{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.996011396011396,
  "eval_steps": 500,
  "global_step": 1314,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022792022792022793,
      "grad_norm": 1.0146420064637809,
      "learning_rate": 1e-05,
      "loss": 0.7412,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 0.7912257831574413,
      "learning_rate": 1e-05,
      "loss": 0.6876,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.8690010677441243,
      "learning_rate": 1e-05,
      "loss": 0.666,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.505631934162416,
      "learning_rate": 1e-05,
      "loss": 0.6638,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.33858449719431943,
      "learning_rate": 1e-05,
      "loss": 0.6608,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.3902928439357306,
      "learning_rate": 1e-05,
      "loss": 0.6445,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.32811851282307186,
      "learning_rate": 1e-05,
      "loss": 0.6448,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.34238369327660734,
      "learning_rate": 1e-05,
      "loss": 0.6497,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.31623988973775263,
      "learning_rate": 1e-05,
      "loss": 0.6353,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.31093405606619007,
      "learning_rate": 1e-05,
      "loss": 0.6368,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.36187170115633943,
      "learning_rate": 1e-05,
      "loss": 0.6284,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.3233998336839521,
      "learning_rate": 1e-05,
      "loss": 0.6366,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.3913907420956762,
      "learning_rate": 1e-05,
      "loss": 0.6377,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.3360481444653111,
      "learning_rate": 1e-05,
      "loss": 0.6398,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.3175168014145369,
      "learning_rate": 1e-05,
      "loss": 0.6323,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.37657481652603003,
      "learning_rate": 1e-05,
      "loss": 0.6376,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.35292598832747574,
      "learning_rate": 1e-05,
      "loss": 0.6294,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.3020552424319043,
      "learning_rate": 1e-05,
      "loss": 0.635,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.3439921293702071,
      "learning_rate": 1e-05,
      "loss": 0.6276,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.3327414470872692,
      "learning_rate": 1e-05,
      "loss": 0.6356,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.34684235410854686,
      "learning_rate": 1e-05,
      "loss": 0.6319,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.3407250677678901,
      "learning_rate": 1e-05,
      "loss": 0.6357,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.357024472193329,
      "learning_rate": 1e-05,
      "loss": 0.6314,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.30797227810550154,
      "learning_rate": 1e-05,
      "loss": 0.6271,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.33312179990469154,
      "learning_rate": 1e-05,
      "loss": 0.6321,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.3367120191713227,
      "learning_rate": 1e-05,
      "loss": 0.6303,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.33627122083313027,
      "learning_rate": 1e-05,
      "loss": 0.6274,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.362508172904337,
      "learning_rate": 1e-05,
      "loss": 0.6382,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.34361915555957834,
      "learning_rate": 1e-05,
      "loss": 0.6269,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.3287032976695359,
      "learning_rate": 1e-05,
      "loss": 0.6249,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.3191486869355932,
      "learning_rate": 1e-05,
      "loss": 0.6248,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.31860851089180897,
      "learning_rate": 1e-05,
      "loss": 0.6254,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.3846001822856447,
      "learning_rate": 1e-05,
      "loss": 0.622,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.3477286187132196,
      "learning_rate": 1e-05,
      "loss": 0.6277,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.366357630454119,
      "learning_rate": 1e-05,
      "loss": 0.6348,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.3609953342647578,
      "learning_rate": 1e-05,
      "loss": 0.6267,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.41707694363193043,
      "learning_rate": 1e-05,
      "loss": 0.6203,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.3638258217776452,
      "learning_rate": 1e-05,
      "loss": 0.6326,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.36073013889545996,
      "learning_rate": 1e-05,
      "loss": 0.6312,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.3707654840473297,
      "learning_rate": 1e-05,
      "loss": 0.6343,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.34309367527787005,
      "learning_rate": 1e-05,
      "loss": 0.6306,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.35582985450029564,
      "learning_rate": 1e-05,
      "loss": 0.6176,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.4461192998565824,
      "learning_rate": 1e-05,
      "loss": 0.6304,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.621112048625946,
      "eval_runtime": 440.3517,
      "eval_samples_per_second": 26.849,
      "eval_steps_per_second": 0.42,
      "step": 438
    },
    {
      "epoch": 1.0034188034188034,
      "grad_norm": 0.40599764408780503,
      "learning_rate": 1e-05,
      "loss": 0.6403,
      "step": 440
    },
    {
      "epoch": 1.0262108262108263,
      "grad_norm": 0.33824605577756234,
      "learning_rate": 1e-05,
      "loss": 0.5777,
      "step": 450
    },
    {
      "epoch": 1.049002849002849,
      "grad_norm": 0.32924589697953344,
      "learning_rate": 1e-05,
      "loss": 0.5713,
      "step": 460
    },
    {
      "epoch": 1.0717948717948718,
      "grad_norm": 0.3390857296918303,
      "learning_rate": 1e-05,
      "loss": 0.5722,
      "step": 470
    },
    {
      "epoch": 1.0945868945868946,
      "grad_norm": 0.35001642645281617,
      "learning_rate": 1e-05,
      "loss": 0.5799,
      "step": 480
    },
    {
      "epoch": 1.1173789173789175,
      "grad_norm": 0.35554307229590787,
      "learning_rate": 1e-05,
      "loss": 0.5849,
      "step": 490
    },
    {
      "epoch": 1.1401709401709401,
      "grad_norm": 0.31083370576221864,
      "learning_rate": 1e-05,
      "loss": 0.5755,
      "step": 500
    },
    {
      "epoch": 1.162962962962963,
      "grad_norm": 0.31553364890263425,
      "learning_rate": 1e-05,
      "loss": 0.5736,
      "step": 510
    },
    {
      "epoch": 1.1857549857549858,
      "grad_norm": 0.2987072829265303,
      "learning_rate": 1e-05,
      "loss": 0.5794,
      "step": 520
    },
    {
      "epoch": 1.2085470085470085,
      "grad_norm": 0.3357868380230108,
      "learning_rate": 1e-05,
      "loss": 0.5731,
      "step": 530
    },
    {
      "epoch": 1.2313390313390313,
      "grad_norm": 0.3424754214162845,
      "learning_rate": 1e-05,
      "loss": 0.5831,
      "step": 540
    },
    {
      "epoch": 1.2541310541310542,
      "grad_norm": 0.2994505023233895,
      "learning_rate": 1e-05,
      "loss": 0.5798,
      "step": 550
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.3261302844209219,
      "learning_rate": 1e-05,
      "loss": 0.5818,
      "step": 560
    },
    {
      "epoch": 1.2997150997150997,
      "grad_norm": 0.32160593176293023,
      "learning_rate": 1e-05,
      "loss": 0.5762,
      "step": 570
    },
    {
      "epoch": 1.3225071225071225,
      "grad_norm": 0.31343014468938596,
      "learning_rate": 1e-05,
      "loss": 0.5747,
      "step": 580
    },
    {
      "epoch": 1.3452991452991454,
      "grad_norm": 0.3029232044781107,
      "learning_rate": 1e-05,
      "loss": 0.5744,
      "step": 590
    },
    {
      "epoch": 1.368091168091168,
      "grad_norm": 0.3204205916615222,
      "learning_rate": 1e-05,
      "loss": 0.5801,
      "step": 600
    },
    {
      "epoch": 1.390883190883191,
      "grad_norm": 0.33901583811674174,
      "learning_rate": 1e-05,
      "loss": 0.5802,
      "step": 610
    },
    {
      "epoch": 1.4136752136752135,
      "grad_norm": 0.35647413040021203,
      "learning_rate": 1e-05,
      "loss": 0.5831,
      "step": 620
    },
    {
      "epoch": 1.4364672364672364,
      "grad_norm": 0.3926041011121538,
      "learning_rate": 1e-05,
      "loss": 0.5813,
      "step": 630
    },
    {
      "epoch": 1.4592592592592593,
      "grad_norm": 0.33806390127793345,
      "learning_rate": 1e-05,
      "loss": 0.5762,
      "step": 640
    },
    {
      "epoch": 1.4820512820512821,
      "grad_norm": 0.328698581982291,
      "learning_rate": 1e-05,
      "loss": 0.5744,
      "step": 650
    },
    {
      "epoch": 1.504843304843305,
      "grad_norm": 0.3395135859147101,
      "learning_rate": 1e-05,
      "loss": 0.5742,
      "step": 660
    },
    {
      "epoch": 1.5276353276353276,
      "grad_norm": 0.3885455805540249,
      "learning_rate": 1e-05,
      "loss": 0.5816,
      "step": 670
    },
    {
      "epoch": 1.5504273504273505,
      "grad_norm": 0.30996592095776465,
      "learning_rate": 1e-05,
      "loss": 0.5707,
      "step": 680
    },
    {
      "epoch": 1.573219373219373,
      "grad_norm": 0.3146912481858014,
      "learning_rate": 1e-05,
      "loss": 0.5744,
      "step": 690
    },
    {
      "epoch": 1.596011396011396,
      "grad_norm": 0.31588213782224217,
      "learning_rate": 1e-05,
      "loss": 0.59,
      "step": 700
    },
    {
      "epoch": 1.6188034188034188,
      "grad_norm": 0.32153673893804763,
      "learning_rate": 1e-05,
      "loss": 0.5774,
      "step": 710
    },
    {
      "epoch": 1.6415954415954417,
      "grad_norm": 0.31257504452618234,
      "learning_rate": 1e-05,
      "loss": 0.5818,
      "step": 720
    },
    {
      "epoch": 1.6643874643874645,
      "grad_norm": 0.3253370468338142,
      "learning_rate": 1e-05,
      "loss": 0.5752,
      "step": 730
    },
    {
      "epoch": 1.6871794871794872,
      "grad_norm": 0.35468087072518323,
      "learning_rate": 1e-05,
      "loss": 0.5765,
      "step": 740
    },
    {
      "epoch": 1.7099715099715098,
      "grad_norm": 0.2941502107066292,
      "learning_rate": 1e-05,
      "loss": 0.574,
      "step": 750
    },
    {
      "epoch": 1.7327635327635327,
      "grad_norm": 0.4040377978043082,
      "learning_rate": 1e-05,
      "loss": 0.5776,
      "step": 760
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.3335681103789512,
      "learning_rate": 1e-05,
      "loss": 0.5743,
      "step": 770
    },
    {
      "epoch": 1.7783475783475784,
      "grad_norm": 0.30226629822048895,
      "learning_rate": 1e-05,
      "loss": 0.5816,
      "step": 780
    },
    {
      "epoch": 1.8011396011396013,
      "grad_norm": 0.3339556013176704,
      "learning_rate": 1e-05,
      "loss": 0.5793,
      "step": 790
    },
    {
      "epoch": 1.823931623931624,
      "grad_norm": 0.3269246369063951,
      "learning_rate": 1e-05,
      "loss": 0.5666,
      "step": 800
    },
    {
      "epoch": 1.8467236467236468,
      "grad_norm": 0.3224956260584643,
      "learning_rate": 1e-05,
      "loss": 0.5742,
      "step": 810
    },
    {
      "epoch": 1.8695156695156694,
      "grad_norm": 0.3655123174434984,
      "learning_rate": 1e-05,
      "loss": 0.5721,
      "step": 820
    },
    {
      "epoch": 1.8923076923076922,
      "grad_norm": 0.33531337558262225,
      "learning_rate": 1e-05,
      "loss": 0.5758,
      "step": 830
    },
    {
      "epoch": 1.915099715099715,
      "grad_norm": 0.33279895151242517,
      "learning_rate": 1e-05,
      "loss": 0.5803,
      "step": 840
    },
    {
      "epoch": 1.937891737891738,
      "grad_norm": 0.31841085542396463,
      "learning_rate": 1e-05,
      "loss": 0.5786,
      "step": 850
    },
    {
      "epoch": 1.9606837606837608,
      "grad_norm": 0.3656774559080548,
      "learning_rate": 1e-05,
      "loss": 0.5798,
      "step": 860
    },
    {
      "epoch": 1.9834757834757835,
      "grad_norm": 0.32129389800623026,
      "learning_rate": 1e-05,
      "loss": 0.5774,
      "step": 870
    },
    {
      "epoch": 1.9994301994301993,
      "eval_loss": 0.6186357736587524,
      "eval_runtime": 442.4653,
      "eval_samples_per_second": 26.721,
      "eval_steps_per_second": 0.418,
      "step": 877
    },
    {
      "epoch": 2.006837606837607,
      "grad_norm": 0.40023961081016884,
      "learning_rate": 1e-05,
      "loss": 0.5896,
      "step": 880
    },
    {
      "epoch": 2.0296296296296297,
      "grad_norm": 0.3934269207415266,
      "learning_rate": 1e-05,
      "loss": 0.5143,
      "step": 890
    },
    {
      "epoch": 2.0524216524216525,
      "grad_norm": 0.3372672329666936,
      "learning_rate": 1e-05,
      "loss": 0.5277,
      "step": 900
    },
    {
      "epoch": 2.0752136752136754,
      "grad_norm": 0.3590605375051872,
      "learning_rate": 1e-05,
      "loss": 0.5262,
      "step": 910
    },
    {
      "epoch": 2.098005698005698,
      "grad_norm": 0.32027005855990875,
      "learning_rate": 1e-05,
      "loss": 0.529,
      "step": 920
    },
    {
      "epoch": 2.1207977207977207,
      "grad_norm": 0.3122240355891651,
      "learning_rate": 1e-05,
      "loss": 0.5279,
      "step": 930
    },
    {
      "epoch": 2.1435897435897435,
      "grad_norm": 0.306328979810517,
      "learning_rate": 1e-05,
      "loss": 0.523,
      "step": 940
    },
    {
      "epoch": 2.1663817663817664,
      "grad_norm": 0.2997763176691866,
      "learning_rate": 1e-05,
      "loss": 0.5239,
      "step": 950
    },
    {
      "epoch": 2.1891737891737892,
      "grad_norm": 0.30072443341331295,
      "learning_rate": 1e-05,
      "loss": 0.5291,
      "step": 960
    },
    {
      "epoch": 2.211965811965812,
      "grad_norm": 0.3659610909649348,
      "learning_rate": 1e-05,
      "loss": 0.529,
      "step": 970
    },
    {
      "epoch": 2.234757834757835,
      "grad_norm": 0.31170766785306336,
      "learning_rate": 1e-05,
      "loss": 0.5197,
      "step": 980
    },
    {
      "epoch": 2.2575498575498574,
      "grad_norm": 0.3107127824005287,
      "learning_rate": 1e-05,
      "loss": 0.5287,
      "step": 990
    },
    {
      "epoch": 2.2803418803418802,
      "grad_norm": 0.3077202897593116,
      "learning_rate": 1e-05,
      "loss": 0.5293,
      "step": 1000
    },
    {
      "epoch": 2.303133903133903,
      "grad_norm": 0.3766294985445228,
      "learning_rate": 1e-05,
      "loss": 0.5269,
      "step": 1010
    },
    {
      "epoch": 2.325925925925926,
      "grad_norm": 0.31670166754832074,
      "learning_rate": 1e-05,
      "loss": 0.5298,
      "step": 1020
    },
    {
      "epoch": 2.348717948717949,
      "grad_norm": 0.3294563307726443,
      "learning_rate": 1e-05,
      "loss": 0.5311,
      "step": 1030
    },
    {
      "epoch": 2.3715099715099717,
      "grad_norm": 0.33934557749302635,
      "learning_rate": 1e-05,
      "loss": 0.5299,
      "step": 1040
    },
    {
      "epoch": 2.394301994301994,
      "grad_norm": 0.29973624613589284,
      "learning_rate": 1e-05,
      "loss": 0.5292,
      "step": 1050
    },
    {
      "epoch": 2.417094017094017,
      "grad_norm": 0.30731911268155737,
      "learning_rate": 1e-05,
      "loss": 0.537,
      "step": 1060
    },
    {
      "epoch": 2.43988603988604,
      "grad_norm": 0.3320184686838146,
      "learning_rate": 1e-05,
      "loss": 0.5397,
      "step": 1070
    },
    {
      "epoch": 2.4626780626780627,
      "grad_norm": 0.33488791378484484,
      "learning_rate": 1e-05,
      "loss": 0.5354,
      "step": 1080
    },
    {
      "epoch": 2.4854700854700855,
      "grad_norm": 0.29869988487306637,
      "learning_rate": 1e-05,
      "loss": 0.5339,
      "step": 1090
    },
    {
      "epoch": 2.5082621082621084,
      "grad_norm": 0.3904880801438361,
      "learning_rate": 1e-05,
      "loss": 0.5394,
      "step": 1100
    },
    {
      "epoch": 2.5310541310541312,
      "grad_norm": 0.38036081075155204,
      "learning_rate": 1e-05,
      "loss": 0.5341,
      "step": 1110
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.30643406351346947,
      "learning_rate": 1e-05,
      "loss": 0.5322,
      "step": 1120
    },
    {
      "epoch": 2.5766381766381765,
      "grad_norm": 0.2893340180647077,
      "learning_rate": 1e-05,
      "loss": 0.5319,
      "step": 1130
    },
    {
      "epoch": 2.5994301994301994,
      "grad_norm": 0.29553745186992597,
      "learning_rate": 1e-05,
      "loss": 0.5318,
      "step": 1140
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.3121235774200754,
      "learning_rate": 1e-05,
      "loss": 0.5324,
      "step": 1150
    },
    {
      "epoch": 2.645014245014245,
      "grad_norm": 0.3537885981034807,
      "learning_rate": 1e-05,
      "loss": 0.5338,
      "step": 1160
    },
    {
      "epoch": 2.667806267806268,
      "grad_norm": 0.3135782078081984,
      "learning_rate": 1e-05,
      "loss": 0.5361,
      "step": 1170
    },
    {
      "epoch": 2.690598290598291,
      "grad_norm": 0.3120319160666968,
      "learning_rate": 1e-05,
      "loss": 0.5316,
      "step": 1180
    },
    {
      "epoch": 2.7133903133903132,
      "grad_norm": 0.3721925648462127,
      "learning_rate": 1e-05,
      "loss": 0.5331,
      "step": 1190
    },
    {
      "epoch": 2.736182336182336,
      "grad_norm": 0.35097259445904583,
      "learning_rate": 1e-05,
      "loss": 0.5362,
      "step": 1200
    },
    {
      "epoch": 2.758974358974359,
      "grad_norm": 0.3191287188931511,
      "learning_rate": 1e-05,
      "loss": 0.5394,
      "step": 1210
    },
    {
      "epoch": 2.781766381766382,
      "grad_norm": 0.3353550527181426,
      "learning_rate": 1e-05,
      "loss": 0.5301,
      "step": 1220
    },
    {
      "epoch": 2.8045584045584047,
      "grad_norm": 0.3662461553840285,
      "learning_rate": 1e-05,
      "loss": 0.5286,
      "step": 1230
    },
    {
      "epoch": 2.827350427350427,
      "grad_norm": 0.3582675691272763,
      "learning_rate": 1e-05,
      "loss": 0.5428,
      "step": 1240
    },
    {
      "epoch": 2.8501424501424504,
      "grad_norm": 0.29421053202127245,
      "learning_rate": 1e-05,
      "loss": 0.5393,
      "step": 1250
    },
    {
      "epoch": 2.872934472934473,
      "grad_norm": 0.3323816797271506,
      "learning_rate": 1e-05,
      "loss": 0.5369,
      "step": 1260
    },
    {
      "epoch": 2.8957264957264957,
      "grad_norm": 0.34833626456933586,
      "learning_rate": 1e-05,
      "loss": 0.5381,
      "step": 1270
    },
    {
      "epoch": 2.9185185185185185,
      "grad_norm": 0.3208962009280921,
      "learning_rate": 1e-05,
      "loss": 0.5288,
      "step": 1280
    },
    {
      "epoch": 2.9413105413105414,
      "grad_norm": 0.3524250244854125,
      "learning_rate": 1e-05,
      "loss": 0.5293,
      "step": 1290
    },
    {
      "epoch": 2.9641025641025642,
      "grad_norm": 0.31554960818197597,
      "learning_rate": 1e-05,
      "loss": 0.5303,
      "step": 1300
    },
    {
      "epoch": 2.9868945868945866,
      "grad_norm": 0.33440739359228305,
      "learning_rate": 1e-05,
      "loss": 0.5394,
      "step": 1310
    },
    {
      "epoch": 2.996011396011396,
      "eval_loss": 0.6266428232192993,
      "eval_runtime": 446.7392,
      "eval_samples_per_second": 26.465,
      "eval_steps_per_second": 0.414,
      "step": 1314
    },
    {
      "epoch": 2.996011396011396,
      "step": 1314,
      "total_flos": 2755219238682624.0,
      "train_loss": 0.5826670261641435,
      "train_runtime": 70447.3802,
      "train_samples_per_second": 9.565,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 10,
  "max_steps": 1314,
  "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": 2755219238682624.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}