262295081966,
"grad_norm": 1.6277581453323364,
"learning_rate": 4.969797684162498e-05,
"loss": 1.1649,
"step": 210
},
{
"epoch": 4.121779859484778,
"grad_norm": 2.1771910190582275,
"learning_rate": 4.966859310093372e-05,
"loss": 1.1471,
"step": 220
},
{
"epoch": 4.309133489461359,
"grad_norm": 1.9214098453521729,
"learning_rate": 4.9637855074124305e-05,
"loss": 1.1064,
"step": 230
},
{
"epoch": 4.496487119437939,
"grad_norm": 2.057615041732788,
"learning_rate": 4.960576444868992e-05,
"loss": 1.1061,
"step": 240
},
{
"epoch": 4.68384074941452,
"grad_norm": 1.851131796836853,
"learning_rate": 4.957232298638036e-05,
"loss": 1.0318,
"step": 250
},
{
"epoch": 4.871194379391101,
"grad_norm": 2.1048285961151123,
"learning_rate": 4.953753252310526e-05,
"loss": 1.0444,
"step": 260
},
{
"epoch": 5.058548009367682,
"grad_norm": 2.0235438346862793,
"learning_rate": 4.950139496883335e-05,
"loss": 1.0303,
"step": 270
},
{
"epoch": 5.245901639344262,
"grad_norm": 2.574484348297119,
"learning_rate": 4.94639123074876e-05,
"loss": 0.9954,
"step": 280
},
{
"epoch": 5.433255269320843,
"grad_norm": 2.1624159812927246,
"learning_rate": 4.9425086596836264e-05,
"loss": 0.9686,
"step": 290
},
{
"epoch": 5.620608899297424,
"grad_norm": 2.923964023590088,
"learning_rate": 4.9384919968379945e-05,
"loss": 0.961,
"step": 300
},
{
"epoch": 5.807962529274005,
"grad_norm": 3.605888843536377,
"learning_rate": 4.934341462723455e-05,
"loss": 0.9713,
"step": 310
},
{
"epoch": 5.995316159250585,
"grad_norm": 2.6934282779693604,
"learning_rate": 4.930057285201027e-05,
"loss": 0.9327,
"step": 320
},
{
"epoch": 6.182669789227166,
"grad_norm": 2.723066568374634,
"learning_rate": 4.925639699468645e-05,
"loss": 0.8974,
"step": 330
},
{
"epoch": 6.370023419203747,
"grad_norm": 2.7989768981933594,
"learning_rate": 4.921088948048247e-05,
"loss": 0.8912,
"step": 340
},
{
"epoch": 6.557377049180328,
"grad_norm": 2.685530424118042,
"learning_rate": 4.916405280772462e-05,
"loss": 0.8809,
"step": 350
},
{
"epoch": 6.744730679156909,
"grad_norm": 2.441941738128662,
"learning_rate": 4.911588954770897e-05,
"loss": 0.8984,
"step": 360
},
{
"epoch": 6.932084309133489,
"grad_norm": 2.7177064418792725,
"learning_rate": 4.9066402344560115e-05,
"loss": 0.855,
"step": 370
},
{
"epoch": 7.11943793911007,
"grad_norm": 3.2908644676208496,
"learning_rate": 4.901559391508611e-05,
"loss": 0.8785,
"step": 380
},
{
"epoch": 7.306791569086651,
"grad_norm": 3.195590019226074,
"learning_rate": 4.896346704862927e-05,
"loss": 0.8542,
"step": 390
},
{
"epoch": 7.494145199063232,
"grad_norm": 3.4960882663726807,
"learning_rate": 4.891002460691306e-05,
"loss": 0.7881,
"step": 400
},
{
"epoch": 7.681498829039812,
"grad_norm": 2.852773666381836,
"learning_rate": 4.885526952388498e-05,
"loss": 0.7957,
"step": 410
},
{
"epoch": 7.868852459016393,
"grad_norm": 2.8862316608428955,
"learning_rate": 4.879920480555549e-05,
"loss": 0.8022,
"step": 420
},
{
"epoch": 8.056206088992974,
"grad_norm": 2.706434488296509,
"learning_rate": 4.874183352983297e-05,
"loss": 0.7811,
"step": 430
},
{
"epoch": 8.243559718969555,
"grad_norm": 3.107057809829712,
"learning_rate": 4.8683158846354786e-05,
"loss": 0.7786,
"step": 440
},
{
"epoch": 8.430913348946136,
"grad_norm": 3.327939033508301,
"learning_rate": 4.862318397631434e-05,
"loss": 0.7431,
"step": 450
},
{
"epoch": 8.618266978922717,
"grad_norm": 3.249922513961792,
"learning_rate": 4.8561912212284223e-05,
"loss": 0.7477,
"step": 460
},
{
"epoch": 8.805620608899297,
"grad_norm": 3.709353446960449,
"learning_rate": 4.84993469180355e-05,
"loss": 0.7973,
"step": 470
},
{
"epoch": 8.992974238875878,
"grad_norm": 2.777991533279419,
"learning_rate": 4.8435491528353026e-05,
"loss": 0.7699,
"step": 480
},
{
"epoch": 9.180327868852459,
"grad_norm": 2.6447904109954834,
"learning_rate": 4.8370349548846823e-05,
"loss": 0.692,
"step": 490
},
{
"epoch": 9.36768149882904,
"grad_norm": 3.150733232498169,
"learning_rate": 4.83039245557597e-05,
"loss": 0.7435,
"step": 500
},
{
"epoch": 9.55503512880562,
"grad_norm": 3.316145420074463,
"learning_rate": 4.823622019577089e-05,
"loss": 0.7589,
"step": 510
},
{
"epoch": 9.742388758782202,
"grad_norm": 3.4923229217529297,
"learning_rate": 4.8167240185795835e-05,
"loss": 0.7262,
"step": 520
},
{
"epoch": 9.929742388758783,
"grad_norm": 3.1557626724243164,
"learning_rate": 4.8096988312782174e-05,
"loss": 0.6824,
"step": 530
},
{
"epoch": 10.117096018735364,
"grad_norm": 3.2009847164154053,
"learning_rate": 4.8025468433501774e-05,
"loss": 0.7238,
"step": 540
},
{
"epoch": 10.304449648711945,
"grad_norm": 3.149319887161255,
"learning_rate": 4.795268447433907e-05,
"loss": 0.7002,
"step": 550
},
{
"epoch": 10.491803278688524,
"grad_norm": 3.1471166610717773,
"learning_rate": 4.787864043107546e-05,
"loss": 0.6933,
"step": 560
},
{
"epoch": 10.679156908665105,
"grad_norm": 2.9310121536254883,
"learning_rate": 4.780334036866997e-05,
"loss": 0.7152,
"step": 570
},
{
"epoch": 10.866510538641686,
"grad_norm": 3.6723790168762207,
"learning_rate": 4.772678842103605e-05,
"loss": 0.679,
"step": 580
},
{
"epoch": 11.053864168618267,
"grad_norm": 3.633692502975464,
"learning_rate": 4.764898879081468e-05,
"loss": 0.6489,
"step": 590
},
{
"epoch": 11.241217798594848,
"grad_norm": 3.9104480743408203,
"learning_rate": 4.756994574914359e-05,
"loss": 0.6116,
"step": 600
},
{
"epoch": 11.428571428571429,
"grad_norm": 3.8203835487365723,
"learning_rate": 4.748966363542285e-05,
"loss": 0.6549,
"step": 610
},
{
"epoch": 11.61592505854801,
"grad_norm": 3.5407750606536865,
"learning_rate": 4.7408146857076566e-05,
"loss": 0.6532,
"step": 620
},
{
"epoch": 11.80327868852459,
"grad_norm": 4.155674457550049,
"learning_rate": 4.732539988931097e-05,
"loss": 0.6684,
"step": 630
},
{
"epoch": 11.99063231850117,
"grad_norm": 4.21943473815918,
"learning_rate": 4.724142727486869e-05,
"loss": 0.683,
"step": 640
},
{
"epoch": 12.177985948477751,
"grad_norm": 3.3667685985565186,
"learning_rate": 4.715623362377939e-05,
"loss": 0.6127,
"step": 650
},
{
"epoch": 12.365339578454332,
"grad_norm": 3.7362210750579834,
"learning_rate": 4.706982361310669e-05,
"loss": 0.606,
"step": 660
},
{
"epoch": 12.552693208430913,
"grad_norm": 3.549915313720703,
"learning_rate": 4.698220198669136e-05,
"loss": 0.6349,
"step": 670
},
{
"epoch": 12.740046838407494,
"grad_norm": 3.360044002532959,
"learning_rate": 4.6893373554890925e-05,
"loss": 0.6335,
"step": 680
},
{
"epoch": 12.927400468384075,
"grad_norm": 3.676515817642212,
"learning_rate": 4.680334319431555e-05,
"loss": 0.6283,
"step": 690
},
{
"epoch": 13.114754098360656,
"grad_norm": 4.325002193450928,
"learning_rate": 4.6712115847560355e-05,
"loss": 0.6248,
"step": 700
},
{
"epoch": 13.302107728337237,
"grad_norm": 4.889411449432373,
"learning_rate": 4.6619696522934024e-05,
"loss": 0.5959,
"step": 710
},
{
"epoch": 13.489461358313818,
"grad_norm": 4.090158939361572,
"learning_rate": 4.652609029418389e-05,
"loss": 0.6068,
"step": 720
},
{
"epoch": 13.676814988290397,
"grad_norm": 3.8901116847991943,
"learning_rate": 4.643130230021737e-05,
"loss": 0.6042,
"step": 730
},
{
"epoch": 13.864168618266978,
"grad_norm": 4.178182125091553,
"learning_rate": 4.6335337744819873e-05,
"loss": 0.6253,
"step": 740
},
{
"epoch": 14.05152224824356,
"grad_norm": 3.4572255611419678,
"learning_rate": 4.6238201896369055e-05,
"loss": 0.6136,
"step": 750
},
{
"epoch": 14.23887587822014,
"grad_norm": 4.382098197937012,
"learning_rate": 4.613990008754565e-05,
"loss": 0.5499,
"step": 760
},
{
"epoch": 14.426229508196721,
"grad_norm": 4.183515548706055,
"learning_rate": 4.6040437715040706e-05,
"loss": 0.5845,
"step": 770
},
{
"epoch": 14.613583138173302,
"grad_norm": 3.2976605892181396,
"learning_rate": 4.593982023925926e-05,
"loss": 0.6097,
"step": 780
},
{
"epoch": 14.800936768149883,
"grad_norm": 4.0663347244262695,
"learning_rate": 4.58380531840206e-05,
"loss": 0.6161,
"step": 790
},
{
"epoch": 14.988290398126464,
"grad_norm": 4.074985980987549,
"learning_rate": 4.573514213625505e-05,
"loss": 0.5597,
"step": 800
},
{
"epoch": 15.175644028103045,
"grad_norm": 4.086116790771484,
"learning_rate": 4.563109274569717e-05,
"loss": 0.5484,
"step": 810
},
{
"epoch": 15.362997658079625,
"grad_norm": 3.6355836391448975,
"learning_rate": 4.552591072457565e-05,
"loss": 0.5561,
"step": 820
},
{
"epoch": 15.550351288056206,
"grad_norm": 4.557271480560303,
"learning_rate": 4.5419601847299706e-05,
"loss": 0.5729,
"step": 830
},
{
"epoch": 15.737704918032787,
"grad_norm": 3.3405730724334717,
"learning_rate": 4.5312171950142034e-05,
"loss": 0.5654,
"step": 840
},
{
"epoch": 15.925058548009368,
"grad_norm": 5.102325439453125,
"learning_rate": 4.5203626930918455e-05,
"loss": 0.5766,
"step": 850
},
{
"epoch": 16.11241217798595,
"grad_norm": 4.394238471984863,
"learning_rate": 4.509397274866409e-05,
"loss": 0.5617,
"step": 860
},
{
"epoch": 16.29976580796253,
"grad_norm": 4.780090808868408,
"learning_rate": 4.498321542330623e-05,
"loss": 0.5363,
"step": 870
},
{
"epoch": 16.48711943793911,
"grad_norm": 3.9079573154449463,
"learning_rate": 4.4871361035333836e-05,
"loss": 0.5387,
"step": 880
},
{
"epoch": 16.67447306791569,
"grad_norm": 4.230076789855957,
"learning_rate": 4.4758415725463746e-05,
"loss": 0.5594,
"step": 890
},
{
"epoch": 16.861826697892273,
"grad_norm": 3.655414581298828,
"learning_rate": 4.464438569430354e-05,
"loss": 0.5556,
"step": 900
},
{
"epoch": 17.049180327868854,
"grad_norm": 3.818207025527954,
"learning_rate": 4.452927720201112e-05,
"loss": 0.5367,
"step": 910
},
{
"epoch": 17.236533957845435,
"grad_norm": 3.827942371368408,
"learning_rate": 4.441309656795106e-05,
"loss": 0.5108,
"step": 920
},
{
"epoch": 17.423887587822016,
"grad_norm": 3.933605194091797,
"learning_rate": 4.4295850170347664e-05,
"loss": 0.5258,
"step": 930
},
{
"epoch": 17.611241217798593,
"grad_norm": 4.577270030975342,
"learning_rate": 4.417754444593478e-05,
"loss": 0.5313,
"step": 940
},
{
"epoch": 17.798594847775174,
"grad_norm": 5.285182476043701,
"learning_rate": 4.40581858896025e-05,
"loss": 0.5421,
"step": 950
},
{
"epoch": 17.985948477751755,
"grad_norm": 4.50776481628418,
"learning_rate": 4.3937781054040505e-05,
"loss": 0.5428,
"step": 960
},
{
"epoch": 18.173302107728336,
"grad_norm": 3.9270503520965576,
"learning_rate": 4.38163365493784e-05,
"loss": 0.4744,
"step": 970
},
{
"epoch": 18.360655737704917,
"grad_norm": 4.346292018890381,
"learning_rate": 4.3693859042822774e-05,
"loss": 0.5177,
"step": 980
},
{
"epoch": 18.548009367681498,
"grad_norm": 3.9130234718322754,
"learning_rate": 4.357035525829123e-05,
"loss": 0.5387,
"step": 990
},
{
"epoch": 18.73536299765808,
"grad_norm": 3.995023250579834,
"learning_rate": 4.344583197604318e-05,
"loss": 0.5071,
"step": 1000
},
{
"epoch": 18.92271662763466,
"grad_norm": 3.8441927433013916,
"learning_rate": 4.3320296032307675e-05,
"loss": 0.5138,
"step": 1010
},
{
"epoch": 19.11007025761124,
"grad_norm": 5.217072010040283,
"learning_rate": 4.319375431890806e-05,
"loss": 0.4962,
"step": 1020
},
{
"epoch": 19.297423887587822,
"grad_norm": 5.450128078460693,
"learning_rate": 4.306621378288364e-05,
"loss": 0.4835,
"step": 1030
},
{
"epoch": 19.484777517564403,
"grad_norm": 3.889098644256592,
"learning_rate": 4.293768142610828e-05,
"loss": 0.499,
"step": 1040
},
{
"epoch": 19.672131147540984,
"grad_norm": 5.706878662109375,
"learning_rate": 4.2808164304906026e-05,
"loss": 0.5214,
"step": 1050
},
{
"epoch": 19.859484777517565,
"grad_norm": 4.337571620941162,
"learning_rate": 4.267766952966369e-05,
"loss": 0.4985,
"step": 1060
},
{
"epoch": 20.046838407494146,
"grad_norm": 4.532181262969971,
"learning_rate": 4.254620426444053e-05,
"loss": 0.5146,
"step": 1070
},
{
"epoch": 20.234192037470727,
"grad_norm": 5.095364570617676,
"learning_rate": 4.241377572657493e-05,
"loss": 0.4821,
"step": 1080
},
{
"epoch": 20.421545667447308,
"grad_norm": 4.10978889465332,
"learning_rate": 4.228039118628816e-05,
"loss": 0.4685,
"step": 1090
},
{
"epoch": 20.60889929742389,
"grad_norm": 3.92051100730896,
"learning_rate": 4.214605796628527e-05,
"loss": 0.4857,
"step": 1100
},
{
"epoch": 20.796252927400467,
"grad_norm": 5.784697532653809,
"learning_rate": 4.2010783441353064e-05,
"loss": 0.478,
"step": 1110
},
{
"epoch": 20.983606557377048,
"grad_norm": 4.860243320465088,
"learning_rate": 4.187457503795527e-05,
"loss": 0.509,
"step": 1120
},
{
"epoch": 21.17096018735363,
"grad_norm": 4.482259750366211,
"learning_rate": 4.173744023382474e-05,
"loss": 0.4508,
"step": 1130
},
{
"epoch": 21.35831381733021,
"grad_norm": 4.613847255706787,
"learning_rate": 4.159938655755306e-05,
"loss": 0.4748,
"step": 1140
},
{
"epoch": 21.54566744730679,
"grad_norm": 5.015346050262451,
"learning_rate": 4.14604215881771e-05,
"loss": 0.4587,
"step": 1150
},
{
"epoch": 21.73302107728337,
"grad_norm": 4.96614933013916,
"learning_rate": 4.1320552954763044e-05,
"loss": 0.4619,
"step": 1160
},
{
"epoch": 21.920374707259953,
"grad_norm": 4.224035739898682,
"learning_rate": 4.117978833598747e-05,
"loss": 0.476,
"step": 1170
},
{
"epoch": 22.107728337236534,
"grad_norm": 4.694319725036621,
"learning_rate": 4.103813545971589e-05,
"loss": 0.4964,
"step": 1180
},
{
"epoch": 22.295081967213115,
"grad_norm": 4.884482383728027,
"learning_rate": 4.089560210257838e-05,
"loss": 0.4527,
"step": 1190
},
{
"epoch": 22.482435597189696,
"grad_norm": 4.385354518890381,
"learning_rate": 4.075219608954278e-05,
"loss": 0.4593,
"step": 1200
},
{
"epoch": 22.669789227166277,
"grad_norm": 4.597926139831543,
"learning_rate": 4.0607925293485e-05,
"loss": 0.4531,
"step": 1210
},
{
"epoch": 22.857142857142858,
"grad_norm": 4.493633270263672,
"learning_rate": 4.046279763475687e-05,
"loss": 0.4357,
"step": 1220
},
{
"epoch": 23.04449648711944,
"grad_norm": 4.796749114990234,
"learning_rate": 4.031682108075129e-05,
"loss": 0.4529,
"step": 1230
},
{
"epoch": 23.23185011709602,
"grad_norm": 4.556844711303711,
"learning_rate": 4.017000364546484e-05,
"loss": 0.4613,
"step": 1240
},
{
"epoch": 23.4192037470726,
"grad_norm": 5.220188140869141,
"learning_rate": 4.00223533890578e-05,
"loss": 0.433,
"step": 1250
},
{
"epoch": 23.60655737704918,
"grad_norm": 5.892832279205322,
"learning_rate": 3.987387841741169e-05,
"loss": 0.4388,
"step": 1260
},
{
"epoch": 23.793911007025763,
"grad_norm": 5.893739700317383,
"learning_rate": 3.972458688168421e-05,
"loss": 0.4542,
"step": 1270
},
{
"epoch": 23.98126463700234,
"grad_norm": 4.80185079574585,
"learning_rate": 3.95744869778618e-05,
"loss": 0.4289,
"step": 1280
},
{
"epoch": 24.16861826697892,
"grad_norm": 4.6050028800964355,
"learning_rate": 3.942358694630967e-05,
"loss": 0.438,
"step": 1290
},
{
"epoch": 24.355971896955502,
"grad_norm": 4.912991046905518,
"learning_rate": 3.927189507131938e-05,
"loss": 0.4329,
"step": 1300
},
{
"epoch": 24.543325526932083,
"grad_norm": 4.563324928283691,
"learning_rate": 3.911941968065408e-05,
"loss": 0.4508,
"step": 1310
},
{
"epoch": 24.730679156908664,
"grad_norm": 5.688429355621338,
"learning_rate": 3.896616914509131e-05,
"loss": 0.4303,
"step": 1320
},
{
"epoch": 24.918032786885245,
"grad_norm": 5.020318984985352,
"learning_rate": 3.881215187796344e-05,
"loss": 0.4255,
"step": 1330
},
{
"epoch": 25.105386416861826,
"grad_norm": 6.469161510467529,
"learning_rate": 3.8657376334695794e-05,
"loss": 0.4206,
"step": 1340
},
{
"epoch": 25.292740046838407,
"grad_norm": 4.912801742553711,
"learning_rate": 3.8501851012342446e-05,
"loss": 0.4545,
"step": 1350
},
{
"epoch": 25.480093676814988,
"grad_norm": 4.866584777832031,
"learning_rate": 3.8345584449119776e-05,
"loss": 0.4167,
"step": 1360
},
{
"epoch": 25.66744730679157,
"grad_norm": 4.946688175201416,
"learning_rate": 3.818858522393764e-05,
"loss": 0.423,
"step": 1370
},
{
"epoch": 25.85480093676815,
"grad_norm": 5.518560886383057,
"learning_rate": 3.80308619559285e-05,
"loss": 0.4393,
"step": 1380
},
{
"epoch": 26.04215456674473,
"grad_norm": 4.3973283767700195,
"learning_rate": 3.787242330397418e-05,
"loss": 0.4142,
"step": 1390
},
{
"epoch": 26.229508196721312,
"grad_norm": 4.848239898681641,
"learning_rate": 3.7713277966230514e-05,
"loss": 0.4099,
"step": 1400
},
{
"epoch": 26.416861826697893,
"grad_norm": 4.581872463226318,
"learning_rate": 3.755343467964981e-05,
"loss": 0.3986,
"step": 1410
},
{
"epoch": 26.604215456674474,
"grad_norm": 4.8950419425964355,
"learning_rate": 3.7392902219501234e-05,
"loss": 0.4239,
"step": 1420
},
{
"epoch": 26.791569086651055,
"grad_norm": 4.911006450653076,
"learning_rate": 3.723168939888901e-05,
"loss": 0.4013,
"step": 1430
},
{
"epoch": 26.978922716627636,
"grad_norm": 5.166593074798584,
"learning_rate": 3.706980506826863e-05,
"loss": 0.4381,
"step": 1440
},
{
"epoch": 27.166276346604217,
"grad_norm": 5.103715896606445,
"learning_rate": 3.690725811496092e-05,
"loss": 0.4018,
"step": 1450
},
{
"epoch": 27.353629976580795,
"grad_norm": 5.886387825012207,
"learning_rate": 3.67440574626642e-05,
"loss": 0.3995,
"step": 1460
},
{
"epoch": 27.540983606557376,
"grad_norm": 5.4808268547058105,
"learning_rate": 3.6580212070964324e-05,
"loss": 0.4004,
"step": 1470
},
{
"epoch": 27.728337236533957,
"grad_norm": 4.735198020935059,
"learning_rate": 3.6415730934842827e-05,
"loss": 0.3999,
"step": 1480
},
{
"epoch": 27.915690866510538,
"grad_norm": 5.017817497253418,
"learning_rate": 3.625062308418312e-05,
"loss": 0.4149,
"step": 1490
},
{
"epoch": 28.10304449648712,
"grad_norm": 5.427640914916992,
"learning_rate": 3.608489758327472e-05,
"loss": 0.4194,
"step": 1500
},
{
"epoch": 28.2903981264637,
"grad_norm": 5.762901306152344,
"learning_rate": 3.5918563530315664e-05,
"loss": 0.3852,
"step": 1510
},
{
"epoch": 28.47775175644028,
"grad_norm": 4.809139728546143,
"learning_rate": 3.575163005691302e-05,
"loss": 0.3858,
"step": 1520
},
{
"epoch": 28.66510538641686,
"grad_norm": 5.195406436920166,
"learning_rate": 3.5584106327581536e-05,
"loss": 0.3931,
"step": 1530
},
{
"epoch": 28.852459016393443,
"grad_norm": 5.359652996063232,
"learning_rate": 3.541600153924058e-05,
"loss": 0.4196,
"step": 1540
},
{
"epoch": 29.039812646370024,
"grad_norm": 4.440913200378418,
"learning_rate": 3.524732492070915e-05,
"loss": 0.3731,
"step": 1550
},
{
"epoch": 29.227166276346605,
"grad_norm": 4.653567790985107,
"learning_rate": 3.507808573219931e-05,
"loss": 0.3628,
"step": 1560
},
{
"epoch": 29.414519906323186,
"grad_norm": 6.330109119415283,
"learning_rate": 3.4908293264807734e-05,
"loss": 0.4074,
"step": 1570
},
{
"epoch": 29.601873536299767,
"grad_norm": 4.850047588348389,
"learning_rate": 3.473795684000569e-05,
"loss": 0.3495,
"step": 1580
},
{
"epoch": 29.789227166276348,
"grad_norm": 5.027477264404297,
"learning_rate": 3.456708580912725e-05,
"loss": 0.409,
"step": 1590
},
{
"epoch": 29.97658079625293,
"grad_norm": 5.475801467895508,
"learning_rate": 3.4395689552855955e-05,
"loss": 0.3954,
"step": 1600
},
{
"epoch": 30.16393442622951,
"grad_norm": 4.786725044250488,
"learning_rate": 3.4223777480709805e-05,
"loss": 0.3666,
"step": 1610
},
{
"epoch": 30.35128805620609,
"grad_norm": 6.034923076629639,
"learning_rate": 3.4051359030524654e-05,
"loss": 0.3557,
"step": 1620
},
{
"epoch": 30.538641686182668,
"grad_norm": 5.1971755027771,
"learning_rate": 3.387844366793614e-05,
"loss": 0.3563,
"step": 1630
},
{
"epoch": 30.72599531615925,
"grad_norm": 5.740716457366943,
"learning_rate": 3.3705040885859975e-05,
"loss": 0.3874,
"step": 1640
},
{
"epoch": 30.91334894613583,
"grad_norm": 5.543055057525635,
"learning_rate": 3.3531160203970805e-05,
"loss": 0.4104,
"step": 1650
},
{
"epoch": 31.10070257611241,
"grad_norm": 4.964486598968506,
"learning_rate": 3.335681116817963e-05,
"loss": 0.3809,
"step": 1660
},
{
"epoch": 31.288056206088992,
"grad_norm": 5.344038963317871,
"learning_rate": 3.318200335010967e-05,
"loss": 0.3536,
"step": 1670
},
{
"epoch": 31.475409836065573,
"grad_norm": 5.5590901374816895,
"learning_rate": 3.300674634657094e-05,
"loss": 0.3613,
"step": 1680
},
{
"epoch": 31.662763466042154,
"grad_norm": 5.377177715301514,
"learning_rate": 3.28310497790334e-05,
"loss": 0.3828,
"step": 1690
},
{
"epoch": 31.850117096018735,
"grad_norm": 5.412164688110352,
"learning_rate": 3.265492329309867e-05,
"loss": 0.3481,
"step": 1700
},
{
"epoch": 32.03747072599531,
"grad_norm": 4.8478593826293945,
"learning_rate": 3.247837655797061e-05,
"loss": 0.3609,
"step": 1710
},
{
"epoch": 32.2248243559719,
"grad_norm": 4.969062328338623,
"learning_rate": 3.2301419265924395e-05,
"loss": 0.3319,
"step": 1720
},
{
"epoch": 32.412177985948475,
"grad_norm": 5.705166816711426,
"learning_rate": 3.212406113177445e-05,
"loss": 0.3464,
"step": 1730
},
{
"epoch": 32.59953161592506,
"grad_norm": 5.679583549499512,
"learning_rate": 3.19463118923411e-05,
"loss": 0.3518,
"step": 1740
},
{
"epoch": 32.78688524590164,
"grad_norm": 5.57464075088501,
"learning_rate": 3.1768181305916066e-05,
"loss": 0.3644,
"step": 1750
},
{
"epoch": 32.97423887587822,
"grad_norm": 5.604707717895508,
"learning_rate": 3.158967915172669e-05,
"loss": 0.3856,
"step": 1760
},
{
"epoch": 33.1615925058548,
"grad_norm": 4.796475887298584,
"learning_rate": 3.1410815229399116e-05,
"loss": 0.349,
"step": 1770
},
{
"epoch": 33.34894613583138,
"grad_norm": 5.308904647827148,
"learning_rate": 3.123159935842024e-05,
"loss": 0.3319,
"step": 1780
},
{
"epoch": 33.53629976580796,
"grad_norm": 5.319141387939453,
"learning_rate": 3.1052041377598674e-05,
"loss": 0.3403,
"step": 1790
},
{
"epoch": 33.723653395784545,
"grad_norm": 6.2813496589660645,
"learning_rate": 3.0872151144524595e-05,
"loss": 0.331,
"step": 1800
},
{
"epoch": 33.91100702576112,
"grad_norm": 6.759060859680176,
"learning_rate": 3.069193853502855e-05,
"loss": 0.3683,
"step": 1810
},
{
"epoch": 34.09836065573771,
"grad_norm": 5.812283515930176,
"learning_rate": 3.0511413442639296e-05,
"loss": 0.3389,
"step": 1820
},
{
"epoch": 34.285714285714285,
"grad_norm": 5.7895026206970215,
"learning_rate": 3.0330585778040677e-05,
"loss": 0.3302,
"step": 1830
},
{
"epoch": 34.47306791569087,
"grad_norm": 5.957363605499268,
"learning_rate": 3.014946546852746e-05,
"loss": 0.3334,
"step": 1840
},
{
"epoch": 34.66042154566745,
"grad_norm": 5.722705364227295,
"learning_rate": 2.996806245746044e-05,
"loss": 0.3419,
"step": 1850
},
{
"epoch": 34.84777517564403,
"grad_norm": 6.884836196899414,
"learning_rate": 2.978638670372047e-05,
"loss": 0.3375,
"step": 1860
},
{
"epoch": 35.03512880562061,
"grad_norm": 4.799129962921143,
"learning_rate": 2.960444818116176e-05,
"loss": 0.3473,
"step": 1870
},
{
"epoch": 35.222482435597186,
"grad_norm": 5.28724479675293,
"learning_rate": 2.9422256878064325e-05,
"loss": 0.2882,
"step": 1880
},
{
"epoch": 35.40983606557377,
"grad_norm": 5.755520343780518,
"learning_rate": 2.923982279658564e-05,
"loss": 0.3336,
"step": 1890
},
{
"epoch": 35.59718969555035,
"grad_norm": 5.549156188964844,
"learning_rate": 2.9057155952211502e-05,
"loss": 0.3487,
"step": 1900
},
{
"epoch": 35.78454332552693,
"grad_norm": 5.643553256988525,
"learning_rate": 2.8874266373206216e-05,
"loss": 0.3483,
"step": 1910
},
{
"epoch": 35.97189695550351,
"grad_norm": 5.7322540283203125,
"learning_rate": 2.8691164100062034e-05,
"loss": 0.3339,
"step": 1920
},
{
"epoch": 36.159250585480095,
"grad_norm": 9.893467903137207,
"learning_rate": 2.8507859184947957e-05,
"loss": 0.3177,
"step": 1930
},
{
"epoch": 36.34660421545667,
"grad_norm": 4.880067348480225,
"learning_rate": 2.8324361691157858e-05,
"loss": 0.3103,
"step": 1940
},
{
"epoch": 36.53395784543326,
"grad_norm": 5.725404262542725,
"learning_rate": 2.8140681692558035e-05,
"loss": 0.3145,
"step": 1950
},
{
"epoch": 36.721311475409834,
"grad_norm": 5.862415313720703,
"learning_rate": 2.7956829273034148e-05,
"loss": 0.3246,
"step": 1960
},
{
"epoch": 36.90866510538642,
"grad_norm": 6.573834419250488,
"learning_rate": 2.7772814525937635e-05,
"loss": 0.3479,
"step": 1970
},
{
"epoch": 37.096018735362996,
"grad_norm": 6.182538032531738,
"learning_rate": 2.7588647553531576e-05,
"loss": 0.324,
"step": 1980
},
{
"epoch": 37.28337236533958,
"grad_norm": 5.400746822357178,
"learning_rate": 2.740433846643612e-05,
"loss": 0.3064,
"step": 1990
},
{
"epoch": 37.47072599531616,
"grad_norm": 5.840080738067627,
"learning_rate": 2.7219897383073373e-05,
"loss": 0.3211,
"step": 2000
},
{
"epoch": 37.65807962529274,
"grad_norm": 5.707023620605469,
"learning_rate": 2.7035334429111958e-05,
"loss": 0.3285,
"step": 2010
},
{
"epoch": 37.84543325526932,
"grad_norm": 5.929535865783691,
"learning_rate": 2.6850659736911073e-05,
"loss": 0.3126,
"step": 2020
},
{
"epoch": 38.032786885245905,
"grad_norm": 4.90598726272583,
"learning_rate": 2.6665883444964278e-05,
"loss": 0.3101,
"step": 2030
},
{
"epoch": 38.22014051522248,
"grad_norm": 6.5826616287231445,
"learning_rate": 2.648101569734286e-05,
"loss": 0.3216,
"step": 2040
},
{
"epoch": 38.40749414519907,
"grad_norm": 5.600116729736328,
"learning_rate": 2.629606664313896e-05,
"loss": 0.2956,
"step": 2050
},
{
"epoch": 38.594847775175644,
"grad_norm": 5.065032482147217,
"learning_rate": 2.6111046435908383e-05,
"loss": 0.2983,
"step": 2060
},
{
"epoch": 38.78220140515222,
"grad_norm": 5.835258483886719,
"learning_rate": 2.5925965233113174e-05,
"loss": 0.3178,
"step": 2070
},
{
"epoch": 38.969555035128806,
"grad_norm": 6.896608352661133,
"learning_rate": 2.5740833195563996e-05,
"loss": 0.309,
"step": 2080
},
{
"epoch": 39.156908665105384,
"grad_norm": 5.803635120391846,
"learning_rate": 2.5555660486862294e-05,
"loss": 0.3285,
"step": 2090
},
{
"epoch": 39.34426229508197,
"grad_norm": 6.226255416870117,
"learning_rate": 2.537045727284232e-05,
"loss": 0.2969,
"step": 2100
},
{
"epoch": 39.531615925058546,
"grad_norm": 5.5187201499938965,
"learning_rate": 2.5185233721013057e-05,
"loss": 0.2787,
"step": 2110
},
{
"epoch": 39.71896955503513,
"grad_norm": 5.887444496154785,
"learning_rate": 2.5e-05,
"loss": 0.2992,
"step": 2120
},
{
"epoch": 39.90632318501171,
"grad_norm": 5.903340816497803,
"learning_rate": 2.481476627898695e-05,
"loss": 0.3051,
"step": 2130
},
{
"epoch": 40.09367681498829,
"grad_norm": 5.660261631011963,
"learning_rate": 2.4629542727157684e-05,
"loss": 0.281,
"step": 2140
},
{
"epoch": 40.28103044496487,
"grad_norm": 4.755375862121582,
"learning_rate": 2.444433951313772e-05,
"loss": 0.2615,
"step": 2150
},
{
"epoch": 40.468384074941454,
"grad_norm": 5.870564937591553,
"learning_rate": 2.4259166804436006e-05,
"loss": 0.3151,
"step": 2160
},
{
"epoch": 40.65573770491803,
"grad_norm": 6.845561504364014,
"learning_rate": 2.407403476688683e-05,
"loss": 0.3095,
"step": 2170
},
{
"epoch": 40.843091334894616,
"grad_norm": 4.970867156982422,
"learning_rate": 2.388895356409162e-05,
"loss": 0.2828,
"step": 2180
},
{
"epoch": 41.030444964871194,
"grad_norm": 5.148143768310547,
"learning_rate": 2.3703933356861048e-05,
"loss": 0.3038,
"step": 2190
},
{
"epoch": 41.21779859484778,
"grad_norm": 5.9692583084106445,
"learning_rate": 2.3518984302657146e-05,
"loss": 0.2893,
"step": 2200
},
{
"epoch": 41.405152224824356,
"grad_norm": 6.505251884460449,
"learning_rate": 2.3334116555035724e-05,
"loss": 0.288,
"step": 2210
},
{
"epoch": 41.59250585480093,
"grad_norm": 5.992464542388916,
"learning_rate": 2.314934026308893e-05,
"loss": 0.2905,
"step": 2220
},
{
"epoch": 41.77985948477752,
"grad_norm": 5.301249980926514,
"learning_rate": 2.296466557088805e-05,
"loss": 0.2704,
"step": 2230
},
{
"epoch": 41.967213114754095,
"grad_norm": 5.807764053344727,
"learning_rate": 2.2780102616926633e-05,
"loss": 0.2902,
"step": 2240
},
{
"epoch": 42.15456674473068,
"grad_norm": 5.2341742515563965,
"learning_rate": 2.259566153356389e-05,
"loss": 0.2753,
"step": 2250
},
{
"epoch": 42.34192037470726,
"grad_norm": 5.364047527313232,
"learning_rate": 2.2411352446468426e-05,
"loss": 0.2797,
"step": 2260
},
{
"epoch": 42.52927400468384,
"grad_norm": 5.803712368011475,
"learning_rate": 2.2227185474062377e-05,
"loss": 0.2825,
"step": 2270
},
{
"epoch": 42.71662763466042,
"grad_norm": 5.672751426696777,
"learning_rate": 2.2043170726965858e-05,
"loss": 0.2881,
"step": 2280
},
{
"epoch": 42.903981264637004,
"grad_norm": 5.412528991699219,
"learning_rate": 2.1859318307441967e-05,
"loss": 0.2791,
"step": 2290
},
{
"epoch": 43.09133489461358,
"grad_norm": 5.854480743408203,
"learning_rate": 2.1675638308842145e-05,
"loss": 0.2962,
"step": 2300
},
{
"epoch": 43.278688524590166,
"grad_norm": 5.328369617462158,
"learning_rate": 2.1492140815052053e-05,
"loss": 0.2699,
"step": 2310
},
{
"epoch": 43.46604215456674,
"grad_norm": 4.856033802032471,
"learning_rate": 2.1308835899937972e-05,
"loss": 0.2734,
"step": 2320
},
{
"epoch": 43.65339578454333,
"grad_norm": 6.26331090927124,
"learning_rate": 2.1125733626793793e-05,
"loss": 0.275,
"step": 2330
},
{
"epoch": 43.840749414519905,
"grad_norm": 6.019165992736816,
"learning_rate": 2.09428440477885e-05,
"loss": 0.3627,
"step": 2340
},
{
"epoch": 44.02810304449649,
"grad_norm": 5.1247711181640625,
"learning_rate": 2.0760177203414368e-05,
"loss": 0.2627,
"step": 2350
},
{
"epoch": 44.21545667447307,
"grad_norm": 5.77355432510376,
"learning_rate": 2.0577743121935684e-05,
"loss": 0.2523,
"step": 2360
},
{
"epoch": 44.40281030444965,
"grad_norm": 6.598211765289307,
"learning_rate": 2.0395551818838247e-05,
"loss": 0.2882,
"step": 2370
},
{
"epoch": 44.59016393442623,
"grad_norm": 6.168797969818115,
"learning_rate": 2.0213613296279533e-05,
"loss": 0.2739,
"step": 2380
},
{
"epoch": 44.777517564402814,
"grad_norm": 5.739145278930664,
"learning_rate": 2.003193754253957e-05,
"loss": 0.2569,
"step": 2390
},
{
"epoch": 44.96487119437939,
"grad_norm": 5.858418941497803,
"learning_rate": 1.9850534531472546e-05,
"loss": 0.2575,
"step": 2400
},
{
"epoch": 45.15222482435597,
"grad_norm": 5.349724769592285,
"learning_rate": 1.9669414221959332e-05,
"loss": 0.2596,
"step": 2410
},
{
"epoch": 45.33957845433255,
"grad_norm": 6.348044395446777,
"learning_rate": 1.9488586557360703e-05,
"loss": 0.2643,
"step": 2420
},
{
"epoch": 45.52693208430913,
"grad_norm": 5.21057653427124,
"learning_rate": 1.930806146497146e-05,
"loss": 0.2649,
"step": 2430
},
{
"epoch": 45.714285714285715,
"grad_norm": 6.046148300170898,
"learning_rate": 1.912784885547541e-05,
"loss": 0.2688,
"step": 2440
},
{
"epoch": 45.90163934426229,
"grad_norm": 5.811086177825928,
"learning_rate": 1.8947958622401328e-05,
"loss": 0.2547,
"step": 2450
},
{
"epoch": 46.08899297423888,
"grad_norm": 6.68256950378418,
"learning_rate": 1.876840064157976e-05,
"loss": 0.2611,
"step": 2460
},
{
"epoch": 46.276346604215455,
"grad_norm": 6.05044412612915,
"learning_rate": 1.8589184770600893e-05,
"loss": 0.2308,
"step": 2470
},
{
"epoch": 46.46370023419204,
"grad_norm": 5.7417073249816895,
"learning_rate": 1.8410320848273315e-05,
"loss": 0.2572,
"step": 2480
},
{
"epoch": 46.65105386416862,
"grad_norm": 5.557978630065918,
"learning_rate": 1.8231818694083937e-05,
"loss": 0.2689,
"step": 2490
},
{
"epoch": 46.8384074941452,
"grad_norm": 5.32368278503418,
"learning_rate": 1.8053688107658908e-05,
"loss": 0.2518,
"step": 2500
},
{
"epoch": 47.02576112412178,
"grad_norm": 5.275130748748779,
"learning_rate": 1.7875938868225563e-05,
"loss": 0.2519,
"step": 2510
},
{
"epoch": 47.21311475409836,
"grad_norm": 5.496984004974365,
"learning_rate": 1.769858073407561e-05,
"loss": 0.2425,
"step": 2520
},
{
"epoch": 47.40046838407494,
"grad_norm": 5.19797420501709,
"learning_rate": 1.752162344202939e-05,
"loss": 0.2665,
"step": 2530
},
{
"epoch": 47.587822014051525,
"grad_norm": 5.920257091522217,
"learning_rate": 1.734507670690133e-05,
"loss": 0.2543,
"step": 2540
},
{
"epoch": 47.7751756440281,
"grad_norm": 5.570456027984619,
"learning_rate": 1.7168950220966614e-05,
"loss": 0.2468,
"step": 2550
},
{
"epoch": 47.96252927400468,
"grad_norm": 6.8460211753845215,
"learning_rate": 1.6993253653429063e-05,
"loss": 0.2541,
"step": 2560
},
{
"epoch": 48.149882903981265,
"grad_norm": 6.266761779785156,
"learning_rate": 1.681799664989033e-05,
"loss": 0.2497,
"step": 2570
},
{
"epoch": 48.33723653395784,
"grad_norm": 5.843891143798828,
"learning_rate": 1.6643188831820375e-05,
"loss": 0.2472,
"step": 2580
},
{
"epoch": 48.52459016393443,
"grad_norm": 5.972542762756348,
"learning_rate": 1.64688397960292e-05,
"loss": 0.2501,
"step": 2590
},
{
"epoch": 48.711943793911004,
"grad_norm": 5.9259724617004395,
"learning_rate": 1.6294959114140034e-05,
"loss": 0.2345,
"step": 2600
},
{
"epoch": 48.89929742388759,
"grad_norm": 6.9172492027282715,
"learning_rate": 1.6121556332063862e-05,
"loss": 0.2492,
"step": 2610
},
{
"epoch": 49.086651053864166,
"grad_norm": 5.66576623916626,
"learning_rate": 1.5948640969475346e-05,
"loss": 0.2464,
"step": 2620
},
{
"epoch": 49.27400468384075,
"grad_norm": 5.968489646911621,
"learning_rate": 1.5776222519290208e-05,
"loss": 0.2453,
"step": 2630
},
{
"epoch": 49.46135831381733,
"grad_norm": 5.3877739906311035,
"learning_rate": 1.560431044714405e-05,
"loss": 0.2331,
"step": 2640
},
{
"epoch": 49.64871194379391,
"grad_norm": 6.003279685974121,
"learning_rate": 1.5432914190872757e-05,
"loss": 0.2451,
"step": 2650
},
{
"epoch": 49.83606557377049,
"grad_norm": 5.7422709465026855,
"learning_rate": 1.5262043159994317e-05,
"loss": 0.2421,
"step": 2660
},
{
"epoch": 50.023419203747075,
"grad_norm": 5.42122745513916,
"learning_rate": 1.5091706735192268e-05,
"loss": 0.2502,
"step": 2670
},
{
"epoch": 50.21077283372365,
"grad_norm": 6.197154998779297,
"learning_rate": 1.49219142678007e-05,
"loss": 0.2319,
"step": 2680
},
{
"epoch": 50.39812646370024,
"grad_norm": 6.868821620941162,
"learning_rate": 1.4752675079290851e-05,
"loss": 0.2446,
"step": 2690
},
{
"epoch": 50.585480093676814,
"grad_norm": 5.866207599639893,
"learning_rate": 1.4583998460759424e-05,
"loss": 0.236,
"step": 2700
},
{
"epoch": 50.7728337236534,
"grad_norm": 5.33125638961792,
"learning_rate": 1.4415893672418462e-05,
"loss": 0.2392,
"step": 2710
},
{
"epoch": 50.960187353629976,
"grad_norm": 5.089175701141357,
"learning_rate": 1.4248369943086998e-05,
"loss": 0.2336,
"step": 2720
},
{
"epoch": 51.14754098360656,
"grad_norm": 6.228028774261475,
"learning_rate": 1.4081436469684339e-05,
"loss": 0.2348,
"step": 2730
},
{
"epoch": 51.33489461358314,
"grad_norm": 5.978231906890869,
"learning_rate": 1.3915102416725287e-05,
"loss": 0.2337,
"step": 2740
},
{
"epoch": 51.522248243559716,
"grad_norm": 5.551085472106934,
"learning_rate": 1.3749376915816886e-05,
"loss": 0.2258,
"step": 2750
},
{
"epoch": 51.7096018735363,
"grad_norm": 6.166746616363525,
"learning_rate": 1.3584269065157174e-05,
"loss": 0.2436,
"step": 2760
},
{
"epoch": 51.89695550351288,
"grad_norm": 6.301324844360352,
"learning_rate": 1.3419787929035682e-05,
"loss": 0.2402,
"step": 2770
},
{
"epoch": 52.08430913348946,
"grad_norm": 4.700679302215576,
"learning_rate": 1.3255942537335805e-05,
"loss": 0.2167,
"step": 2780
},
{
"epoch": 52.27166276346604,
"grad_norm": 5.628973007202148,
"learning_rate": 1.3092741885039087e-05,
"loss": 0.2298,
"step": 2790
},
{
"epoch": 52.459016393442624,
"grad_norm": 5.110661029815674,
"learning_rate": 1.2930194931731382e-05,
"loss": 0.2329,
"step": 2800
},
{
"epoch": 52.6463700234192,
"grad_norm": 6.139814853668213,
"learning_rate": 1.2768310601110994e-05,
"loss": 0.2341,
"step": 2810
},
{
"epoch": 52.833723653395786,
"grad_norm": 5.745288848876953,
"learning_rate": 1.2607097780498772e-05,
"loss": 0.2203,
"step": 2820
},
{
"epoch": 53.021077283372364,
"grad_norm": 4.815990447998047,
"learning_rate": 1.2446565320350185e-05,
"loss": 0.2309,
"step": 2830
},
{
"epoch": 53.20843091334895,
"grad_norm": 5.185337543487549,
"learning_rate": 1.2286722033769493e-05,
"loss": 0.2125,
"step": 2840
},
{
"epoch": 53.395784543325526,
"grad_norm": 5.8394904136657715,
"learning_rate": 1.2127576696025828e-05,
"loss": 0.2138,
"step": 2850
},
{
"epoch": 53.58313817330211,
"grad_norm": 5.652061462402344,
"learning_rate": 1.1969138044071501e-05,
"loss": 0.2351,
"step": 2860
},
{
"epoch": 53.77049180327869,
"grad_norm": 5.9499897956848145,
"learning_rate": 1.1811414776062366e-05,
"loss": 0.2328,
"step": 2870
},
{
"epoch": 53.95784543325527,
"grad_norm": 5.064215660095215,
"learning_rate": 1.1654415550880243e-05,
"loss": 0.2259,
"step": 2880
},
{
"epoch": 54.14519906323185,
"grad_norm": 5.09717321395874,
"learning_rate": 1.149814898765755e-05,
"loss": 0.2289,
"step": 2890
},
{
"epoch": 54.332552693208434,
"grad_norm": 6.277153491973877,
"learning_rate": 1.1342623665304209e-05,
"loss": 0.2218,
"step": 2900
},
{
"epoch": 54.51990632318501,
"grad_norm": 6.414435863494873,
"learning_rate": 1.1187848122036563e-05,
"loss": 0.2083,
"step": 2910
},
{
"epoch": 54.70725995316159,
"grad_norm": 5.3766069412231445,
"learning_rate": 1.1033830854908691e-05,
"loss": 0.2259,
"step": 2920
},
{
"epoch": 54.894613583138174,
"grad_norm": 5.645792007446289,
"learning_rate": 1.088058031934592e-05,
"loss": 0.2237,
"step": 2930
},
{
"epoch": 55.08196721311475,
"grad_norm": 5.73775053024292,
"learning_rate": 1.0728104928680624e-05,
"loss": 0.2135,
"step": 2940
},
{
"epoch": 55.269320843091336,
"grad_norm": 5.055363655090332,
"learning_rate": 1.0576413053690327e-05,
"loss": 0.214,
"step": 2950
},
{
"epoch": 55.45667447306791,
"grad_norm": 5.82523775100708,
"learning_rate": 1.0425513022138203e-05,
"loss": 0.2245,
"step": 2960
},
{
"epoch": 55.6440281030445,
"grad_norm": 5.7269287109375,
"learning_rate": 1.0275413118315799e-05,
"loss": 0.2157,
"step": 2970
},
{
"epoch": 55.831381733021075,
"grad_norm": 5.7951178550720215,
"learning_rate": 1.0126121582588316e-05,
"loss": 0.211,
"step": 2980
},
{
"epoch": 56.01873536299766,
"grad_norm": 4.387237548828125,
"learning_rate": 9.977646610942202e-06,
"loss": 0.203,
"step": 2990
},
{
"epoch": 56.20608899297424,
"grad_norm": 6.9729485511779785,
"learning_rate": 9.829996354535172e-06,
"loss": 0.199,
"step": 3000
},
{
"epoch": 56.39344262295082,
"grad_norm": 5.916283130645752,
"learning_rate": 9.683178919248712e-06,
"loss": 0.2145,
"step": 3010
},
{
"epoch": 56.5807962529274,
"grad_norm": 6.08202600479126,
"learning_rate": 9.53720236524313e-06,
"loss": 0.2071,
"step": 3020
},
{
"epoch": 56.768149882903984,
"grad_norm": 5.249958515167236,
"learning_rate": 9.392074706515003e-06,
"loss": 0.2208,
"step": 3030
},
{
"epoch": 56.95550351288056,
"grad_norm": 5.584343433380127,
"learning_rate": 9.247803910457226e-06,
"loss": 0.2224,
"step": 3040
},
{
"epoch": 57.142857142857146,
"grad_norm": 5.786952018737793,
"learning_rate": 9.104397897421623e-06,
"loss": 0.1905,
"step": 3050
},
{
"epoch": 57.33021077283372,
"grad_norm": 5.917386054992676,
"learning_rate": 8.96186454028412e-06,
"loss": 0.2157,
"step": 3060
},
{
"epoch": 57.51756440281031,
"grad_norm": 7.27882719039917,
"learning_rate": 8.820211664012532e-06,
"loss": 0.2165,
"step": 3070
},
{
"epoch": 57.704918032786885,
"grad_norm": 5.488128662109375,
"learning_rate": 8.679447045236962e-06,
"loss": 0.1975,
"step": 3080
},
{
"epoch": 57.89227166276346,
"grad_norm": 7.09759521484375,
"learning_rate": 8.539578411822901e-06,
"loss": 0.2117,
"step": 3090
},
{
"epoch": 58.07962529274005,
"grad_norm": 5.4233832359313965,
"learning_rate": 8.400613442446948e-06,
"loss": 0.204,
"step": 3100
},
{
"epoch": 58.266978922716625,
"grad_norm": 5.012626647949219,
"learning_rate": 8.262559766175254e-06,
"loss": 0.2188,
"step": 3110
},
{
"epoch": 58.45433255269321,
"grad_norm": 5.272639751434326,
"learning_rate": 8.125424962044742e-06,
"loss": 0.2095,
"step": 3120
},
{
"epoch": 58.64168618266979,
"grad_norm": 5.037263870239258,
"learning_rate": 7.989216558646942e-06,
"loss": 0.2075,
"step": 3130
},
{
"epoch": 58.82903981264637,
"grad_norm": 4.957757949829102,
"learning_rate": 7.853942033714736e-06,
"loss": 0.2034,
"step": 3140
},
{
"epoch": 59.01639344262295,
"grad_norm": 5.24732780456543,
"learning_rate": 7.719608813711848e-06,
"loss": 0.195,
"step": 3150
},
{
"epoch": 59.20374707259953,
"grad_norm": 6.088141441345215,
"learning_rate": 7.586224273425082e-06,
"loss": 0.1972,
"step": 3160
},
{
"epoch": 59.39110070257611,
"grad_norm": 6.778179168701172,
"learning_rate": 7.453795735559471e-06,
"loss": 0.2012,
"step": 3170
},
{
"epoch": 59.578454332552695,
"grad_norm": 5.891854763031006,
"learning_rate": 7.3223304703363135e-06,
"loss": 0.1973,
"step": 3180
},
{
"epoch": 59.76580796252927,
"grad_norm": 5.353849411010742,
"learning_rate": 7.191835695093982e-06,
"loss": 0.2063,
"step": 3190
},
{
"epoch": 59.95316159250586,
"grad_norm": 6.351828098297119,
"learning_rate": 7.062318573891716e-06,
"loss": 0.2082,
"step": 3200
},
{
"epoch": 60.140515222482435,
"grad_norm": 5.508406162261963,
"learning_rate": 6.933786217116364e-06,
"loss": 0.1927,
"step": 3210
},
{
"epoch": 60.32786885245902,
"grad_norm": 5.679818153381348,
"learning_rate": 6.806245681091944e-06,
"loss": 0.2101,
"step": 3220
},
{
"epoch": 60.5152224824356,
"grad_norm": 6.534885406494141,
"learning_rate": 6.679703967692322e-06,
"loss": 0.5943,
"step": 3230
},
{
"epoch": 60.70257611241218,
"grad_norm": 6.105801582336426,
"learning_rate": 6.5541680239568165e-06,
"loss": 0.2805,
"step": 3240
},
{
"epoch": 60.88992974238876,
"grad_norm": 6.5821027755737305,
"learning_rate": 6.429644741708779e-06,
"loss": 0.206,
"step": 3250
},
{
"epoch": 61.077283372365336,
"grad_norm": 5.045831203460693,
"learning_rate": 6.3061409571772254e-06,
"loss": 0.1883,
"step": 3260
},
{
"epoch": 61.26463700234192,
"grad_norm": 5.163257122039795,
"learning_rate": 6.183663450621607e-06,
"loss": 0.1979,
"step": 3270
},
{
"epoch": 61.4519906323185,
"grad_norm": 6.092082500457764,
"learning_rate": 6.062218945959497e-06,
"loss": 0.2002,
"step": 3280
},
{
"epoch": 61.63934426229508,
"grad_norm": 5.395636558532715,
"learning_rate": 5.941814110397503e-06,
"loss": 0.2,
"step": 3290
},
{
"epoch": 61.82669789227166,
"grad_norm": 5.0518903732299805,
"learning_rate": 5.822455554065217e-06,
"loss": 0.202,
"step": 3300
},
{
"epoch": 62.014051522248245,
"grad_norm": 5.086590766906738,
"learning_rate": 5.704149829652342e-06,
"loss": 0.1903,
"step": 3310
},
{
"epoch": 62.20140515222482,
"grad_norm": 5.284370422363281,
"learning_rate": 5.586903432048943e-06,
"loss": 0.2081,
"step": 3320
},
{
"epoch": 62.38875878220141,
"grad_norm": 5.229597568511963,
"learning_rate": 5.4707227979888834e-06,
"loss": 0.1881,
"step": 3330
},
{
"epoch": 62.576112412177984,
"grad_norm": 5.299145698547363,
"learning_rate": 5.355614305696468e-06,
"loss": 0.192,
"step": 3340
},
{
"epoch": 62.76346604215457,
"grad_norm": 5.264816761016846,
"learning_rate": 5.241584274536259e-06,
"loss": 0.1923,
"step": 3350
},
{
"epoch": 62.950819672131146,
"grad_norm": 5.120273590087891,
"learning_rate": 5.128638964666166e-06,
"loss": 0.1954,
"step": 3360
},
{
"epoch": 63.13817330210773,
"grad_norm": 5.393264293670654,
"learning_rate": 5.016784576693781e-06,
"loss": 0.2009,
"step": 3370
},
{
"epoch": 63.32552693208431,
"grad_norm": 6.210027694702148,
"learning_rate": 4.906027251335918e-06,
"loss": 0.1969,
"step": 3380
},
{
"epoch": 63.51288056206089,
"grad_norm": 4.836513042449951,
"learning_rate": 4.796373069081547e-06,
"loss": 0.189,
"step": 3390
},
{
"epoch": 63.70023419203747,
"grad_norm": 5.6751556396484375,
"learning_rate": 4.687828049857967e-06,
"loss": 0.1785,
"step": 3400
},
{
"epoch": 63.887587822014055,
"grad_norm": 5.045291423797607,
"learning_rate": 4.580398152700305e-06,
"loss": 0.1895,
"step": 3410
},
{
"epoch": 64.07494145199063,
"grad_norm": 5.037576198577881,
"learning_rate": 4.474089275424351e-06,
"loss": 0.1897,
"step": 3420
},
{
"epoch": 64.26229508196721,
"grad_norm": 5.322866916656494,
"learning_rate": 4.368907254302837e-06,
"loss": 0.1786,
"step": 3430
},
{
"epoch": 64.4496487119438,
"grad_norm": 5.449312210083008,
"learning_rate": 4.264857863744956e-06,
"loss": 0.1931,
"step": 3440
},
{
"epoch": 64.63700234192038,
"grad_norm": 5.3389177322387695,
"learning_rate": 4.161946815979403e-06,
"loss": 0.1919,
"step": 3450
},
{
"epoch": 64.82435597189695,
"grad_norm": 6.1554789543151855,
"learning_rate": 4.060179760740751e-06,
"loss": 0.1958,
"step": 3460
},
{
"epoch": 65.01170960187353,
"grad_norm": 4.999247074127197,
"learning_rate": 3.9595622849593005e-06,
"loss": 0.1955,
"step": 3470
},
{
"epoch": 65.19906323185012,
"grad_norm": 5.010692596435547,
"learning_rate": 3.860099912454346e-06,
"loss": 0.1883,
"step": 3480
},
{
"epoch": 65.3864168618267,
"grad_norm": 5.899059772491455,
"learning_rate": 3.7617981036309537e-06,
"loss": 0.1997,
"step": 3490
},
{
"epoch": 65.57377049180327,
"grad_norm": 5.52278995513916,
"learning_rate": 3.6646622551801345e-06,
"loss": 0.1814,
"step": 3500
},
{
"epoch": 65.76112412177986,
"grad_norm": 5.3710618019104,
"learning_rate": 3.568697699782625e-06,
"loss": 0.1923,
"step": 3510
},
{
"epoch": 65.94847775175644,
"grad_norm": 5.129755973815918,
"learning_rate": 3.4739097058161114e-06,
"loss": 0.1829,
"step": 3520
},
{
"epoch": 66.13583138173303,
"grad_norm": 5.660995960235596,
"learning_rate": 3.3803034770659825e-06,
"loss": 0.19,
"step": 3530
},
{
"epoch": 66.3231850117096,
"grad_norm": 5.289727210998535,
"learning_rate": 3.2878841524396465e-06,
"loss": 0.192,
"step": 3540
},
{
"epoch": 66.51053864168618,
"grad_norm": 5.043153285980225,
"learning_rate": 3.19665680568445e-06,
"loss": 0.1912,
"step": 3550
},
{
"epoch": 66.69789227166277,
"grad_norm": 4.871051788330078,
"learning_rate": 3.1066264451090815e-06,
"loss": 0.1766,
"step": 3560
},
{
"epoch": 66.88524590163935,
"grad_norm": 4.7814741134643555,
"learning_rate": 3.0177980133086453e-06,
"loss": 0.1744,
"step": 3570
},
{
"epoch": 67.07259953161592,
"grad_norm": 4.574152946472168,
"learning_rate": 2.9301763868933157e-06,
"loss": 0.1908,
"step": 3580
},
{
"epoch": 67.2599531615925,
"grad_norm": 4.687925338745117,
"learning_rate": 2.8437663762206163e-06,
"loss": 0.1914,
"step": 3590
},
{
"epoch": 67.44730679156909,
"grad_norm": 5.131960868835449,
"learning_rate": 2.75857272513132e-06,
"loss": 0.1844,
"step": 3600
},
{
"epoch": 67.63466042154566,
"grad_norm": 6.343697547912598,
"learning_rate": 2.674600110689038e-06,
"loss": 0.1841,
"step": 3610
},
{
"epoch": 67.82201405152225,
"grad_norm": 4.7700676918029785,
"learning_rate": 2.5918531429234368e-06,
"loss": 0.1769,
"step": 3620
},
{
"epoch": 68.00936768149883,
"grad_norm": 5.645007610321045,
"learning_rate": 2.510336364577154e-06,
"loss": 0.185,
"step": 3630
},
{
"epoch": 68.19672131147541,
"grad_norm": 4.07915735244751,
"learning_rate": 2.430054250856412e-06,
"loss": 0.173,
"step": 3640
},
{
"epoch": 68.38407494145198,
"grad_norm": 5.163491725921631,
"learning_rate": 2.351011209185336e-06,
"loss": 0.1972,
"step": 3650
},
{
"epoch": 68.57142857142857,
"grad_norm": 5.53954553604126,
"learning_rate": 2.2732115789639603e-06,
"loss": 0.1818,
"step": 3660
},
{
"epoch": 68.75878220140515,
"grad_norm": 5.660224437713623,
"learning_rate": 2.1966596313300365e-06,
"loss": 0.182,
"step": 3670
},
{
"epoch": 68.94613583138174,
"grad_norm": 5.153733730316162,
"learning_rate": 2.1213595689245386e-06,
"loss": 0.1835,
"step": 3680
},
{
"epoch": 69.13348946135831,
"grad_norm": 4.928243637084961,
"learning_rate": 2.0473155256609366e-06,
"loss": 0.1839,
"step": 3690
},
{
"epoch": 69.3208430913349,
"grad_norm": 4.945793628692627,
"learning_rate": 1.9745315664982276e-06,
"loss": 0.1731,
"step": 3700
},
{
"epoch": 69.50819672131148,
"grad_norm": 4.777456760406494,
"learning_rate": 1.9030116872178316e-06,
"loss": 0.1948,
"step": 3710
},
{
"epoch": 69.69555035128806,
"grad_norm": 4.628859043121338,
"learning_rate": 1.8327598142041658e-06,
"loss": 0.1935,
"step": 3720
},
{
"epoch": 69.88290398126463,
"grad_norm": 6.07702112197876,
"learning_rate": 1.7637798042291126e-06,
"loss": 0.1839,
"step": 3730
},
{
"epoch": 70.07025761124122,
"grad_norm": 4.817112922668457,
"learning_rate": 1.6960754442403054e-06,
"loss": 0.1632,
"step": 3740
},
{
"epoch": 70.2576112412178,
"grad_norm": 5.194154739379883,
"learning_rate": 1.6296504511531836e-06,
"loss": 0.185,
"step": 3750
},
{
"epoch": 70.44496487119437,
"grad_norm": 5.810634613037109,
"learning_rate": 1.5645084716469777e-06,
"loss": 0.1726,
"step": 3760
},
{
"epoch": 70.63231850117096,
"grad_norm": 5.319916248321533,
"learning_rate": 1.5006530819644925e-06,
"loss": 0.194,
"step": 3770
},
{
"epoch": 70.81967213114754,
"grad_norm": 5.039867877960205,
"learning_rate": 1.4380877877157834e-06,
"loss": 0.1659,
"step": 3780
},
{
"epoch": 71.00702576112413,
"grad_norm": 5.392953395843506,
"learning_rate": 1.3768160236856675e-06,
"loss": 0.1863,
"step": 3790
},
{
"epoch": 71.1943793911007,
"grad_norm": 4.837090492248535,
"learning_rate": 1.3168411536452152e-06,
"loss": 0.1843,
"step": 3800
},
{
"epoch": 71.38173302107728,
"grad_norm": 5.398366928100586,
"learning_rate": 1.2581664701670298e-06,
"loss": 0.1748,
"step": 3810
},
{
"epoch": 71.56908665105387,
"grad_norm": 5.430683135986328,
"learning_rate": 1.2007951944445122e-06,
"loss": 0.1855,
"step": 3820
},
{
"epoch": 71.75644028103045,
"grad_norm": 4.792428493499756,
"learning_rate": 1.144730476115019e-06,
"loss": 0.1852,
"step": 3830
},
{
"epoch": 71.94379391100702,
"grad_norm": 5.0115156173706055,
"learning_rate": 1.0899753930869394e-06,
"loss": 0.173,
"step": 3840
},
{
"epoch": 72.1311475409836,
"grad_norm": 5.493814945220947,
"learning_rate": 1.036532951370736e-06,
"loss": 0.1736,
"step": 3850
},
{
"epoch": 72.31850117096019,
"grad_norm": 5.309810638427734,
"learning_rate": 9.844060849138997e-07,
"loss": 0.1764,
"step": 3860
},
{
"epoch": 72.50585480093677,
"grad_norm": 4.86051082611084,
"learning_rate": 9.335976554398912e-07,
"loss": 0.1895,
"step": 3870
},
{
"epoch": 72.69320843091334,
"grad_norm": 5.187326431274414,
"learning_rate": 8.841104522910343e-07,
"loss": 0.1815,
"step": 3880
},
{
"epoch": 72.88056206088993,
"grad_norm": 4.355453968048096,
"learning_rate": 8.359471922753715e-07,
"loss": 0.1745,
"step": 3890
},
{
"epoch": 73.06791569086651,
"grad_norm": 5.000763416290283,
"learning_rate": 7.891105195175358e-07,
"loss": 0.1838,
"step": 3900
},
{
"epoch": 73.2552693208431,
"grad_norm": 5.15885066986084,
"learning_rate": 7.43603005313559e-07,
"loss": 0.1817,
"step": 3910
},
{
"epoch": 73.44262295081967,
"grad_norm": 5.528547286987305,
"learning_rate": 6.994271479897314e-07,
"loss": 0.171,
"step": 3920
},
{
"epoch": 73.62997658079625,
"grad_norm": 4.402473449707031,
"learning_rate": 6.565853727654503e-07,
"loss": 0.1768,
"step": 3930
},
{
"epoch": 73.81733021077284,
"grad_norm": 5.020930290222168,
"learning_rate": 6.150800316200605e-07,
"loss": 0.1995,
"step": 3940
},
{
"epoch": 74.00468384074941,
"grad_norm": 5.047281742095947,
"learning_rate": 5.749134031637349e-07,
"loss": 0.1641,
"step": 3950
},
{
"epoch": 74.19203747072599,
"grad_norm": 5.803074359893799,
"learning_rate": 5.360876925123992e-07,
"loss": 0.1774,
"step": 3960
},
{
"epoch": 74.37939110070258,
"grad_norm": 4.6464924812316895,
"learning_rate": 4.986050311666518e-07,
"loss": 0.175,
"step": 3970
},
{
"epoch": 74.56674473067916,
"grad_norm": 4.660820007324219,
"learning_rate": 4.6246747689474847e-07,
"loss": 0.1715,
"step": 3980
},
{
"epoch": 74.75409836065573,
"grad_norm": 5.668722629547119,
"learning_rate": 4.2767701361964843e-07,
"loss": 0.1853,
"step": 3990
},
{
"epoch": 74.94145199063232,
"grad_norm": 4.63164758682251,
"learning_rate": 3.9423555131007925e-07,
"loss": 0.179,
"step": 4000
},
{
"epoch": 75.1288056206089,
"grad_norm": 4.594822406768799,
"learning_rate": 3.6214492587569316e-07,
"loss": 0.1872,
"step": 4010
},
{
"epoch": 75.31615925058549,
"grad_norm": 4.460590362548828,
"learning_rate": 3.3140689906628054e-07,
"loss": 0.1671,
"step": 4020
},
{
"epoch": 75.50351288056206,
"grad_norm": 5.252081394195557,
"learning_rate": 3.020231583750255e-07,
"loss": 0.1735,
"step": 4030
},
{
"epoch": 75.69086651053864,
"grad_norm": 4.645631313323975,
"learning_rate": 2.739953169458992e-07,
"loss": 0.1887,
"step": 4040
},
{
"epoch": 75.87822014051523,
"grad_norm": 5.47283411026001,
"learning_rate": 2.473249134850808e-07,
"loss": 0.1755,
"step": 4050
},
{
"epoch": 76.06557377049181,
"grad_norm": 4.764420986175537,
"learning_rate": 2.2201341217648331e-07,
"loss": 0.1689,
"step": 4060
},
{
"epoch": 76.25292740046838,
"grad_norm": 5.967309951782227,
"learning_rate": 1.9806220260137064e-07,
"loss": 0.169,
"step": 4070
},
{
"epoch": 76.44028103044496,
"grad_norm": 4.041045665740967,
"learning_rate": 1.7547259966207708e-07,
"loss": 0.1762,
"step": 4080
},
{
"epoch": 76.62763466042155,
"grad_norm": 5.3411030769348145,
"learning_rate": 1.5424584350981487e-07,
"loss": 0.1869,
"step": 4090
},
{
"epoch": 76.81498829039813,
"grad_norm": 5.776910781860352,
"learning_rate": 1.343830994765982e-07,
"loss": 0.1865,
"step": 4100
},
{
"epoch": 77.0023419203747,
"grad_norm": 4.976191520690918,
"learning_rate": 1.1588545801125838e-07,
"loss": 0.1773,
"step": 4110
},
{
"epoch": 77.18969555035129,
"grad_norm": 4.672201156616211,
"learning_rate": 9.87539346195776e-08,
"loss": 0.1874,
"step": 4120
},
{
"epoch": 77.37704918032787,
"grad_norm": 4.933514595031738,
"learning_rate": 8.298946980855315e-08,
"loss": 0.1783,
"step": 4130
},
{
"epoch": 77.56440281030444,
"grad_norm": 4.814449787139893,
"learning_rate": 6.859292903474702e-08,
"loss": 0.1692,
"step": 4140
},
{
"epoch": 77.75175644028103,
"grad_norm": 4.985175132751465,
"learning_rate": 5.5565102656787714e-08,
"loss": 0.1651,
"step": 4150
},
{
"epoch": 77.93911007025761,
"grad_norm": 5.773998260498047,
"learning_rate": 4.390670589196622e-08,
"loss": 0.1877,
"step": 4160
},
{
"epoch": 78.1264637002342,
"grad_norm": 4.613093852996826,
"learning_rate": 3.361837877698115e-08,
"loss": 0.1777,
"step": 4170
},
{
"epoch": 78.31381733021077,
"grad_norm": 5.704171180725098,
"learning_rate": 2.4700686132803076e-08,
"loss": 0.1708,
"step": 4180
},
{
"epoch": 78.50117096018735,
"grad_norm": 4.184200763702393,
"learning_rate": 1.715411753365481e-08,
"loss": 0.1852,
"step": 4190
},
{
"epoch": 78.68852459016394,
"grad_norm": 4.9230475425720215,
"learning_rate": 1.0979087280141298e-08,
"loss": 0.1659,
"step": 4200
},
{
"epoch": 78.87587822014052,
"grad_norm": 5.26874303817749,
"learning_rate": 6.175934376509429e-09,
"loss": 0.1738,
"step": 4210
},
{
"epoch": 79.06323185011709,
"grad_norm": 5.470685958862305,
"learning_rate": 2.7449225120268484e-09,
"loss": 0.199,
"step": 4220
},
{
"epoch": 79.25058548009368,
"grad_norm": 4.462050437927246,
"learning_rate": 6.862400465157403e-10,
"loss": 0.1715,
"step": 4230
},
{
"epoch": 79.43793911007026,
"grad_norm": 5.648906707763672,
"learning_rate": 0.0,
"loss": 0.1815,
"step": 4240
},
{
"epoch": 79.43793911007026,
"step": 4240,
"total_flos": 1.1806200422774342e+19,
"train_loss": 0.4446117949373317,
"train_runtime": 54362.4918,
"train_samples_per_second": 6.279,
"train_steps_per_second": 0.078
}
],
"logging_steps": 10,
"max_steps": 4240,
"num_input_tokens_seen": 0,
"num_train_epochs": 80,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.1806200422774342e+19,
"train_batch_size": 10,
"trial_name": null,
"trial_params": null
}