{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1269,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02364066193853428,
      "grad_norm": 1.7614086866378784,
      "learning_rate": 5e-06,
      "loss": 1.0709,
      "step": 10
    },
    {
      "epoch": 0.04728132387706856,
      "grad_norm": 3.922980546951294,
      "learning_rate": 5e-06,
      "loss": 1.0131,
      "step": 20
    },
    {
      "epoch": 0.07092198581560284,
      "grad_norm": 1.108715295791626,
      "learning_rate": 5e-06,
      "loss": 0.9972,
      "step": 30
    },
    {
      "epoch": 0.09456264775413711,
      "grad_norm": 0.6008648872375488,
      "learning_rate": 5e-06,
      "loss": 0.983,
      "step": 40
    },
    {
      "epoch": 0.1182033096926714,
      "grad_norm": 0.5573455095291138,
      "learning_rate": 5e-06,
      "loss": 0.9748,
      "step": 50
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 0.6367310881614685,
      "learning_rate": 5e-06,
      "loss": 0.9644,
      "step": 60
    },
    {
      "epoch": 0.16548463356973994,
      "grad_norm": 0.5621835589408875,
      "learning_rate": 5e-06,
      "loss": 0.9609,
      "step": 70
    },
    {
      "epoch": 0.18912529550827423,
      "grad_norm": 0.6173996329307556,
      "learning_rate": 5e-06,
      "loss": 0.9607,
      "step": 80
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 0.5042706727981567,
      "learning_rate": 5e-06,
      "loss": 0.9524,
      "step": 90
    },
    {
      "epoch": 0.2364066193853428,
      "grad_norm": 0.7688830494880676,
      "learning_rate": 5e-06,
      "loss": 0.9438,
      "step": 100
    },
    {
      "epoch": 0.26004728132387706,
      "grad_norm": 0.5911379456520081,
      "learning_rate": 5e-06,
      "loss": 0.9401,
      "step": 110
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 0.5532689690589905,
      "learning_rate": 5e-06,
      "loss": 0.9468,
      "step": 120
    },
    {
      "epoch": 0.3073286052009456,
      "grad_norm": 0.8925480246543884,
      "learning_rate": 5e-06,
      "loss": 0.9462,
      "step": 130
    },
    {
      "epoch": 0.3309692671394799,
      "grad_norm": 0.5422332882881165,
      "learning_rate": 5e-06,
      "loss": 0.94,
      "step": 140
    },
    {
      "epoch": 0.3546099290780142,
      "grad_norm": 0.5486394166946411,
      "learning_rate": 5e-06,
      "loss": 0.9344,
      "step": 150
    },
    {
      "epoch": 0.37825059101654845,
      "grad_norm": 0.5163227915763855,
      "learning_rate": 5e-06,
      "loss": 0.9281,
      "step": 160
    },
    {
      "epoch": 0.40189125295508277,
      "grad_norm": 0.53909832239151,
      "learning_rate": 5e-06,
      "loss": 0.9377,
      "step": 170
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.500614583492279,
      "learning_rate": 5e-06,
      "loss": 0.9309,
      "step": 180
    },
    {
      "epoch": 0.4491725768321513,
      "grad_norm": 0.5055537819862366,
      "learning_rate": 5e-06,
      "loss": 0.9326,
      "step": 190
    },
    {
      "epoch": 0.4728132387706856,
      "grad_norm": 0.5739602446556091,
      "learning_rate": 5e-06,
      "loss": 0.9334,
      "step": 200
    },
    {
      "epoch": 0.49645390070921985,
      "grad_norm": 0.4969063103199005,
      "learning_rate": 5e-06,
      "loss": 0.9306,
      "step": 210
    },
    {
      "epoch": 0.5200945626477541,
      "grad_norm": 0.4895598888397217,
      "learning_rate": 5e-06,
      "loss": 0.9326,
      "step": 220
    },
    {
      "epoch": 0.5437352245862884,
      "grad_norm": 0.488599956035614,
      "learning_rate": 5e-06,
      "loss": 0.9251,
      "step": 230
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 0.5502417087554932,
      "learning_rate": 5e-06,
      "loss": 0.9233,
      "step": 240
    },
    {
      "epoch": 0.5910165484633569,
      "grad_norm": 0.5484869480133057,
      "learning_rate": 5e-06,
      "loss": 0.9177,
      "step": 250
    },
    {
      "epoch": 0.6146572104018913,
      "grad_norm": 0.70972740650177,
      "learning_rate": 5e-06,
      "loss": 0.9204,
      "step": 260
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 0.5443243980407715,
      "learning_rate": 5e-06,
      "loss": 0.9203,
      "step": 270
    },
    {
      "epoch": 0.6619385342789598,
      "grad_norm": 0.4656381607055664,
      "learning_rate": 5e-06,
      "loss": 0.9251,
      "step": 280
    },
    {
      "epoch": 0.6855791962174941,
      "grad_norm": 0.49396905303001404,
      "learning_rate": 5e-06,
      "loss": 0.9242,
      "step": 290
    },
    {
      "epoch": 0.7092198581560284,
      "grad_norm": 0.43112456798553467,
      "learning_rate": 5e-06,
      "loss": 0.9238,
      "step": 300
    },
    {
      "epoch": 0.7328605200945626,
      "grad_norm": 0.4588732123374939,
      "learning_rate": 5e-06,
      "loss": 0.9206,
      "step": 310
    },
    {
      "epoch": 0.7565011820330969,
      "grad_norm": 0.5064387321472168,
      "learning_rate": 5e-06,
      "loss": 0.9177,
      "step": 320
    },
    {
      "epoch": 0.7801418439716312,
      "grad_norm": 0.51941978931427,
      "learning_rate": 5e-06,
      "loss": 0.9161,
      "step": 330
    },
    {
      "epoch": 0.8037825059101655,
      "grad_norm": 0.45160844922065735,
      "learning_rate": 5e-06,
      "loss": 0.9197,
      "step": 340
    },
    {
      "epoch": 0.8274231678486997,
      "grad_norm": 0.4652918875217438,
      "learning_rate": 5e-06,
      "loss": 0.9182,
      "step": 350
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.49702754616737366,
      "learning_rate": 5e-06,
      "loss": 0.9115,
      "step": 360
    },
    {
      "epoch": 0.8747044917257684,
      "grad_norm": 0.6036341786384583,
      "learning_rate": 5e-06,
      "loss": 0.9195,
      "step": 370
    },
    {
      "epoch": 0.8983451536643026,
      "grad_norm": 0.4541695713996887,
      "learning_rate": 5e-06,
      "loss": 0.9144,
      "step": 380
    },
    {
      "epoch": 0.9219858156028369,
      "grad_norm": 0.5585927963256836,
      "learning_rate": 5e-06,
      "loss": 0.9139,
      "step": 390
    },
    {
      "epoch": 0.9456264775413712,
      "grad_norm": 0.4704740047454834,
      "learning_rate": 5e-06,
      "loss": 0.9107,
      "step": 400
    },
    {
      "epoch": 0.9692671394799054,
      "grad_norm": 0.43893522024154663,
      "learning_rate": 5e-06,
      "loss": 0.9093,
      "step": 410
    },
    {
      "epoch": 0.9929078014184397,
      "grad_norm": 0.4892677366733551,
      "learning_rate": 5e-06,
      "loss": 0.9018,
      "step": 420
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9103471636772156,
      "eval_runtime": 38.5799,
      "eval_samples_per_second": 295.284,
      "eval_steps_per_second": 1.166,
      "step": 423
    },
    {
      "epoch": 1.016548463356974,
      "grad_norm": 0.5619480609893799,
      "learning_rate": 5e-06,
      "loss": 0.8787,
      "step": 430
    },
    {
      "epoch": 1.0401891252955082,
      "grad_norm": 0.5610897541046143,
      "learning_rate": 5e-06,
      "loss": 0.8696,
      "step": 440
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 0.4962644577026367,
      "learning_rate": 5e-06,
      "loss": 0.8629,
      "step": 450
    },
    {
      "epoch": 1.0874704491725768,
      "grad_norm": 0.8102297782897949,
      "learning_rate": 5e-06,
      "loss": 0.8631,
      "step": 460
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.4762827754020691,
      "learning_rate": 5e-06,
      "loss": 0.865,
      "step": 470
    },
    {
      "epoch": 1.1347517730496455,
      "grad_norm": 0.5226008296012878,
      "learning_rate": 5e-06,
      "loss": 0.8588,
      "step": 480
    },
    {
      "epoch": 1.1583924349881798,
      "grad_norm": 0.4529044032096863,
      "learning_rate": 5e-06,
      "loss": 0.8605,
      "step": 490
    },
    {
      "epoch": 1.1820330969267139,
      "grad_norm": 0.48834407329559326,
      "learning_rate": 5e-06,
      "loss": 0.865,
      "step": 500
    },
    {
      "epoch": 1.2056737588652482,
      "grad_norm": 0.5005617737770081,
      "learning_rate": 5e-06,
      "loss": 0.866,
      "step": 510
    },
    {
      "epoch": 1.2293144208037825,
      "grad_norm": 0.4393448829650879,
      "learning_rate": 5e-06,
      "loss": 0.8652,
      "step": 520
    },
    {
      "epoch": 1.2529550827423168,
      "grad_norm": 0.5248346328735352,
      "learning_rate": 5e-06,
      "loss": 0.8653,
      "step": 530
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 0.5386662483215332,
      "learning_rate": 5e-06,
      "loss": 0.859,
      "step": 540
    },
    {
      "epoch": 1.3002364066193852,
      "grad_norm": 0.48023349046707153,
      "learning_rate": 5e-06,
      "loss": 0.8639,
      "step": 550
    },
    {
      "epoch": 1.3238770685579198,
      "grad_norm": 0.46678417921066284,
      "learning_rate": 5e-06,
      "loss": 0.8678,
      "step": 560
    },
    {
      "epoch": 1.3475177304964538,
      "grad_norm": 0.5156953930854797,
      "learning_rate": 5e-06,
      "loss": 0.863,
      "step": 570
    },
    {
      "epoch": 1.3711583924349882,
      "grad_norm": 0.4521232545375824,
      "learning_rate": 5e-06,
      "loss": 0.8661,
      "step": 580
    },
    {
      "epoch": 1.3947990543735225,
      "grad_norm": 0.4961282014846802,
      "learning_rate": 5e-06,
      "loss": 0.8591,
      "step": 590
    },
    {
      "epoch": 1.4184397163120568,
      "grad_norm": 0.4934581220149994,
      "learning_rate": 5e-06,
      "loss": 0.864,
      "step": 600
    },
    {
      "epoch": 1.442080378250591,
      "grad_norm": 0.5448637008666992,
      "learning_rate": 5e-06,
      "loss": 0.8635,
      "step": 610
    },
    {
      "epoch": 1.4657210401891252,
      "grad_norm": 0.4642185568809509,
      "learning_rate": 5e-06,
      "loss": 0.8631,
      "step": 620
    },
    {
      "epoch": 1.4893617021276595,
      "grad_norm": 0.4816928803920746,
      "learning_rate": 5e-06,
      "loss": 0.8618,
      "step": 630
    },
    {
      "epoch": 1.5130023640661938,
      "grad_norm": 0.4565974175930023,
      "learning_rate": 5e-06,
      "loss": 0.864,
      "step": 640
    },
    {
      "epoch": 1.5366430260047281,
      "grad_norm": 0.580853283405304,
      "learning_rate": 5e-06,
      "loss": 0.8613,
      "step": 650
    },
    {
      "epoch": 1.5602836879432624,
      "grad_norm": 0.5403729677200317,
      "learning_rate": 5e-06,
      "loss": 0.8636,
      "step": 660
    },
    {
      "epoch": 1.5839243498817965,
      "grad_norm": 0.4570687711238861,
      "learning_rate": 5e-06,
      "loss": 0.8636,
      "step": 670
    },
    {
      "epoch": 1.607565011820331,
      "grad_norm": 0.557025134563446,
      "learning_rate": 5e-06,
      "loss": 0.8634,
      "step": 680
    },
    {
      "epoch": 1.6312056737588652,
      "grad_norm": 0.4970671534538269,
      "learning_rate": 5e-06,
      "loss": 0.8582,
      "step": 690
    },
    {
      "epoch": 1.6548463356973995,
      "grad_norm": 0.5011308193206787,
      "learning_rate": 5e-06,
      "loss": 0.8615,
      "step": 700
    },
    {
      "epoch": 1.6784869976359338,
      "grad_norm": 0.5732368230819702,
      "learning_rate": 5e-06,
      "loss": 0.8612,
      "step": 710
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 0.44940251111984253,
      "learning_rate": 5e-06,
      "loss": 0.8654,
      "step": 720
    },
    {
      "epoch": 1.7257683215130024,
      "grad_norm": 0.4695453643798828,
      "learning_rate": 5e-06,
      "loss": 0.8655,
      "step": 730
    },
    {
      "epoch": 1.7494089834515365,
      "grad_norm": 0.6582662463188171,
      "learning_rate": 5e-06,
      "loss": 0.863,
      "step": 740
    },
    {
      "epoch": 1.773049645390071,
      "grad_norm": 0.5361992716789246,
      "learning_rate": 5e-06,
      "loss": 0.857,
      "step": 750
    },
    {
      "epoch": 1.7966903073286051,
      "grad_norm": 0.4670429527759552,
      "learning_rate": 5e-06,
      "loss": 0.8614,
      "step": 760
    },
    {
      "epoch": 1.8203309692671394,
      "grad_norm": 0.44174039363861084,
      "learning_rate": 5e-06,
      "loss": 0.8606,
      "step": 770
    },
    {
      "epoch": 1.8439716312056738,
      "grad_norm": 0.4454022943973541,
      "learning_rate": 5e-06,
      "loss": 0.8603,
      "step": 780
    },
    {
      "epoch": 1.867612293144208,
      "grad_norm": 0.46973222494125366,
      "learning_rate": 5e-06,
      "loss": 0.8624,
      "step": 790
    },
    {
      "epoch": 1.8912529550827424,
      "grad_norm": 0.4946763515472412,
      "learning_rate": 5e-06,
      "loss": 0.8648,
      "step": 800
    },
    {
      "epoch": 1.9148936170212765,
      "grad_norm": 0.4165429472923279,
      "learning_rate": 5e-06,
      "loss": 0.8584,
      "step": 810
    },
    {
      "epoch": 1.938534278959811,
      "grad_norm": 0.44204238057136536,
      "learning_rate": 5e-06,
      "loss": 0.8615,
      "step": 820
    },
    {
      "epoch": 1.962174940898345,
      "grad_norm": 0.4277856647968292,
      "learning_rate": 5e-06,
      "loss": 0.8603,
      "step": 830
    },
    {
      "epoch": 1.9858156028368794,
      "grad_norm": 0.4897569715976715,
      "learning_rate": 5e-06,
      "loss": 0.8586,
      "step": 840
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.9001395106315613,
      "eval_runtime": 38.3885,
      "eval_samples_per_second": 296.756,
      "eval_steps_per_second": 1.172,
      "step": 846
    },
    {
      "epoch": 2.0094562647754137,
      "grad_norm": 0.673308789730072,
      "learning_rate": 5e-06,
      "loss": 0.8393,
      "step": 850
    },
    {
      "epoch": 2.033096926713948,
      "grad_norm": 0.5594461560249329,
      "learning_rate": 5e-06,
      "loss": 0.8071,
      "step": 860
    },
    {
      "epoch": 2.0567375886524824,
      "grad_norm": 0.4584490656852722,
      "learning_rate": 5e-06,
      "loss": 0.8083,
      "step": 870
    },
    {
      "epoch": 2.0803782505910164,
      "grad_norm": 0.5544384121894836,
      "learning_rate": 5e-06,
      "loss": 0.8135,
      "step": 880
    },
    {
      "epoch": 2.104018912529551,
      "grad_norm": 0.5173571705818176,
      "learning_rate": 5e-06,
      "loss": 0.8104,
      "step": 890
    },
    {
      "epoch": 2.127659574468085,
      "grad_norm": 0.488302618265152,
      "learning_rate": 5e-06,
      "loss": 0.8155,
      "step": 900
    },
    {
      "epoch": 2.1513002364066196,
      "grad_norm": 0.5209611058235168,
      "learning_rate": 5e-06,
      "loss": 0.8108,
      "step": 910
    },
    {
      "epoch": 2.1749408983451537,
      "grad_norm": 0.51943439245224,
      "learning_rate": 5e-06,
      "loss": 0.808,
      "step": 920
    },
    {
      "epoch": 2.198581560283688,
      "grad_norm": 0.5136656761169434,
      "learning_rate": 5e-06,
      "loss": 0.8152,
      "step": 930
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.48146888613700867,
      "learning_rate": 5e-06,
      "loss": 0.8114,
      "step": 940
    },
    {
      "epoch": 2.2458628841607564,
      "grad_norm": 0.5011332035064697,
      "learning_rate": 5e-06,
      "loss": 0.8133,
      "step": 950
    },
    {
      "epoch": 2.269503546099291,
      "grad_norm": 0.5616235733032227,
      "learning_rate": 5e-06,
      "loss": 0.815,
      "step": 960
    },
    {
      "epoch": 2.293144208037825,
      "grad_norm": 0.4666649401187897,
      "learning_rate": 5e-06,
      "loss": 0.8096,
      "step": 970
    },
    {
      "epoch": 2.3167848699763596,
      "grad_norm": 0.5732521414756775,
      "learning_rate": 5e-06,
      "loss": 0.8098,
      "step": 980
    },
    {
      "epoch": 2.3404255319148937,
      "grad_norm": 0.4544953405857086,
      "learning_rate": 5e-06,
      "loss": 0.8124,
      "step": 990
    },
    {
      "epoch": 2.3640661938534278,
      "grad_norm": 0.44587448239326477,
      "learning_rate": 5e-06,
      "loss": 0.8095,
      "step": 1000
    },
    {
      "epoch": 2.3877068557919623,
      "grad_norm": 0.484457403421402,
      "learning_rate": 5e-06,
      "loss": 0.8118,
      "step": 1010
    },
    {
      "epoch": 2.4113475177304964,
      "grad_norm": 0.4641134440898895,
      "learning_rate": 5e-06,
      "loss": 0.8124,
      "step": 1020
    },
    {
      "epoch": 2.434988179669031,
      "grad_norm": 0.49560511112213135,
      "learning_rate": 5e-06,
      "loss": 0.8129,
      "step": 1030
    },
    {
      "epoch": 2.458628841607565,
      "grad_norm": 0.4686046540737152,
      "learning_rate": 5e-06,
      "loss": 0.814,
      "step": 1040
    },
    {
      "epoch": 2.482269503546099,
      "grad_norm": 0.5736932158470154,
      "learning_rate": 5e-06,
      "loss": 0.809,
      "step": 1050
    },
    {
      "epoch": 2.5059101654846336,
      "grad_norm": 0.5565879940986633,
      "learning_rate": 5e-06,
      "loss": 0.8192,
      "step": 1060
    },
    {
      "epoch": 2.5295508274231677,
      "grad_norm": 0.5535584092140198,
      "learning_rate": 5e-06,
      "loss": 0.8177,
      "step": 1070
    },
    {
      "epoch": 2.5531914893617023,
      "grad_norm": 0.49917906522750854,
      "learning_rate": 5e-06,
      "loss": 0.817,
      "step": 1080
    },
    {
      "epoch": 2.5768321513002364,
      "grad_norm": 0.48814043402671814,
      "learning_rate": 5e-06,
      "loss": 0.8118,
      "step": 1090
    },
    {
      "epoch": 2.6004728132387704,
      "grad_norm": 0.4942103326320648,
      "learning_rate": 5e-06,
      "loss": 0.8218,
      "step": 1100
    },
    {
      "epoch": 2.624113475177305,
      "grad_norm": 0.5041037797927856,
      "learning_rate": 5e-06,
      "loss": 0.8142,
      "step": 1110
    },
    {
      "epoch": 2.6477541371158395,
      "grad_norm": 0.4969462454319,
      "learning_rate": 5e-06,
      "loss": 0.8194,
      "step": 1120
    },
    {
      "epoch": 2.6713947990543736,
      "grad_norm": 0.5635184049606323,
      "learning_rate": 5e-06,
      "loss": 0.8206,
      "step": 1130
    },
    {
      "epoch": 2.6950354609929077,
      "grad_norm": 0.4972004294395447,
      "learning_rate": 5e-06,
      "loss": 0.8192,
      "step": 1140
    },
    {
      "epoch": 2.7186761229314422,
      "grad_norm": 0.49688395857810974,
      "learning_rate": 5e-06,
      "loss": 0.8165,
      "step": 1150
    },
    {
      "epoch": 2.7423167848699763,
      "grad_norm": 0.4726709723472595,
      "learning_rate": 5e-06,
      "loss": 0.8205,
      "step": 1160
    },
    {
      "epoch": 2.7659574468085104,
      "grad_norm": 0.532228946685791,
      "learning_rate": 5e-06,
      "loss": 0.8139,
      "step": 1170
    },
    {
      "epoch": 2.789598108747045,
      "grad_norm": 0.4629664421081543,
      "learning_rate": 5e-06,
      "loss": 0.8119,
      "step": 1180
    },
    {
      "epoch": 2.813238770685579,
      "grad_norm": 0.4985387921333313,
      "learning_rate": 5e-06,
      "loss": 0.8206,
      "step": 1190
    },
    {
      "epoch": 2.8368794326241136,
      "grad_norm": 0.48208263516426086,
      "learning_rate": 5e-06,
      "loss": 0.8144,
      "step": 1200
    },
    {
      "epoch": 2.8605200945626477,
      "grad_norm": 0.5160050988197327,
      "learning_rate": 5e-06,
      "loss": 0.8179,
      "step": 1210
    },
    {
      "epoch": 2.884160756501182,
      "grad_norm": 0.47810521721839905,
      "learning_rate": 5e-06,
      "loss": 0.8157,
      "step": 1220
    },
    {
      "epoch": 2.9078014184397163,
      "grad_norm": 0.4839594066143036,
      "learning_rate": 5e-06,
      "loss": 0.8162,
      "step": 1230
    },
    {
      "epoch": 2.9314420803782504,
      "grad_norm": 0.49858078360557556,
      "learning_rate": 5e-06,
      "loss": 0.8133,
      "step": 1240
    },
    {
      "epoch": 2.955082742316785,
      "grad_norm": 0.5557030439376831,
      "learning_rate": 5e-06,
      "loss": 0.8167,
      "step": 1250
    },
    {
      "epoch": 2.978723404255319,
      "grad_norm": 0.5793541073799133,
      "learning_rate": 5e-06,
      "loss": 0.8143,
      "step": 1260
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.9010276198387146,
      "eval_runtime": 39.1845,
      "eval_samples_per_second": 290.728,
      "eval_steps_per_second": 1.148,
      "step": 1269
    },
    {
      "epoch": 3.0,
      "step": 1269,
      "total_flos": 5.9918252490593665e+19,
      "train_loss": 0.8716646811452975,
      "train_runtime": 8996.6792,
      "train_samples_per_second": 72.17,
      "train_steps_per_second": 0.141
    }
  ],
  "logging_steps": 10,
  "max_steps": 1269,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.9918252490593665e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}