{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10958153551126636,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013697691938908295,
      "grad_norm": 0.36237362027168274,
      "learning_rate": 3.5e-06,
      "loss": 2.435038375854492,
      "step": 10
    },
    {
      "epoch": 0.002739538387781659,
      "grad_norm": 0.36249515414237976,
      "learning_rate": 8.5e-06,
      "loss": 2.2692413330078125,
      "step": 20
    },
    {
      "epoch": 0.004109307581672488,
      "grad_norm": 0.3869870603084564,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 2.338268280029297,
      "step": 30
    },
    {
      "epoch": 0.005479076775563318,
      "grad_norm": 0.43124574422836304,
      "learning_rate": 1.8500000000000002e-05,
      "loss": 2.3821529388427733,
      "step": 40
    },
    {
      "epoch": 0.006848845969454147,
      "grad_norm": 0.4636060893535614,
      "learning_rate": 1.9815789473684213e-05,
      "loss": 2.3642246246337892,
      "step": 50
    },
    {
      "epoch": 0.008218615163344977,
      "grad_norm": 0.4747641980648041,
      "learning_rate": 1.955263157894737e-05,
      "loss": 2.3556377410888674,
      "step": 60
    },
    {
      "epoch": 0.009588384357235805,
      "grad_norm": 0.6179090738296509,
      "learning_rate": 1.9289473684210526e-05,
      "loss": 2.3772085189819334,
      "step": 70
    },
    {
      "epoch": 0.010958153551126636,
      "grad_norm": 0.6049761772155762,
      "learning_rate": 1.9026315789473686e-05,
      "loss": 2.2972381591796873,
      "step": 80
    },
    {
      "epoch": 0.012327922745017464,
      "grad_norm": 0.6118033528327942,
      "learning_rate": 1.8763157894736843e-05,
      "loss": 2.352596473693848,
      "step": 90
    },
    {
      "epoch": 0.013697691938908295,
      "grad_norm": 0.6712182760238647,
      "learning_rate": 1.8500000000000002e-05,
      "loss": 2.2117843627929688,
      "step": 100
    },
    {
      "epoch": 0.015067461132799123,
      "grad_norm": 0.6315696239471436,
      "learning_rate": 1.823684210526316e-05,
      "loss": 2.239790344238281,
      "step": 110
    },
    {
      "epoch": 0.016437230326689953,
      "grad_norm": 0.5321571230888367,
      "learning_rate": 1.7973684210526315e-05,
      "loss": 2.1258014678955077,
      "step": 120
    },
    {
      "epoch": 0.017806999520580784,
      "grad_norm": 0.5182818174362183,
      "learning_rate": 1.7710526315789475e-05,
      "loss": 2.2043216705322264,
      "step": 130
    },
    {
      "epoch": 0.01917676871447161,
      "grad_norm": 0.5181311964988708,
      "learning_rate": 1.7447368421052632e-05,
      "loss": 2.166463088989258,
      "step": 140
    },
    {
      "epoch": 0.02054653790836244,
      "grad_norm": 0.48421230912208557,
      "learning_rate": 1.7184210526315788e-05,
      "loss": 2.1357837677001954,
      "step": 150
    },
    {
      "epoch": 0.02191630710225327,
      "grad_norm": 0.4353867769241333,
      "learning_rate": 1.6921052631578948e-05,
      "loss": 2.0161502838134764,
      "step": 160
    },
    {
      "epoch": 0.023286076296144098,
      "grad_norm": 0.4691782593727112,
      "learning_rate": 1.6657894736842105e-05,
      "loss": 2.0219562530517576,
      "step": 170
    },
    {
      "epoch": 0.02465584549003493,
      "grad_norm": 0.49481505155563354,
      "learning_rate": 1.6394736842105265e-05,
      "loss": 2.0304351806640626,
      "step": 180
    },
    {
      "epoch": 0.02602561468392576,
      "grad_norm": 0.3865645229816437,
      "learning_rate": 1.613157894736842e-05,
      "loss": 1.9581424713134765,
      "step": 190
    },
    {
      "epoch": 0.02739538387781659,
      "grad_norm": 0.43848446011543274,
      "learning_rate": 1.586842105263158e-05,
      "loss": 1.981527328491211,
      "step": 200
    },
    {
      "epoch": 0.028765153071707416,
      "grad_norm": 0.39352574944496155,
      "learning_rate": 1.5605263157894737e-05,
      "loss": 2.059296798706055,
      "step": 210
    },
    {
      "epoch": 0.030134922265598246,
      "grad_norm": 0.46410003304481506,
      "learning_rate": 1.5342105263157897e-05,
      "loss": 1.913700485229492,
      "step": 220
    },
    {
      "epoch": 0.03150469145948907,
      "grad_norm": 0.3708699345588684,
      "learning_rate": 1.5078947368421054e-05,
      "loss": 1.9376255035400392,
      "step": 230
    },
    {
      "epoch": 0.03287446065337991,
      "grad_norm": 0.410113126039505,
      "learning_rate": 1.4815789473684212e-05,
      "loss": 1.9357620239257813,
      "step": 240
    },
    {
      "epoch": 0.034244229847270734,
      "grad_norm": 0.34002822637557983,
      "learning_rate": 1.455263157894737e-05,
      "loss": 1.855245590209961,
      "step": 250
    },
    {
      "epoch": 0.03561399904116157,
      "grad_norm": 0.38149112462997437,
      "learning_rate": 1.4289473684210527e-05,
      "loss": 1.8379920959472655,
      "step": 260
    },
    {
      "epoch": 0.036983768235052394,
      "grad_norm": 0.3515079915523529,
      "learning_rate": 1.4026315789473685e-05,
      "loss": 1.9092113494873046,
      "step": 270
    },
    {
      "epoch": 0.03835353742894322,
      "grad_norm": 0.34938475489616394,
      "learning_rate": 1.3763157894736843e-05,
      "loss": 1.83590087890625,
      "step": 280
    },
    {
      "epoch": 0.039723306622834055,
      "grad_norm": 0.3297061324119568,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 1.9256158828735352,
      "step": 290
    },
    {
      "epoch": 0.04109307581672488,
      "grad_norm": 0.36877989768981934,
      "learning_rate": 1.323684210526316e-05,
      "loss": 1.8834123611450195,
      "step": 300
    },
    {
      "epoch": 0.04246284501061571,
      "grad_norm": 0.29596567153930664,
      "learning_rate": 1.2973684210526316e-05,
      "loss": 1.7876396179199219,
      "step": 310
    },
    {
      "epoch": 0.04383261420450654,
      "grad_norm": 0.31500086188316345,
      "learning_rate": 1.2710526315789476e-05,
      "loss": 1.8464454650878905,
      "step": 320
    },
    {
      "epoch": 0.04520238339839737,
      "grad_norm": 0.3053838610649109,
      "learning_rate": 1.2447368421052632e-05,
      "loss": 1.8393360137939454,
      "step": 330
    },
    {
      "epoch": 0.046572152592288196,
      "grad_norm": 0.3389897346496582,
      "learning_rate": 1.2184210526315789e-05,
      "loss": 1.8508255004882812,
      "step": 340
    },
    {
      "epoch": 0.04794192178617903,
      "grad_norm": 0.27679404616355896,
      "learning_rate": 1.1921052631578949e-05,
      "loss": 1.8790317535400392,
      "step": 350
    },
    {
      "epoch": 0.04931169098006986,
      "grad_norm": 0.29857176542282104,
      "learning_rate": 1.1657894736842105e-05,
      "loss": 1.8166206359863282,
      "step": 360
    },
    {
      "epoch": 0.05068146017396069,
      "grad_norm": 0.307064950466156,
      "learning_rate": 1.1394736842105265e-05,
      "loss": 1.740498161315918,
      "step": 370
    },
    {
      "epoch": 0.05205122936785152,
      "grad_norm": 0.2849220931529999,
      "learning_rate": 1.1131578947368421e-05,
      "loss": 1.86405029296875,
      "step": 380
    },
    {
      "epoch": 0.053420998561742344,
      "grad_norm": 0.2507258653640747,
      "learning_rate": 1.086842105263158e-05,
      "loss": 1.8203811645507812,
      "step": 390
    },
    {
      "epoch": 0.05479076775563318,
      "grad_norm": 0.32056924700737,
      "learning_rate": 1.0605263157894738e-05,
      "loss": 1.8383829116821289,
      "step": 400
    },
    {
      "epoch": 0.056160536949524005,
      "grad_norm": 0.3862442374229431,
      "learning_rate": 1.0342105263157896e-05,
      "loss": 1.7965122222900392,
      "step": 410
    },
    {
      "epoch": 0.05753030614341483,
      "grad_norm": 0.2158074676990509,
      "learning_rate": 1.0078947368421053e-05,
      "loss": 1.7655912399291993,
      "step": 420
    },
    {
      "epoch": 0.058900075337305666,
      "grad_norm": 0.27215778827667236,
      "learning_rate": 9.815789473684212e-06,
      "loss": 1.7762609481811524,
      "step": 430
    },
    {
      "epoch": 0.06026984453119649,
      "grad_norm": 0.2439756989479065,
      "learning_rate": 9.552631578947369e-06,
      "loss": 1.7678848266601563,
      "step": 440
    },
    {
      "epoch": 0.06163961372508732,
      "grad_norm": 0.3162086009979248,
      "learning_rate": 9.289473684210527e-06,
      "loss": 1.8514827728271483,
      "step": 450
    },
    {
      "epoch": 0.06300938291897815,
      "grad_norm": 0.280586838722229,
      "learning_rate": 9.026315789473685e-06,
      "loss": 1.8047622680664062,
      "step": 460
    },
    {
      "epoch": 0.06437915211286899,
      "grad_norm": 0.22920483350753784,
      "learning_rate": 8.763157894736842e-06,
      "loss": 1.7634853363037108,
      "step": 470
    },
    {
      "epoch": 0.06574892130675981,
      "grad_norm": 0.2582913637161255,
      "learning_rate": 8.5e-06,
      "loss": 1.8084178924560548,
      "step": 480
    },
    {
      "epoch": 0.06711869050065064,
      "grad_norm": 0.22125154733657837,
      "learning_rate": 8.236842105263158e-06,
      "loss": 1.7368389129638673,
      "step": 490
    },
    {
      "epoch": 0.06848845969454147,
      "grad_norm": 0.22868144512176514,
      "learning_rate": 7.973684210526316e-06,
      "loss": 1.7524850845336915,
      "step": 500
    },
    {
      "epoch": 0.0698582288884323,
      "grad_norm": 0.42042723298072815,
      "learning_rate": 7.710526315789474e-06,
      "loss": 1.7123191833496094,
      "step": 510
    },
    {
      "epoch": 0.07122799808232314,
      "grad_norm": 0.2862432599067688,
      "learning_rate": 7.447368421052632e-06,
      "loss": 1.729414939880371,
      "step": 520
    },
    {
      "epoch": 0.07259776727621396,
      "grad_norm": 0.2237967550754547,
      "learning_rate": 7.18421052631579e-06,
      "loss": 1.7572792053222657,
      "step": 530
    },
    {
      "epoch": 0.07396753647010479,
      "grad_norm": 0.2615198493003845,
      "learning_rate": 6.921052631578948e-06,
      "loss": 1.78935546875,
      "step": 540
    },
    {
      "epoch": 0.07533730566399562,
      "grad_norm": 0.215779110789299,
      "learning_rate": 6.6578947368421055e-06,
      "loss": 1.753053855895996,
      "step": 550
    },
    {
      "epoch": 0.07670707485788644,
      "grad_norm": 0.20498128235340118,
      "learning_rate": 6.394736842105264e-06,
      "loss": 1.6631881713867187,
      "step": 560
    },
    {
      "epoch": 0.07807684405177727,
      "grad_norm": 0.216533824801445,
      "learning_rate": 6.131578947368422e-06,
      "loss": 1.7446210861206055,
      "step": 570
    },
    {
      "epoch": 0.07944661324566811,
      "grad_norm": 0.25069892406463623,
      "learning_rate": 5.86842105263158e-06,
      "loss": 1.805841064453125,
      "step": 580
    },
    {
      "epoch": 0.08081638243955894,
      "grad_norm": 0.2501865327358246,
      "learning_rate": 5.605263157894737e-06,
      "loss": 1.7990594863891602,
      "step": 590
    },
    {
      "epoch": 0.08218615163344976,
      "grad_norm": 0.23411990702152252,
      "learning_rate": 5.342105263157895e-06,
      "loss": 1.72657470703125,
      "step": 600
    },
    {
      "epoch": 0.08355592082734059,
      "grad_norm": 0.25468888878822327,
      "learning_rate": 5.078947368421053e-06,
      "loss": 1.6869335174560547,
      "step": 610
    },
    {
      "epoch": 0.08492569002123142,
      "grad_norm": 0.20213402807712555,
      "learning_rate": 4.815789473684211e-06,
      "loss": 1.6238441467285156,
      "step": 620
    },
    {
      "epoch": 0.08629545921512226,
      "grad_norm": 0.22670616209506989,
      "learning_rate": 4.552631578947369e-06,
      "loss": 1.7246341705322266,
      "step": 630
    },
    {
      "epoch": 0.08766522840901309,
      "grad_norm": 0.27973708510398865,
      "learning_rate": 4.289473684210527e-06,
      "loss": 1.7155805587768556,
      "step": 640
    },
    {
      "epoch": 0.08903499760290391,
      "grad_norm": 0.24762506783008575,
      "learning_rate": 4.026315789473684e-06,
      "loss": 1.706759262084961,
      "step": 650
    },
    {
      "epoch": 0.09040476679679474,
      "grad_norm": 0.3544348478317261,
      "learning_rate": 3.7631578947368426e-06,
      "loss": 1.676065444946289,
      "step": 660
    },
    {
      "epoch": 0.09177453599068557,
      "grad_norm": 0.213600754737854,
      "learning_rate": 3.5e-06,
      "loss": 1.7575370788574218,
      "step": 670
    },
    {
      "epoch": 0.09314430518457639,
      "grad_norm": 0.20907212793827057,
      "learning_rate": 3.236842105263158e-06,
      "loss": 1.681616973876953,
      "step": 680
    },
    {
      "epoch": 0.09451407437846723,
      "grad_norm": 0.2494778037071228,
      "learning_rate": 2.973684210526316e-06,
      "loss": 1.7092714309692383,
      "step": 690
    },
    {
      "epoch": 0.09588384357235806,
      "grad_norm": 0.2179274708032608,
      "learning_rate": 2.710526315789474e-06,
      "loss": 1.7354896545410157,
      "step": 700
    },
    {
      "epoch": 0.09725361276624889,
      "grad_norm": 0.24646683037281036,
      "learning_rate": 2.447368421052632e-06,
      "loss": 1.723104476928711,
      "step": 710
    },
    {
      "epoch": 0.09862338196013971,
      "grad_norm": 0.21943680942058563,
      "learning_rate": 2.1842105263157896e-06,
      "loss": 1.8309019088745118,
      "step": 720
    },
    {
      "epoch": 0.09999315115403054,
      "grad_norm": 0.2424953579902649,
      "learning_rate": 1.9210526315789474e-06,
      "loss": 1.703164291381836,
      "step": 730
    },
    {
      "epoch": 0.10136292034792138,
      "grad_norm": 0.2525971531867981,
      "learning_rate": 1.6578947368421053e-06,
      "loss": 1.7882774353027344,
      "step": 740
    },
    {
      "epoch": 0.10273268954181221,
      "grad_norm": 0.2217267006635666,
      "learning_rate": 1.394736842105263e-06,
      "loss": 1.7480182647705078,
      "step": 750
    },
    {
      "epoch": 0.10410245873570304,
      "grad_norm": 0.2686385214328766,
      "learning_rate": 1.1315789473684213e-06,
      "loss": 1.712969970703125,
      "step": 760
    },
    {
      "epoch": 0.10547222792959386,
      "grad_norm": 0.23270924389362335,
      "learning_rate": 8.68421052631579e-07,
      "loss": 1.727523422241211,
      "step": 770
    },
    {
      "epoch": 0.10684199712348469,
      "grad_norm": 0.21745167672634125,
      "learning_rate": 6.052631578947369e-07,
      "loss": 1.7345813751220702,
      "step": 780
    },
    {
      "epoch": 0.10821176631737552,
      "grad_norm": 0.24494187533855438,
      "learning_rate": 3.421052631578948e-07,
      "loss": 1.7722370147705078,
      "step": 790
    },
    {
      "epoch": 0.10958153551126636,
      "grad_norm": 0.19390442967414856,
      "learning_rate": 7.894736842105264e-08,
      "loss": 1.760666275024414,
      "step": 800
    }
  ],
  "logging_steps": 10,
  "max_steps": 800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9111174457838797e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}