rqadri's picture
Upload folder using huggingface_hub
0f4e444 verified
Raw
History Blame Contribute Delete
70.3 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.15729468599033816,
"eval_steps": 500,
"global_step": 4070,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003864734299516908,
"grad_norm": 67.77150678538916,
"learning_rate": 2.910112359550562e-06,
"loss": 1.7119647979736328,
"step": 10
},
{
"epoch": 0.0007729468599033816,
"grad_norm": 112.20087349554393,
"learning_rate": 3.921348314606742e-06,
"loss": 1.0294610977172851,
"step": 20
},
{
"epoch": 0.0011594202898550724,
"grad_norm": 17.998285122767445,
"learning_rate": 4.932584269662922e-06,
"loss": 0.9339380264282227,
"step": 30
},
{
"epoch": 0.0015458937198067632,
"grad_norm": 44.13244966887987,
"learning_rate": 5.943820224719102e-06,
"loss": 0.8280322074890136,
"step": 40
},
{
"epoch": 0.001932367149758454,
"grad_norm": 35.342167635210814,
"learning_rate": 6.955056179775282e-06,
"loss": 0.8310356140136719,
"step": 50
},
{
"epoch": 0.002318840579710145,
"grad_norm": 13.961543042810325,
"learning_rate": 7.966292134831462e-06,
"loss": 0.8424642562866211,
"step": 60
},
{
"epoch": 0.002705314009661836,
"grad_norm": 16.09056628824688,
"learning_rate": 8.977528089887641e-06,
"loss": 0.8591781616210937,
"step": 70
},
{
"epoch": 0.0030917874396135265,
"grad_norm": 54.47103241018983,
"learning_rate": 9.988764044943822e-06,
"loss": 0.8048875808715821,
"step": 80
},
{
"epoch": 0.0034782608695652175,
"grad_norm": 288.41808740691243,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.7839107513427734,
"step": 90
},
{
"epoch": 0.003864734299516908,
"grad_norm": 90.30364936720191,
"learning_rate": 1.2011235955056182e-05,
"loss": 0.8227674484252929,
"step": 100
},
{
"epoch": 0.004251207729468599,
"grad_norm": 7.031443917093176,
"learning_rate": 1.3022471910112362e-05,
"loss": 0.8219305038452148,
"step": 110
},
{
"epoch": 0.00463768115942029,
"grad_norm": 64.81590934958837,
"learning_rate": 1.403370786516854e-05,
"loss": 0.8873563766479492,
"step": 120
},
{
"epoch": 0.00502415458937198,
"grad_norm": 7.4010759674397075,
"learning_rate": 1.504494382022472e-05,
"loss": 0.8595630645751953,
"step": 130
},
{
"epoch": 0.005410628019323672,
"grad_norm": 19.21019328586394,
"learning_rate": 1.60561797752809e-05,
"loss": 0.8214578628540039,
"step": 140
},
{
"epoch": 0.005797101449275362,
"grad_norm": 12.640756734713527,
"learning_rate": 1.706741573033708e-05,
"loss": 0.8313806533813477,
"step": 150
},
{
"epoch": 0.006183574879227053,
"grad_norm": 30.722029453858426,
"learning_rate": 1.8078651685393256e-05,
"loss": 0.8253059387207031,
"step": 160
},
{
"epoch": 0.006570048309178744,
"grad_norm": 9.610182761607462,
"learning_rate": 1.908988764044944e-05,
"loss": 0.8571659088134765,
"step": 170
},
{
"epoch": 0.006956521739130435,
"grad_norm": 66.94480959155315,
"learning_rate": 2e-05,
"loss": 0.825499439239502,
"step": 180
},
{
"epoch": 0.007342995169082126,
"grad_norm": 18.927988413767896,
"learning_rate": 2e-05,
"loss": 0.8307562828063965,
"step": 190
},
{
"epoch": 0.007729468599033816,
"grad_norm": 12.259205440850302,
"learning_rate": 2e-05,
"loss": 0.8559392929077149,
"step": 200
},
{
"epoch": 0.008115942028985508,
"grad_norm": 4.705925662053298,
"learning_rate": 2e-05,
"loss": 0.8608473777770996,
"step": 210
},
{
"epoch": 0.008502415458937198,
"grad_norm": 2.301827055644639,
"learning_rate": 2e-05,
"loss": 0.8078425407409668,
"step": 220
},
{
"epoch": 0.008888888888888889,
"grad_norm": 7.309011200551571,
"learning_rate": 2e-05,
"loss": 0.8398617744445801,
"step": 230
},
{
"epoch": 0.00927536231884058,
"grad_norm": 6.173820350919054,
"learning_rate": 2e-05,
"loss": 0.8554814338684082,
"step": 240
},
{
"epoch": 0.00966183574879227,
"grad_norm": 6.755722543096072,
"learning_rate": 2e-05,
"loss": 0.8236814498901367,
"step": 250
},
{
"epoch": 0.01004830917874396,
"grad_norm": 8.495921320038692,
"learning_rate": 2e-05,
"loss": 0.8807731628417969,
"step": 260
},
{
"epoch": 0.010434782608695653,
"grad_norm": 6.836865467270201,
"learning_rate": 2e-05,
"loss": 0.8989522933959961,
"step": 270
},
{
"epoch": 0.010821256038647344,
"grad_norm": 14.122874054097522,
"learning_rate": 2e-05,
"loss": 0.8458233833312988,
"step": 280
},
{
"epoch": 0.011207729468599034,
"grad_norm": 16.985124793104738,
"learning_rate": 2e-05,
"loss": 0.8226848602294922,
"step": 290
},
{
"epoch": 0.011594202898550725,
"grad_norm": 41.65329788058193,
"learning_rate": 2e-05,
"loss": 0.8596689224243164,
"step": 300
},
{
"epoch": 0.011980676328502415,
"grad_norm": 4.572131278336222,
"learning_rate": 2e-05,
"loss": 0.8586993217468262,
"step": 310
},
{
"epoch": 0.012367149758454106,
"grad_norm": 15.52553197362288,
"learning_rate": 2e-05,
"loss": 0.8715810775756836,
"step": 320
},
{
"epoch": 0.012753623188405797,
"grad_norm": 2.099292672310561,
"learning_rate": 2e-05,
"loss": 0.859681510925293,
"step": 330
},
{
"epoch": 0.013140096618357487,
"grad_norm": 2.9884282294816904,
"learning_rate": 2e-05,
"loss": 0.8609855651855469,
"step": 340
},
{
"epoch": 0.01352657004830918,
"grad_norm": 2.13249355879509,
"learning_rate": 2e-05,
"loss": 0.8378034591674804,
"step": 350
},
{
"epoch": 0.01391304347826087,
"grad_norm": 1.6770141008927584,
"learning_rate": 2e-05,
"loss": 0.8262413024902344,
"step": 360
},
{
"epoch": 0.01429951690821256,
"grad_norm": 4.682041458440538,
"learning_rate": 2e-05,
"loss": 0.8071828842163086,
"step": 370
},
{
"epoch": 0.014685990338164251,
"grad_norm": 1.8513588195141903,
"learning_rate": 2e-05,
"loss": 0.7924742698669434,
"step": 380
},
{
"epoch": 0.015072463768115942,
"grad_norm": 2.4641373360496774,
"learning_rate": 2e-05,
"loss": 0.8004615783691407,
"step": 390
},
{
"epoch": 0.015458937198067632,
"grad_norm": 2.3004772602625914,
"learning_rate": 2e-05,
"loss": 0.7985801219940185,
"step": 400
},
{
"epoch": 0.015845410628019325,
"grad_norm": 2.0543279811562636,
"learning_rate": 2e-05,
"loss": 0.8145970344543457,
"step": 410
},
{
"epoch": 0.016231884057971015,
"grad_norm": 11.830783545012162,
"learning_rate": 2e-05,
"loss": 0.8268651962280273,
"step": 420
},
{
"epoch": 0.016618357487922706,
"grad_norm": 23.315575489389328,
"learning_rate": 2e-05,
"loss": 0.8241431236267089,
"step": 430
},
{
"epoch": 0.017004830917874397,
"grad_norm": 21.42157001872646,
"learning_rate": 2e-05,
"loss": 0.8197898864746094,
"step": 440
},
{
"epoch": 0.017391304347826087,
"grad_norm": 6.089448482941218,
"learning_rate": 2e-05,
"loss": 0.799440574645996,
"step": 450
},
{
"epoch": 0.017777777777777778,
"grad_norm": 2.0297328988872207,
"learning_rate": 2e-05,
"loss": 0.7915650844573975,
"step": 460
},
{
"epoch": 0.01816425120772947,
"grad_norm": 2.5804977642175406,
"learning_rate": 2e-05,
"loss": 0.8292923927307129,
"step": 470
},
{
"epoch": 0.01855072463768116,
"grad_norm": 2.038221241470096,
"learning_rate": 2e-05,
"loss": 0.8466601371765137,
"step": 480
},
{
"epoch": 0.01893719806763285,
"grad_norm": 2.6279678065101404,
"learning_rate": 2e-05,
"loss": 0.7829755306243896,
"step": 490
},
{
"epoch": 0.01932367149758454,
"grad_norm": 3.6287666464295207,
"learning_rate": 2e-05,
"loss": 0.8295025825500488,
"step": 500
},
{
"epoch": 0.01971014492753623,
"grad_norm": 5.056996216526932,
"learning_rate": 2e-05,
"loss": 0.8213679313659668,
"step": 510
},
{
"epoch": 0.02009661835748792,
"grad_norm": 3.2319172805464556,
"learning_rate": 2e-05,
"loss": 0.8206055641174317,
"step": 520
},
{
"epoch": 0.020483091787439612,
"grad_norm": 8.57107033721087,
"learning_rate": 2e-05,
"loss": 0.8187108039855957,
"step": 530
},
{
"epoch": 0.020869565217391306,
"grad_norm": 2.3249597398057866,
"learning_rate": 2e-05,
"loss": 0.8607352256774903,
"step": 540
},
{
"epoch": 0.021256038647342997,
"grad_norm": 4.207073762673164,
"learning_rate": 2e-05,
"loss": 0.803462028503418,
"step": 550
},
{
"epoch": 0.021642512077294687,
"grad_norm": 2.16004233284329,
"learning_rate": 2e-05,
"loss": 0.8118793487548828,
"step": 560
},
{
"epoch": 0.022028985507246378,
"grad_norm": 5.922676764922052,
"learning_rate": 2e-05,
"loss": 0.8660179138183594,
"step": 570
},
{
"epoch": 0.02241545893719807,
"grad_norm": 2.8910298488294783,
"learning_rate": 2e-05,
"loss": 0.8383306503295899,
"step": 580
},
{
"epoch": 0.02280193236714976,
"grad_norm": 10.435855529697001,
"learning_rate": 2e-05,
"loss": 0.8274753570556641,
"step": 590
},
{
"epoch": 0.02318840579710145,
"grad_norm": 5.716952677601055,
"learning_rate": 2e-05,
"loss": 0.8341848373413085,
"step": 600
},
{
"epoch": 0.02357487922705314,
"grad_norm": 1.7990410820641871,
"learning_rate": 2e-05,
"loss": 0.8170646667480469,
"step": 610
},
{
"epoch": 0.02396135265700483,
"grad_norm": 2.5141846970054984,
"learning_rate": 2e-05,
"loss": 0.8089756965637207,
"step": 620
},
{
"epoch": 0.02434782608695652,
"grad_norm": 1.644941789727098,
"learning_rate": 2e-05,
"loss": 0.7915188789367675,
"step": 630
},
{
"epoch": 0.024734299516908212,
"grad_norm": 4.69436608310746,
"learning_rate": 2e-05,
"loss": 0.8204584121704102,
"step": 640
},
{
"epoch": 0.025120772946859903,
"grad_norm": 14.985321654813715,
"learning_rate": 2e-05,
"loss": 0.8408443450927734,
"step": 650
},
{
"epoch": 0.025507246376811593,
"grad_norm": 3.606103990135419,
"learning_rate": 2e-05,
"loss": 0.8335097312927247,
"step": 660
},
{
"epoch": 0.025893719806763284,
"grad_norm": 302.2907667494139,
"learning_rate": 2e-05,
"loss": 0.8303115844726563,
"step": 670
},
{
"epoch": 0.026280193236714974,
"grad_norm": 5.094641064796761,
"learning_rate": 2e-05,
"loss": 0.8183450698852539,
"step": 680
},
{
"epoch": 0.02666666666666667,
"grad_norm": 7.71531360876406,
"learning_rate": 2e-05,
"loss": 0.8168371200561524,
"step": 690
},
{
"epoch": 0.02705314009661836,
"grad_norm": 27.557957472594705,
"learning_rate": 2e-05,
"loss": 0.8344195365905762,
"step": 700
},
{
"epoch": 0.02743961352657005,
"grad_norm": 6.340736949473045,
"learning_rate": 2e-05,
"loss": 0.8478621482849121,
"step": 710
},
{
"epoch": 0.02782608695652174,
"grad_norm": 84.49603950900422,
"learning_rate": 2e-05,
"loss": 0.8494409561157227,
"step": 720
},
{
"epoch": 0.02821256038647343,
"grad_norm": 5.239994048119582,
"learning_rate": 2e-05,
"loss": 0.8430055618286133,
"step": 730
},
{
"epoch": 0.02859903381642512,
"grad_norm": 6.81571454851921,
"learning_rate": 2e-05,
"loss": 0.8379552841186524,
"step": 740
},
{
"epoch": 0.028985507246376812,
"grad_norm": 13.230544669517375,
"learning_rate": 2e-05,
"loss": 0.8137977600097657,
"step": 750
},
{
"epoch": 0.029371980676328503,
"grad_norm": 10.83917272801397,
"learning_rate": 2e-05,
"loss": 0.8010368347167969,
"step": 760
},
{
"epoch": 0.029758454106280193,
"grad_norm": 4.561007311907072,
"learning_rate": 2e-05,
"loss": 0.8132765769958497,
"step": 770
},
{
"epoch": 0.030144927536231884,
"grad_norm": 5.052478275742948,
"learning_rate": 2e-05,
"loss": 0.8024440765380859,
"step": 780
},
{
"epoch": 0.030531400966183574,
"grad_norm": 39.20779782791551,
"learning_rate": 2e-05,
"loss": 0.8082746505737305,
"step": 790
},
{
"epoch": 0.030917874396135265,
"grad_norm": 6.722990812199062,
"learning_rate": 2e-05,
"loss": 0.7964837551116943,
"step": 800
},
{
"epoch": 0.03130434782608696,
"grad_norm": 6.263608751717215,
"learning_rate": 2e-05,
"loss": 0.8117972373962402,
"step": 810
},
{
"epoch": 0.03169082125603865,
"grad_norm": 6.362861042949148,
"learning_rate": 2e-05,
"loss": 0.8188319206237793,
"step": 820
},
{
"epoch": 0.03207729468599034,
"grad_norm": 6.379235603582932,
"learning_rate": 2e-05,
"loss": 0.7999361991882324,
"step": 830
},
{
"epoch": 0.03246376811594203,
"grad_norm": 7.771520162515829,
"learning_rate": 2e-05,
"loss": 0.8278095245361328,
"step": 840
},
{
"epoch": 0.03285024154589372,
"grad_norm": 3.6283672901509307,
"learning_rate": 2e-05,
"loss": 0.8165772438049317,
"step": 850
},
{
"epoch": 0.03323671497584541,
"grad_norm": 24.13531059310475,
"learning_rate": 2e-05,
"loss": 0.8282254219055176,
"step": 860
},
{
"epoch": 0.0336231884057971,
"grad_norm": 6.38211185754252,
"learning_rate": 2e-05,
"loss": 0.857562255859375,
"step": 870
},
{
"epoch": 0.03400966183574879,
"grad_norm": 8.151353292941916,
"learning_rate": 2e-05,
"loss": 0.8778319358825684,
"step": 880
},
{
"epoch": 0.034396135265700484,
"grad_norm": 2.6425732312042793,
"learning_rate": 2e-05,
"loss": 0.8224431991577148,
"step": 890
},
{
"epoch": 0.034782608695652174,
"grad_norm": 3.5769751025573835,
"learning_rate": 2e-05,
"loss": 0.8090167999267578,
"step": 900
},
{
"epoch": 0.035169082125603865,
"grad_norm": 4.710064964796984,
"learning_rate": 2e-05,
"loss": 0.7755887508392334,
"step": 910
},
{
"epoch": 0.035555555555555556,
"grad_norm": 2.85171049842582,
"learning_rate": 2e-05,
"loss": 0.80325927734375,
"step": 920
},
{
"epoch": 0.035942028985507246,
"grad_norm": 2.7025040213443625,
"learning_rate": 2e-05,
"loss": 0.8224540710449219,
"step": 930
},
{
"epoch": 0.03632850241545894,
"grad_norm": 4.365935909605305,
"learning_rate": 2e-05,
"loss": 0.8001300811767578,
"step": 940
},
{
"epoch": 0.03671497584541063,
"grad_norm": 4.205991130813683,
"learning_rate": 2e-05,
"loss": 0.8388648986816406,
"step": 950
},
{
"epoch": 0.03710144927536232,
"grad_norm": 9.511180584595577,
"learning_rate": 2e-05,
"loss": 0.8006820678710938,
"step": 960
},
{
"epoch": 0.03748792270531401,
"grad_norm": 1.8991371909927346,
"learning_rate": 2e-05,
"loss": 0.7927989959716797,
"step": 970
},
{
"epoch": 0.0378743961352657,
"grad_norm": 1.7204963535857005,
"learning_rate": 2e-05,
"loss": 0.7866291046142578,
"step": 980
},
{
"epoch": 0.03826086956521739,
"grad_norm": 4.982975467165141,
"learning_rate": 2e-05,
"loss": 0.8541565895080566,
"step": 990
},
{
"epoch": 0.03864734299516908,
"grad_norm": 1.4823804814569383,
"learning_rate": 2e-05,
"loss": 0.7768624782562256,
"step": 1000
},
{
"epoch": 0.03903381642512077,
"grad_norm": 1.6741186213295625,
"learning_rate": 2e-05,
"loss": 0.7901049613952636,
"step": 1010
},
{
"epoch": 0.03942028985507246,
"grad_norm": 2.4322679920118455,
"learning_rate": 2e-05,
"loss": 0.7638983726501465,
"step": 1020
},
{
"epoch": 0.03980676328502415,
"grad_norm": 3.3701720746584383,
"learning_rate": 2e-05,
"loss": 0.7828890800476074,
"step": 1030
},
{
"epoch": 0.04019323671497584,
"grad_norm": 2.0742844849026607,
"learning_rate": 2e-05,
"loss": 0.8018475532531738,
"step": 1040
},
{
"epoch": 0.04057971014492753,
"grad_norm": 2.1569898099072904,
"learning_rate": 2e-05,
"loss": 0.7848191738128663,
"step": 1050
},
{
"epoch": 0.040966183574879224,
"grad_norm": 1.3882337646082599,
"learning_rate": 2e-05,
"loss": 0.7792089462280274,
"step": 1060
},
{
"epoch": 0.041352657004830914,
"grad_norm": 2.662094444417472,
"learning_rate": 2e-05,
"loss": 0.793889045715332,
"step": 1070
},
{
"epoch": 0.04173913043478261,
"grad_norm": 2.587246330505362,
"learning_rate": 2e-05,
"loss": 0.7864011287689209,
"step": 1080
},
{
"epoch": 0.0421256038647343,
"grad_norm": 1.0896303438627253,
"learning_rate": 2e-05,
"loss": 0.7887033462524414,
"step": 1090
},
{
"epoch": 0.04251207729468599,
"grad_norm": 1.6180241575772059,
"learning_rate": 2e-05,
"loss": 0.7555316925048828,
"step": 1100
},
{
"epoch": 0.042898550724637684,
"grad_norm": 5.15524054228135,
"learning_rate": 2e-05,
"loss": 0.7596688747406006,
"step": 1110
},
{
"epoch": 0.043285024154589374,
"grad_norm": 3.791811827235934,
"learning_rate": 2e-05,
"loss": 0.7762317180633544,
"step": 1120
},
{
"epoch": 0.043671497584541065,
"grad_norm": 3.8840676386572754,
"learning_rate": 2e-05,
"loss": 0.7993937492370605,
"step": 1130
},
{
"epoch": 0.044057971014492756,
"grad_norm": 1.7203756023551415,
"learning_rate": 2e-05,
"loss": 0.8044867515563965,
"step": 1140
},
{
"epoch": 0.044444444444444446,
"grad_norm": 1.8455815673442082,
"learning_rate": 2e-05,
"loss": 0.7740165710449218,
"step": 1150
},
{
"epoch": 0.04483091787439614,
"grad_norm": 1.2497425235654502,
"learning_rate": 2e-05,
"loss": 0.7792739868164062,
"step": 1160
},
{
"epoch": 0.04521739130434783,
"grad_norm": 3.582519109266027,
"learning_rate": 2e-05,
"loss": 0.7844886302947998,
"step": 1170
},
{
"epoch": 0.04560386473429952,
"grad_norm": 1.7447476237477404,
"learning_rate": 2e-05,
"loss": 0.7678474426269531,
"step": 1180
},
{
"epoch": 0.04599033816425121,
"grad_norm": 2.3052344816348285,
"learning_rate": 2e-05,
"loss": 0.7841787338256836,
"step": 1190
},
{
"epoch": 0.0463768115942029,
"grad_norm": 6.171873978979098,
"learning_rate": 2e-05,
"loss": 0.7667727470397949,
"step": 1200
},
{
"epoch": 0.04676328502415459,
"grad_norm": 2.5238752863132166,
"learning_rate": 2e-05,
"loss": 0.7614020824432373,
"step": 1210
},
{
"epoch": 0.04714975845410628,
"grad_norm": 3.3006024749410345,
"learning_rate": 2e-05,
"loss": 0.7787034988403321,
"step": 1220
},
{
"epoch": 0.04753623188405797,
"grad_norm": 1.7800834333389988,
"learning_rate": 2e-05,
"loss": 0.781245756149292,
"step": 1230
},
{
"epoch": 0.04792270531400966,
"grad_norm": 4.086703804045758,
"learning_rate": 2e-05,
"loss": 0.7704942226409912,
"step": 1240
},
{
"epoch": 0.04830917874396135,
"grad_norm": 1.8232412748458093,
"learning_rate": 2e-05,
"loss": 0.830727481842041,
"step": 1250
},
{
"epoch": 0.04869565217391304,
"grad_norm": 1.438606233505821,
"learning_rate": 2e-05,
"loss": 0.7969734191894531,
"step": 1260
},
{
"epoch": 0.04908212560386473,
"grad_norm": 14.874207481468607,
"learning_rate": 2e-05,
"loss": 0.7737374305725098,
"step": 1270
},
{
"epoch": 0.049468599033816424,
"grad_norm": 1.8577472378752176,
"learning_rate": 2e-05,
"loss": 0.7808979034423829,
"step": 1280
},
{
"epoch": 0.049855072463768114,
"grad_norm": 1.1647916231280007,
"learning_rate": 2e-05,
"loss": 0.7798149108886718,
"step": 1290
},
{
"epoch": 0.050241545893719805,
"grad_norm": 1.8949891297132515,
"learning_rate": 2e-05,
"loss": 0.7773360252380371,
"step": 1300
},
{
"epoch": 0.050628019323671496,
"grad_norm": 1.8051946173023403,
"learning_rate": 2e-05,
"loss": 0.7962361812591553,
"step": 1310
},
{
"epoch": 0.051014492753623186,
"grad_norm": 8.517857032168914,
"learning_rate": 2e-05,
"loss": 0.7579530715942383,
"step": 1320
},
{
"epoch": 0.05140096618357488,
"grad_norm": 1.2056710567353992,
"learning_rate": 2e-05,
"loss": 0.7956658840179444,
"step": 1330
},
{
"epoch": 0.05178743961352657,
"grad_norm": 1.5620096177153822,
"learning_rate": 2e-05,
"loss": 0.7909909248352051,
"step": 1340
},
{
"epoch": 0.05217391304347826,
"grad_norm": 1.2051599267987412,
"learning_rate": 2e-05,
"loss": 0.802952766418457,
"step": 1350
},
{
"epoch": 0.05256038647342995,
"grad_norm": 1.442909003316718,
"learning_rate": 2e-05,
"loss": 0.792842435836792,
"step": 1360
},
{
"epoch": 0.05294685990338164,
"grad_norm": 1.8033837673657727,
"learning_rate": 2e-05,
"loss": 0.8045886039733887,
"step": 1370
},
{
"epoch": 0.05333333333333334,
"grad_norm": 1.7301184849803795,
"learning_rate": 2e-05,
"loss": 0.7730770111083984,
"step": 1380
},
{
"epoch": 0.05371980676328503,
"grad_norm": 2.593314064685021,
"learning_rate": 2e-05,
"loss": 0.7898385524749756,
"step": 1390
},
{
"epoch": 0.05410628019323672,
"grad_norm": 2.6612126149781123,
"learning_rate": 2e-05,
"loss": 0.7972373008728028,
"step": 1400
},
{
"epoch": 0.05449275362318841,
"grad_norm": 4.014591492016486,
"learning_rate": 2e-05,
"loss": 0.7940009593963623,
"step": 1410
},
{
"epoch": 0.0548792270531401,
"grad_norm": 1.88666817691601,
"learning_rate": 2e-05,
"loss": 0.7976803779602051,
"step": 1420
},
{
"epoch": 0.05526570048309179,
"grad_norm": 1.6808638117085843,
"learning_rate": 2e-05,
"loss": 0.7751292228698731,
"step": 1430
},
{
"epoch": 0.05565217391304348,
"grad_norm": 2.8607658596215573,
"learning_rate": 2e-05,
"loss": 0.7797608375549316,
"step": 1440
},
{
"epoch": 0.05603864734299517,
"grad_norm": 1.743259772518007,
"learning_rate": 2e-05,
"loss": 0.7893115520477295,
"step": 1450
},
{
"epoch": 0.05642512077294686,
"grad_norm": 4.094105063418816,
"learning_rate": 2e-05,
"loss": 0.7623452186584473,
"step": 1460
},
{
"epoch": 0.05681159420289855,
"grad_norm": 1.0326374629324264,
"learning_rate": 2e-05,
"loss": 0.8003641128540039,
"step": 1470
},
{
"epoch": 0.05719806763285024,
"grad_norm": 1.5470981584627885,
"learning_rate": 2e-05,
"loss": 0.7471415519714355,
"step": 1480
},
{
"epoch": 0.05758454106280193,
"grad_norm": 4.233012132760419,
"learning_rate": 2e-05,
"loss": 0.8017045974731445,
"step": 1490
},
{
"epoch": 0.057971014492753624,
"grad_norm": 1.5670919578440439,
"learning_rate": 2e-05,
"loss": 0.7809749603271484,
"step": 1500
},
{
"epoch": 0.058357487922705314,
"grad_norm": 1.1146358925152047,
"learning_rate": 2e-05,
"loss": 0.8092234611511231,
"step": 1510
},
{
"epoch": 0.058743961352657005,
"grad_norm": 1.8519058887339446,
"learning_rate": 2e-05,
"loss": 0.7762881755828858,
"step": 1520
},
{
"epoch": 0.059130434782608696,
"grad_norm": 1.842244630499373,
"learning_rate": 2e-05,
"loss": 0.7717338085174561,
"step": 1530
},
{
"epoch": 0.059516908212560386,
"grad_norm": 1.8659924669555197,
"learning_rate": 2e-05,
"loss": 0.8045551300048828,
"step": 1540
},
{
"epoch": 0.05990338164251208,
"grad_norm": 1.789268515534286,
"learning_rate": 2e-05,
"loss": 0.802666187286377,
"step": 1550
},
{
"epoch": 0.06028985507246377,
"grad_norm": 3.049390694136811,
"learning_rate": 2e-05,
"loss": 0.7977540493011475,
"step": 1560
},
{
"epoch": 0.06067632850241546,
"grad_norm": 1.1550233137997092,
"learning_rate": 2e-05,
"loss": 0.759410810470581,
"step": 1570
},
{
"epoch": 0.06106280193236715,
"grad_norm": 1.4840972042589198,
"learning_rate": 2e-05,
"loss": 0.7568341255187988,
"step": 1580
},
{
"epoch": 0.06144927536231884,
"grad_norm": 2.4324918941876517,
"learning_rate": 2e-05,
"loss": 0.7721347808837891,
"step": 1590
},
{
"epoch": 0.06183574879227053,
"grad_norm": 1.3236007075392429,
"learning_rate": 2e-05,
"loss": 0.7291332244873047,
"step": 1600
},
{
"epoch": 0.06222222222222222,
"grad_norm": 1.8825475500130031,
"learning_rate": 2e-05,
"loss": 0.7765389919281006,
"step": 1610
},
{
"epoch": 0.06260869565217392,
"grad_norm": 1.5021722283739194,
"learning_rate": 2e-05,
"loss": 0.7942019939422608,
"step": 1620
},
{
"epoch": 0.0629951690821256,
"grad_norm": 1.3488892169893916,
"learning_rate": 2e-05,
"loss": 0.7698382377624512,
"step": 1630
},
{
"epoch": 0.0633816425120773,
"grad_norm": 2.412898234110765,
"learning_rate": 2e-05,
"loss": 0.7915114402770996,
"step": 1640
},
{
"epoch": 0.06376811594202898,
"grad_norm": 4.032177721449734,
"learning_rate": 2e-05,
"loss": 0.767926549911499,
"step": 1650
},
{
"epoch": 0.06415458937198068,
"grad_norm": 3.3886389099102976,
"learning_rate": 2e-05,
"loss": 0.7934833526611328,
"step": 1660
},
{
"epoch": 0.06454106280193236,
"grad_norm": 1.8196514648355098,
"learning_rate": 2e-05,
"loss": 0.8287544250488281,
"step": 1670
},
{
"epoch": 0.06492753623188406,
"grad_norm": 1.933296233701157,
"learning_rate": 2e-05,
"loss": 0.7792496681213379,
"step": 1680
},
{
"epoch": 0.06531400966183575,
"grad_norm": 5.5160092569417944,
"learning_rate": 2e-05,
"loss": 0.7874814987182617,
"step": 1690
},
{
"epoch": 0.06570048309178744,
"grad_norm": 2.6740319109507054,
"learning_rate": 2e-05,
"loss": 0.7673942565917968,
"step": 1700
},
{
"epoch": 0.06608695652173913,
"grad_norm": 4.46192092842804,
"learning_rate": 2e-05,
"loss": 0.7866016387939453,
"step": 1710
},
{
"epoch": 0.06647342995169082,
"grad_norm": 9.393669028550853,
"learning_rate": 2e-05,
"loss": 0.7943299770355224,
"step": 1720
},
{
"epoch": 0.06685990338164251,
"grad_norm": 2.805958882681691,
"learning_rate": 2e-05,
"loss": 0.7814671993255615,
"step": 1730
},
{
"epoch": 0.0672463768115942,
"grad_norm": 8.944621163352808,
"learning_rate": 2e-05,
"loss": 0.7775825500488281,
"step": 1740
},
{
"epoch": 0.06763285024154589,
"grad_norm": 1.3932999773436152,
"learning_rate": 2e-05,
"loss": 0.813438606262207,
"step": 1750
},
{
"epoch": 0.06801932367149759,
"grad_norm": 1.1571499874919873,
"learning_rate": 2e-05,
"loss": 0.7704301834106445,
"step": 1760
},
{
"epoch": 0.06840579710144927,
"grad_norm": 16.767188751455745,
"learning_rate": 2e-05,
"loss": 0.778882360458374,
"step": 1770
},
{
"epoch": 0.06879227053140097,
"grad_norm": 1.8040160227751316,
"learning_rate": 2e-05,
"loss": 0.7672492980957031,
"step": 1780
},
{
"epoch": 0.06917874396135265,
"grad_norm": 1.9003065034750897,
"learning_rate": 2e-05,
"loss": 0.7559861183166504,
"step": 1790
},
{
"epoch": 0.06956521739130435,
"grad_norm": 4.328779850300501,
"learning_rate": 2e-05,
"loss": 0.7670548439025879,
"step": 1800
},
{
"epoch": 0.06995169082125603,
"grad_norm": 1.5009521124497522,
"learning_rate": 2e-05,
"loss": 0.7466334342956543,
"step": 1810
},
{
"epoch": 0.07033816425120773,
"grad_norm": 0.9373529421029959,
"learning_rate": 2e-05,
"loss": 0.7706023216247558,
"step": 1820
},
{
"epoch": 0.07072463768115941,
"grad_norm": 2.5673019538259636,
"learning_rate": 2e-05,
"loss": 0.7813019752502441,
"step": 1830
},
{
"epoch": 0.07111111111111111,
"grad_norm": 10.595792073325587,
"learning_rate": 2e-05,
"loss": 0.7712044715881348,
"step": 1840
},
{
"epoch": 0.07149758454106281,
"grad_norm": 1.4549261759502392,
"learning_rate": 2e-05,
"loss": 0.7399177551269531,
"step": 1850
},
{
"epoch": 0.07188405797101449,
"grad_norm": 1.3679794209107425,
"learning_rate": 2e-05,
"loss": 0.7697343349456787,
"step": 1860
},
{
"epoch": 0.07227053140096619,
"grad_norm": 25.30685684908231,
"learning_rate": 2e-05,
"loss": 0.7722678661346436,
"step": 1870
},
{
"epoch": 0.07265700483091787,
"grad_norm": 5.813362887543927,
"learning_rate": 2e-05,
"loss": 0.8079950332641601,
"step": 1880
},
{
"epoch": 0.07304347826086957,
"grad_norm": 7.55091986778727,
"learning_rate": 2e-05,
"loss": 0.7749129295349121,
"step": 1890
},
{
"epoch": 0.07342995169082125,
"grad_norm": 2.576691425426098,
"learning_rate": 2e-05,
"loss": 0.7901420593261719,
"step": 1900
},
{
"epoch": 0.07381642512077295,
"grad_norm": 2.850989381932755,
"learning_rate": 2e-05,
"loss": 0.7870397567749023,
"step": 1910
},
{
"epoch": 0.07420289855072464,
"grad_norm": 2.8388031664275593,
"learning_rate": 2e-05,
"loss": 0.798320722579956,
"step": 1920
},
{
"epoch": 0.07458937198067633,
"grad_norm": 1.2660870766825572,
"learning_rate": 2e-05,
"loss": 0.7990159034729004,
"step": 1930
},
{
"epoch": 0.07497584541062802,
"grad_norm": 7.521731822457599,
"learning_rate": 2e-05,
"loss": 0.8066888809204101,
"step": 1940
},
{
"epoch": 0.07536231884057971,
"grad_norm": 2.2847479728174886,
"learning_rate": 2e-05,
"loss": 0.7807460784912109,
"step": 1950
},
{
"epoch": 0.0757487922705314,
"grad_norm": 36.52969282187383,
"learning_rate": 2e-05,
"loss": 0.7917587280273437,
"step": 1960
},
{
"epoch": 0.0761352657004831,
"grad_norm": 3.301236759706295,
"learning_rate": 2e-05,
"loss": 0.7987814903259277,
"step": 1970
},
{
"epoch": 0.07652173913043478,
"grad_norm": 2.9129761845971176,
"learning_rate": 2e-05,
"loss": 0.7681584358215332,
"step": 1980
},
{
"epoch": 0.07690821256038648,
"grad_norm": 2.124239464203845,
"learning_rate": 2e-05,
"loss": 0.7853168487548828,
"step": 1990
},
{
"epoch": 0.07729468599033816,
"grad_norm": 6.0767545983301225,
"learning_rate": 2e-05,
"loss": 0.7794623374938965,
"step": 2000
},
{
"epoch": 0.07768115942028986,
"grad_norm": 1.3709998398850736,
"learning_rate": 2e-05,
"loss": 0.7739840984344483,
"step": 2010
},
{
"epoch": 0.07806763285024154,
"grad_norm": 1.5709783521988716,
"learning_rate": 2e-05,
"loss": 0.7280101776123047,
"step": 2020
},
{
"epoch": 0.07845410628019324,
"grad_norm": 2.0426823491051156,
"learning_rate": 2e-05,
"loss": 0.7502191066741943,
"step": 2030
},
{
"epoch": 0.07884057971014492,
"grad_norm": 3.1670032654507825,
"learning_rate": 2e-05,
"loss": 0.7697875022888183,
"step": 2040
},
{
"epoch": 0.07922705314009662,
"grad_norm": 1.519486508417274,
"learning_rate": 2e-05,
"loss": 0.7478765487670899,
"step": 2050
},
{
"epoch": 0.0796135265700483,
"grad_norm": 2.2518000319069476,
"learning_rate": 2e-05,
"loss": 0.7812594413757324,
"step": 2060
},
{
"epoch": 0.08,
"grad_norm": 1.5740210899218194,
"learning_rate": 2e-05,
"loss": 0.7684998989105225,
"step": 2070
},
{
"epoch": 0.08038647342995169,
"grad_norm": 2.0349709099256845,
"learning_rate": 2e-05,
"loss": 0.7811843872070312,
"step": 2080
},
{
"epoch": 0.08077294685990338,
"grad_norm": 2.2636959526681157,
"learning_rate": 2e-05,
"loss": 0.7650601387023925,
"step": 2090
},
{
"epoch": 0.08115942028985507,
"grad_norm": 3.742795215033163,
"learning_rate": 2e-05,
"loss": 0.7615516185760498,
"step": 2100
},
{
"epoch": 0.08154589371980676,
"grad_norm": 1.138738386234341,
"learning_rate": 2e-05,
"loss": 0.7689103126525879,
"step": 2110
},
{
"epoch": 0.08193236714975845,
"grad_norm": 1.6534859784091112,
"learning_rate": 2e-05,
"loss": 0.7665469646453857,
"step": 2120
},
{
"epoch": 0.08231884057971015,
"grad_norm": 1.3318959611026695,
"learning_rate": 2e-05,
"loss": 0.769937801361084,
"step": 2130
},
{
"epoch": 0.08270531400966183,
"grad_norm": 1.3547014303403682,
"learning_rate": 2e-05,
"loss": 0.7504668235778809,
"step": 2140
},
{
"epoch": 0.08309178743961353,
"grad_norm": 17.52193810186475,
"learning_rate": 2e-05,
"loss": 0.7507330894470214,
"step": 2150
},
{
"epoch": 0.08347826086956522,
"grad_norm": 1.8162401489013498,
"learning_rate": 2e-05,
"loss": 0.7667189598083496,
"step": 2160
},
{
"epoch": 0.08386473429951691,
"grad_norm": 2.4747448006663,
"learning_rate": 2e-05,
"loss": 0.7687741279602051,
"step": 2170
},
{
"epoch": 0.0842512077294686,
"grad_norm": 1.8861120110910479,
"learning_rate": 2e-05,
"loss": 0.7431299209594726,
"step": 2180
},
{
"epoch": 0.08463768115942029,
"grad_norm": 1.598592624418475,
"learning_rate": 2e-05,
"loss": 0.7552878379821777,
"step": 2190
},
{
"epoch": 0.08502415458937199,
"grad_norm": 2.431095132727302,
"learning_rate": 2e-05,
"loss": 0.734284496307373,
"step": 2200
},
{
"epoch": 0.08541062801932367,
"grad_norm": 2.7269516195691077,
"learning_rate": 2e-05,
"loss": 0.7517167091369629,
"step": 2210
},
{
"epoch": 0.08579710144927537,
"grad_norm": 1.661492853949561,
"learning_rate": 2e-05,
"loss": 0.7628636360168457,
"step": 2220
},
{
"epoch": 0.08618357487922705,
"grad_norm": 2.855274848798419,
"learning_rate": 2e-05,
"loss": 0.7595593929290771,
"step": 2230
},
{
"epoch": 0.08657004830917875,
"grad_norm": 1.285434436992812,
"learning_rate": 2e-05,
"loss": 0.7832144737243653,
"step": 2240
},
{
"epoch": 0.08695652173913043,
"grad_norm": 1.2309831181727102,
"learning_rate": 2e-05,
"loss": 0.7642119407653809,
"step": 2250
},
{
"epoch": 0.08734299516908213,
"grad_norm": 1.3727116026773452,
"learning_rate": 2e-05,
"loss": 0.7471759796142579,
"step": 2260
},
{
"epoch": 0.08772946859903381,
"grad_norm": 1.3248395463889682,
"learning_rate": 2e-05,
"loss": 0.7310284614562989,
"step": 2270
},
{
"epoch": 0.08811594202898551,
"grad_norm": 7.664609758100217,
"learning_rate": 2e-05,
"loss": 0.7528136253356934,
"step": 2280
},
{
"epoch": 0.0885024154589372,
"grad_norm": 2.339105261431996,
"learning_rate": 2e-05,
"loss": 0.7621146202087402,
"step": 2290
},
{
"epoch": 0.08888888888888889,
"grad_norm": 1.9665131401980414,
"learning_rate": 2e-05,
"loss": 0.7420401573181152,
"step": 2300
},
{
"epoch": 0.08927536231884058,
"grad_norm": 1.2677168413530253,
"learning_rate": 2e-05,
"loss": 0.7691300868988037,
"step": 2310
},
{
"epoch": 0.08966183574879227,
"grad_norm": 2.3372668170559647,
"learning_rate": 2e-05,
"loss": 0.7166595458984375,
"step": 2320
},
{
"epoch": 0.09004830917874396,
"grad_norm": 4.592447961406041,
"learning_rate": 2e-05,
"loss": 0.7677947998046875,
"step": 2330
},
{
"epoch": 0.09043478260869565,
"grad_norm": 2.431963843797448,
"learning_rate": 2e-05,
"loss": 0.7791108608245849,
"step": 2340
},
{
"epoch": 0.09082125603864734,
"grad_norm": 1.5196869951311995,
"learning_rate": 2e-05,
"loss": 0.7593348503112793,
"step": 2350
},
{
"epoch": 0.09120772946859904,
"grad_norm": 3.1796994866171824,
"learning_rate": 2e-05,
"loss": 0.7442672252655029,
"step": 2360
},
{
"epoch": 0.09159420289855072,
"grad_norm": 4.225399402363425,
"learning_rate": 2e-05,
"loss": 0.7718966960906982,
"step": 2370
},
{
"epoch": 0.09198067632850242,
"grad_norm": 1.7013977773889133,
"learning_rate": 2e-05,
"loss": 0.7620273113250733,
"step": 2380
},
{
"epoch": 0.0923671497584541,
"grad_norm": 2.5304881183937313,
"learning_rate": 2e-05,
"loss": 0.7750027656555176,
"step": 2390
},
{
"epoch": 0.0927536231884058,
"grad_norm": 1.5583085149697413,
"learning_rate": 2e-05,
"loss": 0.7332376003265381,
"step": 2400
},
{
"epoch": 0.09314009661835748,
"grad_norm": 2.10232463079107,
"learning_rate": 2e-05,
"loss": 0.7827877044677735,
"step": 2410
},
{
"epoch": 0.09352657004830918,
"grad_norm": 2.598171395066132,
"learning_rate": 2e-05,
"loss": 0.7785562038421631,
"step": 2420
},
{
"epoch": 0.09391304347826086,
"grad_norm": 1.1757264697207033,
"learning_rate": 2e-05,
"loss": 0.7309589385986328,
"step": 2430
},
{
"epoch": 0.09429951690821256,
"grad_norm": 1.6443213162705979,
"learning_rate": 2e-05,
"loss": 0.7487944602966309,
"step": 2440
},
{
"epoch": 0.09468599033816426,
"grad_norm": 1.2468919443245798,
"learning_rate": 2e-05,
"loss": 0.7694966793060303,
"step": 2450
},
{
"epoch": 0.09507246376811594,
"grad_norm": 1.464565055146109,
"learning_rate": 2e-05,
"loss": 0.7803127288818359,
"step": 2460
},
{
"epoch": 0.09545893719806764,
"grad_norm": 3.8074836748750904,
"learning_rate": 2e-05,
"loss": 0.7282808303833008,
"step": 2470
},
{
"epoch": 0.09584541062801932,
"grad_norm": 6.896151811673643,
"learning_rate": 2e-05,
"loss": 0.7671591758728027,
"step": 2480
},
{
"epoch": 0.09623188405797102,
"grad_norm": 2.2239543445775425,
"learning_rate": 2e-05,
"loss": 0.7999413967132568,
"step": 2490
},
{
"epoch": 0.0966183574879227,
"grad_norm": 5.616878725097995,
"learning_rate": 2e-05,
"loss": 0.7862523078918457,
"step": 2500
},
{
"epoch": 0.0970048309178744,
"grad_norm": 1.627578685293566,
"learning_rate": 2e-05,
"loss": 0.7508011817932129,
"step": 2510
},
{
"epoch": 0.09739130434782609,
"grad_norm": 0.9906826307911483,
"learning_rate": 2e-05,
"loss": 0.7621040344238281,
"step": 2520
},
{
"epoch": 0.09777777777777778,
"grad_norm": 3.35224143508381,
"learning_rate": 2e-05,
"loss": 0.74591064453125,
"step": 2530
},
{
"epoch": 0.09816425120772947,
"grad_norm": 2.2671864034926354,
"learning_rate": 2e-05,
"loss": 0.7632014274597168,
"step": 2540
},
{
"epoch": 0.09855072463768116,
"grad_norm": 1.267319283410017,
"learning_rate": 2e-05,
"loss": 0.7705909729003906,
"step": 2550
},
{
"epoch": 0.09893719806763285,
"grad_norm": 2.8927069345813985,
"learning_rate": 2e-05,
"loss": 0.7812301635742187,
"step": 2560
},
{
"epoch": 0.09932367149758455,
"grad_norm": 1.4493285796125683,
"learning_rate": 2e-05,
"loss": 0.7883975028991699,
"step": 2570
},
{
"epoch": 0.09971014492753623,
"grad_norm": 1.2446418817300966,
"learning_rate": 2e-05,
"loss": 0.7746667385101318,
"step": 2580
},
{
"epoch": 0.10009661835748793,
"grad_norm": 3.217368686501776,
"learning_rate": 2e-05,
"loss": 0.7654871940612793,
"step": 2590
},
{
"epoch": 0.10048309178743961,
"grad_norm": 1.1883893155114615,
"learning_rate": 2e-05,
"loss": 0.7502057075500488,
"step": 2600
},
{
"epoch": 0.10086956521739131,
"grad_norm": 1.695556949452006,
"learning_rate": 2e-05,
"loss": 0.7216050148010253,
"step": 2610
},
{
"epoch": 0.10125603864734299,
"grad_norm": 3.473686297073087,
"learning_rate": 2e-05,
"loss": 0.7521714210510254,
"step": 2620
},
{
"epoch": 0.10164251207729469,
"grad_norm": 5.9788011582249805,
"learning_rate": 2e-05,
"loss": 0.7292653560638428,
"step": 2630
},
{
"epoch": 0.10202898550724637,
"grad_norm": 7.808440837834781,
"learning_rate": 2e-05,
"loss": 0.7407905101776123,
"step": 2640
},
{
"epoch": 0.10241545893719807,
"grad_norm": 2.5686061602885637,
"learning_rate": 2e-05,
"loss": 0.7778966426849365,
"step": 2650
},
{
"epoch": 0.10280193236714975,
"grad_norm": 3.154626905551962,
"learning_rate": 2e-05,
"loss": 0.7876219749450684,
"step": 2660
},
{
"epoch": 0.10318840579710145,
"grad_norm": 3.468843923168503,
"learning_rate": 2e-05,
"loss": 0.7734580039978027,
"step": 2670
},
{
"epoch": 0.10357487922705313,
"grad_norm": 8.009584748577065,
"learning_rate": 2e-05,
"loss": 0.7431020259857177,
"step": 2680
},
{
"epoch": 0.10396135265700483,
"grad_norm": 2.6545478840796384,
"learning_rate": 2e-05,
"loss": 0.7354369163513184,
"step": 2690
},
{
"epoch": 0.10434782608695652,
"grad_norm": 3.013460214296052,
"learning_rate": 2e-05,
"loss": 0.7398846626281739,
"step": 2700
},
{
"epoch": 0.10473429951690821,
"grad_norm": 2.8697969948962103,
"learning_rate": 2e-05,
"loss": 0.774082088470459,
"step": 2710
},
{
"epoch": 0.1051207729468599,
"grad_norm": 4.130301132781164,
"learning_rate": 2e-05,
"loss": 0.7540542125701905,
"step": 2720
},
{
"epoch": 0.1055072463768116,
"grad_norm": 3.24272431858663,
"learning_rate": 2e-05,
"loss": 0.7488170146942139,
"step": 2730
},
{
"epoch": 0.10589371980676328,
"grad_norm": 5.974999494911175,
"learning_rate": 2e-05,
"loss": 0.7478822231292724,
"step": 2740
},
{
"epoch": 0.10628019323671498,
"grad_norm": 10.37771215379445,
"learning_rate": 2e-05,
"loss": 0.7524117469787598,
"step": 2750
},
{
"epoch": 0.10666666666666667,
"grad_norm": 2.3430180737894437,
"learning_rate": 2e-05,
"loss": 0.7408059597015381,
"step": 2760
},
{
"epoch": 0.10705314009661836,
"grad_norm": 2.518159773041028,
"learning_rate": 2e-05,
"loss": 0.7606561183929443,
"step": 2770
},
{
"epoch": 0.10743961352657005,
"grad_norm": 4.228058376115772,
"learning_rate": 2e-05,
"loss": 0.7550743103027344,
"step": 2780
},
{
"epoch": 0.10782608695652174,
"grad_norm": 2.0014204387088883,
"learning_rate": 2e-05,
"loss": 0.7893956184387207,
"step": 2790
},
{
"epoch": 0.10821256038647344,
"grad_norm": 1.4580798360101905,
"learning_rate": 2e-05,
"loss": 0.7935238838195801,
"step": 2800
},
{
"epoch": 0.10859903381642512,
"grad_norm": 1.440341687449925,
"learning_rate": 2e-05,
"loss": 0.7824203491210937,
"step": 2810
},
{
"epoch": 0.10898550724637682,
"grad_norm": 1.4960713444728275,
"learning_rate": 2e-05,
"loss": 0.7783860683441162,
"step": 2820
},
{
"epoch": 0.1093719806763285,
"grad_norm": 4.912105643942074,
"learning_rate": 2e-05,
"loss": 0.7596704483032226,
"step": 2830
},
{
"epoch": 0.1097584541062802,
"grad_norm": 4.039027525263609,
"learning_rate": 2e-05,
"loss": 0.7591814994812012,
"step": 2840
},
{
"epoch": 0.11014492753623188,
"grad_norm": 1.5391399654261342,
"learning_rate": 2e-05,
"loss": 0.7540448665618896,
"step": 2850
},
{
"epoch": 0.11053140096618358,
"grad_norm": 1.3907629383677877,
"learning_rate": 2e-05,
"loss": 0.7578011989593506,
"step": 2860
},
{
"epoch": 0.11091787439613526,
"grad_norm": 2.418756458605362,
"learning_rate": 2e-05,
"loss": 0.7361119747161865,
"step": 2870
},
{
"epoch": 0.11130434782608696,
"grad_norm": 3.739348851910294,
"learning_rate": 2e-05,
"loss": 0.7639998912811279,
"step": 2880
},
{
"epoch": 0.11169082125603864,
"grad_norm": 1.670125865609373,
"learning_rate": 2e-05,
"loss": 0.7774595260620117,
"step": 2890
},
{
"epoch": 0.11207729468599034,
"grad_norm": 1.7170327776104877,
"learning_rate": 2e-05,
"loss": 0.6949478149414062,
"step": 2900
},
{
"epoch": 0.11246376811594203,
"grad_norm": 2.4782554453410786,
"learning_rate": 2e-05,
"loss": 0.771298885345459,
"step": 2910
},
{
"epoch": 0.11285024154589372,
"grad_norm": 2.721787201809589,
"learning_rate": 2e-05,
"loss": 0.7795491695404053,
"step": 2920
},
{
"epoch": 0.1132367149758454,
"grad_norm": 1.8882417313191724,
"learning_rate": 2e-05,
"loss": 0.7629229545593261,
"step": 2930
},
{
"epoch": 0.1136231884057971,
"grad_norm": 1.020404408117238,
"learning_rate": 2e-05,
"loss": 0.7520963191986084,
"step": 2940
},
{
"epoch": 0.11400966183574879,
"grad_norm": 1.2953592621672139,
"learning_rate": 2e-05,
"loss": 0.7835359096527099,
"step": 2950
},
{
"epoch": 0.11439613526570049,
"grad_norm": 1.402126121933966,
"learning_rate": 2e-05,
"loss": 0.7469770431518554,
"step": 2960
},
{
"epoch": 0.11478260869565217,
"grad_norm": 1.0565102242948623,
"learning_rate": 2e-05,
"loss": 0.7419232845306396,
"step": 2970
},
{
"epoch": 0.11516908212560387,
"grad_norm": 1.2672419412998372,
"learning_rate": 2e-05,
"loss": 0.7683830261230469,
"step": 2980
},
{
"epoch": 0.11555555555555555,
"grad_norm": 2.401558201984435,
"learning_rate": 2e-05,
"loss": 0.7525971889495849,
"step": 2990
},
{
"epoch": 0.11594202898550725,
"grad_norm": 1.526434742827244,
"learning_rate": 2e-05,
"loss": 0.7671350002288818,
"step": 3000
},
{
"epoch": 0.11632850241545893,
"grad_norm": 1.3426982308084237,
"learning_rate": 2e-05,
"loss": 0.7217348098754883,
"step": 3010
},
{
"epoch": 0.11671497584541063,
"grad_norm": 2.5859563913304275,
"learning_rate": 2e-05,
"loss": 0.724910306930542,
"step": 3020
},
{
"epoch": 0.11710144927536231,
"grad_norm": 1.6037857614752977,
"learning_rate": 2e-05,
"loss": 0.7487847805023193,
"step": 3030
},
{
"epoch": 0.11748792270531401,
"grad_norm": 2.6902562084555504,
"learning_rate": 2e-05,
"loss": 0.7263116359710693,
"step": 3040
},
{
"epoch": 0.1178743961352657,
"grad_norm": 2.2878601990703658,
"learning_rate": 2e-05,
"loss": 0.7548857688903808,
"step": 3050
},
{
"epoch": 0.11826086956521739,
"grad_norm": 2.0090920961910994,
"learning_rate": 2e-05,
"loss": 0.7582263469696044,
"step": 3060
},
{
"epoch": 0.11864734299516909,
"grad_norm": 4.636914226969478,
"learning_rate": 2e-05,
"loss": 0.7098802089691162,
"step": 3070
},
{
"epoch": 0.11903381642512077,
"grad_norm": 10.632169657924953,
"learning_rate": 2e-05,
"loss": 0.7436557292938233,
"step": 3080
},
{
"epoch": 0.11942028985507247,
"grad_norm": 4.092776992680432,
"learning_rate": 2e-05,
"loss": 0.7685037136077881,
"step": 3090
},
{
"epoch": 0.11980676328502415,
"grad_norm": 2.2184443588512455,
"learning_rate": 2e-05,
"loss": 0.7629373073577881,
"step": 3100
},
{
"epoch": 0.12019323671497585,
"grad_norm": 5.981987414163901,
"learning_rate": 2e-05,
"loss": 0.7763461112976074,
"step": 3110
},
{
"epoch": 0.12057971014492753,
"grad_norm": 1.583113847170495,
"learning_rate": 2e-05,
"loss": 0.7681999206542969,
"step": 3120
},
{
"epoch": 0.12096618357487923,
"grad_norm": 1.481558880113795,
"learning_rate": 2e-05,
"loss": 0.7741986751556397,
"step": 3130
},
{
"epoch": 0.12135265700483092,
"grad_norm": 1.9151056127493966,
"learning_rate": 2e-05,
"loss": 0.7652425289154052,
"step": 3140
},
{
"epoch": 0.12173913043478261,
"grad_norm": 2.387560581863014,
"learning_rate": 2e-05,
"loss": 0.7649560451507569,
"step": 3150
},
{
"epoch": 0.1221256038647343,
"grad_norm": 1.1173760546950033,
"learning_rate": 2e-05,
"loss": 0.7181439876556397,
"step": 3160
},
{
"epoch": 0.122512077294686,
"grad_norm": 2.083761932159444,
"learning_rate": 2e-05,
"loss": 0.7495922088623047,
"step": 3170
},
{
"epoch": 0.12289855072463768,
"grad_norm": 1.1652939980593255,
"learning_rate": 2e-05,
"loss": 0.7515378475189209,
"step": 3180
},
{
"epoch": 0.12328502415458938,
"grad_norm": 1.4918368808564153,
"learning_rate": 2e-05,
"loss": 0.7546276092529297,
"step": 3190
},
{
"epoch": 0.12367149758454106,
"grad_norm": 1.0293176663426336,
"learning_rate": 2e-05,
"loss": 0.7552709579467773,
"step": 3200
},
{
"epoch": 0.12405797101449276,
"grad_norm": 1.1057665645933867,
"learning_rate": 2e-05,
"loss": 0.741522741317749,
"step": 3210
},
{
"epoch": 0.12444444444444444,
"grad_norm": 0.9363596854554345,
"learning_rate": 2e-05,
"loss": 0.7667788982391357,
"step": 3220
},
{
"epoch": 0.12483091787439614,
"grad_norm": 1.04985033716726,
"learning_rate": 2e-05,
"loss": 0.7525820732116699,
"step": 3230
},
{
"epoch": 0.12521739130434784,
"grad_norm": 7.721167519610794,
"learning_rate": 2e-05,
"loss": 0.7389856338500976,
"step": 3240
},
{
"epoch": 0.12560386473429952,
"grad_norm": 1.1895781786282957,
"learning_rate": 2e-05,
"loss": 0.7608234405517578,
"step": 3250
},
{
"epoch": 0.1259903381642512,
"grad_norm": 0.9818564982551652,
"learning_rate": 2e-05,
"loss": 0.7519477844238281,
"step": 3260
},
{
"epoch": 0.1263768115942029,
"grad_norm": 1.0761562982208566,
"learning_rate": 2e-05,
"loss": 0.7019442558288574,
"step": 3270
},
{
"epoch": 0.1267632850241546,
"grad_norm": 1.373293148249932,
"learning_rate": 2e-05,
"loss": 0.7445249557495117,
"step": 3280
},
{
"epoch": 0.12714975845410628,
"grad_norm": 1.1099005212509954,
"learning_rate": 2e-05,
"loss": 0.7563081741333008,
"step": 3290
},
{
"epoch": 0.12753623188405797,
"grad_norm": 1.046722701612444,
"learning_rate": 2e-05,
"loss": 0.7404123306274414,
"step": 3300
},
{
"epoch": 0.12792270531400965,
"grad_norm": 0.9518798965383707,
"learning_rate": 2e-05,
"loss": 0.740294361114502,
"step": 3310
},
{
"epoch": 0.12830917874396136,
"grad_norm": 0.9266301254714255,
"learning_rate": 2e-05,
"loss": 0.7460558891296387,
"step": 3320
},
{
"epoch": 0.12869565217391304,
"grad_norm": 1.4702716849340487,
"learning_rate": 2e-05,
"loss": 0.7604526519775391,
"step": 3330
},
{
"epoch": 0.12908212560386473,
"grad_norm": 0.9102929590923553,
"learning_rate": 2e-05,
"loss": 0.7236586570739746,
"step": 3340
},
{
"epoch": 0.1294685990338164,
"grad_norm": 1.6391901805267906,
"learning_rate": 2e-05,
"loss": 0.748450756072998,
"step": 3350
},
{
"epoch": 0.12985507246376812,
"grad_norm": 1.6075723054223627,
"learning_rate": 2e-05,
"loss": 0.7403520584106446,
"step": 3360
},
{
"epoch": 0.1302415458937198,
"grad_norm": 1.5094379479330864,
"learning_rate": 2e-05,
"loss": 0.7653777122497558,
"step": 3370
},
{
"epoch": 0.1306280193236715,
"grad_norm": 7.0703944204633125,
"learning_rate": 2e-05,
"loss": 0.7486815452575684,
"step": 3380
},
{
"epoch": 0.1310144927536232,
"grad_norm": 1.1641301126393144,
"learning_rate": 2e-05,
"loss": 0.7190661907196045,
"step": 3390
},
{
"epoch": 0.13140096618357489,
"grad_norm": 3.2432498754052586,
"learning_rate": 2e-05,
"loss": 0.7289729595184327,
"step": 3400
},
{
"epoch": 0.13178743961352657,
"grad_norm": 1.7875108272154512,
"learning_rate": 2e-05,
"loss": 0.7148953437805176,
"step": 3410
},
{
"epoch": 0.13217391304347825,
"grad_norm": 2.3978591933447944,
"learning_rate": 2e-05,
"loss": 0.7307319641113281,
"step": 3420
},
{
"epoch": 0.13256038647342996,
"grad_norm": 1.090192637666955,
"learning_rate": 2e-05,
"loss": 0.719948673248291,
"step": 3430
},
{
"epoch": 0.13294685990338165,
"grad_norm": 2.38275417744872,
"learning_rate": 2e-05,
"loss": 0.7476545333862304,
"step": 3440
},
{
"epoch": 0.13333333333333333,
"grad_norm": 1.3431211574818809,
"learning_rate": 2e-05,
"loss": 0.756253719329834,
"step": 3450
},
{
"epoch": 0.13371980676328502,
"grad_norm": 3.805683855046064,
"learning_rate": 2e-05,
"loss": 0.7468399047851563,
"step": 3460
},
{
"epoch": 0.13410628019323673,
"grad_norm": 2.2843861478547156,
"learning_rate": 2e-05,
"loss": 0.7557847499847412,
"step": 3470
},
{
"epoch": 0.1344927536231884,
"grad_norm": 1.2152156459163166,
"learning_rate": 2e-05,
"loss": 0.7322972774505615,
"step": 3480
},
{
"epoch": 0.1348792270531401,
"grad_norm": 1.1054501561944003,
"learning_rate": 2e-05,
"loss": 0.7517436027526856,
"step": 3490
},
{
"epoch": 0.13526570048309178,
"grad_norm": 1.091680834103932,
"learning_rate": 2e-05,
"loss": 0.7240757942199707,
"step": 3500
},
{
"epoch": 0.1356521739130435,
"grad_norm": 1.3237009823355679,
"learning_rate": 2e-05,
"loss": 0.7183950424194336,
"step": 3510
},
{
"epoch": 0.13603864734299517,
"grad_norm": 1.370967554841046,
"learning_rate": 2e-05,
"loss": 0.7314060211181641,
"step": 3520
},
{
"epoch": 0.13642512077294686,
"grad_norm": 2.723221150680608,
"learning_rate": 2e-05,
"loss": 0.7527001857757568,
"step": 3530
},
{
"epoch": 0.13681159420289854,
"grad_norm": 1.643858518959685,
"learning_rate": 2e-05,
"loss": 0.7089616775512695,
"step": 3540
},
{
"epoch": 0.13719806763285025,
"grad_norm": 1.8011121015120353,
"learning_rate": 2e-05,
"loss": 0.7594071865081787,
"step": 3550
},
{
"epoch": 0.13758454106280193,
"grad_norm": 1.4392224952583492,
"learning_rate": 2e-05,
"loss": 0.7581882476806641,
"step": 3560
},
{
"epoch": 0.13797101449275362,
"grad_norm": 1.865868005098526,
"learning_rate": 2e-05,
"loss": 0.7558856964111328,
"step": 3570
},
{
"epoch": 0.1383574879227053,
"grad_norm": 1.6923737573552522,
"learning_rate": 2e-05,
"loss": 0.7306047439575195,
"step": 3580
},
{
"epoch": 0.138743961352657,
"grad_norm": 1.88507424299738,
"learning_rate": 2e-05,
"loss": 0.7101869106292724,
"step": 3590
},
{
"epoch": 0.1391304347826087,
"grad_norm": 0.9924120914192339,
"learning_rate": 2e-05,
"loss": 0.7175912380218505,
"step": 3600
},
{
"epoch": 0.13951690821256038,
"grad_norm": 0.8927761483995479,
"learning_rate": 2e-05,
"loss": 0.7569256782531738,
"step": 3610
},
{
"epoch": 0.13990338164251206,
"grad_norm": 1.3692755664777077,
"learning_rate": 2e-05,
"loss": 0.7137792110443115,
"step": 3620
},
{
"epoch": 0.14028985507246378,
"grad_norm": 1.0524944418131104,
"learning_rate": 2e-05,
"loss": 0.744718360900879,
"step": 3630
},
{
"epoch": 0.14067632850241546,
"grad_norm": 2.0607924335998846,
"learning_rate": 2e-05,
"loss": 0.7238254547119141,
"step": 3640
},
{
"epoch": 0.14106280193236714,
"grad_norm": 0.9979369127767396,
"learning_rate": 2e-05,
"loss": 0.7257954597473144,
"step": 3650
},
{
"epoch": 0.14144927536231883,
"grad_norm": 1.055922473652503,
"learning_rate": 2e-05,
"loss": 0.7422584533691406,
"step": 3660
},
{
"epoch": 0.14183574879227054,
"grad_norm": 1.5689729751838162,
"learning_rate": 2e-05,
"loss": 0.7416232585906982,
"step": 3670
},
{
"epoch": 0.14222222222222222,
"grad_norm": 1.8868421803920619,
"learning_rate": 2e-05,
"loss": 0.7324557304382324,
"step": 3680
},
{
"epoch": 0.1426086956521739,
"grad_norm": 12.329809011991264,
"learning_rate": 2e-05,
"loss": 0.7361815929412842,
"step": 3690
},
{
"epoch": 0.14299516908212562,
"grad_norm": 1.0839203997009181,
"learning_rate": 2e-05,
"loss": 0.7092767238616944,
"step": 3700
},
{
"epoch": 0.1433816425120773,
"grad_norm": 0.9551779050924308,
"learning_rate": 2e-05,
"loss": 0.7078923225402832,
"step": 3710
},
{
"epoch": 0.14376811594202898,
"grad_norm": 2.91617148391284,
"learning_rate": 2e-05,
"loss": 0.6721621513366699,
"step": 3720
},
{
"epoch": 0.14415458937198067,
"grad_norm": 0.8751905547586575,
"learning_rate": 2e-05,
"loss": 0.7346085548400879,
"step": 3730
},
{
"epoch": 0.14454106280193238,
"grad_norm": 2.454493767312037,
"learning_rate": 2e-05,
"loss": 0.7111119747161865,
"step": 3740
},
{
"epoch": 0.14492753623188406,
"grad_norm": 1.098230072601708,
"learning_rate": 2e-05,
"loss": 0.7394096374511718,
"step": 3750
},
{
"epoch": 0.14531400966183575,
"grad_norm": 0.847309564400027,
"learning_rate": 2e-05,
"loss": 0.745591688156128,
"step": 3760
},
{
"epoch": 0.14570048309178743,
"grad_norm": 0.8994061014918723,
"learning_rate": 2e-05,
"loss": 0.7250127792358398,
"step": 3770
},
{
"epoch": 0.14608695652173914,
"grad_norm": 1.3998490193646915,
"learning_rate": 2e-05,
"loss": 0.735257625579834,
"step": 3780
},
{
"epoch": 0.14647342995169083,
"grad_norm": 0.9361364759050644,
"learning_rate": 2e-05,
"loss": 0.7239673614501954,
"step": 3790
},
{
"epoch": 0.1468599033816425,
"grad_norm": 1.2674676404999363,
"learning_rate": 2e-05,
"loss": 0.7421964645385742,
"step": 3800
},
{
"epoch": 0.1472463768115942,
"grad_norm": 1.0867546663958008,
"learning_rate": 2e-05,
"loss": 0.7409372329711914,
"step": 3810
},
{
"epoch": 0.1476328502415459,
"grad_norm": 0.9949696992154828,
"learning_rate": 2e-05,
"loss": 0.7259463787078857,
"step": 3820
},
{
"epoch": 0.1480193236714976,
"grad_norm": 0.883986580274618,
"learning_rate": 2e-05,
"loss": 0.7099449157714843,
"step": 3830
},
{
"epoch": 0.14840579710144927,
"grad_norm": 2.2514274137395276,
"learning_rate": 2e-05,
"loss": 0.7430593490600585,
"step": 3840
},
{
"epoch": 0.14879227053140096,
"grad_norm": 1.0936205656684879,
"learning_rate": 2e-05,
"loss": 0.7251758098602294,
"step": 3850
},
{
"epoch": 0.14917874396135267,
"grad_norm": 1.383671343879474,
"learning_rate": 2e-05,
"loss": 0.7615509986877441,
"step": 3860
},
{
"epoch": 0.14956521739130435,
"grad_norm": 1.443464485447786,
"learning_rate": 2e-05,
"loss": 0.7056533813476562,
"step": 3870
},
{
"epoch": 0.14995169082125603,
"grad_norm": 1.064261115918148,
"learning_rate": 2e-05,
"loss": 0.71234130859375,
"step": 3880
},
{
"epoch": 0.15033816425120772,
"grad_norm": 1.0827805440023188,
"learning_rate": 2e-05,
"loss": 0.7419578552246093,
"step": 3890
},
{
"epoch": 0.15072463768115943,
"grad_norm": 1.6136927301190087,
"learning_rate": 2e-05,
"loss": 0.707129955291748,
"step": 3900
},
{
"epoch": 0.1511111111111111,
"grad_norm": 1.249721503946207,
"learning_rate": 2e-05,
"loss": 0.731418228149414,
"step": 3910
},
{
"epoch": 0.1514975845410628,
"grad_norm": 3.687096122389948,
"learning_rate": 2e-05,
"loss": 0.7409755229949951,
"step": 3920
},
{
"epoch": 0.15188405797101448,
"grad_norm": 1.5686049606063899,
"learning_rate": 2e-05,
"loss": 0.7458938121795654,
"step": 3930
},
{
"epoch": 0.1522705314009662,
"grad_norm": 3.820752682189002,
"learning_rate": 2e-05,
"loss": 0.720269775390625,
"step": 3940
},
{
"epoch": 0.15265700483091788,
"grad_norm": 1.1513505198950094,
"learning_rate": 2e-05,
"loss": 0.6879904747009278,
"step": 3950
},
{
"epoch": 0.15304347826086956,
"grad_norm": 9.485762994064826,
"learning_rate": 2e-05,
"loss": 0.7602463722229004,
"step": 3960
},
{
"epoch": 0.15342995169082124,
"grad_norm": 1.8772387698538013,
"learning_rate": 2e-05,
"loss": 0.7675003051757813,
"step": 3970
},
{
"epoch": 0.15381642512077295,
"grad_norm": 1.355858239389418,
"learning_rate": 2e-05,
"loss": 0.7349637031555176,
"step": 3980
},
{
"epoch": 0.15420289855072464,
"grad_norm": 1.8300137058507315,
"learning_rate": 2e-05,
"loss": 0.741055679321289,
"step": 3990
},
{
"epoch": 0.15458937198067632,
"grad_norm": 1.411446637818369,
"learning_rate": 2e-05,
"loss": 0.7304685115814209,
"step": 4000
},
{
"epoch": 0.15497584541062803,
"grad_norm": 1.3254261860847476,
"learning_rate": 2e-05,
"loss": 0.7354779720306397,
"step": 4010
},
{
"epoch": 0.15536231884057972,
"grad_norm": 1.9083967216165392,
"learning_rate": 2e-05,
"loss": 0.7637022972106934,
"step": 4020
},
{
"epoch": 0.1557487922705314,
"grad_norm": 1.1440526920208254,
"learning_rate": 2e-05,
"loss": 0.7484094619750976,
"step": 4030
},
{
"epoch": 0.15613526570048308,
"grad_norm": 0.8919705614319361,
"learning_rate": 2e-05,
"loss": 0.7086593627929687,
"step": 4040
},
{
"epoch": 0.1565217391304348,
"grad_norm": 1.6998920732383438,
"learning_rate": 2e-05,
"loss": 0.7250052928924561,
"step": 4050
},
{
"epoch": 0.15690821256038648,
"grad_norm": 1.3826627270101395,
"learning_rate": 2e-05,
"loss": 0.726510763168335,
"step": 4060
},
{
"epoch": 0.15729468599033816,
"grad_norm": 1.6908756019041942,
"learning_rate": 2e-05,
"loss": 0.7307948112487793,
"step": 4070
}
],
"logging_steps": 10,
"max_steps": 5935,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 2035,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1927226987642880.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}