{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5042864346949067,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.691978168487548,
      "epoch": 0.005042864346949067,
      "grad_norm": 12.8125,
      "learning_rate": 2e-06,
      "loss": 10.8351,
      "mean_token_accuracy": 0.0,
      "num_tokens": 11445.0,
      "step": 5
    },
    {
      "entropy": 10.691911983489991,
      "epoch": 0.010085728693898134,
      "grad_norm": 13.1875,
      "learning_rate": 4.5e-06,
      "loss": 10.7658,
      "mean_token_accuracy": 0.0,
      "num_tokens": 22095.0,
      "step": 10
    },
    {
      "entropy": 10.691094779968262,
      "epoch": 0.015128593040847202,
      "grad_norm": 8.875,
      "learning_rate": 7e-06,
      "loss": 10.5389,
      "mean_token_accuracy": 0.01894580915104598,
      "num_tokens": 33847.0,
      "step": 15
    },
    {
      "entropy": 10.681381797790527,
      "epoch": 0.020171457387796268,
      "grad_norm": 5.8125,
      "learning_rate": 9.5e-06,
      "loss": 10.2545,
      "mean_token_accuracy": 0.036951894313097,
      "num_tokens": 44495.0,
      "step": 20
    },
    {
      "entropy": 10.639113235473634,
      "epoch": 0.025214321734745335,
      "grad_norm": 4.0,
      "learning_rate": 1.2e-05,
      "loss": 9.9884,
      "mean_token_accuracy": 0.038632451370358464,
      "num_tokens": 55298.0,
      "step": 25
    },
    {
      "entropy": 10.603860855102539,
      "epoch": 0.030257186081694403,
      "grad_norm": 3.21875,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 9.8047,
      "mean_token_accuracy": 0.04054084848612547,
      "num_tokens": 66391.0,
      "step": 30
    },
    {
      "entropy": 10.591868877410889,
      "epoch": 0.03530005042864347,
      "grad_norm": 2.65625,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 9.698,
      "mean_token_accuracy": 0.04207097329199314,
      "num_tokens": 77624.0,
      "step": 35
    },
    {
      "entropy": 10.584535121917725,
      "epoch": 0.040342914775592535,
      "grad_norm": 2.546875,
      "learning_rate": 1.95e-05,
      "loss": 9.678,
      "mean_token_accuracy": 0.044261034950613974,
      "num_tokens": 89426.0,
      "step": 40
    },
    {
      "entropy": 10.562712478637696,
      "epoch": 0.0453857791225416,
      "grad_norm": 2.4375,
      "learning_rate": 2.2e-05,
      "loss": 9.6315,
      "mean_token_accuracy": 0.04177976287901401,
      "num_tokens": 100252.0,
      "step": 45
    },
    {
      "entropy": 10.594598770141602,
      "epoch": 0.05042864346949067,
      "grad_norm": 2.5,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.6087,
      "mean_token_accuracy": 0.03483491390943527,
      "num_tokens": 110578.0,
      "step": 50
    },
    {
      "entropy": 10.596640396118165,
      "epoch": 0.05547150781643974,
      "grad_norm": 2.3125,
      "learning_rate": 2.7e-05,
      "loss": 9.5875,
      "mean_token_accuracy": 0.03704058732837438,
      "num_tokens": 121631.0,
      "step": 55
    },
    {
      "entropy": 10.56342658996582,
      "epoch": 0.060514372163388806,
      "grad_norm": 2.21875,
      "learning_rate": 2.95e-05,
      "loss": 9.466,
      "mean_token_accuracy": 0.05011895261704922,
      "num_tokens": 134254.0,
      "step": 60
    },
    {
      "entropy": 10.496850776672364,
      "epoch": 0.06555723651033787,
      "grad_norm": 2.0625,
      "learning_rate": 3.2e-05,
      "loss": 9.4511,
      "mean_token_accuracy": 0.04732503369450569,
      "num_tokens": 144928.0,
      "step": 65
    },
    {
      "entropy": 10.411289405822753,
      "epoch": 0.07060010085728693,
      "grad_norm": 2.234375,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.2913,
      "mean_token_accuracy": 0.04968489818274975,
      "num_tokens": 155518.0,
      "step": 70
    },
    {
      "entropy": 10.424620437622071,
      "epoch": 0.07564296520423601,
      "grad_norm": 2.359375,
      "learning_rate": 3.7e-05,
      "loss": 9.1933,
      "mean_token_accuracy": 0.05173242129385471,
      "num_tokens": 165850.0,
      "step": 75
    },
    {
      "entropy": 10.444954109191894,
      "epoch": 0.08068582955118507,
      "grad_norm": 2.265625,
      "learning_rate": 3.95e-05,
      "loss": 9.1766,
      "mean_token_accuracy": 0.04967899359762669,
      "num_tokens": 176787.0,
      "step": 80
    },
    {
      "entropy": 10.427998161315918,
      "epoch": 0.08572869389813415,
      "grad_norm": 2.015625,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.0647,
      "mean_token_accuracy": 0.04877705723047256,
      "num_tokens": 188345.0,
      "step": 85
    },
    {
      "entropy": 10.456082916259765,
      "epoch": 0.0907715582450832,
      "grad_norm": 2.25,
      "learning_rate": 4.45e-05,
      "loss": 9.0037,
      "mean_token_accuracy": 0.04692690074443817,
      "num_tokens": 199315.0,
      "step": 90
    },
    {
      "entropy": 10.339052677154541,
      "epoch": 0.09581442259203228,
      "grad_norm": 2.15625,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 8.8109,
      "mean_token_accuracy": 0.05837383419275284,
      "num_tokens": 209627.0,
      "step": 95
    },
    {
      "entropy": 10.241901874542236,
      "epoch": 0.10085728693898134,
      "grad_norm": 2.0625,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 8.7101,
      "mean_token_accuracy": 0.0651729203760624,
      "num_tokens": 220872.0,
      "step": 100
    },
    {
      "entropy": 10.15722131729126,
      "epoch": 0.1059001512859304,
      "grad_norm": 2.1875,
      "learning_rate": 5.2e-05,
      "loss": 8.5657,
      "mean_token_accuracy": 0.06282355673611165,
      "num_tokens": 233272.0,
      "step": 105
    },
    {
      "entropy": 10.10981206893921,
      "epoch": 0.11094301563287948,
      "grad_norm": 2.140625,
      "learning_rate": 5.45e-05,
      "loss": 8.4933,
      "mean_token_accuracy": 0.06420289240777492,
      "num_tokens": 243529.0,
      "step": 110
    },
    {
      "entropy": 10.059538745880127,
      "epoch": 0.11598587997982854,
      "grad_norm": 1.734375,
      "learning_rate": 5.7e-05,
      "loss": 8.3948,
      "mean_token_accuracy": 0.05781678333878517,
      "num_tokens": 254942.0,
      "step": 115
    },
    {
      "entropy": 9.973904132843018,
      "epoch": 0.12102874432677761,
      "grad_norm": 1.7734375,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.2972,
      "mean_token_accuracy": 0.06580851301550865,
      "num_tokens": 266552.0,
      "step": 120
    },
    {
      "entropy": 9.73906192779541,
      "epoch": 0.1260716086737267,
      "grad_norm": 1.5625,
      "learning_rate": 6.2e-05,
      "loss": 8.1497,
      "mean_token_accuracy": 0.06753928288817405,
      "num_tokens": 277906.0,
      "step": 125
    },
    {
      "entropy": 9.731296634674072,
      "epoch": 0.13111447302067575,
      "grad_norm": 1.53125,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.0309,
      "mean_token_accuracy": 0.06970244199037552,
      "num_tokens": 289079.0,
      "step": 130
    },
    {
      "entropy": 9.517922592163085,
      "epoch": 0.1361573373676248,
      "grad_norm": 1.4140625,
      "learning_rate": 6.7e-05,
      "loss": 7.9818,
      "mean_token_accuracy": 0.06449979990720749,
      "num_tokens": 300107.0,
      "step": 135
    },
    {
      "entropy": 9.309736728668213,
      "epoch": 0.14120020171457387,
      "grad_norm": 1.640625,
      "learning_rate": 6.950000000000001e-05,
      "loss": 7.8019,
      "mean_token_accuracy": 0.06583718433976174,
      "num_tokens": 310779.0,
      "step": 140
    },
    {
      "entropy": 9.122577667236328,
      "epoch": 0.14624306606152296,
      "grad_norm": 1.359375,
      "learning_rate": 7.2e-05,
      "loss": 7.7857,
      "mean_token_accuracy": 0.0686340156942606,
      "num_tokens": 323478.0,
      "step": 145
    },
    {
      "entropy": 8.875781536102295,
      "epoch": 0.15128593040847202,
      "grad_norm": 1.3515625,
      "learning_rate": 7.45e-05,
      "loss": 7.662,
      "mean_token_accuracy": 0.07218315117061139,
      "num_tokens": 335255.0,
      "step": 150
    },
    {
      "entropy": 8.774222087860107,
      "epoch": 0.15632879475542108,
      "grad_norm": 1.40625,
      "learning_rate": 7.7e-05,
      "loss": 7.5823,
      "mean_token_accuracy": 0.07090610340237617,
      "num_tokens": 344824.0,
      "step": 155
    },
    {
      "entropy": 8.562890911102295,
      "epoch": 0.16137165910237014,
      "grad_norm": 1.34375,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.5779,
      "mean_token_accuracy": 0.06917917579412461,
      "num_tokens": 356283.0,
      "step": 160
    },
    {
      "entropy": 8.52785816192627,
      "epoch": 0.1664145234493192,
      "grad_norm": 1.2265625,
      "learning_rate": 8.2e-05,
      "loss": 7.5443,
      "mean_token_accuracy": 0.07162331864237785,
      "num_tokens": 368098.0,
      "step": 165
    },
    {
      "entropy": 8.293674755096436,
      "epoch": 0.1714573877962683,
      "grad_norm": 1.3828125,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.4885,
      "mean_token_accuracy": 0.07210201621055604,
      "num_tokens": 380948.0,
      "step": 170
    },
    {
      "entropy": 8.206411838531494,
      "epoch": 0.17650025214321735,
      "grad_norm": 1.6953125,
      "learning_rate": 8.7e-05,
      "loss": 7.4311,
      "mean_token_accuracy": 0.07011085003614426,
      "num_tokens": 390392.0,
      "step": 175
    },
    {
      "entropy": 8.1397864818573,
      "epoch": 0.1815431164901664,
      "grad_norm": 1.3125,
      "learning_rate": 8.95e-05,
      "loss": 7.4686,
      "mean_token_accuracy": 0.07223408669233322,
      "num_tokens": 400328.0,
      "step": 180
    },
    {
      "entropy": 8.180228519439698,
      "epoch": 0.18658598083711547,
      "grad_norm": 1.375,
      "learning_rate": 9.2e-05,
      "loss": 7.4529,
      "mean_token_accuracy": 0.07169274277985097,
      "num_tokens": 410909.0,
      "step": 185
    },
    {
      "entropy": 8.057634353637695,
      "epoch": 0.19162884518406456,
      "grad_norm": 1.2421875,
      "learning_rate": 9.45e-05,
      "loss": 7.4423,
      "mean_token_accuracy": 0.07097707688808441,
      "num_tokens": 422726.0,
      "step": 190
    },
    {
      "entropy": 7.975717973709107,
      "epoch": 0.19667170953101362,
      "grad_norm": 1.46875,
      "learning_rate": 9.7e-05,
      "loss": 7.3252,
      "mean_token_accuracy": 0.07745771333575249,
      "num_tokens": 433376.0,
      "step": 195
    },
    {
      "entropy": 7.932044219970703,
      "epoch": 0.20171457387796268,
      "grad_norm": 1.4375,
      "learning_rate": 9.95e-05,
      "loss": 7.4045,
      "mean_token_accuracy": 0.06969214789569378,
      "num_tokens": 443940.0,
      "step": 200
    },
    {
      "entropy": 7.979291915893555,
      "epoch": 0.20675743822491174,
      "grad_norm": 1.3046875,
      "learning_rate": 0.000102,
      "loss": 7.2735,
      "mean_token_accuracy": 0.07643608674407006,
      "num_tokens": 455016.0,
      "step": 205
    },
    {
      "entropy": 7.8824797630310055,
      "epoch": 0.2118003025718608,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.3292,
      "mean_token_accuracy": 0.07622824087738991,
      "num_tokens": 466380.0,
      "step": 210
    },
    {
      "entropy": 7.831804847717285,
      "epoch": 0.2168431669188099,
      "grad_norm": 1.5078125,
      "learning_rate": 0.000107,
      "loss": 7.1783,
      "mean_token_accuracy": 0.08013702630996704,
      "num_tokens": 476915.0,
      "step": 215
    },
    {
      "entropy": 7.80485315322876,
      "epoch": 0.22188603126575895,
      "grad_norm": 1.28125,
      "learning_rate": 0.0001095,
      "loss": 7.2725,
      "mean_token_accuracy": 0.0824611522257328,
      "num_tokens": 488924.0,
      "step": 220
    },
    {
      "entropy": 7.809728908538818,
      "epoch": 0.22692889561270801,
      "grad_norm": 1.203125,
      "learning_rate": 0.000112,
      "loss": 7.2162,
      "mean_token_accuracy": 0.07684922367334365,
      "num_tokens": 498965.0,
      "step": 225
    },
    {
      "entropy": 7.819616842269897,
      "epoch": 0.23197175995965708,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0001145,
      "loss": 7.235,
      "mean_token_accuracy": 0.0765653271228075,
      "num_tokens": 509755.0,
      "step": 230
    },
    {
      "entropy": 7.771869659423828,
      "epoch": 0.23701462430660616,
      "grad_norm": 1.34375,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.2042,
      "mean_token_accuracy": 0.0763448379933834,
      "num_tokens": 521221.0,
      "step": 235
    },
    {
      "entropy": 7.7396564960479735,
      "epoch": 0.24205748865355523,
      "grad_norm": 1.3515625,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.3172,
      "mean_token_accuracy": 0.07263238392770291,
      "num_tokens": 533595.0,
      "step": 240
    },
    {
      "entropy": 7.770624494552612,
      "epoch": 0.24710035300050429,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000122,
      "loss": 7.2608,
      "mean_token_accuracy": 0.07456091418862343,
      "num_tokens": 543672.0,
      "step": 245
    },
    {
      "entropy": 7.743118524551392,
      "epoch": 0.2521432173474534,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001245,
      "loss": 7.127,
      "mean_token_accuracy": 0.0765512753278017,
      "num_tokens": 554906.0,
      "step": 250
    },
    {
      "entropy": 7.675862503051758,
      "epoch": 0.25718608169440244,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000127,
      "loss": 7.2259,
      "mean_token_accuracy": 0.0814048271626234,
      "num_tokens": 566419.0,
      "step": 255
    },
    {
      "entropy": 7.71265172958374,
      "epoch": 0.2622289460413515,
      "grad_norm": 1.3125,
      "learning_rate": 0.0001295,
      "loss": 7.1691,
      "mean_token_accuracy": 0.07766851969063282,
      "num_tokens": 578848.0,
      "step": 260
    },
    {
      "entropy": 7.5628129005432125,
      "epoch": 0.26727181038830056,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000132,
      "loss": 7.1197,
      "mean_token_accuracy": 0.07973449081182479,
      "num_tokens": 590601.0,
      "step": 265
    },
    {
      "entropy": 7.681688404083252,
      "epoch": 0.2723146747352496,
      "grad_norm": 1.2265625,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.1774,
      "mean_token_accuracy": 0.07436439543962478,
      "num_tokens": 602021.0,
      "step": 270
    },
    {
      "entropy": 7.616954660415649,
      "epoch": 0.2773575390821987,
      "grad_norm": 1.15625,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.2583,
      "mean_token_accuracy": 0.07453522607684135,
      "num_tokens": 613966.0,
      "step": 275
    },
    {
      "entropy": 7.710917282104492,
      "epoch": 0.28240040342914774,
      "grad_norm": 1.265625,
      "learning_rate": 0.0001395,
      "loss": 7.0984,
      "mean_token_accuracy": 0.07756517678499222,
      "num_tokens": 624851.0,
      "step": 280
    },
    {
      "entropy": 7.546781873703003,
      "epoch": 0.2874432677760968,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.1915,
      "mean_token_accuracy": 0.07566507011651993,
      "num_tokens": 635580.0,
      "step": 285
    },
    {
      "entropy": 7.662804460525512,
      "epoch": 0.2924861321230459,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0001445,
      "loss": 7.2473,
      "mean_token_accuracy": 0.07517430521547794,
      "num_tokens": 646927.0,
      "step": 290
    },
    {
      "entropy": 7.587956047058105,
      "epoch": 0.297528996469995,
      "grad_norm": 1.2578125,
      "learning_rate": 0.000147,
      "loss": 7.0551,
      "mean_token_accuracy": 0.08050617948174477,
      "num_tokens": 658116.0,
      "step": 295
    },
    {
      "entropy": 7.642880249023437,
      "epoch": 0.30257186081694404,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0001495,
      "loss": 7.0584,
      "mean_token_accuracy": 0.07990356534719467,
      "num_tokens": 669054.0,
      "step": 300
    },
    {
      "entropy": 7.5717206478118895,
      "epoch": 0.3076147251638931,
      "grad_norm": 1.328125,
      "learning_rate": 0.000152,
      "loss": 7.1075,
      "mean_token_accuracy": 0.0826454609632492,
      "num_tokens": 680439.0,
      "step": 305
    },
    {
      "entropy": 7.453785753250122,
      "epoch": 0.31265758951084216,
      "grad_norm": 1.375,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.0661,
      "mean_token_accuracy": 0.08129210546612739,
      "num_tokens": 690909.0,
      "step": 310
    },
    {
      "entropy": 7.5011971950531,
      "epoch": 0.3177004538577912,
      "grad_norm": 1.25,
      "learning_rate": 0.000157,
      "loss": 7.048,
      "mean_token_accuracy": 0.07969367988407612,
      "num_tokens": 701744.0,
      "step": 315
    },
    {
      "entropy": 7.467720365524292,
      "epoch": 0.3227433182047403,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0001595,
      "loss": 7.0817,
      "mean_token_accuracy": 0.08535065315663815,
      "num_tokens": 712268.0,
      "step": 320
    },
    {
      "entropy": 7.59487681388855,
      "epoch": 0.32778618255168934,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000162,
      "loss": 7.1079,
      "mean_token_accuracy": 0.07844235375523567,
      "num_tokens": 722978.0,
      "step": 325
    },
    {
      "entropy": 7.482430076599121,
      "epoch": 0.3328290468986384,
      "grad_norm": 1.234375,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.1011,
      "mean_token_accuracy": 0.08162309601902962,
      "num_tokens": 734278.0,
      "step": 330
    },
    {
      "entropy": 7.5462571144104,
      "epoch": 0.3378719112455875,
      "grad_norm": 1.0625,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.0141,
      "mean_token_accuracy": 0.0776023030281067,
      "num_tokens": 746109.0,
      "step": 335
    },
    {
      "entropy": 7.374982213973999,
      "epoch": 0.3429147755925366,
      "grad_norm": 1.46875,
      "learning_rate": 0.00016950000000000003,
      "loss": 6.9356,
      "mean_token_accuracy": 0.08509711548686028,
      "num_tokens": 757519.0,
      "step": 340
    },
    {
      "entropy": 7.443374300003052,
      "epoch": 0.34795763993948564,
      "grad_norm": 1.421875,
      "learning_rate": 0.00017199999999999998,
      "loss": 6.9149,
      "mean_token_accuracy": 0.08727683797478676,
      "num_tokens": 767665.0,
      "step": 345
    },
    {
      "entropy": 7.435840845108032,
      "epoch": 0.3530005042864347,
      "grad_norm": 1.203125,
      "learning_rate": 0.00017449999999999999,
      "loss": 6.9537,
      "mean_token_accuracy": 0.08823386654257774,
      "num_tokens": 778880.0,
      "step": 350
    },
    {
      "entropy": 7.310178327560425,
      "epoch": 0.35804336863338376,
      "grad_norm": 1.0234375,
      "learning_rate": 0.000177,
      "loss": 6.9559,
      "mean_token_accuracy": 0.09013235792517663,
      "num_tokens": 790360.0,
      "step": 355
    },
    {
      "entropy": 7.387903451919556,
      "epoch": 0.3630862329803328,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0001795,
      "loss": 6.9182,
      "mean_token_accuracy": 0.08709552362561226,
      "num_tokens": 800889.0,
      "step": 360
    },
    {
      "entropy": 7.419098663330078,
      "epoch": 0.3681290973272819,
      "grad_norm": 1.3046875,
      "learning_rate": 0.000182,
      "loss": 6.9171,
      "mean_token_accuracy": 0.08571921288967133,
      "num_tokens": 811414.0,
      "step": 365
    },
    {
      "entropy": 7.240619897842407,
      "epoch": 0.37317196167423095,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0001845,
      "loss": 6.9305,
      "mean_token_accuracy": 0.0850242905318737,
      "num_tokens": 822822.0,
      "step": 370
    },
    {
      "entropy": 7.271744012832642,
      "epoch": 0.37821482602118,
      "grad_norm": 1.234375,
      "learning_rate": 0.000187,
      "loss": 6.829,
      "mean_token_accuracy": 0.09168825820088386,
      "num_tokens": 833145.0,
      "step": 375
    },
    {
      "entropy": 7.2786908626556395,
      "epoch": 0.3832576903681291,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0001895,
      "loss": 6.9405,
      "mean_token_accuracy": 0.0836037501692772,
      "num_tokens": 844015.0,
      "step": 380
    },
    {
      "entropy": 7.349726581573487,
      "epoch": 0.3883005547150782,
      "grad_norm": 1.03125,
      "learning_rate": 0.000192,
      "loss": 6.8706,
      "mean_token_accuracy": 0.08842808604240418,
      "num_tokens": 855806.0,
      "step": 385
    },
    {
      "entropy": 7.209612941741943,
      "epoch": 0.39334341906202724,
      "grad_norm": 1.125,
      "learning_rate": 0.0001945,
      "loss": 6.7935,
      "mean_token_accuracy": 0.08768922984600067,
      "num_tokens": 865750.0,
      "step": 390
    },
    {
      "entropy": 7.334837818145752,
      "epoch": 0.3983862834089763,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00019700000000000002,
      "loss": 6.9248,
      "mean_token_accuracy": 0.08573650568723679,
      "num_tokens": 877630.0,
      "step": 395
    },
    {
      "entropy": 7.157733392715454,
      "epoch": 0.40342914775592537,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00019950000000000002,
      "loss": 6.8054,
      "mean_token_accuracy": 0.09393974989652634,
      "num_tokens": 888667.0,
      "step": 400
    },
    {
      "entropy": 7.3036473274230955,
      "epoch": 0.4084720121028744,
      "grad_norm": 1.09375,
      "learning_rate": 0.000202,
      "loss": 6.8838,
      "mean_token_accuracy": 0.08392557948827743,
      "num_tokens": 900989.0,
      "step": 405
    },
    {
      "entropy": 7.183315801620483,
      "epoch": 0.4135148764498235,
      "grad_norm": 1.125,
      "learning_rate": 0.00020449999999999998,
      "loss": 6.7766,
      "mean_token_accuracy": 0.08522050082683563,
      "num_tokens": 911479.0,
      "step": 410
    },
    {
      "entropy": 7.263188695907592,
      "epoch": 0.41855774079677255,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000207,
      "loss": 6.7898,
      "mean_token_accuracy": 0.08779488950967788,
      "num_tokens": 922434.0,
      "step": 415
    },
    {
      "entropy": 7.146833324432373,
      "epoch": 0.4236006051437216,
      "grad_norm": 1.3046875,
      "learning_rate": 0.0002095,
      "loss": 6.7957,
      "mean_token_accuracy": 0.08833592608571053,
      "num_tokens": 933405.0,
      "step": 420
    },
    {
      "entropy": 7.173463964462281,
      "epoch": 0.4286434694906707,
      "grad_norm": 1.328125,
      "learning_rate": 0.000212,
      "loss": 6.7996,
      "mean_token_accuracy": 0.0885507345199585,
      "num_tokens": 943567.0,
      "step": 425
    },
    {
      "entropy": 7.099128866195679,
      "epoch": 0.4336863338376198,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0002145,
      "loss": 6.8177,
      "mean_token_accuracy": 0.08491698876023293,
      "num_tokens": 955123.0,
      "step": 430
    },
    {
      "entropy": 7.277088403701782,
      "epoch": 0.43872919818456885,
      "grad_norm": 1.296875,
      "learning_rate": 0.00021700000000000002,
      "loss": 6.8615,
      "mean_token_accuracy": 0.08992773070931434,
      "num_tokens": 965565.0,
      "step": 435
    },
    {
      "entropy": 7.159026861190796,
      "epoch": 0.4437720625315179,
      "grad_norm": 1.125,
      "learning_rate": 0.0002195,
      "loss": 6.78,
      "mean_token_accuracy": 0.08791229128837585,
      "num_tokens": 977101.0,
      "step": 440
    },
    {
      "entropy": 7.1419289112091064,
      "epoch": 0.44881492687846697,
      "grad_norm": 1.078125,
      "learning_rate": 0.000222,
      "loss": 6.8314,
      "mean_token_accuracy": 0.08858354166150093,
      "num_tokens": 987445.0,
      "step": 445
    },
    {
      "entropy": 7.118024682998657,
      "epoch": 0.45385779122541603,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0002245,
      "loss": 6.7034,
      "mean_token_accuracy": 0.09504426047205924,
      "num_tokens": 999379.0,
      "step": 450
    },
    {
      "entropy": 6.998180723190307,
      "epoch": 0.4589006555723651,
      "grad_norm": 1.171875,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.6412,
      "mean_token_accuracy": 0.09876157343387604,
      "num_tokens": 1010744.0,
      "step": 455
    },
    {
      "entropy": 7.0912974834442135,
      "epoch": 0.46394351991931415,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.7395,
      "mean_token_accuracy": 0.0892062947154045,
      "num_tokens": 1021808.0,
      "step": 460
    },
    {
      "entropy": 7.138762521743774,
      "epoch": 0.4689863842662632,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.787,
      "mean_token_accuracy": 0.0881411112844944,
      "num_tokens": 1033694.0,
      "step": 465
    },
    {
      "entropy": 7.05295991897583,
      "epoch": 0.47402924861321233,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00023449999999999998,
      "loss": 6.7531,
      "mean_token_accuracy": 0.09112738594412803,
      "num_tokens": 1044690.0,
      "step": 470
    },
    {
      "entropy": 7.110706329345703,
      "epoch": 0.4790721129601614,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000237,
      "loss": 6.7543,
      "mean_token_accuracy": 0.0913363330066204,
      "num_tokens": 1055557.0,
      "step": 475
    },
    {
      "entropy": 7.020756387710572,
      "epoch": 0.48411497730711045,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0002395,
      "loss": 6.6926,
      "mean_token_accuracy": 0.09522736445069313,
      "num_tokens": 1067304.0,
      "step": 480
    },
    {
      "entropy": 7.031440687179566,
      "epoch": 0.4891578416540595,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000242,
      "loss": 6.7153,
      "mean_token_accuracy": 0.09247291311621667,
      "num_tokens": 1078955.0,
      "step": 485
    },
    {
      "entropy": 7.019560098648071,
      "epoch": 0.49420070600100857,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0002445,
      "loss": 6.7608,
      "mean_token_accuracy": 0.09506335482001305,
      "num_tokens": 1091405.0,
      "step": 490
    },
    {
      "entropy": 7.067246627807617,
      "epoch": 0.49924357034795763,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000247,
      "loss": 6.7344,
      "mean_token_accuracy": 0.09412561133503913,
      "num_tokens": 1103227.0,
      "step": 495
    },
    {
      "entropy": 7.013670969009399,
      "epoch": 0.5042864346949067,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0002495,
      "loss": 6.6734,
      "mean_token_accuracy": 0.09890775382518768,
      "num_tokens": 1114485.0,
      "step": 500
    },
    {
      "epoch": 0.5042864346949067,
      "eval_entropy": 6.978830953894074,
      "eval_loss": 6.783904552459717,
      "eval_mean_token_accuracy": 0.09532982510995622,
      "eval_num_tokens": 1114485.0,
      "eval_runtime": 2.7002,
      "eval_samples_per_second": 1162.13,
      "eval_steps_per_second": 145.544,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 9910,
  "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": 1868172705792000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}