{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9956108266276518,
  "eval_steps": 500,
  "global_step": 1023,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029261155815654718,
      "grad_norm": 1.2849662632988823,
      "learning_rate": 5e-06,
      "loss": 0.7988,
      "step": 10
    },
    {
      "epoch": 0.058522311631309436,
      "grad_norm": 1.4199463107396815,
      "learning_rate": 5e-06,
      "loss": 0.7418,
      "step": 20
    },
    {
      "epoch": 0.08778346744696415,
      "grad_norm": 1.2893493708692436,
      "learning_rate": 5e-06,
      "loss": 0.7115,
      "step": 30
    },
    {
      "epoch": 0.11704462326261887,
      "grad_norm": 1.1432331016380537,
      "learning_rate": 5e-06,
      "loss": 0.7017,
      "step": 40
    },
    {
      "epoch": 0.14630577907827358,
      "grad_norm": 1.1990004731837045,
      "learning_rate": 5e-06,
      "loss": 0.6927,
      "step": 50
    },
    {
      "epoch": 0.1755669348939283,
      "grad_norm": 1.0439792841753452,
      "learning_rate": 5e-06,
      "loss": 0.6825,
      "step": 60
    },
    {
      "epoch": 0.20482809070958302,
      "grad_norm": 0.8213062015955013,
      "learning_rate": 5e-06,
      "loss": 0.6749,
      "step": 70
    },
    {
      "epoch": 0.23408924652523774,
      "grad_norm": 0.565278014089242,
      "learning_rate": 5e-06,
      "loss": 0.6679,
      "step": 80
    },
    {
      "epoch": 0.26335040234089246,
      "grad_norm": 0.4143582038233562,
      "learning_rate": 5e-06,
      "loss": 0.6638,
      "step": 90
    },
    {
      "epoch": 0.29261155815654716,
      "grad_norm": 0.35865984273496515,
      "learning_rate": 5e-06,
      "loss": 0.6556,
      "step": 100
    },
    {
      "epoch": 0.3218727139722019,
      "grad_norm": 0.41414344190639485,
      "learning_rate": 5e-06,
      "loss": 0.6642,
      "step": 110
    },
    {
      "epoch": 0.3511338697878566,
      "grad_norm": 0.34647908717327974,
      "learning_rate": 5e-06,
      "loss": 0.6689,
      "step": 120
    },
    {
      "epoch": 0.38039502560351135,
      "grad_norm": 0.36330393207196116,
      "learning_rate": 5e-06,
      "loss": 0.6526,
      "step": 130
    },
    {
      "epoch": 0.40965618141916604,
      "grad_norm": 0.3930489077574971,
      "learning_rate": 5e-06,
      "loss": 0.6533,
      "step": 140
    },
    {
      "epoch": 0.4389173372348208,
      "grad_norm": 0.3495886854477275,
      "learning_rate": 5e-06,
      "loss": 0.6486,
      "step": 150
    },
    {
      "epoch": 0.4681784930504755,
      "grad_norm": 0.3680481244993207,
      "learning_rate": 5e-06,
      "loss": 0.6505,
      "step": 160
    },
    {
      "epoch": 0.49743964886613024,
      "grad_norm": 0.33390637161392955,
      "learning_rate": 5e-06,
      "loss": 0.6555,
      "step": 170
    },
    {
      "epoch": 0.5267008046817849,
      "grad_norm": 0.3746691343413622,
      "learning_rate": 5e-06,
      "loss": 0.6551,
      "step": 180
    },
    {
      "epoch": 0.5559619604974396,
      "grad_norm": 0.3699067808016957,
      "learning_rate": 5e-06,
      "loss": 0.6435,
      "step": 190
    },
    {
      "epoch": 0.5852231163130943,
      "grad_norm": 0.3273208649836799,
      "learning_rate": 5e-06,
      "loss": 0.6447,
      "step": 200
    },
    {
      "epoch": 0.6144842721287491,
      "grad_norm": 0.34866198173958035,
      "learning_rate": 5e-06,
      "loss": 0.6512,
      "step": 210
    },
    {
      "epoch": 0.6437454279444038,
      "grad_norm": 0.3736580548633559,
      "learning_rate": 5e-06,
      "loss": 0.6392,
      "step": 220
    },
    {
      "epoch": 0.6730065837600585,
      "grad_norm": 0.40540717832709844,
      "learning_rate": 5e-06,
      "loss": 0.6391,
      "step": 230
    },
    {
      "epoch": 0.7022677395757132,
      "grad_norm": 0.3585814451014054,
      "learning_rate": 5e-06,
      "loss": 0.646,
      "step": 240
    },
    {
      "epoch": 0.731528895391368,
      "grad_norm": 0.35675567299267796,
      "learning_rate": 5e-06,
      "loss": 0.6443,
      "step": 250
    },
    {
      "epoch": 0.7607900512070227,
      "grad_norm": 0.3373027571596821,
      "learning_rate": 5e-06,
      "loss": 0.6469,
      "step": 260
    },
    {
      "epoch": 0.7900512070226774,
      "grad_norm": 0.3764235288841584,
      "learning_rate": 5e-06,
      "loss": 0.6492,
      "step": 270
    },
    {
      "epoch": 0.8193123628383321,
      "grad_norm": 0.34345099953151875,
      "learning_rate": 5e-06,
      "loss": 0.648,
      "step": 280
    },
    {
      "epoch": 0.8485735186539868,
      "grad_norm": 0.36707918993137767,
      "learning_rate": 5e-06,
      "loss": 0.6402,
      "step": 290
    },
    {
      "epoch": 0.8778346744696416,
      "grad_norm": 0.3366445051962804,
      "learning_rate": 5e-06,
      "loss": 0.632,
      "step": 300
    },
    {
      "epoch": 0.9070958302852963,
      "grad_norm": 0.35479054045825004,
      "learning_rate": 5e-06,
      "loss": 0.6451,
      "step": 310
    },
    {
      "epoch": 0.936356986100951,
      "grad_norm": 0.3598047626988646,
      "learning_rate": 5e-06,
      "loss": 0.637,
      "step": 320
    },
    {
      "epoch": 0.9656181419166057,
      "grad_norm": 0.37200837257756547,
      "learning_rate": 5e-06,
      "loss": 0.6403,
      "step": 330
    },
    {
      "epoch": 0.9948792977322605,
      "grad_norm": 0.371852818867313,
      "learning_rate": 5e-06,
      "loss": 0.6363,
      "step": 340
    },
    {
      "epoch": 0.9978054133138259,
      "eval_loss": 0.6408140063285828,
      "eval_runtime": 343.4861,
      "eval_samples_per_second": 26.81,
      "eval_steps_per_second": 0.419,
      "step": 341
    },
    {
      "epoch": 1.025237746891002,
      "grad_norm": 0.36255101563837305,
      "learning_rate": 5e-06,
      "loss": 0.6518,
      "step": 350
    },
    {
      "epoch": 1.054498902706657,
      "grad_norm": 0.3475892030412215,
      "learning_rate": 5e-06,
      "loss": 0.6058,
      "step": 360
    },
    {
      "epoch": 1.0837600585223117,
      "grad_norm": 0.3513680470415506,
      "learning_rate": 5e-06,
      "loss": 0.6089,
      "step": 370
    },
    {
      "epoch": 1.1130212143379663,
      "grad_norm": 0.3643940293304125,
      "learning_rate": 5e-06,
      "loss": 0.6061,
      "step": 380
    },
    {
      "epoch": 1.142282370153621,
      "grad_norm": 0.3439212708570147,
      "learning_rate": 5e-06,
      "loss": 0.6113,
      "step": 390
    },
    {
      "epoch": 1.1715435259692757,
      "grad_norm": 0.34129141207279823,
      "learning_rate": 5e-06,
      "loss": 0.6127,
      "step": 400
    },
    {
      "epoch": 1.2008046817849305,
      "grad_norm": 0.3701906862300866,
      "learning_rate": 5e-06,
      "loss": 0.6123,
      "step": 410
    },
    {
      "epoch": 1.2300658376005853,
      "grad_norm": 0.33560999336131986,
      "learning_rate": 5e-06,
      "loss": 0.6004,
      "step": 420
    },
    {
      "epoch": 1.2593269934162399,
      "grad_norm": 0.3324858147295424,
      "learning_rate": 5e-06,
      "loss": 0.6106,
      "step": 430
    },
    {
      "epoch": 1.2885881492318947,
      "grad_norm": 0.37518367781371437,
      "learning_rate": 5e-06,
      "loss": 0.6032,
      "step": 440
    },
    {
      "epoch": 1.3178493050475493,
      "grad_norm": 0.356849680993594,
      "learning_rate": 5e-06,
      "loss": 0.607,
      "step": 450
    },
    {
      "epoch": 1.347110460863204,
      "grad_norm": 0.3348178275863291,
      "learning_rate": 5e-06,
      "loss": 0.6047,
      "step": 460
    },
    {
      "epoch": 1.3763716166788589,
      "grad_norm": 0.36740445119696036,
      "learning_rate": 5e-06,
      "loss": 0.602,
      "step": 470
    },
    {
      "epoch": 1.4056327724945135,
      "grad_norm": 0.34440860689908115,
      "learning_rate": 5e-06,
      "loss": 0.603,
      "step": 480
    },
    {
      "epoch": 1.4348939283101683,
      "grad_norm": 0.3551953801924753,
      "learning_rate": 5e-06,
      "loss": 0.6093,
      "step": 490
    },
    {
      "epoch": 1.464155084125823,
      "grad_norm": 0.3381321427625204,
      "learning_rate": 5e-06,
      "loss": 0.5977,
      "step": 500
    },
    {
      "epoch": 1.4934162399414777,
      "grad_norm": 0.38540487853406197,
      "learning_rate": 5e-06,
      "loss": 0.6057,
      "step": 510
    },
    {
      "epoch": 1.5226773957571325,
      "grad_norm": 0.3483825303213825,
      "learning_rate": 5e-06,
      "loss": 0.608,
      "step": 520
    },
    {
      "epoch": 1.5519385515727873,
      "grad_norm": 0.35515838107699704,
      "learning_rate": 5e-06,
      "loss": 0.6067,
      "step": 530
    },
    {
      "epoch": 1.5811997073884418,
      "grad_norm": 0.34459660393892144,
      "learning_rate": 5e-06,
      "loss": 0.6133,
      "step": 540
    },
    {
      "epoch": 1.6104608632040964,
      "grad_norm": 0.39497339870445597,
      "learning_rate": 5e-06,
      "loss": 0.6043,
      "step": 550
    },
    {
      "epoch": 1.6397220190197512,
      "grad_norm": 0.3694243636377289,
      "learning_rate": 5e-06,
      "loss": 0.606,
      "step": 560
    },
    {
      "epoch": 1.668983174835406,
      "grad_norm": 0.3590726039118861,
      "learning_rate": 5e-06,
      "loss": 0.5967,
      "step": 570
    },
    {
      "epoch": 1.6982443306510606,
      "grad_norm": 0.36869766166579304,
      "learning_rate": 5e-06,
      "loss": 0.6059,
      "step": 580
    },
    {
      "epoch": 1.7275054864667154,
      "grad_norm": 0.34392878240140984,
      "learning_rate": 5e-06,
      "loss": 0.6062,
      "step": 590
    },
    {
      "epoch": 1.7567666422823702,
      "grad_norm": 0.3593709100296028,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 600
    },
    {
      "epoch": 1.7860277980980248,
      "grad_norm": 0.373155357664091,
      "learning_rate": 5e-06,
      "loss": 0.6055,
      "step": 610
    },
    {
      "epoch": 1.8152889539136796,
      "grad_norm": 0.3166663124348639,
      "learning_rate": 5e-06,
      "loss": 0.6059,
      "step": 620
    },
    {
      "epoch": 1.8445501097293344,
      "grad_norm": 0.34060892919546276,
      "learning_rate": 5e-06,
      "loss": 0.6051,
      "step": 630
    },
    {
      "epoch": 1.873811265544989,
      "grad_norm": 0.35734395039827416,
      "learning_rate": 5e-06,
      "loss": 0.6,
      "step": 640
    },
    {
      "epoch": 1.9030724213606436,
      "grad_norm": 0.3552215902079519,
      "learning_rate": 5e-06,
      "loss": 0.6056,
      "step": 650
    },
    {
      "epoch": 1.9323335771762986,
      "grad_norm": 0.3967283225312103,
      "learning_rate": 5e-06,
      "loss": 0.606,
      "step": 660
    },
    {
      "epoch": 1.9615947329919532,
      "grad_norm": 0.3690561992266286,
      "learning_rate": 5e-06,
      "loss": 0.595,
      "step": 670
    },
    {
      "epoch": 1.9908558888076078,
      "grad_norm": 0.34197318903675017,
      "learning_rate": 5e-06,
      "loss": 0.6094,
      "step": 680
    },
    {
      "epoch": 1.9967081199707388,
      "eval_loss": 0.6333937644958496,
      "eval_runtime": 346.0759,
      "eval_samples_per_second": 26.61,
      "eval_steps_per_second": 0.416,
      "step": 682
    },
    {
      "epoch": 2.0212143379663496,
      "grad_norm": 0.3577786823104312,
      "learning_rate": 5e-06,
      "loss": 0.6198,
      "step": 690
    },
    {
      "epoch": 2.050475493782004,
      "grad_norm": 0.36976857212352937,
      "learning_rate": 5e-06,
      "loss": 0.5674,
      "step": 700
    },
    {
      "epoch": 2.0797366495976592,
      "grad_norm": 0.4219661366755331,
      "learning_rate": 5e-06,
      "loss": 0.5693,
      "step": 710
    },
    {
      "epoch": 2.108997805413314,
      "grad_norm": 0.36454526563021306,
      "learning_rate": 5e-06,
      "loss": 0.5701,
      "step": 720
    },
    {
      "epoch": 2.1382589612289684,
      "grad_norm": 0.3300103071186534,
      "learning_rate": 5e-06,
      "loss": 0.5718,
      "step": 730
    },
    {
      "epoch": 2.1675201170446234,
      "grad_norm": 0.3431131606438523,
      "learning_rate": 5e-06,
      "loss": 0.5769,
      "step": 740
    },
    {
      "epoch": 2.196781272860278,
      "grad_norm": 0.3404115803112155,
      "learning_rate": 5e-06,
      "loss": 0.5755,
      "step": 750
    },
    {
      "epoch": 2.2260424286759326,
      "grad_norm": 0.34777766479167094,
      "learning_rate": 5e-06,
      "loss": 0.573,
      "step": 760
    },
    {
      "epoch": 2.255303584491587,
      "grad_norm": 0.36637338725930035,
      "learning_rate": 5e-06,
      "loss": 0.5718,
      "step": 770
    },
    {
      "epoch": 2.284564740307242,
      "grad_norm": 0.3401127006615752,
      "learning_rate": 5e-06,
      "loss": 0.5709,
      "step": 780
    },
    {
      "epoch": 2.313825896122897,
      "grad_norm": 0.3211399255469285,
      "learning_rate": 5e-06,
      "loss": 0.5691,
      "step": 790
    },
    {
      "epoch": 2.3430870519385514,
      "grad_norm": 0.35241422018081425,
      "learning_rate": 5e-06,
      "loss": 0.577,
      "step": 800
    },
    {
      "epoch": 2.3723482077542064,
      "grad_norm": 0.35952705840489485,
      "learning_rate": 5e-06,
      "loss": 0.5722,
      "step": 810
    },
    {
      "epoch": 2.401609363569861,
      "grad_norm": 0.3672156927197908,
      "learning_rate": 5e-06,
      "loss": 0.5785,
      "step": 820
    },
    {
      "epoch": 2.4308705193855156,
      "grad_norm": 0.3440442351776407,
      "learning_rate": 5e-06,
      "loss": 0.5708,
      "step": 830
    },
    {
      "epoch": 2.4601316752011706,
      "grad_norm": 0.3898825767349183,
      "learning_rate": 5e-06,
      "loss": 0.5713,
      "step": 840
    },
    {
      "epoch": 2.489392831016825,
      "grad_norm": 0.33974809017708146,
      "learning_rate": 5e-06,
      "loss": 0.5735,
      "step": 850
    },
    {
      "epoch": 2.5186539868324798,
      "grad_norm": 0.34544839564054625,
      "learning_rate": 5e-06,
      "loss": 0.5666,
      "step": 860
    },
    {
      "epoch": 2.547915142648135,
      "grad_norm": 0.34797797241183964,
      "learning_rate": 5e-06,
      "loss": 0.569,
      "step": 870
    },
    {
      "epoch": 2.5771762984637894,
      "grad_norm": 0.31568311093902707,
      "learning_rate": 5e-06,
      "loss": 0.5732,
      "step": 880
    },
    {
      "epoch": 2.606437454279444,
      "grad_norm": 0.33074448431377707,
      "learning_rate": 5e-06,
      "loss": 0.5725,
      "step": 890
    },
    {
      "epoch": 2.6356986100950985,
      "grad_norm": 0.36479016023024724,
      "learning_rate": 5e-06,
      "loss": 0.5772,
      "step": 900
    },
    {
      "epoch": 2.6649597659107536,
      "grad_norm": 0.3411183732214701,
      "learning_rate": 5e-06,
      "loss": 0.5773,
      "step": 910
    },
    {
      "epoch": 2.694220921726408,
      "grad_norm": 0.35602615152768385,
      "learning_rate": 5e-06,
      "loss": 0.5717,
      "step": 920
    },
    {
      "epoch": 2.723482077542063,
      "grad_norm": 0.3343091577258783,
      "learning_rate": 5e-06,
      "loss": 0.5753,
      "step": 930
    },
    {
      "epoch": 2.7527432333577178,
      "grad_norm": 0.36283018567795616,
      "learning_rate": 5e-06,
      "loss": 0.5744,
      "step": 940
    },
    {
      "epoch": 2.7820043891733723,
      "grad_norm": 0.33758581649097497,
      "learning_rate": 5e-06,
      "loss": 0.5731,
      "step": 950
    },
    {
      "epoch": 2.811265544989027,
      "grad_norm": 0.35138966444340514,
      "learning_rate": 5e-06,
      "loss": 0.5769,
      "step": 960
    },
    {
      "epoch": 2.840526700804682,
      "grad_norm": 0.3607307569058118,
      "learning_rate": 5e-06,
      "loss": 0.5726,
      "step": 970
    },
    {
      "epoch": 2.8697878566203365,
      "grad_norm": 0.32691912748118096,
      "learning_rate": 5e-06,
      "loss": 0.5724,
      "step": 980
    },
    {
      "epoch": 2.899049012435991,
      "grad_norm": 0.3350658303015224,
      "learning_rate": 5e-06,
      "loss": 0.5655,
      "step": 990
    },
    {
      "epoch": 2.928310168251646,
      "grad_norm": 0.338209529060621,
      "learning_rate": 5e-06,
      "loss": 0.5732,
      "step": 1000
    },
    {
      "epoch": 2.9575713240673007,
      "grad_norm": 0.32707318222579257,
      "learning_rate": 5e-06,
      "loss": 0.565,
      "step": 1010
    },
    {
      "epoch": 2.9868324798829553,
      "grad_norm": 0.3314799253075643,
      "learning_rate": 5e-06,
      "loss": 0.5767,
      "step": 1020
    },
    {
      "epoch": 2.9956108266276518,
      "eval_loss": 0.633789598941803,
      "eval_runtime": 346.7482,
      "eval_samples_per_second": 26.558,
      "eval_steps_per_second": 0.415,
      "step": 1023
    },
    {
      "epoch": 2.9956108266276518,
      "step": 1023,
      "total_flos": 2144987064041472.0,
      "train_loss": 0.6143466530191117,
      "train_runtime": 55059.5078,
      "train_samples_per_second": 9.533,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 10,
  "max_steps": 1023,
  "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": 2144987064041472.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}