{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.8,
  "eval_steps": 100,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.142920307815075,
      "epoch": 0.016,
      "grad_norm": 290.0,
      "learning_rate": 6.000000000000001e-07,
      "loss": 42.6658,
      "mean_token_accuracy": 0.5620782226324081,
      "num_tokens": 195524.0,
      "step": 10
    },
    {
      "entropy": 1.148210159689188,
      "epoch": 0.032,
      "grad_norm": 239.0,
      "learning_rate": 1.2666666666666669e-06,
      "loss": 41.9984,
      "mean_token_accuracy": 0.5613080382347106,
      "num_tokens": 390903.0,
      "step": 20
    },
    {
      "entropy": 1.1933260083198547,
      "epoch": 0.048,
      "grad_norm": 249.0,
      "learning_rate": 1.9333333333333336e-06,
      "loss": 40.6208,
      "mean_token_accuracy": 0.5657517908141017,
      "num_tokens": 589868.0,
      "step": 30
    },
    {
      "entropy": 1.2957281917333603,
      "epoch": 0.064,
      "grad_norm": 139.0,
      "learning_rate": 2.6e-06,
      "loss": 37.9032,
      "mean_token_accuracy": 0.5714796105399728,
      "num_tokens": 791190.0,
      "step": 40
    },
    {
      "entropy": 1.5075685508549213,
      "epoch": 0.08,
      "grad_norm": 94.0,
      "learning_rate": 3.266666666666667e-06,
      "loss": 35.7561,
      "mean_token_accuracy": 0.5766569443047047,
      "num_tokens": 989860.0,
      "step": 50
    },
    {
      "entropy": 1.7984249681234359,
      "epoch": 0.096,
      "grad_norm": 50.75,
      "learning_rate": 3.9333333333333335e-06,
      "loss": 33.4379,
      "mean_token_accuracy": 0.5814697606489062,
      "num_tokens": 1181777.0,
      "step": 60
    },
    {
      "entropy": 1.8387351341545581,
      "epoch": 0.112,
      "grad_norm": 43.0,
      "learning_rate": 4.600000000000001e-06,
      "loss": 30.4219,
      "mean_token_accuracy": 0.5971228444948793,
      "num_tokens": 1385513.0,
      "step": 70
    },
    {
      "entropy": 1.7275233700871468,
      "epoch": 0.128,
      "grad_norm": 33.5,
      "learning_rate": 5.2666666666666665e-06,
      "loss": 28.4703,
      "mean_token_accuracy": 0.6095364252105355,
      "num_tokens": 1582368.0,
      "step": 80
    },
    {
      "entropy": 1.7214979872107505,
      "epoch": 0.144,
      "grad_norm": 27.0,
      "learning_rate": 5.933333333333335e-06,
      "loss": 26.677,
      "mean_token_accuracy": 0.6243448719382286,
      "num_tokens": 1773764.0,
      "step": 90
    },
    {
      "entropy": 1.6311134904623033,
      "epoch": 0.16,
      "grad_norm": 22.0,
      "learning_rate": 6.600000000000001e-06,
      "loss": 25.7683,
      "mean_token_accuracy": 0.6301404371857643,
      "num_tokens": 1970077.0,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_biology_entropy": 1.5580159120559693,
      "eval_biology_loss": 1.5081593990325928,
      "eval_biology_mean_token_accuracy": 0.6457349667549134,
      "eval_biology_num_tokens": 1970077.0,
      "eval_biology_runtime": 48.7413,
      "eval_biology_samples_per_second": 10.258,
      "eval_biology_steps_per_second": 2.565,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_chemistry_entropy": 1.206756212234497,
      "eval_chemistry_loss": 1.1218774318695068,
      "eval_chemistry_mean_token_accuracy": 0.7205783066749573,
      "eval_chemistry_num_tokens": 1970077.0,
      "eval_chemistry_runtime": 60.3159,
      "eval_chemistry_samples_per_second": 8.29,
      "eval_chemistry_steps_per_second": 2.072,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_math_entropy": 0.9672308325767517,
      "eval_math_loss": 1.159799337387085,
      "eval_math_mean_token_accuracy": 0.7189845342636109,
      "eval_math_num_tokens": 1970077.0,
      "eval_math_runtime": 61.8237,
      "eval_math_samples_per_second": 8.088,
      "eval_math_steps_per_second": 2.022,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_physics_entropy": 1.1670387201309205,
      "eval_physics_loss": 1.1291608810424805,
      "eval_physics_mean_token_accuracy": 0.7211072521209717,
      "eval_physics_num_tokens": 1970077.0,
      "eval_physics_runtime": 70.4586,
      "eval_physics_samples_per_second": 7.096,
      "eval_physics_steps_per_second": 1.774,
      "step": 100
    },
    {
      "entropy": 1.5482715763151647,
      "epoch": 0.176,
      "grad_norm": 21.125,
      "learning_rate": 7.266666666666668e-06,
      "loss": 24.5868,
      "mean_token_accuracy": 0.6385629490017891,
      "num_tokens": 2168354.0,
      "step": 110
    },
    {
      "entropy": 1.5266574397683144,
      "epoch": 0.192,
      "grad_norm": 22.875,
      "learning_rate": 7.933333333333334e-06,
      "loss": 24.2707,
      "mean_token_accuracy": 0.6432460084557533,
      "num_tokens": 2365822.0,
      "step": 120
    },
    {
      "entropy": 1.5192069873213767,
      "epoch": 0.208,
      "grad_norm": 20.875,
      "learning_rate": 8.6e-06,
      "loss": 24.1355,
      "mean_token_accuracy": 0.6436416517943144,
      "num_tokens": 2558762.0,
      "step": 130
    },
    {
      "entropy": 1.4698147468268872,
      "epoch": 0.224,
      "grad_norm": 20.125,
      "learning_rate": 9.266666666666667e-06,
      "loss": 23.5154,
      "mean_token_accuracy": 0.6499760080128908,
      "num_tokens": 2755347.0,
      "step": 140
    },
    {
      "entropy": 1.4506230603903532,
      "epoch": 0.24,
      "grad_norm": 19.625,
      "learning_rate": 9.933333333333334e-06,
      "loss": 23.2013,
      "mean_token_accuracy": 0.6523264441639185,
      "num_tokens": 2947346.0,
      "step": 150
    },
    {
      "entropy": 1.4590953961014748,
      "epoch": 0.256,
      "grad_norm": 18.5,
      "learning_rate": 1.0600000000000002e-05,
      "loss": 23.3227,
      "mean_token_accuracy": 0.6508617259562015,
      "num_tokens": 3139957.0,
      "step": 160
    },
    {
      "entropy": 1.419396448880434,
      "epoch": 0.272,
      "grad_norm": 19.75,
      "learning_rate": 1.1266666666666668e-05,
      "loss": 22.7352,
      "mean_token_accuracy": 0.6572458431124687,
      "num_tokens": 3335951.0,
      "step": 170
    },
    {
      "entropy": 1.4005608204752207,
      "epoch": 0.288,
      "grad_norm": 19.75,
      "learning_rate": 1.1933333333333335e-05,
      "loss": 22.3969,
      "mean_token_accuracy": 0.6585959013551473,
      "num_tokens": 3539731.0,
      "step": 180
    },
    {
      "entropy": 1.391934547200799,
      "epoch": 0.304,
      "grad_norm": 18.75,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 22.31,
      "mean_token_accuracy": 0.6621056370437145,
      "num_tokens": 3733488.0,
      "step": 190
    },
    {
      "entropy": 1.4028674490749835,
      "epoch": 0.32,
      "grad_norm": 22.25,
      "learning_rate": 1.3266666666666668e-05,
      "loss": 22.5559,
      "mean_token_accuracy": 0.6576981086283922,
      "num_tokens": 3920545.0,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_biology_entropy": 1.3209806289672852,
      "eval_biology_loss": 1.338399887084961,
      "eval_biology_mean_token_accuracy": 0.6720403518676757,
      "eval_biology_num_tokens": 3920545.0,
      "eval_biology_runtime": 48.5853,
      "eval_biology_samples_per_second": 10.291,
      "eval_biology_steps_per_second": 2.573,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_chemistry_entropy": 1.0033348879814148,
      "eval_chemistry_loss": 0.9935092926025391,
      "eval_chemistry_mean_token_accuracy": 0.7448974308967591,
      "eval_chemistry_num_tokens": 3920545.0,
      "eval_chemistry_runtime": 60.24,
      "eval_chemistry_samples_per_second": 8.3,
      "eval_chemistry_steps_per_second": 2.075,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_math_entropy": 0.8341804294586181,
      "eval_math_loss": 1.0635857582092285,
      "eval_math_mean_token_accuracy": 0.7432106451988221,
      "eval_math_num_tokens": 3920545.0,
      "eval_math_runtime": 61.8174,
      "eval_math_samples_per_second": 8.088,
      "eval_math_steps_per_second": 2.022,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_physics_entropy": 0.9652358031272888,
      "eval_physics_loss": 0.9950281977653503,
      "eval_physics_mean_token_accuracy": 0.7510108857154846,
      "eval_physics_num_tokens": 3920545.0,
      "eval_physics_runtime": 70.411,
      "eval_physics_samples_per_second": 7.101,
      "eval_physics_steps_per_second": 1.775,
      "step": 200
    },
    {
      "entropy": 1.3548175282776356,
      "epoch": 0.336,
      "grad_norm": 19.625,
      "learning_rate": 1.3933333333333334e-05,
      "loss": 21.7763,
      "mean_token_accuracy": 0.6656343434005976,
      "num_tokens": 4114077.0,
      "step": 210
    },
    {
      "entropy": 1.3656601022928954,
      "epoch": 0.352,
      "grad_norm": 20.625,
      "learning_rate": 1.46e-05,
      "loss": 22.0972,
      "mean_token_accuracy": 0.6638848338276148,
      "num_tokens": 4306949.0,
      "step": 220
    },
    {
      "entropy": 1.3525194190442562,
      "epoch": 0.368,
      "grad_norm": 18.125,
      "learning_rate": 1.5266666666666667e-05,
      "loss": 21.7293,
      "mean_token_accuracy": 0.6680811226367951,
      "num_tokens": 4504001.0,
      "step": 230
    },
    {
      "entropy": 1.3454820621758699,
      "epoch": 0.384,
      "grad_norm": 21.25,
      "learning_rate": 1.5933333333333336e-05,
      "loss": 21.7032,
      "mean_token_accuracy": 0.6671383358538151,
      "num_tokens": 4693812.0,
      "step": 240
    },
    {
      "entropy": 1.3525703553110362,
      "epoch": 0.4,
      "grad_norm": 17.5,
      "learning_rate": 1.66e-05,
      "loss": 21.7856,
      "mean_token_accuracy": 0.666401931643486,
      "num_tokens": 4887094.0,
      "step": 250
    },
    {
      "entropy": 1.351718918606639,
      "epoch": 0.416,
      "grad_norm": 19.0,
      "learning_rate": 1.726666666666667e-05,
      "loss": 21.9058,
      "mean_token_accuracy": 0.6651136819273233,
      "num_tokens": 5085369.0,
      "step": 260
    },
    {
      "entropy": 1.3526419658213853,
      "epoch": 0.432,
      "grad_norm": 20.875,
      "learning_rate": 1.7933333333333333e-05,
      "loss": 21.7813,
      "mean_token_accuracy": 0.6668458927422762,
      "num_tokens": 5271275.0,
      "step": 270
    },
    {
      "entropy": 1.3480545241385697,
      "epoch": 0.448,
      "grad_norm": 22.875,
      "learning_rate": 1.86e-05,
      "loss": 21.627,
      "mean_token_accuracy": 0.6677324704825878,
      "num_tokens": 5460559.0,
      "step": 280
    },
    {
      "entropy": 1.301166184991598,
      "epoch": 0.464,
      "grad_norm": 21.25,
      "learning_rate": 1.926666666666667e-05,
      "loss": 20.889,
      "mean_token_accuracy": 0.676617132872343,
      "num_tokens": 5653809.0,
      "step": 290
    },
    {
      "entropy": 1.318466317281127,
      "epoch": 0.48,
      "grad_norm": 17.125,
      "learning_rate": 1.9933333333333334e-05,
      "loss": 21.2936,
      "mean_token_accuracy": 0.6712827417999506,
      "num_tokens": 5850176.0,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_biology_entropy": 1.2827796216011047,
      "eval_biology_loss": 1.275201678276062,
      "eval_biology_mean_token_accuracy": 0.6830832781791687,
      "eval_biology_num_tokens": 5850176.0,
      "eval_biology_runtime": 48.4915,
      "eval_biology_samples_per_second": 10.311,
      "eval_biology_steps_per_second": 2.578,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_chemistry_entropy": 0.983495129108429,
      "eval_chemistry_loss": 0.9488818645477295,
      "eval_chemistry_mean_token_accuracy": 0.7523409638404847,
      "eval_chemistry_num_tokens": 5850176.0,
      "eval_chemistry_runtime": 60.1707,
      "eval_chemistry_samples_per_second": 8.31,
      "eval_chemistry_steps_per_second": 2.077,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_math_entropy": 0.8216862387657166,
      "eval_math_loss": 1.0297818183898926,
      "eval_math_mean_token_accuracy": 0.7488151121139527,
      "eval_math_num_tokens": 5850176.0,
      "eval_math_runtime": 61.6905,
      "eval_math_samples_per_second": 8.105,
      "eval_math_steps_per_second": 2.026,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_physics_entropy": 0.9433758721351624,
      "eval_physics_loss": 0.9520999193191528,
      "eval_physics_mean_token_accuracy": 0.7585058889389038,
      "eval_physics_num_tokens": 5850176.0,
      "eval_physics_runtime": 70.301,
      "eval_physics_samples_per_second": 7.112,
      "eval_physics_steps_per_second": 1.778,
      "step": 300
    },
    {
      "entropy": 1.2579400472342968,
      "epoch": 0.496,
      "grad_norm": 17.75,
      "learning_rate": 1.9933333333333334e-05,
      "loss": 20.2011,
      "mean_token_accuracy": 0.6842056062072516,
      "num_tokens": 6046503.0,
      "step": 310
    },
    {
      "entropy": 1.3082518883049488,
      "epoch": 0.512,
      "grad_norm": 18.125,
      "learning_rate": 1.985925925925926e-05,
      "loss": 21.0658,
      "mean_token_accuracy": 0.6749501373618841,
      "num_tokens": 6240456.0,
      "step": 320
    },
    {
      "entropy": 1.3003981616348028,
      "epoch": 0.528,
      "grad_norm": 18.125,
      "learning_rate": 1.9785185185185187e-05,
      "loss": 20.9809,
      "mean_token_accuracy": 0.6757604543119669,
      "num_tokens": 6430555.0,
      "step": 330
    },
    {
      "entropy": 1.2986273631453513,
      "epoch": 0.544,
      "grad_norm": 17.0,
      "learning_rate": 1.971111111111111e-05,
      "loss": 20.8809,
      "mean_token_accuracy": 0.6782271713018417,
      "num_tokens": 6626006.0,
      "step": 340
    },
    {
      "entropy": 1.284830729290843,
      "epoch": 0.56,
      "grad_norm": 17.25,
      "learning_rate": 1.963703703703704e-05,
      "loss": 20.8197,
      "mean_token_accuracy": 0.6767117112874985,
      "num_tokens": 6820754.0,
      "step": 350
    },
    {
      "entropy": 1.2683125745505095,
      "epoch": 0.576,
      "grad_norm": 17.0,
      "learning_rate": 1.9562962962962964e-05,
      "loss": 20.4541,
      "mean_token_accuracy": 0.6809794403612613,
      "num_tokens": 7021844.0,
      "step": 360
    },
    {
      "entropy": 1.2863252360373736,
      "epoch": 0.592,
      "grad_norm": 18.875,
      "learning_rate": 1.948888888888889e-05,
      "loss": 20.8043,
      "mean_token_accuracy": 0.676701345667243,
      "num_tokens": 7213951.0,
      "step": 370
    },
    {
      "entropy": 1.2630502216517925,
      "epoch": 0.608,
      "grad_norm": 18.75,
      "learning_rate": 1.9414814814814817e-05,
      "loss": 20.4041,
      "mean_token_accuracy": 0.6803740747272968,
      "num_tokens": 7416773.0,
      "step": 380
    },
    {
      "entropy": 1.2804703898727894,
      "epoch": 0.624,
      "grad_norm": 19.25,
      "learning_rate": 1.9340740740740743e-05,
      "loss": 20.6218,
      "mean_token_accuracy": 0.6788272958248853,
      "num_tokens": 7612843.0,
      "step": 390
    },
    {
      "entropy": 1.2843346055597067,
      "epoch": 0.64,
      "grad_norm": 18.0,
      "learning_rate": 1.926666666666667e-05,
      "loss": 20.7171,
      "mean_token_accuracy": 0.6782444745302201,
      "num_tokens": 7801633.0,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_biology_entropy": 1.226506398677826,
      "eval_biology_loss": 1.2382104396820068,
      "eval_biology_mean_token_accuracy": 0.6894095778465271,
      "eval_biology_num_tokens": 7801633.0,
      "eval_biology_runtime": 48.5507,
      "eval_biology_samples_per_second": 10.299,
      "eval_biology_steps_per_second": 2.575,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_chemistry_entropy": 0.9317227191925049,
      "eval_chemistry_loss": 0.9207452535629272,
      "eval_chemistry_mean_token_accuracy": 0.7581370029449462,
      "eval_chemistry_num_tokens": 7801633.0,
      "eval_chemistry_runtime": 60.2113,
      "eval_chemistry_samples_per_second": 8.304,
      "eval_chemistry_steps_per_second": 2.076,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_math_entropy": 0.7863595089912414,
      "eval_math_loss": 1.010460376739502,
      "eval_math_mean_token_accuracy": 0.7535392093658447,
      "eval_math_num_tokens": 7801633.0,
      "eval_math_runtime": 61.807,
      "eval_math_samples_per_second": 8.09,
      "eval_math_steps_per_second": 2.022,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_physics_entropy": 0.8958085932731629,
      "eval_physics_loss": 0.9257401823997498,
      "eval_physics_mean_token_accuracy": 0.7637984156608582,
      "eval_physics_num_tokens": 7801633.0,
      "eval_physics_runtime": 70.3663,
      "eval_physics_samples_per_second": 7.106,
      "eval_physics_steps_per_second": 1.776,
      "step": 400
    },
    {
      "entropy": 1.278659427165985,
      "epoch": 0.656,
      "grad_norm": 18.25,
      "learning_rate": 1.9192592592592593e-05,
      "loss": 20.6682,
      "mean_token_accuracy": 0.6772829819470644,
      "num_tokens": 7995843.0,
      "step": 410
    },
    {
      "entropy": 1.2931427203118802,
      "epoch": 0.672,
      "grad_norm": 18.625,
      "learning_rate": 1.911851851851852e-05,
      "loss": 20.8656,
      "mean_token_accuracy": 0.6753748003393412,
      "num_tokens": 8183103.0,
      "step": 420
    },
    {
      "entropy": 1.2739692747592926,
      "epoch": 0.688,
      "grad_norm": 16.75,
      "learning_rate": 1.9044444444444446e-05,
      "loss": 20.5407,
      "mean_token_accuracy": 0.6812681049108505,
      "num_tokens": 8385976.0,
      "step": 430
    },
    {
      "entropy": 1.2659825466573238,
      "epoch": 0.704,
      "grad_norm": 16.25,
      "learning_rate": 1.8970370370370372e-05,
      "loss": 20.4243,
      "mean_token_accuracy": 0.6820976916700602,
      "num_tokens": 8578431.0,
      "step": 440
    },
    {
      "entropy": 1.220404140278697,
      "epoch": 0.72,
      "grad_norm": 16.75,
      "learning_rate": 1.8896296296296295e-05,
      "loss": 19.6546,
      "mean_token_accuracy": 0.6908745598047972,
      "num_tokens": 8781342.0,
      "step": 450
    },
    {
      "entropy": 1.2406103231012822,
      "epoch": 0.736,
      "grad_norm": 16.75,
      "learning_rate": 1.8822222222222225e-05,
      "loss": 19.9745,
      "mean_token_accuracy": 0.6853331789374352,
      "num_tokens": 8977918.0,
      "step": 460
    },
    {
      "entropy": 1.2618801843374967,
      "epoch": 0.752,
      "grad_norm": 17.125,
      "learning_rate": 1.874814814814815e-05,
      "loss": 20.4041,
      "mean_token_accuracy": 0.6825968738645315,
      "num_tokens": 9169322.0,
      "step": 470
    },
    {
      "entropy": 1.2232345014810562,
      "epoch": 0.768,
      "grad_norm": 19.25,
      "learning_rate": 1.8674074074074075e-05,
      "loss": 19.7045,
      "mean_token_accuracy": 0.6888250291347504,
      "num_tokens": 9368141.0,
      "step": 480
    },
    {
      "entropy": 1.25159954726696,
      "epoch": 0.784,
      "grad_norm": 18.25,
      "learning_rate": 1.86e-05,
      "loss": 20.2036,
      "mean_token_accuracy": 0.6849453710019588,
      "num_tokens": 9565236.0,
      "step": 490
    },
    {
      "entropy": 1.264250884205103,
      "epoch": 0.8,
      "grad_norm": 19.25,
      "learning_rate": 1.8525925925925928e-05,
      "loss": 20.5299,
      "mean_token_accuracy": 0.6811827480792999,
      "num_tokens": 9761227.0,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_biology_entropy": 1.2163097896575927,
      "eval_biology_loss": 1.2177292108535767,
      "eval_biology_mean_token_accuracy": 0.6932459664344788,
      "eval_biology_num_tokens": 9761227.0,
      "eval_biology_runtime": 48.5438,
      "eval_biology_samples_per_second": 10.3,
      "eval_biology_steps_per_second": 2.575,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_chemistry_entropy": 0.9239063205718994,
      "eval_chemistry_loss": 0.9047155380249023,
      "eval_chemistry_mean_token_accuracy": 0.761792631149292,
      "eval_chemistry_num_tokens": 9761227.0,
      "eval_chemistry_runtime": 59.9546,
      "eval_chemistry_samples_per_second": 8.34,
      "eval_chemistry_steps_per_second": 2.085,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_math_entropy": 0.7864464523792267,
      "eval_math_loss": 0.9939978122711182,
      "eval_math_mean_token_accuracy": 0.7574145245552063,
      "eval_math_num_tokens": 9761227.0,
      "eval_math_runtime": 61.7812,
      "eval_math_samples_per_second": 8.093,
      "eval_math_steps_per_second": 2.023,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_physics_entropy": 0.889360978603363,
      "eval_physics_loss": 0.9096766710281372,
      "eval_physics_mean_token_accuracy": 0.7674052910804748,
      "eval_physics_num_tokens": 9761227.0,
      "eval_physics_runtime": 70.5356,
      "eval_physics_samples_per_second": 7.089,
      "eval_physics_steps_per_second": 1.772,
      "step": 500
    },
    {
      "entropy": 1.2362793002277612,
      "epoch": 0.816,
      "grad_norm": 19.625,
      "learning_rate": 1.8451851851851855e-05,
      "loss": 19.8133,
      "mean_token_accuracy": 0.6863504596054554,
      "num_tokens": 9958727.0,
      "step": 510
    },
    {
      "entropy": 1.2254926670342683,
      "epoch": 0.832,
      "grad_norm": 17.0,
      "learning_rate": 1.8377777777777778e-05,
      "loss": 19.8307,
      "mean_token_accuracy": 0.6866675779223442,
      "num_tokens": 10155771.0,
      "step": 520
    },
    {
      "entropy": 1.2238412775099277,
      "epoch": 0.848,
      "grad_norm": 18.75,
      "learning_rate": 1.8303703703703704e-05,
      "loss": 19.687,
      "mean_token_accuracy": 0.6897137116640806,
      "num_tokens": 10357721.0,
      "step": 530
    },
    {
      "entropy": 1.2536957442760468,
      "epoch": 0.864,
      "grad_norm": 17.125,
      "learning_rate": 1.822962962962963e-05,
      "loss": 20.1565,
      "mean_token_accuracy": 0.6850291140377521,
      "num_tokens": 10552495.0,
      "step": 540
    },
    {
      "entropy": 1.231699001789093,
      "epoch": 0.88,
      "grad_norm": 18.25,
      "learning_rate": 1.8155555555555557e-05,
      "loss": 19.8536,
      "mean_token_accuracy": 0.6891282081604004,
      "num_tokens": 10748749.0,
      "step": 550
    },
    {
      "entropy": 1.2470501396805047,
      "epoch": 0.896,
      "grad_norm": 18.0,
      "learning_rate": 1.8081481481481484e-05,
      "loss": 20.1706,
      "mean_token_accuracy": 0.6856059569865465,
      "num_tokens": 10943319.0,
      "step": 560
    },
    {
      "entropy": 1.2307742841541767,
      "epoch": 0.912,
      "grad_norm": 18.25,
      "learning_rate": 1.800740740740741e-05,
      "loss": 19.9062,
      "mean_token_accuracy": 0.6885740786790848,
      "num_tokens": 11136935.0,
      "step": 570
    },
    {
      "entropy": 1.2445739306509496,
      "epoch": 0.928,
      "grad_norm": 18.0,
      "learning_rate": 1.7933333333333333e-05,
      "loss": 20.0979,
      "mean_token_accuracy": 0.6851089850068093,
      "num_tokens": 11331098.0,
      "step": 580
    },
    {
      "entropy": 1.2021468229591847,
      "epoch": 0.944,
      "grad_norm": 15.875,
      "learning_rate": 1.785925925925926e-05,
      "loss": 19.4077,
      "mean_token_accuracy": 0.6915138956159353,
      "num_tokens": 11530550.0,
      "step": 590
    },
    {
      "entropy": 1.226809823140502,
      "epoch": 0.96,
      "grad_norm": 19.625,
      "learning_rate": 1.7785185185185186e-05,
      "loss": 19.8062,
      "mean_token_accuracy": 0.6897286407649517,
      "num_tokens": 11729645.0,
      "step": 600
    },
    {
      "epoch": 0.96,
      "eval_biology_entropy": 1.1845180039405823,
      "eval_biology_loss": 1.203829050064087,
      "eval_biology_mean_token_accuracy": 0.6961685500144958,
      "eval_biology_num_tokens": 11729645.0,
      "eval_biology_runtime": 48.6169,
      "eval_biology_samples_per_second": 10.284,
      "eval_biology_steps_per_second": 2.571,
      "step": 600
    },
    {
      "epoch": 0.96,
      "eval_chemistry_entropy": 0.90015394115448,
      "eval_chemistry_loss": 0.8946329355239868,
      "eval_chemistry_mean_token_accuracy": 0.7635614371299744,
      "eval_chemistry_num_tokens": 11729645.0,
      "eval_chemistry_runtime": 60.2919,
      "eval_chemistry_samples_per_second": 8.293,
      "eval_chemistry_steps_per_second": 2.073,
      "step": 600
    },
    {
      "epoch": 0.96,
      "eval_math_entropy": 0.7684455904960632,
      "eval_math_loss": 0.9900413751602173,
      "eval_math_mean_token_accuracy": 0.7588200316429138,
      "eval_math_num_tokens": 11729645.0,
      "eval_math_runtime": 61.8301,
      "eval_math_samples_per_second": 8.087,
      "eval_math_steps_per_second": 2.022,
      "step": 600
    },
    {
      "epoch": 0.96,
      "eval_physics_entropy": 0.8686938014030456,
      "eval_physics_loss": 0.9008635878562927,
      "eval_physics_mean_token_accuracy": 0.7692377109527588,
      "eval_physics_num_tokens": 11729645.0,
      "eval_physics_runtime": 70.4349,
      "eval_physics_samples_per_second": 7.099,
      "eval_physics_steps_per_second": 1.775,
      "step": 600
    },
    {
      "entropy": 1.2100978799164295,
      "epoch": 0.976,
      "grad_norm": 18.0,
      "learning_rate": 1.7711111111111113e-05,
      "loss": 19.47,
      "mean_token_accuracy": 0.6918121088296175,
      "num_tokens": 11924644.0,
      "step": 610
    },
    {
      "entropy": 1.2226450834423304,
      "epoch": 0.992,
      "grad_norm": 16.625,
      "learning_rate": 1.763703703703704e-05,
      "loss": 19.8416,
      "mean_token_accuracy": 0.688375661149621,
      "num_tokens": 12123059.0,
      "step": 620
    },
    {
      "entropy": 1.2316548496484756,
      "epoch": 1.008,
      "grad_norm": 16.875,
      "learning_rate": 1.7562962962962962e-05,
      "loss": 19.6116,
      "mean_token_accuracy": 0.6919524800032377,
      "num_tokens": 12319366.0,
      "step": 630
    },
    {
      "entropy": 1.1779099617153406,
      "epoch": 1.024,
      "grad_norm": 19.0,
      "learning_rate": 1.7488888888888892e-05,
      "loss": 18.9763,
      "mean_token_accuracy": 0.6978646669536829,
      "num_tokens": 12524183.0,
      "step": 640
    },
    {
      "entropy": 1.2152834441512823,
      "epoch": 1.04,
      "grad_norm": 17.75,
      "learning_rate": 1.7414814814814815e-05,
      "loss": 19.6247,
      "mean_token_accuracy": 0.6903412740677595,
      "num_tokens": 12718593.0,
      "step": 650
    },
    {
      "entropy": 1.1799768891185523,
      "epoch": 1.056,
      "grad_norm": 18.625,
      "learning_rate": 1.7340740740740742e-05,
      "loss": 19.0432,
      "mean_token_accuracy": 0.6986244544386864,
      "num_tokens": 12917803.0,
      "step": 660
    },
    {
      "entropy": 1.2108702428638936,
      "epoch": 1.072,
      "grad_norm": 19.125,
      "learning_rate": 1.726666666666667e-05,
      "loss": 19.4166,
      "mean_token_accuracy": 0.6927186574786901,
      "num_tokens": 13105826.0,
      "step": 670
    },
    {
      "entropy": 1.1979756511747837,
      "epoch": 1.088,
      "grad_norm": 18.875,
      "learning_rate": 1.7192592592592595e-05,
      "loss": 19.2605,
      "mean_token_accuracy": 0.6957505799829959,
      "num_tokens": 13298619.0,
      "step": 680
    },
    {
      "entropy": 1.192365935444832,
      "epoch": 1.104,
      "grad_norm": 17.875,
      "learning_rate": 1.711851851851852e-05,
      "loss": 19.2461,
      "mean_token_accuracy": 0.695810866355896,
      "num_tokens": 13491486.0,
      "step": 690
    },
    {
      "entropy": 1.212946466356516,
      "epoch": 1.12,
      "grad_norm": 19.25,
      "learning_rate": 1.7044444444444445e-05,
      "loss": 19.5004,
      "mean_token_accuracy": 0.692466252297163,
      "num_tokens": 13674663.0,
      "step": 700
    },
    {
      "epoch": 1.12,
      "eval_biology_entropy": 1.1571769905090332,
      "eval_biology_loss": 1.1946450471878052,
      "eval_biology_mean_token_accuracy": 0.6972691407203674,
      "eval_biology_num_tokens": 13674663.0,
      "eval_biology_runtime": 48.6729,
      "eval_biology_samples_per_second": 10.273,
      "eval_biology_steps_per_second": 2.568,
      "step": 700
    },
    {
      "epoch": 1.12,
      "eval_chemistry_entropy": 0.8766862626075744,
      "eval_chemistry_loss": 0.8891168236732483,
      "eval_chemistry_mean_token_accuracy": 0.7645404329299926,
      "eval_chemistry_num_tokens": 13674663.0,
      "eval_chemistry_runtime": 60.3334,
      "eval_chemistry_samples_per_second": 8.287,
      "eval_chemistry_steps_per_second": 2.072,
      "step": 700
    },
    {
      "epoch": 1.12,
      "eval_math_entropy": 0.7603865313529968,
      "eval_math_loss": 0.9834137558937073,
      "eval_math_mean_token_accuracy": 0.7596666264533997,
      "eval_math_num_tokens": 13674663.0,
      "eval_math_runtime": 61.8146,
      "eval_math_samples_per_second": 8.089,
      "eval_math_steps_per_second": 2.022,
      "step": 700
    },
    {
      "epoch": 1.12,
      "eval_physics_entropy": 0.850571988105774,
      "eval_physics_loss": 0.8937918543815613,
      "eval_physics_mean_token_accuracy": 0.7703958468437195,
      "eval_physics_num_tokens": 13674663.0,
      "eval_physics_runtime": 70.4674,
      "eval_physics_samples_per_second": 7.095,
      "eval_physics_steps_per_second": 1.774,
      "step": 700
    },
    {
      "entropy": 1.1909121543169021,
      "epoch": 1.1360000000000001,
      "grad_norm": 18.875,
      "learning_rate": 1.697037037037037e-05,
      "loss": 19.2462,
      "mean_token_accuracy": 0.6955781776458025,
      "num_tokens": 13869134.0,
      "step": 710
    },
    {
      "entropy": 1.1682380847632885,
      "epoch": 1.152,
      "grad_norm": 16.75,
      "learning_rate": 1.6896296296296298e-05,
      "loss": 18.8229,
      "mean_token_accuracy": 0.6991135813295841,
      "num_tokens": 14078365.0,
      "step": 720
    },
    {
      "entropy": 1.1939557407051324,
      "epoch": 1.168,
      "grad_norm": 16.875,
      "learning_rate": 1.6822222222222224e-05,
      "loss": 19.1346,
      "mean_token_accuracy": 0.6960698150098323,
      "num_tokens": 14266831.0,
      "step": 730
    },
    {
      "entropy": 1.180869185552001,
      "epoch": 1.184,
      "grad_norm": 18.25,
      "learning_rate": 1.6748148148148147e-05,
      "loss": 19.2654,
      "mean_token_accuracy": 0.6941378649324179,
      "num_tokens": 14465660.0,
      "step": 740
    },
    {
      "entropy": 1.1937656667083503,
      "epoch": 1.2,
      "grad_norm": 18.25,
      "learning_rate": 1.6674074074074077e-05,
      "loss": 19.0305,
      "mean_token_accuracy": 0.6964295905083417,
      "num_tokens": 14653228.0,
      "step": 750
    },
    {
      "entropy": 1.1589823190122843,
      "epoch": 1.216,
      "grad_norm": 17.875,
      "learning_rate": 1.66e-05,
      "loss": 18.6048,
      "mean_token_accuracy": 0.7018654596060514,
      "num_tokens": 14857782.0,
      "step": 760
    },
    {
      "entropy": 1.1703605465590954,
      "epoch": 1.232,
      "grad_norm": 17.375,
      "learning_rate": 1.6525925925925927e-05,
      "loss": 18.8831,
      "mean_token_accuracy": 0.7015001580119133,
      "num_tokens": 15047356.0,
      "step": 770
    },
    {
      "entropy": 1.1772115517407655,
      "epoch": 1.248,
      "grad_norm": 17.875,
      "learning_rate": 1.6451851851851853e-05,
      "loss": 19.0432,
      "mean_token_accuracy": 0.6959997840225697,
      "num_tokens": 15241098.0,
      "step": 780
    },
    {
      "entropy": 1.196473068371415,
      "epoch": 1.264,
      "grad_norm": 16.375,
      "learning_rate": 1.637777777777778e-05,
      "loss": 19.1591,
      "mean_token_accuracy": 0.6967897292226553,
      "num_tokens": 15437657.0,
      "step": 790
    },
    {
      "entropy": 1.2014197081327438,
      "epoch": 1.28,
      "grad_norm": 19.125,
      "learning_rate": 1.6303703703703706e-05,
      "loss": 19.4409,
      "mean_token_accuracy": 0.6926549930125475,
      "num_tokens": 15630795.0,
      "step": 800
    },
    {
      "epoch": 1.28,
      "eval_biology_entropy": 1.134603425502777,
      "eval_biology_loss": 1.1884372234344482,
      "eval_biology_mean_token_accuracy": 0.6986491298675537,
      "eval_biology_num_tokens": 15630795.0,
      "eval_biology_runtime": 48.6306,
      "eval_biology_samples_per_second": 10.282,
      "eval_biology_steps_per_second": 2.57,
      "step": 800
    },
    {
      "epoch": 1.28,
      "eval_chemistry_entropy": 0.8623910093307495,
      "eval_chemistry_loss": 0.885444700717926,
      "eval_chemistry_mean_token_accuracy": 0.7653528556823731,
      "eval_chemistry_num_tokens": 15630795.0,
      "eval_chemistry_runtime": 60.3508,
      "eval_chemistry_samples_per_second": 8.285,
      "eval_chemistry_steps_per_second": 2.071,
      "step": 800
    },
    {
      "epoch": 1.28,
      "eval_math_entropy": 0.7589023416042328,
      "eval_math_loss": 0.983073353767395,
      "eval_math_mean_token_accuracy": 0.7593517408370972,
      "eval_math_num_tokens": 15630795.0,
      "eval_math_runtime": 61.9026,
      "eval_math_samples_per_second": 8.077,
      "eval_math_steps_per_second": 2.019,
      "step": 800
    },
    {
      "epoch": 1.28,
      "eval_physics_entropy": 0.84130739736557,
      "eval_physics_loss": 0.8907755613327026,
      "eval_physics_mean_token_accuracy": 0.771062777519226,
      "eval_physics_num_tokens": 15630795.0,
      "eval_physics_runtime": 70.5226,
      "eval_physics_samples_per_second": 7.09,
      "eval_physics_steps_per_second": 1.772,
      "step": 800
    },
    {
      "entropy": 1.2085642520338298,
      "epoch": 1.296,
      "grad_norm": 17.375,
      "learning_rate": 1.622962962962963e-05,
      "loss": 19.3831,
      "mean_token_accuracy": 0.6933640763163567,
      "num_tokens": 15827105.0,
      "step": 810
    },
    {
      "entropy": 1.1861349143087865,
      "epoch": 1.312,
      "grad_norm": 18.75,
      "learning_rate": 1.6155555555555556e-05,
      "loss": 19.3103,
      "mean_token_accuracy": 0.694928414747119,
      "num_tokens": 16019645.0,
      "step": 820
    },
    {
      "entropy": 1.195632776618004,
      "epoch": 1.328,
      "grad_norm": 18.5,
      "learning_rate": 1.6081481481481482e-05,
      "loss": 19.3068,
      "mean_token_accuracy": 0.6934712298214436,
      "num_tokens": 16221726.0,
      "step": 830
    },
    {
      "entropy": 1.1725192748010158,
      "epoch": 1.3439999999999999,
      "grad_norm": 17.0,
      "learning_rate": 1.600740740740741e-05,
      "loss": 18.7963,
      "mean_token_accuracy": 0.700145885720849,
      "num_tokens": 16427594.0,
      "step": 840
    },
    {
      "entropy": 1.179823150858283,
      "epoch": 1.3599999999999999,
      "grad_norm": 18.75,
      "learning_rate": 1.5933333333333336e-05,
      "loss": 19.1154,
      "mean_token_accuracy": 0.6961398232728243,
      "num_tokens": 16621605.0,
      "step": 850
    },
    {
      "entropy": 1.2228495314717294,
      "epoch": 1.376,
      "grad_norm": 19.5,
      "learning_rate": 1.5859259259259262e-05,
      "loss": 19.6627,
      "mean_token_accuracy": 0.6894211061298847,
      "num_tokens": 16813444.0,
      "step": 860
    },
    {
      "entropy": 1.19021125882864,
      "epoch": 1.392,
      "grad_norm": 17.5,
      "learning_rate": 1.5785185185185185e-05,
      "loss": 19.2411,
      "mean_token_accuracy": 0.6957099426537752,
      "num_tokens": 17006509.0,
      "step": 870
    },
    {
      "entropy": 1.184871331602335,
      "epoch": 1.408,
      "grad_norm": 15.4375,
      "learning_rate": 1.571111111111111e-05,
      "loss": 18.9785,
      "mean_token_accuracy": 0.6971315786242485,
      "num_tokens": 17197870.0,
      "step": 880
    },
    {
      "entropy": 1.1884775411337614,
      "epoch": 1.424,
      "grad_norm": 17.25,
      "learning_rate": 1.5637037037037038e-05,
      "loss": 19.1289,
      "mean_token_accuracy": 0.697301234304905,
      "num_tokens": 17394390.0,
      "step": 890
    },
    {
      "entropy": 1.1825116220861673,
      "epoch": 1.44,
      "grad_norm": 20.75,
      "learning_rate": 1.5562962962962965e-05,
      "loss": 19.1266,
      "mean_token_accuracy": 0.6968252252787351,
      "num_tokens": 17587777.0,
      "step": 900
    },
    {
      "epoch": 1.44,
      "eval_biology_entropy": 1.1672434105873108,
      "eval_biology_loss": 1.1815813779830933,
      "eval_biology_mean_token_accuracy": 0.7003293070793152,
      "eval_biology_num_tokens": 17587777.0,
      "eval_biology_runtime": 48.6205,
      "eval_biology_samples_per_second": 10.284,
      "eval_biology_steps_per_second": 2.571,
      "step": 900
    },
    {
      "epoch": 1.44,
      "eval_chemistry_entropy": 0.8869817838668823,
      "eval_chemistry_loss": 0.8829970955848694,
      "eval_chemistry_mean_token_accuracy": 0.7656374487876892,
      "eval_chemistry_num_tokens": 17587777.0,
      "eval_chemistry_runtime": 60.3339,
      "eval_chemistry_samples_per_second": 8.287,
      "eval_chemistry_steps_per_second": 2.072,
      "step": 900
    },
    {
      "epoch": 1.44,
      "eval_math_entropy": 0.7674483435153961,
      "eval_math_loss": 0.9792445302009583,
      "eval_math_mean_token_accuracy": 0.7597224740982056,
      "eval_math_num_tokens": 17587777.0,
      "eval_math_runtime": 61.8239,
      "eval_math_samples_per_second": 8.087,
      "eval_math_steps_per_second": 2.022,
      "step": 900
    },
    {
      "epoch": 1.44,
      "eval_physics_entropy": 0.8621900615692139,
      "eval_physics_loss": 0.8884776830673218,
      "eval_physics_mean_token_accuracy": 0.7715646696090698,
      "eval_physics_num_tokens": 17587777.0,
      "eval_physics_runtime": 70.446,
      "eval_physics_samples_per_second": 7.098,
      "eval_physics_steps_per_second": 1.774,
      "step": 900
    },
    {
      "entropy": 1.1818725422024727,
      "epoch": 1.456,
      "grad_norm": 18.25,
      "learning_rate": 1.548888888888889e-05,
      "loss": 19.032,
      "mean_token_accuracy": 0.698200449720025,
      "num_tokens": 17788456.0,
      "step": 910
    },
    {
      "entropy": 1.1769807077944279,
      "epoch": 1.472,
      "grad_norm": 16.0,
      "learning_rate": 1.5414814814814814e-05,
      "loss": 18.8791,
      "mean_token_accuracy": 0.7008779179304838,
      "num_tokens": 17984063.0,
      "step": 920
    },
    {
      "entropy": 1.1641013238579034,
      "epoch": 1.488,
      "grad_norm": 18.5,
      "learning_rate": 1.5340740740740744e-05,
      "loss": 18.9913,
      "mean_token_accuracy": 0.6998269848525525,
      "num_tokens": 18175640.0,
      "step": 930
    },
    {
      "entropy": 1.1960251219570637,
      "epoch": 1.504,
      "grad_norm": 17.0,
      "learning_rate": 1.5266666666666667e-05,
      "loss": 19.2076,
      "mean_token_accuracy": 0.696322177350521,
      "num_tokens": 18367857.0,
      "step": 940
    },
    {
      "entropy": 1.1745740845799446,
      "epoch": 1.52,
      "grad_norm": 16.875,
      "learning_rate": 1.5192592592592594e-05,
      "loss": 19.0307,
      "mean_token_accuracy": 0.6969408400356769,
      "num_tokens": 18569146.0,
      "step": 950
    },
    {
      "entropy": 1.2008745949715376,
      "epoch": 1.536,
      "grad_norm": 18.75,
      "learning_rate": 1.5118518518518519e-05,
      "loss": 19.2895,
      "mean_token_accuracy": 0.6946466054767371,
      "num_tokens": 18755079.0,
      "step": 960
    },
    {
      "entropy": 1.1710849691182375,
      "epoch": 1.552,
      "grad_norm": 19.375,
      "learning_rate": 1.5044444444444445e-05,
      "loss": 18.9073,
      "mean_token_accuracy": 0.699705482646823,
      "num_tokens": 18956248.0,
      "step": 970
    },
    {
      "entropy": 1.163971472159028,
      "epoch": 1.568,
      "grad_norm": 18.5,
      "learning_rate": 1.497037037037037e-05,
      "loss": 18.7379,
      "mean_token_accuracy": 0.7023108277469874,
      "num_tokens": 19150315.0,
      "step": 980
    },
    {
      "entropy": 1.1755164857953786,
      "epoch": 1.584,
      "grad_norm": 17.75,
      "learning_rate": 1.4896296296296298e-05,
      "loss": 18.8826,
      "mean_token_accuracy": 0.6997408363968134,
      "num_tokens": 19344260.0,
      "step": 990
    },
    {
      "entropy": 1.2020615819841622,
      "epoch": 1.6,
      "grad_norm": 17.125,
      "learning_rate": 1.4822222222222225e-05,
      "loss": 19.3858,
      "mean_token_accuracy": 0.6933612376451492,
      "num_tokens": 19532552.0,
      "step": 1000
    },
    {
      "epoch": 1.6,
      "eval_biology_entropy": 1.1451181559562682,
      "eval_biology_loss": 1.1767185926437378,
      "eval_biology_mean_token_accuracy": 0.7013368840217591,
      "eval_biology_num_tokens": 19532552.0,
      "eval_biology_runtime": 48.6261,
      "eval_biology_samples_per_second": 10.283,
      "eval_biology_steps_per_second": 2.571,
      "step": 1000
    },
    {
      "epoch": 1.6,
      "eval_chemistry_entropy": 0.8642943887710571,
      "eval_chemistry_loss": 0.8798553347587585,
      "eval_chemistry_mean_token_accuracy": 0.7664505195617676,
      "eval_chemistry_num_tokens": 19532552.0,
      "eval_chemistry_runtime": 59.8839,
      "eval_chemistry_samples_per_second": 8.349,
      "eval_chemistry_steps_per_second": 2.087,
      "step": 1000
    },
    {
      "epoch": 1.6,
      "eval_math_entropy": 0.7490488801002503,
      "eval_math_loss": 0.9804874062538147,
      "eval_math_mean_token_accuracy": 0.7602896738052368,
      "eval_math_num_tokens": 19532552.0,
      "eval_math_runtime": 61.7317,
      "eval_math_samples_per_second": 8.1,
      "eval_math_steps_per_second": 2.025,
      "step": 1000
    },
    {
      "epoch": 1.6,
      "eval_physics_entropy": 0.8397411880493164,
      "eval_physics_loss": 0.885618269443512,
      "eval_physics_mean_token_accuracy": 0.7722613711357117,
      "eval_physics_num_tokens": 19532552.0,
      "eval_physics_runtime": 70.4574,
      "eval_physics_samples_per_second": 7.096,
      "eval_physics_steps_per_second": 1.774,
      "step": 1000
    },
    {
      "entropy": 1.1645312760025264,
      "epoch": 1.616,
      "grad_norm": 17.125,
      "learning_rate": 1.474814814814815e-05,
      "loss": 18.8318,
      "mean_token_accuracy": 0.7000049009919167,
      "num_tokens": 19732719.0,
      "step": 1010
    },
    {
      "entropy": 1.2018159918487072,
      "epoch": 1.6320000000000001,
      "grad_norm": 19.625,
      "learning_rate": 1.4674074074074076e-05,
      "loss": 19.3741,
      "mean_token_accuracy": 0.6942509710788727,
      "num_tokens": 19926830.0,
      "step": 1020
    },
    {
      "entropy": 1.1848741736263038,
      "epoch": 1.6480000000000001,
      "grad_norm": 16.25,
      "learning_rate": 1.46e-05,
      "loss": 19.0931,
      "mean_token_accuracy": 0.6962833561003208,
      "num_tokens": 20118800.0,
      "step": 1030
    },
    {
      "entropy": 1.1461675189435483,
      "epoch": 1.6640000000000001,
      "grad_norm": 16.5,
      "learning_rate": 1.4525925925925927e-05,
      "loss": 18.5384,
      "mean_token_accuracy": 0.7037994157522917,
      "num_tokens": 20320511.0,
      "step": 1040
    },
    {
      "entropy": 1.1853893544524907,
      "epoch": 1.6800000000000002,
      "grad_norm": 18.375,
      "learning_rate": 1.4451851851851852e-05,
      "loss": 18.9769,
      "mean_token_accuracy": 0.6986714884638786,
      "num_tokens": 20513393.0,
      "step": 1050
    },
    {
      "entropy": 1.1721675164997578,
      "epoch": 1.696,
      "grad_norm": 17.5,
      "learning_rate": 1.4377777777777779e-05,
      "loss": 18.9508,
      "mean_token_accuracy": 0.7003318756818772,
      "num_tokens": 20707237.0,
      "step": 1060
    },
    {
      "entropy": 1.1738170266151429,
      "epoch": 1.712,
      "grad_norm": 19.5,
      "learning_rate": 1.4303703703703703e-05,
      "loss": 18.9752,
      "mean_token_accuracy": 0.6993441980332136,
      "num_tokens": 20910419.0,
      "step": 1070
    },
    {
      "entropy": 1.190333865955472,
      "epoch": 1.728,
      "grad_norm": 18.5,
      "learning_rate": 1.4229629629629632e-05,
      "loss": 19.1838,
      "mean_token_accuracy": 0.6956166718155146,
      "num_tokens": 21107498.0,
      "step": 1080
    },
    {
      "entropy": 1.1574083410203457,
      "epoch": 1.744,
      "grad_norm": 18.25,
      "learning_rate": 1.4155555555555556e-05,
      "loss": 18.5378,
      "mean_token_accuracy": 0.7021385233849287,
      "num_tokens": 21303955.0,
      "step": 1090
    },
    {
      "entropy": 1.1666433937847613,
      "epoch": 1.76,
      "grad_norm": 18.75,
      "learning_rate": 1.4081481481481483e-05,
      "loss": 18.9266,
      "mean_token_accuracy": 0.7011374026536942,
      "num_tokens": 21499572.0,
      "step": 1100
    },
    {
      "epoch": 1.76,
      "eval_biology_entropy": 1.1345319437980652,
      "eval_biology_loss": 1.1725776195526123,
      "eval_biology_mean_token_accuracy": 0.7024298944473266,
      "eval_biology_num_tokens": 21499572.0,
      "eval_biology_runtime": 48.5727,
      "eval_biology_samples_per_second": 10.294,
      "eval_biology_steps_per_second": 2.573,
      "step": 1100
    },
    {
      "epoch": 1.76,
      "eval_chemistry_entropy": 0.8619537029266358,
      "eval_chemistry_loss": 0.8766760230064392,
      "eval_chemistry_mean_token_accuracy": 0.7667445015907287,
      "eval_chemistry_num_tokens": 21499572.0,
      "eval_chemistry_runtime": 60.4564,
      "eval_chemistry_samples_per_second": 8.27,
      "eval_chemistry_steps_per_second": 2.068,
      "step": 1100
    },
    {
      "epoch": 1.76,
      "eval_math_entropy": 0.7560438480377197,
      "eval_math_loss": 0.9768902063369751,
      "eval_math_mean_token_accuracy": 0.7610512175559998,
      "eval_math_num_tokens": 21499572.0,
      "eval_math_runtime": 61.7554,
      "eval_math_samples_per_second": 8.096,
      "eval_math_steps_per_second": 2.024,
      "step": 1100
    },
    {
      "epoch": 1.76,
      "eval_physics_entropy": 0.840686586856842,
      "eval_physics_loss": 0.8825888633728027,
      "eval_physics_mean_token_accuracy": 0.7726316556930543,
      "eval_physics_num_tokens": 21499572.0,
      "eval_physics_runtime": 70.3673,
      "eval_physics_samples_per_second": 7.106,
      "eval_physics_steps_per_second": 1.776,
      "step": 1100
    },
    {
      "entropy": 1.177320409566164,
      "epoch": 1.776,
      "grad_norm": 17.875,
      "learning_rate": 1.400740740740741e-05,
      "loss": 18.9676,
      "mean_token_accuracy": 0.6986722864210606,
      "num_tokens": 21692804.0,
      "step": 1110
    },
    {
      "entropy": 1.148191200569272,
      "epoch": 1.792,
      "grad_norm": 19.875,
      "learning_rate": 1.3933333333333334e-05,
      "loss": 18.5112,
      "mean_token_accuracy": 0.7040422059595585,
      "num_tokens": 21894218.0,
      "step": 1120
    },
    {
      "entropy": 1.1709640648216009,
      "epoch": 1.808,
      "grad_norm": 19.5,
      "learning_rate": 1.385925925925926e-05,
      "loss": 18.8424,
      "mean_token_accuracy": 0.7009096905589104,
      "num_tokens": 22082522.0,
      "step": 1130
    },
    {
      "entropy": 1.1934551119804382,
      "epoch": 1.8239999999999998,
      "grad_norm": 19.375,
      "learning_rate": 1.3785185185185186e-05,
      "loss": 19.3396,
      "mean_token_accuracy": 0.693663826212287,
      "num_tokens": 22278933.0,
      "step": 1140
    },
    {
      "entropy": 1.2042058877646924,
      "epoch": 1.8399999999999999,
      "grad_norm": 19.375,
      "learning_rate": 1.3711111111111112e-05,
      "loss": 19.393,
      "mean_token_accuracy": 0.6937405589967967,
      "num_tokens": 22473801.0,
      "step": 1150
    },
    {
      "entropy": 1.1648973379284144,
      "epoch": 1.8559999999999999,
      "grad_norm": 18.125,
      "learning_rate": 1.3637037037037037e-05,
      "loss": 18.7484,
      "mean_token_accuracy": 0.6991217479109764,
      "num_tokens": 22677853.0,
      "step": 1160
    },
    {
      "entropy": 1.1554684847593308,
      "epoch": 1.8719999999999999,
      "grad_norm": 17.375,
      "learning_rate": 1.3562962962962965e-05,
      "loss": 18.5305,
      "mean_token_accuracy": 0.7038368381559849,
      "num_tokens": 22874965.0,
      "step": 1170
    },
    {
      "entropy": 1.1899018451571464,
      "epoch": 1.888,
      "grad_norm": 20.75,
      "learning_rate": 1.3488888888888888e-05,
      "loss": 19.2428,
      "mean_token_accuracy": 0.6950660139322281,
      "num_tokens": 23068892.0,
      "step": 1180
    },
    {
      "entropy": 1.1851763129234314,
      "epoch": 1.904,
      "grad_norm": 18.375,
      "learning_rate": 1.3414814814814817e-05,
      "loss": 19.126,
      "mean_token_accuracy": 0.6976218212395906,
      "num_tokens": 23263827.0,
      "step": 1190
    },
    {
      "entropy": 1.1869227845221757,
      "epoch": 1.92,
      "grad_norm": 18.375,
      "learning_rate": 1.3340740740740741e-05,
      "loss": 19.135,
      "mean_token_accuracy": 0.6959322843700647,
      "num_tokens": 23463627.0,
      "step": 1200
    },
    {
      "epoch": 1.92,
      "eval_biology_entropy": 1.1337207446098327,
      "eval_biology_loss": 1.168716311454773,
      "eval_biology_mean_token_accuracy": 0.7030426645278931,
      "eval_biology_num_tokens": 23463627.0,
      "eval_biology_runtime": 48.5387,
      "eval_biology_samples_per_second": 10.301,
      "eval_biology_steps_per_second": 2.575,
      "step": 1200
    },
    {
      "epoch": 1.92,
      "eval_chemistry_entropy": 0.8601148505210876,
      "eval_chemistry_loss": 0.8744351267814636,
      "eval_chemistry_mean_token_accuracy": 0.767286482334137,
      "eval_chemistry_num_tokens": 23463627.0,
      "eval_chemistry_runtime": 60.2148,
      "eval_chemistry_samples_per_second": 8.304,
      "eval_chemistry_steps_per_second": 2.076,
      "step": 1200
    },
    {
      "epoch": 1.92,
      "eval_math_entropy": 0.7519172282218933,
      "eval_math_loss": 0.9753768444061279,
      "eval_math_mean_token_accuracy": 0.7615019774436951,
      "eval_math_num_tokens": 23463627.0,
      "eval_math_runtime": 61.7169,
      "eval_math_samples_per_second": 8.102,
      "eval_math_steps_per_second": 2.025,
      "step": 1200
    },
    {
      "epoch": 1.92,
      "eval_physics_entropy": 0.836491331577301,
      "eval_physics_loss": 0.8801184296607971,
      "eval_physics_mean_token_accuracy": 0.7731836423873901,
      "eval_physics_num_tokens": 23463627.0,
      "eval_physics_runtime": 70.3444,
      "eval_physics_samples_per_second": 7.108,
      "eval_physics_steps_per_second": 1.777,
      "step": 1200
    },
    {
      "entropy": 1.1517000958323478,
      "epoch": 1.936,
      "grad_norm": 18.875,
      "learning_rate": 1.3266666666666668e-05,
      "loss": 18.5112,
      "mean_token_accuracy": 0.7040315445512533,
      "num_tokens": 23660418.0,
      "step": 1210
    },
    {
      "entropy": 1.172454860061407,
      "epoch": 1.952,
      "grad_norm": 18.75,
      "learning_rate": 1.3192592592592594e-05,
      "loss": 18.8708,
      "mean_token_accuracy": 0.6998139064759016,
      "num_tokens": 23858145.0,
      "step": 1220
    },
    {
      "entropy": 1.18152665682137,
      "epoch": 1.968,
      "grad_norm": 18.5,
      "learning_rate": 1.311851851851852e-05,
      "loss": 19.0753,
      "mean_token_accuracy": 0.6981570664793253,
      "num_tokens": 24053364.0,
      "step": 1230
    },
    {
      "entropy": 1.1768125779926777,
      "epoch": 1.984,
      "grad_norm": 17.625,
      "learning_rate": 1.3044444444444446e-05,
      "loss": 18.9463,
      "mean_token_accuracy": 0.6988612022250891,
      "num_tokens": 24249465.0,
      "step": 1240
    },
    {
      "entropy": 1.180902672186494,
      "epoch": 2.0,
      "grad_norm": 19.375,
      "learning_rate": 1.297037037037037e-05,
      "loss": 18.999,
      "mean_token_accuracy": 0.7006669268012047,
      "num_tokens": 24442582.0,
      "step": 1250
    },
    {
      "entropy": 1.1616276282817126,
      "epoch": 2.016,
      "grad_norm": 19.75,
      "learning_rate": 1.2896296296296299e-05,
      "loss": 18.592,
      "mean_token_accuracy": 0.7041712146252394,
      "num_tokens": 24632353.0,
      "step": 1260
    },
    {
      "entropy": 1.1689807120710611,
      "epoch": 2.032,
      "grad_norm": 18.625,
      "learning_rate": 1.2822222222222222e-05,
      "loss": 18.9039,
      "mean_token_accuracy": 0.7014766734093427,
      "num_tokens": 24822715.0,
      "step": 1270
    },
    {
      "entropy": 1.1456513587385415,
      "epoch": 2.048,
      "grad_norm": 20.0,
      "learning_rate": 1.274814814814815e-05,
      "loss": 18.4096,
      "mean_token_accuracy": 0.7051771484315396,
      "num_tokens": 25023118.0,
      "step": 1280
    },
    {
      "entropy": 1.1587952699512243,
      "epoch": 2.064,
      "grad_norm": 18.625,
      "learning_rate": 1.2674074074074075e-05,
      "loss": 18.6378,
      "mean_token_accuracy": 0.7034870360046626,
      "num_tokens": 25217414.0,
      "step": 1290
    },
    {
      "entropy": 1.1504007514566184,
      "epoch": 2.08,
      "grad_norm": 18.0,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 18.4703,
      "mean_token_accuracy": 0.7041630525141954,
      "num_tokens": 25408961.0,
      "step": 1300
    },
    {
      "epoch": 2.08,
      "eval_biology_entropy": 1.1164145894050599,
      "eval_biology_loss": 1.1683411598205566,
      "eval_biology_mean_token_accuracy": 0.7027085943222046,
      "eval_biology_num_tokens": 25408961.0,
      "eval_biology_runtime": 48.5837,
      "eval_biology_samples_per_second": 10.292,
      "eval_biology_steps_per_second": 2.573,
      "step": 1300
    },
    {
      "epoch": 2.08,
      "eval_chemistry_entropy": 0.8446620798110962,
      "eval_chemistry_loss": 0.8756071925163269,
      "eval_chemistry_mean_token_accuracy": 0.7672800846099853,
      "eval_chemistry_num_tokens": 25408961.0,
      "eval_chemistry_runtime": 60.224,
      "eval_chemistry_samples_per_second": 8.302,
      "eval_chemistry_steps_per_second": 2.076,
      "step": 1300
    },
    {
      "epoch": 2.08,
      "eval_math_entropy": 0.7416602709293365,
      "eval_math_loss": 0.9767736792564392,
      "eval_math_mean_token_accuracy": 0.7612695918083191,
      "eval_math_num_tokens": 25408961.0,
      "eval_math_runtime": 61.7354,
      "eval_math_samples_per_second": 8.099,
      "eval_math_steps_per_second": 2.025,
      "step": 1300
    },
    {
      "epoch": 2.08,
      "eval_physics_entropy": 0.822511604309082,
      "eval_physics_loss": 0.8807807564735413,
      "eval_physics_mean_token_accuracy": 0.7734324297904969,
      "eval_physics_num_tokens": 25408961.0,
      "eval_physics_runtime": 70.3722,
      "eval_physics_samples_per_second": 7.105,
      "eval_physics_steps_per_second": 1.776,
      "step": 1300
    },
    {
      "entropy": 1.145626274123788,
      "epoch": 2.096,
      "grad_norm": 20.75,
      "learning_rate": 1.2525925925925928e-05,
      "loss": 18.4669,
      "mean_token_accuracy": 0.7053351275622844,
      "num_tokens": 25600511.0,
      "step": 1310
    },
    {
      "entropy": 1.1261590894311666,
      "epoch": 2.112,
      "grad_norm": 19.375,
      "learning_rate": 1.2451851851851853e-05,
      "loss": 18.0421,
      "mean_token_accuracy": 0.7101508729159832,
      "num_tokens": 25796565.0,
      "step": 1320
    },
    {
      "entropy": 1.1319866240024568,
      "epoch": 2.128,
      "grad_norm": 18.375,
      "learning_rate": 1.237777777777778e-05,
      "loss": 18.2326,
      "mean_token_accuracy": 0.7063661482185125,
      "num_tokens": 25991156.0,
      "step": 1330
    },
    {
      "entropy": 1.12694109082222,
      "epoch": 2.144,
      "grad_norm": 21.625,
      "learning_rate": 1.2303703703703704e-05,
      "loss": 18.27,
      "mean_token_accuracy": 0.7078616585582495,
      "num_tokens": 26193237.0,
      "step": 1340
    },
    {
      "entropy": 1.1670064296573401,
      "epoch": 2.16,
      "grad_norm": 20.0,
      "learning_rate": 1.222962962962963e-05,
      "loss": 18.6321,
      "mean_token_accuracy": 0.704596522077918,
      "num_tokens": 26387993.0,
      "step": 1350
    },
    {
      "entropy": 1.1611683428287507,
      "epoch": 2.176,
      "grad_norm": 19.75,
      "learning_rate": 1.2155555555555555e-05,
      "loss": 18.8084,
      "mean_token_accuracy": 0.7007863517850638,
      "num_tokens": 26585269.0,
      "step": 1360
    },
    {
      "entropy": 1.1334992978721856,
      "epoch": 2.192,
      "grad_norm": 17.0,
      "learning_rate": 1.2081481481481484e-05,
      "loss": 18.1002,
      "mean_token_accuracy": 0.7102227192372084,
      "num_tokens": 26776318.0,
      "step": 1370
    },
    {
      "entropy": 1.142113695293665,
      "epoch": 2.208,
      "grad_norm": 18.25,
      "learning_rate": 1.2007407407407408e-05,
      "loss": 18.4288,
      "mean_token_accuracy": 0.7056139782071114,
      "num_tokens": 26974420.0,
      "step": 1380
    },
    {
      "entropy": 1.165258849412203,
      "epoch": 2.224,
      "grad_norm": 18.375,
      "learning_rate": 1.1933333333333335e-05,
      "loss": 18.8072,
      "mean_token_accuracy": 0.7021366007626056,
      "num_tokens": 27167577.0,
      "step": 1390
    },
    {
      "entropy": 1.1230817057192326,
      "epoch": 2.24,
      "grad_norm": 18.0,
      "learning_rate": 1.185925925925926e-05,
      "loss": 18.0154,
      "mean_token_accuracy": 0.7094326011836529,
      "num_tokens": 27364189.0,
      "step": 1400
    },
    {
      "epoch": 2.24,
      "eval_biology_entropy": 1.107084683418274,
      "eval_biology_loss": 1.166341781616211,
      "eval_biology_mean_token_accuracy": 0.7033038935661315,
      "eval_biology_num_tokens": 27364189.0,
      "eval_biology_runtime": 48.5794,
      "eval_biology_samples_per_second": 10.292,
      "eval_biology_steps_per_second": 2.573,
      "step": 1400
    },
    {
      "epoch": 2.24,
      "eval_chemistry_entropy": 0.8436218018531799,
      "eval_chemistry_loss": 0.8749056458473206,
      "eval_chemistry_mean_token_accuracy": 0.7673236474990844,
      "eval_chemistry_num_tokens": 27364189.0,
      "eval_chemistry_runtime": 60.2275,
      "eval_chemistry_samples_per_second": 8.302,
      "eval_chemistry_steps_per_second": 2.075,
      "step": 1400
    },
    {
      "epoch": 2.24,
      "eval_math_entropy": 0.7436552357673645,
      "eval_math_loss": 0.9768530130386353,
      "eval_math_mean_token_accuracy": 0.7615942449569703,
      "eval_math_num_tokens": 27364189.0,
      "eval_math_runtime": 61.7353,
      "eval_math_samples_per_second": 8.099,
      "eval_math_steps_per_second": 2.025,
      "step": 1400
    },
    {
      "epoch": 2.24,
      "eval_physics_entropy": 0.8238044924736023,
      "eval_physics_loss": 0.880571186542511,
      "eval_physics_mean_token_accuracy": 0.7732309465408325,
      "eval_physics_num_tokens": 27364189.0,
      "eval_physics_runtime": 70.3425,
      "eval_physics_samples_per_second": 7.108,
      "eval_physics_steps_per_second": 1.777,
      "step": 1400
    },
    {
      "entropy": 1.1227998584508896,
      "epoch": 2.2560000000000002,
      "grad_norm": 17.875,
      "learning_rate": 1.1785185185185186e-05,
      "loss": 17.9995,
      "mean_token_accuracy": 0.71092384532094,
      "num_tokens": 27557387.0,
      "step": 1410
    },
    {
      "entropy": 1.1192971892654895,
      "epoch": 2.2720000000000002,
      "grad_norm": 19.5,
      "learning_rate": 1.1711111111111113e-05,
      "loss": 18.0703,
      "mean_token_accuracy": 0.7088606022298336,
      "num_tokens": 27755725.0,
      "step": 1420
    },
    {
      "entropy": 1.157552171498537,
      "epoch": 2.288,
      "grad_norm": 18.75,
      "learning_rate": 1.1637037037037037e-05,
      "loss": 18.6818,
      "mean_token_accuracy": 0.7010403741151094,
      "num_tokens": 27950694.0,
      "step": 1430
    },
    {
      "entropy": 1.1524705573916436,
      "epoch": 2.304,
      "grad_norm": 17.75,
      "learning_rate": 1.1562962962962964e-05,
      "loss": 18.6601,
      "mean_token_accuracy": 0.7030924465507269,
      "num_tokens": 28150719.0,
      "step": 1440
    },
    {
      "entropy": 1.1215086288750171,
      "epoch": 2.32,
      "grad_norm": 17.5,
      "learning_rate": 1.1488888888888889e-05,
      "loss": 17.9268,
      "mean_token_accuracy": 0.7104179698973894,
      "num_tokens": 28348652.0,
      "step": 1450
    },
    {
      "entropy": 1.1350885152816772,
      "epoch": 2.336,
      "grad_norm": 18.375,
      "learning_rate": 1.1414814814814817e-05,
      "loss": 18.3565,
      "mean_token_accuracy": 0.7067790202796459,
      "num_tokens": 28542945.0,
      "step": 1460
    },
    {
      "entropy": 1.156265541538596,
      "epoch": 2.352,
      "grad_norm": 19.0,
      "learning_rate": 1.1340740740740742e-05,
      "loss": 18.6992,
      "mean_token_accuracy": 0.7013768840581178,
      "num_tokens": 28731927.0,
      "step": 1470
    },
    {
      "entropy": 1.1396565582603215,
      "epoch": 2.368,
      "grad_norm": 18.75,
      "learning_rate": 1.1266666666666668e-05,
      "loss": 18.2949,
      "mean_token_accuracy": 0.7059750188142061,
      "num_tokens": 28929298.0,
      "step": 1480
    },
    {
      "entropy": 1.1448044694960118,
      "epoch": 2.384,
      "grad_norm": 20.625,
      "learning_rate": 1.1192592592592593e-05,
      "loss": 18.526,
      "mean_token_accuracy": 0.703592960909009,
      "num_tokens": 29121142.0,
      "step": 1490
    },
    {
      "entropy": 1.140185246989131,
      "epoch": 2.4,
      "grad_norm": 18.0,
      "learning_rate": 1.111851851851852e-05,
      "loss": 18.3273,
      "mean_token_accuracy": 0.706566022336483,
      "num_tokens": 29317919.0,
      "step": 1500
    },
    {
      "epoch": 2.4,
      "eval_biology_entropy": 1.1156310276985169,
      "eval_biology_loss": 1.1647558212280273,
      "eval_biology_mean_token_accuracy": 0.7032402672767639,
      "eval_biology_num_tokens": 29317919.0,
      "eval_biology_runtime": 48.611,
      "eval_biology_samples_per_second": 10.286,
      "eval_biology_steps_per_second": 2.571,
      "step": 1500
    },
    {
      "epoch": 2.4,
      "eval_chemistry_entropy": 0.8463425951004029,
      "eval_chemistry_loss": 0.8742334246635437,
      "eval_chemistry_mean_token_accuracy": 0.767361388683319,
      "eval_chemistry_num_tokens": 29317919.0,
      "eval_chemistry_runtime": 59.9689,
      "eval_chemistry_samples_per_second": 8.338,
      "eval_chemistry_steps_per_second": 2.084,
      "step": 1500
    },
    {
      "epoch": 2.4,
      "eval_math_entropy": 0.7472673971652984,
      "eval_math_loss": 0.9761422872543335,
      "eval_math_mean_token_accuracy": 0.7615765709877014,
      "eval_math_num_tokens": 29317919.0,
      "eval_math_runtime": 61.7442,
      "eval_math_samples_per_second": 8.098,
      "eval_math_steps_per_second": 2.024,
      "step": 1500
    },
    {
      "epoch": 2.4,
      "eval_physics_entropy": 0.8270321841239929,
      "eval_physics_loss": 0.8801943063735962,
      "eval_physics_mean_token_accuracy": 0.7734404511451721,
      "eval_physics_num_tokens": 29317919.0,
      "eval_physics_runtime": 70.5165,
      "eval_physics_samples_per_second": 7.091,
      "eval_physics_steps_per_second": 1.773,
      "step": 1500
    },
    {
      "entropy": 1.1317574352025985,
      "epoch": 2.416,
      "grad_norm": 19.625,
      "learning_rate": 1.1044444444444444e-05,
      "loss": 18.3109,
      "mean_token_accuracy": 0.7062701795250177,
      "num_tokens": 29518541.0,
      "step": 1510
    },
    {
      "entropy": 1.130976415425539,
      "epoch": 2.432,
      "grad_norm": 20.25,
      "learning_rate": 1.0970370370370371e-05,
      "loss": 18.1642,
      "mean_token_accuracy": 0.7086035583168269,
      "num_tokens": 29720768.0,
      "step": 1520
    },
    {
      "entropy": 1.1605936624109745,
      "epoch": 2.448,
      "grad_norm": 20.5,
      "learning_rate": 1.0896296296296298e-05,
      "loss": 18.7972,
      "mean_token_accuracy": 0.7010477486997843,
      "num_tokens": 29916619.0,
      "step": 1530
    },
    {
      "entropy": 1.1125331491231918,
      "epoch": 2.464,
      "grad_norm": 20.375,
      "learning_rate": 1.0822222222222222e-05,
      "loss": 17.8199,
      "mean_token_accuracy": 0.7112086053937674,
      "num_tokens": 30121198.0,
      "step": 1540
    },
    {
      "entropy": 1.1271852746605873,
      "epoch": 2.48,
      "grad_norm": 18.5,
      "learning_rate": 1.074814814814815e-05,
      "loss": 18.1447,
      "mean_token_accuracy": 0.707981801405549,
      "num_tokens": 30325508.0,
      "step": 1550
    },
    {
      "entropy": 1.1350488025695085,
      "epoch": 2.496,
      "grad_norm": 17.875,
      "learning_rate": 1.0674074074074074e-05,
      "loss": 18.3331,
      "mean_token_accuracy": 0.706438259780407,
      "num_tokens": 30517445.0,
      "step": 1560
    },
    {
      "entropy": 1.149303700402379,
      "epoch": 2.512,
      "grad_norm": 21.25,
      "learning_rate": 1.0600000000000002e-05,
      "loss": 18.5415,
      "mean_token_accuracy": 0.7031121108680963,
      "num_tokens": 30714049.0,
      "step": 1570
    },
    {
      "entropy": 1.134909725189209,
      "epoch": 2.528,
      "grad_norm": 19.0,
      "learning_rate": 1.0525925925925927e-05,
      "loss": 18.3422,
      "mean_token_accuracy": 0.7059885617345572,
      "num_tokens": 30911317.0,
      "step": 1580
    },
    {
      "entropy": 1.1456572752445937,
      "epoch": 2.544,
      "grad_norm": 17.875,
      "learning_rate": 1.0451851851851853e-05,
      "loss": 18.3318,
      "mean_token_accuracy": 0.70671008490026,
      "num_tokens": 31108983.0,
      "step": 1590
    },
    {
      "entropy": 1.1408224642276763,
      "epoch": 2.56,
      "grad_norm": 18.875,
      "learning_rate": 1.0377777777777778e-05,
      "loss": 18.441,
      "mean_token_accuracy": 0.705613837391138,
      "num_tokens": 31298994.0,
      "step": 1600
    },
    {
      "epoch": 2.56,
      "eval_biology_entropy": 1.1095367937088012,
      "eval_biology_loss": 1.1631091833114624,
      "eval_biology_mean_token_accuracy": 0.7037216110229492,
      "eval_biology_num_tokens": 31298994.0,
      "eval_biology_runtime": 48.5574,
      "eval_biology_samples_per_second": 10.297,
      "eval_biology_steps_per_second": 2.574,
      "step": 1600
    },
    {
      "epoch": 2.56,
      "eval_chemistry_entropy": 0.842681580543518,
      "eval_chemistry_loss": 0.8729196786880493,
      "eval_chemistry_mean_token_accuracy": 0.7677588958740235,
      "eval_chemistry_num_tokens": 31298994.0,
      "eval_chemistry_runtime": 60.3125,
      "eval_chemistry_samples_per_second": 8.29,
      "eval_chemistry_steps_per_second": 2.073,
      "step": 1600
    },
    {
      "epoch": 2.56,
      "eval_math_entropy": 0.7447464742660522,
      "eval_math_loss": 0.9752342700958252,
      "eval_math_mean_token_accuracy": 0.7617981548309326,
      "eval_math_num_tokens": 31298994.0,
      "eval_math_runtime": 61.7884,
      "eval_math_samples_per_second": 8.092,
      "eval_math_steps_per_second": 2.023,
      "step": 1600
    },
    {
      "epoch": 2.56,
      "eval_physics_entropy": 0.8225784077644348,
      "eval_physics_loss": 0.8789661526679993,
      "eval_physics_mean_token_accuracy": 0.7737646398544311,
      "eval_physics_num_tokens": 31298994.0,
      "eval_physics_runtime": 70.3931,
      "eval_physics_samples_per_second": 7.103,
      "eval_physics_steps_per_second": 1.776,
      "step": 1600
    },
    {
      "entropy": 1.152071548998356,
      "epoch": 2.576,
      "grad_norm": 18.5,
      "learning_rate": 1.0303703703703705e-05,
      "loss": 18.5693,
      "mean_token_accuracy": 0.7044297493994236,
      "num_tokens": 31488512.0,
      "step": 1610
    },
    {
      "entropy": 1.1696349333971738,
      "epoch": 2.592,
      "grad_norm": 19.0,
      "learning_rate": 1.0229629629629631e-05,
      "loss": 18.8544,
      "mean_token_accuracy": 0.7005049493163824,
      "num_tokens": 31684651.0,
      "step": 1620
    },
    {
      "entropy": 1.1627265084534883,
      "epoch": 2.608,
      "grad_norm": 19.0,
      "learning_rate": 1.0155555555555556e-05,
      "loss": 18.6882,
      "mean_token_accuracy": 0.7010684039443731,
      "num_tokens": 31876008.0,
      "step": 1630
    },
    {
      "entropy": 1.130651018768549,
      "epoch": 2.624,
      "grad_norm": 19.375,
      "learning_rate": 1.0081481481481484e-05,
      "loss": 18.1415,
      "mean_token_accuracy": 0.7068800464272499,
      "num_tokens": 32069617.0,
      "step": 1640
    },
    {
      "entropy": 1.1576575651764869,
      "epoch": 2.64,
      "grad_norm": 18.25,
      "learning_rate": 1.0007407407407407e-05,
      "loss": 18.7397,
      "mean_token_accuracy": 0.700667466595769,
      "num_tokens": 32262932.0,
      "step": 1650
    },
    {
      "entropy": 1.1208720214664936,
      "epoch": 2.656,
      "grad_norm": 18.625,
      "learning_rate": 9.933333333333334e-06,
      "loss": 17.9602,
      "mean_token_accuracy": 0.7097393788397313,
      "num_tokens": 32465495.0,
      "step": 1660
    },
    {
      "entropy": 1.1169210582971574,
      "epoch": 2.672,
      "grad_norm": 18.5,
      "learning_rate": 9.85925925925926e-06,
      "loss": 18.0691,
      "mean_token_accuracy": 0.7105248533189297,
      "num_tokens": 32665458.0,
      "step": 1670
    },
    {
      "entropy": 1.1241317071020602,
      "epoch": 2.6879999999999997,
      "grad_norm": 18.25,
      "learning_rate": 9.785185185185187e-06,
      "loss": 18.1474,
      "mean_token_accuracy": 0.7082856688648462,
      "num_tokens": 32867135.0,
      "step": 1680
    },
    {
      "entropy": 1.1339986488223075,
      "epoch": 2.7039999999999997,
      "grad_norm": 18.75,
      "learning_rate": 9.711111111111111e-06,
      "loss": 18.2237,
      "mean_token_accuracy": 0.7075312845408916,
      "num_tokens": 33070366.0,
      "step": 1690
    },
    {
      "entropy": 1.1257793482393026,
      "epoch": 2.7199999999999998,
      "grad_norm": 21.0,
      "learning_rate": 9.637037037037038e-06,
      "loss": 18.1537,
      "mean_token_accuracy": 0.707587756216526,
      "num_tokens": 33269122.0,
      "step": 1700
    },
    {
      "epoch": 2.7199999999999998,
      "eval_biology_entropy": 1.1073571362495422,
      "eval_biology_loss": 1.161886215209961,
      "eval_biology_mean_token_accuracy": 0.7041741323471069,
      "eval_biology_num_tokens": 33269122.0,
      "eval_biology_runtime": 48.635,
      "eval_biology_samples_per_second": 10.281,
      "eval_biology_steps_per_second": 2.57,
      "step": 1700
    },
    {
      "epoch": 2.7199999999999998,
      "eval_chemistry_entropy": 0.8408446173667907,
      "eval_chemistry_loss": 0.8714523911476135,
      "eval_chemistry_mean_token_accuracy": 0.7681687192916871,
      "eval_chemistry_num_tokens": 33269122.0,
      "eval_chemistry_runtime": 60.3526,
      "eval_chemistry_samples_per_second": 8.285,
      "eval_chemistry_steps_per_second": 2.071,
      "step": 1700
    },
    {
      "epoch": 2.7199999999999998,
      "eval_math_entropy": 0.74438600897789,
      "eval_math_loss": 0.9744483828544617,
      "eval_math_mean_token_accuracy": 0.7620029444694519,
      "eval_math_num_tokens": 33269122.0,
      "eval_math_runtime": 61.8511,
      "eval_math_samples_per_second": 8.084,
      "eval_math_steps_per_second": 2.021,
      "step": 1700
    },
    {
      "epoch": 2.7199999999999998,
      "eval_physics_entropy": 0.8209939393997192,
      "eval_physics_loss": 0.8775029182434082,
      "eval_physics_mean_token_accuracy": 0.7741135511398315,
      "eval_physics_num_tokens": 33269122.0,
      "eval_physics_runtime": 70.4692,
      "eval_physics_samples_per_second": 7.095,
      "eval_physics_steps_per_second": 1.774,
      "step": 1700
    },
    {
      "entropy": 1.1649049088358878,
      "epoch": 2.7359999999999998,
      "grad_norm": 18.0,
      "learning_rate": 9.562962962962965e-06,
      "loss": 18.7293,
      "mean_token_accuracy": 0.7025999147444963,
      "num_tokens": 33456592.0,
      "step": 1710
    },
    {
      "entropy": 1.15311808437109,
      "epoch": 2.752,
      "grad_norm": 19.25,
      "learning_rate": 9.48888888888889e-06,
      "loss": 18.4325,
      "mean_token_accuracy": 0.7036401994526387,
      "num_tokens": 33645862.0,
      "step": 1720
    },
    {
      "entropy": 1.1674226205796003,
      "epoch": 2.768,
      "grad_norm": 18.75,
      "learning_rate": 9.414814814814816e-06,
      "loss": 18.8481,
      "mean_token_accuracy": 0.699421489983797,
      "num_tokens": 33835740.0,
      "step": 1730
    },
    {
      "entropy": 1.1250699553638697,
      "epoch": 2.784,
      "grad_norm": 18.0,
      "learning_rate": 9.34074074074074e-06,
      "loss": 18.1108,
      "mean_token_accuracy": 0.7099443785846233,
      "num_tokens": 34034702.0,
      "step": 1740
    },
    {
      "entropy": 1.1213359594345094,
      "epoch": 2.8,
      "grad_norm": 17.875,
      "learning_rate": 9.266666666666667e-06,
      "loss": 18.1123,
      "mean_token_accuracy": 0.7095074690878391,
      "num_tokens": 34235603.0,
      "step": 1750
    },
    {
      "entropy": 1.1317555967718362,
      "epoch": 2.816,
      "grad_norm": 19.625,
      "learning_rate": 9.192592592592594e-06,
      "loss": 18.2156,
      "mean_token_accuracy": 0.7085574407130479,
      "num_tokens": 34434833.0,
      "step": 1760
    },
    {
      "entropy": 1.1643431086093188,
      "epoch": 2.832,
      "grad_norm": 19.875,
      "learning_rate": 9.118518518518518e-06,
      "loss": 18.7866,
      "mean_token_accuracy": 0.702312757447362,
      "num_tokens": 34625581.0,
      "step": 1770
    },
    {
      "entropy": 1.1494974169880152,
      "epoch": 2.848,
      "grad_norm": 20.375,
      "learning_rate": 9.044444444444445e-06,
      "loss": 18.5235,
      "mean_token_accuracy": 0.705839891731739,
      "num_tokens": 34816521.0,
      "step": 1780
    },
    {
      "entropy": 1.1289043568074704,
      "epoch": 2.864,
      "grad_norm": 19.125,
      "learning_rate": 8.970370370370372e-06,
      "loss": 18.2474,
      "mean_token_accuracy": 0.7077045034617185,
      "num_tokens": 35013631.0,
      "step": 1790
    },
    {
      "entropy": 1.1608365170657635,
      "epoch": 2.88,
      "grad_norm": 20.75,
      "learning_rate": 8.896296296296298e-06,
      "loss": 18.651,
      "mean_token_accuracy": 0.7021035224199295,
      "num_tokens": 35207800.0,
      "step": 1800
    },
    {
      "epoch": 2.88,
      "eval_biology_entropy": 1.1227384514808654,
      "eval_biology_loss": 1.1606189012527466,
      "eval_biology_mean_token_accuracy": 0.7041417050361634,
      "eval_biology_num_tokens": 35207800.0,
      "eval_biology_runtime": 48.5521,
      "eval_biology_samples_per_second": 10.298,
      "eval_biology_steps_per_second": 2.575,
      "step": 1800
    },
    {
      "epoch": 2.88,
      "eval_chemistry_entropy": 0.8532550582885742,
      "eval_chemistry_loss": 0.8718345761299133,
      "eval_chemistry_mean_token_accuracy": 0.7678817505836487,
      "eval_chemistry_num_tokens": 35207800.0,
      "eval_chemistry_runtime": 60.2048,
      "eval_chemistry_samples_per_second": 8.305,
      "eval_chemistry_steps_per_second": 2.076,
      "step": 1800
    },
    {
      "epoch": 2.88,
      "eval_math_entropy": 0.7495931763648986,
      "eval_math_loss": 0.9741966724395752,
      "eval_math_mean_token_accuracy": 0.7619234776496887,
      "eval_math_num_tokens": 35207800.0,
      "eval_math_runtime": 61.7637,
      "eval_math_samples_per_second": 8.095,
      "eval_math_steps_per_second": 2.024,
      "step": 1800
    },
    {
      "epoch": 2.88,
      "eval_physics_entropy": 0.8320713305473327,
      "eval_physics_loss": 0.8780032992362976,
      "eval_physics_mean_token_accuracy": 0.7738002591133117,
      "eval_physics_num_tokens": 35207800.0,
      "eval_physics_runtime": 70.3744,
      "eval_physics_samples_per_second": 7.105,
      "eval_physics_steps_per_second": 1.776,
      "step": 1800
    },
    {
      "entropy": 1.1618830259889363,
      "epoch": 2.896,
      "grad_norm": 19.0,
      "learning_rate": 8.822222222222223e-06,
      "loss": 18.4927,
      "mean_token_accuracy": 0.7027845978736877,
      "num_tokens": 35402995.0,
      "step": 1810
    },
    {
      "entropy": 1.153843991830945,
      "epoch": 2.912,
      "grad_norm": 19.375,
      "learning_rate": 8.74814814814815e-06,
      "loss": 18.7586,
      "mean_token_accuracy": 0.7019136741757392,
      "num_tokens": 35595456.0,
      "step": 1820
    },
    {
      "entropy": 1.1577350933104753,
      "epoch": 2.928,
      "grad_norm": 19.5,
      "learning_rate": 8.674074074074074e-06,
      "loss": 18.625,
      "mean_token_accuracy": 0.703600461781025,
      "num_tokens": 35787309.0,
      "step": 1830
    },
    {
      "entropy": 1.140915045887232,
      "epoch": 2.944,
      "grad_norm": 17.875,
      "learning_rate": 8.6e-06,
      "loss": 18.3324,
      "mean_token_accuracy": 0.7066537465900182,
      "num_tokens": 35982686.0,
      "step": 1840
    },
    {
      "entropy": 1.1303145423531533,
      "epoch": 2.96,
      "grad_norm": 19.5,
      "learning_rate": 8.525925925925927e-06,
      "loss": 18.2798,
      "mean_token_accuracy": 0.7072657477110624,
      "num_tokens": 36179520.0,
      "step": 1850
    },
    {
      "entropy": 1.1355241533368825,
      "epoch": 2.976,
      "grad_norm": 18.625,
      "learning_rate": 8.451851851851852e-06,
      "loss": 18.3476,
      "mean_token_accuracy": 0.7064431738108397,
      "num_tokens": 36373689.0,
      "step": 1860
    },
    {
      "entropy": 1.1398762241005898,
      "epoch": 2.992,
      "grad_norm": 22.375,
      "learning_rate": 8.377777777777779e-06,
      "loss": 18.4292,
      "mean_token_accuracy": 0.7060572128742933,
      "num_tokens": 36569612.0,
      "step": 1870
    },
    {
      "entropy": 1.1687027130275964,
      "epoch": 3.008,
      "grad_norm": 19.875,
      "learning_rate": 8.303703703703705e-06,
      "loss": 18.6648,
      "mean_token_accuracy": 0.7008682768791914,
      "num_tokens": 36759194.0,
      "step": 1880
    },
    {
      "entropy": 1.1632583592087031,
      "epoch": 3.024,
      "grad_norm": 18.625,
      "learning_rate": 8.229629629629632e-06,
      "loss": 18.7022,
      "mean_token_accuracy": 0.7013984300196171,
      "num_tokens": 36947293.0,
      "step": 1890
    },
    {
      "entropy": 1.1147421635687351,
      "epoch": 3.04,
      "grad_norm": 19.75,
      "learning_rate": 8.155555555555556e-06,
      "loss": 18.0582,
      "mean_token_accuracy": 0.7098672483116388,
      "num_tokens": 37136901.0,
      "step": 1900
    },
    {
      "epoch": 3.04,
      "eval_biology_entropy": 1.1026909346580505,
      "eval_biology_loss": 1.1605921983718872,
      "eval_biology_mean_token_accuracy": 0.7041417622566223,
      "eval_biology_num_tokens": 37136901.0,
      "eval_biology_runtime": 48.5111,
      "eval_biology_samples_per_second": 10.307,
      "eval_biology_steps_per_second": 2.577,
      "step": 1900
    },
    {
      "epoch": 3.04,
      "eval_chemistry_entropy": 0.835658191204071,
      "eval_chemistry_loss": 0.8722280859947205,
      "eval_chemistry_mean_token_accuracy": 0.7677701048851013,
      "eval_chemistry_num_tokens": 37136901.0,
      "eval_chemistry_runtime": 60.1707,
      "eval_chemistry_samples_per_second": 8.31,
      "eval_chemistry_steps_per_second": 2.077,
      "step": 1900
    },
    {
      "epoch": 3.04,
      "eval_math_entropy": 0.7388259909152984,
      "eval_math_loss": 0.9761671423912048,
      "eval_math_mean_token_accuracy": 0.7617930121421814,
      "eval_math_num_tokens": 37136901.0,
      "eval_math_runtime": 61.9396,
      "eval_math_samples_per_second": 8.072,
      "eval_math_steps_per_second": 2.018,
      "step": 1900
    },
    {
      "epoch": 3.04,
      "eval_physics_entropy": 0.8157856950759887,
      "eval_physics_loss": 0.8783439993858337,
      "eval_physics_mean_token_accuracy": 0.7741703715324402,
      "eval_physics_num_tokens": 37136901.0,
      "eval_physics_runtime": 70.3241,
      "eval_physics_samples_per_second": 7.11,
      "eval_physics_steps_per_second": 1.777,
      "step": 1900
    },
    {
      "entropy": 1.1322670388966798,
      "epoch": 3.056,
      "grad_norm": 18.875,
      "learning_rate": 8.081481481481483e-06,
      "loss": 18.1169,
      "mean_token_accuracy": 0.7071005918085576,
      "num_tokens": 37331588.0,
      "step": 1910
    },
    {
      "entropy": 1.1061217069625855,
      "epoch": 3.072,
      "grad_norm": 19.875,
      "learning_rate": 8.007407407407408e-06,
      "loss": 17.7951,
      "mean_token_accuracy": 0.71182203553617,
      "num_tokens": 37521211.0,
      "step": 1920
    },
    {
      "entropy": 1.1269909385591745,
      "epoch": 3.088,
      "grad_norm": 19.125,
      "learning_rate": 7.933333333333334e-06,
      "loss": 18.2156,
      "mean_token_accuracy": 0.7076956331729889,
      "num_tokens": 37713328.0,
      "step": 1930
    },
    {
      "entropy": 1.1100518554449081,
      "epoch": 3.104,
      "grad_norm": 18.625,
      "learning_rate": 7.859259259259259e-06,
      "loss": 17.7995,
      "mean_token_accuracy": 0.7128304049372673,
      "num_tokens": 37913470.0,
      "step": 1940
    },
    {
      "entropy": 1.1166743770241738,
      "epoch": 3.12,
      "grad_norm": 18.5,
      "learning_rate": 7.785185185185185e-06,
      "loss": 18.061,
      "mean_token_accuracy": 0.7102392159402371,
      "num_tokens": 38106718.0,
      "step": 1950
    },
    {
      "entropy": 1.1333389516919852,
      "epoch": 3.136,
      "grad_norm": 20.625,
      "learning_rate": 7.711111111111112e-06,
      "loss": 18.1058,
      "mean_token_accuracy": 0.7095236502587795,
      "num_tokens": 38295701.0,
      "step": 1960
    },
    {
      "entropy": 1.1190204188227653,
      "epoch": 3.152,
      "grad_norm": 19.25,
      "learning_rate": 7.637037037037037e-06,
      "loss": 17.9389,
      "mean_token_accuracy": 0.7105425789952278,
      "num_tokens": 38493951.0,
      "step": 1970
    },
    {
      "entropy": 1.146292532607913,
      "epoch": 3.168,
      "grad_norm": 20.125,
      "learning_rate": 7.562962962962963e-06,
      "loss": 18.4401,
      "mean_token_accuracy": 0.7044953163713217,
      "num_tokens": 38688390.0,
      "step": 1980
    },
    {
      "entropy": 1.1336342521011828,
      "epoch": 3.184,
      "grad_norm": 17.875,
      "learning_rate": 7.48888888888889e-06,
      "loss": 18.2461,
      "mean_token_accuracy": 0.7075372830033302,
      "num_tokens": 38880157.0,
      "step": 1990
    },
    {
      "entropy": 1.110951554775238,
      "epoch": 3.2,
      "grad_norm": 18.5,
      "learning_rate": 7.4148148148148155e-06,
      "loss": 18.0452,
      "mean_token_accuracy": 0.7110834132879973,
      "num_tokens": 39081782.0,
      "step": 2000
    },
    {
      "epoch": 3.2,
      "eval_biology_entropy": 1.0987086420059204,
      "eval_biology_loss": 1.1604441404342651,
      "eval_biology_mean_token_accuracy": 0.7043456192016602,
      "eval_biology_num_tokens": 39081782.0,
      "eval_biology_runtime": 48.5741,
      "eval_biology_samples_per_second": 10.294,
      "eval_biology_steps_per_second": 2.573,
      "step": 2000
    },
    {
      "epoch": 3.2,
      "eval_chemistry_entropy": 0.8334956364631653,
      "eval_chemistry_loss": 0.8719582557678223,
      "eval_chemistry_mean_token_accuracy": 0.7679322199821472,
      "eval_chemistry_num_tokens": 39081782.0,
      "eval_chemistry_runtime": 60.6063,
      "eval_chemistry_samples_per_second": 8.25,
      "eval_chemistry_steps_per_second": 2.062,
      "step": 2000
    },
    {
      "epoch": 3.2,
      "eval_math_entropy": 0.7380490090847015,
      "eval_math_loss": 0.9763364195823669,
      "eval_math_mean_token_accuracy": 0.7618815884590149,
      "eval_math_num_tokens": 39081782.0,
      "eval_math_runtime": 62.6076,
      "eval_math_samples_per_second": 7.986,
      "eval_math_steps_per_second": 1.997,
      "step": 2000
    },
    {
      "epoch": 3.2,
      "eval_physics_entropy": 0.814041579246521,
      "eval_physics_loss": 0.8782714605331421,
      "eval_physics_mean_token_accuracy": 0.7738414001464844,
      "eval_physics_num_tokens": 39081782.0,
      "eval_physics_runtime": 71.4094,
      "eval_physics_samples_per_second": 7.002,
      "eval_physics_steps_per_second": 1.75,
      "step": 2000
    },
    {
      "entropy": 1.1354887392371893,
      "epoch": 3.216,
      "grad_norm": 21.125,
      "learning_rate": 7.340740740740742e-06,
      "loss": 18.2102,
      "mean_token_accuracy": 0.708154209703207,
      "num_tokens": 39275055.0,
      "step": 2010
    },
    {
      "entropy": 1.12113347761333,
      "epoch": 3.232,
      "grad_norm": 20.5,
      "learning_rate": 7.266666666666668e-06,
      "loss": 18.05,
      "mean_token_accuracy": 0.7111630469560624,
      "num_tokens": 39474717.0,
      "step": 2020
    },
    {
      "entropy": 1.1566194161772727,
      "epoch": 3.248,
      "grad_norm": 22.5,
      "learning_rate": 7.192592592592593e-06,
      "loss": 18.5836,
      "mean_token_accuracy": 0.7029663059860468,
      "num_tokens": 39660543.0,
      "step": 2030
    },
    {
      "entropy": 1.1064893435686827,
      "epoch": 3.2640000000000002,
      "grad_norm": 19.875,
      "learning_rate": 7.118518518518519e-06,
      "loss": 17.9265,
      "mean_token_accuracy": 0.7116453271359205,
      "num_tokens": 39866885.0,
      "step": 2040
    },
    {
      "entropy": 1.117007714137435,
      "epoch": 3.2800000000000002,
      "grad_norm": 20.125,
      "learning_rate": 7.044444444444445e-06,
      "loss": 17.9832,
      "mean_token_accuracy": 0.7106686752289534,
      "num_tokens": 40060390.0,
      "step": 2050
    },
    {
      "entropy": 1.133465865254402,
      "epoch": 3.296,
      "grad_norm": 20.625,
      "learning_rate": 6.97037037037037e-06,
      "loss": 18.1734,
      "mean_token_accuracy": 0.7074764121323824,
      "num_tokens": 40253053.0,
      "step": 2060
    },
    {
      "entropy": 1.1380175232887269,
      "epoch": 3.312,
      "grad_norm": 20.25,
      "learning_rate": 6.896296296296297e-06,
      "loss": 18.404,
      "mean_token_accuracy": 0.7049634169787169,
      "num_tokens": 40444210.0,
      "step": 2070
    },
    {
      "entropy": 1.1117772050201893,
      "epoch": 3.328,
      "grad_norm": 19.25,
      "learning_rate": 6.8222222222222225e-06,
      "loss": 17.8341,
      "mean_token_accuracy": 0.7136213395744562,
      "num_tokens": 40644156.0,
      "step": 2080
    },
    {
      "entropy": 1.120354413986206,
      "epoch": 3.344,
      "grad_norm": 20.375,
      "learning_rate": 6.748148148148149e-06,
      "loss": 18.1816,
      "mean_token_accuracy": 0.7078599747270345,
      "num_tokens": 40837974.0,
      "step": 2090
    },
    {
      "entropy": 1.1193263031542302,
      "epoch": 3.36,
      "grad_norm": 18.375,
      "learning_rate": 6.674074074074075e-06,
      "loss": 17.9094,
      "mean_token_accuracy": 0.7105781909078359,
      "num_tokens": 41037512.0,
      "step": 2100
    },
    {
      "epoch": 3.36,
      "eval_biology_entropy": 1.0968467388153076,
      "eval_biology_loss": 1.1601123809814453,
      "eval_biology_mean_token_accuracy": 0.7041891474723816,
      "eval_biology_num_tokens": 41037512.0,
      "eval_biology_runtime": 49.3769,
      "eval_biology_samples_per_second": 10.126,
      "eval_biology_steps_per_second": 2.532,
      "step": 2100
    },
    {
      "epoch": 3.36,
      "eval_chemistry_entropy": 0.8338381066322327,
      "eval_chemistry_loss": 0.8716986775398254,
      "eval_chemistry_mean_token_accuracy": 0.7677229156494141,
      "eval_chemistry_num_tokens": 41037512.0,
      "eval_chemistry_runtime": 61.2003,
      "eval_chemistry_samples_per_second": 8.17,
      "eval_chemistry_steps_per_second": 2.042,
      "step": 2100
    },
    {
      "epoch": 3.36,
      "eval_math_entropy": 0.739958809375763,
      "eval_math_loss": 0.976417601108551,
      "eval_math_mean_token_accuracy": 0.7617873783111573,
      "eval_math_num_tokens": 41037512.0,
      "eval_math_runtime": 62.7508,
      "eval_math_samples_per_second": 7.968,
      "eval_math_steps_per_second": 1.992,
      "step": 2100
    },
    {
      "epoch": 3.36,
      "eval_physics_entropy": 0.8157489862442017,
      "eval_physics_loss": 0.8782733082771301,
      "eval_physics_mean_token_accuracy": 0.7740161881446839,
      "eval_physics_num_tokens": 41037512.0,
      "eval_physics_runtime": 71.4573,
      "eval_physics_samples_per_second": 6.997,
      "eval_physics_steps_per_second": 1.749,
      "step": 2100
    },
    {
      "entropy": 1.1283354975283146,
      "epoch": 3.376,
      "grad_norm": 18.375,
      "learning_rate": 6.600000000000001e-06,
      "loss": 18.2687,
      "mean_token_accuracy": 0.7075107876211405,
      "num_tokens": 41234279.0,
      "step": 2110
    },
    {
      "entropy": 1.164820646867156,
      "epoch": 3.392,
      "grad_norm": 20.125,
      "learning_rate": 6.525925925925927e-06,
      "loss": 18.6247,
      "mean_token_accuracy": 0.7037689939141274,
      "num_tokens": 41427328.0,
      "step": 2120
    },
    {
      "entropy": 1.1609703712165356,
      "epoch": 3.408,
      "grad_norm": 18.5,
      "learning_rate": 6.4518518518518525e-06,
      "loss": 18.6601,
      "mean_token_accuracy": 0.7022816762328148,
      "num_tokens": 41613930.0,
      "step": 2130
    },
    {
      "entropy": 1.118883929029107,
      "epoch": 3.424,
      "grad_norm": 17.375,
      "learning_rate": 6.377777777777778e-06,
      "loss": 18.1224,
      "mean_token_accuracy": 0.7102984309196472,
      "num_tokens": 41809259.0,
      "step": 2140
    },
    {
      "entropy": 1.1378046832978725,
      "epoch": 3.44,
      "grad_norm": 20.25,
      "learning_rate": 6.303703703703704e-06,
      "loss": 18.2796,
      "mean_token_accuracy": 0.7064081773161888,
      "num_tokens": 42008278.0,
      "step": 2150
    },
    {
      "entropy": 1.1136955060064793,
      "epoch": 3.456,
      "grad_norm": 18.625,
      "learning_rate": 6.2296296296296295e-06,
      "loss": 17.9429,
      "mean_token_accuracy": 0.7102738797664643,
      "num_tokens": 42210283.0,
      "step": 2160
    },
    {
      "entropy": 1.1351352456957102,
      "epoch": 3.472,
      "grad_norm": 19.5,
      "learning_rate": 6.155555555555556e-06,
      "loss": 18.2105,
      "mean_token_accuracy": 0.7089967802166939,
      "num_tokens": 42405493.0,
      "step": 2170
    },
    {
      "entropy": 1.0994913596659899,
      "epoch": 3.488,
      "grad_norm": 18.75,
      "learning_rate": 6.081481481481482e-06,
      "loss": 17.6731,
      "mean_token_accuracy": 0.7132742658257485,
      "num_tokens": 42601837.0,
      "step": 2180
    },
    {
      "entropy": 1.1243377164006234,
      "epoch": 3.504,
      "grad_norm": 19.5,
      "learning_rate": 6.007407407407407e-06,
      "loss": 18.1375,
      "mean_token_accuracy": 0.7097833503037692,
      "num_tokens": 42798533.0,
      "step": 2190
    },
    {
      "entropy": 1.1014703746885062,
      "epoch": 3.52,
      "grad_norm": 20.75,
      "learning_rate": 5.933333333333335e-06,
      "loss": 17.8044,
      "mean_token_accuracy": 0.712919196113944,
      "num_tokens": 43001779.0,
      "step": 2200
    },
    {
      "epoch": 3.52,
      "eval_biology_entropy": 1.0952841796875,
      "eval_biology_loss": 1.1598260402679443,
      "eval_biology_mean_token_accuracy": 0.7040795273780823,
      "eval_biology_num_tokens": 43001779.0,
      "eval_biology_runtime": 48.6822,
      "eval_biology_samples_per_second": 10.271,
      "eval_biology_steps_per_second": 2.568,
      "step": 2200
    },
    {
      "epoch": 3.52,
      "eval_chemistry_entropy": 0.8339877910614014,
      "eval_chemistry_loss": 0.8721098899841309,
      "eval_chemistry_mean_token_accuracy": 0.7680032277107238,
      "eval_chemistry_num_tokens": 43001779.0,
      "eval_chemistry_runtime": 60.3472,
      "eval_chemistry_samples_per_second": 8.285,
      "eval_chemistry_steps_per_second": 2.071,
      "step": 2200
    },
    {
      "epoch": 3.52,
      "eval_math_entropy": 0.7390543642044067,
      "eval_math_loss": 0.9761691093444824,
      "eval_math_mean_token_accuracy": 0.7619256863594055,
      "eval_math_num_tokens": 43001779.0,
      "eval_math_runtime": 61.856,
      "eval_math_samples_per_second": 8.083,
      "eval_math_steps_per_second": 2.021,
      "step": 2200
    },
    {
      "epoch": 3.52,
      "eval_physics_entropy": 0.8150221276283264,
      "eval_physics_loss": 0.8782007098197937,
      "eval_physics_mean_token_accuracy": 0.773835651397705,
      "eval_physics_num_tokens": 43001779.0,
      "eval_physics_runtime": 70.5185,
      "eval_physics_samples_per_second": 7.09,
      "eval_physics_steps_per_second": 1.773,
      "step": 2200
    },
    {
      "entropy": 1.131494064256549,
      "epoch": 3.536,
      "grad_norm": 18.75,
      "learning_rate": 5.85925925925926e-06,
      "loss": 18.2698,
      "mean_token_accuracy": 0.7066725388169288,
      "num_tokens": 43192229.0,
      "step": 2210
    },
    {
      "entropy": 1.1356515496969224,
      "epoch": 3.552,
      "grad_norm": 19.75,
      "learning_rate": 5.785185185185186e-06,
      "loss": 18.2761,
      "mean_token_accuracy": 0.7078566204756498,
      "num_tokens": 43386416.0,
      "step": 2220
    },
    {
      "entropy": 1.1160131219774485,
      "epoch": 3.568,
      "grad_norm": 19.375,
      "learning_rate": 5.711111111111112e-06,
      "loss": 17.9301,
      "mean_token_accuracy": 0.711183400452137,
      "num_tokens": 43586122.0,
      "step": 2230
    },
    {
      "entropy": 1.1139442063868046,
      "epoch": 3.584,
      "grad_norm": 19.125,
      "learning_rate": 5.637037037037037e-06,
      "loss": 17.9737,
      "mean_token_accuracy": 0.7113449327647686,
      "num_tokens": 43783769.0,
      "step": 2240
    },
    {
      "entropy": 1.1195767130702734,
      "epoch": 3.6,
      "grad_norm": 21.125,
      "learning_rate": 5.562962962962963e-06,
      "loss": 17.9187,
      "mean_token_accuracy": 0.7108651768416167,
      "num_tokens": 43973235.0,
      "step": 2250
    },
    {
      "entropy": 1.0934316322207451,
      "epoch": 3.616,
      "grad_norm": 19.125,
      "learning_rate": 5.4888888888888895e-06,
      "loss": 17.6835,
      "mean_token_accuracy": 0.713237265124917,
      "num_tokens": 44176594.0,
      "step": 2260
    },
    {
      "entropy": 1.1332040429115295,
      "epoch": 3.632,
      "grad_norm": 21.375,
      "learning_rate": 5.414814814814815e-06,
      "loss": 18.1103,
      "mean_token_accuracy": 0.7089979019016027,
      "num_tokens": 44377465.0,
      "step": 2270
    },
    {
      "entropy": 1.1584312468767166,
      "epoch": 3.648,
      "grad_norm": 19.875,
      "learning_rate": 5.340740740740741e-06,
      "loss": 18.7558,
      "mean_token_accuracy": 0.7008867420256137,
      "num_tokens": 44569130.0,
      "step": 2280
    },
    {
      "entropy": 1.1106038503348827,
      "epoch": 3.664,
      "grad_norm": 18.875,
      "learning_rate": 5.2666666666666665e-06,
      "loss": 17.7824,
      "mean_token_accuracy": 0.7132147330790758,
      "num_tokens": 44772500.0,
      "step": 2290
    },
    {
      "entropy": 1.115388607978821,
      "epoch": 3.68,
      "grad_norm": 19.0,
      "learning_rate": 5.192592592592594e-06,
      "loss": 18.0662,
      "mean_token_accuracy": 0.7111902508884669,
      "num_tokens": 44972326.0,
      "step": 2300
    },
    {
      "epoch": 3.68,
      "eval_biology_entropy": 1.0993176627159118,
      "eval_biology_loss": 1.1593457460403442,
      "eval_biology_mean_token_accuracy": 0.7043005504608154,
      "eval_biology_num_tokens": 44972326.0,
      "eval_biology_runtime": 48.6262,
      "eval_biology_samples_per_second": 10.283,
      "eval_biology_steps_per_second": 2.571,
      "step": 2300
    },
    {
      "epoch": 3.68,
      "eval_chemistry_entropy": 0.8339422068595886,
      "eval_chemistry_loss": 0.8719797134399414,
      "eval_chemistry_mean_token_accuracy": 0.7679404969215393,
      "eval_chemistry_num_tokens": 44972326.0,
      "eval_chemistry_runtime": 60.2942,
      "eval_chemistry_samples_per_second": 8.293,
      "eval_chemistry_steps_per_second": 2.073,
      "step": 2300
    },
    {
      "epoch": 3.68,
      "eval_math_entropy": 0.7411710631847381,
      "eval_math_loss": 0.9758427143096924,
      "eval_math_mean_token_accuracy": 0.7618683638572693,
      "eval_math_num_tokens": 44972326.0,
      "eval_math_runtime": 61.768,
      "eval_math_samples_per_second": 8.095,
      "eval_math_steps_per_second": 2.024,
      "step": 2300
    },
    {
      "epoch": 3.68,
      "eval_physics_entropy": 0.8151098203659057,
      "eval_physics_loss": 0.8783143162727356,
      "eval_physics_mean_token_accuracy": 0.7738341612815857,
      "eval_physics_num_tokens": 44972326.0,
      "eval_physics_runtime": 70.3991,
      "eval_physics_samples_per_second": 7.102,
      "eval_physics_steps_per_second": 1.776,
      "step": 2300
    },
    {
      "entropy": 1.1294588424265384,
      "epoch": 3.6959999999999997,
      "grad_norm": 20.125,
      "learning_rate": 5.1185185185185195e-06,
      "loss": 18.2591,
      "mean_token_accuracy": 0.7078940033912658,
      "num_tokens": 45171386.0,
      "step": 2310
    },
    {
      "entropy": 1.1489933133125305,
      "epoch": 3.7119999999999997,
      "grad_norm": 18.625,
      "learning_rate": 5.044444444444445e-06,
      "loss": 18.4725,
      "mean_token_accuracy": 0.705705888569355,
      "num_tokens": 45361017.0,
      "step": 2320
    },
    {
      "entropy": 1.1155077636241912,
      "epoch": 3.7279999999999998,
      "grad_norm": 19.375,
      "learning_rate": 4.970370370370371e-06,
      "loss": 17.9265,
      "mean_token_accuracy": 0.7115162432193756,
      "num_tokens": 45561773.0,
      "step": 2330
    },
    {
      "entropy": 1.1495999217033386,
      "epoch": 3.7439999999999998,
      "grad_norm": 19.0,
      "learning_rate": 4.8962962962962965e-06,
      "loss": 18.516,
      "mean_token_accuracy": 0.7043994337320327,
      "num_tokens": 45753014.0,
      "step": 2340
    },
    {
      "entropy": 1.13122322447598,
      "epoch": 3.76,
      "grad_norm": 20.75,
      "learning_rate": 4.822222222222222e-06,
      "loss": 18.2202,
      "mean_token_accuracy": 0.7084156259894371,
      "num_tokens": 45947397.0,
      "step": 2350
    },
    {
      "entropy": 1.122436200082302,
      "epoch": 3.776,
      "grad_norm": 18.125,
      "learning_rate": 4.748148148148149e-06,
      "loss": 18.0499,
      "mean_token_accuracy": 0.7104008805006743,
      "num_tokens": 46143253.0,
      "step": 2360
    },
    {
      "entropy": 1.1514490522444247,
      "epoch": 3.792,
      "grad_norm": 18.625,
      "learning_rate": 4.674074074074074e-06,
      "loss": 18.549,
      "mean_token_accuracy": 0.7031971588730812,
      "num_tokens": 46337744.0,
      "step": 2370
    },
    {
      "entropy": 1.119861488416791,
      "epoch": 3.808,
      "grad_norm": 19.875,
      "learning_rate": 4.600000000000001e-06,
      "loss": 18.087,
      "mean_token_accuracy": 0.7108966052532196,
      "num_tokens": 46528272.0,
      "step": 2380
    },
    {
      "entropy": 1.135647664964199,
      "epoch": 3.824,
      "grad_norm": 19.125,
      "learning_rate": 4.5259259259259265e-06,
      "loss": 18.3009,
      "mean_token_accuracy": 0.7064112696796656,
      "num_tokens": 46719274.0,
      "step": 2390
    },
    {
      "entropy": 1.114129998907447,
      "epoch": 3.84,
      "grad_norm": 19.125,
      "learning_rate": 4.451851851851852e-06,
      "loss": 17.9589,
      "mean_token_accuracy": 0.7134663391858339,
      "num_tokens": 46916027.0,
      "step": 2400
    },
    {
      "epoch": 3.84,
      "eval_biology_entropy": 1.1034115777015685,
      "eval_biology_loss": 1.1590811014175415,
      "eval_biology_mean_token_accuracy": 0.7044289937019348,
      "eval_biology_num_tokens": 46916027.0,
      "eval_biology_runtime": 48.5938,
      "eval_biology_samples_per_second": 10.289,
      "eval_biology_steps_per_second": 2.572,
      "step": 2400
    },
    {
      "epoch": 3.84,
      "eval_chemistry_entropy": 0.8372816433906555,
      "eval_chemistry_loss": 0.8715822696685791,
      "eval_chemistry_mean_token_accuracy": 0.7678695392608642,
      "eval_chemistry_num_tokens": 46916027.0,
      "eval_chemistry_runtime": 60.2605,
      "eval_chemistry_samples_per_second": 8.297,
      "eval_chemistry_steps_per_second": 2.074,
      "step": 2400
    },
    {
      "epoch": 3.84,
      "eval_math_entropy": 0.7421645526885986,
      "eval_math_loss": 0.9759746193885803,
      "eval_math_mean_token_accuracy": 0.7618973565101623,
      "eval_math_num_tokens": 46916027.0,
      "eval_math_runtime": 61.9787,
      "eval_math_samples_per_second": 8.067,
      "eval_math_steps_per_second": 2.017,
      "step": 2400
    },
    {
      "epoch": 3.84,
      "eval_physics_entropy": 0.8176065077781677,
      "eval_physics_loss": 0.8779301643371582,
      "eval_physics_mean_token_accuracy": 0.774030951499939,
      "eval_physics_num_tokens": 46916027.0,
      "eval_physics_runtime": 70.3314,
      "eval_physics_samples_per_second": 7.109,
      "eval_physics_steps_per_second": 1.777,
      "step": 2400
    },
    {
      "entropy": 1.1277068488299846,
      "epoch": 3.856,
      "grad_norm": 20.125,
      "learning_rate": 4.377777777777778e-06,
      "loss": 18.0574,
      "mean_token_accuracy": 0.7107046756893396,
      "num_tokens": 47114880.0,
      "step": 2410
    },
    {
      "entropy": 1.144086579605937,
      "epoch": 3.872,
      "grad_norm": 19.125,
      "learning_rate": 4.3037037037037035e-06,
      "loss": 18.3726,
      "mean_token_accuracy": 0.7060531999915838,
      "num_tokens": 47311977.0,
      "step": 2420
    },
    {
      "entropy": 1.119268636032939,
      "epoch": 3.888,
      "grad_norm": 19.875,
      "learning_rate": 4.22962962962963e-06,
      "loss": 18.0165,
      "mean_token_accuracy": 0.7108395133167505,
      "num_tokens": 47509800.0,
      "step": 2430
    },
    {
      "entropy": 1.124232827872038,
      "epoch": 3.904,
      "grad_norm": 19.25,
      "learning_rate": 4.155555555555556e-06,
      "loss": 18.1055,
      "mean_token_accuracy": 0.7098960153758526,
      "num_tokens": 47704018.0,
      "step": 2440
    },
    {
      "entropy": 1.1140838485211133,
      "epoch": 3.92,
      "grad_norm": 18.875,
      "learning_rate": 4.081481481481482e-06,
      "loss": 17.8969,
      "mean_token_accuracy": 0.7108140826225281,
      "num_tokens": 47903745.0,
      "step": 2450
    },
    {
      "entropy": 1.1396939534693957,
      "epoch": 3.936,
      "grad_norm": 20.25,
      "learning_rate": 4.007407407407408e-06,
      "loss": 18.3584,
      "mean_token_accuracy": 0.7066603232175112,
      "num_tokens": 48102312.0,
      "step": 2460
    },
    {
      "entropy": 1.1124013729393483,
      "epoch": 3.952,
      "grad_norm": 18.75,
      "learning_rate": 3.9333333333333335e-06,
      "loss": 17.9989,
      "mean_token_accuracy": 0.7095886286348104,
      "num_tokens": 48299684.0,
      "step": 2470
    },
    {
      "entropy": 1.144656204432249,
      "epoch": 3.968,
      "grad_norm": 21.5,
      "learning_rate": 3.85925925925926e-06,
      "loss": 18.405,
      "mean_token_accuracy": 0.7056023754179478,
      "num_tokens": 48496831.0,
      "step": 2480
    },
    {
      "entropy": 1.126984755322337,
      "epoch": 3.984,
      "grad_norm": 18.625,
      "learning_rate": 3.7851851851851857e-06,
      "loss": 18.1717,
      "mean_token_accuracy": 0.7091844279319048,
      "num_tokens": 48694070.0,
      "step": 2490
    },
    {
      "entropy": 1.1470630817115306,
      "epoch": 4.0,
      "grad_norm": 20.5,
      "learning_rate": 3.7111111111111113e-06,
      "loss": 18.6232,
      "mean_token_accuracy": 0.7034741207957268,
      "num_tokens": 48885164.0,
      "step": 2500
    },
    {
      "epoch": 4.0,
      "eval_biology_entropy": 1.100130069732666,
      "eval_biology_loss": 1.1589951515197754,
      "eval_biology_mean_token_accuracy": 0.7041674499511719,
      "eval_biology_num_tokens": 48885164.0,
      "eval_biology_runtime": 48.5982,
      "eval_biology_samples_per_second": 10.288,
      "eval_biology_steps_per_second": 2.572,
      "step": 2500
    },
    {
      "epoch": 4.0,
      "eval_chemistry_entropy": 0.8349951648712158,
      "eval_chemistry_loss": 0.8717024326324463,
      "eval_chemistry_mean_token_accuracy": 0.7677888073921204,
      "eval_chemistry_num_tokens": 48885164.0,
      "eval_chemistry_runtime": 60.793,
      "eval_chemistry_samples_per_second": 8.225,
      "eval_chemistry_steps_per_second": 2.056,
      "step": 2500
    },
    {
      "epoch": 4.0,
      "eval_math_entropy": 0.7401801931858063,
      "eval_math_loss": 0.9758692383766174,
      "eval_math_mean_token_accuracy": 0.7619253330230713,
      "eval_math_num_tokens": 48885164.0,
      "eval_math_runtime": 62.6315,
      "eval_math_samples_per_second": 7.983,
      "eval_math_steps_per_second": 1.996,
      "step": 2500
    },
    {
      "epoch": 4.0,
      "eval_physics_entropy": 0.815434151172638,
      "eval_physics_loss": 0.8780592679977417,
      "eval_physics_mean_token_accuracy": 0.7740482540130615,
      "eval_physics_num_tokens": 48885164.0,
      "eval_physics_runtime": 70.9878,
      "eval_physics_samples_per_second": 7.043,
      "eval_physics_steps_per_second": 1.761,
      "step": 2500
    },
    {
      "entropy": 1.1160879634320735,
      "epoch": 4.016,
      "grad_norm": 18.875,
      "learning_rate": 3.6370370370370374e-06,
      "loss": 17.8992,
      "mean_token_accuracy": 0.7137045960873365,
      "num_tokens": 49083717.0,
      "step": 2510
    },
    {
      "entropy": 1.1370587714016438,
      "epoch": 4.032,
      "grad_norm": 18.875,
      "learning_rate": 3.562962962962963e-06,
      "loss": 18.2029,
      "mean_token_accuracy": 0.7086552571505308,
      "num_tokens": 49282689.0,
      "step": 2520
    },
    {
      "entropy": 1.1187588647007942,
      "epoch": 4.048,
      "grad_norm": 21.75,
      "learning_rate": 3.4888888888888896e-06,
      "loss": 17.936,
      "mean_token_accuracy": 0.7125615429133176,
      "num_tokens": 49480172.0,
      "step": 2530
    },
    {
      "entropy": 1.1416249305009842,
      "epoch": 4.064,
      "grad_norm": 21.25,
      "learning_rate": 3.4148148148148153e-06,
      "loss": 18.4587,
      "mean_token_accuracy": 0.7071565296500921,
      "num_tokens": 49670167.0,
      "step": 2540
    },
    {
      "entropy": 1.1168063767254353,
      "epoch": 4.08,
      "grad_norm": 19.625,
      "learning_rate": 3.340740740740741e-06,
      "loss": 17.962,
      "mean_token_accuracy": 0.7106139473617077,
      "num_tokens": 49866326.0,
      "step": 2550
    },
    {
      "entropy": 1.1387323811650276,
      "epoch": 4.096,
      "grad_norm": 17.625,
      "learning_rate": 3.266666666666667e-06,
      "loss": 18.2881,
      "mean_token_accuracy": 0.7052336398512125,
      "num_tokens": 50056950.0,
      "step": 2560
    },
    {
      "entropy": 1.1328555908054114,
      "epoch": 4.112,
      "grad_norm": 19.75,
      "learning_rate": 3.1925925925925927e-06,
      "loss": 18.169,
      "mean_token_accuracy": 0.7100179735571146,
      "num_tokens": 50251768.0,
      "step": 2570
    },
    {
      "entropy": 1.1460201136767865,
      "epoch": 4.128,
      "grad_norm": 20.25,
      "learning_rate": 3.1185185185185183e-06,
      "loss": 18.5196,
      "mean_token_accuracy": 0.7043800208717584,
      "num_tokens": 50444319.0,
      "step": 2580
    },
    {
      "entropy": 1.1398494437336921,
      "epoch": 4.144,
      "grad_norm": 19.75,
      "learning_rate": 3.044444444444445e-06,
      "loss": 18.2388,
      "mean_token_accuracy": 0.7064049437642097,
      "num_tokens": 50631631.0,
      "step": 2590
    },
    {
      "entropy": 1.141350831091404,
      "epoch": 4.16,
      "grad_norm": 19.125,
      "learning_rate": 2.9703703703703705e-06,
      "loss": 18.3667,
      "mean_token_accuracy": 0.7068084985017776,
      "num_tokens": 50826513.0,
      "step": 2600
    },
    {
      "epoch": 4.16,
      "eval_biology_entropy": 1.0955388507843018,
      "eval_biology_loss": 1.1590566635131836,
      "eval_biology_mean_token_accuracy": 0.7045985751152039,
      "eval_biology_num_tokens": 50826513.0,
      "eval_biology_runtime": 48.7104,
      "eval_biology_samples_per_second": 10.265,
      "eval_biology_steps_per_second": 2.566,
      "step": 2600
    },
    {
      "epoch": 4.16,
      "eval_chemistry_entropy": 0.8316172590255737,
      "eval_chemistry_loss": 0.8717626333236694,
      "eval_chemistry_mean_token_accuracy": 0.767913815498352,
      "eval_chemistry_num_tokens": 50826513.0,
      "eval_chemistry_runtime": 60.7653,
      "eval_chemistry_samples_per_second": 8.228,
      "eval_chemistry_steps_per_second": 2.057,
      "step": 2600
    },
    {
      "epoch": 4.16,
      "eval_math_entropy": 0.7378519124984741,
      "eval_math_loss": 0.9764444828033447,
      "eval_math_mean_token_accuracy": 0.7619533925056458,
      "eval_math_num_tokens": 50826513.0,
      "eval_math_runtime": 61.9671,
      "eval_math_samples_per_second": 8.069,
      "eval_math_steps_per_second": 2.017,
      "step": 2600
    },
    {
      "epoch": 4.16,
      "eval_physics_entropy": 0.8122129874229431,
      "eval_physics_loss": 0.878105878829956,
      "eval_physics_mean_token_accuracy": 0.7741021389961242,
      "eval_physics_num_tokens": 50826513.0,
      "eval_physics_runtime": 70.6183,
      "eval_physics_samples_per_second": 7.08,
      "eval_physics_steps_per_second": 1.77,
      "step": 2600
    },
    {
      "entropy": 1.1222807440906764,
      "epoch": 4.176,
      "grad_norm": 19.125,
      "learning_rate": 2.8962962962962966e-06,
      "loss": 18.0717,
      "mean_token_accuracy": 0.7091497462242842,
      "num_tokens": 51026177.0,
      "step": 2610
    },
    {
      "entropy": 1.1358438849449157,
      "epoch": 4.192,
      "grad_norm": 20.125,
      "learning_rate": 2.8222222222222223e-06,
      "loss": 18.2249,
      "mean_token_accuracy": 0.7061910640448332,
      "num_tokens": 51218570.0,
      "step": 2620
    },
    {
      "entropy": 1.108224703371525,
      "epoch": 4.208,
      "grad_norm": 18.125,
      "learning_rate": 2.748148148148148e-06,
      "loss": 17.8847,
      "mean_token_accuracy": 0.7117452036589385,
      "num_tokens": 51417937.0,
      "step": 2630
    },
    {
      "entropy": 1.121630134433508,
      "epoch": 4.224,
      "grad_norm": 18.625,
      "learning_rate": 2.6740740740740744e-06,
      "loss": 18.071,
      "mean_token_accuracy": 0.7106337703764438,
      "num_tokens": 51615267.0,
      "step": 2640
    },
    {
      "entropy": 1.0866072356700898,
      "epoch": 4.24,
      "grad_norm": 19.5,
      "learning_rate": 2.6e-06,
      "loss": 17.4428,
      "mean_token_accuracy": 0.716962655633688,
      "num_tokens": 51815136.0,
      "step": 2650
    },
    {
      "entropy": 1.0989352997392416,
      "epoch": 4.256,
      "grad_norm": 18.375,
      "learning_rate": 2.525925925925926e-06,
      "loss": 17.5111,
      "mean_token_accuracy": 0.7172319073230028,
      "num_tokens": 52018293.0,
      "step": 2660
    },
    {
      "entropy": 1.1121397718787194,
      "epoch": 4.272,
      "grad_norm": 18.75,
      "learning_rate": 2.451851851851852e-06,
      "loss": 17.8373,
      "mean_token_accuracy": 0.713592042773962,
      "num_tokens": 52214165.0,
      "step": 2670
    },
    {
      "entropy": 1.0949925631284714,
      "epoch": 4.288,
      "grad_norm": 18.875,
      "learning_rate": 2.377777777777778e-06,
      "loss": 17.6726,
      "mean_token_accuracy": 0.714476003870368,
      "num_tokens": 52422210.0,
      "step": 2680
    },
    {
      "entropy": 1.1069289091974497,
      "epoch": 4.304,
      "grad_norm": 19.125,
      "learning_rate": 2.303703703703704e-06,
      "loss": 17.7715,
      "mean_token_accuracy": 0.7128037516027689,
      "num_tokens": 52617031.0,
      "step": 2690
    },
    {
      "entropy": 1.1163511652499438,
      "epoch": 4.32,
      "grad_norm": 18.375,
      "learning_rate": 2.22962962962963e-06,
      "loss": 18.0913,
      "mean_token_accuracy": 0.7107409708201885,
      "num_tokens": 52814574.0,
      "step": 2700
    },
    {
      "epoch": 4.32,
      "eval_biology_entropy": 1.0932833123207093,
      "eval_biology_loss": 1.1590940952301025,
      "eval_biology_mean_token_accuracy": 0.7046565957069397,
      "eval_biology_num_tokens": 52814574.0,
      "eval_biology_runtime": 49.2743,
      "eval_biology_samples_per_second": 10.147,
      "eval_biology_steps_per_second": 2.537,
      "step": 2700
    },
    {
      "epoch": 4.32,
      "eval_chemistry_entropy": 0.8303835077285766,
      "eval_chemistry_loss": 0.87211012840271,
      "eval_chemistry_mean_token_accuracy": 0.7680432667732239,
      "eval_chemistry_num_tokens": 52814574.0,
      "eval_chemistry_runtime": 60.8922,
      "eval_chemistry_samples_per_second": 8.211,
      "eval_chemistry_steps_per_second": 2.053,
      "step": 2700
    },
    {
      "epoch": 4.32,
      "eval_math_entropy": 0.7375843653678894,
      "eval_math_loss": 0.9766404032707214,
      "eval_math_mean_token_accuracy": 0.7619228887557984,
      "eval_math_num_tokens": 52814574.0,
      "eval_math_runtime": 62.4061,
      "eval_math_samples_per_second": 8.012,
      "eval_math_steps_per_second": 2.003,
      "step": 2700
    },
    {
      "epoch": 4.32,
      "eval_physics_entropy": 0.8115231275558472,
      "eval_physics_loss": 0.8783358335494995,
      "eval_physics_mean_token_accuracy": 0.7739383320808411,
      "eval_physics_num_tokens": 52814574.0,
      "eval_physics_runtime": 71.1956,
      "eval_physics_samples_per_second": 7.023,
      "eval_physics_steps_per_second": 1.756,
      "step": 2700
    },
    {
      "entropy": 1.1100974697619677,
      "epoch": 4.336,
      "grad_norm": 20.5,
      "learning_rate": 2.1555555555555558e-06,
      "loss": 17.9798,
      "mean_token_accuracy": 0.7109350692480803,
      "num_tokens": 53013899.0,
      "step": 2710
    },
    {
      "entropy": 1.1317887622863054,
      "epoch": 4.352,
      "grad_norm": 18.625,
      "learning_rate": 2.0814814814814814e-06,
      "loss": 18.2432,
      "mean_token_accuracy": 0.7078307528048754,
      "num_tokens": 53209262.0,
      "step": 2720
    },
    {
      "entropy": 1.12730851508677,
      "epoch": 4.368,
      "grad_norm": 19.875,
      "learning_rate": 2.0074074074074075e-06,
      "loss": 18.0828,
      "mean_token_accuracy": 0.7095625881105662,
      "num_tokens": 53404971.0,
      "step": 2730
    },
    {
      "entropy": 1.134312851727009,
      "epoch": 4.384,
      "grad_norm": 19.375,
      "learning_rate": 1.9333333333333336e-06,
      "loss": 18.2957,
      "mean_token_accuracy": 0.7060767561197281,
      "num_tokens": 53594766.0,
      "step": 2740
    },
    {
      "entropy": 1.1393331296741962,
      "epoch": 4.4,
      "grad_norm": 21.0,
      "learning_rate": 1.8592592592592595e-06,
      "loss": 18.418,
      "mean_token_accuracy": 0.7064639564603568,
      "num_tokens": 53787876.0,
      "step": 2750
    },
    {
      "entropy": 1.1089225117117167,
      "epoch": 4.416,
      "grad_norm": 19.375,
      "learning_rate": 1.7851851851851853e-06,
      "loss": 17.8242,
      "mean_token_accuracy": 0.7097496975213289,
      "num_tokens": 53991437.0,
      "step": 2760
    },
    {
      "entropy": 1.1256129287183285,
      "epoch": 4.432,
      "grad_norm": 20.0,
      "learning_rate": 1.7111111111111112e-06,
      "loss": 18.0238,
      "mean_token_accuracy": 0.7105293430387973,
      "num_tokens": 54191547.0,
      "step": 2770
    },
    {
      "entropy": 1.113245976343751,
      "epoch": 4.448,
      "grad_norm": 20.375,
      "learning_rate": 1.6370370370370373e-06,
      "loss": 17.7909,
      "mean_token_accuracy": 0.7116924650967121,
      "num_tokens": 54385194.0,
      "step": 2780
    },
    {
      "entropy": 1.124070692807436,
      "epoch": 4.464,
      "grad_norm": 19.0,
      "learning_rate": 1.562962962962963e-06,
      "loss": 18.0812,
      "mean_token_accuracy": 0.7098761692643165,
      "num_tokens": 54577099.0,
      "step": 2790
    },
    {
      "entropy": 1.1426789626479148,
      "epoch": 4.48,
      "grad_norm": 20.375,
      "learning_rate": 1.4888888888888888e-06,
      "loss": 18.4486,
      "mean_token_accuracy": 0.705568815022707,
      "num_tokens": 54769022.0,
      "step": 2800
    },
    {
      "epoch": 4.48,
      "eval_biology_entropy": 1.0955566415786744,
      "eval_biology_loss": 1.1589276790618896,
      "eval_biology_mean_token_accuracy": 0.7042924590110778,
      "eval_biology_num_tokens": 54769022.0,
      "eval_biology_runtime": 48.5409,
      "eval_biology_samples_per_second": 10.301,
      "eval_biology_steps_per_second": 2.575,
      "step": 2800
    },
    {
      "epoch": 4.48,
      "eval_chemistry_entropy": 0.831970660686493,
      "eval_chemistry_loss": 0.871811032295227,
      "eval_chemistry_mean_token_accuracy": 0.7678974647521972,
      "eval_chemistry_num_tokens": 54769022.0,
      "eval_chemistry_runtime": 60.2241,
      "eval_chemistry_samples_per_second": 8.302,
      "eval_chemistry_steps_per_second": 2.076,
      "step": 2800
    },
    {
      "epoch": 4.48,
      "eval_math_entropy": 0.7386114675998687,
      "eval_math_loss": 0.9762167930603027,
      "eval_math_mean_token_accuracy": 0.7621296954154968,
      "eval_math_num_tokens": 54769022.0,
      "eval_math_runtime": 61.8181,
      "eval_math_samples_per_second": 8.088,
      "eval_math_steps_per_second": 2.022,
      "step": 2800
    },
    {
      "epoch": 4.48,
      "eval_physics_entropy": 0.8128011884689331,
      "eval_physics_loss": 0.8782095909118652,
      "eval_physics_mean_token_accuracy": 0.7740145058631897,
      "eval_physics_num_tokens": 54769022.0,
      "eval_physics_runtime": 70.385,
      "eval_physics_samples_per_second": 7.104,
      "eval_physics_steps_per_second": 1.776,
      "step": 2800
    },
    {
      "entropy": 1.1157229054719209,
      "epoch": 4.496,
      "grad_norm": 18.0,
      "learning_rate": 1.414814814814815e-06,
      "loss": 17.9071,
      "mean_token_accuracy": 0.7103788953274488,
      "num_tokens": 54968338.0,
      "step": 2810
    },
    {
      "entropy": 1.1294743590056897,
      "epoch": 4.5120000000000005,
      "grad_norm": 19.875,
      "learning_rate": 1.3407407407407408e-06,
      "loss": 18.2126,
      "mean_token_accuracy": 0.7076791927218438,
      "num_tokens": 55167039.0,
      "step": 2820
    },
    {
      "entropy": 1.1057243023067713,
      "epoch": 4.5280000000000005,
      "grad_norm": 18.625,
      "learning_rate": 1.2666666666666669e-06,
      "loss": 17.7167,
      "mean_token_accuracy": 0.7155276846140624,
      "num_tokens": 55369598.0,
      "step": 2830
    },
    {
      "entropy": 1.1095443222671748,
      "epoch": 4.5440000000000005,
      "grad_norm": 20.125,
      "learning_rate": 1.1925925925925928e-06,
      "loss": 17.8819,
      "mean_token_accuracy": 0.7097273614257574,
      "num_tokens": 55563629.0,
      "step": 2840
    },
    {
      "entropy": 1.1140538066625596,
      "epoch": 4.5600000000000005,
      "grad_norm": 20.125,
      "learning_rate": 1.1185185185185186e-06,
      "loss": 17.9501,
      "mean_token_accuracy": 0.7119776252657175,
      "num_tokens": 55759240.0,
      "step": 2850
    },
    {
      "entropy": 1.1115111865103244,
      "epoch": 4.576,
      "grad_norm": 20.375,
      "learning_rate": 1.0444444444444445e-06,
      "loss": 17.9192,
      "mean_token_accuracy": 0.711128744110465,
      "num_tokens": 55953631.0,
      "step": 2860
    },
    {
      "entropy": 1.1233138255774975,
      "epoch": 4.592,
      "grad_norm": 21.0,
      "learning_rate": 9.703703703703704e-07,
      "loss": 18.1225,
      "mean_token_accuracy": 0.7096393074840307,
      "num_tokens": 56150202.0,
      "step": 2870
    },
    {
      "entropy": 1.1561065390706062,
      "epoch": 4.608,
      "grad_norm": 21.25,
      "learning_rate": 8.962962962962964e-07,
      "loss": 18.6791,
      "mean_token_accuracy": 0.7017291557043791,
      "num_tokens": 56336358.0,
      "step": 2880
    },
    {
      "entropy": 1.140657200664282,
      "epoch": 4.624,
      "grad_norm": 18.5,
      "learning_rate": 8.222222222222223e-07,
      "loss": 18.4252,
      "mean_token_accuracy": 0.7071378316730261,
      "num_tokens": 56532634.0,
      "step": 2890
    },
    {
      "entropy": 1.117747975513339,
      "epoch": 4.64,
      "grad_norm": 20.625,
      "learning_rate": 7.481481481481482e-07,
      "loss": 18.0552,
      "mean_token_accuracy": 0.7107968173921109,
      "num_tokens": 56721597.0,
      "step": 2900
    },
    {
      "epoch": 4.64,
      "eval_biology_entropy": 1.095109058856964,
      "eval_biology_loss": 1.1590646505355835,
      "eval_biology_mean_token_accuracy": 0.7044678544998169,
      "eval_biology_num_tokens": 56721597.0,
      "eval_biology_runtime": 48.5811,
      "eval_biology_samples_per_second": 10.292,
      "eval_biology_steps_per_second": 2.573,
      "step": 2900
    },
    {
      "epoch": 4.64,
      "eval_chemistry_entropy": 0.8311039981842041,
      "eval_chemistry_loss": 0.8717870712280273,
      "eval_chemistry_mean_token_accuracy": 0.7681379013061523,
      "eval_chemistry_num_tokens": 56721597.0,
      "eval_chemistry_runtime": 60.3714,
      "eval_chemistry_samples_per_second": 8.282,
      "eval_chemistry_steps_per_second": 2.071,
      "step": 2900
    },
    {
      "epoch": 4.64,
      "eval_math_entropy": 0.7375130612850189,
      "eval_math_loss": 0.9765008687973022,
      "eval_math_mean_token_accuracy": 0.7620035552978516,
      "eval_math_num_tokens": 56721597.0,
      "eval_math_runtime": 61.7727,
      "eval_math_samples_per_second": 8.094,
      "eval_math_steps_per_second": 2.024,
      "step": 2900
    },
    {
      "epoch": 4.64,
      "eval_physics_entropy": 0.8118382081985474,
      "eval_physics_loss": 0.8782839775085449,
      "eval_physics_mean_token_accuracy": 0.7739185023307801,
      "eval_physics_num_tokens": 56721597.0,
      "eval_physics_runtime": 70.3938,
      "eval_physics_samples_per_second": 7.103,
      "eval_physics_steps_per_second": 1.776,
      "step": 2900
    },
    {
      "entropy": 1.1298798985779286,
      "epoch": 4.656,
      "grad_norm": 19.5,
      "learning_rate": 6.740740740740741e-07,
      "loss": 18.1305,
      "mean_token_accuracy": 0.708253213763237,
      "num_tokens": 56915763.0,
      "step": 2910
    },
    {
      "entropy": 1.1272273954004048,
      "epoch": 4.672,
      "grad_norm": 17.625,
      "learning_rate": 6.000000000000001e-07,
      "loss": 18.2545,
      "mean_token_accuracy": 0.7086662597954273,
      "num_tokens": 57106674.0,
      "step": 2920
    },
    {
      "entropy": 1.1215174172073603,
      "epoch": 4.688,
      "grad_norm": 20.0,
      "learning_rate": 5.25925925925926e-07,
      "loss": 18.2098,
      "mean_token_accuracy": 0.7087991438806057,
      "num_tokens": 57308644.0,
      "step": 2930
    },
    {
      "entropy": 1.1302482053637504,
      "epoch": 4.704,
      "grad_norm": 19.875,
      "learning_rate": 4.518518518518519e-07,
      "loss": 18.1629,
      "mean_token_accuracy": 0.7095564223825932,
      "num_tokens": 57503295.0,
      "step": 2940
    },
    {
      "entropy": 1.1331190101802349,
      "epoch": 4.72,
      "grad_norm": 19.5,
      "learning_rate": 3.777777777777778e-07,
      "loss": 18.3343,
      "mean_token_accuracy": 0.7055216923356056,
      "num_tokens": 57694635.0,
      "step": 2950
    },
    {
      "entropy": 1.1156794786453248,
      "epoch": 4.736,
      "grad_norm": 18.125,
      "learning_rate": 3.0370370370370374e-07,
      "loss": 17.967,
      "mean_token_accuracy": 0.7111107666045428,
      "num_tokens": 57898052.0,
      "step": 2960
    },
    {
      "entropy": 1.122471484914422,
      "epoch": 4.752,
      "grad_norm": 18.75,
      "learning_rate": 2.2962962962962964e-07,
      "loss": 18.0766,
      "mean_token_accuracy": 0.7092397723346948,
      "num_tokens": 58091828.0,
      "step": 2970
    },
    {
      "entropy": 1.0995518658310175,
      "epoch": 4.768,
      "grad_norm": 18.375,
      "learning_rate": 1.5555555555555556e-07,
      "loss": 17.5004,
      "mean_token_accuracy": 0.7156328197568655,
      "num_tokens": 58290608.0,
      "step": 2980
    },
    {
      "entropy": 1.1175754133611917,
      "epoch": 4.784,
      "grad_norm": 21.25,
      "learning_rate": 8.148148148148148e-08,
      "loss": 18.0567,
      "mean_token_accuracy": 0.7084891442209482,
      "num_tokens": 58491415.0,
      "step": 2990
    },
    {
      "entropy": 1.134732787311077,
      "epoch": 4.8,
      "grad_norm": 21.0,
      "learning_rate": 7.407407407407408e-09,
      "loss": 18.1648,
      "mean_token_accuracy": 0.7078682146966457,
      "num_tokens": 58681639.0,
      "step": 3000
    },
    {
      "epoch": 4.8,
      "eval_biology_entropy": 1.095814537525177,
      "eval_biology_loss": 1.1591075658798218,
      "eval_biology_mean_token_accuracy": 0.7045488510131835,
      "eval_biology_num_tokens": 58681639.0,
      "eval_biology_runtime": 49.2299,
      "eval_biology_samples_per_second": 10.156,
      "eval_biology_steps_per_second": 2.539,
      "step": 3000
    },
    {
      "epoch": 4.8,
      "eval_chemistry_entropy": 0.8320227708816529,
      "eval_chemistry_loss": 0.8718997836112976,
      "eval_chemistry_mean_token_accuracy": 0.7678845291137695,
      "eval_chemistry_num_tokens": 58681639.0,
      "eval_chemistry_runtime": 60.1789,
      "eval_chemistry_samples_per_second": 8.309,
      "eval_chemistry_steps_per_second": 2.077,
      "step": 3000
    },
    {
      "epoch": 4.8,
      "eval_math_entropy": 0.7383916871547699,
      "eval_math_loss": 0.9763190746307373,
      "eval_math_mean_token_accuracy": 0.7621074786186218,
      "eval_math_num_tokens": 58681639.0,
      "eval_math_runtime": 62.0839,
      "eval_math_samples_per_second": 8.054,
      "eval_math_steps_per_second": 2.013,
      "step": 3000
    },
    {
      "epoch": 4.8,
      "eval_physics_entropy": 0.8127228660583496,
      "eval_physics_loss": 0.878301739692688,
      "eval_physics_mean_token_accuracy": 0.7740593042373657,
      "eval_physics_num_tokens": 58681639.0,
      "eval_physics_runtime": 70.7249,
      "eval_physics_samples_per_second": 7.07,
      "eval_physics_steps_per_second": 1.767,
      "step": 3000
    }
  ],
  "logging_steps": 10,
  "max_steps": 3000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.622995707307729e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}