{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 468,
  "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
    },
    {
      "epoch": 1.0085470085470085,
      "grad_norm": 0.12867018580436707,
      "learning_rate": 0.00017379206305962526,
      "loss": 0.4912,
      "step": 118
    },
    {
      "epoch": 1.017094017094017,
      "grad_norm": 0.12265478074550629,
      "learning_rate": 0.00017332740021608722,
      "loss": 0.4865,
      "step": 119
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.12497735023498535,
      "learning_rate": 0.00017285928725911562,
      "loss": 0.5407,
      "step": 120
    },
    {
      "epoch": 1.0341880341880343,
      "grad_norm": 0.15299785137176514,
      "learning_rate": 0.00017238774621380337,
      "loss": 0.5391,
      "step": 121
    },
    {
      "epoch": 1.0427350427350428,
      "grad_norm": 0.13409839570522308,
      "learning_rate": 0.00017191279926653761,
      "loss": 1.1214,
      "step": 122
    },
    {
      "epoch": 1.0512820512820513,
      "grad_norm": 0.1429445594549179,
      "learning_rate": 0.00017143446876395602,
      "loss": 0.9628,
      "step": 123
    },
    {
      "epoch": 1.0598290598290598,
      "grad_norm": 0.12664200365543365,
      "learning_rate": 0.00017095277721189528,
      "loss": 0.9409,
      "step": 124
    },
    {
      "epoch": 1.0683760683760684,
      "grad_norm": 0.17288966476917267,
      "learning_rate": 0.00017046774727433222,
      "loss": 0.6203,
      "step": 125
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.14868439733982086,
      "learning_rate": 0.00016997940177231722,
      "loss": 0.5074,
      "step": 126
    },
    {
      "epoch": 1.0854700854700854,
      "grad_norm": 0.11606048047542572,
      "learning_rate": 0.00016948776368290084,
      "loss": 1.0314,
      "step": 127
    },
    {
      "epoch": 1.0940170940170941,
      "grad_norm": 0.15571007132530212,
      "learning_rate": 0.00016899285613805246,
      "loss": 0.4376,
      "step": 128
    },
    {
      "epoch": 1.1025641025641026,
      "grad_norm": 0.16392119228839874,
      "learning_rate": 0.00016849470242357196,
      "loss": 0.4872,
      "step": 129
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.15567384660243988,
      "learning_rate": 0.00016799332597799413,
      "loss": 0.4809,
      "step": 130
    },
    {
      "epoch": 1.1196581196581197,
      "grad_norm": 0.15922518074512482,
      "learning_rate": 0.00016748875039148593,
      "loss": 0.8579,
      "step": 131
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 0.14013421535491943,
      "learning_rate": 0.0001669809994047364,
      "loss": 0.9431,
      "step": 132
    },
    {
      "epoch": 1.1367521367521367,
      "grad_norm": 0.1704006940126419,
      "learning_rate": 0.0001664700969078398,
      "loss": 0.5517,
      "step": 133
    },
    {
      "epoch": 1.1452991452991452,
      "grad_norm": 0.13392962515354156,
      "learning_rate": 0.00016595606693917142,
      "loss": 0.9121,
      "step": 134
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.1552940011024475,
      "learning_rate": 0.00016543893368425666,
      "loss": 0.4912,
      "step": 135
    },
    {
      "epoch": 1.1623931623931625,
      "grad_norm": 0.18563082814216614,
      "learning_rate": 0.00016491872147463306,
      "loss": 0.4675,
      "step": 136
    },
    {
      "epoch": 1.170940170940171,
      "grad_norm": 0.15236620604991913,
      "learning_rate": 0.00016439545478670543,
      "loss": 1.3404,
      "step": 137
    },
    {
      "epoch": 1.1794871794871795,
      "grad_norm": 0.174940288066864,
      "learning_rate": 0.00016386915824059427,
      "loss": 0.4409,
      "step": 138
    },
    {
      "epoch": 1.188034188034188,
      "grad_norm": 0.15595194697380066,
      "learning_rate": 0.00016333985659897735,
      "loss": 0.4154,
      "step": 139
    },
    {
      "epoch": 1.1965811965811965,
      "grad_norm": 0.228506937623024,
      "learning_rate": 0.00016280757476592466,
      "loss": 0.5345,
      "step": 140
    },
    {
      "epoch": 1.205128205128205,
      "grad_norm": 0.190291628241539,
      "learning_rate": 0.0001622723377857265,
      "loss": 0.4737,
      "step": 141
    },
    {
      "epoch": 1.2136752136752136,
      "grad_norm": 0.16119037568569183,
      "learning_rate": 0.00016173417084171536,
      "loss": 1.0343,
      "step": 142
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.1885722428560257,
      "learning_rate": 0.00016119309925508078,
      "loss": 0.4301,
      "step": 143
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.2301076203584671,
      "learning_rate": 0.0001606491484836782,
      "loss": 0.4663,
      "step": 144
    },
    {
      "epoch": 1.2393162393162394,
      "grad_norm": 0.22810214757919312,
      "learning_rate": 0.00016010234412083086,
      "loss": 0.5471,
      "step": 145
    },
    {
      "epoch": 1.2478632478632479,
      "grad_norm": 0.2208271473646164,
      "learning_rate": 0.00015955271189412598,
      "loss": 0.5562,
      "step": 146
    },
    {
      "epoch": 1.2564102564102564,
      "grad_norm": 0.21081416308879852,
      "learning_rate": 0.00015900027766420393,
      "loss": 0.4473,
      "step": 147
    },
    {
      "epoch": 1.264957264957265,
      "grad_norm": 0.21207793056964874,
      "learning_rate": 0.00015844506742354164,
      "loss": 0.5266,
      "step": 148
    },
    {
      "epoch": 1.2735042735042734,
      "grad_norm": 0.16276563704013824,
      "learning_rate": 0.00015788710729522953,
      "loss": 0.7908,
      "step": 149
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 0.22083953022956848,
      "learning_rate": 0.00015732642353174259,
      "loss": 0.8843,
      "step": 150
    },
    {
      "epoch": 1.2905982905982907,
      "grad_norm": 0.17566369473934174,
      "learning_rate": 0.0001567630425137049,
      "loss": 0.4006,
      "step": 151
    },
    {
      "epoch": 1.2991452991452992,
      "grad_norm": 0.20828555524349213,
      "learning_rate": 0.00015619699074864864,
      "loss": 0.4822,
      "step": 152
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.24228675663471222,
      "learning_rate": 0.00015562829486976673,
      "loss": 0.5371,
      "step": 153
    },
    {
      "epoch": 1.3162393162393162,
      "grad_norm": 0.20822276175022125,
      "learning_rate": 0.00015505698163465986,
      "loss": 0.5768,
      "step": 154
    },
    {
      "epoch": 1.3247863247863247,
      "grad_norm": 0.24567489326000214,
      "learning_rate": 0.00015448307792407734,
      "loss": 0.4823,
      "step": 155
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.197309672832489,
      "learning_rate": 0.00015390661074065256,
      "loss": 0.4762,
      "step": 156
    },
    {
      "epoch": 1.341880341880342,
      "grad_norm": 0.197679802775383,
      "learning_rate": 0.00015332760720763232,
      "loss": 0.9415,
      "step": 157
    },
    {
      "epoch": 1.3504273504273505,
      "grad_norm": 0.25542306900024414,
      "learning_rate": 0.00015274609456760073,
      "loss": 0.597,
      "step": 158
    },
    {
      "epoch": 1.358974358974359,
      "grad_norm": 0.2353532910346985,
      "learning_rate": 0.00015216210018119733,
      "loss": 0.6134,
      "step": 159
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": 0.2198248952627182,
      "learning_rate": 0.00015157565152583002,
      "loss": 0.404,
      "step": 160
    },
    {
      "epoch": 1.376068376068376,
      "grad_norm": 0.23019669950008392,
      "learning_rate": 0.0001509867761943818,
      "loss": 0.7029,
      "step": 161
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.23030109703540802,
      "learning_rate": 0.00015039550189391298,
      "loss": 0.4926,
      "step": 162
    },
    {
      "epoch": 1.393162393162393,
      "grad_norm": 0.22199463844299316,
      "learning_rate": 0.0001498018564443571,
      "loss": 0.7314,
      "step": 163
    },
    {
      "epoch": 1.4017094017094016,
      "grad_norm": 0.2894566059112549,
      "learning_rate": 0.0001492058677772123,
      "loss": 0.6278,
      "step": 164
    },
    {
      "epoch": 1.4102564102564101,
      "grad_norm": 0.23239579796791077,
      "learning_rate": 0.000148607563934227,
      "loss": 0.5154,
      "step": 165
    },
    {
      "epoch": 1.4188034188034189,
      "grad_norm": 0.1754232496023178,
      "learning_rate": 0.00014800697306608044,
      "loss": 0.3844,
      "step": 166
    },
    {
      "epoch": 1.4273504273504274,
      "grad_norm": 0.21024148166179657,
      "learning_rate": 0.00014740412343105828,
      "loss": 0.7683,
      "step": 167
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.19907836616039276,
      "learning_rate": 0.00014679904339372302,
      "loss": 0.4233,
      "step": 168
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.23564042150974274,
      "learning_rate": 0.00014619176142357935,
      "loss": 0.4311,
      "step": 169
    },
    {
      "epoch": 1.452991452991453,
      "grad_norm": 0.2250904142856598,
      "learning_rate": 0.0001455823060937347,
      "loss": 0.4856,
      "step": 170
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.23243001103401184,
      "learning_rate": 0.00014497070607955476,
      "loss": 0.4631,
      "step": 171
    },
    {
      "epoch": 1.4700854700854702,
      "grad_norm": 0.23028317093849182,
      "learning_rate": 0.00014435699015731448,
      "loss": 0.4553,
      "step": 172
    },
    {
      "epoch": 1.4786324786324787,
      "grad_norm": 0.22723744809627533,
      "learning_rate": 0.00014374118720284388,
      "loss": 0.5416,
      "step": 173
    },
    {
      "epoch": 1.4871794871794872,
      "grad_norm": 0.19445589184761047,
      "learning_rate": 0.00014312332619016965,
      "loss": 0.6555,
      "step": 174
    },
    {
      "epoch": 1.4957264957264957,
      "grad_norm": 0.2619200348854065,
      "learning_rate": 0.0001425034361901516,
      "loss": 0.514,
      "step": 175
    },
    {
      "epoch": 1.5042735042735043,
      "grad_norm": 0.21888214349746704,
      "learning_rate": 0.00014188154636911524,
      "loss": 1.0691,
      "step": 176
    },
    {
      "epoch": 1.5128205128205128,
      "grad_norm": 0.27063801884651184,
      "learning_rate": 0.0001412576859874791,
      "loss": 0.4708,
      "step": 177
    },
    {
      "epoch": 1.5213675213675213,
      "grad_norm": 0.2242051512002945,
      "learning_rate": 0.00014063188439837832,
      "loss": 0.4148,
      "step": 178
    },
    {
      "epoch": 1.5299145299145298,
      "grad_norm": 0.23847071826457977,
      "learning_rate": 0.0001400041710462833,
      "loss": 0.4079,
      "step": 179
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.2358533889055252,
      "learning_rate": 0.0001393745754656146,
      "loss": 0.4605,
      "step": 180
    },
    {
      "epoch": 1.547008547008547,
      "grad_norm": 0.21623782813549042,
      "learning_rate": 0.00013874312727935292,
      "loss": 0.4267,
      "step": 181
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.24794210493564606,
      "learning_rate": 0.00013810985619764572,
      "loss": 0.891,
      "step": 182
    },
    {
      "epoch": 1.564102564102564,
      "grad_norm": 0.23464177548885345,
      "learning_rate": 0.00013747479201640914,
      "loss": 0.4279,
      "step": 183
    },
    {
      "epoch": 1.5726495726495726,
      "grad_norm": 0.2624233365058899,
      "learning_rate": 0.00013683796461592604,
      "loss": 0.5339,
      "step": 184
    },
    {
      "epoch": 1.5811965811965814,
      "grad_norm": 0.2277112752199173,
      "learning_rate": 0.00013619940395944027,
      "loss": 0.4799,
      "step": 185
    },
    {
      "epoch": 1.5897435897435899,
      "grad_norm": 0.23767705261707306,
      "learning_rate": 0.00013555914009174663,
      "loss": 0.4674,
      "step": 186
    },
    {
      "epoch": 1.5982905982905984,
      "grad_norm": 0.25418999791145325,
      "learning_rate": 0.00013491720313777756,
      "loss": 0.8197,
      "step": 187
    },
    {
      "epoch": 1.606837606837607,
      "grad_norm": 0.23988768458366394,
      "learning_rate": 0.00013427362330118543,
      "loss": 0.4751,
      "step": 188
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.24494890868663788,
      "learning_rate": 0.0001336284308629216,
      "loss": 0.5937,
      "step": 189
    },
    {
      "epoch": 1.623931623931624,
      "grad_norm": 0.2371889352798462,
      "learning_rate": 0.00013298165617981172,
      "loss": 0.6011,
      "step": 190
    },
    {
      "epoch": 1.6324786324786325,
      "grad_norm": 0.2653796970844269,
      "learning_rate": 0.00013233332968312715,
      "loss": 0.6948,
      "step": 191
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.25794872641563416,
      "learning_rate": 0.0001316834818771535,
      "loss": 0.5216,
      "step": 192
    },
    {
      "epoch": 1.6495726495726495,
      "grad_norm": 0.2563187777996063,
      "learning_rate": 0.00013103214333775521,
      "loss": 0.5315,
      "step": 193
    },
    {
      "epoch": 1.658119658119658,
      "grad_norm": 0.25503745675086975,
      "learning_rate": 0.00013037934471093682,
      "loss": 0.4844,
      "step": 194
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.24019081890583038,
      "learning_rate": 0.00012972511671140125,
      "loss": 0.432,
      "step": 195
    },
    {
      "epoch": 1.6752136752136753,
      "grad_norm": 0.2514346241950989,
      "learning_rate": 0.00012906949012110456,
      "loss": 0.6718,
      "step": 196
    },
    {
      "epoch": 1.6837606837606838,
      "grad_norm": 0.25518113374710083,
      "learning_rate": 0.00012841249578780757,
      "loss": 0.5857,
      "step": 197
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.1949378252029419,
      "learning_rate": 0.00012775416462362457,
      "loss": 0.5007,
      "step": 198
    },
    {
      "epoch": 1.7008547008547008,
      "grad_norm": 0.2098771333694458,
      "learning_rate": 0.00012709452760356884,
      "loss": 1.0816,
      "step": 199
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 0.22702141106128693,
      "learning_rate": 0.00012643361576409516,
      "loss": 0.4873,
      "step": 200
    },
    {
      "epoch": 1.717948717948718,
      "grad_norm": 0.2466471642255783,
      "learning_rate": 0.00012577146020163968,
      "loss": 0.531,
      "step": 201
    },
    {
      "epoch": 1.7264957264957266,
      "grad_norm": 0.271100252866745,
      "learning_rate": 0.00012510809207115666,
      "loss": 0.4665,
      "step": 202
    },
    {
      "epoch": 1.735042735042735,
      "grad_norm": 0.23357507586479187,
      "learning_rate": 0.00012444354258465268,
      "loss": 0.4377,
      "step": 203
    },
    {
      "epoch": 1.7435897435897436,
      "grad_norm": 0.27511459589004517,
      "learning_rate": 0.00012377784300971807,
      "loss": 0.7007,
      "step": 204
    },
    {
      "epoch": 1.7521367521367521,
      "grad_norm": 0.2679981291294098,
      "learning_rate": 0.0001231110246680558,
      "loss": 0.9589,
      "step": 205
    },
    {
      "epoch": 1.7606837606837606,
      "grad_norm": 0.30028238892555237,
      "learning_rate": 0.00012244311893400763,
      "loss": 0.5532,
      "step": 206
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.2935997545719147,
      "learning_rate": 0.00012177415723307808,
      "loss": 0.5076,
      "step": 207
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.23444046080112457,
      "learning_rate": 0.00012110417104045575,
      "loss": 0.4156,
      "step": 208
    },
    {
      "epoch": 1.7863247863247862,
      "grad_norm": 0.2363792359828949,
      "learning_rate": 0.00012043319187953241,
      "loss": 0.5128,
      "step": 209
    },
    {
      "epoch": 1.7948717948717947,
      "grad_norm": 0.26668813824653625,
      "learning_rate": 0.00011976125132041974,
      "loss": 0.532,
      "step": 210
    },
    {
      "epoch": 1.8034188034188035,
      "grad_norm": 0.2957119941711426,
      "learning_rate": 0.00011908838097846404,
      "loss": 0.6331,
      "step": 211
    },
    {
      "epoch": 1.811965811965812,
      "grad_norm": 0.25156503915786743,
      "learning_rate": 0.00011841461251275867,
      "loss": 0.6589,
      "step": 212
    },
    {
      "epoch": 1.8205128205128205,
      "grad_norm": 0.287786602973938,
      "learning_rate": 0.00011773997762465429,
      "loss": 0.4924,
      "step": 213
    },
    {
      "epoch": 1.8290598290598292,
      "grad_norm": 0.24399590492248535,
      "learning_rate": 0.0001170645080562676,
      "loss": 0.5602,
      "step": 214
    },
    {
      "epoch": 1.8376068376068377,
      "grad_norm": 0.21881946921348572,
      "learning_rate": 0.00011638823558898762,
      "loss": 0.4379,
      "step": 215
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.238422691822052,
      "learning_rate": 0.00011571119204198037,
      "loss": 0.4542,
      "step": 216
    },
    {
      "epoch": 1.8547008547008548,
      "grad_norm": 0.22345015406608582,
      "learning_rate": 0.00011503340927069189,
      "loss": 0.5594,
      "step": 217
    },
    {
      "epoch": 1.8632478632478633,
      "grad_norm": 0.2149413377046585,
      "learning_rate": 0.00011435491916534919,
      "loss": 0.4606,
      "step": 218
    },
    {
      "epoch": 1.8717948717948718,
      "grad_norm": 0.23460443317890167,
      "learning_rate": 0.00011367575364946006,
      "loss": 0.468,
      "step": 219
    },
    {
      "epoch": 1.8803418803418803,
      "grad_norm": 0.25990983843803406,
      "learning_rate": 0.00011299594467831078,
      "loss": 0.4717,
      "step": 220
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.2715575098991394,
      "learning_rate": 0.00011231552423746283,
      "loss": 0.5399,
      "step": 221
    },
    {
      "epoch": 1.8974358974358974,
      "grad_norm": 0.22398780286312103,
      "learning_rate": 0.00011163452434124773,
      "loss": 0.4537,
      "step": 222
    },
    {
      "epoch": 1.9059829059829059,
      "grad_norm": 0.23402731120586395,
      "learning_rate": 0.00011095297703126093,
      "loss": 0.4228,
      "step": 223
    },
    {
      "epoch": 1.9145299145299144,
      "grad_norm": 0.24860350787639618,
      "learning_rate": 0.00011027091437485404,
      "loss": 0.5115,
      "step": 224
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.27918487787246704,
      "learning_rate": 0.00010958836846362621,
      "loss": 0.598,
      "step": 225
    },
    {
      "epoch": 1.9316239316239316,
      "grad_norm": 0.2415376901626587,
      "learning_rate": 0.00010890537141191417,
      "loss": 0.4511,
      "step": 226
    },
    {
      "epoch": 1.9401709401709402,
      "grad_norm": 0.29969534277915955,
      "learning_rate": 0.00010822195535528106,
      "loss": 0.6956,
      "step": 227
    },
    {
      "epoch": 1.9487179487179487,
      "grad_norm": 0.22788582742214203,
      "learning_rate": 0.00010753815244900458,
      "loss": 0.444,
      "step": 228
    },
    {
      "epoch": 1.9572649572649574,
      "grad_norm": 0.27178987860679626,
      "learning_rate": 0.00010685399486656406,
      "loss": 0.4885,
      "step": 229
    },
    {
      "epoch": 1.965811965811966,
      "grad_norm": 0.2516106367111206,
      "learning_rate": 0.00010616951479812658,
      "loss": 0.4628,
      "step": 230
    },
    {
      "epoch": 1.9743589743589745,
      "grad_norm": 0.27476766705513,
      "learning_rate": 0.00010548474444903247,
      "loss": 0.4074,
      "step": 231
    },
    {
      "epoch": 1.982905982905983,
      "grad_norm": 0.24148069322109222,
      "learning_rate": 0.00010479971603828,
      "loss": 0.4478,
      "step": 232
    },
    {
      "epoch": 1.9914529914529915,
      "grad_norm": 0.21842096745967865,
      "learning_rate": 0.00010411446179700943,
      "loss": 0.4399,
      "step": 233
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.37498506903648376,
      "learning_rate": 0.00010342901396698659,
      "loss": 0.4834,
      "step": 234
    },
    {
      "epoch": 2.0085470085470085,
      "grad_norm": 0.19363939762115479,
      "learning_rate": 0.00010274340479908568,
      "loss": 0.255,
      "step": 235
    },
    {
      "epoch": 2.017094017094017,
      "grad_norm": 0.2148725390434265,
      "learning_rate": 0.00010205766655177215,
      "loss": 0.2766,
      "step": 236
    },
    {
      "epoch": 2.0256410256410255,
      "grad_norm": 0.2098715603351593,
      "learning_rate": 0.00010137183148958463,
      "loss": 0.4017,
      "step": 237
    },
    {
      "epoch": 2.034188034188034,
      "grad_norm": 0.2367039918899536,
      "learning_rate": 0.00010068593188161697,
      "loss": 0.2509,
      "step": 238
    },
    {
      "epoch": 2.0427350427350426,
      "grad_norm": 0.2819689214229584,
      "learning_rate": 0.0001,
      "loss": 0.3205,
      "step": 239
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 0.24612751603126526,
      "learning_rate": 9.931406811838308e-05,
      "loss": 0.2399,
      "step": 240
    },
    {
      "epoch": 2.0598290598290596,
      "grad_norm": 0.26913249492645264,
      "learning_rate": 9.862816851041541e-05,
      "loss": 0.2114,
      "step": 241
    },
    {
      "epoch": 2.0683760683760686,
      "grad_norm": 0.2225734293460846,
      "learning_rate": 9.79423334482279e-05,
      "loss": 0.3501,
      "step": 242
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 0.29952186346054077,
      "learning_rate": 9.725659520091433e-05,
      "loss": 0.2845,
      "step": 243
    },
    {
      "epoch": 2.0854700854700856,
      "grad_norm": 0.3168615400791168,
      "learning_rate": 9.657098603301346e-05,
      "loss": 0.3215,
      "step": 244
    },
    {
      "epoch": 2.094017094017094,
      "grad_norm": 0.2955262064933777,
      "learning_rate": 9.588553820299056e-05,
      "loss": 0.2687,
      "step": 245
    },
    {
      "epoch": 2.1025641025641026,
      "grad_norm": 0.3473421335220337,
      "learning_rate": 9.520028396172003e-05,
      "loss": 0.4656,
      "step": 246
    },
    {
      "epoch": 2.111111111111111,
      "grad_norm": 0.3319595158100128,
      "learning_rate": 9.451525555096753e-05,
      "loss": 0.2646,
      "step": 247
    },
    {
      "epoch": 2.1196581196581197,
      "grad_norm": 0.28052112460136414,
      "learning_rate": 9.383048520187344e-05,
      "loss": 0.2316,
      "step": 248
    },
    {
      "epoch": 2.128205128205128,
      "grad_norm": 0.31672582030296326,
      "learning_rate": 9.314600513343595e-05,
      "loss": 0.2554,
      "step": 249
    },
    {
      "epoch": 2.1367521367521367,
      "grad_norm": 0.31639257073402405,
      "learning_rate": 9.246184755099545e-05,
      "loss": 0.5943,
      "step": 250
    },
    {
      "epoch": 2.1452991452991452,
      "grad_norm": 0.32504305243492126,
      "learning_rate": 9.177804464471898e-05,
      "loss": 0.6759,
      "step": 251
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.31236812472343445,
      "learning_rate": 9.109462858808586e-05,
      "loss": 0.6995,
      "step": 252
    },
    {
      "epoch": 2.1623931623931623,
      "grad_norm": 0.2664802074432373,
      "learning_rate": 9.041163153637381e-05,
      "loss": 0.25,
      "step": 253
    },
    {
      "epoch": 2.1709401709401708,
      "grad_norm": 0.3435586392879486,
      "learning_rate": 8.972908562514598e-05,
      "loss": 0.3131,
      "step": 254
    },
    {
      "epoch": 2.1794871794871793,
      "grad_norm": 0.34814453125,
      "learning_rate": 8.904702296873912e-05,
      "loss": 0.2966,
      "step": 255
    },
    {
      "epoch": 2.1880341880341883,
      "grad_norm": 0.28498131036758423,
      "learning_rate": 8.836547565875227e-05,
      "loss": 0.2533,
      "step": 256
    },
    {
      "epoch": 2.1965811965811968,
      "grad_norm": 0.24858739972114563,
      "learning_rate": 8.76844757625372e-05,
      "loss": 0.8398,
      "step": 257
    },
    {
      "epoch": 2.2051282051282053,
      "grad_norm": 0.29406729340553284,
      "learning_rate": 8.70040553216892e-05,
      "loss": 0.2527,
      "step": 258
    },
    {
      "epoch": 2.213675213675214,
      "grad_norm": 0.3250654637813568,
      "learning_rate": 8.632424635053997e-05,
      "loss": 0.3872,
      "step": 259
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.27981558442115784,
      "learning_rate": 8.564508083465079e-05,
      "loss": 0.2431,
      "step": 260
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.2734360694885254,
      "learning_rate": 8.496659072930813e-05,
      "loss": 0.2392,
      "step": 261
    },
    {
      "epoch": 2.2393162393162394,
      "grad_norm": 0.28624212741851807,
      "learning_rate": 8.428880795801965e-05,
      "loss": 0.2388,
      "step": 262
    },
    {
      "epoch": 2.247863247863248,
      "grad_norm": 0.3781333863735199,
      "learning_rate": 8.36117644110124e-05,
      "loss": 0.3461,
      "step": 263
    },
    {
      "epoch": 2.2564102564102564,
      "grad_norm": 0.2944338023662567,
      "learning_rate": 8.293549194373243e-05,
      "loss": 0.2242,
      "step": 264
    },
    {
      "epoch": 2.264957264957265,
      "grad_norm": 0.3108060359954834,
      "learning_rate": 8.226002237534572e-05,
      "loss": 0.2555,
      "step": 265
    },
    {
      "epoch": 2.2735042735042734,
      "grad_norm": 0.4619787335395813,
      "learning_rate": 8.158538748724139e-05,
      "loss": 0.4434,
      "step": 266
    },
    {
      "epoch": 2.282051282051282,
      "grad_norm": 0.40326377749443054,
      "learning_rate": 8.091161902153595e-05,
      "loss": 0.2889,
      "step": 267
    },
    {
      "epoch": 2.2905982905982905,
      "grad_norm": 0.2909954786300659,
      "learning_rate": 8.023874867958027e-05,
      "loss": 0.5651,
      "step": 268
    },
    {
      "epoch": 2.299145299145299,
      "grad_norm": 0.3555508852005005,
      "learning_rate": 7.95668081204676e-05,
      "loss": 0.3184,
      "step": 269
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.3254183530807495,
      "learning_rate": 7.889582895954427e-05,
      "loss": 0.2694,
      "step": 270
    },
    {
      "epoch": 2.316239316239316,
      "grad_norm": 0.3343075215816498,
      "learning_rate": 7.822584276692191e-05,
      "loss": 0.2277,
      "step": 271
    },
    {
      "epoch": 2.324786324786325,
      "grad_norm": 0.34715527296066284,
      "learning_rate": 7.755688106599241e-05,
      "loss": 0.2935,
      "step": 272
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.3642890751361847,
      "learning_rate": 7.688897533194424e-05,
      "loss": 0.3397,
      "step": 273
    },
    {
      "epoch": 2.341880341880342,
      "grad_norm": 0.39590999484062195,
      "learning_rate": 7.622215699028196e-05,
      "loss": 0.2385,
      "step": 274
    },
    {
      "epoch": 2.3504273504273505,
      "grad_norm": 0.29188475012779236,
      "learning_rate": 7.555645741534736e-05,
      "loss": 0.2629,
      "step": 275
    },
    {
      "epoch": 2.358974358974359,
      "grad_norm": 0.5034640431404114,
      "learning_rate": 7.489190792884338e-05,
      "loss": 0.579,
      "step": 276
    },
    {
      "epoch": 2.3675213675213675,
      "grad_norm": 0.419330894947052,
      "learning_rate": 7.422853979836034e-05,
      "loss": 0.4862,
      "step": 277
    },
    {
      "epoch": 2.376068376068376,
      "grad_norm": 0.2967374622821808,
      "learning_rate": 7.356638423590485e-05,
      "loss": 0.229,
      "step": 278
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 0.3208567202091217,
      "learning_rate": 7.290547239643117e-05,
      "loss": 0.2645,
      "step": 279
    },
    {
      "epoch": 2.393162393162393,
      "grad_norm": 0.286146879196167,
      "learning_rate": 7.224583537637544e-05,
      "loss": 0.2623,
      "step": 280
    },
    {
      "epoch": 2.4017094017094016,
      "grad_norm": 0.4479420781135559,
      "learning_rate": 7.158750421219244e-05,
      "loss": 0.7091,
      "step": 281
    },
    {
      "epoch": 2.41025641025641,
      "grad_norm": 0.3299665153026581,
      "learning_rate": 7.093050987889547e-05,
      "loss": 0.239,
      "step": 282
    },
    {
      "epoch": 2.4188034188034186,
      "grad_norm": 0.3034355640411377,
      "learning_rate": 7.027488328859876e-05,
      "loss": 0.2449,
      "step": 283
    },
    {
      "epoch": 2.427350427350427,
      "grad_norm": 0.2865277826786041,
      "learning_rate": 6.96206552890632e-05,
      "loss": 0.264,
      "step": 284
    },
    {
      "epoch": 2.435897435897436,
      "grad_norm": 0.33174970746040344,
      "learning_rate": 6.896785666224481e-05,
      "loss": 0.2591,
      "step": 285
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.47158727049827576,
      "learning_rate": 6.831651812284652e-05,
      "loss": 0.2271,
      "step": 286
    },
    {
      "epoch": 2.452991452991453,
      "grad_norm": 0.3159971535205841,
      "learning_rate": 6.766667031687286e-05,
      "loss": 0.2939,
      "step": 287
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.33401429653167725,
      "learning_rate": 6.701834382018832e-05,
      "loss": 0.2688,
      "step": 288
    },
    {
      "epoch": 2.47008547008547,
      "grad_norm": 0.30884698033332825,
      "learning_rate": 6.637156913707839e-05,
      "loss": 0.221,
      "step": 289
    },
    {
      "epoch": 2.4786324786324787,
      "grad_norm": 0.3034002184867859,
      "learning_rate": 6.572637669881458e-05,
      "loss": 0.2341,
      "step": 290
    },
    {
      "epoch": 2.4871794871794872,
      "grad_norm": 0.45387423038482666,
      "learning_rate": 6.508279686222243e-05,
      "loss": 0.5931,
      "step": 291
    },
    {
      "epoch": 2.4957264957264957,
      "grad_norm": 0.31251057982444763,
      "learning_rate": 6.444085990825338e-05,
      "loss": 0.235,
      "step": 292
    },
    {
      "epoch": 2.5042735042735043,
      "grad_norm": 0.2936059236526489,
      "learning_rate": 6.380059604055974e-05,
      "loss": 0.2365,
      "step": 293
    },
    {
      "epoch": 2.5128205128205128,
      "grad_norm": 0.5007711052894592,
      "learning_rate": 6.316203538407397e-05,
      "loss": 0.4366,
      "step": 294
    },
    {
      "epoch": 2.5213675213675213,
      "grad_norm": 0.33560439944267273,
      "learning_rate": 6.252520798359092e-05,
      "loss": 0.2563,
      "step": 295
    },
    {
      "epoch": 2.52991452991453,
      "grad_norm": 0.3034367859363556,
      "learning_rate": 6.18901438023543e-05,
      "loss": 0.2346,
      "step": 296
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 0.3213258385658264,
      "learning_rate": 6.125687272064713e-05,
      "loss": 0.2659,
      "step": 297
    },
    {
      "epoch": 2.547008547008547,
      "grad_norm": 0.2833086848258972,
      "learning_rate": 6.0625424534385425e-05,
      "loss": 0.22,
      "step": 298
    },
    {
      "epoch": 2.5555555555555554,
      "grad_norm": 0.37906017899513245,
      "learning_rate": 5.9995828953716695e-05,
      "loss": 0.3529,
      "step": 299
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 0.30926746129989624,
      "learning_rate": 5.936811560162169e-05,
      "loss": 0.2607,
      "step": 300
    },
    {
      "epoch": 2.5726495726495724,
      "grad_norm": 0.2918412387371063,
      "learning_rate": 5.87423140125209e-05,
      "loss": 0.2328,
      "step": 301
    },
    {
      "epoch": 2.5811965811965814,
      "grad_norm": 0.28964853286743164,
      "learning_rate": 5.811845363088477e-05,
      "loss": 0.2032,
      "step": 302
    },
    {
      "epoch": 2.58974358974359,
      "grad_norm": 0.3795534372329712,
      "learning_rate": 5.749656380984844e-05,
      "loss": 0.2818,
      "step": 303
    },
    {
      "epoch": 2.5982905982905984,
      "grad_norm": 0.36522042751312256,
      "learning_rate": 5.687667380983037e-05,
      "loss": 0.2479,
      "step": 304
    },
    {
      "epoch": 2.606837606837607,
      "grad_norm": 0.28648072481155396,
      "learning_rate": 5.625881279715615e-05,
      "loss": 0.2325,
      "step": 305
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.3319568634033203,
      "learning_rate": 5.5643009842685554e-05,
      "loss": 0.6223,
      "step": 306
    },
    {
      "epoch": 2.623931623931624,
      "grad_norm": 0.31825199723243713,
      "learning_rate": 5.502929392044528e-05,
      "loss": 0.2626,
      "step": 307
    },
    {
      "epoch": 2.6324786324786325,
      "grad_norm": 0.31757840514183044,
      "learning_rate": 5.4417693906265365e-05,
      "loss": 0.1985,
      "step": 308
    },
    {
      "epoch": 2.641025641025641,
      "grad_norm": 0.3652052581310272,
      "learning_rate": 5.380823857642069e-05,
      "loss": 0.2996,
      "step": 309
    },
    {
      "epoch": 2.6495726495726495,
      "grad_norm": 0.46834203600883484,
      "learning_rate": 5.3200956606277006e-05,
      "loss": 0.3504,
      "step": 310
    },
    {
      "epoch": 2.658119658119658,
      "grad_norm": 0.3154442310333252,
      "learning_rate": 5.259587656894174e-05,
      "loss": 0.2344,
      "step": 311
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.3850618898868561,
      "learning_rate": 5.199302693391959e-05,
      "loss": 0.2938,
      "step": 312
    },
    {
      "epoch": 2.6752136752136755,
      "grad_norm": 0.5739899277687073,
      "learning_rate": 5.139243606577302e-05,
      "loss": 0.3775,
      "step": 313
    },
    {
      "epoch": 2.683760683760684,
      "grad_norm": 0.39588040113449097,
      "learning_rate": 5.0794132222787707e-05,
      "loss": 0.2708,
      "step": 314
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.3245130777359009,
      "learning_rate": 5.019814355564292e-05,
      "loss": 0.2513,
      "step": 315
    },
    {
      "epoch": 2.700854700854701,
      "grad_norm": 0.34261611104011536,
      "learning_rate": 4.960449810608705e-05,
      "loss": 0.3577,
      "step": 316
    },
    {
      "epoch": 2.7094017094017095,
      "grad_norm": 0.32460838556289673,
      "learning_rate": 4.90132238056182e-05,
      "loss": 0.2306,
      "step": 317
    },
    {
      "epoch": 2.717948717948718,
      "grad_norm": 0.38145536184310913,
      "learning_rate": 4.8424348474170014e-05,
      "loss": 0.7211,
      "step": 318
    },
    {
      "epoch": 2.7264957264957266,
      "grad_norm": 0.3700217306613922,
      "learning_rate": 4.783789981880267e-05,
      "loss": 0.2318,
      "step": 319
    },
    {
      "epoch": 2.735042735042735,
      "grad_norm": 0.27968108654022217,
      "learning_rate": 4.725390543239929e-05,
      "loss": 0.1733,
      "step": 320
    },
    {
      "epoch": 2.7435897435897436,
      "grad_norm": 0.3555721342563629,
      "learning_rate": 4.667239279236768e-05,
      "loss": 0.3995,
      "step": 321
    },
    {
      "epoch": 2.752136752136752,
      "grad_norm": 0.37104782462120056,
      "learning_rate": 4.609338925934743e-05,
      "loss": 0.2746,
      "step": 322
    },
    {
      "epoch": 2.7606837606837606,
      "grad_norm": 0.38219180703163147,
      "learning_rate": 4.551692207592265e-05,
      "loss": 0.4816,
      "step": 323
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.3220447599887848,
      "learning_rate": 4.494301836534016e-05,
      "loss": 0.2259,
      "step": 324
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.4126596748828888,
      "learning_rate": 4.4371705130233275e-05,
      "loss": 0.2903,
      "step": 325
    },
    {
      "epoch": 2.786324786324786,
      "grad_norm": 0.3305305242538452,
      "learning_rate": 4.380300925135138e-05,
      "loss": 0.1877,
      "step": 326
    },
    {
      "epoch": 2.7948717948717947,
      "grad_norm": 0.3647128641605377,
      "learning_rate": 4.3236957486295115e-05,
      "loss": 0.6341,
      "step": 327
    },
    {
      "epoch": 2.8034188034188032,
      "grad_norm": 0.4659888744354248,
      "learning_rate": 4.267357646825746e-05,
      "loss": 0.5346,
      "step": 328
    },
    {
      "epoch": 2.8119658119658117,
      "grad_norm": 0.37838730216026306,
      "learning_rate": 4.211289270477047e-05,
      "loss": 0.2331,
      "step": 329
    },
    {
      "epoch": 2.8205128205128203,
      "grad_norm": 0.3572704792022705,
      "learning_rate": 4.1554932576458415e-05,
      "loss": 0.259,
      "step": 330
    },
    {
      "epoch": 2.8290598290598292,
      "grad_norm": 0.4293743371963501,
      "learning_rate": 4.0999722335796075e-05,
      "loss": 0.485,
      "step": 331
    },
    {
      "epoch": 2.8376068376068377,
      "grad_norm": 0.36608031392097473,
      "learning_rate": 4.044728810587406e-05,
      "loss": 0.24,
      "step": 332
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 0.36508500576019287,
      "learning_rate": 3.989765587916914e-05,
      "loss": 0.2183,
      "step": 333
    },
    {
      "epoch": 2.8547008547008548,
      "grad_norm": 0.3653337359428406,
      "learning_rate": 3.935085151632185e-05,
      "loss": 0.2941,
      "step": 334
    },
    {
      "epoch": 2.8632478632478633,
      "grad_norm": 0.33566993474960327,
      "learning_rate": 3.8806900744919205e-05,
      "loss": 0.1972,
      "step": 335
    },
    {
      "epoch": 2.871794871794872,
      "grad_norm": 0.4166345000267029,
      "learning_rate": 3.826582915828468e-05,
      "loss": 0.3246,
      "step": 336
    },
    {
      "epoch": 2.8803418803418803,
      "grad_norm": 0.33019134402275085,
      "learning_rate": 3.7727662214273495e-05,
      "loss": 0.2262,
      "step": 337
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.2849208116531372,
      "learning_rate": 3.719242523407539e-05,
      "loss": 0.1684,
      "step": 338
    },
    {
      "epoch": 2.8974358974358974,
      "grad_norm": 0.48358550667762756,
      "learning_rate": 3.666014340102268e-05,
      "loss": 0.5395,
      "step": 339
    },
    {
      "epoch": 2.905982905982906,
      "grad_norm": 0.40972188115119934,
      "learning_rate": 3.613084175940578e-05,
      "loss": 0.4852,
      "step": 340
    },
    {
      "epoch": 2.9145299145299144,
      "grad_norm": 0.34858328104019165,
      "learning_rate": 3.5604545213294616e-05,
      "loss": 0.5135,
      "step": 341
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.3521900773048401,
      "learning_rate": 3.508127852536698e-05,
      "loss": 0.4108,
      "step": 342
    },
    {
      "epoch": 2.931623931623932,
      "grad_norm": 0.3895696997642517,
      "learning_rate": 3.456106631574336e-05,
      "loss": 0.3179,
      "step": 343
    },
    {
      "epoch": 2.9401709401709404,
      "grad_norm": 0.3148210942745209,
      "learning_rate": 3.4043933060828605e-05,
      "loss": 0.2433,
      "step": 344
    },
    {
      "epoch": 2.948717948717949,
      "grad_norm": 0.34274551272392273,
      "learning_rate": 3.352990309216022e-05,
      "loss": 0.4979,
      "step": 345
    },
    {
      "epoch": 2.9572649572649574,
      "grad_norm": 0.40572017431259155,
      "learning_rate": 3.3019000595263574e-05,
      "loss": 0.2549,
      "step": 346
    },
    {
      "epoch": 2.965811965811966,
      "grad_norm": 0.3175290524959564,
      "learning_rate": 3.251124960851408e-05,
      "loss": 0.2092,
      "step": 347
    },
    {
      "epoch": 2.9743589743589745,
      "grad_norm": 0.39352893829345703,
      "learning_rate": 3.200667402200586e-05,
      "loss": 0.2827,
      "step": 348
    },
    {
      "epoch": 2.982905982905983,
      "grad_norm": 0.37667280435562134,
      "learning_rate": 3.1505297576428075e-05,
      "loss": 0.2258,
      "step": 349
    },
    {
      "epoch": 2.9914529914529915,
      "grad_norm": 0.3290167450904846,
      "learning_rate": 3.100714386194757e-05,
      "loss": 0.2499,
      "step": 350
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.31929585337638855,
      "learning_rate": 3.0512236317099175e-05,
      "loss": 0.2217,
      "step": 351
    },
    {
      "epoch": 3.0085470085470085,
      "grad_norm": 0.25231093168258667,
      "learning_rate": 3.0020598227682795e-05,
      "loss": 0.1592,
      "step": 352
    },
    {
      "epoch": 3.017094017094017,
      "grad_norm": 0.2783128321170807,
      "learning_rate": 2.953225272566782e-05,
      "loss": 0.1587,
      "step": 353
    },
    {
      "epoch": 3.0256410256410255,
      "grad_norm": 0.2709429860115051,
      "learning_rate": 2.904722278810471e-05,
      "loss": 0.138,
      "step": 354
    },
    {
      "epoch": 3.034188034188034,
      "grad_norm": 0.2641993463039398,
      "learning_rate": 2.8565531236043997e-05,
      "loss": 0.1398,
      "step": 355
    },
    {
      "epoch": 3.0427350427350426,
      "grad_norm": 0.29233217239379883,
      "learning_rate": 2.8087200733462425e-05,
      "loss": 0.1863,
      "step": 356
    },
    {
      "epoch": 3.051282051282051,
      "grad_norm": 0.3354048728942871,
      "learning_rate": 2.7612253786196664e-05,
      "loss": 0.229,
      "step": 357
    },
    {
      "epoch": 3.0598290598290596,
      "grad_norm": 0.23641164600849152,
      "learning_rate": 2.7140712740884376e-05,
      "loss": 0.0967,
      "step": 358
    },
    {
      "epoch": 3.0683760683760686,
      "grad_norm": 0.31092557311058044,
      "learning_rate": 2.667259978391281e-05,
      "loss": 0.1503,
      "step": 359
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.3478125035762787,
      "learning_rate": 2.6207936940374767e-05,
      "loss": 0.158,
      "step": 360
    },
    {
      "epoch": 3.0854700854700856,
      "grad_norm": 0.43139657378196716,
      "learning_rate": 2.5746746073032625e-05,
      "loss": 0.2012,
      "step": 361
    },
    {
      "epoch": 3.094017094017094,
      "grad_norm": 0.2283385694026947,
      "learning_rate": 2.5289048881289256e-05,
      "loss": 0.1198,
      "step": 362
    },
    {
      "epoch": 3.1025641025641026,
      "grad_norm": 0.29495614767074585,
      "learning_rate": 2.4834866900167475e-05,
      "loss": 0.1571,
      "step": 363
    },
    {
      "epoch": 3.111111111111111,
      "grad_norm": 0.28707411885261536,
      "learning_rate": 2.4384221499296466e-05,
      "loss": 0.117,
      "step": 364
    },
    {
      "epoch": 3.1196581196581197,
      "grad_norm": 0.2678401470184326,
      "learning_rate": 2.393713388190648e-05,
      "loss": 0.1061,
      "step": 365
    },
    {
      "epoch": 3.128205128205128,
      "grad_norm": 0.28327521681785583,
      "learning_rate": 2.3493625083831217e-05,
      "loss": 0.3351,
      "step": 366
    },
    {
      "epoch": 3.1367521367521367,
      "grad_norm": 0.2834165692329407,
      "learning_rate": 2.3053715972518e-05,
      "loss": 0.1307,
      "step": 367
    },
    {
      "epoch": 3.1452991452991452,
      "grad_norm": 0.4773244559764862,
      "learning_rate": 2.2617427246045973e-05,
      "loss": 0.4119,
      "step": 368
    },
    {
      "epoch": 3.1538461538461537,
      "grad_norm": 0.5910007357597351,
      "learning_rate": 2.218477943215229e-05,
      "loss": 0.3174,
      "step": 369
    },
    {
      "epoch": 3.1623931623931623,
      "grad_norm": 0.3223881125450134,
      "learning_rate": 2.1755792887266234e-05,
      "loss": 0.2194,
      "step": 370
    },
    {
      "epoch": 3.1709401709401708,
      "grad_norm": 0.44032856822013855,
      "learning_rate": 2.133048779555129e-05,
      "loss": 0.2329,
      "step": 371
    },
    {
      "epoch": 3.1794871794871793,
      "grad_norm": 0.4083745777606964,
      "learning_rate": 2.0908884167955824e-05,
      "loss": 0.1986,
      "step": 372
    },
    {
      "epoch": 3.1880341880341883,
      "grad_norm": 0.3356578052043915,
      "learning_rate": 2.0491001841271074e-05,
      "loss": 0.149,
      "step": 373
    },
    {
      "epoch": 3.1965811965811968,
      "grad_norm": 0.3564605414867401,
      "learning_rate": 2.0076860477198313e-05,
      "loss": 0.1208,
      "step": 374
    },
    {
      "epoch": 3.2051282051282053,
      "grad_norm": 0.32371172308921814,
      "learning_rate": 1.9666479561423244e-05,
      "loss": 0.1442,
      "step": 375
    },
    {
      "epoch": 3.213675213675214,
      "grad_norm": 0.334807813167572,
      "learning_rate": 1.9259878402699705e-05,
      "loss": 0.1011,
      "step": 376
    },
    {
      "epoch": 3.2222222222222223,
      "grad_norm": 0.3495379388332367,
      "learning_rate": 1.8857076131940642e-05,
      "loss": 0.109,
      "step": 377
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 0.3352341055870056,
      "learning_rate": 1.8458091701318504e-05,
      "loss": 0.151,
      "step": 378
    },
    {
      "epoch": 3.2393162393162394,
      "grad_norm": 0.34603044390678406,
      "learning_rate": 1.806294388337305e-05,
      "loss": 0.1292,
      "step": 379
    },
    {
      "epoch": 3.247863247863248,
      "grad_norm": 0.3652786314487457,
      "learning_rate": 1.7671651270128532e-05,
      "loss": 0.1322,
      "step": 380
    },
    {
      "epoch": 3.2564102564102564,
      "grad_norm": 0.32136398553848267,
      "learning_rate": 1.7284232272218504e-05,
      "loss": 0.1175,
      "step": 381
    },
    {
      "epoch": 3.264957264957265,
      "grad_norm": 0.35561975836753845,
      "learning_rate": 1.69007051180199e-05,
      "loss": 0.3736,
      "step": 382
    },
    {
      "epoch": 3.2735042735042734,
      "grad_norm": 0.4261399209499359,
      "learning_rate": 1.652108785279526e-05,
      "loss": 0.1571,
      "step": 383
    },
    {
      "epoch": 3.282051282051282,
      "grad_norm": 0.35193243622779846,
      "learning_rate": 1.6145398337843652e-05,
      "loss": 0.0893,
      "step": 384
    },
    {
      "epoch": 3.2905982905982905,
      "grad_norm": 0.330085426568985,
      "learning_rate": 1.577365424966034e-05,
      "loss": 0.1053,
      "step": 385
    },
    {
      "epoch": 3.299145299145299,
      "grad_norm": 0.5352822542190552,
      "learning_rate": 1.540587307910508e-05,
      "loss": 0.1738,
      "step": 386
    },
    {
      "epoch": 3.3076923076923075,
      "grad_norm": 0.35743480920791626,
      "learning_rate": 1.504207213057912e-05,
      "loss": 0.3253,
      "step": 387
    },
    {
      "epoch": 3.316239316239316,
      "grad_norm": 0.3298165500164032,
      "learning_rate": 1.4682268521211073e-05,
      "loss": 0.7715,
      "step": 388
    },
    {
      "epoch": 3.324786324786325,
      "grad_norm": 0.2609596848487854,
      "learning_rate": 1.43264791800515e-05,
      "loss": 0.1023,
      "step": 389
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.2767914831638336,
      "learning_rate": 1.3974720847276412e-05,
      "loss": 0.0662,
      "step": 390
    },
    {
      "epoch": 3.341880341880342,
      "grad_norm": 0.28199678659439087,
      "learning_rate": 1.3627010073399604e-05,
      "loss": 0.1275,
      "step": 391
    },
    {
      "epoch": 3.3504273504273505,
      "grad_norm": 0.3435691297054291,
      "learning_rate": 1.328336321849396e-05,
      "loss": 0.1238,
      "step": 392
    },
    {
      "epoch": 3.358974358974359,
      "grad_norm": 0.527239203453064,
      "learning_rate": 1.2943796451421686e-05,
      "loss": 0.1578,
      "step": 393
    },
    {
      "epoch": 3.3675213675213675,
      "grad_norm": 0.3848626911640167,
      "learning_rate": 1.2608325749073591e-05,
      "loss": 0.1266,
      "step": 394
    },
    {
      "epoch": 3.376068376068376,
      "grad_norm": 0.33509427309036255,
      "learning_rate": 1.227696689561727e-05,
      "loss": 0.1236,
      "step": 395
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 0.30514073371887207,
      "learning_rate": 1.1949735481754565e-05,
      "loss": 0.0847,
      "step": 396
    },
    {
      "epoch": 3.393162393162393,
      "grad_norm": 0.29753297567367554,
      "learning_rate": 1.1626646903987904e-05,
      "loss": 0.1121,
      "step": 397
    },
    {
      "epoch": 3.4017094017094016,
      "grad_norm": 0.482013076543808,
      "learning_rate": 1.130771636389596e-05,
      "loss": 0.1401,
      "step": 398
    },
    {
      "epoch": 3.41025641025641,
      "grad_norm": 0.5458863973617554,
      "learning_rate": 1.0992958867418357e-05,
      "loss": 0.124,
      "step": 399
    },
    {
      "epoch": 3.4188034188034186,
      "grad_norm": 0.32971060276031494,
      "learning_rate": 1.0682389224149647e-05,
      "loss": 0.1159,
      "step": 400
    },
    {
      "epoch": 3.427350427350427,
      "grad_norm": 0.3122265040874481,
      "learning_rate": 1.037602204664252e-05,
      "loss": 0.1294,
      "step": 401
    },
    {
      "epoch": 3.435897435897436,
      "grad_norm": 0.3240589201450348,
      "learning_rate": 1.0073871749720221e-05,
      "loss": 0.1197,
      "step": 402
    },
    {
      "epoch": 3.4444444444444446,
      "grad_norm": 0.25612542033195496,
      "learning_rate": 9.775952549798406e-06,
      "loss": 0.0953,
      "step": 403
    },
    {
      "epoch": 3.452991452991453,
      "grad_norm": 0.3129337430000305,
      "learning_rate": 9.482278464216121e-06,
      "loss": 0.292,
      "step": 404
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 0.3538060188293457,
      "learning_rate": 9.192863310576472e-06,
      "loss": 0.2617,
      "step": 405
    },
    {
      "epoch": 3.47008547008547,
      "grad_norm": 0.39724695682525635,
      "learning_rate": 8.907720706096224e-06,
      "loss": 0.3621,
      "step": 406
    },
    {
      "epoch": 3.4786324786324787,
      "grad_norm": 0.26678666472435,
      "learning_rate": 8.626864066965402e-06,
      "loss": 0.077,
      "step": 407
    },
    {
      "epoch": 3.4871794871794872,
      "grad_norm": 0.3215920925140381,
      "learning_rate": 8.350306607715774e-06,
      "loss": 0.1251,
      "step": 408
    },
    {
      "epoch": 3.4957264957264957,
      "grad_norm": 0.3566943407058716,
      "learning_rate": 8.07806134059933e-06,
      "loss": 0.1276,
      "step": 409
    },
    {
      "epoch": 3.5042735042735043,
      "grad_norm": 0.4169897139072418,
      "learning_rate": 7.810141074975818e-06,
      "loss": 0.2404,
      "step": 410
    },
    {
      "epoch": 3.5128205128205128,
      "grad_norm": 0.328621506690979,
      "learning_rate": 7.546558416710292e-06,
      "loss": 0.0995,
      "step": 411
    },
    {
      "epoch": 3.5213675213675213,
      "grad_norm": 0.565329372882843,
      "learning_rate": 7.287325767579756e-06,
      "loss": 0.1966,
      "step": 412
    },
    {
      "epoch": 3.52991452991453,
      "grad_norm": 0.4235149621963501,
      "learning_rate": 7.032455324689902e-06,
      "loss": 0.1539,
      "step": 413
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 0.3190467357635498,
      "learning_rate": 6.781959079900957e-06,
      "loss": 0.1375,
      "step": 414
    },
    {
      "epoch": 3.547008547008547,
      "grad_norm": 0.3970963656902313,
      "learning_rate": 6.535848819263679e-06,
      "loss": 0.2572,
      "step": 415
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.40918058156967163,
      "learning_rate": 6.2941361224647e-06,
      "loss": 0.1785,
      "step": 416
    },
    {
      "epoch": 3.564102564102564,
      "grad_norm": 0.37111562490463257,
      "learning_rate": 6.056832362281728e-06,
      "loss": 0.1356,
      "step": 417
    },
    {
      "epoch": 3.5726495726495724,
      "grad_norm": 0.30336591601371765,
      "learning_rate": 5.823948704048443e-06,
      "loss": 0.0943,
      "step": 418
    },
    {
      "epoch": 3.5811965811965814,
      "grad_norm": 0.3331542909145355,
      "learning_rate": 5.5954961051291384e-06,
      "loss": 0.1167,
      "step": 419
    },
    {
      "epoch": 3.58974358974359,
      "grad_norm": 0.3731980323791504,
      "learning_rate": 5.371485314403202e-06,
      "loss": 0.1454,
      "step": 420
    },
    {
      "epoch": 3.5982905982905984,
      "grad_norm": 0.4047635793685913,
      "learning_rate": 5.151926871759349e-06,
      "loss": 0.1992,
      "step": 421
    },
    {
      "epoch": 3.606837606837607,
      "grad_norm": 0.5668995380401611,
      "learning_rate": 4.936831107599749e-06,
      "loss": 0.1276,
      "step": 422
    },
    {
      "epoch": 3.6153846153846154,
      "grad_norm": 0.5091368556022644,
      "learning_rate": 4.7262081423538716e-06,
      "loss": 0.2935,
      "step": 423
    },
    {
      "epoch": 3.623931623931624,
      "grad_norm": 0.3514919877052307,
      "learning_rate": 4.5200678860024885e-06,
      "loss": 0.1079,
      "step": 424
    },
    {
      "epoch": 3.6324786324786325,
      "grad_norm": 0.3287922739982605,
      "learning_rate": 4.3184200376111815e-06,
      "loss": 0.0967,
      "step": 425
    },
    {
      "epoch": 3.641025641025641,
      "grad_norm": 0.3324579894542694,
      "learning_rate": 4.121274084874194e-06,
      "loss": 0.119,
      "step": 426
    },
    {
      "epoch": 3.6495726495726495,
      "grad_norm": 0.32925722002983093,
      "learning_rate": 3.928639303667891e-06,
      "loss": 0.1104,
      "step": 427
    },
    {
      "epoch": 3.658119658119658,
      "grad_norm": 0.33713653683662415,
      "learning_rate": 3.7405247576144054e-06,
      "loss": 0.1065,
      "step": 428
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 0.3364379405975342,
      "learning_rate": 3.556939297655115e-06,
      "loss": 0.1196,
      "step": 429
    },
    {
      "epoch": 3.6752136752136755,
      "grad_norm": 0.3627510368824005,
      "learning_rate": 3.3778915616342943e-06,
      "loss": 0.1096,
      "step": 430
    },
    {
      "epoch": 3.683760683760684,
      "grad_norm": 0.32618480920791626,
      "learning_rate": 3.203389973892579e-06,
      "loss": 0.1043,
      "step": 431
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.33231377601623535,
      "learning_rate": 3.0334427448706847e-06,
      "loss": 0.1114,
      "step": 432
    },
    {
      "epoch": 3.700854700854701,
      "grad_norm": 0.37258434295654297,
      "learning_rate": 2.868057870723073e-06,
      "loss": 0.1108,
      "step": 433
    },
    {
      "epoch": 3.7094017094017095,
      "grad_norm": 0.33310258388519287,
      "learning_rate": 2.707243132941717e-06,
      "loss": 0.1411,
      "step": 434
    },
    {
      "epoch": 3.717948717948718,
      "grad_norm": 0.3012758493423462,
      "learning_rate": 2.5510060979899607e-06,
      "loss": 0.0968,
      "step": 435
    },
    {
      "epoch": 3.7264957264957266,
      "grad_norm": 0.4315149188041687,
      "learning_rate": 2.3993541169465837e-06,
      "loss": 0.3345,
      "step": 436
    },
    {
      "epoch": 3.735042735042735,
      "grad_norm": 0.3669329285621643,
      "learning_rate": 2.2522943251597873e-06,
      "loss": 0.1063,
      "step": 437
    },
    {
      "epoch": 3.7435897435897436,
      "grad_norm": 0.32640382647514343,
      "learning_rate": 2.1098336419116625e-06,
      "loss": 0.1441,
      "step": 438
    },
    {
      "epoch": 3.752136752136752,
      "grad_norm": 0.39195308089256287,
      "learning_rate": 1.971978770092431e-06,
      "loss": 0.1259,
      "step": 439
    },
    {
      "epoch": 3.7606837606837606,
      "grad_norm": 0.46261560916900635,
      "learning_rate": 1.838736195885238e-06,
      "loss": 0.2368,
      "step": 440
    },
    {
      "epoch": 3.769230769230769,
      "grad_norm": 0.2374536246061325,
      "learning_rate": 1.710112188460844e-06,
      "loss": 0.0773,
      "step": 441
    },
    {
      "epoch": 3.7777777777777777,
      "grad_norm": 0.36584457755088806,
      "learning_rate": 1.5861127996827597e-06,
      "loss": 0.1559,
      "step": 442
    },
    {
      "epoch": 3.786324786324786,
      "grad_norm": 0.3893975615501404,
      "learning_rate": 1.4667438638224062e-06,
      "loss": 0.1334,
      "step": 443
    },
    {
      "epoch": 3.7948717948717947,
      "grad_norm": 0.604230523109436,
      "learning_rate": 1.3520109972846917e-06,
      "loss": 0.1421,
      "step": 444
    },
    {
      "epoch": 3.8034188034188032,
      "grad_norm": 0.30988043546676636,
      "learning_rate": 1.2419195983436881e-06,
      "loss": 0.1263,
      "step": 445
    },
    {
      "epoch": 3.8119658119658117,
      "grad_norm": 0.43840423226356506,
      "learning_rate": 1.1364748468886687e-06,
      "loss": 0.456,
      "step": 446
    },
    {
      "epoch": 3.8205128205128203,
      "grad_norm": 0.43162277340888977,
      "learning_rate": 1.0356817041804246e-06,
      "loss": 0.3257,
      "step": 447
    },
    {
      "epoch": 3.8290598290598292,
      "grad_norm": 0.3156612515449524,
      "learning_rate": 9.395449126177291e-07,
      "loss": 0.0927,
      "step": 448
    },
    {
      "epoch": 3.8376068376068377,
      "grad_norm": 0.369768351316452,
      "learning_rate": 8.480689955143395e-07,
      "loss": 0.0979,
      "step": 449
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.36806395649909973,
      "learning_rate": 7.612582568860549e-07,
      "loss": 0.1624,
      "step": 450
    },
    {
      "epoch": 3.8547008547008548,
      "grad_norm": 0.32407721877098083,
      "learning_rate": 6.791167812483012e-07,
      "loss": 0.1467,
      "step": 451
    },
    {
      "epoch": 3.8632478632478633,
      "grad_norm": 0.38585758209228516,
      "learning_rate": 6.016484334238515e-07,
      "loss": 0.2306,
      "step": 452
    },
    {
      "epoch": 3.871794871794872,
      "grad_norm": 0.33580198884010315,
      "learning_rate": 5.288568583610931e-07,
      "loss": 0.1309,
      "step": 453
    },
    {
      "epoch": 3.8803418803418803,
      "grad_norm": 0.2997514605522156,
      "learning_rate": 4.607454809624434e-07,
      "loss": 0.1175,
      "step": 454
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 0.3412640392780304,
      "learning_rate": 3.9731750592325587e-07,
      "loss": 0.1274,
      "step": 455
    },
    {
      "epoch": 3.8974358974358974,
      "grad_norm": 0.2880537509918213,
      "learning_rate": 3.385759175809966e-07,
      "loss": 0.1227,
      "step": 456
    },
    {
      "epoch": 3.905982905982906,
      "grad_norm": 0.4961593747138977,
      "learning_rate": 2.845234797748897e-07,
      "loss": 0.1557,
      "step": 457
    },
    {
      "epoch": 3.9145299145299144,
      "grad_norm": 0.3552994728088379,
      "learning_rate": 2.3516273571577708e-07,
      "loss": 0.118,
      "step": 458
    },
    {
      "epoch": 3.9230769230769234,
      "grad_norm": 0.3282444477081299,
      "learning_rate": 1.9049600786658073e-07,
      "loss": 0.1375,
      "step": 459
    },
    {
      "epoch": 3.931623931623932,
      "grad_norm": 0.3986610770225525,
      "learning_rate": 1.505253978329235e-07,
      "loss": 0.2402,
      "step": 460
    },
    {
      "epoch": 3.9401709401709404,
      "grad_norm": 0.3198491632938385,
      "learning_rate": 1.1525278626431934e-07,
      "loss": 0.1186,
      "step": 461
    },
    {
      "epoch": 3.948717948717949,
      "grad_norm": 0.3509187698364258,
      "learning_rate": 8.467983276563284e-08,
      "loss": 0.2249,
      "step": 462
    },
    {
      "epoch": 3.9572649572649574,
      "grad_norm": 0.3045540452003479,
      "learning_rate": 5.880797581904185e-08,
      "loss": 0.1109,
      "step": 463
    },
    {
      "epoch": 3.965811965811966,
      "grad_norm": 0.39755794405937195,
      "learning_rate": 3.763843271631373e-08,
      "loss": 0.22,
      "step": 464
    },
    {
      "epoch": 3.9743589743589745,
      "grad_norm": 0.43977466225624084,
      "learning_rate": 2.1172199501573455e-08,
      "loss": 0.1666,
      "step": 465
    },
    {
      "epoch": 3.982905982905983,
      "grad_norm": 0.44676533341407776,
      "learning_rate": 9.410050924374415e-09,
      "loss": 0.1582,
      "step": 466
    },
    {
      "epoch": 3.9914529914529915,
      "grad_norm": 0.437174528837204,
      "learning_rate": 2.3525404033275523e-09,
      "loss": 0.1578,
      "step": 467
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.41418156027793884,
      "learning_rate": 0.0,
      "loss": 0.1431,
      "step": 468
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.2426231966371676e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}