{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.994548758328286,
  "eval_steps": 500,
  "global_step": 1236,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024227740763173834,
      "grad_norm": 3.9645989545939098,
      "learning_rate": 5e-06,
      "loss": 0.9024,
      "step": 10
    },
    {
      "epoch": 0.04845548152634767,
      "grad_norm": 2.6091656491728203,
      "learning_rate": 5e-06,
      "loss": 0.7644,
      "step": 20
    },
    {
      "epoch": 0.0726832222895215,
      "grad_norm": 1.6703261434511345,
      "learning_rate": 5e-06,
      "loss": 0.7238,
      "step": 30
    },
    {
      "epoch": 0.09691096305269534,
      "grad_norm": 1.461094134640432,
      "learning_rate": 5e-06,
      "loss": 0.6977,
      "step": 40
    },
    {
      "epoch": 0.12113870381586916,
      "grad_norm": 0.8067370661660782,
      "learning_rate": 5e-06,
      "loss": 0.6812,
      "step": 50
    },
    {
      "epoch": 0.145366444579043,
      "grad_norm": 1.4104496160894404,
      "learning_rate": 5e-06,
      "loss": 0.6629,
      "step": 60
    },
    {
      "epoch": 0.16959418534221685,
      "grad_norm": 1.2867495210279274,
      "learning_rate": 5e-06,
      "loss": 0.6521,
      "step": 70
    },
    {
      "epoch": 0.19382192610539067,
      "grad_norm": 0.9866240288945327,
      "learning_rate": 5e-06,
      "loss": 0.6341,
      "step": 80
    },
    {
      "epoch": 0.2180496668685645,
      "grad_norm": 0.7803813977069882,
      "learning_rate": 5e-06,
      "loss": 0.6285,
      "step": 90
    },
    {
      "epoch": 0.24227740763173833,
      "grad_norm": 0.5198909215148648,
      "learning_rate": 5e-06,
      "loss": 0.6244,
      "step": 100
    },
    {
      "epoch": 0.2665051483949122,
      "grad_norm": 0.5514332756156626,
      "learning_rate": 5e-06,
      "loss": 0.6184,
      "step": 110
    },
    {
      "epoch": 0.290732889158086,
      "grad_norm": 1.2655246772691944,
      "learning_rate": 5e-06,
      "loss": 0.6167,
      "step": 120
    },
    {
      "epoch": 0.31496062992125984,
      "grad_norm": 0.5276778250168523,
      "learning_rate": 5e-06,
      "loss": 0.6077,
      "step": 130
    },
    {
      "epoch": 0.3391883706844337,
      "grad_norm": 0.5180368157026216,
      "learning_rate": 5e-06,
      "loss": 0.6025,
      "step": 140
    },
    {
      "epoch": 0.3634161114476075,
      "grad_norm": 0.5457057952002654,
      "learning_rate": 5e-06,
      "loss": 0.6051,
      "step": 150
    },
    {
      "epoch": 0.38764385221078135,
      "grad_norm": 0.6644602782199635,
      "learning_rate": 5e-06,
      "loss": 0.6054,
      "step": 160
    },
    {
      "epoch": 0.4118715929739552,
      "grad_norm": 0.5187189241493725,
      "learning_rate": 5e-06,
      "loss": 0.6004,
      "step": 170
    },
    {
      "epoch": 0.436099333737129,
      "grad_norm": 0.5056757936675704,
      "learning_rate": 5e-06,
      "loss": 0.5938,
      "step": 180
    },
    {
      "epoch": 0.46032707450030286,
      "grad_norm": 0.5710728558545756,
      "learning_rate": 5e-06,
      "loss": 0.598,
      "step": 190
    },
    {
      "epoch": 0.48455481526347666,
      "grad_norm": 0.5927928756195961,
      "learning_rate": 5e-06,
      "loss": 0.5983,
      "step": 200
    },
    {
      "epoch": 0.5087825560266506,
      "grad_norm": 0.48351208074872803,
      "learning_rate": 5e-06,
      "loss": 0.59,
      "step": 210
    },
    {
      "epoch": 0.5330102967898244,
      "grad_norm": 0.5309314168696151,
      "learning_rate": 5e-06,
      "loss": 0.5882,
      "step": 220
    },
    {
      "epoch": 0.5572380375529982,
      "grad_norm": 0.5313229865997172,
      "learning_rate": 5e-06,
      "loss": 0.5926,
      "step": 230
    },
    {
      "epoch": 0.581465778316172,
      "grad_norm": 0.5147829777258456,
      "learning_rate": 5e-06,
      "loss": 0.5851,
      "step": 240
    },
    {
      "epoch": 0.6056935190793459,
      "grad_norm": 0.8359724219646064,
      "learning_rate": 5e-06,
      "loss": 0.5863,
      "step": 250
    },
    {
      "epoch": 0.6299212598425197,
      "grad_norm": 0.4652543495079898,
      "learning_rate": 5e-06,
      "loss": 0.5813,
      "step": 260
    },
    {
      "epoch": 0.6541490006056935,
      "grad_norm": 0.9372041174809007,
      "learning_rate": 5e-06,
      "loss": 0.5794,
      "step": 270
    },
    {
      "epoch": 0.6783767413688674,
      "grad_norm": 0.5998442061578241,
      "learning_rate": 5e-06,
      "loss": 0.5828,
      "step": 280
    },
    {
      "epoch": 0.7026044821320412,
      "grad_norm": 0.6092016010381666,
      "learning_rate": 5e-06,
      "loss": 0.5777,
      "step": 290
    },
    {
      "epoch": 0.726832222895215,
      "grad_norm": 0.5895950017891558,
      "learning_rate": 5e-06,
      "loss": 0.5753,
      "step": 300
    },
    {
      "epoch": 0.7510599636583889,
      "grad_norm": 0.45074902625510205,
      "learning_rate": 5e-06,
      "loss": 0.569,
      "step": 310
    },
    {
      "epoch": 0.7752877044215627,
      "grad_norm": 0.6565760889840895,
      "learning_rate": 5e-06,
      "loss": 0.578,
      "step": 320
    },
    {
      "epoch": 0.7995154451847365,
      "grad_norm": 0.6113007537505482,
      "learning_rate": 5e-06,
      "loss": 0.5792,
      "step": 330
    },
    {
      "epoch": 0.8237431859479104,
      "grad_norm": 0.49731635826965837,
      "learning_rate": 5e-06,
      "loss": 0.5811,
      "step": 340
    },
    {
      "epoch": 0.8479709267110842,
      "grad_norm": 0.5433055892052826,
      "learning_rate": 5e-06,
      "loss": 0.5727,
      "step": 350
    },
    {
      "epoch": 0.872198667474258,
      "grad_norm": 0.5791498183091245,
      "learning_rate": 5e-06,
      "loss": 0.5722,
      "step": 360
    },
    {
      "epoch": 0.8964264082374318,
      "grad_norm": 0.6563753601996463,
      "learning_rate": 5e-06,
      "loss": 0.5716,
      "step": 370
    },
    {
      "epoch": 0.9206541490006057,
      "grad_norm": 0.5662298833739237,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 380
    },
    {
      "epoch": 0.9448818897637795,
      "grad_norm": 0.5441406943018641,
      "learning_rate": 5e-06,
      "loss": 0.5708,
      "step": 390
    },
    {
      "epoch": 0.9691096305269533,
      "grad_norm": 0.6030868477920374,
      "learning_rate": 5e-06,
      "loss": 0.5707,
      "step": 400
    },
    {
      "epoch": 0.9933373712901272,
      "grad_norm": 0.6009876519163959,
      "learning_rate": 5e-06,
      "loss": 0.5624,
      "step": 410
    },
    {
      "epoch": 0.9981829194427619,
      "eval_loss": 0.5625064373016357,
      "eval_runtime": 220.8608,
      "eval_samples_per_second": 50.353,
      "eval_steps_per_second": 0.394,
      "step": 412
    },
    {
      "epoch": 1.0175651120533011,
      "grad_norm": 0.7010348009420115,
      "learning_rate": 5e-06,
      "loss": 0.542,
      "step": 420
    },
    {
      "epoch": 1.0417928528164748,
      "grad_norm": 0.48384852790918653,
      "learning_rate": 5e-06,
      "loss": 0.5311,
      "step": 430
    },
    {
      "epoch": 1.0660205935796487,
      "grad_norm": 0.7302174149962929,
      "learning_rate": 5e-06,
      "loss": 0.5346,
      "step": 440
    },
    {
      "epoch": 1.0902483343428226,
      "grad_norm": 0.6089180089825021,
      "learning_rate": 5e-06,
      "loss": 0.5341,
      "step": 450
    },
    {
      "epoch": 1.1144760751059963,
      "grad_norm": 0.6370901566175011,
      "learning_rate": 5e-06,
      "loss": 0.5278,
      "step": 460
    },
    {
      "epoch": 1.1387038158691702,
      "grad_norm": 1.0810998793516953,
      "learning_rate": 5e-06,
      "loss": 0.5282,
      "step": 470
    },
    {
      "epoch": 1.1629315566323442,
      "grad_norm": 0.5546290586428997,
      "learning_rate": 5e-06,
      "loss": 0.5294,
      "step": 480
    },
    {
      "epoch": 1.1871592973955178,
      "grad_norm": 0.5393162492751344,
      "learning_rate": 5e-06,
      "loss": 0.5312,
      "step": 490
    },
    {
      "epoch": 1.2113870381586918,
      "grad_norm": 0.539293775840461,
      "learning_rate": 5e-06,
      "loss": 0.5327,
      "step": 500
    },
    {
      "epoch": 1.2356147789218654,
      "grad_norm": 0.5510862357568564,
      "learning_rate": 5e-06,
      "loss": 0.5292,
      "step": 510
    },
    {
      "epoch": 1.2598425196850394,
      "grad_norm": 0.7420323514260083,
      "learning_rate": 5e-06,
      "loss": 0.5282,
      "step": 520
    },
    {
      "epoch": 1.2840702604482133,
      "grad_norm": 0.7139637253621622,
      "learning_rate": 5e-06,
      "loss": 0.5305,
      "step": 530
    },
    {
      "epoch": 1.3082980012113872,
      "grad_norm": 0.5530723883454477,
      "learning_rate": 5e-06,
      "loss": 0.5262,
      "step": 540
    },
    {
      "epoch": 1.3325257419745609,
      "grad_norm": 0.5575001199886374,
      "learning_rate": 5e-06,
      "loss": 0.5219,
      "step": 550
    },
    {
      "epoch": 1.3567534827377348,
      "grad_norm": 0.5598952872055329,
      "learning_rate": 5e-06,
      "loss": 0.5238,
      "step": 560
    },
    {
      "epoch": 1.3809812235009085,
      "grad_norm": 0.541421977102063,
      "learning_rate": 5e-06,
      "loss": 0.5277,
      "step": 570
    },
    {
      "epoch": 1.4052089642640824,
      "grad_norm": 0.4779799353516479,
      "learning_rate": 5e-06,
      "loss": 0.5233,
      "step": 580
    },
    {
      "epoch": 1.4294367050272563,
      "grad_norm": 0.4967009823362501,
      "learning_rate": 5e-06,
      "loss": 0.5259,
      "step": 590
    },
    {
      "epoch": 1.45366444579043,
      "grad_norm": 0.671567804923544,
      "learning_rate": 5e-06,
      "loss": 0.52,
      "step": 600
    },
    {
      "epoch": 1.4778921865536039,
      "grad_norm": 0.5142557306648593,
      "learning_rate": 5e-06,
      "loss": 0.5219,
      "step": 610
    },
    {
      "epoch": 1.5021199273167776,
      "grad_norm": 0.48133107485569593,
      "learning_rate": 5e-06,
      "loss": 0.5227,
      "step": 620
    },
    {
      "epoch": 1.5263476680799517,
      "grad_norm": 0.4824602880697514,
      "learning_rate": 5e-06,
      "loss": 0.5254,
      "step": 630
    },
    {
      "epoch": 1.5505754088431254,
      "grad_norm": 0.5818160150007355,
      "learning_rate": 5e-06,
      "loss": 0.5167,
      "step": 640
    },
    {
      "epoch": 1.574803149606299,
      "grad_norm": 0.5210634892581837,
      "learning_rate": 5e-06,
      "loss": 0.5188,
      "step": 650
    },
    {
      "epoch": 1.5990308903694732,
      "grad_norm": 0.5785709705676149,
      "learning_rate": 5e-06,
      "loss": 0.5247,
      "step": 660
    },
    {
      "epoch": 1.623258631132647,
      "grad_norm": 0.49452413290015934,
      "learning_rate": 5e-06,
      "loss": 0.5163,
      "step": 670
    },
    {
      "epoch": 1.6474863718958206,
      "grad_norm": 0.548802848702529,
      "learning_rate": 5e-06,
      "loss": 0.5156,
      "step": 680
    },
    {
      "epoch": 1.6717141126589945,
      "grad_norm": 0.49091799711876205,
      "learning_rate": 5e-06,
      "loss": 0.519,
      "step": 690
    },
    {
      "epoch": 1.6959418534221684,
      "grad_norm": 0.49801605722138825,
      "learning_rate": 5e-06,
      "loss": 0.5168,
      "step": 700
    },
    {
      "epoch": 1.720169594185342,
      "grad_norm": 0.5325592423676614,
      "learning_rate": 5e-06,
      "loss": 0.5159,
      "step": 710
    },
    {
      "epoch": 1.744397334948516,
      "grad_norm": 0.5638908149569352,
      "learning_rate": 5e-06,
      "loss": 0.5178,
      "step": 720
    },
    {
      "epoch": 1.76862507571169,
      "grad_norm": 0.5592361495425977,
      "learning_rate": 5e-06,
      "loss": 0.5201,
      "step": 730
    },
    {
      "epoch": 1.7928528164748636,
      "grad_norm": 0.6123941159516728,
      "learning_rate": 5e-06,
      "loss": 0.5158,
      "step": 740
    },
    {
      "epoch": 1.8170805572380375,
      "grad_norm": 0.6140218865131343,
      "learning_rate": 5e-06,
      "loss": 0.5212,
      "step": 750
    },
    {
      "epoch": 1.8413082980012114,
      "grad_norm": 0.5120361752286156,
      "learning_rate": 5e-06,
      "loss": 0.5165,
      "step": 760
    },
    {
      "epoch": 1.8655360387643851,
      "grad_norm": 0.6257809652633152,
      "learning_rate": 5e-06,
      "loss": 0.5154,
      "step": 770
    },
    {
      "epoch": 1.889763779527559,
      "grad_norm": 0.5517067441775361,
      "learning_rate": 5e-06,
      "loss": 0.5149,
      "step": 780
    },
    {
      "epoch": 1.913991520290733,
      "grad_norm": 0.6184341957543669,
      "learning_rate": 5e-06,
      "loss": 0.5161,
      "step": 790
    },
    {
      "epoch": 1.9382192610539066,
      "grad_norm": 0.45820885449224846,
      "learning_rate": 5e-06,
      "loss": 0.5163,
      "step": 800
    },
    {
      "epoch": 1.9624470018170805,
      "grad_norm": 0.47230402419753703,
      "learning_rate": 5e-06,
      "loss": 0.5097,
      "step": 810
    },
    {
      "epoch": 1.9866747425802544,
      "grad_norm": 0.5117535404655704,
      "learning_rate": 5e-06,
      "loss": 0.5104,
      "step": 820
    },
    {
      "epoch": 1.9987886129618413,
      "eval_loss": 0.5373826026916504,
      "eval_runtime": 221.5646,
      "eval_samples_per_second": 50.193,
      "eval_steps_per_second": 0.393,
      "step": 825
    },
    {
      "epoch": 2.010902483343428,
      "grad_norm": 0.7236309822644943,
      "learning_rate": 5e-06,
      "loss": 0.4992,
      "step": 830
    },
    {
      "epoch": 2.0351302241066023,
      "grad_norm": 0.51924831256788,
      "learning_rate": 5e-06,
      "loss": 0.4661,
      "step": 840
    },
    {
      "epoch": 2.059357964869776,
      "grad_norm": 0.6287431376712824,
      "learning_rate": 5e-06,
      "loss": 0.4782,
      "step": 850
    },
    {
      "epoch": 2.0835857056329496,
      "grad_norm": 0.5560237407779974,
      "learning_rate": 5e-06,
      "loss": 0.4752,
      "step": 860
    },
    {
      "epoch": 2.107813446396124,
      "grad_norm": 0.4951419799289088,
      "learning_rate": 5e-06,
      "loss": 0.4783,
      "step": 870
    },
    {
      "epoch": 2.1320411871592975,
      "grad_norm": 0.6200927154763336,
      "learning_rate": 5e-06,
      "loss": 0.4744,
      "step": 880
    },
    {
      "epoch": 2.156268927922471,
      "grad_norm": 0.5434006657342179,
      "learning_rate": 5e-06,
      "loss": 0.4805,
      "step": 890
    },
    {
      "epoch": 2.1804966686856453,
      "grad_norm": 0.5223425161148432,
      "learning_rate": 5e-06,
      "loss": 0.4754,
      "step": 900
    },
    {
      "epoch": 2.204724409448819,
      "grad_norm": 0.6825783856408546,
      "learning_rate": 5e-06,
      "loss": 0.4758,
      "step": 910
    },
    {
      "epoch": 2.2289521502119927,
      "grad_norm": 0.7441341191332547,
      "learning_rate": 5e-06,
      "loss": 0.4745,
      "step": 920
    },
    {
      "epoch": 2.253179890975167,
      "grad_norm": 0.5442102121881107,
      "learning_rate": 5e-06,
      "loss": 0.4784,
      "step": 930
    },
    {
      "epoch": 2.2774076317383405,
      "grad_norm": 0.6283995286149499,
      "learning_rate": 5e-06,
      "loss": 0.4804,
      "step": 940
    },
    {
      "epoch": 2.301635372501514,
      "grad_norm": 0.5816653838824051,
      "learning_rate": 5e-06,
      "loss": 0.4778,
      "step": 950
    },
    {
      "epoch": 2.3258631132646883,
      "grad_norm": 0.5549081081953725,
      "learning_rate": 5e-06,
      "loss": 0.4769,
      "step": 960
    },
    {
      "epoch": 2.350090854027862,
      "grad_norm": 0.5279973698132591,
      "learning_rate": 5e-06,
      "loss": 0.4784,
      "step": 970
    },
    {
      "epoch": 2.3743185947910357,
      "grad_norm": 0.6086532168897438,
      "learning_rate": 5e-06,
      "loss": 0.4859,
      "step": 980
    },
    {
      "epoch": 2.39854633555421,
      "grad_norm": 0.5428630520508304,
      "learning_rate": 5e-06,
      "loss": 0.4797,
      "step": 990
    },
    {
      "epoch": 2.4227740763173835,
      "grad_norm": 0.5159093369572579,
      "learning_rate": 5e-06,
      "loss": 0.4767,
      "step": 1000
    },
    {
      "epoch": 2.447001817080557,
      "grad_norm": 0.6376648956193381,
      "learning_rate": 5e-06,
      "loss": 0.4797,
      "step": 1010
    },
    {
      "epoch": 2.471229557843731,
      "grad_norm": 0.5547640740107239,
      "learning_rate": 5e-06,
      "loss": 0.4747,
      "step": 1020
    },
    {
      "epoch": 2.495457298606905,
      "grad_norm": 0.4712927664253549,
      "learning_rate": 5e-06,
      "loss": 0.483,
      "step": 1030
    },
    {
      "epoch": 2.5196850393700787,
      "grad_norm": 0.5246957682925482,
      "learning_rate": 5e-06,
      "loss": 0.4831,
      "step": 1040
    },
    {
      "epoch": 2.543912780133253,
      "grad_norm": 0.49350610935172784,
      "learning_rate": 5e-06,
      "loss": 0.4761,
      "step": 1050
    },
    {
      "epoch": 2.5681405208964265,
      "grad_norm": 0.5385640165749516,
      "learning_rate": 5e-06,
      "loss": 0.4781,
      "step": 1060
    },
    {
      "epoch": 2.5923682616596,
      "grad_norm": 0.5103595421050182,
      "learning_rate": 5e-06,
      "loss": 0.4745,
      "step": 1070
    },
    {
      "epoch": 2.6165960024227743,
      "grad_norm": 0.4917765675984819,
      "learning_rate": 5e-06,
      "loss": 0.4744,
      "step": 1080
    },
    {
      "epoch": 2.640823743185948,
      "grad_norm": 0.5057838998647487,
      "learning_rate": 5e-06,
      "loss": 0.4812,
      "step": 1090
    },
    {
      "epoch": 2.6650514839491217,
      "grad_norm": 0.5132155115777407,
      "learning_rate": 5e-06,
      "loss": 0.4714,
      "step": 1100
    },
    {
      "epoch": 2.6892792247122954,
      "grad_norm": 0.5268065417493973,
      "learning_rate": 5e-06,
      "loss": 0.4761,
      "step": 1110
    },
    {
      "epoch": 2.7135069654754695,
      "grad_norm": 0.552687045729179,
      "learning_rate": 5e-06,
      "loss": 0.4752,
      "step": 1120
    },
    {
      "epoch": 2.7377347062386432,
      "grad_norm": 0.5709091633003863,
      "learning_rate": 5e-06,
      "loss": 0.4761,
      "step": 1130
    },
    {
      "epoch": 2.761962447001817,
      "grad_norm": 0.4924939447065247,
      "learning_rate": 5e-06,
      "loss": 0.4817,
      "step": 1140
    },
    {
      "epoch": 2.786190187764991,
      "grad_norm": 0.613145736032828,
      "learning_rate": 5e-06,
      "loss": 0.4758,
      "step": 1150
    },
    {
      "epoch": 2.8104179285281647,
      "grad_norm": 0.5517385387267716,
      "learning_rate": 5e-06,
      "loss": 0.4732,
      "step": 1160
    },
    {
      "epoch": 2.8346456692913384,
      "grad_norm": 0.5952199661627586,
      "learning_rate": 5e-06,
      "loss": 0.4832,
      "step": 1170
    },
    {
      "epoch": 2.8588734100545126,
      "grad_norm": 0.6646202856678104,
      "learning_rate": 5e-06,
      "loss": 0.4767,
      "step": 1180
    },
    {
      "epoch": 2.8831011508176863,
      "grad_norm": 0.7488420183599482,
      "learning_rate": 5e-06,
      "loss": 0.4773,
      "step": 1190
    },
    {
      "epoch": 2.90732889158086,
      "grad_norm": 0.634712672540643,
      "learning_rate": 5e-06,
      "loss": 0.4803,
      "step": 1200
    },
    {
      "epoch": 2.931556632344034,
      "grad_norm": 0.479455288955399,
      "learning_rate": 5e-06,
      "loss": 0.476,
      "step": 1210
    },
    {
      "epoch": 2.9557843731072078,
      "grad_norm": 0.4788695949163765,
      "learning_rate": 5e-06,
      "loss": 0.4792,
      "step": 1220
    },
    {
      "epoch": 2.9800121138703815,
      "grad_norm": 0.5724033736756394,
      "learning_rate": 5e-06,
      "loss": 0.4815,
      "step": 1230
    },
    {
      "epoch": 2.994548758328286,
      "eval_loss": 0.530586838722229,
      "eval_runtime": 221.8544,
      "eval_samples_per_second": 50.127,
      "eval_steps_per_second": 0.392,
      "step": 1236
    },
    {
      "epoch": 2.994548758328286,
      "step": 1236,
      "total_flos": 2069927276052480.0,
      "train_loss": 0.5379253575716976,
      "train_runtime": 37041.7776,
      "train_samples_per_second": 17.113,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 10,
  "max_steps": 1236,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2069927276052480.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}