{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1307787876806382,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000653893938403191,
      "grad_norm": 8.1875,
      "learning_rate": 1e-05,
      "loss": 10.9496,
      "step": 5
    },
    {
      "epoch": 0.001307787876806382,
      "grad_norm": 7.6875,
      "learning_rate": 2e-05,
      "loss": 10.8725,
      "step": 10
    },
    {
      "epoch": 0.001961681815209573,
      "grad_norm": 5.09375,
      "learning_rate": 3e-05,
      "loss": 10.6675,
      "step": 15
    },
    {
      "epoch": 0.002615575753612764,
      "grad_norm": 3.609375,
      "learning_rate": 4e-05,
      "loss": 10.4669,
      "step": 20
    },
    {
      "epoch": 0.003269469692015955,
      "grad_norm": 3.296875,
      "learning_rate": 5e-05,
      "loss": 10.315,
      "step": 25
    },
    {
      "epoch": 0.003923363630419146,
      "grad_norm": 3.21875,
      "learning_rate": 6e-05,
      "loss": 10.1836,
      "step": 30
    },
    {
      "epoch": 0.004577257568822337,
      "grad_norm": 2.875,
      "learning_rate": 7.000000000000001e-05,
      "loss": 10.0898,
      "step": 35
    },
    {
      "epoch": 0.005231151507225528,
      "grad_norm": 2.859375,
      "learning_rate": 8e-05,
      "loss": 9.9304,
      "step": 40
    },
    {
      "epoch": 0.005885045445628719,
      "grad_norm": 2.53125,
      "learning_rate": 8.999999999999999e-05,
      "loss": 9.7707,
      "step": 45
    },
    {
      "epoch": 0.00653893938403191,
      "grad_norm": 2.65625,
      "learning_rate": 0.0001,
      "loss": 9.5651,
      "step": 50
    },
    {
      "epoch": 0.007192833322435101,
      "grad_norm": 2.21875,
      "learning_rate": 0.00011,
      "loss": 9.3713,
      "step": 55
    },
    {
      "epoch": 0.007846727260838291,
      "grad_norm": 2.15625,
      "learning_rate": 0.00012,
      "loss": 9.1757,
      "step": 60
    },
    {
      "epoch": 0.008500621199241483,
      "grad_norm": 1.890625,
      "learning_rate": 0.00013000000000000002,
      "loss": 9.0253,
      "step": 65
    },
    {
      "epoch": 0.009154515137644674,
      "grad_norm": 1.515625,
      "learning_rate": 0.00014000000000000001,
      "loss": 8.8424,
      "step": 70
    },
    {
      "epoch": 0.009808409076047865,
      "grad_norm": 1.4375,
      "learning_rate": 0.00015,
      "loss": 8.686,
      "step": 75
    },
    {
      "epoch": 0.010462303014451056,
      "grad_norm": 1.265625,
      "learning_rate": 0.00016,
      "loss": 8.5556,
      "step": 80
    },
    {
      "epoch": 0.011116196952854247,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00017,
      "loss": 8.5653,
      "step": 85
    },
    {
      "epoch": 0.011770090891257438,
      "grad_norm": 1.21875,
      "learning_rate": 0.00017999999999999998,
      "loss": 8.4762,
      "step": 90
    },
    {
      "epoch": 0.01242398482966063,
      "grad_norm": 1.234375,
      "learning_rate": 0.00019,
      "loss": 8.4341,
      "step": 95
    },
    {
      "epoch": 0.01307787876806382,
      "grad_norm": 1.4375,
      "learning_rate": 0.0002,
      "loss": 8.4259,
      "step": 100
    },
    {
      "epoch": 0.013731772706467011,
      "grad_norm": 1.234375,
      "learning_rate": 0.00021,
      "loss": 8.4247,
      "step": 105
    },
    {
      "epoch": 0.014385666644870202,
      "grad_norm": 1.7578125,
      "learning_rate": 0.00022,
      "loss": 8.4139,
      "step": 110
    },
    {
      "epoch": 0.015039560583273394,
      "grad_norm": 1.6796875,
      "learning_rate": 0.00023,
      "loss": 8.3534,
      "step": 115
    },
    {
      "epoch": 0.015693454521676583,
      "grad_norm": 1.9140625,
      "learning_rate": 0.00024,
      "loss": 8.3723,
      "step": 120
    },
    {
      "epoch": 0.016347348460079774,
      "grad_norm": 1.6484375,
      "learning_rate": 0.00025,
      "loss": 8.266,
      "step": 125
    },
    {
      "epoch": 0.017001242398482965,
      "grad_norm": 1.3125,
      "learning_rate": 0.00026000000000000003,
      "loss": 8.3037,
      "step": 130
    },
    {
      "epoch": 0.017655136336886156,
      "grad_norm": 1.734375,
      "learning_rate": 0.00027,
      "loss": 8.2941,
      "step": 135
    },
    {
      "epoch": 0.018309030275289347,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00028000000000000003,
      "loss": 8.3108,
      "step": 140
    },
    {
      "epoch": 0.01896292421369254,
      "grad_norm": 1.53125,
      "learning_rate": 0.00029,
      "loss": 8.2322,
      "step": 145
    },
    {
      "epoch": 0.01961681815209573,
      "grad_norm": 1.703125,
      "learning_rate": 0.0003,
      "loss": 8.2601,
      "step": 150
    },
    {
      "epoch": 0.02027071209049892,
      "grad_norm": 1.75,
      "learning_rate": 0.00031,
      "loss": 8.2087,
      "step": 155
    },
    {
      "epoch": 0.02092460602890211,
      "grad_norm": 1.46875,
      "learning_rate": 0.00032,
      "loss": 8.3123,
      "step": 160
    },
    {
      "epoch": 0.021578499967305303,
      "grad_norm": 1.5625,
      "learning_rate": 0.00033,
      "loss": 8.1831,
      "step": 165
    },
    {
      "epoch": 0.022232393905708494,
      "grad_norm": 1.421875,
      "learning_rate": 0.00034,
      "loss": 8.1369,
      "step": 170
    },
    {
      "epoch": 0.022886287844111685,
      "grad_norm": 1.421875,
      "learning_rate": 0.00035,
      "loss": 8.1271,
      "step": 175
    },
    {
      "epoch": 0.023540181782514876,
      "grad_norm": 1.328125,
      "learning_rate": 0.00035999999999999997,
      "loss": 8.1362,
      "step": 180
    },
    {
      "epoch": 0.024194075720918067,
      "grad_norm": 1.4375,
      "learning_rate": 0.00037,
      "loss": 8.1593,
      "step": 185
    },
    {
      "epoch": 0.02484796965932126,
      "grad_norm": 1.421875,
      "learning_rate": 0.00038,
      "loss": 8.0507,
      "step": 190
    },
    {
      "epoch": 0.02550186359772445,
      "grad_norm": 1.7890625,
      "learning_rate": 0.00039000000000000005,
      "loss": 8.0434,
      "step": 195
    },
    {
      "epoch": 0.02615575753612764,
      "grad_norm": 1.4140625,
      "learning_rate": 0.0004,
      "loss": 8.0434,
      "step": 200
    },
    {
      "epoch": 0.02680965147453083,
      "grad_norm": 1.515625,
      "learning_rate": 0.00041,
      "loss": 8.0618,
      "step": 205
    },
    {
      "epoch": 0.027463545412934023,
      "grad_norm": 1.3515625,
      "learning_rate": 0.00042,
      "loss": 8.0447,
      "step": 210
    },
    {
      "epoch": 0.028117439351337214,
      "grad_norm": 1.59375,
      "learning_rate": 0.00043,
      "loss": 8.0226,
      "step": 215
    },
    {
      "epoch": 0.028771333289740405,
      "grad_norm": 1.40625,
      "learning_rate": 0.00044,
      "loss": 7.9504,
      "step": 220
    },
    {
      "epoch": 0.029425227228143596,
      "grad_norm": 1.359375,
      "learning_rate": 0.00045000000000000004,
      "loss": 7.9587,
      "step": 225
    },
    {
      "epoch": 0.030079121166546787,
      "grad_norm": 1.4453125,
      "learning_rate": 0.00046,
      "loss": 7.9141,
      "step": 230
    },
    {
      "epoch": 0.030733015104949978,
      "grad_norm": 1.59375,
      "learning_rate": 0.00047,
      "loss": 7.923,
      "step": 235
    },
    {
      "epoch": 0.031386909043353166,
      "grad_norm": 1.4140625,
      "learning_rate": 0.00048,
      "loss": 7.9591,
      "step": 240
    },
    {
      "epoch": 0.03204080298175636,
      "grad_norm": 1.6640625,
      "learning_rate": 0.00049,
      "loss": 7.9369,
      "step": 245
    },
    {
      "epoch": 0.03269469692015955,
      "grad_norm": 1.390625,
      "learning_rate": 0.0005,
      "loss": 7.9401,
      "step": 250
    },
    {
      "epoch": 0.03334859085856274,
      "grad_norm": 1.7109375,
      "learning_rate": 0.00051,
      "loss": 7.9218,
      "step": 255
    },
    {
      "epoch": 0.03400248479696593,
      "grad_norm": 1.5703125,
      "learning_rate": 0.0005200000000000001,
      "loss": 7.9144,
      "step": 260
    },
    {
      "epoch": 0.03465637873536912,
      "grad_norm": 1.421875,
      "learning_rate": 0.0005300000000000001,
      "loss": 7.8008,
      "step": 265
    },
    {
      "epoch": 0.03531027267377231,
      "grad_norm": 1.7578125,
      "learning_rate": 0.00054,
      "loss": 7.8906,
      "step": 270
    },
    {
      "epoch": 0.035964166612175504,
      "grad_norm": 1.6171875,
      "learning_rate": 0.00055,
      "loss": 7.8308,
      "step": 275
    },
    {
      "epoch": 0.036618060550578695,
      "grad_norm": 1.5859375,
      "learning_rate": 0.0005600000000000001,
      "loss": 7.8048,
      "step": 280
    },
    {
      "epoch": 0.037271954488981886,
      "grad_norm": 1.7578125,
      "learning_rate": 0.00057,
      "loss": 7.8612,
      "step": 285
    },
    {
      "epoch": 0.03792584842738508,
      "grad_norm": 1.875,
      "learning_rate": 0.00058,
      "loss": 7.7612,
      "step": 290
    },
    {
      "epoch": 0.03857974236578827,
      "grad_norm": 1.546875,
      "learning_rate": 0.00059,
      "loss": 7.8016,
      "step": 295
    },
    {
      "epoch": 0.03923363630419146,
      "grad_norm": 1.578125,
      "learning_rate": 0.0006,
      "loss": 7.7855,
      "step": 300
    },
    {
      "epoch": 0.03988753024259465,
      "grad_norm": 1.4765625,
      "learning_rate": 0.00061,
      "loss": 7.7743,
      "step": 305
    },
    {
      "epoch": 0.04054142418099784,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00062,
      "loss": 7.7267,
      "step": 310
    },
    {
      "epoch": 0.04119531811940103,
      "grad_norm": 1.8515625,
      "learning_rate": 0.00063,
      "loss": 7.6867,
      "step": 315
    },
    {
      "epoch": 0.04184921205780422,
      "grad_norm": 1.7265625,
      "learning_rate": 0.00064,
      "loss": 7.7052,
      "step": 320
    },
    {
      "epoch": 0.042503105996207415,
      "grad_norm": 1.484375,
      "learning_rate": 0.0006500000000000001,
      "loss": 7.6547,
      "step": 325
    },
    {
      "epoch": 0.043156999934610606,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00066,
      "loss": 7.5959,
      "step": 330
    },
    {
      "epoch": 0.0438108938730138,
      "grad_norm": 1.4765625,
      "learning_rate": 0.00067,
      "loss": 7.6249,
      "step": 335
    },
    {
      "epoch": 0.04446478781141699,
      "grad_norm": 1.5390625,
      "learning_rate": 0.00068,
      "loss": 7.6151,
      "step": 340
    },
    {
      "epoch": 0.04511868174982018,
      "grad_norm": 1.515625,
      "learning_rate": 0.00069,
      "loss": 7.6108,
      "step": 345
    },
    {
      "epoch": 0.04577257568822337,
      "grad_norm": 1.46875,
      "learning_rate": 0.0007,
      "loss": 7.6138,
      "step": 350
    },
    {
      "epoch": 0.04642646962662656,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00071,
      "loss": 7.6191,
      "step": 355
    },
    {
      "epoch": 0.04708036356502975,
      "grad_norm": 1.515625,
      "learning_rate": 0.0007199999999999999,
      "loss": 7.6052,
      "step": 360
    },
    {
      "epoch": 0.04773425750343294,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00073,
      "loss": 7.5601,
      "step": 365
    },
    {
      "epoch": 0.048388151441836134,
      "grad_norm": 1.5625,
      "learning_rate": 0.00074,
      "loss": 7.544,
      "step": 370
    },
    {
      "epoch": 0.049042045380239326,
      "grad_norm": 1.65625,
      "learning_rate": 0.00075,
      "loss": 7.6637,
      "step": 375
    },
    {
      "epoch": 0.04969593931864252,
      "grad_norm": 1.59375,
      "learning_rate": 0.00076,
      "loss": 7.5337,
      "step": 380
    },
    {
      "epoch": 0.05034983325704571,
      "grad_norm": 1.4921875,
      "learning_rate": 0.0007700000000000001,
      "loss": 7.5765,
      "step": 385
    },
    {
      "epoch": 0.0510037271954489,
      "grad_norm": 1.5234375,
      "learning_rate": 0.0007800000000000001,
      "loss": 7.5058,
      "step": 390
    },
    {
      "epoch": 0.05165762113385209,
      "grad_norm": 1.546875,
      "learning_rate": 0.00079,
      "loss": 7.4771,
      "step": 395
    },
    {
      "epoch": 0.05231151507225528,
      "grad_norm": 1.5625,
      "learning_rate": 0.0008,
      "loss": 7.5002,
      "step": 400
    },
    {
      "epoch": 0.05296540901065847,
      "grad_norm": 1.4609375,
      "learning_rate": 0.0008100000000000001,
      "loss": 7.4754,
      "step": 405
    },
    {
      "epoch": 0.05361930294906166,
      "grad_norm": 1.46875,
      "learning_rate": 0.00082,
      "loss": 7.4979,
      "step": 410
    },
    {
      "epoch": 0.054273196887464854,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00083,
      "loss": 7.4688,
      "step": 415
    },
    {
      "epoch": 0.054927090825868045,
      "grad_norm": 1.6640625,
      "learning_rate": 0.00084,
      "loss": 7.4894,
      "step": 420
    },
    {
      "epoch": 0.055580984764271237,
      "grad_norm": 1.34375,
      "learning_rate": 0.00085,
      "loss": 7.4744,
      "step": 425
    },
    {
      "epoch": 0.05623487870267443,
      "grad_norm": 1.515625,
      "learning_rate": 0.00086,
      "loss": 7.4532,
      "step": 430
    },
    {
      "epoch": 0.05688877264107762,
      "grad_norm": 1.4921875,
      "learning_rate": 0.00087,
      "loss": 7.4408,
      "step": 435
    },
    {
      "epoch": 0.05754266657948081,
      "grad_norm": 1.5625,
      "learning_rate": 0.00088,
      "loss": 7.3857,
      "step": 440
    },
    {
      "epoch": 0.058196560517884,
      "grad_norm": 1.6171875,
      "learning_rate": 0.0008900000000000001,
      "loss": 7.3989,
      "step": 445
    },
    {
      "epoch": 0.05885045445628719,
      "grad_norm": 1.390625,
      "learning_rate": 0.0009000000000000001,
      "loss": 7.4182,
      "step": 450
    },
    {
      "epoch": 0.05950434839469038,
      "grad_norm": 1.6328125,
      "learning_rate": 0.00091,
      "loss": 7.4086,
      "step": 455
    },
    {
      "epoch": 0.060158242333093574,
      "grad_norm": 1.53125,
      "learning_rate": 0.00092,
      "loss": 7.5019,
      "step": 460
    },
    {
      "epoch": 0.060812136271496765,
      "grad_norm": 1.7109375,
      "learning_rate": 0.00093,
      "loss": 7.3263,
      "step": 465
    },
    {
      "epoch": 0.061466030209899956,
      "grad_norm": 1.359375,
      "learning_rate": 0.00094,
      "loss": 7.3745,
      "step": 470
    },
    {
      "epoch": 0.06211992414830315,
      "grad_norm": 1.390625,
      "learning_rate": 0.00095,
      "loss": 7.4221,
      "step": 475
    },
    {
      "epoch": 0.06277381808670633,
      "grad_norm": 1.375,
      "learning_rate": 0.00096,
      "loss": 7.4204,
      "step": 480
    },
    {
      "epoch": 0.06342771202510952,
      "grad_norm": 1.671875,
      "learning_rate": 0.0009699999999999999,
      "loss": 7.3489,
      "step": 485
    },
    {
      "epoch": 0.06408160596351271,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00098,
      "loss": 7.3887,
      "step": 490
    },
    {
      "epoch": 0.0647354999019159,
      "grad_norm": 1.6328125,
      "learning_rate": 0.00099,
      "loss": 7.3143,
      "step": 495
    },
    {
      "epoch": 0.0653893938403191,
      "grad_norm": 1.515625,
      "learning_rate": 0.001,
      "loss": 7.271,
      "step": 500
    },
    {
      "epoch": 0.06604328777872229,
      "grad_norm": 1.4375,
      "learning_rate": 0.0009999954680464025,
      "loss": 7.3593,
      "step": 505
    },
    {
      "epoch": 0.06669718171712548,
      "grad_norm": 1.5,
      "learning_rate": 0.000999981872276892,
      "loss": 7.3076,
      "step": 510
    },
    {
      "epoch": 0.06735107565552867,
      "grad_norm": 1.4296875,
      "learning_rate": 0.0009999592129653152,
      "loss": 7.313,
      "step": 515
    },
    {
      "epoch": 0.06800496959393186,
      "grad_norm": 1.4375,
      "learning_rate": 0.0009999274905680762,
      "loss": 7.31,
      "step": 520
    },
    {
      "epoch": 0.06865886353233505,
      "grad_norm": 1.609375,
      "learning_rate": 0.000999886705724128,
      "loss": 7.2787,
      "step": 525
    },
    {
      "epoch": 0.06931275747073824,
      "grad_norm": 1.625,
      "learning_rate": 0.0009998368592549595,
      "loss": 7.2677,
      "step": 530
    },
    {
      "epoch": 0.06996665140914143,
      "grad_norm": 1.3828125,
      "learning_rate": 0.0009997779521645793,
      "loss": 7.2741,
      "step": 535
    },
    {
      "epoch": 0.07062054534754462,
      "grad_norm": 1.609375,
      "learning_rate": 0.0009997099856394946,
      "loss": 7.2711,
      "step": 540
    },
    {
      "epoch": 0.07127443928594782,
      "grad_norm": 1.7109375,
      "learning_rate": 0.0009996329610486886,
      "loss": 7.2754,
      "step": 545
    },
    {
      "epoch": 0.07192833322435101,
      "grad_norm": 1.40625,
      "learning_rate": 0.0009995468799435915,
      "loss": 7.2382,
      "step": 550
    },
    {
      "epoch": 0.0725822271627542,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0009994517440580508,
      "loss": 7.1999,
      "step": 555
    },
    {
      "epoch": 0.07323612110115739,
      "grad_norm": 1.3828125,
      "learning_rate": 0.0009993475553082944,
      "loss": 7.2034,
      "step": 560
    },
    {
      "epoch": 0.07389001503956058,
      "grad_norm": 1.484375,
      "learning_rate": 0.0009992343157928943,
      "loss": 7.2751,
      "step": 565
    },
    {
      "epoch": 0.07454390897796377,
      "grad_norm": 1.4140625,
      "learning_rate": 0.0009991120277927223,
      "loss": 7.2415,
      "step": 570
    },
    {
      "epoch": 0.07519780291636696,
      "grad_norm": 1.4140625,
      "learning_rate": 0.0009989806937709053,
      "loss": 7.2109,
      "step": 575
    },
    {
      "epoch": 0.07585169685477015,
      "grad_norm": 1.3125,
      "learning_rate": 0.0009988403163727754,
      "loss": 7.2565,
      "step": 580
    },
    {
      "epoch": 0.07650559079317334,
      "grad_norm": 1.390625,
      "learning_rate": 0.0009986908984258162,
      "loss": 7.1342,
      "step": 585
    },
    {
      "epoch": 0.07715948473157654,
      "grad_norm": 1.484375,
      "learning_rate": 0.0009985324429396065,
      "loss": 7.185,
      "step": 590
    },
    {
      "epoch": 0.07781337866997973,
      "grad_norm": 1.3671875,
      "learning_rate": 0.0009983649531057593,
      "loss": 7.1715,
      "step": 595
    },
    {
      "epoch": 0.07846727260838292,
      "grad_norm": 1.3828125,
      "learning_rate": 0.0009981884322978576,
      "loss": 7.1502,
      "step": 600
    },
    {
      "epoch": 0.07912116654678611,
      "grad_norm": 1.40625,
      "learning_rate": 0.000998002884071386,
      "loss": 7.1753,
      "step": 605
    },
    {
      "epoch": 0.0797750604851893,
      "grad_norm": 1.4609375,
      "learning_rate": 0.0009978083121636601,
      "loss": 7.1488,
      "step": 610
    },
    {
      "epoch": 0.08042895442359249,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0009976047204937502,
      "loss": 7.0875,
      "step": 615
    },
    {
      "epoch": 0.08108284836199568,
      "grad_norm": 1.375,
      "learning_rate": 0.0009973921131624032,
      "loss": 7.1062,
      "step": 620
    },
    {
      "epoch": 0.08173674230039887,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0009971704944519593,
      "loss": 7.1608,
      "step": 625
    },
    {
      "epoch": 0.08239063623880206,
      "grad_norm": 1.265625,
      "learning_rate": 0.0009969398688262658,
      "loss": 7.0695,
      "step": 630
    },
    {
      "epoch": 0.08304453017720526,
      "grad_norm": 1.4453125,
      "learning_rate": 0.000996700240930588,
      "loss": 7.1272,
      "step": 635
    },
    {
      "epoch": 0.08369842411560845,
      "grad_norm": 1.3125,
      "learning_rate": 0.000996451615591515,
      "loss": 7.165,
      "step": 640
    },
    {
      "epoch": 0.08435231805401164,
      "grad_norm": 1.3515625,
      "learning_rate": 0.000996193997816862,
      "loss": 7.0286,
      "step": 645
    },
    {
      "epoch": 0.08500621199241483,
      "grad_norm": 1.4140625,
      "learning_rate": 0.0009959273927955706,
      "loss": 7.1258,
      "step": 650
    },
    {
      "epoch": 0.08566010593081802,
      "grad_norm": 1.4375,
      "learning_rate": 0.0009956518058976034,
      "loss": 7.1288,
      "step": 655
    },
    {
      "epoch": 0.08631399986922121,
      "grad_norm": 1.390625,
      "learning_rate": 0.0009953672426738357,
      "loss": 7.0871,
      "step": 660
    },
    {
      "epoch": 0.0869678938076244,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000995073708855945,
      "loss": 7.1641,
      "step": 665
    },
    {
      "epoch": 0.0876217877460276,
      "grad_norm": 1.28125,
      "learning_rate": 0.000994771210356294,
      "loss": 7.0944,
      "step": 670
    },
    {
      "epoch": 0.08827568168443078,
      "grad_norm": 1.3671875,
      "learning_rate": 0.0009944597532678121,
      "loss": 7.1015,
      "step": 675
    },
    {
      "epoch": 0.08892957562283398,
      "grad_norm": 1.40625,
      "learning_rate": 0.0009941393438638731,
      "loss": 7.0149,
      "step": 680
    },
    {
      "epoch": 0.08958346956123717,
      "grad_norm": 1.359375,
      "learning_rate": 0.0009938099885981684,
      "loss": 7.0454,
      "step": 685
    },
    {
      "epoch": 0.09023736349964036,
      "grad_norm": 1.2421875,
      "learning_rate": 0.000993471694104577,
      "loss": 7.0213,
      "step": 690
    },
    {
      "epoch": 0.09089125743804355,
      "grad_norm": 1.3125,
      "learning_rate": 0.0009931244671970319,
      "loss": 6.9903,
      "step": 695
    },
    {
      "epoch": 0.09154515137644674,
      "grad_norm": 1.3046875,
      "learning_rate": 0.0009927683148693834,
      "loss": 7.0954,
      "step": 700
    },
    {
      "epoch": 0.09219904531484993,
      "grad_norm": 1.4296875,
      "learning_rate": 0.0009924032442952568,
      "loss": 6.9755,
      "step": 705
    },
    {
      "epoch": 0.09285293925325312,
      "grad_norm": 1.40625,
      "learning_rate": 0.00099202926282791,
      "loss": 6.9701,
      "step": 710
    },
    {
      "epoch": 0.09350683319165631,
      "grad_norm": 1.3125,
      "learning_rate": 0.0009916463780000832,
      "loss": 6.9305,
      "step": 715
    },
    {
      "epoch": 0.0941607271300595,
      "grad_norm": 1.2578125,
      "learning_rate": 0.000991254597523849,
      "loss": 6.9923,
      "step": 720
    },
    {
      "epoch": 0.0948146210684627,
      "grad_norm": 1.3046875,
      "learning_rate": 0.000990853929290456,
      "loss": 6.9572,
      "step": 725
    },
    {
      "epoch": 0.09546851500686589,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0009904443813701703,
      "loss": 6.9629,
      "step": 730
    },
    {
      "epoch": 0.09612240894526908,
      "grad_norm": 1.3125,
      "learning_rate": 0.0009900259620121122,
      "loss": 6.9625,
      "step": 735
    },
    {
      "epoch": 0.09677630288367227,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0009895986796440914,
      "loss": 7.01,
      "step": 740
    },
    {
      "epoch": 0.09743019682207546,
      "grad_norm": 1.4296875,
      "learning_rate": 0.0009891625428724363,
      "loss": 6.9931,
      "step": 745
    },
    {
      "epoch": 0.09808409076047865,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0009887175604818205,
      "loss": 6.8903,
      "step": 750
    },
    {
      "epoch": 0.09873798469888184,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0009882637414350868,
      "loss": 6.932,
      "step": 755
    },
    {
      "epoch": 0.09939187863728503,
      "grad_norm": 1.375,
      "learning_rate": 0.0009878010948730653,
      "loss": 6.9914,
      "step": 760
    },
    {
      "epoch": 0.10004577257568822,
      "grad_norm": 1.296875,
      "learning_rate": 0.0009873296301143905,
      "loss": 7.0011,
      "step": 765
    },
    {
      "epoch": 0.10069966651409142,
      "grad_norm": 1.265625,
      "learning_rate": 0.000986849356655313,
      "loss": 6.9424,
      "step": 770
    },
    {
      "epoch": 0.1013535604524946,
      "grad_norm": 1.3125,
      "learning_rate": 0.000986360284169509,
      "loss": 6.9339,
      "step": 775
    },
    {
      "epoch": 0.1020074543908978,
      "grad_norm": 1.3984375,
      "learning_rate": 0.000985862422507884,
      "loss": 6.8763,
      "step": 780
    },
    {
      "epoch": 0.10266134832930099,
      "grad_norm": 1.234375,
      "learning_rate": 0.0009853557816983756,
      "loss": 6.9077,
      "step": 785
    },
    {
      "epoch": 0.10331524226770418,
      "grad_norm": 1.296875,
      "learning_rate": 0.0009848403719457507,
      "loss": 6.8373,
      "step": 790
    },
    {
      "epoch": 0.10396913620610737,
      "grad_norm": 1.296875,
      "learning_rate": 0.0009843162036314015,
      "loss": 6.9411,
      "step": 795
    },
    {
      "epoch": 0.10462303014451056,
      "grad_norm": 1.2421875,
      "learning_rate": 0.000983783287313134,
      "loss": 6.9162,
      "step": 800
    },
    {
      "epoch": 0.10527692408291375,
      "grad_norm": 1.5703125,
      "learning_rate": 0.0009832416337249574,
      "loss": 6.8853,
      "step": 805
    },
    {
      "epoch": 0.10593081802131694,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000982691253776867,
      "loss": 6.8588,
      "step": 810
    },
    {
      "epoch": 0.10658471195972014,
      "grad_norm": 4.4375,
      "learning_rate": 0.0009821321585546244,
      "loss": 6.8837,
      "step": 815
    },
    {
      "epoch": 0.10723860589812333,
      "grad_norm": 1.28125,
      "learning_rate": 0.0009815643593195345,
      "loss": 6.8783,
      "step": 820
    },
    {
      "epoch": 0.10789249983652652,
      "grad_norm": 1.390625,
      "learning_rate": 0.0009809878675082187,
      "loss": 6.8979,
      "step": 825
    },
    {
      "epoch": 0.10854639377492971,
      "grad_norm": 1.859375,
      "learning_rate": 0.0009804026947323843,
      "loss": 6.9705,
      "step": 830
    },
    {
      "epoch": 0.1092002877133329,
      "grad_norm": 1.2890625,
      "learning_rate": 0.0009798088527785903,
      "loss": 6.8603,
      "step": 835
    },
    {
      "epoch": 0.10985418165173609,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0009792063536080114,
      "loss": 6.8919,
      "step": 840
    },
    {
      "epoch": 0.11050807559013928,
      "grad_norm": 1.2109375,
      "learning_rate": 0.0009785952093561952,
      "loss": 6.8132,
      "step": 845
    },
    {
      "epoch": 0.11116196952854247,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0009779754323328191,
      "loss": 6.8783,
      "step": 850
    },
    {
      "epoch": 0.11181586346694566,
      "grad_norm": 1.25,
      "learning_rate": 0.0009773470350214418,
      "loss": 6.8379,
      "step": 855
    },
    {
      "epoch": 0.11246975740534886,
      "grad_norm": 1.234375,
      "learning_rate": 0.0009767100300792518,
      "loss": 6.8265,
      "step": 860
    },
    {
      "epoch": 0.11312365134375205,
      "grad_norm": 1.453125,
      "learning_rate": 0.0009760644303368132,
      "loss": 6.913,
      "step": 865
    },
    {
      "epoch": 0.11377754528215524,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0009754102487978059,
      "loss": 6.8268,
      "step": 870
    },
    {
      "epoch": 0.11443143922055843,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0009747474986387655,
      "loss": 6.802,
      "step": 875
    },
    {
      "epoch": 0.11508533315896162,
      "grad_norm": 1.296875,
      "learning_rate": 0.0009740761932088156,
      "loss": 6.7553,
      "step": 880
    },
    {
      "epoch": 0.11573922709736481,
      "grad_norm": 1.3671875,
      "learning_rate": 0.0009733963460294015,
      "loss": 6.8835,
      "step": 885
    },
    {
      "epoch": 0.116393121035768,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0009727079707940157,
      "loss": 6.7702,
      "step": 890
    },
    {
      "epoch": 0.11704701497417119,
      "grad_norm": 1.234375,
      "learning_rate": 0.0009720110813679232,
      "loss": 6.7631,
      "step": 895
    },
    {
      "epoch": 0.11770090891257438,
      "grad_norm": 1.4375,
      "learning_rate": 0.0009713056917878818,
      "loss": 6.7896,
      "step": 900
    },
    {
      "epoch": 0.11835480285097758,
      "grad_norm": 1.2890625,
      "learning_rate": 0.0009705918162618599,
      "loss": 6.8376,
      "step": 905
    },
    {
      "epoch": 0.11900869678938077,
      "grad_norm": 1.21875,
      "learning_rate": 0.00096986946916875,
      "loss": 6.8153,
      "step": 910
    },
    {
      "epoch": 0.11966259072778396,
      "grad_norm": 1.328125,
      "learning_rate": 0.0009691386650580782,
      "loss": 6.7687,
      "step": 915
    },
    {
      "epoch": 0.12031648466618715,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0009683994186497132,
      "loss": 6.7558,
      "step": 920
    },
    {
      "epoch": 0.12097037860459034,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0009676517448335676,
      "loss": 6.8054,
      "step": 925
    },
    {
      "epoch": 0.12162427254299353,
      "grad_norm": 1.3671875,
      "learning_rate": 0.0009668956586692994,
      "loss": 6.7817,
      "step": 930
    },
    {
      "epoch": 0.12227816648139672,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0009661311753860083,
      "loss": 6.7898,
      "step": 935
    },
    {
      "epoch": 0.12293206041979991,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0009653583103819289,
      "loss": 6.8257,
      "step": 940
    },
    {
      "epoch": 0.1235859543582031,
      "grad_norm": 1.3828125,
      "learning_rate": 0.0009645770792241201,
      "loss": 6.722,
      "step": 945
    },
    {
      "epoch": 0.1242398482966063,
      "grad_norm": 1.46875,
      "learning_rate": 0.0009637874976481528,
      "loss": 6.7903,
      "step": 950
    },
    {
      "epoch": 0.12489374223500949,
      "grad_norm": 1.234375,
      "learning_rate": 0.0009629895815577914,
      "loss": 6.8768,
      "step": 955
    },
    {
      "epoch": 0.12554763617341266,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0009621833470246749,
      "loss": 6.7096,
      "step": 960
    },
    {
      "epoch": 0.12620153011181587,
      "grad_norm": 1.328125,
      "learning_rate": 0.000961368810287992,
      "loss": 6.7841,
      "step": 965
    },
    {
      "epoch": 0.12685542405021905,
      "grad_norm": 1.375,
      "learning_rate": 0.0009605459877541544,
      "loss": 6.7317,
      "step": 970
    },
    {
      "epoch": 0.12750931798862225,
      "grad_norm": 1.25,
      "learning_rate": 0.0009597148959964672,
      "loss": 6.7939,
      "step": 975
    },
    {
      "epoch": 0.12816321192702543,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0009588755517547935,
      "loss": 6.7337,
      "step": 980
    },
    {
      "epoch": 0.12881710586542863,
      "grad_norm": 1.390625,
      "learning_rate": 0.0009580279719352186,
      "loss": 6.74,
      "step": 985
    },
    {
      "epoch": 0.1294709998038318,
      "grad_norm": 1.203125,
      "learning_rate": 0.0009571721736097089,
      "loss": 6.7336,
      "step": 990
    },
    {
      "epoch": 0.13012489374223501,
      "grad_norm": 1.234375,
      "learning_rate": 0.0009563081740157675,
      "loss": 6.6854,
      "step": 995
    },
    {
      "epoch": 0.1307787876806382,
      "grad_norm": 1.3046875,
      "learning_rate": 0.0009554359905560886,
      "loss": 6.7032,
      "step": 1000
    }
  ],
  "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": 1312421534760960.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}