{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1036,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009652509652509652,
      "grad_norm": 1.4631391763687134,
      "learning_rate": 0.0001,
      "loss": 0.664,
      "step": 10
    },
    {
      "epoch": 0.019305019305019305,
      "grad_norm": 1.8917441368103027,
      "learning_rate": 0.0002,
      "loss": 0.1575,
      "step": 20
    },
    {
      "epoch": 0.02895752895752896,
      "grad_norm": 1.5227961540222168,
      "learning_rate": 0.00019803149606299213,
      "loss": 0.1233,
      "step": 30
    },
    {
      "epoch": 0.03861003861003861,
      "grad_norm": 0.9390913248062134,
      "learning_rate": 0.00019606299212598428,
      "loss": 0.1106,
      "step": 40
    },
    {
      "epoch": 0.04826254826254826,
      "grad_norm": 0.8157206177711487,
      "learning_rate": 0.0001940944881889764,
      "loss": 0.0869,
      "step": 50
    },
    {
      "epoch": 0.05791505791505792,
      "grad_norm": 0.5291563868522644,
      "learning_rate": 0.0001921259842519685,
      "loss": 0.0903,
      "step": 60
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 1.155928373336792,
      "learning_rate": 0.00019015748031496065,
      "loss": 0.1186,
      "step": 70
    },
    {
      "epoch": 0.07722007722007722,
      "grad_norm": 0.5892627239227295,
      "learning_rate": 0.00018818897637795277,
      "loss": 0.0914,
      "step": 80
    },
    {
      "epoch": 0.08687258687258688,
      "grad_norm": 0.5989981889724731,
      "learning_rate": 0.0001862204724409449,
      "loss": 0.0917,
      "step": 90
    },
    {
      "epoch": 0.09652509652509653,
      "grad_norm": 0.9171364903450012,
      "learning_rate": 0.000184251968503937,
      "loss": 0.0888,
      "step": 100
    },
    {
      "epoch": 0.10617760617760617,
      "grad_norm": 0.37568220496177673,
      "learning_rate": 0.00018228346456692916,
      "loss": 0.0865,
      "step": 110
    },
    {
      "epoch": 0.11583011583011583,
      "grad_norm": 0.5606808662414551,
      "learning_rate": 0.00018031496062992125,
      "loss": 0.0898,
      "step": 120
    },
    {
      "epoch": 0.12548262548262548,
      "grad_norm": 0.6872594356536865,
      "learning_rate": 0.00017834645669291338,
      "loss": 0.0851,
      "step": 130
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 0.6313247680664062,
      "learning_rate": 0.00017637795275590552,
      "loss": 0.088,
      "step": 140
    },
    {
      "epoch": 0.14478764478764478,
      "grad_norm": 0.7841348648071289,
      "learning_rate": 0.00017440944881889765,
      "loss": 0.0966,
      "step": 150
    },
    {
      "epoch": 0.15444015444015444,
      "grad_norm": 0.8097236752510071,
      "learning_rate": 0.00017244094488188977,
      "loss": 0.0626,
      "step": 160
    },
    {
      "epoch": 0.1640926640926641,
      "grad_norm": 0.7307904362678528,
      "learning_rate": 0.00017047244094488192,
      "loss": 0.084,
      "step": 170
    },
    {
      "epoch": 0.17374517374517376,
      "grad_norm": 0.5725339651107788,
      "learning_rate": 0.000168503937007874,
      "loss": 0.071,
      "step": 180
    },
    {
      "epoch": 0.1833976833976834,
      "grad_norm": 0.7641273736953735,
      "learning_rate": 0.00016653543307086613,
      "loss": 0.0958,
      "step": 190
    },
    {
      "epoch": 0.19305019305019305,
      "grad_norm": 0.6539800763130188,
      "learning_rate": 0.00016456692913385828,
      "loss": 0.0803,
      "step": 200
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 0.6908950805664062,
      "learning_rate": 0.0001625984251968504,
      "loss": 0.0885,
      "step": 210
    },
    {
      "epoch": 0.21235521235521235,
      "grad_norm": 0.31019431352615356,
      "learning_rate": 0.00016062992125984252,
      "loss": 0.0588,
      "step": 220
    },
    {
      "epoch": 0.222007722007722,
      "grad_norm": 0.7413542866706848,
      "learning_rate": 0.00015866141732283467,
      "loss": 0.0827,
      "step": 230
    },
    {
      "epoch": 0.23166023166023167,
      "grad_norm": 0.7324005365371704,
      "learning_rate": 0.0001566929133858268,
      "loss": 0.0926,
      "step": 240
    },
    {
      "epoch": 0.2413127413127413,
      "grad_norm": 0.5140088796615601,
      "learning_rate": 0.0001547244094488189,
      "loss": 0.0768,
      "step": 250
    },
    {
      "epoch": 0.25096525096525096,
      "grad_norm": 0.3749833405017853,
      "learning_rate": 0.00015275590551181104,
      "loss": 0.0741,
      "step": 260
    },
    {
      "epoch": 0.2606177606177606,
      "grad_norm": 0.5479316711425781,
      "learning_rate": 0.00015078740157480316,
      "loss": 0.068,
      "step": 270
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 0.5078131556510925,
      "learning_rate": 0.00014881889763779528,
      "loss": 0.0763,
      "step": 280
    },
    {
      "epoch": 0.2799227799227799,
      "grad_norm": 0.5565307140350342,
      "learning_rate": 0.0001468503937007874,
      "loss": 0.0657,
      "step": 290
    },
    {
      "epoch": 0.28957528957528955,
      "grad_norm": 0.5333523750305176,
      "learning_rate": 0.00014488188976377955,
      "loss": 0.0467,
      "step": 300
    },
    {
      "epoch": 0.29922779922779924,
      "grad_norm": 0.9170491695404053,
      "learning_rate": 0.00014291338582677165,
      "loss": 0.0677,
      "step": 310
    },
    {
      "epoch": 0.3088803088803089,
      "grad_norm": 0.6521899104118347,
      "learning_rate": 0.00014094488188976377,
      "loss": 0.0692,
      "step": 320
    },
    {
      "epoch": 0.3185328185328185,
      "grad_norm": 0.5061705708503723,
      "learning_rate": 0.00013897637795275592,
      "loss": 0.086,
      "step": 330
    },
    {
      "epoch": 0.3281853281853282,
      "grad_norm": 0.643752932548523,
      "learning_rate": 0.00013700787401574804,
      "loss": 0.0621,
      "step": 340
    },
    {
      "epoch": 0.33783783783783783,
      "grad_norm": 0.5780313014984131,
      "learning_rate": 0.00013503937007874016,
      "loss": 0.0691,
      "step": 350
    },
    {
      "epoch": 0.3474903474903475,
      "grad_norm": 0.36350390315055847,
      "learning_rate": 0.0001330708661417323,
      "loss": 0.0679,
      "step": 360
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.6011677384376526,
      "learning_rate": 0.0001311023622047244,
      "loss": 0.0707,
      "step": 370
    },
    {
      "epoch": 0.3667953667953668,
      "grad_norm": 0.5352160930633545,
      "learning_rate": 0.00012913385826771653,
      "loss": 0.0543,
      "step": 380
    },
    {
      "epoch": 0.3764478764478765,
      "grad_norm": 0.4793628752231598,
      "learning_rate": 0.00012716535433070867,
      "loss": 0.058,
      "step": 390
    },
    {
      "epoch": 0.3861003861003861,
      "grad_norm": 0.6923650503158569,
      "learning_rate": 0.0001251968503937008,
      "loss": 0.0691,
      "step": 400
    },
    {
      "epoch": 0.39575289575289574,
      "grad_norm": 0.49190232157707214,
      "learning_rate": 0.00012322834645669292,
      "loss": 0.0579,
      "step": 410
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 0.23852688074111938,
      "learning_rate": 0.00012125984251968505,
      "loss": 0.0524,
      "step": 420
    },
    {
      "epoch": 0.41505791505791506,
      "grad_norm": 0.6561082005500793,
      "learning_rate": 0.00011929133858267719,
      "loss": 0.057,
      "step": 430
    },
    {
      "epoch": 0.4247104247104247,
      "grad_norm": 0.613944411277771,
      "learning_rate": 0.00011732283464566928,
      "loss": 0.0575,
      "step": 440
    },
    {
      "epoch": 0.4343629343629344,
      "grad_norm": 0.3899982273578644,
      "learning_rate": 0.00011535433070866142,
      "loss": 0.0527,
      "step": 450
    },
    {
      "epoch": 0.444015444015444,
      "grad_norm": 0.5278599262237549,
      "learning_rate": 0.00011338582677165355,
      "loss": 0.0589,
      "step": 460
    },
    {
      "epoch": 0.45366795366795365,
      "grad_norm": 0.29473400115966797,
      "learning_rate": 0.00011141732283464567,
      "loss": 0.0271,
      "step": 470
    },
    {
      "epoch": 0.46332046332046334,
      "grad_norm": 0.6821677088737488,
      "learning_rate": 0.00010944881889763781,
      "loss": 0.0772,
      "step": 480
    },
    {
      "epoch": 0.47297297297297297,
      "grad_norm": 0.3420783281326294,
      "learning_rate": 0.00010748031496062993,
      "loss": 0.0543,
      "step": 490
    },
    {
      "epoch": 0.4826254826254826,
      "grad_norm": 0.5966827869415283,
      "learning_rate": 0.00010551181102362204,
      "loss": 0.0552,
      "step": 500
    },
    {
      "epoch": 0.4922779922779923,
      "grad_norm": 0.656173825263977,
      "learning_rate": 0.00010354330708661417,
      "loss": 0.0692,
      "step": 510
    },
    {
      "epoch": 0.5019305019305019,
      "grad_norm": 0.46832337975502014,
      "learning_rate": 0.0001015748031496063,
      "loss": 0.0456,
      "step": 520
    },
    {
      "epoch": 0.5115830115830116,
      "grad_norm": 0.5552840828895569,
      "learning_rate": 9.960629921259843e-05,
      "loss": 0.0581,
      "step": 530
    },
    {
      "epoch": 0.5212355212355212,
      "grad_norm": 0.7662914395332336,
      "learning_rate": 9.763779527559055e-05,
      "loss": 0.0542,
      "step": 540
    },
    {
      "epoch": 0.5308880308880309,
      "grad_norm": 0.5977205634117126,
      "learning_rate": 9.566929133858268e-05,
      "loss": 0.0432,
      "step": 550
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.41738152503967285,
      "learning_rate": 9.370078740157481e-05,
      "loss": 0.0606,
      "step": 560
    },
    {
      "epoch": 0.5501930501930502,
      "grad_norm": 0.3176082670688629,
      "learning_rate": 9.173228346456693e-05,
      "loss": 0.053,
      "step": 570
    },
    {
      "epoch": 0.5598455598455598,
      "grad_norm": 0.5319856405258179,
      "learning_rate": 8.976377952755905e-05,
      "loss": 0.0548,
      "step": 580
    },
    {
      "epoch": 0.5694980694980695,
      "grad_norm": 0.6625571250915527,
      "learning_rate": 8.779527559055119e-05,
      "loss": 0.0735,
      "step": 590
    },
    {
      "epoch": 0.5791505791505791,
      "grad_norm": 0.6264726519584656,
      "learning_rate": 8.582677165354331e-05,
      "loss": 0.0574,
      "step": 600
    },
    {
      "epoch": 0.5888030888030888,
      "grad_norm": 0.49182403087615967,
      "learning_rate": 8.385826771653543e-05,
      "loss": 0.046,
      "step": 610
    },
    {
      "epoch": 0.5984555984555985,
      "grad_norm": 0.712940514087677,
      "learning_rate": 8.188976377952757e-05,
      "loss": 0.0451,
      "step": 620
    },
    {
      "epoch": 0.6081081081081081,
      "grad_norm": 0.5095399022102356,
      "learning_rate": 7.992125984251969e-05,
      "loss": 0.0527,
      "step": 630
    },
    {
      "epoch": 0.6177606177606177,
      "grad_norm": 0.4520854949951172,
      "learning_rate": 7.795275590551181e-05,
      "loss": 0.0498,
      "step": 640
    },
    {
      "epoch": 0.6274131274131274,
      "grad_norm": 0.7156594395637512,
      "learning_rate": 7.598425196850393e-05,
      "loss": 0.0482,
      "step": 650
    },
    {
      "epoch": 0.637065637065637,
      "grad_norm": 0.3221661150455475,
      "learning_rate": 7.401574803149607e-05,
      "loss": 0.0399,
      "step": 660
    },
    {
      "epoch": 0.6467181467181468,
      "grad_norm": 0.22723270952701569,
      "learning_rate": 7.20472440944882e-05,
      "loss": 0.0388,
      "step": 670
    },
    {
      "epoch": 0.6563706563706564,
      "grad_norm": 0.5212529301643372,
      "learning_rate": 7.007874015748031e-05,
      "loss": 0.0389,
      "step": 680
    },
    {
      "epoch": 0.666023166023166,
      "grad_norm": 0.5126072764396667,
      "learning_rate": 6.811023622047245e-05,
      "loss": 0.0525,
      "step": 690
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 0.7248953580856323,
      "learning_rate": 6.614173228346457e-05,
      "loss": 0.0619,
      "step": 700
    },
    {
      "epoch": 0.6853281853281853,
      "grad_norm": 0.3085402548313141,
      "learning_rate": 6.417322834645669e-05,
      "loss": 0.053,
      "step": 710
    },
    {
      "epoch": 0.694980694980695,
      "grad_norm": 0.3684390187263489,
      "learning_rate": 6.220472440944882e-05,
      "loss": 0.0352,
      "step": 720
    },
    {
      "epoch": 0.7046332046332047,
      "grad_norm": 0.5736101269721985,
      "learning_rate": 6.0236220472440953e-05,
      "loss": 0.0524,
      "step": 730
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.24105365574359894,
      "learning_rate": 5.826771653543307e-05,
      "loss": 0.0361,
      "step": 740
    },
    {
      "epoch": 0.7239382239382239,
      "grad_norm": 0.4142036736011505,
      "learning_rate": 5.62992125984252e-05,
      "loss": 0.0423,
      "step": 750
    },
    {
      "epoch": 0.7335907335907336,
      "grad_norm": 0.43454453349113464,
      "learning_rate": 5.433070866141733e-05,
      "loss": 0.0573,
      "step": 760
    },
    {
      "epoch": 0.7432432432432432,
      "grad_norm": 0.6893749833106995,
      "learning_rate": 5.236220472440945e-05,
      "loss": 0.0578,
      "step": 770
    },
    {
      "epoch": 0.752895752895753,
      "grad_norm": 0.38158169388771057,
      "learning_rate": 5.0393700787401575e-05,
      "loss": 0.042,
      "step": 780
    },
    {
      "epoch": 0.7625482625482626,
      "grad_norm": 0.6105143427848816,
      "learning_rate": 4.84251968503937e-05,
      "loss": 0.0632,
      "step": 790
    },
    {
      "epoch": 0.7722007722007722,
      "grad_norm": 0.28586989641189575,
      "learning_rate": 4.645669291338583e-05,
      "loss": 0.0453,
      "step": 800
    },
    {
      "epoch": 0.7818532818532818,
      "grad_norm": 0.4869031012058258,
      "learning_rate": 4.4488188976377954e-05,
      "loss": 0.0426,
      "step": 810
    },
    {
      "epoch": 0.7915057915057915,
      "grad_norm": 0.09411308914422989,
      "learning_rate": 4.251968503937008e-05,
      "loss": 0.034,
      "step": 820
    },
    {
      "epoch": 0.8011583011583011,
      "grad_norm": 0.43962639570236206,
      "learning_rate": 4.0551181102362204e-05,
      "loss": 0.0528,
      "step": 830
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 0.33696189522743225,
      "learning_rate": 3.858267716535433e-05,
      "loss": 0.0331,
      "step": 840
    },
    {
      "epoch": 0.8204633204633205,
      "grad_norm": 0.4021511673927307,
      "learning_rate": 3.661417322834646e-05,
      "loss": 0.0406,
      "step": 850
    },
    {
      "epoch": 0.8301158301158301,
      "grad_norm": 0.6140969395637512,
      "learning_rate": 3.464566929133858e-05,
      "loss": 0.0466,
      "step": 860
    },
    {
      "epoch": 0.8397683397683398,
      "grad_norm": 0.4614850878715515,
      "learning_rate": 3.2677165354330704e-05,
      "loss": 0.0285,
      "step": 870
    },
    {
      "epoch": 0.8494208494208494,
      "grad_norm": 0.6398894786834717,
      "learning_rate": 3.070866141732284e-05,
      "loss": 0.0515,
      "step": 880
    },
    {
      "epoch": 0.859073359073359,
      "grad_norm": 0.3512854278087616,
      "learning_rate": 2.874015748031496e-05,
      "loss": 0.0336,
      "step": 890
    },
    {
      "epoch": 0.8687258687258688,
      "grad_norm": 0.2678048610687256,
      "learning_rate": 2.677165354330709e-05,
      "loss": 0.0286,
      "step": 900
    },
    {
      "epoch": 0.8783783783783784,
      "grad_norm": 0.5848315358161926,
      "learning_rate": 2.4803149606299215e-05,
      "loss": 0.0384,
      "step": 910
    },
    {
      "epoch": 0.888030888030888,
      "grad_norm": 0.2881620228290558,
      "learning_rate": 2.283464566929134e-05,
      "loss": 0.0424,
      "step": 920
    },
    {
      "epoch": 0.8976833976833977,
      "grad_norm": 0.3219210207462311,
      "learning_rate": 2.0866141732283465e-05,
      "loss": 0.0488,
      "step": 930
    },
    {
      "epoch": 0.9073359073359073,
      "grad_norm": 0.408877432346344,
      "learning_rate": 1.889763779527559e-05,
      "loss": 0.0345,
      "step": 940
    },
    {
      "epoch": 0.916988416988417,
      "grad_norm": 0.20342448353767395,
      "learning_rate": 1.692913385826772e-05,
      "loss": 0.049,
      "step": 950
    },
    {
      "epoch": 0.9266409266409267,
      "grad_norm": 0.4167528748512268,
      "learning_rate": 1.4960629921259845e-05,
      "loss": 0.043,
      "step": 960
    },
    {
      "epoch": 0.9362934362934363,
      "grad_norm": 0.49826258420944214,
      "learning_rate": 1.2992125984251968e-05,
      "loss": 0.0412,
      "step": 970
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 0.5426783561706543,
      "learning_rate": 1.1023622047244095e-05,
      "loss": 0.0538,
      "step": 980
    },
    {
      "epoch": 0.9555984555984556,
      "grad_norm": 0.170461505651474,
      "learning_rate": 9.055118110236222e-06,
      "loss": 0.0483,
      "step": 990
    },
    {
      "epoch": 0.9652509652509652,
      "grad_norm": 0.3618116080760956,
      "learning_rate": 7.086614173228347e-06,
      "loss": 0.038,
      "step": 1000
    },
    {
      "epoch": 0.974903474903475,
      "grad_norm": 0.417107492685318,
      "learning_rate": 5.118110236220473e-06,
      "loss": 0.0373,
      "step": 1010
    },
    {
      "epoch": 0.9845559845559846,
      "grad_norm": 0.4384624660015106,
      "learning_rate": 3.1496062992125985e-06,
      "loss": 0.0534,
      "step": 1020
    },
    {
      "epoch": 0.9942084942084942,
      "grad_norm": 0.7793737649917603,
      "learning_rate": 1.1811023622047244e-06,
      "loss": 0.0406,
      "step": 1030
    }
  ],
  "logging_steps": 10,
  "max_steps": 1036,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0789424666431488e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}