{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.995875721748694,
  "eval_steps": 500,
  "global_step": 1362,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021996150673632114,
      "grad_norm": 44.935070793507286,
      "learning_rate": 5e-06,
      "loss": 0.7982,
      "step": 10
    },
    {
      "epoch": 0.04399230134726423,
      "grad_norm": 51.99237463948744,
      "learning_rate": 5e-06,
      "loss": 0.6818,
      "step": 20
    },
    {
      "epoch": 0.06598845202089634,
      "grad_norm": 2.029518123215705,
      "learning_rate": 5e-06,
      "loss": 0.6576,
      "step": 30
    },
    {
      "epoch": 0.08798460269452846,
      "grad_norm": 0.8501991380139163,
      "learning_rate": 5e-06,
      "loss": 0.6179,
      "step": 40
    },
    {
      "epoch": 0.10998075336816057,
      "grad_norm": 0.7157876899989635,
      "learning_rate": 5e-06,
      "loss": 0.5951,
      "step": 50
    },
    {
      "epoch": 0.1319769040417927,
      "grad_norm": 0.6923489466872192,
      "learning_rate": 5e-06,
      "loss": 0.579,
      "step": 60
    },
    {
      "epoch": 0.1539730547154248,
      "grad_norm": 0.6162592994801409,
      "learning_rate": 5e-06,
      "loss": 0.5625,
      "step": 70
    },
    {
      "epoch": 0.17596920538905692,
      "grad_norm": 0.6070124857659416,
      "learning_rate": 5e-06,
      "loss": 0.5544,
      "step": 80
    },
    {
      "epoch": 0.19796535606268903,
      "grad_norm": 0.7389354403531135,
      "learning_rate": 5e-06,
      "loss": 0.5474,
      "step": 90
    },
    {
      "epoch": 0.21996150673632114,
      "grad_norm": 0.5830266561233308,
      "learning_rate": 5e-06,
      "loss": 0.5403,
      "step": 100
    },
    {
      "epoch": 0.24195765740995326,
      "grad_norm": 0.609863769379669,
      "learning_rate": 5e-06,
      "loss": 0.5409,
      "step": 110
    },
    {
      "epoch": 0.2639538080835854,
      "grad_norm": 0.5471425920538027,
      "learning_rate": 5e-06,
      "loss": 0.5282,
      "step": 120
    },
    {
      "epoch": 0.28594995875721746,
      "grad_norm": 0.5504648496085665,
      "learning_rate": 5e-06,
      "loss": 0.5315,
      "step": 130
    },
    {
      "epoch": 0.3079461094308496,
      "grad_norm": 0.5600291116467604,
      "learning_rate": 5e-06,
      "loss": 0.5307,
      "step": 140
    },
    {
      "epoch": 0.3299422601044817,
      "grad_norm": 0.6781742737436763,
      "learning_rate": 5e-06,
      "loss": 0.5256,
      "step": 150
    },
    {
      "epoch": 0.35193841077811383,
      "grad_norm": 0.5570436479921453,
      "learning_rate": 5e-06,
      "loss": 0.5236,
      "step": 160
    },
    {
      "epoch": 0.3739345614517459,
      "grad_norm": 0.7382087470875334,
      "learning_rate": 5e-06,
      "loss": 0.5148,
      "step": 170
    },
    {
      "epoch": 0.39593071212537806,
      "grad_norm": 0.6677212573270707,
      "learning_rate": 5e-06,
      "loss": 0.5147,
      "step": 180
    },
    {
      "epoch": 0.41792686279901015,
      "grad_norm": 0.6534622609569957,
      "learning_rate": 5e-06,
      "loss": 0.5184,
      "step": 190
    },
    {
      "epoch": 0.4399230134726423,
      "grad_norm": 0.6389305122495185,
      "learning_rate": 5e-06,
      "loss": 0.5099,
      "step": 200
    },
    {
      "epoch": 0.4619191641462744,
      "grad_norm": 0.5533607211490192,
      "learning_rate": 5e-06,
      "loss": 0.5117,
      "step": 210
    },
    {
      "epoch": 0.4839153148199065,
      "grad_norm": 0.5615265500686734,
      "learning_rate": 5e-06,
      "loss": 0.5055,
      "step": 220
    },
    {
      "epoch": 0.5059114654935386,
      "grad_norm": 0.6044913138154236,
      "learning_rate": 5e-06,
      "loss": 0.5043,
      "step": 230
    },
    {
      "epoch": 0.5279076161671707,
      "grad_norm": 0.6911732267120813,
      "learning_rate": 5e-06,
      "loss": 0.5084,
      "step": 240
    },
    {
      "epoch": 0.5499037668408029,
      "grad_norm": 0.6913728871930638,
      "learning_rate": 5e-06,
      "loss": 0.5007,
      "step": 250
    },
    {
      "epoch": 0.5718999175144349,
      "grad_norm": 0.5458408162252775,
      "learning_rate": 5e-06,
      "loss": 0.5004,
      "step": 260
    },
    {
      "epoch": 0.5938960681880671,
      "grad_norm": 0.4864371771009518,
      "learning_rate": 5e-06,
      "loss": 0.4997,
      "step": 270
    },
    {
      "epoch": 0.6158922188616992,
      "grad_norm": 0.5505465151810486,
      "learning_rate": 5e-06,
      "loss": 0.4933,
      "step": 280
    },
    {
      "epoch": 0.6378883695353313,
      "grad_norm": 0.5500982529995515,
      "learning_rate": 5e-06,
      "loss": 0.4969,
      "step": 290
    },
    {
      "epoch": 0.6598845202089634,
      "grad_norm": 0.6818273388657722,
      "learning_rate": 5e-06,
      "loss": 0.4971,
      "step": 300
    },
    {
      "epoch": 0.6818806708825955,
      "grad_norm": 0.8228558846974066,
      "learning_rate": 5e-06,
      "loss": 0.4883,
      "step": 310
    },
    {
      "epoch": 0.7038768215562277,
      "grad_norm": 0.5100124377410133,
      "learning_rate": 5e-06,
      "loss": 0.4912,
      "step": 320
    },
    {
      "epoch": 0.7258729722298598,
      "grad_norm": 0.5023160939160082,
      "learning_rate": 5e-06,
      "loss": 0.4961,
      "step": 330
    },
    {
      "epoch": 0.7478691229034918,
      "grad_norm": 0.5390556024217283,
      "learning_rate": 5e-06,
      "loss": 0.4879,
      "step": 340
    },
    {
      "epoch": 0.769865273577124,
      "grad_norm": 0.5699354382297954,
      "learning_rate": 5e-06,
      "loss": 0.4948,
      "step": 350
    },
    {
      "epoch": 0.7918614242507561,
      "grad_norm": 0.5193233018168463,
      "learning_rate": 5e-06,
      "loss": 0.491,
      "step": 360
    },
    {
      "epoch": 0.8138575749243883,
      "grad_norm": 0.4831702719594887,
      "learning_rate": 5e-06,
      "loss": 0.4924,
      "step": 370
    },
    {
      "epoch": 0.8358537255980203,
      "grad_norm": 0.46518212576460566,
      "learning_rate": 5e-06,
      "loss": 0.485,
      "step": 380
    },
    {
      "epoch": 0.8578498762716524,
      "grad_norm": 0.6352722047223296,
      "learning_rate": 5e-06,
      "loss": 0.4913,
      "step": 390
    },
    {
      "epoch": 0.8798460269452846,
      "grad_norm": 0.53358894593737,
      "learning_rate": 5e-06,
      "loss": 0.4946,
      "step": 400
    },
    {
      "epoch": 0.9018421776189167,
      "grad_norm": 0.7885388229348029,
      "learning_rate": 5e-06,
      "loss": 0.478,
      "step": 410
    },
    {
      "epoch": 0.9238383282925487,
      "grad_norm": 0.529600748072463,
      "learning_rate": 5e-06,
      "loss": 0.485,
      "step": 420
    },
    {
      "epoch": 0.9458344789661809,
      "grad_norm": 0.7784357593762018,
      "learning_rate": 5e-06,
      "loss": 0.4841,
      "step": 430
    },
    {
      "epoch": 0.967830629639813,
      "grad_norm": 0.5061344396278,
      "learning_rate": 5e-06,
      "loss": 0.4805,
      "step": 440
    },
    {
      "epoch": 0.9898267803134452,
      "grad_norm": 0.6066757845714082,
      "learning_rate": 5e-06,
      "loss": 0.4822,
      "step": 450
    },
    {
      "epoch": 0.998625240582898,
      "eval_loss": 0.4843384027481079,
      "eval_runtime": 321.1703,
      "eval_samples_per_second": 38.145,
      "eval_steps_per_second": 0.598,
      "step": 454
    },
    {
      "epoch": 1.0118229309870772,
      "grad_norm": 0.6845501483696066,
      "learning_rate": 5e-06,
      "loss": 0.4742,
      "step": 460
    },
    {
      "epoch": 1.0338190816607093,
      "grad_norm": 0.5184208422093173,
      "learning_rate": 5e-06,
      "loss": 0.4381,
      "step": 470
    },
    {
      "epoch": 1.0558152323343415,
      "grad_norm": 0.5477404832032738,
      "learning_rate": 5e-06,
      "loss": 0.4396,
      "step": 480
    },
    {
      "epoch": 1.0778113830079736,
      "grad_norm": 0.5481304063783221,
      "learning_rate": 5e-06,
      "loss": 0.436,
      "step": 490
    },
    {
      "epoch": 1.0998075336816058,
      "grad_norm": 0.560826060704074,
      "learning_rate": 5e-06,
      "loss": 0.4308,
      "step": 500
    },
    {
      "epoch": 1.121803684355238,
      "grad_norm": 0.5361777988288693,
      "learning_rate": 5e-06,
      "loss": 0.4368,
      "step": 510
    },
    {
      "epoch": 1.14379983502887,
      "grad_norm": 0.6716133763509267,
      "learning_rate": 5e-06,
      "loss": 0.4419,
      "step": 520
    },
    {
      "epoch": 1.165795985702502,
      "grad_norm": 0.5542234581455023,
      "learning_rate": 5e-06,
      "loss": 0.4361,
      "step": 530
    },
    {
      "epoch": 1.1877921363761341,
      "grad_norm": 0.7101633877411753,
      "learning_rate": 5e-06,
      "loss": 0.4345,
      "step": 540
    },
    {
      "epoch": 1.2097882870497663,
      "grad_norm": 0.5238276115814429,
      "learning_rate": 5e-06,
      "loss": 0.4339,
      "step": 550
    },
    {
      "epoch": 1.2317844377233984,
      "grad_norm": 0.603854926816251,
      "learning_rate": 5e-06,
      "loss": 0.4385,
      "step": 560
    },
    {
      "epoch": 1.2537805883970305,
      "grad_norm": 0.5352576431626216,
      "learning_rate": 5e-06,
      "loss": 0.4329,
      "step": 570
    },
    {
      "epoch": 1.2757767390706627,
      "grad_norm": 0.6947929349739098,
      "learning_rate": 5e-06,
      "loss": 0.4333,
      "step": 580
    },
    {
      "epoch": 1.2977728897442948,
      "grad_norm": 0.4804562251229763,
      "learning_rate": 5e-06,
      "loss": 0.4317,
      "step": 590
    },
    {
      "epoch": 1.3197690404179268,
      "grad_norm": 0.48050470497866915,
      "learning_rate": 5e-06,
      "loss": 0.4294,
      "step": 600
    },
    {
      "epoch": 1.341765191091559,
      "grad_norm": 0.5373174751277382,
      "learning_rate": 5e-06,
      "loss": 0.4305,
      "step": 610
    },
    {
      "epoch": 1.363761341765191,
      "grad_norm": 0.6344457366504956,
      "learning_rate": 5e-06,
      "loss": 0.4358,
      "step": 620
    },
    {
      "epoch": 1.3857574924388232,
      "grad_norm": 0.5663331681106669,
      "learning_rate": 5e-06,
      "loss": 0.433,
      "step": 630
    },
    {
      "epoch": 1.4077536431124553,
      "grad_norm": 0.5460973181725048,
      "learning_rate": 5e-06,
      "loss": 0.4316,
      "step": 640
    },
    {
      "epoch": 1.4297497937860875,
      "grad_norm": 0.5442052750881347,
      "learning_rate": 5e-06,
      "loss": 0.4309,
      "step": 650
    },
    {
      "epoch": 1.4517459444597196,
      "grad_norm": 0.5157106290187707,
      "learning_rate": 5e-06,
      "loss": 0.438,
      "step": 660
    },
    {
      "epoch": 1.4737420951333515,
      "grad_norm": 0.46892587832002125,
      "learning_rate": 5e-06,
      "loss": 0.4279,
      "step": 670
    },
    {
      "epoch": 1.495738245806984,
      "grad_norm": 0.5037695737266917,
      "learning_rate": 5e-06,
      "loss": 0.4326,
      "step": 680
    },
    {
      "epoch": 1.5177343964806158,
      "grad_norm": 0.48561399580013187,
      "learning_rate": 5e-06,
      "loss": 0.4359,
      "step": 690
    },
    {
      "epoch": 1.539730547154248,
      "grad_norm": 0.5653965550940685,
      "learning_rate": 5e-06,
      "loss": 0.4291,
      "step": 700
    },
    {
      "epoch": 1.56172669782788,
      "grad_norm": 0.5113826224264425,
      "learning_rate": 5e-06,
      "loss": 0.4303,
      "step": 710
    },
    {
      "epoch": 1.5837228485015122,
      "grad_norm": 0.7476801211084287,
      "learning_rate": 5e-06,
      "loss": 0.4324,
      "step": 720
    },
    {
      "epoch": 1.6057189991751444,
      "grad_norm": 0.4798585808975909,
      "learning_rate": 5e-06,
      "loss": 0.4345,
      "step": 730
    },
    {
      "epoch": 1.6277151498487763,
      "grad_norm": 0.5013555582898901,
      "learning_rate": 5e-06,
      "loss": 0.4311,
      "step": 740
    },
    {
      "epoch": 1.6497113005224087,
      "grad_norm": 0.5533026167279893,
      "learning_rate": 5e-06,
      "loss": 0.4297,
      "step": 750
    },
    {
      "epoch": 1.6717074511960406,
      "grad_norm": 0.5907648181268995,
      "learning_rate": 5e-06,
      "loss": 0.4258,
      "step": 760
    },
    {
      "epoch": 1.693703601869673,
      "grad_norm": 0.5116875739971738,
      "learning_rate": 5e-06,
      "loss": 0.4308,
      "step": 770
    },
    {
      "epoch": 1.7156997525433049,
      "grad_norm": 0.525277015168684,
      "learning_rate": 5e-06,
      "loss": 0.4278,
      "step": 780
    },
    {
      "epoch": 1.737695903216937,
      "grad_norm": 0.5212298654810674,
      "learning_rate": 5e-06,
      "loss": 0.4267,
      "step": 790
    },
    {
      "epoch": 1.7596920538905692,
      "grad_norm": 0.6835093490085559,
      "learning_rate": 5e-06,
      "loss": 0.4323,
      "step": 800
    },
    {
      "epoch": 1.7816882045642013,
      "grad_norm": 0.8213379235049009,
      "learning_rate": 5e-06,
      "loss": 0.4265,
      "step": 810
    },
    {
      "epoch": 1.8036843552378334,
      "grad_norm": 0.671899265464039,
      "learning_rate": 5e-06,
      "loss": 0.4299,
      "step": 820
    },
    {
      "epoch": 1.8256805059114654,
      "grad_norm": 0.7589383979560413,
      "learning_rate": 5e-06,
      "loss": 0.4254,
      "step": 830
    },
    {
      "epoch": 1.8476766565850977,
      "grad_norm": 0.6394372109420436,
      "learning_rate": 5e-06,
      "loss": 0.4268,
      "step": 840
    },
    {
      "epoch": 1.8696728072587296,
      "grad_norm": 0.5031956602689452,
      "learning_rate": 5e-06,
      "loss": 0.4229,
      "step": 850
    },
    {
      "epoch": 1.8916689579323618,
      "grad_norm": 0.7072710176459912,
      "learning_rate": 5e-06,
      "loss": 0.4238,
      "step": 860
    },
    {
      "epoch": 1.913665108605994,
      "grad_norm": 0.5781484479035767,
      "learning_rate": 5e-06,
      "loss": 0.4267,
      "step": 870
    },
    {
      "epoch": 1.935661259279626,
      "grad_norm": 0.50576234221162,
      "learning_rate": 5e-06,
      "loss": 0.426,
      "step": 880
    },
    {
      "epoch": 1.9576574099532582,
      "grad_norm": 0.559285180763617,
      "learning_rate": 5e-06,
      "loss": 0.4274,
      "step": 890
    },
    {
      "epoch": 1.9796535606268901,
      "grad_norm": 0.4843867002926747,
      "learning_rate": 5e-06,
      "loss": 0.4246,
      "step": 900
    },
    {
      "epoch": 1.9994500962331592,
      "eval_loss": 0.46506866812705994,
      "eval_runtime": 316.6503,
      "eval_samples_per_second": 38.689,
      "eval_steps_per_second": 0.606,
      "step": 909
    },
    {
      "epoch": 2.0016497113005225,
      "grad_norm": 0.8494799052840408,
      "learning_rate": 5e-06,
      "loss": 0.4343,
      "step": 910
    },
    {
      "epoch": 2.0236458619741544,
      "grad_norm": 0.7542208485006762,
      "learning_rate": 5e-06,
      "loss": 0.3763,
      "step": 920
    },
    {
      "epoch": 2.045642012647787,
      "grad_norm": 0.5843095386968228,
      "learning_rate": 5e-06,
      "loss": 0.3715,
      "step": 930
    },
    {
      "epoch": 2.0676381633214187,
      "grad_norm": 0.8058969339731762,
      "learning_rate": 5e-06,
      "loss": 0.3793,
      "step": 940
    },
    {
      "epoch": 2.089634313995051,
      "grad_norm": 0.8326514799311344,
      "learning_rate": 5e-06,
      "loss": 0.3768,
      "step": 950
    },
    {
      "epoch": 2.111630464668683,
      "grad_norm": 0.6448233607735808,
      "learning_rate": 5e-06,
      "loss": 0.381,
      "step": 960
    },
    {
      "epoch": 2.133626615342315,
      "grad_norm": 0.5603778242637936,
      "learning_rate": 5e-06,
      "loss": 0.3779,
      "step": 970
    },
    {
      "epoch": 2.1556227660159473,
      "grad_norm": 0.7046094765859149,
      "learning_rate": 5e-06,
      "loss": 0.3757,
      "step": 980
    },
    {
      "epoch": 2.177618916689579,
      "grad_norm": 0.6615858803316566,
      "learning_rate": 5e-06,
      "loss": 0.3799,
      "step": 990
    },
    {
      "epoch": 2.1996150673632116,
      "grad_norm": 0.5789910902142025,
      "learning_rate": 5e-06,
      "loss": 0.3791,
      "step": 1000
    },
    {
      "epoch": 2.2216112180368435,
      "grad_norm": 0.6112779977098899,
      "learning_rate": 5e-06,
      "loss": 0.3767,
      "step": 1010
    },
    {
      "epoch": 2.243607368710476,
      "grad_norm": 0.5885271436566493,
      "learning_rate": 5e-06,
      "loss": 0.3775,
      "step": 1020
    },
    {
      "epoch": 2.2656035193841078,
      "grad_norm": 0.6688990731888627,
      "learning_rate": 5e-06,
      "loss": 0.3776,
      "step": 1030
    },
    {
      "epoch": 2.28759967005774,
      "grad_norm": 0.7043543929663795,
      "learning_rate": 5e-06,
      "loss": 0.3768,
      "step": 1040
    },
    {
      "epoch": 2.309595820731372,
      "grad_norm": 0.7912879028175118,
      "learning_rate": 5e-06,
      "loss": 0.3743,
      "step": 1050
    },
    {
      "epoch": 2.331591971405004,
      "grad_norm": 0.6172549511091338,
      "learning_rate": 5e-06,
      "loss": 0.3817,
      "step": 1060
    },
    {
      "epoch": 2.3535881220786363,
      "grad_norm": 0.5772395414215311,
      "learning_rate": 5e-06,
      "loss": 0.3782,
      "step": 1070
    },
    {
      "epoch": 2.3755842727522682,
      "grad_norm": 0.5396724355578864,
      "learning_rate": 5e-06,
      "loss": 0.3802,
      "step": 1080
    },
    {
      "epoch": 2.3975804234259006,
      "grad_norm": 0.5780443375091662,
      "learning_rate": 5e-06,
      "loss": 0.3756,
      "step": 1090
    },
    {
      "epoch": 2.4195765740995325,
      "grad_norm": 0.7751240393805268,
      "learning_rate": 5e-06,
      "loss": 0.3792,
      "step": 1100
    },
    {
      "epoch": 2.441572724773165,
      "grad_norm": 0.568262735148636,
      "learning_rate": 5e-06,
      "loss": 0.3842,
      "step": 1110
    },
    {
      "epoch": 2.463568875446797,
      "grad_norm": 0.7876139455832769,
      "learning_rate": 5e-06,
      "loss": 0.3767,
      "step": 1120
    },
    {
      "epoch": 2.4855650261204287,
      "grad_norm": 0.6545602235246707,
      "learning_rate": 5e-06,
      "loss": 0.3827,
      "step": 1130
    },
    {
      "epoch": 2.507561176794061,
      "grad_norm": 0.6169218266323959,
      "learning_rate": 5e-06,
      "loss": 0.3849,
      "step": 1140
    },
    {
      "epoch": 2.529557327467693,
      "grad_norm": 0.5892651118636095,
      "learning_rate": 5e-06,
      "loss": 0.3813,
      "step": 1150
    },
    {
      "epoch": 2.5515534781413254,
      "grad_norm": 0.6065064990736145,
      "learning_rate": 5e-06,
      "loss": 0.3804,
      "step": 1160
    },
    {
      "epoch": 2.5735496288149573,
      "grad_norm": 0.5193806106328419,
      "learning_rate": 5e-06,
      "loss": 0.3751,
      "step": 1170
    },
    {
      "epoch": 2.5955457794885897,
      "grad_norm": 0.8060929375102633,
      "learning_rate": 5e-06,
      "loss": 0.3731,
      "step": 1180
    },
    {
      "epoch": 2.6175419301622216,
      "grad_norm": 0.5602720976042392,
      "learning_rate": 5e-06,
      "loss": 0.3757,
      "step": 1190
    },
    {
      "epoch": 2.6395380808358535,
      "grad_norm": 0.5369906898701031,
      "learning_rate": 5e-06,
      "loss": 0.3742,
      "step": 1200
    },
    {
      "epoch": 2.661534231509486,
      "grad_norm": 0.5808022200937785,
      "learning_rate": 5e-06,
      "loss": 0.3753,
      "step": 1210
    },
    {
      "epoch": 2.683530382183118,
      "grad_norm": 0.5699624059009394,
      "learning_rate": 5e-06,
      "loss": 0.3741,
      "step": 1220
    },
    {
      "epoch": 2.70552653285675,
      "grad_norm": 0.591131213351509,
      "learning_rate": 5e-06,
      "loss": 0.3785,
      "step": 1230
    },
    {
      "epoch": 2.727522683530382,
      "grad_norm": 0.6838767595972525,
      "learning_rate": 5e-06,
      "loss": 0.3761,
      "step": 1240
    },
    {
      "epoch": 2.7495188342040144,
      "grad_norm": 0.584986984671218,
      "learning_rate": 5e-06,
      "loss": 0.3748,
      "step": 1250
    },
    {
      "epoch": 2.7715149848776464,
      "grad_norm": 0.8416063162832514,
      "learning_rate": 5e-06,
      "loss": 0.3728,
      "step": 1260
    },
    {
      "epoch": 2.7935111355512783,
      "grad_norm": 0.5715014930298087,
      "learning_rate": 5e-06,
      "loss": 0.3794,
      "step": 1270
    },
    {
      "epoch": 2.8155072862249106,
      "grad_norm": 0.5701895352860433,
      "learning_rate": 5e-06,
      "loss": 0.3789,
      "step": 1280
    },
    {
      "epoch": 2.837503436898543,
      "grad_norm": 0.5198659680168832,
      "learning_rate": 5e-06,
      "loss": 0.3732,
      "step": 1290
    },
    {
      "epoch": 2.859499587572175,
      "grad_norm": 0.642696455858834,
      "learning_rate": 5e-06,
      "loss": 0.3741,
      "step": 1300
    },
    {
      "epoch": 2.881495738245807,
      "grad_norm": 0.5347069585895822,
      "learning_rate": 5e-06,
      "loss": 0.3753,
      "step": 1310
    },
    {
      "epoch": 2.903491888919439,
      "grad_norm": 0.6499155207375088,
      "learning_rate": 5e-06,
      "loss": 0.3756,
      "step": 1320
    },
    {
      "epoch": 2.925488039593071,
      "grad_norm": 0.7295378497969262,
      "learning_rate": 5e-06,
      "loss": 0.378,
      "step": 1330
    },
    {
      "epoch": 2.947484190266703,
      "grad_norm": 0.6568947705176402,
      "learning_rate": 5e-06,
      "loss": 0.3795,
      "step": 1340
    },
    {
      "epoch": 2.9694803409403354,
      "grad_norm": 0.532205526706625,
      "learning_rate": 5e-06,
      "loss": 0.3742,
      "step": 1350
    },
    {
      "epoch": 2.991476491613968,
      "grad_norm": 0.5881809630311479,
      "learning_rate": 5e-06,
      "loss": 0.3735,
      "step": 1360
    },
    {
      "epoch": 2.995875721748694,
      "eval_loss": 0.46309909224510193,
      "eval_runtime": 307.2866,
      "eval_samples_per_second": 39.868,
      "eval_steps_per_second": 0.625,
      "step": 1362
    },
    {
      "epoch": 2.995875721748694,
      "step": 1362,
      "total_flos": 2281191348633600.0,
      "train_loss": 0.44531785190192963,
      "train_runtime": 45435.4893,
      "train_samples_per_second": 15.368,
      "train_steps_per_second": 0.03
    }
  ],
  "logging_steps": 10,
  "max_steps": 1362,
  "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": 2281191348633600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}