{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9644670050761421,
  "eval_steps": 98,
  "global_step": 196,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01015228426395939,
      "grad_norm": 0.516016960144043,
      "learning_rate": 2e-05,
      "loss": 4.3699,
      "step": 1
    },
    {
      "epoch": 0.01015228426395939,
      "eval_loss": 4.561354637145996,
      "eval_runtime": 58.1653,
      "eval_samples_per_second": 10.144,
      "eval_steps_per_second": 1.272,
      "step": 1
    },
    {
      "epoch": 0.02030456852791878,
      "grad_norm": 0.5144633650779724,
      "learning_rate": 4e-05,
      "loss": 4.5708,
      "step": 2
    },
    {
      "epoch": 0.030456852791878174,
      "grad_norm": 0.5246109962463379,
      "learning_rate": 6e-05,
      "loss": 4.5871,
      "step": 3
    },
    {
      "epoch": 0.04060913705583756,
      "grad_norm": 0.5753014087677002,
      "learning_rate": 8e-05,
      "loss": 4.3818,
      "step": 4
    },
    {
      "epoch": 0.050761421319796954,
      "grad_norm": 0.6615588665008545,
      "learning_rate": 0.0001,
      "loss": 4.448,
      "step": 5
    },
    {
      "epoch": 0.06091370558375635,
      "grad_norm": 0.751004159450531,
      "learning_rate": 0.00012,
      "loss": 4.4964,
      "step": 6
    },
    {
      "epoch": 0.07106598984771574,
      "grad_norm": 0.886650562286377,
      "learning_rate": 0.00014,
      "loss": 4.4011,
      "step": 7
    },
    {
      "epoch": 0.08121827411167512,
      "grad_norm": 1.1175657510757446,
      "learning_rate": 0.00016,
      "loss": 3.9849,
      "step": 8
    },
    {
      "epoch": 0.09137055837563451,
      "grad_norm": 0.9861809015274048,
      "learning_rate": 0.00018,
      "loss": 3.8218,
      "step": 9
    },
    {
      "epoch": 0.10152284263959391,
      "grad_norm": 1.1107577085494995,
      "learning_rate": 0.0002,
      "loss": 3.6451,
      "step": 10
    },
    {
      "epoch": 0.1116751269035533,
      "grad_norm": 0.9435870051383972,
      "learning_rate": 0.000199985736255971,
      "loss": 3.5619,
      "step": 11
    },
    {
      "epoch": 0.1218274111675127,
      "grad_norm": 0.9529088139533997,
      "learning_rate": 0.0001999429490929718,
      "loss": 3.4561,
      "step": 12
    },
    {
      "epoch": 0.1319796954314721,
      "grad_norm": 1.3805211782455444,
      "learning_rate": 0.00019987165071710527,
      "loss": 3.2067,
      "step": 13
    },
    {
      "epoch": 0.14213197969543148,
      "grad_norm": 1.319393515586853,
      "learning_rate": 0.00019977186146800707,
      "loss": 3.0656,
      "step": 14
    },
    {
      "epoch": 0.15228426395939088,
      "grad_norm": 1.061409592628479,
      "learning_rate": 0.0001996436098130433,
      "loss": 2.7711,
      "step": 15
    },
    {
      "epoch": 0.16243654822335024,
      "grad_norm": 1.036845326423645,
      "learning_rate": 0.00019948693233918952,
      "loss": 2.6576,
      "step": 16
    },
    {
      "epoch": 0.17258883248730963,
      "grad_norm": 1.0924557447433472,
      "learning_rate": 0.00019930187374259337,
      "loss": 2.4101,
      "step": 17
    },
    {
      "epoch": 0.18274111675126903,
      "grad_norm": 1.0557212829589844,
      "learning_rate": 0.00019908848681582391,
      "loss": 2.2991,
      "step": 18
    },
    {
      "epoch": 0.19289340101522842,
      "grad_norm": 1.1735273599624634,
      "learning_rate": 0.00019884683243281116,
      "loss": 2.3991,
      "step": 19
    },
    {
      "epoch": 0.20304568527918782,
      "grad_norm": 0.8104203343391418,
      "learning_rate": 0.00019857697953148037,
      "loss": 2.107,
      "step": 20
    },
    {
      "epoch": 0.2131979695431472,
      "grad_norm": 0.7275764346122742,
      "learning_rate": 0.00019827900509408581,
      "loss": 2.0596,
      "step": 21
    },
    {
      "epoch": 0.2233502538071066,
      "grad_norm": 1.0672590732574463,
      "learning_rate": 0.00019795299412524945,
      "loss": 1.9543,
      "step": 22
    },
    {
      "epoch": 0.233502538071066,
      "grad_norm": 0.5848283767700195,
      "learning_rate": 0.00019759903962771156,
      "loss": 1.8091,
      "step": 23
    },
    {
      "epoch": 0.2436548223350254,
      "grad_norm": 0.9580035209655762,
      "learning_rate": 0.00019721724257579907,
      "loss": 1.7178,
      "step": 24
    },
    {
      "epoch": 0.25380710659898476,
      "grad_norm": 0.5362741351127625,
      "learning_rate": 0.00019680771188662044,
      "loss": 1.6739,
      "step": 25
    },
    {
      "epoch": 0.2639593908629442,
      "grad_norm": 0.5108774304389954,
      "learning_rate": 0.0001963705643889941,
      "loss": 1.7575,
      "step": 26
    },
    {
      "epoch": 0.27411167512690354,
      "grad_norm": 0.5604164004325867,
      "learning_rate": 0.00019590592479012023,
      "loss": 1.6815,
      "step": 27
    },
    {
      "epoch": 0.28426395939086296,
      "grad_norm": 0.7223322987556458,
      "learning_rate": 0.00019541392564000488,
      "loss": 1.6213,
      "step": 28
    },
    {
      "epoch": 0.29441624365482233,
      "grad_norm": 0.5081471800804138,
      "learning_rate": 0.00019489470729364692,
      "loss": 1.5935,
      "step": 29
    },
    {
      "epoch": 0.30456852791878175,
      "grad_norm": 0.5000993013381958,
      "learning_rate": 0.00019434841787099803,
      "loss": 1.6237,
      "step": 30
    },
    {
      "epoch": 0.3147208121827411,
      "grad_norm": 0.45925211906433105,
      "learning_rate": 0.00019377521321470805,
      "loss": 1.6201,
      "step": 31
    },
    {
      "epoch": 0.3248730964467005,
      "grad_norm": 0.38572826981544495,
      "learning_rate": 0.00019317525684566685,
      "loss": 1.4805,
      "step": 32
    },
    {
      "epoch": 0.3350253807106599,
      "grad_norm": 0.28524091839790344,
      "learning_rate": 0.00019254871991635598,
      "loss": 1.5985,
      "step": 33
    },
    {
      "epoch": 0.34517766497461927,
      "grad_norm": 0.3277890980243683,
      "learning_rate": 0.00019189578116202307,
      "loss": 1.4994,
      "step": 34
    },
    {
      "epoch": 0.3553299492385787,
      "grad_norm": 0.3320370018482208,
      "learning_rate": 0.00019121662684969335,
      "loss": 1.5039,
      "step": 35
    },
    {
      "epoch": 0.36548223350253806,
      "grad_norm": 0.2798719108104706,
      "learning_rate": 0.00019051145072503215,
      "loss": 1.4997,
      "step": 36
    },
    {
      "epoch": 0.3756345177664975,
      "grad_norm": 1.7497050762176514,
      "learning_rate": 0.00018978045395707418,
      "loss": 1.5465,
      "step": 37
    },
    {
      "epoch": 0.38578680203045684,
      "grad_norm": 0.27379170060157776,
      "learning_rate": 0.00018902384508083517,
      "loss": 1.4846,
      "step": 38
    },
    {
      "epoch": 0.39593908629441626,
      "grad_norm": 0.36681699752807617,
      "learning_rate": 0.00018824183993782192,
      "loss": 1.4154,
      "step": 39
    },
    {
      "epoch": 0.40609137055837563,
      "grad_norm": 0.45136329531669617,
      "learning_rate": 0.00018743466161445823,
      "loss": 1.3928,
      "step": 40
    },
    {
      "epoch": 0.41624365482233505,
      "grad_norm": 0.27879664301872253,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.5119,
      "step": 41
    },
    {
      "epoch": 0.4263959390862944,
      "grad_norm": 0.29230332374572754,
      "learning_rate": 0.0001857457136130651,
      "loss": 1.5095,
      "step": 42
    },
    {
      "epoch": 0.4365482233502538,
      "grad_norm": 0.2731008231639862,
      "learning_rate": 0.00018486442574947511,
      "loss": 1.4672,
      "step": 43
    },
    {
      "epoch": 0.4467005076142132,
      "grad_norm": 0.23685932159423828,
      "learning_rate": 0.00018395892819696389,
      "loss": 1.4173,
      "step": 44
    },
    {
      "epoch": 0.45685279187817257,
      "grad_norm": 0.2703058421611786,
      "learning_rate": 0.00018302947927123766,
      "loss": 1.4088,
      "step": 45
    },
    {
      "epoch": 0.467005076142132,
      "grad_norm": 1.65743887424469,
      "learning_rate": 0.00018207634412072764,
      "loss": 1.4672,
      "step": 46
    },
    {
      "epoch": 0.47715736040609136,
      "grad_norm": 0.21287347376346588,
      "learning_rate": 0.00018109979465095013,
      "loss": 1.3975,
      "step": 47
    },
    {
      "epoch": 0.4873096446700508,
      "grad_norm": 0.3460160791873932,
      "learning_rate": 0.00018010010944693848,
      "loss": 1.4501,
      "step": 48
    },
    {
      "epoch": 0.49746192893401014,
      "grad_norm": 0.4228818714618683,
      "learning_rate": 0.00017907757369376985,
      "loss": 1.4632,
      "step": 49
    },
    {
      "epoch": 0.5076142131979695,
      "grad_norm": 0.46471402049064636,
      "learning_rate": 0.0001780324790952092,
      "loss": 1.3696,
      "step": 50
    },
    {
      "epoch": 0.5177664974619289,
      "grad_norm": 0.35602033138275146,
      "learning_rate": 0.00017696512379049325,
      "loss": 1.4096,
      "step": 51
    },
    {
      "epoch": 0.5279187817258884,
      "grad_norm": 0.2879682779312134,
      "learning_rate": 0.0001758758122692791,
      "loss": 1.337,
      "step": 52
    },
    {
      "epoch": 0.5380710659898477,
      "grad_norm": 0.1947374939918518,
      "learning_rate": 0.00017476485528478093,
      "loss": 1.3815,
      "step": 53
    },
    {
      "epoch": 0.5482233502538071,
      "grad_norm": 0.22819018363952637,
      "learning_rate": 0.00017363256976511972,
      "loss": 1.4021,
      "step": 54
    },
    {
      "epoch": 0.5583756345177665,
      "grad_norm": 0.19164641201496124,
      "learning_rate": 0.000172479278722912,
      "loss": 1.3899,
      "step": 55
    },
    {
      "epoch": 0.5685279187817259,
      "grad_norm": 0.5477288961410522,
      "learning_rate": 0.00017130531116312203,
      "loss": 1.4089,
      "step": 56
    },
    {
      "epoch": 0.5786802030456852,
      "grad_norm": 0.6282036900520325,
      "learning_rate": 0.0001701110019892053,
      "loss": 1.3983,
      "step": 57
    },
    {
      "epoch": 0.5888324873096447,
      "grad_norm": 0.5962779521942139,
      "learning_rate": 0.00016889669190756868,
      "loss": 1.3126,
      "step": 58
    },
    {
      "epoch": 0.5989847715736041,
      "grad_norm": 0.39695534110069275,
      "learning_rate": 0.00016766272733037576,
      "loss": 1.3693,
      "step": 59
    },
    {
      "epoch": 0.6091370558375635,
      "grad_norm": 0.2737330198287964,
      "learning_rate": 0.00016640946027672392,
      "loss": 1.4286,
      "step": 60
    },
    {
      "epoch": 0.6192893401015228,
      "grad_norm": 0.34324145317077637,
      "learning_rate": 0.00016513724827222227,
      "loss": 1.3363,
      "step": 61
    },
    {
      "epoch": 0.6294416243654822,
      "grad_norm": 0.4945085942745209,
      "learning_rate": 0.00016384645424699835,
      "loss": 1.4388,
      "step": 62
    },
    {
      "epoch": 0.6395939086294417,
      "grad_norm": 0.3939533829689026,
      "learning_rate": 0.00016253744643216368,
      "loss": 1.325,
      "step": 63
    },
    {
      "epoch": 0.649746192893401,
      "grad_norm": 0.3593675196170807,
      "learning_rate": 0.0001612105982547663,
      "loss": 1.353,
      "step": 64
    },
    {
      "epoch": 0.6598984771573604,
      "grad_norm": 0.3457062244415283,
      "learning_rate": 0.0001598662882312615,
      "loss": 1.3119,
      "step": 65
    },
    {
      "epoch": 0.6700507614213198,
      "grad_norm": 0.22607868909835815,
      "learning_rate": 0.00015850489985953076,
      "loss": 1.3281,
      "step": 66
    },
    {
      "epoch": 0.6802030456852792,
      "grad_norm": 0.1937730461359024,
      "learning_rate": 0.00015712682150947923,
      "loss": 1.3061,
      "step": 67
    },
    {
      "epoch": 0.6903553299492385,
      "grad_norm": 0.19334916770458221,
      "learning_rate": 0.00015573244631224365,
      "loss": 1.2995,
      "step": 68
    },
    {
      "epoch": 0.700507614213198,
      "grad_norm": 0.43978920578956604,
      "learning_rate": 0.0001543221720480419,
      "loss": 1.3196,
      "step": 69
    },
    {
      "epoch": 0.7106598984771574,
      "grad_norm": 0.20429864525794983,
      "learning_rate": 0.00015289640103269625,
      "loss": 1.3428,
      "step": 70
    },
    {
      "epoch": 0.7208121827411168,
      "grad_norm": 0.2042793482542038,
      "learning_rate": 0.0001514555400028629,
      "loss": 1.2717,
      "step": 71
    },
    {
      "epoch": 0.7309644670050761,
      "grad_norm": 0.2089298814535141,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.2823,
      "step": 72
    },
    {
      "epoch": 0.7411167512690355,
      "grad_norm": 0.29447218775749207,
      "learning_rate": 0.00014853019625310813,
      "loss": 1.2596,
      "step": 73
    },
    {
      "epoch": 0.751269035532995,
      "grad_norm": 0.20766524970531464,
      "learning_rate": 0.0001470465480602756,
      "loss": 1.3421,
      "step": 74
    },
    {
      "epoch": 0.7614213197969543,
      "grad_norm": 0.19240014255046844,
      "learning_rate": 0.0001455494786690634,
      "loss": 1.3871,
      "step": 75
    },
    {
      "epoch": 0.7715736040609137,
      "grad_norm": 0.16677537560462952,
      "learning_rate": 0.00014403941515576344,
      "loss": 1.2507,
      "step": 76
    },
    {
      "epoch": 0.7817258883248731,
      "grad_norm": 0.1933940052986145,
      "learning_rate": 0.00014251678830356408,
      "loss": 1.2792,
      "step": 77
    },
    {
      "epoch": 0.7918781725888325,
      "grad_norm": 0.19050206243991852,
      "learning_rate": 0.00014098203247965875,
      "loss": 1.3017,
      "step": 78
    },
    {
      "epoch": 0.8020304568527918,
      "grad_norm": 0.25748810172080994,
      "learning_rate": 0.00013943558551133186,
      "loss": 1.2879,
      "step": 79
    },
    {
      "epoch": 0.8121827411167513,
      "grad_norm": 0.2314893752336502,
      "learning_rate": 0.0001378778885610576,
      "loss": 1.3692,
      "step": 80
    },
    {
      "epoch": 0.8223350253807107,
      "grad_norm": 0.20771433413028717,
      "learning_rate": 0.00013630938600064747,
      "loss": 1.3268,
      "step": 81
    },
    {
      "epoch": 0.8324873096446701,
      "grad_norm": 0.18968452513217926,
      "learning_rate": 0.00013473052528448201,
      "loss": 1.2663,
      "step": 82
    },
    {
      "epoch": 0.8426395939086294,
      "grad_norm": 0.1978602409362793,
      "learning_rate": 0.0001331417568218636,
      "loss": 1.2968,
      "step": 83
    },
    {
      "epoch": 0.8527918781725888,
      "grad_norm": 0.9941853284835815,
      "learning_rate": 0.00013154353384852558,
      "loss": 1.3187,
      "step": 84
    },
    {
      "epoch": 0.8629441624365483,
      "grad_norm": 0.18706466257572174,
      "learning_rate": 0.00012993631229733582,
      "loss": 1.2808,
      "step": 85
    },
    {
      "epoch": 0.8730964467005076,
      "grad_norm": 0.18098409473896027,
      "learning_rate": 0.00012832055066823038,
      "loss": 1.2246,
      "step": 86
    },
    {
      "epoch": 0.883248730964467,
      "grad_norm": 0.22270160913467407,
      "learning_rate": 0.00012669670989741517,
      "loss": 1.3028,
      "step": 87
    },
    {
      "epoch": 0.8934010152284264,
      "grad_norm": 0.25465860962867737,
      "learning_rate": 0.00012506525322587207,
      "loss": 1.347,
      "step": 88
    },
    {
      "epoch": 0.9035532994923858,
      "grad_norm": 0.23076751828193665,
      "learning_rate": 0.00012342664606720822,
      "loss": 1.3099,
      "step": 89
    },
    {
      "epoch": 0.9137055837563451,
      "grad_norm": 0.19831228256225586,
      "learning_rate": 0.00012178135587488515,
      "loss": 1.278,
      "step": 90
    },
    {
      "epoch": 0.9238578680203046,
      "grad_norm": 0.22052858769893646,
      "learning_rate": 0.00012012985200886602,
      "loss": 1.2165,
      "step": 91
    },
    {
      "epoch": 0.934010152284264,
      "grad_norm": 0.18730390071868896,
      "learning_rate": 0.00011847260560171896,
      "loss": 1.2814,
      "step": 92
    },
    {
      "epoch": 0.9441624365482234,
      "grad_norm": 0.16983264684677124,
      "learning_rate": 0.00011681008942421483,
      "loss": 1.2235,
      "step": 93
    },
    {
      "epoch": 0.9543147208121827,
      "grad_norm": 0.17806044220924377,
      "learning_rate": 0.00011514277775045768,
      "loss": 1.1867,
      "step": 94
    },
    {
      "epoch": 0.9644670050761421,
      "grad_norm": 0.1574580818414688,
      "learning_rate": 0.00011347114622258612,
      "loss": 1.2718,
      "step": 95
    },
    {
      "epoch": 0.9746192893401016,
      "grad_norm": 0.15895454585552216,
      "learning_rate": 0.00011179567171508463,
      "loss": 1.245,
      "step": 96
    },
    {
      "epoch": 0.9847715736040609,
      "grad_norm": 0.22224721312522888,
      "learning_rate": 0.00011011683219874323,
      "loss": 1.2945,
      "step": 97
    },
    {
      "epoch": 0.9949238578680203,
      "grad_norm": 0.16613103449344635,
      "learning_rate": 0.00010843510660430447,
      "loss": 1.3054,
      "step": 98
    },
    {
      "epoch": 0.9949238578680203,
      "eval_loss": 1.249497413635254,
      "eval_runtime": 58.5386,
      "eval_samples_per_second": 10.079,
      "eval_steps_per_second": 1.264,
      "step": 98
    },
    {
      "epoch": 1.0050761421319796,
      "grad_norm": 0.18297390639781952,
      "learning_rate": 0.00010675097468583652,
      "loss": 1.2749,
      "step": 99
    },
    {
      "epoch": 1.015228426395939,
      "grad_norm": 0.1834397166967392,
      "learning_rate": 0.00010506491688387127,
      "loss": 1.3218,
      "step": 100
    },
    {
      "epoch": 1.0253807106598984,
      "grad_norm": 0.37363290786743164,
      "learning_rate": 0.00010337741418834684,
      "loss": 1.2591,
      "step": 101
    },
    {
      "epoch": 1.0101522842639594,
      "grad_norm": 0.14738723635673523,
      "learning_rate": 0.0001016889480013931,
      "loss": 1.2353,
      "step": 102
    },
    {
      "epoch": 1.0203045685279188,
      "grad_norm": 0.17808881402015686,
      "learning_rate": 0.0001,
      "loss": 1.2708,
      "step": 103
    },
    {
      "epoch": 1.0304568527918783,
      "grad_norm": 0.1652560830116272,
      "learning_rate": 9.83110519986069e-05,
      "loss": 1.2261,
      "step": 104
    },
    {
      "epoch": 1.0406091370558375,
      "grad_norm": 0.1601293385028839,
      "learning_rate": 9.662258581165319e-05,
      "loss": 1.2336,
      "step": 105
    },
    {
      "epoch": 1.0507614213197969,
      "grad_norm": 0.18094658851623535,
      "learning_rate": 9.493508311612874e-05,
      "loss": 1.2165,
      "step": 106
    },
    {
      "epoch": 1.0609137055837563,
      "grad_norm": 0.17732879519462585,
      "learning_rate": 9.324902531416349e-05,
      "loss": 1.2647,
      "step": 107
    },
    {
      "epoch": 1.0710659898477157,
      "grad_norm": 0.16203966736793518,
      "learning_rate": 9.156489339569554e-05,
      "loss": 1.2343,
      "step": 108
    },
    {
      "epoch": 1.0812182741116751,
      "grad_norm": 0.21242284774780273,
      "learning_rate": 8.98831678012568e-05,
      "loss": 1.2335,
      "step": 109
    },
    {
      "epoch": 1.0913705583756346,
      "grad_norm": 0.1700202375650406,
      "learning_rate": 8.820432828491542e-05,
      "loss": 1.175,
      "step": 110
    },
    {
      "epoch": 1.101522842639594,
      "grad_norm": 0.1947324275970459,
      "learning_rate": 8.652885377741393e-05,
      "loss": 1.2354,
      "step": 111
    },
    {
      "epoch": 1.1116751269035534,
      "grad_norm": 0.15965348482131958,
      "learning_rate": 8.485722224954237e-05,
      "loss": 1.1937,
      "step": 112
    },
    {
      "epoch": 1.1218274111675126,
      "grad_norm": 0.1767743080854416,
      "learning_rate": 8.31899105757852e-05,
      "loss": 1.2075,
      "step": 113
    },
    {
      "epoch": 1.131979695431472,
      "grad_norm": 0.1793358474969864,
      "learning_rate": 8.15273943982811e-05,
      "loss": 1.2963,
      "step": 114
    },
    {
      "epoch": 1.1421319796954315,
      "grad_norm": 0.17889666557312012,
      "learning_rate": 7.987014799113397e-05,
      "loss": 1.208,
      "step": 115
    },
    {
      "epoch": 1.1522842639593909,
      "grad_norm": 0.16769151389598846,
      "learning_rate": 7.821864412511485e-05,
      "loss": 1.2279,
      "step": 116
    },
    {
      "epoch": 1.1624365482233503,
      "grad_norm": 0.1788126677274704,
      "learning_rate": 7.65733539327918e-05,
      "loss": 1.2341,
      "step": 117
    },
    {
      "epoch": 1.1725888324873097,
      "grad_norm": 0.17543092370033264,
      "learning_rate": 7.493474677412794e-05,
      "loss": 1.3065,
      "step": 118
    },
    {
      "epoch": 1.1827411167512691,
      "grad_norm": 0.18606220185756683,
      "learning_rate": 7.330329010258483e-05,
      "loss": 1.2233,
      "step": 119
    },
    {
      "epoch": 1.1928934010152283,
      "grad_norm": 0.23003295063972473,
      "learning_rate": 7.16794493317696e-05,
      "loss": 1.2107,
      "step": 120
    },
    {
      "epoch": 1.2030456852791878,
      "grad_norm": 0.15619252622127533,
      "learning_rate": 7.006368770266421e-05,
      "loss": 1.1885,
      "step": 121
    },
    {
      "epoch": 1.2131979695431472,
      "grad_norm": 0.22341646254062653,
      "learning_rate": 6.845646615147445e-05,
      "loss": 1.2421,
      "step": 122
    },
    {
      "epoch": 1.2233502538071066,
      "grad_norm": 0.1528923660516739,
      "learning_rate": 6.685824317813643e-05,
      "loss": 1.207,
      "step": 123
    },
    {
      "epoch": 1.233502538071066,
      "grad_norm": 0.15776072442531586,
      "learning_rate": 6.526947471551798e-05,
      "loss": 1.278,
      "step": 124
    },
    {
      "epoch": 1.2436548223350254,
      "grad_norm": 0.1788446009159088,
      "learning_rate": 6.369061399935255e-05,
      "loss": 1.2107,
      "step": 125
    },
    {
      "epoch": 1.2538071065989849,
      "grad_norm": 0.17271803319454193,
      "learning_rate": 6.21221114389424e-05,
      "loss": 1.2333,
      "step": 126
    },
    {
      "epoch": 1.263959390862944,
      "grad_norm": 0.15987545251846313,
      "learning_rate": 6.0564414488668165e-05,
      "loss": 1.238,
      "step": 127
    },
    {
      "epoch": 1.2741116751269035,
      "grad_norm": 0.16485555469989777,
      "learning_rate": 5.901796752034128e-05,
      "loss": 1.2471,
      "step": 128
    },
    {
      "epoch": 1.284263959390863,
      "grad_norm": 0.18228358030319214,
      "learning_rate": 5.748321169643596e-05,
      "loss": 1.1761,
      "step": 129
    },
    {
      "epoch": 1.2944162436548223,
      "grad_norm": 0.1641974151134491,
      "learning_rate": 5.596058484423656e-05,
      "loss": 1.2469,
      "step": 130
    },
    {
      "epoch": 1.3045685279187818,
      "grad_norm": 0.20411786437034607,
      "learning_rate": 5.44505213309366e-05,
      "loss": 1.212,
      "step": 131
    },
    {
      "epoch": 1.3147208121827412,
      "grad_norm": 0.16920053958892822,
      "learning_rate": 5.2953451939724454e-05,
      "loss": 1.254,
      "step": 132
    },
    {
      "epoch": 1.3248730964467006,
      "grad_norm": 0.19527798891067505,
      "learning_rate": 5.146980374689192e-05,
      "loss": 1.2187,
      "step": 133
    },
    {
      "epoch": 1.3350253807106598,
      "grad_norm": 0.19046878814697266,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.2035,
      "step": 134
    },
    {
      "epoch": 1.3451776649746192,
      "grad_norm": 0.1827058643102646,
      "learning_rate": 4.854445999713715e-05,
      "loss": 1.1891,
      "step": 135
    },
    {
      "epoch": 1.3553299492385786,
      "grad_norm": 0.16475000977516174,
      "learning_rate": 4.710359896730379e-05,
      "loss": 1.2263,
      "step": 136
    },
    {
      "epoch": 1.365482233502538,
      "grad_norm": 0.15977239608764648,
      "learning_rate": 4.567782795195816e-05,
      "loss": 1.2006,
      "step": 137
    },
    {
      "epoch": 1.3756345177664975,
      "grad_norm": 0.16366241872310638,
      "learning_rate": 4.426755368775637e-05,
      "loss": 1.1572,
      "step": 138
    },
    {
      "epoch": 1.385786802030457,
      "grad_norm": 0.16748002171516418,
      "learning_rate": 4.287317849052075e-05,
      "loss": 1.1932,
      "step": 139
    },
    {
      "epoch": 1.3959390862944163,
      "grad_norm": 0.17944949865341187,
      "learning_rate": 4.149510014046922e-05,
      "loss": 1.1635,
      "step": 140
    },
    {
      "epoch": 1.4060913705583755,
      "grad_norm": 0.15999887883663177,
      "learning_rate": 4.013371176873849e-05,
      "loss": 1.1987,
      "step": 141
    },
    {
      "epoch": 1.4162436548223352,
      "grad_norm": 0.17952662706375122,
      "learning_rate": 3.878940174523371e-05,
      "loss": 1.2722,
      "step": 142
    },
    {
      "epoch": 1.4263959390862944,
      "grad_norm": 0.16714362800121307,
      "learning_rate": 3.746255356783632e-05,
      "loss": 1.2027,
      "step": 143
    },
    {
      "epoch": 1.4365482233502538,
      "grad_norm": 0.21137690544128418,
      "learning_rate": 3.615354575300166e-05,
      "loss": 1.2099,
      "step": 144
    },
    {
      "epoch": 1.4467005076142132,
      "grad_norm": 0.16340382397174835,
      "learning_rate": 3.4862751727777797e-05,
      "loss": 1.2476,
      "step": 145
    },
    {
      "epoch": 1.4568527918781726,
      "grad_norm": 0.33795541524887085,
      "learning_rate": 3.3590539723276083e-05,
      "loss": 1.1955,
      "step": 146
    },
    {
      "epoch": 1.467005076142132,
      "grad_norm": 0.1949048787355423,
      "learning_rate": 3.233727266962425e-05,
      "loss": 1.2588,
      "step": 147
    },
    {
      "epoch": 1.4771573604060912,
      "grad_norm": 0.15895332396030426,
      "learning_rate": 3.110330809243134e-05,
      "loss": 1.1895,
      "step": 148
    },
    {
      "epoch": 1.487309644670051,
      "grad_norm": 0.17805150151252747,
      "learning_rate": 2.9888998010794743e-05,
      "loss": 1.2412,
      "step": 149
    },
    {
      "epoch": 1.49746192893401,
      "grad_norm": 0.16068041324615479,
      "learning_rate": 2.869468883687798e-05,
      "loss": 1.1935,
      "step": 150
    },
    {
      "epoch": 1.5076142131979695,
      "grad_norm": 0.16954682767391205,
      "learning_rate": 2.7520721277088024e-05,
      "loss": 1.2139,
      "step": 151
    },
    {
      "epoch": 1.517766497461929,
      "grad_norm": 0.17811493575572968,
      "learning_rate": 2.6367430234880284e-05,
      "loss": 1.2791,
      "step": 152
    },
    {
      "epoch": 1.5279187817258884,
      "grad_norm": 0.1642419546842575,
      "learning_rate": 2.523514471521913e-05,
      "loss": 1.2178,
      "step": 153
    },
    {
      "epoch": 1.5380710659898478,
      "grad_norm": 0.16778188943862915,
      "learning_rate": 2.4124187730720917e-05,
      "loss": 1.2735,
      "step": 154
    },
    {
      "epoch": 1.548223350253807,
      "grad_norm": 0.17863012850284576,
      "learning_rate": 2.3034876209506772e-05,
      "loss": 1.1632,
      "step": 155
    },
    {
      "epoch": 1.5583756345177666,
      "grad_norm": 0.15400968492031097,
      "learning_rate": 2.1967520904790827e-05,
      "loss": 1.2465,
      "step": 156
    },
    {
      "epoch": 1.5685279187817258,
      "grad_norm": 0.1574324369430542,
      "learning_rate": 2.092242630623016e-05,
      "loss": 1.2346,
      "step": 157
    },
    {
      "epoch": 1.5786802030456852,
      "grad_norm": 0.15566711127758026,
      "learning_rate": 1.9899890553061562e-05,
      "loss": 1.188,
      "step": 158
    },
    {
      "epoch": 1.5888324873096447,
      "grad_norm": 0.1699032336473465,
      "learning_rate": 1.8900205349049904e-05,
      "loss": 1.2062,
      "step": 159
    },
    {
      "epoch": 1.598984771573604,
      "grad_norm": 0.20871774852275848,
      "learning_rate": 1.7923655879272393e-05,
      "loss": 1.2349,
      "step": 160
    },
    {
      "epoch": 1.6091370558375635,
      "grad_norm": 0.19627781212329865,
      "learning_rate": 1.6970520728762375e-05,
      "loss": 1.193,
      "step": 161
    },
    {
      "epoch": 1.6192893401015227,
      "grad_norm": 0.1803133487701416,
      "learning_rate": 1.60410718030361e-05,
      "loss": 1.28,
      "step": 162
    },
    {
      "epoch": 1.6294416243654823,
      "grad_norm": 0.17840127646923065,
      "learning_rate": 1.5135574250524897e-05,
      "loss": 1.285,
      "step": 163
    },
    {
      "epoch": 1.6395939086294415,
      "grad_norm": 0.1523265242576599,
      "learning_rate": 1.425428638693489e-05,
      "loss": 1.2491,
      "step": 164
    },
    {
      "epoch": 1.649746192893401,
      "grad_norm": 0.17296157777309418,
      "learning_rate": 1.339745962155613e-05,
      "loss": 1.231,
      "step": 165
    },
    {
      "epoch": 1.6598984771573604,
      "grad_norm": 0.17164817452430725,
      "learning_rate": 1.2565338385541792e-05,
      "loss": 1.2217,
      "step": 166
    },
    {
      "epoch": 1.6700507614213198,
      "grad_norm": 0.17271456122398376,
      "learning_rate": 1.1758160062178093e-05,
      "loss": 1.285,
      "step": 167
    },
    {
      "epoch": 1.6802030456852792,
      "grad_norm": 0.16020996868610382,
      "learning_rate": 1.097615491916485e-05,
      "loss": 1.1259,
      "step": 168
    },
    {
      "epoch": 1.6903553299492384,
      "grad_norm": 0.17722178995609283,
      "learning_rate": 1.0219546042925843e-05,
      "loss": 1.2601,
      "step": 169
    },
    {
      "epoch": 1.700507614213198,
      "grad_norm": 0.1641930788755417,
      "learning_rate": 9.488549274967872e-06,
      "loss": 1.1552,
      "step": 170
    },
    {
      "epoch": 1.7106598984771573,
      "grad_norm": 0.17400699853897095,
      "learning_rate": 8.783373150306661e-06,
      "loss": 1.2226,
      "step": 171
    },
    {
      "epoch": 1.720812182741117,
      "grad_norm": 0.16899757087230682,
      "learning_rate": 8.10421883797694e-06,
      "loss": 1.3269,
      "step": 172
    },
    {
      "epoch": 1.7309644670050761,
      "grad_norm": 0.20650531351566315,
      "learning_rate": 7.4512800836440525e-06,
      "loss": 1.1627,
      "step": 173
    },
    {
      "epoch": 1.7411167512690355,
      "grad_norm": 0.15405453741550446,
      "learning_rate": 6.824743154333157e-06,
      "loss": 1.1767,
      "step": 174
    },
    {
      "epoch": 1.751269035532995,
      "grad_norm": 0.16714583337306976,
      "learning_rate": 6.22478678529197e-06,
      "loss": 1.2332,
      "step": 175
    },
    {
      "epoch": 1.7614213197969542,
      "grad_norm": 0.16613709926605225,
      "learning_rate": 5.651582129001986e-06,
      "loss": 1.2306,
      "step": 176
    },
    {
      "epoch": 1.7715736040609138,
      "grad_norm": 0.22227272391319275,
      "learning_rate": 5.105292706353093e-06,
      "loss": 1.1969,
      "step": 177
    },
    {
      "epoch": 1.781725888324873,
      "grad_norm": 0.18371812999248505,
      "learning_rate": 4.586074359995119e-06,
      "loss": 1.2643,
      "step": 178
    },
    {
      "epoch": 1.7918781725888326,
      "grad_norm": 0.1571132242679596,
      "learning_rate": 4.094075209879788e-06,
      "loss": 1.208,
      "step": 179
    },
    {
      "epoch": 1.8020304568527918,
      "grad_norm": 0.16985946893692017,
      "learning_rate": 3.6294356110059157e-06,
      "loss": 1.2069,
      "step": 180
    },
    {
      "epoch": 1.8121827411167513,
      "grad_norm": 0.16651304066181183,
      "learning_rate": 3.1922881133795825e-06,
      "loss": 1.2017,
      "step": 181
    },
    {
      "epoch": 1.8223350253807107,
      "grad_norm": 0.16982710361480713,
      "learning_rate": 2.7827574242009437e-06,
      "loss": 1.1706,
      "step": 182
    },
    {
      "epoch": 1.83248730964467,
      "grad_norm": 0.16492588818073273,
      "learning_rate": 2.4009603722884742e-06,
      "loss": 1.2733,
      "step": 183
    },
    {
      "epoch": 1.8426395939086295,
      "grad_norm": 0.165365532040596,
      "learning_rate": 2.0470058747505516e-06,
      "loss": 1.1843,
      "step": 184
    },
    {
      "epoch": 1.8527918781725887,
      "grad_norm": 0.15770269930362701,
      "learning_rate": 1.7209949059142083e-06,
      "loss": 1.2168,
      "step": 185
    },
    {
      "epoch": 1.8629441624365484,
      "grad_norm": 0.16646115481853485,
      "learning_rate": 1.4230204685196203e-06,
      "loss": 1.1774,
      "step": 186
    },
    {
      "epoch": 1.8730964467005076,
      "grad_norm": 0.17410410940647125,
      "learning_rate": 1.1531675671888619e-06,
      "loss": 1.2268,
      "step": 187
    },
    {
      "epoch": 1.883248730964467,
      "grad_norm": 0.17677107453346252,
      "learning_rate": 9.11513184176116e-07,
      "loss": 1.1485,
      "step": 188
    },
    {
      "epoch": 1.8934010152284264,
      "grad_norm": 0.15033933520317078,
      "learning_rate": 6.981262574066394e-07,
      "loss": 1.2125,
      "step": 189
    },
    {
      "epoch": 1.9035532994923858,
      "grad_norm": 0.1645897626876831,
      "learning_rate": 5.130676608104845e-07,
      "loss": 1.2151,
      "step": 190
    },
    {
      "epoch": 1.9137055837563453,
      "grad_norm": 0.17260093986988068,
      "learning_rate": 3.56390186956701e-07,
      "loss": 1.2509,
      "step": 191
    },
    {
      "epoch": 1.9238578680203045,
      "grad_norm": 0.16453680396080017,
      "learning_rate": 2.2813853199292746e-07,
      "loss": 1.264,
      "step": 192
    },
    {
      "epoch": 1.934010152284264,
      "grad_norm": 0.1580802947282791,
      "learning_rate": 1.2834928289472416e-07,
      "loss": 1.193,
      "step": 193
    },
    {
      "epoch": 1.9441624365482233,
      "grad_norm": 0.18191225826740265,
      "learning_rate": 5.705090702819993e-08,
      "loss": 1.2404,
      "step": 194
    },
    {
      "epoch": 1.9543147208121827,
      "grad_norm": 0.19886773824691772,
      "learning_rate": 1.426374402901942e-08,
      "loss": 1.1602,
      "step": 195
    },
    {
      "epoch": 1.9644670050761421,
      "grad_norm": 0.19592063128948212,
      "learning_rate": 0.0,
      "loss": 1.1879,
      "step": 196
    },
    {
      "epoch": 1.9644670050761421,
      "eval_loss": 1.2216618061065674,
      "eval_runtime": 58.8162,
      "eval_samples_per_second": 10.031,
      "eval_steps_per_second": 1.258,
      "step": 196
    }
  ],
  "logging_steps": 1,
  "max_steps": 196,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 98,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0307946378260644e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}