{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.07216308858019123,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036081544290095615,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00036081544290095615,
      "eval_loss": NaN,
      "eval_runtime": 350.8893,
      "eval_samples_per_second": 13.303,
      "eval_steps_per_second": 3.326,
      "step": 1
    },
    {
      "epoch": 0.0007216308858019123,
      "grad_norm": 0.0,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0010824463287028685,
      "grad_norm": 0.0,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0014432617716038246,
      "grad_norm": 0.0,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0018040772145047808,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.002164892657405737,
      "grad_norm": 0.0,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0025257081003066933,
      "grad_norm": 0.0,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.002886523543207649,
      "grad_norm": 0.0,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0032473389861086056,
      "grad_norm": 0.0,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0036081544290095615,
      "grad_norm": 0.0,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.003968969871910518,
      "grad_norm": 0.0,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.004329785314811474,
      "grad_norm": 0.0,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00469060075771243,
      "grad_norm": 0.0,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0050514162006133866,
      "grad_norm": 0.0,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0054122316435143425,
      "grad_norm": 0.0,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.005773047086415298,
      "grad_norm": 0.0,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.006133862529316254,
      "grad_norm": 0.0,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.006494677972217211,
      "grad_norm": 0.0,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.006855493415118167,
      "grad_norm": 0.0,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.007216308858019123,
      "grad_norm": 0.0,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.007577124300920079,
      "grad_norm": 0.0,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.007937939743821036,
      "grad_norm": 0.0,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.008298755186721992,
      "grad_norm": 0.0,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.008659570629622948,
      "grad_norm": 0.0,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.009020386072523904,
      "grad_norm": 0.0,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.00938120151542486,
      "grad_norm": 0.0,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.009742016958325817,
      "grad_norm": 0.0,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.010102832401226773,
      "grad_norm": 0.0,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.010463647844127729,
      "grad_norm": 0.0,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.010824463287028685,
      "grad_norm": 0.0,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.011185278729929641,
      "grad_norm": 0.0,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.011546094172830597,
      "grad_norm": 0.0,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.011906909615731553,
      "grad_norm": 0.0,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.012267725058632509,
      "grad_norm": 0.0,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.012628540501533466,
      "grad_norm": 0.0,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.012989355944434422,
      "grad_norm": 0.0,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.013350171387335378,
      "grad_norm": 0.0,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.013710986830236334,
      "grad_norm": 0.0,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.01407180227313729,
      "grad_norm": 0.0,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.014432617716038246,
      "grad_norm": 0.0,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.014793433158939202,
      "grad_norm": 0.0,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.015154248601840158,
      "grad_norm": 0.0,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.015515064044741116,
      "grad_norm": 0.0,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.01587587948764207,
      "grad_norm": 0.0,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.016236694930543027,
      "grad_norm": 0.0,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.016597510373443983,
      "grad_norm": 0.0,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.01695832581634494,
      "grad_norm": 0.0,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.017319141259245895,
      "grad_norm": 0.0,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.01767995670214685,
      "grad_norm": 0.0,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.018040772145047807,
      "grad_norm": 0.0,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.018040772145047807,
      "eval_loss": NaN,
      "eval_runtime": 351.9281,
      "eval_samples_per_second": 13.264,
      "eval_steps_per_second": 3.316,
      "step": 50
    },
    {
      "epoch": 0.018401587587948763,
      "grad_norm": 0.0,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.01876240303084972,
      "grad_norm": 0.0,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.019123218473750675,
      "grad_norm": 0.0,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.019484033916651634,
      "grad_norm": 0.0,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.01984484935955259,
      "grad_norm": 0.0,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.020205664802453546,
      "grad_norm": 0.0,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.020566480245354502,
      "grad_norm": 0.0,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.020927295688255458,
      "grad_norm": 0.0,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.021288111131156414,
      "grad_norm": 0.0,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.02164892657405737,
      "grad_norm": 0.0,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.022009742016958326,
      "grad_norm": 0.0,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.022370557459859282,
      "grad_norm": 0.0,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.022731372902760238,
      "grad_norm": 0.0,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.023092188345661194,
      "grad_norm": 0.0,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.02345300378856215,
      "grad_norm": 0.0,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.023813819231463106,
      "grad_norm": 0.0,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.02417463467436406,
      "grad_norm": 0.0,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.024535450117265017,
      "grad_norm": 0.0,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.024896265560165973,
      "grad_norm": 0.0,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.025257081003066933,
      "grad_norm": 0.0,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.02561789644596789,
      "grad_norm": 0.0,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.025978711888868845,
      "grad_norm": 0.0,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.0263395273317698,
      "grad_norm": 0.0,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.026700342774670757,
      "grad_norm": 0.0,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.027061158217571712,
      "grad_norm": 0.0,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.02742197366047267,
      "grad_norm": 0.0,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.027782789103373624,
      "grad_norm": 0.0,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.02814360454627458,
      "grad_norm": 0.0,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.028504419989175536,
      "grad_norm": 0.0,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.028865235432076492,
      "grad_norm": 0.0,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.029226050874977448,
      "grad_norm": 0.0,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.029586866317878404,
      "grad_norm": 0.0,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.02994768176077936,
      "grad_norm": 0.0,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.030308497203680316,
      "grad_norm": 0.0,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.030669312646581275,
      "grad_norm": 0.0,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.03103012808948223,
      "grad_norm": 0.0,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.031390943532383184,
      "grad_norm": 0.0,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.03175175897528414,
      "grad_norm": 0.0,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.032112574418185096,
      "grad_norm": 0.0,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.032473389861086055,
      "grad_norm": 0.0,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.03283420530398701,
      "grad_norm": 0.0,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.03319502074688797,
      "grad_norm": 0.0,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.033555836189788926,
      "grad_norm": 0.0,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.03391665163268988,
      "grad_norm": 0.0,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.03427746707559084,
      "grad_norm": 0.0,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.03463828251849179,
      "grad_norm": 0.0,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.03499909796139275,
      "grad_norm": 0.0,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.0353599134042937,
      "grad_norm": 0.0,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.03572072884719466,
      "grad_norm": 0.0,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.036081544290095614,
      "grad_norm": 0.0,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.036081544290095614,
      "eval_loss": NaN,
      "eval_runtime": 352.0309,
      "eval_samples_per_second": 13.26,
      "eval_steps_per_second": 3.315,
      "step": 100
    },
    {
      "epoch": 0.036442359732996574,
      "grad_norm": 0.0,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.0,
      "step": 101
    },
    {
      "epoch": 0.036803175175897526,
      "grad_norm": 0.0,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.037163990618798486,
      "grad_norm": 0.0,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.0,
      "step": 103
    },
    {
      "epoch": 0.03752480606169944,
      "grad_norm": 0.0,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.0,
      "step": 104
    },
    {
      "epoch": 0.0378856215046004,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.03824643694750135,
      "grad_norm": 0.0,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.0,
      "step": 106
    },
    {
      "epoch": 0.03860725239040231,
      "grad_norm": 0.0,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.0,
      "step": 107
    },
    {
      "epoch": 0.03896806783330327,
      "grad_norm": 0.0,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.03932888327620422,
      "grad_norm": 0.0,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.0,
      "step": 109
    },
    {
      "epoch": 0.03968969871910518,
      "grad_norm": 0.0,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.04005051416200613,
      "grad_norm": 0.0,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.0,
      "step": 111
    },
    {
      "epoch": 0.04041132960490709,
      "grad_norm": 0.0,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.0,
      "step": 112
    },
    {
      "epoch": 0.040772145047808045,
      "grad_norm": 0.0,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.0,
      "step": 113
    },
    {
      "epoch": 0.041132960490709004,
      "grad_norm": 0.0,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0,
      "step": 114
    },
    {
      "epoch": 0.04149377593360996,
      "grad_norm": 0.0,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.041854591376510916,
      "grad_norm": 0.0,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.0,
      "step": 116
    },
    {
      "epoch": 0.04221540681941187,
      "grad_norm": 0.0,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.0,
      "step": 117
    },
    {
      "epoch": 0.04257622226231283,
      "grad_norm": 0.0,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.0,
      "step": 118
    },
    {
      "epoch": 0.04293703770521378,
      "grad_norm": 0.0,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.0,
      "step": 119
    },
    {
      "epoch": 0.04329785314811474,
      "grad_norm": 0.0,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.04365866859101569,
      "grad_norm": 0.0,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.0,
      "step": 121
    },
    {
      "epoch": 0.04401948403391665,
      "grad_norm": 0.0,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.0,
      "step": 122
    },
    {
      "epoch": 0.04438029947681761,
      "grad_norm": 0.0,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0,
      "step": 123
    },
    {
      "epoch": 0.044741114919718564,
      "grad_norm": 0.0,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 124
    },
    {
      "epoch": 0.04510193036261952,
      "grad_norm": 0.0,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.045462745805520476,
      "grad_norm": 0.0,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 0.045823561248421435,
      "grad_norm": 0.0,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.0,
      "step": 127
    },
    {
      "epoch": 0.04618437669132239,
      "grad_norm": 0.0,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0,
      "step": 128
    },
    {
      "epoch": 0.04654519213422335,
      "grad_norm": 0.0,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0,
      "step": 129
    },
    {
      "epoch": 0.0469060075771243,
      "grad_norm": 0.0,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.04726682302002526,
      "grad_norm": 0.0,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.0,
      "step": 131
    },
    {
      "epoch": 0.04762763846292621,
      "grad_norm": 0.0,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0,
      "step": 132
    },
    {
      "epoch": 0.04798845390582717,
      "grad_norm": 0.0,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.0,
      "step": 133
    },
    {
      "epoch": 0.04834926934872812,
      "grad_norm": 0.0,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.0,
      "step": 134
    },
    {
      "epoch": 0.04871008479162908,
      "grad_norm": 0.0,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.049070900234530035,
      "grad_norm": 0.0,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0,
      "step": 136
    },
    {
      "epoch": 0.049431715677430994,
      "grad_norm": 0.0,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0,
      "step": 137
    },
    {
      "epoch": 0.04979253112033195,
      "grad_norm": 0.0,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0,
      "step": 138
    },
    {
      "epoch": 0.050153346563232906,
      "grad_norm": 0.0,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0,
      "step": 139
    },
    {
      "epoch": 0.050514162006133866,
      "grad_norm": 0.0,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.05087497744903482,
      "grad_norm": 0.0,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0,
      "step": 141
    },
    {
      "epoch": 0.05123579289193578,
      "grad_norm": 0.0,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0,
      "step": 142
    },
    {
      "epoch": 0.05159660833483673,
      "grad_norm": 0.0,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 143
    },
    {
      "epoch": 0.05195742377773769,
      "grad_norm": 0.0,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0,
      "step": 144
    },
    {
      "epoch": 0.05231823922063864,
      "grad_norm": 0.0,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0,
      "step": 145
    },
    {
      "epoch": 0.0526790546635396,
      "grad_norm": 0.0,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0,
      "step": 146
    },
    {
      "epoch": 0.053039870106440554,
      "grad_norm": 0.0,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0,
      "step": 147
    },
    {
      "epoch": 0.05340068554934151,
      "grad_norm": 0.0,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0,
      "step": 148
    },
    {
      "epoch": 0.053761500992242466,
      "grad_norm": 0.0,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0,
      "step": 149
    },
    {
      "epoch": 0.054122316435143425,
      "grad_norm": 0.0,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.054122316435143425,
      "eval_loss": NaN,
      "eval_runtime": 352.3423,
      "eval_samples_per_second": 13.248,
      "eval_steps_per_second": 3.312,
      "step": 150
    },
    {
      "epoch": 0.05448313187804438,
      "grad_norm": 0.0,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.0,
      "step": 151
    },
    {
      "epoch": 0.05484394732094534,
      "grad_norm": 0.0,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.0,
      "step": 152
    },
    {
      "epoch": 0.05520476276384629,
      "grad_norm": 0.0,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.0,
      "step": 153
    },
    {
      "epoch": 0.05556557820674725,
      "grad_norm": 0.0,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0,
      "step": 154
    },
    {
      "epoch": 0.05592639364964821,
      "grad_norm": 0.0,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0,
      "step": 155
    },
    {
      "epoch": 0.05628720909254916,
      "grad_norm": 0.0,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0,
      "step": 156
    },
    {
      "epoch": 0.05664802453545012,
      "grad_norm": 0.0,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.0,
      "step": 157
    },
    {
      "epoch": 0.05700883997835107,
      "grad_norm": 0.0,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0,
      "step": 158
    },
    {
      "epoch": 0.05736965542125203,
      "grad_norm": 0.0,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0,
      "step": 159
    },
    {
      "epoch": 0.057730470864152984,
      "grad_norm": 0.0,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.058091286307053944,
      "grad_norm": 0.0,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0,
      "step": 161
    },
    {
      "epoch": 0.058452101749954896,
      "grad_norm": 0.0,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 162
    },
    {
      "epoch": 0.058812917192855856,
      "grad_norm": 0.0,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.0,
      "step": 163
    },
    {
      "epoch": 0.05917373263575681,
      "grad_norm": 0.0,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0,
      "step": 164
    },
    {
      "epoch": 0.05953454807865777,
      "grad_norm": 0.0,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.05989536352155872,
      "grad_norm": 0.0,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0,
      "step": 166
    },
    {
      "epoch": 0.06025617896445968,
      "grad_norm": 0.0,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0,
      "step": 167
    },
    {
      "epoch": 0.06061699440736063,
      "grad_norm": 0.0,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0,
      "step": 168
    },
    {
      "epoch": 0.06097780985026159,
      "grad_norm": 0.0,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0,
      "step": 169
    },
    {
      "epoch": 0.06133862529316255,
      "grad_norm": 0.0,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.0616994407360635,
      "grad_norm": 0.0,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0,
      "step": 171
    },
    {
      "epoch": 0.06206025617896446,
      "grad_norm": 0.0,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0,
      "step": 172
    },
    {
      "epoch": 0.062421071621865415,
      "grad_norm": 0.0,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.0,
      "step": 173
    },
    {
      "epoch": 0.06278188706476637,
      "grad_norm": 0.0,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0,
      "step": 174
    },
    {
      "epoch": 0.06314270250766733,
      "grad_norm": 0.0,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.0,
      "step": 175
    },
    {
      "epoch": 0.06350351795056829,
      "grad_norm": 0.0,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0,
      "step": 176
    },
    {
      "epoch": 0.06386433339346924,
      "grad_norm": 0.0,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0,
      "step": 177
    },
    {
      "epoch": 0.06422514883637019,
      "grad_norm": 0.0,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.0,
      "step": 178
    },
    {
      "epoch": 0.06458596427927116,
      "grad_norm": 0.0,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0,
      "step": 179
    },
    {
      "epoch": 0.06494677972217211,
      "grad_norm": 0.0,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.06530759516507306,
      "grad_norm": 0.0,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 181
    },
    {
      "epoch": 0.06566841060797401,
      "grad_norm": 0.0,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0,
      "step": 182
    },
    {
      "epoch": 0.06602922605087498,
      "grad_norm": 0.0,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0,
      "step": 183
    },
    {
      "epoch": 0.06639004149377593,
      "grad_norm": 0.0,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0,
      "step": 184
    },
    {
      "epoch": 0.06675085693667689,
      "grad_norm": 0.0,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.0,
      "step": 185
    },
    {
      "epoch": 0.06711167237957785,
      "grad_norm": 0.0,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0,
      "step": 186
    },
    {
      "epoch": 0.0674724878224788,
      "grad_norm": 0.0,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0,
      "step": 187
    },
    {
      "epoch": 0.06783330326537976,
      "grad_norm": 0.0,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0,
      "step": 188
    },
    {
      "epoch": 0.06819411870828071,
      "grad_norm": 0.0,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0,
      "step": 189
    },
    {
      "epoch": 0.06855493415118168,
      "grad_norm": 0.0,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.06891574959408263,
      "grad_norm": 0.0,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0,
      "step": 191
    },
    {
      "epoch": 0.06927656503698358,
      "grad_norm": 0.0,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0,
      "step": 192
    },
    {
      "epoch": 0.06963738047988453,
      "grad_norm": 0.0,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0,
      "step": 193
    },
    {
      "epoch": 0.0699981959227855,
      "grad_norm": 0.0,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0,
      "step": 194
    },
    {
      "epoch": 0.07035901136568645,
      "grad_norm": 0.0,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.0707198268085874,
      "grad_norm": 0.0,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0,
      "step": 196
    },
    {
      "epoch": 0.07108064225148836,
      "grad_norm": 0.0,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0,
      "step": 197
    },
    {
      "epoch": 0.07144145769438932,
      "grad_norm": 0.0,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0,
      "step": 198
    },
    {
      "epoch": 0.07180227313729028,
      "grad_norm": 0.0,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0,
      "step": 199
    },
    {
      "epoch": 0.07216308858019123,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.07216308858019123,
      "eval_loss": NaN,
      "eval_runtime": 351.8856,
      "eval_samples_per_second": 13.266,
      "eval_steps_per_second": 3.316,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.017027157491712e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}