{
  "best_global_step": 1800,
  "best_metric": 2.285778284072876,
  "best_model_checkpoint": "models/mini_stage2/checkpoint-1800",
  "epoch": 0.8933002481389578,
  "eval_steps": 300,
  "global_step": 1800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004962779156327543,
      "grad_norm": 7.886381149291992,
      "learning_rate": 1.3366336633663365e-06,
      "loss": 4.6656,
      "step": 10
    },
    {
      "epoch": 0.009925558312655087,
      "grad_norm": 5.6866021156311035,
      "learning_rate": 2.821782178217822e-06,
      "loss": 4.4733,
      "step": 20
    },
    {
      "epoch": 0.01488833746898263,
      "grad_norm": 4.5250091552734375,
      "learning_rate": 4.306930693069306e-06,
      "loss": 4.0093,
      "step": 30
    },
    {
      "epoch": 0.019851116625310174,
      "grad_norm": 3.3117995262145996,
      "learning_rate": 5.792079207920792e-06,
      "loss": 3.9259,
      "step": 40
    },
    {
      "epoch": 0.02481389578163772,
      "grad_norm": 3.5785279273986816,
      "learning_rate": 7.277227722772277e-06,
      "loss": 3.8315,
      "step": 50
    },
    {
      "epoch": 0.02977667493796526,
      "grad_norm": 5.32008695602417,
      "learning_rate": 8.762376237623762e-06,
      "loss": 3.673,
      "step": 60
    },
    {
      "epoch": 0.034739454094292806,
      "grad_norm": 4.776355266571045,
      "learning_rate": 1.0247524752475248e-05,
      "loss": 3.5076,
      "step": 70
    },
    {
      "epoch": 0.03970223325062035,
      "grad_norm": 4.523674488067627,
      "learning_rate": 1.1732673267326734e-05,
      "loss": 3.4416,
      "step": 80
    },
    {
      "epoch": 0.04466501240694789,
      "grad_norm": 4.444321155548096,
      "learning_rate": 1.3217821782178218e-05,
      "loss": 3.4362,
      "step": 90
    },
    {
      "epoch": 0.04962779156327544,
      "grad_norm": 4.364451885223389,
      "learning_rate": 1.4702970297029704e-05,
      "loss": 3.3934,
      "step": 100
    },
    {
      "epoch": 0.05459057071960298,
      "grad_norm": 5.098319053649902,
      "learning_rate": 1.618811881188119e-05,
      "loss": 3.3343,
      "step": 110
    },
    {
      "epoch": 0.05955334987593052,
      "grad_norm": 4.762153148651123,
      "learning_rate": 1.7673267326732672e-05,
      "loss": 3.3018,
      "step": 120
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 4.8034563064575195,
      "learning_rate": 1.915841584158416e-05,
      "loss": 3.2882,
      "step": 130
    },
    {
      "epoch": 0.06947890818858561,
      "grad_norm": 4.955429553985596,
      "learning_rate": 2.0643564356435643e-05,
      "loss": 3.3027,
      "step": 140
    },
    {
      "epoch": 0.07444168734491315,
      "grad_norm": 4.338839530944824,
      "learning_rate": 2.212871287128713e-05,
      "loss": 3.2177,
      "step": 150
    },
    {
      "epoch": 0.0794044665012407,
      "grad_norm": 4.854152202606201,
      "learning_rate": 2.3613861386138615e-05,
      "loss": 3.2708,
      "step": 160
    },
    {
      "epoch": 0.08436724565756824,
      "grad_norm": 4.855740070343018,
      "learning_rate": 2.5099009900990097e-05,
      "loss": 3.2645,
      "step": 170
    },
    {
      "epoch": 0.08933002481389578,
      "grad_norm": 5.82074499130249,
      "learning_rate": 2.6584158415841586e-05,
      "loss": 3.1939,
      "step": 180
    },
    {
      "epoch": 0.09429280397022333,
      "grad_norm": 5.284363746643066,
      "learning_rate": 2.8069306930693072e-05,
      "loss": 3.0575,
      "step": 190
    },
    {
      "epoch": 0.09925558312655088,
      "grad_norm": 5.663958549499512,
      "learning_rate": 2.9554455445544555e-05,
      "loss": 3.0799,
      "step": 200
    },
    {
      "epoch": 0.10421836228287841,
      "grad_norm": 5.67520809173584,
      "learning_rate": 2.9884169884169887e-05,
      "loss": 3.0824,
      "step": 210
    },
    {
      "epoch": 0.10918114143920596,
      "grad_norm": 5.432056903839111,
      "learning_rate": 2.9718698290126862e-05,
      "loss": 3.0693,
      "step": 220
    },
    {
      "epoch": 0.1141439205955335,
      "grad_norm": 5.387454032897949,
      "learning_rate": 2.9553226696083837e-05,
      "loss": 3.1014,
      "step": 230
    },
    {
      "epoch": 0.11910669975186104,
      "grad_norm": 5.515647888183594,
      "learning_rate": 2.9387755102040816e-05,
      "loss": 3.0458,
      "step": 240
    },
    {
      "epoch": 0.12406947890818859,
      "grad_norm": 5.962894916534424,
      "learning_rate": 2.9222283507997795e-05,
      "loss": 3.04,
      "step": 250
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 5.549206733703613,
      "learning_rate": 2.9056811913954774e-05,
      "loss": 3.0311,
      "step": 260
    },
    {
      "epoch": 0.13399503722084366,
      "grad_norm": 4.67368221282959,
      "learning_rate": 2.889134031991175e-05,
      "loss": 2.9778,
      "step": 270
    },
    {
      "epoch": 0.13895781637717122,
      "grad_norm": 5.445274829864502,
      "learning_rate": 2.8725868725868724e-05,
      "loss": 3.0701,
      "step": 280
    },
    {
      "epoch": 0.14392059553349876,
      "grad_norm": 5.643553256988525,
      "learning_rate": 2.8560397131825703e-05,
      "loss": 2.9039,
      "step": 290
    },
    {
      "epoch": 0.1488833746898263,
      "grad_norm": 5.453239440917969,
      "learning_rate": 2.8394925537782682e-05,
      "loss": 3.0449,
      "step": 300
    },
    {
      "epoch": 0.1488833746898263,
      "eval_loss": 2.5684616565704346,
      "eval_runtime": 119.1131,
      "eval_samples_per_second": 142.251,
      "eval_steps_per_second": 4.45,
      "step": 300
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 5.800920009613037,
      "learning_rate": 2.822945394373966e-05,
      "loss": 2.8896,
      "step": 310
    },
    {
      "epoch": 0.1588089330024814,
      "grad_norm": 4.8736724853515625,
      "learning_rate": 2.8063982349696636e-05,
      "loss": 3.0527,
      "step": 320
    },
    {
      "epoch": 0.16377171215880892,
      "grad_norm": 4.498941898345947,
      "learning_rate": 2.7898510755653615e-05,
      "loss": 3.0153,
      "step": 330
    },
    {
      "epoch": 0.1687344913151365,
      "grad_norm": 5.518968105316162,
      "learning_rate": 2.773303916161059e-05,
      "loss": 2.869,
      "step": 340
    },
    {
      "epoch": 0.17369727047146402,
      "grad_norm": 5.431845188140869,
      "learning_rate": 2.756756756756757e-05,
      "loss": 2.9678,
      "step": 350
    },
    {
      "epoch": 0.17866004962779156,
      "grad_norm": 5.1342973709106445,
      "learning_rate": 2.7402095973524544e-05,
      "loss": 2.9756,
      "step": 360
    },
    {
      "epoch": 0.18362282878411912,
      "grad_norm": 4.8498101234436035,
      "learning_rate": 2.7236624379481523e-05,
      "loss": 2.9348,
      "step": 370
    },
    {
      "epoch": 0.18858560794044665,
      "grad_norm": 5.223404407501221,
      "learning_rate": 2.70711527854385e-05,
      "loss": 2.9967,
      "step": 380
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 5.078680038452148,
      "learning_rate": 2.690568119139548e-05,
      "loss": 2.8953,
      "step": 390
    },
    {
      "epoch": 0.19851116625310175,
      "grad_norm": 4.336000442504883,
      "learning_rate": 2.6740209597352456e-05,
      "loss": 2.9546,
      "step": 400
    },
    {
      "epoch": 0.20347394540942929,
      "grad_norm": 5.194223880767822,
      "learning_rate": 2.657473800330943e-05,
      "loss": 2.9919,
      "step": 410
    },
    {
      "epoch": 0.20843672456575682,
      "grad_norm": 4.870718002319336,
      "learning_rate": 2.640926640926641e-05,
      "loss": 2.8487,
      "step": 420
    },
    {
      "epoch": 0.21339950372208435,
      "grad_norm": 5.526561260223389,
      "learning_rate": 2.624379481522339e-05,
      "loss": 2.7609,
      "step": 430
    },
    {
      "epoch": 0.21836228287841192,
      "grad_norm": 5.372407913208008,
      "learning_rate": 2.6078323221180364e-05,
      "loss": 2.9126,
      "step": 440
    },
    {
      "epoch": 0.22332506203473945,
      "grad_norm": 4.934298992156982,
      "learning_rate": 2.5912851627137343e-05,
      "loss": 2.8991,
      "step": 450
    },
    {
      "epoch": 0.228287841191067,
      "grad_norm": 4.916905403137207,
      "learning_rate": 2.574738003309432e-05,
      "loss": 2.9272,
      "step": 460
    },
    {
      "epoch": 0.23325062034739455,
      "grad_norm": 5.660480976104736,
      "learning_rate": 2.5581908439051297e-05,
      "loss": 2.9084,
      "step": 470
    },
    {
      "epoch": 0.23821339950372208,
      "grad_norm": 4.987634658813477,
      "learning_rate": 2.5416436845008272e-05,
      "loss": 2.7963,
      "step": 480
    },
    {
      "epoch": 0.24317617866004962,
      "grad_norm": 6.746623992919922,
      "learning_rate": 2.525096525096525e-05,
      "loss": 2.822,
      "step": 490
    },
    {
      "epoch": 0.24813895781637718,
      "grad_norm": 4.658477783203125,
      "learning_rate": 2.508549365692223e-05,
      "loss": 2.9376,
      "step": 500
    },
    {
      "epoch": 0.2531017369727047,
      "grad_norm": 5.2974162101745605,
      "learning_rate": 2.492002206287921e-05,
      "loss": 2.8969,
      "step": 510
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 5.682817459106445,
      "learning_rate": 2.4754550468836184e-05,
      "loss": 2.7745,
      "step": 520
    },
    {
      "epoch": 0.2630272952853598,
      "grad_norm": 5.85469388961792,
      "learning_rate": 2.458907887479316e-05,
      "loss": 2.8103,
      "step": 530
    },
    {
      "epoch": 0.2679900744416873,
      "grad_norm": 4.600194454193115,
      "learning_rate": 2.4423607280750138e-05,
      "loss": 2.8189,
      "step": 540
    },
    {
      "epoch": 0.2729528535980149,
      "grad_norm": 6.168639659881592,
      "learning_rate": 2.4258135686707117e-05,
      "loss": 2.8322,
      "step": 550
    },
    {
      "epoch": 0.27791563275434245,
      "grad_norm": 4.763863563537598,
      "learning_rate": 2.4092664092664092e-05,
      "loss": 2.7627,
      "step": 560
    },
    {
      "epoch": 0.28287841191067,
      "grad_norm": 5.0977091789245605,
      "learning_rate": 2.392719249862107e-05,
      "loss": 2.7796,
      "step": 570
    },
    {
      "epoch": 0.2878411910669975,
      "grad_norm": 4.786524772644043,
      "learning_rate": 2.376172090457805e-05,
      "loss": 2.8515,
      "step": 580
    },
    {
      "epoch": 0.29280397022332505,
      "grad_norm": 5.386171817779541,
      "learning_rate": 2.3596249310535025e-05,
      "loss": 2.8758,
      "step": 590
    },
    {
      "epoch": 0.2977667493796526,
      "grad_norm": 4.96185827255249,
      "learning_rate": 2.3430777716492e-05,
      "loss": 2.7963,
      "step": 600
    },
    {
      "epoch": 0.2977667493796526,
      "eval_loss": 2.4141688346862793,
      "eval_runtime": 112.2744,
      "eval_samples_per_second": 150.916,
      "eval_steps_per_second": 4.721,
      "step": 600
    },
    {
      "epoch": 0.3027295285359802,
      "grad_norm": 7.280220985412598,
      "learning_rate": 2.326530612244898e-05,
      "loss": 2.8259,
      "step": 610
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 5.671541690826416,
      "learning_rate": 2.3099834528405958e-05,
      "loss": 2.829,
      "step": 620
    },
    {
      "epoch": 0.31265508684863524,
      "grad_norm": 5.268543720245361,
      "learning_rate": 2.2934362934362936e-05,
      "loss": 2.7699,
      "step": 630
    },
    {
      "epoch": 0.3176178660049628,
      "grad_norm": 4.945257186889648,
      "learning_rate": 2.2768891340319915e-05,
      "loss": 2.7311,
      "step": 640
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 5.198265075683594,
      "learning_rate": 2.2603419746276887e-05,
      "loss": 2.735,
      "step": 650
    },
    {
      "epoch": 0.32754342431761785,
      "grad_norm": 4.624203205108643,
      "learning_rate": 2.2437948152233866e-05,
      "loss": 2.7306,
      "step": 660
    },
    {
      "epoch": 0.3325062034739454,
      "grad_norm": 5.143148899078369,
      "learning_rate": 2.2272476558190845e-05,
      "loss": 2.7467,
      "step": 670
    },
    {
      "epoch": 0.337468982630273,
      "grad_norm": 4.643360614776611,
      "learning_rate": 2.2107004964147823e-05,
      "loss": 2.7494,
      "step": 680
    },
    {
      "epoch": 0.3424317617866005,
      "grad_norm": 5.404439926147461,
      "learning_rate": 2.19415333701048e-05,
      "loss": 2.7386,
      "step": 690
    },
    {
      "epoch": 0.34739454094292804,
      "grad_norm": 4.590571403503418,
      "learning_rate": 2.1776061776061778e-05,
      "loss": 2.8513,
      "step": 700
    },
    {
      "epoch": 0.3523573200992556,
      "grad_norm": 5.185126781463623,
      "learning_rate": 2.1610590182018756e-05,
      "loss": 2.673,
      "step": 710
    },
    {
      "epoch": 0.3573200992555831,
      "grad_norm": 5.4743547439575195,
      "learning_rate": 2.144511858797573e-05,
      "loss": 2.8101,
      "step": 720
    },
    {
      "epoch": 0.36228287841191065,
      "grad_norm": 5.463687896728516,
      "learning_rate": 2.1279646993932707e-05,
      "loss": 2.7527,
      "step": 730
    },
    {
      "epoch": 0.36724565756823824,
      "grad_norm": 6.102997303009033,
      "learning_rate": 2.1114175399889686e-05,
      "loss": 2.7213,
      "step": 740
    },
    {
      "epoch": 0.37220843672456577,
      "grad_norm": 5.1998724937438965,
      "learning_rate": 2.0948703805846664e-05,
      "loss": 2.753,
      "step": 750
    },
    {
      "epoch": 0.3771712158808933,
      "grad_norm": 5.181605815887451,
      "learning_rate": 2.0783232211803643e-05,
      "loss": 2.8034,
      "step": 760
    },
    {
      "epoch": 0.38213399503722084,
      "grad_norm": 5.865420818328857,
      "learning_rate": 2.061776061776062e-05,
      "loss": 2.8288,
      "step": 770
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 4.965085029602051,
      "learning_rate": 2.0452289023717594e-05,
      "loss": 2.613,
      "step": 780
    },
    {
      "epoch": 0.3920595533498759,
      "grad_norm": 5.534601211547852,
      "learning_rate": 2.0286817429674573e-05,
      "loss": 2.7315,
      "step": 790
    },
    {
      "epoch": 0.3970223325062035,
      "grad_norm": 5.220632076263428,
      "learning_rate": 2.012134583563155e-05,
      "loss": 2.8077,
      "step": 800
    },
    {
      "epoch": 0.40198511166253104,
      "grad_norm": 5.059537410736084,
      "learning_rate": 1.9955874241588527e-05,
      "loss": 2.7442,
      "step": 810
    },
    {
      "epoch": 0.40694789081885857,
      "grad_norm": 5.325795650482178,
      "learning_rate": 1.9790402647545506e-05,
      "loss": 2.7351,
      "step": 820
    },
    {
      "epoch": 0.4119106699751861,
      "grad_norm": 8.455648422241211,
      "learning_rate": 1.9624931053502484e-05,
      "loss": 2.7643,
      "step": 830
    },
    {
      "epoch": 0.41687344913151364,
      "grad_norm": 5.344241619110107,
      "learning_rate": 1.945945945945946e-05,
      "loss": 2.8984,
      "step": 840
    },
    {
      "epoch": 0.4218362282878412,
      "grad_norm": 4.816617965698242,
      "learning_rate": 1.9293987865416435e-05,
      "loss": 2.7377,
      "step": 850
    },
    {
      "epoch": 0.4267990074441687,
      "grad_norm": 5.334592819213867,
      "learning_rate": 1.9128516271373414e-05,
      "loss": 2.7021,
      "step": 860
    },
    {
      "epoch": 0.4317617866004963,
      "grad_norm": 5.0712385177612305,
      "learning_rate": 1.8963044677330393e-05,
      "loss": 2.6756,
      "step": 870
    },
    {
      "epoch": 0.43672456575682383,
      "grad_norm": 5.225603103637695,
      "learning_rate": 1.879757308328737e-05,
      "loss": 2.7852,
      "step": 880
    },
    {
      "epoch": 0.44168734491315137,
      "grad_norm": 5.172723770141602,
      "learning_rate": 1.8632101489244347e-05,
      "loss": 2.7531,
      "step": 890
    },
    {
      "epoch": 0.4466501240694789,
      "grad_norm": 4.887333869934082,
      "learning_rate": 1.8466629895201322e-05,
      "loss": 2.6636,
      "step": 900
    },
    {
      "epoch": 0.4466501240694789,
      "eval_loss": 2.3456013202667236,
      "eval_runtime": 113.8402,
      "eval_samples_per_second": 148.84,
      "eval_steps_per_second": 4.656,
      "step": 900
    },
    {
      "epoch": 0.45161290322580644,
      "grad_norm": 5.249894142150879,
      "learning_rate": 1.83011583011583e-05,
      "loss": 2.7089,
      "step": 910
    },
    {
      "epoch": 0.456575682382134,
      "grad_norm": 4.984340667724609,
      "learning_rate": 1.813568670711528e-05,
      "loss": 2.8029,
      "step": 920
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 5.297105312347412,
      "learning_rate": 1.7970215113072255e-05,
      "loss": 2.721,
      "step": 930
    },
    {
      "epoch": 0.4665012406947891,
      "grad_norm": 5.074361801147461,
      "learning_rate": 1.7804743519029234e-05,
      "loss": 2.5606,
      "step": 940
    },
    {
      "epoch": 0.47146401985111663,
      "grad_norm": 5.639915943145752,
      "learning_rate": 1.7639271924986212e-05,
      "loss": 2.6397,
      "step": 950
    },
    {
      "epoch": 0.47642679900744417,
      "grad_norm": 5.445567607879639,
      "learning_rate": 1.7473800330943188e-05,
      "loss": 2.6563,
      "step": 960
    },
    {
      "epoch": 0.4813895781637717,
      "grad_norm": 4.462475299835205,
      "learning_rate": 1.7308328736900166e-05,
      "loss": 2.7163,
      "step": 970
    },
    {
      "epoch": 0.48635235732009924,
      "grad_norm": 5.833073139190674,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 2.6225,
      "step": 980
    },
    {
      "epoch": 0.4913151364764268,
      "grad_norm": 5.428512096405029,
      "learning_rate": 1.697738554881412e-05,
      "loss": 2.645,
      "step": 990
    },
    {
      "epoch": 0.49627791563275436,
      "grad_norm": 4.768510818481445,
      "learning_rate": 1.68119139547711e-05,
      "loss": 2.6576,
      "step": 1000
    },
    {
      "epoch": 0.5012406947890818,
      "grad_norm": 4.692178726196289,
      "learning_rate": 1.6646442360728078e-05,
      "loss": 2.7019,
      "step": 1010
    },
    {
      "epoch": 0.5062034739454094,
      "grad_norm": 5.51165771484375,
      "learning_rate": 1.6480970766685053e-05,
      "loss": 2.7195,
      "step": 1020
    },
    {
      "epoch": 0.511166253101737,
      "grad_norm": 4.9710516929626465,
      "learning_rate": 1.631549917264203e-05,
      "loss": 2.7242,
      "step": 1030
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 5.166830062866211,
      "learning_rate": 1.6150027578599008e-05,
      "loss": 2.6729,
      "step": 1040
    },
    {
      "epoch": 0.5210918114143921,
      "grad_norm": 4.945868015289307,
      "learning_rate": 1.5984555984555986e-05,
      "loss": 2.7637,
      "step": 1050
    },
    {
      "epoch": 0.5260545905707196,
      "grad_norm": 5.7991943359375,
      "learning_rate": 1.581908439051296e-05,
      "loss": 2.677,
      "step": 1060
    },
    {
      "epoch": 0.5310173697270472,
      "grad_norm": 5.255971431732178,
      "learning_rate": 1.565361279646994e-05,
      "loss": 2.7018,
      "step": 1070
    },
    {
      "epoch": 0.5359801488833746,
      "grad_norm": 5.910732746124268,
      "learning_rate": 1.548814120242692e-05,
      "loss": 2.6469,
      "step": 1080
    },
    {
      "epoch": 0.5409429280397022,
      "grad_norm": 4.5612616539001465,
      "learning_rate": 1.5322669608383895e-05,
      "loss": 2.7186,
      "step": 1090
    },
    {
      "epoch": 0.5459057071960298,
      "grad_norm": 5.111081600189209,
      "learning_rate": 1.515719801434087e-05,
      "loss": 2.6728,
      "step": 1100
    },
    {
      "epoch": 0.5508684863523573,
      "grad_norm": 5.450465202331543,
      "learning_rate": 1.4991726420297849e-05,
      "loss": 2.6694,
      "step": 1110
    },
    {
      "epoch": 0.5558312655086849,
      "grad_norm": 4.850940704345703,
      "learning_rate": 1.4826254826254827e-05,
      "loss": 2.7839,
      "step": 1120
    },
    {
      "epoch": 0.5607940446650124,
      "grad_norm": 5.036434173583984,
      "learning_rate": 1.4660783232211803e-05,
      "loss": 2.5834,
      "step": 1130
    },
    {
      "epoch": 0.56575682382134,
      "grad_norm": 40.256370544433594,
      "learning_rate": 1.4495311638168781e-05,
      "loss": 2.6905,
      "step": 1140
    },
    {
      "epoch": 0.5707196029776674,
      "grad_norm": 5.939204692840576,
      "learning_rate": 1.4329840044125759e-05,
      "loss": 2.7223,
      "step": 1150
    },
    {
      "epoch": 0.575682382133995,
      "grad_norm": 5.288106441497803,
      "learning_rate": 1.4164368450082736e-05,
      "loss": 2.7235,
      "step": 1160
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 5.540660858154297,
      "learning_rate": 1.3998896856039713e-05,
      "loss": 2.636,
      "step": 1170
    },
    {
      "epoch": 0.5856079404466501,
      "grad_norm": 5.182808876037598,
      "learning_rate": 1.3833425261996691e-05,
      "loss": 2.6314,
      "step": 1180
    },
    {
      "epoch": 0.5905707196029777,
      "grad_norm": 4.9914140701293945,
      "learning_rate": 1.3667953667953668e-05,
      "loss": 2.5941,
      "step": 1190
    },
    {
      "epoch": 0.5955334987593052,
      "grad_norm": 4.8229475021362305,
      "learning_rate": 1.3502482073910646e-05,
      "loss": 2.7827,
      "step": 1200
    },
    {
      "epoch": 0.5955334987593052,
      "eval_loss": 2.2910733222961426,
      "eval_runtime": 115.8769,
      "eval_samples_per_second": 146.224,
      "eval_steps_per_second": 4.574,
      "step": 1200
    },
    {
      "epoch": 0.6004962779156328,
      "grad_norm": 5.556408882141113,
      "learning_rate": 1.3337010479867623e-05,
      "loss": 2.6104,
      "step": 1210
    },
    {
      "epoch": 0.6054590570719603,
      "grad_norm": 6.0620551109313965,
      "learning_rate": 1.3171538885824601e-05,
      "loss": 2.6148,
      "step": 1220
    },
    {
      "epoch": 0.6104218362282878,
      "grad_norm": 5.285867214202881,
      "learning_rate": 1.3006067291781577e-05,
      "loss": 2.6355,
      "step": 1230
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 5.499397277832031,
      "learning_rate": 1.2840595697738555e-05,
      "loss": 2.6269,
      "step": 1240
    },
    {
      "epoch": 0.6203473945409429,
      "grad_norm": 4.932219505310059,
      "learning_rate": 1.2675124103695532e-05,
      "loss": 2.6003,
      "step": 1250
    },
    {
      "epoch": 0.6253101736972705,
      "grad_norm": 5.04417610168457,
      "learning_rate": 1.250965250965251e-05,
      "loss": 2.6256,
      "step": 1260
    },
    {
      "epoch": 0.630272952853598,
      "grad_norm": 5.0753679275512695,
      "learning_rate": 1.2344180915609488e-05,
      "loss": 2.6326,
      "step": 1270
    },
    {
      "epoch": 0.6352357320099256,
      "grad_norm": 5.003329753875732,
      "learning_rate": 1.2178709321566465e-05,
      "loss": 2.681,
      "step": 1280
    },
    {
      "epoch": 0.6401985111662531,
      "grad_norm": 5.094631671905518,
      "learning_rate": 1.2013237727523442e-05,
      "loss": 2.5776,
      "step": 1290
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 4.915186405181885,
      "learning_rate": 1.184776613348042e-05,
      "loss": 2.7528,
      "step": 1300
    },
    {
      "epoch": 0.6501240694789082,
      "grad_norm": 5.3234076499938965,
      "learning_rate": 1.1682294539437398e-05,
      "loss": 2.6076,
      "step": 1310
    },
    {
      "epoch": 0.6550868486352357,
      "grad_norm": 6.5297064781188965,
      "learning_rate": 1.1516822945394374e-05,
      "loss": 2.5784,
      "step": 1320
    },
    {
      "epoch": 0.6600496277915633,
      "grad_norm": 5.549312591552734,
      "learning_rate": 1.1351351351351352e-05,
      "loss": 2.6064,
      "step": 1330
    },
    {
      "epoch": 0.6650124069478908,
      "grad_norm": 4.589717388153076,
      "learning_rate": 1.118587975730833e-05,
      "loss": 2.5757,
      "step": 1340
    },
    {
      "epoch": 0.6699751861042184,
      "grad_norm": 6.217405796051025,
      "learning_rate": 1.1020408163265306e-05,
      "loss": 2.5851,
      "step": 1350
    },
    {
      "epoch": 0.674937965260546,
      "grad_norm": 5.602436542510986,
      "learning_rate": 1.0854936569222283e-05,
      "loss": 2.6007,
      "step": 1360
    },
    {
      "epoch": 0.6799007444168734,
      "grad_norm": 4.934968948364258,
      "learning_rate": 1.0689464975179262e-05,
      "loss": 2.5674,
      "step": 1370
    },
    {
      "epoch": 0.684863523573201,
      "grad_norm": 5.8763322830200195,
      "learning_rate": 1.0523993381136238e-05,
      "loss": 2.6984,
      "step": 1380
    },
    {
      "epoch": 0.6898263027295285,
      "grad_norm": 5.077223777770996,
      "learning_rate": 1.0358521787093216e-05,
      "loss": 2.6202,
      "step": 1390
    },
    {
      "epoch": 0.6947890818858561,
      "grad_norm": 6.423431873321533,
      "learning_rate": 1.0193050193050193e-05,
      "loss": 2.6729,
      "step": 1400
    },
    {
      "epoch": 0.6997518610421837,
      "grad_norm": 5.683679103851318,
      "learning_rate": 1.002757859900717e-05,
      "loss": 2.6683,
      "step": 1410
    },
    {
      "epoch": 0.7047146401985112,
      "grad_norm": 5.217991828918457,
      "learning_rate": 9.862107004964148e-06,
      "loss": 2.6355,
      "step": 1420
    },
    {
      "epoch": 0.7096774193548387,
      "grad_norm": 5.0821332931518555,
      "learning_rate": 9.696635410921126e-06,
      "loss": 2.6033,
      "step": 1430
    },
    {
      "epoch": 0.7146401985111662,
      "grad_norm": 5.337713718414307,
      "learning_rate": 9.531163816878102e-06,
      "loss": 2.6834,
      "step": 1440
    },
    {
      "epoch": 0.7196029776674938,
      "grad_norm": 5.425897598266602,
      "learning_rate": 9.36569222283508e-06,
      "loss": 2.6597,
      "step": 1450
    },
    {
      "epoch": 0.7245657568238213,
      "grad_norm": 4.878344535827637,
      "learning_rate": 9.200220628792057e-06,
      "loss": 2.6298,
      "step": 1460
    },
    {
      "epoch": 0.7295285359801489,
      "grad_norm": 5.754893779754639,
      "learning_rate": 9.034749034749034e-06,
      "loss": 2.6232,
      "step": 1470
    },
    {
      "epoch": 0.7344913151364765,
      "grad_norm": 4.991476535797119,
      "learning_rate": 8.869277440706012e-06,
      "loss": 2.5672,
      "step": 1480
    },
    {
      "epoch": 0.739454094292804,
      "grad_norm": 6.236905097961426,
      "learning_rate": 8.70380584666299e-06,
      "loss": 2.5139,
      "step": 1490
    },
    {
      "epoch": 0.7444168734491315,
      "grad_norm": 4.892019748687744,
      "learning_rate": 8.538334252619966e-06,
      "loss": 2.6248,
      "step": 1500
    },
    {
      "epoch": 0.7444168734491315,
      "eval_loss": 2.3090243339538574,
      "eval_runtime": 114.529,
      "eval_samples_per_second": 147.945,
      "eval_steps_per_second": 4.628,
      "step": 1500
    },
    {
      "epoch": 0.749379652605459,
      "grad_norm": 5.293705463409424,
      "learning_rate": 8.372862658576944e-06,
      "loss": 2.6417,
      "step": 1510
    },
    {
      "epoch": 0.7543424317617866,
      "grad_norm": 6.500164031982422,
      "learning_rate": 8.207391064533921e-06,
      "loss": 2.6197,
      "step": 1520
    },
    {
      "epoch": 0.7593052109181141,
      "grad_norm": 5.456136226654053,
      "learning_rate": 8.0419194704909e-06,
      "loss": 2.6911,
      "step": 1530
    },
    {
      "epoch": 0.7642679900744417,
      "grad_norm": 5.395550727844238,
      "learning_rate": 7.876447876447876e-06,
      "loss": 2.5542,
      "step": 1540
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 5.446476936340332,
      "learning_rate": 7.710976282404854e-06,
      "loss": 2.6584,
      "step": 1550
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 5.699354648590088,
      "learning_rate": 7.5455046883618305e-06,
      "loss": 2.6182,
      "step": 1560
    },
    {
      "epoch": 0.7791563275434243,
      "grad_norm": 5.835291862487793,
      "learning_rate": 7.3800330943188084e-06,
      "loss": 2.6301,
      "step": 1570
    },
    {
      "epoch": 0.7841191066997518,
      "grad_norm": 5.066339015960693,
      "learning_rate": 7.214561500275786e-06,
      "loss": 2.5629,
      "step": 1580
    },
    {
      "epoch": 0.7890818858560794,
      "grad_norm": 6.113178253173828,
      "learning_rate": 7.049089906232763e-06,
      "loss": 2.5965,
      "step": 1590
    },
    {
      "epoch": 0.794044665012407,
      "grad_norm": 5.544576168060303,
      "learning_rate": 6.8836183121897404e-06,
      "loss": 2.5722,
      "step": 1600
    },
    {
      "epoch": 0.7990074441687345,
      "grad_norm": 5.560300350189209,
      "learning_rate": 6.718146718146718e-06,
      "loss": 2.5835,
      "step": 1610
    },
    {
      "epoch": 0.8039702233250621,
      "grad_norm": 5.354392051696777,
      "learning_rate": 6.552675124103695e-06,
      "loss": 2.5901,
      "step": 1620
    },
    {
      "epoch": 0.8089330024813896,
      "grad_norm": 5.256809234619141,
      "learning_rate": 6.387203530060673e-06,
      "loss": 2.6055,
      "step": 1630
    },
    {
      "epoch": 0.8138957816377171,
      "grad_norm": 6.089339256286621,
      "learning_rate": 6.22173193601765e-06,
      "loss": 2.6019,
      "step": 1640
    },
    {
      "epoch": 0.8188585607940446,
      "grad_norm": 4.713355541229248,
      "learning_rate": 6.056260341974627e-06,
      "loss": 2.6421,
      "step": 1650
    },
    {
      "epoch": 0.8238213399503722,
      "grad_norm": 6.513923168182373,
      "learning_rate": 5.890788747931605e-06,
      "loss": 2.6049,
      "step": 1660
    },
    {
      "epoch": 0.8287841191066998,
      "grad_norm": 5.37587833404541,
      "learning_rate": 5.725317153888582e-06,
      "loss": 2.5351,
      "step": 1670
    },
    {
      "epoch": 0.8337468982630273,
      "grad_norm": 6.346861362457275,
      "learning_rate": 5.5598455598455594e-06,
      "loss": 2.6158,
      "step": 1680
    },
    {
      "epoch": 0.8387096774193549,
      "grad_norm": 5.206553936004639,
      "learning_rate": 5.394373965802537e-06,
      "loss": 2.5994,
      "step": 1690
    },
    {
      "epoch": 0.8436724565756824,
      "grad_norm": 6.567471504211426,
      "learning_rate": 5.228902371759514e-06,
      "loss": 2.5816,
      "step": 1700
    },
    {
      "epoch": 0.8486352357320099,
      "grad_norm": 5.689151287078857,
      "learning_rate": 5.0634307777164914e-06,
      "loss": 2.5848,
      "step": 1710
    },
    {
      "epoch": 0.8535980148883374,
      "grad_norm": 5.288684844970703,
      "learning_rate": 4.897959183673469e-06,
      "loss": 2.6138,
      "step": 1720
    },
    {
      "epoch": 0.858560794044665,
      "grad_norm": 5.238705635070801,
      "learning_rate": 4.732487589630447e-06,
      "loss": 2.5811,
      "step": 1730
    },
    {
      "epoch": 0.8635235732009926,
      "grad_norm": 5.114046573638916,
      "learning_rate": 4.567015995587424e-06,
      "loss": 2.5933,
      "step": 1740
    },
    {
      "epoch": 0.8684863523573201,
      "grad_norm": 6.13997220993042,
      "learning_rate": 4.401544401544402e-06,
      "loss": 2.5869,
      "step": 1750
    },
    {
      "epoch": 0.8734491315136477,
      "grad_norm": 5.258871555328369,
      "learning_rate": 4.236072807501379e-06,
      "loss": 2.5464,
      "step": 1760
    },
    {
      "epoch": 0.8784119106699751,
      "grad_norm": 5.823874473571777,
      "learning_rate": 4.070601213458356e-06,
      "loss": 2.6842,
      "step": 1770
    },
    {
      "epoch": 0.8833746898263027,
      "grad_norm": 5.351442337036133,
      "learning_rate": 3.905129619415334e-06,
      "loss": 2.6312,
      "step": 1780
    },
    {
      "epoch": 0.8883374689826302,
      "grad_norm": 5.9153947830200195,
      "learning_rate": 3.739658025372311e-06,
      "loss": 2.5621,
      "step": 1790
    },
    {
      "epoch": 0.8933002481389578,
      "grad_norm": 5.032203197479248,
      "learning_rate": 3.5741864313292883e-06,
      "loss": 2.6103,
      "step": 1800
    },
    {
      "epoch": 0.8933002481389578,
      "eval_loss": 2.285778284072876,
      "eval_runtime": 108.9864,
      "eval_samples_per_second": 155.469,
      "eval_steps_per_second": 4.863,
      "step": 1800
    }
  ],
  "logging_steps": 10,
  "max_steps": 2015,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 300,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}