{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0061855670103093,
  "eval_steps": 61,
  "global_step": 122,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008247422680412371,
      "grad_norm": 2.2737574577331543,
      "learning_rate": 2e-05,
      "loss": 1.0155,
      "step": 1
    },
    {
      "epoch": 0.008247422680412371,
      "eval_loss": 1.2302311658859253,
      "eval_runtime": 295.4772,
      "eval_samples_per_second": 2.031,
      "eval_steps_per_second": 1.015,
      "step": 1
    },
    {
      "epoch": 0.016494845360824743,
      "grad_norm": 2.203125476837158,
      "learning_rate": 4e-05,
      "loss": 1.1137,
      "step": 2
    },
    {
      "epoch": 0.024742268041237112,
      "grad_norm": 1.7233558893203735,
      "learning_rate": 6e-05,
      "loss": 0.9453,
      "step": 3
    },
    {
      "epoch": 0.032989690721649485,
      "grad_norm": 2.38301420211792,
      "learning_rate": 8e-05,
      "loss": 1.1091,
      "step": 4
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 1.6754157543182373,
      "learning_rate": 0.0001,
      "loss": 0.9209,
      "step": 5
    },
    {
      "epoch": 0.049484536082474224,
      "grad_norm": 1.6663925647735596,
      "learning_rate": 0.00012,
      "loss": 0.9145,
      "step": 6
    },
    {
      "epoch": 0.0577319587628866,
      "grad_norm": 1.6516679525375366,
      "learning_rate": 0.00014,
      "loss": 0.8456,
      "step": 7
    },
    {
      "epoch": 0.06597938144329897,
      "grad_norm": 1.4858132600784302,
      "learning_rate": 0.00016,
      "loss": 0.8257,
      "step": 8
    },
    {
      "epoch": 0.07422680412371134,
      "grad_norm": 1.2829698324203491,
      "learning_rate": 0.00018,
      "loss": 0.7396,
      "step": 9
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.8841626644134521,
      "learning_rate": 0.0002,
      "loss": 0.6599,
      "step": 10
    },
    {
      "epoch": 0.09072164948453608,
      "grad_norm": 0.6680086255073547,
      "learning_rate": 0.0001999960397967811,
      "loss": 0.6368,
      "step": 11
    },
    {
      "epoch": 0.09896907216494845,
      "grad_norm": 0.9510122537612915,
      "learning_rate": 0.00019998415950078858,
      "loss": 0.7061,
      "step": 12
    },
    {
      "epoch": 0.10721649484536082,
      "grad_norm": 0.8464949131011963,
      "learning_rate": 0.00019996436005299012,
      "loss": 0.6674,
      "step": 13
    },
    {
      "epoch": 0.1154639175257732,
      "grad_norm": 0.8255585432052612,
      "learning_rate": 0.00019993664302158255,
      "loss": 0.6971,
      "step": 14
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.7613081932067871,
      "learning_rate": 0.00019990101060186733,
      "loss": 0.6621,
      "step": 15
    },
    {
      "epoch": 0.13195876288659794,
      "grad_norm": 0.6413361430168152,
      "learning_rate": 0.00019985746561607698,
      "loss": 0.6336,
      "step": 16
    },
    {
      "epoch": 0.1402061855670103,
      "grad_norm": 0.7216547727584839,
      "learning_rate": 0.0001998060115131513,
      "loss": 0.7165,
      "step": 17
    },
    {
      "epoch": 0.14845360824742268,
      "grad_norm": 0.7801871299743652,
      "learning_rate": 0.00019974665236846442,
      "loss": 0.7449,
      "step": 18
    },
    {
      "epoch": 0.15670103092783505,
      "grad_norm": 0.6427637338638306,
      "learning_rate": 0.00019967939288350182,
      "loss": 0.6344,
      "step": 19
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.6753759980201721,
      "learning_rate": 0.00019960423838548814,
      "loss": 0.735,
      "step": 20
    },
    {
      "epoch": 0.1731958762886598,
      "grad_norm": 0.6213053464889526,
      "learning_rate": 0.00019952119482696503,
      "loss": 0.6675,
      "step": 21
    },
    {
      "epoch": 0.18144329896907216,
      "grad_norm": 0.6505969762802124,
      "learning_rate": 0.00019943026878531983,
      "loss": 0.6129,
      "step": 22
    },
    {
      "epoch": 0.18969072164948453,
      "grad_norm": 0.6324624419212341,
      "learning_rate": 0.0001993314674622646,
      "loss": 0.6289,
      "step": 23
    },
    {
      "epoch": 0.1979381443298969,
      "grad_norm": 0.6155864000320435,
      "learning_rate": 0.00019922479868326578,
      "loss": 0.6358,
      "step": 24
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.6395933628082275,
      "learning_rate": 0.0001991102708969241,
      "loss": 0.6225,
      "step": 25
    },
    {
      "epoch": 0.21443298969072164,
      "grad_norm": 0.5889492034912109,
      "learning_rate": 0.00019898789317430575,
      "loss": 0.6674,
      "step": 26
    },
    {
      "epoch": 0.22268041237113403,
      "grad_norm": 0.5262942910194397,
      "learning_rate": 0.00019885767520822376,
      "loss": 0.6077,
      "step": 27
    },
    {
      "epoch": 0.2309278350515464,
      "grad_norm": 0.5878570675849915,
      "learning_rate": 0.0001987196273124703,
      "loss": 0.6145,
      "step": 28
    },
    {
      "epoch": 0.23917525773195877,
      "grad_norm": 0.5845457315444946,
      "learning_rate": 0.00019857376042099983,
      "loss": 0.6435,
      "step": 29
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 0.6508314609527588,
      "learning_rate": 0.00019842008608706295,
      "loss": 0.6799,
      "step": 30
    },
    {
      "epoch": 0.2556701030927835,
      "grad_norm": 0.5770230293273926,
      "learning_rate": 0.00019825861648229152,
      "loss": 0.6092,
      "step": 31
    },
    {
      "epoch": 0.2639175257731959,
      "grad_norm": 0.5438909530639648,
      "learning_rate": 0.00019808936439573454,
      "loss": 0.5952,
      "step": 32
    },
    {
      "epoch": 0.2721649484536082,
      "grad_norm": 0.5276155471801758,
      "learning_rate": 0.00019791234323284513,
      "loss": 0.5899,
      "step": 33
    },
    {
      "epoch": 0.2804123711340206,
      "grad_norm": 0.6430350542068481,
      "learning_rate": 0.00019772756701441887,
      "loss": 0.6581,
      "step": 34
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 0.6087874174118042,
      "learning_rate": 0.0001975350503754833,
      "loss": 0.654,
      "step": 35
    },
    {
      "epoch": 0.29690721649484536,
      "grad_norm": 0.610534131526947,
      "learning_rate": 0.00019733480856413868,
      "loss": 0.6655,
      "step": 36
    },
    {
      "epoch": 0.30515463917525776,
      "grad_norm": 0.5277837514877319,
      "learning_rate": 0.0001971268574403503,
      "loss": 0.6228,
      "step": 37
    },
    {
      "epoch": 0.3134020618556701,
      "grad_norm": 0.6729940176010132,
      "learning_rate": 0.00019691121347469235,
      "loss": 0.8324,
      "step": 38
    },
    {
      "epoch": 0.3216494845360825,
      "grad_norm": 0.541552722454071,
      "learning_rate": 0.00019668789374704338,
      "loss": 0.54,
      "step": 39
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 0.5642793774604797,
      "learning_rate": 0.0001964569159452335,
      "loss": 0.641,
      "step": 40
    },
    {
      "epoch": 0.33814432989690724,
      "grad_norm": 0.5639921426773071,
      "learning_rate": 0.00019621829836364337,
      "loss": 0.6042,
      "step": 41
    },
    {
      "epoch": 0.3463917525773196,
      "grad_norm": 0.566059410572052,
      "learning_rate": 0.00019597205990175525,
      "loss": 0.6364,
      "step": 42
    },
    {
      "epoch": 0.354639175257732,
      "grad_norm": 0.5911106467247009,
      "learning_rate": 0.00019571822006265622,
      "loss": 0.6777,
      "step": 43
    },
    {
      "epoch": 0.3628865979381443,
      "grad_norm": 0.5940718054771423,
      "learning_rate": 0.00019545679895149315,
      "loss": 0.713,
      "step": 44
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 0.46311718225479126,
      "learning_rate": 0.0001951878172738806,
      "loss": 0.5298,
      "step": 45
    },
    {
      "epoch": 0.37938144329896906,
      "grad_norm": 0.5446880459785461,
      "learning_rate": 0.00019491129633426068,
      "loss": 0.546,
      "step": 46
    },
    {
      "epoch": 0.38762886597938145,
      "grad_norm": 0.6126728653907776,
      "learning_rate": 0.00019462725803421566,
      "loss": 0.5725,
      "step": 47
    },
    {
      "epoch": 0.3958762886597938,
      "grad_norm": 0.49817898869514465,
      "learning_rate": 0.0001943357248707334,
      "loss": 0.6224,
      "step": 48
    },
    {
      "epoch": 0.4041237113402062,
      "grad_norm": 0.4865269362926483,
      "learning_rate": 0.0001940367199344253,
      "loss": 0.544,
      "step": 49
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 0.48718348145484924,
      "learning_rate": 0.00019373026690769763,
      "loss": 0.6132,
      "step": 50
    },
    {
      "epoch": 0.42061855670103093,
      "grad_norm": 0.5080978274345398,
      "learning_rate": 0.0001934163900628756,
      "loss": 0.6278,
      "step": 51
    },
    {
      "epoch": 0.4288659793814433,
      "grad_norm": 0.4930504262447357,
      "learning_rate": 0.00019309511426028104,
      "loss": 0.602,
      "step": 52
    },
    {
      "epoch": 0.43711340206185567,
      "grad_norm": 0.4977351725101471,
      "learning_rate": 0.00019276646494626332,
      "loss": 0.5516,
      "step": 53
    },
    {
      "epoch": 0.44536082474226807,
      "grad_norm": 0.4758591055870056,
      "learning_rate": 0.00019243046815118386,
      "loss": 0.5136,
      "step": 54
    },
    {
      "epoch": 0.4536082474226804,
      "grad_norm": 0.4887770712375641,
      "learning_rate": 0.00019208715048735445,
      "loss": 0.6265,
      "step": 55
    },
    {
      "epoch": 0.4618556701030928,
      "grad_norm": 0.5064010620117188,
      "learning_rate": 0.00019173653914692946,
      "loss": 0.6524,
      "step": 56
    },
    {
      "epoch": 0.47010309278350515,
      "grad_norm": 0.5001596808433533,
      "learning_rate": 0.00019137866189975202,
      "loss": 0.622,
      "step": 57
    },
    {
      "epoch": 0.47835051546391755,
      "grad_norm": 0.4940868616104126,
      "learning_rate": 0.00019101354709115468,
      "loss": 0.6362,
      "step": 58
    },
    {
      "epoch": 0.4865979381443299,
      "grad_norm": 0.4839000701904297,
      "learning_rate": 0.00019064122363971427,
      "loss": 0.6223,
      "step": 59
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 0.4475175440311432,
      "learning_rate": 0.00019026172103496137,
      "loss": 0.5625,
      "step": 60
    },
    {
      "epoch": 0.5030927835051546,
      "grad_norm": 0.4716227352619171,
      "learning_rate": 0.0001898750693350447,
      "loss": 0.5161,
      "step": 61
    },
    {
      "epoch": 0.5030927835051546,
      "eval_loss": 0.5744044780731201,
      "eval_runtime": 296.9417,
      "eval_samples_per_second": 2.021,
      "eval_steps_per_second": 1.01,
      "step": 61
    },
    {
      "epoch": 0.511340206185567,
      "grad_norm": 0.47013187408447266,
      "learning_rate": 0.00018948129916435046,
      "loss": 0.592,
      "step": 62
    },
    {
      "epoch": 0.5195876288659794,
      "grad_norm": 0.44856756925582886,
      "learning_rate": 0.00018908044171107657,
      "loss": 0.5981,
      "step": 63
    },
    {
      "epoch": 0.5278350515463918,
      "grad_norm": 0.4443698525428772,
      "learning_rate": 0.00018867252872476257,
      "loss": 0.6068,
      "step": 64
    },
    {
      "epoch": 0.5360824742268041,
      "grad_norm": 0.423221617937088,
      "learning_rate": 0.00018825759251377483,
      "loss": 0.537,
      "step": 65
    },
    {
      "epoch": 0.5443298969072164,
      "grad_norm": 0.4647126793861389,
      "learning_rate": 0.00018783566594274783,
      "loss": 0.5896,
      "step": 66
    },
    {
      "epoch": 0.5525773195876289,
      "grad_norm": 0.4287152588367462,
      "learning_rate": 0.00018740678242998077,
      "loss": 0.5424,
      "step": 67
    },
    {
      "epoch": 0.5608247422680412,
      "grad_norm": 0.4562716484069824,
      "learning_rate": 0.00018697097594479103,
      "loss": 0.5571,
      "step": 68
    },
    {
      "epoch": 0.5690721649484536,
      "grad_norm": 0.37922483682632446,
      "learning_rate": 0.0001865282810048235,
      "loss": 0.5337,
      "step": 69
    },
    {
      "epoch": 0.5773195876288659,
      "grad_norm": 0.4227437973022461,
      "learning_rate": 0.0001860787326733168,
      "loss": 0.5989,
      "step": 70
    },
    {
      "epoch": 0.5855670103092784,
      "grad_norm": 0.39743122458457947,
      "learning_rate": 0.0001856223665563258,
      "loss": 0.537,
      "step": 71
    },
    {
      "epoch": 0.5938144329896907,
      "grad_norm": 0.41971203684806824,
      "learning_rate": 0.00018515921879990187,
      "loss": 0.5353,
      "step": 72
    },
    {
      "epoch": 0.6020618556701031,
      "grad_norm": 0.4010031819343567,
      "learning_rate": 0.00018468932608722973,
      "loss": 0.5954,
      "step": 73
    },
    {
      "epoch": 0.6103092783505155,
      "grad_norm": 0.469838947057724,
      "learning_rate": 0.000184212725635722,
      "loss": 0.6942,
      "step": 74
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 0.381673663854599,
      "learning_rate": 0.00018372945519407158,
      "loss": 0.557,
      "step": 75
    },
    {
      "epoch": 0.6268041237113402,
      "grad_norm": 0.3736635446548462,
      "learning_rate": 0.00018323955303926163,
      "loss": 0.5174,
      "step": 76
    },
    {
      "epoch": 0.6350515463917525,
      "grad_norm": 0.4390040338039398,
      "learning_rate": 0.00018274305797353395,
      "loss": 0.6249,
      "step": 77
    },
    {
      "epoch": 0.643298969072165,
      "grad_norm": 0.4298490285873413,
      "learning_rate": 0.00018224000932131568,
      "loss": 0.5682,
      "step": 78
    },
    {
      "epoch": 0.6515463917525773,
      "grad_norm": 0.3995118737220764,
      "learning_rate": 0.00018173044692610467,
      "loss": 0.5261,
      "step": 79
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": 0.41546231508255005,
      "learning_rate": 0.00018121441114731367,
      "loss": 0.5296,
      "step": 80
    },
    {
      "epoch": 0.668041237113402,
      "grad_norm": 0.4129379093647003,
      "learning_rate": 0.0001806919428570737,
      "loss": 0.5576,
      "step": 81
    },
    {
      "epoch": 0.6762886597938145,
      "grad_norm": 0.4260002672672272,
      "learning_rate": 0.00018016308343699687,
      "loss": 0.6042,
      "step": 82
    },
    {
      "epoch": 0.6845360824742268,
      "grad_norm": 0.3927561640739441,
      "learning_rate": 0.00017962787477489878,
      "loss": 0.5349,
      "step": 83
    },
    {
      "epoch": 0.6927835051546392,
      "grad_norm": 0.39806240797042847,
      "learning_rate": 0.00017908635926148069,
      "loss": 0.5386,
      "step": 84
    },
    {
      "epoch": 0.7010309278350515,
      "grad_norm": 0.3762768805027008,
      "learning_rate": 0.00017853857978697223,
      "loss": 0.545,
      "step": 85
    },
    {
      "epoch": 0.709278350515464,
      "grad_norm": 0.4306787848472595,
      "learning_rate": 0.00017798457973773417,
      "loss": 0.6305,
      "step": 86
    },
    {
      "epoch": 0.7175257731958763,
      "grad_norm": 0.3811737596988678,
      "learning_rate": 0.00017742440299282203,
      "loss": 0.539,
      "step": 87
    },
    {
      "epoch": 0.7257731958762886,
      "grad_norm": 0.39163580536842346,
      "learning_rate": 0.00017685809392051083,
      "loss": 0.5286,
      "step": 88
    },
    {
      "epoch": 0.734020618556701,
      "grad_norm": 0.4237455725669861,
      "learning_rate": 0.00017628569737478076,
      "loss": 0.5801,
      "step": 89
    },
    {
      "epoch": 0.7422680412371134,
      "grad_norm": 0.41603776812553406,
      "learning_rate": 0.00017570725869176467,
      "loss": 0.6001,
      "step": 90
    },
    {
      "epoch": 0.7505154639175258,
      "grad_norm": 0.3811546862125397,
      "learning_rate": 0.00017512282368615728,
      "loss": 0.5942,
      "step": 91
    },
    {
      "epoch": 0.7587628865979381,
      "grad_norm": 0.3982357680797577,
      "learning_rate": 0.00017453243864758638,
      "loss": 0.5655,
      "step": 92
    },
    {
      "epoch": 0.7670103092783506,
      "grad_norm": 0.43069708347320557,
      "learning_rate": 0.00017393615033694656,
      "loss": 0.5251,
      "step": 93
    },
    {
      "epoch": 0.7752577319587629,
      "grad_norm": 0.3952259421348572,
      "learning_rate": 0.0001733340059826956,
      "loss": 0.5462,
      "step": 94
    },
    {
      "epoch": 0.7835051546391752,
      "grad_norm": 0.40667715668678284,
      "learning_rate": 0.00017272605327711365,
      "loss": 0.5303,
      "step": 95
    },
    {
      "epoch": 0.7917525773195876,
      "grad_norm": 0.3917592465877533,
      "learning_rate": 0.000172112340372526,
      "loss": 0.612,
      "step": 96
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.37455278635025024,
      "learning_rate": 0.00017149291587748898,
      "loss": 0.4831,
      "step": 97
    },
    {
      "epoch": 0.8082474226804124,
      "grad_norm": 0.3805007040500641,
      "learning_rate": 0.00017086782885294025,
      "loss": 0.5237,
      "step": 98
    },
    {
      "epoch": 0.8164948453608247,
      "grad_norm": 0.4057518541812897,
      "learning_rate": 0.0001702371288083127,
      "loss": 0.611,
      "step": 99
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": 0.424902081489563,
      "learning_rate": 0.00016960086569761332,
      "loss": 0.5071,
      "step": 100
    },
    {
      "epoch": 0.8329896907216495,
      "grad_norm": 0.41015303134918213,
      "learning_rate": 0.0001689590899154664,
      "loss": 0.6073,
      "step": 101
    },
    {
      "epoch": 0.8412371134020619,
      "grad_norm": 0.3922909200191498,
      "learning_rate": 0.00016831185229312237,
      "loss": 0.5923,
      "step": 102
    },
    {
      "epoch": 0.8494845360824742,
      "grad_norm": 0.43730470538139343,
      "learning_rate": 0.0001676592040944315,
      "loss": 0.5937,
      "step": 103
    },
    {
      "epoch": 0.8577319587628865,
      "grad_norm": 0.3726069927215576,
      "learning_rate": 0.0001670011970117838,
      "loss": 0.4912,
      "step": 104
    },
    {
      "epoch": 0.865979381443299,
      "grad_norm": 0.404433012008667,
      "learning_rate": 0.00016633788316201454,
      "loss": 0.474,
      "step": 105
    },
    {
      "epoch": 0.8742268041237113,
      "grad_norm": 0.41312918066978455,
      "learning_rate": 0.0001656693150822766,
      "loss": 0.5545,
      "step": 106
    },
    {
      "epoch": 0.8824742268041237,
      "grad_norm": 0.42073437571525574,
      "learning_rate": 0.0001649955457258792,
      "loss": 0.5488,
      "step": 107
    },
    {
      "epoch": 0.8907216494845361,
      "grad_norm": 0.39594408869743347,
      "learning_rate": 0.00016431662845809388,
      "loss": 0.5798,
      "step": 108
    },
    {
      "epoch": 0.8989690721649485,
      "grad_norm": 0.41331595182418823,
      "learning_rate": 0.00016363261705192757,
      "loss": 0.5188,
      "step": 109
    },
    {
      "epoch": 0.9072164948453608,
      "grad_norm": 0.3879910111427307,
      "learning_rate": 0.00016294356568386369,
      "loss": 0.5676,
      "step": 110
    },
    {
      "epoch": 0.9154639175257732,
      "grad_norm": 0.41248220205307007,
      "learning_rate": 0.00016224952892957123,
      "loss": 0.541,
      "step": 111
    },
    {
      "epoch": 0.9237113402061856,
      "grad_norm": 0.3406890034675598,
      "learning_rate": 0.0001615505617595819,
      "loss": 0.4902,
      "step": 112
    },
    {
      "epoch": 0.931958762886598,
      "grad_norm": 0.3741547167301178,
      "learning_rate": 0.00016084671953493643,
      "loss": 0.5247,
      "step": 113
    },
    {
      "epoch": 0.9402061855670103,
      "grad_norm": 0.37796300649642944,
      "learning_rate": 0.00016013805800279976,
      "loss": 0.5091,
      "step": 114
    },
    {
      "epoch": 0.9484536082474226,
      "grad_norm": 0.3957986533641815,
      "learning_rate": 0.00015942463329204546,
      "loss": 0.5809,
      "step": 115
    },
    {
      "epoch": 0.9567010309278351,
      "grad_norm": 0.38373249769210815,
      "learning_rate": 0.00015870650190881022,
      "loss": 0.4693,
      "step": 116
    },
    {
      "epoch": 0.9649484536082474,
      "grad_norm": 0.4250248074531555,
      "learning_rate": 0.00015798372073201836,
      "loss": 0.5668,
      "step": 117
    },
    {
      "epoch": 0.9731958762886598,
      "grad_norm": 0.37807247042655945,
      "learning_rate": 0.00015725634700887678,
      "loss": 0.5159,
      "step": 118
    },
    {
      "epoch": 0.9814432989690721,
      "grad_norm": 0.3726092278957367,
      "learning_rate": 0.00015652443835034068,
      "loss": 0.5605,
      "step": 119
    },
    {
      "epoch": 0.9896907216494846,
      "grad_norm": 0.38076040148735046,
      "learning_rate": 0.0001557880527265505,
      "loss": 0.537,
      "step": 120
    },
    {
      "epoch": 0.9979381443298969,
      "grad_norm": 0.37176623940467834,
      "learning_rate": 0.00015504724846224064,
      "loss": 0.5603,
      "step": 121
    },
    {
      "epoch": 1.0061855670103093,
      "grad_norm": 0.36700350046157837,
      "learning_rate": 0.00015430208423211975,
      "loss": 0.5398,
      "step": 122
    },
    {
      "epoch": 1.0061855670103093,
      "eval_loss": 0.5378922820091248,
      "eval_runtime": 296.9545,
      "eval_samples_per_second": 2.021,
      "eval_steps_per_second": 1.01,
      "step": 122
    }
  ],
  "logging_steps": 1,
  "max_steps": 363,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.642172793225216e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}