{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1722,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017421602787456445,
      "grad_norm": 1.110547889420809,
      "learning_rate": 5e-06,
      "loss": 0.8085,
      "step": 10
    },
    {
      "epoch": 0.03484320557491289,
      "grad_norm": 0.9516650393814576,
      "learning_rate": 5e-06,
      "loss": 0.7273,
      "step": 20
    },
    {
      "epoch": 0.05226480836236934,
      "grad_norm": 0.8745560758252257,
      "learning_rate": 5e-06,
      "loss": 0.7151,
      "step": 30
    },
    {
      "epoch": 0.06968641114982578,
      "grad_norm": 0.6458692027569163,
      "learning_rate": 5e-06,
      "loss": 0.7042,
      "step": 40
    },
    {
      "epoch": 0.08710801393728224,
      "grad_norm": 0.6419702080069286,
      "learning_rate": 5e-06,
      "loss": 0.6797,
      "step": 50
    },
    {
      "epoch": 0.10452961672473868,
      "grad_norm": 1.3167787941292113,
      "learning_rate": 5e-06,
      "loss": 0.6939,
      "step": 60
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 0.5165069959452926,
      "learning_rate": 5e-06,
      "loss": 0.6731,
      "step": 70
    },
    {
      "epoch": 0.13937282229965156,
      "grad_norm": 0.6494172258411438,
      "learning_rate": 5e-06,
      "loss": 0.6653,
      "step": 80
    },
    {
      "epoch": 0.156794425087108,
      "grad_norm": 0.8433361988376273,
      "learning_rate": 5e-06,
      "loss": 0.6834,
      "step": 90
    },
    {
      "epoch": 0.17421602787456447,
      "grad_norm": 0.7333617572332245,
      "learning_rate": 5e-06,
      "loss": 0.674,
      "step": 100
    },
    {
      "epoch": 0.1916376306620209,
      "grad_norm": 0.46328020438675316,
      "learning_rate": 5e-06,
      "loss": 0.6705,
      "step": 110
    },
    {
      "epoch": 0.20905923344947736,
      "grad_norm": 0.5375878274323563,
      "learning_rate": 5e-06,
      "loss": 0.6546,
      "step": 120
    },
    {
      "epoch": 0.2264808362369338,
      "grad_norm": 0.6043348556726694,
      "learning_rate": 5e-06,
      "loss": 0.6506,
      "step": 130
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.4508554439777698,
      "learning_rate": 5e-06,
      "loss": 0.6536,
      "step": 140
    },
    {
      "epoch": 0.2613240418118467,
      "grad_norm": 1.1359138470696808,
      "learning_rate": 5e-06,
      "loss": 0.638,
      "step": 150
    },
    {
      "epoch": 0.2787456445993031,
      "grad_norm": 0.5757321381081676,
      "learning_rate": 5e-06,
      "loss": 0.6492,
      "step": 160
    },
    {
      "epoch": 0.2961672473867596,
      "grad_norm": 0.49845234216314765,
      "learning_rate": 5e-06,
      "loss": 0.6481,
      "step": 170
    },
    {
      "epoch": 0.313588850174216,
      "grad_norm": 0.4885975758468272,
      "learning_rate": 5e-06,
      "loss": 0.6445,
      "step": 180
    },
    {
      "epoch": 0.3310104529616725,
      "grad_norm": 0.46363877509236,
      "learning_rate": 5e-06,
      "loss": 0.6437,
      "step": 190
    },
    {
      "epoch": 0.34843205574912894,
      "grad_norm": 0.4685718300832952,
      "learning_rate": 5e-06,
      "loss": 0.6386,
      "step": 200
    },
    {
      "epoch": 0.36585365853658536,
      "grad_norm": 0.5605596050023267,
      "learning_rate": 5e-06,
      "loss": 0.6507,
      "step": 210
    },
    {
      "epoch": 0.3832752613240418,
      "grad_norm": 0.6403424736477891,
      "learning_rate": 5e-06,
      "loss": 0.6418,
      "step": 220
    },
    {
      "epoch": 0.40069686411149824,
      "grad_norm": 0.5838158484945601,
      "learning_rate": 5e-06,
      "loss": 0.6493,
      "step": 230
    },
    {
      "epoch": 0.4181184668989547,
      "grad_norm": 0.45330751179903367,
      "learning_rate": 5e-06,
      "loss": 0.6498,
      "step": 240
    },
    {
      "epoch": 0.4355400696864111,
      "grad_norm": 0.47780598447174244,
      "learning_rate": 5e-06,
      "loss": 0.6359,
      "step": 250
    },
    {
      "epoch": 0.4529616724738676,
      "grad_norm": 0.4754778849361075,
      "learning_rate": 5e-06,
      "loss": 0.6402,
      "step": 260
    },
    {
      "epoch": 0.47038327526132406,
      "grad_norm": 0.9267353139931963,
      "learning_rate": 5e-06,
      "loss": 0.6453,
      "step": 270
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 1.09959569850648,
      "learning_rate": 5e-06,
      "loss": 0.6381,
      "step": 280
    },
    {
      "epoch": 0.5052264808362369,
      "grad_norm": 0.46907276389959596,
      "learning_rate": 5e-06,
      "loss": 0.6142,
      "step": 290
    },
    {
      "epoch": 0.5226480836236934,
      "grad_norm": 0.9009500821986945,
      "learning_rate": 5e-06,
      "loss": 0.6349,
      "step": 300
    },
    {
      "epoch": 0.5400696864111498,
      "grad_norm": 0.8732778985630532,
      "learning_rate": 5e-06,
      "loss": 0.633,
      "step": 310
    },
    {
      "epoch": 0.5574912891986062,
      "grad_norm": 0.5330855012377655,
      "learning_rate": 5e-06,
      "loss": 0.6292,
      "step": 320
    },
    {
      "epoch": 0.5749128919860628,
      "grad_norm": 0.5021412884291475,
      "learning_rate": 5e-06,
      "loss": 0.6253,
      "step": 330
    },
    {
      "epoch": 0.5923344947735192,
      "grad_norm": 0.5447288950929059,
      "learning_rate": 5e-06,
      "loss": 0.6308,
      "step": 340
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 0.7644080552686335,
      "learning_rate": 5e-06,
      "loss": 0.6267,
      "step": 350
    },
    {
      "epoch": 0.627177700348432,
      "grad_norm": 0.4607717863440372,
      "learning_rate": 5e-06,
      "loss": 0.637,
      "step": 360
    },
    {
      "epoch": 0.6445993031358885,
      "grad_norm": 0.6059522443076883,
      "learning_rate": 5e-06,
      "loss": 0.6276,
      "step": 370
    },
    {
      "epoch": 0.662020905923345,
      "grad_norm": 0.6368838367327173,
      "learning_rate": 5e-06,
      "loss": 0.6227,
      "step": 380
    },
    {
      "epoch": 0.6794425087108014,
      "grad_norm": 0.4571682914981839,
      "learning_rate": 5e-06,
      "loss": 0.6204,
      "step": 390
    },
    {
      "epoch": 0.6968641114982579,
      "grad_norm": 0.7704076665510348,
      "learning_rate": 5e-06,
      "loss": 0.6332,
      "step": 400
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.48016934744783224,
      "learning_rate": 5e-06,
      "loss": 0.6317,
      "step": 410
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 0.4659861774424128,
      "learning_rate": 5e-06,
      "loss": 0.614,
      "step": 420
    },
    {
      "epoch": 0.7491289198606271,
      "grad_norm": 0.5709628311962424,
      "learning_rate": 5e-06,
      "loss": 0.617,
      "step": 430
    },
    {
      "epoch": 0.7665505226480837,
      "grad_norm": 0.9275541597160887,
      "learning_rate": 5e-06,
      "loss": 0.6259,
      "step": 440
    },
    {
      "epoch": 0.7839721254355401,
      "grad_norm": 0.4590863644330183,
      "learning_rate": 5e-06,
      "loss": 0.6432,
      "step": 450
    },
    {
      "epoch": 0.8013937282229965,
      "grad_norm": 0.44311113231679206,
      "learning_rate": 5e-06,
      "loss": 0.6325,
      "step": 460
    },
    {
      "epoch": 0.818815331010453,
      "grad_norm": 0.42872958673136763,
      "learning_rate": 5e-06,
      "loss": 0.6254,
      "step": 470
    },
    {
      "epoch": 0.8362369337979094,
      "grad_norm": 0.6968494949424339,
      "learning_rate": 5e-06,
      "loss": 0.6282,
      "step": 480
    },
    {
      "epoch": 0.8536585365853658,
      "grad_norm": 0.475991569929859,
      "learning_rate": 5e-06,
      "loss": 0.6104,
      "step": 490
    },
    {
      "epoch": 0.8710801393728222,
      "grad_norm": 0.4036764356634414,
      "learning_rate": 5e-06,
      "loss": 0.6192,
      "step": 500
    },
    {
      "epoch": 0.8885017421602788,
      "grad_norm": 0.4800314428435892,
      "learning_rate": 5e-06,
      "loss": 0.6226,
      "step": 510
    },
    {
      "epoch": 0.9059233449477352,
      "grad_norm": 0.4448196930678713,
      "learning_rate": 5e-06,
      "loss": 0.6141,
      "step": 520
    },
    {
      "epoch": 0.9233449477351916,
      "grad_norm": 0.43823469299056167,
      "learning_rate": 5e-06,
      "loss": 0.6137,
      "step": 530
    },
    {
      "epoch": 0.9407665505226481,
      "grad_norm": 0.46401352050703015,
      "learning_rate": 5e-06,
      "loss": 0.6155,
      "step": 540
    },
    {
      "epoch": 0.9581881533101045,
      "grad_norm": 0.4741335427712111,
      "learning_rate": 5e-06,
      "loss": 0.6239,
      "step": 550
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.5404449413086233,
      "learning_rate": 5e-06,
      "loss": 0.6228,
      "step": 560
    },
    {
      "epoch": 0.9930313588850174,
      "grad_norm": 0.4865700073464584,
      "learning_rate": 5e-06,
      "loss": 0.6057,
      "step": 570
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6242489218711853,
      "eval_runtime": 156.3164,
      "eval_samples_per_second": 98.902,
      "eval_steps_per_second": 0.39,
      "step": 574
    },
    {
      "epoch": 1.0104529616724738,
      "grad_norm": 0.49999642055125576,
      "learning_rate": 5e-06,
      "loss": 0.5959,
      "step": 580
    },
    {
      "epoch": 1.0278745644599303,
      "grad_norm": 0.45102982348932047,
      "learning_rate": 5e-06,
      "loss": 0.5783,
      "step": 590
    },
    {
      "epoch": 1.0452961672473868,
      "grad_norm": 0.4675746175963686,
      "learning_rate": 5e-06,
      "loss": 0.5907,
      "step": 600
    },
    {
      "epoch": 1.0627177700348431,
      "grad_norm": 0.4332204857821093,
      "learning_rate": 5e-06,
      "loss": 0.5721,
      "step": 610
    },
    {
      "epoch": 1.0801393728222997,
      "grad_norm": 0.46797084979476816,
      "learning_rate": 5e-06,
      "loss": 0.5728,
      "step": 620
    },
    {
      "epoch": 1.0975609756097562,
      "grad_norm": 0.45462105008725134,
      "learning_rate": 5e-06,
      "loss": 0.5766,
      "step": 630
    },
    {
      "epoch": 1.1149825783972125,
      "grad_norm": 0.45583632727945284,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 640
    },
    {
      "epoch": 1.132404181184669,
      "grad_norm": 0.6045690088290018,
      "learning_rate": 5e-06,
      "loss": 0.5839,
      "step": 650
    },
    {
      "epoch": 1.1498257839721253,
      "grad_norm": 0.4772407436839459,
      "learning_rate": 5e-06,
      "loss": 0.5745,
      "step": 660
    },
    {
      "epoch": 1.1672473867595818,
      "grad_norm": 0.7134135897555454,
      "learning_rate": 5e-06,
      "loss": 0.5763,
      "step": 670
    },
    {
      "epoch": 1.1846689895470384,
      "grad_norm": 0.5626507275472277,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 680
    },
    {
      "epoch": 1.202090592334495,
      "grad_norm": 0.4587849239706485,
      "learning_rate": 5e-06,
      "loss": 0.5975,
      "step": 690
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": 0.45602175911022613,
      "learning_rate": 5e-06,
      "loss": 0.5727,
      "step": 700
    },
    {
      "epoch": 1.2369337979094077,
      "grad_norm": 0.4760989235025255,
      "learning_rate": 5e-06,
      "loss": 0.5743,
      "step": 710
    },
    {
      "epoch": 1.254355400696864,
      "grad_norm": 0.57636457602915,
      "learning_rate": 5e-06,
      "loss": 0.5723,
      "step": 720
    },
    {
      "epoch": 1.2717770034843205,
      "grad_norm": 0.7070463930124464,
      "learning_rate": 5e-06,
      "loss": 0.5734,
      "step": 730
    },
    {
      "epoch": 1.289198606271777,
      "grad_norm": 0.451570248773914,
      "learning_rate": 5e-06,
      "loss": 0.5654,
      "step": 740
    },
    {
      "epoch": 1.3066202090592334,
      "grad_norm": 0.4634040338505886,
      "learning_rate": 5e-06,
      "loss": 0.5734,
      "step": 750
    },
    {
      "epoch": 1.32404181184669,
      "grad_norm": 0.461184295216135,
      "learning_rate": 5e-06,
      "loss": 0.5659,
      "step": 760
    },
    {
      "epoch": 1.3414634146341464,
      "grad_norm": 0.5502438318822999,
      "learning_rate": 5e-06,
      "loss": 0.5638,
      "step": 770
    },
    {
      "epoch": 1.3588850174216027,
      "grad_norm": 0.40334764475120544,
      "learning_rate": 5e-06,
      "loss": 0.5741,
      "step": 780
    },
    {
      "epoch": 1.3763066202090593,
      "grad_norm": 0.46619326588491156,
      "learning_rate": 5e-06,
      "loss": 0.5816,
      "step": 790
    },
    {
      "epoch": 1.3937282229965158,
      "grad_norm": 0.43450365905550786,
      "learning_rate": 5e-06,
      "loss": 0.5879,
      "step": 800
    },
    {
      "epoch": 1.411149825783972,
      "grad_norm": 0.4491332694126357,
      "learning_rate": 5e-06,
      "loss": 0.5834,
      "step": 810
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.4492632982117168,
      "learning_rate": 5e-06,
      "loss": 0.5704,
      "step": 820
    },
    {
      "epoch": 1.445993031358885,
      "grad_norm": 0.48204516908878015,
      "learning_rate": 5e-06,
      "loss": 0.5726,
      "step": 830
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 0.4451434847610245,
      "learning_rate": 5e-06,
      "loss": 0.5725,
      "step": 840
    },
    {
      "epoch": 1.480836236933798,
      "grad_norm": 0.4817077921497448,
      "learning_rate": 5e-06,
      "loss": 0.578,
      "step": 850
    },
    {
      "epoch": 1.4982578397212545,
      "grad_norm": 0.4114565463440688,
      "learning_rate": 5e-06,
      "loss": 0.5756,
      "step": 860
    },
    {
      "epoch": 1.5156794425087108,
      "grad_norm": 0.4364153090393298,
      "learning_rate": 5e-06,
      "loss": 0.5781,
      "step": 870
    },
    {
      "epoch": 1.533101045296167,
      "grad_norm": 0.4641250735638994,
      "learning_rate": 5e-06,
      "loss": 0.5858,
      "step": 880
    },
    {
      "epoch": 1.5505226480836236,
      "grad_norm": 0.5414804208775645,
      "learning_rate": 5e-06,
      "loss": 0.576,
      "step": 890
    },
    {
      "epoch": 1.5679442508710801,
      "grad_norm": 0.4046063470124716,
      "learning_rate": 5e-06,
      "loss": 0.5764,
      "step": 900
    },
    {
      "epoch": 1.5853658536585367,
      "grad_norm": 0.5021694200790203,
      "learning_rate": 5e-06,
      "loss": 0.5832,
      "step": 910
    },
    {
      "epoch": 1.6027874564459932,
      "grad_norm": 0.44359324558365465,
      "learning_rate": 5e-06,
      "loss": 0.5702,
      "step": 920
    },
    {
      "epoch": 1.6202090592334495,
      "grad_norm": 0.4590082845753106,
      "learning_rate": 5e-06,
      "loss": 0.5702,
      "step": 930
    },
    {
      "epoch": 1.6376306620209058,
      "grad_norm": 0.42340672053613443,
      "learning_rate": 5e-06,
      "loss": 0.5788,
      "step": 940
    },
    {
      "epoch": 1.6550522648083623,
      "grad_norm": 0.4144352252936342,
      "learning_rate": 5e-06,
      "loss": 0.5766,
      "step": 950
    },
    {
      "epoch": 1.6724738675958188,
      "grad_norm": 0.4171029941084573,
      "learning_rate": 5e-06,
      "loss": 0.5695,
      "step": 960
    },
    {
      "epoch": 1.6898954703832754,
      "grad_norm": 0.43911657202438914,
      "learning_rate": 5e-06,
      "loss": 0.5661,
      "step": 970
    },
    {
      "epoch": 1.7073170731707317,
      "grad_norm": 0.4114986035010171,
      "learning_rate": 5e-06,
      "loss": 0.571,
      "step": 980
    },
    {
      "epoch": 1.7247386759581882,
      "grad_norm": 0.43109782590499385,
      "learning_rate": 5e-06,
      "loss": 0.5747,
      "step": 990
    },
    {
      "epoch": 1.7421602787456445,
      "grad_norm": 0.4565580100991871,
      "learning_rate": 5e-06,
      "loss": 0.5771,
      "step": 1000
    },
    {
      "epoch": 1.759581881533101,
      "grad_norm": 0.4138828268586911,
      "learning_rate": 5e-06,
      "loss": 0.5629,
      "step": 1010
    },
    {
      "epoch": 1.7770034843205575,
      "grad_norm": 0.4542995316054866,
      "learning_rate": 5e-06,
      "loss": 0.5856,
      "step": 1020
    },
    {
      "epoch": 1.794425087108014,
      "grad_norm": 0.6622604112941458,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 1030
    },
    {
      "epoch": 1.8118466898954704,
      "grad_norm": 0.4507517659371942,
      "learning_rate": 5e-06,
      "loss": 0.5774,
      "step": 1040
    },
    {
      "epoch": 1.8292682926829267,
      "grad_norm": 0.4309645347763417,
      "learning_rate": 5e-06,
      "loss": 0.5704,
      "step": 1050
    },
    {
      "epoch": 1.8466898954703832,
      "grad_norm": 0.41185890423116756,
      "learning_rate": 5e-06,
      "loss": 0.5734,
      "step": 1060
    },
    {
      "epoch": 1.8641114982578397,
      "grad_norm": 0.4455851719114888,
      "learning_rate": 5e-06,
      "loss": 0.5747,
      "step": 1070
    },
    {
      "epoch": 1.8815331010452963,
      "grad_norm": 0.41686045633860264,
      "learning_rate": 5e-06,
      "loss": 0.5771,
      "step": 1080
    },
    {
      "epoch": 1.8989547038327528,
      "grad_norm": 0.4333938820779194,
      "learning_rate": 5e-06,
      "loss": 0.579,
      "step": 1090
    },
    {
      "epoch": 1.916376306620209,
      "grad_norm": 0.4045207725207787,
      "learning_rate": 5e-06,
      "loss": 0.5758,
      "step": 1100
    },
    {
      "epoch": 1.9337979094076654,
      "grad_norm": 0.4520222740004976,
      "learning_rate": 5e-06,
      "loss": 0.5563,
      "step": 1110
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 0.4311997583086096,
      "learning_rate": 5e-06,
      "loss": 0.5681,
      "step": 1120
    },
    {
      "epoch": 1.9686411149825784,
      "grad_norm": 0.4383316797763638,
      "learning_rate": 5e-06,
      "loss": 0.5819,
      "step": 1130
    },
    {
      "epoch": 1.986062717770035,
      "grad_norm": 0.5477336634704406,
      "learning_rate": 5e-06,
      "loss": 0.5711,
      "step": 1140
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6141585111618042,
      "eval_runtime": 156.1142,
      "eval_samples_per_second": 99.03,
      "eval_steps_per_second": 0.391,
      "step": 1148
    },
    {
      "epoch": 2.0034843205574915,
      "grad_norm": 0.4640944945247334,
      "learning_rate": 5e-06,
      "loss": 0.5571,
      "step": 1150
    },
    {
      "epoch": 2.0209059233449476,
      "grad_norm": 0.45843359238558995,
      "learning_rate": 5e-06,
      "loss": 0.5249,
      "step": 1160
    },
    {
      "epoch": 2.038327526132404,
      "grad_norm": 0.4837328490077125,
      "learning_rate": 5e-06,
      "loss": 0.5282,
      "step": 1170
    },
    {
      "epoch": 2.0557491289198606,
      "grad_norm": 0.44590774801900834,
      "learning_rate": 5e-06,
      "loss": 0.5337,
      "step": 1180
    },
    {
      "epoch": 2.073170731707317,
      "grad_norm": 0.43363076292724995,
      "learning_rate": 5e-06,
      "loss": 0.5374,
      "step": 1190
    },
    {
      "epoch": 2.0905923344947737,
      "grad_norm": 0.4931511449549238,
      "learning_rate": 5e-06,
      "loss": 0.5309,
      "step": 1200
    },
    {
      "epoch": 2.10801393728223,
      "grad_norm": 0.4504251344307032,
      "learning_rate": 5e-06,
      "loss": 0.5271,
      "step": 1210
    },
    {
      "epoch": 2.1254355400696863,
      "grad_norm": 0.49526543085134606,
      "learning_rate": 5e-06,
      "loss": 0.5319,
      "step": 1220
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.4677844909297682,
      "learning_rate": 5e-06,
      "loss": 0.5306,
      "step": 1230
    },
    {
      "epoch": 2.1602787456445993,
      "grad_norm": 0.47260212803851326,
      "learning_rate": 5e-06,
      "loss": 0.5228,
      "step": 1240
    },
    {
      "epoch": 2.177700348432056,
      "grad_norm": 0.5490671664415253,
      "learning_rate": 5e-06,
      "loss": 0.5276,
      "step": 1250
    },
    {
      "epoch": 2.1951219512195124,
      "grad_norm": 0.4780364714560436,
      "learning_rate": 5e-06,
      "loss": 0.5307,
      "step": 1260
    },
    {
      "epoch": 2.2125435540069684,
      "grad_norm": 0.44095382556774654,
      "learning_rate": 5e-06,
      "loss": 0.5273,
      "step": 1270
    },
    {
      "epoch": 2.229965156794425,
      "grad_norm": 0.471163066518852,
      "learning_rate": 5e-06,
      "loss": 0.5095,
      "step": 1280
    },
    {
      "epoch": 2.2473867595818815,
      "grad_norm": 0.4509784260620687,
      "learning_rate": 5e-06,
      "loss": 0.525,
      "step": 1290
    },
    {
      "epoch": 2.264808362369338,
      "grad_norm": 0.42926159657173546,
      "learning_rate": 5e-06,
      "loss": 0.5254,
      "step": 1300
    },
    {
      "epoch": 2.2822299651567945,
      "grad_norm": 0.47746501662453417,
      "learning_rate": 5e-06,
      "loss": 0.5229,
      "step": 1310
    },
    {
      "epoch": 2.2996515679442506,
      "grad_norm": 0.4747495543682741,
      "learning_rate": 5e-06,
      "loss": 0.5259,
      "step": 1320
    },
    {
      "epoch": 2.317073170731707,
      "grad_norm": 0.5228901131403929,
      "learning_rate": 5e-06,
      "loss": 0.5243,
      "step": 1330
    },
    {
      "epoch": 2.3344947735191637,
      "grad_norm": 0.4834167699517272,
      "learning_rate": 5e-06,
      "loss": 0.5306,
      "step": 1340
    },
    {
      "epoch": 2.35191637630662,
      "grad_norm": 0.45707310674276885,
      "learning_rate": 5e-06,
      "loss": 0.5276,
      "step": 1350
    },
    {
      "epoch": 2.3693379790940767,
      "grad_norm": 0.47685998083437814,
      "learning_rate": 5e-06,
      "loss": 0.5312,
      "step": 1360
    },
    {
      "epoch": 2.3867595818815333,
      "grad_norm": 0.47877017672465005,
      "learning_rate": 5e-06,
      "loss": 0.5274,
      "step": 1370
    },
    {
      "epoch": 2.40418118466899,
      "grad_norm": 0.5258496984168791,
      "learning_rate": 5e-06,
      "loss": 0.5226,
      "step": 1380
    },
    {
      "epoch": 2.421602787456446,
      "grad_norm": 0.47709678060118926,
      "learning_rate": 5e-06,
      "loss": 0.5189,
      "step": 1390
    },
    {
      "epoch": 2.4390243902439024,
      "grad_norm": 0.581254404109644,
      "learning_rate": 5e-06,
      "loss": 0.54,
      "step": 1400
    },
    {
      "epoch": 2.456445993031359,
      "grad_norm": 0.43351552520462094,
      "learning_rate": 5e-06,
      "loss": 0.5345,
      "step": 1410
    },
    {
      "epoch": 2.4738675958188154,
      "grad_norm": 0.4485068008247544,
      "learning_rate": 5e-06,
      "loss": 0.5361,
      "step": 1420
    },
    {
      "epoch": 2.491289198606272,
      "grad_norm": 0.4729416207097551,
      "learning_rate": 5e-06,
      "loss": 0.5351,
      "step": 1430
    },
    {
      "epoch": 2.508710801393728,
      "grad_norm": 0.44072110157252653,
      "learning_rate": 5e-06,
      "loss": 0.5294,
      "step": 1440
    },
    {
      "epoch": 2.5261324041811846,
      "grad_norm": 0.5219007442544961,
      "learning_rate": 5e-06,
      "loss": 0.5238,
      "step": 1450
    },
    {
      "epoch": 2.543554006968641,
      "grad_norm": 0.4809656167510028,
      "learning_rate": 5e-06,
      "loss": 0.5288,
      "step": 1460
    },
    {
      "epoch": 2.5609756097560976,
      "grad_norm": 0.4531184946595288,
      "learning_rate": 5e-06,
      "loss": 0.536,
      "step": 1470
    },
    {
      "epoch": 2.578397212543554,
      "grad_norm": 0.48164003860440047,
      "learning_rate": 5e-06,
      "loss": 0.5324,
      "step": 1480
    },
    {
      "epoch": 2.59581881533101,
      "grad_norm": 0.4758292139458944,
      "learning_rate": 5e-06,
      "loss": 0.5133,
      "step": 1490
    },
    {
      "epoch": 2.6132404181184667,
      "grad_norm": 0.4634797349634793,
      "learning_rate": 5e-06,
      "loss": 0.5295,
      "step": 1500
    },
    {
      "epoch": 2.6306620209059233,
      "grad_norm": 0.47375952821313455,
      "learning_rate": 5e-06,
      "loss": 0.5273,
      "step": 1510
    },
    {
      "epoch": 2.64808362369338,
      "grad_norm": 0.4441843444201693,
      "learning_rate": 5e-06,
      "loss": 0.5334,
      "step": 1520
    },
    {
      "epoch": 2.6655052264808363,
      "grad_norm": 0.42211766638465,
      "learning_rate": 5e-06,
      "loss": 0.5138,
      "step": 1530
    },
    {
      "epoch": 2.682926829268293,
      "grad_norm": 0.48817131427198845,
      "learning_rate": 5e-06,
      "loss": 0.5134,
      "step": 1540
    },
    {
      "epoch": 2.7003484320557494,
      "grad_norm": 0.45942488735176895,
      "learning_rate": 5e-06,
      "loss": 0.5361,
      "step": 1550
    },
    {
      "epoch": 2.7177700348432055,
      "grad_norm": 0.4854175238598141,
      "learning_rate": 5e-06,
      "loss": 0.5394,
      "step": 1560
    },
    {
      "epoch": 2.735191637630662,
      "grad_norm": 0.4604289027255158,
      "learning_rate": 5e-06,
      "loss": 0.5187,
      "step": 1570
    },
    {
      "epoch": 2.7526132404181185,
      "grad_norm": 0.4936790258884402,
      "learning_rate": 5e-06,
      "loss": 0.5246,
      "step": 1580
    },
    {
      "epoch": 2.770034843205575,
      "grad_norm": 0.541536408959734,
      "learning_rate": 5e-06,
      "loss": 0.5278,
      "step": 1590
    },
    {
      "epoch": 2.7874564459930316,
      "grad_norm": 0.484918416204369,
      "learning_rate": 5e-06,
      "loss": 0.5382,
      "step": 1600
    },
    {
      "epoch": 2.8048780487804876,
      "grad_norm": 0.4885761374101617,
      "learning_rate": 5e-06,
      "loss": 0.533,
      "step": 1610
    },
    {
      "epoch": 2.822299651567944,
      "grad_norm": 0.4349789229036019,
      "learning_rate": 5e-06,
      "loss": 0.5388,
      "step": 1620
    },
    {
      "epoch": 2.8397212543554007,
      "grad_norm": 0.4314276877403793,
      "learning_rate": 5e-06,
      "loss": 0.5391,
      "step": 1630
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.43396532487130346,
      "learning_rate": 5e-06,
      "loss": 0.5302,
      "step": 1640
    },
    {
      "epoch": 2.8745644599303137,
      "grad_norm": 0.43625746208041316,
      "learning_rate": 5e-06,
      "loss": 0.5275,
      "step": 1650
    },
    {
      "epoch": 2.89198606271777,
      "grad_norm": 0.4646206916137346,
      "learning_rate": 5e-06,
      "loss": 0.5209,
      "step": 1660
    },
    {
      "epoch": 2.9094076655052263,
      "grad_norm": 0.4840563025343255,
      "learning_rate": 5e-06,
      "loss": 0.5246,
      "step": 1670
    },
    {
      "epoch": 2.926829268292683,
      "grad_norm": 0.45066810285940856,
      "learning_rate": 5e-06,
      "loss": 0.5318,
      "step": 1680
    },
    {
      "epoch": 2.9442508710801394,
      "grad_norm": 0.46846871284532293,
      "learning_rate": 5e-06,
      "loss": 0.5324,
      "step": 1690
    },
    {
      "epoch": 2.961672473867596,
      "grad_norm": 0.5421178557930114,
      "learning_rate": 5e-06,
      "loss": 0.5317,
      "step": 1700
    },
    {
      "epoch": 2.979094076655052,
      "grad_norm": 0.44573049149554844,
      "learning_rate": 5e-06,
      "loss": 0.5284,
      "step": 1710
    },
    {
      "epoch": 2.996515679442509,
      "grad_norm": 0.4720545406402456,
      "learning_rate": 5e-06,
      "loss": 0.5286,
      "step": 1720
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6146459579467773,
      "eval_runtime": 156.0276,
      "eval_samples_per_second": 99.085,
      "eval_steps_per_second": 0.391,
      "step": 1722
    },
    {
      "epoch": 3.0,
      "step": 1722,
      "total_flos": 2883576618024960.0,
      "train_loss": 0.5825082723410426,
      "train_runtime": 26219.2762,
      "train_samples_per_second": 33.609,
      "train_steps_per_second": 0.066
    }
  ],
  "logging_steps": 10,
  "max_steps": 1722,
  "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": 2883576618024960.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}