{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.033488496701383076,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.691980457305908,
      "epoch": 0.00033488496701383075,
      "grad_norm": 11.875,
      "learning_rate": 2e-06,
      "loss": 10.8068,
      "mean_token_accuracy": 0.0,
      "num_tokens": 9336.0,
      "step": 5
    },
    {
      "entropy": 10.691903591156006,
      "epoch": 0.0006697699340276615,
      "grad_norm": 11.0625,
      "learning_rate": 4.5e-06,
      "loss": 10.7633,
      "mean_token_accuracy": 8.298755274154246e-05,
      "num_tokens": 18837.0,
      "step": 10
    },
    {
      "entropy": 10.690729331970214,
      "epoch": 0.0010046549010414923,
      "grad_norm": 8.1875,
      "learning_rate": 7e-06,
      "loss": 10.5956,
      "mean_token_accuracy": 0.024797544209286572,
      "num_tokens": 28150.0,
      "step": 15
    },
    {
      "entropy": 10.671813011169434,
      "epoch": 0.001339539868055323,
      "grad_norm": 5.9375,
      "learning_rate": 9.5e-06,
      "loss": 10.3354,
      "mean_token_accuracy": 0.03901095166802406,
      "num_tokens": 37469.0,
      "step": 20
    },
    {
      "entropy": 10.546046257019043,
      "epoch": 0.0016744248350691537,
      "grad_norm": 4.25,
      "learning_rate": 1.2e-05,
      "loss": 10.1607,
      "mean_token_accuracy": 0.04424795918166637,
      "num_tokens": 47955.0,
      "step": 25
    },
    {
      "entropy": 10.492891216278077,
      "epoch": 0.0020093098020829846,
      "grad_norm": 3.03125,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.0269,
      "mean_token_accuracy": 0.042472783103585245,
      "num_tokens": 58421.0,
      "step": 30
    },
    {
      "entropy": 10.515302562713623,
      "epoch": 0.0023441947690968153,
      "grad_norm": 2.640625,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 9.9959,
      "mean_token_accuracy": 0.043728823959827426,
      "num_tokens": 69338.0,
      "step": 35
    },
    {
      "entropy": 10.499641704559327,
      "epoch": 0.002679079736110646,
      "grad_norm": 2.640625,
      "learning_rate": 1.95e-05,
      "loss": 9.9476,
      "mean_token_accuracy": 0.038607921078801156,
      "num_tokens": 78964.0,
      "step": 40
    },
    {
      "entropy": 10.51818790435791,
      "epoch": 0.0030139647031244767,
      "grad_norm": 2.25,
      "learning_rate": 2.2e-05,
      "loss": 9.8996,
      "mean_token_accuracy": 0.04694473557174206,
      "num_tokens": 90312.0,
      "step": 45
    },
    {
      "entropy": 10.432500553131103,
      "epoch": 0.0033488496701383074,
      "grad_norm": 2.484375,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.8796,
      "mean_token_accuracy": 0.04102238342165947,
      "num_tokens": 99706.0,
      "step": 50
    },
    {
      "entropy": 10.511144351959228,
      "epoch": 0.003683734637152138,
      "grad_norm": 2.484375,
      "learning_rate": 2.7e-05,
      "loss": 9.7999,
      "mean_token_accuracy": 0.05329355746507645,
      "num_tokens": 109737.0,
      "step": 55
    },
    {
      "entropy": 10.39623498916626,
      "epoch": 0.004018619604165969,
      "grad_norm": 1.9375,
      "learning_rate": 2.95e-05,
      "loss": 9.7913,
      "mean_token_accuracy": 0.05464463010430336,
      "num_tokens": 119471.0,
      "step": 60
    },
    {
      "entropy": 10.326496887207032,
      "epoch": 0.0043535045711798,
      "grad_norm": 1.8671875,
      "learning_rate": 3.2e-05,
      "loss": 9.7391,
      "mean_token_accuracy": 0.05522452406585217,
      "num_tokens": 130844.0,
      "step": 65
    },
    {
      "entropy": 10.346483325958252,
      "epoch": 0.0046883895381936306,
      "grad_norm": 1.65625,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.6734,
      "mean_token_accuracy": 0.05130590014159679,
      "num_tokens": 141266.0,
      "step": 70
    },
    {
      "entropy": 10.326040744781494,
      "epoch": 0.005023274505207461,
      "grad_norm": 1.6796875,
      "learning_rate": 3.7e-05,
      "loss": 9.5759,
      "mean_token_accuracy": 0.053099123388528825,
      "num_tokens": 152222.0,
      "step": 75
    },
    {
      "entropy": 10.252498531341553,
      "epoch": 0.005358159472221292,
      "grad_norm": 1.625,
      "learning_rate": 3.95e-05,
      "loss": 9.4974,
      "mean_token_accuracy": 0.057894356176257135,
      "num_tokens": 162931.0,
      "step": 80
    },
    {
      "entropy": 10.303020477294922,
      "epoch": 0.005693044439235123,
      "grad_norm": 1.6171875,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.459,
      "mean_token_accuracy": 0.0599411066621542,
      "num_tokens": 172587.0,
      "step": 85
    },
    {
      "entropy": 10.248745536804199,
      "epoch": 0.006027929406248953,
      "grad_norm": 1.5703125,
      "learning_rate": 4.45e-05,
      "loss": 9.3844,
      "mean_token_accuracy": 0.06057738587260246,
      "num_tokens": 181877.0,
      "step": 90
    },
    {
      "entropy": 10.166729736328126,
      "epoch": 0.006362814373262784,
      "grad_norm": 1.4375,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.3398,
      "mean_token_accuracy": 0.06227475889027119,
      "num_tokens": 192196.0,
      "step": 95
    },
    {
      "entropy": 10.17726526260376,
      "epoch": 0.006697699340276615,
      "grad_norm": 1.53125,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.2079,
      "mean_token_accuracy": 0.06091195158660412,
      "num_tokens": 201009.0,
      "step": 100
    },
    {
      "entropy": 10.157612991333007,
      "epoch": 0.007032584307290445,
      "grad_norm": 1.515625,
      "learning_rate": 5.2e-05,
      "loss": 9.1724,
      "mean_token_accuracy": 0.06171322390437126,
      "num_tokens": 209066.0,
      "step": 105
    },
    {
      "entropy": 10.070836448669434,
      "epoch": 0.007367469274304276,
      "grad_norm": 1.3671875,
      "learning_rate": 5.45e-05,
      "loss": 9.066,
      "mean_token_accuracy": 0.0612255796790123,
      "num_tokens": 218721.0,
      "step": 110
    },
    {
      "entropy": 10.060692882537841,
      "epoch": 0.007702354241318108,
      "grad_norm": 1.765625,
      "learning_rate": 5.7e-05,
      "loss": 9.0073,
      "mean_token_accuracy": 0.06116213873028755,
      "num_tokens": 228511.0,
      "step": 115
    },
    {
      "entropy": 9.899711894989014,
      "epoch": 0.008037239208331938,
      "grad_norm": 1.4140625,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.9327,
      "mean_token_accuracy": 0.06402782052755356,
      "num_tokens": 237097.0,
      "step": 120
    },
    {
      "entropy": 9.886706161499024,
      "epoch": 0.008372124175345769,
      "grad_norm": 1.46875,
      "learning_rate": 6.2e-05,
      "loss": 8.8186,
      "mean_token_accuracy": 0.06528197042644024,
      "num_tokens": 246013.0,
      "step": 125
    },
    {
      "entropy": 9.725101757049561,
      "epoch": 0.0087070091423596,
      "grad_norm": 1.2734375,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.7975,
      "mean_token_accuracy": 0.06460081338882447,
      "num_tokens": 255741.0,
      "step": 130
    },
    {
      "entropy": 9.658132648468017,
      "epoch": 0.00904189410937343,
      "grad_norm": 1.1015625,
      "learning_rate": 6.7e-05,
      "loss": 8.6777,
      "mean_token_accuracy": 0.06698540337383747,
      "num_tokens": 265877.0,
      "step": 135
    },
    {
      "entropy": 9.571129512786865,
      "epoch": 0.009376779076387261,
      "grad_norm": 1.828125,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.6745,
      "mean_token_accuracy": 0.06440977044403554,
      "num_tokens": 275631.0,
      "step": 140
    },
    {
      "entropy": 9.40587911605835,
      "epoch": 0.009711664043401092,
      "grad_norm": 1.3984375,
      "learning_rate": 7.2e-05,
      "loss": 8.6249,
      "mean_token_accuracy": 0.06725125461816787,
      "num_tokens": 286584.0,
      "step": 145
    },
    {
      "entropy": 9.319342231750488,
      "epoch": 0.010046549010414923,
      "grad_norm": 1.2265625,
      "learning_rate": 7.45e-05,
      "loss": 8.6003,
      "mean_token_accuracy": 0.06583596840500831,
      "num_tokens": 296903.0,
      "step": 150
    },
    {
      "entropy": 9.266637802124023,
      "epoch": 0.010381433977428753,
      "grad_norm": 1.0234375,
      "learning_rate": 7.7e-05,
      "loss": 8.5182,
      "mean_token_accuracy": 0.06669672690331936,
      "num_tokens": 306940.0,
      "step": 155
    },
    {
      "entropy": 9.121322727203369,
      "epoch": 0.010716318944442584,
      "grad_norm": 1.09375,
      "learning_rate": 7.950000000000001e-05,
      "loss": 8.5713,
      "mean_token_accuracy": 0.05945994444191456,
      "num_tokens": 317344.0,
      "step": 160
    },
    {
      "entropy": 9.144170761108398,
      "epoch": 0.011051203911456415,
      "grad_norm": 1.234375,
      "learning_rate": 8.2e-05,
      "loss": 8.4318,
      "mean_token_accuracy": 0.06840684190392494,
      "num_tokens": 326076.0,
      "step": 165
    },
    {
      "entropy": 9.001359462738037,
      "epoch": 0.011386088878470245,
      "grad_norm": 1.09375,
      "learning_rate": 8.450000000000001e-05,
      "loss": 8.4173,
      "mean_token_accuracy": 0.06733019910752773,
      "num_tokens": 334645.0,
      "step": 170
    },
    {
      "entropy": 8.87405948638916,
      "epoch": 0.011720973845484076,
      "grad_norm": 1.34375,
      "learning_rate": 8.7e-05,
      "loss": 8.457,
      "mean_token_accuracy": 0.06887451484799385,
      "num_tokens": 343784.0,
      "step": 175
    },
    {
      "entropy": 8.911943817138672,
      "epoch": 0.012055858812497907,
      "grad_norm": 1.109375,
      "learning_rate": 8.95e-05,
      "loss": 8.4102,
      "mean_token_accuracy": 0.06883096322417259,
      "num_tokens": 353230.0,
      "step": 180
    },
    {
      "entropy": 8.82119836807251,
      "epoch": 0.012390743779511737,
      "grad_norm": 1.3671875,
      "learning_rate": 9.2e-05,
      "loss": 8.3994,
      "mean_token_accuracy": 0.072719157487154,
      "num_tokens": 362406.0,
      "step": 185
    },
    {
      "entropy": 8.854674816131592,
      "epoch": 0.012725628746525568,
      "grad_norm": 1.109375,
      "learning_rate": 9.45e-05,
      "loss": 8.3534,
      "mean_token_accuracy": 0.07635012455284595,
      "num_tokens": 372418.0,
      "step": 190
    },
    {
      "entropy": 8.726993560791016,
      "epoch": 0.013060513713539399,
      "grad_norm": 1.5078125,
      "learning_rate": 9.7e-05,
      "loss": 8.3505,
      "mean_token_accuracy": 0.06566916257143021,
      "num_tokens": 381089.0,
      "step": 195
    },
    {
      "entropy": 8.8147479057312,
      "epoch": 0.01339539868055323,
      "grad_norm": 1.0703125,
      "learning_rate": 9.95e-05,
      "loss": 8.4281,
      "mean_token_accuracy": 0.06762638352811337,
      "num_tokens": 391801.0,
      "step": 200
    },
    {
      "entropy": 8.720731449127197,
      "epoch": 0.01373028364756706,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000102,
      "loss": 8.3811,
      "mean_token_accuracy": 0.06919934712350369,
      "num_tokens": 402234.0,
      "step": 205
    },
    {
      "entropy": 8.717157459259033,
      "epoch": 0.01406516861458089,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00010449999999999999,
      "loss": 8.3737,
      "mean_token_accuracy": 0.06955731771886349,
      "num_tokens": 411665.0,
      "step": 210
    },
    {
      "entropy": 8.639013862609863,
      "epoch": 0.014400053581594721,
      "grad_norm": 1.03125,
      "learning_rate": 0.000107,
      "loss": 8.3918,
      "mean_token_accuracy": 0.07283912301063537,
      "num_tokens": 421989.0,
      "step": 215
    },
    {
      "entropy": 8.687447452545166,
      "epoch": 0.014734938548608552,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001095,
      "loss": 8.26,
      "mean_token_accuracy": 0.07393333688378334,
      "num_tokens": 431258.0,
      "step": 220
    },
    {
      "entropy": 8.666478729248047,
      "epoch": 0.015069823515622383,
      "grad_norm": 0.94921875,
      "learning_rate": 0.000112,
      "loss": 8.3854,
      "mean_token_accuracy": 0.06810639537870884,
      "num_tokens": 441920.0,
      "step": 225
    },
    {
      "entropy": 8.616051387786865,
      "epoch": 0.015404708482636215,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0001145,
      "loss": 8.2877,
      "mean_token_accuracy": 0.07677756659686566,
      "num_tokens": 451460.0,
      "step": 230
    },
    {
      "entropy": 8.660403823852539,
      "epoch": 0.015739593449650046,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00011700000000000001,
      "loss": 8.2816,
      "mean_token_accuracy": 0.06862423159182071,
      "num_tokens": 461612.0,
      "step": 235
    },
    {
      "entropy": 8.5113130569458,
      "epoch": 0.016074478416663877,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00011949999999999999,
      "loss": 8.3412,
      "mean_token_accuracy": 0.073118532076478,
      "num_tokens": 472706.0,
      "step": 240
    },
    {
      "entropy": 8.678703594207764,
      "epoch": 0.016409363383677707,
      "grad_norm": 1.25,
      "learning_rate": 0.000122,
      "loss": 8.3613,
      "mean_token_accuracy": 0.06715637855231762,
      "num_tokens": 482709.0,
      "step": 245
    },
    {
      "entropy": 8.611370754241943,
      "epoch": 0.016744248350691538,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001245,
      "loss": 8.3567,
      "mean_token_accuracy": 0.06981554329395294,
      "num_tokens": 492566.0,
      "step": 250
    },
    {
      "entropy": 8.615898895263673,
      "epoch": 0.01707913331770537,
      "grad_norm": 0.9921875,
      "learning_rate": 0.000127,
      "loss": 8.2729,
      "mean_token_accuracy": 0.07023949660360813,
      "num_tokens": 502912.0,
      "step": 255
    },
    {
      "entropy": 8.566937446594238,
      "epoch": 0.0174140182847192,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001295,
      "loss": 8.3078,
      "mean_token_accuracy": 0.06855836510658264,
      "num_tokens": 513000.0,
      "step": 260
    },
    {
      "entropy": 8.519447898864746,
      "epoch": 0.01774890325173303,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000132,
      "loss": 8.2477,
      "mean_token_accuracy": 0.07444192729890346,
      "num_tokens": 523345.0,
      "step": 265
    },
    {
      "entropy": 8.572467136383057,
      "epoch": 0.01808378821874686,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00013450000000000002,
      "loss": 8.2611,
      "mean_token_accuracy": 0.0756999634206295,
      "num_tokens": 532121.0,
      "step": 270
    },
    {
      "entropy": 8.594667053222656,
      "epoch": 0.01841867318576069,
      "grad_norm": 1.15625,
      "learning_rate": 0.00013700000000000002,
      "loss": 8.3316,
      "mean_token_accuracy": 0.0701010324060917,
      "num_tokens": 541895.0,
      "step": 275
    },
    {
      "entropy": 8.535953617095947,
      "epoch": 0.018753558152774522,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0001395,
      "loss": 8.2591,
      "mean_token_accuracy": 0.07193546742200851,
      "num_tokens": 552144.0,
      "step": 280
    },
    {
      "entropy": 8.536889743804931,
      "epoch": 0.019088443119788353,
      "grad_norm": 1.109375,
      "learning_rate": 0.00014199999999999998,
      "loss": 8.2719,
      "mean_token_accuracy": 0.0705334760248661,
      "num_tokens": 562336.0,
      "step": 285
    },
    {
      "entropy": 8.450227165222168,
      "epoch": 0.019423328086802184,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0001445,
      "loss": 8.218,
      "mean_token_accuracy": 0.08047289326786995,
      "num_tokens": 572020.0,
      "step": 290
    },
    {
      "entropy": 8.459360504150391,
      "epoch": 0.019758213053816014,
      "grad_norm": 1.109375,
      "learning_rate": 0.000147,
      "loss": 8.2205,
      "mean_token_accuracy": 0.07739253155887127,
      "num_tokens": 581418.0,
      "step": 295
    },
    {
      "entropy": 8.509122371673584,
      "epoch": 0.020093098020829845,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0001495,
      "loss": 8.2136,
      "mean_token_accuracy": 0.07784642353653907,
      "num_tokens": 590716.0,
      "step": 300
    },
    {
      "entropy": 8.435087871551513,
      "epoch": 0.020427982987843676,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000152,
      "loss": 8.0997,
      "mean_token_accuracy": 0.08416117876768112,
      "num_tokens": 599337.0,
      "step": 305
    },
    {
      "entropy": 8.536314296722413,
      "epoch": 0.020762867954857506,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00015450000000000001,
      "loss": 8.2036,
      "mean_token_accuracy": 0.07563756629824639,
      "num_tokens": 609600.0,
      "step": 310
    },
    {
      "entropy": 8.392087364196778,
      "epoch": 0.021097752921871337,
      "grad_norm": 1.140625,
      "learning_rate": 0.000157,
      "loss": 8.0995,
      "mean_token_accuracy": 0.08121243491768837,
      "num_tokens": 619121.0,
      "step": 315
    },
    {
      "entropy": 8.443190097808838,
      "epoch": 0.021432637888885168,
      "grad_norm": 1.25,
      "learning_rate": 0.0001595,
      "loss": 8.1407,
      "mean_token_accuracy": 0.07933203130960464,
      "num_tokens": 628741.0,
      "step": 320
    },
    {
      "entropy": 8.41283540725708,
      "epoch": 0.021767522855899,
      "grad_norm": 1.2109375,
      "learning_rate": 0.000162,
      "loss": 8.2179,
      "mean_token_accuracy": 0.07958511859178544,
      "num_tokens": 637422.0,
      "step": 325
    },
    {
      "entropy": 8.518020153045654,
      "epoch": 0.02210240782291283,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00016450000000000001,
      "loss": 8.241,
      "mean_token_accuracy": 0.07295509129762649,
      "num_tokens": 646541.0,
      "step": 330
    },
    {
      "entropy": 8.41762990951538,
      "epoch": 0.02243729278992666,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00016700000000000002,
      "loss": 8.1165,
      "mean_token_accuracy": 0.07536539658904076,
      "num_tokens": 656771.0,
      "step": 335
    },
    {
      "entropy": 8.371623420715332,
      "epoch": 0.02277217775694049,
      "grad_norm": 1.171875,
      "learning_rate": 0.00016950000000000003,
      "loss": 8.1849,
      "mean_token_accuracy": 0.08415180742740631,
      "num_tokens": 666273.0,
      "step": 340
    },
    {
      "entropy": 8.425055980682373,
      "epoch": 0.02310706272395432,
      "grad_norm": 1.140625,
      "learning_rate": 0.00017199999999999998,
      "loss": 8.0979,
      "mean_token_accuracy": 0.08333219587802887,
      "num_tokens": 676473.0,
      "step": 345
    },
    {
      "entropy": 8.404365062713623,
      "epoch": 0.023441947690968152,
      "grad_norm": 1.234375,
      "learning_rate": 0.00017449999999999999,
      "loss": 8.1858,
      "mean_token_accuracy": 0.07680471651256085,
      "num_tokens": 686180.0,
      "step": 350
    },
    {
      "entropy": 8.4719557762146,
      "epoch": 0.023776832657981983,
      "grad_norm": 1.34375,
      "learning_rate": 0.000177,
      "loss": 8.1134,
      "mean_token_accuracy": 0.08005921840667725,
      "num_tokens": 695372.0,
      "step": 355
    },
    {
      "entropy": 8.450627994537353,
      "epoch": 0.024111717624995813,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0001795,
      "loss": 8.202,
      "mean_token_accuracy": 0.07519823238253594,
      "num_tokens": 706182.0,
      "step": 360
    },
    {
      "entropy": 8.343936538696289,
      "epoch": 0.024446602592009644,
      "grad_norm": 1.125,
      "learning_rate": 0.000182,
      "loss": 8.0952,
      "mean_token_accuracy": 0.08658334016799926,
      "num_tokens": 715601.0,
      "step": 365
    },
    {
      "entropy": 8.429388046264648,
      "epoch": 0.024781487559023475,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0001845,
      "loss": 8.1968,
      "mean_token_accuracy": 0.0763387732207775,
      "num_tokens": 724919.0,
      "step": 370
    },
    {
      "entropy": 8.473710441589356,
      "epoch": 0.025116372526037305,
      "grad_norm": 1.15625,
      "learning_rate": 0.000187,
      "loss": 8.0876,
      "mean_token_accuracy": 0.0873330645263195,
      "num_tokens": 733214.0,
      "step": 375
    },
    {
      "entropy": 8.316863822937012,
      "epoch": 0.025451257493051136,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0001895,
      "loss": 8.1652,
      "mean_token_accuracy": 0.08139564543962478,
      "num_tokens": 743230.0,
      "step": 380
    },
    {
      "entropy": 8.357980537414551,
      "epoch": 0.025786142460064967,
      "grad_norm": 1.078125,
      "learning_rate": 0.000192,
      "loss": 8.1065,
      "mean_token_accuracy": 0.08524948060512542,
      "num_tokens": 753175.0,
      "step": 385
    },
    {
      "entropy": 8.391164398193359,
      "epoch": 0.026121027427078797,
      "grad_norm": 1.28125,
      "learning_rate": 0.0001945,
      "loss": 8.0377,
      "mean_token_accuracy": 0.08165767267346383,
      "num_tokens": 763168.0,
      "step": 390
    },
    {
      "entropy": 8.216160011291503,
      "epoch": 0.026455912394092628,
      "grad_norm": 0.96875,
      "learning_rate": 0.00019700000000000002,
      "loss": 8.1343,
      "mean_token_accuracy": 0.078636434674263,
      "num_tokens": 773477.0,
      "step": 395
    },
    {
      "entropy": 8.393694496154785,
      "epoch": 0.02679079736110646,
      "grad_norm": 1.2890625,
      "learning_rate": 0.00019950000000000002,
      "loss": 8.1224,
      "mean_token_accuracy": 0.07863845936954021,
      "num_tokens": 782351.0,
      "step": 400
    },
    {
      "entropy": 8.31768217086792,
      "epoch": 0.02712568232812029,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000202,
      "loss": 8.0673,
      "mean_token_accuracy": 0.08583122119307518,
      "num_tokens": 792179.0,
      "step": 405
    },
    {
      "entropy": 8.328267860412598,
      "epoch": 0.02746056729513412,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00020449999999999998,
      "loss": 8.0654,
      "mean_token_accuracy": 0.08307353034615517,
      "num_tokens": 802243.0,
      "step": 410
    },
    {
      "entropy": 8.319038486480713,
      "epoch": 0.02779545226214795,
      "grad_norm": 1.171875,
      "learning_rate": 0.000207,
      "loss": 8.0445,
      "mean_token_accuracy": 0.08092730417847634,
      "num_tokens": 812069.0,
      "step": 415
    },
    {
      "entropy": 8.23815851211548,
      "epoch": 0.02813033722916178,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0002095,
      "loss": 8.033,
      "mean_token_accuracy": 0.08340432792901993,
      "num_tokens": 821608.0,
      "step": 420
    },
    {
      "entropy": 8.37398271560669,
      "epoch": 0.028465222196175612,
      "grad_norm": 0.99609375,
      "learning_rate": 0.000212,
      "loss": 8.1558,
      "mean_token_accuracy": 0.08059651404619217,
      "num_tokens": 831677.0,
      "step": 425
    },
    {
      "entropy": 8.293180561065673,
      "epoch": 0.028800107163189443,
      "grad_norm": 1.234375,
      "learning_rate": 0.0002145,
      "loss": 8.01,
      "mean_token_accuracy": 0.07991714328527451,
      "num_tokens": 840087.0,
      "step": 430
    },
    {
      "entropy": 8.316405105590821,
      "epoch": 0.029134992130203274,
      "grad_norm": 1.296875,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.9978,
      "mean_token_accuracy": 0.0796763051301241,
      "num_tokens": 850516.0,
      "step": 435
    },
    {
      "entropy": 8.243999099731445,
      "epoch": 0.029469877097217104,
      "grad_norm": 1.1875,
      "learning_rate": 0.0002195,
      "loss": 8.0956,
      "mean_token_accuracy": 0.0780600018799305,
      "num_tokens": 860921.0,
      "step": 440
    },
    {
      "entropy": 8.28464241027832,
      "epoch": 0.029804762064230935,
      "grad_norm": 1.125,
      "learning_rate": 0.000222,
      "loss": 8.0153,
      "mean_token_accuracy": 0.07812976092100143,
      "num_tokens": 871450.0,
      "step": 445
    },
    {
      "entropy": 8.157562828063964,
      "epoch": 0.030139647031244766,
      "grad_norm": 1.15625,
      "learning_rate": 0.0002245,
      "loss": 7.9852,
      "mean_token_accuracy": 0.08450187891721725,
      "num_tokens": 880241.0,
      "step": 450
    },
    {
      "entropy": 8.207323741912841,
      "epoch": 0.030474531998258596,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00022700000000000002,
      "loss": 8.0256,
      "mean_token_accuracy": 0.08647001013159752,
      "num_tokens": 890156.0,
      "step": 455
    },
    {
      "entropy": 8.360474586486816,
      "epoch": 0.03080941696527243,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00022950000000000002,
      "loss": 8.0575,
      "mean_token_accuracy": 0.08064594492316246,
      "num_tokens": 899718.0,
      "step": 460
    },
    {
      "entropy": 8.222134017944336,
      "epoch": 0.03114430193228626,
      "grad_norm": 1.296875,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.9727,
      "mean_token_accuracy": 0.08729927316308021,
      "num_tokens": 908461.0,
      "step": 465
    },
    {
      "entropy": 8.155136108398438,
      "epoch": 0.03147918689930009,
      "grad_norm": 1.1875,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.9164,
      "mean_token_accuracy": 0.09267583414912224,
      "num_tokens": 917418.0,
      "step": 470
    },
    {
      "entropy": 8.265091705322266,
      "epoch": 0.03181407186631392,
      "grad_norm": 1.03125,
      "learning_rate": 0.000237,
      "loss": 8.005,
      "mean_token_accuracy": 0.08021655455231666,
      "num_tokens": 927495.0,
      "step": 475
    },
    {
      "entropy": 8.160477352142333,
      "epoch": 0.03214895683332775,
      "grad_norm": 1.109375,
      "learning_rate": 0.0002395,
      "loss": 8.026,
      "mean_token_accuracy": 0.08863752149045467,
      "num_tokens": 937510.0,
      "step": 480
    },
    {
      "entropy": 8.250221538543702,
      "epoch": 0.032483841800341584,
      "grad_norm": 1.078125,
      "learning_rate": 0.000242,
      "loss": 7.9761,
      "mean_token_accuracy": 0.08346135094761849,
      "num_tokens": 948171.0,
      "step": 485
    },
    {
      "entropy": 8.188724803924561,
      "epoch": 0.032818726767355415,
      "grad_norm": 1.265625,
      "learning_rate": 0.0002445,
      "loss": 7.9508,
      "mean_token_accuracy": 0.08198098838329315,
      "num_tokens": 956506.0,
      "step": 490
    },
    {
      "entropy": 8.181706428527832,
      "epoch": 0.033153611734369245,
      "grad_norm": 1.296875,
      "learning_rate": 0.000247,
      "loss": 7.9687,
      "mean_token_accuracy": 0.08284949623048306,
      "num_tokens": 966063.0,
      "step": 495
    },
    {
      "entropy": 8.172396850585937,
      "epoch": 0.033488496701383076,
      "grad_norm": 1.0625,
      "learning_rate": 0.0002495,
      "loss": 7.9673,
      "mean_token_accuracy": 0.08704572841525078,
      "num_tokens": 976793.0,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 4000,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1525586190336000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}