{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990732159406858,
  "eval_steps": 500,
  "global_step": 539,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018535681186283596,
      "grad_norm": 26.35410018433926,
      "learning_rate": 5.555555555555555e-06,
      "loss": 1.6809,
      "step": 1
    },
    {
      "epoch": 0.009267840593141797,
      "grad_norm": 39.94533926724377,
      "learning_rate": 2.7777777777777772e-05,
      "loss": 1.343,
      "step": 5
    },
    {
      "epoch": 0.018535681186283594,
      "grad_norm": 4.5543620999927485,
      "learning_rate": 5.5555555555555545e-05,
      "loss": 0.8749,
      "step": 10
    },
    {
      "epoch": 0.027803521779425393,
      "grad_norm": 4.24495034141875,
      "learning_rate": 8.333333333333333e-05,
      "loss": 0.8704,
      "step": 15
    },
    {
      "epoch": 0.03707136237256719,
      "grad_norm": 39.42543160126464,
      "learning_rate": 0.00011111111111111109,
      "loss": 0.8733,
      "step": 20
    },
    {
      "epoch": 0.04633920296570899,
      "grad_norm": 11.962483325702362,
      "learning_rate": 0.0001388888888888889,
      "loss": 1.0553,
      "step": 25
    },
    {
      "epoch": 0.05560704355885079,
      "grad_norm": 14.195688905715766,
      "learning_rate": 0.00016666666666666666,
      "loss": 1.0623,
      "step": 30
    },
    {
      "epoch": 0.06487488415199258,
      "grad_norm": 4.164105779251046,
      "learning_rate": 0.00019444444444444443,
      "loss": 0.8718,
      "step": 35
    },
    {
      "epoch": 0.07414272474513438,
      "grad_norm": 6.991113945747281,
      "learning_rate": 0.00022222222222222218,
      "loss": 0.8619,
      "step": 40
    },
    {
      "epoch": 0.08341056533827618,
      "grad_norm": 631.4969668103296,
      "learning_rate": 0.00025,
      "loss": 1.8292,
      "step": 45
    },
    {
      "epoch": 0.09267840593141798,
      "grad_norm": 51.99035558508526,
      "learning_rate": 0.0002777777777777778,
      "loss": 1.6128,
      "step": 50
    },
    {
      "epoch": 0.10194624652455977,
      "grad_norm": 5.615188207831111,
      "learning_rate": 0.0002999968531502098,
      "loss": 1.1458,
      "step": 55
    },
    {
      "epoch": 0.11121408711770157,
      "grad_norm": 162.57564664314097,
      "learning_rate": 0.0002998867272706619,
      "loss": 1.7169,
      "step": 60
    },
    {
      "epoch": 0.12048192771084337,
      "grad_norm": 27.819505339583905,
      "learning_rate": 0.0002996193909122197,
      "loss": 2.1196,
      "step": 65
    },
    {
      "epoch": 0.12974976830398516,
      "grad_norm": 12.017979123334465,
      "learning_rate": 0.00029919512447380625,
      "loss": 1.3348,
      "step": 70
    },
    {
      "epoch": 0.13901760889712697,
      "grad_norm": 529.5307829885717,
      "learning_rate": 0.0002986143729523282,
      "loss": 1.0105,
      "step": 75
    },
    {
      "epoch": 0.14828544949026876,
      "grad_norm": 2.511805320667406,
      "learning_rate": 0.000297877745475935,
      "loss": 1.0586,
      "step": 80
    },
    {
      "epoch": 0.15755329008341057,
      "grad_norm": 4.022429995067504,
      "learning_rate": 0.0002969860146651276,
      "loss": 0.9055,
      "step": 85
    },
    {
      "epoch": 0.16682113067655235,
      "grad_norm": 512.3998660297882,
      "learning_rate": 0.0002959401158223867,
      "loss": 5.3655,
      "step": 90
    },
    {
      "epoch": 0.17608897126969417,
      "grad_norm": 131.99417407337796,
      "learning_rate": 0.00029474114595116896,
      "loss": 3.1238,
      "step": 95
    },
    {
      "epoch": 0.18535681186283595,
      "grad_norm": 19.953838142892188,
      "learning_rate": 0.0002933903626053024,
      "loss": 1.9603,
      "step": 100
    },
    {
      "epoch": 0.19462465245597776,
      "grad_norm": 7.472797510255509,
      "learning_rate": 0.00029188918256998564,
      "loss": 1.4801,
      "step": 105
    },
    {
      "epoch": 0.20389249304911955,
      "grad_norm": 9.70552960980865,
      "learning_rate": 0.00029023918037577635,
      "loss": 1.3544,
      "step": 110
    },
    {
      "epoch": 0.21316033364226136,
      "grad_norm": 17.11916105312361,
      "learning_rate": 0.00028844208664712575,
      "loss": 1.0681,
      "step": 115
    },
    {
      "epoch": 0.22242817423540315,
      "grad_norm": 22.28855318123011,
      "learning_rate": 0.00028649978628719254,
      "loss": 1.2611,
      "step": 120
    },
    {
      "epoch": 0.23169601482854496,
      "grad_norm": 34.76579789562846,
      "learning_rate": 0.00028441431650084016,
      "loss": 1.6181,
      "step": 125
    },
    {
      "epoch": 0.24096385542168675,
      "grad_norm": 15.11803328233237,
      "learning_rate": 0.0002821878646578898,
      "loss": 1.1601,
      "step": 130
    },
    {
      "epoch": 0.25023169601482853,
      "grad_norm": 10.594239787348334,
      "learning_rate": 0.0002798227659988717,
      "loss": 1.0309,
      "step": 135
    },
    {
      "epoch": 0.2594995366079703,
      "grad_norm": 3.881883182518721,
      "learning_rate": 0.00027732150118568017,
      "loss": 1.5651,
      "step": 140
    },
    {
      "epoch": 0.26876737720111216,
      "grad_norm": 3.036719624432077,
      "learning_rate": 0.00027468669369970207,
      "loss": 1.1445,
      "step": 145
    },
    {
      "epoch": 0.27803521779425394,
      "grad_norm": 14.352629655607771,
      "learning_rate": 0.00027192110709014697,
      "loss": 0.9305,
      "step": 150
    },
    {
      "epoch": 0.2873030583873957,
      "grad_norm": 2.933168446331413,
      "learning_rate": 0.0002690276420754655,
      "loss": 0.9324,
      "step": 155
    },
    {
      "epoch": 0.2965708989805375,
      "grad_norm": 4.661928504358525,
      "learning_rate": 0.00026600933350089654,
      "loss": 0.9491,
      "step": 160
    },
    {
      "epoch": 0.30583873957367935,
      "grad_norm": 5.782107803222577,
      "learning_rate": 0.0002628693471553335,
      "loss": 0.8689,
      "step": 165
    },
    {
      "epoch": 0.31510658016682114,
      "grad_norm": 4.287118434199453,
      "learning_rate": 0.00025961097645084885,
      "loss": 1.112,
      "step": 170
    },
    {
      "epoch": 0.3243744207599629,
      "grad_norm": 170.8246279898043,
      "learning_rate": 0.0002562376389683599,
      "loss": 2.2669,
      "step": 175
    },
    {
      "epoch": 0.3336422613531047,
      "grad_norm": 243.40178580373365,
      "learning_rate": 0.00025275287287305814,
      "loss": 3.2917,
      "step": 180
    },
    {
      "epoch": 0.34291010194624655,
      "grad_norm": 160.38147120987801,
      "learning_rate": 0.00024916033320336264,
      "loss": 3.067,
      "step": 185
    },
    {
      "epoch": 0.35217794253938833,
      "grad_norm": 30.070071532273786,
      "learning_rate": 0.0002454637880372892,
      "loss": 3.1301,
      "step": 190
    },
    {
      "epoch": 0.3614457831325301,
      "grad_norm": 48.47525499191394,
      "learning_rate": 0.0002416671145402575,
      "loss": 2.6178,
      "step": 195
    },
    {
      "epoch": 0.3707136237256719,
      "grad_norm": 48.37664262960068,
      "learning_rate": 0.00023777429489847934,
      "loss": 1.441,
      "step": 200
    },
    {
      "epoch": 0.3799814643188137,
      "grad_norm": 3.8665655676681245,
      "learning_rate": 0.0002337894121421954,
      "loss": 1.2978,
      "step": 205
    },
    {
      "epoch": 0.38924930491195553,
      "grad_norm": 2.9273559971935055,
      "learning_rate": 0.00022971664586314054,
      "loss": 1.0238,
      "step": 210
    },
    {
      "epoch": 0.3985171455050973,
      "grad_norm": 20.165413444524287,
      "learning_rate": 0.00022556026783072895,
      "loss": 0.8787,
      "step": 215
    },
    {
      "epoch": 0.4077849860982391,
      "grad_norm": 2.3870488681045203,
      "learning_rate": 0.00022132463751155812,
      "loss": 0.9467,
      "step": 220
    },
    {
      "epoch": 0.4170528266913809,
      "grad_norm": 4.038604860534557,
      "learning_rate": 0.00021701419749693034,
      "loss": 0.9708,
      "step": 225
    },
    {
      "epoch": 0.4263206672845227,
      "grad_norm": 2.7240106071190535,
      "learning_rate": 0.00021263346884318777,
      "loss": 1.0564,
      "step": 230
    },
    {
      "epoch": 0.4355885078776645,
      "grad_norm": 1.6377519083501402,
      "learning_rate": 0.00020818704632974896,
      "loss": 0.7724,
      "step": 235
    },
    {
      "epoch": 0.4448563484708063,
      "grad_norm": 1.0433662853439323,
      "learning_rate": 0.00020367959363981936,
      "loss": 0.8052,
      "step": 240
    },
    {
      "epoch": 0.4541241890639481,
      "grad_norm": 1.5351301360333338,
      "learning_rate": 0.00019911583846883197,
      "loss": 0.8407,
      "step": 245
    },
    {
      "epoch": 0.4633920296570899,
      "grad_norm": 1.2741936551633426,
      "learning_rate": 0.0001945005675657475,
      "loss": 0.8344,
      "step": 250
    },
    {
      "epoch": 0.4726598702502317,
      "grad_norm": 2.4652187839401467,
      "learning_rate": 0.00018983862171241577,
      "loss": 0.9688,
      "step": 255
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 1.1552631433359035,
      "learning_rate": 0.00018513489064626398,
      "loss": 0.8647,
      "step": 260
    },
    {
      "epoch": 0.4911955514365153,
      "grad_norm": 1.113328634852908,
      "learning_rate": 0.00018039430793163753,
      "loss": 0.8514,
      "step": 265
    },
    {
      "epoch": 0.5004633920296571,
      "grad_norm": 0.995245914359209,
      "learning_rate": 0.00017562184578517203,
      "loss": 0.8845,
      "step": 270
    },
    {
      "epoch": 0.5097312326227988,
      "grad_norm": 1.5488835001137233,
      "learning_rate": 0.00017082250986062502,
      "loss": 0.7809,
      "step": 275
    },
    {
      "epoch": 0.5189990732159406,
      "grad_norm": 1.5756484423065427,
      "learning_rate": 0.00016600133399863594,
      "loss": 0.8326,
      "step": 280
    },
    {
      "epoch": 0.5282669138090825,
      "grad_norm": 206.03580929049917,
      "learning_rate": 0.0001611633749469231,
      "loss": 2.2034,
      "step": 285
    },
    {
      "epoch": 0.5375347544022243,
      "grad_norm": 4.169210184616496,
      "learning_rate": 0.0001563137070564528,
      "loss": 1.9396,
      "step": 290
    },
    {
      "epoch": 0.5468025949953661,
      "grad_norm": 7.018651154352153,
      "learning_rate": 0.0001514574169591466,
      "loss": 1.4702,
      "step": 295
    },
    {
      "epoch": 0.5560704355885079,
      "grad_norm": 1.7304196471580864,
      "learning_rate": 0.0001465995982327065,
      "loss": 0.9425,
      "step": 300
    },
    {
      "epoch": 0.5653382761816497,
      "grad_norm": 2.241775914452003,
      "learning_rate": 0.00014174534605815525,
      "loss": 0.7961,
      "step": 305
    },
    {
      "epoch": 0.5746061167747915,
      "grad_norm": 3.456242970621782,
      "learning_rate": 0.0001368997518756954,
      "loss": 0.834,
      "step": 310
    },
    {
      "epoch": 0.5838739573679332,
      "grad_norm": 5.072902047355265,
      "learning_rate": 0.00013206789804449116,
      "loss": 0.99,
      "step": 315
    },
    {
      "epoch": 0.593141797961075,
      "grad_norm": 6.231760889035276,
      "learning_rate": 0.0001272548525119758,
      "loss": 0.8985,
      "step": 320
    },
    {
      "epoch": 0.6024096385542169,
      "grad_norm": 0.8710278075890822,
      "learning_rate": 0.0001224656634982746,
      "loss": 0.7725,
      "step": 325
    },
    {
      "epoch": 0.6116774791473587,
      "grad_norm": 1.799368795567863,
      "learning_rate": 0.00011770535420131876,
      "loss": 0.7621,
      "step": 330
    },
    {
      "epoch": 0.6209453197405005,
      "grad_norm": 0.9742992413928552,
      "learning_rate": 0.00011297891752820484,
      "loss": 0.8327,
      "step": 335
    },
    {
      "epoch": 0.6302131603336423,
      "grad_norm": 0.85009149768552,
      "learning_rate": 0.0001082913108583245,
      "loss": 0.6863,
      "step": 340
    },
    {
      "epoch": 0.6394810009267841,
      "grad_norm": 0.8181844995131707,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.6779,
      "step": 345
    },
    {
      "epoch": 0.6487488415199258,
      "grad_norm": 0.9546399988989202,
      "learning_rate": 9.905220825238491e-05,
      "loss": 0.6872,
      "step": 350
    },
    {
      "epoch": 0.6580166821130676,
      "grad_norm": 0.6995327936772554,
      "learning_rate": 9.45104028591222e-05,
      "loss": 0.7025,
      "step": 355
    },
    {
      "epoch": 0.6672845227062094,
      "grad_norm": 0.7195227820211112,
      "learning_rate": 9.002679839064463e-05,
      "loss": 0.6807,
      "step": 360
    },
    {
      "epoch": 0.6765523632993512,
      "grad_norm": 0.6283846451216366,
      "learning_rate": 8.560609752889412e-05,
      "loss": 0.6888,
      "step": 365
    },
    {
      "epoch": 0.6858202038924931,
      "grad_norm": 0.7394400936445648,
      "learning_rate": 8.125293697861548e-05,
      "loss": 0.6542,
      "step": 370
    },
    {
      "epoch": 0.6950880444856349,
      "grad_norm": 0.6824620929581083,
      "learning_rate": 7.697188260409356e-05,
      "loss": 0.671,
      "step": 375
    },
    {
      "epoch": 0.7043558850787767,
      "grad_norm": 0.6116075298871171,
      "learning_rate": 7.276742464019198e-05,
      "loss": 0.6729,
      "step": 380
    },
    {
      "epoch": 0.7136237256719185,
      "grad_norm": 0.6453928151826652,
      "learning_rate": 6.864397298271699e-05,
      "loss": 0.6626,
      "step": 385
    },
    {
      "epoch": 0.7228915662650602,
      "grad_norm": 0.6716078881868212,
      "learning_rate": 6.460585256304559e-05,
      "loss": 0.6851,
      "step": 390
    },
    {
      "epoch": 0.732159406858202,
      "grad_norm": 0.6801638199214254,
      "learning_rate": 6.065729881186982e-05,
      "loss": 0.6168,
      "step": 395
    },
    {
      "epoch": 0.7414272474513438,
      "grad_norm": 0.4794662188577268,
      "learning_rate": 5.680245321681471e-05,
      "loss": 0.6531,
      "step": 400
    },
    {
      "epoch": 0.7506950880444856,
      "grad_norm": 1.029961404045439,
      "learning_rate": 5.304535897858999e-05,
      "loss": 0.6295,
      "step": 405
    },
    {
      "epoch": 0.7599629286376274,
      "grad_norm": 0.5284338458030478,
      "learning_rate": 4.938995677023054e-05,
      "loss": 0.6201,
      "step": 410
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.4516339145236783,
      "learning_rate": 4.584008060387455e-05,
      "loss": 0.6083,
      "step": 415
    },
    {
      "epoch": 0.7784986098239111,
      "grad_norm": 0.5727589086366411,
      "learning_rate": 4.239945380941461e-05,
      "loss": 0.6021,
      "step": 420
    },
    {
      "epoch": 0.7877664504170528,
      "grad_norm": 0.4804742186453503,
      "learning_rate": 3.907168512923842e-05,
      "loss": 0.5933,
      "step": 425
    },
    {
      "epoch": 0.7970342910101946,
      "grad_norm": 0.45776606255626884,
      "learning_rate": 3.5860264933156324e-05,
      "loss": 0.5774,
      "step": 430
    },
    {
      "epoch": 0.8063021316033364,
      "grad_norm": 1.2302657626291176,
      "learning_rate": 3.276856155748584e-05,
      "loss": 0.5908,
      "step": 435
    },
    {
      "epoch": 0.8155699721964782,
      "grad_norm": 0.9348743887035583,
      "learning_rate": 2.9799817772131516e-05,
      "loss": 0.592,
      "step": 440
    },
    {
      "epoch": 0.82483781278962,
      "grad_norm": 0.4027186043623421,
      "learning_rate": 2.6957147379367217e-05,
      "loss": 0.5798,
      "step": 445
    },
    {
      "epoch": 0.8341056533827618,
      "grad_norm": 0.5240634600695104,
      "learning_rate": 2.4243531947887802e-05,
      "loss": 0.5805,
      "step": 450
    },
    {
      "epoch": 0.8433734939759037,
      "grad_norm": 0.5416112282286268,
      "learning_rate": 2.1661817685554833e-05,
      "loss": 0.6067,
      "step": 455
    },
    {
      "epoch": 0.8526413345690455,
      "grad_norm": 0.47266676591358336,
      "learning_rate": 1.921471245411794e-05,
      "loss": 0.5962,
      "step": 460
    },
    {
      "epoch": 0.8619091751621872,
      "grad_norm": 0.6382596120183166,
      "learning_rate": 1.6904782929041693e-05,
      "loss": 0.5791,
      "step": 465
    },
    {
      "epoch": 0.871177015755329,
      "grad_norm": 0.49306751144827193,
      "learning_rate": 1.4734451907417255e-05,
      "loss": 0.6182,
      "step": 470
    },
    {
      "epoch": 0.8804448563484708,
      "grad_norm": 0.49635162924553927,
      "learning_rate": 1.2705995766783079e-05,
      "loss": 0.5521,
      "step": 475
    },
    {
      "epoch": 0.8897126969416126,
      "grad_norm": 0.49868563464480065,
      "learning_rate": 1.0821542077519169e-05,
      "loss": 0.5579,
      "step": 480
    },
    {
      "epoch": 0.8989805375347544,
      "grad_norm": 0.384294096915848,
      "learning_rate": 9.083067371319324e-06,
      "loss": 0.5532,
      "step": 485
    },
    {
      "epoch": 0.9082483781278962,
      "grad_norm": 0.6584770004045724,
      "learning_rate": 7.492395068082619e-06,
      "loss": 0.544,
      "step": 490
    },
    {
      "epoch": 0.917516218721038,
      "grad_norm": 0.5198655418147264,
      "learning_rate": 6.051193563397599e-06,
      "loss": 0.555,
      "step": 495
    },
    {
      "epoch": 0.9267840593141798,
      "grad_norm": 0.46652880015863485,
      "learning_rate": 4.760974478625634e-06,
      "loss": 0.5437,
      "step": 500
    },
    {
      "epoch": 0.9360518999073216,
      "grad_norm": 1.0569529661255628,
      "learning_rate": 3.623091075418977e-06,
      "loss": 0.5573,
      "step": 505
    },
    {
      "epoch": 0.9453197405004634,
      "grad_norm": 0.4373874071284105,
      "learning_rate": 2.638736836336158e-06,
      "loss": 0.5312,
      "step": 510
    },
    {
      "epoch": 0.9545875810936052,
      "grad_norm": 0.46826046078794514,
      "learning_rate": 1.8089442130434061e-06,
      "loss": 0.5648,
      "step": 515
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 0.40638149868456475,
      "learning_rate": 1.1345835434156736e-06,
      "loss": 0.5417,
      "step": 520
    },
    {
      "epoch": 0.9731232622798888,
      "grad_norm": 0.4274920327067933,
      "learning_rate": 6.163621386722218e-07,
      "loss": 0.5528,
      "step": 525
    },
    {
      "epoch": 0.9823911028730306,
      "grad_norm": 0.41954954402917344,
      "learning_rate": 2.5482354150493935e-07,
      "loss": 0.549,
      "step": 530
    },
    {
      "epoch": 0.9916589434661723,
      "grad_norm": 0.46407841167410513,
      "learning_rate": 5.0346955976976467e-08,
      "loss": 0.5499,
      "step": 535
    },
    {
      "epoch": 0.9990732159406858,
      "eval_loss": 2.2535195350646973,
      "eval_runtime": 2.3617,
      "eval_samples_per_second": 1.694,
      "eval_steps_per_second": 0.423,
      "step": 539
    },
    {
      "epoch": 0.9990732159406858,
      "step": 539,
      "total_flos": 28187736145920.0,
      "train_loss": 1.0674916249259283,
      "train_runtime": 10422.8572,
      "train_samples_per_second": 1.655,
      "train_steps_per_second": 0.052
    }
  ],
  "logging_steps": 5,
  "max_steps": 539,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 28187736145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}