{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004651162790697674,
      "grad_norm": 19.566913604736328,
      "learning_rate": 0.0,
      "loss": 0.842,
      "mean_token_accuracy": 0.8234314918518066,
      "step": 1
    },
    {
      "epoch": 0.009302325581395349,
      "grad_norm": 21.503646850585938,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 0.8773,
      "mean_token_accuracy": 0.8220880627632141,
      "step": 2
    },
    {
      "epoch": 0.013953488372093023,
      "grad_norm": 19.072912216186523,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.8522,
      "mean_token_accuracy": 0.832254946231842,
      "step": 3
    },
    {
      "epoch": 0.018604651162790697,
      "grad_norm": 18.07330322265625,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.8166,
      "mean_token_accuracy": 0.8297423720359802,
      "step": 4
    },
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 21.246156692504883,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.9312,
      "mean_token_accuracy": 0.8097259998321533,
      "step": 5
    },
    {
      "epoch": 0.027906976744186046,
      "grad_norm": 18.991504669189453,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.7816,
      "mean_token_accuracy": 0.8285066485404968,
      "step": 6
    },
    {
      "epoch": 0.03255813953488372,
      "grad_norm": 16.567394256591797,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.8123,
      "mean_token_accuracy": 0.8268486261367798,
      "step": 7
    },
    {
      "epoch": 0.037209302325581395,
      "grad_norm": 10.308907508850098,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.6385,
      "mean_token_accuracy": 0.8507297039031982,
      "step": 8
    },
    {
      "epoch": 0.04186046511627907,
      "grad_norm": 8.591865539550781,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.5651,
      "mean_token_accuracy": 0.863410234451294,
      "step": 9
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 9.019761085510254,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.4933,
      "mean_token_accuracy": 0.8713976144790649,
      "step": 10
    },
    {
      "epoch": 0.05116279069767442,
      "grad_norm": 9.10396671295166,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.4211,
      "mean_token_accuracy": 0.8915254473686218,
      "step": 11
    },
    {
      "epoch": 0.05581395348837209,
      "grad_norm": 7.293844223022461,
      "learning_rate": 5e-06,
      "loss": 0.4411,
      "mean_token_accuracy": 0.8812285661697388,
      "step": 12
    },
    {
      "epoch": 0.06046511627906977,
      "grad_norm": 4.323971271514893,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.4205,
      "mean_token_accuracy": 0.8759526610374451,
      "step": 13
    },
    {
      "epoch": 0.06511627906976744,
      "grad_norm": 5.9293413162231445,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.364,
      "mean_token_accuracy": 0.8886061906814575,
      "step": 14
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 3.369750738143921,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.3435,
      "mean_token_accuracy": 0.8966382145881653,
      "step": 15
    },
    {
      "epoch": 0.07441860465116279,
      "grad_norm": 3.6587915420532227,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.3801,
      "mean_token_accuracy": 0.8860718607902527,
      "step": 16
    },
    {
      "epoch": 0.07906976744186046,
      "grad_norm": 3.0630006790161133,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.333,
      "mean_token_accuracy": 0.9021540880203247,
      "step": 17
    },
    {
      "epoch": 0.08372093023255814,
      "grad_norm": 3.0884928703308105,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.3774,
      "mean_token_accuracy": 0.8831896185874939,
      "step": 18
    },
    {
      "epoch": 0.08837209302325581,
      "grad_norm": 3.343445301055908,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.3834,
      "mean_token_accuracy": 0.884019136428833,
      "step": 19
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 2.862471580505371,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.3523,
      "mean_token_accuracy": 0.8919129371643066,
      "step": 20
    },
    {
      "epoch": 0.09767441860465116,
      "grad_norm": 3.1519503593444824,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.3994,
      "mean_token_accuracy": 0.8742711544036865,
      "step": 21
    },
    {
      "epoch": 0.10232558139534884,
      "grad_norm": 3.08125376701355,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.3518,
      "mean_token_accuracy": 0.8841822147369385,
      "step": 22
    },
    {
      "epoch": 0.10697674418604651,
      "grad_norm": 3.0018293857574463,
      "learning_rate": 1e-05,
      "loss": 0.345,
      "mean_token_accuracy": 0.8950249552726746,
      "step": 23
    },
    {
      "epoch": 0.11162790697674418,
      "grad_norm": 3.267643451690674,
      "learning_rate": 9.999403846557509e-06,
      "loss": 0.3704,
      "mean_token_accuracy": 0.8792986273765564,
      "step": 24
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 3.051391839981079,
      "learning_rate": 9.99761554418511e-06,
      "loss": 0.3331,
      "mean_token_accuracy": 0.896356999874115,
      "step": 25
    },
    {
      "epoch": 0.12093023255813953,
      "grad_norm": 3.030799627304077,
      "learning_rate": 9.99463556670619e-06,
      "loss": 0.3339,
      "mean_token_accuracy": 0.9024479985237122,
      "step": 26
    },
    {
      "epoch": 0.12558139534883722,
      "grad_norm": 3.1301109790802,
      "learning_rate": 9.990464703686895e-06,
      "loss": 0.3652,
      "mean_token_accuracy": 0.8962038159370422,
      "step": 27
    },
    {
      "epoch": 0.13023255813953488,
      "grad_norm": 3.1041147708892822,
      "learning_rate": 9.985104060226937e-06,
      "loss": 0.3538,
      "mean_token_accuracy": 0.8938086032867432,
      "step": 28
    },
    {
      "epoch": 0.13488372093023257,
      "grad_norm": 3.011711835861206,
      "learning_rate": 9.978555056666784e-06,
      "loss": 0.3763,
      "mean_token_accuracy": 0.878600537776947,
      "step": 29
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 3.104379653930664,
      "learning_rate": 9.97081942821133e-06,
      "loss": 0.3706,
      "mean_token_accuracy": 0.8877567648887634,
      "step": 30
    },
    {
      "epoch": 0.14418604651162792,
      "grad_norm": 3.3601248264312744,
      "learning_rate": 9.961899224470146e-06,
      "loss": 0.3956,
      "mean_token_accuracy": 0.8821022510528564,
      "step": 31
    },
    {
      "epoch": 0.14883720930232558,
      "grad_norm": 3.0410044193267822,
      "learning_rate": 9.95179680891442e-06,
      "loss": 0.318,
      "mean_token_accuracy": 0.9060280323028564,
      "step": 32
    },
    {
      "epoch": 0.15348837209302327,
      "grad_norm": 3.7731399536132812,
      "learning_rate": 9.940514858250736e-06,
      "loss": 0.3565,
      "mean_token_accuracy": 0.8926541209220886,
      "step": 33
    },
    {
      "epoch": 0.15813953488372093,
      "grad_norm": 2.947474241256714,
      "learning_rate": 9.928056361711854e-06,
      "loss": 0.3035,
      "mean_token_accuracy": 0.9058524370193481,
      "step": 34
    },
    {
      "epoch": 0.16279069767441862,
      "grad_norm": 3.0079967975616455,
      "learning_rate": 9.914424620264714e-06,
      "loss": 0.3581,
      "mean_token_accuracy": 0.8900263905525208,
      "step": 35
    },
    {
      "epoch": 0.16744186046511628,
      "grad_norm": 3.0129306316375732,
      "learning_rate": 9.899623245735798e-06,
      "loss": 0.3283,
      "mean_token_accuracy": 0.8980950713157654,
      "step": 36
    },
    {
      "epoch": 0.17209302325581396,
      "grad_norm": 3.025678873062134,
      "learning_rate": 9.883656159854166e-06,
      "loss": 0.3179,
      "mean_token_accuracy": 0.9024977087974548,
      "step": 37
    },
    {
      "epoch": 0.17674418604651163,
      "grad_norm": 3.019639253616333,
      "learning_rate": 9.866527593212355e-06,
      "loss": 0.3314,
      "mean_token_accuracy": 0.899016261100769,
      "step": 38
    },
    {
      "epoch": 0.1813953488372093,
      "grad_norm": 2.9794199466705322,
      "learning_rate": 9.848242084145462e-06,
      "loss": 0.3199,
      "mean_token_accuracy": 0.9022731184959412,
      "step": 39
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 2.8634836673736572,
      "learning_rate": 9.82880447752868e-06,
      "loss": 0.3377,
      "mean_token_accuracy": 0.8929729461669922,
      "step": 40
    },
    {
      "epoch": 0.19069767441860466,
      "grad_norm": 3.023061990737915,
      "learning_rate": 9.808219923493606e-06,
      "loss": 0.3331,
      "mean_token_accuracy": 0.8968125581741333,
      "step": 41
    },
    {
      "epoch": 0.19534883720930232,
      "grad_norm": 3.201726198196411,
      "learning_rate": 9.786493876063685e-06,
      "loss": 0.3291,
      "mean_token_accuracy": 0.8950858116149902,
      "step": 42
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.0741653442382812,
      "learning_rate": 9.763632091709125e-06,
      "loss": 0.31,
      "mean_token_accuracy": 0.8963869214057922,
      "step": 43
    },
    {
      "epoch": 0.20465116279069767,
      "grad_norm": 2.884732723236084,
      "learning_rate": 9.739640627821678e-06,
      "loss": 0.3381,
      "mean_token_accuracy": 0.8979052901268005,
      "step": 44
    },
    {
      "epoch": 0.20930232558139536,
      "grad_norm": 3.245725631713867,
      "learning_rate": 9.714525841109697e-06,
      "loss": 0.2951,
      "mean_token_accuracy": 0.9035796523094177,
      "step": 45
    },
    {
      "epoch": 0.21395348837209302,
      "grad_norm": 3.057401180267334,
      "learning_rate": 9.68829438591387e-06,
      "loss": 0.3034,
      "mean_token_accuracy": 0.9002149701118469,
      "step": 46
    },
    {
      "epoch": 0.2186046511627907,
      "grad_norm": 3.0023374557495117,
      "learning_rate": 9.660953212444116e-06,
      "loss": 0.3138,
      "mean_token_accuracy": 0.8987898826599121,
      "step": 47
    },
    {
      "epoch": 0.22325581395348837,
      "grad_norm": 2.846851110458374,
      "learning_rate": 9.632509564938073e-06,
      "loss": 0.3213,
      "mean_token_accuracy": 0.8954131603240967,
      "step": 48
    },
    {
      "epoch": 0.22790697674418606,
      "grad_norm": 2.9974007606506348,
      "learning_rate": 9.60297097974169e-06,
      "loss": 0.3149,
      "mean_token_accuracy": 0.8978151082992554,
      "step": 49
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 2.860105037689209,
      "learning_rate": 9.572345283312407e-06,
      "loss": 0.3152,
      "mean_token_accuracy": 0.8984004259109497,
      "step": 50
    },
    {
      "epoch": 0.2372093023255814,
      "grad_norm": 3.178861141204834,
      "learning_rate": 9.540640590145496e-06,
      "loss": 0.3362,
      "mean_token_accuracy": 0.8821947574615479,
      "step": 51
    },
    {
      "epoch": 0.24186046511627907,
      "grad_norm": 2.8864493370056152,
      "learning_rate": 9.507865300624057e-06,
      "loss": 0.338,
      "mean_token_accuracy": 0.8844265937805176,
      "step": 52
    },
    {
      "epoch": 0.24651162790697675,
      "grad_norm": 2.9779324531555176,
      "learning_rate": 9.474028098793277e-06,
      "loss": 0.3133,
      "mean_token_accuracy": 0.8958209753036499,
      "step": 53
    },
    {
      "epoch": 0.25116279069767444,
      "grad_norm": 2.81357479095459,
      "learning_rate": 9.439137950059539e-06,
      "loss": 0.3293,
      "mean_token_accuracy": 0.8908188343048096,
      "step": 54
    },
    {
      "epoch": 0.2558139534883721,
      "grad_norm": 2.7432124614715576,
      "learning_rate": 9.403204098814965e-06,
      "loss": 0.3289,
      "mean_token_accuracy": 0.8898541927337646,
      "step": 55
    },
    {
      "epoch": 0.26046511627906976,
      "grad_norm": 2.78106689453125,
      "learning_rate": 9.366236065988053e-06,
      "loss": 0.3222,
      "mean_token_accuracy": 0.8953770995140076,
      "step": 56
    },
    {
      "epoch": 0.2651162790697674,
      "grad_norm": 2.4186606407165527,
      "learning_rate": 9.32824364652104e-06,
      "loss": 0.2825,
      "mean_token_accuracy": 0.908851146697998,
      "step": 57
    },
    {
      "epoch": 0.26976744186046514,
      "grad_norm": 2.4946393966674805,
      "learning_rate": 9.289236906774663e-06,
      "loss": 0.3115,
      "mean_token_accuracy": 0.8956378698348999,
      "step": 58
    },
    {
      "epoch": 0.2744186046511628,
      "grad_norm": 2.7663369178771973,
      "learning_rate": 9.249226181861e-06,
      "loss": 0.2915,
      "mean_token_accuracy": 0.9062834978103638,
      "step": 59
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 2.6216726303100586,
      "learning_rate": 9.208222072905113e-06,
      "loss": 0.3069,
      "mean_token_accuracy": 0.8927038908004761,
      "step": 60
    },
    {
      "epoch": 0.2837209302325581,
      "grad_norm": 2.7621278762817383,
      "learning_rate": 9.166235444236209e-06,
      "loss": 0.3425,
      "mean_token_accuracy": 0.8820893168449402,
      "step": 61
    },
    {
      "epoch": 0.28837209302325584,
      "grad_norm": 2.748720407485962,
      "learning_rate": 9.123277420509053e-06,
      "loss": 0.3364,
      "mean_token_accuracy": 0.8870337605476379,
      "step": 62
    },
    {
      "epoch": 0.2930232558139535,
      "grad_norm": 2.5530190467834473,
      "learning_rate": 9.079359383756411e-06,
      "loss": 0.3133,
      "mean_token_accuracy": 0.8994490504264832,
      "step": 63
    },
    {
      "epoch": 0.29767441860465116,
      "grad_norm": 2.48974609375,
      "learning_rate": 9.034492970373305e-06,
      "loss": 0.3035,
      "mean_token_accuracy": 0.8979023098945618,
      "step": 64
    },
    {
      "epoch": 0.3023255813953488,
      "grad_norm": 2.6978116035461426,
      "learning_rate": 8.988690068033864e-06,
      "loss": 0.3339,
      "mean_token_accuracy": 0.8893972635269165,
      "step": 65
    },
    {
      "epoch": 0.30697674418604654,
      "grad_norm": 2.308871030807495,
      "learning_rate": 8.941962812541604e-06,
      "loss": 0.3016,
      "mean_token_accuracy": 0.8937329649925232,
      "step": 66
    },
    {
      "epoch": 0.3116279069767442,
      "grad_norm": 2.511657953262329,
      "learning_rate": 8.894323584613951e-06,
      "loss": 0.3194,
      "mean_token_accuracy": 0.889618456363678,
      "step": 67
    },
    {
      "epoch": 0.31627906976744186,
      "grad_norm": 2.389920949935913,
      "learning_rate": 8.845785006601898e-06,
      "loss": 0.281,
      "mean_token_accuracy": 0.9037378430366516,
      "step": 68
    },
    {
      "epoch": 0.3209302325581395,
      "grad_norm": 2.5016298294067383,
      "learning_rate": 8.796359939145614e-06,
      "loss": 0.3076,
      "mean_token_accuracy": 0.8938754200935364,
      "step": 69
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 2.682018518447876,
      "learning_rate": 8.74606147776692e-06,
      "loss": 0.3102,
      "mean_token_accuracy": 0.8926771879196167,
      "step": 70
    },
    {
      "epoch": 0.3302325581395349,
      "grad_norm": 2.5323574542999268,
      "learning_rate": 8.694902949399555e-06,
      "loss": 0.3095,
      "mean_token_accuracy": 0.8985507488250732,
      "step": 71
    },
    {
      "epoch": 0.33488372093023255,
      "grad_norm": 2.5909910202026367,
      "learning_rate": 8.642897908858096e-06,
      "loss": 0.3112,
      "mean_token_accuracy": 0.8959133625030518,
      "step": 72
    },
    {
      "epoch": 0.3395348837209302,
      "grad_norm": 2.635803461074829,
      "learning_rate": 8.590060135246516e-06,
      "loss": 0.3358,
      "mean_token_accuracy": 0.8812984228134155,
      "step": 73
    },
    {
      "epoch": 0.34418604651162793,
      "grad_norm": 2.2963192462921143,
      "learning_rate": 8.53640362830732e-06,
      "loss": 0.2899,
      "mean_token_accuracy": 0.9005515575408936,
      "step": 74
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 2.634748935699463,
      "learning_rate": 8.481942604712209e-06,
      "loss": 0.3187,
      "mean_token_accuracy": 0.891135573387146,
      "step": 75
    },
    {
      "epoch": 0.35348837209302325,
      "grad_norm": 2.4233202934265137,
      "learning_rate": 8.426691494295269e-06,
      "loss": 0.2874,
      "mean_token_accuracy": 0.9031267762184143,
      "step": 76
    },
    {
      "epoch": 0.3581395348837209,
      "grad_norm": 2.462113618850708,
      "learning_rate": 8.370664936229688e-06,
      "loss": 0.314,
      "mean_token_accuracy": 0.8929266929626465,
      "step": 77
    },
    {
      "epoch": 0.3627906976744186,
      "grad_norm": 2.456052780151367,
      "learning_rate": 8.313877775149009e-06,
      "loss": 0.2742,
      "mean_token_accuracy": 0.9058647155761719,
      "step": 78
    },
    {
      "epoch": 0.3674418604651163,
      "grad_norm": 2.792787790298462,
      "learning_rate": 8.256345057213925e-06,
      "loss": 0.3157,
      "mean_token_accuracy": 0.8885141015052795,
      "step": 79
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 2.2764811515808105,
      "learning_rate": 8.198082026125707e-06,
      "loss": 0.3285,
      "mean_token_accuracy": 0.8876305222511292,
      "step": 80
    },
    {
      "epoch": 0.3767441860465116,
      "grad_norm": 2.815459966659546,
      "learning_rate": 8.139104119087265e-06,
      "loss": 0.2839,
      "mean_token_accuracy": 0.9014216065406799,
      "step": 81
    },
    {
      "epoch": 0.3813953488372093,
      "grad_norm": 2.5127663612365723,
      "learning_rate": 8.07942696271296e-06,
      "loss": 0.2825,
      "mean_token_accuracy": 0.9009503126144409,
      "step": 82
    },
    {
      "epoch": 0.386046511627907,
      "grad_norm": 2.3554956912994385,
      "learning_rate": 8.019066368888222e-06,
      "loss": 0.2873,
      "mean_token_accuracy": 0.902760922908783,
      "step": 83
    },
    {
      "epoch": 0.39069767441860465,
      "grad_norm": 2.4911487102508545,
      "learning_rate": 7.958038330580067e-06,
      "loss": 0.3324,
      "mean_token_accuracy": 0.883284866809845,
      "step": 84
    },
    {
      "epoch": 0.3953488372093023,
      "grad_norm": 2.3755667209625244,
      "learning_rate": 7.89635901759967e-06,
      "loss": 0.3,
      "mean_token_accuracy": 0.8920915126800537,
      "step": 85
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.7483432292938232,
      "learning_rate": 7.834044772318033e-06,
      "loss": 0.3282,
      "mean_token_accuracy": 0.8910906910896301,
      "step": 86
    },
    {
      "epoch": 0.4046511627906977,
      "grad_norm": 2.4823901653289795,
      "learning_rate": 7.77111210533597e-06,
      "loss": 0.3,
      "mean_token_accuracy": 0.8902961015701294,
      "step": 87
    },
    {
      "epoch": 0.40930232558139534,
      "grad_norm": 2.6033935546875,
      "learning_rate": 7.707577691109519e-06,
      "loss": 0.3548,
      "mean_token_accuracy": 0.880534827709198,
      "step": 88
    },
    {
      "epoch": 0.413953488372093,
      "grad_norm": 2.27488374710083,
      "learning_rate": 7.6434583635319e-06,
      "loss": 0.3022,
      "mean_token_accuracy": 0.9012537002563477,
      "step": 89
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 2.287916660308838,
      "learning_rate": 7.578771111473276e-06,
      "loss": 0.2578,
      "mean_token_accuracy": 0.9131473898887634,
      "step": 90
    },
    {
      "epoch": 0.4232558139534884,
      "grad_norm": 2.3548431396484375,
      "learning_rate": 7.513533074279427e-06,
      "loss": 0.2677,
      "mean_token_accuracy": 0.9082207083702087,
      "step": 91
    },
    {
      "epoch": 0.42790697674418604,
      "grad_norm": 2.484837532043457,
      "learning_rate": 7.4477615372305545e-06,
      "loss": 0.3218,
      "mean_token_accuracy": 0.8943215012550354,
      "step": 92
    },
    {
      "epoch": 0.4325581395348837,
      "grad_norm": 2.419360637664795,
      "learning_rate": 7.3814739269614265e-06,
      "loss": 0.2945,
      "mean_token_accuracy": 0.9002562165260315,
      "step": 93
    },
    {
      "epoch": 0.4372093023255814,
      "grad_norm": 2.4345784187316895,
      "learning_rate": 7.314687806844067e-06,
      "loss": 0.3091,
      "mean_token_accuracy": 0.8968407511711121,
      "step": 94
    },
    {
      "epoch": 0.4418604651162791,
      "grad_norm": 2.479210376739502,
      "learning_rate": 7.247420872334221e-06,
      "loss": 0.3019,
      "mean_token_accuracy": 0.8969621658325195,
      "step": 95
    },
    {
      "epoch": 0.44651162790697674,
      "grad_norm": 2.2260143756866455,
      "learning_rate": 7.179690946282808e-06,
      "loss": 0.2833,
      "mean_token_accuracy": 0.9025951027870178,
      "step": 96
    },
    {
      "epoch": 0.4511627906976744,
      "grad_norm": 2.2926838397979736,
      "learning_rate": 7.111515974213639e-06,
      "loss": 0.2491,
      "mean_token_accuracy": 0.9109234809875488,
      "step": 97
    },
    {
      "epoch": 0.4558139534883721,
      "grad_norm": 2.386190414428711,
      "learning_rate": 7.042914019568621e-06,
      "loss": 0.3028,
      "mean_token_accuracy": 0.8939149379730225,
      "step": 98
    },
    {
      "epoch": 0.4604651162790698,
      "grad_norm": 2.2225522994995117,
      "learning_rate": 6.973903258921719e-06,
      "loss": 0.2564,
      "mean_token_accuracy": 0.909423291683197,
      "step": 99
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 2.3535642623901367,
      "learning_rate": 6.904501977162949e-06,
      "loss": 0.3274,
      "mean_token_accuracy": 0.88499915599823,
      "step": 100
    },
    {
      "epoch": 0.4697674418604651,
      "grad_norm": 2.362877607345581,
      "learning_rate": 6.834728562653659e-06,
      "loss": 0.309,
      "mean_token_accuracy": 0.8906528353691101,
      "step": 101
    },
    {
      "epoch": 0.4744186046511628,
      "grad_norm": 2.4089605808258057,
      "learning_rate": 6.764601502354403e-06,
      "loss": 0.3059,
      "mean_token_accuracy": 0.8971619009971619,
      "step": 102
    },
    {
      "epoch": 0.4790697674418605,
      "grad_norm": 2.2496674060821533,
      "learning_rate": 6.6941393769266995e-06,
      "loss": 0.2987,
      "mean_token_accuracy": 0.8985577821731567,
      "step": 103
    },
    {
      "epoch": 0.48372093023255813,
      "grad_norm": 2.0976436138153076,
      "learning_rate": 6.6233608558099405e-06,
      "loss": 0.2774,
      "mean_token_accuracy": 0.9051709771156311,
      "step": 104
    },
    {
      "epoch": 0.4883720930232558,
      "grad_norm": 2.2868094444274902,
      "learning_rate": 6.552284692274803e-06,
      "loss": 0.3088,
      "mean_token_accuracy": 0.8942136764526367,
      "step": 105
    },
    {
      "epoch": 0.4930232558139535,
      "grad_norm": 2.3689169883728027,
      "learning_rate": 6.48092971845443e-06,
      "loss": 0.2793,
      "mean_token_accuracy": 0.9030190706253052,
      "step": 106
    },
    {
      "epoch": 0.49767441860465117,
      "grad_norm": 2.390408515930176,
      "learning_rate": 6.409314840354724e-06,
      "loss": 0.3383,
      "mean_token_accuracy": 0.8868411779403687,
      "step": 107
    },
    {
      "epoch": 0.5023255813953489,
      "grad_norm": 2.522303342819214,
      "learning_rate": 6.337459032845068e-06,
      "loss": 0.3146,
      "mean_token_accuracy": 0.8873773217201233,
      "step": 108
    },
    {
      "epoch": 0.5069767441860465,
      "grad_norm": 2.418745279312134,
      "learning_rate": 6.2653813346308e-06,
      "loss": 0.2738,
      "mean_token_accuracy": 0.9050701260566711,
      "step": 109
    },
    {
      "epoch": 0.5116279069767442,
      "grad_norm": 2.2483389377593994,
      "learning_rate": 6.193100843208772e-06,
      "loss": 0.282,
      "mean_token_accuracy": 0.8973640203475952,
      "step": 110
    },
    {
      "epoch": 0.5162790697674419,
      "grad_norm": 2.3183794021606445,
      "learning_rate": 6.120636709807334e-06,
      "loss": 0.3109,
      "mean_token_accuracy": 0.8886767029762268,
      "step": 111
    },
    {
      "epoch": 0.5209302325581395,
      "grad_norm": 2.3985159397125244,
      "learning_rate": 6.048008134312078e-06,
      "loss": 0.2891,
      "mean_token_accuracy": 0.9019830226898193,
      "step": 112
    },
    {
      "epoch": 0.5255813953488372,
      "grad_norm": 2.401186943054199,
      "learning_rate": 5.975234360178698e-06,
      "loss": 0.3263,
      "mean_token_accuracy": 0.8926165103912354,
      "step": 113
    },
    {
      "epoch": 0.5302325581395348,
      "grad_norm": 2.2257766723632812,
      "learning_rate": 5.902334669334287e-06,
      "loss": 0.2991,
      "mean_token_accuracy": 0.9015018939971924,
      "step": 114
    },
    {
      "epoch": 0.5348837209302325,
      "grad_norm": 2.4873902797698975,
      "learning_rate": 5.829328377068476e-06,
      "loss": 0.2952,
      "mean_token_accuracy": 0.8938588500022888,
      "step": 115
    },
    {
      "epoch": 0.5395348837209303,
      "grad_norm": 2.5127971172332764,
      "learning_rate": 5.756234826915686e-06,
      "loss": 0.3015,
      "mean_token_accuracy": 0.8990825414657593,
      "step": 116
    },
    {
      "epoch": 0.5441860465116279,
      "grad_norm": 2.7055206298828125,
      "learning_rate": 5.683073385529938e-06,
      "loss": 0.3148,
      "mean_token_accuracy": 0.8902867436408997,
      "step": 117
    },
    {
      "epoch": 0.5488372093023256,
      "grad_norm": 2.184539794921875,
      "learning_rate": 5.60986343755352e-06,
      "loss": 0.2628,
      "mean_token_accuracy": 0.907613217830658,
      "step": 118
    },
    {
      "epoch": 0.5534883720930233,
      "grad_norm": 2.460629463195801,
      "learning_rate": 5.536624380480878e-06,
      "loss": 0.2526,
      "mean_token_accuracy": 0.9117704629898071,
      "step": 119
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 2.3159563541412354,
      "learning_rate": 5.4633756195191235e-06,
      "loss": 0.261,
      "mean_token_accuracy": 0.90885990858078,
      "step": 120
    },
    {
      "epoch": 0.5627906976744186,
      "grad_norm": 2.0507678985595703,
      "learning_rate": 5.390136562446482e-06,
      "loss": 0.2262,
      "mean_token_accuracy": 0.9185211062431335,
      "step": 121
    },
    {
      "epoch": 0.5674418604651162,
      "grad_norm": 2.456918954849243,
      "learning_rate": 5.316926614470063e-06,
      "loss": 0.3052,
      "mean_token_accuracy": 0.8933428525924683,
      "step": 122
    },
    {
      "epoch": 0.5720930232558139,
      "grad_norm": 2.683582067489624,
      "learning_rate": 5.2437651730843165e-06,
      "loss": 0.3406,
      "mean_token_accuracy": 0.8779610991477966,
      "step": 123
    },
    {
      "epoch": 0.5767441860465117,
      "grad_norm": 2.5005733966827393,
      "learning_rate": 5.170671622931527e-06,
      "loss": 0.3104,
      "mean_token_accuracy": 0.8913931250572205,
      "step": 124
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 2.073763370513916,
      "learning_rate": 5.097665330665714e-06,
      "loss": 0.2393,
      "mean_token_accuracy": 0.9153239727020264,
      "step": 125
    },
    {
      "epoch": 0.586046511627907,
      "grad_norm": 2.638117551803589,
      "learning_rate": 5.024765639821305e-06,
      "loss": 0.321,
      "mean_token_accuracy": 0.8932949900627136,
      "step": 126
    },
    {
      "epoch": 0.5906976744186047,
      "grad_norm": 2.077889919281006,
      "learning_rate": 4.951991865687923e-06,
      "loss": 0.2523,
      "mean_token_accuracy": 0.916557788848877,
      "step": 127
    },
    {
      "epoch": 0.5953488372093023,
      "grad_norm": 2.4227733612060547,
      "learning_rate": 4.879363290192667e-06,
      "loss": 0.2931,
      "mean_token_accuracy": 0.9004586338996887,
      "step": 128
    },
    {
      "epoch": 0.6,
      "grad_norm": 2.7623236179351807,
      "learning_rate": 4.806899156791231e-06,
      "loss": 0.359,
      "mean_token_accuracy": 0.8809077143669128,
      "step": 129
    },
    {
      "epoch": 0.6046511627906976,
      "grad_norm": 2.4066247940063477,
      "learning_rate": 4.734618665369202e-06,
      "loss": 0.2844,
      "mean_token_accuracy": 0.8950888514518738,
      "step": 130
    },
    {
      "epoch": 0.6093023255813953,
      "grad_norm": 2.34375,
      "learning_rate": 4.662540967154934e-06,
      "loss": 0.2673,
      "mean_token_accuracy": 0.9051871299743652,
      "step": 131
    },
    {
      "epoch": 0.6139534883720931,
      "grad_norm": 2.1489133834838867,
      "learning_rate": 4.5906851596452765e-06,
      "loss": 0.2721,
      "mean_token_accuracy": 0.9027295112609863,
      "step": 132
    },
    {
      "epoch": 0.6186046511627907,
      "grad_norm": 2.2944834232330322,
      "learning_rate": 4.519070281545571e-06,
      "loss": 0.3041,
      "mean_token_accuracy": 0.8964738845825195,
      "step": 133
    },
    {
      "epoch": 0.6232558139534884,
      "grad_norm": 2.323543071746826,
      "learning_rate": 4.447715307725197e-06,
      "loss": 0.3137,
      "mean_token_accuracy": 0.8975229263305664,
      "step": 134
    },
    {
      "epoch": 0.627906976744186,
      "grad_norm": 2.3029696941375732,
      "learning_rate": 4.376639144190061e-06,
      "loss": 0.3004,
      "mean_token_accuracy": 0.8968156576156616,
      "step": 135
    },
    {
      "epoch": 0.6325581395348837,
      "grad_norm": 2.538562536239624,
      "learning_rate": 4.305860623073304e-06,
      "loss": 0.2989,
      "mean_token_accuracy": 0.8975074291229248,
      "step": 136
    },
    {
      "epoch": 0.6372093023255814,
      "grad_norm": 2.164029836654663,
      "learning_rate": 4.2353984976456e-06,
      "loss": 0.2795,
      "mean_token_accuracy": 0.9066439270973206,
      "step": 137
    },
    {
      "epoch": 0.641860465116279,
      "grad_norm": 2.2238547801971436,
      "learning_rate": 4.1652714373463435e-06,
      "loss": 0.2878,
      "mean_token_accuracy": 0.8984693884849548,
      "step": 138
    },
    {
      "epoch": 0.6465116279069767,
      "grad_norm": 2.2204103469848633,
      "learning_rate": 4.095498022837051e-06,
      "loss": 0.2723,
      "mean_token_accuracy": 0.9076555967330933,
      "step": 139
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 2.327342987060547,
      "learning_rate": 4.026096741078281e-06,
      "loss": 0.3144,
      "mean_token_accuracy": 0.8956175446510315,
      "step": 140
    },
    {
      "epoch": 0.6558139534883721,
      "grad_norm": 2.408447027206421,
      "learning_rate": 3.957085980431382e-06,
      "loss": 0.3109,
      "mean_token_accuracy": 0.8903638124465942,
      "step": 141
    },
    {
      "epoch": 0.6604651162790698,
      "grad_norm": 2.17551851272583,
      "learning_rate": 3.888484025786364e-06,
      "loss": 0.2808,
      "mean_token_accuracy": 0.9039127230644226,
      "step": 142
    },
    {
      "epoch": 0.6651162790697674,
      "grad_norm": 2.148789405822754,
      "learning_rate": 3.820309053717195e-06,
      "loss": 0.2644,
      "mean_token_accuracy": 0.9068344831466675,
      "step": 143
    },
    {
      "epoch": 0.6697674418604651,
      "grad_norm": 2.4230973720550537,
      "learning_rate": 3.75257912766578e-06,
      "loss": 0.3521,
      "mean_token_accuracy": 0.8838323354721069,
      "step": 144
    },
    {
      "epoch": 0.6744186046511628,
      "grad_norm": 2.407576560974121,
      "learning_rate": 3.6853121931559334e-06,
      "loss": 0.3176,
      "mean_token_accuracy": 0.8907623291015625,
      "step": 145
    },
    {
      "epoch": 0.6790697674418604,
      "grad_norm": 2.257375478744507,
      "learning_rate": 3.618526073038574e-06,
      "loss": 0.3402,
      "mean_token_accuracy": 0.877872109413147,
      "step": 146
    },
    {
      "epoch": 0.6837209302325581,
      "grad_norm": 2.3605127334594727,
      "learning_rate": 3.552238462769446e-06,
      "loss": 0.2822,
      "mean_token_accuracy": 0.898716390132904,
      "step": 147
    },
    {
      "epoch": 0.6883720930232559,
      "grad_norm": 2.5195729732513428,
      "learning_rate": 3.4864669257205745e-06,
      "loss": 0.2726,
      "mean_token_accuracy": 0.9063690900802612,
      "step": 148
    },
    {
      "epoch": 0.6930232558139535,
      "grad_norm": 2.344093084335327,
      "learning_rate": 3.4212288885267246e-06,
      "loss": 0.3185,
      "mean_token_accuracy": 0.8916053771972656,
      "step": 149
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 2.4580070972442627,
      "learning_rate": 3.3565416364681016e-06,
      "loss": 0.2861,
      "mean_token_accuracy": 0.8970394134521484,
      "step": 150
    },
    {
      "epoch": 0.7023255813953488,
      "grad_norm": 2.1077418327331543,
      "learning_rate": 3.2924223088904816e-06,
      "loss": 0.2753,
      "mean_token_accuracy": 0.9032756090164185,
      "step": 151
    },
    {
      "epoch": 0.7069767441860465,
      "grad_norm": 2.571012258529663,
      "learning_rate": 3.228887894664029e-06,
      "loss": 0.3382,
      "mean_token_accuracy": 0.8874310851097107,
      "step": 152
    },
    {
      "epoch": 0.7116279069767442,
      "grad_norm": 2.415187358856201,
      "learning_rate": 3.1659552276819693e-06,
      "loss": 0.311,
      "mean_token_accuracy": 0.8911898136138916,
      "step": 153
    },
    {
      "epoch": 0.7162790697674418,
      "grad_norm": 2.24096941947937,
      "learning_rate": 3.1036409824003324e-06,
      "loss": 0.2866,
      "mean_token_accuracy": 0.9001513123512268,
      "step": 154
    },
    {
      "epoch": 0.7209302325581395,
      "grad_norm": 2.1161606311798096,
      "learning_rate": 3.0419616694199327e-06,
      "loss": 0.2648,
      "mean_token_accuracy": 0.9077988862991333,
      "step": 155
    },
    {
      "epoch": 0.7255813953488373,
      "grad_norm": 2.244520425796509,
      "learning_rate": 2.98093363111178e-06,
      "loss": 0.2427,
      "mean_token_accuracy": 0.9150313138961792,
      "step": 156
    },
    {
      "epoch": 0.7302325581395349,
      "grad_norm": 2.494776725769043,
      "learning_rate": 2.92057303728704e-06,
      "loss": 0.2976,
      "mean_token_accuracy": 0.8998464941978455,
      "step": 157
    },
    {
      "epoch": 0.7348837209302326,
      "grad_norm": 2.248281717300415,
      "learning_rate": 2.860895880912735e-06,
      "loss": 0.2849,
      "mean_token_accuracy": 0.9054994583129883,
      "step": 158
    },
    {
      "epoch": 0.7395348837209302,
      "grad_norm": 2.331533432006836,
      "learning_rate": 2.801917973874294e-06,
      "loss": 0.3037,
      "mean_token_accuracy": 0.8930827379226685,
      "step": 159
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 2.3448197841644287,
      "learning_rate": 2.7436549427860766e-06,
      "loss": 0.3222,
      "mean_token_accuracy": 0.889302134513855,
      "step": 160
    },
    {
      "epoch": 0.7488372093023256,
      "grad_norm": 2.071540355682373,
      "learning_rate": 2.6861222248509926e-06,
      "loss": 0.2476,
      "mean_token_accuracy": 0.9146341681480408,
      "step": 161
    },
    {
      "epoch": 0.7534883720930232,
      "grad_norm": 2.1529202461242676,
      "learning_rate": 2.6293350637703123e-06,
      "loss": 0.2813,
      "mean_token_accuracy": 0.9099606871604919,
      "step": 162
    },
    {
      "epoch": 0.7581395348837209,
      "grad_norm": 2.4522061347961426,
      "learning_rate": 2.5733085057047325e-06,
      "loss": 0.2871,
      "mean_token_accuracy": 0.9062443971633911,
      "step": 163
    },
    {
      "epoch": 0.7627906976744186,
      "grad_norm": 2.1827683448791504,
      "learning_rate": 2.518057395287792e-06,
      "loss": 0.2984,
      "mean_token_accuracy": 0.8948549628257751,
      "step": 164
    },
    {
      "epoch": 0.7674418604651163,
      "grad_norm": 2.5053515434265137,
      "learning_rate": 2.463596371692681e-06,
      "loss": 0.297,
      "mean_token_accuracy": 0.8924633860588074,
      "step": 165
    },
    {
      "epoch": 0.772093023255814,
      "grad_norm": 2.1398110389709473,
      "learning_rate": 2.409939864753487e-06,
      "loss": 0.2976,
      "mean_token_accuracy": 0.8955926895141602,
      "step": 166
    },
    {
      "epoch": 0.7767441860465116,
      "grad_norm": 2.19425892829895,
      "learning_rate": 2.3571020911419067e-06,
      "loss": 0.2816,
      "mean_token_accuracy": 0.9085714221000671,
      "step": 167
    },
    {
      "epoch": 0.7813953488372093,
      "grad_norm": 2.4098033905029297,
      "learning_rate": 2.3050970506004463e-06,
      "loss": 0.3113,
      "mean_token_accuracy": 0.8950749635696411,
      "step": 168
    },
    {
      "epoch": 0.786046511627907,
      "grad_norm": 2.4144301414489746,
      "learning_rate": 2.2539385222330797e-06,
      "loss": 0.2541,
      "mean_token_accuracy": 0.90910804271698,
      "step": 169
    },
    {
      "epoch": 0.7906976744186046,
      "grad_norm": 2.286418914794922,
      "learning_rate": 2.203640060854387e-06,
      "loss": 0.269,
      "mean_token_accuracy": 0.9078757166862488,
      "step": 170
    },
    {
      "epoch": 0.7953488372093023,
      "grad_norm": 2.281157970428467,
      "learning_rate": 2.1542149933981014e-06,
      "loss": 0.3069,
      "mean_token_accuracy": 0.893151581287384,
      "step": 171
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.220977544784546,
      "learning_rate": 2.10567641538605e-06,
      "loss": 0.279,
      "mean_token_accuracy": 0.9098817110061646,
      "step": 172
    },
    {
      "epoch": 0.8046511627906977,
      "grad_norm": 2.178304433822632,
      "learning_rate": 2.058037187458398e-06,
      "loss": 0.2903,
      "mean_token_accuracy": 0.9047447443008423,
      "step": 173
    },
    {
      "epoch": 0.8093023255813954,
      "grad_norm": 2.4263737201690674,
      "learning_rate": 2.011309931966136e-06,
      "loss": 0.2844,
      "mean_token_accuracy": 0.9039999842643738,
      "step": 174
    },
    {
      "epoch": 0.813953488372093,
      "grad_norm": 2.2288589477539062,
      "learning_rate": 1.965507029626695e-06,
      "loss": 0.2977,
      "mean_token_accuracy": 0.8857610821723938,
      "step": 175
    },
    {
      "epoch": 0.8186046511627907,
      "grad_norm": 2.2465760707855225,
      "learning_rate": 1.920640616243589e-06,
      "loss": 0.2632,
      "mean_token_accuracy": 0.9077427387237549,
      "step": 176
    },
    {
      "epoch": 0.8232558139534883,
      "grad_norm": 2.478376626968384,
      "learning_rate": 1.8767225794909484e-06,
      "loss": 0.321,
      "mean_token_accuracy": 0.8919563889503479,
      "step": 177
    },
    {
      "epoch": 0.827906976744186,
      "grad_norm": 2.138991594314575,
      "learning_rate": 1.8337645557637929e-06,
      "loss": 0.2744,
      "mean_token_accuracy": 0.9032313227653503,
      "step": 178
    },
    {
      "epoch": 0.8325581395348837,
      "grad_norm": 2.145294189453125,
      "learning_rate": 1.7917779270948887e-06,
      "loss": 0.2934,
      "mean_token_accuracy": 0.8986738324165344,
      "step": 179
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 2.3890199661254883,
      "learning_rate": 1.7507738181390027e-06,
      "loss": 0.2847,
      "mean_token_accuracy": 0.9007092118263245,
      "step": 180
    },
    {
      "epoch": 0.8418604651162791,
      "grad_norm": 2.3594157695770264,
      "learning_rate": 1.7107630932253383e-06,
      "loss": 0.2853,
      "mean_token_accuracy": 0.8999655842781067,
      "step": 181
    },
    {
      "epoch": 0.8465116279069768,
      "grad_norm": 2.2847506999969482,
      "learning_rate": 1.6717563534789594e-06,
      "loss": 0.2909,
      "mean_token_accuracy": 0.9014893174171448,
      "step": 182
    },
    {
      "epoch": 0.8511627906976744,
      "grad_norm": 2.3248329162597656,
      "learning_rate": 1.6337639340119476e-06,
      "loss": 0.2996,
      "mean_token_accuracy": 0.8940504193305969,
      "step": 183
    },
    {
      "epoch": 0.8558139534883721,
      "grad_norm": 2.390031576156616,
      "learning_rate": 1.596795901185037e-06,
      "loss": 0.305,
      "mean_token_accuracy": 0.8964377641677856,
      "step": 184
    },
    {
      "epoch": 0.8604651162790697,
      "grad_norm": 2.054699420928955,
      "learning_rate": 1.5608620499404628e-06,
      "loss": 0.2769,
      "mean_token_accuracy": 0.9020813703536987,
      "step": 185
    },
    {
      "epoch": 0.8651162790697674,
      "grad_norm": 2.3316433429718018,
      "learning_rate": 1.5259719012067249e-06,
      "loss": 0.3028,
      "mean_token_accuracy": 0.8970876932144165,
      "step": 186
    },
    {
      "epoch": 0.8697674418604651,
      "grad_norm": 2.2691869735717773,
      "learning_rate": 1.4921346993759453e-06,
      "loss": 0.27,
      "mean_token_accuracy": 0.9035449028015137,
      "step": 187
    },
    {
      "epoch": 0.8744186046511628,
      "grad_norm": 2.1666178703308105,
      "learning_rate": 1.459359409854505e-06,
      "loss": 0.2836,
      "mean_token_accuracy": 0.9079626202583313,
      "step": 188
    },
    {
      "epoch": 0.8790697674418605,
      "grad_norm": 2.2185068130493164,
      "learning_rate": 1.4276547166875946e-06,
      "loss": 0.2652,
      "mean_token_accuracy": 0.9092705249786377,
      "step": 189
    },
    {
      "epoch": 0.8837209302325582,
      "grad_norm": 2.47299861907959,
      "learning_rate": 1.397029020258313e-06,
      "loss": 0.2879,
      "mean_token_accuracy": 0.896272599697113,
      "step": 190
    },
    {
      "epoch": 0.8883720930232558,
      "grad_norm": 2.3769164085388184,
      "learning_rate": 1.367490435061928e-06,
      "loss": 0.3358,
      "mean_token_accuracy": 0.8814517259597778,
      "step": 191
    },
    {
      "epoch": 0.8930232558139535,
      "grad_norm": 2.21427845954895,
      "learning_rate": 1.3390467875558855e-06,
      "loss": 0.2465,
      "mean_token_accuracy": 0.9141114950180054,
      "step": 192
    },
    {
      "epoch": 0.8976744186046511,
      "grad_norm": 2.2213754653930664,
      "learning_rate": 1.3117056140861317e-06,
      "loss": 0.2912,
      "mean_token_accuracy": 0.9031753540039062,
      "step": 193
    },
    {
      "epoch": 0.9023255813953488,
      "grad_norm": 2.2283401489257812,
      "learning_rate": 1.285474158890304e-06,
      "loss": 0.2645,
      "mean_token_accuracy": 0.9112547039985657,
      "step": 194
    },
    {
      "epoch": 0.9069767441860465,
      "grad_norm": 2.1087920665740967,
      "learning_rate": 1.2603593721783219e-06,
      "loss": 0.2653,
      "mean_token_accuracy": 0.9116804599761963,
      "step": 195
    },
    {
      "epoch": 0.9116279069767442,
      "grad_norm": 2.2635421752929688,
      "learning_rate": 1.2363679082908766e-06,
      "loss": 0.2987,
      "mean_token_accuracy": 0.8961791396141052,
      "step": 196
    },
    {
      "epoch": 0.9162790697674419,
      "grad_norm": 2.3147056102752686,
      "learning_rate": 1.2135061239363161e-06,
      "loss": 0.2587,
      "mean_token_accuracy": 0.9121925234794617,
      "step": 197
    },
    {
      "epoch": 0.9209302325581395,
      "grad_norm": 2.262284755706787,
      "learning_rate": 1.1917800765063954e-06,
      "loss": 0.2704,
      "mean_token_accuracy": 0.9092745780944824,
      "step": 198
    },
    {
      "epoch": 0.9255813953488372,
      "grad_norm": 2.5080342292785645,
      "learning_rate": 1.1711955224713209e-06,
      "loss": 0.2932,
      "mean_token_accuracy": 0.898510217666626,
      "step": 199
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 2.2359910011291504,
      "learning_rate": 1.1517579158545386e-06,
      "loss": 0.2699,
      "mean_token_accuracy": 0.9084086418151855,
      "step": 200
    },
    {
      "epoch": 0.9348837209302325,
      "grad_norm": 2.4288928508758545,
      "learning_rate": 1.1334724067876463e-06,
      "loss": 0.3007,
      "mean_token_accuracy": 0.8988877534866333,
      "step": 201
    },
    {
      "epoch": 0.9395348837209302,
      "grad_norm": 2.267275810241699,
      "learning_rate": 1.1163438401458358e-06,
      "loss": 0.2668,
      "mean_token_accuracy": 0.9053376913070679,
      "step": 202
    },
    {
      "epoch": 0.9441860465116279,
      "grad_norm": 2.3959038257598877,
      "learning_rate": 1.1003767542642021e-06,
      "loss": 0.2833,
      "mean_token_accuracy": 0.9051226377487183,
      "step": 203
    },
    {
      "epoch": 0.9488372093023256,
      "grad_norm": 2.2642016410827637,
      "learning_rate": 1.0855753797352868e-06,
      "loss": 0.2544,
      "mean_token_accuracy": 0.9085396528244019,
      "step": 204
    },
    {
      "epoch": 0.9534883720930233,
      "grad_norm": 2.1275274753570557,
      "learning_rate": 1.0719436382881466e-06,
      "loss": 0.2614,
      "mean_token_accuracy": 0.9060357809066772,
      "step": 205
    },
    {
      "epoch": 0.958139534883721,
      "grad_norm": 2.3473360538482666,
      "learning_rate": 1.0594851417492665e-06,
      "loss": 0.2869,
      "mean_token_accuracy": 0.9008370637893677,
      "step": 206
    },
    {
      "epoch": 0.9627906976744186,
      "grad_norm": 2.4919135570526123,
      "learning_rate": 1.0482031910855804e-06,
      "loss": 0.3038,
      "mean_token_accuracy": 0.8915042281150818,
      "step": 207
    },
    {
      "epoch": 0.9674418604651163,
      "grad_norm": 2.309241533279419,
      "learning_rate": 1.0381007755298547e-06,
      "loss": 0.2765,
      "mean_token_accuracy": 0.9052693843841553,
      "step": 208
    },
    {
      "epoch": 0.9720930232558139,
      "grad_norm": 2.2533209323883057,
      "learning_rate": 1.029180571788672e-06,
      "loss": 0.2576,
      "mean_token_accuracy": 0.9127118587493896,
      "step": 209
    },
    {
      "epoch": 0.9767441860465116,
      "grad_norm": 2.08575439453125,
      "learning_rate": 1.021444943333218e-06,
      "loss": 0.2668,
      "mean_token_accuracy": 0.908217191696167,
      "step": 210
    },
    {
      "epoch": 0.9813953488372092,
      "grad_norm": 2.299942970275879,
      "learning_rate": 1.0148959397730637e-06,
      "loss": 0.2626,
      "mean_token_accuracy": 0.9057932496070862,
      "step": 211
    },
    {
      "epoch": 0.986046511627907,
      "grad_norm": 2.232316017150879,
      "learning_rate": 1.0095352963131057e-06,
      "loss": 0.2853,
      "mean_token_accuracy": 0.9010600447654724,
      "step": 212
    },
    {
      "epoch": 0.9906976744186047,
      "grad_norm": 2.287255048751831,
      "learning_rate": 1.0053644332938118e-06,
      "loss": 0.251,
      "mean_token_accuracy": 0.9092245697975159,
      "step": 213
    },
    {
      "epoch": 0.9953488372093023,
      "grad_norm": 2.229083776473999,
      "learning_rate": 1.0023844558148912e-06,
      "loss": 0.2969,
      "mean_token_accuracy": 0.8984347581863403,
      "step": 214
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.0628480911254883,
      "learning_rate": 1.0005961534424925e-06,
      "loss": 0.2309,
      "mean_token_accuracy": 0.909231960773468,
      "step": 215
    },
    {
      "epoch": 1.0,
      "step": 215,
      "total_flos": 2.0144468407196058e+17,
      "train_loss": 0.325891209826913,
      "train_runtime": 788.7208,
      "train_samples_per_second": 8.686,
      "train_steps_per_second": 0.273
    }
  ],
  "logging_steps": 1,
  "max_steps": 215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0144468407196058e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}