{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9979879275653923,
  "eval_steps": 500,
  "global_step": 248,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 25.44632132209837,
      "learning_rate": 2.5e-06,
      "loss": 1.3648,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 26.82614372299625,
      "learning_rate": 5e-06,
      "loss": 1.3942,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 13.9715403592573,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.1252,
      "step": 3
    },
    {
      "epoch": 0.02,
      "grad_norm": 15.286834533293131,
      "learning_rate": 1e-05,
      "loss": 1.0818,
      "step": 4
    },
    {
      "epoch": 0.02,
      "grad_norm": 14.471396755749431,
      "learning_rate": 1.25e-05,
      "loss": 1.1813,
      "step": 5
    },
    {
      "epoch": 0.02,
      "grad_norm": 12.237430405223677,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.1299,
      "step": 6
    },
    {
      "epoch": 0.03,
      "grad_norm": 6.9798621851072555,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 1.0423,
      "step": 7
    },
    {
      "epoch": 0.03,
      "grad_norm": 7.627011952933091,
      "learning_rate": 2e-05,
      "loss": 1.0391,
      "step": 8
    },
    {
      "epoch": 0.04,
      "grad_norm": 6.338193690447886,
      "learning_rate": 1.999914327574007e-05,
      "loss": 1.0047,
      "step": 9
    },
    {
      "epoch": 0.04,
      "grad_norm": 6.475097294635981,
      "learning_rate": 1.9996573249755573e-05,
      "loss": 1.005,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 5.531252376135597,
      "learning_rate": 1.9992290362407232e-05,
      "loss": 0.9707,
      "step": 11
    },
    {
      "epoch": 0.05,
      "grad_norm": 5.317214783421387,
      "learning_rate": 1.9986295347545738e-05,
      "loss": 0.9753,
      "step": 12
    },
    {
      "epoch": 0.05,
      "grad_norm": 5.640147587545481,
      "learning_rate": 1.9978589232386036e-05,
      "loss": 0.9624,
      "step": 13
    },
    {
      "epoch": 0.06,
      "grad_norm": 5.126066528619183,
      "learning_rate": 1.9969173337331283e-05,
      "loss": 0.9512,
      "step": 14
    },
    {
      "epoch": 0.06,
      "grad_norm": 4.850786120717325,
      "learning_rate": 1.9958049275746617e-05,
      "loss": 0.8941,
      "step": 15
    },
    {
      "epoch": 0.06,
      "grad_norm": 4.8304718970780325,
      "learning_rate": 1.9945218953682736e-05,
      "loss": 0.9285,
      "step": 16
    },
    {
      "epoch": 0.07,
      "grad_norm": 5.125832227875177,
      "learning_rate": 1.9930684569549265e-05,
      "loss": 0.9549,
      "step": 17
    },
    {
      "epoch": 0.07,
      "grad_norm": 4.543222096297247,
      "learning_rate": 1.9914448613738107e-05,
      "loss": 0.875,
      "step": 18
    },
    {
      "epoch": 0.08,
      "grad_norm": 4.866406355068015,
      "learning_rate": 1.9896513868196706e-05,
      "loss": 0.887,
      "step": 19
    },
    {
      "epoch": 0.08,
      "grad_norm": 4.40294926385364,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.8993,
      "step": 20
    },
    {
      "epoch": 0.08,
      "grad_norm": 4.2001601720505235,
      "learning_rate": 1.985556059058078e-05,
      "loss": 0.8272,
      "step": 21
    },
    {
      "epoch": 0.09,
      "grad_norm": 4.187650647600877,
      "learning_rate": 1.983254907563955e-05,
      "loss": 0.9189,
      "step": 22
    },
    {
      "epoch": 0.09,
      "grad_norm": 4.140973612741013,
      "learning_rate": 1.9807852804032306e-05,
      "loss": 0.8639,
      "step": 23
    },
    {
      "epoch": 0.1,
      "grad_norm": 4.415440527647099,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 0.8491,
      "step": 24
    },
    {
      "epoch": 0.1,
      "grad_norm": 4.289016374139926,
      "learning_rate": 1.9753423205085127e-05,
      "loss": 0.8367,
      "step": 25
    },
    {
      "epoch": 0.1,
      "grad_norm": 4.645874111538804,
      "learning_rate": 1.9723699203976768e-05,
      "loss": 0.9382,
      "step": 26
    },
    {
      "epoch": 0.11,
      "grad_norm": 4.037001045668538,
      "learning_rate": 1.9692309097067546e-05,
      "loss": 0.8327,
      "step": 27
    },
    {
      "epoch": 0.11,
      "grad_norm": 3.8726436235571375,
      "learning_rate": 1.9659258262890683e-05,
      "loss": 0.8093,
      "step": 28
    },
    {
      "epoch": 0.12,
      "grad_norm": 4.416369152341517,
      "learning_rate": 1.9624552364536472e-05,
      "loss": 0.8577,
      "step": 29
    },
    {
      "epoch": 0.12,
      "grad_norm": 4.079448182986533,
      "learning_rate": 1.958819734868193e-05,
      "loss": 0.7915,
      "step": 30
    },
    {
      "epoch": 0.12,
      "grad_norm": 4.164527502124648,
      "learning_rate": 1.9550199444571868e-05,
      "loss": 0.8252,
      "step": 31
    },
    {
      "epoch": 0.13,
      "grad_norm": 4.4507473422121775,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 0.815,
      "step": 32
    },
    {
      "epoch": 0.13,
      "grad_norm": 12.77537962179865,
      "learning_rate": 1.946930129495106e-05,
      "loss": 0.8069,
      "step": 33
    },
    {
      "epoch": 0.14,
      "grad_norm": 3.7744322929833296,
      "learning_rate": 1.9426414910921785e-05,
      "loss": 0.7753,
      "step": 34
    },
    {
      "epoch": 0.14,
      "grad_norm": 4.295099720887015,
      "learning_rate": 1.9381913359224844e-05,
      "loss": 0.8439,
      "step": 35
    },
    {
      "epoch": 0.14,
      "grad_norm": 4.120379389632878,
      "learning_rate": 1.9335804264972018e-05,
      "loss": 0.8494,
      "step": 36
    },
    {
      "epoch": 0.15,
      "grad_norm": 3.884534051899803,
      "learning_rate": 1.9288095528719245e-05,
      "loss": 0.8404,
      "step": 37
    },
    {
      "epoch": 0.15,
      "grad_norm": 4.178148754105961,
      "learning_rate": 1.9238795325112867e-05,
      "loss": 0.8591,
      "step": 38
    },
    {
      "epoch": 0.16,
      "grad_norm": 10.652352262549975,
      "learning_rate": 1.9187912101488986e-05,
      "loss": 0.7778,
      "step": 39
    },
    {
      "epoch": 0.16,
      "grad_norm": 4.04745940629276,
      "learning_rate": 1.913545457642601e-05,
      "loss": 0.832,
      "step": 40
    },
    {
      "epoch": 0.16,
      "grad_norm": 3.9873121487474337,
      "learning_rate": 1.9081431738250815e-05,
      "loss": 0.8204,
      "step": 41
    },
    {
      "epoch": 0.17,
      "grad_norm": 6.913137388754365,
      "learning_rate": 1.902585284349861e-05,
      "loss": 0.8412,
      "step": 42
    },
    {
      "epoch": 0.17,
      "grad_norm": 3.9299159507148334,
      "learning_rate": 1.8968727415326885e-05,
      "loss": 0.8434,
      "step": 43
    },
    {
      "epoch": 0.18,
      "grad_norm": 4.130005216850926,
      "learning_rate": 1.891006524188368e-05,
      "loss": 0.8399,
      "step": 44
    },
    {
      "epoch": 0.18,
      "grad_norm": 4.111257084020728,
      "learning_rate": 1.884987637463042e-05,
      "loss": 0.7785,
      "step": 45
    },
    {
      "epoch": 0.19,
      "grad_norm": 3.6735042536428484,
      "learning_rate": 1.8788171126619653e-05,
      "loss": 0.7343,
      "step": 46
    },
    {
      "epoch": 0.19,
      "grad_norm": 3.8990711963820597,
      "learning_rate": 1.8724960070727974e-05,
      "loss": 0.8213,
      "step": 47
    },
    {
      "epoch": 0.19,
      "grad_norm": 4.136288457593519,
      "learning_rate": 1.866025403784439e-05,
      "loss": 0.838,
      "step": 48
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.955324397606123,
      "learning_rate": 1.8594064115014528e-05,
      "loss": 0.8352,
      "step": 49
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.9095890701470313,
      "learning_rate": 1.8526401643540924e-05,
      "loss": 0.807,
      "step": 50
    },
    {
      "epoch": 0.21,
      "grad_norm": 4.012637364526424,
      "learning_rate": 1.8457278217039735e-05,
      "loss": 0.8111,
      "step": 51
    },
    {
      "epoch": 0.21,
      "grad_norm": 3.558222179890737,
      "learning_rate": 1.8386705679454243e-05,
      "loss": 0.8135,
      "step": 52
    },
    {
      "epoch": 0.21,
      "grad_norm": 3.672167676885502,
      "learning_rate": 1.8314696123025456e-05,
      "loss": 0.7625,
      "step": 53
    },
    {
      "epoch": 0.22,
      "grad_norm": 3.590125761608772,
      "learning_rate": 1.8241261886220155e-05,
      "loss": 0.8209,
      "step": 54
    },
    {
      "epoch": 0.22,
      "grad_norm": 3.48665453782569,
      "learning_rate": 1.816641555161679e-05,
      "loss": 0.77,
      "step": 55
    },
    {
      "epoch": 0.23,
      "grad_norm": 3.412813388073817,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.7626,
      "step": 56
    },
    {
      "epoch": 0.23,
      "grad_norm": 3.5133210634504857,
      "learning_rate": 1.801253812691061e-05,
      "loss": 0.7901,
      "step": 57
    },
    {
      "epoch": 0.23,
      "grad_norm": 3.4853560508903505,
      "learning_rate": 1.7933533402912354e-05,
      "loss": 0.7738,
      "step": 58
    },
    {
      "epoch": 0.24,
      "grad_norm": 3.6247689551435216,
      "learning_rate": 1.785316930880745e-05,
      "loss": 0.7469,
      "step": 59
    },
    {
      "epoch": 0.24,
      "grad_norm": 3.59970014872682,
      "learning_rate": 1.777145961456971e-05,
      "loss": 0.7944,
      "step": 60
    },
    {
      "epoch": 0.25,
      "grad_norm": 3.6367785536835586,
      "learning_rate": 1.7688418320734596e-05,
      "loss": 0.8042,
      "step": 61
    },
    {
      "epoch": 0.25,
      "grad_norm": 3.699950696770654,
      "learning_rate": 1.7604059656000313e-05,
      "loss": 0.7859,
      "step": 62
    },
    {
      "epoch": 0.25,
      "grad_norm": 3.4181345198902955,
      "learning_rate": 1.7518398074789776e-05,
      "loss": 0.8028,
      "step": 63
    },
    {
      "epoch": 0.26,
      "grad_norm": 3.4041141423280847,
      "learning_rate": 1.7431448254773943e-05,
      "loss": 0.7515,
      "step": 64
    },
    {
      "epoch": 0.26,
      "grad_norm": 3.3993634760898335,
      "learning_rate": 1.7343225094356857e-05,
      "loss": 0.7667,
      "step": 65
    },
    {
      "epoch": 0.27,
      "grad_norm": 3.533268561628967,
      "learning_rate": 1.7253743710122877e-05,
      "loss": 0.8509,
      "step": 66
    },
    {
      "epoch": 0.27,
      "grad_norm": 3.718968675350464,
      "learning_rate": 1.7163019434246545e-05,
      "loss": 0.8054,
      "step": 67
    },
    {
      "epoch": 0.27,
      "grad_norm": 3.473906783474757,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.7787,
      "step": 68
    },
    {
      "epoch": 0.28,
      "grad_norm": 3.309223190700808,
      "learning_rate": 1.6977904598416803e-05,
      "loss": 0.8111,
      "step": 69
    },
    {
      "epoch": 0.28,
      "grad_norm": 3.3323854800128996,
      "learning_rate": 1.688354575693754e-05,
      "loss": 0.7216,
      "step": 70
    },
    {
      "epoch": 0.29,
      "grad_norm": 3.273500374358199,
      "learning_rate": 1.678800745532942e-05,
      "loss": 0.7443,
      "step": 71
    },
    {
      "epoch": 0.29,
      "grad_norm": 3.2243255860973172,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 0.7604,
      "step": 72
    },
    {
      "epoch": 0.29,
      "grad_norm": 3.380060721400282,
      "learning_rate": 1.659345815100069e-05,
      "loss": 0.7893,
      "step": 73
    },
    {
      "epoch": 0.3,
      "grad_norm": 3.521827557852244,
      "learning_rate": 1.6494480483301836e-05,
      "loss": 0.7608,
      "step": 74
    },
    {
      "epoch": 0.3,
      "grad_norm": 3.0365735054611545,
      "learning_rate": 1.639439001980585e-05,
      "loss": 0.7263,
      "step": 75
    },
    {
      "epoch": 0.31,
      "grad_norm": 4.49203041454867,
      "learning_rate": 1.6293203910498375e-05,
      "loss": 0.7583,
      "step": 76
    },
    {
      "epoch": 0.31,
      "grad_norm": 3.2444303812731623,
      "learning_rate": 1.6190939493098344e-05,
      "loss": 0.7872,
      "step": 77
    },
    {
      "epoch": 0.31,
      "grad_norm": 3.376153822696857,
      "learning_rate": 1.608761429008721e-05,
      "loss": 0.7922,
      "step": 78
    },
    {
      "epoch": 0.32,
      "grad_norm": 3.719824211433031,
      "learning_rate": 1.5983246005706592e-05,
      "loss": 0.7683,
      "step": 79
    },
    {
      "epoch": 0.32,
      "grad_norm": 3.4139581998539947,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 0.7532,
      "step": 80
    },
    {
      "epoch": 0.33,
      "grad_norm": 3.129827729305358,
      "learning_rate": 1.577145190037234e-05,
      "loss": 0.7223,
      "step": 81
    },
    {
      "epoch": 0.33,
      "grad_norm": 3.1658157169018804,
      "learning_rate": 1.566406236924833e-05,
      "loss": 0.7414,
      "step": 82
    },
    {
      "epoch": 0.33,
      "grad_norm": 3.430341660294287,
      "learning_rate": 1.5555702330196024e-05,
      "loss": 0.7922,
      "step": 83
    },
    {
      "epoch": 0.34,
      "grad_norm": 4.04724234853034,
      "learning_rate": 1.5446390350150272e-05,
      "loss": 0.7526,
      "step": 84
    },
    {
      "epoch": 0.34,
      "grad_norm": 3.4653721119226413,
      "learning_rate": 1.533614515915612e-05,
      "loss": 0.7833,
      "step": 85
    },
    {
      "epoch": 0.35,
      "grad_norm": 3.197900416322239,
      "learning_rate": 1.5224985647159489e-05,
      "loss": 0.758,
      "step": 86
    },
    {
      "epoch": 0.35,
      "grad_norm": 3.52173786666907,
      "learning_rate": 1.511293086077052e-05,
      "loss": 0.7454,
      "step": 87
    },
    {
      "epoch": 0.35,
      "grad_norm": 3.495026674196132,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.7472,
      "step": 88
    },
    {
      "epoch": 0.36,
      "grad_norm": 3.2393960637436816,
      "learning_rate": 1.4886212414969551e-05,
      "loss": 0.7543,
      "step": 89
    },
    {
      "epoch": 0.36,
      "grad_norm": 3.0910664428999612,
      "learning_rate": 1.4771587602596085e-05,
      "loss": 0.7421,
      "step": 90
    },
    {
      "epoch": 0.37,
      "grad_norm": 3.6107091294490945,
      "learning_rate": 1.4656145203251116e-05,
      "loss": 0.7618,
      "step": 91
    },
    {
      "epoch": 0.37,
      "grad_norm": 3.5342077543575825,
      "learning_rate": 1.4539904997395468e-05,
      "loss": 0.7727,
      "step": 92
    },
    {
      "epoch": 0.37,
      "grad_norm": 3.4193733553018193,
      "learning_rate": 1.4422886902190014e-05,
      "loss": 0.7307,
      "step": 93
    },
    {
      "epoch": 0.38,
      "grad_norm": 3.2389287534428366,
      "learning_rate": 1.4305110968082953e-05,
      "loss": 0.7783,
      "step": 94
    },
    {
      "epoch": 0.38,
      "grad_norm": 3.0870530781931866,
      "learning_rate": 1.4186597375374283e-05,
      "loss": 0.7474,
      "step": 95
    },
    {
      "epoch": 0.39,
      "grad_norm": 3.2151506956493727,
      "learning_rate": 1.4067366430758004e-05,
      "loss": 0.7482,
      "step": 96
    },
    {
      "epoch": 0.39,
      "grad_norm": 3.160262916154622,
      "learning_rate": 1.3947438563842672e-05,
      "loss": 0.7416,
      "step": 97
    },
    {
      "epoch": 0.39,
      "grad_norm": 3.1075632651286518,
      "learning_rate": 1.3826834323650899e-05,
      "loss": 0.7762,
      "step": 98
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.205700217323795,
      "learning_rate": 1.3705574375098365e-05,
      "loss": 0.745,
      "step": 99
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.4195350896069536,
      "learning_rate": 1.3583679495453e-05,
      "loss": 0.7327,
      "step": 100
    },
    {
      "epoch": 0.41,
      "grad_norm": 3.4497001651504693,
      "learning_rate": 1.346117057077493e-05,
      "loss": 0.7366,
      "step": 101
    },
    {
      "epoch": 0.41,
      "grad_norm": 3.1459425100147533,
      "learning_rate": 1.333806859233771e-05,
      "loss": 0.7161,
      "step": 102
    },
    {
      "epoch": 0.41,
      "grad_norm": 3.2990164183970734,
      "learning_rate": 1.3214394653031616e-05,
      "loss": 0.7444,
      "step": 103
    },
    {
      "epoch": 0.42,
      "grad_norm": 3.2715408463923095,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.6994,
      "step": 104
    },
    {
      "epoch": 0.42,
      "grad_norm": 3.198689955623241,
      "learning_rate": 1.296541574975571e-05,
      "loss": 0.7575,
      "step": 105
    },
    {
      "epoch": 0.43,
      "grad_norm": 3.2635915335110712,
      "learning_rate": 1.284015344703923e-05,
      "loss": 0.7443,
      "step": 106
    },
    {
      "epoch": 0.43,
      "grad_norm": 3.3517089083418883,
      "learning_rate": 1.2714404498650743e-05,
      "loss": 0.7386,
      "step": 107
    },
    {
      "epoch": 0.43,
      "grad_norm": 3.1108466834694526,
      "learning_rate": 1.2588190451025209e-05,
      "loss": 0.7084,
      "step": 108
    },
    {
      "epoch": 0.44,
      "grad_norm": 3.2564530056706813,
      "learning_rate": 1.2461532930289932e-05,
      "loss": 0.7283,
      "step": 109
    },
    {
      "epoch": 0.44,
      "grad_norm": 3.130748292471953,
      "learning_rate": 1.2334453638559057e-05,
      "loss": 0.6998,
      "step": 110
    },
    {
      "epoch": 0.45,
      "grad_norm": 3.284504968679618,
      "learning_rate": 1.2206974350215016e-05,
      "loss": 0.6947,
      "step": 111
    },
    {
      "epoch": 0.45,
      "grad_norm": 3.117247061760117,
      "learning_rate": 1.2079116908177592e-05,
      "loss": 0.6882,
      "step": 112
    },
    {
      "epoch": 0.45,
      "grad_norm": 3.123247895047925,
      "learning_rate": 1.1950903220161286e-05,
      "loss": 0.7537,
      "step": 113
    },
    {
      "epoch": 0.46,
      "grad_norm": 3.264995727676228,
      "learning_rate": 1.1822355254921478e-05,
      "loss": 0.6361,
      "step": 114
    },
    {
      "epoch": 0.46,
      "grad_norm": 3.203793038591507,
      "learning_rate": 1.1693495038490247e-05,
      "loss": 0.6931,
      "step": 115
    },
    {
      "epoch": 0.47,
      "grad_norm": 3.2167335628559237,
      "learning_rate": 1.156434465040231e-05,
      "loss": 0.7523,
      "step": 116
    },
    {
      "epoch": 0.47,
      "grad_norm": 3.155872681751441,
      "learning_rate": 1.1434926219911792e-05,
      "loss": 0.7434,
      "step": 117
    },
    {
      "epoch": 0.47,
      "grad_norm": 3.1649337966193403,
      "learning_rate": 1.130526192220052e-05,
      "loss": 0.7091,
      "step": 118
    },
    {
      "epoch": 0.48,
      "grad_norm": 3.380161608617727,
      "learning_rate": 1.1175373974578378e-05,
      "loss": 0.7091,
      "step": 119
    },
    {
      "epoch": 0.48,
      "grad_norm": 3.3404772682405373,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 0.6949,
      "step": 120
    },
    {
      "epoch": 0.49,
      "grad_norm": 3.098310219091935,
      "learning_rate": 1.0915016186634027e-05,
      "loss": 0.6727,
      "step": 121
    },
    {
      "epoch": 0.49,
      "grad_norm": 2.836208750823026,
      "learning_rate": 1.0784590957278452e-05,
      "loss": 0.7163,
      "step": 122
    },
    {
      "epoch": 0.49,
      "grad_norm": 3.105805092683989,
      "learning_rate": 1.0654031292301432e-05,
      "loss": 0.7335,
      "step": 123
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.196297017297509,
      "learning_rate": 1.0523359562429441e-05,
      "loss": 0.7292,
      "step": 124
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.1414369865053735,
      "learning_rate": 1.0392598157590687e-05,
      "loss": 0.6763,
      "step": 125
    },
    {
      "epoch": 0.51,
      "grad_norm": 2.975147216836934,
      "learning_rate": 1.0261769483078734e-05,
      "loss": 0.7414,
      "step": 126
    },
    {
      "epoch": 0.51,
      "grad_norm": 2.970580210348648,
      "learning_rate": 1.0130895955713445e-05,
      "loss": 0.6802,
      "step": 127
    },
    {
      "epoch": 0.52,
      "grad_norm": 3.104117571248321,
      "learning_rate": 1e-05,
      "loss": 0.7463,
      "step": 128
    },
    {
      "epoch": 0.52,
      "grad_norm": 2.9640689423655435,
      "learning_rate": 9.869104044286558e-06,
      "loss": 0.7618,
      "step": 129
    },
    {
      "epoch": 0.52,
      "grad_norm": 2.9911767076629086,
      "learning_rate": 9.738230516921272e-06,
      "loss": 0.6836,
      "step": 130
    },
    {
      "epoch": 0.53,
      "grad_norm": 2.809626960477857,
      "learning_rate": 9.607401842409318e-06,
      "loss": 0.6627,
      "step": 131
    },
    {
      "epoch": 0.53,
      "grad_norm": 2.908538129946587,
      "learning_rate": 9.476640437570562e-06,
      "loss": 0.7006,
      "step": 132
    },
    {
      "epoch": 0.54,
      "grad_norm": 2.8082973364393564,
      "learning_rate": 9.34596870769857e-06,
      "loss": 0.678,
      "step": 133
    },
    {
      "epoch": 0.54,
      "grad_norm": 3.0593289133945105,
      "learning_rate": 9.215409042721553e-06,
      "loss": 0.67,
      "step": 134
    },
    {
      "epoch": 0.54,
      "grad_norm": 3.0420292673706553,
      "learning_rate": 9.084983813365977e-06,
      "loss": 0.6944,
      "step": 135
    },
    {
      "epoch": 0.55,
      "grad_norm": 2.9083755105673563,
      "learning_rate": 8.954715367323468e-06,
      "loss": 0.6556,
      "step": 136
    },
    {
      "epoch": 0.55,
      "grad_norm": 3.0620025648931497,
      "learning_rate": 8.824626025421625e-06,
      "loss": 0.7284,
      "step": 137
    },
    {
      "epoch": 0.56,
      "grad_norm": 2.6998083461153914,
      "learning_rate": 8.694738077799487e-06,
      "loss": 0.6639,
      "step": 138
    },
    {
      "epoch": 0.56,
      "grad_norm": 3.2797119376895716,
      "learning_rate": 8.56507378008821e-06,
      "loss": 0.6733,
      "step": 139
    },
    {
      "epoch": 0.56,
      "grad_norm": 3.0126953406724577,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.6964,
      "step": 140
    },
    {
      "epoch": 0.57,
      "grad_norm": 2.796580811831135,
      "learning_rate": 8.306504961509755e-06,
      "loss": 0.6658,
      "step": 141
    },
    {
      "epoch": 0.57,
      "grad_norm": 2.932629980237771,
      "learning_rate": 8.177644745078525e-06,
      "loss": 0.667,
      "step": 142
    },
    {
      "epoch": 0.58,
      "grad_norm": 2.9247233852395187,
      "learning_rate": 8.04909677983872e-06,
      "loss": 0.6974,
      "step": 143
    },
    {
      "epoch": 0.58,
      "grad_norm": 3.0053778956703794,
      "learning_rate": 7.92088309182241e-06,
      "loss": 0.6624,
      "step": 144
    },
    {
      "epoch": 0.58,
      "grad_norm": 3.0788826712069977,
      "learning_rate": 7.793025649784991e-06,
      "loss": 0.6777,
      "step": 145
    },
    {
      "epoch": 0.59,
      "grad_norm": 3.2162223008398323,
      "learning_rate": 7.66554636144095e-06,
      "loss": 0.6918,
      "step": 146
    },
    {
      "epoch": 0.59,
      "grad_norm": 2.8521413927812755,
      "learning_rate": 7.53846706971007e-06,
      "loss": 0.6591,
      "step": 147
    },
    {
      "epoch": 0.6,
      "grad_norm": 2.991270423637478,
      "learning_rate": 7.411809548974792e-06,
      "loss": 0.6713,
      "step": 148
    },
    {
      "epoch": 0.6,
      "grad_norm": 3.1599919666313516,
      "learning_rate": 7.285595501349259e-06,
      "loss": 0.7135,
      "step": 149
    },
    {
      "epoch": 0.6,
      "grad_norm": 3.0904062770574745,
      "learning_rate": 7.159846552960774e-06,
      "loss": 0.6744,
      "step": 150
    },
    {
      "epoch": 0.61,
      "grad_norm": 2.8902364976568364,
      "learning_rate": 7.034584250244292e-06,
      "loss": 0.6943,
      "step": 151
    },
    {
      "epoch": 0.61,
      "grad_norm": 2.8502834417573215,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.6993,
      "step": 152
    },
    {
      "epoch": 0.62,
      "grad_norm": 3.039432383226104,
      "learning_rate": 6.785605346968387e-06,
      "loss": 0.6613,
      "step": 153
    },
    {
      "epoch": 0.62,
      "grad_norm": 3.099964107537924,
      "learning_rate": 6.661931407662292e-06,
      "loss": 0.6866,
      "step": 154
    },
    {
      "epoch": 0.62,
      "grad_norm": 2.8889343463672175,
      "learning_rate": 6.538829429225068e-06,
      "loss": 0.6776,
      "step": 155
    },
    {
      "epoch": 0.63,
      "grad_norm": 2.847366391568978,
      "learning_rate": 6.4163205045469975e-06,
      "loss": 0.6816,
      "step": 156
    },
    {
      "epoch": 0.63,
      "grad_norm": 2.9467521016074696,
      "learning_rate": 6.294425624901638e-06,
      "loss": 0.6635,
      "step": 157
    },
    {
      "epoch": 0.64,
      "grad_norm": 3.297231125096767,
      "learning_rate": 6.173165676349103e-06,
      "loss": 0.6641,
      "step": 158
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.9170789319469823,
      "learning_rate": 6.052561436157329e-06,
      "loss": 0.7041,
      "step": 159
    },
    {
      "epoch": 0.64,
      "grad_norm": 3.001510747801933,
      "learning_rate": 5.932633569242e-06,
      "loss": 0.6715,
      "step": 160
    },
    {
      "epoch": 0.65,
      "grad_norm": 2.7789700387504723,
      "learning_rate": 5.813402624625722e-06,
      "loss": 0.6649,
      "step": 161
    },
    {
      "epoch": 0.65,
      "grad_norm": 2.822714205810188,
      "learning_rate": 5.694889031917047e-06,
      "loss": 0.6755,
      "step": 162
    },
    {
      "epoch": 0.66,
      "grad_norm": 3.084288103394142,
      "learning_rate": 5.5771130978099896e-06,
      "loss": 0.6785,
      "step": 163
    },
    {
      "epoch": 0.66,
      "grad_norm": 3.0177738819527855,
      "learning_rate": 5.460095002604533e-06,
      "loss": 0.678,
      "step": 164
    },
    {
      "epoch": 0.66,
      "grad_norm": 2.8895474680758855,
      "learning_rate": 5.343854796748886e-06,
      "loss": 0.6408,
      "step": 165
    },
    {
      "epoch": 0.67,
      "grad_norm": 2.803858385834539,
      "learning_rate": 5.228412397403916e-06,
      "loss": 0.6651,
      "step": 166
    },
    {
      "epoch": 0.67,
      "grad_norm": 2.774857548804327,
      "learning_rate": 5.1137875850304545e-06,
      "loss": 0.6447,
      "step": 167
    },
    {
      "epoch": 0.68,
      "grad_norm": 2.789673330528513,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.6452,
      "step": 168
    },
    {
      "epoch": 0.68,
      "grad_norm": 2.98273381240324,
      "learning_rate": 4.887069139229481e-06,
      "loss": 0.6376,
      "step": 169
    },
    {
      "epoch": 0.68,
      "grad_norm": 2.8036691683017216,
      "learning_rate": 4.775014352840512e-06,
      "loss": 0.6723,
      "step": 170
    },
    {
      "epoch": 0.69,
      "grad_norm": 2.7401403980125076,
      "learning_rate": 4.663854840843885e-06,
      "loss": 0.646,
      "step": 171
    },
    {
      "epoch": 0.69,
      "grad_norm": 2.798310553331552,
      "learning_rate": 4.5536096498497295e-06,
      "loss": 0.6417,
      "step": 172
    },
    {
      "epoch": 0.7,
      "grad_norm": 2.8010908037740574,
      "learning_rate": 4.444297669803981e-06,
      "loss": 0.6729,
      "step": 173
    },
    {
      "epoch": 0.7,
      "grad_norm": 2.8901027733270253,
      "learning_rate": 4.335937630751675e-06,
      "loss": 0.647,
      "step": 174
    },
    {
      "epoch": 0.7,
      "grad_norm": 2.8708777981874842,
      "learning_rate": 4.228548099627665e-06,
      "loss": 0.6075,
      "step": 175
    },
    {
      "epoch": 0.71,
      "grad_norm": 3.0167040995991443,
      "learning_rate": 4.12214747707527e-06,
      "loss": 0.6698,
      "step": 176
    },
    {
      "epoch": 0.71,
      "grad_norm": 3.0362453259039466,
      "learning_rate": 4.01675399429341e-06,
      "loss": 0.6617,
      "step": 177
    },
    {
      "epoch": 0.72,
      "grad_norm": 3.0116169669427317,
      "learning_rate": 3.912385709912794e-06,
      "loss": 0.6784,
      "step": 178
    },
    {
      "epoch": 0.72,
      "grad_norm": 2.835828506403738,
      "learning_rate": 3.8090605069016596e-06,
      "loss": 0.6969,
      "step": 179
    },
    {
      "epoch": 0.72,
      "grad_norm": 2.6737268997585284,
      "learning_rate": 3.7067960895016277e-06,
      "loss": 0.6,
      "step": 180
    },
    {
      "epoch": 0.73,
      "grad_norm": 2.6541442936760484,
      "learning_rate": 3.6056099801941535e-06,
      "loss": 0.6495,
      "step": 181
    },
    {
      "epoch": 0.73,
      "grad_norm": 2.8493615837669366,
      "learning_rate": 3.505519516698165e-06,
      "loss": 0.6312,
      "step": 182
    },
    {
      "epoch": 0.74,
      "grad_norm": 2.771298137375993,
      "learning_rate": 3.4065418489993118e-06,
      "loss": 0.6753,
      "step": 183
    },
    {
      "epoch": 0.74,
      "grad_norm": 2.8644565083781623,
      "learning_rate": 3.308693936411421e-06,
      "loss": 0.6462,
      "step": 184
    },
    {
      "epoch": 0.74,
      "grad_norm": 2.816001462856791,
      "learning_rate": 3.2119925446705824e-06,
      "loss": 0.6424,
      "step": 185
    },
    {
      "epoch": 0.75,
      "grad_norm": 2.646021894966294,
      "learning_rate": 3.116454243062459e-06,
      "loss": 0.6284,
      "step": 186
    },
    {
      "epoch": 0.75,
      "grad_norm": 2.9145304607591203,
      "learning_rate": 3.0220954015832004e-06,
      "loss": 0.637,
      "step": 187
    },
    {
      "epoch": 0.76,
      "grad_norm": 2.829949472425193,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.6676,
      "step": 188
    },
    {
      "epoch": 0.76,
      "grad_norm": 2.814064839600381,
      "learning_rate": 2.8369805657534576e-06,
      "loss": 0.5785,
      "step": 189
    },
    {
      "epoch": 0.76,
      "grad_norm": 2.821035799840264,
      "learning_rate": 2.746256289877126e-06,
      "loss": 0.6863,
      "step": 190
    },
    {
      "epoch": 0.77,
      "grad_norm": 2.8168022476870553,
      "learning_rate": 2.656774905643147e-06,
      "loss": 0.63,
      "step": 191
    },
    {
      "epoch": 0.77,
      "grad_norm": 3.0001762703176564,
      "learning_rate": 2.5685517452260566e-06,
      "loss": 0.6554,
      "step": 192
    },
    {
      "epoch": 0.78,
      "grad_norm": 2.7403139778831522,
      "learning_rate": 2.4816019252102274e-06,
      "loss": 0.6522,
      "step": 193
    },
    {
      "epoch": 0.78,
      "grad_norm": 2.9114201705549405,
      "learning_rate": 2.395940343999691e-06,
      "loss": 0.6661,
      "step": 194
    },
    {
      "epoch": 0.78,
      "grad_norm": 2.8451422578510064,
      "learning_rate": 2.3115816792654057e-06,
      "loss": 0.6189,
      "step": 195
    },
    {
      "epoch": 0.79,
      "grad_norm": 2.7642273669714936,
      "learning_rate": 2.2285403854302912e-06,
      "loss": 0.6603,
      "step": 196
    },
    {
      "epoch": 0.79,
      "grad_norm": 2.749436453803936,
      "learning_rate": 2.146830691192553e-06,
      "loss": 0.6404,
      "step": 197
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.938271887153146,
      "learning_rate": 2.0664665970876496e-06,
      "loss": 0.6015,
      "step": 198
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.712810660184342,
      "learning_rate": 1.9874618730893947e-06,
      "loss": 0.6255,
      "step": 199
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.7426161198212444,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.6035,
      "step": 200
    },
    {
      "epoch": 0.81,
      "grad_norm": 2.786594710662645,
      "learning_rate": 1.833584448383211e-06,
      "loss": 0.6125,
      "step": 201
    },
    {
      "epoch": 0.81,
      "grad_norm": 2.789074670925281,
      "learning_rate": 1.7587381137798432e-06,
      "loss": 0.6349,
      "step": 202
    },
    {
      "epoch": 0.82,
      "grad_norm": 2.7434410420361166,
      "learning_rate": 1.6853038769745466e-06,
      "loss": 0.6523,
      "step": 203
    },
    {
      "epoch": 0.82,
      "grad_norm": 2.8817669021799435,
      "learning_rate": 1.6132943205457607e-06,
      "loss": 0.6351,
      "step": 204
    },
    {
      "epoch": 0.82,
      "grad_norm": 2.714117428189331,
      "learning_rate": 1.542721782960268e-06,
      "loss": 0.635,
      "step": 205
    },
    {
      "epoch": 0.83,
      "grad_norm": 2.735558137768747,
      "learning_rate": 1.4735983564590784e-06,
      "loss": 0.6379,
      "step": 206
    },
    {
      "epoch": 0.83,
      "grad_norm": 2.6895646826293103,
      "learning_rate": 1.4059358849854732e-06,
      "loss": 0.618,
      "step": 207
    },
    {
      "epoch": 0.84,
      "grad_norm": 2.7529613446845156,
      "learning_rate": 1.339745962155613e-06,
      "loss": 0.6235,
      "step": 208
    },
    {
      "epoch": 0.84,
      "grad_norm": 2.851839132806964,
      "learning_rate": 1.2750399292720284e-06,
      "loss": 0.5998,
      "step": 209
    },
    {
      "epoch": 0.85,
      "grad_norm": 2.7768293105129693,
      "learning_rate": 1.2118288733803474e-06,
      "loss": 0.6383,
      "step": 210
    },
    {
      "epoch": 0.85,
      "grad_norm": 2.963876749861089,
      "learning_rate": 1.1501236253695823e-06,
      "loss": 0.628,
      "step": 211
    },
    {
      "epoch": 0.85,
      "grad_norm": 2.820228034768241,
      "learning_rate": 1.0899347581163222e-06,
      "loss": 0.6211,
      "step": 212
    },
    {
      "epoch": 0.86,
      "grad_norm": 2.7274136730411165,
      "learning_rate": 1.0312725846731174e-06,
      "loss": 0.616,
      "step": 213
    },
    {
      "epoch": 0.86,
      "grad_norm": 2.7218980983734347,
      "learning_rate": 9.74147156501396e-07,
      "loss": 0.6037,
      "step": 214
    },
    {
      "epoch": 0.87,
      "grad_norm": 2.737999465536997,
      "learning_rate": 9.185682617491865e-07,
      "loss": 0.6045,
      "step": 215
    },
    {
      "epoch": 0.87,
      "grad_norm": 2.9200659935554945,
      "learning_rate": 8.645454235739903e-07,
      "loss": 0.5958,
      "step": 216
    },
    {
      "epoch": 0.87,
      "grad_norm": 3.051643258357116,
      "learning_rate": 8.120878985110181e-07,
      "loss": 0.6423,
      "step": 217
    },
    {
      "epoch": 0.88,
      "grad_norm": 2.875639951997766,
      "learning_rate": 7.612046748871327e-07,
      "loss": 0.622,
      "step": 218
    },
    {
      "epoch": 0.88,
      "grad_norm": 2.862069233951138,
      "learning_rate": 7.119044712807577e-07,
      "loss": 0.6087,
      "step": 219
    },
    {
      "epoch": 0.89,
      "grad_norm": 2.73899349322012,
      "learning_rate": 6.641957350279838e-07,
      "loss": 0.6168,
      "step": 220
    },
    {
      "epoch": 0.89,
      "grad_norm": 2.588971392693757,
      "learning_rate": 6.180866407751595e-07,
      "loss": 0.6451,
      "step": 221
    },
    {
      "epoch": 0.89,
      "grad_norm": 2.8718397708259378,
      "learning_rate": 5.735850890782158e-07,
      "loss": 0.6324,
      "step": 222
    },
    {
      "epoch": 0.9,
      "grad_norm": 2.8852875585668376,
      "learning_rate": 5.306987050489442e-07,
      "loss": 0.6182,
      "step": 223
    },
    {
      "epoch": 0.9,
      "grad_norm": 2.7650647838693914,
      "learning_rate": 4.894348370484648e-07,
      "loss": 0.5667,
      "step": 224
    },
    {
      "epoch": 0.91,
      "grad_norm": 2.8230403126857335,
      "learning_rate": 4.498005554281337e-07,
      "loss": 0.6128,
      "step": 225
    },
    {
      "epoch": 0.91,
      "grad_norm": 2.879794950330522,
      "learning_rate": 4.118026513180695e-07,
      "loss": 0.5941,
      "step": 226
    },
    {
      "epoch": 0.91,
      "grad_norm": 2.7446275251769396,
      "learning_rate": 3.7544763546352834e-07,
      "loss": 0.6244,
      "step": 227
    },
    {
      "epoch": 0.92,
      "grad_norm": 2.6887576536241857,
      "learning_rate": 3.4074173710931804e-07,
      "loss": 0.6248,
      "step": 228
    },
    {
      "epoch": 0.92,
      "grad_norm": 2.690551981809345,
      "learning_rate": 3.076909029324571e-07,
      "loss": 0.5963,
      "step": 229
    },
    {
      "epoch": 0.93,
      "grad_norm": 2.5654549052946223,
      "learning_rate": 2.7630079602323447e-07,
      "loss": 0.5789,
      "step": 230
    },
    {
      "epoch": 0.93,
      "grad_norm": 2.513351667440747,
      "learning_rate": 2.465767949148734e-07,
      "loss": 0.6351,
      "step": 231
    },
    {
      "epoch": 0.93,
      "grad_norm": 2.749586720660501,
      "learning_rate": 2.1852399266194312e-07,
      "loss": 0.6373,
      "step": 232
    },
    {
      "epoch": 0.94,
      "grad_norm": 2.6870474359556566,
      "learning_rate": 1.921471959676957e-07,
      "loss": 0.6309,
      "step": 233
    },
    {
      "epoch": 0.94,
      "grad_norm": 2.7513850116508274,
      "learning_rate": 1.6745092436045495e-07,
      "loss": 0.5698,
      "step": 234
    },
    {
      "epoch": 0.95,
      "grad_norm": 2.6939401360582864,
      "learning_rate": 1.444394094192225e-07,
      "loss": 0.6262,
      "step": 235
    },
    {
      "epoch": 0.95,
      "grad_norm": 2.6232813652434164,
      "learning_rate": 1.231165940486234e-07,
      "loss": 0.5612,
      "step": 236
    },
    {
      "epoch": 0.95,
      "grad_norm": 2.6706512156376334,
      "learning_rate": 1.0348613180329758e-07,
      "loss": 0.6505,
      "step": 237
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.6189528225089354,
      "learning_rate": 8.555138626189619e-08,
      "loss": 0.634,
      "step": 238
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.6761943618849466,
      "learning_rate": 6.931543045073708e-08,
      "loss": 0.6273,
      "step": 239
    },
    {
      "epoch": 0.97,
      "grad_norm": 2.7119751713467353,
      "learning_rate": 5.4781046317267103e-08,
      "loss": 0.6477,
      "step": 240
    },
    {
      "epoch": 0.97,
      "grad_norm": 2.9647323401672763,
      "learning_rate": 4.195072425338342e-08,
      "loss": 0.6499,
      "step": 241
    },
    {
      "epoch": 0.97,
      "grad_norm": 2.8796872154425297,
      "learning_rate": 3.082666266872036e-08,
      "loss": 0.6351,
      "step": 242
    },
    {
      "epoch": 0.98,
      "grad_norm": 2.9530423997992816,
      "learning_rate": 2.1410767613965212e-08,
      "loss": 0.6236,
      "step": 243
    },
    {
      "epoch": 0.98,
      "grad_norm": 2.6835243061567717,
      "learning_rate": 1.370465245426167e-08,
      "loss": 0.6255,
      "step": 244
    },
    {
      "epoch": 0.99,
      "grad_norm": 2.5543834123109304,
      "learning_rate": 7.70963759277099e-09,
      "loss": 0.6047,
      "step": 245
    },
    {
      "epoch": 0.99,
      "grad_norm": 2.8683018354650076,
      "learning_rate": 3.4267502444274013e-09,
      "loss": 0.6621,
      "step": 246
    },
    {
      "epoch": 0.99,
      "grad_norm": 2.710239191614037,
      "learning_rate": 8.567242599299974e-10,
      "loss": 0.6167,
      "step": 247
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.874215046360088,
      "learning_rate": 0.0,
      "loss": 0.6717,
      "step": 248
    },
    {
      "epoch": 1.0,
      "step": 248,
      "total_flos": 189717537947648.0,
      "train_loss": 0.732585372223008,
      "train_runtime": 5539.945,
      "train_samples_per_second": 2.87,
      "train_steps_per_second": 0.045
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 248,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 300,
  "total_flos": 189717537947648.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}