{
  "best_metric": 0.34131553769111633,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.12266176019625881,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006133088009812941,
      "grad_norm": 0.3022943437099457,
      "learning_rate": 1e-05,
      "loss": 0.3556,
      "step": 1
    },
    {
      "epoch": 0.0006133088009812941,
      "eval_loss": 0.6296672821044922,
      "eval_runtime": 219.2328,
      "eval_samples_per_second": 12.525,
      "eval_steps_per_second": 3.134,
      "step": 1
    },
    {
      "epoch": 0.0012266176019625882,
      "grad_norm": 0.36883726716041565,
      "learning_rate": 2e-05,
      "loss": 0.3984,
      "step": 2
    },
    {
      "epoch": 0.0018399264029438822,
      "grad_norm": 0.3520399332046509,
      "learning_rate": 3e-05,
      "loss": 0.3867,
      "step": 3
    },
    {
      "epoch": 0.0024532352039251764,
      "grad_norm": 0.3818536102771759,
      "learning_rate": 4e-05,
      "loss": 0.4334,
      "step": 4
    },
    {
      "epoch": 0.0030665440049064702,
      "grad_norm": 0.34331899881362915,
      "learning_rate": 5e-05,
      "loss": 0.4142,
      "step": 5
    },
    {
      "epoch": 0.0036798528058877645,
      "grad_norm": 0.3278089761734009,
      "learning_rate": 6e-05,
      "loss": 0.4237,
      "step": 6
    },
    {
      "epoch": 0.004293161606869059,
      "grad_norm": 0.3553948402404785,
      "learning_rate": 7e-05,
      "loss": 0.387,
      "step": 7
    },
    {
      "epoch": 0.004906470407850353,
      "grad_norm": 0.37796276807785034,
      "learning_rate": 8e-05,
      "loss": 0.3794,
      "step": 8
    },
    {
      "epoch": 0.005519779208831647,
      "grad_norm": 0.41262099146842957,
      "learning_rate": 9e-05,
      "loss": 0.3688,
      "step": 9
    },
    {
      "epoch": 0.0061330880098129405,
      "grad_norm": 0.4160615801811218,
      "learning_rate": 0.0001,
      "loss": 0.3627,
      "step": 10
    },
    {
      "epoch": 0.006746396810794235,
      "grad_norm": 0.4473973512649536,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.3751,
      "step": 11
    },
    {
      "epoch": 0.007359705611775529,
      "grad_norm": 0.3327968418598175,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.3653,
      "step": 12
    },
    {
      "epoch": 0.007973014412756822,
      "grad_norm": 0.3294541835784912,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.4077,
      "step": 13
    },
    {
      "epoch": 0.008586323213738117,
      "grad_norm": 0.28400251269340515,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4105,
      "step": 14
    },
    {
      "epoch": 0.00919963201471941,
      "grad_norm": 0.2906724214553833,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4052,
      "step": 15
    },
    {
      "epoch": 0.009812940815700706,
      "grad_norm": 0.2757435739040375,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.375,
      "step": 16
    },
    {
      "epoch": 0.010426249616682,
      "grad_norm": 0.2972464859485626,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.411,
      "step": 17
    },
    {
      "epoch": 0.011039558417663294,
      "grad_norm": 0.32555270195007324,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.3648,
      "step": 18
    },
    {
      "epoch": 0.011652867218644588,
      "grad_norm": 0.33771705627441406,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.4569,
      "step": 19
    },
    {
      "epoch": 0.012266176019625881,
      "grad_norm": 0.3100060224533081,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.4075,
      "step": 20
    },
    {
      "epoch": 0.012879484820607176,
      "grad_norm": 0.3115110993385315,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.414,
      "step": 21
    },
    {
      "epoch": 0.01349279362158847,
      "grad_norm": 0.3101189434528351,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.3749,
      "step": 22
    },
    {
      "epoch": 0.014106102422569764,
      "grad_norm": 0.30109214782714844,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.4002,
      "step": 23
    },
    {
      "epoch": 0.014719411223551058,
      "grad_norm": 0.31071263551712036,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.3963,
      "step": 24
    },
    {
      "epoch": 0.015332720024532351,
      "grad_norm": 0.31883418560028076,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4353,
      "step": 25
    },
    {
      "epoch": 0.015946028825513645,
      "grad_norm": 0.32263994216918945,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.38,
      "step": 26
    },
    {
      "epoch": 0.01655933762649494,
      "grad_norm": 0.3300021290779114,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4058,
      "step": 27
    },
    {
      "epoch": 0.017172646427476235,
      "grad_norm": 0.3408714532852173,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4137,
      "step": 28
    },
    {
      "epoch": 0.01778595522845753,
      "grad_norm": 0.3325856924057007,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3937,
      "step": 29
    },
    {
      "epoch": 0.01839926402943882,
      "grad_norm": 0.3017386496067047,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3862,
      "step": 30
    },
    {
      "epoch": 0.019012572830420117,
      "grad_norm": 0.31614962220191956,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.3928,
      "step": 31
    },
    {
      "epoch": 0.01962588163140141,
      "grad_norm": 0.34579160809516907,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.3955,
      "step": 32
    },
    {
      "epoch": 0.020239190432382703,
      "grad_norm": 0.334962397813797,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.4097,
      "step": 33
    },
    {
      "epoch": 0.020852499233364,
      "grad_norm": 0.3280732035636902,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.4127,
      "step": 34
    },
    {
      "epoch": 0.021465808034345293,
      "grad_norm": 0.34333860874176025,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3811,
      "step": 35
    },
    {
      "epoch": 0.02207911683532659,
      "grad_norm": 0.3256630003452301,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3848,
      "step": 36
    },
    {
      "epoch": 0.02269242563630788,
      "grad_norm": 0.332073837518692,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4119,
      "step": 37
    },
    {
      "epoch": 0.023305734437289175,
      "grad_norm": 0.3388371765613556,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.4294,
      "step": 38
    },
    {
      "epoch": 0.02391904323827047,
      "grad_norm": 0.3451681435108185,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.4129,
      "step": 39
    },
    {
      "epoch": 0.024532352039251762,
      "grad_norm": 0.3570638597011566,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.4176,
      "step": 40
    },
    {
      "epoch": 0.025145660840233057,
      "grad_norm": 0.34661781787872314,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.4178,
      "step": 41
    },
    {
      "epoch": 0.025758969641214352,
      "grad_norm": 0.3466348648071289,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.4125,
      "step": 42
    },
    {
      "epoch": 0.026372278442195647,
      "grad_norm": 0.349714070558548,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.422,
      "step": 43
    },
    {
      "epoch": 0.02698558724317694,
      "grad_norm": 0.395971417427063,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4628,
      "step": 44
    },
    {
      "epoch": 0.027598896044158234,
      "grad_norm": 0.3631829619407654,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.4211,
      "step": 45
    },
    {
      "epoch": 0.02821220484513953,
      "grad_norm": 0.37482091784477234,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.411,
      "step": 46
    },
    {
      "epoch": 0.02882551364612082,
      "grad_norm": 0.41901448369026184,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.4317,
      "step": 47
    },
    {
      "epoch": 0.029438822447102116,
      "grad_norm": 0.4255604147911072,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4519,
      "step": 48
    },
    {
      "epoch": 0.03005213124808341,
      "grad_norm": 0.4364151060581207,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.4379,
      "step": 49
    },
    {
      "epoch": 0.030665440049064702,
      "grad_norm": 0.4957652986049652,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.3896,
      "step": 50
    },
    {
      "epoch": 0.030665440049064702,
      "eval_loss": 0.3710000514984131,
      "eval_runtime": 220.7322,
      "eval_samples_per_second": 12.44,
      "eval_steps_per_second": 3.112,
      "step": 50
    },
    {
      "epoch": 0.031278748850046,
      "grad_norm": 0.15296220779418945,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.1773,
      "step": 51
    },
    {
      "epoch": 0.03189205765102729,
      "grad_norm": 0.19297577440738678,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.2468,
      "step": 52
    },
    {
      "epoch": 0.032505366452008584,
      "grad_norm": 0.21050745248794556,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.231,
      "step": 53
    },
    {
      "epoch": 0.03311867525298988,
      "grad_norm": 0.22146226465702057,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.2665,
      "step": 54
    },
    {
      "epoch": 0.033731984053971174,
      "grad_norm": 0.2096215784549713,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.2947,
      "step": 55
    },
    {
      "epoch": 0.03434529285495247,
      "grad_norm": 0.21803472936153412,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.253,
      "step": 56
    },
    {
      "epoch": 0.034958601655933765,
      "grad_norm": 0.21237118542194366,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.2902,
      "step": 57
    },
    {
      "epoch": 0.03557191045691506,
      "grad_norm": 0.23298391699790955,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3026,
      "step": 58
    },
    {
      "epoch": 0.03618521925789635,
      "grad_norm": 0.2220010608434677,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.3101,
      "step": 59
    },
    {
      "epoch": 0.03679852805887764,
      "grad_norm": 0.23363174498081207,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3601,
      "step": 60
    },
    {
      "epoch": 0.03741183685985894,
      "grad_norm": 0.23582279682159424,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3456,
      "step": 61
    },
    {
      "epoch": 0.03802514566084023,
      "grad_norm": 0.2466915249824524,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.3397,
      "step": 62
    },
    {
      "epoch": 0.03863845446182153,
      "grad_norm": 0.21774590015411377,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.3337,
      "step": 63
    },
    {
      "epoch": 0.03925176326280282,
      "grad_norm": 0.20931164920330048,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.2819,
      "step": 64
    },
    {
      "epoch": 0.03986507206378412,
      "grad_norm": 0.2225279062986374,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.3271,
      "step": 65
    },
    {
      "epoch": 0.040478380864765406,
      "grad_norm": 0.25011786818504333,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.3738,
      "step": 66
    },
    {
      "epoch": 0.0410916896657467,
      "grad_norm": 0.24709101021289825,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3543,
      "step": 67
    },
    {
      "epoch": 0.041704998466728,
      "grad_norm": 0.23869197070598602,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.3287,
      "step": 68
    },
    {
      "epoch": 0.04231830726770929,
      "grad_norm": 0.23837392032146454,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3416,
      "step": 69
    },
    {
      "epoch": 0.04293161606869059,
      "grad_norm": 0.2550102174282074,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.3247,
      "step": 70
    },
    {
      "epoch": 0.04354492486967188,
      "grad_norm": 0.28500837087631226,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.3901,
      "step": 71
    },
    {
      "epoch": 0.04415823367065318,
      "grad_norm": 0.2559871971607208,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.3583,
      "step": 72
    },
    {
      "epoch": 0.044771542471634465,
      "grad_norm": 0.25514087080955505,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.3656,
      "step": 73
    },
    {
      "epoch": 0.04538485127261576,
      "grad_norm": 0.2661421597003937,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.3841,
      "step": 74
    },
    {
      "epoch": 0.045998160073597055,
      "grad_norm": 0.28271472454071045,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.3848,
      "step": 75
    },
    {
      "epoch": 0.04661146887457835,
      "grad_norm": 0.2915990948677063,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.3736,
      "step": 76
    },
    {
      "epoch": 0.047224777675559645,
      "grad_norm": 0.27764442563056946,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.3542,
      "step": 77
    },
    {
      "epoch": 0.04783808647654094,
      "grad_norm": 0.30097103118896484,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.388,
      "step": 78
    },
    {
      "epoch": 0.048451395277522236,
      "grad_norm": 0.287272185087204,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.355,
      "step": 79
    },
    {
      "epoch": 0.049064704078503524,
      "grad_norm": 0.3174525797367096,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4057,
      "step": 80
    },
    {
      "epoch": 0.04967801287948482,
      "grad_norm": 0.32427293062210083,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3693,
      "step": 81
    },
    {
      "epoch": 0.050291321680466114,
      "grad_norm": 0.287952184677124,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.364,
      "step": 82
    },
    {
      "epoch": 0.05090463048144741,
      "grad_norm": 0.3045385479927063,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3585,
      "step": 83
    },
    {
      "epoch": 0.051517939282428704,
      "grad_norm": 0.2992158830165863,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3698,
      "step": 84
    },
    {
      "epoch": 0.05213124808341,
      "grad_norm": 0.3164645731449127,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3962,
      "step": 85
    },
    {
      "epoch": 0.052744556884391294,
      "grad_norm": 0.34315919876098633,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4161,
      "step": 86
    },
    {
      "epoch": 0.05335786568537258,
      "grad_norm": 0.3459291160106659,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3962,
      "step": 87
    },
    {
      "epoch": 0.05397117448635388,
      "grad_norm": 0.31577181816101074,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.395,
      "step": 88
    },
    {
      "epoch": 0.05458448328733517,
      "grad_norm": 0.3199935853481293,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.423,
      "step": 89
    },
    {
      "epoch": 0.05519779208831647,
      "grad_norm": 0.32555022835731506,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.411,
      "step": 90
    },
    {
      "epoch": 0.05581110088929776,
      "grad_norm": 0.3312777876853943,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.3889,
      "step": 91
    },
    {
      "epoch": 0.05642440969027906,
      "grad_norm": 0.3316109776496887,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.4013,
      "step": 92
    },
    {
      "epoch": 0.05703771849126035,
      "grad_norm": 0.3671054244041443,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4363,
      "step": 93
    },
    {
      "epoch": 0.05765102729224164,
      "grad_norm": 0.3669225573539734,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.4263,
      "step": 94
    },
    {
      "epoch": 0.058264336093222936,
      "grad_norm": 0.342974990606308,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4056,
      "step": 95
    },
    {
      "epoch": 0.05887764489420423,
      "grad_norm": 0.373455286026001,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.4315,
      "step": 96
    },
    {
      "epoch": 0.059490953695185526,
      "grad_norm": 0.3646349608898163,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.415,
      "step": 97
    },
    {
      "epoch": 0.06010426249616682,
      "grad_norm": 0.40072110295295715,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.4544,
      "step": 98
    },
    {
      "epoch": 0.06071757129714812,
      "grad_norm": 0.4139806032180786,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.4212,
      "step": 99
    },
    {
      "epoch": 0.061330880098129405,
      "grad_norm": 0.4375724494457245,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.3542,
      "step": 100
    },
    {
      "epoch": 0.061330880098129405,
      "eval_loss": 0.35311567783355713,
      "eval_runtime": 220.5609,
      "eval_samples_per_second": 12.45,
      "eval_steps_per_second": 3.115,
      "step": 100
    },
    {
      "epoch": 0.0619441888991107,
      "grad_norm": 0.14297135174274445,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.186,
      "step": 101
    },
    {
      "epoch": 0.062557497700092,
      "grad_norm": 0.16984869539737701,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.2433,
      "step": 102
    },
    {
      "epoch": 0.06317080650107329,
      "grad_norm": 0.18036068975925446,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.2517,
      "step": 103
    },
    {
      "epoch": 0.06378411530205458,
      "grad_norm": 0.203562930226326,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.3014,
      "step": 104
    },
    {
      "epoch": 0.06439742410303588,
      "grad_norm": 0.21880516409873962,
      "learning_rate": 5e-05,
      "loss": 0.3114,
      "step": 105
    },
    {
      "epoch": 0.06501073290401717,
      "grad_norm": 0.19703908264636993,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.2727,
      "step": 106
    },
    {
      "epoch": 0.06562404170499847,
      "grad_norm": 0.20121800899505615,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.3128,
      "step": 107
    },
    {
      "epoch": 0.06623735050597976,
      "grad_norm": 0.22021602094173431,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.2977,
      "step": 108
    },
    {
      "epoch": 0.06685065930696106,
      "grad_norm": 0.21838457882404327,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3013,
      "step": 109
    },
    {
      "epoch": 0.06746396810794235,
      "grad_norm": 0.2020447850227356,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3006,
      "step": 110
    },
    {
      "epoch": 0.06807727690892364,
      "grad_norm": 0.22435148060321808,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.3614,
      "step": 111
    },
    {
      "epoch": 0.06869058570990494,
      "grad_norm": 0.21225163340568542,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.3358,
      "step": 112
    },
    {
      "epoch": 0.06930389451088623,
      "grad_norm": 0.22227871417999268,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.3429,
      "step": 113
    },
    {
      "epoch": 0.06991720331186753,
      "grad_norm": 0.2170470952987671,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.3194,
      "step": 114
    },
    {
      "epoch": 0.07053051211284882,
      "grad_norm": 0.24869808554649353,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.3856,
      "step": 115
    },
    {
      "epoch": 0.07114382091383012,
      "grad_norm": 0.2273949682712555,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.3327,
      "step": 116
    },
    {
      "epoch": 0.07175712971481141,
      "grad_norm": 0.24974454939365387,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.3648,
      "step": 117
    },
    {
      "epoch": 0.0723704385157927,
      "grad_norm": 0.2473083883523941,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.361,
      "step": 118
    },
    {
      "epoch": 0.072983747316774,
      "grad_norm": 0.2563985586166382,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.3799,
      "step": 119
    },
    {
      "epoch": 0.07359705611775529,
      "grad_norm": 0.2372652292251587,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.3455,
      "step": 120
    },
    {
      "epoch": 0.07421036491873659,
      "grad_norm": 0.25966471433639526,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.3722,
      "step": 121
    },
    {
      "epoch": 0.07482367371971788,
      "grad_norm": 0.27156397700309753,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.3817,
      "step": 122
    },
    {
      "epoch": 0.07543698252069918,
      "grad_norm": 0.25948086380958557,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3441,
      "step": 123
    },
    {
      "epoch": 0.07605029132168047,
      "grad_norm": 0.25913044810295105,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3715,
      "step": 124
    },
    {
      "epoch": 0.07666360012266175,
      "grad_norm": 0.2692747414112091,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.36,
      "step": 125
    },
    {
      "epoch": 0.07727690892364306,
      "grad_norm": 0.26968130469322205,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3845,
      "step": 126
    },
    {
      "epoch": 0.07789021772462434,
      "grad_norm": 0.27973347902297974,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.3591,
      "step": 127
    },
    {
      "epoch": 0.07850352652560565,
      "grad_norm": 0.2643369138240814,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.3567,
      "step": 128
    },
    {
      "epoch": 0.07911683532658693,
      "grad_norm": 0.27118900418281555,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3541,
      "step": 129
    },
    {
      "epoch": 0.07973014412756824,
      "grad_norm": 0.2777666449546814,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3584,
      "step": 130
    },
    {
      "epoch": 0.08034345292854952,
      "grad_norm": 0.28747764229774475,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3621,
      "step": 131
    },
    {
      "epoch": 0.08095676172953081,
      "grad_norm": 0.2967444956302643,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3819,
      "step": 132
    },
    {
      "epoch": 0.08157007053051211,
      "grad_norm": 0.2715611159801483,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.3645,
      "step": 133
    },
    {
      "epoch": 0.0821833793314934,
      "grad_norm": 0.2922961711883545,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.4103,
      "step": 134
    },
    {
      "epoch": 0.0827966881324747,
      "grad_norm": 0.2891833484172821,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.3837,
      "step": 135
    },
    {
      "epoch": 0.083409996933456,
      "grad_norm": 0.3045870363712311,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3726,
      "step": 136
    },
    {
      "epoch": 0.0840233057344373,
      "grad_norm": 0.3037290871143341,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3861,
      "step": 137
    },
    {
      "epoch": 0.08463661453541858,
      "grad_norm": 0.3093765079975128,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.3951,
      "step": 138
    },
    {
      "epoch": 0.08524992333639987,
      "grad_norm": 0.32258591055870056,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.403,
      "step": 139
    },
    {
      "epoch": 0.08586323213738117,
      "grad_norm": 0.3109833300113678,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3595,
      "step": 140
    },
    {
      "epoch": 0.08647654093836246,
      "grad_norm": 0.31597959995269775,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.4016,
      "step": 141
    },
    {
      "epoch": 0.08708984973934376,
      "grad_norm": 0.3226120173931122,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3938,
      "step": 142
    },
    {
      "epoch": 0.08770315854032505,
      "grad_norm": 0.33344128727912903,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3938,
      "step": 143
    },
    {
      "epoch": 0.08831646734130635,
      "grad_norm": 0.3264431059360504,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.3881,
      "step": 144
    },
    {
      "epoch": 0.08892977614228764,
      "grad_norm": 0.35919469594955444,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.3961,
      "step": 145
    },
    {
      "epoch": 0.08954308494326893,
      "grad_norm": 0.3426930010318756,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.3803,
      "step": 146
    },
    {
      "epoch": 0.09015639374425023,
      "grad_norm": 0.35507500171661377,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.4,
      "step": 147
    },
    {
      "epoch": 0.09076970254523152,
      "grad_norm": 0.39351052045822144,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.4207,
      "step": 148
    },
    {
      "epoch": 0.09138301134621282,
      "grad_norm": 0.38654205203056335,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.4047,
      "step": 149
    },
    {
      "epoch": 0.09199632014719411,
      "grad_norm": 0.4969562292098999,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.4101,
      "step": 150
    },
    {
      "epoch": 0.09199632014719411,
      "eval_loss": 0.34416279196739197,
      "eval_runtime": 219.9752,
      "eval_samples_per_second": 12.483,
      "eval_steps_per_second": 3.123,
      "step": 150
    },
    {
      "epoch": 0.09260962894817541,
      "grad_norm": 0.13795159757137299,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.2041,
      "step": 151
    },
    {
      "epoch": 0.0932229377491567,
      "grad_norm": 0.18278461694717407,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.2348,
      "step": 152
    },
    {
      "epoch": 0.09383624655013799,
      "grad_norm": 0.18963085114955902,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.2742,
      "step": 153
    },
    {
      "epoch": 0.09444955535111929,
      "grad_norm": 0.1875893920660019,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.2851,
      "step": 154
    },
    {
      "epoch": 0.09506286415210058,
      "grad_norm": 0.1966901272535324,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.2993,
      "step": 155
    },
    {
      "epoch": 0.09567617295308188,
      "grad_norm": 0.19441860914230347,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.2898,
      "step": 156
    },
    {
      "epoch": 0.09628948175406317,
      "grad_norm": 0.20160691440105438,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.2713,
      "step": 157
    },
    {
      "epoch": 0.09690279055504447,
      "grad_norm": 0.20832929015159607,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.322,
      "step": 158
    },
    {
      "epoch": 0.09751609935602576,
      "grad_norm": 0.2035316526889801,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.2814,
      "step": 159
    },
    {
      "epoch": 0.09812940815700705,
      "grad_norm": 0.22239522635936737,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.3167,
      "step": 160
    },
    {
      "epoch": 0.09874271695798835,
      "grad_norm": 0.22371673583984375,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.33,
      "step": 161
    },
    {
      "epoch": 0.09935602575896964,
      "grad_norm": 0.21961507201194763,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3128,
      "step": 162
    },
    {
      "epoch": 0.09996933455995094,
      "grad_norm": 0.226009801030159,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.3639,
      "step": 163
    },
    {
      "epoch": 0.10058264336093223,
      "grad_norm": 0.22174425423145294,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.3036,
      "step": 164
    },
    {
      "epoch": 0.10119595216191353,
      "grad_norm": 0.24946357309818268,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.3936,
      "step": 165
    },
    {
      "epoch": 0.10180926096289482,
      "grad_norm": 0.235744908452034,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.3267,
      "step": 166
    },
    {
      "epoch": 0.1024225697638761,
      "grad_norm": 0.22804810106754303,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.3102,
      "step": 167
    },
    {
      "epoch": 0.10303587856485741,
      "grad_norm": 0.23976342380046844,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.3522,
      "step": 168
    },
    {
      "epoch": 0.1036491873658387,
      "grad_norm": 0.23267774283885956,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.3519,
      "step": 169
    },
    {
      "epoch": 0.10426249616682,
      "grad_norm": 0.24617773294448853,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.3471,
      "step": 170
    },
    {
      "epoch": 0.10487580496780129,
      "grad_norm": 0.2518331706523895,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.3452,
      "step": 171
    },
    {
      "epoch": 0.10548911376878259,
      "grad_norm": 0.2807620167732239,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.3787,
      "step": 172
    },
    {
      "epoch": 0.10610242256976388,
      "grad_norm": 0.2519250810146332,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.3314,
      "step": 173
    },
    {
      "epoch": 0.10671573137074516,
      "grad_norm": 0.26201778650283813,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.3599,
      "step": 174
    },
    {
      "epoch": 0.10732904017172647,
      "grad_norm": 0.26512831449508667,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.3672,
      "step": 175
    },
    {
      "epoch": 0.10794234897270776,
      "grad_norm": 0.27233150601387024,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.326,
      "step": 176
    },
    {
      "epoch": 0.10855565777368906,
      "grad_norm": 0.2850625514984131,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.3952,
      "step": 177
    },
    {
      "epoch": 0.10916896657467035,
      "grad_norm": 0.2683158814907074,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.3535,
      "step": 178
    },
    {
      "epoch": 0.10978227537565165,
      "grad_norm": 0.2730138897895813,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.3767,
      "step": 179
    },
    {
      "epoch": 0.11039558417663294,
      "grad_norm": 0.2909507751464844,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.366,
      "step": 180
    },
    {
      "epoch": 0.11100889297761422,
      "grad_norm": 0.27138763666152954,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3284,
      "step": 181
    },
    {
      "epoch": 0.11162220177859553,
      "grad_norm": 0.2935401201248169,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.3845,
      "step": 182
    },
    {
      "epoch": 0.11223551057957681,
      "grad_norm": 0.2869737148284912,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.3639,
      "step": 183
    },
    {
      "epoch": 0.11284881938055812,
      "grad_norm": 0.30029740929603577,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.3661,
      "step": 184
    },
    {
      "epoch": 0.1134621281815394,
      "grad_norm": 0.30771201848983765,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.3776,
      "step": 185
    },
    {
      "epoch": 0.1140754369825207,
      "grad_norm": 0.30514422059059143,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.3561,
      "step": 186
    },
    {
      "epoch": 0.114688745783502,
      "grad_norm": 0.2983490824699402,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.3342,
      "step": 187
    },
    {
      "epoch": 0.11530205458448328,
      "grad_norm": 0.30422964692115784,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.3592,
      "step": 188
    },
    {
      "epoch": 0.11591536338546458,
      "grad_norm": 0.3023673892021179,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.368,
      "step": 189
    },
    {
      "epoch": 0.11652867218644587,
      "grad_norm": 0.3084518015384674,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3958,
      "step": 190
    },
    {
      "epoch": 0.11714198098742717,
      "grad_norm": 0.31332510709762573,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.3661,
      "step": 191
    },
    {
      "epoch": 0.11775528978840846,
      "grad_norm": 0.31766006350517273,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.4168,
      "step": 192
    },
    {
      "epoch": 0.11836859858938976,
      "grad_norm": 0.3280036449432373,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.3728,
      "step": 193
    },
    {
      "epoch": 0.11898190739037105,
      "grad_norm": 0.3443011939525604,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.3819,
      "step": 194
    },
    {
      "epoch": 0.11959521619135234,
      "grad_norm": 0.3751179575920105,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.4507,
      "step": 195
    },
    {
      "epoch": 0.12020852499233364,
      "grad_norm": 0.37313684821128845,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.4074,
      "step": 196
    },
    {
      "epoch": 0.12082183379331493,
      "grad_norm": 0.3668825328350067,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.3748,
      "step": 197
    },
    {
      "epoch": 0.12143514259429623,
      "grad_norm": 0.405875027179718,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.4188,
      "step": 198
    },
    {
      "epoch": 0.12204845139527752,
      "grad_norm": 0.4382794499397278,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.3794,
      "step": 199
    },
    {
      "epoch": 0.12266176019625881,
      "grad_norm": 0.43143340945243835,
      "learning_rate": 0.0,
      "loss": 0.3128,
      "step": 200
    },
    {
      "epoch": 0.12266176019625881,
      "eval_loss": 0.34131553769111633,
      "eval_runtime": 220.6075,
      "eval_samples_per_second": 12.447,
      "eval_steps_per_second": 3.114,
      "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": 3.160335947472568e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}