{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9961880559085133,
  "eval_steps": 49,
  "global_step": 196,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005082592121982211,
      "grad_norm": 2.417446798898839,
      "learning_rate": 6.666666666666667e-07,
      "loss": 1.3227,
      "step": 1
    },
    {
      "epoch": 0.005082592121982211,
      "eval_loss": NaN,
      "eval_runtime": 462.2137,
      "eval_samples_per_second": 3.014,
      "eval_steps_per_second": 0.379,
      "step": 1
    },
    {
      "epoch": 0.010165184243964422,
      "grad_norm": 2.928692071056059,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 1.3358,
      "step": 2
    },
    {
      "epoch": 0.015247776365946633,
      "grad_norm": 2.295922498777242,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.3668,
      "step": 3
    },
    {
      "epoch": 0.020330368487928845,
      "grad_norm": 2.165639635427681,
      "learning_rate": 2.666666666666667e-06,
      "loss": 1.2876,
      "step": 4
    },
    {
      "epoch": 0.025412960609911054,
      "grad_norm": 1.4335801076375077,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.2307,
      "step": 5
    },
    {
      "epoch": 0.030495552731893267,
      "grad_norm": 1.3021209574622363,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.2824,
      "step": 6
    },
    {
      "epoch": 0.035578144853875476,
      "grad_norm": 1.233144475780061,
      "learning_rate": 4.666666666666667e-06,
      "loss": 1.2609,
      "step": 7
    },
    {
      "epoch": 0.04066073697585769,
      "grad_norm": 1.8649443938694577,
      "learning_rate": 5.333333333333334e-06,
      "loss": 1.2592,
      "step": 8
    },
    {
      "epoch": 0.045743329097839895,
      "grad_norm": 2.344947953156482,
      "learning_rate": 6e-06,
      "loss": 1.1416,
      "step": 9
    },
    {
      "epoch": 0.05082592121982211,
      "grad_norm": 4.601477812008778,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.1554,
      "step": 10
    },
    {
      "epoch": 0.05590851334180432,
      "grad_norm": 0.9781052406224989,
      "learning_rate": 7.333333333333334e-06,
      "loss": 1.1799,
      "step": 11
    },
    {
      "epoch": 0.060991105463786534,
      "grad_norm": 1.5150887808544182,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.1938,
      "step": 12
    },
    {
      "epoch": 0.06607369758576874,
      "grad_norm": 1.195420841394076,
      "learning_rate": 8.666666666666668e-06,
      "loss": 1.2875,
      "step": 13
    },
    {
      "epoch": 0.07115628970775095,
      "grad_norm": 1.446747842249035,
      "learning_rate": 9.333333333333334e-06,
      "loss": 1.2113,
      "step": 14
    },
    {
      "epoch": 0.07623888182973317,
      "grad_norm": 1.0206440434231885,
      "learning_rate": 1e-05,
      "loss": 1.1023,
      "step": 15
    },
    {
      "epoch": 0.08132147395171538,
      "grad_norm": 0.7766830838305955,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 1.1893,
      "step": 16
    },
    {
      "epoch": 0.08640406607369759,
      "grad_norm": 0.8562502894880828,
      "learning_rate": 1.1333333333333334e-05,
      "loss": 1.099,
      "step": 17
    },
    {
      "epoch": 0.09148665819567979,
      "grad_norm": 1.1790195599158821,
      "learning_rate": 1.2e-05,
      "loss": 1.1266,
      "step": 18
    },
    {
      "epoch": 0.096569250317662,
      "grad_norm": 1.1536312340591073,
      "learning_rate": 1.2666666666666667e-05,
      "loss": 1.1868,
      "step": 19
    },
    {
      "epoch": 0.10165184243964422,
      "grad_norm": 0.7170693721812672,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.1192,
      "step": 20
    },
    {
      "epoch": 0.10673443456162643,
      "grad_norm": 0.960585656847019,
      "learning_rate": 1.4e-05,
      "loss": 1.1264,
      "step": 21
    },
    {
      "epoch": 0.11181702668360864,
      "grad_norm": 0.8933902995648031,
      "learning_rate": 1.4666666666666668e-05,
      "loss": 1.0475,
      "step": 22
    },
    {
      "epoch": 0.11689961880559085,
      "grad_norm": 0.9526763881562114,
      "learning_rate": 1.5333333333333334e-05,
      "loss": 1.0869,
      "step": 23
    },
    {
      "epoch": 0.12198221092757307,
      "grad_norm": 0.8261066261177119,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.1273,
      "step": 24
    },
    {
      "epoch": 0.12706480304955528,
      "grad_norm": 1.0138316404290697,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.0167,
      "step": 25
    },
    {
      "epoch": 0.13214739517153748,
      "grad_norm": 0.6244135166489783,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 1.0642,
      "step": 26
    },
    {
      "epoch": 0.1372299872935197,
      "grad_norm": 0.6860413953391165,
      "learning_rate": 1.8e-05,
      "loss": 1.0598,
      "step": 27
    },
    {
      "epoch": 0.1423125794155019,
      "grad_norm": 0.7123933488497386,
      "learning_rate": 1.866666666666667e-05,
      "loss": 1.1359,
      "step": 28
    },
    {
      "epoch": 0.1473951715374841,
      "grad_norm": 0.8194224963685599,
      "learning_rate": 1.9333333333333333e-05,
      "loss": 1.0469,
      "step": 29
    },
    {
      "epoch": 0.15247776365946633,
      "grad_norm": 0.7428981466577943,
      "learning_rate": 2e-05,
      "loss": 1.0621,
      "step": 30
    },
    {
      "epoch": 0.15756035578144853,
      "grad_norm": 0.5978655906350417,
      "learning_rate": 1.9994461368042097e-05,
      "loss": 1.0809,
      "step": 31
    },
    {
      "epoch": 0.16264294790343076,
      "grad_norm": 0.5523263409594675,
      "learning_rate": 1.9988895058300946e-05,
      "loss": 1.1207,
      "step": 32
    },
    {
      "epoch": 0.16772554002541296,
      "grad_norm": 0.6386088808060907,
      "learning_rate": 1.998330086278876e-05,
      "loss": 1.1099,
      "step": 33
    },
    {
      "epoch": 0.17280813214739518,
      "grad_norm": 0.5889449105044371,
      "learning_rate": 1.9977678571428572e-05,
      "loss": 1.1882,
      "step": 34
    },
    {
      "epoch": 0.17789072426937738,
      "grad_norm": 0.6171122595004415,
      "learning_rate": 1.9972027972027975e-05,
      "loss": 1.1434,
      "step": 35
    },
    {
      "epoch": 0.18297331639135958,
      "grad_norm": 0.660722632169665,
      "learning_rate": 1.9966348850252384e-05,
      "loss": 1.1197,
      "step": 36
    },
    {
      "epoch": 0.1880559085133418,
      "grad_norm": 0.8384340606450145,
      "learning_rate": 1.9960640989597977e-05,
      "loss": 1.0796,
      "step": 37
    },
    {
      "epoch": 0.193138500635324,
      "grad_norm": 0.6854031551884068,
      "learning_rate": 1.995490417136415e-05,
      "loss": 1.081,
      "step": 38
    },
    {
      "epoch": 0.19822109275730623,
      "grad_norm": 0.6791992732368597,
      "learning_rate": 1.9949138174625602e-05,
      "loss": 1.1199,
      "step": 39
    },
    {
      "epoch": 0.20330368487928843,
      "grad_norm": 0.5653035313976759,
      "learning_rate": 1.9943342776203965e-05,
      "loss": 1.1191,
      "step": 40
    },
    {
      "epoch": 0.20838627700127066,
      "grad_norm": 0.7529491506419821,
      "learning_rate": 1.9937517750639022e-05,
      "loss": 1.1309,
      "step": 41
    },
    {
      "epoch": 0.21346886912325286,
      "grad_norm": 2.739538155317824,
      "learning_rate": 1.9931662870159458e-05,
      "loss": 1.1405,
      "step": 42
    },
    {
      "epoch": 0.21855146124523506,
      "grad_norm": 0.8235383414154238,
      "learning_rate": 1.9925777904653155e-05,
      "loss": 1.0874,
      "step": 43
    },
    {
      "epoch": 0.22363405336721728,
      "grad_norm": 0.636431907641577,
      "learning_rate": 1.9919862621637095e-05,
      "loss": 1.1171,
      "step": 44
    },
    {
      "epoch": 0.22871664548919948,
      "grad_norm": 0.5849746433127464,
      "learning_rate": 1.9913916786226688e-05,
      "loss": 1.0112,
      "step": 45
    },
    {
      "epoch": 0.2337992376111817,
      "grad_norm": 0.771258264938101,
      "learning_rate": 1.990794016110472e-05,
      "loss": 1.0638,
      "step": 46
    },
    {
      "epoch": 0.2388818297331639,
      "grad_norm": 0.7496683574824505,
      "learning_rate": 1.9901932506489762e-05,
      "loss": 0.9786,
      "step": 47
    },
    {
      "epoch": 0.24396442185514614,
      "grad_norm": 0.8193989912254472,
      "learning_rate": 1.989589358010411e-05,
      "loss": 1.1322,
      "step": 48
    },
    {
      "epoch": 0.24904701397712833,
      "grad_norm": 0.5316839323339139,
      "learning_rate": 1.98898231371412e-05,
      "loss": 1.0685,
      "step": 49
    },
    {
      "epoch": 0.24904701397712833,
      "eval_loss": NaN,
      "eval_runtime": 454.8058,
      "eval_samples_per_second": 3.063,
      "eval_steps_per_second": 0.385,
      "step": 49
    },
    {
      "epoch": 0.25412960609911056,
      "grad_norm": 0.5814548864442379,
      "learning_rate": 1.988372093023256e-05,
      "loss": 0.9883,
      "step": 50
    },
    {
      "epoch": 0.25921219822109276,
      "grad_norm": 0.6816224250940385,
      "learning_rate": 1.9877586709414165e-05,
      "loss": 1.0678,
      "step": 51
    },
    {
      "epoch": 0.26429479034307496,
      "grad_norm": 0.6659302304663588,
      "learning_rate": 1.9871420222092346e-05,
      "loss": 1.1103,
      "step": 52
    },
    {
      "epoch": 0.26937738246505716,
      "grad_norm": 0.6557010282469508,
      "learning_rate": 1.9865221213009086e-05,
      "loss": 1.1027,
      "step": 53
    },
    {
      "epoch": 0.2744599745870394,
      "grad_norm": 0.5102660591956714,
      "learning_rate": 1.9858989424206816e-05,
      "loss": 1.0463,
      "step": 54
    },
    {
      "epoch": 0.2795425667090216,
      "grad_norm": 0.9092403386769214,
      "learning_rate": 1.985272459499264e-05,
      "loss": 1.1451,
      "step": 55
    },
    {
      "epoch": 0.2846251588310038,
      "grad_norm": 0.6067477876422573,
      "learning_rate": 1.984642646190195e-05,
      "loss": 1.0269,
      "step": 56
    },
    {
      "epoch": 0.289707750952986,
      "grad_norm": 0.9539627940086233,
      "learning_rate": 1.9840094758661536e-05,
      "loss": 1.035,
      "step": 57
    },
    {
      "epoch": 0.2947903430749682,
      "grad_norm": 0.5662189783414849,
      "learning_rate": 1.983372921615202e-05,
      "loss": 1.0151,
      "step": 58
    },
    {
      "epoch": 0.29987293519695046,
      "grad_norm": 0.657165599335774,
      "learning_rate": 1.9827329562369756e-05,
      "loss": 1.0643,
      "step": 59
    },
    {
      "epoch": 0.30495552731893266,
      "grad_norm": 0.6751154617452281,
      "learning_rate": 1.9820895522388063e-05,
      "loss": 1.054,
      "step": 60
    },
    {
      "epoch": 0.31003811944091486,
      "grad_norm": 0.6619429396351022,
      "learning_rate": 1.9814426818317872e-05,
      "loss": 1.078,
      "step": 61
    },
    {
      "epoch": 0.31512071156289706,
      "grad_norm": 0.5939366111849416,
      "learning_rate": 1.980792316926771e-05,
      "loss": 1.0312,
      "step": 62
    },
    {
      "epoch": 0.3202033036848793,
      "grad_norm": 0.6050698536675223,
      "learning_rate": 1.980138429130304e-05,
      "loss": 0.9909,
      "step": 63
    },
    {
      "epoch": 0.3252858958068615,
      "grad_norm": 0.709448530717843,
      "learning_rate": 1.9794809897404953e-05,
      "loss": 1.0087,
      "step": 64
    },
    {
      "epoch": 0.3303684879288437,
      "grad_norm": 0.669736059058813,
      "learning_rate": 1.978819969742814e-05,
      "loss": 1.0107,
      "step": 65
    },
    {
      "epoch": 0.3354510800508259,
      "grad_norm": 0.6986784735462407,
      "learning_rate": 1.9781553398058257e-05,
      "loss": 0.9947,
      "step": 66
    },
    {
      "epoch": 0.3405336721728081,
      "grad_norm": 1.1264664572165972,
      "learning_rate": 1.977487070276848e-05,
      "loss": 0.9921,
      "step": 67
    },
    {
      "epoch": 0.34561626429479037,
      "grad_norm": 0.6700835793434858,
      "learning_rate": 1.9768151311775475e-05,
      "loss": 1.111,
      "step": 68
    },
    {
      "epoch": 0.35069885641677256,
      "grad_norm": 0.6822724145331737,
      "learning_rate": 1.9761394921994493e-05,
      "loss": 1.0596,
      "step": 69
    },
    {
      "epoch": 0.35578144853875476,
      "grad_norm": 0.6040759384639588,
      "learning_rate": 1.9754601226993868e-05,
      "loss": 1.1039,
      "step": 70
    },
    {
      "epoch": 0.36086404066073696,
      "grad_norm": 0.6449973639426745,
      "learning_rate": 1.9747769916948632e-05,
      "loss": 1.0643,
      "step": 71
    },
    {
      "epoch": 0.36594663278271916,
      "grad_norm": 1.3707597910260259,
      "learning_rate": 1.9740900678593462e-05,
      "loss": 1.0051,
      "step": 72
    },
    {
      "epoch": 0.3710292249047014,
      "grad_norm": 0.8317766567975909,
      "learning_rate": 1.973399319517476e-05,
      "loss": 1.0358,
      "step": 73
    },
    {
      "epoch": 0.3761118170266836,
      "grad_norm": 0.6836349542770239,
      "learning_rate": 1.972704714640199e-05,
      "loss": 0.9989,
      "step": 74
    },
    {
      "epoch": 0.3811944091486658,
      "grad_norm": 0.672285267907023,
      "learning_rate": 1.9720062208398136e-05,
      "loss": 1.1016,
      "step": 75
    },
    {
      "epoch": 0.386277001270648,
      "grad_norm": 0.6008642636107718,
      "learning_rate": 1.971303805364941e-05,
      "loss": 1.0148,
      "step": 76
    },
    {
      "epoch": 0.39135959339263027,
      "grad_norm": 0.6137126435530088,
      "learning_rate": 1.9705974350954024e-05,
      "loss": 0.946,
      "step": 77
    },
    {
      "epoch": 0.39644218551461247,
      "grad_norm": 0.6511125540817548,
      "learning_rate": 1.9698870765370138e-05,
      "loss": 1.0868,
      "step": 78
    },
    {
      "epoch": 0.40152477763659467,
      "grad_norm": 0.65753027445619,
      "learning_rate": 1.9691726958162946e-05,
      "loss": 1.0311,
      "step": 79
    },
    {
      "epoch": 0.40660736975857686,
      "grad_norm": 0.5461817721258532,
      "learning_rate": 1.968454258675079e-05,
      "loss": 0.9735,
      "step": 80
    },
    {
      "epoch": 0.41168996188055906,
      "grad_norm": 4.0148449609783015,
      "learning_rate": 1.967731730465043e-05,
      "loss": 1.087,
      "step": 81
    },
    {
      "epoch": 0.4167725540025413,
      "grad_norm": 0.5687951661793367,
      "learning_rate": 1.967005076142132e-05,
      "loss": 1.0163,
      "step": 82
    },
    {
      "epoch": 0.4218551461245235,
      "grad_norm": 0.5981525816475669,
      "learning_rate": 1.9662742602608975e-05,
      "loss": 0.953,
      "step": 83
    },
    {
      "epoch": 0.4269377382465057,
      "grad_norm": 0.6527915836371785,
      "learning_rate": 1.96553924696873e-05,
      "loss": 1.0516,
      "step": 84
    },
    {
      "epoch": 0.4320203303684879,
      "grad_norm": 0.5963214365816606,
      "learning_rate": 1.9648000000000002e-05,
      "loss": 1.1112,
      "step": 85
    },
    {
      "epoch": 0.4371029224904701,
      "grad_norm": 0.8494180495407153,
      "learning_rate": 1.96405648267009e-05,
      "loss": 1.0262,
      "step": 86
    },
    {
      "epoch": 0.44218551461245237,
      "grad_norm": 0.5619218395689203,
      "learning_rate": 1.9633086578693274e-05,
      "loss": 0.9716,
      "step": 87
    },
    {
      "epoch": 0.44726810673443457,
      "grad_norm": 0.5453585209280232,
      "learning_rate": 1.9625564880568112e-05,
      "loss": 1.0342,
      "step": 88
    },
    {
      "epoch": 0.45235069885641677,
      "grad_norm": 0.8362630225169261,
      "learning_rate": 1.9617999352541277e-05,
      "loss": 0.9356,
      "step": 89
    },
    {
      "epoch": 0.45743329097839897,
      "grad_norm": 0.5377879009778299,
      "learning_rate": 1.9610389610389612e-05,
      "loss": 0.9989,
      "step": 90
    },
    {
      "epoch": 0.4625158831003812,
      "grad_norm": 0.6137834508091341,
      "learning_rate": 1.9602735265385868e-05,
      "loss": 0.9171,
      "step": 91
    },
    {
      "epoch": 0.4675984752223634,
      "grad_norm": 1.769683080350329,
      "learning_rate": 1.959503592423253e-05,
      "loss": 1.0589,
      "step": 92
    },
    {
      "epoch": 0.4726810673443456,
      "grad_norm": 0.6001041891666766,
      "learning_rate": 1.9587291188994433e-05,
      "loss": 1.0287,
      "step": 93
    },
    {
      "epoch": 0.4777636594663278,
      "grad_norm": 0.6289491210658303,
      "learning_rate": 1.9579500657030224e-05,
      "loss": 1.0286,
      "step": 94
    },
    {
      "epoch": 0.48284625158831,
      "grad_norm": 0.7114332846322945,
      "learning_rate": 1.957166392092257e-05,
      "loss": 0.9367,
      "step": 95
    },
    {
      "epoch": 0.48792884371029227,
      "grad_norm": 0.5391940496295085,
      "learning_rate": 1.956378056840714e-05,
      "loss": 0.9247,
      "step": 96
    },
    {
      "epoch": 0.49301143583227447,
      "grad_norm": 0.589674085065515,
      "learning_rate": 1.9555850182300298e-05,
      "loss": 0.9389,
      "step": 97
    },
    {
      "epoch": 0.49809402795425667,
      "grad_norm": 2.5768068703243765,
      "learning_rate": 1.9547872340425533e-05,
      "loss": 1.0362,
      "step": 98
    },
    {
      "epoch": 0.49809402795425667,
      "eval_loss": NaN,
      "eval_runtime": 454.7897,
      "eval_samples_per_second": 3.063,
      "eval_steps_per_second": 0.385,
      "step": 98
    },
    {
      "epoch": 0.5031766200762389,
      "grad_norm": 0.5898947886720844,
      "learning_rate": 1.9539846615538515e-05,
      "loss": 1.0852,
      "step": 99
    },
    {
      "epoch": 0.5082592121982211,
      "grad_norm": 1.170247791808104,
      "learning_rate": 1.9531772575250837e-05,
      "loss": 0.9584,
      "step": 100
    },
    {
      "epoch": 0.5133418043202033,
      "grad_norm": 0.5296707610138294,
      "learning_rate": 1.9523649781952368e-05,
      "loss": 0.9995,
      "step": 101
    },
    {
      "epoch": 0.5184243964421855,
      "grad_norm": 1.005560288522664,
      "learning_rate": 1.9515477792732166e-05,
      "loss": 0.9777,
      "step": 102
    },
    {
      "epoch": 0.5235069885641678,
      "grad_norm": 1.0428938939017154,
      "learning_rate": 1.9507256159298012e-05,
      "loss": 1.0735,
      "step": 103
    },
    {
      "epoch": 0.5285895806861499,
      "grad_norm": 0.7851181913743503,
      "learning_rate": 1.949898442789438e-05,
      "loss": 0.991,
      "step": 104
    },
    {
      "epoch": 0.5336721728081322,
      "grad_norm": 1.2550922763496395,
      "learning_rate": 1.9490662139219015e-05,
      "loss": 0.983,
      "step": 105
    },
    {
      "epoch": 0.5387547649301143,
      "grad_norm": 0.622273113232527,
      "learning_rate": 1.9482288828337875e-05,
      "loss": 0.9351,
      "step": 106
    },
    {
      "epoch": 0.5438373570520966,
      "grad_norm": 1.3022101837507225,
      "learning_rate": 1.9473864024598567e-05,
      "loss": 0.9618,
      "step": 107
    },
    {
      "epoch": 0.5489199491740788,
      "grad_norm": 0.5578554807566163,
      "learning_rate": 1.946538725154215e-05,
      "loss": 1.0337,
      "step": 108
    },
    {
      "epoch": 0.554002541296061,
      "grad_norm": 0.7324460383858523,
      "learning_rate": 1.9456858026813338e-05,
      "loss": 1.0602,
      "step": 109
    },
    {
      "epoch": 0.5590851334180432,
      "grad_norm": 0.5524354794155449,
      "learning_rate": 1.9448275862068968e-05,
      "loss": 0.9662,
      "step": 110
    },
    {
      "epoch": 0.5641677255400254,
      "grad_norm": 0.668823878032025,
      "learning_rate": 1.9439640262884816e-05,
      "loss": 1.0083,
      "step": 111
    },
    {
      "epoch": 0.5692503176620076,
      "grad_norm": 0.6100277575552286,
      "learning_rate": 1.9430950728660656e-05,
      "loss": 1.0001,
      "step": 112
    },
    {
      "epoch": 0.5743329097839899,
      "grad_norm": 0.5908486995002686,
      "learning_rate": 1.9422206752523496e-05,
      "loss": 1.094,
      "step": 113
    },
    {
      "epoch": 0.579415501905972,
      "grad_norm": 0.5679655400443153,
      "learning_rate": 1.9413407821229053e-05,
      "loss": 0.9961,
      "step": 114
    },
    {
      "epoch": 0.5844980940279543,
      "grad_norm": 0.6224828274554025,
      "learning_rate": 1.9404553415061298e-05,
      "loss": 1.0172,
      "step": 115
    },
    {
      "epoch": 0.5895806861499364,
      "grad_norm": 0.5913419268978121,
      "learning_rate": 1.939564300773015e-05,
      "loss": 1.0175,
      "step": 116
    },
    {
      "epoch": 0.5946632782719187,
      "grad_norm": 0.6162736480008056,
      "learning_rate": 1.9386676066267185e-05,
      "loss": 1.0338,
      "step": 117
    },
    {
      "epoch": 0.5997458703939009,
      "grad_norm": 0.6128921125188392,
      "learning_rate": 1.937765205091938e-05,
      "loss": 1.0118,
      "step": 118
    },
    {
      "epoch": 0.6048284625158831,
      "grad_norm": 0.5935201407467202,
      "learning_rate": 1.9368570415040795e-05,
      "loss": 1.0772,
      "step": 119
    },
    {
      "epoch": 0.6099110546378653,
      "grad_norm": 2.2955297203218574,
      "learning_rate": 1.935943060498221e-05,
      "loss": 1.0561,
      "step": 120
    },
    {
      "epoch": 0.6149936467598475,
      "grad_norm": 0.6021547556099237,
      "learning_rate": 1.9350232059978583e-05,
      "loss": 1.0433,
      "step": 121
    },
    {
      "epoch": 0.6200762388818297,
      "grad_norm": 15.458265619359883,
      "learning_rate": 1.9340974212034385e-05,
      "loss": 0.9981,
      "step": 122
    },
    {
      "epoch": 0.625158831003812,
      "grad_norm": 1.2140568290030576,
      "learning_rate": 1.9331656485806687e-05,
      "loss": 1.0703,
      "step": 123
    },
    {
      "epoch": 0.6302414231257941,
      "grad_norm": 1.072369391194644,
      "learning_rate": 1.932227829848594e-05,
      "loss": 1.0085,
      "step": 124
    },
    {
      "epoch": 0.6353240152477764,
      "grad_norm": 0.5560086533767725,
      "learning_rate": 1.9312839059674507e-05,
      "loss": 0.948,
      "step": 125
    },
    {
      "epoch": 0.6404066073697586,
      "grad_norm": 0.6835673411297744,
      "learning_rate": 1.93033381712627e-05,
      "loss": 1.0326,
      "step": 126
    },
    {
      "epoch": 0.6454891994917408,
      "grad_norm": 0.5632555836113124,
      "learning_rate": 1.9293775027302514e-05,
      "loss": 1.0066,
      "step": 127
    },
    {
      "epoch": 0.650571791613723,
      "grad_norm": 0.756797864885407,
      "learning_rate": 1.9284149013878745e-05,
      "loss": 1.0946,
      "step": 128
    },
    {
      "epoch": 0.6556543837357052,
      "grad_norm": 0.5284862562943021,
      "learning_rate": 1.927445950897765e-05,
      "loss": 1.006,
      "step": 129
    },
    {
      "epoch": 0.6607369758576874,
      "grad_norm": 0.6743386059861107,
      "learning_rate": 1.926470588235294e-05,
      "loss": 1.0845,
      "step": 130
    },
    {
      "epoch": 0.6658195679796697,
      "grad_norm": 0.600326744146643,
      "learning_rate": 1.9254887495389156e-05,
      "loss": 1.0703,
      "step": 131
    },
    {
      "epoch": 0.6709021601016518,
      "grad_norm": 0.6781151858674082,
      "learning_rate": 1.9245003700962252e-05,
      "loss": 1.039,
      "step": 132
    },
    {
      "epoch": 0.6759847522236341,
      "grad_norm": 0.6330220485375354,
      "learning_rate": 1.923505384329744e-05,
      "loss": 1.0711,
      "step": 133
    },
    {
      "epoch": 0.6810673443456162,
      "grad_norm": 0.7355514488741505,
      "learning_rate": 1.9225037257824145e-05,
      "loss": 1.0303,
      "step": 134
    },
    {
      "epoch": 0.6861499364675985,
      "grad_norm": 1.2520345572978264,
      "learning_rate": 1.921495327102804e-05,
      "loss": 1.1175,
      "step": 135
    },
    {
      "epoch": 0.6912325285895807,
      "grad_norm": 0.6090687761757717,
      "learning_rate": 1.920480120030008e-05,
      "loss": 0.9646,
      "step": 136
    },
    {
      "epoch": 0.6963151207115629,
      "grad_norm": 0.5292705285452848,
      "learning_rate": 1.9194580353782463e-05,
      "loss": 0.9466,
      "step": 137
    },
    {
      "epoch": 0.7013977128335451,
      "grad_norm": 0.631666235944858,
      "learning_rate": 1.9184290030211485e-05,
      "loss": 1.0214,
      "step": 138
    },
    {
      "epoch": 0.7064803049555273,
      "grad_norm": 0.5330412095712574,
      "learning_rate": 1.9173929518757108e-05,
      "loss": 1.0399,
      "step": 139
    },
    {
      "epoch": 0.7115628970775095,
      "grad_norm": 0.5857060018855021,
      "learning_rate": 1.9163498098859318e-05,
      "loss": 0.8816,
      "step": 140
    },
    {
      "epoch": 0.7166454891994918,
      "grad_norm": 0.5525598551714797,
      "learning_rate": 1.9152995040061047e-05,
      "loss": 1.059,
      "step": 141
    },
    {
      "epoch": 0.7217280813214739,
      "grad_norm": 0.5680224766891685,
      "learning_rate": 1.9142419601837675e-05,
      "loss": 1.0108,
      "step": 142
    },
    {
      "epoch": 0.7268106734434562,
      "grad_norm": 0.8442456969016195,
      "learning_rate": 1.9131771033422974e-05,
      "loss": 1.1537,
      "step": 143
    },
    {
      "epoch": 0.7318932655654383,
      "grad_norm": 0.6777941101499753,
      "learning_rate": 1.912104857363146e-05,
      "loss": 0.9485,
      "step": 144
    },
    {
      "epoch": 0.7369758576874206,
      "grad_norm": 0.6047611797963537,
      "learning_rate": 1.9110251450676987e-05,
      "loss": 1.1167,
      "step": 145
    },
    {
      "epoch": 0.7420584498094028,
      "grad_norm": 0.7302224761524364,
      "learning_rate": 1.9099378881987576e-05,
      "loss": 1.0066,
      "step": 146
    },
    {
      "epoch": 0.747141041931385,
      "grad_norm": 0.679593185673484,
      "learning_rate": 1.9088430074016365e-05,
      "loss": 1.0814,
      "step": 147
    },
    {
      "epoch": 0.747141041931385,
      "eval_loss": NaN,
      "eval_runtime": 454.9184,
      "eval_samples_per_second": 3.062,
      "eval_steps_per_second": 0.385,
      "step": 147
    },
    {
      "epoch": 0.7522236340533672,
      "grad_norm": 0.5396369338052232,
      "learning_rate": 1.9077404222048476e-05,
      "loss": 1.0294,
      "step": 148
    },
    {
      "epoch": 0.7573062261753494,
      "grad_norm": 0.569056375341392,
      "learning_rate": 1.9066300510003925e-05,
      "loss": 1.0177,
      "step": 149
    },
    {
      "epoch": 0.7623888182973316,
      "grad_norm": 0.6924084063596142,
      "learning_rate": 1.905511811023622e-05,
      "loss": 0.9484,
      "step": 150
    },
    {
      "epoch": 0.7674714104193139,
      "grad_norm": 0.776918131135741,
      "learning_rate": 1.904385618332675e-05,
      "loss": 1.0091,
      "step": 151
    },
    {
      "epoch": 0.772554002541296,
      "grad_norm": 0.5631403333949265,
      "learning_rate": 1.9032513877874704e-05,
      "loss": 1.0455,
      "step": 152
    },
    {
      "epoch": 0.7776365946632783,
      "grad_norm": 0.5234633902025975,
      "learning_rate": 1.9021090330282533e-05,
      "loss": 0.8902,
      "step": 153
    },
    {
      "epoch": 0.7827191867852605,
      "grad_norm": 0.8954844619126904,
      "learning_rate": 1.9009584664536742e-05,
      "loss": 1.1005,
      "step": 154
    },
    {
      "epoch": 0.7878017789072427,
      "grad_norm": 0.9593051257588633,
      "learning_rate": 1.899799599198397e-05,
      "loss": 1.0136,
      "step": 155
    },
    {
      "epoch": 0.7928843710292249,
      "grad_norm": 0.7462701977681836,
      "learning_rate": 1.8986323411102173e-05,
      "loss": 0.9644,
      "step": 156
    },
    {
      "epoch": 0.7979669631512071,
      "grad_norm": 0.5185601200545743,
      "learning_rate": 1.8974566007266858e-05,
      "loss": 1.0351,
      "step": 157
    },
    {
      "epoch": 0.8030495552731893,
      "grad_norm": 0.5198417937751084,
      "learning_rate": 1.896272285251216e-05,
      "loss": 1.0483,
      "step": 158
    },
    {
      "epoch": 0.8081321473951716,
      "grad_norm": 0.6547184013524777,
      "learning_rate": 1.8950793005286704e-05,
      "loss": 1.064,
      "step": 159
    },
    {
      "epoch": 0.8132147395171537,
      "grad_norm": 0.6353570340115701,
      "learning_rate": 1.8938775510204083e-05,
      "loss": 0.9942,
      "step": 160
    },
    {
      "epoch": 0.818297331639136,
      "grad_norm": 0.6593647760506935,
      "learning_rate": 1.8926669397787795e-05,
      "loss": 0.9364,
      "step": 161
    },
    {
      "epoch": 0.8233799237611181,
      "grad_norm": 0.7127754736535036,
      "learning_rate": 1.8914473684210527e-05,
      "loss": 1.0383,
      "step": 162
    },
    {
      "epoch": 0.8284625158831004,
      "grad_norm": 0.5387503654944155,
      "learning_rate": 1.8902187371027652e-05,
      "loss": 1.013,
      "step": 163
    },
    {
      "epoch": 0.8335451080050826,
      "grad_norm": 0.5486326058897425,
      "learning_rate": 1.8889809444904724e-05,
      "loss": 1.0064,
      "step": 164
    },
    {
      "epoch": 0.8386277001270648,
      "grad_norm": 0.5469444493707462,
      "learning_rate": 1.887733887733888e-05,
      "loss": 0.9686,
      "step": 165
    },
    {
      "epoch": 0.843710292249047,
      "grad_norm": 1.2362111579657413,
      "learning_rate": 1.8864774624373957e-05,
      "loss": 0.9969,
      "step": 166
    },
    {
      "epoch": 0.8487928843710292,
      "grad_norm": 0.6714649440871081,
      "learning_rate": 1.8852115626309178e-05,
      "loss": 0.9914,
      "step": 167
    },
    {
      "epoch": 0.8538754764930114,
      "grad_norm": 0.5790818230708058,
      "learning_rate": 1.883936080740118e-05,
      "loss": 0.9756,
      "step": 168
    },
    {
      "epoch": 0.8589580686149937,
      "grad_norm": 0.7837618766260191,
      "learning_rate": 1.882650907555931e-05,
      "loss": 1.0127,
      "step": 169
    },
    {
      "epoch": 0.8640406607369758,
      "grad_norm": 0.7086746606620099,
      "learning_rate": 1.88135593220339e-05,
      "loss": 1.1598,
      "step": 170
    },
    {
      "epoch": 0.8691232528589581,
      "grad_norm": 0.6038564000981422,
      "learning_rate": 1.880051042109741e-05,
      "loss": 1.0328,
      "step": 171
    },
    {
      "epoch": 0.8742058449809402,
      "grad_norm": 0.5480641081333995,
      "learning_rate": 1.878736122971819e-05,
      "loss": 1.0436,
      "step": 172
    },
    {
      "epoch": 0.8792884371029225,
      "grad_norm": 0.5760210427645431,
      "learning_rate": 1.8774110587226747e-05,
      "loss": 0.9944,
      "step": 173
    },
    {
      "epoch": 0.8843710292249047,
      "grad_norm": 0.5973246266208786,
      "learning_rate": 1.8760757314974183e-05,
      "loss": 0.9776,
      "step": 174
    },
    {
      "epoch": 0.8894536213468869,
      "grad_norm": 0.5919506841693293,
      "learning_rate": 1.8747300215982725e-05,
      "loss": 0.9878,
      "step": 175
    },
    {
      "epoch": 0.8945362134688691,
      "grad_norm": 1.0854485554789506,
      "learning_rate": 1.873373807458803e-05,
      "loss": 1.106,
      "step": 176
    },
    {
      "epoch": 0.8996188055908514,
      "grad_norm": 0.5983944451554725,
      "learning_rate": 1.872006965607314e-05,
      "loss": 1.0879,
      "step": 177
    },
    {
      "epoch": 0.9047013977128335,
      "grad_norm": 0.6634154303973875,
      "learning_rate": 1.870629370629371e-05,
      "loss": 0.9286,
      "step": 178
    },
    {
      "epoch": 0.9097839898348158,
      "grad_norm": 0.5854692268990905,
      "learning_rate": 1.869240895129443e-05,
      "loss": 0.9738,
      "step": 179
    },
    {
      "epoch": 0.9148665819567979,
      "grad_norm": 0.6129124494505737,
      "learning_rate": 1.8678414096916303e-05,
      "loss": 1.1037,
      "step": 180
    },
    {
      "epoch": 0.9199491740787802,
      "grad_norm": 1.0109462911647256,
      "learning_rate": 1.8664307828394515e-05,
      "loss": 0.9844,
      "step": 181
    },
    {
      "epoch": 0.9250317662007624,
      "grad_norm": 0.5765605814856808,
      "learning_rate": 1.8650088809946714e-05,
      "loss": 1.0584,
      "step": 182
    },
    {
      "epoch": 0.9301143583227446,
      "grad_norm": 0.5399969782623486,
      "learning_rate": 1.8635755684351314e-05,
      "loss": 1.0444,
      "step": 183
    },
    {
      "epoch": 0.9351969504447268,
      "grad_norm": 0.6015410734318279,
      "learning_rate": 1.862130707251567e-05,
      "loss": 1.0178,
      "step": 184
    },
    {
      "epoch": 0.940279542566709,
      "grad_norm": 0.5028759554734284,
      "learning_rate": 1.8606741573033708e-05,
      "loss": 0.9699,
      "step": 185
    },
    {
      "epoch": 0.9453621346886912,
      "grad_norm": 0.5458432185038177,
      "learning_rate": 1.8592057761732854e-05,
      "loss": 0.9319,
      "step": 186
    },
    {
      "epoch": 0.9504447268106735,
      "grad_norm": 0.5646703109862106,
      "learning_rate": 1.8577254191209787e-05,
      "loss": 0.9879,
      "step": 187
    },
    {
      "epoch": 0.9555273189326556,
      "grad_norm": 0.5213455747955001,
      "learning_rate": 1.856232939035487e-05,
      "loss": 0.93,
      "step": 188
    },
    {
      "epoch": 0.9606099110546379,
      "grad_norm": 0.6160630051745865,
      "learning_rate": 1.854728186386478e-05,
      "loss": 0.9984,
      "step": 189
    },
    {
      "epoch": 0.96569250317662,
      "grad_norm": 0.5717108146075167,
      "learning_rate": 1.853211009174312e-05,
      "loss": 0.9986,
      "step": 190
    },
    {
      "epoch": 0.9707750952986023,
      "grad_norm": 1.1933909225187864,
      "learning_rate": 1.8516812528788576e-05,
      "loss": 0.9603,
      "step": 191
    },
    {
      "epoch": 0.9758576874205845,
      "grad_norm": 0.5476464515272882,
      "learning_rate": 1.8501387604070308e-05,
      "loss": 1.0174,
      "step": 192
    },
    {
      "epoch": 0.9809402795425667,
      "grad_norm": 0.6026655085443507,
      "learning_rate": 1.8485833720390153e-05,
      "loss": 0.9648,
      "step": 193
    },
    {
      "epoch": 0.9860228716645489,
      "grad_norm": 0.5597982416459779,
      "learning_rate": 1.8470149253731344e-05,
      "loss": 1.064,
      "step": 194
    },
    {
      "epoch": 0.9911054637865311,
      "grad_norm": 0.5256542216530053,
      "learning_rate": 1.845433255269321e-05,
      "loss": 0.9485,
      "step": 195
    },
    {
      "epoch": 0.9961880559085133,
      "grad_norm": 0.5698011465117779,
      "learning_rate": 1.843838193791157e-05,
      "loss": 1.0465,
      "step": 196
    },
    {
      "epoch": 0.9961880559085133,
      "eval_loss": NaN,
      "eval_runtime": 454.5687,
      "eval_samples_per_second": 3.064,
      "eval_steps_per_second": 0.385,
      "step": 196
    }
  ],
  "logging_steps": 1,
  "max_steps": 392,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 196,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.09553504082985e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}