{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008753118298393803,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.753118298393803e-05,
      "grad_norm": 9.70646858215332,
      "learning_rate": 1e-05,
      "loss": 5.4108,
      "step": 1
    },
    {
      "epoch": 8.753118298393803e-05,
      "eval_loss": 5.437164783477783,
      "eval_runtime": 295.9882,
      "eval_samples_per_second": 32.505,
      "eval_steps_per_second": 4.064,
      "step": 1
    },
    {
      "epoch": 0.00017506236596787607,
      "grad_norm": 9.148581504821777,
      "learning_rate": 2e-05,
      "loss": 4.1876,
      "step": 2
    },
    {
      "epoch": 0.00026259354895181406,
      "grad_norm": 17.097013473510742,
      "learning_rate": 3e-05,
      "loss": 6.8057,
      "step": 3
    },
    {
      "epoch": 0.00035012473193575213,
      "grad_norm": 9.966192245483398,
      "learning_rate": 4e-05,
      "loss": 5.3739,
      "step": 4
    },
    {
      "epoch": 0.00043765591491969015,
      "grad_norm": 13.026144981384277,
      "learning_rate": 5e-05,
      "loss": 4.655,
      "step": 5
    },
    {
      "epoch": 0.0005251870979036281,
      "grad_norm": 11.39557933807373,
      "learning_rate": 6e-05,
      "loss": 5.0293,
      "step": 6
    },
    {
      "epoch": 0.0006127182808875662,
      "grad_norm": 10.354576110839844,
      "learning_rate": 7e-05,
      "loss": 5.7822,
      "step": 7
    },
    {
      "epoch": 0.0007002494638715043,
      "grad_norm": 13.632707595825195,
      "learning_rate": 8e-05,
      "loss": 5.101,
      "step": 8
    },
    {
      "epoch": 0.0007877806468554422,
      "grad_norm": 11.034542083740234,
      "learning_rate": 9e-05,
      "loss": 4.5662,
      "step": 9
    },
    {
      "epoch": 0.0007877806468554422,
      "eval_loss": 4.414220809936523,
      "eval_runtime": 295.1919,
      "eval_samples_per_second": 32.592,
      "eval_steps_per_second": 4.075,
      "step": 9
    },
    {
      "epoch": 0.0008753118298393803,
      "grad_norm": 31.181407928466797,
      "learning_rate": 0.0001,
      "loss": 4.3073,
      "step": 10
    },
    {
      "epoch": 0.0009628430128233183,
      "grad_norm": 38.48316955566406,
      "learning_rate": 9.99695413509548e-05,
      "loss": 4.4779,
      "step": 11
    },
    {
      "epoch": 0.0010503741958072562,
      "grad_norm": 19.27284812927246,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.2171,
      "step": 12
    },
    {
      "epoch": 0.0011379053787911944,
      "grad_norm": 7.969431400299072,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.9336,
      "step": 13
    },
    {
      "epoch": 0.0012254365617751324,
      "grad_norm": 13.702813148498535,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.9514,
      "step": 14
    },
    {
      "epoch": 0.0013129677447590703,
      "grad_norm": 8.929804801940918,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.402,
      "step": 15
    },
    {
      "epoch": 0.0014004989277430085,
      "grad_norm": 9.007357597351074,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.7387,
      "step": 16
    },
    {
      "epoch": 0.0014880301107269465,
      "grad_norm": 10.724602699279785,
      "learning_rate": 9.851478631379982e-05,
      "loss": 3.1314,
      "step": 17
    },
    {
      "epoch": 0.0015755612937108845,
      "grad_norm": 9.780793190002441,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.0842,
      "step": 18
    },
    {
      "epoch": 0.0015755612937108845,
      "eval_loss": 2.6529042720794678,
      "eval_runtime": 295.1693,
      "eval_samples_per_second": 32.595,
      "eval_steps_per_second": 4.076,
      "step": 18
    },
    {
      "epoch": 0.0016630924766948226,
      "grad_norm": 42.64231491088867,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.7356,
      "step": 19
    },
    {
      "epoch": 0.0017506236596787606,
      "grad_norm": 8.039458274841309,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.9829,
      "step": 20
    },
    {
      "epoch": 0.0018381548426626986,
      "grad_norm": 12.14621639251709,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.2411,
      "step": 21
    },
    {
      "epoch": 0.0019256860256466365,
      "grad_norm": 9.838249206542969,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.2109,
      "step": 22
    },
    {
      "epoch": 0.0020132172086305745,
      "grad_norm": 6.6005778312683105,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.3652,
      "step": 23
    },
    {
      "epoch": 0.0021007483916145125,
      "grad_norm": 11.20893669128418,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.9689,
      "step": 24
    },
    {
      "epoch": 0.002188279574598451,
      "grad_norm": 7.862691402435303,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.7746,
      "step": 25
    },
    {
      "epoch": 0.002275810757582389,
      "grad_norm": 7.793013095855713,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.4048,
      "step": 26
    },
    {
      "epoch": 0.002363341940566327,
      "grad_norm": 5.6689066886901855,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.5291,
      "step": 27
    },
    {
      "epoch": 0.002363341940566327,
      "eval_loss": 1.8446345329284668,
      "eval_runtime": 295.1813,
      "eval_samples_per_second": 32.594,
      "eval_steps_per_second": 4.075,
      "step": 27
    },
    {
      "epoch": 0.0024508731235502648,
      "grad_norm": 7.587317943572998,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.8188,
      "step": 28
    },
    {
      "epoch": 0.0025384043065342027,
      "grad_norm": 6.163393497467041,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.8708,
      "step": 29
    },
    {
      "epoch": 0.0026259354895181407,
      "grad_norm": 9.271770477294922,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.948,
      "step": 30
    },
    {
      "epoch": 0.002713466672502079,
      "grad_norm": 7.210991382598877,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.6504,
      "step": 31
    },
    {
      "epoch": 0.002800997855486017,
      "grad_norm": 6.960716724395752,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.2732,
      "step": 32
    },
    {
      "epoch": 0.002888529038469955,
      "grad_norm": 8.12993335723877,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.9916,
      "step": 33
    },
    {
      "epoch": 0.002976060221453893,
      "grad_norm": 11.74069595336914,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.8845,
      "step": 34
    },
    {
      "epoch": 0.003063591404437831,
      "grad_norm": 9.337483406066895,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.1789,
      "step": 35
    },
    {
      "epoch": 0.003151122587421769,
      "grad_norm": 3.5326576232910156,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.2162,
      "step": 36
    },
    {
      "epoch": 0.003151122587421769,
      "eval_loss": 1.5431464910507202,
      "eval_runtime": 295.1525,
      "eval_samples_per_second": 32.597,
      "eval_steps_per_second": 4.076,
      "step": 36
    },
    {
      "epoch": 0.003238653770405707,
      "grad_norm": 10.800670623779297,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.8533,
      "step": 37
    },
    {
      "epoch": 0.0033261849533896453,
      "grad_norm": 6.670267105102539,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.623,
      "step": 38
    },
    {
      "epoch": 0.0034137161363735832,
      "grad_norm": 5.949354648590088,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.4547,
      "step": 39
    },
    {
      "epoch": 0.003501247319357521,
      "grad_norm": 6.5009026527404785,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.711,
      "step": 40
    },
    {
      "epoch": 0.003588778502341459,
      "grad_norm": 4.838705062866211,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.3266,
      "step": 41
    },
    {
      "epoch": 0.003676309685325397,
      "grad_norm": 6.21650505065918,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.3676,
      "step": 42
    },
    {
      "epoch": 0.003763840868309335,
      "grad_norm": 13.958775520324707,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.205,
      "step": 43
    },
    {
      "epoch": 0.003851372051293273,
      "grad_norm": 7.129842281341553,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.5973,
      "step": 44
    },
    {
      "epoch": 0.003938903234277211,
      "grad_norm": 5.955078601837158,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.9352,
      "step": 45
    },
    {
      "epoch": 0.003938903234277211,
      "eval_loss": 1.3934128284454346,
      "eval_runtime": 295.1039,
      "eval_samples_per_second": 32.602,
      "eval_steps_per_second": 4.077,
      "step": 45
    },
    {
      "epoch": 0.004026434417261149,
      "grad_norm": 7.522401332855225,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.2901,
      "step": 46
    },
    {
      "epoch": 0.004113965600245087,
      "grad_norm": 7.637457847595215,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.2937,
      "step": 47
    },
    {
      "epoch": 0.004201496783229025,
      "grad_norm": 4.988274574279785,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.9206,
      "step": 48
    },
    {
      "epoch": 0.004289027966212964,
      "grad_norm": 4.970093250274658,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.1996,
      "step": 49
    },
    {
      "epoch": 0.004376559149196902,
      "grad_norm": 5.910721302032471,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.8865,
      "step": 50
    },
    {
      "epoch": 0.00446409033218084,
      "grad_norm": 5.796518325805664,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.0543,
      "step": 51
    },
    {
      "epoch": 0.004551621515164778,
      "grad_norm": 6.383048057556152,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.1899,
      "step": 52
    },
    {
      "epoch": 0.004639152698148716,
      "grad_norm": 8.441072463989258,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.853,
      "step": 53
    },
    {
      "epoch": 0.004726683881132654,
      "grad_norm": 4.844428062438965,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.1318,
      "step": 54
    },
    {
      "epoch": 0.004726683881132654,
      "eval_loss": 1.2637803554534912,
      "eval_runtime": 295.0992,
      "eval_samples_per_second": 32.603,
      "eval_steps_per_second": 4.077,
      "step": 54
    },
    {
      "epoch": 0.0048142150641165915,
      "grad_norm": 5.350905895233154,
      "learning_rate": 5e-05,
      "loss": 1.1295,
      "step": 55
    },
    {
      "epoch": 0.0049017462471005295,
      "grad_norm": 3.5436036586761475,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.6779,
      "step": 56
    },
    {
      "epoch": 0.0049892774300844675,
      "grad_norm": 4.656448841094971,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.1424,
      "step": 57
    },
    {
      "epoch": 0.005076808613068405,
      "grad_norm": 10.876627922058105,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.5671,
      "step": 58
    },
    {
      "epoch": 0.005164339796052343,
      "grad_norm": 6.925072193145752,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.051,
      "step": 59
    },
    {
      "epoch": 0.005251870979036281,
      "grad_norm": 5.39897346496582,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.2641,
      "step": 60
    },
    {
      "epoch": 0.005339402162020219,
      "grad_norm": 4.6381754875183105,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.9157,
      "step": 61
    },
    {
      "epoch": 0.005426933345004158,
      "grad_norm": 6.519228935241699,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.3082,
      "step": 62
    },
    {
      "epoch": 0.005514464527988096,
      "grad_norm": 9.517118453979492,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.8158,
      "step": 63
    },
    {
      "epoch": 0.005514464527988096,
      "eval_loss": 1.2056524753570557,
      "eval_runtime": 295.124,
      "eval_samples_per_second": 32.6,
      "eval_steps_per_second": 4.076,
      "step": 63
    },
    {
      "epoch": 0.005601995710972034,
      "grad_norm": 4.163848876953125,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7853,
      "step": 64
    },
    {
      "epoch": 0.005689526893955972,
      "grad_norm": 8.454404830932617,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.6983,
      "step": 65
    },
    {
      "epoch": 0.00577705807693991,
      "grad_norm": 4.995180606842041,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.2404,
      "step": 66
    },
    {
      "epoch": 0.005864589259923848,
      "grad_norm": 6.102477550506592,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.8774,
      "step": 67
    },
    {
      "epoch": 0.005952120442907786,
      "grad_norm": 5.160752773284912,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.2424,
      "step": 68
    },
    {
      "epoch": 0.006039651625891724,
      "grad_norm": 12.11997127532959,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.3793,
      "step": 69
    },
    {
      "epoch": 0.006127182808875662,
      "grad_norm": 4.08521032333374,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7081,
      "step": 70
    },
    {
      "epoch": 0.0062147139918596,
      "grad_norm": 5.965517997741699,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.2613,
      "step": 71
    },
    {
      "epoch": 0.006302245174843538,
      "grad_norm": 9.013812065124512,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.4851,
      "step": 72
    },
    {
      "epoch": 0.006302245174843538,
      "eval_loss": 1.149828553199768,
      "eval_runtime": 295.042,
      "eval_samples_per_second": 32.609,
      "eval_steps_per_second": 4.077,
      "step": 72
    },
    {
      "epoch": 0.006389776357827476,
      "grad_norm": 4.008739471435547,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7525,
      "step": 73
    },
    {
      "epoch": 0.006477307540811414,
      "grad_norm": 4.971322059631348,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.0027,
      "step": 74
    },
    {
      "epoch": 0.006564838723795352,
      "grad_norm": 3.989278793334961,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.0143,
      "step": 75
    },
    {
      "epoch": 0.0066523699067792905,
      "grad_norm": 8.679134368896484,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.6159,
      "step": 76
    },
    {
      "epoch": 0.0067399010897632285,
      "grad_norm": 4.6100850105285645,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.0441,
      "step": 77
    },
    {
      "epoch": 0.0068274322727471665,
      "grad_norm": 3.9601824283599854,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.6739,
      "step": 78
    },
    {
      "epoch": 0.006914963455731104,
      "grad_norm": 5.406814098358154,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.1113,
      "step": 79
    },
    {
      "epoch": 0.007002494638715042,
      "grad_norm": 6.396301746368408,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.9932,
      "step": 80
    },
    {
      "epoch": 0.00709002582169898,
      "grad_norm": 8.984944343566895,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.2545,
      "step": 81
    },
    {
      "epoch": 0.00709002582169898,
      "eval_loss": 1.1259727478027344,
      "eval_runtime": 295.1355,
      "eval_samples_per_second": 32.599,
      "eval_steps_per_second": 4.076,
      "step": 81
    },
    {
      "epoch": 0.007177557004682918,
      "grad_norm": 4.506406784057617,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7675,
      "step": 82
    },
    {
      "epoch": 0.007265088187666856,
      "grad_norm": 7.563035011291504,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.7437,
      "step": 83
    },
    {
      "epoch": 0.007352619370650794,
      "grad_norm": 7.010645389556885,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.3697,
      "step": 84
    },
    {
      "epoch": 0.007440150553634732,
      "grad_norm": 4.244420051574707,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.9396,
      "step": 85
    },
    {
      "epoch": 0.00752768173661867,
      "grad_norm": 6.9684576988220215,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.6496,
      "step": 86
    },
    {
      "epoch": 0.007615212919602608,
      "grad_norm": 6.6828718185424805,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.2345,
      "step": 87
    },
    {
      "epoch": 0.007702744102586546,
      "grad_norm": 13.264280319213867,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.6867,
      "step": 88
    },
    {
      "epoch": 0.007790275285570484,
      "grad_norm": 5.590743064880371,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.3572,
      "step": 89
    },
    {
      "epoch": 0.007877806468554422,
      "grad_norm": 5.790264129638672,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.7421,
      "step": 90
    },
    {
      "epoch": 0.007877806468554422,
      "eval_loss": 1.1100659370422363,
      "eval_runtime": 295.112,
      "eval_samples_per_second": 32.601,
      "eval_steps_per_second": 4.076,
      "step": 90
    },
    {
      "epoch": 0.007965337651538361,
      "grad_norm": 6.471609115600586,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.1764,
      "step": 91
    },
    {
      "epoch": 0.008052868834522298,
      "grad_norm": 5.196161270141602,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.0228,
      "step": 92
    },
    {
      "epoch": 0.008140400017506237,
      "grad_norm": 5.157146453857422,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.1801,
      "step": 93
    },
    {
      "epoch": 0.008227931200490174,
      "grad_norm": 5.235270023345947,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.8866,
      "step": 94
    },
    {
      "epoch": 0.008315462383474113,
      "grad_norm": 4.621222972869873,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.1422,
      "step": 95
    },
    {
      "epoch": 0.00840299356645805,
      "grad_norm": 5.371739387512207,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.8709,
      "step": 96
    },
    {
      "epoch": 0.008490524749441989,
      "grad_norm": 4.3551130294799805,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.1157,
      "step": 97
    },
    {
      "epoch": 0.008578055932425927,
      "grad_norm": 7.401463031768799,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.0076,
      "step": 98
    },
    {
      "epoch": 0.008665587115409865,
      "grad_norm": 5.7351531982421875,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.0131,
      "step": 99
    },
    {
      "epoch": 0.008665587115409865,
      "eval_loss": 1.1067209243774414,
      "eval_runtime": 295.2298,
      "eval_samples_per_second": 32.588,
      "eval_steps_per_second": 4.075,
      "step": 99
    },
    {
      "epoch": 0.008753118298393803,
      "grad_norm": 4.822691917419434,
      "learning_rate": 0.0,
      "loss": 0.9012,
      "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": 2.0484438563487744e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}