{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9954545454545455,
  "eval_steps": 500,
  "global_step": 146,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006818181818181818,
      "grad_norm": 2.020231246948242,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 0.8736,
      "step": 1
    },
    {
      "epoch": 0.013636363636363636,
      "grad_norm": 1.9368854761123657,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 0.8543,
      "step": 2
    },
    {
      "epoch": 0.020454545454545454,
      "grad_norm": 1.908379077911377,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 0.8339,
      "step": 3
    },
    {
      "epoch": 0.02727272727272727,
      "grad_norm": 1.9313658475875854,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.834,
      "step": 4
    },
    {
      "epoch": 0.03409090909090909,
      "grad_norm": 1.983262062072754,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 0.8726,
      "step": 5
    },
    {
      "epoch": 0.04090909090909091,
      "grad_norm": 1.9994115829467773,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.8135,
      "step": 6
    },
    {
      "epoch": 0.04772727272727273,
      "grad_norm": 1.8889026641845703,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 0.8439,
      "step": 7
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 1.9258317947387695,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.84,
      "step": 8
    },
    {
      "epoch": 0.06136363636363636,
      "grad_norm": 1.9654443264007568,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 0.8609,
      "step": 9
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 1.9278813600540161,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.8515,
      "step": 10
    },
    {
      "epoch": 0.075,
      "grad_norm": 1.8698863983154297,
      "learning_rate": 5.5e-07,
      "loss": 0.8632,
      "step": 11
    },
    {
      "epoch": 0.08181818181818182,
      "grad_norm": 2.7078285217285156,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.8643,
      "step": 12
    },
    {
      "epoch": 0.08863636363636364,
      "grad_norm": 1.959272027015686,
      "learning_rate": 6.5e-07,
      "loss": 0.861,
      "step": 13
    },
    {
      "epoch": 0.09545454545454546,
      "grad_norm": 1.8952852487564087,
      "learning_rate": 7.000000000000001e-07,
      "loss": 0.8599,
      "step": 14
    },
    {
      "epoch": 0.10227272727272728,
      "grad_norm": 1.9469462633132935,
      "learning_rate": 7.5e-07,
      "loss": 0.8467,
      "step": 15
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 2.0111300945281982,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.8078,
      "step": 16
    },
    {
      "epoch": 0.1159090909090909,
      "grad_norm": 1.739009141921997,
      "learning_rate": 8.500000000000001e-07,
      "loss": 0.8114,
      "step": 17
    },
    {
      "epoch": 0.12272727272727273,
      "grad_norm": 1.7578809261322021,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.8489,
      "step": 18
    },
    {
      "epoch": 0.12954545454545455,
      "grad_norm": 1.9787132740020752,
      "learning_rate": 9.500000000000001e-07,
      "loss": 0.8052,
      "step": 19
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 1.6380164623260498,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.7882,
      "step": 20
    },
    {
      "epoch": 0.1431818181818182,
      "grad_norm": 1.686877727508545,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 0.8126,
      "step": 21
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.690590739250183,
      "learning_rate": 1.1e-06,
      "loss": 0.8248,
      "step": 22
    },
    {
      "epoch": 0.15681818181818183,
      "grad_norm": 1.612255334854126,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 0.8024,
      "step": 23
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 1.6669739484786987,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.818,
      "step": 24
    },
    {
      "epoch": 0.17045454545454544,
      "grad_norm": 1.7726502418518066,
      "learning_rate": 1.25e-06,
      "loss": 0.8158,
      "step": 25
    },
    {
      "epoch": 0.17727272727272728,
      "grad_norm": 1.5930036306381226,
      "learning_rate": 1.3e-06,
      "loss": 0.7886,
      "step": 26
    },
    {
      "epoch": 0.18409090909090908,
      "grad_norm": 1.5480856895446777,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.7747,
      "step": 27
    },
    {
      "epoch": 0.19090909090909092,
      "grad_norm": 1.3537116050720215,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.7891,
      "step": 28
    },
    {
      "epoch": 0.19772727272727272,
      "grad_norm": 1.3412829637527466,
      "learning_rate": 1.45e-06,
      "loss": 0.7799,
      "step": 29
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 1.237492322921753,
      "learning_rate": 1.5e-06,
      "loss": 0.7768,
      "step": 30
    },
    {
      "epoch": 0.21136363636363636,
      "grad_norm": 1.3467835187911987,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.7344,
      "step": 31
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 1.1665314435958862,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.7152,
      "step": 32
    },
    {
      "epoch": 0.225,
      "grad_norm": 1.2461743354797363,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.758,
      "step": 33
    },
    {
      "epoch": 0.2318181818181818,
      "grad_norm": 1.0343059301376343,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.7362,
      "step": 34
    },
    {
      "epoch": 0.23863636363636365,
      "grad_norm": 1.112117052078247,
      "learning_rate": 1.75e-06,
      "loss": 0.7771,
      "step": 35
    },
    {
      "epoch": 0.24545454545454545,
      "grad_norm": 1.104337453842163,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.7479,
      "step": 36
    },
    {
      "epoch": 0.25227272727272726,
      "grad_norm": 0.9324578642845154,
      "learning_rate": 1.85e-06,
      "loss": 0.6936,
      "step": 37
    },
    {
      "epoch": 0.2590909090909091,
      "grad_norm": 1.0733048915863037,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.7302,
      "step": 38
    },
    {
      "epoch": 0.26590909090909093,
      "grad_norm": 0.8614453673362732,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.7466,
      "step": 39
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.7729659080505371,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.725,
      "step": 40
    },
    {
      "epoch": 0.27954545454545454,
      "grad_norm": 0.9341004490852356,
      "learning_rate": 2.05e-06,
      "loss": 0.6949,
      "step": 41
    },
    {
      "epoch": 0.2863636363636364,
      "grad_norm": 0.6668925881385803,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.6587,
      "step": 42
    },
    {
      "epoch": 0.29318181818181815,
      "grad_norm": 0.681847333908081,
      "learning_rate": 2.15e-06,
      "loss": 0.6984,
      "step": 43
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.6222082376480103,
      "learning_rate": 2.2e-06,
      "loss": 0.7063,
      "step": 44
    },
    {
      "epoch": 0.3068181818181818,
      "grad_norm": 0.790607213973999,
      "learning_rate": 2.25e-06,
      "loss": 0.6804,
      "step": 45
    },
    {
      "epoch": 0.31363636363636366,
      "grad_norm": 0.6110427379608154,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.6694,
      "step": 46
    },
    {
      "epoch": 0.32045454545454544,
      "grad_norm": 0.6481993794441223,
      "learning_rate": 2.35e-06,
      "loss": 0.7321,
      "step": 47
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.5973438620567322,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.6508,
      "step": 48
    },
    {
      "epoch": 0.3340909090909091,
      "grad_norm": 0.6252740621566772,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.6911,
      "step": 49
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.6826481819152832,
      "learning_rate": 2.5e-06,
      "loss": 0.6855,
      "step": 50
    },
    {
      "epoch": 0.3477272727272727,
      "grad_norm": 0.6307975649833679,
      "learning_rate": 2.55e-06,
      "loss": 0.714,
      "step": 51
    },
    {
      "epoch": 0.35454545454545455,
      "grad_norm": 0.5900976061820984,
      "learning_rate": 2.6e-06,
      "loss": 0.6619,
      "step": 52
    },
    {
      "epoch": 0.3613636363636364,
      "grad_norm": 0.6203920841217041,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.6822,
      "step": 53
    },
    {
      "epoch": 0.36818181818181817,
      "grad_norm": 0.6197589039802551,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.6584,
      "step": 54
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.5921110510826111,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.6739,
      "step": 55
    },
    {
      "epoch": 0.38181818181818183,
      "grad_norm": 0.6215619444847107,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.6631,
      "step": 56
    },
    {
      "epoch": 0.3886363636363636,
      "grad_norm": 0.5495648980140686,
      "learning_rate": 2.85e-06,
      "loss": 0.6531,
      "step": 57
    },
    {
      "epoch": 0.39545454545454545,
      "grad_norm": 0.531947910785675,
      "learning_rate": 2.9e-06,
      "loss": 0.6365,
      "step": 58
    },
    {
      "epoch": 0.4022727272727273,
      "grad_norm": 0.559112548828125,
      "learning_rate": 2.95e-06,
      "loss": 0.6391,
      "step": 59
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.5377560257911682,
      "learning_rate": 3e-06,
      "loss": 0.6775,
      "step": 60
    },
    {
      "epoch": 0.4159090909090909,
      "grad_norm": 0.5167352557182312,
      "learning_rate": 3.05e-06,
      "loss": 0.6518,
      "step": 61
    },
    {
      "epoch": 0.42272727272727273,
      "grad_norm": 0.5483390092849731,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.5972,
      "step": 62
    },
    {
      "epoch": 0.42954545454545456,
      "grad_norm": 0.5687050223350525,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.6515,
      "step": 63
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.9046968817710876,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.6497,
      "step": 64
    },
    {
      "epoch": 0.4431818181818182,
      "grad_norm": 0.5231667757034302,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.6364,
      "step": 65
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.49699342250823975,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.6144,
      "step": 66
    },
    {
      "epoch": 0.45681818181818185,
      "grad_norm": 0.5390080213546753,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.6051,
      "step": 67
    },
    {
      "epoch": 0.4636363636363636,
      "grad_norm": 0.5252938270568848,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.6353,
      "step": 68
    },
    {
      "epoch": 0.47045454545454546,
      "grad_norm": 0.6291780471801758,
      "learning_rate": 3.45e-06,
      "loss": 0.6326,
      "step": 69
    },
    {
      "epoch": 0.4772727272727273,
      "grad_norm": 0.5545375943183899,
      "learning_rate": 3.5e-06,
      "loss": 0.647,
      "step": 70
    },
    {
      "epoch": 0.48409090909090907,
      "grad_norm": 0.47775956988334656,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.5993,
      "step": 71
    },
    {
      "epoch": 0.4909090909090909,
      "grad_norm": 0.5016375184059143,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.6056,
      "step": 72
    },
    {
      "epoch": 0.49772727272727274,
      "grad_norm": 0.4780517816543579,
      "learning_rate": 3.65e-06,
      "loss": 0.6189,
      "step": 73
    },
    {
      "epoch": 0.5045454545454545,
      "grad_norm": 0.5763716697692871,
      "learning_rate": 3.7e-06,
      "loss": 0.6262,
      "step": 74
    },
    {
      "epoch": 0.5113636363636364,
      "grad_norm": 0.5321404337882996,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.6336,
      "step": 75
    },
    {
      "epoch": 0.5181818181818182,
      "grad_norm": 0.4641991853713989,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.6317,
      "step": 76
    },
    {
      "epoch": 0.525,
      "grad_norm": 0.45118412375450134,
      "learning_rate": 3.85e-06,
      "loss": 0.5927,
      "step": 77
    },
    {
      "epoch": 0.5318181818181819,
      "grad_norm": 0.5500645041465759,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.62,
      "step": 78
    },
    {
      "epoch": 0.5386363636363637,
      "grad_norm": 0.5197616219520569,
      "learning_rate": 3.95e-06,
      "loss": 0.6063,
      "step": 79
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.4672992527484894,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6156,
      "step": 80
    },
    {
      "epoch": 0.5522727272727272,
      "grad_norm": 0.5995073318481445,
      "learning_rate": 4.05e-06,
      "loss": 0.6219,
      "step": 81
    },
    {
      "epoch": 0.5590909090909091,
      "grad_norm": 0.5593804717063904,
      "learning_rate": 4.1e-06,
      "loss": 0.6282,
      "step": 82
    },
    {
      "epoch": 0.5659090909090909,
      "grad_norm": 0.7544977068901062,
      "learning_rate": 4.15e-06,
      "loss": 0.6246,
      "step": 83
    },
    {
      "epoch": 0.5727272727272728,
      "grad_norm": 0.45378655195236206,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.5881,
      "step": 84
    },
    {
      "epoch": 0.5795454545454546,
      "grad_norm": 0.4407907724380493,
      "learning_rate": 4.25e-06,
      "loss": 0.6026,
      "step": 85
    },
    {
      "epoch": 0.5863636363636363,
      "grad_norm": 0.4333001673221588,
      "learning_rate": 4.3e-06,
      "loss": 0.6098,
      "step": 86
    },
    {
      "epoch": 0.5931818181818181,
      "grad_norm": 0.45020997524261475,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.5858,
      "step": 87
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.424003541469574,
      "learning_rate": 4.4e-06,
      "loss": 0.6186,
      "step": 88
    },
    {
      "epoch": 0.6068181818181818,
      "grad_norm": 0.427081435918808,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.6164,
      "step": 89
    },
    {
      "epoch": 0.6136363636363636,
      "grad_norm": 0.4430546164512634,
      "learning_rate": 4.5e-06,
      "loss": 0.6049,
      "step": 90
    },
    {
      "epoch": 0.6204545454545455,
      "grad_norm": 0.5469494462013245,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.608,
      "step": 91
    },
    {
      "epoch": 0.6272727272727273,
      "grad_norm": 0.4481559693813324,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.5532,
      "step": 92
    },
    {
      "epoch": 0.634090909090909,
      "grad_norm": 0.6563135981559753,
      "learning_rate": 4.65e-06,
      "loss": 0.6105,
      "step": 93
    },
    {
      "epoch": 0.6409090909090909,
      "grad_norm": 0.4572807252407074,
      "learning_rate": 4.7e-06,
      "loss": 0.5976,
      "step": 94
    },
    {
      "epoch": 0.6477272727272727,
      "grad_norm": 0.4423324167728424,
      "learning_rate": 4.75e-06,
      "loss": 0.616,
      "step": 95
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.6230632066726685,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.5879,
      "step": 96
    },
    {
      "epoch": 0.6613636363636364,
      "grad_norm": 0.461467981338501,
      "learning_rate": 4.85e-06,
      "loss": 0.5992,
      "step": 97
    },
    {
      "epoch": 0.6681818181818182,
      "grad_norm": 0.44455233216285706,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.6138,
      "step": 98
    },
    {
      "epoch": 0.675,
      "grad_norm": 0.47281715273857117,
      "learning_rate": 4.95e-06,
      "loss": 0.59,
      "step": 99
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.46114516258239746,
      "learning_rate": 5e-06,
      "loss": 0.6216,
      "step": 100
    },
    {
      "epoch": 0.6886363636363636,
      "grad_norm": 0.49900761246681213,
      "learning_rate": 4.9999795126530275e-06,
      "loss": 0.6222,
      "step": 101
    },
    {
      "epoch": 0.6954545454545454,
      "grad_norm": 0.4764839708805084,
      "learning_rate": 4.999918050947891e-06,
      "loss": 0.5829,
      "step": 102
    },
    {
      "epoch": 0.7022727272727273,
      "grad_norm": 0.43502742052078247,
      "learning_rate": 4.999815615891943e-06,
      "loss": 0.5982,
      "step": 103
    },
    {
      "epoch": 0.7090909090909091,
      "grad_norm": 0.43318599462509155,
      "learning_rate": 4.9996722091640805e-06,
      "loss": 0.5827,
      "step": 104
    },
    {
      "epoch": 0.7159090909090909,
      "grad_norm": 0.47218361496925354,
      "learning_rate": 4.9994878331147225e-06,
      "loss": 0.5907,
      "step": 105
    },
    {
      "epoch": 0.7227272727272728,
      "grad_norm": 0.48492228984832764,
      "learning_rate": 4.99926249076577e-06,
      "loss": 0.5459,
      "step": 106
    },
    {
      "epoch": 0.7295454545454545,
      "grad_norm": 0.4019850194454193,
      "learning_rate": 4.998996185810557e-06,
      "loss": 0.5957,
      "step": 107
    },
    {
      "epoch": 0.7363636363636363,
      "grad_norm": 0.47361984848976135,
      "learning_rate": 4.998688922613788e-06,
      "loss": 0.579,
      "step": 108
    },
    {
      "epoch": 0.7431818181818182,
      "grad_norm": 0.4612269401550293,
      "learning_rate": 4.9983407062114695e-06,
      "loss": 0.5814,
      "step": 109
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.45558398962020874,
      "learning_rate": 4.9979515423108255e-06,
      "loss": 0.6036,
      "step": 110
    },
    {
      "epoch": 0.7568181818181818,
      "grad_norm": 0.41492199897766113,
      "learning_rate": 4.997521437290205e-06,
      "loss": 0.5891,
      "step": 111
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.4484409689903259,
      "learning_rate": 4.997050398198977e-06,
      "loss": 0.6031,
      "step": 112
    },
    {
      "epoch": 0.7704545454545455,
      "grad_norm": 0.42671382427215576,
      "learning_rate": 4.996538432757414e-06,
      "loss": 0.6106,
      "step": 113
    },
    {
      "epoch": 0.7772727272727272,
      "grad_norm": 0.4222075343132019,
      "learning_rate": 4.995985549356568e-06,
      "loss": 0.5774,
      "step": 114
    },
    {
      "epoch": 0.7840909090909091,
      "grad_norm": 0.421021431684494,
      "learning_rate": 4.995391757058129e-06,
      "loss": 0.5754,
      "step": 115
    },
    {
      "epoch": 0.7909090909090909,
      "grad_norm": 0.4215952754020691,
      "learning_rate": 4.99475706559428e-06,
      "loss": 0.5895,
      "step": 116
    },
    {
      "epoch": 0.7977272727272727,
      "grad_norm": 0.42652982473373413,
      "learning_rate": 4.994081485367537e-06,
      "loss": 0.5646,
      "step": 117
    },
    {
      "epoch": 0.8045454545454546,
      "grad_norm": 0.4145742654800415,
      "learning_rate": 4.993365027450576e-06,
      "loss": 0.5862,
      "step": 118
    },
    {
      "epoch": 0.8113636363636364,
      "grad_norm": 0.4754612445831299,
      "learning_rate": 4.992607703586058e-06,
      "loss": 0.5645,
      "step": 119
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.4694959223270416,
      "learning_rate": 4.991809526186424e-06,
      "loss": 0.5989,
      "step": 120
    },
    {
      "epoch": 0.825,
      "grad_norm": 0.4573237895965576,
      "learning_rate": 4.990970508333707e-06,
      "loss": 0.5769,
      "step": 121
    },
    {
      "epoch": 0.8318181818181818,
      "grad_norm": 0.4592607915401459,
      "learning_rate": 4.990090663779305e-06,
      "loss": 0.5529,
      "step": 122
    },
    {
      "epoch": 0.8386363636363636,
      "grad_norm": 0.4325920045375824,
      "learning_rate": 4.9891700069437635e-06,
      "loss": 0.5846,
      "step": 123
    },
    {
      "epoch": 0.8454545454545455,
      "grad_norm": 0.44623467326164246,
      "learning_rate": 4.988208552916535e-06,
      "loss": 0.5997,
      "step": 124
    },
    {
      "epoch": 0.8522727272727273,
      "grad_norm": 0.46071872115135193,
      "learning_rate": 4.987206317455734e-06,
      "loss": 0.5687,
      "step": 125
    },
    {
      "epoch": 0.8590909090909091,
      "grad_norm": 0.43121206760406494,
      "learning_rate": 4.986163316987877e-06,
      "loss": 0.5277,
      "step": 126
    },
    {
      "epoch": 0.865909090909091,
      "grad_norm": 0.4711630046367645,
      "learning_rate": 4.985079568607613e-06,
      "loss": 0.592,
      "step": 127
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.4450221657752991,
      "learning_rate": 4.983955090077445e-06,
      "loss": 0.5656,
      "step": 128
    },
    {
      "epoch": 0.8795454545454545,
      "grad_norm": 0.6546564102172852,
      "learning_rate": 4.982789899827439e-06,
      "loss": 0.572,
      "step": 129
    },
    {
      "epoch": 0.8863636363636364,
      "grad_norm": 0.49622273445129395,
      "learning_rate": 4.9815840169549216e-06,
      "loss": 0.5719,
      "step": 130
    },
    {
      "epoch": 0.8931818181818182,
      "grad_norm": 0.5478544235229492,
      "learning_rate": 4.980337461224164e-06,
      "loss": 0.5774,
      "step": 131
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.4340018033981323,
      "learning_rate": 4.979050253066064e-06,
      "loss": 0.5444,
      "step": 132
    },
    {
      "epoch": 0.9068181818181819,
      "grad_norm": 0.4243793189525604,
      "learning_rate": 4.977722413577802e-06,
      "loss": 0.5759,
      "step": 133
    },
    {
      "epoch": 0.9136363636363637,
      "grad_norm": 0.45201942324638367,
      "learning_rate": 4.976353964522509e-06,
      "loss": 0.5746,
      "step": 134
    },
    {
      "epoch": 0.9204545454545454,
      "grad_norm": 0.42892220616340637,
      "learning_rate": 4.974944928328894e-06,
      "loss": 0.544,
      "step": 135
    },
    {
      "epoch": 0.9272727272727272,
      "grad_norm": 0.43185824155807495,
      "learning_rate": 4.973495328090891e-06,
      "loss": 0.5803,
      "step": 136
    },
    {
      "epoch": 0.9340909090909091,
      "grad_norm": 0.5512542724609375,
      "learning_rate": 4.972005187567267e-06,
      "loss": 0.5694,
      "step": 137
    },
    {
      "epoch": 0.9409090909090909,
      "grad_norm": 0.4836059808731079,
      "learning_rate": 4.970474531181245e-06,
      "loss": 0.5581,
      "step": 138
    },
    {
      "epoch": 0.9477272727272728,
      "grad_norm": 0.4508282244205475,
      "learning_rate": 4.968903384020095e-06,
      "loss": 0.5553,
      "step": 139
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.4764733612537384,
      "learning_rate": 4.967291771834727e-06,
      "loss": 0.5798,
      "step": 140
    },
    {
      "epoch": 0.9613636363636363,
      "grad_norm": 0.463468074798584,
      "learning_rate": 4.965639721039267e-06,
      "loss": 0.559,
      "step": 141
    },
    {
      "epoch": 0.9681818181818181,
      "grad_norm": 0.4655650854110718,
      "learning_rate": 4.963947258710626e-06,
      "loss": 0.5576,
      "step": 142
    },
    {
      "epoch": 0.975,
      "grad_norm": 0.4651234745979309,
      "learning_rate": 4.962214412588053e-06,
      "loss": 0.5792,
      "step": 143
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.43080538511276245,
      "learning_rate": 4.960441211072686e-06,
      "loss": 0.5314,
      "step": 144
    },
    {
      "epoch": 0.9886363636363636,
      "grad_norm": 0.4403238594532013,
      "learning_rate": 4.9586276832270785e-06,
      "loss": 0.5592,
      "step": 145
    },
    {
      "epoch": 0.9954545454545455,
      "grad_norm": 0.43968647718429565,
      "learning_rate": 4.9567738587747314e-06,
      "loss": 0.5573,
      "step": 146
    }
  ],
  "logging_steps": 1,
  "max_steps": 876,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 146,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.39244756481029e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}