{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9994900560938297,
  "eval_steps": 245,
  "global_step": 490,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002039775624681285,
      "grad_norm": 0.08994754403829575,
      "learning_rate": 2e-05,
      "loss": 2.6733,
      "step": 1
    },
    {
      "epoch": 0.002039775624681285,
      "eval_loss": 2.6805498600006104,
      "eval_runtime": 48.2372,
      "eval_samples_per_second": 17.124,
      "eval_steps_per_second": 2.156,
      "step": 1
    },
    {
      "epoch": 0.00407955124936257,
      "grad_norm": 0.09641231596469879,
      "learning_rate": 4e-05,
      "loss": 2.7875,
      "step": 2
    },
    {
      "epoch": 0.006119326874043855,
      "grad_norm": 0.10044872015714645,
      "learning_rate": 6e-05,
      "loss": 2.6516,
      "step": 3
    },
    {
      "epoch": 0.00815910249872514,
      "grad_norm": 0.08677750825881958,
      "learning_rate": 8e-05,
      "loss": 2.4109,
      "step": 4
    },
    {
      "epoch": 0.010198878123406425,
      "grad_norm": 0.10869669914245605,
      "learning_rate": 0.0001,
      "loss": 2.6336,
      "step": 5
    },
    {
      "epoch": 0.01223865374808771,
      "grad_norm": 0.1180991679430008,
      "learning_rate": 0.00012,
      "loss": 2.6001,
      "step": 6
    },
    {
      "epoch": 0.014278429372768995,
      "grad_norm": 0.1641693264245987,
      "learning_rate": 0.00014,
      "loss": 2.9137,
      "step": 7
    },
    {
      "epoch": 0.01631820499745028,
      "grad_norm": 0.17794281244277954,
      "learning_rate": 0.00016,
      "loss": 2.835,
      "step": 8
    },
    {
      "epoch": 0.018357980622131564,
      "grad_norm": 0.16260501742362976,
      "learning_rate": 0.00018,
      "loss": 2.6015,
      "step": 9
    },
    {
      "epoch": 0.02039775624681285,
      "grad_norm": 0.13795699179172516,
      "learning_rate": 0.0002,
      "loss": 2.2552,
      "step": 10
    },
    {
      "epoch": 0.022437531871494134,
      "grad_norm": 0.15532873570919037,
      "learning_rate": 0.00019999947552365961,
      "loss": 2.4393,
      "step": 11
    },
    {
      "epoch": 0.02447730749617542,
      "grad_norm": 0.159002423286438,
      "learning_rate": 0.00019999790210013988,
      "loss": 2.7684,
      "step": 12
    },
    {
      "epoch": 0.026517083120856707,
      "grad_norm": 0.17115084826946259,
      "learning_rate": 0.0001999952797459453,
      "loss": 2.2409,
      "step": 13
    },
    {
      "epoch": 0.02855685874553799,
      "grad_norm": 0.26108402013778687,
      "learning_rate": 0.0001999916084885832,
      "loss": 2.6388,
      "step": 14
    },
    {
      "epoch": 0.030596634370219276,
      "grad_norm": 0.29758986830711365,
      "learning_rate": 0.00019998688836656323,
      "loss": 2.4358,
      "step": 15
    },
    {
      "epoch": 0.03263640999490056,
      "grad_norm": 0.2338196337223053,
      "learning_rate": 0.0001999811194293973,
      "loss": 2.3898,
      "step": 16
    },
    {
      "epoch": 0.03467618561958185,
      "grad_norm": 0.2143183797597885,
      "learning_rate": 0.00019997430173759875,
      "loss": 2.6874,
      "step": 17
    },
    {
      "epoch": 0.03671596124426313,
      "grad_norm": 0.19598309695720673,
      "learning_rate": 0.00019996643536268204,
      "loss": 2.409,
      "step": 18
    },
    {
      "epoch": 0.038755736868944415,
      "grad_norm": 0.16046980023384094,
      "learning_rate": 0.00019995752038716168,
      "loss": 2.2378,
      "step": 19
    },
    {
      "epoch": 0.0407955124936257,
      "grad_norm": 0.15274696052074432,
      "learning_rate": 0.00019994755690455152,
      "loss": 2.3413,
      "step": 20
    },
    {
      "epoch": 0.04283528811830699,
      "grad_norm": 0.24761317670345306,
      "learning_rate": 0.0001999365450193638,
      "loss": 2.3382,
      "step": 21
    },
    {
      "epoch": 0.04487506374298827,
      "grad_norm": 0.2602517604827881,
      "learning_rate": 0.00019992448484710797,
      "loss": 2.3355,
      "step": 22
    },
    {
      "epoch": 0.046914839367669554,
      "grad_norm": 0.25506100058555603,
      "learning_rate": 0.00019991137651428957,
      "loss": 2.4828,
      "step": 23
    },
    {
      "epoch": 0.04895461499235084,
      "grad_norm": 0.19493895769119263,
      "learning_rate": 0.0001998972201584088,
      "loss": 2.3154,
      "step": 24
    },
    {
      "epoch": 0.05099439061703213,
      "grad_norm": 0.16005843877792358,
      "learning_rate": 0.0001998820159279591,
      "loss": 2.1472,
      "step": 25
    },
    {
      "epoch": 0.053034166241713414,
      "grad_norm": 0.17840257287025452,
      "learning_rate": 0.00019986576398242566,
      "loss": 2.1624,
      "step": 26
    },
    {
      "epoch": 0.05507394186639469,
      "grad_norm": 0.15280942618846893,
      "learning_rate": 0.0001998484644922837,
      "loss": 2.0526,
      "step": 27
    },
    {
      "epoch": 0.05711371749107598,
      "grad_norm": 0.16933050751686096,
      "learning_rate": 0.00019983011763899673,
      "loss": 2.2176,
      "step": 28
    },
    {
      "epoch": 0.059153493115757266,
      "grad_norm": 0.21265609562397003,
      "learning_rate": 0.0001998107236150145,
      "loss": 2.2559,
      "step": 29
    },
    {
      "epoch": 0.06119326874043855,
      "grad_norm": 0.19340573251247406,
      "learning_rate": 0.00019979028262377118,
      "loss": 2.3202,
      "step": 30
    },
    {
      "epoch": 0.06323304436511984,
      "grad_norm": 0.16693681478500366,
      "learning_rate": 0.0001997687948796831,
      "loss": 2.0623,
      "step": 31
    },
    {
      "epoch": 0.06527281998980113,
      "grad_norm": 0.18830184638500214,
      "learning_rate": 0.00019974626060814647,
      "loss": 2.1929,
      "step": 32
    },
    {
      "epoch": 0.06731259561448241,
      "grad_norm": 0.16206099092960358,
      "learning_rate": 0.0001997226800455352,
      "loss": 2.3048,
      "step": 33
    },
    {
      "epoch": 0.0693523712391637,
      "grad_norm": 0.21650008857250214,
      "learning_rate": 0.00019969805343919821,
      "loss": 2.2928,
      "step": 34
    },
    {
      "epoch": 0.07139214686384497,
      "grad_norm": 0.19560708105564117,
      "learning_rate": 0.00019967238104745696,
      "loss": 2.4389,
      "step": 35
    },
    {
      "epoch": 0.07343192248852626,
      "grad_norm": 0.17428375780582428,
      "learning_rate": 0.00019964566313960264,
      "loss": 2.1017,
      "step": 36
    },
    {
      "epoch": 0.07547169811320754,
      "grad_norm": 0.14846819639205933,
      "learning_rate": 0.00019961789999589356,
      "loss": 2.0431,
      "step": 37
    },
    {
      "epoch": 0.07751147373788883,
      "grad_norm": 0.14796215295791626,
      "learning_rate": 0.00019958909190755187,
      "loss": 2.0363,
      "step": 38
    },
    {
      "epoch": 0.07955124936257012,
      "grad_norm": 0.17396488785743713,
      "learning_rate": 0.0001995592391767608,
      "loss": 2.0835,
      "step": 39
    },
    {
      "epoch": 0.0815910249872514,
      "grad_norm": 0.1914213001728058,
      "learning_rate": 0.0001995283421166614,
      "loss": 2.0242,
      "step": 40
    },
    {
      "epoch": 0.08363080061193269,
      "grad_norm": 0.16040053963661194,
      "learning_rate": 0.00019949640105134918,
      "loss": 2.2171,
      "step": 41
    },
    {
      "epoch": 0.08567057623661398,
      "grad_norm": 0.16291815042495728,
      "learning_rate": 0.00019946341631587087,
      "loss": 2.2144,
      "step": 42
    },
    {
      "epoch": 0.08771035186129526,
      "grad_norm": 0.16890890896320343,
      "learning_rate": 0.00019942938825622065,
      "loss": 2.0775,
      "step": 43
    },
    {
      "epoch": 0.08975012748597654,
      "grad_norm": 0.18898645043373108,
      "learning_rate": 0.0001993943172293368,
      "loss": 2.262,
      "step": 44
    },
    {
      "epoch": 0.09178990311065782,
      "grad_norm": 0.19105440378189087,
      "learning_rate": 0.00019935820360309777,
      "loss": 2.0232,
      "step": 45
    },
    {
      "epoch": 0.09382967873533911,
      "grad_norm": 0.17944768071174622,
      "learning_rate": 0.00019932104775631846,
      "loss": 2.2564,
      "step": 46
    },
    {
      "epoch": 0.0958694543600204,
      "grad_norm": 0.1691497266292572,
      "learning_rate": 0.0001992828500787461,
      "loss": 2.0249,
      "step": 47
    },
    {
      "epoch": 0.09790922998470168,
      "grad_norm": 0.18704521656036377,
      "learning_rate": 0.00019924361097105623,
      "loss": 2.2058,
      "step": 48
    },
    {
      "epoch": 0.09994900560938297,
      "grad_norm": 0.24133948981761932,
      "learning_rate": 0.00019920333084484857,
      "loss": 2.2835,
      "step": 49
    },
    {
      "epoch": 0.10198878123406425,
      "grad_norm": 0.210649773478508,
      "learning_rate": 0.00019916201012264254,
      "loss": 2.1052,
      "step": 50
    },
    {
      "epoch": 0.10402855685874554,
      "grad_norm": 0.19624340534210205,
      "learning_rate": 0.00019911964923787295,
      "loss": 2.2474,
      "step": 51
    },
    {
      "epoch": 0.10606833248342683,
      "grad_norm": 0.2529032230377197,
      "learning_rate": 0.0001990762486348855,
      "loss": 1.9782,
      "step": 52
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.2078029066324234,
      "learning_rate": 0.00019903180876893194,
      "loss": 2.3627,
      "step": 53
    },
    {
      "epoch": 0.11014788373278939,
      "grad_norm": 0.23153568804264069,
      "learning_rate": 0.00019898633010616542,
      "loss": 1.9749,
      "step": 54
    },
    {
      "epoch": 0.11218765935747067,
      "grad_norm": 0.20798815786838531,
      "learning_rate": 0.00019893981312363562,
      "loss": 2.111,
      "step": 55
    },
    {
      "epoch": 0.11422743498215196,
      "grad_norm": 0.20742167532444,
      "learning_rate": 0.00019889225830928365,
      "loss": 2.113,
      "step": 56
    },
    {
      "epoch": 0.11626721060683325,
      "grad_norm": 0.21235893666744232,
      "learning_rate": 0.00019884366616193706,
      "loss": 2.0307,
      "step": 57
    },
    {
      "epoch": 0.11830698623151453,
      "grad_norm": 0.19754983484745026,
      "learning_rate": 0.0001987940371913044,
      "loss": 1.9883,
      "step": 58
    },
    {
      "epoch": 0.12034676185619582,
      "grad_norm": 0.20224173367023468,
      "learning_rate": 0.0001987433719179702,
      "loss": 2.0299,
      "step": 59
    },
    {
      "epoch": 0.1223865374808771,
      "grad_norm": 0.20431111752986908,
      "learning_rate": 0.00019869167087338907,
      "loss": 2.0,
      "step": 60
    },
    {
      "epoch": 0.12442631310555839,
      "grad_norm": 0.21355204284191132,
      "learning_rate": 0.00019863893459988062,
      "loss": 1.9365,
      "step": 61
    },
    {
      "epoch": 0.12646608873023968,
      "grad_norm": 0.2394651174545288,
      "learning_rate": 0.00019858516365062334,
      "loss": 1.9264,
      "step": 62
    },
    {
      "epoch": 0.12850586435492095,
      "grad_norm": 0.20690159499645233,
      "learning_rate": 0.00019853035858964906,
      "loss": 1.9777,
      "step": 63
    },
    {
      "epoch": 0.13054563997960225,
      "grad_norm": 0.21029432117938995,
      "learning_rate": 0.00019847451999183694,
      "loss": 2.2063,
      "step": 64
    },
    {
      "epoch": 0.13258541560428352,
      "grad_norm": 0.2483580857515335,
      "learning_rate": 0.00019841764844290744,
      "loss": 1.9817,
      "step": 65
    },
    {
      "epoch": 0.13462519122896482,
      "grad_norm": 0.2200578898191452,
      "learning_rate": 0.0001983597445394162,
      "loss": 1.8286,
      "step": 66
    },
    {
      "epoch": 0.1366649668536461,
      "grad_norm": 0.23194506764411926,
      "learning_rate": 0.00019830080888874778,
      "loss": 1.8918,
      "step": 67
    },
    {
      "epoch": 0.1387047424783274,
      "grad_norm": 0.2092316597700119,
      "learning_rate": 0.00019824084210910925,
      "loss": 2.0326,
      "step": 68
    },
    {
      "epoch": 0.14074451810300867,
      "grad_norm": 0.226849764585495,
      "learning_rate": 0.00019817984482952376,
      "loss": 2.1387,
      "step": 69
    },
    {
      "epoch": 0.14278429372768994,
      "grad_norm": 0.25519493222236633,
      "learning_rate": 0.0001981178176898239,
      "loss": 1.9261,
      "step": 70
    },
    {
      "epoch": 0.14482406935237124,
      "grad_norm": 0.2155541330575943,
      "learning_rate": 0.00019805476134064507,
      "loss": 2.2176,
      "step": 71
    },
    {
      "epoch": 0.14686384497705252,
      "grad_norm": 0.23612210154533386,
      "learning_rate": 0.00019799067644341844,
      "loss": 2.1125,
      "step": 72
    },
    {
      "epoch": 0.14890362060173382,
      "grad_norm": 0.2563931941986084,
      "learning_rate": 0.00019792556367036432,
      "loss": 1.9459,
      "step": 73
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 0.34834709763526917,
      "learning_rate": 0.0001978594237044849,
      "loss": 2.091,
      "step": 74
    },
    {
      "epoch": 0.1529831718510964,
      "grad_norm": 0.221855029463768,
      "learning_rate": 0.00019779225723955707,
      "loss": 1.8867,
      "step": 75
    },
    {
      "epoch": 0.15502294747577766,
      "grad_norm": 0.2613975405693054,
      "learning_rate": 0.0001977240649801253,
      "loss": 1.9889,
      "step": 76
    },
    {
      "epoch": 0.15706272310045896,
      "grad_norm": 0.3117937743663788,
      "learning_rate": 0.00019765484764149415,
      "loss": 2.0743,
      "step": 77
    },
    {
      "epoch": 0.15910249872514023,
      "grad_norm": 0.23428964614868164,
      "learning_rate": 0.00019758460594972068,
      "loss": 2.1752,
      "step": 78
    },
    {
      "epoch": 0.1611422743498215,
      "grad_norm": 0.23182815313339233,
      "learning_rate": 0.00019751334064160706,
      "loss": 1.9315,
      "step": 79
    },
    {
      "epoch": 0.1631820499745028,
      "grad_norm": 0.3055015206336975,
      "learning_rate": 0.00019744105246469263,
      "loss": 2.0348,
      "step": 80
    },
    {
      "epoch": 0.16522182559918408,
      "grad_norm": 0.22985045611858368,
      "learning_rate": 0.00019736774217724614,
      "loss": 1.792,
      "step": 81
    },
    {
      "epoch": 0.16726160122386538,
      "grad_norm": 0.2585189938545227,
      "learning_rate": 0.00019729341054825782,
      "loss": 2.0945,
      "step": 82
    },
    {
      "epoch": 0.16930137684854665,
      "grad_norm": 0.2798707187175751,
      "learning_rate": 0.00019721805835743134,
      "loss": 2.0114,
      "step": 83
    },
    {
      "epoch": 0.17134115247322795,
      "grad_norm": 0.2886582016944885,
      "learning_rate": 0.00019714168639517544,
      "loss": 2.0575,
      "step": 84
    },
    {
      "epoch": 0.17338092809790923,
      "grad_norm": 0.2944013178348541,
      "learning_rate": 0.00019706429546259593,
      "loss": 2.1074,
      "step": 85
    },
    {
      "epoch": 0.17542070372259053,
      "grad_norm": 0.318002313375473,
      "learning_rate": 0.00019698588637148703,
      "loss": 1.9883,
      "step": 86
    },
    {
      "epoch": 0.1774604793472718,
      "grad_norm": 0.256496787071228,
      "learning_rate": 0.00019690645994432305,
      "loss": 1.8408,
      "step": 87
    },
    {
      "epoch": 0.17950025497195307,
      "grad_norm": 0.3593447208404541,
      "learning_rate": 0.0001968260170142496,
      "loss": 1.9313,
      "step": 88
    },
    {
      "epoch": 0.18154003059663437,
      "grad_norm": 0.4645783305168152,
      "learning_rate": 0.00019674455842507492,
      "loss": 1.9448,
      "step": 89
    },
    {
      "epoch": 0.18357980622131564,
      "grad_norm": 0.2802218198776245,
      "learning_rate": 0.00019666208503126112,
      "loss": 1.9091,
      "step": 90
    },
    {
      "epoch": 0.18561958184599694,
      "grad_norm": 0.39699026942253113,
      "learning_rate": 0.00019657859769791505,
      "loss": 1.9936,
      "step": 91
    },
    {
      "epoch": 0.18765935747067822,
      "grad_norm": 0.4515025317668915,
      "learning_rate": 0.00019649409730077935,
      "loss": 2.2269,
      "step": 92
    },
    {
      "epoch": 0.18969913309535952,
      "grad_norm": 0.24775496125221252,
      "learning_rate": 0.00019640858472622316,
      "loss": 1.8843,
      "step": 93
    },
    {
      "epoch": 0.1917389087200408,
      "grad_norm": 0.35014575719833374,
      "learning_rate": 0.00019632206087123296,
      "loss": 2.0159,
      "step": 94
    },
    {
      "epoch": 0.1937786843447221,
      "grad_norm": 0.4293341040611267,
      "learning_rate": 0.00019623452664340306,
      "loss": 2.1129,
      "step": 95
    },
    {
      "epoch": 0.19581845996940336,
      "grad_norm": 0.249364972114563,
      "learning_rate": 0.000196145982960926,
      "loss": 2.1385,
      "step": 96
    },
    {
      "epoch": 0.19785823559408466,
      "grad_norm": 0.3796793222427368,
      "learning_rate": 0.00019605643075258321,
      "loss": 1.9737,
      "step": 97
    },
    {
      "epoch": 0.19989801121876594,
      "grad_norm": 0.41410332918167114,
      "learning_rate": 0.00019596587095773495,
      "loss": 1.895,
      "step": 98
    },
    {
      "epoch": 0.2019377868434472,
      "grad_norm": 0.2810049057006836,
      "learning_rate": 0.0001958743045263106,
      "loss": 1.9859,
      "step": 99
    },
    {
      "epoch": 0.2039775624681285,
      "grad_norm": 0.37417009472846985,
      "learning_rate": 0.00019578173241879872,
      "loss": 1.9447,
      "step": 100
    },
    {
      "epoch": 0.20601733809280978,
      "grad_norm": 0.33988890051841736,
      "learning_rate": 0.0001956881556062369,
      "loss": 1.8362,
      "step": 101
    },
    {
      "epoch": 0.20805711371749108,
      "grad_norm": 0.27952101826667786,
      "learning_rate": 0.00019559357507020162,
      "loss": 1.9745,
      "step": 102
    },
    {
      "epoch": 0.21009688934217235,
      "grad_norm": 0.24870562553405762,
      "learning_rate": 0.00019549799180279792,
      "loss": 1.8926,
      "step": 103
    },
    {
      "epoch": 0.21213666496685366,
      "grad_norm": 0.33430561423301697,
      "learning_rate": 0.00019540140680664913,
      "loss": 2.0914,
      "step": 104
    },
    {
      "epoch": 0.21417644059153493,
      "grad_norm": 0.3203825056552887,
      "learning_rate": 0.0001953038210948861,
      "loss": 2.0238,
      "step": 105
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.2822887897491455,
      "learning_rate": 0.00019520523569113677,
      "loss": 2.053,
      "step": 106
    },
    {
      "epoch": 0.2182559918408975,
      "grad_norm": 0.31055620312690735,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.8936,
      "step": 107
    },
    {
      "epoch": 0.22029576746557877,
      "grad_norm": 0.3920172452926636,
      "learning_rate": 0.0001950050699546116,
      "loss": 2.1061,
      "step": 108
    },
    {
      "epoch": 0.22233554309026007,
      "grad_norm": 0.2737603187561035,
      "learning_rate": 0.00019490349172147963,
      "loss": 2.0772,
      "step": 109
    },
    {
      "epoch": 0.22437531871494135,
      "grad_norm": 0.27526190876960754,
      "learning_rate": 0.00019480091799562704,
      "loss": 1.9078,
      "step": 110
    },
    {
      "epoch": 0.22641509433962265,
      "grad_norm": 0.3213340938091278,
      "learning_rate": 0.00019469734985300371,
      "loss": 1.8632,
      "step": 111
    },
    {
      "epoch": 0.22845486996430392,
      "grad_norm": 0.3409796953201294,
      "learning_rate": 0.00019459278837999046,
      "loss": 1.8264,
      "step": 112
    },
    {
      "epoch": 0.23049464558898522,
      "grad_norm": 0.2637316882610321,
      "learning_rate": 0.00019448723467338763,
      "loss": 1.9274,
      "step": 113
    },
    {
      "epoch": 0.2325344212136665,
      "grad_norm": 0.2738693952560425,
      "learning_rate": 0.00019438068984040365,
      "loss": 2.0925,
      "step": 114
    },
    {
      "epoch": 0.2345741968383478,
      "grad_norm": 0.43626368045806885,
      "learning_rate": 0.00019427315499864344,
      "loss": 1.9424,
      "step": 115
    },
    {
      "epoch": 0.23661397246302907,
      "grad_norm": 0.3207686245441437,
      "learning_rate": 0.00019416463127609656,
      "loss": 1.8188,
      "step": 116
    },
    {
      "epoch": 0.23865374808771037,
      "grad_norm": 0.28913381695747375,
      "learning_rate": 0.0001940551198111255,
      "loss": 1.9561,
      "step": 117
    },
    {
      "epoch": 0.24069352371239164,
      "grad_norm": 0.3558366894721985,
      "learning_rate": 0.00019394462175245381,
      "loss": 1.8839,
      "step": 118
    },
    {
      "epoch": 0.2427332993370729,
      "grad_norm": 0.3230222463607788,
      "learning_rate": 0.0001938331382591537,
      "loss": 1.8197,
      "step": 119
    },
    {
      "epoch": 0.2447730749617542,
      "grad_norm": 0.31508007645606995,
      "learning_rate": 0.00019372067050063438,
      "loss": 2.0963,
      "step": 120
    },
    {
      "epoch": 0.24681285058643548,
      "grad_norm": 0.28743404150009155,
      "learning_rate": 0.00019360721965662933,
      "loss": 1.8382,
      "step": 121
    },
    {
      "epoch": 0.24885262621111678,
      "grad_norm": 0.32556018233299255,
      "learning_rate": 0.00019349278691718427,
      "loss": 1.8255,
      "step": 122
    },
    {
      "epoch": 0.2508924018357981,
      "grad_norm": 0.3947349488735199,
      "learning_rate": 0.00019337737348264447,
      "loss": 2.1048,
      "step": 123
    },
    {
      "epoch": 0.25293217746047936,
      "grad_norm": 0.280627965927124,
      "learning_rate": 0.00019326098056364222,
      "loss": 1.7557,
      "step": 124
    },
    {
      "epoch": 0.25497195308516063,
      "grad_norm": 0.34356269240379333,
      "learning_rate": 0.00019314360938108425,
      "loss": 1.9692,
      "step": 125
    },
    {
      "epoch": 0.2570117287098419,
      "grad_norm": 0.30822035670280457,
      "learning_rate": 0.00019302526116613864,
      "loss": 1.9135,
      "step": 126
    },
    {
      "epoch": 0.2590515043345232,
      "grad_norm": 0.28359460830688477,
      "learning_rate": 0.00019290593716022217,
      "loss": 2.0667,
      "step": 127
    },
    {
      "epoch": 0.2610912799592045,
      "grad_norm": 0.2782716751098633,
      "learning_rate": 0.00019278563861498723,
      "loss": 1.7958,
      "step": 128
    },
    {
      "epoch": 0.2631310555838858,
      "grad_norm": 0.2571290135383606,
      "learning_rate": 0.00019266436679230865,
      "loss": 2.1198,
      "step": 129
    },
    {
      "epoch": 0.26517083120856705,
      "grad_norm": 0.3336668908596039,
      "learning_rate": 0.00019254212296427044,
      "loss": 1.8137,
      "step": 130
    },
    {
      "epoch": 0.2672106068332483,
      "grad_norm": 0.23998981714248657,
      "learning_rate": 0.00019241890841315248,
      "loss": 2.0071,
      "step": 131
    },
    {
      "epoch": 0.26925038245792965,
      "grad_norm": 0.3191507160663605,
      "learning_rate": 0.0001922947244314172,
      "loss": 2.0239,
      "step": 132
    },
    {
      "epoch": 0.2712901580826109,
      "grad_norm": 0.30696266889572144,
      "learning_rate": 0.0001921695723216957,
      "loss": 2.2377,
      "step": 133
    },
    {
      "epoch": 0.2733299337072922,
      "grad_norm": 0.2688175439834595,
      "learning_rate": 0.00019204345339677442,
      "loss": 1.8686,
      "step": 134
    },
    {
      "epoch": 0.27536970933197347,
      "grad_norm": 0.27408865094184875,
      "learning_rate": 0.00019191636897958122,
      "loss": 2.0253,
      "step": 135
    },
    {
      "epoch": 0.2774094849566548,
      "grad_norm": 0.2917419672012329,
      "learning_rate": 0.00019178832040317155,
      "loss": 1.905,
      "step": 136
    },
    {
      "epoch": 0.27944926058133607,
      "grad_norm": 0.27972346544265747,
      "learning_rate": 0.0001916593090107143,
      "loss": 1.8001,
      "step": 137
    },
    {
      "epoch": 0.28148903620601734,
      "grad_norm": 0.2744503915309906,
      "learning_rate": 0.00019152933615547798,
      "loss": 1.9057,
      "step": 138
    },
    {
      "epoch": 0.2835288118306986,
      "grad_norm": 0.27640461921691895,
      "learning_rate": 0.0001913984032008163,
      "loss": 2.0683,
      "step": 139
    },
    {
      "epoch": 0.2855685874553799,
      "grad_norm": 0.28741398453712463,
      "learning_rate": 0.00019126651152015403,
      "loss": 1.9567,
      "step": 140
    },
    {
      "epoch": 0.2876083630800612,
      "grad_norm": 0.31334587931632996,
      "learning_rate": 0.0001911336624969725,
      "loss": 1.8974,
      "step": 141
    },
    {
      "epoch": 0.2896481387047425,
      "grad_norm": 0.2697933614253998,
      "learning_rate": 0.00019099985752479506,
      "loss": 1.8786,
      "step": 142
    },
    {
      "epoch": 0.29168791432942376,
      "grad_norm": 0.2917918562889099,
      "learning_rate": 0.00019086509800717258,
      "loss": 2.0443,
      "step": 143
    },
    {
      "epoch": 0.29372768995410503,
      "grad_norm": 0.2908966541290283,
      "learning_rate": 0.00019072938535766865,
      "loss": 1.9817,
      "step": 144
    },
    {
      "epoch": 0.29576746557878636,
      "grad_norm": 0.2819146513938904,
      "learning_rate": 0.0001905927209998447,
      "loss": 2.0689,
      "step": 145
    },
    {
      "epoch": 0.29780724120346763,
      "grad_norm": 0.3112149238586426,
      "learning_rate": 0.0001904551063672452,
      "loss": 1.9045,
      "step": 146
    },
    {
      "epoch": 0.2998470168281489,
      "grad_norm": 0.2511192560195923,
      "learning_rate": 0.00019031654290338254,
      "loss": 2.007,
      "step": 147
    },
    {
      "epoch": 0.3018867924528302,
      "grad_norm": 0.2944158911705017,
      "learning_rate": 0.00019017703206172185,
      "loss": 1.9059,
      "step": 148
    },
    {
      "epoch": 0.30392656807751145,
      "grad_norm": 0.2799970209598541,
      "learning_rate": 0.0001900365753056659,
      "loss": 1.8268,
      "step": 149
    },
    {
      "epoch": 0.3059663437021928,
      "grad_norm": 0.3119431436061859,
      "learning_rate": 0.00018989517410853955,
      "loss": 1.7999,
      "step": 150
    },
    {
      "epoch": 0.30800611932687405,
      "grad_norm": 0.27174267172813416,
      "learning_rate": 0.00018975282995357446,
      "loss": 1.8971,
      "step": 151
    },
    {
      "epoch": 0.3100458949515553,
      "grad_norm": 0.3147140443325043,
      "learning_rate": 0.00018960954433389345,
      "loss": 1.9755,
      "step": 152
    },
    {
      "epoch": 0.3120856705762366,
      "grad_norm": 0.27466344833374023,
      "learning_rate": 0.00018946531875249493,
      "loss": 1.9819,
      "step": 153
    },
    {
      "epoch": 0.3141254462009179,
      "grad_norm": 0.2912920117378235,
      "learning_rate": 0.00018932015472223693,
      "loss": 2.1079,
      "step": 154
    },
    {
      "epoch": 0.3161652218255992,
      "grad_norm": 0.3123255968093872,
      "learning_rate": 0.00018917405376582145,
      "loss": 1.93,
      "step": 155
    },
    {
      "epoch": 0.31820499745028047,
      "grad_norm": 0.3270852565765381,
      "learning_rate": 0.0001890270174157784,
      "loss": 1.8386,
      "step": 156
    },
    {
      "epoch": 0.32024477307496174,
      "grad_norm": 0.30445969104766846,
      "learning_rate": 0.00018887904721444953,
      "loss": 2.1993,
      "step": 157
    },
    {
      "epoch": 0.322284548699643,
      "grad_norm": 0.2974015474319458,
      "learning_rate": 0.00018873014471397224,
      "loss": 1.8965,
      "step": 158
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 0.3236542046070099,
      "learning_rate": 0.00018858031147626325,
      "loss": 2.041,
      "step": 159
    },
    {
      "epoch": 0.3263640999490056,
      "grad_norm": 0.2958833575248718,
      "learning_rate": 0.00018842954907300236,
      "loss": 1.8681,
      "step": 160
    },
    {
      "epoch": 0.3284038755736869,
      "grad_norm": 0.27163368463516235,
      "learning_rate": 0.00018827785908561584,
      "loss": 1.9664,
      "step": 161
    },
    {
      "epoch": 0.33044365119836816,
      "grad_norm": 0.2662605941295624,
      "learning_rate": 0.0001881252431052599,
      "loss": 1.9255,
      "step": 162
    },
    {
      "epoch": 0.3324834268230495,
      "grad_norm": 0.2995011508464813,
      "learning_rate": 0.00018797170273280388,
      "loss": 2.1172,
      "step": 163
    },
    {
      "epoch": 0.33452320244773076,
      "grad_norm": 0.2997836768627167,
      "learning_rate": 0.00018781723957881372,
      "loss": 1.9044,
      "step": 164
    },
    {
      "epoch": 0.33656297807241203,
      "grad_norm": 0.2867211401462555,
      "learning_rate": 0.0001876618552635348,
      "loss": 1.8,
      "step": 165
    },
    {
      "epoch": 0.3386027536970933,
      "grad_norm": 0.2972771227359772,
      "learning_rate": 0.000187505551416875,
      "loss": 1.7879,
      "step": 166
    },
    {
      "epoch": 0.3406425293217746,
      "grad_norm": 0.27393755316734314,
      "learning_rate": 0.00018734832967838775,
      "loss": 2.1209,
      "step": 167
    },
    {
      "epoch": 0.3426823049464559,
      "grad_norm": 0.31422799825668335,
      "learning_rate": 0.00018719019169725472,
      "loss": 1.9435,
      "step": 168
    },
    {
      "epoch": 0.3447220805711372,
      "grad_norm": 0.3372005224227905,
      "learning_rate": 0.00018703113913226847,
      "loss": 2.0911,
      "step": 169
    },
    {
      "epoch": 0.34676185619581845,
      "grad_norm": 0.29995280504226685,
      "learning_rate": 0.00018687117365181512,
      "loss": 1.9077,
      "step": 170
    },
    {
      "epoch": 0.3488016318204997,
      "grad_norm": 0.2770789861679077,
      "learning_rate": 0.0001867102969338569,
      "loss": 1.7649,
      "step": 171
    },
    {
      "epoch": 0.35084140744518105,
      "grad_norm": 0.2982628047466278,
      "learning_rate": 0.00018654851066591448,
      "loss": 2.0258,
      "step": 172
    },
    {
      "epoch": 0.3528811830698623,
      "grad_norm": 0.2924087643623352,
      "learning_rate": 0.0001863858165450492,
      "loss": 1.9533,
      "step": 173
    },
    {
      "epoch": 0.3549209586945436,
      "grad_norm": 0.29398518800735474,
      "learning_rate": 0.0001862222162778454,
      "loss": 1.8298,
      "step": 174
    },
    {
      "epoch": 0.35696073431922487,
      "grad_norm": 0.34897300601005554,
      "learning_rate": 0.00018605771158039253,
      "loss": 1.7459,
      "step": 175
    },
    {
      "epoch": 0.35900050994390614,
      "grad_norm": 0.33509624004364014,
      "learning_rate": 0.00018589230417826697,
      "loss": 1.8843,
      "step": 176
    },
    {
      "epoch": 0.36104028556858747,
      "grad_norm": 0.30635756254196167,
      "learning_rate": 0.00018572599580651415,
      "loss": 2.0315,
      "step": 177
    },
    {
      "epoch": 0.36308006119326874,
      "grad_norm": 0.3544027805328369,
      "learning_rate": 0.00018555878820963013,
      "loss": 1.9821,
      "step": 178
    },
    {
      "epoch": 0.36511983681795,
      "grad_norm": 0.283241331577301,
      "learning_rate": 0.00018539068314154354,
      "loss": 1.7482,
      "step": 179
    },
    {
      "epoch": 0.3671596124426313,
      "grad_norm": 0.2630005478858948,
      "learning_rate": 0.00018522168236559695,
      "loss": 1.887,
      "step": 180
    },
    {
      "epoch": 0.3691993880673126,
      "grad_norm": 0.2816585898399353,
      "learning_rate": 0.00018505178765452853,
      "loss": 1.8995,
      "step": 181
    },
    {
      "epoch": 0.3712391636919939,
      "grad_norm": 0.30843281745910645,
      "learning_rate": 0.00018488100079045344,
      "loss": 1.943,
      "step": 182
    },
    {
      "epoch": 0.37327893931667516,
      "grad_norm": 0.30149805545806885,
      "learning_rate": 0.00018470932356484508,
      "loss": 1.8764,
      "step": 183
    },
    {
      "epoch": 0.37531871494135643,
      "grad_norm": 0.27851638197898865,
      "learning_rate": 0.00018453675777851627,
      "loss": 1.8901,
      "step": 184
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 0.34025222063064575,
      "learning_rate": 0.00018436330524160047,
      "loss": 2.167,
      "step": 185
    },
    {
      "epoch": 0.37939826619071904,
      "grad_norm": 0.3183801472187042,
      "learning_rate": 0.0001841889677735327,
      "loss": 1.9419,
      "step": 186
    },
    {
      "epoch": 0.3814380418154003,
      "grad_norm": 0.3072781562805176,
      "learning_rate": 0.00018401374720303056,
      "loss": 1.9817,
      "step": 187
    },
    {
      "epoch": 0.3834778174400816,
      "grad_norm": 0.2894771993160248,
      "learning_rate": 0.00018383764536807485,
      "loss": 2.114,
      "step": 188
    },
    {
      "epoch": 0.38551759306476285,
      "grad_norm": 0.3198698163032532,
      "learning_rate": 0.0001836606641158905,
      "loss": 1.8609,
      "step": 189
    },
    {
      "epoch": 0.3875573686894442,
      "grad_norm": 0.3462139964103699,
      "learning_rate": 0.00018348280530292713,
      "loss": 1.7753,
      "step": 190
    },
    {
      "epoch": 0.38959714431412545,
      "grad_norm": 0.2793361246585846,
      "learning_rate": 0.00018330407079483952,
      "loss": 2.1784,
      "step": 191
    },
    {
      "epoch": 0.3916369199388067,
      "grad_norm": 0.29519417881965637,
      "learning_rate": 0.0001831244624664681,
      "loss": 1.9627,
      "step": 192
    },
    {
      "epoch": 0.393676695563488,
      "grad_norm": 0.3317961096763611,
      "learning_rate": 0.00018294398220181917,
      "loss": 1.7643,
      "step": 193
    },
    {
      "epoch": 0.3957164711881693,
      "grad_norm": 0.3138796091079712,
      "learning_rate": 0.0001827626318940454,
      "loss": 1.792,
      "step": 194
    },
    {
      "epoch": 0.3977562468128506,
      "grad_norm": 0.30172964930534363,
      "learning_rate": 0.00018258041344542566,
      "loss": 1.8828,
      "step": 195
    },
    {
      "epoch": 0.3997960224375319,
      "grad_norm": 0.3473678529262543,
      "learning_rate": 0.00018239732876734527,
      "loss": 1.9373,
      "step": 196
    },
    {
      "epoch": 0.40183579806221315,
      "grad_norm": 0.3263239562511444,
      "learning_rate": 0.00018221337978027583,
      "loss": 1.9933,
      "step": 197
    },
    {
      "epoch": 0.4038755736868944,
      "grad_norm": 0.32656848430633545,
      "learning_rate": 0.00018202856841375518,
      "loss": 1.8501,
      "step": 198
    },
    {
      "epoch": 0.40591534931157575,
      "grad_norm": 0.3206334412097931,
      "learning_rate": 0.00018184289660636715,
      "loss": 2.0026,
      "step": 199
    },
    {
      "epoch": 0.407955124936257,
      "grad_norm": 0.31711164116859436,
      "learning_rate": 0.0001816563663057211,
      "loss": 1.9573,
      "step": 200
    },
    {
      "epoch": 0.4099949005609383,
      "grad_norm": 0.2891688048839569,
      "learning_rate": 0.00018146897946843163,
      "loss": 1.939,
      "step": 201
    },
    {
      "epoch": 0.41203467618561956,
      "grad_norm": 0.3304015100002289,
      "learning_rate": 0.000181280738060098,
      "loss": 1.874,
      "step": 202
    },
    {
      "epoch": 0.4140744518103009,
      "grad_norm": 0.2902586758136749,
      "learning_rate": 0.0001810916440552835,
      "loss": 1.8516,
      "step": 203
    },
    {
      "epoch": 0.41611422743498216,
      "grad_norm": 0.3066134452819824,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.909,
      "step": 204
    },
    {
      "epoch": 0.41815400305966344,
      "grad_norm": 0.2844925820827484,
      "learning_rate": 0.00018071090619916093,
      "loss": 1.8373,
      "step": 205
    },
    {
      "epoch": 0.4201937786843447,
      "grad_norm": 0.2905077338218689,
      "learning_rate": 0.00018051926634161282,
      "loss": 1.8031,
      "step": 206
    },
    {
      "epoch": 0.422233554309026,
      "grad_norm": 0.3110411763191223,
      "learning_rate": 0.00018032678187506187,
      "loss": 1.9915,
      "step": 207
    },
    {
      "epoch": 0.4242733299337073,
      "grad_norm": 0.27634483575820923,
      "learning_rate": 0.00018013345481857903,
      "loss": 2.0072,
      "step": 208
    },
    {
      "epoch": 0.4263131055583886,
      "grad_norm": 0.29069051146507263,
      "learning_rate": 0.0001799392872000736,
      "loss": 2.0632,
      "step": 209
    },
    {
      "epoch": 0.42835288118306986,
      "grad_norm": 0.28966760635375977,
      "learning_rate": 0.00017974428105627208,
      "loss": 1.8184,
      "step": 210
    },
    {
      "epoch": 0.43039265680775113,
      "grad_norm": 0.2768760621547699,
      "learning_rate": 0.00017954843843269664,
      "loss": 1.8344,
      "step": 211
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.30277568101882935,
      "learning_rate": 0.0001793517613836437,
      "loss": 1.931,
      "step": 212
    },
    {
      "epoch": 0.43447220805711373,
      "grad_norm": 0.30833378434181213,
      "learning_rate": 0.00017915425197216245,
      "loss": 1.8319,
      "step": 213
    },
    {
      "epoch": 0.436511983681795,
      "grad_norm": 0.2517772316932678,
      "learning_rate": 0.00017895591227003315,
      "loss": 2.0335,
      "step": 214
    },
    {
      "epoch": 0.4385517593064763,
      "grad_norm": 0.3051300346851349,
      "learning_rate": 0.00017875674435774547,
      "loss": 1.8523,
      "step": 215
    },
    {
      "epoch": 0.44059153493115755,
      "grad_norm": 0.331875741481781,
      "learning_rate": 0.00017855675032447648,
      "loss": 1.902,
      "step": 216
    },
    {
      "epoch": 0.4426313105558389,
      "grad_norm": 0.3102109134197235,
      "learning_rate": 0.00017835593226806903,
      "loss": 1.9391,
      "step": 217
    },
    {
      "epoch": 0.44467108618052015,
      "grad_norm": 0.28581124544143677,
      "learning_rate": 0.00017815429229500946,
      "loss": 1.9595,
      "step": 218
    },
    {
      "epoch": 0.4467108618052014,
      "grad_norm": 0.2874554693698883,
      "learning_rate": 0.00017795183252040567,
      "loss": 1.8683,
      "step": 219
    },
    {
      "epoch": 0.4487506374298827,
      "grad_norm": 0.3131530284881592,
      "learning_rate": 0.00017774855506796496,
      "loss": 2.003,
      "step": 220
    },
    {
      "epoch": 0.450790413054564,
      "grad_norm": 0.3006989359855652,
      "learning_rate": 0.0001775444620699715,
      "loss": 1.8058,
      "step": 221
    },
    {
      "epoch": 0.4528301886792453,
      "grad_norm": 0.29621464014053345,
      "learning_rate": 0.0001773395556672644,
      "loss": 1.9781,
      "step": 222
    },
    {
      "epoch": 0.45486996430392657,
      "grad_norm": 0.325095534324646,
      "learning_rate": 0.00017713383800921478,
      "loss": 1.8633,
      "step": 223
    },
    {
      "epoch": 0.45690973992860784,
      "grad_norm": 0.306911826133728,
      "learning_rate": 0.00017692731125370354,
      "loss": 1.9318,
      "step": 224
    },
    {
      "epoch": 0.4589495155532891,
      "grad_norm": 0.335014283657074,
      "learning_rate": 0.00017671997756709863,
      "loss": 1.7637,
      "step": 225
    },
    {
      "epoch": 0.46098929117797044,
      "grad_norm": 0.28670719265937805,
      "learning_rate": 0.00017651183912423228,
      "loss": 1.988,
      "step": 226
    },
    {
      "epoch": 0.4630290668026517,
      "grad_norm": 0.2969343364238739,
      "learning_rate": 0.00017630289810837834,
      "loss": 1.7984,
      "step": 227
    },
    {
      "epoch": 0.465068842427333,
      "grad_norm": 0.3015127182006836,
      "learning_rate": 0.0001760931567112291,
      "loss": 1.7022,
      "step": 228
    },
    {
      "epoch": 0.46710861805201426,
      "grad_norm": 0.32308632135391235,
      "learning_rate": 0.00017588261713287267,
      "loss": 1.8067,
      "step": 229
    },
    {
      "epoch": 0.4691483936766956,
      "grad_norm": 0.30818650126457214,
      "learning_rate": 0.00017567128158176953,
      "loss": 1.7096,
      "step": 230
    },
    {
      "epoch": 0.47118816930137686,
      "grad_norm": 0.28488847613334656,
      "learning_rate": 0.00017545915227472965,
      "loss": 1.8784,
      "step": 231
    },
    {
      "epoch": 0.47322794492605813,
      "grad_norm": 0.3801325857639313,
      "learning_rate": 0.00017524623143688902,
      "loss": 1.9555,
      "step": 232
    },
    {
      "epoch": 0.4752677205507394,
      "grad_norm": 0.31661075353622437,
      "learning_rate": 0.00017503252130168657,
      "loss": 1.8717,
      "step": 233
    },
    {
      "epoch": 0.47730749617542073,
      "grad_norm": 0.296003520488739,
      "learning_rate": 0.00017481802411084042,
      "loss": 1.7293,
      "step": 234
    },
    {
      "epoch": 0.479347271800102,
      "grad_norm": 0.3210139274597168,
      "learning_rate": 0.0001746027421143246,
      "loss": 1.9587,
      "step": 235
    },
    {
      "epoch": 0.4813870474247833,
      "grad_norm": 0.2968738079071045,
      "learning_rate": 0.00017438667757034546,
      "loss": 2.0743,
      "step": 236
    },
    {
      "epoch": 0.48342682304946455,
      "grad_norm": 0.3373945355415344,
      "learning_rate": 0.00017416983274531775,
      "loss": 1.8239,
      "step": 237
    },
    {
      "epoch": 0.4854665986741458,
      "grad_norm": 0.29180705547332764,
      "learning_rate": 0.0001739522099138411,
      "loss": 1.9563,
      "step": 238
    },
    {
      "epoch": 0.48750637429882715,
      "grad_norm": 0.342316597700119,
      "learning_rate": 0.00017373381135867604,
      "loss": 1.9012,
      "step": 239
    },
    {
      "epoch": 0.4895461499235084,
      "grad_norm": 0.29859068989753723,
      "learning_rate": 0.00017351463937072004,
      "loss": 1.723,
      "step": 240
    },
    {
      "epoch": 0.4915859255481897,
      "grad_norm": 0.32331928610801697,
      "learning_rate": 0.0001732946962489836,
      "loss": 1.9278,
      "step": 241
    },
    {
      "epoch": 0.49362570117287097,
      "grad_norm": 0.3604521155357361,
      "learning_rate": 0.00017307398430056593,
      "loss": 1.9691,
      "step": 242
    },
    {
      "epoch": 0.4956654767975523,
      "grad_norm": 0.30965346097946167,
      "learning_rate": 0.000172852505840631,
      "loss": 1.7225,
      "step": 243
    },
    {
      "epoch": 0.49770525242223357,
      "grad_norm": 0.2769593894481659,
      "learning_rate": 0.00017263026319238301,
      "loss": 1.7938,
      "step": 244
    },
    {
      "epoch": 0.49974502804691484,
      "grad_norm": 0.33169788122177124,
      "learning_rate": 0.00017240725868704218,
      "loss": 1.6576,
      "step": 245
    },
    {
      "epoch": 0.49974502804691484,
      "eval_loss": 1.874290943145752,
      "eval_runtime": 49.8203,
      "eval_samples_per_second": 16.58,
      "eval_steps_per_second": 2.088,
      "step": 245
    },
    {
      "epoch": 0.5017848036715962,
      "grad_norm": 0.3088040053844452,
      "learning_rate": 0.00017218349466382023,
      "loss": 1.7977,
      "step": 246
    },
    {
      "epoch": 0.5038245792962774,
      "grad_norm": 0.3247360289096832,
      "learning_rate": 0.0001719589734698959,
      "loss": 1.9595,
      "step": 247
    },
    {
      "epoch": 0.5058643549209587,
      "grad_norm": 0.30020302534103394,
      "learning_rate": 0.00017173369746039025,
      "loss": 1.7303,
      "step": 248
    },
    {
      "epoch": 0.50790413054564,
      "grad_norm": 0.2880503833293915,
      "learning_rate": 0.00017150766899834204,
      "loss": 1.9203,
      "step": 249
    },
    {
      "epoch": 0.5099439061703213,
      "grad_norm": 0.2775571048259735,
      "learning_rate": 0.00017128089045468294,
      "loss": 1.8347,
      "step": 250
    },
    {
      "epoch": 0.5119836817950025,
      "grad_norm": 0.31517794728279114,
      "learning_rate": 0.00017105336420821247,
      "loss": 1.9258,
      "step": 251
    },
    {
      "epoch": 0.5140234574196838,
      "grad_norm": 0.315845251083374,
      "learning_rate": 0.0001708250926455733,
      "loss": 1.6125,
      "step": 252
    },
    {
      "epoch": 0.5160632330443651,
      "grad_norm": 0.3020716607570648,
      "learning_rate": 0.00017059607816122618,
      "loss": 2.036,
      "step": 253
    },
    {
      "epoch": 0.5181030086690463,
      "grad_norm": 0.3116091787815094,
      "learning_rate": 0.00017036632315742462,
      "loss": 1.7882,
      "step": 254
    },
    {
      "epoch": 0.5201427842937277,
      "grad_norm": 0.2845454216003418,
      "learning_rate": 0.00017013583004418993,
      "loss": 1.9165,
      "step": 255
    },
    {
      "epoch": 0.522182559918409,
      "grad_norm": 0.3218507468700409,
      "learning_rate": 0.00016990460123928575,
      "loss": 1.9143,
      "step": 256
    },
    {
      "epoch": 0.5242223355430903,
      "grad_norm": 0.32271113991737366,
      "learning_rate": 0.00016967263916819287,
      "loss": 1.7233,
      "step": 257
    },
    {
      "epoch": 0.5262621111677716,
      "grad_norm": 0.32956361770629883,
      "learning_rate": 0.00016943994626408363,
      "loss": 2.1151,
      "step": 258
    },
    {
      "epoch": 0.5283018867924528,
      "grad_norm": 0.309712678194046,
      "learning_rate": 0.0001692065249677965,
      "loss": 1.7285,
      "step": 259
    },
    {
      "epoch": 0.5303416624171341,
      "grad_norm": 0.3099533021450043,
      "learning_rate": 0.00016897237772781044,
      "loss": 1.8461,
      "step": 260
    },
    {
      "epoch": 0.5323814380418154,
      "grad_norm": 0.2932775914669037,
      "learning_rate": 0.00016873750700021915,
      "loss": 1.869,
      "step": 261
    },
    {
      "epoch": 0.5344212136664966,
      "grad_norm": 0.2912542223930359,
      "learning_rate": 0.00016850191524870546,
      "loss": 1.7672,
      "step": 262
    },
    {
      "epoch": 0.536460989291178,
      "grad_norm": 0.33142998814582825,
      "learning_rate": 0.00016826560494451537,
      "loss": 1.8723,
      "step": 263
    },
    {
      "epoch": 0.5385007649158593,
      "grad_norm": 0.26213347911834717,
      "learning_rate": 0.00016802857856643215,
      "loss": 1.6971,
      "step": 264
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.2854675352573395,
      "learning_rate": 0.00016779083860075033,
      "loss": 1.8517,
      "step": 265
    },
    {
      "epoch": 0.5425803161652218,
      "grad_norm": 0.3256230354309082,
      "learning_rate": 0.00016755238754124965,
      "loss": 1.9159,
      "step": 266
    },
    {
      "epoch": 0.5446200917899031,
      "grad_norm": 0.30096253752708435,
      "learning_rate": 0.00016731322788916892,
      "loss": 1.7229,
      "step": 267
    },
    {
      "epoch": 0.5466598674145844,
      "grad_norm": 0.2952723801136017,
      "learning_rate": 0.00016707336215317968,
      "loss": 1.8191,
      "step": 268
    },
    {
      "epoch": 0.5486996430392657,
      "grad_norm": 0.32182615995407104,
      "learning_rate": 0.00016683279284936004,
      "loss": 1.9188,
      "step": 269
    },
    {
      "epoch": 0.5507394186639469,
      "grad_norm": 0.3065682351589203,
      "learning_rate": 0.00016659152250116812,
      "loss": 1.5902,
      "step": 270
    },
    {
      "epoch": 0.5527791942886282,
      "grad_norm": 0.27141043543815613,
      "learning_rate": 0.00016634955363941574,
      "loss": 1.705,
      "step": 271
    },
    {
      "epoch": 0.5548189699133096,
      "grad_norm": 0.3703926205635071,
      "learning_rate": 0.00016610688880224178,
      "loss": 1.9515,
      "step": 272
    },
    {
      "epoch": 0.5568587455379909,
      "grad_norm": 0.3434322476387024,
      "learning_rate": 0.0001658635305350855,
      "loss": 1.6887,
      "step": 273
    },
    {
      "epoch": 0.5588985211626721,
      "grad_norm": 0.2847291827201843,
      "learning_rate": 0.00016561948139065996,
      "loss": 2.0415,
      "step": 274
    },
    {
      "epoch": 0.5609382967873534,
      "grad_norm": 0.27591603994369507,
      "learning_rate": 0.00016537474392892528,
      "loss": 1.8893,
      "step": 275
    },
    {
      "epoch": 0.5629780724120347,
      "grad_norm": 0.32474270462989807,
      "learning_rate": 0.00016512932071706152,
      "loss": 1.8589,
      "step": 276
    },
    {
      "epoch": 0.565017848036716,
      "grad_norm": 0.33138149976730347,
      "learning_rate": 0.0001648832143294422,
      "loss": 1.7978,
      "step": 277
    },
    {
      "epoch": 0.5670576236613972,
      "grad_norm": 0.321053683757782,
      "learning_rate": 0.0001646364273476067,
      "loss": 1.911,
      "step": 278
    },
    {
      "epoch": 0.5690973992860785,
      "grad_norm": 0.313310444355011,
      "learning_rate": 0.00016438896236023375,
      "loss": 1.7816,
      "step": 279
    },
    {
      "epoch": 0.5711371749107598,
      "grad_norm": 0.2893736958503723,
      "learning_rate": 0.000164140821963114,
      "loss": 1.7197,
      "step": 280
    },
    {
      "epoch": 0.5731769505354412,
      "grad_norm": 0.3043624758720398,
      "learning_rate": 0.00016389200875912278,
      "loss": 1.7415,
      "step": 281
    },
    {
      "epoch": 0.5752167261601224,
      "grad_norm": 0.29861506819725037,
      "learning_rate": 0.00016364252535819282,
      "loss": 1.7317,
      "step": 282
    },
    {
      "epoch": 0.5772565017848037,
      "grad_norm": 0.3631903827190399,
      "learning_rate": 0.000163392374377287,
      "loss": 1.8116,
      "step": 283
    },
    {
      "epoch": 0.579296277409485,
      "grad_norm": 0.32387158274650574,
      "learning_rate": 0.00016314155844037074,
      "loss": 1.8652,
      "step": 284
    },
    {
      "epoch": 0.5813360530341662,
      "grad_norm": 0.3442007899284363,
      "learning_rate": 0.00016289008017838445,
      "loss": 2.0466,
      "step": 285
    },
    {
      "epoch": 0.5833758286588475,
      "grad_norm": 0.3226166367530823,
      "learning_rate": 0.0001626379422292162,
      "loss": 1.8803,
      "step": 286
    },
    {
      "epoch": 0.5854156042835288,
      "grad_norm": 0.2765788733959198,
      "learning_rate": 0.00016238514723767374,
      "loss": 1.8048,
      "step": 287
    },
    {
      "epoch": 0.5874553799082101,
      "grad_norm": 0.26808875799179077,
      "learning_rate": 0.0001621316978554569,
      "loss": 1.9358,
      "step": 288
    },
    {
      "epoch": 0.5894951555328913,
      "grad_norm": 0.34248560667037964,
      "learning_rate": 0.00016187759674112973,
      "loss": 1.7614,
      "step": 289
    },
    {
      "epoch": 0.5915349311575727,
      "grad_norm": 0.3485107123851776,
      "learning_rate": 0.00016162284656009274,
      "loss": 1.7487,
      "step": 290
    },
    {
      "epoch": 0.593574706782254,
      "grad_norm": 0.31153398752212524,
      "learning_rate": 0.00016136744998455476,
      "loss": 2.0895,
      "step": 291
    },
    {
      "epoch": 0.5956144824069353,
      "grad_norm": 0.3104468584060669,
      "learning_rate": 0.00016111140969350503,
      "loss": 1.6566,
      "step": 292
    },
    {
      "epoch": 0.5976542580316165,
      "grad_norm": 0.32697245478630066,
      "learning_rate": 0.00016085472837268502,
      "loss": 1.7631,
      "step": 293
    },
    {
      "epoch": 0.5996940336562978,
      "grad_norm": 0.3330870270729065,
      "learning_rate": 0.00016059740871456036,
      "loss": 1.6047,
      "step": 294
    },
    {
      "epoch": 0.6017338092809791,
      "grad_norm": 0.3144790828227997,
      "learning_rate": 0.00016033945341829248,
      "loss": 1.5975,
      "step": 295
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": 0.32482099533081055,
      "learning_rate": 0.00016008086518971037,
      "loss": 1.9879,
      "step": 296
    },
    {
      "epoch": 0.6058133605303416,
      "grad_norm": 0.320336252450943,
      "learning_rate": 0.0001598216467412822,
      "loss": 1.9723,
      "step": 297
    },
    {
      "epoch": 0.6078531361550229,
      "grad_norm": 0.2934703528881073,
      "learning_rate": 0.00015956180079208682,
      "loss": 1.7771,
      "step": 298
    },
    {
      "epoch": 0.6098929117797043,
      "grad_norm": 0.3081587851047516,
      "learning_rate": 0.0001593013300677853,
      "loss": 1.869,
      "step": 299
    },
    {
      "epoch": 0.6119326874043856,
      "grad_norm": 0.30365437269210815,
      "learning_rate": 0.00015904023730059228,
      "loss": 1.795,
      "step": 300
    },
    {
      "epoch": 0.6139724630290668,
      "grad_norm": 0.3306022882461548,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.8786,
      "step": 301
    },
    {
      "epoch": 0.6160122386537481,
      "grad_norm": 0.3081189692020416,
      "learning_rate": 0.00015851619659898623,
      "loss": 1.8389,
      "step": 302
    },
    {
      "epoch": 0.6180520142784294,
      "grad_norm": 0.3126586973667145,
      "learning_rate": 0.00015825325416151222,
      "loss": 1.8404,
      "step": 303
    },
    {
      "epoch": 0.6200917899031106,
      "grad_norm": 0.2832873463630676,
      "learning_rate": 0.000157989700674967,
      "loss": 1.9894,
      "step": 304
    },
    {
      "epoch": 0.6221315655277919,
      "grad_norm": 0.3080177903175354,
      "learning_rate": 0.00015772553890390197,
      "loss": 1.9813,
      "step": 305
    },
    {
      "epoch": 0.6241713411524732,
      "grad_norm": 0.30326464772224426,
      "learning_rate": 0.00015746077161924905,
      "loss": 1.7597,
      "step": 306
    },
    {
      "epoch": 0.6262111167771545,
      "grad_norm": 0.3071492910385132,
      "learning_rate": 0.00015719540159829184,
      "loss": 1.8149,
      "step": 307
    },
    {
      "epoch": 0.6282508924018358,
      "grad_norm": 0.3333245515823364,
      "learning_rate": 0.00015692943162463628,
      "loss": 1.9806,
      "step": 308
    },
    {
      "epoch": 0.6302906680265171,
      "grad_norm": 0.2858702838420868,
      "learning_rate": 0.0001566628644881815,
      "loss": 1.7616,
      "step": 309
    },
    {
      "epoch": 0.6323304436511984,
      "grad_norm": 0.27514535188674927,
      "learning_rate": 0.00015639570298509064,
      "loss": 1.7516,
      "step": 310
    },
    {
      "epoch": 0.6343702192758797,
      "grad_norm": 0.29323917627334595,
      "learning_rate": 0.00015612794991776147,
      "loss": 1.8444,
      "step": 311
    },
    {
      "epoch": 0.6364099949005609,
      "grad_norm": 0.3227652907371521,
      "learning_rate": 0.00015585960809479696,
      "loss": 1.8715,
      "step": 312
    },
    {
      "epoch": 0.6384497705252422,
      "grad_norm": 0.2898751497268677,
      "learning_rate": 0.00015559068033097582,
      "loss": 1.9242,
      "step": 313
    },
    {
      "epoch": 0.6404895461499235,
      "grad_norm": 0.2990049421787262,
      "learning_rate": 0.00015532116944722308,
      "loss": 1.7412,
      "step": 314
    },
    {
      "epoch": 0.6425293217746048,
      "grad_norm": 0.28128162026405334,
      "learning_rate": 0.00015505107827058036,
      "loss": 1.7801,
      "step": 315
    },
    {
      "epoch": 0.644569097399286,
      "grad_norm": 0.32478880882263184,
      "learning_rate": 0.0001547804096341763,
      "loss": 1.681,
      "step": 316
    },
    {
      "epoch": 0.6466088730239674,
      "grad_norm": 0.31724509596824646,
      "learning_rate": 0.00015450916637719684,
      "loss": 1.9405,
      "step": 317
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.36439332365989685,
      "learning_rate": 0.00015423735134485536,
      "loss": 1.7013,
      "step": 318
    },
    {
      "epoch": 0.65068842427333,
      "grad_norm": 0.3085692226886749,
      "learning_rate": 0.00015396496738836292,
      "loss": 1.7641,
      "step": 319
    },
    {
      "epoch": 0.6527281998980112,
      "grad_norm": 0.2774830758571625,
      "learning_rate": 0.0001536920173648984,
      "loss": 1.6727,
      "step": 320
    },
    {
      "epoch": 0.6547679755226925,
      "grad_norm": 0.3212391138076782,
      "learning_rate": 0.0001534185041375783,
      "loss": 1.7221,
      "step": 321
    },
    {
      "epoch": 0.6568077511473738,
      "grad_norm": 0.30237263441085815,
      "learning_rate": 0.00015314443057542703,
      "loss": 1.7456,
      "step": 322
    },
    {
      "epoch": 0.658847526772055,
      "grad_norm": 0.2800453305244446,
      "learning_rate": 0.00015286979955334652,
      "loss": 1.7978,
      "step": 323
    },
    {
      "epoch": 0.6608873023967363,
      "grad_norm": 0.28402194380760193,
      "learning_rate": 0.00015259461395208628,
      "loss": 1.8785,
      "step": 324
    },
    {
      "epoch": 0.6629270780214176,
      "grad_norm": 0.3377262353897095,
      "learning_rate": 0.000152318876658213,
      "loss": 1.7113,
      "step": 325
    },
    {
      "epoch": 0.664966853646099,
      "grad_norm": 0.376544326543808,
      "learning_rate": 0.00015204259056408046,
      "loss": 1.6237,
      "step": 326
    },
    {
      "epoch": 0.6670066292707802,
      "grad_norm": 0.3138863742351532,
      "learning_rate": 0.00015176575856779904,
      "loss": 1.8357,
      "step": 327
    },
    {
      "epoch": 0.6690464048954615,
      "grad_norm": 0.40277865529060364,
      "learning_rate": 0.00015148838357320537,
      "loss": 1.9038,
      "step": 328
    },
    {
      "epoch": 0.6710861805201428,
      "grad_norm": 0.2998698055744171,
      "learning_rate": 0.0001512104684898319,
      "loss": 1.7583,
      "step": 329
    },
    {
      "epoch": 0.6731259561448241,
      "grad_norm": 0.33020147681236267,
      "learning_rate": 0.00015093201623287631,
      "loss": 1.7446,
      "step": 330
    },
    {
      "epoch": 0.6751657317695053,
      "grad_norm": 0.3545725643634796,
      "learning_rate": 0.00015065302972317108,
      "loss": 1.8882,
      "step": 331
    },
    {
      "epoch": 0.6772055073941866,
      "grad_norm": 0.2989177107810974,
      "learning_rate": 0.00015037351188715265,
      "loss": 1.7751,
      "step": 332
    },
    {
      "epoch": 0.6792452830188679,
      "grad_norm": 0.3225865662097931,
      "learning_rate": 0.00015009346565683087,
      "loss": 1.8539,
      "step": 333
    },
    {
      "epoch": 0.6812850586435492,
      "grad_norm": 0.31957486271858215,
      "learning_rate": 0.00014981289396975817,
      "loss": 1.6078,
      "step": 334
    },
    {
      "epoch": 0.6833248342682305,
      "grad_norm": 0.323512464761734,
      "learning_rate": 0.00014953179976899878,
      "loss": 1.9539,
      "step": 335
    },
    {
      "epoch": 0.6853646098929118,
      "grad_norm": 0.3451762795448303,
      "learning_rate": 0.00014925018600309785,
      "loss": 1.8435,
      "step": 336
    },
    {
      "epoch": 0.6874043855175931,
      "grad_norm": 0.3474057614803314,
      "learning_rate": 0.0001489680556260505,
      "loss": 1.8385,
      "step": 337
    },
    {
      "epoch": 0.6894441611422744,
      "grad_norm": 0.3119589686393738,
      "learning_rate": 0.00014868541159727096,
      "loss": 1.7582,
      "step": 338
    },
    {
      "epoch": 0.6914839367669556,
      "grad_norm": 0.3289264738559723,
      "learning_rate": 0.0001484022568815613,
      "loss": 1.8391,
      "step": 339
    },
    {
      "epoch": 0.6935237123916369,
      "grad_norm": 0.32644519209861755,
      "learning_rate": 0.00014811859444908052,
      "loss": 1.7676,
      "step": 340
    },
    {
      "epoch": 0.6955634880163182,
      "grad_norm": 0.2529926002025604,
      "learning_rate": 0.00014783442727531328,
      "loss": 1.6483,
      "step": 341
    },
    {
      "epoch": 0.6976032636409994,
      "grad_norm": 0.39409515261650085,
      "learning_rate": 0.00014754975834103877,
      "loss": 1.8951,
      "step": 342
    },
    {
      "epoch": 0.6996430392656807,
      "grad_norm": 0.312379390001297,
      "learning_rate": 0.00014726459063229945,
      "loss": 1.8388,
      "step": 343
    },
    {
      "epoch": 0.7016828148903621,
      "grad_norm": 0.3048081696033478,
      "learning_rate": 0.00014697892714036958,
      "loss": 1.9482,
      "step": 344
    },
    {
      "epoch": 0.7037225905150434,
      "grad_norm": 0.37214845418930054,
      "learning_rate": 0.00014669277086172406,
      "loss": 1.8466,
      "step": 345
    },
    {
      "epoch": 0.7057623661397247,
      "grad_norm": 0.3273617923259735,
      "learning_rate": 0.00014640612479800686,
      "loss": 1.5934,
      "step": 346
    },
    {
      "epoch": 0.7078021417644059,
      "grad_norm": 0.3283670246601105,
      "learning_rate": 0.00014611899195599953,
      "loss": 1.7837,
      "step": 347
    },
    {
      "epoch": 0.7098419173890872,
      "grad_norm": 0.38148233294487,
      "learning_rate": 0.00014583137534758967,
      "loss": 1.8952,
      "step": 348
    },
    {
      "epoch": 0.7118816930137685,
      "grad_norm": 0.35573315620422363,
      "learning_rate": 0.0001455432779897395,
      "loss": 1.6698,
      "step": 349
    },
    {
      "epoch": 0.7139214686384497,
      "grad_norm": 0.362224280834198,
      "learning_rate": 0.00014525470290445392,
      "loss": 1.7698,
      "step": 350
    },
    {
      "epoch": 0.715961244263131,
      "grad_norm": 0.3312818706035614,
      "learning_rate": 0.00014496565311874902,
      "loss": 1.7951,
      "step": 351
    },
    {
      "epoch": 0.7180010198878123,
      "grad_norm": 0.3737257719039917,
      "learning_rate": 0.00014467613166462023,
      "loss": 1.9562,
      "step": 352
    },
    {
      "epoch": 0.7200407955124937,
      "grad_norm": 0.37132444977760315,
      "learning_rate": 0.0001443861415790107,
      "loss": 1.9022,
      "step": 353
    },
    {
      "epoch": 0.7220805711371749,
      "grad_norm": 0.30398017168045044,
      "learning_rate": 0.00014409568590377918,
      "loss": 2.0578,
      "step": 354
    },
    {
      "epoch": 0.7241203467618562,
      "grad_norm": 0.3135487139225006,
      "learning_rate": 0.00014380476768566824,
      "loss": 1.777,
      "step": 355
    },
    {
      "epoch": 0.7261601223865375,
      "grad_norm": 0.3089943826198578,
      "learning_rate": 0.00014351338997627234,
      "loss": 1.638,
      "step": 356
    },
    {
      "epoch": 0.7281998980112188,
      "grad_norm": 0.2791310250759125,
      "learning_rate": 0.00014322155583200576,
      "loss": 1.7786,
      "step": 357
    },
    {
      "epoch": 0.7302396736359,
      "grad_norm": 0.30986955761909485,
      "learning_rate": 0.00014292926831407061,
      "loss": 1.7467,
      "step": 358
    },
    {
      "epoch": 0.7322794492605813,
      "grad_norm": 0.29783159494400024,
      "learning_rate": 0.0001426365304884246,
      "loss": 1.6486,
      "step": 359
    },
    {
      "epoch": 0.7343192248852626,
      "grad_norm": 0.29579076170921326,
      "learning_rate": 0.00014234334542574906,
      "loss": 1.665,
      "step": 360
    },
    {
      "epoch": 0.7363590005099439,
      "grad_norm": 0.31017670035362244,
      "learning_rate": 0.00014204971620141647,
      "loss": 1.7287,
      "step": 361
    },
    {
      "epoch": 0.7383987761346252,
      "grad_norm": 0.34222882986068726,
      "learning_rate": 0.00014175564589545854,
      "loss": 1.7475,
      "step": 362
    },
    {
      "epoch": 0.7404385517593065,
      "grad_norm": 0.2956671714782715,
      "learning_rate": 0.00014146113759253362,
      "loss": 1.757,
      "step": 363
    },
    {
      "epoch": 0.7424783273839878,
      "grad_norm": 0.35265278816223145,
      "learning_rate": 0.0001411661943818944,
      "loss": 1.6731,
      "step": 364
    },
    {
      "epoch": 0.744518103008669,
      "grad_norm": 0.3606823682785034,
      "learning_rate": 0.00014087081935735564,
      "loss": 1.8684,
      "step": 365
    },
    {
      "epoch": 0.7465578786333503,
      "grad_norm": 0.27310827374458313,
      "learning_rate": 0.00014057501561726157,
      "loss": 1.7656,
      "step": 366
    },
    {
      "epoch": 0.7485976542580316,
      "grad_norm": 0.3064682185649872,
      "learning_rate": 0.0001402787862644534,
      "loss": 1.7646,
      "step": 367
    },
    {
      "epoch": 0.7506374298827129,
      "grad_norm": 0.40648531913757324,
      "learning_rate": 0.0001399821344062369,
      "loss": 1.672,
      "step": 368
    },
    {
      "epoch": 0.7526772055073941,
      "grad_norm": 0.28727683424949646,
      "learning_rate": 0.00013968506315434974,
      "loss": 1.5766,
      "step": 369
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.30638012290000916,
      "learning_rate": 0.00013938757562492873,
      "loss": 1.6456,
      "step": 370
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 0.3163774311542511,
      "learning_rate": 0.0001390896749384773,
      "loss": 1.8618,
      "step": 371
    },
    {
      "epoch": 0.7587965323814381,
      "grad_norm": 0.36798760294914246,
      "learning_rate": 0.00013879136421983266,
      "loss": 2.1013,
      "step": 372
    },
    {
      "epoch": 0.7608363080061193,
      "grad_norm": 0.30383849143981934,
      "learning_rate": 0.00013849264659813312,
      "loss": 1.7117,
      "step": 373
    },
    {
      "epoch": 0.7628760836308006,
      "grad_norm": 0.35814371705055237,
      "learning_rate": 0.0001381935252067852,
      "loss": 1.9741,
      "step": 374
    },
    {
      "epoch": 0.7649158592554819,
      "grad_norm": 0.29710692167282104,
      "learning_rate": 0.00013789400318343068,
      "loss": 1.5538,
      "step": 375
    },
    {
      "epoch": 0.7669556348801632,
      "grad_norm": 0.30160966515541077,
      "learning_rate": 0.0001375940836699139,
      "loss": 1.7604,
      "step": 376
    },
    {
      "epoch": 0.7689954105048444,
      "grad_norm": 0.28164952993392944,
      "learning_rate": 0.0001372937698122487,
      "loss": 1.736,
      "step": 377
    },
    {
      "epoch": 0.7710351861295257,
      "grad_norm": 0.293729692697525,
      "learning_rate": 0.0001369930647605852,
      "loss": 1.9099,
      "step": 378
    },
    {
      "epoch": 0.7730749617542071,
      "grad_norm": 0.28284940123558044,
      "learning_rate": 0.00013669197166917723,
      "loss": 1.7251,
      "step": 379
    },
    {
      "epoch": 0.7751147373788884,
      "grad_norm": 0.26181384921073914,
      "learning_rate": 0.00013639049369634876,
      "loss": 1.6381,
      "step": 380
    },
    {
      "epoch": 0.7771545130035696,
      "grad_norm": 0.3301055431365967,
      "learning_rate": 0.00013608863400446113,
      "loss": 1.998,
      "step": 381
    },
    {
      "epoch": 0.7791942886282509,
      "grad_norm": 0.3116731643676758,
      "learning_rate": 0.00013578639575987958,
      "loss": 1.8277,
      "step": 382
    },
    {
      "epoch": 0.7812340642529322,
      "grad_norm": 0.30362340807914734,
      "learning_rate": 0.0001354837821329404,
      "loss": 1.888,
      "step": 383
    },
    {
      "epoch": 0.7832738398776135,
      "grad_norm": 0.29050615429878235,
      "learning_rate": 0.00013518079629791724,
      "loss": 1.7116,
      "step": 384
    },
    {
      "epoch": 0.7853136155022947,
      "grad_norm": 0.29679572582244873,
      "learning_rate": 0.00013487744143298822,
      "loss": 1.6066,
      "step": 385
    },
    {
      "epoch": 0.787353391126976,
      "grad_norm": 0.3293478488922119,
      "learning_rate": 0.0001345737207202023,
      "loss": 1.7222,
      "step": 386
    },
    {
      "epoch": 0.7893931667516573,
      "grad_norm": 0.34148016571998596,
      "learning_rate": 0.000134269637345446,
      "loss": 1.7243,
      "step": 387
    },
    {
      "epoch": 0.7914329423763387,
      "grad_norm": 0.31480157375335693,
      "learning_rate": 0.00013396519449841005,
      "loss": 1.8812,
      "step": 388
    },
    {
      "epoch": 0.7934727180010199,
      "grad_norm": 0.2998044192790985,
      "learning_rate": 0.0001336603953725559,
      "loss": 1.9205,
      "step": 389
    },
    {
      "epoch": 0.7955124936257012,
      "grad_norm": 0.33707278966903687,
      "learning_rate": 0.00013335524316508208,
      "loss": 1.9246,
      "step": 390
    },
    {
      "epoch": 0.7975522692503825,
      "grad_norm": 0.33658990263938904,
      "learning_rate": 0.00013304974107689087,
      "loss": 1.849,
      "step": 391
    },
    {
      "epoch": 0.7995920448750637,
      "grad_norm": 0.2800214886665344,
      "learning_rate": 0.00013274389231255466,
      "loss": 1.7607,
      "step": 392
    },
    {
      "epoch": 0.801631820499745,
      "grad_norm": 0.29528602957725525,
      "learning_rate": 0.00013243770008028224,
      "loss": 1.6146,
      "step": 393
    },
    {
      "epoch": 0.8036715961244263,
      "grad_norm": 0.316123902797699,
      "learning_rate": 0.00013213116759188523,
      "loss": 1.7578,
      "step": 394
    },
    {
      "epoch": 0.8057113717491076,
      "grad_norm": 0.339609295129776,
      "learning_rate": 0.0001318242980627444,
      "loss": 1.6968,
      "step": 395
    },
    {
      "epoch": 0.8077511473737888,
      "grad_norm": 0.29195457696914673,
      "learning_rate": 0.00013151709471177588,
      "loss": 1.6553,
      "step": 396
    },
    {
      "epoch": 0.8097909229984702,
      "grad_norm": 0.3093162477016449,
      "learning_rate": 0.00013120956076139746,
      "loss": 1.6833,
      "step": 397
    },
    {
      "epoch": 0.8118306986231515,
      "grad_norm": 0.343049019575119,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.717,
      "step": 398
    },
    {
      "epoch": 0.8138704742478328,
      "grad_norm": 0.30858704447746277,
      "learning_rate": 0.0001305935139693874,
      "loss": 1.5495,
      "step": 399
    },
    {
      "epoch": 0.815910249872514,
      "grad_norm": 0.28386467695236206,
      "learning_rate": 0.00013028500758979506,
      "loss": 1.8721,
      "step": 400
    },
    {
      "epoch": 0.8179500254971953,
      "grad_norm": 0.3261226713657379,
      "learning_rate": 0.00012997618353480377,
      "loss": 1.7956,
      "step": 401
    },
    {
      "epoch": 0.8199898011218766,
      "grad_norm": 0.3289451003074646,
      "learning_rate": 0.00012966704504383168,
      "loss": 1.7322,
      "step": 402
    },
    {
      "epoch": 0.8220295767465579,
      "grad_norm": 0.3098496198654175,
      "learning_rate": 0.00012935759535959528,
      "loss": 1.7224,
      "step": 403
    },
    {
      "epoch": 0.8240693523712391,
      "grad_norm": 0.2830435335636139,
      "learning_rate": 0.00012904783772807533,
      "loss": 1.7597,
      "step": 404
    },
    {
      "epoch": 0.8261091279959204,
      "grad_norm": 0.3040255010128021,
      "learning_rate": 0.00012873777539848283,
      "loss": 1.8111,
      "step": 405
    },
    {
      "epoch": 0.8281489036206018,
      "grad_norm": 0.30722421407699585,
      "learning_rate": 0.00012842741162322487,
      "loss": 1.6308,
      "step": 406
    },
    {
      "epoch": 0.8301886792452831,
      "grad_norm": 0.28365135192871094,
      "learning_rate": 0.00012811674965787056,
      "loss": 1.932,
      "step": 407
    },
    {
      "epoch": 0.8322284548699643,
      "grad_norm": 0.26628825068473816,
      "learning_rate": 0.00012780579276111702,
      "loss": 1.5047,
      "step": 408
    },
    {
      "epoch": 0.8342682304946456,
      "grad_norm": 0.3449050486087799,
      "learning_rate": 0.00012749454419475487,
      "loss": 1.9364,
      "step": 409
    },
    {
      "epoch": 0.8363080061193269,
      "grad_norm": 0.2961723208427429,
      "learning_rate": 0.0001271830072236343,
      "loss": 1.6638,
      "step": 410
    },
    {
      "epoch": 0.8383477817440081,
      "grad_norm": 0.2808418273925781,
      "learning_rate": 0.00012687118511563075,
      "loss": 1.6743,
      "step": 411
    },
    {
      "epoch": 0.8403875573686894,
      "grad_norm": 0.30065590143203735,
      "learning_rate": 0.0001265590811416105,
      "loss": 1.8681,
      "step": 412
    },
    {
      "epoch": 0.8424273329933707,
      "grad_norm": 0.311669260263443,
      "learning_rate": 0.0001262466985753967,
      "loss": 1.7563,
      "step": 413
    },
    {
      "epoch": 0.844467108618052,
      "grad_norm": 0.31335267424583435,
      "learning_rate": 0.0001259340406937345,
      "loss": 1.9591,
      "step": 414
    },
    {
      "epoch": 0.8465068842427333,
      "grad_norm": 0.306470662355423,
      "learning_rate": 0.00012562111077625722,
      "loss": 1.7165,
      "step": 415
    },
    {
      "epoch": 0.8485466598674146,
      "grad_norm": 0.278089314699173,
      "learning_rate": 0.00012530791210545162,
      "loss": 1.7441,
      "step": 416
    },
    {
      "epoch": 0.8505864354920959,
      "grad_norm": 0.28886333107948303,
      "learning_rate": 0.00012499444796662353,
      "loss": 1.7301,
      "step": 417
    },
    {
      "epoch": 0.8526262111167772,
      "grad_norm": 0.31261351704597473,
      "learning_rate": 0.0001246807216478634,
      "loss": 2.062,
      "step": 418
    },
    {
      "epoch": 0.8546659867414584,
      "grad_norm": 0.3184990882873535,
      "learning_rate": 0.00012436673644001197,
      "loss": 2.0039,
      "step": 419
    },
    {
      "epoch": 0.8567057623661397,
      "grad_norm": 0.28797486424446106,
      "learning_rate": 0.00012405249563662537,
      "loss": 1.5982,
      "step": 420
    },
    {
      "epoch": 0.858745537990821,
      "grad_norm": 0.32951340079307556,
      "learning_rate": 0.00012373800253394102,
      "loss": 1.6121,
      "step": 421
    },
    {
      "epoch": 0.8607853136155023,
      "grad_norm": 0.28868240118026733,
      "learning_rate": 0.00012342326043084266,
      "loss": 1.7456,
      "step": 422
    },
    {
      "epoch": 0.8628250892401835,
      "grad_norm": 0.3051716387271881,
      "learning_rate": 0.00012310827262882615,
      "loss": 1.7698,
      "step": 423
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.3326285183429718,
      "learning_rate": 0.00012279304243196436,
      "loss": 1.7834,
      "step": 424
    },
    {
      "epoch": 0.8669046404895462,
      "grad_norm": 0.3435324430465698,
      "learning_rate": 0.00012247757314687297,
      "loss": 1.7208,
      "step": 425
    },
    {
      "epoch": 0.8689444161142275,
      "grad_norm": 0.35181501507759094,
      "learning_rate": 0.00012216186808267546,
      "loss": 1.7401,
      "step": 426
    },
    {
      "epoch": 0.8709841917389087,
      "grad_norm": 0.30371034145355225,
      "learning_rate": 0.00012184593055096854,
      "loss": 1.655,
      "step": 427
    },
    {
      "epoch": 0.87302396736359,
      "grad_norm": 0.29926905035972595,
      "learning_rate": 0.0001215297638657875,
      "loss": 1.686,
      "step": 428
    },
    {
      "epoch": 0.8750637429882713,
      "grad_norm": 0.32623806595802307,
      "learning_rate": 0.0001212133713435712,
      "loss": 1.6556,
      "step": 429
    },
    {
      "epoch": 0.8771035186129525,
      "grad_norm": 0.32232004404067993,
      "learning_rate": 0.00012089675630312754,
      "loss": 1.7736,
      "step": 430
    },
    {
      "epoch": 0.8791432942376338,
      "grad_norm": 0.3392092287540436,
      "learning_rate": 0.00012057992206559837,
      "loss": 1.8754,
      "step": 431
    },
    {
      "epoch": 0.8811830698623151,
      "grad_norm": 0.34549203515052795,
      "learning_rate": 0.00012026287195442503,
      "loss": 1.7624,
      "step": 432
    },
    {
      "epoch": 0.8832228454869965,
      "grad_norm": 0.3612309694290161,
      "learning_rate": 0.00011994560929531309,
      "loss": 1.6408,
      "step": 433
    },
    {
      "epoch": 0.8852626211116777,
      "grad_norm": 0.30541735887527466,
      "learning_rate": 0.00011962813741619777,
      "loss": 1.6785,
      "step": 434
    },
    {
      "epoch": 0.887302396736359,
      "grad_norm": 0.2894171476364136,
      "learning_rate": 0.00011931045964720881,
      "loss": 1.6609,
      "step": 435
    },
    {
      "epoch": 0.8893421723610403,
      "grad_norm": 0.31241005659103394,
      "learning_rate": 0.0001189925793206357,
      "loss": 1.7421,
      "step": 436
    },
    {
      "epoch": 0.8913819479857216,
      "grad_norm": 0.36774688959121704,
      "learning_rate": 0.00011867449977089265,
      "loss": 1.902,
      "step": 437
    },
    {
      "epoch": 0.8934217236104028,
      "grad_norm": 0.3658794164657593,
      "learning_rate": 0.00011835622433448361,
      "loss": 1.9666,
      "step": 438
    },
    {
      "epoch": 0.8954614992350841,
      "grad_norm": 0.33153945207595825,
      "learning_rate": 0.00011803775634996734,
      "loss": 1.6772,
      "step": 439
    },
    {
      "epoch": 0.8975012748597654,
      "grad_norm": 0.34272125363349915,
      "learning_rate": 0.0001177190991579223,
      "loss": 1.7911,
      "step": 440
    },
    {
      "epoch": 0.8995410504844467,
      "grad_norm": 0.3852793276309967,
      "learning_rate": 0.00011740025610091159,
      "loss": 1.7358,
      "step": 441
    },
    {
      "epoch": 0.901580826109128,
      "grad_norm": 0.33693379163742065,
      "learning_rate": 0.00011708123052344804,
      "loss": 1.7078,
      "step": 442
    },
    {
      "epoch": 0.9036206017338093,
      "grad_norm": 0.35405832529067993,
      "learning_rate": 0.00011676202577195901,
      "loss": 1.6454,
      "step": 443
    },
    {
      "epoch": 0.9056603773584906,
      "grad_norm": 0.38638654351234436,
      "learning_rate": 0.0001164426451947513,
      "loss": 1.7611,
      "step": 444
    },
    {
      "epoch": 0.9077001529831719,
      "grad_norm": 0.3415047824382782,
      "learning_rate": 0.00011612309214197599,
      "loss": 1.6206,
      "step": 445
    },
    {
      "epoch": 0.9097399286078531,
      "grad_norm": 0.3022047281265259,
      "learning_rate": 0.00011580336996559343,
      "loss": 1.8017,
      "step": 446
    },
    {
      "epoch": 0.9117797042325344,
      "grad_norm": 0.3650202751159668,
      "learning_rate": 0.00011548348201933798,
      "loss": 1.6507,
      "step": 447
    },
    {
      "epoch": 0.9138194798572157,
      "grad_norm": 0.44297119975090027,
      "learning_rate": 0.00011516343165868279,
      "loss": 1.8607,
      "step": 448
    },
    {
      "epoch": 0.915859255481897,
      "grad_norm": 0.3508884906768799,
      "learning_rate": 0.00011484322224080472,
      "loss": 1.6549,
      "step": 449
    },
    {
      "epoch": 0.9178990311065782,
      "grad_norm": 0.31238260865211487,
      "learning_rate": 0.00011452285712454904,
      "loss": 1.603,
      "step": 450
    },
    {
      "epoch": 0.9199388067312596,
      "grad_norm": 0.36678579449653625,
      "learning_rate": 0.00011420233967039422,
      "loss": 1.7984,
      "step": 451
    },
    {
      "epoch": 0.9219785823559409,
      "grad_norm": 0.3467310965061188,
      "learning_rate": 0.00011388167324041669,
      "loss": 1.7691,
      "step": 452
    },
    {
      "epoch": 0.9240183579806222,
      "grad_norm": 0.2987074553966522,
      "learning_rate": 0.00011356086119825553,
      "loss": 1.617,
      "step": 453
    },
    {
      "epoch": 0.9260581336053034,
      "grad_norm": 0.2808781862258911,
      "learning_rate": 0.00011323990690907733,
      "loss": 1.6362,
      "step": 454
    },
    {
      "epoch": 0.9280979092299847,
      "grad_norm": 0.356692910194397,
      "learning_rate": 0.00011291881373954065,
      "loss": 1.7279,
      "step": 455
    },
    {
      "epoch": 0.930137684854666,
      "grad_norm": 0.3478505611419678,
      "learning_rate": 0.00011259758505776092,
      "loss": 1.6011,
      "step": 456
    },
    {
      "epoch": 0.9321774604793472,
      "grad_norm": 0.3229358196258545,
      "learning_rate": 0.00011227622423327502,
      "loss": 1.7874,
      "step": 457
    },
    {
      "epoch": 0.9342172361040285,
      "grad_norm": 0.30234581232070923,
      "learning_rate": 0.0001119547346370059,
      "loss": 1.6098,
      "step": 458
    },
    {
      "epoch": 0.9362570117287098,
      "grad_norm": 0.356154203414917,
      "learning_rate": 0.00011163311964122734,
      "loss": 1.8164,
      "step": 459
    },
    {
      "epoch": 0.9382967873533912,
      "grad_norm": 0.35306453704833984,
      "learning_rate": 0.00011131138261952845,
      "loss": 1.8833,
      "step": 460
    },
    {
      "epoch": 0.9403365629780724,
      "grad_norm": 0.29947206377983093,
      "learning_rate": 0.00011098952694677829,
      "loss": 1.6675,
      "step": 461
    },
    {
      "epoch": 0.9423763386027537,
      "grad_norm": 0.3290257155895233,
      "learning_rate": 0.00011066755599909064,
      "loss": 1.7463,
      "step": 462
    },
    {
      "epoch": 0.944416114227435,
      "grad_norm": 0.32332712411880493,
      "learning_rate": 0.00011034547315378838,
      "loss": 1.5748,
      "step": 463
    },
    {
      "epoch": 0.9464558898521163,
      "grad_norm": 0.40129172801971436,
      "learning_rate": 0.00011002328178936811,
      "loss": 1.6484,
      "step": 464
    },
    {
      "epoch": 0.9484956654767975,
      "grad_norm": 0.34289342164993286,
      "learning_rate": 0.00010970098528546481,
      "loss": 1.7533,
      "step": 465
    },
    {
      "epoch": 0.9505354411014788,
      "grad_norm": 0.30435630679130554,
      "learning_rate": 0.00010937858702281631,
      "loss": 1.8037,
      "step": 466
    },
    {
      "epoch": 0.9525752167261601,
      "grad_norm": 0.29155558347702026,
      "learning_rate": 0.00010905609038322779,
      "loss": 1.5628,
      "step": 467
    },
    {
      "epoch": 0.9546149923508415,
      "grad_norm": 0.31822967529296875,
      "learning_rate": 0.0001087334987495364,
      "loss": 1.7222,
      "step": 468
    },
    {
      "epoch": 0.9566547679755227,
      "grad_norm": 0.2868748605251312,
      "learning_rate": 0.00010841081550557578,
      "loss": 1.86,
      "step": 469
    },
    {
      "epoch": 0.958694543600204,
      "grad_norm": 0.3066910207271576,
      "learning_rate": 0.00010808804403614043,
      "loss": 1.7278,
      "step": 470
    },
    {
      "epoch": 0.9607343192248853,
      "grad_norm": 0.28570494055747986,
      "learning_rate": 0.00010776518772695034,
      "loss": 1.7328,
      "step": 471
    },
    {
      "epoch": 0.9627740948495666,
      "grad_norm": 0.28472283482551575,
      "learning_rate": 0.0001074422499646154,
      "loss": 1.7311,
      "step": 472
    },
    {
      "epoch": 0.9648138704742478,
      "grad_norm": 0.30987489223480225,
      "learning_rate": 0.00010711923413659995,
      "loss": 1.7628,
      "step": 473
    },
    {
      "epoch": 0.9668536460989291,
      "grad_norm": 0.32321545481681824,
      "learning_rate": 0.00010679614363118717,
      "loss": 1.8949,
      "step": 474
    },
    {
      "epoch": 0.9688934217236104,
      "grad_norm": 0.32413583993911743,
      "learning_rate": 0.00010647298183744359,
      "loss": 1.6379,
      "step": 475
    },
    {
      "epoch": 0.9709331973482916,
      "grad_norm": 0.3008846044540405,
      "learning_rate": 0.0001061497521451835,
      "loss": 1.7546,
      "step": 476
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 0.3248610198497772,
      "learning_rate": 0.00010582645794493337,
      "loss": 1.8915,
      "step": 477
    },
    {
      "epoch": 0.9750127485976543,
      "grad_norm": 0.3182532489299774,
      "learning_rate": 0.00010550310262789649,
      "loss": 1.8771,
      "step": 478
    },
    {
      "epoch": 0.9770525242223356,
      "grad_norm": 0.317730188369751,
      "learning_rate": 0.00010517968958591705,
      "loss": 1.7348,
      "step": 479
    },
    {
      "epoch": 0.9790922998470168,
      "grad_norm": 0.3585616648197174,
      "learning_rate": 0.00010485622221144484,
      "loss": 1.6916,
      "step": 480
    },
    {
      "epoch": 0.9811320754716981,
      "grad_norm": 0.2927946150302887,
      "learning_rate": 0.00010453270389749957,
      "loss": 1.7284,
      "step": 481
    },
    {
      "epoch": 0.9831718510963794,
      "grad_norm": 0.2869007885456085,
      "learning_rate": 0.00010420913803763521,
      "loss": 1.7312,
      "step": 482
    },
    {
      "epoch": 0.9852116267210607,
      "grad_norm": 0.34274759888648987,
      "learning_rate": 0.00010388552802590462,
      "loss": 1.6405,
      "step": 483
    },
    {
      "epoch": 0.9872514023457419,
      "grad_norm": 0.3203391134738922,
      "learning_rate": 0.00010356187725682359,
      "loss": 1.666,
      "step": 484
    },
    {
      "epoch": 0.9892911779704232,
      "grad_norm": 0.3370297849178314,
      "learning_rate": 0.00010323818912533561,
      "loss": 1.757,
      "step": 485
    },
    {
      "epoch": 0.9913309535951046,
      "grad_norm": 0.3095087707042694,
      "learning_rate": 0.00010291446702677599,
      "loss": 1.7015,
      "step": 486
    },
    {
      "epoch": 0.9933707292197859,
      "grad_norm": 0.33249640464782715,
      "learning_rate": 0.00010259071435683636,
      "loss": 1.9363,
      "step": 487
    },
    {
      "epoch": 0.9954105048444671,
      "grad_norm": 0.3441324830055237,
      "learning_rate": 0.000102266934511529,
      "loss": 1.5975,
      "step": 488
    },
    {
      "epoch": 0.9974502804691484,
      "grad_norm": 0.31439101696014404,
      "learning_rate": 0.00010194313088715135,
      "loss": 1.7025,
      "step": 489
    },
    {
      "epoch": 0.9994900560938297,
      "grad_norm": 0.34762027859687805,
      "learning_rate": 0.00010161930688025017,
      "loss": 1.7399,
      "step": 490
    },
    {
      "epoch": 0.9994900560938297,
      "eval_loss": 1.752766489982605,
      "eval_runtime": 57.5155,
      "eval_samples_per_second": 14.361,
      "eval_steps_per_second": 1.808,
      "step": 490
    }
  ],
  "logging_steps": 1,
  "max_steps": 980,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 490,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.735357947750646e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}