{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016886187098953058,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016886187098953058,
      "grad_norm": 13.738941192626953,
      "learning_rate": 1e-05,
      "loss": 6.6647,
      "step": 1
    },
    {
      "epoch": 0.00016886187098953058,
      "eval_loss": 7.013807773590088,
      "eval_runtime": 547.6222,
      "eval_samples_per_second": 9.107,
      "eval_steps_per_second": 1.139,
      "step": 1
    },
    {
      "epoch": 0.00033772374197906115,
      "grad_norm": 11.927528381347656,
      "learning_rate": 2e-05,
      "loss": 6.6838,
      "step": 2
    },
    {
      "epoch": 0.0005065856129685917,
      "grad_norm": 12.927790641784668,
      "learning_rate": 3e-05,
      "loss": 6.7555,
      "step": 3
    },
    {
      "epoch": 0.0006754474839581223,
      "grad_norm": 16.575254440307617,
      "learning_rate": 4e-05,
      "loss": 6.658,
      "step": 4
    },
    {
      "epoch": 0.0008443093549476528,
      "grad_norm": 16.825057983398438,
      "learning_rate": 5e-05,
      "loss": 6.912,
      "step": 5
    },
    {
      "epoch": 0.0010131712259371835,
      "grad_norm": 19.55130958557129,
      "learning_rate": 6e-05,
      "loss": 7.1032,
      "step": 6
    },
    {
      "epoch": 0.001182033096926714,
      "grad_norm": 18.538299560546875,
      "learning_rate": 7e-05,
      "loss": 5.4669,
      "step": 7
    },
    {
      "epoch": 0.0013508949679162446,
      "grad_norm": 16.627212524414062,
      "learning_rate": 8e-05,
      "loss": 3.6652,
      "step": 8
    },
    {
      "epoch": 0.001519756838905775,
      "grad_norm": 17.426902770996094,
      "learning_rate": 9e-05,
      "loss": 1.4218,
      "step": 9
    },
    {
      "epoch": 0.001519756838905775,
      "eval_loss": 1.1324265003204346,
      "eval_runtime": 547.8033,
      "eval_samples_per_second": 9.104,
      "eval_steps_per_second": 1.139,
      "step": 9
    },
    {
      "epoch": 0.0016886187098953055,
      "grad_norm": 9.461427688598633,
      "learning_rate": 0.0001,
      "loss": 0.8645,
      "step": 10
    },
    {
      "epoch": 0.0018574805808848362,
      "grad_norm": 14.465333938598633,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.5779,
      "step": 11
    },
    {
      "epoch": 0.002026342451874367,
      "grad_norm": 4.43085241317749,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.2061,
      "step": 12
    },
    {
      "epoch": 0.002195204322863897,
      "grad_norm": 3.272099018096924,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.2045,
      "step": 13
    },
    {
      "epoch": 0.002364066193853428,
      "grad_norm": 6.308006763458252,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.151,
      "step": 14
    },
    {
      "epoch": 0.0025329280648429585,
      "grad_norm": 2.1944222450256348,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0865,
      "step": 15
    },
    {
      "epoch": 0.002701789935832489,
      "grad_norm": 3.657510280609131,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0805,
      "step": 16
    },
    {
      "epoch": 0.0028706518068220195,
      "grad_norm": 7.360884189605713,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.2637,
      "step": 17
    },
    {
      "epoch": 0.00303951367781155,
      "grad_norm": 7.242488384246826,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.2653,
      "step": 18
    },
    {
      "epoch": 0.00303951367781155,
      "eval_loss": 0.1920052468776703,
      "eval_runtime": 548.1102,
      "eval_samples_per_second": 9.099,
      "eval_steps_per_second": 1.138,
      "step": 18
    },
    {
      "epoch": 0.003208375548801081,
      "grad_norm": 4.502208709716797,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0484,
      "step": 19
    },
    {
      "epoch": 0.003377237419790611,
      "grad_norm": 22.75486946105957,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.4917,
      "step": 20
    },
    {
      "epoch": 0.0035460992907801418,
      "grad_norm": 10.100854873657227,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3209,
      "step": 21
    },
    {
      "epoch": 0.0037149611617696724,
      "grad_norm": 7.107204437255859,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1272,
      "step": 22
    },
    {
      "epoch": 0.003883823032759203,
      "grad_norm": 8.472229957580566,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1549,
      "step": 23
    },
    {
      "epoch": 0.004052684903748734,
      "grad_norm": 7.11989164352417,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.3053,
      "step": 24
    },
    {
      "epoch": 0.0042215467747382645,
      "grad_norm": 8.643906593322754,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.467,
      "step": 25
    },
    {
      "epoch": 0.004390408645727794,
      "grad_norm": 11.489653587341309,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.6607,
      "step": 26
    },
    {
      "epoch": 0.004559270516717325,
      "grad_norm": 10.87166690826416,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.251,
      "step": 27
    },
    {
      "epoch": 0.004559270516717325,
      "eval_loss": 0.19702549278736115,
      "eval_runtime": 549.5055,
      "eval_samples_per_second": 9.075,
      "eval_steps_per_second": 1.136,
      "step": 27
    },
    {
      "epoch": 0.004728132387706856,
      "grad_norm": 4.551630973815918,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1867,
      "step": 28
    },
    {
      "epoch": 0.004896994258696386,
      "grad_norm": 4.584312915802002,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.1185,
      "step": 29
    },
    {
      "epoch": 0.005065856129685917,
      "grad_norm": 3.1855695247650146,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0763,
      "step": 30
    },
    {
      "epoch": 0.005234718000675448,
      "grad_norm": 3.6154963970184326,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.1514,
      "step": 31
    },
    {
      "epoch": 0.005403579871664978,
      "grad_norm": 2.6439056396484375,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.106,
      "step": 32
    },
    {
      "epoch": 0.005572441742654508,
      "grad_norm": 3.4792051315307617,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.2561,
      "step": 33
    },
    {
      "epoch": 0.005741303613644039,
      "grad_norm": 2.5845413208007812,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0694,
      "step": 34
    },
    {
      "epoch": 0.00591016548463357,
      "grad_norm": 5.633108615875244,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.2615,
      "step": 35
    },
    {
      "epoch": 0.0060790273556231,
      "grad_norm": 1.69390070438385,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0489,
      "step": 36
    },
    {
      "epoch": 0.0060790273556231,
      "eval_loss": 0.14112035930156708,
      "eval_runtime": 549.905,
      "eval_samples_per_second": 9.069,
      "eval_steps_per_second": 1.135,
      "step": 36
    },
    {
      "epoch": 0.006247889226612631,
      "grad_norm": 3.9095728397369385,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.177,
      "step": 37
    },
    {
      "epoch": 0.006416751097602162,
      "grad_norm": 3.213510751724243,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.1018,
      "step": 38
    },
    {
      "epoch": 0.006585612968591692,
      "grad_norm": 0.6583210825920105,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0182,
      "step": 39
    },
    {
      "epoch": 0.006754474839581222,
      "grad_norm": 2.233595371246338,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0855,
      "step": 40
    },
    {
      "epoch": 0.006923336710570753,
      "grad_norm": 4.077779769897461,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.2739,
      "step": 41
    },
    {
      "epoch": 0.0070921985815602835,
      "grad_norm": 0.9433442950248718,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0213,
      "step": 42
    },
    {
      "epoch": 0.007261060452549814,
      "grad_norm": 1.9460291862487793,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0612,
      "step": 43
    },
    {
      "epoch": 0.007429922323539345,
      "grad_norm": 1.7257614135742188,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0572,
      "step": 44
    },
    {
      "epoch": 0.007598784194528876,
      "grad_norm": 2.224824905395508,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0212,
      "step": 45
    },
    {
      "epoch": 0.007598784194528876,
      "eval_loss": 0.11776414513587952,
      "eval_runtime": 549.1937,
      "eval_samples_per_second": 9.081,
      "eval_steps_per_second": 1.136,
      "step": 45
    },
    {
      "epoch": 0.007767646065518406,
      "grad_norm": 2.233121395111084,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0473,
      "step": 46
    },
    {
      "epoch": 0.007936507936507936,
      "grad_norm": 5.550644874572754,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.3432,
      "step": 47
    },
    {
      "epoch": 0.008105369807497468,
      "grad_norm": 1.9874426126480103,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0844,
      "step": 48
    },
    {
      "epoch": 0.008274231678486997,
      "grad_norm": 0.4189305901527405,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0099,
      "step": 49
    },
    {
      "epoch": 0.008443093549476529,
      "grad_norm": 4.122661590576172,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0626,
      "step": 50
    },
    {
      "epoch": 0.008611955420466059,
      "grad_norm": 1.935459852218628,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0458,
      "step": 51
    },
    {
      "epoch": 0.008780817291455589,
      "grad_norm": 4.436528205871582,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2329,
      "step": 52
    },
    {
      "epoch": 0.00894967916244512,
      "grad_norm": 5.652027130126953,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.246,
      "step": 53
    },
    {
      "epoch": 0.00911854103343465,
      "grad_norm": 2.375805616378784,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0326,
      "step": 54
    },
    {
      "epoch": 0.00911854103343465,
      "eval_loss": 0.09233339130878448,
      "eval_runtime": 549.7539,
      "eval_samples_per_second": 9.071,
      "eval_steps_per_second": 1.135,
      "step": 54
    },
    {
      "epoch": 0.009287402904424182,
      "grad_norm": 3.6387789249420166,
      "learning_rate": 5e-05,
      "loss": 0.2236,
      "step": 55
    },
    {
      "epoch": 0.009456264775413711,
      "grad_norm": 2.7353525161743164,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.137,
      "step": 56
    },
    {
      "epoch": 0.009625126646403243,
      "grad_norm": 4.310062885284424,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.2697,
      "step": 57
    },
    {
      "epoch": 0.009793988517392773,
      "grad_norm": 4.689754486083984,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1093,
      "step": 58
    },
    {
      "epoch": 0.009962850388382303,
      "grad_norm": 0.28570395708084106,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0058,
      "step": 59
    },
    {
      "epoch": 0.010131712259371834,
      "grad_norm": 2.6869800090789795,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1282,
      "step": 60
    },
    {
      "epoch": 0.010300574130361364,
      "grad_norm": 3.4605836868286133,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0432,
      "step": 61
    },
    {
      "epoch": 0.010469436001350895,
      "grad_norm": 2.410428047180176,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0395,
      "step": 62
    },
    {
      "epoch": 0.010638297872340425,
      "grad_norm": 0.8962574005126953,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0161,
      "step": 63
    },
    {
      "epoch": 0.010638297872340425,
      "eval_loss": 0.08070806413888931,
      "eval_runtime": 548.9743,
      "eval_samples_per_second": 9.084,
      "eval_steps_per_second": 1.137,
      "step": 63
    },
    {
      "epoch": 0.010807159743329957,
      "grad_norm": 2.4982762336730957,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1033,
      "step": 64
    },
    {
      "epoch": 0.010976021614319487,
      "grad_norm": 2.2008962631225586,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0379,
      "step": 65
    },
    {
      "epoch": 0.011144883485309016,
      "grad_norm": 2.7710535526275635,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.056,
      "step": 66
    },
    {
      "epoch": 0.011313745356298548,
      "grad_norm": 1.5169901847839355,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.1376,
      "step": 67
    },
    {
      "epoch": 0.011482607227288078,
      "grad_norm": 4.770974636077881,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.2865,
      "step": 68
    },
    {
      "epoch": 0.01165146909827761,
      "grad_norm": 1.257779836654663,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0276,
      "step": 69
    },
    {
      "epoch": 0.01182033096926714,
      "grad_norm": 1.8166325092315674,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0374,
      "step": 70
    },
    {
      "epoch": 0.01198919284025667,
      "grad_norm": 2.774444103240967,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0976,
      "step": 71
    },
    {
      "epoch": 0.0121580547112462,
      "grad_norm": 2.698269844055176,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.144,
      "step": 72
    },
    {
      "epoch": 0.0121580547112462,
      "eval_loss": 0.0661754235625267,
      "eval_runtime": 548.8204,
      "eval_samples_per_second": 9.087,
      "eval_steps_per_second": 1.137,
      "step": 72
    },
    {
      "epoch": 0.01232691658223573,
      "grad_norm": 0.39094191789627075,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0049,
      "step": 73
    },
    {
      "epoch": 0.012495778453225262,
      "grad_norm": 1.9535773992538452,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0903,
      "step": 74
    },
    {
      "epoch": 0.012664640324214792,
      "grad_norm": 4.114951133728027,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.2374,
      "step": 75
    },
    {
      "epoch": 0.012833502195204323,
      "grad_norm": 6.92727518081665,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0763,
      "step": 76
    },
    {
      "epoch": 0.013002364066193853,
      "grad_norm": 2.045363187789917,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0438,
      "step": 77
    },
    {
      "epoch": 0.013171225937183385,
      "grad_norm": 0.5398113131523132,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0111,
      "step": 78
    },
    {
      "epoch": 0.013340087808172914,
      "grad_norm": 0.021576276049017906,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0005,
      "step": 79
    },
    {
      "epoch": 0.013508949679162444,
      "grad_norm": 2.4949581623077393,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0727,
      "step": 80
    },
    {
      "epoch": 0.013677811550151976,
      "grad_norm": 3.859738349914551,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.1469,
      "step": 81
    },
    {
      "epoch": 0.013677811550151976,
      "eval_loss": 0.055368997156620026,
      "eval_runtime": 549.2203,
      "eval_samples_per_second": 9.08,
      "eval_steps_per_second": 1.136,
      "step": 81
    },
    {
      "epoch": 0.013846673421141506,
      "grad_norm": 2.325451135635376,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0345,
      "step": 82
    },
    {
      "epoch": 0.014015535292131037,
      "grad_norm": 0.9638977646827698,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0166,
      "step": 83
    },
    {
      "epoch": 0.014184397163120567,
      "grad_norm": 0.6836529970169067,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0114,
      "step": 84
    },
    {
      "epoch": 0.014353259034110099,
      "grad_norm": 2.1207351684570312,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0357,
      "step": 85
    },
    {
      "epoch": 0.014522120905099628,
      "grad_norm": 0.31320345401763916,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.004,
      "step": 86
    },
    {
      "epoch": 0.014690982776089158,
      "grad_norm": 2.221935272216797,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1703,
      "step": 87
    },
    {
      "epoch": 0.01485984464707869,
      "grad_norm": 0.486160010099411,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0152,
      "step": 88
    },
    {
      "epoch": 0.01502870651806822,
      "grad_norm": 0.8668288588523865,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0133,
      "step": 89
    },
    {
      "epoch": 0.015197568389057751,
      "grad_norm": 2.698561429977417,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1563,
      "step": 90
    },
    {
      "epoch": 0.015197568389057751,
      "eval_loss": 0.05165484547615051,
      "eval_runtime": 549.0935,
      "eval_samples_per_second": 9.082,
      "eval_steps_per_second": 1.136,
      "step": 90
    },
    {
      "epoch": 0.015366430260047281,
      "grad_norm": 1.8739296197891235,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0499,
      "step": 91
    },
    {
      "epoch": 0.015535292131036813,
      "grad_norm": 1.749314546585083,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1767,
      "step": 92
    },
    {
      "epoch": 0.015704154002026342,
      "grad_norm": 2.652275800704956,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1609,
      "step": 93
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 2.8473572731018066,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.348,
      "step": 94
    },
    {
      "epoch": 0.016041877744005402,
      "grad_norm": 1.411710500717163,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0292,
      "step": 95
    },
    {
      "epoch": 0.016210739614994935,
      "grad_norm": 3.422239065170288,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0503,
      "step": 96
    },
    {
      "epoch": 0.016379601485984465,
      "grad_norm": 0.6517059803009033,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0131,
      "step": 97
    },
    {
      "epoch": 0.016548463356973995,
      "grad_norm": 1.2050694227218628,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0304,
      "step": 98
    },
    {
      "epoch": 0.016717325227963525,
      "grad_norm": 2.157958984375,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0815,
      "step": 99
    },
    {
      "epoch": 0.016717325227963525,
      "eval_loss": 0.05151946842670441,
      "eval_runtime": 549.1548,
      "eval_samples_per_second": 9.081,
      "eval_steps_per_second": 1.136,
      "step": 99
    },
    {
      "epoch": 0.016886187098953058,
      "grad_norm": 0.8211965560913086,
      "learning_rate": 0.0,
      "loss": 0.0152,
      "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
}