{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5847953216374269,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 3.011503052711487,
      "epoch": 0.005847953216374269,
      "grad_norm": 35.75,
      "learning_rate": 2e-06,
      "loss": 14.1046,
      "mean_token_accuracy": 0.035688506253063676,
      "num_tokens": 13999.0,
      "step": 5
    },
    {
      "entropy": 3.1570172786712645,
      "epoch": 0.011695906432748537,
      "grad_norm": 33.0,
      "learning_rate": 4.5e-06,
      "loss": 13.9181,
      "mean_token_accuracy": 0.037344493344426154,
      "num_tokens": 25888.0,
      "step": 10
    },
    {
      "entropy": 3.506499719619751,
      "epoch": 0.017543859649122806,
      "grad_norm": 39.0,
      "learning_rate": 7e-06,
      "loss": 13.4816,
      "mean_token_accuracy": 0.033669637702405456,
      "num_tokens": 37699.0,
      "step": 15
    },
    {
      "entropy": 4.382130026817322,
      "epoch": 0.023391812865497075,
      "grad_norm": 39.5,
      "learning_rate": 9.5e-06,
      "loss": 12.8513,
      "mean_token_accuracy": 0.019791487697511913,
      "num_tokens": 49648.0,
      "step": 20
    },
    {
      "entropy": 7.491881942749023,
      "epoch": 0.029239766081871343,
      "grad_norm": 14.5625,
      "learning_rate": 1.2e-05,
      "loss": 11.2853,
      "mean_token_accuracy": 0.019448780827224253,
      "num_tokens": 62255.0,
      "step": 25
    },
    {
      "entropy": 10.010943794250489,
      "epoch": 0.03508771929824561,
      "grad_norm": 4.84375,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.7751,
      "mean_token_accuracy": 0.00878947232849896,
      "num_tokens": 76003.0,
      "step": 30
    },
    {
      "entropy": 10.62158660888672,
      "epoch": 0.04093567251461988,
      "grad_norm": 3.40625,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.5825,
      "mean_token_accuracy": 0.009877379098907114,
      "num_tokens": 87585.0,
      "step": 35
    },
    {
      "entropy": 10.41454849243164,
      "epoch": 0.04678362573099415,
      "grad_norm": 4.59375,
      "learning_rate": 1.95e-05,
      "loss": 10.1549,
      "mean_token_accuracy": 0.019071799516677857,
      "num_tokens": 100404.0,
      "step": 40
    },
    {
      "entropy": 10.373588752746581,
      "epoch": 0.05263157894736842,
      "grad_norm": 2.421875,
      "learning_rate": 2.2e-05,
      "loss": 9.91,
      "mean_token_accuracy": 0.0510077447630465,
      "num_tokens": 113130.0,
      "step": 45
    },
    {
      "entropy": 10.290110111236572,
      "epoch": 0.05847953216374269,
      "grad_norm": 2.65625,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.5708,
      "mean_token_accuracy": 0.08142316564917565,
      "num_tokens": 125430.0,
      "step": 50
    },
    {
      "entropy": 10.002687644958495,
      "epoch": 0.06432748538011696,
      "grad_norm": 3.078125,
      "learning_rate": 2.7e-05,
      "loss": 9.5528,
      "mean_token_accuracy": 0.0672168917953968,
      "num_tokens": 137550.0,
      "step": 55
    },
    {
      "entropy": 10.2318941116333,
      "epoch": 0.07017543859649122,
      "grad_norm": 1.90625,
      "learning_rate": 2.95e-05,
      "loss": 9.4611,
      "mean_token_accuracy": 0.07226917184889317,
      "num_tokens": 149530.0,
      "step": 60
    },
    {
      "entropy": 10.194271087646484,
      "epoch": 0.07602339181286549,
      "grad_norm": 2.375,
      "learning_rate": 3.2e-05,
      "loss": 9.4491,
      "mean_token_accuracy": 0.07329789400100709,
      "num_tokens": 161671.0,
      "step": 65
    },
    {
      "entropy": 10.232907676696778,
      "epoch": 0.08187134502923976,
      "grad_norm": 1.6796875,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.4074,
      "mean_token_accuracy": 0.0754720564931631,
      "num_tokens": 174160.0,
      "step": 70
    },
    {
      "entropy": 10.223019981384278,
      "epoch": 0.08771929824561403,
      "grad_norm": 1.90625,
      "learning_rate": 3.7e-05,
      "loss": 9.357,
      "mean_token_accuracy": 0.06809913516044616,
      "num_tokens": 186969.0,
      "step": 75
    },
    {
      "entropy": 9.965007305145264,
      "epoch": 0.0935672514619883,
      "grad_norm": 1.59375,
      "learning_rate": 3.95e-05,
      "loss": 9.2625,
      "mean_token_accuracy": 0.0748597014695406,
      "num_tokens": 199470.0,
      "step": 80
    },
    {
      "entropy": 10.107829475402832,
      "epoch": 0.09941520467836257,
      "grad_norm": 1.8984375,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.1703,
      "mean_token_accuracy": 0.07800811901688576,
      "num_tokens": 211306.0,
      "step": 85
    },
    {
      "entropy": 9.909124755859375,
      "epoch": 0.10526315789473684,
      "grad_norm": 1.8203125,
      "learning_rate": 4.45e-05,
      "loss": 9.1713,
      "mean_token_accuracy": 0.07304236702620984,
      "num_tokens": 223323.0,
      "step": 90
    },
    {
      "entropy": 10.078854656219482,
      "epoch": 0.1111111111111111,
      "grad_norm": 1.953125,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.0578,
      "mean_token_accuracy": 0.08289388790726662,
      "num_tokens": 235896.0,
      "step": 95
    },
    {
      "entropy": 9.830192375183106,
      "epoch": 0.11695906432748537,
      "grad_norm": 2.5,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.021,
      "mean_token_accuracy": 0.07751639671623707,
      "num_tokens": 247879.0,
      "step": 100
    },
    {
      "entropy": 9.94895429611206,
      "epoch": 0.12280701754385964,
      "grad_norm": 1.5234375,
      "learning_rate": 5.2e-05,
      "loss": 8.9105,
      "mean_token_accuracy": 0.07603972963988781,
      "num_tokens": 259714.0,
      "step": 105
    },
    {
      "entropy": 9.896305179595947,
      "epoch": 0.1286549707602339,
      "grad_norm": 1.578125,
      "learning_rate": 5.45e-05,
      "loss": 8.8763,
      "mean_token_accuracy": 0.08195686042308807,
      "num_tokens": 272429.0,
      "step": 110
    },
    {
      "entropy": 9.760246086120606,
      "epoch": 0.13450292397660818,
      "grad_norm": 1.328125,
      "learning_rate": 5.7e-05,
      "loss": 8.8484,
      "mean_token_accuracy": 0.07280035950243473,
      "num_tokens": 285924.0,
      "step": 115
    },
    {
      "entropy": 9.702124404907227,
      "epoch": 0.14035087719298245,
      "grad_norm": 1.40625,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.6942,
      "mean_token_accuracy": 0.08684460520744323,
      "num_tokens": 299453.0,
      "step": 120
    },
    {
      "entropy": 9.505807209014893,
      "epoch": 0.14619883040935672,
      "grad_norm": 1.296875,
      "learning_rate": 6.2e-05,
      "loss": 8.6969,
      "mean_token_accuracy": 0.0838764600455761,
      "num_tokens": 312295.0,
      "step": 125
    },
    {
      "entropy": 9.498956871032714,
      "epoch": 0.15204678362573099,
      "grad_norm": 1.3046875,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.5488,
      "mean_token_accuracy": 0.08384966105222702,
      "num_tokens": 324730.0,
      "step": 130
    },
    {
      "entropy": 9.271528625488282,
      "epoch": 0.15789473684210525,
      "grad_norm": 1.234375,
      "learning_rate": 6.7e-05,
      "loss": 8.4801,
      "mean_token_accuracy": 0.08416559919714928,
      "num_tokens": 336481.0,
      "step": 135
    },
    {
      "entropy": 9.22463436126709,
      "epoch": 0.16374269005847952,
      "grad_norm": 1.4296875,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.4865,
      "mean_token_accuracy": 0.08492137640714645,
      "num_tokens": 348987.0,
      "step": 140
    },
    {
      "entropy": 9.034030055999756,
      "epoch": 0.1695906432748538,
      "grad_norm": 0.90234375,
      "learning_rate": 7.2e-05,
      "loss": 8.3974,
      "mean_token_accuracy": 0.08240444362163543,
      "num_tokens": 360390.0,
      "step": 145
    },
    {
      "entropy": 8.999344062805175,
      "epoch": 0.17543859649122806,
      "grad_norm": 0.96875,
      "learning_rate": 7.45e-05,
      "loss": 8.4036,
      "mean_token_accuracy": 0.08263231143355369,
      "num_tokens": 372456.0,
      "step": 150
    },
    {
      "entropy": 8.908535861968994,
      "epoch": 0.18128654970760233,
      "grad_norm": 0.8671875,
      "learning_rate": 7.7e-05,
      "loss": 8.3422,
      "mean_token_accuracy": 0.07766095399856568,
      "num_tokens": 384185.0,
      "step": 155
    },
    {
      "entropy": 8.835869979858398,
      "epoch": 0.1871345029239766,
      "grad_norm": 1.0078125,
      "learning_rate": 7.950000000000001e-05,
      "loss": 8.3227,
      "mean_token_accuracy": 0.08606852069497109,
      "num_tokens": 395399.0,
      "step": 160
    },
    {
      "entropy": 8.697229862213135,
      "epoch": 0.19298245614035087,
      "grad_norm": 0.953125,
      "learning_rate": 8.2e-05,
      "loss": 8.337,
      "mean_token_accuracy": 0.08855125159025193,
      "num_tokens": 408676.0,
      "step": 165
    },
    {
      "entropy": 8.610207080841064,
      "epoch": 0.19883040935672514,
      "grad_norm": 1.0078125,
      "learning_rate": 8.450000000000001e-05,
      "loss": 8.3123,
      "mean_token_accuracy": 0.08628950268030167,
      "num_tokens": 421861.0,
      "step": 170
    },
    {
      "entropy": 8.750581073760987,
      "epoch": 0.2046783625730994,
      "grad_norm": 0.99609375,
      "learning_rate": 8.7e-05,
      "loss": 8.353,
      "mean_token_accuracy": 0.09162932708859443,
      "num_tokens": 434852.0,
      "step": 175
    },
    {
      "entropy": 8.575475406646728,
      "epoch": 0.21052631578947367,
      "grad_norm": 0.9921875,
      "learning_rate": 8.95e-05,
      "loss": 8.3025,
      "mean_token_accuracy": 0.08264983892440796,
      "num_tokens": 447313.0,
      "step": 180
    },
    {
      "entropy": 8.66052532196045,
      "epoch": 0.21637426900584794,
      "grad_norm": 1.328125,
      "learning_rate": 9.2e-05,
      "loss": 8.242,
      "mean_token_accuracy": 0.09072699844837188,
      "num_tokens": 460271.0,
      "step": 185
    },
    {
      "entropy": 8.458691787719726,
      "epoch": 0.2222222222222222,
      "grad_norm": 1.5703125,
      "learning_rate": 9.45e-05,
      "loss": 8.2117,
      "mean_token_accuracy": 0.0964887373149395,
      "num_tokens": 473006.0,
      "step": 190
    },
    {
      "entropy": 8.625473880767823,
      "epoch": 0.22807017543859648,
      "grad_norm": 1.0390625,
      "learning_rate": 9.7e-05,
      "loss": 8.2416,
      "mean_token_accuracy": 0.08616446778178215,
      "num_tokens": 486100.0,
      "step": 195
    },
    {
      "entropy": 8.410247135162354,
      "epoch": 0.23391812865497075,
      "grad_norm": 1.1328125,
      "learning_rate": 9.95e-05,
      "loss": 8.1352,
      "mean_token_accuracy": 0.09261524304747581,
      "num_tokens": 499460.0,
      "step": 200
    },
    {
      "entropy": 8.550405311584473,
      "epoch": 0.23976608187134502,
      "grad_norm": 1.0703125,
      "learning_rate": 0.000102,
      "loss": 8.1476,
      "mean_token_accuracy": 0.091904778778553,
      "num_tokens": 511795.0,
      "step": 205
    },
    {
      "entropy": 8.412632751464844,
      "epoch": 0.24561403508771928,
      "grad_norm": 0.953125,
      "learning_rate": 0.00010449999999999999,
      "loss": 8.204,
      "mean_token_accuracy": 0.09843768626451492,
      "num_tokens": 524897.0,
      "step": 210
    },
    {
      "entropy": 8.52775535583496,
      "epoch": 0.25146198830409355,
      "grad_norm": 1.296875,
      "learning_rate": 0.000107,
      "loss": 8.1374,
      "mean_token_accuracy": 0.09786352440714836,
      "num_tokens": 538325.0,
      "step": 215
    },
    {
      "entropy": 8.386085700988769,
      "epoch": 0.2573099415204678,
      "grad_norm": 0.96484375,
      "learning_rate": 0.0001095,
      "loss": 8.1911,
      "mean_token_accuracy": 0.09132648184895516,
      "num_tokens": 550979.0,
      "step": 220
    },
    {
      "entropy": 8.483522033691406,
      "epoch": 0.2631578947368421,
      "grad_norm": 1.484375,
      "learning_rate": 0.000112,
      "loss": 8.1602,
      "mean_token_accuracy": 0.09506673067808151,
      "num_tokens": 563001.0,
      "step": 225
    },
    {
      "entropy": 8.336331844329834,
      "epoch": 0.26900584795321636,
      "grad_norm": 1.5390625,
      "learning_rate": 0.0001145,
      "loss": 8.0781,
      "mean_token_accuracy": 0.09937207028269768,
      "num_tokens": 573600.0,
      "step": 230
    },
    {
      "entropy": 8.444112873077392,
      "epoch": 0.27485380116959063,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00011700000000000001,
      "loss": 8.0893,
      "mean_token_accuracy": 0.10078474283218383,
      "num_tokens": 585287.0,
      "step": 235
    },
    {
      "entropy": 8.33163080215454,
      "epoch": 0.2807017543859649,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00011949999999999999,
      "loss": 8.1193,
      "mean_token_accuracy": 0.09278298616409301,
      "num_tokens": 597386.0,
      "step": 240
    },
    {
      "entropy": 8.417845058441163,
      "epoch": 0.28654970760233917,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000122,
      "loss": 8.0979,
      "mean_token_accuracy": 0.09884399548172951,
      "num_tokens": 609256.0,
      "step": 245
    },
    {
      "entropy": 8.383094787597656,
      "epoch": 0.29239766081871343,
      "grad_norm": 1.4140625,
      "learning_rate": 0.0001245,
      "loss": 8.0968,
      "mean_token_accuracy": 0.10301539301872253,
      "num_tokens": 621506.0,
      "step": 250
    },
    {
      "entropy": 8.22484188079834,
      "epoch": 0.2982456140350877,
      "grad_norm": 1.3984375,
      "learning_rate": 0.000127,
      "loss": 8.0108,
      "mean_token_accuracy": 0.10739858150482177,
      "num_tokens": 633512.0,
      "step": 255
    },
    {
      "entropy": 8.35753002166748,
      "epoch": 0.30409356725146197,
      "grad_norm": 1.15625,
      "learning_rate": 0.0001295,
      "loss": 8.1404,
      "mean_token_accuracy": 0.09757127910852433,
      "num_tokens": 647098.0,
      "step": 260
    },
    {
      "entropy": 8.389013767242432,
      "epoch": 0.30994152046783624,
      "grad_norm": 1.0390625,
      "learning_rate": 0.000132,
      "loss": 8.1411,
      "mean_token_accuracy": 0.09518403038382531,
      "num_tokens": 659559.0,
      "step": 265
    },
    {
      "entropy": 8.338126182556152,
      "epoch": 0.3157894736842105,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00013450000000000002,
      "loss": 8.0745,
      "mean_token_accuracy": 0.09692913815379142,
      "num_tokens": 672621.0,
      "step": 270
    },
    {
      "entropy": 8.312376308441163,
      "epoch": 0.3216374269005848,
      "grad_norm": 2.828125,
      "learning_rate": 0.00013700000000000002,
      "loss": 8.0387,
      "mean_token_accuracy": 0.10461566746234893,
      "num_tokens": 685652.0,
      "step": 275
    },
    {
      "entropy": 8.29957218170166,
      "epoch": 0.32748538011695905,
      "grad_norm": 1.171875,
      "learning_rate": 0.0001395,
      "loss": 8.0998,
      "mean_token_accuracy": 0.10161212980747222,
      "num_tokens": 696910.0,
      "step": 280
    },
    {
      "entropy": 8.248525142669678,
      "epoch": 0.3333333333333333,
      "grad_norm": 1.640625,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.9659,
      "mean_token_accuracy": 0.10607651099562646,
      "num_tokens": 709054.0,
      "step": 285
    },
    {
      "entropy": 8.277126693725586,
      "epoch": 0.3391812865497076,
      "grad_norm": 0.94921875,
      "learning_rate": 0.0001445,
      "loss": 7.997,
      "mean_token_accuracy": 0.1044411912560463,
      "num_tokens": 720902.0,
      "step": 290
    },
    {
      "entropy": 8.320906162261963,
      "epoch": 0.34502923976608185,
      "grad_norm": 1.203125,
      "learning_rate": 0.000147,
      "loss": 8.0586,
      "mean_token_accuracy": 0.10378434732556344,
      "num_tokens": 733319.0,
      "step": 295
    },
    {
      "entropy": 8.274054527282715,
      "epoch": 0.3508771929824561,
      "grad_norm": 1.15625,
      "learning_rate": 0.0001495,
      "loss": 7.9508,
      "mean_token_accuracy": 0.10693862661719322,
      "num_tokens": 744817.0,
      "step": 300
    },
    {
      "entropy": 8.191329860687256,
      "epoch": 0.3567251461988304,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000152,
      "loss": 8.0044,
      "mean_token_accuracy": 0.1035879172384739,
      "num_tokens": 756582.0,
      "step": 305
    },
    {
      "entropy": 8.263913822174072,
      "epoch": 0.36257309941520466,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.9151,
      "mean_token_accuracy": 0.1130017727613449,
      "num_tokens": 769273.0,
      "step": 310
    },
    {
      "entropy": 8.111418914794921,
      "epoch": 0.3684210526315789,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000157,
      "loss": 7.9862,
      "mean_token_accuracy": 0.10989293605089187,
      "num_tokens": 782001.0,
      "step": 315
    },
    {
      "entropy": 8.221540355682373,
      "epoch": 0.3742690058479532,
      "grad_norm": 1.421875,
      "learning_rate": 0.0001595,
      "loss": 7.9703,
      "mean_token_accuracy": 0.112515377253294,
      "num_tokens": 794575.0,
      "step": 320
    },
    {
      "entropy": 8.238408851623536,
      "epoch": 0.38011695906432746,
      "grad_norm": 1.34375,
      "learning_rate": 0.000162,
      "loss": 7.9488,
      "mean_token_accuracy": 0.10909051299095154,
      "num_tokens": 805583.0,
      "step": 325
    },
    {
      "entropy": 8.123234272003174,
      "epoch": 0.38596491228070173,
      "grad_norm": 1.65625,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.993,
      "mean_token_accuracy": 0.10957283899188042,
      "num_tokens": 817617.0,
      "step": 330
    },
    {
      "entropy": 8.23239221572876,
      "epoch": 0.391812865497076,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.8943,
      "mean_token_accuracy": 0.11208963096141815,
      "num_tokens": 830043.0,
      "step": 335
    },
    {
      "entropy": 8.07594804763794,
      "epoch": 0.39766081871345027,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.8714,
      "mean_token_accuracy": 0.1205448180437088,
      "num_tokens": 843200.0,
      "step": 340
    },
    {
      "entropy": 8.210996723175048,
      "epoch": 0.40350877192982454,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.918,
      "mean_token_accuracy": 0.11632056310772895,
      "num_tokens": 856031.0,
      "step": 345
    },
    {
      "entropy": 8.029043245315552,
      "epoch": 0.4093567251461988,
      "grad_norm": 1.1875,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.8883,
      "mean_token_accuracy": 0.11492086499929428,
      "num_tokens": 869119.0,
      "step": 350
    },
    {
      "entropy": 8.107694482803344,
      "epoch": 0.4152046783625731,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000177,
      "loss": 7.9053,
      "mean_token_accuracy": 0.11929167732596398,
      "num_tokens": 880802.0,
      "step": 355
    },
    {
      "entropy": 8.145207405090332,
      "epoch": 0.42105263157894735,
      "grad_norm": 1.078125,
      "learning_rate": 0.0001795,
      "loss": 7.8911,
      "mean_token_accuracy": 0.1157754972577095,
      "num_tokens": 894237.0,
      "step": 360
    },
    {
      "entropy": 8.104444217681884,
      "epoch": 0.4269005847953216,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000182,
      "loss": 7.9097,
      "mean_token_accuracy": 0.11690913587808609,
      "num_tokens": 906695.0,
      "step": 365
    },
    {
      "entropy": 8.126790809631348,
      "epoch": 0.4327485380116959,
      "grad_norm": 1.7109375,
      "learning_rate": 0.0001845,
      "loss": 7.8766,
      "mean_token_accuracy": 0.11690322905778885,
      "num_tokens": 918955.0,
      "step": 370
    },
    {
      "entropy": 8.079369258880615,
      "epoch": 0.43859649122807015,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000187,
      "loss": 7.9117,
      "mean_token_accuracy": 0.11631168648600579,
      "num_tokens": 931812.0,
      "step": 375
    },
    {
      "entropy": 8.124732828140258,
      "epoch": 0.4444444444444444,
      "grad_norm": 0.984375,
      "learning_rate": 0.0001895,
      "loss": 7.9105,
      "mean_token_accuracy": 0.10793866887688637,
      "num_tokens": 945261.0,
      "step": 380
    },
    {
      "entropy": 8.059471893310548,
      "epoch": 0.4502923976608187,
      "grad_norm": 1.2109375,
      "learning_rate": 0.000192,
      "loss": 7.8211,
      "mean_token_accuracy": 0.12420412302017211,
      "num_tokens": 958376.0,
      "step": 385
    },
    {
      "entropy": 8.045862627029418,
      "epoch": 0.45614035087719296,
      "grad_norm": 1.0,
      "learning_rate": 0.0001945,
      "loss": 7.8396,
      "mean_token_accuracy": 0.12700849547982215,
      "num_tokens": 971709.0,
      "step": 390
    },
    {
      "entropy": 8.091754007339478,
      "epoch": 0.4619883040935672,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.8096,
      "mean_token_accuracy": 0.1235598661005497,
      "num_tokens": 983847.0,
      "step": 395
    },
    {
      "entropy": 8.116325187683106,
      "epoch": 0.4678362573099415,
      "grad_norm": 1.15625,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.8836,
      "mean_token_accuracy": 0.11197860836982727,
      "num_tokens": 997034.0,
      "step": 400
    },
    {
      "entropy": 7.948489475250244,
      "epoch": 0.47368421052631576,
      "grad_norm": 1.2109375,
      "learning_rate": 0.000202,
      "loss": 7.9183,
      "mean_token_accuracy": 0.11601087674498559,
      "num_tokens": 1010213.0,
      "step": 405
    },
    {
      "entropy": 8.183907890319825,
      "epoch": 0.47953216374269003,
      "grad_norm": 1.3984375,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.7917,
      "mean_token_accuracy": 0.11840821728110314,
      "num_tokens": 1021618.0,
      "step": 410
    },
    {
      "entropy": 8.002576017379761,
      "epoch": 0.4853801169590643,
      "grad_norm": 1.125,
      "learning_rate": 0.000207,
      "loss": 7.8151,
      "mean_token_accuracy": 0.11744796931743622,
      "num_tokens": 1033809.0,
      "step": 415
    },
    {
      "entropy": 8.077327156066895,
      "epoch": 0.49122807017543857,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0002095,
      "loss": 7.8025,
      "mean_token_accuracy": 0.11957534328103066,
      "num_tokens": 1045291.0,
      "step": 420
    },
    {
      "entropy": 8.03057599067688,
      "epoch": 0.49707602339181284,
      "grad_norm": 1.4375,
      "learning_rate": 0.000212,
      "loss": 7.7792,
      "mean_token_accuracy": 0.11945864260196686,
      "num_tokens": 1057516.0,
      "step": 425
    },
    {
      "entropy": 7.868794345855713,
      "epoch": 0.5029239766081871,
      "grad_norm": 0.98828125,
      "learning_rate": 0.0002145,
      "loss": 7.7351,
      "mean_token_accuracy": 0.12831166237592698,
      "num_tokens": 1070675.0,
      "step": 430
    },
    {
      "entropy": 8.045708703994752,
      "epoch": 0.5087719298245614,
      "grad_norm": 1.234375,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.8167,
      "mean_token_accuracy": 0.12775540575385094,
      "num_tokens": 1082965.0,
      "step": 435
    },
    {
      "entropy": 7.97526912689209,
      "epoch": 0.5146198830409356,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0002195,
      "loss": 7.7974,
      "mean_token_accuracy": 0.11712993755936622,
      "num_tokens": 1095922.0,
      "step": 440
    },
    {
      "entropy": 7.9973499298095705,
      "epoch": 0.52046783625731,
      "grad_norm": 1.21875,
      "learning_rate": 0.000222,
      "loss": 7.7752,
      "mean_token_accuracy": 0.12419187352061271,
      "num_tokens": 1109002.0,
      "step": 445
    },
    {
      "entropy": 8.025882577896118,
      "epoch": 0.5263157894736842,
      "grad_norm": 1.3046875,
      "learning_rate": 0.0002245,
      "loss": 7.7881,
      "mean_token_accuracy": 0.11773632392287255,
      "num_tokens": 1121199.0,
      "step": 450
    },
    {
      "entropy": 7.909945821762085,
      "epoch": 0.5321637426900585,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00022700000000000002,
      "loss": 7.7307,
      "mean_token_accuracy": 0.12722171917557717,
      "num_tokens": 1134721.0,
      "step": 455
    },
    {
      "entropy": 7.956731367111206,
      "epoch": 0.5380116959064327,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.7963,
      "mean_token_accuracy": 0.12164180129766464,
      "num_tokens": 1147954.0,
      "step": 460
    },
    {
      "entropy": 7.956630373001099,
      "epoch": 0.543859649122807,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.7275,
      "mean_token_accuracy": 0.1270610734820366,
      "num_tokens": 1161208.0,
      "step": 465
    },
    {
      "entropy": 7.929465818405151,
      "epoch": 0.5497076023391813,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.8257,
      "mean_token_accuracy": 0.11997483149170876,
      "num_tokens": 1173789.0,
      "step": 470
    },
    {
      "entropy": 8.05664644241333,
      "epoch": 0.5555555555555556,
      "grad_norm": 1.125,
      "learning_rate": 0.000237,
      "loss": 7.7272,
      "mean_token_accuracy": 0.12666135057806968,
      "num_tokens": 1185765.0,
      "step": 475
    },
    {
      "entropy": 7.764935064315796,
      "epoch": 0.5614035087719298,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0002395,
      "loss": 7.7499,
      "mean_token_accuracy": 0.12476444989442825,
      "num_tokens": 1197954.0,
      "step": 480
    },
    {
      "entropy": 8.030300664901734,
      "epoch": 0.5672514619883041,
      "grad_norm": 1.34375,
      "learning_rate": 0.000242,
      "loss": 7.679,
      "mean_token_accuracy": 0.12792463153600692,
      "num_tokens": 1211285.0,
      "step": 485
    },
    {
      "entropy": 7.9220020294189455,
      "epoch": 0.5730994152046783,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0002445,
      "loss": 7.7543,
      "mean_token_accuracy": 0.11961747631430626,
      "num_tokens": 1223197.0,
      "step": 490
    },
    {
      "entropy": 7.8508258819580075,
      "epoch": 0.5789473684210527,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000247,
      "loss": 7.68,
      "mean_token_accuracy": 0.12632347792387008,
      "num_tokens": 1234817.0,
      "step": 495
    },
    {
      "entropy": 7.9022626876831055,
      "epoch": 0.5847953216374269,
      "grad_norm": 1.09375,
      "learning_rate": 0.0002495,
      "loss": 7.7281,
      "mean_token_accuracy": 0.1318517729640007,
      "num_tokens": 1249305.0,
      "step": 500
    },
    {
      "epoch": 0.5847953216374269,
      "eval_entropy": 7.841686710143863,
      "eval_loss": 7.758663654327393,
      "eval_mean_token_accuracy": 0.1180623706160965,
      "eval_num_tokens": 1249305.0,
      "eval_runtime": 2.3012,
      "eval_samples_per_second": 1176.366,
      "eval_steps_per_second": 147.317,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 8540,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1810059724800000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}