{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 117,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008547008547008548,
      "grad_norm": 0.10617450624704361,
      "learning_rate": 2e-05,
      "loss": 1.0609,
      "step": 1
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 0.08922120183706284,
      "learning_rate": 4e-05,
      "loss": 0.8002,
      "step": 2
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.09796449542045593,
      "learning_rate": 6e-05,
      "loss": 1.0642,
      "step": 3
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 0.07504308968782425,
      "learning_rate": 8e-05,
      "loss": 1.3314,
      "step": 4
    },
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 0.13153880834579468,
      "learning_rate": 0.0001,
      "loss": 0.9096,
      "step": 5
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 0.12239871919155121,
      "learning_rate": 0.00012,
      "loss": 1.3066,
      "step": 6
    },
    {
      "epoch": 0.05982905982905983,
      "grad_norm": 0.16333891451358795,
      "learning_rate": 0.00014,
      "loss": 0.9084,
      "step": 7
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.1972486823797226,
      "learning_rate": 0.00016,
      "loss": 0.9529,
      "step": 8
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.20466002821922302,
      "learning_rate": 0.00018,
      "loss": 0.7854,
      "step": 9
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 0.159206360578537,
      "learning_rate": 0.0002,
      "loss": 0.9573,
      "step": 10
    },
    {
      "epoch": 0.09401709401709402,
      "grad_norm": 0.1436036378145218,
      "learning_rate": 0.0001999976474595967,
      "loss": 0.9198,
      "step": 11
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.09368328005075455,
      "learning_rate": 0.00019999058994907564,
      "loss": 0.7141,
      "step": 12
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.15052762627601624,
      "learning_rate": 0.00019997882780049847,
      "loss": 0.8308,
      "step": 13
    },
    {
      "epoch": 0.11965811965811966,
      "grad_norm": 0.1979999989271164,
      "learning_rate": 0.0001999623615672837,
      "loss": 0.9606,
      "step": 14
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 0.09997200220823288,
      "learning_rate": 0.00019994119202418098,
      "loss": 1.0576,
      "step": 15
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.1111062690615654,
      "learning_rate": 0.00019991532016723439,
      "loss": 0.7494,
      "step": 16
    },
    {
      "epoch": 0.1452991452991453,
      "grad_norm": 0.06569597870111465,
      "learning_rate": 0.00019988474721373568,
      "loss": 1.1465,
      "step": 17
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.0768122747540474,
      "learning_rate": 0.00019984947460216707,
      "loss": 0.6043,
      "step": 18
    },
    {
      "epoch": 0.1623931623931624,
      "grad_norm": 0.08672061562538147,
      "learning_rate": 0.00019980950399213344,
      "loss": 0.7305,
      "step": 19
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 0.0832589790225029,
      "learning_rate": 0.00019976483726428422,
      "loss": 0.6337,
      "step": 20
    },
    {
      "epoch": 0.1794871794871795,
      "grad_norm": 0.10938091576099396,
      "learning_rate": 0.0001997154765202251,
      "loss": 0.6276,
      "step": 21
    },
    {
      "epoch": 0.18803418803418803,
      "grad_norm": 0.0857069194316864,
      "learning_rate": 0.00019966142408241901,
      "loss": 0.724,
      "step": 22
    },
    {
      "epoch": 0.19658119658119658,
      "grad_norm": 0.09225357323884964,
      "learning_rate": 0.00019960268249407675,
      "loss": 0.7827,
      "step": 23
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.12936490774154663,
      "learning_rate": 0.00019953925451903756,
      "loss": 0.7738,
      "step": 24
    },
    {
      "epoch": 0.21367521367521367,
      "grad_norm": 0.07518186420202255,
      "learning_rate": 0.0001994711431416389,
      "loss": 1.349,
      "step": 25
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.10044313967227936,
      "learning_rate": 0.00019939835156657616,
      "loss": 1.1649,
      "step": 26
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.08518682420253754,
      "learning_rate": 0.00019932088321875172,
      "loss": 0.6649,
      "step": 27
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 0.1104423925280571,
      "learning_rate": 0.00019923874174311394,
      "loss": 0.6019,
      "step": 28
    },
    {
      "epoch": 0.24786324786324787,
      "grad_norm": 0.10217441618442535,
      "learning_rate": 0.0001991519310044857,
      "loss": 1.0116,
      "step": 29
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.09339523315429688,
      "learning_rate": 0.00019906045508738228,
      "loss": 0.8906,
      "step": 30
    },
    {
      "epoch": 0.26495726495726496,
      "grad_norm": 0.09020253270864487,
      "learning_rate": 0.0001989643182958196,
      "loss": 0.6326,
      "step": 31
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.12317769229412079,
      "learning_rate": 0.00019886352515311134,
      "loss": 0.6621,
      "step": 32
    },
    {
      "epoch": 0.28205128205128205,
      "grad_norm": 0.0980222076177597,
      "learning_rate": 0.0001987580804016563,
      "loss": 0.9014,
      "step": 33
    },
    {
      "epoch": 0.2905982905982906,
      "grad_norm": 0.0993993878364563,
      "learning_rate": 0.00019864798900271532,
      "loss": 0.8123,
      "step": 34
    },
    {
      "epoch": 0.29914529914529914,
      "grad_norm": 0.09411144256591797,
      "learning_rate": 0.0001985332561361776,
      "loss": 0.629,
      "step": 35
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.08556198328733444,
      "learning_rate": 0.00019841388720031727,
      "loss": 0.5643,
      "step": 36
    },
    {
      "epoch": 0.3162393162393162,
      "grad_norm": 0.10584603995084763,
      "learning_rate": 0.00019828988781153917,
      "loss": 0.6573,
      "step": 37
    },
    {
      "epoch": 0.3247863247863248,
      "grad_norm": 0.12134706228971481,
      "learning_rate": 0.00019816126380411476,
      "loss": 0.6593,
      "step": 38
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.09265974164009094,
      "learning_rate": 0.00019802802122990758,
      "loss": 0.6899,
      "step": 39
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.12015959620475769,
      "learning_rate": 0.00019789016635808837,
      "loss": 0.7139,
      "step": 40
    },
    {
      "epoch": 0.3504273504273504,
      "grad_norm": 0.10590967535972595,
      "learning_rate": 0.00019774770567484022,
      "loss": 0.8659,
      "step": 41
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 0.0821319967508316,
      "learning_rate": 0.00019760064588305345,
      "loss": 0.6225,
      "step": 42
    },
    {
      "epoch": 0.36752136752136755,
      "grad_norm": 0.08947279304265976,
      "learning_rate": 0.00019744899390201006,
      "loss": 0.6633,
      "step": 43
    },
    {
      "epoch": 0.37606837606837606,
      "grad_norm": 0.09095878899097443,
      "learning_rate": 0.0001972927568670583,
      "loss": 1.0491,
      "step": 44
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.11080043762922287,
      "learning_rate": 0.00019713194212927696,
      "loss": 0.7607,
      "step": 45
    },
    {
      "epoch": 0.39316239316239315,
      "grad_norm": 0.1101192831993103,
      "learning_rate": 0.00019696655725512933,
      "loss": 0.6905,
      "step": 46
    },
    {
      "epoch": 0.4017094017094017,
      "grad_norm": 0.10834185779094696,
      "learning_rate": 0.00019679661002610743,
      "loss": 0.7658,
      "step": 47
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.09499570727348328,
      "learning_rate": 0.00019662210843836574,
      "loss": 0.6548,
      "step": 48
    },
    {
      "epoch": 0.4188034188034188,
      "grad_norm": 0.10409791767597198,
      "learning_rate": 0.0001964430607023449,
      "loss": 0.6481,
      "step": 49
    },
    {
      "epoch": 0.42735042735042733,
      "grad_norm": 0.14213934540748596,
      "learning_rate": 0.00019625947524238563,
      "loss": 0.9427,
      "step": 50
    },
    {
      "epoch": 0.4358974358974359,
      "grad_norm": 0.1068490594625473,
      "learning_rate": 0.00019607136069633212,
      "loss": 0.6032,
      "step": 51
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.09627290815114975,
      "learning_rate": 0.0001958787259151258,
      "loss": 0.6374,
      "step": 52
    },
    {
      "epoch": 0.452991452991453,
      "grad_norm": 0.11231101304292679,
      "learning_rate": 0.00019568157996238884,
      "loss": 0.6044,
      "step": 53
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.08818076550960541,
      "learning_rate": 0.0001954799321139975,
      "loss": 0.938,
      "step": 54
    },
    {
      "epoch": 0.4700854700854701,
      "grad_norm": 0.09192392230033875,
      "learning_rate": 0.00019527379185764612,
      "loss": 0.6002,
      "step": 55
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.13584138453006744,
      "learning_rate": 0.00019506316889240027,
      "loss": 1.0875,
      "step": 56
    },
    {
      "epoch": 0.48717948717948717,
      "grad_norm": 0.1015191301703453,
      "learning_rate": 0.00019484807312824067,
      "loss": 0.5469,
      "step": 57
    },
    {
      "epoch": 0.49572649572649574,
      "grad_norm": 0.13013221323490143,
      "learning_rate": 0.0001946285146855968,
      "loss": 0.6786,
      "step": 58
    },
    {
      "epoch": 0.5042735042735043,
      "grad_norm": 0.11627920717000961,
      "learning_rate": 0.0001944045038948709,
      "loss": 0.685,
      "step": 59
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.12050677835941315,
      "learning_rate": 0.00019417605129595157,
      "loss": 0.6231,
      "step": 60
    },
    {
      "epoch": 0.5213675213675214,
      "grad_norm": 0.1218978613615036,
      "learning_rate": 0.0001939431676377183,
      "loss": 0.6177,
      "step": 61
    },
    {
      "epoch": 0.5299145299145299,
      "grad_norm": 0.10386243462562561,
      "learning_rate": 0.0001937058638775353,
      "loss": 0.5893,
      "step": 62
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.08668994158506393,
      "learning_rate": 0.00019346415118073632,
      "loss": 1.1945,
      "step": 63
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.1240827739238739,
      "learning_rate": 0.00019321804092009906,
      "loss": 0.6633,
      "step": 64
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.11331409960985184,
      "learning_rate": 0.00019296754467531014,
      "loss": 0.629,
      "step": 65
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 0.14046786725521088,
      "learning_rate": 0.00019271267423242024,
      "loss": 0.6328,
      "step": 66
    },
    {
      "epoch": 0.5726495726495726,
      "grad_norm": 0.12209989875555038,
      "learning_rate": 0.00019245344158328972,
      "loss": 0.7198,
      "step": 67
    },
    {
      "epoch": 0.5811965811965812,
      "grad_norm": 0.11325013637542725,
      "learning_rate": 0.0001921898589250242,
      "loss": 0.5967,
      "step": 68
    },
    {
      "epoch": 0.5897435897435898,
      "grad_norm": 0.10685242712497711,
      "learning_rate": 0.0001919219386594007,
      "loss": 0.6475,
      "step": 69
    },
    {
      "epoch": 0.5982905982905983,
      "grad_norm": 0.12094041705131531,
      "learning_rate": 0.00019164969339228422,
      "loss": 0.6646,
      "step": 70
    },
    {
      "epoch": 0.6068376068376068,
      "grad_norm": 0.12835665047168732,
      "learning_rate": 0.00019137313593303463,
      "loss": 0.7256,
      "step": 71
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.09861553460359573,
      "learning_rate": 0.00019109227929390378,
      "loss": 1.2889,
      "step": 72
    },
    {
      "epoch": 0.6239316239316239,
      "grad_norm": 0.1085813045501709,
      "learning_rate": 0.00019080713668942356,
      "loss": 0.6072,
      "step": 73
    },
    {
      "epoch": 0.6324786324786325,
      "grad_norm": 0.11427804082632065,
      "learning_rate": 0.00019051772153578389,
      "loss": 0.6251,
      "step": 74
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 0.13322962820529938,
      "learning_rate": 0.00019022404745020163,
      "loss": 0.6276,
      "step": 75
    },
    {
      "epoch": 0.6495726495726496,
      "grad_norm": 0.10408783704042435,
      "learning_rate": 0.00018992612825027976,
      "loss": 0.6471,
      "step": 76
    },
    {
      "epoch": 0.6581196581196581,
      "grad_norm": 0.13549701869487762,
      "learning_rate": 0.0001896239779533575,
      "loss": 0.7443,
      "step": 77
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.10901051014661789,
      "learning_rate": 0.00018931761077585035,
      "loss": 0.6207,
      "step": 78
    },
    {
      "epoch": 0.6752136752136753,
      "grad_norm": 0.12259478867053986,
      "learning_rate": 0.00018900704113258165,
      "loss": 0.6064,
      "step": 79
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.11373128741979599,
      "learning_rate": 0.00018869228363610404,
      "loss": 0.5889,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.12991991639137268,
      "learning_rate": 0.00018837335309601213,
      "loss": 0.6436,
      "step": 81
    },
    {
      "epoch": 0.7008547008547008,
      "grad_norm": 0.10556752979755402,
      "learning_rate": 0.00018805026451824546,
      "loss": 1.1581,
      "step": 82
    },
    {
      "epoch": 0.7094017094017094,
      "grad_norm": 0.09846064448356628,
      "learning_rate": 0.00018772303310438275,
      "loss": 1.0829,
      "step": 83
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.11470722407102585,
      "learning_rate": 0.00018739167425092644,
      "loss": 1.0479,
      "step": 84
    },
    {
      "epoch": 0.7264957264957265,
      "grad_norm": 0.13047707080841064,
      "learning_rate": 0.00018705620354857833,
      "loss": 0.5753,
      "step": 85
    },
    {
      "epoch": 0.7350427350427351,
      "grad_norm": 0.11538581550121307,
      "learning_rate": 0.00018671663678150607,
      "loss": 0.5662,
      "step": 86
    },
    {
      "epoch": 0.7435897435897436,
      "grad_norm": 0.10746373981237411,
      "learning_rate": 0.0001863729899266004,
      "loss": 0.599,
      "step": 87
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.11938890069723129,
      "learning_rate": 0.0001860252791527236,
      "loss": 0.9395,
      "step": 88
    },
    {
      "epoch": 0.7606837606837606,
      "grad_norm": 0.09598677605390549,
      "learning_rate": 0.00018567352081994852,
      "loss": 1.1635,
      "step": 89
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.09986315667629242,
      "learning_rate": 0.00018531773147878895,
      "loss": 1.0348,
      "step": 90
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.10799750685691833,
      "learning_rate": 0.0001849579278694209,
      "loss": 0.6233,
      "step": 91
    },
    {
      "epoch": 0.7863247863247863,
      "grad_norm": 0.11003697663545609,
      "learning_rate": 0.00018459412692089494,
      "loss": 0.5853,
      "step": 92
    },
    {
      "epoch": 0.7948717948717948,
      "grad_norm": 0.10201738029718399,
      "learning_rate": 0.0001842263457503397,
      "loss": 0.5653,
      "step": 93
    },
    {
      "epoch": 0.8034188034188035,
      "grad_norm": 0.12902310490608215,
      "learning_rate": 0.00018385460166215638,
      "loss": 0.7434,
      "step": 94
    },
    {
      "epoch": 0.811965811965812,
      "grad_norm": 0.1216060072183609,
      "learning_rate": 0.00018347891214720477,
      "loss": 0.6264,
      "step": 95
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.10260992497205734,
      "learning_rate": 0.00018309929488198012,
      "loss": 1.0943,
      "step": 96
    },
    {
      "epoch": 0.8290598290598291,
      "grad_norm": 0.11333200335502625,
      "learning_rate": 0.00018271576772778154,
      "loss": 0.6031,
      "step": 97
    },
    {
      "epoch": 0.8376068376068376,
      "grad_norm": 0.10730260610580444,
      "learning_rate": 0.00018232834872987147,
      "loss": 1.0912,
      "step": 98
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.12327554821968079,
      "learning_rate": 0.00018193705611662696,
      "loss": 0.7166,
      "step": 99
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.16586735844612122,
      "learning_rate": 0.0001815419082986815,
      "loss": 0.6869,
      "step": 100
    },
    {
      "epoch": 0.8632478632478633,
      "grad_norm": 0.10598164051771164,
      "learning_rate": 0.00018114292386805936,
      "loss": 0.9929,
      "step": 101
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 0.09722983837127686,
      "learning_rate": 0.00018074012159730032,
      "loss": 1.0678,
      "step": 102
    },
    {
      "epoch": 0.8803418803418803,
      "grad_norm": 0.0981651172041893,
      "learning_rate": 0.00018033352043857675,
      "loss": 0.8761,
      "step": 103
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.1134006604552269,
      "learning_rate": 0.00017992313952280172,
      "loss": 1.0277,
      "step": 104
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 0.11528769880533218,
      "learning_rate": 0.00017950899815872892,
      "loss": 1.1271,
      "step": 105
    },
    {
      "epoch": 0.905982905982906,
      "grad_norm": 0.15807704627513885,
      "learning_rate": 0.00017909111583204422,
      "loss": 1.0239,
      "step": 106
    },
    {
      "epoch": 0.9145299145299145,
      "grad_norm": 0.16159194707870483,
      "learning_rate": 0.0001786695122044487,
      "loss": 0.7818,
      "step": 107
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.11592184752225876,
      "learning_rate": 0.0001782442071127338,
      "loss": 1.0227,
      "step": 108
    },
    {
      "epoch": 0.9316239316239316,
      "grad_norm": 0.15580905973911285,
      "learning_rate": 0.0001778152205678477,
      "loss": 1.0292,
      "step": 109
    },
    {
      "epoch": 0.9401709401709402,
      "grad_norm": 0.1733143925666809,
      "learning_rate": 0.00017738257275395404,
      "loss": 0.7282,
      "step": 110
    },
    {
      "epoch": 0.9487179487179487,
      "grad_norm": 0.13020546734333038,
      "learning_rate": 0.00017694628402748202,
      "loss": 0.6528,
      "step": 111
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.12256832420825958,
      "learning_rate": 0.0001765063749161688,
      "loss": 0.6689,
      "step": 112
    },
    {
      "epoch": 0.9658119658119658,
      "grad_norm": 0.13194310665130615,
      "learning_rate": 0.00017606286611809353,
      "loss": 0.6712,
      "step": 113
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 0.12272733449935913,
      "learning_rate": 0.00017561577850070355,
      "loss": 0.7668,
      "step": 114
    },
    {
      "epoch": 0.9829059829059829,
      "grad_norm": 0.10930750519037247,
      "learning_rate": 0.00017516513309983253,
      "loss": 0.5466,
      "step": 115
    },
    {
      "epoch": 0.9914529914529915,
      "grad_norm": 0.14313393831253052,
      "learning_rate": 0.00017471095111871074,
      "loss": 0.6853,
      "step": 116
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.11835158616304398,
      "learning_rate": 0.0001742532539269674,
      "loss": 0.6175,
      "step": 117
    }
  ],
  "logging_steps": 1,
  "max_steps": 468,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 117,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.106557991592919e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}