{
  "best_metric": 0.45032814145088196,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.029624143677096836,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014812071838548417,
      "grad_norm": 1.9046655893325806,
      "learning_rate": 1e-05,
      "loss": 0.3333,
      "step": 1
    },
    {
      "epoch": 0.00014812071838548417,
      "eval_loss": 1.5247727632522583,
      "eval_runtime": 199.0743,
      "eval_samples_per_second": 57.119,
      "eval_steps_per_second": 14.281,
      "step": 1
    },
    {
      "epoch": 0.00029624143677096834,
      "grad_norm": 2.0361180305480957,
      "learning_rate": 2e-05,
      "loss": 0.3183,
      "step": 2
    },
    {
      "epoch": 0.00044436215515645253,
      "grad_norm": 1.2657564878463745,
      "learning_rate": 3e-05,
      "loss": 0.425,
      "step": 3
    },
    {
      "epoch": 0.0005924828735419367,
      "grad_norm": 1.1639090776443481,
      "learning_rate": 4e-05,
      "loss": 0.4265,
      "step": 4
    },
    {
      "epoch": 0.0007406035919274209,
      "grad_norm": 1.73726487159729,
      "learning_rate": 5e-05,
      "loss": 0.7745,
      "step": 5
    },
    {
      "epoch": 0.0008887243103129051,
      "grad_norm": 2.931978225708008,
      "learning_rate": 6e-05,
      "loss": 0.7544,
      "step": 6
    },
    {
      "epoch": 0.0010368450286983891,
      "grad_norm": 1.1456927061080933,
      "learning_rate": 7e-05,
      "loss": 0.5126,
      "step": 7
    },
    {
      "epoch": 0.0011849657470838733,
      "grad_norm": 1.3564872741699219,
      "learning_rate": 8e-05,
      "loss": 0.6145,
      "step": 8
    },
    {
      "epoch": 0.0013330864654693575,
      "grad_norm": 1.2266627550125122,
      "learning_rate": 9e-05,
      "loss": 0.4569,
      "step": 9
    },
    {
      "epoch": 0.0014812071838548417,
      "grad_norm": 1.0785515308380127,
      "learning_rate": 0.0001,
      "loss": 0.5328,
      "step": 10
    },
    {
      "epoch": 0.001629327902240326,
      "grad_norm": 1.2059049606323242,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.5362,
      "step": 11
    },
    {
      "epoch": 0.0017774486206258101,
      "grad_norm": 1.4599133729934692,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6371,
      "step": 12
    },
    {
      "epoch": 0.001925569339011294,
      "grad_norm": 1.16817307472229,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6196,
      "step": 13
    },
    {
      "epoch": 0.0020736900573967783,
      "grad_norm": 1.2377264499664307,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.6265,
      "step": 14
    },
    {
      "epoch": 0.0022218107757822625,
      "grad_norm": 1.1837877035140991,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5807,
      "step": 15
    },
    {
      "epoch": 0.0023699314941677467,
      "grad_norm": 1.4035372734069824,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.72,
      "step": 16
    },
    {
      "epoch": 0.002518052212553231,
      "grad_norm": 1.425987958908081,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.7055,
      "step": 17
    },
    {
      "epoch": 0.002666172930938715,
      "grad_norm": 1.4049324989318848,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.6729,
      "step": 18
    },
    {
      "epoch": 0.0028142936493241993,
      "grad_norm": 1.4342765808105469,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7349,
      "step": 19
    },
    {
      "epoch": 0.0029624143677096835,
      "grad_norm": 1.610926628112793,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6987,
      "step": 20
    },
    {
      "epoch": 0.0031105350860951677,
      "grad_norm": 1.4963016510009766,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6844,
      "step": 21
    },
    {
      "epoch": 0.003258655804480652,
      "grad_norm": 1.4254350662231445,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7,
      "step": 22
    },
    {
      "epoch": 0.003406776522866136,
      "grad_norm": 1.3612539768218994,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.727,
      "step": 23
    },
    {
      "epoch": 0.0035548972412516202,
      "grad_norm": 1.3839017152786255,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.6871,
      "step": 24
    },
    {
      "epoch": 0.0037030179596371044,
      "grad_norm": 1.4511075019836426,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6212,
      "step": 25
    },
    {
      "epoch": 0.003851138678022588,
      "grad_norm": 1.4771878719329834,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7191,
      "step": 26
    },
    {
      "epoch": 0.003999259396408073,
      "grad_norm": 1.4691141843795776,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7135,
      "step": 27
    },
    {
      "epoch": 0.004147380114793557,
      "grad_norm": 1.6518168449401855,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6422,
      "step": 28
    },
    {
      "epoch": 0.004295500833179041,
      "grad_norm": 1.4498182535171509,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6173,
      "step": 29
    },
    {
      "epoch": 0.004443621551564525,
      "grad_norm": 1.587878942489624,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.5715,
      "step": 30
    },
    {
      "epoch": 0.00459174226995001,
      "grad_norm": 1.4145408868789673,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.5115,
      "step": 31
    },
    {
      "epoch": 0.004739862988335493,
      "grad_norm": 1.7366639375686646,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6457,
      "step": 32
    },
    {
      "epoch": 0.004887983706720978,
      "grad_norm": 1.4102771282196045,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.5717,
      "step": 33
    },
    {
      "epoch": 0.005036104425106462,
      "grad_norm": 1.293555736541748,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5448,
      "step": 34
    },
    {
      "epoch": 0.0051842251434919455,
      "grad_norm": 1.6558605432510376,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5792,
      "step": 35
    },
    {
      "epoch": 0.00533234586187743,
      "grad_norm": 1.4412734508514404,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.6439,
      "step": 36
    },
    {
      "epoch": 0.005480466580262914,
      "grad_norm": 1.3806065320968628,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.5742,
      "step": 37
    },
    {
      "epoch": 0.0056285872986483985,
      "grad_norm": 1.491209626197815,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.6883,
      "step": 38
    },
    {
      "epoch": 0.005776708017033882,
      "grad_norm": 1.7017310857772827,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.5492,
      "step": 39
    },
    {
      "epoch": 0.005924828735419367,
      "grad_norm": 1.8791207075119019,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6265,
      "step": 40
    },
    {
      "epoch": 0.006072949453804851,
      "grad_norm": 1.8401401042938232,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6705,
      "step": 41
    },
    {
      "epoch": 0.006221070172190335,
      "grad_norm": 1.9637707471847534,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.6352,
      "step": 42
    },
    {
      "epoch": 0.006369190890575819,
      "grad_norm": 2.041590690612793,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6033,
      "step": 43
    },
    {
      "epoch": 0.006517311608961304,
      "grad_norm": 2.0323519706726074,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6802,
      "step": 44
    },
    {
      "epoch": 0.0066654323273467875,
      "grad_norm": 2.431664228439331,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.769,
      "step": 45
    },
    {
      "epoch": 0.006813553045732272,
      "grad_norm": 1.9587597846984863,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6888,
      "step": 46
    },
    {
      "epoch": 0.006961673764117756,
      "grad_norm": 2.1718862056732178,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6387,
      "step": 47
    },
    {
      "epoch": 0.0071097944825032405,
      "grad_norm": 2.2434709072113037,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6872,
      "step": 48
    },
    {
      "epoch": 0.007257915200888724,
      "grad_norm": 2.0263822078704834,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6743,
      "step": 49
    },
    {
      "epoch": 0.007406035919274209,
      "grad_norm": 2.3752622604370117,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.5942,
      "step": 50
    },
    {
      "epoch": 0.007406035919274209,
      "eval_loss": 0.6091567277908325,
      "eval_runtime": 198.9605,
      "eval_samples_per_second": 57.152,
      "eval_steps_per_second": 14.289,
      "step": 50
    },
    {
      "epoch": 0.007554156637659693,
      "grad_norm": 1.5589680671691895,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.1799,
      "step": 51
    },
    {
      "epoch": 0.007702277356045176,
      "grad_norm": 0.3515014052391052,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0933,
      "step": 52
    },
    {
      "epoch": 0.007850398074430661,
      "grad_norm": 0.45875218510627747,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.1784,
      "step": 53
    },
    {
      "epoch": 0.007998518792816146,
      "grad_norm": 0.6269052624702454,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.2778,
      "step": 54
    },
    {
      "epoch": 0.008146639511201629,
      "grad_norm": 1.1689852476119995,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4904,
      "step": 55
    },
    {
      "epoch": 0.008294760229587113,
      "grad_norm": 0.8358094692230225,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.3861,
      "step": 56
    },
    {
      "epoch": 0.008442880947972598,
      "grad_norm": 0.7253592014312744,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.3949,
      "step": 57
    },
    {
      "epoch": 0.008591001666358082,
      "grad_norm": 0.5812123417854309,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3646,
      "step": 58
    },
    {
      "epoch": 0.008739122384743565,
      "grad_norm": 0.4843596816062927,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.2807,
      "step": 59
    },
    {
      "epoch": 0.00888724310312905,
      "grad_norm": 0.740838348865509,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.33,
      "step": 60
    },
    {
      "epoch": 0.009035363821514535,
      "grad_norm": 0.6797621846199036,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3849,
      "step": 61
    },
    {
      "epoch": 0.00918348453990002,
      "grad_norm": 0.8141345977783203,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5828,
      "step": 62
    },
    {
      "epoch": 0.009331605258285502,
      "grad_norm": 0.8279635310173035,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.4488,
      "step": 63
    },
    {
      "epoch": 0.009479725976670987,
      "grad_norm": 0.7811763882637024,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.5753,
      "step": 64
    },
    {
      "epoch": 0.009627846695056471,
      "grad_norm": 0.8266785144805908,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5867,
      "step": 65
    },
    {
      "epoch": 0.009775967413441956,
      "grad_norm": 0.9202486276626587,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6306,
      "step": 66
    },
    {
      "epoch": 0.009924088131827439,
      "grad_norm": 0.8798254728317261,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5484,
      "step": 67
    },
    {
      "epoch": 0.010072208850212924,
      "grad_norm": 0.9810667634010315,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.629,
      "step": 68
    },
    {
      "epoch": 0.010220329568598408,
      "grad_norm": 0.9303103685379028,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.6537,
      "step": 69
    },
    {
      "epoch": 0.010368450286983891,
      "grad_norm": 1.0939483642578125,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6746,
      "step": 70
    },
    {
      "epoch": 0.010516571005369376,
      "grad_norm": 1.0398846864700317,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6258,
      "step": 71
    },
    {
      "epoch": 0.01066469172375486,
      "grad_norm": 1.010213851928711,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5371,
      "step": 72
    },
    {
      "epoch": 0.010812812442140345,
      "grad_norm": 0.9675101041793823,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5268,
      "step": 73
    },
    {
      "epoch": 0.010960933160525828,
      "grad_norm": 1.2306679487228394,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7031,
      "step": 74
    },
    {
      "epoch": 0.011109053878911312,
      "grad_norm": 1.0080821514129639,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.5835,
      "step": 75
    },
    {
      "epoch": 0.011257174597296797,
      "grad_norm": 0.9551141262054443,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5755,
      "step": 76
    },
    {
      "epoch": 0.011405295315682282,
      "grad_norm": 0.9900866746902466,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.5303,
      "step": 77
    },
    {
      "epoch": 0.011553416034067765,
      "grad_norm": 1.0662058591842651,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.5197,
      "step": 78
    },
    {
      "epoch": 0.01170153675245325,
      "grad_norm": 0.9889392852783203,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.499,
      "step": 79
    },
    {
      "epoch": 0.011849657470838734,
      "grad_norm": 1.0202381610870361,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.5596,
      "step": 80
    },
    {
      "epoch": 0.011997778189224219,
      "grad_norm": 1.0612425804138184,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.5745,
      "step": 81
    },
    {
      "epoch": 0.012145898907609701,
      "grad_norm": 0.996573805809021,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.4494,
      "step": 82
    },
    {
      "epoch": 0.012294019625995186,
      "grad_norm": 1.028623342514038,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.5359,
      "step": 83
    },
    {
      "epoch": 0.01244214034438067,
      "grad_norm": 0.9804308414459229,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.4899,
      "step": 84
    },
    {
      "epoch": 0.012590261062766155,
      "grad_norm": 1.0140541791915894,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.4538,
      "step": 85
    },
    {
      "epoch": 0.012738381781151638,
      "grad_norm": 1.1482181549072266,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4932,
      "step": 86
    },
    {
      "epoch": 0.012886502499537123,
      "grad_norm": 1.0970213413238525,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.5062,
      "step": 87
    },
    {
      "epoch": 0.013034623217922607,
      "grad_norm": 1.2930101156234741,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.5562,
      "step": 88
    },
    {
      "epoch": 0.01318274393630809,
      "grad_norm": 1.2993074655532837,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6827,
      "step": 89
    },
    {
      "epoch": 0.013330864654693575,
      "grad_norm": 1.2092087268829346,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5543,
      "step": 90
    },
    {
      "epoch": 0.01347898537307906,
      "grad_norm": 1.3151931762695312,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6098,
      "step": 91
    },
    {
      "epoch": 0.013627106091464544,
      "grad_norm": 1.3638769388198853,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.5903,
      "step": 92
    },
    {
      "epoch": 0.013775226809850027,
      "grad_norm": 1.42976975440979,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.5858,
      "step": 93
    },
    {
      "epoch": 0.013923347528235512,
      "grad_norm": 1.5196677446365356,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.5238,
      "step": 94
    },
    {
      "epoch": 0.014071468246620996,
      "grad_norm": 1.5567885637283325,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.5884,
      "step": 95
    },
    {
      "epoch": 0.014219588965006481,
      "grad_norm": 1.482249140739441,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5593,
      "step": 96
    },
    {
      "epoch": 0.014367709683391964,
      "grad_norm": 1.4134503602981567,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.4576,
      "step": 97
    },
    {
      "epoch": 0.014515830401777449,
      "grad_norm": 1.6437745094299316,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5049,
      "step": 98
    },
    {
      "epoch": 0.014663951120162933,
      "grad_norm": 2.009922981262207,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5317,
      "step": 99
    },
    {
      "epoch": 0.014812071838548418,
      "grad_norm": 2.5810420513153076,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6961,
      "step": 100
    },
    {
      "epoch": 0.014812071838548418,
      "eval_loss": 0.5101078748703003,
      "eval_runtime": 199.0632,
      "eval_samples_per_second": 57.123,
      "eval_steps_per_second": 14.282,
      "step": 100
    },
    {
      "epoch": 0.0149601925569339,
      "grad_norm": 0.2928839921951294,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.129,
      "step": 101
    },
    {
      "epoch": 0.015108313275319385,
      "grad_norm": 0.3165152072906494,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.1613,
      "step": 102
    },
    {
      "epoch": 0.01525643399370487,
      "grad_norm": 0.4189492166042328,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.2141,
      "step": 103
    },
    {
      "epoch": 0.015404554712090353,
      "grad_norm": 0.40022605657577515,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.1804,
      "step": 104
    },
    {
      "epoch": 0.015552675430475837,
      "grad_norm": 0.6710470914840698,
      "learning_rate": 5e-05,
      "loss": 0.4009,
      "step": 105
    },
    {
      "epoch": 0.015700796148861322,
      "grad_norm": 0.6430503129959106,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.3503,
      "step": 106
    },
    {
      "epoch": 0.015848916867246807,
      "grad_norm": 0.5378831624984741,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.3128,
      "step": 107
    },
    {
      "epoch": 0.01599703758563229,
      "grad_norm": 0.49076685309410095,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.2968,
      "step": 108
    },
    {
      "epoch": 0.016145158304017776,
      "grad_norm": 0.5540745258331299,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3346,
      "step": 109
    },
    {
      "epoch": 0.016293279022403257,
      "grad_norm": 0.5119587779045105,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3118,
      "step": 110
    },
    {
      "epoch": 0.016441399740788742,
      "grad_norm": 0.6406883597373962,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.375,
      "step": 111
    },
    {
      "epoch": 0.016589520459174226,
      "grad_norm": 0.6898975372314453,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.4419,
      "step": 112
    },
    {
      "epoch": 0.01673764117755971,
      "grad_norm": 0.7687708139419556,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.5171,
      "step": 113
    },
    {
      "epoch": 0.016885761895945196,
      "grad_norm": 0.7855069637298584,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.5475,
      "step": 114
    },
    {
      "epoch": 0.01703388261433068,
      "grad_norm": 0.7931081652641296,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6011,
      "step": 115
    },
    {
      "epoch": 0.017182003332716165,
      "grad_norm": 0.7942522764205933,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5,
      "step": 116
    },
    {
      "epoch": 0.01733012405110165,
      "grad_norm": 0.9614619612693787,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5715,
      "step": 117
    },
    {
      "epoch": 0.01747824476948713,
      "grad_norm": 0.9708893299102783,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.6281,
      "step": 118
    },
    {
      "epoch": 0.017626365487872615,
      "grad_norm": 1.0538705587387085,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6374,
      "step": 119
    },
    {
      "epoch": 0.0177744862062581,
      "grad_norm": 0.8764832019805908,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.5421,
      "step": 120
    },
    {
      "epoch": 0.017922606924643585,
      "grad_norm": 0.9661458134651184,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6215,
      "step": 121
    },
    {
      "epoch": 0.01807072764302907,
      "grad_norm": 0.9920438528060913,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.5866,
      "step": 122
    },
    {
      "epoch": 0.018218848361414554,
      "grad_norm": 1.0065603256225586,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6933,
      "step": 123
    },
    {
      "epoch": 0.01836696907980004,
      "grad_norm": 0.9531041979789734,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5314,
      "step": 124
    },
    {
      "epoch": 0.01851508979818552,
      "grad_norm": 0.9090996980667114,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4949,
      "step": 125
    },
    {
      "epoch": 0.018663210516571004,
      "grad_norm": 0.8488869071006775,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.4477,
      "step": 126
    },
    {
      "epoch": 0.01881133123495649,
      "grad_norm": 1.0461419820785522,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.5849,
      "step": 127
    },
    {
      "epoch": 0.018959451953341974,
      "grad_norm": 0.981137752532959,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5357,
      "step": 128
    },
    {
      "epoch": 0.019107572671727458,
      "grad_norm": 0.8888973593711853,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4588,
      "step": 129
    },
    {
      "epoch": 0.019255693390112943,
      "grad_norm": 1.1795852184295654,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.4605,
      "step": 130
    },
    {
      "epoch": 0.019403814108498427,
      "grad_norm": 0.9877604842185974,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.4755,
      "step": 131
    },
    {
      "epoch": 0.019551934826883912,
      "grad_norm": 0.8946038484573364,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.4329,
      "step": 132
    },
    {
      "epoch": 0.019700055545269393,
      "grad_norm": 1.0449777841567993,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.5331,
      "step": 133
    },
    {
      "epoch": 0.019848176263654878,
      "grad_norm": 1.0828975439071655,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.4947,
      "step": 134
    },
    {
      "epoch": 0.019996296982040362,
      "grad_norm": 1.0072964429855347,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.4448,
      "step": 135
    },
    {
      "epoch": 0.020144417700425847,
      "grad_norm": 1.0057286024093628,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.4234,
      "step": 136
    },
    {
      "epoch": 0.02029253841881133,
      "grad_norm": 0.9978479146957397,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.4174,
      "step": 137
    },
    {
      "epoch": 0.020440659137196816,
      "grad_norm": 1.2018839120864868,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.5695,
      "step": 138
    },
    {
      "epoch": 0.0205887798555823,
      "grad_norm": 1.1432225704193115,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.5267,
      "step": 139
    },
    {
      "epoch": 0.020736900573967782,
      "grad_norm": 1.3152858018875122,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.5674,
      "step": 140
    },
    {
      "epoch": 0.020885021292353267,
      "grad_norm": 1.2799584865570068,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5091,
      "step": 141
    },
    {
      "epoch": 0.02103314201073875,
      "grad_norm": 1.4054597616195679,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6329,
      "step": 142
    },
    {
      "epoch": 0.021181262729124236,
      "grad_norm": 1.3290269374847412,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5537,
      "step": 143
    },
    {
      "epoch": 0.02132938344750972,
      "grad_norm": 1.3101061582565308,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.4856,
      "step": 144
    },
    {
      "epoch": 0.021477504165895205,
      "grad_norm": 1.369173526763916,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.4726,
      "step": 145
    },
    {
      "epoch": 0.02162562488428069,
      "grad_norm": 1.644787311553955,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.4671,
      "step": 146
    },
    {
      "epoch": 0.021773745602666175,
      "grad_norm": 1.6183255910873413,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5197,
      "step": 147
    },
    {
      "epoch": 0.021921866321051656,
      "grad_norm": 1.4817479848861694,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5047,
      "step": 148
    },
    {
      "epoch": 0.02206998703943714,
      "grad_norm": 1.6811562776565552,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.4774,
      "step": 149
    },
    {
      "epoch": 0.022218107757822625,
      "grad_norm": 1.923085331916809,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5187,
      "step": 150
    },
    {
      "epoch": 0.022218107757822625,
      "eval_loss": 0.46560943126678467,
      "eval_runtime": 199.6065,
      "eval_samples_per_second": 56.967,
      "eval_steps_per_second": 14.243,
      "step": 150
    },
    {
      "epoch": 0.02236622847620811,
      "grad_norm": 0.20941248536109924,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.1182,
      "step": 151
    },
    {
      "epoch": 0.022514349194593594,
      "grad_norm": 0.2344285398721695,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.1013,
      "step": 152
    },
    {
      "epoch": 0.02266246991297908,
      "grad_norm": 0.3138427138328552,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.1661,
      "step": 153
    },
    {
      "epoch": 0.022810590631364563,
      "grad_norm": 0.5025657415390015,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.3055,
      "step": 154
    },
    {
      "epoch": 0.022958711349750045,
      "grad_norm": 0.6071274280548096,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.3456,
      "step": 155
    },
    {
      "epoch": 0.02310683206813553,
      "grad_norm": 0.5330672860145569,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.3517,
      "step": 156
    },
    {
      "epoch": 0.023254952786521014,
      "grad_norm": 0.601538896560669,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.3983,
      "step": 157
    },
    {
      "epoch": 0.0234030735049065,
      "grad_norm": 0.5490806698799133,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.2814,
      "step": 158
    },
    {
      "epoch": 0.023551194223291983,
      "grad_norm": 0.5824691653251648,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.2956,
      "step": 159
    },
    {
      "epoch": 0.023699314941677468,
      "grad_norm": 0.5539517402648926,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.2881,
      "step": 160
    },
    {
      "epoch": 0.023847435660062952,
      "grad_norm": 0.6878145933151245,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.4291,
      "step": 161
    },
    {
      "epoch": 0.023995556378448437,
      "grad_norm": 0.7237358689308167,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.4343,
      "step": 162
    },
    {
      "epoch": 0.024143677096833918,
      "grad_norm": 0.7397705912590027,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.406,
      "step": 163
    },
    {
      "epoch": 0.024291797815219403,
      "grad_norm": 0.8276383876800537,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.4433,
      "step": 164
    },
    {
      "epoch": 0.024439918533604887,
      "grad_norm": 0.8936088681221008,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.4192,
      "step": 165
    },
    {
      "epoch": 0.024588039251990372,
      "grad_norm": 0.9209784865379333,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.5406,
      "step": 166
    },
    {
      "epoch": 0.024736159970375857,
      "grad_norm": 0.9000647068023682,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.5619,
      "step": 167
    },
    {
      "epoch": 0.02488428068876134,
      "grad_norm": 1.0542950630187988,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.6577,
      "step": 168
    },
    {
      "epoch": 0.025032401407146826,
      "grad_norm": 0.9185472130775452,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.5438,
      "step": 169
    },
    {
      "epoch": 0.02518052212553231,
      "grad_norm": 0.9907153844833374,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.5316,
      "step": 170
    },
    {
      "epoch": 0.02532864284391779,
      "grad_norm": 1.1477930545806885,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.6302,
      "step": 171
    },
    {
      "epoch": 0.025476763562303276,
      "grad_norm": 1.0704671144485474,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.4798,
      "step": 172
    },
    {
      "epoch": 0.02562488428068876,
      "grad_norm": 1.0404762029647827,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.5279,
      "step": 173
    },
    {
      "epoch": 0.025773004999074246,
      "grad_norm": 1.0343756675720215,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.5494,
      "step": 174
    },
    {
      "epoch": 0.02592112571745973,
      "grad_norm": 1.0992413759231567,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.5632,
      "step": 175
    },
    {
      "epoch": 0.026069246435845215,
      "grad_norm": 1.025407075881958,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.5955,
      "step": 176
    },
    {
      "epoch": 0.0262173671542307,
      "grad_norm": 1.067736268043518,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.5233,
      "step": 177
    },
    {
      "epoch": 0.02636548787261618,
      "grad_norm": 1.0653537511825562,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.5646,
      "step": 178
    },
    {
      "epoch": 0.026513608591001665,
      "grad_norm": 0.9249374270439148,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.4409,
      "step": 179
    },
    {
      "epoch": 0.02666172930938715,
      "grad_norm": 1.0879504680633545,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.5168,
      "step": 180
    },
    {
      "epoch": 0.026809850027772635,
      "grad_norm": 1.0837440490722656,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5198,
      "step": 181
    },
    {
      "epoch": 0.02695797074615812,
      "grad_norm": 1.0245712995529175,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.476,
      "step": 182
    },
    {
      "epoch": 0.027106091464543604,
      "grad_norm": 1.0423688888549805,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.4694,
      "step": 183
    },
    {
      "epoch": 0.02725421218292909,
      "grad_norm": 1.0829427242279053,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.5408,
      "step": 184
    },
    {
      "epoch": 0.027402332901314573,
      "grad_norm": 0.9738335609436035,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.4779,
      "step": 185
    },
    {
      "epoch": 0.027550453619700054,
      "grad_norm": 1.0937557220458984,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.534,
      "step": 186
    },
    {
      "epoch": 0.02769857433808554,
      "grad_norm": 1.232407569885254,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.5488,
      "step": 187
    },
    {
      "epoch": 0.027846695056471023,
      "grad_norm": 1.1606992483139038,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.5095,
      "step": 188
    },
    {
      "epoch": 0.027994815774856508,
      "grad_norm": 1.1883195638656616,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.4591,
      "step": 189
    },
    {
      "epoch": 0.028142936493241993,
      "grad_norm": 1.180808663368225,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.5011,
      "step": 190
    },
    {
      "epoch": 0.028291057211627477,
      "grad_norm": 1.3043136596679688,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.5021,
      "step": 191
    },
    {
      "epoch": 0.028439177930012962,
      "grad_norm": 1.4346354007720947,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.5283,
      "step": 192
    },
    {
      "epoch": 0.028587298648398443,
      "grad_norm": 1.5261142253875732,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.5269,
      "step": 193
    },
    {
      "epoch": 0.028735419366783928,
      "grad_norm": 1.5818681716918945,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.5632,
      "step": 194
    },
    {
      "epoch": 0.028883540085169412,
      "grad_norm": 1.3146681785583496,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.4757,
      "step": 195
    },
    {
      "epoch": 0.029031660803554897,
      "grad_norm": 1.6426080465316772,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5518,
      "step": 196
    },
    {
      "epoch": 0.02917978152194038,
      "grad_norm": 1.7299507856369019,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.5217,
      "step": 197
    },
    {
      "epoch": 0.029327902240325866,
      "grad_norm": 1.793937087059021,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.5452,
      "step": 198
    },
    {
      "epoch": 0.02947602295871135,
      "grad_norm": 1.5423643589019775,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5069,
      "step": 199
    },
    {
      "epoch": 0.029624143677096836,
      "grad_norm": 2.509003162384033,
      "learning_rate": 0.0,
      "loss": 0.6874,
      "step": 200
    },
    {
      "epoch": 0.029624143677096836,
      "eval_loss": 0.45032814145088196,
      "eval_runtime": 199.1154,
      "eval_samples_per_second": 57.108,
      "eval_steps_per_second": 14.278,
      "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": 1.5476286069669888e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}