{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5339028296849974,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 8.144560241699219,
      "epoch": 0.005339028296849973,
      "grad_norm": 0.99609375,
      "learning_rate": 2e-06,
      "loss": 7.8897,
      "mean_token_accuracy": 0.06864776574075222,
      "num_tokens": 10658.0,
      "step": 5
    },
    {
      "entropy": 8.15593843460083,
      "epoch": 0.010678056593699947,
      "grad_norm": 0.9140625,
      "learning_rate": 4.5e-06,
      "loss": 7.8846,
      "mean_token_accuracy": 0.06999277919530869,
      "num_tokens": 21327.0,
      "step": 10
    },
    {
      "entropy": 8.144119453430175,
      "epoch": 0.01601708489054992,
      "grad_norm": 0.8828125,
      "learning_rate": 7e-06,
      "loss": 7.9107,
      "mean_token_accuracy": 0.06488565169274807,
      "num_tokens": 32403.0,
      "step": 15
    },
    {
      "entropy": 8.17639331817627,
      "epoch": 0.021356113187399894,
      "grad_norm": 0.9375,
      "learning_rate": 9.5e-06,
      "loss": 7.8553,
      "mean_token_accuracy": 0.0711637206375599,
      "num_tokens": 43471.0,
      "step": 20
    },
    {
      "entropy": 8.177908802032471,
      "epoch": 0.026695141484249868,
      "grad_norm": 0.8359375,
      "learning_rate": 1.2e-05,
      "loss": 7.8379,
      "mean_token_accuracy": 0.07274281270802022,
      "num_tokens": 53724.0,
      "step": 25
    },
    {
      "entropy": 8.16096534729004,
      "epoch": 0.03203416978109984,
      "grad_norm": 0.7890625,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 7.9025,
      "mean_token_accuracy": 0.0708409644663334,
      "num_tokens": 65115.0,
      "step": 30
    },
    {
      "entropy": 8.17019271850586,
      "epoch": 0.03737319807794982,
      "grad_norm": 0.921875,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 7.8468,
      "mean_token_accuracy": 0.07302796579897404,
      "num_tokens": 75902.0,
      "step": 35
    },
    {
      "entropy": 8.207113361358642,
      "epoch": 0.04271222637479979,
      "grad_norm": 0.85546875,
      "learning_rate": 1.95e-05,
      "loss": 7.8962,
      "mean_token_accuracy": 0.06636322438716888,
      "num_tokens": 87051.0,
      "step": 40
    },
    {
      "entropy": 8.1253080368042,
      "epoch": 0.04805125467164976,
      "grad_norm": 0.78125,
      "learning_rate": 2.2e-05,
      "loss": 7.8199,
      "mean_token_accuracy": 0.07184852361679077,
      "num_tokens": 98998.0,
      "step": 45
    },
    {
      "entropy": 8.162546825408935,
      "epoch": 0.053390282968499736,
      "grad_norm": 0.99609375,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 7.8969,
      "mean_token_accuracy": 0.07030453905463219,
      "num_tokens": 111207.0,
      "step": 50
    },
    {
      "entropy": 8.178112983703613,
      "epoch": 0.05872931126534971,
      "grad_norm": 0.80078125,
      "learning_rate": 2.7e-05,
      "loss": 7.8128,
      "mean_token_accuracy": 0.07619077749550343,
      "num_tokens": 121039.0,
      "step": 55
    },
    {
      "entropy": 8.193019104003906,
      "epoch": 0.06406833956219968,
      "grad_norm": 0.8828125,
      "learning_rate": 2.95e-05,
      "loss": 7.9013,
      "mean_token_accuracy": 0.07129124961793423,
      "num_tokens": 132604.0,
      "step": 60
    },
    {
      "entropy": 8.207361793518066,
      "epoch": 0.06940736785904965,
      "grad_norm": 0.87109375,
      "learning_rate": 3.2e-05,
      "loss": 7.8666,
      "mean_token_accuracy": 0.07484896555542946,
      "num_tokens": 142825.0,
      "step": 65
    },
    {
      "entropy": 8.12415533065796,
      "epoch": 0.07474639615589963,
      "grad_norm": 0.91796875,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 7.8463,
      "mean_token_accuracy": 0.07354214936494827,
      "num_tokens": 153121.0,
      "step": 70
    },
    {
      "entropy": 8.101186609268188,
      "epoch": 0.0800854244527496,
      "grad_norm": 0.78515625,
      "learning_rate": 3.7e-05,
      "loss": 7.7585,
      "mean_token_accuracy": 0.07698194943368435,
      "num_tokens": 164675.0,
      "step": 75
    },
    {
      "entropy": 8.125961208343506,
      "epoch": 0.08542445274959957,
      "grad_norm": 0.92578125,
      "learning_rate": 3.95e-05,
      "loss": 7.7999,
      "mean_token_accuracy": 0.07594770528376102,
      "num_tokens": 175146.0,
      "step": 80
    },
    {
      "entropy": 8.141195964813232,
      "epoch": 0.09076348104644955,
      "grad_norm": 0.8046875,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 7.8825,
      "mean_token_accuracy": 0.06618092842400074,
      "num_tokens": 186177.0,
      "step": 85
    },
    {
      "entropy": 8.16831111907959,
      "epoch": 0.09610250934329952,
      "grad_norm": 0.8984375,
      "learning_rate": 4.45e-05,
      "loss": 7.8295,
      "mean_token_accuracy": 0.06966978162527085,
      "num_tokens": 197143.0,
      "step": 90
    },
    {
      "entropy": 8.187948417663574,
      "epoch": 0.10144153764014949,
      "grad_norm": 0.7265625,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 7.8424,
      "mean_token_accuracy": 0.06987790018320084,
      "num_tokens": 207979.0,
      "step": 95
    },
    {
      "entropy": 8.142891693115235,
      "epoch": 0.10678056593699947,
      "grad_norm": 0.875,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 7.8131,
      "mean_token_accuracy": 0.07337651327252388,
      "num_tokens": 218733.0,
      "step": 100
    },
    {
      "entropy": 8.133907985687255,
      "epoch": 0.11211959423384944,
      "grad_norm": 0.93359375,
      "learning_rate": 5.2e-05,
      "loss": 7.8532,
      "mean_token_accuracy": 0.06986705549061298,
      "num_tokens": 228887.0,
      "step": 105
    },
    {
      "entropy": 8.112241554260255,
      "epoch": 0.11745862253069941,
      "grad_norm": 0.92578125,
      "learning_rate": 5.45e-05,
      "loss": 7.7902,
      "mean_token_accuracy": 0.07219611443579196,
      "num_tokens": 240289.0,
      "step": 110
    },
    {
      "entropy": 8.137475204467773,
      "epoch": 0.12279765082754938,
      "grad_norm": 0.82421875,
      "learning_rate": 5.7e-05,
      "loss": 7.8648,
      "mean_token_accuracy": 0.07478626742959023,
      "num_tokens": 250548.0,
      "step": 115
    },
    {
      "entropy": 8.1454008102417,
      "epoch": 0.12813667912439936,
      "grad_norm": 1.015625,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 7.7908,
      "mean_token_accuracy": 0.07535585910081863,
      "num_tokens": 261669.0,
      "step": 120
    },
    {
      "entropy": 8.10846242904663,
      "epoch": 0.13347570742124934,
      "grad_norm": 0.78515625,
      "learning_rate": 6.2e-05,
      "loss": 7.8424,
      "mean_token_accuracy": 0.07433099895715714,
      "num_tokens": 272926.0,
      "step": 125
    },
    {
      "entropy": 8.147141361236573,
      "epoch": 0.1388147357180993,
      "grad_norm": 0.91015625,
      "learning_rate": 6.450000000000001e-05,
      "loss": 7.7477,
      "mean_token_accuracy": 0.0750483900308609,
      "num_tokens": 284173.0,
      "step": 130
    },
    {
      "entropy": 8.172099399566651,
      "epoch": 0.14415376401494928,
      "grad_norm": 0.875,
      "learning_rate": 6.7e-05,
      "loss": 7.7941,
      "mean_token_accuracy": 0.07234857454895974,
      "num_tokens": 294850.0,
      "step": 135
    },
    {
      "entropy": 8.106251430511474,
      "epoch": 0.14949279231179927,
      "grad_norm": 0.84765625,
      "learning_rate": 6.950000000000001e-05,
      "loss": 7.8398,
      "mean_token_accuracy": 0.07133509777486324,
      "num_tokens": 305727.0,
      "step": 140
    },
    {
      "entropy": 8.116196441650391,
      "epoch": 0.15483182060864922,
      "grad_norm": 0.89453125,
      "learning_rate": 7.2e-05,
      "loss": 7.7629,
      "mean_token_accuracy": 0.07706886641681195,
      "num_tokens": 317243.0,
      "step": 145
    },
    {
      "entropy": 8.17130641937256,
      "epoch": 0.1601708489054992,
      "grad_norm": 0.84375,
      "learning_rate": 7.45e-05,
      "loss": 7.8893,
      "mean_token_accuracy": 0.07055514976382256,
      "num_tokens": 328334.0,
      "step": 150
    },
    {
      "entropy": 8.190022945404053,
      "epoch": 0.16550987720234916,
      "grad_norm": 0.828125,
      "learning_rate": 7.7e-05,
      "loss": 7.8261,
      "mean_token_accuracy": 0.06939826495945453,
      "num_tokens": 339774.0,
      "step": 155
    },
    {
      "entropy": 8.1759521484375,
      "epoch": 0.17084890549919915,
      "grad_norm": 0.8515625,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.8223,
      "mean_token_accuracy": 0.07344263643026352,
      "num_tokens": 350211.0,
      "step": 160
    },
    {
      "entropy": 8.092726516723634,
      "epoch": 0.1761879337960491,
      "grad_norm": 0.859375,
      "learning_rate": 8.2e-05,
      "loss": 7.7982,
      "mean_token_accuracy": 0.07263314053416252,
      "num_tokens": 360109.0,
      "step": 165
    },
    {
      "entropy": 8.08326988220215,
      "epoch": 0.1815269620928991,
      "grad_norm": 0.86328125,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.779,
      "mean_token_accuracy": 0.07205527275800705,
      "num_tokens": 370911.0,
      "step": 170
    },
    {
      "entropy": 8.193898010253907,
      "epoch": 0.18686599038974908,
      "grad_norm": 0.83984375,
      "learning_rate": 8.7e-05,
      "loss": 7.8104,
      "mean_token_accuracy": 0.0764952365309,
      "num_tokens": 381808.0,
      "step": 175
    },
    {
      "entropy": 8.056710386276245,
      "epoch": 0.19220501868659903,
      "grad_norm": 0.87890625,
      "learning_rate": 8.95e-05,
      "loss": 7.7494,
      "mean_token_accuracy": 0.07683732137084007,
      "num_tokens": 392175.0,
      "step": 180
    },
    {
      "entropy": 8.197551059722901,
      "epoch": 0.19754404698344902,
      "grad_norm": 0.9609375,
      "learning_rate": 9.2e-05,
      "loss": 7.8564,
      "mean_token_accuracy": 0.0671585526317358,
      "num_tokens": 403261.0,
      "step": 185
    },
    {
      "entropy": 8.099643325805664,
      "epoch": 0.20288307528029897,
      "grad_norm": 0.86328125,
      "learning_rate": 9.45e-05,
      "loss": 7.7407,
      "mean_token_accuracy": 0.07576573640108109,
      "num_tokens": 414992.0,
      "step": 190
    },
    {
      "entropy": 8.113563442230225,
      "epoch": 0.20822210357714896,
      "grad_norm": 0.90234375,
      "learning_rate": 9.7e-05,
      "loss": 7.754,
      "mean_token_accuracy": 0.07667017802596092,
      "num_tokens": 425316.0,
      "step": 195
    },
    {
      "entropy": 8.137048149108887,
      "epoch": 0.21356113187399894,
      "grad_norm": 0.84375,
      "learning_rate": 9.95e-05,
      "loss": 7.8145,
      "mean_token_accuracy": 0.07361620292067528,
      "num_tokens": 437759.0,
      "step": 200
    },
    {
      "entropy": 8.08598484992981,
      "epoch": 0.2189001601708489,
      "grad_norm": 0.91796875,
      "learning_rate": 0.000102,
      "loss": 7.7784,
      "mean_token_accuracy": 0.07368727251887322,
      "num_tokens": 448066.0,
      "step": 205
    },
    {
      "entropy": 8.077975082397462,
      "epoch": 0.22423918846769889,
      "grad_norm": 0.8203125,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.7068,
      "mean_token_accuracy": 0.07944998890161514,
      "num_tokens": 458632.0,
      "step": 210
    },
    {
      "entropy": 8.1232834815979,
      "epoch": 0.22957821676454884,
      "grad_norm": 0.9453125,
      "learning_rate": 0.000107,
      "loss": 7.7381,
      "mean_token_accuracy": 0.07455957531929017,
      "num_tokens": 469224.0,
      "step": 215
    },
    {
      "entropy": 8.161263799667358,
      "epoch": 0.23491724506139883,
      "grad_norm": 0.95703125,
      "learning_rate": 0.0001095,
      "loss": 7.8058,
      "mean_token_accuracy": 0.07331273853778839,
      "num_tokens": 480492.0,
      "step": 220
    },
    {
      "entropy": 8.1416805267334,
      "epoch": 0.2402562733582488,
      "grad_norm": 0.98046875,
      "learning_rate": 0.000112,
      "loss": 7.7529,
      "mean_token_accuracy": 0.07843170017004013,
      "num_tokens": 491325.0,
      "step": 225
    },
    {
      "entropy": 8.065291547775269,
      "epoch": 0.24559530165509877,
      "grad_norm": 0.83203125,
      "learning_rate": 0.0001145,
      "loss": 7.8025,
      "mean_token_accuracy": 0.0766532089561224,
      "num_tokens": 502240.0,
      "step": 230
    },
    {
      "entropy": 8.098965644836426,
      "epoch": 0.25093432995194875,
      "grad_norm": 0.9453125,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.7488,
      "mean_token_accuracy": 0.0799623742699623,
      "num_tokens": 512710.0,
      "step": 235
    },
    {
      "entropy": 8.122612571716308,
      "epoch": 0.2562733582487987,
      "grad_norm": 0.921875,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.7845,
      "mean_token_accuracy": 0.07602895051240921,
      "num_tokens": 524023.0,
      "step": 240
    },
    {
      "entropy": 8.073074436187744,
      "epoch": 0.26161238654564867,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000122,
      "loss": 7.7022,
      "mean_token_accuracy": 0.07955551408231258,
      "num_tokens": 534612.0,
      "step": 245
    },
    {
      "entropy": 8.09334044456482,
      "epoch": 0.2669514148424987,
      "grad_norm": 0.9375,
      "learning_rate": 0.0001245,
      "loss": 7.7678,
      "mean_token_accuracy": 0.07153690792620182,
      "num_tokens": 544866.0,
      "step": 250
    },
    {
      "entropy": 8.147175598144532,
      "epoch": 0.27229044313934864,
      "grad_norm": 0.84765625,
      "learning_rate": 0.000127,
      "loss": 7.8087,
      "mean_token_accuracy": 0.07087494693696499,
      "num_tokens": 556091.0,
      "step": 255
    },
    {
      "entropy": 8.130566596984863,
      "epoch": 0.2776294714361986,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0001295,
      "loss": 7.805,
      "mean_token_accuracy": 0.07419991269707679,
      "num_tokens": 566946.0,
      "step": 260
    },
    {
      "entropy": 8.10559663772583,
      "epoch": 0.2829684997330486,
      "grad_norm": 0.8671875,
      "learning_rate": 0.000132,
      "loss": 7.6823,
      "mean_token_accuracy": 0.07802616208791732,
      "num_tokens": 577164.0,
      "step": 265
    },
    {
      "entropy": 8.044942378997803,
      "epoch": 0.28830752802989856,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.7173,
      "mean_token_accuracy": 0.07408697754144669,
      "num_tokens": 588744.0,
      "step": 270
    },
    {
      "entropy": 8.085132789611816,
      "epoch": 0.2936465563267485,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.716,
      "mean_token_accuracy": 0.07610422372817993,
      "num_tokens": 600943.0,
      "step": 275
    },
    {
      "entropy": 8.05778079032898,
      "epoch": 0.29898558462359853,
      "grad_norm": 0.9375,
      "learning_rate": 0.0001395,
      "loss": 7.7647,
      "mean_token_accuracy": 0.07883780151605606,
      "num_tokens": 611864.0,
      "step": 280
    },
    {
      "entropy": 8.074516010284423,
      "epoch": 0.3043246129204485,
      "grad_norm": 1.0,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.7126,
      "mean_token_accuracy": 0.07594608515501022,
      "num_tokens": 623314.0,
      "step": 285
    },
    {
      "entropy": 8.077810096740723,
      "epoch": 0.30966364121729845,
      "grad_norm": 0.9921875,
      "learning_rate": 0.0001445,
      "loss": 7.7528,
      "mean_token_accuracy": 0.07607153356075287,
      "num_tokens": 633509.0,
      "step": 290
    },
    {
      "entropy": 8.050742769241333,
      "epoch": 0.3150026695141484,
      "grad_norm": 1.015625,
      "learning_rate": 0.000147,
      "loss": 7.6563,
      "mean_token_accuracy": 0.08295750319957733,
      "num_tokens": 644655.0,
      "step": 295
    },
    {
      "entropy": 7.979042816162109,
      "epoch": 0.3203416978109984,
      "grad_norm": 0.87890625,
      "learning_rate": 0.0001495,
      "loss": 7.6899,
      "mean_token_accuracy": 0.07570353075861931,
      "num_tokens": 655940.0,
      "step": 300
    },
    {
      "entropy": 8.179082679748536,
      "epoch": 0.3256807261078484,
      "grad_norm": 0.85546875,
      "learning_rate": 0.000152,
      "loss": 7.6518,
      "mean_token_accuracy": 0.08190892487764359,
      "num_tokens": 667074.0,
      "step": 305
    },
    {
      "entropy": 8.127972841262817,
      "epoch": 0.33101975440469833,
      "grad_norm": 1.03125,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.7623,
      "mean_token_accuracy": 0.07947569712996483,
      "num_tokens": 677942.0,
      "step": 310
    },
    {
      "entropy": 7.998423624038696,
      "epoch": 0.33635878270154834,
      "grad_norm": 1.0625,
      "learning_rate": 0.000157,
      "loss": 7.6751,
      "mean_token_accuracy": 0.08147123157978058,
      "num_tokens": 689226.0,
      "step": 315
    },
    {
      "entropy": 8.068508625030518,
      "epoch": 0.3416978109983983,
      "grad_norm": 0.9296875,
      "learning_rate": 0.0001595,
      "loss": 7.7416,
      "mean_token_accuracy": 0.07528223097324371,
      "num_tokens": 700830.0,
      "step": 320
    },
    {
      "entropy": 8.10600996017456,
      "epoch": 0.34703683929524826,
      "grad_norm": 0.94921875,
      "learning_rate": 0.000162,
      "loss": 7.7188,
      "mean_token_accuracy": 0.07650677599012852,
      "num_tokens": 712677.0,
      "step": 325
    },
    {
      "entropy": 8.095576429367066,
      "epoch": 0.3523758675920982,
      "grad_norm": 1.0,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.786,
      "mean_token_accuracy": 0.07437327429652214,
      "num_tokens": 723833.0,
      "step": 330
    },
    {
      "entropy": 8.124511957168579,
      "epoch": 0.3577148958889482,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.763,
      "mean_token_accuracy": 0.07475610859692097,
      "num_tokens": 735526.0,
      "step": 335
    },
    {
      "entropy": 8.08799343109131,
      "epoch": 0.3630539241857982,
      "grad_norm": 0.9921875,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.707,
      "mean_token_accuracy": 0.0765246257185936,
      "num_tokens": 745934.0,
      "step": 340
    },
    {
      "entropy": 7.979455900192261,
      "epoch": 0.36839295248264814,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.6603,
      "mean_token_accuracy": 0.07649911046028138,
      "num_tokens": 756693.0,
      "step": 345
    },
    {
      "entropy": 8.125656652450562,
      "epoch": 0.37373198077949815,
      "grad_norm": 0.96484375,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.7286,
      "mean_token_accuracy": 0.07443214356899261,
      "num_tokens": 767236.0,
      "step": 350
    },
    {
      "entropy": 8.090236711502076,
      "epoch": 0.3790710090763481,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000177,
      "loss": 7.6527,
      "mean_token_accuracy": 0.0805337481200695,
      "num_tokens": 778552.0,
      "step": 355
    },
    {
      "entropy": 8.011722564697266,
      "epoch": 0.38441003737319807,
      "grad_norm": 0.96875,
      "learning_rate": 0.0001795,
      "loss": 7.7639,
      "mean_token_accuracy": 0.07575679123401642,
      "num_tokens": 789615.0,
      "step": 360
    },
    {
      "entropy": 8.122366762161255,
      "epoch": 0.3897490656700481,
      "grad_norm": 0.9375,
      "learning_rate": 0.000182,
      "loss": 7.7259,
      "mean_token_accuracy": 0.07842210233211518,
      "num_tokens": 799998.0,
      "step": 365
    },
    {
      "entropy": 8.053548765182494,
      "epoch": 0.39508809396689804,
      "grad_norm": 0.99609375,
      "learning_rate": 0.0001845,
      "loss": 7.6542,
      "mean_token_accuracy": 0.0804023414850235,
      "num_tokens": 810042.0,
      "step": 370
    },
    {
      "entropy": 7.964968490600586,
      "epoch": 0.400427122263748,
      "grad_norm": 0.90234375,
      "learning_rate": 0.000187,
      "loss": 7.6593,
      "mean_token_accuracy": 0.08147385269403458,
      "num_tokens": 821692.0,
      "step": 375
    },
    {
      "entropy": 8.106051301956176,
      "epoch": 0.40576615056059795,
      "grad_norm": 0.90625,
      "learning_rate": 0.0001895,
      "loss": 7.6801,
      "mean_token_accuracy": 0.0805871419608593,
      "num_tokens": 832262.0,
      "step": 380
    },
    {
      "entropy": 7.96937050819397,
      "epoch": 0.41110517885744796,
      "grad_norm": 1.0078125,
      "learning_rate": 0.000192,
      "loss": 7.6426,
      "mean_token_accuracy": 0.08224374130368232,
      "num_tokens": 843006.0,
      "step": 385
    },
    {
      "entropy": 8.042943239212036,
      "epoch": 0.4164442071542979,
      "grad_norm": 1.0625,
      "learning_rate": 0.0001945,
      "loss": 7.6272,
      "mean_token_accuracy": 0.07847281098365784,
      "num_tokens": 853978.0,
      "step": 390
    },
    {
      "entropy": 7.956211996078491,
      "epoch": 0.4217832354511479,
      "grad_norm": 1.015625,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.6663,
      "mean_token_accuracy": 0.07781294696033,
      "num_tokens": 864634.0,
      "step": 395
    },
    {
      "entropy": 8.029766321182251,
      "epoch": 0.4271222637479979,
      "grad_norm": 1.09375,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.6238,
      "mean_token_accuracy": 0.0834050565958023,
      "num_tokens": 875379.0,
      "step": 400
    },
    {
      "entropy": 8.130194091796875,
      "epoch": 0.43246129204484784,
      "grad_norm": 1.0625,
      "learning_rate": 0.000202,
      "loss": 7.671,
      "mean_token_accuracy": 0.07772457972168922,
      "num_tokens": 886428.0,
      "step": 405
    },
    {
      "entropy": 7.950660228729248,
      "epoch": 0.4378003203416978,
      "grad_norm": 0.94921875,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.6705,
      "mean_token_accuracy": 0.08004693239927292,
      "num_tokens": 896700.0,
      "step": 410
    },
    {
      "entropy": 8.066575813293458,
      "epoch": 0.44313934863854776,
      "grad_norm": 1.0,
      "learning_rate": 0.000207,
      "loss": 7.6757,
      "mean_token_accuracy": 0.08255721405148506,
      "num_tokens": 907478.0,
      "step": 415
    },
    {
      "entropy": 7.987462520599365,
      "epoch": 0.44847837693539777,
      "grad_norm": 1.265625,
      "learning_rate": 0.0002095,
      "loss": 7.5464,
      "mean_token_accuracy": 0.08664339035749435,
      "num_tokens": 918170.0,
      "step": 420
    },
    {
      "entropy": 7.865429925918579,
      "epoch": 0.45381740523224773,
      "grad_norm": 1.0,
      "learning_rate": 0.000212,
      "loss": 7.6636,
      "mean_token_accuracy": 0.08613021895289422,
      "num_tokens": 928866.0,
      "step": 425
    },
    {
      "entropy": 8.097207736968993,
      "epoch": 0.4591564335290977,
      "grad_norm": 0.97265625,
      "learning_rate": 0.0002145,
      "loss": 7.6311,
      "mean_token_accuracy": 0.08184469342231751,
      "num_tokens": 940395.0,
      "step": 430
    },
    {
      "entropy": 7.960992765426636,
      "epoch": 0.4644954618259477,
      "grad_norm": 1.09375,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.6702,
      "mean_token_accuracy": 0.07761614620685578,
      "num_tokens": 950814.0,
      "step": 435
    },
    {
      "entropy": 8.00200891494751,
      "epoch": 0.46983449012279765,
      "grad_norm": 1.09375,
      "learning_rate": 0.0002195,
      "loss": 7.6605,
      "mean_token_accuracy": 0.08137712515890598,
      "num_tokens": 961658.0,
      "step": 440
    },
    {
      "entropy": 8.125977849960327,
      "epoch": 0.4751735184196476,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000222,
      "loss": 7.6775,
      "mean_token_accuracy": 0.0752656638622284,
      "num_tokens": 974790.0,
      "step": 445
    },
    {
      "entropy": 7.911575841903686,
      "epoch": 0.4805125467164976,
      "grad_norm": 0.90234375,
      "learning_rate": 0.0002245,
      "loss": 7.6076,
      "mean_token_accuracy": 0.07721198052167892,
      "num_tokens": 986599.0,
      "step": 450
    },
    {
      "entropy": 7.994818162918091,
      "epoch": 0.4858515750133476,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00022700000000000002,
      "loss": 7.6094,
      "mean_token_accuracy": 0.07961493879556655,
      "num_tokens": 997731.0,
      "step": 455
    },
    {
      "entropy": 7.987026691436768,
      "epoch": 0.49119060331019754,
      "grad_norm": 0.9765625,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.6809,
      "mean_token_accuracy": 0.07975055277347565,
      "num_tokens": 1009343.0,
      "step": 460
    },
    {
      "entropy": 7.982935428619385,
      "epoch": 0.4965296316070475,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.5893,
      "mean_token_accuracy": 0.082920853048563,
      "num_tokens": 1019878.0,
      "step": 465
    },
    {
      "entropy": 7.984060430526734,
      "epoch": 0.5018686599038975,
      "grad_norm": 0.92578125,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.5769,
      "mean_token_accuracy": 0.08544681146740914,
      "num_tokens": 1030551.0,
      "step": 470
    },
    {
      "entropy": 7.922175931930542,
      "epoch": 0.5072076882007475,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000237,
      "loss": 7.6051,
      "mean_token_accuracy": 0.08194510340690613,
      "num_tokens": 1041432.0,
      "step": 475
    },
    {
      "entropy": 7.9855893611907955,
      "epoch": 0.5125467164975974,
      "grad_norm": 1.09375,
      "learning_rate": 0.0002395,
      "loss": 7.6037,
      "mean_token_accuracy": 0.082750453799963,
      "num_tokens": 1051769.0,
      "step": 480
    },
    {
      "entropy": 7.929568576812744,
      "epoch": 0.5178857447944474,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000242,
      "loss": 7.5625,
      "mean_token_accuracy": 0.08361941576004028,
      "num_tokens": 1062334.0,
      "step": 485
    },
    {
      "entropy": 7.949040317535401,
      "epoch": 0.5232247730912973,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0002445,
      "loss": 7.5365,
      "mean_token_accuracy": 0.08294312208890915,
      "num_tokens": 1072792.0,
      "step": 490
    },
    {
      "entropy": 7.850654411315918,
      "epoch": 0.5285638013881474,
      "grad_norm": 1.0234375,
      "learning_rate": 0.000247,
      "loss": 7.4228,
      "mean_token_accuracy": 0.08585703298449517,
      "num_tokens": 1083642.0,
      "step": 495
    },
    {
      "entropy": 7.871733045578003,
      "epoch": 0.5339028296849974,
      "grad_norm": 1.0625,
      "learning_rate": 0.0002495,
      "loss": 7.5653,
      "mean_token_accuracy": 0.08959369659423828,
      "num_tokens": 1094454.0,
      "step": 500
    },
    {
      "epoch": 0.5339028296849974,
      "eval_entropy": 7.677815706079657,
      "eval_loss": 7.619736671447754,
      "eval_mean_token_accuracy": 0.08080657599614813,
      "eval_num_tokens": 1094454.0,
      "eval_runtime": 2.3822,
      "eval_samples_per_second": 1292.919,
      "eval_steps_per_second": 161.615,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 9360,
  "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": 236538190725120.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}