{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.997134670487106,
  "eval_steps": 500,
  "global_step": 174,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 1.9996968507766724,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.8702,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.5313825607299805,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.8359,
      "step": 2
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.5655955076217651,
      "learning_rate": 0.0001,
      "loss": 0.9499,
      "step": 3
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.336176872253418,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.8982,
      "step": 4
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.739897608757019,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.7752,
      "step": 5
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.4859261512756348,
      "learning_rate": 0.0002,
      "loss": 0.8191,
      "step": 6
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.5755207538604736,
      "learning_rate": 0.00019998251609127464,
      "loss": 0.7395,
      "step": 7
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.5322685241699219,
      "learning_rate": 0.00019993007047883988,
      "loss": 0.7178,
      "step": 8
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.1697393655776978,
      "learning_rate": 0.00019984268150178167,
      "loss": 0.7346,
      "step": 9
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.9915004372596741,
      "learning_rate": 0.00019972037971811802,
      "loss": 0.7384,
      "step": 10
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.3418762683868408,
      "learning_rate": 0.00019956320789411337,
      "loss": 0.6448,
      "step": 11
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.367616057395935,
      "learning_rate": 0.00019937122098932428,
      "loss": 0.7262,
      "step": 12
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.5906193256378174,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.5596,
      "step": 13
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.3098320960998535,
      "learning_rate": 0.00019888308262251285,
      "loss": 0.7048,
      "step": 14
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.0479499101638794,
      "learning_rate": 0.0001985871018518236,
      "loss": 0.4957,
      "step": 15
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.7250303030014038,
      "learning_rate": 0.00019825664732332884,
      "loss": 0.7647,
      "step": 16
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.1252228021621704,
      "learning_rate": 0.00019789183458976484,
      "loss": 0.6322,
      "step": 17
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.2008912563323975,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.4648,
      "step": 18
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.2641726732254028,
      "learning_rate": 0.0001970596567453391,
      "loss": 1.1271,
      "step": 19
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.3506691455841064,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.7563,
      "step": 20
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.0392251014709473,
      "learning_rate": 0.00019609173219450998,
      "loss": 0.7428,
      "step": 21
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.2239336967468262,
      "learning_rate": 0.0001955572805786141,
      "loss": 0.7053,
      "step": 22
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.221558928489685,
      "learning_rate": 0.0001949894146672846,
      "loss": 0.5294,
      "step": 23
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.4633010625839233,
      "learning_rate": 0.00019438833303083678,
      "loss": 0.5635,
      "step": 24
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.1936019659042358,
      "learning_rate": 0.00019375424585439994,
      "loss": 0.4888,
      "step": 25
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.2357252836227417,
      "learning_rate": 0.00019308737486442045,
      "loss": 0.667,
      "step": 26
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.4489282369613647,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.7923,
      "step": 27
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.149989128112793,
      "learning_rate": 0.00019165622558699763,
      "loss": 0.6681,
      "step": 28
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.4635039567947388,
      "learning_rate": 0.0001908924477412211,
      "loss": 0.5343,
      "step": 29
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.2030097246170044,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.568,
      "step": 30
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.032403588294983,
      "learning_rate": 0.00018926982092436117,
      "loss": 0.5707,
      "step": 31
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.2733995914459229,
      "learning_rate": 0.00018841153935046098,
      "loss": 0.621,
      "step": 32
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.3361601829528809,
      "learning_rate": 0.00018752234219087538,
      "loss": 0.7366,
      "step": 33
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.068040132522583,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.6821,
      "step": 34
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.2753121852874756,
      "learning_rate": 0.00018565245554778517,
      "loss": 0.6429,
      "step": 35
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.3101242780685425,
      "learning_rate": 0.00018467241992282843,
      "loss": 0.6494,
      "step": 36
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.1557663679122925,
      "learning_rate": 0.00018366277620064197,
      "loss": 0.4877,
      "step": 37
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.8449192047119141,
      "learning_rate": 0.0001826238774315995,
      "loss": 0.6382,
      "step": 38
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.0876007080078125,
      "learning_rate": 0.00018155608689592604,
      "loss": 0.5395,
      "step": 39
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.223763108253479,
      "learning_rate": 0.00018045977797666684,
      "loss": 0.6391,
      "step": 40
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.3192774057388306,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.9222,
      "step": 41
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.6065058708190918,
      "learning_rate": 0.000178183148246803,
      "loss": 0.699,
      "step": 42
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.0040181875228882,
      "learning_rate": 0.0001770036235239263,
      "loss": 0.5911,
      "step": 43
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.4657773971557617,
      "learning_rate": 0.0001757971723145453,
      "loss": 0.7135,
      "step": 44
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.4623713493347168,
      "learning_rate": 0.00017456421648831655,
      "loss": 0.8692,
      "step": 45
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.9319050312042236,
      "learning_rate": 0.00017330518718298264,
      "loss": 0.6411,
      "step": 46
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.3076001405715942,
      "learning_rate": 0.00017202052465361268,
      "loss": 0.6273,
      "step": 47
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.3123239278793335,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.6402,
      "step": 48
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.2312636375427246,
      "learning_rate": 0.00016937610560285418,
      "loss": 0.7375,
      "step": 49
    },
    {
      "epoch": 0.29,
      "grad_norm": 1.3208093643188477,
      "learning_rate": 0.00016801727377709194,
      "loss": 0.5201,
      "step": 50
    },
    {
      "epoch": 0.29,
      "grad_norm": 1.5665061473846436,
      "learning_rate": 0.0001666346577952004,
      "loss": 0.7437,
      "step": 51
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.2510838508605957,
      "learning_rate": 0.00016522874112781213,
      "loss": 0.8225,
      "step": 52
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.992620587348938,
      "learning_rate": 0.0001638000153933009,
      "loss": 0.6432,
      "step": 53
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.0591328144073486,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.7487,
      "step": 54
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.1704132556915283,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.6461,
      "step": 55
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.127586841583252,
      "learning_rate": 0.00015938201855735014,
      "loss": 0.5765,
      "step": 56
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.078080415725708,
      "learning_rate": 0.0001578671296179806,
      "loss": 0.7739,
      "step": 57
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.8577872514724731,
      "learning_rate": 0.0001563320058063622,
      "loss": 0.6798,
      "step": 58
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.841907262802124,
      "learning_rate": 0.00015477718392178716,
      "loss": 0.8779,
      "step": 59
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.103470802307129,
      "learning_rate": 0.00015320320765153367,
      "loss": 0.5571,
      "step": 60
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.0301905870437622,
      "learning_rate": 0.00015161062738075067,
      "loss": 0.5628,
      "step": 61
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.3095691204071045,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.7975,
      "step": 62
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.9905968904495239,
      "learning_rate": 0.000148371888710524,
      "loss": 0.5076,
      "step": 63
    },
    {
      "epoch": 0.37,
      "grad_norm": 1.1895394325256348,
      "learning_rate": 0.0001467268628273062,
      "loss": 0.6454,
      "step": 64
    },
    {
      "epoch": 0.37,
      "grad_norm": 1.064146876335144,
      "learning_rate": 0.00014506549757999454,
      "loss": 0.6619,
      "step": 65
    },
    {
      "epoch": 0.38,
      "grad_norm": 1.1531059741973877,
      "learning_rate": 0.00014338837391175582,
      "loss": 0.6753,
      "step": 66
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.9704313278198242,
      "learning_rate": 0.00014169607827613283,
      "loss": 0.9793,
      "step": 67
    },
    {
      "epoch": 0.39,
      "grad_norm": 1.2401033639907837,
      "learning_rate": 0.00013998920243197407,
      "loss": 0.8405,
      "step": 68
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.5912938117980957,
      "learning_rate": 0.000138268343236509,
      "loss": 0.7367,
      "step": 69
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.199100136756897,
      "learning_rate": 0.00013653410243663952,
      "loss": 0.6981,
      "step": 70
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.1692229509353638,
      "learning_rate": 0.00013478708645852272,
      "loss": 0.5552,
      "step": 71
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.1189988851547241,
      "learning_rate": 0.00013302790619551674,
      "loss": 0.5807,
      "step": 72
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.2706007957458496,
      "learning_rate": 0.00013125717679456447,
      "loss": 0.795,
      "step": 73
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.3663891553878784,
      "learning_rate": 0.00012947551744109043,
      "loss": 0.7185,
      "step": 74
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.0806580781936646,
      "learning_rate": 0.00012768355114248494,
      "loss": 0.725,
      "step": 75
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.899416983127594,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.2994,
      "step": 76
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.0771483182907104,
      "learning_rate": 0.00012407120754089732,
      "loss": 0.8243,
      "step": 77
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.4580143690109253,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.6778,
      "step": 78
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.16950261592865,
      "learning_rate": 0.00012042519817896804,
      "loss": 0.5453,
      "step": 79
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.0602941513061523,
      "learning_rate": 0.00011859116071629149,
      "loss": 0.6036,
      "step": 80
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.2422832250595093,
      "learning_rate": 0.00011675062233047364,
      "loss": 0.7027,
      "step": 81
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.0794113874435425,
      "learning_rate": 0.00011490422661761744,
      "loss": 0.6626,
      "step": 82
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.3527191877365112,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.5989,
      "step": 83
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.1593997478485107,
      "learning_rate": 0.00011119644761033078,
      "loss": 0.5045,
      "step": 84
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.2227619886398315,
      "learning_rate": 0.00010933636084529506,
      "loss": 0.5855,
      "step": 85
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.9840473532676697,
      "learning_rate": 0.00010747300935864243,
      "loss": 0.6959,
      "step": 86
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.059381127357483,
      "learning_rate": 0.00010560704472371919,
      "loss": 0.6402,
      "step": 87
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.6882269382476807,
      "learning_rate": 0.0001037391194276326,
      "loss": 0.7913,
      "step": 88
    },
    {
      "epoch": 0.51,
      "grad_norm": 1.2182209491729736,
      "learning_rate": 0.00010186988664309023,
      "loss": 0.7404,
      "step": 89
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.1175509691238403,
      "learning_rate": 0.0001,
      "loss": 0.6732,
      "step": 90
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.369556188583374,
      "learning_rate": 9.813011335690981e-05,
      "loss": 0.5596,
      "step": 91
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.1430643796920776,
      "learning_rate": 9.626088057236745e-05,
      "loss": 0.5835,
      "step": 92
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.254775881767273,
      "learning_rate": 9.439295527628081e-05,
      "loss": 0.5155,
      "step": 93
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.2139248847961426,
      "learning_rate": 9.252699064135758e-05,
      "loss": 0.6411,
      "step": 94
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.3170784711837769,
      "learning_rate": 9.066363915470495e-05,
      "loss": 0.7952,
      "step": 95
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.2811988592147827,
      "learning_rate": 8.880355238966923e-05,
      "loss": 0.7964,
      "step": 96
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.5923776626586914,
      "learning_rate": 8.694738077799488e-05,
      "loss": 0.7752,
      "step": 97
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.0868611335754395,
      "learning_rate": 8.509577338238255e-05,
      "loss": 0.7895,
      "step": 98
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.738330602645874,
      "learning_rate": 8.324937766952638e-05,
      "loss": 0.4511,
      "step": 99
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.0786418914794922,
      "learning_rate": 8.140883928370855e-05,
      "loss": 0.726,
      "step": 100
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.8921433091163635,
      "learning_rate": 7.957480182103198e-05,
      "loss": 0.3153,
      "step": 101
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.8898999094963074,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.4152,
      "step": 102
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.8994467258453369,
      "learning_rate": 7.592879245910273e-05,
      "loss": 0.6082,
      "step": 103
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.0093451738357544,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.7098,
      "step": 104
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.3192236423492432,
      "learning_rate": 7.231644885751507e-05,
      "loss": 0.6607,
      "step": 105
    },
    {
      "epoch": 0.61,
      "grad_norm": 1.1677393913269043,
      "learning_rate": 7.052448255890957e-05,
      "loss": 0.6892,
      "step": 106
    },
    {
      "epoch": 0.61,
      "grad_norm": 1.1743494272232056,
      "learning_rate": 6.874282320543557e-05,
      "loss": 0.4914,
      "step": 107
    },
    {
      "epoch": 0.62,
      "grad_norm": 1.0391740798950195,
      "learning_rate": 6.697209380448333e-05,
      "loss": 0.5603,
      "step": 108
    },
    {
      "epoch": 0.62,
      "grad_norm": 1.492876648902893,
      "learning_rate": 6.521291354147727e-05,
      "loss": 0.5301,
      "step": 109
    },
    {
      "epoch": 0.63,
      "grad_norm": 1.498785138130188,
      "learning_rate": 6.34658975633605e-05,
      "loss": 0.5596,
      "step": 110
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.0714867115020752,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.5014,
      "step": 111
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.9467328786849976,
      "learning_rate": 6.001079756802592e-05,
      "loss": 0.3966,
      "step": 112
    },
    {
      "epoch": 0.65,
      "grad_norm": 1.2287578582763672,
      "learning_rate": 5.830392172386723e-05,
      "loss": 0.688,
      "step": 113
    },
    {
      "epoch": 0.65,
      "grad_norm": 1.0478023290634155,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.5189,
      "step": 114
    },
    {
      "epoch": 0.66,
      "grad_norm": 1.1996300220489502,
      "learning_rate": 5.493450242000546e-05,
      "loss": 0.817,
      "step": 115
    },
    {
      "epoch": 0.66,
      "grad_norm": 1.2935843467712402,
      "learning_rate": 5.32731371726938e-05,
      "loss": 0.8832,
      "step": 116
    },
    {
      "epoch": 0.67,
      "grad_norm": 1.2258471250534058,
      "learning_rate": 5.162811128947602e-05,
      "loss": 0.6955,
      "step": 117
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.025177001953125,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.432,
      "step": 118
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.2166136503219604,
      "learning_rate": 4.8389372619249326e-05,
      "loss": 0.4972,
      "step": 119
    },
    {
      "epoch": 0.69,
      "grad_norm": 1.0988982915878296,
      "learning_rate": 4.6796792348466356e-05,
      "loss": 0.7484,
      "step": 120
    },
    {
      "epoch": 0.69,
      "grad_norm": 1.0646111965179443,
      "learning_rate": 4.522281607821288e-05,
      "loss": 0.7397,
      "step": 121
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.0885090827941895,
      "learning_rate": 4.3667994193637796e-05,
      "loss": 0.69,
      "step": 122
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.0070377588272095,
      "learning_rate": 4.213287038201943e-05,
      "loss": 0.6798,
      "step": 123
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.1084964275360107,
      "learning_rate": 4.0617981442649855e-05,
      "loss": 0.4984,
      "step": 124
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.2662650346755981,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 0.6031,
      "step": 125
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.0789271593093872,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 0.7263,
      "step": 126
    },
    {
      "epoch": 0.73,
      "grad_norm": 1.1152573823928833,
      "learning_rate": 3.6199984606699155e-05,
      "loss": 0.5901,
      "step": 127
    },
    {
      "epoch": 0.73,
      "grad_norm": 1.2624356746673584,
      "learning_rate": 3.477125887218792e-05,
      "loss": 0.5302,
      "step": 128
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.1492183208465576,
      "learning_rate": 3.336534220479961e-05,
      "loss": 0.4703,
      "step": 129
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.1994153261184692,
      "learning_rate": 3.198272622290804e-05,
      "loss": 0.6033,
      "step": 130
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.8388205170631409,
      "learning_rate": 3.062389439714584e-05,
      "loss": 0.5517,
      "step": 131
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.1319376230239868,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.5563,
      "step": 132
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.0953915119171143,
      "learning_rate": 2.797947534638736e-05,
      "loss": 0.4382,
      "step": 133
    },
    {
      "epoch": 0.77,
      "grad_norm": 1.3944048881530762,
      "learning_rate": 2.669481281701739e-05,
      "loss": 0.7719,
      "step": 134
    },
    {
      "epoch": 0.77,
      "grad_norm": 1.2075766324996948,
      "learning_rate": 2.5435783511683443e-05,
      "loss": 0.7832,
      "step": 135
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.0302568674087524,
      "learning_rate": 2.420282768545469e-05,
      "loss": 0.5348,
      "step": 136
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.9179348945617676,
      "learning_rate": 2.2996376476073723e-05,
      "loss": 0.5576,
      "step": 137
    },
    {
      "epoch": 0.79,
      "grad_norm": 1.6255179643630981,
      "learning_rate": 2.181685175319702e-05,
      "loss": 0.5651,
      "step": 138
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.0162822008132935,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 0.6177,
      "step": 139
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.0871258974075317,
      "learning_rate": 1.9540222023333166e-05,
      "loss": 0.5514,
      "step": 140
    },
    {
      "epoch": 0.81,
      "grad_norm": 1.1647260189056396,
      "learning_rate": 1.8443913104073983e-05,
      "loss": 0.3784,
      "step": 141
    },
    {
      "epoch": 0.81,
      "grad_norm": 1.1097166538238525,
      "learning_rate": 1.7376122568400532e-05,
      "loss": 0.6258,
      "step": 142
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.9427088499069214,
      "learning_rate": 1.6337223799358026e-05,
      "loss": 0.5978,
      "step": 143
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.307686448097229,
      "learning_rate": 1.5327580077171587e-05,
      "loss": 0.5625,
      "step": 144
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.8880772590637207,
      "learning_rate": 1.4347544452214868e-05,
      "loss": 0.5293,
      "step": 145
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.0818653106689453,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.7303,
      "step": 146
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.1671406030654907,
      "learning_rate": 1.2477657809124631e-05,
      "loss": 0.7759,
      "step": 147
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.5812010765075684,
      "learning_rate": 1.1588460649539035e-05,
      "loss": 0.8125,
      "step": 148
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.2229740619659424,
      "learning_rate": 1.0730179075638868e-05,
      "loss": 0.6869,
      "step": 149
    },
    {
      "epoch": 0.86,
      "grad_norm": 1.4635610580444336,
      "learning_rate": 9.903113209758096e-06,
      "loss": 0.7056,
      "step": 150
    },
    {
      "epoch": 0.87,
      "grad_norm": 1.0302622318267822,
      "learning_rate": 9.107552258778907e-06,
      "loss": 0.7185,
      "step": 151
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.9198307394981384,
      "learning_rate": 8.343774413002381e-06,
      "loss": 0.7054,
      "step": 152
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.063753604888916,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.8275,
      "step": 153
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.9813847541809082,
      "learning_rate": 6.9126251355795864e-06,
      "loss": 0.5853,
      "step": 154
    },
    {
      "epoch": 0.89,
      "grad_norm": 1.0063732862472534,
      "learning_rate": 6.245754145600091e-06,
      "loss": 0.5504,
      "step": 155
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.8452687859535217,
      "learning_rate": 5.611666969163243e-06,
      "loss": 0.4793,
      "step": 156
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.2720369100570679,
      "learning_rate": 5.0105853327154e-06,
      "loss": 0.6192,
      "step": 157
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.0188275575637817,
      "learning_rate": 4.442719421385922e-06,
      "loss": 0.6451,
      "step": 158
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.8996236324310303,
      "learning_rate": 3.908267805490051e-06,
      "loss": 0.5704,
      "step": 159
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.9807499051094055,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.6076,
      "step": 160
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.9825880527496338,
      "learning_rate": 2.9403432546609043e-06,
      "loss": 0.4702,
      "step": 161
    },
    {
      "epoch": 0.93,
      "grad_norm": 1.181723713874817,
      "learning_rate": 2.5072087818176382e-06,
      "loss": 0.3018,
      "step": 162
    },
    {
      "epoch": 0.93,
      "grad_norm": 1.1127053499221802,
      "learning_rate": 2.1081654102351635e-06,
      "loss": 0.587,
      "step": 163
    },
    {
      "epoch": 0.94,
      "grad_norm": 1.0752973556518555,
      "learning_rate": 1.7433526766711728e-06,
      "loss": 0.6908,
      "step": 164
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.0229278802871704,
      "learning_rate": 1.4128981481764115e-06,
      "loss": 0.5199,
      "step": 165
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.9454005360603333,
      "learning_rate": 1.1169173774871478e-06,
      "loss": 0.4818,
      "step": 166
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.4845045804977417,
      "learning_rate": 8.555138626189618e-07,
      "loss": 0.5741,
      "step": 167
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.9463722109794617,
      "learning_rate": 6.287790106757396e-07,
      "loss": 0.4218,
      "step": 168
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.9009414911270142,
      "learning_rate": 4.3679210588661866e-07,
      "loss": 0.5095,
      "step": 169
    },
    {
      "epoch": 0.97,
      "grad_norm": 1.0209568738937378,
      "learning_rate": 2.7962028188198706e-07,
      "loss": 0.5586,
      "step": 170
    },
    {
      "epoch": 0.98,
      "grad_norm": 1.2022913694381714,
      "learning_rate": 1.5731849821833954e-07,
      "loss": 0.599,
      "step": 171
    },
    {
      "epoch": 0.99,
      "grad_norm": 1.01807701587677,
      "learning_rate": 6.992952116013918e-08,
      "loss": 0.6367,
      "step": 172
    },
    {
      "epoch": 0.99,
      "grad_norm": 1.1196523904800415,
      "learning_rate": 1.7483908725357545e-08,
      "loss": 0.6932,
      "step": 173
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.058908462524414,
      "learning_rate": 0.0,
      "loss": 0.5663,
      "step": 174
    },
    {
      "epoch": 1.0,
      "step": 174,
      "total_flos": 8141179086438400.0,
      "train_loss": 0.6448915855980467,
      "train_runtime": 3124.8032,
      "train_samples_per_second": 0.894,
      "train_steps_per_second": 0.056
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 174,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 8141179086438400.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}