{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9994378864530633,
  "eval_steps": 500,
  "global_step": 2001,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014989694584972832,
      "grad_norm": 3.2230756947704684,
      "learning_rate": 5e-06,
      "loss": 0.8065,
      "step": 10
    },
    {
      "epoch": 0.029979389169945664,
      "grad_norm": 4.087000478453515,
      "learning_rate": 5e-06,
      "loss": 0.651,
      "step": 20
    },
    {
      "epoch": 0.044969083754918496,
      "grad_norm": 2.503327595683403,
      "learning_rate": 5e-06,
      "loss": 0.6152,
      "step": 30
    },
    {
      "epoch": 0.05995877833989133,
      "grad_norm": 2.6733564049479916,
      "learning_rate": 5e-06,
      "loss": 0.5859,
      "step": 40
    },
    {
      "epoch": 0.07494847292486416,
      "grad_norm": 2.7328394257454245,
      "learning_rate": 5e-06,
      "loss": 0.5786,
      "step": 50
    },
    {
      "epoch": 0.08993816750983699,
      "grad_norm": 3.1797521945570693,
      "learning_rate": 5e-06,
      "loss": 0.5685,
      "step": 60
    },
    {
      "epoch": 0.10492786209480982,
      "grad_norm": 2.684949545099637,
      "learning_rate": 5e-06,
      "loss": 0.5586,
      "step": 70
    },
    {
      "epoch": 0.11991755667978266,
      "grad_norm": 2.9219404511166824,
      "learning_rate": 5e-06,
      "loss": 0.5529,
      "step": 80
    },
    {
      "epoch": 0.13490725126475547,
      "grad_norm": 2.3100236702034826,
      "learning_rate": 5e-06,
      "loss": 0.5461,
      "step": 90
    },
    {
      "epoch": 0.14989694584972832,
      "grad_norm": 2.2049571056422397,
      "learning_rate": 5e-06,
      "loss": 0.5381,
      "step": 100
    },
    {
      "epoch": 0.16488664043470114,
      "grad_norm": 1.7661938201026661,
      "learning_rate": 5e-06,
      "loss": 0.5359,
      "step": 110
    },
    {
      "epoch": 0.17987633501967398,
      "grad_norm": 2.1859179504620174,
      "learning_rate": 5e-06,
      "loss": 0.5318,
      "step": 120
    },
    {
      "epoch": 0.1948660296046468,
      "grad_norm": 1.6326069613621976,
      "learning_rate": 5e-06,
      "loss": 0.5279,
      "step": 130
    },
    {
      "epoch": 0.20985572418961965,
      "grad_norm": 1.5360852906450997,
      "learning_rate": 5e-06,
      "loss": 0.5309,
      "step": 140
    },
    {
      "epoch": 0.22484541877459246,
      "grad_norm": 1.7724258855816508,
      "learning_rate": 5e-06,
      "loss": 0.5207,
      "step": 150
    },
    {
      "epoch": 0.2398351133595653,
      "grad_norm": 1.7886911455233951,
      "learning_rate": 5e-06,
      "loss": 0.5203,
      "step": 160
    },
    {
      "epoch": 0.25482480794453816,
      "grad_norm": 1.436404813254963,
      "learning_rate": 5e-06,
      "loss": 0.5179,
      "step": 170
    },
    {
      "epoch": 0.26981450252951095,
      "grad_norm": 1.892553234562171,
      "learning_rate": 5e-06,
      "loss": 0.5134,
      "step": 180
    },
    {
      "epoch": 0.2848041971144838,
      "grad_norm": 1.6450239492265477,
      "learning_rate": 5e-06,
      "loss": 0.5124,
      "step": 190
    },
    {
      "epoch": 0.29979389169945664,
      "grad_norm": 1.894402097483371,
      "learning_rate": 5e-06,
      "loss": 0.508,
      "step": 200
    },
    {
      "epoch": 0.31478358628442943,
      "grad_norm": 1.6348153643564973,
      "learning_rate": 5e-06,
      "loss": 0.5032,
      "step": 210
    },
    {
      "epoch": 0.3297732808694023,
      "grad_norm": 1.3715172854305366,
      "learning_rate": 5e-06,
      "loss": 0.5051,
      "step": 220
    },
    {
      "epoch": 0.3447629754543751,
      "grad_norm": 1.742102338514997,
      "learning_rate": 5e-06,
      "loss": 0.5036,
      "step": 230
    },
    {
      "epoch": 0.35975267003934797,
      "grad_norm": 1.7426571084822509,
      "learning_rate": 5e-06,
      "loss": 0.5041,
      "step": 240
    },
    {
      "epoch": 0.37474236462432076,
      "grad_norm": 2.1505290746647465,
      "learning_rate": 5e-06,
      "loss": 0.5001,
      "step": 250
    },
    {
      "epoch": 0.3897320592092936,
      "grad_norm": 1.793888447963483,
      "learning_rate": 5e-06,
      "loss": 0.5015,
      "step": 260
    },
    {
      "epoch": 0.40472175379426645,
      "grad_norm": 1.8644855732640748,
      "learning_rate": 5e-06,
      "loss": 0.4958,
      "step": 270
    },
    {
      "epoch": 0.4197114483792393,
      "grad_norm": 2.6049833173978825,
      "learning_rate": 5e-06,
      "loss": 0.4996,
      "step": 280
    },
    {
      "epoch": 0.4347011429642121,
      "grad_norm": 1.4405086279628676,
      "learning_rate": 5e-06,
      "loss": 0.4929,
      "step": 290
    },
    {
      "epoch": 0.44969083754918493,
      "grad_norm": 1.604860450889284,
      "learning_rate": 5e-06,
      "loss": 0.4897,
      "step": 300
    },
    {
      "epoch": 0.4646805321341578,
      "grad_norm": 1.662135718621203,
      "learning_rate": 5e-06,
      "loss": 0.4927,
      "step": 310
    },
    {
      "epoch": 0.4796702267191306,
      "grad_norm": 2.062302477917024,
      "learning_rate": 5e-06,
      "loss": 0.4892,
      "step": 320
    },
    {
      "epoch": 0.4946599213041034,
      "grad_norm": 1.4281806778360036,
      "learning_rate": 5e-06,
      "loss": 0.4889,
      "step": 330
    },
    {
      "epoch": 0.5096496158890763,
      "grad_norm": 1.4534145149693543,
      "learning_rate": 5e-06,
      "loss": 0.4872,
      "step": 340
    },
    {
      "epoch": 0.5246393104740491,
      "grad_norm": 1.8740427050796966,
      "learning_rate": 5e-06,
      "loss": 0.4839,
      "step": 350
    },
    {
      "epoch": 0.5396290050590219,
      "grad_norm": 1.5668501527936287,
      "learning_rate": 5e-06,
      "loss": 0.4886,
      "step": 360
    },
    {
      "epoch": 0.5546186996439948,
      "grad_norm": 1.3759231439903845,
      "learning_rate": 5e-06,
      "loss": 0.4837,
      "step": 370
    },
    {
      "epoch": 0.5696083942289676,
      "grad_norm": 1.498739905029643,
      "learning_rate": 5e-06,
      "loss": 0.4822,
      "step": 380
    },
    {
      "epoch": 0.5845980888139404,
      "grad_norm": 1.5404538522347584,
      "learning_rate": 5e-06,
      "loss": 0.4798,
      "step": 390
    },
    {
      "epoch": 0.5995877833989133,
      "grad_norm": 2.0684145258599544,
      "learning_rate": 5e-06,
      "loss": 0.4831,
      "step": 400
    },
    {
      "epoch": 0.6145774779838861,
      "grad_norm": 1.7365319201533058,
      "learning_rate": 5e-06,
      "loss": 0.4803,
      "step": 410
    },
    {
      "epoch": 0.6295671725688589,
      "grad_norm": 1.7707026206608905,
      "learning_rate": 5e-06,
      "loss": 0.4759,
      "step": 420
    },
    {
      "epoch": 0.6445568671538318,
      "grad_norm": 1.4832433269572964,
      "learning_rate": 5e-06,
      "loss": 0.4759,
      "step": 430
    },
    {
      "epoch": 0.6595465617388045,
      "grad_norm": 1.4849966253145612,
      "learning_rate": 5e-06,
      "loss": 0.4731,
      "step": 440
    },
    {
      "epoch": 0.6745362563237775,
      "grad_norm": 2.1406203761167037,
      "learning_rate": 5e-06,
      "loss": 0.4748,
      "step": 450
    },
    {
      "epoch": 0.6895259509087502,
      "grad_norm": 1.6432408076200942,
      "learning_rate": 5e-06,
      "loss": 0.4692,
      "step": 460
    },
    {
      "epoch": 0.704515645493723,
      "grad_norm": 2.110147852343459,
      "learning_rate": 5e-06,
      "loss": 0.469,
      "step": 470
    },
    {
      "epoch": 0.7195053400786959,
      "grad_norm": 2.67027429796622,
      "learning_rate": 5e-06,
      "loss": 0.4742,
      "step": 480
    },
    {
      "epoch": 0.7344950346636687,
      "grad_norm": 2.1612548231072197,
      "learning_rate": 5e-06,
      "loss": 0.4734,
      "step": 490
    },
    {
      "epoch": 0.7494847292486415,
      "grad_norm": 1.9020717675158103,
      "learning_rate": 5e-06,
      "loss": 0.4693,
      "step": 500
    },
    {
      "epoch": 0.7644744238336144,
      "grad_norm": 1.8918141412998646,
      "learning_rate": 5e-06,
      "loss": 0.4734,
      "step": 510
    },
    {
      "epoch": 0.7794641184185872,
      "grad_norm": 1.368955726552673,
      "learning_rate": 5e-06,
      "loss": 0.4663,
      "step": 520
    },
    {
      "epoch": 0.7944538130035601,
      "grad_norm": 1.5459750086281097,
      "learning_rate": 5e-06,
      "loss": 0.4645,
      "step": 530
    },
    {
      "epoch": 0.8094435075885329,
      "grad_norm": 1.5230854042747586,
      "learning_rate": 5e-06,
      "loss": 0.4647,
      "step": 540
    },
    {
      "epoch": 0.8244332021735057,
      "grad_norm": 1.5090270259811516,
      "learning_rate": 5e-06,
      "loss": 0.4707,
      "step": 550
    },
    {
      "epoch": 0.8394228967584786,
      "grad_norm": 1.5558244270343213,
      "learning_rate": 5e-06,
      "loss": 0.4674,
      "step": 560
    },
    {
      "epoch": 0.8544125913434514,
      "grad_norm": 1.4739129842995866,
      "learning_rate": 5e-06,
      "loss": 0.4678,
      "step": 570
    },
    {
      "epoch": 0.8694022859284242,
      "grad_norm": 1.7227702869131336,
      "learning_rate": 5e-06,
      "loss": 0.4614,
      "step": 580
    },
    {
      "epoch": 0.8843919805133971,
      "grad_norm": 1.412974957600055,
      "learning_rate": 5e-06,
      "loss": 0.4634,
      "step": 590
    },
    {
      "epoch": 0.8993816750983699,
      "grad_norm": 1.3755393868079429,
      "learning_rate": 5e-06,
      "loss": 0.4649,
      "step": 600
    },
    {
      "epoch": 0.9143713696833426,
      "grad_norm": 1.3451129180593917,
      "learning_rate": 5e-06,
      "loss": 0.4638,
      "step": 610
    },
    {
      "epoch": 0.9293610642683156,
      "grad_norm": 1.4949083165414878,
      "learning_rate": 5e-06,
      "loss": 0.4639,
      "step": 620
    },
    {
      "epoch": 0.9443507588532883,
      "grad_norm": 1.3507178958809956,
      "learning_rate": 5e-06,
      "loss": 0.4656,
      "step": 630
    },
    {
      "epoch": 0.9593404534382612,
      "grad_norm": 1.572459968859256,
      "learning_rate": 5e-06,
      "loss": 0.4592,
      "step": 640
    },
    {
      "epoch": 0.974330148023234,
      "grad_norm": 1.2767150139708328,
      "learning_rate": 5e-06,
      "loss": 0.4632,
      "step": 650
    },
    {
      "epoch": 0.9893198426082068,
      "grad_norm": 1.5510115795503987,
      "learning_rate": 5e-06,
      "loss": 0.4596,
      "step": 660
    },
    {
      "epoch": 0.9998126288176878,
      "eval_loss": 0.05758751183748245,
      "eval_runtime": 454.8318,
      "eval_samples_per_second": 39.525,
      "eval_steps_per_second": 0.618,
      "step": 667
    },
    {
      "epoch": 1.0043095371931796,
      "grad_norm": 2.7775612629774344,
      "learning_rate": 5e-06,
      "loss": 0.4348,
      "step": 670
    },
    {
      "epoch": 1.0192992317781526,
      "grad_norm": 1.9710376561762528,
      "learning_rate": 5e-06,
      "loss": 0.364,
      "step": 680
    },
    {
      "epoch": 1.0342889263631254,
      "grad_norm": 1.5909045555502788,
      "learning_rate": 5e-06,
      "loss": 0.3558,
      "step": 690
    },
    {
      "epoch": 1.0492786209480982,
      "grad_norm": 1.3602748984083428,
      "learning_rate": 5e-06,
      "loss": 0.355,
      "step": 700
    },
    {
      "epoch": 1.064268315533071,
      "grad_norm": 1.6434233988948692,
      "learning_rate": 5e-06,
      "loss": 0.3519,
      "step": 710
    },
    {
      "epoch": 1.0792580101180438,
      "grad_norm": 1.4242278638735506,
      "learning_rate": 5e-06,
      "loss": 0.3545,
      "step": 720
    },
    {
      "epoch": 1.0942477047030166,
      "grad_norm": 1.547462512141288,
      "learning_rate": 5e-06,
      "loss": 0.3583,
      "step": 730
    },
    {
      "epoch": 1.1092373992879896,
      "grad_norm": 1.4513237085400739,
      "learning_rate": 5e-06,
      "loss": 0.3558,
      "step": 740
    },
    {
      "epoch": 1.1242270938729624,
      "grad_norm": 2.1885817879178404,
      "learning_rate": 5e-06,
      "loss": 0.3563,
      "step": 750
    },
    {
      "epoch": 1.1392167884579352,
      "grad_norm": 1.695688809842665,
      "learning_rate": 5e-06,
      "loss": 0.358,
      "step": 760
    },
    {
      "epoch": 1.154206483042908,
      "grad_norm": 2.289531376884916,
      "learning_rate": 5e-06,
      "loss": 0.3574,
      "step": 770
    },
    {
      "epoch": 1.1691961776278808,
      "grad_norm": 1.9357596883149255,
      "learning_rate": 5e-06,
      "loss": 0.3584,
      "step": 780
    },
    {
      "epoch": 1.1841858722128538,
      "grad_norm": 2.1618585974064395,
      "learning_rate": 5e-06,
      "loss": 0.3564,
      "step": 790
    },
    {
      "epoch": 1.1991755667978266,
      "grad_norm": 1.6373234010519413,
      "learning_rate": 5e-06,
      "loss": 0.3527,
      "step": 800
    },
    {
      "epoch": 1.2141652613827993,
      "grad_norm": 1.8399099410223894,
      "learning_rate": 5e-06,
      "loss": 0.3566,
      "step": 810
    },
    {
      "epoch": 1.2291549559677721,
      "grad_norm": 1.6753343512169294,
      "learning_rate": 5e-06,
      "loss": 0.3601,
      "step": 820
    },
    {
      "epoch": 1.244144650552745,
      "grad_norm": 1.505241949293805,
      "learning_rate": 5e-06,
      "loss": 0.3583,
      "step": 830
    },
    {
      "epoch": 1.259134345137718,
      "grad_norm": 1.5312665902757236,
      "learning_rate": 5e-06,
      "loss": 0.3542,
      "step": 840
    },
    {
      "epoch": 1.2741240397226907,
      "grad_norm": 1.8665087434383938,
      "learning_rate": 5e-06,
      "loss": 0.3575,
      "step": 850
    },
    {
      "epoch": 1.2891137343076635,
      "grad_norm": 1.7982799864263068,
      "learning_rate": 5e-06,
      "loss": 0.3586,
      "step": 860
    },
    {
      "epoch": 1.3041034288926363,
      "grad_norm": 1.5371290759554668,
      "learning_rate": 5e-06,
      "loss": 0.3622,
      "step": 870
    },
    {
      "epoch": 1.319093123477609,
      "grad_norm": 1.5167552093630703,
      "learning_rate": 5e-06,
      "loss": 0.3588,
      "step": 880
    },
    {
      "epoch": 1.334082818062582,
      "grad_norm": 1.6591098979757748,
      "learning_rate": 5e-06,
      "loss": 0.3634,
      "step": 890
    },
    {
      "epoch": 1.3490725126475547,
      "grad_norm": 1.5726838898036415,
      "learning_rate": 5e-06,
      "loss": 0.3539,
      "step": 900
    },
    {
      "epoch": 1.3640622072325277,
      "grad_norm": 1.7507238369968354,
      "learning_rate": 5e-06,
      "loss": 0.3632,
      "step": 910
    },
    {
      "epoch": 1.3790519018175005,
      "grad_norm": 1.475358404698048,
      "learning_rate": 5e-06,
      "loss": 0.3625,
      "step": 920
    },
    {
      "epoch": 1.3940415964024733,
      "grad_norm": 1.5954088726182911,
      "learning_rate": 5e-06,
      "loss": 0.3595,
      "step": 930
    },
    {
      "epoch": 1.409031290987446,
      "grad_norm": 1.520181904849792,
      "learning_rate": 5e-06,
      "loss": 0.3597,
      "step": 940
    },
    {
      "epoch": 1.4240209855724189,
      "grad_norm": 1.6317070098760134,
      "learning_rate": 5e-06,
      "loss": 0.3611,
      "step": 950
    },
    {
      "epoch": 1.4390106801573919,
      "grad_norm": 1.768300641616324,
      "learning_rate": 5e-06,
      "loss": 0.3603,
      "step": 960
    },
    {
      "epoch": 1.4540003747423647,
      "grad_norm": 1.5408964888063073,
      "learning_rate": 5e-06,
      "loss": 0.3631,
      "step": 970
    },
    {
      "epoch": 1.4689900693273374,
      "grad_norm": 1.452167086951644,
      "learning_rate": 5e-06,
      "loss": 0.3609,
      "step": 980
    },
    {
      "epoch": 1.4839797639123102,
      "grad_norm": 1.6249338530074764,
      "learning_rate": 5e-06,
      "loss": 0.3625,
      "step": 990
    },
    {
      "epoch": 1.498969458497283,
      "grad_norm": 1.7743633699281656,
      "learning_rate": 5e-06,
      "loss": 0.3618,
      "step": 1000
    },
    {
      "epoch": 1.513959153082256,
      "grad_norm": 1.7741260951568605,
      "learning_rate": 5e-06,
      "loss": 0.3612,
      "step": 1010
    },
    {
      "epoch": 1.5289488476672288,
      "grad_norm": 1.3987893388986192,
      "learning_rate": 5e-06,
      "loss": 0.3628,
      "step": 1020
    },
    {
      "epoch": 1.5439385422522016,
      "grad_norm": 1.4893576161794635,
      "learning_rate": 5e-06,
      "loss": 0.3626,
      "step": 1030
    },
    {
      "epoch": 1.5589282368371744,
      "grad_norm": 1.4112328226196433,
      "learning_rate": 5e-06,
      "loss": 0.3618,
      "step": 1040
    },
    {
      "epoch": 1.5739179314221472,
      "grad_norm": 1.3858150270139942,
      "learning_rate": 5e-06,
      "loss": 0.3615,
      "step": 1050
    },
    {
      "epoch": 1.5889076260071202,
      "grad_norm": 1.5535049280480435,
      "learning_rate": 5e-06,
      "loss": 0.3618,
      "step": 1060
    },
    {
      "epoch": 1.6038973205920928,
      "grad_norm": 1.3757444255540903,
      "learning_rate": 5e-06,
      "loss": 0.365,
      "step": 1070
    },
    {
      "epoch": 1.6188870151770658,
      "grad_norm": 1.5995972790776192,
      "learning_rate": 5e-06,
      "loss": 0.3632,
      "step": 1080
    },
    {
      "epoch": 1.6338767097620386,
      "grad_norm": 1.7108799556122343,
      "learning_rate": 5e-06,
      "loss": 0.3643,
      "step": 1090
    },
    {
      "epoch": 1.6488664043470114,
      "grad_norm": 1.686754492103127,
      "learning_rate": 5e-06,
      "loss": 0.3649,
      "step": 1100
    },
    {
      "epoch": 1.6638560989319844,
      "grad_norm": 1.7693708666917307,
      "learning_rate": 5e-06,
      "loss": 0.3612,
      "step": 1110
    },
    {
      "epoch": 1.678845793516957,
      "grad_norm": 1.520817212897819,
      "learning_rate": 5e-06,
      "loss": 0.3614,
      "step": 1120
    },
    {
      "epoch": 1.69383548810193,
      "grad_norm": 1.9406706141560084,
      "learning_rate": 5e-06,
      "loss": 0.3601,
      "step": 1130
    },
    {
      "epoch": 1.7088251826869028,
      "grad_norm": 1.488137404772404,
      "learning_rate": 5e-06,
      "loss": 0.3627,
      "step": 1140
    },
    {
      "epoch": 1.7238148772718755,
      "grad_norm": 1.8331126631936938,
      "learning_rate": 5e-06,
      "loss": 0.3609,
      "step": 1150
    },
    {
      "epoch": 1.7388045718568486,
      "grad_norm": 1.5561141952783655,
      "learning_rate": 5e-06,
      "loss": 0.3601,
      "step": 1160
    },
    {
      "epoch": 1.7537942664418211,
      "grad_norm": 1.4134693187494294,
      "learning_rate": 5e-06,
      "loss": 0.3596,
      "step": 1170
    },
    {
      "epoch": 1.7687839610267941,
      "grad_norm": 1.696827607327685,
      "learning_rate": 5e-06,
      "loss": 0.3614,
      "step": 1180
    },
    {
      "epoch": 1.783773655611767,
      "grad_norm": 1.5042455149771978,
      "learning_rate": 5e-06,
      "loss": 0.3629,
      "step": 1190
    },
    {
      "epoch": 1.7987633501967397,
      "grad_norm": 1.619841917897079,
      "learning_rate": 5e-06,
      "loss": 0.364,
      "step": 1200
    },
    {
      "epoch": 1.8137530447817127,
      "grad_norm": 1.9678117854674795,
      "learning_rate": 5e-06,
      "loss": 0.3623,
      "step": 1210
    },
    {
      "epoch": 1.8287427393666853,
      "grad_norm": 2.000250566254895,
      "learning_rate": 5e-06,
      "loss": 0.3629,
      "step": 1220
    },
    {
      "epoch": 1.8437324339516583,
      "grad_norm": 1.7246823549895025,
      "learning_rate": 5e-06,
      "loss": 0.3639,
      "step": 1230
    },
    {
      "epoch": 1.858722128536631,
      "grad_norm": 1.9341838486216245,
      "learning_rate": 5e-06,
      "loss": 0.3614,
      "step": 1240
    },
    {
      "epoch": 1.873711823121604,
      "grad_norm": 1.6254030300504665,
      "learning_rate": 5e-06,
      "loss": 0.3628,
      "step": 1250
    },
    {
      "epoch": 1.8887015177065767,
      "grad_norm": 1.5870549405395955,
      "learning_rate": 5e-06,
      "loss": 0.3624,
      "step": 1260
    },
    {
      "epoch": 1.9036912122915495,
      "grad_norm": 1.5435102287374787,
      "learning_rate": 5e-06,
      "loss": 0.362,
      "step": 1270
    },
    {
      "epoch": 1.9186809068765225,
      "grad_norm": 1.4063275660945347,
      "learning_rate": 5e-06,
      "loss": 0.363,
      "step": 1280
    },
    {
      "epoch": 1.9336706014614953,
      "grad_norm": 1.5087142670105975,
      "learning_rate": 5e-06,
      "loss": 0.3587,
      "step": 1290
    },
    {
      "epoch": 1.948660296046468,
      "grad_norm": 1.3583330142096965,
      "learning_rate": 5e-06,
      "loss": 0.3608,
      "step": 1300
    },
    {
      "epoch": 1.9636499906314409,
      "grad_norm": 1.5780539376028968,
      "learning_rate": 5e-06,
      "loss": 0.3621,
      "step": 1310
    },
    {
      "epoch": 1.9786396852164136,
      "grad_norm": 1.451758117798617,
      "learning_rate": 5e-06,
      "loss": 0.3632,
      "step": 1320
    },
    {
      "epoch": 1.9936293798013867,
      "grad_norm": 1.428577561948826,
      "learning_rate": 5e-06,
      "loss": 0.3617,
      "step": 1330
    },
    {
      "epoch": 1.9996252576353757,
      "eval_loss": 0.056735917925834656,
      "eval_runtime": 450.721,
      "eval_samples_per_second": 39.885,
      "eval_steps_per_second": 0.623,
      "step": 1334
    },
    {
      "epoch": 2.0086190743863592,
      "grad_norm": 2.693760600411948,
      "learning_rate": 5e-06,
      "loss": 0.3009,
      "step": 1340
    },
    {
      "epoch": 2.0236087689713322,
      "grad_norm": 1.8123948443076334,
      "learning_rate": 5e-06,
      "loss": 0.2445,
      "step": 1350
    },
    {
      "epoch": 2.0385984635563053,
      "grad_norm": 1.8233844327944795,
      "learning_rate": 5e-06,
      "loss": 0.2404,
      "step": 1360
    },
    {
      "epoch": 2.053588158141278,
      "grad_norm": 1.659782737096887,
      "learning_rate": 5e-06,
      "loss": 0.2396,
      "step": 1370
    },
    {
      "epoch": 2.068577852726251,
      "grad_norm": 1.6369760989914484,
      "learning_rate": 5e-06,
      "loss": 0.2399,
      "step": 1380
    },
    {
      "epoch": 2.0835675473112234,
      "grad_norm": 1.6159958358268898,
      "learning_rate": 5e-06,
      "loss": 0.2398,
      "step": 1390
    },
    {
      "epoch": 2.0985572418961964,
      "grad_norm": 1.8629592527737424,
      "learning_rate": 5e-06,
      "loss": 0.2404,
      "step": 1400
    },
    {
      "epoch": 2.1135469364811694,
      "grad_norm": 1.9402493917715093,
      "learning_rate": 5e-06,
      "loss": 0.2406,
      "step": 1410
    },
    {
      "epoch": 2.128536631066142,
      "grad_norm": 1.9914438604583353,
      "learning_rate": 5e-06,
      "loss": 0.2445,
      "step": 1420
    },
    {
      "epoch": 2.143526325651115,
      "grad_norm": 1.6486122695508032,
      "learning_rate": 5e-06,
      "loss": 0.2428,
      "step": 1430
    },
    {
      "epoch": 2.1585160202360876,
      "grad_norm": 1.5254691785643584,
      "learning_rate": 5e-06,
      "loss": 0.2443,
      "step": 1440
    },
    {
      "epoch": 2.1735057148210606,
      "grad_norm": 1.9133206318932665,
      "learning_rate": 5e-06,
      "loss": 0.2431,
      "step": 1450
    },
    {
      "epoch": 2.188495409406033,
      "grad_norm": 1.6550777901047227,
      "learning_rate": 5e-06,
      "loss": 0.2448,
      "step": 1460
    },
    {
      "epoch": 2.203485103991006,
      "grad_norm": 1.8001235821461439,
      "learning_rate": 5e-06,
      "loss": 0.247,
      "step": 1470
    },
    {
      "epoch": 2.218474798575979,
      "grad_norm": 1.6442525813509412,
      "learning_rate": 5e-06,
      "loss": 0.2491,
      "step": 1480
    },
    {
      "epoch": 2.2334644931609517,
      "grad_norm": 1.6551298330853466,
      "learning_rate": 5e-06,
      "loss": 0.2485,
      "step": 1490
    },
    {
      "epoch": 2.2484541877459248,
      "grad_norm": 1.691060089285524,
      "learning_rate": 5e-06,
      "loss": 0.2463,
      "step": 1500
    },
    {
      "epoch": 2.2634438823308973,
      "grad_norm": 1.680873308991847,
      "learning_rate": 5e-06,
      "loss": 0.2486,
      "step": 1510
    },
    {
      "epoch": 2.2784335769158703,
      "grad_norm": 1.5264889834969293,
      "learning_rate": 5e-06,
      "loss": 0.2497,
      "step": 1520
    },
    {
      "epoch": 2.2934232715008434,
      "grad_norm": 1.9490999202092631,
      "learning_rate": 5e-06,
      "loss": 0.2492,
      "step": 1530
    },
    {
      "epoch": 2.308412966085816,
      "grad_norm": 1.5890774001111174,
      "learning_rate": 5e-06,
      "loss": 0.2503,
      "step": 1540
    },
    {
      "epoch": 2.323402660670789,
      "grad_norm": 1.8381634501461115,
      "learning_rate": 5e-06,
      "loss": 0.2505,
      "step": 1550
    },
    {
      "epoch": 2.3383923552557615,
      "grad_norm": 1.8112499776123423,
      "learning_rate": 5e-06,
      "loss": 0.2518,
      "step": 1560
    },
    {
      "epoch": 2.3533820498407345,
      "grad_norm": 1.7701674873383388,
      "learning_rate": 5e-06,
      "loss": 0.2504,
      "step": 1570
    },
    {
      "epoch": 2.3683717444257075,
      "grad_norm": 1.7787057235293418,
      "learning_rate": 5e-06,
      "loss": 0.2511,
      "step": 1580
    },
    {
      "epoch": 2.38336143901068,
      "grad_norm": 1.6220489456862308,
      "learning_rate": 5e-06,
      "loss": 0.2517,
      "step": 1590
    },
    {
      "epoch": 2.398351133595653,
      "grad_norm": 1.6092461385206882,
      "learning_rate": 5e-06,
      "loss": 0.2519,
      "step": 1600
    },
    {
      "epoch": 2.4133408281806257,
      "grad_norm": 1.6892803378685273,
      "learning_rate": 5e-06,
      "loss": 0.2537,
      "step": 1610
    },
    {
      "epoch": 2.4283305227655987,
      "grad_norm": 1.5514590659702057,
      "learning_rate": 5e-06,
      "loss": 0.2525,
      "step": 1620
    },
    {
      "epoch": 2.4433202173505713,
      "grad_norm": 1.6463095287912044,
      "learning_rate": 5e-06,
      "loss": 0.2519,
      "step": 1630
    },
    {
      "epoch": 2.4583099119355443,
      "grad_norm": 1.8642417904545223,
      "learning_rate": 5e-06,
      "loss": 0.2542,
      "step": 1640
    },
    {
      "epoch": 2.4732996065205173,
      "grad_norm": 2.1833462931941483,
      "learning_rate": 5e-06,
      "loss": 0.2523,
      "step": 1650
    },
    {
      "epoch": 2.48828930110549,
      "grad_norm": 1.7334334035624595,
      "learning_rate": 5e-06,
      "loss": 0.2525,
      "step": 1660
    },
    {
      "epoch": 2.503278995690463,
      "grad_norm": 1.996879481861675,
      "learning_rate": 5e-06,
      "loss": 0.2512,
      "step": 1670
    },
    {
      "epoch": 2.518268690275436,
      "grad_norm": 1.7646159599515048,
      "learning_rate": 5e-06,
      "loss": 0.2543,
      "step": 1680
    },
    {
      "epoch": 2.5332583848604084,
      "grad_norm": 1.5280180383047155,
      "learning_rate": 5e-06,
      "loss": 0.2542,
      "step": 1690
    },
    {
      "epoch": 2.5482480794453815,
      "grad_norm": 1.6854655209849605,
      "learning_rate": 5e-06,
      "loss": 0.2543,
      "step": 1700
    },
    {
      "epoch": 2.563237774030354,
      "grad_norm": 1.614184312338993,
      "learning_rate": 5e-06,
      "loss": 0.2547,
      "step": 1710
    },
    {
      "epoch": 2.578227468615327,
      "grad_norm": 1.7759088208026037,
      "learning_rate": 5e-06,
      "loss": 0.2577,
      "step": 1720
    },
    {
      "epoch": 2.5932171632002996,
      "grad_norm": 1.7074767316934885,
      "learning_rate": 5e-06,
      "loss": 0.2585,
      "step": 1730
    },
    {
      "epoch": 2.6082068577852726,
      "grad_norm": 1.666840211483153,
      "learning_rate": 5e-06,
      "loss": 0.2566,
      "step": 1740
    },
    {
      "epoch": 2.6231965523702456,
      "grad_norm": 1.5612601726380533,
      "learning_rate": 5e-06,
      "loss": 0.2577,
      "step": 1750
    },
    {
      "epoch": 2.638186246955218,
      "grad_norm": 1.6048678229351492,
      "learning_rate": 5e-06,
      "loss": 0.2584,
      "step": 1760
    },
    {
      "epoch": 2.653175941540191,
      "grad_norm": 1.535012707234654,
      "learning_rate": 5e-06,
      "loss": 0.258,
      "step": 1770
    },
    {
      "epoch": 2.668165636125164,
      "grad_norm": 1.5594137106457704,
      "learning_rate": 5e-06,
      "loss": 0.2596,
      "step": 1780
    },
    {
      "epoch": 2.683155330710137,
      "grad_norm": 1.7412507218140363,
      "learning_rate": 5e-06,
      "loss": 0.259,
      "step": 1790
    },
    {
      "epoch": 2.6981450252951094,
      "grad_norm": 1.8620927203026323,
      "learning_rate": 5e-06,
      "loss": 0.2613,
      "step": 1800
    },
    {
      "epoch": 2.7131347198800824,
      "grad_norm": 1.5875808505192006,
      "learning_rate": 5e-06,
      "loss": 0.2585,
      "step": 1810
    },
    {
      "epoch": 2.7281244144650554,
      "grad_norm": 1.6955850941699981,
      "learning_rate": 5e-06,
      "loss": 0.2597,
      "step": 1820
    },
    {
      "epoch": 2.743114109050028,
      "grad_norm": 1.7569205126042602,
      "learning_rate": 5e-06,
      "loss": 0.2571,
      "step": 1830
    },
    {
      "epoch": 2.758103803635001,
      "grad_norm": 1.519918624729941,
      "learning_rate": 5e-06,
      "loss": 0.263,
      "step": 1840
    },
    {
      "epoch": 2.773093498219974,
      "grad_norm": 1.5838501646665883,
      "learning_rate": 5e-06,
      "loss": 0.2608,
      "step": 1850
    },
    {
      "epoch": 2.7880831928049465,
      "grad_norm": 1.6657424039076156,
      "learning_rate": 5e-06,
      "loss": 0.2613,
      "step": 1860
    },
    {
      "epoch": 2.8030728873899196,
      "grad_norm": 1.595659803150772,
      "learning_rate": 5e-06,
      "loss": 0.2611,
      "step": 1870
    },
    {
      "epoch": 2.818062581974892,
      "grad_norm": 1.7789456591238404,
      "learning_rate": 5e-06,
      "loss": 0.2622,
      "step": 1880
    },
    {
      "epoch": 2.833052276559865,
      "grad_norm": 1.6114699686236196,
      "learning_rate": 5e-06,
      "loss": 0.2615,
      "step": 1890
    },
    {
      "epoch": 2.8480419711448377,
      "grad_norm": 1.6465619591478904,
      "learning_rate": 5e-06,
      "loss": 0.263,
      "step": 1900
    },
    {
      "epoch": 2.8630316657298107,
      "grad_norm": 1.6736896325417563,
      "learning_rate": 5e-06,
      "loss": 0.2649,
      "step": 1910
    },
    {
      "epoch": 2.8780213603147837,
      "grad_norm": 1.52817706604071,
      "learning_rate": 5e-06,
      "loss": 0.2611,
      "step": 1920
    },
    {
      "epoch": 2.8930110548997563,
      "grad_norm": 1.7454962824468059,
      "learning_rate": 5e-06,
      "loss": 0.2626,
      "step": 1930
    },
    {
      "epoch": 2.9080007494847293,
      "grad_norm": 1.6946473714595274,
      "learning_rate": 5e-06,
      "loss": 0.2627,
      "step": 1940
    },
    {
      "epoch": 2.9229904440697023,
      "grad_norm": 1.6411356019714227,
      "learning_rate": 5e-06,
      "loss": 0.2628,
      "step": 1950
    },
    {
      "epoch": 2.937980138654675,
      "grad_norm": 1.9705938078449712,
      "learning_rate": 5e-06,
      "loss": 0.2627,
      "step": 1960
    },
    {
      "epoch": 2.952969833239648,
      "grad_norm": 1.9589063291434328,
      "learning_rate": 5e-06,
      "loss": 0.2646,
      "step": 1970
    },
    {
      "epoch": 2.9679595278246205,
      "grad_norm": 1.6622226531628324,
      "learning_rate": 5e-06,
      "loss": 0.2637,
      "step": 1980
    },
    {
      "epoch": 2.9829492224095935,
      "grad_norm": 1.7651652877550925,
      "learning_rate": 5e-06,
      "loss": 0.2637,
      "step": 1990
    },
    {
      "epoch": 2.997938916994566,
      "grad_norm": 1.6491028582670904,
      "learning_rate": 5e-06,
      "loss": 0.2629,
      "step": 2000
    },
    {
      "epoch": 2.9994378864530633,
      "eval_loss": 0.061618607491254807,
      "eval_runtime": 450.5684,
      "eval_samples_per_second": 39.898,
      "eval_steps_per_second": 0.624,
      "step": 2001
    },
    {
      "epoch": 2.9994378864530633,
      "step": 2001,
      "total_flos": 3351540148469760.0,
      "train_loss": 0.37255630833932246,
      "train_runtime": 64694.9321,
      "train_samples_per_second": 15.838,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 10,
  "max_steps": 2001,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3351540148469760.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}