{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5763688760806917,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005763688760806916,
      "grad_norm": 2.4409587383270264,
      "learning_rate": 1e-05,
      "loss": 5.5006,
      "step": 1
    },
    {
      "epoch": 0.005763688760806916,
      "eval_loss": 5.976919174194336,
      "eval_runtime": 0.8589,
      "eval_samples_per_second": 678.789,
      "eval_steps_per_second": 22.122,
      "step": 1
    },
    {
      "epoch": 0.011527377521613832,
      "grad_norm": 2.5246589183807373,
      "learning_rate": 2e-05,
      "loss": 5.7539,
      "step": 2
    },
    {
      "epoch": 0.01729106628242075,
      "grad_norm": 5.136504173278809,
      "learning_rate": 3e-05,
      "loss": 5.7782,
      "step": 3
    },
    {
      "epoch": 0.023054755043227664,
      "grad_norm": 1.6736292839050293,
      "learning_rate": 4e-05,
      "loss": 5.7622,
      "step": 4
    },
    {
      "epoch": 0.02881844380403458,
      "grad_norm": 2.1508893966674805,
      "learning_rate": 5e-05,
      "loss": 5.9264,
      "step": 5
    },
    {
      "epoch": 0.0345821325648415,
      "grad_norm": 2.719834089279175,
      "learning_rate": 6e-05,
      "loss": 5.6231,
      "step": 6
    },
    {
      "epoch": 0.040345821325648415,
      "grad_norm": 1.862425684928894,
      "learning_rate": 7e-05,
      "loss": 5.7143,
      "step": 7
    },
    {
      "epoch": 0.04610951008645533,
      "grad_norm": 2.0583953857421875,
      "learning_rate": 8e-05,
      "loss": 5.7937,
      "step": 8
    },
    {
      "epoch": 0.05187319884726225,
      "grad_norm": 3.5244977474212646,
      "learning_rate": 9e-05,
      "loss": 5.5759,
      "step": 9
    },
    {
      "epoch": 0.05187319884726225,
      "eval_loss": 5.762571334838867,
      "eval_runtime": 0.8404,
      "eval_samples_per_second": 693.698,
      "eval_steps_per_second": 22.608,
      "step": 9
    },
    {
      "epoch": 0.05763688760806916,
      "grad_norm": 2.2905080318450928,
      "learning_rate": 0.0001,
      "loss": 5.6307,
      "step": 10
    },
    {
      "epoch": 0.06340057636887608,
      "grad_norm": 2.9346985816955566,
      "learning_rate": 9.99695413509548e-05,
      "loss": 5.5274,
      "step": 11
    },
    {
      "epoch": 0.069164265129683,
      "grad_norm": 3.4477925300598145,
      "learning_rate": 9.987820251299122e-05,
      "loss": 5.4946,
      "step": 12
    },
    {
      "epoch": 0.07492795389048991,
      "grad_norm": 2.5624496936798096,
      "learning_rate": 9.972609476841367e-05,
      "loss": 5.5983,
      "step": 13
    },
    {
      "epoch": 0.08069164265129683,
      "grad_norm": 2.30907940864563,
      "learning_rate": 9.951340343707852e-05,
      "loss": 4.965,
      "step": 14
    },
    {
      "epoch": 0.08645533141210375,
      "grad_norm": 3.060831308364868,
      "learning_rate": 9.924038765061042e-05,
      "loss": 5.0549,
      "step": 15
    },
    {
      "epoch": 0.09221902017291066,
      "grad_norm": 1.7213447093963623,
      "learning_rate": 9.890738003669029e-05,
      "loss": 5.1858,
      "step": 16
    },
    {
      "epoch": 0.09798270893371758,
      "grad_norm": 1.8246761560440063,
      "learning_rate": 9.851478631379982e-05,
      "loss": 5.1216,
      "step": 17
    },
    {
      "epoch": 0.1037463976945245,
      "grad_norm": 1.6783112287521362,
      "learning_rate": 9.806308479691595e-05,
      "loss": 5.0034,
      "step": 18
    },
    {
      "epoch": 0.1037463976945245,
      "eval_loss": 4.902072429656982,
      "eval_runtime": 0.8459,
      "eval_samples_per_second": 689.167,
      "eval_steps_per_second": 22.46,
      "step": 18
    },
    {
      "epoch": 0.10951008645533142,
      "grad_norm": 1.777565836906433,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.9386,
      "step": 19
    },
    {
      "epoch": 0.11527377521613832,
      "grad_norm": 2.9292523860931396,
      "learning_rate": 9.698463103929542e-05,
      "loss": 4.5237,
      "step": 20
    },
    {
      "epoch": 0.12103746397694524,
      "grad_norm": 1.343632459640503,
      "learning_rate": 9.635919272833938e-05,
      "loss": 4.4949,
      "step": 21
    },
    {
      "epoch": 0.12680115273775217,
      "grad_norm": 1.9242039918899536,
      "learning_rate": 9.567727288213005e-05,
      "loss": 4.7291,
      "step": 22
    },
    {
      "epoch": 0.13256484149855907,
      "grad_norm": 1.7752628326416016,
      "learning_rate": 9.493970231495835e-05,
      "loss": 4.6048,
      "step": 23
    },
    {
      "epoch": 0.138328530259366,
      "grad_norm": 1.608022689819336,
      "learning_rate": 9.414737964294636e-05,
      "loss": 4.3314,
      "step": 24
    },
    {
      "epoch": 0.1440922190201729,
      "grad_norm": 1.1817405223846436,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.163,
      "step": 25
    },
    {
      "epoch": 0.14985590778097982,
      "grad_norm": 1.5801705121994019,
      "learning_rate": 9.24024048078213e-05,
      "loss": 4.3659,
      "step": 26
    },
    {
      "epoch": 0.15561959654178675,
      "grad_norm": 3.451111316680908,
      "learning_rate": 9.145187862775209e-05,
      "loss": 4.3982,
      "step": 27
    },
    {
      "epoch": 0.15561959654178675,
      "eval_loss": 4.300004005432129,
      "eval_runtime": 0.8515,
      "eval_samples_per_second": 684.681,
      "eval_steps_per_second": 22.314,
      "step": 27
    },
    {
      "epoch": 0.16138328530259366,
      "grad_norm": 1.6136767864227295,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.3207,
      "step": 28
    },
    {
      "epoch": 0.16714697406340057,
      "grad_norm": 1.5284059047698975,
      "learning_rate": 8.940053768033609e-05,
      "loss": 4.2439,
      "step": 29
    },
    {
      "epoch": 0.1729106628242075,
      "grad_norm": 1.335671305656433,
      "learning_rate": 8.83022221559489e-05,
      "loss": 3.9352,
      "step": 30
    },
    {
      "epoch": 0.1786743515850144,
      "grad_norm": 2.7042202949523926,
      "learning_rate": 8.715724127386972e-05,
      "loss": 4.0291,
      "step": 31
    },
    {
      "epoch": 0.1844380403458213,
      "grad_norm": 2.1285061836242676,
      "learning_rate": 8.596699001693255e-05,
      "loss": 3.9501,
      "step": 32
    },
    {
      "epoch": 0.19020172910662825,
      "grad_norm": 1.8937512636184692,
      "learning_rate": 8.473291852294987e-05,
      "loss": 3.7774,
      "step": 33
    },
    {
      "epoch": 0.19596541786743515,
      "grad_norm": 1.931766152381897,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.7974,
      "step": 34
    },
    {
      "epoch": 0.2017291066282421,
      "grad_norm": 1.651713490486145,
      "learning_rate": 8.213938048432697e-05,
      "loss": 3.8174,
      "step": 35
    },
    {
      "epoch": 0.207492795389049,
      "grad_norm": 1.7000616788864136,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.8321,
      "step": 36
    },
    {
      "epoch": 0.207492795389049,
      "eval_loss": 3.770657777786255,
      "eval_runtime": 0.8553,
      "eval_samples_per_second": 681.651,
      "eval_steps_per_second": 22.215,
      "step": 36
    },
    {
      "epoch": 0.2132564841498559,
      "grad_norm": 1.4033437967300415,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.7747,
      "step": 37
    },
    {
      "epoch": 0.21902017291066284,
      "grad_norm": 2.2183494567871094,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.7118,
      "step": 38
    },
    {
      "epoch": 0.22478386167146974,
      "grad_norm": 1.5647684335708618,
      "learning_rate": 7.649596321166024e-05,
      "loss": 3.6716,
      "step": 39
    },
    {
      "epoch": 0.23054755043227665,
      "grad_norm": 1.6753904819488525,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.4879,
      "step": 40
    },
    {
      "epoch": 0.23631123919308358,
      "grad_norm": 1.5152138471603394,
      "learning_rate": 7.347357813929454e-05,
      "loss": 3.4866,
      "step": 41
    },
    {
      "epoch": 0.2420749279538905,
      "grad_norm": 1.228210210800171,
      "learning_rate": 7.191855733945387e-05,
      "loss": 3.4079,
      "step": 42
    },
    {
      "epoch": 0.2478386167146974,
      "grad_norm": 1.3091694116592407,
      "learning_rate": 7.033683215379002e-05,
      "loss": 3.7129,
      "step": 43
    },
    {
      "epoch": 0.25360230547550433,
      "grad_norm": 1.4786443710327148,
      "learning_rate": 6.873032967079561e-05,
      "loss": 3.3594,
      "step": 44
    },
    {
      "epoch": 0.25936599423631124,
      "grad_norm": 1.6930687427520752,
      "learning_rate": 6.710100716628344e-05,
      "loss": 3.4402,
      "step": 45
    },
    {
      "epoch": 0.25936599423631124,
      "eval_loss": 3.5291929244995117,
      "eval_runtime": 0.8391,
      "eval_samples_per_second": 694.79,
      "eval_steps_per_second": 22.643,
      "step": 45
    },
    {
      "epoch": 0.26512968299711814,
      "grad_norm": 1.3388841152191162,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.2864,
      "step": 46
    },
    {
      "epoch": 0.27089337175792505,
      "grad_norm": 1.3085576295852661,
      "learning_rate": 6.378186779084995e-05,
      "loss": 3.5233,
      "step": 47
    },
    {
      "epoch": 0.276657060518732,
      "grad_norm": 1.5007169246673584,
      "learning_rate": 6.209609477998338e-05,
      "loss": 3.4159,
      "step": 48
    },
    {
      "epoch": 0.2824207492795389,
      "grad_norm": 1.2105474472045898,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 3.4101,
      "step": 49
    },
    {
      "epoch": 0.2881844380403458,
      "grad_norm": 1.4784791469573975,
      "learning_rate": 5.868240888334653e-05,
      "loss": 3.3902,
      "step": 50
    },
    {
      "epoch": 0.29394812680115273,
      "grad_norm": 1.1657159328460693,
      "learning_rate": 5.695865504800327e-05,
      "loss": 3.2061,
      "step": 51
    },
    {
      "epoch": 0.29971181556195964,
      "grad_norm": 2.5311169624328613,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.4019,
      "step": 52
    },
    {
      "epoch": 0.30547550432276654,
      "grad_norm": 0.9755938053131104,
      "learning_rate": 5.348782368720626e-05,
      "loss": 3.3383,
      "step": 53
    },
    {
      "epoch": 0.3112391930835735,
      "grad_norm": 1.1348779201507568,
      "learning_rate": 5.174497483512506e-05,
      "loss": 3.291,
      "step": 54
    },
    {
      "epoch": 0.3112391930835735,
      "eval_loss": 3.400496244430542,
      "eval_runtime": 0.8408,
      "eval_samples_per_second": 693.404,
      "eval_steps_per_second": 22.598,
      "step": 54
    },
    {
      "epoch": 0.3170028818443804,
      "grad_norm": 1.2503737211227417,
      "learning_rate": 5e-05,
      "loss": 3.3476,
      "step": 55
    },
    {
      "epoch": 0.3227665706051873,
      "grad_norm": 1.3162040710449219,
      "learning_rate": 4.825502516487497e-05,
      "loss": 3.2786,
      "step": 56
    },
    {
      "epoch": 0.3285302593659942,
      "grad_norm": 0.9366883635520935,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 3.1063,
      "step": 57
    },
    {
      "epoch": 0.33429394812680113,
      "grad_norm": 1.1236789226531982,
      "learning_rate": 4.477357683661734e-05,
      "loss": 3.2441,
      "step": 58
    },
    {
      "epoch": 0.3400576368876081,
      "grad_norm": 1.0356336832046509,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 3.2383,
      "step": 59
    },
    {
      "epoch": 0.345821325648415,
      "grad_norm": 0.9869205355644226,
      "learning_rate": 4.131759111665349e-05,
      "loss": 3.285,
      "step": 60
    },
    {
      "epoch": 0.3515850144092219,
      "grad_norm": 0.9632741808891296,
      "learning_rate": 3.960441545911204e-05,
      "loss": 3.3328,
      "step": 61
    },
    {
      "epoch": 0.3573487031700288,
      "grad_norm": 1.1241796016693115,
      "learning_rate": 3.790390522001662e-05,
      "loss": 3.2734,
      "step": 62
    },
    {
      "epoch": 0.3631123919308357,
      "grad_norm": 0.957284152507782,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 3.1737,
      "step": 63
    },
    {
      "epoch": 0.3631123919308357,
      "eval_loss": 3.323737621307373,
      "eval_runtime": 0.8415,
      "eval_samples_per_second": 692.849,
      "eval_steps_per_second": 22.58,
      "step": 63
    },
    {
      "epoch": 0.3688760806916426,
      "grad_norm": 0.9445111751556396,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.3264,
      "step": 64
    },
    {
      "epoch": 0.3746397694524496,
      "grad_norm": 0.8956809043884277,
      "learning_rate": 3.289899283371657e-05,
      "loss": 3.2459,
      "step": 65
    },
    {
      "epoch": 0.3804034582132565,
      "grad_norm": 0.9865849018096924,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.1544,
      "step": 66
    },
    {
      "epoch": 0.3861671469740634,
      "grad_norm": 0.9300174117088318,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 3.2718,
      "step": 67
    },
    {
      "epoch": 0.3919308357348703,
      "grad_norm": 0.9978016018867493,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 3.238,
      "step": 68
    },
    {
      "epoch": 0.3976945244956772,
      "grad_norm": 1.1084285974502563,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 3.1262,
      "step": 69
    },
    {
      "epoch": 0.4034582132564842,
      "grad_norm": 0.9832095503807068,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.1283,
      "step": 70
    },
    {
      "epoch": 0.4092219020172911,
      "grad_norm": 0.9915679693222046,
      "learning_rate": 2.350403678833976e-05,
      "loss": 3.2205,
      "step": 71
    },
    {
      "epoch": 0.414985590778098,
      "grad_norm": 1.198361873626709,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 3.3567,
      "step": 72
    },
    {
      "epoch": 0.414985590778098,
      "eval_loss": 3.2791378498077393,
      "eval_runtime": 0.8409,
      "eval_samples_per_second": 693.297,
      "eval_steps_per_second": 22.595,
      "step": 72
    },
    {
      "epoch": 0.4207492795389049,
      "grad_norm": 1.0045987367630005,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.1023,
      "step": 73
    },
    {
      "epoch": 0.4265129682997118,
      "grad_norm": 0.8780484795570374,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.9411,
      "step": 74
    },
    {
      "epoch": 0.4322766570605187,
      "grad_norm": 0.9004272818565369,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 3.1457,
      "step": 75
    },
    {
      "epoch": 0.43804034582132567,
      "grad_norm": 1.0064634084701538,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 3.2492,
      "step": 76
    },
    {
      "epoch": 0.4438040345821326,
      "grad_norm": 0.993618905544281,
      "learning_rate": 1.526708147705013e-05,
      "loss": 3.2248,
      "step": 77
    },
    {
      "epoch": 0.4495677233429395,
      "grad_norm": 0.9184038639068604,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 3.3028,
      "step": 78
    },
    {
      "epoch": 0.4553314121037464,
      "grad_norm": 1.4929434061050415,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 3.08,
      "step": 79
    },
    {
      "epoch": 0.4610951008645533,
      "grad_norm": 0.8565345406532288,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 3.0604,
      "step": 80
    },
    {
      "epoch": 0.4668587896253602,
      "grad_norm": 1.0060956478118896,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 3.2126,
      "step": 81
    },
    {
      "epoch": 0.4668587896253602,
      "eval_loss": 3.25429105758667,
      "eval_runtime": 0.8563,
      "eval_samples_per_second": 680.804,
      "eval_steps_per_second": 22.187,
      "step": 81
    },
    {
      "epoch": 0.47262247838616717,
      "grad_norm": 1.0326199531555176,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.1554,
      "step": 82
    },
    {
      "epoch": 0.4783861671469741,
      "grad_norm": 1.0476312637329102,
      "learning_rate": 8.548121372247918e-06,
      "loss": 3.0711,
      "step": 83
    },
    {
      "epoch": 0.484149855907781,
      "grad_norm": 0.9754363298416138,
      "learning_rate": 7.597595192178702e-06,
      "loss": 3.0958,
      "step": 84
    },
    {
      "epoch": 0.4899135446685879,
      "grad_norm": 0.9376251697540283,
      "learning_rate": 6.698729810778065e-06,
      "loss": 3.1599,
      "step": 85
    },
    {
      "epoch": 0.4956772334293948,
      "grad_norm": 1.141634464263916,
      "learning_rate": 5.852620357053651e-06,
      "loss": 3.3735,
      "step": 86
    },
    {
      "epoch": 0.5014409221902018,
      "grad_norm": 1.1722526550292969,
      "learning_rate": 5.060297685041659e-06,
      "loss": 3.2415,
      "step": 87
    },
    {
      "epoch": 0.5072046109510087,
      "grad_norm": 1.0881351232528687,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.1117,
      "step": 88
    },
    {
      "epoch": 0.5129682997118156,
      "grad_norm": 0.9429522752761841,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 3.2167,
      "step": 89
    },
    {
      "epoch": 0.5187319884726225,
      "grad_norm": 0.940540075302124,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 3.1963,
      "step": 90
    },
    {
      "epoch": 0.5187319884726225,
      "eval_loss": 3.24446439743042,
      "eval_runtime": 0.8414,
      "eval_samples_per_second": 692.9,
      "eval_steps_per_second": 22.582,
      "step": 90
    },
    {
      "epoch": 0.5244956772334294,
      "grad_norm": 0.9718915820121765,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 3.1742,
      "step": 91
    },
    {
      "epoch": 0.5302593659942363,
      "grad_norm": 1.0493394136428833,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.3019,
      "step": 92
    },
    {
      "epoch": 0.5360230547550432,
      "grad_norm": 0.9497436285018921,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 3.1389,
      "step": 93
    },
    {
      "epoch": 0.5417867435158501,
      "grad_norm": 0.9836515188217163,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 3.2025,
      "step": 94
    },
    {
      "epoch": 0.547550432276657,
      "grad_norm": 0.8586398959159851,
      "learning_rate": 7.596123493895991e-07,
      "loss": 3.1825,
      "step": 95
    },
    {
      "epoch": 0.553314121037464,
      "grad_norm": 0.9107511043548584,
      "learning_rate": 4.865965629214819e-07,
      "loss": 3.1041,
      "step": 96
    },
    {
      "epoch": 0.5590778097982709,
      "grad_norm": 1.0116721391677856,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 3.2034,
      "step": 97
    },
    {
      "epoch": 0.5648414985590778,
      "grad_norm": 1.0893186330795288,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 3.1851,
      "step": 98
    },
    {
      "epoch": 0.5706051873198847,
      "grad_norm": 1.1509395837783813,
      "learning_rate": 3.04586490452119e-08,
      "loss": 3.0855,
      "step": 99
    },
    {
      "epoch": 0.5706051873198847,
      "eval_loss": 3.242032051086426,
      "eval_runtime": 0.8412,
      "eval_samples_per_second": 693.07,
      "eval_steps_per_second": 22.587,
      "step": 99
    },
    {
      "epoch": 0.5763688760806917,
      "grad_norm": 0.9414284229278564,
      "learning_rate": 0.0,
      "loss": 3.0767,
      "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": 5553503443353600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}