{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.48426150121065376,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004842615012106538,
      "grad_norm": 6.951022148132324,
      "learning_rate": 1e-05,
      "loss": 4.4499,
      "step": 1
    },
    {
      "epoch": 0.004842615012106538,
      "eval_loss": 4.435294151306152,
      "eval_runtime": 19.3661,
      "eval_samples_per_second": 8.985,
      "eval_steps_per_second": 1.136,
      "step": 1
    },
    {
      "epoch": 0.009685230024213076,
      "grad_norm": 7.089580535888672,
      "learning_rate": 2e-05,
      "loss": 4.5236,
      "step": 2
    },
    {
      "epoch": 0.014527845036319613,
      "grad_norm": 5.838200092315674,
      "learning_rate": 3e-05,
      "loss": 4.7935,
      "step": 3
    },
    {
      "epoch": 0.01937046004842615,
      "grad_norm": 7.749260425567627,
      "learning_rate": 4e-05,
      "loss": 4.2716,
      "step": 4
    },
    {
      "epoch": 0.024213075060532687,
      "grad_norm": 5.93482780456543,
      "learning_rate": 5e-05,
      "loss": 4.0175,
      "step": 5
    },
    {
      "epoch": 0.029055690072639227,
      "grad_norm": 5.986671447753906,
      "learning_rate": 6e-05,
      "loss": 4.0304,
      "step": 6
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 9.270807266235352,
      "learning_rate": 7e-05,
      "loss": 3.8371,
      "step": 7
    },
    {
      "epoch": 0.0387409200968523,
      "grad_norm": 4.2939581871032715,
      "learning_rate": 8e-05,
      "loss": 3.419,
      "step": 8
    },
    {
      "epoch": 0.043583535108958835,
      "grad_norm": 5.0304856300354,
      "learning_rate": 9e-05,
      "loss": 3.234,
      "step": 9
    },
    {
      "epoch": 0.043583535108958835,
      "eval_loss": 3.272956132888794,
      "eval_runtime": 18.9235,
      "eval_samples_per_second": 9.195,
      "eval_steps_per_second": 1.163,
      "step": 9
    },
    {
      "epoch": 0.048426150121065374,
      "grad_norm": 3.3577680587768555,
      "learning_rate": 0.0001,
      "loss": 3.6277,
      "step": 10
    },
    {
      "epoch": 0.053268765133171914,
      "grad_norm": 3.3006627559661865,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.0964,
      "step": 11
    },
    {
      "epoch": 0.05811138014527845,
      "grad_norm": 3.9956471920013428,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.513,
      "step": 12
    },
    {
      "epoch": 0.06295399515738499,
      "grad_norm": 3.6589813232421875,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.0589,
      "step": 13
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 2.8601772785186768,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.1075,
      "step": 14
    },
    {
      "epoch": 0.07263922518159806,
      "grad_norm": 2.350567579269409,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.9396,
      "step": 15
    },
    {
      "epoch": 0.0774818401937046,
      "grad_norm": 3.1738619804382324,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.4016,
      "step": 16
    },
    {
      "epoch": 0.08232445520581114,
      "grad_norm": 2.2036235332489014,
      "learning_rate": 9.851478631379982e-05,
      "loss": 3.2708,
      "step": 17
    },
    {
      "epoch": 0.08716707021791767,
      "grad_norm": 1.8742477893829346,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.0718,
      "step": 18
    },
    {
      "epoch": 0.08716707021791767,
      "eval_loss": 3.21498966217041,
      "eval_runtime": 18.9258,
      "eval_samples_per_second": 9.194,
      "eval_steps_per_second": 1.162,
      "step": 18
    },
    {
      "epoch": 0.09200968523002422,
      "grad_norm": 1.7467906475067139,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.2518,
      "step": 19
    },
    {
      "epoch": 0.09685230024213075,
      "grad_norm": 1.91806161403656,
      "learning_rate": 9.698463103929542e-05,
      "loss": 3.6172,
      "step": 20
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": 3.020704746246338,
      "learning_rate": 9.635919272833938e-05,
      "loss": 3.3863,
      "step": 21
    },
    {
      "epoch": 0.10653753026634383,
      "grad_norm": 2.5391972064971924,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.3373,
      "step": 22
    },
    {
      "epoch": 0.11138014527845036,
      "grad_norm": 4.1953043937683105,
      "learning_rate": 9.493970231495835e-05,
      "loss": 3.2729,
      "step": 23
    },
    {
      "epoch": 0.1162227602905569,
      "grad_norm": 3.60253643989563,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.3414,
      "step": 24
    },
    {
      "epoch": 0.12106537530266344,
      "grad_norm": 1.7871415615081787,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.2021,
      "step": 25
    },
    {
      "epoch": 0.12590799031476999,
      "grad_norm": 1.662522792816162,
      "learning_rate": 9.24024048078213e-05,
      "loss": 3.0991,
      "step": 26
    },
    {
      "epoch": 0.13075060532687652,
      "grad_norm": 2.686455011367798,
      "learning_rate": 9.145187862775209e-05,
      "loss": 3.2832,
      "step": 27
    },
    {
      "epoch": 0.13075060532687652,
      "eval_loss": 3.157177209854126,
      "eval_runtime": 18.9382,
      "eval_samples_per_second": 9.188,
      "eval_steps_per_second": 1.162,
      "step": 27
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 2.5698466300964355,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.1181,
      "step": 28
    },
    {
      "epoch": 0.14043583535108958,
      "grad_norm": 1.9049105644226074,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.9334,
      "step": 29
    },
    {
      "epoch": 0.14527845036319612,
      "grad_norm": 2.964027166366577,
      "learning_rate": 8.83022221559489e-05,
      "loss": 3.2234,
      "step": 30
    },
    {
      "epoch": 0.15012106537530268,
      "grad_norm": 1.3506639003753662,
      "learning_rate": 8.715724127386972e-05,
      "loss": 3.1192,
      "step": 31
    },
    {
      "epoch": 0.1549636803874092,
      "grad_norm": 1.3407896757125854,
      "learning_rate": 8.596699001693255e-05,
      "loss": 3.0793,
      "step": 32
    },
    {
      "epoch": 0.15980629539951574,
      "grad_norm": 2.121093988418579,
      "learning_rate": 8.473291852294987e-05,
      "loss": 3.0593,
      "step": 33
    },
    {
      "epoch": 0.16464891041162227,
      "grad_norm": 1.9535635709762573,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.2278,
      "step": 34
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 2.7124617099761963,
      "learning_rate": 8.213938048432697e-05,
      "loss": 3.4606,
      "step": 35
    },
    {
      "epoch": 0.17433414043583534,
      "grad_norm": 1.7934988737106323,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.1656,
      "step": 36
    },
    {
      "epoch": 0.17433414043583534,
      "eval_loss": 3.129340171813965,
      "eval_runtime": 18.9783,
      "eval_samples_per_second": 9.168,
      "eval_steps_per_second": 1.159,
      "step": 36
    },
    {
      "epoch": 0.1791767554479419,
      "grad_norm": 1.6445538997650146,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.0207,
      "step": 37
    },
    {
      "epoch": 0.18401937046004843,
      "grad_norm": 1.3065544366836548,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.7292,
      "step": 38
    },
    {
      "epoch": 0.18886198547215496,
      "grad_norm": 1.4131739139556885,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.8626,
      "step": 39
    },
    {
      "epoch": 0.1937046004842615,
      "grad_norm": 3.710179328918457,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.2187,
      "step": 40
    },
    {
      "epoch": 0.19854721549636803,
      "grad_norm": 1.917811393737793,
      "learning_rate": 7.347357813929454e-05,
      "loss": 3.1257,
      "step": 41
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 1.0857932567596436,
      "learning_rate": 7.191855733945387e-05,
      "loss": 3.0203,
      "step": 42
    },
    {
      "epoch": 0.20823244552058112,
      "grad_norm": 0.9913411736488342,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.9028,
      "step": 43
    },
    {
      "epoch": 0.21307506053268765,
      "grad_norm": 2.206404685974121,
      "learning_rate": 6.873032967079561e-05,
      "loss": 3.0664,
      "step": 44
    },
    {
      "epoch": 0.2179176755447942,
      "grad_norm": 1.5370384454727173,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.9419,
      "step": 45
    },
    {
      "epoch": 0.2179176755447942,
      "eval_loss": 3.1047704219818115,
      "eval_runtime": 18.9369,
      "eval_samples_per_second": 9.188,
      "eval_steps_per_second": 1.162,
      "step": 45
    },
    {
      "epoch": 0.22276029055690072,
      "grad_norm": 1.9688664674758911,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.193,
      "step": 46
    },
    {
      "epoch": 0.22760290556900725,
      "grad_norm": 2.1754133701324463,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.9325,
      "step": 47
    },
    {
      "epoch": 0.2324455205811138,
      "grad_norm": 2.6705334186553955,
      "learning_rate": 6.209609477998338e-05,
      "loss": 3.2207,
      "step": 48
    },
    {
      "epoch": 0.23728813559322035,
      "grad_norm": 1.4950735569000244,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 3.0829,
      "step": 49
    },
    {
      "epoch": 0.24213075060532688,
      "grad_norm": 2.104860782623291,
      "learning_rate": 5.868240888334653e-05,
      "loss": 3.1599,
      "step": 50
    },
    {
      "epoch": 0.2469733656174334,
      "grad_norm": 1.263146996498108,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.975,
      "step": 51
    },
    {
      "epoch": 0.25181598062953997,
      "grad_norm": 3.4207539558410645,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.4015,
      "step": 52
    },
    {
      "epoch": 0.2566585956416465,
      "grad_norm": 1.5546566247940063,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.9378,
      "step": 53
    },
    {
      "epoch": 0.26150121065375304,
      "grad_norm": 2.120374917984009,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.9896,
      "step": 54
    },
    {
      "epoch": 0.26150121065375304,
      "eval_loss": 3.084446668624878,
      "eval_runtime": 18.926,
      "eval_samples_per_second": 9.194,
      "eval_steps_per_second": 1.162,
      "step": 54
    },
    {
      "epoch": 0.26634382566585957,
      "grad_norm": 1.9824186563491821,
      "learning_rate": 5e-05,
      "loss": 3.0358,
      "step": 55
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 1.7688870429992676,
      "learning_rate": 4.825502516487497e-05,
      "loss": 3.1711,
      "step": 56
    },
    {
      "epoch": 0.27602905569007263,
      "grad_norm": 2.102198839187622,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 3.4714,
      "step": 57
    },
    {
      "epoch": 0.28087167070217917,
      "grad_norm": 1.664321780204773,
      "learning_rate": 4.477357683661734e-05,
      "loss": 3.0841,
      "step": 58
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.4341115951538086,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 3.2948,
      "step": 59
    },
    {
      "epoch": 0.29055690072639223,
      "grad_norm": 0.9612340927124023,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.9165,
      "step": 60
    },
    {
      "epoch": 0.29539951573849876,
      "grad_norm": 1.2795825004577637,
      "learning_rate": 3.960441545911204e-05,
      "loss": 3.1389,
      "step": 61
    },
    {
      "epoch": 0.30024213075060535,
      "grad_norm": 0.9679549932479858,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.9197,
      "step": 62
    },
    {
      "epoch": 0.3050847457627119,
      "grad_norm": 1.515199899673462,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 3.0526,
      "step": 63
    },
    {
      "epoch": 0.3050847457627119,
      "eval_loss": 3.055881977081299,
      "eval_runtime": 18.9316,
      "eval_samples_per_second": 9.191,
      "eval_steps_per_second": 1.162,
      "step": 63
    },
    {
      "epoch": 0.3099273607748184,
      "grad_norm": 1.8831665515899658,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.1823,
      "step": 64
    },
    {
      "epoch": 0.31476997578692495,
      "grad_norm": 1.6448265314102173,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.922,
      "step": 65
    },
    {
      "epoch": 0.3196125907990315,
      "grad_norm": 1.7221674919128418,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.2304,
      "step": 66
    },
    {
      "epoch": 0.324455205811138,
      "grad_norm": 1.9639180898666382,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 3.296,
      "step": 67
    },
    {
      "epoch": 0.32929782082324455,
      "grad_norm": 1.215235710144043,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.6854,
      "step": 68
    },
    {
      "epoch": 0.3341404358353511,
      "grad_norm": 2.490431785583496,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 3.0375,
      "step": 69
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 1.9049839973449707,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.2666,
      "step": 70
    },
    {
      "epoch": 0.34382566585956414,
      "grad_norm": 1.5522865056991577,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.8866,
      "step": 71
    },
    {
      "epoch": 0.3486682808716707,
      "grad_norm": 1.4543166160583496,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 3.0314,
      "step": 72
    },
    {
      "epoch": 0.3486682808716707,
      "eval_loss": 3.0360867977142334,
      "eval_runtime": 18.9447,
      "eval_samples_per_second": 9.185,
      "eval_steps_per_second": 1.161,
      "step": 72
    },
    {
      "epoch": 0.35351089588377727,
      "grad_norm": 3.4857094287872314,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.3805,
      "step": 73
    },
    {
      "epoch": 0.3583535108958838,
      "grad_norm": 1.6463013887405396,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 3.0626,
      "step": 74
    },
    {
      "epoch": 0.36319612590799033,
      "grad_norm": 1.6041393280029297,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.9819,
      "step": 75
    },
    {
      "epoch": 0.36803874092009686,
      "grad_norm": 2.1586506366729736,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 3.2151,
      "step": 76
    },
    {
      "epoch": 0.3728813559322034,
      "grad_norm": 1.8652886152267456,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.8469,
      "step": 77
    },
    {
      "epoch": 0.37772397094430993,
      "grad_norm": 1.0568983554840088,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 3.0914,
      "step": 78
    },
    {
      "epoch": 0.38256658595641646,
      "grad_norm": 2.529310941696167,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.9987,
      "step": 79
    },
    {
      "epoch": 0.387409200968523,
      "grad_norm": 2.5289180278778076,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 3.3993,
      "step": 80
    },
    {
      "epoch": 0.3922518159806295,
      "grad_norm": 1.687282681465149,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 3.1609,
      "step": 81
    },
    {
      "epoch": 0.3922518159806295,
      "eval_loss": 3.032550573348999,
      "eval_runtime": 18.9409,
      "eval_samples_per_second": 9.186,
      "eval_steps_per_second": 1.162,
      "step": 81
    },
    {
      "epoch": 0.39709443099273606,
      "grad_norm": 1.1963615417480469,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.1623,
      "step": 82
    },
    {
      "epoch": 0.4019370460048426,
      "grad_norm": 1.187296748161316,
      "learning_rate": 8.548121372247918e-06,
      "loss": 3.0359,
      "step": 83
    },
    {
      "epoch": 0.4067796610169492,
      "grad_norm": 2.5232021808624268,
      "learning_rate": 7.597595192178702e-06,
      "loss": 3.042,
      "step": 84
    },
    {
      "epoch": 0.4116222760290557,
      "grad_norm": 0.9182229042053223,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.8504,
      "step": 85
    },
    {
      "epoch": 0.41646489104116224,
      "grad_norm": 1.5995279550552368,
      "learning_rate": 5.852620357053651e-06,
      "loss": 3.1284,
      "step": 86
    },
    {
      "epoch": 0.4213075060532688,
      "grad_norm": 0.9825161695480347,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.8729,
      "step": 87
    },
    {
      "epoch": 0.4261501210653753,
      "grad_norm": 1.644863486289978,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.9239,
      "step": 88
    },
    {
      "epoch": 0.43099273607748184,
      "grad_norm": 1.652917742729187,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.978,
      "step": 89
    },
    {
      "epoch": 0.4358353510895884,
      "grad_norm": 1.7402114868164062,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 3.2838,
      "step": 90
    },
    {
      "epoch": 0.4358353510895884,
      "eval_loss": 3.0317323207855225,
      "eval_runtime": 18.9411,
      "eval_samples_per_second": 9.186,
      "eval_steps_per_second": 1.161,
      "step": 90
    },
    {
      "epoch": 0.4406779661016949,
      "grad_norm": 0.950768232345581,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.9166,
      "step": 91
    },
    {
      "epoch": 0.44552058111380144,
      "grad_norm": 1.404856562614441,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.0537,
      "step": 92
    },
    {
      "epoch": 0.45036319612590797,
      "grad_norm": 2.394108772277832,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 3.1149,
      "step": 93
    },
    {
      "epoch": 0.4552058111380145,
      "grad_norm": 0.9558013677597046,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.8942,
      "step": 94
    },
    {
      "epoch": 0.4600484261501211,
      "grad_norm": 1.7184518575668335,
      "learning_rate": 7.596123493895991e-07,
      "loss": 3.172,
      "step": 95
    },
    {
      "epoch": 0.4648910411622276,
      "grad_norm": 1.2304576635360718,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.854,
      "step": 96
    },
    {
      "epoch": 0.46973365617433416,
      "grad_norm": 0.9844062328338623,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.823,
      "step": 97
    },
    {
      "epoch": 0.4745762711864407,
      "grad_norm": 1.5699692964553833,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 3.0896,
      "step": 98
    },
    {
      "epoch": 0.4794188861985472,
      "grad_norm": 0.9208653569221497,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.8619,
      "step": 99
    },
    {
      "epoch": 0.4794188861985472,
      "eval_loss": 3.029693603515625,
      "eval_runtime": 18.916,
      "eval_samples_per_second": 9.199,
      "eval_steps_per_second": 1.163,
      "step": 99
    },
    {
      "epoch": 0.48426150121065376,
      "grad_norm": 1.2649552822113037,
      "learning_rate": 0.0,
      "loss": 2.9492,
      "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": 7.41887283560448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}