{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.48685491723466406,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019474196689386564,
      "grad_norm": 0.6627452969551086,
      "learning_rate": 2.5e-05,
      "loss": 1.8562,
      "step": 1
    },
    {
      "epoch": 0.0038948393378773127,
      "grad_norm": 0.9325484037399292,
      "learning_rate": 5e-05,
      "loss": 2.0532,
      "step": 2
    },
    {
      "epoch": 0.005842259006815969,
      "grad_norm": 0.8353978991508484,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.8732,
      "step": 3
    },
    {
      "epoch": 0.007789678675754625,
      "grad_norm": 0.6053460836410522,
      "learning_rate": 0.0001,
      "loss": 1.942,
      "step": 4
    },
    {
      "epoch": 0.009737098344693282,
      "grad_norm": 0.5565560460090637,
      "learning_rate": 0.000125,
      "loss": 1.6511,
      "step": 5
    },
    {
      "epoch": 0.011684518013631937,
      "grad_norm": 0.9751281142234802,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.9445,
      "step": 6
    },
    {
      "epoch": 0.013631937682570594,
      "grad_norm": 0.730299711227417,
      "learning_rate": 0.000175,
      "loss": 1.3815,
      "step": 7
    },
    {
      "epoch": 0.01557935735150925,
      "grad_norm": 0.753030002117157,
      "learning_rate": 0.0002,
      "loss": 1.1519,
      "step": 8
    },
    {
      "epoch": 0.017526777020447908,
      "grad_norm": 0.8523620367050171,
      "learning_rate": 0.00019917355371900828,
      "loss": 1.2913,
      "step": 9
    },
    {
      "epoch": 0.019474196689386564,
      "grad_norm": 1.002160906791687,
      "learning_rate": 0.00019834710743801655,
      "loss": 0.8663,
      "step": 10
    },
    {
      "epoch": 0.021421616358325218,
      "grad_norm": 1.114942193031311,
      "learning_rate": 0.00019752066115702482,
      "loss": 0.7233,
      "step": 11
    },
    {
      "epoch": 0.023369036027263874,
      "grad_norm": 1.1557896137237549,
      "learning_rate": 0.0001966942148760331,
      "loss": 0.9432,
      "step": 12
    },
    {
      "epoch": 0.02531645569620253,
      "grad_norm": 2.1235923767089844,
      "learning_rate": 0.00019586776859504133,
      "loss": 0.6598,
      "step": 13
    },
    {
      "epoch": 0.027263875365141188,
      "grad_norm": 1.2073708772659302,
      "learning_rate": 0.0001950413223140496,
      "loss": 1.0136,
      "step": 14
    },
    {
      "epoch": 0.029211295034079845,
      "grad_norm": 1.1807072162628174,
      "learning_rate": 0.00019421487603305787,
      "loss": 1.0244,
      "step": 15
    },
    {
      "epoch": 0.0311587147030185,
      "grad_norm": 0.9304102659225464,
      "learning_rate": 0.0001933884297520661,
      "loss": 0.5349,
      "step": 16
    },
    {
      "epoch": 0.033106134371957155,
      "grad_norm": 0.7814887762069702,
      "learning_rate": 0.00019256198347107438,
      "loss": 0.5058,
      "step": 17
    },
    {
      "epoch": 0.035053554040895815,
      "grad_norm": 0.8314672708511353,
      "learning_rate": 0.00019173553719008265,
      "loss": 0.3814,
      "step": 18
    },
    {
      "epoch": 0.03700097370983447,
      "grad_norm": 0.916557788848877,
      "learning_rate": 0.00019090909090909092,
      "loss": 0.4953,
      "step": 19
    },
    {
      "epoch": 0.03894839337877313,
      "grad_norm": 0.9891867637634277,
      "learning_rate": 0.0001900826446280992,
      "loss": 0.932,
      "step": 20
    },
    {
      "epoch": 0.04089581304771178,
      "grad_norm": 0.9992872476577759,
      "learning_rate": 0.00018925619834710743,
      "loss": 0.8751,
      "step": 21
    },
    {
      "epoch": 0.042843232716650435,
      "grad_norm": 0.5688315033912659,
      "learning_rate": 0.0001884297520661157,
      "loss": 0.3556,
      "step": 22
    },
    {
      "epoch": 0.044790652385589096,
      "grad_norm": 0.5576704144477844,
      "learning_rate": 0.00018760330578512397,
      "loss": 0.2855,
      "step": 23
    },
    {
      "epoch": 0.04673807205452775,
      "grad_norm": 0.8203558921813965,
      "learning_rate": 0.00018677685950413224,
      "loss": 0.9009,
      "step": 24
    },
    {
      "epoch": 0.04868549172346641,
      "grad_norm": 0.7509244680404663,
      "learning_rate": 0.0001859504132231405,
      "loss": 0.5587,
      "step": 25
    },
    {
      "epoch": 0.05063291139240506,
      "grad_norm": 0.9155460596084595,
      "learning_rate": 0.00018512396694214878,
      "loss": 0.7122,
      "step": 26
    },
    {
      "epoch": 0.05258033106134372,
      "grad_norm": 0.5604537129402161,
      "learning_rate": 0.00018429752066115705,
      "loss": 0.4308,
      "step": 27
    },
    {
      "epoch": 0.054527750730282376,
      "grad_norm": 0.902310311794281,
      "learning_rate": 0.00018347107438016532,
      "loss": 0.7039,
      "step": 28
    },
    {
      "epoch": 0.05647517039922103,
      "grad_norm": 0.6863579154014587,
      "learning_rate": 0.00018264462809917356,
      "loss": 0.7063,
      "step": 29
    },
    {
      "epoch": 0.05842259006815969,
      "grad_norm": 0.6778506636619568,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.6357,
      "step": 30
    },
    {
      "epoch": 0.06037000973709834,
      "grad_norm": 0.5920571684837341,
      "learning_rate": 0.00018099173553719008,
      "loss": 0.4388,
      "step": 31
    },
    {
      "epoch": 0.062317429406037,
      "grad_norm": 0.5040196776390076,
      "learning_rate": 0.00018016528925619835,
      "loss": 0.4409,
      "step": 32
    },
    {
      "epoch": 0.06426484907497566,
      "grad_norm": 0.5752211809158325,
      "learning_rate": 0.00017933884297520662,
      "loss": 0.4516,
      "step": 33
    },
    {
      "epoch": 0.06621226874391431,
      "grad_norm": 0.7298389673233032,
      "learning_rate": 0.00017851239669421489,
      "loss": 0.571,
      "step": 34
    },
    {
      "epoch": 0.06815968841285297,
      "grad_norm": 0.7012993693351746,
      "learning_rate": 0.00017768595041322316,
      "loss": 0.4716,
      "step": 35
    },
    {
      "epoch": 0.07010710808179163,
      "grad_norm": 0.7051262855529785,
      "learning_rate": 0.00017685950413223143,
      "loss": 0.6295,
      "step": 36
    },
    {
      "epoch": 0.07205452775073028,
      "grad_norm": 0.7011151909828186,
      "learning_rate": 0.00017603305785123967,
      "loss": 0.4605,
      "step": 37
    },
    {
      "epoch": 0.07400194741966894,
      "grad_norm": 1.0121755599975586,
      "learning_rate": 0.00017520661157024794,
      "loss": 0.7132,
      "step": 38
    },
    {
      "epoch": 0.0759493670886076,
      "grad_norm": 1.274100422859192,
      "learning_rate": 0.0001743801652892562,
      "loss": 1.0475,
      "step": 39
    },
    {
      "epoch": 0.07789678675754626,
      "grad_norm": 1.2915902137756348,
      "learning_rate": 0.00017355371900826448,
      "loss": 0.9126,
      "step": 40
    },
    {
      "epoch": 0.0798442064264849,
      "grad_norm": 1.1296463012695312,
      "learning_rate": 0.00017272727272727275,
      "loss": 1.0518,
      "step": 41
    },
    {
      "epoch": 0.08179162609542356,
      "grad_norm": 0.7432142496109009,
      "learning_rate": 0.00017190082644628102,
      "loss": 0.5967,
      "step": 42
    },
    {
      "epoch": 0.08373904576436222,
      "grad_norm": 0.878311812877655,
      "learning_rate": 0.00017107438016528926,
      "loss": 0.6643,
      "step": 43
    },
    {
      "epoch": 0.08568646543330087,
      "grad_norm": 1.0814746618270874,
      "learning_rate": 0.00017024793388429753,
      "loss": 0.7934,
      "step": 44
    },
    {
      "epoch": 0.08763388510223953,
      "grad_norm": 1.0332353115081787,
      "learning_rate": 0.00016942148760330577,
      "loss": 0.7566,
      "step": 45
    },
    {
      "epoch": 0.08958130477117819,
      "grad_norm": 0.952813446521759,
      "learning_rate": 0.00016859504132231404,
      "loss": 0.6161,
      "step": 46
    },
    {
      "epoch": 0.09152872444011685,
      "grad_norm": 0.9768489003181458,
      "learning_rate": 0.0001677685950413223,
      "loss": 0.8178,
      "step": 47
    },
    {
      "epoch": 0.0934761441090555,
      "grad_norm": 0.7100651860237122,
      "learning_rate": 0.00016694214876033058,
      "loss": 0.6014,
      "step": 48
    },
    {
      "epoch": 0.09542356377799416,
      "grad_norm": 0.906511127948761,
      "learning_rate": 0.00016611570247933885,
      "loss": 0.952,
      "step": 49
    },
    {
      "epoch": 0.09737098344693282,
      "grad_norm": 1.0189696550369263,
      "learning_rate": 0.00016528925619834712,
      "loss": 0.8181,
      "step": 50
    },
    {
      "epoch": 0.09931840311587146,
      "grad_norm": 0.8355782628059387,
      "learning_rate": 0.0001644628099173554,
      "loss": 0.6442,
      "step": 51
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 0.747944176197052,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.5864,
      "step": 52
    },
    {
      "epoch": 0.10321324245374879,
      "grad_norm": 0.6874829530715942,
      "learning_rate": 0.0001628099173553719,
      "loss": 0.5721,
      "step": 53
    },
    {
      "epoch": 0.10516066212268745,
      "grad_norm": 0.8766732811927795,
      "learning_rate": 0.00016198347107438017,
      "loss": 1.1118,
      "step": 54
    },
    {
      "epoch": 0.10710808179162609,
      "grad_norm": 0.503648579120636,
      "learning_rate": 0.00016115702479338844,
      "loss": 0.4632,
      "step": 55
    },
    {
      "epoch": 0.10905550146056475,
      "grad_norm": 0.5597368478775024,
      "learning_rate": 0.0001603305785123967,
      "loss": 0.6327,
      "step": 56
    },
    {
      "epoch": 0.11100292112950341,
      "grad_norm": 0.5331040024757385,
      "learning_rate": 0.00015950413223140498,
      "loss": 0.4662,
      "step": 57
    },
    {
      "epoch": 0.11295034079844206,
      "grad_norm": 0.4501107335090637,
      "learning_rate": 0.00015867768595041322,
      "loss": 0.4593,
      "step": 58
    },
    {
      "epoch": 0.11489776046738072,
      "grad_norm": 0.5544815063476562,
      "learning_rate": 0.0001578512396694215,
      "loss": 0.6111,
      "step": 59
    },
    {
      "epoch": 0.11684518013631938,
      "grad_norm": 0.5640352964401245,
      "learning_rate": 0.00015702479338842976,
      "loss": 0.5499,
      "step": 60
    },
    {
      "epoch": 0.11879259980525804,
      "grad_norm": 0.6318275332450867,
      "learning_rate": 0.000156198347107438,
      "loss": 0.4993,
      "step": 61
    },
    {
      "epoch": 0.12074001947419669,
      "grad_norm": 0.5284496545791626,
      "learning_rate": 0.00015537190082644627,
      "loss": 0.6777,
      "step": 62
    },
    {
      "epoch": 0.12268743914313535,
      "grad_norm": 0.44762396812438965,
      "learning_rate": 0.00015454545454545454,
      "loss": 0.3336,
      "step": 63
    },
    {
      "epoch": 0.124634858812074,
      "grad_norm": 0.7527077794075012,
      "learning_rate": 0.00015371900826446281,
      "loss": 0.5085,
      "step": 64
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": 0.5384949445724487,
      "learning_rate": 0.00015289256198347108,
      "loss": 0.4182,
      "step": 65
    },
    {
      "epoch": 0.12852969814995133,
      "grad_norm": 0.6809192895889282,
      "learning_rate": 0.00015206611570247935,
      "loss": 0.5201,
      "step": 66
    },
    {
      "epoch": 0.13047711781888996,
      "grad_norm": 0.6038883328437805,
      "learning_rate": 0.00015123966942148762,
      "loss": 0.4331,
      "step": 67
    },
    {
      "epoch": 0.13242453748782862,
      "grad_norm": 0.489505797624588,
      "learning_rate": 0.0001504132231404959,
      "loss": 0.3439,
      "step": 68
    },
    {
      "epoch": 0.13437195715676728,
      "grad_norm": 0.4495028555393219,
      "learning_rate": 0.00014958677685950414,
      "loss": 0.3788,
      "step": 69
    },
    {
      "epoch": 0.13631937682570594,
      "grad_norm": 0.3689400255680084,
      "learning_rate": 0.0001487603305785124,
      "loss": 0.299,
      "step": 70
    },
    {
      "epoch": 0.1382667964946446,
      "grad_norm": 0.440514475107193,
      "learning_rate": 0.00014793388429752067,
      "loss": 0.2871,
      "step": 71
    },
    {
      "epoch": 0.14021421616358326,
      "grad_norm": 0.6603713035583496,
      "learning_rate": 0.00014710743801652894,
      "loss": 0.4321,
      "step": 72
    },
    {
      "epoch": 0.14216163583252192,
      "grad_norm": 0.353661447763443,
      "learning_rate": 0.0001462809917355372,
      "loss": 0.2402,
      "step": 73
    },
    {
      "epoch": 0.14410905550146055,
      "grad_norm": 0.7928922772407532,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.8787,
      "step": 74
    },
    {
      "epoch": 0.1460564751703992,
      "grad_norm": 0.502176821231842,
      "learning_rate": 0.00014462809917355373,
      "loss": 0.3636,
      "step": 75
    },
    {
      "epoch": 0.14800389483933787,
      "grad_norm": 0.5314487814903259,
      "learning_rate": 0.000143801652892562,
      "loss": 0.409,
      "step": 76
    },
    {
      "epoch": 0.14995131450827653,
      "grad_norm": 0.6997962594032288,
      "learning_rate": 0.00014297520661157024,
      "loss": 0.5591,
      "step": 77
    },
    {
      "epoch": 0.1518987341772152,
      "grad_norm": 0.7340275645256042,
      "learning_rate": 0.0001421487603305785,
      "loss": 0.6306,
      "step": 78
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.722694993019104,
      "learning_rate": 0.00014132231404958678,
      "loss": 0.5656,
      "step": 79
    },
    {
      "epoch": 0.15579357351509251,
      "grad_norm": 0.7989778518676758,
      "learning_rate": 0.00014049586776859505,
      "loss": 0.8676,
      "step": 80
    },
    {
      "epoch": 0.15774099318403115,
      "grad_norm": 0.514163613319397,
      "learning_rate": 0.00013966942148760332,
      "loss": 0.492,
      "step": 81
    },
    {
      "epoch": 0.1596884128529698,
      "grad_norm": 0.78263920545578,
      "learning_rate": 0.0001388429752066116,
      "loss": 0.7545,
      "step": 82
    },
    {
      "epoch": 0.16163583252190847,
      "grad_norm": 0.5553173422813416,
      "learning_rate": 0.00013801652892561986,
      "loss": 0.5447,
      "step": 83
    },
    {
      "epoch": 0.16358325219084713,
      "grad_norm": 0.6660541892051697,
      "learning_rate": 0.00013719008264462813,
      "loss": 0.7586,
      "step": 84
    },
    {
      "epoch": 0.1655306718597858,
      "grad_norm": 0.5211347341537476,
      "learning_rate": 0.00013636363636363637,
      "loss": 0.3946,
      "step": 85
    },
    {
      "epoch": 0.16747809152872445,
      "grad_norm": 0.9146146774291992,
      "learning_rate": 0.00013553719008264464,
      "loss": 0.6544,
      "step": 86
    },
    {
      "epoch": 0.1694255111976631,
      "grad_norm": 0.5467679500579834,
      "learning_rate": 0.00013471074380165288,
      "loss": 0.5245,
      "step": 87
    },
    {
      "epoch": 0.17137293086660174,
      "grad_norm": 0.7478577494621277,
      "learning_rate": 0.00013388429752066115,
      "loss": 0.8132,
      "step": 88
    },
    {
      "epoch": 0.1733203505355404,
      "grad_norm": 0.6577962636947632,
      "learning_rate": 0.00013305785123966942,
      "loss": 0.59,
      "step": 89
    },
    {
      "epoch": 0.17526777020447906,
      "grad_norm": 0.775256335735321,
      "learning_rate": 0.0001322314049586777,
      "loss": 0.5544,
      "step": 90
    },
    {
      "epoch": 0.17721518987341772,
      "grad_norm": 0.5346238613128662,
      "learning_rate": 0.00013140495867768596,
      "loss": 0.4337,
      "step": 91
    },
    {
      "epoch": 0.17916260954235638,
      "grad_norm": 0.578333854675293,
      "learning_rate": 0.00013057851239669423,
      "loss": 0.4799,
      "step": 92
    },
    {
      "epoch": 0.18111002921129504,
      "grad_norm": 0.6039044857025146,
      "learning_rate": 0.00012975206611570247,
      "loss": 0.4282,
      "step": 93
    },
    {
      "epoch": 0.1830574488802337,
      "grad_norm": 0.6463829874992371,
      "learning_rate": 0.00012892561983471074,
      "loss": 0.6641,
      "step": 94
    },
    {
      "epoch": 0.18500486854917234,
      "grad_norm": 0.9733583331108093,
      "learning_rate": 0.000128099173553719,
      "loss": 0.6536,
      "step": 95
    },
    {
      "epoch": 0.186952288218111,
      "grad_norm": 0.6739547252655029,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.6845,
      "step": 96
    },
    {
      "epoch": 0.18889970788704966,
      "grad_norm": 0.7450870275497437,
      "learning_rate": 0.00012644628099173555,
      "loss": 0.7029,
      "step": 97
    },
    {
      "epoch": 0.19084712755598832,
      "grad_norm": 0.7437999248504639,
      "learning_rate": 0.00012561983471074382,
      "loss": 0.6285,
      "step": 98
    },
    {
      "epoch": 0.19279454722492698,
      "grad_norm": 0.6908058524131775,
      "learning_rate": 0.0001247933884297521,
      "loss": 0.6161,
      "step": 99
    },
    {
      "epoch": 0.19474196689386564,
      "grad_norm": 0.6222776174545288,
      "learning_rate": 0.00012396694214876033,
      "loss": 0.5389,
      "step": 100
    },
    {
      "epoch": 0.1966893865628043,
      "grad_norm": 0.7415236234664917,
      "learning_rate": 0.0001231404958677686,
      "loss": 0.7564,
      "step": 101
    },
    {
      "epoch": 0.19863680623174293,
      "grad_norm": 0.725433349609375,
      "learning_rate": 0.00012231404958677685,
      "loss": 0.5624,
      "step": 102
    },
    {
      "epoch": 0.2005842259006816,
      "grad_norm": 0.5979681611061096,
      "learning_rate": 0.00012148760330578513,
      "loss": 0.4344,
      "step": 103
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 0.6501683592796326,
      "learning_rate": 0.0001206611570247934,
      "loss": 0.5137,
      "step": 104
    },
    {
      "epoch": 0.2044790652385589,
      "grad_norm": 0.4350631535053253,
      "learning_rate": 0.00011983471074380165,
      "loss": 0.4055,
      "step": 105
    },
    {
      "epoch": 0.20642648490749757,
      "grad_norm": 0.7034055590629578,
      "learning_rate": 0.00011900826446280992,
      "loss": 0.6413,
      "step": 106
    },
    {
      "epoch": 0.20837390457643623,
      "grad_norm": 0.606842041015625,
      "learning_rate": 0.0001181818181818182,
      "loss": 0.6433,
      "step": 107
    },
    {
      "epoch": 0.2103213242453749,
      "grad_norm": 0.6555774807929993,
      "learning_rate": 0.00011735537190082646,
      "loss": 0.8194,
      "step": 108
    },
    {
      "epoch": 0.21226874391431352,
      "grad_norm": 0.6111577749252319,
      "learning_rate": 0.0001165289256198347,
      "loss": 0.5042,
      "step": 109
    },
    {
      "epoch": 0.21421616358325218,
      "grad_norm": 0.6553054451942444,
      "learning_rate": 0.00011570247933884298,
      "loss": 0.6989,
      "step": 110
    },
    {
      "epoch": 0.21616358325219084,
      "grad_norm": 0.4501146972179413,
      "learning_rate": 0.00011487603305785125,
      "loss": 0.3658,
      "step": 111
    },
    {
      "epoch": 0.2181110029211295,
      "grad_norm": 0.44687238335609436,
      "learning_rate": 0.0001140495867768595,
      "loss": 0.3615,
      "step": 112
    },
    {
      "epoch": 0.22005842259006816,
      "grad_norm": 0.7412980198860168,
      "learning_rate": 0.00011322314049586777,
      "loss": 0.8426,
      "step": 113
    },
    {
      "epoch": 0.22200584225900682,
      "grad_norm": 0.4677373170852661,
      "learning_rate": 0.00011239669421487604,
      "loss": 0.3759,
      "step": 114
    },
    {
      "epoch": 0.22395326192794549,
      "grad_norm": 0.5156281590461731,
      "learning_rate": 0.00011157024793388431,
      "loss": 0.4241,
      "step": 115
    },
    {
      "epoch": 0.22590068159688412,
      "grad_norm": 0.655049741268158,
      "learning_rate": 0.00011074380165289258,
      "loss": 0.4153,
      "step": 116
    },
    {
      "epoch": 0.22784810126582278,
      "grad_norm": 0.4297865927219391,
      "learning_rate": 0.00010991735537190082,
      "loss": 0.3184,
      "step": 117
    },
    {
      "epoch": 0.22979552093476144,
      "grad_norm": 0.6195393204689026,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.7035,
      "step": 118
    },
    {
      "epoch": 0.2317429406037001,
      "grad_norm": 0.6508321762084961,
      "learning_rate": 0.00010826446280991735,
      "loss": 0.6435,
      "step": 119
    },
    {
      "epoch": 0.23369036027263876,
      "grad_norm": 0.5999849438667297,
      "learning_rate": 0.00010743801652892562,
      "loss": 0.5618,
      "step": 120
    },
    {
      "epoch": 0.23563777994157742,
      "grad_norm": 0.4445487856864929,
      "learning_rate": 0.00010661157024793389,
      "loss": 0.3008,
      "step": 121
    },
    {
      "epoch": 0.23758519961051608,
      "grad_norm": 0.46502161026000977,
      "learning_rate": 0.00010578512396694216,
      "loss": 0.4989,
      "step": 122
    },
    {
      "epoch": 0.2395326192794547,
      "grad_norm": 0.5087387561798096,
      "learning_rate": 0.00010495867768595043,
      "loss": 0.3852,
      "step": 123
    },
    {
      "epoch": 0.24148003894839337,
      "grad_norm": 0.4807125926017761,
      "learning_rate": 0.0001041322314049587,
      "loss": 0.3579,
      "step": 124
    },
    {
      "epoch": 0.24342745861733203,
      "grad_norm": 0.5348750948905945,
      "learning_rate": 0.00010330578512396694,
      "loss": 0.4919,
      "step": 125
    },
    {
      "epoch": 0.2453748782862707,
      "grad_norm": 0.8607493042945862,
      "learning_rate": 0.00010247933884297521,
      "loss": 0.8142,
      "step": 126
    },
    {
      "epoch": 0.24732229795520935,
      "grad_norm": 0.4636419415473938,
      "learning_rate": 0.00010165289256198347,
      "loss": 0.407,
      "step": 127
    },
    {
      "epoch": 0.249269717624148,
      "grad_norm": 0.49384385347366333,
      "learning_rate": 0.00010082644628099174,
      "loss": 0.4263,
      "step": 128
    },
    {
      "epoch": 0.25121713729308665,
      "grad_norm": 0.5093722343444824,
      "learning_rate": 0.0001,
      "loss": 0.3402,
      "step": 129
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 0.6678729057312012,
      "learning_rate": 9.917355371900827e-05,
      "loss": 0.5644,
      "step": 130
    },
    {
      "epoch": 0.25511197663096397,
      "grad_norm": 0.7193764448165894,
      "learning_rate": 9.834710743801654e-05,
      "loss": 0.6274,
      "step": 131
    },
    {
      "epoch": 0.25705939629990265,
      "grad_norm": 0.3708731234073639,
      "learning_rate": 9.75206611570248e-05,
      "loss": 0.269,
      "step": 132
    },
    {
      "epoch": 0.2590068159688413,
      "grad_norm": 0.6703848242759705,
      "learning_rate": 9.669421487603306e-05,
      "loss": 0.5984,
      "step": 133
    },
    {
      "epoch": 0.2609542356377799,
      "grad_norm": 0.5617924928665161,
      "learning_rate": 9.586776859504133e-05,
      "loss": 0.5166,
      "step": 134
    },
    {
      "epoch": 0.2629016553067186,
      "grad_norm": 0.6645628213882446,
      "learning_rate": 9.50413223140496e-05,
      "loss": 0.7676,
      "step": 135
    },
    {
      "epoch": 0.26484907497565724,
      "grad_norm": 0.6777731776237488,
      "learning_rate": 9.421487603305785e-05,
      "loss": 0.4477,
      "step": 136
    },
    {
      "epoch": 0.2667964946445959,
      "grad_norm": 1.0802561044692993,
      "learning_rate": 9.338842975206612e-05,
      "loss": 0.7692,
      "step": 137
    },
    {
      "epoch": 0.26874391431353456,
      "grad_norm": 0.5928775072097778,
      "learning_rate": 9.256198347107439e-05,
      "loss": 0.5721,
      "step": 138
    },
    {
      "epoch": 0.27069133398247325,
      "grad_norm": 0.73649001121521,
      "learning_rate": 9.173553719008266e-05,
      "loss": 0.6324,
      "step": 139
    },
    {
      "epoch": 0.2726387536514119,
      "grad_norm": 0.6584858298301697,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.5763,
      "step": 140
    },
    {
      "epoch": 0.2745861733203505,
      "grad_norm": 0.6551913619041443,
      "learning_rate": 9.008264462809917e-05,
      "loss": 0.6005,
      "step": 141
    },
    {
      "epoch": 0.2765335929892892,
      "grad_norm": 0.5698264837265015,
      "learning_rate": 8.925619834710744e-05,
      "loss": 0.4164,
      "step": 142
    },
    {
      "epoch": 0.27848101265822783,
      "grad_norm": 0.5793282985687256,
      "learning_rate": 8.842975206611571e-05,
      "loss": 0.4952,
      "step": 143
    },
    {
      "epoch": 0.2804284323271665,
      "grad_norm": 0.52625972032547,
      "learning_rate": 8.760330578512397e-05,
      "loss": 0.4534,
      "step": 144
    },
    {
      "epoch": 0.28237585199610515,
      "grad_norm": 0.6003084778785706,
      "learning_rate": 8.677685950413224e-05,
      "loss": 0.5206,
      "step": 145
    },
    {
      "epoch": 0.28432327166504384,
      "grad_norm": 0.5583734512329102,
      "learning_rate": 8.595041322314051e-05,
      "loss": 0.5323,
      "step": 146
    },
    {
      "epoch": 0.2862706913339825,
      "grad_norm": 0.600612461566925,
      "learning_rate": 8.512396694214876e-05,
      "loss": 0.5463,
      "step": 147
    },
    {
      "epoch": 0.2882181110029211,
      "grad_norm": 0.8786905407905579,
      "learning_rate": 8.429752066115702e-05,
      "loss": 0.48,
      "step": 148
    },
    {
      "epoch": 0.2901655306718598,
      "grad_norm": 0.6033667922019958,
      "learning_rate": 8.347107438016529e-05,
      "loss": 0.4997,
      "step": 149
    },
    {
      "epoch": 0.2921129503407984,
      "grad_norm": 0.7072091102600098,
      "learning_rate": 8.264462809917356e-05,
      "loss": 0.5164,
      "step": 150
    },
    {
      "epoch": 0.2940603700097371,
      "grad_norm": 0.5921626687049866,
      "learning_rate": 8.181818181818183e-05,
      "loss": 0.6378,
      "step": 151
    },
    {
      "epoch": 0.29600778967867575,
      "grad_norm": 0.5669450759887695,
      "learning_rate": 8.099173553719009e-05,
      "loss": 0.501,
      "step": 152
    },
    {
      "epoch": 0.29795520934761444,
      "grad_norm": 0.5064852237701416,
      "learning_rate": 8.016528925619836e-05,
      "loss": 0.3843,
      "step": 153
    },
    {
      "epoch": 0.29990262901655307,
      "grad_norm": 0.5336524248123169,
      "learning_rate": 7.933884297520661e-05,
      "loss": 0.3716,
      "step": 154
    },
    {
      "epoch": 0.3018500486854917,
      "grad_norm": 0.44651252031326294,
      "learning_rate": 7.851239669421488e-05,
      "loss": 0.3773,
      "step": 155
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 0.38342341780662537,
      "learning_rate": 7.768595041322314e-05,
      "loss": 0.2936,
      "step": 156
    },
    {
      "epoch": 0.305744888023369,
      "grad_norm": 0.4770042598247528,
      "learning_rate": 7.685950413223141e-05,
      "loss": 0.4883,
      "step": 157
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.6555917263031006,
      "learning_rate": 7.603305785123968e-05,
      "loss": 0.606,
      "step": 158
    },
    {
      "epoch": 0.30963972736124634,
      "grad_norm": 0.4627241790294647,
      "learning_rate": 7.520661157024795e-05,
      "loss": 0.3273,
      "step": 159
    },
    {
      "epoch": 0.31158714703018503,
      "grad_norm": 0.3865076005458832,
      "learning_rate": 7.43801652892562e-05,
      "loss": 0.2885,
      "step": 160
    },
    {
      "epoch": 0.31353456669912366,
      "grad_norm": 0.37422531843185425,
      "learning_rate": 7.355371900826447e-05,
      "loss": 0.3094,
      "step": 161
    },
    {
      "epoch": 0.3154819863680623,
      "grad_norm": 0.4276966452598572,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.3022,
      "step": 162
    },
    {
      "epoch": 0.317429406037001,
      "grad_norm": 0.31993845105171204,
      "learning_rate": 7.1900826446281e-05,
      "loss": 0.2376,
      "step": 163
    },
    {
      "epoch": 0.3193768257059396,
      "grad_norm": 0.3512668013572693,
      "learning_rate": 7.107438016528925e-05,
      "loss": 0.2865,
      "step": 164
    },
    {
      "epoch": 0.3213242453748783,
      "grad_norm": 1.2840955257415771,
      "learning_rate": 7.024793388429752e-05,
      "loss": 0.9994,
      "step": 165
    },
    {
      "epoch": 0.32327166504381694,
      "grad_norm": 0.7181655168533325,
      "learning_rate": 6.94214876033058e-05,
      "loss": 1.3493,
      "step": 166
    },
    {
      "epoch": 0.3252190847127556,
      "grad_norm": 0.5071792602539062,
      "learning_rate": 6.859504132231406e-05,
      "loss": 0.4438,
      "step": 167
    },
    {
      "epoch": 0.32716650438169426,
      "grad_norm": 0.7322396636009216,
      "learning_rate": 6.776859504132232e-05,
      "loss": 0.6287,
      "step": 168
    },
    {
      "epoch": 0.3291139240506329,
      "grad_norm": 0.26013123989105225,
      "learning_rate": 6.694214876033058e-05,
      "loss": 0.2015,
      "step": 169
    },
    {
      "epoch": 0.3310613437195716,
      "grad_norm": 0.41022831201553345,
      "learning_rate": 6.611570247933885e-05,
      "loss": 0.2814,
      "step": 170
    },
    {
      "epoch": 0.3330087633885102,
      "grad_norm": 0.4295414388179779,
      "learning_rate": 6.528925619834711e-05,
      "loss": 0.3253,
      "step": 171
    },
    {
      "epoch": 0.3349561830574489,
      "grad_norm": 0.5953055024147034,
      "learning_rate": 6.446280991735537e-05,
      "loss": 0.5285,
      "step": 172
    },
    {
      "epoch": 0.33690360272638753,
      "grad_norm": 0.585370659828186,
      "learning_rate": 6.363636363636364e-05,
      "loss": 0.5672,
      "step": 173
    },
    {
      "epoch": 0.3388510223953262,
      "grad_norm": 0.469965398311615,
      "learning_rate": 6.280991735537191e-05,
      "loss": 0.3597,
      "step": 174
    },
    {
      "epoch": 0.34079844206426485,
      "grad_norm": 0.5699323415756226,
      "learning_rate": 6.198347107438017e-05,
      "loss": 0.4781,
      "step": 175
    },
    {
      "epoch": 0.3427458617332035,
      "grad_norm": 0.6034254431724548,
      "learning_rate": 6.115702479338842e-05,
      "loss": 0.468,
      "step": 176
    },
    {
      "epoch": 0.34469328140214217,
      "grad_norm": 0.646748423576355,
      "learning_rate": 6.03305785123967e-05,
      "loss": 0.4904,
      "step": 177
    },
    {
      "epoch": 0.3466407010710808,
      "grad_norm": 0.4674849212169647,
      "learning_rate": 5.950413223140496e-05,
      "loss": 0.4888,
      "step": 178
    },
    {
      "epoch": 0.3485881207400195,
      "grad_norm": 0.5764815807342529,
      "learning_rate": 5.867768595041323e-05,
      "loss": 0.5268,
      "step": 179
    },
    {
      "epoch": 0.3505355404089581,
      "grad_norm": 0.5898470878601074,
      "learning_rate": 5.785123966942149e-05,
      "loss": 0.4667,
      "step": 180
    },
    {
      "epoch": 0.3524829600778968,
      "grad_norm": 0.38661783933639526,
      "learning_rate": 5.702479338842975e-05,
      "loss": 0.3538,
      "step": 181
    },
    {
      "epoch": 0.35443037974683544,
      "grad_norm": 0.4027338922023773,
      "learning_rate": 5.619834710743802e-05,
      "loss": 0.3705,
      "step": 182
    },
    {
      "epoch": 0.3563777994157741,
      "grad_norm": 0.3949303925037384,
      "learning_rate": 5.537190082644629e-05,
      "loss": 0.3463,
      "step": 183
    },
    {
      "epoch": 0.35832521908471276,
      "grad_norm": 0.5721768736839294,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.4461,
      "step": 184
    },
    {
      "epoch": 0.3602726387536514,
      "grad_norm": 0.5568830966949463,
      "learning_rate": 5.371900826446281e-05,
      "loss": 0.3703,
      "step": 185
    },
    {
      "epoch": 0.3622200584225901,
      "grad_norm": 0.4944753646850586,
      "learning_rate": 5.289256198347108e-05,
      "loss": 0.4531,
      "step": 186
    },
    {
      "epoch": 0.3641674780915287,
      "grad_norm": 0.5557789206504822,
      "learning_rate": 5.206611570247935e-05,
      "loss": 0.5426,
      "step": 187
    },
    {
      "epoch": 0.3661148977604674,
      "grad_norm": 0.6477212309837341,
      "learning_rate": 5.1239669421487605e-05,
      "loss": 0.5483,
      "step": 188
    },
    {
      "epoch": 0.36806231742940604,
      "grad_norm": 0.7089900374412537,
      "learning_rate": 5.041322314049587e-05,
      "loss": 0.6709,
      "step": 189
    },
    {
      "epoch": 0.37000973709834467,
      "grad_norm": 0.5330088138580322,
      "learning_rate": 4.958677685950414e-05,
      "loss": 0.7063,
      "step": 190
    },
    {
      "epoch": 0.37195715676728336,
      "grad_norm": 0.5296370387077332,
      "learning_rate": 4.87603305785124e-05,
      "loss": 0.5056,
      "step": 191
    },
    {
      "epoch": 0.373904576436222,
      "grad_norm": 0.8069382309913635,
      "learning_rate": 4.793388429752066e-05,
      "loss": 0.7653,
      "step": 192
    },
    {
      "epoch": 0.3758519961051607,
      "grad_norm": 0.43892863392829895,
      "learning_rate": 4.7107438016528926e-05,
      "loss": 0.4423,
      "step": 193
    },
    {
      "epoch": 0.3777994157740993,
      "grad_norm": 0.7146729826927185,
      "learning_rate": 4.6280991735537196e-05,
      "loss": 0.7297,
      "step": 194
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 0.41250815987586975,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.404,
      "step": 195
    },
    {
      "epoch": 0.38169425511197663,
      "grad_norm": 0.4819222390651703,
      "learning_rate": 4.462809917355372e-05,
      "loss": 0.4106,
      "step": 196
    },
    {
      "epoch": 0.38364167478091526,
      "grad_norm": 0.41315364837646484,
      "learning_rate": 4.3801652892561984e-05,
      "loss": 0.3445,
      "step": 197
    },
    {
      "epoch": 0.38558909444985395,
      "grad_norm": 0.4681267738342285,
      "learning_rate": 4.2975206611570254e-05,
      "loss": 0.3611,
      "step": 198
    },
    {
      "epoch": 0.3875365141187926,
      "grad_norm": 0.48512405157089233,
      "learning_rate": 4.214876033057851e-05,
      "loss": 0.3842,
      "step": 199
    },
    {
      "epoch": 0.3894839337877313,
      "grad_norm": 0.49099263548851013,
      "learning_rate": 4.132231404958678e-05,
      "loss": 0.3824,
      "step": 200
    },
    {
      "epoch": 0.3914313534566699,
      "grad_norm": 0.3325710892677307,
      "learning_rate": 4.049586776859504e-05,
      "loss": 0.2954,
      "step": 201
    },
    {
      "epoch": 0.3933787731256086,
      "grad_norm": 0.30682113766670227,
      "learning_rate": 3.9669421487603306e-05,
      "loss": 0.2274,
      "step": 202
    },
    {
      "epoch": 0.3953261927945472,
      "grad_norm": 0.3700462579727173,
      "learning_rate": 3.884297520661157e-05,
      "loss": 0.2983,
      "step": 203
    },
    {
      "epoch": 0.39727361246348586,
      "grad_norm": 0.4219472110271454,
      "learning_rate": 3.801652892561984e-05,
      "loss": 0.3604,
      "step": 204
    },
    {
      "epoch": 0.39922103213242455,
      "grad_norm": 0.2869436740875244,
      "learning_rate": 3.71900826446281e-05,
      "loss": 0.2366,
      "step": 205
    },
    {
      "epoch": 0.4011684518013632,
      "grad_norm": 0.5798669457435608,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.6483,
      "step": 206
    },
    {
      "epoch": 0.40311587147030187,
      "grad_norm": 0.5161038637161255,
      "learning_rate": 3.553719008264463e-05,
      "loss": 0.557,
      "step": 207
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 0.43804600834846497,
      "learning_rate": 3.47107438016529e-05,
      "loss": 0.2817,
      "step": 208
    },
    {
      "epoch": 0.4070107108081792,
      "grad_norm": 0.2725582420825958,
      "learning_rate": 3.388429752066116e-05,
      "loss": 0.2317,
      "step": 209
    },
    {
      "epoch": 0.4089581304771178,
      "grad_norm": 0.4551626443862915,
      "learning_rate": 3.305785123966942e-05,
      "loss": 0.3523,
      "step": 210
    },
    {
      "epoch": 0.41090555014605645,
      "grad_norm": 0.4810575842857361,
      "learning_rate": 3.2231404958677685e-05,
      "loss": 0.4526,
      "step": 211
    },
    {
      "epoch": 0.41285296981499514,
      "grad_norm": 0.6466739773750305,
      "learning_rate": 3.1404958677685955e-05,
      "loss": 0.8117,
      "step": 212
    },
    {
      "epoch": 0.4148003894839338,
      "grad_norm": 0.5906726717948914,
      "learning_rate": 3.057851239669421e-05,
      "loss": 0.6446,
      "step": 213
    },
    {
      "epoch": 0.41674780915287246,
      "grad_norm": 0.5657168626785278,
      "learning_rate": 2.975206611570248e-05,
      "loss": 0.4798,
      "step": 214
    },
    {
      "epoch": 0.4186952288218111,
      "grad_norm": 0.45190712809562683,
      "learning_rate": 2.8925619834710744e-05,
      "loss": 0.4177,
      "step": 215
    },
    {
      "epoch": 0.4206426484907498,
      "grad_norm": 0.36461302638053894,
      "learning_rate": 2.809917355371901e-05,
      "loss": 0.3125,
      "step": 216
    },
    {
      "epoch": 0.4225900681596884,
      "grad_norm": 0.5353040099143982,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.6517,
      "step": 217
    },
    {
      "epoch": 0.42453748782862705,
      "grad_norm": 0.7112963795661926,
      "learning_rate": 2.644628099173554e-05,
      "loss": 0.6613,
      "step": 218
    },
    {
      "epoch": 0.42648490749756574,
      "grad_norm": 0.4022853374481201,
      "learning_rate": 2.5619834710743802e-05,
      "loss": 0.3589,
      "step": 219
    },
    {
      "epoch": 0.42843232716650437,
      "grad_norm": 0.4931185841560364,
      "learning_rate": 2.479338842975207e-05,
      "loss": 0.5696,
      "step": 220
    },
    {
      "epoch": 0.43037974683544306,
      "grad_norm": 0.28436464071273804,
      "learning_rate": 2.396694214876033e-05,
      "loss": 0.2196,
      "step": 221
    },
    {
      "epoch": 0.4323271665043817,
      "grad_norm": 0.4250311553478241,
      "learning_rate": 2.3140495867768598e-05,
      "loss": 0.3458,
      "step": 222
    },
    {
      "epoch": 0.4342745861733204,
      "grad_norm": 0.23114222288131714,
      "learning_rate": 2.231404958677686e-05,
      "loss": 0.2124,
      "step": 223
    },
    {
      "epoch": 0.436222005842259,
      "grad_norm": 0.46653562784194946,
      "learning_rate": 2.1487603305785127e-05,
      "loss": 0.3793,
      "step": 224
    },
    {
      "epoch": 0.43816942551119764,
      "grad_norm": 0.7057761549949646,
      "learning_rate": 2.066115702479339e-05,
      "loss": 0.7023,
      "step": 225
    },
    {
      "epoch": 0.44011684518013633,
      "grad_norm": 0.4195654094219208,
      "learning_rate": 1.9834710743801653e-05,
      "loss": 0.4148,
      "step": 226
    },
    {
      "epoch": 0.44206426484907496,
      "grad_norm": 0.4446503221988678,
      "learning_rate": 1.900826446280992e-05,
      "loss": 0.4615,
      "step": 227
    },
    {
      "epoch": 0.44401168451801365,
      "grad_norm": 0.28336820006370544,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.1496,
      "step": 228
    },
    {
      "epoch": 0.4459591041869523,
      "grad_norm": 0.5226246118545532,
      "learning_rate": 1.735537190082645e-05,
      "loss": 0.5196,
      "step": 229
    },
    {
      "epoch": 0.44790652385589097,
      "grad_norm": 0.5695878267288208,
      "learning_rate": 1.652892561983471e-05,
      "loss": 0.5308,
      "step": 230
    },
    {
      "epoch": 0.4498539435248296,
      "grad_norm": 0.5476521849632263,
      "learning_rate": 1.5702479338842978e-05,
      "loss": 0.4681,
      "step": 231
    },
    {
      "epoch": 0.45180136319376824,
      "grad_norm": 0.5449410676956177,
      "learning_rate": 1.487603305785124e-05,
      "loss": 0.5434,
      "step": 232
    },
    {
      "epoch": 0.4537487828627069,
      "grad_norm": 0.47294700145721436,
      "learning_rate": 1.4049586776859505e-05,
      "loss": 0.435,
      "step": 233
    },
    {
      "epoch": 0.45569620253164556,
      "grad_norm": 0.6122575998306274,
      "learning_rate": 1.322314049586777e-05,
      "loss": 0.5793,
      "step": 234
    },
    {
      "epoch": 0.45764362220058424,
      "grad_norm": 0.7652103900909424,
      "learning_rate": 1.2396694214876034e-05,
      "loss": 0.8786,
      "step": 235
    },
    {
      "epoch": 0.4595910418695229,
      "grad_norm": 0.5390903949737549,
      "learning_rate": 1.1570247933884299e-05,
      "loss": 0.4212,
      "step": 236
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.6218725442886353,
      "learning_rate": 1.0743801652892564e-05,
      "loss": 0.5875,
      "step": 237
    },
    {
      "epoch": 0.4634858812074002,
      "grad_norm": 0.3942383825778961,
      "learning_rate": 9.917355371900826e-06,
      "loss": 0.3841,
      "step": 238
    },
    {
      "epoch": 0.46543330087633883,
      "grad_norm": 0.34732937812805176,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.2677,
      "step": 239
    },
    {
      "epoch": 0.4673807205452775,
      "grad_norm": 0.5432242751121521,
      "learning_rate": 8.264462809917356e-06,
      "loss": 0.5924,
      "step": 240
    },
    {
      "epoch": 0.46932814021421615,
      "grad_norm": 0.6005178689956665,
      "learning_rate": 7.43801652892562e-06,
      "loss": 0.5235,
      "step": 241
    },
    {
      "epoch": 0.47127555988315484,
      "grad_norm": 0.6554625630378723,
      "learning_rate": 6.611570247933885e-06,
      "loss": 0.6429,
      "step": 242
    },
    {
      "epoch": 0.47322297955209347,
      "grad_norm": 0.3775584399700165,
      "learning_rate": 5.7851239669421495e-06,
      "loss": 0.3247,
      "step": 243
    },
    {
      "epoch": 0.47517039922103216,
      "grad_norm": 0.5196499824523926,
      "learning_rate": 4.958677685950413e-06,
      "loss": 0.3589,
      "step": 244
    },
    {
      "epoch": 0.4771178188899708,
      "grad_norm": 0.462444931268692,
      "learning_rate": 4.132231404958678e-06,
      "loss": 0.4217,
      "step": 245
    },
    {
      "epoch": 0.4790652385589094,
      "grad_norm": 0.3943294286727905,
      "learning_rate": 3.3057851239669424e-06,
      "loss": 0.2937,
      "step": 246
    },
    {
      "epoch": 0.4810126582278481,
      "grad_norm": 0.3740336298942566,
      "learning_rate": 2.4793388429752066e-06,
      "loss": 0.3033,
      "step": 247
    },
    {
      "epoch": 0.48296007789678674,
      "grad_norm": 0.3156736493110657,
      "learning_rate": 1.6528925619834712e-06,
      "loss": 0.2708,
      "step": 248
    },
    {
      "epoch": 0.48490749756572543,
      "grad_norm": 0.6795382499694824,
      "learning_rate": 8.264462809917356e-07,
      "loss": 0.5882,
      "step": 249
    },
    {
      "epoch": 0.48685491723466406,
      "grad_norm": 0.45327121019363403,
      "learning_rate": 0.0,
      "loss": 0.3451,
      "step": 250
    }
  ],
  "logging_steps": 1,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1165175740907520.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}