{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 421,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023788284269997025,
      "grad_norm": 1.0281301736831665,
      "learning_rate": 0.0,
      "loss": 2.0766,
      "step": 1
    },
    {
      "epoch": 0.004757656853999405,
      "grad_norm": 1.2767698764801025,
      "learning_rate": 1e-05,
      "loss": 2.3525,
      "step": 2
    },
    {
      "epoch": 0.007136485280999108,
      "grad_norm": 1.3647927045822144,
      "learning_rate": 2e-05,
      "loss": 2.4261,
      "step": 3
    },
    {
      "epoch": 0.00951531370799881,
      "grad_norm": 0.8589039444923401,
      "learning_rate": 3e-05,
      "loss": 1.7271,
      "step": 4
    },
    {
      "epoch": 0.011894142134998514,
      "grad_norm": 1.1814510822296143,
      "learning_rate": 4e-05,
      "loss": 2.1379,
      "step": 5
    },
    {
      "epoch": 0.014272970561998216,
      "grad_norm": 1.012987732887268,
      "learning_rate": 5e-05,
      "loss": 1.8598,
      "step": 6
    },
    {
      "epoch": 0.016651798988997917,
      "grad_norm": 1.052037239074707,
      "learning_rate": 6e-05,
      "loss": 1.9315,
      "step": 7
    },
    {
      "epoch": 0.01903062741599762,
      "grad_norm": 0.8621532320976257,
      "learning_rate": 7e-05,
      "loss": 1.7205,
      "step": 8
    },
    {
      "epoch": 0.021409455842997322,
      "grad_norm": 0.7924615740776062,
      "learning_rate": 8e-05,
      "loss": 1.589,
      "step": 9
    },
    {
      "epoch": 0.023788284269997028,
      "grad_norm": 0.6322035789489746,
      "learning_rate": 9e-05,
      "loss": 1.3374,
      "step": 10
    },
    {
      "epoch": 0.02616711269699673,
      "grad_norm": 0.7854194641113281,
      "learning_rate": 0.0001,
      "loss": 1.4292,
      "step": 11
    },
    {
      "epoch": 0.028545941123996433,
      "grad_norm": 0.6697576642036438,
      "learning_rate": 9.975669099756692e-05,
      "loss": 1.206,
      "step": 12
    },
    {
      "epoch": 0.030924769550996135,
      "grad_norm": 0.7266756296157837,
      "learning_rate": 9.951338199513383e-05,
      "loss": 1.2737,
      "step": 13
    },
    {
      "epoch": 0.033303597977995834,
      "grad_norm": 0.7196414470672607,
      "learning_rate": 9.927007299270074e-05,
      "loss": 1.2023,
      "step": 14
    },
    {
      "epoch": 0.03568242640499554,
      "grad_norm": 0.7868577241897583,
      "learning_rate": 9.902676399026765e-05,
      "loss": 1.1486,
      "step": 15
    },
    {
      "epoch": 0.03806125483199524,
      "grad_norm": 0.7759497761726379,
      "learning_rate": 9.878345498783455e-05,
      "loss": 1.112,
      "step": 16
    },
    {
      "epoch": 0.040440083258994945,
      "grad_norm": 0.7133831977844238,
      "learning_rate": 9.854014598540146e-05,
      "loss": 1.0158,
      "step": 17
    },
    {
      "epoch": 0.042818911685994644,
      "grad_norm": 0.644658088684082,
      "learning_rate": 9.829683698296837e-05,
      "loss": 0.9656,
      "step": 18
    },
    {
      "epoch": 0.04519774011299435,
      "grad_norm": 0.6295652985572815,
      "learning_rate": 9.805352798053529e-05,
      "loss": 0.9295,
      "step": 19
    },
    {
      "epoch": 0.047576568539994056,
      "grad_norm": 0.6460481882095337,
      "learning_rate": 9.78102189781022e-05,
      "loss": 0.9851,
      "step": 20
    },
    {
      "epoch": 0.049955396966993755,
      "grad_norm": 0.5485146045684814,
      "learning_rate": 9.756690997566911e-05,
      "loss": 0.864,
      "step": 21
    },
    {
      "epoch": 0.05233422539399346,
      "grad_norm": 0.6552495360374451,
      "learning_rate": 9.732360097323602e-05,
      "loss": 0.7903,
      "step": 22
    },
    {
      "epoch": 0.05471305382099316,
      "grad_norm": 0.5481061935424805,
      "learning_rate": 9.708029197080293e-05,
      "loss": 0.843,
      "step": 23
    },
    {
      "epoch": 0.057091882247992866,
      "grad_norm": 0.6262676119804382,
      "learning_rate": 9.683698296836983e-05,
      "loss": 0.9421,
      "step": 24
    },
    {
      "epoch": 0.059470710674992565,
      "grad_norm": 0.5493852496147156,
      "learning_rate": 9.659367396593674e-05,
      "loss": 0.9045,
      "step": 25
    },
    {
      "epoch": 0.06184953910199227,
      "grad_norm": 0.542617678642273,
      "learning_rate": 9.635036496350366e-05,
      "loss": 0.8028,
      "step": 26
    },
    {
      "epoch": 0.06422836752899197,
      "grad_norm": 0.4842965602874756,
      "learning_rate": 9.610705596107057e-05,
      "loss": 0.716,
      "step": 27
    },
    {
      "epoch": 0.06660719595599167,
      "grad_norm": 0.5457621216773987,
      "learning_rate": 9.586374695863748e-05,
      "loss": 0.7069,
      "step": 28
    },
    {
      "epoch": 0.06898602438299138,
      "grad_norm": 0.5163421034812927,
      "learning_rate": 9.562043795620439e-05,
      "loss": 0.6999,
      "step": 29
    },
    {
      "epoch": 0.07136485280999108,
      "grad_norm": 0.4519389569759369,
      "learning_rate": 9.537712895377129e-05,
      "loss": 0.6219,
      "step": 30
    },
    {
      "epoch": 0.07374368123699078,
      "grad_norm": 0.5117298364639282,
      "learning_rate": 9.51338199513382e-05,
      "loss": 0.597,
      "step": 31
    },
    {
      "epoch": 0.07612250966399048,
      "grad_norm": 0.5518686771392822,
      "learning_rate": 9.489051094890511e-05,
      "loss": 0.6789,
      "step": 32
    },
    {
      "epoch": 0.07850133809099019,
      "grad_norm": 0.5353817939758301,
      "learning_rate": 9.464720194647201e-05,
      "loss": 0.6493,
      "step": 33
    },
    {
      "epoch": 0.08088016651798989,
      "grad_norm": 0.48304057121276855,
      "learning_rate": 9.440389294403893e-05,
      "loss": 0.5638,
      "step": 34
    },
    {
      "epoch": 0.08325899494498959,
      "grad_norm": 0.42356157302856445,
      "learning_rate": 9.416058394160584e-05,
      "loss": 0.5589,
      "step": 35
    },
    {
      "epoch": 0.08563782337198929,
      "grad_norm": 0.39856433868408203,
      "learning_rate": 9.391727493917275e-05,
      "loss": 0.5208,
      "step": 36
    },
    {
      "epoch": 0.088016651798989,
      "grad_norm": 0.4774276912212372,
      "learning_rate": 9.367396593673966e-05,
      "loss": 0.6367,
      "step": 37
    },
    {
      "epoch": 0.0903954802259887,
      "grad_norm": 0.48944222927093506,
      "learning_rate": 9.343065693430657e-05,
      "loss": 0.6261,
      "step": 38
    },
    {
      "epoch": 0.0927743086529884,
      "grad_norm": 0.4067060053348541,
      "learning_rate": 9.318734793187348e-05,
      "loss": 0.5512,
      "step": 39
    },
    {
      "epoch": 0.09515313707998811,
      "grad_norm": 0.4157446622848511,
      "learning_rate": 9.29440389294404e-05,
      "loss": 0.5823,
      "step": 40
    },
    {
      "epoch": 0.09753196550698781,
      "grad_norm": 0.43023228645324707,
      "learning_rate": 9.27007299270073e-05,
      "loss": 0.5499,
      "step": 41
    },
    {
      "epoch": 0.09991079393398751,
      "grad_norm": 0.40139999985694885,
      "learning_rate": 9.245742092457421e-05,
      "loss": 0.5808,
      "step": 42
    },
    {
      "epoch": 0.10228962236098721,
      "grad_norm": 0.4564228653907776,
      "learning_rate": 9.221411192214112e-05,
      "loss": 0.652,
      "step": 43
    },
    {
      "epoch": 0.10466845078798692,
      "grad_norm": 0.40338802337646484,
      "learning_rate": 9.197080291970803e-05,
      "loss": 0.5065,
      "step": 44
    },
    {
      "epoch": 0.10704727921498662,
      "grad_norm": 0.5054526925086975,
      "learning_rate": 9.172749391727494e-05,
      "loss": 0.6194,
      "step": 45
    },
    {
      "epoch": 0.10942610764198632,
      "grad_norm": 0.44123998284339905,
      "learning_rate": 9.148418491484186e-05,
      "loss": 0.5657,
      "step": 46
    },
    {
      "epoch": 0.11180493606898602,
      "grad_norm": 0.4445621371269226,
      "learning_rate": 9.124087591240877e-05,
      "loss": 0.5808,
      "step": 47
    },
    {
      "epoch": 0.11418376449598573,
      "grad_norm": 0.3913380801677704,
      "learning_rate": 9.099756690997568e-05,
      "loss": 0.5816,
      "step": 48
    },
    {
      "epoch": 0.11656259292298543,
      "grad_norm": 0.43966594338417053,
      "learning_rate": 9.075425790754258e-05,
      "loss": 0.4836,
      "step": 49
    },
    {
      "epoch": 0.11894142134998513,
      "grad_norm": 0.4385397434234619,
      "learning_rate": 9.051094890510949e-05,
      "loss": 0.5962,
      "step": 50
    },
    {
      "epoch": 0.12132024977698483,
      "grad_norm": 0.41545379161834717,
      "learning_rate": 9.02676399026764e-05,
      "loss": 0.5748,
      "step": 51
    },
    {
      "epoch": 0.12369907820398454,
      "grad_norm": 0.3504558801651001,
      "learning_rate": 9.002433090024331e-05,
      "loss": 0.5202,
      "step": 52
    },
    {
      "epoch": 0.12607790663098423,
      "grad_norm": 0.44601067900657654,
      "learning_rate": 8.978102189781023e-05,
      "loss": 0.5451,
      "step": 53
    },
    {
      "epoch": 0.12845673505798394,
      "grad_norm": 0.3965899646282196,
      "learning_rate": 8.953771289537714e-05,
      "loss": 0.5578,
      "step": 54
    },
    {
      "epoch": 0.13083556348498365,
      "grad_norm": 0.44455817341804504,
      "learning_rate": 8.929440389294405e-05,
      "loss": 0.4968,
      "step": 55
    },
    {
      "epoch": 0.13321439191198334,
      "grad_norm": 0.45583397150039673,
      "learning_rate": 8.905109489051096e-05,
      "loss": 0.598,
      "step": 56
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 0.46639132499694824,
      "learning_rate": 8.880778588807786e-05,
      "loss": 0.5857,
      "step": 57
    },
    {
      "epoch": 0.13797204876598276,
      "grad_norm": 0.4358392655849457,
      "learning_rate": 8.856447688564477e-05,
      "loss": 0.5299,
      "step": 58
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 0.4803287088871002,
      "learning_rate": 8.832116788321168e-05,
      "loss": 0.5082,
      "step": 59
    },
    {
      "epoch": 0.14272970561998216,
      "grad_norm": 0.41488590836524963,
      "learning_rate": 8.80778588807786e-05,
      "loss": 0.5223,
      "step": 60
    },
    {
      "epoch": 0.14510853404698187,
      "grad_norm": 0.46010011434555054,
      "learning_rate": 8.783454987834551e-05,
      "loss": 0.5125,
      "step": 61
    },
    {
      "epoch": 0.14748736247398156,
      "grad_norm": 0.3907822370529175,
      "learning_rate": 8.759124087591242e-05,
      "loss": 0.5121,
      "step": 62
    },
    {
      "epoch": 0.14986619090098127,
      "grad_norm": 0.4548039138317108,
      "learning_rate": 8.734793187347933e-05,
      "loss": 0.577,
      "step": 63
    },
    {
      "epoch": 0.15224501932798096,
      "grad_norm": 0.3938556909561157,
      "learning_rate": 8.710462287104624e-05,
      "loss": 0.4726,
      "step": 64
    },
    {
      "epoch": 0.15462384775498067,
      "grad_norm": 0.46850043535232544,
      "learning_rate": 8.686131386861314e-05,
      "loss": 0.5203,
      "step": 65
    },
    {
      "epoch": 0.15700267618198038,
      "grad_norm": 0.43241533637046814,
      "learning_rate": 8.661800486618005e-05,
      "loss": 0.4683,
      "step": 66
    },
    {
      "epoch": 0.15938150460898007,
      "grad_norm": 0.43365252017974854,
      "learning_rate": 8.637469586374697e-05,
      "loss": 0.5508,
      "step": 67
    },
    {
      "epoch": 0.16176033303597978,
      "grad_norm": 0.4271024763584137,
      "learning_rate": 8.613138686131386e-05,
      "loss": 0.4992,
      "step": 68
    },
    {
      "epoch": 0.1641391614629795,
      "grad_norm": 0.4089069366455078,
      "learning_rate": 8.588807785888078e-05,
      "loss": 0.4575,
      "step": 69
    },
    {
      "epoch": 0.16651798988997918,
      "grad_norm": 0.43635204434394836,
      "learning_rate": 8.564476885644769e-05,
      "loss": 0.5513,
      "step": 70
    },
    {
      "epoch": 0.1688968183169789,
      "grad_norm": 0.4246712625026703,
      "learning_rate": 8.54014598540146e-05,
      "loss": 0.4759,
      "step": 71
    },
    {
      "epoch": 0.17127564674397858,
      "grad_norm": 0.463638573884964,
      "learning_rate": 8.515815085158151e-05,
      "loss": 0.5323,
      "step": 72
    },
    {
      "epoch": 0.1736544751709783,
      "grad_norm": 0.4437566101551056,
      "learning_rate": 8.491484184914842e-05,
      "loss": 0.5446,
      "step": 73
    },
    {
      "epoch": 0.176033303597978,
      "grad_norm": 0.4280001223087311,
      "learning_rate": 8.467153284671534e-05,
      "loss": 0.5092,
      "step": 74
    },
    {
      "epoch": 0.1784121320249777,
      "grad_norm": 0.4512069523334503,
      "learning_rate": 8.442822384428223e-05,
      "loss": 0.5002,
      "step": 75
    },
    {
      "epoch": 0.1807909604519774,
      "grad_norm": 0.39247390627861023,
      "learning_rate": 8.418491484184915e-05,
      "loss": 0.4522,
      "step": 76
    },
    {
      "epoch": 0.1831697888789771,
      "grad_norm": 0.531852662563324,
      "learning_rate": 8.394160583941606e-05,
      "loss": 0.5507,
      "step": 77
    },
    {
      "epoch": 0.1855486173059768,
      "grad_norm": 0.49727141857147217,
      "learning_rate": 8.369829683698297e-05,
      "loss": 0.519,
      "step": 78
    },
    {
      "epoch": 0.1879274457329765,
      "grad_norm": 0.46292659640312195,
      "learning_rate": 8.345498783454988e-05,
      "loss": 0.5271,
      "step": 79
    },
    {
      "epoch": 0.19030627415997622,
      "grad_norm": 0.4514133036136627,
      "learning_rate": 8.32116788321168e-05,
      "loss": 0.5499,
      "step": 80
    },
    {
      "epoch": 0.1926851025869759,
      "grad_norm": 0.42186304926872253,
      "learning_rate": 8.29683698296837e-05,
      "loss": 0.541,
      "step": 81
    },
    {
      "epoch": 0.19506393101397562,
      "grad_norm": 0.4527208209037781,
      "learning_rate": 8.272506082725062e-05,
      "loss": 0.482,
      "step": 82
    },
    {
      "epoch": 0.1974427594409753,
      "grad_norm": 0.4818190634250641,
      "learning_rate": 8.248175182481752e-05,
      "loss": 0.5627,
      "step": 83
    },
    {
      "epoch": 0.19982158786797502,
      "grad_norm": 0.44998934864997864,
      "learning_rate": 8.223844282238443e-05,
      "loss": 0.5169,
      "step": 84
    },
    {
      "epoch": 0.20220041629497473,
      "grad_norm": 0.42806658148765564,
      "learning_rate": 8.199513381995134e-05,
      "loss": 0.5613,
      "step": 85
    },
    {
      "epoch": 0.20457924472197442,
      "grad_norm": 0.4187542796134949,
      "learning_rate": 8.175182481751825e-05,
      "loss": 0.4584,
      "step": 86
    },
    {
      "epoch": 0.20695807314897413,
      "grad_norm": 0.5182843804359436,
      "learning_rate": 8.150851581508516e-05,
      "loss": 0.5253,
      "step": 87
    },
    {
      "epoch": 0.20933690157597384,
      "grad_norm": 0.4145914614200592,
      "learning_rate": 8.126520681265208e-05,
      "loss": 0.4828,
      "step": 88
    },
    {
      "epoch": 0.21171573000297353,
      "grad_norm": 0.46647554636001587,
      "learning_rate": 8.102189781021899e-05,
      "loss": 0.4496,
      "step": 89
    },
    {
      "epoch": 0.21409455842997324,
      "grad_norm": 0.4022408723831177,
      "learning_rate": 8.07785888077859e-05,
      "loss": 0.4329,
      "step": 90
    },
    {
      "epoch": 0.21647338685697295,
      "grad_norm": 0.4754613935947418,
      "learning_rate": 8.05352798053528e-05,
      "loss": 0.5314,
      "step": 91
    },
    {
      "epoch": 0.21885221528397264,
      "grad_norm": 0.41736510396003723,
      "learning_rate": 8.029197080291971e-05,
      "loss": 0.4906,
      "step": 92
    },
    {
      "epoch": 0.22123104371097235,
      "grad_norm": 0.4199044406414032,
      "learning_rate": 8.004866180048662e-05,
      "loss": 0.495,
      "step": 93
    },
    {
      "epoch": 0.22360987213797204,
      "grad_norm": 0.4374317526817322,
      "learning_rate": 7.980535279805353e-05,
      "loss": 0.533,
      "step": 94
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 0.4060494899749756,
      "learning_rate": 7.956204379562045e-05,
      "loss": 0.4711,
      "step": 95
    },
    {
      "epoch": 0.22836752899197146,
      "grad_norm": 0.49371036887168884,
      "learning_rate": 7.931873479318736e-05,
      "loss": 0.5417,
      "step": 96
    },
    {
      "epoch": 0.23074635741897115,
      "grad_norm": 0.4903344511985779,
      "learning_rate": 7.907542579075427e-05,
      "loss": 0.4595,
      "step": 97
    },
    {
      "epoch": 0.23312518584597086,
      "grad_norm": 0.4055982530117035,
      "learning_rate": 7.883211678832118e-05,
      "loss": 0.4926,
      "step": 98
    },
    {
      "epoch": 0.23550401427297057,
      "grad_norm": 0.4552580416202545,
      "learning_rate": 7.858880778588808e-05,
      "loss": 0.5644,
      "step": 99
    },
    {
      "epoch": 0.23788284269997026,
      "grad_norm": 0.4261854588985443,
      "learning_rate": 7.834549878345499e-05,
      "loss": 0.4915,
      "step": 100
    },
    {
      "epoch": 0.23788284269997026,
      "eval_loss": 0.48822253942489624,
      "eval_runtime": 27.0528,
      "eval_samples_per_second": 27.65,
      "eval_steps_per_second": 13.825,
      "step": 100
    },
    {
      "epoch": 0.24026167112696997,
      "grad_norm": 0.48629841208457947,
      "learning_rate": 7.81021897810219e-05,
      "loss": 0.4824,
      "step": 101
    },
    {
      "epoch": 0.24264049955396966,
      "grad_norm": 0.4699622094631195,
      "learning_rate": 7.785888077858882e-05,
      "loss": 0.4642,
      "step": 102
    },
    {
      "epoch": 0.24501932798096937,
      "grad_norm": 0.39009714126586914,
      "learning_rate": 7.761557177615573e-05,
      "loss": 0.4614,
      "step": 103
    },
    {
      "epoch": 0.24739815640796908,
      "grad_norm": 0.4852162003517151,
      "learning_rate": 7.737226277372264e-05,
      "loss": 0.5112,
      "step": 104
    },
    {
      "epoch": 0.24977698483496877,
      "grad_norm": 0.5088614821434021,
      "learning_rate": 7.712895377128954e-05,
      "loss": 0.4914,
      "step": 105
    },
    {
      "epoch": 0.25215581326196845,
      "grad_norm": 0.4846271276473999,
      "learning_rate": 7.688564476885645e-05,
      "loss": 0.4832,
      "step": 106
    },
    {
      "epoch": 0.25453464168896817,
      "grad_norm": 0.48459744453430176,
      "learning_rate": 7.664233576642336e-05,
      "loss": 0.5386,
      "step": 107
    },
    {
      "epoch": 0.2569134701159679,
      "grad_norm": 0.47507190704345703,
      "learning_rate": 7.639902676399027e-05,
      "loss": 0.4593,
      "step": 108
    },
    {
      "epoch": 0.2592922985429676,
      "grad_norm": 0.46605178713798523,
      "learning_rate": 7.615571776155717e-05,
      "loss": 0.5265,
      "step": 109
    },
    {
      "epoch": 0.2616711269699673,
      "grad_norm": 0.4616071283817291,
      "learning_rate": 7.591240875912408e-05,
      "loss": 0.4323,
      "step": 110
    },
    {
      "epoch": 0.264049955396967,
      "grad_norm": 0.5419961214065552,
      "learning_rate": 7.5669099756691e-05,
      "loss": 0.5403,
      "step": 111
    },
    {
      "epoch": 0.2664287838239667,
      "grad_norm": 0.4992631673812866,
      "learning_rate": 7.542579075425791e-05,
      "loss": 0.4558,
      "step": 112
    },
    {
      "epoch": 0.2688076122509664,
      "grad_norm": 0.5071640610694885,
      "learning_rate": 7.518248175182482e-05,
      "loss": 0.5385,
      "step": 113
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 0.5004437565803528,
      "learning_rate": 7.493917274939173e-05,
      "loss": 0.5106,
      "step": 114
    },
    {
      "epoch": 0.2735652691049658,
      "grad_norm": 0.4706288278102875,
      "learning_rate": 7.469586374695864e-05,
      "loss": 0.5333,
      "step": 115
    },
    {
      "epoch": 0.2759440975319655,
      "grad_norm": 0.5518192052841187,
      "learning_rate": 7.445255474452556e-05,
      "loss": 0.5945,
      "step": 116
    },
    {
      "epoch": 0.2783229259589652,
      "grad_norm": 0.4758547246456146,
      "learning_rate": 7.420924574209245e-05,
      "loss": 0.533,
      "step": 117
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 0.4491472840309143,
      "learning_rate": 7.396593673965937e-05,
      "loss": 0.4213,
      "step": 118
    },
    {
      "epoch": 0.2830805828129646,
      "grad_norm": 0.4540884494781494,
      "learning_rate": 7.372262773722628e-05,
      "loss": 0.4747,
      "step": 119
    },
    {
      "epoch": 0.2854594112399643,
      "grad_norm": 0.4252176880836487,
      "learning_rate": 7.347931873479319e-05,
      "loss": 0.4639,
      "step": 120
    },
    {
      "epoch": 0.28783823966696404,
      "grad_norm": 0.4695313274860382,
      "learning_rate": 7.32360097323601e-05,
      "loss": 0.5563,
      "step": 121
    },
    {
      "epoch": 0.29021706809396375,
      "grad_norm": 0.49951449036598206,
      "learning_rate": 7.299270072992701e-05,
      "loss": 0.4517,
      "step": 122
    },
    {
      "epoch": 0.2925958965209634,
      "grad_norm": 0.4763878285884857,
      "learning_rate": 7.274939172749393e-05,
      "loss": 0.5223,
      "step": 123
    },
    {
      "epoch": 0.2949747249479631,
      "grad_norm": 0.49518251419067383,
      "learning_rate": 7.250608272506084e-05,
      "loss": 0.5832,
      "step": 124
    },
    {
      "epoch": 0.29735355337496283,
      "grad_norm": 0.4721708595752716,
      "learning_rate": 7.226277372262774e-05,
      "loss": 0.5259,
      "step": 125
    },
    {
      "epoch": 0.29973238180196254,
      "grad_norm": 0.4356157183647156,
      "learning_rate": 7.201946472019465e-05,
      "loss": 0.408,
      "step": 126
    },
    {
      "epoch": 0.30211121022896226,
      "grad_norm": 0.4771776795387268,
      "learning_rate": 7.177615571776156e-05,
      "loss": 0.4909,
      "step": 127
    },
    {
      "epoch": 0.3044900386559619,
      "grad_norm": 0.5367064476013184,
      "learning_rate": 7.153284671532847e-05,
      "loss": 0.556,
      "step": 128
    },
    {
      "epoch": 0.3068688670829616,
      "grad_norm": 0.43037423491477966,
      "learning_rate": 7.128953771289538e-05,
      "loss": 0.3805,
      "step": 129
    },
    {
      "epoch": 0.30924769550996134,
      "grad_norm": 0.4576215445995331,
      "learning_rate": 7.10462287104623e-05,
      "loss": 0.437,
      "step": 130
    },
    {
      "epoch": 0.31162652393696105,
      "grad_norm": 0.46385103464126587,
      "learning_rate": 7.080291970802921e-05,
      "loss": 0.4561,
      "step": 131
    },
    {
      "epoch": 0.31400535236396077,
      "grad_norm": 0.4961807131767273,
      "learning_rate": 7.055961070559612e-05,
      "loss": 0.3691,
      "step": 132
    },
    {
      "epoch": 0.3163841807909605,
      "grad_norm": 0.5330118536949158,
      "learning_rate": 7.031630170316302e-05,
      "loss": 0.5341,
      "step": 133
    },
    {
      "epoch": 0.31876300921796014,
      "grad_norm": 0.4410998225212097,
      "learning_rate": 7.007299270072993e-05,
      "loss": 0.4867,
      "step": 134
    },
    {
      "epoch": 0.32114183764495985,
      "grad_norm": 0.4794428050518036,
      "learning_rate": 6.982968369829684e-05,
      "loss": 0.4818,
      "step": 135
    },
    {
      "epoch": 0.32352066607195956,
      "grad_norm": 0.49389636516571045,
      "learning_rate": 6.958637469586375e-05,
      "loss": 0.5156,
      "step": 136
    },
    {
      "epoch": 0.3258994944989593,
      "grad_norm": 0.49501174688339233,
      "learning_rate": 6.934306569343067e-05,
      "loss": 0.5122,
      "step": 137
    },
    {
      "epoch": 0.328278322925959,
      "grad_norm": 0.4967164695262909,
      "learning_rate": 6.909975669099758e-05,
      "loss": 0.4853,
      "step": 138
    },
    {
      "epoch": 0.33065715135295864,
      "grad_norm": 0.5276123881340027,
      "learning_rate": 6.885644768856449e-05,
      "loss": 0.4703,
      "step": 139
    },
    {
      "epoch": 0.33303597977995836,
      "grad_norm": 0.5336246490478516,
      "learning_rate": 6.86131386861314e-05,
      "loss": 0.4652,
      "step": 140
    },
    {
      "epoch": 0.33541480820695807,
      "grad_norm": 0.3898225426673889,
      "learning_rate": 6.83698296836983e-05,
      "loss": 0.3983,
      "step": 141
    },
    {
      "epoch": 0.3377936366339578,
      "grad_norm": 0.4705723226070404,
      "learning_rate": 6.81265206812652e-05,
      "loss": 0.4646,
      "step": 142
    },
    {
      "epoch": 0.3401724650609575,
      "grad_norm": 0.4973605275154114,
      "learning_rate": 6.788321167883211e-05,
      "loss": 0.4848,
      "step": 143
    },
    {
      "epoch": 0.34255129348795715,
      "grad_norm": 0.5203383564949036,
      "learning_rate": 6.763990267639902e-05,
      "loss": 0.4992,
      "step": 144
    },
    {
      "epoch": 0.34493012191495687,
      "grad_norm": 0.47000083327293396,
      "learning_rate": 6.739659367396593e-05,
      "loss": 0.4665,
      "step": 145
    },
    {
      "epoch": 0.3473089503419566,
      "grad_norm": 0.4483359456062317,
      "learning_rate": 6.715328467153285e-05,
      "loss": 0.4553,
      "step": 146
    },
    {
      "epoch": 0.3496877787689563,
      "grad_norm": 0.4584805965423584,
      "learning_rate": 6.690997566909976e-05,
      "loss": 0.4945,
      "step": 147
    },
    {
      "epoch": 0.352066607195956,
      "grad_norm": 0.5037974119186401,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.4723,
      "step": 148
    },
    {
      "epoch": 0.3544454356229557,
      "grad_norm": 0.4981141984462738,
      "learning_rate": 6.642335766423358e-05,
      "loss": 0.5417,
      "step": 149
    },
    {
      "epoch": 0.3568242640499554,
      "grad_norm": 0.49627479910850525,
      "learning_rate": 6.618004866180048e-05,
      "loss": 0.4569,
      "step": 150
    },
    {
      "epoch": 0.3592030924769551,
      "grad_norm": 0.49889135360717773,
      "learning_rate": 6.593673965936739e-05,
      "loss": 0.5391,
      "step": 151
    },
    {
      "epoch": 0.3615819209039548,
      "grad_norm": 0.5222321152687073,
      "learning_rate": 6.56934306569343e-05,
      "loss": 0.4482,
      "step": 152
    },
    {
      "epoch": 0.3639607493309545,
      "grad_norm": 0.48798415064811707,
      "learning_rate": 6.545012165450122e-05,
      "loss": 0.5148,
      "step": 153
    },
    {
      "epoch": 0.3663395777579542,
      "grad_norm": 0.4458797574043274,
      "learning_rate": 6.520681265206813e-05,
      "loss": 0.4516,
      "step": 154
    },
    {
      "epoch": 0.3687184061849539,
      "grad_norm": 0.4997321665287018,
      "learning_rate": 6.496350364963504e-05,
      "loss": 0.4769,
      "step": 155
    },
    {
      "epoch": 0.3710972346119536,
      "grad_norm": 0.5233137011528015,
      "learning_rate": 6.472019464720195e-05,
      "loss": 0.5108,
      "step": 156
    },
    {
      "epoch": 0.3734760630389533,
      "grad_norm": 0.5136488676071167,
      "learning_rate": 6.447688564476886e-05,
      "loss": 0.4755,
      "step": 157
    },
    {
      "epoch": 0.375854891465953,
      "grad_norm": 0.4736205041408539,
      "learning_rate": 6.423357664233576e-05,
      "loss": 0.3712,
      "step": 158
    },
    {
      "epoch": 0.37823371989295274,
      "grad_norm": 0.43539518117904663,
      "learning_rate": 6.399026763990267e-05,
      "loss": 0.416,
      "step": 159
    },
    {
      "epoch": 0.38061254831995245,
      "grad_norm": 0.44481900334358215,
      "learning_rate": 6.374695863746959e-05,
      "loss": 0.4628,
      "step": 160
    },
    {
      "epoch": 0.3829913767469521,
      "grad_norm": 0.45447418093681335,
      "learning_rate": 6.35036496350365e-05,
      "loss": 0.4273,
      "step": 161
    },
    {
      "epoch": 0.3853702051739518,
      "grad_norm": 0.43469730019569397,
      "learning_rate": 6.326034063260341e-05,
      "loss": 0.4584,
      "step": 162
    },
    {
      "epoch": 0.38774903360095153,
      "grad_norm": 0.4581772983074188,
      "learning_rate": 6.301703163017032e-05,
      "loss": 0.4379,
      "step": 163
    },
    {
      "epoch": 0.39012786202795124,
      "grad_norm": 0.42583826184272766,
      "learning_rate": 6.277372262773723e-05,
      "loss": 0.4336,
      "step": 164
    },
    {
      "epoch": 0.39250669045495096,
      "grad_norm": 0.5775184631347656,
      "learning_rate": 6.253041362530415e-05,
      "loss": 0.4901,
      "step": 165
    },
    {
      "epoch": 0.3948855188819506,
      "grad_norm": 0.4797421991825104,
      "learning_rate": 6.228710462287104e-05,
      "loss": 0.4319,
      "step": 166
    },
    {
      "epoch": 0.3972643473089503,
      "grad_norm": 0.5240707397460938,
      "learning_rate": 6.204379562043796e-05,
      "loss": 0.4638,
      "step": 167
    },
    {
      "epoch": 0.39964317573595004,
      "grad_norm": 0.5036562085151672,
      "learning_rate": 6.180048661800487e-05,
      "loss": 0.5198,
      "step": 168
    },
    {
      "epoch": 0.40202200416294975,
      "grad_norm": 0.5376377105712891,
      "learning_rate": 6.155717761557178e-05,
      "loss": 0.4564,
      "step": 169
    },
    {
      "epoch": 0.40440083258994947,
      "grad_norm": 0.5044119954109192,
      "learning_rate": 6.131386861313869e-05,
      "loss": 0.4269,
      "step": 170
    },
    {
      "epoch": 0.4067796610169492,
      "grad_norm": 0.5195197463035583,
      "learning_rate": 6.10705596107056e-05,
      "loss": 0.4866,
      "step": 171
    },
    {
      "epoch": 0.40915848944394884,
      "grad_norm": 0.4676225483417511,
      "learning_rate": 6.082725060827251e-05,
      "loss": 0.4509,
      "step": 172
    },
    {
      "epoch": 0.41153731787094855,
      "grad_norm": 0.4422922134399414,
      "learning_rate": 6.058394160583942e-05,
      "loss": 0.4498,
      "step": 173
    },
    {
      "epoch": 0.41391614629794826,
      "grad_norm": 0.5001342296600342,
      "learning_rate": 6.034063260340633e-05,
      "loss": 0.4743,
      "step": 174
    },
    {
      "epoch": 0.416294974724948,
      "grad_norm": 0.4759523272514343,
      "learning_rate": 6.0097323600973245e-05,
      "loss": 0.4514,
      "step": 175
    },
    {
      "epoch": 0.4186738031519477,
      "grad_norm": 0.46963706612586975,
      "learning_rate": 5.985401459854016e-05,
      "loss": 0.4776,
      "step": 176
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.49028345942497253,
      "learning_rate": 5.961070559610706e-05,
      "loss": 0.4632,
      "step": 177
    },
    {
      "epoch": 0.42343146000594706,
      "grad_norm": 0.4388274848461151,
      "learning_rate": 5.9367396593673974e-05,
      "loss": 0.4822,
      "step": 178
    },
    {
      "epoch": 0.42581028843294677,
      "grad_norm": 0.4349250793457031,
      "learning_rate": 5.9124087591240886e-05,
      "loss": 0.4468,
      "step": 179
    },
    {
      "epoch": 0.4281891168599465,
      "grad_norm": 0.4884635806083679,
      "learning_rate": 5.8880778588807784e-05,
      "loss": 0.4724,
      "step": 180
    },
    {
      "epoch": 0.4305679452869462,
      "grad_norm": 0.4598194360733032,
      "learning_rate": 5.8637469586374696e-05,
      "loss": 0.4762,
      "step": 181
    },
    {
      "epoch": 0.4329467737139459,
      "grad_norm": 0.5073289275169373,
      "learning_rate": 5.83941605839416e-05,
      "loss": 0.4732,
      "step": 182
    },
    {
      "epoch": 0.43532560214094557,
      "grad_norm": 0.4630277752876282,
      "learning_rate": 5.815085158150851e-05,
      "loss": 0.4301,
      "step": 183
    },
    {
      "epoch": 0.4377044305679453,
      "grad_norm": 0.42805591225624084,
      "learning_rate": 5.7907542579075425e-05,
      "loss": 0.47,
      "step": 184
    },
    {
      "epoch": 0.440083258994945,
      "grad_norm": 0.6053451299667358,
      "learning_rate": 5.766423357664234e-05,
      "loss": 0.4977,
      "step": 185
    },
    {
      "epoch": 0.4424620874219447,
      "grad_norm": 0.530331552028656,
      "learning_rate": 5.742092457420924e-05,
      "loss": 0.4492,
      "step": 186
    },
    {
      "epoch": 0.4448409158489444,
      "grad_norm": 0.46791204810142517,
      "learning_rate": 5.7177615571776154e-05,
      "loss": 0.4402,
      "step": 187
    },
    {
      "epoch": 0.4472197442759441,
      "grad_norm": 0.543755829334259,
      "learning_rate": 5.6934306569343066e-05,
      "loss": 0.5958,
      "step": 188
    },
    {
      "epoch": 0.4495985727029438,
      "grad_norm": 0.4579405188560486,
      "learning_rate": 5.669099756690998e-05,
      "loss": 0.4145,
      "step": 189
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 0.5464953184127808,
      "learning_rate": 5.644768856447688e-05,
      "loss": 0.4869,
      "step": 190
    },
    {
      "epoch": 0.4543562295569432,
      "grad_norm": 0.4730067551136017,
      "learning_rate": 5.6204379562043795e-05,
      "loss": 0.4432,
      "step": 191
    },
    {
      "epoch": 0.4567350579839429,
      "grad_norm": 0.4859981834888458,
      "learning_rate": 5.596107055961071e-05,
      "loss": 0.4376,
      "step": 192
    },
    {
      "epoch": 0.4591138864109426,
      "grad_norm": 0.4743499159812927,
      "learning_rate": 5.571776155717762e-05,
      "loss": 0.4542,
      "step": 193
    },
    {
      "epoch": 0.4614927148379423,
      "grad_norm": 0.5267781019210815,
      "learning_rate": 5.5474452554744524e-05,
      "loss": 0.4684,
      "step": 194
    },
    {
      "epoch": 0.463871543264942,
      "grad_norm": 0.5235748291015625,
      "learning_rate": 5.5231143552311436e-05,
      "loss": 0.4412,
      "step": 195
    },
    {
      "epoch": 0.4662503716919417,
      "grad_norm": 0.4266457259654999,
      "learning_rate": 5.498783454987835e-05,
      "loss": 0.3855,
      "step": 196
    },
    {
      "epoch": 0.46862920011894144,
      "grad_norm": 0.49032875895500183,
      "learning_rate": 5.474452554744526e-05,
      "loss": 0.4413,
      "step": 197
    },
    {
      "epoch": 0.47100802854594115,
      "grad_norm": 0.5913426280021667,
      "learning_rate": 5.4501216545012165e-05,
      "loss": 0.5653,
      "step": 198
    },
    {
      "epoch": 0.4733868569729408,
      "grad_norm": 0.5137138366699219,
      "learning_rate": 5.425790754257908e-05,
      "loss": 0.4835,
      "step": 199
    },
    {
      "epoch": 0.4757656853999405,
      "grad_norm": 0.43370646238327026,
      "learning_rate": 5.401459854014599e-05,
      "loss": 0.41,
      "step": 200
    },
    {
      "epoch": 0.4757656853999405,
      "eval_loss": 0.4463058412075043,
      "eval_runtime": 24.577,
      "eval_samples_per_second": 30.435,
      "eval_steps_per_second": 15.218,
      "step": 200
    },
    {
      "epoch": 0.47814451382694023,
      "grad_norm": 0.5559374690055847,
      "learning_rate": 5.37712895377129e-05,
      "loss": 0.5726,
      "step": 201
    },
    {
      "epoch": 0.48052334225393994,
      "grad_norm": 0.48858100175857544,
      "learning_rate": 5.3527980535279806e-05,
      "loss": 0.481,
      "step": 202
    },
    {
      "epoch": 0.48290217068093966,
      "grad_norm": 0.45764482021331787,
      "learning_rate": 5.328467153284672e-05,
      "loss": 0.4345,
      "step": 203
    },
    {
      "epoch": 0.4852809991079393,
      "grad_norm": 0.5081002116203308,
      "learning_rate": 5.304136253041363e-05,
      "loss": 0.4091,
      "step": 204
    },
    {
      "epoch": 0.487659827534939,
      "grad_norm": 0.47981277108192444,
      "learning_rate": 5.279805352798054e-05,
      "loss": 0.4198,
      "step": 205
    },
    {
      "epoch": 0.49003865596193874,
      "grad_norm": 0.5422961115837097,
      "learning_rate": 5.255474452554745e-05,
      "loss": 0.4645,
      "step": 206
    },
    {
      "epoch": 0.49241748438893845,
      "grad_norm": 0.5617045164108276,
      "learning_rate": 5.231143552311436e-05,
      "loss": 0.499,
      "step": 207
    },
    {
      "epoch": 0.49479631281593817,
      "grad_norm": 0.5472312569618225,
      "learning_rate": 5.206812652068127e-05,
      "loss": 0.4303,
      "step": 208
    },
    {
      "epoch": 0.4971751412429379,
      "grad_norm": 0.560845136642456,
      "learning_rate": 5.182481751824818e-05,
      "loss": 0.507,
      "step": 209
    },
    {
      "epoch": 0.49955396966993754,
      "grad_norm": 0.5158256888389587,
      "learning_rate": 5.158150851581509e-05,
      "loss": 0.5126,
      "step": 210
    },
    {
      "epoch": 0.5019327980969372,
      "grad_norm": 0.49810492992401123,
      "learning_rate": 5.1338199513382e-05,
      "loss": 0.3799,
      "step": 211
    },
    {
      "epoch": 0.5043116265239369,
      "grad_norm": 0.5269343852996826,
      "learning_rate": 5.109489051094891e-05,
      "loss": 0.5066,
      "step": 212
    },
    {
      "epoch": 0.5066904549509367,
      "grad_norm": 0.48883453011512756,
      "learning_rate": 5.0851581508515824e-05,
      "loss": 0.4593,
      "step": 213
    },
    {
      "epoch": 0.5090692833779363,
      "grad_norm": 0.5003328919410706,
      "learning_rate": 5.060827250608273e-05,
      "loss": 0.4672,
      "step": 214
    },
    {
      "epoch": 0.5114481118049361,
      "grad_norm": 0.5346857905387878,
      "learning_rate": 5.036496350364964e-05,
      "loss": 0.459,
      "step": 215
    },
    {
      "epoch": 0.5138269402319358,
      "grad_norm": 0.5018550157546997,
      "learning_rate": 5.012165450121655e-05,
      "loss": 0.427,
      "step": 216
    },
    {
      "epoch": 0.5162057686589355,
      "grad_norm": 0.5394279956817627,
      "learning_rate": 4.987834549878346e-05,
      "loss": 0.4906,
      "step": 217
    },
    {
      "epoch": 0.5185845970859352,
      "grad_norm": 0.41929885745048523,
      "learning_rate": 4.963503649635037e-05,
      "loss": 0.4719,
      "step": 218
    },
    {
      "epoch": 0.5209634255129348,
      "grad_norm": 0.5181702375411987,
      "learning_rate": 4.9391727493917275e-05,
      "loss": 0.4187,
      "step": 219
    },
    {
      "epoch": 0.5233422539399346,
      "grad_norm": 0.5157968997955322,
      "learning_rate": 4.914841849148419e-05,
      "loss": 0.3988,
      "step": 220
    },
    {
      "epoch": 0.5257210823669343,
      "grad_norm": 0.5713850259780884,
      "learning_rate": 4.89051094890511e-05,
      "loss": 0.4988,
      "step": 221
    },
    {
      "epoch": 0.528099910793934,
      "grad_norm": 0.5276979804039001,
      "learning_rate": 4.866180048661801e-05,
      "loss": 0.4289,
      "step": 222
    },
    {
      "epoch": 0.5304787392209337,
      "grad_norm": 0.5099546313285828,
      "learning_rate": 4.8418491484184916e-05,
      "loss": 0.4143,
      "step": 223
    },
    {
      "epoch": 0.5328575676479334,
      "grad_norm": 0.5845214128494263,
      "learning_rate": 4.817518248175183e-05,
      "loss": 0.528,
      "step": 224
    },
    {
      "epoch": 0.5352363960749331,
      "grad_norm": 0.5065467357635498,
      "learning_rate": 4.793187347931874e-05,
      "loss": 0.4109,
      "step": 225
    },
    {
      "epoch": 0.5376152245019328,
      "grad_norm": 0.46541669964790344,
      "learning_rate": 4.7688564476885646e-05,
      "loss": 0.4202,
      "step": 226
    },
    {
      "epoch": 0.5399940529289325,
      "grad_norm": 0.571874737739563,
      "learning_rate": 4.744525547445256e-05,
      "loss": 0.5088,
      "step": 227
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 0.542327880859375,
      "learning_rate": 4.720194647201946e-05,
      "loss": 0.458,
      "step": 228
    },
    {
      "epoch": 0.5447517097829319,
      "grad_norm": 0.48291677236557007,
      "learning_rate": 4.6958637469586375e-05,
      "loss": 0.3743,
      "step": 229
    },
    {
      "epoch": 0.5471305382099316,
      "grad_norm": 0.5330439805984497,
      "learning_rate": 4.6715328467153287e-05,
      "loss": 0.4217,
      "step": 230
    },
    {
      "epoch": 0.5495093666369313,
      "grad_norm": 0.47011399269104004,
      "learning_rate": 4.64720194647202e-05,
      "loss": 0.4582,
      "step": 231
    },
    {
      "epoch": 0.551888195063931,
      "grad_norm": 0.5513572692871094,
      "learning_rate": 4.6228710462287104e-05,
      "loss": 0.4527,
      "step": 232
    },
    {
      "epoch": 0.5542670234909307,
      "grad_norm": 0.61734539270401,
      "learning_rate": 4.5985401459854016e-05,
      "loss": 0.5963,
      "step": 233
    },
    {
      "epoch": 0.5566458519179304,
      "grad_norm": 0.4924643933773041,
      "learning_rate": 4.574209245742093e-05,
      "loss": 0.3916,
      "step": 234
    },
    {
      "epoch": 0.5590246803449301,
      "grad_norm": 0.4713283181190491,
      "learning_rate": 4.549878345498784e-05,
      "loss": 0.3963,
      "step": 235
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.4790879786014557,
      "learning_rate": 4.5255474452554745e-05,
      "loss": 0.4097,
      "step": 236
    },
    {
      "epoch": 0.5637823371989296,
      "grad_norm": 0.4752825200557709,
      "learning_rate": 4.5012165450121657e-05,
      "loss": 0.3671,
      "step": 237
    },
    {
      "epoch": 0.5661611656259292,
      "grad_norm": 0.6054632663726807,
      "learning_rate": 4.476885644768857e-05,
      "loss": 0.478,
      "step": 238
    },
    {
      "epoch": 0.568539994052929,
      "grad_norm": 0.5796523094177246,
      "learning_rate": 4.452554744525548e-05,
      "loss": 0.4677,
      "step": 239
    },
    {
      "epoch": 0.5709188224799286,
      "grad_norm": 0.7159845232963562,
      "learning_rate": 4.4282238442822386e-05,
      "loss": 0.6,
      "step": 240
    },
    {
      "epoch": 0.5732976509069283,
      "grad_norm": 0.4576638638973236,
      "learning_rate": 4.40389294403893e-05,
      "loss": 0.3984,
      "step": 241
    },
    {
      "epoch": 0.5756764793339281,
      "grad_norm": 0.5089020133018494,
      "learning_rate": 4.379562043795621e-05,
      "loss": 0.4245,
      "step": 242
    },
    {
      "epoch": 0.5780553077609277,
      "grad_norm": 0.4587903618812561,
      "learning_rate": 4.355231143552312e-05,
      "loss": 0.399,
      "step": 243
    },
    {
      "epoch": 0.5804341361879275,
      "grad_norm": 0.46936094760894775,
      "learning_rate": 4.3309002433090027e-05,
      "loss": 0.3892,
      "step": 244
    },
    {
      "epoch": 0.5828129646149272,
      "grad_norm": 0.5407763719558716,
      "learning_rate": 4.306569343065693e-05,
      "loss": 0.5055,
      "step": 245
    },
    {
      "epoch": 0.5851917930419268,
      "grad_norm": 0.5131598114967346,
      "learning_rate": 4.2822384428223844e-05,
      "loss": 0.469,
      "step": 246
    },
    {
      "epoch": 0.5875706214689266,
      "grad_norm": 0.48786240816116333,
      "learning_rate": 4.2579075425790756e-05,
      "loss": 0.3993,
      "step": 247
    },
    {
      "epoch": 0.5899494498959262,
      "grad_norm": 0.5068132281303406,
      "learning_rate": 4.233576642335767e-05,
      "loss": 0.4114,
      "step": 248
    },
    {
      "epoch": 0.592328278322926,
      "grad_norm": 0.5316363573074341,
      "learning_rate": 4.209245742092457e-05,
      "loss": 0.446,
      "step": 249
    },
    {
      "epoch": 0.5947071067499257,
      "grad_norm": 0.511885404586792,
      "learning_rate": 4.1849148418491485e-05,
      "loss": 0.4738,
      "step": 250
    },
    {
      "epoch": 0.5970859351769253,
      "grad_norm": 0.6263471245765686,
      "learning_rate": 4.16058394160584e-05,
      "loss": 0.5074,
      "step": 251
    },
    {
      "epoch": 0.5994647636039251,
      "grad_norm": 0.5359822511672974,
      "learning_rate": 4.136253041362531e-05,
      "loss": 0.4239,
      "step": 252
    },
    {
      "epoch": 0.6018435920309247,
      "grad_norm": 0.5764995217323303,
      "learning_rate": 4.1119221411192214e-05,
      "loss": 0.5247,
      "step": 253
    },
    {
      "epoch": 0.6042224204579245,
      "grad_norm": 0.5081723928451538,
      "learning_rate": 4.0875912408759126e-05,
      "loss": 0.4104,
      "step": 254
    },
    {
      "epoch": 0.6066012488849242,
      "grad_norm": 0.5557652115821838,
      "learning_rate": 4.063260340632604e-05,
      "loss": 0.4889,
      "step": 255
    },
    {
      "epoch": 0.6089800773119238,
      "grad_norm": 0.48941561579704285,
      "learning_rate": 4.038929440389295e-05,
      "loss": 0.4557,
      "step": 256
    },
    {
      "epoch": 0.6113589057389236,
      "grad_norm": 0.565647304058075,
      "learning_rate": 4.0145985401459855e-05,
      "loss": 0.4924,
      "step": 257
    },
    {
      "epoch": 0.6137377341659233,
      "grad_norm": 0.5029006004333496,
      "learning_rate": 3.990267639902677e-05,
      "loss": 0.4885,
      "step": 258
    },
    {
      "epoch": 0.616116562592923,
      "grad_norm": 0.5224466323852539,
      "learning_rate": 3.965936739659368e-05,
      "loss": 0.4433,
      "step": 259
    },
    {
      "epoch": 0.6184953910199227,
      "grad_norm": 0.6890097260475159,
      "learning_rate": 3.941605839416059e-05,
      "loss": 0.5399,
      "step": 260
    },
    {
      "epoch": 0.6208742194469223,
      "grad_norm": 0.48153895139694214,
      "learning_rate": 3.9172749391727496e-05,
      "loss": 0.3881,
      "step": 261
    },
    {
      "epoch": 0.6232530478739221,
      "grad_norm": 0.5819414258003235,
      "learning_rate": 3.892944038929441e-05,
      "loss": 0.4568,
      "step": 262
    },
    {
      "epoch": 0.6256318763009218,
      "grad_norm": 0.4706772267818451,
      "learning_rate": 3.868613138686132e-05,
      "loss": 0.4382,
      "step": 263
    },
    {
      "epoch": 0.6280107047279215,
      "grad_norm": 0.5553036332130432,
      "learning_rate": 3.8442822384428225e-05,
      "loss": 0.4611,
      "step": 264
    },
    {
      "epoch": 0.6303895331549212,
      "grad_norm": 0.5100443959236145,
      "learning_rate": 3.819951338199514e-05,
      "loss": 0.424,
      "step": 265
    },
    {
      "epoch": 0.632768361581921,
      "grad_norm": 0.47650212049484253,
      "learning_rate": 3.795620437956204e-05,
      "loss": 0.4642,
      "step": 266
    },
    {
      "epoch": 0.6351471900089206,
      "grad_norm": 0.5056859254837036,
      "learning_rate": 3.7712895377128954e-05,
      "loss": 0.4643,
      "step": 267
    },
    {
      "epoch": 0.6375260184359203,
      "grad_norm": 0.48869505524635315,
      "learning_rate": 3.7469586374695866e-05,
      "loss": 0.4058,
      "step": 268
    },
    {
      "epoch": 0.63990484686292,
      "grad_norm": 0.5686202645301819,
      "learning_rate": 3.722627737226278e-05,
      "loss": 0.4772,
      "step": 269
    },
    {
      "epoch": 0.6422836752899197,
      "grad_norm": 0.523289680480957,
      "learning_rate": 3.698296836982968e-05,
      "loss": 0.4257,
      "step": 270
    },
    {
      "epoch": 0.6446625037169195,
      "grad_norm": 0.4355628192424774,
      "learning_rate": 3.6739659367396595e-05,
      "loss": 0.4035,
      "step": 271
    },
    {
      "epoch": 0.6470413321439191,
      "grad_norm": 0.5667319297790527,
      "learning_rate": 3.649635036496351e-05,
      "loss": 0.5109,
      "step": 272
    },
    {
      "epoch": 0.6494201605709188,
      "grad_norm": 0.49869677424430847,
      "learning_rate": 3.625304136253042e-05,
      "loss": 0.4496,
      "step": 273
    },
    {
      "epoch": 0.6517989889979185,
      "grad_norm": 0.4514950215816498,
      "learning_rate": 3.6009732360097324e-05,
      "loss": 0.3948,
      "step": 274
    },
    {
      "epoch": 0.6541778174249182,
      "grad_norm": 0.5341079235076904,
      "learning_rate": 3.5766423357664236e-05,
      "loss": 0.5351,
      "step": 275
    },
    {
      "epoch": 0.656556645851918,
      "grad_norm": 0.5494990348815918,
      "learning_rate": 3.552311435523115e-05,
      "loss": 0.5355,
      "step": 276
    },
    {
      "epoch": 0.6589354742789176,
      "grad_norm": 0.5039032697677612,
      "learning_rate": 3.527980535279806e-05,
      "loss": 0.388,
      "step": 277
    },
    {
      "epoch": 0.6613143027059173,
      "grad_norm": 0.543323278427124,
      "learning_rate": 3.5036496350364965e-05,
      "loss": 0.5407,
      "step": 278
    },
    {
      "epoch": 0.6636931311329171,
      "grad_norm": 0.5307977795600891,
      "learning_rate": 3.479318734793188e-05,
      "loss": 0.4416,
      "step": 279
    },
    {
      "epoch": 0.6660719595599167,
      "grad_norm": 0.5810051560401917,
      "learning_rate": 3.454987834549879e-05,
      "loss": 0.4984,
      "step": 280
    },
    {
      "epoch": 0.6684507879869165,
      "grad_norm": 0.5557127594947815,
      "learning_rate": 3.43065693430657e-05,
      "loss": 0.4426,
      "step": 281
    },
    {
      "epoch": 0.6708296164139161,
      "grad_norm": 0.49247419834136963,
      "learning_rate": 3.40632603406326e-05,
      "loss": 0.4353,
      "step": 282
    },
    {
      "epoch": 0.6732084448409158,
      "grad_norm": 0.5093483328819275,
      "learning_rate": 3.381995133819951e-05,
      "loss": 0.4141,
      "step": 283
    },
    {
      "epoch": 0.6755872732679156,
      "grad_norm": 0.5625473856925964,
      "learning_rate": 3.357664233576642e-05,
      "loss": 0.5592,
      "step": 284
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 0.47916609048843384,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4519,
      "step": 285
    },
    {
      "epoch": 0.680344930121915,
      "grad_norm": 0.514183759689331,
      "learning_rate": 3.309002433090024e-05,
      "loss": 0.3704,
      "step": 286
    },
    {
      "epoch": 0.6827237585489146,
      "grad_norm": 0.5638673305511475,
      "learning_rate": 3.284671532846715e-05,
      "loss": 0.4813,
      "step": 287
    },
    {
      "epoch": 0.6851025869759143,
      "grad_norm": 0.436166375875473,
      "learning_rate": 3.2603406326034064e-05,
      "loss": 0.4546,
      "step": 288
    },
    {
      "epoch": 0.6874814154029141,
      "grad_norm": 0.5311592221260071,
      "learning_rate": 3.2360097323600976e-05,
      "loss": 0.4948,
      "step": 289
    },
    {
      "epoch": 0.6898602438299137,
      "grad_norm": 0.5682978630065918,
      "learning_rate": 3.211678832116788e-05,
      "loss": 0.4595,
      "step": 290
    },
    {
      "epoch": 0.6922390722569135,
      "grad_norm": 0.5363884568214417,
      "learning_rate": 3.187347931873479e-05,
      "loss": 0.3572,
      "step": 291
    },
    {
      "epoch": 0.6946179006839132,
      "grad_norm": 0.517888069152832,
      "learning_rate": 3.1630170316301705e-05,
      "loss": 0.3949,
      "step": 292
    },
    {
      "epoch": 0.6969967291109129,
      "grad_norm": 0.5211926698684692,
      "learning_rate": 3.138686131386862e-05,
      "loss": 0.4904,
      "step": 293
    },
    {
      "epoch": 0.6993755575379126,
      "grad_norm": 0.5304282903671265,
      "learning_rate": 3.114355231143552e-05,
      "loss": 0.4632,
      "step": 294
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.4735037386417389,
      "learning_rate": 3.0900243309002434e-05,
      "loss": 0.4002,
      "step": 295
    },
    {
      "epoch": 0.704133214391912,
      "grad_norm": 0.5239513516426086,
      "learning_rate": 3.0656934306569346e-05,
      "loss": 0.4758,
      "step": 296
    },
    {
      "epoch": 0.7065120428189117,
      "grad_norm": 0.5408491492271423,
      "learning_rate": 3.0413625304136255e-05,
      "loss": 0.4993,
      "step": 297
    },
    {
      "epoch": 0.7088908712459114,
      "grad_norm": 0.6086730360984802,
      "learning_rate": 3.0170316301703166e-05,
      "loss": 0.5048,
      "step": 298
    },
    {
      "epoch": 0.7112696996729111,
      "grad_norm": 0.4720120131969452,
      "learning_rate": 2.992700729927008e-05,
      "loss": 0.4215,
      "step": 299
    },
    {
      "epoch": 0.7136485280999108,
      "grad_norm": 0.5266088843345642,
      "learning_rate": 2.9683698296836987e-05,
      "loss": 0.4553,
      "step": 300
    },
    {
      "epoch": 0.7136485280999108,
      "eval_loss": 0.42479127645492554,
      "eval_runtime": 24.6017,
      "eval_samples_per_second": 30.404,
      "eval_steps_per_second": 15.202,
      "step": 300
    },
    {
      "epoch": 0.7160273565269105,
      "grad_norm": 0.5402945280075073,
      "learning_rate": 2.9440389294403892e-05,
      "loss": 0.4477,
      "step": 301
    },
    {
      "epoch": 0.7184061849539102,
      "grad_norm": 0.5225419402122498,
      "learning_rate": 2.91970802919708e-05,
      "loss": 0.4112,
      "step": 302
    },
    {
      "epoch": 0.72078501338091,
      "grad_norm": 0.516687273979187,
      "learning_rate": 2.8953771289537713e-05,
      "loss": 0.51,
      "step": 303
    },
    {
      "epoch": 0.7231638418079096,
      "grad_norm": 0.5380510091781616,
      "learning_rate": 2.871046228710462e-05,
      "loss": 0.3956,
      "step": 304
    },
    {
      "epoch": 0.7255426702349093,
      "grad_norm": 0.5149944424629211,
      "learning_rate": 2.8467153284671533e-05,
      "loss": 0.4596,
      "step": 305
    },
    {
      "epoch": 0.727921498661909,
      "grad_norm": 0.5109550356864929,
      "learning_rate": 2.822384428223844e-05,
      "loss": 0.4538,
      "step": 306
    },
    {
      "epoch": 0.7303003270889087,
      "grad_norm": 0.4751725196838379,
      "learning_rate": 2.7980535279805354e-05,
      "loss": 0.3858,
      "step": 307
    },
    {
      "epoch": 0.7326791555159085,
      "grad_norm": 0.5320805907249451,
      "learning_rate": 2.7737226277372262e-05,
      "loss": 0.4388,
      "step": 308
    },
    {
      "epoch": 0.7350579839429081,
      "grad_norm": 0.4881283938884735,
      "learning_rate": 2.7493917274939174e-05,
      "loss": 0.3787,
      "step": 309
    },
    {
      "epoch": 0.7374368123699078,
      "grad_norm": 0.5177855491638184,
      "learning_rate": 2.7250608272506083e-05,
      "loss": 0.4489,
      "step": 310
    },
    {
      "epoch": 0.7398156407969075,
      "grad_norm": 0.4821816682815552,
      "learning_rate": 2.7007299270072995e-05,
      "loss": 0.4178,
      "step": 311
    },
    {
      "epoch": 0.7421944692239072,
      "grad_norm": 0.5222703218460083,
      "learning_rate": 2.6763990267639903e-05,
      "loss": 0.3892,
      "step": 312
    },
    {
      "epoch": 0.744573297650907,
      "grad_norm": 0.554428219795227,
      "learning_rate": 2.6520681265206815e-05,
      "loss": 0.425,
      "step": 313
    },
    {
      "epoch": 0.7469521260779066,
      "grad_norm": 0.47558993101119995,
      "learning_rate": 2.6277372262773724e-05,
      "loss": 0.4414,
      "step": 314
    },
    {
      "epoch": 0.7493309545049064,
      "grad_norm": 0.5236990451812744,
      "learning_rate": 2.6034063260340636e-05,
      "loss": 0.4194,
      "step": 315
    },
    {
      "epoch": 0.751709782931906,
      "grad_norm": 0.5379797220230103,
      "learning_rate": 2.5790754257907544e-05,
      "loss": 0.4434,
      "step": 316
    },
    {
      "epoch": 0.7540886113589057,
      "grad_norm": 0.7105163931846619,
      "learning_rate": 2.5547445255474456e-05,
      "loss": 0.6032,
      "step": 317
    },
    {
      "epoch": 0.7564674397859055,
      "grad_norm": 0.5832124352455139,
      "learning_rate": 2.5304136253041365e-05,
      "loss": 0.5152,
      "step": 318
    },
    {
      "epoch": 0.7588462682129051,
      "grad_norm": 0.5089643597602844,
      "learning_rate": 2.5060827250608277e-05,
      "loss": 0.4333,
      "step": 319
    },
    {
      "epoch": 0.7612250966399049,
      "grad_norm": 0.509891152381897,
      "learning_rate": 2.4817518248175185e-05,
      "loss": 0.4357,
      "step": 320
    },
    {
      "epoch": 0.7636039250669046,
      "grad_norm": 0.6722425222396851,
      "learning_rate": 2.4574209245742094e-05,
      "loss": 0.5146,
      "step": 321
    },
    {
      "epoch": 0.7659827534939042,
      "grad_norm": 0.5415557622909546,
      "learning_rate": 2.4330900243309006e-05,
      "loss": 0.5069,
      "step": 322
    },
    {
      "epoch": 0.768361581920904,
      "grad_norm": 0.4898138642311096,
      "learning_rate": 2.4087591240875914e-05,
      "loss": 0.4025,
      "step": 323
    },
    {
      "epoch": 0.7707404103479036,
      "grad_norm": 0.47411227226257324,
      "learning_rate": 2.3844282238442823e-05,
      "loss": 0.4339,
      "step": 324
    },
    {
      "epoch": 0.7731192387749034,
      "grad_norm": 0.5482645034790039,
      "learning_rate": 2.360097323600973e-05,
      "loss": 0.4023,
      "step": 325
    },
    {
      "epoch": 0.7754980672019031,
      "grad_norm": 0.4828038513660431,
      "learning_rate": 2.3357664233576643e-05,
      "loss": 0.4683,
      "step": 326
    },
    {
      "epoch": 0.7778768956289027,
      "grad_norm": 0.47106465697288513,
      "learning_rate": 2.3114355231143552e-05,
      "loss": 0.3926,
      "step": 327
    },
    {
      "epoch": 0.7802557240559025,
      "grad_norm": 0.5016714930534363,
      "learning_rate": 2.2871046228710464e-05,
      "loss": 0.3897,
      "step": 328
    },
    {
      "epoch": 0.7826345524829021,
      "grad_norm": 0.48692432045936584,
      "learning_rate": 2.2627737226277372e-05,
      "loss": 0.4213,
      "step": 329
    },
    {
      "epoch": 0.7850133809099019,
      "grad_norm": 0.625466525554657,
      "learning_rate": 2.2384428223844284e-05,
      "loss": 0.4761,
      "step": 330
    },
    {
      "epoch": 0.7873922093369016,
      "grad_norm": 0.5269051194190979,
      "learning_rate": 2.2141119221411193e-05,
      "loss": 0.4216,
      "step": 331
    },
    {
      "epoch": 0.7897710377639012,
      "grad_norm": 0.6055566072463989,
      "learning_rate": 2.1897810218978105e-05,
      "loss": 0.5351,
      "step": 332
    },
    {
      "epoch": 0.792149866190901,
      "grad_norm": 0.5403903126716614,
      "learning_rate": 2.1654501216545013e-05,
      "loss": 0.4028,
      "step": 333
    },
    {
      "epoch": 0.7945286946179007,
      "grad_norm": 0.6619285941123962,
      "learning_rate": 2.1411192214111922e-05,
      "loss": 0.4291,
      "step": 334
    },
    {
      "epoch": 0.7969075230449004,
      "grad_norm": 0.48977240920066833,
      "learning_rate": 2.1167883211678834e-05,
      "loss": 0.4171,
      "step": 335
    },
    {
      "epoch": 0.7992863514719001,
      "grad_norm": 0.5986789464950562,
      "learning_rate": 2.0924574209245742e-05,
      "loss": 0.3742,
      "step": 336
    },
    {
      "epoch": 0.8016651798988997,
      "grad_norm": 0.5153005719184875,
      "learning_rate": 2.0681265206812654e-05,
      "loss": 0.4147,
      "step": 337
    },
    {
      "epoch": 0.8040440083258995,
      "grad_norm": 0.5173148512840271,
      "learning_rate": 2.0437956204379563e-05,
      "loss": 0.4648,
      "step": 338
    },
    {
      "epoch": 0.8064228367528992,
      "grad_norm": 0.5250167846679688,
      "learning_rate": 2.0194647201946475e-05,
      "loss": 0.4919,
      "step": 339
    },
    {
      "epoch": 0.8088016651798989,
      "grad_norm": 0.5532633066177368,
      "learning_rate": 1.9951338199513383e-05,
      "loss": 0.3462,
      "step": 340
    },
    {
      "epoch": 0.8111804936068986,
      "grad_norm": 0.4855538308620453,
      "learning_rate": 1.9708029197080295e-05,
      "loss": 0.4902,
      "step": 341
    },
    {
      "epoch": 0.8135593220338984,
      "grad_norm": 0.597204864025116,
      "learning_rate": 1.9464720194647204e-05,
      "loss": 0.4741,
      "step": 342
    },
    {
      "epoch": 0.815938150460898,
      "grad_norm": 0.5064167380332947,
      "learning_rate": 1.9221411192214112e-05,
      "loss": 0.4488,
      "step": 343
    },
    {
      "epoch": 0.8183169788878977,
      "grad_norm": 0.5640056133270264,
      "learning_rate": 1.897810218978102e-05,
      "loss": 0.4408,
      "step": 344
    },
    {
      "epoch": 0.8206958073148974,
      "grad_norm": 0.5452293753623962,
      "learning_rate": 1.8734793187347933e-05,
      "loss": 0.4406,
      "step": 345
    },
    {
      "epoch": 0.8230746357418971,
      "grad_norm": 0.5527360439300537,
      "learning_rate": 1.849148418491484e-05,
      "loss": 0.432,
      "step": 346
    },
    {
      "epoch": 0.8254534641688969,
      "grad_norm": 0.5353720784187317,
      "learning_rate": 1.8248175182481753e-05,
      "loss": 0.4195,
      "step": 347
    },
    {
      "epoch": 0.8278322925958965,
      "grad_norm": 0.4622812569141388,
      "learning_rate": 1.8004866180048662e-05,
      "loss": 0.4146,
      "step": 348
    },
    {
      "epoch": 0.8302111210228962,
      "grad_norm": 0.5472270250320435,
      "learning_rate": 1.7761557177615574e-05,
      "loss": 0.4521,
      "step": 349
    },
    {
      "epoch": 0.832589949449896,
      "grad_norm": 0.5854270458221436,
      "learning_rate": 1.7518248175182482e-05,
      "loss": 0.3974,
      "step": 350
    },
    {
      "epoch": 0.8349687778768956,
      "grad_norm": 0.4779118597507477,
      "learning_rate": 1.7274939172749394e-05,
      "loss": 0.3683,
      "step": 351
    },
    {
      "epoch": 0.8373476063038954,
      "grad_norm": 0.5334904789924622,
      "learning_rate": 1.70316301703163e-05,
      "loss": 0.4319,
      "step": 352
    },
    {
      "epoch": 0.839726434730895,
      "grad_norm": 0.49920886754989624,
      "learning_rate": 1.678832116788321e-05,
      "loss": 0.4115,
      "step": 353
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.6039828658103943,
      "learning_rate": 1.654501216545012e-05,
      "loss": 0.4133,
      "step": 354
    },
    {
      "epoch": 0.8444840915848945,
      "grad_norm": 0.5769008994102478,
      "learning_rate": 1.6301703163017032e-05,
      "loss": 0.4316,
      "step": 355
    },
    {
      "epoch": 0.8468629200118941,
      "grad_norm": 0.5622073411941528,
      "learning_rate": 1.605839416058394e-05,
      "loss": 0.5002,
      "step": 356
    },
    {
      "epoch": 0.8492417484388939,
      "grad_norm": 0.5158018469810486,
      "learning_rate": 1.5815085158150852e-05,
      "loss": 0.3537,
      "step": 357
    },
    {
      "epoch": 0.8516205768658935,
      "grad_norm": 0.5640501379966736,
      "learning_rate": 1.557177615571776e-05,
      "loss": 0.5049,
      "step": 358
    },
    {
      "epoch": 0.8539994052928932,
      "grad_norm": 0.5024840831756592,
      "learning_rate": 1.5328467153284673e-05,
      "loss": 0.4185,
      "step": 359
    },
    {
      "epoch": 0.856378233719893,
      "grad_norm": 0.5789101123809814,
      "learning_rate": 1.5085158150851583e-05,
      "loss": 0.4016,
      "step": 360
    },
    {
      "epoch": 0.8587570621468926,
      "grad_norm": 0.5746119022369385,
      "learning_rate": 1.4841849148418493e-05,
      "loss": 0.4421,
      "step": 361
    },
    {
      "epoch": 0.8611358905738924,
      "grad_norm": 0.5970929861068726,
      "learning_rate": 1.45985401459854e-05,
      "loss": 0.5766,
      "step": 362
    },
    {
      "epoch": 0.863514719000892,
      "grad_norm": 0.5322396755218506,
      "learning_rate": 1.435523114355231e-05,
      "loss": 0.4418,
      "step": 363
    },
    {
      "epoch": 0.8658935474278918,
      "grad_norm": 0.5240874886512756,
      "learning_rate": 1.411192214111922e-05,
      "loss": 0.461,
      "step": 364
    },
    {
      "epoch": 0.8682723758548915,
      "grad_norm": 0.6501151919364929,
      "learning_rate": 1.3868613138686131e-05,
      "loss": 0.3628,
      "step": 365
    },
    {
      "epoch": 0.8706512042818911,
      "grad_norm": 0.5303117036819458,
      "learning_rate": 1.3625304136253041e-05,
      "loss": 0.441,
      "step": 366
    },
    {
      "epoch": 0.8730300327088909,
      "grad_norm": 0.48986294865608215,
      "learning_rate": 1.3381995133819952e-05,
      "loss": 0.4371,
      "step": 367
    },
    {
      "epoch": 0.8754088611358906,
      "grad_norm": 0.5813177824020386,
      "learning_rate": 1.3138686131386862e-05,
      "loss": 0.4787,
      "step": 368
    },
    {
      "epoch": 0.8777876895628903,
      "grad_norm": 0.5057734251022339,
      "learning_rate": 1.2895377128953772e-05,
      "loss": 0.3852,
      "step": 369
    },
    {
      "epoch": 0.88016651798989,
      "grad_norm": 0.5309827923774719,
      "learning_rate": 1.2652068126520682e-05,
      "loss": 0.4518,
      "step": 370
    },
    {
      "epoch": 0.8825453464168896,
      "grad_norm": 0.5106115341186523,
      "learning_rate": 1.2408759124087593e-05,
      "loss": 0.414,
      "step": 371
    },
    {
      "epoch": 0.8849241748438894,
      "grad_norm": 0.6071767210960388,
      "learning_rate": 1.2165450121654503e-05,
      "loss": 0.4988,
      "step": 372
    },
    {
      "epoch": 0.8873030032708891,
      "grad_norm": 0.5328472852706909,
      "learning_rate": 1.1922141119221411e-05,
      "loss": 0.5115,
      "step": 373
    },
    {
      "epoch": 0.8896818316978888,
      "grad_norm": 0.4671655595302582,
      "learning_rate": 1.1678832116788322e-05,
      "loss": 0.3692,
      "step": 374
    },
    {
      "epoch": 0.8920606601248885,
      "grad_norm": 0.5364991426467896,
      "learning_rate": 1.1435523114355232e-05,
      "loss": 0.369,
      "step": 375
    },
    {
      "epoch": 0.8944394885518882,
      "grad_norm": 0.5912413597106934,
      "learning_rate": 1.1192214111922142e-05,
      "loss": 0.4404,
      "step": 376
    },
    {
      "epoch": 0.8968183169788879,
      "grad_norm": 0.54830402135849,
      "learning_rate": 1.0948905109489052e-05,
      "loss": 0.3858,
      "step": 377
    },
    {
      "epoch": 0.8991971454058876,
      "grad_norm": 0.5137721300125122,
      "learning_rate": 1.0705596107055961e-05,
      "loss": 0.3976,
      "step": 378
    },
    {
      "epoch": 0.9015759738328873,
      "grad_norm": 0.5718546509742737,
      "learning_rate": 1.0462287104622871e-05,
      "loss": 0.4714,
      "step": 379
    },
    {
      "epoch": 0.903954802259887,
      "grad_norm": 0.5441231727600098,
      "learning_rate": 1.0218978102189781e-05,
      "loss": 0.4706,
      "step": 380
    },
    {
      "epoch": 0.9063336306868867,
      "grad_norm": 0.5782937407493591,
      "learning_rate": 9.975669099756692e-06,
      "loss": 0.4758,
      "step": 381
    },
    {
      "epoch": 0.9087124591138864,
      "grad_norm": 0.5077878832817078,
      "learning_rate": 9.732360097323602e-06,
      "loss": 0.4739,
      "step": 382
    },
    {
      "epoch": 0.9110912875408861,
      "grad_norm": 0.5690765380859375,
      "learning_rate": 9.48905109489051e-06,
      "loss": 0.3926,
      "step": 383
    },
    {
      "epoch": 0.9134701159678859,
      "grad_norm": 0.5629989504814148,
      "learning_rate": 9.24574209245742e-06,
      "loss": 0.4728,
      "step": 384
    },
    {
      "epoch": 0.9158489443948855,
      "grad_norm": 0.46644964814186096,
      "learning_rate": 9.002433090024331e-06,
      "loss": 0.3798,
      "step": 385
    },
    {
      "epoch": 0.9182277728218852,
      "grad_norm": 0.5197304487228394,
      "learning_rate": 8.759124087591241e-06,
      "loss": 0.4181,
      "step": 386
    },
    {
      "epoch": 0.9206066012488849,
      "grad_norm": 0.5880502462387085,
      "learning_rate": 8.51581508515815e-06,
      "loss": 0.5106,
      "step": 387
    },
    {
      "epoch": 0.9229854296758846,
      "grad_norm": 0.6154156923294067,
      "learning_rate": 8.27250608272506e-06,
      "loss": 0.4669,
      "step": 388
    },
    {
      "epoch": 0.9253642581028844,
      "grad_norm": 0.604262113571167,
      "learning_rate": 8.02919708029197e-06,
      "loss": 0.451,
      "step": 389
    },
    {
      "epoch": 0.927743086529884,
      "grad_norm": 0.5451841354370117,
      "learning_rate": 7.78588807785888e-06,
      "loss": 0.4477,
      "step": 390
    },
    {
      "epoch": 0.9301219149568838,
      "grad_norm": 0.6219511032104492,
      "learning_rate": 7.542579075425792e-06,
      "loss": 0.4633,
      "step": 391
    },
    {
      "epoch": 0.9325007433838834,
      "grad_norm": 0.5371522903442383,
      "learning_rate": 7.2992700729927e-06,
      "loss": 0.4109,
      "step": 392
    },
    {
      "epoch": 0.9348795718108831,
      "grad_norm": 0.5737317800521851,
      "learning_rate": 7.05596107055961e-06,
      "loss": 0.434,
      "step": 393
    },
    {
      "epoch": 0.9372584002378829,
      "grad_norm": 0.6237983703613281,
      "learning_rate": 6.812652068126521e-06,
      "loss": 0.4657,
      "step": 394
    },
    {
      "epoch": 0.9396372286648825,
      "grad_norm": 0.5219160914421082,
      "learning_rate": 6.569343065693431e-06,
      "loss": 0.3983,
      "step": 395
    },
    {
      "epoch": 0.9420160570918823,
      "grad_norm": 0.5657615661621094,
      "learning_rate": 6.326034063260341e-06,
      "loss": 0.3901,
      "step": 396
    },
    {
      "epoch": 0.944394885518882,
      "grad_norm": 0.6130802035331726,
      "learning_rate": 6.082725060827251e-06,
      "loss": 0.4844,
      "step": 397
    },
    {
      "epoch": 0.9467737139458816,
      "grad_norm": 0.6125937104225159,
      "learning_rate": 5.839416058394161e-06,
      "loss": 0.4312,
      "step": 398
    },
    {
      "epoch": 0.9491525423728814,
      "grad_norm": 0.5268482565879822,
      "learning_rate": 5.596107055961071e-06,
      "loss": 0.3764,
      "step": 399
    },
    {
      "epoch": 0.951531370799881,
      "grad_norm": 0.601588785648346,
      "learning_rate": 5.3527980535279805e-06,
      "loss": 0.429,
      "step": 400
    },
    {
      "epoch": 0.951531370799881,
      "eval_loss": 0.4152432680130005,
      "eval_runtime": 24.6197,
      "eval_samples_per_second": 30.382,
      "eval_steps_per_second": 15.191,
      "step": 400
    },
    {
      "epoch": 0.9539101992268808,
      "grad_norm": 0.6177543997764587,
      "learning_rate": 5.109489051094891e-06,
      "loss": 0.4553,
      "step": 401
    },
    {
      "epoch": 0.9562890276538805,
      "grad_norm": 0.5756453275680542,
      "learning_rate": 4.866180048661801e-06,
      "loss": 0.4026,
      "step": 402
    },
    {
      "epoch": 0.9586678560808801,
      "grad_norm": 0.575804591178894,
      "learning_rate": 4.62287104622871e-06,
      "loss": 0.4351,
      "step": 403
    },
    {
      "epoch": 0.9610466845078799,
      "grad_norm": 0.5242466926574707,
      "learning_rate": 4.379562043795621e-06,
      "loss": 0.4606,
      "step": 404
    },
    {
      "epoch": 0.9634255129348795,
      "grad_norm": 0.5496498346328735,
      "learning_rate": 4.13625304136253e-06,
      "loss": 0.5175,
      "step": 405
    },
    {
      "epoch": 0.9658043413618793,
      "grad_norm": 0.5221502184867859,
      "learning_rate": 3.89294403892944e-06,
      "loss": 0.3652,
      "step": 406
    },
    {
      "epoch": 0.968183169788879,
      "grad_norm": 0.5580674409866333,
      "learning_rate": 3.64963503649635e-06,
      "loss": 0.3914,
      "step": 407
    },
    {
      "epoch": 0.9705619982158786,
      "grad_norm": 0.5373774170875549,
      "learning_rate": 3.4063260340632603e-06,
      "loss": 0.399,
      "step": 408
    },
    {
      "epoch": 0.9729408266428784,
      "grad_norm": 0.44664666056632996,
      "learning_rate": 3.1630170316301706e-06,
      "loss": 0.3659,
      "step": 409
    },
    {
      "epoch": 0.975319655069878,
      "grad_norm": 0.5495840311050415,
      "learning_rate": 2.9197080291970804e-06,
      "loss": 0.4548,
      "step": 410
    },
    {
      "epoch": 0.9776984834968778,
      "grad_norm": 0.6554842591285706,
      "learning_rate": 2.6763990267639902e-06,
      "loss": 0.3963,
      "step": 411
    },
    {
      "epoch": 0.9800773119238775,
      "grad_norm": 0.5366389155387878,
      "learning_rate": 2.4330900243309005e-06,
      "loss": 0.391,
      "step": 412
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 0.5802214741706848,
      "learning_rate": 2.1897810218978103e-06,
      "loss": 0.4397,
      "step": 413
    },
    {
      "epoch": 0.9848349687778769,
      "grad_norm": 0.5553064942359924,
      "learning_rate": 1.94647201946472e-06,
      "loss": 0.384,
      "step": 414
    },
    {
      "epoch": 0.9872137972048766,
      "grad_norm": 0.5031337141990662,
      "learning_rate": 1.7031630170316302e-06,
      "loss": 0.3638,
      "step": 415
    },
    {
      "epoch": 0.9895926256318763,
      "grad_norm": 0.5195873379707336,
      "learning_rate": 1.4598540145985402e-06,
      "loss": 0.4275,
      "step": 416
    },
    {
      "epoch": 0.991971454058876,
      "grad_norm": 0.5617223978042603,
      "learning_rate": 1.2165450121654502e-06,
      "loss": 0.4383,
      "step": 417
    },
    {
      "epoch": 0.9943502824858758,
      "grad_norm": 0.5391303300857544,
      "learning_rate": 9.7323600973236e-07,
      "loss": 0.5038,
      "step": 418
    },
    {
      "epoch": 0.9967291109128754,
      "grad_norm": 0.5291772484779358,
      "learning_rate": 7.299270072992701e-07,
      "loss": 0.4119,
      "step": 419
    },
    {
      "epoch": 0.9991079393398751,
      "grad_norm": 0.52870112657547,
      "learning_rate": 4.8661800486618e-07,
      "loss": 0.4272,
      "step": 420
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8552002310752869,
      "learning_rate": 2.4330900243309e-07,
      "loss": 0.3481,
      "step": 421
    }
  ],
  "logging_steps": 1,
  "max_steps": 421,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4660818389684224e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}