{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009009009009009009,
      "grad_norm": 608.0,
      "learning_rate": 1.801801801801802e-06,
      "loss": 58.5641,
      "step": 1
    },
    {
      "epoch": 0.04504504504504504,
      "grad_norm": 532.0,
      "learning_rate": 9.00900900900901e-06,
      "loss": 54.6181,
      "step": 5
    },
    {
      "epoch": 0.09009009009009009,
      "grad_norm": 446.0,
      "learning_rate": 1.801801801801802e-05,
      "loss": 50.0236,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 193.0,
      "learning_rate": 2.702702702702703e-05,
      "loss": 33.1549,
      "step": 15
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 44.5,
      "learning_rate": 3.603603603603604e-05,
      "loss": 25.2428,
      "step": 20
    },
    {
      "epoch": 0.22522522522522523,
      "grad_norm": 26.625,
      "learning_rate": 4.5045045045045046e-05,
      "loss": 22.4735,
      "step": 25
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 17.25,
      "learning_rate": 5.405405405405406e-05,
      "loss": 20.4661,
      "step": 30
    },
    {
      "epoch": 0.3153153153153153,
      "grad_norm": 7.6875,
      "learning_rate": 6.306306306306306e-05,
      "loss": 19.1401,
      "step": 35
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 11.6875,
      "learning_rate": 7.207207207207208e-05,
      "loss": 18.3188,
      "step": 40
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 23.5,
      "learning_rate": 8.108108108108109e-05,
      "loss": 16.7622,
      "step": 45
    },
    {
      "epoch": 0.45045045045045046,
      "grad_norm": 56.25,
      "learning_rate": 9.009009009009009e-05,
      "loss": 12.6183,
      "step": 50
    },
    {
      "epoch": 0.4954954954954955,
      "grad_norm": 13.0,
      "learning_rate": 9.90990990990991e-05,
      "loss": 4.3593,
      "step": 55
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 3.875,
      "learning_rate": 0.00010810810810810812,
      "loss": 2.18,
      "step": 60
    },
    {
      "epoch": 0.5855855855855856,
      "grad_norm": 2.421875,
      "learning_rate": 0.00011711711711711712,
      "loss": 1.8179,
      "step": 65
    },
    {
      "epoch": 0.6306306306306306,
      "grad_norm": 3.265625,
      "learning_rate": 0.00012612612612612612,
      "loss": 1.5974,
      "step": 70
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 2.375,
      "learning_rate": 0.00013513513513513514,
      "loss": 1.486,
      "step": 75
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00014414414414414415,
      "loss": 1.361,
      "step": 80
    },
    {
      "epoch": 0.7657657657657657,
      "grad_norm": 3.890625,
      "learning_rate": 0.00015315315315315314,
      "loss": 1.3001,
      "step": 85
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 4.46875,
      "learning_rate": 0.00016216216216216218,
      "loss": 1.261,
      "step": 90
    },
    {
      "epoch": 0.8558558558558559,
      "grad_norm": 5.03125,
      "learning_rate": 0.0001711711711711712,
      "loss": 1.2015,
      "step": 95
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 32.25,
      "learning_rate": 0.00018018018018018018,
      "loss": 1.1886,
      "step": 100
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 1.703125,
      "learning_rate": 0.0001891891891891892,
      "loss": 1.1679,
      "step": 105
    },
    {
      "epoch": 0.990990990990991,
      "grad_norm": 2.984375,
      "learning_rate": 0.0001981981981981982,
      "loss": 1.1572,
      "step": 110
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.307225465774536,
      "eval_runtime": 1.0056,
      "eval_samples_per_second": 4.972,
      "eval_steps_per_second": 1.989,
      "step": 111
    },
    {
      "epoch": 1.0360360360360361,
      "grad_norm": 1.546875,
      "learning_rate": 0.00019999208860571255,
      "loss": 1.0473,
      "step": 115
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 1.546875,
      "learning_rate": 0.0001999599507118322,
      "loss": 1.0618,
      "step": 120
    },
    {
      "epoch": 1.1261261261261262,
      "grad_norm": 10.0,
      "learning_rate": 0.00019990309979553045,
      "loss": 1.0458,
      "step": 125
    },
    {
      "epoch": 1.1711711711711712,
      "grad_norm": 8.4375,
      "learning_rate": 0.00019982154991201608,
      "loss": 1.0364,
      "step": 130
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 2.0,
      "learning_rate": 0.00019971532122280464,
      "loss": 1.0457,
      "step": 135
    },
    {
      "epoch": 1.2612612612612613,
      "grad_norm": 1.4453125,
      "learning_rate": 0.00019958443999073397,
      "loss": 0.9906,
      "step": 140
    },
    {
      "epoch": 1.3063063063063063,
      "grad_norm": 18.25,
      "learning_rate": 0.00019942893857347128,
      "loss": 0.9911,
      "step": 145
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 2.578125,
      "learning_rate": 0.0001992488554155135,
      "loss": 0.9996,
      "step": 150
    },
    {
      "epoch": 1.3963963963963963,
      "grad_norm": 1.7734375,
      "learning_rate": 0.00019904423503868247,
      "loss": 0.9656,
      "step": 155
    },
    {
      "epoch": 1.4414414414414414,
      "grad_norm": 5.65625,
      "learning_rate": 0.00019881512803111796,
      "loss": 0.9753,
      "step": 160
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 3.78125,
      "learning_rate": 0.00019856159103477086,
      "loss": 0.9239,
      "step": 165
    },
    {
      "epoch": 1.5315315315315314,
      "grad_norm": 0.86328125,
      "learning_rate": 0.00019828368673139947,
      "loss": 0.9428,
      "step": 170
    },
    {
      "epoch": 1.5765765765765765,
      "grad_norm": 0.7265625,
      "learning_rate": 0.00019798148382707296,
      "loss": 0.9455,
      "step": 175
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 1.8125,
      "learning_rate": 0.00019765505703518496,
      "loss": 0.9373,
      "step": 180
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00019730448705798239,
      "loss": 0.9659,
      "step": 185
    },
    {
      "epoch": 1.7117117117117115,
      "grad_norm": 3.859375,
      "learning_rate": 0.00019692986056661356,
      "loss": 0.9271,
      "step": 190
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 3.34375,
      "learning_rate": 0.00019653127017970034,
      "loss": 0.9303,
      "step": 195
    },
    {
      "epoch": 1.8018018018018018,
      "grad_norm": 0.91796875,
      "learning_rate": 0.0001961088144404403,
      "loss": 0.9333,
      "step": 200
    },
    {
      "epoch": 1.8468468468468469,
      "grad_norm": 1.4453125,
      "learning_rate": 0.00019566259779224378,
      "loss": 0.8923,
      "step": 205
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 3.171875,
      "learning_rate": 0.00019519273055291266,
      "loss": 0.9,
      "step": 210
    },
    {
      "epoch": 1.936936936936937,
      "grad_norm": 14.3125,
      "learning_rate": 0.00019469932888736632,
      "loss": 0.8988,
      "step": 215
    },
    {
      "epoch": 1.981981981981982,
      "grad_norm": 3.46875,
      "learning_rate": 0.0001941825147789225,
      "loss": 0.9296,
      "step": 220
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.178852081298828,
      "eval_runtime": 1.0053,
      "eval_samples_per_second": 4.973,
      "eval_steps_per_second": 1.989,
      "step": 222
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 1.4921875,
      "learning_rate": 0.00019364241599913924,
      "loss": 0.8696,
      "step": 225
    },
    {
      "epoch": 2.0720720720720722,
      "grad_norm": 2.65625,
      "learning_rate": 0.0001930791660762262,
      "loss": 0.8363,
      "step": 230
    },
    {
      "epoch": 2.1171171171171173,
      "grad_norm": 1.265625,
      "learning_rate": 0.00019249290426203252,
      "loss": 0.821,
      "step": 235
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 2.546875,
      "learning_rate": 0.00019188377549761963,
      "loss": 0.8511,
      "step": 240
    },
    {
      "epoch": 2.2072072072072073,
      "grad_norm": 0.828125,
      "learning_rate": 0.0001912519303774276,
      "loss": 0.8231,
      "step": 245
    },
    {
      "epoch": 2.2522522522522523,
      "grad_norm": 0.73046875,
      "learning_rate": 0.000190597525112044,
      "loss": 0.8496,
      "step": 250
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00018992072148958368,
      "loss": 0.852,
      "step": 255
    },
    {
      "epoch": 2.3423423423423424,
      "grad_norm": 1.578125,
      "learning_rate": 0.0001892216868356904,
      "loss": 0.8131,
      "step": 260
    },
    {
      "epoch": 2.3873873873873874,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00018850059397216876,
      "loss": 0.8483,
      "step": 265
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 1.125,
      "learning_rate": 0.00018775762117425777,
      "loss": 0.8432,
      "step": 270
    },
    {
      "epoch": 2.4774774774774775,
      "grad_norm": 0.6015625,
      "learning_rate": 0.00018699295212655596,
      "loss": 0.8493,
      "step": 275
    },
    {
      "epoch": 2.5225225225225225,
      "grad_norm": 0.8828125,
      "learning_rate": 0.00018620677587760916,
      "loss": 0.7998,
      "step": 280
    },
    {
      "epoch": 2.5675675675675675,
      "grad_norm": 0.73046875,
      "learning_rate": 0.0001853992867931721,
      "loss": 0.8256,
      "step": 285
    },
    {
      "epoch": 2.6126126126126126,
      "grad_norm": 0.6796875,
      "learning_rate": 0.00018457068450815562,
      "loss": 0.8162,
      "step": 290
    },
    {
      "epoch": 2.6576576576576576,
      "grad_norm": 0.671875,
      "learning_rate": 0.0001837211738772711,
      "loss": 0.8338,
      "step": 295
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00018285096492438424,
      "loss": 0.8279,
      "step": 300
    },
    {
      "epoch": 2.7477477477477477,
      "grad_norm": 0.60546875,
      "learning_rate": 0.00018196027279059117,
      "loss": 0.7962,
      "step": 305
    },
    {
      "epoch": 2.7927927927927927,
      "grad_norm": 2.78125,
      "learning_rate": 0.0001810493176810292,
      "loss": 0.8192,
      "step": 310
    },
    {
      "epoch": 2.8378378378378377,
      "grad_norm": 0.63671875,
      "learning_rate": 0.00018011832481043576,
      "loss": 0.8147,
      "step": 315
    },
    {
      "epoch": 2.8828828828828827,
      "grad_norm": 0.56640625,
      "learning_rate": 0.00017916752434746856,
      "loss": 0.8255,
      "step": 320
    },
    {
      "epoch": 2.9279279279279278,
      "grad_norm": 1.8046875,
      "learning_rate": 0.0001781971513578013,
      "loss": 0.8059,
      "step": 325
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00017720744574600863,
      "loss": 0.8273,
      "step": 330
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.1709225177764893,
      "eval_runtime": 1.0054,
      "eval_samples_per_second": 4.973,
      "eval_steps_per_second": 1.989,
      "step": 333
    },
    {
      "epoch": 3.018018018018018,
      "grad_norm": 0.83984375,
      "learning_rate": 0.00017619865219625452,
      "loss": 0.7934,
      "step": 335
    },
    {
      "epoch": 3.063063063063063,
      "grad_norm": 1.5859375,
      "learning_rate": 0.00017517102011179933,
      "loss": 0.7096,
      "step": 340
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 0.91796875,
      "learning_rate": 0.00017412480355334005,
      "loss": 0.7203,
      "step": 345
    },
    {
      "epoch": 3.153153153153153,
      "grad_norm": 1.9296875,
      "learning_rate": 0.00017306026117619889,
      "loss": 0.7237,
      "step": 350
    },
    {
      "epoch": 3.1981981981981984,
      "grad_norm": 1.6328125,
      "learning_rate": 0.00017197765616637636,
      "loss": 0.738,
      "step": 355
    },
    {
      "epoch": 3.2432432432432434,
      "grad_norm": 2.0625,
      "learning_rate": 0.00017087725617548385,
      "loss": 0.7214,
      "step": 360
    },
    {
      "epoch": 3.2882882882882885,
      "grad_norm": 3.53125,
      "learning_rate": 0.0001697593332545723,
      "loss": 0.7549,
      "step": 365
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 4.25,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.7575,
      "step": 370
    },
    {
      "epoch": 3.3783783783783785,
      "grad_norm": 1.6484375,
      "learning_rate": 0.00016747202841946928,
      "loss": 0.7392,
      "step": 375
    },
    {
      "epoch": 3.4234234234234235,
      "grad_norm": 1.6171875,
      "learning_rate": 0.00016630321199390867,
      "loss": 0.7251,
      "step": 380
    },
    {
      "epoch": 3.4684684684684686,
      "grad_norm": 1.5546875,
      "learning_rate": 0.0001651180034757856,
      "loss": 0.7285,
      "step": 385
    },
    {
      "epoch": 3.5135135135135136,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0001639166958832985,
      "loss": 0.7114,
      "step": 390
    },
    {
      "epoch": 3.5585585585585586,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00016269958621480788,
      "loss": 0.7223,
      "step": 395
    },
    {
      "epoch": 3.6036036036036037,
      "grad_norm": 0.61328125,
      "learning_rate": 0.00016146697537540924,
      "loss": 0.7273,
      "step": 400
    },
    {
      "epoch": 3.6486486486486487,
      "grad_norm": 0.67578125,
      "learning_rate": 0.00016021916810254097,
      "loss": 0.7328,
      "step": 405
    },
    {
      "epoch": 3.6936936936936937,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00015895647289064396,
      "loss": 0.7409,
      "step": 410
    },
    {
      "epoch": 3.7387387387387387,
      "grad_norm": 0.7578125,
      "learning_rate": 0.000157679201914893,
      "loss": 0.7247,
      "step": 415
    },
    {
      "epoch": 3.7837837837837838,
      "grad_norm": 1.890625,
      "learning_rate": 0.0001563876709540178,
      "loss": 0.7446,
      "step": 420
    },
    {
      "epoch": 3.828828828828829,
      "grad_norm": 0.7109375,
      "learning_rate": 0.0001550821993122334,
      "loss": 0.7421,
      "step": 425
    },
    {
      "epoch": 3.873873873873874,
      "grad_norm": 0.73046875,
      "learning_rate": 0.00015376310974029873,
      "loss": 0.7362,
      "step": 430
    },
    {
      "epoch": 3.918918918918919,
      "grad_norm": 0.66015625,
      "learning_rate": 0.00015243072835572318,
      "loss": 0.7398,
      "step": 435
    },
    {
      "epoch": 3.963963963963964,
      "grad_norm": 0.69921875,
      "learning_rate": 0.0001510853845621409,
      "loss": 0.7586,
      "step": 440
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.2163968086242676,
      "eval_runtime": 1.0061,
      "eval_samples_per_second": 4.97,
      "eval_steps_per_second": 1.988,
      "step": 444
    },
    {
      "epoch": 4.009009009009009,
      "grad_norm": 0.58203125,
      "learning_rate": 0.00014972741096787242,
      "loss": 0.7128,
      "step": 445
    },
    {
      "epoch": 4.054054054054054,
      "grad_norm": 0.75,
      "learning_rate": 0.00014835714330369446,
      "loss": 0.6463,
      "step": 450
    },
    {
      "epoch": 4.099099099099099,
      "grad_norm": 0.83203125,
      "learning_rate": 0.00014697492033983707,
      "loss": 0.6453,
      "step": 455
    },
    {
      "epoch": 4.1441441441441444,
      "grad_norm": 0.55859375,
      "learning_rate": 0.00014558108380223012,
      "loss": 0.647,
      "step": 460
    },
    {
      "epoch": 4.1891891891891895,
      "grad_norm": 1.3125,
      "learning_rate": 0.00014417597828801832,
      "loss": 0.626,
      "step": 465
    },
    {
      "epoch": 4.2342342342342345,
      "grad_norm": 0.85546875,
      "learning_rate": 0.00014275995118036693,
      "loss": 0.6334,
      "step": 470
    },
    {
      "epoch": 4.2792792792792795,
      "grad_norm": 0.69921875,
      "learning_rate": 0.0001413333525625784,
      "loss": 0.6435,
      "step": 475
    },
    {
      "epoch": 4.324324324324325,
      "grad_norm": 0.8046875,
      "learning_rate": 0.00013989653513154165,
      "loss": 0.6439,
      "step": 480
    },
    {
      "epoch": 4.36936936936937,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00013844985411053492,
      "loss": 0.6559,
      "step": 485
    },
    {
      "epoch": 4.414414414414415,
      "grad_norm": 1.3359375,
      "learning_rate": 0.00013699366716140435,
      "loss": 0.6654,
      "step": 490
    },
    {
      "epoch": 4.45945945945946,
      "grad_norm": 0.80859375,
      "learning_rate": 0.00013552833429613938,
      "loss": 0.6783,
      "step": 495
    },
    {
      "epoch": 4.504504504504505,
      "grad_norm": 0.6875,
      "learning_rate": 0.00013405421778786737,
      "loss": 0.6543,
      "step": 500
    },
    {
      "epoch": 4.54954954954955,
      "grad_norm": 0.62890625,
      "learning_rate": 0.00013257168208128908,
      "loss": 0.6608,
      "step": 505
    },
    {
      "epoch": 4.594594594594595,
      "grad_norm": 0.60546875,
      "learning_rate": 0.00013108109370257712,
      "loss": 0.6621,
      "step": 510
    },
    {
      "epoch": 4.63963963963964,
      "grad_norm": 0.67578125,
      "learning_rate": 0.00012958282116876026,
      "loss": 0.656,
      "step": 515
    },
    {
      "epoch": 4.684684684684685,
      "grad_norm": 0.65234375,
      "learning_rate": 0.00012807723489661495,
      "loss": 0.6505,
      "step": 520
    },
    {
      "epoch": 4.72972972972973,
      "grad_norm": 0.921875,
      "learning_rate": 0.00012656470711108764,
      "loss": 0.6789,
      "step": 525
    },
    {
      "epoch": 4.774774774774775,
      "grad_norm": 0.61328125,
      "learning_rate": 0.00012504561175326985,
      "loss": 0.6588,
      "step": 530
    },
    {
      "epoch": 4.81981981981982,
      "grad_norm": 0.703125,
      "learning_rate": 0.00012352032438794902,
      "loss": 0.6534,
      "step": 535
    },
    {
      "epoch": 4.864864864864865,
      "grad_norm": 0.74609375,
      "learning_rate": 0.00012198922211075778,
      "loss": 0.6482,
      "step": 540
    },
    {
      "epoch": 4.90990990990991,
      "grad_norm": 0.94140625,
      "learning_rate": 0.00012045268345494511,
      "loss": 0.6595,
      "step": 545
    },
    {
      "epoch": 4.954954954954955,
      "grad_norm": 0.59765625,
      "learning_rate": 0.00011891108829779165,
      "loss": 0.6624,
      "step": 550
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.578125,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.6613,
      "step": 555
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.3182225227355957,
      "eval_runtime": 1.0028,
      "eval_samples_per_second": 4.986,
      "eval_steps_per_second": 1.994,
      "step": 555
    },
    {
      "epoch": 5.045045045045045,
      "grad_norm": 0.98046875,
      "learning_rate": 0.0001158142541449341,
      "loss": 0.5564,
      "step": 560
    },
    {
      "epoch": 5.09009009009009,
      "grad_norm": 0.69140625,
      "learning_rate": 0.00011425978077717709,
      "loss": 0.5273,
      "step": 565
    },
    {
      "epoch": 5.135135135135135,
      "grad_norm": 0.69921875,
      "learning_rate": 0.00011270178197468789,
      "loss": 0.5589,
      "step": 570
    },
    {
      "epoch": 5.18018018018018,
      "grad_norm": 0.6171875,
      "learning_rate": 0.00011114064292032282,
      "loss": 0.5593,
      "step": 575
    },
    {
      "epoch": 5.225225225225225,
      "grad_norm": 0.69921875,
      "learning_rate": 0.00010957674957330042,
      "loss": 0.5672,
      "step": 580
    },
    {
      "epoch": 5.27027027027027,
      "grad_norm": 0.69140625,
      "learning_rate": 0.00010801048857378071,
      "loss": 0.5444,
      "step": 585
    },
    {
      "epoch": 5.315315315315315,
      "grad_norm": 0.66796875,
      "learning_rate": 0.00010644224714727681,
      "loss": 0.5747,
      "step": 590
    },
    {
      "epoch": 5.36036036036036,
      "grad_norm": 0.68359375,
      "learning_rate": 0.0001048724130089212,
      "loss": 0.5609,
      "step": 595
    },
    {
      "epoch": 5.405405405405405,
      "grad_norm": 0.8984375,
      "learning_rate": 0.00010330137426761135,
      "loss": 0.5625,
      "step": 600
    },
    {
      "epoch": 5.45045045045045,
      "grad_norm": 0.76171875,
      "learning_rate": 0.00010172951933005775,
      "loss": 0.5671,
      "step": 605
    },
    {
      "epoch": 5.495495495495495,
      "grad_norm": 0.80859375,
      "learning_rate": 0.00010015723680475846,
      "loss": 0.564,
      "step": 610
    },
    {
      "epoch": 5.54054054054054,
      "grad_norm": 0.76171875,
      "learning_rate": 9.858491540592382e-05,
      "loss": 0.5784,
      "step": 615
    },
    {
      "epoch": 5.585585585585585,
      "grad_norm": 0.7265625,
      "learning_rate": 9.70129438573747e-05,
      "loss": 0.5672,
      "step": 620
    },
    {
      "epoch": 5.63063063063063,
      "grad_norm": 0.75390625,
      "learning_rate": 9.54417107964389e-05,
      "loss": 0.5592,
      "step": 625
    },
    {
      "epoch": 5.675675675675675,
      "grad_norm": 0.734375,
      "learning_rate": 9.38716046778684e-05,
      "loss": 0.5634,
      "step": 630
    },
    {
      "epoch": 5.7207207207207205,
      "grad_norm": 0.6640625,
      "learning_rate": 9.230301367780208e-05,
      "loss": 0.5691,
      "step": 635
    },
    {
      "epoch": 5.7657657657657655,
      "grad_norm": 0.6875,
      "learning_rate": 9.07363255977973e-05,
      "loss": 0.5722,
      "step": 640
    },
    {
      "epoch": 5.8108108108108105,
      "grad_norm": 0.76953125,
      "learning_rate": 8.917192776895382e-05,
      "loss": 0.5827,
      "step": 645
    },
    {
      "epoch": 5.8558558558558556,
      "grad_norm": 0.83203125,
      "learning_rate": 8.76102069561545e-05,
      "loss": 0.5745,
      "step": 650
    },
    {
      "epoch": 5.900900900900901,
      "grad_norm": 0.7265625,
      "learning_rate": 8.605154926244543e-05,
      "loss": 0.5614,
      "step": 655
    },
    {
      "epoch": 5.945945945945946,
      "grad_norm": 0.65625,
      "learning_rate": 8.449634003358022e-05,
      "loss": 0.5731,
      "step": 660
    },
    {
      "epoch": 5.990990990990991,
      "grad_norm": 0.8828125,
      "learning_rate": 8.294496376275104e-05,
      "loss": 0.577,
      "step": 665
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.4773526191711426,
      "eval_runtime": 1.0034,
      "eval_samples_per_second": 4.983,
      "eval_steps_per_second": 1.993,
      "step": 666
    },
    {
      "epoch": 6.036036036036036,
      "grad_norm": 0.8984375,
      "learning_rate": 8.13978039955308e-05,
      "loss": 0.5142,
      "step": 670
    },
    {
      "epoch": 6.081081081081081,
      "grad_norm": 0.8359375,
      "learning_rate": 7.985524323504948e-05,
      "loss": 0.4725,
      "step": 675
    },
    {
      "epoch": 6.126126126126126,
      "grad_norm": 0.7734375,
      "learning_rate": 7.831766284742807e-05,
      "loss": 0.4671,
      "step": 680
    },
    {
      "epoch": 6.171171171171171,
      "grad_norm": 0.7578125,
      "learning_rate": 7.678544296749384e-05,
      "loss": 0.4804,
      "step": 685
    },
    {
      "epoch": 6.216216216216216,
      "grad_norm": 0.82421875,
      "learning_rate": 7.525896240479976e-05,
      "loss": 0.4704,
      "step": 690
    },
    {
      "epoch": 6.261261261261261,
      "grad_norm": 0.75,
      "learning_rate": 7.37385985499718e-05,
      "loss": 0.4659,
      "step": 695
    },
    {
      "epoch": 6.306306306306306,
      "grad_norm": 0.71484375,
      "learning_rate": 7.222472728140695e-05,
      "loss": 0.4697,
      "step": 700
    },
    {
      "epoch": 6.351351351351352,
      "grad_norm": 0.79296875,
      "learning_rate": 7.071772287234497e-05,
      "loss": 0.4912,
      "step": 705
    },
    {
      "epoch": 6.396396396396397,
      "grad_norm": 0.76953125,
      "learning_rate": 6.921795789833723e-05,
      "loss": 0.4689,
      "step": 710
    },
    {
      "epoch": 6.441441441441442,
      "grad_norm": 0.66796875,
      "learning_rate": 6.772580314513508e-05,
      "loss": 0.4753,
      "step": 715
    },
    {
      "epoch": 6.486486486486487,
      "grad_norm": 0.75,
      "learning_rate": 6.624162751702076e-05,
      "loss": 0.4759,
      "step": 720
    },
    {
      "epoch": 6.531531531531532,
      "grad_norm": 0.70703125,
      "learning_rate": 6.476579794560356e-05,
      "loss": 0.489,
      "step": 725
    },
    {
      "epoch": 6.576576576576577,
      "grad_norm": 0.7265625,
      "learning_rate": 6.329867929910347e-05,
      "loss": 0.473,
      "step": 730
    },
    {
      "epoch": 6.621621621621622,
      "grad_norm": 0.7109375,
      "learning_rate": 6.184063429214515e-05,
      "loss": 0.4793,
      "step": 735
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.76171875,
      "learning_rate": 6.039202339608432e-05,
      "loss": 0.5071,
      "step": 740
    },
    {
      "epoch": 6.711711711711712,
      "grad_norm": 0.69921875,
      "learning_rate": 5.895320474988864e-05,
      "loss": 0.4741,
      "step": 745
    },
    {
      "epoch": 6.756756756756757,
      "grad_norm": 0.69921875,
      "learning_rate": 5.752453407159522e-05,
      "loss": 0.4799,
      "step": 750
    },
    {
      "epoch": 6.801801801801802,
      "grad_norm": 0.7578125,
      "learning_rate": 5.610636457036693e-05,
      "loss": 0.4901,
      "step": 755
    },
    {
      "epoch": 6.846846846846847,
      "grad_norm": 0.6953125,
      "learning_rate": 5.469904685916861e-05,
      "loss": 0.4858,
      "step": 760
    },
    {
      "epoch": 6.891891891891892,
      "grad_norm": 0.76953125,
      "learning_rate": 5.33029288680852e-05,
      "loss": 0.4895,
      "step": 765
    },
    {
      "epoch": 6.936936936936937,
      "grad_norm": 0.70703125,
      "learning_rate": 5.191835575830352e-05,
      "loss": 0.4935,
      "step": 770
    },
    {
      "epoch": 6.981981981981982,
      "grad_norm": 0.69921875,
      "learning_rate": 5.0545669836778144e-05,
      "loss": 0.4958,
      "step": 775
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.7035882472991943,
      "eval_runtime": 1.0058,
      "eval_samples_per_second": 4.971,
      "eval_steps_per_second": 1.988,
      "step": 777
    },
    {
      "epoch": 7.027027027027027,
      "grad_norm": 0.6875,
      "learning_rate": 4.918521047160308e-05,
      "loss": 0.4443,
      "step": 780
    },
    {
      "epoch": 7.072072072072072,
      "grad_norm": 0.7734375,
      "learning_rate": 4.783731400811022e-05,
      "loss": 0.4139,
      "step": 785
    },
    {
      "epoch": 7.117117117117117,
      "grad_norm": 0.734375,
      "learning_rate": 4.650231368571486e-05,
      "loss": 0.41,
      "step": 790
    },
    {
      "epoch": 7.162162162162162,
      "grad_norm": 0.90625,
      "learning_rate": 4.518053955552903e-05,
      "loss": 0.4291,
      "step": 795
    },
    {
      "epoch": 7.207207207207207,
      "grad_norm": 0.71875,
      "learning_rate": 4.387231839876349e-05,
      "loss": 0.4141,
      "step": 800
    },
    {
      "epoch": 7.252252252252252,
      "grad_norm": 0.7265625,
      "learning_rate": 4.2577973645937674e-05,
      "loss": 0.4139,
      "step": 805
    },
    {
      "epoch": 7.297297297297297,
      "grad_norm": 0.76171875,
      "learning_rate": 4.129782529691815e-05,
      "loss": 0.4278,
      "step": 810
    },
    {
      "epoch": 7.342342342342342,
      "grad_norm": 0.73046875,
      "learning_rate": 4.003218984180552e-05,
      "loss": 0.4148,
      "step": 815
    },
    {
      "epoch": 7.387387387387387,
      "grad_norm": 0.79296875,
      "learning_rate": 3.878138018268866e-05,
      "loss": 0.4168,
      "step": 820
    },
    {
      "epoch": 7.4324324324324325,
      "grad_norm": 0.82421875,
      "learning_rate": 3.7545705556286126e-05,
      "loss": 0.4182,
      "step": 825
    },
    {
      "epoch": 7.4774774774774775,
      "grad_norm": 0.70703125,
      "learning_rate": 3.632547145749395e-05,
      "loss": 0.4239,
      "step": 830
    },
    {
      "epoch": 7.5225225225225225,
      "grad_norm": 0.78515625,
      "learning_rate": 3.5120979563858266e-05,
      "loss": 0.4137,
      "step": 835
    },
    {
      "epoch": 7.5675675675675675,
      "grad_norm": 0.73828125,
      "learning_rate": 3.393252766099187e-05,
      "loss": 0.4111,
      "step": 840
    },
    {
      "epoch": 7.612612612612613,
      "grad_norm": 0.7421875,
      "learning_rate": 3.2760409568952766e-05,
      "loss": 0.4179,
      "step": 845
    },
    {
      "epoch": 7.657657657657658,
      "grad_norm": 0.76171875,
      "learning_rate": 3.1604915069603436e-05,
      "loss": 0.429,
      "step": 850
    },
    {
      "epoch": 7.702702702702703,
      "grad_norm": 0.75,
      "learning_rate": 3.0466329834968233e-05,
      "loss": 0.4118,
      "step": 855
    },
    {
      "epoch": 7.747747747747748,
      "grad_norm": 0.71484375,
      "learning_rate": 2.9344935356606773e-05,
      "loss": 0.4049,
      "step": 860
    },
    {
      "epoch": 7.792792792792793,
      "grad_norm": 0.74609375,
      "learning_rate": 2.8241008876021215e-05,
      "loss": 0.413,
      "step": 865
    },
    {
      "epoch": 7.837837837837838,
      "grad_norm": 0.72265625,
      "learning_rate": 2.7154823316113932e-05,
      "loss": 0.4071,
      "step": 870
    },
    {
      "epoch": 7.882882882882883,
      "grad_norm": 0.734375,
      "learning_rate": 2.60866472137129e-05,
      "loss": 0.4073,
      "step": 875
    },
    {
      "epoch": 7.927927927927928,
      "grad_norm": 0.71875,
      "learning_rate": 2.5036744653181753e-05,
      "loss": 0.4124,
      "step": 880
    },
    {
      "epoch": 7.972972972972973,
      "grad_norm": 0.7578125,
      "learning_rate": 2.4005375201130274e-05,
      "loss": 0.4205,
      "step": 885
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.9689488410949707,
      "eval_runtime": 1.0053,
      "eval_samples_per_second": 4.973,
      "eval_steps_per_second": 1.989,
      "step": 888
    },
    {
      "epoch": 8.018018018018019,
      "grad_norm": 0.68359375,
      "learning_rate": 2.29927938422419e-05,
      "loss": 0.4012,
      "step": 890
    },
    {
      "epoch": 8.063063063063064,
      "grad_norm": 1.0078125,
      "learning_rate": 2.199925091623418e-05,
      "loss": 0.3781,
      "step": 895
    },
    {
      "epoch": 8.108108108108109,
      "grad_norm": 0.8671875,
      "learning_rate": 2.102499205596743e-05,
      "loss": 0.3809,
      "step": 900
    },
    {
      "epoch": 8.153153153153154,
      "grad_norm": 0.70703125,
      "learning_rate": 2.0070258126717e-05,
      "loss": 0.3699,
      "step": 905
    },
    {
      "epoch": 8.198198198198199,
      "grad_norm": 0.6875,
      "learning_rate": 1.913528516662452e-05,
      "loss": 0.3742,
      "step": 910
    },
    {
      "epoch": 8.243243243243244,
      "grad_norm": 0.70703125,
      "learning_rate": 1.8220304328342252e-05,
      "loss": 0.378,
      "step": 915
    },
    {
      "epoch": 8.288288288288289,
      "grad_norm": 0.70703125,
      "learning_rate": 1.7325541821885384e-05,
      "loss": 0.3842,
      "step": 920
    },
    {
      "epoch": 8.333333333333334,
      "grad_norm": 0.75390625,
      "learning_rate": 1.6451218858706374e-05,
      "loss": 0.3894,
      "step": 925
    },
    {
      "epoch": 8.378378378378379,
      "grad_norm": 0.71875,
      "learning_rate": 1.5597551597004966e-05,
      "loss": 0.3758,
      "step": 930
    },
    {
      "epoch": 8.423423423423424,
      "grad_norm": 0.671875,
      "learning_rate": 1.476475108828762e-05,
      "loss": 0.3717,
      "step": 935
    },
    {
      "epoch": 8.468468468468469,
      "grad_norm": 0.703125,
      "learning_rate": 1.3953023225189243e-05,
      "loss": 0.3771,
      "step": 940
    },
    {
      "epoch": 8.513513513513514,
      "grad_norm": 0.71875,
      "learning_rate": 1.3162568690570743e-05,
      "loss": 0.3759,
      "step": 945
    },
    {
      "epoch": 8.558558558558559,
      "grad_norm": 0.74609375,
      "learning_rate": 1.23935829079042e-05,
      "loss": 0.3786,
      "step": 950
    },
    {
      "epoch": 8.603603603603604,
      "grad_norm": 0.7109375,
      "learning_rate": 1.1646255992958466e-05,
      "loss": 0.3734,
      "step": 955
    },
    {
      "epoch": 8.64864864864865,
      "grad_norm": 0.7265625,
      "learning_rate": 1.0920772706797167e-05,
      "loss": 0.3809,
      "step": 960
    },
    {
      "epoch": 8.693693693693694,
      "grad_norm": 0.7109375,
      "learning_rate": 1.0217312410100089e-05,
      "loss": 0.3767,
      "step": 965
    },
    {
      "epoch": 8.73873873873874,
      "grad_norm": 0.68359375,
      "learning_rate": 9.536049018820192e-06,
      "loss": 0.3786,
      "step": 970
    },
    {
      "epoch": 8.783783783783784,
      "grad_norm": 0.71875,
      "learning_rate": 8.87715096118642e-06,
      "loss": 0.3786,
      "step": 975
    },
    {
      "epoch": 8.82882882882883,
      "grad_norm": 0.74609375,
      "learning_rate": 8.240781136063346e-06,
      "loss": 0.3868,
      "step": 980
    },
    {
      "epoch": 8.873873873873874,
      "grad_norm": 0.72265625,
      "learning_rate": 7.6270968726777414e-06,
      "loss": 0.3767,
      "step": 985
    },
    {
      "epoch": 8.91891891891892,
      "grad_norm": 0.7578125,
      "learning_rate": 7.03624989172228e-06,
      "loss": 0.3791,
      "step": 990
    },
    {
      "epoch": 8.963963963963964,
      "grad_norm": 0.71875,
      "learning_rate": 6.468386267845717e-06,
      "loss": 0.382,
      "step": 995
    },
    {
      "epoch": 9.0,
      "eval_loss": 3.2251663208007812,
      "eval_runtime": 1.0069,
      "eval_samples_per_second": 4.966,
      "eval_steps_per_second": 1.986,
      "step": 999
    },
    {
      "epoch": 9.00900900900901,
      "grad_norm": 0.71484375,
      "learning_rate": 5.9236463935389065e-06,
      "loss": 0.3794,
      "step": 1000
    },
    {
      "epoch": 9.054054054054054,
      "grad_norm": 0.671875,
      "learning_rate": 5.402164944425758e-06,
      "loss": 0.3777,
      "step": 1005
    },
    {
      "epoch": 9.0990990990991,
      "grad_norm": 0.734375,
      "learning_rate": 4.904070845967468e-06,
      "loss": 0.3779,
      "step": 1010
    },
    {
      "epoch": 9.144144144144144,
      "grad_norm": 0.703125,
      "learning_rate": 4.429487241588304e-06,
      "loss": 0.3744,
      "step": 1015
    },
    {
      "epoch": 9.18918918918919,
      "grad_norm": 0.6953125,
      "learning_rate": 3.9785314622310495e-06,
      "loss": 0.3694,
      "step": 1020
    },
    {
      "epoch": 9.234234234234235,
      "grad_norm": 0.71875,
      "learning_rate": 3.5513149973492976e-06,
      "loss": 0.3751,
      "step": 1025
    },
    {
      "epoch": 9.27927927927928,
      "grad_norm": 0.7265625,
      "learning_rate": 3.1479434673440167e-06,
      "loss": 0.3685,
      "step": 1030
    },
    {
      "epoch": 9.324324324324325,
      "grad_norm": 0.68359375,
      "learning_rate": 2.7685165974510986e-06,
      "loss": 0.3653,
      "step": 1035
    },
    {
      "epoch": 9.36936936936937,
      "grad_norm": 0.71484375,
      "learning_rate": 2.4131281930864002e-06,
      "loss": 0.3728,
      "step": 1040
    },
    {
      "epoch": 9.414414414414415,
      "grad_norm": 0.734375,
      "learning_rate": 2.0818661166542074e-06,
      "loss": 0.3693,
      "step": 1045
    },
    {
      "epoch": 9.45945945945946,
      "grad_norm": 0.6875,
      "learning_rate": 1.7748122658251876e-06,
      "loss": 0.3764,
      "step": 1050
    },
    {
      "epoch": 9.504504504504505,
      "grad_norm": 0.7265625,
      "learning_rate": 1.4920425532888526e-06,
      "loss": 0.3654,
      "step": 1055
    },
    {
      "epoch": 9.54954954954955,
      "grad_norm": 0.66796875,
      "learning_rate": 1.2336268879856727e-06,
      "loss": 0.3747,
      "step": 1060
    },
    {
      "epoch": 9.594594594594595,
      "grad_norm": 0.69140625,
      "learning_rate": 9.996291578236228e-07,
      "loss": 0.3711,
      "step": 1065
    },
    {
      "epoch": 9.63963963963964,
      "grad_norm": 0.71484375,
      "learning_rate": 7.901072138831511e-07,
      "loss": 0.3722,
      "step": 1070
    },
    {
      "epoch": 9.684684684684685,
      "grad_norm": 0.7109375,
      "learning_rate": 6.051128561147756e-07,
      "loss": 0.3612,
      "step": 1075
    },
    {
      "epoch": 9.72972972972973,
      "grad_norm": 0.74609375,
      "learning_rate": 4.44691820532539e-07,
      "loss": 0.3647,
      "step": 1080
    },
    {
      "epoch": 9.774774774774775,
      "grad_norm": 0.6875,
      "learning_rate": 3.0888376790679795e-07,
      "loss": 0.3672,
      "step": 1085
    },
    {
      "epoch": 9.81981981981982,
      "grad_norm": 0.6484375,
      "learning_rate": 1.977222739588891e-07,
      "loss": 0.3659,
      "step": 1090
    },
    {
      "epoch": 9.864864864864865,
      "grad_norm": 0.67578125,
      "learning_rate": 1.1123482106021322e-07,
      "loss": 0.3692,
      "step": 1095
    },
    {
      "epoch": 9.90990990990991,
      "grad_norm": 0.6875,
      "learning_rate": 4.9442791437848136e-08,
      "loss": 0.3663,
      "step": 1100
    },
    {
      "epoch": 9.954954954954955,
      "grad_norm": 0.6875,
      "learning_rate": 1.2361461888166226e-08,
      "loss": 0.3673,
      "step": 1105
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.6640625,
      "learning_rate": 0.0,
      "loss": 0.372,
      "step": 1110
    },
    {
      "epoch": 10.0,
      "eval_loss": 3.242992401123047,
      "eval_runtime": 1.0031,
      "eval_samples_per_second": 4.984,
      "eval_steps_per_second": 1.994,
      "step": 1110
    },
    {
      "epoch": 10.0,
      "step": 1110,
      "total_flos": 1.697049221804327e+18,
      "train_loss": 1.8630313719715084,
      "train_runtime": 9058.6901,
      "train_samples_per_second": 1.957,
      "train_steps_per_second": 0.123
    }
  ],
  "logging_steps": 5,
  "max_steps": 1110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.697049221804327e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}