{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.021961128802020422,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010980564401010212,
      "grad_norm": 2.7161130905151367,
      "learning_rate": 1e-05,
      "loss": 8.6012,
      "step": 1
    },
    {
      "epoch": 0.00010980564401010212,
      "eval_loss": NaN,
      "eval_runtime": 737.1477,
      "eval_samples_per_second": 20.807,
      "eval_steps_per_second": 5.202,
      "step": 1
    },
    {
      "epoch": 0.00021961128802020424,
      "grad_norm": 3.004807949066162,
      "learning_rate": 2e-05,
      "loss": 8.2653,
      "step": 2
    },
    {
      "epoch": 0.00032941693203030636,
      "grad_norm": 3.3578619956970215,
      "learning_rate": 3e-05,
      "loss": 8.847,
      "step": 3
    },
    {
      "epoch": 0.0004392225760404085,
      "grad_norm": 3.37322998046875,
      "learning_rate": 4e-05,
      "loss": 8.7671,
      "step": 4
    },
    {
      "epoch": 0.0005490282200505106,
      "grad_norm": 3.2195563316345215,
      "learning_rate": 5e-05,
      "loss": 8.7924,
      "step": 5
    },
    {
      "epoch": 0.0006588338640606127,
      "grad_norm": 2.674182891845703,
      "learning_rate": 6e-05,
      "loss": 8.3141,
      "step": 6
    },
    {
      "epoch": 0.0007686395080707148,
      "grad_norm": 2.661257266998291,
      "learning_rate": 7e-05,
      "loss": 8.3609,
      "step": 7
    },
    {
      "epoch": 0.000878445152080817,
      "grad_norm": 2.7521419525146484,
      "learning_rate": 8e-05,
      "loss": 8.2754,
      "step": 8
    },
    {
      "epoch": 0.000988250796090919,
      "grad_norm": 3.07326602935791,
      "learning_rate": 9e-05,
      "loss": 8.6254,
      "step": 9
    },
    {
      "epoch": 0.0010980564401010212,
      "grad_norm": 3.248418092727661,
      "learning_rate": 0.0001,
      "loss": 8.5796,
      "step": 10
    },
    {
      "epoch": 0.0012078620841111233,
      "grad_norm": 2.995969533920288,
      "learning_rate": 9.999316524962345e-05,
      "loss": 8.2093,
      "step": 11
    },
    {
      "epoch": 0.0013176677281212254,
      "grad_norm": 3.205688714981079,
      "learning_rate": 9.997266286704631e-05,
      "loss": 8.2658,
      "step": 12
    },
    {
      "epoch": 0.0014274733721313276,
      "grad_norm": 3.046626567840576,
      "learning_rate": 9.993849845741524e-05,
      "loss": 8.012,
      "step": 13
    },
    {
      "epoch": 0.0015372790161414297,
      "grad_norm": 3.573356866836548,
      "learning_rate": 9.989068136093873e-05,
      "loss": 8.2981,
      "step": 14
    },
    {
      "epoch": 0.0016470846601515318,
      "grad_norm": 3.3220691680908203,
      "learning_rate": 9.98292246503335e-05,
      "loss": 7.7083,
      "step": 15
    },
    {
      "epoch": 0.001756890304161634,
      "grad_norm": 4.213425159454346,
      "learning_rate": 9.975414512725057e-05,
      "loss": 8.6166,
      "step": 16
    },
    {
      "epoch": 0.001866695948171736,
      "grad_norm": 3.786961078643799,
      "learning_rate": 9.966546331768191e-05,
      "loss": 7.9526,
      "step": 17
    },
    {
      "epoch": 0.001976501592181838,
      "grad_norm": 3.9734761714935303,
      "learning_rate": 9.956320346634876e-05,
      "loss": 7.8794,
      "step": 18
    },
    {
      "epoch": 0.00208630723619194,
      "grad_norm": 4.260437488555908,
      "learning_rate": 9.944739353007344e-05,
      "loss": 8.3705,
      "step": 19
    },
    {
      "epoch": 0.0021961128802020424,
      "grad_norm": 5.297092437744141,
      "learning_rate": 9.931806517013612e-05,
      "loss": 7.3302,
      "step": 20
    },
    {
      "epoch": 0.0023059185242121443,
      "grad_norm": 4.251699924468994,
      "learning_rate": 9.917525374361912e-05,
      "loss": 7.3464,
      "step": 21
    },
    {
      "epoch": 0.0024157241682222466,
      "grad_norm": 6.946352958679199,
      "learning_rate": 9.901899829374047e-05,
      "loss": 7.8851,
      "step": 22
    },
    {
      "epoch": 0.0025255298122323485,
      "grad_norm": 5.673103332519531,
      "learning_rate": 9.884934153917997e-05,
      "loss": 7.5413,
      "step": 23
    },
    {
      "epoch": 0.002635335456242451,
      "grad_norm": 5.916378498077393,
      "learning_rate": 9.86663298624003e-05,
      "loss": 7.4979,
      "step": 24
    },
    {
      "epoch": 0.0027451411002525528,
      "grad_norm": 6.43757963180542,
      "learning_rate": 9.847001329696653e-05,
      "loss": 7.3496,
      "step": 25
    },
    {
      "epoch": 0.002854946744262655,
      "grad_norm": 5.8122711181640625,
      "learning_rate": 9.826044551386744e-05,
      "loss": 7.5674,
      "step": 26
    },
    {
      "epoch": 0.002964752388272757,
      "grad_norm": 6.8075432777404785,
      "learning_rate": 9.803768380684242e-05,
      "loss": 6.1831,
      "step": 27
    },
    {
      "epoch": 0.0030745580322828594,
      "grad_norm": 7.1936211585998535,
      "learning_rate": 9.780178907671789e-05,
      "loss": 6.7105,
      "step": 28
    },
    {
      "epoch": 0.0031843636762929613,
      "grad_norm": 4.657627582550049,
      "learning_rate": 9.755282581475769e-05,
      "loss": 6.1084,
      "step": 29
    },
    {
      "epoch": 0.0032941693203030636,
      "grad_norm": 7.0909857749938965,
      "learning_rate": 9.729086208503174e-05,
      "loss": 7.7716,
      "step": 30
    },
    {
      "epoch": 0.0034039749643131655,
      "grad_norm": 6.1650919914245605,
      "learning_rate": 9.701596950580806e-05,
      "loss": 4.6458,
      "step": 31
    },
    {
      "epoch": 0.003513780608323268,
      "grad_norm": 7.23681640625,
      "learning_rate": 9.672822322997305e-05,
      "loss": 5.568,
      "step": 32
    },
    {
      "epoch": 0.0036235862523333697,
      "grad_norm": 5.733531951904297,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.8351,
      "step": 33
    },
    {
      "epoch": 0.003733391896343472,
      "grad_norm": 6.215145587921143,
      "learning_rate": 9.611448774886924e-05,
      "loss": 4.3953,
      "step": 34
    },
    {
      "epoch": 0.003843197540353574,
      "grad_norm": 6.279800891876221,
      "learning_rate": 9.578866633275288e-05,
      "loss": 4.7791,
      "step": 35
    },
    {
      "epoch": 0.003953003184363676,
      "grad_norm": 4.827843189239502,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.4756,
      "step": 36
    },
    {
      "epoch": 0.004062808828373779,
      "grad_norm": 4.591087818145752,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.0854,
      "step": 37
    },
    {
      "epoch": 0.00417261447238388,
      "grad_norm": 10.339739799499512,
      "learning_rate": 9.473646649103818e-05,
      "loss": 6.4096,
      "step": 38
    },
    {
      "epoch": 0.0042824201163939824,
      "grad_norm": 3.7601234912872314,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.9831,
      "step": 39
    },
    {
      "epoch": 0.004392225760404085,
      "grad_norm": 16.57860565185547,
      "learning_rate": 9.397368756032445e-05,
      "loss": 7.9202,
      "step": 40
    },
    {
      "epoch": 0.004502031404414187,
      "grad_norm": 5.044294834136963,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.8466,
      "step": 41
    },
    {
      "epoch": 0.004611837048424289,
      "grad_norm": 3.652592897415161,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9577,
      "step": 42
    },
    {
      "epoch": 0.004721642692434391,
      "grad_norm": 5.5954718589782715,
      "learning_rate": 9.273963562927695e-05,
      "loss": 4.0106,
      "step": 43
    },
    {
      "epoch": 0.004831448336444493,
      "grad_norm": 5.061215877532959,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.4645,
      "step": 44
    },
    {
      "epoch": 0.004941253980454596,
      "grad_norm": 3.15812087059021,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.2177,
      "step": 45
    },
    {
      "epoch": 0.005051059624464697,
      "grad_norm": 6.519346714019775,
      "learning_rate": 9.140044155740101e-05,
      "loss": 3.6067,
      "step": 46
    },
    {
      "epoch": 0.005160865268474799,
      "grad_norm": 6.544234275817871,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.275,
      "step": 47
    },
    {
      "epoch": 0.005270670912484902,
      "grad_norm": 5.094490051269531,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.3375,
      "step": 48
    },
    {
      "epoch": 0.005380476556495004,
      "grad_norm": 5.9715704917907715,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.9657,
      "step": 49
    },
    {
      "epoch": 0.0054902822005051055,
      "grad_norm": 0.0,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0054902822005051055,
      "eval_loss": NaN,
      "eval_runtime": 741.3812,
      "eval_samples_per_second": 20.688,
      "eval_steps_per_second": 5.173,
      "step": 50
    },
    {
      "epoch": 0.005600087844515208,
      "grad_norm": 9.463225364685059,
      "learning_rate": 8.894386393810563e-05,
      "loss": 9.6738,
      "step": 51
    },
    {
      "epoch": 0.00570989348852531,
      "grad_norm": 8.132834434509277,
      "learning_rate": 8.842005554284296e-05,
      "loss": 9.6316,
      "step": 52
    },
    {
      "epoch": 0.0058196991325354126,
      "grad_norm": 5.708906173706055,
      "learning_rate": 8.788574348801675e-05,
      "loss": 8.8454,
      "step": 53
    },
    {
      "epoch": 0.005929504776545514,
      "grad_norm": 3.9556775093078613,
      "learning_rate": 8.73410738492077e-05,
      "loss": 8.6647,
      "step": 54
    },
    {
      "epoch": 0.006039310420555616,
      "grad_norm": 2.9282186031341553,
      "learning_rate": 8.678619553365659e-05,
      "loss": 8.2555,
      "step": 55
    },
    {
      "epoch": 0.006149116064565719,
      "grad_norm": 2.401756763458252,
      "learning_rate": 8.622126023955446e-05,
      "loss": 7.9873,
      "step": 56
    },
    {
      "epoch": 0.006258921708575821,
      "grad_norm": 2.2049758434295654,
      "learning_rate": 8.564642241456986e-05,
      "loss": 7.9323,
      "step": 57
    },
    {
      "epoch": 0.0063687273525859225,
      "grad_norm": 2.1958506107330322,
      "learning_rate": 8.506183921362443e-05,
      "loss": 7.9758,
      "step": 58
    },
    {
      "epoch": 0.006478532996596025,
      "grad_norm": 2.2442681789398193,
      "learning_rate": 8.44676704559283e-05,
      "loss": 7.5856,
      "step": 59
    },
    {
      "epoch": 0.006588338640606127,
      "grad_norm": 2.557832956314087,
      "learning_rate": 8.386407858128706e-05,
      "loss": 7.6964,
      "step": 60
    },
    {
      "epoch": 0.0066981442846162295,
      "grad_norm": 2.753185510635376,
      "learning_rate": 8.32512286056924e-05,
      "loss": 8.4816,
      "step": 61
    },
    {
      "epoch": 0.006807949928626331,
      "grad_norm": 2.944416046142578,
      "learning_rate": 8.262928807620843e-05,
      "loss": 8.0642,
      "step": 62
    },
    {
      "epoch": 0.006917755572636433,
      "grad_norm": 2.9375786781311035,
      "learning_rate": 8.199842702516583e-05,
      "loss": 7.7386,
      "step": 63
    },
    {
      "epoch": 0.007027561216646536,
      "grad_norm": 2.9413585662841797,
      "learning_rate": 8.135881792367686e-05,
      "loss": 7.8791,
      "step": 64
    },
    {
      "epoch": 0.007137366860656638,
      "grad_norm": 3.0389130115509033,
      "learning_rate": 8.07106356344834e-05,
      "loss": 7.589,
      "step": 65
    },
    {
      "epoch": 0.0072471725046667395,
      "grad_norm": 2.980114459991455,
      "learning_rate": 8.005405736415126e-05,
      "loss": 8.1093,
      "step": 66
    },
    {
      "epoch": 0.007356978148676842,
      "grad_norm": 3.0315589904785156,
      "learning_rate": 7.938926261462366e-05,
      "loss": 7.553,
      "step": 67
    },
    {
      "epoch": 0.007466783792686944,
      "grad_norm": 3.9058520793914795,
      "learning_rate": 7.871643313414718e-05,
      "loss": 7.9683,
      "step": 68
    },
    {
      "epoch": 0.0075765894366970465,
      "grad_norm": 3.8679585456848145,
      "learning_rate": 7.803575286758364e-05,
      "loss": 7.6281,
      "step": 69
    },
    {
      "epoch": 0.007686395080707148,
      "grad_norm": 4.688099384307861,
      "learning_rate": 7.734740790612136e-05,
      "loss": 7.4288,
      "step": 70
    },
    {
      "epoch": 0.00779620072471725,
      "grad_norm": 4.150933265686035,
      "learning_rate": 7.66515864363997e-05,
      "loss": 6.8626,
      "step": 71
    },
    {
      "epoch": 0.007906006368727353,
      "grad_norm": 4.803603649139404,
      "learning_rate": 7.594847868906076e-05,
      "loss": 8.215,
      "step": 72
    },
    {
      "epoch": 0.008015812012737454,
      "grad_norm": 4.512092113494873,
      "learning_rate": 7.52382768867422e-05,
      "loss": 7.2232,
      "step": 73
    },
    {
      "epoch": 0.008125617656747557,
      "grad_norm": 4.6369194984436035,
      "learning_rate": 7.452117519152542e-05,
      "loss": 7.1716,
      "step": 74
    },
    {
      "epoch": 0.008235423300757659,
      "grad_norm": 4.765970706939697,
      "learning_rate": 7.379736965185368e-05,
      "loss": 5.8784,
      "step": 75
    },
    {
      "epoch": 0.00834522894476776,
      "grad_norm": 4.6872992515563965,
      "learning_rate": 7.30670581489344e-05,
      "loss": 5.4378,
      "step": 76
    },
    {
      "epoch": 0.008455034588777863,
      "grad_norm": 7.018468379974365,
      "learning_rate": 7.233044034264034e-05,
      "loss": 7.9395,
      "step": 77
    },
    {
      "epoch": 0.008564840232787965,
      "grad_norm": 6.165883541107178,
      "learning_rate": 7.158771761692464e-05,
      "loss": 3.8578,
      "step": 78
    },
    {
      "epoch": 0.008674645876798068,
      "grad_norm": 7.593461036682129,
      "learning_rate": 7.083909302476453e-05,
      "loss": 7.0937,
      "step": 79
    },
    {
      "epoch": 0.00878445152080817,
      "grad_norm": 6.752357482910156,
      "learning_rate": 7.008477123264848e-05,
      "loss": 3.9847,
      "step": 80
    },
    {
      "epoch": 0.008894257164818271,
      "grad_norm": 6.351367950439453,
      "learning_rate": 6.932495846462261e-05,
      "loss": 6.1021,
      "step": 81
    },
    {
      "epoch": 0.009004062808828374,
      "grad_norm": 10.381793975830078,
      "learning_rate": 6.855986244591104e-05,
      "loss": 4.6649,
      "step": 82
    },
    {
      "epoch": 0.009113868452838476,
      "grad_norm": 4.580819606781006,
      "learning_rate": 6.778969234612584e-05,
      "loss": 3.1031,
      "step": 83
    },
    {
      "epoch": 0.009223674096848577,
      "grad_norm": 4.219026565551758,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.049,
      "step": 84
    },
    {
      "epoch": 0.00933347974085868,
      "grad_norm": 3.4299182891845703,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.9404,
      "step": 85
    },
    {
      "epoch": 0.009443285384868782,
      "grad_norm": 5.052021026611328,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.6781,
      "step": 86
    },
    {
      "epoch": 0.009553091028878885,
      "grad_norm": 7.963156223297119,
      "learning_rate": 6.466250186922325e-05,
      "loss": 4.6172,
      "step": 87
    },
    {
      "epoch": 0.009662896672888987,
      "grad_norm": 4.278861999511719,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.9618,
      "step": 88
    },
    {
      "epoch": 0.009772702316899088,
      "grad_norm": 8.701187133789062,
      "learning_rate": 6.307399704769099e-05,
      "loss": 3.7099,
      "step": 89
    },
    {
      "epoch": 0.009882507960909191,
      "grad_norm": 5.64361047744751,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.8238,
      "step": 90
    },
    {
      "epoch": 0.009992313604919293,
      "grad_norm": 5.1440229415893555,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.888,
      "step": 91
    },
    {
      "epoch": 0.010102119248929394,
      "grad_norm": 3.518712043762207,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0734,
      "step": 92
    },
    {
      "epoch": 0.010211924892939497,
      "grad_norm": 2.053778648376465,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.1332,
      "step": 93
    },
    {
      "epoch": 0.010321730536949599,
      "grad_norm": 2.489741086959839,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.2033,
      "step": 94
    },
    {
      "epoch": 0.010431536180959702,
      "grad_norm": 0.421085387468338,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0271,
      "step": 95
    },
    {
      "epoch": 0.010541341824969803,
      "grad_norm": 3.636638641357422,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.5786,
      "step": 96
    },
    {
      "epoch": 0.010651147468979905,
      "grad_norm": 2.510557174682617,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.1571,
      "step": 97
    },
    {
      "epoch": 0.010760953112990008,
      "grad_norm": 1.3211489915847778,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0779,
      "step": 98
    },
    {
      "epoch": 0.01087075875700011,
      "grad_norm": 9.46850872039795,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.3132,
      "step": 99
    },
    {
      "epoch": 0.010980564401010211,
      "grad_norm": 0.0,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.010980564401010211,
      "eval_loss": NaN,
      "eval_runtime": 740.9038,
      "eval_samples_per_second": 20.702,
      "eval_steps_per_second": 5.176,
      "step": 100
    },
    {
      "epoch": 0.011090370045020314,
      "grad_norm": 20.45694351196289,
      "learning_rate": 5.330452921628497e-05,
      "loss": 10.5906,
      "step": 101
    },
    {
      "epoch": 0.011200175689030416,
      "grad_norm": 20.208576202392578,
      "learning_rate": 5.247918773366112e-05,
      "loss": 10.5516,
      "step": 102
    },
    {
      "epoch": 0.011309981333040519,
      "grad_norm": 16.03057289123535,
      "learning_rate": 5.165316846586541e-05,
      "loss": 10.2739,
      "step": 103
    },
    {
      "epoch": 0.01141978697705062,
      "grad_norm": 10.210489273071289,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 9.5909,
      "step": 104
    },
    {
      "epoch": 0.011529592621060722,
      "grad_norm": 6.760451316833496,
      "learning_rate": 5e-05,
      "loss": 8.9993,
      "step": 105
    },
    {
      "epoch": 0.011639398265070825,
      "grad_norm": 5.211626052856445,
      "learning_rate": 4.917330276168208e-05,
      "loss": 8.7965,
      "step": 106
    },
    {
      "epoch": 0.011749203909080927,
      "grad_norm": 4.2196807861328125,
      "learning_rate": 4.834683153413459e-05,
      "loss": 8.8297,
      "step": 107
    },
    {
      "epoch": 0.011859009553091028,
      "grad_norm": 3.3772363662719727,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 8.147,
      "step": 108
    },
    {
      "epoch": 0.011968815197101131,
      "grad_norm": 2.891902446746826,
      "learning_rate": 4.669547078371504e-05,
      "loss": 8.22,
      "step": 109
    },
    {
      "epoch": 0.012078620841111233,
      "grad_norm": 2.8242688179016113,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 8.0372,
      "step": 110
    },
    {
      "epoch": 0.012188426485121336,
      "grad_norm": 2.6514458656311035,
      "learning_rate": 4.504772348747687e-05,
      "loss": 7.6994,
      "step": 111
    },
    {
      "epoch": 0.012298232129131437,
      "grad_norm": 2.300794839859009,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 8.288,
      "step": 112
    },
    {
      "epoch": 0.012408037773141539,
      "grad_norm": 2.474613904953003,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 7.3987,
      "step": 113
    },
    {
      "epoch": 0.012517843417151642,
      "grad_norm": 2.609527111053467,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 7.8919,
      "step": 114
    },
    {
      "epoch": 0.012627649061161744,
      "grad_norm": 2.5009570121765137,
      "learning_rate": 4.17702704859633e-05,
      "loss": 7.3564,
      "step": 115
    },
    {
      "epoch": 0.012737454705171845,
      "grad_norm": 2.662105083465576,
      "learning_rate": 4.095597328339452e-05,
      "loss": 7.4941,
      "step": 116
    },
    {
      "epoch": 0.012847260349181948,
      "grad_norm": 3.0076329708099365,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 7.4937,
      "step": 117
    },
    {
      "epoch": 0.01295706599319205,
      "grad_norm": 3.004589080810547,
      "learning_rate": 3.933501846281267e-05,
      "loss": 7.2203,
      "step": 118
    },
    {
      "epoch": 0.013066871637202153,
      "grad_norm": 3.4633359909057617,
      "learning_rate": 3.852880399766243e-05,
      "loss": 7.6346,
      "step": 119
    },
    {
      "epoch": 0.013176677281212254,
      "grad_norm": 3.890493154525757,
      "learning_rate": 3.772572564296005e-05,
      "loss": 6.8105,
      "step": 120
    },
    {
      "epoch": 0.013286482925222356,
      "grad_norm": 3.7691519260406494,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 7.5134,
      "step": 121
    },
    {
      "epoch": 0.013396288569232459,
      "grad_norm": 3.8573248386383057,
      "learning_rate": 3.612985456190778e-05,
      "loss": 6.6637,
      "step": 122
    },
    {
      "epoch": 0.01350609421324256,
      "grad_norm": 4.269960880279541,
      "learning_rate": 3.533749813077677e-05,
      "loss": 7.3906,
      "step": 123
    },
    {
      "epoch": 0.013615899857252662,
      "grad_norm": 4.763161659240723,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 6.9964,
      "step": 124
    },
    {
      "epoch": 0.013725705501262765,
      "grad_norm": 4.414470195770264,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 7.1694,
      "step": 125
    },
    {
      "epoch": 0.013835511145272867,
      "grad_norm": 5.532976150512695,
      "learning_rate": 3.298534127791785e-05,
      "loss": 7.2089,
      "step": 126
    },
    {
      "epoch": 0.01394531678928297,
      "grad_norm": 4.728195667266846,
      "learning_rate": 3.221030765387417e-05,
      "loss": 4.5307,
      "step": 127
    },
    {
      "epoch": 0.014055122433293071,
      "grad_norm": 5.885075092315674,
      "learning_rate": 3.144013755408895e-05,
      "loss": 7.0725,
      "step": 128
    },
    {
      "epoch": 0.014164928077303173,
      "grad_norm": 4.972570896148682,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 5.6568,
      "step": 129
    },
    {
      "epoch": 0.014274733721313276,
      "grad_norm": 6.9741082191467285,
      "learning_rate": 2.991522876735154e-05,
      "loss": 6.1196,
      "step": 130
    },
    {
      "epoch": 0.014384539365323377,
      "grad_norm": 5.954209804534912,
      "learning_rate": 2.916090697523549e-05,
      "loss": 2.5699,
      "step": 131
    },
    {
      "epoch": 0.014494345009333479,
      "grad_norm": 4.719747066497803,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.9211,
      "step": 132
    },
    {
      "epoch": 0.014604150653343582,
      "grad_norm": 5.227957248687744,
      "learning_rate": 2.766955965735968e-05,
      "loss": 3.698,
      "step": 133
    },
    {
      "epoch": 0.014713956297353684,
      "grad_norm": 6.323407173156738,
      "learning_rate": 2.693294185106562e-05,
      "loss": 5.9789,
      "step": 134
    },
    {
      "epoch": 0.014823761941363787,
      "grad_norm": 5.449718952178955,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 4.8832,
      "step": 135
    },
    {
      "epoch": 0.014933567585373888,
      "grad_norm": 5.971116542816162,
      "learning_rate": 2.547882480847461e-05,
      "loss": 4.3537,
      "step": 136
    },
    {
      "epoch": 0.01504337322938399,
      "grad_norm": 3.7302913665771484,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.2352,
      "step": 137
    },
    {
      "epoch": 0.015153178873394093,
      "grad_norm": 4.9671454429626465,
      "learning_rate": 2.405152131093926e-05,
      "loss": 4.0662,
      "step": 138
    },
    {
      "epoch": 0.015262984517404194,
      "grad_norm": 7.596904754638672,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 5.2013,
      "step": 139
    },
    {
      "epoch": 0.015372790161414296,
      "grad_norm": 5.907480716705322,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 4.7367,
      "step": 140
    },
    {
      "epoch": 0.015482595805424399,
      "grad_norm": 3.6994857788085938,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.6144,
      "step": 141
    },
    {
      "epoch": 0.0155924014494345,
      "grad_norm": 7.294979095458984,
      "learning_rate": 2.128356686585282e-05,
      "loss": 3.4866,
      "step": 142
    },
    {
      "epoch": 0.015702207093444602,
      "grad_norm": 7.470644474029541,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.1506,
      "step": 143
    },
    {
      "epoch": 0.015812012737454705,
      "grad_norm": 6.4925384521484375,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.1371,
      "step": 144
    },
    {
      "epoch": 0.01592181838146481,
      "grad_norm": 6.598365306854248,
      "learning_rate": 1.928936436551661e-05,
      "loss": 2.4088,
      "step": 145
    },
    {
      "epoch": 0.016031624025474908,
      "grad_norm": 17.1204833984375,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.3349,
      "step": 146
    },
    {
      "epoch": 0.01614142966948501,
      "grad_norm": 4.782659530639648,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.4368,
      "step": 147
    },
    {
      "epoch": 0.016251235313495115,
      "grad_norm": 1.4083176851272583,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.289,
      "step": 148
    },
    {
      "epoch": 0.016361040957505214,
      "grad_norm": 0.5383197069168091,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.2754,
      "step": 149
    },
    {
      "epoch": 0.016470846601515318,
      "grad_norm": 2.5022101402282715,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.4931,
      "step": 150
    },
    {
      "epoch": 0.016470846601515318,
      "eval_loss": NaN,
      "eval_runtime": 741.4401,
      "eval_samples_per_second": 20.687,
      "eval_steps_per_second": 5.172,
      "step": 150
    },
    {
      "epoch": 0.01658065224552542,
      "grad_norm": 3.0889387130737305,
      "learning_rate": 1.553232954407171e-05,
      "loss": 8.3523,
      "step": 151
    },
    {
      "epoch": 0.01669045788953552,
      "grad_norm": 3.1849732398986816,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 8.1232,
      "step": 152
    },
    {
      "epoch": 0.016800263533545624,
      "grad_norm": 3.1280314922332764,
      "learning_rate": 1.435357758543015e-05,
      "loss": 8.2144,
      "step": 153
    },
    {
      "epoch": 0.016910069177555727,
      "grad_norm": 2.9414608478546143,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 7.9757,
      "step": 154
    },
    {
      "epoch": 0.01701987482156583,
      "grad_norm": 3.0714926719665527,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 7.8922,
      "step": 155
    },
    {
      "epoch": 0.01712968046557593,
      "grad_norm": 3.011420965194702,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 7.8759,
      "step": 156
    },
    {
      "epoch": 0.017239486109586033,
      "grad_norm": 2.951658248901367,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 8.1141,
      "step": 157
    },
    {
      "epoch": 0.017349291753596136,
      "grad_norm": 2.6962552070617676,
      "learning_rate": 1.157994445715706e-05,
      "loss": 7.9807,
      "step": 158
    },
    {
      "epoch": 0.017459097397606236,
      "grad_norm": 2.861264228820801,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 7.9556,
      "step": 159
    },
    {
      "epoch": 0.01756890304161634,
      "grad_norm": 3.118795156478882,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 7.9712,
      "step": 160
    },
    {
      "epoch": 0.017678708685626442,
      "grad_norm": 2.927898645401001,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 8.4965,
      "step": 161
    },
    {
      "epoch": 0.017788514329636542,
      "grad_norm": 2.930448293685913,
      "learning_rate": 9.549150281252633e-06,
      "loss": 7.9375,
      "step": 162
    },
    {
      "epoch": 0.017898319973646645,
      "grad_norm": 2.924659013748169,
      "learning_rate": 9.068759265665384e-06,
      "loss": 7.7409,
      "step": 163
    },
    {
      "epoch": 0.01800812561765675,
      "grad_norm": 3.2053565979003906,
      "learning_rate": 8.599558442598998e-06,
      "loss": 8.3463,
      "step": 164
    },
    {
      "epoch": 0.018117931261666848,
      "grad_norm": 3.1684060096740723,
      "learning_rate": 8.141676086873572e-06,
      "loss": 7.6019,
      "step": 165
    },
    {
      "epoch": 0.01822773690567695,
      "grad_norm": 3.3047680854797363,
      "learning_rate": 7.695237378953223e-06,
      "loss": 7.7493,
      "step": 166
    },
    {
      "epoch": 0.018337542549687055,
      "grad_norm": 3.415890693664551,
      "learning_rate": 7.260364370723044e-06,
      "loss": 7.6015,
      "step": 167
    },
    {
      "epoch": 0.018447348193697154,
      "grad_norm": 3.6551132202148438,
      "learning_rate": 6.837175952121306e-06,
      "loss": 7.6918,
      "step": 168
    },
    {
      "epoch": 0.018557153837707258,
      "grad_norm": 3.726558208465576,
      "learning_rate": 6.425787818636131e-06,
      "loss": 8.2394,
      "step": 169
    },
    {
      "epoch": 0.01866695948171736,
      "grad_norm": 3.9399800300598145,
      "learning_rate": 6.026312439675552e-06,
      "loss": 8.239,
      "step": 170
    },
    {
      "epoch": 0.018776765125727464,
      "grad_norm": 3.9510254859924316,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 8.0134,
      "step": 171
    },
    {
      "epoch": 0.018886570769737564,
      "grad_norm": 4.580173969268799,
      "learning_rate": 5.263533508961827e-06,
      "loss": 7.1026,
      "step": 172
    },
    {
      "epoch": 0.018996376413747667,
      "grad_norm": 4.148317337036133,
      "learning_rate": 4.900438493352055e-06,
      "loss": 7.2101,
      "step": 173
    },
    {
      "epoch": 0.01910618205775777,
      "grad_norm": 5.554497241973877,
      "learning_rate": 4.549673247541875e-06,
      "loss": 7.3974,
      "step": 174
    },
    {
      "epoch": 0.01921598770176787,
      "grad_norm": 4.18766975402832,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 7.2134,
      "step": 175
    },
    {
      "epoch": 0.019325793345777973,
      "grad_norm": 6.652616500854492,
      "learning_rate": 3.885512251130763e-06,
      "loss": 7.3577,
      "step": 176
    },
    {
      "epoch": 0.019435598989788076,
      "grad_norm": 4.758925914764404,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 5.0034,
      "step": 177
    },
    {
      "epoch": 0.019545404633798176,
      "grad_norm": 4.417860984802246,
      "learning_rate": 3.271776770026963e-06,
      "loss": 5.8207,
      "step": 178
    },
    {
      "epoch": 0.01965521027780828,
      "grad_norm": 5.554479598999023,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 5.6854,
      "step": 179
    },
    {
      "epoch": 0.019765015921818382,
      "grad_norm": 4.131188869476318,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 3.0541,
      "step": 180
    },
    {
      "epoch": 0.019874821565828482,
      "grad_norm": 5.953482151031494,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 6.097,
      "step": 181
    },
    {
      "epoch": 0.019984627209838585,
      "grad_norm": 9.003937721252441,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 4.9898,
      "step": 182
    },
    {
      "epoch": 0.02009443285384869,
      "grad_norm": 4.7416205406188965,
      "learning_rate": 1.962316193157593e-06,
      "loss": 3.6722,
      "step": 183
    },
    {
      "epoch": 0.02020423849785879,
      "grad_norm": 5.74725341796875,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 2.8708,
      "step": 184
    },
    {
      "epoch": 0.02031404414186889,
      "grad_norm": 2.796290159225464,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.5991,
      "step": 185
    },
    {
      "epoch": 0.020423849785878995,
      "grad_norm": 3.3942573070526123,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.1204,
      "step": 186
    },
    {
      "epoch": 0.020533655429889098,
      "grad_norm": 8.720481872558594,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 6.2964,
      "step": 187
    },
    {
      "epoch": 0.020643461073899198,
      "grad_norm": 4.75813102722168,
      "learning_rate": 9.810017062595322e-07,
      "loss": 4.0443,
      "step": 188
    },
    {
      "epoch": 0.0207532667179093,
      "grad_norm": 3.315704345703125,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.9966,
      "step": 189
    },
    {
      "epoch": 0.020863072361919404,
      "grad_norm": 7.119941711425781,
      "learning_rate": 6.819348298638839e-07,
      "loss": 5.9438,
      "step": 190
    },
    {
      "epoch": 0.020972878005929504,
      "grad_norm": 3.7410435676574707,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.8509,
      "step": 191
    },
    {
      "epoch": 0.021082683649939607,
      "grad_norm": 2.839000940322876,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.4466,
      "step": 192
    },
    {
      "epoch": 0.02119248929394971,
      "grad_norm": 2.3004705905914307,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.1933,
      "step": 193
    },
    {
      "epoch": 0.02130229493795981,
      "grad_norm": 8.033716201782227,
      "learning_rate": 2.458548727494292e-07,
      "loss": 4.6829,
      "step": 194
    },
    {
      "epoch": 0.021412100581969913,
      "grad_norm": 2.918515205383301,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.8743,
      "step": 195
    },
    {
      "epoch": 0.021521906225980016,
      "grad_norm": 6.088643550872803,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.107,
      "step": 196
    },
    {
      "epoch": 0.021631711869990116,
      "grad_norm": 4.089409351348877,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6646,
      "step": 197
    },
    {
      "epoch": 0.02174151751400022,
      "grad_norm": 9.533114433288574,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 5.2135,
      "step": 198
    },
    {
      "epoch": 0.021851323158010322,
      "grad_norm": 4.8926100730896,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.8566,
      "step": 199
    },
    {
      "epoch": 0.021961128802020422,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.021961128802020422,
      "eval_loss": NaN,
      "eval_runtime": 741.4801,
      "eval_samples_per_second": 20.686,
      "eval_steps_per_second": 5.172,
      "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5164471555968205e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}