{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9996634885025238,
  "eval_steps": 500,
  "global_step": 1114,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0089736399326977,
      "grad_norm": 2.1750009059906006,
      "learning_rate": 2e-05,
      "loss": 1.9421,
      "step": 10
    },
    {
      "epoch": 0.0179472798653954,
      "grad_norm": 1.2129733562469482,
      "learning_rate": 4e-05,
      "loss": 1.6421,
      "step": 20
    },
    {
      "epoch": 0.0269209197980931,
      "grad_norm": 1.2686073780059814,
      "learning_rate": 6e-05,
      "loss": 1.6084,
      "step": 30
    },
    {
      "epoch": 0.0358945597307908,
      "grad_norm": 0.8401476740837097,
      "learning_rate": 8e-05,
      "loss": 1.4811,
      "step": 40
    },
    {
      "epoch": 0.044868199663488505,
      "grad_norm": 1.3034749031066895,
      "learning_rate": 0.0001,
      "loss": 1.4327,
      "step": 50
    },
    {
      "epoch": 0.0538418395961862,
      "grad_norm": 0.6824946403503418,
      "learning_rate": 0.00012,
      "loss": 1.4694,
      "step": 60
    },
    {
      "epoch": 0.0628154795288839,
      "grad_norm": 0.670620858669281,
      "learning_rate": 0.00014,
      "loss": 1.3643,
      "step": 70
    },
    {
      "epoch": 0.0717891194615816,
      "grad_norm": 0.8601792454719543,
      "learning_rate": 0.00016,
      "loss": 1.3669,
      "step": 80
    },
    {
      "epoch": 0.08076275939427931,
      "grad_norm": 0.6021562814712524,
      "learning_rate": 0.00018,
      "loss": 1.3697,
      "step": 90
    },
    {
      "epoch": 0.08973639932697701,
      "grad_norm": 0.672222912311554,
      "learning_rate": 0.0002,
      "loss": 1.3505,
      "step": 100
    },
    {
      "epoch": 0.09871003925967471,
      "grad_norm": 0.5645850896835327,
      "learning_rate": 0.00019995200907733468,
      "loss": 1.3051,
      "step": 110
    },
    {
      "epoch": 0.1076836791923724,
      "grad_norm": 0.6567140817642212,
      "learning_rate": 0.00019980808237191178,
      "loss": 1.3072,
      "step": 120
    },
    {
      "epoch": 0.1166573191250701,
      "grad_norm": 0.5479955077171326,
      "learning_rate": 0.00019956835802723916,
      "loss": 1.42,
      "step": 130
    },
    {
      "epoch": 0.1256309590577678,
      "grad_norm": 0.710563600063324,
      "learning_rate": 0.0001992330661351665,
      "loss": 1.318,
      "step": 140
    },
    {
      "epoch": 0.1346045989904655,
      "grad_norm": 0.5019824504852295,
      "learning_rate": 0.00019880252851503915,
      "loss": 1.3518,
      "step": 150
    },
    {
      "epoch": 0.1435782389231632,
      "grad_norm": 0.783736526966095,
      "learning_rate": 0.0001982771584048096,
      "loss": 1.3841,
      "step": 160
    },
    {
      "epoch": 0.1525518788558609,
      "grad_norm": 0.5478121042251587,
      "learning_rate": 0.00019765746006440455,
      "loss": 1.2956,
      "step": 170
    },
    {
      "epoch": 0.16152551878855861,
      "grad_norm": 0.675541877746582,
      "learning_rate": 0.00019694402829172663,
      "loss": 1.4014,
      "step": 180
    },
    {
      "epoch": 0.17049915872125632,
      "grad_norm": 0.7109649777412415,
      "learning_rate": 0.0001961375478517564,
      "loss": 1.2814,
      "step": 190
    },
    {
      "epoch": 0.17947279865395402,
      "grad_norm": 0.6496264338493347,
      "learning_rate": 0.00019523879281930235,
      "loss": 1.33,
      "step": 200
    },
    {
      "epoch": 0.18844643858665172,
      "grad_norm": 0.7981849908828735,
      "learning_rate": 0.00019424862583602965,
      "loss": 1.3878,
      "step": 210
    },
    {
      "epoch": 0.19742007851934942,
      "grad_norm": 0.5120641589164734,
      "learning_rate": 0.00019316799728248075,
      "loss": 1.2728,
      "step": 220
    },
    {
      "epoch": 0.2063937184520471,
      "grad_norm": 0.5666424632072449,
      "learning_rate": 0.00019199794436588243,
      "loss": 1.3446,
      "step": 230
    },
    {
      "epoch": 0.2153673583847448,
      "grad_norm": 0.6776772141456604,
      "learning_rate": 0.00019073959012461545,
      "loss": 1.3373,
      "step": 240
    },
    {
      "epoch": 0.2243409983174425,
      "grad_norm": 0.7518035173416138,
      "learning_rate": 0.00018939414235030134,
      "loss": 1.3381,
      "step": 250
    },
    {
      "epoch": 0.2333146382501402,
      "grad_norm": 0.6173065304756165,
      "learning_rate": 0.0001879628924285419,
      "loss": 1.3331,
      "step": 260
    },
    {
      "epoch": 0.2422882781828379,
      "grad_norm": 0.6449307203292847,
      "learning_rate": 0.00018644721409942323,
      "loss": 1.3048,
      "step": 270
    },
    {
      "epoch": 0.2512619181155356,
      "grad_norm": 0.7187690734863281,
      "learning_rate": 0.00018484856213897498,
      "loss": 1.3328,
      "step": 280
    },
    {
      "epoch": 0.26023555804823334,
      "grad_norm": 0.5725300312042236,
      "learning_rate": 0.00018316847096284917,
      "loss": 1.4003,
      "step": 290
    },
    {
      "epoch": 0.269209197980931,
      "grad_norm": 5.041274070739746,
      "learning_rate": 0.0001814085531535599,
      "loss": 1.3066,
      "step": 300
    },
    {
      "epoch": 0.2781828379136287,
      "grad_norm": 0.4397372603416443,
      "learning_rate": 0.00017957049791269685,
      "loss": 1.3193,
      "step": 310
    },
    {
      "epoch": 0.2871564778463264,
      "grad_norm": 0.5465174913406372,
      "learning_rate": 0.00017765606943959833,
      "loss": 1.2508,
      "step": 320
    },
    {
      "epoch": 0.2961301177790241,
      "grad_norm": 0.5439965724945068,
      "learning_rate": 0.00017566710523804043,
      "loss": 1.3258,
      "step": 330
    },
    {
      "epoch": 0.3051037577117218,
      "grad_norm": 0.6401047110557556,
      "learning_rate": 0.00017360551435256674,
      "loss": 1.3563,
      "step": 340
    },
    {
      "epoch": 0.3140773976444195,
      "grad_norm": 0.5497185587882996,
      "learning_rate": 0.0001714732755361523,
      "loss": 1.267,
      "step": 350
    },
    {
      "epoch": 0.32305103757711723,
      "grad_norm": 0.6040382981300354,
      "learning_rate": 0.00016927243535095997,
      "loss": 1.3057,
      "step": 360
    },
    {
      "epoch": 0.3320246775098149,
      "grad_norm": 0.6971787810325623,
      "learning_rate": 0.00016700510620401224,
      "loss": 1.4139,
      "step": 370
    },
    {
      "epoch": 0.34099831744251263,
      "grad_norm": 0.5650486946105957,
      "learning_rate": 0.00016467346431966413,
      "loss": 1.3388,
      "step": 380
    },
    {
      "epoch": 0.3499719573752103,
      "grad_norm": 0.5824179649353027,
      "learning_rate": 0.00016227974765082274,
      "loss": 1.3194,
      "step": 390
    },
    {
      "epoch": 0.35894559730790804,
      "grad_norm": 0.4857507646083832,
      "learning_rate": 0.00015982625373091875,
      "loss": 1.3274,
      "step": 400
    },
    {
      "epoch": 0.3679192372406057,
      "grad_norm": 0.49048104882240295,
      "learning_rate": 0.00015731533746869163,
      "loss": 1.2175,
      "step": 410
    },
    {
      "epoch": 0.37689287717330344,
      "grad_norm": 0.5631568431854248,
      "learning_rate": 0.00015474940888790455,
      "loss": 1.2392,
      "step": 420
    },
    {
      "epoch": 0.3858665171060011,
      "grad_norm": 0.5326385498046875,
      "learning_rate": 0.0001521309308141592,
      "loss": 1.3241,
      "step": 430
    },
    {
      "epoch": 0.39484015703869885,
      "grad_norm": 0.4978722631931305,
      "learning_rate": 0.00014946241651103034,
      "loss": 1.2032,
      "step": 440
    },
    {
      "epoch": 0.4038137969713965,
      "grad_norm": 0.4760749936103821,
      "learning_rate": 0.00014674642726778906,
      "loss": 1.2336,
      "step": 450
    },
    {
      "epoch": 0.4127874369040942,
      "grad_norm": 0.5480512380599976,
      "learning_rate": 0.00014398556994102996,
      "loss": 1.3644,
      "step": 460
    },
    {
      "epoch": 0.4217610768367919,
      "grad_norm": 0.5921517014503479,
      "learning_rate": 0.00014118249445256223,
      "loss": 1.2761,
      "step": 470
    },
    {
      "epoch": 0.4307347167694896,
      "grad_norm": 0.505266547203064,
      "learning_rate": 0.00013833989124596572,
      "loss": 1.2971,
      "step": 480
    },
    {
      "epoch": 0.43970835670218733,
      "grad_norm": 0.432982861995697,
      "learning_rate": 0.00013546048870425356,
      "loss": 1.2217,
      "step": 490
    },
    {
      "epoch": 0.448681996634885,
      "grad_norm": 0.5738311409950256,
      "learning_rate": 0.0001325470505311198,
      "loss": 1.2898,
      "step": 500
    },
    {
      "epoch": 0.45765563656758274,
      "grad_norm": 0.6067373752593994,
      "learning_rate": 0.0001296023730982855,
      "loss": 1.3245,
      "step": 510
    },
    {
      "epoch": 0.4666292765002804,
      "grad_norm": 0.5424025058746338,
      "learning_rate": 0.00012662928276148985,
      "loss": 1.2277,
      "step": 520
    },
    {
      "epoch": 0.47560291643297814,
      "grad_norm": 0.5827418565750122,
      "learning_rate": 0.00012363063314770135,
      "loss": 1.2828,
      "step": 530
    },
    {
      "epoch": 0.4845765563656758,
      "grad_norm": 0.5253446102142334,
      "learning_rate": 0.0001206093024161544,
      "loss": 1.2969,
      "step": 540
    },
    {
      "epoch": 0.49355019629837354,
      "grad_norm": 0.6067509055137634,
      "learning_rate": 0.00011756819049583861,
      "loss": 1.3125,
      "step": 550
    },
    {
      "epoch": 0.5025238362310712,
      "grad_norm": 0.5548892617225647,
      "learning_rate": 0.00011451021630209371,
      "loss": 1.2726,
      "step": 560
    },
    {
      "epoch": 0.511497476163769,
      "grad_norm": 0.6270582675933838,
      "learning_rate": 0.0001114383149349806,
      "loss": 1.241,
      "step": 570
    },
    {
      "epoch": 0.5204711160964667,
      "grad_norm": 0.5589553117752075,
      "learning_rate": 0.00010835543486211815,
      "loss": 1.2897,
      "step": 580
    },
    {
      "epoch": 0.5294447560291643,
      "grad_norm": 0.5768513083457947,
      "learning_rate": 0.00010526453508868961,
      "loss": 1.266,
      "step": 590
    },
    {
      "epoch": 0.538418395961862,
      "grad_norm": 0.6176390051841736,
      "learning_rate": 0.00010216858231733488,
      "loss": 1.2771,
      "step": 600
    },
    {
      "epoch": 0.5473920358945598,
      "grad_norm": 0.5259169340133667,
      "learning_rate": 9.907054810065446e-05,
      "loss": 1.314,
      "step": 610
    },
    {
      "epoch": 0.5563656758272574,
      "grad_norm": 0.48984938859939575,
      "learning_rate": 9.597340598905852e-05,
      "loss": 1.2227,
      "step": 620
    },
    {
      "epoch": 0.5653393157599551,
      "grad_norm": 0.504762589931488,
      "learning_rate": 9.28801286766982e-05,
      "loss": 1.2152,
      "step": 630
    },
    {
      "epoch": 0.5743129556926528,
      "grad_norm": 0.6546471118927002,
      "learning_rate": 8.979368514821916e-05,
      "loss": 1.2996,
      "step": 640
    },
    {
      "epoch": 0.5832865956253506,
      "grad_norm": 0.6191439032554626,
      "learning_rate": 8.671703782907518e-05,
      "loss": 1.2966,
      "step": 650
    },
    {
      "epoch": 0.5922602355580482,
      "grad_norm": 0.4806272089481354,
      "learning_rate": 8.365313974213737e-05,
      "loss": 1.2665,
      "step": 660
    },
    {
      "epoch": 0.6012338754907459,
      "grad_norm": 0.4365353286266327,
      "learning_rate": 8.060493167332874e-05,
      "loss": 1.2466,
      "step": 670
    },
    {
      "epoch": 0.6102075154234436,
      "grad_norm": 0.5589653849601746,
      "learning_rate": 7.757533934900316e-05,
      "loss": 1.2992,
      "step": 680
    },
    {
      "epoch": 0.6191811553561414,
      "grad_norm": 0.6361960172653198,
      "learning_rate": 7.456727062777958e-05,
      "loss": 1.2096,
      "step": 690
    },
    {
      "epoch": 0.628154795288839,
      "grad_norm": 0.6086412072181702,
      "learning_rate": 7.15836127095254e-05,
      "loss": 1.3301,
      "step": 700
    },
    {
      "epoch": 0.6371284352215367,
      "grad_norm": 0.5902493596076965,
      "learning_rate": 6.862722936416897e-05,
      "loss": 1.3265,
      "step": 710
    },
    {
      "epoch": 0.6461020751542345,
      "grad_norm": 0.4792775809764862,
      "learning_rate": 6.570095818300012e-05,
      "loss": 1.2416,
      "step": 720
    },
    {
      "epoch": 0.6550757150869322,
      "grad_norm": 0.48689934611320496,
      "learning_rate": 6.280760785509801e-05,
      "loss": 1.2668,
      "step": 730
    },
    {
      "epoch": 0.6640493550196298,
      "grad_norm": 0.5720877051353455,
      "learning_rate": 5.9949955471499186e-05,
      "loss": 1.2979,
      "step": 740
    },
    {
      "epoch": 0.6730229949523275,
      "grad_norm": 0.6165252327919006,
      "learning_rate": 5.713074385969457e-05,
      "loss": 1.2269,
      "step": 750
    },
    {
      "epoch": 0.6819966348850253,
      "grad_norm": 0.554986298084259,
      "learning_rate": 5.435267895101302e-05,
      "loss": 1.3656,
      "step": 760
    },
    {
      "epoch": 0.6909702748177229,
      "grad_norm": 0.6707109808921814,
      "learning_rate": 5.161842718341825e-05,
      "loss": 1.3012,
      "step": 770
    },
    {
      "epoch": 0.6999439147504206,
      "grad_norm": 0.45011788606643677,
      "learning_rate": 4.8930612942212916e-05,
      "loss": 1.2375,
      "step": 780
    },
    {
      "epoch": 0.7089175546831183,
      "grad_norm": 0.5251748561859131,
      "learning_rate": 4.629181604110464e-05,
      "loss": 1.2007,
      "step": 790
    },
    {
      "epoch": 0.7178911946158161,
      "grad_norm": 0.5204996466636658,
      "learning_rate": 4.3704569246053805e-05,
      "loss": 1.3049,
      "step": 800
    },
    {
      "epoch": 0.7268648345485137,
      "grad_norm": 0.6533709764480591,
      "learning_rate": 4.1171355844277394e-05,
      "loss": 1.293,
      "step": 810
    },
    {
      "epoch": 0.7358384744812114,
      "grad_norm": 0.589524507522583,
      "learning_rate": 3.869460726074474e-05,
      "loss": 1.3565,
      "step": 820
    },
    {
      "epoch": 0.7448121144139092,
      "grad_norm": 0.6437689661979675,
      "learning_rate": 3.6276700724450384e-05,
      "loss": 1.2496,
      "step": 830
    },
    {
      "epoch": 0.7537857543466069,
      "grad_norm": 0.634338915348053,
      "learning_rate": 3.391995698670638e-05,
      "loss": 1.2889,
      "step": 840
    },
    {
      "epoch": 0.7627593942793045,
      "grad_norm": 0.5487192869186401,
      "learning_rate": 3.162663809364178e-05,
      "loss": 1.204,
      "step": 850
    },
    {
      "epoch": 0.7717330342120022,
      "grad_norm": 0.5915932655334473,
      "learning_rate": 2.9398945215049567e-05,
      "loss": 1.2491,
      "step": 860
    },
    {
      "epoch": 0.7807066741447,
      "grad_norm": 0.5967379212379456,
      "learning_rate": 2.7239016531662887e-05,
      "loss": 1.2519,
      "step": 870
    },
    {
      "epoch": 0.7896803140773977,
      "grad_norm": 0.589465320110321,
      "learning_rate": 2.514892518288988e-05,
      "loss": 1.3233,
      "step": 880
    },
    {
      "epoch": 0.7986539540100953,
      "grad_norm": 0.625720202922821,
      "learning_rate": 2.3130677276976232e-05,
      "loss": 1.2831,
      "step": 890
    },
    {
      "epoch": 0.807627593942793,
      "grad_norm": 0.5853390693664551,
      "learning_rate": 2.118620996550529e-05,
      "loss": 1.2793,
      "step": 900
    },
    {
      "epoch": 0.8166012338754908,
      "grad_norm": 0.5645495653152466,
      "learning_rate": 1.9317389584084568e-05,
      "loss": 1.2646,
      "step": 910
    },
    {
      "epoch": 0.8255748738081884,
      "grad_norm": 0.5386382341384888,
      "learning_rate": 1.7526009861001956e-05,
      "loss": 1.2479,
      "step": 920
    },
    {
      "epoch": 0.8345485137408861,
      "grad_norm": 0.5386704802513123,
      "learning_rate": 1.5813790195572674e-05,
      "loss": 1.2772,
      "step": 930
    },
    {
      "epoch": 0.8435221536735839,
      "grad_norm": 0.6007257103919983,
      "learning_rate": 1.4182374007827603e-05,
      "loss": 1.2606,
      "step": 940
    },
    {
      "epoch": 0.8524957936062816,
      "grad_norm": 0.6834496259689331,
      "learning_rate": 1.263332716112885e-05,
      "loss": 1.2778,
      "step": 950
    },
    {
      "epoch": 0.8614694335389792,
      "grad_norm": 0.5198489427566528,
      "learning_rate": 1.1168136459224842e-05,
      "loss": 1.2838,
      "step": 960
    },
    {
      "epoch": 0.8704430734716769,
      "grad_norm": 0.5519130825996399,
      "learning_rate": 9.788208219188932e-06,
      "loss": 1.2267,
      "step": 970
    },
    {
      "epoch": 0.8794167134043747,
      "grad_norm": 0.5107753276824951,
      "learning_rate": 8.494866921610133e-06,
      "loss": 1.2613,
      "step": 980
    },
    {
      "epoch": 0.8883903533370724,
      "grad_norm": 0.4735373556613922,
      "learning_rate": 7.289353939332288e-06,
      "loss": 1.2303,
      "step": 990
    },
    {
      "epoch": 0.89736399326977,
      "grad_norm": 0.4740982949733734,
      "learning_rate": 6.1728263459614796e-06,
      "loss": 1.2695,
      "step": 1000
    },
    {
      "epoch": 0.9063376332024677,
      "grad_norm": 0.580386221408844,
      "learning_rate": 5.146355805285452e-06,
      "loss": 1.2746,
      "step": 1010
    },
    {
      "epoch": 0.9153112731351655,
      "grad_norm": 0.5270484089851379,
      "learning_rate": 4.210927542670917e-06,
      "loss": 1.3423,
      "step": 1020
    },
    {
      "epoch": 0.9242849130678632,
      "grad_norm": 0.6918372511863708,
      "learning_rate": 3.367439399426087e-06,
      "loss": 1.2658,
      "step": 1030
    },
    {
      "epoch": 0.9332585530005608,
      "grad_norm": 0.5074269771575928,
      "learning_rate": 2.616700971036001e-06,
      "loss": 1.2453,
      "step": 1040
    },
    {
      "epoch": 0.9422321929332585,
      "grad_norm": 0.5192223191261292,
      "learning_rate": 1.959432830097807e-06,
      "loss": 1.2882,
      "step": 1050
    },
    {
      "epoch": 0.9512058328659563,
      "grad_norm": 0.6576820611953735,
      "learning_rate": 1.396265834701982e-06,
      "loss": 1.3017,
      "step": 1060
    },
    {
      "epoch": 0.9601794727986539,
      "grad_norm": 0.6131830215454102,
      "learning_rate": 9.277405229229708e-07,
      "loss": 1.2788,
      "step": 1070
    },
    {
      "epoch": 0.9691531127313516,
      "grad_norm": 0.7722458839416504,
      "learning_rate": 5.543065940008862e-07,
      "loss": 1.3333,
      "step": 1080
    },
    {
      "epoch": 0.9781267526640494,
      "grad_norm": 0.5115715265274048,
      "learning_rate": 2.7632247671177667e-07,
      "loss": 1.2451,
      "step": 1090
    },
    {
      "epoch": 0.9871003925967471,
      "grad_norm": 0.4745628237724304,
      "learning_rate": 9.405498534115209e-08,
      "loss": 1.2909,
      "step": 1100
    },
    {
      "epoch": 0.9960740325294447,
      "grad_norm": 0.5007497668266296,
      "learning_rate": 7.679063590670942e-09,
      "loss": 1.274,
      "step": 1110
    }
  ],
  "logging_steps": 10,
  "max_steps": 1114,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.558882397416325e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}