{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.934950385887541,
  "eval_steps": 50,
  "global_step": 3360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01470047776552738,
      "grad_norm": 0.5667821168899536,
      "learning_rate": 0.0003,
      "loss": 14.1829,
      "step": 10
    },
    {
      "epoch": 0.02940095553105476,
      "grad_norm": 0.34381482005119324,
      "learning_rate": 0.0002995581737849779,
      "loss": 10.6392,
      "step": 20
    },
    {
      "epoch": 0.044101433296582136,
      "grad_norm": 0.4359741806983948,
      "learning_rate": 0.00029911634756995577,
      "loss": 9.822,
      "step": 30
    },
    {
      "epoch": 0.05880191106210952,
      "grad_norm": 0.4812168478965759,
      "learning_rate": 0.0002986745213549337,
      "loss": 9.5543,
      "step": 40
    },
    {
      "epoch": 0.07350238882763689,
      "grad_norm": 0.5038645267486572,
      "learning_rate": 0.0002982326951399116,
      "loss": 9.2649,
      "step": 50
    },
    {
      "epoch": 0.07350238882763689,
      "eval_loss": 1.1481549739837646,
      "eval_runtime": 122.7544,
      "eval_samples_per_second": 7.079,
      "eval_steps_per_second": 0.888,
      "step": 50
    },
    {
      "epoch": 0.08820286659316427,
      "grad_norm": 0.5140169858932495,
      "learning_rate": 0.00029779086892488954,
      "loss": 9.0792,
      "step": 60
    },
    {
      "epoch": 0.10290334435869165,
      "grad_norm": 0.5402693152427673,
      "learning_rate": 0.0002973490427098674,
      "loss": 8.9419,
      "step": 70
    },
    {
      "epoch": 0.11760382212421903,
      "grad_norm": 0.5764286518096924,
      "learning_rate": 0.00029690721649484533,
      "loss": 8.8216,
      "step": 80
    },
    {
      "epoch": 0.13230429988974643,
      "grad_norm": 0.5907140374183655,
      "learning_rate": 0.00029646539027982326,
      "loss": 8.7672,
      "step": 90
    },
    {
      "epoch": 0.14700477765527378,
      "grad_norm": 0.6670350432395935,
      "learning_rate": 0.0002960235640648012,
      "loss": 8.6517,
      "step": 100
    },
    {
      "epoch": 0.14700477765527378,
      "eval_loss": 1.0773104429244995,
      "eval_runtime": 122.6477,
      "eval_samples_per_second": 7.085,
      "eval_steps_per_second": 0.889,
      "step": 100
    },
    {
      "epoch": 0.16170525542080116,
      "grad_norm": 0.6163733601570129,
      "learning_rate": 0.00029558173784977905,
      "loss": 8.514,
      "step": 110
    },
    {
      "epoch": 0.17640573318632854,
      "grad_norm": 0.6671579480171204,
      "learning_rate": 0.000295139911634757,
      "loss": 8.453,
      "step": 120
    },
    {
      "epoch": 0.19110621095185593,
      "grad_norm": 0.6266494989395142,
      "learning_rate": 0.00029469808541973485,
      "loss": 8.432,
      "step": 130
    },
    {
      "epoch": 0.2058066887173833,
      "grad_norm": 0.6384584307670593,
      "learning_rate": 0.00029425625920471277,
      "loss": 8.4165,
      "step": 140
    },
    {
      "epoch": 0.2205071664829107,
      "grad_norm": 0.6454419493675232,
      "learning_rate": 0.0002938144329896907,
      "loss": 8.3296,
      "step": 150
    },
    {
      "epoch": 0.2205071664829107,
      "eval_loss": 1.0390021800994873,
      "eval_runtime": 122.6855,
      "eval_samples_per_second": 7.083,
      "eval_steps_per_second": 0.888,
      "step": 150
    },
    {
      "epoch": 0.23520764424843807,
      "grad_norm": 0.7196301817893982,
      "learning_rate": 0.0002933726067746686,
      "loss": 8.3398,
      "step": 160
    },
    {
      "epoch": 0.24990812201396545,
      "grad_norm": 0.6549277305603027,
      "learning_rate": 0.0002929307805596465,
      "loss": 8.2129,
      "step": 170
    },
    {
      "epoch": 0.26460859977949286,
      "grad_norm": 0.7620148062705994,
      "learning_rate": 0.0002924889543446244,
      "loss": 8.1606,
      "step": 180
    },
    {
      "epoch": 0.2793090775450202,
      "grad_norm": 0.7137699723243713,
      "learning_rate": 0.00029204712812960234,
      "loss": 8.149,
      "step": 190
    },
    {
      "epoch": 0.29400955531054757,
      "grad_norm": 0.8829444050788879,
      "learning_rate": 0.00029160530191458026,
      "loss": 8.1411,
      "step": 200
    },
    {
      "epoch": 0.29400955531054757,
      "eval_loss": 1.013519048690796,
      "eval_runtime": 122.7693,
      "eval_samples_per_second": 7.078,
      "eval_steps_per_second": 0.888,
      "step": 200
    },
    {
      "epoch": 0.308710033076075,
      "grad_norm": 0.7682989239692688,
      "learning_rate": 0.00029116347569955813,
      "loss": 8.0776,
      "step": 210
    },
    {
      "epoch": 0.32341051084160233,
      "grad_norm": 0.7389448285102844,
      "learning_rate": 0.00029072164948453606,
      "loss": 8.0282,
      "step": 220
    },
    {
      "epoch": 0.33811098860712974,
      "grad_norm": 0.6548839211463928,
      "learning_rate": 0.000290279823269514,
      "loss": 7.9301,
      "step": 230
    },
    {
      "epoch": 0.3528114663726571,
      "grad_norm": 0.6590954065322876,
      "learning_rate": 0.0002898379970544919,
      "loss": 7.9751,
      "step": 240
    },
    {
      "epoch": 0.3675119441381845,
      "grad_norm": 0.6717875003814697,
      "learning_rate": 0.0002893961708394698,
      "loss": 7.9119,
      "step": 250
    },
    {
      "epoch": 0.3675119441381845,
      "eval_loss": 0.9925356507301331,
      "eval_runtime": 122.9342,
      "eval_samples_per_second": 7.069,
      "eval_steps_per_second": 0.887,
      "step": 250
    },
    {
      "epoch": 0.38221242190371185,
      "grad_norm": 0.7246499061584473,
      "learning_rate": 0.0002889543446244477,
      "loss": 7.967,
      "step": 260
    },
    {
      "epoch": 0.39691289966923926,
      "grad_norm": 0.6811556220054626,
      "learning_rate": 0.0002885125184094256,
      "loss": 7.8876,
      "step": 270
    },
    {
      "epoch": 0.4116133774347666,
      "grad_norm": 0.6982465386390686,
      "learning_rate": 0.0002880706921944035,
      "loss": 7.7926,
      "step": 280
    },
    {
      "epoch": 0.426313855200294,
      "grad_norm": 0.7146357893943787,
      "learning_rate": 0.0002876288659793814,
      "loss": 7.8198,
      "step": 290
    },
    {
      "epoch": 0.4410143329658214,
      "grad_norm": 0.6905196309089661,
      "learning_rate": 0.00028718703976435934,
      "loss": 7.8613,
      "step": 300
    },
    {
      "epoch": 0.4410143329658214,
      "eval_loss": 0.9757246971130371,
      "eval_runtime": 122.6633,
      "eval_samples_per_second": 7.084,
      "eval_steps_per_second": 0.889,
      "step": 300
    },
    {
      "epoch": 0.4557148107313488,
      "grad_norm": 0.7458569407463074,
      "learning_rate": 0.00028674521354933726,
      "loss": 7.753,
      "step": 310
    },
    {
      "epoch": 0.47041528849687614,
      "grad_norm": 0.6701686382293701,
      "learning_rate": 0.00028630338733431513,
      "loss": 7.7493,
      "step": 320
    },
    {
      "epoch": 0.48511576626240355,
      "grad_norm": 0.6544702053070068,
      "learning_rate": 0.00028586156111929306,
      "loss": 7.7707,
      "step": 330
    },
    {
      "epoch": 0.4998162440279309,
      "grad_norm": 0.7933269739151001,
      "learning_rate": 0.00028541973490427093,
      "loss": 7.6491,
      "step": 340
    },
    {
      "epoch": 0.5145167217934583,
      "grad_norm": 0.9241804480552673,
      "learning_rate": 0.00028497790868924885,
      "loss": 7.654,
      "step": 350
    },
    {
      "epoch": 0.5145167217934583,
      "eval_loss": 0.9614924788475037,
      "eval_runtime": 122.7436,
      "eval_samples_per_second": 7.08,
      "eval_steps_per_second": 0.888,
      "step": 350
    },
    {
      "epoch": 0.5292171995589857,
      "grad_norm": 0.7038714289665222,
      "learning_rate": 0.0002845360824742268,
      "loss": 7.6464,
      "step": 360
    },
    {
      "epoch": 0.543917677324513,
      "grad_norm": 0.6981613636016846,
      "learning_rate": 0.0002840942562592047,
      "loss": 7.7035,
      "step": 370
    },
    {
      "epoch": 0.5586181550900404,
      "grad_norm": 0.7330546379089355,
      "learning_rate": 0.00028365243004418257,
      "loss": 7.5588,
      "step": 380
    },
    {
      "epoch": 0.5733186328555678,
      "grad_norm": 0.7032233476638794,
      "learning_rate": 0.0002832106038291605,
      "loss": 7.558,
      "step": 390
    },
    {
      "epoch": 0.5880191106210951,
      "grad_norm": 0.6604267358779907,
      "learning_rate": 0.0002827687776141384,
      "loss": 7.5529,
      "step": 400
    },
    {
      "epoch": 0.5880191106210951,
      "eval_loss": 0.9492942094802856,
      "eval_runtime": 122.7734,
      "eval_samples_per_second": 7.078,
      "eval_steps_per_second": 0.888,
      "step": 400
    },
    {
      "epoch": 0.6027195883866225,
      "grad_norm": 0.6671615839004517,
      "learning_rate": 0.00028232695139911634,
      "loss": 7.5444,
      "step": 410
    },
    {
      "epoch": 0.61742006615215,
      "grad_norm": 0.8184302449226379,
      "learning_rate": 0.0002818851251840942,
      "loss": 7.55,
      "step": 420
    },
    {
      "epoch": 0.6321205439176774,
      "grad_norm": 0.7789945006370544,
      "learning_rate": 0.00028144329896907214,
      "loss": 7.5528,
      "step": 430
    },
    {
      "epoch": 0.6468210216832047,
      "grad_norm": 0.6673751473426819,
      "learning_rate": 0.00028100147275405006,
      "loss": 7.5363,
      "step": 440
    },
    {
      "epoch": 0.6615214994487321,
      "grad_norm": 0.6923938989639282,
      "learning_rate": 0.000280559646539028,
      "loss": 7.4971,
      "step": 450
    },
    {
      "epoch": 0.6615214994487321,
      "eval_loss": 0.9389350414276123,
      "eval_runtime": 122.7652,
      "eval_samples_per_second": 7.079,
      "eval_steps_per_second": 0.888,
      "step": 450
    },
    {
      "epoch": 0.6762219772142595,
      "grad_norm": 0.7583535313606262,
      "learning_rate": 0.00028011782032400586,
      "loss": 7.5674,
      "step": 460
    },
    {
      "epoch": 0.6909224549797869,
      "grad_norm": 0.8926804065704346,
      "learning_rate": 0.0002796759941089838,
      "loss": 7.494,
      "step": 470
    },
    {
      "epoch": 0.7056229327453142,
      "grad_norm": 0.6774755716323853,
      "learning_rate": 0.0002792341678939617,
      "loss": 7.4429,
      "step": 480
    },
    {
      "epoch": 0.7203234105108416,
      "grad_norm": 0.7251358032226562,
      "learning_rate": 0.00027879234167893963,
      "loss": 7.4177,
      "step": 490
    },
    {
      "epoch": 0.735023888276369,
      "grad_norm": 0.7453545928001404,
      "learning_rate": 0.0002783505154639175,
      "loss": 7.4214,
      "step": 500
    },
    {
      "epoch": 0.735023888276369,
      "eval_loss": 0.9294928312301636,
      "eval_runtime": 122.745,
      "eval_samples_per_second": 7.08,
      "eval_steps_per_second": 0.888,
      "step": 500
    },
    {
      "epoch": 0.7497243660418964,
      "grad_norm": 0.7907696962356567,
      "learning_rate": 0.0002779086892488954,
      "loss": 7.4205,
      "step": 510
    },
    {
      "epoch": 0.7644248438074237,
      "grad_norm": 0.8346834182739258,
      "learning_rate": 0.00027746686303387335,
      "loss": 7.3813,
      "step": 520
    },
    {
      "epoch": 0.7791253215729511,
      "grad_norm": 0.6804636120796204,
      "learning_rate": 0.0002770250368188512,
      "loss": 7.381,
      "step": 530
    },
    {
      "epoch": 0.7938257993384785,
      "grad_norm": 0.6866320371627808,
      "learning_rate": 0.00027658321060382914,
      "loss": 7.3764,
      "step": 540
    },
    {
      "epoch": 0.8085262771040059,
      "grad_norm": 0.669920027256012,
      "learning_rate": 0.000276141384388807,
      "loss": 7.3525,
      "step": 550
    },
    {
      "epoch": 0.8085262771040059,
      "eval_loss": 0.9208266735076904,
      "eval_runtime": 122.7608,
      "eval_samples_per_second": 7.079,
      "eval_steps_per_second": 0.888,
      "step": 550
    },
    {
      "epoch": 0.8232267548695332,
      "grad_norm": 0.6660575866699219,
      "learning_rate": 0.00027569955817378493,
      "loss": 7.3205,
      "step": 560
    },
    {
      "epoch": 0.8379272326350606,
      "grad_norm": 0.6585595011711121,
      "learning_rate": 0.00027525773195876286,
      "loss": 7.3378,
      "step": 570
    },
    {
      "epoch": 0.852627710400588,
      "grad_norm": 0.6798352003097534,
      "learning_rate": 0.0002748159057437408,
      "loss": 7.3742,
      "step": 580
    },
    {
      "epoch": 0.8673281881661153,
      "grad_norm": 0.6834390759468079,
      "learning_rate": 0.00027437407952871865,
      "loss": 7.3129,
      "step": 590
    },
    {
      "epoch": 0.8820286659316428,
      "grad_norm": 0.6835374236106873,
      "learning_rate": 0.0002739322533136966,
      "loss": 7.3155,
      "step": 600
    },
    {
      "epoch": 0.8820286659316428,
      "eval_loss": 0.914364218711853,
      "eval_runtime": 122.6825,
      "eval_samples_per_second": 7.083,
      "eval_steps_per_second": 0.888,
      "step": 600
    },
    {
      "epoch": 0.8967291436971702,
      "grad_norm": 0.6754274368286133,
      "learning_rate": 0.0002734904270986745,
      "loss": 7.2469,
      "step": 610
    },
    {
      "epoch": 0.9114296214626976,
      "grad_norm": 0.685310959815979,
      "learning_rate": 0.0002730486008836524,
      "loss": 7.2842,
      "step": 620
    },
    {
      "epoch": 0.9261300992282249,
      "grad_norm": 0.6500253081321716,
      "learning_rate": 0.0002726067746686303,
      "loss": 7.2391,
      "step": 630
    },
    {
      "epoch": 0.9408305769937523,
      "grad_norm": 0.6883764863014221,
      "learning_rate": 0.0002721649484536082,
      "loss": 7.2422,
      "step": 640
    },
    {
      "epoch": 0.9555310547592797,
      "grad_norm": 0.6952683329582214,
      "learning_rate": 0.00027172312223858614,
      "loss": 7.2299,
      "step": 650
    },
    {
      "epoch": 0.9555310547592797,
      "eval_loss": 0.9077203273773193,
      "eval_runtime": 122.8456,
      "eval_samples_per_second": 7.074,
      "eval_steps_per_second": 0.887,
      "step": 650
    },
    {
      "epoch": 0.9702315325248071,
      "grad_norm": 0.689813494682312,
      "learning_rate": 0.00027128129602356407,
      "loss": 7.195,
      "step": 660
    },
    {
      "epoch": 0.9849320102903344,
      "grad_norm": 0.7432010173797607,
      "learning_rate": 0.00027083946980854194,
      "loss": 7.2269,
      "step": 670
    },
    {
      "epoch": 0.9996324880558618,
      "grad_norm": 0.6559237837791443,
      "learning_rate": 0.00027039764359351986,
      "loss": 7.2033,
      "step": 680
    },
    {
      "epoch": 1.0132304299889747,
      "grad_norm": 0.6594626307487488,
      "learning_rate": 0.0002699558173784978,
      "loss": 6.3891,
      "step": 690
    },
    {
      "epoch": 1.027930907754502,
      "grad_norm": 0.7604880928993225,
      "learning_rate": 0.0002695139911634757,
      "loss": 6.9323,
      "step": 700
    },
    {
      "epoch": 1.027930907754502,
      "eval_loss": 0.9017989039421082,
      "eval_runtime": 122.7598,
      "eval_samples_per_second": 7.079,
      "eval_steps_per_second": 0.888,
      "step": 700
    },
    {
      "epoch": 1.0426313855200293,
      "grad_norm": 0.6518153548240662,
      "learning_rate": 0.0002690721649484536,
      "loss": 6.8683,
      "step": 710
    },
    {
      "epoch": 1.0573318632855568,
      "grad_norm": 0.6659955978393555,
      "learning_rate": 0.0002686303387334315,
      "loss": 6.8752,
      "step": 720
    },
    {
      "epoch": 1.0720323410510841,
      "grad_norm": 0.6533622145652771,
      "learning_rate": 0.00026818851251840943,
      "loss": 6.9249,
      "step": 730
    },
    {
      "epoch": 1.0867328188166114,
      "grad_norm": 0.6731697916984558,
      "learning_rate": 0.00026774668630338735,
      "loss": 6.8896,
      "step": 740
    },
    {
      "epoch": 1.101433296582139,
      "grad_norm": 0.6576088070869446,
      "learning_rate": 0.0002673048600883652,
      "loss": 6.9015,
      "step": 750
    },
    {
      "epoch": 1.101433296582139,
      "eval_loss": 0.8985611200332642,
      "eval_runtime": 122.7501,
      "eval_samples_per_second": 7.079,
      "eval_steps_per_second": 0.888,
      "step": 750
    },
    {
      "epoch": 1.1161337743476663,
      "grad_norm": 0.6596420407295227,
      "learning_rate": 0.0002668630338733431,
      "loss": 6.9081,
      "step": 760
    },
    {
      "epoch": 1.1308342521131938,
      "grad_norm": 0.6679617762565613,
      "learning_rate": 0.000266421207658321,
      "loss": 6.8619,
      "step": 770
    },
    {
      "epoch": 1.145534729878721,
      "grad_norm": 0.6485927700996399,
      "learning_rate": 0.00026597938144329894,
      "loss": 6.9068,
      "step": 780
    },
    {
      "epoch": 1.1602352076442484,
      "grad_norm": 0.679757297039032,
      "learning_rate": 0.00026553755522827686,
      "loss": 6.9091,
      "step": 790
    },
    {
      "epoch": 1.1749356854097759,
      "grad_norm": 0.7027860879898071,
      "learning_rate": 0.00026509572901325473,
      "loss": 6.9184,
      "step": 800
    },
    {
      "epoch": 1.1749356854097759,
      "eval_loss": 0.8939267992973328,
      "eval_runtime": 122.7304,
      "eval_samples_per_second": 7.081,
      "eval_steps_per_second": 0.888,
      "step": 800
    },
    {
      "epoch": 1.1896361631753032,
      "grad_norm": 0.651599645614624,
      "learning_rate": 0.00026465390279823266,
      "loss": 6.8758,
      "step": 810
    },
    {
      "epoch": 1.2043366409408305,
      "grad_norm": 0.6500714421272278,
      "learning_rate": 0.0002642120765832106,
      "loss": 6.8177,
      "step": 820
    },
    {
      "epoch": 1.219037118706358,
      "grad_norm": 0.7008342146873474,
      "learning_rate": 0.0002637702503681885,
      "loss": 6.8862,
      "step": 830
    },
    {
      "epoch": 1.2337375964718853,
      "grad_norm": 0.6531012058258057,
      "learning_rate": 0.0002633284241531664,
      "loss": 6.8651,
      "step": 840
    },
    {
      "epoch": 1.2484380742374128,
      "grad_norm": 0.6673538684844971,
      "learning_rate": 0.0002628865979381443,
      "loss": 6.8483,
      "step": 850
    },
    {
      "epoch": 1.2484380742374128,
      "eval_loss": 0.8902646899223328,
      "eval_runtime": 122.8026,
      "eval_samples_per_second": 7.076,
      "eval_steps_per_second": 0.888,
      "step": 850
    },
    {
      "epoch": 1.2631385520029401,
      "grad_norm": 0.6538046002388,
      "learning_rate": 0.0002624447717231222,
      "loss": 6.8312,
      "step": 860
    },
    {
      "epoch": 1.2778390297684674,
      "grad_norm": 0.7091453671455383,
      "learning_rate": 0.00026200294550810015,
      "loss": 6.8254,
      "step": 870
    },
    {
      "epoch": 1.292539507533995,
      "grad_norm": 0.6591873168945312,
      "learning_rate": 0.000261561119293078,
      "loss": 6.8611,
      "step": 880
    },
    {
      "epoch": 1.3072399852995222,
      "grad_norm": 0.6869573593139648,
      "learning_rate": 0.00026111929307805594,
      "loss": 6.8559,
      "step": 890
    },
    {
      "epoch": 1.3219404630650495,
      "grad_norm": 0.6487476229667664,
      "learning_rate": 0.00026067746686303387,
      "loss": 6.841,
      "step": 900
    },
    {
      "epoch": 1.3219404630650495,
      "eval_loss": 0.8851333260536194,
      "eval_runtime": 122.7209,
      "eval_samples_per_second": 7.081,
      "eval_steps_per_second": 0.888,
      "step": 900
    },
    {
      "epoch": 1.336640940830577,
      "grad_norm": 0.957991361618042,
      "learning_rate": 0.0002602356406480118,
      "loss": 6.8572,
      "step": 910
    },
    {
      "epoch": 1.3513414185961043,
      "grad_norm": 0.6700526475906372,
      "learning_rate": 0.00025979381443298966,
      "loss": 6.8354,
      "step": 920
    },
    {
      "epoch": 1.3660418963616316,
      "grad_norm": 0.6402295827865601,
      "learning_rate": 0.0002593519882179676,
      "loss": 6.7743,
      "step": 930
    },
    {
      "epoch": 1.3807423741271592,
      "grad_norm": 0.6479661464691162,
      "learning_rate": 0.0002589101620029455,
      "loss": 6.8425,
      "step": 940
    },
    {
      "epoch": 1.3954428518926865,
      "grad_norm": 0.638687789440155,
      "learning_rate": 0.00025846833578792343,
      "loss": 6.8481,
      "step": 950
    },
    {
      "epoch": 1.3954428518926865,
      "eval_loss": 0.881273627281189,
      "eval_runtime": 122.7019,
      "eval_samples_per_second": 7.082,
      "eval_steps_per_second": 0.888,
      "step": 950
    },
    {
      "epoch": 1.4101433296582138,
      "grad_norm": 0.6479136347770691,
      "learning_rate": 0.0002580265095729013,
      "loss": 6.851,
      "step": 960
    },
    {
      "epoch": 1.4248438074237413,
      "grad_norm": 0.6393547654151917,
      "learning_rate": 0.0002575846833578792,
      "loss": 6.7861,
      "step": 970
    },
    {
      "epoch": 1.4395442851892686,
      "grad_norm": 0.6324586272239685,
      "learning_rate": 0.0002571428571428571,
      "loss": 6.8184,
      "step": 980
    },
    {
      "epoch": 1.454244762954796,
      "grad_norm": 0.6082057952880859,
      "learning_rate": 0.000256701030927835,
      "loss": 6.7677,
      "step": 990
    },
    {
      "epoch": 1.4689452407203234,
      "grad_norm": 0.6476999521255493,
      "learning_rate": 0.00025625920471281295,
      "loss": 6.846,
      "step": 1000
    },
    {
      "epoch": 1.4689452407203234,
      "eval_loss": 0.877618134021759,
      "eval_runtime": 122.7086,
      "eval_samples_per_second": 7.082,
      "eval_steps_per_second": 0.888,
      "step": 1000
    },
    {
      "epoch": 1.483645718485851,
      "grad_norm": 0.6280727386474609,
      "learning_rate": 0.0002558173784977908,
      "loss": 6.785,
      "step": 1010
    },
    {
      "epoch": 1.4983461962513782,
      "grad_norm": 0.6497882604598999,
      "learning_rate": 0.00025537555228276874,
      "loss": 6.7953,
      "step": 1020
    },
    {
      "epoch": 1.5130466740169055,
      "grad_norm": 0.6304103136062622,
      "learning_rate": 0.00025493372606774666,
      "loss": 6.7844,
      "step": 1030
    },
    {
      "epoch": 1.527747151782433,
      "grad_norm": 0.6390955448150635,
      "learning_rate": 0.0002544918998527246,
      "loss": 6.8057,
      "step": 1040
    },
    {
      "epoch": 1.5424476295479603,
      "grad_norm": 0.6420630812644958,
      "learning_rate": 0.00025405007363770246,
      "loss": 6.772,
      "step": 1050
    },
    {
      "epoch": 1.5424476295479603,
      "eval_loss": 0.8740328550338745,
      "eval_runtime": 122.7668,
      "eval_samples_per_second": 7.078,
      "eval_steps_per_second": 0.888,
      "step": 1050
    },
    {
      "epoch": 1.5571481073134876,
      "grad_norm": 0.6527525186538696,
      "learning_rate": 0.0002536082474226804,
      "loss": 6.7597,
      "step": 1060
    },
    {
      "epoch": 1.5718485850790151,
      "grad_norm": 0.63811856508255,
      "learning_rate": 0.0002531664212076583,
      "loss": 6.7273,
      "step": 1070
    },
    {
      "epoch": 1.5865490628445424,
      "grad_norm": 0.6332401037216187,
      "learning_rate": 0.00025272459499263623,
      "loss": 6.7035,
      "step": 1080
    },
    {
      "epoch": 1.6012495406100697,
      "grad_norm": 0.631254255771637,
      "learning_rate": 0.0002522827687776141,
      "loss": 6.7374,
      "step": 1090
    },
    {
      "epoch": 1.6159500183755973,
      "grad_norm": 0.5980453491210938,
      "learning_rate": 0.000251840942562592,
      "loss": 6.7379,
      "step": 1100
    },
    {
      "epoch": 1.6159500183755973,
      "eval_loss": 0.8703284859657288,
      "eval_runtime": 122.7173,
      "eval_samples_per_second": 7.081,
      "eval_steps_per_second": 0.888,
      "step": 1100
    },
    {
      "epoch": 1.6306504961411246,
      "grad_norm": 0.6735087633132935,
      "learning_rate": 0.00025139911634756995,
      "loss": 6.729,
      "step": 1110
    },
    {
      "epoch": 1.6453509739066519,
      "grad_norm": 0.629978597164154,
      "learning_rate": 0.00025095729013254787,
      "loss": 6.7366,
      "step": 1120
    },
    {
      "epoch": 1.6600514516721794,
      "grad_norm": 0.6302997469902039,
      "learning_rate": 0.00025051546391752574,
      "loss": 6.743,
      "step": 1130
    },
    {
      "epoch": 1.6747519294377067,
      "grad_norm": 0.6438983082771301,
      "learning_rate": 0.00025007363770250367,
      "loss": 6.7066,
      "step": 1140
    },
    {
      "epoch": 1.689452407203234,
      "grad_norm": 0.6278811097145081,
      "learning_rate": 0.0002496318114874816,
      "loss": 6.7407,
      "step": 1150
    },
    {
      "epoch": 1.689452407203234,
      "eval_loss": 0.8671343922615051,
      "eval_runtime": 122.7608,
      "eval_samples_per_second": 7.079,
      "eval_steps_per_second": 0.888,
      "step": 1150
    },
    {
      "epoch": 1.7041528849687615,
      "grad_norm": 0.625558614730835,
      "learning_rate": 0.0002491899852724595,
      "loss": 6.7356,
      "step": 1160
    },
    {
      "epoch": 1.718853362734289,
      "grad_norm": 0.6096333861351013,
      "learning_rate": 0.0002487481590574374,
      "loss": 6.7057,
      "step": 1170
    },
    {
      "epoch": 1.733553840499816,
      "grad_norm": 0.619067370891571,
      "learning_rate": 0.00024830633284241525,
      "loss": 6.6987,
      "step": 1180
    },
    {
      "epoch": 1.7482543182653436,
      "grad_norm": 0.6105065941810608,
      "learning_rate": 0.0002478645066273932,
      "loss": 6.6905,
      "step": 1190
    },
    {
      "epoch": 1.7629547960308711,
      "grad_norm": 0.6466421484947205,
      "learning_rate": 0.0002474226804123711,
      "loss": 6.714,
      "step": 1200
    },
    {
      "epoch": 1.7629547960308711,
      "eval_loss": 0.8641793131828308,
      "eval_runtime": 122.7219,
      "eval_samples_per_second": 7.081,
      "eval_steps_per_second": 0.888,
      "step": 1200
    },
    {
      "epoch": 1.7776552737963984,
      "grad_norm": 0.6360054612159729,
      "learning_rate": 0.000246980854197349,
      "loss": 6.7256,
      "step": 1210
    },
    {
      "epoch": 1.7923557515619257,
      "grad_norm": 0.604234516620636,
      "learning_rate": 0.0002465390279823269,
      "loss": 6.7378,
      "step": 1220
    },
    {
      "epoch": 1.8070562293274532,
      "grad_norm": 0.5942307710647583,
      "learning_rate": 0.0002460972017673048,
      "loss": 6.6839,
      "step": 1230
    },
    {
      "epoch": 1.8217567070929805,
      "grad_norm": 0.6054413318634033,
      "learning_rate": 0.00024565537555228275,
      "loss": 6.6793,
      "step": 1240
    },
    {
      "epoch": 1.8364571848585078,
      "grad_norm": 0.6159862279891968,
      "learning_rate": 0.00024521354933726067,
      "loss": 6.7124,
      "step": 1250
    },
    {
      "epoch": 1.8364571848585078,
      "eval_loss": 0.8611465096473694,
      "eval_runtime": 122.7049,
      "eval_samples_per_second": 7.082,
      "eval_steps_per_second": 0.888,
      "step": 1250
    },
    {
      "epoch": 1.8511576626240354,
      "grad_norm": 0.6350423693656921,
      "learning_rate": 0.00024477172312223854,
      "loss": 6.6738,
      "step": 1260
    },
    {
      "epoch": 1.8658581403895627,
      "grad_norm": 0.6083235740661621,
      "learning_rate": 0.00024432989690721646,
      "loss": 6.6895,
      "step": 1270
    },
    {
      "epoch": 1.88055861815509,
      "grad_norm": 0.6661822199821472,
      "learning_rate": 0.0002438880706921944,
      "loss": 6.6935,
      "step": 1280
    },
    {
      "epoch": 1.8952590959206175,
      "grad_norm": 0.6287885308265686,
      "learning_rate": 0.00024344624447717228,
      "loss": 6.6507,
      "step": 1290
    },
    {
      "epoch": 1.9099595736861448,
      "grad_norm": 0.6344292759895325,
      "learning_rate": 0.0002430044182621502,
      "loss": 6.6706,
      "step": 1300
    },
    {
      "epoch": 1.9099595736861448,
      "eval_loss": 0.8582596778869629,
      "eval_runtime": 122.7802,
      "eval_samples_per_second": 7.078,
      "eval_steps_per_second": 0.888,
      "step": 1300
    },
    {
      "epoch": 1.924660051451672,
      "grad_norm": 0.6139386892318726,
      "learning_rate": 0.0002425625920471281,
      "loss": 6.6578,
      "step": 1310
    },
    {
      "epoch": 1.9393605292171996,
      "grad_norm": 0.6080993413925171,
      "learning_rate": 0.00024212076583210603,
      "loss": 6.6478,
      "step": 1320
    },
    {
      "epoch": 1.954061006982727,
      "grad_norm": 0.6097526550292969,
      "learning_rate": 0.00024167893961708393,
      "loss": 6.6307,
      "step": 1330
    },
    {
      "epoch": 1.9687614847482542,
      "grad_norm": 0.603585958480835,
      "learning_rate": 0.00024123711340206185,
      "loss": 6.6696,
      "step": 1340
    },
    {
      "epoch": 1.9834619625137817,
      "grad_norm": 0.6306211948394775,
      "learning_rate": 0.00024079528718703975,
      "loss": 6.6335,
      "step": 1350
    },
    {
      "epoch": 1.9834619625137817,
      "eval_loss": 0.8551880121231079,
      "eval_runtime": 122.671,
      "eval_samples_per_second": 7.084,
      "eval_steps_per_second": 0.889,
      "step": 1350
    },
    {
      "epoch": 1.9981624402793092,
      "grad_norm": 0.6002718806266785,
      "learning_rate": 0.00024035346097201767,
      "loss": 6.6681,
      "step": 1360
    },
    {
      "epoch": 2.011760382212422,
      "grad_norm": 0.609912097454071,
      "learning_rate": 0.00023991163475699557,
      "loss": 5.7921,
      "step": 1370
    },
    {
      "epoch": 2.0264608599779494,
      "grad_norm": 0.631758451461792,
      "learning_rate": 0.0002394698085419735,
      "loss": 6.2318,
      "step": 1380
    },
    {
      "epoch": 2.0411613377434765,
      "grad_norm": 0.6468050479888916,
      "learning_rate": 0.00023902798232695136,
      "loss": 6.2074,
      "step": 1390
    },
    {
      "epoch": 2.055861815509004,
      "grad_norm": 0.6332272887229919,
      "learning_rate": 0.00023858615611192926,
      "loss": 6.2245,
      "step": 1400
    },
    {
      "epoch": 2.055861815509004,
      "eval_loss": 0.8581995368003845,
      "eval_runtime": 122.7582,
      "eval_samples_per_second": 7.079,
      "eval_steps_per_second": 0.888,
      "step": 1400
    },
    {
      "epoch": 2.0705622932745316,
      "grad_norm": 0.6591159105300903,
      "learning_rate": 0.00023814432989690718,
      "loss": 6.1981,
      "step": 1410
    },
    {
      "epoch": 2.0852627710400586,
      "grad_norm": 0.634479820728302,
      "learning_rate": 0.00023770250368188508,
      "loss": 6.2003,
      "step": 1420
    },
    {
      "epoch": 2.099963248805586,
      "grad_norm": 0.6693385243415833,
      "learning_rate": 0.000237260677466863,
      "loss": 6.2305,
      "step": 1430
    },
    {
      "epoch": 2.1146637265711137,
      "grad_norm": 0.68646639585495,
      "learning_rate": 0.0002368188512518409,
      "loss": 6.2214,
      "step": 1440
    },
    {
      "epoch": 2.1293642043366408,
      "grad_norm": 0.6264299750328064,
      "learning_rate": 0.00023637702503681883,
      "loss": 6.1968,
      "step": 1450
    },
    {
      "epoch": 2.1293642043366408,
      "eval_loss": 0.8580149412155151,
      "eval_runtime": 122.7321,
      "eval_samples_per_second": 7.08,
      "eval_steps_per_second": 0.888,
      "step": 1450
    },
    {
      "epoch": 2.1440646821021683,
      "grad_norm": 0.6439588069915771,
      "learning_rate": 0.00023593519882179672,
      "loss": 6.2362,
      "step": 1460
    },
    {
      "epoch": 2.158765159867696,
      "grad_norm": 0.6767362952232361,
      "learning_rate": 0.00023549337260677465,
      "loss": 6.2137,
      "step": 1470
    },
    {
      "epoch": 2.173465637633223,
      "grad_norm": 0.6421840786933899,
      "learning_rate": 0.00023505154639175254,
      "loss": 6.2331,
      "step": 1480
    },
    {
      "epoch": 2.1881661153987504,
      "grad_norm": 0.6356670260429382,
      "learning_rate": 0.00023460972017673047,
      "loss": 6.1292,
      "step": 1490
    },
    {
      "epoch": 2.202866593164278,
      "grad_norm": 0.6405894756317139,
      "learning_rate": 0.00023416789396170837,
      "loss": 6.212,
      "step": 1500
    },
    {
      "epoch": 2.202866593164278,
      "eval_loss": 0.8558148741722107,
      "eval_runtime": 122.8325,
      "eval_samples_per_second": 7.075,
      "eval_steps_per_second": 0.887,
      "step": 1500
    },
    {
      "epoch": 2.217567070929805,
      "grad_norm": 0.640738308429718,
      "learning_rate": 0.0002337260677466863,
      "loss": 6.2344,
      "step": 1510
    },
    {
      "epoch": 2.2322675486953325,
      "grad_norm": 0.6253748536109924,
      "learning_rate": 0.0002332842415316642,
      "loss": 6.2409,
      "step": 1520
    },
    {
      "epoch": 2.24696802646086,
      "grad_norm": 0.6264599561691284,
      "learning_rate": 0.0002328424153166421,
      "loss": 6.2622,
      "step": 1530
    },
    {
      "epoch": 2.2616685042263875,
      "grad_norm": 0.6570128202438354,
      "learning_rate": 0.00023240058910162,
      "loss": 6.2325,
      "step": 1540
    },
    {
      "epoch": 2.2763689819919146,
      "grad_norm": 0.6414036750793457,
      "learning_rate": 0.00023195876288659793,
      "loss": 6.2025,
      "step": 1550
    },
    {
      "epoch": 2.2763689819919146,
      "eval_loss": 0.8544706702232361,
      "eval_runtime": 122.7389,
      "eval_samples_per_second": 7.08,
      "eval_steps_per_second": 0.888,
      "step": 1550
    },
    {
      "epoch": 2.291069459757442,
      "grad_norm": 0.6400018930435181,
      "learning_rate": 0.00023151693667157583,
      "loss": 6.2232,
      "step": 1560
    },
    {
      "epoch": 2.3057699375229697,
      "grad_norm": 0.657616376876831,
      "learning_rate": 0.00023107511045655375,
      "loss": 6.1867,
      "step": 1570
    },
    {
      "epoch": 2.3204704152884967,
      "grad_norm": 0.6157673001289368,
      "learning_rate": 0.00023063328424153165,
      "loss": 6.2029,
      "step": 1580
    },
    {
      "epoch": 2.3351708930540243,
      "grad_norm": 0.6498163342475891,
      "learning_rate": 0.00023019145802650957,
      "loss": 6.2112,
      "step": 1590
    },
    {
      "epoch": 2.3498713708195518,
      "grad_norm": 0.6593335866928101,
      "learning_rate": 0.00022974963181148747,
      "loss": 6.1991,
      "step": 1600
    },
    {
      "epoch": 2.3498713708195518,
      "eval_loss": 0.8528178930282593,
      "eval_runtime": 122.9309,
      "eval_samples_per_second": 7.069,
      "eval_steps_per_second": 0.887,
      "step": 1600
    },
    {
      "epoch": 2.364571848585079,
      "grad_norm": 0.6478355526924133,
      "learning_rate": 0.00022930780559646534,
      "loss": 6.2688,
      "step": 1610
    },
    {
      "epoch": 2.3792723263506064,
      "grad_norm": 0.6342290043830872,
      "learning_rate": 0.00022886597938144327,
      "loss": 6.2411,
      "step": 1620
    },
    {
      "epoch": 2.393972804116134,
      "grad_norm": 0.6611024737358093,
      "learning_rate": 0.00022842415316642116,
      "loss": 6.233,
      "step": 1630
    },
    {
      "epoch": 2.408673281881661,
      "grad_norm": 0.6265544295310974,
      "learning_rate": 0.0002279823269513991,
      "loss": 6.1916,
      "step": 1640
    },
    {
      "epoch": 2.4233737596471885,
      "grad_norm": 0.6478269696235657,
      "learning_rate": 0.00022754050073637698,
      "loss": 6.1738,
      "step": 1650
    },
    {
      "epoch": 2.4233737596471885,
      "eval_loss": 0.8510602712631226,
      "eval_runtime": 122.8125,
      "eval_samples_per_second": 7.076,
      "eval_steps_per_second": 0.888,
      "step": 1650
    },
    {
      "epoch": 2.438074237412716,
      "grad_norm": 0.6446574926376343,
      "learning_rate": 0.0002270986745213549,
      "loss": 6.2713,
      "step": 1660
    },
    {
      "epoch": 2.4527747151782435,
      "grad_norm": 0.6360475420951843,
      "learning_rate": 0.0002266568483063328,
      "loss": 6.2584,
      "step": 1670
    },
    {
      "epoch": 2.4674751929437706,
      "grad_norm": 0.6492727398872375,
      "learning_rate": 0.00022621502209131073,
      "loss": 6.2234,
      "step": 1680
    },
    {
      "epoch": 2.482175670709298,
      "grad_norm": 0.6489901542663574,
      "learning_rate": 0.00022577319587628863,
      "loss": 6.2155,
      "step": 1690
    },
    {
      "epoch": 2.4968761484748256,
      "grad_norm": 0.6320230960845947,
      "learning_rate": 0.00022533136966126655,
      "loss": 6.1839,
      "step": 1700
    },
    {
      "epoch": 2.4968761484748256,
      "eval_loss": 0.8486818075180054,
      "eval_runtime": 122.741,
      "eval_samples_per_second": 7.08,
      "eval_steps_per_second": 0.888,
      "step": 1700
    },
    {
      "epoch": 2.5115766262403527,
      "grad_norm": 0.642189621925354,
      "learning_rate": 0.00022488954344624445,
      "loss": 6.1757,
      "step": 1710
    },
    {
      "epoch": 2.5262771040058802,
      "grad_norm": 0.6360085010528564,
      "learning_rate": 0.00022444771723122237,
      "loss": 6.2302,
      "step": 1720
    },
    {
      "epoch": 2.5409775817714078,
      "grad_norm": 0.6216627359390259,
      "learning_rate": 0.00022400589101620027,
      "loss": 6.2138,
      "step": 1730
    },
    {
      "epoch": 2.555678059536935,
      "grad_norm": 0.6285056471824646,
      "learning_rate": 0.0002235640648011782,
      "loss": 6.2394,
      "step": 1740
    },
    {
      "epoch": 2.5703785373024624,
      "grad_norm": 0.6265233755111694,
      "learning_rate": 0.0002231222385861561,
      "loss": 6.2358,
      "step": 1750
    },
    {
      "epoch": 2.5703785373024624,
      "eval_loss": 0.846447765827179,
      "eval_runtime": 122.9508,
      "eval_samples_per_second": 7.068,
      "eval_steps_per_second": 0.887,
      "step": 1750
    },
    {
      "epoch": 2.58507901506799,
      "grad_norm": 0.6178449988365173,
      "learning_rate": 0.00022268041237113401,
      "loss": 6.2289,
      "step": 1760
    },
    {
      "epoch": 2.599779492833517,
      "grad_norm": 0.6336231827735901,
      "learning_rate": 0.0002222385861561119,
      "loss": 6.1892,
      "step": 1770
    },
    {
      "epoch": 2.6144799705990445,
      "grad_norm": 0.6177706718444824,
      "learning_rate": 0.00022179675994108984,
      "loss": 6.2211,
      "step": 1780
    },
    {
      "epoch": 2.629180448364572,
      "grad_norm": 0.6471459269523621,
      "learning_rate": 0.00022135493372606773,
      "loss": 6.2231,
      "step": 1790
    },
    {
      "epoch": 2.643880926130099,
      "grad_norm": 0.6517642140388489,
      "learning_rate": 0.00022091310751104566,
      "loss": 6.2072,
      "step": 1800
    },
    {
      "epoch": 2.643880926130099,
      "eval_loss": 0.8459606170654297,
      "eval_runtime": 122.7829,
      "eval_samples_per_second": 7.078,
      "eval_steps_per_second": 0.888,
      "step": 1800
    },
    {
      "epoch": 2.6585814038956266,
      "grad_norm": 0.6251035332679749,
      "learning_rate": 0.00022047128129602355,
      "loss": 6.2043,
      "step": 1810
    },
    {
      "epoch": 2.673281881661154,
      "grad_norm": 0.6282381415367126,
      "learning_rate": 0.00022002945508100145,
      "loss": 6.2106,
      "step": 1820
    },
    {
      "epoch": 2.687982359426681,
      "grad_norm": 0.6424158811569214,
      "learning_rate": 0.00021958762886597935,
      "loss": 6.1704,
      "step": 1830
    },
    {
      "epoch": 2.7026828371922087,
      "grad_norm": 0.6325989365577698,
      "learning_rate": 0.00021914580265095727,
      "loss": 6.2082,
      "step": 1840
    },
    {
      "epoch": 2.717383314957736,
      "grad_norm": 0.6277638673782349,
      "learning_rate": 0.00021870397643593517,
      "loss": 6.2104,
      "step": 1850
    },
    {
      "epoch": 2.717383314957736,
      "eval_loss": 0.8437173366546631,
      "eval_runtime": 122.7354,
      "eval_samples_per_second": 7.08,
      "eval_steps_per_second": 0.888,
      "step": 1850
    },
    {
      "epoch": 2.7320837927232633,
      "grad_norm": 0.59511798620224,
      "learning_rate": 0.00021826215022091307,
      "loss": 6.2104,
      "step": 1860
    },
    {
      "epoch": 2.746784270488791,
      "grad_norm": 0.6076375246047974,
      "learning_rate": 0.000217820324005891,
      "loss": 6.2272,
      "step": 1870
    },
    {
      "epoch": 2.7614847482543183,
      "grad_norm": 0.6336222290992737,
      "learning_rate": 0.0002173784977908689,
      "loss": 6.2629,
      "step": 1880
    },
    {
      "epoch": 2.7761852260198454,
      "grad_norm": 0.6477245092391968,
      "learning_rate": 0.0002169366715758468,
      "loss": 6.2086,
      "step": 1890
    },
    {
      "epoch": 2.790885703785373,
      "grad_norm": 0.63583904504776,
      "learning_rate": 0.0002164948453608247,
      "loss": 6.2289,
      "step": 1900
    },
    {
      "epoch": 2.790885703785373,
      "eval_loss": 0.8419505953788757,
      "eval_runtime": 122.7793,
      "eval_samples_per_second": 7.078,
      "eval_steps_per_second": 0.888,
      "step": 1900
    },
    {
      "epoch": 2.8055861815509004,
      "grad_norm": 0.6694473028182983,
      "learning_rate": 0.00021605301914580263,
      "loss": 6.2386,
      "step": 1910
    },
    {
      "epoch": 2.8202866593164275,
      "grad_norm": 0.6175634860992432,
      "learning_rate": 0.00021561119293078053,
      "loss": 6.1825,
      "step": 1920
    },
    {
      "epoch": 2.834987137081955,
      "grad_norm": 0.6627750992774963,
      "learning_rate": 0.00021516936671575845,
      "loss": 6.204,
      "step": 1930
    },
    {
      "epoch": 2.8496876148474826,
      "grad_norm": 0.6206278800964355,
      "learning_rate": 0.00021472754050073635,
      "loss": 6.1706,
      "step": 1940
    },
    {
      "epoch": 2.86438809261301,
      "grad_norm": 0.6408950686454773,
      "learning_rate": 0.00021428571428571427,
      "loss": 6.2532,
      "step": 1950
    },
    {
      "epoch": 2.86438809261301,
      "eval_loss": 0.8408024907112122,
      "eval_runtime": 122.8418,
      "eval_samples_per_second": 7.074,
      "eval_steps_per_second": 0.887,
      "step": 1950
    },
    {
      "epoch": 2.879088570378537,
      "grad_norm": 0.6331806778907776,
      "learning_rate": 0.00021384388807069217,
      "loss": 6.1977,
      "step": 1960
    },
    {
      "epoch": 2.8937890481440647,
      "grad_norm": 0.6263200640678406,
      "learning_rate": 0.0002134020618556701,
      "loss": 6.2267,
      "step": 1970
    },
    {
      "epoch": 2.908489525909592,
      "grad_norm": 0.6077616214752197,
      "learning_rate": 0.000212960235640648,
      "loss": 6.2016,
      "step": 1980
    },
    {
      "epoch": 2.9231900036751193,
      "grad_norm": 0.6300930976867676,
      "learning_rate": 0.00021251840942562592,
      "loss": 6.1878,
      "step": 1990
    },
    {
      "epoch": 2.937890481440647,
      "grad_norm": 0.6281541585922241,
      "learning_rate": 0.00021207658321060381,
      "loss": 6.2084,
      "step": 2000
    },
    {
      "epoch": 2.937890481440647,
      "eval_loss": 0.8391561508178711,
      "eval_runtime": 122.7198,
      "eval_samples_per_second": 7.081,
      "eval_steps_per_second": 0.888,
      "step": 2000
    },
    {
      "epoch": 2.9525909592061743,
      "grad_norm": 0.6204951405525208,
      "learning_rate": 0.00021163475699558174,
      "loss": 6.2271,
      "step": 2010
    },
    {
      "epoch": 2.967291436971702,
      "grad_norm": 0.6341344118118286,
      "learning_rate": 0.00021119293078055964,
      "loss": 6.2171,
      "step": 2020
    },
    {
      "epoch": 2.981991914737229,
      "grad_norm": 0.6163744330406189,
      "learning_rate": 0.00021075110456553753,
      "loss": 6.2194,
      "step": 2030
    },
    {
      "epoch": 2.9966923925027564,
      "grad_norm": 0.635434627532959,
      "learning_rate": 0.00021030927835051543,
      "loss": 6.1609,
      "step": 2040
    },
    {
      "epoch": 3.010290334435869,
      "grad_norm": 0.8156677484512329,
      "learning_rate": 0.00020986745213549335,
      "loss": 5.3662,
      "step": 2050
    },
    {
      "epoch": 3.010290334435869,
      "eval_loss": 0.8518180251121521,
      "eval_runtime": 122.7832,
      "eval_samples_per_second": 7.078,
      "eval_steps_per_second": 0.888,
      "step": 2050
    },
    {
      "epoch": 3.0249908122013967,
      "grad_norm": 0.6709501147270203,
      "learning_rate": 0.00020942562592047125,
      "loss": 5.657,
      "step": 2060
    },
    {
      "epoch": 3.0396912899669237,
      "grad_norm": 0.6364277601242065,
      "learning_rate": 0.00020898379970544917,
      "loss": 5.6556,
      "step": 2070
    },
    {
      "epoch": 3.0543917677324512,
      "grad_norm": 0.6877652406692505,
      "learning_rate": 0.00020854197349042707,
      "loss": 5.6971,
      "step": 2080
    },
    {
      "epoch": 3.0690922454979788,
      "grad_norm": 0.6691612005233765,
      "learning_rate": 0.000208100147275405,
      "loss": 5.6758,
      "step": 2090
    },
    {
      "epoch": 3.083792723263506,
      "grad_norm": 0.6702853441238403,
      "learning_rate": 0.0002076583210603829,
      "loss": 5.6567,
      "step": 2100
    },
    {
      "epoch": 3.083792723263506,
      "eval_loss": 0.8499862551689148,
      "eval_runtime": 122.6921,
      "eval_samples_per_second": 7.083,
      "eval_steps_per_second": 0.888,
      "step": 2100
    },
    {
      "epoch": 3.0984932010290334,
      "grad_norm": 0.6671494245529175,
      "learning_rate": 0.0002072164948453608,
      "loss": 5.6459,
      "step": 2110
    },
    {
      "epoch": 3.113193678794561,
      "grad_norm": 0.6615011692047119,
      "learning_rate": 0.00020677466863033871,
      "loss": 5.6901,
      "step": 2120
    },
    {
      "epoch": 3.1278941565600884,
      "grad_norm": 0.6596587300300598,
      "learning_rate": 0.0002063328424153166,
      "loss": 5.6881,
      "step": 2130
    },
    {
      "epoch": 3.1425946343256155,
      "grad_norm": 0.66860032081604,
      "learning_rate": 0.00020589101620029454,
      "loss": 5.6988,
      "step": 2140
    },
    {
      "epoch": 3.157295112091143,
      "grad_norm": 0.6529964208602905,
      "learning_rate": 0.00020544918998527243,
      "loss": 5.7,
      "step": 2150
    },
    {
      "epoch": 3.157295112091143,
      "eval_loss": 0.8492234945297241,
      "eval_runtime": 122.695,
      "eval_samples_per_second": 7.083,
      "eval_steps_per_second": 0.888,
      "step": 2150
    },
    {
      "epoch": 3.1719955898566705,
      "grad_norm": 0.6981674432754517,
      "learning_rate": 0.00020500736377025036,
      "loss": 5.6757,
      "step": 2160
    },
    {
      "epoch": 3.1866960676221976,
      "grad_norm": 0.6831721067428589,
      "learning_rate": 0.00020456553755522825,
      "loss": 5.7149,
      "step": 2170
    },
    {
      "epoch": 3.201396545387725,
      "grad_norm": 0.6813935041427612,
      "learning_rate": 0.00020412371134020618,
      "loss": 5.6557,
      "step": 2180
    },
    {
      "epoch": 3.2160970231532526,
      "grad_norm": 0.6628422737121582,
      "learning_rate": 0.00020368188512518407,
      "loss": 5.6812,
      "step": 2190
    },
    {
      "epoch": 3.2307975009187797,
      "grad_norm": 0.6785872578620911,
      "learning_rate": 0.000203240058910162,
      "loss": 5.74,
      "step": 2200
    },
    {
      "epoch": 3.2307975009187797,
      "eval_loss": 0.8484858870506287,
      "eval_runtime": 122.7176,
      "eval_samples_per_second": 7.081,
      "eval_steps_per_second": 0.888,
      "step": 2200
    },
    {
      "epoch": 3.2454979786843072,
      "grad_norm": 0.6826450228691101,
      "learning_rate": 0.0002027982326951399,
      "loss": 5.7303,
      "step": 2210
    },
    {
      "epoch": 3.2601984564498347,
      "grad_norm": 0.6782203912734985,
      "learning_rate": 0.00020235640648011782,
      "loss": 5.7306,
      "step": 2220
    },
    {
      "epoch": 3.274898934215362,
      "grad_norm": 0.7322261929512024,
      "learning_rate": 0.00020191458026509572,
      "loss": 5.7121,
      "step": 2230
    },
    {
      "epoch": 3.2895994119808893,
      "grad_norm": 0.676398754119873,
      "learning_rate": 0.00020147275405007361,
      "loss": 5.676,
      "step": 2240
    },
    {
      "epoch": 3.304299889746417,
      "grad_norm": 0.6796535849571228,
      "learning_rate": 0.0002010309278350515,
      "loss": 5.6793,
      "step": 2250
    },
    {
      "epoch": 3.304299889746417,
      "eval_loss": 0.8485282063484192,
      "eval_runtime": 122.7649,
      "eval_samples_per_second": 7.079,
      "eval_steps_per_second": 0.888,
      "step": 2250
    },
    {
      "epoch": 3.3190003675119444,
      "grad_norm": 0.6691915392875671,
      "learning_rate": 0.00020058910162002944,
      "loss": 5.7447,
      "step": 2260
    },
    {
      "epoch": 3.3337008452774715,
      "grad_norm": 0.6691219210624695,
      "learning_rate": 0.00020014727540500733,
      "loss": 5.7213,
      "step": 2270
    },
    {
      "epoch": 3.348401323042999,
      "grad_norm": 0.691150963306427,
      "learning_rate": 0.00019970544918998526,
      "loss": 5.7139,
      "step": 2280
    },
    {
      "epoch": 3.3631018008085265,
      "grad_norm": 0.6797978281974792,
      "learning_rate": 0.00019926362297496315,
      "loss": 5.7259,
      "step": 2290
    },
    {
      "epoch": 3.3778022785740536,
      "grad_norm": 0.680253803730011,
      "learning_rate": 0.00019882179675994108,
      "loss": 5.729,
      "step": 2300
    },
    {
      "epoch": 3.3778022785740536,
      "eval_loss": 0.8467084765434265,
      "eval_runtime": 122.7168,
      "eval_samples_per_second": 7.081,
      "eval_steps_per_second": 0.888,
      "step": 2300
    },
    {
      "epoch": 3.392502756339581,
      "grad_norm": 0.6667632460594177,
      "learning_rate": 0.00019837997054491897,
      "loss": 5.7414,
      "step": 2310
    },
    {
      "epoch": 3.4072032341051086,
      "grad_norm": 0.6695231795310974,
      "learning_rate": 0.0001979381443298969,
      "loss": 5.6706,
      "step": 2320
    },
    {
      "epoch": 3.4219037118706357,
      "grad_norm": 0.6954268217086792,
      "learning_rate": 0.0001974963181148748,
      "loss": 5.786,
      "step": 2330
    },
    {
      "epoch": 3.436604189636163,
      "grad_norm": 0.6876401901245117,
      "learning_rate": 0.00019705449189985272,
      "loss": 5.7293,
      "step": 2340
    },
    {
      "epoch": 3.4513046674016907,
      "grad_norm": 0.6845841407775879,
      "learning_rate": 0.00019661266568483062,
      "loss": 5.7367,
      "step": 2350
    },
    {
      "epoch": 3.4513046674016907,
      "eval_loss": 0.8462281823158264,
      "eval_runtime": 122.7084,
      "eval_samples_per_second": 7.082,
      "eval_steps_per_second": 0.888,
      "step": 2350
    },
    {
      "epoch": 3.466005145167218,
      "grad_norm": 0.6698250770568848,
      "learning_rate": 0.00019617083946980851,
      "loss": 5.7564,
      "step": 2360
    },
    {
      "epoch": 3.4807056229327453,
      "grad_norm": 0.691417396068573,
      "learning_rate": 0.00019572901325478644,
      "loss": 5.7239,
      "step": 2370
    },
    {
      "epoch": 3.495406100698273,
      "grad_norm": 0.69003826379776,
      "learning_rate": 0.00019528718703976433,
      "loss": 5.7359,
      "step": 2380
    },
    {
      "epoch": 3.5101065784638,
      "grad_norm": 0.665431797504425,
      "learning_rate": 0.00019484536082474226,
      "loss": 5.7405,
      "step": 2390
    },
    {
      "epoch": 3.5248070562293274,
      "grad_norm": 0.6713572144508362,
      "learning_rate": 0.00019440353460972016,
      "loss": 5.7417,
      "step": 2400
    },
    {
      "epoch": 3.5248070562293274,
      "eval_loss": 0.8447020053863525,
      "eval_runtime": 122.7287,
      "eval_samples_per_second": 7.081,
      "eval_steps_per_second": 0.888,
      "step": 2400
    },
    {
      "epoch": 3.539507533994855,
      "grad_norm": 0.6731536388397217,
      "learning_rate": 0.00019396170839469808,
      "loss": 5.7519,
      "step": 2410
    },
    {
      "epoch": 3.554208011760382,
      "grad_norm": 0.6862500905990601,
      "learning_rate": 0.00019351988217967598,
      "loss": 5.7698,
      "step": 2420
    },
    {
      "epoch": 3.5689084895259096,
      "grad_norm": 0.6730573773384094,
      "learning_rate": 0.0001930780559646539,
      "loss": 5.7444,
      "step": 2430
    },
    {
      "epoch": 3.583608967291437,
      "grad_norm": 0.7046417593955994,
      "learning_rate": 0.0001926362297496318,
      "loss": 5.7886,
      "step": 2440
    },
    {
      "epoch": 3.598309445056964,
      "grad_norm": 0.6981428265571594,
      "learning_rate": 0.00019219440353460972,
      "loss": 5.7708,
      "step": 2450
    },
    {
      "epoch": 3.598309445056964,
      "eval_loss": 0.8444002270698547,
      "eval_runtime": 122.7558,
      "eval_samples_per_second": 7.079,
      "eval_steps_per_second": 0.888,
      "step": 2450
    },
    {
      "epoch": 3.6130099228224917,
      "grad_norm": 0.6807316541671753,
      "learning_rate": 0.0001917525773195876,
      "loss": 5.7589,
      "step": 2460
    },
    {
      "epoch": 3.627710400588019,
      "grad_norm": 0.6898190975189209,
      "learning_rate": 0.00019131075110456552,
      "loss": 5.716,
      "step": 2470
    },
    {
      "epoch": 3.6424108783535463,
      "grad_norm": 0.6854293942451477,
      "learning_rate": 0.00019086892488954341,
      "loss": 5.7499,
      "step": 2480
    },
    {
      "epoch": 3.657111356119074,
      "grad_norm": 0.6629763245582581,
      "learning_rate": 0.00019042709867452134,
      "loss": 5.763,
      "step": 2490
    },
    {
      "epoch": 3.6718118338846013,
      "grad_norm": 0.6828572750091553,
      "learning_rate": 0.00018998527245949923,
      "loss": 5.748,
      "step": 2500
    },
    {
      "epoch": 3.6718118338846013,
      "eval_loss": 0.8433157801628113,
      "eval_runtime": 122.7268,
      "eval_samples_per_second": 7.081,
      "eval_steps_per_second": 0.888,
      "step": 2500
    },
    {
      "epoch": 3.6865123116501284,
      "grad_norm": 0.6758775115013123,
      "learning_rate": 0.00018954344624447716,
      "loss": 5.8063,
      "step": 2510
    },
    {
      "epoch": 3.701212789415656,
      "grad_norm": 0.699603796005249,
      "learning_rate": 0.00018910162002945506,
      "loss": 5.7323,
      "step": 2520
    },
    {
      "epoch": 3.7159132671811834,
      "grad_norm": 0.6797698140144348,
      "learning_rate": 0.00018865979381443298,
      "loss": 5.7159,
      "step": 2530
    },
    {
      "epoch": 3.7306137449467105,
      "grad_norm": 0.7055732011795044,
      "learning_rate": 0.00018821796759941088,
      "loss": 5.7788,
      "step": 2540
    },
    {
      "epoch": 3.745314222712238,
      "grad_norm": 0.6939615607261658,
      "learning_rate": 0.0001877761413843888,
      "loss": 5.8017,
      "step": 2550
    },
    {
      "epoch": 3.745314222712238,
      "eval_loss": 0.8415707349777222,
      "eval_runtime": 122.7864,
      "eval_samples_per_second": 7.077,
      "eval_steps_per_second": 0.888,
      "step": 2550
    },
    {
      "epoch": 3.7600147004777655,
      "grad_norm": 0.6803593635559082,
      "learning_rate": 0.0001873343151693667,
      "loss": 5.7542,
      "step": 2560
    },
    {
      "epoch": 3.774715178243293,
      "grad_norm": 0.6966648101806641,
      "learning_rate": 0.00018689248895434462,
      "loss": 5.7682,
      "step": 2570
    },
    {
      "epoch": 3.78941565600882,
      "grad_norm": 0.6992161870002747,
      "learning_rate": 0.00018645066273932252,
      "loss": 5.7216,
      "step": 2580
    },
    {
      "epoch": 3.8041161337743477,
      "grad_norm": 0.6834452152252197,
      "learning_rate": 0.00018600883652430044,
      "loss": 5.7347,
      "step": 2590
    },
    {
      "epoch": 3.818816611539875,
      "grad_norm": 0.6835057139396667,
      "learning_rate": 0.00018556701030927834,
      "loss": 5.7475,
      "step": 2600
    },
    {
      "epoch": 3.818816611539875,
      "eval_loss": 0.8405690789222717,
      "eval_runtime": 122.7131,
      "eval_samples_per_second": 7.082,
      "eval_steps_per_second": 0.888,
      "step": 2600
    },
    {
      "epoch": 3.8335170893054027,
      "grad_norm": 0.6868228316307068,
      "learning_rate": 0.00018512518409425626,
      "loss": 5.7805,
      "step": 2610
    },
    {
      "epoch": 3.8482175670709298,
      "grad_norm": 0.6829861402511597,
      "learning_rate": 0.00018468335787923416,
      "loss": 5.7193,
      "step": 2620
    },
    {
      "epoch": 3.8629180448364573,
      "grad_norm": 0.6857191920280457,
      "learning_rate": 0.00018424153166421206,
      "loss": 5.7893,
      "step": 2630
    },
    {
      "epoch": 3.877618522601985,
      "grad_norm": 0.6723675727844238,
      "learning_rate": 0.00018379970544918998,
      "loss": 5.7788,
      "step": 2640
    },
    {
      "epoch": 3.892319000367512,
      "grad_norm": 0.6871203780174255,
      "learning_rate": 0.00018335787923416788,
      "loss": 5.7881,
      "step": 2650
    },
    {
      "epoch": 3.892319000367512,
      "eval_loss": 0.8391252160072327,
      "eval_runtime": 122.6983,
      "eval_samples_per_second": 7.082,
      "eval_steps_per_second": 0.888,
      "step": 2650
    },
    {
      "epoch": 3.9070194781330394,
      "grad_norm": 0.6965262293815613,
      "learning_rate": 0.0001829160530191458,
      "loss": 5.7777,
      "step": 2660
    },
    {
      "epoch": 3.921719955898567,
      "grad_norm": 0.6634519696235657,
      "learning_rate": 0.00018247422680412367,
      "loss": 5.7385,
      "step": 2670
    },
    {
      "epoch": 3.936420433664094,
      "grad_norm": 0.658750593662262,
      "learning_rate": 0.0001820324005891016,
      "loss": 5.7514,
      "step": 2680
    },
    {
      "epoch": 3.9511209114296215,
      "grad_norm": 0.6765331029891968,
      "learning_rate": 0.0001815905743740795,
      "loss": 5.7902,
      "step": 2690
    },
    {
      "epoch": 3.965821389195149,
      "grad_norm": 0.684141993522644,
      "learning_rate": 0.00018114874815905742,
      "loss": 5.8105,
      "step": 2700
    },
    {
      "epoch": 3.965821389195149,
      "eval_loss": 0.8379185795783997,
      "eval_runtime": 122.8086,
      "eval_samples_per_second": 7.076,
      "eval_steps_per_second": 0.888,
      "step": 2700
    },
    {
      "epoch": 3.980521866960676,
      "grad_norm": 0.668866753578186,
      "learning_rate": 0.00018070692194403532,
      "loss": 5.7643,
      "step": 2710
    },
    {
      "epoch": 3.9952223447262036,
      "grad_norm": 0.6660596132278442,
      "learning_rate": 0.00018026509572901324,
      "loss": 5.757,
      "step": 2720
    },
    {
      "epoch": 4.008820286659317,
      "grad_norm": 1.04069983959198,
      "learning_rate": 0.00017982326951399114,
      "loss": 5.0052,
      "step": 2730
    },
    {
      "epoch": 4.023520764424844,
      "grad_norm": 0.7606070637702942,
      "learning_rate": 0.00017938144329896906,
      "loss": 5.2139,
      "step": 2740
    },
    {
      "epoch": 4.038221242190371,
      "grad_norm": 0.743680477142334,
      "learning_rate": 0.00017893961708394696,
      "loss": 5.1857,
      "step": 2750
    },
    {
      "epoch": 4.038221242190371,
      "eval_loss": 0.8622083067893982,
      "eval_runtime": 122.732,
      "eval_samples_per_second": 7.08,
      "eval_steps_per_second": 0.888,
      "step": 2750
    },
    {
      "epoch": 4.052921719955899,
      "grad_norm": 0.7183839678764343,
      "learning_rate": 0.00017849779086892488,
      "loss": 5.1678,
      "step": 2760
    },
    {
      "epoch": 4.067622197721426,
      "grad_norm": 0.7291563153266907,
      "learning_rate": 0.00017805596465390278,
      "loss": 5.2046,
      "step": 2770
    },
    {
      "epoch": 4.082322675486953,
      "grad_norm": 0.7452117204666138,
      "learning_rate": 0.0001776141384388807,
      "loss": 5.1908,
      "step": 2780
    },
    {
      "epoch": 4.097023153252481,
      "grad_norm": 0.730151355266571,
      "learning_rate": 0.0001771723122238586,
      "loss": 5.1827,
      "step": 2790
    },
    {
      "epoch": 4.111723631018008,
      "grad_norm": 0.7287917137145996,
      "learning_rate": 0.00017673048600883653,
      "loss": 5.2302,
      "step": 2800
    },
    {
      "epoch": 4.111723631018008,
      "eval_loss": 0.8607571125030518,
      "eval_runtime": 122.8437,
      "eval_samples_per_second": 7.074,
      "eval_steps_per_second": 0.887,
      "step": 2800
    },
    {
      "epoch": 4.126424108783535,
      "grad_norm": 0.7352184653282166,
      "learning_rate": 0.00017628865979381442,
      "loss": 5.2023,
      "step": 2810
    },
    {
      "epoch": 4.141124586549063,
      "grad_norm": 0.7560921311378479,
      "learning_rate": 0.00017584683357879235,
      "loss": 5.1905,
      "step": 2820
    },
    {
      "epoch": 4.15582506431459,
      "grad_norm": 0.7419695258140564,
      "learning_rate": 0.00017540500736377024,
      "loss": 5.187,
      "step": 2830
    },
    {
      "epoch": 4.170525542080117,
      "grad_norm": 0.7407976388931274,
      "learning_rate": 0.00017496318114874817,
      "loss": 5.2322,
      "step": 2840
    },
    {
      "epoch": 4.185226019845645,
      "grad_norm": 0.7482364773750305,
      "learning_rate": 0.00017452135493372606,
      "loss": 5.2617,
      "step": 2850
    },
    {
      "epoch": 4.185226019845645,
      "eval_loss": 0.8609734177589417,
      "eval_runtime": 122.7306,
      "eval_samples_per_second": 7.081,
      "eval_steps_per_second": 0.888,
      "step": 2850
    },
    {
      "epoch": 4.199926497611172,
      "grad_norm": 0.7562023997306824,
      "learning_rate": 0.000174079528718704,
      "loss": 5.2432,
      "step": 2860
    },
    {
      "epoch": 4.214626975376699,
      "grad_norm": 0.76356440782547,
      "learning_rate": 0.00017363770250368189,
      "loss": 5.2342,
      "step": 2870
    },
    {
      "epoch": 4.229327453142227,
      "grad_norm": 0.7754319906234741,
      "learning_rate": 0.00017319587628865976,
      "loss": 5.2736,
      "step": 2880
    },
    {
      "epoch": 4.244027930907754,
      "grad_norm": 0.7472639679908752,
      "learning_rate": 0.00017275405007363768,
      "loss": 5.1607,
      "step": 2890
    },
    {
      "epoch": 4.2587284086732815,
      "grad_norm": 0.759757936000824,
      "learning_rate": 0.00017231222385861558,
      "loss": 5.2299,
      "step": 2900
    },
    {
      "epoch": 4.2587284086732815,
      "eval_loss": 0.8612560629844666,
      "eval_runtime": 122.7459,
      "eval_samples_per_second": 7.08,
      "eval_steps_per_second": 0.888,
      "step": 2900
    },
    {
      "epoch": 4.2734288864388095,
      "grad_norm": 0.80708247423172,
      "learning_rate": 0.0001718703976435935,
      "loss": 5.2688,
      "step": 2910
    },
    {
      "epoch": 4.2881293642043365,
      "grad_norm": 0.7704065442085266,
      "learning_rate": 0.0001714285714285714,
      "loss": 5.2478,
      "step": 2920
    },
    {
      "epoch": 4.302829841969864,
      "grad_norm": 0.7821296453475952,
      "learning_rate": 0.00017098674521354932,
      "loss": 5.2805,
      "step": 2930
    },
    {
      "epoch": 4.317530319735392,
      "grad_norm": 0.7851975560188293,
      "learning_rate": 0.00017054491899852722,
      "loss": 5.246,
      "step": 2940
    },
    {
      "epoch": 4.332230797500919,
      "grad_norm": 0.7333672046661377,
      "learning_rate": 0.00017010309278350514,
      "loss": 5.2627,
      "step": 2950
    },
    {
      "epoch": 4.332230797500919,
      "eval_loss": 0.8597420454025269,
      "eval_runtime": 122.891,
      "eval_samples_per_second": 7.071,
      "eval_steps_per_second": 0.887,
      "step": 2950
    },
    {
      "epoch": 4.346931275266446,
      "grad_norm": 0.7573877573013306,
      "learning_rate": 0.00016966126656848304,
      "loss": 5.2539,
      "step": 2960
    },
    {
      "epoch": 4.361631753031974,
      "grad_norm": 0.7531468272209167,
      "learning_rate": 0.00016921944035346096,
      "loss": 5.2819,
      "step": 2970
    },
    {
      "epoch": 4.376332230797501,
      "grad_norm": 0.7768471837043762,
      "learning_rate": 0.00016877761413843886,
      "loss": 5.2684,
      "step": 2980
    },
    {
      "epoch": 4.391032708563028,
      "grad_norm": 0.7904699444770813,
      "learning_rate": 0.00016833578792341679,
      "loss": 5.2538,
      "step": 2990
    },
    {
      "epoch": 4.405733186328556,
      "grad_norm": 0.8030019402503967,
      "learning_rate": 0.00016789396170839468,
      "loss": 5.2828,
      "step": 3000
    },
    {
      "epoch": 4.405733186328556,
      "eval_loss": 0.8594609498977661,
      "eval_runtime": 122.7873,
      "eval_samples_per_second": 7.077,
      "eval_steps_per_second": 0.888,
      "step": 3000
    },
    {
      "epoch": 4.420433664094083,
      "grad_norm": 0.751737117767334,
      "learning_rate": 0.0001674521354933726,
      "loss": 5.3038,
      "step": 3010
    },
    {
      "epoch": 4.43513414185961,
      "grad_norm": 0.7465061545372009,
      "learning_rate": 0.0001670103092783505,
      "loss": 5.2605,
      "step": 3020
    },
    {
      "epoch": 4.449834619625138,
      "grad_norm": 0.759131669998169,
      "learning_rate": 0.00016656848306332843,
      "loss": 5.2886,
      "step": 3030
    },
    {
      "epoch": 4.464535097390665,
      "grad_norm": 0.7656858563423157,
      "learning_rate": 0.00016612665684830633,
      "loss": 5.2273,
      "step": 3040
    },
    {
      "epoch": 4.479235575156193,
      "grad_norm": 0.7533978223800659,
      "learning_rate": 0.00016568483063328425,
      "loss": 5.2777,
      "step": 3050
    },
    {
      "epoch": 4.479235575156193,
      "eval_loss": 0.8585497140884399,
      "eval_runtime": 122.7392,
      "eval_samples_per_second": 7.08,
      "eval_steps_per_second": 0.888,
      "step": 3050
    },
    {
      "epoch": 4.49393605292172,
      "grad_norm": 0.7555689811706543,
      "learning_rate": 0.00016524300441826215,
      "loss": 5.2478,
      "step": 3060
    },
    {
      "epoch": 4.508636530687247,
      "grad_norm": 0.7516697645187378,
      "learning_rate": 0.00016480117820324007,
      "loss": 5.2559,
      "step": 3070
    },
    {
      "epoch": 4.523337008452775,
      "grad_norm": 0.7887890934944153,
      "learning_rate": 0.00016435935198821797,
      "loss": 5.3158,
      "step": 3080
    },
    {
      "epoch": 4.538037486218302,
      "grad_norm": 0.7691967487335205,
      "learning_rate": 0.00016391752577319584,
      "loss": 5.2946,
      "step": 3090
    },
    {
      "epoch": 4.552737963983829,
      "grad_norm": 0.7757486701011658,
      "learning_rate": 0.00016347569955817376,
      "loss": 5.2849,
      "step": 3100
    },
    {
      "epoch": 4.552737963983829,
      "eval_loss": 0.8570435047149658,
      "eval_runtime": 122.7277,
      "eval_samples_per_second": 7.081,
      "eval_steps_per_second": 0.888,
      "step": 3100
    },
    {
      "epoch": 4.567438441749357,
      "grad_norm": 0.7805380821228027,
      "learning_rate": 0.00016303387334315166,
      "loss": 5.3412,
      "step": 3110
    },
    {
      "epoch": 4.582138919514884,
      "grad_norm": 0.7780531048774719,
      "learning_rate": 0.00016259204712812958,
      "loss": 5.2718,
      "step": 3120
    },
    {
      "epoch": 4.596839397280411,
      "grad_norm": 0.7380784749984741,
      "learning_rate": 0.00016215022091310748,
      "loss": 5.3036,
      "step": 3130
    },
    {
      "epoch": 4.611539875045939,
      "grad_norm": 0.7692278623580933,
      "learning_rate": 0.0001617083946980854,
      "loss": 5.3028,
      "step": 3140
    },
    {
      "epoch": 4.626240352811466,
      "grad_norm": 0.7445947527885437,
      "learning_rate": 0.0001612665684830633,
      "loss": 5.2811,
      "step": 3150
    },
    {
      "epoch": 4.626240352811466,
      "eval_loss": 0.8577845692634583,
      "eval_runtime": 122.7855,
      "eval_samples_per_second": 7.077,
      "eval_steps_per_second": 0.888,
      "step": 3150
    },
    {
      "epoch": 4.6409408305769935,
      "grad_norm": 0.7451578974723816,
      "learning_rate": 0.00016082474226804122,
      "loss": 5.3035,
      "step": 3160
    },
    {
      "epoch": 4.655641308342521,
      "grad_norm": 0.7448246479034424,
      "learning_rate": 0.00016038291605301912,
      "loss": 5.2956,
      "step": 3170
    },
    {
      "epoch": 4.6703417861080485,
      "grad_norm": 0.7711780071258545,
      "learning_rate": 0.00015994108983799705,
      "loss": 5.281,
      "step": 3180
    },
    {
      "epoch": 4.685042263873576,
      "grad_norm": 0.7698442339897156,
      "learning_rate": 0.00015949926362297494,
      "loss": 5.3382,
      "step": 3190
    },
    {
      "epoch": 4.6997427416391035,
      "grad_norm": 0.7665743231773376,
      "learning_rate": 0.00015905743740795287,
      "loss": 5.2781,
      "step": 3200
    },
    {
      "epoch": 4.6997427416391035,
      "eval_loss": 0.8565701842308044,
      "eval_runtime": 122.777,
      "eval_samples_per_second": 7.078,
      "eval_steps_per_second": 0.888,
      "step": 3200
    },
    {
      "epoch": 4.714443219404631,
      "grad_norm": 0.7319465279579163,
      "learning_rate": 0.00015861561119293076,
      "loss": 5.3044,
      "step": 3210
    },
    {
      "epoch": 4.729143697170158,
      "grad_norm": 0.7576644420623779,
      "learning_rate": 0.0001581737849779087,
      "loss": 5.3616,
      "step": 3220
    },
    {
      "epoch": 4.743844174935686,
      "grad_norm": 0.7484728693962097,
      "learning_rate": 0.00015773195876288659,
      "loss": 5.3121,
      "step": 3230
    },
    {
      "epoch": 4.758544652701213,
      "grad_norm": 0.7493030428886414,
      "learning_rate": 0.0001572901325478645,
      "loss": 5.2786,
      "step": 3240
    },
    {
      "epoch": 4.77324513046674,
      "grad_norm": 0.7527353763580322,
      "learning_rate": 0.0001568483063328424,
      "loss": 5.3367,
      "step": 3250
    },
    {
      "epoch": 4.77324513046674,
      "eval_loss": 0.8557420372962952,
      "eval_runtime": 122.7867,
      "eval_samples_per_second": 7.077,
      "eval_steps_per_second": 0.888,
      "step": 3250
    },
    {
      "epoch": 4.787945608232268,
      "grad_norm": 0.7508755326271057,
      "learning_rate": 0.00015640648011782033,
      "loss": 5.3221,
      "step": 3260
    },
    {
      "epoch": 4.802646085997795,
      "grad_norm": 0.7572493553161621,
      "learning_rate": 0.00015596465390279823,
      "loss": 5.2777,
      "step": 3270
    },
    {
      "epoch": 4.817346563763322,
      "grad_norm": 0.7531789541244507,
      "learning_rate": 0.00015552282768777615,
      "loss": 5.2999,
      "step": 3280
    },
    {
      "epoch": 4.83204704152885,
      "grad_norm": 0.7436636686325073,
      "learning_rate": 0.00015508100147275405,
      "loss": 5.2683,
      "step": 3290
    },
    {
      "epoch": 4.846747519294377,
      "grad_norm": 0.746624767780304,
      "learning_rate": 0.00015463917525773192,
      "loss": 5.3402,
      "step": 3300
    },
    {
      "epoch": 4.846747519294377,
      "eval_loss": 0.8542863726615906,
      "eval_runtime": 122.7376,
      "eval_samples_per_second": 7.08,
      "eval_steps_per_second": 0.888,
      "step": 3300
    },
    {
      "epoch": 4.861447997059905,
      "grad_norm": 0.7520425319671631,
      "learning_rate": 0.00015419734904270984,
      "loss": 5.3424,
      "step": 3310
    },
    {
      "epoch": 4.876148474825432,
      "grad_norm": 0.7883239388465881,
      "learning_rate": 0.00015375552282768774,
      "loss": 5.3252,
      "step": 3320
    },
    {
      "epoch": 4.890848952590959,
      "grad_norm": 0.7612333297729492,
      "learning_rate": 0.00015331369661266566,
      "loss": 5.314,
      "step": 3330
    },
    {
      "epoch": 4.905549430356487,
      "grad_norm": 0.7855140566825867,
      "learning_rate": 0.00015287187039764356,
      "loss": 5.2951,
      "step": 3340
    },
    {
      "epoch": 4.920249908122014,
      "grad_norm": 0.7624037861824036,
      "learning_rate": 0.00015243004418262149,
      "loss": 5.331,
      "step": 3350
    },
    {
      "epoch": 4.920249908122014,
      "eval_loss": 0.8540411591529846,
      "eval_runtime": 122.7574,
      "eval_samples_per_second": 7.079,
      "eval_steps_per_second": 0.888,
      "step": 3350
    },
    {
      "epoch": 4.934950385887541,
      "grad_norm": 0.7521130442619324,
      "learning_rate": 0.00015198821796759938,
      "loss": 5.2818,
      "step": 3360
    }
  ],
  "logging_steps": 10,
  "max_steps": 6800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 120,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7030313392487583e+20,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}