{
  "best_metric": 0.38096651434898376,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.33222591362126247,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016611295681063123,
      "grad_norm": 1.2991793155670166,
      "learning_rate": 1e-05,
      "loss": 0.6513,
      "step": 1
    },
    {
      "epoch": 0.0016611295681063123,
      "eval_loss": 0.8317100405693054,
      "eval_runtime": 132.9593,
      "eval_samples_per_second": 7.626,
      "eval_steps_per_second": 1.91,
      "step": 1
    },
    {
      "epoch": 0.0033222591362126247,
      "grad_norm": 1.2579532861709595,
      "learning_rate": 2e-05,
      "loss": 0.6749,
      "step": 2
    },
    {
      "epoch": 0.0049833887043189366,
      "grad_norm": 1.0699290037155151,
      "learning_rate": 3e-05,
      "loss": 0.6399,
      "step": 3
    },
    {
      "epoch": 0.006644518272425249,
      "grad_norm": 0.7915657162666321,
      "learning_rate": 4e-05,
      "loss": 0.6214,
      "step": 4
    },
    {
      "epoch": 0.008305647840531562,
      "grad_norm": 0.5864650011062622,
      "learning_rate": 5e-05,
      "loss": 0.5893,
      "step": 5
    },
    {
      "epoch": 0.009966777408637873,
      "grad_norm": 0.4930439591407776,
      "learning_rate": 6e-05,
      "loss": 0.5539,
      "step": 6
    },
    {
      "epoch": 0.011627906976744186,
      "grad_norm": 0.8789781928062439,
      "learning_rate": 7e-05,
      "loss": 0.5859,
      "step": 7
    },
    {
      "epoch": 0.013289036544850499,
      "grad_norm": 0.6858446598052979,
      "learning_rate": 8e-05,
      "loss": 0.5161,
      "step": 8
    },
    {
      "epoch": 0.014950166112956811,
      "grad_norm": 0.4820753037929535,
      "learning_rate": 9e-05,
      "loss": 0.4945,
      "step": 9
    },
    {
      "epoch": 0.016611295681063124,
      "grad_norm": 0.35846245288848877,
      "learning_rate": 0.0001,
      "loss": 0.4702,
      "step": 10
    },
    {
      "epoch": 0.018272425249169437,
      "grad_norm": 0.3399806022644043,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.4192,
      "step": 11
    },
    {
      "epoch": 0.019933554817275746,
      "grad_norm": 0.32994091510772705,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.4455,
      "step": 12
    },
    {
      "epoch": 0.02159468438538206,
      "grad_norm": 0.2916202247142792,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.4491,
      "step": 13
    },
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 0.2513728439807892,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4192,
      "step": 14
    },
    {
      "epoch": 0.024916943521594685,
      "grad_norm": 0.20601803064346313,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4135,
      "step": 15
    },
    {
      "epoch": 0.026578073089700997,
      "grad_norm": 0.20515939593315125,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4149,
      "step": 16
    },
    {
      "epoch": 0.02823920265780731,
      "grad_norm": 0.24935221672058105,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.4144,
      "step": 17
    },
    {
      "epoch": 0.029900332225913623,
      "grad_norm": 0.22809065878391266,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.4117,
      "step": 18
    },
    {
      "epoch": 0.03156146179401993,
      "grad_norm": 0.2064090371131897,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.3975,
      "step": 19
    },
    {
      "epoch": 0.03322259136212625,
      "grad_norm": 0.20076528191566467,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.3937,
      "step": 20
    },
    {
      "epoch": 0.03488372093023256,
      "grad_norm": 0.20907463133335114,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.3936,
      "step": 21
    },
    {
      "epoch": 0.036544850498338874,
      "grad_norm": 0.20472639799118042,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.3875,
      "step": 22
    },
    {
      "epoch": 0.03820598006644518,
      "grad_norm": 0.17747552692890167,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.3996,
      "step": 23
    },
    {
      "epoch": 0.03986710963455149,
      "grad_norm": 0.18577048182487488,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.4622,
      "step": 24
    },
    {
      "epoch": 0.04152823920265781,
      "grad_norm": 0.18465018272399902,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4465,
      "step": 25
    },
    {
      "epoch": 0.04318936877076412,
      "grad_norm": 0.36926233768463135,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.6891,
      "step": 26
    },
    {
      "epoch": 0.044850498338870434,
      "grad_norm": 0.3326234817504883,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.6926,
      "step": 27
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.24597014486789703,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6492,
      "step": 28
    },
    {
      "epoch": 0.04817275747508306,
      "grad_norm": 0.22998689115047455,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6338,
      "step": 29
    },
    {
      "epoch": 0.04983388704318937,
      "grad_norm": 0.2597779631614685,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.6451,
      "step": 30
    },
    {
      "epoch": 0.05149501661129568,
      "grad_norm": 0.30236122012138367,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.622,
      "step": 31
    },
    {
      "epoch": 0.053156146179401995,
      "grad_norm": 0.2684450149536133,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6151,
      "step": 32
    },
    {
      "epoch": 0.054817275747508304,
      "grad_norm": 0.25038909912109375,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.593,
      "step": 33
    },
    {
      "epoch": 0.05647840531561462,
      "grad_norm": 0.25587284564971924,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5875,
      "step": 34
    },
    {
      "epoch": 0.05813953488372093,
      "grad_norm": 0.19960953295230865,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5488,
      "step": 35
    },
    {
      "epoch": 0.059800664451827246,
      "grad_norm": 0.19124135375022888,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.5632,
      "step": 36
    },
    {
      "epoch": 0.061461794019933555,
      "grad_norm": 0.1789243221282959,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.5588,
      "step": 37
    },
    {
      "epoch": 0.06312292358803986,
      "grad_norm": 0.17890439927577972,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.5598,
      "step": 38
    },
    {
      "epoch": 0.06478405315614617,
      "grad_norm": 0.1927339732646942,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.5882,
      "step": 39
    },
    {
      "epoch": 0.0664451827242525,
      "grad_norm": 0.20116066932678223,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.5741,
      "step": 40
    },
    {
      "epoch": 0.0681063122923588,
      "grad_norm": 0.17227494716644287,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.5436,
      "step": 41
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 0.18728812038898468,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.5824,
      "step": 42
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.1641688197851181,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.5773,
      "step": 43
    },
    {
      "epoch": 0.07308970099667775,
      "grad_norm": 0.16669844090938568,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.5692,
      "step": 44
    },
    {
      "epoch": 0.07475083056478406,
      "grad_norm": 0.16173191368579865,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5706,
      "step": 45
    },
    {
      "epoch": 0.07641196013289037,
      "grad_norm": 0.16865822672843933,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.5794,
      "step": 46
    },
    {
      "epoch": 0.07807308970099668,
      "grad_norm": 0.1681707352399826,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.5831,
      "step": 47
    },
    {
      "epoch": 0.07973421926910298,
      "grad_norm": 0.18740896880626678,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.5991,
      "step": 48
    },
    {
      "epoch": 0.08139534883720931,
      "grad_norm": 0.18814262747764587,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6662,
      "step": 49
    },
    {
      "epoch": 0.08305647840531562,
      "grad_norm": 0.24064107239246368,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7061,
      "step": 50
    },
    {
      "epoch": 0.08305647840531562,
      "eval_loss": 0.45007362961769104,
      "eval_runtime": 134.6502,
      "eval_samples_per_second": 7.531,
      "eval_steps_per_second": 1.886,
      "step": 50
    },
    {
      "epoch": 0.08471760797342193,
      "grad_norm": 0.18804551661014557,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.3224,
      "step": 51
    },
    {
      "epoch": 0.08637873754152824,
      "grad_norm": 0.16869483888149261,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.3237,
      "step": 52
    },
    {
      "epoch": 0.08803986710963455,
      "grad_norm": 0.16511651873588562,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.353,
      "step": 53
    },
    {
      "epoch": 0.08970099667774087,
      "grad_norm": 0.1492200344800949,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.3538,
      "step": 54
    },
    {
      "epoch": 0.09136212624584718,
      "grad_norm": 0.13702312111854553,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.3423,
      "step": 55
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 0.14534348249435425,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.331,
      "step": 56
    },
    {
      "epoch": 0.0946843853820598,
      "grad_norm": 0.1291942298412323,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.3115,
      "step": 57
    },
    {
      "epoch": 0.09634551495016612,
      "grad_norm": 0.13093352317810059,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3066,
      "step": 58
    },
    {
      "epoch": 0.09800664451827243,
      "grad_norm": 0.1452917754650116,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.3485,
      "step": 59
    },
    {
      "epoch": 0.09966777408637874,
      "grad_norm": 0.13886800408363342,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3127,
      "step": 60
    },
    {
      "epoch": 0.10132890365448505,
      "grad_norm": 0.14664413034915924,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3349,
      "step": 61
    },
    {
      "epoch": 0.10299003322259136,
      "grad_norm": 0.13130126893520355,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.3031,
      "step": 62
    },
    {
      "epoch": 0.10465116279069768,
      "grad_norm": 0.13619501888751984,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.3359,
      "step": 63
    },
    {
      "epoch": 0.10631229235880399,
      "grad_norm": 0.14423972368240356,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.3169,
      "step": 64
    },
    {
      "epoch": 0.1079734219269103,
      "grad_norm": 0.13670726120471954,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.3358,
      "step": 65
    },
    {
      "epoch": 0.10963455149501661,
      "grad_norm": 0.13185586035251617,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.3096,
      "step": 66
    },
    {
      "epoch": 0.11129568106312292,
      "grad_norm": 0.13396374881267548,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3091,
      "step": 67
    },
    {
      "epoch": 0.11295681063122924,
      "grad_norm": 0.1417226344347,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.3102,
      "step": 68
    },
    {
      "epoch": 0.11461794019933555,
      "grad_norm": 0.1466892659664154,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3403,
      "step": 69
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 0.1433144360780716,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.324,
      "step": 70
    },
    {
      "epoch": 0.11794019933554817,
      "grad_norm": 0.1436891257762909,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.3434,
      "step": 71
    },
    {
      "epoch": 0.11960132890365449,
      "grad_norm": 0.15285548567771912,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.3344,
      "step": 72
    },
    {
      "epoch": 0.1212624584717608,
      "grad_norm": 0.14362435042858124,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.3191,
      "step": 73
    },
    {
      "epoch": 0.12292358803986711,
      "grad_norm": 0.15305458009243011,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.3776,
      "step": 74
    },
    {
      "epoch": 0.12458471760797342,
      "grad_norm": 0.1848021298646927,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4502,
      "step": 75
    },
    {
      "epoch": 0.12624584717607973,
      "grad_norm": 0.18864738941192627,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5257,
      "step": 76
    },
    {
      "epoch": 0.12790697674418605,
      "grad_norm": 0.16458578407764435,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.526,
      "step": 77
    },
    {
      "epoch": 0.12956810631229235,
      "grad_norm": 0.14648108184337616,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.5084,
      "step": 78
    },
    {
      "epoch": 0.13122923588039867,
      "grad_norm": 0.13501055538654327,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.4777,
      "step": 79
    },
    {
      "epoch": 0.132890365448505,
      "grad_norm": 0.15276943147182465,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.5236,
      "step": 80
    },
    {
      "epoch": 0.1345514950166113,
      "grad_norm": 0.1511184722185135,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.5364,
      "step": 81
    },
    {
      "epoch": 0.1362126245847176,
      "grad_norm": 0.14624027907848358,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.5027,
      "step": 82
    },
    {
      "epoch": 0.1378737541528239,
      "grad_norm": 0.13957354426383972,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.4793,
      "step": 83
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.13981389999389648,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.4919,
      "step": 84
    },
    {
      "epoch": 0.14119601328903655,
      "grad_norm": 0.15372055768966675,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.5226,
      "step": 85
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.1438971310853958,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5232,
      "step": 86
    },
    {
      "epoch": 0.14451827242524917,
      "grad_norm": 0.1383737474679947,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.5007,
      "step": 87
    },
    {
      "epoch": 0.1461794019933555,
      "grad_norm": 0.14018723368644714,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.5328,
      "step": 88
    },
    {
      "epoch": 0.1478405315614618,
      "grad_norm": 0.1336921900510788,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.5123,
      "step": 89
    },
    {
      "epoch": 0.14950166112956811,
      "grad_norm": 0.14490532875061035,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.4996,
      "step": 90
    },
    {
      "epoch": 0.1511627906976744,
      "grad_norm": 0.14218592643737793,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.5103,
      "step": 91
    },
    {
      "epoch": 0.15282392026578073,
      "grad_norm": 0.13371700048446655,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.4695,
      "step": 92
    },
    {
      "epoch": 0.15448504983388706,
      "grad_norm": 0.14268216490745544,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4996,
      "step": 93
    },
    {
      "epoch": 0.15614617940199335,
      "grad_norm": 0.15761351585388184,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.5142,
      "step": 94
    },
    {
      "epoch": 0.15780730897009967,
      "grad_norm": 0.14862477779388428,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4953,
      "step": 95
    },
    {
      "epoch": 0.15946843853820597,
      "grad_norm": 0.15104886889457703,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5656,
      "step": 96
    },
    {
      "epoch": 0.1611295681063123,
      "grad_norm": 0.1583997756242752,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.538,
      "step": 97
    },
    {
      "epoch": 0.16279069767441862,
      "grad_norm": 0.16727805137634277,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5618,
      "step": 98
    },
    {
      "epoch": 0.1644518272425249,
      "grad_norm": 0.18140842020511627,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5916,
      "step": 99
    },
    {
      "epoch": 0.16611295681063123,
      "grad_norm": 0.2026122659444809,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.677,
      "step": 100
    },
    {
      "epoch": 0.16611295681063123,
      "eval_loss": 0.409039705991745,
      "eval_runtime": 134.7555,
      "eval_samples_per_second": 7.525,
      "eval_steps_per_second": 1.885,
      "step": 100
    },
    {
      "epoch": 0.16777408637873753,
      "grad_norm": 0.1708502620458603,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.2821,
      "step": 101
    },
    {
      "epoch": 0.16943521594684385,
      "grad_norm": 0.1842401623725891,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.2969,
      "step": 102
    },
    {
      "epoch": 0.17109634551495018,
      "grad_norm": 0.15198273956775665,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.2685,
      "step": 103
    },
    {
      "epoch": 0.17275747508305647,
      "grad_norm": 0.14956019818782806,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.2899,
      "step": 104
    },
    {
      "epoch": 0.1744186046511628,
      "grad_norm": 0.1505981981754303,
      "learning_rate": 5e-05,
      "loss": 0.2836,
      "step": 105
    },
    {
      "epoch": 0.1760797342192691,
      "grad_norm": 0.15199552476406097,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.2911,
      "step": 106
    },
    {
      "epoch": 0.1777408637873754,
      "grad_norm": 0.15069696307182312,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.2961,
      "step": 107
    },
    {
      "epoch": 0.17940199335548174,
      "grad_norm": 0.14875832200050354,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.287,
      "step": 108
    },
    {
      "epoch": 0.18106312292358803,
      "grad_norm": 0.1654970794916153,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3096,
      "step": 109
    },
    {
      "epoch": 0.18272425249169436,
      "grad_norm": 0.14778447151184082,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.2612,
      "step": 110
    },
    {
      "epoch": 0.18438538205980065,
      "grad_norm": 0.14741088449954987,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.2852,
      "step": 111
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 0.1445004642009735,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.2849,
      "step": 112
    },
    {
      "epoch": 0.1877076411960133,
      "grad_norm": 0.16333213448524475,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.2977,
      "step": 113
    },
    {
      "epoch": 0.1893687707641196,
      "grad_norm": 0.1434721201658249,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2925,
      "step": 114
    },
    {
      "epoch": 0.19102990033222592,
      "grad_norm": 0.13791555166244507,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.2619,
      "step": 115
    },
    {
      "epoch": 0.19269102990033224,
      "grad_norm": 0.14811094105243683,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.2951,
      "step": 116
    },
    {
      "epoch": 0.19435215946843853,
      "grad_norm": 0.13586348295211792,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.2758,
      "step": 117
    },
    {
      "epoch": 0.19601328903654486,
      "grad_norm": 0.15308637917041779,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.2889,
      "step": 118
    },
    {
      "epoch": 0.19767441860465115,
      "grad_norm": 0.1554800420999527,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.2985,
      "step": 119
    },
    {
      "epoch": 0.19933554817275748,
      "grad_norm": 0.1462528556585312,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.293,
      "step": 120
    },
    {
      "epoch": 0.2009966777408638,
      "grad_norm": 0.15194445848464966,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.3062,
      "step": 121
    },
    {
      "epoch": 0.2026578073089701,
      "grad_norm": 0.15283334255218506,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.3033,
      "step": 122
    },
    {
      "epoch": 0.20431893687707642,
      "grad_norm": 0.1533212512731552,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3403,
      "step": 123
    },
    {
      "epoch": 0.2059800664451827,
      "grad_norm": 0.17399577796459198,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.415,
      "step": 124
    },
    {
      "epoch": 0.20764119601328904,
      "grad_norm": 0.1844712793827057,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4619,
      "step": 125
    },
    {
      "epoch": 0.20930232558139536,
      "grad_norm": 0.18232126533985138,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.4879,
      "step": 126
    },
    {
      "epoch": 0.21096345514950166,
      "grad_norm": 0.17209911346435547,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.4918,
      "step": 127
    },
    {
      "epoch": 0.21262458471760798,
      "grad_norm": 0.15540632605552673,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.4778,
      "step": 128
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.14485326409339905,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.498,
      "step": 129
    },
    {
      "epoch": 0.2159468438538206,
      "grad_norm": 0.1500222533941269,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.4784,
      "step": 130
    },
    {
      "epoch": 0.21760797342192692,
      "grad_norm": 0.1539774239063263,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.4763,
      "step": 131
    },
    {
      "epoch": 0.21926910299003322,
      "grad_norm": 0.1498161256313324,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.4736,
      "step": 132
    },
    {
      "epoch": 0.22093023255813954,
      "grad_norm": 0.15067896246910095,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.4791,
      "step": 133
    },
    {
      "epoch": 0.22259136212624583,
      "grad_norm": 0.1555660367012024,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.5062,
      "step": 134
    },
    {
      "epoch": 0.22425249169435216,
      "grad_norm": 0.15103194117546082,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.4651,
      "step": 135
    },
    {
      "epoch": 0.22591362126245848,
      "grad_norm": 0.15316762030124664,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.4843,
      "step": 136
    },
    {
      "epoch": 0.22757475083056478,
      "grad_norm": 0.15561173856258392,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.5106,
      "step": 137
    },
    {
      "epoch": 0.2292358803986711,
      "grad_norm": 0.15198399126529694,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.4786,
      "step": 138
    },
    {
      "epoch": 0.23089700996677742,
      "grad_norm": 0.15727408230304718,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.4604,
      "step": 139
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.15432614088058472,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.4822,
      "step": 140
    },
    {
      "epoch": 0.23421926910299004,
      "grad_norm": 0.14581052958965302,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.4861,
      "step": 141
    },
    {
      "epoch": 0.23588039867109634,
      "grad_norm": 0.14340969920158386,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.4584,
      "step": 142
    },
    {
      "epoch": 0.23754152823920266,
      "grad_norm": 0.15534572303295135,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.4786,
      "step": 143
    },
    {
      "epoch": 0.23920265780730898,
      "grad_norm": 0.1554005742073059,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5156,
      "step": 144
    },
    {
      "epoch": 0.24086378737541528,
      "grad_norm": 0.15117494761943817,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.5163,
      "step": 145
    },
    {
      "epoch": 0.2425249169435216,
      "grad_norm": 0.1590317040681839,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5077,
      "step": 146
    },
    {
      "epoch": 0.2441860465116279,
      "grad_norm": 0.15675310790538788,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.485,
      "step": 147
    },
    {
      "epoch": 0.24584717607973422,
      "grad_norm": 0.16706211864948273,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5485,
      "step": 148
    },
    {
      "epoch": 0.24750830564784054,
      "grad_norm": 0.18405000865459442,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.568,
      "step": 149
    },
    {
      "epoch": 0.24916943521594684,
      "grad_norm": 0.232390895485878,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6994,
      "step": 150
    },
    {
      "epoch": 0.24916943521594684,
      "eval_loss": 0.3880166709423065,
      "eval_runtime": 135.2855,
      "eval_samples_per_second": 7.495,
      "eval_steps_per_second": 1.878,
      "step": 150
    },
    {
      "epoch": 0.25083056478405313,
      "grad_norm": 0.1730739325284958,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.2892,
      "step": 151
    },
    {
      "epoch": 0.25249169435215946,
      "grad_norm": 0.15850678086280823,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.2542,
      "step": 152
    },
    {
      "epoch": 0.2541528239202658,
      "grad_norm": 0.1620084047317505,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.259,
      "step": 153
    },
    {
      "epoch": 0.2558139534883721,
      "grad_norm": 0.16261513531208038,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.2655,
      "step": 154
    },
    {
      "epoch": 0.2574750830564784,
      "grad_norm": 0.15043796598911285,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.2809,
      "step": 155
    },
    {
      "epoch": 0.2591362126245847,
      "grad_norm": 0.1493295282125473,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.2721,
      "step": 156
    },
    {
      "epoch": 0.260797342192691,
      "grad_norm": 0.1420331448316574,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.254,
      "step": 157
    },
    {
      "epoch": 0.26245847176079734,
      "grad_norm": 0.13924731314182281,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.2624,
      "step": 158
    },
    {
      "epoch": 0.26411960132890366,
      "grad_norm": 0.1446397304534912,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.2683,
      "step": 159
    },
    {
      "epoch": 0.26578073089701,
      "grad_norm": 0.13315437734127045,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.2467,
      "step": 160
    },
    {
      "epoch": 0.26744186046511625,
      "grad_norm": 0.13552388548851013,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.2508,
      "step": 161
    },
    {
      "epoch": 0.2691029900332226,
      "grad_norm": 0.13076385855674744,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2516,
      "step": 162
    },
    {
      "epoch": 0.2707641196013289,
      "grad_norm": 0.13947907090187073,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.2672,
      "step": 163
    },
    {
      "epoch": 0.2724252491694352,
      "grad_norm": 0.14179465174674988,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.2657,
      "step": 164
    },
    {
      "epoch": 0.27408637873754155,
      "grad_norm": 0.1354580968618393,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.2633,
      "step": 165
    },
    {
      "epoch": 0.2757475083056478,
      "grad_norm": 0.143931046128273,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.2623,
      "step": 166
    },
    {
      "epoch": 0.27740863787375414,
      "grad_norm": 0.14093278348445892,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.2587,
      "step": 167
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 0.13632744550704956,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.2625,
      "step": 168
    },
    {
      "epoch": 0.2807308970099668,
      "grad_norm": 0.14669150114059448,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.2895,
      "step": 169
    },
    {
      "epoch": 0.2823920265780731,
      "grad_norm": 0.14640481770038605,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.2644,
      "step": 170
    },
    {
      "epoch": 0.2840531561461794,
      "grad_norm": 0.1421024203300476,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.2917,
      "step": 171
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.14989648759365082,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.3455,
      "step": 172
    },
    {
      "epoch": 0.287375415282392,
      "grad_norm": 0.14961613714694977,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.4074,
      "step": 173
    },
    {
      "epoch": 0.28903654485049834,
      "grad_norm": 0.1498543918132782,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.4368,
      "step": 174
    },
    {
      "epoch": 0.29069767441860467,
      "grad_norm": 0.15873299539089203,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.462,
      "step": 175
    },
    {
      "epoch": 0.292358803986711,
      "grad_norm": 0.15671579539775848,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.4607,
      "step": 176
    },
    {
      "epoch": 0.29401993355481726,
      "grad_norm": 0.16347020864486694,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.4631,
      "step": 177
    },
    {
      "epoch": 0.2956810631229236,
      "grad_norm": 0.15467208623886108,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.4825,
      "step": 178
    },
    {
      "epoch": 0.2973421926910299,
      "grad_norm": 0.15377561748027802,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.4624,
      "step": 179
    },
    {
      "epoch": 0.29900332225913623,
      "grad_norm": 0.160777747631073,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.48,
      "step": 180
    },
    {
      "epoch": 0.30066445182724255,
      "grad_norm": 0.15274566411972046,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.4978,
      "step": 181
    },
    {
      "epoch": 0.3023255813953488,
      "grad_norm": 0.15474535524845123,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.4641,
      "step": 182
    },
    {
      "epoch": 0.30398671096345514,
      "grad_norm": 0.15535560250282288,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.4961,
      "step": 183
    },
    {
      "epoch": 0.30564784053156147,
      "grad_norm": 0.15338659286499023,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.4865,
      "step": 184
    },
    {
      "epoch": 0.3073089700996678,
      "grad_norm": 0.15274019539356232,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.4978,
      "step": 185
    },
    {
      "epoch": 0.3089700996677741,
      "grad_norm": 0.14997823536396027,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.4733,
      "step": 186
    },
    {
      "epoch": 0.3106312292358804,
      "grad_norm": 0.14499768614768982,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.4833,
      "step": 187
    },
    {
      "epoch": 0.3122923588039867,
      "grad_norm": 0.14702832698822021,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.4618,
      "step": 188
    },
    {
      "epoch": 0.313953488372093,
      "grad_norm": 0.14408934116363525,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.4748,
      "step": 189
    },
    {
      "epoch": 0.31561461794019935,
      "grad_norm": 0.14656466245651245,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.4584,
      "step": 190
    },
    {
      "epoch": 0.31727574750830567,
      "grad_norm": 0.14636141061782837,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.4915,
      "step": 191
    },
    {
      "epoch": 0.31893687707641194,
      "grad_norm": 0.14926789700984955,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.4958,
      "step": 192
    },
    {
      "epoch": 0.32059800664451826,
      "grad_norm": 0.1512245237827301,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.4979,
      "step": 193
    },
    {
      "epoch": 0.3222591362126246,
      "grad_norm": 0.1518077850341797,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.4767,
      "step": 194
    },
    {
      "epoch": 0.3239202657807309,
      "grad_norm": 0.15790244936943054,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.5174,
      "step": 195
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 0.16024570167064667,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5091,
      "step": 196
    },
    {
      "epoch": 0.3272425249169435,
      "grad_norm": 0.15498998761177063,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.5075,
      "step": 197
    },
    {
      "epoch": 0.3289036544850498,
      "grad_norm": 0.15918047726154327,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.5357,
      "step": 198
    },
    {
      "epoch": 0.33056478405315615,
      "grad_norm": 0.18461520969867706,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5895,
      "step": 199
    },
    {
      "epoch": 0.33222591362126247,
      "grad_norm": 0.2483561933040619,
      "learning_rate": 0.0,
      "loss": 0.6524,
      "step": 200
    },
    {
      "epoch": 0.33222591362126247,
      "eval_loss": 0.38096651434898376,
      "eval_runtime": 135.189,
      "eval_samples_per_second": 7.501,
      "eval_steps_per_second": 1.879,
      "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": 4.91878059343872e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}