{
  "best_global_step": null,
  "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": 0.10029701143503189,
      "learning_rate": 0.0,
      "loss": 0.9306,
      "step": 1
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 0.08052678406238556,
      "learning_rate": 2e-05,
      "loss": 0.7117,
      "step": 2
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.08854332566261292,
      "learning_rate": 4e-05,
      "loss": 0.9713,
      "step": 3
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 0.08534839749336243,
      "learning_rate": 6e-05,
      "loss": 1.2294,
      "step": 4
    },
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 0.10985274612903595,
      "learning_rate": 8e-05,
      "loss": 0.7663,
      "step": 5
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 0.11135748773813248,
      "learning_rate": 0.0001,
      "loss": 1.2196,
      "step": 6
    },
    {
      "epoch": 0.05982905982905983,
      "grad_norm": 0.14041584730148315,
      "learning_rate": 0.00012,
      "loss": 0.8264,
      "step": 7
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.1369175761938095,
      "learning_rate": 0.00014,
      "loss": 0.8466,
      "step": 8
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.15486544370651245,
      "learning_rate": 0.00016,
      "loss": 0.6706,
      "step": 9
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 0.13222217559814453,
      "learning_rate": 0.00018,
      "loss": 0.9259,
      "step": 10
    },
    {
      "epoch": 0.09401709401709402,
      "grad_norm": 0.18782587349414825,
      "learning_rate": 0.0002,
      "loss": 0.8703,
      "step": 11
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.10356240719556808,
      "learning_rate": 0.0001999976474595967,
      "loss": 0.6685,
      "step": 12
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.2092558741569519,
      "learning_rate": 0.00019999058994907564,
      "loss": 0.7975,
      "step": 13
    },
    {
      "epoch": 0.11965811965811966,
      "grad_norm": 0.2504117786884308,
      "learning_rate": 0.00019997882780049847,
      "loss": 0.8819,
      "step": 14
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 0.11324036121368408,
      "learning_rate": 0.0001999623615672837,
      "loss": 1.0256,
      "step": 15
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.11058590561151505,
      "learning_rate": 0.00019994119202418098,
      "loss": 0.7114,
      "step": 16
    },
    {
      "epoch": 0.1452991452991453,
      "grad_norm": 0.10105215013027191,
      "learning_rate": 0.00019991532016723439,
      "loss": 1.1117,
      "step": 17
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.10304293781518936,
      "learning_rate": 0.00019988474721373568,
      "loss": 0.5724,
      "step": 18
    },
    {
      "epoch": 0.1623931623931624,
      "grad_norm": 0.10554756969213486,
      "learning_rate": 0.00019984947460216707,
      "loss": 0.6811,
      "step": 19
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 0.08927387744188309,
      "learning_rate": 0.00019980950399213344,
      "loss": 0.5931,
      "step": 20
    },
    {
      "epoch": 0.1794871794871795,
      "grad_norm": 0.12103314697742462,
      "learning_rate": 0.00019976483726428422,
      "loss": 0.6178,
      "step": 21
    },
    {
      "epoch": 0.18803418803418803,
      "grad_norm": 0.10690393298864365,
      "learning_rate": 0.0001997154765202251,
      "loss": 0.684,
      "step": 22
    },
    {
      "epoch": 0.19658119658119658,
      "grad_norm": 0.12019173800945282,
      "learning_rate": 0.00019966142408241901,
      "loss": 0.7525,
      "step": 23
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.15269601345062256,
      "learning_rate": 0.00019960268249407675,
      "loss": 0.7275,
      "step": 24
    },
    {
      "epoch": 0.21367521367521367,
      "grad_norm": 0.10956241190433502,
      "learning_rate": 0.00019953925451903756,
      "loss": 1.3161,
      "step": 25
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.14796307682991028,
      "learning_rate": 0.0001994711431416389,
      "loss": 1.1426,
      "step": 26
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.11839503049850464,
      "learning_rate": 0.00019939835156657616,
      "loss": 0.6399,
      "step": 27
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 0.12927889823913574,
      "learning_rate": 0.00019932088321875172,
      "loss": 0.5716,
      "step": 28
    },
    {
      "epoch": 0.24786324786324787,
      "grad_norm": 0.09907636791467667,
      "learning_rate": 0.00019923874174311394,
      "loss": 1.0023,
      "step": 29
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.12379587441682816,
      "learning_rate": 0.0001991519310044857,
      "loss": 0.8321,
      "step": 30
    },
    {
      "epoch": 0.26495726495726496,
      "grad_norm": 0.09996245801448822,
      "learning_rate": 0.00019906045508738228,
      "loss": 0.6025,
      "step": 31
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.11665821075439453,
      "learning_rate": 0.0001989643182958196,
      "loss": 0.6523,
      "step": 32
    },
    {
      "epoch": 0.28205128205128205,
      "grad_norm": 0.11341066658496857,
      "learning_rate": 0.00019886352515311134,
      "loss": 0.876,
      "step": 33
    },
    {
      "epoch": 0.2905982905982906,
      "grad_norm": 0.13329532742500305,
      "learning_rate": 0.0001987580804016563,
      "loss": 0.7652,
      "step": 34
    },
    {
      "epoch": 0.29914529914529914,
      "grad_norm": 0.10840101540088654,
      "learning_rate": 0.00019864798900271532,
      "loss": 0.6088,
      "step": 35
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.11314339935779572,
      "learning_rate": 0.0001985332561361776,
      "loss": 0.5457,
      "step": 36
    },
    {
      "epoch": 0.3162393162393162,
      "grad_norm": 0.11959721893072128,
      "learning_rate": 0.00019841388720031727,
      "loss": 0.629,
      "step": 37
    },
    {
      "epoch": 0.3247863247863248,
      "grad_norm": 0.11554648727178574,
      "learning_rate": 0.00019828988781153917,
      "loss": 0.6265,
      "step": 38
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.10103408247232437,
      "learning_rate": 0.00019816126380411476,
      "loss": 0.6454,
      "step": 39
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.13491952419281006,
      "learning_rate": 0.00019802802122990758,
      "loss": 0.6986,
      "step": 40
    },
    {
      "epoch": 0.3504273504273504,
      "grad_norm": 0.1392458826303482,
      "learning_rate": 0.00019789016635808837,
      "loss": 0.8382,
      "step": 41
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 0.09617948532104492,
      "learning_rate": 0.00019774770567484022,
      "loss": 0.5997,
      "step": 42
    },
    {
      "epoch": 0.36752136752136755,
      "grad_norm": 0.10370145738124847,
      "learning_rate": 0.00019760064588305345,
      "loss": 0.6277,
      "step": 43
    },
    {
      "epoch": 0.37606837606837606,
      "grad_norm": 0.10094348341226578,
      "learning_rate": 0.00019744899390201006,
      "loss": 0.9894,
      "step": 44
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.10623869299888611,
      "learning_rate": 0.0001972927568670583,
      "loss": 0.7392,
      "step": 45
    },
    {
      "epoch": 0.39316239316239315,
      "grad_norm": 0.11181250214576721,
      "learning_rate": 0.00019713194212927696,
      "loss": 0.643,
      "step": 46
    },
    {
      "epoch": 0.4017094017094017,
      "grad_norm": 0.1113968938589096,
      "learning_rate": 0.00019696655725512933,
      "loss": 0.7241,
      "step": 47
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.10064343363046646,
      "learning_rate": 0.00019679661002610743,
      "loss": 0.6307,
      "step": 48
    },
    {
      "epoch": 0.4188034188034188,
      "grad_norm": 0.112760029733181,
      "learning_rate": 0.00019662210843836574,
      "loss": 0.6217,
      "step": 49
    },
    {
      "epoch": 0.42735042735042733,
      "grad_norm": 0.14465677738189697,
      "learning_rate": 0.0001964430607023449,
      "loss": 0.9281,
      "step": 50
    },
    {
      "epoch": 0.4358974358974359,
      "grad_norm": 0.11411717534065247,
      "learning_rate": 0.00019625947524238563,
      "loss": 0.5907,
      "step": 51
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.0978076159954071,
      "learning_rate": 0.00019607136069633212,
      "loss": 0.6345,
      "step": 52
    },
    {
      "epoch": 0.452991452991453,
      "grad_norm": 0.12608304619789124,
      "learning_rate": 0.0001958787259151258,
      "loss": 0.596,
      "step": 53
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.09676168859004974,
      "learning_rate": 0.00019568157996238884,
      "loss": 0.9186,
      "step": 54
    },
    {
      "epoch": 0.4700854700854701,
      "grad_norm": 0.09405568987131119,
      "learning_rate": 0.0001954799321139975,
      "loss": 0.57,
      "step": 55
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.13291001319885254,
      "learning_rate": 0.00019527379185764612,
      "loss": 1.0303,
      "step": 56
    },
    {
      "epoch": 0.48717948717948717,
      "grad_norm": 0.11191993951797485,
      "learning_rate": 0.00019506316889240027,
      "loss": 0.5275,
      "step": 57
    },
    {
      "epoch": 0.49572649572649574,
      "grad_norm": 0.14287959039211273,
      "learning_rate": 0.00019484807312824067,
      "loss": 0.6479,
      "step": 58
    },
    {
      "epoch": 0.5042735042735043,
      "grad_norm": 0.12776006758213043,
      "learning_rate": 0.0001946285146855968,
      "loss": 0.6753,
      "step": 59
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.12789414823055267,
      "learning_rate": 0.0001944045038948709,
      "loss": 0.6047,
      "step": 60
    },
    {
      "epoch": 0.5213675213675214,
      "grad_norm": 0.13046938180923462,
      "learning_rate": 0.00019417605129595157,
      "loss": 0.6116,
      "step": 61
    },
    {
      "epoch": 0.5299145299145299,
      "grad_norm": 0.11159400641918182,
      "learning_rate": 0.0001939431676377183,
      "loss": 0.5822,
      "step": 62
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.09287029504776001,
      "learning_rate": 0.0001937058638775353,
      "loss": 1.1475,
      "step": 63
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.12367334216833115,
      "learning_rate": 0.00019346415118073632,
      "loss": 0.65,
      "step": 64
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.11623897403478622,
      "learning_rate": 0.00019321804092009906,
      "loss": 0.6084,
      "step": 65
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 0.14225900173187256,
      "learning_rate": 0.00019296754467531014,
      "loss": 0.6197,
      "step": 66
    },
    {
      "epoch": 0.5726495726495726,
      "grad_norm": 0.13906919956207275,
      "learning_rate": 0.00019271267423242024,
      "loss": 0.6995,
      "step": 67
    },
    {
      "epoch": 0.5811965811965812,
      "grad_norm": 0.11439445614814758,
      "learning_rate": 0.00019245344158328972,
      "loss": 0.5928,
      "step": 68
    },
    {
      "epoch": 0.5897435897435898,
      "grad_norm": 0.11236923187971115,
      "learning_rate": 0.0001921898589250242,
      "loss": 0.6241,
      "step": 69
    },
    {
      "epoch": 0.5982905982905983,
      "grad_norm": 0.11481335014104843,
      "learning_rate": 0.0001919219386594007,
      "loss": 0.6516,
      "step": 70
    },
    {
      "epoch": 0.6068376068376068,
      "grad_norm": 0.14102552831172943,
      "learning_rate": 0.00019164969339228422,
      "loss": 0.7192,
      "step": 71
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.10549416393041611,
      "learning_rate": 0.00019137313593303463,
      "loss": 1.278,
      "step": 72
    },
    {
      "epoch": 0.6239316239316239,
      "grad_norm": 0.11090132594108582,
      "learning_rate": 0.00019109227929390378,
      "loss": 0.5899,
      "step": 73
    },
    {
      "epoch": 0.6324786324786325,
      "grad_norm": 0.1176087036728859,
      "learning_rate": 0.00019080713668942356,
      "loss": 0.5984,
      "step": 74
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 0.118958480656147,
      "learning_rate": 0.00019051772153578389,
      "loss": 0.59,
      "step": 75
    },
    {
      "epoch": 0.6495726495726496,
      "grad_norm": 0.1070268377661705,
      "learning_rate": 0.00019022404745020163,
      "loss": 0.6014,
      "step": 76
    },
    {
      "epoch": 0.6581196581196581,
      "grad_norm": 0.1408545821905136,
      "learning_rate": 0.00018992612825027976,
      "loss": 0.7224,
      "step": 77
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.11387020349502563,
      "learning_rate": 0.0001896239779533575,
      "loss": 0.5814,
      "step": 78
    },
    {
      "epoch": 0.6752136752136753,
      "grad_norm": 0.11680617928504944,
      "learning_rate": 0.00018931761077585035,
      "loss": 0.5971,
      "step": 79
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.11444367468357086,
      "learning_rate": 0.00018900704113258165,
      "loss": 0.5768,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.14060752093791962,
      "learning_rate": 0.00018869228363610404,
      "loss": 0.643,
      "step": 81
    },
    {
      "epoch": 0.7008547008547008,
      "grad_norm": 0.10634893923997879,
      "learning_rate": 0.00018837335309601213,
      "loss": 1.1269,
      "step": 82
    },
    {
      "epoch": 0.7094017094017094,
      "grad_norm": 0.09636690467596054,
      "learning_rate": 0.00018805026451824546,
      "loss": 1.0619,
      "step": 83
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.11181914061307907,
      "learning_rate": 0.00018772303310438275,
      "loss": 1.034,
      "step": 84
    },
    {
      "epoch": 0.7264957264957265,
      "grad_norm": 0.10488723963499069,
      "learning_rate": 0.00018739167425092644,
      "loss": 0.5419,
      "step": 85
    },
    {
      "epoch": 0.7350427350427351,
      "grad_norm": 0.10924818366765976,
      "learning_rate": 0.00018705620354857833,
      "loss": 0.5407,
      "step": 86
    },
    {
      "epoch": 0.7435897435897436,
      "grad_norm": 0.10910097509622574,
      "learning_rate": 0.00018671663678150607,
      "loss": 0.5555,
      "step": 87
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.15176987648010254,
      "learning_rate": 0.0001863729899266004,
      "loss": 0.9265,
      "step": 88
    },
    {
      "epoch": 0.7606837606837606,
      "grad_norm": 0.10738107562065125,
      "learning_rate": 0.0001860252791527236,
      "loss": 1.1366,
      "step": 89
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.10837385058403015,
      "learning_rate": 0.00018567352081994852,
      "loss": 1.0204,
      "step": 90
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.11676616221666336,
      "learning_rate": 0.00018531773147878895,
      "loss": 0.6022,
      "step": 91
    },
    {
      "epoch": 0.7863247863247863,
      "grad_norm": 0.1307855248451233,
      "learning_rate": 0.0001849579278694209,
      "loss": 0.553,
      "step": 92
    },
    {
      "epoch": 0.7948717948717948,
      "grad_norm": 0.11278946697711945,
      "learning_rate": 0.00018459412692089494,
      "loss": 0.5289,
      "step": 93
    },
    {
      "epoch": 0.8034188034188035,
      "grad_norm": 0.12913955748081207,
      "learning_rate": 0.0001842263457503397,
      "loss": 0.7054,
      "step": 94
    },
    {
      "epoch": 0.811965811965812,
      "grad_norm": 0.14240923523902893,
      "learning_rate": 0.00018385460166215638,
      "loss": 0.6079,
      "step": 95
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.10546304285526276,
      "learning_rate": 0.00018347891214720477,
      "loss": 1.0793,
      "step": 96
    },
    {
      "epoch": 0.8290598290598291,
      "grad_norm": 0.12517417967319489,
      "learning_rate": 0.00018309929488198012,
      "loss": 0.6028,
      "step": 97
    },
    {
      "epoch": 0.8376068376068376,
      "grad_norm": 0.17086289823055267,
      "learning_rate": 0.00018271576772778154,
      "loss": 1.0978,
      "step": 98
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.1711576133966446,
      "learning_rate": 0.00018232834872987147,
      "loss": 0.7112,
      "step": 99
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.16446515917778015,
      "learning_rate": 0.00018193705611662696,
      "loss": 0.6505,
      "step": 100
    },
    {
      "epoch": 0.8632478632478633,
      "grad_norm": 0.11196751147508621,
      "learning_rate": 0.0001815419082986815,
      "loss": 0.9739,
      "step": 101
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 0.10960141569375992,
      "learning_rate": 0.00018114292386805936,
      "loss": 1.0624,
      "step": 102
    },
    {
      "epoch": 0.8803418803418803,
      "grad_norm": 0.10503633320331573,
      "learning_rate": 0.00018074012159730032,
      "loss": 0.8604,
      "step": 103
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.11748067289590836,
      "learning_rate": 0.00018033352043857675,
      "loss": 1.0286,
      "step": 104
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 0.11271696537733078,
      "learning_rate": 0.00017992313952280172,
      "loss": 1.1229,
      "step": 105
    },
    {
      "epoch": 0.905982905982906,
      "grad_norm": 0.1583077758550644,
      "learning_rate": 0.00017950899815872892,
      "loss": 0.9875,
      "step": 106
    },
    {
      "epoch": 0.9145299145299145,
      "grad_norm": 0.17239651083946228,
      "learning_rate": 0.00017909111583204422,
      "loss": 0.7642,
      "step": 107
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.13163897395133972,
      "learning_rate": 0.0001786695122044487,
      "loss": 1.0019,
      "step": 108
    },
    {
      "epoch": 0.9316239316239316,
      "grad_norm": 0.16588492691516876,
      "learning_rate": 0.0001782442071127338,
      "loss": 1.0177,
      "step": 109
    },
    {
      "epoch": 0.9401709401709402,
      "grad_norm": 0.14383426308631897,
      "learning_rate": 0.0001778152205678477,
      "loss": 0.711,
      "step": 110
    },
    {
      "epoch": 0.9487179487179487,
      "grad_norm": 0.13344882428646088,
      "learning_rate": 0.00017738257275395404,
      "loss": 0.656,
      "step": 111
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.129191055893898,
      "learning_rate": 0.00017694628402748202,
      "loss": 0.6431,
      "step": 112
    },
    {
      "epoch": 0.9658119658119658,
      "grad_norm": 0.1446438431739807,
      "learning_rate": 0.0001765063749161688,
      "loss": 0.636,
      "step": 113
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 0.15262292325496674,
      "learning_rate": 0.00017606286611809353,
      "loss": 0.744,
      "step": 114
    },
    {
      "epoch": 0.9829059829059829,
      "grad_norm": 0.1067751869559288,
      "learning_rate": 0.00017561577850070355,
      "loss": 0.5441,
      "step": 115
    },
    {
      "epoch": 0.9914529914529915,
      "grad_norm": 0.14896689355373383,
      "learning_rate": 0.00017516513309983253,
      "loss": 0.6838,
      "step": 116
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.11880003660917282,
      "learning_rate": 0.00017471095111871074,
      "loss": 0.5858,
      "step": 117
    },
    {
      "epoch": 1.0085470085470085,
      "grad_norm": 0.12439899146556854,
      "learning_rate": 0.0001742532539269674,
      "loss": 0.4993,
      "step": 118
    },
    {
      "epoch": 1.017094017094017,
      "grad_norm": 0.1361227184534073,
      "learning_rate": 0.00017379206305962526,
      "loss": 0.4957,
      "step": 119
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.13620759546756744,
      "learning_rate": 0.00017332740021608722,
      "loss": 0.5197,
      "step": 120
    },
    {
      "epoch": 1.0341880341880343,
      "grad_norm": 0.15686914324760437,
      "learning_rate": 0.00017285928725911562,
      "loss": 0.5357,
      "step": 121
    },
    {
      "epoch": 1.0427350427350428,
      "grad_norm": 0.1435684859752655,
      "learning_rate": 0.00017238774621380337,
      "loss": 1.1386,
      "step": 122
    },
    {
      "epoch": 1.0512820512820513,
      "grad_norm": 0.14536544680595398,
      "learning_rate": 0.00017191279926653761,
      "loss": 0.9482,
      "step": 123
    },
    {
      "epoch": 1.0598290598290598,
      "grad_norm": 0.1260910928249359,
      "learning_rate": 0.00017143446876395602,
      "loss": 0.9274,
      "step": 124
    },
    {
      "epoch": 1.0683760683760684,
      "grad_norm": 0.1781182587146759,
      "learning_rate": 0.00017095277721189528,
      "loss": 0.5891,
      "step": 125
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.14145347476005554,
      "learning_rate": 0.00017046774727433222,
      "loss": 0.501,
      "step": 126
    },
    {
      "epoch": 1.0854700854700854,
      "grad_norm": 0.11792827397584915,
      "learning_rate": 0.00016997940177231722,
      "loss": 1.0352,
      "step": 127
    },
    {
      "epoch": 1.0940170940170941,
      "grad_norm": 0.14413173496723175,
      "learning_rate": 0.00016948776368290084,
      "loss": 0.4415,
      "step": 128
    },
    {
      "epoch": 1.1025641025641026,
      "grad_norm": 0.16644181311130524,
      "learning_rate": 0.00016899285613805246,
      "loss": 0.4965,
      "step": 129
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.16641896963119507,
      "learning_rate": 0.00016849470242357196,
      "loss": 0.5147,
      "step": 130
    },
    {
      "epoch": 1.1196581196581197,
      "grad_norm": 0.15483292937278748,
      "learning_rate": 0.00016799332597799413,
      "loss": 0.8552,
      "step": 131
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 0.14025500416755676,
      "learning_rate": 0.00016748875039148593,
      "loss": 0.9426,
      "step": 132
    },
    {
      "epoch": 1.1367521367521367,
      "grad_norm": 0.17571879923343658,
      "learning_rate": 0.0001669809994047364,
      "loss": 0.5733,
      "step": 133
    },
    {
      "epoch": 1.1452991452991452,
      "grad_norm": 0.13522569835186005,
      "learning_rate": 0.0001664700969078398,
      "loss": 0.9103,
      "step": 134
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.14884212613105774,
      "learning_rate": 0.00016595606693917142,
      "loss": 0.476,
      "step": 135
    },
    {
      "epoch": 1.1623931623931625,
      "grad_norm": 0.1804390847682953,
      "learning_rate": 0.00016543893368425666,
      "loss": 0.4718,
      "step": 136
    },
    {
      "epoch": 1.170940170940171,
      "grad_norm": 0.15217268466949463,
      "learning_rate": 0.00016491872147463306,
      "loss": 1.3519,
      "step": 137
    },
    {
      "epoch": 1.1794871794871795,
      "grad_norm": 0.17225416004657745,
      "learning_rate": 0.00016439545478670543,
      "loss": 0.4524,
      "step": 138
    },
    {
      "epoch": 1.188034188034188,
      "grad_norm": 0.1462716907262802,
      "learning_rate": 0.00016386915824059427,
      "loss": 0.4086,
      "step": 139
    },
    {
      "epoch": 1.1965811965811965,
      "grad_norm": 0.21960391104221344,
      "learning_rate": 0.00016333985659897735,
      "loss": 0.5162,
      "step": 140
    },
    {
      "epoch": 1.205128205128205,
      "grad_norm": 0.18565863370895386,
      "learning_rate": 0.00016280757476592466,
      "loss": 0.4705,
      "step": 141
    },
    {
      "epoch": 1.2136752136752136,
      "grad_norm": 0.17508681118488312,
      "learning_rate": 0.0001622723377857265,
      "loss": 1.0217,
      "step": 142
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.17788398265838623,
      "learning_rate": 0.00016173417084171536,
      "loss": 0.4372,
      "step": 143
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.22421914339065552,
      "learning_rate": 0.00016119309925508078,
      "loss": 0.4929,
      "step": 144
    },
    {
      "epoch": 1.2393162393162394,
      "grad_norm": 0.21721677482128143,
      "learning_rate": 0.0001606491484836782,
      "loss": 0.5423,
      "step": 145
    },
    {
      "epoch": 1.2478632478632479,
      "grad_norm": 0.20979344844818115,
      "learning_rate": 0.00016010234412083086,
      "loss": 0.5425,
      "step": 146
    },
    {
      "epoch": 1.2564102564102564,
      "grad_norm": 0.22250452637672424,
      "learning_rate": 0.00015955271189412598,
      "loss": 0.4379,
      "step": 147
    },
    {
      "epoch": 1.264957264957265,
      "grad_norm": 0.20327910780906677,
      "learning_rate": 0.00015900027766420393,
      "loss": 0.524,
      "step": 148
    },
    {
      "epoch": 1.2735042735042734,
      "grad_norm": 0.1663840413093567,
      "learning_rate": 0.00015844506742354164,
      "loss": 0.7961,
      "step": 149
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 0.23894113302230835,
      "learning_rate": 0.00015788710729522953,
      "loss": 0.8949,
      "step": 150
    },
    {
      "epoch": 1.2905982905982907,
      "grad_norm": 0.17409992218017578,
      "learning_rate": 0.00015732642353174259,
      "loss": 0.4062,
      "step": 151
    },
    {
      "epoch": 1.2991452991452992,
      "grad_norm": 0.21271589398384094,
      "learning_rate": 0.0001567630425137049,
      "loss": 0.4782,
      "step": 152
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.23666754364967346,
      "learning_rate": 0.00015619699074864864,
      "loss": 0.5285,
      "step": 153
    },
    {
      "epoch": 1.3162393162393162,
      "grad_norm": 0.21044865250587463,
      "learning_rate": 0.00015562829486976673,
      "loss": 0.5783,
      "step": 154
    },
    {
      "epoch": 1.3247863247863247,
      "grad_norm": 0.23277460038661957,
      "learning_rate": 0.00015505698163465986,
      "loss": 0.4776,
      "step": 155
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.1925256997346878,
      "learning_rate": 0.00015448307792407734,
      "loss": 0.4818,
      "step": 156
    },
    {
      "epoch": 1.341880341880342,
      "grad_norm": 0.20035819709300995,
      "learning_rate": 0.00015390661074065256,
      "loss": 0.9167,
      "step": 157
    },
    {
      "epoch": 1.3504273504273505,
      "grad_norm": 0.24011678993701935,
      "learning_rate": 0.00015332760720763232,
      "loss": 0.5709,
      "step": 158
    },
    {
      "epoch": 1.358974358974359,
      "grad_norm": 0.22502844035625458,
      "learning_rate": 0.00015274609456760073,
      "loss": 0.6155,
      "step": 159
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": 0.22170566022396088,
      "learning_rate": 0.00015216210018119733,
      "loss": 0.4219,
      "step": 160
    },
    {
      "epoch": 1.376068376068376,
      "grad_norm": 0.22208936512470245,
      "learning_rate": 0.00015157565152583002,
      "loss": 0.7116,
      "step": 161
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.23360729217529297,
      "learning_rate": 0.0001509867761943818,
      "loss": 0.522,
      "step": 162
    },
    {
      "epoch": 1.393162393162393,
      "grad_norm": 0.21807582676410675,
      "learning_rate": 0.00015039550189391298,
      "loss": 0.7489,
      "step": 163
    },
    {
      "epoch": 1.4017094017094016,
      "grad_norm": 0.27986690402030945,
      "learning_rate": 0.0001498018564443571,
      "loss": 0.6231,
      "step": 164
    },
    {
      "epoch": 1.4102564102564101,
      "grad_norm": 0.21058622002601624,
      "learning_rate": 0.0001492058677772123,
      "loss": 0.5104,
      "step": 165
    },
    {
      "epoch": 1.4188034188034189,
      "grad_norm": 0.16068929433822632,
      "learning_rate": 0.000148607563934227,
      "loss": 0.3926,
      "step": 166
    },
    {
      "epoch": 1.4273504273504274,
      "grad_norm": 0.2269625961780548,
      "learning_rate": 0.00014800697306608044,
      "loss": 0.7447,
      "step": 167
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.1981010138988495,
      "learning_rate": 0.00014740412343105828,
      "loss": 0.4337,
      "step": 168
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.22520595788955688,
      "learning_rate": 0.00014679904339372302,
      "loss": 0.4477,
      "step": 169
    },
    {
      "epoch": 1.452991452991453,
      "grad_norm": 0.23164638876914978,
      "learning_rate": 0.00014619176142357935,
      "loss": 0.5253,
      "step": 170
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.22553618252277374,
      "learning_rate": 0.0001455823060937347,
      "loss": 0.4774,
      "step": 171
    },
    {
      "epoch": 1.4700854700854702,
      "grad_norm": 0.21466051042079926,
      "learning_rate": 0.00014497070607955476,
      "loss": 0.4562,
      "step": 172
    },
    {
      "epoch": 1.4786324786324787,
      "grad_norm": 0.20833134651184082,
      "learning_rate": 0.00014435699015731448,
      "loss": 0.5463,
      "step": 173
    },
    {
      "epoch": 1.4871794871794872,
      "grad_norm": 0.18441559374332428,
      "learning_rate": 0.00014374118720284388,
      "loss": 0.6737,
      "step": 174
    },
    {
      "epoch": 1.4957264957264957,
      "grad_norm": 0.2528011202812195,
      "learning_rate": 0.00014312332619016965,
      "loss": 0.532,
      "step": 175
    },
    {
      "epoch": 1.5042735042735043,
      "grad_norm": 0.21312370896339417,
      "learning_rate": 0.0001425034361901516,
      "loss": 1.0594,
      "step": 176
    },
    {
      "epoch": 1.5128205128205128,
      "grad_norm": 0.25666671991348267,
      "learning_rate": 0.00014188154636911524,
      "loss": 0.4847,
      "step": 177
    },
    {
      "epoch": 1.5213675213675213,
      "grad_norm": 0.21520811319351196,
      "learning_rate": 0.0001412576859874791,
      "loss": 0.4071,
      "step": 178
    },
    {
      "epoch": 1.5299145299145298,
      "grad_norm": 0.2236626148223877,
      "learning_rate": 0.00014063188439837832,
      "loss": 0.425,
      "step": 179
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.2238091081380844,
      "learning_rate": 0.0001400041710462833,
      "loss": 0.4791,
      "step": 180
    },
    {
      "epoch": 1.547008547008547,
      "grad_norm": 0.20724694430828094,
      "learning_rate": 0.0001393745754656146,
      "loss": 0.4313,
      "step": 181
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.26612359285354614,
      "learning_rate": 0.00013874312727935292,
      "loss": 0.9138,
      "step": 182
    },
    {
      "epoch": 1.564102564102564,
      "grad_norm": 0.21410779654979706,
      "learning_rate": 0.00013810985619764572,
      "loss": 0.4273,
      "step": 183
    },
    {
      "epoch": 1.5726495726495726,
      "grad_norm": 0.2510058283805847,
      "learning_rate": 0.00013747479201640914,
      "loss": 0.5195,
      "step": 184
    },
    {
      "epoch": 1.5811965811965814,
      "grad_norm": 0.22717450559139252,
      "learning_rate": 0.00013683796461592604,
      "loss": 0.4871,
      "step": 185
    },
    {
      "epoch": 1.5897435897435899,
      "grad_norm": 0.22889962792396545,
      "learning_rate": 0.00013619940395944027,
      "loss": 0.4665,
      "step": 186
    },
    {
      "epoch": 1.5982905982905984,
      "grad_norm": 0.2468930035829544,
      "learning_rate": 0.00013555914009174663,
      "loss": 0.8223,
      "step": 187
    },
    {
      "epoch": 1.606837606837607,
      "grad_norm": 0.23853667080402374,
      "learning_rate": 0.00013491720313777756,
      "loss": 0.4891,
      "step": 188
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.23056018352508545,
      "learning_rate": 0.00013427362330118543,
      "loss": 0.5895,
      "step": 189
    },
    {
      "epoch": 1.623931623931624,
      "grad_norm": 0.22705025970935822,
      "learning_rate": 0.0001336284308629216,
      "loss": 0.6313,
      "step": 190
    },
    {
      "epoch": 1.6324786324786325,
      "grad_norm": 0.25321999192237854,
      "learning_rate": 0.00013298165617981172,
      "loss": 0.6763,
      "step": 191
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.24222753942012787,
      "learning_rate": 0.00013233332968312715,
      "loss": 0.53,
      "step": 192
    },
    {
      "epoch": 1.6495726495726495,
      "grad_norm": 0.26378950476646423,
      "learning_rate": 0.0001316834818771535,
      "loss": 0.5352,
      "step": 193
    },
    {
      "epoch": 1.658119658119658,
      "grad_norm": 0.2504538893699646,
      "learning_rate": 0.00013103214333775521,
      "loss": 0.4826,
      "step": 194
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.23577313125133514,
      "learning_rate": 0.00013037934471093682,
      "loss": 0.4581,
      "step": 195
    },
    {
      "epoch": 1.6752136752136753,
      "grad_norm": 0.220009908080101,
      "learning_rate": 0.00012972511671140125,
      "loss": 0.6969,
      "step": 196
    },
    {
      "epoch": 1.6837606837606838,
      "grad_norm": 0.25640594959259033,
      "learning_rate": 0.00012906949012110456,
      "loss": 0.6035,
      "step": 197
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.19390055537223816,
      "learning_rate": 0.00012841249578780757,
      "loss": 0.4922,
      "step": 198
    },
    {
      "epoch": 1.7008547008547008,
      "grad_norm": 0.22488202154636383,
      "learning_rate": 0.00012775416462362457,
      "loss": 1.0472,
      "step": 199
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 0.21580709517002106,
      "learning_rate": 0.00012709452760356884,
      "loss": 0.5015,
      "step": 200
    },
    {
      "epoch": 1.717948717948718,
      "grad_norm": 0.23680485785007477,
      "learning_rate": 0.00012643361576409516,
      "loss": 0.5403,
      "step": 201
    },
    {
      "epoch": 1.7264957264957266,
      "grad_norm": 0.2667020559310913,
      "learning_rate": 0.00012577146020163968,
      "loss": 0.4656,
      "step": 202
    },
    {
      "epoch": 1.735042735042735,
      "grad_norm": 0.22838228940963745,
      "learning_rate": 0.00012510809207115666,
      "loss": 0.4476,
      "step": 203
    },
    {
      "epoch": 1.7435897435897436,
      "grad_norm": 0.26171278953552246,
      "learning_rate": 0.00012444354258465268,
      "loss": 0.7452,
      "step": 204
    },
    {
      "epoch": 1.7521367521367521,
      "grad_norm": 0.23705759644508362,
      "learning_rate": 0.00012377784300971807,
      "loss": 0.9891,
      "step": 205
    },
    {
      "epoch": 1.7606837606837606,
      "grad_norm": 0.27953648567199707,
      "learning_rate": 0.0001231110246680558,
      "loss": 0.5599,
      "step": 206
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.27142223715782166,
      "learning_rate": 0.00012244311893400763,
      "loss": 0.5326,
      "step": 207
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.21326057612895966,
      "learning_rate": 0.00012177415723307808,
      "loss": 0.4255,
      "step": 208
    },
    {
      "epoch": 1.7863247863247862,
      "grad_norm": 0.22959581017494202,
      "learning_rate": 0.00012110417104045575,
      "loss": 0.5416,
      "step": 209
    },
    {
      "epoch": 1.7948717948717947,
      "grad_norm": 0.24283497035503387,
      "learning_rate": 0.00012043319187953241,
      "loss": 0.5293,
      "step": 210
    },
    {
      "epoch": 1.8034188034188035,
      "grad_norm": 0.2807612419128418,
      "learning_rate": 0.00011976125132041974,
      "loss": 0.6265,
      "step": 211
    },
    {
      "epoch": 1.811965811965812,
      "grad_norm": 0.24878078699111938,
      "learning_rate": 0.00011908838097846404,
      "loss": 0.6735,
      "step": 212
    },
    {
      "epoch": 1.8205128205128205,
      "grad_norm": 0.2810921370983124,
      "learning_rate": 0.00011841461251275867,
      "loss": 0.5031,
      "step": 213
    },
    {
      "epoch": 1.8290598290598292,
      "grad_norm": 0.2413010597229004,
      "learning_rate": 0.00011773997762465429,
      "loss": 0.5623,
      "step": 214
    },
    {
      "epoch": 1.8376068376068377,
      "grad_norm": 0.21322430670261383,
      "learning_rate": 0.0001170645080562676,
      "loss": 0.4471,
      "step": 215
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.23753418028354645,
      "learning_rate": 0.00011638823558898762,
      "loss": 0.4685,
      "step": 216
    },
    {
      "epoch": 1.8547008547008548,
      "grad_norm": 0.20267492532730103,
      "learning_rate": 0.00011571119204198037,
      "loss": 0.5507,
      "step": 217
    },
    {
      "epoch": 1.8632478632478633,
      "grad_norm": 0.1974036991596222,
      "learning_rate": 0.00011503340927069189,
      "loss": 0.4572,
      "step": 218
    },
    {
      "epoch": 1.8717948717948718,
      "grad_norm": 0.21735450625419617,
      "learning_rate": 0.00011435491916534919,
      "loss": 0.4472,
      "step": 219
    },
    {
      "epoch": 1.8803418803418803,
      "grad_norm": 0.25369778275489807,
      "learning_rate": 0.00011367575364946006,
      "loss": 0.4999,
      "step": 220
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.26653316617012024,
      "learning_rate": 0.00011299594467831078,
      "loss": 0.5495,
      "step": 221
    },
    {
      "epoch": 1.8974358974358974,
      "grad_norm": 0.21130070090293884,
      "learning_rate": 0.00011231552423746283,
      "loss": 0.4658,
      "step": 222
    },
    {
      "epoch": 1.9059829059829059,
      "grad_norm": 0.23141616582870483,
      "learning_rate": 0.00011163452434124773,
      "loss": 0.4348,
      "step": 223
    },
    {
      "epoch": 1.9145299145299144,
      "grad_norm": 0.2377730756998062,
      "learning_rate": 0.00011095297703126093,
      "loss": 0.5474,
      "step": 224
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.35745319724082947,
      "learning_rate": 0.00011027091437485404,
      "loss": 0.6158,
      "step": 225
    },
    {
      "epoch": 1.9316239316239316,
      "grad_norm": 0.23032304644584656,
      "learning_rate": 0.00010958836846362621,
      "loss": 0.4319,
      "step": 226
    },
    {
      "epoch": 1.9401709401709402,
      "grad_norm": 0.28677475452423096,
      "learning_rate": 0.00010890537141191417,
      "loss": 0.7205,
      "step": 227
    },
    {
      "epoch": 1.9487179487179487,
      "grad_norm": 0.21683649718761444,
      "learning_rate": 0.00010822195535528106,
      "loss": 0.4585,
      "step": 228
    },
    {
      "epoch": 1.9572649572649574,
      "grad_norm": 0.2756011188030243,
      "learning_rate": 0.00010753815244900458,
      "loss": 0.4982,
      "step": 229
    },
    {
      "epoch": 1.965811965811966,
      "grad_norm": 0.23516656458377838,
      "learning_rate": 0.00010685399486656406,
      "loss": 0.481,
      "step": 230
    },
    {
      "epoch": 1.9743589743589745,
      "grad_norm": 0.2550671696662903,
      "learning_rate": 0.00010616951479812658,
      "loss": 0.4317,
      "step": 231
    },
    {
      "epoch": 1.982905982905983,
      "grad_norm": 0.22818918526172638,
      "learning_rate": 0.00010548474444903247,
      "loss": 0.4573,
      "step": 232
    },
    {
      "epoch": 1.9914529914529915,
      "grad_norm": 0.20925907790660858,
      "learning_rate": 0.00010479971603828,
      "loss": 0.4439,
      "step": 233
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.35145893692970276,
      "learning_rate": 0.00010411446179700943,
      "loss": 0.4724,
      "step": 234
    },
    {
      "epoch": 2.0085470085470085,
      "grad_norm": 0.19043906033039093,
      "learning_rate": 0.00010342901396698659,
      "loss": 0.2868,
      "step": 235
    },
    {
      "epoch": 2.017094017094017,
      "grad_norm": 0.20932860672473907,
      "learning_rate": 0.00010274340479908568,
      "loss": 0.2977,
      "step": 236
    },
    {
      "epoch": 2.0256410256410255,
      "grad_norm": 0.21426555514335632,
      "learning_rate": 0.00010205766655177215,
      "loss": 0.4124,
      "step": 237
    },
    {
      "epoch": 2.034188034188034,
      "grad_norm": 0.23439767956733704,
      "learning_rate": 0.00010137183148958463,
      "loss": 0.2718,
      "step": 238
    },
    {
      "epoch": 2.0427350427350426,
      "grad_norm": 0.2915153205394745,
      "learning_rate": 0.00010068593188161697,
      "loss": 0.3733,
      "step": 239
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 0.2572071850299835,
      "learning_rate": 0.0001,
      "loss": 0.2552,
      "step": 240
    },
    {
      "epoch": 2.0598290598290596,
      "grad_norm": 0.2856186032295227,
      "learning_rate": 9.931406811838308e-05,
      "loss": 0.2397,
      "step": 241
    },
    {
      "epoch": 2.0683760683760686,
      "grad_norm": 0.22636406123638153,
      "learning_rate": 9.862816851041541e-05,
      "loss": 0.3619,
      "step": 242
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 0.3647303581237793,
      "learning_rate": 9.79423334482279e-05,
      "loss": 0.3409,
      "step": 243
    },
    {
      "epoch": 2.0854700854700856,
      "grad_norm": 0.288728803396225,
      "learning_rate": 9.725659520091433e-05,
      "loss": 0.3683,
      "step": 244
    },
    {
      "epoch": 2.094017094017094,
      "grad_norm": 0.273608535528183,
      "learning_rate": 9.657098603301346e-05,
      "loss": 0.2936,
      "step": 245
    },
    {
      "epoch": 2.1025641025641026,
      "grad_norm": 0.3561798632144928,
      "learning_rate": 9.588553820299056e-05,
      "loss": 0.4896,
      "step": 246
    },
    {
      "epoch": 2.111111111111111,
      "grad_norm": 0.31504279375076294,
      "learning_rate": 9.520028396172003e-05,
      "loss": 0.3079,
      "step": 247
    },
    {
      "epoch": 2.1196581196581197,
      "grad_norm": 0.2631787955760956,
      "learning_rate": 9.451525555096753e-05,
      "loss": 0.2827,
      "step": 248
    },
    {
      "epoch": 2.128205128205128,
      "grad_norm": 0.27960190176963806,
      "learning_rate": 9.383048520187344e-05,
      "loss": 0.2822,
      "step": 249
    },
    {
      "epoch": 2.1367521367521367,
      "grad_norm": 0.2931435704231262,
      "learning_rate": 9.314600513343595e-05,
      "loss": 0.665,
      "step": 250
    },
    {
      "epoch": 2.1452991452991452,
      "grad_norm": 0.30018237233161926,
      "learning_rate": 9.246184755099545e-05,
      "loss": 0.6836,
      "step": 251
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.30725207924842834,
      "learning_rate": 9.177804464471898e-05,
      "loss": 0.6928,
      "step": 252
    },
    {
      "epoch": 2.1623931623931623,
      "grad_norm": 0.2561006247997284,
      "learning_rate": 9.109462858808586e-05,
      "loss": 0.2961,
      "step": 253
    },
    {
      "epoch": 2.1709401709401708,
      "grad_norm": 0.3232431709766388,
      "learning_rate": 9.041163153637381e-05,
      "loss": 0.3225,
      "step": 254
    },
    {
      "epoch": 2.1794871794871793,
      "grad_norm": 0.33738312125205994,
      "learning_rate": 8.972908562514598e-05,
      "loss": 0.3124,
      "step": 255
    },
    {
      "epoch": 2.1880341880341883,
      "grad_norm": 0.2684638500213623,
      "learning_rate": 8.904702296873912e-05,
      "loss": 0.284,
      "step": 256
    },
    {
      "epoch": 2.1965811965811968,
      "grad_norm": 0.25262558460235596,
      "learning_rate": 8.836547565875227e-05,
      "loss": 0.8309,
      "step": 257
    },
    {
      "epoch": 2.2051282051282053,
      "grad_norm": 0.3041893541812897,
      "learning_rate": 8.76844757625372e-05,
      "loss": 0.2924,
      "step": 258
    },
    {
      "epoch": 2.213675213675214,
      "grad_norm": 0.322780579328537,
      "learning_rate": 8.70040553216892e-05,
      "loss": 0.4039,
      "step": 259
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.2556815445423126,
      "learning_rate": 8.632424635053997e-05,
      "loss": 0.2625,
      "step": 260
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.2778356373310089,
      "learning_rate": 8.564508083465079e-05,
      "loss": 0.2757,
      "step": 261
    },
    {
      "epoch": 2.2393162393162394,
      "grad_norm": 0.27824416756629944,
      "learning_rate": 8.496659072930813e-05,
      "loss": 0.2628,
      "step": 262
    },
    {
      "epoch": 2.247863247863248,
      "grad_norm": 0.4368916153907776,
      "learning_rate": 8.428880795801965e-05,
      "loss": 0.4293,
      "step": 263
    },
    {
      "epoch": 2.2564102564102564,
      "grad_norm": 0.3195033669471741,
      "learning_rate": 8.36117644110124e-05,
      "loss": 0.2558,
      "step": 264
    },
    {
      "epoch": 2.264957264957265,
      "grad_norm": 0.29170483350753784,
      "learning_rate": 8.293549194373243e-05,
      "loss": 0.262,
      "step": 265
    },
    {
      "epoch": 2.2735042735042734,
      "grad_norm": 0.532306432723999,
      "learning_rate": 8.226002237534572e-05,
      "loss": 0.5096,
      "step": 266
    },
    {
      "epoch": 2.282051282051282,
      "grad_norm": 0.41781437397003174,
      "learning_rate": 8.158538748724139e-05,
      "loss": 0.3313,
      "step": 267
    },
    {
      "epoch": 2.2905982905982905,
      "grad_norm": 0.2892751097679138,
      "learning_rate": 8.091161902153595e-05,
      "loss": 0.5872,
      "step": 268
    },
    {
      "epoch": 2.299145299145299,
      "grad_norm": 0.35854271054267883,
      "learning_rate": 8.023874867958027e-05,
      "loss": 0.396,
      "step": 269
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.3375587463378906,
      "learning_rate": 7.95668081204676e-05,
      "loss": 0.3,
      "step": 270
    },
    {
      "epoch": 2.316239316239316,
      "grad_norm": 0.32262086868286133,
      "learning_rate": 7.889582895954427e-05,
      "loss": 0.2471,
      "step": 271
    },
    {
      "epoch": 2.324786324786325,
      "grad_norm": 0.37641438841819763,
      "learning_rate": 7.822584276692191e-05,
      "loss": 0.3104,
      "step": 272
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.38596442341804504,
      "learning_rate": 7.755688106599241e-05,
      "loss": 0.3585,
      "step": 273
    },
    {
      "epoch": 2.341880341880342,
      "grad_norm": 0.4003375172615051,
      "learning_rate": 7.688897533194424e-05,
      "loss": 0.254,
      "step": 274
    },
    {
      "epoch": 2.3504273504273505,
      "grad_norm": 0.2852441966533661,
      "learning_rate": 7.622215699028196e-05,
      "loss": 0.2801,
      "step": 275
    },
    {
      "epoch": 2.358974358974359,
      "grad_norm": 0.4940102696418762,
      "learning_rate": 7.555645741534736e-05,
      "loss": 0.6457,
      "step": 276
    },
    {
      "epoch": 2.3675213675213675,
      "grad_norm": 0.3977501094341278,
      "learning_rate": 7.489190792884338e-05,
      "loss": 0.5146,
      "step": 277
    },
    {
      "epoch": 2.376068376068376,
      "grad_norm": 0.3095978796482086,
      "learning_rate": 7.422853979836034e-05,
      "loss": 0.283,
      "step": 278
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 0.3174421191215515,
      "learning_rate": 7.356638423590485e-05,
      "loss": 0.2963,
      "step": 279
    },
    {
      "epoch": 2.393162393162393,
      "grad_norm": 0.2932930588722229,
      "learning_rate": 7.290547239643117e-05,
      "loss": 0.3011,
      "step": 280
    },
    {
      "epoch": 2.4017094017094016,
      "grad_norm": 0.3848772346973419,
      "learning_rate": 7.224583537637544e-05,
      "loss": 0.7638,
      "step": 281
    },
    {
      "epoch": 2.41025641025641,
      "grad_norm": 0.3451789319515228,
      "learning_rate": 7.158750421219244e-05,
      "loss": 0.2564,
      "step": 282
    },
    {
      "epoch": 2.4188034188034186,
      "grad_norm": 0.29511570930480957,
      "learning_rate": 7.093050987889547e-05,
      "loss": 0.2592,
      "step": 283
    },
    {
      "epoch": 2.427350427350427,
      "grad_norm": 0.2932649254798889,
      "learning_rate": 7.027488328859876e-05,
      "loss": 0.3156,
      "step": 284
    },
    {
      "epoch": 2.435897435897436,
      "grad_norm": 0.33523324131965637,
      "learning_rate": 6.96206552890632e-05,
      "loss": 0.2827,
      "step": 285
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.48287665843963623,
      "learning_rate": 6.896785666224481e-05,
      "loss": 0.2812,
      "step": 286
    },
    {
      "epoch": 2.452991452991453,
      "grad_norm": 0.3235511779785156,
      "learning_rate": 6.831651812284652e-05,
      "loss": 0.315,
      "step": 287
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.3387332856655121,
      "learning_rate": 6.766667031687286e-05,
      "loss": 0.292,
      "step": 288
    },
    {
      "epoch": 2.47008547008547,
      "grad_norm": 0.31083184480667114,
      "learning_rate": 6.701834382018832e-05,
      "loss": 0.248,
      "step": 289
    },
    {
      "epoch": 2.4786324786324787,
      "grad_norm": 0.329478919506073,
      "learning_rate": 6.637156913707839e-05,
      "loss": 0.2848,
      "step": 290
    },
    {
      "epoch": 2.4871794871794872,
      "grad_norm": 0.5998380780220032,
      "learning_rate": 6.572637669881458e-05,
      "loss": 0.6285,
      "step": 291
    },
    {
      "epoch": 2.4957264957264957,
      "grad_norm": 0.35336780548095703,
      "learning_rate": 6.508279686222243e-05,
      "loss": 0.2744,
      "step": 292
    },
    {
      "epoch": 2.5042735042735043,
      "grad_norm": 0.2966953217983246,
      "learning_rate": 6.444085990825338e-05,
      "loss": 0.2704,
      "step": 293
    },
    {
      "epoch": 2.5128205128205128,
      "grad_norm": 0.47633370757102966,
      "learning_rate": 6.380059604055974e-05,
      "loss": 0.4362,
      "step": 294
    },
    {
      "epoch": 2.5213675213675213,
      "grad_norm": 0.3295687735080719,
      "learning_rate": 6.316203538407397e-05,
      "loss": 0.2769,
      "step": 295
    },
    {
      "epoch": 2.52991452991453,
      "grad_norm": 0.3237827718257904,
      "learning_rate": 6.252520798359092e-05,
      "loss": 0.2566,
      "step": 296
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 0.3498840630054474,
      "learning_rate": 6.18901438023543e-05,
      "loss": 0.3012,
      "step": 297
    },
    {
      "epoch": 2.547008547008547,
      "grad_norm": 0.30624261498451233,
      "learning_rate": 6.125687272064713e-05,
      "loss": 0.3081,
      "step": 298
    },
    {
      "epoch": 2.5555555555555554,
      "grad_norm": 0.3936445116996765,
      "learning_rate": 6.0625424534385425e-05,
      "loss": 0.3941,
      "step": 299
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 0.33280324935913086,
      "learning_rate": 5.9995828953716695e-05,
      "loss": 0.285,
      "step": 300
    },
    {
      "epoch": 2.5726495726495724,
      "grad_norm": 0.31433093547821045,
      "learning_rate": 5.936811560162169e-05,
      "loss": 0.2723,
      "step": 301
    },
    {
      "epoch": 2.5811965811965814,
      "grad_norm": 0.2975870966911316,
      "learning_rate": 5.87423140125209e-05,
      "loss": 0.2275,
      "step": 302
    },
    {
      "epoch": 2.58974358974359,
      "grad_norm": 0.3790895640850067,
      "learning_rate": 5.811845363088477e-05,
      "loss": 0.2922,
      "step": 303
    },
    {
      "epoch": 2.5982905982905984,
      "grad_norm": 0.3952803909778595,
      "learning_rate": 5.749656380984844e-05,
      "loss": 0.2825,
      "step": 304
    },
    {
      "epoch": 2.606837606837607,
      "grad_norm": 0.2977108061313629,
      "learning_rate": 5.687667380983037e-05,
      "loss": 0.2612,
      "step": 305
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.340876042842865,
      "learning_rate": 5.625881279715615e-05,
      "loss": 0.6881,
      "step": 306
    },
    {
      "epoch": 2.623931623931624,
      "grad_norm": 0.32907164096832275,
      "learning_rate": 5.5643009842685554e-05,
      "loss": 0.3054,
      "step": 307
    },
    {
      "epoch": 2.6324786324786325,
      "grad_norm": 0.34214216470718384,
      "learning_rate": 5.502929392044528e-05,
      "loss": 0.2245,
      "step": 308
    },
    {
      "epoch": 2.641025641025641,
      "grad_norm": 0.381902813911438,
      "learning_rate": 5.4417693906265365e-05,
      "loss": 0.3187,
      "step": 309
    },
    {
      "epoch": 2.6495726495726495,
      "grad_norm": 0.4639606177806854,
      "learning_rate": 5.380823857642069e-05,
      "loss": 0.4606,
      "step": 310
    },
    {
      "epoch": 2.658119658119658,
      "grad_norm": 0.328600138425827,
      "learning_rate": 5.3200956606277006e-05,
      "loss": 0.2735,
      "step": 311
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.4025443196296692,
      "learning_rate": 5.259587656894174e-05,
      "loss": 0.3401,
      "step": 312
    },
    {
      "epoch": 2.6752136752136755,
      "grad_norm": 0.6007752418518066,
      "learning_rate": 5.199302693391959e-05,
      "loss": 0.3937,
      "step": 313
    },
    {
      "epoch": 2.683760683760684,
      "grad_norm": 0.41876208782196045,
      "learning_rate": 5.139243606577302e-05,
      "loss": 0.2997,
      "step": 314
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.3358153998851776,
      "learning_rate": 5.0794132222787707e-05,
      "loss": 0.2867,
      "step": 315
    },
    {
      "epoch": 2.700854700854701,
      "grad_norm": 0.3381877839565277,
      "learning_rate": 5.019814355564292e-05,
      "loss": 0.3769,
      "step": 316
    },
    {
      "epoch": 2.7094017094017095,
      "grad_norm": 0.32228657603263855,
      "learning_rate": 4.960449810608705e-05,
      "loss": 0.2631,
      "step": 317
    },
    {
      "epoch": 2.717948717948718,
      "grad_norm": 0.348818302154541,
      "learning_rate": 4.90132238056182e-05,
      "loss": 0.8126,
      "step": 318
    },
    {
      "epoch": 2.7264957264957266,
      "grad_norm": 0.3677196502685547,
      "learning_rate": 4.8424348474170014e-05,
      "loss": 0.2595,
      "step": 319
    },
    {
      "epoch": 2.735042735042735,
      "grad_norm": 0.2946872413158417,
      "learning_rate": 4.783789981880267e-05,
      "loss": 0.2031,
      "step": 320
    },
    {
      "epoch": 2.7435897435897436,
      "grad_norm": 0.3554361164569855,
      "learning_rate": 4.725390543239929e-05,
      "loss": 0.4463,
      "step": 321
    },
    {
      "epoch": 2.752136752136752,
      "grad_norm": 0.353966623544693,
      "learning_rate": 4.667239279236768e-05,
      "loss": 0.315,
      "step": 322
    },
    {
      "epoch": 2.7606837606837606,
      "grad_norm": 0.4126017987728119,
      "learning_rate": 4.609338925934743e-05,
      "loss": 0.5124,
      "step": 323
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.3502495288848877,
      "learning_rate": 4.551692207592265e-05,
      "loss": 0.2424,
      "step": 324
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.4098051190376282,
      "learning_rate": 4.494301836534016e-05,
      "loss": 0.3305,
      "step": 325
    },
    {
      "epoch": 2.786324786324786,
      "grad_norm": 0.3290156424045563,
      "learning_rate": 4.4371705130233275e-05,
      "loss": 0.2424,
      "step": 326
    },
    {
      "epoch": 2.7948717948717947,
      "grad_norm": 0.3581879138946533,
      "learning_rate": 4.380300925135138e-05,
      "loss": 0.7653,
      "step": 327
    },
    {
      "epoch": 2.8034188034188032,
      "grad_norm": 0.4264296293258667,
      "learning_rate": 4.3236957486295115e-05,
      "loss": 0.6662,
      "step": 328
    },
    {
      "epoch": 2.8119658119658117,
      "grad_norm": 0.3510429859161377,
      "learning_rate": 4.267357646825746e-05,
      "loss": 0.2576,
      "step": 329
    },
    {
      "epoch": 2.8205128205128203,
      "grad_norm": 0.3552672266960144,
      "learning_rate": 4.211289270477047e-05,
      "loss": 0.2799,
      "step": 330
    },
    {
      "epoch": 2.8290598290598292,
      "grad_norm": 0.4459509551525116,
      "learning_rate": 4.1554932576458415e-05,
      "loss": 0.5763,
      "step": 331
    },
    {
      "epoch": 2.8376068376068377,
      "grad_norm": 0.34545478224754333,
      "learning_rate": 4.0999722335796075e-05,
      "loss": 0.2777,
      "step": 332
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 0.36245977878570557,
      "learning_rate": 4.044728810587406e-05,
      "loss": 0.2251,
      "step": 333
    },
    {
      "epoch": 2.8547008547008548,
      "grad_norm": 0.31824609637260437,
      "learning_rate": 3.989765587916914e-05,
      "loss": 0.3392,
      "step": 334
    },
    {
      "epoch": 2.8632478632478633,
      "grad_norm": 0.3003866970539093,
      "learning_rate": 3.935085151632185e-05,
      "loss": 0.2152,
      "step": 335
    },
    {
      "epoch": 2.871794871794872,
      "grad_norm": 0.3742835819721222,
      "learning_rate": 3.8806900744919205e-05,
      "loss": 0.3928,
      "step": 336
    },
    {
      "epoch": 2.8803418803418803,
      "grad_norm": 0.343273788690567,
      "learning_rate": 3.826582915828468e-05,
      "loss": 0.2669,
      "step": 337
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.282025545835495,
      "learning_rate": 3.7727662214273495e-05,
      "loss": 0.2225,
      "step": 338
    },
    {
      "epoch": 2.8974358974358974,
      "grad_norm": 0.4748214781284332,
      "learning_rate": 3.719242523407539e-05,
      "loss": 0.6038,
      "step": 339
    },
    {
      "epoch": 2.905982905982906,
      "grad_norm": 0.3875848352909088,
      "learning_rate": 3.666014340102268e-05,
      "loss": 0.5478,
      "step": 340
    },
    {
      "epoch": 2.9145299145299144,
      "grad_norm": 0.3508703112602234,
      "learning_rate": 3.613084175940578e-05,
      "loss": 0.6079,
      "step": 341
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.3366300165653229,
      "learning_rate": 3.5604545213294616e-05,
      "loss": 0.4433,
      "step": 342
    },
    {
      "epoch": 2.931623931623932,
      "grad_norm": 0.39028677344322205,
      "learning_rate": 3.508127852536698e-05,
      "loss": 0.3464,
      "step": 343
    },
    {
      "epoch": 2.9401709401709404,
      "grad_norm": 0.3091813027858734,
      "learning_rate": 3.456106631574336e-05,
      "loss": 0.2788,
      "step": 344
    },
    {
      "epoch": 2.948717948717949,
      "grad_norm": 0.3452043831348419,
      "learning_rate": 3.4043933060828605e-05,
      "loss": 0.6002,
      "step": 345
    },
    {
      "epoch": 2.9572649572649574,
      "grad_norm": 0.4122669994831085,
      "learning_rate": 3.352990309216022e-05,
      "loss": 0.2817,
      "step": 346
    },
    {
      "epoch": 2.965811965811966,
      "grad_norm": 0.3466607332229614,
      "learning_rate": 3.3019000595263574e-05,
      "loss": 0.2374,
      "step": 347
    },
    {
      "epoch": 2.9743589743589745,
      "grad_norm": 0.3909549415111542,
      "learning_rate": 3.251124960851408e-05,
      "loss": 0.2916,
      "step": 348
    },
    {
      "epoch": 2.982905982905983,
      "grad_norm": 0.455856055021286,
      "learning_rate": 3.200667402200586e-05,
      "loss": 0.2869,
      "step": 349
    },
    {
      "epoch": 2.9914529914529915,
      "grad_norm": 0.32305237650871277,
      "learning_rate": 3.1505297576428075e-05,
      "loss": 0.2783,
      "step": 350
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.34499669075012207,
      "learning_rate": 3.100714386194757e-05,
      "loss": 0.2562,
      "step": 351
    },
    {
      "epoch": 3.0085470085470085,
      "grad_norm": 0.2704463601112366,
      "learning_rate": 3.0512236317099175e-05,
      "loss": 0.1887,
      "step": 352
    },
    {
      "epoch": 3.017094017094017,
      "grad_norm": 0.30573076009750366,
      "learning_rate": 3.0020598227682795e-05,
      "loss": 0.1851,
      "step": 353
    },
    {
      "epoch": 3.0256410256410255,
      "grad_norm": 0.2949523329734802,
      "learning_rate": 2.953225272566782e-05,
      "loss": 0.1704,
      "step": 354
    },
    {
      "epoch": 3.034188034188034,
      "grad_norm": 0.30406391620635986,
      "learning_rate": 2.904722278810471e-05,
      "loss": 0.1785,
      "step": 355
    },
    {
      "epoch": 3.0427350427350426,
      "grad_norm": 0.30164244771003723,
      "learning_rate": 2.8565531236043997e-05,
      "loss": 0.2137,
      "step": 356
    },
    {
      "epoch": 3.051282051282051,
      "grad_norm": 0.31406161189079285,
      "learning_rate": 2.8087200733462425e-05,
      "loss": 0.3024,
      "step": 357
    },
    {
      "epoch": 3.0598290598290596,
      "grad_norm": 0.2808714807033539,
      "learning_rate": 2.7612253786196664e-05,
      "loss": 0.1289,
      "step": 358
    },
    {
      "epoch": 3.0683760683760686,
      "grad_norm": 0.3476700186729431,
      "learning_rate": 2.7140712740884376e-05,
      "loss": 0.1839,
      "step": 359
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.3637332022190094,
      "learning_rate": 2.667259978391281e-05,
      "loss": 0.2042,
      "step": 360
    },
    {
      "epoch": 3.0854700854700856,
      "grad_norm": 0.45450517535209656,
      "learning_rate": 2.6207936940374767e-05,
      "loss": 0.2548,
      "step": 361
    },
    {
      "epoch": 3.094017094017094,
      "grad_norm": 0.2504849135875702,
      "learning_rate": 2.5746746073032625e-05,
      "loss": 0.1485,
      "step": 362
    },
    {
      "epoch": 3.1025641025641026,
      "grad_norm": 0.32385873794555664,
      "learning_rate": 2.5289048881289256e-05,
      "loss": 0.2157,
      "step": 363
    },
    {
      "epoch": 3.111111111111111,
      "grad_norm": 0.33799242973327637,
      "learning_rate": 2.4834866900167475e-05,
      "loss": 0.1555,
      "step": 364
    },
    {
      "epoch": 3.1196581196581197,
      "grad_norm": 0.31787970662117004,
      "learning_rate": 2.4384221499296466e-05,
      "loss": 0.1281,
      "step": 365
    },
    {
      "epoch": 3.128205128205128,
      "grad_norm": 0.3274690806865692,
      "learning_rate": 2.393713388190648e-05,
      "loss": 0.3944,
      "step": 366
    },
    {
      "epoch": 3.1367521367521367,
      "grad_norm": 0.3551839292049408,
      "learning_rate": 2.3493625083831217e-05,
      "loss": 0.1854,
      "step": 367
    },
    {
      "epoch": 3.1452991452991452,
      "grad_norm": 0.6003894209861755,
      "learning_rate": 2.3053715972518e-05,
      "loss": 0.4562,
      "step": 368
    },
    {
      "epoch": 3.1538461538461537,
      "grad_norm": 0.4693816006183624,
      "learning_rate": 2.2617427246045973e-05,
      "loss": 0.3313,
      "step": 369
    },
    {
      "epoch": 3.1623931623931623,
      "grad_norm": 0.40278398990631104,
      "learning_rate": 2.218477943215229e-05,
      "loss": 0.2476,
      "step": 370
    },
    {
      "epoch": 3.1709401709401708,
      "grad_norm": 0.4294925034046173,
      "learning_rate": 2.1755792887266234e-05,
      "loss": 0.2763,
      "step": 371
    },
    {
      "epoch": 3.1794871794871793,
      "grad_norm": 0.39484453201293945,
      "learning_rate": 2.133048779555129e-05,
      "loss": 0.2439,
      "step": 372
    },
    {
      "epoch": 3.1880341880341883,
      "grad_norm": 0.3761466145515442,
      "learning_rate": 2.0908884167955824e-05,
      "loss": 0.1951,
      "step": 373
    },
    {
      "epoch": 3.1965811965811968,
      "grad_norm": 0.39632537961006165,
      "learning_rate": 2.0491001841271074e-05,
      "loss": 0.1416,
      "step": 374
    },
    {
      "epoch": 3.2051282051282053,
      "grad_norm": 0.3734767436981201,
      "learning_rate": 2.0076860477198313e-05,
      "loss": 0.2049,
      "step": 375
    },
    {
      "epoch": 3.213675213675214,
      "grad_norm": 0.41963204741477966,
      "learning_rate": 1.9666479561423244e-05,
      "loss": 0.1297,
      "step": 376
    },
    {
      "epoch": 3.2222222222222223,
      "grad_norm": 0.40617361664772034,
      "learning_rate": 1.9259878402699705e-05,
      "loss": 0.1283,
      "step": 377
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 0.3304429352283478,
      "learning_rate": 1.8857076131940642e-05,
      "loss": 0.1752,
      "step": 378
    },
    {
      "epoch": 3.2393162393162394,
      "grad_norm": 0.37188851833343506,
      "learning_rate": 1.8458091701318504e-05,
      "loss": 0.1434,
      "step": 379
    },
    {
      "epoch": 3.247863247863248,
      "grad_norm": 0.3777998685836792,
      "learning_rate": 1.806294388337305e-05,
      "loss": 0.1718,
      "step": 380
    },
    {
      "epoch": 3.2564102564102564,
      "grad_norm": 0.3467237949371338,
      "learning_rate": 1.7671651270128532e-05,
      "loss": 0.1437,
      "step": 381
    },
    {
      "epoch": 3.264957264957265,
      "grad_norm": 0.42175063490867615,
      "learning_rate": 1.7284232272218504e-05,
      "loss": 0.3937,
      "step": 382
    },
    {
      "epoch": 3.2735042735042734,
      "grad_norm": 0.5283070802688599,
      "learning_rate": 1.69007051180199e-05,
      "loss": 0.1712,
      "step": 383
    },
    {
      "epoch": 3.282051282051282,
      "grad_norm": 0.3623201251029968,
      "learning_rate": 1.652108785279526e-05,
      "loss": 0.1157,
      "step": 384
    },
    {
      "epoch": 3.2905982905982905,
      "grad_norm": 0.3367072641849518,
      "learning_rate": 1.6145398337843652e-05,
      "loss": 0.1296,
      "step": 385
    },
    {
      "epoch": 3.299145299145299,
      "grad_norm": 0.5496230125427246,
      "learning_rate": 1.577365424966034e-05,
      "loss": 0.2481,
      "step": 386
    },
    {
      "epoch": 3.3076923076923075,
      "grad_norm": 0.39186400175094604,
      "learning_rate": 1.540587307910508e-05,
      "loss": 0.4597,
      "step": 387
    },
    {
      "epoch": 3.316239316239316,
      "grad_norm": 0.3299206793308258,
      "learning_rate": 1.504207213057912e-05,
      "loss": 0.7461,
      "step": 388
    },
    {
      "epoch": 3.324786324786325,
      "grad_norm": 0.31231385469436646,
      "learning_rate": 1.4682268521211073e-05,
      "loss": 0.1392,
      "step": 389
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.26779109239578247,
      "learning_rate": 1.43264791800515e-05,
      "loss": 0.0795,
      "step": 390
    },
    {
      "epoch": 3.341880341880342,
      "grad_norm": 0.32874441146850586,
      "learning_rate": 1.3974720847276412e-05,
      "loss": 0.1651,
      "step": 391
    },
    {
      "epoch": 3.3504273504273505,
      "grad_norm": 0.3623116910457611,
      "learning_rate": 1.3627010073399604e-05,
      "loss": 0.1474,
      "step": 392
    },
    {
      "epoch": 3.358974358974359,
      "grad_norm": 0.46444785594940186,
      "learning_rate": 1.328336321849396e-05,
      "loss": 0.2324,
      "step": 393
    },
    {
      "epoch": 3.3675213675213675,
      "grad_norm": 0.41633984446525574,
      "learning_rate": 1.2943796451421686e-05,
      "loss": 0.1545,
      "step": 394
    },
    {
      "epoch": 3.376068376068376,
      "grad_norm": 0.3474414646625519,
      "learning_rate": 1.2608325749073591e-05,
      "loss": 0.142,
      "step": 395
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 0.3417489230632782,
      "learning_rate": 1.227696689561727e-05,
      "loss": 0.1157,
      "step": 396
    },
    {
      "epoch": 3.393162393162393,
      "grad_norm": 0.33023884892463684,
      "learning_rate": 1.1949735481754565e-05,
      "loss": 0.1514,
      "step": 397
    },
    {
      "epoch": 3.4017094017094016,
      "grad_norm": 0.5069023370742798,
      "learning_rate": 1.1626646903987904e-05,
      "loss": 0.1721,
      "step": 398
    },
    {
      "epoch": 3.41025641025641,
      "grad_norm": 0.4400981664657593,
      "learning_rate": 1.130771636389596e-05,
      "loss": 0.127,
      "step": 399
    },
    {
      "epoch": 3.4188034188034186,
      "grad_norm": 0.34662753343582153,
      "learning_rate": 1.0992958867418357e-05,
      "loss": 0.1399,
      "step": 400
    },
    {
      "epoch": 3.427350427350427,
      "grad_norm": 0.29363980889320374,
      "learning_rate": 1.0682389224149647e-05,
      "loss": 0.1446,
      "step": 401
    },
    {
      "epoch": 3.435897435897436,
      "grad_norm": 0.33367815613746643,
      "learning_rate": 1.037602204664252e-05,
      "loss": 0.1505,
      "step": 402
    },
    {
      "epoch": 3.4444444444444446,
      "grad_norm": 0.26712965965270996,
      "learning_rate": 1.0073871749720221e-05,
      "loss": 0.1197,
      "step": 403
    },
    {
      "epoch": 3.452991452991453,
      "grad_norm": 0.33563879132270813,
      "learning_rate": 9.775952549798406e-06,
      "loss": 0.4108,
      "step": 404
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 0.37614428997039795,
      "learning_rate": 9.482278464216121e-06,
      "loss": 0.3326,
      "step": 405
    },
    {
      "epoch": 3.47008547008547,
      "grad_norm": 0.4337684214115143,
      "learning_rate": 9.192863310576472e-06,
      "loss": 0.4751,
      "step": 406
    },
    {
      "epoch": 3.4786324786324787,
      "grad_norm": 0.3003832697868347,
      "learning_rate": 8.907720706096224e-06,
      "loss": 0.1034,
      "step": 407
    },
    {
      "epoch": 3.4871794871794872,
      "grad_norm": 0.33007341623306274,
      "learning_rate": 8.626864066965402e-06,
      "loss": 0.157,
      "step": 408
    },
    {
      "epoch": 3.4957264957264957,
      "grad_norm": 0.44596633315086365,
      "learning_rate": 8.350306607715774e-06,
      "loss": 0.1683,
      "step": 409
    },
    {
      "epoch": 3.5042735042735043,
      "grad_norm": 0.36065036058425903,
      "learning_rate": 8.07806134059933e-06,
      "loss": 0.2873,
      "step": 410
    },
    {
      "epoch": 3.5128205128205128,
      "grad_norm": 0.3523757755756378,
      "learning_rate": 7.810141074975818e-06,
      "loss": 0.1142,
      "step": 411
    },
    {
      "epoch": 3.5213675213675213,
      "grad_norm": 0.5489363074302673,
      "learning_rate": 7.546558416710292e-06,
      "loss": 0.2459,
      "step": 412
    },
    {
      "epoch": 3.52991452991453,
      "grad_norm": 0.45634669065475464,
      "learning_rate": 7.287325767579756e-06,
      "loss": 0.1954,
      "step": 413
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 0.31889015436172485,
      "learning_rate": 7.032455324689902e-06,
      "loss": 0.1686,
      "step": 414
    },
    {
      "epoch": 3.547008547008547,
      "grad_norm": 0.46840614080429077,
      "learning_rate": 6.781959079900957e-06,
      "loss": 0.3054,
      "step": 415
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.39593732357025146,
      "learning_rate": 6.535848819263679e-06,
      "loss": 0.2042,
      "step": 416
    },
    {
      "epoch": 3.564102564102564,
      "grad_norm": 0.38878628611564636,
      "learning_rate": 6.2941361224647e-06,
      "loss": 0.1649,
      "step": 417
    },
    {
      "epoch": 3.5726495726495724,
      "grad_norm": 0.35097816586494446,
      "learning_rate": 6.056832362281728e-06,
      "loss": 0.156,
      "step": 418
    },
    {
      "epoch": 3.5811965811965814,
      "grad_norm": 0.3477489948272705,
      "learning_rate": 5.823948704048443e-06,
      "loss": 0.1357,
      "step": 419
    },
    {
      "epoch": 3.58974358974359,
      "grad_norm": 0.3644021153450012,
      "learning_rate": 5.5954961051291384e-06,
      "loss": 0.1769,
      "step": 420
    },
    {
      "epoch": 3.5982905982905984,
      "grad_norm": 0.41597941517829895,
      "learning_rate": 5.371485314403202e-06,
      "loss": 0.2497,
      "step": 421
    },
    {
      "epoch": 3.606837606837607,
      "grad_norm": 0.4599474370479584,
      "learning_rate": 5.151926871759349e-06,
      "loss": 0.1468,
      "step": 422
    },
    {
      "epoch": 3.6153846153846154,
      "grad_norm": 0.514677882194519,
      "learning_rate": 4.936831107599749e-06,
      "loss": 0.3793,
      "step": 423
    },
    {
      "epoch": 3.623931623931624,
      "grad_norm": 0.40429508686065674,
      "learning_rate": 4.7262081423538716e-06,
      "loss": 0.1722,
      "step": 424
    },
    {
      "epoch": 3.6324786324786325,
      "grad_norm": 0.3798697590827942,
      "learning_rate": 4.5200678860024885e-06,
      "loss": 0.1304,
      "step": 425
    },
    {
      "epoch": 3.641025641025641,
      "grad_norm": 0.3338325023651123,
      "learning_rate": 4.3184200376111815e-06,
      "loss": 0.1439,
      "step": 426
    },
    {
      "epoch": 3.6495726495726495,
      "grad_norm": 0.35740965604782104,
      "learning_rate": 4.121274084874194e-06,
      "loss": 0.1435,
      "step": 427
    },
    {
      "epoch": 3.658119658119658,
      "grad_norm": 0.3547815978527069,
      "learning_rate": 3.928639303667891e-06,
      "loss": 0.1444,
      "step": 428
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 0.37178459763526917,
      "learning_rate": 3.7405247576144054e-06,
      "loss": 0.1803,
      "step": 429
    },
    {
      "epoch": 3.6752136752136755,
      "grad_norm": 0.3906807601451874,
      "learning_rate": 3.556939297655115e-06,
      "loss": 0.1465,
      "step": 430
    },
    {
      "epoch": 3.683760683760684,
      "grad_norm": 0.3673214912414551,
      "learning_rate": 3.3778915616342943e-06,
      "loss": 0.147,
      "step": 431
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.3543328046798706,
      "learning_rate": 3.203389973892579e-06,
      "loss": 0.1432,
      "step": 432
    },
    {
      "epoch": 3.700854700854701,
      "grad_norm": 0.3586738407611847,
      "learning_rate": 3.0334427448706847e-06,
      "loss": 0.127,
      "step": 433
    },
    {
      "epoch": 3.7094017094017095,
      "grad_norm": 0.33187445998191833,
      "learning_rate": 2.868057870723073e-06,
      "loss": 0.1636,
      "step": 434
    },
    {
      "epoch": 3.717948717948718,
      "grad_norm": 0.3415738642215729,
      "learning_rate": 2.707243132941717e-06,
      "loss": 0.1261,
      "step": 435
    },
    {
      "epoch": 3.7264957264957266,
      "grad_norm": 0.49677029252052307,
      "learning_rate": 2.5510060979899607e-06,
      "loss": 0.414,
      "step": 436
    },
    {
      "epoch": 3.735042735042735,
      "grad_norm": 0.38063541054725647,
      "learning_rate": 2.3993541169465837e-06,
      "loss": 0.126,
      "step": 437
    },
    {
      "epoch": 3.7435897435897436,
      "grad_norm": 0.3602873384952545,
      "learning_rate": 2.2522943251597873e-06,
      "loss": 0.1859,
      "step": 438
    },
    {
      "epoch": 3.752136752136752,
      "grad_norm": 0.47542595863342285,
      "learning_rate": 2.1098336419116625e-06,
      "loss": 0.1512,
      "step": 439
    },
    {
      "epoch": 3.7606837606837606,
      "grad_norm": 0.49939459562301636,
      "learning_rate": 1.971978770092431e-06,
      "loss": 0.2858,
      "step": 440
    },
    {
      "epoch": 3.769230769230769,
      "grad_norm": 0.2789536714553833,
      "learning_rate": 1.838736195885238e-06,
      "loss": 0.0912,
      "step": 441
    },
    {
      "epoch": 3.7777777777777777,
      "grad_norm": 0.3888574540615082,
      "learning_rate": 1.710112188460844e-06,
      "loss": 0.1802,
      "step": 442
    },
    {
      "epoch": 3.786324786324786,
      "grad_norm": 0.4002698063850403,
      "learning_rate": 1.5861127996827597e-06,
      "loss": 0.1511,
      "step": 443
    },
    {
      "epoch": 3.7948717948717947,
      "grad_norm": 0.8915614485740662,
      "learning_rate": 1.4667438638224062e-06,
      "loss": 0.2002,
      "step": 444
    },
    {
      "epoch": 3.8034188034188032,
      "grad_norm": 0.35627490282058716,
      "learning_rate": 1.3520109972846917e-06,
      "loss": 0.1631,
      "step": 445
    },
    {
      "epoch": 3.8119658119658117,
      "grad_norm": 0.4355277121067047,
      "learning_rate": 1.2419195983436881e-06,
      "loss": 0.6266,
      "step": 446
    },
    {
      "epoch": 3.8205128205128203,
      "grad_norm": 0.4429440200328827,
      "learning_rate": 1.1364748468886687e-06,
      "loss": 0.4393,
      "step": 447
    },
    {
      "epoch": 3.8290598290598292,
      "grad_norm": 0.3531508147716522,
      "learning_rate": 1.0356817041804246e-06,
      "loss": 0.1252,
      "step": 448
    },
    {
      "epoch": 3.8376068376068377,
      "grad_norm": 0.4377833306789398,
      "learning_rate": 9.395449126177291e-07,
      "loss": 0.1469,
      "step": 449
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.38173285126686096,
      "learning_rate": 8.480689955143395e-07,
      "loss": 0.1841,
      "step": 450
    },
    {
      "epoch": 3.8547008547008548,
      "grad_norm": 0.3975220322608948,
      "learning_rate": 7.612582568860549e-07,
      "loss": 0.2123,
      "step": 451
    },
    {
      "epoch": 3.8632478632478633,
      "grad_norm": 0.5331549644470215,
      "learning_rate": 6.791167812483012e-07,
      "loss": 0.2345,
      "step": 452
    },
    {
      "epoch": 3.871794871794872,
      "grad_norm": 0.3654056489467621,
      "learning_rate": 6.016484334238515e-07,
      "loss": 0.156,
      "step": 453
    },
    {
      "epoch": 3.8803418803418803,
      "grad_norm": 0.33425813913345337,
      "learning_rate": 5.288568583610931e-07,
      "loss": 0.1423,
      "step": 454
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 0.3364427089691162,
      "learning_rate": 4.607454809624434e-07,
      "loss": 0.1565,
      "step": 455
    },
    {
      "epoch": 3.8974358974358974,
      "grad_norm": 0.31947681307792664,
      "learning_rate": 3.9731750592325587e-07,
      "loss": 0.1518,
      "step": 456
    },
    {
      "epoch": 3.905982905982906,
      "grad_norm": 0.6322484016418457,
      "learning_rate": 3.385759175809966e-07,
      "loss": 0.2136,
      "step": 457
    },
    {
      "epoch": 3.9145299145299144,
      "grad_norm": 0.3786238729953766,
      "learning_rate": 2.845234797748897e-07,
      "loss": 0.1494,
      "step": 458
    },
    {
      "epoch": 3.9230769230769234,
      "grad_norm": 0.3211478292942047,
      "learning_rate": 2.3516273571577708e-07,
      "loss": 0.1668,
      "step": 459
    },
    {
      "epoch": 3.931623931623932,
      "grad_norm": 0.4070224165916443,
      "learning_rate": 1.9049600786658073e-07,
      "loss": 0.3244,
      "step": 460
    },
    {
      "epoch": 3.9401709401709404,
      "grad_norm": 0.397226482629776,
      "learning_rate": 1.505253978329235e-07,
      "loss": 0.1626,
      "step": 461
    },
    {
      "epoch": 3.948717948717949,
      "grad_norm": 0.41211414337158203,
      "learning_rate": 1.1525278626431934e-07,
      "loss": 0.3139,
      "step": 462
    },
    {
      "epoch": 3.9572649572649574,
      "grad_norm": 0.342115193605423,
      "learning_rate": 8.467983276563284e-08,
      "loss": 0.1348,
      "step": 463
    },
    {
      "epoch": 3.965811965811966,
      "grad_norm": 0.3899388611316681,
      "learning_rate": 5.880797581904185e-08,
      "loss": 0.2597,
      "step": 464
    },
    {
      "epoch": 3.9743589743589745,
      "grad_norm": 0.44626280665397644,
      "learning_rate": 3.763843271631373e-08,
      "loss": 0.2058,
      "step": 465
    },
    {
      "epoch": 3.982905982905983,
      "grad_norm": 0.4797934293746948,
      "learning_rate": 2.1172199501573455e-08,
      "loss": 0.2167,
      "step": 466
    },
    {
      "epoch": 3.9914529914529915,
      "grad_norm": 0.42446234822273254,
      "learning_rate": 9.410050924374415e-09,
      "loss": 0.1914,
      "step": 467
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.4239805340766907,
      "learning_rate": 2.3525404033275523e-09,
      "loss": 0.1631,
      "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": 3.2426028449346355e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}