{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4537205081669691,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004537205081669692,
      "grad_norm": 1.4140625,
      "learning_rate": 1.7632653061224493e-05,
      "loss": 2.0708,
      "step": 5
    },
    {
      "epoch": 0.009074410163339383,
      "grad_norm": 1.1796875,
      "learning_rate": 3.96734693877551e-05,
      "loss": 1.9893,
      "step": 10
    },
    {
      "epoch": 0.013611615245009074,
      "grad_norm": 0.85546875,
      "learning_rate": 6.171428571428573e-05,
      "loss": 1.955,
      "step": 15
    },
    {
      "epoch": 0.018148820326678767,
      "grad_norm": 1.0,
      "learning_rate": 8.375510204081634e-05,
      "loss": 1.9002,
      "step": 20
    },
    {
      "epoch": 0.022686025408348458,
      "grad_norm": 0.78515625,
      "learning_rate": 0.00010579591836734696,
      "loss": 1.8666,
      "step": 25
    },
    {
      "epoch": 0.02722323049001815,
      "grad_norm": 0.71875,
      "learning_rate": 0.00012783673469387758,
      "loss": 1.9462,
      "step": 30
    },
    {
      "epoch": 0.03176043557168784,
      "grad_norm": 0.734375,
      "learning_rate": 0.00014987755102040818,
      "loss": 1.9157,
      "step": 35
    },
    {
      "epoch": 0.036297640653357534,
      "grad_norm": 0.703125,
      "learning_rate": 0.00015428528732777552,
      "loss": 1.9,
      "step": 40
    },
    {
      "epoch": 0.04083484573502722,
      "grad_norm": 0.7265625,
      "learning_rate": 0.00015428355282194904,
      "loss": 1.9086,
      "step": 45
    },
    {
      "epoch": 0.045372050816696916,
      "grad_norm": 0.69921875,
      "learning_rate": 0.00015428048412333237,
      "loss": 1.918,
      "step": 50
    },
    {
      "epoch": 0.0499092558983666,
      "grad_norm": 0.6484375,
      "learning_rate": 0.00015427608130269275,
      "loss": 1.8871,
      "step": 55
    },
    {
      "epoch": 0.0544464609800363,
      "grad_norm": 0.66015625,
      "learning_rate": 0.00015427034446156347,
      "loss": 1.879,
      "step": 60
    },
    {
      "epoch": 0.05898366606170599,
      "grad_norm": 0.6484375,
      "learning_rate": 0.00015426327373224179,
      "loss": 1.8881,
      "step": 65
    },
    {
      "epoch": 0.06352087114337568,
      "grad_norm": 0.69921875,
      "learning_rate": 0.00015425486927778568,
      "loss": 1.8637,
      "step": 70
    },
    {
      "epoch": 0.06805807622504537,
      "grad_norm": 0.66796875,
      "learning_rate": 0.0001542451312920101,
      "loss": 1.9391,
      "step": 75
    },
    {
      "epoch": 0.07259528130671507,
      "grad_norm": 0.65234375,
      "learning_rate": 0.0001542340599994826,
      "loss": 1.9262,
      "step": 80
    },
    {
      "epoch": 0.07713248638838476,
      "grad_norm": 0.6171875,
      "learning_rate": 0.0001542216556555181,
      "loss": 1.9177,
      "step": 85
    },
    {
      "epoch": 0.08166969147005444,
      "grad_norm": 0.66015625,
      "learning_rate": 0.00015420791854617294,
      "loss": 1.9026,
      "step": 90
    },
    {
      "epoch": 0.08620689655172414,
      "grad_norm": 0.69140625,
      "learning_rate": 0.0001541928489882384,
      "loss": 1.868,
      "step": 95
    },
    {
      "epoch": 0.09074410163339383,
      "grad_norm": 0.62890625,
      "learning_rate": 0.0001541764473292333,
      "loss": 1.8556,
      "step": 100
    },
    {
      "epoch": 0.09528130671506352,
      "grad_norm": 0.69921875,
      "learning_rate": 0.00015415871394739605,
      "loss": 1.8941,
      "step": 105
    },
    {
      "epoch": 0.0998185117967332,
      "grad_norm": 0.6640625,
      "learning_rate": 0.00015413964925167585,
      "loss": 1.8843,
      "step": 110
    },
    {
      "epoch": 0.10435571687840291,
      "grad_norm": 0.609375,
      "learning_rate": 0.00015411925368172337,
      "loss": 1.8913,
      "step": 115
    },
    {
      "epoch": 0.1088929219600726,
      "grad_norm": 0.60546875,
      "learning_rate": 0.0001540975277078805,
      "loss": 1.8362,
      "step": 120
    },
    {
      "epoch": 0.11343012704174228,
      "grad_norm": 0.62109375,
      "learning_rate": 0.0001540744718311696,
      "loss": 1.851,
      "step": 125
    },
    {
      "epoch": 0.11796733212341198,
      "grad_norm": 0.671875,
      "learning_rate": 0.00015405008658328184,
      "loss": 1.8704,
      "step": 130
    },
    {
      "epoch": 0.12250453720508167,
      "grad_norm": 0.640625,
      "learning_rate": 0.000154024372526565,
      "loss": 1.8304,
      "step": 135
    },
    {
      "epoch": 0.12704174228675136,
      "grad_norm": 0.609375,
      "learning_rate": 0.0001539973302540106,
      "loss": 1.8121,
      "step": 140
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 0.66015625,
      "learning_rate": 0.00015396896038924,
      "loss": 1.861,
      "step": 145
    },
    {
      "epoch": 0.13611615245009073,
      "grad_norm": 0.96484375,
      "learning_rate": 0.0001539392635864902,
      "loss": 1.858,
      "step": 150
    },
    {
      "epoch": 0.14065335753176045,
      "grad_norm": 0.6328125,
      "learning_rate": 0.00015390824053059868,
      "loss": 1.8305,
      "step": 155
    },
    {
      "epoch": 0.14519056261343014,
      "grad_norm": 0.61328125,
      "learning_rate": 0.00015387589193698766,
      "loss": 1.8998,
      "step": 160
    },
    {
      "epoch": 0.14972776769509982,
      "grad_norm": 0.921875,
      "learning_rate": 0.00015384221855164752,
      "loss": 1.8725,
      "step": 165
    },
    {
      "epoch": 0.1542649727767695,
      "grad_norm": 0.59375,
      "learning_rate": 0.00015380722115111966,
      "loss": 1.8505,
      "step": 170
    },
    {
      "epoch": 0.1588021778584392,
      "grad_norm": 0.62109375,
      "learning_rate": 0.00015377090054247852,
      "loss": 1.8817,
      "step": 175
    },
    {
      "epoch": 0.16333938294010888,
      "grad_norm": 0.59765625,
      "learning_rate": 0.00015373325756331313,
      "loss": 1.8494,
      "step": 180
    },
    {
      "epoch": 0.16787658802177857,
      "grad_norm": 0.61328125,
      "learning_rate": 0.00015369429308170762,
      "loss": 1.9201,
      "step": 185
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 0.609375,
      "learning_rate": 0.00015365400799622123,
      "loss": 1.8467,
      "step": 190
    },
    {
      "epoch": 0.17695099818511797,
      "grad_norm": 0.703125,
      "learning_rate": 0.00015361240323586768,
      "loss": 1.8867,
      "step": 195
    },
    {
      "epoch": 0.18148820326678766,
      "grad_norm": 0.60546875,
      "learning_rate": 0.00015356947976009368,
      "loss": 1.8469,
      "step": 200
    },
    {
      "epoch": 0.18602540834845735,
      "grad_norm": 0.703125,
      "learning_rate": 0.00015352523855875685,
      "loss": 1.8678,
      "step": 205
    },
    {
      "epoch": 0.19056261343012704,
      "grad_norm": 0.6171875,
      "learning_rate": 0.00015347968065210273,
      "loss": 1.8783,
      "step": 210
    },
    {
      "epoch": 0.19509981851179672,
      "grad_norm": 0.55859375,
      "learning_rate": 0.00015343280709074155,
      "loss": 1.8663,
      "step": 215
    },
    {
      "epoch": 0.1996370235934664,
      "grad_norm": 0.6328125,
      "learning_rate": 0.0001533846189556237,
      "loss": 1.8891,
      "step": 220
    },
    {
      "epoch": 0.20417422867513613,
      "grad_norm": 0.55859375,
      "learning_rate": 0.000153335117358015,
      "loss": 1.87,
      "step": 225
    },
    {
      "epoch": 0.20871143375680581,
      "grad_norm": 0.6015625,
      "learning_rate": 0.00015328430343947104,
      "loss": 1.7773,
      "step": 230
    },
    {
      "epoch": 0.2132486388384755,
      "grad_norm": 0.58203125,
      "learning_rate": 0.00015323217837181068,
      "loss": 1.8276,
      "step": 235
    },
    {
      "epoch": 0.2177858439201452,
      "grad_norm": 0.55078125,
      "learning_rate": 0.00015317874335708936,
      "loss": 1.8301,
      "step": 240
    },
    {
      "epoch": 0.22232304900181488,
      "grad_norm": 0.5859375,
      "learning_rate": 0.00015312399962757098,
      "loss": 1.8491,
      "step": 245
    },
    {
      "epoch": 0.22686025408348456,
      "grad_norm": 0.5703125,
      "learning_rate": 0.0001530679484456999,
      "loss": 1.8976,
      "step": 250
    },
    {
      "epoch": 0.23139745916515425,
      "grad_norm": 0.57421875,
      "learning_rate": 0.00015301059110407148,
      "loss": 1.7919,
      "step": 255
    },
    {
      "epoch": 0.23593466424682397,
      "grad_norm": 0.578125,
      "learning_rate": 0.00015295192892540244,
      "loss": 1.8364,
      "step": 260
    },
    {
      "epoch": 0.24047186932849365,
      "grad_norm": 0.6640625,
      "learning_rate": 0.00015289196326250036,
      "loss": 1.846,
      "step": 265
    },
    {
      "epoch": 0.24500907441016334,
      "grad_norm": 0.58203125,
      "learning_rate": 0.00015283069549823237,
      "loss": 1.8033,
      "step": 270
    },
    {
      "epoch": 0.24954627949183303,
      "grad_norm": 0.609375,
      "learning_rate": 0.00015276812704549347,
      "loss": 1.8463,
      "step": 275
    },
    {
      "epoch": 0.2540834845735027,
      "grad_norm": 0.5703125,
      "learning_rate": 0.00015270425934717368,
      "loss": 1.7821,
      "step": 280
    },
    {
      "epoch": 0.25862068965517243,
      "grad_norm": 0.59765625,
      "learning_rate": 0.00015263909387612496,
      "loss": 1.7916,
      "step": 285
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.671875,
      "learning_rate": 0.0001525726321351272,
      "loss": 1.8298,
      "step": 290
    },
    {
      "epoch": 0.2676950998185118,
      "grad_norm": 0.5078125,
      "learning_rate": 0.00015250487565685353,
      "loss": 1.8417,
      "step": 295
    },
    {
      "epoch": 0.27223230490018147,
      "grad_norm": 0.5703125,
      "learning_rate": 0.000152435826003835,
      "loss": 1.8475,
      "step": 300
    },
    {
      "epoch": 0.2767695099818512,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00015236548476842452,
      "loss": 1.7997,
      "step": 305
    },
    {
      "epoch": 0.2813067150635209,
      "grad_norm": 0.6640625,
      "learning_rate": 0.00015229385357276023,
      "loss": 1.8284,
      "step": 310
    },
    {
      "epoch": 0.28584392014519056,
      "grad_norm": 0.56640625,
      "learning_rate": 0.00015222093406872794,
      "loss": 1.8628,
      "step": 315
    },
    {
      "epoch": 0.29038112522686027,
      "grad_norm": 0.5703125,
      "learning_rate": 0.00015214672793792313,
      "loss": 1.8286,
      "step": 320
    },
    {
      "epoch": 0.29491833030852993,
      "grad_norm": 0.53125,
      "learning_rate": 0.00015207123689161224,
      "loss": 1.8207,
      "step": 325
    },
    {
      "epoch": 0.29945553539019965,
      "grad_norm": 0.74609375,
      "learning_rate": 0.00015199446267069304,
      "loss": 1.8005,
      "step": 330
    },
    {
      "epoch": 0.3039927404718693,
      "grad_norm": 0.58984375,
      "learning_rate": 0.0001519164070456546,
      "loss": 1.8659,
      "step": 335
    },
    {
      "epoch": 0.308529945553539,
      "grad_norm": 0.58984375,
      "learning_rate": 0.00015183707181653643,
      "loss": 1.8642,
      "step": 340
    },
    {
      "epoch": 0.31306715063520874,
      "grad_norm": 0.6015625,
      "learning_rate": 0.00015175645881288695,
      "loss": 1.7679,
      "step": 345
    },
    {
      "epoch": 0.3176043557168784,
      "grad_norm": 0.60546875,
      "learning_rate": 0.00015167456989372132,
      "loss": 1.8267,
      "step": 350
    },
    {
      "epoch": 0.3221415607985481,
      "grad_norm": 0.55859375,
      "learning_rate": 0.00015159140694747864,
      "loss": 1.826,
      "step": 355
    },
    {
      "epoch": 0.32667876588021777,
      "grad_norm": 0.6328125,
      "learning_rate": 0.0001515069718919782,
      "loss": 1.8233,
      "step": 360
    },
    {
      "epoch": 0.3312159709618875,
      "grad_norm": 0.51171875,
      "learning_rate": 0.0001514212666743755,
      "loss": 1.8402,
      "step": 365
    },
    {
      "epoch": 0.33575317604355714,
      "grad_norm": 0.52734375,
      "learning_rate": 0.00015133429327111715,
      "loss": 1.8067,
      "step": 370
    },
    {
      "epoch": 0.34029038112522686,
      "grad_norm": 0.5234375,
      "learning_rate": 0.00015124605368789542,
      "loss": 1.7867,
      "step": 375
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.546875,
      "learning_rate": 0.00015115654995960187,
      "loss": 1.8151,
      "step": 380
    },
    {
      "epoch": 0.34936479128856623,
      "grad_norm": 0.58984375,
      "learning_rate": 0.00015106578415028057,
      "loss": 1.7844,
      "step": 385
    },
    {
      "epoch": 0.35390199637023595,
      "grad_norm": 0.5625,
      "learning_rate": 0.00015097375835308036,
      "loss": 1.818,
      "step": 390
    },
    {
      "epoch": 0.3584392014519056,
      "grad_norm": 0.60546875,
      "learning_rate": 0.00015088047469020668,
      "loss": 1.8075,
      "step": 395
    },
    {
      "epoch": 0.3629764065335753,
      "grad_norm": 0.56640625,
      "learning_rate": 0.00015078593531287252,
      "loss": 1.8531,
      "step": 400
    },
    {
      "epoch": 0.367513611615245,
      "grad_norm": 0.73828125,
      "learning_rate": 0.00015069014240124903,
      "loss": 1.7792,
      "step": 405
    },
    {
      "epoch": 0.3720508166969147,
      "grad_norm": 0.546875,
      "learning_rate": 0.0001505930981644149,
      "loss": 1.8016,
      "step": 410
    },
    {
      "epoch": 0.3765880217785844,
      "grad_norm": 0.55859375,
      "learning_rate": 0.00015049480484030574,
      "loss": 1.7925,
      "step": 415
    },
    {
      "epoch": 0.3811252268602541,
      "grad_norm": 0.609375,
      "learning_rate": 0.0001503952646956623,
      "loss": 1.7902,
      "step": 420
    },
    {
      "epoch": 0.3856624319419238,
      "grad_norm": 0.55078125,
      "learning_rate": 0.00015029448002597828,
      "loss": 1.785,
      "step": 425
    },
    {
      "epoch": 0.39019963702359345,
      "grad_norm": 0.54296875,
      "learning_rate": 0.00015019245315544728,
      "loss": 1.8234,
      "step": 430
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 0.56640625,
      "learning_rate": 0.00015008918643690932,
      "loss": 1.7869,
      "step": 435
    },
    {
      "epoch": 0.3992740471869328,
      "grad_norm": 0.5703125,
      "learning_rate": 0.00014998468225179657,
      "loss": 1.8319,
      "step": 440
    },
    {
      "epoch": 0.40381125226860254,
      "grad_norm": 0.54296875,
      "learning_rate": 0.00014987894301007825,
      "loss": 1.7935,
      "step": 445
    },
    {
      "epoch": 0.40834845735027225,
      "grad_norm": 0.55859375,
      "learning_rate": 0.0001497719711502054,
      "loss": 1.7998,
      "step": 450
    },
    {
      "epoch": 0.4128856624319419,
      "grad_norm": 0.578125,
      "learning_rate": 0.0001496637691390543,
      "loss": 1.8234,
      "step": 455
    },
    {
      "epoch": 0.41742286751361163,
      "grad_norm": 1.40625,
      "learning_rate": 0.00014955433947186982,
      "loss": 1.7724,
      "step": 460
    },
    {
      "epoch": 0.4219600725952813,
      "grad_norm": 0.56640625,
      "learning_rate": 0.0001494436846722077,
      "loss": 1.7939,
      "step": 465
    },
    {
      "epoch": 0.426497277676951,
      "grad_norm": 0.55859375,
      "learning_rate": 0.00014933180729187652,
      "loss": 1.7921,
      "step": 470
    },
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 0.5390625,
      "learning_rate": 0.0001492187099108787,
      "loss": 1.8269,
      "step": 475
    },
    {
      "epoch": 0.4355716878402904,
      "grad_norm": 0.55078125,
      "learning_rate": 0.00014910439513735114,
      "loss": 1.8065,
      "step": 480
    },
    {
      "epoch": 0.4401088929219601,
      "grad_norm": 0.59765625,
      "learning_rate": 0.00014898886560750502,
      "loss": 1.793,
      "step": 485
    },
    {
      "epoch": 0.44464609800362975,
      "grad_norm": 0.5859375,
      "learning_rate": 0.00014887212398556488,
      "loss": 1.8052,
      "step": 490
    },
    {
      "epoch": 0.44918330308529947,
      "grad_norm": 0.5625,
      "learning_rate": 0.00014875417296370742,
      "loss": 1.7471,
      "step": 495
    },
    {
      "epoch": 0.4537205081669691,
      "grad_norm": 0.55078125,
      "learning_rate": 0.00014863501526199925,
      "loss": 1.7734,
      "step": 500
    },
    {
      "epoch": 0.4537205081669691,
      "eval_loss": 1.7299695014953613,
      "eval_runtime": 4.0995,
      "eval_samples_per_second": 15.612,
      "eval_steps_per_second": 15.612,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 3306,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.097833201532928e+18,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}