{
  "best_metric": 3.2505762577056885,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.12972271769093563,
  "eval_steps": 100,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006486135884546781,
      "grad_norm": 3.839925765991211,
      "learning_rate": 2e-05,
      "loss": 5.3671,
      "step": 1
    },
    {
      "epoch": 0.0006486135884546781,
      "eval_loss": 5.341527462005615,
      "eval_runtime": 35.046,
      "eval_samples_per_second": 58.666,
      "eval_steps_per_second": 14.666,
      "step": 1
    },
    {
      "epoch": 0.0012972271769093563,
      "grad_norm": 3.8855299949645996,
      "learning_rate": 4e-05,
      "loss": 5.2735,
      "step": 2
    },
    {
      "epoch": 0.0019458407653640344,
      "grad_norm": 3.7578446865081787,
      "learning_rate": 6e-05,
      "loss": 4.8599,
      "step": 3
    },
    {
      "epoch": 0.0025944543538187126,
      "grad_norm": 2.840263843536377,
      "learning_rate": 8e-05,
      "loss": 4.3011,
      "step": 4
    },
    {
      "epoch": 0.0032430679422733905,
      "grad_norm": 3.2963178157806396,
      "learning_rate": 0.0001,
      "loss": 4.7049,
      "step": 5
    },
    {
      "epoch": 0.003891681530728069,
      "grad_norm": 2.3765435218811035,
      "learning_rate": 0.00012,
      "loss": 4.4563,
      "step": 6
    },
    {
      "epoch": 0.004540295119182747,
      "grad_norm": 3.072453022003174,
      "learning_rate": 0.00014,
      "loss": 4.4638,
      "step": 7
    },
    {
      "epoch": 0.005188908707637425,
      "grad_norm": 3.7620046138763428,
      "learning_rate": 0.00016,
      "loss": 4.8635,
      "step": 8
    },
    {
      "epoch": 0.0058375222960921035,
      "grad_norm": 2.274141311645508,
      "learning_rate": 0.00018,
      "loss": 4.0879,
      "step": 9
    },
    {
      "epoch": 0.006486135884546781,
      "grad_norm": 2.1749279499053955,
      "learning_rate": 0.0002,
      "loss": 4.0116,
      "step": 10
    },
    {
      "epoch": 0.007134749473001459,
      "grad_norm": 2.7090888023376465,
      "learning_rate": 0.0001999999477769797,
      "loss": 4.1352,
      "step": 11
    },
    {
      "epoch": 0.007783363061456138,
      "grad_norm": 2.8192594051361084,
      "learning_rate": 0.00019999979110797331,
      "loss": 3.7506,
      "step": 12
    },
    {
      "epoch": 0.008431976649910815,
      "grad_norm": 2.1979215145111084,
      "learning_rate": 0.00019999952999314444,
      "loss": 4.0342,
      "step": 13
    },
    {
      "epoch": 0.009080590238365494,
      "grad_norm": 1.9726805686950684,
      "learning_rate": 0.0001999991644327659,
      "loss": 3.6903,
      "step": 14
    },
    {
      "epoch": 0.009729203826820172,
      "grad_norm": 2.4161455631256104,
      "learning_rate": 0.0001999986944272194,
      "loss": 3.2464,
      "step": 15
    },
    {
      "epoch": 0.01037781741527485,
      "grad_norm": 1.8676812648773193,
      "learning_rate": 0.00019999811997699593,
      "loss": 3.7741,
      "step": 16
    },
    {
      "epoch": 0.011026431003729529,
      "grad_norm": 1.7903848886489868,
      "learning_rate": 0.00019999744108269542,
      "loss": 3.7455,
      "step": 17
    },
    {
      "epoch": 0.011675044592184207,
      "grad_norm": 2.043623924255371,
      "learning_rate": 0.00019999665774502696,
      "loss": 3.8827,
      "step": 18
    },
    {
      "epoch": 0.012323658180638884,
      "grad_norm": 1.8445640802383423,
      "learning_rate": 0.00019999576996480872,
      "loss": 3.9371,
      "step": 19
    },
    {
      "epoch": 0.012972271769093562,
      "grad_norm": 1.5927119255065918,
      "learning_rate": 0.000199994777742968,
      "loss": 3.5422,
      "step": 20
    },
    {
      "epoch": 0.01362088535754824,
      "grad_norm": 1.3268831968307495,
      "learning_rate": 0.0001999936810805411,
      "loss": 3.286,
      "step": 21
    },
    {
      "epoch": 0.014269498946002919,
      "grad_norm": 1.617830514907837,
      "learning_rate": 0.0001999924799786734,
      "loss": 3.3049,
      "step": 22
    },
    {
      "epoch": 0.014918112534457597,
      "grad_norm": 1.592024803161621,
      "learning_rate": 0.00019999117443861942,
      "loss": 3.3464,
      "step": 23
    },
    {
      "epoch": 0.015566726122912275,
      "grad_norm": 1.5516711473464966,
      "learning_rate": 0.00019998976446174277,
      "loss": 3.399,
      "step": 24
    },
    {
      "epoch": 0.016215339711366954,
      "grad_norm": 1.7870945930480957,
      "learning_rate": 0.00019998825004951612,
      "loss": 3.5775,
      "step": 25
    },
    {
      "epoch": 0.01686395329982163,
      "grad_norm": 1.6130069494247437,
      "learning_rate": 0.00019998663120352118,
      "loss": 3.6604,
      "step": 26
    },
    {
      "epoch": 0.01751256688827631,
      "grad_norm": 1.4511877298355103,
      "learning_rate": 0.00019998490792544883,
      "loss": 3.243,
      "step": 27
    },
    {
      "epoch": 0.018161180476730987,
      "grad_norm": 1.6252033710479736,
      "learning_rate": 0.0001999830802170989,
      "loss": 3.6021,
      "step": 28
    },
    {
      "epoch": 0.018809794065185667,
      "grad_norm": 1.7277567386627197,
      "learning_rate": 0.00019998114808038043,
      "loss": 3.5944,
      "step": 29
    },
    {
      "epoch": 0.019458407653640344,
      "grad_norm": 1.6731386184692383,
      "learning_rate": 0.00019997911151731134,
      "loss": 3.3969,
      "step": 30
    },
    {
      "epoch": 0.02010702124209502,
      "grad_norm": 1.6243277788162231,
      "learning_rate": 0.00019997697053001886,
      "loss": 3.035,
      "step": 31
    },
    {
      "epoch": 0.0207556348305497,
      "grad_norm": 1.773876667022705,
      "learning_rate": 0.00019997472512073912,
      "loss": 3.6559,
      "step": 32
    },
    {
      "epoch": 0.021404248419004377,
      "grad_norm": 1.47771155834198,
      "learning_rate": 0.00019997237529181737,
      "loss": 3.103,
      "step": 33
    },
    {
      "epoch": 0.022052862007459057,
      "grad_norm": 1.3901262283325195,
      "learning_rate": 0.0001999699210457079,
      "loss": 2.8133,
      "step": 34
    },
    {
      "epoch": 0.022701475595913734,
      "grad_norm": 1.6069719791412354,
      "learning_rate": 0.00019996736238497406,
      "loss": 3.3517,
      "step": 35
    },
    {
      "epoch": 0.023350089184368414,
      "grad_norm": 1.5524790287017822,
      "learning_rate": 0.0001999646993122883,
      "loss": 3.3211,
      "step": 36
    },
    {
      "epoch": 0.02399870277282309,
      "grad_norm": 1.6193372011184692,
      "learning_rate": 0.0001999619318304321,
      "loss": 3.5321,
      "step": 37
    },
    {
      "epoch": 0.024647316361277767,
      "grad_norm": 1.6295925378799438,
      "learning_rate": 0.00019995905994229593,
      "loss": 3.4257,
      "step": 38
    },
    {
      "epoch": 0.025295929949732447,
      "grad_norm": 1.9165164232254028,
      "learning_rate": 0.00019995608365087946,
      "loss": 3.9521,
      "step": 39
    },
    {
      "epoch": 0.025944543538187124,
      "grad_norm": 1.5593171119689941,
      "learning_rate": 0.0001999530029592912,
      "loss": 3.4656,
      "step": 40
    },
    {
      "epoch": 0.026593157126641804,
      "grad_norm": 1.691826581954956,
      "learning_rate": 0.0001999498178707489,
      "loss": 3.2846,
      "step": 41
    },
    {
      "epoch": 0.02724177071509648,
      "grad_norm": 1.709882140159607,
      "learning_rate": 0.00019994652838857917,
      "loss": 3.4973,
      "step": 42
    },
    {
      "epoch": 0.02789038430355116,
      "grad_norm": 1.5011334419250488,
      "learning_rate": 0.00019994313451621783,
      "loss": 3.0221,
      "step": 43
    },
    {
      "epoch": 0.028538997892005837,
      "grad_norm": 1.3794457912445068,
      "learning_rate": 0.0001999396362572096,
      "loss": 3.5346,
      "step": 44
    },
    {
      "epoch": 0.029187611480460517,
      "grad_norm": 1.6306489706039429,
      "learning_rate": 0.00019993603361520828,
      "loss": 3.4094,
      "step": 45
    },
    {
      "epoch": 0.029836225068915194,
      "grad_norm": 1.2462743520736694,
      "learning_rate": 0.00019993232659397666,
      "loss": 3.1227,
      "step": 46
    },
    {
      "epoch": 0.03048483865736987,
      "grad_norm": 1.4848414659500122,
      "learning_rate": 0.00019992851519738664,
      "loss": 3.2734,
      "step": 47
    },
    {
      "epoch": 0.03113345224582455,
      "grad_norm": 1.7278729677200317,
      "learning_rate": 0.00019992459942941906,
      "loss": 3.3184,
      "step": 48
    },
    {
      "epoch": 0.03178206583427923,
      "grad_norm": 1.4307690858840942,
      "learning_rate": 0.00019992057929416371,
      "loss": 3.5227,
      "step": 49
    },
    {
      "epoch": 0.03243067942273391,
      "grad_norm": 1.530920147895813,
      "learning_rate": 0.00019991645479581956,
      "loss": 3.1131,
      "step": 50
    },
    {
      "epoch": 0.03307929301118859,
      "grad_norm": 1.5259414911270142,
      "learning_rate": 0.00019991222593869444,
      "loss": 3.7062,
      "step": 51
    },
    {
      "epoch": 0.03372790659964326,
      "grad_norm": 1.562098503112793,
      "learning_rate": 0.0001999078927272052,
      "loss": 3.3501,
      "step": 52
    },
    {
      "epoch": 0.03437652018809794,
      "grad_norm": 1.539969801902771,
      "learning_rate": 0.00019990345516587775,
      "loss": 3.7154,
      "step": 53
    },
    {
      "epoch": 0.03502513377655262,
      "grad_norm": 1.8281248807907104,
      "learning_rate": 0.00019989891325934692,
      "loss": 3.5978,
      "step": 54
    },
    {
      "epoch": 0.035673747365007294,
      "grad_norm": 1.5411529541015625,
      "learning_rate": 0.00019989426701235653,
      "loss": 3.3103,
      "step": 55
    },
    {
      "epoch": 0.036322360953461974,
      "grad_norm": 1.3391532897949219,
      "learning_rate": 0.00019988951642975947,
      "loss": 2.9469,
      "step": 56
    },
    {
      "epoch": 0.036970974541916654,
      "grad_norm": 1.5546962022781372,
      "learning_rate": 0.00019988466151651748,
      "loss": 3.5001,
      "step": 57
    },
    {
      "epoch": 0.037619588130371334,
      "grad_norm": 1.673667550086975,
      "learning_rate": 0.00019987970227770135,
      "loss": 3.5981,
      "step": 58
    },
    {
      "epoch": 0.03826820171882601,
      "grad_norm": 1.5357543230056763,
      "learning_rate": 0.00019987463871849078,
      "loss": 3.2209,
      "step": 59
    },
    {
      "epoch": 0.03891681530728069,
      "grad_norm": 1.5452758073806763,
      "learning_rate": 0.0001998694708441745,
      "loss": 2.9202,
      "step": 60
    },
    {
      "epoch": 0.03956542889573537,
      "grad_norm": 1.5281524658203125,
      "learning_rate": 0.00019986419866015013,
      "loss": 3.1143,
      "step": 61
    },
    {
      "epoch": 0.04021404248419004,
      "grad_norm": 1.6060402393341064,
      "learning_rate": 0.00019985882217192423,
      "loss": 3.5452,
      "step": 62
    },
    {
      "epoch": 0.04086265607264472,
      "grad_norm": 1.6011849641799927,
      "learning_rate": 0.00019985334138511237,
      "loss": 3.5304,
      "step": 63
    },
    {
      "epoch": 0.0415112696610994,
      "grad_norm": 1.8889275789260864,
      "learning_rate": 0.00019984775630543902,
      "loss": 3.2174,
      "step": 64
    },
    {
      "epoch": 0.04215988324955408,
      "grad_norm": 1.7960286140441895,
      "learning_rate": 0.00019984206693873753,
      "loss": 3.6113,
      "step": 65
    },
    {
      "epoch": 0.042808496838008754,
      "grad_norm": 1.4898135662078857,
      "learning_rate": 0.00019983627329095028,
      "loss": 3.2973,
      "step": 66
    },
    {
      "epoch": 0.043457110426463434,
      "grad_norm": 1.5716447830200195,
      "learning_rate": 0.00019983037536812842,
      "loss": 3.011,
      "step": 67
    },
    {
      "epoch": 0.044105724014918114,
      "grad_norm": 1.4708287715911865,
      "learning_rate": 0.00019982437317643217,
      "loss": 3.3225,
      "step": 68
    },
    {
      "epoch": 0.04475433760337279,
      "grad_norm": 1.4985527992248535,
      "learning_rate": 0.00019981826672213054,
      "loss": 3.1602,
      "step": 69
    },
    {
      "epoch": 0.04540295119182747,
      "grad_norm": 1.4717998504638672,
      "learning_rate": 0.0001998120560116015,
      "loss": 3.2304,
      "step": 70
    },
    {
      "epoch": 0.04605156478028215,
      "grad_norm": 1.9946448802947998,
      "learning_rate": 0.00019980574105133187,
      "loss": 3.3665,
      "step": 71
    },
    {
      "epoch": 0.04670017836873683,
      "grad_norm": 1.5488526821136475,
      "learning_rate": 0.00019979932184791742,
      "loss": 3.0899,
      "step": 72
    },
    {
      "epoch": 0.0473487919571915,
      "grad_norm": 1.3588461875915527,
      "learning_rate": 0.00019979279840806271,
      "loss": 3.0037,
      "step": 73
    },
    {
      "epoch": 0.04799740554564618,
      "grad_norm": 1.368888258934021,
      "learning_rate": 0.00019978617073858123,
      "loss": 3.1688,
      "step": 74
    },
    {
      "epoch": 0.04864601913410086,
      "grad_norm": 1.7766389846801758,
      "learning_rate": 0.00019977943884639534,
      "loss": 3.0139,
      "step": 75
    },
    {
      "epoch": 0.049294632722555534,
      "grad_norm": 1.4920904636383057,
      "learning_rate": 0.0001997726027385362,
      "loss": 3.2154,
      "step": 76
    },
    {
      "epoch": 0.049943246311010214,
      "grad_norm": 1.707010269165039,
      "learning_rate": 0.00019976566242214388,
      "loss": 3.3891,
      "step": 77
    },
    {
      "epoch": 0.050591859899464894,
      "grad_norm": 1.7228715419769287,
      "learning_rate": 0.00019975861790446722,
      "loss": 3.4335,
      "step": 78
    },
    {
      "epoch": 0.051240473487919574,
      "grad_norm": 1.423966646194458,
      "learning_rate": 0.000199751469192864,
      "loss": 3.0397,
      "step": 79
    },
    {
      "epoch": 0.05188908707637425,
      "grad_norm": 1.5038292407989502,
      "learning_rate": 0.00019974421629480075,
      "loss": 3.0318,
      "step": 80
    },
    {
      "epoch": 0.05253770066482893,
      "grad_norm": 1.4808934926986694,
      "learning_rate": 0.00019973685921785282,
      "loss": 3.1422,
      "step": 81
    },
    {
      "epoch": 0.05318631425328361,
      "grad_norm": 1.4777363538742065,
      "learning_rate": 0.00019972939796970436,
      "loss": 3.3775,
      "step": 82
    },
    {
      "epoch": 0.05383492784173829,
      "grad_norm": 1.7979999780654907,
      "learning_rate": 0.00019972183255814843,
      "loss": 3.3686,
      "step": 83
    },
    {
      "epoch": 0.05448354143019296,
      "grad_norm": 1.5056769847869873,
      "learning_rate": 0.00019971416299108672,
      "loss": 3.2013,
      "step": 84
    },
    {
      "epoch": 0.05513215501864764,
      "grad_norm": 1.389157772064209,
      "learning_rate": 0.0001997063892765298,
      "loss": 3.0217,
      "step": 85
    },
    {
      "epoch": 0.05578076860710232,
      "grad_norm": 1.7881611585617065,
      "learning_rate": 0.00019969851142259706,
      "loss": 3.1829,
      "step": 86
    },
    {
      "epoch": 0.056429382195556994,
      "grad_norm": 1.3970147371292114,
      "learning_rate": 0.0001996905294375166,
      "loss": 3.059,
      "step": 87
    },
    {
      "epoch": 0.057077995784011674,
      "grad_norm": 1.655731439590454,
      "learning_rate": 0.0001996824433296252,
      "loss": 3.3041,
      "step": 88
    },
    {
      "epoch": 0.057726609372466355,
      "grad_norm": 1.7357268333435059,
      "learning_rate": 0.0001996742531073686,
      "loss": 3.4154,
      "step": 89
    },
    {
      "epoch": 0.058375222960921035,
      "grad_norm": 1.6906143426895142,
      "learning_rate": 0.00019966595877930106,
      "loss": 3.186,
      "step": 90
    },
    {
      "epoch": 0.05902383654937571,
      "grad_norm": 1.3434598445892334,
      "learning_rate": 0.00019965756035408573,
      "loss": 3.0845,
      "step": 91
    },
    {
      "epoch": 0.05967245013783039,
      "grad_norm": 1.5761163234710693,
      "learning_rate": 0.00019964905784049442,
      "loss": 3.2079,
      "step": 92
    },
    {
      "epoch": 0.06032106372628507,
      "grad_norm": 1.366127371788025,
      "learning_rate": 0.00019964045124740772,
      "loss": 3.0052,
      "step": 93
    },
    {
      "epoch": 0.06096967731473974,
      "grad_norm": 1.5109351873397827,
      "learning_rate": 0.0001996317405838148,
      "loss": 3.0047,
      "step": 94
    },
    {
      "epoch": 0.06161829090319442,
      "grad_norm": 1.2576245069503784,
      "learning_rate": 0.0001996229258588136,
      "loss": 3.1236,
      "step": 95
    },
    {
      "epoch": 0.0622669044916491,
      "grad_norm": 1.4992951154708862,
      "learning_rate": 0.0001996140070816108,
      "loss": 3.1032,
      "step": 96
    },
    {
      "epoch": 0.06291551808010377,
      "grad_norm": 1.4879511594772339,
      "learning_rate": 0.0001996049842615217,
      "loss": 3.2732,
      "step": 97
    },
    {
      "epoch": 0.06356413166855845,
      "grad_norm": 1.2676115036010742,
      "learning_rate": 0.00019959585740797028,
      "loss": 3.0975,
      "step": 98
    },
    {
      "epoch": 0.06421274525701313,
      "grad_norm": 1.826397180557251,
      "learning_rate": 0.00019958662653048913,
      "loss": 3.3263,
      "step": 99
    },
    {
      "epoch": 0.06486135884546781,
      "grad_norm": 1.3498917818069458,
      "learning_rate": 0.00019957729163871962,
      "loss": 3.1325,
      "step": 100
    },
    {
      "epoch": 0.06486135884546781,
      "eval_loss": 3.3947603702545166,
      "eval_runtime": 35.0846,
      "eval_samples_per_second": 58.601,
      "eval_steps_per_second": 14.65,
      "step": 100
    },
    {
      "epoch": 0.0655099724339225,
      "grad_norm": 1.445410966873169,
      "learning_rate": 0.00019956785274241164,
      "loss": 3.236,
      "step": 101
    },
    {
      "epoch": 0.06615858602237717,
      "grad_norm": 1.6176825761795044,
      "learning_rate": 0.00019955830985142367,
      "loss": 3.0255,
      "step": 102
    },
    {
      "epoch": 0.06680719961083184,
      "grad_norm": 1.61312735080719,
      "learning_rate": 0.000199548662975723,
      "loss": 3.2001,
      "step": 103
    },
    {
      "epoch": 0.06745581319928652,
      "grad_norm": 1.36332368850708,
      "learning_rate": 0.00019953891212538534,
      "loss": 3.0994,
      "step": 104
    },
    {
      "epoch": 0.0681044267877412,
      "grad_norm": 1.7672650814056396,
      "learning_rate": 0.00019952905731059506,
      "loss": 3.2036,
      "step": 105
    },
    {
      "epoch": 0.06875304037619588,
      "grad_norm": 1.484741449356079,
      "learning_rate": 0.00019951909854164517,
      "loss": 3.0926,
      "step": 106
    },
    {
      "epoch": 0.06940165396465056,
      "grad_norm": 1.6508300304412842,
      "learning_rate": 0.00019950903582893718,
      "loss": 3.3921,
      "step": 107
    },
    {
      "epoch": 0.07005026755310524,
      "grad_norm": 1.5160471200942993,
      "learning_rate": 0.0001994988691829812,
      "loss": 3.2314,
      "step": 108
    },
    {
      "epoch": 0.07069888114155992,
      "grad_norm": 1.6546351909637451,
      "learning_rate": 0.00019948859861439587,
      "loss": 3.6566,
      "step": 109
    },
    {
      "epoch": 0.07134749473001459,
      "grad_norm": 1.401430368423462,
      "learning_rate": 0.00019947822413390843,
      "loss": 3.0595,
      "step": 110
    },
    {
      "epoch": 0.07199610831846927,
      "grad_norm": 1.4741144180297852,
      "learning_rate": 0.0001994677457523546,
      "loss": 2.5762,
      "step": 111
    },
    {
      "epoch": 0.07264472190692395,
      "grad_norm": 1.4336308240890503,
      "learning_rate": 0.0001994571634806786,
      "loss": 3.2864,
      "step": 112
    },
    {
      "epoch": 0.07329333549537863,
      "grad_norm": 1.3772560358047485,
      "learning_rate": 0.00019944647732993324,
      "loss": 2.9711,
      "step": 113
    },
    {
      "epoch": 0.07394194908383331,
      "grad_norm": 1.8636032342910767,
      "learning_rate": 0.0001994356873112798,
      "loss": 3.6032,
      "step": 114
    },
    {
      "epoch": 0.07459056267228799,
      "grad_norm": 1.5523511171340942,
      "learning_rate": 0.00019942479343598794,
      "loss": 2.9138,
      "step": 115
    },
    {
      "epoch": 0.07523917626074267,
      "grad_norm": 1.3805291652679443,
      "learning_rate": 0.00019941379571543596,
      "loss": 3.1352,
      "step": 116
    },
    {
      "epoch": 0.07588778984919733,
      "grad_norm": 1.7657650709152222,
      "learning_rate": 0.00019940269416111054,
      "loss": 3.6572,
      "step": 117
    },
    {
      "epoch": 0.07653640343765201,
      "grad_norm": 1.0355079174041748,
      "learning_rate": 0.00019939148878460677,
      "loss": 3.1429,
      "step": 118
    },
    {
      "epoch": 0.0771850170261067,
      "grad_norm": 2.0980677604675293,
      "learning_rate": 0.00019938017959762822,
      "loss": 3.6367,
      "step": 119
    },
    {
      "epoch": 0.07783363061456137,
      "grad_norm": 1.554826259613037,
      "learning_rate": 0.00019936876661198692,
      "loss": 3.0011,
      "step": 120
    },
    {
      "epoch": 0.07848224420301605,
      "grad_norm": 1.5516928434371948,
      "learning_rate": 0.0001993572498396033,
      "loss": 2.8849,
      "step": 121
    },
    {
      "epoch": 0.07913085779147074,
      "grad_norm": 1.8022054433822632,
      "learning_rate": 0.00019934562929250612,
      "loss": 3.3661,
      "step": 122
    },
    {
      "epoch": 0.07977947137992542,
      "grad_norm": 1.523295521736145,
      "learning_rate": 0.00019933390498283262,
      "loss": 3.37,
      "step": 123
    },
    {
      "epoch": 0.08042808496838008,
      "grad_norm": 1.5638176202774048,
      "learning_rate": 0.0001993220769228284,
      "loss": 3.0696,
      "step": 124
    },
    {
      "epoch": 0.08107669855683476,
      "grad_norm": 1.4551162719726562,
      "learning_rate": 0.00019931014512484732,
      "loss": 2.9773,
      "step": 125
    },
    {
      "epoch": 0.08172531214528944,
      "grad_norm": 1.8125625848770142,
      "learning_rate": 0.00019929810960135172,
      "loss": 3.5409,
      "step": 126
    },
    {
      "epoch": 0.08237392573374412,
      "grad_norm": 1.598616361618042,
      "learning_rate": 0.0001992859703649122,
      "loss": 3.2174,
      "step": 127
    },
    {
      "epoch": 0.0830225393221988,
      "grad_norm": 1.6178065538406372,
      "learning_rate": 0.00019927372742820779,
      "loss": 3.1763,
      "step": 128
    },
    {
      "epoch": 0.08367115291065348,
      "grad_norm": 1.5398484468460083,
      "learning_rate": 0.00019926138080402566,
      "loss": 3.174,
      "step": 129
    },
    {
      "epoch": 0.08431976649910816,
      "grad_norm": 1.6358362436294556,
      "learning_rate": 0.0001992489305052614,
      "loss": 3.3533,
      "step": 130
    },
    {
      "epoch": 0.08496838008756283,
      "grad_norm": 1.5181739330291748,
      "learning_rate": 0.00019923637654491888,
      "loss": 3.0561,
      "step": 131
    },
    {
      "epoch": 0.08561699367601751,
      "grad_norm": 1.4952844381332397,
      "learning_rate": 0.00019922371893611022,
      "loss": 2.8942,
      "step": 132
    },
    {
      "epoch": 0.08626560726447219,
      "grad_norm": 1.55109441280365,
      "learning_rate": 0.00019921095769205574,
      "loss": 2.9548,
      "step": 133
    },
    {
      "epoch": 0.08691422085292687,
      "grad_norm": 1.258230209350586,
      "learning_rate": 0.00019919809282608407,
      "loss": 2.6494,
      "step": 134
    },
    {
      "epoch": 0.08756283444138155,
      "grad_norm": 1.5716472864151,
      "learning_rate": 0.0001991851243516321,
      "loss": 3.0505,
      "step": 135
    },
    {
      "epoch": 0.08821144802983623,
      "grad_norm": 2.0663163661956787,
      "learning_rate": 0.00019917205228224481,
      "loss": 3.699,
      "step": 136
    },
    {
      "epoch": 0.08886006161829091,
      "grad_norm": 1.6701781749725342,
      "learning_rate": 0.00019915887663157555,
      "loss": 3.3952,
      "step": 137
    },
    {
      "epoch": 0.08950867520674557,
      "grad_norm": 1.5281134843826294,
      "learning_rate": 0.0001991455974133857,
      "loss": 3.1934,
      "step": 138
    },
    {
      "epoch": 0.09015728879520025,
      "grad_norm": 1.577763557434082,
      "learning_rate": 0.00019913221464154488,
      "loss": 3.266,
      "step": 139
    },
    {
      "epoch": 0.09080590238365494,
      "grad_norm": 1.510722041130066,
      "learning_rate": 0.0001991187283300309,
      "loss": 3.0935,
      "step": 140
    },
    {
      "epoch": 0.09145451597210962,
      "grad_norm": 1.5357921123504639,
      "learning_rate": 0.00019910513849292962,
      "loss": 3.1124,
      "step": 141
    },
    {
      "epoch": 0.0921031295605643,
      "grad_norm": 1.441179633140564,
      "learning_rate": 0.00019909144514443518,
      "loss": 3.0029,
      "step": 142
    },
    {
      "epoch": 0.09275174314901898,
      "grad_norm": 1.5612683296203613,
      "learning_rate": 0.00019907764829884964,
      "loss": 2.9997,
      "step": 143
    },
    {
      "epoch": 0.09340035673747366,
      "grad_norm": 1.4757554531097412,
      "learning_rate": 0.00019906374797058334,
      "loss": 3.0236,
      "step": 144
    },
    {
      "epoch": 0.09404897032592832,
      "grad_norm": 1.4126044511795044,
      "learning_rate": 0.00019904974417415456,
      "loss": 2.7912,
      "step": 145
    },
    {
      "epoch": 0.094697583914383,
      "grad_norm": 1.751099944114685,
      "learning_rate": 0.00019903563692418976,
      "loss": 3.2925,
      "step": 146
    },
    {
      "epoch": 0.09534619750283768,
      "grad_norm": 1.6099004745483398,
      "learning_rate": 0.00019902142623542336,
      "loss": 3.0836,
      "step": 147
    },
    {
      "epoch": 0.09599481109129236,
      "grad_norm": 1.4375733137130737,
      "learning_rate": 0.0001990071121226979,
      "loss": 3.0289,
      "step": 148
    },
    {
      "epoch": 0.09664342467974704,
      "grad_norm": 1.8070977926254272,
      "learning_rate": 0.0001989926946009639,
      "loss": 3.1598,
      "step": 149
    },
    {
      "epoch": 0.09729203826820172,
      "grad_norm": 1.9119011163711548,
      "learning_rate": 0.00019897817368527985,
      "loss": 3.484,
      "step": 150
    },
    {
      "epoch": 0.0979406518566564,
      "grad_norm": 1.6774824857711792,
      "learning_rate": 0.00019896354939081233,
      "loss": 3.3953,
      "step": 151
    },
    {
      "epoch": 0.09858926544511107,
      "grad_norm": 1.5909019708633423,
      "learning_rate": 0.00019894882173283578,
      "loss": 3.3354,
      "step": 152
    },
    {
      "epoch": 0.09923787903356575,
      "grad_norm": 1.9849345684051514,
      "learning_rate": 0.00019893399072673268,
      "loss": 3.6584,
      "step": 153
    },
    {
      "epoch": 0.09988649262202043,
      "grad_norm": 1.6064544916152954,
      "learning_rate": 0.00019891905638799346,
      "loss": 2.8525,
      "step": 154
    },
    {
      "epoch": 0.10053510621047511,
      "grad_norm": 1.518021821975708,
      "learning_rate": 0.0001989040187322164,
      "loss": 3.1254,
      "step": 155
    },
    {
      "epoch": 0.10118371979892979,
      "grad_norm": 1.3452222347259521,
      "learning_rate": 0.00019888887777510776,
      "loss": 2.8711,
      "step": 156
    },
    {
      "epoch": 0.10183233338738447,
      "grad_norm": 1.5667740106582642,
      "learning_rate": 0.00019887363353248168,
      "loss": 2.8838,
      "step": 157
    },
    {
      "epoch": 0.10248094697583915,
      "grad_norm": 1.9317669868469238,
      "learning_rate": 0.0001988582860202601,
      "loss": 3.6402,
      "step": 158
    },
    {
      "epoch": 0.10312956056429382,
      "grad_norm": 1.5328751802444458,
      "learning_rate": 0.00019884283525447297,
      "loss": 3.4408,
      "step": 159
    },
    {
      "epoch": 0.1037781741527485,
      "grad_norm": 1.5413289070129395,
      "learning_rate": 0.00019882728125125799,
      "loss": 3.2537,
      "step": 160
    },
    {
      "epoch": 0.10442678774120318,
      "grad_norm": 1.7009034156799316,
      "learning_rate": 0.00019881162402686064,
      "loss": 3.2318,
      "step": 161
    },
    {
      "epoch": 0.10507540132965786,
      "grad_norm": 1.3361696004867554,
      "learning_rate": 0.00019879586359763436,
      "loss": 3.042,
      "step": 162
    },
    {
      "epoch": 0.10572401491811254,
      "grad_norm": 1.5617996454238892,
      "learning_rate": 0.0001987799999800402,
      "loss": 3.2803,
      "step": 163
    },
    {
      "epoch": 0.10637262850656722,
      "grad_norm": 1.399532437324524,
      "learning_rate": 0.00019876403319064715,
      "loss": 3.0391,
      "step": 164
    },
    {
      "epoch": 0.1070212420950219,
      "grad_norm": 1.429004192352295,
      "learning_rate": 0.0001987479632461319,
      "loss": 2.9923,
      "step": 165
    },
    {
      "epoch": 0.10766985568347658,
      "grad_norm": 1.4386272430419922,
      "learning_rate": 0.0001987317901632788,
      "loss": 2.7631,
      "step": 166
    },
    {
      "epoch": 0.10831846927193124,
      "grad_norm": 1.4610167741775513,
      "learning_rate": 0.00019871551395898003,
      "loss": 3.152,
      "step": 167
    },
    {
      "epoch": 0.10896708286038592,
      "grad_norm": 1.275974154472351,
      "learning_rate": 0.00019869913465023548,
      "loss": 3.0508,
      "step": 168
    },
    {
      "epoch": 0.1096156964488406,
      "grad_norm": 1.895013451576233,
      "learning_rate": 0.00019868265225415265,
      "loss": 3.4938,
      "step": 169
    },
    {
      "epoch": 0.11026431003729528,
      "grad_norm": 1.966009497642517,
      "learning_rate": 0.0001986660667879467,
      "loss": 3.4529,
      "step": 170
    },
    {
      "epoch": 0.11091292362574996,
      "grad_norm": 1.5443345308303833,
      "learning_rate": 0.0001986493782689406,
      "loss": 2.8802,
      "step": 171
    },
    {
      "epoch": 0.11156153721420464,
      "grad_norm": 1.4930187463760376,
      "learning_rate": 0.00019863258671456478,
      "loss": 3.1778,
      "step": 172
    },
    {
      "epoch": 0.11221015080265932,
      "grad_norm": 1.4915255308151245,
      "learning_rate": 0.00019861569214235737,
      "loss": 3.0042,
      "step": 173
    },
    {
      "epoch": 0.11285876439111399,
      "grad_norm": 1.735092043876648,
      "learning_rate": 0.00019859869456996407,
      "loss": 3.5419,
      "step": 174
    },
    {
      "epoch": 0.11350737797956867,
      "grad_norm": 1.5523368120193481,
      "learning_rate": 0.00019858159401513819,
      "loss": 3.0072,
      "step": 175
    },
    {
      "epoch": 0.11415599156802335,
      "grad_norm": 1.5719223022460938,
      "learning_rate": 0.00019856439049574057,
      "loss": 3.0198,
      "step": 176
    },
    {
      "epoch": 0.11480460515647803,
      "grad_norm": 1.835192084312439,
      "learning_rate": 0.0001985470840297396,
      "loss": 3.0267,
      "step": 177
    },
    {
      "epoch": 0.11545321874493271,
      "grad_norm": 1.9231184720993042,
      "learning_rate": 0.00019852967463521124,
      "loss": 3.1645,
      "step": 178
    },
    {
      "epoch": 0.11610183233338739,
      "grad_norm": 1.5600292682647705,
      "learning_rate": 0.00019851216233033884,
      "loss": 3.0769,
      "step": 179
    },
    {
      "epoch": 0.11675044592184207,
      "grad_norm": 1.7042049169540405,
      "learning_rate": 0.00019849454713341338,
      "loss": 3.4191,
      "step": 180
    },
    {
      "epoch": 0.11739905951029674,
      "grad_norm": 1.5651507377624512,
      "learning_rate": 0.0001984768290628332,
      "loss": 2.922,
      "step": 181
    },
    {
      "epoch": 0.11804767309875142,
      "grad_norm": 1.469074010848999,
      "learning_rate": 0.0001984590081371041,
      "loss": 2.9323,
      "step": 182
    },
    {
      "epoch": 0.1186962866872061,
      "grad_norm": 1.4901165962219238,
      "learning_rate": 0.00019844108437483938,
      "loss": 2.9711,
      "step": 183
    },
    {
      "epoch": 0.11934490027566078,
      "grad_norm": 1.219331979751587,
      "learning_rate": 0.00019842305779475968,
      "loss": 2.4844,
      "step": 184
    },
    {
      "epoch": 0.11999351386411546,
      "grad_norm": 1.562193751335144,
      "learning_rate": 0.00019840492841569307,
      "loss": 3.0347,
      "step": 185
    },
    {
      "epoch": 0.12064212745257014,
      "grad_norm": 1.3141801357269287,
      "learning_rate": 0.0001983866962565749,
      "loss": 2.8955,
      "step": 186
    },
    {
      "epoch": 0.12129074104102482,
      "grad_norm": 1.7868186235427856,
      "learning_rate": 0.00019836836133644802,
      "loss": 3.371,
      "step": 187
    },
    {
      "epoch": 0.12193935462947948,
      "grad_norm": 1.5469980239868164,
      "learning_rate": 0.0001983499236744625,
      "loss": 3.1649,
      "step": 188
    },
    {
      "epoch": 0.12258796821793416,
      "grad_norm": 1.5688115358352661,
      "learning_rate": 0.00019833138328987572,
      "loss": 3.102,
      "step": 189
    },
    {
      "epoch": 0.12323658180638884,
      "grad_norm": 1.9711377620697021,
      "learning_rate": 0.00019831274020205242,
      "loss": 3.2971,
      "step": 190
    },
    {
      "epoch": 0.12388519539484352,
      "grad_norm": 1.5055005550384521,
      "learning_rate": 0.00019829399443046454,
      "loss": 3.0587,
      "step": 191
    },
    {
      "epoch": 0.1245338089832982,
      "grad_norm": 1.5554633140563965,
      "learning_rate": 0.00019827514599469128,
      "loss": 3.2015,
      "step": 192
    },
    {
      "epoch": 0.12518242257175288,
      "grad_norm": 1.476672887802124,
      "learning_rate": 0.00019825619491441914,
      "loss": 3.0183,
      "step": 193
    },
    {
      "epoch": 0.12583103616020755,
      "grad_norm": 1.6196556091308594,
      "learning_rate": 0.0001982371412094417,
      "loss": 3.1581,
      "step": 194
    },
    {
      "epoch": 0.12647964974866224,
      "grad_norm": 1.4986144304275513,
      "learning_rate": 0.0001982179848996599,
      "loss": 3.2815,
      "step": 195
    },
    {
      "epoch": 0.1271282633371169,
      "grad_norm": 1.511244773864746,
      "learning_rate": 0.00019819872600508162,
      "loss": 3.1595,
      "step": 196
    },
    {
      "epoch": 0.1277768769255716,
      "grad_norm": 1.9068719148635864,
      "learning_rate": 0.00019817936454582212,
      "loss": 3.3151,
      "step": 197
    },
    {
      "epoch": 0.12842549051402627,
      "grad_norm": 2.2623164653778076,
      "learning_rate": 0.00019815990054210361,
      "loss": 3.6853,
      "step": 198
    },
    {
      "epoch": 0.12907410410248094,
      "grad_norm": 1.4253089427947998,
      "learning_rate": 0.00019814033401425554,
      "loss": 2.919,
      "step": 199
    },
    {
      "epoch": 0.12972271769093563,
      "grad_norm": 1.7597752809524536,
      "learning_rate": 0.0001981206649827143,
      "loss": 3.3967,
      "step": 200
    },
    {
      "epoch": 0.12972271769093563,
      "eval_loss": 3.2505762577056885,
      "eval_runtime": 35.0313,
      "eval_samples_per_second": 58.69,
      "eval_steps_per_second": 14.673,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 3084,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4419086016512e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}