{
  "best_metric": 0.6435860395431519,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.15082956259426847,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001005530417295123,
      "grad_norm": 2.4352548122406006,
      "learning_rate": 1e-05,
      "loss": 0.6833,
      "step": 1
    },
    {
      "epoch": 0.001005530417295123,
      "eval_loss": 0.859174907207489,
      "eval_runtime": 144.4981,
      "eval_samples_per_second": 11.592,
      "eval_steps_per_second": 2.9,
      "step": 1
    },
    {
      "epoch": 0.002011060834590246,
      "grad_norm": 2.3664867877960205,
      "learning_rate": 2e-05,
      "loss": 0.6703,
      "step": 2
    },
    {
      "epoch": 0.0030165912518853697,
      "grad_norm": 2.0348565578460693,
      "learning_rate": 3e-05,
      "loss": 0.6261,
      "step": 3
    },
    {
      "epoch": 0.004022121669180492,
      "grad_norm": 0.7516242265701294,
      "learning_rate": 4e-05,
      "loss": 0.5305,
      "step": 4
    },
    {
      "epoch": 0.005027652086475616,
      "grad_norm": 1.6016530990600586,
      "learning_rate": 5e-05,
      "loss": 0.5401,
      "step": 5
    },
    {
      "epoch": 0.006033182503770739,
      "grad_norm": 0.9149666428565979,
      "learning_rate": 6e-05,
      "loss": 0.503,
      "step": 6
    },
    {
      "epoch": 0.007038712921065862,
      "grad_norm": 0.5540153980255127,
      "learning_rate": 7e-05,
      "loss": 0.4683,
      "step": 7
    },
    {
      "epoch": 0.008044243338360985,
      "grad_norm": 0.4465714693069458,
      "learning_rate": 8e-05,
      "loss": 0.4362,
      "step": 8
    },
    {
      "epoch": 0.00904977375565611,
      "grad_norm": 0.37307798862457275,
      "learning_rate": 9e-05,
      "loss": 0.4216,
      "step": 9
    },
    {
      "epoch": 0.010055304172951232,
      "grad_norm": 0.3346532881259918,
      "learning_rate": 0.0001,
      "loss": 0.426,
      "step": 10
    },
    {
      "epoch": 0.011060834590246356,
      "grad_norm": 0.2881012558937073,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.4022,
      "step": 11
    },
    {
      "epoch": 0.012066365007541479,
      "grad_norm": 0.252236008644104,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.3923,
      "step": 12
    },
    {
      "epoch": 0.013071895424836602,
      "grad_norm": 0.23015816509723663,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.3805,
      "step": 13
    },
    {
      "epoch": 0.014077425842131725,
      "grad_norm": 0.34804385900497437,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4176,
      "step": 14
    },
    {
      "epoch": 0.015082956259426848,
      "grad_norm": 0.23283986747264862,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4384,
      "step": 15
    },
    {
      "epoch": 0.01608848667672197,
      "grad_norm": 3.591134786605835,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.6849,
      "step": 16
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 0.9220762252807617,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.016,
      "step": 17
    },
    {
      "epoch": 0.01809954751131222,
      "grad_norm": 1.198287010192871,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9521,
      "step": 18
    },
    {
      "epoch": 0.019105077928607342,
      "grad_norm": 0.5396149158477783,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8114,
      "step": 19
    },
    {
      "epoch": 0.020110608345902465,
      "grad_norm": 0.3927422761917114,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8306,
      "step": 20
    },
    {
      "epoch": 0.021116138763197588,
      "grad_norm": 0.35858792066574097,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7893,
      "step": 21
    },
    {
      "epoch": 0.02212166918049271,
      "grad_norm": 0.3317579925060272,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.792,
      "step": 22
    },
    {
      "epoch": 0.023127199597787834,
      "grad_norm": 0.3556971549987793,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7937,
      "step": 23
    },
    {
      "epoch": 0.024132730015082957,
      "grad_norm": 0.3509909212589264,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8118,
      "step": 24
    },
    {
      "epoch": 0.02513826043237808,
      "grad_norm": 0.21706604957580566,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7938,
      "step": 25
    },
    {
      "epoch": 0.026143790849673203,
      "grad_norm": 0.3561152219772339,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8021,
      "step": 26
    },
    {
      "epoch": 0.027149321266968326,
      "grad_norm": 0.23132124543190002,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.783,
      "step": 27
    },
    {
      "epoch": 0.02815485168426345,
      "grad_norm": 0.22269226610660553,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7959,
      "step": 28
    },
    {
      "epoch": 0.029160382101558573,
      "grad_norm": 0.24683009088039398,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7602,
      "step": 29
    },
    {
      "epoch": 0.030165912518853696,
      "grad_norm": 0.25816789269447327,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.797,
      "step": 30
    },
    {
      "epoch": 0.03117144293614882,
      "grad_norm": 0.2194022387266159,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7661,
      "step": 31
    },
    {
      "epoch": 0.03217697335344394,
      "grad_norm": 0.20569732785224915,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7757,
      "step": 32
    },
    {
      "epoch": 0.033182503770739065,
      "grad_norm": 0.26061707735061646,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8045,
      "step": 33
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 0.2521941065788269,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.771,
      "step": 34
    },
    {
      "epoch": 0.03519356460532931,
      "grad_norm": 0.7167894244194031,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.9258,
      "step": 35
    },
    {
      "epoch": 0.03619909502262444,
      "grad_norm": 0.7023014426231384,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.9272,
      "step": 36
    },
    {
      "epoch": 0.03720462543991956,
      "grad_norm": 0.7939850091934204,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8852,
      "step": 37
    },
    {
      "epoch": 0.038210155857214684,
      "grad_norm": 0.37145453691482544,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8617,
      "step": 38
    },
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 0.36598095297813416,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8387,
      "step": 39
    },
    {
      "epoch": 0.04022121669180493,
      "grad_norm": 0.3641310930252075,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8293,
      "step": 40
    },
    {
      "epoch": 0.04122674710910005,
      "grad_norm": 0.40900740027427673,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8166,
      "step": 41
    },
    {
      "epoch": 0.042232277526395176,
      "grad_norm": 0.40440893173217773,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7699,
      "step": 42
    },
    {
      "epoch": 0.043237807943690296,
      "grad_norm": 0.4703547954559326,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.789,
      "step": 43
    },
    {
      "epoch": 0.04424333836098542,
      "grad_norm": 0.3685894012451172,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7647,
      "step": 44
    },
    {
      "epoch": 0.04524886877828054,
      "grad_norm": 0.36992567777633667,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7527,
      "step": 45
    },
    {
      "epoch": 0.04625439919557567,
      "grad_norm": 0.8148142099380493,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7516,
      "step": 46
    },
    {
      "epoch": 0.04725992961287079,
      "grad_norm": 2.1370339393615723,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7484,
      "step": 47
    },
    {
      "epoch": 0.048265460030165915,
      "grad_norm": 0.40228700637817383,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7357,
      "step": 48
    },
    {
      "epoch": 0.049270990447461034,
      "grad_norm": 0.6028892397880554,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7278,
      "step": 49
    },
    {
      "epoch": 0.05027652086475616,
      "grad_norm": 0.35520774126052856,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7097,
      "step": 50
    },
    {
      "epoch": 0.05027652086475616,
      "eval_loss": 0.7820449471473694,
      "eval_runtime": 145.6031,
      "eval_samples_per_second": 11.504,
      "eval_steps_per_second": 2.878,
      "step": 50
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 3.0911669731140137,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7859,
      "step": 51
    },
    {
      "epoch": 0.05228758169934641,
      "grad_norm": 1.030360221862793,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6146,
      "step": 52
    },
    {
      "epoch": 0.053293112116641526,
      "grad_norm": 0.717653751373291,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5158,
      "step": 53
    },
    {
      "epoch": 0.05429864253393665,
      "grad_norm": 0.537287175655365,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.4709,
      "step": 54
    },
    {
      "epoch": 0.05530417295123177,
      "grad_norm": 0.3627510368824005,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4339,
      "step": 55
    },
    {
      "epoch": 0.0563097033685269,
      "grad_norm": 0.2506343424320221,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.4205,
      "step": 56
    },
    {
      "epoch": 0.05731523378582202,
      "grad_norm": 0.24423518776893616,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.4194,
      "step": 57
    },
    {
      "epoch": 0.058320764203117145,
      "grad_norm": 0.29906725883483887,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.4156,
      "step": 58
    },
    {
      "epoch": 0.059326294620412265,
      "grad_norm": 0.22299951314926147,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.4193,
      "step": 59
    },
    {
      "epoch": 0.06033182503770739,
      "grad_norm": 0.20469671487808228,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3833,
      "step": 60
    },
    {
      "epoch": 0.06133735545500251,
      "grad_norm": 0.25047266483306885,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3803,
      "step": 61
    },
    {
      "epoch": 0.06234288587229764,
      "grad_norm": 0.17370571196079254,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.3761,
      "step": 62
    },
    {
      "epoch": 0.06334841628959276,
      "grad_norm": 0.27698203921318054,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.3905,
      "step": 63
    },
    {
      "epoch": 0.06435394670688788,
      "grad_norm": 0.14930705726146698,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.3794,
      "step": 64
    },
    {
      "epoch": 0.06535947712418301,
      "grad_norm": 0.2859864830970764,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.4343,
      "step": 65
    },
    {
      "epoch": 0.06636500754147813,
      "grad_norm": 0.3993275761604309,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.2331,
      "step": 66
    },
    {
      "epoch": 0.06737053795877325,
      "grad_norm": 2.1870105266571045,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.9635,
      "step": 67
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.7155138254165649,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.8389,
      "step": 68
    },
    {
      "epoch": 0.0693815987933635,
      "grad_norm": 0.3495980501174927,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7636,
      "step": 69
    },
    {
      "epoch": 0.07038712921065862,
      "grad_norm": 0.28488680720329285,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.779,
      "step": 70
    },
    {
      "epoch": 0.07139265962795374,
      "grad_norm": 0.321956068277359,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7593,
      "step": 71
    },
    {
      "epoch": 0.07239819004524888,
      "grad_norm": 0.30106544494628906,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7582,
      "step": 72
    },
    {
      "epoch": 0.073403720462544,
      "grad_norm": 0.2426968514919281,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7843,
      "step": 73
    },
    {
      "epoch": 0.07440925087983911,
      "grad_norm": 0.23462745547294617,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7782,
      "step": 74
    },
    {
      "epoch": 0.07541478129713423,
      "grad_norm": 0.19406434893608093,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7624,
      "step": 75
    },
    {
      "epoch": 0.07642031171442937,
      "grad_norm": 0.2184755802154541,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7927,
      "step": 76
    },
    {
      "epoch": 0.07742584213172449,
      "grad_norm": 0.21943315863609314,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7767,
      "step": 77
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 0.16851526498794556,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7379,
      "step": 78
    },
    {
      "epoch": 0.07943690296631473,
      "grad_norm": 0.19421535730361938,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7925,
      "step": 79
    },
    {
      "epoch": 0.08044243338360986,
      "grad_norm": 0.17354494333267212,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7493,
      "step": 80
    },
    {
      "epoch": 0.08144796380090498,
      "grad_norm": 0.1771775633096695,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7674,
      "step": 81
    },
    {
      "epoch": 0.0824534942182001,
      "grad_norm": 0.23186761140823364,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7458,
      "step": 82
    },
    {
      "epoch": 0.08345902463549522,
      "grad_norm": 0.19266724586486816,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.7253,
      "step": 83
    },
    {
      "epoch": 0.08446455505279035,
      "grad_norm": 0.22116349637508392,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7195,
      "step": 84
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 0.3103989064693451,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.8048,
      "step": 85
    },
    {
      "epoch": 0.08647561588738059,
      "grad_norm": 0.443766713142395,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7976,
      "step": 86
    },
    {
      "epoch": 0.08748114630467571,
      "grad_norm": 0.7230583429336548,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8926,
      "step": 87
    },
    {
      "epoch": 0.08848667672197084,
      "grad_norm": 0.30479729175567627,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.8041,
      "step": 88
    },
    {
      "epoch": 0.08949220713926596,
      "grad_norm": 0.2751973867416382,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8375,
      "step": 89
    },
    {
      "epoch": 0.09049773755656108,
      "grad_norm": 0.5401359796524048,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7718,
      "step": 90
    },
    {
      "epoch": 0.0915032679738562,
      "grad_norm": 0.3586420714855194,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7999,
      "step": 91
    },
    {
      "epoch": 0.09250879839115134,
      "grad_norm": 0.26797112822532654,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7566,
      "step": 92
    },
    {
      "epoch": 0.09351432880844646,
      "grad_norm": 0.2583998739719391,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7565,
      "step": 93
    },
    {
      "epoch": 0.09451985922574158,
      "grad_norm": 0.258475661277771,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7338,
      "step": 94
    },
    {
      "epoch": 0.0955253896430367,
      "grad_norm": 0.22778931260108948,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7501,
      "step": 95
    },
    {
      "epoch": 0.09653092006033183,
      "grad_norm": 0.27645596861839294,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7565,
      "step": 96
    },
    {
      "epoch": 0.09753645047762695,
      "grad_norm": 0.28205233812332153,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7319,
      "step": 97
    },
    {
      "epoch": 0.09854198089492207,
      "grad_norm": 0.23500730097293854,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7307,
      "step": 98
    },
    {
      "epoch": 0.09954751131221719,
      "grad_norm": 0.17771759629249573,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7032,
      "step": 99
    },
    {
      "epoch": 0.10055304172951232,
      "grad_norm": 0.36362266540527344,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6929,
      "step": 100
    },
    {
      "epoch": 0.10055304172951232,
      "eval_loss": 0.771354079246521,
      "eval_runtime": 145.706,
      "eval_samples_per_second": 11.496,
      "eval_steps_per_second": 2.876,
      "step": 100
    },
    {
      "epoch": 0.10155857214680744,
      "grad_norm": 4.397695064544678,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.6436,
      "step": 101
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.6622849702835083,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.564,
      "step": 102
    },
    {
      "epoch": 0.1035696329813977,
      "grad_norm": 0.38446009159088135,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5081,
      "step": 103
    },
    {
      "epoch": 0.10457516339869281,
      "grad_norm": 0.3722815215587616,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.4774,
      "step": 104
    },
    {
      "epoch": 0.10558069381598793,
      "grad_norm": 0.3972223997116089,
      "learning_rate": 5e-05,
      "loss": 0.4457,
      "step": 105
    },
    {
      "epoch": 0.10658622423328305,
      "grad_norm": 0.3055289387702942,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4365,
      "step": 106
    },
    {
      "epoch": 0.10759175465057819,
      "grad_norm": 0.28584370017051697,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.4166,
      "step": 107
    },
    {
      "epoch": 0.1085972850678733,
      "grad_norm": 0.30272936820983887,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.3847,
      "step": 108
    },
    {
      "epoch": 0.10960281548516843,
      "grad_norm": 0.2166903167963028,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3942,
      "step": 109
    },
    {
      "epoch": 0.11060834590246355,
      "grad_norm": 0.22697070240974426,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3818,
      "step": 110
    },
    {
      "epoch": 0.11161387631975868,
      "grad_norm": 0.3706066310405731,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.3955,
      "step": 111
    },
    {
      "epoch": 0.1126194067370538,
      "grad_norm": 0.24521887302398682,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.3698,
      "step": 112
    },
    {
      "epoch": 0.11362493715434892,
      "grad_norm": 0.20502431690692902,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.39,
      "step": 113
    },
    {
      "epoch": 0.11463046757164404,
      "grad_norm": 0.3430691361427307,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4146,
      "step": 114
    },
    {
      "epoch": 0.11563599798893917,
      "grad_norm": 0.2945917844772339,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.3447,
      "step": 115
    },
    {
      "epoch": 0.11664152840623429,
      "grad_norm": 0.8488739132881165,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.9821,
      "step": 116
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.6183751225471497,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9052,
      "step": 117
    },
    {
      "epoch": 0.11865258924082453,
      "grad_norm": 0.6295905709266663,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8095,
      "step": 118
    },
    {
      "epoch": 0.11965811965811966,
      "grad_norm": 0.658058226108551,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7223,
      "step": 119
    },
    {
      "epoch": 0.12066365007541478,
      "grad_norm": 0.3815332055091858,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7446,
      "step": 120
    },
    {
      "epoch": 0.1216691804927099,
      "grad_norm": 0.45176973938941956,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7509,
      "step": 121
    },
    {
      "epoch": 0.12267471091000502,
      "grad_norm": 0.31807297468185425,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7303,
      "step": 122
    },
    {
      "epoch": 0.12368024132730016,
      "grad_norm": 0.20828258991241455,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7336,
      "step": 123
    },
    {
      "epoch": 0.12468577174459528,
      "grad_norm": 0.248319610953331,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.753,
      "step": 124
    },
    {
      "epoch": 0.1256913021618904,
      "grad_norm": 0.2716839015483856,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7684,
      "step": 125
    },
    {
      "epoch": 0.12669683257918551,
      "grad_norm": 0.24676644802093506,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7213,
      "step": 126
    },
    {
      "epoch": 0.12770236299648063,
      "grad_norm": 0.21484322845935822,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7585,
      "step": 127
    },
    {
      "epoch": 0.12870789341377575,
      "grad_norm": 0.1997540146112442,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7374,
      "step": 128
    },
    {
      "epoch": 0.1297134238310709,
      "grad_norm": 0.149921715259552,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.749,
      "step": 129
    },
    {
      "epoch": 0.13071895424836602,
      "grad_norm": 0.1527470201253891,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7825,
      "step": 130
    },
    {
      "epoch": 0.13172448466566114,
      "grad_norm": 0.19612222909927368,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7622,
      "step": 131
    },
    {
      "epoch": 0.13273001508295626,
      "grad_norm": 0.16798371076583862,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7769,
      "step": 132
    },
    {
      "epoch": 0.13373554550025138,
      "grad_norm": 0.1868869513273239,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7331,
      "step": 133
    },
    {
      "epoch": 0.1347410759175465,
      "grad_norm": 0.24473780393600464,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7863,
      "step": 134
    },
    {
      "epoch": 0.13574660633484162,
      "grad_norm": 1.1770341396331787,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7561,
      "step": 135
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.6070170998573303,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.8728,
      "step": 136
    },
    {
      "epoch": 0.13775766716943189,
      "grad_norm": 0.35857340693473816,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7889,
      "step": 137
    },
    {
      "epoch": 0.138763197586727,
      "grad_norm": 0.3490099608898163,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7993,
      "step": 138
    },
    {
      "epoch": 0.13976872800402212,
      "grad_norm": 0.3244432210922241,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.8064,
      "step": 139
    },
    {
      "epoch": 0.14077425842131724,
      "grad_norm": 0.27973413467407227,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7832,
      "step": 140
    },
    {
      "epoch": 0.14177978883861236,
      "grad_norm": 0.2573448717594147,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7433,
      "step": 141
    },
    {
      "epoch": 0.14278531925590748,
      "grad_norm": 0.2445351928472519,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7559,
      "step": 142
    },
    {
      "epoch": 0.1437908496732026,
      "grad_norm": 0.2401212453842163,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7547,
      "step": 143
    },
    {
      "epoch": 0.14479638009049775,
      "grad_norm": 0.2452555149793625,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.746,
      "step": 144
    },
    {
      "epoch": 0.14580191050779287,
      "grad_norm": 0.22607146203517914,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.749,
      "step": 145
    },
    {
      "epoch": 0.146807440925088,
      "grad_norm": 0.20661811530590057,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7128,
      "step": 146
    },
    {
      "epoch": 0.1478129713423831,
      "grad_norm": 0.20959605276584625,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.7274,
      "step": 147
    },
    {
      "epoch": 0.14881850175967823,
      "grad_norm": 0.16401396691799164,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7214,
      "step": 148
    },
    {
      "epoch": 0.14982403217697335,
      "grad_norm": 0.23852993547916412,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6941,
      "step": 149
    },
    {
      "epoch": 0.15082956259426847,
      "grad_norm": 0.18602079153060913,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6926,
      "step": 150
    },
    {
      "epoch": 0.15082956259426847,
      "eval_loss": 0.6435860395431519,
      "eval_runtime": 145.6929,
      "eval_samples_per_second": 11.497,
      "eval_steps_per_second": 2.876,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.243104078200832e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}