{
  "best_metric": 1.7315505743026733,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.3513513513513513,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006756756756756757,
      "grad_norm": 1.4881850481033325,
      "learning_rate": 1e-05,
      "loss": 2.2896,
      "step": 1
    },
    {
      "epoch": 0.006756756756756757,
      "eval_loss": 2.4700465202331543,
      "eval_runtime": 18.7535,
      "eval_samples_per_second": 13.331,
      "eval_steps_per_second": 3.359,
      "step": 1
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 1.8108983039855957,
      "learning_rate": 2e-05,
      "loss": 2.3382,
      "step": 2
    },
    {
      "epoch": 0.02027027027027027,
      "grad_norm": 1.7592962980270386,
      "learning_rate": 3e-05,
      "loss": 2.3745,
      "step": 3
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 1.7991939783096313,
      "learning_rate": 4e-05,
      "loss": 2.3313,
      "step": 4
    },
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 1.6926255226135254,
      "learning_rate": 5e-05,
      "loss": 2.2734,
      "step": 5
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 1.478215217590332,
      "learning_rate": 6e-05,
      "loss": 2.1964,
      "step": 6
    },
    {
      "epoch": 0.0472972972972973,
      "grad_norm": 1.6067980527877808,
      "learning_rate": 7e-05,
      "loss": 2.055,
      "step": 7
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.6643190383911133,
      "learning_rate": 8e-05,
      "loss": 1.9669,
      "step": 8
    },
    {
      "epoch": 0.060810810810810814,
      "grad_norm": 2.5624747276306152,
      "learning_rate": 9e-05,
      "loss": 2.108,
      "step": 9
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 2.2052178382873535,
      "learning_rate": 0.0001,
      "loss": 2.0193,
      "step": 10
    },
    {
      "epoch": 0.07432432432432433,
      "grad_norm": 1.8947843313217163,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.2201,
      "step": 11
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 1.5539779663085938,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.7039,
      "step": 12
    },
    {
      "epoch": 0.08783783783783784,
      "grad_norm": 1.84231698513031,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.7398,
      "step": 13
    },
    {
      "epoch": 0.0945945945945946,
      "grad_norm": 1.828019380569458,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.8482,
      "step": 14
    },
    {
      "epoch": 0.10135135135135136,
      "grad_norm": 1.671506643295288,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.9443,
      "step": 15
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 1.468369722366333,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.8729,
      "step": 16
    },
    {
      "epoch": 0.11486486486486487,
      "grad_norm": 1.5108083486557007,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.6741,
      "step": 17
    },
    {
      "epoch": 0.12162162162162163,
      "grad_norm": 1.6598519086837769,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.8642,
      "step": 18
    },
    {
      "epoch": 0.12837837837837837,
      "grad_norm": 1.6918882131576538,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.8382,
      "step": 19
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 1.6050759553909302,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.7366,
      "step": 20
    },
    {
      "epoch": 0.14189189189189189,
      "grad_norm": 1.6648799180984497,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.8261,
      "step": 21
    },
    {
      "epoch": 0.14864864864864866,
      "grad_norm": 1.6134958267211914,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.7829,
      "step": 22
    },
    {
      "epoch": 0.1554054054054054,
      "grad_norm": 2.065173625946045,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.9168,
      "step": 23
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 1.8863788843154907,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.853,
      "step": 24
    },
    {
      "epoch": 0.16891891891891891,
      "grad_norm": 1.7413650751113892,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.8379,
      "step": 25
    },
    {
      "epoch": 0.17567567567567569,
      "grad_norm": 2.1949267387390137,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.9647,
      "step": 26
    },
    {
      "epoch": 0.18243243243243243,
      "grad_norm": 1.8597412109375,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.8375,
      "step": 27
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 1.9108561277389526,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.7963,
      "step": 28
    },
    {
      "epoch": 0.19594594594594594,
      "grad_norm": 1.9742248058319092,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.8186,
      "step": 29
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 2.1315524578094482,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.7129,
      "step": 30
    },
    {
      "epoch": 0.20945945945945946,
      "grad_norm": 2.3003602027893066,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.8527,
      "step": 31
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 2.4031295776367188,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.739,
      "step": 32
    },
    {
      "epoch": 0.22297297297297297,
      "grad_norm": 2.5433454513549805,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.8151,
      "step": 33
    },
    {
      "epoch": 0.22972972972972974,
      "grad_norm": 2.519287347793579,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.962,
      "step": 34
    },
    {
      "epoch": 0.23648648648648649,
      "grad_norm": 3.300830125808716,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.8442,
      "step": 35
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 2.7878737449645996,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.7497,
      "step": 36
    },
    {
      "epoch": 0.25,
      "grad_norm": 3.9603471755981445,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.1078,
      "step": 37
    },
    {
      "epoch": 0.25675675675675674,
      "grad_norm": 2.3182380199432373,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.2206,
      "step": 38
    },
    {
      "epoch": 0.2635135135135135,
      "grad_norm": 1.6530444622039795,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.1639,
      "step": 39
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 1.4002788066864014,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.9908,
      "step": 40
    },
    {
      "epoch": 0.27702702702702703,
      "grad_norm": 1.275628685951233,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.9277,
      "step": 41
    },
    {
      "epoch": 0.28378378378378377,
      "grad_norm": 1.3413888216018677,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.938,
      "step": 42
    },
    {
      "epoch": 0.2905405405405405,
      "grad_norm": 1.3855804204940796,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.0718,
      "step": 43
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 1.3543145656585693,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.8385,
      "step": 44
    },
    {
      "epoch": 0.30405405405405406,
      "grad_norm": 1.2580598592758179,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.6167,
      "step": 45
    },
    {
      "epoch": 0.3108108108108108,
      "grad_norm": 1.4251524209976196,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.9111,
      "step": 46
    },
    {
      "epoch": 0.31756756756756754,
      "grad_norm": 1.4891302585601807,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.7776,
      "step": 47
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 1.366258978843689,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.8972,
      "step": 48
    },
    {
      "epoch": 0.3310810810810811,
      "grad_norm": 1.3790669441223145,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.752,
      "step": 49
    },
    {
      "epoch": 0.33783783783783783,
      "grad_norm": 1.4619343280792236,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.7721,
      "step": 50
    },
    {
      "epoch": 0.33783783783783783,
      "eval_loss": 1.83683443069458,
      "eval_runtime": 19.0928,
      "eval_samples_per_second": 13.094,
      "eval_steps_per_second": 3.3,
      "step": 50
    },
    {
      "epoch": 0.34459459459459457,
      "grad_norm": 1.3250302076339722,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.7536,
      "step": 51
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 1.4403053522109985,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.8012,
      "step": 52
    },
    {
      "epoch": 0.3581081081081081,
      "grad_norm": 1.4917315244674683,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.6892,
      "step": 53
    },
    {
      "epoch": 0.36486486486486486,
      "grad_norm": 1.6446894407272339,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.9525,
      "step": 54
    },
    {
      "epoch": 0.3716216216216216,
      "grad_norm": 1.5200042724609375,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.7824,
      "step": 55
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 1.5620120763778687,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.741,
      "step": 56
    },
    {
      "epoch": 0.38513513513513514,
      "grad_norm": 1.6956976652145386,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.8795,
      "step": 57
    },
    {
      "epoch": 0.3918918918918919,
      "grad_norm": 1.553536057472229,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.5654,
      "step": 58
    },
    {
      "epoch": 0.39864864864864863,
      "grad_norm": 1.6930755376815796,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.7697,
      "step": 59
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 1.745659351348877,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.8022,
      "step": 60
    },
    {
      "epoch": 0.41216216216216217,
      "grad_norm": 1.6643089056015015,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.707,
      "step": 61
    },
    {
      "epoch": 0.4189189189189189,
      "grad_norm": 1.793350338935852,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.8,
      "step": 62
    },
    {
      "epoch": 0.42567567567567566,
      "grad_norm": 1.9255919456481934,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.8301,
      "step": 63
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 1.9301384687423706,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.7742,
      "step": 64
    },
    {
      "epoch": 0.4391891891891892,
      "grad_norm": 1.8651753664016724,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.623,
      "step": 65
    },
    {
      "epoch": 0.44594594594594594,
      "grad_norm": 1.840767741203308,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.697,
      "step": 66
    },
    {
      "epoch": 0.4527027027027027,
      "grad_norm": 2.4083311557769775,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.7304,
      "step": 67
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 2.3095617294311523,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.9634,
      "step": 68
    },
    {
      "epoch": 0.46621621621621623,
      "grad_norm": 2.0998966693878174,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.688,
      "step": 69
    },
    {
      "epoch": 0.47297297297297297,
      "grad_norm": 2.2831101417541504,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.7282,
      "step": 70
    },
    {
      "epoch": 0.4797297297297297,
      "grad_norm": 2.6891002655029297,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.6371,
      "step": 71
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 3.39951229095459,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.8312,
      "step": 72
    },
    {
      "epoch": 0.49324324324324326,
      "grad_norm": 1.6419343948364258,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.9608,
      "step": 73
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.8251267671585083,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.0402,
      "step": 74
    },
    {
      "epoch": 0.5067567567567568,
      "grad_norm": 1.3056743144989014,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.9794,
      "step": 75
    },
    {
      "epoch": 0.5135135135135135,
      "grad_norm": 1.2231546640396118,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.8808,
      "step": 76
    },
    {
      "epoch": 0.5202702702702703,
      "grad_norm": 1.0886365175247192,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.9188,
      "step": 77
    },
    {
      "epoch": 0.527027027027027,
      "grad_norm": 1.088363766670227,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.7402,
      "step": 78
    },
    {
      "epoch": 0.5337837837837838,
      "grad_norm": 1.1260857582092285,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.823,
      "step": 79
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 1.1230112314224243,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.8329,
      "step": 80
    },
    {
      "epoch": 0.5472972972972973,
      "grad_norm": 1.212681770324707,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.8555,
      "step": 81
    },
    {
      "epoch": 0.5540540540540541,
      "grad_norm": 1.3454909324645996,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.8396,
      "step": 82
    },
    {
      "epoch": 0.5608108108108109,
      "grad_norm": 1.3234645128250122,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.7526,
      "step": 83
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 1.3924024105072021,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.7653,
      "step": 84
    },
    {
      "epoch": 0.5743243243243243,
      "grad_norm": 1.4511988162994385,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.8858,
      "step": 85
    },
    {
      "epoch": 0.581081081081081,
      "grad_norm": 1.4272857904434204,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7755,
      "step": 86
    },
    {
      "epoch": 0.5878378378378378,
      "grad_norm": 1.396707534790039,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.8197,
      "step": 87
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 1.3739862442016602,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.7488,
      "step": 88
    },
    {
      "epoch": 0.6013513513513513,
      "grad_norm": 1.3782387971878052,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.6464,
      "step": 89
    },
    {
      "epoch": 0.6081081081081081,
      "grad_norm": 1.355536699295044,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.6933,
      "step": 90
    },
    {
      "epoch": 0.6148648648648649,
      "grad_norm": 1.3642878532409668,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.7555,
      "step": 91
    },
    {
      "epoch": 0.6216216216216216,
      "grad_norm": 1.4226493835449219,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.6599,
      "step": 92
    },
    {
      "epoch": 0.6283783783783784,
      "grad_norm": 1.3061779737472534,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.5284,
      "step": 93
    },
    {
      "epoch": 0.6351351351351351,
      "grad_norm": 1.3788888454437256,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.6622,
      "step": 94
    },
    {
      "epoch": 0.6418918918918919,
      "grad_norm": 1.7191851139068604,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.6717,
      "step": 95
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 1.4940510988235474,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.5653,
      "step": 96
    },
    {
      "epoch": 0.6554054054054054,
      "grad_norm": 1.5173310041427612,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.7142,
      "step": 97
    },
    {
      "epoch": 0.6621621621621622,
      "grad_norm": 1.6589378118515015,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.7946,
      "step": 98
    },
    {
      "epoch": 0.668918918918919,
      "grad_norm": 1.6999168395996094,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.6087,
      "step": 99
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 1.5908018350601196,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.7041,
      "step": 100
    },
    {
      "epoch": 0.6756756756756757,
      "eval_loss": 1.7584482431411743,
      "eval_runtime": 19.1007,
      "eval_samples_per_second": 13.089,
      "eval_steps_per_second": 3.298,
      "step": 100
    },
    {
      "epoch": 0.6824324324324325,
      "grad_norm": 1.836527943611145,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.7546,
      "step": 101
    },
    {
      "epoch": 0.6891891891891891,
      "grad_norm": 1.8849434852600098,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.6365,
      "step": 102
    },
    {
      "epoch": 0.6959459459459459,
      "grad_norm": 1.9299622774124146,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.6052,
      "step": 103
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 2.089512825012207,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.7296,
      "step": 104
    },
    {
      "epoch": 0.7094594594594594,
      "grad_norm": 1.808120608329773,
      "learning_rate": 5e-05,
      "loss": 1.6889,
      "step": 105
    },
    {
      "epoch": 0.7162162162162162,
      "grad_norm": 2.2202186584472656,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.6959,
      "step": 106
    },
    {
      "epoch": 0.722972972972973,
      "grad_norm": 2.3467860221862793,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.6461,
      "step": 107
    },
    {
      "epoch": 0.7297297297297297,
      "grad_norm": 3.3338701725006104,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.8413,
      "step": 108
    },
    {
      "epoch": 0.7364864864864865,
      "grad_norm": 0.9207017421722412,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.7965,
      "step": 109
    },
    {
      "epoch": 0.7432432432432432,
      "grad_norm": 1.0568395853042603,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.9779,
      "step": 110
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.077010989189148,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.9172,
      "step": 111
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 1.1530791521072388,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.9039,
      "step": 112
    },
    {
      "epoch": 0.7635135135135135,
      "grad_norm": 1.0896953344345093,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.8296,
      "step": 113
    },
    {
      "epoch": 0.7702702702702703,
      "grad_norm": 1.1918020248413086,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.9247,
      "step": 114
    },
    {
      "epoch": 0.777027027027027,
      "grad_norm": 1.1241543292999268,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.7553,
      "step": 115
    },
    {
      "epoch": 0.7837837837837838,
      "grad_norm": 1.2757718563079834,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.8879,
      "step": 116
    },
    {
      "epoch": 0.7905405405405406,
      "grad_norm": 1.1494501829147339,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.7533,
      "step": 117
    },
    {
      "epoch": 0.7972972972972973,
      "grad_norm": 1.2045955657958984,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.8376,
      "step": 118
    },
    {
      "epoch": 0.8040540540540541,
      "grad_norm": 1.1379261016845703,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.7582,
      "step": 119
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 1.1892424821853638,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.8122,
      "step": 120
    },
    {
      "epoch": 0.8175675675675675,
      "grad_norm": 1.3637396097183228,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.8529,
      "step": 121
    },
    {
      "epoch": 0.8243243243243243,
      "grad_norm": 1.3209075927734375,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.819,
      "step": 122
    },
    {
      "epoch": 0.831081081081081,
      "grad_norm": 1.2940394878387451,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.6662,
      "step": 123
    },
    {
      "epoch": 0.8378378378378378,
      "grad_norm": 1.4017469882965088,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.7371,
      "step": 124
    },
    {
      "epoch": 0.8445945945945946,
      "grad_norm": 1.3841819763183594,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.6858,
      "step": 125
    },
    {
      "epoch": 0.8513513513513513,
      "grad_norm": 1.4161312580108643,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.7909,
      "step": 126
    },
    {
      "epoch": 0.8581081081081081,
      "grad_norm": 1.2421355247497559,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.5222,
      "step": 127
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 1.4063892364501953,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.6815,
      "step": 128
    },
    {
      "epoch": 0.8716216216216216,
      "grad_norm": 1.6757177114486694,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.6262,
      "step": 129
    },
    {
      "epoch": 0.8783783783783784,
      "grad_norm": 1.5155936479568481,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.7655,
      "step": 130
    },
    {
      "epoch": 0.8851351351351351,
      "grad_norm": 1.5159090757369995,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.6841,
      "step": 131
    },
    {
      "epoch": 0.8918918918918919,
      "grad_norm": 1.5409551858901978,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.6255,
      "step": 132
    },
    {
      "epoch": 0.8986486486486487,
      "grad_norm": 1.6696666479110718,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.7015,
      "step": 133
    },
    {
      "epoch": 0.9054054054054054,
      "grad_norm": 1.5418610572814941,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.5711,
      "step": 134
    },
    {
      "epoch": 0.9121621621621622,
      "grad_norm": 1.5207306146621704,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.5325,
      "step": 135
    },
    {
      "epoch": 0.918918918918919,
      "grad_norm": 1.7531079053878784,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.7186,
      "step": 136
    },
    {
      "epoch": 0.9256756756756757,
      "grad_norm": 1.7365700006484985,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.679,
      "step": 137
    },
    {
      "epoch": 0.9324324324324325,
      "grad_norm": 1.9208725690841675,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.7983,
      "step": 138
    },
    {
      "epoch": 0.9391891891891891,
      "grad_norm": 1.9840606451034546,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.5804,
      "step": 139
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 1.9370635747909546,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.8238,
      "step": 140
    },
    {
      "epoch": 0.9527027027027027,
      "grad_norm": 1.777245044708252,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.615,
      "step": 141
    },
    {
      "epoch": 0.9594594594594594,
      "grad_norm": 1.962254524230957,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.7675,
      "step": 142
    },
    {
      "epoch": 0.9662162162162162,
      "grad_norm": 2.394348621368408,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.7884,
      "step": 143
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 3.6063008308410645,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.0449,
      "step": 144
    },
    {
      "epoch": 0.9797297297297297,
      "grad_norm": 0.8878645300865173,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.7525,
      "step": 145
    },
    {
      "epoch": 0.9864864864864865,
      "grad_norm": 1.3657875061035156,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.7504,
      "step": 146
    },
    {
      "epoch": 0.9932432432432432,
      "grad_norm": 1.707741618156433,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.714,
      "step": 147
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.2892343997955322,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.7755,
      "step": 148
    },
    {
      "epoch": 1.0067567567567568,
      "grad_norm": 0.6727629899978638,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.7335,
      "step": 149
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 0.7982877492904663,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.6699,
      "step": 150
    },
    {
      "epoch": 1.0135135135135136,
      "eval_loss": 1.7333842515945435,
      "eval_runtime": 19.0871,
      "eval_samples_per_second": 13.098,
      "eval_steps_per_second": 3.301,
      "step": 150
    },
    {
      "epoch": 1.0202702702702702,
      "grad_norm": 1.0961229801177979,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.5556,
      "step": 151
    },
    {
      "epoch": 1.027027027027027,
      "grad_norm": 0.8351145386695862,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.6791,
      "step": 152
    },
    {
      "epoch": 1.0337837837837838,
      "grad_norm": 0.881202220916748,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.483,
      "step": 153
    },
    {
      "epoch": 1.0405405405405406,
      "grad_norm": 0.9148615598678589,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.5782,
      "step": 154
    },
    {
      "epoch": 1.0472972972972974,
      "grad_norm": 0.9518046379089355,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.4297,
      "step": 155
    },
    {
      "epoch": 1.054054054054054,
      "grad_norm": 0.8803594708442688,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.5431,
      "step": 156
    },
    {
      "epoch": 1.0608108108108107,
      "grad_norm": 0.9387824535369873,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.5236,
      "step": 157
    },
    {
      "epoch": 1.0675675675675675,
      "grad_norm": 0.9106830954551697,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.4598,
      "step": 158
    },
    {
      "epoch": 1.0743243243243243,
      "grad_norm": 1.0289093255996704,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.426,
      "step": 159
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.935211718082428,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.3979,
      "step": 160
    },
    {
      "epoch": 1.087837837837838,
      "grad_norm": 0.9888346791267395,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.4918,
      "step": 161
    },
    {
      "epoch": 1.0945945945945945,
      "grad_norm": 0.9276695847511292,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.3791,
      "step": 162
    },
    {
      "epoch": 1.1013513513513513,
      "grad_norm": 1.0374265909194946,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.3833,
      "step": 163
    },
    {
      "epoch": 1.1081081081081081,
      "grad_norm": 0.9723080992698669,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.3818,
      "step": 164
    },
    {
      "epoch": 1.114864864864865,
      "grad_norm": 0.9936453700065613,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.1786,
      "step": 165
    },
    {
      "epoch": 1.1216216216216217,
      "grad_norm": 1.0306607484817505,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.2918,
      "step": 166
    },
    {
      "epoch": 1.1283783783783783,
      "grad_norm": 1.0798985958099365,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.3631,
      "step": 167
    },
    {
      "epoch": 1.135135135135135,
      "grad_norm": 1.1167194843292236,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.3679,
      "step": 168
    },
    {
      "epoch": 1.1418918918918919,
      "grad_norm": 1.054006814956665,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.2199,
      "step": 169
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 1.1359713077545166,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.2494,
      "step": 170
    },
    {
      "epoch": 1.1554054054054055,
      "grad_norm": 1.173397421836853,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.2015,
      "step": 171
    },
    {
      "epoch": 1.1621621621621623,
      "grad_norm": 1.1659588813781738,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.3098,
      "step": 172
    },
    {
      "epoch": 1.1689189189189189,
      "grad_norm": 1.1626965999603271,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.1552,
      "step": 173
    },
    {
      "epoch": 1.1756756756756757,
      "grad_norm": 1.1938607692718506,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.3259,
      "step": 174
    },
    {
      "epoch": 1.1824324324324325,
      "grad_norm": 1.3839091062545776,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.3317,
      "step": 175
    },
    {
      "epoch": 1.1891891891891893,
      "grad_norm": 1.2780675888061523,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.1455,
      "step": 176
    },
    {
      "epoch": 1.195945945945946,
      "grad_norm": 1.3545082807540894,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.2065,
      "step": 177
    },
    {
      "epoch": 1.2027027027027026,
      "grad_norm": 1.3624012470245361,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.3555,
      "step": 178
    },
    {
      "epoch": 1.2094594594594594,
      "grad_norm": 1.5422807931900024,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.2722,
      "step": 179
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 1.5503495931625366,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.3365,
      "step": 180
    },
    {
      "epoch": 1.222972972972973,
      "grad_norm": 1.6035807132720947,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.3917,
      "step": 181
    },
    {
      "epoch": 1.2297297297297298,
      "grad_norm": 1.641324758529663,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.2891,
      "step": 182
    },
    {
      "epoch": 1.2364864864864864,
      "grad_norm": 2.169276475906372,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.2757,
      "step": 183
    },
    {
      "epoch": 1.2432432432432432,
      "grad_norm": 2.748438835144043,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.4344,
      "step": 184
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.811975359916687,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.6134,
      "step": 185
    },
    {
      "epoch": 1.2567567567567568,
      "grad_norm": 0.88874751329422,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.6381,
      "step": 186
    },
    {
      "epoch": 1.2635135135135136,
      "grad_norm": 0.9452928304672241,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.6264,
      "step": 187
    },
    {
      "epoch": 1.2702702702702702,
      "grad_norm": 1.001508116722107,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.5002,
      "step": 188
    },
    {
      "epoch": 1.277027027027027,
      "grad_norm": 0.9683878421783447,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.5317,
      "step": 189
    },
    {
      "epoch": 1.2837837837837838,
      "grad_norm": 0.9598335027694702,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.4752,
      "step": 190
    },
    {
      "epoch": 1.2905405405405406,
      "grad_norm": 1.0072753429412842,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.468,
      "step": 191
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 1.0365445613861084,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.529,
      "step": 192
    },
    {
      "epoch": 1.304054054054054,
      "grad_norm": 0.9871605634689331,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.417,
      "step": 193
    },
    {
      "epoch": 1.3108108108108107,
      "grad_norm": 1.0450514554977417,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.4976,
      "step": 194
    },
    {
      "epoch": 1.3175675675675675,
      "grad_norm": 1.0782577991485596,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.4995,
      "step": 195
    },
    {
      "epoch": 1.3243243243243243,
      "grad_norm": 1.0584638118743896,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.4653,
      "step": 196
    },
    {
      "epoch": 1.3310810810810811,
      "grad_norm": 1.061495304107666,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.3184,
      "step": 197
    },
    {
      "epoch": 1.3378378378378377,
      "grad_norm": 1.1168327331542969,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.3966,
      "step": 198
    },
    {
      "epoch": 1.3445945945945945,
      "grad_norm": 1.1341110467910767,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.4455,
      "step": 199
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 1.033117413520813,
      "learning_rate": 0.0,
      "loss": 1.3281,
      "step": 200
    },
    {
      "epoch": 1.3513513513513513,
      "eval_loss": 1.7315505743026733,
      "eval_runtime": 19.0891,
      "eval_samples_per_second": 13.096,
      "eval_steps_per_second": 3.3,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.015612926011638e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}