{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 210.173828125,
      "learning_rate": 6.000000000000001e-07,
      "loss": 8.791841125488281,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 161.85198974609375,
      "learning_rate": 1.2666666666666669e-06,
      "loss": 6.186199951171875,
      "step": 20
    },
    {
      "epoch": 0.06,
      "grad_norm": 79.59968566894531,
      "learning_rate": 1.9333333333333336e-06,
      "loss": 5.037051010131836,
      "step": 30
    },
    {
      "epoch": 0.08,
      "grad_norm": 77.91535949707031,
      "learning_rate": 2.6e-06,
      "loss": 3.229383850097656,
      "step": 40
    },
    {
      "epoch": 0.1,
      "grad_norm": 45.42420959472656,
      "learning_rate": 3.266666666666667e-06,
      "loss": 2.6033956527709963,
      "step": 50
    },
    {
      "epoch": 0.12,
      "grad_norm": 41.46728515625,
      "learning_rate": 3.9333333333333335e-06,
      "loss": 2.942063903808594,
      "step": 60
    },
    {
      "epoch": 0.14,
      "grad_norm": 78.79148864746094,
      "learning_rate": 4.600000000000001e-06,
      "loss": 2.450759506225586,
      "step": 70
    },
    {
      "epoch": 0.16,
      "grad_norm": 62.13072967529297,
      "learning_rate": 5.2666666666666665e-06,
      "loss": 2.3624486923217773,
      "step": 80
    },
    {
      "epoch": 0.18,
      "grad_norm": 52.63612747192383,
      "learning_rate": 5.933333333333335e-06,
      "loss": 1.8120697021484375,
      "step": 90
    },
    {
      "epoch": 0.2,
      "grad_norm": 67.64952850341797,
      "learning_rate": 6.600000000000001e-06,
      "loss": 2.04521484375,
      "step": 100
    },
    {
      "epoch": 0.22,
      "grad_norm": 43.48116683959961,
      "learning_rate": 7.266666666666668e-06,
      "loss": 2.3016538619995117,
      "step": 110
    },
    {
      "epoch": 0.24,
      "grad_norm": 51.687042236328125,
      "learning_rate": 7.933333333333334e-06,
      "loss": 2.394601821899414,
      "step": 120
    },
    {
      "epoch": 0.26,
      "grad_norm": 66.71311950683594,
      "learning_rate": 8.6e-06,
      "loss": 2.0336360931396484,
      "step": 130
    },
    {
      "epoch": 0.28,
      "grad_norm": 44.05624771118164,
      "learning_rate": 9.266666666666667e-06,
      "loss": 2.5297100067138674,
      "step": 140
    },
    {
      "epoch": 0.3,
      "grad_norm": 43.44951629638672,
      "learning_rate": 9.933333333333334e-06,
      "loss": 2.532087707519531,
      "step": 150
    },
    {
      "epoch": 0.32,
      "grad_norm": 39.6384162902832,
      "learning_rate": 9.998903417374228e-06,
      "loss": 2.106338310241699,
      "step": 160
    },
    {
      "epoch": 0.34,
      "grad_norm": 38.4444694519043,
      "learning_rate": 9.995113378907791e-06,
      "loss": 1.8893505096435548,
      "step": 170
    },
    {
      "epoch": 0.36,
      "grad_norm": 40.845069885253906,
      "learning_rate": 9.988618398427495e-06,
      "loss": 2.187959671020508,
      "step": 180
    },
    {
      "epoch": 0.38,
      "grad_norm": 32.24748611450195,
      "learning_rate": 9.979421993079853e-06,
      "loss": 2.390948677062988,
      "step": 190
    },
    {
      "epoch": 0.4,
      "grad_norm": 47.72621536254883,
      "learning_rate": 9.967529142880592e-06,
      "loss": 2.4106063842773438,
      "step": 200
    },
    {
      "epoch": 0.42,
      "grad_norm": 25.50874137878418,
      "learning_rate": 9.952946288017899e-06,
      "loss": 2.082447624206543,
      "step": 210
    },
    {
      "epoch": 0.44,
      "grad_norm": 51.26837158203125,
      "learning_rate": 9.93568132536494e-06,
      "loss": 2.0642595291137695,
      "step": 220
    },
    {
      "epoch": 0.46,
      "grad_norm": 65.230712890625,
      "learning_rate": 9.915743604203563e-06,
      "loss": 2.5710067749023438,
      "step": 230
    },
    {
      "epoch": 0.48,
      "grad_norm": 37.009708404541016,
      "learning_rate": 9.893143921161501e-06,
      "loss": 2.123330307006836,
      "step": 240
    },
    {
      "epoch": 0.5,
      "grad_norm": 42.43490982055664,
      "learning_rate": 9.867894514365802e-06,
      "loss": 2.516407012939453,
      "step": 250
    },
    {
      "epoch": 0.52,
      "grad_norm": 33.466773986816406,
      "learning_rate": 9.840009056815674e-06,
      "loss": 2.5996524810791017,
      "step": 260
    },
    {
      "epoch": 0.54,
      "grad_norm": 38.300453186035156,
      "learning_rate": 9.809502648978311e-06,
      "loss": 2.2154964447021483,
      "step": 270
    },
    {
      "epoch": 0.56,
      "grad_norm": 41.977272033691406,
      "learning_rate": 9.776391810611719e-06,
      "loss": 2.7604133605957033,
      "step": 280
    },
    {
      "epoch": 0.58,
      "grad_norm": 39.470916748046875,
      "learning_rate": 9.740694471818988e-06,
      "loss": 2.422298240661621,
      "step": 290
    },
    {
      "epoch": 0.6,
      "grad_norm": 25.746841430664062,
      "learning_rate": 9.702429963338812e-06,
      "loss": 1.9244077682495118,
      "step": 300
    },
    {
      "epoch": 0.62,
      "grad_norm": 61.744041442871094,
      "learning_rate": 9.661619006077562e-06,
      "loss": 1.9998054504394531,
      "step": 310
    },
    {
      "epoch": 0.64,
      "grad_norm": 81.94461822509766,
      "learning_rate": 9.618283699888543e-06,
      "loss": 2.256130027770996,
      "step": 320
    },
    {
      "epoch": 0.66,
      "grad_norm": 35.797786712646484,
      "learning_rate": 9.572447511604536e-06,
      "loss": 2.06947021484375,
      "step": 330
    },
    {
      "epoch": 0.68,
      "grad_norm": 32.96639633178711,
      "learning_rate": 9.524135262330098e-06,
      "loss": 2.0332563400268553,
      "step": 340
    },
    {
      "epoch": 0.7,
      "grad_norm": 32.352699279785156,
      "learning_rate": 9.473373114000493e-06,
      "loss": 2.068455696105957,
      "step": 350
    },
    {
      "epoch": 0.72,
      "grad_norm": 38.09100341796875,
      "learning_rate": 9.420188555214537e-06,
      "loss": 2.32584171295166,
      "step": 360
    },
    {
      "epoch": 0.74,
      "grad_norm": 50.007049560546875,
      "learning_rate": 9.364610386349048e-06,
      "loss": 2.5027301788330076,
      "step": 370
    },
    {
      "epoch": 0.76,
      "grad_norm": 27.599956512451172,
      "learning_rate": 9.306668703962927e-06,
      "loss": 2.2121116638183596,
      "step": 380
    },
    {
      "epoch": 0.78,
      "grad_norm": 36.08063507080078,
      "learning_rate": 9.246394884499334e-06,
      "loss": 2.542919158935547,
      "step": 390
    },
    {
      "epoch": 0.8,
      "grad_norm": 49.41411209106445,
      "learning_rate": 9.18382156729481e-06,
      "loss": 1.9286565780639648,
      "step": 400
    },
    {
      "epoch": 0.82,
      "grad_norm": 54.925540924072266,
      "learning_rate": 9.118982636904476e-06,
      "loss": 2.313096809387207,
      "step": 410
    },
    {
      "epoch": 0.84,
      "grad_norm": 56.74051284790039,
      "learning_rate": 9.051913204752972e-06,
      "loss": 2.0929283142089843,
      "step": 420
    },
    {
      "epoch": 0.86,
      "grad_norm": 24.994333267211914,
      "learning_rate": 8.982649590120982e-06,
      "loss": 2.0113702774047852,
      "step": 430
    },
    {
      "epoch": 0.88,
      "grad_norm": 41.89128494262695,
      "learning_rate": 8.911229300477716e-06,
      "loss": 1.6521787643432617,
      "step": 440
    },
    {
      "epoch": 0.9,
      "grad_norm": 44.65105438232422,
      "learning_rate": 8.837691011169944e-06,
      "loss": 2.2836629867553713,
      "step": 450
    },
    {
      "epoch": 0.92,
      "grad_norm": 42.151737213134766,
      "learning_rate": 8.762074544478622e-06,
      "loss": 1.705312156677246,
      "step": 460
    },
    {
      "epoch": 0.94,
      "grad_norm": 36.330989837646484,
      "learning_rate": 8.68442084805442e-06,
      "loss": 1.4402057647705078,
      "step": 470
    },
    {
      "epoch": 0.96,
      "grad_norm": 27.495149612426758,
      "learning_rate": 8.604771972743848e-06,
      "loss": 1.9172407150268556,
      "step": 480
    },
    {
      "epoch": 0.98,
      "grad_norm": 17.782899856567383,
      "learning_rate": 8.523171049817974e-06,
      "loss": 1.5030399322509767,
      "step": 490
    },
    {
      "epoch": 1.0,
      "grad_norm": 34.83807373046875,
      "learning_rate": 8.439662267616093e-06,
      "loss": 1.9837615966796875,
      "step": 500
    },
    {
      "epoch": 1.02,
      "grad_norm": 13.142373085021973,
      "learning_rate": 8.354290847616954e-06,
      "loss": 1.2435311317443847,
      "step": 510
    },
    {
      "epoch": 1.04,
      "grad_norm": 37.417720794677734,
      "learning_rate": 8.267103019950529e-06,
      "loss": 1.23653564453125,
      "step": 520
    },
    {
      "epoch": 1.06,
      "grad_norm": 18.470767974853516,
      "learning_rate": 8.178145998363585e-06,
      "loss": 0.8462669372558593,
      "step": 530
    },
    {
      "epoch": 1.08,
      "grad_norm": 27.512048721313477,
      "learning_rate": 8.087467954652608e-06,
      "loss": 1.2925146102905274,
      "step": 540
    },
    {
      "epoch": 1.1,
      "grad_norm": 37.81305694580078,
      "learning_rate": 7.99511799257793e-06,
      "loss": 0.901913833618164,
      "step": 550
    },
    {
      "epoch": 1.12,
      "grad_norm": 37.69697570800781,
      "learning_rate": 7.901146121273165e-06,
      "loss": 1.3357799530029297,
      "step": 560
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 34.828433990478516,
      "learning_rate": 7.80560322816439e-06,
      "loss": 1.3306777954101563,
      "step": 570
    },
    {
      "epoch": 1.16,
      "grad_norm": 38.92500305175781,
      "learning_rate": 7.7085410514137e-06,
      "loss": 0.944632625579834,
      "step": 580
    },
    {
      "epoch": 1.18,
      "grad_norm": 19.071941375732422,
      "learning_rate": 7.610012151902091e-06,
      "loss": 1.3212141036987304,
      "step": 590
    },
    {
      "epoch": 1.2,
      "grad_norm": 34.952938079833984,
      "learning_rate": 7.510069884766802e-06,
      "loss": 1.2321388244628906,
      "step": 600
    },
    {
      "epoch": 1.22,
      "grad_norm": 32.1840934753418,
      "learning_rate": 7.408768370508577e-06,
      "loss": 1.3100163459777832,
      "step": 610
    },
    {
      "epoch": 1.24,
      "grad_norm": 23.4957275390625,
      "learning_rate": 7.3061624656844544e-06,
      "loss": 1.179959774017334,
      "step": 620
    },
    {
      "epoch": 1.26,
      "grad_norm": 40.54483413696289,
      "learning_rate": 7.2023077332019755e-06,
      "loss": 0.8590527534484863,
      "step": 630
    },
    {
      "epoch": 1.28,
      "grad_norm": 42.49688720703125,
      "learning_rate": 7.0972604122308865e-06,
      "loss": 1.3245353698730469,
      "step": 640
    },
    {
      "epoch": 1.3,
      "grad_norm": 38.857479095458984,
      "learning_rate": 6.991077387748643e-06,
      "loss": 0.9064340591430664,
      "step": 650
    },
    {
      "epoch": 1.32,
      "grad_norm": 24.489877700805664,
      "learning_rate": 6.883816159736187e-06,
      "loss": 1.3220383644104003,
      "step": 660
    },
    {
      "epoch": 1.34,
      "grad_norm": 18.46355628967285,
      "learning_rate": 6.775534812040686e-06,
      "loss": 0.7077834129333496,
      "step": 670
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 24.25245475769043,
      "learning_rate": 6.666291980922122e-06,
      "loss": 0.9919247627258301,
      "step": 680
    },
    {
      "epoch": 1.38,
      "grad_norm": 48.17041778564453,
      "learning_rate": 6.556146823300701e-06,
      "loss": 1.6220426559448242,
      "step": 690
    },
    {
      "epoch": 1.4,
      "grad_norm": 47.63260269165039,
      "learning_rate": 6.445158984722358e-06,
      "loss": 1.3412548065185548,
      "step": 700
    },
    {
      "epoch": 1.42,
      "grad_norm": 24.807323455810547,
      "learning_rate": 6.3333885670596285e-06,
      "loss": 1.2461795806884766,
      "step": 710
    },
    {
      "epoch": 1.44,
      "grad_norm": 11.098411560058594,
      "learning_rate": 6.220896095965428e-06,
      "loss": 1.0722078323364257,
      "step": 720
    },
    {
      "epoch": 1.46,
      "grad_norm": 36.12248611450195,
      "learning_rate": 6.107742488097338e-06,
      "loss": 0.83670015335083,
      "step": 730
    },
    {
      "epoch": 1.48,
      "grad_norm": 39.64963150024414,
      "learning_rate": 5.993989018130173e-06,
      "loss": 1.1005640029907227,
      "step": 740
    },
    {
      "epoch": 1.5,
      "grad_norm": 35.805389404296875,
      "learning_rate": 5.879697285574655e-06,
      "loss": 1.5326812744140625,
      "step": 750
    },
    {
      "epoch": 1.52,
      "grad_norm": 20.854694366455078,
      "learning_rate": 5.764929181420191e-06,
      "loss": 1.028077983856201,
      "step": 760
    },
    {
      "epoch": 1.54,
      "grad_norm": 19.16396141052246,
      "learning_rate": 5.649746854619814e-06,
      "loss": 1.1157980918884278,
      "step": 770
    },
    {
      "epoch": 1.56,
      "grad_norm": 26.597848892211914,
      "learning_rate": 5.5342126784354265e-06,
      "loss": 1.2585329055786132,
      "step": 780
    },
    {
      "epoch": 1.58,
      "grad_norm": 43.42577362060547,
      "learning_rate": 5.41838921666158e-06,
      "loss": 1.1203573226928711,
      "step": 790
    },
    {
      "epoch": 1.6,
      "grad_norm": 63.867942810058594,
      "learning_rate": 5.3023391897460715e-06,
      "loss": 1.0436135292053224,
      "step": 800
    },
    {
      "epoch": 1.62,
      "grad_norm": 36.27252960205078,
      "learning_rate": 5.18612544082573e-06,
      "loss": 0.9347926139831543,
      "step": 810
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 33.137611389160156,
      "learning_rate": 5.069810901695727e-06,
      "loss": 1.5266364097595215,
      "step": 820
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 46.118202209472656,
      "learning_rate": 4.953458558730917e-06,
      "loss": 1.1257129669189454,
      "step": 830
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 31.607257843017578,
      "learning_rate": 4.837131418777595e-06,
      "loss": 0.9643683433532715,
      "step": 840
    },
    {
      "epoch": 1.7,
      "grad_norm": 50.87643814086914,
      "learning_rate": 4.720892475034181e-06,
      "loss": 1.3242192268371582,
      "step": 850
    },
    {
      "epoch": 1.72,
      "grad_norm": 27.850143432617188,
      "learning_rate": 4.604804672939295e-06,
      "loss": 1.251343059539795,
      "step": 860
    },
    {
      "epoch": 1.74,
      "grad_norm": 45.26017379760742,
      "learning_rate": 4.4889308760856826e-06,
      "loss": 1.1028053283691406,
      "step": 870
    },
    {
      "epoch": 1.76,
      "grad_norm": 3.31717586517334,
      "learning_rate": 4.373333832178478e-06,
      "loss": 0.8769556045532226,
      "step": 880
    },
    {
      "epoch": 1.78,
      "grad_norm": 26.864580154418945,
      "learning_rate": 4.258076139056217e-06,
      "loss": 1.1681681632995606,
      "step": 890
    },
    {
      "epoch": 1.8,
      "grad_norm": 33.86524200439453,
      "learning_rate": 4.143220210792993e-06,
      "loss": 0.9344164848327636,
      "step": 900
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 25.299028396606445,
      "learning_rate": 4.028828243900141e-06,
      "loss": 1.634626579284668,
      "step": 910
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 28.403207778930664,
      "learning_rate": 3.914962183645733e-06,
      "loss": 1.0626420974731445,
      "step": 920
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 29.372901916503906,
      "learning_rate": 3.8016836905101157e-06,
      "loss": 1.375041389465332,
      "step": 930
    },
    {
      "epoch": 1.88,
      "grad_norm": 21.600330352783203,
      "learning_rate": 3.6890541067956775e-06,
      "loss": 0.9415129661560059,
      "step": 940
    },
    {
      "epoch": 1.9,
      "grad_norm": 20.263734817504883,
      "learning_rate": 3.577134423408906e-06,
      "loss": 0.8620157241821289,
      "step": 950
    },
    {
      "epoch": 1.92,
      "grad_norm": 37.88676834106445,
      "learning_rate": 3.465985246832739e-06,
      "loss": 1.1039237976074219,
      "step": 960
    },
    {
      "epoch": 1.94,
      "grad_norm": 8.769469261169434,
      "learning_rate": 3.355666766307084e-06,
      "loss": 0.8490506172180176,
      "step": 970
    },
    {
      "epoch": 1.96,
      "grad_norm": 44.77504348754883,
      "learning_rate": 3.246238721235283e-06,
      "loss": 1.2799974441528321,
      "step": 980
    },
    {
      "epoch": 1.98,
      "grad_norm": 15.338781356811523,
      "learning_rate": 3.137760368834169e-06,
      "loss": 0.8015480995178222,
      "step": 990
    },
    {
      "epoch": 2.0,
      "grad_norm": 33.2166748046875,
      "learning_rate": 3.030290452045245e-06,
      "loss": 1.091315746307373,
      "step": 1000
    },
    {
      "epoch": 2.02,
      "grad_norm": 4.909487247467041,
      "learning_rate": 2.9238871677243354e-06,
      "loss": 0.47315549850463867,
      "step": 1010
    },
    {
      "epoch": 2.04,
      "grad_norm": 39.29719161987305,
      "learning_rate": 2.818608135126967e-06,
      "loss": 0.3728752613067627,
      "step": 1020
    },
    {
      "epoch": 2.06,
      "grad_norm": 21.967544555664062,
      "learning_rate": 2.714510364706531e-06,
      "loss": 0.33084559440612793,
      "step": 1030
    },
    {
      "epoch": 2.08,
      "grad_norm": 25.645288467407227,
      "learning_rate": 2.611650227242102e-06,
      "loss": 0.32590973377227783,
      "step": 1040
    },
    {
      "epoch": 2.1,
      "grad_norm": 18.202743530273438,
      "learning_rate": 2.5100834233126827e-06,
      "loss": 0.4684451580047607,
      "step": 1050
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.5234746336936951,
      "learning_rate": 2.40986495313435e-06,
      "loss": 0.26931188106536863,
      "step": 1060
    },
    {
      "epoch": 2.14,
      "grad_norm": 21.24897575378418,
      "learning_rate": 2.3110490867766644e-06,
      "loss": 0.499393892288208,
      "step": 1070
    },
    {
      "epoch": 2.16,
      "grad_norm": 13.816218376159668,
      "learning_rate": 2.213689334774479e-06,
      "loss": 0.3078450202941895,
      "step": 1080
    },
    {
      "epoch": 2.18,
      "grad_norm": 23.9191837310791,
      "learning_rate": 2.1178384191510344e-06,
      "loss": 0.47670416831970214,
      "step": 1090
    },
    {
      "epoch": 2.2,
      "grad_norm": 34.2762451171875,
      "learning_rate": 2.023548244868051e-06,
      "loss": 0.47382168769836425,
      "step": 1100
    },
    {
      "epoch": 2.22,
      "grad_norm": 19.34497833251953,
      "learning_rate": 1.9308698717182874e-06,
      "loss": 0.19442765712738036,
      "step": 1110
    },
    {
      "epoch": 2.24,
      "grad_norm": 28.95246124267578,
      "learning_rate": 1.8398534866757455e-06,
      "loss": 0.44660329818725586,
      "step": 1120
    },
    {
      "epoch": 2.26,
      "grad_norm": 1.9053665399551392,
      "learning_rate": 1.7505483767185583e-06,
      "loss": 0.36274888515472414,
      "step": 1130
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 31.379884719848633,
      "learning_rate": 1.6630029021392007e-06,
      "loss": 0.24480688571929932,
      "step": 1140
    },
    {
      "epoch": 2.3,
      "grad_norm": 17.360788345336914,
      "learning_rate": 1.5772644703565564e-06,
      "loss": 0.14373520612716675,
      "step": 1150
    },
    {
      "epoch": 2.32,
      "grad_norm": 36.79311752319336,
      "learning_rate": 1.4933795102439558e-06,
      "loss": 0.34253692626953125,
      "step": 1160
    },
    {
      "epoch": 2.34,
      "grad_norm": 9.673837661743164,
      "learning_rate": 1.4113934469871166e-06,
      "loss": 0.1978028893470764,
      "step": 1170
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.5280386805534363,
      "learning_rate": 1.3313506774856177e-06,
      "loss": 0.29554598331451415,
      "step": 1180
    },
    {
      "epoch": 2.38,
      "grad_norm": 1.7119940519332886,
      "learning_rate": 1.2532945463111856e-06,
      "loss": 0.3423331260681152,
      "step": 1190
    },
    {
      "epoch": 2.4,
      "grad_norm": 9.490172386169434,
      "learning_rate": 1.1772673222358421e-06,
      "loss": 0.3274805784225464,
      "step": 1200
    },
    {
      "epoch": 2.42,
      "grad_norm": 2.7689626216888428,
      "learning_rate": 1.1033101753426285e-06,
      "loss": 0.29171273708343504,
      "step": 1210
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.009632566943764687,
      "learning_rate": 1.0314631547312738e-06,
      "loss": 0.2250969171524048,
      "step": 1220
    },
    {
      "epoch": 2.46,
      "grad_norm": 46.948333740234375,
      "learning_rate": 9.617651668308914e-07,
      "loss": 0.2975991487503052,
      "step": 1230
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.1608089804649353,
      "learning_rate": 8.942539543314799e-07,
      "loss": 0.3745620012283325,
      "step": 1240
    },
    {
      "epoch": 2.5,
      "grad_norm": 41.225494384765625,
      "learning_rate": 8.289660757455803e-07,
      "loss": 0.3142155885696411,
      "step": 1250
    },
    {
      "epoch": 2.52,
      "grad_norm": 38.09383010864258,
      "learning_rate": 7.659368856111926e-07,
      "loss": 0.4468146800994873,
      "step": 1260
    },
    {
      "epoch": 2.54,
      "grad_norm": 25.196218490600586,
      "learning_rate": 7.052005153466779e-07,
      "loss": 0.514287281036377,
      "step": 1270
    },
    {
      "epoch": 2.56,
      "grad_norm": 22.963035583496094,
      "learning_rate": 6.467898547679913e-07,
      "loss": 0.21953434944152833,
      "step": 1280
    },
    {
      "epoch": 2.58,
      "grad_norm": 17.07082176208496,
      "learning_rate": 5.9073653427826e-07,
      "loss": 0.3766503095626831,
      "step": 1290
    },
    {
      "epoch": 2.6,
      "grad_norm": 38.808040618896484,
      "learning_rate": 5.370709077393721e-07,
      "loss": 0.3407785892486572,
      "step": 1300
    },
    {
      "epoch": 2.62,
      "grad_norm": 52.602874755859375,
      "learning_rate": 4.858220360348187e-07,
      "loss": 0.2537382125854492,
      "step": 1310
    },
    {
      "epoch": 2.64,
      "grad_norm": 19.56964874267578,
      "learning_rate": 4.370176713327118e-07,
      "loss": 0.25959508419036864,
      "step": 1320
    },
    {
      "epoch": 2.66,
      "grad_norm": 5.28275203704834,
      "learning_rate": 3.90684242057498e-07,
      "loss": 0.43554534912109377,
      "step": 1330
    },
    {
      "epoch": 2.68,
      "grad_norm": 31.416179656982422,
      "learning_rate": 3.468468385785023e-07,
      "loss": 0.5232177257537842,
      "step": 1340
    },
    {
      "epoch": 2.7,
      "grad_norm": 46.08461380004883,
      "learning_rate": 3.055291996230492e-07,
      "loss": 0.2125147581100464,
      "step": 1350
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 11.485236167907715,
      "learning_rate": 2.6675369942151864e-07,
      "loss": 0.21367454528808594,
      "step": 1360
    },
    {
      "epoch": 2.74,
      "grad_norm": 31.298377990722656,
      "learning_rate": 2.3054133559131163e-07,
      "loss": 0.1693113088607788,
      "step": 1370
    },
    {
      "epoch": 2.76,
      "grad_norm": 30.015377044677734,
      "learning_rate": 1.9691171776626882e-07,
      "loss": 0.2792075157165527,
      "step": 1380
    },
    {
      "epoch": 2.7800000000000002,
      "grad_norm": 0.11436483263969421,
      "learning_rate": 1.6588305697770313e-07,
      "loss": 0.13291265964508056,
      "step": 1390
    },
    {
      "epoch": 2.8,
      "grad_norm": 54.67913818359375,
      "learning_rate": 1.374721557928116e-07,
      "loss": 0.4104594707489014,
      "step": 1400
    },
    {
      "epoch": 2.82,
      "grad_norm": 29.346342086791992,
      "learning_rate": 1.1169439921578485e-07,
      "loss": 0.5142350196838379,
      "step": 1410
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.025704028084874153,
      "learning_rate": 8.856374635655696e-08,
      "loss": 0.31447272300720214,
      "step": 1420
    },
    {
      "epoch": 2.86,
      "grad_norm": 14.04995059967041,
      "learning_rate": 6.809272287169988e-08,
      "loss": 0.32525787353515623,
      "step": 1430
    },
    {
      "epoch": 2.88,
      "grad_norm": 5.467782020568848,
      "learning_rate": 5.029241418156139e-08,
      "loss": 0.1824193000793457,
      "step": 1440
    },
    {
      "epoch": 2.9,
      "grad_norm": 14.223469734191895,
      "learning_rate": 3.517245946731529e-08,
      "loss": 0.2836474895477295,
      "step": 1450
    },
    {
      "epoch": 2.92,
      "grad_norm": 18.699003219604492,
      "learning_rate": 2.27410464511707e-08,
      "loss": 0.20449333190917968,
      "step": 1460
    },
    {
      "epoch": 2.94,
      "grad_norm": 12.462102890014648,
      "learning_rate": 1.3004906962578723e-08,
      "loss": 0.30746448040008545,
      "step": 1470
    },
    {
      "epoch": 2.96,
      "grad_norm": 2.1692745685577393,
      "learning_rate": 5.969313292830126e-09,
      "loss": 0.2320650577545166,
      "step": 1480
    },
    {
      "epoch": 2.98,
      "grad_norm": 30.105022430419922,
      "learning_rate": 1.638075340010814e-09,
      "loss": 0.39888916015625,
      "step": 1490
    },
    {
      "epoch": 3.0,
      "grad_norm": 50.01400375366211,
      "learning_rate": 1.3538545881042198e-11,
      "loss": 0.3253091096878052,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "step": 1500,
      "total_flos": 2.273097293733888e+16,
      "train_loss": 1.3163418625195822,
      "train_runtime": 1442.119,
      "train_samples_per_second": 2.08,
      "train_steps_per_second": 1.04
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.273097293733888e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}