{
  "best_metric": 12.397581100463867,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 2.1621621621621623,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010810810810810811,
      "grad_norm": 0.011410352773964405,
      "learning_rate": 1e-05,
      "loss": 12.4555,
      "step": 1
    },
    {
      "epoch": 0.010810810810810811,
      "eval_loss": 12.456661224365234,
      "eval_runtime": 1.1817,
      "eval_samples_per_second": 132.016,
      "eval_steps_per_second": 33.004,
      "step": 1
    },
    {
      "epoch": 0.021621621621621623,
      "grad_norm": 0.0127186831086874,
      "learning_rate": 2e-05,
      "loss": 12.4583,
      "step": 2
    },
    {
      "epoch": 0.032432432432432434,
      "grad_norm": 0.013318352401256561,
      "learning_rate": 3e-05,
      "loss": 12.4565,
      "step": 3
    },
    {
      "epoch": 0.043243243243243246,
      "grad_norm": 0.012860357761383057,
      "learning_rate": 4e-05,
      "loss": 12.4564,
      "step": 4
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 0.014547891914844513,
      "learning_rate": 5e-05,
      "loss": 12.4551,
      "step": 5
    },
    {
      "epoch": 0.06486486486486487,
      "grad_norm": 0.013768386095762253,
      "learning_rate": 6e-05,
      "loss": 12.456,
      "step": 6
    },
    {
      "epoch": 0.07567567567567568,
      "grad_norm": 0.013836418278515339,
      "learning_rate": 7e-05,
      "loss": 12.4583,
      "step": 7
    },
    {
      "epoch": 0.08648648648648649,
      "grad_norm": 0.014699624851346016,
      "learning_rate": 8e-05,
      "loss": 12.4584,
      "step": 8
    },
    {
      "epoch": 0.0972972972972973,
      "grad_norm": 0.013957439921796322,
      "learning_rate": 9e-05,
      "loss": 12.458,
      "step": 9
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.017159353941679,
      "learning_rate": 0.0001,
      "loss": 12.459,
      "step": 10
    },
    {
      "epoch": 0.11891891891891893,
      "grad_norm": 0.015626920387148857,
      "learning_rate": 9.999316524962345e-05,
      "loss": 12.4565,
      "step": 11
    },
    {
      "epoch": 0.12972972972972974,
      "grad_norm": 0.01788908801972866,
      "learning_rate": 9.997266286704631e-05,
      "loss": 12.4564,
      "step": 12
    },
    {
      "epoch": 0.14054054054054055,
      "grad_norm": 0.019801383838057518,
      "learning_rate": 9.993849845741524e-05,
      "loss": 12.4581,
      "step": 13
    },
    {
      "epoch": 0.15135135135135136,
      "grad_norm": 0.01969742216169834,
      "learning_rate": 9.989068136093873e-05,
      "loss": 12.4592,
      "step": 14
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 0.02021048218011856,
      "learning_rate": 9.98292246503335e-05,
      "loss": 12.4574,
      "step": 15
    },
    {
      "epoch": 0.17297297297297298,
      "grad_norm": 0.02216586470603943,
      "learning_rate": 9.975414512725057e-05,
      "loss": 12.4531,
      "step": 16
    },
    {
      "epoch": 0.1837837837837838,
      "grad_norm": 0.02436438389122486,
      "learning_rate": 9.966546331768191e-05,
      "loss": 12.4536,
      "step": 17
    },
    {
      "epoch": 0.1945945945945946,
      "grad_norm": 0.029499387368559837,
      "learning_rate": 9.956320346634876e-05,
      "loss": 12.4531,
      "step": 18
    },
    {
      "epoch": 0.20540540540540542,
      "grad_norm": 0.026935743167996407,
      "learning_rate": 9.944739353007344e-05,
      "loss": 12.4585,
      "step": 19
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.03182888403534889,
      "learning_rate": 9.931806517013612e-05,
      "loss": 12.4548,
      "step": 20
    },
    {
      "epoch": 0.22702702702702704,
      "grad_norm": 0.030906682834029198,
      "learning_rate": 9.917525374361912e-05,
      "loss": 12.4548,
      "step": 21
    },
    {
      "epoch": 0.23783783783783785,
      "grad_norm": 0.029409030452370644,
      "learning_rate": 9.901899829374047e-05,
      "loss": 12.4559,
      "step": 22
    },
    {
      "epoch": 0.24864864864864866,
      "grad_norm": 0.030133800581097603,
      "learning_rate": 9.884934153917997e-05,
      "loss": 12.45,
      "step": 23
    },
    {
      "epoch": 0.2594594594594595,
      "grad_norm": 0.027129922062158585,
      "learning_rate": 9.86663298624003e-05,
      "loss": 12.4562,
      "step": 24
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 0.027564454823732376,
      "learning_rate": 9.847001329696653e-05,
      "loss": 12.4576,
      "step": 25
    },
    {
      "epoch": 0.2810810810810811,
      "grad_norm": 0.03618146851658821,
      "learning_rate": 9.826044551386744e-05,
      "loss": 12.4569,
      "step": 26
    },
    {
      "epoch": 0.2918918918918919,
      "grad_norm": 0.03172038495540619,
      "learning_rate": 9.803768380684242e-05,
      "loss": 12.4549,
      "step": 27
    },
    {
      "epoch": 0.3027027027027027,
      "grad_norm": 0.03866088390350342,
      "learning_rate": 9.780178907671789e-05,
      "loss": 12.4563,
      "step": 28
    },
    {
      "epoch": 0.31351351351351353,
      "grad_norm": 0.03798335790634155,
      "learning_rate": 9.755282581475769e-05,
      "loss": 12.4561,
      "step": 29
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 0.04091477021574974,
      "learning_rate": 9.729086208503174e-05,
      "loss": 12.4559,
      "step": 30
    },
    {
      "epoch": 0.33513513513513515,
      "grad_norm": 0.04230833426117897,
      "learning_rate": 9.701596950580806e-05,
      "loss": 12.4552,
      "step": 31
    },
    {
      "epoch": 0.34594594594594597,
      "grad_norm": 0.03847480192780495,
      "learning_rate": 9.672822322997305e-05,
      "loss": 12.4574,
      "step": 32
    },
    {
      "epoch": 0.3567567567567568,
      "grad_norm": 0.04986431077122688,
      "learning_rate": 9.642770192448536e-05,
      "loss": 12.4561,
      "step": 33
    },
    {
      "epoch": 0.3675675675675676,
      "grad_norm": 0.05425199493765831,
      "learning_rate": 9.611448774886924e-05,
      "loss": 12.4554,
      "step": 34
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 0.05048635974526405,
      "learning_rate": 9.578866633275288e-05,
      "loss": 12.4563,
      "step": 35
    },
    {
      "epoch": 0.3891891891891892,
      "grad_norm": 0.05176055431365967,
      "learning_rate": 9.545032675245813e-05,
      "loss": 12.4541,
      "step": 36
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.05784906819462776,
      "learning_rate": 9.509956150664796e-05,
      "loss": 12.454,
      "step": 37
    },
    {
      "epoch": 0.41081081081081083,
      "grad_norm": 0.056869521737098694,
      "learning_rate": 9.473646649103818e-05,
      "loss": 12.4548,
      "step": 38
    },
    {
      "epoch": 0.42162162162162165,
      "grad_norm": 0.06188880279660225,
      "learning_rate": 9.43611409721806e-05,
      "loss": 12.4512,
      "step": 39
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.0658450499176979,
      "learning_rate": 9.397368756032445e-05,
      "loss": 12.4522,
      "step": 40
    },
    {
      "epoch": 0.44324324324324327,
      "grad_norm": 0.06984926015138626,
      "learning_rate": 9.357421218136386e-05,
      "loss": 12.45,
      "step": 41
    },
    {
      "epoch": 0.4540540540540541,
      "grad_norm": 0.08171503245830536,
      "learning_rate": 9.316282404787871e-05,
      "loss": 12.4489,
      "step": 42
    },
    {
      "epoch": 0.4648648648648649,
      "grad_norm": 0.06859689205884933,
      "learning_rate": 9.273963562927695e-05,
      "loss": 12.4539,
      "step": 43
    },
    {
      "epoch": 0.4756756756756757,
      "grad_norm": 0.08337778598070145,
      "learning_rate": 9.230476262104677e-05,
      "loss": 12.4529,
      "step": 44
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 0.0855226144194603,
      "learning_rate": 9.185832391312644e-05,
      "loss": 12.45,
      "step": 45
    },
    {
      "epoch": 0.4972972972972973,
      "grad_norm": 0.08600504696369171,
      "learning_rate": 9.140044155740101e-05,
      "loss": 12.4498,
      "step": 46
    },
    {
      "epoch": 0.5081081081081081,
      "grad_norm": 0.06074056774377823,
      "learning_rate": 9.093124073433463e-05,
      "loss": 12.4511,
      "step": 47
    },
    {
      "epoch": 0.518918918918919,
      "grad_norm": 0.07113663852214813,
      "learning_rate": 9.045084971874738e-05,
      "loss": 12.4503,
      "step": 48
    },
    {
      "epoch": 0.5297297297297298,
      "grad_norm": 0.08515233546495438,
      "learning_rate": 8.995939984474624e-05,
      "loss": 12.4483,
      "step": 49
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.08048766106367111,
      "learning_rate": 8.945702546981969e-05,
      "loss": 12.4493,
      "step": 50
    },
    {
      "epoch": 0.5405405405405406,
      "eval_loss": 12.448390007019043,
      "eval_runtime": 1.1848,
      "eval_samples_per_second": 131.667,
      "eval_steps_per_second": 32.917,
      "step": 50
    },
    {
      "epoch": 0.5513513513513514,
      "grad_norm": 0.08097800612449646,
      "learning_rate": 8.894386393810563e-05,
      "loss": 12.451,
      "step": 51
    },
    {
      "epoch": 0.5621621621621622,
      "grad_norm": 0.08834439516067505,
      "learning_rate": 8.842005554284296e-05,
      "loss": 12.4503,
      "step": 52
    },
    {
      "epoch": 0.572972972972973,
      "grad_norm": 0.10415896773338318,
      "learning_rate": 8.788574348801675e-05,
      "loss": 12.4474,
      "step": 53
    },
    {
      "epoch": 0.5837837837837838,
      "grad_norm": 0.08738260716199875,
      "learning_rate": 8.73410738492077e-05,
      "loss": 12.448,
      "step": 54
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 0.10076502710580826,
      "learning_rate": 8.678619553365659e-05,
      "loss": 12.4481,
      "step": 55
    },
    {
      "epoch": 0.6054054054054054,
      "grad_norm": 0.10652615875005722,
      "learning_rate": 8.622126023955446e-05,
      "loss": 12.447,
      "step": 56
    },
    {
      "epoch": 0.6162162162162163,
      "grad_norm": 0.10304449498653412,
      "learning_rate": 8.564642241456986e-05,
      "loss": 12.4481,
      "step": 57
    },
    {
      "epoch": 0.6270270270270271,
      "grad_norm": 0.11053697019815445,
      "learning_rate": 8.506183921362443e-05,
      "loss": 12.4467,
      "step": 58
    },
    {
      "epoch": 0.6378378378378379,
      "grad_norm": 0.12599627673625946,
      "learning_rate": 8.44676704559283e-05,
      "loss": 12.4418,
      "step": 59
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.11627623438835144,
      "learning_rate": 8.386407858128706e-05,
      "loss": 12.4446,
      "step": 60
    },
    {
      "epoch": 0.6594594594594595,
      "grad_norm": 0.12287788093090057,
      "learning_rate": 8.32512286056924e-05,
      "loss": 12.4425,
      "step": 61
    },
    {
      "epoch": 0.6702702702702703,
      "grad_norm": 0.12733852863311768,
      "learning_rate": 8.262928807620843e-05,
      "loss": 12.4423,
      "step": 62
    },
    {
      "epoch": 0.6810810810810811,
      "grad_norm": 0.13020053505897522,
      "learning_rate": 8.199842702516583e-05,
      "loss": 12.4417,
      "step": 63
    },
    {
      "epoch": 0.6918918918918919,
      "grad_norm": 0.12520404160022736,
      "learning_rate": 8.135881792367686e-05,
      "loss": 12.4376,
      "step": 64
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 0.120334692299366,
      "learning_rate": 8.07106356344834e-05,
      "loss": 12.4385,
      "step": 65
    },
    {
      "epoch": 0.7135135135135136,
      "grad_norm": 0.1278742104768753,
      "learning_rate": 8.005405736415126e-05,
      "loss": 12.4386,
      "step": 66
    },
    {
      "epoch": 0.7243243243243244,
      "grad_norm": 0.13986234366893768,
      "learning_rate": 7.938926261462366e-05,
      "loss": 12.4399,
      "step": 67
    },
    {
      "epoch": 0.7351351351351352,
      "grad_norm": 0.14203161001205444,
      "learning_rate": 7.871643313414718e-05,
      "loss": 12.4347,
      "step": 68
    },
    {
      "epoch": 0.745945945945946,
      "grad_norm": 0.12454916536808014,
      "learning_rate": 7.803575286758364e-05,
      "loss": 12.4359,
      "step": 69
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 0.11711882054805756,
      "learning_rate": 7.734740790612136e-05,
      "loss": 12.4398,
      "step": 70
    },
    {
      "epoch": 0.7675675675675676,
      "grad_norm": 0.11687122285366058,
      "learning_rate": 7.66515864363997e-05,
      "loss": 12.4435,
      "step": 71
    },
    {
      "epoch": 0.7783783783783784,
      "grad_norm": 0.13044419884681702,
      "learning_rate": 7.594847868906076e-05,
      "loss": 12.439,
      "step": 72
    },
    {
      "epoch": 0.7891891891891892,
      "grad_norm": 0.14645253121852875,
      "learning_rate": 7.52382768867422e-05,
      "loss": 12.4353,
      "step": 73
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.14442750811576843,
      "learning_rate": 7.452117519152542e-05,
      "loss": 12.4345,
      "step": 74
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 0.1307346671819687,
      "learning_rate": 7.379736965185368e-05,
      "loss": 12.4377,
      "step": 75
    },
    {
      "epoch": 0.8216216216216217,
      "grad_norm": 0.14447931945323944,
      "learning_rate": 7.30670581489344e-05,
      "loss": 12.4353,
      "step": 76
    },
    {
      "epoch": 0.8324324324324325,
      "grad_norm": 0.13398462533950806,
      "learning_rate": 7.233044034264034e-05,
      "loss": 12.4369,
      "step": 77
    },
    {
      "epoch": 0.8432432432432433,
      "grad_norm": 0.15480872988700867,
      "learning_rate": 7.158771761692464e-05,
      "loss": 12.4304,
      "step": 78
    },
    {
      "epoch": 0.8540540540540541,
      "grad_norm": 0.13609907031059265,
      "learning_rate": 7.083909302476453e-05,
      "loss": 12.4355,
      "step": 79
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.14836253225803375,
      "learning_rate": 7.008477123264848e-05,
      "loss": 12.4319,
      "step": 80
    },
    {
      "epoch": 0.8756756756756757,
      "grad_norm": 0.14326833188533783,
      "learning_rate": 6.932495846462261e-05,
      "loss": 12.4302,
      "step": 81
    },
    {
      "epoch": 0.8864864864864865,
      "grad_norm": 0.15603004395961761,
      "learning_rate": 6.855986244591104e-05,
      "loss": 12.4311,
      "step": 82
    },
    {
      "epoch": 0.8972972972972973,
      "grad_norm": 0.15438219904899597,
      "learning_rate": 6.778969234612584e-05,
      "loss": 12.4318,
      "step": 83
    },
    {
      "epoch": 0.9081081081081082,
      "grad_norm": 0.16214002668857574,
      "learning_rate": 6.701465872208216e-05,
      "loss": 12.4257,
      "step": 84
    },
    {
      "epoch": 0.918918918918919,
      "grad_norm": 0.1482042819261551,
      "learning_rate": 6.623497346023418e-05,
      "loss": 12.4299,
      "step": 85
    },
    {
      "epoch": 0.9297297297297298,
      "grad_norm": 0.15572600066661835,
      "learning_rate": 6.545084971874738e-05,
      "loss": 12.4237,
      "step": 86
    },
    {
      "epoch": 0.9405405405405406,
      "grad_norm": 0.16485613584518433,
      "learning_rate": 6.466250186922325e-05,
      "loss": 12.4218,
      "step": 87
    },
    {
      "epoch": 0.9513513513513514,
      "grad_norm": 0.17954082787036896,
      "learning_rate": 6.387014543809223e-05,
      "loss": 12.4207,
      "step": 88
    },
    {
      "epoch": 0.9621621621621622,
      "grad_norm": 0.16537728905677795,
      "learning_rate": 6.307399704769099e-05,
      "loss": 12.4168,
      "step": 89
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 0.16587455570697784,
      "learning_rate": 6.227427435703997e-05,
      "loss": 12.4243,
      "step": 90
    },
    {
      "epoch": 0.9837837837837838,
      "grad_norm": 0.16844815015792847,
      "learning_rate": 6.147119600233758e-05,
      "loss": 12.4186,
      "step": 91
    },
    {
      "epoch": 0.9945945945945946,
      "grad_norm": 0.14412705600261688,
      "learning_rate": 6.066498153718735e-05,
      "loss": 12.4269,
      "step": 92
    },
    {
      "epoch": 1.0054054054054054,
      "grad_norm": 0.2297983467578888,
      "learning_rate": 5.985585137257401e-05,
      "loss": 19.2004,
      "step": 93
    },
    {
      "epoch": 1.0162162162162163,
      "grad_norm": 0.15252849459648132,
      "learning_rate": 5.90440267166055e-05,
      "loss": 12.27,
      "step": 94
    },
    {
      "epoch": 1.027027027027027,
      "grad_norm": 0.1588127166032791,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 12.4543,
      "step": 95
    },
    {
      "epoch": 1.037837837837838,
      "grad_norm": 0.1570507287979126,
      "learning_rate": 5.74131823855921e-05,
      "loss": 12.0112,
      "step": 96
    },
    {
      "epoch": 1.0486486486486486,
      "grad_norm": 0.15935370326042175,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 12.5718,
      "step": 97
    },
    {
      "epoch": 1.0594594594594595,
      "grad_norm": 0.14587226510047913,
      "learning_rate": 5.577423184847932e-05,
      "loss": 12.1423,
      "step": 98
    },
    {
      "epoch": 1.0702702702702702,
      "grad_norm": 0.15620863437652588,
      "learning_rate": 5.495227651252315e-05,
      "loss": 12.572,
      "step": 99
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.16118139028549194,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 12.526,
      "step": 100
    },
    {
      "epoch": 1.0810810810810811,
      "eval_loss": 12.416610717773438,
      "eval_runtime": 1.1894,
      "eval_samples_per_second": 131.154,
      "eval_steps_per_second": 32.789,
      "step": 100
    },
    {
      "epoch": 1.0918918918918918,
      "grad_norm": 0.16899381577968597,
      "learning_rate": 5.330452921628497e-05,
      "loss": 12.2351,
      "step": 101
    },
    {
      "epoch": 1.1027027027027028,
      "grad_norm": 0.1550283432006836,
      "learning_rate": 5.247918773366112e-05,
      "loss": 12.5192,
      "step": 102
    },
    {
      "epoch": 1.1135135135135135,
      "grad_norm": 0.15760944783687592,
      "learning_rate": 5.165316846586541e-05,
      "loss": 12.4065,
      "step": 103
    },
    {
      "epoch": 1.1243243243243244,
      "grad_norm": 0.16366960108280182,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 12.4329,
      "step": 104
    },
    {
      "epoch": 1.135135135135135,
      "grad_norm": 0.15075188875198364,
      "learning_rate": 5e-05,
      "loss": 12.2649,
      "step": 105
    },
    {
      "epoch": 1.145945945945946,
      "grad_norm": 0.16289706528186798,
      "learning_rate": 4.917330276168208e-05,
      "loss": 12.6488,
      "step": 106
    },
    {
      "epoch": 1.1567567567567567,
      "grad_norm": 0.1553780734539032,
      "learning_rate": 4.834683153413459e-05,
      "loss": 12.4061,
      "step": 107
    },
    {
      "epoch": 1.1675675675675676,
      "grad_norm": 0.15287522971630096,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 12.315,
      "step": 108
    },
    {
      "epoch": 1.1783783783783783,
      "grad_norm": 0.15912698209285736,
      "learning_rate": 4.669547078371504e-05,
      "loss": 12.3281,
      "step": 109
    },
    {
      "epoch": 1.1891891891891893,
      "grad_norm": 0.16240181028842926,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 12.379,
      "step": 110
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.16783976554870605,
      "learning_rate": 4.504772348747687e-05,
      "loss": 12.5496,
      "step": 111
    },
    {
      "epoch": 1.2108108108108109,
      "grad_norm": 0.18104086816310883,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 12.4819,
      "step": 112
    },
    {
      "epoch": 1.2216216216216216,
      "grad_norm": 0.1588224470615387,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 12.5298,
      "step": 113
    },
    {
      "epoch": 1.2324324324324325,
      "grad_norm": 0.16586121916770935,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 12.6781,
      "step": 114
    },
    {
      "epoch": 1.2432432432432432,
      "grad_norm": 0.17710217833518982,
      "learning_rate": 4.17702704859633e-05,
      "loss": 13.3042,
      "step": 115
    },
    {
      "epoch": 1.2540540540540541,
      "grad_norm": 0.13910342752933502,
      "learning_rate": 4.095597328339452e-05,
      "loss": 11.1646,
      "step": 116
    },
    {
      "epoch": 1.2648648648648648,
      "grad_norm": 0.15712970495224,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 12.5142,
      "step": 117
    },
    {
      "epoch": 1.2756756756756757,
      "grad_norm": 0.15199324488639832,
      "learning_rate": 3.933501846281267e-05,
      "loss": 12.1472,
      "step": 118
    },
    {
      "epoch": 1.2864864864864864,
      "grad_norm": 0.15523052215576172,
      "learning_rate": 3.852880399766243e-05,
      "loss": 12.5112,
      "step": 119
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 0.1529281884431839,
      "learning_rate": 3.772572564296005e-05,
      "loss": 12.3212,
      "step": 120
    },
    {
      "epoch": 1.308108108108108,
      "grad_norm": 0.15450085699558258,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 12.4326,
      "step": 121
    },
    {
      "epoch": 1.318918918918919,
      "grad_norm": 0.14709068834781647,
      "learning_rate": 3.612985456190778e-05,
      "loss": 12.3935,
      "step": 122
    },
    {
      "epoch": 1.3297297297297297,
      "grad_norm": 0.16221345961093903,
      "learning_rate": 3.533749813077677e-05,
      "loss": 12.3008,
      "step": 123
    },
    {
      "epoch": 1.3405405405405406,
      "grad_norm": 0.1565379649400711,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 12.4509,
      "step": 124
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 0.1541808545589447,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 12.5938,
      "step": 125
    },
    {
      "epoch": 1.3621621621621622,
      "grad_norm": 0.15661218762397766,
      "learning_rate": 3.298534127791785e-05,
      "loss": 12.3216,
      "step": 126
    },
    {
      "epoch": 1.372972972972973,
      "grad_norm": 0.15609484910964966,
      "learning_rate": 3.221030765387417e-05,
      "loss": 12.4369,
      "step": 127
    },
    {
      "epoch": 1.3837837837837839,
      "grad_norm": 0.13928954303264618,
      "learning_rate": 3.144013755408895e-05,
      "loss": 12.3067,
      "step": 128
    },
    {
      "epoch": 1.3945945945945946,
      "grad_norm": 0.15151768922805786,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 12.246,
      "step": 129
    },
    {
      "epoch": 1.4054054054054055,
      "grad_norm": 0.1370520293712616,
      "learning_rate": 2.991522876735154e-05,
      "loss": 12.6144,
      "step": 130
    },
    {
      "epoch": 1.4162162162162162,
      "grad_norm": 0.14478237926959991,
      "learning_rate": 2.916090697523549e-05,
      "loss": 12.3879,
      "step": 131
    },
    {
      "epoch": 1.427027027027027,
      "grad_norm": 0.1462717354297638,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 12.5031,
      "step": 132
    },
    {
      "epoch": 1.4378378378378378,
      "grad_norm": 0.1453448235988617,
      "learning_rate": 2.766955965735968e-05,
      "loss": 12.195,
      "step": 133
    },
    {
      "epoch": 1.4486486486486487,
      "grad_norm": 0.13649863004684448,
      "learning_rate": 2.693294185106562e-05,
      "loss": 12.2595,
      "step": 134
    },
    {
      "epoch": 1.4594594594594594,
      "grad_norm": 0.14277991652488708,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 12.753,
      "step": 135
    },
    {
      "epoch": 1.4702702702702704,
      "grad_norm": 0.1390213519334793,
      "learning_rate": 2.547882480847461e-05,
      "loss": 12.1753,
      "step": 136
    },
    {
      "epoch": 1.481081081081081,
      "grad_norm": 0.1433957815170288,
      "learning_rate": 2.476172311325783e-05,
      "loss": 12.6571,
      "step": 137
    },
    {
      "epoch": 1.491891891891892,
      "grad_norm": 0.1736254096031189,
      "learning_rate": 2.405152131093926e-05,
      "loss": 13.6777,
      "step": 138
    },
    {
      "epoch": 1.5027027027027027,
      "grad_norm": 0.13041651248931885,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 11.1024,
      "step": 139
    },
    {
      "epoch": 1.5135135135135136,
      "grad_norm": 0.15117383003234863,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 12.5951,
      "step": 140
    },
    {
      "epoch": 1.5243243243243243,
      "grad_norm": 0.13394992053508759,
      "learning_rate": 2.196424713241637e-05,
      "loss": 12.2069,
      "step": 141
    },
    {
      "epoch": 1.535135135135135,
      "grad_norm": 0.13596802949905396,
      "learning_rate": 2.128356686585282e-05,
      "loss": 12.2357,
      "step": 142
    },
    {
      "epoch": 1.545945945945946,
      "grad_norm": 0.14062215387821198,
      "learning_rate": 2.061073738537635e-05,
      "loss": 12.3386,
      "step": 143
    },
    {
      "epoch": 1.5567567567567568,
      "grad_norm": 0.13152442872524261,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 12.44,
      "step": 144
    },
    {
      "epoch": 1.5675675675675675,
      "grad_norm": 0.1441609114408493,
      "learning_rate": 1.928936436551661e-05,
      "loss": 12.4983,
      "step": 145
    },
    {
      "epoch": 1.5783783783783782,
      "grad_norm": 0.13354404270648956,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 12.2525,
      "step": 146
    },
    {
      "epoch": 1.5891891891891892,
      "grad_norm": 0.13479739427566528,
      "learning_rate": 1.800157297483417e-05,
      "loss": 12.4118,
      "step": 147
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.13881456851959229,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 12.7056,
      "step": 148
    },
    {
      "epoch": 1.6108108108108108,
      "grad_norm": 0.11934009939432144,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 11.9915,
      "step": 149
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 0.12421932816505432,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 12.4338,
      "step": 150
    },
    {
      "epoch": 1.6216216216216215,
      "eval_loss": 12.399171829223633,
      "eval_runtime": 1.2032,
      "eval_samples_per_second": 129.654,
      "eval_steps_per_second": 32.414,
      "step": 150
    },
    {
      "epoch": 1.6324324324324324,
      "grad_norm": 0.13919909298419952,
      "learning_rate": 1.553232954407171e-05,
      "loss": 12.5867,
      "step": 151
    },
    {
      "epoch": 1.6432432432432433,
      "grad_norm": 0.12235915660858154,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 12.2461,
      "step": 152
    },
    {
      "epoch": 1.654054054054054,
      "grad_norm": 0.13523922860622406,
      "learning_rate": 1.435357758543015e-05,
      "loss": 12.6054,
      "step": 153
    },
    {
      "epoch": 1.6648648648648647,
      "grad_norm": 0.12796221673488617,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 12.4349,
      "step": 154
    },
    {
      "epoch": 1.6756756756756757,
      "grad_norm": 0.12376177310943604,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 12.4648,
      "step": 155
    },
    {
      "epoch": 1.6864864864864866,
      "grad_norm": 0.11597909778356552,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 12.3233,
      "step": 156
    },
    {
      "epoch": 1.6972972972972973,
      "grad_norm": 0.12139812111854553,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 12.315,
      "step": 157
    },
    {
      "epoch": 1.708108108108108,
      "grad_norm": 0.1198643296957016,
      "learning_rate": 1.157994445715706e-05,
      "loss": 12.4021,
      "step": 158
    },
    {
      "epoch": 1.718918918918919,
      "grad_norm": 0.11841056495904922,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 12.238,
      "step": 159
    },
    {
      "epoch": 1.7297297297297298,
      "grad_norm": 0.13044923543930054,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 12.5955,
      "step": 160
    },
    {
      "epoch": 1.7405405405405405,
      "grad_norm": 0.11754146963357925,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 13.871,
      "step": 161
    },
    {
      "epoch": 1.7513513513513512,
      "grad_norm": 0.11048613488674164,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.9149,
      "step": 162
    },
    {
      "epoch": 1.7621621621621621,
      "grad_norm": 0.12779003381729126,
      "learning_rate": 9.068759265665384e-06,
      "loss": 12.3881,
      "step": 163
    },
    {
      "epoch": 1.772972972972973,
      "grad_norm": 0.12158031016588211,
      "learning_rate": 8.599558442598998e-06,
      "loss": 12.2095,
      "step": 164
    },
    {
      "epoch": 1.7837837837837838,
      "grad_norm": 0.1225953996181488,
      "learning_rate": 8.141676086873572e-06,
      "loss": 12.602,
      "step": 165
    },
    {
      "epoch": 1.7945945945945945,
      "grad_norm": 0.1197371855378151,
      "learning_rate": 7.695237378953223e-06,
      "loss": 12.3767,
      "step": 166
    },
    {
      "epoch": 1.8054054054054054,
      "grad_norm": 0.11833854764699936,
      "learning_rate": 7.260364370723044e-06,
      "loss": 12.1618,
      "step": 167
    },
    {
      "epoch": 1.8162162162162163,
      "grad_norm": 0.11639880388975143,
      "learning_rate": 6.837175952121306e-06,
      "loss": 12.5333,
      "step": 168
    },
    {
      "epoch": 1.827027027027027,
      "grad_norm": 0.1150984838604927,
      "learning_rate": 6.425787818636131e-06,
      "loss": 12.3282,
      "step": 169
    },
    {
      "epoch": 1.8378378378378377,
      "grad_norm": 0.11583307385444641,
      "learning_rate": 6.026312439675552e-06,
      "loss": 12.4116,
      "step": 170
    },
    {
      "epoch": 1.8486486486486486,
      "grad_norm": 0.12116102129220963,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 12.2405,
      "step": 171
    },
    {
      "epoch": 1.8594594594594596,
      "grad_norm": 0.11664839088916779,
      "learning_rate": 5.263533508961827e-06,
      "loss": 12.5526,
      "step": 172
    },
    {
      "epoch": 1.8702702702702703,
      "grad_norm": 0.11866392940282822,
      "learning_rate": 4.900438493352055e-06,
      "loss": 12.331,
      "step": 173
    },
    {
      "epoch": 1.881081081081081,
      "grad_norm": 0.11440639942884445,
      "learning_rate": 4.549673247541875e-06,
      "loss": 12.4863,
      "step": 174
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 0.11529631167650223,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 12.3776,
      "step": 175
    },
    {
      "epoch": 1.9027027027027028,
      "grad_norm": 0.1338910609483719,
      "learning_rate": 3.885512251130763e-06,
      "loss": 12.8782,
      "step": 176
    },
    {
      "epoch": 1.9135135135135135,
      "grad_norm": 0.10222285240888596,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 12.0436,
      "step": 177
    },
    {
      "epoch": 1.9243243243243242,
      "grad_norm": 0.11875727027654648,
      "learning_rate": 3.271776770026963e-06,
      "loss": 12.5464,
      "step": 178
    },
    {
      "epoch": 1.9351351351351351,
      "grad_norm": 0.10068827867507935,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 12.3293,
      "step": 179
    },
    {
      "epoch": 1.945945945945946,
      "grad_norm": 0.09821882843971252,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 12.3627,
      "step": 180
    },
    {
      "epoch": 1.9567567567567568,
      "grad_norm": 0.09903934597969055,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 12.3272,
      "step": 181
    },
    {
      "epoch": 1.9675675675675675,
      "grad_norm": 0.11194190382957458,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 12.5977,
      "step": 182
    },
    {
      "epoch": 1.9783783783783784,
      "grad_norm": 0.11247821152210236,
      "learning_rate": 1.962316193157593e-06,
      "loss": 12.5913,
      "step": 183
    },
    {
      "epoch": 1.9891891891891893,
      "grad_norm": 0.1526566594839096,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 13.5784,
      "step": 184
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.19195906817913055,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 16.9369,
      "step": 185
    },
    {
      "epoch": 2.0108108108108107,
      "grad_norm": 0.10987367480993271,
      "learning_rate": 1.333670137599713e-06,
      "loss": 12.4035,
      "step": 186
    },
    {
      "epoch": 2.0216216216216214,
      "grad_norm": 0.12922699749469757,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 12.4017,
      "step": 187
    },
    {
      "epoch": 2.0324324324324325,
      "grad_norm": 0.11122409254312515,
      "learning_rate": 9.810017062595322e-07,
      "loss": 12.3968,
      "step": 188
    },
    {
      "epoch": 2.0432432432432432,
      "grad_norm": 0.11720285564661026,
      "learning_rate": 8.247462563808817e-07,
      "loss": 12.399,
      "step": 189
    },
    {
      "epoch": 2.054054054054054,
      "grad_norm": 0.11604964733123779,
      "learning_rate": 6.819348298638839e-07,
      "loss": 12.3972,
      "step": 190
    },
    {
      "epoch": 2.064864864864865,
      "grad_norm": 0.11731291562318802,
      "learning_rate": 5.526064699265753e-07,
      "loss": 12.3972,
      "step": 191
    },
    {
      "epoch": 2.075675675675676,
      "grad_norm": 0.11097109317779541,
      "learning_rate": 4.367965336512403e-07,
      "loss": 12.3984,
      "step": 192
    },
    {
      "epoch": 2.0864864864864865,
      "grad_norm": 0.12843982875347137,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 12.3999,
      "step": 193
    },
    {
      "epoch": 2.097297297297297,
      "grad_norm": 0.12849590182304382,
      "learning_rate": 2.458548727494292e-07,
      "loss": 12.3988,
      "step": 194
    },
    {
      "epoch": 2.108108108108108,
      "grad_norm": 0.12087294459342957,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 12.3994,
      "step": 195
    },
    {
      "epoch": 2.118918918918919,
      "grad_norm": 0.11092659831047058,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 12.3964,
      "step": 196
    },
    {
      "epoch": 2.1297297297297297,
      "grad_norm": 0.11395292729139328,
      "learning_rate": 6.150154258476315e-08,
      "loss": 12.3938,
      "step": 197
    },
    {
      "epoch": 2.1405405405405404,
      "grad_norm": 0.11920268833637238,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 12.3955,
      "step": 198
    },
    {
      "epoch": 2.1513513513513516,
      "grad_norm": 0.12856729328632355,
      "learning_rate": 6.834750376549792e-09,
      "loss": 12.4,
      "step": 199
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 0.10635647922754288,
      "learning_rate": 0.0,
      "loss": 12.3946,
      "step": 200
    },
    {
      "epoch": 2.1621621621621623,
      "eval_loss": 12.397581100463867,
      "eval_runtime": 1.1996,
      "eval_samples_per_second": 130.041,
      "eval_steps_per_second": 32.51,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 778804789248.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}