{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.837209302325581,
  "eval_steps": 11,
  "global_step": 215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 22.073590049775476,
      "learning_rate": 2e-08,
      "loss": 1.5029,
      "step": 1
    },
    {
      "epoch": 0.02,
      "eval_loss": 1.5676738023757935,
      "eval_runtime": 1.7229,
      "eval_samples_per_second": 11.028,
      "eval_steps_per_second": 1.741,
      "step": 1
    },
    {
      "epoch": 0.05,
      "grad_norm": 21.339319978585014,
      "learning_rate": 4e-08,
      "loss": 1.5411,
      "step": 2
    },
    {
      "epoch": 0.07,
      "grad_norm": 21.89138128266215,
      "learning_rate": 6e-08,
      "loss": 1.535,
      "step": 3
    },
    {
      "epoch": 0.09,
      "grad_norm": 35.68832946989201,
      "learning_rate": 8e-08,
      "loss": 1.4248,
      "step": 4
    },
    {
      "epoch": 0.12,
      "grad_norm": 18.922589465764027,
      "learning_rate": 1e-07,
      "loss": 1.512,
      "step": 5
    },
    {
      "epoch": 0.14,
      "grad_norm": 22.05229837285426,
      "learning_rate": 1.2e-07,
      "loss": 1.5849,
      "step": 6
    },
    {
      "epoch": 0.16,
      "grad_norm": 29.050954317842017,
      "learning_rate": 1.4e-07,
      "loss": 1.4915,
      "step": 7
    },
    {
      "epoch": 0.19,
      "grad_norm": 16.415909544756897,
      "learning_rate": 1.6e-07,
      "loss": 1.4711,
      "step": 8
    },
    {
      "epoch": 0.21,
      "grad_norm": 24.72099068344741,
      "learning_rate": 1.8e-07,
      "loss": 1.5618,
      "step": 9
    },
    {
      "epoch": 0.23,
      "grad_norm": 15.495802280155232,
      "learning_rate": 2e-07,
      "loss": 1.5432,
      "step": 10
    },
    {
      "epoch": 0.26,
      "grad_norm": 15.385087340525107,
      "learning_rate": 2.1999999999999998e-07,
      "loss": 1.5892,
      "step": 11
    },
    {
      "epoch": 0.26,
      "eval_loss": 1.5673789978027344,
      "eval_runtime": 0.7198,
      "eval_samples_per_second": 26.396,
      "eval_steps_per_second": 4.168,
      "step": 11
    },
    {
      "epoch": 0.28,
      "grad_norm": 18.316263378494824,
      "learning_rate": 2.4e-07,
      "loss": 1.5068,
      "step": 12
    },
    {
      "epoch": 0.3,
      "grad_norm": 16.604978508847786,
      "learning_rate": 2.6e-07,
      "loss": 1.5079,
      "step": 13
    },
    {
      "epoch": 0.33,
      "grad_norm": 19.088434906193037,
      "learning_rate": 2.8e-07,
      "loss": 1.3923,
      "step": 14
    },
    {
      "epoch": 0.35,
      "grad_norm": 13.367337607829006,
      "learning_rate": 3e-07,
      "loss": 1.4215,
      "step": 15
    },
    {
      "epoch": 0.37,
      "grad_norm": 14.12443554856015,
      "learning_rate": 3.2e-07,
      "loss": 1.5182,
      "step": 16
    },
    {
      "epoch": 0.4,
      "grad_norm": 21.547074702210885,
      "learning_rate": 3.4000000000000003e-07,
      "loss": 1.6407,
      "step": 17
    },
    {
      "epoch": 0.42,
      "grad_norm": 19.983618321532845,
      "learning_rate": 3.6e-07,
      "loss": 1.6124,
      "step": 18
    },
    {
      "epoch": 0.44,
      "grad_norm": 14.12870699420598,
      "learning_rate": 3.7999999999999996e-07,
      "loss": 1.3535,
      "step": 19
    },
    {
      "epoch": 0.47,
      "grad_norm": 17.73177207632663,
      "learning_rate": 4e-07,
      "loss": 1.4723,
      "step": 20
    },
    {
      "epoch": 0.49,
      "grad_norm": 24.017411591807985,
      "learning_rate": 4.1999999999999995e-07,
      "loss": 1.3109,
      "step": 21
    },
    {
      "epoch": 0.51,
      "grad_norm": 15.47289342392699,
      "learning_rate": 4.3999999999999997e-07,
      "loss": 1.2975,
      "step": 22
    },
    {
      "epoch": 0.51,
      "eval_loss": 1.5646436214447021,
      "eval_runtime": 0.7176,
      "eval_samples_per_second": 26.478,
      "eval_steps_per_second": 4.181,
      "step": 22
    },
    {
      "epoch": 0.53,
      "grad_norm": 21.160644074933437,
      "learning_rate": 4.6e-07,
      "loss": 1.5044,
      "step": 23
    },
    {
      "epoch": 0.56,
      "grad_norm": 15.065995566576719,
      "learning_rate": 4.8e-07,
      "loss": 1.4756,
      "step": 24
    },
    {
      "epoch": 0.58,
      "grad_norm": 17.05786606459713,
      "learning_rate": 5e-07,
      "loss": 1.4934,
      "step": 25
    },
    {
      "epoch": 0.6,
      "grad_norm": 15.821412963269017,
      "learning_rate": 5.2e-07,
      "loss": 1.6885,
      "step": 26
    },
    {
      "epoch": 0.63,
      "grad_norm": 17.42199498977738,
      "learning_rate": 5.4e-07,
      "loss": 1.3696,
      "step": 27
    },
    {
      "epoch": 0.65,
      "grad_norm": 17.118541529912182,
      "learning_rate": 5.6e-07,
      "loss": 1.4963,
      "step": 28
    },
    {
      "epoch": 0.67,
      "grad_norm": 16.14285401779511,
      "learning_rate": 5.8e-07,
      "loss": 1.523,
      "step": 29
    },
    {
      "epoch": 0.7,
      "grad_norm": 14.413715273595537,
      "learning_rate": 6e-07,
      "loss": 1.4205,
      "step": 30
    },
    {
      "epoch": 0.72,
      "grad_norm": 15.696143212367938,
      "learning_rate": 6.2e-07,
      "loss": 1.417,
      "step": 31
    },
    {
      "epoch": 0.74,
      "grad_norm": 18.422902888255102,
      "learning_rate": 6.4e-07,
      "loss": 1.513,
      "step": 32
    },
    {
      "epoch": 0.77,
      "grad_norm": 15.348458059196757,
      "learning_rate": 6.6e-07,
      "loss": 1.6405,
      "step": 33
    },
    {
      "epoch": 0.77,
      "eval_loss": 1.558524489402771,
      "eval_runtime": 0.7067,
      "eval_samples_per_second": 26.885,
      "eval_steps_per_second": 4.245,
      "step": 33
    },
    {
      "epoch": 0.79,
      "grad_norm": 31.510016892264296,
      "learning_rate": 6.800000000000001e-07,
      "loss": 1.395,
      "step": 34
    },
    {
      "epoch": 0.81,
      "grad_norm": 15.63296379080965,
      "learning_rate": 7e-07,
      "loss": 1.5409,
      "step": 35
    },
    {
      "epoch": 0.84,
      "grad_norm": 15.627218592491115,
      "learning_rate": 7.2e-07,
      "loss": 1.3137,
      "step": 36
    },
    {
      "epoch": 0.86,
      "grad_norm": 15.337191607694441,
      "learning_rate": 7.4e-07,
      "loss": 1.7298,
      "step": 37
    },
    {
      "epoch": 0.88,
      "grad_norm": 16.11020188378557,
      "learning_rate": 7.599999999999999e-07,
      "loss": 1.403,
      "step": 38
    },
    {
      "epoch": 0.91,
      "grad_norm": 19.261102026351743,
      "learning_rate": 7.799999999999999e-07,
      "loss": 1.5199,
      "step": 39
    },
    {
      "epoch": 0.93,
      "grad_norm": 15.249059429242267,
      "learning_rate": 8e-07,
      "loss": 1.5028,
      "step": 40
    },
    {
      "epoch": 0.95,
      "grad_norm": 17.026025037114596,
      "learning_rate": 8.199999999999999e-07,
      "loss": 1.5746,
      "step": 41
    },
    {
      "epoch": 0.98,
      "grad_norm": 20.241389951964763,
      "learning_rate": 8.399999999999999e-07,
      "loss": 1.5432,
      "step": 42
    },
    {
      "epoch": 1.0,
      "grad_norm": 13.357942060394901,
      "learning_rate": 8.599999999999999e-07,
      "loss": 1.3017,
      "step": 43
    },
    {
      "epoch": 1.02,
      "grad_norm": 19.122899956188,
      "learning_rate": 8.799999999999999e-07,
      "loss": 1.4797,
      "step": 44
    },
    {
      "epoch": 1.02,
      "eval_loss": 1.5534765720367432,
      "eval_runtime": 0.7056,
      "eval_samples_per_second": 26.926,
      "eval_steps_per_second": 4.251,
      "step": 44
    },
    {
      "epoch": 1.05,
      "grad_norm": 12.993274416162807,
      "learning_rate": 9e-07,
      "loss": 1.3812,
      "step": 45
    },
    {
      "epoch": 1.02,
      "grad_norm": 15.57715477404305,
      "learning_rate": 9.2e-07,
      "loss": 1.5169,
      "step": 46
    },
    {
      "epoch": 1.05,
      "grad_norm": 15.047562025949741,
      "learning_rate": 9.399999999999999e-07,
      "loss": 1.597,
      "step": 47
    },
    {
      "epoch": 1.07,
      "grad_norm": 13.154118671073913,
      "learning_rate": 9.6e-07,
      "loss": 1.4144,
      "step": 48
    },
    {
      "epoch": 1.09,
      "grad_norm": 17.445553030977283,
      "learning_rate": 9.8e-07,
      "loss": 1.5843,
      "step": 49
    },
    {
      "epoch": 1.12,
      "grad_norm": 11.552943553949452,
      "learning_rate": 1e-06,
      "loss": 1.3343,
      "step": 50
    },
    {
      "epoch": 1.14,
      "grad_norm": 14.151856403767372,
      "learning_rate": 1.02e-06,
      "loss": 1.428,
      "step": 51
    },
    {
      "epoch": 1.16,
      "grad_norm": 12.579639490538433,
      "learning_rate": 1.04e-06,
      "loss": 1.4277,
      "step": 52
    },
    {
      "epoch": 1.19,
      "grad_norm": 13.03970026338736,
      "learning_rate": 1.06e-06,
      "loss": 1.3097,
      "step": 53
    },
    {
      "epoch": 1.21,
      "grad_norm": 18.55159266953034,
      "learning_rate": 1.08e-06,
      "loss": 1.4071,
      "step": 54
    },
    {
      "epoch": 1.23,
      "grad_norm": 17.185477508845405,
      "learning_rate": 1.1e-06,
      "loss": 1.4285,
      "step": 55
    },
    {
      "epoch": 1.23,
      "eval_loss": 1.5510258674621582,
      "eval_runtime": 0.7063,
      "eval_samples_per_second": 26.902,
      "eval_steps_per_second": 4.248,
      "step": 55
    },
    {
      "epoch": 1.26,
      "grad_norm": 12.433682723330731,
      "learning_rate": 1.12e-06,
      "loss": 1.4209,
      "step": 56
    },
    {
      "epoch": 1.28,
      "grad_norm": 17.533881821169835,
      "learning_rate": 1.1399999999999999e-06,
      "loss": 1.1525,
      "step": 57
    },
    {
      "epoch": 1.3,
      "grad_norm": 21.371274746194803,
      "learning_rate": 1.16e-06,
      "loss": 1.4803,
      "step": 58
    },
    {
      "epoch": 1.33,
      "grad_norm": 12.91252932992948,
      "learning_rate": 1.18e-06,
      "loss": 1.342,
      "step": 59
    },
    {
      "epoch": 1.35,
      "grad_norm": 15.301368123637772,
      "learning_rate": 1.2e-06,
      "loss": 1.3903,
      "step": 60
    },
    {
      "epoch": 1.37,
      "grad_norm": 20.669912185962247,
      "learning_rate": 1.22e-06,
      "loss": 1.3419,
      "step": 61
    },
    {
      "epoch": 1.4,
      "grad_norm": 14.306797274099731,
      "learning_rate": 1.24e-06,
      "loss": 1.3697,
      "step": 62
    },
    {
      "epoch": 1.42,
      "grad_norm": 14.399414559225576,
      "learning_rate": 1.26e-06,
      "loss": 1.4607,
      "step": 63
    },
    {
      "epoch": 1.44,
      "grad_norm": 14.679866284169409,
      "learning_rate": 1.28e-06,
      "loss": 1.4576,
      "step": 64
    },
    {
      "epoch": 1.47,
      "grad_norm": 15.66686870904599,
      "learning_rate": 1.3e-06,
      "loss": 1.4088,
      "step": 65
    },
    {
      "epoch": 1.49,
      "grad_norm": 15.299128708308798,
      "learning_rate": 1.32e-06,
      "loss": 1.565,
      "step": 66
    },
    {
      "epoch": 1.49,
      "eval_loss": 1.5496699810028076,
      "eval_runtime": 0.7108,
      "eval_samples_per_second": 26.732,
      "eval_steps_per_second": 4.221,
      "step": 66
    },
    {
      "epoch": 1.51,
      "grad_norm": 17.72956466975166,
      "learning_rate": 1.34e-06,
      "loss": 1.5139,
      "step": 67
    },
    {
      "epoch": 1.53,
      "grad_norm": 12.468931115539235,
      "learning_rate": 1.3600000000000001e-06,
      "loss": 1.4851,
      "step": 68
    },
    {
      "epoch": 1.56,
      "grad_norm": 18.51314016158734,
      "learning_rate": 1.38e-06,
      "loss": 1.3645,
      "step": 69
    },
    {
      "epoch": 1.58,
      "grad_norm": 14.247910195754642,
      "learning_rate": 1.4e-06,
      "loss": 1.3199,
      "step": 70
    },
    {
      "epoch": 1.6,
      "grad_norm": 14.996917407863565,
      "learning_rate": 1.42e-06,
      "loss": 1.5712,
      "step": 71
    },
    {
      "epoch": 1.63,
      "grad_norm": 13.685317610155064,
      "learning_rate": 1.44e-06,
      "loss": 1.37,
      "step": 72
    },
    {
      "epoch": 1.65,
      "grad_norm": 20.67582737513748,
      "learning_rate": 1.46e-06,
      "loss": 1.5281,
      "step": 73
    },
    {
      "epoch": 1.67,
      "grad_norm": 24.21873361894607,
      "learning_rate": 1.48e-06,
      "loss": 1.5432,
      "step": 74
    },
    {
      "epoch": 1.7,
      "grad_norm": 18.530551736423014,
      "learning_rate": 1.5e-06,
      "loss": 1.5514,
      "step": 75
    },
    {
      "epoch": 1.72,
      "grad_norm": 13.006185380590916,
      "learning_rate": 1.5199999999999998e-06,
      "loss": 1.3638,
      "step": 76
    },
    {
      "epoch": 1.74,
      "grad_norm": 16.338789878308003,
      "learning_rate": 1.5399999999999999e-06,
      "loss": 1.2469,
      "step": 77
    },
    {
      "epoch": 1.74,
      "eval_loss": 1.5485225915908813,
      "eval_runtime": 0.7202,
      "eval_samples_per_second": 26.383,
      "eval_steps_per_second": 4.166,
      "step": 77
    },
    {
      "epoch": 1.77,
      "grad_norm": 12.226940015138254,
      "learning_rate": 1.5599999999999999e-06,
      "loss": 1.2613,
      "step": 78
    },
    {
      "epoch": 1.79,
      "grad_norm": 16.35044079107655,
      "learning_rate": 1.58e-06,
      "loss": 1.3039,
      "step": 79
    },
    {
      "epoch": 1.81,
      "grad_norm": 16.425588490991444,
      "learning_rate": 1.6e-06,
      "loss": 1.5878,
      "step": 80
    },
    {
      "epoch": 1.84,
      "grad_norm": 23.31190960420298,
      "learning_rate": 1.62e-06,
      "loss": 1.1774,
      "step": 81
    },
    {
      "epoch": 1.86,
      "grad_norm": 12.69134252831033,
      "learning_rate": 1.6399999999999998e-06,
      "loss": 1.2935,
      "step": 82
    },
    {
      "epoch": 1.88,
      "grad_norm": 14.81387052352272,
      "learning_rate": 1.6599999999999998e-06,
      "loss": 1.2247,
      "step": 83
    },
    {
      "epoch": 1.91,
      "grad_norm": 12.705757722264147,
      "learning_rate": 1.6799999999999998e-06,
      "loss": 1.4163,
      "step": 84
    },
    {
      "epoch": 1.93,
      "grad_norm": 15.14994784808861,
      "learning_rate": 1.6999999999999998e-06,
      "loss": 1.329,
      "step": 85
    },
    {
      "epoch": 1.95,
      "grad_norm": 25.616427443741422,
      "learning_rate": 1.7199999999999998e-06,
      "loss": 1.3684,
      "step": 86
    },
    {
      "epoch": 1.98,
      "grad_norm": 14.45050387972439,
      "learning_rate": 1.7399999999999999e-06,
      "loss": 1.4462,
      "step": 87
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.186429067007214,
      "learning_rate": 1.7599999999999999e-06,
      "loss": 1.6729,
      "step": 88
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.5481523275375366,
      "eval_runtime": 0.7439,
      "eval_samples_per_second": 25.543,
      "eval_steps_per_second": 4.033,
      "step": 88
    },
    {
      "epoch": 2.02,
      "grad_norm": 16.215693014828933,
      "learning_rate": 1.78e-06,
      "loss": 1.399,
      "step": 89
    },
    {
      "epoch": 2.02,
      "grad_norm": 16.266362330190216,
      "learning_rate": 1.8e-06,
      "loss": 1.4634,
      "step": 90
    },
    {
      "epoch": 2.05,
      "grad_norm": 11.670525775431027,
      "learning_rate": 1.82e-06,
      "loss": 1.2869,
      "step": 91
    },
    {
      "epoch": 2.07,
      "grad_norm": 19.036151423939565,
      "learning_rate": 1.84e-06,
      "loss": 1.4018,
      "step": 92
    },
    {
      "epoch": 2.09,
      "grad_norm": 12.989617529943626,
      "learning_rate": 1.86e-06,
      "loss": 1.354,
      "step": 93
    },
    {
      "epoch": 2.12,
      "grad_norm": 13.461044054279371,
      "learning_rate": 1.8799999999999998e-06,
      "loss": 1.1984,
      "step": 94
    },
    {
      "epoch": 2.14,
      "grad_norm": 15.14966533026854,
      "learning_rate": 1.8999999999999998e-06,
      "loss": 1.2233,
      "step": 95
    },
    {
      "epoch": 2.16,
      "grad_norm": 16.64522841989231,
      "learning_rate": 1.92e-06,
      "loss": 1.2439,
      "step": 96
    },
    {
      "epoch": 2.19,
      "grad_norm": 15.286892650701205,
      "learning_rate": 1.94e-06,
      "loss": 1.312,
      "step": 97
    },
    {
      "epoch": 2.21,
      "grad_norm": 17.83944388305422,
      "learning_rate": 1.96e-06,
      "loss": 1.4154,
      "step": 98
    },
    {
      "epoch": 2.23,
      "grad_norm": 19.7098985928153,
      "learning_rate": 1.98e-06,
      "loss": 1.2883,
      "step": 99
    },
    {
      "epoch": 2.23,
      "eval_loss": 1.5585265159606934,
      "eval_runtime": 0.7291,
      "eval_samples_per_second": 26.059,
      "eval_steps_per_second": 4.115,
      "step": 99
    },
    {
      "epoch": 2.26,
      "grad_norm": 12.323486383746712,
      "learning_rate": 2e-06,
      "loss": 1.2074,
      "step": 100
    },
    {
      "epoch": 2.28,
      "grad_norm": 12.53366621130023,
      "learning_rate": 1.9996268812619105e-06,
      "loss": 1.2052,
      "step": 101
    },
    {
      "epoch": 2.3,
      "grad_norm": 13.525403457800772,
      "learning_rate": 1.998507803482828e-06,
      "loss": 1.443,
      "step": 102
    },
    {
      "epoch": 2.33,
      "grad_norm": 21.496984225945436,
      "learning_rate": 1.9966436017605294e-06,
      "loss": 1.2814,
      "step": 103
    },
    {
      "epoch": 2.35,
      "grad_norm": 13.853473081890478,
      "learning_rate": 1.9940356672322033e-06,
      "loss": 1.1953,
      "step": 104
    },
    {
      "epoch": 2.37,
      "grad_norm": 16.848081467071964,
      "learning_rate": 1.9906859460363304e-06,
      "loss": 1.079,
      "step": 105
    },
    {
      "epoch": 2.4,
      "grad_norm": 18.08619313399252,
      "learning_rate": 1.986596937860402e-06,
      "loss": 1.1758,
      "step": 106
    },
    {
      "epoch": 2.42,
      "grad_norm": 30.916344763492923,
      "learning_rate": 1.9817716940755586e-06,
      "loss": 1.2324,
      "step": 107
    },
    {
      "epoch": 2.44,
      "grad_norm": 17.258511861961132,
      "learning_rate": 1.9762138154595447e-06,
      "loss": 1.1936,
      "step": 108
    },
    {
      "epoch": 2.47,
      "grad_norm": 24.524385733499397,
      "learning_rate": 1.969927449509671e-06,
      "loss": 1.2165,
      "step": 109
    },
    {
      "epoch": 2.49,
      "grad_norm": 26.715644236526586,
      "learning_rate": 1.9629172873477994e-06,
      "loss": 1.2285,
      "step": 110
    },
    {
      "epoch": 2.49,
      "eval_loss": 1.5651321411132812,
      "eval_runtime": 0.7146,
      "eval_samples_per_second": 26.587,
      "eval_steps_per_second": 4.198,
      "step": 110
    },
    {
      "epoch": 2.51,
      "grad_norm": 17.531011515200536,
      "learning_rate": 1.955188560219648e-06,
      "loss": 1.4038,
      "step": 111
    },
    {
      "epoch": 2.53,
      "grad_norm": 18.16843193413544,
      "learning_rate": 1.9467470355910435e-06,
      "loss": 1.1457,
      "step": 112
    },
    {
      "epoch": 2.56,
      "grad_norm": 18.30477919577972,
      "learning_rate": 1.93759901284402e-06,
      "loss": 1.3241,
      "step": 113
    },
    {
      "epoch": 2.58,
      "grad_norm": 15.24159083916747,
      "learning_rate": 1.9277513185759843e-06,
      "loss": 1.1836,
      "step": 114
    },
    {
      "epoch": 2.6,
      "grad_norm": 17.98268651120172,
      "learning_rate": 1.9172113015054528e-06,
      "loss": 1.3287,
      "step": 115
    },
    {
      "epoch": 2.63,
      "grad_norm": 19.765482182043318,
      "learning_rate": 1.9059868269881636e-06,
      "loss": 1.2563,
      "step": 116
    },
    {
      "epoch": 2.65,
      "grad_norm": 15.321519585287346,
      "learning_rate": 1.894086271147651e-06,
      "loss": 1.333,
      "step": 117
    },
    {
      "epoch": 2.67,
      "grad_norm": 15.240451512494225,
      "learning_rate": 1.8815185146246715e-06,
      "loss": 1.303,
      "step": 118
    },
    {
      "epoch": 2.7,
      "grad_norm": 26.618086369471722,
      "learning_rate": 1.8682929359501337e-06,
      "loss": 1.1407,
      "step": 119
    },
    {
      "epoch": 2.72,
      "grad_norm": 16.760378227245127,
      "learning_rate": 1.8544194045464886e-06,
      "loss": 1.3433,
      "step": 120
    },
    {
      "epoch": 2.74,
      "grad_norm": 15.731131741212232,
      "learning_rate": 1.8399082733627965e-06,
      "loss": 1.2074,
      "step": 121
    },
    {
      "epoch": 2.74,
      "eval_loss": 1.563856601715088,
      "eval_runtime": 0.7192,
      "eval_samples_per_second": 26.42,
      "eval_steps_per_second": 4.172,
      "step": 121
    },
    {
      "epoch": 2.77,
      "grad_norm": 12.983444823217722,
      "learning_rate": 1.8247703711489684e-06,
      "loss": 1.3574,
      "step": 122
    },
    {
      "epoch": 2.79,
      "grad_norm": 12.49029286171803,
      "learning_rate": 1.8090169943749474e-06,
      "loss": 1.2959,
      "step": 123
    },
    {
      "epoch": 2.81,
      "grad_norm": 13.615451091420056,
      "learning_rate": 1.792659898800858e-06,
      "loss": 1.3111,
      "step": 124
    },
    {
      "epoch": 2.84,
      "grad_norm": 13.83043214333827,
      "learning_rate": 1.7757112907044198e-06,
      "loss": 1.164,
      "step": 125
    },
    {
      "epoch": 2.86,
      "grad_norm": 17.199617532425503,
      "learning_rate": 1.7581838177721627e-06,
      "loss": 1.2572,
      "step": 126
    },
    {
      "epoch": 2.88,
      "grad_norm": 13.886856649280148,
      "learning_rate": 1.7400905596612518e-06,
      "loss": 1.3808,
      "step": 127
    },
    {
      "epoch": 2.91,
      "grad_norm": 17.01161335716492,
      "learning_rate": 1.7214450182389558e-06,
      "loss": 1.2377,
      "step": 128
    },
    {
      "epoch": 2.93,
      "grad_norm": 16.95998475128064,
      "learning_rate": 1.7022611075070473e-06,
      "loss": 1.3853,
      "step": 129
    },
    {
      "epoch": 2.95,
      "grad_norm": 13.954711140424775,
      "learning_rate": 1.682553143218654e-06,
      "loss": 1.3123,
      "step": 130
    },
    {
      "epoch": 2.98,
      "grad_norm": 12.766235187566373,
      "learning_rate": 1.6623358321953075e-06,
      "loss": 1.3318,
      "step": 131
    },
    {
      "epoch": 3.0,
      "grad_norm": 15.881992031808778,
      "learning_rate": 1.6416242613521608e-06,
      "loss": 1.1427,
      "step": 132
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.5613698959350586,
      "eval_runtime": 0.7121,
      "eval_samples_per_second": 26.682,
      "eval_steps_per_second": 4.213,
      "step": 132
    },
    {
      "epoch": 3.02,
      "grad_norm": 22.32758169934701,
      "learning_rate": 1.620433886439568e-06,
      "loss": 1.2566,
      "step": 133
    },
    {
      "epoch": 3.05,
      "grad_norm": 19.283171374081274,
      "learning_rate": 1.5987805205094225e-06,
      "loss": 1.2843,
      "step": 134
    },
    {
      "epoch": 3.02,
      "grad_norm": 23.43177794733975,
      "learning_rate": 1.5766803221148673e-06,
      "loss": 1.07,
      "step": 135
    },
    {
      "epoch": 3.05,
      "grad_norm": 18.182020692564503,
      "learning_rate": 1.5541497832521748e-06,
      "loss": 1.282,
      "step": 136
    },
    {
      "epoch": 3.07,
      "grad_norm": 20.628541954390826,
      "learning_rate": 1.5312057170538033e-06,
      "loss": 1.3346,
      "step": 137
    },
    {
      "epoch": 3.09,
      "grad_norm": 15.580608816530566,
      "learning_rate": 1.5078652452418061e-06,
      "loss": 1.1438,
      "step": 138
    },
    {
      "epoch": 3.12,
      "grad_norm": 30.651996033534974,
      "learning_rate": 1.4841457853509606e-06,
      "loss": 1.1336,
      "step": 139
    },
    {
      "epoch": 3.14,
      "grad_norm": 27.90625437429977,
      "learning_rate": 1.460065037731152e-06,
      "loss": 1.0438,
      "step": 140
    },
    {
      "epoch": 3.16,
      "grad_norm": 20.028259149281578,
      "learning_rate": 1.435640972338709e-06,
      "loss": 1.0063,
      "step": 141
    },
    {
      "epoch": 3.19,
      "grad_norm": 80.43631627916895,
      "learning_rate": 1.4108918153265483e-06,
      "loss": 1.1825,
      "step": 142
    },
    {
      "epoch": 3.21,
      "grad_norm": 25.77403308079665,
      "learning_rate": 1.3858360354431353e-06,
      "loss": 1.1015,
      "step": 143
    },
    {
      "epoch": 3.21,
      "eval_loss": 1.589799165725708,
      "eval_runtime": 0.7172,
      "eval_samples_per_second": 26.492,
      "eval_steps_per_second": 4.183,
      "step": 143
    },
    {
      "epoch": 3.23,
      "grad_norm": 16.049824385113027,
      "learning_rate": 1.3604923302504146e-06,
      "loss": 1.2436,
      "step": 144
    },
    {
      "epoch": 3.26,
      "grad_norm": 17.554830050600568,
      "learning_rate": 1.334879612170986e-06,
      "loss": 1.2744,
      "step": 145
    },
    {
      "epoch": 3.28,
      "grad_norm": 34.29698177659916,
      "learning_rate": 1.3090169943749473e-06,
      "loss": 1.1353,
      "step": 146
    },
    {
      "epoch": 3.3,
      "grad_norm": 15.066763246839983,
      "learning_rate": 1.28292377651693e-06,
      "loss": 1.0975,
      "step": 147
    },
    {
      "epoch": 3.33,
      "grad_norm": 15.41708692373067,
      "learning_rate": 1.2566194303339736e-06,
      "loss": 1.0563,
      "step": 148
    },
    {
      "epoch": 3.35,
      "grad_norm": 18.267303206961834,
      "learning_rate": 1.2301235851149864e-06,
      "loss": 1.0356,
      "step": 149
    },
    {
      "epoch": 3.37,
      "grad_norm": 20.142637118265448,
      "learning_rate": 1.203456013052634e-06,
      "loss": 0.9916,
      "step": 150
    },
    {
      "epoch": 3.4,
      "grad_norm": 18.348855031228275,
      "learning_rate": 1.1766366144885876e-06,
      "loss": 1.0912,
      "step": 151
    },
    {
      "epoch": 3.42,
      "grad_norm": 22.975817365085188,
      "learning_rate": 1.1496854030631443e-06,
      "loss": 1.2215,
      "step": 152
    },
    {
      "epoch": 3.44,
      "grad_norm": 21.405025341337048,
      "learning_rate": 1.1226224907802983e-06,
      "loss": 1.0011,
      "step": 153
    },
    {
      "epoch": 3.47,
      "grad_norm": 25.38439827494932,
      "learning_rate": 1.09546807299941e-06,
      "loss": 1.0554,
      "step": 154
    },
    {
      "epoch": 3.47,
      "eval_loss": 1.598961353302002,
      "eval_runtime": 0.7053,
      "eval_samples_per_second": 26.939,
      "eval_steps_per_second": 4.253,
      "step": 154
    },
    {
      "epoch": 3.49,
      "grad_norm": 23.869269037708953,
      "learning_rate": 1.068242413364671e-06,
      "loss": 1.0765,
      "step": 155
    },
    {
      "epoch": 3.51,
      "grad_norm": 20.257462245092007,
      "learning_rate": 1.0409658286836142e-06,
      "loss": 1.0582,
      "step": 156
    },
    {
      "epoch": 3.53,
      "grad_norm": 19.46568448101564,
      "learning_rate": 1.013658673765951e-06,
      "loss": 0.9385,
      "step": 157
    },
    {
      "epoch": 3.56,
      "grad_norm": 17.633329114330536,
      "learning_rate": 9.863413262340491e-07,
      "loss": 1.0655,
      "step": 158
    },
    {
      "epoch": 3.58,
      "grad_norm": 18.360830228231016,
      "learning_rate": 9.590341713163857e-07,
      "loss": 1.0585,
      "step": 159
    },
    {
      "epoch": 3.6,
      "grad_norm": 28.280116948987985,
      "learning_rate": 9.317575866353291e-07,
      "loss": 1.0745,
      "step": 160
    },
    {
      "epoch": 3.63,
      "grad_norm": 18.714484593323697,
      "learning_rate": 9.045319270005899e-07,
      "loss": 1.1066,
      "step": 161
    },
    {
      "epoch": 3.65,
      "grad_norm": 18.493407853427207,
      "learning_rate": 8.773775092197017e-07,
      "loss": 1.1487,
      "step": 162
    },
    {
      "epoch": 3.67,
      "grad_norm": 15.418345317006398,
      "learning_rate": 8.503145969368561e-07,
      "loss": 1.0612,
      "step": 163
    },
    {
      "epoch": 3.7,
      "grad_norm": 20.396322689348853,
      "learning_rate": 8.233633855114126e-07,
      "loss": 1.2003,
      "step": 164
    },
    {
      "epoch": 3.72,
      "grad_norm": 17.509296672645167,
      "learning_rate": 7.965439869473663e-07,
      "loss": 1.1675,
      "step": 165
    },
    {
      "epoch": 3.72,
      "eval_loss": 1.5823198556900024,
      "eval_runtime": 0.7074,
      "eval_samples_per_second": 26.859,
      "eval_steps_per_second": 4.241,
      "step": 165
    },
    {
      "epoch": 3.74,
      "grad_norm": 17.874492077847012,
      "learning_rate": 7.698764148850136e-07,
      "loss": 1.1659,
      "step": 166
    },
    {
      "epoch": 3.77,
      "grad_norm": 14.51843668106554,
      "learning_rate": 7.433805696660265e-07,
      "loss": 1.2677,
      "step": 167
    },
    {
      "epoch": 3.79,
      "grad_norm": 16.411484470021765,
      "learning_rate": 7.170762234830698e-07,
      "loss": 1.0716,
      "step": 168
    },
    {
      "epoch": 3.81,
      "grad_norm": 15.081980158065493,
      "learning_rate": 6.909830056250526e-07,
      "loss": 1.0398,
      "step": 169
    },
    {
      "epoch": 3.84,
      "grad_norm": 36.853088696666596,
      "learning_rate": 6.651203878290138e-07,
      "loss": 1.1363,
      "step": 170
    },
    {
      "epoch": 3.86,
      "grad_norm": 20.85086144147437,
      "learning_rate": 6.395076697495854e-07,
      "loss": 1.0982,
      "step": 171
    },
    {
      "epoch": 3.88,
      "grad_norm": 20.688913164535432,
      "learning_rate": 6.141639645568645e-07,
      "loss": 1.2441,
      "step": 172
    },
    {
      "epoch": 3.91,
      "grad_norm": 18.59793479693209,
      "learning_rate": 5.891081846734518e-07,
      "loss": 1.2716,
      "step": 173
    },
    {
      "epoch": 3.93,
      "grad_norm": 17.721440079083937,
      "learning_rate": 5.643590276612909e-07,
      "loss": 1.0584,
      "step": 174
    },
    {
      "epoch": 3.95,
      "grad_norm": 15.00406388227531,
      "learning_rate": 5.399349622688478e-07,
      "loss": 1.1342,
      "step": 175
    },
    {
      "epoch": 3.98,
      "grad_norm": 25.699720756705826,
      "learning_rate": 5.158542146490399e-07,
      "loss": 1.0228,
      "step": 176
    },
    {
      "epoch": 3.98,
      "eval_loss": 1.59492826461792,
      "eval_runtime": 0.7093,
      "eval_samples_per_second": 26.788,
      "eval_steps_per_second": 4.23,
      "step": 176
    },
    {
      "epoch": 4.0,
      "grad_norm": 83.83203479931613,
      "learning_rate": 4.921347547581939e-07,
      "loss": 1.0583,
      "step": 177
    },
    {
      "epoch": 4.02,
      "grad_norm": 18.908590376838315,
      "learning_rate": 4.687942829461968e-07,
      "loss": 1.2002,
      "step": 178
    },
    {
      "epoch": 4.05,
      "grad_norm": 20.093904912894295,
      "learning_rate": 4.458502167478253e-07,
      "loss": 1.1312,
      "step": 179
    },
    {
      "epoch": 4.02,
      "grad_norm": 17.927361470853445,
      "learning_rate": 4.233196778851329e-07,
      "loss": 0.9887,
      "step": 180
    },
    {
      "epoch": 4.05,
      "grad_norm": 17.500466476762753,
      "learning_rate": 4.0121947949057745e-07,
      "loss": 1.0448,
      "step": 181
    },
    {
      "epoch": 4.07,
      "grad_norm": 20.450518926551336,
      "learning_rate": 3.7956611356043187e-07,
      "loss": 1.0033,
      "step": 182
    },
    {
      "epoch": 4.09,
      "grad_norm": 13.154322829642174,
      "learning_rate": 3.5837573864783886e-07,
      "loss": 1.0149,
      "step": 183
    },
    {
      "epoch": 4.12,
      "grad_norm": 15.437488138912448,
      "learning_rate": 3.376641678046925e-07,
      "loss": 0.9763,
      "step": 184
    },
    {
      "epoch": 4.14,
      "grad_norm": 15.105733912044274,
      "learning_rate": 3.174468567813461e-07,
      "loss": 1.0967,
      "step": 185
    },
    {
      "epoch": 4.16,
      "grad_norm": 17.305766755283663,
      "learning_rate": 2.977388924929529e-07,
      "loss": 1.1039,
      "step": 186
    },
    {
      "epoch": 4.19,
      "grad_norm": 16.231545635905064,
      "learning_rate": 2.785549817610443e-07,
      "loss": 1.0462,
      "step": 187
    },
    {
      "epoch": 4.19,
      "eval_loss": 1.603925347328186,
      "eval_runtime": 0.7063,
      "eval_samples_per_second": 26.901,
      "eval_steps_per_second": 4.248,
      "step": 187
    },
    {
      "epoch": 4.21,
      "grad_norm": 18.893987339054704,
      "learning_rate": 2.5990944033874805e-07,
      "loss": 1.0632,
      "step": 188
    },
    {
      "epoch": 4.23,
      "grad_norm": 17.44980507116009,
      "learning_rate": 2.418161822278374e-07,
      "loss": 0.9842,
      "step": 189
    },
    {
      "epoch": 4.26,
      "grad_norm": 29.138435113761794,
      "learning_rate": 2.2428870929558007e-07,
      "loss": 1.0093,
      "step": 190
    },
    {
      "epoch": 4.28,
      "grad_norm": 16.019392658965238,
      "learning_rate": 2.0734010119914192e-07,
      "loss": 1.1514,
      "step": 191
    },
    {
      "epoch": 4.3,
      "grad_norm": 18.422606371985193,
      "learning_rate": 1.9098300562505264e-07,
      "loss": 0.9936,
      "step": 192
    },
    {
      "epoch": 4.33,
      "grad_norm": 20.29935346804679,
      "learning_rate": 1.7522962885103143e-07,
      "loss": 0.9865,
      "step": 193
    },
    {
      "epoch": 4.35,
      "grad_norm": 20.824832412759804,
      "learning_rate": 1.600917266372035e-07,
      "loss": 0.9231,
      "step": 194
    },
    {
      "epoch": 4.37,
      "grad_norm": 21.027061101922552,
      "learning_rate": 1.4558059545351142e-07,
      "loss": 1.1464,
      "step": 195
    },
    {
      "epoch": 4.4,
      "grad_norm": 17.71341082614252,
      "learning_rate": 1.3170706404986641e-07,
      "loss": 1.0501,
      "step": 196
    },
    {
      "epoch": 4.42,
      "grad_norm": 40.59586545440542,
      "learning_rate": 1.1848148537532842e-07,
      "loss": 0.8546,
      "step": 197
    },
    {
      "epoch": 4.44,
      "grad_norm": 15.527142785649184,
      "learning_rate": 1.0591372885234884e-07,
      "loss": 1.0623,
      "step": 198
    },
    {
      "epoch": 4.44,
      "eval_loss": 1.6127262115478516,
      "eval_runtime": 0.7139,
      "eval_samples_per_second": 26.613,
      "eval_steps_per_second": 4.202,
      "step": 198
    },
    {
      "epoch": 4.47,
      "grad_norm": 17.44495563338529,
      "learning_rate": 9.401317301183653e-08,
      "loss": 1.0214,
      "step": 199
    },
    {
      "epoch": 4.49,
      "grad_norm": 16.79562586198273,
      "learning_rate": 8.278869849454717e-08,
      "loss": 1.062,
      "step": 200
    },
    {
      "epoch": 4.51,
      "grad_norm": 37.42592455907486,
      "learning_rate": 7.224868142401541e-08,
      "loss": 1.0987,
      "step": 201
    },
    {
      "epoch": 4.53,
      "grad_norm": 18.88865561746405,
      "learning_rate": 6.240098715597975e-08,
      "loss": 1.1737,
      "step": 202
    },
    {
      "epoch": 4.56,
      "grad_norm": 16.06520526829645,
      "learning_rate": 5.325296440895621e-08,
      "loss": 1.0698,
      "step": 203
    },
    {
      "epoch": 4.58,
      "grad_norm": 16.96266292755209,
      "learning_rate": 4.4811439780351954e-08,
      "loss": 1.0868,
      "step": 204
    },
    {
      "epoch": 4.6,
      "grad_norm": 21.607421080544366,
      "learning_rate": 3.708271265220087e-08,
      "loss": 1.0023,
      "step": 205
    },
    {
      "epoch": 4.63,
      "grad_norm": 37.09802951566717,
      "learning_rate": 3.0072550490328754e-08,
      "loss": 1.0426,
      "step": 206
    },
    {
      "epoch": 4.65,
      "grad_norm": 19.227406904456235,
      "learning_rate": 2.3786184540455445e-08,
      "loss": 0.99,
      "step": 207
    },
    {
      "epoch": 4.67,
      "grad_norm": 27.515824637265553,
      "learning_rate": 1.8228305924441466e-08,
      "loss": 1.0157,
      "step": 208
    },
    {
      "epoch": 4.7,
      "grad_norm": 17.81534294061714,
      "learning_rate": 1.3403062139598077e-08,
      "loss": 1.1305,
      "step": 209
    },
    {
      "epoch": 4.7,
      "eval_loss": 1.6108512878417969,
      "eval_runtime": 0.7173,
      "eval_samples_per_second": 26.487,
      "eval_steps_per_second": 4.182,
      "step": 209
    },
    {
      "epoch": 4.72,
      "grad_norm": 20.179310179641224,
      "learning_rate": 9.314053963669244e-09,
      "loss": 1.1015,
      "step": 210
    },
    {
      "epoch": 4.74,
      "grad_norm": 17.981551146678783,
      "learning_rate": 5.964332767796399e-09,
      "loss": 0.959,
      "step": 211
    },
    {
      "epoch": 4.77,
      "grad_norm": 65.99980024827727,
      "learning_rate": 3.356398239470426e-09,
      "loss": 1.062,
      "step": 212
    },
    {
      "epoch": 4.79,
      "grad_norm": 19.48904424180376,
      "learning_rate": 1.4921965171720286e-09,
      "loss": 1.0008,
      "step": 213
    },
    {
      "epoch": 4.81,
      "grad_norm": 17.408148670571457,
      "learning_rate": 3.731187380893175e-10,
      "loss": 0.9879,
      "step": 214
    },
    {
      "epoch": 4.84,
      "grad_norm": 20.859206021085225,
      "learning_rate": 0.0,
      "loss": 0.9305,
      "step": 215
    }
  ],
  "logging_steps": 1,
  "max_steps": 215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 43,
  "total_flos": 3.005727219331891e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}