{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09586961732044419,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031956539106814733,
      "grad_norm": 5.807275295257568,
      "learning_rate": 0.0,
      "loss": 5.0454,
      "step": 1
    },
    {
      "epoch": 0.0006391307821362947,
      "grad_norm": 6.20149564743042,
      "learning_rate": 6.369426751592357e-07,
      "loss": 5.1424,
      "step": 2
    },
    {
      "epoch": 0.0012782615642725893,
      "grad_norm": 5.7567291259765625,
      "learning_rate": 1.910828025477707e-06,
      "loss": 5.0835,
      "step": 4
    },
    {
      "epoch": 0.001917392346408884,
      "grad_norm": 5.017141819000244,
      "learning_rate": 3.1847133757961785e-06,
      "loss": 5.0733,
      "step": 6
    },
    {
      "epoch": 0.0025565231285451786,
      "grad_norm": 3.2059810161590576,
      "learning_rate": 4.45859872611465e-06,
      "loss": 5.0714,
      "step": 8
    },
    {
      "epoch": 0.003195653910681473,
      "grad_norm": 6.303244113922119,
      "learning_rate": 5.732484076433121e-06,
      "loss": 4.9915,
      "step": 10
    },
    {
      "epoch": 0.003834784692817768,
      "grad_norm": 4.852840423583984,
      "learning_rate": 7.006369426751593e-06,
      "loss": 4.9307,
      "step": 12
    },
    {
      "epoch": 0.004473915474954062,
      "grad_norm": 3.78067946434021,
      "learning_rate": 8.280254777070064e-06,
      "loss": 4.8924,
      "step": 14
    },
    {
      "epoch": 0.005113046257090357,
      "grad_norm": 3.5641331672668457,
      "learning_rate": 9.554140127388536e-06,
      "loss": 4.8244,
      "step": 16
    },
    {
      "epoch": 0.005752177039226652,
      "grad_norm": 2.191957712173462,
      "learning_rate": 1.0828025477707008e-05,
      "loss": 4.6179,
      "step": 18
    },
    {
      "epoch": 0.006391307821362946,
      "grad_norm": 2.0675458908081055,
      "learning_rate": 1.2101910828025478e-05,
      "loss": 4.5827,
      "step": 20
    },
    {
      "epoch": 0.007030438603499241,
      "grad_norm": 1.6559146642684937,
      "learning_rate": 1.337579617834395e-05,
      "loss": 4.4544,
      "step": 22
    },
    {
      "epoch": 0.007669569385635536,
      "grad_norm": 1.3731284141540527,
      "learning_rate": 1.464968152866242e-05,
      "loss": 4.3748,
      "step": 24
    },
    {
      "epoch": 0.00830870016777183,
      "grad_norm": 1.3962030410766602,
      "learning_rate": 1.592356687898089e-05,
      "loss": 4.3269,
      "step": 26
    },
    {
      "epoch": 0.008947830949908125,
      "grad_norm": 1.2659896612167358,
      "learning_rate": 1.7197452229299362e-05,
      "loss": 4.2133,
      "step": 28
    },
    {
      "epoch": 0.00958696173204442,
      "grad_norm": 0.9881806373596191,
      "learning_rate": 1.8471337579617834e-05,
      "loss": 4.0961,
      "step": 30
    },
    {
      "epoch": 0.010226092514180714,
      "grad_norm": 0.9945515394210815,
      "learning_rate": 1.974522292993631e-05,
      "loss": 4.0158,
      "step": 32
    },
    {
      "epoch": 0.01086522329631701,
      "grad_norm": 0.9396588802337646,
      "learning_rate": 2.1019108280254778e-05,
      "loss": 3.8763,
      "step": 34
    },
    {
      "epoch": 0.011504354078453304,
      "grad_norm": 1.0665779113769531,
      "learning_rate": 2.229299363057325e-05,
      "loss": 3.8635,
      "step": 36
    },
    {
      "epoch": 0.012143484860589597,
      "grad_norm": 1.077245831489563,
      "learning_rate": 2.356687898089172e-05,
      "loss": 3.802,
      "step": 38
    },
    {
      "epoch": 0.012782615642725892,
      "grad_norm": 0.8040191531181335,
      "learning_rate": 2.4840764331210193e-05,
      "loss": 3.7284,
      "step": 40
    },
    {
      "epoch": 0.013421746424862187,
      "grad_norm": 1.4325759410858154,
      "learning_rate": 2.6114649681528662e-05,
      "loss": 3.665,
      "step": 42
    },
    {
      "epoch": 0.014060877206998482,
      "grad_norm": 1.3450332880020142,
      "learning_rate": 2.7388535031847134e-05,
      "loss": 3.6242,
      "step": 44
    },
    {
      "epoch": 0.014700007989134777,
      "grad_norm": 0.8203895688056946,
      "learning_rate": 2.8662420382165606e-05,
      "loss": 3.5576,
      "step": 46
    },
    {
      "epoch": 0.015339138771271072,
      "grad_norm": 1.1661335229873657,
      "learning_rate": 2.9936305732484078e-05,
      "loss": 3.522,
      "step": 48
    },
    {
      "epoch": 0.015978269553407365,
      "grad_norm": 1.0148671865463257,
      "learning_rate": 3.121019108280255e-05,
      "loss": 3.4594,
      "step": 50
    },
    {
      "epoch": 0.01661740033554366,
      "grad_norm": 0.6624857187271118,
      "learning_rate": 3.248407643312102e-05,
      "loss": 3.465,
      "step": 52
    },
    {
      "epoch": 0.017256531117679955,
      "grad_norm": 0.943125307559967,
      "learning_rate": 3.375796178343949e-05,
      "loss": 3.4021,
      "step": 54
    },
    {
      "epoch": 0.01789566189981625,
      "grad_norm": 0.9854550957679749,
      "learning_rate": 3.503184713375796e-05,
      "loss": 3.3361,
      "step": 56
    },
    {
      "epoch": 0.018534792681952544,
      "grad_norm": 1.2242411375045776,
      "learning_rate": 3.630573248407643e-05,
      "loss": 3.3283,
      "step": 58
    },
    {
      "epoch": 0.01917392346408884,
      "grad_norm": 0.9556372761726379,
      "learning_rate": 3.7579617834394906e-05,
      "loss": 3.2914,
      "step": 60
    },
    {
      "epoch": 0.019813054246225134,
      "grad_norm": 1.3133809566497803,
      "learning_rate": 3.885350318471338e-05,
      "loss": 3.3126,
      "step": 62
    },
    {
      "epoch": 0.02045218502836143,
      "grad_norm": 0.9322234392166138,
      "learning_rate": 4.012738853503185e-05,
      "loss": 3.2443,
      "step": 64
    },
    {
      "epoch": 0.021091315810497724,
      "grad_norm": 1.4383481740951538,
      "learning_rate": 4.1401273885350325e-05,
      "loss": 3.2428,
      "step": 66
    },
    {
      "epoch": 0.02173044659263402,
      "grad_norm": 1.0156841278076172,
      "learning_rate": 4.267515923566879e-05,
      "loss": 3.1735,
      "step": 68
    },
    {
      "epoch": 0.022369577374770314,
      "grad_norm": 1.1754450798034668,
      "learning_rate": 4.394904458598726e-05,
      "loss": 3.1788,
      "step": 70
    },
    {
      "epoch": 0.02300870815690661,
      "grad_norm": 1.0960084199905396,
      "learning_rate": 4.522292993630574e-05,
      "loss": 3.1963,
      "step": 72
    },
    {
      "epoch": 0.023647838939042903,
      "grad_norm": 1.054401159286499,
      "learning_rate": 4.6496815286624206e-05,
      "loss": 3.1604,
      "step": 74
    },
    {
      "epoch": 0.024286969721179195,
      "grad_norm": 1.1957581043243408,
      "learning_rate": 4.777070063694268e-05,
      "loss": 3.1648,
      "step": 76
    },
    {
      "epoch": 0.02492610050331549,
      "grad_norm": 0.7756203413009644,
      "learning_rate": 4.904458598726115e-05,
      "loss": 3.1066,
      "step": 78
    },
    {
      "epoch": 0.025565231285451784,
      "grad_norm": 1.0459190607070923,
      "learning_rate": 5.031847133757962e-05,
      "loss": 3.1571,
      "step": 80
    },
    {
      "epoch": 0.02620436206758808,
      "grad_norm": 0.9746761322021484,
      "learning_rate": 5.159235668789809e-05,
      "loss": 3.1026,
      "step": 82
    },
    {
      "epoch": 0.026843492849724374,
      "grad_norm": 1.0770882368087769,
      "learning_rate": 5.286624203821656e-05,
      "loss": 3.1125,
      "step": 84
    },
    {
      "epoch": 0.02748262363186067,
      "grad_norm": 0.9542138576507568,
      "learning_rate": 5.414012738853504e-05,
      "loss": 3.059,
      "step": 86
    },
    {
      "epoch": 0.028121754413996964,
      "grad_norm": 1.3454134464263916,
      "learning_rate": 5.5414012738853505e-05,
      "loss": 3.0645,
      "step": 88
    },
    {
      "epoch": 0.02876088519613326,
      "grad_norm": 1.0354089736938477,
      "learning_rate": 5.6687898089171974e-05,
      "loss": 3.04,
      "step": 90
    },
    {
      "epoch": 0.029400015978269554,
      "grad_norm": 1.1339548826217651,
      "learning_rate": 5.796178343949045e-05,
      "loss": 3.0625,
      "step": 92
    },
    {
      "epoch": 0.03003914676040585,
      "grad_norm": 1.200062870979309,
      "learning_rate": 5.923566878980892e-05,
      "loss": 3.057,
      "step": 94
    },
    {
      "epoch": 0.030678277542542143,
      "grad_norm": 1.395698070526123,
      "learning_rate": 6.0509554140127386e-05,
      "loss": 3.0341,
      "step": 96
    },
    {
      "epoch": 0.031317408324678435,
      "grad_norm": 0.9392653703689575,
      "learning_rate": 6.178343949044585e-05,
      "loss": 3.0087,
      "step": 98
    },
    {
      "epoch": 0.03195653910681473,
      "grad_norm": 1.1301568746566772,
      "learning_rate": 6.305732484076433e-05,
      "loss": 3.0294,
      "step": 100
    },
    {
      "epoch": 0.032595669888951025,
      "grad_norm": 0.9571443796157837,
      "learning_rate": 6.43312101910828e-05,
      "loss": 3.0522,
      "step": 102
    },
    {
      "epoch": 0.03323480067108732,
      "grad_norm": 0.9494081735610962,
      "learning_rate": 6.560509554140127e-05,
      "loss": 3.0012,
      "step": 104
    },
    {
      "epoch": 0.033873931453223614,
      "grad_norm": 1.3672889471054077,
      "learning_rate": 6.687898089171974e-05,
      "loss": 3.0188,
      "step": 106
    },
    {
      "epoch": 0.03451306223535991,
      "grad_norm": 1.2122056484222412,
      "learning_rate": 6.815286624203822e-05,
      "loss": 2.9497,
      "step": 108
    },
    {
      "epoch": 0.035152193017496204,
      "grad_norm": 1.2184698581695557,
      "learning_rate": 6.942675159235669e-05,
      "loss": 2.9739,
      "step": 110
    },
    {
      "epoch": 0.0357913237996325,
      "grad_norm": 1.09404456615448,
      "learning_rate": 7.070063694267515e-05,
      "loss": 3.0241,
      "step": 112
    },
    {
      "epoch": 0.036430454581768794,
      "grad_norm": 1.1653715372085571,
      "learning_rate": 7.197452229299363e-05,
      "loss": 2.9606,
      "step": 114
    },
    {
      "epoch": 0.03706958536390509,
      "grad_norm": 1.050194501876831,
      "learning_rate": 7.32484076433121e-05,
      "loss": 2.9582,
      "step": 116
    },
    {
      "epoch": 0.037708716146041384,
      "grad_norm": 1.1262322664260864,
      "learning_rate": 7.452229299363057e-05,
      "loss": 2.9462,
      "step": 118
    },
    {
      "epoch": 0.03834784692817768,
      "grad_norm": 1.1232227087020874,
      "learning_rate": 7.579617834394906e-05,
      "loss": 2.9784,
      "step": 120
    },
    {
      "epoch": 0.03898697771031397,
      "grad_norm": 0.9088072776794434,
      "learning_rate": 7.707006369426753e-05,
      "loss": 2.944,
      "step": 122
    },
    {
      "epoch": 0.03962610849245027,
      "grad_norm": 0.8985419869422913,
      "learning_rate": 7.834394904458599e-05,
      "loss": 2.9003,
      "step": 124
    },
    {
      "epoch": 0.04026523927458656,
      "grad_norm": 1.2419854402542114,
      "learning_rate": 7.961783439490447e-05,
      "loss": 2.9753,
      "step": 126
    },
    {
      "epoch": 0.04090437005672286,
      "grad_norm": 1.4533154964447021,
      "learning_rate": 8.089171974522294e-05,
      "loss": 2.9069,
      "step": 128
    },
    {
      "epoch": 0.04154350083885915,
      "grad_norm": 1.475258231163025,
      "learning_rate": 8.21656050955414e-05,
      "loss": 2.9402,
      "step": 130
    },
    {
      "epoch": 0.04218263162099545,
      "grad_norm": 1.0348827838897705,
      "learning_rate": 8.343949044585988e-05,
      "loss": 2.9295,
      "step": 132
    },
    {
      "epoch": 0.04282176240313174,
      "grad_norm": 0.9143719673156738,
      "learning_rate": 8.471337579617836e-05,
      "loss": 2.9408,
      "step": 134
    },
    {
      "epoch": 0.04346089318526804,
      "grad_norm": 1.1310492753982544,
      "learning_rate": 8.598726114649682e-05,
      "loss": 2.875,
      "step": 136
    },
    {
      "epoch": 0.04410002396740433,
      "grad_norm": 1.0483386516571045,
      "learning_rate": 8.726114649681529e-05,
      "loss": 2.9142,
      "step": 138
    },
    {
      "epoch": 0.04473915474954063,
      "grad_norm": 0.921519935131073,
      "learning_rate": 8.853503184713377e-05,
      "loss": 2.9188,
      "step": 140
    },
    {
      "epoch": 0.04537828553167692,
      "grad_norm": 1.3271907567977905,
      "learning_rate": 8.980891719745223e-05,
      "loss": 2.9075,
      "step": 142
    },
    {
      "epoch": 0.04601741631381322,
      "grad_norm": 1.7488983869552612,
      "learning_rate": 9.10828025477707e-05,
      "loss": 2.9201,
      "step": 144
    },
    {
      "epoch": 0.04665654709594951,
      "grad_norm": 1.4263213872909546,
      "learning_rate": 9.235668789808918e-05,
      "loss": 2.9045,
      "step": 146
    },
    {
      "epoch": 0.04729567787808581,
      "grad_norm": 0.8777288794517517,
      "learning_rate": 9.363057324840766e-05,
      "loss": 2.8959,
      "step": 148
    },
    {
      "epoch": 0.047934808660222095,
      "grad_norm": 1.3402196168899536,
      "learning_rate": 9.490445859872612e-05,
      "loss": 2.8893,
      "step": 150
    },
    {
      "epoch": 0.04857393944235839,
      "grad_norm": 1.0943351984024048,
      "learning_rate": 9.617834394904459e-05,
      "loss": 2.9137,
      "step": 152
    },
    {
      "epoch": 0.049213070224494684,
      "grad_norm": 1.0603907108306885,
      "learning_rate": 9.745222929936307e-05,
      "loss": 2.8677,
      "step": 154
    },
    {
      "epoch": 0.04985220100663098,
      "grad_norm": 1.010772705078125,
      "learning_rate": 9.872611464968153e-05,
      "loss": 2.8374,
      "step": 156
    },
    {
      "epoch": 0.050491331788767274,
      "grad_norm": 1.2628934383392334,
      "learning_rate": 0.0001,
      "loss": 2.9009,
      "step": 158
    },
    {
      "epoch": 0.05113046257090357,
      "grad_norm": 1.146183729171753,
      "learning_rate": 9.999988833687822e-05,
      "loss": 2.8633,
      "step": 160
    },
    {
      "epoch": 0.051769593353039864,
      "grad_norm": 0.8704808354377747,
      "learning_rate": 9.99995533480116e-05,
      "loss": 2.8464,
      "step": 162
    },
    {
      "epoch": 0.05240872413517616,
      "grad_norm": 1.044418454170227,
      "learning_rate": 9.999899503489641e-05,
      "loss": 2.8695,
      "step": 164
    },
    {
      "epoch": 0.053047854917312454,
      "grad_norm": 0.833791196346283,
      "learning_rate": 9.999821340002636e-05,
      "loss": 2.8605,
      "step": 166
    },
    {
      "epoch": 0.05368698569944875,
      "grad_norm": 0.922815203666687,
      "learning_rate": 9.99972084468926e-05,
      "loss": 2.8737,
      "step": 168
    },
    {
      "epoch": 0.05432611648158504,
      "grad_norm": 0.9120809435844421,
      "learning_rate": 9.999598017998384e-05,
      "loss": 2.8753,
      "step": 170
    },
    {
      "epoch": 0.05496524726372134,
      "grad_norm": 1.0272431373596191,
      "learning_rate": 9.999452860478611e-05,
      "loss": 2.8907,
      "step": 172
    },
    {
      "epoch": 0.05560437804585763,
      "grad_norm": 0.7777165174484253,
      "learning_rate": 9.999285372778295e-05,
      "loss": 2.8517,
      "step": 174
    },
    {
      "epoch": 0.05624350882799393,
      "grad_norm": 0.7110999822616577,
      "learning_rate": 9.999095555645523e-05,
      "loss": 2.8211,
      "step": 176
    },
    {
      "epoch": 0.05688263961013022,
      "grad_norm": 0.7857067584991455,
      "learning_rate": 9.998883409928117e-05,
      "loss": 2.8463,
      "step": 178
    },
    {
      "epoch": 0.05752177039226652,
      "grad_norm": 0.8582798838615417,
      "learning_rate": 9.998648936573629e-05,
      "loss": 2.8197,
      "step": 180
    },
    {
      "epoch": 0.05816090117440281,
      "grad_norm": 0.9790541529655457,
      "learning_rate": 9.998392136629345e-05,
      "loss": 2.8193,
      "step": 182
    },
    {
      "epoch": 0.05880003195653911,
      "grad_norm": 1.1599719524383545,
      "learning_rate": 9.998113011242264e-05,
      "loss": 2.8206,
      "step": 184
    },
    {
      "epoch": 0.0594391627386754,
      "grad_norm": 0.8326631188392639,
      "learning_rate": 9.99781156165911e-05,
      "loss": 2.8349,
      "step": 186
    },
    {
      "epoch": 0.0600782935208117,
      "grad_norm": 0.8876377940177917,
      "learning_rate": 9.997487789226312e-05,
      "loss": 2.8225,
      "step": 188
    },
    {
      "epoch": 0.06071742430294799,
      "grad_norm": 0.9899202585220337,
      "learning_rate": 9.997141695390009e-05,
      "loss": 2.7875,
      "step": 190
    },
    {
      "epoch": 0.06135655508508429,
      "grad_norm": 1.0686557292938232,
      "learning_rate": 9.996773281696037e-05,
      "loss": 2.8024,
      "step": 192
    },
    {
      "epoch": 0.06199568586722058,
      "grad_norm": 0.8899752497673035,
      "learning_rate": 9.996382549789926e-05,
      "loss": 2.8225,
      "step": 194
    },
    {
      "epoch": 0.06263481664935687,
      "grad_norm": 0.7781797647476196,
      "learning_rate": 9.995969501416891e-05,
      "loss": 2.8046,
      "step": 196
    },
    {
      "epoch": 0.06327394743149317,
      "grad_norm": 0.6428512930870056,
      "learning_rate": 9.995534138421818e-05,
      "loss": 2.7693,
      "step": 198
    },
    {
      "epoch": 0.06391307821362946,
      "grad_norm": 0.7047809958457947,
      "learning_rate": 9.995076462749273e-05,
      "loss": 2.766,
      "step": 200
    },
    {
      "epoch": 0.06455220899576576,
      "grad_norm": 0.6256312131881714,
      "learning_rate": 9.99459647644347e-05,
      "loss": 2.8071,
      "step": 202
    },
    {
      "epoch": 0.06519133977790205,
      "grad_norm": 0.699400007724762,
      "learning_rate": 9.994094181648283e-05,
      "loss": 2.8347,
      "step": 204
    },
    {
      "epoch": 0.06583047056003835,
      "grad_norm": 0.7256817817687988,
      "learning_rate": 9.993569580607225e-05,
      "loss": 2.8074,
      "step": 206
    },
    {
      "epoch": 0.06646960134217464,
      "grad_norm": 0.573846161365509,
      "learning_rate": 9.993022675663437e-05,
      "loss": 2.7413,
      "step": 208
    },
    {
      "epoch": 0.06710873212431094,
      "grad_norm": 0.7314406037330627,
      "learning_rate": 9.992453469259685e-05,
      "loss": 2.7983,
      "step": 210
    },
    {
      "epoch": 0.06774786290644723,
      "grad_norm": 0.7307546734809875,
      "learning_rate": 9.991861963938342e-05,
      "loss": 2.8026,
      "step": 212
    },
    {
      "epoch": 0.06838699368858353,
      "grad_norm": 0.6367102861404419,
      "learning_rate": 9.991248162341384e-05,
      "loss": 2.7424,
      "step": 214
    },
    {
      "epoch": 0.06902612447071982,
      "grad_norm": 0.8630378246307373,
      "learning_rate": 9.99061206721037e-05,
      "loss": 2.7395,
      "step": 216
    },
    {
      "epoch": 0.06966525525285612,
      "grad_norm": 0.7586290240287781,
      "learning_rate": 9.989953681386433e-05,
      "loss": 2.7624,
      "step": 218
    },
    {
      "epoch": 0.07030438603499241,
      "grad_norm": 0.7091168761253357,
      "learning_rate": 9.989273007810271e-05,
      "loss": 2.7719,
      "step": 220
    },
    {
      "epoch": 0.07094351681712871,
      "grad_norm": 0.684183657169342,
      "learning_rate": 9.98857004952213e-05,
      "loss": 2.7806,
      "step": 222
    },
    {
      "epoch": 0.071582647599265,
      "grad_norm": 0.920498788356781,
      "learning_rate": 9.987844809661791e-05,
      "loss": 2.7626,
      "step": 224
    },
    {
      "epoch": 0.0722217783814013,
      "grad_norm": 0.730060875415802,
      "learning_rate": 9.987097291468552e-05,
      "loss": 2.8107,
      "step": 226
    },
    {
      "epoch": 0.07286090916353759,
      "grad_norm": 0.8606828451156616,
      "learning_rate": 9.986327498281227e-05,
      "loss": 2.7814,
      "step": 228
    },
    {
      "epoch": 0.07350003994567389,
      "grad_norm": 0.8068298101425171,
      "learning_rate": 9.985535433538113e-05,
      "loss": 2.7775,
      "step": 230
    },
    {
      "epoch": 0.07413917072781018,
      "grad_norm": 0.6887542009353638,
      "learning_rate": 9.984721100776989e-05,
      "loss": 2.784,
      "step": 232
    },
    {
      "epoch": 0.07477830150994648,
      "grad_norm": 0.84773850440979,
      "learning_rate": 9.98388450363509e-05,
      "loss": 2.7333,
      "step": 234
    },
    {
      "epoch": 0.07541743229208277,
      "grad_norm": 0.7914923429489136,
      "learning_rate": 9.9830256458491e-05,
      "loss": 2.7363,
      "step": 236
    },
    {
      "epoch": 0.07605656307421906,
      "grad_norm": 0.8284217715263367,
      "learning_rate": 9.982144531255127e-05,
      "loss": 2.7389,
      "step": 238
    },
    {
      "epoch": 0.07669569385635536,
      "grad_norm": 0.7706480622291565,
      "learning_rate": 9.981241163788694e-05,
      "loss": 2.7377,
      "step": 240
    },
    {
      "epoch": 0.07733482463849164,
      "grad_norm": 0.6147120594978333,
      "learning_rate": 9.980315547484711e-05,
      "loss": 2.7862,
      "step": 242
    },
    {
      "epoch": 0.07797395542062795,
      "grad_norm": 0.6364494562149048,
      "learning_rate": 9.979367686477469e-05,
      "loss": 2.762,
      "step": 244
    },
    {
      "epoch": 0.07861308620276423,
      "grad_norm": 0.6944818496704102,
      "learning_rate": 9.978397585000611e-05,
      "loss": 2.7624,
      "step": 246
    },
    {
      "epoch": 0.07925221698490054,
      "grad_norm": 1.2648204565048218,
      "learning_rate": 9.977405247387119e-05,
      "loss": 2.7544,
      "step": 248
    },
    {
      "epoch": 0.07989134776703682,
      "grad_norm": 1.0054659843444824,
      "learning_rate": 9.976390678069295e-05,
      "loss": 2.7523,
      "step": 250
    },
    {
      "epoch": 0.08053047854917313,
      "grad_norm": 0.715492308139801,
      "learning_rate": 9.975353881578738e-05,
      "loss": 2.7341,
      "step": 252
    },
    {
      "epoch": 0.08116960933130941,
      "grad_norm": 0.7963582277297974,
      "learning_rate": 9.974294862546325e-05,
      "loss": 2.7484,
      "step": 254
    },
    {
      "epoch": 0.08180874011344572,
      "grad_norm": 0.7069251537322998,
      "learning_rate": 9.97321362570219e-05,
      "loss": 2.7719,
      "step": 256
    },
    {
      "epoch": 0.082447870895582,
      "grad_norm": 0.5716209411621094,
      "learning_rate": 9.972110175875706e-05,
      "loss": 2.8079,
      "step": 258
    },
    {
      "epoch": 0.0830870016777183,
      "grad_norm": 0.65562903881073,
      "learning_rate": 9.970984517995456e-05,
      "loss": 2.7642,
      "step": 260
    },
    {
      "epoch": 0.0837261324598546,
      "grad_norm": 0.647085964679718,
      "learning_rate": 9.969836657089225e-05,
      "loss": 2.7139,
      "step": 262
    },
    {
      "epoch": 0.0843652632419909,
      "grad_norm": 0.6401609778404236,
      "learning_rate": 9.968666598283955e-05,
      "loss": 2.7278,
      "step": 264
    },
    {
      "epoch": 0.08500439402412718,
      "grad_norm": 0.5514021515846252,
      "learning_rate": 9.967474346805746e-05,
      "loss": 2.7332,
      "step": 266
    },
    {
      "epoch": 0.08564352480626349,
      "grad_norm": 0.5908826589584351,
      "learning_rate": 9.96625990797982e-05,
      "loss": 2.741,
      "step": 268
    },
    {
      "epoch": 0.08628265558839977,
      "grad_norm": 0.5510653853416443,
      "learning_rate": 9.965023287230497e-05,
      "loss": 2.7025,
      "step": 270
    },
    {
      "epoch": 0.08692178637053607,
      "grad_norm": 0.5656317472457886,
      "learning_rate": 9.963764490081176e-05,
      "loss": 2.7184,
      "step": 272
    },
    {
      "epoch": 0.08756091715267236,
      "grad_norm": 0.5132441520690918,
      "learning_rate": 9.962483522154302e-05,
      "loss": 2.7632,
      "step": 274
    },
    {
      "epoch": 0.08820004793480866,
      "grad_norm": 0.6730588674545288,
      "learning_rate": 9.961180389171352e-05,
      "loss": 2.7705,
      "step": 276
    },
    {
      "epoch": 0.08883917871694495,
      "grad_norm": 0.5657472610473633,
      "learning_rate": 9.959855096952804e-05,
      "loss": 2.7191,
      "step": 278
    },
    {
      "epoch": 0.08947830949908125,
      "grad_norm": 0.8265955448150635,
      "learning_rate": 9.958507651418106e-05,
      "loss": 2.7718,
      "step": 280
    },
    {
      "epoch": 0.09011744028121754,
      "grad_norm": 0.8996996879577637,
      "learning_rate": 9.957138058585658e-05,
      "loss": 2.7124,
      "step": 282
    },
    {
      "epoch": 0.09075657106335384,
      "grad_norm": 0.6458889842033386,
      "learning_rate": 9.955746324572781e-05,
      "loss": 2.7403,
      "step": 284
    },
    {
      "epoch": 0.09139570184549013,
      "grad_norm": 0.7175470590591431,
      "learning_rate": 9.954332455595689e-05,
      "loss": 2.7188,
      "step": 286
    },
    {
      "epoch": 0.09203483262762643,
      "grad_norm": 0.6640183329582214,
      "learning_rate": 9.952896457969463e-05,
      "loss": 2.7223,
      "step": 288
    },
    {
      "epoch": 0.09267396340976272,
      "grad_norm": 0.6551202535629272,
      "learning_rate": 9.951438338108022e-05,
      "loss": 2.7189,
      "step": 290
    },
    {
      "epoch": 0.09331309419189902,
      "grad_norm": 0.6980673670768738,
      "learning_rate": 9.949958102524093e-05,
      "loss": 2.7183,
      "step": 292
    },
    {
      "epoch": 0.09395222497403531,
      "grad_norm": 0.5926324129104614,
      "learning_rate": 9.948455757829187e-05,
      "loss": 2.7476,
      "step": 294
    },
    {
      "epoch": 0.09459135575617161,
      "grad_norm": 0.5434746742248535,
      "learning_rate": 9.946931310733565e-05,
      "loss": 2.7368,
      "step": 296
    },
    {
      "epoch": 0.0952304865383079,
      "grad_norm": 0.6466372609138489,
      "learning_rate": 9.945384768046206e-05,
      "loss": 2.7307,
      "step": 298
    },
    {
      "epoch": 0.09586961732044419,
      "grad_norm": 0.6376985311508179,
      "learning_rate": 9.943816136674782e-05,
      "loss": 2.7239,
      "step": 300
    }
  ],
  "logging_steps": 2,
  "max_steps": 3130,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.377550336196608e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}