{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0395136778115504,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030395136778115502,
      "grad_norm": 9.889811515808105,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.6102,
      "step": 10
    },
    {
      "epoch": 0.060790273556231005,
      "grad_norm": 11.921159744262695,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.4517,
      "step": 20
    },
    {
      "epoch": 0.0911854103343465,
      "grad_norm": 8.763319969177246,
      "learning_rate": 6e-06,
      "loss": 1.3953,
      "step": 30
    },
    {
      "epoch": 0.12158054711246201,
      "grad_norm": 4.841191291809082,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0262,
      "step": 40
    },
    {
      "epoch": 0.1519756838905775,
      "grad_norm": 4.8184733390808105,
      "learning_rate": 1e-05,
      "loss": 0.6875,
      "step": 50
    },
    {
      "epoch": 0.182370820668693,
      "grad_norm": 4.519493579864502,
      "learning_rate": 1.2e-05,
      "loss": 0.5443,
      "step": 60
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 2.340122699737549,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.3662,
      "step": 70
    },
    {
      "epoch": 0.24316109422492402,
      "grad_norm": 1.4288235902786255,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.2864,
      "step": 80
    },
    {
      "epoch": 0.2735562310030395,
      "grad_norm": 1.979983925819397,
      "learning_rate": 1.8e-05,
      "loss": 0.2239,
      "step": 90
    },
    {
      "epoch": 0.303951367781155,
      "grad_norm": 1.3639392852783203,
      "learning_rate": 2e-05,
      "loss": 0.166,
      "step": 100
    },
    {
      "epoch": 0.3343465045592705,
      "grad_norm": 0.9854844808578491,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.1515,
      "step": 110
    },
    {
      "epoch": 0.364741641337386,
      "grad_norm": 1.101383924484253,
      "learning_rate": 2.4e-05,
      "loss": 0.1637,
      "step": 120
    },
    {
      "epoch": 0.3951367781155015,
      "grad_norm": 1.665946125984192,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.1045,
      "step": 130
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.7495555877685547,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.1058,
      "step": 140
    },
    {
      "epoch": 0.45592705167173253,
      "grad_norm": 1.0226916074752808,
      "learning_rate": 3e-05,
      "loss": 0.1079,
      "step": 150
    },
    {
      "epoch": 0.48632218844984804,
      "grad_norm": 0.6161096096038818,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.0993,
      "step": 160
    },
    {
      "epoch": 0.5167173252279635,
      "grad_norm": 0.7106040120124817,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.1079,
      "step": 170
    },
    {
      "epoch": 0.547112462006079,
      "grad_norm": 1.0743619203567505,
      "learning_rate": 3.6e-05,
      "loss": 0.0882,
      "step": 180
    },
    {
      "epoch": 0.5775075987841946,
      "grad_norm": 0.85890132188797,
      "learning_rate": 3.8e-05,
      "loss": 0.0943,
      "step": 190
    },
    {
      "epoch": 0.60790273556231,
      "grad_norm": 1.4179412126541138,
      "learning_rate": 4e-05,
      "loss": 0.0969,
      "step": 200
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 2.021270513534546,
      "learning_rate": 4.2e-05,
      "loss": 0.0934,
      "step": 210
    },
    {
      "epoch": 0.668693009118541,
      "grad_norm": 1.4204037189483643,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.0992,
      "step": 220
    },
    {
      "epoch": 0.6990881458966566,
      "grad_norm": 1.0484898090362549,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.0807,
      "step": 230
    },
    {
      "epoch": 0.729483282674772,
      "grad_norm": 1.0355311632156372,
      "learning_rate": 4.8e-05,
      "loss": 0.0827,
      "step": 240
    },
    {
      "epoch": 0.7598784194528876,
      "grad_norm": 0.7956388592720032,
      "learning_rate": 5e-05,
      "loss": 0.0818,
      "step": 250
    },
    {
      "epoch": 0.790273556231003,
      "grad_norm": 0.8189113736152649,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.076,
      "step": 260
    },
    {
      "epoch": 0.8206686930091185,
      "grad_norm": 0.6537955403327942,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.0738,
      "step": 270
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.8595532774925232,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.0797,
      "step": 280
    },
    {
      "epoch": 0.8814589665653495,
      "grad_norm": 0.9948979020118713,
      "learning_rate": 5.8e-05,
      "loss": 0.0674,
      "step": 290
    },
    {
      "epoch": 0.9118541033434651,
      "grad_norm": 0.7822934985160828,
      "learning_rate": 6e-05,
      "loss": 0.0839,
      "step": 300
    },
    {
      "epoch": 0.9422492401215805,
      "grad_norm": 0.9252318143844604,
      "learning_rate": 6.2e-05,
      "loss": 0.0657,
      "step": 310
    },
    {
      "epoch": 0.9726443768996961,
      "grad_norm": 1.2264695167541504,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.0751,
      "step": 320
    },
    {
      "epoch": 1.0030395136778116,
      "grad_norm": 0.6637468338012695,
      "learning_rate": 6.6e-05,
      "loss": 0.0766,
      "step": 330
    },
    {
      "epoch": 1.033434650455927,
      "grad_norm": 1.3035773038864136,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.0637,
      "step": 340
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 0.8334704637527466,
      "learning_rate": 7e-05,
      "loss": 0.0753,
      "step": 350
    },
    {
      "epoch": 1.094224924012158,
      "grad_norm": 1.2079942226409912,
      "learning_rate": 7.2e-05,
      "loss": 0.0729,
      "step": 360
    },
    {
      "epoch": 1.1246200607902737,
      "grad_norm": 0.8719915747642517,
      "learning_rate": 7.4e-05,
      "loss": 0.0577,
      "step": 370
    },
    {
      "epoch": 1.155015197568389,
      "grad_norm": 0.9174433350563049,
      "learning_rate": 7.6e-05,
      "loss": 0.0705,
      "step": 380
    },
    {
      "epoch": 1.1854103343465046,
      "grad_norm": 1.2214233875274658,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.0837,
      "step": 390
    },
    {
      "epoch": 1.21580547112462,
      "grad_norm": 1.2708603143692017,
      "learning_rate": 8e-05,
      "loss": 0.0658,
      "step": 400
    },
    {
      "epoch": 1.2462006079027357,
      "grad_norm": 1.0723034143447876,
      "learning_rate": 8.2e-05,
      "loss": 0.0625,
      "step": 410
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 1.0916433334350586,
      "learning_rate": 8.4e-05,
      "loss": 0.087,
      "step": 420
    },
    {
      "epoch": 1.3069908814589666,
      "grad_norm": 0.6322633624076843,
      "learning_rate": 8.6e-05,
      "loss": 0.0722,
      "step": 430
    },
    {
      "epoch": 1.337386018237082,
      "grad_norm": 0.5855675339698792,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.0635,
      "step": 440
    },
    {
      "epoch": 1.3677811550151975,
      "grad_norm": 1.0976413488388062,
      "learning_rate": 9e-05,
      "loss": 0.0664,
      "step": 450
    },
    {
      "epoch": 1.3981762917933132,
      "grad_norm": 0.9359951019287109,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.0647,
      "step": 460
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.7038888335227966,
      "learning_rate": 9.4e-05,
      "loss": 0.0716,
      "step": 470
    },
    {
      "epoch": 1.458966565349544,
      "grad_norm": 0.5396299958229065,
      "learning_rate": 9.6e-05,
      "loss": 0.0527,
      "step": 480
    },
    {
      "epoch": 1.4893617021276595,
      "grad_norm": 0.5245558619499207,
      "learning_rate": 9.8e-05,
      "loss": 0.0627,
      "step": 490
    },
    {
      "epoch": 1.5197568389057752,
      "grad_norm": 1.350913405418396,
      "learning_rate": 0.0001,
      "loss": 0.0555,
      "step": 500
    },
    {
      "epoch": 1.5501519756838906,
      "grad_norm": 0.6774181723594666,
      "learning_rate": 9.999972660400536e-05,
      "loss": 0.061,
      "step": 510
    },
    {
      "epoch": 1.580547112462006,
      "grad_norm": 0.5291458964347839,
      "learning_rate": 9.999890641901125e-05,
      "loss": 0.0497,
      "step": 520
    },
    {
      "epoch": 1.6109422492401215,
      "grad_norm": 0.8055920600891113,
      "learning_rate": 9.999753945398704e-05,
      "loss": 0.0612,
      "step": 530
    },
    {
      "epoch": 1.641337386018237,
      "grad_norm": 0.6707597374916077,
      "learning_rate": 9.99956257238817e-05,
      "loss": 0.0618,
      "step": 540
    },
    {
      "epoch": 1.6717325227963524,
      "grad_norm": 0.6728675365447998,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.0569,
      "step": 550
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 0.5206692814826965,
      "learning_rate": 9.999015805811965e-05,
      "loss": 0.0574,
      "step": 560
    },
    {
      "epoch": 1.7325227963525835,
      "grad_norm": 0.7465855479240417,
      "learning_rate": 9.998660418225645e-05,
      "loss": 0.0665,
      "step": 570
    },
    {
      "epoch": 1.7629179331306992,
      "grad_norm": 0.5522341728210449,
      "learning_rate": 9.998250366089848e-05,
      "loss": 0.072,
      "step": 580
    },
    {
      "epoch": 1.7933130699088147,
      "grad_norm": 0.6498285531997681,
      "learning_rate": 9.997785653888835e-05,
      "loss": 0.0471,
      "step": 590
    },
    {
      "epoch": 1.8237082066869301,
      "grad_norm": 0.8599438071250916,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.056,
      "step": 600
    },
    {
      "epoch": 1.8541033434650456,
      "grad_norm": 2.1041059494018555,
      "learning_rate": 9.996692270216947e-05,
      "loss": 0.0732,
      "step": 610
    },
    {
      "epoch": 1.884498480243161,
      "grad_norm": 1.016334891319275,
      "learning_rate": 9.996063610703137e-05,
      "loss": 0.0657,
      "step": 620
    },
    {
      "epoch": 1.9148936170212765,
      "grad_norm": 0.6369310021400452,
      "learning_rate": 9.995380315038119e-05,
      "loss": 0.0499,
      "step": 630
    },
    {
      "epoch": 1.9452887537993921,
      "grad_norm": 0.6747097969055176,
      "learning_rate": 9.994642390694308e-05,
      "loss": 0.0552,
      "step": 640
    },
    {
      "epoch": 1.9756838905775076,
      "grad_norm": 0.8461899161338806,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.051,
      "step": 650
    },
    {
      "epoch": 2.0060790273556233,
      "grad_norm": 1.1829544305801392,
      "learning_rate": 9.993002688846913e-05,
      "loss": 0.0548,
      "step": 660
    },
    {
      "epoch": 2.0364741641337387,
      "grad_norm": 0.5973241329193115,
      "learning_rate": 9.992100929274846e-05,
      "loss": 0.0505,
      "step": 670
    },
    {
      "epoch": 2.066869300911854,
      "grad_norm": 0.4595549404621124,
      "learning_rate": 9.991144576886823e-05,
      "loss": 0.064,
      "step": 680
    },
    {
      "epoch": 2.0972644376899696,
      "grad_norm": 0.5466217994689941,
      "learning_rate": 9.990133642141359e-05,
      "loss": 0.0475,
      "step": 690
    },
    {
      "epoch": 2.127659574468085,
      "grad_norm": 0.4098721146583557,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.0459,
      "step": 700
    },
    {
      "epoch": 2.1580547112462005,
      "grad_norm": 0.5519854426383972,
      "learning_rate": 9.987948070396571e-05,
      "loss": 0.0463,
      "step": 710
    },
    {
      "epoch": 2.188449848024316,
      "grad_norm": 0.5170401930809021,
      "learning_rate": 9.986773457298311e-05,
      "loss": 0.0484,
      "step": 720
    },
    {
      "epoch": 2.2188449848024314,
      "grad_norm": 0.3473241925239563,
      "learning_rate": 9.985544309644475e-05,
      "loss": 0.0546,
      "step": 730
    },
    {
      "epoch": 2.2492401215805473,
      "grad_norm": 0.38744667172431946,
      "learning_rate": 9.984260640876821e-05,
      "loss": 0.0428,
      "step": 740
    },
    {
      "epoch": 2.2796352583586628,
      "grad_norm": 0.7359247803688049,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0592,
      "step": 750
    },
    {
      "epoch": 2.310030395136778,
      "grad_norm": 0.5814300179481506,
      "learning_rate": 9.981529796748134e-05,
      "loss": 0.0399,
      "step": 760
    },
    {
      "epoch": 2.3404255319148937,
      "grad_norm": 0.5898028016090393,
      "learning_rate": 9.980082651251175e-05,
      "loss": 0.046,
      "step": 770
    },
    {
      "epoch": 2.370820668693009,
      "grad_norm": 0.4852890968322754,
      "learning_rate": 9.97858104436822e-05,
      "loss": 0.046,
      "step": 780
    },
    {
      "epoch": 2.4012158054711246,
      "grad_norm": 0.4703480899333954,
      "learning_rate": 9.977024992520602e-05,
      "loss": 0.0374,
      "step": 790
    },
    {
      "epoch": 2.43161094224924,
      "grad_norm": 0.43933120369911194,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.0454,
      "step": 800
    },
    {
      "epoch": 2.4620060790273555,
      "grad_norm": 0.639541745185852,
      "learning_rate": 9.973749622593534e-05,
      "loss": 0.0379,
      "step": 810
    },
    {
      "epoch": 2.4924012158054714,
      "grad_norm": 0.6174078583717346,
      "learning_rate": 9.972030340333001e-05,
      "loss": 0.0539,
      "step": 820
    },
    {
      "epoch": 2.522796352583587,
      "grad_norm": 0.49048295617103577,
      "learning_rate": 9.970256684745258e-05,
      "loss": 0.045,
      "step": 830
    },
    {
      "epoch": 2.5531914893617023,
      "grad_norm": 0.3859421908855438,
      "learning_rate": 9.968428675226714e-05,
      "loss": 0.038,
      "step": 840
    },
    {
      "epoch": 2.5835866261398177,
      "grad_norm": 0.5661002993583679,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.0377,
      "step": 850
    },
    {
      "epoch": 2.613981762917933,
      "grad_norm": 0.6421768665313721,
      "learning_rate": 9.964609674954696e-05,
      "loss": 0.0516,
      "step": 860
    },
    {
      "epoch": 2.6443768996960486,
      "grad_norm": 0.36835750937461853,
      "learning_rate": 9.962618725965196e-05,
      "loss": 0.0354,
      "step": 870
    },
    {
      "epoch": 2.674772036474164,
      "grad_norm": 0.34994593262672424,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.0391,
      "step": 880
    },
    {
      "epoch": 2.7051671732522795,
      "grad_norm": 0.501876175403595,
      "learning_rate": 9.95847403914247e-05,
      "loss": 0.0459,
      "step": 890
    },
    {
      "epoch": 2.735562310030395,
      "grad_norm": 0.4514513611793518,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.0368,
      "step": 900
    },
    {
      "epoch": 2.7659574468085104,
      "grad_norm": 0.4428149461746216,
      "learning_rate": 9.954112452602045e-05,
      "loss": 0.033,
      "step": 910
    },
    {
      "epoch": 2.7963525835866263,
      "grad_norm": 0.7399154305458069,
      "learning_rate": 9.95185038118915e-05,
      "loss": 0.0443,
      "step": 920
    },
    {
      "epoch": 2.8267477203647418,
      "grad_norm": 0.4058426320552826,
      "learning_rate": 9.949534157133844e-05,
      "loss": 0.051,
      "step": 930
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.3738716244697571,
      "learning_rate": 9.94716380576598e-05,
      "loss": 0.0318,
      "step": 940
    },
    {
      "epoch": 2.8875379939209727,
      "grad_norm": 0.5219188332557678,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.0383,
      "step": 950
    },
    {
      "epoch": 2.917933130699088,
      "grad_norm": 0.28857406973838806,
      "learning_rate": 9.942260825371358e-05,
      "loss": 0.0413,
      "step": 960
    },
    {
      "epoch": 2.9483282674772036,
      "grad_norm": 0.4435504674911499,
      "learning_rate": 9.939728249962807e-05,
      "loss": 0.0331,
      "step": 970
    },
    {
      "epoch": 2.978723404255319,
      "grad_norm": 0.6941442489624023,
      "learning_rate": 9.937141654477528e-05,
      "loss": 0.039,
      "step": 980
    },
    {
      "epoch": 3.0091185410334345,
      "grad_norm": 0.5373895764350891,
      "learning_rate": 9.934501067202117e-05,
      "loss": 0.0434,
      "step": 990
    },
    {
      "epoch": 3.0395136778115504,
      "grad_norm": 0.3684053122997284,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0367,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 31,
  "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": 3.301578581152896e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}