{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11926058437686345,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011926058437686344,
      "grad_norm": 0.028310367837548256,
      "learning_rate": 1e-05,
      "loss": 10.3757,
      "step": 1
    },
    {
      "epoch": 0.0011926058437686344,
      "eval_loss": 10.374403953552246,
      "eval_runtime": 1.2981,
      "eval_samples_per_second": 543.892,
      "eval_steps_per_second": 68.564,
      "step": 1
    },
    {
      "epoch": 0.002385211687537269,
      "grad_norm": 0.03164586424827576,
      "learning_rate": 2e-05,
      "loss": 10.3722,
      "step": 2
    },
    {
      "epoch": 0.0035778175313059034,
      "grad_norm": 0.029512399807572365,
      "learning_rate": 3e-05,
      "loss": 10.3745,
      "step": 3
    },
    {
      "epoch": 0.004770423375074538,
      "grad_norm": 0.026691459119319916,
      "learning_rate": 4e-05,
      "loss": 10.3714,
      "step": 4
    },
    {
      "epoch": 0.005963029218843173,
      "grad_norm": 0.02487982250750065,
      "learning_rate": 5e-05,
      "loss": 10.3785,
      "step": 5
    },
    {
      "epoch": 0.007155635062611807,
      "grad_norm": 0.03070474974811077,
      "learning_rate": 6e-05,
      "loss": 10.3763,
      "step": 6
    },
    {
      "epoch": 0.008348240906380441,
      "grad_norm": 0.026400011032819748,
      "learning_rate": 7e-05,
      "loss": 10.3702,
      "step": 7
    },
    {
      "epoch": 0.009540846750149075,
      "grad_norm": 0.029420413076877594,
      "learning_rate": 8e-05,
      "loss": 10.3734,
      "step": 8
    },
    {
      "epoch": 0.01073345259391771,
      "grad_norm": 0.02753315307199955,
      "learning_rate": 9e-05,
      "loss": 10.3707,
      "step": 9
    },
    {
      "epoch": 0.01073345259391771,
      "eval_loss": 10.374176025390625,
      "eval_runtime": 1.3566,
      "eval_samples_per_second": 520.423,
      "eval_steps_per_second": 65.606,
      "step": 9
    },
    {
      "epoch": 0.011926058437686345,
      "grad_norm": 0.029479164630174637,
      "learning_rate": 0.0001,
      "loss": 10.379,
      "step": 10
    },
    {
      "epoch": 0.01311866428145498,
      "grad_norm": 0.03541594371199608,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3755,
      "step": 11
    },
    {
      "epoch": 0.014311270125223614,
      "grad_norm": 0.02918224409222603,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3716,
      "step": 12
    },
    {
      "epoch": 0.015503875968992248,
      "grad_norm": 0.024971051141619682,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3763,
      "step": 13
    },
    {
      "epoch": 0.016696481812760882,
      "grad_norm": 0.03236817568540573,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3733,
      "step": 14
    },
    {
      "epoch": 0.017889087656529516,
      "grad_norm": 0.03112615831196308,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3704,
      "step": 15
    },
    {
      "epoch": 0.01908169350029815,
      "grad_norm": 0.031148822978138924,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3724,
      "step": 16
    },
    {
      "epoch": 0.020274299344066785,
      "grad_norm": 0.023717327043414116,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3755,
      "step": 17
    },
    {
      "epoch": 0.02146690518783542,
      "grad_norm": 0.030834253877401352,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.373,
      "step": 18
    },
    {
      "epoch": 0.02146690518783542,
      "eval_loss": 10.373565673828125,
      "eval_runtime": 1.3256,
      "eval_samples_per_second": 532.577,
      "eval_steps_per_second": 67.138,
      "step": 18
    },
    {
      "epoch": 0.022659511031604056,
      "grad_norm": 0.02731081284582615,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3715,
      "step": 19
    },
    {
      "epoch": 0.02385211687537269,
      "grad_norm": 0.03342270106077194,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3723,
      "step": 20
    },
    {
      "epoch": 0.025044722719141325,
      "grad_norm": 0.026991521939635277,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.371,
      "step": 21
    },
    {
      "epoch": 0.02623732856290996,
      "grad_norm": 0.026482809334993362,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3701,
      "step": 22
    },
    {
      "epoch": 0.027429934406678593,
      "grad_norm": 0.03881950303912163,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3726,
      "step": 23
    },
    {
      "epoch": 0.028622540250447227,
      "grad_norm": 0.04189687594771385,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3686,
      "step": 24
    },
    {
      "epoch": 0.02981514609421586,
      "grad_norm": 0.02757728472352028,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3762,
      "step": 25
    },
    {
      "epoch": 0.031007751937984496,
      "grad_norm": 0.030814575031399727,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3724,
      "step": 26
    },
    {
      "epoch": 0.03220035778175313,
      "grad_norm": 0.041639234870672226,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3687,
      "step": 27
    },
    {
      "epoch": 0.03220035778175313,
      "eval_loss": 10.37288761138916,
      "eval_runtime": 1.4457,
      "eval_samples_per_second": 488.342,
      "eval_steps_per_second": 61.562,
      "step": 27
    },
    {
      "epoch": 0.033392963625521764,
      "grad_norm": 0.033235449343919754,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3687,
      "step": 28
    },
    {
      "epoch": 0.0345855694692904,
      "grad_norm": 0.03943062946200371,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3701,
      "step": 29
    },
    {
      "epoch": 0.03577817531305903,
      "grad_norm": 0.03091137297451496,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3748,
      "step": 30
    },
    {
      "epoch": 0.03697078115682767,
      "grad_norm": 0.032856788486242294,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3732,
      "step": 31
    },
    {
      "epoch": 0.0381633870005963,
      "grad_norm": 0.033723410218954086,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.372,
      "step": 32
    },
    {
      "epoch": 0.03935599284436494,
      "grad_norm": 0.03143460303544998,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3778,
      "step": 33
    },
    {
      "epoch": 0.04054859868813357,
      "grad_norm": 0.04015008732676506,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3748,
      "step": 34
    },
    {
      "epoch": 0.04174120453190221,
      "grad_norm": 0.03837386518716812,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.376,
      "step": 35
    },
    {
      "epoch": 0.04293381037567084,
      "grad_norm": 0.03937862068414688,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3753,
      "step": 36
    },
    {
      "epoch": 0.04293381037567084,
      "eval_loss": 10.372147560119629,
      "eval_runtime": 1.3806,
      "eval_samples_per_second": 511.379,
      "eval_steps_per_second": 64.466,
      "step": 36
    },
    {
      "epoch": 0.044126416219439475,
      "grad_norm": 0.0406220406293869,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3738,
      "step": 37
    },
    {
      "epoch": 0.04531902206320811,
      "grad_norm": 0.04260128363966942,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.375,
      "step": 38
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.03788283094763756,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3741,
      "step": 39
    },
    {
      "epoch": 0.04770423375074538,
      "grad_norm": 0.04250438138842583,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3744,
      "step": 40
    },
    {
      "epoch": 0.04889683959451401,
      "grad_norm": 0.04480942711234093,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3732,
      "step": 41
    },
    {
      "epoch": 0.05008944543828265,
      "grad_norm": 0.038544051349163055,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3734,
      "step": 42
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 0.04134129360318184,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3719,
      "step": 43
    },
    {
      "epoch": 0.05247465712581992,
      "grad_norm": 0.037152618169784546,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3742,
      "step": 44
    },
    {
      "epoch": 0.05366726296958855,
      "grad_norm": 0.04474302753806114,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3699,
      "step": 45
    },
    {
      "epoch": 0.05366726296958855,
      "eval_loss": 10.371367454528809,
      "eval_runtime": 1.3423,
      "eval_samples_per_second": 525.961,
      "eval_steps_per_second": 66.304,
      "step": 45
    },
    {
      "epoch": 0.054859868813357186,
      "grad_norm": 0.04609611630439758,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.378,
      "step": 46
    },
    {
      "epoch": 0.05605247465712582,
      "grad_norm": 0.05456465855240822,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3707,
      "step": 47
    },
    {
      "epoch": 0.057245080500894455,
      "grad_norm": 0.0481850728392601,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3727,
      "step": 48
    },
    {
      "epoch": 0.05843768634466309,
      "grad_norm": 0.04843265563249588,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3749,
      "step": 49
    },
    {
      "epoch": 0.05963029218843172,
      "grad_norm": 0.04366787523031235,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3662,
      "step": 50
    },
    {
      "epoch": 0.06082289803220036,
      "grad_norm": 0.04697554558515549,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3749,
      "step": 51
    },
    {
      "epoch": 0.06201550387596899,
      "grad_norm": 0.04818224534392357,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3719,
      "step": 52
    },
    {
      "epoch": 0.06320810971973763,
      "grad_norm": 0.05981869250535965,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3733,
      "step": 53
    },
    {
      "epoch": 0.06440071556350627,
      "grad_norm": 0.03551531583070755,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3679,
      "step": 54
    },
    {
      "epoch": 0.06440071556350627,
      "eval_loss": 10.370601654052734,
      "eval_runtime": 1.407,
      "eval_samples_per_second": 501.781,
      "eval_steps_per_second": 63.256,
      "step": 54
    },
    {
      "epoch": 0.06559332140727489,
      "grad_norm": 0.054153647273778915,
      "learning_rate": 5e-05,
      "loss": 10.3686,
      "step": 55
    },
    {
      "epoch": 0.06678592725104353,
      "grad_norm": 0.056153807789087296,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3693,
      "step": 56
    },
    {
      "epoch": 0.06797853309481217,
      "grad_norm": 0.059691403061151505,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3712,
      "step": 57
    },
    {
      "epoch": 0.0691711389385808,
      "grad_norm": 0.05296963453292847,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3684,
      "step": 58
    },
    {
      "epoch": 0.07036374478234943,
      "grad_norm": 0.05294171720743179,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3702,
      "step": 59
    },
    {
      "epoch": 0.07155635062611806,
      "grad_norm": 0.058304980397224426,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3684,
      "step": 60
    },
    {
      "epoch": 0.0727489564698867,
      "grad_norm": 0.05720147863030434,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3688,
      "step": 61
    },
    {
      "epoch": 0.07394156231365534,
      "grad_norm": 0.05712497606873512,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3677,
      "step": 62
    },
    {
      "epoch": 0.07513416815742398,
      "grad_norm": 0.05657053366303444,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.369,
      "step": 63
    },
    {
      "epoch": 0.07513416815742398,
      "eval_loss": 10.3699312210083,
      "eval_runtime": 1.3966,
      "eval_samples_per_second": 505.497,
      "eval_steps_per_second": 63.724,
      "step": 63
    },
    {
      "epoch": 0.0763267740011926,
      "grad_norm": 0.06129881739616394,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3663,
      "step": 64
    },
    {
      "epoch": 0.07751937984496124,
      "grad_norm": 0.05678679794073105,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3734,
      "step": 65
    },
    {
      "epoch": 0.07871198568872988,
      "grad_norm": 0.054665569216012955,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3676,
      "step": 66
    },
    {
      "epoch": 0.07990459153249851,
      "grad_norm": 0.053208716213703156,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3679,
      "step": 67
    },
    {
      "epoch": 0.08109719737626714,
      "grad_norm": 0.06714367121458054,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3629,
      "step": 68
    },
    {
      "epoch": 0.08228980322003578,
      "grad_norm": 0.05434398725628853,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3735,
      "step": 69
    },
    {
      "epoch": 0.08348240906380441,
      "grad_norm": 0.06771057844161987,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3695,
      "step": 70
    },
    {
      "epoch": 0.08467501490757305,
      "grad_norm": 0.053727179765701294,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3692,
      "step": 71
    },
    {
      "epoch": 0.08586762075134168,
      "grad_norm": 0.0703674703836441,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3643,
      "step": 72
    },
    {
      "epoch": 0.08586762075134168,
      "eval_loss": 10.369429588317871,
      "eval_runtime": 1.3413,
      "eval_samples_per_second": 526.339,
      "eval_steps_per_second": 66.352,
      "step": 72
    },
    {
      "epoch": 0.08706022659511031,
      "grad_norm": 0.05981586128473282,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3704,
      "step": 73
    },
    {
      "epoch": 0.08825283243887895,
      "grad_norm": 0.054827235639095306,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3701,
      "step": 74
    },
    {
      "epoch": 0.08944543828264759,
      "grad_norm": 0.06241114065051079,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3686,
      "step": 75
    },
    {
      "epoch": 0.09063804412641623,
      "grad_norm": 0.0732855573296547,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3666,
      "step": 76
    },
    {
      "epoch": 0.09183064997018485,
      "grad_norm": 0.05297171697020531,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3696,
      "step": 77
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 0.05004735663533211,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3691,
      "step": 78
    },
    {
      "epoch": 0.09421586165772212,
      "grad_norm": 0.056061867624521255,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3688,
      "step": 79
    },
    {
      "epoch": 0.09540846750149076,
      "grad_norm": 0.06218897923827171,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3682,
      "step": 80
    },
    {
      "epoch": 0.09660107334525939,
      "grad_norm": 0.05653758719563484,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3744,
      "step": 81
    },
    {
      "epoch": 0.09660107334525939,
      "eval_loss": 10.369139671325684,
      "eval_runtime": 1.4083,
      "eval_samples_per_second": 501.311,
      "eval_steps_per_second": 63.196,
      "step": 81
    },
    {
      "epoch": 0.09779367918902802,
      "grad_norm": 0.0647573173046112,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.371,
      "step": 82
    },
    {
      "epoch": 0.09898628503279666,
      "grad_norm": 0.0794467180967331,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3652,
      "step": 83
    },
    {
      "epoch": 0.1001788908765653,
      "grad_norm": 0.06957988440990448,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3704,
      "step": 84
    },
    {
      "epoch": 0.10137149672033392,
      "grad_norm": 0.050267431885004044,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3687,
      "step": 85
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.05273786932229996,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3704,
      "step": 86
    },
    {
      "epoch": 0.1037567084078712,
      "grad_norm": 0.050435155630111694,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3724,
      "step": 87
    },
    {
      "epoch": 0.10494931425163984,
      "grad_norm": 0.05046040192246437,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3641,
      "step": 88
    },
    {
      "epoch": 0.10614192009540847,
      "grad_norm": 0.08423416316509247,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3732,
      "step": 89
    },
    {
      "epoch": 0.1073345259391771,
      "grad_norm": 0.0676737129688263,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3709,
      "step": 90
    },
    {
      "epoch": 0.1073345259391771,
      "eval_loss": 10.369009971618652,
      "eval_runtime": 1.4423,
      "eval_samples_per_second": 489.493,
      "eval_steps_per_second": 61.707,
      "step": 90
    },
    {
      "epoch": 0.10852713178294573,
      "grad_norm": 0.061363909393548965,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.371,
      "step": 91
    },
    {
      "epoch": 0.10971973762671437,
      "grad_norm": 0.05670735239982605,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3729,
      "step": 92
    },
    {
      "epoch": 0.11091234347048301,
      "grad_norm": 0.04956693947315216,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3691,
      "step": 93
    },
    {
      "epoch": 0.11210494931425163,
      "grad_norm": 0.06154552474617958,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.369,
      "step": 94
    },
    {
      "epoch": 0.11329755515802027,
      "grad_norm": 0.07234995067119598,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3676,
      "step": 95
    },
    {
      "epoch": 0.11449016100178891,
      "grad_norm": 0.07232902944087982,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3691,
      "step": 96
    },
    {
      "epoch": 0.11568276684555755,
      "grad_norm": 0.05388721078634262,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3661,
      "step": 97
    },
    {
      "epoch": 0.11687537268932618,
      "grad_norm": 0.04916412755846977,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3708,
      "step": 98
    },
    {
      "epoch": 0.11806797853309481,
      "grad_norm": 0.06878488510847092,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3664,
      "step": 99
    },
    {
      "epoch": 0.11806797853309481,
      "eval_loss": 10.368987083435059,
      "eval_runtime": 1.3332,
      "eval_samples_per_second": 529.551,
      "eval_steps_per_second": 66.756,
      "step": 99
    },
    {
      "epoch": 0.11926058437686345,
      "grad_norm": 0.05977727845311165,
      "learning_rate": 0.0,
      "loss": 10.3683,
      "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": 5230244659200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}