{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5042864346949067,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.742588329315186,
      "epoch": 0.005042864346949067,
      "grad_norm": 4.78125,
      "learning_rate": 2e-06,
      "loss": 10.7888,
      "mean_token_accuracy": 6.958942394703626e-05,
      "num_tokens": 11445.0,
      "step": 5
    },
    {
      "entropy": 10.742593383789062,
      "epoch": 0.010085728693898134,
      "grad_norm": 5.25,
      "learning_rate": 4.5e-06,
      "loss": 10.7696,
      "mean_token_accuracy": 0.0,
      "num_tokens": 22095.0,
      "step": 10
    },
    {
      "entropy": 10.742596626281738,
      "epoch": 0.015128593040847202,
      "grad_norm": 4.5625,
      "learning_rate": 7e-06,
      "loss": 10.7579,
      "mean_token_accuracy": 0.00017376195173710585,
      "num_tokens": 33847.0,
      "step": 15
    },
    {
      "entropy": 10.742617321014404,
      "epoch": 0.020171457387796268,
      "grad_norm": 4.53125,
      "learning_rate": 9.5e-06,
      "loss": 10.7022,
      "mean_token_accuracy": 0.0003061072085984051,
      "num_tokens": 44495.0,
      "step": 20
    },
    {
      "entropy": 10.742618179321289,
      "epoch": 0.025214321734745335,
      "grad_norm": 4.0625,
      "learning_rate": 1.2e-05,
      "loss": 10.6161,
      "mean_token_accuracy": 0.0038310963835101576,
      "num_tokens": 55298.0,
      "step": 25
    },
    {
      "entropy": 10.742384719848634,
      "epoch": 0.030257186081694403,
      "grad_norm": 3.859375,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.4928,
      "mean_token_accuracy": 0.023839639127254487,
      "num_tokens": 66391.0,
      "step": 30
    },
    {
      "entropy": 10.741421985626221,
      "epoch": 0.03530005042864347,
      "grad_norm": 3.125,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.3446,
      "mean_token_accuracy": 0.037043477036058904,
      "num_tokens": 77624.0,
      "step": 35
    },
    {
      "entropy": 10.738873195648193,
      "epoch": 0.040342914775592535,
      "grad_norm": 2.578125,
      "learning_rate": 1.95e-05,
      "loss": 10.2004,
      "mean_token_accuracy": 0.04290186390280724,
      "num_tokens": 89426.0,
      "step": 40
    },
    {
      "entropy": 10.734352970123291,
      "epoch": 0.0453857791225416,
      "grad_norm": 2.1875,
      "learning_rate": 2.2e-05,
      "loss": 10.1008,
      "mean_token_accuracy": 0.04177976287901401,
      "num_tokens": 100252.0,
      "step": 45
    },
    {
      "entropy": 10.731473350524903,
      "epoch": 0.05042864346949067,
      "grad_norm": 2.0625,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 10.0294,
      "mean_token_accuracy": 0.035502530820667746,
      "num_tokens": 110578.0,
      "step": 50
    },
    {
      "entropy": 10.731419467926026,
      "epoch": 0.05547150781643974,
      "grad_norm": 1.9453125,
      "learning_rate": 2.7e-05,
      "loss": 9.9893,
      "mean_token_accuracy": 0.03719575461000204,
      "num_tokens": 121631.0,
      "step": 55
    },
    {
      "entropy": 10.730601024627685,
      "epoch": 0.060514372163388806,
      "grad_norm": 1.96875,
      "learning_rate": 2.95e-05,
      "loss": 9.9237,
      "mean_token_accuracy": 0.043491701036691664,
      "num_tokens": 134254.0,
      "step": 60
    },
    {
      "entropy": 10.727654361724854,
      "epoch": 0.06555723651033787,
      "grad_norm": 1.734375,
      "learning_rate": 3.2e-05,
      "loss": 9.8843,
      "mean_token_accuracy": 0.03803328052163124,
      "num_tokens": 144928.0,
      "step": 65
    },
    {
      "entropy": 10.724302101135255,
      "epoch": 0.07060010085728693,
      "grad_norm": 1.8203125,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.7798,
      "mean_token_accuracy": 0.039696192182600495,
      "num_tokens": 155518.0,
      "step": 70
    },
    {
      "entropy": 10.720338535308837,
      "epoch": 0.07564296520423601,
      "grad_norm": 1.9375,
      "learning_rate": 3.7e-05,
      "loss": 9.7038,
      "mean_token_accuracy": 0.04226764794439077,
      "num_tokens": 165850.0,
      "step": 75
    },
    {
      "entropy": 10.71519594192505,
      "epoch": 0.08068582955118507,
      "grad_norm": 1.8828125,
      "learning_rate": 3.95e-05,
      "loss": 9.6932,
      "mean_token_accuracy": 0.04092370942234993,
      "num_tokens": 176787.0,
      "step": 80
    },
    {
      "entropy": 10.709799861907959,
      "epoch": 0.08572869389813415,
      "grad_norm": 1.7578125,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.6293,
      "mean_token_accuracy": 0.03919961098581552,
      "num_tokens": 188345.0,
      "step": 85
    },
    {
      "entropy": 10.706261253356933,
      "epoch": 0.0907715582450832,
      "grad_norm": 1.78125,
      "learning_rate": 4.45e-05,
      "loss": 9.5833,
      "mean_token_accuracy": 0.03263202589005232,
      "num_tokens": 199315.0,
      "step": 90
    },
    {
      "entropy": 10.702005004882812,
      "epoch": 0.09581442259203228,
      "grad_norm": 1.7578125,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.4401,
      "mean_token_accuracy": 0.04271471928805113,
      "num_tokens": 209627.0,
      "step": 95
    },
    {
      "entropy": 10.688950729370116,
      "epoch": 0.10085728693898134,
      "grad_norm": 1.8125,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.3648,
      "mean_token_accuracy": 0.04892551712691784,
      "num_tokens": 220872.0,
      "step": 100
    },
    {
      "entropy": 10.666452217102051,
      "epoch": 0.1059001512859304,
      "grad_norm": 1.8125,
      "learning_rate": 5.2e-05,
      "loss": 9.2706,
      "mean_token_accuracy": 0.04733602069318295,
      "num_tokens": 233272.0,
      "step": 105
    },
    {
      "entropy": 10.643214797973632,
      "epoch": 0.11094301563287948,
      "grad_norm": 1.8125,
      "learning_rate": 5.45e-05,
      "loss": 9.1724,
      "mean_token_accuracy": 0.05065925419330597,
      "num_tokens": 243529.0,
      "step": 110
    },
    {
      "entropy": 10.622024440765381,
      "epoch": 0.11598587997982854,
      "grad_norm": 1.640625,
      "learning_rate": 5.7e-05,
      "loss": 9.0982,
      "mean_token_accuracy": 0.04518871679902077,
      "num_tokens": 254942.0,
      "step": 115
    },
    {
      "entropy": 10.591822242736816,
      "epoch": 0.12102874432677761,
      "grad_norm": 1.7421875,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.9746,
      "mean_token_accuracy": 0.05078088715672493,
      "num_tokens": 266552.0,
      "step": 120
    },
    {
      "entropy": 10.53172492980957,
      "epoch": 0.1260716086737267,
      "grad_norm": 1.59375,
      "learning_rate": 6.2e-05,
      "loss": 8.8367,
      "mean_token_accuracy": 0.049286961928009985,
      "num_tokens": 277906.0,
      "step": 125
    },
    {
      "entropy": 10.461231136322022,
      "epoch": 0.13111447302067575,
      "grad_norm": 1.6328125,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.7177,
      "mean_token_accuracy": 0.05140590891242027,
      "num_tokens": 289079.0,
      "step": 130
    },
    {
      "entropy": 10.385406398773194,
      "epoch": 0.1361573373676248,
      "grad_norm": 1.5,
      "learning_rate": 6.7e-05,
      "loss": 8.6441,
      "mean_token_accuracy": 0.04429629724472761,
      "num_tokens": 300107.0,
      "step": 135
    },
    {
      "entropy": 10.312572288513184,
      "epoch": 0.14120020171457387,
      "grad_norm": 1.5234375,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.4806,
      "mean_token_accuracy": 0.05319313518702984,
      "num_tokens": 310779.0,
      "step": 140
    },
    {
      "entropy": 10.203822803497314,
      "epoch": 0.14624306606152296,
      "grad_norm": 1.453125,
      "learning_rate": 7.2e-05,
      "loss": 8.4202,
      "mean_token_accuracy": 0.051876432821154596,
      "num_tokens": 323478.0,
      "step": 145
    },
    {
      "entropy": 10.096873664855957,
      "epoch": 0.15128593040847202,
      "grad_norm": 1.3515625,
      "learning_rate": 7.45e-05,
      "loss": 8.2552,
      "mean_token_accuracy": 0.05630794763565063,
      "num_tokens": 335255.0,
      "step": 150
    },
    {
      "entropy": 9.960623264312744,
      "epoch": 0.15632879475542108,
      "grad_norm": 1.3046875,
      "learning_rate": 7.7e-05,
      "loss": 8.1385,
      "mean_token_accuracy": 0.05476163513958454,
      "num_tokens": 344824.0,
      "step": 155
    },
    {
      "entropy": 9.771032524108886,
      "epoch": 0.16137165910237014,
      "grad_norm": 1.265625,
      "learning_rate": 7.950000000000001e-05,
      "loss": 8.0754,
      "mean_token_accuracy": 0.05333587229251861,
      "num_tokens": 356283.0,
      "step": 160
    },
    {
      "entropy": 9.623997592926026,
      "epoch": 0.1664145234493192,
      "grad_norm": 1.015625,
      "learning_rate": 8.2e-05,
      "loss": 7.996,
      "mean_token_accuracy": 0.05669583305716515,
      "num_tokens": 368098.0,
      "step": 165
    },
    {
      "entropy": 9.383370685577393,
      "epoch": 0.1714573877962683,
      "grad_norm": 1.03125,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.8796,
      "mean_token_accuracy": 0.059235493466258046,
      "num_tokens": 380948.0,
      "step": 170
    },
    {
      "entropy": 9.174373054504395,
      "epoch": 0.17650025214321735,
      "grad_norm": 1.0234375,
      "learning_rate": 8.7e-05,
      "loss": 7.7633,
      "mean_token_accuracy": 0.05942847430706024,
      "num_tokens": 390392.0,
      "step": 175
    },
    {
      "entropy": 8.980836009979248,
      "epoch": 0.1815431164901664,
      "grad_norm": 1.3203125,
      "learning_rate": 8.95e-05,
      "loss": 7.7496,
      "mean_token_accuracy": 0.06362583562731743,
      "num_tokens": 400328.0,
      "step": 180
    },
    {
      "entropy": 8.7655029296875,
      "epoch": 0.18658598083711547,
      "grad_norm": 0.828125,
      "learning_rate": 9.2e-05,
      "loss": 7.7544,
      "mean_token_accuracy": 0.06182343065738678,
      "num_tokens": 410909.0,
      "step": 185
    },
    {
      "entropy": 8.639219570159913,
      "epoch": 0.19162884518406456,
      "grad_norm": 0.9375,
      "learning_rate": 9.45e-05,
      "loss": 7.691,
      "mean_token_accuracy": 0.06425628773868083,
      "num_tokens": 422726.0,
      "step": 190
    },
    {
      "entropy": 8.559172058105469,
      "epoch": 0.19667170953101362,
      "grad_norm": 0.91796875,
      "learning_rate": 9.7e-05,
      "loss": 7.5594,
      "mean_token_accuracy": 0.07219541147351265,
      "num_tokens": 433376.0,
      "step": 195
    },
    {
      "entropy": 8.397376251220702,
      "epoch": 0.20171457387796268,
      "grad_norm": 1.0078125,
      "learning_rate": 9.95e-05,
      "loss": 7.6275,
      "mean_token_accuracy": 0.06337097361683845,
      "num_tokens": 443940.0,
      "step": 200
    },
    {
      "entropy": 8.361763286590577,
      "epoch": 0.20675743822491174,
      "grad_norm": 0.78125,
      "learning_rate": 0.000102,
      "loss": 7.5213,
      "mean_token_accuracy": 0.06769266054034233,
      "num_tokens": 455016.0,
      "step": 205
    },
    {
      "entropy": 8.303247165679931,
      "epoch": 0.2118003025718608,
      "grad_norm": 0.92578125,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.553,
      "mean_token_accuracy": 0.06669275388121605,
      "num_tokens": 466380.0,
      "step": 210
    },
    {
      "entropy": 8.23162612915039,
      "epoch": 0.2168431669188099,
      "grad_norm": 1.140625,
      "learning_rate": 0.000107,
      "loss": 7.4065,
      "mean_token_accuracy": 0.07161542177200317,
      "num_tokens": 476915.0,
      "step": 215
    },
    {
      "entropy": 8.226816177368164,
      "epoch": 0.22188603126575895,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001095,
      "loss": 7.4817,
      "mean_token_accuracy": 0.07145784981548786,
      "num_tokens": 488924.0,
      "step": 220
    },
    {
      "entropy": 8.18234987258911,
      "epoch": 0.22692889561270801,
      "grad_norm": 0.83984375,
      "learning_rate": 0.000112,
      "loss": 7.4263,
      "mean_token_accuracy": 0.07183554545044898,
      "num_tokens": 498965.0,
      "step": 225
    },
    {
      "entropy": 8.137568473815918,
      "epoch": 0.23197175995965708,
      "grad_norm": 0.828125,
      "learning_rate": 0.0001145,
      "loss": 7.4409,
      "mean_token_accuracy": 0.07232684977352619,
      "num_tokens": 509755.0,
      "step": 230
    },
    {
      "entropy": 8.12470645904541,
      "epoch": 0.23701462430660616,
      "grad_norm": 0.796875,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.4064,
      "mean_token_accuracy": 0.07139695808291435,
      "num_tokens": 521221.0,
      "step": 235
    },
    {
      "entropy": 8.080301761627197,
      "epoch": 0.24205748865355523,
      "grad_norm": 0.91015625,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.503,
      "mean_token_accuracy": 0.06776785589754582,
      "num_tokens": 533595.0,
      "step": 240
    },
    {
      "entropy": 8.111075401306152,
      "epoch": 0.24710035300050429,
      "grad_norm": 0.94140625,
      "learning_rate": 0.000122,
      "loss": 7.4348,
      "mean_token_accuracy": 0.07060522697865963,
      "num_tokens": 543672.0,
      "step": 245
    },
    {
      "entropy": 8.046464586257935,
      "epoch": 0.2521432173474534,
      "grad_norm": 0.7734375,
      "learning_rate": 0.0001245,
      "loss": 7.3208,
      "mean_token_accuracy": 0.07489579617977142,
      "num_tokens": 554906.0,
      "step": 250
    },
    {
      "entropy": 7.984986257553101,
      "epoch": 0.25718608169440244,
      "grad_norm": 0.90234375,
      "learning_rate": 0.000127,
      "loss": 7.3941,
      "mean_token_accuracy": 0.07390029206871987,
      "num_tokens": 566419.0,
      "step": 255
    },
    {
      "entropy": 8.038315868377685,
      "epoch": 0.2622289460413515,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0001295,
      "loss": 7.3625,
      "mean_token_accuracy": 0.07229974381625652,
      "num_tokens": 578848.0,
      "step": 260
    },
    {
      "entropy": 7.896354866027832,
      "epoch": 0.26727181038830056,
      "grad_norm": 0.92578125,
      "learning_rate": 0.000132,
      "loss": 7.305,
      "mean_token_accuracy": 0.07605222910642624,
      "num_tokens": 590601.0,
      "step": 265
    },
    {
      "entropy": 7.9424131393432615,
      "epoch": 0.2723146747352496,
      "grad_norm": 0.9375,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.3548,
      "mean_token_accuracy": 0.07202886901795864,
      "num_tokens": 602021.0,
      "step": 270
    },
    {
      "entropy": 8.004773712158203,
      "epoch": 0.2773575390821987,
      "grad_norm": 0.95703125,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.4443,
      "mean_token_accuracy": 0.06653593964874745,
      "num_tokens": 613966.0,
      "step": 275
    },
    {
      "entropy": 7.990764474868774,
      "epoch": 0.28240040342914774,
      "grad_norm": 1.5390625,
      "learning_rate": 0.0001395,
      "loss": 7.2762,
      "mean_token_accuracy": 0.07293831780552865,
      "num_tokens": 624851.0,
      "step": 280
    },
    {
      "entropy": 7.808479070663452,
      "epoch": 0.2874432677760968,
      "grad_norm": 0.8515625,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.3518,
      "mean_token_accuracy": 0.07462373450398445,
      "num_tokens": 635580.0,
      "step": 285
    },
    {
      "entropy": 7.965742826461792,
      "epoch": 0.2924861321230459,
      "grad_norm": 0.9296875,
      "learning_rate": 0.0001445,
      "loss": 7.4071,
      "mean_token_accuracy": 0.0715030949562788,
      "num_tokens": 646927.0,
      "step": 290
    },
    {
      "entropy": 7.943162631988526,
      "epoch": 0.297528996469995,
      "grad_norm": 1.0234375,
      "learning_rate": 0.000147,
      "loss": 7.2414,
      "mean_token_accuracy": 0.07769636139273643,
      "num_tokens": 658116.0,
      "step": 295
    },
    {
      "entropy": 7.861419916152954,
      "epoch": 0.30257186081694404,
      "grad_norm": 0.9453125,
      "learning_rate": 0.0001495,
      "loss": 7.2404,
      "mean_token_accuracy": 0.07680558413267136,
      "num_tokens": 669054.0,
      "step": 300
    },
    {
      "entropy": 7.859039735794068,
      "epoch": 0.3076147251638931,
      "grad_norm": 1.203125,
      "learning_rate": 0.000152,
      "loss": 7.2846,
      "mean_token_accuracy": 0.07930284813046455,
      "num_tokens": 680439.0,
      "step": 305
    },
    {
      "entropy": 7.81926383972168,
      "epoch": 0.31265758951084216,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.2209,
      "mean_token_accuracy": 0.0794371448457241,
      "num_tokens": 690909.0,
      "step": 310
    },
    {
      "entropy": 7.75442066192627,
      "epoch": 0.3177004538577912,
      "grad_norm": 1.0234375,
      "learning_rate": 0.000157,
      "loss": 7.209,
      "mean_token_accuracy": 0.07925689667463302,
      "num_tokens": 701744.0,
      "step": 315
    },
    {
      "entropy": 7.746679449081421,
      "epoch": 0.3227433182047403,
      "grad_norm": 0.9296875,
      "learning_rate": 0.0001595,
      "loss": 7.2338,
      "mean_token_accuracy": 0.08032149039208888,
      "num_tokens": 712268.0,
      "step": 320
    },
    {
      "entropy": 7.765822124481201,
      "epoch": 0.32778618255168934,
      "grad_norm": 0.9765625,
      "learning_rate": 0.000162,
      "loss": 7.2609,
      "mean_token_accuracy": 0.07947171069681644,
      "num_tokens": 722978.0,
      "step": 325
    },
    {
      "entropy": 7.870586299896241,
      "epoch": 0.3328290468986384,
      "grad_norm": 0.94921875,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.253,
      "mean_token_accuracy": 0.07748774662613869,
      "num_tokens": 734278.0,
      "step": 330
    },
    {
      "entropy": 7.8009439468383786,
      "epoch": 0.3378719112455875,
      "grad_norm": 0.8515625,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.1867,
      "mean_token_accuracy": 0.07406368069350719,
      "num_tokens": 746109.0,
      "step": 335
    },
    {
      "entropy": 7.751057529449463,
      "epoch": 0.3429147755925366,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.1104,
      "mean_token_accuracy": 0.07908297292888164,
      "num_tokens": 757519.0,
      "step": 340
    },
    {
      "entropy": 7.711837816238403,
      "epoch": 0.34795763993948564,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.0784,
      "mean_token_accuracy": 0.08319444209337234,
      "num_tokens": 767665.0,
      "step": 345
    },
    {
      "entropy": 7.729198932647705,
      "epoch": 0.3530005042864347,
      "grad_norm": 1.125,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.118,
      "mean_token_accuracy": 0.08570092767477036,
      "num_tokens": 778880.0,
      "step": 350
    },
    {
      "entropy": 7.589126014709473,
      "epoch": 0.35804336863338376,
      "grad_norm": 0.94140625,
      "learning_rate": 0.000177,
      "loss": 7.1275,
      "mean_token_accuracy": 0.08408626839518547,
      "num_tokens": 790360.0,
      "step": 355
    },
    {
      "entropy": 7.650224447250366,
      "epoch": 0.3630862329803328,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0001795,
      "loss": 7.0884,
      "mean_token_accuracy": 0.08589479774236679,
      "num_tokens": 800889.0,
      "step": 360
    },
    {
      "entropy": 7.698587417602539,
      "epoch": 0.3681290973272819,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000182,
      "loss": 7.0774,
      "mean_token_accuracy": 0.08224210813641548,
      "num_tokens": 811414.0,
      "step": 365
    },
    {
      "entropy": 7.551970529556274,
      "epoch": 0.37317196167423095,
      "grad_norm": 0.96484375,
      "learning_rate": 0.0001845,
      "loss": 7.0729,
      "mean_token_accuracy": 0.08361641615629196,
      "num_tokens": 822822.0,
      "step": 370
    },
    {
      "entropy": 7.61205792427063,
      "epoch": 0.37821482602118,
      "grad_norm": 1.09375,
      "learning_rate": 0.000187,
      "loss": 6.9949,
      "mean_token_accuracy": 0.09048431143164634,
      "num_tokens": 833145.0,
      "step": 375
    },
    {
      "entropy": 7.606620168685913,
      "epoch": 0.3832576903681291,
      "grad_norm": 1.046875,
      "learning_rate": 0.0001895,
      "loss": 7.1067,
      "mean_token_accuracy": 0.08064279481768608,
      "num_tokens": 844015.0,
      "step": 380
    },
    {
      "entropy": 7.537594938278199,
      "epoch": 0.3883005547150782,
      "grad_norm": 0.8984375,
      "learning_rate": 0.000192,
      "loss": 7.0227,
      "mean_token_accuracy": 0.08781845718622208,
      "num_tokens": 855806.0,
      "step": 385
    },
    {
      "entropy": 7.601389598846436,
      "epoch": 0.39334341906202724,
      "grad_norm": 1.09375,
      "learning_rate": 0.0001945,
      "loss": 6.952,
      "mean_token_accuracy": 0.08714486509561539,
      "num_tokens": 865750.0,
      "step": 390
    },
    {
      "entropy": 7.603587245941162,
      "epoch": 0.3983862834089763,
      "grad_norm": 0.9296875,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.0798,
      "mean_token_accuracy": 0.08171837627887726,
      "num_tokens": 877630.0,
      "step": 395
    },
    {
      "entropy": 7.46077446937561,
      "epoch": 0.40342914775592537,
      "grad_norm": 0.921875,
      "learning_rate": 0.00019950000000000002,
      "loss": 6.9621,
      "mean_token_accuracy": 0.08956382796168327,
      "num_tokens": 888667.0,
      "step": 400
    },
    {
      "entropy": 7.612736940383911,
      "epoch": 0.4084720121028744,
      "grad_norm": 1.0625,
      "learning_rate": 0.000202,
      "loss": 7.0383,
      "mean_token_accuracy": 0.0815612755715847,
      "num_tokens": 900989.0,
      "step": 405
    },
    {
      "entropy": 7.4917103290557865,
      "epoch": 0.4135148764498235,
      "grad_norm": 0.94921875,
      "learning_rate": 0.00020449999999999998,
      "loss": 6.9247,
      "mean_token_accuracy": 0.08268933743238449,
      "num_tokens": 911479.0,
      "step": 410
    },
    {
      "entropy": 7.538983345031738,
      "epoch": 0.41855774079677255,
      "grad_norm": 0.96875,
      "learning_rate": 0.000207,
      "loss": 6.9579,
      "mean_token_accuracy": 0.0860539086163044,
      "num_tokens": 922434.0,
      "step": 415
    },
    {
      "entropy": 7.502885150909424,
      "epoch": 0.4236006051437216,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0002095,
      "loss": 6.9417,
      "mean_token_accuracy": 0.08750939816236496,
      "num_tokens": 933405.0,
      "step": 420
    },
    {
      "entropy": 7.503132390975952,
      "epoch": 0.4286434694906707,
      "grad_norm": 1.09375,
      "learning_rate": 0.000212,
      "loss": 6.9414,
      "mean_token_accuracy": 0.0863698624074459,
      "num_tokens": 943567.0,
      "step": 425
    },
    {
      "entropy": 7.433593511581421,
      "epoch": 0.4336863338376198,
      "grad_norm": 1.015625,
      "learning_rate": 0.0002145,
      "loss": 6.9729,
      "mean_token_accuracy": 0.08398969918489456,
      "num_tokens": 955123.0,
      "step": 430
    },
    {
      "entropy": 7.4864178657531735,
      "epoch": 0.43872919818456885,
      "grad_norm": 1.140625,
      "learning_rate": 0.00021700000000000002,
      "loss": 6.9878,
      "mean_token_accuracy": 0.08637007214128971,
      "num_tokens": 965565.0,
      "step": 435
    },
    {
      "entropy": 7.533525228500366,
      "epoch": 0.4437720625315179,
      "grad_norm": 0.890625,
      "learning_rate": 0.0002195,
      "loss": 6.9331,
      "mean_token_accuracy": 0.09186888933181762,
      "num_tokens": 977101.0,
      "step": 440
    },
    {
      "entropy": 7.447479343414306,
      "epoch": 0.44881492687846697,
      "grad_norm": 0.96484375,
      "learning_rate": 0.000222,
      "loss": 6.9676,
      "mean_token_accuracy": 0.08773500472307205,
      "num_tokens": 987445.0,
      "step": 445
    },
    {
      "entropy": 7.413919162750244,
      "epoch": 0.45385779122541603,
      "grad_norm": 0.98828125,
      "learning_rate": 0.0002245,
      "loss": 6.8527,
      "mean_token_accuracy": 0.0943599946796894,
      "num_tokens": 999379.0,
      "step": 450
    },
    {
      "entropy": 7.366581916809082,
      "epoch": 0.4589006555723651,
      "grad_norm": 1.0625,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.7887,
      "mean_token_accuracy": 0.09886589571833611,
      "num_tokens": 1010744.0,
      "step": 455
    },
    {
      "entropy": 7.395628499984741,
      "epoch": 0.46394351991931415,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.8751,
      "mean_token_accuracy": 0.09002586975693702,
      "num_tokens": 1021808.0,
      "step": 460
    },
    {
      "entropy": 7.436336374282837,
      "epoch": 0.4689863842662632,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.9197,
      "mean_token_accuracy": 0.08965835645794869,
      "num_tokens": 1033694.0,
      "step": 465
    },
    {
      "entropy": 7.366260051727295,
      "epoch": 0.47402924861321233,
      "grad_norm": 1.1875,
      "learning_rate": 0.00023449999999999998,
      "loss": 6.8866,
      "mean_token_accuracy": 0.08940717950463295,
      "num_tokens": 1044690.0,
      "step": 470
    },
    {
      "entropy": 7.3759284019470215,
      "epoch": 0.4790721129601614,
      "grad_norm": 0.96484375,
      "learning_rate": 0.000237,
      "loss": 6.883,
      "mean_token_accuracy": 0.09023785665631294,
      "num_tokens": 1055557.0,
      "step": 475
    },
    {
      "entropy": 7.412348127365112,
      "epoch": 0.48411497730711045,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0002395,
      "loss": 6.8225,
      "mean_token_accuracy": 0.09234220460057259,
      "num_tokens": 1067304.0,
      "step": 480
    },
    {
      "entropy": 7.280447006225586,
      "epoch": 0.4891578416540595,
      "grad_norm": 1.15625,
      "learning_rate": 0.000242,
      "loss": 6.8498,
      "mean_token_accuracy": 0.09138206690549851,
      "num_tokens": 1078955.0,
      "step": 485
    },
    {
      "entropy": 7.339125728607177,
      "epoch": 0.49420070600100857,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0002445,
      "loss": 6.8907,
      "mean_token_accuracy": 0.09167812019586563,
      "num_tokens": 1091405.0,
      "step": 490
    },
    {
      "entropy": 7.334241151809692,
      "epoch": 0.49924357034795763,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000247,
      "loss": 6.8625,
      "mean_token_accuracy": 0.09363722130656242,
      "num_tokens": 1103227.0,
      "step": 495
    },
    {
      "entropy": 7.351650381088257,
      "epoch": 0.5042864346949067,
      "grad_norm": 0.890625,
      "learning_rate": 0.0002495,
      "loss": 6.7968,
      "mean_token_accuracy": 0.09819836765527726,
      "num_tokens": 1114485.0,
      "step": 500
    },
    {
      "epoch": 0.5042864346949067,
      "eval_entropy": 7.210145644559205,
      "eval_loss": 6.899664402008057,
      "eval_mean_token_accuracy": 0.09479910408267538,
      "eval_num_tokens": 1114485.0,
      "eval_runtime": 2.1175,
      "eval_samples_per_second": 1481.964,
      "eval_steps_per_second": 185.6,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 9910,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 276978743377920.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}