{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014187415762218911,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014187415762218912,
      "grad_norm": 8.55720329284668,
      "learning_rate": 1e-05,
      "loss": 9.5763,
      "step": 1
    },
    {
      "epoch": 0.00014187415762218912,
      "eval_loss": 5.170290470123291,
      "eval_runtime": 541.5833,
      "eval_samples_per_second": 10.96,
      "eval_steps_per_second": 1.37,
      "step": 1
    },
    {
      "epoch": 0.00028374831524437824,
      "grad_norm": 15.271714210510254,
      "learning_rate": 2e-05,
      "loss": 14.2221,
      "step": 2
    },
    {
      "epoch": 0.00042562247286656737,
      "grad_norm": 10.752700805664062,
      "learning_rate": 3e-05,
      "loss": 8.8528,
      "step": 3
    },
    {
      "epoch": 0.0005674966304887565,
      "grad_norm": 9.006422996520996,
      "learning_rate": 4e-05,
      "loss": 8.1531,
      "step": 4
    },
    {
      "epoch": 0.0007093707881109456,
      "grad_norm": 8.735152244567871,
      "learning_rate": 5e-05,
      "loss": 7.5536,
      "step": 5
    },
    {
      "epoch": 0.0008512449457331347,
      "grad_norm": 11.253613471984863,
      "learning_rate": 6e-05,
      "loss": 7.8477,
      "step": 6
    },
    {
      "epoch": 0.0009931191033553239,
      "grad_norm": 13.532144546508789,
      "learning_rate": 7e-05,
      "loss": 9.7863,
      "step": 7
    },
    {
      "epoch": 0.001134993260977513,
      "grad_norm": 11.745100021362305,
      "learning_rate": 8e-05,
      "loss": 8.1758,
      "step": 8
    },
    {
      "epoch": 0.001276867418599702,
      "grad_norm": 25.068866729736328,
      "learning_rate": 9e-05,
      "loss": 8.8081,
      "step": 9
    },
    {
      "epoch": 0.001276867418599702,
      "eval_loss": 3.618622064590454,
      "eval_runtime": 541.2297,
      "eval_samples_per_second": 10.968,
      "eval_steps_per_second": 1.371,
      "step": 9
    },
    {
      "epoch": 0.0014187415762218912,
      "grad_norm": 30.30573844909668,
      "learning_rate": 0.0001,
      "loss": 7.2207,
      "step": 10
    },
    {
      "epoch": 0.0015606157338440803,
      "grad_norm": 24.609844207763672,
      "learning_rate": 9.99695413509548e-05,
      "loss": 5.9715,
      "step": 11
    },
    {
      "epoch": 0.0017024898914662695,
      "grad_norm": 25.285606384277344,
      "learning_rate": 9.987820251299122e-05,
      "loss": 5.8464,
      "step": 12
    },
    {
      "epoch": 0.0018443640490884586,
      "grad_norm": 14.56118106842041,
      "learning_rate": 9.972609476841367e-05,
      "loss": 4.0568,
      "step": 13
    },
    {
      "epoch": 0.0019862382067106477,
      "grad_norm": 26.332727432250977,
      "learning_rate": 9.951340343707852e-05,
      "loss": 4.3524,
      "step": 14
    },
    {
      "epoch": 0.0021281123643328366,
      "grad_norm": 19.993797302246094,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.1353,
      "step": 15
    },
    {
      "epoch": 0.002269986521955026,
      "grad_norm": 15.966957092285156,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.3459,
      "step": 16
    },
    {
      "epoch": 0.002411860679577215,
      "grad_norm": 26.18716049194336,
      "learning_rate": 9.851478631379982e-05,
      "loss": 3.4877,
      "step": 17
    },
    {
      "epoch": 0.002553734837199404,
      "grad_norm": 17.52493667602539,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.121,
      "step": 18
    },
    {
      "epoch": 0.002553734837199404,
      "eval_loss": 1.0831109285354614,
      "eval_runtime": 540.9677,
      "eval_samples_per_second": 10.973,
      "eval_steps_per_second": 1.372,
      "step": 18
    },
    {
      "epoch": 0.002695608994821593,
      "grad_norm": 12.01088809967041,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0823,
      "step": 19
    },
    {
      "epoch": 0.0028374831524437824,
      "grad_norm": 11.361188888549805,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.0118,
      "step": 20
    },
    {
      "epoch": 0.0029793573100659713,
      "grad_norm": 13.85122299194336,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.5319,
      "step": 21
    },
    {
      "epoch": 0.0031212314676881607,
      "grad_norm": 9.590019226074219,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.8167,
      "step": 22
    },
    {
      "epoch": 0.0032631056253103496,
      "grad_norm": 14.33270263671875,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.2387,
      "step": 23
    },
    {
      "epoch": 0.003404979782932539,
      "grad_norm": 6.969985008239746,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.853,
      "step": 24
    },
    {
      "epoch": 0.003546853940554728,
      "grad_norm": 6.836635112762451,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.1543,
      "step": 25
    },
    {
      "epoch": 0.003688728098176917,
      "grad_norm": 9.076546669006348,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3788,
      "step": 26
    },
    {
      "epoch": 0.003830602255799106,
      "grad_norm": 12.995061874389648,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.2468,
      "step": 27
    },
    {
      "epoch": 0.003830602255799106,
      "eval_loss": 0.6279391646385193,
      "eval_runtime": 541.7801,
      "eval_samples_per_second": 10.956,
      "eval_steps_per_second": 1.37,
      "step": 27
    },
    {
      "epoch": 0.003972476413421295,
      "grad_norm": 8.741141319274902,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.9294,
      "step": 28
    },
    {
      "epoch": 0.004114350571043484,
      "grad_norm": 11.498311996459961,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.2281,
      "step": 29
    },
    {
      "epoch": 0.004256224728665673,
      "grad_norm": 11.130197525024414,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.5019,
      "step": 30
    },
    {
      "epoch": 0.004398098886287863,
      "grad_norm": 7.296480655670166,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.1992,
      "step": 31
    },
    {
      "epoch": 0.004539973043910052,
      "grad_norm": 7.6955389976501465,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1805,
      "step": 32
    },
    {
      "epoch": 0.004681847201532241,
      "grad_norm": 10.107093811035156,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.253,
      "step": 33
    },
    {
      "epoch": 0.00482372135915443,
      "grad_norm": 10.577054023742676,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.7774,
      "step": 34
    },
    {
      "epoch": 0.0049655955167766195,
      "grad_norm": 7.113376617431641,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.7259,
      "step": 35
    },
    {
      "epoch": 0.005107469674398808,
      "grad_norm": 10.733963966369629,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.3057,
      "step": 36
    },
    {
      "epoch": 0.005107469674398808,
      "eval_loss": 0.4863208532333374,
      "eval_runtime": 540.8283,
      "eval_samples_per_second": 10.976,
      "eval_steps_per_second": 1.372,
      "step": 36
    },
    {
      "epoch": 0.005249343832020997,
      "grad_norm": 8.43188762664795,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2677,
      "step": 37
    },
    {
      "epoch": 0.005391217989643186,
      "grad_norm": 6.6493611335754395,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.6093,
      "step": 38
    },
    {
      "epoch": 0.005533092147265376,
      "grad_norm": 7.014468193054199,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.7699,
      "step": 39
    },
    {
      "epoch": 0.005674966304887565,
      "grad_norm": 6.780705451965332,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9263,
      "step": 40
    },
    {
      "epoch": 0.005816840462509754,
      "grad_norm": 6.085496425628662,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.6976,
      "step": 41
    },
    {
      "epoch": 0.005958714620131943,
      "grad_norm": 6.213381767272949,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.9982,
      "step": 42
    },
    {
      "epoch": 0.0061005887777541325,
      "grad_norm": 6.507991790771484,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.7347,
      "step": 43
    },
    {
      "epoch": 0.006242462935376321,
      "grad_norm": 5.2897748947143555,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.6589,
      "step": 44
    },
    {
      "epoch": 0.00638433709299851,
      "grad_norm": 11.325580596923828,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.0976,
      "step": 45
    },
    {
      "epoch": 0.00638433709299851,
      "eval_loss": 0.4915553629398346,
      "eval_runtime": 541.0971,
      "eval_samples_per_second": 10.97,
      "eval_steps_per_second": 1.371,
      "step": 45
    },
    {
      "epoch": 0.006526211250620699,
      "grad_norm": 9.572626113891602,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.924,
      "step": 46
    },
    {
      "epoch": 0.006668085408242889,
      "grad_norm": 6.726538181304932,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.6873,
      "step": 47
    },
    {
      "epoch": 0.006809959565865078,
      "grad_norm": 6.53619384765625,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.7005,
      "step": 48
    },
    {
      "epoch": 0.006951833723487267,
      "grad_norm": 4.928836822509766,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.6345,
      "step": 49
    },
    {
      "epoch": 0.007093707881109456,
      "grad_norm": 6.096105098724365,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.8714,
      "step": 50
    },
    {
      "epoch": 0.0072355820387316454,
      "grad_norm": 6.460239410400391,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.8425,
      "step": 51
    },
    {
      "epoch": 0.007377456196353834,
      "grad_norm": 7.313208103179932,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.9399,
      "step": 52
    },
    {
      "epoch": 0.007519330353976023,
      "grad_norm": 5.7543206214904785,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.8304,
      "step": 53
    },
    {
      "epoch": 0.007661204511598212,
      "grad_norm": 8.54841136932373,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.1842,
      "step": 54
    },
    {
      "epoch": 0.007661204511598212,
      "eval_loss": 0.4334222078323364,
      "eval_runtime": 541.1045,
      "eval_samples_per_second": 10.97,
      "eval_steps_per_second": 1.371,
      "step": 54
    },
    {
      "epoch": 0.007803078669220402,
      "grad_norm": 3.552095651626587,
      "learning_rate": 5e-05,
      "loss": 0.5944,
      "step": 55
    },
    {
      "epoch": 0.00794495282684259,
      "grad_norm": 4.194748401641846,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.7586,
      "step": 56
    },
    {
      "epoch": 0.008086826984464779,
      "grad_norm": 6.412907600402832,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.9264,
      "step": 57
    },
    {
      "epoch": 0.008228701142086969,
      "grad_norm": 5.4873785972595215,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.9442,
      "step": 58
    },
    {
      "epoch": 0.008370575299709158,
      "grad_norm": 5.020580768585205,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.7963,
      "step": 59
    },
    {
      "epoch": 0.008512449457331346,
      "grad_norm": 9.607460975646973,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.6891,
      "step": 60
    },
    {
      "epoch": 0.008654323614953536,
      "grad_norm": 11.415412902832031,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.1025,
      "step": 61
    },
    {
      "epoch": 0.008796197772575726,
      "grad_norm": 4.338674068450928,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.5018,
      "step": 62
    },
    {
      "epoch": 0.008938071930197914,
      "grad_norm": 8.46346664428711,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.7072,
      "step": 63
    },
    {
      "epoch": 0.008938071930197914,
      "eval_loss": 0.4158031642436981,
      "eval_runtime": 541.0438,
      "eval_samples_per_second": 10.971,
      "eval_steps_per_second": 1.371,
      "step": 63
    },
    {
      "epoch": 0.009079946087820104,
      "grad_norm": 5.24552583694458,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5167,
      "step": 64
    },
    {
      "epoch": 0.009221820245442292,
      "grad_norm": 4.212309837341309,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.5451,
      "step": 65
    },
    {
      "epoch": 0.009363694403064482,
      "grad_norm": 4.912107944488525,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.7611,
      "step": 66
    },
    {
      "epoch": 0.009505568560686671,
      "grad_norm": 5.346253871917725,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.624,
      "step": 67
    },
    {
      "epoch": 0.00964744271830886,
      "grad_norm": 4.815743446350098,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.5705,
      "step": 68
    },
    {
      "epoch": 0.00978931687593105,
      "grad_norm": 3.5380396842956543,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.4037,
      "step": 69
    },
    {
      "epoch": 0.009931191033553239,
      "grad_norm": 4.5514044761657715,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.6228,
      "step": 70
    },
    {
      "epoch": 0.010073065191175427,
      "grad_norm": 6.931221008300781,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.9966,
      "step": 71
    },
    {
      "epoch": 0.010214939348797617,
      "grad_norm": 8.248758316040039,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.0049,
      "step": 72
    },
    {
      "epoch": 0.010214939348797617,
      "eval_loss": 0.38347503542900085,
      "eval_runtime": 541.0584,
      "eval_samples_per_second": 10.971,
      "eval_steps_per_second": 1.371,
      "step": 72
    },
    {
      "epoch": 0.010356813506419805,
      "grad_norm": 7.816049575805664,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8902,
      "step": 73
    },
    {
      "epoch": 0.010498687664041995,
      "grad_norm": 14.4616060256958,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.985,
      "step": 74
    },
    {
      "epoch": 0.010640561821664184,
      "grad_norm": 5.556700229644775,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.8064,
      "step": 75
    },
    {
      "epoch": 0.010782435979286372,
      "grad_norm": 5.031896591186523,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.8174,
      "step": 76
    },
    {
      "epoch": 0.010924310136908562,
      "grad_norm": 3.872175455093384,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.6007,
      "step": 77
    },
    {
      "epoch": 0.011066184294530752,
      "grad_norm": 4.109659671783447,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.5097,
      "step": 78
    },
    {
      "epoch": 0.01120805845215294,
      "grad_norm": 6.500185489654541,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.8836,
      "step": 79
    },
    {
      "epoch": 0.01134993260977513,
      "grad_norm": 8.053261756896973,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.6566,
      "step": 80
    },
    {
      "epoch": 0.011491806767397318,
      "grad_norm": 4.231142044067383,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.7664,
      "step": 81
    },
    {
      "epoch": 0.011491806767397318,
      "eval_loss": 0.3777725398540497,
      "eval_runtime": 540.9366,
      "eval_samples_per_second": 10.974,
      "eval_steps_per_second": 1.372,
      "step": 81
    },
    {
      "epoch": 0.011633680925019508,
      "grad_norm": 5.413785934448242,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7267,
      "step": 82
    },
    {
      "epoch": 0.011775555082641697,
      "grad_norm": 5.458988189697266,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.8067,
      "step": 83
    },
    {
      "epoch": 0.011917429240263885,
      "grad_norm": 3.969133138656616,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.5833,
      "step": 84
    },
    {
      "epoch": 0.012059303397886075,
      "grad_norm": 4.596381187438965,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.8829,
      "step": 85
    },
    {
      "epoch": 0.012201177555508265,
      "grad_norm": 6.600720405578613,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.9084,
      "step": 86
    },
    {
      "epoch": 0.012343051713130453,
      "grad_norm": 8.138842582702637,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.6855,
      "step": 87
    },
    {
      "epoch": 0.012484925870752643,
      "grad_norm": 4.982905387878418,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.5768,
      "step": 88
    },
    {
      "epoch": 0.01262680002837483,
      "grad_norm": 4.94661283493042,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.7711,
      "step": 89
    },
    {
      "epoch": 0.01276867418599702,
      "grad_norm": 5.5673136711120605,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.601,
      "step": 90
    },
    {
      "epoch": 0.01276867418599702,
      "eval_loss": 0.36759427189826965,
      "eval_runtime": 541.9128,
      "eval_samples_per_second": 10.954,
      "eval_steps_per_second": 1.369,
      "step": 90
    },
    {
      "epoch": 0.01291054834361921,
      "grad_norm": 4.802902698516846,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6431,
      "step": 91
    },
    {
      "epoch": 0.013052422501241398,
      "grad_norm": 4.773902416229248,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.7515,
      "step": 92
    },
    {
      "epoch": 0.013194296658863588,
      "grad_norm": 3.6889700889587402,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.5724,
      "step": 93
    },
    {
      "epoch": 0.013336170816485778,
      "grad_norm": 5.018240451812744,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.7002,
      "step": 94
    },
    {
      "epoch": 0.013478044974107966,
      "grad_norm": 3.2519288063049316,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.5406,
      "step": 95
    },
    {
      "epoch": 0.013619919131730156,
      "grad_norm": 4.466538906097412,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.7291,
      "step": 96
    },
    {
      "epoch": 0.013761793289352344,
      "grad_norm": 4.562383651733398,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.4869,
      "step": 97
    },
    {
      "epoch": 0.013903667446974534,
      "grad_norm": 3.9905810356140137,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.639,
      "step": 98
    },
    {
      "epoch": 0.014045541604596723,
      "grad_norm": 5.33958625793457,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.7274,
      "step": 99
    },
    {
      "epoch": 0.014045541604596723,
      "eval_loss": 0.36495569348335266,
      "eval_runtime": 541.0666,
      "eval_samples_per_second": 10.971,
      "eval_steps_per_second": 1.371,
      "step": 99
    },
    {
      "epoch": 0.014187415762218911,
      "grad_norm": 6.187318325042725,
      "learning_rate": 0.0,
      "loss": 1.056,
      "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": 6.53458201903104e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}