{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9934123847167324,
  "eval_steps": 500,
  "global_step": 852,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03513394817742644,
      "grad_norm": 0.43717896938323975,
      "learning_rate": 0.00019230769230769233,
      "loss": 1.994,
      "step": 10
    },
    {
      "epoch": 0.07026789635485288,
      "grad_norm": 0.4105484187602997,
      "learning_rate": 0.00038461538461538467,
      "loss": 1.7122,
      "step": 20
    },
    {
      "epoch": 0.10540184453227931,
      "grad_norm": 0.39099714159965515,
      "learning_rate": 0.0004999710691449165,
      "loss": 1.7017,
      "step": 30
    },
    {
      "epoch": 0.14053579270970576,
      "grad_norm": 0.418653279542923,
      "learning_rate": 0.0004996456739191905,
      "loss": 1.7533,
      "step": 40
    },
    {
      "epoch": 0.1756697408871322,
      "grad_norm": 0.402630478143692,
      "learning_rate": 0.0004989591921187147,
      "loss": 1.6842,
      "step": 50
    },
    {
      "epoch": 0.21080368906455862,
      "grad_norm": 0.4017012119293213,
      "learning_rate": 0.0004979126166682133,
      "loss": 1.6915,
      "step": 60
    },
    {
      "epoch": 0.24593763724198506,
      "grad_norm": 0.5224213004112244,
      "learning_rate": 0.0004965074613305277,
      "loss": 1.7208,
      "step": 70
    },
    {
      "epoch": 0.2810715854194115,
      "grad_norm": 0.5111001133918762,
      "learning_rate": 0.0004947457585171148,
      "loss": 1.6386,
      "step": 80
    },
    {
      "epoch": 0.31620553359683795,
      "grad_norm": 0.6671903133392334,
      "learning_rate": 0.000492630056348375,
      "loss": 1.6592,
      "step": 90
    },
    {
      "epoch": 0.3513394817742644,
      "grad_norm": 0.4950112998485565,
      "learning_rate": 0.0004901634149680608,
      "loss": 1.6741,
      "step": 100
    },
    {
      "epoch": 0.3864734299516908,
      "grad_norm": 0.5058407783508301,
      "learning_rate": 0.0004873494021170953,
      "loss": 1.7568,
      "step": 110
    },
    {
      "epoch": 0.42160737812911725,
      "grad_norm": 0.8665825724601746,
      "learning_rate": 0.00048419208797320564,
      "loss": 1.7356,
      "step": 120
    },
    {
      "epoch": 0.4567413263065437,
      "grad_norm": 0.5124475955963135,
      "learning_rate": 0.00048069603926383277,
      "loss": 1.7199,
      "step": 130
    },
    {
      "epoch": 0.4918752744839701,
      "grad_norm": 0.505696177482605,
      "learning_rate": 0.0004768663126608342,
      "loss": 1.6813,
      "step": 140
    },
    {
      "epoch": 0.5270092226613966,
      "grad_norm": 0.509445071220398,
      "learning_rate": 0.0004727084474665322,
      "loss": 1.7074,
      "step": 150
    },
    {
      "epoch": 0.562143170838823,
      "grad_norm": 0.5511056184768677,
      "learning_rate": 0.00046822845760168783,
      "loss": 1.6766,
      "step": 160
    },
    {
      "epoch": 0.5972771190162495,
      "grad_norm": 0.46946030855178833,
      "learning_rate": 0.0004634328229069881,
      "loss": 1.7018,
      "step": 170
    },
    {
      "epoch": 0.6324110671936759,
      "grad_norm": 0.49886614084243774,
      "learning_rate": 0.00045832847977062875,
      "loss": 1.7293,
      "step": 180
    },
    {
      "epoch": 0.6675450153711023,
      "grad_norm": 0.49424228072166443,
      "learning_rate": 0.0004529228110955478,
      "loss": 1.7306,
      "step": 190
    },
    {
      "epoch": 0.7026789635485288,
      "grad_norm": 0.5640605092048645,
      "learning_rate": 0.00044722363562082237,
      "loss": 1.7369,
      "step": 200
    },
    {
      "epoch": 0.7378129117259552,
      "grad_norm": 0.5802103281021118,
      "learning_rate": 0.0004412391966126735,
      "loss": 1.7463,
      "step": 210
    },
    {
      "epoch": 0.7729468599033816,
      "grad_norm": 0.5365092158317566,
      "learning_rate": 0.0004349781499414369,
      "loss": 1.7198,
      "step": 220
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.5591799020767212,
      "learning_rate": 0.00042844955156174345,
      "loss": 1.7298,
      "step": 230
    },
    {
      "epoch": 0.8432147562582345,
      "grad_norm": 0.5256664156913757,
      "learning_rate": 0.000421662844414021,
      "loss": 1.6863,
      "step": 240
    },
    {
      "epoch": 0.8783487044356609,
      "grad_norm": 0.6382088661193848,
      "learning_rate": 0.0004146278447662597,
      "loss": 1.7195,
      "step": 250
    },
    {
      "epoch": 0.9134826526130874,
      "grad_norm": 0.5260637402534485,
      "learning_rate": 0.00040735472801579887,
      "loss": 1.7135,
      "step": 260
    },
    {
      "epoch": 0.9486166007905138,
      "grad_norm": 0.5244185328483582,
      "learning_rate": 0.0003998540139716701,
      "loss": 1.6944,
      "step": 270
    },
    {
      "epoch": 0.9837505489679402,
      "grad_norm": 0.5998988747596741,
      "learning_rate": 0.00039213655163878436,
      "loss": 1.6982,
      "step": 280
    },
    {
      "epoch": 1.0188844971453668,
      "grad_norm": 0.6315314173698425,
      "learning_rate": 0.00038421350352597195,
      "loss": 1.5473,
      "step": 290
    },
    {
      "epoch": 1.0540184453227932,
      "grad_norm": 0.6495606899261475,
      "learning_rate": 0.00037609632950057095,
      "loss": 1.3535,
      "step": 300
    },
    {
      "epoch": 1.0891523935002196,
      "grad_norm": 0.6094574928283691,
      "learning_rate": 0.0003677967702129177,
      "loss": 1.3452,
      "step": 310
    },
    {
      "epoch": 1.124286341677646,
      "grad_norm": 0.5786643028259277,
      "learning_rate": 0.0003593268301147139,
      "loss": 1.3433,
      "step": 320
    },
    {
      "epoch": 1.1594202898550725,
      "grad_norm": 0.6357799172401428,
      "learning_rate": 0.00035069876009583234,
      "loss": 1.4166,
      "step": 330
    },
    {
      "epoch": 1.194554238032499,
      "grad_norm": 0.6568606495857239,
      "learning_rate": 0.00034192503976467525,
      "loss": 1.323,
      "step": 340
    },
    {
      "epoch": 1.2296881862099254,
      "grad_norm": 0.6073617339134216,
      "learning_rate": 0.0003330183593977152,
      "loss": 1.389,
      "step": 350
    },
    {
      "epoch": 1.2648221343873518,
      "grad_norm": 0.5338005423545837,
      "learning_rate": 0.00032399160158432606,
      "loss": 1.3739,
      "step": 360
    },
    {
      "epoch": 1.2999560825647782,
      "grad_norm": 0.6769421100616455,
      "learning_rate": 0.00031485782259345406,
      "loss": 1.4024,
      "step": 370
    },
    {
      "epoch": 1.3350900307422047,
      "grad_norm": 0.6495899558067322,
      "learning_rate": 0.0003056302334890786,
      "loss": 1.3615,
      "step": 380
    },
    {
      "epoch": 1.370223978919631,
      "grad_norm": 0.6488791108131409,
      "learning_rate": 0.0002963221810217786,
      "loss": 1.3548,
      "step": 390
    },
    {
      "epoch": 1.4053579270970575,
      "grad_norm": 0.746868908405304,
      "learning_rate": 0.00028694712832404195,
      "loss": 1.3749,
      "step": 400
    },
    {
      "epoch": 1.440491875274484,
      "grad_norm": 0.6373124122619629,
      "learning_rate": 0.0002775186354372408,
      "loss": 1.3555,
      "step": 410
    },
    {
      "epoch": 1.4756258234519104,
      "grad_norm": 0.6247098445892334,
      "learning_rate": 0.0002680503396984382,
      "loss": 1.3977,
      "step": 420
    },
    {
      "epoch": 1.5107597716293368,
      "grad_norm": 0.6373061537742615,
      "learning_rate": 0.00025855593601539415,
      "loss": 1.3637,
      "step": 430
    },
    {
      "epoch": 1.5458937198067633,
      "grad_norm": 0.7269704341888428,
      "learning_rate": 0.00024904915705830234,
      "loss": 1.4263,
      "step": 440
    },
    {
      "epoch": 1.5810276679841897,
      "grad_norm": 0.6946704983711243,
      "learning_rate": 0.0002395437533969069,
      "loss": 1.3822,
      "step": 450
    },
    {
      "epoch": 1.6161616161616161,
      "grad_norm": 0.6399605870246887,
      "learning_rate": 0.0002300534736117292,
      "loss": 1.4348,
      "step": 460
    },
    {
      "epoch": 1.6512955643390426,
      "grad_norm": 0.6449073553085327,
      "learning_rate": 0.00022059204440817246,
      "loss": 1.3793,
      "step": 470
    },
    {
      "epoch": 1.686429512516469,
      "grad_norm": 0.616384744644165,
      "learning_rate": 0.00021117315076226557,
      "loss": 1.3917,
      "step": 480
    },
    {
      "epoch": 1.7215634606938954,
      "grad_norm": 0.6383651494979858,
      "learning_rate": 0.0002018104161267652,
      "loss": 1.4097,
      "step": 490
    },
    {
      "epoch": 1.7566974088713219,
      "grad_norm": 0.720451295375824,
      "learning_rate": 0.00019251738272624416,
      "loss": 1.3997,
      "step": 500
    },
    {
      "epoch": 1.7918313570487485,
      "grad_norm": 0.6487829685211182,
      "learning_rate": 0.00018330749196966806,
      "loss": 1.4366,
      "step": 510
    },
    {
      "epoch": 1.826965305226175,
      "grad_norm": 0.6398463249206543,
      "learning_rate": 0.00017419406500879115,
      "loss": 1.3536,
      "step": 520
    },
    {
      "epoch": 1.8620992534036014,
      "grad_norm": 0.7006503939628601,
      "learning_rate": 0.00016519028347049242,
      "loss": 1.3934,
      "step": 530
    },
    {
      "epoch": 1.8972332015810278,
      "grad_norm": 0.6170542240142822,
      "learning_rate": 0.00015630917039091919,
      "loss": 1.4171,
      "step": 540
    },
    {
      "epoch": 1.9323671497584543,
      "grad_norm": 0.6998418569564819,
      "learning_rate": 0.00014756357137901604,
      "loss": 1.3809,
      "step": 550
    },
    {
      "epoch": 1.9675010979358807,
      "grad_norm": 0.6567032933235168,
      "learning_rate": 0.00013896613603668365,
      "loss": 1.3223,
      "step": 560
    },
    {
      "epoch": 2.002635046113307,
      "grad_norm": 0.6512529253959656,
      "learning_rate": 0.00013052929966244216,
      "loss": 1.3693,
      "step": 570
    },
    {
      "epoch": 2.0377689942907335,
      "grad_norm": 0.8671336770057678,
      "learning_rate": 0.00012226526526506093,
      "loss": 1.0046,
      "step": 580
    },
    {
      "epoch": 2.07290294246816,
      "grad_norm": 0.7728586792945862,
      "learning_rate": 0.00011418598591317242,
      "loss": 1.0138,
      "step": 590
    },
    {
      "epoch": 2.1080368906455864,
      "grad_norm": 0.8196272253990173,
      "learning_rate": 0.0001063031474463983,
      "loss": 0.9985,
      "step": 600
    },
    {
      "epoch": 2.143170838823013,
      "grad_norm": 0.899488091468811,
      "learning_rate": 9.862815157299391e-05,
      "loss": 0.9397,
      "step": 610
    },
    {
      "epoch": 2.1783047870004393,
      "grad_norm": 0.7770416736602783,
      "learning_rate": 9.117209937846053e-05,
      "loss": 0.9307,
      "step": 620
    },
    {
      "epoch": 2.2134387351778657,
      "grad_norm": 0.8353050947189331,
      "learning_rate": 8.394577526897565e-05,
      "loss": 0.9334,
      "step": 630
    },
    {
      "epoch": 2.248572683355292,
      "grad_norm": 0.7152834534645081,
      "learning_rate": 7.69596313728691e-05,
      "loss": 0.9483,
      "step": 640
    },
    {
      "epoch": 2.2837066315327186,
      "grad_norm": 1.0104659795761108,
      "learning_rate": 7.022377242270251e-05,
      "loss": 0.942,
      "step": 650
    },
    {
      "epoch": 2.318840579710145,
      "grad_norm": 0.7319175004959106,
      "learning_rate": 6.374794113982232e-05,
      "loss": 0.9242,
      "step": 660
    },
    {
      "epoch": 2.3539745278875714,
      "grad_norm": 0.7895592451095581,
      "learning_rate": 5.7541504142523406e-05,
      "loss": 0.99,
      "step": 670
    },
    {
      "epoch": 2.389108476064998,
      "grad_norm": 0.9462332725524902,
      "learning_rate": 5.161343839820762e-05,
      "loss": 0.9733,
      "step": 680
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.9174964427947998,
      "learning_rate": 4.597231823913112e-05,
      "loss": 0.9478,
      "step": 690
    },
    {
      "epoch": 2.4593763724198507,
      "grad_norm": 0.7435886859893799,
      "learning_rate": 4.062630296052222e-05,
      "loss": 0.9487,
      "step": 700
    },
    {
      "epoch": 2.494510320597277,
      "grad_norm": 0.908430278301239,
      "learning_rate": 3.558312501900718e-05,
      "loss": 0.9517,
      "step": 710
    },
    {
      "epoch": 2.5296442687747036,
      "grad_norm": 0.8427926301956177,
      "learning_rate": 3.0850078848413704e-05,
      "loss": 0.93,
      "step": 720
    },
    {
      "epoch": 2.56477821695213,
      "grad_norm": 0.8396946787834167,
      "learning_rate": 2.643401030912876e-05,
      "loss": 0.9528,
      "step": 730
    },
    {
      "epoch": 2.5999121651295565,
      "grad_norm": 0.8085779547691345,
      "learning_rate": 2.234130678627169e-05,
      "loss": 0.9257,
      "step": 740
    },
    {
      "epoch": 2.635046113306983,
      "grad_norm": 0.872416079044342,
      "learning_rate": 1.8577887951004264e-05,
      "loss": 0.9294,
      "step": 750
    },
    {
      "epoch": 2.6701800614844093,
      "grad_norm": 0.8148744702339172,
      "learning_rate": 1.5149197198340014e-05,
      "loss": 0.9166,
      "step": 760
    },
    {
      "epoch": 2.7053140096618358,
      "grad_norm": 0.8573042750358582,
      "learning_rate": 1.206019377383813e-05,
      "loss": 0.9481,
      "step": 770
    },
    {
      "epoch": 2.740447957839262,
      "grad_norm": 0.7604958415031433,
      "learning_rate": 9.315345600569069e-06,
      "loss": 0.9425,
      "step": 780
    },
    {
      "epoch": 2.7755819060166886,
      "grad_norm": 0.870971143245697,
      "learning_rate": 6.918622816727255e-06,
      "loss": 0.9087,
      "step": 790
    },
    {
      "epoch": 2.810715854194115,
      "grad_norm": 0.9157975316047668,
      "learning_rate": 4.873492033237864e-06,
      "loss": 0.9547,
      "step": 800
    },
    {
      "epoch": 2.8458498023715415,
      "grad_norm": 0.9207829236984253,
      "learning_rate": 3.1829113196638614e-06,
      "loss": 0.9275,
      "step": 810
    },
    {
      "epoch": 2.880983750548968,
      "grad_norm": 0.9513605237007141,
      "learning_rate": 1.8493259256649187e-06,
      "loss": 0.981,
      "step": 820
    },
    {
      "epoch": 2.9161176987263944,
      "grad_norm": 0.854158878326416,
      "learning_rate": 8.746647441975619e-07,
      "loss": 0.9124,
      "step": 830
    },
    {
      "epoch": 2.951251646903821,
      "grad_norm": 0.8659394383430481,
      "learning_rate": 2.603375215716186e-07,
      "loss": 0.9643,
      "step": 840
    },
    {
      "epoch": 2.9863855950812472,
      "grad_norm": 0.94295734167099,
      "learning_rate": 7.23281839820622e-09,
      "loss": 0.9282,
      "step": 850
    }
  ],
  "logging_steps": 10,
  "max_steps": 852,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0935759953200589e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}