{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 71,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014222222222222223,
      "grad_norm": 0.506786584854126,
      "learning_rate": 0.0,
      "loss": 1.1951476335525513,
      "step": 1
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 0.5440636277198792,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 1.2398298978805542,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.4429919421672821,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.9777733087539673,
      "step": 3
    },
    {
      "epoch": 0.05688888888888889,
      "grad_norm": 0.34922653436660767,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.8064044713973999,
      "step": 4
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.16975589096546173,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.5294505953788757,
      "step": 5
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 0.16188450157642365,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.636877179145813,
      "step": 6
    },
    {
      "epoch": 0.09955555555555555,
      "grad_norm": 0.11110807955265045,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.6087832450866699,
      "step": 7
    },
    {
      "epoch": 0.11377777777777778,
      "grad_norm": 0.0641367956995964,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.5258303880691528,
      "step": 8
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.052072592079639435,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.5444644689559937,
      "step": 9
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.0392303504049778,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.5337975025177002,
      "step": 10
    },
    {
      "epoch": 0.15644444444444444,
      "grad_norm": 0.028075236827135086,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.45043277740478516,
      "step": 11
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 0.02663014456629753,
      "learning_rate": 5e-06,
      "loss": 0.49355342984199524,
      "step": 12
    },
    {
      "epoch": 0.18488888888888888,
      "grad_norm": 0.028838366270065308,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.487549751996994,
      "step": 13
    },
    {
      "epoch": 0.1991111111111111,
      "grad_norm": 0.03057004138827324,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.500217616558075,
      "step": 14
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.028651155531406403,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.49628522992134094,
      "step": 15
    },
    {
      "epoch": 0.22755555555555557,
      "grad_norm": 0.028336627408862114,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.48170676827430725,
      "step": 16
    },
    {
      "epoch": 0.24177777777777779,
      "grad_norm": 0.019824286922812462,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.4609394073486328,
      "step": 17
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.02125639095902443,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.4759177565574646,
      "step": 18
    },
    {
      "epoch": 0.2702222222222222,
      "grad_norm": 0.025788351893424988,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.4962843060493469,
      "step": 19
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.033310867846012115,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.5028114318847656,
      "step": 20
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.020624130964279175,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.44575220346450806,
      "step": 21
    },
    {
      "epoch": 0.3128888888888889,
      "grad_norm": 0.020986203104257584,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.4755765199661255,
      "step": 22
    },
    {
      "epoch": 0.32711111111111113,
      "grad_norm": 2526660.75,
      "learning_rate": 1e-05,
      "loss": 0.4706365466117859,
      "step": 23
    },
    {
      "epoch": 0.3413333333333333,
      "grad_norm": 0.021011805161833763,
      "learning_rate": 9.999323662872998e-06,
      "loss": 0.4945886731147766,
      "step": 24
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.020573964342474937,
      "learning_rate": 9.99729483446475e-06,
      "loss": 0.4544343054294586,
      "step": 25
    },
    {
      "epoch": 0.36977777777777776,
      "grad_norm": 0.021116767078638077,
      "learning_rate": 9.993914063644053e-06,
      "loss": 0.4556806683540344,
      "step": 26
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.019978955388069153,
      "learning_rate": 9.989182265027232e-06,
      "loss": 0.4431076645851135,
      "step": 27
    },
    {
      "epoch": 0.3982222222222222,
      "grad_norm": 0.019631512463092804,
      "learning_rate": 9.98310071873072e-06,
      "loss": 0.4541151523590088,
      "step": 28
    },
    {
      "epoch": 0.41244444444444445,
      "grad_norm": 0.01977457106113434,
      "learning_rate": 9.975671070024741e-06,
      "loss": 0.4352927803993225,
      "step": 29
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.022281618788838387,
      "learning_rate": 9.966895328888195e-06,
      "loss": 0.5559179186820984,
      "step": 30
    },
    {
      "epoch": 0.4408888888888889,
      "grad_norm": 0.018352897837758064,
      "learning_rate": 9.956775869464901e-06,
      "loss": 0.42942947149276733,
      "step": 31
    },
    {
      "epoch": 0.45511111111111113,
      "grad_norm": 0.019121287390589714,
      "learning_rate": 9.945315429421307e-06,
      "loss": 0.45916861295700073,
      "step": 32
    },
    {
      "epoch": 0.4693333333333333,
      "grad_norm": 0.01712602935731411,
      "learning_rate": 9.932517109205849e-06,
      "loss": 0.4312085807323456,
      "step": 33
    },
    {
      "epoch": 0.48355555555555557,
      "grad_norm": 0.01892935112118721,
      "learning_rate": 9.918384371210178e-06,
      "loss": 0.5169366598129272,
      "step": 34
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.02034984715282917,
      "learning_rate": 9.902921038832456e-06,
      "loss": 0.49438145756721497,
      "step": 35
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.017887447029352188,
      "learning_rate": 9.886131295443003e-06,
      "loss": 0.4683716893196106,
      "step": 36
    },
    {
      "epoch": 0.5262222222222223,
      "grad_norm": 0.01887686364352703,
      "learning_rate": 9.868019683252543e-06,
      "loss": 0.46688079833984375,
      "step": 37
    },
    {
      "epoch": 0.5404444444444444,
      "grad_norm": 0.019363289698958397,
      "learning_rate": 9.848591102083375e-06,
      "loss": 0.4786224067211151,
      "step": 38
    },
    {
      "epoch": 0.5546666666666666,
      "grad_norm": 0.0201108418405056,
      "learning_rate": 9.82785080804381e-06,
      "loss": 0.47358086705207825,
      "step": 39
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.019631700590252876,
      "learning_rate": 9.805804412106197e-06,
      "loss": 0.585416316986084,
      "step": 40
    },
    {
      "epoch": 0.5831111111111111,
      "grad_norm": 0.01689487136900425,
      "learning_rate": 9.782457878588977e-06,
      "loss": 0.47205525636672974,
      "step": 41
    },
    {
      "epoch": 0.5973333333333334,
      "grad_norm": 0.01628926210105419,
      "learning_rate": 9.75781752354311e-06,
      "loss": 0.4348371624946594,
      "step": 42
    },
    {
      "epoch": 0.6115555555555555,
      "grad_norm": 0.01758437603712082,
      "learning_rate": 9.731890013043367e-06,
      "loss": 0.4891083538532257,
      "step": 43
    },
    {
      "epoch": 0.6257777777777778,
      "grad_norm": 0.017766334116458893,
      "learning_rate": 9.704682361384941e-06,
      "loss": 0.46330946683883667,
      "step": 44
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.017524050548672676,
      "learning_rate": 9.676201929185809e-06,
      "loss": 0.4083091914653778,
      "step": 45
    },
    {
      "epoch": 0.6542222222222223,
      "grad_norm": 0.017291702330112457,
      "learning_rate": 9.646456421395447e-06,
      "loss": 0.4653710126876831,
      "step": 46
    },
    {
      "epoch": 0.6684444444444444,
      "grad_norm": 0.017993608489632607,
      "learning_rate": 9.615453885210368e-06,
      "loss": 0.4626290202140808,
      "step": 47
    },
    {
      "epoch": 0.6826666666666666,
      "grad_norm": 0.017247265204787254,
      "learning_rate": 9.583202707897075e-06,
      "loss": 0.47964128851890564,
      "step": 48
    },
    {
      "epoch": 0.6968888888888889,
      "grad_norm": 0.017244094982743263,
      "learning_rate": 9.549711614523007e-06,
      "loss": 0.46718651056289673,
      "step": 49
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.01574530452489853,
      "learning_rate": 9.514989665596114e-06,
      "loss": 0.4456287622451782,
      "step": 50
    },
    {
      "epoch": 0.7111111111111111,
      "eval_loss": 0.4940151274204254,
      "eval_runtime": 6.2328,
      "eval_samples_per_second": 32.088,
      "eval_steps_per_second": 8.022,
      "step": 50
    },
    {
      "epoch": 0.7253333333333334,
      "grad_norm": 0.01783670485019684,
      "learning_rate": 9.479046254613673e-06,
      "loss": 0.45046865940093994,
      "step": 51
    },
    {
      "epoch": 0.7395555555555555,
      "grad_norm": 0.015281656756997108,
      "learning_rate": 9.441891105521005e-06,
      "loss": 0.43093934655189514,
      "step": 52
    },
    {
      "epoch": 0.7537777777777778,
      "grad_norm": 0.017853204160928726,
      "learning_rate": 9.40353427008083e-06,
      "loss": 0.4706975519657135,
      "step": 53
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.01542010996490717,
      "learning_rate": 9.3639861251539e-06,
      "loss": 0.4405261278152466,
      "step": 54
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.017832862213253975,
      "learning_rate": 9.323257369891702e-06,
      "loss": 0.47680750489234924,
      "step": 55
    },
    {
      "epoch": 0.7964444444444444,
      "grad_norm": 0.015628881752490997,
      "learning_rate": 9.281359022841966e-06,
      "loss": 0.42392900586128235,
      "step": 56
    },
    {
      "epoch": 0.8106666666666666,
      "grad_norm": 0.01757017895579338,
      "learning_rate": 9.238302418967757e-06,
      "loss": 0.48122283816337585,
      "step": 57
    },
    {
      "epoch": 0.8248888888888889,
      "grad_norm": 0.017186852172017097,
      "learning_rate": 9.194099206580981e-06,
      "loss": 0.5255264043807983,
      "step": 58
    },
    {
      "epoch": 0.8391111111111111,
      "grad_norm": 0.017161328345537186,
      "learning_rate": 9.14876134419111e-06,
      "loss": 0.4682884216308594,
      "step": 59
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.01665889099240303,
      "learning_rate": 9.102301097269974e-06,
      "loss": 0.5003230571746826,
      "step": 60
    },
    {
      "epoch": 0.8675555555555555,
      "grad_norm": 0.02079184167087078,
      "learning_rate": 9.05473103493355e-06,
      "loss": 0.45744988322257996,
      "step": 61
    },
    {
      "epoch": 0.8817777777777778,
      "grad_norm": 0.018035434186458588,
      "learning_rate": 9.006064026541549e-06,
      "loss": 0.5037047863006592,
      "step": 62
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.015980787575244904,
      "learning_rate": 8.956313238215824e-06,
      "loss": 0.4382043778896332,
      "step": 63
    },
    {
      "epoch": 0.9102222222222223,
      "grad_norm": 0.016865955665707588,
      "learning_rate": 8.905492129278478e-06,
      "loss": 0.44455963373184204,
      "step": 64
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.014777022413909435,
      "learning_rate": 8.85361444861063e-06,
      "loss": 0.4215100109577179,
      "step": 65
    },
    {
      "epoch": 0.9386666666666666,
      "grad_norm": 0.01814866065979004,
      "learning_rate": 8.800694230932885e-06,
      "loss": 0.48813939094543457,
      "step": 66
    },
    {
      "epoch": 0.9528888888888889,
      "grad_norm": 0.013353748247027397,
      "learning_rate": 8.74674579300843e-06,
      "loss": 3.263723850250244,
      "step": 67
    },
    {
      "epoch": 0.9671111111111111,
      "grad_norm": 0.014444677159190178,
      "learning_rate": 8.691783729769874e-06,
      "loss": 2.8557608127593994,
      "step": 68
    },
    {
      "epoch": 0.9813333333333333,
      "grad_norm": 0.01388335507363081,
      "learning_rate": 8.635822910370793e-06,
      "loss": 3.485170602798462,
      "step": 69
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.01357923075556755,
      "learning_rate": 8.578878474163115e-06,
      "loss": 3.1958985328674316,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.02305089496076107,
      "learning_rate": 8.520965826601394e-06,
      "loss": 2.678990364074707,
      "step": 71
    }
  ],
  "logging_steps": 1,
  "max_steps": 213,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.436159949812531e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}