{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.15535991714137753,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010357327809425167,
      "grad_norm": 0.00024563074111938477,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0010357327809425167,
      "eval_loss": 11.5,
      "eval_runtime": 7.3195,
      "eval_samples_per_second": 222.146,
      "eval_steps_per_second": 55.605,
      "step": 1
    },
    {
      "epoch": 0.0020714655618850335,
      "grad_norm": 0.00034109369153156877,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0031071983428275505,
      "grad_norm": 0.000328395253745839,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.004142931123770067,
      "grad_norm": 0.0002929143374785781,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.005178663904712584,
      "grad_norm": 0.00021536297572311014,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.006214396685655101,
      "grad_norm": 0.00023290813260246068,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0072501294665976174,
      "grad_norm": 0.00034604850225150585,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.008285862247540134,
      "grad_norm": 0.0003155435551889241,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.009321595028482652,
      "grad_norm": 0.00034708177554421127,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.010357327809425169,
      "grad_norm": 0.0003184312954545021,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.011393060590367685,
      "grad_norm": 0.0004194458306301385,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.012428793371310202,
      "grad_norm": 0.00041123389382846653,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.013464526152252718,
      "grad_norm": 0.00044018946937285364,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.014500258933195235,
      "grad_norm": 0.0005088478210382164,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.015535991714137753,
      "grad_norm": 0.0005095250671729445,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.016571724495080268,
      "grad_norm": 0.00044094581971876323,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.017607457276022784,
      "grad_norm": 0.0006345334695652127,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.018643190056965304,
      "grad_norm": 0.000751802115701139,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.01967892283790782,
      "grad_norm": 0.0006887521594762802,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.020714655618850338,
      "grad_norm": 0.0008954176446422935,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.021750388399792854,
      "grad_norm": 0.0007898196345195174,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.02278612118073537,
      "grad_norm": 0.0009244951070286334,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.023821853961677887,
      "grad_norm": 0.0008067691815085709,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.024857586742620404,
      "grad_norm": 0.0008697854937054217,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.02589331952356292,
      "grad_norm": 0.0009124932694248855,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.026929052304505437,
      "grad_norm": 0.0011016872012987733,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.027964785085447953,
      "grad_norm": 0.0012876555556431413,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.02900051786639047,
      "grad_norm": 0.0012321434915065765,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.03003625064733299,
      "grad_norm": 0.0012619965709745884,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.031071983428275506,
      "grad_norm": 0.0011572017101570964,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.03210771620921802,
      "grad_norm": 0.0012235662434250116,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.033143448990160536,
      "grad_norm": 0.001188664697110653,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.03417918177110305,
      "grad_norm": 0.0012291519669815898,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.03521491455204557,
      "grad_norm": 0.0014081398257985711,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.03625064733298809,
      "grad_norm": 0.0016422814223915339,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.03728638011393061,
      "grad_norm": 0.0016299200942739844,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.038322112894873125,
      "grad_norm": 0.0018552629044279456,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.03935784567581564,
      "grad_norm": 0.00203379662707448,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.04039357845675816,
      "grad_norm": 0.0021950488444417715,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.041429311237700675,
      "grad_norm": 0.0023453899193555117,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.04246504401864319,
      "grad_norm": 0.002360742539167404,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.04350077679958571,
      "grad_norm": 0.0019548246636986732,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.044536509580528225,
      "grad_norm": 0.0020764681976288557,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.04557224236147074,
      "grad_norm": 0.002427465282380581,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.04660797514241326,
      "grad_norm": 0.0019412738038226962,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.047643707923355774,
      "grad_norm": 0.0023013383615761995,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.04867944070429829,
      "grad_norm": 0.0022615636698901653,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.04971517348524081,
      "grad_norm": 0.0022852038964629173,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.050750906266183324,
      "grad_norm": 0.0027075260877609253,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.05178663904712584,
      "grad_norm": 0.002084064995869994,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.05178663904712584,
      "eval_loss": 11.5,
      "eval_runtime": 7.3011,
      "eval_samples_per_second": 222.707,
      "eval_steps_per_second": 55.745,
      "step": 50
    },
    {
      "epoch": 0.05282237182806836,
      "grad_norm": 0.002694334601983428,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.05385810460901087,
      "grad_norm": 0.00214453530497849,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.05489383738995339,
      "grad_norm": 0.0033553086686879396,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.055929570170895906,
      "grad_norm": 0.001713861944153905,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.05696530295183842,
      "grad_norm": 0.0022790112998336554,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.05800103573278094,
      "grad_norm": 0.0031809762585908175,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.059036768513723456,
      "grad_norm": 0.0028212748002260923,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.06007250129466598,
      "grad_norm": 0.0035379191394895315,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.061108234075608496,
      "grad_norm": 0.0038749927189201117,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.06214396685655101,
      "grad_norm": 0.0038268519565463066,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.06317969963749352,
      "grad_norm": 0.0037553689908236265,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.06421543241843604,
      "grad_norm": 0.0039026180747896433,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.06525116519937856,
      "grad_norm": 0.004169592633843422,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.06628689798032107,
      "grad_norm": 0.0037143162917345762,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.06732263076126359,
      "grad_norm": 0.004098223056644201,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.0683583635422061,
      "grad_norm": 0.003964508883655071,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.06939409632314862,
      "grad_norm": 0.0037962498608976603,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.07042982910409114,
      "grad_norm": 0.003942782524973154,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.07146556188503367,
      "grad_norm": 0.004652809351682663,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.07250129466597618,
      "grad_norm": 0.004166955128312111,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.0735370274469187,
      "grad_norm": 0.003926089499145746,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.07457276022786122,
      "grad_norm": 0.0039015389047563076,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.07560849300880373,
      "grad_norm": 0.004201927222311497,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.07664422578974625,
      "grad_norm": 0.00470288610085845,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.07767995857068877,
      "grad_norm": 0.0058531733229756355,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.07871569135163128,
      "grad_norm": 0.0046242899261415005,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.0797514241325738,
      "grad_norm": 0.005070409271866083,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.08078715691351632,
      "grad_norm": 0.004674416966736317,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.08182288969445883,
      "grad_norm": 0.004346765112131834,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.08285862247540135,
      "grad_norm": 0.0037284111604094505,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.08389435525634387,
      "grad_norm": 0.004156739916652441,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.08493008803728638,
      "grad_norm": 0.0033007911406457424,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.0859658208182289,
      "grad_norm": 0.004007807467132807,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.08700155359917142,
      "grad_norm": 0.004331013187766075,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.08803728638011393,
      "grad_norm": 0.005234028212726116,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.08907301916105645,
      "grad_norm": 0.004950706381350756,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.09010875194199897,
      "grad_norm": 0.005768347065895796,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.09114448472294148,
      "grad_norm": 0.005533686373382807,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.092180217503884,
      "grad_norm": 0.005541697144508362,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.09321595028482652,
      "grad_norm": 0.006376004312187433,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.09425168306576903,
      "grad_norm": 0.005532476585358381,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.09528741584671155,
      "grad_norm": 0.004794495180249214,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.09632314862765406,
      "grad_norm": 0.005649871658533812,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.09735888140859658,
      "grad_norm": 0.005638834089040756,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.0983946141895391,
      "grad_norm": 0.004809532314538956,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.09943034697048161,
      "grad_norm": 0.005273715127259493,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.10046607975142413,
      "grad_norm": 0.005207295063883066,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.10150181253236665,
      "grad_norm": 0.004798053298145533,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.10253754531330916,
      "grad_norm": 0.005067740101367235,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.10357327809425168,
      "grad_norm": 0.004756320733577013,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.10357327809425168,
      "eval_loss": 11.5,
      "eval_runtime": 7.3114,
      "eval_samples_per_second": 222.393,
      "eval_steps_per_second": 55.667,
      "step": 100
    },
    {
      "epoch": 0.1046090108751942,
      "grad_norm": 0.0066249072551727295,
      "learning_rate": 5.330452921628497e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.10564474365613671,
      "grad_norm": 0.0054819826036691666,
      "learning_rate": 5.247918773366112e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.10668047643707923,
      "grad_norm": 0.004463305231183767,
      "learning_rate": 5.165316846586541e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.10771620921802175,
      "grad_norm": 0.002863190835341811,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.10875194199896426,
      "grad_norm": 0.004746824968606234,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.10978767477990678,
      "grad_norm": 0.005478134378790855,
      "learning_rate": 4.917330276168208e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.1108234075608493,
      "grad_norm": 0.005706458352506161,
      "learning_rate": 4.834683153413459e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.11185914034179181,
      "grad_norm": 0.0051987674087285995,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.11289487312273433,
      "grad_norm": 0.006376180797815323,
      "learning_rate": 4.669547078371504e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.11393060590367685,
      "grad_norm": 0.005378680303692818,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.11496633868461936,
      "grad_norm": 0.0063791582360863686,
      "learning_rate": 4.504772348747687e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.11600207146556188,
      "grad_norm": 0.005811464972794056,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.1170378042465044,
      "grad_norm": 0.006197675131261349,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.11807353702744691,
      "grad_norm": 0.005307814572006464,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.11910926980838944,
      "grad_norm": 0.00603079330176115,
      "learning_rate": 4.17702704859633e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.12014500258933196,
      "grad_norm": 0.0051902164705097675,
      "learning_rate": 4.095597328339452e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.12118073537027448,
      "grad_norm": 0.0051511856727302074,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.12221646815121699,
      "grad_norm": 0.006126652471721172,
      "learning_rate": 3.933501846281267e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.12325220093215951,
      "grad_norm": 0.005203056149184704,
      "learning_rate": 3.852880399766243e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.12428793371310203,
      "grad_norm": 0.005633100401610136,
      "learning_rate": 3.772572564296005e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.12532366649404453,
      "grad_norm": 0.006000136025249958,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.12635939927498704,
      "grad_norm": 0.005856860429048538,
      "learning_rate": 3.612985456190778e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.12739513205592956,
      "grad_norm": 0.0061734262853860855,
      "learning_rate": 3.533749813077677e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.12843086483687208,
      "grad_norm": 0.005927558522671461,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.1294665976178146,
      "grad_norm": 0.006376845296472311,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.1305023303987571,
      "grad_norm": 0.006281055510044098,
      "learning_rate": 3.298534127791785e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.13153806317969963,
      "grad_norm": 0.006313808728009462,
      "learning_rate": 3.221030765387417e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.13257379596064214,
      "grad_norm": 0.006140004377812147,
      "learning_rate": 3.144013755408895e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.13360952874158466,
      "grad_norm": 0.005959945265203714,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.13464526152252718,
      "grad_norm": 0.004513842053711414,
      "learning_rate": 2.991522876735154e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.1356809943034697,
      "grad_norm": 0.005219967104494572,
      "learning_rate": 2.916090697523549e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.1367167270844122,
      "grad_norm": 0.0047820252366364,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.13775245986535473,
      "grad_norm": 0.004098827019333839,
      "learning_rate": 2.766955965735968e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.13878819264629724,
      "grad_norm": 0.0047775073908269405,
      "learning_rate": 2.693294185106562e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.13982392542723976,
      "grad_norm": 0.005546234548091888,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.14085965820818228,
      "grad_norm": 0.005169082898646593,
      "learning_rate": 2.547882480847461e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.1418953909891248,
      "grad_norm": 0.005796536803245544,
      "learning_rate": 2.476172311325783e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.14293112377006734,
      "grad_norm": 0.005169686861336231,
      "learning_rate": 2.405152131093926e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.14396685655100985,
      "grad_norm": 0.005810331087559462,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.14500258933195237,
      "grad_norm": 0.005767869763076305,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.14603832211289489,
      "grad_norm": 0.006022621411830187,
      "learning_rate": 2.196424713241637e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.1470740548938374,
      "grad_norm": 0.00463132793083787,
      "learning_rate": 2.128356686585282e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.14810978767477992,
      "grad_norm": 0.005357954651117325,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.14914552045572244,
      "grad_norm": 0.00604967912659049,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.15018125323666495,
      "grad_norm": 0.005418510176241398,
      "learning_rate": 1.928936436551661e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.15121698601760747,
      "grad_norm": 0.005434873979538679,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.15225271879854999,
      "grad_norm": 0.005299575626850128,
      "learning_rate": 1.800157297483417e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.1532884515794925,
      "grad_norm": 0.0047104679979383945,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.15432418436043502,
      "grad_norm": 0.005120421759784222,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.15535991714137753,
      "grad_norm": 0.004393105395138264,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.15535991714137753,
      "eval_loss": 11.5,
      "eval_runtime": 7.33,
      "eval_samples_per_second": 221.827,
      "eval_steps_per_second": 55.525,
      "step": 150
    }
  ],
  "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": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 24118847078400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}