{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016612675471384668,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016612675471384668,
      "grad_norm": 0.9919585585594177,
      "learning_rate": 1e-05,
      "loss": 1.8966,
      "step": 1
    },
    {
      "epoch": 0.00016612675471384668,
      "eval_loss": 1.0414841175079346,
      "eval_runtime": 673.9747,
      "eval_samples_per_second": 7.521,
      "eval_steps_per_second": 0.941,
      "step": 1
    },
    {
      "epoch": 0.00033225350942769335,
      "grad_norm": 1.5468533039093018,
      "learning_rate": 2e-05,
      "loss": 2.8453,
      "step": 2
    },
    {
      "epoch": 0.00049838026414154,
      "grad_norm": 1.3301949501037598,
      "learning_rate": 3e-05,
      "loss": 2.3285,
      "step": 3
    },
    {
      "epoch": 0.0006645070188553867,
      "grad_norm": 1.870064377784729,
      "learning_rate": 4e-05,
      "loss": 2.5663,
      "step": 4
    },
    {
      "epoch": 0.0008306337735692333,
      "grad_norm": 1.6597638130187988,
      "learning_rate": 5e-05,
      "loss": 2.1576,
      "step": 5
    },
    {
      "epoch": 0.00099676052828308,
      "grad_norm": 0.5557398796081543,
      "learning_rate": 6e-05,
      "loss": 1.2538,
      "step": 6
    },
    {
      "epoch": 0.0011628872829969267,
      "grad_norm": 0.991572916507721,
      "learning_rate": 7e-05,
      "loss": 1.6291,
      "step": 7
    },
    {
      "epoch": 0.0013290140377107734,
      "grad_norm": 0.6162525415420532,
      "learning_rate": 8e-05,
      "loss": 1.8258,
      "step": 8
    },
    {
      "epoch": 0.00149514079242462,
      "grad_norm": 1.4342612028121948,
      "learning_rate": 9e-05,
      "loss": 2.7709,
      "step": 9
    },
    {
      "epoch": 0.00149514079242462,
      "eval_loss": 0.9687274694442749,
      "eval_runtime": 675.7106,
      "eval_samples_per_second": 7.502,
      "eval_steps_per_second": 0.938,
      "step": 9
    },
    {
      "epoch": 0.0016612675471384666,
      "grad_norm": 1.043684720993042,
      "learning_rate": 0.0001,
      "loss": 1.713,
      "step": 10
    },
    {
      "epoch": 0.0018273943018523133,
      "grad_norm": 1.1158920526504517,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.2303,
      "step": 11
    },
    {
      "epoch": 0.00199352105656616,
      "grad_norm": 0.8735452890396118,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.0613,
      "step": 12
    },
    {
      "epoch": 0.0021596478112800065,
      "grad_norm": 0.6356571912765503,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.1697,
      "step": 13
    },
    {
      "epoch": 0.0023257745659938534,
      "grad_norm": 0.5694183111190796,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.2002,
      "step": 14
    },
    {
      "epoch": 0.0024919013207077,
      "grad_norm": 0.589718759059906,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.5224,
      "step": 15
    },
    {
      "epoch": 0.002658028075421547,
      "grad_norm": 1.3405238389968872,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.5344,
      "step": 16
    },
    {
      "epoch": 0.0028241548301353933,
      "grad_norm": 2.1417508125305176,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.131,
      "step": 17
    },
    {
      "epoch": 0.00299028158484924,
      "grad_norm": 1.19926917552948,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.9731,
      "step": 18
    },
    {
      "epoch": 0.00299028158484924,
      "eval_loss": 0.7821024656295776,
      "eval_runtime": 675.4552,
      "eval_samples_per_second": 7.505,
      "eval_steps_per_second": 0.939,
      "step": 18
    },
    {
      "epoch": 0.0031564083395630867,
      "grad_norm": 0.885982871055603,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3646,
      "step": 19
    },
    {
      "epoch": 0.003322535094276933,
      "grad_norm": 1.1024696826934814,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.4764,
      "step": 20
    },
    {
      "epoch": 0.00348866184899078,
      "grad_norm": 3.787921667098999,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.868,
      "step": 21
    },
    {
      "epoch": 0.0036547886037046266,
      "grad_norm": 1.1288354396820068,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.7279,
      "step": 22
    },
    {
      "epoch": 0.003820915358418473,
      "grad_norm": 1.6195688247680664,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.1748,
      "step": 23
    },
    {
      "epoch": 0.00398704211313232,
      "grad_norm": 3.927457094192505,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.8016,
      "step": 24
    },
    {
      "epoch": 0.004153168867846167,
      "grad_norm": 2.22636342048645,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.4189,
      "step": 25
    },
    {
      "epoch": 0.004319295622560013,
      "grad_norm": 1.719977855682373,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.7547,
      "step": 26
    },
    {
      "epoch": 0.00448542237727386,
      "grad_norm": 1.4725106954574585,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.498,
      "step": 27
    },
    {
      "epoch": 0.00448542237727386,
      "eval_loss": 0.7110866904258728,
      "eval_runtime": 675.4946,
      "eval_samples_per_second": 7.504,
      "eval_steps_per_second": 0.939,
      "step": 27
    },
    {
      "epoch": 0.004651549131987707,
      "grad_norm": 1.9094619750976562,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.0087,
      "step": 28
    },
    {
      "epoch": 0.004817675886701553,
      "grad_norm": 1.453922986984253,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.3544,
      "step": 29
    },
    {
      "epoch": 0.0049838026414154,
      "grad_norm": 4.656007766723633,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.3588,
      "step": 30
    },
    {
      "epoch": 0.005149929396129247,
      "grad_norm": 1.933850884437561,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.9921,
      "step": 31
    },
    {
      "epoch": 0.005316056150843094,
      "grad_norm": 1.3430155515670776,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.6642,
      "step": 32
    },
    {
      "epoch": 0.00548218290555694,
      "grad_norm": 1.802078366279602,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.4628,
      "step": 33
    },
    {
      "epoch": 0.005648309660270787,
      "grad_norm": 2.6342110633850098,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.4388,
      "step": 34
    },
    {
      "epoch": 0.0058144364149846335,
      "grad_norm": 1.334199070930481,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.0315,
      "step": 35
    },
    {
      "epoch": 0.00598056316969848,
      "grad_norm": 0.9666208028793335,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.6273,
      "step": 36
    },
    {
      "epoch": 0.00598056316969848,
      "eval_loss": 0.6773849725723267,
      "eval_runtime": 675.1591,
      "eval_samples_per_second": 7.508,
      "eval_steps_per_second": 0.939,
      "step": 36
    },
    {
      "epoch": 0.0061466899244123265,
      "grad_norm": 2.4796395301818848,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2106,
      "step": 37
    },
    {
      "epoch": 0.0063128166791261734,
      "grad_norm": 2.0141119956970215,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.0963,
      "step": 38
    },
    {
      "epoch": 0.00647894343384002,
      "grad_norm": 1.0724881887435913,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.7781,
      "step": 39
    },
    {
      "epoch": 0.006645070188553866,
      "grad_norm": 1.5177243947982788,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1593,
      "step": 40
    },
    {
      "epoch": 0.006811196943267713,
      "grad_norm": 2.06948184967041,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.6186,
      "step": 41
    },
    {
      "epoch": 0.00697732369798156,
      "grad_norm": 2.045438051223755,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.5002,
      "step": 42
    },
    {
      "epoch": 0.007143450452695406,
      "grad_norm": 1.8725861310958862,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.289,
      "step": 43
    },
    {
      "epoch": 0.007309577207409253,
      "grad_norm": 0.9375693798065186,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.0544,
      "step": 44
    },
    {
      "epoch": 0.0074757039621231,
      "grad_norm": 3.7686853408813477,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.0144,
      "step": 45
    },
    {
      "epoch": 0.0074757039621231,
      "eval_loss": 0.6617150902748108,
      "eval_runtime": 675.1702,
      "eval_samples_per_second": 7.508,
      "eval_steps_per_second": 0.939,
      "step": 45
    },
    {
      "epoch": 0.007641830716836946,
      "grad_norm": 1.291003704071045,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.3174,
      "step": 46
    },
    {
      "epoch": 0.007807957471550793,
      "grad_norm": 1.5664713382720947,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.6628,
      "step": 47
    },
    {
      "epoch": 0.00797408422626464,
      "grad_norm": 1.041298270225525,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.6944,
      "step": 48
    },
    {
      "epoch": 0.008140210980978486,
      "grad_norm": 1.353527307510376,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.7041,
      "step": 49
    },
    {
      "epoch": 0.008306337735692334,
      "grad_norm": 0.8514286875724792,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.7434,
      "step": 50
    },
    {
      "epoch": 0.00847246449040618,
      "grad_norm": 1.392175555229187,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.627,
      "step": 51
    },
    {
      "epoch": 0.008638591245120026,
      "grad_norm": 2.5748090744018555,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.297,
      "step": 52
    },
    {
      "epoch": 0.008804717999833874,
      "grad_norm": 1.3663445711135864,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.9941,
      "step": 53
    },
    {
      "epoch": 0.00897084475454772,
      "grad_norm": 1.5222846269607544,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.8739,
      "step": 54
    },
    {
      "epoch": 0.00897084475454772,
      "eval_loss": 0.6527463793754578,
      "eval_runtime": 675.2164,
      "eval_samples_per_second": 7.507,
      "eval_steps_per_second": 0.939,
      "step": 54
    },
    {
      "epoch": 0.009136971509261566,
      "grad_norm": 1.4149327278137207,
      "learning_rate": 5e-05,
      "loss": 1.0193,
      "step": 55
    },
    {
      "epoch": 0.009303098263975414,
      "grad_norm": 1.3249423503875732,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.386,
      "step": 56
    },
    {
      "epoch": 0.00946922501868926,
      "grad_norm": 1.4684275388717651,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.6665,
      "step": 57
    },
    {
      "epoch": 0.009635351773403106,
      "grad_norm": 0.864578902721405,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.6305,
      "step": 58
    },
    {
      "epoch": 0.009801478528116954,
      "grad_norm": 0.8630561828613281,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.5473,
      "step": 59
    },
    {
      "epoch": 0.0099676052828308,
      "grad_norm": 1.2544828653335571,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.0987,
      "step": 60
    },
    {
      "epoch": 0.010133732037544647,
      "grad_norm": 1.6959971189498901,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.9921,
      "step": 61
    },
    {
      "epoch": 0.010299858792258493,
      "grad_norm": 1.5748471021652222,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.033,
      "step": 62
    },
    {
      "epoch": 0.01046598554697234,
      "grad_norm": 0.922096312046051,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.8486,
      "step": 63
    },
    {
      "epoch": 0.01046598554697234,
      "eval_loss": 0.6467626094818115,
      "eval_runtime": 675.6424,
      "eval_samples_per_second": 7.502,
      "eval_steps_per_second": 0.938,
      "step": 63
    },
    {
      "epoch": 0.010632112301686187,
      "grad_norm": 1.0161826610565186,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1515,
      "step": 64
    },
    {
      "epoch": 0.010798239056400033,
      "grad_norm": 0.8706979751586914,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.8809,
      "step": 65
    },
    {
      "epoch": 0.01096436581111388,
      "grad_norm": 1.361327052116394,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.8019,
      "step": 66
    },
    {
      "epoch": 0.011130492565827727,
      "grad_norm": 0.8916012048721313,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.9665,
      "step": 67
    },
    {
      "epoch": 0.011296619320541573,
      "grad_norm": 1.261985182762146,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.5859,
      "step": 68
    },
    {
      "epoch": 0.01146274607525542,
      "grad_norm": 1.4368607997894287,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.3238,
      "step": 69
    },
    {
      "epoch": 0.011628872829969267,
      "grad_norm": 3.813182830810547,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.1585,
      "step": 70
    },
    {
      "epoch": 0.011794999584683113,
      "grad_norm": 1.8414254188537598,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.3511,
      "step": 71
    },
    {
      "epoch": 0.01196112633939696,
      "grad_norm": 2.074822187423706,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.1272,
      "step": 72
    },
    {
      "epoch": 0.01196112633939696,
      "eval_loss": 0.6417830586433411,
      "eval_runtime": 675.5888,
      "eval_samples_per_second": 7.503,
      "eval_steps_per_second": 0.938,
      "step": 72
    },
    {
      "epoch": 0.012127253094110807,
      "grad_norm": 1.6472017765045166,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.2974,
      "step": 73
    },
    {
      "epoch": 0.012293379848824653,
      "grad_norm": 0.7575200200080872,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.0512,
      "step": 74
    },
    {
      "epoch": 0.012459506603538499,
      "grad_norm": 0.760666012763977,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.3661,
      "step": 75
    },
    {
      "epoch": 0.012625633358252347,
      "grad_norm": 0.9253103733062744,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.8792,
      "step": 76
    },
    {
      "epoch": 0.012791760112966193,
      "grad_norm": 0.8572337627410889,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.4814,
      "step": 77
    },
    {
      "epoch": 0.01295788686768004,
      "grad_norm": 0.9993001222610474,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.9611,
      "step": 78
    },
    {
      "epoch": 0.013124013622393887,
      "grad_norm": 1.4929710626602173,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.0746,
      "step": 79
    },
    {
      "epoch": 0.013290140377107733,
      "grad_norm": 0.9178129434585571,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.9345,
      "step": 80
    },
    {
      "epoch": 0.01345626713182158,
      "grad_norm": 3.765681266784668,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.5544,
      "step": 81
    },
    {
      "epoch": 0.01345626713182158,
      "eval_loss": 0.6383609175682068,
      "eval_runtime": 675.7818,
      "eval_samples_per_second": 7.501,
      "eval_steps_per_second": 0.938,
      "step": 81
    },
    {
      "epoch": 0.013622393886535427,
      "grad_norm": 0.6158009767532349,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9353,
      "step": 82
    },
    {
      "epoch": 0.013788520641249273,
      "grad_norm": 1.4671916961669922,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.0639,
      "step": 83
    },
    {
      "epoch": 0.01395464739596312,
      "grad_norm": 0.7955529093742371,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.5659,
      "step": 84
    },
    {
      "epoch": 0.014120774150676967,
      "grad_norm": 1.442224144935608,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.1151,
      "step": 85
    },
    {
      "epoch": 0.014286900905390813,
      "grad_norm": 8.284345626831055,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.5541,
      "step": 86
    },
    {
      "epoch": 0.01445302766010466,
      "grad_norm": 3.518461227416992,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.1257,
      "step": 87
    },
    {
      "epoch": 0.014619154414818506,
      "grad_norm": 0.9966995120048523,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.9855,
      "step": 88
    },
    {
      "epoch": 0.014785281169532353,
      "grad_norm": 0.6061037182807922,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.334,
      "step": 89
    },
    {
      "epoch": 0.0149514079242462,
      "grad_norm": 0.7604615092277527,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.0108,
      "step": 90
    },
    {
      "epoch": 0.0149514079242462,
      "eval_loss": 0.6369998455047607,
      "eval_runtime": 675.7546,
      "eval_samples_per_second": 7.501,
      "eval_steps_per_second": 0.938,
      "step": 90
    },
    {
      "epoch": 0.015117534678960046,
      "grad_norm": 0.8596745729446411,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.0798,
      "step": 91
    },
    {
      "epoch": 0.015283661433673892,
      "grad_norm": 1.0218279361724854,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.4505,
      "step": 92
    },
    {
      "epoch": 0.01544978818838774,
      "grad_norm": 0.8115531802177429,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.9605,
      "step": 93
    },
    {
      "epoch": 0.015615914943101586,
      "grad_norm": 0.94814133644104,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.8255,
      "step": 94
    },
    {
      "epoch": 0.015782041697815434,
      "grad_norm": 0.9431392550468445,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.7101,
      "step": 95
    },
    {
      "epoch": 0.01594816845252928,
      "grad_norm": 1.5731805562973022,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.8258,
      "step": 96
    },
    {
      "epoch": 0.016114295207243126,
      "grad_norm": 0.644458532333374,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.153,
      "step": 97
    },
    {
      "epoch": 0.016280421961956972,
      "grad_norm": 3.3635175228118896,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.6484,
      "step": 98
    },
    {
      "epoch": 0.016446548716670818,
      "grad_norm": 1.0303000211715698,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.3279,
      "step": 99
    },
    {
      "epoch": 0.016446548716670818,
      "eval_loss": 0.6366809606552124,
      "eval_runtime": 675.6737,
      "eval_samples_per_second": 7.502,
      "eval_steps_per_second": 0.938,
      "step": 99
    },
    {
      "epoch": 0.016612675471384668,
      "grad_norm": 2.6675288677215576,
      "learning_rate": 0.0,
      "loss": 2.1576,
      "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": 9.638508478070784e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}