{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03214813862277374,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.742344284057618,
      "epoch": 0.00032148138622773744,
      "grad_norm": 5.1875,
      "learning_rate": 2e-06,
      "loss": 10.7889,
      "mean_token_accuracy": 0.0001923076924867928,
      "num_tokens": 10787.0,
      "step": 5
    },
    {
      "entropy": 10.742341995239258,
      "epoch": 0.0006429627724554749,
      "grad_norm": 4.6875,
      "learning_rate": 4.5e-06,
      "loss": 10.7754,
      "mean_token_accuracy": 9.199631749652326e-05,
      "num_tokens": 21408.0,
      "step": 10
    },
    {
      "entropy": 10.74231481552124,
      "epoch": 0.0009644441586832123,
      "grad_norm": 4.84375,
      "learning_rate": 7e-06,
      "loss": 10.7745,
      "mean_token_accuracy": 0.0,
      "num_tokens": 33838.0,
      "step": 15
    },
    {
      "entropy": 10.742263031005859,
      "epoch": 0.0012859255449109497,
      "grad_norm": 4.875,
      "learning_rate": 9.5e-06,
      "loss": 10.7415,
      "mean_token_accuracy": 0.0,
      "num_tokens": 46592.0,
      "step": 20
    },
    {
      "entropy": 10.742058944702148,
      "epoch": 0.001607406931138687,
      "grad_norm": 4.21875,
      "learning_rate": 1.2e-05,
      "loss": 10.6278,
      "mean_token_accuracy": 0.00028761792345903813,
      "num_tokens": 57409.0,
      "step": 25
    },
    {
      "entropy": 10.741728782653809,
      "epoch": 0.0019288883173664245,
      "grad_norm": 3.71875,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.5262,
      "mean_token_accuracy": 0.005182119726669043,
      "num_tokens": 68705.0,
      "step": 30
    },
    {
      "entropy": 10.74124059677124,
      "epoch": 0.002250369703594162,
      "grad_norm": 3.09375,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.4297,
      "mean_token_accuracy": 0.019557270966470242,
      "num_tokens": 81460.0,
      "step": 35
    },
    {
      "entropy": 10.740433311462402,
      "epoch": 0.0025718510898218995,
      "grad_norm": 2.5,
      "learning_rate": 1.95e-05,
      "loss": 10.2725,
      "mean_token_accuracy": 0.02960890345275402,
      "num_tokens": 93576.0,
      "step": 40
    },
    {
      "entropy": 10.739229869842529,
      "epoch": 0.0028933324760496365,
      "grad_norm": 2.125,
      "learning_rate": 2.2e-05,
      "loss": 10.1857,
      "mean_token_accuracy": 0.02886150423437357,
      "num_tokens": 105556.0,
      "step": 45
    },
    {
      "entropy": 10.738618659973145,
      "epoch": 0.003214813862277374,
      "grad_norm": 2.03125,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 10.0792,
      "mean_token_accuracy": 0.031074166856706144,
      "num_tokens": 117850.0,
      "step": 50
    },
    {
      "entropy": 10.738714694976807,
      "epoch": 0.0035362952485051115,
      "grad_norm": 1.9296875,
      "learning_rate": 2.7e-05,
      "loss": 10.0244,
      "mean_token_accuracy": 0.031163782812654972,
      "num_tokens": 130955.0,
      "step": 55
    },
    {
      "entropy": 10.738016033172608,
      "epoch": 0.003857776634732849,
      "grad_norm": 1.9140625,
      "learning_rate": 2.95e-05,
      "loss": 9.9307,
      "mean_token_accuracy": 0.03660368006676436,
      "num_tokens": 141959.0,
      "step": 60
    },
    {
      "entropy": 10.736786365509033,
      "epoch": 0.0041792580209605865,
      "grad_norm": 1.84375,
      "learning_rate": 3.2e-05,
      "loss": 9.8915,
      "mean_token_accuracy": 0.03608605414628983,
      "num_tokens": 153856.0,
      "step": 65
    },
    {
      "entropy": 10.73516550064087,
      "epoch": 0.004500739407188324,
      "grad_norm": 1.9140625,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.8384,
      "mean_token_accuracy": 0.043716078624129295,
      "num_tokens": 166748.0,
      "step": 70
    },
    {
      "entropy": 10.732550621032715,
      "epoch": 0.0048222207934160615,
      "grad_norm": 1.9375,
      "learning_rate": 3.7e-05,
      "loss": 9.728,
      "mean_token_accuracy": 0.04251385778188706,
      "num_tokens": 177172.0,
      "step": 75
    },
    {
      "entropy": 10.728882122039796,
      "epoch": 0.005143702179643799,
      "grad_norm": 1.8046875,
      "learning_rate": 3.95e-05,
      "loss": 9.6737,
      "mean_token_accuracy": 0.04158058017492294,
      "num_tokens": 189418.0,
      "step": 80
    },
    {
      "entropy": 10.723980331420899,
      "epoch": 0.0054651835658715365,
      "grad_norm": 2.0625,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.5846,
      "mean_token_accuracy": 0.039340490289032456,
      "num_tokens": 201349.0,
      "step": 85
    },
    {
      "entropy": 10.718004131317139,
      "epoch": 0.005786664952099273,
      "grad_norm": 1.8046875,
      "learning_rate": 4.45e-05,
      "loss": 9.5176,
      "mean_token_accuracy": 0.04345524609088898,
      "num_tokens": 212298.0,
      "step": 90
    },
    {
      "entropy": 10.710467433929443,
      "epoch": 0.0061081463383270106,
      "grad_norm": 1.796875,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.467,
      "mean_token_accuracy": 0.04573878571391106,
      "num_tokens": 223831.0,
      "step": 95
    },
    {
      "entropy": 10.699566841125488,
      "epoch": 0.006429627724554748,
      "grad_norm": 1.78125,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.3601,
      "mean_token_accuracy": 0.04835316389799118,
      "num_tokens": 236675.0,
      "step": 100
    },
    {
      "entropy": 10.683355236053467,
      "epoch": 0.0067511091107824855,
      "grad_norm": 1.7421875,
      "learning_rate": 5.2e-05,
      "loss": 9.242,
      "mean_token_accuracy": 0.04662417732179165,
      "num_tokens": 247634.0,
      "step": 105
    },
    {
      "entropy": 10.66143503189087,
      "epoch": 0.007072590497010223,
      "grad_norm": 1.8046875,
      "learning_rate": 5.45e-05,
      "loss": 9.1162,
      "mean_token_accuracy": 0.05328451320528984,
      "num_tokens": 259101.0,
      "step": 110
    },
    {
      "entropy": 10.631138801574707,
      "epoch": 0.0073940718832379605,
      "grad_norm": 1.6328125,
      "learning_rate": 5.7e-05,
      "loss": 9.0393,
      "mean_token_accuracy": 0.05271790884435177,
      "num_tokens": 272151.0,
      "step": 115
    },
    {
      "entropy": 10.594438171386718,
      "epoch": 0.007715553269465698,
      "grad_norm": 1.75,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.8606,
      "mean_token_accuracy": 0.057512912154197696,
      "num_tokens": 283619.0,
      "step": 120
    },
    {
      "entropy": 10.537901401519775,
      "epoch": 0.008037034655693436,
      "grad_norm": 1.734375,
      "learning_rate": 6.2e-05,
      "loss": 8.7551,
      "mean_token_accuracy": 0.05864038914442062,
      "num_tokens": 296233.0,
      "step": 125
    },
    {
      "entropy": 10.46686897277832,
      "epoch": 0.008358516041921173,
      "grad_norm": 1.6015625,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.6685,
      "mean_token_accuracy": 0.05632430389523506,
      "num_tokens": 309222.0,
      "step": 130
    },
    {
      "entropy": 10.386721515655518,
      "epoch": 0.00867999742814891,
      "grad_norm": 1.515625,
      "learning_rate": 6.7e-05,
      "loss": 8.4983,
      "mean_token_accuracy": 0.05754401199519634,
      "num_tokens": 322291.0,
      "step": 135
    },
    {
      "entropy": 10.285922241210937,
      "epoch": 0.009001478814376648,
      "grad_norm": 1.484375,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.3328,
      "mean_token_accuracy": 0.06465739980340005,
      "num_tokens": 333520.0,
      "step": 140
    },
    {
      "entropy": 10.168986701965332,
      "epoch": 0.009322960200604385,
      "grad_norm": 1.453125,
      "learning_rate": 7.2e-05,
      "loss": 8.1641,
      "mean_token_accuracy": 0.0657901257276535,
      "num_tokens": 344883.0,
      "step": 145
    },
    {
      "entropy": 10.042533111572265,
      "epoch": 0.009644441586832123,
      "grad_norm": 1.3515625,
      "learning_rate": 7.45e-05,
      "loss": 8.0727,
      "mean_token_accuracy": 0.07245785929262638,
      "num_tokens": 356600.0,
      "step": 150
    },
    {
      "entropy": 9.882461643218994,
      "epoch": 0.00996592297305986,
      "grad_norm": 1.4609375,
      "learning_rate": 7.7e-05,
      "loss": 7.9127,
      "mean_token_accuracy": 0.0721237450838089,
      "num_tokens": 368527.0,
      "step": 155
    },
    {
      "entropy": 9.694390869140625,
      "epoch": 0.010287404359287598,
      "grad_norm": 1.5,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.8511,
      "mean_token_accuracy": 0.06826285421848297,
      "num_tokens": 379836.0,
      "step": 160
    },
    {
      "entropy": 9.510071659088135,
      "epoch": 0.010608885745515335,
      "grad_norm": 1.0625,
      "learning_rate": 8.2e-05,
      "loss": 7.8393,
      "mean_token_accuracy": 0.0674971140921116,
      "num_tokens": 392535.0,
      "step": 165
    },
    {
      "entropy": 9.299476528167725,
      "epoch": 0.010930367131743073,
      "grad_norm": 0.91015625,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.7515,
      "mean_token_accuracy": 0.06860553249716758,
      "num_tokens": 405259.0,
      "step": 170
    },
    {
      "entropy": 9.040483093261718,
      "epoch": 0.011251848517970809,
      "grad_norm": 0.96875,
      "learning_rate": 8.7e-05,
      "loss": 7.599,
      "mean_token_accuracy": 0.07114262394607067,
      "num_tokens": 417922.0,
      "step": 175
    },
    {
      "entropy": 8.870688247680665,
      "epoch": 0.011573329904198546,
      "grad_norm": 1.078125,
      "learning_rate": 8.95e-05,
      "loss": 7.6169,
      "mean_token_accuracy": 0.07012484185397624,
      "num_tokens": 429411.0,
      "step": 180
    },
    {
      "entropy": 8.67488489151001,
      "epoch": 0.011894811290426284,
      "grad_norm": 1.171875,
      "learning_rate": 9.2e-05,
      "loss": 7.386,
      "mean_token_accuracy": 0.0772802360355854,
      "num_tokens": 439950.0,
      "step": 185
    },
    {
      "entropy": 8.489033699035645,
      "epoch": 0.012216292676654021,
      "grad_norm": 1.328125,
      "learning_rate": 9.45e-05,
      "loss": 7.3822,
      "mean_token_accuracy": 0.07805034667253494,
      "num_tokens": 451245.0,
      "step": 190
    },
    {
      "entropy": 8.393837928771973,
      "epoch": 0.012537774062881759,
      "grad_norm": 0.8671875,
      "learning_rate": 9.7e-05,
      "loss": 7.4539,
      "mean_token_accuracy": 0.07150709182024002,
      "num_tokens": 465146.0,
      "step": 195
    },
    {
      "entropy": 8.359711456298829,
      "epoch": 0.012859255449109496,
      "grad_norm": 1.28125,
      "learning_rate": 9.95e-05,
      "loss": 7.4708,
      "mean_token_accuracy": 0.07765417769551278,
      "num_tokens": 477079.0,
      "step": 200
    },
    {
      "entropy": 8.254557895660401,
      "epoch": 0.013180736835337234,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000102,
      "loss": 7.2964,
      "mean_token_accuracy": 0.08167731463909149,
      "num_tokens": 488216.0,
      "step": 205
    },
    {
      "entropy": 8.201800632476807,
      "epoch": 0.013502218221564971,
      "grad_norm": 1.3984375,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.2996,
      "mean_token_accuracy": 0.08416381254792213,
      "num_tokens": 501040.0,
      "step": 210
    },
    {
      "entropy": 8.122812938690185,
      "epoch": 0.013823699607792709,
      "grad_norm": 1.015625,
      "learning_rate": 0.000107,
      "loss": 7.2535,
      "mean_token_accuracy": 0.08663205504417419,
      "num_tokens": 512636.0,
      "step": 215
    },
    {
      "entropy": 8.088646793365479,
      "epoch": 0.014145180994020446,
      "grad_norm": 0.9765625,
      "learning_rate": 0.0001095,
      "loss": 7.301,
      "mean_token_accuracy": 0.08183000981807709,
      "num_tokens": 525249.0,
      "step": 220
    },
    {
      "entropy": 8.097221660614014,
      "epoch": 0.014466662380248184,
      "grad_norm": 1.34375,
      "learning_rate": 0.000112,
      "loss": 7.3486,
      "mean_token_accuracy": 0.08002460822463035,
      "num_tokens": 536963.0,
      "step": 225
    },
    {
      "entropy": 8.05938491821289,
      "epoch": 0.014788143766475921,
      "grad_norm": 1.171875,
      "learning_rate": 0.0001145,
      "loss": 7.2099,
      "mean_token_accuracy": 0.08030182272195815,
      "num_tokens": 549008.0,
      "step": 230
    },
    {
      "entropy": 8.041013956069946,
      "epoch": 0.015109625152703659,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.2319,
      "mean_token_accuracy": 0.09074903577566147,
      "num_tokens": 560958.0,
      "step": 235
    },
    {
      "entropy": 7.961578607559204,
      "epoch": 0.015431106538931396,
      "grad_norm": 0.9921875,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.1147,
      "mean_token_accuracy": 0.09378238469362259,
      "num_tokens": 572472.0,
      "step": 240
    },
    {
      "entropy": 7.922268009185791,
      "epoch": 0.015752587925159132,
      "grad_norm": 1.015625,
      "learning_rate": 0.000122,
      "loss": 7.1808,
      "mean_token_accuracy": 0.08942435756325721,
      "num_tokens": 585125.0,
      "step": 245
    },
    {
      "entropy": 7.913467741012573,
      "epoch": 0.01607406931138687,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0001245,
      "loss": 7.1259,
      "mean_token_accuracy": 0.09376866966485978,
      "num_tokens": 597774.0,
      "step": 250
    },
    {
      "entropy": 7.856596946716309,
      "epoch": 0.016395550697614607,
      "grad_norm": 0.98828125,
      "learning_rate": 0.000127,
      "loss": 7.1233,
      "mean_token_accuracy": 0.09992039278149605,
      "num_tokens": 610130.0,
      "step": 255
    },
    {
      "entropy": 7.8915050506591795,
      "epoch": 0.016717032083842346,
      "grad_norm": 1.03125,
      "learning_rate": 0.0001295,
      "loss": 7.1488,
      "mean_token_accuracy": 0.09605236500501632,
      "num_tokens": 621659.0,
      "step": 260
    },
    {
      "entropy": 7.833514070510864,
      "epoch": 0.017038513470070082,
      "grad_norm": 1.0078125,
      "learning_rate": 0.000132,
      "loss": 7.0552,
      "mean_token_accuracy": 0.09916835874319077,
      "num_tokens": 633172.0,
      "step": 265
    },
    {
      "entropy": 7.854182243347168,
      "epoch": 0.01735999485629782,
      "grad_norm": 1.125,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.0595,
      "mean_token_accuracy": 0.09681920260190964,
      "num_tokens": 643928.0,
      "step": 270
    },
    {
      "entropy": 7.712904834747315,
      "epoch": 0.017681476242525557,
      "grad_norm": 1.2265625,
      "learning_rate": 0.00013700000000000002,
      "loss": 6.9556,
      "mean_token_accuracy": 0.09763396382331849,
      "num_tokens": 654693.0,
      "step": 275
    },
    {
      "entropy": 7.817079973220825,
      "epoch": 0.018002957628753296,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0001395,
      "loss": 7.1338,
      "mean_token_accuracy": 0.09172611869871616,
      "num_tokens": 667216.0,
      "step": 280
    },
    {
      "entropy": 7.727632856369018,
      "epoch": 0.01832443901498103,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00014199999999999998,
      "loss": 6.9273,
      "mean_token_accuracy": 0.10492636933922768,
      "num_tokens": 679605.0,
      "step": 285
    },
    {
      "entropy": 7.6807286739349365,
      "epoch": 0.01864592040120877,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0001445,
      "loss": 7.0243,
      "mean_token_accuracy": 0.09721777960658073,
      "num_tokens": 691581.0,
      "step": 290
    },
    {
      "entropy": 7.730735111236572,
      "epoch": 0.018967401787436507,
      "grad_norm": 1.203125,
      "learning_rate": 0.000147,
      "loss": 7.064,
      "mean_token_accuracy": 0.10062759071588516,
      "num_tokens": 703162.0,
      "step": 295
    },
    {
      "entropy": 7.675752592086792,
      "epoch": 0.019288883173664246,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0001495,
      "loss": 6.947,
      "mean_token_accuracy": 0.10126433670520782,
      "num_tokens": 715024.0,
      "step": 300
    },
    {
      "entropy": 7.604991054534912,
      "epoch": 0.01961036455989198,
      "grad_norm": 1.390625,
      "learning_rate": 0.000152,
      "loss": 6.9484,
      "mean_token_accuracy": 0.10657469853758812,
      "num_tokens": 728434.0,
      "step": 305
    },
    {
      "entropy": 7.582369089126587,
      "epoch": 0.01993184594611972,
      "grad_norm": 1.109375,
      "learning_rate": 0.00015450000000000001,
      "loss": 6.9856,
      "mean_token_accuracy": 0.10384280532598496,
      "num_tokens": 741049.0,
      "step": 310
    },
    {
      "entropy": 7.556066989898682,
      "epoch": 0.020253327332347457,
      "grad_norm": 1.0234375,
      "learning_rate": 0.000157,
      "loss": 6.8995,
      "mean_token_accuracy": 0.10891256630420684,
      "num_tokens": 753316.0,
      "step": 315
    },
    {
      "entropy": 7.487519884109497,
      "epoch": 0.020574808718575196,
      "grad_norm": 1.078125,
      "learning_rate": 0.0001595,
      "loss": 6.8976,
      "mean_token_accuracy": 0.10375816151499748,
      "num_tokens": 766605.0,
      "step": 320
    },
    {
      "entropy": 7.575658369064331,
      "epoch": 0.02089629010480293,
      "grad_norm": 1.125,
      "learning_rate": 0.000162,
      "loss": 6.8776,
      "mean_token_accuracy": 0.10548696890473366,
      "num_tokens": 778857.0,
      "step": 325
    },
    {
      "entropy": 7.49542875289917,
      "epoch": 0.02121777149103067,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00016450000000000001,
      "loss": 6.8801,
      "mean_token_accuracy": 0.0980547919869423,
      "num_tokens": 790497.0,
      "step": 330
    },
    {
      "entropy": 7.548171281814575,
      "epoch": 0.021539252877258407,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00016700000000000002,
      "loss": 6.9457,
      "mean_token_accuracy": 0.10034449025988579,
      "num_tokens": 803021.0,
      "step": 335
    },
    {
      "entropy": 7.514672136306762,
      "epoch": 0.021860734263486146,
      "grad_norm": 1.234375,
      "learning_rate": 0.00016950000000000003,
      "loss": 6.8973,
      "mean_token_accuracy": 0.10233017727732659,
      "num_tokens": 815056.0,
      "step": 340
    },
    {
      "entropy": 7.548324632644653,
      "epoch": 0.02218221564971388,
      "grad_norm": 0.984375,
      "learning_rate": 0.00017199999999999998,
      "loss": 6.8436,
      "mean_token_accuracy": 0.11048155352473259,
      "num_tokens": 827149.0,
      "step": 345
    },
    {
      "entropy": 7.47729377746582,
      "epoch": 0.022503697035941617,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00017449999999999999,
      "loss": 6.8877,
      "mean_token_accuracy": 0.10872978940606118,
      "num_tokens": 839172.0,
      "step": 350
    },
    {
      "entropy": 7.497987508773804,
      "epoch": 0.022825178422169357,
      "grad_norm": 1.75,
      "learning_rate": 0.000177,
      "loss": 6.9329,
      "mean_token_accuracy": 0.10738308876752853,
      "num_tokens": 851148.0,
      "step": 355
    },
    {
      "entropy": 7.548883295059204,
      "epoch": 0.023146659808397092,
      "grad_norm": 1.140625,
      "learning_rate": 0.0001795,
      "loss": 6.8783,
      "mean_token_accuracy": 0.10820900201797486,
      "num_tokens": 862904.0,
      "step": 360
    },
    {
      "entropy": 7.436304187774658,
      "epoch": 0.02346814119462483,
      "grad_norm": 1.359375,
      "learning_rate": 0.000182,
      "loss": 6.7668,
      "mean_token_accuracy": 0.11688080206513404,
      "num_tokens": 874720.0,
      "step": 365
    },
    {
      "entropy": 7.409350728988647,
      "epoch": 0.023789622580852567,
      "grad_norm": 1.0625,
      "learning_rate": 0.0001845,
      "loss": 6.8078,
      "mean_token_accuracy": 0.11283540055155754,
      "num_tokens": 887261.0,
      "step": 370
    },
    {
      "entropy": 7.4675617694854735,
      "epoch": 0.024111103967080307,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000187,
      "loss": 6.7767,
      "mean_token_accuracy": 0.1088891163468361,
      "num_tokens": 898048.0,
      "step": 375
    },
    {
      "entropy": 7.336610507965088,
      "epoch": 0.024432585353308042,
      "grad_norm": 1.03125,
      "learning_rate": 0.0001895,
      "loss": 6.8343,
      "mean_token_accuracy": 0.11030351296067238,
      "num_tokens": 910297.0,
      "step": 380
    },
    {
      "entropy": 7.432262849807739,
      "epoch": 0.02475406673953578,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000192,
      "loss": 6.8693,
      "mean_token_accuracy": 0.10626164525747299,
      "num_tokens": 923463.0,
      "step": 385
    },
    {
      "entropy": 7.399855327606201,
      "epoch": 0.025075548125763517,
      "grad_norm": 0.99609375,
      "learning_rate": 0.0001945,
      "loss": 6.8379,
      "mean_token_accuracy": 0.11091364100575447,
      "num_tokens": 935306.0,
      "step": 390
    },
    {
      "entropy": 7.355379390716553,
      "epoch": 0.025397029511991256,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00019700000000000002,
      "loss": 6.7379,
      "mean_token_accuracy": 0.115155877918005,
      "num_tokens": 947827.0,
      "step": 395
    },
    {
      "entropy": 7.281255531311035,
      "epoch": 0.025718510898218992,
      "grad_norm": 1.375,
      "learning_rate": 0.00019950000000000002,
      "loss": 6.6838,
      "mean_token_accuracy": 0.12000245451927186,
      "num_tokens": 961664.0,
      "step": 400
    },
    {
      "entropy": 7.312869071960449,
      "epoch": 0.02603999228444673,
      "grad_norm": 1.21875,
      "learning_rate": 0.000202,
      "loss": 6.7829,
      "mean_token_accuracy": 0.09842887446284294,
      "num_tokens": 973981.0,
      "step": 405
    },
    {
      "entropy": 7.335048866271973,
      "epoch": 0.026361473670674467,
      "grad_norm": 1.3515625,
      "learning_rate": 0.00020449999999999998,
      "loss": 6.8181,
      "mean_token_accuracy": 0.11232979372143745,
      "num_tokens": 986702.0,
      "step": 410
    },
    {
      "entropy": 7.318604183197022,
      "epoch": 0.026682955056902206,
      "grad_norm": 1.1640625,
      "learning_rate": 0.000207,
      "loss": 6.7181,
      "mean_token_accuracy": 0.11695454865694047,
      "num_tokens": 998513.0,
      "step": 415
    },
    {
      "entropy": 7.294521141052246,
      "epoch": 0.027004436443129942,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0002095,
      "loss": 6.7037,
      "mean_token_accuracy": 0.11898418515920639,
      "num_tokens": 1011111.0,
      "step": 420
    },
    {
      "entropy": 7.186019515991211,
      "epoch": 0.02732591782935768,
      "grad_norm": 1.2578125,
      "learning_rate": 0.000212,
      "loss": 6.6799,
      "mean_token_accuracy": 0.11566238775849343,
      "num_tokens": 1021779.0,
      "step": 425
    },
    {
      "entropy": 7.370555067062378,
      "epoch": 0.027647399215585417,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0002145,
      "loss": 6.7381,
      "mean_token_accuracy": 0.11263754442334176,
      "num_tokens": 1033228.0,
      "step": 430
    },
    {
      "entropy": 7.226527881622315,
      "epoch": 0.027968880601813156,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00021700000000000002,
      "loss": 6.6415,
      "mean_token_accuracy": 0.11632440984249115,
      "num_tokens": 1044964.0,
      "step": 435
    },
    {
      "entropy": 7.18967342376709,
      "epoch": 0.028290361988040892,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0002195,
      "loss": 6.6058,
      "mean_token_accuracy": 0.12256524711847305,
      "num_tokens": 1056450.0,
      "step": 440
    },
    {
      "entropy": 7.242304182052612,
      "epoch": 0.02861184337426863,
      "grad_norm": 1.0703125,
      "learning_rate": 0.000222,
      "loss": 6.7402,
      "mean_token_accuracy": 0.1159943200647831,
      "num_tokens": 1067031.0,
      "step": 445
    },
    {
      "entropy": 7.1245410442352295,
      "epoch": 0.028933324760496367,
      "grad_norm": 1.3046875,
      "learning_rate": 0.0002245,
      "loss": 6.6051,
      "mean_token_accuracy": 0.1228414848446846,
      "num_tokens": 1078718.0,
      "step": 450
    },
    {
      "entropy": 7.182725429534912,
      "epoch": 0.029254806146724106,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.6217,
      "mean_token_accuracy": 0.11590910404920578,
      "num_tokens": 1091630.0,
      "step": 455
    },
    {
      "entropy": 7.229373598098755,
      "epoch": 0.029576287532951842,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.6761,
      "mean_token_accuracy": 0.11919770017266273,
      "num_tokens": 1102339.0,
      "step": 460
    },
    {
      "entropy": 7.166626882553101,
      "epoch": 0.029897768919179578,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.6491,
      "mean_token_accuracy": 0.11653751060366631,
      "num_tokens": 1114385.0,
      "step": 465
    },
    {
      "entropy": 7.213460397720337,
      "epoch": 0.030219250305407317,
      "grad_norm": 1.0625,
      "learning_rate": 0.00023449999999999998,
      "loss": 6.6627,
      "mean_token_accuracy": 0.12240460664033889,
      "num_tokens": 1126364.0,
      "step": 470
    },
    {
      "entropy": 7.160998678207397,
      "epoch": 0.030540731691635053,
      "grad_norm": 1.265625,
      "learning_rate": 0.000237,
      "loss": 6.6469,
      "mean_token_accuracy": 0.12170583978295327,
      "num_tokens": 1137492.0,
      "step": 475
    },
    {
      "entropy": 7.108113145828247,
      "epoch": 0.030862213077862792,
      "grad_norm": 1.078125,
      "learning_rate": 0.0002395,
      "loss": 6.5317,
      "mean_token_accuracy": 0.12732059210538865,
      "num_tokens": 1148734.0,
      "step": 480
    },
    {
      "entropy": 7.14542589187622,
      "epoch": 0.031183694464090528,
      "grad_norm": 0.96875,
      "learning_rate": 0.000242,
      "loss": 6.6757,
      "mean_token_accuracy": 0.12211950346827508,
      "num_tokens": 1163229.0,
      "step": 485
    },
    {
      "entropy": 7.165257167816162,
      "epoch": 0.031505175850318264,
      "grad_norm": 1.015625,
      "learning_rate": 0.0002445,
      "loss": 6.6959,
      "mean_token_accuracy": 0.1155033528804779,
      "num_tokens": 1175452.0,
      "step": 490
    },
    {
      "entropy": 7.1013343334198,
      "epoch": 0.031826657236546006,
      "grad_norm": 1.0078125,
      "learning_rate": 0.000247,
      "loss": 6.5479,
      "mean_token_accuracy": 0.12406643405556679,
      "num_tokens": 1187836.0,
      "step": 495
    },
    {
      "entropy": 7.197257661819458,
      "epoch": 0.03214813862277374,
      "grad_norm": 1.09375,
      "learning_rate": 0.0002495,
      "loss": 6.6297,
      "mean_token_accuracy": 0.12298163026571274,
      "num_tokens": 1198867.0,
      "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": 267606171648000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}