{
  "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": 0.253393292427063,
      "learning_rate": 0.0,
      "loss": 1.19514799118042,
      "step": 1
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 0.2720104455947876,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 1.2398133277893066,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.22159169614315033,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.9782462120056152,
      "step": 3
    },
    {
      "epoch": 0.05688888888888889,
      "grad_norm": 0.17487271130084991,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.8072947263717651,
      "step": 4
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.08528934419155121,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.5301008224487305,
      "step": 5
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 0.08074624091386795,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.6367583274841309,
      "step": 6
    },
    {
      "epoch": 0.09955555555555555,
      "grad_norm": 0.05584918335080147,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.6089775562286377,
      "step": 7
    },
    {
      "epoch": 0.11377777777777778,
      "grad_norm": 0.032228983938694,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.5260579586029053,
      "step": 8
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.026230908930301666,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.5446298122406006,
      "step": 9
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.019648801535367966,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.5338459610939026,
      "step": 10
    },
    {
      "epoch": 0.15644444444444444,
      "grad_norm": 0.014007463119924068,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.45045405626296997,
      "step": 11
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 0.013295263983309269,
      "learning_rate": 5e-06,
      "loss": 0.49363279342651367,
      "step": 12
    },
    {
      "epoch": 0.18488888888888888,
      "grad_norm": 0.01435786858201027,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.48757249116897583,
      "step": 13
    },
    {
      "epoch": 0.1991111111111111,
      "grad_norm": 0.015238163061439991,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.5002430081367493,
      "step": 14
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.014418123289942741,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.4964277148246765,
      "step": 15
    },
    {
      "epoch": 0.22755555555555557,
      "grad_norm": 0.014306087978184223,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.4818333387374878,
      "step": 16
    },
    {
      "epoch": 0.24177777777777779,
      "grad_norm": 0.009899069555103779,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.4609573483467102,
      "step": 17
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.010643995366990566,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.47600606083869934,
      "step": 18
    },
    {
      "epoch": 0.2702222222222222,
      "grad_norm": 0.012857547029852867,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.4962907135486603,
      "step": 19
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.01670556701719761,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.5028363466262817,
      "step": 20
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.010331347584724426,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.44582226872444153,
      "step": 21
    },
    {
      "epoch": 0.3128888888888889,
      "grad_norm": 0.010525904595851898,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.4757377505302429,
      "step": 22
    },
    {
      "epoch": 0.32711111111111113,
      "grad_norm": 0.009544270113110542,
      "learning_rate": 1e-05,
      "loss": 0.4707476496696472,
      "step": 23
    },
    {
      "epoch": 0.3413333333333333,
      "grad_norm": 0.009730499237775803,
      "learning_rate": 9.999323662872998e-06,
      "loss": 0.49240708351135254,
      "step": 24
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.008985932916402817,
      "learning_rate": 9.99729483446475e-06,
      "loss": 0.450992614030838,
      "step": 25
    },
    {
      "epoch": 0.36977777777777776,
      "grad_norm": 0.01072725746780634,
      "learning_rate": 9.993914063644053e-06,
      "loss": 0.4514142870903015,
      "step": 26
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.01058228686451912,
      "learning_rate": 9.989182265027232e-06,
      "loss": 0.44021710753440857,
      "step": 27
    },
    {
      "epoch": 0.3982222222222222,
      "grad_norm": 0.009333685040473938,
      "learning_rate": 9.98310071873072e-06,
      "loss": 0.4491778016090393,
      "step": 28
    },
    {
      "epoch": 0.41244444444444445,
      "grad_norm": 0.009250632487237453,
      "learning_rate": 9.975671070024741e-06,
      "loss": 0.4285920560359955,
      "step": 29
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.010210932232439518,
      "learning_rate": 9.966895328888195e-06,
      "loss": 0.5484102368354797,
      "step": 30
    },
    {
      "epoch": 0.4408888888888889,
      "grad_norm": 0.008848125115036964,
      "learning_rate": 9.956775869464901e-06,
      "loss": 0.4242202043533325,
      "step": 31
    },
    {
      "epoch": 0.45511111111111113,
      "grad_norm": 0.00905672088265419,
      "learning_rate": 9.945315429421307e-06,
      "loss": 0.4533390402793884,
      "step": 32
    },
    {
      "epoch": 0.4693333333333333,
      "grad_norm": 0.008254914544522762,
      "learning_rate": 9.932517109205849e-06,
      "loss": 0.4243648052215576,
      "step": 33
    },
    {
      "epoch": 0.48355555555555557,
      "grad_norm": 0.009192033670842648,
      "learning_rate": 9.918384371210178e-06,
      "loss": 0.5120309591293335,
      "step": 34
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.009636987932026386,
      "learning_rate": 9.902921038832456e-06,
      "loss": 0.4871100187301636,
      "step": 35
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.008572430349886417,
      "learning_rate": 9.886131295443003e-06,
      "loss": 0.46277713775634766,
      "step": 36
    },
    {
      "epoch": 0.5262222222222223,
      "grad_norm": 0.008587818592786789,
      "learning_rate": 9.868019683252543e-06,
      "loss": 0.45996755361557007,
      "step": 37
    },
    {
      "epoch": 0.5404444444444444,
      "grad_norm": 0.010775095783174038,
      "learning_rate": 9.848591102083375e-06,
      "loss": 0.47378021478652954,
      "step": 38
    },
    {
      "epoch": 0.5546666666666666,
      "grad_norm": 0.00995537731796503,
      "learning_rate": 9.82785080804381e-06,
      "loss": 0.4684975743293762,
      "step": 39
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.009079818613827229,
      "learning_rate": 9.805804412106197e-06,
      "loss": 0.5784010887145996,
      "step": 40
    },
    {
      "epoch": 0.5831111111111111,
      "grad_norm": 0.008139098063111305,
      "learning_rate": 9.782457878588977e-06,
      "loss": 0.46650874614715576,
      "step": 41
    },
    {
      "epoch": 0.5973333333333334,
      "grad_norm": 0.007847482338547707,
      "learning_rate": 9.75781752354311e-06,
      "loss": 0.42804157733917236,
      "step": 42
    },
    {
      "epoch": 0.6115555555555555,
      "grad_norm": 0.008446140214800835,
      "learning_rate": 9.731890013043367e-06,
      "loss": 0.48224180936813354,
      "step": 43
    },
    {
      "epoch": 0.6257777777777778,
      "grad_norm": 0.008632696233689785,
      "learning_rate": 9.704682361384941e-06,
      "loss": 0.4561079144477844,
      "step": 44
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.008637293241918087,
      "learning_rate": 9.676201929185809e-06,
      "loss": 0.4007866382598877,
      "step": 45
    },
    {
      "epoch": 0.6542222222222223,
      "grad_norm": 0.008761093020439148,
      "learning_rate": 9.646456421395447e-06,
      "loss": 0.4587845802307129,
      "step": 46
    },
    {
      "epoch": 0.6684444444444444,
      "grad_norm": 0.008726399391889572,
      "learning_rate": 9.615453885210368e-06,
      "loss": 0.4571158289909363,
      "step": 47
    },
    {
      "epoch": 0.6826666666666666,
      "grad_norm": 0.008282204158604145,
      "learning_rate": 9.583202707897075e-06,
      "loss": 0.4724605679512024,
      "step": 48
    },
    {
      "epoch": 0.6968888888888889,
      "grad_norm": 0.008231760933995247,
      "learning_rate": 9.549711614523007e-06,
      "loss": 0.4600468575954437,
      "step": 49
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.00751511100679636,
      "learning_rate": 9.514989665596114e-06,
      "loss": 0.4377005994319916,
      "step": 50
    },
    {
      "epoch": 0.7111111111111111,
      "eval_loss": 0.4685295820236206,
      "eval_runtime": 5.4716,
      "eval_samples_per_second": 36.553,
      "eval_steps_per_second": 18.276,
      "step": 50
    },
    {
      "epoch": 0.7253333333333334,
      "grad_norm": 0.008261662907898426,
      "learning_rate": 9.479046254613673e-06,
      "loss": 0.4415626525878906,
      "step": 51
    },
    {
      "epoch": 0.7395555555555555,
      "grad_norm": 0.007395230233669281,
      "learning_rate": 9.441891105521005e-06,
      "loss": 0.42561036348342896,
      "step": 52
    },
    {
      "epoch": 0.7537777777777778,
      "grad_norm": 0.008451394736766815,
      "learning_rate": 9.40353427008083e-06,
      "loss": 0.4630648195743561,
      "step": 53
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.007475187536329031,
      "learning_rate": 9.3639861251539e-06,
      "loss": 0.43418699502944946,
      "step": 54
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.00859637837857008,
      "learning_rate": 9.323257369891702e-06,
      "loss": 0.47063255310058594,
      "step": 55
    },
    {
      "epoch": 0.7964444444444444,
      "grad_norm": 0.007597765419632196,
      "learning_rate": 9.281359022841966e-06,
      "loss": 0.41920918226242065,
      "step": 56
    },
    {
      "epoch": 0.8106666666666666,
      "grad_norm": 0.018636908382177353,
      "learning_rate": 9.238302418967757e-06,
      "loss": 0.4757845401763916,
      "step": 57
    },
    {
      "epoch": 0.8248888888888889,
      "grad_norm": 0.008423218503594398,
      "learning_rate": 9.194099206580981e-06,
      "loss": 0.5198032855987549,
      "step": 58
    },
    {
      "epoch": 0.8391111111111111,
      "grad_norm": 0.008149159140884876,
      "learning_rate": 9.14876134419111e-06,
      "loss": 0.46035224199295044,
      "step": 59
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.00819750688970089,
      "learning_rate": 9.102301097269974e-06,
      "loss": 0.4945712983608246,
      "step": 60
    },
    {
      "epoch": 0.8675555555555555,
      "grad_norm": 0.00855066254734993,
      "learning_rate": 9.05473103493355e-06,
      "loss": 0.4513372778892517,
      "step": 61
    },
    {
      "epoch": 0.8817777777777778,
      "grad_norm": 0.008660132065415382,
      "learning_rate": 9.006064026541549e-06,
      "loss": 0.49865084886550903,
      "step": 62
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.007741494104266167,
      "learning_rate": 8.956313238215824e-06,
      "loss": 0.4319220185279846,
      "step": 63
    },
    {
      "epoch": 0.9102222222222223,
      "grad_norm": 0.007900395430624485,
      "learning_rate": 8.905492129278478e-06,
      "loss": 0.43760013580322266,
      "step": 64
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.007346940692514181,
      "learning_rate": 8.85361444861063e-06,
      "loss": 0.41593095660209656,
      "step": 65
    },
    {
      "epoch": 0.9386666666666666,
      "grad_norm": 0.00902250874787569,
      "learning_rate": 8.800694230932885e-06,
      "loss": 0.48464590311050415,
      "step": 66
    },
    {
      "epoch": 0.9528888888888889,
      "grad_norm": 0.007672084029763937,
      "learning_rate": 8.74674579300843e-06,
      "loss": 0.41884416341781616,
      "step": 67
    },
    {
      "epoch": 0.9671111111111111,
      "grad_norm": 0.008009645156562328,
      "learning_rate": 8.691783729769874e-06,
      "loss": 0.40650737285614014,
      "step": 68
    },
    {
      "epoch": 0.9813333333333333,
      "grad_norm": 0.008077424019575119,
      "learning_rate": 8.635822910370793e-06,
      "loss": 0.4726918637752533,
      "step": 69
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.007576521951705217,
      "learning_rate": 8.578878474163115e-06,
      "loss": 0.4404842257499695,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.012638773769140244,
      "learning_rate": 8.520965826601394e-06,
      "loss": 0.42633137106895447,
      "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": 3.4361599565234176e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}