{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7782101167315175,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007782101167315175,
      "grad_norm": 0.15050330758094788,
      "learning_rate": 1e-05,
      "loss": 10.3688,
      "step": 1
    },
    {
      "epoch": 0.007782101167315175,
      "eval_loss": NaN,
      "eval_runtime": 0.3507,
      "eval_samples_per_second": 307.972,
      "eval_steps_per_second": 39.922,
      "step": 1
    },
    {
      "epoch": 0.01556420233463035,
      "grad_norm": 0.2052978277206421,
      "learning_rate": 2e-05,
      "loss": 10.3736,
      "step": 2
    },
    {
      "epoch": 0.023346303501945526,
      "grad_norm": 0.22770772874355316,
      "learning_rate": 3e-05,
      "loss": 10.3135,
      "step": 3
    },
    {
      "epoch": 0.0311284046692607,
      "grad_norm": 0.20140793919563293,
      "learning_rate": 4e-05,
      "loss": 10.2939,
      "step": 4
    },
    {
      "epoch": 0.038910505836575876,
      "grad_norm": 0.19401751458644867,
      "learning_rate": 5e-05,
      "loss": 10.3256,
      "step": 5
    },
    {
      "epoch": 0.04669260700389105,
      "grad_norm": 0.18698450922966003,
      "learning_rate": 6e-05,
      "loss": 10.3705,
      "step": 6
    },
    {
      "epoch": 0.054474708171206226,
      "grad_norm": 0.27336716651916504,
      "learning_rate": 7e-05,
      "loss": 10.3191,
      "step": 7
    },
    {
      "epoch": 0.0622568093385214,
      "grad_norm": 0.22764867544174194,
      "learning_rate": 8e-05,
      "loss": 10.3599,
      "step": 8
    },
    {
      "epoch": 0.07003891050583658,
      "grad_norm": 0.21836555004119873,
      "learning_rate": 9e-05,
      "loss": 10.3509,
      "step": 9
    },
    {
      "epoch": 0.07003891050583658,
      "eval_loss": NaN,
      "eval_runtime": 0.3723,
      "eval_samples_per_second": 290.06,
      "eval_steps_per_second": 37.6,
      "step": 9
    },
    {
      "epoch": 0.07782101167315175,
      "grad_norm": 0.09972412884235382,
      "learning_rate": 0.0001,
      "loss": 10.3629,
      "step": 10
    },
    {
      "epoch": 0.08560311284046693,
      "grad_norm": 0.1307542771100998,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3581,
      "step": 11
    },
    {
      "epoch": 0.0933852140077821,
      "grad_norm": 0.21208789944648743,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3348,
      "step": 12
    },
    {
      "epoch": 0.10116731517509728,
      "grad_norm": 0.22375652194023132,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3007,
      "step": 13
    },
    {
      "epoch": 0.10894941634241245,
      "grad_norm": 0.2047107070684433,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.32,
      "step": 14
    },
    {
      "epoch": 0.11673151750972763,
      "grad_norm": 0.16958235204219818,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3279,
      "step": 15
    },
    {
      "epoch": 0.1245136186770428,
      "grad_norm": 0.26593777537345886,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3441,
      "step": 16
    },
    {
      "epoch": 0.13229571984435798,
      "grad_norm": 0.3536827862262726,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3664,
      "step": 17
    },
    {
      "epoch": 0.14007782101167315,
      "grad_norm": 0.38606491684913635,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.2935,
      "step": 18
    },
    {
      "epoch": 0.14007782101167315,
      "eval_loss": NaN,
      "eval_runtime": 0.3716,
      "eval_samples_per_second": 290.664,
      "eval_steps_per_second": 37.679,
      "step": 18
    },
    {
      "epoch": 0.14785992217898833,
      "grad_norm": 0.0,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.1556420233463035,
      "grad_norm": 0.0,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.16342412451361868,
      "grad_norm": 0.3168112635612488,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3187,
      "step": 21
    },
    {
      "epoch": 0.17120622568093385,
      "grad_norm": 0.0,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.17898832684824903,
      "grad_norm": 0.2514454126358032,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3512,
      "step": 23
    },
    {
      "epoch": 0.1867704280155642,
      "grad_norm": 0.0,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.19455252918287938,
      "grad_norm": 0.21714404225349426,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3402,
      "step": 25
    },
    {
      "epoch": 0.20233463035019456,
      "grad_norm": 0.09935510903596878,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.367,
      "step": 26
    },
    {
      "epoch": 0.21011673151750973,
      "grad_norm": 0.1893402338027954,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.343,
      "step": 27
    },
    {
      "epoch": 0.21011673151750973,
      "eval_loss": NaN,
      "eval_runtime": 0.396,
      "eval_samples_per_second": 272.742,
      "eval_steps_per_second": 35.355,
      "step": 27
    },
    {
      "epoch": 0.2178988326848249,
      "grad_norm": 0.16203711926937103,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3318,
      "step": 28
    },
    {
      "epoch": 0.22568093385214008,
      "grad_norm": 0.19412550330162048,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3913,
      "step": 29
    },
    {
      "epoch": 0.23346303501945526,
      "grad_norm": 0.3511830270290375,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.2959,
      "step": 30
    },
    {
      "epoch": 0.24124513618677043,
      "grad_norm": 0.2315189391374588,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3486,
      "step": 31
    },
    {
      "epoch": 0.2490272373540856,
      "grad_norm": 0.1658879965543747,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3505,
      "step": 32
    },
    {
      "epoch": 0.25680933852140075,
      "grad_norm": 0.1770622283220291,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3333,
      "step": 33
    },
    {
      "epoch": 0.26459143968871596,
      "grad_norm": 0.0,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.2723735408560311,
      "grad_norm": 0.28501346707344055,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.2935,
      "step": 35
    },
    {
      "epoch": 0.2801556420233463,
      "grad_norm": 0.2703624367713928,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3251,
      "step": 36
    },
    {
      "epoch": 0.2801556420233463,
      "eval_loss": NaN,
      "eval_runtime": 0.3829,
      "eval_samples_per_second": 282.076,
      "eval_steps_per_second": 36.565,
      "step": 36
    },
    {
      "epoch": 0.28793774319066145,
      "grad_norm": 0.16514138877391815,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3588,
      "step": 37
    },
    {
      "epoch": 0.29571984435797666,
      "grad_norm": 0.17835251986980438,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3294,
      "step": 38
    },
    {
      "epoch": 0.3035019455252918,
      "grad_norm": 0.0,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.311284046692607,
      "grad_norm": 0.35127612948417664,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3466,
      "step": 40
    },
    {
      "epoch": 0.31906614785992216,
      "grad_norm": 0.23155651986598969,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3373,
      "step": 41
    },
    {
      "epoch": 0.32684824902723736,
      "grad_norm": 0.31581297516822815,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3105,
      "step": 42
    },
    {
      "epoch": 0.3346303501945525,
      "grad_norm": 0.0,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.3424124513618677,
      "grad_norm": 0.1989944577217102,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3353,
      "step": 44
    },
    {
      "epoch": 0.35019455252918286,
      "grad_norm": 0.10988571494817734,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3591,
      "step": 45
    },
    {
      "epoch": 0.35019455252918286,
      "eval_loss": NaN,
      "eval_runtime": 0.4084,
      "eval_samples_per_second": 264.436,
      "eval_steps_per_second": 34.279,
      "step": 45
    },
    {
      "epoch": 0.35797665369649806,
      "grad_norm": 0.2702690362930298,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3186,
      "step": 46
    },
    {
      "epoch": 0.3657587548638132,
      "grad_norm": 0.2404761016368866,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3323,
      "step": 47
    },
    {
      "epoch": 0.3735408560311284,
      "grad_norm": 0.24785469472408295,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.2847,
      "step": 48
    },
    {
      "epoch": 0.38132295719844356,
      "grad_norm": 0.17176614701747894,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3431,
      "step": 49
    },
    {
      "epoch": 0.38910505836575876,
      "grad_norm": 0.2749108672142029,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3002,
      "step": 50
    },
    {
      "epoch": 0.3968871595330739,
      "grad_norm": 0.0,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.4046692607003891,
      "grad_norm": 0.18099191784858704,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3323,
      "step": 52
    },
    {
      "epoch": 0.41245136186770426,
      "grad_norm": 0.10944093763828278,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.347,
      "step": 53
    },
    {
      "epoch": 0.42023346303501946,
      "grad_norm": 0.27111586928367615,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.2841,
      "step": 54
    },
    {
      "epoch": 0.42023346303501946,
      "eval_loss": NaN,
      "eval_runtime": 0.3823,
      "eval_samples_per_second": 282.498,
      "eval_steps_per_second": 36.62,
      "step": 54
    },
    {
      "epoch": 0.4280155642023346,
      "grad_norm": 0.23218759894371033,
      "learning_rate": 5e-05,
      "loss": 10.3536,
      "step": 55
    },
    {
      "epoch": 0.4357976653696498,
      "grad_norm": 0.32123154401779175,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.2888,
      "step": 56
    },
    {
      "epoch": 0.44357976653696496,
      "grad_norm": 0.11285388469696045,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3688,
      "step": 57
    },
    {
      "epoch": 0.45136186770428016,
      "grad_norm": 0.2072630375623703,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3193,
      "step": 58
    },
    {
      "epoch": 0.4591439688715953,
      "grad_norm": 0.22816087305545807,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3542,
      "step": 59
    },
    {
      "epoch": 0.4669260700389105,
      "grad_norm": 0.2683489918708801,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.309,
      "step": 60
    },
    {
      "epoch": 0.47470817120622566,
      "grad_norm": 0.20230989158153534,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3389,
      "step": 61
    },
    {
      "epoch": 0.48249027237354086,
      "grad_norm": 0.5085319876670837,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3247,
      "step": 62
    },
    {
      "epoch": 0.490272373540856,
      "grad_norm": 0.25417184829711914,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3218,
      "step": 63
    },
    {
      "epoch": 0.490272373540856,
      "eval_loss": NaN,
      "eval_runtime": 0.3868,
      "eval_samples_per_second": 279.247,
      "eval_steps_per_second": 36.199,
      "step": 63
    },
    {
      "epoch": 0.4980544747081712,
      "grad_norm": 0.0,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.5058365758754864,
      "grad_norm": 0.0,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.5136186770428015,
      "grad_norm": 0.35637524724006653,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.2719,
      "step": 66
    },
    {
      "epoch": 0.5214007782101168,
      "grad_norm": 0.31268998980522156,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3118,
      "step": 67
    },
    {
      "epoch": 0.5291828793774319,
      "grad_norm": 0.17281199991703033,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3455,
      "step": 68
    },
    {
      "epoch": 0.5369649805447471,
      "grad_norm": 0.18739189207553864,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3066,
      "step": 69
    },
    {
      "epoch": 0.5447470817120622,
      "grad_norm": 0.1419634222984314,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3226,
      "step": 70
    },
    {
      "epoch": 0.5525291828793775,
      "grad_norm": 0.27168574929237366,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3416,
      "step": 71
    },
    {
      "epoch": 0.5603112840466926,
      "grad_norm": 0.44093209505081177,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.2672,
      "step": 72
    },
    {
      "epoch": 0.5603112840466926,
      "eval_loss": NaN,
      "eval_runtime": 0.4726,
      "eval_samples_per_second": 228.515,
      "eval_steps_per_second": 29.622,
      "step": 72
    },
    {
      "epoch": 0.5680933852140078,
      "grad_norm": 0.3372398316860199,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3153,
      "step": 73
    },
    {
      "epoch": 0.5758754863813229,
      "grad_norm": 0.3003866672515869,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3436,
      "step": 74
    },
    {
      "epoch": 0.5836575875486382,
      "grad_norm": 0.163679301738739,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.357,
      "step": 75
    },
    {
      "epoch": 0.5914396887159533,
      "grad_norm": 0.0,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.5992217898832685,
      "grad_norm": 0.4258427619934082,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3103,
      "step": 77
    },
    {
      "epoch": 0.6070038910505836,
      "grad_norm": 0.3290005326271057,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3019,
      "step": 78
    },
    {
      "epoch": 0.6147859922178989,
      "grad_norm": 0.16638368368148804,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3301,
      "step": 79
    },
    {
      "epoch": 0.622568093385214,
      "grad_norm": 0.0,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.6303501945525292,
      "grad_norm": 0.20695820450782776,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3287,
      "step": 81
    },
    {
      "epoch": 0.6303501945525292,
      "eval_loss": NaN,
      "eval_runtime": 0.4656,
      "eval_samples_per_second": 231.97,
      "eval_steps_per_second": 30.07,
      "step": 81
    },
    {
      "epoch": 0.6381322957198443,
      "grad_norm": 0.28333377838134766,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3335,
      "step": 82
    },
    {
      "epoch": 0.6459143968871596,
      "grad_norm": 0.0,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.6536964980544747,
      "grad_norm": 0.0,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.6614785992217899,
      "grad_norm": 0.22484956681728363,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3235,
      "step": 85
    },
    {
      "epoch": 0.669260700389105,
      "grad_norm": 0.15221866965293884,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3531,
      "step": 86
    },
    {
      "epoch": 0.6770428015564203,
      "grad_norm": 0.12713178992271423,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3367,
      "step": 87
    },
    {
      "epoch": 0.6848249027237354,
      "grad_norm": 0.17537634074687958,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3255,
      "step": 88
    },
    {
      "epoch": 0.6926070038910506,
      "grad_norm": 0.1998535841703415,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3831,
      "step": 89
    },
    {
      "epoch": 0.7003891050583657,
      "grad_norm": 0.1796063929796219,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3197,
      "step": 90
    },
    {
      "epoch": 0.7003891050583657,
      "eval_loss": NaN,
      "eval_runtime": 0.4096,
      "eval_samples_per_second": 263.683,
      "eval_steps_per_second": 34.181,
      "step": 90
    },
    {
      "epoch": 0.708171206225681,
      "grad_norm": 0.20497995615005493,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3191,
      "step": 91
    },
    {
      "epoch": 0.7159533073929961,
      "grad_norm": 0.4476834833621979,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3319,
      "step": 92
    },
    {
      "epoch": 0.7237354085603113,
      "grad_norm": 0.5001630187034607,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.2647,
      "step": 93
    },
    {
      "epoch": 0.7315175097276264,
      "grad_norm": 0.3534506857395172,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.2811,
      "step": 94
    },
    {
      "epoch": 0.7392996108949417,
      "grad_norm": 0.32725393772125244,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3196,
      "step": 95
    },
    {
      "epoch": 0.7470817120622568,
      "grad_norm": 0.1588638424873352,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.354,
      "step": 96
    },
    {
      "epoch": 0.754863813229572,
      "grad_norm": 0.3359444737434387,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3324,
      "step": 97
    },
    {
      "epoch": 0.7626459143968871,
      "grad_norm": 0.0,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.7704280155642024,
      "grad_norm": 0.1817806214094162,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3151,
      "step": 99
    },
    {
      "epoch": 0.7704280155642024,
      "eval_loss": NaN,
      "eval_runtime": 0.3852,
      "eval_samples_per_second": 280.368,
      "eval_steps_per_second": 36.344,
      "step": 99
    },
    {
      "epoch": 0.7782101167315175,
      "grad_norm": 0.19820758700370789,
      "learning_rate": 0.0,
      "loss": 10.3539,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7400796192768.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}