{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004810771316978715,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.8107713169787154e-05,
      "grad_norm": 28.79413414001465,
      "learning_rate": 1e-05,
      "loss": 46.3785,
      "step": 1
    },
    {
      "epoch": 4.8107713169787154e-05,
      "eval_loss": 3.159205675125122,
      "eval_runtime": 1020.1376,
      "eval_samples_per_second": 34.319,
      "eval_steps_per_second": 17.159,
      "step": 1
    },
    {
      "epoch": 9.621542633957431e-05,
      "grad_norm": 24.000699996948242,
      "learning_rate": 2e-05,
      "loss": 54.7236,
      "step": 2
    },
    {
      "epoch": 0.00014432313950936147,
      "grad_norm": 20.53596305847168,
      "learning_rate": 3e-05,
      "loss": 50.8974,
      "step": 3
    },
    {
      "epoch": 0.00019243085267914861,
      "grad_norm": 20.681873321533203,
      "learning_rate": 4e-05,
      "loss": 47.2597,
      "step": 4
    },
    {
      "epoch": 0.00024053856584893576,
      "grad_norm": 23.725183486938477,
      "learning_rate": 5e-05,
      "loss": 48.6015,
      "step": 5
    },
    {
      "epoch": 0.00028864627901872294,
      "grad_norm": 24.895259857177734,
      "learning_rate": 6e-05,
      "loss": 49.2229,
      "step": 6
    },
    {
      "epoch": 0.0003367539921885101,
      "grad_norm": 31.08332633972168,
      "learning_rate": 7e-05,
      "loss": 49.7453,
      "step": 7
    },
    {
      "epoch": 0.00038486170535829723,
      "grad_norm": 28.04768180847168,
      "learning_rate": 8e-05,
      "loss": 45.4243,
      "step": 8
    },
    {
      "epoch": 0.0004329694185280844,
      "grad_norm": 34.26695251464844,
      "learning_rate": 9e-05,
      "loss": 45.0237,
      "step": 9
    },
    {
      "epoch": 0.0004810771316978715,
      "grad_norm": 28.066192626953125,
      "learning_rate": 0.0001,
      "loss": 40.1862,
      "step": 10
    },
    {
      "epoch": 0.0005291848448676587,
      "grad_norm": 36.87377166748047,
      "learning_rate": 9.99695413509548e-05,
      "loss": 42.7223,
      "step": 11
    },
    {
      "epoch": 0.0005772925580374459,
      "grad_norm": 51.84431457519531,
      "learning_rate": 9.987820251299122e-05,
      "loss": 41.4564,
      "step": 12
    },
    {
      "epoch": 0.000625400271207233,
      "grad_norm": 37.15995788574219,
      "learning_rate": 9.972609476841367e-05,
      "loss": 36.3818,
      "step": 13
    },
    {
      "epoch": 0.0006735079843770202,
      "grad_norm": 32.011775970458984,
      "learning_rate": 9.951340343707852e-05,
      "loss": 37.9136,
      "step": 14
    },
    {
      "epoch": 0.0007216156975468073,
      "grad_norm": 36.100765228271484,
      "learning_rate": 9.924038765061042e-05,
      "loss": 34.0668,
      "step": 15
    },
    {
      "epoch": 0.0007697234107165945,
      "grad_norm": 31.221710205078125,
      "learning_rate": 9.890738003669029e-05,
      "loss": 32.4345,
      "step": 16
    },
    {
      "epoch": 0.0008178311238863816,
      "grad_norm": 38.979557037353516,
      "learning_rate": 9.851478631379982e-05,
      "loss": 32.5324,
      "step": 17
    },
    {
      "epoch": 0.0008659388370561688,
      "grad_norm": 29.161985397338867,
      "learning_rate": 9.806308479691595e-05,
      "loss": 28.3464,
      "step": 18
    },
    {
      "epoch": 0.0009140465502259559,
      "grad_norm": 34.893436431884766,
      "learning_rate": 9.755282581475769e-05,
      "loss": 28.3675,
      "step": 19
    },
    {
      "epoch": 0.000962154263395743,
      "grad_norm": 25.342071533203125,
      "learning_rate": 9.698463103929542e-05,
      "loss": 25.7898,
      "step": 20
    },
    {
      "epoch": 0.0010102619765655302,
      "grad_norm": 29.598787307739258,
      "learning_rate": 9.635919272833938e-05,
      "loss": 27.7703,
      "step": 21
    },
    {
      "epoch": 0.0010583696897353174,
      "grad_norm": 27.906885147094727,
      "learning_rate": 9.567727288213005e-05,
      "loss": 23.4641,
      "step": 22
    },
    {
      "epoch": 0.0011064774029051045,
      "grad_norm": 36.29619216918945,
      "learning_rate": 9.493970231495835e-05,
      "loss": 26.2492,
      "step": 23
    },
    {
      "epoch": 0.0011545851160748917,
      "grad_norm": 37.084129333496094,
      "learning_rate": 9.414737964294636e-05,
      "loss": 24.152,
      "step": 24
    },
    {
      "epoch": 0.0012026928292446788,
      "grad_norm": 27.066692352294922,
      "learning_rate": 9.330127018922194e-05,
      "loss": 20.1506,
      "step": 25
    },
    {
      "epoch": 0.0012026928292446788,
      "eval_loss": 1.1929811239242554,
      "eval_runtime": 960.029,
      "eval_samples_per_second": 36.468,
      "eval_steps_per_second": 18.234,
      "step": 25
    },
    {
      "epoch": 0.001250800542414466,
      "grad_norm": 27.218626022338867,
      "learning_rate": 9.24024048078213e-05,
      "loss": 20.0776,
      "step": 26
    },
    {
      "epoch": 0.001298908255584253,
      "grad_norm": 25.43698501586914,
      "learning_rate": 9.145187862775209e-05,
      "loss": 18.0897,
      "step": 27
    },
    {
      "epoch": 0.0013470159687540403,
      "grad_norm": 26.085866928100586,
      "learning_rate": 9.045084971874738e-05,
      "loss": 17.6861,
      "step": 28
    },
    {
      "epoch": 0.0013951236819238274,
      "grad_norm": 28.28208351135254,
      "learning_rate": 8.940053768033609e-05,
      "loss": 17.7331,
      "step": 29
    },
    {
      "epoch": 0.0014432313950936146,
      "grad_norm": 20.444143295288086,
      "learning_rate": 8.83022221559489e-05,
      "loss": 15.5734,
      "step": 30
    },
    {
      "epoch": 0.0014913391082634017,
      "grad_norm": 23.68974494934082,
      "learning_rate": 8.715724127386972e-05,
      "loss": 15.233,
      "step": 31
    },
    {
      "epoch": 0.001539446821433189,
      "grad_norm": 27.690643310546875,
      "learning_rate": 8.596699001693255e-05,
      "loss": 14.4445,
      "step": 32
    },
    {
      "epoch": 0.001587554534602976,
      "grad_norm": 24.823087692260742,
      "learning_rate": 8.473291852294987e-05,
      "loss": 13.5306,
      "step": 33
    },
    {
      "epoch": 0.0016356622477727632,
      "grad_norm": 20.906787872314453,
      "learning_rate": 8.345653031794292e-05,
      "loss": 12.5153,
      "step": 34
    },
    {
      "epoch": 0.0016837699609425505,
      "grad_norm": 23.420969009399414,
      "learning_rate": 8.213938048432697e-05,
      "loss": 13.0124,
      "step": 35
    },
    {
      "epoch": 0.0017318776741123375,
      "grad_norm": 18.17311668395996,
      "learning_rate": 8.07830737662829e-05,
      "loss": 13.3438,
      "step": 36
    },
    {
      "epoch": 0.0017799853872821248,
      "grad_norm": 22.257150650024414,
      "learning_rate": 7.938926261462366e-05,
      "loss": 13.308,
      "step": 37
    },
    {
      "epoch": 0.0018280931004519118,
      "grad_norm": 29.457996368408203,
      "learning_rate": 7.795964517353735e-05,
      "loss": 13.6901,
      "step": 38
    },
    {
      "epoch": 0.001876200813621699,
      "grad_norm": 21.267175674438477,
      "learning_rate": 7.649596321166024e-05,
      "loss": 13.0333,
      "step": 39
    },
    {
      "epoch": 0.001924308526791486,
      "grad_norm": 21.757160186767578,
      "learning_rate": 7.500000000000001e-05,
      "loss": 12.0777,
      "step": 40
    },
    {
      "epoch": 0.0019724162399612733,
      "grad_norm": 14.248445510864258,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.7264,
      "step": 41
    },
    {
      "epoch": 0.0020205239531310604,
      "grad_norm": 18.01346206665039,
      "learning_rate": 7.191855733945387e-05,
      "loss": 11.4455,
      "step": 42
    },
    {
      "epoch": 0.0020686316663008474,
      "grad_norm": 16.95344352722168,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.1439,
      "step": 43
    },
    {
      "epoch": 0.002116739379470635,
      "grad_norm": 19.399534225463867,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.2624,
      "step": 44
    },
    {
      "epoch": 0.002164847092640422,
      "grad_norm": 14.035258293151855,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.0812,
      "step": 45
    },
    {
      "epoch": 0.002212954805810209,
      "grad_norm": 21.936786651611328,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.9526,
      "step": 46
    },
    {
      "epoch": 0.002261062518979996,
      "grad_norm": 37.380340576171875,
      "learning_rate": 6.378186779084995e-05,
      "loss": 11.2345,
      "step": 47
    },
    {
      "epoch": 0.0023091702321497835,
      "grad_norm": 17.827646255493164,
      "learning_rate": 6.209609477998338e-05,
      "loss": 9.6337,
      "step": 48
    },
    {
      "epoch": 0.0023572779453195705,
      "grad_norm": 18.466480255126953,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 8.5151,
      "step": 49
    },
    {
      "epoch": 0.0024053856584893576,
      "grad_norm": 26.748825073242188,
      "learning_rate": 5.868240888334653e-05,
      "loss": 9.8757,
      "step": 50
    },
    {
      "epoch": 0.0024053856584893576,
      "eval_loss": 0.5901936292648315,
      "eval_runtime": 749.3104,
      "eval_samples_per_second": 46.723,
      "eval_steps_per_second": 23.361,
      "step": 50
    },
    {
      "epoch": 0.002453493371659145,
      "grad_norm": 17.362829208374023,
      "learning_rate": 5.695865504800327e-05,
      "loss": 9.4627,
      "step": 51
    },
    {
      "epoch": 0.002501601084828932,
      "grad_norm": 15.710803031921387,
      "learning_rate": 5.522642316338268e-05,
      "loss": 7.1618,
      "step": 52
    },
    {
      "epoch": 0.002549708797998719,
      "grad_norm": 24.15390968322754,
      "learning_rate": 5.348782368720626e-05,
      "loss": 9.0488,
      "step": 53
    },
    {
      "epoch": 0.002597816511168506,
      "grad_norm": 16.362722396850586,
      "learning_rate": 5.174497483512506e-05,
      "loss": 8.9919,
      "step": 54
    },
    {
      "epoch": 0.0026459242243382936,
      "grad_norm": 19.021665573120117,
      "learning_rate": 5e-05,
      "loss": 9.1912,
      "step": 55
    },
    {
      "epoch": 0.0026940319375080807,
      "grad_norm": 17.228673934936523,
      "learning_rate": 4.825502516487497e-05,
      "loss": 8.5915,
      "step": 56
    },
    {
      "epoch": 0.0027421396506778677,
      "grad_norm": 16.646337509155273,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 8.0812,
      "step": 57
    },
    {
      "epoch": 0.0027902473638476547,
      "grad_norm": 21.439090728759766,
      "learning_rate": 4.477357683661734e-05,
      "loss": 9.7901,
      "step": 58
    },
    {
      "epoch": 0.002838355077017442,
      "grad_norm": 14.49473762512207,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 7.1048,
      "step": 59
    },
    {
      "epoch": 0.0028864627901872292,
      "grad_norm": 21.155902862548828,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.7377,
      "step": 60
    },
    {
      "epoch": 0.0029345705033570163,
      "grad_norm": 25.964038848876953,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.4005,
      "step": 61
    },
    {
      "epoch": 0.0029826782165268033,
      "grad_norm": 17.16797637939453,
      "learning_rate": 3.790390522001662e-05,
      "loss": 7.4939,
      "step": 62
    },
    {
      "epoch": 0.003030785929696591,
      "grad_norm": 18.470211029052734,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 7.8696,
      "step": 63
    },
    {
      "epoch": 0.003078893642866378,
      "grad_norm": 22.93252182006836,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 8.0851,
      "step": 64
    },
    {
      "epoch": 0.003127001356036165,
      "grad_norm": 17.68440818786621,
      "learning_rate": 3.289899283371657e-05,
      "loss": 7.3134,
      "step": 65
    },
    {
      "epoch": 0.003175109069205952,
      "grad_norm": 21.785123825073242,
      "learning_rate": 3.12696703292044e-05,
      "loss": 8.7969,
      "step": 66
    },
    {
      "epoch": 0.0032232167823757394,
      "grad_norm": 15.482522010803223,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 6.0866,
      "step": 67
    },
    {
      "epoch": 0.0032713244955455264,
      "grad_norm": 16.00934600830078,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 7.6092,
      "step": 68
    },
    {
      "epoch": 0.0033194322087153135,
      "grad_norm": 19.86813735961914,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 7.5374,
      "step": 69
    },
    {
      "epoch": 0.003367539921885101,
      "grad_norm": 19.0589542388916,
      "learning_rate": 2.500000000000001e-05,
      "loss": 7.9793,
      "step": 70
    },
    {
      "epoch": 0.003415647635054888,
      "grad_norm": 16.755290985107422,
      "learning_rate": 2.350403678833976e-05,
      "loss": 6.9908,
      "step": 71
    },
    {
      "epoch": 0.003463755348224675,
      "grad_norm": 33.61604309082031,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 6.9951,
      "step": 72
    },
    {
      "epoch": 0.003511863061394462,
      "grad_norm": 16.12103271484375,
      "learning_rate": 2.061073738537635e-05,
      "loss": 7.0701,
      "step": 73
    },
    {
      "epoch": 0.0035599707745642495,
      "grad_norm": 15.112361907958984,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 7.0203,
      "step": 74
    },
    {
      "epoch": 0.0036080784877340366,
      "grad_norm": 27.100276947021484,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 7.3535,
      "step": 75
    },
    {
      "epoch": 0.0036080784877340366,
      "eval_loss": 0.4549826979637146,
      "eval_runtime": 1059.2638,
      "eval_samples_per_second": 33.051,
      "eval_steps_per_second": 16.526,
      "step": 75
    },
    {
      "epoch": 0.0036561862009038236,
      "grad_norm": 17.09381675720215,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 7.9682,
      "step": 76
    },
    {
      "epoch": 0.0037042939140736106,
      "grad_norm": 41.06929397583008,
      "learning_rate": 1.526708147705013e-05,
      "loss": 6.666,
      "step": 77
    },
    {
      "epoch": 0.003752401627243398,
      "grad_norm": 18.997638702392578,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 8.8896,
      "step": 78
    },
    {
      "epoch": 0.003800509340413185,
      "grad_norm": 17.806833267211914,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 5.5866,
      "step": 79
    },
    {
      "epoch": 0.003848617053582972,
      "grad_norm": 16.152570724487305,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 6.114,
      "step": 80
    },
    {
      "epoch": 0.0038967247667527592,
      "grad_norm": 20.27669334411621,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 8.8004,
      "step": 81
    },
    {
      "epoch": 0.003944832479922547,
      "grad_norm": 23.097076416015625,
      "learning_rate": 9.549150281252633e-06,
      "loss": 7.4391,
      "step": 82
    },
    {
      "epoch": 0.003992940193092334,
      "grad_norm": 31.06700897216797,
      "learning_rate": 8.548121372247918e-06,
      "loss": 9.0983,
      "step": 83
    },
    {
      "epoch": 0.004041047906262121,
      "grad_norm": 22.504980087280273,
      "learning_rate": 7.597595192178702e-06,
      "loss": 8.9527,
      "step": 84
    },
    {
      "epoch": 0.004089155619431908,
      "grad_norm": 19.458494186401367,
      "learning_rate": 6.698729810778065e-06,
      "loss": 6.1833,
      "step": 85
    },
    {
      "epoch": 0.004137263332601695,
      "grad_norm": 17.132970809936523,
      "learning_rate": 5.852620357053651e-06,
      "loss": 6.1848,
      "step": 86
    },
    {
      "epoch": 0.004185371045771482,
      "grad_norm": 19.203487396240234,
      "learning_rate": 5.060297685041659e-06,
      "loss": 7.0421,
      "step": 87
    },
    {
      "epoch": 0.00423347875894127,
      "grad_norm": 19.03404426574707,
      "learning_rate": 4.322727117869951e-06,
      "loss": 7.3711,
      "step": 88
    },
    {
      "epoch": 0.004281586472111056,
      "grad_norm": 17.356229782104492,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 7.0651,
      "step": 89
    },
    {
      "epoch": 0.004329694185280844,
      "grad_norm": 17.76946258544922,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 6.8242,
      "step": 90
    },
    {
      "epoch": 0.004377801898450631,
      "grad_norm": 22.919456481933594,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 6.8237,
      "step": 91
    },
    {
      "epoch": 0.004425909611620418,
      "grad_norm": 18.166902542114258,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 6.936,
      "step": 92
    },
    {
      "epoch": 0.004474017324790205,
      "grad_norm": 17.692848205566406,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 7.2349,
      "step": 93
    },
    {
      "epoch": 0.004522125037959992,
      "grad_norm": 18.518360137939453,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 6.0009,
      "step": 94
    },
    {
      "epoch": 0.0045702327511297795,
      "grad_norm": 18.700481414794922,
      "learning_rate": 7.596123493895991e-07,
      "loss": 8.2517,
      "step": 95
    },
    {
      "epoch": 0.004618340464299567,
      "grad_norm": 16.704484939575195,
      "learning_rate": 4.865965629214819e-07,
      "loss": 6.4917,
      "step": 96
    },
    {
      "epoch": 0.004666448177469354,
      "grad_norm": 21.030405044555664,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 6.2497,
      "step": 97
    },
    {
      "epoch": 0.004714555890639141,
      "grad_norm": 20.96607780456543,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 6.0075,
      "step": 98
    },
    {
      "epoch": 0.0047626636038089285,
      "grad_norm": 22.39644432067871,
      "learning_rate": 3.04586490452119e-08,
      "loss": 6.1534,
      "step": 99
    },
    {
      "epoch": 0.004810771316978715,
      "grad_norm": 18.28731918334961,
      "learning_rate": 0.0,
      "loss": 7.457,
      "step": 100
    },
    {
      "epoch": 0.004810771316978715,
      "eval_loss": 0.43572717905044556,
      "eval_runtime": 827.9428,
      "eval_samples_per_second": 42.286,
      "eval_steps_per_second": 21.143,
      "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": 6.51499696816128e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}