{
  "best_metric": 1.731801986694336,
  "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": 1.4424006938934326,
      "learning_rate": 1e-05,
      "loss": 2.2896,
      "step": 1
    },
    {
      "epoch": 0.006756756756756757,
      "eval_loss": 2.4700465202331543,
      "eval_runtime": 18.613,
      "eval_samples_per_second": 13.431,
      "eval_steps_per_second": 3.385,
      "step": 1
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 1.7567722797393799,
      "learning_rate": 2e-05,
      "loss": 2.3382,
      "step": 2
    },
    {
      "epoch": 0.02027027027027027,
      "grad_norm": 1.7165125608444214,
      "learning_rate": 3e-05,
      "loss": 2.3747,
      "step": 3
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 1.7339659929275513,
      "learning_rate": 4e-05,
      "loss": 2.3317,
      "step": 4
    },
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 1.658001184463501,
      "learning_rate": 5e-05,
      "loss": 2.2753,
      "step": 5
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 1.4608352184295654,
      "learning_rate": 6e-05,
      "loss": 2.1977,
      "step": 6
    },
    {
      "epoch": 0.0472972972972973,
      "grad_norm": 1.592839002609253,
      "learning_rate": 7e-05,
      "loss": 2.0545,
      "step": 7
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.6094963550567627,
      "learning_rate": 8e-05,
      "loss": 1.9669,
      "step": 8
    },
    {
      "epoch": 0.060810810810810814,
      "grad_norm": 2.4839794635772705,
      "learning_rate": 9e-05,
      "loss": 2.1095,
      "step": 9
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 2.2013440132141113,
      "learning_rate": 0.0001,
      "loss": 2.0207,
      "step": 10
    },
    {
      "epoch": 0.07432432432432433,
      "grad_norm": 1.868704915046692,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.219,
      "step": 11
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 1.5163902044296265,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.7047,
      "step": 12
    },
    {
      "epoch": 0.08783783783783784,
      "grad_norm": 1.818183183670044,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.7389,
      "step": 13
    },
    {
      "epoch": 0.0945945945945946,
      "grad_norm": 1.8183751106262207,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.8483,
      "step": 14
    },
    {
      "epoch": 0.10135135135135136,
      "grad_norm": 1.6848615407943726,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.9458,
      "step": 15
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 1.4533350467681885,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.8722,
      "step": 16
    },
    {
      "epoch": 0.11486486486486487,
      "grad_norm": 1.4766217470169067,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.6756,
      "step": 17
    },
    {
      "epoch": 0.12162162162162163,
      "grad_norm": 1.6617404222488403,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.8676,
      "step": 18
    },
    {
      "epoch": 0.12837837837837837,
      "grad_norm": 1.667425274848938,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.8379,
      "step": 19
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 1.5992474555969238,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.7354,
      "step": 20
    },
    {
      "epoch": 0.14189189189189189,
      "grad_norm": 1.6577551364898682,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.8265,
      "step": 21
    },
    {
      "epoch": 0.14864864864864866,
      "grad_norm": 1.6034307479858398,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.783,
      "step": 22
    },
    {
      "epoch": 0.1554054054054054,
      "grad_norm": 2.068225145339966,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.9163,
      "step": 23
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 1.7155823707580566,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.8537,
      "step": 24
    },
    {
      "epoch": 0.16891891891891891,
      "grad_norm": 1.703191876411438,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.839,
      "step": 25
    },
    {
      "epoch": 0.17567567567567569,
      "grad_norm": 2.158104658126831,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.9672,
      "step": 26
    },
    {
      "epoch": 0.18243243243243243,
      "grad_norm": 1.834190011024475,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.8346,
      "step": 27
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 1.9021737575531006,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.7981,
      "step": 28
    },
    {
      "epoch": 0.19594594594594594,
      "grad_norm": 1.9429136514663696,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.8159,
      "step": 29
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 2.137256383895874,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.7183,
      "step": 30
    },
    {
      "epoch": 0.20945945945945946,
      "grad_norm": 2.3155884742736816,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.8515,
      "step": 31
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 2.3982532024383545,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.7351,
      "step": 32
    },
    {
      "epoch": 0.22297297297297297,
      "grad_norm": 2.658118724822998,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.8166,
      "step": 33
    },
    {
      "epoch": 0.22972972972972974,
      "grad_norm": 2.4856467247009277,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.9582,
      "step": 34
    },
    {
      "epoch": 0.23648648648648649,
      "grad_norm": 3.3881924152374268,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.8473,
      "step": 35
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 2.7870328426361084,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.7502,
      "step": 36
    },
    {
      "epoch": 0.25,
      "grad_norm": 4.050192356109619,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.1093,
      "step": 37
    },
    {
      "epoch": 0.25675675675675674,
      "grad_norm": 2.349740982055664,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.2211,
      "step": 38
    },
    {
      "epoch": 0.2635135135135135,
      "grad_norm": 1.6817964315414429,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.1682,
      "step": 39
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 1.4059157371520996,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.9945,
      "step": 40
    },
    {
      "epoch": 0.27702702702702703,
      "grad_norm": 1.2649842500686646,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.927,
      "step": 41
    },
    {
      "epoch": 0.28378378378378377,
      "grad_norm": 1.327721357345581,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.9329,
      "step": 42
    },
    {
      "epoch": 0.2905405405405405,
      "grad_norm": 1.3768377304077148,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.0718,
      "step": 43
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 1.3469047546386719,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.8375,
      "step": 44
    },
    {
      "epoch": 0.30405405405405406,
      "grad_norm": 1.2437846660614014,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.6175,
      "step": 45
    },
    {
      "epoch": 0.3108108108108108,
      "grad_norm": 1.410740613937378,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.909,
      "step": 46
    },
    {
      "epoch": 0.31756756756756754,
      "grad_norm": 1.4747393131256104,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.7801,
      "step": 47
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 1.3618700504302979,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.8941,
      "step": 48
    },
    {
      "epoch": 0.3310810810810811,
      "grad_norm": 1.3720588684082031,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.7513,
      "step": 49
    },
    {
      "epoch": 0.33783783783783783,
      "grad_norm": 1.4571261405944824,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.77,
      "step": 50
    },
    {
      "epoch": 0.33783783783783783,
      "eval_loss": 1.8364510536193848,
      "eval_runtime": 19.046,
      "eval_samples_per_second": 13.126,
      "eval_steps_per_second": 3.308,
      "step": 50
    },
    {
      "epoch": 0.34459459459459457,
      "grad_norm": 1.3135939836502075,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.7529,
      "step": 51
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 1.4373500347137451,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.7974,
      "step": 52
    },
    {
      "epoch": 0.3581081081081081,
      "grad_norm": 1.4697256088256836,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.6894,
      "step": 53
    },
    {
      "epoch": 0.36486486486486486,
      "grad_norm": 1.5970127582550049,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.9512,
      "step": 54
    },
    {
      "epoch": 0.3716216216216216,
      "grad_norm": 1.5128464698791504,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.7841,
      "step": 55
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 1.5473500490188599,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.7422,
      "step": 56
    },
    {
      "epoch": 0.38513513513513514,
      "grad_norm": 1.6563612222671509,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.8778,
      "step": 57
    },
    {
      "epoch": 0.3918918918918919,
      "grad_norm": 1.554996371269226,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.5663,
      "step": 58
    },
    {
      "epoch": 0.39864864864864863,
      "grad_norm": 1.7116591930389404,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.7736,
      "step": 59
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 1.7566837072372437,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.8033,
      "step": 60
    },
    {
      "epoch": 0.41216216216216217,
      "grad_norm": 1.6613717079162598,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.7087,
      "step": 61
    },
    {
      "epoch": 0.4189189189189189,
      "grad_norm": 1.7990913391113281,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.7977,
      "step": 62
    },
    {
      "epoch": 0.42567567567567566,
      "grad_norm": 1.9019392728805542,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.8293,
      "step": 63
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 1.8706392049789429,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.7699,
      "step": 64
    },
    {
      "epoch": 0.4391891891891892,
      "grad_norm": 1.7907861471176147,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.6263,
      "step": 65
    },
    {
      "epoch": 0.44594594594594594,
      "grad_norm": 1.8318133354187012,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.6942,
      "step": 66
    },
    {
      "epoch": 0.4527027027027027,
      "grad_norm": 2.4412620067596436,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.7295,
      "step": 67
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 2.297849416732788,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.9598,
      "step": 68
    },
    {
      "epoch": 0.46621621621621623,
      "grad_norm": 2.302893877029419,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.6941,
      "step": 69
    },
    {
      "epoch": 0.47297297297297297,
      "grad_norm": 2.3092434406280518,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.7261,
      "step": 70
    },
    {
      "epoch": 0.4797297297297297,
      "grad_norm": 2.717576026916504,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.6447,
      "step": 71
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 3.4354751110076904,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.8257,
      "step": 72
    },
    {
      "epoch": 0.49324324324324326,
      "grad_norm": 1.7039185762405396,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.9664,
      "step": 73
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.869041085243225,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.0434,
      "step": 74
    },
    {
      "epoch": 0.5067567567567568,
      "grad_norm": 1.3360240459442139,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.9819,
      "step": 75
    },
    {
      "epoch": 0.5135135135135135,
      "grad_norm": 1.2354875802993774,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.8833,
      "step": 76
    },
    {
      "epoch": 0.5202702702702703,
      "grad_norm": 1.0735878944396973,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.9188,
      "step": 77
    },
    {
      "epoch": 0.527027027027027,
      "grad_norm": 1.0975722074508667,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.7407,
      "step": 78
    },
    {
      "epoch": 0.5337837837837838,
      "grad_norm": 1.1281282901763916,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.8215,
      "step": 79
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 1.1505932807922363,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.8352,
      "step": 80
    },
    {
      "epoch": 0.5472972972972973,
      "grad_norm": 1.2216392755508423,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.857,
      "step": 81
    },
    {
      "epoch": 0.5540540540540541,
      "grad_norm": 1.3606364727020264,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.8384,
      "step": 82
    },
    {
      "epoch": 0.5608108108108109,
      "grad_norm": 1.2895755767822266,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.7498,
      "step": 83
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 1.3863445520401,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.7625,
      "step": 84
    },
    {
      "epoch": 0.5743243243243243,
      "grad_norm": 1.4560896158218384,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.8851,
      "step": 85
    },
    {
      "epoch": 0.581081081081081,
      "grad_norm": 1.383874535560608,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7746,
      "step": 86
    },
    {
      "epoch": 0.5878378378378378,
      "grad_norm": 1.4054803848266602,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.8148,
      "step": 87
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 1.3873168230056763,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.7478,
      "step": 88
    },
    {
      "epoch": 0.6013513513513513,
      "grad_norm": 1.3346433639526367,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.6446,
      "step": 89
    },
    {
      "epoch": 0.6081081081081081,
      "grad_norm": 1.3729857206344604,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.6928,
      "step": 90
    },
    {
      "epoch": 0.6148648648648649,
      "grad_norm": 1.3824392557144165,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.7588,
      "step": 91
    },
    {
      "epoch": 0.6216216216216216,
      "grad_norm": 1.4349851608276367,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.6533,
      "step": 92
    },
    {
      "epoch": 0.6283783783783784,
      "grad_norm": 1.316225528717041,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.5275,
      "step": 93
    },
    {
      "epoch": 0.6351351351351351,
      "grad_norm": 1.3668450117111206,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.6587,
      "step": 94
    },
    {
      "epoch": 0.6418918918918919,
      "grad_norm": 1.7887675762176514,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.6733,
      "step": 95
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 1.5239506959915161,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.561,
      "step": 96
    },
    {
      "epoch": 0.6554054054054054,
      "grad_norm": 1.5424968004226685,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.7148,
      "step": 97
    },
    {
      "epoch": 0.6621621621621622,
      "grad_norm": 1.6639710664749146,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.7896,
      "step": 98
    },
    {
      "epoch": 0.668918918918919,
      "grad_norm": 1.7059831619262695,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.6107,
      "step": 99
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 1.5801199674606323,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.7029,
      "step": 100
    },
    {
      "epoch": 0.6756756756756757,
      "eval_loss": 1.7584396600723267,
      "eval_runtime": 19.0458,
      "eval_samples_per_second": 13.126,
      "eval_steps_per_second": 3.308,
      "step": 100
    },
    {
      "epoch": 0.6824324324324325,
      "grad_norm": 1.8537980318069458,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.7517,
      "step": 101
    },
    {
      "epoch": 0.6891891891891891,
      "grad_norm": 1.8177871704101562,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.6352,
      "step": 102
    },
    {
      "epoch": 0.6959459459459459,
      "grad_norm": 1.9382191896438599,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.5982,
      "step": 103
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 2.128898859024048,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.732,
      "step": 104
    },
    {
      "epoch": 0.7094594594594594,
      "grad_norm": 1.784104347229004,
      "learning_rate": 5e-05,
      "loss": 1.6939,
      "step": 105
    },
    {
      "epoch": 0.7162162162162162,
      "grad_norm": 2.270146608352661,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.6915,
      "step": 106
    },
    {
      "epoch": 0.722972972972973,
      "grad_norm": 2.3428573608398438,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.6535,
      "step": 107
    },
    {
      "epoch": 0.7297297297297297,
      "grad_norm": 3.3533735275268555,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.8415,
      "step": 108
    },
    {
      "epoch": 0.7364864864864865,
      "grad_norm": 0.9056187272071838,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.7962,
      "step": 109
    },
    {
      "epoch": 0.7432432432432432,
      "grad_norm": 1.0447241067886353,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.9744,
      "step": 110
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.0797970294952393,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.9122,
      "step": 111
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 1.1365164518356323,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.9016,
      "step": 112
    },
    {
      "epoch": 0.7635135135135135,
      "grad_norm": 1.0872780084609985,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.8274,
      "step": 113
    },
    {
      "epoch": 0.7702702702702703,
      "grad_norm": 1.184290885925293,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.9215,
      "step": 114
    },
    {
      "epoch": 0.777027027027027,
      "grad_norm": 1.1291645765304565,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.7554,
      "step": 115
    },
    {
      "epoch": 0.7837837837837838,
      "grad_norm": 1.2960712909698486,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.8886,
      "step": 116
    },
    {
      "epoch": 0.7905405405405406,
      "grad_norm": 1.1408990621566772,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.7567,
      "step": 117
    },
    {
      "epoch": 0.7972972972972973,
      "grad_norm": 1.1692568063735962,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.8379,
      "step": 118
    },
    {
      "epoch": 0.8040540540540541,
      "grad_norm": 1.127036690711975,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.7573,
      "step": 119
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 1.2699527740478516,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.8159,
      "step": 120
    },
    {
      "epoch": 0.8175675675675675,
      "grad_norm": 1.3854831457138062,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.8549,
      "step": 121
    },
    {
      "epoch": 0.8243243243243243,
      "grad_norm": 1.3047043085098267,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.8136,
      "step": 122
    },
    {
      "epoch": 0.831081081081081,
      "grad_norm": 1.2977917194366455,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.6685,
      "step": 123
    },
    {
      "epoch": 0.8378378378378378,
      "grad_norm": 1.3917666673660278,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.7359,
      "step": 124
    },
    {
      "epoch": 0.8445945945945946,
      "grad_norm": 1.344507098197937,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.6795,
      "step": 125
    },
    {
      "epoch": 0.8513513513513513,
      "grad_norm": 1.4202960729599,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.7903,
      "step": 126
    },
    {
      "epoch": 0.8581081081081081,
      "grad_norm": 1.2365199327468872,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.523,
      "step": 127
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 1.397666096687317,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.677,
      "step": 128
    },
    {
      "epoch": 0.8716216216216216,
      "grad_norm": 1.6794039011001587,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.6318,
      "step": 129
    },
    {
      "epoch": 0.8783783783783784,
      "grad_norm": 1.5319836139678955,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.7702,
      "step": 130
    },
    {
      "epoch": 0.8851351351351351,
      "grad_norm": 1.506230354309082,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.6815,
      "step": 131
    },
    {
      "epoch": 0.8918918918918919,
      "grad_norm": 1.5346109867095947,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.626,
      "step": 132
    },
    {
      "epoch": 0.8986486486486487,
      "grad_norm": 1.6561803817749023,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.7026,
      "step": 133
    },
    {
      "epoch": 0.9054054054054054,
      "grad_norm": 1.5465972423553467,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.5765,
      "step": 134
    },
    {
      "epoch": 0.9121621621621622,
      "grad_norm": 1.5170146226882935,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.5319,
      "step": 135
    },
    {
      "epoch": 0.918918918918919,
      "grad_norm": 1.771231770515442,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.7212,
      "step": 136
    },
    {
      "epoch": 0.9256756756756757,
      "grad_norm": 1.7398310899734497,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.68,
      "step": 137
    },
    {
      "epoch": 0.9324324324324325,
      "grad_norm": 1.9382745027542114,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.8069,
      "step": 138
    },
    {
      "epoch": 0.9391891891891891,
      "grad_norm": 1.9916131496429443,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.5806,
      "step": 139
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 1.9692929983139038,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.8319,
      "step": 140
    },
    {
      "epoch": 0.9527027027027027,
      "grad_norm": 1.797459363937378,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.6157,
      "step": 141
    },
    {
      "epoch": 0.9594594594594594,
      "grad_norm": 1.936741590499878,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.7699,
      "step": 142
    },
    {
      "epoch": 0.9662162162162162,
      "grad_norm": 2.5726919174194336,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.7985,
      "step": 143
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 3.5902199745178223,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.0564,
      "step": 144
    },
    {
      "epoch": 0.9797297297297297,
      "grad_norm": 0.8869878053665161,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.7503,
      "step": 145
    },
    {
      "epoch": 0.9864864864864865,
      "grad_norm": 1.3740302324295044,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.7532,
      "step": 146
    },
    {
      "epoch": 0.9932432432432432,
      "grad_norm": 1.689588189125061,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.7129,
      "step": 147
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.279188871383667,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.768,
      "step": 148
    },
    {
      "epoch": 1.0067567567567568,
      "grad_norm": 0.6688696146011353,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.7331,
      "step": 149
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 0.7973382472991943,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.6709,
      "step": 150
    },
    {
      "epoch": 1.0135135135135136,
      "eval_loss": 1.7332968711853027,
      "eval_runtime": 19.0141,
      "eval_samples_per_second": 13.148,
      "eval_steps_per_second": 3.313,
      "step": 150
    },
    {
      "epoch": 1.0202702702702702,
      "grad_norm": 0.8185219764709473,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.5568,
      "step": 151
    },
    {
      "epoch": 1.027027027027027,
      "grad_norm": 0.8312488794326782,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.678,
      "step": 152
    },
    {
      "epoch": 1.0337837837837838,
      "grad_norm": 0.8709858655929565,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.482,
      "step": 153
    },
    {
      "epoch": 1.0405405405405406,
      "grad_norm": 0.9107933044433594,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.5784,
      "step": 154
    },
    {
      "epoch": 1.0472972972972974,
      "grad_norm": 0.9437603950500488,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.4273,
      "step": 155
    },
    {
      "epoch": 1.054054054054054,
      "grad_norm": 0.8831038475036621,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.5457,
      "step": 156
    },
    {
      "epoch": 1.0608108108108107,
      "grad_norm": 0.9698243141174316,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.5227,
      "step": 157
    },
    {
      "epoch": 1.0675675675675675,
      "grad_norm": 0.9177638292312622,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.4566,
      "step": 158
    },
    {
      "epoch": 1.0743243243243243,
      "grad_norm": 1.007506251335144,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.4223,
      "step": 159
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.9366555213928223,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.4004,
      "step": 160
    },
    {
      "epoch": 1.087837837837838,
      "grad_norm": 0.9916661977767944,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.4907,
      "step": 161
    },
    {
      "epoch": 1.0945945945945945,
      "grad_norm": 0.92591392993927,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.38,
      "step": 162
    },
    {
      "epoch": 1.1013513513513513,
      "grad_norm": 1.0461336374282837,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.3842,
      "step": 163
    },
    {
      "epoch": 1.1081081081081081,
      "grad_norm": 0.9681600332260132,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.3824,
      "step": 164
    },
    {
      "epoch": 1.114864864864865,
      "grad_norm": 1.0069831609725952,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.1757,
      "step": 165
    },
    {
      "epoch": 1.1216216216216217,
      "grad_norm": 1.0250517129898071,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.2832,
      "step": 166
    },
    {
      "epoch": 1.1283783783783783,
      "grad_norm": 1.082542896270752,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.3635,
      "step": 167
    },
    {
      "epoch": 1.135135135135135,
      "grad_norm": 1.1224950551986694,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.3682,
      "step": 168
    },
    {
      "epoch": 1.1418918918918919,
      "grad_norm": 1.050126075744629,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.2205,
      "step": 169
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 1.1560009717941284,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.2521,
      "step": 170
    },
    {
      "epoch": 1.1554054054054055,
      "grad_norm": 1.1718311309814453,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.2053,
      "step": 171
    },
    {
      "epoch": 1.1621621621621623,
      "grad_norm": 1.1508018970489502,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.3024,
      "step": 172
    },
    {
      "epoch": 1.1689189189189189,
      "grad_norm": 1.1649116277694702,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.1522,
      "step": 173
    },
    {
      "epoch": 1.1756756756756757,
      "grad_norm": 1.1973979473114014,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.327,
      "step": 174
    },
    {
      "epoch": 1.1824324324324325,
      "grad_norm": 1.3160618543624878,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.3266,
      "step": 175
    },
    {
      "epoch": 1.1891891891891893,
      "grad_norm": 1.2832850217819214,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.1432,
      "step": 176
    },
    {
      "epoch": 1.195945945945946,
      "grad_norm": 1.3258612155914307,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.205,
      "step": 177
    },
    {
      "epoch": 1.2027027027027026,
      "grad_norm": 1.3601106405258179,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.3564,
      "step": 178
    },
    {
      "epoch": 1.2094594594594594,
      "grad_norm": 1.4891834259033203,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.2718,
      "step": 179
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 1.5640510320663452,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.3434,
      "step": 180
    },
    {
      "epoch": 1.222972972972973,
      "grad_norm": 1.5793720483779907,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.3986,
      "step": 181
    },
    {
      "epoch": 1.2297297297297298,
      "grad_norm": 1.6748934984207153,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.2959,
      "step": 182
    },
    {
      "epoch": 1.2364864864864864,
      "grad_norm": 2.135706663131714,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.2804,
      "step": 183
    },
    {
      "epoch": 1.2432432432432432,
      "grad_norm": 2.754852771759033,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.4341,
      "step": 184
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.8117123246192932,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.6149,
      "step": 185
    },
    {
      "epoch": 1.2567567567567568,
      "grad_norm": 0.9120969772338867,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.6406,
      "step": 186
    },
    {
      "epoch": 1.2635135135135136,
      "grad_norm": 0.9482656121253967,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.629,
      "step": 187
    },
    {
      "epoch": 1.2702702702702702,
      "grad_norm": 0.9888730645179749,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.501,
      "step": 188
    },
    {
      "epoch": 1.277027027027027,
      "grad_norm": 0.9671918749809265,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.5323,
      "step": 189
    },
    {
      "epoch": 1.2837837837837838,
      "grad_norm": 0.9644412994384766,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.4768,
      "step": 190
    },
    {
      "epoch": 1.2905405405405406,
      "grad_norm": 1.0121159553527832,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.4677,
      "step": 191
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 1.029511570930481,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.528,
      "step": 192
    },
    {
      "epoch": 1.304054054054054,
      "grad_norm": 0.9636542797088623,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.418,
      "step": 193
    },
    {
      "epoch": 1.3108108108108107,
      "grad_norm": 1.07045578956604,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.4994,
      "step": 194
    },
    {
      "epoch": 1.3175675675675675,
      "grad_norm": 1.074533462524414,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.5014,
      "step": 195
    },
    {
      "epoch": 1.3243243243243243,
      "grad_norm": 1.0579618215560913,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.4661,
      "step": 196
    },
    {
      "epoch": 1.3310810810810811,
      "grad_norm": 1.0530486106872559,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.3151,
      "step": 197
    },
    {
      "epoch": 1.3378378378378377,
      "grad_norm": 1.0989681482315063,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.3949,
      "step": 198
    },
    {
      "epoch": 1.3445945945945945,
      "grad_norm": 1.1458007097244263,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.4455,
      "step": 199
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 1.029989242553711,
      "learning_rate": 0.0,
      "loss": 1.3269,
      "step": 200
    },
    {
      "epoch": 1.3513513513513513,
      "eval_loss": 1.731801986694336,
      "eval_runtime": 19.0592,
      "eval_samples_per_second": 13.117,
      "eval_steps_per_second": 3.305,
      "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
}