{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7692307692307693,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005494505494505495,
      "grad_norm": 0.29632216691970825,
      "learning_rate": 4e-05,
      "loss": 1.5561,
      "step": 1
    },
    {
      "epoch": 0.01098901098901099,
      "grad_norm": 0.3113888204097748,
      "learning_rate": 8e-05,
      "loss": 1.5458,
      "step": 2
    },
    {
      "epoch": 0.016483516483516484,
      "grad_norm": 0.3019237518310547,
      "learning_rate": 0.00012,
      "loss": 1.5507,
      "step": 3
    },
    {
      "epoch": 0.02197802197802198,
      "grad_norm": 0.29094433784484863,
      "learning_rate": 0.00016,
      "loss": 1.4652,
      "step": 4
    },
    {
      "epoch": 0.027472527472527472,
      "grad_norm": 0.27828261256217957,
      "learning_rate": 0.0002,
      "loss": 1.4454,
      "step": 5
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.3085501492023468,
      "learning_rate": 0.0001999842488663838,
      "loss": 1.1417,
      "step": 6
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 0.30620744824409485,
      "learning_rate": 0.00019993700042749937,
      "loss": 1.225,
      "step": 7
    },
    {
      "epoch": 0.04395604395604396,
      "grad_norm": 0.41407617926597595,
      "learning_rate": 0.0001998582695676762,
      "loss": 0.9375,
      "step": 8
    },
    {
      "epoch": 0.04945054945054945,
      "grad_norm": 0.3822758197784424,
      "learning_rate": 0.00019974808108892016,
      "loss": 0.8788,
      "step": 9
    },
    {
      "epoch": 0.054945054945054944,
      "grad_norm": 0.40259653329849243,
      "learning_rate": 0.00019960646970310027,
      "loss": 0.7664,
      "step": 10
    },
    {
      "epoch": 0.06043956043956044,
      "grad_norm": 0.5633108019828796,
      "learning_rate": 0.00019943348002101371,
      "loss": 0.6699,
      "step": 11
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.37629789113998413,
      "learning_rate": 0.00019922916653833248,
      "loss": 0.5892,
      "step": 12
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.31924572587013245,
      "learning_rate": 0.0001989935936184358,
      "loss": 0.5198,
      "step": 13
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.38061216473579407,
      "learning_rate": 0.00019872683547213446,
      "loss": 0.5894,
      "step": 14
    },
    {
      "epoch": 0.08241758241758242,
      "grad_norm": 0.2537476122379303,
      "learning_rate": 0.00019842897613429262,
      "loss": 0.5341,
      "step": 15
    },
    {
      "epoch": 0.08791208791208792,
      "grad_norm": 0.24057163298130035,
      "learning_rate": 0.00019810010943735479,
      "loss": 0.3744,
      "step": 16
    },
    {
      "epoch": 0.09340659340659341,
      "grad_norm": 0.2103324830532074,
      "learning_rate": 0.00019774033898178667,
      "loss": 0.5054,
      "step": 17
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.18747441470623016,
      "learning_rate": 0.00019734977810343865,
      "loss": 0.3734,
      "step": 18
    },
    {
      "epoch": 0.1043956043956044,
      "grad_norm": 0.19926677644252777,
      "learning_rate": 0.00019692854983784235,
      "loss": 0.399,
      "step": 19
    },
    {
      "epoch": 0.10989010989010989,
      "grad_norm": 0.20050929486751556,
      "learning_rate": 0.0001964767868814516,
      "loss": 0.4754,
      "step": 20
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": 0.18073034286499023,
      "learning_rate": 0.0001959946315498402,
      "loss": 0.4375,
      "step": 21
    },
    {
      "epoch": 0.12087912087912088,
      "grad_norm": 0.20278413593769073,
      "learning_rate": 0.0001954822357328692,
      "loss": 0.4896,
      "step": 22
    },
    {
      "epoch": 0.12637362637362637,
      "grad_norm": 0.16931243240833282,
      "learning_rate": 0.00019493976084683813,
      "loss": 0.4137,
      "step": 23
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.18224675953388214,
      "learning_rate": 0.00019436737778363527,
      "loss": 0.3895,
      "step": 24
    },
    {
      "epoch": 0.13736263736263737,
      "grad_norm": 0.16282841563224792,
      "learning_rate": 0.0001937652668569028,
      "loss": 0.364,
      "step": 25
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.19350826740264893,
      "learning_rate": 0.00019313361774523385,
      "loss": 0.3578,
      "step": 26
    },
    {
      "epoch": 0.14835164835164835,
      "grad_norm": 0.20993147790431976,
      "learning_rate": 0.0001924726294324196,
      "loss": 0.4351,
      "step": 27
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.20188163220882416,
      "learning_rate": 0.00019178251014476466,
      "loss": 0.3965,
      "step": 28
    },
    {
      "epoch": 0.15934065934065933,
      "grad_norm": 0.2008114606142044,
      "learning_rate": 0.00019106347728549135,
      "loss": 0.3193,
      "step": 29
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.1973695605993271,
      "learning_rate": 0.00019031575736625238,
      "loss": 0.298,
      "step": 30
    },
    {
      "epoch": 0.17032967032967034,
      "grad_norm": 0.20849934220314026,
      "learning_rate": 0.00018953958593577493,
      "loss": 0.2995,
      "step": 31
    },
    {
      "epoch": 0.17582417582417584,
      "grad_norm": 0.20263291895389557,
      "learning_rate": 0.00018873520750565718,
      "loss": 0.3021,
      "step": 32
    },
    {
      "epoch": 0.1813186813186813,
      "grad_norm": 0.20541806519031525,
      "learning_rate": 0.00018790287547334176,
      "loss": 0.2883,
      "step": 33
    },
    {
      "epoch": 0.18681318681318682,
      "grad_norm": 0.24142159521579742,
      "learning_rate": 0.00018704285204228973,
      "loss": 0.3396,
      "step": 34
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 0.20562608540058136,
      "learning_rate": 0.0001861554081393806,
      "loss": 0.2773,
      "step": 35
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.26048898696899414,
      "learning_rate": 0.00018524082332956428,
      "loss": 0.3024,
      "step": 36
    },
    {
      "epoch": 0.2032967032967033,
      "grad_norm": 0.23103846609592438,
      "learning_rate": 0.00018429938572779152,
      "loss": 0.2843,
      "step": 37
    },
    {
      "epoch": 0.2087912087912088,
      "grad_norm": 0.23378689587116241,
      "learning_rate": 0.0001833313919082515,
      "loss": 0.2963,
      "step": 38
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.27318716049194336,
      "learning_rate": 0.00018233714681094404,
      "loss": 0.3863,
      "step": 39
    },
    {
      "epoch": 0.21978021978021978,
      "grad_norm": 0.219524085521698,
      "learning_rate": 0.00018131696364561667,
      "loss": 0.2703,
      "step": 40
    },
    {
      "epoch": 0.22527472527472528,
      "grad_norm": 0.21837233006954193,
      "learning_rate": 0.00018027116379309638,
      "loss": 0.2695,
      "step": 41
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2384708672761917,
      "learning_rate": 0.0001792000767040474,
      "loss": 0.2819,
      "step": 42
    },
    {
      "epoch": 0.23626373626373626,
      "grad_norm": 0.20765846967697144,
      "learning_rate": 0.00017810403979518681,
      "loss": 0.2658,
      "step": 43
    },
    {
      "epoch": 0.24175824175824176,
      "grad_norm": 0.22932475805282593,
      "learning_rate": 0.00017698339834299061,
      "loss": 0.2276,
      "step": 44
    },
    {
      "epoch": 0.24725274725274726,
      "grad_norm": 0.2080792635679245,
      "learning_rate": 0.00017583850537492387,
      "loss": 0.1902,
      "step": 45
    },
    {
      "epoch": 0.25274725274725274,
      "grad_norm": 0.2754678428173065,
      "learning_rate": 0.0001746697215582288,
      "loss": 0.2797,
      "step": 46
    },
    {
      "epoch": 0.25824175824175827,
      "grad_norm": 0.22715018689632416,
      "learning_rate": 0.00017347741508630672,
      "loss": 0.1703,
      "step": 47
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.31407058238983154,
      "learning_rate": 0.00017226196156272874,
      "loss": 0.281,
      "step": 48
    },
    {
      "epoch": 0.2692307692307692,
      "grad_norm": 0.2527458071708679,
      "learning_rate": 0.00017102374388291183,
      "loss": 0.2579,
      "step": 49
    },
    {
      "epoch": 0.27472527472527475,
      "grad_norm": 0.2112707644701004,
      "learning_rate": 0.0001697631521134985,
      "loss": 0.264,
      "step": 50
    },
    {
      "epoch": 0.2802197802197802,
      "grad_norm": 0.20465674996376038,
      "learning_rate": 0.00016848058336947657,
      "loss": 0.2882,
      "step": 51
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.2256706804037094,
      "learning_rate": 0.0001671764416890793,
      "loss": 0.1847,
      "step": 52
    },
    {
      "epoch": 0.29120879120879123,
      "grad_norm": 0.20961597561836243,
      "learning_rate": 0.00016585113790650388,
      "loss": 0.196,
      "step": 53
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2462984025478363,
      "learning_rate": 0.00016450508952248956,
      "loss": 0.2032,
      "step": 54
    },
    {
      "epoch": 0.3021978021978022,
      "grad_norm": 0.22251084446907043,
      "learning_rate": 0.00016313872057279534,
      "loss": 0.203,
      "step": 55
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.23791608214378357,
      "learning_rate": 0.0001617524614946192,
      "loss": 0.2458,
      "step": 56
    },
    {
      "epoch": 0.3131868131868132,
      "grad_norm": 0.23427598178386688,
      "learning_rate": 0.0001603467489910004,
      "loss": 0.149,
      "step": 57
    },
    {
      "epoch": 0.31868131868131866,
      "grad_norm": 0.23513749241828918,
      "learning_rate": 0.00015892202589324835,
      "loss": 0.1449,
      "step": 58
    },
    {
      "epoch": 0.3241758241758242,
      "grad_norm": 0.23785251379013062,
      "learning_rate": 0.0001574787410214407,
      "loss": 0.1938,
      "step": 59
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.20233368873596191,
      "learning_rate": 0.0001560173490430346,
      "loss": 0.1226,
      "step": 60
    },
    {
      "epoch": 0.33516483516483514,
      "grad_norm": 0.2437211126089096,
      "learning_rate": 0.0001545383103296365,
      "loss": 0.1892,
      "step": 61
    },
    {
      "epoch": 0.34065934065934067,
      "grad_norm": 0.2462146282196045,
      "learning_rate": 0.00015304209081197425,
      "loss": 0.1581,
      "step": 62
    },
    {
      "epoch": 0.34615384615384615,
      "grad_norm": 0.3353044092655182,
      "learning_rate": 0.0001515291618331188,
      "loss": 0.2195,
      "step": 63
    },
    {
      "epoch": 0.3516483516483517,
      "grad_norm": 0.22197988629341125,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.1739,
      "step": 64
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.2737789750099182,
      "learning_rate": 0.00014845508703326504,
      "loss": 0.1717,
      "step": 65
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.22385859489440918,
      "learning_rate": 0.00014689490961552513,
      "loss": 0.1724,
      "step": 66
    },
    {
      "epoch": 0.36813186813186816,
      "grad_norm": 0.27109456062316895,
      "learning_rate": 0.00014531995923803973,
      "loss": 0.196,
      "step": 67
    },
    {
      "epoch": 0.37362637362637363,
      "grad_norm": 0.20588435232639313,
      "learning_rate": 0.00014373073204588556,
      "loss": 0.1351,
      "step": 68
    },
    {
      "epoch": 0.3791208791208791,
      "grad_norm": 0.22479820251464844,
      "learning_rate": 0.00014212772868165958,
      "loss": 0.1083,
      "step": 69
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.2374928891658783,
      "learning_rate": 0.00014051145412776535,
      "loss": 0.136,
      "step": 70
    },
    {
      "epoch": 0.3901098901098901,
      "grad_norm": 0.25980404019355774,
      "learning_rate": 0.00013888241754733208,
      "loss": 0.1505,
      "step": 71
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3704344928264618,
      "learning_rate": 0.0001372411321238166,
      "loss": 0.2365,
      "step": 72
    },
    {
      "epoch": 0.4010989010989011,
      "grad_norm": 0.2545515298843384,
      "learning_rate": 0.00013558811489933908,
      "loss": 0.1645,
      "step": 73
    },
    {
      "epoch": 0.4065934065934066,
      "grad_norm": 0.2218877524137497,
      "learning_rate": 0.00013392388661180303,
      "loss": 0.1178,
      "step": 74
    },
    {
      "epoch": 0.41208791208791207,
      "grad_norm": 0.19732226431369781,
      "learning_rate": 0.0001322489715308509,
      "loss": 0.1001,
      "step": 75
    },
    {
      "epoch": 0.4175824175824176,
      "grad_norm": 0.28702080249786377,
      "learning_rate": 0.00013056389729270738,
      "loss": 0.1437,
      "step": 76
    },
    {
      "epoch": 0.4230769230769231,
      "grad_norm": 0.27200955152511597,
      "learning_rate": 0.0001288691947339621,
      "loss": 0.1753,
      "step": 77
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.20188194513320923,
      "learning_rate": 0.00012716539772434388,
      "loss": 0.0998,
      "step": 78
    },
    {
      "epoch": 0.4340659340659341,
      "grad_norm": 0.2388327270746231,
      "learning_rate": 0.00012545304299853977,
      "loss": 0.1339,
      "step": 79
    },
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 0.21373318135738373,
      "learning_rate": 0.0001237326699871115,
      "loss": 0.1205,
      "step": 80
    },
    {
      "epoch": 0.44505494505494503,
      "grad_norm": 0.29054194688796997,
      "learning_rate": 0.00012200482064656248,
      "loss": 0.1632,
      "step": 81
    },
    {
      "epoch": 0.45054945054945056,
      "grad_norm": 0.24942484498023987,
      "learning_rate": 0.00012027003928860937,
      "loss": 0.1282,
      "step": 82
    },
    {
      "epoch": 0.45604395604395603,
      "grad_norm": 0.20856431126594543,
      "learning_rate": 0.00011852887240871145,
      "loss": 0.1168,
      "step": 83
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.2552940249443054,
      "learning_rate": 0.00011678186851391218,
      "loss": 0.1269,
      "step": 84
    },
    {
      "epoch": 0.46703296703296704,
      "grad_norm": 0.2256869375705719,
      "learning_rate": 0.00011502957795004705,
      "loss": 0.1043,
      "step": 85
    },
    {
      "epoch": 0.4725274725274725,
      "grad_norm": 0.20186680555343628,
      "learning_rate": 0.00011327255272837221,
      "loss": 0.0929,
      "step": 86
    },
    {
      "epoch": 0.47802197802197804,
      "grad_norm": 0.2341729998588562,
      "learning_rate": 0.00011151134635166829,
      "loss": 0.0981,
      "step": 87
    },
    {
      "epoch": 0.4835164835164835,
      "grad_norm": 0.23417356610298157,
      "learning_rate": 0.00010974651363987465,
      "loss": 0.1066,
      "step": 88
    },
    {
      "epoch": 0.489010989010989,
      "grad_norm": 0.18209996819496155,
      "learning_rate": 0.00010797861055530831,
      "loss": 0.1032,
      "step": 89
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.18998686969280243,
      "learning_rate": 0.0001062081940275234,
      "loss": 0.0965,
      "step": 90
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.20998521149158478,
      "learning_rate": 0.00010443582177786564,
      "loss": 0.144,
      "step": 91
    },
    {
      "epoch": 0.5054945054945055,
      "grad_norm": 0.22074103355407715,
      "learning_rate": 0.00010266205214377748,
      "loss": 0.1184,
      "step": 92
    },
    {
      "epoch": 0.510989010989011,
      "grad_norm": 0.15477561950683594,
      "learning_rate": 0.0001008874439029091,
      "loss": 0.0796,
      "step": 93
    },
    {
      "epoch": 0.5164835164835165,
      "grad_norm": 0.2496633678674698,
      "learning_rate": 9.91125560970909e-05,
      "loss": 0.142,
      "step": 94
    },
    {
      "epoch": 0.521978021978022,
      "grad_norm": 0.3139898180961609,
      "learning_rate": 9.733794785622253e-05,
      "loss": 0.1407,
      "step": 95
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.21977433562278748,
      "learning_rate": 9.556417822213435e-05,
      "loss": 0.1164,
      "step": 96
    },
    {
      "epoch": 0.532967032967033,
      "grad_norm": 0.19279415905475616,
      "learning_rate": 9.379180597247661e-05,
      "loss": 0.0876,
      "step": 97
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.23302212357521057,
      "learning_rate": 9.202138944469168e-05,
      "loss": 0.1269,
      "step": 98
    },
    {
      "epoch": 0.5439560439560439,
      "grad_norm": 0.1825583428144455,
      "learning_rate": 9.025348636012536e-05,
      "loss": 0.0936,
      "step": 99
    },
    {
      "epoch": 0.5494505494505495,
      "grad_norm": 0.19986358284950256,
      "learning_rate": 8.84886536483317e-05,
      "loss": 0.113,
      "step": 100
    },
    {
      "epoch": 0.554945054945055,
      "grad_norm": 0.19531255960464478,
      "learning_rate": 8.672744727162781e-05,
      "loss": 0.0941,
      "step": 101
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.2396000772714615,
      "learning_rate": 8.497042204995299e-05,
      "loss": 0.0992,
      "step": 102
    },
    {
      "epoch": 0.5659340659340659,
      "grad_norm": 0.196890726685524,
      "learning_rate": 8.321813148608783e-05,
      "loss": 0.0833,
      "step": 103
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.2729422450065613,
      "learning_rate": 8.147112759128859e-05,
      "loss": 0.1452,
      "step": 104
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 0.1796470433473587,
      "learning_rate": 7.972996071139064e-05,
      "loss": 0.0799,
      "step": 105
    },
    {
      "epoch": 0.5824175824175825,
      "grad_norm": 0.14928919076919556,
      "learning_rate": 7.799517935343757e-05,
      "loss": 0.0481,
      "step": 106
    },
    {
      "epoch": 0.5879120879120879,
      "grad_norm": 0.21496616303920746,
      "learning_rate": 7.626733001288851e-05,
      "loss": 0.0693,
      "step": 107
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.24284154176712036,
      "learning_rate": 7.454695700146024e-05,
      "loss": 0.1201,
      "step": 108
    },
    {
      "epoch": 0.5989010989010989,
      "grad_norm": 0.2560741603374481,
      "learning_rate": 7.283460227565613e-05,
      "loss": 0.1095,
      "step": 109
    },
    {
      "epoch": 0.6043956043956044,
      "grad_norm": 0.13009899854660034,
      "learning_rate": 7.113080526603792e-05,
      "loss": 0.0512,
      "step": 110
    },
    {
      "epoch": 0.6098901098901099,
      "grad_norm": 0.20721551775932312,
      "learning_rate": 6.94361027072926e-05,
      "loss": 0.1132,
      "step": 111
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.154499813914299,
      "learning_rate": 6.775102846914911e-05,
      "loss": 0.0755,
      "step": 112
    },
    {
      "epoch": 0.6208791208791209,
      "grad_norm": 0.19335274398326874,
      "learning_rate": 6.607611338819697e-05,
      "loss": 0.0847,
      "step": 113
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.17462438344955444,
      "learning_rate": 6.441188510066091e-05,
      "loss": 0.0569,
      "step": 114
    },
    {
      "epoch": 0.6318681318681318,
      "grad_norm": 0.33881354331970215,
      "learning_rate": 6.275886787618339e-05,
      "loss": 0.1436,
      "step": 115
    },
    {
      "epoch": 0.6373626373626373,
      "grad_norm": 0.14344196021556854,
      "learning_rate": 6.111758245266794e-05,
      "loss": 0.0628,
      "step": 116
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.10723075270652771,
      "learning_rate": 5.9488545872234645e-05,
      "loss": 0.0462,
      "step": 117
    },
    {
      "epoch": 0.6483516483516484,
      "grad_norm": 0.19554950296878815,
      "learning_rate": 5.787227131834043e-05,
      "loss": 0.1092,
      "step": 118
    },
    {
      "epoch": 0.6538461538461539,
      "grad_norm": 0.13956406712532043,
      "learning_rate": 5.626926795411447e-05,
      "loss": 0.0674,
      "step": 119
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.2507220506668091,
      "learning_rate": 5.468004076196029e-05,
      "loss": 0.1,
      "step": 120
    },
    {
      "epoch": 0.6648351648351648,
      "grad_norm": 0.1673005074262619,
      "learning_rate": 5.310509038447492e-05,
      "loss": 0.1039,
      "step": 121
    },
    {
      "epoch": 0.6703296703296703,
      "grad_norm": 0.12703153491020203,
      "learning_rate": 5.1544912966734994e-05,
      "loss": 0.0704,
      "step": 122
    },
    {
      "epoch": 0.6758241758241759,
      "grad_norm": 0.17319592833518982,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0724,
      "step": 123
    },
    {
      "epoch": 0.6813186813186813,
      "grad_norm": 0.154402956366539,
      "learning_rate": 4.8470838166881226e-05,
      "loss": 0.047,
      "step": 124
    },
    {
      "epoch": 0.6868131868131868,
      "grad_norm": 0.15553316473960876,
      "learning_rate": 4.695790918802576e-05,
      "loss": 0.0932,
      "step": 125
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.1012202799320221,
      "learning_rate": 4.546168967036351e-05,
      "loss": 0.0456,
      "step": 126
    },
    {
      "epoch": 0.6978021978021978,
      "grad_norm": 0.1133142039179802,
      "learning_rate": 4.398265095696539e-05,
      "loss": 0.0482,
      "step": 127
    },
    {
      "epoch": 0.7032967032967034,
      "grad_norm": 0.14953628182411194,
      "learning_rate": 4.252125897855932e-05,
      "loss": 0.0577,
      "step": 128
    },
    {
      "epoch": 0.7087912087912088,
      "grad_norm": 0.145247682929039,
      "learning_rate": 4.107797410675166e-05,
      "loss": 0.0645,
      "step": 129
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.09949145466089249,
      "learning_rate": 3.965325100899961e-05,
      "loss": 0.0486,
      "step": 130
    },
    {
      "epoch": 0.7197802197802198,
      "grad_norm": 0.128681942820549,
      "learning_rate": 3.824753850538082e-05,
      "loss": 0.0561,
      "step": 131
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.16942492127418518,
      "learning_rate": 3.686127942720463e-05,
      "loss": 0.0614,
      "step": 132
    },
    {
      "epoch": 0.7307692307692307,
      "grad_norm": 0.1377490609884262,
      "learning_rate": 3.5494910477510445e-05,
      "loss": 0.0634,
      "step": 133
    },
    {
      "epoch": 0.7362637362637363,
      "grad_norm": 0.1743365377187729,
      "learning_rate": 3.414886209349615e-05,
      "loss": 0.0695,
      "step": 134
    },
    {
      "epoch": 0.7417582417582418,
      "grad_norm": 0.18100859224796295,
      "learning_rate": 3.282355831092072e-05,
      "loss": 0.0561,
      "step": 135
    },
    {
      "epoch": 0.7472527472527473,
      "grad_norm": 0.1113915666937828,
      "learning_rate": 3.1519416630523444e-05,
      "loss": 0.0609,
      "step": 136
    },
    {
      "epoch": 0.7527472527472527,
      "grad_norm": 0.11914083361625671,
      "learning_rate": 3.0236847886501542e-05,
      "loss": 0.0437,
      "step": 137
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.16115868091583252,
      "learning_rate": 2.8976256117088195e-05,
      "loss": 0.0668,
      "step": 138
    },
    {
      "epoch": 0.7637362637362637,
      "grad_norm": 0.1613149493932724,
      "learning_rate": 2.7738038437271284e-05,
      "loss": 0.0769,
      "step": 139
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.12686750292778015,
      "learning_rate": 2.6522584913693294e-05,
      "loss": 0.0586,
      "step": 140
    }
  ],
  "logging_steps": 1,
  "max_steps": 182,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.078551699224986e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}