{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 2470,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020242914979757085,
      "grad_norm": 2.8825272538542044,
      "learning_rate": 5e-06,
      "loss": 0.7569,
      "step": 10
    },
    {
      "epoch": 0.04048582995951417,
      "grad_norm": 2.3606485385931157,
      "learning_rate": 5e-06,
      "loss": 0.6504,
      "step": 20
    },
    {
      "epoch": 0.06072874493927125,
      "grad_norm": 1.426935919321139,
      "learning_rate": 5e-06,
      "loss": 0.6287,
      "step": 30
    },
    {
      "epoch": 0.08097165991902834,
      "grad_norm": 1.9896158325770887,
      "learning_rate": 5e-06,
      "loss": 0.6136,
      "step": 40
    },
    {
      "epoch": 0.10121457489878542,
      "grad_norm": 1.2993488018928139,
      "learning_rate": 5e-06,
      "loss": 0.6036,
      "step": 50
    },
    {
      "epoch": 0.1214574898785425,
      "grad_norm": 1.3692905065095424,
      "learning_rate": 5e-06,
      "loss": 0.5974,
      "step": 60
    },
    {
      "epoch": 0.1417004048582996,
      "grad_norm": 1.817904836385203,
      "learning_rate": 5e-06,
      "loss": 0.5925,
      "step": 70
    },
    {
      "epoch": 0.16194331983805668,
      "grad_norm": 1.37930069536892,
      "learning_rate": 5e-06,
      "loss": 0.5878,
      "step": 80
    },
    {
      "epoch": 0.18218623481781376,
      "grad_norm": 1.9672481173378518,
      "learning_rate": 5e-06,
      "loss": 0.5869,
      "step": 90
    },
    {
      "epoch": 0.20242914979757085,
      "grad_norm": 1.5190200995442689,
      "learning_rate": 5e-06,
      "loss": 0.5895,
      "step": 100
    },
    {
      "epoch": 0.22267206477732793,
      "grad_norm": 1.467909545843528,
      "learning_rate": 5e-06,
      "loss": 0.5814,
      "step": 110
    },
    {
      "epoch": 0.242914979757085,
      "grad_norm": 1.2624328705735892,
      "learning_rate": 5e-06,
      "loss": 0.579,
      "step": 120
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 2.8330967598290644,
      "learning_rate": 5e-06,
      "loss": 0.5783,
      "step": 130
    },
    {
      "epoch": 0.2834008097165992,
      "grad_norm": 2.606189250371495,
      "learning_rate": 5e-06,
      "loss": 0.5692,
      "step": 140
    },
    {
      "epoch": 0.30364372469635625,
      "grad_norm": 2.0755945998925616,
      "learning_rate": 5e-06,
      "loss": 0.5778,
      "step": 150
    },
    {
      "epoch": 0.32388663967611336,
      "grad_norm": 2.112489158829737,
      "learning_rate": 5e-06,
      "loss": 0.5757,
      "step": 160
    },
    {
      "epoch": 0.3441295546558704,
      "grad_norm": 1.773147820799013,
      "learning_rate": 5e-06,
      "loss": 0.5757,
      "step": 170
    },
    {
      "epoch": 0.3643724696356275,
      "grad_norm": 1.9389286348778036,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 180
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 2.0257261841165506,
      "learning_rate": 5e-06,
      "loss": 0.5708,
      "step": 190
    },
    {
      "epoch": 0.4048582995951417,
      "grad_norm": 1.6235586407175255,
      "learning_rate": 5e-06,
      "loss": 0.5664,
      "step": 200
    },
    {
      "epoch": 0.4251012145748988,
      "grad_norm": 1.3600120185742202,
      "learning_rate": 5e-06,
      "loss": 0.5624,
      "step": 210
    },
    {
      "epoch": 0.44534412955465585,
      "grad_norm": 1.5782442409144959,
      "learning_rate": 5e-06,
      "loss": 0.5686,
      "step": 220
    },
    {
      "epoch": 0.46558704453441296,
      "grad_norm": 1.9084679996506322,
      "learning_rate": 5e-06,
      "loss": 0.5681,
      "step": 230
    },
    {
      "epoch": 0.48582995951417,
      "grad_norm": 1.562642052863713,
      "learning_rate": 5e-06,
      "loss": 0.5643,
      "step": 240
    },
    {
      "epoch": 0.5060728744939271,
      "grad_norm": 1.9619840593224824,
      "learning_rate": 5e-06,
      "loss": 0.5666,
      "step": 250
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 1.5861604962625888,
      "learning_rate": 5e-06,
      "loss": 0.5518,
      "step": 260
    },
    {
      "epoch": 0.5465587044534413,
      "grad_norm": 1.7006302815881864,
      "learning_rate": 5e-06,
      "loss": 0.5605,
      "step": 270
    },
    {
      "epoch": 0.5668016194331984,
      "grad_norm": 1.6651788716675646,
      "learning_rate": 5e-06,
      "loss": 0.5568,
      "step": 280
    },
    {
      "epoch": 0.5870445344129555,
      "grad_norm": 2.2785089542841708,
      "learning_rate": 5e-06,
      "loss": 0.5565,
      "step": 290
    },
    {
      "epoch": 0.6072874493927125,
      "grad_norm": 1.5770155712986973,
      "learning_rate": 5e-06,
      "loss": 0.5575,
      "step": 300
    },
    {
      "epoch": 0.6275303643724697,
      "grad_norm": 1.3220149177446632,
      "learning_rate": 5e-06,
      "loss": 0.5622,
      "step": 310
    },
    {
      "epoch": 0.6477732793522267,
      "grad_norm": 1.3472535369102203,
      "learning_rate": 5e-06,
      "loss": 0.5594,
      "step": 320
    },
    {
      "epoch": 0.6680161943319838,
      "grad_norm": 1.3309997590990947,
      "learning_rate": 5e-06,
      "loss": 0.5601,
      "step": 330
    },
    {
      "epoch": 0.6882591093117408,
      "grad_norm": 1.4273218646615096,
      "learning_rate": 5e-06,
      "loss": 0.5601,
      "step": 340
    },
    {
      "epoch": 0.708502024291498,
      "grad_norm": 1.2085847860457979,
      "learning_rate": 5e-06,
      "loss": 0.5619,
      "step": 350
    },
    {
      "epoch": 0.728744939271255,
      "grad_norm": 1.122941072415825,
      "learning_rate": 5e-06,
      "loss": 0.564,
      "step": 360
    },
    {
      "epoch": 0.7489878542510121,
      "grad_norm": 1.3973216531402086,
      "learning_rate": 5e-06,
      "loss": 0.5571,
      "step": 370
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 1.18082932151255,
      "learning_rate": 5e-06,
      "loss": 0.5538,
      "step": 380
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 1.1780579152037594,
      "learning_rate": 5e-06,
      "loss": 0.557,
      "step": 390
    },
    {
      "epoch": 0.8097165991902834,
      "grad_norm": 1.3785246959799171,
      "learning_rate": 5e-06,
      "loss": 0.5576,
      "step": 400
    },
    {
      "epoch": 0.8299595141700404,
      "grad_norm": 1.2948034196229,
      "learning_rate": 5e-06,
      "loss": 0.5524,
      "step": 410
    },
    {
      "epoch": 0.8502024291497976,
      "grad_norm": 1.186346298990548,
      "learning_rate": 5e-06,
      "loss": 0.5598,
      "step": 420
    },
    {
      "epoch": 0.8704453441295547,
      "grad_norm": 1.1531795830071445,
      "learning_rate": 5e-06,
      "loss": 0.5532,
      "step": 430
    },
    {
      "epoch": 0.8906882591093117,
      "grad_norm": 1.238207775770585,
      "learning_rate": 5e-06,
      "loss": 0.5587,
      "step": 440
    },
    {
      "epoch": 0.9109311740890689,
      "grad_norm": 1.579785932754029,
      "learning_rate": 5e-06,
      "loss": 0.5499,
      "step": 450
    },
    {
      "epoch": 0.9311740890688259,
      "grad_norm": 1.0932455184252672,
      "learning_rate": 5e-06,
      "loss": 0.5547,
      "step": 460
    },
    {
      "epoch": 0.951417004048583,
      "grad_norm": 1.1455184663362503,
      "learning_rate": 5e-06,
      "loss": 0.5548,
      "step": 470
    },
    {
      "epoch": 0.97165991902834,
      "grad_norm": 1.0783335686803248,
      "learning_rate": 5e-06,
      "loss": 0.5515,
      "step": 480
    },
    {
      "epoch": 0.9919028340080972,
      "grad_norm": 1.221913718764988,
      "learning_rate": 5e-06,
      "loss": 0.5486,
      "step": 490
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.27600792050361633,
      "eval_runtime": 127.9056,
      "eval_samples_per_second": 104.014,
      "eval_steps_per_second": 0.407,
      "step": 494
    },
    {
      "epoch": 1.0121457489878543,
      "grad_norm": 1.946031690795471,
      "learning_rate": 5e-06,
      "loss": 0.5099,
      "step": 500
    },
    {
      "epoch": 1.0323886639676114,
      "grad_norm": 1.9289680946263923,
      "learning_rate": 5e-06,
      "loss": 0.4748,
      "step": 510
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 1.353788705122084,
      "learning_rate": 5e-06,
      "loss": 0.468,
      "step": 520
    },
    {
      "epoch": 1.0728744939271255,
      "grad_norm": 1.205205720059485,
      "learning_rate": 5e-06,
      "loss": 0.4735,
      "step": 530
    },
    {
      "epoch": 1.0931174089068827,
      "grad_norm": 1.282155131195443,
      "learning_rate": 5e-06,
      "loss": 0.4657,
      "step": 540
    },
    {
      "epoch": 1.1133603238866396,
      "grad_norm": 1.5080942345199266,
      "learning_rate": 5e-06,
      "loss": 0.4699,
      "step": 550
    },
    {
      "epoch": 1.1336032388663968,
      "grad_norm": 2.00023442913857,
      "learning_rate": 5e-06,
      "loss": 0.4659,
      "step": 560
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 1.7909520333071323,
      "learning_rate": 5e-06,
      "loss": 0.4715,
      "step": 570
    },
    {
      "epoch": 1.174089068825911,
      "grad_norm": 1.6662712618465199,
      "learning_rate": 5e-06,
      "loss": 0.4705,
      "step": 580
    },
    {
      "epoch": 1.194331983805668,
      "grad_norm": 1.3259873704215552,
      "learning_rate": 5e-06,
      "loss": 0.4633,
      "step": 590
    },
    {
      "epoch": 1.214574898785425,
      "grad_norm": 1.6651495485618664,
      "learning_rate": 5e-06,
      "loss": 0.4706,
      "step": 600
    },
    {
      "epoch": 1.2348178137651822,
      "grad_norm": 1.477115453248806,
      "learning_rate": 5e-06,
      "loss": 0.4674,
      "step": 610
    },
    {
      "epoch": 1.2550607287449393,
      "grad_norm": 1.263440522189552,
      "learning_rate": 5e-06,
      "loss": 0.4715,
      "step": 620
    },
    {
      "epoch": 1.2753036437246963,
      "grad_norm": 1.4025183176779765,
      "learning_rate": 5e-06,
      "loss": 0.4715,
      "step": 630
    },
    {
      "epoch": 1.2955465587044535,
      "grad_norm": 1.3060745387835275,
      "learning_rate": 5e-06,
      "loss": 0.473,
      "step": 640
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 1.2936497262200077,
      "learning_rate": 5e-06,
      "loss": 0.4775,
      "step": 650
    },
    {
      "epoch": 1.3360323886639676,
      "grad_norm": 1.2889809170808153,
      "learning_rate": 5e-06,
      "loss": 0.4671,
      "step": 660
    },
    {
      "epoch": 1.3562753036437247,
      "grad_norm": 1.3063275232148253,
      "learning_rate": 5e-06,
      "loss": 0.4808,
      "step": 670
    },
    {
      "epoch": 1.376518218623482,
      "grad_norm": 1.1392335054785994,
      "learning_rate": 5e-06,
      "loss": 0.4765,
      "step": 680
    },
    {
      "epoch": 1.3967611336032388,
      "grad_norm": 1.1028492143829693,
      "learning_rate": 5e-06,
      "loss": 0.4759,
      "step": 690
    },
    {
      "epoch": 1.417004048582996,
      "grad_norm": 1.1765124226702088,
      "learning_rate": 5e-06,
      "loss": 0.4739,
      "step": 700
    },
    {
      "epoch": 1.4372469635627532,
      "grad_norm": 1.2359278437898007,
      "learning_rate": 5e-06,
      "loss": 0.4799,
      "step": 710
    },
    {
      "epoch": 1.45748987854251,
      "grad_norm": 1.206361807359358,
      "learning_rate": 5e-06,
      "loss": 0.4792,
      "step": 720
    },
    {
      "epoch": 1.4777327935222673,
      "grad_norm": 1.2584288631713865,
      "learning_rate": 5e-06,
      "loss": 0.4829,
      "step": 730
    },
    {
      "epoch": 1.4979757085020242,
      "grad_norm": 1.3266851287176349,
      "learning_rate": 5e-06,
      "loss": 0.4757,
      "step": 740
    },
    {
      "epoch": 1.5182186234817814,
      "grad_norm": 1.174062885309594,
      "learning_rate": 5e-06,
      "loss": 0.4786,
      "step": 750
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 1.217286859959994,
      "learning_rate": 5e-06,
      "loss": 0.48,
      "step": 760
    },
    {
      "epoch": 1.5587044534412957,
      "grad_norm": 1.2963071104766335,
      "learning_rate": 5e-06,
      "loss": 0.4771,
      "step": 770
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 1.1301017979019057,
      "learning_rate": 5e-06,
      "loss": 0.4788,
      "step": 780
    },
    {
      "epoch": 1.5991902834008096,
      "grad_norm": 1.2142771905592493,
      "learning_rate": 5e-06,
      "loss": 0.4813,
      "step": 790
    },
    {
      "epoch": 1.6194331983805668,
      "grad_norm": 1.1156710660198195,
      "learning_rate": 5e-06,
      "loss": 0.478,
      "step": 800
    },
    {
      "epoch": 1.639676113360324,
      "grad_norm": 1.3426333112263065,
      "learning_rate": 5e-06,
      "loss": 0.4712,
      "step": 810
    },
    {
      "epoch": 1.6599190283400809,
      "grad_norm": 1.3351933873992157,
      "learning_rate": 5e-06,
      "loss": 0.4782,
      "step": 820
    },
    {
      "epoch": 1.680161943319838,
      "grad_norm": 1.1798934266276804,
      "learning_rate": 5e-06,
      "loss": 0.4759,
      "step": 830
    },
    {
      "epoch": 1.7004048582995952,
      "grad_norm": 1.0719853459322617,
      "learning_rate": 5e-06,
      "loss": 0.4751,
      "step": 840
    },
    {
      "epoch": 1.7206477732793521,
      "grad_norm": 1.1539682879539461,
      "learning_rate": 5e-06,
      "loss": 0.4787,
      "step": 850
    },
    {
      "epoch": 1.7408906882591093,
      "grad_norm": 1.1331656389881875,
      "learning_rate": 5e-06,
      "loss": 0.4782,
      "step": 860
    },
    {
      "epoch": 1.7611336032388665,
      "grad_norm": 1.2305656250383992,
      "learning_rate": 5e-06,
      "loss": 0.4808,
      "step": 870
    },
    {
      "epoch": 1.7813765182186234,
      "grad_norm": 1.484161550142479,
      "learning_rate": 5e-06,
      "loss": 0.4829,
      "step": 880
    },
    {
      "epoch": 1.8016194331983806,
      "grad_norm": 1.180007815990233,
      "learning_rate": 5e-06,
      "loss": 0.4781,
      "step": 890
    },
    {
      "epoch": 1.8218623481781377,
      "grad_norm": 1.200692474334057,
      "learning_rate": 5e-06,
      "loss": 0.4779,
      "step": 900
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 1.1652057043804007,
      "learning_rate": 5e-06,
      "loss": 0.48,
      "step": 910
    },
    {
      "epoch": 1.8623481781376519,
      "grad_norm": 1.2546941772227673,
      "learning_rate": 5e-06,
      "loss": 0.4796,
      "step": 920
    },
    {
      "epoch": 1.882591093117409,
      "grad_norm": 1.1919644772038955,
      "learning_rate": 5e-06,
      "loss": 0.4754,
      "step": 930
    },
    {
      "epoch": 1.902834008097166,
      "grad_norm": 1.086719187935772,
      "learning_rate": 5e-06,
      "loss": 0.4798,
      "step": 940
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 1.1603089251078402,
      "learning_rate": 5e-06,
      "loss": 0.4816,
      "step": 950
    },
    {
      "epoch": 1.9433198380566803,
      "grad_norm": 1.082753063279857,
      "learning_rate": 5e-06,
      "loss": 0.4842,
      "step": 960
    },
    {
      "epoch": 1.9635627530364372,
      "grad_norm": 1.1470965026545579,
      "learning_rate": 5e-06,
      "loss": 0.4826,
      "step": 970
    },
    {
      "epoch": 1.9838056680161942,
      "grad_norm": 1.317035146950926,
      "learning_rate": 5e-06,
      "loss": 0.4834,
      "step": 980
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.2760300040245056,
      "eval_runtime": 128.3279,
      "eval_samples_per_second": 103.672,
      "eval_steps_per_second": 0.405,
      "step": 988
    },
    {
      "epoch": 2.0040485829959516,
      "grad_norm": 2.423406809168664,
      "learning_rate": 5e-06,
      "loss": 0.4596,
      "step": 990
    },
    {
      "epoch": 2.0242914979757085,
      "grad_norm": 1.8171058614039022,
      "learning_rate": 5e-06,
      "loss": 0.3883,
      "step": 1000
    },
    {
      "epoch": 2.0445344129554655,
      "grad_norm": 1.5419534841689435,
      "learning_rate": 5e-06,
      "loss": 0.3836,
      "step": 1010
    },
    {
      "epoch": 2.064777327935223,
      "grad_norm": 1.476614885030913,
      "learning_rate": 5e-06,
      "loss": 0.3801,
      "step": 1020
    },
    {
      "epoch": 2.08502024291498,
      "grad_norm": 1.379440361306421,
      "learning_rate": 5e-06,
      "loss": 0.3784,
      "step": 1030
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 1.4083322026387224,
      "learning_rate": 5e-06,
      "loss": 0.3778,
      "step": 1040
    },
    {
      "epoch": 2.125506072874494,
      "grad_norm": 1.4696113259366608,
      "learning_rate": 5e-06,
      "loss": 0.3879,
      "step": 1050
    },
    {
      "epoch": 2.145748987854251,
      "grad_norm": 1.2713132554208233,
      "learning_rate": 5e-06,
      "loss": 0.3806,
      "step": 1060
    },
    {
      "epoch": 2.165991902834008,
      "grad_norm": 1.3917546218353265,
      "learning_rate": 5e-06,
      "loss": 0.386,
      "step": 1070
    },
    {
      "epoch": 2.1862348178137654,
      "grad_norm": 1.4708546369587632,
      "learning_rate": 5e-06,
      "loss": 0.3845,
      "step": 1080
    },
    {
      "epoch": 2.2064777327935223,
      "grad_norm": 1.595163601660772,
      "learning_rate": 5e-06,
      "loss": 0.3828,
      "step": 1090
    },
    {
      "epoch": 2.2267206477732793,
      "grad_norm": 1.4877074059133855,
      "learning_rate": 5e-06,
      "loss": 0.3897,
      "step": 1100
    },
    {
      "epoch": 2.246963562753036,
      "grad_norm": 1.7370364288636082,
      "learning_rate": 5e-06,
      "loss": 0.3875,
      "step": 1110
    },
    {
      "epoch": 2.2672064777327936,
      "grad_norm": 1.8541525908514815,
      "learning_rate": 5e-06,
      "loss": 0.3884,
      "step": 1120
    },
    {
      "epoch": 2.2874493927125505,
      "grad_norm": 1.5781496384158298,
      "learning_rate": 5e-06,
      "loss": 0.3894,
      "step": 1130
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 1.7708762236924664,
      "learning_rate": 5e-06,
      "loss": 0.3859,
      "step": 1140
    },
    {
      "epoch": 2.327935222672065,
      "grad_norm": 1.4475591252123796,
      "learning_rate": 5e-06,
      "loss": 0.3887,
      "step": 1150
    },
    {
      "epoch": 2.348178137651822,
      "grad_norm": 1.2226909125336796,
      "learning_rate": 5e-06,
      "loss": 0.3885,
      "step": 1160
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 1.3657056897603896,
      "learning_rate": 5e-06,
      "loss": 0.392,
      "step": 1170
    },
    {
      "epoch": 2.388663967611336,
      "grad_norm": 1.314590138508193,
      "learning_rate": 5e-06,
      "loss": 0.3926,
      "step": 1180
    },
    {
      "epoch": 2.408906882591093,
      "grad_norm": 1.4093248309707875,
      "learning_rate": 5e-06,
      "loss": 0.3929,
      "step": 1190
    },
    {
      "epoch": 2.42914979757085,
      "grad_norm": 1.3473340294150489,
      "learning_rate": 5e-06,
      "loss": 0.39,
      "step": 1200
    },
    {
      "epoch": 2.4493927125506074,
      "grad_norm": 1.4512860257939517,
      "learning_rate": 5e-06,
      "loss": 0.3902,
      "step": 1210
    },
    {
      "epoch": 2.4696356275303644,
      "grad_norm": 1.4529803502641332,
      "learning_rate": 5e-06,
      "loss": 0.3947,
      "step": 1220
    },
    {
      "epoch": 2.4898785425101213,
      "grad_norm": 1.384452479045095,
      "learning_rate": 5e-06,
      "loss": 0.3953,
      "step": 1230
    },
    {
      "epoch": 2.5101214574898787,
      "grad_norm": 1.2935497884972742,
      "learning_rate": 5e-06,
      "loss": 0.3986,
      "step": 1240
    },
    {
      "epoch": 2.5303643724696356,
      "grad_norm": 1.190834719805313,
      "learning_rate": 5e-06,
      "loss": 0.3914,
      "step": 1250
    },
    {
      "epoch": 2.5506072874493926,
      "grad_norm": 1.5623940633492222,
      "learning_rate": 5e-06,
      "loss": 0.3887,
      "step": 1260
    },
    {
      "epoch": 2.57085020242915,
      "grad_norm": 1.4071250725201772,
      "learning_rate": 5e-06,
      "loss": 0.3941,
      "step": 1270
    },
    {
      "epoch": 2.591093117408907,
      "grad_norm": 1.4686855669517231,
      "learning_rate": 5e-06,
      "loss": 0.3956,
      "step": 1280
    },
    {
      "epoch": 2.611336032388664,
      "grad_norm": 1.29119112691104,
      "learning_rate": 5e-06,
      "loss": 0.3998,
      "step": 1290
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 1.2673323070448081,
      "learning_rate": 5e-06,
      "loss": 0.3961,
      "step": 1300
    },
    {
      "epoch": 2.651821862348178,
      "grad_norm": 1.2450186102009178,
      "learning_rate": 5e-06,
      "loss": 0.395,
      "step": 1310
    },
    {
      "epoch": 2.672064777327935,
      "grad_norm": 1.3598218086289704,
      "learning_rate": 5e-06,
      "loss": 0.3969,
      "step": 1320
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 1.476188415686639,
      "learning_rate": 5e-06,
      "loss": 0.401,
      "step": 1330
    },
    {
      "epoch": 2.7125506072874495,
      "grad_norm": 1.2772087881864984,
      "learning_rate": 5e-06,
      "loss": 0.3981,
      "step": 1340
    },
    {
      "epoch": 2.7327935222672064,
      "grad_norm": 1.3901040643475941,
      "learning_rate": 5e-06,
      "loss": 0.399,
      "step": 1350
    },
    {
      "epoch": 2.753036437246964,
      "grad_norm": 1.2669956962100783,
      "learning_rate": 5e-06,
      "loss": 0.3936,
      "step": 1360
    },
    {
      "epoch": 2.7732793522267207,
      "grad_norm": 1.3605832094262316,
      "learning_rate": 5e-06,
      "loss": 0.3996,
      "step": 1370
    },
    {
      "epoch": 2.7935222672064777,
      "grad_norm": 1.4625604256084817,
      "learning_rate": 5e-06,
      "loss": 0.3997,
      "step": 1380
    },
    {
      "epoch": 2.813765182186235,
      "grad_norm": 1.784848571739763,
      "learning_rate": 5e-06,
      "loss": 0.4012,
      "step": 1390
    },
    {
      "epoch": 2.834008097165992,
      "grad_norm": 1.6211701201270445,
      "learning_rate": 5e-06,
      "loss": 0.3948,
      "step": 1400
    },
    {
      "epoch": 2.854251012145749,
      "grad_norm": 1.5362470053479813,
      "learning_rate": 5e-06,
      "loss": 0.4017,
      "step": 1410
    },
    {
      "epoch": 2.8744939271255063,
      "grad_norm": 1.4029392342160418,
      "learning_rate": 5e-06,
      "loss": 0.3992,
      "step": 1420
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 1.4342688190560124,
      "learning_rate": 5e-06,
      "loss": 0.395,
      "step": 1430
    },
    {
      "epoch": 2.91497975708502,
      "grad_norm": 1.2695118103828797,
      "learning_rate": 5e-06,
      "loss": 0.4008,
      "step": 1440
    },
    {
      "epoch": 2.9352226720647776,
      "grad_norm": 1.2741085284215934,
      "learning_rate": 5e-06,
      "loss": 0.4111,
      "step": 1450
    },
    {
      "epoch": 2.9554655870445345,
      "grad_norm": 1.2910941516817205,
      "learning_rate": 5e-06,
      "loss": 0.3975,
      "step": 1460
    },
    {
      "epoch": 2.9757085020242915,
      "grad_norm": 1.4853937254356013,
      "learning_rate": 5e-06,
      "loss": 0.4012,
      "step": 1470
    },
    {
      "epoch": 2.9959514170040484,
      "grad_norm": 1.4022248360408927,
      "learning_rate": 5e-06,
      "loss": 0.4034,
      "step": 1480
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.29170867800712585,
      "eval_runtime": 128.4123,
      "eval_samples_per_second": 103.604,
      "eval_steps_per_second": 0.405,
      "step": 1482
    },
    {
      "epoch": 3.016194331983806,
      "grad_norm": 2.450301362827223,
      "learning_rate": 5e-06,
      "loss": 0.3253,
      "step": 1490
    },
    {
      "epoch": 3.0364372469635628,
      "grad_norm": 1.7227064520999624,
      "learning_rate": 5e-06,
      "loss": 0.2917,
      "step": 1500
    },
    {
      "epoch": 3.0566801619433197,
      "grad_norm": 1.708297211407951,
      "learning_rate": 5e-06,
      "loss": 0.2951,
      "step": 1510
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 1.6773762742996041,
      "learning_rate": 5e-06,
      "loss": 0.2916,
      "step": 1520
    },
    {
      "epoch": 3.097165991902834,
      "grad_norm": 1.5835044005502448,
      "learning_rate": 5e-06,
      "loss": 0.2949,
      "step": 1530
    },
    {
      "epoch": 3.117408906882591,
      "grad_norm": 1.6991756969105973,
      "learning_rate": 5e-06,
      "loss": 0.2906,
      "step": 1540
    },
    {
      "epoch": 3.1376518218623484,
      "grad_norm": 1.6309085248071211,
      "learning_rate": 5e-06,
      "loss": 0.2887,
      "step": 1550
    },
    {
      "epoch": 3.1578947368421053,
      "grad_norm": 1.467082791239925,
      "learning_rate": 5e-06,
      "loss": 0.2958,
      "step": 1560
    },
    {
      "epoch": 3.1781376518218623,
      "grad_norm": 1.5977415982902385,
      "learning_rate": 5e-06,
      "loss": 0.2958,
      "step": 1570
    },
    {
      "epoch": 3.1983805668016196,
      "grad_norm": 1.794838585622722,
      "learning_rate": 5e-06,
      "loss": 0.2985,
      "step": 1580
    },
    {
      "epoch": 3.2186234817813766,
      "grad_norm": 1.6188047839576813,
      "learning_rate": 5e-06,
      "loss": 0.3009,
      "step": 1590
    },
    {
      "epoch": 3.2388663967611335,
      "grad_norm": 1.5996247856636512,
      "learning_rate": 5e-06,
      "loss": 0.2993,
      "step": 1600
    },
    {
      "epoch": 3.2591093117408905,
      "grad_norm": 1.5799607329692924,
      "learning_rate": 5e-06,
      "loss": 0.2981,
      "step": 1610
    },
    {
      "epoch": 3.279352226720648,
      "grad_norm": 1.6462393560491397,
      "learning_rate": 5e-06,
      "loss": 0.3014,
      "step": 1620
    },
    {
      "epoch": 3.299595141700405,
      "grad_norm": 1.743995264000295,
      "learning_rate": 5e-06,
      "loss": 0.3034,
      "step": 1630
    },
    {
      "epoch": 3.3198380566801617,
      "grad_norm": 1.6858202723993232,
      "learning_rate": 5e-06,
      "loss": 0.303,
      "step": 1640
    },
    {
      "epoch": 3.340080971659919,
      "grad_norm": 1.8191610290572566,
      "learning_rate": 5e-06,
      "loss": 0.3003,
      "step": 1650
    },
    {
      "epoch": 3.360323886639676,
      "grad_norm": 1.601413073895001,
      "learning_rate": 5e-06,
      "loss": 0.3051,
      "step": 1660
    },
    {
      "epoch": 3.380566801619433,
      "grad_norm": 1.7563790440673033,
      "learning_rate": 5e-06,
      "loss": 0.2999,
      "step": 1670
    },
    {
      "epoch": 3.4008097165991904,
      "grad_norm": 1.5579994158970751,
      "learning_rate": 5e-06,
      "loss": 0.2989,
      "step": 1680
    },
    {
      "epoch": 3.4210526315789473,
      "grad_norm": 1.516213960669368,
      "learning_rate": 5e-06,
      "loss": 0.3011,
      "step": 1690
    },
    {
      "epoch": 3.4412955465587043,
      "grad_norm": 1.658051304756316,
      "learning_rate": 5e-06,
      "loss": 0.3024,
      "step": 1700
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 1.5918375939252065,
      "learning_rate": 5e-06,
      "loss": 0.3056,
      "step": 1710
    },
    {
      "epoch": 3.4817813765182186,
      "grad_norm": 1.6167160427713403,
      "learning_rate": 5e-06,
      "loss": 0.3059,
      "step": 1720
    },
    {
      "epoch": 3.5020242914979756,
      "grad_norm": 1.633353659275257,
      "learning_rate": 5e-06,
      "loss": 0.3103,
      "step": 1730
    },
    {
      "epoch": 3.522267206477733,
      "grad_norm": 1.6652424042294116,
      "learning_rate": 5e-06,
      "loss": 0.3047,
      "step": 1740
    },
    {
      "epoch": 3.54251012145749,
      "grad_norm": 1.5945478465514338,
      "learning_rate": 5e-06,
      "loss": 0.3097,
      "step": 1750
    },
    {
      "epoch": 3.562753036437247,
      "grad_norm": 1.4266070240229398,
      "learning_rate": 5e-06,
      "loss": 0.3053,
      "step": 1760
    },
    {
      "epoch": 3.582995951417004,
      "grad_norm": 1.5417916459202972,
      "learning_rate": 5e-06,
      "loss": 0.3107,
      "step": 1770
    },
    {
      "epoch": 3.603238866396761,
      "grad_norm": 1.6806576746631992,
      "learning_rate": 5e-06,
      "loss": 0.3077,
      "step": 1780
    },
    {
      "epoch": 3.623481781376518,
      "grad_norm": 1.6366680075861002,
      "learning_rate": 5e-06,
      "loss": 0.3096,
      "step": 1790
    },
    {
      "epoch": 3.6437246963562755,
      "grad_norm": 1.8008610671747132,
      "learning_rate": 5e-06,
      "loss": 0.3095,
      "step": 1800
    },
    {
      "epoch": 3.6639676113360324,
      "grad_norm": 1.7218050046753175,
      "learning_rate": 5e-06,
      "loss": 0.3129,
      "step": 1810
    },
    {
      "epoch": 3.6842105263157894,
      "grad_norm": 1.54966815167092,
      "learning_rate": 5e-06,
      "loss": 0.3089,
      "step": 1820
    },
    {
      "epoch": 3.7044534412955468,
      "grad_norm": 1.5907699518804959,
      "learning_rate": 5e-06,
      "loss": 0.3115,
      "step": 1830
    },
    {
      "epoch": 3.7246963562753037,
      "grad_norm": 1.5950760981279428,
      "learning_rate": 5e-06,
      "loss": 0.3132,
      "step": 1840
    },
    {
      "epoch": 3.7449392712550607,
      "grad_norm": 1.6178462612967588,
      "learning_rate": 5e-06,
      "loss": 0.3112,
      "step": 1850
    },
    {
      "epoch": 3.765182186234818,
      "grad_norm": 1.6595052047937346,
      "learning_rate": 5e-06,
      "loss": 0.3144,
      "step": 1860
    },
    {
      "epoch": 3.785425101214575,
      "grad_norm": 1.5960921622659012,
      "learning_rate": 5e-06,
      "loss": 0.3181,
      "step": 1870
    },
    {
      "epoch": 3.805668016194332,
      "grad_norm": 1.8789757609659636,
      "learning_rate": 5e-06,
      "loss": 0.3128,
      "step": 1880
    },
    {
      "epoch": 3.8259109311740893,
      "grad_norm": 1.6017653115735,
      "learning_rate": 5e-06,
      "loss": 0.318,
      "step": 1890
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 1.4883871110556444,
      "learning_rate": 5e-06,
      "loss": 0.3168,
      "step": 1900
    },
    {
      "epoch": 3.866396761133603,
      "grad_norm": 1.7783804818718214,
      "learning_rate": 5e-06,
      "loss": 0.3114,
      "step": 1910
    },
    {
      "epoch": 3.8866396761133606,
      "grad_norm": 1.7097670030385954,
      "learning_rate": 5e-06,
      "loss": 0.3196,
      "step": 1920
    },
    {
      "epoch": 3.9068825910931175,
      "grad_norm": 1.519954953217676,
      "learning_rate": 5e-06,
      "loss": 0.3161,
      "step": 1930
    },
    {
      "epoch": 3.9271255060728745,
      "grad_norm": 1.5786075983313086,
      "learning_rate": 5e-06,
      "loss": 0.3142,
      "step": 1940
    },
    {
      "epoch": 3.9473684210526314,
      "grad_norm": 1.8339039956017331,
      "learning_rate": 5e-06,
      "loss": 0.3156,
      "step": 1950
    },
    {
      "epoch": 3.967611336032389,
      "grad_norm": 1.504586213513185,
      "learning_rate": 5e-06,
      "loss": 0.3173,
      "step": 1960
    },
    {
      "epoch": 3.9878542510121457,
      "grad_norm": 1.603597507259475,
      "learning_rate": 5e-06,
      "loss": 0.3182,
      "step": 1970
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.3246242105960846,
      "eval_runtime": 128.1021,
      "eval_samples_per_second": 103.855,
      "eval_steps_per_second": 0.406,
      "step": 1976
    },
    {
      "epoch": 4.008097165991903,
      "grad_norm": 5.133136743732594,
      "learning_rate": 5e-06,
      "loss": 0.2774,
      "step": 1980
    },
    {
      "epoch": 4.02834008097166,
      "grad_norm": 2.5228879416463936,
      "learning_rate": 5e-06,
      "loss": 0.2123,
      "step": 1990
    },
    {
      "epoch": 4.048582995951417,
      "grad_norm": 2.0169504998470833,
      "learning_rate": 5e-06,
      "loss": 0.2057,
      "step": 2000
    },
    {
      "epoch": 4.068825910931174,
      "grad_norm": 1.9085723632427691,
      "learning_rate": 5e-06,
      "loss": 0.2061,
      "step": 2010
    },
    {
      "epoch": 4.089068825910931,
      "grad_norm": 1.8551214473550242,
      "learning_rate": 5e-06,
      "loss": 0.2058,
      "step": 2020
    },
    {
      "epoch": 4.109311740890688,
      "grad_norm": 1.8804505495475972,
      "learning_rate": 5e-06,
      "loss": 0.2076,
      "step": 2030
    },
    {
      "epoch": 4.129554655870446,
      "grad_norm": 1.8325377033435544,
      "learning_rate": 5e-06,
      "loss": 0.2055,
      "step": 2040
    },
    {
      "epoch": 4.149797570850202,
      "grad_norm": 1.892921271335565,
      "learning_rate": 5e-06,
      "loss": 0.2073,
      "step": 2050
    },
    {
      "epoch": 4.17004048582996,
      "grad_norm": 2.00985346837552,
      "learning_rate": 5e-06,
      "loss": 0.2084,
      "step": 2060
    },
    {
      "epoch": 4.190283400809717,
      "grad_norm": 1.820158031557001,
      "learning_rate": 5e-06,
      "loss": 0.209,
      "step": 2070
    },
    {
      "epoch": 4.2105263157894735,
      "grad_norm": 1.8327459405866524,
      "learning_rate": 5e-06,
      "loss": 0.2127,
      "step": 2080
    },
    {
      "epoch": 4.230769230769231,
      "grad_norm": 1.9394580410768052,
      "learning_rate": 5e-06,
      "loss": 0.2123,
      "step": 2090
    },
    {
      "epoch": 4.251012145748988,
      "grad_norm": 1.9657450113344472,
      "learning_rate": 5e-06,
      "loss": 0.2108,
      "step": 2100
    },
    {
      "epoch": 4.271255060728745,
      "grad_norm": 1.949924211787456,
      "learning_rate": 5e-06,
      "loss": 0.2139,
      "step": 2110
    },
    {
      "epoch": 4.291497975708502,
      "grad_norm": 1.8700037789000614,
      "learning_rate": 5e-06,
      "loss": 0.2146,
      "step": 2120
    },
    {
      "epoch": 4.3117408906882595,
      "grad_norm": 1.8948956761363887,
      "learning_rate": 5e-06,
      "loss": 0.2145,
      "step": 2130
    },
    {
      "epoch": 4.331983805668016,
      "grad_norm": 2.183456888675007,
      "learning_rate": 5e-06,
      "loss": 0.2168,
      "step": 2140
    },
    {
      "epoch": 4.352226720647773,
      "grad_norm": 2.01397562728079,
      "learning_rate": 5e-06,
      "loss": 0.2151,
      "step": 2150
    },
    {
      "epoch": 4.372469635627531,
      "grad_norm": 2.1466988238739697,
      "learning_rate": 5e-06,
      "loss": 0.2148,
      "step": 2160
    },
    {
      "epoch": 4.392712550607287,
      "grad_norm": 1.8790514185213776,
      "learning_rate": 5e-06,
      "loss": 0.2159,
      "step": 2170
    },
    {
      "epoch": 4.412955465587045,
      "grad_norm": 1.9845491426747,
      "learning_rate": 5e-06,
      "loss": 0.2179,
      "step": 2180
    },
    {
      "epoch": 4.433198380566802,
      "grad_norm": 1.9657898682355717,
      "learning_rate": 5e-06,
      "loss": 0.2173,
      "step": 2190
    },
    {
      "epoch": 4.4534412955465585,
      "grad_norm": 1.8874931048307386,
      "learning_rate": 5e-06,
      "loss": 0.2156,
      "step": 2200
    },
    {
      "epoch": 4.473684210526316,
      "grad_norm": 1.845963836099471,
      "learning_rate": 5e-06,
      "loss": 0.2188,
      "step": 2210
    },
    {
      "epoch": 4.493927125506072,
      "grad_norm": 1.9372215749139772,
      "learning_rate": 5e-06,
      "loss": 0.2191,
      "step": 2220
    },
    {
      "epoch": 4.51417004048583,
      "grad_norm": 2.150693124788377,
      "learning_rate": 5e-06,
      "loss": 0.2201,
      "step": 2230
    },
    {
      "epoch": 4.534412955465587,
      "grad_norm": 2.0442818699824317,
      "learning_rate": 5e-06,
      "loss": 0.22,
      "step": 2240
    },
    {
      "epoch": 4.554655870445345,
      "grad_norm": 1.9514620437414862,
      "learning_rate": 5e-06,
      "loss": 0.2185,
      "step": 2250
    },
    {
      "epoch": 4.574898785425101,
      "grad_norm": 1.8963967573781124,
      "learning_rate": 5e-06,
      "loss": 0.2213,
      "step": 2260
    },
    {
      "epoch": 4.5951417004048585,
      "grad_norm": 1.8526961706560494,
      "learning_rate": 5e-06,
      "loss": 0.2221,
      "step": 2270
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 1.9821664496420446,
      "learning_rate": 5e-06,
      "loss": 0.2214,
      "step": 2280
    },
    {
      "epoch": 4.635627530364372,
      "grad_norm": 1.915513929466144,
      "learning_rate": 5e-06,
      "loss": 0.2237,
      "step": 2290
    },
    {
      "epoch": 4.65587044534413,
      "grad_norm": 1.8762006846363004,
      "learning_rate": 5e-06,
      "loss": 0.2249,
      "step": 2300
    },
    {
      "epoch": 4.676113360323887,
      "grad_norm": 1.9227849786208417,
      "learning_rate": 5e-06,
      "loss": 0.2265,
      "step": 2310
    },
    {
      "epoch": 4.696356275303644,
      "grad_norm": 1.9572380827157467,
      "learning_rate": 5e-06,
      "loss": 0.2265,
      "step": 2320
    },
    {
      "epoch": 4.716599190283401,
      "grad_norm": 1.8826393602367635,
      "learning_rate": 5e-06,
      "loss": 0.2252,
      "step": 2330
    },
    {
      "epoch": 4.7368421052631575,
      "grad_norm": 1.825743956937918,
      "learning_rate": 5e-06,
      "loss": 0.2234,
      "step": 2340
    },
    {
      "epoch": 4.757085020242915,
      "grad_norm": 2.194102804306542,
      "learning_rate": 5e-06,
      "loss": 0.2243,
      "step": 2350
    },
    {
      "epoch": 4.777327935222672,
      "grad_norm": 1.8765617982862395,
      "learning_rate": 5e-06,
      "loss": 0.2246,
      "step": 2360
    },
    {
      "epoch": 4.797570850202429,
      "grad_norm": 1.8687466226351828,
      "learning_rate": 5e-06,
      "loss": 0.2276,
      "step": 2370
    },
    {
      "epoch": 4.817813765182186,
      "grad_norm": 1.7759017848087686,
      "learning_rate": 5e-06,
      "loss": 0.2257,
      "step": 2380
    },
    {
      "epoch": 4.838056680161944,
      "grad_norm": 1.8906492602012772,
      "learning_rate": 5e-06,
      "loss": 0.2253,
      "step": 2390
    },
    {
      "epoch": 4.8582995951417,
      "grad_norm": 2.050008885412097,
      "learning_rate": 5e-06,
      "loss": 0.2294,
      "step": 2400
    },
    {
      "epoch": 4.8785425101214575,
      "grad_norm": 1.9449950754235916,
      "learning_rate": 5e-06,
      "loss": 0.2307,
      "step": 2410
    },
    {
      "epoch": 4.898785425101215,
      "grad_norm": 1.866407529076546,
      "learning_rate": 5e-06,
      "loss": 0.2293,
      "step": 2420
    },
    {
      "epoch": 4.919028340080971,
      "grad_norm": 1.9434490467739143,
      "learning_rate": 5e-06,
      "loss": 0.2285,
      "step": 2430
    },
    {
      "epoch": 4.939271255060729,
      "grad_norm": 1.9646396229024239,
      "learning_rate": 5e-06,
      "loss": 0.2306,
      "step": 2440
    },
    {
      "epoch": 4.959514170040486,
      "grad_norm": 1.8683726614276728,
      "learning_rate": 5e-06,
      "loss": 0.2277,
      "step": 2450
    },
    {
      "epoch": 4.979757085020243,
      "grad_norm": 1.984199504770925,
      "learning_rate": 5e-06,
      "loss": 0.2312,
      "step": 2460
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.8362584513440876,
      "learning_rate": 5e-06,
      "loss": 0.2292,
      "step": 2470
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.37886306643486023,
      "eval_runtime": 128.1269,
      "eval_samples_per_second": 103.835,
      "eval_steps_per_second": 0.406,
      "step": 2470
    },
    {
      "epoch": 5.0,
      "step": 2470,
      "total_flos": 4136504477614080.0,
      "train_loss": 0.39363470135430095,
      "train_runtime": 36289.8965,
      "train_samples_per_second": 34.825,
      "train_steps_per_second": 0.068
    }
  ],
  "logging_steps": 10,
  "max_steps": 2470,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4136504477614080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}