{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.01953125,
  "eval_steps": 500,
  "global_step": 256,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00390625,
      "grad_norm": 988.0331420898438,
      "learning_rate": 3.846153846153847e-06,
      "loss": 23.0443,
      "step": 1
    },
    {
      "epoch": 0.0078125,
      "grad_norm": 1018.0032958984375,
      "learning_rate": 7.692307692307694e-06,
      "loss": 22.2415,
      "step": 2
    },
    {
      "epoch": 0.01171875,
      "grad_norm": 905.46435546875,
      "learning_rate": 1.153846153846154e-05,
      "loss": 23.9407,
      "step": 3
    },
    {
      "epoch": 0.015625,
      "grad_norm": 772.3015747070312,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 20.3585,
      "step": 4
    },
    {
      "epoch": 0.01953125,
      "grad_norm": 1083.967529296875,
      "learning_rate": 1.923076923076923e-05,
      "loss": 17.7004,
      "step": 5
    },
    {
      "epoch": 0.0234375,
      "grad_norm": 518.4392700195312,
      "learning_rate": 2.307692307692308e-05,
      "loss": 14.8905,
      "step": 6
    },
    {
      "epoch": 0.02734375,
      "grad_norm": 588.9624633789062,
      "learning_rate": 2.6923076923076923e-05,
      "loss": 15.46,
      "step": 7
    },
    {
      "epoch": 0.03125,
      "grad_norm": 291.337646484375,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 11.7233,
      "step": 8
    },
    {
      "epoch": 0.03515625,
      "grad_norm": 243.8762969970703,
      "learning_rate": 3.461538461538462e-05,
      "loss": 9.8939,
      "step": 9
    },
    {
      "epoch": 0.0390625,
      "grad_norm": 306.4288635253906,
      "learning_rate": 3.846153846153846e-05,
      "loss": 10.5548,
      "step": 10
    },
    {
      "epoch": 0.04296875,
      "grad_norm": 138.4855194091797,
      "learning_rate": 4.230769230769231e-05,
      "loss": 7.1429,
      "step": 11
    },
    {
      "epoch": 0.046875,
      "grad_norm": 79.80815887451172,
      "learning_rate": 4.615384615384616e-05,
      "loss": 7.0453,
      "step": 12
    },
    {
      "epoch": 0.05078125,
      "grad_norm": 95.14498901367188,
      "learning_rate": 5e-05,
      "loss": 6.2978,
      "step": 13
    },
    {
      "epoch": 0.0546875,
      "grad_norm": 76.86641693115234,
      "learning_rate": 4.9794238683127575e-05,
      "loss": 6.9177,
      "step": 14
    },
    {
      "epoch": 0.05859375,
      "grad_norm": 90.26302337646484,
      "learning_rate": 4.958847736625515e-05,
      "loss": 5.7372,
      "step": 15
    },
    {
      "epoch": 0.0625,
      "grad_norm": 51.85117721557617,
      "learning_rate": 4.938271604938271e-05,
      "loss": 5.7694,
      "step": 16
    },
    {
      "epoch": 0.06640625,
      "grad_norm": 28.343177795410156,
      "learning_rate": 4.9176954732510286e-05,
      "loss": 5.8857,
      "step": 17
    },
    {
      "epoch": 0.0703125,
      "grad_norm": 28.591285705566406,
      "learning_rate": 4.8971193415637865e-05,
      "loss": 5.2027,
      "step": 18
    },
    {
      "epoch": 0.07421875,
      "grad_norm": 23.616016387939453,
      "learning_rate": 4.876543209876544e-05,
      "loss": 4.8946,
      "step": 19
    },
    {
      "epoch": 0.078125,
      "grad_norm": 20.2352294921875,
      "learning_rate": 4.855967078189301e-05,
      "loss": 5.0189,
      "step": 20
    },
    {
      "epoch": 0.08203125,
      "grad_norm": 16.59236717224121,
      "learning_rate": 4.835390946502058e-05,
      "loss": 4.9116,
      "step": 21
    },
    {
      "epoch": 0.0859375,
      "grad_norm": 15.008003234863281,
      "learning_rate": 4.814814814814815e-05,
      "loss": 4.8674,
      "step": 22
    },
    {
      "epoch": 0.08984375,
      "grad_norm": 11.656904220581055,
      "learning_rate": 4.794238683127572e-05,
      "loss": 4.96,
      "step": 23
    },
    {
      "epoch": 0.09375,
      "grad_norm": 17.49643898010254,
      "learning_rate": 4.773662551440329e-05,
      "loss": 4.7911,
      "step": 24
    },
    {
      "epoch": 0.09765625,
      "grad_norm": 12.967889785766602,
      "learning_rate": 4.7530864197530866e-05,
      "loss": 4.7574,
      "step": 25
    },
    {
      "epoch": 0.1015625,
      "grad_norm": 13.78781795501709,
      "learning_rate": 4.732510288065844e-05,
      "loss": 4.5257,
      "step": 26
    },
    {
      "epoch": 0.10546875,
      "grad_norm": 14.40069580078125,
      "learning_rate": 4.711934156378601e-05,
      "loss": 4.6842,
      "step": 27
    },
    {
      "epoch": 0.109375,
      "grad_norm": 8.558459281921387,
      "learning_rate": 4.691358024691358e-05,
      "loss": 4.4912,
      "step": 28
    },
    {
      "epoch": 0.11328125,
      "grad_norm": 9.563591003417969,
      "learning_rate": 4.6707818930041156e-05,
      "loss": 4.3927,
      "step": 29
    },
    {
      "epoch": 0.1171875,
      "grad_norm": 13.471641540527344,
      "learning_rate": 4.650205761316873e-05,
      "loss": 4.446,
      "step": 30
    },
    {
      "epoch": 0.12109375,
      "grad_norm": 8.875003814697266,
      "learning_rate": 4.62962962962963e-05,
      "loss": 4.4367,
      "step": 31
    },
    {
      "epoch": 0.125,
      "grad_norm": 9.281575202941895,
      "learning_rate": 4.609053497942387e-05,
      "loss": 4.4643,
      "step": 32
    },
    {
      "epoch": 0.12890625,
      "grad_norm": 9.402353286743164,
      "learning_rate": 4.5884773662551446e-05,
      "loss": 4.4036,
      "step": 33
    },
    {
      "epoch": 0.1328125,
      "grad_norm": 8.509848594665527,
      "learning_rate": 4.567901234567901e-05,
      "loss": 4.3953,
      "step": 34
    },
    {
      "epoch": 0.13671875,
      "grad_norm": 9.05785846710205,
      "learning_rate": 4.5473251028806584e-05,
      "loss": 4.4259,
      "step": 35
    },
    {
      "epoch": 0.140625,
      "grad_norm": 7.090909481048584,
      "learning_rate": 4.5267489711934157e-05,
      "loss": 4.2375,
      "step": 36
    },
    {
      "epoch": 0.14453125,
      "grad_norm": 10.807791709899902,
      "learning_rate": 4.506172839506173e-05,
      "loss": 4.3719,
      "step": 37
    },
    {
      "epoch": 0.1484375,
      "grad_norm": 13.562170028686523,
      "learning_rate": 4.48559670781893e-05,
      "loss": 4.6153,
      "step": 38
    },
    {
      "epoch": 0.15234375,
      "grad_norm": 11.16930103302002,
      "learning_rate": 4.4650205761316874e-05,
      "loss": 4.4007,
      "step": 39
    },
    {
      "epoch": 0.15625,
      "grad_norm": 12.779727935791016,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 4.5876,
      "step": 40
    },
    {
      "epoch": 0.16015625,
      "grad_norm": 14.613138198852539,
      "learning_rate": 4.423868312757202e-05,
      "loss": 4.3842,
      "step": 41
    },
    {
      "epoch": 0.1640625,
      "grad_norm": 16.920902252197266,
      "learning_rate": 4.403292181069959e-05,
      "loss": 4.2888,
      "step": 42
    },
    {
      "epoch": 0.16796875,
      "grad_norm": 23.178911209106445,
      "learning_rate": 4.3827160493827164e-05,
      "loss": 4.4708,
      "step": 43
    },
    {
      "epoch": 0.171875,
      "grad_norm": 28.53046989440918,
      "learning_rate": 4.3621399176954737e-05,
      "loss": 4.5108,
      "step": 44
    },
    {
      "epoch": 0.17578125,
      "grad_norm": 19.8005428314209,
      "learning_rate": 4.341563786008231e-05,
      "loss": 4.4592,
      "step": 45
    },
    {
      "epoch": 0.1796875,
      "grad_norm": 12.320777893066406,
      "learning_rate": 4.3209876543209875e-05,
      "loss": 4.5041,
      "step": 46
    },
    {
      "epoch": 0.18359375,
      "grad_norm": 8.350976943969727,
      "learning_rate": 4.300411522633745e-05,
      "loss": 4.3769,
      "step": 47
    },
    {
      "epoch": 0.1875,
      "grad_norm": 14.553681373596191,
      "learning_rate": 4.279835390946502e-05,
      "loss": 4.683,
      "step": 48
    },
    {
      "epoch": 0.19140625,
      "grad_norm": 13.202040672302246,
      "learning_rate": 4.259259259259259e-05,
      "loss": 4.4271,
      "step": 49
    },
    {
      "epoch": 0.1953125,
      "grad_norm": 12.252931594848633,
      "learning_rate": 4.2386831275720165e-05,
      "loss": 4.202,
      "step": 50
    },
    {
      "epoch": 0.19921875,
      "grad_norm": 9.770834922790527,
      "learning_rate": 4.2181069958847744e-05,
      "loss": 4.4271,
      "step": 51
    },
    {
      "epoch": 0.203125,
      "grad_norm": 10.324782371520996,
      "learning_rate": 4.197530864197531e-05,
      "loss": 4.3385,
      "step": 52
    },
    {
      "epoch": 0.20703125,
      "grad_norm": 8.983942031860352,
      "learning_rate": 4.176954732510288e-05,
      "loss": 4.2885,
      "step": 53
    },
    {
      "epoch": 0.2109375,
      "grad_norm": 8.984896659851074,
      "learning_rate": 4.1563786008230455e-05,
      "loss": 4.446,
      "step": 54
    },
    {
      "epoch": 0.21484375,
      "grad_norm": 10.578001022338867,
      "learning_rate": 4.135802469135803e-05,
      "loss": 4.3787,
      "step": 55
    },
    {
      "epoch": 0.21875,
      "grad_norm": 12.245546340942383,
      "learning_rate": 4.11522633744856e-05,
      "loss": 4.1896,
      "step": 56
    },
    {
      "epoch": 0.22265625,
      "grad_norm": 12.414233207702637,
      "learning_rate": 4.094650205761317e-05,
      "loss": 4.4919,
      "step": 57
    },
    {
      "epoch": 0.2265625,
      "grad_norm": 10.887884140014648,
      "learning_rate": 4.074074074074074e-05,
      "loss": 4.2051,
      "step": 58
    },
    {
      "epoch": 0.23046875,
      "grad_norm": 11.619287490844727,
      "learning_rate": 4.053497942386831e-05,
      "loss": 4.015,
      "step": 59
    },
    {
      "epoch": 0.234375,
      "grad_norm": 16.54395294189453,
      "learning_rate": 4.032921810699588e-05,
      "loss": 3.9459,
      "step": 60
    },
    {
      "epoch": 0.23828125,
      "grad_norm": 22.401296615600586,
      "learning_rate": 4.012345679012346e-05,
      "loss": 3.8599,
      "step": 61
    },
    {
      "epoch": 0.2421875,
      "grad_norm": 30.748231887817383,
      "learning_rate": 3.9917695473251035e-05,
      "loss": 3.8411,
      "step": 62
    },
    {
      "epoch": 0.24609375,
      "grad_norm": 48.33995056152344,
      "learning_rate": 3.971193415637861e-05,
      "loss": 3.8338,
      "step": 63
    },
    {
      "epoch": 0.25,
      "grad_norm": 40.25141906738281,
      "learning_rate": 3.950617283950617e-05,
      "loss": 3.7575,
      "step": 64
    },
    {
      "epoch": 0.25390625,
      "grad_norm": 70.64269256591797,
      "learning_rate": 3.9300411522633746e-05,
      "loss": 3.7886,
      "step": 65
    },
    {
      "epoch": 0.2578125,
      "grad_norm": 46.51031494140625,
      "learning_rate": 3.909465020576132e-05,
      "loss": 3.7727,
      "step": 66
    },
    {
      "epoch": 0.26171875,
      "grad_norm": 44.5860481262207,
      "learning_rate": 3.888888888888889e-05,
      "loss": 3.7284,
      "step": 67
    },
    {
      "epoch": 0.265625,
      "grad_norm": 37.13584899902344,
      "learning_rate": 3.868312757201646e-05,
      "loss": 3.7974,
      "step": 68
    },
    {
      "epoch": 0.26953125,
      "grad_norm": 17.04970932006836,
      "learning_rate": 3.8477366255144036e-05,
      "loss": 3.7399,
      "step": 69
    },
    {
      "epoch": 0.2734375,
      "grad_norm": 25.48470687866211,
      "learning_rate": 3.82716049382716e-05,
      "loss": 3.6582,
      "step": 70
    },
    {
      "epoch": 0.27734375,
      "grad_norm": 15.296791076660156,
      "learning_rate": 3.806584362139918e-05,
      "loss": 3.759,
      "step": 71
    },
    {
      "epoch": 0.28125,
      "grad_norm": 18.959625244140625,
      "learning_rate": 3.786008230452675e-05,
      "loss": 3.6962,
      "step": 72
    },
    {
      "epoch": 0.28515625,
      "grad_norm": 16.249454498291016,
      "learning_rate": 3.7654320987654326e-05,
      "loss": 3.5659,
      "step": 73
    },
    {
      "epoch": 0.2890625,
      "grad_norm": 17.6076602935791,
      "learning_rate": 3.74485596707819e-05,
      "loss": 3.6214,
      "step": 74
    },
    {
      "epoch": 0.29296875,
      "grad_norm": 15.325469017028809,
      "learning_rate": 3.724279835390947e-05,
      "loss": 3.5469,
      "step": 75
    },
    {
      "epoch": 0.296875,
      "grad_norm": 14.967309951782227,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 3.5844,
      "step": 76
    },
    {
      "epoch": 0.30078125,
      "grad_norm": 16.454774856567383,
      "learning_rate": 3.683127572016461e-05,
      "loss": 3.4725,
      "step": 77
    },
    {
      "epoch": 0.3046875,
      "grad_norm": 15.80962085723877,
      "learning_rate": 3.662551440329218e-05,
      "loss": 3.4781,
      "step": 78
    },
    {
      "epoch": 0.30859375,
      "grad_norm": 12.834327697753906,
      "learning_rate": 3.6419753086419754e-05,
      "loss": 3.6498,
      "step": 79
    },
    {
      "epoch": 0.3125,
      "grad_norm": 12.81863784790039,
      "learning_rate": 3.6213991769547327e-05,
      "loss": 3.4208,
      "step": 80
    },
    {
      "epoch": 0.31640625,
      "grad_norm": 16.791345596313477,
      "learning_rate": 3.60082304526749e-05,
      "loss": 3.4432,
      "step": 81
    },
    {
      "epoch": 0.3203125,
      "grad_norm": 20.827123641967773,
      "learning_rate": 3.580246913580247e-05,
      "loss": 3.4386,
      "step": 82
    },
    {
      "epoch": 0.32421875,
      "grad_norm": 14.668889999389648,
      "learning_rate": 3.5596707818930044e-05,
      "loss": 3.3887,
      "step": 83
    },
    {
      "epoch": 0.328125,
      "grad_norm": 17.22427749633789,
      "learning_rate": 3.539094650205762e-05,
      "loss": 3.6215,
      "step": 84
    },
    {
      "epoch": 0.33203125,
      "grad_norm": 16.612550735473633,
      "learning_rate": 3.518518518518519e-05,
      "loss": 3.4215,
      "step": 85
    },
    {
      "epoch": 0.3359375,
      "grad_norm": 15.173816680908203,
      "learning_rate": 3.497942386831276e-05,
      "loss": 3.3305,
      "step": 86
    },
    {
      "epoch": 0.33984375,
      "grad_norm": 18.891874313354492,
      "learning_rate": 3.4773662551440334e-05,
      "loss": 3.4129,
      "step": 87
    },
    {
      "epoch": 0.34375,
      "grad_norm": 19.012630462646484,
      "learning_rate": 3.45679012345679e-05,
      "loss": 3.4039,
      "step": 88
    },
    {
      "epoch": 0.34765625,
      "grad_norm": 25.285091400146484,
      "learning_rate": 3.436213991769547e-05,
      "loss": 3.7148,
      "step": 89
    },
    {
      "epoch": 0.3515625,
      "grad_norm": 23.138742446899414,
      "learning_rate": 3.4156378600823045e-05,
      "loss": 3.3594,
      "step": 90
    },
    {
      "epoch": 0.35546875,
      "grad_norm": 24.770191192626953,
      "learning_rate": 3.395061728395062e-05,
      "loss": 3.3106,
      "step": 91
    },
    {
      "epoch": 0.359375,
      "grad_norm": 17.597614288330078,
      "learning_rate": 3.374485596707819e-05,
      "loss": 3.2024,
      "step": 92
    },
    {
      "epoch": 0.36328125,
      "grad_norm": 13.329920768737793,
      "learning_rate": 3.353909465020576e-05,
      "loss": 3.196,
      "step": 93
    },
    {
      "epoch": 0.3671875,
      "grad_norm": 20.01732635498047,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.3282,
      "step": 94
    },
    {
      "epoch": 0.37109375,
      "grad_norm": 21.501489639282227,
      "learning_rate": 3.312757201646091e-05,
      "loss": 3.2842,
      "step": 95
    },
    {
      "epoch": 0.375,
      "grad_norm": 15.159469604492188,
      "learning_rate": 3.292181069958848e-05,
      "loss": 3.149,
      "step": 96
    },
    {
      "epoch": 0.37890625,
      "grad_norm": 15.139326095581055,
      "learning_rate": 3.271604938271605e-05,
      "loss": 3.2335,
      "step": 97
    },
    {
      "epoch": 0.3828125,
      "grad_norm": 14.6196870803833,
      "learning_rate": 3.2510288065843625e-05,
      "loss": 3.104,
      "step": 98
    },
    {
      "epoch": 0.38671875,
      "grad_norm": 12.317699432373047,
      "learning_rate": 3.230452674897119e-05,
      "loss": 3.1088,
      "step": 99
    },
    {
      "epoch": 0.390625,
      "grad_norm": 17.009883880615234,
      "learning_rate": 3.209876543209876e-05,
      "loss": 3.1713,
      "step": 100
    },
    {
      "epoch": 0.39453125,
      "grad_norm": 22.170177459716797,
      "learning_rate": 3.1893004115226336e-05,
      "loss": 3.1348,
      "step": 101
    },
    {
      "epoch": 0.3984375,
      "grad_norm": 18.459367752075195,
      "learning_rate": 3.168724279835391e-05,
      "loss": 3.1625,
      "step": 102
    },
    {
      "epoch": 0.40234375,
      "grad_norm": 11.8716402053833,
      "learning_rate": 3.148148148148148e-05,
      "loss": 3.0979,
      "step": 103
    },
    {
      "epoch": 0.40625,
      "grad_norm": 16.9968204498291,
      "learning_rate": 3.127572016460906e-05,
      "loss": 3.1705,
      "step": 104
    },
    {
      "epoch": 0.41015625,
      "grad_norm": 18.078325271606445,
      "learning_rate": 3.1069958847736626e-05,
      "loss": 3.1945,
      "step": 105
    },
    {
      "epoch": 0.4140625,
      "grad_norm": 16.14826202392578,
      "learning_rate": 3.08641975308642e-05,
      "loss": 3.2458,
      "step": 106
    },
    {
      "epoch": 0.41796875,
      "grad_norm": 14.381550788879395,
      "learning_rate": 3.065843621399177e-05,
      "loss": 3.1335,
      "step": 107
    },
    {
      "epoch": 0.421875,
      "grad_norm": 11.909482955932617,
      "learning_rate": 3.0452674897119343e-05,
      "loss": 3.09,
      "step": 108
    },
    {
      "epoch": 0.42578125,
      "grad_norm": 17.585634231567383,
      "learning_rate": 3.0246913580246916e-05,
      "loss": 3.0548,
      "step": 109
    },
    {
      "epoch": 0.4296875,
      "grad_norm": 15.303757667541504,
      "learning_rate": 3.0041152263374488e-05,
      "loss": 2.9545,
      "step": 110
    },
    {
      "epoch": 0.43359375,
      "grad_norm": 15.899727821350098,
      "learning_rate": 2.9835390946502057e-05,
      "loss": 3.0344,
      "step": 111
    },
    {
      "epoch": 0.4375,
      "grad_norm": 12.18794059753418,
      "learning_rate": 2.962962962962963e-05,
      "loss": 3.1163,
      "step": 112
    },
    {
      "epoch": 0.44140625,
      "grad_norm": 15.14059066772461,
      "learning_rate": 2.9423868312757202e-05,
      "loss": 3.0572,
      "step": 113
    },
    {
      "epoch": 0.4453125,
      "grad_norm": 16.42298698425293,
      "learning_rate": 2.9218106995884775e-05,
      "loss": 2.9781,
      "step": 114
    },
    {
      "epoch": 0.44921875,
      "grad_norm": 16.090763092041016,
      "learning_rate": 2.9012345679012347e-05,
      "loss": 3.1644,
      "step": 115
    },
    {
      "epoch": 0.453125,
      "grad_norm": 18.76362419128418,
      "learning_rate": 2.880658436213992e-05,
      "loss": 3.0987,
      "step": 116
    },
    {
      "epoch": 0.45703125,
      "grad_norm": 17.354793548583984,
      "learning_rate": 2.860082304526749e-05,
      "loss": 2.9983,
      "step": 117
    },
    {
      "epoch": 0.4609375,
      "grad_norm": 13.282272338867188,
      "learning_rate": 2.839506172839506e-05,
      "loss": 3.0733,
      "step": 118
    },
    {
      "epoch": 0.46484375,
      "grad_norm": 21.229665756225586,
      "learning_rate": 2.8189300411522634e-05,
      "loss": 3.0484,
      "step": 119
    },
    {
      "epoch": 0.46875,
      "grad_norm": 16.58381462097168,
      "learning_rate": 2.7983539094650207e-05,
      "loss": 3.1174,
      "step": 120
    },
    {
      "epoch": 0.47265625,
      "grad_norm": 15.544482231140137,
      "learning_rate": 2.777777777777778e-05,
      "loss": 3.1705,
      "step": 121
    },
    {
      "epoch": 0.4765625,
      "grad_norm": 15.846022605895996,
      "learning_rate": 2.757201646090535e-05,
      "loss": 3.0341,
      "step": 122
    },
    {
      "epoch": 0.48046875,
      "grad_norm": 21.867094039916992,
      "learning_rate": 2.736625514403292e-05,
      "loss": 2.9884,
      "step": 123
    },
    {
      "epoch": 0.484375,
      "grad_norm": 13.162125587463379,
      "learning_rate": 2.7160493827160493e-05,
      "loss": 3.0612,
      "step": 124
    },
    {
      "epoch": 0.48828125,
      "grad_norm": 11.88615608215332,
      "learning_rate": 2.6954732510288066e-05,
      "loss": 2.9845,
      "step": 125
    },
    {
      "epoch": 0.4921875,
      "grad_norm": 11.516526222229004,
      "learning_rate": 2.6748971193415638e-05,
      "loss": 2.9974,
      "step": 126
    },
    {
      "epoch": 0.49609375,
      "grad_norm": 13.762920379638672,
      "learning_rate": 2.654320987654321e-05,
      "loss": 3.0515,
      "step": 127
    },
    {
      "epoch": 0.5,
      "grad_norm": 13.856005668640137,
      "learning_rate": 2.6337448559670787e-05,
      "loss": 3.0096,
      "step": 128
    },
    {
      "epoch": 0.50390625,
      "grad_norm": 12.380202293395996,
      "learning_rate": 2.6131687242798352e-05,
      "loss": 3.0274,
      "step": 129
    },
    {
      "epoch": 0.5078125,
      "grad_norm": 15.164392471313477,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 2.9838,
      "step": 130
    },
    {
      "epoch": 0.51171875,
      "grad_norm": 15.10387134552002,
      "learning_rate": 2.5720164609053497e-05,
      "loss": 3.1058,
      "step": 131
    },
    {
      "epoch": 0.515625,
      "grad_norm": 11.87817096710205,
      "learning_rate": 2.551440329218107e-05,
      "loss": 3.0164,
      "step": 132
    },
    {
      "epoch": 0.51953125,
      "grad_norm": 17.242656707763672,
      "learning_rate": 2.5308641975308646e-05,
      "loss": 2.9376,
      "step": 133
    },
    {
      "epoch": 0.5234375,
      "grad_norm": 20.221240997314453,
      "learning_rate": 2.510288065843622e-05,
      "loss": 3.0894,
      "step": 134
    },
    {
      "epoch": 0.52734375,
      "grad_norm": 12.36820125579834,
      "learning_rate": 2.4897119341563787e-05,
      "loss": 3.0347,
      "step": 135
    },
    {
      "epoch": 0.53125,
      "grad_norm": 14.862237930297852,
      "learning_rate": 2.4691358024691357e-05,
      "loss": 3.0826,
      "step": 136
    },
    {
      "epoch": 0.53515625,
      "grad_norm": 14.29667854309082,
      "learning_rate": 2.4485596707818932e-05,
      "loss": 3.0467,
      "step": 137
    },
    {
      "epoch": 0.5390625,
      "grad_norm": 15.347952842712402,
      "learning_rate": 2.4279835390946505e-05,
      "loss": 2.9934,
      "step": 138
    },
    {
      "epoch": 0.54296875,
      "grad_norm": 19.236717224121094,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 2.8921,
      "step": 139
    },
    {
      "epoch": 0.546875,
      "grad_norm": 13.943548202514648,
      "learning_rate": 2.3868312757201647e-05,
      "loss": 3.1285,
      "step": 140
    },
    {
      "epoch": 0.55078125,
      "grad_norm": 15.554057121276855,
      "learning_rate": 2.366255144032922e-05,
      "loss": 2.9709,
      "step": 141
    },
    {
      "epoch": 0.5546875,
      "grad_norm": 15.124194145202637,
      "learning_rate": 2.345679012345679e-05,
      "loss": 2.9845,
      "step": 142
    },
    {
      "epoch": 0.55859375,
      "grad_norm": 15.458159446716309,
      "learning_rate": 2.3251028806584364e-05,
      "loss": 2.9581,
      "step": 143
    },
    {
      "epoch": 0.5625,
      "grad_norm": 11.531893730163574,
      "learning_rate": 2.3045267489711937e-05,
      "loss": 3.0545,
      "step": 144
    },
    {
      "epoch": 0.56640625,
      "grad_norm": 16.634984970092773,
      "learning_rate": 2.2839506172839506e-05,
      "loss": 2.9772,
      "step": 145
    },
    {
      "epoch": 0.5703125,
      "grad_norm": 13.670973777770996,
      "learning_rate": 2.2633744855967078e-05,
      "loss": 2.9478,
      "step": 146
    },
    {
      "epoch": 0.57421875,
      "grad_norm": 13.582576751708984,
      "learning_rate": 2.242798353909465e-05,
      "loss": 3.1053,
      "step": 147
    },
    {
      "epoch": 0.578125,
      "grad_norm": 17.05980110168457,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 2.9789,
      "step": 148
    },
    {
      "epoch": 0.58203125,
      "grad_norm": 13.586709976196289,
      "learning_rate": 2.2016460905349796e-05,
      "loss": 2.9268,
      "step": 149
    },
    {
      "epoch": 0.5859375,
      "grad_norm": 14.885200500488281,
      "learning_rate": 2.1810699588477368e-05,
      "loss": 3.0281,
      "step": 150
    },
    {
      "epoch": 0.58984375,
      "grad_norm": 14.411493301391602,
      "learning_rate": 2.1604938271604937e-05,
      "loss": 2.9164,
      "step": 151
    },
    {
      "epoch": 0.59375,
      "grad_norm": 16.72563934326172,
      "learning_rate": 2.139917695473251e-05,
      "loss": 2.9586,
      "step": 152
    },
    {
      "epoch": 0.59765625,
      "grad_norm": 11.668434143066406,
      "learning_rate": 2.1193415637860082e-05,
      "loss": 3.0239,
      "step": 153
    },
    {
      "epoch": 0.6015625,
      "grad_norm": 11.849235534667969,
      "learning_rate": 2.0987654320987655e-05,
      "loss": 2.9665,
      "step": 154
    },
    {
      "epoch": 0.60546875,
      "grad_norm": 17.961620330810547,
      "learning_rate": 2.0781893004115227e-05,
      "loss": 3.0192,
      "step": 155
    },
    {
      "epoch": 0.609375,
      "grad_norm": 13.321170806884766,
      "learning_rate": 2.05761316872428e-05,
      "loss": 2.9901,
      "step": 156
    },
    {
      "epoch": 0.61328125,
      "grad_norm": 12.714600563049316,
      "learning_rate": 2.037037037037037e-05,
      "loss": 2.9933,
      "step": 157
    },
    {
      "epoch": 0.6171875,
      "grad_norm": 11.27708625793457,
      "learning_rate": 2.016460905349794e-05,
      "loss": 2.9186,
      "step": 158
    },
    {
      "epoch": 0.62109375,
      "grad_norm": 11.366385459899902,
      "learning_rate": 1.9958847736625517e-05,
      "loss": 2.9615,
      "step": 159
    },
    {
      "epoch": 0.625,
      "grad_norm": 14.28786849975586,
      "learning_rate": 1.9753086419753087e-05,
      "loss": 3.0847,
      "step": 160
    },
    {
      "epoch": 0.62890625,
      "grad_norm": 17.186941146850586,
      "learning_rate": 1.954732510288066e-05,
      "loss": 3.1361,
      "step": 161
    },
    {
      "epoch": 0.6328125,
      "grad_norm": 12.188273429870605,
      "learning_rate": 1.934156378600823e-05,
      "loss": 3.0134,
      "step": 162
    },
    {
      "epoch": 0.63671875,
      "grad_norm": 18.98809051513672,
      "learning_rate": 1.91358024691358e-05,
      "loss": 2.904,
      "step": 163
    },
    {
      "epoch": 0.640625,
      "grad_norm": 12.578585624694824,
      "learning_rate": 1.8930041152263377e-05,
      "loss": 2.9072,
      "step": 164
    },
    {
      "epoch": 0.64453125,
      "grad_norm": 13.295378684997559,
      "learning_rate": 1.872427983539095e-05,
      "loss": 3.0163,
      "step": 165
    },
    {
      "epoch": 0.6484375,
      "grad_norm": 16.138151168823242,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 2.9509,
      "step": 166
    },
    {
      "epoch": 0.65234375,
      "grad_norm": 18.39076805114746,
      "learning_rate": 1.831275720164609e-05,
      "loss": 2.9098,
      "step": 167
    },
    {
      "epoch": 0.65625,
      "grad_norm": 19.46346664428711,
      "learning_rate": 1.8106995884773663e-05,
      "loss": 2.9096,
      "step": 168
    },
    {
      "epoch": 0.66015625,
      "grad_norm": 13.3604154586792,
      "learning_rate": 1.7901234567901236e-05,
      "loss": 2.8992,
      "step": 169
    },
    {
      "epoch": 0.6640625,
      "grad_norm": 12.542205810546875,
      "learning_rate": 1.769547325102881e-05,
      "loss": 2.9293,
      "step": 170
    },
    {
      "epoch": 0.66796875,
      "grad_norm": 12.55959415435791,
      "learning_rate": 1.748971193415638e-05,
      "loss": 2.8809,
      "step": 171
    },
    {
      "epoch": 0.671875,
      "grad_norm": 15.57677936553955,
      "learning_rate": 1.728395061728395e-05,
      "loss": 2.7552,
      "step": 172
    },
    {
      "epoch": 0.67578125,
      "grad_norm": 11.344679832458496,
      "learning_rate": 1.7078189300411522e-05,
      "loss": 2.9377,
      "step": 173
    },
    {
      "epoch": 0.6796875,
      "grad_norm": 15.26870059967041,
      "learning_rate": 1.6872427983539095e-05,
      "loss": 2.9145,
      "step": 174
    },
    {
      "epoch": 0.68359375,
      "grad_norm": 12.774370193481445,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.9775,
      "step": 175
    },
    {
      "epoch": 0.6875,
      "grad_norm": 19.02437400817871,
      "learning_rate": 1.646090534979424e-05,
      "loss": 2.9581,
      "step": 176
    },
    {
      "epoch": 0.69140625,
      "grad_norm": 14.445993423461914,
      "learning_rate": 1.6255144032921812e-05,
      "loss": 2.9639,
      "step": 177
    },
    {
      "epoch": 0.6953125,
      "grad_norm": 13.563401222229004,
      "learning_rate": 1.604938271604938e-05,
      "loss": 2.8964,
      "step": 178
    },
    {
      "epoch": 0.69921875,
      "grad_norm": 17.80751609802246,
      "learning_rate": 1.5843621399176954e-05,
      "loss": 3.0603,
      "step": 179
    },
    {
      "epoch": 0.703125,
      "grad_norm": 13.13770866394043,
      "learning_rate": 1.563786008230453e-05,
      "loss": 3.0473,
      "step": 180
    },
    {
      "epoch": 0.70703125,
      "grad_norm": 15.236124038696289,
      "learning_rate": 1.54320987654321e-05,
      "loss": 2.8392,
      "step": 181
    },
    {
      "epoch": 0.7109375,
      "grad_norm": 17.386003494262695,
      "learning_rate": 1.5226337448559672e-05,
      "loss": 2.8805,
      "step": 182
    },
    {
      "epoch": 0.71484375,
      "grad_norm": 16.233539581298828,
      "learning_rate": 1.5020576131687244e-05,
      "loss": 2.9692,
      "step": 183
    },
    {
      "epoch": 0.71875,
      "grad_norm": 19.721954345703125,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 3.0988,
      "step": 184
    },
    {
      "epoch": 0.72265625,
      "grad_norm": 12.52316951751709,
      "learning_rate": 1.4609053497942387e-05,
      "loss": 2.933,
      "step": 185
    },
    {
      "epoch": 0.7265625,
      "grad_norm": 12.95042610168457,
      "learning_rate": 1.440329218106996e-05,
      "loss": 2.927,
      "step": 186
    },
    {
      "epoch": 0.73046875,
      "grad_norm": 12.077346801757812,
      "learning_rate": 1.419753086419753e-05,
      "loss": 2.8952,
      "step": 187
    },
    {
      "epoch": 0.734375,
      "grad_norm": 11.764900207519531,
      "learning_rate": 1.3991769547325103e-05,
      "loss": 2.8488,
      "step": 188
    },
    {
      "epoch": 0.73828125,
      "grad_norm": 13.644368171691895,
      "learning_rate": 1.3786008230452676e-05,
      "loss": 2.8838,
      "step": 189
    },
    {
      "epoch": 0.7421875,
      "grad_norm": 12.35655689239502,
      "learning_rate": 1.3580246913580247e-05,
      "loss": 2.9183,
      "step": 190
    },
    {
      "epoch": 0.74609375,
      "grad_norm": 13.980887413024902,
      "learning_rate": 1.3374485596707819e-05,
      "loss": 2.8803,
      "step": 191
    },
    {
      "epoch": 0.75,
      "grad_norm": 18.003271102905273,
      "learning_rate": 1.3168724279835393e-05,
      "loss": 3.0357,
      "step": 192
    },
    {
      "epoch": 0.75390625,
      "grad_norm": 14.126523971557617,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 2.9313,
      "step": 193
    },
    {
      "epoch": 0.7578125,
      "grad_norm": 12.55939769744873,
      "learning_rate": 1.2757201646090535e-05,
      "loss": 2.9224,
      "step": 194
    },
    {
      "epoch": 0.76171875,
      "grad_norm": 13.05750846862793,
      "learning_rate": 1.255144032921811e-05,
      "loss": 2.9167,
      "step": 195
    },
    {
      "epoch": 0.765625,
      "grad_norm": 16.52781867980957,
      "learning_rate": 1.2345679012345678e-05,
      "loss": 2.8645,
      "step": 196
    },
    {
      "epoch": 0.76953125,
      "grad_norm": 15.458019256591797,
      "learning_rate": 1.2139917695473252e-05,
      "loss": 2.9848,
      "step": 197
    },
    {
      "epoch": 0.7734375,
      "grad_norm": 12.694581985473633,
      "learning_rate": 1.1934156378600823e-05,
      "loss": 3.0691,
      "step": 198
    },
    {
      "epoch": 0.77734375,
      "grad_norm": 11.771615982055664,
      "learning_rate": 1.1728395061728396e-05,
      "loss": 2.9316,
      "step": 199
    },
    {
      "epoch": 0.78125,
      "grad_norm": 15.438037872314453,
      "learning_rate": 1.1522633744855968e-05,
      "loss": 2.9295,
      "step": 200
    },
    {
      "epoch": 0.78515625,
      "grad_norm": 13.371684074401855,
      "learning_rate": 1.1316872427983539e-05,
      "loss": 2.8849,
      "step": 201
    },
    {
      "epoch": 0.7890625,
      "grad_norm": 11.904099464416504,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 2.862,
      "step": 202
    },
    {
      "epoch": 0.79296875,
      "grad_norm": 11.638395309448242,
      "learning_rate": 1.0905349794238684e-05,
      "loss": 2.949,
      "step": 203
    },
    {
      "epoch": 0.796875,
      "grad_norm": 14.490175247192383,
      "learning_rate": 1.0699588477366255e-05,
      "loss": 2.9131,
      "step": 204
    },
    {
      "epoch": 0.80078125,
      "grad_norm": 11.613717079162598,
      "learning_rate": 1.0493827160493827e-05,
      "loss": 2.9497,
      "step": 205
    },
    {
      "epoch": 0.8046875,
      "grad_norm": 13.931456565856934,
      "learning_rate": 1.02880658436214e-05,
      "loss": 2.917,
      "step": 206
    },
    {
      "epoch": 0.80859375,
      "grad_norm": 12.256906509399414,
      "learning_rate": 1.008230452674897e-05,
      "loss": 2.9048,
      "step": 207
    },
    {
      "epoch": 0.8125,
      "grad_norm": 12.851861953735352,
      "learning_rate": 9.876543209876543e-06,
      "loss": 2.9084,
      "step": 208
    },
    {
      "epoch": 0.81640625,
      "grad_norm": 18.05097770690918,
      "learning_rate": 9.670781893004116e-06,
      "loss": 2.802,
      "step": 209
    },
    {
      "epoch": 0.8203125,
      "grad_norm": 12.831151962280273,
      "learning_rate": 9.465020576131688e-06,
      "loss": 2.8659,
      "step": 210
    },
    {
      "epoch": 0.82421875,
      "grad_norm": 11.60468864440918,
      "learning_rate": 9.259259259259259e-06,
      "loss": 2.8285,
      "step": 211
    },
    {
      "epoch": 0.828125,
      "grad_norm": 14.392627716064453,
      "learning_rate": 9.053497942386832e-06,
      "loss": 2.8605,
      "step": 212
    },
    {
      "epoch": 0.83203125,
      "grad_norm": 17.23533821105957,
      "learning_rate": 8.847736625514404e-06,
      "loss": 2.9186,
      "step": 213
    },
    {
      "epoch": 0.8359375,
      "grad_norm": 13.937773704528809,
      "learning_rate": 8.641975308641975e-06,
      "loss": 2.9164,
      "step": 214
    },
    {
      "epoch": 0.83984375,
      "grad_norm": 16.57691764831543,
      "learning_rate": 8.436213991769547e-06,
      "loss": 2.8829,
      "step": 215
    },
    {
      "epoch": 0.84375,
      "grad_norm": 12.391244888305664,
      "learning_rate": 8.23045267489712e-06,
      "loss": 2.8417,
      "step": 216
    },
    {
      "epoch": 0.84765625,
      "grad_norm": 15.762882232666016,
      "learning_rate": 8.02469135802469e-06,
      "loss": 2.871,
      "step": 217
    },
    {
      "epoch": 0.8515625,
      "grad_norm": 16.37859344482422,
      "learning_rate": 7.818930041152265e-06,
      "loss": 2.9265,
      "step": 218
    },
    {
      "epoch": 0.85546875,
      "grad_norm": 21.5294132232666,
      "learning_rate": 7.613168724279836e-06,
      "loss": 2.9628,
      "step": 219
    },
    {
      "epoch": 0.859375,
      "grad_norm": 18.281295776367188,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 2.8301,
      "step": 220
    },
    {
      "epoch": 0.86328125,
      "grad_norm": 16.0869140625,
      "learning_rate": 7.20164609053498e-06,
      "loss": 2.8179,
      "step": 221
    },
    {
      "epoch": 0.8671875,
      "grad_norm": 21.662134170532227,
      "learning_rate": 6.995884773662552e-06,
      "loss": 2.8893,
      "step": 222
    },
    {
      "epoch": 0.87109375,
      "grad_norm": 12.4130277633667,
      "learning_rate": 6.790123456790123e-06,
      "loss": 2.8628,
      "step": 223
    },
    {
      "epoch": 0.875,
      "grad_norm": 15.154963493347168,
      "learning_rate": 6.584362139917697e-06,
      "loss": 2.8991,
      "step": 224
    },
    {
      "epoch": 0.87890625,
      "grad_norm": 12.677474021911621,
      "learning_rate": 6.3786008230452675e-06,
      "loss": 2.9428,
      "step": 225
    },
    {
      "epoch": 0.8828125,
      "grad_norm": 12.973712921142578,
      "learning_rate": 6.172839506172839e-06,
      "loss": 2.8694,
      "step": 226
    },
    {
      "epoch": 0.88671875,
      "grad_norm": 13.162025451660156,
      "learning_rate": 5.967078189300412e-06,
      "loss": 2.8119,
      "step": 227
    },
    {
      "epoch": 0.890625,
      "grad_norm": 13.606464385986328,
      "learning_rate": 5.761316872427984e-06,
      "loss": 2.8455,
      "step": 228
    },
    {
      "epoch": 0.89453125,
      "grad_norm": 17.518091201782227,
      "learning_rate": 5.555555555555556e-06,
      "loss": 2.8708,
      "step": 229
    },
    {
      "epoch": 0.8984375,
      "grad_norm": 13.689889907836914,
      "learning_rate": 5.3497942386831275e-06,
      "loss": 2.8384,
      "step": 230
    },
    {
      "epoch": 0.90234375,
      "grad_norm": 14.69385051727295,
      "learning_rate": 5.1440329218107e-06,
      "loss": 2.8291,
      "step": 231
    },
    {
      "epoch": 0.90625,
      "grad_norm": 17.468791961669922,
      "learning_rate": 4.938271604938272e-06,
      "loss": 2.8588,
      "step": 232
    },
    {
      "epoch": 0.91015625,
      "grad_norm": 14.33683967590332,
      "learning_rate": 4.732510288065844e-06,
      "loss": 2.7762,
      "step": 233
    },
    {
      "epoch": 0.9140625,
      "grad_norm": 17.65381622314453,
      "learning_rate": 4.526748971193416e-06,
      "loss": 2.8697,
      "step": 234
    },
    {
      "epoch": 0.91796875,
      "grad_norm": 17.74317169189453,
      "learning_rate": 4.3209876543209875e-06,
      "loss": 2.8151,
      "step": 235
    },
    {
      "epoch": 0.921875,
      "grad_norm": 20.99629020690918,
      "learning_rate": 4.11522633744856e-06,
      "loss": 2.893,
      "step": 236
    },
    {
      "epoch": 0.92578125,
      "grad_norm": 17.19089698791504,
      "learning_rate": 3.9094650205761325e-06,
      "loss": 2.8025,
      "step": 237
    },
    {
      "epoch": 0.9296875,
      "grad_norm": 12.898162841796875,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 2.9405,
      "step": 238
    },
    {
      "epoch": 0.93359375,
      "grad_norm": 13.902021408081055,
      "learning_rate": 3.497942386831276e-06,
      "loss": 2.8937,
      "step": 239
    },
    {
      "epoch": 0.9375,
      "grad_norm": 13.255682945251465,
      "learning_rate": 3.2921810699588483e-06,
      "loss": 2.7604,
      "step": 240
    },
    {
      "epoch": 0.94140625,
      "grad_norm": 14.98218822479248,
      "learning_rate": 3.0864197530864196e-06,
      "loss": 2.8931,
      "step": 241
    },
    {
      "epoch": 0.9453125,
      "grad_norm": 15.084565162658691,
      "learning_rate": 2.880658436213992e-06,
      "loss": 2.8565,
      "step": 242
    },
    {
      "epoch": 0.94921875,
      "grad_norm": 12.473812103271484,
      "learning_rate": 2.6748971193415637e-06,
      "loss": 2.795,
      "step": 243
    },
    {
      "epoch": 0.953125,
      "grad_norm": 13.222654342651367,
      "learning_rate": 2.469135802469136e-06,
      "loss": 2.8734,
      "step": 244
    },
    {
      "epoch": 0.95703125,
      "grad_norm": 13.204935073852539,
      "learning_rate": 2.263374485596708e-06,
      "loss": 2.8013,
      "step": 245
    },
    {
      "epoch": 0.9609375,
      "grad_norm": 15.458930015563965,
      "learning_rate": 2.05761316872428e-06,
      "loss": 2.8541,
      "step": 246
    },
    {
      "epoch": 0.96484375,
      "grad_norm": 17.476573944091797,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 2.7538,
      "step": 247
    },
    {
      "epoch": 0.96875,
      "grad_norm": 13.751199722290039,
      "learning_rate": 1.6460905349794242e-06,
      "loss": 2.8324,
      "step": 248
    },
    {
      "epoch": 0.97265625,
      "grad_norm": 15.517616271972656,
      "learning_rate": 1.440329218106996e-06,
      "loss": 2.8402,
      "step": 249
    },
    {
      "epoch": 0.9765625,
      "grad_norm": 16.016067504882812,
      "learning_rate": 1.234567901234568e-06,
      "loss": 2.895,
      "step": 250
    },
    {
      "epoch": 0.98046875,
      "grad_norm": 11.978571891784668,
      "learning_rate": 1.02880658436214e-06,
      "loss": 2.9139,
      "step": 251
    },
    {
      "epoch": 1.00390625,
      "grad_norm": 58.774688720703125,
      "learning_rate": 8.230452674897121e-07,
      "loss": 3.7051,
      "step": 252
    },
    {
      "epoch": 1.0078125,
      "grad_norm": 52.733154296875,
      "learning_rate": 6.17283950617284e-07,
      "loss": 3.7482,
      "step": 253
    },
    {
      "epoch": 1.01171875,
      "grad_norm": 68.14625549316406,
      "learning_rate": 4.1152263374485604e-07,
      "loss": 3.8065,
      "step": 254
    },
    {
      "epoch": 1.015625,
      "grad_norm": 59.991546630859375,
      "learning_rate": 2.0576131687242802e-07,
      "loss": 3.6531,
      "step": 255
    },
    {
      "epoch": 1.01953125,
      "grad_norm": 40.77336883544922,
      "learning_rate": 0.0,
      "loss": 3.4788,
      "step": 256
    }
  ],
  "logging_steps": 1,
  "max_steps": 256,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 1.0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}