{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.764835164835165,
  "eval_steps": 500,
  "global_step": 420,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 0.8349836468696594,
      "learning_rate": 0.0,
      "loss": 0.9434,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 0.8700987696647644,
      "learning_rate": 4e-05,
      "loss": 0.9905,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.9241365194320679,
      "learning_rate": 8e-05,
      "loss": 0.9438,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 0.9019892811775208,
      "learning_rate": 0.00012,
      "loss": 0.9216,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.8872910141944885,
      "learning_rate": 0.00016,
      "loss": 0.9374,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.5874530076980591,
      "learning_rate": 0.0002,
      "loss": 0.7673,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5062956809997559,
      "learning_rate": 0.00019955654101995565,
      "loss": 0.8011,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.5953829288482666,
      "learning_rate": 0.00019911308203991133,
      "loss": 0.8455,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.5616072416305542,
      "learning_rate": 0.00019866962305986697,
      "loss": 0.8265,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.49180087447166443,
      "learning_rate": 0.00019822616407982261,
      "loss": 0.8561,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.42030951380729675,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.8796,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.3004567325115204,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.8636,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.2698984444141388,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.718,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.25445133447647095,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.7235,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.22418756783008575,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.688,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.2096303105354309,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.7267,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.3029191195964813,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.7763,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.2644464075565338,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7618,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.2536560893058777,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.7999,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.24718916416168213,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.752,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.2625150680541992,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.736,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.32164040207862854,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.7043,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3981449604034424,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.7057,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3817313015460968,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.7413,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.29256680607795715,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.693,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.27523350715637207,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.6474,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.23511967062950134,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.6519,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.2961374819278717,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.6426,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.2760772407054901,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.7388,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.2285313606262207,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.7756,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.2657061517238617,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.7275,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.22572828829288483,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.6793,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.26335304975509644,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.7131,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.25231942534446716,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.7715,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2437426745891571,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.7094,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.28558826446533203,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.6937,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.2915894687175751,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.7238,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.25342074036598206,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.7323,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.22744007408618927,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.703,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.25383231043815613,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.7093,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.2194337695837021,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.7367,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.32021859288215637,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.6652,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.2328304797410965,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.7016,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.24166613817214966,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.6717,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2733803391456604,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.6979,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.2689957320690155,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.6977,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.2698104977607727,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.723,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.25856417417526245,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.723,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.22988826036453247,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.7356,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.24859416484832764,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.6671,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.24891626834869385,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.6628,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.22740386426448822,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.6377,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.2636365294456482,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.6901,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2437390238046646,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.72,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.23658742010593414,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.7365,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.23923538625240326,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.706,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2877054512500763,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.7436,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.2839520573616028,
      "learning_rate": 0.000176940133037694,
      "loss": 0.6779,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.2308293879032135,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.6357,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.24402214586734772,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.7508,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.23816415667533875,
      "learning_rate": 0.000175609756097561,
      "loss": 0.7249,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.28321942687034607,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.7479,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.23680296540260315,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.6413,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.23129238188266754,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.6786,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.25140181183815,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.7167,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.27190810441970825,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.6267,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.23768772184848785,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.7397,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.2618238031864166,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.6987,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.24789907038211823,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.6223,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.2744330167770386,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.6964,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.23732465505599976,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.6524,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.2278261035680771,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.7437,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.24909941852092743,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.6955,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3007880449295044,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.625,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.2338089644908905,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.6843,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.27349653840065,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.6825,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.2793181836605072,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.6529,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2612224221229553,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.6807,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.2740105986595154,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.6294,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.2226412147283554,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.6569,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.2254134714603424,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.6569,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.22373083233833313,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.6733,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.2485770583152771,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.6422,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.25764942169189453,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.6682,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.24047411978244781,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.7126,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.21252930164337158,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.7109,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.25431081652641296,
      "learning_rate": 0.000164079822616408,
      "loss": 0.6416,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.24909189343452454,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.6963,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.25534072518348694,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.7898,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.22847016155719757,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.6903,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.27691230177879333,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.6963,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.2628577649593353,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.7605,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.29095378518104553,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.6878,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.24262812733650208,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.7383,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.21234223246574402,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.6735,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.2478182166814804,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.6334,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.22873812913894653,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.6968,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.24787071347236633,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.7076,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2913095951080322,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.6785,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.27481356263160706,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.7055,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.24760739505290985,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.7027,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.2754676342010498,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.7027,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.2395099550485611,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.6846,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.2519392669200897,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.7722,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.24618907272815704,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.6933,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.2342153638601303,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.6866,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.23813366889953613,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.6476,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.21853409707546234,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.6401,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.22005102038383484,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.6173,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.2145771086215973,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.6712,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.2519795894622803,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.7036,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.21608349680900574,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.7213,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.2526698410511017,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.6326,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.22119538486003876,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.643,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.23445621132850647,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.6562,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.21006852388381958,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.7381,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.2904897928237915,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.723,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.28895437717437744,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.6517,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.24994221329689026,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.6621,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.24564869701862335,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.7548,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.2209189534187317,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.6474,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.24389097094535828,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.7471,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.23514863848686218,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.6859,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.26364991068840027,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.6276,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.2185850590467453,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.7346,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.22511166334152222,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.7208,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.20826543867588043,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.6757,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.22027815878391266,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.6839,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.23337896168231964,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.6555,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.21975719928741455,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.6829,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.2579653263092041,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.6567,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.19928398728370667,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.7138,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.23015153408050537,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.695,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.25714021921157837,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.7245,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.2980111837387085,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.7276,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.22255489230155945,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.6282,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.1886795461177826,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.703,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.20825117826461792,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.7088,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.23884426057338715,
      "learning_rate": 0.000141019955654102,
      "loss": 0.6704,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.23004014790058136,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.6254,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.21654583513736725,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.7034,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.2495403289794922,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.7006,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.22400696575641632,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.6787,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.2399936020374298,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.6231,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.23908363282680511,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.7955,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.2390311360359192,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.7071,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.24296815693378448,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.6154,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.2415105700492859,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.7034,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.23874816298484802,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.6519,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.23809735476970673,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.7036,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.2647075653076172,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.7314,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.31311991810798645,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.6548,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.21374206244945526,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.6873,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.23409698903560638,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.5987,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.23090939223766327,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.6663,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.21316714584827423,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.7029,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.22960595786571503,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.7227,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.22792965173721313,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.6432,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.23443835973739624,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.6985,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.28602835536003113,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.7104,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.24389949440956116,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.6263,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.23545803129673004,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.633,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.24627815186977386,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.6681,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.23184970021247864,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.6301,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.2684311866760254,
      "learning_rate": 0.000129490022172949,
      "loss": 0.5843,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.21682627499103546,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.6899,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.2188265174627304,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.566,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.28629106283187866,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.7402,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.23270383477210999,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.618,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.23773661255836487,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.663,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.22746062278747559,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.5676,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.2408296763896942,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.6188,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.25889304280281067,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.6481,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.2609748840332031,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.7144,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.25349873304367065,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.6217,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.27652761340141296,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.608,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.2542835474014282,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.6508,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.26467981934547424,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.6415,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.22944307327270508,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.6887,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.26799389719963074,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.7367,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.2525601387023926,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.6422,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.2355557680130005,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.6603,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.25457942485809326,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.6029,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.26432162523269653,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.6016,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.2523304522037506,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.6058,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.23987026512622833,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.6255,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.23296266794204712,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.6211,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.25674763321876526,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.6418,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.2774389982223511,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.7059,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.24446550011634827,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.6688,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.27265456318855286,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.5647,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.24586018919944763,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.6014,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.269580215215683,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.7209,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.27124646306037903,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.6919,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.2509947717189789,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.6371,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.2711145281791687,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.6902,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.2748906910419464,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.6314,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.2656286656856537,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.626,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.2800760567188263,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.6644,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.25644972920417786,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.6175,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.32209092378616333,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.6923,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.289835661649704,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.684,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.26838189363479614,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.6269,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.2978680729866028,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.6146,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.26538562774658203,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.722,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.28731569647789,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.6014,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.2782905101776123,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.6199,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.30587491393089294,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.6627,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.26933780312538147,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.653,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.2531006336212158,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.6236,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.27851951122283936,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.5646,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.3055563271045685,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.6261,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.35534387826919556,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.7499,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.3039867877960205,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.7448,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.29222774505615234,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.6994,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.3348762094974518,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.6899,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.2643917202949524,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.6327,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.2829495072364807,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.5995,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.2924668788909912,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.6857,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.2968837320804596,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.6998,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.2751065790653229,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.649,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.28774625062942505,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.6907,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.291047602891922,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.6437,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.3040315806865692,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.6347,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.3117130398750305,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.7243,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.30897200107574463,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.672,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.2905803322792053,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.6652,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.29437223076820374,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.6125,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.3070380389690399,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.7046,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.2748529314994812,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.6595,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.2682563364505768,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.6459,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.27401265501976013,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.6199,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.2843487560749054,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.6358,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.27725502848625183,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.6806,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.2414613515138626,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.6155,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.2569555938243866,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.7321,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.2681421935558319,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.6719,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.25046780705451965,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.7639,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.25275540351867676,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.6275,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.26329776644706726,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.7055,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.2912167012691498,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.6592,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.2765107750892639,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.6444,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.2599141597747803,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.6624,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.3005516231060028,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.6846,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.2981216013431549,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.6819,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.3102389872074127,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.6963,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.2801750898361206,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.6016,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.2696482539176941,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.6498,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.2741401195526123,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.6663,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.2642763555049896,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.6921,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.2582313120365143,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.6325,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.2626502215862274,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.6366,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.2749052345752716,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.6176,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.2907024919986725,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.662,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.2934260368347168,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.6578,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.24928325414657593,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.6723,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.2799281179904938,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.6556,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.27133285999298096,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.7093,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.28980451822280884,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.6223,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.29531198740005493,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.6124,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.26588279008865356,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.6216,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.2749369740486145,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.6549,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.2783108949661255,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.6716,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.31840136647224426,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.6266,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.3002336323261261,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.6807,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.2735682427883148,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.6891,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.26801374554634094,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.6474,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.262231707572937,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.6596,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.29779019951820374,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.8202,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.26252323389053345,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.6694,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.244583860039711,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.6733,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.2495196908712387,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.701,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.26171785593032837,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.6406,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.2872734069824219,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.6258,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.281949520111084,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.7101,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.2897920310497284,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.5471,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.3084937334060669,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.656,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.26816326379776,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.6479,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.3056108355522156,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.6031,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.28158485889434814,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.6718,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.27613478899002075,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.6204,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.29629531502723694,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.6532,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.2641867995262146,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.7478,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.2649998962879181,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.6201,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.267092227935791,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.665,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.2623145282268524,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.5897,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.2677851617336273,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.6252,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.28442463278770447,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.6841,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.29269593954086304,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.6912,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.28295204043388367,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.6292,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.28216615319252014,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.5749,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.2640226483345032,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.6872,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.27898797392845154,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.6575,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.30361807346343994,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.6235,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.2861906886100769,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.5945,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.30551525950431824,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.6664,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.27989670634269714,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.6828,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.2802552282810211,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.5834,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.25322502851486206,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.6603,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.2840248942375183,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.7114,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.2925967574119568,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.617,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.2550450563430786,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.6113,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.27554598450660706,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.6508,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.36187660694122314,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.6119,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.2669368386268616,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.5645,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.2961459457874298,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.5679,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.2856895923614502,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.6078,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.2743946611881256,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.6207,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.29815220832824707,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.6407,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.27454665303230286,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.5693,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.30620837211608887,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.5923,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.3297302722930908,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.6362,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.3292776346206665,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.5807,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.307224303483963,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.5757,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.3267006278038025,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.639,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.2853327691555023,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.5718,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.2932675778865814,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.5937,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.3221415877342224,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.6692,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.2854374647140503,
      "learning_rate": 6.119733924611974e-05,
      "loss": 0.6085,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.3008936047554016,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.5379,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.30253729224205017,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.6217,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.3198719620704651,
      "learning_rate": 5.98669623059867e-05,
      "loss": 0.6546,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.29466813802719116,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.6951,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.2989588975906372,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.5965,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.3200170695781708,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.6611,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.3269204795360565,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.6712,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.3217758238315582,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.6093,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.33345234394073486,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.6251,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.32402846217155457,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.6183,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.3157860040664673,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.5349,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.36150726675987244,
      "learning_rate": 5.587583148558758e-05,
      "loss": 0.5896,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.3478860855102539,
      "learning_rate": 5.543237250554324e-05,
      "loss": 0.6031,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.3517143428325653,
      "learning_rate": 5.4988913525498895e-05,
      "loss": 0.6576,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.3470364212989807,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.5538,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.3451264202594757,
      "learning_rate": 5.4101995565410204e-05,
      "loss": 0.6682,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.3541184961795807,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.6403,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.33449625968933105,
      "learning_rate": 5.3215077605321506e-05,
      "loss": 0.7003,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.32849395275115967,
      "learning_rate": 5.2771618625277164e-05,
      "loss": 0.665,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.33040931820869446,
      "learning_rate": 5.232815964523282e-05,
      "loss": 0.6448,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.3629243075847626,
      "learning_rate": 5.1884700665188466e-05,
      "loss": 0.6031,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.35075902938842773,
      "learning_rate": 5.1441241685144124e-05,
      "loss": 0.6391,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.3558412790298462,
      "learning_rate": 5.099778270509978e-05,
      "loss": 0.5543,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.35990020632743835,
      "learning_rate": 5.0554323725055433e-05,
      "loss": 0.5988,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.3391597270965576,
      "learning_rate": 5.011086474501109e-05,
      "loss": 0.648,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.3764243423938751,
      "learning_rate": 4.966740576496674e-05,
      "loss": 0.5712,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 0.3697277903556824,
      "learning_rate": 4.92239467849224e-05,
      "loss": 0.5835,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 0.3969104588031769,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.615,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 0.39072567224502563,
      "learning_rate": 4.833702882483371e-05,
      "loss": 0.6098,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.39250054955482483,
      "learning_rate": 4.789356984478936e-05,
      "loss": 0.648,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 0.3846372961997986,
      "learning_rate": 4.745011086474501e-05,
      "loss": 0.5604,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 0.4122708737850189,
      "learning_rate": 4.700665188470067e-05,
      "loss": 0.5934,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 0.32369640469551086,
      "learning_rate": 4.656319290465632e-05,
      "loss": 0.5478,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 0.3832913339138031,
      "learning_rate": 4.611973392461197e-05,
      "loss": 0.6163,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.36105120182037354,
      "learning_rate": 4.567627494456763e-05,
      "loss": 0.6547,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 0.3539276719093323,
      "learning_rate": 4.523281596452328e-05,
      "loss": 0.547,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.361166387796402,
      "learning_rate": 4.478935698447894e-05,
      "loss": 0.6272,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 0.41106733679771423,
      "learning_rate": 4.4345898004434597e-05,
      "loss": 0.6149,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 0.3543967306613922,
      "learning_rate": 4.390243902439025e-05,
      "loss": 0.6304,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 0.4170666038990021,
      "learning_rate": 4.34589800443459e-05,
      "loss": 0.6095,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 0.37213292717933655,
      "learning_rate": 4.301552106430156e-05,
      "loss": 0.5235,
      "step": 360
    },
    {
      "epoch": 2.375824175824176,
      "grad_norm": 0.38063541054725647,
      "learning_rate": 4.257206208425721e-05,
      "loss": 0.6474,
      "step": 361
    },
    {
      "epoch": 2.3824175824175824,
      "grad_norm": 0.411310076713562,
      "learning_rate": 4.212860310421286e-05,
      "loss": 0.6181,
      "step": 362
    },
    {
      "epoch": 2.389010989010989,
      "grad_norm": 0.42125841975212097,
      "learning_rate": 4.168514412416852e-05,
      "loss": 0.5714,
      "step": 363
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 0.41150984168052673,
      "learning_rate": 4.124168514412417e-05,
      "loss": 0.7046,
      "step": 364
    },
    {
      "epoch": 2.402197802197802,
      "grad_norm": 0.4161834418773651,
      "learning_rate": 4.0798226164079826e-05,
      "loss": 0.616,
      "step": 365
    },
    {
      "epoch": 2.4087912087912087,
      "grad_norm": 0.390655517578125,
      "learning_rate": 4.035476718403548e-05,
      "loss": 0.5892,
      "step": 366
    },
    {
      "epoch": 2.4153846153846152,
      "grad_norm": 0.3745560050010681,
      "learning_rate": 3.9911308203991135e-05,
      "loss": 0.6158,
      "step": 367
    },
    {
      "epoch": 2.421978021978022,
      "grad_norm": 0.4399837553501129,
      "learning_rate": 3.9467849223946786e-05,
      "loss": 0.5602,
      "step": 368
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.3739384412765503,
      "learning_rate": 3.9024390243902444e-05,
      "loss": 0.575,
      "step": 369
    },
    {
      "epoch": 2.4351648351648354,
      "grad_norm": 0.402792751789093,
      "learning_rate": 3.8580931263858095e-05,
      "loss": 0.6134,
      "step": 370
    },
    {
      "epoch": 2.441758241758242,
      "grad_norm": 0.375630646944046,
      "learning_rate": 3.8137472283813746e-05,
      "loss": 0.5871,
      "step": 371
    },
    {
      "epoch": 2.4483516483516485,
      "grad_norm": 0.39739781618118286,
      "learning_rate": 3.7694013303769404e-05,
      "loss": 0.6279,
      "step": 372
    },
    {
      "epoch": 2.454945054945055,
      "grad_norm": 0.4211947023868561,
      "learning_rate": 3.7250554323725055e-05,
      "loss": 0.6334,
      "step": 373
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.40559887886047363,
      "learning_rate": 3.6807095343680706e-05,
      "loss": 0.6303,
      "step": 374
    },
    {
      "epoch": 2.4681318681318682,
      "grad_norm": 0.4357641935348511,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.6174,
      "step": 375
    },
    {
      "epoch": 2.474725274725275,
      "grad_norm": 0.4123687148094177,
      "learning_rate": 3.5920177383592015e-05,
      "loss": 0.5863,
      "step": 376
    },
    {
      "epoch": 2.4813186813186814,
      "grad_norm": 0.436879426240921,
      "learning_rate": 3.547671840354767e-05,
      "loss": 0.6119,
      "step": 377
    },
    {
      "epoch": 2.487912087912088,
      "grad_norm": 0.3765966296195984,
      "learning_rate": 3.503325942350333e-05,
      "loss": 0.7202,
      "step": 378
    },
    {
      "epoch": 2.4945054945054945,
      "grad_norm": 0.4370464086532593,
      "learning_rate": 3.458980044345898e-05,
      "loss": 0.6504,
      "step": 379
    },
    {
      "epoch": 2.501098901098901,
      "grad_norm": 0.393479585647583,
      "learning_rate": 3.414634146341464e-05,
      "loss": 0.6345,
      "step": 380
    },
    {
      "epoch": 2.5076923076923077,
      "grad_norm": 0.41891852021217346,
      "learning_rate": 3.370288248337029e-05,
      "loss": 0.6489,
      "step": 381
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.3806121051311493,
      "learning_rate": 3.325942350332594e-05,
      "loss": 0.5942,
      "step": 382
    },
    {
      "epoch": 2.520879120879121,
      "grad_norm": 0.40185481309890747,
      "learning_rate": 3.28159645232816e-05,
      "loss": 0.614,
      "step": 383
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 0.3859177529811859,
      "learning_rate": 3.237250554323725e-05,
      "loss": 0.548,
      "step": 384
    },
    {
      "epoch": 2.534065934065934,
      "grad_norm": 0.4168393313884735,
      "learning_rate": 3.19290465631929e-05,
      "loss": 0.5738,
      "step": 385
    },
    {
      "epoch": 2.5406593406593405,
      "grad_norm": 0.40933817625045776,
      "learning_rate": 3.148558758314856e-05,
      "loss": 0.5846,
      "step": 386
    },
    {
      "epoch": 2.547252747252747,
      "grad_norm": 0.4150947332382202,
      "learning_rate": 3.104212860310421e-05,
      "loss": 0.6076,
      "step": 387
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.414905846118927,
      "learning_rate": 3.059866962305987e-05,
      "loss": 0.6391,
      "step": 388
    },
    {
      "epoch": 2.5604395604395602,
      "grad_norm": 0.38989564776420593,
      "learning_rate": 3.0155210643015524e-05,
      "loss": 0.6822,
      "step": 389
    },
    {
      "epoch": 2.567032967032967,
      "grad_norm": 0.39022666215896606,
      "learning_rate": 2.971175166297118e-05,
      "loss": 0.6548,
      "step": 390
    },
    {
      "epoch": 2.5736263736263734,
      "grad_norm": 0.40663039684295654,
      "learning_rate": 2.926829268292683e-05,
      "loss": 0.6674,
      "step": 391
    },
    {
      "epoch": 2.5802197802197804,
      "grad_norm": 0.40955108404159546,
      "learning_rate": 2.8824833702882487e-05,
      "loss": 0.5946,
      "step": 392
    },
    {
      "epoch": 2.586813186813187,
      "grad_norm": 0.41145095229148865,
      "learning_rate": 2.838137472283814e-05,
      "loss": 0.6074,
      "step": 393
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 0.4239591658115387,
      "learning_rate": 2.793791574279379e-05,
      "loss": 0.6417,
      "step": 394
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.39044350385665894,
      "learning_rate": 2.7494456762749448e-05,
      "loss": 0.5979,
      "step": 395
    },
    {
      "epoch": 2.6065934065934067,
      "grad_norm": 0.3947911560535431,
      "learning_rate": 2.7050997782705102e-05,
      "loss": 0.5186,
      "step": 396
    },
    {
      "epoch": 2.6131868131868132,
      "grad_norm": 0.41458046436309814,
      "learning_rate": 2.6607538802660753e-05,
      "loss": 0.5271,
      "step": 397
    },
    {
      "epoch": 2.61978021978022,
      "grad_norm": 0.3941086232662201,
      "learning_rate": 2.616407982261641e-05,
      "loss": 0.5187,
      "step": 398
    },
    {
      "epoch": 2.6263736263736264,
      "grad_norm": 0.42568811774253845,
      "learning_rate": 2.5720620842572062e-05,
      "loss": 0.5788,
      "step": 399
    },
    {
      "epoch": 2.632967032967033,
      "grad_norm": 0.44265496730804443,
      "learning_rate": 2.5277161862527717e-05,
      "loss": 0.6517,
      "step": 400
    },
    {
      "epoch": 2.6395604395604395,
      "grad_norm": 0.4618811309337616,
      "learning_rate": 2.483370288248337e-05,
      "loss": 0.6758,
      "step": 401
    },
    {
      "epoch": 2.646153846153846,
      "grad_norm": 0.4668862521648407,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 0.6236,
      "step": 402
    },
    {
      "epoch": 2.6527472527472526,
      "grad_norm": 0.4158099293708801,
      "learning_rate": 2.394678492239468e-05,
      "loss": 0.5667,
      "step": 403
    },
    {
      "epoch": 2.659340659340659,
      "grad_norm": 0.4353012144565582,
      "learning_rate": 2.3503325942350335e-05,
      "loss": 0.6195,
      "step": 404
    },
    {
      "epoch": 2.665934065934066,
      "grad_norm": 0.44201722741127014,
      "learning_rate": 2.3059866962305986e-05,
      "loss": 0.5694,
      "step": 405
    },
    {
      "epoch": 2.672527472527473,
      "grad_norm": 0.459583580493927,
      "learning_rate": 2.261640798226164e-05,
      "loss": 0.6507,
      "step": 406
    },
    {
      "epoch": 2.6791208791208794,
      "grad_norm": 0.42428407073020935,
      "learning_rate": 2.2172949002217298e-05,
      "loss": 0.6216,
      "step": 407
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 0.436824768781662,
      "learning_rate": 2.172949002217295e-05,
      "loss": 0.6598,
      "step": 408
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.4050062894821167,
      "learning_rate": 2.1286031042128604e-05,
      "loss": 0.5749,
      "step": 409
    },
    {
      "epoch": 2.698901098901099,
      "grad_norm": 0.4440152645111084,
      "learning_rate": 2.084257206208426e-05,
      "loss": 0.678,
      "step": 410
    },
    {
      "epoch": 2.7054945054945057,
      "grad_norm": 0.40955832600593567,
      "learning_rate": 2.0399113082039913e-05,
      "loss": 0.6095,
      "step": 411
    },
    {
      "epoch": 2.7120879120879122,
      "grad_norm": 0.4440530240535736,
      "learning_rate": 1.9955654101995567e-05,
      "loss": 0.6546,
      "step": 412
    },
    {
      "epoch": 2.718681318681319,
      "grad_norm": 0.41944122314453125,
      "learning_rate": 1.9512195121951222e-05,
      "loss": 0.572,
      "step": 413
    },
    {
      "epoch": 2.7252747252747254,
      "grad_norm": 0.4287332594394684,
      "learning_rate": 1.9068736141906873e-05,
      "loss": 0.5933,
      "step": 414
    },
    {
      "epoch": 2.731868131868132,
      "grad_norm": 0.39590445160865784,
      "learning_rate": 1.8625277161862528e-05,
      "loss": 0.5951,
      "step": 415
    },
    {
      "epoch": 2.7384615384615385,
      "grad_norm": 0.4376000463962555,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.622,
      "step": 416
    },
    {
      "epoch": 2.745054945054945,
      "grad_norm": 0.4252130091190338,
      "learning_rate": 1.7738359201773837e-05,
      "loss": 0.571,
      "step": 417
    },
    {
      "epoch": 2.7516483516483516,
      "grad_norm": 0.42905572056770325,
      "learning_rate": 1.729490022172949e-05,
      "loss": 0.6083,
      "step": 418
    },
    {
      "epoch": 2.758241758241758,
      "grad_norm": 0.4269070327281952,
      "learning_rate": 1.6851441241685146e-05,
      "loss": 0.6004,
      "step": 419
    },
    {
      "epoch": 2.764835164835165,
      "grad_norm": 0.40956637263298035,
      "learning_rate": 1.64079822616408e-05,
      "loss": 0.4729,
      "step": 420
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9324242574672896e+17,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}