{
  "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": 8.045226430892944,
      "epoch": 0.005847953216374269,
      "grad_norm": 1.1640625,
      "learning_rate": 2e-06,
      "loss": 7.818,
      "mean_token_accuracy": 0.11080007404088973,
      "num_tokens": 13999.0,
      "step": 5
    },
    {
      "entropy": 8.016419839859008,
      "epoch": 0.011695906432748537,
      "grad_norm": 1.203125,
      "learning_rate": 4.5e-06,
      "loss": 7.7674,
      "mean_token_accuracy": 0.12552170008420943,
      "num_tokens": 25888.0,
      "step": 10
    },
    {
      "entropy": 7.983883237838745,
      "epoch": 0.017543859649122806,
      "grad_norm": 1.0,
      "learning_rate": 7e-06,
      "loss": 7.7832,
      "mean_token_accuracy": 0.12148510366678238,
      "num_tokens": 37699.0,
      "step": 15
    },
    {
      "entropy": 8.008830261230468,
      "epoch": 0.023391812865497075,
      "grad_norm": 0.9609375,
      "learning_rate": 9.5e-06,
      "loss": 7.8146,
      "mean_token_accuracy": 0.11834284961223603,
      "num_tokens": 49648.0,
      "step": 20
    },
    {
      "entropy": 8.017287445068359,
      "epoch": 0.029239766081871343,
      "grad_norm": 0.91015625,
      "learning_rate": 1.2e-05,
      "loss": 7.7518,
      "mean_token_accuracy": 0.12864405438303947,
      "num_tokens": 62255.0,
      "step": 25
    },
    {
      "entropy": 7.999194955825805,
      "epoch": 0.03508771929824561,
      "grad_norm": 0.94921875,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 7.792,
      "mean_token_accuracy": 0.11829871609807015,
      "num_tokens": 76003.0,
      "step": 30
    },
    {
      "entropy": 7.996608638763428,
      "epoch": 0.04093567251461988,
      "grad_norm": 0.85546875,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 7.7807,
      "mean_token_accuracy": 0.12491086795926094,
      "num_tokens": 87585.0,
      "step": 35
    },
    {
      "entropy": 8.053028106689453,
      "epoch": 0.04678362573099415,
      "grad_norm": 1.0625,
      "learning_rate": 1.95e-05,
      "loss": 7.7457,
      "mean_token_accuracy": 0.1264454424381256,
      "num_tokens": 100404.0,
      "step": 40
    },
    {
      "entropy": 8.056242990493775,
      "epoch": 0.05263157894736842,
      "grad_norm": 0.83203125,
      "learning_rate": 2.2e-05,
      "loss": 7.7331,
      "mean_token_accuracy": 0.12377208396792412,
      "num_tokens": 113130.0,
      "step": 45
    },
    {
      "entropy": 7.999864816665649,
      "epoch": 0.05847953216374269,
      "grad_norm": 1.1015625,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 7.6657,
      "mean_token_accuracy": 0.13675192892551422,
      "num_tokens": 125430.0,
      "step": 50
    },
    {
      "entropy": 8.017994022369384,
      "epoch": 0.06432748538011696,
      "grad_norm": 1.1015625,
      "learning_rate": 2.7e-05,
      "loss": 7.6988,
      "mean_token_accuracy": 0.12444054186344147,
      "num_tokens": 137550.0,
      "step": 55
    },
    {
      "entropy": 7.978502178192139,
      "epoch": 0.07017543859649122,
      "grad_norm": 1.015625,
      "learning_rate": 2.95e-05,
      "loss": 7.7037,
      "mean_token_accuracy": 0.13199957981705665,
      "num_tokens": 149530.0,
      "step": 60
    },
    {
      "entropy": 8.002739524841308,
      "epoch": 0.07602339181286549,
      "grad_norm": 0.9375,
      "learning_rate": 3.2e-05,
      "loss": 7.7433,
      "mean_token_accuracy": 0.11834913790225983,
      "num_tokens": 161671.0,
      "step": 65
    },
    {
      "entropy": 8.044865322113036,
      "epoch": 0.08187134502923976,
      "grad_norm": 0.92578125,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 7.7415,
      "mean_token_accuracy": 0.12546497955918312,
      "num_tokens": 174160.0,
      "step": 70
    },
    {
      "entropy": 8.031145143508912,
      "epoch": 0.08771929824561403,
      "grad_norm": 0.9609375,
      "learning_rate": 3.7e-05,
      "loss": 7.7769,
      "mean_token_accuracy": 0.11971935406327247,
      "num_tokens": 186969.0,
      "step": 75
    },
    {
      "entropy": 8.05164942741394,
      "epoch": 0.0935672514619883,
      "grad_norm": 0.859375,
      "learning_rate": 3.95e-05,
      "loss": 7.8155,
      "mean_token_accuracy": 0.12601222917437555,
      "num_tokens": 199470.0,
      "step": 80
    },
    {
      "entropy": 8.037533330917359,
      "epoch": 0.09941520467836257,
      "grad_norm": 0.92578125,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 7.7126,
      "mean_token_accuracy": 0.12613636404275894,
      "num_tokens": 211306.0,
      "step": 85
    },
    {
      "entropy": 7.987277841567993,
      "epoch": 0.10526315789473684,
      "grad_norm": 0.96875,
      "learning_rate": 4.45e-05,
      "loss": 7.6838,
      "mean_token_accuracy": 0.11928426325321198,
      "num_tokens": 223323.0,
      "step": 90
    },
    {
      "entropy": 7.975043487548828,
      "epoch": 0.1111111111111111,
      "grad_norm": 1.03125,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 7.7213,
      "mean_token_accuracy": 0.12729128673672677,
      "num_tokens": 235896.0,
      "step": 95
    },
    {
      "entropy": 7.983143472671509,
      "epoch": 0.11695906432748537,
      "grad_norm": 0.90234375,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 7.7478,
      "mean_token_accuracy": 0.11931364014744758,
      "num_tokens": 247879.0,
      "step": 100
    },
    {
      "entropy": 8.00935206413269,
      "epoch": 0.12280701754385964,
      "grad_norm": 0.85546875,
      "learning_rate": 5.2e-05,
      "loss": 7.643,
      "mean_token_accuracy": 0.12651290744543076,
      "num_tokens": 259714.0,
      "step": 105
    },
    {
      "entropy": 8.024541139602661,
      "epoch": 0.1286549707602339,
      "grad_norm": 0.93359375,
      "learning_rate": 5.45e-05,
      "loss": 7.7247,
      "mean_token_accuracy": 0.13059264943003654,
      "num_tokens": 272429.0,
      "step": 110
    },
    {
      "entropy": 8.002756261825562,
      "epoch": 0.13450292397660818,
      "grad_norm": 0.92578125,
      "learning_rate": 5.7e-05,
      "loss": 7.7266,
      "mean_token_accuracy": 0.12073208466172218,
      "num_tokens": 285924.0,
      "step": 115
    },
    {
      "entropy": 7.962329769134522,
      "epoch": 0.14035087719298245,
      "grad_norm": 0.7890625,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 7.7193,
      "mean_token_accuracy": 0.12854890897870064,
      "num_tokens": 299453.0,
      "step": 120
    },
    {
      "entropy": 8.003749895095826,
      "epoch": 0.14619883040935672,
      "grad_norm": 0.88671875,
      "learning_rate": 6.2e-05,
      "loss": 7.7368,
      "mean_token_accuracy": 0.126718270778656,
      "num_tokens": 312295.0,
      "step": 125
    },
    {
      "entropy": 8.033454608917236,
      "epoch": 0.15204678362573099,
      "grad_norm": 0.92578125,
      "learning_rate": 6.450000000000001e-05,
      "loss": 7.6836,
      "mean_token_accuracy": 0.12897008657455444,
      "num_tokens": 324730.0,
      "step": 130
    },
    {
      "entropy": 7.970009756088257,
      "epoch": 0.15789473684210525,
      "grad_norm": 0.91015625,
      "learning_rate": 6.7e-05,
      "loss": 7.6357,
      "mean_token_accuracy": 0.1297009363770485,
      "num_tokens": 336481.0,
      "step": 135
    },
    {
      "entropy": 7.994677114486694,
      "epoch": 0.16374269005847952,
      "grad_norm": 0.92578125,
      "learning_rate": 6.950000000000001e-05,
      "loss": 7.6983,
      "mean_token_accuracy": 0.1270280137658119,
      "num_tokens": 348987.0,
      "step": 140
    },
    {
      "entropy": 8.016926193237305,
      "epoch": 0.1695906432748538,
      "grad_norm": 0.921875,
      "learning_rate": 7.2e-05,
      "loss": 7.6826,
      "mean_token_accuracy": 0.12861572131514548,
      "num_tokens": 360390.0,
      "step": 145
    },
    {
      "entropy": 7.914753246307373,
      "epoch": 0.17543859649122806,
      "grad_norm": 0.91796875,
      "learning_rate": 7.45e-05,
      "loss": 7.6898,
      "mean_token_accuracy": 0.12696985229849816,
      "num_tokens": 372456.0,
      "step": 150
    },
    {
      "entropy": 8.051334762573243,
      "epoch": 0.18128654970760233,
      "grad_norm": 0.93359375,
      "learning_rate": 7.7e-05,
      "loss": 7.6932,
      "mean_token_accuracy": 0.1194346971809864,
      "num_tokens": 384185.0,
      "step": 155
    },
    {
      "entropy": 7.977176713943481,
      "epoch": 0.1871345029239766,
      "grad_norm": 1.03125,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.7047,
      "mean_token_accuracy": 0.1230759084224701,
      "num_tokens": 395399.0,
      "step": 160
    },
    {
      "entropy": 8.035953950881957,
      "epoch": 0.19298245614035087,
      "grad_norm": 0.9453125,
      "learning_rate": 8.2e-05,
      "loss": 7.7026,
      "mean_token_accuracy": 0.12683228254318238,
      "num_tokens": 408676.0,
      "step": 165
    },
    {
      "entropy": 8.06921739578247,
      "epoch": 0.19883040935672514,
      "grad_norm": 0.984375,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.7717,
      "mean_token_accuracy": 0.12356067821383476,
      "num_tokens": 421861.0,
      "step": 170
    },
    {
      "entropy": 7.930960464477539,
      "epoch": 0.2046783625730994,
      "grad_norm": 0.9140625,
      "learning_rate": 8.7e-05,
      "loss": 7.7268,
      "mean_token_accuracy": 0.12672705948352814,
      "num_tokens": 434852.0,
      "step": 175
    },
    {
      "entropy": 8.079622077941895,
      "epoch": 0.21052631578947367,
      "grad_norm": 0.91796875,
      "learning_rate": 8.95e-05,
      "loss": 7.7208,
      "mean_token_accuracy": 0.12138797342777252,
      "num_tokens": 447313.0,
      "step": 180
    },
    {
      "entropy": 8.027794551849365,
      "epoch": 0.21637426900584794,
      "grad_norm": 0.9296875,
      "learning_rate": 9.2e-05,
      "loss": 7.6783,
      "mean_token_accuracy": 0.12779284864664078,
      "num_tokens": 460271.0,
      "step": 185
    },
    {
      "entropy": 7.856478452682495,
      "epoch": 0.2222222222222222,
      "grad_norm": 1.0390625,
      "learning_rate": 9.45e-05,
      "loss": 7.681,
      "mean_token_accuracy": 0.12920279279351235,
      "num_tokens": 473006.0,
      "step": 190
    },
    {
      "entropy": 8.003684854507446,
      "epoch": 0.22807017543859648,
      "grad_norm": 1.03125,
      "learning_rate": 9.7e-05,
      "loss": 7.654,
      "mean_token_accuracy": 0.1259481579065323,
      "num_tokens": 486100.0,
      "step": 195
    },
    {
      "entropy": 7.972032690048218,
      "epoch": 0.23391812865497075,
      "grad_norm": 1.0390625,
      "learning_rate": 9.95e-05,
      "loss": 7.5933,
      "mean_token_accuracy": 0.14003728628158568,
      "num_tokens": 499460.0,
      "step": 200
    },
    {
      "entropy": 7.951391363143921,
      "epoch": 0.23976608187134502,
      "grad_norm": 1.0,
      "learning_rate": 0.000102,
      "loss": 7.6514,
      "mean_token_accuracy": 0.12902599275112153,
      "num_tokens": 511795.0,
      "step": 205
    },
    {
      "entropy": 7.95180230140686,
      "epoch": 0.24561403508771928,
      "grad_norm": 1.15625,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.7382,
      "mean_token_accuracy": 0.12644921094179154,
      "num_tokens": 524897.0,
      "step": 210
    },
    {
      "entropy": 7.979979419708252,
      "epoch": 0.25146198830409355,
      "grad_norm": 0.9375,
      "learning_rate": 0.000107,
      "loss": 7.6319,
      "mean_token_accuracy": 0.1295425295829773,
      "num_tokens": 538325.0,
      "step": 215
    },
    {
      "entropy": 7.990107727050781,
      "epoch": 0.2573099415204678,
      "grad_norm": 0.97265625,
      "learning_rate": 0.0001095,
      "loss": 7.7107,
      "mean_token_accuracy": 0.12212530672550201,
      "num_tokens": 550979.0,
      "step": 220
    },
    {
      "entropy": 8.008913707733154,
      "epoch": 0.2631578947368421,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000112,
      "loss": 7.6891,
      "mean_token_accuracy": 0.12676209211349487,
      "num_tokens": 563001.0,
      "step": 225
    },
    {
      "entropy": 7.963163757324219,
      "epoch": 0.26900584795321636,
      "grad_norm": 0.96484375,
      "learning_rate": 0.0001145,
      "loss": 7.6043,
      "mean_token_accuracy": 0.12866764068603515,
      "num_tokens": 573600.0,
      "step": 230
    },
    {
      "entropy": 7.968063545227051,
      "epoch": 0.27485380116959063,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.6265,
      "mean_token_accuracy": 0.1300235703587532,
      "num_tokens": 585287.0,
      "step": 235
    },
    {
      "entropy": 7.902215766906738,
      "epoch": 0.2807017543859649,
      "grad_norm": 1.109375,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.6554,
      "mean_token_accuracy": 0.12321203649044037,
      "num_tokens": 597386.0,
      "step": 240
    },
    {
      "entropy": 7.978629684448242,
      "epoch": 0.28654970760233917,
      "grad_norm": 0.99609375,
      "learning_rate": 0.000122,
      "loss": 7.6527,
      "mean_token_accuracy": 0.12698477283120155,
      "num_tokens": 609256.0,
      "step": 245
    },
    {
      "entropy": 7.978091716766357,
      "epoch": 0.29239766081871343,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0001245,
      "loss": 7.6533,
      "mean_token_accuracy": 0.12933312207460404,
      "num_tokens": 621506.0,
      "step": 250
    },
    {
      "entropy": 7.905685138702393,
      "epoch": 0.2982456140350877,
      "grad_norm": 0.98828125,
      "learning_rate": 0.000127,
      "loss": 7.5799,
      "mean_token_accuracy": 0.13296303376555443,
      "num_tokens": 633512.0,
      "step": 255
    },
    {
      "entropy": 8.041613578796387,
      "epoch": 0.30409356725146197,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0001295,
      "loss": 7.7242,
      "mean_token_accuracy": 0.12240937054157257,
      "num_tokens": 647098.0,
      "step": 260
    },
    {
      "entropy": 7.9852275371551515,
      "epoch": 0.30994152046783624,
      "grad_norm": 0.98828125,
      "learning_rate": 0.000132,
      "loss": 7.7257,
      "mean_token_accuracy": 0.1233548603951931,
      "num_tokens": 659559.0,
      "step": 265
    },
    {
      "entropy": 8.069615888595582,
      "epoch": 0.3157894736842105,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.6581,
      "mean_token_accuracy": 0.12490400299429893,
      "num_tokens": 672621.0,
      "step": 270
    },
    {
      "entropy": 7.8597798347473145,
      "epoch": 0.3216374269005848,
      "grad_norm": 0.91796875,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.6462,
      "mean_token_accuracy": 0.12783507704734803,
      "num_tokens": 685652.0,
      "step": 275
    },
    {
      "entropy": 8.071738576889038,
      "epoch": 0.32748538011695905,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0001395,
      "loss": 7.7153,
      "mean_token_accuracy": 0.12348538860678673,
      "num_tokens": 696910.0,
      "step": 280
    },
    {
      "entropy": 7.863040113449097,
      "epoch": 0.3333333333333333,
      "grad_norm": 1.5625,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.578,
      "mean_token_accuracy": 0.13220044150948523,
      "num_tokens": 709054.0,
      "step": 285
    },
    {
      "entropy": 8.035344123840332,
      "epoch": 0.3391812865497076,
      "grad_norm": 0.9375,
      "learning_rate": 0.0001445,
      "loss": 7.5782,
      "mean_token_accuracy": 0.1288279578089714,
      "num_tokens": 720902.0,
      "step": 290
    },
    {
      "entropy": 7.9420812129974365,
      "epoch": 0.34502923976608185,
      "grad_norm": 1.078125,
      "learning_rate": 0.000147,
      "loss": 7.682,
      "mean_token_accuracy": 0.12467397823929786,
      "num_tokens": 733319.0,
      "step": 295
    },
    {
      "entropy": 7.934081220626831,
      "epoch": 0.3508771929824561,
      "grad_norm": 0.96875,
      "learning_rate": 0.0001495,
      "loss": 7.5585,
      "mean_token_accuracy": 0.13054021298885346,
      "num_tokens": 744817.0,
      "step": 300
    },
    {
      "entropy": 7.9335449695587155,
      "epoch": 0.3567251461988304,
      "grad_norm": 0.94140625,
      "learning_rate": 0.000152,
      "loss": 7.6303,
      "mean_token_accuracy": 0.12146333456039429,
      "num_tokens": 756582.0,
      "step": 305
    },
    {
      "entropy": 7.948399925231934,
      "epoch": 0.36257309941520466,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.5449,
      "mean_token_accuracy": 0.132960344851017,
      "num_tokens": 769273.0,
      "step": 310
    },
    {
      "entropy": 7.933630418777466,
      "epoch": 0.3684210526315789,
      "grad_norm": 1.3046875,
      "learning_rate": 0.000157,
      "loss": 7.6025,
      "mean_token_accuracy": 0.1318463236093521,
      "num_tokens": 782001.0,
      "step": 315
    },
    {
      "entropy": 7.923580074310303,
      "epoch": 0.3742690058479532,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001595,
      "loss": 7.6304,
      "mean_token_accuracy": 0.13039980456233025,
      "num_tokens": 794575.0,
      "step": 320
    },
    {
      "entropy": 7.862440013885498,
      "epoch": 0.38011695906432746,
      "grad_norm": 1.140625,
      "learning_rate": 0.000162,
      "loss": 7.6157,
      "mean_token_accuracy": 0.12852895334362985,
      "num_tokens": 805583.0,
      "step": 325
    },
    {
      "entropy": 7.954799365997315,
      "epoch": 0.38596491228070173,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.6656,
      "mean_token_accuracy": 0.12845203652977943,
      "num_tokens": 817617.0,
      "step": 330
    },
    {
      "entropy": 7.96801438331604,
      "epoch": 0.391812865497076,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.5744,
      "mean_token_accuracy": 0.1288806565105915,
      "num_tokens": 830043.0,
      "step": 335
    },
    {
      "entropy": 7.787790775299072,
      "epoch": 0.39766081871345027,
      "grad_norm": 0.99609375,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.5246,
      "mean_token_accuracy": 0.13534748554229736,
      "num_tokens": 843200.0,
      "step": 340
    },
    {
      "entropy": 7.927206993103027,
      "epoch": 0.40350877192982454,
      "grad_norm": 1.203125,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.5919,
      "mean_token_accuracy": 0.1352095700800419,
      "num_tokens": 856031.0,
      "step": 345
    },
    {
      "entropy": 7.932764101028442,
      "epoch": 0.4093567251461988,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.5701,
      "mean_token_accuracy": 0.13280727341771126,
      "num_tokens": 869119.0,
      "step": 350
    },
    {
      "entropy": 7.834122610092163,
      "epoch": 0.4152046783625731,
      "grad_norm": 0.99609375,
      "learning_rate": 0.000177,
      "loss": 7.5864,
      "mean_token_accuracy": 0.13350669145584107,
      "num_tokens": 880802.0,
      "step": 355
    },
    {
      "entropy": 7.999099969863892,
      "epoch": 0.42105263157894735,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0001795,
      "loss": 7.6039,
      "mean_token_accuracy": 0.13265340849757196,
      "num_tokens": 894237.0,
      "step": 360
    },
    {
      "entropy": 7.928555250167847,
      "epoch": 0.4269005847953216,
      "grad_norm": 1.15625,
      "learning_rate": 0.000182,
      "loss": 7.605,
      "mean_token_accuracy": 0.12948731631040572,
      "num_tokens": 906695.0,
      "step": 365
    },
    {
      "entropy": 7.827572917938232,
      "epoch": 0.4327485380116959,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0001845,
      "loss": 7.5653,
      "mean_token_accuracy": 0.1352884441614151,
      "num_tokens": 918955.0,
      "step": 370
    },
    {
      "entropy": 7.882963037490844,
      "epoch": 0.43859649122807015,
      "grad_norm": 0.9921875,
      "learning_rate": 0.000187,
      "loss": 7.6175,
      "mean_token_accuracy": 0.13342018574476242,
      "num_tokens": 931812.0,
      "step": 375
    },
    {
      "entropy": 8.043187236785888,
      "epoch": 0.4444444444444444,
      "grad_norm": 1.03125,
      "learning_rate": 0.0001895,
      "loss": 7.6117,
      "mean_token_accuracy": 0.1259584277868271,
      "num_tokens": 945261.0,
      "step": 380
    },
    {
      "entropy": 7.798225545883179,
      "epoch": 0.4502923976608187,
      "grad_norm": 1.140625,
      "learning_rate": 0.000192,
      "loss": 7.5332,
      "mean_token_accuracy": 0.13877285420894622,
      "num_tokens": 958376.0,
      "step": 385
    },
    {
      "entropy": 7.8840476989746096,
      "epoch": 0.45614035087719296,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0001945,
      "loss": 7.5497,
      "mean_token_accuracy": 0.1363872230052948,
      "num_tokens": 971709.0,
      "step": 390
    },
    {
      "entropy": 7.952695989608765,
      "epoch": 0.4619883040935672,
      "grad_norm": 1.09375,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.5272,
      "mean_token_accuracy": 0.13542769774794577,
      "num_tokens": 983847.0,
      "step": 395
    },
    {
      "entropy": 7.852967643737793,
      "epoch": 0.4678362573099415,
      "grad_norm": 1.0625,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.6325,
      "mean_token_accuracy": 0.12114153057336807,
      "num_tokens": 997034.0,
      "step": 400
    },
    {
      "entropy": 7.9122217178344725,
      "epoch": 0.47368421052631576,
      "grad_norm": 1.046875,
      "learning_rate": 0.000202,
      "loss": 7.6585,
      "mean_token_accuracy": 0.12669240608811377,
      "num_tokens": 1010213.0,
      "step": 405
    },
    {
      "entropy": 7.966189193725586,
      "epoch": 0.47953216374269003,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.5094,
      "mean_token_accuracy": 0.1325475551187992,
      "num_tokens": 1021618.0,
      "step": 410
    },
    {
      "entropy": 7.752740716934204,
      "epoch": 0.4853801169590643,
      "grad_norm": 1.09375,
      "learning_rate": 0.000207,
      "loss": 7.5722,
      "mean_token_accuracy": 0.12650121599435807,
      "num_tokens": 1033809.0,
      "step": 415
    },
    {
      "entropy": 7.968109512329102,
      "epoch": 0.49122807017543857,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0002095,
      "loss": 7.5408,
      "mean_token_accuracy": 0.13147031590342523,
      "num_tokens": 1045291.0,
      "step": 420
    },
    {
      "entropy": 7.82607216835022,
      "epoch": 0.49707602339181284,
      "grad_norm": 1.09375,
      "learning_rate": 0.000212,
      "loss": 7.5405,
      "mean_token_accuracy": 0.13000031486153601,
      "num_tokens": 1057516.0,
      "step": 425
    },
    {
      "entropy": 7.792825746536255,
      "epoch": 0.5029239766081871,
      "grad_norm": 1.0625,
      "learning_rate": 0.0002145,
      "loss": 7.4731,
      "mean_token_accuracy": 0.14245186597108841,
      "num_tokens": 1070675.0,
      "step": 430
    },
    {
      "entropy": 7.928640842437744,
      "epoch": 0.5087719298245614,
      "grad_norm": 1.03125,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.5646,
      "mean_token_accuracy": 0.13614390641450883,
      "num_tokens": 1082965.0,
      "step": 435
    },
    {
      "entropy": 7.782242202758789,
      "epoch": 0.5146198830409356,
      "grad_norm": 0.94140625,
      "learning_rate": 0.0002195,
      "loss": 7.5514,
      "mean_token_accuracy": 0.12592832893133163,
      "num_tokens": 1095922.0,
      "step": 440
    },
    {
      "entropy": 7.94010591506958,
      "epoch": 0.52046783625731,
      "grad_norm": 1.171875,
      "learning_rate": 0.000222,
      "loss": 7.5318,
      "mean_token_accuracy": 0.1322290450334549,
      "num_tokens": 1109002.0,
      "step": 445
    },
    {
      "entropy": 7.902499675750732,
      "epoch": 0.5263157894736842,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0002245,
      "loss": 7.5483,
      "mean_token_accuracy": 0.12942796126008033,
      "num_tokens": 1121199.0,
      "step": 450
    },
    {
      "entropy": 7.8024513721466064,
      "epoch": 0.5321637426900585,
      "grad_norm": 0.9765625,
      "learning_rate": 0.00022700000000000002,
      "loss": 7.498,
      "mean_token_accuracy": 0.13429903537034987,
      "num_tokens": 1134721.0,
      "step": 455
    },
    {
      "entropy": 7.875277853012085,
      "epoch": 0.5380116959064327,
      "grad_norm": 0.9921875,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.5853,
      "mean_token_accuracy": 0.13090707287192344,
      "num_tokens": 1147954.0,
      "step": 460
    },
    {
      "entropy": 7.777953195571899,
      "epoch": 0.543859649122807,
      "grad_norm": 1.0,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.4904,
      "mean_token_accuracy": 0.13606545925140381,
      "num_tokens": 1161208.0,
      "step": 465
    },
    {
      "entropy": 7.901414012908935,
      "epoch": 0.5497076023391813,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.6013,
      "mean_token_accuracy": 0.12688619866967202,
      "num_tokens": 1173789.0,
      "step": 470
    },
    {
      "entropy": 7.890290832519531,
      "epoch": 0.5555555555555556,
      "grad_norm": 1.09375,
      "learning_rate": 0.000237,
      "loss": 7.5108,
      "mean_token_accuracy": 0.13075993657112123,
      "num_tokens": 1185765.0,
      "step": 475
    },
    {
      "entropy": 7.818354701995849,
      "epoch": 0.5614035087719298,
      "grad_norm": 1.015625,
      "learning_rate": 0.0002395,
      "loss": 7.5364,
      "mean_token_accuracy": 0.13063954189419746,
      "num_tokens": 1197954.0,
      "step": 480
    },
    {
      "entropy": 7.836427164077759,
      "epoch": 0.5672514619883041,
      "grad_norm": 0.98046875,
      "learning_rate": 0.000242,
      "loss": 7.4666,
      "mean_token_accuracy": 0.13487003445625306,
      "num_tokens": 1211285.0,
      "step": 485
    },
    {
      "entropy": 7.822644567489624,
      "epoch": 0.5730994152046783,
      "grad_norm": 0.9765625,
      "learning_rate": 0.0002445,
      "loss": 7.5392,
      "mean_token_accuracy": 0.12864260450005532,
      "num_tokens": 1223197.0,
      "step": 490
    },
    {
      "entropy": 7.805648565292358,
      "epoch": 0.5789473684210527,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000247,
      "loss": 7.4746,
      "mean_token_accuracy": 0.13128072768449783,
      "num_tokens": 1234817.0,
      "step": 495
    },
    {
      "entropy": 7.884338331222534,
      "epoch": 0.5847953216374269,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0002495,
      "loss": 7.5232,
      "mean_token_accuracy": 0.14004627764225006,
      "num_tokens": 1249305.0,
      "step": 500
    },
    {
      "epoch": 0.5847953216374269,
      "eval_entropy": 7.763977130957409,
      "eval_loss": 7.5110273361206055,
      "eval_mean_token_accuracy": 0.12611977400252689,
      "eval_num_tokens": 1249305.0,
      "eval_runtime": 1.7446,
      "eval_samples_per_second": 1551.671,
      "eval_steps_per_second": 194.317,
      "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": 268362805248000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}