{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.2222222222222223,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 6.603886604309082,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 1.7454,
      "step": 10
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 4.177036285400391,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 1.5071,
      "step": 20
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 6.5375285148620605,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 1.6012,
      "step": 30
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 2.4201414585113525,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 1.543,
      "step": 40
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 8.420122146606445,
      "learning_rate": 3.62962962962963e-05,
      "loss": 1.6806,
      "step": 50
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 2.9238393306732178,
      "learning_rate": 4.3703703703703705e-05,
      "loss": 1.4376,
      "step": 60
    },
    {
      "epoch": 0.15555555555555556,
      "grad_norm": 4.334264278411865,
      "learning_rate": 5.111111111111111e-05,
      "loss": 1.5629,
      "step": 70
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 4.047328472137451,
      "learning_rate": 5.851851851851852e-05,
      "loss": 1.5502,
      "step": 80
    },
    {
      "epoch": 0.2,
      "grad_norm": 6.695739269256592,
      "learning_rate": 6.592592592592593e-05,
      "loss": 1.5744,
      "step": 90
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 2.579887628555298,
      "learning_rate": 7.333333333333333e-05,
      "loss": 1.4887,
      "step": 100
    },
    {
      "epoch": 0.24444444444444444,
      "grad_norm": 8.655933380126953,
      "learning_rate": 8.074074074074075e-05,
      "loss": 1.4432,
      "step": 110
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 2.3287596702575684,
      "learning_rate": 8.814814814814815e-05,
      "loss": 1.7349,
      "step": 120
    },
    {
      "epoch": 0.28888888888888886,
      "grad_norm": 3.626464366912842,
      "learning_rate": 9.555555555555557e-05,
      "loss": 1.8419,
      "step": 130
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 13.17669677734375,
      "learning_rate": 9.999732574196451e-05,
      "loss": 1.7434,
      "step": 140
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.938781261444092,
      "learning_rate": 9.996724362426075e-05,
      "loss": 1.7345,
      "step": 150
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 3.3643951416015625,
      "learning_rate": 9.990375674425109e-05,
      "loss": 1.6652,
      "step": 160
    },
    {
      "epoch": 0.37777777777777777,
      "grad_norm": 4.0528178215026855,
      "learning_rate": 9.980690754502393e-05,
      "loss": 1.6247,
      "step": 170
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.2510921955108643,
      "learning_rate": 9.96767607734863e-05,
      "loss": 1.9226,
      "step": 180
    },
    {
      "epoch": 0.4222222222222222,
      "grad_norm": 3.1616647243499756,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.9507,
      "step": 190
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.816512107849121,
      "learning_rate": 9.931694474560686e-05,
      "loss": 1.5901,
      "step": 200
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 3.0883939266204834,
      "learning_rate": 9.908751603823301e-05,
      "loss": 1.7762,
      "step": 210
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 3.496539354324341,
      "learning_rate": 9.882527069566965e-05,
      "loss": 1.7833,
      "step": 220
    },
    {
      "epoch": 0.5111111111111111,
      "grad_norm": 3.6071531772613525,
      "learning_rate": 9.853038403764021e-05,
      "loss": 1.5891,
      "step": 230
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 3.1297965049743652,
      "learning_rate": 9.820305320567192e-05,
      "loss": 1.7261,
      "step": 240
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 2.707146167755127,
      "learning_rate": 9.784349703130007e-05,
      "loss": 1.6448,
      "step": 250
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 3.1915082931518555,
      "learning_rate": 9.745195588977192e-05,
      "loss": 1.9097,
      "step": 260
    },
    {
      "epoch": 0.6,
      "grad_norm": 2.056610584259033,
      "learning_rate": 9.702869153934782e-05,
      "loss": 1.6173,
      "step": 270
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 3.044048309326172,
      "learning_rate": 9.657398694630712e-05,
      "loss": 1.8324,
      "step": 280
    },
    {
      "epoch": 0.6444444444444445,
      "grad_norm": 3.3219234943389893,
      "learning_rate": 9.608814609577585e-05,
      "loss": 1.818,
      "step": 290
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.5632572174072266,
      "learning_rate": 9.557149378850254e-05,
      "loss": 1.618,
      "step": 300
    },
    {
      "epoch": 0.6888888888888889,
      "grad_norm": 2.3387904167175293,
      "learning_rate": 9.502437542371812e-05,
      "loss": 1.6228,
      "step": 310
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 2.6883046627044678,
      "learning_rate": 9.444715676822501e-05,
      "loss": 1.7307,
      "step": 320
    },
    {
      "epoch": 0.7333333333333333,
      "grad_norm": 2.9449591636657715,
      "learning_rate": 9.384022371187003e-05,
      "loss": 1.7338,
      "step": 330
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 2.4884233474731445,
      "learning_rate": 9.320398200956403e-05,
      "loss": 1.4941,
      "step": 340
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 5.446136951446533,
      "learning_rate": 9.253885701002134e-05,
      "loss": 1.9377,
      "step": 350
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.122303009033203,
      "learning_rate": 9.184529337140002e-05,
      "loss": 1.5295,
      "step": 360
    },
    {
      "epoch": 0.8222222222222222,
      "grad_norm": 3.4902145862579346,
      "learning_rate": 9.112375476403312e-05,
      "loss": 1.688,
      "step": 370
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 3.041170597076416,
      "learning_rate": 9.037472356044962e-05,
      "loss": 1.7526,
      "step": 380
    },
    {
      "epoch": 0.8666666666666667,
      "grad_norm": 2.029374837875366,
      "learning_rate": 8.959870051289241e-05,
      "loss": 1.5125,
      "step": 390
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 4.354530334472656,
      "learning_rate": 8.879620441854872e-05,
      "loss": 1.6507,
      "step": 400
    },
    {
      "epoch": 0.9111111111111111,
      "grad_norm": 3.2502028942108154,
      "learning_rate": 8.796777177271708e-05,
      "loss": 1.6118,
      "step": 410
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 2.198453903198242,
      "learning_rate": 8.711395641014228e-05,
      "loss": 1.6589,
      "step": 420
    },
    {
      "epoch": 0.9555555555555556,
      "grad_norm": 3.6842291355133057,
      "learning_rate": 8.623532913475847e-05,
      "loss": 1.6891,
      "step": 430
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 2.3169732093811035,
      "learning_rate": 8.533247733808776e-05,
      "loss": 1.5275,
      "step": 440
    },
    {
      "epoch": 1.0,
      "grad_norm": 5.430471897125244,
      "learning_rate": 8.440600460654958e-05,
      "loss": 1.7984,
      "step": 450
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": 4.782519817352295,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.9174,
      "step": 460
    },
    {
      "epoch": 1.0444444444444445,
      "grad_norm": 3.547177314758301,
      "learning_rate": 8.248468922737188e-05,
      "loss": 1.3878,
      "step": 470
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 2.446197748184204,
      "learning_rate": 8.149113104289063e-05,
      "loss": 1.1277,
      "step": 480
    },
    {
      "epoch": 1.0888888888888888,
      "grad_norm": 3.3164918422698975,
      "learning_rate": 8.047651999115217e-05,
      "loss": 1.0124,
      "step": 490
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 7.3411359786987305,
      "learning_rate": 7.944153437335057e-05,
      "loss": 1.0102,
      "step": 500
    },
    {
      "epoch": 1.1111111111111112,
      "eval_loss": 1.7722898721694946,
      "eval_runtime": 4.268,
      "eval_samples_per_second": 23.43,
      "eval_steps_per_second": 23.43,
      "step": 500
    },
    {
      "epoch": 1.1333333333333333,
      "grad_norm": 3.1477370262145996,
      "learning_rate": 7.838686611175421e-05,
      "loss": 1.1386,
      "step": 510
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 3.3324782848358154,
      "learning_rate": 7.73132202871327e-05,
      "loss": 1.0376,
      "step": 520
    },
    {
      "epoch": 1.1777777777777778,
      "grad_norm": 4.7969136238098145,
      "learning_rate": 7.6221314667387e-05,
      "loss": 1.2585,
      "step": 530
    },
    {
      "epoch": 1.2,
      "grad_norm": 3.488189697265625,
      "learning_rate": 7.511187922769768e-05,
      "loss": 1.2203,
      "step": 540
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 3.5396199226379395,
      "learning_rate": 7.398565566251232e-05,
      "loss": 1.1651,
      "step": 550
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 4.660005569458008,
      "learning_rate": 7.284339688969809e-05,
      "loss": 1.1229,
      "step": 560
    },
    {
      "epoch": 1.2666666666666666,
      "grad_norm": 6.269535541534424,
      "learning_rate": 7.168586654719117e-05,
      "loss": 1.1348,
      "step": 570
    },
    {
      "epoch": 1.2888888888888888,
      "grad_norm": 5.864573955535889,
      "learning_rate": 7.051383848247942e-05,
      "loss": 1.1637,
      "step": 580
    },
    {
      "epoch": 1.3111111111111111,
      "grad_norm": 3.3166041374206543,
      "learning_rate": 6.944726507547169e-05,
      "loss": 1.0358,
      "step": 590
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 4.742485523223877,
      "learning_rate": 6.824985757903016e-05,
      "loss": 1.0499,
      "step": 600
    },
    {
      "epoch": 1.3555555555555556,
      "grad_norm": 2.5902740955352783,
      "learning_rate": 6.704024944652537e-05,
      "loss": 0.9614,
      "step": 610
    },
    {
      "epoch": 1.3777777777777778,
      "grad_norm": 4.31684684753418,
      "learning_rate": 6.581924934117782e-05,
      "loss": 1.2387,
      "step": 620
    },
    {
      "epoch": 1.4,
      "grad_norm": 6.753187656402588,
      "learning_rate": 6.458767354212036e-05,
      "loss": 0.9807,
      "step": 630
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 4.625970363616943,
      "learning_rate": 6.334634539868836e-05,
      "loss": 1.047,
      "step": 640
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 4.617323875427246,
      "learning_rate": 6.22214975761865e-05,
      "loss": 1.1423,
      "step": 650
    },
    {
      "epoch": 1.4666666666666668,
      "grad_norm": 5.007408142089844,
      "learning_rate": 6.096393120939516e-05,
      "loss": 1.1181,
      "step": 660
    },
    {
      "epoch": 1.488888888888889,
      "grad_norm": 6.361126899719238,
      "learning_rate": 5.969903509036172e-05,
      "loss": 0.8642,
      "step": 670
    },
    {
      "epoch": 1.511111111111111,
      "grad_norm": 3.4635279178619385,
      "learning_rate": 5.842765484416237e-05,
      "loss": 0.9609,
      "step": 680
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 2.583265781402588,
      "learning_rate": 5.715064043072771e-05,
      "loss": 0.9543,
      "step": 690
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 3.2295000553131104,
      "learning_rate": 5.586884557661638e-05,
      "loss": 1.3545,
      "step": 700
    },
    {
      "epoch": 1.5777777777777777,
      "grad_norm": 3.589311361312866,
      "learning_rate": 5.458312720427037e-05,
      "loss": 1.1898,
      "step": 710
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.749166965484619,
      "learning_rate": 5.329434485913393e-05,
      "loss": 0.9212,
      "step": 720
    },
    {
      "epoch": 1.6222222222222222,
      "grad_norm": 5.566150665283203,
      "learning_rate": 5.200336013501898e-05,
      "loss": 1.0051,
      "step": 730
    },
    {
      "epoch": 1.6444444444444444,
      "grad_norm": 4.666942596435547,
      "learning_rate": 5.07110360981009e-05,
      "loss": 0.9947,
      "step": 740
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 4.7450737953186035,
      "learning_rate": 4.941823670993016e-05,
      "loss": 1.2966,
      "step": 750
    },
    {
      "epoch": 1.6888888888888889,
      "grad_norm": 3.922316551208496,
      "learning_rate": 4.8125826249845375e-05,
      "loss": 0.9482,
      "step": 760
    },
    {
      "epoch": 1.7111111111111112,
      "grad_norm": 2.466024398803711,
      "learning_rate": 4.683466873717379e-05,
      "loss": 1.1203,
      "step": 770
    },
    {
      "epoch": 1.7333333333333334,
      "grad_norm": 3.1226003170013428,
      "learning_rate": 4.55456273536057e-05,
      "loss": 0.9876,
      "step": 780
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 3.574613571166992,
      "learning_rate": 4.4259563866128754e-05,
      "loss": 0.9708,
      "step": 790
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 4.307621002197266,
      "learning_rate": 4.297733805090819e-05,
      "loss": 1.1659,
      "step": 800
    },
    {
      "epoch": 1.8,
      "grad_norm": 3.263989210128784,
      "learning_rate": 4.169980711849781e-05,
      "loss": 1.0767,
      "step": 810
    },
    {
      "epoch": 1.8222222222222222,
      "grad_norm": 4.091586112976074,
      "learning_rate": 4.0427825140766306e-05,
      "loss": 0.9197,
      "step": 820
    },
    {
      "epoch": 1.8444444444444446,
      "grad_norm": 6.540091037750244,
      "learning_rate": 3.916224247992184e-05,
      "loss": 1.0032,
      "step": 830
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 3.0093724727630615,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.9162,
      "step": 840
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 3.8956823348999023,
      "learning_rate": 3.665365460131165e-05,
      "loss": 0.9894,
      "step": 850
    },
    {
      "epoch": 1.911111111111111,
      "grad_norm": 6.698014736175537,
      "learning_rate": 3.541232645787964e-05,
      "loss": 1.0847,
      "step": 860
    },
    {
      "epoch": 1.9333333333333333,
      "grad_norm": 3.408623218536377,
      "learning_rate": 3.418075065882217e-05,
      "loss": 1.0293,
      "step": 870
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 5.4307780265808105,
      "learning_rate": 3.295975055347464e-05,
      "loss": 1.1167,
      "step": 880
    },
    {
      "epoch": 1.9777777777777779,
      "grad_norm": 3.301551103591919,
      "learning_rate": 3.175014242096985e-05,
      "loss": 0.9419,
      "step": 890
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.311927080154419,
      "learning_rate": 3.0552734924528306e-05,
      "loss": 1.0782,
      "step": 900
    },
    {
      "epoch": 2.022222222222222,
      "grad_norm": 3.594782590866089,
      "learning_rate": 2.936832857084003e-05,
      "loss": 0.7008,
      "step": 910
    },
    {
      "epoch": 2.0444444444444443,
      "grad_norm": 2.127872943878174,
      "learning_rate": 2.8197715174899185e-05,
      "loss": 0.5128,
      "step": 920
    },
    {
      "epoch": 2.066666666666667,
      "grad_norm": 1.7860101461410522,
      "learning_rate": 2.7041677330649407e-05,
      "loss": 0.4185,
      "step": 930
    },
    {
      "epoch": 2.088888888888889,
      "grad_norm": 5.212789058685303,
      "learning_rate": 2.590098788779396e-05,
      "loss": 0.52,
      "step": 940
    },
    {
      "epoch": 2.111111111111111,
      "grad_norm": 2.7228968143463135,
      "learning_rate": 2.4776409435119775e-05,
      "loss": 0.7065,
      "step": 950
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 2.3301429748535156,
      "learning_rate": 2.3668693790681634e-05,
      "loss": 0.3988,
      "step": 960
    },
    {
      "epoch": 2.1555555555555554,
      "grad_norm": 3.8069827556610107,
      "learning_rate": 2.257858149918688e-05,
      "loss": 0.6353,
      "step": 970
    },
    {
      "epoch": 2.1777777777777776,
      "grad_norm": 3.177034854888916,
      "learning_rate": 2.15068013369166e-05,
      "loss": 0.4815,
      "step": 980
    },
    {
      "epoch": 2.2,
      "grad_norm": 2.7649686336517334,
      "learning_rate": 2.0454069824514444e-05,
      "loss": 0.5903,
      "step": 990
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 3.8075079917907715,
      "learning_rate": 1.942109074796888e-05,
      "loss": 0.5375,
      "step": 1000
    },
    {
      "epoch": 2.2222222222222223,
      "eval_loss": 1.9768437147140503,
      "eval_runtime": 4.0891,
      "eval_samples_per_second": 24.455,
      "eval_steps_per_second": 24.455,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1350,
  "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": 2314334064574464.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}