{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5847953216374269,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.691974544525147,
      "epoch": 0.005847953216374269,
      "grad_norm": 13.5,
      "learning_rate": 2e-06,
      "loss": 10.8755,
      "mean_token_accuracy": 0.0,
      "num_tokens": 13999.0,
      "step": 5
    },
    {
      "entropy": 10.691928291320801,
      "epoch": 0.011695906432748537,
      "grad_norm": 13.1875,
      "learning_rate": 4.5e-06,
      "loss": 10.7881,
      "mean_token_accuracy": 8.032128680497408e-05,
      "num_tokens": 25888.0,
      "step": 10
    },
    {
      "entropy": 10.690763854980469,
      "epoch": 0.017543859649122806,
      "grad_norm": 10.5625,
      "learning_rate": 7e-06,
      "loss": 10.5299,
      "mean_token_accuracy": 0.029781045974232256,
      "num_tokens": 37699.0,
      "step": 15
    },
    {
      "entropy": 10.669985389709472,
      "epoch": 0.023391812865497075,
      "grad_norm": 5.9375,
      "learning_rate": 9.5e-06,
      "loss": 10.2235,
      "mean_token_accuracy": 0.05048878975212574,
      "num_tokens": 49648.0,
      "step": 20
    },
    {
      "entropy": 10.5446457862854,
      "epoch": 0.029239766081871343,
      "grad_norm": 4.0,
      "learning_rate": 1.2e-05,
      "loss": 9.9371,
      "mean_token_accuracy": 0.049999012425541875,
      "num_tokens": 62255.0,
      "step": 25
    },
    {
      "entropy": 10.506792068481445,
      "epoch": 0.03508771929824561,
      "grad_norm": 3.4375,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 9.8635,
      "mean_token_accuracy": 0.048928847163915636,
      "num_tokens": 76003.0,
      "step": 30
    },
    {
      "entropy": 10.482833862304688,
      "epoch": 0.04093567251461988,
      "grad_norm": 2.484375,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 9.7065,
      "mean_token_accuracy": 0.06288735270500183,
      "num_tokens": 87585.0,
      "step": 35
    },
    {
      "entropy": 10.464082145690918,
      "epoch": 0.04678362573099415,
      "grad_norm": 2.984375,
      "learning_rate": 1.95e-05,
      "loss": 9.6752,
      "mean_token_accuracy": 0.061649443581700325,
      "num_tokens": 100404.0,
      "step": 40
    },
    {
      "entropy": 10.373864269256591,
      "epoch": 0.05263157894736842,
      "grad_norm": 2.25,
      "learning_rate": 2.2e-05,
      "loss": 9.6279,
      "mean_token_accuracy": 0.0631986454129219,
      "num_tokens": 113130.0,
      "step": 45
    },
    {
      "entropy": 10.265812587738036,
      "epoch": 0.05847953216374269,
      "grad_norm": 3.265625,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.4722,
      "mean_token_accuracy": 0.0745375208556652,
      "num_tokens": 125430.0,
      "step": 50
    },
    {
      "entropy": 10.30671148300171,
      "epoch": 0.06432748538011696,
      "grad_norm": 2.703125,
      "learning_rate": 2.7e-05,
      "loss": 9.5423,
      "mean_token_accuracy": 0.06626624949276447,
      "num_tokens": 137550.0,
      "step": 55
    },
    {
      "entropy": 10.23580093383789,
      "epoch": 0.07017543859649122,
      "grad_norm": 2.609375,
      "learning_rate": 2.95e-05,
      "loss": 9.4244,
      "mean_token_accuracy": 0.08311915919184684,
      "num_tokens": 149530.0,
      "step": 60
    },
    {
      "entropy": 10.123470211029053,
      "epoch": 0.07602339181286549,
      "grad_norm": 2.828125,
      "learning_rate": 3.2e-05,
      "loss": 9.4496,
      "mean_token_accuracy": 0.07575741671025753,
      "num_tokens": 161671.0,
      "step": 65
    },
    {
      "entropy": 10.18219289779663,
      "epoch": 0.08187134502923976,
      "grad_norm": 2.078125,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.3854,
      "mean_token_accuracy": 0.07742468379437924,
      "num_tokens": 174160.0,
      "step": 70
    },
    {
      "entropy": 10.220508003234864,
      "epoch": 0.08771929824561403,
      "grad_norm": 2.515625,
      "learning_rate": 3.7e-05,
      "loss": 9.3404,
      "mean_token_accuracy": 0.07739944010972977,
      "num_tokens": 186969.0,
      "step": 75
    },
    {
      "entropy": 10.152502727508544,
      "epoch": 0.0935672514619883,
      "grad_norm": 2.078125,
      "learning_rate": 3.95e-05,
      "loss": 9.2504,
      "mean_token_accuracy": 0.08422459289431572,
      "num_tokens": 199470.0,
      "step": 80
    },
    {
      "entropy": 10.011490631103516,
      "epoch": 0.09941520467836257,
      "grad_norm": 2.484375,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.1723,
      "mean_token_accuracy": 0.09044785127043724,
      "num_tokens": 211306.0,
      "step": 85
    },
    {
      "entropy": 10.162246799468994,
      "epoch": 0.10526315789473684,
      "grad_norm": 2.21875,
      "learning_rate": 4.45e-05,
      "loss": 9.1514,
      "mean_token_accuracy": 0.08413446620106697,
      "num_tokens": 223323.0,
      "step": 90
    },
    {
      "entropy": 9.993253993988038,
      "epoch": 0.1111111111111111,
      "grad_norm": 2.046875,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.0369,
      "mean_token_accuracy": 0.09222856536507607,
      "num_tokens": 235896.0,
      "step": 95
    },
    {
      "entropy": 10.006341552734375,
      "epoch": 0.11695906432748537,
      "grad_norm": 2.375,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.0269,
      "mean_token_accuracy": 0.08629260584712029,
      "num_tokens": 247879.0,
      "step": 100
    },
    {
      "entropy": 9.960891246795654,
      "epoch": 0.12280701754385964,
      "grad_norm": 2.265625,
      "learning_rate": 5.2e-05,
      "loss": 8.8842,
      "mean_token_accuracy": 0.08838528990745545,
      "num_tokens": 259714.0,
      "step": 105
    },
    {
      "entropy": 9.847960281372071,
      "epoch": 0.1286549707602339,
      "grad_norm": 1.84375,
      "learning_rate": 5.45e-05,
      "loss": 8.8575,
      "mean_token_accuracy": 0.09311703070998192,
      "num_tokens": 272429.0,
      "step": 110
    },
    {
      "entropy": 9.824352073669434,
      "epoch": 0.13450292397660818,
      "grad_norm": 2.0625,
      "learning_rate": 5.7e-05,
      "loss": 8.834,
      "mean_token_accuracy": 0.08550347462296486,
      "num_tokens": 285924.0,
      "step": 115
    },
    {
      "entropy": 9.759407234191894,
      "epoch": 0.14035087719298245,
      "grad_norm": 1.3828125,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.6848,
      "mean_token_accuracy": 0.09789064452052117,
      "num_tokens": 299453.0,
      "step": 120
    },
    {
      "entropy": 9.61653537750244,
      "epoch": 0.14619883040935672,
      "grad_norm": 2.046875,
      "learning_rate": 6.2e-05,
      "loss": 8.6997,
      "mean_token_accuracy": 0.09431982859969139,
      "num_tokens": 312295.0,
      "step": 125
    },
    {
      "entropy": 9.595601081848145,
      "epoch": 0.15204678362573099,
      "grad_norm": 1.8671875,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.5501,
      "mean_token_accuracy": 0.09463789388537407,
      "num_tokens": 324730.0,
      "step": 130
    },
    {
      "entropy": 9.421235179901123,
      "epoch": 0.15789473684210525,
      "grad_norm": 1.4296875,
      "learning_rate": 6.7e-05,
      "loss": 8.4792,
      "mean_token_accuracy": 0.09828749150037766,
      "num_tokens": 336481.0,
      "step": 135
    },
    {
      "entropy": 9.258519268035888,
      "epoch": 0.16374269005847952,
      "grad_norm": 1.4296875,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.4926,
      "mean_token_accuracy": 0.0937332771718502,
      "num_tokens": 348987.0,
      "step": 140
    },
    {
      "entropy": 9.255396842956543,
      "epoch": 0.1695906432748538,
      "grad_norm": 1.15625,
      "learning_rate": 7.2e-05,
      "loss": 8.4024,
      "mean_token_accuracy": 0.09496198520064354,
      "num_tokens": 360390.0,
      "step": 145
    },
    {
      "entropy": 9.080035209655762,
      "epoch": 0.17543859649122806,
      "grad_norm": 1.40625,
      "learning_rate": 7.45e-05,
      "loss": 8.3663,
      "mean_token_accuracy": 0.0986220009624958,
      "num_tokens": 372456.0,
      "step": 150
    },
    {
      "entropy": 9.131995296478271,
      "epoch": 0.18128654970760233,
      "grad_norm": 1.3359375,
      "learning_rate": 7.7e-05,
      "loss": 8.3326,
      "mean_token_accuracy": 0.09041213691234588,
      "num_tokens": 384185.0,
      "step": 155
    },
    {
      "entropy": 8.906043529510498,
      "epoch": 0.1871345029239766,
      "grad_norm": 1.203125,
      "learning_rate": 7.950000000000001e-05,
      "loss": 8.2872,
      "mean_token_accuracy": 0.0966079480946064,
      "num_tokens": 395399.0,
      "step": 160
    },
    {
      "entropy": 8.800198173522949,
      "epoch": 0.19298245614035087,
      "grad_norm": 1.9140625,
      "learning_rate": 8.2e-05,
      "loss": 8.2863,
      "mean_token_accuracy": 0.09909554198384285,
      "num_tokens": 408676.0,
      "step": 165
    },
    {
      "entropy": 8.711225223541259,
      "epoch": 0.19883040935672514,
      "grad_norm": 1.0859375,
      "learning_rate": 8.450000000000001e-05,
      "loss": 8.2698,
      "mean_token_accuracy": 0.09550312235951423,
      "num_tokens": 421861.0,
      "step": 170
    },
    {
      "entropy": 8.798204135894775,
      "epoch": 0.2046783625730994,
      "grad_norm": 1.484375,
      "learning_rate": 8.7e-05,
      "loss": 8.3183,
      "mean_token_accuracy": 0.09797023683786392,
      "num_tokens": 434852.0,
      "step": 175
    },
    {
      "entropy": 8.719051837921143,
      "epoch": 0.21052631578947367,
      "grad_norm": 1.4296875,
      "learning_rate": 8.95e-05,
      "loss": 8.2497,
      "mean_token_accuracy": 0.09236074090003968,
      "num_tokens": 447313.0,
      "step": 180
    },
    {
      "entropy": 8.575885391235351,
      "epoch": 0.21637426900584794,
      "grad_norm": 1.125,
      "learning_rate": 9.2e-05,
      "loss": 8.1896,
      "mean_token_accuracy": 0.10111410841345787,
      "num_tokens": 460271.0,
      "step": 185
    },
    {
      "entropy": 8.562645149230956,
      "epoch": 0.2222222222222222,
      "grad_norm": 1.3203125,
      "learning_rate": 9.45e-05,
      "loss": 8.1582,
      "mean_token_accuracy": 0.1076015666127205,
      "num_tokens": 473006.0,
      "step": 190
    },
    {
      "entropy": 8.600567626953126,
      "epoch": 0.22807017543859648,
      "grad_norm": 1.1796875,
      "learning_rate": 9.7e-05,
      "loss": 8.1814,
      "mean_token_accuracy": 0.09954929873347282,
      "num_tokens": 486100.0,
      "step": 195
    },
    {
      "entropy": 8.427424430847168,
      "epoch": 0.23391812865497075,
      "grad_norm": 1.5390625,
      "learning_rate": 9.95e-05,
      "loss": 8.0686,
      "mean_token_accuracy": 0.108884796500206,
      "num_tokens": 499460.0,
      "step": 200
    },
    {
      "entropy": 8.508369827270508,
      "epoch": 0.23976608187134502,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000102,
      "loss": 8.0849,
      "mean_token_accuracy": 0.10188826620578766,
      "num_tokens": 511795.0,
      "step": 205
    },
    {
      "entropy": 8.331426906585694,
      "epoch": 0.24561403508771928,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00010449999999999999,
      "loss": 8.1497,
      "mean_token_accuracy": 0.10387411639094353,
      "num_tokens": 524897.0,
      "step": 210
    },
    {
      "entropy": 8.393550872802734,
      "epoch": 0.25146198830409355,
      "grad_norm": 1.2109375,
      "learning_rate": 0.000107,
      "loss": 8.0901,
      "mean_token_accuracy": 0.10539199337363243,
      "num_tokens": 538325.0,
      "step": 215
    },
    {
      "entropy": 8.538016510009765,
      "epoch": 0.2573099415204678,
      "grad_norm": 1.15625,
      "learning_rate": 0.0001095,
      "loss": 8.1375,
      "mean_token_accuracy": 0.09665202274918556,
      "num_tokens": 550979.0,
      "step": 220
    },
    {
      "entropy": 8.389378452301026,
      "epoch": 0.2631578947368421,
      "grad_norm": 1.15625,
      "learning_rate": 0.000112,
      "loss": 8.1055,
      "mean_token_accuracy": 0.10522033721208572,
      "num_tokens": 563001.0,
      "step": 225
    },
    {
      "entropy": 8.339937973022462,
      "epoch": 0.26900584795321636,
      "grad_norm": 1.421875,
      "learning_rate": 0.0001145,
      "loss": 8.0235,
      "mean_token_accuracy": 0.1068884126842022,
      "num_tokens": 573600.0,
      "step": 230
    },
    {
      "entropy": 8.336192607879639,
      "epoch": 0.27485380116959063,
      "grad_norm": 1.296875,
      "learning_rate": 0.00011700000000000001,
      "loss": 8.0318,
      "mean_token_accuracy": 0.10861181318759919,
      "num_tokens": 585287.0,
      "step": 235
    },
    {
      "entropy": 8.343888473510741,
      "epoch": 0.2807017543859649,
      "grad_norm": 1.484375,
      "learning_rate": 0.00011949999999999999,
      "loss": 8.0583,
      "mean_token_accuracy": 0.10137449800968171,
      "num_tokens": 597386.0,
      "step": 240
    },
    {
      "entropy": 8.288441467285157,
      "epoch": 0.28654970760233917,
      "grad_norm": 1.015625,
      "learning_rate": 0.000122,
      "loss": 8.0481,
      "mean_token_accuracy": 0.10464474633336067,
      "num_tokens": 609256.0,
      "step": 245
    },
    {
      "entropy": 8.411810398101807,
      "epoch": 0.29239766081871343,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0001245,
      "loss": 8.0474,
      "mean_token_accuracy": 0.10834256708621978,
      "num_tokens": 621506.0,
      "step": 250
    },
    {
      "entropy": 8.100932836532593,
      "epoch": 0.2982456140350877,
      "grad_norm": 1.328125,
      "learning_rate": 0.000127,
      "loss": 7.9646,
      "mean_token_accuracy": 0.1123759962618351,
      "num_tokens": 633512.0,
      "step": 255
    },
    {
      "entropy": 8.300220108032226,
      "epoch": 0.30409356725146197,
      "grad_norm": 1.2890625,
      "learning_rate": 0.0001295,
      "loss": 8.0895,
      "mean_token_accuracy": 0.10339951142668724,
      "num_tokens": 647098.0,
      "step": 260
    },
    {
      "entropy": 8.343167591094971,
      "epoch": 0.30994152046783624,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000132,
      "loss": 8.0972,
      "mean_token_accuracy": 0.09793601483106613,
      "num_tokens": 659559.0,
      "step": 265
    },
    {
      "entropy": 8.258354759216308,
      "epoch": 0.3157894736842105,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00013450000000000002,
      "loss": 8.0199,
      "mean_token_accuracy": 0.10353473275899887,
      "num_tokens": 672621.0,
      "step": 270
    },
    {
      "entropy": 8.298446559906006,
      "epoch": 0.3216374269005848,
      "grad_norm": 1.234375,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.9906,
      "mean_token_accuracy": 0.10663355737924576,
      "num_tokens": 685652.0,
      "step": 275
    },
    {
      "entropy": 8.19245777130127,
      "epoch": 0.32748538011695905,
      "grad_norm": 1.140625,
      "learning_rate": 0.0001395,
      "loss": 8.04,
      "mean_token_accuracy": 0.11108417361974716,
      "num_tokens": 696910.0,
      "step": 280
    },
    {
      "entropy": 8.219241619110107,
      "epoch": 0.3333333333333333,
      "grad_norm": 1.78125,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.9193,
      "mean_token_accuracy": 0.11071920469403267,
      "num_tokens": 709054.0,
      "step": 285
    },
    {
      "entropy": 8.26666088104248,
      "epoch": 0.3391812865497076,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0001445,
      "loss": 7.9479,
      "mean_token_accuracy": 0.11016275808215141,
      "num_tokens": 720902.0,
      "step": 290
    },
    {
      "entropy": 8.227052402496337,
      "epoch": 0.34502923976608185,
      "grad_norm": 1.21875,
      "learning_rate": 0.000147,
      "loss": 8.0106,
      "mean_token_accuracy": 0.10988251566886902,
      "num_tokens": 733319.0,
      "step": 295
    },
    {
      "entropy": 8.17465419769287,
      "epoch": 0.3508771929824561,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0001495,
      "loss": 7.8917,
      "mean_token_accuracy": 0.11573786139488221,
      "num_tokens": 744817.0,
      "step": 300
    },
    {
      "entropy": 8.232967758178711,
      "epoch": 0.3567251461988304,
      "grad_norm": 1.078125,
      "learning_rate": 0.000152,
      "loss": 7.9535,
      "mean_token_accuracy": 0.10650328993797302,
      "num_tokens": 756582.0,
      "step": 305
    },
    {
      "entropy": 8.144847440719605,
      "epoch": 0.36257309941520466,
      "grad_norm": 1.453125,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.8627,
      "mean_token_accuracy": 0.12130056619644165,
      "num_tokens": 769273.0,
      "step": 310
    },
    {
      "entropy": 8.138186359405518,
      "epoch": 0.3684210526315789,
      "grad_norm": 1.296875,
      "learning_rate": 0.000157,
      "loss": 7.9351,
      "mean_token_accuracy": 0.11499258056282997,
      "num_tokens": 782001.0,
      "step": 315
    },
    {
      "entropy": 8.08138952255249,
      "epoch": 0.3742690058479532,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0001595,
      "loss": 7.926,
      "mean_token_accuracy": 0.11798002570867538,
      "num_tokens": 794575.0,
      "step": 320
    },
    {
      "entropy": 8.198786306381226,
      "epoch": 0.38011695906432746,
      "grad_norm": 1.171875,
      "learning_rate": 0.000162,
      "loss": 7.9014,
      "mean_token_accuracy": 0.11587951257824898,
      "num_tokens": 805583.0,
      "step": 325
    },
    {
      "entropy": 8.112969303131104,
      "epoch": 0.38596491228070173,
      "grad_norm": 1.4765625,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.9467,
      "mean_token_accuracy": 0.1160537801682949,
      "num_tokens": 817617.0,
      "step": 330
    },
    {
      "entropy": 8.17340841293335,
      "epoch": 0.391812865497076,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.8426,
      "mean_token_accuracy": 0.11603786572813987,
      "num_tokens": 830043.0,
      "step": 335
    },
    {
      "entropy": 8.051109790802002,
      "epoch": 0.39766081871345027,
      "grad_norm": 1.203125,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.8356,
      "mean_token_accuracy": 0.12449322417378425,
      "num_tokens": 843200.0,
      "step": 340
    },
    {
      "entropy": 8.152585649490357,
      "epoch": 0.40350877192982454,
      "grad_norm": 1.9921875,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.8698,
      "mean_token_accuracy": 0.12035520151257514,
      "num_tokens": 856031.0,
      "step": 345
    },
    {
      "entropy": 8.055157375335693,
      "epoch": 0.4093567251461988,
      "grad_norm": 1.28125,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.8494,
      "mean_token_accuracy": 0.1174808993935585,
      "num_tokens": 869119.0,
      "step": 350
    },
    {
      "entropy": 7.974756145477295,
      "epoch": 0.4152046783625731,
      "grad_norm": 1.0625,
      "learning_rate": 0.000177,
      "loss": 7.8566,
      "mean_token_accuracy": 0.12319247648119927,
      "num_tokens": 880802.0,
      "step": 355
    },
    {
      "entropy": 8.131376028060913,
      "epoch": 0.42105263157894735,
      "grad_norm": 1.125,
      "learning_rate": 0.0001795,
      "loss": 7.8644,
      "mean_token_accuracy": 0.11949887052178383,
      "num_tokens": 894237.0,
      "step": 360
    },
    {
      "entropy": 8.112016677856445,
      "epoch": 0.4269005847953216,
      "grad_norm": 1.109375,
      "learning_rate": 0.000182,
      "loss": 7.8648,
      "mean_token_accuracy": 0.12209260165691375,
      "num_tokens": 906695.0,
      "step": 365
    },
    {
      "entropy": 8.052251434326172,
      "epoch": 0.4327485380116959,
      "grad_norm": 1.34375,
      "learning_rate": 0.0001845,
      "loss": 7.8327,
      "mean_token_accuracy": 0.1234503522515297,
      "num_tokens": 918955.0,
      "step": 370
    },
    {
      "entropy": 7.96677598953247,
      "epoch": 0.43859649122807015,
      "grad_norm": 1.015625,
      "learning_rate": 0.000187,
      "loss": 7.8616,
      "mean_token_accuracy": 0.12289973944425583,
      "num_tokens": 931812.0,
      "step": 375
    },
    {
      "entropy": 8.08064661026001,
      "epoch": 0.4444444444444444,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0001895,
      "loss": 7.8693,
      "mean_token_accuracy": 0.11234893426299095,
      "num_tokens": 945261.0,
      "step": 380
    },
    {
      "entropy": 8.010916709899902,
      "epoch": 0.4502923976608187,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000192,
      "loss": 7.781,
      "mean_token_accuracy": 0.12615325823426246,
      "num_tokens": 958376.0,
      "step": 385
    },
    {
      "entropy": 7.934221315383911,
      "epoch": 0.45614035087719296,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0001945,
      "loss": 7.7977,
      "mean_token_accuracy": 0.12733107730746268,
      "num_tokens": 971709.0,
      "step": 390
    },
    {
      "entropy": 8.095316505432129,
      "epoch": 0.4619883040935672,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.772,
      "mean_token_accuracy": 0.12458922639489174,
      "num_tokens": 983847.0,
      "step": 395
    },
    {
      "entropy": 8.061276531219482,
      "epoch": 0.4678362573099415,
      "grad_norm": 0.95703125,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.8479,
      "mean_token_accuracy": 0.11282772347331047,
      "num_tokens": 997034.0,
      "step": 400
    },
    {
      "entropy": 7.900276470184326,
      "epoch": 0.47368421052631576,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000202,
      "loss": 7.8811,
      "mean_token_accuracy": 0.11630931496620178,
      "num_tokens": 1010213.0,
      "step": 405
    },
    {
      "entropy": 8.164872455596925,
      "epoch": 0.47953216374269003,
      "grad_norm": 1.28125,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.7587,
      "mean_token_accuracy": 0.12265534400939941,
      "num_tokens": 1021618.0,
      "step": 410
    },
    {
      "entropy": 7.90818042755127,
      "epoch": 0.4853801169590643,
      "grad_norm": 1.2578125,
      "learning_rate": 0.000207,
      "loss": 7.7779,
      "mean_token_accuracy": 0.119289730489254,
      "num_tokens": 1033809.0,
      "step": 415
    },
    {
      "entropy": 8.035586547851562,
      "epoch": 0.49122807017543857,
      "grad_norm": 1.1328125,
      "learning_rate": 0.0002095,
      "loss": 7.7602,
      "mean_token_accuracy": 0.122083730250597,
      "num_tokens": 1045291.0,
      "step": 420
    },
    {
      "entropy": 7.94893217086792,
      "epoch": 0.49707602339181284,
      "grad_norm": 1.28125,
      "learning_rate": 0.000212,
      "loss": 7.7345,
      "mean_token_accuracy": 0.12310368940234184,
      "num_tokens": 1057516.0,
      "step": 425
    },
    {
      "entropy": 7.834074544906616,
      "epoch": 0.5029239766081871,
      "grad_norm": 1.015625,
      "learning_rate": 0.0002145,
      "loss": 7.7166,
      "mean_token_accuracy": 0.13022998943924904,
      "num_tokens": 1070675.0,
      "step": 430
    },
    {
      "entropy": 7.962926816940308,
      "epoch": 0.5087719298245614,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.7871,
      "mean_token_accuracy": 0.12778857946395875,
      "num_tokens": 1082965.0,
      "step": 435
    },
    {
      "entropy": 7.948134422302246,
      "epoch": 0.5146198830409356,
      "grad_norm": 1.0,
      "learning_rate": 0.0002195,
      "loss": 7.767,
      "mean_token_accuracy": 0.11752260848879814,
      "num_tokens": 1095922.0,
      "step": 440
    },
    {
      "entropy": 7.899146366119385,
      "epoch": 0.52046783625731,
      "grad_norm": 1.2890625,
      "learning_rate": 0.000222,
      "loss": 7.7519,
      "mean_token_accuracy": 0.1246542438864708,
      "num_tokens": 1109002.0,
      "step": 445
    },
    {
      "entropy": 8.014074802398682,
      "epoch": 0.5263157894736842,
      "grad_norm": 1.078125,
      "learning_rate": 0.0002245,
      "loss": 7.7662,
      "mean_token_accuracy": 0.11872777864336967,
      "num_tokens": 1121199.0,
      "step": 450
    },
    {
      "entropy": 7.865769338607788,
      "epoch": 0.5321637426900585,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00022700000000000002,
      "loss": 7.7036,
      "mean_token_accuracy": 0.12603166699409485,
      "num_tokens": 1134721.0,
      "step": 455
    },
    {
      "entropy": 7.8770805358886715,
      "epoch": 0.5380116959064327,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.788,
      "mean_token_accuracy": 0.12093541622161866,
      "num_tokens": 1147954.0,
      "step": 460
    },
    {
      "entropy": 7.915914726257324,
      "epoch": 0.543859649122807,
      "grad_norm": 1.125,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.7121,
      "mean_token_accuracy": 0.12637170255184174,
      "num_tokens": 1161208.0,
      "step": 465
    },
    {
      "entropy": 7.918968534469604,
      "epoch": 0.5497076023391813,
      "grad_norm": 1.171875,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.8051,
      "mean_token_accuracy": 0.11931493803858757,
      "num_tokens": 1173789.0,
      "step": 470
    },
    {
      "entropy": 7.964196968078613,
      "epoch": 0.5555555555555556,
      "grad_norm": 1.0,
      "learning_rate": 0.000237,
      "loss": 7.7054,
      "mean_token_accuracy": 0.12410269007086754,
      "num_tokens": 1185765.0,
      "step": 475
    },
    {
      "entropy": 7.763233613967896,
      "epoch": 0.5614035087719298,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0002395,
      "loss": 7.7242,
      "mean_token_accuracy": 0.12448163107037544,
      "num_tokens": 1197954.0,
      "step": 480
    },
    {
      "entropy": 7.995425701141357,
      "epoch": 0.5672514619883041,
      "grad_norm": 1.046875,
      "learning_rate": 0.000242,
      "loss": 7.6458,
      "mean_token_accuracy": 0.12746693715453147,
      "num_tokens": 1211285.0,
      "step": 485
    },
    {
      "entropy": 7.84964427947998,
      "epoch": 0.5730994152046783,
      "grad_norm": 1.0625,
      "learning_rate": 0.0002445,
      "loss": 7.7247,
      "mean_token_accuracy": 0.12084417417645454,
      "num_tokens": 1223197.0,
      "step": 490
    },
    {
      "entropy": 7.825186395645142,
      "epoch": 0.5789473684210527,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000247,
      "loss": 7.6581,
      "mean_token_accuracy": 0.12425737157464027,
      "num_tokens": 1234817.0,
      "step": 495
    },
    {
      "entropy": 7.8655126094818115,
      "epoch": 0.5847953216374269,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0002495,
      "loss": 7.7119,
      "mean_token_accuracy": 0.13079003244638443,
      "num_tokens": 1249305.0,
      "step": 500
    },
    {
      "epoch": 0.5847953216374269,
      "eval_entropy": 7.929424790857816,
      "eval_loss": 7.730849742889404,
      "eval_mean_token_accuracy": 0.11598945001640239,
      "eval_num_tokens": 1249305.0,
      "eval_runtime": 2.3042,
      "eval_samples_per_second": 1174.802,
      "eval_steps_per_second": 147.121,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 8540,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1810059724800000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}