{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010868620119989566,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.692033958435058,
      "epoch": 0.00010868620119989566,
      "grad_norm": 14.125,
      "learning_rate": 2e-06,
      "loss": 10.7755,
      "mean_token_accuracy": 0.0,
      "num_tokens": 7936.0,
      "step": 5
    },
    {
      "entropy": 10.691999912261963,
      "epoch": 0.00021737240239979132,
      "grad_norm": 15.1875,
      "learning_rate": 4.5e-06,
      "loss": 10.6915,
      "mean_token_accuracy": 0.0,
      "num_tokens": 15561.0,
      "step": 10
    },
    {
      "entropy": 10.690576362609864,
      "epoch": 0.000326058603599687,
      "grad_norm": 10.0,
      "learning_rate": 7e-06,
      "loss": 10.4237,
      "mean_token_accuracy": 0.03714140746742487,
      "num_tokens": 23101.0,
      "step": 15
    },
    {
      "entropy": 10.662552452087402,
      "epoch": 0.00043474480479958265,
      "grad_norm": 6.4375,
      "learning_rate": 9.5e-06,
      "loss": 10.13,
      "mean_token_accuracy": 0.053733503073453905,
      "num_tokens": 31122.0,
      "step": 20
    },
    {
      "entropy": 10.53134651184082,
      "epoch": 0.0005434310059994783,
      "grad_norm": 4.21875,
      "learning_rate": 1.2e-05,
      "loss": 9.8666,
      "mean_token_accuracy": 0.049097494408488276,
      "num_tokens": 39424.0,
      "step": 25
    },
    {
      "entropy": 10.499347591400147,
      "epoch": 0.000652117207199374,
      "grad_norm": 3.40625,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 9.6573,
      "mean_token_accuracy": 0.05333031602203846,
      "num_tokens": 46113.0,
      "step": 30
    },
    {
      "entropy": 10.45414752960205,
      "epoch": 0.0007608034083992696,
      "grad_norm": 4.03125,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 9.5644,
      "mean_token_accuracy": 0.050568538904190066,
      "num_tokens": 53459.0,
      "step": 35
    },
    {
      "entropy": 10.488454818725586,
      "epoch": 0.0008694896095991653,
      "grad_norm": 2.875,
      "learning_rate": 1.95e-05,
      "loss": 9.5746,
      "mean_token_accuracy": 0.054808919131755826,
      "num_tokens": 61325.0,
      "step": 40
    },
    {
      "entropy": 10.44335298538208,
      "epoch": 0.0009781758107990609,
      "grad_norm": 2.578125,
      "learning_rate": 2.2e-05,
      "loss": 9.5243,
      "mean_token_accuracy": 0.05896916501224041,
      "num_tokens": 68741.0,
      "step": 45
    },
    {
      "entropy": 10.389917469024658,
      "epoch": 0.0010868620119989566,
      "grad_norm": 2.703125,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.4498,
      "mean_token_accuracy": 0.07500801645219327,
      "num_tokens": 76827.0,
      "step": 50
    },
    {
      "entropy": 10.32972011566162,
      "epoch": 0.0011955482131988523,
      "grad_norm": 2.28125,
      "learning_rate": 2.7e-05,
      "loss": 9.4108,
      "mean_token_accuracy": 0.06764259599149228,
      "num_tokens": 84543.0,
      "step": 55
    },
    {
      "entropy": 10.223662376403809,
      "epoch": 0.001304234414398748,
      "grad_norm": 2.1875,
      "learning_rate": 2.95e-05,
      "loss": 9.3763,
      "mean_token_accuracy": 0.06775642447173595,
      "num_tokens": 92505.0,
      "step": 60
    },
    {
      "entropy": 10.253492069244384,
      "epoch": 0.0014129206155986437,
      "grad_norm": 2.046875,
      "learning_rate": 3.2e-05,
      "loss": 9.292,
      "mean_token_accuracy": 0.07278058938682079,
      "num_tokens": 100004.0,
      "step": 65
    },
    {
      "entropy": 10.179506492614745,
      "epoch": 0.0015216068167985392,
      "grad_norm": 2.125,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.1464,
      "mean_token_accuracy": 0.07609819024801254,
      "num_tokens": 106865.0,
      "step": 70
    },
    {
      "entropy": 10.167201709747314,
      "epoch": 0.0016302930179984349,
      "grad_norm": 1.828125,
      "learning_rate": 3.7e-05,
      "loss": 9.184,
      "mean_token_accuracy": 0.07288527600467205,
      "num_tokens": 115745.0,
      "step": 75
    },
    {
      "entropy": 10.253772735595703,
      "epoch": 0.0017389792191983306,
      "grad_norm": 1.9609375,
      "learning_rate": 3.95e-05,
      "loss": 9.1019,
      "mean_token_accuracy": 0.07272576205432416,
      "num_tokens": 124724.0,
      "step": 80
    },
    {
      "entropy": 10.141531181335449,
      "epoch": 0.0018476654203982263,
      "grad_norm": 1.921875,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 8.9728,
      "mean_token_accuracy": 0.07559517920017242,
      "num_tokens": 131933.0,
      "step": 85
    },
    {
      "entropy": 10.05212688446045,
      "epoch": 0.0019563516215981218,
      "grad_norm": 2.125,
      "learning_rate": 4.45e-05,
      "loss": 8.9554,
      "mean_token_accuracy": 0.07529733926057816,
      "num_tokens": 139726.0,
      "step": 90
    },
    {
      "entropy": 10.118945980072022,
      "epoch": 0.0020650378227980177,
      "grad_norm": 1.9453125,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 8.8937,
      "mean_token_accuracy": 0.07433236017823219,
      "num_tokens": 147276.0,
      "step": 95
    },
    {
      "entropy": 10.070981788635255,
      "epoch": 0.002173724023997913,
      "grad_norm": 1.671875,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 8.8032,
      "mean_token_accuracy": 0.07382776252925397,
      "num_tokens": 155449.0,
      "step": 100
    },
    {
      "entropy": 9.931837844848634,
      "epoch": 0.002282410225197809,
      "grad_norm": 1.828125,
      "learning_rate": 5.2e-05,
      "loss": 8.6788,
      "mean_token_accuracy": 0.06880230605602264,
      "num_tokens": 163547.0,
      "step": 105
    },
    {
      "entropy": 9.92315607070923,
      "epoch": 0.0023910964263977046,
      "grad_norm": 1.71875,
      "learning_rate": 5.45e-05,
      "loss": 8.5975,
      "mean_token_accuracy": 0.0769424244761467,
      "num_tokens": 171777.0,
      "step": 110
    },
    {
      "entropy": 9.855748653411865,
      "epoch": 0.0024997826275976,
      "grad_norm": 1.671875,
      "learning_rate": 5.7e-05,
      "loss": 8.4659,
      "mean_token_accuracy": 0.0743311032652855,
      "num_tokens": 179337.0,
      "step": 115
    },
    {
      "entropy": 9.745928478240966,
      "epoch": 0.002608468828797496,
      "grad_norm": 1.796875,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.3905,
      "mean_token_accuracy": 0.07685245871543885,
      "num_tokens": 186939.0,
      "step": 120
    },
    {
      "entropy": 9.60959987640381,
      "epoch": 0.0027171550299973915,
      "grad_norm": 1.3125,
      "learning_rate": 6.2e-05,
      "loss": 8.2612,
      "mean_token_accuracy": 0.07991581708192826,
      "num_tokens": 194755.0,
      "step": 125
    },
    {
      "entropy": 9.507084274291993,
      "epoch": 0.0028258412311972874,
      "grad_norm": 1.6015625,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.1596,
      "mean_token_accuracy": 0.07951611280441284,
      "num_tokens": 202610.0,
      "step": 130
    },
    {
      "entropy": 9.229420471191407,
      "epoch": 0.002934527432397183,
      "grad_norm": 1.546875,
      "learning_rate": 6.7e-05,
      "loss": 8.0589,
      "mean_token_accuracy": 0.07813627794384956,
      "num_tokens": 211305.0,
      "step": 135
    },
    {
      "entropy": 9.083441066741944,
      "epoch": 0.0030432136335970784,
      "grad_norm": 1.4296875,
      "learning_rate": 6.950000000000001e-05,
      "loss": 7.9516,
      "mean_token_accuracy": 0.07972251251339912,
      "num_tokens": 218447.0,
      "step": 140
    },
    {
      "entropy": 8.977557182312012,
      "epoch": 0.0031518998347969743,
      "grad_norm": 1.328125,
      "learning_rate": 7.2e-05,
      "loss": 7.9735,
      "mean_token_accuracy": 0.07708753384649754,
      "num_tokens": 226108.0,
      "step": 145
    },
    {
      "entropy": 8.854303741455078,
      "epoch": 0.0032605860359968698,
      "grad_norm": 1.3515625,
      "learning_rate": 7.45e-05,
      "loss": 7.9018,
      "mean_token_accuracy": 0.0749433733522892,
      "num_tokens": 233213.0,
      "step": 150
    },
    {
      "entropy": 8.737026977539063,
      "epoch": 0.0033692722371967657,
      "grad_norm": 1.34375,
      "learning_rate": 7.7e-05,
      "loss": 7.9657,
      "mean_token_accuracy": 0.07061286456882954,
      "num_tokens": 241483.0,
      "step": 155
    },
    {
      "entropy": 8.660515594482423,
      "epoch": 0.003477958438396661,
      "grad_norm": 1.28125,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.8216,
      "mean_token_accuracy": 0.08022509105503559,
      "num_tokens": 249537.0,
      "step": 160
    },
    {
      "entropy": 8.48324089050293,
      "epoch": 0.0035866446395965567,
      "grad_norm": 1.1484375,
      "learning_rate": 8.2e-05,
      "loss": 7.7574,
      "mean_token_accuracy": 0.08265799134969712,
      "num_tokens": 256775.0,
      "step": 165
    },
    {
      "entropy": 8.382307147979736,
      "epoch": 0.0036953308407964526,
      "grad_norm": 1.40625,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.7628,
      "mean_token_accuracy": 0.08266141265630722,
      "num_tokens": 263931.0,
      "step": 170
    },
    {
      "entropy": 8.312588787078857,
      "epoch": 0.003804017041996348,
      "grad_norm": 1.1953125,
      "learning_rate": 8.7e-05,
      "loss": 7.7557,
      "mean_token_accuracy": 0.08323334604501724,
      "num_tokens": 272293.0,
      "step": 175
    },
    {
      "entropy": 8.368490505218507,
      "epoch": 0.0039127032431962435,
      "grad_norm": 1.390625,
      "learning_rate": 8.95e-05,
      "loss": 7.7964,
      "mean_token_accuracy": 0.07600408792495728,
      "num_tokens": 280599.0,
      "step": 180
    },
    {
      "entropy": 8.208444499969483,
      "epoch": 0.00402138944439614,
      "grad_norm": 1.4921875,
      "learning_rate": 9.2e-05,
      "loss": 7.7604,
      "mean_token_accuracy": 0.07719066366553307,
      "num_tokens": 287961.0,
      "step": 185
    },
    {
      "entropy": 8.142381763458252,
      "epoch": 0.004130075645596035,
      "grad_norm": 1.8671875,
      "learning_rate": 9.45e-05,
      "loss": 7.684,
      "mean_token_accuracy": 0.08424306884407998,
      "num_tokens": 297280.0,
      "step": 190
    },
    {
      "entropy": 8.162713718414306,
      "epoch": 0.004238761846795931,
      "grad_norm": 1.2421875,
      "learning_rate": 9.7e-05,
      "loss": 7.7526,
      "mean_token_accuracy": 0.08235807195305825,
      "num_tokens": 304699.0,
      "step": 195
    },
    {
      "entropy": 8.149117755889893,
      "epoch": 0.004347448047995826,
      "grad_norm": 1.125,
      "learning_rate": 9.95e-05,
      "loss": 7.6864,
      "mean_token_accuracy": 0.08296664133667946,
      "num_tokens": 313026.0,
      "step": 200
    },
    {
      "entropy": 8.115727186203003,
      "epoch": 0.004456134249195722,
      "grad_norm": 1.140625,
      "learning_rate": 0.000102,
      "loss": 7.7092,
      "mean_token_accuracy": 0.08166395723819733,
      "num_tokens": 320738.0,
      "step": 205
    },
    {
      "entropy": 8.076230096817017,
      "epoch": 0.004564820450395618,
      "grad_norm": 1.2265625,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.6861,
      "mean_token_accuracy": 0.07836256250739097,
      "num_tokens": 328740.0,
      "step": 210
    },
    {
      "entropy": 8.025853300094605,
      "epoch": 0.004673506651595514,
      "grad_norm": 1.09375,
      "learning_rate": 0.000107,
      "loss": 7.6627,
      "mean_token_accuracy": 0.08186743408441544,
      "num_tokens": 336819.0,
      "step": 215
    },
    {
      "entropy": 8.132151794433593,
      "epoch": 0.004782192852795409,
      "grad_norm": 1.234375,
      "learning_rate": 0.0001095,
      "loss": 7.5969,
      "mean_token_accuracy": 0.08840056881308556,
      "num_tokens": 343978.0,
      "step": 220
    },
    {
      "entropy": 8.009299278259277,
      "epoch": 0.004890879053995305,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000112,
      "loss": 7.6897,
      "mean_token_accuracy": 0.07886088080704212,
      "num_tokens": 353783.0,
      "step": 225
    },
    {
      "entropy": 7.969748306274414,
      "epoch": 0.0049995652551952,
      "grad_norm": 1.34375,
      "learning_rate": 0.0001145,
      "loss": 7.5909,
      "mean_token_accuracy": 0.08582306802272796,
      "num_tokens": 361371.0,
      "step": 230
    },
    {
      "entropy": 7.9828167915344235,
      "epoch": 0.0051082514563950965,
      "grad_norm": 1.3984375,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.6185,
      "mean_token_accuracy": 0.07745145447552204,
      "num_tokens": 367717.0,
      "step": 235
    },
    {
      "entropy": 8.051587057113647,
      "epoch": 0.005216937657594992,
      "grad_norm": 1.203125,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.6177,
      "mean_token_accuracy": 0.08022010251879692,
      "num_tokens": 375529.0,
      "step": 240
    },
    {
      "entropy": 7.905487108230591,
      "epoch": 0.0053256238587948874,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000122,
      "loss": 7.5073,
      "mean_token_accuracy": 0.08242316544055939,
      "num_tokens": 383031.0,
      "step": 245
    },
    {
      "entropy": 7.966064023971557,
      "epoch": 0.005434310059994783,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0001245,
      "loss": 7.6472,
      "mean_token_accuracy": 0.0840654157102108,
      "num_tokens": 391914.0,
      "step": 250
    },
    {
      "entropy": 7.939682960510254,
      "epoch": 0.005542996261194678,
      "grad_norm": 1.34375,
      "learning_rate": 0.000127,
      "loss": 7.6111,
      "mean_token_accuracy": 0.08445862084627151,
      "num_tokens": 399447.0,
      "step": 255
    },
    {
      "entropy": 7.95916223526001,
      "epoch": 0.005651682462394575,
      "grad_norm": 1.5078125,
      "learning_rate": 0.0001295,
      "loss": 7.6053,
      "mean_token_accuracy": 0.08623345196247101,
      "num_tokens": 407636.0,
      "step": 260
    },
    {
      "entropy": 7.863192081451416,
      "epoch": 0.00576036866359447,
      "grad_norm": 1.25,
      "learning_rate": 0.000132,
      "loss": 7.5498,
      "mean_token_accuracy": 0.08252564668655396,
      "num_tokens": 416650.0,
      "step": 265
    },
    {
      "entropy": 7.940821886062622,
      "epoch": 0.005869054864794366,
      "grad_norm": 1.71875,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.4851,
      "mean_token_accuracy": 0.08535419404506683,
      "num_tokens": 424619.0,
      "step": 270
    },
    {
      "entropy": 7.923966264724731,
      "epoch": 0.005977741065994261,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.5731,
      "mean_token_accuracy": 0.08694756105542183,
      "num_tokens": 432854.0,
      "step": 275
    },
    {
      "entropy": 7.861378288269043,
      "epoch": 0.006086427267194157,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0001395,
      "loss": 7.5646,
      "mean_token_accuracy": 0.08049703910946845,
      "num_tokens": 440472.0,
      "step": 280
    },
    {
      "entropy": 7.979065895080566,
      "epoch": 0.006195113468394053,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.4921,
      "mean_token_accuracy": 0.08637023121118545,
      "num_tokens": 447843.0,
      "step": 285
    },
    {
      "entropy": 7.926018571853637,
      "epoch": 0.0063037996695939486,
      "grad_norm": 1.4921875,
      "learning_rate": 0.0001445,
      "loss": 7.6005,
      "mean_token_accuracy": 0.08329573571681977,
      "num_tokens": 455272.0,
      "step": 290
    },
    {
      "entropy": 7.811395597457886,
      "epoch": 0.006412485870793844,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000147,
      "loss": 7.4287,
      "mean_token_accuracy": 0.08994799107313156,
      "num_tokens": 462190.0,
      "step": 295
    },
    {
      "entropy": 7.937566328048706,
      "epoch": 0.0065211720719937395,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0001495,
      "loss": 7.5291,
      "mean_token_accuracy": 0.08383448868989944,
      "num_tokens": 470562.0,
      "step": 300
    },
    {
      "entropy": 7.770080280303955,
      "epoch": 0.006629858273193635,
      "grad_norm": 1.140625,
      "learning_rate": 0.000152,
      "loss": 7.433,
      "mean_token_accuracy": 0.09061657935380936,
      "num_tokens": 478523.0,
      "step": 305
    },
    {
      "entropy": 7.844554090499878,
      "epoch": 0.006738544474393531,
      "grad_norm": 1.3359375,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.517,
      "mean_token_accuracy": 0.08662905022501946,
      "num_tokens": 486759.0,
      "step": 310
    },
    {
      "entropy": 7.828848934173584,
      "epoch": 0.006847230675593427,
      "grad_norm": 1.2421875,
      "learning_rate": 0.000157,
      "loss": 7.5283,
      "mean_token_accuracy": 0.08165703043341636,
      "num_tokens": 495168.0,
      "step": 315
    },
    {
      "entropy": 7.823043441772461,
      "epoch": 0.006955916876793322,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0001595,
      "loss": 7.4207,
      "mean_token_accuracy": 0.08956636488437653,
      "num_tokens": 503490.0,
      "step": 320
    },
    {
      "entropy": 7.771451330184936,
      "epoch": 0.007064603077993218,
      "grad_norm": 1.171875,
      "learning_rate": 0.000162,
      "loss": 7.5539,
      "mean_token_accuracy": 0.08244621530175208,
      "num_tokens": 512522.0,
      "step": 325
    },
    {
      "entropy": 7.877453756332398,
      "epoch": 0.007173289279193113,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.4913,
      "mean_token_accuracy": 0.08120876513421535,
      "num_tokens": 521100.0,
      "step": 330
    },
    {
      "entropy": 7.771992826461792,
      "epoch": 0.00728197548039301,
      "grad_norm": 1.1875,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.396,
      "mean_token_accuracy": 0.0948154278099537,
      "num_tokens": 528027.0,
      "step": 335
    },
    {
      "entropy": 7.7505473613739015,
      "epoch": 0.007390661681592905,
      "grad_norm": 1.390625,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.3994,
      "mean_token_accuracy": 0.08797064200043678,
      "num_tokens": 535541.0,
      "step": 340
    },
    {
      "entropy": 7.820106267929077,
      "epoch": 0.007499347882792801,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.4177,
      "mean_token_accuracy": 0.08866829052567482,
      "num_tokens": 543253.0,
      "step": 345
    },
    {
      "entropy": 7.8131262302398685,
      "epoch": 0.007608034083992696,
      "grad_norm": 1.515625,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.4312,
      "mean_token_accuracy": 0.08869538456201553,
      "num_tokens": 550414.0,
      "step": 350
    },
    {
      "entropy": 7.678452491760254,
      "epoch": 0.007716720285192592,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000177,
      "loss": 7.4866,
      "mean_token_accuracy": 0.08567069470882416,
      "num_tokens": 558554.0,
      "step": 355
    },
    {
      "entropy": 7.860786962509155,
      "epoch": 0.007825406486392487,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0001795,
      "loss": 7.4562,
      "mean_token_accuracy": 0.0866042397916317,
      "num_tokens": 566297.0,
      "step": 360
    },
    {
      "entropy": 7.691314792633056,
      "epoch": 0.007934092687592383,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000182,
      "loss": 7.399,
      "mean_token_accuracy": 0.09093262627720833,
      "num_tokens": 574600.0,
      "step": 365
    },
    {
      "entropy": 7.761751461029053,
      "epoch": 0.00804277888879228,
      "grad_norm": 1.03125,
      "learning_rate": 0.0001845,
      "loss": 7.4278,
      "mean_token_accuracy": 0.08792822286486626,
      "num_tokens": 583349.0,
      "step": 370
    },
    {
      "entropy": 7.841218614578247,
      "epoch": 0.008151465089992175,
      "grad_norm": 1.3671875,
      "learning_rate": 0.000187,
      "loss": 7.3269,
      "mean_token_accuracy": 0.08868191167712211,
      "num_tokens": 590169.0,
      "step": 375
    },
    {
      "entropy": 7.639244318008423,
      "epoch": 0.00826015129119207,
      "grad_norm": 1.296875,
      "learning_rate": 0.0001895,
      "loss": 7.2957,
      "mean_token_accuracy": 0.09457754641771317,
      "num_tokens": 597508.0,
      "step": 380
    },
    {
      "entropy": 7.685401201248169,
      "epoch": 0.008368837492391966,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000192,
      "loss": 7.375,
      "mean_token_accuracy": 0.09122001230716706,
      "num_tokens": 605412.0,
      "step": 385
    },
    {
      "entropy": 7.795647668838501,
      "epoch": 0.008477523693591862,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0001945,
      "loss": 7.3872,
      "mean_token_accuracy": 0.09148699790239334,
      "num_tokens": 613512.0,
      "step": 390
    },
    {
      "entropy": 7.641701507568359,
      "epoch": 0.008586209894791757,
      "grad_norm": 1.078125,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.3275,
      "mean_token_accuracy": 0.09618531838059426,
      "num_tokens": 621117.0,
      "step": 395
    },
    {
      "entropy": 7.689551591873169,
      "epoch": 0.008694896095991653,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.3832,
      "mean_token_accuracy": 0.08407204449176789,
      "num_tokens": 629970.0,
      "step": 400
    },
    {
      "entropy": 7.637691450119019,
      "epoch": 0.008803582297191548,
      "grad_norm": 1.375,
      "learning_rate": 0.000202,
      "loss": 7.3219,
      "mean_token_accuracy": 0.09131594821810722,
      "num_tokens": 638184.0,
      "step": 405
    },
    {
      "entropy": 7.5977555274963375,
      "epoch": 0.008912268498391444,
      "grad_norm": 1.3515625,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.2837,
      "mean_token_accuracy": 0.08929966911673545,
      "num_tokens": 645953.0,
      "step": 410
    },
    {
      "entropy": 7.6464704990386965,
      "epoch": 0.00902095469959134,
      "grad_norm": 1.25,
      "learning_rate": 0.000207,
      "loss": 7.3305,
      "mean_token_accuracy": 0.08722574934363365,
      "num_tokens": 654291.0,
      "step": 415
    },
    {
      "entropy": 7.672793436050415,
      "epoch": 0.009129640900791236,
      "grad_norm": 1.21875,
      "learning_rate": 0.0002095,
      "loss": 7.3299,
      "mean_token_accuracy": 0.08851959705352783,
      "num_tokens": 661393.0,
      "step": 420
    },
    {
      "entropy": 7.531088209152221,
      "epoch": 0.009238327101991132,
      "grad_norm": 1.4296875,
      "learning_rate": 0.000212,
      "loss": 7.3139,
      "mean_token_accuracy": 0.0963095597922802,
      "num_tokens": 669913.0,
      "step": 425
    },
    {
      "entropy": 7.74607515335083,
      "epoch": 0.009347013303191027,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0002145,
      "loss": 7.3663,
      "mean_token_accuracy": 0.09074652194976807,
      "num_tokens": 678745.0,
      "step": 430
    },
    {
      "entropy": 7.417545986175537,
      "epoch": 0.009455699504390923,
      "grad_norm": 1.265625,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.2468,
      "mean_token_accuracy": 0.09117906540632248,
      "num_tokens": 686191.0,
      "step": 435
    },
    {
      "entropy": 7.690976524353028,
      "epoch": 0.009564385705590818,
      "grad_norm": 2.109375,
      "learning_rate": 0.0002195,
      "loss": 7.2921,
      "mean_token_accuracy": 0.08830784261226654,
      "num_tokens": 694776.0,
      "step": 440
    },
    {
      "entropy": 7.471565675735474,
      "epoch": 0.009673071906790714,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000222,
      "loss": 7.2498,
      "mean_token_accuracy": 0.08958808556199074,
      "num_tokens": 702481.0,
      "step": 445
    },
    {
      "entropy": 7.601398086547851,
      "epoch": 0.00978175810799061,
      "grad_norm": 1.265625,
      "learning_rate": 0.0002245,
      "loss": 7.2892,
      "mean_token_accuracy": 0.08943363651633263,
      "num_tokens": 710304.0,
      "step": 450
    },
    {
      "entropy": 7.6107948303222654,
      "epoch": 0.009890444309190505,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00022700000000000002,
      "loss": 7.2655,
      "mean_token_accuracy": 0.0950858935713768,
      "num_tokens": 718462.0,
      "step": 455
    },
    {
      "entropy": 7.4872644424438475,
      "epoch": 0.0099991305103904,
      "grad_norm": 1.0625,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.2699,
      "mean_token_accuracy": 0.09967489093542099,
      "num_tokens": 726798.0,
      "step": 460
    },
    {
      "entropy": 7.636318254470825,
      "epoch": 0.010107816711590296,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.2289,
      "mean_token_accuracy": 0.09415075033903123,
      "num_tokens": 735054.0,
      "step": 465
    },
    {
      "entropy": 7.467661046981812,
      "epoch": 0.010216502912790193,
      "grad_norm": 1.34375,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.2689,
      "mean_token_accuracy": 0.08854644820094108,
      "num_tokens": 743701.0,
      "step": 470
    },
    {
      "entropy": 7.5553264141082765,
      "epoch": 0.010325189113990088,
      "grad_norm": 1.2421875,
      "learning_rate": 0.000237,
      "loss": 7.3436,
      "mean_token_accuracy": 0.08918146193027496,
      "num_tokens": 751548.0,
      "step": 475
    },
    {
      "entropy": 7.606575393676758,
      "epoch": 0.010433875315189984,
      "grad_norm": 1.359375,
      "learning_rate": 0.0002395,
      "loss": 7.1245,
      "mean_token_accuracy": 0.09939143806695938,
      "num_tokens": 758580.0,
      "step": 480
    },
    {
      "entropy": 7.376218938827515,
      "epoch": 0.01054256151638988,
      "grad_norm": 1.375,
      "learning_rate": 0.000242,
      "loss": 7.1472,
      "mean_token_accuracy": 0.09824580624699593,
      "num_tokens": 766240.0,
      "step": 485
    },
    {
      "entropy": 7.460130596160889,
      "epoch": 0.010651247717589775,
      "grad_norm": 1.3125,
      "learning_rate": 0.0002445,
      "loss": 7.1908,
      "mean_token_accuracy": 0.09887742102146149,
      "num_tokens": 774206.0,
      "step": 490
    },
    {
      "entropy": 7.499665117263794,
      "epoch": 0.01075993391878967,
      "grad_norm": 1.15625,
      "learning_rate": 0.000247,
      "loss": 7.135,
      "mean_token_accuracy": 0.10001260414719582,
      "num_tokens": 782005.0,
      "step": 495
    },
    {
      "entropy": 7.313957262039184,
      "epoch": 0.010868620119989566,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0002495,
      "loss": 7.1614,
      "mean_token_accuracy": 0.10134897753596306,
      "num_tokens": 790043.0,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1294440726528000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}