{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 3895,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012836970474967908,
      "grad_norm": 9.613142967224121,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 41.77240234375,
      "step": 50
    },
    {
      "epoch": 0.025673940949935817,
      "grad_norm": 12.086573600769043,
      "learning_rate": 9.900000000000002e-06,
      "loss": 41.345263671875,
      "step": 100
    },
    {
      "epoch": 0.038510911424903725,
      "grad_norm": 15.577580451965332,
      "learning_rate": 1.49e-05,
      "loss": 39.77162353515625,
      "step": 150
    },
    {
      "epoch": 0.051347881899871634,
      "grad_norm": 16.892032623291016,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 36.19188232421875,
      "step": 200
    },
    {
      "epoch": 0.06418485237483953,
      "grad_norm": 14.969869613647461,
      "learning_rate": 2.4900000000000002e-05,
      "loss": 29.95966552734375,
      "step": 250
    },
    {
      "epoch": 0.07702182284980745,
      "grad_norm": 13.74810791015625,
      "learning_rate": 2.9900000000000002e-05,
      "loss": 20.95840576171875,
      "step": 300
    },
    {
      "epoch": 0.08985879332477535,
      "grad_norm": 1.4417412281036377,
      "learning_rate": 3.49e-05,
      "loss": 8.538499755859375,
      "step": 350
    },
    {
      "epoch": 0.10269576379974327,
      "grad_norm": 0.6216239929199219,
      "learning_rate": 3.99e-05,
      "loss": 4.5771658325195315,
      "step": 400
    },
    {
      "epoch": 0.11553273427471117,
      "grad_norm": 0.9508069753646851,
      "learning_rate": 4.49e-05,
      "loss": 3.7787127685546875,
      "step": 450
    },
    {
      "epoch": 0.12836970474967907,
      "grad_norm": 0.7577052116394043,
      "learning_rate": 4.99e-05,
      "loss": 2.3774658203125,
      "step": 500
    },
    {
      "epoch": 0.14120667522464697,
      "grad_norm": 0.5324252843856812,
      "learning_rate": 5.4900000000000006e-05,
      "loss": 1.3881097412109376,
      "step": 550
    },
    {
      "epoch": 0.1540436456996149,
      "grad_norm": 0.2926165461540222,
      "learning_rate": 5.99e-05,
      "loss": 0.9267782592773437,
      "step": 600
    },
    {
      "epoch": 0.1668806161745828,
      "grad_norm": 0.22473636269569397,
      "learning_rate": 6.49e-05,
      "loss": 0.7232732391357422,
      "step": 650
    },
    {
      "epoch": 0.1797175866495507,
      "grad_norm": 0.2170993536710739,
      "learning_rate": 6.99e-05,
      "loss": 0.618229866027832,
      "step": 700
    },
    {
      "epoch": 0.1925545571245186,
      "grad_norm": 0.1855248361825943,
      "learning_rate": 7.49e-05,
      "loss": 0.55061279296875,
      "step": 750
    },
    {
      "epoch": 0.20539152759948653,
      "grad_norm": 0.21753183007240295,
      "learning_rate": 7.99e-05,
      "loss": 0.5079140853881836,
      "step": 800
    },
    {
      "epoch": 0.21822849807445444,
      "grad_norm": 0.19918011128902435,
      "learning_rate": 8.49e-05,
      "loss": 0.4798870849609375,
      "step": 850
    },
    {
      "epoch": 0.23106546854942234,
      "grad_norm": 0.14776983857154846,
      "learning_rate": 8.99e-05,
      "loss": 0.455287971496582,
      "step": 900
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.18482066690921783,
      "learning_rate": 9.49e-05,
      "loss": 0.43446586608886717,
      "step": 950
    },
    {
      "epoch": 0.25673940949935814,
      "grad_norm": 0.11275222152471542,
      "learning_rate": 9.99e-05,
      "loss": 0.41681861877441406,
      "step": 1000
    },
    {
      "epoch": 0.26957637997432604,
      "grad_norm": 0.12698912620544434,
      "learning_rate": 9.830742659758204e-05,
      "loss": 0.39793609619140624,
      "step": 1050
    },
    {
      "epoch": 0.28241335044929394,
      "grad_norm": 0.10060737282037735,
      "learning_rate": 9.658031088082901e-05,
      "loss": 0.38213893890380857,
      "step": 1100
    },
    {
      "epoch": 0.2952503209242619,
      "grad_norm": 0.15134458243846893,
      "learning_rate": 9.4853195164076e-05,
      "loss": 0.37621440887451174,
      "step": 1150
    },
    {
      "epoch": 0.3080872913992298,
      "grad_norm": 0.1552213877439499,
      "learning_rate": 9.312607944732298e-05,
      "loss": 0.3793338394165039,
      "step": 1200
    },
    {
      "epoch": 0.3209242618741977,
      "grad_norm": 0.09579262137413025,
      "learning_rate": 9.139896373056995e-05,
      "loss": 0.37672374725341795,
      "step": 1250
    },
    {
      "epoch": 0.3337612323491656,
      "grad_norm": 0.09922993928194046,
      "learning_rate": 8.967184801381693e-05,
      "loss": 0.3724240493774414,
      "step": 1300
    },
    {
      "epoch": 0.3465982028241335,
      "grad_norm": 0.18115203082561493,
      "learning_rate": 8.79447322970639e-05,
      "loss": 0.36812400817871094,
      "step": 1350
    },
    {
      "epoch": 0.3594351732991014,
      "grad_norm": 0.2976175844669342,
      "learning_rate": 8.621761658031089e-05,
      "loss": 0.36315170288085935,
      "step": 1400
    },
    {
      "epoch": 0.3722721437740693,
      "grad_norm": 0.09647338092327118,
      "learning_rate": 8.449050086355786e-05,
      "loss": 0.36435611724853517,
      "step": 1450
    },
    {
      "epoch": 0.3851091142490372,
      "grad_norm": 0.35241127014160156,
      "learning_rate": 8.276338514680484e-05,
      "loss": 0.37430931091308595,
      "step": 1500
    },
    {
      "epoch": 0.3979460847240051,
      "grad_norm": 0.22899076342582703,
      "learning_rate": 8.103626943005181e-05,
      "loss": 0.371390266418457,
      "step": 1550
    },
    {
      "epoch": 0.41078305519897307,
      "grad_norm": 0.11063692718744278,
      "learning_rate": 7.930915371329879e-05,
      "loss": 0.36332809448242187,
      "step": 1600
    },
    {
      "epoch": 0.42362002567394097,
      "grad_norm": 0.2355065792798996,
      "learning_rate": 7.758203799654577e-05,
      "loss": 0.35760486602783204,
      "step": 1650
    },
    {
      "epoch": 0.43645699614890887,
      "grad_norm": 0.12667398154735565,
      "learning_rate": 7.585492227979275e-05,
      "loss": 0.35097503662109375,
      "step": 1700
    },
    {
      "epoch": 0.4492939666238768,
      "grad_norm": 0.1517057865858078,
      "learning_rate": 7.412780656303972e-05,
      "loss": 0.3489809799194336,
      "step": 1750
    },
    {
      "epoch": 0.4621309370988447,
      "grad_norm": 0.1491526961326599,
      "learning_rate": 7.24006908462867e-05,
      "loss": 0.3445814895629883,
      "step": 1800
    },
    {
      "epoch": 0.4749679075738126,
      "grad_norm": 0.35639867186546326,
      "learning_rate": 7.067357512953368e-05,
      "loss": 0.3502203369140625,
      "step": 1850
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.23348164558410645,
      "learning_rate": 6.894645941278066e-05,
      "loss": 0.35449127197265623,
      "step": 1900
    },
    {
      "epoch": 0.5006418485237484,
      "grad_norm": 0.23395156860351562,
      "learning_rate": 6.721934369602763e-05,
      "loss": 0.34555843353271487,
      "step": 1950
    },
    {
      "epoch": 0.5134788189987163,
      "grad_norm": 0.08784468472003937,
      "learning_rate": 6.549222797927461e-05,
      "loss": 0.3361371994018555,
      "step": 2000
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.19914951920509338,
      "learning_rate": 6.376511226252158e-05,
      "loss": 0.3310558319091797,
      "step": 2050
    },
    {
      "epoch": 0.5391527599486521,
      "grad_norm": 0.10957474261522293,
      "learning_rate": 6.203799654576857e-05,
      "loss": 0.3278776550292969,
      "step": 2100
    },
    {
      "epoch": 0.55198973042362,
      "grad_norm": 0.09552228450775146,
      "learning_rate": 6.031088082901555e-05,
      "loss": 0.33646728515625,
      "step": 2150
    },
    {
      "epoch": 0.5648267008985879,
      "grad_norm": 0.12445715069770813,
      "learning_rate": 5.8583765112262525e-05,
      "loss": 0.3413481903076172,
      "step": 2200
    },
    {
      "epoch": 0.5776636713735558,
      "grad_norm": 0.12201932072639465,
      "learning_rate": 5.68566493955095e-05,
      "loss": 0.3390993118286133,
      "step": 2250
    },
    {
      "epoch": 0.5905006418485238,
      "grad_norm": 0.4175962209701538,
      "learning_rate": 5.512953367875648e-05,
      "loss": 0.33532310485839845,
      "step": 2300
    },
    {
      "epoch": 0.6033376123234917,
      "grad_norm": 0.12227510660886765,
      "learning_rate": 5.340241796200346e-05,
      "loss": 0.3344745635986328,
      "step": 2350
    },
    {
      "epoch": 0.6161745827984596,
      "grad_norm": 0.11136194318532944,
      "learning_rate": 5.1675302245250436e-05,
      "loss": 0.33181922912597656,
      "step": 2400
    },
    {
      "epoch": 0.6290115532734275,
      "grad_norm": 0.4821062684059143,
      "learning_rate": 4.994818652849741e-05,
      "loss": 0.32976619720458983,
      "step": 2450
    },
    {
      "epoch": 0.6418485237483954,
      "grad_norm": 0.23706191778182983,
      "learning_rate": 4.822107081174439e-05,
      "loss": 0.3250557327270508,
      "step": 2500
    },
    {
      "epoch": 0.6546854942233633,
      "grad_norm": 0.09493366628885269,
      "learning_rate": 4.6493955094991366e-05,
      "loss": 0.3231216049194336,
      "step": 2550
    },
    {
      "epoch": 0.6675224646983312,
      "grad_norm": 0.0930773913860321,
      "learning_rate": 4.476683937823835e-05,
      "loss": 0.32086544036865233,
      "step": 2600
    },
    {
      "epoch": 0.6803594351732991,
      "grad_norm": 0.08754566311836243,
      "learning_rate": 4.303972366148532e-05,
      "loss": 0.31904102325439454,
      "step": 2650
    },
    {
      "epoch": 0.693196405648267,
      "grad_norm": 0.12373068183660507,
      "learning_rate": 4.13126079447323e-05,
      "loss": 0.31563213348388675,
      "step": 2700
    },
    {
      "epoch": 0.7060333761232349,
      "grad_norm": 0.16497094929218292,
      "learning_rate": 3.958549222797928e-05,
      "loss": 0.31960479736328123,
      "step": 2750
    },
    {
      "epoch": 0.7188703465982028,
      "grad_norm": 0.0955139547586441,
      "learning_rate": 3.785837651122626e-05,
      "loss": 0.3205603790283203,
      "step": 2800
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 0.15006078779697418,
      "learning_rate": 3.613126079447323e-05,
      "loss": 0.32104141235351563,
      "step": 2850
    },
    {
      "epoch": 0.7445442875481386,
      "grad_norm": 0.13589662313461304,
      "learning_rate": 3.440414507772021e-05,
      "loss": 0.32076522827148435,
      "step": 2900
    },
    {
      "epoch": 0.7573812580231065,
      "grad_norm": 0.09831491112709045,
      "learning_rate": 3.267702936096719e-05,
      "loss": 0.31948944091796877,
      "step": 2950
    },
    {
      "epoch": 0.7702182284980744,
      "grad_norm": 0.14385093748569489,
      "learning_rate": 3.094991364421416e-05,
      "loss": 0.3176760673522949,
      "step": 3000
    },
    {
      "epoch": 0.7830551989730423,
      "grad_norm": 0.09578834474086761,
      "learning_rate": 2.9222797927461144e-05,
      "loss": 0.31971689224243166,
      "step": 3050
    },
    {
      "epoch": 0.7958921694480102,
      "grad_norm": 0.09932112693786621,
      "learning_rate": 2.749568221070812e-05,
      "loss": 0.3154916000366211,
      "step": 3100
    },
    {
      "epoch": 0.8087291399229781,
      "grad_norm": 0.16507507860660553,
      "learning_rate": 2.57685664939551e-05,
      "loss": 0.30985294342041014,
      "step": 3150
    },
    {
      "epoch": 0.8215661103979461,
      "grad_norm": 0.1454581916332245,
      "learning_rate": 2.4041450777202074e-05,
      "loss": 0.30778188705444337,
      "step": 3200
    },
    {
      "epoch": 0.834403080872914,
      "grad_norm": 0.09813928604125977,
      "learning_rate": 2.231433506044905e-05,
      "loss": 0.3117471504211426,
      "step": 3250
    },
    {
      "epoch": 0.8472400513478819,
      "grad_norm": 0.1607631891965866,
      "learning_rate": 2.058721934369603e-05,
      "loss": 0.3139165687561035,
      "step": 3300
    },
    {
      "epoch": 0.8600770218228498,
      "grad_norm": 0.11378655582666397,
      "learning_rate": 1.8860103626943007e-05,
      "loss": 0.3133310127258301,
      "step": 3350
    },
    {
      "epoch": 0.8729139922978177,
      "grad_norm": 0.14272405207157135,
      "learning_rate": 1.7132987910189985e-05,
      "loss": 0.31023677825927737,
      "step": 3400
    },
    {
      "epoch": 0.8857509627727856,
      "grad_norm": 0.09286146610975266,
      "learning_rate": 1.540587219343696e-05,
      "loss": 0.308338623046875,
      "step": 3450
    },
    {
      "epoch": 0.8985879332477535,
      "grad_norm": 0.10180367529392242,
      "learning_rate": 1.3678756476683937e-05,
      "loss": 0.3110722541809082,
      "step": 3500
    },
    {
      "epoch": 0.9114249037227214,
      "grad_norm": 0.09780056774616241,
      "learning_rate": 1.1951640759930915e-05,
      "loss": 0.32003807067871093,
      "step": 3550
    },
    {
      "epoch": 0.9242618741976893,
      "grad_norm": 0.09449557214975357,
      "learning_rate": 1.0224525043177893e-05,
      "loss": 0.3211833953857422,
      "step": 3600
    },
    {
      "epoch": 0.9370988446726572,
      "grad_norm": 0.12358680367469788,
      "learning_rate": 8.49740932642487e-06,
      "loss": 0.31855316162109376,
      "step": 3650
    },
    {
      "epoch": 0.9499358151476252,
      "grad_norm": 0.09521187096834183,
      "learning_rate": 6.770293609671849e-06,
      "loss": 0.3195349884033203,
      "step": 3700
    },
    {
      "epoch": 0.962772785622593,
      "grad_norm": 0.09164498001337051,
      "learning_rate": 5.043177892918826e-06,
      "loss": 0.3159216117858887,
      "step": 3750
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.08823825418949127,
      "learning_rate": 3.3160621761658032e-06,
      "loss": 0.31672914505004884,
      "step": 3800
    },
    {
      "epoch": 0.9884467265725289,
      "grad_norm": 0.1414022296667099,
      "learning_rate": 1.5889464594127806e-06,
      "loss": 0.31752862930297854,
      "step": 3850
    }
  ],
  "logging_steps": 50,
  "max_steps": 3895,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.85487770459177e+17,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}