{
  "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": 10.21201439945407,
      "learning_rate": 0.0,
      "loss": 0.9819135069847107,
      "step": 1
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 10.607308805754391,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 0.992728054523468,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 8.137000657744727,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.88365638256073,
      "step": 3
    },
    {
      "epoch": 0.05688888888888889,
      "grad_norm": 5.015580274302158,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.8155229091644287,
      "step": 4
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 3.513429105458463,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.7148971557617188,
      "step": 5
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 2.890137665957255,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.7388776540756226,
      "step": 6
    },
    {
      "epoch": 0.09955555555555555,
      "grad_norm": 2.6650307199214267,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.6954053044319153,
      "step": 7
    },
    {
      "epoch": 0.11377777777777778,
      "grad_norm": 2.1027438786791453,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.6385300159454346,
      "step": 8
    },
    {
      "epoch": 0.128,
      "grad_norm": 1.9707186974912183,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.5974307060241699,
      "step": 9
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 1.7892988232740288,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.5823870897293091,
      "step": 10
    },
    {
      "epoch": 0.15644444444444444,
      "grad_norm": 1.8117663888596973,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.5595569610595703,
      "step": 11
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 1.6892201331978909,
      "learning_rate": 5e-06,
      "loss": 0.5447146892547607,
      "step": 12
    },
    {
      "epoch": 0.18488888888888888,
      "grad_norm": 1.5301037695464916,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.5179443359375,
      "step": 13
    },
    {
      "epoch": 0.1991111111111111,
      "grad_norm": 1.2533624125991738,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.5241127014160156,
      "step": 14
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 1.2394418596122698,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.4842333197593689,
      "step": 15
    },
    {
      "epoch": 0.22755555555555557,
      "grad_norm": 1.1420735285454937,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.5132038593292236,
      "step": 16
    },
    {
      "epoch": 0.24177777777777779,
      "grad_norm": 1.0423494529114559,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.4917834401130676,
      "step": 17
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.9878207423648759,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.4813205897808075,
      "step": 18
    },
    {
      "epoch": 0.2702222222222222,
      "grad_norm": 0.9711754260021513,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.4883510172367096,
      "step": 19
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.9163050690645712,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.4871647357940674,
      "step": 20
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.8404612592234425,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.46865272521972656,
      "step": 21
    },
    {
      "epoch": 0.3128888888888889,
      "grad_norm": 0.8673877914303936,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.4601229727268219,
      "step": 22
    },
    {
      "epoch": 0.32711111111111113,
      "grad_norm": 0.8211864748561771,
      "learning_rate": 1e-05,
      "loss": 0.45921051502227783,
      "step": 23
    },
    {
      "epoch": 0.3413333333333333,
      "grad_norm": 0.8242615873645178,
      "learning_rate": 9.999323662872998e-06,
      "loss": 0.46318507194519043,
      "step": 24
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.7839407977142685,
      "learning_rate": 9.99729483446475e-06,
      "loss": 0.4633931815624237,
      "step": 25
    },
    {
      "epoch": 0.36977777777777776,
      "grad_norm": 0.7111762322751543,
      "learning_rate": 9.993914063644053e-06,
      "loss": 0.45212602615356445,
      "step": 26
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.718221639194032,
      "learning_rate": 9.989182265027232e-06,
      "loss": 0.44105663895606995,
      "step": 27
    },
    {
      "epoch": 0.3982222222222222,
      "grad_norm": 0.7040716895578701,
      "learning_rate": 9.98310071873072e-06,
      "loss": 0.4427238404750824,
      "step": 28
    },
    {
      "epoch": 0.41244444444444445,
      "grad_norm": 0.7489850512171834,
      "learning_rate": 9.975671070024741e-06,
      "loss": 0.443437397480011,
      "step": 29
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.7002493913122244,
      "learning_rate": 9.966895328888195e-06,
      "loss": 0.4632475674152374,
      "step": 30
    },
    {
      "epoch": 0.4408888888888889,
      "grad_norm": 0.6824040285805486,
      "learning_rate": 9.956775869464901e-06,
      "loss": 0.4354594349861145,
      "step": 31
    },
    {
      "epoch": 0.45511111111111113,
      "grad_norm": 0.6597936132766806,
      "learning_rate": 9.945315429421307e-06,
      "loss": 0.429914653301239,
      "step": 32
    },
    {
      "epoch": 0.4693333333333333,
      "grad_norm": 0.6352588389251546,
      "learning_rate": 9.932517109205849e-06,
      "loss": 0.43607252836227417,
      "step": 33
    },
    {
      "epoch": 0.48355555555555557,
      "grad_norm": 0.6921974704448327,
      "learning_rate": 9.918384371210178e-06,
      "loss": 0.45671695470809937,
      "step": 34
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.6491660902599252,
      "learning_rate": 9.902921038832456e-06,
      "loss": 0.4388338327407837,
      "step": 35
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.6096750069184391,
      "learning_rate": 9.886131295443003e-06,
      "loss": 0.4141705334186554,
      "step": 36
    },
    {
      "epoch": 0.5262222222222223,
      "grad_norm": 0.6503340768273712,
      "learning_rate": 9.868019683252543e-06,
      "loss": 0.4218006432056427,
      "step": 37
    },
    {
      "epoch": 0.5404444444444444,
      "grad_norm": 0.714483452396674,
      "learning_rate": 9.848591102083375e-06,
      "loss": 0.4457612931728363,
      "step": 38
    },
    {
      "epoch": 0.5546666666666666,
      "grad_norm": 0.6231964594158875,
      "learning_rate": 9.82785080804381e-06,
      "loss": 0.4331759214401245,
      "step": 39
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.6572593116495337,
      "learning_rate": 9.805804412106197e-06,
      "loss": 0.4507564902305603,
      "step": 40
    },
    {
      "epoch": 0.5831111111111111,
      "grad_norm": 0.673487925488406,
      "learning_rate": 9.782457878588977e-06,
      "loss": 0.4254251718521118,
      "step": 41
    },
    {
      "epoch": 0.5973333333333334,
      "grad_norm": 0.5846423543296639,
      "learning_rate": 9.75781752354311e-06,
      "loss": 0.4125726819038391,
      "step": 42
    },
    {
      "epoch": 0.6115555555555555,
      "grad_norm": 0.598724301403679,
      "learning_rate": 9.731890013043367e-06,
      "loss": 0.4325122535228729,
      "step": 43
    },
    {
      "epoch": 0.6257777777777778,
      "grad_norm": 0.6218044129681044,
      "learning_rate": 9.704682361384941e-06,
      "loss": 0.4131222367286682,
      "step": 44
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.617001419027673,
      "learning_rate": 9.676201929185809e-06,
      "loss": 0.42036178708076477,
      "step": 45
    },
    {
      "epoch": 0.6542222222222223,
      "grad_norm": 0.5809155918543004,
      "learning_rate": 9.646456421395447e-06,
      "loss": 0.4182787537574768,
      "step": 46
    },
    {
      "epoch": 0.6684444444444444,
      "grad_norm": 0.5850555211488232,
      "learning_rate": 9.615453885210368e-06,
      "loss": 0.4234634041786194,
      "step": 47
    },
    {
      "epoch": 0.6826666666666666,
      "grad_norm": 0.5511675603941021,
      "learning_rate": 9.583202707897075e-06,
      "loss": 0.40563416481018066,
      "step": 48
    },
    {
      "epoch": 0.6968888888888889,
      "grad_norm": 0.6111190985848377,
      "learning_rate": 9.549711614523007e-06,
      "loss": 0.3980520963668823,
      "step": 49
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.5736293779202373,
      "learning_rate": 9.514989665596114e-06,
      "loss": 0.4036375880241394,
      "step": 50
    },
    {
      "epoch": 0.7111111111111111,
      "eval_loss": 0.41823333501815796,
      "eval_runtime": 28.2382,
      "eval_samples_per_second": 7.083,
      "eval_steps_per_second": 1.771,
      "step": 50
    },
    {
      "epoch": 0.7253333333333334,
      "grad_norm": 0.5785272249494463,
      "learning_rate": 9.479046254613673e-06,
      "loss": 0.41144663095474243,
      "step": 51
    },
    {
      "epoch": 0.7395555555555555,
      "grad_norm": 0.5517717884994647,
      "learning_rate": 9.441891105521005e-06,
      "loss": 0.38760095834732056,
      "step": 52
    },
    {
      "epoch": 0.7537777777777778,
      "grad_norm": 0.5648730368507402,
      "learning_rate": 9.40353427008083e-06,
      "loss": 0.4036053717136383,
      "step": 53
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.6019960018903892,
      "learning_rate": 9.3639861251539e-06,
      "loss": 0.39992809295654297,
      "step": 54
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.5943571857589287,
      "learning_rate": 9.323257369891702e-06,
      "loss": 0.420696496963501,
      "step": 55
    },
    {
      "epoch": 0.7964444444444444,
      "grad_norm": 0.5800482521740772,
      "learning_rate": 9.281359022841966e-06,
      "loss": 0.41333717107772827,
      "step": 56
    },
    {
      "epoch": 0.8106666666666666,
      "grad_norm": 0.5896438771006596,
      "learning_rate": 9.238302418967757e-06,
      "loss": 0.41053399443626404,
      "step": 57
    },
    {
      "epoch": 0.8248888888888889,
      "grad_norm": 0.5828843912613246,
      "learning_rate": 9.194099206580981e-06,
      "loss": 0.4167237877845764,
      "step": 58
    },
    {
      "epoch": 0.8391111111111111,
      "grad_norm": 0.636505663941606,
      "learning_rate": 9.14876134419111e-06,
      "loss": 0.4126594066619873,
      "step": 59
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.5954156377152778,
      "learning_rate": 9.102301097269974e-06,
      "loss": 0.40986335277557373,
      "step": 60
    },
    {
      "epoch": 0.8675555555555555,
      "grad_norm": 0.5663259824764864,
      "learning_rate": 9.05473103493355e-06,
      "loss": 0.39707833528518677,
      "step": 61
    },
    {
      "epoch": 0.8817777777777778,
      "grad_norm": 0.6233708113516392,
      "learning_rate": 9.006064026541549e-06,
      "loss": 0.4146142601966858,
      "step": 62
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.583882066947991,
      "learning_rate": 8.956313238215824e-06,
      "loss": 0.3761865794658661,
      "step": 63
    },
    {
      "epoch": 0.9102222222222223,
      "grad_norm": 0.559228243852746,
      "learning_rate": 8.905492129278478e-06,
      "loss": 0.397402286529541,
      "step": 64
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.5630501047235328,
      "learning_rate": 8.85361444861063e-06,
      "loss": 0.40299445390701294,
      "step": 65
    },
    {
      "epoch": 0.9386666666666666,
      "grad_norm": 0.5778346041245924,
      "learning_rate": 8.800694230932885e-06,
      "loss": 0.4066828489303589,
      "step": 66
    },
    {
      "epoch": 0.9528888888888889,
      "grad_norm": 0.5735220314699014,
      "learning_rate": 8.74674579300843e-06,
      "loss": 0.39874544739723206,
      "step": 67
    },
    {
      "epoch": 0.9671111111111111,
      "grad_norm": 0.5774583972046927,
      "learning_rate": 8.691783729769874e-06,
      "loss": 0.38473668694496155,
      "step": 68
    },
    {
      "epoch": 0.9813333333333333,
      "grad_norm": 0.6169263233631689,
      "learning_rate": 8.635822910370793e-06,
      "loss": 0.4083672761917114,
      "step": 69
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.5815111675806847,
      "learning_rate": 8.578878474163115e-06,
      "loss": 0.3794967234134674,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9420572347818393,
      "learning_rate": 8.520965826601394e-06,
      "loss": 0.40614083409309387,
      "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": 20960610426880.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}