{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.571428571428571,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 0.10301133245229721,
      "learning_rate": 9.970149253731344e-05,
      "loss": 1.0487,
      "step": 10
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.13997109234333038,
      "learning_rate": 9.91044776119403e-05,
      "loss": 0.7479,
      "step": 20
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 0.07622478902339935,
      "learning_rate": 9.850746268656717e-05,
      "loss": 0.4974,
      "step": 30
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.06940005719661713,
      "learning_rate": 9.791044776119404e-05,
      "loss": 0.4081,
      "step": 40
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.056480951607227325,
      "learning_rate": 9.731343283582089e-05,
      "loss": 0.4592,
      "step": 50
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.055311448872089386,
      "learning_rate": 9.671641791044777e-05,
      "loss": 0.5037,
      "step": 60
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.05507435277104378,
      "learning_rate": 9.611940298507464e-05,
      "loss": 0.4667,
      "step": 70
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.054898519068956375,
      "learning_rate": 9.552238805970149e-05,
      "loss": 0.4856,
      "step": 80
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 0.04788612574338913,
      "learning_rate": 9.492537313432837e-05,
      "loss": 0.4145,
      "step": 90
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.06482447683811188,
      "learning_rate": 9.432835820895522e-05,
      "loss": 0.4418,
      "step": 100
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 0.058699481189250946,
      "learning_rate": 9.373134328358209e-05,
      "loss": 0.6189,
      "step": 110
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.05194304883480072,
      "learning_rate": 9.313432835820896e-05,
      "loss": 0.4142,
      "step": 120
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 0.07520686835050583,
      "learning_rate": 9.253731343283582e-05,
      "loss": 0.4576,
      "step": 130
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.0573502779006958,
      "learning_rate": 9.194029850746269e-05,
      "loss": 0.4354,
      "step": 140
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.061439767479896545,
      "learning_rate": 9.134328358208956e-05,
      "loss": 0.4084,
      "step": 150
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.058765340596437454,
      "learning_rate": 9.074626865671642e-05,
      "loss": 0.405,
      "step": 160
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 0.055010490119457245,
      "learning_rate": 9.014925373134329e-05,
      "loss": 0.4748,
      "step": 170
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.0870099738240242,
      "learning_rate": 8.955223880597016e-05,
      "loss": 0.4428,
      "step": 180
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 0.06115978583693504,
      "learning_rate": 8.895522388059702e-05,
      "loss": 0.4274,
      "step": 190
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.052583467215299606,
      "learning_rate": 8.835820895522389e-05,
      "loss": 0.4513,
      "step": 200
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.054836906492710114,
      "learning_rate": 8.776119402985074e-05,
      "loss": 0.454,
      "step": 210
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.05478864163160324,
      "learning_rate": 8.716417910447762e-05,
      "loss": 0.4935,
      "step": 220
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 0.04880619794130325,
      "learning_rate": 8.656716417910447e-05,
      "loss": 0.5444,
      "step": 230
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.05223756283521652,
      "learning_rate": 8.597014925373134e-05,
      "loss": 0.4363,
      "step": 240
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 0.07902172952890396,
      "learning_rate": 8.537313432835822e-05,
      "loss": 0.4591,
      "step": 250
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 0.05140472576022148,
      "learning_rate": 8.477611940298507e-05,
      "loss": 0.4274,
      "step": 260
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 0.06524641066789627,
      "learning_rate": 8.417910447761194e-05,
      "loss": 0.4718,
      "step": 270
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.06143767759203911,
      "learning_rate": 8.358208955223881e-05,
      "loss": 0.4073,
      "step": 280
    },
    {
      "epoch": 1.0357142857142858,
      "grad_norm": 0.061438463628292084,
      "learning_rate": 8.298507462686567e-05,
      "loss": 0.4232,
      "step": 290
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 0.06389790773391724,
      "learning_rate": 8.238805970149254e-05,
      "loss": 0.4539,
      "step": 300
    },
    {
      "epoch": 1.1071428571428572,
      "grad_norm": 0.06448990106582642,
      "learning_rate": 8.179104477611941e-05,
      "loss": 0.3898,
      "step": 310
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.07985088974237442,
      "learning_rate": 8.119402985074627e-05,
      "loss": 0.3905,
      "step": 320
    },
    {
      "epoch": 1.1785714285714286,
      "grad_norm": 0.06921962648630142,
      "learning_rate": 8.059701492537314e-05,
      "loss": 0.471,
      "step": 330
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 0.09291083365678787,
      "learning_rate": 8e-05,
      "loss": 0.3922,
      "step": 340
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.0728558897972107,
      "learning_rate": 7.940298507462687e-05,
      "loss": 0.4263,
      "step": 350
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.0626588836312294,
      "learning_rate": 7.880597014925374e-05,
      "loss": 0.4269,
      "step": 360
    },
    {
      "epoch": 1.3214285714285714,
      "grad_norm": 0.0737665668129921,
      "learning_rate": 7.820895522388059e-05,
      "loss": 0.4146,
      "step": 370
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 0.07175736874341965,
      "learning_rate": 7.761194029850747e-05,
      "loss": 0.5322,
      "step": 380
    },
    {
      "epoch": 1.3928571428571428,
      "grad_norm": 0.0721152052283287,
      "learning_rate": 7.701492537313433e-05,
      "loss": 0.3717,
      "step": 390
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.06777182966470718,
      "learning_rate": 7.641791044776119e-05,
      "loss": 0.4049,
      "step": 400
    },
    {
      "epoch": 1.4642857142857144,
      "grad_norm": 0.08008120208978653,
      "learning_rate": 7.582089552238806e-05,
      "loss": 0.3878,
      "step": 410
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.08273333311080933,
      "learning_rate": 7.522388059701493e-05,
      "loss": 0.3975,
      "step": 420
    },
    {
      "epoch": 1.5357142857142856,
      "grad_norm": 0.07972041517496109,
      "learning_rate": 7.46268656716418e-05,
      "loss": 0.3897,
      "step": 430
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.07434827834367752,
      "learning_rate": 7.402985074626866e-05,
      "loss": 0.4029,
      "step": 440
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 0.09134312719106674,
      "learning_rate": 7.343283582089552e-05,
      "loss": 0.4254,
      "step": 450
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 0.10692407935857773,
      "learning_rate": 7.283582089552239e-05,
      "loss": 0.4101,
      "step": 460
    },
    {
      "epoch": 1.6785714285714286,
      "grad_norm": 0.0963137298822403,
      "learning_rate": 7.223880597014926e-05,
      "loss": 0.417,
      "step": 470
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.08129405975341797,
      "learning_rate": 7.164179104477612e-05,
      "loss": 0.4739,
      "step": 480
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.09193170815706253,
      "learning_rate": 7.104477611940299e-05,
      "loss": 0.3555,
      "step": 490
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.07470010221004486,
      "learning_rate": 7.044776119402984e-05,
      "loss": 0.4238,
      "step": 500
    },
    {
      "epoch": 1.8214285714285714,
      "grad_norm": 0.09832178801298141,
      "learning_rate": 6.985074626865672e-05,
      "loss": 0.4187,
      "step": 510
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.08799290657043457,
      "learning_rate": 6.925373134328359e-05,
      "loss": 0.4022,
      "step": 520
    },
    {
      "epoch": 1.8928571428571428,
      "grad_norm": 0.08097486197948456,
      "learning_rate": 6.865671641791044e-05,
      "loss": 0.428,
      "step": 530
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 0.08261922746896744,
      "learning_rate": 6.805970149253732e-05,
      "loss": 0.5208,
      "step": 540
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 0.0832519382238388,
      "learning_rate": 6.746268656716418e-05,
      "loss": 0.4323,
      "step": 550
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.07341128587722778,
      "learning_rate": 6.686567164179106e-05,
      "loss": 0.3885,
      "step": 560
    },
    {
      "epoch": 2.0357142857142856,
      "grad_norm": 0.06848422437906265,
      "learning_rate": 6.626865671641791e-05,
      "loss": 0.3713,
      "step": 570
    },
    {
      "epoch": 2.0714285714285716,
      "grad_norm": 0.08991721272468567,
      "learning_rate": 6.567164179104478e-05,
      "loss": 0.3903,
      "step": 580
    },
    {
      "epoch": 2.107142857142857,
      "grad_norm": 0.12314411252737045,
      "learning_rate": 6.507462686567164e-05,
      "loss": 0.3742,
      "step": 590
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.0857195034623146,
      "learning_rate": 6.447761194029851e-05,
      "loss": 0.3501,
      "step": 600
    },
    {
      "epoch": 2.1785714285714284,
      "grad_norm": 0.08988986909389496,
      "learning_rate": 6.388059701492538e-05,
      "loss": 0.3783,
      "step": 610
    },
    {
      "epoch": 2.2142857142857144,
      "grad_norm": 0.1092318519949913,
      "learning_rate": 6.328358208955224e-05,
      "loss": 0.3741,
      "step": 620
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.11366426199674606,
      "learning_rate": 6.268656716417911e-05,
      "loss": 0.4403,
      "step": 630
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.11339179426431656,
      "learning_rate": 6.208955223880598e-05,
      "loss": 0.4135,
      "step": 640
    },
    {
      "epoch": 2.3214285714285716,
      "grad_norm": 0.11044107377529144,
      "learning_rate": 6.149253731343284e-05,
      "loss": 0.3279,
      "step": 650
    },
    {
      "epoch": 2.357142857142857,
      "grad_norm": 0.11268908530473709,
      "learning_rate": 6.08955223880597e-05,
      "loss": 0.3495,
      "step": 660
    },
    {
      "epoch": 2.392857142857143,
      "grad_norm": 0.11684803664684296,
      "learning_rate": 6.029850746268657e-05,
      "loss": 0.3811,
      "step": 670
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.13463515043258667,
      "learning_rate": 5.970149253731343e-05,
      "loss": 0.3605,
      "step": 680
    },
    {
      "epoch": 2.4642857142857144,
      "grad_norm": 0.0957857295870781,
      "learning_rate": 5.91044776119403e-05,
      "loss": 0.3896,
      "step": 690
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.10150361061096191,
      "learning_rate": 5.8507462686567175e-05,
      "loss": 0.3401,
      "step": 700
    },
    {
      "epoch": 2.5357142857142856,
      "grad_norm": 0.10616330057382584,
      "learning_rate": 5.7910447761194034e-05,
      "loss": 0.3846,
      "step": 710
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.09289854764938354,
      "learning_rate": 5.73134328358209e-05,
      "loss": 0.346,
      "step": 720
    },
    {
      "epoch": 2.607142857142857,
      "grad_norm": 0.13642659783363342,
      "learning_rate": 5.671641791044776e-05,
      "loss": 0.3898,
      "step": 730
    },
    {
      "epoch": 2.642857142857143,
      "grad_norm": 0.10691198706626892,
      "learning_rate": 5.6119402985074634e-05,
      "loss": 0.3798,
      "step": 740
    },
    {
      "epoch": 2.678571428571429,
      "grad_norm": 0.12347331643104553,
      "learning_rate": 5.5522388059701494e-05,
      "loss": 0.3919,
      "step": 750
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.1209939643740654,
      "learning_rate": 5.492537313432836e-05,
      "loss": 0.3716,
      "step": 760
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.09330391138792038,
      "learning_rate": 5.432835820895522e-05,
      "loss": 0.3832,
      "step": 770
    },
    {
      "epoch": 2.7857142857142856,
      "grad_norm": 0.13387814164161682,
      "learning_rate": 5.373134328358209e-05,
      "loss": 0.3602,
      "step": 780
    },
    {
      "epoch": 2.821428571428571,
      "grad_norm": 0.11489560455083847,
      "learning_rate": 5.313432835820896e-05,
      "loss": 0.4088,
      "step": 790
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.13628144562244415,
      "learning_rate": 5.253731343283582e-05,
      "loss": 0.3813,
      "step": 800
    },
    {
      "epoch": 2.892857142857143,
      "grad_norm": 0.11659189313650131,
      "learning_rate": 5.194029850746269e-05,
      "loss": 0.3797,
      "step": 810
    },
    {
      "epoch": 2.928571428571429,
      "grad_norm": 0.12676863372325897,
      "learning_rate": 5.134328358208955e-05,
      "loss": 0.329,
      "step": 820
    },
    {
      "epoch": 2.9642857142857144,
      "grad_norm": 0.10595127195119858,
      "learning_rate": 5.074626865671642e-05,
      "loss": 0.3765,
      "step": 830
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.11963572353124619,
      "learning_rate": 5.014925373134328e-05,
      "loss": 0.3701,
      "step": 840
    },
    {
      "epoch": 3.0357142857142856,
      "grad_norm": 0.13174974918365479,
      "learning_rate": 4.955223880597015e-05,
      "loss": 0.2597,
      "step": 850
    },
    {
      "epoch": 3.0714285714285716,
      "grad_norm": 0.16706831753253937,
      "learning_rate": 4.895522388059702e-05,
      "loss": 0.3411,
      "step": 860
    },
    {
      "epoch": 3.107142857142857,
      "grad_norm": 0.12361631542444229,
      "learning_rate": 4.8358208955223885e-05,
      "loss": 0.3653,
      "step": 870
    },
    {
      "epoch": 3.142857142857143,
      "grad_norm": 0.12208428233861923,
      "learning_rate": 4.7761194029850745e-05,
      "loss": 0.3632,
      "step": 880
    },
    {
      "epoch": 3.1785714285714284,
      "grad_norm": 0.1192869320511818,
      "learning_rate": 4.716417910447761e-05,
      "loss": 0.3367,
      "step": 890
    },
    {
      "epoch": 3.2142857142857144,
      "grad_norm": 0.1340082734823227,
      "learning_rate": 4.656716417910448e-05,
      "loss": 0.337,
      "step": 900
    },
    {
      "epoch": 3.25,
      "grad_norm": 0.15136446058750153,
      "learning_rate": 4.5970149253731345e-05,
      "loss": 0.3168,
      "step": 910
    },
    {
      "epoch": 3.2857142857142856,
      "grad_norm": 0.15890203416347504,
      "learning_rate": 4.537313432835821e-05,
      "loss": 0.3723,
      "step": 920
    },
    {
      "epoch": 3.3214285714285716,
      "grad_norm": 0.14035534858703613,
      "learning_rate": 4.477611940298508e-05,
      "loss": 0.3235,
      "step": 930
    },
    {
      "epoch": 3.357142857142857,
      "grad_norm": 0.14109626412391663,
      "learning_rate": 4.4179104477611944e-05,
      "loss": 0.3404,
      "step": 940
    },
    {
      "epoch": 3.392857142857143,
      "grad_norm": 0.12994477152824402,
      "learning_rate": 4.358208955223881e-05,
      "loss": 0.3578,
      "step": 950
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 0.15381306409835815,
      "learning_rate": 4.298507462686567e-05,
      "loss": 0.3197,
      "step": 960
    },
    {
      "epoch": 3.4642857142857144,
      "grad_norm": 0.12908071279525757,
      "learning_rate": 4.238805970149254e-05,
      "loss": 0.334,
      "step": 970
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.16112634539604187,
      "learning_rate": 4.1791044776119404e-05,
      "loss": 0.3051,
      "step": 980
    },
    {
      "epoch": 3.5357142857142856,
      "grad_norm": 0.15946915745735168,
      "learning_rate": 4.119402985074627e-05,
      "loss": 0.3806,
      "step": 990
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 0.13795320689678192,
      "learning_rate": 4.059701492537314e-05,
      "loss": 0.2901,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1680,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 4.0255297151791104e+17,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}