{
  "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": 7.563443850319552,
      "learning_rate": 7.575757575757576e-07,
      "loss": 0.8288,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 2.069894997399947,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 0.7833,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 1.0951593292405446,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.7256,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.9570723175425797,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 0.7101,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.8831901989346106,
      "learning_rate": 3.7878787878787882e-06,
      "loss": 0.7005,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.8399574591771969,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.6762,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.7081038745458517,
      "learning_rate": 4.983974358974359e-06,
      "loss": 0.6695,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.7750443970644509,
      "learning_rate": 4.943910256410257e-06,
      "loss": 0.6681,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.5306496088378102,
      "learning_rate": 4.903846153846154e-06,
      "loss": 0.6484,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.36609891971184366,
      "learning_rate": 4.863782051282052e-06,
      "loss": 0.6466,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.3456819325276499,
      "learning_rate": 4.823717948717949e-06,
      "loss": 0.6365,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.3186657302554089,
      "learning_rate": 4.783653846153847e-06,
      "loss": 0.6442,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.29084055713477347,
      "learning_rate": 4.743589743589744e-06,
      "loss": 0.6448,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.3003217749153154,
      "learning_rate": 4.7035256410256415e-06,
      "loss": 0.6466,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.31939854359800846,
      "learning_rate": 4.663461538461539e-06,
      "loss": 0.639,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.30895012076792827,
      "learning_rate": 4.623397435897436e-06,
      "loss": 0.644,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.35585443697630714,
      "learning_rate": 4.583333333333333e-06,
      "loss": 0.6357,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.29878623305709656,
      "learning_rate": 4.543269230769231e-06,
      "loss": 0.6411,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.29730331822347505,
      "learning_rate": 4.503205128205129e-06,
      "loss": 0.6336,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.31243811923009124,
      "learning_rate": 4.463141025641027e-06,
      "loss": 0.6415,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.29584604963611283,
      "learning_rate": 4.423076923076924e-06,
      "loss": 0.6378,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.29488537179203217,
      "learning_rate": 4.3830128205128206e-06,
      "loss": 0.6415,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.32492728331662146,
      "learning_rate": 4.342948717948718e-06,
      "loss": 0.637,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.3194677150235114,
      "learning_rate": 4.302884615384616e-06,
      "loss": 0.6328,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.31627777356793907,
      "learning_rate": 4.262820512820513e-06,
      "loss": 0.6377,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.28760763287042235,
      "learning_rate": 4.222756410256411e-06,
      "loss": 0.6359,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.2989125557638224,
      "learning_rate": 4.182692307692308e-06,
      "loss": 0.633,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.3103751275679,
      "learning_rate": 4.142628205128206e-06,
      "loss": 0.6438,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.30192264686060283,
      "learning_rate": 4.102564102564103e-06,
      "loss": 0.6324,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.2946637494704321,
      "learning_rate": 4.0625000000000005e-06,
      "loss": 0.6305,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.2986657276028727,
      "learning_rate": 4.022435897435898e-06,
      "loss": 0.6303,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.3049145767911953,
      "learning_rate": 3.982371794871795e-06,
      "loss": 0.6308,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.28812002846768286,
      "learning_rate": 3.942307692307692e-06,
      "loss": 0.6275,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.2758928743235643,
      "learning_rate": 3.90224358974359e-06,
      "loss": 0.6333,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.30279539214078177,
      "learning_rate": 3.862179487179488e-06,
      "loss": 0.6404,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.3104427328062765,
      "learning_rate": 3.822115384615385e-06,
      "loss": 0.6322,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.3005469414557822,
      "learning_rate": 3.782051282051282e-06,
      "loss": 0.6259,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.30924601486415865,
      "learning_rate": 3.74198717948718e-06,
      "loss": 0.6382,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.2964094756288656,
      "learning_rate": 3.7019230769230774e-06,
      "loss": 0.6368,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.3090567248841478,
      "learning_rate": 3.6618589743589743e-06,
      "loss": 0.64,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.2838110155015848,
      "learning_rate": 3.621794871794872e-06,
      "loss": 0.6362,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.30496014665438614,
      "learning_rate": 3.5817307692307695e-06,
      "loss": 0.6231,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.31188325289853797,
      "learning_rate": 3.5416666666666673e-06,
      "loss": 0.6362,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.6268377304077148,
      "eval_runtime": 443.6425,
      "eval_samples_per_second": 26.65,
      "eval_steps_per_second": 0.417,
      "step": 438
    },
    {
      "epoch": 1.0034188034188034,
      "grad_norm": 0.29364232405555024,
      "learning_rate": 3.5016025641025643e-06,
      "loss": 0.6497,
      "step": 440
    },
    {
      "epoch": 1.0262108262108263,
      "grad_norm": 0.31981780705379115,
      "learning_rate": 3.4615384615384617e-06,
      "loss": 0.6081,
      "step": 450
    },
    {
      "epoch": 1.049002849002849,
      "grad_norm": 0.3379406051463282,
      "learning_rate": 3.4214743589743595e-06,
      "loss": 0.6017,
      "step": 460
    },
    {
      "epoch": 1.0717948717948718,
      "grad_norm": 0.27328364084706896,
      "learning_rate": 3.381410256410257e-06,
      "loss": 0.6026,
      "step": 470
    },
    {
      "epoch": 1.0945868945868946,
      "grad_norm": 0.28167732967230286,
      "learning_rate": 3.341346153846154e-06,
      "loss": 0.61,
      "step": 480
    },
    {
      "epoch": 1.1173789173789175,
      "grad_norm": 0.3112853102416662,
      "learning_rate": 3.3012820512820517e-06,
      "loss": 0.6151,
      "step": 490
    },
    {
      "epoch": 1.1401709401709401,
      "grad_norm": 0.26768737253395175,
      "learning_rate": 3.261217948717949e-06,
      "loss": 0.6048,
      "step": 500
    },
    {
      "epoch": 1.162962962962963,
      "grad_norm": 0.3015714674832931,
      "learning_rate": 3.2211538461538464e-06,
      "loss": 0.6026,
      "step": 510
    },
    {
      "epoch": 1.1857549857549858,
      "grad_norm": 0.29070810171665257,
      "learning_rate": 3.181089743589744e-06,
      "loss": 0.6084,
      "step": 520
    },
    {
      "epoch": 1.2085470085470085,
      "grad_norm": 0.2804057086061334,
      "learning_rate": 3.141025641025641e-06,
      "loss": 0.6012,
      "step": 530
    },
    {
      "epoch": 1.2313390313390313,
      "grad_norm": 0.3051491611645033,
      "learning_rate": 3.100961538461539e-06,
      "loss": 0.6114,
      "step": 540
    },
    {
      "epoch": 1.2541310541310542,
      "grad_norm": 0.28496795787621204,
      "learning_rate": 3.0608974358974364e-06,
      "loss": 0.608,
      "step": 550
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.2890705705036619,
      "learning_rate": 3.0208333333333334e-06,
      "loss": 0.6094,
      "step": 560
    },
    {
      "epoch": 1.2997150997150997,
      "grad_norm": 0.2821514015007823,
      "learning_rate": 2.980769230769231e-06,
      "loss": 0.6033,
      "step": 570
    },
    {
      "epoch": 1.3225071225071225,
      "grad_norm": 0.26245132615316724,
      "learning_rate": 2.9407051282051285e-06,
      "loss": 0.6018,
      "step": 580
    },
    {
      "epoch": 1.3452991452991454,
      "grad_norm": 0.27788872357165967,
      "learning_rate": 2.900641025641026e-06,
      "loss": 0.6017,
      "step": 590
    },
    {
      "epoch": 1.368091168091168,
      "grad_norm": 0.30663368769607446,
      "learning_rate": 2.8605769230769233e-06,
      "loss": 0.6072,
      "step": 600
    },
    {
      "epoch": 1.390883190883191,
      "grad_norm": 0.2819546196706112,
      "learning_rate": 2.8205128205128207e-06,
      "loss": 0.6073,
      "step": 610
    },
    {
      "epoch": 1.4136752136752135,
      "grad_norm": 0.28474896513932474,
      "learning_rate": 2.780448717948718e-06,
      "loss": 0.6098,
      "step": 620
    },
    {
      "epoch": 1.4364672364672364,
      "grad_norm": 0.28494585228462754,
      "learning_rate": 2.740384615384616e-06,
      "loss": 0.6077,
      "step": 630
    },
    {
      "epoch": 1.4592592592592593,
      "grad_norm": 0.2879015224805682,
      "learning_rate": 2.700320512820513e-06,
      "loss": 0.6025,
      "step": 640
    },
    {
      "epoch": 1.4820512820512821,
      "grad_norm": 0.2976592409984262,
      "learning_rate": 2.6602564102564107e-06,
      "loss": 0.6003,
      "step": 650
    },
    {
      "epoch": 1.504843304843305,
      "grad_norm": 0.27200073619702764,
      "learning_rate": 2.620192307692308e-06,
      "loss": 0.6001,
      "step": 660
    },
    {
      "epoch": 1.5276353276353276,
      "grad_norm": 0.2955439549422962,
      "learning_rate": 2.5801282051282054e-06,
      "loss": 0.6077,
      "step": 670
    },
    {
      "epoch": 1.5504273504273505,
      "grad_norm": 0.2676226289524205,
      "learning_rate": 2.540064102564103e-06,
      "loss": 0.5962,
      "step": 680
    },
    {
      "epoch": 1.573219373219373,
      "grad_norm": 0.31136629575883906,
      "learning_rate": 2.5e-06,
      "loss": 0.6002,
      "step": 690
    },
    {
      "epoch": 1.596011396011396,
      "grad_norm": 0.2772313323471075,
      "learning_rate": 2.4599358974358976e-06,
      "loss": 0.6158,
      "step": 700
    },
    {
      "epoch": 1.6188034188034188,
      "grad_norm": 0.28549595413000944,
      "learning_rate": 2.419871794871795e-06,
      "loss": 0.6027,
      "step": 710
    },
    {
      "epoch": 1.6415954415954417,
      "grad_norm": 0.2933120544993909,
      "learning_rate": 2.3798076923076924e-06,
      "loss": 0.6073,
      "step": 720
    },
    {
      "epoch": 1.6643874643874645,
      "grad_norm": 0.28866735452263864,
      "learning_rate": 2.3397435897435897e-06,
      "loss": 0.6003,
      "step": 730
    },
    {
      "epoch": 1.6871794871794872,
      "grad_norm": 0.29020449596497094,
      "learning_rate": 2.299679487179487e-06,
      "loss": 0.6014,
      "step": 740
    },
    {
      "epoch": 1.7099715099715098,
      "grad_norm": 0.28552651020815345,
      "learning_rate": 2.259615384615385e-06,
      "loss": 0.5986,
      "step": 750
    },
    {
      "epoch": 1.7327635327635327,
      "grad_norm": 0.2882476895056393,
      "learning_rate": 2.2195512820512823e-06,
      "loss": 0.6028,
      "step": 760
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.2907268519578784,
      "learning_rate": 2.1794871794871797e-06,
      "loss": 0.5992,
      "step": 770
    },
    {
      "epoch": 1.7783475783475784,
      "grad_norm": 0.28182550191927,
      "learning_rate": 2.139423076923077e-06,
      "loss": 0.6064,
      "step": 780
    },
    {
      "epoch": 1.8011396011396013,
      "grad_norm": 0.2724647162571741,
      "learning_rate": 2.0993589743589745e-06,
      "loss": 0.6038,
      "step": 790
    },
    {
      "epoch": 1.823931623931624,
      "grad_norm": 0.27721155400507375,
      "learning_rate": 2.059294871794872e-06,
      "loss": 0.5906,
      "step": 800
    },
    {
      "epoch": 1.8467236467236468,
      "grad_norm": 0.291466141079195,
      "learning_rate": 2.0192307692307692e-06,
      "loss": 0.5985,
      "step": 810
    },
    {
      "epoch": 1.8695156695156694,
      "grad_norm": 0.2796038508020198,
      "learning_rate": 1.9791666666666666e-06,
      "loss": 0.5963,
      "step": 820
    },
    {
      "epoch": 1.8923076923076922,
      "grad_norm": 0.27317922594215693,
      "learning_rate": 1.9391025641025644e-06,
      "loss": 0.6,
      "step": 830
    },
    {
      "epoch": 1.915099715099715,
      "grad_norm": 0.28298652617327985,
      "learning_rate": 1.8990384615384616e-06,
      "loss": 0.6047,
      "step": 840
    },
    {
      "epoch": 1.937891737891738,
      "grad_norm": 0.2903891315487511,
      "learning_rate": 1.8589743589743592e-06,
      "loss": 0.6026,
      "step": 850
    },
    {
      "epoch": 1.9606837606837608,
      "grad_norm": 0.28012300347137203,
      "learning_rate": 1.8189102564102564e-06,
      "loss": 0.6038,
      "step": 860
    },
    {
      "epoch": 1.9834757834757835,
      "grad_norm": 0.3035569641972659,
      "learning_rate": 1.778846153846154e-06,
      "loss": 0.6014,
      "step": 870
    },
    {
      "epoch": 1.9994301994301993,
      "eval_loss": 0.621010959148407,
      "eval_runtime": 445.207,
      "eval_samples_per_second": 26.556,
      "eval_steps_per_second": 0.416,
      "step": 877
    },
    {
      "epoch": 2.006837606837607,
      "grad_norm": 0.26768636592085615,
      "learning_rate": 1.7387820512820514e-06,
      "loss": 0.6248,
      "step": 880
    },
    {
      "epoch": 2.0296296296296297,
      "grad_norm": 0.27888200357433934,
      "learning_rate": 1.698717948717949e-06,
      "loss": 0.5721,
      "step": 890
    },
    {
      "epoch": 2.0524216524216525,
      "grad_norm": 0.2881472147576323,
      "learning_rate": 1.6586538461538461e-06,
      "loss": 0.5879,
      "step": 900
    },
    {
      "epoch": 2.0752136752136754,
      "grad_norm": 0.2977603684346802,
      "learning_rate": 1.6185897435897437e-06,
      "loss": 0.5858,
      "step": 910
    },
    {
      "epoch": 2.098005698005698,
      "grad_norm": 0.2781969078934306,
      "learning_rate": 1.5785256410256411e-06,
      "loss": 0.5888,
      "step": 920
    },
    {
      "epoch": 2.1207977207977207,
      "grad_norm": 0.27492645717526487,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 0.5865,
      "step": 930
    },
    {
      "epoch": 2.1435897435897435,
      "grad_norm": 0.2800554861661004,
      "learning_rate": 1.4983974358974359e-06,
      "loss": 0.5811,
      "step": 940
    },
    {
      "epoch": 2.1663817663817664,
      "grad_norm": 0.26985268733531637,
      "learning_rate": 1.4583333333333335e-06,
      "loss": 0.582,
      "step": 950
    },
    {
      "epoch": 2.1891737891737892,
      "grad_norm": 0.2753016907270945,
      "learning_rate": 1.4182692307692309e-06,
      "loss": 0.5869,
      "step": 960
    },
    {
      "epoch": 2.211965811965812,
      "grad_norm": 0.28037267728285564,
      "learning_rate": 1.3782051282051285e-06,
      "loss": 0.5859,
      "step": 970
    },
    {
      "epoch": 2.234757834757835,
      "grad_norm": 0.28436987555383886,
      "learning_rate": 1.3381410256410256e-06,
      "loss": 0.5754,
      "step": 980
    },
    {
      "epoch": 2.2575498575498574,
      "grad_norm": 0.2803550128990695,
      "learning_rate": 1.2980769230769232e-06,
      "loss": 0.5844,
      "step": 990
    },
    {
      "epoch": 2.2803418803418802,
      "grad_norm": 0.2659778635394388,
      "learning_rate": 1.2580128205128206e-06,
      "loss": 0.5845,
      "step": 1000
    },
    {
      "epoch": 2.303133903133903,
      "grad_norm": 0.28140777482551493,
      "learning_rate": 1.217948717948718e-06,
      "loss": 0.5821,
      "step": 1010
    },
    {
      "epoch": 2.325925925925926,
      "grad_norm": 0.2892632291415875,
      "learning_rate": 1.1778846153846154e-06,
      "loss": 0.585,
      "step": 1020
    },
    {
      "epoch": 2.348717948717949,
      "grad_norm": 0.2722036325372003,
      "learning_rate": 1.137820512820513e-06,
      "loss": 0.5864,
      "step": 1030
    },
    {
      "epoch": 2.3715099715099717,
      "grad_norm": 0.26493405372021606,
      "learning_rate": 1.0977564102564104e-06,
      "loss": 0.5839,
      "step": 1040
    },
    {
      "epoch": 2.394301994301994,
      "grad_norm": 0.28850992801768355,
      "learning_rate": 1.0576923076923078e-06,
      "loss": 0.5834,
      "step": 1050
    },
    {
      "epoch": 2.417094017094017,
      "grad_norm": 0.2729847822645752,
      "learning_rate": 1.0176282051282051e-06,
      "loss": 0.5916,
      "step": 1060
    },
    {
      "epoch": 2.43988603988604,
      "grad_norm": 0.26437445495212103,
      "learning_rate": 9.775641025641027e-07,
      "loss": 0.5947,
      "step": 1070
    },
    {
      "epoch": 2.4626780626780627,
      "grad_norm": 0.2742367213187613,
      "learning_rate": 9.375000000000001e-07,
      "loss": 0.59,
      "step": 1080
    },
    {
      "epoch": 2.4854700854700855,
      "grad_norm": 0.2657954288218422,
      "learning_rate": 8.974358974358975e-07,
      "loss": 0.5872,
      "step": 1090
    },
    {
      "epoch": 2.5082621082621084,
      "grad_norm": 0.30095641226018094,
      "learning_rate": 8.573717948717949e-07,
      "loss": 0.5939,
      "step": 1100
    },
    {
      "epoch": 2.5310541310541312,
      "grad_norm": 0.2662148333596707,
      "learning_rate": 8.173076923076924e-07,
      "loss": 0.5868,
      "step": 1110
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.2657177782263582,
      "learning_rate": 7.772435897435898e-07,
      "loss": 0.5851,
      "step": 1120
    },
    {
      "epoch": 2.5766381766381765,
      "grad_norm": 0.2718615976628775,
      "learning_rate": 7.371794871794873e-07,
      "loss": 0.5844,
      "step": 1130
    },
    {
      "epoch": 2.5994301994301994,
      "grad_norm": 0.2678629053671283,
      "learning_rate": 6.971153846153847e-07,
      "loss": 0.584,
      "step": 1140
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.2773427724130542,
      "learning_rate": 6.570512820512821e-07,
      "loss": 0.5842,
      "step": 1150
    },
    {
      "epoch": 2.645014245014245,
      "grad_norm": 0.27422295693317505,
      "learning_rate": 6.169871794871795e-07,
      "loss": 0.5849,
      "step": 1160
    },
    {
      "epoch": 2.667806267806268,
      "grad_norm": 0.2717927046678724,
      "learning_rate": 5.76923076923077e-07,
      "loss": 0.5883,
      "step": 1170
    },
    {
      "epoch": 2.690598290598291,
      "grad_norm": 0.2698950926558539,
      "learning_rate": 5.368589743589744e-07,
      "loss": 0.5832,
      "step": 1180
    },
    {
      "epoch": 2.7133903133903132,
      "grad_norm": 0.26157546217035227,
      "learning_rate": 4.967948717948718e-07,
      "loss": 0.584,
      "step": 1190
    },
    {
      "epoch": 2.736182336182336,
      "grad_norm": 0.2668593347862196,
      "learning_rate": 4.5673076923076923e-07,
      "loss": 0.5874,
      "step": 1200
    },
    {
      "epoch": 2.758974358974359,
      "grad_norm": 0.2635777288568656,
      "learning_rate": 4.1666666666666667e-07,
      "loss": 0.5906,
      "step": 1210
    },
    {
      "epoch": 2.781766381766382,
      "grad_norm": 0.2616417705187902,
      "learning_rate": 3.766025641025641e-07,
      "loss": 0.5803,
      "step": 1220
    },
    {
      "epoch": 2.8045584045584047,
      "grad_norm": 0.2547272016384533,
      "learning_rate": 3.3653846153846154e-07,
      "loss": 0.5788,
      "step": 1230
    },
    {
      "epoch": 2.827350427350427,
      "grad_norm": 0.2684812952212607,
      "learning_rate": 2.96474358974359e-07,
      "loss": 0.5937,
      "step": 1240
    },
    {
      "epoch": 2.8501424501424504,
      "grad_norm": 0.2598663155219884,
      "learning_rate": 2.564102564102564e-07,
      "loss": 0.5906,
      "step": 1250
    },
    {
      "epoch": 2.872934472934473,
      "grad_norm": 0.26617491206629446,
      "learning_rate": 2.1634615384615386e-07,
      "loss": 0.5877,
      "step": 1260
    },
    {
      "epoch": 2.8957264957264957,
      "grad_norm": 0.2661834047466182,
      "learning_rate": 1.762820512820513e-07,
      "loss": 0.5885,
      "step": 1270
    },
    {
      "epoch": 2.9185185185185185,
      "grad_norm": 0.26318388069962756,
      "learning_rate": 1.3621794871794873e-07,
      "loss": 0.5786,
      "step": 1280
    },
    {
      "epoch": 2.9413105413105414,
      "grad_norm": 0.2662608166458492,
      "learning_rate": 9.615384615384617e-08,
      "loss": 0.5786,
      "step": 1290
    },
    {
      "epoch": 2.9641025641025642,
      "grad_norm": 0.2695214709593339,
      "learning_rate": 5.6089743589743595e-08,
      "loss": 0.5799,
      "step": 1300
    },
    {
      "epoch": 2.9868945868945866,
      "grad_norm": 0.27157379597305825,
      "learning_rate": 1.6025641025641026e-08,
      "loss": 0.5901,
      "step": 1310
    },
    {
      "epoch": 2.996011396011396,
      "eval_loss": 0.6206214427947998,
      "eval_runtime": 445.449,
      "eval_samples_per_second": 26.542,
      "eval_steps_per_second": 0.415,
      "step": 1314
    },
    {
      "epoch": 2.996011396011396,
      "step": 1314,
      "total_flos": 2755219238682624.0,
      "train_loss": 0.6141638697735976,
      "train_runtime": 70696.0648,
      "train_samples_per_second": 9.532,
      "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
}