{
  "best_metric": 0.5969458818435669,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.27434842249657065,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013717421124828531,
      "grad_norm": 1.8108248710632324,
      "learning_rate": 1e-05,
      "loss": 2.1791,
      "step": 1
    },
    {
      "epoch": 0.0013717421124828531,
      "eval_loss": 2.359384059906006,
      "eval_runtime": 102.5952,
      "eval_samples_per_second": 11.969,
      "eval_steps_per_second": 2.992,
      "step": 1
    },
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 2.168975591659546,
      "learning_rate": 2e-05,
      "loss": 2.4753,
      "step": 2
    },
    {
      "epoch": 0.00411522633744856,
      "grad_norm": 1.929791808128357,
      "learning_rate": 3e-05,
      "loss": 2.5551,
      "step": 3
    },
    {
      "epoch": 0.0054869684499314125,
      "grad_norm": 2.3733065128326416,
      "learning_rate": 4e-05,
      "loss": 2.6526,
      "step": 4
    },
    {
      "epoch": 0.006858710562414266,
      "grad_norm": 2.5940165519714355,
      "learning_rate": 5e-05,
      "loss": 2.4588,
      "step": 5
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 2.2310335636138916,
      "learning_rate": 6e-05,
      "loss": 2.5103,
      "step": 6
    },
    {
      "epoch": 0.009602194787379973,
      "grad_norm": 1.8037067651748657,
      "learning_rate": 7e-05,
      "loss": 2.1907,
      "step": 7
    },
    {
      "epoch": 0.010973936899862825,
      "grad_norm": 1.7454071044921875,
      "learning_rate": 8e-05,
      "loss": 1.7885,
      "step": 8
    },
    {
      "epoch": 0.012345679012345678,
      "grad_norm": 1.7510610818862915,
      "learning_rate": 9e-05,
      "loss": 1.554,
      "step": 9
    },
    {
      "epoch": 0.013717421124828532,
      "grad_norm": 1.5554914474487305,
      "learning_rate": 0.0001,
      "loss": 1.475,
      "step": 10
    },
    {
      "epoch": 0.015089163237311385,
      "grad_norm": 1.3975311517715454,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.346,
      "step": 11
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 1.5020421743392944,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.2495,
      "step": 12
    },
    {
      "epoch": 0.01783264746227709,
      "grad_norm": 1.7484345436096191,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.2833,
      "step": 13
    },
    {
      "epoch": 0.019204389574759947,
      "grad_norm": 1.5758137702941895,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.2012,
      "step": 14
    },
    {
      "epoch": 0.0205761316872428,
      "grad_norm": 1.180163860321045,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1123,
      "step": 15
    },
    {
      "epoch": 0.02194787379972565,
      "grad_norm": 1.1840097904205322,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0274,
      "step": 16
    },
    {
      "epoch": 0.023319615912208505,
      "grad_norm": 1.1171801090240479,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.1094,
      "step": 17
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 1.2143296003341675,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.0646,
      "step": 18
    },
    {
      "epoch": 0.02606310013717421,
      "grad_norm": 1.1554465293884277,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.1274,
      "step": 19
    },
    {
      "epoch": 0.027434842249657063,
      "grad_norm": 0.978050947189331,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8353,
      "step": 20
    },
    {
      "epoch": 0.02880658436213992,
      "grad_norm": 1.0037025213241577,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9977,
      "step": 21
    },
    {
      "epoch": 0.03017832647462277,
      "grad_norm": 1.0239306688308716,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.945,
      "step": 22
    },
    {
      "epoch": 0.03155006858710562,
      "grad_norm": 1.0410940647125244,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8752,
      "step": 23
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 1.0184775590896606,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8255,
      "step": 24
    },
    {
      "epoch": 0.03429355281207133,
      "grad_norm": 0.9275608658790588,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.9649,
      "step": 25
    },
    {
      "epoch": 0.03566529492455418,
      "grad_norm": 0.884083092212677,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8024,
      "step": 26
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.0138894319534302,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.879,
      "step": 27
    },
    {
      "epoch": 0.038408779149519894,
      "grad_norm": 1.2958335876464844,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.845,
      "step": 28
    },
    {
      "epoch": 0.039780521262002745,
      "grad_norm": 0.8304831981658936,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8288,
      "step": 29
    },
    {
      "epoch": 0.0411522633744856,
      "grad_norm": 0.850218653678894,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9146,
      "step": 30
    },
    {
      "epoch": 0.04252400548696845,
      "grad_norm": 1.0305699110031128,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8331,
      "step": 31
    },
    {
      "epoch": 0.0438957475994513,
      "grad_norm": 0.8513186573982239,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7539,
      "step": 32
    },
    {
      "epoch": 0.04526748971193416,
      "grad_norm": 0.9753694534301758,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8104,
      "step": 33
    },
    {
      "epoch": 0.04663923182441701,
      "grad_norm": 0.9042930603027344,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8383,
      "step": 34
    },
    {
      "epoch": 0.04801097393689986,
      "grad_norm": 1.0121922492980957,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.9992,
      "step": 35
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.9063836932182312,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8403,
      "step": 36
    },
    {
      "epoch": 0.05075445816186557,
      "grad_norm": 0.7969421148300171,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8814,
      "step": 37
    },
    {
      "epoch": 0.05212620027434842,
      "grad_norm": 0.8667128086090088,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8195,
      "step": 38
    },
    {
      "epoch": 0.053497942386831275,
      "grad_norm": 0.7646212577819824,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.731,
      "step": 39
    },
    {
      "epoch": 0.05486968449931413,
      "grad_norm": 0.8752400875091553,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.792,
      "step": 40
    },
    {
      "epoch": 0.056241426611796985,
      "grad_norm": 0.7880658507347107,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8621,
      "step": 41
    },
    {
      "epoch": 0.05761316872427984,
      "grad_norm": 0.7580417990684509,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7901,
      "step": 42
    },
    {
      "epoch": 0.05898491083676269,
      "grad_norm": 0.8328334093093872,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.876,
      "step": 43
    },
    {
      "epoch": 0.06035665294924554,
      "grad_norm": 0.7832382321357727,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7966,
      "step": 44
    },
    {
      "epoch": 0.06172839506172839,
      "grad_norm": 0.9131791591644287,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8224,
      "step": 45
    },
    {
      "epoch": 0.06310013717421124,
      "grad_norm": 0.853861927986145,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8777,
      "step": 46
    },
    {
      "epoch": 0.0644718792866941,
      "grad_norm": 0.8206557631492615,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7516,
      "step": 47
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 0.8616703748703003,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7658,
      "step": 48
    },
    {
      "epoch": 0.06721536351165981,
      "grad_norm": 0.7976633310317993,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7094,
      "step": 49
    },
    {
      "epoch": 0.06858710562414266,
      "grad_norm": 0.9627761244773865,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7091,
      "step": 50
    },
    {
      "epoch": 0.06858710562414266,
      "eval_loss": 0.7677202820777893,
      "eval_runtime": 104.2498,
      "eval_samples_per_second": 11.779,
      "eval_steps_per_second": 2.945,
      "step": 50
    },
    {
      "epoch": 0.06995884773662552,
      "grad_norm": 0.8886013627052307,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.0666,
      "step": 51
    },
    {
      "epoch": 0.07133058984910837,
      "grad_norm": 0.9581699967384338,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0,
      "step": 52
    },
    {
      "epoch": 0.07270233196159122,
      "grad_norm": 0.7953754663467407,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0147,
      "step": 53
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.7907536029815674,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8676,
      "step": 54
    },
    {
      "epoch": 0.07544581618655692,
      "grad_norm": 0.7577344179153442,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.9509,
      "step": 55
    },
    {
      "epoch": 0.07681755829903979,
      "grad_norm": 0.980762779712677,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8895,
      "step": 56
    },
    {
      "epoch": 0.07818930041152264,
      "grad_norm": 0.8946378827095032,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.867,
      "step": 57
    },
    {
      "epoch": 0.07956104252400549,
      "grad_norm": 0.9008687734603882,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8059,
      "step": 58
    },
    {
      "epoch": 0.08093278463648834,
      "grad_norm": 0.8883490562438965,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7215,
      "step": 59
    },
    {
      "epoch": 0.0823045267489712,
      "grad_norm": 0.8660940527915955,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.705,
      "step": 60
    },
    {
      "epoch": 0.08367626886145405,
      "grad_norm": 0.8446040153503418,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.8148,
      "step": 61
    },
    {
      "epoch": 0.0850480109739369,
      "grad_norm": 0.7114365696907043,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7353,
      "step": 62
    },
    {
      "epoch": 0.08641975308641975,
      "grad_norm": 0.6913666725158691,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7051,
      "step": 63
    },
    {
      "epoch": 0.0877914951989026,
      "grad_norm": 0.7440309524536133,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6897,
      "step": 64
    },
    {
      "epoch": 0.08916323731138547,
      "grad_norm": 0.6593201756477356,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7488,
      "step": 65
    },
    {
      "epoch": 0.09053497942386832,
      "grad_norm": 0.8882130980491638,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7327,
      "step": 66
    },
    {
      "epoch": 0.09190672153635117,
      "grad_norm": 0.7141872644424438,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.763,
      "step": 67
    },
    {
      "epoch": 0.09327846364883402,
      "grad_norm": 0.7310812473297119,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6181,
      "step": 68
    },
    {
      "epoch": 0.09465020576131687,
      "grad_norm": 0.6965682506561279,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.736,
      "step": 69
    },
    {
      "epoch": 0.09602194787379972,
      "grad_norm": 0.6382268071174622,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.666,
      "step": 70
    },
    {
      "epoch": 0.09739368998628258,
      "grad_norm": 0.738567054271698,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7502,
      "step": 71
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.7237371802330017,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7352,
      "step": 72
    },
    {
      "epoch": 0.10013717421124829,
      "grad_norm": 0.6134920716285706,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.699,
      "step": 73
    },
    {
      "epoch": 0.10150891632373114,
      "grad_norm": 0.6023762822151184,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.5733,
      "step": 74
    },
    {
      "epoch": 0.102880658436214,
      "grad_norm": 0.7722994685173035,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.712,
      "step": 75
    },
    {
      "epoch": 0.10425240054869685,
      "grad_norm": 0.6359792351722717,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6032,
      "step": 76
    },
    {
      "epoch": 0.1056241426611797,
      "grad_norm": 1.0157991647720337,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6771,
      "step": 77
    },
    {
      "epoch": 0.10699588477366255,
      "grad_norm": 0.7552648186683655,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8228,
      "step": 78
    },
    {
      "epoch": 0.1083676268861454,
      "grad_norm": 0.6754823923110962,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7058,
      "step": 79
    },
    {
      "epoch": 0.10973936899862825,
      "grad_norm": 0.7087421417236328,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7568,
      "step": 80
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.907531201839447,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7217,
      "step": 81
    },
    {
      "epoch": 0.11248285322359397,
      "grad_norm": 0.6867223381996155,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.6275,
      "step": 82
    },
    {
      "epoch": 0.11385459533607682,
      "grad_norm": 0.6423940658569336,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.5992,
      "step": 83
    },
    {
      "epoch": 0.11522633744855967,
      "grad_norm": 0.7836233973503113,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7563,
      "step": 84
    },
    {
      "epoch": 0.11659807956104253,
      "grad_norm": 0.7429043054580688,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7826,
      "step": 85
    },
    {
      "epoch": 0.11796982167352538,
      "grad_norm": 0.7121160626411438,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6765,
      "step": 86
    },
    {
      "epoch": 0.11934156378600823,
      "grad_norm": 0.6519823670387268,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6412,
      "step": 87
    },
    {
      "epoch": 0.12071330589849108,
      "grad_norm": 0.7616689801216125,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6675,
      "step": 88
    },
    {
      "epoch": 0.12208504801097393,
      "grad_norm": 0.7042734026908875,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6333,
      "step": 89
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 0.7615177035331726,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.6755,
      "step": 90
    },
    {
      "epoch": 0.12482853223593965,
      "grad_norm": 0.6770451068878174,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6777,
      "step": 91
    },
    {
      "epoch": 0.1262002743484225,
      "grad_norm": 0.7251375913619995,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7271,
      "step": 92
    },
    {
      "epoch": 0.12757201646090535,
      "grad_norm": 0.762030839920044,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7694,
      "step": 93
    },
    {
      "epoch": 0.1289437585733882,
      "grad_norm": 0.7940636873245239,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.67,
      "step": 94
    },
    {
      "epoch": 0.13031550068587106,
      "grad_norm": 0.7140344381332397,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7463,
      "step": 95
    },
    {
      "epoch": 0.13168724279835392,
      "grad_norm": 0.8514577150344849,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7389,
      "step": 96
    },
    {
      "epoch": 0.13305898491083676,
      "grad_norm": 0.8461818099021912,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7734,
      "step": 97
    },
    {
      "epoch": 0.13443072702331962,
      "grad_norm": 0.6528753042221069,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5591,
      "step": 98
    },
    {
      "epoch": 0.13580246913580246,
      "grad_norm": 0.829468846321106,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.693,
      "step": 99
    },
    {
      "epoch": 0.13717421124828533,
      "grad_norm": 0.6663625240325928,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5723,
      "step": 100
    },
    {
      "epoch": 0.13717421124828533,
      "eval_loss": 0.672206699848175,
      "eval_runtime": 104.206,
      "eval_samples_per_second": 11.784,
      "eval_steps_per_second": 2.946,
      "step": 100
    },
    {
      "epoch": 0.13854595336076816,
      "grad_norm": 0.8562477231025696,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.8562,
      "step": 101
    },
    {
      "epoch": 0.13991769547325103,
      "grad_norm": 0.7904437780380249,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8184,
      "step": 102
    },
    {
      "epoch": 0.1412894375857339,
      "grad_norm": 0.7612579464912415,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.7431,
      "step": 103
    },
    {
      "epoch": 0.14266117969821673,
      "grad_norm": 0.7944357991218567,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8306,
      "step": 104
    },
    {
      "epoch": 0.1440329218106996,
      "grad_norm": 0.8757091164588928,
      "learning_rate": 5e-05,
      "loss": 0.8112,
      "step": 105
    },
    {
      "epoch": 0.14540466392318244,
      "grad_norm": 0.8323887586593628,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.845,
      "step": 106
    },
    {
      "epoch": 0.1467764060356653,
      "grad_norm": 1.0452089309692383,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.8206,
      "step": 107
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.8026246428489685,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.6358,
      "step": 108
    },
    {
      "epoch": 0.149519890260631,
      "grad_norm": 0.7053074240684509,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6551,
      "step": 109
    },
    {
      "epoch": 0.15089163237311384,
      "grad_norm": 0.7820671200752258,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.7273,
      "step": 110
    },
    {
      "epoch": 0.1522633744855967,
      "grad_norm": 0.6408292055130005,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.6921,
      "step": 111
    },
    {
      "epoch": 0.15363511659807957,
      "grad_norm": 0.8520627021789551,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.6687,
      "step": 112
    },
    {
      "epoch": 0.1550068587105624,
      "grad_norm": 0.8060234785079956,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7333,
      "step": 113
    },
    {
      "epoch": 0.15637860082304528,
      "grad_norm": 0.7795156240463257,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6638,
      "step": 114
    },
    {
      "epoch": 0.15775034293552812,
      "grad_norm": 0.7019467353820801,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6059,
      "step": 115
    },
    {
      "epoch": 0.15912208504801098,
      "grad_norm": 0.612472414970398,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5828,
      "step": 116
    },
    {
      "epoch": 0.16049382716049382,
      "grad_norm": 0.6435325741767883,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.6374,
      "step": 117
    },
    {
      "epoch": 0.16186556927297668,
      "grad_norm": 0.5975001454353333,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.6109,
      "step": 118
    },
    {
      "epoch": 0.16323731138545952,
      "grad_norm": 0.7002080082893372,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7187,
      "step": 119
    },
    {
      "epoch": 0.1646090534979424,
      "grad_norm": 0.6034038066864014,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.546,
      "step": 120
    },
    {
      "epoch": 0.16598079561042525,
      "grad_norm": 0.6676492691040039,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6277,
      "step": 121
    },
    {
      "epoch": 0.1673525377229081,
      "grad_norm": 0.6104670763015747,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6314,
      "step": 122
    },
    {
      "epoch": 0.16872427983539096,
      "grad_norm": 0.6292206645011902,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5635,
      "step": 123
    },
    {
      "epoch": 0.1700960219478738,
      "grad_norm": 0.7178395390510559,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5409,
      "step": 124
    },
    {
      "epoch": 0.17146776406035666,
      "grad_norm": 0.8147343397140503,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.6926,
      "step": 125
    },
    {
      "epoch": 0.1728395061728395,
      "grad_norm": 0.6960216760635376,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.5881,
      "step": 126
    },
    {
      "epoch": 0.17421124828532236,
      "grad_norm": 0.7283644080162048,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.6052,
      "step": 127
    },
    {
      "epoch": 0.1755829903978052,
      "grad_norm": 0.6765355467796326,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.655,
      "step": 128
    },
    {
      "epoch": 0.17695473251028807,
      "grad_norm": 0.6663551926612854,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.6652,
      "step": 129
    },
    {
      "epoch": 0.17832647462277093,
      "grad_norm": 0.6969720721244812,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.5723,
      "step": 130
    },
    {
      "epoch": 0.17969821673525377,
      "grad_norm": 0.7039170861244202,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.5804,
      "step": 131
    },
    {
      "epoch": 0.18106995884773663,
      "grad_norm": 0.7064164280891418,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.6461,
      "step": 132
    },
    {
      "epoch": 0.18244170096021947,
      "grad_norm": 0.7170747518539429,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.6305,
      "step": 133
    },
    {
      "epoch": 0.18381344307270234,
      "grad_norm": 0.6113563776016235,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.5905,
      "step": 134
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.6517019271850586,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.5822,
      "step": 135
    },
    {
      "epoch": 0.18655692729766804,
      "grad_norm": 0.7371748685836792,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.6782,
      "step": 136
    },
    {
      "epoch": 0.18792866941015088,
      "grad_norm": 0.6541342735290527,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.537,
      "step": 137
    },
    {
      "epoch": 0.18930041152263374,
      "grad_norm": 0.6819432377815247,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.5513,
      "step": 138
    },
    {
      "epoch": 0.1906721536351166,
      "grad_norm": 0.7174123525619507,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6587,
      "step": 139
    },
    {
      "epoch": 0.19204389574759945,
      "grad_norm": 0.7462933659553528,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6906,
      "step": 140
    },
    {
      "epoch": 0.1934156378600823,
      "grad_norm": 0.7279201745986938,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.66,
      "step": 141
    },
    {
      "epoch": 0.19478737997256515,
      "grad_norm": 0.6597824692726135,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.5869,
      "step": 142
    },
    {
      "epoch": 0.19615912208504802,
      "grad_norm": 0.679593563079834,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7251,
      "step": 143
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.7546609044075012,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.6566,
      "step": 144
    },
    {
      "epoch": 0.19890260631001372,
      "grad_norm": 0.6918153762817383,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7013,
      "step": 145
    },
    {
      "epoch": 0.20027434842249658,
      "grad_norm": 0.7258621454238892,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6628,
      "step": 146
    },
    {
      "epoch": 0.20164609053497942,
      "grad_norm": 0.7612497210502625,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5154,
      "step": 147
    },
    {
      "epoch": 0.2030178326474623,
      "grad_norm": 0.6649760603904724,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.6336,
      "step": 148
    },
    {
      "epoch": 0.20438957475994513,
      "grad_norm": 0.7184985876083374,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6192,
      "step": 149
    },
    {
      "epoch": 0.205761316872428,
      "grad_norm": 0.6290855407714844,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5122,
      "step": 150
    },
    {
      "epoch": 0.205761316872428,
      "eval_loss": 0.6107121109962463,
      "eval_runtime": 103.8833,
      "eval_samples_per_second": 11.821,
      "eval_steps_per_second": 2.955,
      "step": 150
    },
    {
      "epoch": 0.20713305898491083,
      "grad_norm": 0.8412699699401855,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.8167,
      "step": 151
    },
    {
      "epoch": 0.2085048010973937,
      "grad_norm": 0.7035219669342041,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.6823,
      "step": 152
    },
    {
      "epoch": 0.20987654320987653,
      "grad_norm": 0.7104437947273254,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.6701,
      "step": 153
    },
    {
      "epoch": 0.2112482853223594,
      "grad_norm": 0.6493154764175415,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.7611,
      "step": 154
    },
    {
      "epoch": 0.21262002743484226,
      "grad_norm": 0.7417904734611511,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7218,
      "step": 155
    },
    {
      "epoch": 0.2139917695473251,
      "grad_norm": 0.7097898721694946,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.6828,
      "step": 156
    },
    {
      "epoch": 0.21536351165980797,
      "grad_norm": 0.7343249320983887,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.723,
      "step": 157
    },
    {
      "epoch": 0.2167352537722908,
      "grad_norm": 0.815818190574646,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.6736,
      "step": 158
    },
    {
      "epoch": 0.21810699588477367,
      "grad_norm": 0.6389595866203308,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.556,
      "step": 159
    },
    {
      "epoch": 0.2194787379972565,
      "grad_norm": 0.7238613367080688,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.6268,
      "step": 160
    },
    {
      "epoch": 0.22085048010973937,
      "grad_norm": 0.7338687181472778,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.6671,
      "step": 161
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.7689810991287231,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6173,
      "step": 162
    },
    {
      "epoch": 0.22359396433470508,
      "grad_norm": 0.7819945216178894,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.6166,
      "step": 163
    },
    {
      "epoch": 0.22496570644718794,
      "grad_norm": 0.6502705216407776,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.6235,
      "step": 164
    },
    {
      "epoch": 0.22633744855967078,
      "grad_norm": 0.6586165428161621,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.5372,
      "step": 165
    },
    {
      "epoch": 0.22770919067215364,
      "grad_norm": 0.6288943290710449,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.6276,
      "step": 166
    },
    {
      "epoch": 0.22908093278463648,
      "grad_norm": 0.721246063709259,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6393,
      "step": 167
    },
    {
      "epoch": 0.23045267489711935,
      "grad_norm": 0.6689321994781494,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.59,
      "step": 168
    },
    {
      "epoch": 0.23182441700960219,
      "grad_norm": 0.7488172054290771,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.622,
      "step": 169
    },
    {
      "epoch": 0.23319615912208505,
      "grad_norm": 0.6907728314399719,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.5844,
      "step": 170
    },
    {
      "epoch": 0.2345679012345679,
      "grad_norm": 0.5986167788505554,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.5409,
      "step": 171
    },
    {
      "epoch": 0.23593964334705075,
      "grad_norm": 0.655593752861023,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6123,
      "step": 172
    },
    {
      "epoch": 0.23731138545953362,
      "grad_norm": 0.5802649259567261,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.5298,
      "step": 173
    },
    {
      "epoch": 0.23868312757201646,
      "grad_norm": 0.6311508417129517,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.618,
      "step": 174
    },
    {
      "epoch": 0.24005486968449932,
      "grad_norm": 0.6052727699279785,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.5006,
      "step": 175
    },
    {
      "epoch": 0.24142661179698216,
      "grad_norm": 0.6206656098365784,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.5755,
      "step": 176
    },
    {
      "epoch": 0.24279835390946503,
      "grad_norm": 0.6726948618888855,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.559,
      "step": 177
    },
    {
      "epoch": 0.24417009602194786,
      "grad_norm": 0.543907642364502,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.4804,
      "step": 178
    },
    {
      "epoch": 0.24554183813443073,
      "grad_norm": 0.5792737007141113,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.5413,
      "step": 179
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 0.6379660964012146,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6109,
      "step": 180
    },
    {
      "epoch": 0.24828532235939643,
      "grad_norm": 0.6824044585227966,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5906,
      "step": 181
    },
    {
      "epoch": 0.2496570644718793,
      "grad_norm": 0.5448079705238342,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.516,
      "step": 182
    },
    {
      "epoch": 0.25102880658436216,
      "grad_norm": 0.6041187047958374,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.5567,
      "step": 183
    },
    {
      "epoch": 0.252400548696845,
      "grad_norm": 0.6621652841567993,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.5803,
      "step": 184
    },
    {
      "epoch": 0.25377229080932784,
      "grad_norm": 0.7022476196289062,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6153,
      "step": 185
    },
    {
      "epoch": 0.2551440329218107,
      "grad_norm": 0.7221360206604004,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.5139,
      "step": 186
    },
    {
      "epoch": 0.25651577503429357,
      "grad_norm": 0.8074687719345093,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.6357,
      "step": 187
    },
    {
      "epoch": 0.2578875171467764,
      "grad_norm": 0.5829501152038574,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.4931,
      "step": 188
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.6312186121940613,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.5368,
      "step": 189
    },
    {
      "epoch": 0.2606310013717421,
      "grad_norm": 0.7040186524391174,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6182,
      "step": 190
    },
    {
      "epoch": 0.262002743484225,
      "grad_norm": 0.875453531742096,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.586,
      "step": 191
    },
    {
      "epoch": 0.26337448559670784,
      "grad_norm": 0.7327673435211182,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.6671,
      "step": 192
    },
    {
      "epoch": 0.26474622770919065,
      "grad_norm": 0.6968852281570435,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.6468,
      "step": 193
    },
    {
      "epoch": 0.2661179698216735,
      "grad_norm": 0.7647964358329773,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.7126,
      "step": 194
    },
    {
      "epoch": 0.2674897119341564,
      "grad_norm": 0.6941498517990112,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6302,
      "step": 195
    },
    {
      "epoch": 0.26886145404663925,
      "grad_norm": 0.7134644389152527,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.586,
      "step": 196
    },
    {
      "epoch": 0.27023319615912206,
      "grad_norm": 0.7716729640960693,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.7013,
      "step": 197
    },
    {
      "epoch": 0.2716049382716049,
      "grad_norm": 0.6042746305465698,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.5283,
      "step": 198
    },
    {
      "epoch": 0.2729766803840878,
      "grad_norm": 0.727422297000885,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6771,
      "step": 199
    },
    {
      "epoch": 0.27434842249657065,
      "grad_norm": 0.7105741500854492,
      "learning_rate": 0.0,
      "loss": 0.526,
      "step": 200
    },
    {
      "epoch": 0.27434842249657065,
      "eval_loss": 0.5969458818435669,
      "eval_runtime": 104.0919,
      "eval_samples_per_second": 11.797,
      "eval_steps_per_second": 2.949,
      "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": 3.139970027256545e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}