{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 461,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021691973969631237,
      "grad_norm": 299.83172607421875,
      "learning_rate": 0.0,
      "loss": 5.7764,
      "step": 1
    },
    {
      "epoch": 0.004338394793926247,
      "grad_norm": 299.2650146484375,
      "learning_rate": 1.4492753623188406e-06,
      "loss": 5.8564,
      "step": 2
    },
    {
      "epoch": 0.006507592190889371,
      "grad_norm": 146.00950622558594,
      "learning_rate": 2.898550724637681e-06,
      "loss": 5.6626,
      "step": 3
    },
    {
      "epoch": 0.008676789587852495,
      "grad_norm": 49.815025329589844,
      "learning_rate": 4.347826086956522e-06,
      "loss": 5.3285,
      "step": 4
    },
    {
      "epoch": 0.010845986984815618,
      "grad_norm": 101.3691635131836,
      "learning_rate": 5.797101449275362e-06,
      "loss": 5.1811,
      "step": 5
    },
    {
      "epoch": 0.013015184381778741,
      "grad_norm": 37.71101379394531,
      "learning_rate": 7.246376811594203e-06,
      "loss": 4.9561,
      "step": 6
    },
    {
      "epoch": 0.015184381778741865,
      "grad_norm": 20.28386116027832,
      "learning_rate": 8.695652173913044e-06,
      "loss": 4.7239,
      "step": 7
    },
    {
      "epoch": 0.01735357917570499,
      "grad_norm": 13.960871696472168,
      "learning_rate": 1.0144927536231885e-05,
      "loss": 4.5337,
      "step": 8
    },
    {
      "epoch": 0.019522776572668113,
      "grad_norm": 6.646677494049072,
      "learning_rate": 1.1594202898550725e-05,
      "loss": 4.3586,
      "step": 9
    },
    {
      "epoch": 0.021691973969631236,
      "grad_norm": 5.420104026794434,
      "learning_rate": 1.3043478260869566e-05,
      "loss": 4.1465,
      "step": 10
    },
    {
      "epoch": 0.02386117136659436,
      "grad_norm": 4.748775959014893,
      "learning_rate": 1.4492753623188407e-05,
      "loss": 3.9432,
      "step": 11
    },
    {
      "epoch": 0.026030368763557483,
      "grad_norm": 3.7249014377593994,
      "learning_rate": 1.5942028985507246e-05,
      "loss": 3.8879,
      "step": 12
    },
    {
      "epoch": 0.028199566160520606,
      "grad_norm": 3.1089460849761963,
      "learning_rate": 1.739130434782609e-05,
      "loss": 3.6623,
      "step": 13
    },
    {
      "epoch": 0.03036876355748373,
      "grad_norm": 2.689898729324341,
      "learning_rate": 1.8840579710144928e-05,
      "loss": 3.4669,
      "step": 14
    },
    {
      "epoch": 0.03253796095444685,
      "grad_norm": 2.224663496017456,
      "learning_rate": 2.028985507246377e-05,
      "loss": 3.3815,
      "step": 15
    },
    {
      "epoch": 0.03470715835140998,
      "grad_norm": 2.2241079807281494,
      "learning_rate": 2.173913043478261e-05,
      "loss": 3.3829,
      "step": 16
    },
    {
      "epoch": 0.0368763557483731,
      "grad_norm": 2.080374240875244,
      "learning_rate": 2.318840579710145e-05,
      "loss": 3.0973,
      "step": 17
    },
    {
      "epoch": 0.039045553145336226,
      "grad_norm": 1.9164319038391113,
      "learning_rate": 2.4637681159420292e-05,
      "loss": 2.9733,
      "step": 18
    },
    {
      "epoch": 0.04121475054229935,
      "grad_norm": 1.8816795349121094,
      "learning_rate": 2.608695652173913e-05,
      "loss": 2.7914,
      "step": 19
    },
    {
      "epoch": 0.04338394793926247,
      "grad_norm": 1.7498589754104614,
      "learning_rate": 2.753623188405797e-05,
      "loss": 2.6662,
      "step": 20
    },
    {
      "epoch": 0.0455531453362256,
      "grad_norm": 1.4596140384674072,
      "learning_rate": 2.8985507246376814e-05,
      "loss": 2.7011,
      "step": 21
    },
    {
      "epoch": 0.04772234273318872,
      "grad_norm": 1.218394160270691,
      "learning_rate": 3.0434782608695656e-05,
      "loss": 2.4695,
      "step": 22
    },
    {
      "epoch": 0.049891540130151846,
      "grad_norm": 0.9504335522651672,
      "learning_rate": 3.188405797101449e-05,
      "loss": 2.1591,
      "step": 23
    },
    {
      "epoch": 0.052060737527114966,
      "grad_norm": 0.9289931058883667,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.2166,
      "step": 24
    },
    {
      "epoch": 0.05422993492407809,
      "grad_norm": 0.8010533452033997,
      "learning_rate": 3.478260869565218e-05,
      "loss": 1.9909,
      "step": 25
    },
    {
      "epoch": 0.05639913232104121,
      "grad_norm": 0.8402034044265747,
      "learning_rate": 3.6231884057971014e-05,
      "loss": 1.9815,
      "step": 26
    },
    {
      "epoch": 0.05856832971800434,
      "grad_norm": 0.9097695350646973,
      "learning_rate": 3.7681159420289856e-05,
      "loss": 1.8434,
      "step": 27
    },
    {
      "epoch": 0.06073752711496746,
      "grad_norm": 0.8697475790977478,
      "learning_rate": 3.91304347826087e-05,
      "loss": 1.7416,
      "step": 28
    },
    {
      "epoch": 0.06290672451193059,
      "grad_norm": 0.9520090222358704,
      "learning_rate": 4.057971014492754e-05,
      "loss": 1.6109,
      "step": 29
    },
    {
      "epoch": 0.0650759219088937,
      "grad_norm": 0.9434909820556641,
      "learning_rate": 4.202898550724638e-05,
      "loss": 1.498,
      "step": 30
    },
    {
      "epoch": 0.06724511930585683,
      "grad_norm": 0.8209748864173889,
      "learning_rate": 4.347826086956522e-05,
      "loss": 1.3927,
      "step": 31
    },
    {
      "epoch": 0.06941431670281996,
      "grad_norm": 0.7369216680526733,
      "learning_rate": 4.492753623188406e-05,
      "loss": 1.3064,
      "step": 32
    },
    {
      "epoch": 0.07158351409978309,
      "grad_norm": 0.6995232701301575,
      "learning_rate": 4.63768115942029e-05,
      "loss": 1.2692,
      "step": 33
    },
    {
      "epoch": 0.0737527114967462,
      "grad_norm": 0.529533326625824,
      "learning_rate": 4.782608695652174e-05,
      "loss": 1.1112,
      "step": 34
    },
    {
      "epoch": 0.07592190889370933,
      "grad_norm": 0.5113012194633484,
      "learning_rate": 4.9275362318840584e-05,
      "loss": 1.1204,
      "step": 35
    },
    {
      "epoch": 0.07809110629067245,
      "grad_norm": 0.42345812916755676,
      "learning_rate": 5.072463768115943e-05,
      "loss": 1.027,
      "step": 36
    },
    {
      "epoch": 0.08026030368763558,
      "grad_norm": 0.4768829047679901,
      "learning_rate": 5.217391304347826e-05,
      "loss": 1.0236,
      "step": 37
    },
    {
      "epoch": 0.0824295010845987,
      "grad_norm": 0.38925743103027344,
      "learning_rate": 5.3623188405797106e-05,
      "loss": 0.9804,
      "step": 38
    },
    {
      "epoch": 0.08459869848156182,
      "grad_norm": 0.36462751030921936,
      "learning_rate": 5.507246376811594e-05,
      "loss": 0.9612,
      "step": 39
    },
    {
      "epoch": 0.08676789587852494,
      "grad_norm": 0.3321199119091034,
      "learning_rate": 5.652173913043478e-05,
      "loss": 0.9274,
      "step": 40
    },
    {
      "epoch": 0.08893709327548807,
      "grad_norm": 0.30222928524017334,
      "learning_rate": 5.797101449275363e-05,
      "loss": 0.8924,
      "step": 41
    },
    {
      "epoch": 0.0911062906724512,
      "grad_norm": 0.26241984963417053,
      "learning_rate": 5.942028985507246e-05,
      "loss": 0.8575,
      "step": 42
    },
    {
      "epoch": 0.09327548806941431,
      "grad_norm": 0.25762739777565,
      "learning_rate": 6.086956521739131e-05,
      "loss": 0.833,
      "step": 43
    },
    {
      "epoch": 0.09544468546637744,
      "grad_norm": 0.21620191633701324,
      "learning_rate": 6.231884057971015e-05,
      "loss": 0.8215,
      "step": 44
    },
    {
      "epoch": 0.09761388286334056,
      "grad_norm": 0.27904072403907776,
      "learning_rate": 6.376811594202898e-05,
      "loss": 0.7831,
      "step": 45
    },
    {
      "epoch": 0.09978308026030369,
      "grad_norm": 0.2075566202402115,
      "learning_rate": 6.521739130434783e-05,
      "loss": 0.7973,
      "step": 46
    },
    {
      "epoch": 0.1019522776572668,
      "grad_norm": 0.18121053278446198,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.7783,
      "step": 47
    },
    {
      "epoch": 0.10412147505422993,
      "grad_norm": 0.16793856024742126,
      "learning_rate": 6.811594202898552e-05,
      "loss": 0.7935,
      "step": 48
    },
    {
      "epoch": 0.10629067245119306,
      "grad_norm": 0.19764654338359833,
      "learning_rate": 6.956521739130436e-05,
      "loss": 0.771,
      "step": 49
    },
    {
      "epoch": 0.10845986984815618,
      "grad_norm": 0.17589959502220154,
      "learning_rate": 7.101449275362319e-05,
      "loss": 0.7754,
      "step": 50
    },
    {
      "epoch": 0.11062906724511931,
      "grad_norm": 0.1461871862411499,
      "learning_rate": 7.246376811594203e-05,
      "loss": 0.7735,
      "step": 51
    },
    {
      "epoch": 0.11279826464208242,
      "grad_norm": 0.14310722053050995,
      "learning_rate": 7.391304347826086e-05,
      "loss": 0.7593,
      "step": 52
    },
    {
      "epoch": 0.11496746203904555,
      "grad_norm": 0.13652552664279938,
      "learning_rate": 7.536231884057971e-05,
      "loss": 0.7243,
      "step": 53
    },
    {
      "epoch": 0.11713665943600868,
      "grad_norm": 0.13344769179821014,
      "learning_rate": 7.681159420289855e-05,
      "loss": 0.7199,
      "step": 54
    },
    {
      "epoch": 0.1193058568329718,
      "grad_norm": 0.15576966106891632,
      "learning_rate": 7.82608695652174e-05,
      "loss": 0.757,
      "step": 55
    },
    {
      "epoch": 0.12147505422993492,
      "grad_norm": 0.12085387855768204,
      "learning_rate": 7.971014492753623e-05,
      "loss": 0.7245,
      "step": 56
    },
    {
      "epoch": 0.12364425162689804,
      "grad_norm": 0.12265641242265701,
      "learning_rate": 8.115942028985508e-05,
      "loss": 0.7498,
      "step": 57
    },
    {
      "epoch": 0.12581344902386118,
      "grad_norm": 0.11970438063144684,
      "learning_rate": 8.260869565217392e-05,
      "loss": 0.7156,
      "step": 58
    },
    {
      "epoch": 0.1279826464208243,
      "grad_norm": 0.12227176874876022,
      "learning_rate": 8.405797101449276e-05,
      "loss": 0.7364,
      "step": 59
    },
    {
      "epoch": 0.1301518438177874,
      "grad_norm": 0.1107563003897667,
      "learning_rate": 8.55072463768116e-05,
      "loss": 0.6884,
      "step": 60
    },
    {
      "epoch": 0.13232104121475055,
      "grad_norm": 0.1294761449098587,
      "learning_rate": 8.695652173913044e-05,
      "loss": 0.7143,
      "step": 61
    },
    {
      "epoch": 0.13449023861171366,
      "grad_norm": 0.1295582801103592,
      "learning_rate": 8.840579710144929e-05,
      "loss": 0.7223,
      "step": 62
    },
    {
      "epoch": 0.13665943600867678,
      "grad_norm": 0.10569227486848831,
      "learning_rate": 8.985507246376813e-05,
      "loss": 0.6808,
      "step": 63
    },
    {
      "epoch": 0.13882863340563992,
      "grad_norm": 0.13948985934257507,
      "learning_rate": 9.130434782608696e-05,
      "loss": 0.7076,
      "step": 64
    },
    {
      "epoch": 0.14099783080260303,
      "grad_norm": 0.10574542731046677,
      "learning_rate": 9.27536231884058e-05,
      "loss": 0.6866,
      "step": 65
    },
    {
      "epoch": 0.14316702819956617,
      "grad_norm": 0.10029765218496323,
      "learning_rate": 9.420289855072463e-05,
      "loss": 0.6574,
      "step": 66
    },
    {
      "epoch": 0.14533622559652928,
      "grad_norm": 0.10338126868009567,
      "learning_rate": 9.565217391304348e-05,
      "loss": 0.7028,
      "step": 67
    },
    {
      "epoch": 0.1475054229934924,
      "grad_norm": 0.10685493797063828,
      "learning_rate": 9.710144927536232e-05,
      "loss": 0.708,
      "step": 68
    },
    {
      "epoch": 0.14967462039045554,
      "grad_norm": 0.10911104083061218,
      "learning_rate": 9.855072463768117e-05,
      "loss": 0.6891,
      "step": 69
    },
    {
      "epoch": 0.15184381778741865,
      "grad_norm": 0.10852951556444168,
      "learning_rate": 0.0001,
      "loss": 0.688,
      "step": 70
    },
    {
      "epoch": 0.1540130151843818,
      "grad_norm": 0.10942931473255157,
      "learning_rate": 0.00010144927536231885,
      "loss": 0.6853,
      "step": 71
    },
    {
      "epoch": 0.1561822125813449,
      "grad_norm": 0.10086481273174286,
      "learning_rate": 0.00010289855072463768,
      "loss": 0.6708,
      "step": 72
    },
    {
      "epoch": 0.15835140997830802,
      "grad_norm": 0.10610347241163254,
      "learning_rate": 0.00010434782608695653,
      "loss": 0.6763,
      "step": 73
    },
    {
      "epoch": 0.16052060737527116,
      "grad_norm": 0.09837855398654938,
      "learning_rate": 0.00010579710144927538,
      "loss": 0.6724,
      "step": 74
    },
    {
      "epoch": 0.16268980477223427,
      "grad_norm": 0.11700849235057831,
      "learning_rate": 0.00010724637681159421,
      "loss": 0.6798,
      "step": 75
    },
    {
      "epoch": 0.1648590021691974,
      "grad_norm": 0.11173564940690994,
      "learning_rate": 0.00010869565217391305,
      "loss": 0.6822,
      "step": 76
    },
    {
      "epoch": 0.16702819956616052,
      "grad_norm": 0.1051546111702919,
      "learning_rate": 0.00011014492753623188,
      "loss": 0.6613,
      "step": 77
    },
    {
      "epoch": 0.16919739696312364,
      "grad_norm": 0.12865373492240906,
      "learning_rate": 0.00011159420289855073,
      "loss": 0.6401,
      "step": 78
    },
    {
      "epoch": 0.17136659436008678,
      "grad_norm": 0.16578811407089233,
      "learning_rate": 0.00011304347826086956,
      "loss": 0.6303,
      "step": 79
    },
    {
      "epoch": 0.1735357917570499,
      "grad_norm": 0.16050302982330322,
      "learning_rate": 0.0001144927536231884,
      "loss": 0.6367,
      "step": 80
    },
    {
      "epoch": 0.175704989154013,
      "grad_norm": 0.20346365869045258,
      "learning_rate": 0.00011594202898550725,
      "loss": 0.6909,
      "step": 81
    },
    {
      "epoch": 0.17787418655097614,
      "grad_norm": 0.17011521756649017,
      "learning_rate": 0.0001173913043478261,
      "loss": 0.6209,
      "step": 82
    },
    {
      "epoch": 0.18004338394793926,
      "grad_norm": 0.14147906005382538,
      "learning_rate": 0.00011884057971014493,
      "loss": 0.644,
      "step": 83
    },
    {
      "epoch": 0.1822125813449024,
      "grad_norm": 0.13821075856685638,
      "learning_rate": 0.00012028985507246378,
      "loss": 0.6558,
      "step": 84
    },
    {
      "epoch": 0.1843817787418655,
      "grad_norm": 0.13610365986824036,
      "learning_rate": 0.00012173913043478263,
      "loss": 0.6416,
      "step": 85
    },
    {
      "epoch": 0.18655097613882862,
      "grad_norm": 0.18554848432540894,
      "learning_rate": 0.00012318840579710145,
      "loss": 0.6725,
      "step": 86
    },
    {
      "epoch": 0.18872017353579176,
      "grad_norm": 0.1432654708623886,
      "learning_rate": 0.0001246376811594203,
      "loss": 0.6358,
      "step": 87
    },
    {
      "epoch": 0.19088937093275488,
      "grad_norm": 0.14024198055267334,
      "learning_rate": 0.00012608695652173915,
      "loss": 0.6459,
      "step": 88
    },
    {
      "epoch": 0.19305856832971802,
      "grad_norm": 0.16156652569770813,
      "learning_rate": 0.00012753623188405797,
      "loss": 0.6487,
      "step": 89
    },
    {
      "epoch": 0.19522776572668113,
      "grad_norm": 0.13298125565052032,
      "learning_rate": 0.00012898550724637682,
      "loss": 0.6632,
      "step": 90
    },
    {
      "epoch": 0.19739696312364424,
      "grad_norm": 0.14112567901611328,
      "learning_rate": 0.00013043478260869567,
      "loss": 0.6646,
      "step": 91
    },
    {
      "epoch": 0.19956616052060738,
      "grad_norm": 0.136703222990036,
      "learning_rate": 0.00013188405797101452,
      "loss": 0.6561,
      "step": 92
    },
    {
      "epoch": 0.2017353579175705,
      "grad_norm": 0.14667080342769623,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.6473,
      "step": 93
    },
    {
      "epoch": 0.2039045553145336,
      "grad_norm": 0.1748354583978653,
      "learning_rate": 0.0001347826086956522,
      "loss": 0.646,
      "step": 94
    },
    {
      "epoch": 0.20607375271149675,
      "grad_norm": 0.12816791236400604,
      "learning_rate": 0.00013623188405797104,
      "loss": 0.6323,
      "step": 95
    },
    {
      "epoch": 0.20824295010845986,
      "grad_norm": 0.1466742753982544,
      "learning_rate": 0.00013768115942028986,
      "loss": 0.6697,
      "step": 96
    },
    {
      "epoch": 0.210412147505423,
      "grad_norm": 0.20765802264213562,
      "learning_rate": 0.0001391304347826087,
      "loss": 0.6518,
      "step": 97
    },
    {
      "epoch": 0.21258134490238612,
      "grad_norm": 0.226384699344635,
      "learning_rate": 0.00014057971014492753,
      "loss": 0.6236,
      "step": 98
    },
    {
      "epoch": 0.21475054229934923,
      "grad_norm": 0.21525003015995026,
      "learning_rate": 0.00014202898550724638,
      "loss": 0.642,
      "step": 99
    },
    {
      "epoch": 0.21691973969631237,
      "grad_norm": 0.1788046807050705,
      "learning_rate": 0.0001434782608695652,
      "loss": 0.6381,
      "step": 100
    },
    {
      "epoch": 0.21908893709327548,
      "grad_norm": 0.15480148792266846,
      "learning_rate": 0.00014492753623188405,
      "loss": 0.6123,
      "step": 101
    },
    {
      "epoch": 0.22125813449023862,
      "grad_norm": 0.17489440739154816,
      "learning_rate": 0.0001463768115942029,
      "loss": 0.661,
      "step": 102
    },
    {
      "epoch": 0.22342733188720174,
      "grad_norm": 0.2911432981491089,
      "learning_rate": 0.00014782608695652173,
      "loss": 0.6613,
      "step": 103
    },
    {
      "epoch": 0.22559652928416485,
      "grad_norm": 0.6389259099960327,
      "learning_rate": 0.00014927536231884058,
      "loss": 0.6778,
      "step": 104
    },
    {
      "epoch": 0.227765726681128,
      "grad_norm": 0.9701236486434937,
      "learning_rate": 0.00015072463768115943,
      "loss": 0.6574,
      "step": 105
    },
    {
      "epoch": 0.2299349240780911,
      "grad_norm": 0.5144535899162292,
      "learning_rate": 0.00015217391304347827,
      "loss": 0.6917,
      "step": 106
    },
    {
      "epoch": 0.23210412147505424,
      "grad_norm": 0.4424351155757904,
      "learning_rate": 0.0001536231884057971,
      "loss": 0.6468,
      "step": 107
    },
    {
      "epoch": 0.23427331887201736,
      "grad_norm": 0.2877040505409241,
      "learning_rate": 0.00015507246376811595,
      "loss": 0.625,
      "step": 108
    },
    {
      "epoch": 0.23644251626898047,
      "grad_norm": 0.4436647891998291,
      "learning_rate": 0.0001565217391304348,
      "loss": 0.6776,
      "step": 109
    },
    {
      "epoch": 0.2386117136659436,
      "grad_norm": 0.2553921639919281,
      "learning_rate": 0.00015797101449275362,
      "loss": 0.6132,
      "step": 110
    },
    {
      "epoch": 0.24078091106290672,
      "grad_norm": 0.4680798053741455,
      "learning_rate": 0.00015942028985507247,
      "loss": 0.6524,
      "step": 111
    },
    {
      "epoch": 0.24295010845986983,
      "grad_norm": 0.4368642270565033,
      "learning_rate": 0.00016086956521739132,
      "loss": 0.678,
      "step": 112
    },
    {
      "epoch": 0.24511930585683298,
      "grad_norm": 0.2609938085079193,
      "learning_rate": 0.00016231884057971017,
      "loss": 0.6652,
      "step": 113
    },
    {
      "epoch": 0.2472885032537961,
      "grad_norm": 0.2643669843673706,
      "learning_rate": 0.000163768115942029,
      "loss": 0.6628,
      "step": 114
    },
    {
      "epoch": 0.24945770065075923,
      "grad_norm": 0.1935800462961197,
      "learning_rate": 0.00016521739130434784,
      "loss": 0.6195,
      "step": 115
    },
    {
      "epoch": 0.25162689804772237,
      "grad_norm": 0.2796177268028259,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.6686,
      "step": 116
    },
    {
      "epoch": 0.25379609544468545,
      "grad_norm": 0.20364832878112793,
      "learning_rate": 0.0001681159420289855,
      "loss": 0.6581,
      "step": 117
    },
    {
      "epoch": 0.2559652928416486,
      "grad_norm": 0.24016427993774414,
      "learning_rate": 0.00016956521739130436,
      "loss": 0.6364,
      "step": 118
    },
    {
      "epoch": 0.25813449023861174,
      "grad_norm": 0.1821931004524231,
      "learning_rate": 0.0001710144927536232,
      "loss": 0.635,
      "step": 119
    },
    {
      "epoch": 0.2603036876355748,
      "grad_norm": 0.20883452892303467,
      "learning_rate": 0.00017246376811594206,
      "loss": 0.6342,
      "step": 120
    },
    {
      "epoch": 0.26247288503253796,
      "grad_norm": 0.18570640683174133,
      "learning_rate": 0.00017391304347826088,
      "loss": 0.6438,
      "step": 121
    },
    {
      "epoch": 0.2646420824295011,
      "grad_norm": 0.17819873988628387,
      "learning_rate": 0.00017536231884057973,
      "loss": 0.644,
      "step": 122
    },
    {
      "epoch": 0.2668112798264642,
      "grad_norm": 0.1719266027212143,
      "learning_rate": 0.00017681159420289858,
      "loss": 0.6372,
      "step": 123
    },
    {
      "epoch": 0.26898047722342733,
      "grad_norm": 0.18508559465408325,
      "learning_rate": 0.0001782608695652174,
      "loss": 0.645,
      "step": 124
    },
    {
      "epoch": 0.27114967462039047,
      "grad_norm": 0.1743556410074234,
      "learning_rate": 0.00017971014492753625,
      "loss": 0.6533,
      "step": 125
    },
    {
      "epoch": 0.27331887201735355,
      "grad_norm": 0.167171448469162,
      "learning_rate": 0.00018115942028985507,
      "loss": 0.5842,
      "step": 126
    },
    {
      "epoch": 0.2754880694143167,
      "grad_norm": 0.1678585261106491,
      "learning_rate": 0.00018260869565217392,
      "loss": 0.6269,
      "step": 127
    },
    {
      "epoch": 0.27765726681127983,
      "grad_norm": 0.24307562410831451,
      "learning_rate": 0.00018405797101449275,
      "loss": 0.6305,
      "step": 128
    },
    {
      "epoch": 0.279826464208243,
      "grad_norm": 0.2230542004108429,
      "learning_rate": 0.0001855072463768116,
      "loss": 0.6637,
      "step": 129
    },
    {
      "epoch": 0.28199566160520606,
      "grad_norm": 0.19641122221946716,
      "learning_rate": 0.00018695652173913045,
      "loss": 0.6399,
      "step": 130
    },
    {
      "epoch": 0.2841648590021692,
      "grad_norm": 0.27579671144485474,
      "learning_rate": 0.00018840579710144927,
      "loss": 0.6451,
      "step": 131
    },
    {
      "epoch": 0.28633405639913234,
      "grad_norm": 0.3411884009838104,
      "learning_rate": 0.00018985507246376812,
      "loss": 0.6305,
      "step": 132
    },
    {
      "epoch": 0.2885032537960954,
      "grad_norm": 0.3600616157054901,
      "learning_rate": 0.00019130434782608697,
      "loss": 0.6387,
      "step": 133
    },
    {
      "epoch": 0.29067245119305857,
      "grad_norm": 0.5395304560661316,
      "learning_rate": 0.0001927536231884058,
      "loss": 0.6105,
      "step": 134
    },
    {
      "epoch": 0.2928416485900217,
      "grad_norm": 0.6782134175300598,
      "learning_rate": 0.00019420289855072464,
      "loss": 0.6576,
      "step": 135
    },
    {
      "epoch": 0.2950108459869848,
      "grad_norm": 0.5986435413360596,
      "learning_rate": 0.0001956521739130435,
      "loss": 0.6214,
      "step": 136
    },
    {
      "epoch": 0.29718004338394793,
      "grad_norm": 0.23965002596378326,
      "learning_rate": 0.00019710144927536234,
      "loss": 0.6391,
      "step": 137
    },
    {
      "epoch": 0.2993492407809111,
      "grad_norm": 0.3806755840778351,
      "learning_rate": 0.00019855072463768116,
      "loss": 0.6202,
      "step": 138
    },
    {
      "epoch": 0.30151843817787416,
      "grad_norm": 0.2182237058877945,
      "learning_rate": 0.0002,
      "loss": 0.6523,
      "step": 139
    },
    {
      "epoch": 0.3036876355748373,
      "grad_norm": 0.32559895515441895,
      "learning_rate": 0.0001999996816309684,
      "loss": 0.6325,
      "step": 140
    },
    {
      "epoch": 0.30585683297180044,
      "grad_norm": 0.2741132378578186,
      "learning_rate": 0.00019999872652590078,
      "loss": 0.6296,
      "step": 141
    },
    {
      "epoch": 0.3080260303687636,
      "grad_norm": 0.19383494555950165,
      "learning_rate": 0.00019999713469087867,
      "loss": 0.6072,
      "step": 142
    },
    {
      "epoch": 0.31019522776572667,
      "grad_norm": 0.32313209772109985,
      "learning_rate": 0.00019999490613603784,
      "loss": 0.6464,
      "step": 143
    },
    {
      "epoch": 0.3123644251626898,
      "grad_norm": 0.20122329890727997,
      "learning_rate": 0.0001999920408755684,
      "loss": 0.6594,
      "step": 144
    },
    {
      "epoch": 0.31453362255965295,
      "grad_norm": 0.18296824395656586,
      "learning_rate": 0.00019998853892771453,
      "loss": 0.6352,
      "step": 145
    },
    {
      "epoch": 0.31670281995661603,
      "grad_norm": 0.200248122215271,
      "learning_rate": 0.00019998440031477447,
      "loss": 0.6441,
      "step": 146
    },
    {
      "epoch": 0.3188720173535792,
      "grad_norm": 0.18448396027088165,
      "learning_rate": 0.0001999796250631003,
      "loss": 0.6222,
      "step": 147
    },
    {
      "epoch": 0.3210412147505423,
      "grad_norm": 0.18192757666110992,
      "learning_rate": 0.00019997421320309795,
      "loss": 0.6286,
      "step": 148
    },
    {
      "epoch": 0.3232104121475054,
      "grad_norm": 0.23341625928878784,
      "learning_rate": 0.00019996816476922677,
      "loss": 0.6591,
      "step": 149
    },
    {
      "epoch": 0.32537960954446854,
      "grad_norm": 0.25029829144477844,
      "learning_rate": 0.0001999614797999994,
      "loss": 0.6366,
      "step": 150
    },
    {
      "epoch": 0.3275488069414317,
      "grad_norm": 0.23827116191387177,
      "learning_rate": 0.00019995415833798158,
      "loss": 0.6264,
      "step": 151
    },
    {
      "epoch": 0.3297180043383948,
      "grad_norm": 0.23082979023456573,
      "learning_rate": 0.0001999462004297919,
      "loss": 0.6038,
      "step": 152
    },
    {
      "epoch": 0.3318872017353579,
      "grad_norm": 0.23424038290977478,
      "learning_rate": 0.00019993760612610134,
      "loss": 0.6299,
      "step": 153
    },
    {
      "epoch": 0.33405639913232105,
      "grad_norm": 0.3439392149448395,
      "learning_rate": 0.00019992837548163316,
      "loss": 0.6767,
      "step": 154
    },
    {
      "epoch": 0.3362255965292842,
      "grad_norm": 0.6126989126205444,
      "learning_rate": 0.00019991850855516233,
      "loss": 0.6031,
      "step": 155
    },
    {
      "epoch": 0.3383947939262473,
      "grad_norm": 0.7207016348838806,
      "learning_rate": 0.00019990800540951534,
      "loss": 0.6191,
      "step": 156
    },
    {
      "epoch": 0.3405639913232104,
      "grad_norm": 0.7369017601013184,
      "learning_rate": 0.00019989686611156972,
      "loss": 0.6689,
      "step": 157
    },
    {
      "epoch": 0.34273318872017355,
      "grad_norm": 0.37963396310806274,
      "learning_rate": 0.00019988509073225362,
      "loss": 0.6258,
      "step": 158
    },
    {
      "epoch": 0.34490238611713664,
      "grad_norm": 0.415025532245636,
      "learning_rate": 0.00019987267934654538,
      "loss": 0.6269,
      "step": 159
    },
    {
      "epoch": 0.3470715835140998,
      "grad_norm": 0.2826947867870331,
      "learning_rate": 0.000199859632033473,
      "loss": 0.6747,
      "step": 160
    },
    {
      "epoch": 0.3492407809110629,
      "grad_norm": 0.27534136176109314,
      "learning_rate": 0.0001998459488761137,
      "loss": 0.6366,
      "step": 161
    },
    {
      "epoch": 0.351409978308026,
      "grad_norm": 0.37555989623069763,
      "learning_rate": 0.0001998316299615933,
      "loss": 0.656,
      "step": 162
    },
    {
      "epoch": 0.35357917570498915,
      "grad_norm": 0.22409367561340332,
      "learning_rate": 0.00019981667538108587,
      "loss": 0.5981,
      "step": 163
    },
    {
      "epoch": 0.3557483731019523,
      "grad_norm": 0.42973995208740234,
      "learning_rate": 0.00019980108522981284,
      "loss": 0.6358,
      "step": 164
    },
    {
      "epoch": 0.3579175704989154,
      "grad_norm": 0.4034169018268585,
      "learning_rate": 0.00019978485960704266,
      "loss": 0.6554,
      "step": 165
    },
    {
      "epoch": 0.3600867678958785,
      "grad_norm": 0.2308664172887802,
      "learning_rate": 0.00019976799861609008,
      "loss": 0.645,
      "step": 166
    },
    {
      "epoch": 0.36225596529284165,
      "grad_norm": 0.32269302010536194,
      "learning_rate": 0.0001997505023643154,
      "loss": 0.6289,
      "step": 167
    },
    {
      "epoch": 0.3644251626898048,
      "grad_norm": 0.26976749300956726,
      "learning_rate": 0.00019973237096312393,
      "loss": 0.6105,
      "step": 168
    },
    {
      "epoch": 0.3665943600867679,
      "grad_norm": 0.2500403821468353,
      "learning_rate": 0.00019971360452796522,
      "loss": 0.6172,
      "step": 169
    },
    {
      "epoch": 0.368763557483731,
      "grad_norm": 0.4227772355079651,
      "learning_rate": 0.00019969420317833227,
      "loss": 0.6573,
      "step": 170
    },
    {
      "epoch": 0.37093275488069416,
      "grad_norm": 0.49822697043418884,
      "learning_rate": 0.0001996741670377609,
      "loss": 0.6813,
      "step": 171
    },
    {
      "epoch": 0.37310195227765725,
      "grad_norm": 0.36717575788497925,
      "learning_rate": 0.0001996534962338288,
      "loss": 0.6241,
      "step": 172
    },
    {
      "epoch": 0.3752711496746204,
      "grad_norm": 0.22469429671764374,
      "learning_rate": 0.00019963219089815488,
      "loss": 0.6571,
      "step": 173
    },
    {
      "epoch": 0.3774403470715835,
      "grad_norm": 0.4309958517551422,
      "learning_rate": 0.0001996102511663983,
      "loss": 0.6483,
      "step": 174
    },
    {
      "epoch": 0.3796095444685466,
      "grad_norm": 0.5014271140098572,
      "learning_rate": 0.0001995876771782577,
      "loss": 0.635,
      "step": 175
    },
    {
      "epoch": 0.38177874186550975,
      "grad_norm": 0.5144173502922058,
      "learning_rate": 0.00019956446907747026,
      "loss": 0.6605,
      "step": 176
    },
    {
      "epoch": 0.3839479392624729,
      "grad_norm": 0.5632807016372681,
      "learning_rate": 0.00019954062701181078,
      "loss": 0.6815,
      "step": 177
    },
    {
      "epoch": 0.38611713665943603,
      "grad_norm": 0.6516217589378357,
      "learning_rate": 0.00019951615113309075,
      "loss": 0.619,
      "step": 178
    },
    {
      "epoch": 0.3882863340563991,
      "grad_norm": 0.500882089138031,
      "learning_rate": 0.00019949104159715743,
      "loss": 0.6245,
      "step": 179
    },
    {
      "epoch": 0.39045553145336226,
      "grad_norm": 0.26451072096824646,
      "learning_rate": 0.0001994652985638928,
      "loss": 0.6082,
      "step": 180
    },
    {
      "epoch": 0.3926247288503254,
      "grad_norm": 0.4731830954551697,
      "learning_rate": 0.00019943892219721253,
      "loss": 0.6651,
      "step": 181
    },
    {
      "epoch": 0.3947939262472885,
      "grad_norm": 0.455352246761322,
      "learning_rate": 0.00019941191266506497,
      "loss": 0.6563,
      "step": 182
    },
    {
      "epoch": 0.3969631236442516,
      "grad_norm": 0.39906707406044006,
      "learning_rate": 0.00019938427013943015,
      "loss": 0.6574,
      "step": 183
    },
    {
      "epoch": 0.39913232104121477,
      "grad_norm": 0.31368449330329895,
      "learning_rate": 0.0001993559947963185,
      "loss": 0.6282,
      "step": 184
    },
    {
      "epoch": 0.40130151843817785,
      "grad_norm": 0.3973885476589203,
      "learning_rate": 0.00019932708681576992,
      "loss": 0.6127,
      "step": 185
    },
    {
      "epoch": 0.403470715835141,
      "grad_norm": 0.3392525613307953,
      "learning_rate": 0.0001992975463818525,
      "loss": 0.6423,
      "step": 186
    },
    {
      "epoch": 0.40563991323210413,
      "grad_norm": 0.38504526019096375,
      "learning_rate": 0.00019926737368266144,
      "loss": 0.6372,
      "step": 187
    },
    {
      "epoch": 0.4078091106290672,
      "grad_norm": 0.44855180382728577,
      "learning_rate": 0.00019923656891031782,
      "loss": 0.6312,
      "step": 188
    },
    {
      "epoch": 0.40997830802603036,
      "grad_norm": 0.37712424993515015,
      "learning_rate": 0.00019920513226096733,
      "loss": 0.6549,
      "step": 189
    },
    {
      "epoch": 0.4121475054229935,
      "grad_norm": 0.2295152097940445,
      "learning_rate": 0.00019917306393477907,
      "loss": 0.6163,
      "step": 190
    },
    {
      "epoch": 0.41431670281995664,
      "grad_norm": 0.3899190127849579,
      "learning_rate": 0.00019914036413594432,
      "loss": 0.62,
      "step": 191
    },
    {
      "epoch": 0.4164859002169197,
      "grad_norm": 0.40775805711746216,
      "learning_rate": 0.00019910703307267512,
      "loss": 0.6387,
      "step": 192
    },
    {
      "epoch": 0.41865509761388287,
      "grad_norm": 0.42771974205970764,
      "learning_rate": 0.00019907307095720303,
      "loss": 0.6086,
      "step": 193
    },
    {
      "epoch": 0.420824295010846,
      "grad_norm": 0.35891193151474,
      "learning_rate": 0.00019903847800577777,
      "loss": 0.6255,
      "step": 194
    },
    {
      "epoch": 0.4229934924078091,
      "grad_norm": 0.31806233525276184,
      "learning_rate": 0.00019900325443866583,
      "loss": 0.5984,
      "step": 195
    },
    {
      "epoch": 0.42516268980477223,
      "grad_norm": 0.39749711751937866,
      "learning_rate": 0.00019896740048014908,
      "loss": 0.6573,
      "step": 196
    },
    {
      "epoch": 0.42733188720173537,
      "grad_norm": 0.44788193702697754,
      "learning_rate": 0.0001989309163585233,
      "loss": 0.6067,
      "step": 197
    },
    {
      "epoch": 0.42950108459869846,
      "grad_norm": 0.5522041320800781,
      "learning_rate": 0.0001988938023060968,
      "loss": 0.6779,
      "step": 198
    },
    {
      "epoch": 0.4316702819956616,
      "grad_norm": 0.812641978263855,
      "learning_rate": 0.00019885605855918885,
      "loss": 0.6724,
      "step": 199
    },
    {
      "epoch": 0.43383947939262474,
      "grad_norm": 0.8492263555526733,
      "learning_rate": 0.0001988176853581283,
      "loss": 0.6341,
      "step": 200
    },
    {
      "epoch": 0.4360086767895879,
      "grad_norm": 0.3399752378463745,
      "learning_rate": 0.0001987786829472519,
      "loss": 0.6301,
      "step": 201
    },
    {
      "epoch": 0.43817787418655096,
      "grad_norm": 0.4870372414588928,
      "learning_rate": 0.00019873905157490285,
      "loss": 0.6215,
      "step": 202
    },
    {
      "epoch": 0.4403470715835141,
      "grad_norm": 0.5011846423149109,
      "learning_rate": 0.00019869879149342915,
      "loss": 0.6266,
      "step": 203
    },
    {
      "epoch": 0.44251626898047725,
      "grad_norm": 0.2909952700138092,
      "learning_rate": 0.00019865790295918212,
      "loss": 0.657,
      "step": 204
    },
    {
      "epoch": 0.44468546637744033,
      "grad_norm": 0.48578405380249023,
      "learning_rate": 0.0001986163862325146,
      "loss": 0.657,
      "step": 205
    },
    {
      "epoch": 0.44685466377440347,
      "grad_norm": 0.5385676622390747,
      "learning_rate": 0.00019857424157777935,
      "loss": 0.6225,
      "step": 206
    },
    {
      "epoch": 0.4490238611713666,
      "grad_norm": 0.44127026200294495,
      "learning_rate": 0.0001985314692633275,
      "loss": 0.6477,
      "step": 207
    },
    {
      "epoch": 0.4511930585683297,
      "grad_norm": 0.29449865221977234,
      "learning_rate": 0.0001984880695615066,
      "loss": 0.6372,
      "step": 208
    },
    {
      "epoch": 0.45336225596529284,
      "grad_norm": 0.2879779040813446,
      "learning_rate": 0.0001984440427486591,
      "loss": 0.6014,
      "step": 209
    },
    {
      "epoch": 0.455531453362256,
      "grad_norm": 0.4030214846134186,
      "learning_rate": 0.00019839938910512045,
      "loss": 0.6277,
      "step": 210
    },
    {
      "epoch": 0.45770065075921906,
      "grad_norm": 0.42353007197380066,
      "learning_rate": 0.0001983541089152174,
      "loss": 0.6338,
      "step": 211
    },
    {
      "epoch": 0.4598698481561822,
      "grad_norm": 0.40985336899757385,
      "learning_rate": 0.0001983082024672662,
      "loss": 0.6479,
      "step": 212
    },
    {
      "epoch": 0.46203904555314534,
      "grad_norm": 0.461015909910202,
      "learning_rate": 0.0001982616700535706,
      "loss": 0.6522,
      "step": 213
    },
    {
      "epoch": 0.4642082429501085,
      "grad_norm": 0.9165703654289246,
      "learning_rate": 0.00019821451197042026,
      "loss": 0.6509,
      "step": 214
    },
    {
      "epoch": 0.46637744034707157,
      "grad_norm": 1.504171371459961,
      "learning_rate": 0.00019816672851808863,
      "loss": 0.6567,
      "step": 215
    },
    {
      "epoch": 0.4685466377440347,
      "grad_norm": 0.4625106453895569,
      "learning_rate": 0.0001981183200008311,
      "loss": 0.6178,
      "step": 216
    },
    {
      "epoch": 0.47071583514099785,
      "grad_norm": 0.9716832637786865,
      "learning_rate": 0.0001980692867268832,
      "loss": 0.6661,
      "step": 217
    },
    {
      "epoch": 0.47288503253796094,
      "grad_norm": 1.0294218063354492,
      "learning_rate": 0.00019801962900845835,
      "loss": 0.6168,
      "step": 218
    },
    {
      "epoch": 0.4750542299349241,
      "grad_norm": 0.4468556344509125,
      "learning_rate": 0.0001979693471617462,
      "loss": 0.6373,
      "step": 219
    },
    {
      "epoch": 0.4772234273318872,
      "grad_norm": 0.7019622325897217,
      "learning_rate": 0.0001979184415069104,
      "loss": 0.6505,
      "step": 220
    },
    {
      "epoch": 0.4793926247288503,
      "grad_norm": 0.9103279709815979,
      "learning_rate": 0.00019786691236808664,
      "loss": 0.6485,
      "step": 221
    },
    {
      "epoch": 0.48156182212581344,
      "grad_norm": 0.5492876172065735,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.6164,
      "step": 222
    },
    {
      "epoch": 0.4837310195227766,
      "grad_norm": 0.5885651707649231,
      "learning_rate": 0.00019776198495486565,
      "loss": 0.6189,
      "step": 223
    },
    {
      "epoch": 0.48590021691973967,
      "grad_norm": 0.49900850653648376,
      "learning_rate": 0.00019770858734858126,
      "loss": 0.6286,
      "step": 224
    },
    {
      "epoch": 0.4880694143167028,
      "grad_norm": 0.5765913128852844,
      "learning_rate": 0.00019765456759453012,
      "loss": 0.6215,
      "step": 225
    },
    {
      "epoch": 0.49023861171366595,
      "grad_norm": 0.6540525555610657,
      "learning_rate": 0.00019759992603667667,
      "loss": 0.6325,
      "step": 226
    },
    {
      "epoch": 0.4924078091106291,
      "grad_norm": 0.45637235045433044,
      "learning_rate": 0.0001975446630229445,
      "loss": 0.6254,
      "step": 227
    },
    {
      "epoch": 0.4945770065075922,
      "grad_norm": 0.27883636951446533,
      "learning_rate": 0.00019748877890521426,
      "loss": 0.6414,
      "step": 228
    },
    {
      "epoch": 0.4967462039045553,
      "grad_norm": 0.4387315511703491,
      "learning_rate": 0.00019743227403932134,
      "loss": 0.6562,
      "step": 229
    },
    {
      "epoch": 0.49891540130151846,
      "grad_norm": 0.38010311126708984,
      "learning_rate": 0.0001973751487850538,
      "loss": 0.624,
      "step": 230
    },
    {
      "epoch": 0.5010845986984815,
      "grad_norm": 0.3720833361148834,
      "learning_rate": 0.00019731740350614985,
      "loss": 0.6428,
      "step": 231
    },
    {
      "epoch": 0.5032537960954447,
      "grad_norm": 0.7834355235099792,
      "learning_rate": 0.00019725903857029564,
      "loss": 0.6504,
      "step": 232
    },
    {
      "epoch": 0.5054229934924078,
      "grad_norm": 0.7910520434379578,
      "learning_rate": 0.00019720005434912294,
      "loss": 0.6182,
      "step": 233
    },
    {
      "epoch": 0.5075921908893709,
      "grad_norm": 0.435019314289093,
      "learning_rate": 0.00019714045121820676,
      "loss": 0.6816,
      "step": 234
    },
    {
      "epoch": 0.5097613882863341,
      "grad_norm": 0.3282682001590729,
      "learning_rate": 0.00019708022955706292,
      "loss": 0.6233,
      "step": 235
    },
    {
      "epoch": 0.5119305856832972,
      "grad_norm": 0.49331432580947876,
      "learning_rate": 0.00019701938974914566,
      "loss": 0.6126,
      "step": 236
    },
    {
      "epoch": 0.5140997830802603,
      "grad_norm": 0.42824822664260864,
      "learning_rate": 0.00019695793218184516,
      "loss": 0.6245,
      "step": 237
    },
    {
      "epoch": 0.5162689804772235,
      "grad_norm": 0.31621289253234863,
      "learning_rate": 0.00019689585724648516,
      "loss": 0.6501,
      "step": 238
    },
    {
      "epoch": 0.5184381778741866,
      "grad_norm": 0.4137878715991974,
      "learning_rate": 0.00019683316533832042,
      "loss": 0.6015,
      "step": 239
    },
    {
      "epoch": 0.5206073752711496,
      "grad_norm": 0.6244151592254639,
      "learning_rate": 0.00019676985685653414,
      "loss": 0.6476,
      "step": 240
    },
    {
      "epoch": 0.5227765726681128,
      "grad_norm": 0.4826190173625946,
      "learning_rate": 0.00019670593220423558,
      "loss": 0.6376,
      "step": 241
    },
    {
      "epoch": 0.5249457700650759,
      "grad_norm": 0.3096715211868286,
      "learning_rate": 0.0001966413917884573,
      "loss": 0.5759,
      "step": 242
    },
    {
      "epoch": 0.527114967462039,
      "grad_norm": 0.4366465210914612,
      "learning_rate": 0.0001965762360201527,
      "loss": 0.6597,
      "step": 243
    },
    {
      "epoch": 0.5292841648590022,
      "grad_norm": 0.41002994775772095,
      "learning_rate": 0.00019651046531419332,
      "loss": 0.6047,
      "step": 244
    },
    {
      "epoch": 0.5314533622559653,
      "grad_norm": 0.46513354778289795,
      "learning_rate": 0.00019644408008936636,
      "loss": 0.6259,
      "step": 245
    },
    {
      "epoch": 0.5336225596529284,
      "grad_norm": 0.5387598276138306,
      "learning_rate": 0.00019637708076837175,
      "loss": 0.6398,
      "step": 246
    },
    {
      "epoch": 0.5357917570498916,
      "grad_norm": 0.5738980174064636,
      "learning_rate": 0.00019630946777781966,
      "loss": 0.653,
      "step": 247
    },
    {
      "epoch": 0.5379609544468547,
      "grad_norm": 0.7524402737617493,
      "learning_rate": 0.0001962412415482278,
      "loss": 0.6567,
      "step": 248
    },
    {
      "epoch": 0.5401301518438177,
      "grad_norm": 1.0303419828414917,
      "learning_rate": 0.0001961724025140185,
      "loss": 0.6563,
      "step": 249
    },
    {
      "epoch": 0.5422993492407809,
      "grad_norm": 1.353436827659607,
      "learning_rate": 0.0001961029511135161,
      "loss": 0.6387,
      "step": 250
    },
    {
      "epoch": 0.544468546637744,
      "grad_norm": 0.4112069308757782,
      "learning_rate": 0.00019603288778894407,
      "loss": 0.6027,
      "step": 251
    },
    {
      "epoch": 0.5466377440347071,
      "grad_norm": 1.217024803161621,
      "learning_rate": 0.0001959622129864223,
      "loss": 0.6901,
      "step": 252
    },
    {
      "epoch": 0.5488069414316703,
      "grad_norm": 1.6233456134796143,
      "learning_rate": 0.00019589092715596417,
      "loss": 0.6462,
      "step": 253
    },
    {
      "epoch": 0.5509761388286334,
      "grad_norm": 0.6854282021522522,
      "learning_rate": 0.0001958190307514737,
      "loss": 0.5939,
      "step": 254
    },
    {
      "epoch": 0.5531453362255966,
      "grad_norm": 1.5472182035446167,
      "learning_rate": 0.00019574652423074262,
      "loss": 0.641,
      "step": 255
    },
    {
      "epoch": 0.5553145336225597,
      "grad_norm": 0.6749058961868286,
      "learning_rate": 0.00019567340805544758,
      "loss": 0.6267,
      "step": 256
    },
    {
      "epoch": 0.5574837310195228,
      "grad_norm": 1.5917607545852661,
      "learning_rate": 0.00019559968269114707,
      "loss": 0.6589,
      "step": 257
    },
    {
      "epoch": 0.559652928416486,
      "grad_norm": 0.8307267427444458,
      "learning_rate": 0.0001955253486072786,
      "loss": 0.6719,
      "step": 258
    },
    {
      "epoch": 0.561822125813449,
      "grad_norm": 1.301090121269226,
      "learning_rate": 0.0001954504062771555,
      "loss": 0.6378,
      "step": 259
    },
    {
      "epoch": 0.5639913232104121,
      "grad_norm": 0.8628901243209839,
      "learning_rate": 0.0001953748561779642,
      "loss": 0.6485,
      "step": 260
    },
    {
      "epoch": 0.5661605206073753,
      "grad_norm": 1.6593358516693115,
      "learning_rate": 0.00019529869879076088,
      "loss": 0.6474,
      "step": 261
    },
    {
      "epoch": 0.5683297180043384,
      "grad_norm": 1.0214110612869263,
      "learning_rate": 0.00019522193460046864,
      "loss": 0.64,
      "step": 262
    },
    {
      "epoch": 0.5704989154013015,
      "grad_norm": 0.9431339502334595,
      "learning_rate": 0.00019514456409587422,
      "loss": 0.6503,
      "step": 263
    },
    {
      "epoch": 0.5726681127982647,
      "grad_norm": 0.7939339280128479,
      "learning_rate": 0.0001950665877696252,
      "loss": 0.6267,
      "step": 264
    },
    {
      "epoch": 0.5748373101952278,
      "grad_norm": 0.585902214050293,
      "learning_rate": 0.00019498800611822645,
      "loss": 0.5936,
      "step": 265
    },
    {
      "epoch": 0.5770065075921909,
      "grad_norm": 1.0052146911621094,
      "learning_rate": 0.00019490881964203725,
      "loss": 0.6376,
      "step": 266
    },
    {
      "epoch": 0.579175704989154,
      "grad_norm": 0.8818138837814331,
      "learning_rate": 0.00019482902884526807,
      "loss": 0.6596,
      "step": 267
    },
    {
      "epoch": 0.5813449023861171,
      "grad_norm": 0.5019932985305786,
      "learning_rate": 0.00019474863423597728,
      "loss": 0.605,
      "step": 268
    },
    {
      "epoch": 0.5835140997830802,
      "grad_norm": 0.5718139410018921,
      "learning_rate": 0.0001946676363260679,
      "loss": 0.6433,
      "step": 269
    },
    {
      "epoch": 0.5856832971800434,
      "grad_norm": 0.4019048810005188,
      "learning_rate": 0.00019458603563128453,
      "loss": 0.6048,
      "step": 270
    },
    {
      "epoch": 0.5878524945770065,
      "grad_norm": 0.5700424313545227,
      "learning_rate": 0.00019450383267120982,
      "loss": 0.6464,
      "step": 271
    },
    {
      "epoch": 0.5900216919739696,
      "grad_norm": 0.5973300933837891,
      "learning_rate": 0.0001944210279692613,
      "loss": 0.601,
      "step": 272
    },
    {
      "epoch": 0.5921908893709328,
      "grad_norm": 0.5007997751235962,
      "learning_rate": 0.00019433762205268805,
      "loss": 0.633,
      "step": 273
    },
    {
      "epoch": 0.5943600867678959,
      "grad_norm": 0.5061407685279846,
      "learning_rate": 0.00019425361545256727,
      "loss": 0.6347,
      "step": 274
    },
    {
      "epoch": 0.596529284164859,
      "grad_norm": 0.3419846296310425,
      "learning_rate": 0.00019416900870380098,
      "loss": 0.6002,
      "step": 275
    },
    {
      "epoch": 0.5986984815618221,
      "grad_norm": 0.5171356201171875,
      "learning_rate": 0.0001940838023451125,
      "loss": 0.6139,
      "step": 276
    },
    {
      "epoch": 0.6008676789587852,
      "grad_norm": 0.4738871157169342,
      "learning_rate": 0.0001939979969190432,
      "loss": 0.592,
      "step": 277
    },
    {
      "epoch": 0.6030368763557483,
      "grad_norm": 0.43548280000686646,
      "learning_rate": 0.00019391159297194887,
      "loss": 0.614,
      "step": 278
    },
    {
      "epoch": 0.6052060737527115,
      "grad_norm": 0.7416541576385498,
      "learning_rate": 0.00019382459105399632,
      "loss": 0.6574,
      "step": 279
    },
    {
      "epoch": 0.6073752711496746,
      "grad_norm": 0.7889977693557739,
      "learning_rate": 0.00019373699171915988,
      "loss": 0.6312,
      "step": 280
    },
    {
      "epoch": 0.6095444685466378,
      "grad_norm": 0.6459334492683411,
      "learning_rate": 0.0001936487955252179,
      "loss": 0.6068,
      "step": 281
    },
    {
      "epoch": 0.6117136659436009,
      "grad_norm": 0.7178688049316406,
      "learning_rate": 0.00019356000303374904,
      "loss": 0.694,
      "step": 282
    },
    {
      "epoch": 0.613882863340564,
      "grad_norm": 0.7192567586898804,
      "learning_rate": 0.00019347061481012894,
      "loss": 0.5886,
      "step": 283
    },
    {
      "epoch": 0.6160520607375272,
      "grad_norm": 0.4567294120788574,
      "learning_rate": 0.00019338063142352644,
      "loss": 0.6373,
      "step": 284
    },
    {
      "epoch": 0.6182212581344902,
      "grad_norm": 0.568526566028595,
      "learning_rate": 0.00019329005344690002,
      "loss": 0.6259,
      "step": 285
    },
    {
      "epoch": 0.6203904555314533,
      "grad_norm": 0.7539410591125488,
      "learning_rate": 0.00019319888145699415,
      "loss": 0.6698,
      "step": 286
    },
    {
      "epoch": 0.6225596529284165,
      "grad_norm": 0.8219669461250305,
      "learning_rate": 0.00019310711603433552,
      "loss": 0.644,
      "step": 287
    },
    {
      "epoch": 0.6247288503253796,
      "grad_norm": 0.5713582038879395,
      "learning_rate": 0.00019301475776322956,
      "loss": 0.6316,
      "step": 288
    },
    {
      "epoch": 0.6268980477223427,
      "grad_norm": 0.47236549854278564,
      "learning_rate": 0.00019292180723175654,
      "loss": 0.6284,
      "step": 289
    },
    {
      "epoch": 0.6290672451193059,
      "grad_norm": 0.6406205892562866,
      "learning_rate": 0.00019282826503176783,
      "loss": 0.6243,
      "step": 290
    },
    {
      "epoch": 0.631236442516269,
      "grad_norm": 0.564037561416626,
      "learning_rate": 0.0001927341317588823,
      "loss": 0.605,
      "step": 291
    },
    {
      "epoch": 0.6334056399132321,
      "grad_norm": 0.6610985994338989,
      "learning_rate": 0.00019263940801248226,
      "loss": 0.6531,
      "step": 292
    },
    {
      "epoch": 0.6355748373101953,
      "grad_norm": 0.6878519654273987,
      "learning_rate": 0.0001925440943957099,
      "loss": 0.622,
      "step": 293
    },
    {
      "epoch": 0.6377440347071583,
      "grad_norm": 0.6926371455192566,
      "learning_rate": 0.00019244819151546322,
      "loss": 0.6373,
      "step": 294
    },
    {
      "epoch": 0.6399132321041214,
      "grad_norm": 0.5461336970329285,
      "learning_rate": 0.0001923516999823925,
      "loss": 0.5882,
      "step": 295
    },
    {
      "epoch": 0.6420824295010846,
      "grad_norm": 0.4566306173801422,
      "learning_rate": 0.00019225462041089594,
      "loss": 0.6364,
      "step": 296
    },
    {
      "epoch": 0.6442516268980477,
      "grad_norm": 0.76320481300354,
      "learning_rate": 0.00019215695341911614,
      "loss": 0.6459,
      "step": 297
    },
    {
      "epoch": 0.6464208242950108,
      "grad_norm": 1.0129058361053467,
      "learning_rate": 0.00019205869962893605,
      "loss": 0.6268,
      "step": 298
    },
    {
      "epoch": 0.648590021691974,
      "grad_norm": 1.0688267946243286,
      "learning_rate": 0.00019195985966597494,
      "loss": 0.6172,
      "step": 299
    },
    {
      "epoch": 0.6507592190889371,
      "grad_norm": 0.7970043420791626,
      "learning_rate": 0.00019186043415958447,
      "loss": 0.6227,
      "step": 300
    },
    {
      "epoch": 0.6529284164859002,
      "grad_norm": 0.6005694270133972,
      "learning_rate": 0.0001917604237428447,
      "loss": 0.6167,
      "step": 301
    },
    {
      "epoch": 0.6550976138828634,
      "grad_norm": 0.9996739029884338,
      "learning_rate": 0.00019165982905255998,
      "loss": 0.6409,
      "step": 302
    },
    {
      "epoch": 0.6572668112798264,
      "grad_norm": 1.1741567850112915,
      "learning_rate": 0.00019155865072925502,
      "loss": 0.6764,
      "step": 303
    },
    {
      "epoch": 0.6594360086767896,
      "grad_norm": 0.7148496508598328,
      "learning_rate": 0.00019145688941717075,
      "loss": 0.6356,
      "step": 304
    },
    {
      "epoch": 0.6616052060737527,
      "grad_norm": 0.4557119607925415,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.6171,
      "step": 305
    },
    {
      "epoch": 0.6637744034707158,
      "grad_norm": 0.48480424284935,
      "learning_rate": 0.00019125162042218412,
      "loss": 0.5739,
      "step": 306
    },
    {
      "epoch": 0.665943600867679,
      "grad_norm": 0.5445453524589539,
      "learning_rate": 0.00019114811404630762,
      "loss": 0.6525,
      "step": 307
    },
    {
      "epoch": 0.6681127982646421,
      "grad_norm": 0.42577245831489563,
      "learning_rate": 0.0001910440272956951,
      "loss": 0.6386,
      "step": 308
    },
    {
      "epoch": 0.6702819956616052,
      "grad_norm": 0.5067809224128723,
      "learning_rate": 0.00019093936083310653,
      "loss": 0.6038,
      "step": 309
    },
    {
      "epoch": 0.6724511930585684,
      "grad_norm": 0.44123509526252747,
      "learning_rate": 0.0001908341153249931,
      "loss": 0.5882,
      "step": 310
    },
    {
      "epoch": 0.6746203904555315,
      "grad_norm": 0.41951557993888855,
      "learning_rate": 0.000190728291441493,
      "loss": 0.6196,
      "step": 311
    },
    {
      "epoch": 0.6767895878524945,
      "grad_norm": 0.6330427527427673,
      "learning_rate": 0.0001906218898564272,
      "loss": 0.6504,
      "step": 312
    },
    {
      "epoch": 0.6789587852494577,
      "grad_norm": 0.7235706448554993,
      "learning_rate": 0.00019051491124729512,
      "loss": 0.6335,
      "step": 313
    },
    {
      "epoch": 0.6811279826464208,
      "grad_norm": 0.7178884148597717,
      "learning_rate": 0.00019040735629527027,
      "loss": 0.606,
      "step": 314
    },
    {
      "epoch": 0.6832971800433839,
      "grad_norm": 0.5714476108551025,
      "learning_rate": 0.0001902992256851959,
      "loss": 0.6456,
      "step": 315
    },
    {
      "epoch": 0.6854663774403471,
      "grad_norm": 0.45265328884124756,
      "learning_rate": 0.00019019052010558088,
      "loss": 0.6263,
      "step": 316
    },
    {
      "epoch": 0.6876355748373102,
      "grad_norm": 0.4798274636268616,
      "learning_rate": 0.00019008124024859487,
      "loss": 0.6154,
      "step": 317
    },
    {
      "epoch": 0.6898047722342733,
      "grad_norm": 0.4614523947238922,
      "learning_rate": 0.00018997138681006446,
      "loss": 0.6288,
      "step": 318
    },
    {
      "epoch": 0.6919739696312365,
      "grad_norm": 0.6244158148765564,
      "learning_rate": 0.00018986096048946824,
      "loss": 0.6183,
      "step": 319
    },
    {
      "epoch": 0.6941431670281996,
      "grad_norm": 0.914400041103363,
      "learning_rate": 0.0001897499619899326,
      "loss": 0.6317,
      "step": 320
    },
    {
      "epoch": 0.6963123644251626,
      "grad_norm": 1.2058935165405273,
      "learning_rate": 0.00018963839201822726,
      "loss": 0.6453,
      "step": 321
    },
    {
      "epoch": 0.6984815618221258,
      "grad_norm": 0.6527420878410339,
      "learning_rate": 0.0001895262512847607,
      "loss": 0.626,
      "step": 322
    },
    {
      "epoch": 0.7006507592190889,
      "grad_norm": 0.5786762237548828,
      "learning_rate": 0.00018941354050357566,
      "loss": 0.6337,
      "step": 323
    },
    {
      "epoch": 0.702819956616052,
      "grad_norm": 1.1447784900665283,
      "learning_rate": 0.0001893002603923446,
      "loss": 0.6291,
      "step": 324
    },
    {
      "epoch": 0.7049891540130152,
      "grad_norm": 1.1215901374816895,
      "learning_rate": 0.00018918641167236505,
      "loss": 0.6605,
      "step": 325
    },
    {
      "epoch": 0.7071583514099783,
      "grad_norm": 0.5069162845611572,
      "learning_rate": 0.0001890719950685552,
      "loss": 0.6137,
      "step": 326
    },
    {
      "epoch": 0.7093275488069414,
      "grad_norm": 0.6415742039680481,
      "learning_rate": 0.00018895701130944908,
      "loss": 0.5928,
      "step": 327
    },
    {
      "epoch": 0.7114967462039046,
      "grad_norm": 0.8517307639122009,
      "learning_rate": 0.00018884146112719207,
      "loss": 0.6346,
      "step": 328
    },
    {
      "epoch": 0.7136659436008677,
      "grad_norm": 1.0719935894012451,
      "learning_rate": 0.00018872534525753615,
      "loss": 0.5914,
      "step": 329
    },
    {
      "epoch": 0.7158351409978309,
      "grad_norm": 1.205763816833496,
      "learning_rate": 0.0001886086644398353,
      "loss": 0.6566,
      "step": 330
    },
    {
      "epoch": 0.7180043383947939,
      "grad_norm": 0.6757149696350098,
      "learning_rate": 0.00018849141941704067,
      "loss": 0.67,
      "step": 331
    },
    {
      "epoch": 0.720173535791757,
      "grad_norm": 0.6967810988426208,
      "learning_rate": 0.00018837361093569592,
      "loss": 0.6226,
      "step": 332
    },
    {
      "epoch": 0.7223427331887202,
      "grad_norm": 1.1503727436065674,
      "learning_rate": 0.00018825523974593252,
      "loss": 0.6411,
      "step": 333
    },
    {
      "epoch": 0.7245119305856833,
      "grad_norm": 1.1901216506958008,
      "learning_rate": 0.00018813630660146488,
      "loss": 0.6174,
      "step": 334
    },
    {
      "epoch": 0.7266811279826464,
      "grad_norm": 0.6187192797660828,
      "learning_rate": 0.00018801681225958565,
      "loss": 0.616,
      "step": 335
    },
    {
      "epoch": 0.7288503253796096,
      "grad_norm": 0.9013387560844421,
      "learning_rate": 0.0001878967574811607,
      "loss": 0.6218,
      "step": 336
    },
    {
      "epoch": 0.7310195227765727,
      "grad_norm": 0.9816798567771912,
      "learning_rate": 0.00018777614303062457,
      "loss": 0.6517,
      "step": 337
    },
    {
      "epoch": 0.7331887201735358,
      "grad_norm": 0.705035924911499,
      "learning_rate": 0.00018765496967597536,
      "loss": 0.6243,
      "step": 338
    },
    {
      "epoch": 0.735357917570499,
      "grad_norm": 0.6011426448822021,
      "learning_rate": 0.0001875332381887699,
      "loss": 0.6135,
      "step": 339
    },
    {
      "epoch": 0.737527114967462,
      "grad_norm": 1.000373125076294,
      "learning_rate": 0.000187410949344119,
      "loss": 0.6198,
      "step": 340
    },
    {
      "epoch": 0.7396963123644251,
      "grad_norm": 0.7643341422080994,
      "learning_rate": 0.0001872881039206822,
      "loss": 0.5889,
      "step": 341
    },
    {
      "epoch": 0.7418655097613883,
      "grad_norm": 0.6658336520195007,
      "learning_rate": 0.00018716470270066306,
      "loss": 0.6428,
      "step": 342
    },
    {
      "epoch": 0.7440347071583514,
      "grad_norm": 0.9525390863418579,
      "learning_rate": 0.00018704074646980415,
      "loss": 0.6392,
      "step": 343
    },
    {
      "epoch": 0.7462039045553145,
      "grad_norm": 0.7604145407676697,
      "learning_rate": 0.00018691623601738199,
      "loss": 0.6042,
      "step": 344
    },
    {
      "epoch": 0.7483731019522777,
      "grad_norm": 0.3855660855770111,
      "learning_rate": 0.00018679117213620203,
      "loss": 0.6537,
      "step": 345
    },
    {
      "epoch": 0.7505422993492408,
      "grad_norm": 0.7270882725715637,
      "learning_rate": 0.00018666555562259356,
      "loss": 0.6218,
      "step": 346
    },
    {
      "epoch": 0.7527114967462039,
      "grad_norm": 0.9166734218597412,
      "learning_rate": 0.00018653938727640474,
      "loss": 0.6577,
      "step": 347
    },
    {
      "epoch": 0.754880694143167,
      "grad_norm": 0.7549094557762146,
      "learning_rate": 0.0001864126679009975,
      "loss": 0.6121,
      "step": 348
    },
    {
      "epoch": 0.7570498915401301,
      "grad_norm": 0.5652804970741272,
      "learning_rate": 0.00018628539830324229,
      "loss": 0.6322,
      "step": 349
    },
    {
      "epoch": 0.7592190889370932,
      "grad_norm": 0.7185519337654114,
      "learning_rate": 0.00018615757929351312,
      "loss": 0.6038,
      "step": 350
    },
    {
      "epoch": 0.7613882863340564,
      "grad_norm": 0.7408043742179871,
      "learning_rate": 0.00018602921168568224,
      "loss": 0.6287,
      "step": 351
    },
    {
      "epoch": 0.7635574837310195,
      "grad_norm": 0.5190253257751465,
      "learning_rate": 0.00018590029629711506,
      "loss": 0.6414,
      "step": 352
    },
    {
      "epoch": 0.7657266811279827,
      "grad_norm": 0.5458491444587708,
      "learning_rate": 0.00018577083394866496,
      "loss": 0.6043,
      "step": 353
    },
    {
      "epoch": 0.7678958785249458,
      "grad_norm": 0.4569520354270935,
      "learning_rate": 0.00018564082546466805,
      "loss": 0.6351,
      "step": 354
    },
    {
      "epoch": 0.7700650759219089,
      "grad_norm": 0.48480477929115295,
      "learning_rate": 0.00018551027167293768,
      "loss": 0.6327,
      "step": 355
    },
    {
      "epoch": 0.7722342733188721,
      "grad_norm": 0.4298776388168335,
      "learning_rate": 0.00018537917340475968,
      "loss": 0.6567,
      "step": 356
    },
    {
      "epoch": 0.7744034707158352,
      "grad_norm": 0.4909803867340088,
      "learning_rate": 0.00018524753149488655,
      "loss": 0.6343,
      "step": 357
    },
    {
      "epoch": 0.7765726681127982,
      "grad_norm": 0.5192337036132812,
      "learning_rate": 0.00018511534678153244,
      "loss": 0.6404,
      "step": 358
    },
    {
      "epoch": 0.7787418655097614,
      "grad_norm": 0.5625739693641663,
      "learning_rate": 0.00018498262010636774,
      "loss": 0.6353,
      "step": 359
    },
    {
      "epoch": 0.7809110629067245,
      "grad_norm": 0.6345406174659729,
      "learning_rate": 0.00018484935231451375,
      "loss": 0.6658,
      "step": 360
    },
    {
      "epoch": 0.7830802603036876,
      "grad_norm": 0.7685250043869019,
      "learning_rate": 0.0001847155442545372,
      "loss": 0.6343,
      "step": 361
    },
    {
      "epoch": 0.7852494577006508,
      "grad_norm": 0.9012033939361572,
      "learning_rate": 0.0001845811967784449,
      "loss": 0.6074,
      "step": 362
    },
    {
      "epoch": 0.7874186550976139,
      "grad_norm": 1.0009187459945679,
      "learning_rate": 0.0001844463107416784,
      "loss": 0.6339,
      "step": 363
    },
    {
      "epoch": 0.789587852494577,
      "grad_norm": 0.9587237238883972,
      "learning_rate": 0.00018431088700310844,
      "loss": 0.6036,
      "step": 364
    },
    {
      "epoch": 0.7917570498915402,
      "grad_norm": 0.9709300398826599,
      "learning_rate": 0.00018417492642502955,
      "loss": 0.6186,
      "step": 365
    },
    {
      "epoch": 0.7939262472885033,
      "grad_norm": 1.0402799844741821,
      "learning_rate": 0.00018403842987315438,
      "loss": 0.6373,
      "step": 366
    },
    {
      "epoch": 0.7960954446854663,
      "grad_norm": 0.8855934739112854,
      "learning_rate": 0.00018390139821660855,
      "loss": 0.6085,
      "step": 367
    },
    {
      "epoch": 0.7982646420824295,
      "grad_norm": 0.5206902027130127,
      "learning_rate": 0.00018376383232792466,
      "loss": 0.6362,
      "step": 368
    },
    {
      "epoch": 0.8004338394793926,
      "grad_norm": 0.519858181476593,
      "learning_rate": 0.00018362573308303718,
      "loss": 0.64,
      "step": 369
    },
    {
      "epoch": 0.8026030368763557,
      "grad_norm": 0.9195985198020935,
      "learning_rate": 0.00018348710136127655,
      "loss": 0.649,
      "step": 370
    },
    {
      "epoch": 0.8047722342733189,
      "grad_norm": 1.0799591541290283,
      "learning_rate": 0.00018334793804536363,
      "loss": 0.6598,
      "step": 371
    },
    {
      "epoch": 0.806941431670282,
      "grad_norm": 0.5174670219421387,
      "learning_rate": 0.00018320824402140432,
      "loss": 0.6247,
      "step": 372
    },
    {
      "epoch": 0.8091106290672451,
      "grad_norm": 0.7728611826896667,
      "learning_rate": 0.0001830680201788836,
      "loss": 0.6613,
      "step": 373
    },
    {
      "epoch": 0.8112798264642083,
      "grad_norm": 0.8309534192085266,
      "learning_rate": 0.00018292726741066007,
      "loss": 0.6315,
      "step": 374
    },
    {
      "epoch": 0.8134490238611713,
      "grad_norm": 0.9046960473060608,
      "learning_rate": 0.00018278598661296012,
      "loss": 0.6099,
      "step": 375
    },
    {
      "epoch": 0.8156182212581344,
      "grad_norm": 0.8798112869262695,
      "learning_rate": 0.00018264417868537244,
      "loss": 0.634,
      "step": 376
    },
    {
      "epoch": 0.8177874186550976,
      "grad_norm": 0.9738354682922363,
      "learning_rate": 0.00018250184453084205,
      "loss": 0.6349,
      "step": 377
    },
    {
      "epoch": 0.8199566160520607,
      "grad_norm": 1.1812074184417725,
      "learning_rate": 0.0001823589850556647,
      "loss": 0.6397,
      "step": 378
    },
    {
      "epoch": 0.8221258134490239,
      "grad_norm": 0.6148251295089722,
      "learning_rate": 0.00018221560116948103,
      "loss": 0.6123,
      "step": 379
    },
    {
      "epoch": 0.824295010845987,
      "grad_norm": 0.4913065433502197,
      "learning_rate": 0.0001820716937852708,
      "loss": 0.6142,
      "step": 380
    },
    {
      "epoch": 0.8264642082429501,
      "grad_norm": 0.6303558945655823,
      "learning_rate": 0.00018192726381934711,
      "loss": 0.6435,
      "step": 381
    },
    {
      "epoch": 0.8286334056399133,
      "grad_norm": 0.6138083338737488,
      "learning_rate": 0.0001817823121913506,
      "loss": 0.634,
      "step": 382
    },
    {
      "epoch": 0.8308026030368764,
      "grad_norm": 0.5394029021263123,
      "learning_rate": 0.00018163683982424337,
      "loss": 0.647,
      "step": 383
    },
    {
      "epoch": 0.8329718004338394,
      "grad_norm": 0.4430651068687439,
      "learning_rate": 0.0001814908476443034,
      "loss": 0.6335,
      "step": 384
    },
    {
      "epoch": 0.8351409978308026,
      "grad_norm": 0.513456404209137,
      "learning_rate": 0.00018134433658111845,
      "loss": 0.5981,
      "step": 385
    },
    {
      "epoch": 0.8373101952277657,
      "grad_norm": 0.4959484040737152,
      "learning_rate": 0.00018119730756758023,
      "loss": 0.6373,
      "step": 386
    },
    {
      "epoch": 0.8394793926247288,
      "grad_norm": 0.5900697708129883,
      "learning_rate": 0.00018104976153987843,
      "loss": 0.6404,
      "step": 387
    },
    {
      "epoch": 0.841648590021692,
      "grad_norm": 0.72898268699646,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.6392,
      "step": 388
    },
    {
      "epoch": 0.8438177874186551,
      "grad_norm": 0.9979819655418396,
      "learning_rate": 0.000180753122203197,
      "loss": 0.6165,
      "step": 389
    },
    {
      "epoch": 0.8459869848156182,
      "grad_norm": 1.151595115661621,
      "learning_rate": 0.00018060403078303295,
      "loss": 0.6355,
      "step": 390
    },
    {
      "epoch": 0.8481561822125814,
      "grad_norm": 0.693111777305603,
      "learning_rate": 0.00018045442612632444,
      "loss": 0.6257,
      "step": 391
    },
    {
      "epoch": 0.8503253796095445,
      "grad_norm": 0.456032395362854,
      "learning_rate": 0.00018030430918566123,
      "loss": 0.6309,
      "step": 392
    },
    {
      "epoch": 0.8524945770065075,
      "grad_norm": 0.7478503584861755,
      "learning_rate": 0.0001801536809168951,
      "loss": 0.6473,
      "step": 393
    },
    {
      "epoch": 0.8546637744034707,
      "grad_norm": 1.1302615404129028,
      "learning_rate": 0.00018000254227913348,
      "loss": 0.5997,
      "step": 394
    },
    {
      "epoch": 0.8568329718004338,
      "grad_norm": 1.0344661474227905,
      "learning_rate": 0.00017985089423473363,
      "loss": 0.6035,
      "step": 395
    },
    {
      "epoch": 0.8590021691973969,
      "grad_norm": 0.7855858206748962,
      "learning_rate": 0.00017969873774929639,
      "loss": 0.6376,
      "step": 396
    },
    {
      "epoch": 0.8611713665943601,
      "grad_norm": 0.6902018785476685,
      "learning_rate": 0.00017954607379166,
      "loss": 0.6246,
      "step": 397
    },
    {
      "epoch": 0.8633405639913232,
      "grad_norm": 0.9296028017997742,
      "learning_rate": 0.000179392903333894,
      "loss": 0.625,
      "step": 398
    },
    {
      "epoch": 0.8655097613882863,
      "grad_norm": 1.1793439388275146,
      "learning_rate": 0.00017923922735129302,
      "loss": 0.6397,
      "step": 399
    },
    {
      "epoch": 0.8676789587852495,
      "grad_norm": 0.7893816828727722,
      "learning_rate": 0.00017908504682237047,
      "loss": 0.6082,
      "step": 400
    },
    {
      "epoch": 0.8698481561822126,
      "grad_norm": 0.5155619382858276,
      "learning_rate": 0.00017893036272885254,
      "loss": 0.6462,
      "step": 401
    },
    {
      "epoch": 0.8720173535791758,
      "grad_norm": 0.7989358901977539,
      "learning_rate": 0.00017877517605567164,
      "loss": 0.6193,
      "step": 402
    },
    {
      "epoch": 0.8741865509761388,
      "grad_norm": 1.0920588970184326,
      "learning_rate": 0.00017861948779096046,
      "loss": 0.6543,
      "step": 403
    },
    {
      "epoch": 0.8763557483731019,
      "grad_norm": 0.9544174671173096,
      "learning_rate": 0.00017846329892604547,
      "loss": 0.6331,
      "step": 404
    },
    {
      "epoch": 0.8785249457700651,
      "grad_norm": 0.8040409088134766,
      "learning_rate": 0.00017830661045544055,
      "loss": 0.6536,
      "step": 405
    },
    {
      "epoch": 0.8806941431670282,
      "grad_norm": 0.6409693956375122,
      "learning_rate": 0.0001781494233768408,
      "loss": 0.648,
      "step": 406
    },
    {
      "epoch": 0.8828633405639913,
      "grad_norm": 0.5207626223564148,
      "learning_rate": 0.00017799173869111632,
      "loss": 0.6592,
      "step": 407
    },
    {
      "epoch": 0.8850325379609545,
      "grad_norm": 0.5719370245933533,
      "learning_rate": 0.0001778335574023054,
      "loss": 0.6238,
      "step": 408
    },
    {
      "epoch": 0.8872017353579176,
      "grad_norm": 0.8807241320610046,
      "learning_rate": 0.00017767488051760857,
      "loss": 0.6529,
      "step": 409
    },
    {
      "epoch": 0.8893709327548807,
      "grad_norm": 1.105629563331604,
      "learning_rate": 0.00017751570904738192,
      "loss": 0.6506,
      "step": 410
    },
    {
      "epoch": 0.8915401301518439,
      "grad_norm": 0.7086028456687927,
      "learning_rate": 0.00017735604400513083,
      "loss": 0.6344,
      "step": 411
    },
    {
      "epoch": 0.8937093275488069,
      "grad_norm": 0.4514036476612091,
      "learning_rate": 0.00017719588640750336,
      "loss": 0.6386,
      "step": 412
    },
    {
      "epoch": 0.89587852494577,
      "grad_norm": 0.7691593766212463,
      "learning_rate": 0.00017703523727428388,
      "loss": 0.6449,
      "step": 413
    },
    {
      "epoch": 0.8980477223427332,
      "grad_norm": 0.9623990654945374,
      "learning_rate": 0.00017687409762838664,
      "loss": 0.6014,
      "step": 414
    },
    {
      "epoch": 0.9002169197396963,
      "grad_norm": 0.7851717472076416,
      "learning_rate": 0.00017671246849584903,
      "loss": 0.6323,
      "step": 415
    },
    {
      "epoch": 0.9023861171366594,
      "grad_norm": 0.5283617973327637,
      "learning_rate": 0.00017655035090582532,
      "loss": 0.629,
      "step": 416
    },
    {
      "epoch": 0.9045553145336226,
      "grad_norm": 0.48515915870666504,
      "learning_rate": 0.00017638774589057987,
      "loss": 0.6381,
      "step": 417
    },
    {
      "epoch": 0.9067245119305857,
      "grad_norm": 0.5369405150413513,
      "learning_rate": 0.0001762246544854807,
      "loss": 0.6574,
      "step": 418
    },
    {
      "epoch": 0.9088937093275488,
      "grad_norm": 0.7174472808837891,
      "learning_rate": 0.00017606107772899287,
      "loss": 0.6113,
      "step": 419
    },
    {
      "epoch": 0.911062906724512,
      "grad_norm": 0.9402954578399658,
      "learning_rate": 0.0001758970166626719,
      "loss": 0.6457,
      "step": 420
    },
    {
      "epoch": 0.913232104121475,
      "grad_norm": 1.016424298286438,
      "learning_rate": 0.00017573247233115694,
      "loss": 0.6834,
      "step": 421
    },
    {
      "epoch": 0.9154013015184381,
      "grad_norm": 0.8186083436012268,
      "learning_rate": 0.00017556744578216447,
      "loss": 0.6241,
      "step": 422
    },
    {
      "epoch": 0.9175704989154013,
      "grad_norm": 0.650930643081665,
      "learning_rate": 0.00017540193806648134,
      "loss": 0.6298,
      "step": 423
    },
    {
      "epoch": 0.9197396963123644,
      "grad_norm": 0.5683746933937073,
      "learning_rate": 0.00017523595023795813,
      "loss": 0.6412,
      "step": 424
    },
    {
      "epoch": 0.9219088937093276,
      "grad_norm": 0.5509985089302063,
      "learning_rate": 0.00017506948335350254,
      "loss": 0.6282,
      "step": 425
    },
    {
      "epoch": 0.9240780911062907,
      "grad_norm": 0.6051164269447327,
      "learning_rate": 0.0001749025384730726,
      "loss": 0.6468,
      "step": 426
    },
    {
      "epoch": 0.9262472885032538,
      "grad_norm": 0.7694234848022461,
      "learning_rate": 0.00017473511665966993,
      "loss": 0.6056,
      "step": 427
    },
    {
      "epoch": 0.928416485900217,
      "grad_norm": 0.6827411651611328,
      "learning_rate": 0.00017456721897933286,
      "loss": 0.6089,
      "step": 428
    },
    {
      "epoch": 0.93058568329718,
      "grad_norm": 0.6468983888626099,
      "learning_rate": 0.00017439884650112989,
      "loss": 0.6475,
      "step": 429
    },
    {
      "epoch": 0.9327548806941431,
      "grad_norm": 0.556389570236206,
      "learning_rate": 0.00017423000029715267,
      "loss": 0.6267,
      "step": 430
    },
    {
      "epoch": 0.9349240780911063,
      "grad_norm": 0.5071318745613098,
      "learning_rate": 0.00017406068144250924,
      "loss": 0.6468,
      "step": 431
    },
    {
      "epoch": 0.9370932754880694,
      "grad_norm": 0.5068785548210144,
      "learning_rate": 0.00017389089101531722,
      "loss": 0.6413,
      "step": 432
    },
    {
      "epoch": 0.9392624728850325,
      "grad_norm": 0.7769328951835632,
      "learning_rate": 0.00017372063009669686,
      "loss": 0.6143,
      "step": 433
    },
    {
      "epoch": 0.9414316702819957,
      "grad_norm": 0.9907039999961853,
      "learning_rate": 0.00017354989977076422,
      "loss": 0.6185,
      "step": 434
    },
    {
      "epoch": 0.9436008676789588,
      "grad_norm": 1.006850004196167,
      "learning_rate": 0.0001733787011246243,
      "loss": 0.6327,
      "step": 435
    },
    {
      "epoch": 0.9457700650759219,
      "grad_norm": 0.8385252952575684,
      "learning_rate": 0.00017320703524836405,
      "loss": 0.6462,
      "step": 436
    },
    {
      "epoch": 0.9479392624728851,
      "grad_norm": 0.806705892086029,
      "learning_rate": 0.00017303490323504543,
      "loss": 0.6313,
      "step": 437
    },
    {
      "epoch": 0.9501084598698482,
      "grad_norm": 0.5839858055114746,
      "learning_rate": 0.0001728623061806985,
      "loss": 0.6231,
      "step": 438
    },
    {
      "epoch": 0.9522776572668112,
      "grad_norm": 0.502601683139801,
      "learning_rate": 0.00017268924518431438,
      "loss": 0.6295,
      "step": 439
    },
    {
      "epoch": 0.9544468546637744,
      "grad_norm": 0.5183345675468445,
      "learning_rate": 0.00017251572134783832,
      "loss": 0.6206,
      "step": 440
    },
    {
      "epoch": 0.9566160520607375,
      "grad_norm": 0.414736807346344,
      "learning_rate": 0.0001723417357761626,
      "loss": 0.622,
      "step": 441
    },
    {
      "epoch": 0.9587852494577006,
      "grad_norm": 0.5313084125518799,
      "learning_rate": 0.00017216728957711967,
      "loss": 0.579,
      "step": 442
    },
    {
      "epoch": 0.9609544468546638,
      "grad_norm": 0.5338884592056274,
      "learning_rate": 0.0001719923838614748,
      "loss": 0.5985,
      "step": 443
    },
    {
      "epoch": 0.9631236442516269,
      "grad_norm": 0.6575837135314941,
      "learning_rate": 0.0001718170197429193,
      "loss": 0.6347,
      "step": 444
    },
    {
      "epoch": 0.96529284164859,
      "grad_norm": 0.7642272114753723,
      "learning_rate": 0.0001716411983380632,
      "loss": 0.6209,
      "step": 445
    },
    {
      "epoch": 0.9674620390455532,
      "grad_norm": 0.8659293055534363,
      "learning_rate": 0.00017146492076642838,
      "loss": 0.6653,
      "step": 446
    },
    {
      "epoch": 0.9696312364425163,
      "grad_norm": 0.7543999552726746,
      "learning_rate": 0.00017128818815044115,
      "loss": 0.5855,
      "step": 447
    },
    {
      "epoch": 0.9718004338394793,
      "grad_norm": 0.6930994987487793,
      "learning_rate": 0.00017111100161542545,
      "loss": 0.6468,
      "step": 448
    },
    {
      "epoch": 0.9739696312364425,
      "grad_norm": 0.5262666940689087,
      "learning_rate": 0.00017093336228959536,
      "loss": 0.6289,
      "step": 449
    },
    {
      "epoch": 0.9761388286334056,
      "grad_norm": 0.785383403301239,
      "learning_rate": 0.00017075527130404802,
      "loss": 0.6521,
      "step": 450
    },
    {
      "epoch": 0.9783080260303688,
      "grad_norm": 0.9148966073989868,
      "learning_rate": 0.00017057672979275656,
      "loss": 0.6364,
      "step": 451
    },
    {
      "epoch": 0.9804772234273319,
      "grad_norm": 0.7715286612510681,
      "learning_rate": 0.00017039773889256278,
      "loss": 0.627,
      "step": 452
    },
    {
      "epoch": 0.982646420824295,
      "grad_norm": 0.6080709099769592,
      "learning_rate": 0.00017021829974316982,
      "loss": 0.6446,
      "step": 453
    },
    {
      "epoch": 0.9848156182212582,
      "grad_norm": 0.6626065969467163,
      "learning_rate": 0.0001700384134871351,
      "loss": 0.6224,
      "step": 454
    },
    {
      "epoch": 0.9869848156182213,
      "grad_norm": 0.7066227793693542,
      "learning_rate": 0.0001698580812698628,
      "loss": 0.6055,
      "step": 455
    },
    {
      "epoch": 0.9891540130151844,
      "grad_norm": 0.7028903365135193,
      "learning_rate": 0.00016967730423959684,
      "loss": 0.644,
      "step": 456
    },
    {
      "epoch": 0.9913232104121475,
      "grad_norm": 0.44121044874191284,
      "learning_rate": 0.0001694960835474134,
      "loss": 0.5894,
      "step": 457
    },
    {
      "epoch": 0.9934924078091106,
      "grad_norm": 0.5421911478042603,
      "learning_rate": 0.00016931442034721355,
      "loss": 0.6574,
      "step": 458
    },
    {
      "epoch": 0.9956616052060737,
      "grad_norm": 0.6020808815956116,
      "learning_rate": 0.00016913231579571608,
      "loss": 0.6338,
      "step": 459
    },
    {
      "epoch": 0.9978308026030369,
      "grad_norm": 0.6902042627334595,
      "learning_rate": 0.00016894977105244997,
      "loss": 0.6432,
      "step": 460
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6089836955070496,
      "learning_rate": 0.00016876678727974705,
      "loss": 0.6351,
      "step": 461
    }
  ],
  "logging_steps": 1,
  "max_steps": 1383,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0035726240029082e+19,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}