{
  "best_metric": 0.7400540113449097,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.2250351617440225,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011251758087201125,
      "grad_norm": 0.28744256496429443,
      "learning_rate": 1e-05,
      "loss": 0.7099,
      "step": 1
    },
    {
      "epoch": 0.0011251758087201125,
      "eval_loss": 1.053613305091858,
      "eval_runtime": 72.6286,
      "eval_samples_per_second": 20.612,
      "eval_steps_per_second": 5.163,
      "step": 1
    },
    {
      "epoch": 0.002250351617440225,
      "grad_norm": 0.3241807520389557,
      "learning_rate": 2e-05,
      "loss": 0.6829,
      "step": 2
    },
    {
      "epoch": 0.0033755274261603376,
      "grad_norm": 0.28037703037261963,
      "learning_rate": 3e-05,
      "loss": 0.6832,
      "step": 3
    },
    {
      "epoch": 0.00450070323488045,
      "grad_norm": 0.3197740912437439,
      "learning_rate": 4e-05,
      "loss": 0.9174,
      "step": 4
    },
    {
      "epoch": 0.005625879043600563,
      "grad_norm": 0.29462507367134094,
      "learning_rate": 5e-05,
      "loss": 0.8519,
      "step": 5
    },
    {
      "epoch": 0.006751054852320675,
      "grad_norm": 0.16718615591526031,
      "learning_rate": 6e-05,
      "loss": 0.8271,
      "step": 6
    },
    {
      "epoch": 0.007876230661040788,
      "grad_norm": 0.14618206024169922,
      "learning_rate": 7e-05,
      "loss": 0.9054,
      "step": 7
    },
    {
      "epoch": 0.0090014064697609,
      "grad_norm": 0.16193798184394836,
      "learning_rate": 8e-05,
      "loss": 1.0648,
      "step": 8
    },
    {
      "epoch": 0.010126582278481013,
      "grad_norm": 0.17764081060886383,
      "learning_rate": 9e-05,
      "loss": 0.9539,
      "step": 9
    },
    {
      "epoch": 0.011251758087201125,
      "grad_norm": 0.17770443856716156,
      "learning_rate": 0.0001,
      "loss": 1.0266,
      "step": 10
    },
    {
      "epoch": 0.012376933895921238,
      "grad_norm": 0.16426071524620056,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9196,
      "step": 11
    },
    {
      "epoch": 0.01350210970464135,
      "grad_norm": 0.21448597311973572,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.0292,
      "step": 12
    },
    {
      "epoch": 0.014627285513361463,
      "grad_norm": 0.21064357459545135,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.0497,
      "step": 13
    },
    {
      "epoch": 0.015752461322081576,
      "grad_norm": 0.19723820686340332,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.0151,
      "step": 14
    },
    {
      "epoch": 0.016877637130801686,
      "grad_norm": 0.1874244511127472,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.0827,
      "step": 15
    },
    {
      "epoch": 0.0180028129395218,
      "grad_norm": 0.18503165245056152,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0066,
      "step": 16
    },
    {
      "epoch": 0.01912798874824191,
      "grad_norm": 0.1754753291606903,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.009,
      "step": 17
    },
    {
      "epoch": 0.020253164556962026,
      "grad_norm": 0.1839926391839981,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.1238,
      "step": 18
    },
    {
      "epoch": 0.021378340365682136,
      "grad_norm": 0.1689082682132721,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.085,
      "step": 19
    },
    {
      "epoch": 0.02250351617440225,
      "grad_norm": 0.17413866519927979,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.033,
      "step": 20
    },
    {
      "epoch": 0.02362869198312236,
      "grad_norm": 0.17532522976398468,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9727,
      "step": 21
    },
    {
      "epoch": 0.024753867791842476,
      "grad_norm": 0.18257589638233185,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.0807,
      "step": 22
    },
    {
      "epoch": 0.025879043600562587,
      "grad_norm": 0.1621837317943573,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.0076,
      "step": 23
    },
    {
      "epoch": 0.0270042194092827,
      "grad_norm": 0.16744545102119446,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.1783,
      "step": 24
    },
    {
      "epoch": 0.02812939521800281,
      "grad_norm": 0.16235262155532837,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.8438,
      "step": 25
    },
    {
      "epoch": 0.029254571026722926,
      "grad_norm": 0.1746976673603058,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9799,
      "step": 26
    },
    {
      "epoch": 0.030379746835443037,
      "grad_norm": 0.17585837841033936,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9044,
      "step": 27
    },
    {
      "epoch": 0.03150492264416315,
      "grad_norm": 0.16757063567638397,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.9115,
      "step": 28
    },
    {
      "epoch": 0.03263009845288326,
      "grad_norm": 0.1784668117761612,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.0876,
      "step": 29
    },
    {
      "epoch": 0.03375527426160337,
      "grad_norm": 0.1938614696264267,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9925,
      "step": 30
    },
    {
      "epoch": 0.03488045007032349,
      "grad_norm": 0.18237663805484772,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8752,
      "step": 31
    },
    {
      "epoch": 0.0360056258790436,
      "grad_norm": 0.1855391412973404,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9484,
      "step": 32
    },
    {
      "epoch": 0.03713080168776371,
      "grad_norm": 0.19223161041736603,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7977,
      "step": 33
    },
    {
      "epoch": 0.03825597749648382,
      "grad_norm": 0.19526338577270508,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8975,
      "step": 34
    },
    {
      "epoch": 0.03938115330520394,
      "grad_norm": 0.1823018491268158,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8103,
      "step": 35
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 0.18328078091144562,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.7762,
      "step": 36
    },
    {
      "epoch": 0.04163150492264416,
      "grad_norm": 0.18645304441452026,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7021,
      "step": 37
    },
    {
      "epoch": 0.04275668073136427,
      "grad_norm": 0.20200158655643463,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7997,
      "step": 38
    },
    {
      "epoch": 0.04388185654008439,
      "grad_norm": 0.20194019377231598,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.6985,
      "step": 39
    },
    {
      "epoch": 0.0450070323488045,
      "grad_norm": 0.20087574422359467,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6051,
      "step": 40
    },
    {
      "epoch": 0.04613220815752461,
      "grad_norm": 0.2152727246284485,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7307,
      "step": 41
    },
    {
      "epoch": 0.04725738396624472,
      "grad_norm": 0.2125573754310608,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.6525,
      "step": 42
    },
    {
      "epoch": 0.04838255977496484,
      "grad_norm": 0.22942820191383362,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7193,
      "step": 43
    },
    {
      "epoch": 0.04950773558368495,
      "grad_norm": 0.24401390552520752,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6857,
      "step": 44
    },
    {
      "epoch": 0.05063291139240506,
      "grad_norm": 0.24477997422218323,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.6882,
      "step": 45
    },
    {
      "epoch": 0.05175808720112517,
      "grad_norm": 0.24917973577976227,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.5965,
      "step": 46
    },
    {
      "epoch": 0.05288326300984529,
      "grad_norm": 0.28255143761634827,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.5233,
      "step": 47
    },
    {
      "epoch": 0.0540084388185654,
      "grad_norm": 0.34546536207199097,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6246,
      "step": 48
    },
    {
      "epoch": 0.05513361462728551,
      "grad_norm": 0.3906535804271698,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6146,
      "step": 49
    },
    {
      "epoch": 0.05625879043600562,
      "grad_norm": 0.43594563007354736,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.6796,
      "step": 50
    },
    {
      "epoch": 0.05625879043600562,
      "eval_loss": 0.8176083564758301,
      "eval_runtime": 73.477,
      "eval_samples_per_second": 20.374,
      "eval_steps_per_second": 5.104,
      "step": 50
    },
    {
      "epoch": 0.05738396624472574,
      "grad_norm": 0.3089423179626465,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.6435,
      "step": 51
    },
    {
      "epoch": 0.05850914205344585,
      "grad_norm": 0.24479182064533234,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.5626,
      "step": 52
    },
    {
      "epoch": 0.05963431786216596,
      "grad_norm": 0.17990699410438538,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.57,
      "step": 53
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 0.16024604439735413,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7353,
      "step": 54
    },
    {
      "epoch": 0.06188466947960619,
      "grad_norm": 0.14513233304023743,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7228,
      "step": 55
    },
    {
      "epoch": 0.0630098452883263,
      "grad_norm": 0.12998345494270325,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7456,
      "step": 56
    },
    {
      "epoch": 0.06413502109704641,
      "grad_norm": 0.13989439606666565,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7529,
      "step": 57
    },
    {
      "epoch": 0.06526019690576652,
      "grad_norm": 0.1476536989212036,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8503,
      "step": 58
    },
    {
      "epoch": 0.06638537271448663,
      "grad_norm": 0.1412176638841629,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8842,
      "step": 59
    },
    {
      "epoch": 0.06751054852320675,
      "grad_norm": 0.1470104157924652,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.988,
      "step": 60
    },
    {
      "epoch": 0.06863572433192687,
      "grad_norm": 0.14214804768562317,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.879,
      "step": 61
    },
    {
      "epoch": 0.06976090014064698,
      "grad_norm": 0.13851666450500488,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8755,
      "step": 62
    },
    {
      "epoch": 0.07088607594936709,
      "grad_norm": 0.14373120665550232,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.9876,
      "step": 63
    },
    {
      "epoch": 0.0720112517580872,
      "grad_norm": 0.1432083547115326,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8902,
      "step": 64
    },
    {
      "epoch": 0.07313642756680731,
      "grad_norm": 0.1372254490852356,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7859,
      "step": 65
    },
    {
      "epoch": 0.07426160337552742,
      "grad_norm": 0.1492379903793335,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.916,
      "step": 66
    },
    {
      "epoch": 0.07538677918424753,
      "grad_norm": 0.14066049456596375,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8237,
      "step": 67
    },
    {
      "epoch": 0.07651195499296765,
      "grad_norm": 0.1484062820672989,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9237,
      "step": 68
    },
    {
      "epoch": 0.07763713080168777,
      "grad_norm": 0.15595759451389313,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9254,
      "step": 69
    },
    {
      "epoch": 0.07876230661040788,
      "grad_norm": 0.14984622597694397,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.9135,
      "step": 70
    },
    {
      "epoch": 0.07988748241912799,
      "grad_norm": 0.1518310010433197,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8526,
      "step": 71
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 0.14291878044605255,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7966,
      "step": 72
    },
    {
      "epoch": 0.08213783403656821,
      "grad_norm": 0.14978663623332977,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.8995,
      "step": 73
    },
    {
      "epoch": 0.08326300984528832,
      "grad_norm": 0.15922611951828003,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.924,
      "step": 74
    },
    {
      "epoch": 0.08438818565400844,
      "grad_norm": 0.1653391420841217,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.9522,
      "step": 75
    },
    {
      "epoch": 0.08551336146272855,
      "grad_norm": 0.1648348867893219,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.9158,
      "step": 76
    },
    {
      "epoch": 0.08663853727144867,
      "grad_norm": 0.1728581339120865,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.9934,
      "step": 77
    },
    {
      "epoch": 0.08776371308016878,
      "grad_norm": 0.16981300711631775,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9469,
      "step": 78
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.1611807942390442,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.777,
      "step": 79
    },
    {
      "epoch": 0.090014064697609,
      "grad_norm": 0.17365488409996033,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.896,
      "step": 80
    },
    {
      "epoch": 0.09113924050632911,
      "grad_norm": 0.173142209649086,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7878,
      "step": 81
    },
    {
      "epoch": 0.09226441631504922,
      "grad_norm": 0.174965038895607,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7868,
      "step": 82
    },
    {
      "epoch": 0.09338959212376934,
      "grad_norm": 0.17928966879844666,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8433,
      "step": 83
    },
    {
      "epoch": 0.09451476793248945,
      "grad_norm": 0.1770177185535431,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.8024,
      "step": 84
    },
    {
      "epoch": 0.09563994374120956,
      "grad_norm": 0.17353080213069916,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7235,
      "step": 85
    },
    {
      "epoch": 0.09676511954992968,
      "grad_norm": 0.19138696789741516,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8868,
      "step": 86
    },
    {
      "epoch": 0.09789029535864979,
      "grad_norm": 0.1914050281047821,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8618,
      "step": 87
    },
    {
      "epoch": 0.0990154711673699,
      "grad_norm": 0.18584732711315155,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.672,
      "step": 88
    },
    {
      "epoch": 0.10014064697609001,
      "grad_norm": 0.19127503037452698,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7385,
      "step": 89
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 0.20417876541614532,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.6295,
      "step": 90
    },
    {
      "epoch": 0.10239099859353024,
      "grad_norm": 0.20187601447105408,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6068,
      "step": 91
    },
    {
      "epoch": 0.10351617440225035,
      "grad_norm": 0.20402470231056213,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.5709,
      "step": 92
    },
    {
      "epoch": 0.10464135021097046,
      "grad_norm": 0.21485945582389832,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.5194,
      "step": 93
    },
    {
      "epoch": 0.10576652601969058,
      "grad_norm": 0.2264915555715561,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.5609,
      "step": 94
    },
    {
      "epoch": 0.10689170182841069,
      "grad_norm": 0.24080972373485565,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6146,
      "step": 95
    },
    {
      "epoch": 0.1080168776371308,
      "grad_norm": 0.2546713650226593,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.6081,
      "step": 96
    },
    {
      "epoch": 0.10914205344585091,
      "grad_norm": 0.2535207271575928,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.4883,
      "step": 97
    },
    {
      "epoch": 0.11026722925457103,
      "grad_norm": 0.2906816601753235,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5954,
      "step": 98
    },
    {
      "epoch": 0.11139240506329114,
      "grad_norm": 0.37003785371780396,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6574,
      "step": 99
    },
    {
      "epoch": 0.11251758087201125,
      "grad_norm": 0.45093151926994324,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6752,
      "step": 100
    },
    {
      "epoch": 0.11251758087201125,
      "eval_loss": 0.772516131401062,
      "eval_runtime": 73.5359,
      "eval_samples_per_second": 20.357,
      "eval_steps_per_second": 5.1,
      "step": 100
    },
    {
      "epoch": 0.11364275668073136,
      "grad_norm": 0.22953110933303833,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.6165,
      "step": 101
    },
    {
      "epoch": 0.11476793248945148,
      "grad_norm": 0.22733551263809204,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5645,
      "step": 102
    },
    {
      "epoch": 0.1158931082981716,
      "grad_norm": 0.1909782588481903,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5878,
      "step": 103
    },
    {
      "epoch": 0.1170182841068917,
      "grad_norm": 0.18363453447818756,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7127,
      "step": 104
    },
    {
      "epoch": 0.11814345991561181,
      "grad_norm": 0.16456936299800873,
      "learning_rate": 5e-05,
      "loss": 0.6618,
      "step": 105
    },
    {
      "epoch": 0.11926863572433193,
      "grad_norm": 0.14698876440525055,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7152,
      "step": 106
    },
    {
      "epoch": 0.12039381153305204,
      "grad_norm": 0.1356571763753891,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.7407,
      "step": 107
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 0.13574330508708954,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.77,
      "step": 108
    },
    {
      "epoch": 0.12264416315049226,
      "grad_norm": 0.13620668649673462,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.745,
      "step": 109
    },
    {
      "epoch": 0.12376933895921238,
      "grad_norm": 0.14419007301330566,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.9416,
      "step": 110
    },
    {
      "epoch": 0.1248945147679325,
      "grad_norm": 0.15939465165138245,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9578,
      "step": 111
    },
    {
      "epoch": 0.1260196905766526,
      "grad_norm": 0.1532604992389679,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.9745,
      "step": 112
    },
    {
      "epoch": 0.1271448663853727,
      "grad_norm": 0.15922436118125916,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.9107,
      "step": 113
    },
    {
      "epoch": 0.12827004219409283,
      "grad_norm": 0.16051270067691803,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.0319,
      "step": 114
    },
    {
      "epoch": 0.12939521800281295,
      "grad_norm": 0.15996387600898743,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8851,
      "step": 115
    },
    {
      "epoch": 0.13052039381153305,
      "grad_norm": 0.16803978383541107,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.0785,
      "step": 116
    },
    {
      "epoch": 0.13164556962025317,
      "grad_norm": 0.1578872948884964,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9266,
      "step": 117
    },
    {
      "epoch": 0.13277074542897327,
      "grad_norm": 0.15383996069431305,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8485,
      "step": 118
    },
    {
      "epoch": 0.1338959212376934,
      "grad_norm": 0.15688839554786682,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8195,
      "step": 119
    },
    {
      "epoch": 0.1350210970464135,
      "grad_norm": 0.153232604265213,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.775,
      "step": 120
    },
    {
      "epoch": 0.13614627285513362,
      "grad_norm": 0.17287659645080566,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.9116,
      "step": 121
    },
    {
      "epoch": 0.13727144866385374,
      "grad_norm": 0.14835681021213531,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.775,
      "step": 122
    },
    {
      "epoch": 0.13839662447257384,
      "grad_norm": 0.1736976057291031,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.9944,
      "step": 123
    },
    {
      "epoch": 0.13952180028129396,
      "grad_norm": 0.16409090161323547,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9142,
      "step": 124
    },
    {
      "epoch": 0.14064697609001406,
      "grad_norm": 0.16181126236915588,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7883,
      "step": 125
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 0.1793828010559082,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.0582,
      "step": 126
    },
    {
      "epoch": 0.14289732770745428,
      "grad_norm": 0.16566577553749084,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.8617,
      "step": 127
    },
    {
      "epoch": 0.1440225035161744,
      "grad_norm": 0.17740024626255035,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.954,
      "step": 128
    },
    {
      "epoch": 0.1451476793248945,
      "grad_norm": 0.179423987865448,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.8954,
      "step": 129
    },
    {
      "epoch": 0.14627285513361463,
      "grad_norm": 0.18432916700839996,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.953,
      "step": 130
    },
    {
      "epoch": 0.14739803094233475,
      "grad_norm": 0.17559075355529785,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7705,
      "step": 131
    },
    {
      "epoch": 0.14852320675105485,
      "grad_norm": 0.1845751702785492,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.8383,
      "step": 132
    },
    {
      "epoch": 0.14964838255977497,
      "grad_norm": 0.19049273431301117,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8802,
      "step": 133
    },
    {
      "epoch": 0.15077355836849507,
      "grad_norm": 0.18441186845302582,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8099,
      "step": 134
    },
    {
      "epoch": 0.1518987341772152,
      "grad_norm": 0.1854603886604309,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7365,
      "step": 135
    },
    {
      "epoch": 0.1530239099859353,
      "grad_norm": 0.19071020185947418,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7677,
      "step": 136
    },
    {
      "epoch": 0.15414908579465542,
      "grad_norm": 0.19896270334720612,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7863,
      "step": 137
    },
    {
      "epoch": 0.15527426160337554,
      "grad_norm": 0.20366181433200836,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.674,
      "step": 138
    },
    {
      "epoch": 0.15639943741209564,
      "grad_norm": 0.20192216336727142,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6419,
      "step": 139
    },
    {
      "epoch": 0.15752461322081576,
      "grad_norm": 0.20215179026126862,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6013,
      "step": 140
    },
    {
      "epoch": 0.15864978902953586,
      "grad_norm": 0.2117607742547989,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.6145,
      "step": 141
    },
    {
      "epoch": 0.15977496483825598,
      "grad_norm": 0.22218337655067444,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6115,
      "step": 142
    },
    {
      "epoch": 0.16090014064697608,
      "grad_norm": 0.23613807559013367,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6019,
      "step": 143
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 0.23598013818264008,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5546,
      "step": 144
    },
    {
      "epoch": 0.1631504922644163,
      "grad_norm": 0.24847006797790527,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.5478,
      "step": 145
    },
    {
      "epoch": 0.16427566807313643,
      "grad_norm": 0.2659261226654053,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6526,
      "step": 146
    },
    {
      "epoch": 0.16540084388185655,
      "grad_norm": 0.297800749540329,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5923,
      "step": 147
    },
    {
      "epoch": 0.16652601969057665,
      "grad_norm": 0.2947784662246704,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5992,
      "step": 148
    },
    {
      "epoch": 0.16765119549929677,
      "grad_norm": 0.34464070200920105,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5523,
      "step": 149
    },
    {
      "epoch": 0.16877637130801687,
      "grad_norm": 0.47710785269737244,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6658,
      "step": 150
    },
    {
      "epoch": 0.16877637130801687,
      "eval_loss": 0.7469105124473572,
      "eval_runtime": 73.3748,
      "eval_samples_per_second": 20.402,
      "eval_steps_per_second": 5.111,
      "step": 150
    },
    {
      "epoch": 0.169901547116737,
      "grad_norm": 0.1582491099834442,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5628,
      "step": 151
    },
    {
      "epoch": 0.1710267229254571,
      "grad_norm": 0.1542208045721054,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4797,
      "step": 152
    },
    {
      "epoch": 0.17215189873417722,
      "grad_norm": 0.15295161306858063,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5469,
      "step": 153
    },
    {
      "epoch": 0.17327707454289734,
      "grad_norm": 0.1632860004901886,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.5956,
      "step": 154
    },
    {
      "epoch": 0.17440225035161744,
      "grad_norm": 0.16465741395950317,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.6921,
      "step": 155
    },
    {
      "epoch": 0.17552742616033756,
      "grad_norm": 0.1658942550420761,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.6817,
      "step": 156
    },
    {
      "epoch": 0.17665260196905766,
      "grad_norm": 0.1764805167913437,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.791,
      "step": 157
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.1769816130399704,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.7917,
      "step": 158
    },
    {
      "epoch": 0.17890295358649788,
      "grad_norm": 0.17534379661083221,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8361,
      "step": 159
    },
    {
      "epoch": 0.180028129395218,
      "grad_norm": 0.16584567725658417,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.861,
      "step": 160
    },
    {
      "epoch": 0.1811533052039381,
      "grad_norm": 0.16908419132232666,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.8828,
      "step": 161
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 0.16447937488555908,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8599,
      "step": 162
    },
    {
      "epoch": 0.18340365682137835,
      "grad_norm": 0.15618117153644562,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.8877,
      "step": 163
    },
    {
      "epoch": 0.18452883263009845,
      "grad_norm": 0.1508748084306717,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.8117,
      "step": 164
    },
    {
      "epoch": 0.18565400843881857,
      "grad_norm": 0.14652839303016663,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.8105,
      "step": 165
    },
    {
      "epoch": 0.18677918424753867,
      "grad_norm": 0.14726658165454865,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7873,
      "step": 166
    },
    {
      "epoch": 0.1879043600562588,
      "grad_norm": 0.1607804000377655,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.9894,
      "step": 167
    },
    {
      "epoch": 0.1890295358649789,
      "grad_norm": 0.16779617965221405,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.0314,
      "step": 168
    },
    {
      "epoch": 0.19015471167369902,
      "grad_norm": 0.15478791296482086,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7906,
      "step": 169
    },
    {
      "epoch": 0.19127988748241911,
      "grad_norm": 0.16402015089988708,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.9198,
      "step": 170
    },
    {
      "epoch": 0.19240506329113924,
      "grad_norm": 0.1725064367055893,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.0657,
      "step": 171
    },
    {
      "epoch": 0.19353023909985936,
      "grad_norm": 0.16302773356437683,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.827,
      "step": 172
    },
    {
      "epoch": 0.19465541490857946,
      "grad_norm": 0.16457612812519073,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.8887,
      "step": 173
    },
    {
      "epoch": 0.19578059071729959,
      "grad_norm": 0.1730884611606598,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.8992,
      "step": 174
    },
    {
      "epoch": 0.19690576652601968,
      "grad_norm": 0.17574100196361542,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.9013,
      "step": 175
    },
    {
      "epoch": 0.1980309423347398,
      "grad_norm": 0.17158779501914978,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.8673,
      "step": 176
    },
    {
      "epoch": 0.1991561181434599,
      "grad_norm": 0.18105894327163696,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.9216,
      "step": 177
    },
    {
      "epoch": 0.20028129395218003,
      "grad_norm": 0.17232400178909302,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.8429,
      "step": 178
    },
    {
      "epoch": 0.20140646976090015,
      "grad_norm": 0.18575268983840942,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.9932,
      "step": 179
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 0.1802740842103958,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.9037,
      "step": 180
    },
    {
      "epoch": 0.20365682137834037,
      "grad_norm": 0.1830461174249649,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.8986,
      "step": 181
    },
    {
      "epoch": 0.20478199718706047,
      "grad_norm": 0.19233980774879456,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.9323,
      "step": 182
    },
    {
      "epoch": 0.2059071729957806,
      "grad_norm": 0.1919834464788437,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.8753,
      "step": 183
    },
    {
      "epoch": 0.2070323488045007,
      "grad_norm": 0.18953673541545868,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7629,
      "step": 184
    },
    {
      "epoch": 0.20815752461322082,
      "grad_norm": 0.19449080526828766,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.8019,
      "step": 185
    },
    {
      "epoch": 0.20928270042194091,
      "grad_norm": 0.20156420767307281,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.8906,
      "step": 186
    },
    {
      "epoch": 0.21040787623066104,
      "grad_norm": 0.19894199073314667,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.7401,
      "step": 187
    },
    {
      "epoch": 0.21153305203938116,
      "grad_norm": 0.20983977615833282,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.7363,
      "step": 188
    },
    {
      "epoch": 0.21265822784810126,
      "grad_norm": 0.20518995821475983,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6407,
      "step": 189
    },
    {
      "epoch": 0.21378340365682139,
      "grad_norm": 0.20329764485359192,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.554,
      "step": 190
    },
    {
      "epoch": 0.21490857946554148,
      "grad_norm": 0.22132454812526703,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6635,
      "step": 191
    },
    {
      "epoch": 0.2160337552742616,
      "grad_norm": 0.22702468931674957,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.6114,
      "step": 192
    },
    {
      "epoch": 0.2171589310829817,
      "grad_norm": 0.23989348113536835,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.5186,
      "step": 193
    },
    {
      "epoch": 0.21828410689170183,
      "grad_norm": 0.24007925391197205,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.451,
      "step": 194
    },
    {
      "epoch": 0.21940928270042195,
      "grad_norm": 0.2690707743167877,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.5844,
      "step": 195
    },
    {
      "epoch": 0.22053445850914205,
      "grad_norm": 0.26564493775367737,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5892,
      "step": 196
    },
    {
      "epoch": 0.22165963431786218,
      "grad_norm": 0.28619420528411865,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.5762,
      "step": 197
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 0.31425023078918457,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.5186,
      "step": 198
    },
    {
      "epoch": 0.2239099859353024,
      "grad_norm": 0.37038055062294006,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5492,
      "step": 199
    },
    {
      "epoch": 0.2250351617440225,
      "grad_norm": 0.4530652165412903,
      "learning_rate": 0.0,
      "loss": 0.6368,
      "step": 200
    },
    {
      "epoch": 0.2250351617440225,
      "eval_loss": 0.7400540113449097,
      "eval_runtime": 73.6329,
      "eval_samples_per_second": 20.331,
      "eval_steps_per_second": 5.093,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5087188916043776e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}