{
  "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": 1.8943578004837036,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 0.8676,
      "step": 1
    },
    {
      "epoch": 0.013636363636363636,
      "grad_norm": 7.775813102722168,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 0.8513,
      "step": 2
    },
    {
      "epoch": 0.020454545454545454,
      "grad_norm": 1.768803596496582,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 0.8339,
      "step": 3
    },
    {
      "epoch": 0.02727272727272727,
      "grad_norm": 1.7032263278961182,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.8348,
      "step": 4
    },
    {
      "epoch": 0.03409090909090909,
      "grad_norm": 1.8244796991348267,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 0.8687,
      "step": 5
    },
    {
      "epoch": 0.04090909090909091,
      "grad_norm": 1.7780181169509888,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.8113,
      "step": 6
    },
    {
      "epoch": 0.04772727272727273,
      "grad_norm": 1.8362191915512085,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 0.8463,
      "step": 7
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 1.6640979051589966,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.8336,
      "step": 8
    },
    {
      "epoch": 0.06136363636363636,
      "grad_norm": 1.8013464212417603,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 0.8572,
      "step": 9
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 1.7237999439239502,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.8501,
      "step": 10
    },
    {
      "epoch": 0.075,
      "grad_norm": 1.989346981048584,
      "learning_rate": 5.5e-07,
      "loss": 0.8615,
      "step": 11
    },
    {
      "epoch": 0.08181818181818182,
      "grad_norm": 2.0312082767486572,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.858,
      "step": 12
    },
    {
      "epoch": 0.08863636363636364,
      "grad_norm": 1.6921299695968628,
      "learning_rate": 6.5e-07,
      "loss": 0.8577,
      "step": 13
    },
    {
      "epoch": 0.09545454545454546,
      "grad_norm": 2.4207160472869873,
      "learning_rate": 7.000000000000001e-07,
      "loss": 0.8564,
      "step": 14
    },
    {
      "epoch": 0.10227272727272728,
      "grad_norm": 1.7572585344314575,
      "learning_rate": 7.5e-07,
      "loss": 0.8409,
      "step": 15
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 1.6135950088500977,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.8086,
      "step": 16
    },
    {
      "epoch": 0.1159090909090909,
      "grad_norm": 2.226036787033081,
      "learning_rate": 8.500000000000001e-07,
      "loss": 0.8106,
      "step": 17
    },
    {
      "epoch": 0.12272727272727273,
      "grad_norm": 1.7164231538772583,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.8494,
      "step": 18
    },
    {
      "epoch": 0.12954545454545455,
      "grad_norm": 1.6572000980377197,
      "learning_rate": 9.500000000000001e-07,
      "loss": 0.8023,
      "step": 19
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 1.5672118663787842,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.787,
      "step": 20
    },
    {
      "epoch": 0.1431818181818182,
      "grad_norm": 1.5080257654190063,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 0.8105,
      "step": 21
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.484892725944519,
      "learning_rate": 1.1e-06,
      "loss": 0.8258,
      "step": 22
    },
    {
      "epoch": 0.15681818181818183,
      "grad_norm": 1.4591134786605835,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 0.8032,
      "step": 23
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 1.5506278276443481,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.8236,
      "step": 24
    },
    {
      "epoch": 0.17045454545454544,
      "grad_norm": 1.639350414276123,
      "learning_rate": 1.25e-06,
      "loss": 0.8185,
      "step": 25
    },
    {
      "epoch": 0.17727272727272728,
      "grad_norm": 1.592640995979309,
      "learning_rate": 1.3e-06,
      "loss": 0.7898,
      "step": 26
    },
    {
      "epoch": 0.18409090909090908,
      "grad_norm": 1.5280641317367554,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.7731,
      "step": 27
    },
    {
      "epoch": 0.19090909090909092,
      "grad_norm": 1.4015443325042725,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.7956,
      "step": 28
    },
    {
      "epoch": 0.19772727272727272,
      "grad_norm": 1.4890056848526,
      "learning_rate": 1.45e-06,
      "loss": 0.7838,
      "step": 29
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 2.4770750999450684,
      "learning_rate": 1.5e-06,
      "loss": 0.7766,
      "step": 30
    },
    {
      "epoch": 0.21136363636363636,
      "grad_norm": 1.5863685607910156,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.7353,
      "step": 31
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 1.058114767074585,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.7237,
      "step": 32
    },
    {
      "epoch": 0.225,
      "grad_norm": 1.5869101285934448,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.7597,
      "step": 33
    },
    {
      "epoch": 0.2318181818181818,
      "grad_norm": 1.0012413263320923,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.7388,
      "step": 34
    },
    {
      "epoch": 0.23863636363636365,
      "grad_norm": 1.118056058883667,
      "learning_rate": 1.75e-06,
      "loss": 0.7786,
      "step": 35
    },
    {
      "epoch": 0.24545454545454545,
      "grad_norm": 1.0648820400238037,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.7502,
      "step": 36
    },
    {
      "epoch": 0.25227272727272726,
      "grad_norm": 0.9440382719039917,
      "learning_rate": 1.85e-06,
      "loss": 0.6942,
      "step": 37
    },
    {
      "epoch": 0.2590909090909091,
      "grad_norm": 0.8300187587738037,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.7312,
      "step": 38
    },
    {
      "epoch": 0.26590909090909093,
      "grad_norm": 0.8296191692352295,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.7461,
      "step": 39
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.7797508239746094,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.7234,
      "step": 40
    },
    {
      "epoch": 0.27954545454545454,
      "grad_norm": 0.7335019707679749,
      "learning_rate": 2.05e-06,
      "loss": 0.6927,
      "step": 41
    },
    {
      "epoch": 0.2863636363636364,
      "grad_norm": 0.7062106728553772,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.6552,
      "step": 42
    },
    {
      "epoch": 0.29318181818181815,
      "grad_norm": 1.2342087030410767,
      "learning_rate": 2.15e-06,
      "loss": 0.6959,
      "step": 43
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.8967597484588623,
      "learning_rate": 2.2e-06,
      "loss": 0.704,
      "step": 44
    },
    {
      "epoch": 0.3068181818181818,
      "grad_norm": 0.7228404879570007,
      "learning_rate": 2.25e-06,
      "loss": 0.6777,
      "step": 45
    },
    {
      "epoch": 0.31363636363636366,
      "grad_norm": 0.6731488704681396,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.6652,
      "step": 46
    },
    {
      "epoch": 0.32045454545454544,
      "grad_norm": 0.71966952085495,
      "learning_rate": 2.35e-06,
      "loss": 0.7281,
      "step": 47
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.7057356238365173,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.6476,
      "step": 48
    },
    {
      "epoch": 0.3340909090909091,
      "grad_norm": 0.6346054077148438,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.6865,
      "step": 49
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.6938223838806152,
      "learning_rate": 2.5e-06,
      "loss": 0.6808,
      "step": 50
    },
    {
      "epoch": 0.3477272727272727,
      "grad_norm": 0.7425184845924377,
      "learning_rate": 2.55e-06,
      "loss": 0.7074,
      "step": 51
    },
    {
      "epoch": 0.35454545454545455,
      "grad_norm": 0.6743818521499634,
      "learning_rate": 2.6e-06,
      "loss": 0.657,
      "step": 52
    },
    {
      "epoch": 0.3613636363636364,
      "grad_norm": 0.6785942316055298,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.6768,
      "step": 53
    },
    {
      "epoch": 0.36818181818181817,
      "grad_norm": 0.586974024772644,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.651,
      "step": 54
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.5727331042289734,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.669,
      "step": 55
    },
    {
      "epoch": 0.38181818181818183,
      "grad_norm": 0.7333543300628662,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.6571,
      "step": 56
    },
    {
      "epoch": 0.3886363636363636,
      "grad_norm": 0.5710961818695068,
      "learning_rate": 2.85e-06,
      "loss": 0.6475,
      "step": 57
    },
    {
      "epoch": 0.39545454545454545,
      "grad_norm": 0.5614489912986755,
      "learning_rate": 2.9e-06,
      "loss": 0.6314,
      "step": 58
    },
    {
      "epoch": 0.4022727272727273,
      "grad_norm": 0.5007341504096985,
      "learning_rate": 2.95e-06,
      "loss": 0.6346,
      "step": 59
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.54221510887146,
      "learning_rate": 3e-06,
      "loss": 0.6715,
      "step": 60
    },
    {
      "epoch": 0.4159090909090909,
      "grad_norm": 0.5177039504051208,
      "learning_rate": 3.05e-06,
      "loss": 0.6459,
      "step": 61
    },
    {
      "epoch": 0.42272727272727273,
      "grad_norm": 0.4741189181804657,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.592,
      "step": 62
    },
    {
      "epoch": 0.42954545454545456,
      "grad_norm": 0.5637328028678894,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.6459,
      "step": 63
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.5478869676589966,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.6447,
      "step": 64
    },
    {
      "epoch": 0.4431818181818182,
      "grad_norm": 0.5483130216598511,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.6319,
      "step": 65
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.478081613779068,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.6102,
      "step": 66
    },
    {
      "epoch": 0.45681818181818185,
      "grad_norm": 0.4777645766735077,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.5986,
      "step": 67
    },
    {
      "epoch": 0.4636363636363636,
      "grad_norm": 0.5291482210159302,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.6314,
      "step": 68
    },
    {
      "epoch": 0.47045454545454546,
      "grad_norm": 0.5224051475524902,
      "learning_rate": 3.45e-06,
      "loss": 0.6278,
      "step": 69
    },
    {
      "epoch": 0.4772727272727273,
      "grad_norm": 0.6474127173423767,
      "learning_rate": 3.5e-06,
      "loss": 0.6398,
      "step": 70
    },
    {
      "epoch": 0.48409090909090907,
      "grad_norm": 0.5060178637504578,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.5936,
      "step": 71
    },
    {
      "epoch": 0.4909090909090909,
      "grad_norm": 3.0769243240356445,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.5975,
      "step": 72
    },
    {
      "epoch": 0.49772727272727274,
      "grad_norm": 0.5319749116897583,
      "learning_rate": 3.65e-06,
      "loss": 0.6119,
      "step": 73
    },
    {
      "epoch": 0.5045454545454545,
      "grad_norm": 0.6745399236679077,
      "learning_rate": 3.7e-06,
      "loss": 0.6213,
      "step": 74
    },
    {
      "epoch": 0.5113636363636364,
      "grad_norm": 0.5156731009483337,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.6262,
      "step": 75
    },
    {
      "epoch": 0.5181818181818182,
      "grad_norm": 0.9138725399971008,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.6244,
      "step": 76
    },
    {
      "epoch": 0.525,
      "grad_norm": 0.4362037777900696,
      "learning_rate": 3.85e-06,
      "loss": 0.5874,
      "step": 77
    },
    {
      "epoch": 0.5318181818181819,
      "grad_norm": 0.4674088954925537,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.615,
      "step": 78
    },
    {
      "epoch": 0.5386363636363637,
      "grad_norm": 0.4590819180011749,
      "learning_rate": 3.95e-06,
      "loss": 0.6003,
      "step": 79
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.5145031809806824,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6079,
      "step": 80
    },
    {
      "epoch": 0.5522727272727272,
      "grad_norm": 0.46660348773002625,
      "learning_rate": 4.05e-06,
      "loss": 0.6174,
      "step": 81
    },
    {
      "epoch": 0.5590909090909091,
      "grad_norm": 0.48053789138793945,
      "learning_rate": 4.1e-06,
      "loss": 0.6232,
      "step": 82
    },
    {
      "epoch": 0.5659090909090909,
      "grad_norm": 0.540793776512146,
      "learning_rate": 4.15e-06,
      "loss": 0.619,
      "step": 83
    },
    {
      "epoch": 0.5727272727272728,
      "grad_norm": 0.4925222396850586,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.5838,
      "step": 84
    },
    {
      "epoch": 0.5795454545454546,
      "grad_norm": 0.44989290833473206,
      "learning_rate": 4.25e-06,
      "loss": 0.5972,
      "step": 85
    },
    {
      "epoch": 0.5863636363636363,
      "grad_norm": 0.42691388726234436,
      "learning_rate": 4.3e-06,
      "loss": 0.6046,
      "step": 86
    },
    {
      "epoch": 0.5931818181818181,
      "grad_norm": 0.4512398838996887,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.5828,
      "step": 87
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.44399499893188477,
      "learning_rate": 4.4e-06,
      "loss": 0.6143,
      "step": 88
    },
    {
      "epoch": 0.6068181818181818,
      "grad_norm": 0.46058326959609985,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.6117,
      "step": 89
    },
    {
      "epoch": 0.6136363636363636,
      "grad_norm": 0.8795785903930664,
      "learning_rate": 4.5e-06,
      "loss": 0.6,
      "step": 90
    },
    {
      "epoch": 0.6204545454545455,
      "grad_norm": 0.5148798227310181,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.6041,
      "step": 91
    },
    {
      "epoch": 0.6272727272727273,
      "grad_norm": 0.48829612135887146,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.5492,
      "step": 92
    },
    {
      "epoch": 0.634090909090909,
      "grad_norm": 0.5211894512176514,
      "learning_rate": 4.65e-06,
      "loss": 0.6044,
      "step": 93
    },
    {
      "epoch": 0.6409090909090909,
      "grad_norm": 0.44403275847435,
      "learning_rate": 4.7e-06,
      "loss": 0.5929,
      "step": 94
    },
    {
      "epoch": 0.6477272727272727,
      "grad_norm": 0.6037693619728088,
      "learning_rate": 4.75e-06,
      "loss": 0.6132,
      "step": 95
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.4381515085697174,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.5822,
      "step": 96
    },
    {
      "epoch": 0.6613636363636364,
      "grad_norm": 0.4997427761554718,
      "learning_rate": 4.85e-06,
      "loss": 0.593,
      "step": 97
    },
    {
      "epoch": 0.6681818181818182,
      "grad_norm": 0.440571665763855,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.6072,
      "step": 98
    },
    {
      "epoch": 0.675,
      "grad_norm": 0.5020624995231628,
      "learning_rate": 4.95e-06,
      "loss": 0.5861,
      "step": 99
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.4280160963535309,
      "learning_rate": 5e-06,
      "loss": 0.6163,
      "step": 100
    },
    {
      "epoch": 0.6886363636363636,
      "grad_norm": 0.4584537148475647,
      "learning_rate": 4.9999795126530275e-06,
      "loss": 0.6177,
      "step": 101
    },
    {
      "epoch": 0.6954545454545454,
      "grad_norm": 0.6835049390792847,
      "learning_rate": 4.999918050947891e-06,
      "loss": 0.579,
      "step": 102
    },
    {
      "epoch": 0.7022727272727273,
      "grad_norm": 0.4551607072353363,
      "learning_rate": 4.999815615891943e-06,
      "loss": 0.5927,
      "step": 103
    },
    {
      "epoch": 0.7090909090909091,
      "grad_norm": 0.5893972516059875,
      "learning_rate": 4.9996722091640805e-06,
      "loss": 0.5775,
      "step": 104
    },
    {
      "epoch": 0.7159090909090909,
      "grad_norm": 0.4574092924594879,
      "learning_rate": 4.9994878331147225e-06,
      "loss": 0.5863,
      "step": 105
    },
    {
      "epoch": 0.7227272727272728,
      "grad_norm": 0.5354658365249634,
      "learning_rate": 4.99926249076577e-06,
      "loss": 0.5453,
      "step": 106
    },
    {
      "epoch": 0.7295454545454545,
      "grad_norm": 0.4347354471683502,
      "learning_rate": 4.998996185810557e-06,
      "loss": 0.5913,
      "step": 107
    },
    {
      "epoch": 0.7363636363636363,
      "grad_norm": 0.4487966299057007,
      "learning_rate": 4.998688922613788e-06,
      "loss": 0.5749,
      "step": 108
    },
    {
      "epoch": 0.7431818181818182,
      "grad_norm": 0.42477577924728394,
      "learning_rate": 4.9983407062114695e-06,
      "loss": 0.5761,
      "step": 109
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.4801446497440338,
      "learning_rate": 4.9979515423108255e-06,
      "loss": 0.5977,
      "step": 110
    },
    {
      "epoch": 0.7568181818181818,
      "grad_norm": 0.4876883029937744,
      "learning_rate": 4.997521437290205e-06,
      "loss": 0.5849,
      "step": 111
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.4328872263431549,
      "learning_rate": 4.997050398198977e-06,
      "loss": 0.5988,
      "step": 112
    },
    {
      "epoch": 0.7704545454545455,
      "grad_norm": 0.4332719147205353,
      "learning_rate": 4.996538432757414e-06,
      "loss": 0.6059,
      "step": 113
    },
    {
      "epoch": 0.7772727272727272,
      "grad_norm": 0.4455336630344391,
      "learning_rate": 4.995985549356568e-06,
      "loss": 0.5725,
      "step": 114
    },
    {
      "epoch": 0.7840909090909091,
      "grad_norm": 0.4197766184806824,
      "learning_rate": 4.995391757058129e-06,
      "loss": 0.5715,
      "step": 115
    },
    {
      "epoch": 0.7909090909090909,
      "grad_norm": 0.41945499181747437,
      "learning_rate": 4.99475706559428e-06,
      "loss": 0.5845,
      "step": 116
    },
    {
      "epoch": 0.7977272727272727,
      "grad_norm": 0.42414823174476624,
      "learning_rate": 4.994081485367537e-06,
      "loss": 0.5595,
      "step": 117
    },
    {
      "epoch": 0.8045454545454546,
      "grad_norm": 0.4056423008441925,
      "learning_rate": 4.993365027450576e-06,
      "loss": 0.582,
      "step": 118
    },
    {
      "epoch": 0.8113636363636364,
      "grad_norm": 0.4554205536842346,
      "learning_rate": 4.992607703586058e-06,
      "loss": 0.5591,
      "step": 119
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.4307089149951935,
      "learning_rate": 4.991809526186424e-06,
      "loss": 0.5927,
      "step": 120
    },
    {
      "epoch": 0.825,
      "grad_norm": 0.48133528232574463,
      "learning_rate": 4.990970508333707e-06,
      "loss": 0.5703,
      "step": 121
    },
    {
      "epoch": 0.8318181818181818,
      "grad_norm": 0.48582738637924194,
      "learning_rate": 4.990090663779305e-06,
      "loss": 0.5491,
      "step": 122
    },
    {
      "epoch": 0.8386363636363636,
      "grad_norm": 0.44926196336746216,
      "learning_rate": 4.9891700069437635e-06,
      "loss": 0.5803,
      "step": 123
    },
    {
      "epoch": 0.8454545454545455,
      "grad_norm": 0.4562165141105652,
      "learning_rate": 4.988208552916535e-06,
      "loss": 0.5945,
      "step": 124
    },
    {
      "epoch": 0.8522727272727273,
      "grad_norm": 0.5885360836982727,
      "learning_rate": 4.987206317455734e-06,
      "loss": 0.5632,
      "step": 125
    },
    {
      "epoch": 0.8590909090909091,
      "grad_norm": 0.4525550603866577,
      "learning_rate": 4.986163316987877e-06,
      "loss": 0.5221,
      "step": 126
    },
    {
      "epoch": 0.865909090909091,
      "grad_norm": 0.4545478820800781,
      "learning_rate": 4.985079568607613e-06,
      "loss": 0.587,
      "step": 127
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.4364396333694458,
      "learning_rate": 4.983955090077445e-06,
      "loss": 0.5626,
      "step": 128
    },
    {
      "epoch": 0.8795454545454545,
      "grad_norm": 0.4354369640350342,
      "learning_rate": 4.982789899827439e-06,
      "loss": 0.5674,
      "step": 129
    },
    {
      "epoch": 0.8863636363636364,
      "grad_norm": 0.4822773337364197,
      "learning_rate": 4.9815840169549216e-06,
      "loss": 0.5685,
      "step": 130
    },
    {
      "epoch": 0.8931818181818182,
      "grad_norm": 0.44673025608062744,
      "learning_rate": 4.980337461224164e-06,
      "loss": 0.5733,
      "step": 131
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.6294501423835754,
      "learning_rate": 4.979050253066064e-06,
      "loss": 0.5396,
      "step": 132
    },
    {
      "epoch": 0.9068181818181819,
      "grad_norm": 0.42890027165412903,
      "learning_rate": 4.977722413577802e-06,
      "loss": 0.5718,
      "step": 133
    },
    {
      "epoch": 0.9136363636363637,
      "grad_norm": 0.470587819814682,
      "learning_rate": 4.976353964522509e-06,
      "loss": 0.5705,
      "step": 134
    },
    {
      "epoch": 0.9204545454545454,
      "grad_norm": 0.4632768929004669,
      "learning_rate": 4.974944928328894e-06,
      "loss": 0.5394,
      "step": 135
    },
    {
      "epoch": 0.9272727272727272,
      "grad_norm": 0.5304691195487976,
      "learning_rate": 4.973495328090891e-06,
      "loss": 0.5762,
      "step": 136
    },
    {
      "epoch": 0.9340909090909091,
      "grad_norm": 0.42036354541778564,
      "learning_rate": 4.972005187567267e-06,
      "loss": 0.5649,
      "step": 137
    },
    {
      "epoch": 0.9409090909090909,
      "grad_norm": 0.45189663767814636,
      "learning_rate": 4.970474531181245e-06,
      "loss": 0.5554,
      "step": 138
    },
    {
      "epoch": 0.9477272727272728,
      "grad_norm": 0.47352468967437744,
      "learning_rate": 4.968903384020095e-06,
      "loss": 0.5511,
      "step": 139
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.525702953338623,
      "learning_rate": 4.967291771834727e-06,
      "loss": 0.5777,
      "step": 140
    },
    {
      "epoch": 0.9613636363636363,
      "grad_norm": 0.46146854758262634,
      "learning_rate": 4.965639721039267e-06,
      "loss": 0.5537,
      "step": 141
    },
    {
      "epoch": 0.9681818181818181,
      "grad_norm": 0.5200941562652588,
      "learning_rate": 4.963947258710626e-06,
      "loss": 0.5522,
      "step": 142
    },
    {
      "epoch": 0.975,
      "grad_norm": 0.5260375142097473,
      "learning_rate": 4.962214412588053e-06,
      "loss": 0.5747,
      "step": 143
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.518645703792572,
      "learning_rate": 4.960441211072686e-06,
      "loss": 0.5257,
      "step": 144
    },
    {
      "epoch": 0.9886363636363636,
      "grad_norm": 0.4528891444206238,
      "learning_rate": 4.9586276832270785e-06,
      "loss": 0.5548,
      "step": 145
    },
    {
      "epoch": 0.9954545454545455,
      "grad_norm": 0.5137557983398438,
      "learning_rate": 4.9567738587747314e-06,
      "loss": 0.5526,
      "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
}