{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2003454231433506,
  "eval_steps": 869,
  "global_step": 348,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005757052389176742,
      "grad_norm": 2.557003974914551,
      "learning_rate": 0.0,
      "loss": 5.4277,
      "step": 1
    },
    {
      "epoch": 0.0005757052389176742,
      "eval_loss": 5.319709300994873,
      "eval_runtime": 1026.7022,
      "eval_samples_per_second": 2.496,
      "eval_steps_per_second": 2.496,
      "step": 1
    },
    {
      "epoch": 0.0011514104778353484,
      "grad_norm": 2.985229969024658,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 5.7019,
      "step": 2
    },
    {
      "epoch": 0.0017271157167530224,
      "grad_norm": 3.0353081226348877,
      "learning_rate": 8.000000000000001e-07,
      "loss": 6.1934,
      "step": 3
    },
    {
      "epoch": 0.002302820955670697,
      "grad_norm": 3.724905490875244,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 5.4617,
      "step": 4
    },
    {
      "epoch": 0.0028785261945883708,
      "grad_norm": 2.6505627632141113,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 5.4285,
      "step": 5
    },
    {
      "epoch": 0.0034542314335060447,
      "grad_norm": 2.7363409996032715,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 5.8634,
      "step": 6
    },
    {
      "epoch": 0.004029936672423719,
      "grad_norm": 3.082538366317749,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 4.7461,
      "step": 7
    },
    {
      "epoch": 0.004605641911341394,
      "grad_norm": 9.095250129699707,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 7.5703,
      "step": 8
    },
    {
      "epoch": 0.0051813471502590676,
      "grad_norm": 2.2597923278808594,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 5.3631,
      "step": 9
    },
    {
      "epoch": 0.0057570523891767415,
      "grad_norm": 5.053525924682617,
      "learning_rate": 3.6e-06,
      "loss": 6.0132,
      "step": 10
    },
    {
      "epoch": 0.0063327576280944155,
      "grad_norm": 2.7407820224761963,
      "learning_rate": 4.000000000000001e-06,
      "loss": 5.9776,
      "step": 11
    },
    {
      "epoch": 0.0069084628670120895,
      "grad_norm": 2.4892263412475586,
      "learning_rate": 4.4e-06,
      "loss": 5.524,
      "step": 12
    },
    {
      "epoch": 0.007484168105929764,
      "grad_norm": 2.5302274227142334,
      "learning_rate": 4.800000000000001e-06,
      "loss": 5.8044,
      "step": 13
    },
    {
      "epoch": 0.008059873344847437,
      "grad_norm": 2.992504358291626,
      "learning_rate": 5.2e-06,
      "loss": 6.0307,
      "step": 14
    },
    {
      "epoch": 0.008635578583765112,
      "grad_norm": 4.081608295440674,
      "learning_rate": 5.600000000000001e-06,
      "loss": 4.6732,
      "step": 15
    },
    {
      "epoch": 0.009211283822682787,
      "grad_norm": 2.33296799659729,
      "learning_rate": 6e-06,
      "loss": 4.6356,
      "step": 16
    },
    {
      "epoch": 0.00978698906160046,
      "grad_norm": 2.798452854156494,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 5.2941,
      "step": 17
    },
    {
      "epoch": 0.010362694300518135,
      "grad_norm": 2.290029525756836,
      "learning_rate": 6.800000000000001e-06,
      "loss": 4.9405,
      "step": 18
    },
    {
      "epoch": 0.010938399539435808,
      "grad_norm": 3.2164740562438965,
      "learning_rate": 7.2e-06,
      "loss": 5.6711,
      "step": 19
    },
    {
      "epoch": 0.011514104778353483,
      "grad_norm": 2.4481987953186035,
      "learning_rate": 7.6e-06,
      "loss": 5.0366,
      "step": 20
    },
    {
      "epoch": 0.012089810017271158,
      "grad_norm": 3.398063898086548,
      "learning_rate": 8.000000000000001e-06,
      "loss": 5.9377,
      "step": 21
    },
    {
      "epoch": 0.012665515256188831,
      "grad_norm": 2.3936686515808105,
      "learning_rate": 8.400000000000001e-06,
      "loss": 5.4237,
      "step": 22
    },
    {
      "epoch": 0.013241220495106506,
      "grad_norm": 2.7233810424804688,
      "learning_rate": 8.8e-06,
      "loss": 5.6551,
      "step": 23
    },
    {
      "epoch": 0.013816925734024179,
      "grad_norm": 2.9957566261291504,
      "learning_rate": 9.2e-06,
      "loss": 4.7701,
      "step": 24
    },
    {
      "epoch": 0.014392630972941854,
      "grad_norm": 6.397132396697998,
      "learning_rate": 9.600000000000001e-06,
      "loss": 6.4459,
      "step": 25
    },
    {
      "epoch": 0.014968336211859529,
      "grad_norm": 3.0593409538269043,
      "learning_rate": 1e-05,
      "loss": 5.2758,
      "step": 26
    },
    {
      "epoch": 0.015544041450777202,
      "grad_norm": 2.9723803997039795,
      "learning_rate": 1.04e-05,
      "loss": 5.6136,
      "step": 27
    },
    {
      "epoch": 0.016119746689694875,
      "grad_norm": 2.03314471244812,
      "learning_rate": 1.08e-05,
      "loss": 5.3556,
      "step": 28
    },
    {
      "epoch": 0.01669545192861255,
      "grad_norm": 1.777107834815979,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 5.1061,
      "step": 29
    },
    {
      "epoch": 0.017271157167530225,
      "grad_norm": 3.2192044258117676,
      "learning_rate": 1.16e-05,
      "loss": 5.2414,
      "step": 30
    },
    {
      "epoch": 0.017846862406447898,
      "grad_norm": 3.924452066421509,
      "learning_rate": 1.2e-05,
      "loss": 5.2754,
      "step": 31
    },
    {
      "epoch": 0.018422567645365574,
      "grad_norm": 3.5611093044281006,
      "learning_rate": 1.24e-05,
      "loss": 5.2817,
      "step": 32
    },
    {
      "epoch": 0.018998272884283247,
      "grad_norm": 2.5194263458251953,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 5.9063,
      "step": 33
    },
    {
      "epoch": 0.01957397812320092,
      "grad_norm": 2.403895854949951,
      "learning_rate": 1.32e-05,
      "loss": 5.1161,
      "step": 34
    },
    {
      "epoch": 0.020149683362118594,
      "grad_norm": 2.496400833129883,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 5.3049,
      "step": 35
    },
    {
      "epoch": 0.02072538860103627,
      "grad_norm": 3.0970828533172607,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 5.5807,
      "step": 36
    },
    {
      "epoch": 0.021301093839953943,
      "grad_norm": 3.941403388977051,
      "learning_rate": 1.44e-05,
      "loss": 6.0418,
      "step": 37
    },
    {
      "epoch": 0.021876799078871616,
      "grad_norm": 2.291431188583374,
      "learning_rate": 1.48e-05,
      "loss": 4.3686,
      "step": 38
    },
    {
      "epoch": 0.022452504317789293,
      "grad_norm": 2.783054828643799,
      "learning_rate": 1.52e-05,
      "loss": 5.15,
      "step": 39
    },
    {
      "epoch": 0.023028209556706966,
      "grad_norm": 3.579267978668213,
      "learning_rate": 1.56e-05,
      "loss": 5.7507,
      "step": 40
    },
    {
      "epoch": 0.02360391479562464,
      "grad_norm": 3.5277323722839355,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 6.112,
      "step": 41
    },
    {
      "epoch": 0.024179620034542316,
      "grad_norm": 2.5100817680358887,
      "learning_rate": 1.6400000000000002e-05,
      "loss": 5.2133,
      "step": 42
    },
    {
      "epoch": 0.02475532527345999,
      "grad_norm": 2.3821561336517334,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 6.0345,
      "step": 43
    },
    {
      "epoch": 0.025331030512377662,
      "grad_norm": 3.0675108432769775,
      "learning_rate": 1.7199999999999998e-05,
      "loss": 5.2294,
      "step": 44
    },
    {
      "epoch": 0.025906735751295335,
      "grad_norm": 2.8790383338928223,
      "learning_rate": 1.76e-05,
      "loss": 5.6393,
      "step": 45
    },
    {
      "epoch": 0.02648244099021301,
      "grad_norm": 3.3649141788482666,
      "learning_rate": 1.8e-05,
      "loss": 6.014,
      "step": 46
    },
    {
      "epoch": 0.027058146229130685,
      "grad_norm": 3.4695286750793457,
      "learning_rate": 1.84e-05,
      "loss": 5.3457,
      "step": 47
    },
    {
      "epoch": 0.027633851468048358,
      "grad_norm": 3.303622245788574,
      "learning_rate": 1.88e-05,
      "loss": 5.593,
      "step": 48
    },
    {
      "epoch": 0.028209556706966035,
      "grad_norm": 2.481895923614502,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 5.1439,
      "step": 49
    },
    {
      "epoch": 0.028785261945883708,
      "grad_norm": 2.888579845428467,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 4.6318,
      "step": 50
    },
    {
      "epoch": 0.02936096718480138,
      "grad_norm": 3.4528300762176514,
      "learning_rate": 2e-05,
      "loss": 5.0376,
      "step": 51
    },
    {
      "epoch": 0.029936672423719057,
      "grad_norm": 3.6751370429992676,
      "learning_rate": 2.04e-05,
      "loss": 4.9183,
      "step": 52
    },
    {
      "epoch": 0.03051237766263673,
      "grad_norm": 3.382035970687866,
      "learning_rate": 2.08e-05,
      "loss": 5.499,
      "step": 53
    },
    {
      "epoch": 0.031088082901554404,
      "grad_norm": 2.8802406787872314,
      "learning_rate": 2.12e-05,
      "loss": 5.3177,
      "step": 54
    },
    {
      "epoch": 0.03166378814047208,
      "grad_norm": 6.158539772033691,
      "learning_rate": 2.16e-05,
      "loss": 6.2133,
      "step": 55
    },
    {
      "epoch": 0.03223949337938975,
      "grad_norm": 2.599864959716797,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 5.3691,
      "step": 56
    },
    {
      "epoch": 0.03281519861830743,
      "grad_norm": 3.4526188373565674,
      "learning_rate": 2.2400000000000002e-05,
      "loss": 5.3801,
      "step": 57
    },
    {
      "epoch": 0.0333909038572251,
      "grad_norm": 9.494807243347168,
      "learning_rate": 2.2800000000000002e-05,
      "loss": 7.3116,
      "step": 58
    },
    {
      "epoch": 0.033966609096142776,
      "grad_norm": 4.3456130027771,
      "learning_rate": 2.32e-05,
      "loss": 4.7467,
      "step": 59
    },
    {
      "epoch": 0.03454231433506045,
      "grad_norm": 3.8471431732177734,
      "learning_rate": 2.36e-05,
      "loss": 5.2742,
      "step": 60
    },
    {
      "epoch": 0.03511801957397812,
      "grad_norm": 3.985994815826416,
      "learning_rate": 2.4e-05,
      "loss": 5.4615,
      "step": 61
    },
    {
      "epoch": 0.035693724812895795,
      "grad_norm": 9.588626861572266,
      "learning_rate": 2.44e-05,
      "loss": 6.8261,
      "step": 62
    },
    {
      "epoch": 0.03626943005181347,
      "grad_norm": 5.3343915939331055,
      "learning_rate": 2.48e-05,
      "loss": 6.0899,
      "step": 63
    },
    {
      "epoch": 0.03684513529073115,
      "grad_norm": 5.611617088317871,
      "learning_rate": 2.5200000000000003e-05,
      "loss": 6.4523,
      "step": 64
    },
    {
      "epoch": 0.03742084052964882,
      "grad_norm": 4.497012615203857,
      "learning_rate": 2.5600000000000002e-05,
      "loss": 4.787,
      "step": 65
    },
    {
      "epoch": 0.037996545768566495,
      "grad_norm": 5.032821178436279,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 5.6337,
      "step": 66
    },
    {
      "epoch": 0.03857225100748417,
      "grad_norm": 3.732733726501465,
      "learning_rate": 2.64e-05,
      "loss": 5.5212,
      "step": 67
    },
    {
      "epoch": 0.03914795624640184,
      "grad_norm": 4.3597517013549805,
      "learning_rate": 2.6800000000000004e-05,
      "loss": 4.647,
      "step": 68
    },
    {
      "epoch": 0.039723661485319514,
      "grad_norm": 5.359225273132324,
      "learning_rate": 2.7200000000000004e-05,
      "loss": 5.7052,
      "step": 69
    },
    {
      "epoch": 0.04029936672423719,
      "grad_norm": 4.9161601066589355,
      "learning_rate": 2.7600000000000003e-05,
      "loss": 5.3191,
      "step": 70
    },
    {
      "epoch": 0.04087507196315487,
      "grad_norm": 4.137385368347168,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 5.1797,
      "step": 71
    },
    {
      "epoch": 0.04145077720207254,
      "grad_norm": 4.728359699249268,
      "learning_rate": 2.84e-05,
      "loss": 5.1125,
      "step": 72
    },
    {
      "epoch": 0.042026482440990214,
      "grad_norm": 4.568793773651123,
      "learning_rate": 2.88e-05,
      "loss": 5.7705,
      "step": 73
    },
    {
      "epoch": 0.04260218767990789,
      "grad_norm": 4.931026935577393,
      "learning_rate": 2.9199999999999998e-05,
      "loss": 5.1052,
      "step": 74
    },
    {
      "epoch": 0.04317789291882556,
      "grad_norm": 4.697461128234863,
      "learning_rate": 2.96e-05,
      "loss": 5.1404,
      "step": 75
    },
    {
      "epoch": 0.04375359815774323,
      "grad_norm": 6.393320083618164,
      "learning_rate": 3e-05,
      "loss": 6.2212,
      "step": 76
    },
    {
      "epoch": 0.04432930339666091,
      "grad_norm": 5.876922607421875,
      "learning_rate": 3.04e-05,
      "loss": 5.7775,
      "step": 77
    },
    {
      "epoch": 0.044905008635578586,
      "grad_norm": 4.749701499938965,
      "learning_rate": 3.08e-05,
      "loss": 4.7321,
      "step": 78
    },
    {
      "epoch": 0.04548071387449626,
      "grad_norm": 4.894115447998047,
      "learning_rate": 3.12e-05,
      "loss": 5.2017,
      "step": 79
    },
    {
      "epoch": 0.04605641911341393,
      "grad_norm": 5.125804424285889,
      "learning_rate": 3.16e-05,
      "loss": 5.1661,
      "step": 80
    },
    {
      "epoch": 0.046632124352331605,
      "grad_norm": 7.571075439453125,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 6.1439,
      "step": 81
    },
    {
      "epoch": 0.04720782959124928,
      "grad_norm": 4.469061374664307,
      "learning_rate": 3.24e-05,
      "loss": 5.1732,
      "step": 82
    },
    {
      "epoch": 0.04778353483016695,
      "grad_norm": 4.565371513366699,
      "learning_rate": 3.2800000000000004e-05,
      "loss": 5.4892,
      "step": 83
    },
    {
      "epoch": 0.04835924006908463,
      "grad_norm": 5.844489097595215,
      "learning_rate": 3.32e-05,
      "loss": 5.875,
      "step": 84
    },
    {
      "epoch": 0.048934945308002305,
      "grad_norm": 10.564720153808594,
      "learning_rate": 3.3600000000000004e-05,
      "loss": 5.9008,
      "step": 85
    },
    {
      "epoch": 0.04951065054691998,
      "grad_norm": 6.923472881317139,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 5.4949,
      "step": 86
    },
    {
      "epoch": 0.05008635578583765,
      "grad_norm": 6.902386665344238,
      "learning_rate": 3.4399999999999996e-05,
      "loss": 4.9801,
      "step": 87
    },
    {
      "epoch": 0.050662061024755324,
      "grad_norm": 8.239148139953613,
      "learning_rate": 3.48e-05,
      "loss": 5.6578,
      "step": 88
    },
    {
      "epoch": 0.051237766263673,
      "grad_norm": 6.162630081176758,
      "learning_rate": 3.52e-05,
      "loss": 4.9911,
      "step": 89
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 7.2612433433532715,
      "learning_rate": 3.56e-05,
      "loss": 5.7976,
      "step": 90
    },
    {
      "epoch": 0.05238917674150835,
      "grad_norm": 6.149419784545898,
      "learning_rate": 3.6e-05,
      "loss": 4.9756,
      "step": 91
    },
    {
      "epoch": 0.05296488198042602,
      "grad_norm": 7.4116106033325195,
      "learning_rate": 3.6400000000000004e-05,
      "loss": 5.5805,
      "step": 92
    },
    {
      "epoch": 0.0535405872193437,
      "grad_norm": 5.512300491333008,
      "learning_rate": 3.68e-05,
      "loss": 4.5575,
      "step": 93
    },
    {
      "epoch": 0.05411629245826137,
      "grad_norm": 14.799551963806152,
      "learning_rate": 3.72e-05,
      "loss": 5.2244,
      "step": 94
    },
    {
      "epoch": 0.05469199769717904,
      "grad_norm": 9.756938934326172,
      "learning_rate": 3.76e-05,
      "loss": 4.8444,
      "step": 95
    },
    {
      "epoch": 0.055267702936096716,
      "grad_norm": 6.400147914886475,
      "learning_rate": 3.8e-05,
      "loss": 5.5091,
      "step": 96
    },
    {
      "epoch": 0.055843408175014396,
      "grad_norm": 8.406181335449219,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 5.2641,
      "step": 97
    },
    {
      "epoch": 0.05641911341393207,
      "grad_norm": 6.860042572021484,
      "learning_rate": 3.88e-05,
      "loss": 5.2917,
      "step": 98
    },
    {
      "epoch": 0.05699481865284974,
      "grad_norm": 7.542653560638428,
      "learning_rate": 3.9200000000000004e-05,
      "loss": 5.1584,
      "step": 99
    },
    {
      "epoch": 0.057570523891767415,
      "grad_norm": 8.149137496948242,
      "learning_rate": 3.960000000000001e-05,
      "loss": 5.5326,
      "step": 100
    },
    {
      "epoch": 0.05814622913068509,
      "grad_norm": 5.590121269226074,
      "learning_rate": 4e-05,
      "loss": 5.2789,
      "step": 101
    },
    {
      "epoch": 0.05872193436960276,
      "grad_norm": 7.877676010131836,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 4.8526,
      "step": 102
    },
    {
      "epoch": 0.059297639608520435,
      "grad_norm": 5.773808479309082,
      "learning_rate": 4.08e-05,
      "loss": 5.033,
      "step": 103
    },
    {
      "epoch": 0.059873344847438115,
      "grad_norm": 6.092824935913086,
      "learning_rate": 4.12e-05,
      "loss": 4.8936,
      "step": 104
    },
    {
      "epoch": 0.06044905008635579,
      "grad_norm": 5.934675693511963,
      "learning_rate": 4.16e-05,
      "loss": 4.4764,
      "step": 105
    },
    {
      "epoch": 0.06102475532527346,
      "grad_norm": 5.622652530670166,
      "learning_rate": 4.2e-05,
      "loss": 5.1344,
      "step": 106
    },
    {
      "epoch": 0.061600460564191134,
      "grad_norm": 7.697418212890625,
      "learning_rate": 4.24e-05,
      "loss": 5.2087,
      "step": 107
    },
    {
      "epoch": 0.06217616580310881,
      "grad_norm": 5.204082489013672,
      "learning_rate": 4.2800000000000004e-05,
      "loss": 4.6294,
      "step": 108
    },
    {
      "epoch": 0.06275187104202648,
      "grad_norm": 6.288537979125977,
      "learning_rate": 4.32e-05,
      "loss": 5.3009,
      "step": 109
    },
    {
      "epoch": 0.06332757628094415,
      "grad_norm": 6.717288017272949,
      "learning_rate": 4.36e-05,
      "loss": 5.5392,
      "step": 110
    },
    {
      "epoch": 0.06390328151986183,
      "grad_norm": 5.432399272918701,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 4.3602,
      "step": 111
    },
    {
      "epoch": 0.0644789867587795,
      "grad_norm": 6.823062896728516,
      "learning_rate": 4.44e-05,
      "loss": 5.7343,
      "step": 112
    },
    {
      "epoch": 0.06505469199769717,
      "grad_norm": 6.532074928283691,
      "learning_rate": 4.4800000000000005e-05,
      "loss": 5.0605,
      "step": 113
    },
    {
      "epoch": 0.06563039723661486,
      "grad_norm": 5.982126712799072,
      "learning_rate": 4.52e-05,
      "loss": 5.2182,
      "step": 114
    },
    {
      "epoch": 0.06620610247553253,
      "grad_norm": 5.759943962097168,
      "learning_rate": 4.5600000000000004e-05,
      "loss": 4.9098,
      "step": 115
    },
    {
      "epoch": 0.0667818077144502,
      "grad_norm": 5.147834300994873,
      "learning_rate": 4.600000000000001e-05,
      "loss": 4.8671,
      "step": 116
    },
    {
      "epoch": 0.06735751295336788,
      "grad_norm": 8.015042304992676,
      "learning_rate": 4.64e-05,
      "loss": 5.7445,
      "step": 117
    },
    {
      "epoch": 0.06793321819228555,
      "grad_norm": 7.161843299865723,
      "learning_rate": 4.6800000000000006e-05,
      "loss": 5.9092,
      "step": 118
    },
    {
      "epoch": 0.06850892343120323,
      "grad_norm": 9.394163131713867,
      "learning_rate": 4.72e-05,
      "loss": 4.7243,
      "step": 119
    },
    {
      "epoch": 0.0690846286701209,
      "grad_norm": 4.96219539642334,
      "learning_rate": 4.76e-05,
      "loss": 4.7233,
      "step": 120
    },
    {
      "epoch": 0.06966033390903857,
      "grad_norm": 6.473387241363525,
      "learning_rate": 4.8e-05,
      "loss": 5.1295,
      "step": 121
    },
    {
      "epoch": 0.07023603914795624,
      "grad_norm": 6.797422885894775,
      "learning_rate": 4.8400000000000004e-05,
      "loss": 4.7697,
      "step": 122
    },
    {
      "epoch": 0.07081174438687392,
      "grad_norm": 6.656020641326904,
      "learning_rate": 4.88e-05,
      "loss": 5.2377,
      "step": 123
    },
    {
      "epoch": 0.07138744962579159,
      "grad_norm": 5.552718639373779,
      "learning_rate": 4.92e-05,
      "loss": 4.4741,
      "step": 124
    },
    {
      "epoch": 0.07196315486470926,
      "grad_norm": 6.101820468902588,
      "learning_rate": 4.96e-05,
      "loss": 4.4192,
      "step": 125
    },
    {
      "epoch": 0.07253886010362694,
      "grad_norm": 7.695935249328613,
      "learning_rate": 5e-05,
      "loss": 5.4128,
      "step": 126
    },
    {
      "epoch": 0.07311456534254462,
      "grad_norm": 6.9946208000183105,
      "learning_rate": 5.0400000000000005e-05,
      "loss": 5.4829,
      "step": 127
    },
    {
      "epoch": 0.0736902705814623,
      "grad_norm": 16.10480308532715,
      "learning_rate": 5.08e-05,
      "loss": 4.6945,
      "step": 128
    },
    {
      "epoch": 0.07426597582037997,
      "grad_norm": 5.313148021697998,
      "learning_rate": 5.1200000000000004e-05,
      "loss": 4.2429,
      "step": 129
    },
    {
      "epoch": 0.07484168105929764,
      "grad_norm": 5.506260871887207,
      "learning_rate": 5.16e-05,
      "loss": 4.7241,
      "step": 130
    },
    {
      "epoch": 0.07541738629821532,
      "grad_norm": 5.655925273895264,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 5.4156,
      "step": 131
    },
    {
      "epoch": 0.07599309153713299,
      "grad_norm": 6.528857231140137,
      "learning_rate": 5.2400000000000007e-05,
      "loss": 5.3606,
      "step": 132
    },
    {
      "epoch": 0.07656879677605066,
      "grad_norm": 5.360299110412598,
      "learning_rate": 5.28e-05,
      "loss": 5.0686,
      "step": 133
    },
    {
      "epoch": 0.07714450201496834,
      "grad_norm": 5.301785945892334,
      "learning_rate": 5.3200000000000006e-05,
      "loss": 4.845,
      "step": 134
    },
    {
      "epoch": 0.07772020725388601,
      "grad_norm": 4.986385345458984,
      "learning_rate": 5.360000000000001e-05,
      "loss": 5.1493,
      "step": 135
    },
    {
      "epoch": 0.07829591249280368,
      "grad_norm": 5.200460433959961,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 4.781,
      "step": 136
    },
    {
      "epoch": 0.07887161773172136,
      "grad_norm": 7.154032230377197,
      "learning_rate": 5.440000000000001e-05,
      "loss": 5.8801,
      "step": 137
    },
    {
      "epoch": 0.07944732297063903,
      "grad_norm": 4.641168117523193,
      "learning_rate": 5.4800000000000004e-05,
      "loss": 5.1929,
      "step": 138
    },
    {
      "epoch": 0.0800230282095567,
      "grad_norm": 4.8809123039245605,
      "learning_rate": 5.520000000000001e-05,
      "loss": 5.0221,
      "step": 139
    },
    {
      "epoch": 0.08059873344847437,
      "grad_norm": 5.0507402420043945,
      "learning_rate": 5.560000000000001e-05,
      "loss": 4.8543,
      "step": 140
    },
    {
      "epoch": 0.08117443868739206,
      "grad_norm": 6.459733963012695,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 5.051,
      "step": 141
    },
    {
      "epoch": 0.08175014392630973,
      "grad_norm": 6.107847690582275,
      "learning_rate": 5.6399999999999995e-05,
      "loss": 4.8338,
      "step": 142
    },
    {
      "epoch": 0.08232584916522741,
      "grad_norm": 6.28361701965332,
      "learning_rate": 5.68e-05,
      "loss": 5.1373,
      "step": 143
    },
    {
      "epoch": 0.08290155440414508,
      "grad_norm": 4.957414627075195,
      "learning_rate": 5.72e-05,
      "loss": 4.8154,
      "step": 144
    },
    {
      "epoch": 0.08347725964306275,
      "grad_norm": 4.774332046508789,
      "learning_rate": 5.76e-05,
      "loss": 4.7262,
      "step": 145
    },
    {
      "epoch": 0.08405296488198043,
      "grad_norm": 7.41762113571167,
      "learning_rate": 5.8e-05,
      "loss": 5.5137,
      "step": 146
    },
    {
      "epoch": 0.0846286701208981,
      "grad_norm": 7.484424591064453,
      "learning_rate": 5.8399999999999997e-05,
      "loss": 5.766,
      "step": 147
    },
    {
      "epoch": 0.08520437535981577,
      "grad_norm": 4.917182922363281,
      "learning_rate": 5.88e-05,
      "loss": 5.0193,
      "step": 148
    },
    {
      "epoch": 0.08578008059873345,
      "grad_norm": 4.608645915985107,
      "learning_rate": 5.92e-05,
      "loss": 5.0873,
      "step": 149
    },
    {
      "epoch": 0.08635578583765112,
      "grad_norm": 6.5947794914245605,
      "learning_rate": 5.96e-05,
      "loss": 4.9855,
      "step": 150
    },
    {
      "epoch": 0.08693149107656879,
      "grad_norm": 3.8302507400512695,
      "learning_rate": 6e-05,
      "loss": 3.7953,
      "step": 151
    },
    {
      "epoch": 0.08750719631548647,
      "grad_norm": 3.6352171897888184,
      "learning_rate": 6.04e-05,
      "loss": 4.1647,
      "step": 152
    },
    {
      "epoch": 0.08808290155440414,
      "grad_norm": 4.818563461303711,
      "learning_rate": 6.08e-05,
      "loss": 4.2128,
      "step": 153
    },
    {
      "epoch": 0.08865860679332183,
      "grad_norm": 7.7323503494262695,
      "learning_rate": 6.12e-05,
      "loss": 5.4562,
      "step": 154
    },
    {
      "epoch": 0.0892343120322395,
      "grad_norm": 5.785284996032715,
      "learning_rate": 6.16e-05,
      "loss": 4.8956,
      "step": 155
    },
    {
      "epoch": 0.08981001727115717,
      "grad_norm": 6.181385040283203,
      "learning_rate": 6.2e-05,
      "loss": 5.2373,
      "step": 156
    },
    {
      "epoch": 0.09038572251007485,
      "grad_norm": 6.015028476715088,
      "learning_rate": 6.24e-05,
      "loss": 4.3663,
      "step": 157
    },
    {
      "epoch": 0.09096142774899252,
      "grad_norm": 4.41657829284668,
      "learning_rate": 6.280000000000001e-05,
      "loss": 4.5991,
      "step": 158
    },
    {
      "epoch": 0.09153713298791019,
      "grad_norm": 6.5107622146606445,
      "learning_rate": 6.32e-05,
      "loss": 4.8784,
      "step": 159
    },
    {
      "epoch": 0.09211283822682786,
      "grad_norm": 4.11070442199707,
      "learning_rate": 6.36e-05,
      "loss": 4.6766,
      "step": 160
    },
    {
      "epoch": 0.09268854346574554,
      "grad_norm": 8.204343795776367,
      "learning_rate": 6.400000000000001e-05,
      "loss": 5.5088,
      "step": 161
    },
    {
      "epoch": 0.09326424870466321,
      "grad_norm": 3.9389288425445557,
      "learning_rate": 6.440000000000001e-05,
      "loss": 4.3476,
      "step": 162
    },
    {
      "epoch": 0.09383995394358088,
      "grad_norm": 5.597643852233887,
      "learning_rate": 6.48e-05,
      "loss": 4.9976,
      "step": 163
    },
    {
      "epoch": 0.09441565918249856,
      "grad_norm": 8.994287490844727,
      "learning_rate": 6.52e-05,
      "loss": 5.5959,
      "step": 164
    },
    {
      "epoch": 0.09499136442141623,
      "grad_norm": 5.60779333114624,
      "learning_rate": 6.560000000000001e-05,
      "loss": 4.6283,
      "step": 165
    },
    {
      "epoch": 0.0955670696603339,
      "grad_norm": 4.319982528686523,
      "learning_rate": 6.6e-05,
      "loss": 4.041,
      "step": 166
    },
    {
      "epoch": 0.09614277489925158,
      "grad_norm": 5.684337615966797,
      "learning_rate": 6.64e-05,
      "loss": 4.8941,
      "step": 167
    },
    {
      "epoch": 0.09671848013816926,
      "grad_norm": 3.872518539428711,
      "learning_rate": 6.680000000000001e-05,
      "loss": 4.2242,
      "step": 168
    },
    {
      "epoch": 0.09729418537708694,
      "grad_norm": 4.826557636260986,
      "learning_rate": 6.720000000000001e-05,
      "loss": 4.8546,
      "step": 169
    },
    {
      "epoch": 0.09786989061600461,
      "grad_norm": 4.660156726837158,
      "learning_rate": 6.76e-05,
      "loss": 4.3797,
      "step": 170
    },
    {
      "epoch": 0.09844559585492228,
      "grad_norm": 4.616059303283691,
      "learning_rate": 6.800000000000001e-05,
      "loss": 4.7293,
      "step": 171
    },
    {
      "epoch": 0.09902130109383996,
      "grad_norm": 7.685507774353027,
      "learning_rate": 6.840000000000001e-05,
      "loss": 5.6251,
      "step": 172
    },
    {
      "epoch": 0.09959700633275763,
      "grad_norm": 7.424576282501221,
      "learning_rate": 6.879999999999999e-05,
      "loss": 4.8253,
      "step": 173
    },
    {
      "epoch": 0.1001727115716753,
      "grad_norm": 4.379521369934082,
      "learning_rate": 6.92e-05,
      "loss": 4.5287,
      "step": 174
    },
    {
      "epoch": 0.10074841681059298,
      "grad_norm": 4.753964424133301,
      "learning_rate": 6.96e-05,
      "loss": 4.5554,
      "step": 175
    },
    {
      "epoch": 0.10132412204951065,
      "grad_norm": 4.559609413146973,
      "learning_rate": 7e-05,
      "loss": 4.5615,
      "step": 176
    },
    {
      "epoch": 0.10189982728842832,
      "grad_norm": 5.178406238555908,
      "learning_rate": 7.04e-05,
      "loss": 4.6344,
      "step": 177
    },
    {
      "epoch": 0.102475532527346,
      "grad_norm": 7.4183526039123535,
      "learning_rate": 7.08e-05,
      "loss": 4.5451,
      "step": 178
    },
    {
      "epoch": 0.10305123776626367,
      "grad_norm": 5.832037448883057,
      "learning_rate": 7.12e-05,
      "loss": 4.7097,
      "step": 179
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 4.9681925773620605,
      "learning_rate": 7.16e-05,
      "loss": 4.6288,
      "step": 180
    },
    {
      "epoch": 0.10420264824409903,
      "grad_norm": 4.886664867401123,
      "learning_rate": 7.2e-05,
      "loss": 4.7019,
      "step": 181
    },
    {
      "epoch": 0.1047783534830167,
      "grad_norm": 4.668741226196289,
      "learning_rate": 7.24e-05,
      "loss": 4.4534,
      "step": 182
    },
    {
      "epoch": 0.10535405872193437,
      "grad_norm": 7.459389686584473,
      "learning_rate": 7.280000000000001e-05,
      "loss": 5.4758,
      "step": 183
    },
    {
      "epoch": 0.10592976396085205,
      "grad_norm": 31.545869827270508,
      "learning_rate": 7.32e-05,
      "loss": 6.179,
      "step": 184
    },
    {
      "epoch": 0.10650546919976972,
      "grad_norm": 9.739182472229004,
      "learning_rate": 7.36e-05,
      "loss": 4.9662,
      "step": 185
    },
    {
      "epoch": 0.1070811744386874,
      "grad_norm": 4.12076997756958,
      "learning_rate": 7.4e-05,
      "loss": 3.88,
      "step": 186
    },
    {
      "epoch": 0.10765687967760507,
      "grad_norm": 5.808717727661133,
      "learning_rate": 7.44e-05,
      "loss": 4.6157,
      "step": 187
    },
    {
      "epoch": 0.10823258491652274,
      "grad_norm": 3.6208741664886475,
      "learning_rate": 7.48e-05,
      "loss": 3.9156,
      "step": 188
    },
    {
      "epoch": 0.10880829015544041,
      "grad_norm": 4.674955368041992,
      "learning_rate": 7.52e-05,
      "loss": 4.4751,
      "step": 189
    },
    {
      "epoch": 0.10938399539435809,
      "grad_norm": 5.331599235534668,
      "learning_rate": 7.560000000000001e-05,
      "loss": 4.3887,
      "step": 190
    },
    {
      "epoch": 0.10995970063327576,
      "grad_norm": 5.1405534744262695,
      "learning_rate": 7.6e-05,
      "loss": 4.9114,
      "step": 191
    },
    {
      "epoch": 0.11053540587219343,
      "grad_norm": 3.7066593170166016,
      "learning_rate": 7.64e-05,
      "loss": 3.8948,
      "step": 192
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 5.185431003570557,
      "learning_rate": 7.680000000000001e-05,
      "loss": 4.232,
      "step": 193
    },
    {
      "epoch": 0.11168681635002879,
      "grad_norm": 4.900607585906982,
      "learning_rate": 7.72e-05,
      "loss": 4.667,
      "step": 194
    },
    {
      "epoch": 0.11226252158894647,
      "grad_norm": 5.091091632843018,
      "learning_rate": 7.76e-05,
      "loss": 4.3946,
      "step": 195
    },
    {
      "epoch": 0.11283822682786414,
      "grad_norm": 4.859619617462158,
      "learning_rate": 7.800000000000001e-05,
      "loss": 4.6306,
      "step": 196
    },
    {
      "epoch": 0.11341393206678181,
      "grad_norm": 3.544200897216797,
      "learning_rate": 7.840000000000001e-05,
      "loss": 4.2118,
      "step": 197
    },
    {
      "epoch": 0.11398963730569948,
      "grad_norm": 8.28862190246582,
      "learning_rate": 7.88e-05,
      "loss": 4.4431,
      "step": 198
    },
    {
      "epoch": 0.11456534254461716,
      "grad_norm": 6.373688220977783,
      "learning_rate": 7.920000000000001e-05,
      "loss": 4.7554,
      "step": 199
    },
    {
      "epoch": 0.11514104778353483,
      "grad_norm": 6.8544392585754395,
      "learning_rate": 7.960000000000001e-05,
      "loss": 4.8723,
      "step": 200
    },
    {
      "epoch": 0.1157167530224525,
      "grad_norm": 7.207869052886963,
      "learning_rate": 8e-05,
      "loss": 4.1096,
      "step": 201
    },
    {
      "epoch": 0.11629245826137018,
      "grad_norm": 4.9073333740234375,
      "learning_rate": 8.04e-05,
      "loss": 3.6834,
      "step": 202
    },
    {
      "epoch": 0.11686816350028785,
      "grad_norm": 6.523554801940918,
      "learning_rate": 8.080000000000001e-05,
      "loss": 4.4934,
      "step": 203
    },
    {
      "epoch": 0.11744386873920552,
      "grad_norm": 9.581537246704102,
      "learning_rate": 8.120000000000001e-05,
      "loss": 4.8199,
      "step": 204
    },
    {
      "epoch": 0.1180195739781232,
      "grad_norm": 5.319664001464844,
      "learning_rate": 8.16e-05,
      "loss": 4.0881,
      "step": 205
    },
    {
      "epoch": 0.11859527921704087,
      "grad_norm": 7.609442710876465,
      "learning_rate": 8.2e-05,
      "loss": 5.1011,
      "step": 206
    },
    {
      "epoch": 0.11917098445595854,
      "grad_norm": 5.437283515930176,
      "learning_rate": 8.24e-05,
      "loss": 4.7683,
      "step": 207
    },
    {
      "epoch": 0.11974668969487623,
      "grad_norm": 9.015962600708008,
      "learning_rate": 8.28e-05,
      "loss": 5.1197,
      "step": 208
    },
    {
      "epoch": 0.1203223949337939,
      "grad_norm": 5.41486120223999,
      "learning_rate": 8.32e-05,
      "loss": 4.2228,
      "step": 209
    },
    {
      "epoch": 0.12089810017271158,
      "grad_norm": 4.068630218505859,
      "learning_rate": 8.36e-05,
      "loss": 3.9683,
      "step": 210
    },
    {
      "epoch": 0.12147380541162925,
      "grad_norm": 4.818974494934082,
      "learning_rate": 8.4e-05,
      "loss": 4.3969,
      "step": 211
    },
    {
      "epoch": 0.12204951065054692,
      "grad_norm": 8.309637069702148,
      "learning_rate": 8.44e-05,
      "loss": 4.8983,
      "step": 212
    },
    {
      "epoch": 0.1226252158894646,
      "grad_norm": 5.997379302978516,
      "learning_rate": 8.48e-05,
      "loss": 4.6983,
      "step": 213
    },
    {
      "epoch": 0.12320092112838227,
      "grad_norm": 6.416568279266357,
      "learning_rate": 8.52e-05,
      "loss": 4.6,
      "step": 214
    },
    {
      "epoch": 0.12377662636729994,
      "grad_norm": 5.038214206695557,
      "learning_rate": 8.560000000000001e-05,
      "loss": 4.1803,
      "step": 215
    },
    {
      "epoch": 0.12435233160621761,
      "grad_norm": 5.035988807678223,
      "learning_rate": 8.6e-05,
      "loss": 4.1585,
      "step": 216
    },
    {
      "epoch": 0.12492803684513529,
      "grad_norm": 6.7663726806640625,
      "learning_rate": 8.64e-05,
      "loss": 4.4256,
      "step": 217
    },
    {
      "epoch": 0.12550374208405296,
      "grad_norm": 5.394269943237305,
      "learning_rate": 8.680000000000001e-05,
      "loss": 3.9008,
      "step": 218
    },
    {
      "epoch": 0.12607944732297063,
      "grad_norm": 5.4501800537109375,
      "learning_rate": 8.72e-05,
      "loss": 3.9869,
      "step": 219
    },
    {
      "epoch": 0.1266551525618883,
      "grad_norm": 4.7380170822143555,
      "learning_rate": 8.76e-05,
      "loss": 4.0876,
      "step": 220
    },
    {
      "epoch": 0.12723085780080598,
      "grad_norm": 6.059116840362549,
      "learning_rate": 8.800000000000001e-05,
      "loss": 4.147,
      "step": 221
    },
    {
      "epoch": 0.12780656303972365,
      "grad_norm": 5.5021586418151855,
      "learning_rate": 8.840000000000001e-05,
      "loss": 4.4547,
      "step": 222
    },
    {
      "epoch": 0.12838226827864133,
      "grad_norm": 4.760106563568115,
      "learning_rate": 8.88e-05,
      "loss": 4.075,
      "step": 223
    },
    {
      "epoch": 0.128957973517559,
      "grad_norm": 7.5847649574279785,
      "learning_rate": 8.92e-05,
      "loss": 4.6163,
      "step": 224
    },
    {
      "epoch": 0.12953367875647667,
      "grad_norm": 6.257955074310303,
      "learning_rate": 8.960000000000001e-05,
      "loss": 4.6043,
      "step": 225
    },
    {
      "epoch": 0.13010938399539435,
      "grad_norm": 7.368046283721924,
      "learning_rate": 9e-05,
      "loss": 4.7961,
      "step": 226
    },
    {
      "epoch": 0.13068508923431202,
      "grad_norm": 4.385096549987793,
      "learning_rate": 9.04e-05,
      "loss": 4.1968,
      "step": 227
    },
    {
      "epoch": 0.13126079447322972,
      "grad_norm": 6.34293794631958,
      "learning_rate": 9.080000000000001e-05,
      "loss": 4.3076,
      "step": 228
    },
    {
      "epoch": 0.1318364997121474,
      "grad_norm": 6.403743267059326,
      "learning_rate": 9.120000000000001e-05,
      "loss": 3.8917,
      "step": 229
    },
    {
      "epoch": 0.13241220495106507,
      "grad_norm": 6.792156219482422,
      "learning_rate": 9.16e-05,
      "loss": 3.9843,
      "step": 230
    },
    {
      "epoch": 0.13298791018998274,
      "grad_norm": 8.062408447265625,
      "learning_rate": 9.200000000000001e-05,
      "loss": 4.2562,
      "step": 231
    },
    {
      "epoch": 0.1335636154289004,
      "grad_norm": 8.513936042785645,
      "learning_rate": 9.240000000000001e-05,
      "loss": 4.6536,
      "step": 232
    },
    {
      "epoch": 0.13413932066781808,
      "grad_norm": 5.92789363861084,
      "learning_rate": 9.28e-05,
      "loss": 4.104,
      "step": 233
    },
    {
      "epoch": 0.13471502590673576,
      "grad_norm": 44.009300231933594,
      "learning_rate": 9.320000000000002e-05,
      "loss": 4.8297,
      "step": 234
    },
    {
      "epoch": 0.13529073114565343,
      "grad_norm": 5.342921257019043,
      "learning_rate": 9.360000000000001e-05,
      "loss": 4.0662,
      "step": 235
    },
    {
      "epoch": 0.1358664363845711,
      "grad_norm": 5.618771076202393,
      "learning_rate": 9.4e-05,
      "loss": 4.1692,
      "step": 236
    },
    {
      "epoch": 0.13644214162348878,
      "grad_norm": 6.6655473709106445,
      "learning_rate": 9.44e-05,
      "loss": 4.2759,
      "step": 237
    },
    {
      "epoch": 0.13701784686240645,
      "grad_norm": 6.415508270263672,
      "learning_rate": 9.48e-05,
      "loss": 4.025,
      "step": 238
    },
    {
      "epoch": 0.13759355210132412,
      "grad_norm": 62.65280532836914,
      "learning_rate": 9.52e-05,
      "loss": 5.3187,
      "step": 239
    },
    {
      "epoch": 0.1381692573402418,
      "grad_norm": 5.9870147705078125,
      "learning_rate": 9.56e-05,
      "loss": 4.3549,
      "step": 240
    },
    {
      "epoch": 0.13874496257915947,
      "grad_norm": 6.323814868927002,
      "learning_rate": 9.6e-05,
      "loss": 4.0618,
      "step": 241
    },
    {
      "epoch": 0.13932066781807714,
      "grad_norm": 7.25873327255249,
      "learning_rate": 9.64e-05,
      "loss": 4.6113,
      "step": 242
    },
    {
      "epoch": 0.13989637305699482,
      "grad_norm": 6.708962440490723,
      "learning_rate": 9.680000000000001e-05,
      "loss": 4.2734,
      "step": 243
    },
    {
      "epoch": 0.1404720782959125,
      "grad_norm": 6.766256332397461,
      "learning_rate": 9.72e-05,
      "loss": 3.8169,
      "step": 244
    },
    {
      "epoch": 0.14104778353483016,
      "grad_norm": 9.25779914855957,
      "learning_rate": 9.76e-05,
      "loss": 4.0823,
      "step": 245
    },
    {
      "epoch": 0.14162348877374784,
      "grad_norm": 6.24402379989624,
      "learning_rate": 9.8e-05,
      "loss": 3.9761,
      "step": 246
    },
    {
      "epoch": 0.1421991940126655,
      "grad_norm": 4.627258777618408,
      "learning_rate": 9.84e-05,
      "loss": 3.3376,
      "step": 247
    },
    {
      "epoch": 0.14277489925158318,
      "grad_norm": 6.5364766120910645,
      "learning_rate": 9.88e-05,
      "loss": 3.9101,
      "step": 248
    },
    {
      "epoch": 0.14335060449050085,
      "grad_norm": 6.722381591796875,
      "learning_rate": 9.92e-05,
      "loss": 4.2916,
      "step": 249
    },
    {
      "epoch": 0.14392630972941853,
      "grad_norm": 7.2800493240356445,
      "learning_rate": 9.960000000000001e-05,
      "loss": 4.1714,
      "step": 250
    },
    {
      "epoch": 0.1445020149683362,
      "grad_norm": 9.137832641601562,
      "learning_rate": 0.0001,
      "loss": 3.9733,
      "step": 251
    },
    {
      "epoch": 0.14507772020725387,
      "grad_norm": 5.290084362030029,
      "learning_rate": 0.0001004,
      "loss": 3.8465,
      "step": 252
    },
    {
      "epoch": 0.14565342544617155,
      "grad_norm": 7.146475791931152,
      "learning_rate": 0.00010080000000000001,
      "loss": 4.154,
      "step": 253
    },
    {
      "epoch": 0.14622913068508925,
      "grad_norm": 5.462000370025635,
      "learning_rate": 0.00010120000000000001,
      "loss": 3.8403,
      "step": 254
    },
    {
      "epoch": 0.14680483592400692,
      "grad_norm": 8.053996086120605,
      "learning_rate": 0.0001016,
      "loss": 4.224,
      "step": 255
    },
    {
      "epoch": 0.1473805411629246,
      "grad_norm": 56.904518127441406,
      "learning_rate": 0.00010200000000000001,
      "loss": 5.3512,
      "step": 256
    },
    {
      "epoch": 0.14795624640184227,
      "grad_norm": 67.7396469116211,
      "learning_rate": 0.00010240000000000001,
      "loss": 4.136,
      "step": 257
    },
    {
      "epoch": 0.14853195164075994,
      "grad_norm": 5.19423770904541,
      "learning_rate": 0.0001028,
      "loss": 3.6272,
      "step": 258
    },
    {
      "epoch": 0.1491076568796776,
      "grad_norm": 6.946446418762207,
      "learning_rate": 0.0001032,
      "loss": 3.7617,
      "step": 259
    },
    {
      "epoch": 0.1496833621185953,
      "grad_norm": 6.839754104614258,
      "learning_rate": 0.00010360000000000001,
      "loss": 4.2895,
      "step": 260
    },
    {
      "epoch": 0.15025906735751296,
      "grad_norm": 7.3253254890441895,
      "learning_rate": 0.00010400000000000001,
      "loss": 4.0997,
      "step": 261
    },
    {
      "epoch": 0.15083477259643063,
      "grad_norm": 6.981521129608154,
      "learning_rate": 0.0001044,
      "loss": 3.4663,
      "step": 262
    },
    {
      "epoch": 0.1514104778353483,
      "grad_norm": 6.424066543579102,
      "learning_rate": 0.00010480000000000001,
      "loss": 4.0914,
      "step": 263
    },
    {
      "epoch": 0.15198618307426598,
      "grad_norm": 6.7790398597717285,
      "learning_rate": 0.00010520000000000001,
      "loss": 4.0818,
      "step": 264
    },
    {
      "epoch": 0.15256188831318365,
      "grad_norm": 7.887113094329834,
      "learning_rate": 0.0001056,
      "loss": 4.3784,
      "step": 265
    },
    {
      "epoch": 0.15313759355210133,
      "grad_norm": 8.3016939163208,
      "learning_rate": 0.00010600000000000002,
      "loss": 3.7843,
      "step": 266
    },
    {
      "epoch": 0.153713298791019,
      "grad_norm": 10.073237419128418,
      "learning_rate": 0.00010640000000000001,
      "loss": 4.0118,
      "step": 267
    },
    {
      "epoch": 0.15428900402993667,
      "grad_norm": 6.9664106369018555,
      "learning_rate": 0.00010680000000000001,
      "loss": 3.8644,
      "step": 268
    },
    {
      "epoch": 0.15486470926885434,
      "grad_norm": 8.479534149169922,
      "learning_rate": 0.00010720000000000002,
      "loss": 3.7009,
      "step": 269
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 8.317602157592773,
      "learning_rate": 0.00010760000000000001,
      "loss": 3.7018,
      "step": 270
    },
    {
      "epoch": 0.1560161197466897,
      "grad_norm": 6.020889759063721,
      "learning_rate": 0.00010800000000000001,
      "loss": 3.656,
      "step": 271
    },
    {
      "epoch": 0.15659182498560736,
      "grad_norm": 7.147673606872559,
      "learning_rate": 0.00010840000000000002,
      "loss": 3.9216,
      "step": 272
    },
    {
      "epoch": 0.15716753022452504,
      "grad_norm": 5.485556125640869,
      "learning_rate": 0.00010880000000000002,
      "loss": 3.4732,
      "step": 273
    },
    {
      "epoch": 0.1577432354634427,
      "grad_norm": 7.432086944580078,
      "learning_rate": 0.00010920000000000001,
      "loss": 3.423,
      "step": 274
    },
    {
      "epoch": 0.15831894070236038,
      "grad_norm": 6.897833824157715,
      "learning_rate": 0.00010960000000000001,
      "loss": 3.6169,
      "step": 275
    },
    {
      "epoch": 0.15889464594127806,
      "grad_norm": 7.707437992095947,
      "learning_rate": 0.00011000000000000002,
      "loss": 3.6883,
      "step": 276
    },
    {
      "epoch": 0.15947035118019573,
      "grad_norm": 5.546234607696533,
      "learning_rate": 0.00011040000000000001,
      "loss": 3.8388,
      "step": 277
    },
    {
      "epoch": 0.1600460564191134,
      "grad_norm": 10.001431465148926,
      "learning_rate": 0.00011080000000000001,
      "loss": 3.372,
      "step": 278
    },
    {
      "epoch": 0.16062176165803108,
      "grad_norm": 8.793180465698242,
      "learning_rate": 0.00011120000000000002,
      "loss": 3.7929,
      "step": 279
    },
    {
      "epoch": 0.16119746689694875,
      "grad_norm": 8.189177513122559,
      "learning_rate": 0.00011160000000000002,
      "loss": 4.0091,
      "step": 280
    },
    {
      "epoch": 0.16177317213586645,
      "grad_norm": 6.998697280883789,
      "learning_rate": 0.00011200000000000001,
      "loss": 3.648,
      "step": 281
    },
    {
      "epoch": 0.16234887737478412,
      "grad_norm": 8.115317344665527,
      "learning_rate": 0.00011240000000000002,
      "loss": 4.0327,
      "step": 282
    },
    {
      "epoch": 0.1629245826137018,
      "grad_norm": 7.597106456756592,
      "learning_rate": 0.00011279999999999999,
      "loss": 3.7811,
      "step": 283
    },
    {
      "epoch": 0.16350028785261947,
      "grad_norm": 6.518374443054199,
      "learning_rate": 0.0001132,
      "loss": 3.3359,
      "step": 284
    },
    {
      "epoch": 0.16407599309153714,
      "grad_norm": 6.962795257568359,
      "learning_rate": 0.0001136,
      "loss": 3.3726,
      "step": 285
    },
    {
      "epoch": 0.16465169833045482,
      "grad_norm": 8.1845703125,
      "learning_rate": 0.00011399999999999999,
      "loss": 4.0042,
      "step": 286
    },
    {
      "epoch": 0.1652274035693725,
      "grad_norm": 6.869271755218506,
      "learning_rate": 0.0001144,
      "loss": 3.4989,
      "step": 287
    },
    {
      "epoch": 0.16580310880829016,
      "grad_norm": 12.261098861694336,
      "learning_rate": 0.0001148,
      "loss": 4.1045,
      "step": 288
    },
    {
      "epoch": 0.16637881404720783,
      "grad_norm": 6.912962913513184,
      "learning_rate": 0.0001152,
      "loss": 3.6853,
      "step": 289
    },
    {
      "epoch": 0.1669545192861255,
      "grad_norm": 8.545379638671875,
      "learning_rate": 0.00011559999999999999,
      "loss": 3.8903,
      "step": 290
    },
    {
      "epoch": 0.16753022452504318,
      "grad_norm": 15.040228843688965,
      "learning_rate": 0.000116,
      "loss": 3.4079,
      "step": 291
    },
    {
      "epoch": 0.16810592976396085,
      "grad_norm": 7.038132667541504,
      "learning_rate": 0.0001164,
      "loss": 3.7119,
      "step": 292
    },
    {
      "epoch": 0.16868163500287853,
      "grad_norm": 6.259817123413086,
      "learning_rate": 0.00011679999999999999,
      "loss": 3.4931,
      "step": 293
    },
    {
      "epoch": 0.1692573402417962,
      "grad_norm": 6.947351455688477,
      "learning_rate": 0.0001172,
      "loss": 3.677,
      "step": 294
    },
    {
      "epoch": 0.16983304548071387,
      "grad_norm": 14.260014533996582,
      "learning_rate": 0.0001176,
      "loss": 3.9591,
      "step": 295
    },
    {
      "epoch": 0.17040875071963155,
      "grad_norm": 6.70070743560791,
      "learning_rate": 0.000118,
      "loss": 3.2433,
      "step": 296
    },
    {
      "epoch": 0.17098445595854922,
      "grad_norm": 11.697699546813965,
      "learning_rate": 0.0001184,
      "loss": 4.0909,
      "step": 297
    },
    {
      "epoch": 0.1715601611974669,
      "grad_norm": 10.029029846191406,
      "learning_rate": 0.0001188,
      "loss": 3.5743,
      "step": 298
    },
    {
      "epoch": 0.17213586643638457,
      "grad_norm": 6.6930365562438965,
      "learning_rate": 0.0001192,
      "loss": 3.2007,
      "step": 299
    },
    {
      "epoch": 0.17271157167530224,
      "grad_norm": 21.772619247436523,
      "learning_rate": 0.00011960000000000001,
      "loss": 3.8505,
      "step": 300
    },
    {
      "epoch": 0.1732872769142199,
      "grad_norm": 9.126256942749023,
      "learning_rate": 0.00012,
      "loss": 3.5777,
      "step": 301
    },
    {
      "epoch": 0.17386298215313759,
      "grad_norm": 7.574469566345215,
      "learning_rate": 0.0001204,
      "loss": 3.5329,
      "step": 302
    },
    {
      "epoch": 0.17443868739205526,
      "grad_norm": 6.436075687408447,
      "learning_rate": 0.0001208,
      "loss": 3.279,
      "step": 303
    },
    {
      "epoch": 0.17501439263097293,
      "grad_norm": 5.945929527282715,
      "learning_rate": 0.0001212,
      "loss": 3.4338,
      "step": 304
    },
    {
      "epoch": 0.1755900978698906,
      "grad_norm": 5.7057785987854,
      "learning_rate": 0.0001216,
      "loss": 3.2369,
      "step": 305
    },
    {
      "epoch": 0.17616580310880828,
      "grad_norm": 9.411810874938965,
      "learning_rate": 0.000122,
      "loss": 3.5364,
      "step": 306
    },
    {
      "epoch": 0.17674150834772595,
      "grad_norm": 8.872260093688965,
      "learning_rate": 0.0001224,
      "loss": 3.7803,
      "step": 307
    },
    {
      "epoch": 0.17731721358664365,
      "grad_norm": 46.1115837097168,
      "learning_rate": 0.0001228,
      "loss": 3.7188,
      "step": 308
    },
    {
      "epoch": 0.17789291882556132,
      "grad_norm": 48.33805465698242,
      "learning_rate": 0.0001232,
      "loss": 3.7491,
      "step": 309
    },
    {
      "epoch": 0.178468624064479,
      "grad_norm": 7.272097587585449,
      "learning_rate": 0.0001236,
      "loss": 3.559,
      "step": 310
    },
    {
      "epoch": 0.17904432930339667,
      "grad_norm": 7.471408367156982,
      "learning_rate": 0.000124,
      "loss": 3.6014,
      "step": 311
    },
    {
      "epoch": 0.17962003454231434,
      "grad_norm": 11.095893859863281,
      "learning_rate": 0.00012440000000000002,
      "loss": 3.5741,
      "step": 312
    },
    {
      "epoch": 0.18019573978123202,
      "grad_norm": 8.782601356506348,
      "learning_rate": 0.0001248,
      "loss": 3.2475,
      "step": 313
    },
    {
      "epoch": 0.1807714450201497,
      "grad_norm": 7.485610485076904,
      "learning_rate": 0.0001252,
      "loss": 3.0304,
      "step": 314
    },
    {
      "epoch": 0.18134715025906736,
      "grad_norm": 7.794425964355469,
      "learning_rate": 0.00012560000000000002,
      "loss": 2.9428,
      "step": 315
    },
    {
      "epoch": 0.18192285549798504,
      "grad_norm": 6.470662593841553,
      "learning_rate": 0.000126,
      "loss": 3.4341,
      "step": 316
    },
    {
      "epoch": 0.1824985607369027,
      "grad_norm": 10.054426193237305,
      "learning_rate": 0.0001264,
      "loss": 2.941,
      "step": 317
    },
    {
      "epoch": 0.18307426597582038,
      "grad_norm": 93.38629150390625,
      "learning_rate": 0.00012680000000000002,
      "loss": 4.2291,
      "step": 318
    },
    {
      "epoch": 0.18364997121473806,
      "grad_norm": 9.805968284606934,
      "learning_rate": 0.0001272,
      "loss": 3.0641,
      "step": 319
    },
    {
      "epoch": 0.18422567645365573,
      "grad_norm": 6.104334831237793,
      "learning_rate": 0.0001276,
      "loss": 3.0856,
      "step": 320
    },
    {
      "epoch": 0.1848013816925734,
      "grad_norm": 8.24195384979248,
      "learning_rate": 0.00012800000000000002,
      "loss": 3.0774,
      "step": 321
    },
    {
      "epoch": 0.18537708693149108,
      "grad_norm": 6.327628135681152,
      "learning_rate": 0.0001284,
      "loss": 3.0826,
      "step": 322
    },
    {
      "epoch": 0.18595279217040875,
      "grad_norm": 11.529990196228027,
      "learning_rate": 0.00012880000000000001,
      "loss": 3.7882,
      "step": 323
    },
    {
      "epoch": 0.18652849740932642,
      "grad_norm": 9.700762748718262,
      "learning_rate": 0.00012920000000000002,
      "loss": 3.4958,
      "step": 324
    },
    {
      "epoch": 0.1871042026482441,
      "grad_norm": 10.289152145385742,
      "learning_rate": 0.0001296,
      "loss": 3.3652,
      "step": 325
    },
    {
      "epoch": 0.18767990788716177,
      "grad_norm": 6.888269901275635,
      "learning_rate": 0.00013000000000000002,
      "loss": 3.1086,
      "step": 326
    },
    {
      "epoch": 0.18825561312607944,
      "grad_norm": 9.220719337463379,
      "learning_rate": 0.0001304,
      "loss": 3.5314,
      "step": 327
    },
    {
      "epoch": 0.1888313183649971,
      "grad_norm": 9.044048309326172,
      "learning_rate": 0.0001308,
      "loss": 2.943,
      "step": 328
    },
    {
      "epoch": 0.1894070236039148,
      "grad_norm": 11.338268280029297,
      "learning_rate": 0.00013120000000000002,
      "loss": 3.4617,
      "step": 329
    },
    {
      "epoch": 0.18998272884283246,
      "grad_norm": 5.949525833129883,
      "learning_rate": 0.0001316,
      "loss": 2.8324,
      "step": 330
    },
    {
      "epoch": 0.19055843408175013,
      "grad_norm": 9.158703804016113,
      "learning_rate": 0.000132,
      "loss": 3.1961,
      "step": 331
    },
    {
      "epoch": 0.1911341393206678,
      "grad_norm": 8.708706855773926,
      "learning_rate": 0.00013240000000000002,
      "loss": 3.1941,
      "step": 332
    },
    {
      "epoch": 0.19170984455958548,
      "grad_norm": 10.610583305358887,
      "learning_rate": 0.0001328,
      "loss": 3.3617,
      "step": 333
    },
    {
      "epoch": 0.19228554979850315,
      "grad_norm": 8.023892402648926,
      "learning_rate": 0.0001332,
      "loss": 3.1775,
      "step": 334
    },
    {
      "epoch": 0.19286125503742085,
      "grad_norm": 7.895623683929443,
      "learning_rate": 0.00013360000000000002,
      "loss": 3.1033,
      "step": 335
    },
    {
      "epoch": 0.19343696027633853,
      "grad_norm": 6.376975059509277,
      "learning_rate": 0.000134,
      "loss": 2.808,
      "step": 336
    },
    {
      "epoch": 0.1940126655152562,
      "grad_norm": 5.185142993927002,
      "learning_rate": 0.00013440000000000001,
      "loss": 2.8337,
      "step": 337
    },
    {
      "epoch": 0.19458837075417387,
      "grad_norm": 6.408693790435791,
      "learning_rate": 0.00013480000000000002,
      "loss": 3.0604,
      "step": 338
    },
    {
      "epoch": 0.19516407599309155,
      "grad_norm": 21.610239028930664,
      "learning_rate": 0.0001352,
      "loss": 3.431,
      "step": 339
    },
    {
      "epoch": 0.19573978123200922,
      "grad_norm": 9.485398292541504,
      "learning_rate": 0.00013560000000000002,
      "loss": 3.2208,
      "step": 340
    },
    {
      "epoch": 0.1963154864709269,
      "grad_norm": 6.460340976715088,
      "learning_rate": 0.00013600000000000003,
      "loss": 2.793,
      "step": 341
    },
    {
      "epoch": 0.19689119170984457,
      "grad_norm": 5.64215612411499,
      "learning_rate": 0.0001364,
      "loss": 2.8589,
      "step": 342
    },
    {
      "epoch": 0.19746689694876224,
      "grad_norm": 6.9033427238464355,
      "learning_rate": 0.00013680000000000002,
      "loss": 3.1031,
      "step": 343
    },
    {
      "epoch": 0.1980426021876799,
      "grad_norm": 5.724493980407715,
      "learning_rate": 0.00013720000000000003,
      "loss": 2.8605,
      "step": 344
    },
    {
      "epoch": 0.19861830742659758,
      "grad_norm": 15.779448509216309,
      "learning_rate": 0.00013759999999999998,
      "loss": 3.2151,
      "step": 345
    },
    {
      "epoch": 0.19919401266551526,
      "grad_norm": 6.960752964019775,
      "learning_rate": 0.000138,
      "loss": 2.8537,
      "step": 346
    },
    {
      "epoch": 0.19976971790443293,
      "grad_norm": 8.871850967407227,
      "learning_rate": 0.0001384,
      "loss": 2.7536,
      "step": 347
    },
    {
      "epoch": 0.2003454231433506,
      "grad_norm": 6.670348644256592,
      "learning_rate": 0.00013879999999999999,
      "loss": 2.9525,
      "step": 348
    }
  ],
  "logging_steps": 1,
  "max_steps": 1737,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 348,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.022631528658895e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}