{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.22878168438266558,
  "eval_steps": 500,
  "global_step": 2798,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008176614881439084,
      "grad_norm": 10.534998893737793,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 2.2924,
      "step": 10
    },
    {
      "epoch": 0.001635322976287817,
      "grad_norm": 6.318049430847168,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 2.3794,
      "step": 20
    },
    {
      "epoch": 0.0024529844644317253,
      "grad_norm": 2.999676465988159,
      "learning_rate": 3.342134831460675e-06,
      "loss": 1.9011,
      "step": 30
    },
    {
      "epoch": 0.003270645952575634,
      "grad_norm": 1.3771625757217407,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 1.5254,
      "step": 40
    },
    {
      "epoch": 0.004088307440719542,
      "grad_norm": 0.8931247591972351,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 1.226,
      "step": 50
    },
    {
      "epoch": 0.004905968928863451,
      "grad_norm": 1.1269806623458862,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 1.0716,
      "step": 60
    },
    {
      "epoch": 0.005723630417007359,
      "grad_norm": 1.387283205986023,
      "learning_rate": 7.814044943820226e-06,
      "loss": 1.011,
      "step": 70
    },
    {
      "epoch": 0.006541291905151268,
      "grad_norm": 0.6601500511169434,
      "learning_rate": 8.932022471910112e-06,
      "loss": 1.0061,
      "step": 80
    },
    {
      "epoch": 0.007358953393295176,
      "grad_norm": 0.6297673583030701,
      "learning_rate": 1.005e-05,
      "loss": 0.9876,
      "step": 90
    },
    {
      "epoch": 0.008176614881439084,
      "grad_norm": 0.5978390574455261,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.93,
      "step": 100
    },
    {
      "epoch": 0.008994276369582993,
      "grad_norm": 0.6085056662559509,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.911,
      "step": 110
    },
    {
      "epoch": 0.009811937857726901,
      "grad_norm": 0.630516767501831,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.9181,
      "step": 120
    },
    {
      "epoch": 0.01062959934587081,
      "grad_norm": 0.659934937953949,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.8963,
      "step": 130
    },
    {
      "epoch": 0.011447260834014717,
      "grad_norm": 0.5893965363502502,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.9024,
      "step": 140
    },
    {
      "epoch": 0.012264922322158627,
      "grad_norm": 0.5959360003471375,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.926,
      "step": 150
    },
    {
      "epoch": 0.013082583810302535,
      "grad_norm": 0.5704044699668884,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.8832,
      "step": 160
    },
    {
      "epoch": 0.013900245298446443,
      "grad_norm": 0.6047025322914124,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.9009,
      "step": 170
    },
    {
      "epoch": 0.014717906786590351,
      "grad_norm": 0.5899404883384705,
      "learning_rate": 2e-05,
      "loss": 0.8876,
      "step": 180
    },
    {
      "epoch": 0.01553556827473426,
      "grad_norm": 0.5657159090042114,
      "learning_rate": 2e-05,
      "loss": 0.8758,
      "step": 190
    },
    {
      "epoch": 0.016353229762878167,
      "grad_norm": 0.5136110186576843,
      "learning_rate": 2e-05,
      "loss": 0.892,
      "step": 200
    },
    {
      "epoch": 0.017170891251022075,
      "grad_norm": 0.5496647357940674,
      "learning_rate": 2e-05,
      "loss": 0.9069,
      "step": 210
    },
    {
      "epoch": 0.017988552739165987,
      "grad_norm": 0.5497331023216248,
      "learning_rate": 2e-05,
      "loss": 0.863,
      "step": 220
    },
    {
      "epoch": 0.018806214227309895,
      "grad_norm": 0.5021716952323914,
      "learning_rate": 2e-05,
      "loss": 0.8952,
      "step": 230
    },
    {
      "epoch": 0.019623875715453803,
      "grad_norm": 0.5393562912940979,
      "learning_rate": 2e-05,
      "loss": 0.8577,
      "step": 240
    },
    {
      "epoch": 0.02044153720359771,
      "grad_norm": 0.5259848833084106,
      "learning_rate": 2e-05,
      "loss": 0.8904,
      "step": 250
    },
    {
      "epoch": 0.02125919869174162,
      "grad_norm": 0.562362790107727,
      "learning_rate": 2e-05,
      "loss": 0.922,
      "step": 260
    },
    {
      "epoch": 0.022076860179885527,
      "grad_norm": 0.514157235622406,
      "learning_rate": 2e-05,
      "loss": 0.8547,
      "step": 270
    },
    {
      "epoch": 0.022894521668029435,
      "grad_norm": 0.5613844394683838,
      "learning_rate": 2e-05,
      "loss": 0.8867,
      "step": 280
    },
    {
      "epoch": 0.023712183156173343,
      "grad_norm": 0.5137860774993896,
      "learning_rate": 2e-05,
      "loss": 0.864,
      "step": 290
    },
    {
      "epoch": 0.024529844644317254,
      "grad_norm": 0.5275009274482727,
      "learning_rate": 2e-05,
      "loss": 0.927,
      "step": 300
    },
    {
      "epoch": 0.025347506132461162,
      "grad_norm": 0.5223109722137451,
      "learning_rate": 2e-05,
      "loss": 0.8691,
      "step": 310
    },
    {
      "epoch": 0.02616516762060507,
      "grad_norm": 0.5527063012123108,
      "learning_rate": 2e-05,
      "loss": 0.8648,
      "step": 320
    },
    {
      "epoch": 0.02698282910874898,
      "grad_norm": 0.49740317463874817,
      "learning_rate": 2e-05,
      "loss": 0.8486,
      "step": 330
    },
    {
      "epoch": 0.027800490596892886,
      "grad_norm": 0.49503129720687866,
      "learning_rate": 2e-05,
      "loss": 0.8395,
      "step": 340
    },
    {
      "epoch": 0.028618152085036794,
      "grad_norm": 0.5311452150344849,
      "learning_rate": 2e-05,
      "loss": 0.8358,
      "step": 350
    },
    {
      "epoch": 0.029435813573180702,
      "grad_norm": 0.5130277872085571,
      "learning_rate": 2e-05,
      "loss": 0.8554,
      "step": 360
    },
    {
      "epoch": 0.03025347506132461,
      "grad_norm": 0.46086397767066956,
      "learning_rate": 2e-05,
      "loss": 0.8545,
      "step": 370
    },
    {
      "epoch": 0.03107113654946852,
      "grad_norm": 0.49420565366744995,
      "learning_rate": 2e-05,
      "loss": 0.8401,
      "step": 380
    },
    {
      "epoch": 0.03188879803761243,
      "grad_norm": 0.4804873764514923,
      "learning_rate": 2e-05,
      "loss": 0.8533,
      "step": 390
    },
    {
      "epoch": 0.032706459525756335,
      "grad_norm": 0.4856545329093933,
      "learning_rate": 2e-05,
      "loss": 0.8172,
      "step": 400
    },
    {
      "epoch": 0.033524121013900246,
      "grad_norm": 0.5700660347938538,
      "learning_rate": 2e-05,
      "loss": 0.87,
      "step": 410
    },
    {
      "epoch": 0.03434178250204415,
      "grad_norm": 0.48742008209228516,
      "learning_rate": 2e-05,
      "loss": 0.8653,
      "step": 420
    },
    {
      "epoch": 0.03515944399018806,
      "grad_norm": 0.5448684096336365,
      "learning_rate": 2e-05,
      "loss": 0.8574,
      "step": 430
    },
    {
      "epoch": 0.035977105478331974,
      "grad_norm": 0.9145104289054871,
      "learning_rate": 2e-05,
      "loss": 0.8529,
      "step": 440
    },
    {
      "epoch": 0.03679476696647588,
      "grad_norm": 0.6051157712936401,
      "learning_rate": 2e-05,
      "loss": 0.8492,
      "step": 450
    },
    {
      "epoch": 0.03761242845461979,
      "grad_norm": 0.5123623013496399,
      "learning_rate": 2e-05,
      "loss": 0.8689,
      "step": 460
    },
    {
      "epoch": 0.038430089942763694,
      "grad_norm": 0.49921512603759766,
      "learning_rate": 2e-05,
      "loss": 0.8126,
      "step": 470
    },
    {
      "epoch": 0.039247751430907606,
      "grad_norm": 0.5155230760574341,
      "learning_rate": 2e-05,
      "loss": 0.7817,
      "step": 480
    },
    {
      "epoch": 0.04006541291905151,
      "grad_norm": 0.46784713864326477,
      "learning_rate": 2e-05,
      "loss": 0.8324,
      "step": 490
    },
    {
      "epoch": 0.04088307440719542,
      "grad_norm": 0.4902730882167816,
      "learning_rate": 2e-05,
      "loss": 0.8196,
      "step": 500
    },
    {
      "epoch": 0.041700735895339326,
      "grad_norm": 0.47778692841529846,
      "learning_rate": 2e-05,
      "loss": 0.8537,
      "step": 510
    },
    {
      "epoch": 0.04251839738348324,
      "grad_norm": 0.46416184306144714,
      "learning_rate": 2e-05,
      "loss": 0.815,
      "step": 520
    },
    {
      "epoch": 0.04333605887162715,
      "grad_norm": 0.4957575798034668,
      "learning_rate": 2e-05,
      "loss": 0.8317,
      "step": 530
    },
    {
      "epoch": 0.044153720359771054,
      "grad_norm": 0.4955309331417084,
      "learning_rate": 2e-05,
      "loss": 0.8053,
      "step": 540
    },
    {
      "epoch": 0.044971381847914965,
      "grad_norm": 0.47801926732063293,
      "learning_rate": 2e-05,
      "loss": 0.8318,
      "step": 550
    },
    {
      "epoch": 0.04578904333605887,
      "grad_norm": 0.4526337683200836,
      "learning_rate": 2e-05,
      "loss": 0.8297,
      "step": 560
    },
    {
      "epoch": 0.04660670482420278,
      "grad_norm": 0.5001497864723206,
      "learning_rate": 2e-05,
      "loss": 0.7966,
      "step": 570
    },
    {
      "epoch": 0.047424366312346686,
      "grad_norm": 0.4969994127750397,
      "learning_rate": 2e-05,
      "loss": 0.849,
      "step": 580
    },
    {
      "epoch": 0.0482420278004906,
      "grad_norm": 0.4873654246330261,
      "learning_rate": 2e-05,
      "loss": 0.8098,
      "step": 590
    },
    {
      "epoch": 0.04905968928863451,
      "grad_norm": 0.46147921681404114,
      "learning_rate": 2e-05,
      "loss": 0.8462,
      "step": 600
    },
    {
      "epoch": 0.04987735077677841,
      "grad_norm": 0.48419851064682007,
      "learning_rate": 2e-05,
      "loss": 0.7878,
      "step": 610
    },
    {
      "epoch": 0.050695012264922325,
      "grad_norm": 0.48362842202186584,
      "learning_rate": 2e-05,
      "loss": 0.8309,
      "step": 620
    },
    {
      "epoch": 0.05151267375306623,
      "grad_norm": 0.4815925657749176,
      "learning_rate": 2e-05,
      "loss": 0.8409,
      "step": 630
    },
    {
      "epoch": 0.05233033524121014,
      "grad_norm": 0.5199002027511597,
      "learning_rate": 2e-05,
      "loss": 0.8685,
      "step": 640
    },
    {
      "epoch": 0.053147996729354045,
      "grad_norm": 0.4724765419960022,
      "learning_rate": 2e-05,
      "loss": 0.8279,
      "step": 650
    },
    {
      "epoch": 0.05396565821749796,
      "grad_norm": 0.5170514583587646,
      "learning_rate": 2e-05,
      "loss": 0.8361,
      "step": 660
    },
    {
      "epoch": 0.05478331970564186,
      "grad_norm": 0.5067883133888245,
      "learning_rate": 2e-05,
      "loss": 0.8425,
      "step": 670
    },
    {
      "epoch": 0.05560098119378577,
      "grad_norm": 0.43147748708724976,
      "learning_rate": 2e-05,
      "loss": 0.8048,
      "step": 680
    },
    {
      "epoch": 0.056418642681929684,
      "grad_norm": 0.508711576461792,
      "learning_rate": 2e-05,
      "loss": 0.848,
      "step": 690
    },
    {
      "epoch": 0.05723630417007359,
      "grad_norm": 0.4623899459838867,
      "learning_rate": 2e-05,
      "loss": 0.826,
      "step": 700
    },
    {
      "epoch": 0.0580539656582175,
      "grad_norm": 0.48188719153404236,
      "learning_rate": 2e-05,
      "loss": 0.8371,
      "step": 710
    },
    {
      "epoch": 0.058871627146361405,
      "grad_norm": 0.4509360194206238,
      "learning_rate": 2e-05,
      "loss": 0.8107,
      "step": 720
    },
    {
      "epoch": 0.059689288634505316,
      "grad_norm": 0.4348622262477875,
      "learning_rate": 2e-05,
      "loss": 0.7997,
      "step": 730
    },
    {
      "epoch": 0.06050695012264922,
      "grad_norm": 0.4793204963207245,
      "learning_rate": 2e-05,
      "loss": 0.8357,
      "step": 740
    },
    {
      "epoch": 0.06132461161079313,
      "grad_norm": 0.47185131907463074,
      "learning_rate": 2e-05,
      "loss": 0.814,
      "step": 750
    },
    {
      "epoch": 0.06214227309893704,
      "grad_norm": 0.5104201436042786,
      "learning_rate": 2e-05,
      "loss": 0.8447,
      "step": 760
    },
    {
      "epoch": 0.06295993458708095,
      "grad_norm": 0.45201629400253296,
      "learning_rate": 2e-05,
      "loss": 0.8265,
      "step": 770
    },
    {
      "epoch": 0.06377759607522486,
      "grad_norm": 1.1489161252975464,
      "learning_rate": 2e-05,
      "loss": 0.8434,
      "step": 780
    },
    {
      "epoch": 0.06459525756336877,
      "grad_norm": 0.5133305788040161,
      "learning_rate": 2e-05,
      "loss": 0.821,
      "step": 790
    },
    {
      "epoch": 0.06541291905151267,
      "grad_norm": 0.45519399642944336,
      "learning_rate": 2e-05,
      "loss": 0.8432,
      "step": 800
    },
    {
      "epoch": 0.06623058053965658,
      "grad_norm": 1.8952999114990234,
      "learning_rate": 2e-05,
      "loss": 0.7693,
      "step": 810
    },
    {
      "epoch": 0.06704824202780049,
      "grad_norm": 0.4610855281352997,
      "learning_rate": 2e-05,
      "loss": 0.8228,
      "step": 820
    },
    {
      "epoch": 0.0678659035159444,
      "grad_norm": 0.49510180950164795,
      "learning_rate": 2e-05,
      "loss": 0.8122,
      "step": 830
    },
    {
      "epoch": 0.0686835650040883,
      "grad_norm": 0.4776274561882019,
      "learning_rate": 2e-05,
      "loss": 0.7767,
      "step": 840
    },
    {
      "epoch": 0.06950122649223221,
      "grad_norm": 0.47551512718200684,
      "learning_rate": 2e-05,
      "loss": 0.8284,
      "step": 850
    },
    {
      "epoch": 0.07031888798037612,
      "grad_norm": 0.49425825476646423,
      "learning_rate": 2e-05,
      "loss": 0.802,
      "step": 860
    },
    {
      "epoch": 0.07113654946852004,
      "grad_norm": 0.46732547879219055,
      "learning_rate": 2e-05,
      "loss": 0.822,
      "step": 870
    },
    {
      "epoch": 0.07195421095666395,
      "grad_norm": 0.44407016038894653,
      "learning_rate": 2e-05,
      "loss": 0.8251,
      "step": 880
    },
    {
      "epoch": 0.07277187244480784,
      "grad_norm": 0.45862287282943726,
      "learning_rate": 2e-05,
      "loss": 0.8219,
      "step": 890
    },
    {
      "epoch": 0.07358953393295176,
      "grad_norm": 0.48010408878326416,
      "learning_rate": 2e-05,
      "loss": 0.815,
      "step": 900
    },
    {
      "epoch": 0.07440719542109567,
      "grad_norm": 0.4639987349510193,
      "learning_rate": 2e-05,
      "loss": 0.811,
      "step": 910
    },
    {
      "epoch": 0.07522485690923958,
      "grad_norm": 0.4830052852630615,
      "learning_rate": 2e-05,
      "loss": 0.8209,
      "step": 920
    },
    {
      "epoch": 0.07604251839738348,
      "grad_norm": 0.44569143652915955,
      "learning_rate": 2e-05,
      "loss": 0.7969,
      "step": 930
    },
    {
      "epoch": 0.07686017988552739,
      "grad_norm": 0.4402197301387787,
      "learning_rate": 2e-05,
      "loss": 0.8048,
      "step": 940
    },
    {
      "epoch": 0.0776778413736713,
      "grad_norm": 0.4393838346004486,
      "learning_rate": 2e-05,
      "loss": 0.7999,
      "step": 950
    },
    {
      "epoch": 0.07849550286181521,
      "grad_norm": 0.45926329493522644,
      "learning_rate": 2e-05,
      "loss": 0.7993,
      "step": 960
    },
    {
      "epoch": 0.07931316434995912,
      "grad_norm": 0.45618489384651184,
      "learning_rate": 2e-05,
      "loss": 0.7941,
      "step": 970
    },
    {
      "epoch": 0.08013082583810302,
      "grad_norm": 0.4323713779449463,
      "learning_rate": 2e-05,
      "loss": 0.8128,
      "step": 980
    },
    {
      "epoch": 0.08094848732624693,
      "grad_norm": 0.4577762484550476,
      "learning_rate": 2e-05,
      "loss": 0.8158,
      "step": 990
    },
    {
      "epoch": 0.08176614881439084,
      "grad_norm": 0.44366759061813354,
      "learning_rate": 2e-05,
      "loss": 0.801,
      "step": 1000
    },
    {
      "epoch": 0.08258381030253475,
      "grad_norm": 0.43710198998451233,
      "learning_rate": 2e-05,
      "loss": 0.8178,
      "step": 1010
    },
    {
      "epoch": 0.08340147179067865,
      "grad_norm": 0.5216193795204163,
      "learning_rate": 2e-05,
      "loss": 0.8356,
      "step": 1020
    },
    {
      "epoch": 0.08421913327882256,
      "grad_norm": 0.6718442440032959,
      "learning_rate": 2e-05,
      "loss": 0.8186,
      "step": 1030
    },
    {
      "epoch": 0.08503679476696648,
      "grad_norm": 0.45956555008888245,
      "learning_rate": 2e-05,
      "loss": 0.7599,
      "step": 1040
    },
    {
      "epoch": 0.08585445625511039,
      "grad_norm": 0.4390004575252533,
      "learning_rate": 2e-05,
      "loss": 0.7939,
      "step": 1050
    },
    {
      "epoch": 0.0866721177432543,
      "grad_norm": 0.458306223154068,
      "learning_rate": 2e-05,
      "loss": 0.8154,
      "step": 1060
    },
    {
      "epoch": 0.0874897792313982,
      "grad_norm": 0.46446549892425537,
      "learning_rate": 2e-05,
      "loss": 0.8013,
      "step": 1070
    },
    {
      "epoch": 0.08830744071954211,
      "grad_norm": 0.46321365237236023,
      "learning_rate": 2e-05,
      "loss": 0.7987,
      "step": 1080
    },
    {
      "epoch": 0.08912510220768602,
      "grad_norm": 0.4468840956687927,
      "learning_rate": 2e-05,
      "loss": 0.8049,
      "step": 1090
    },
    {
      "epoch": 0.08994276369582993,
      "grad_norm": 0.4241533577442169,
      "learning_rate": 2e-05,
      "loss": 0.7683,
      "step": 1100
    },
    {
      "epoch": 0.09076042518397383,
      "grad_norm": 0.4573608934879303,
      "learning_rate": 2e-05,
      "loss": 0.7942,
      "step": 1110
    },
    {
      "epoch": 0.09157808667211774,
      "grad_norm": 0.4434383809566498,
      "learning_rate": 2e-05,
      "loss": 0.8005,
      "step": 1120
    },
    {
      "epoch": 0.09239574816026165,
      "grad_norm": 0.5078239440917969,
      "learning_rate": 2e-05,
      "loss": 0.8192,
      "step": 1130
    },
    {
      "epoch": 0.09321340964840556,
      "grad_norm": 0.4617445766925812,
      "learning_rate": 2e-05,
      "loss": 0.804,
      "step": 1140
    },
    {
      "epoch": 0.09403107113654947,
      "grad_norm": 0.43501752614974976,
      "learning_rate": 2e-05,
      "loss": 0.8172,
      "step": 1150
    },
    {
      "epoch": 0.09484873262469337,
      "grad_norm": 0.4166872501373291,
      "learning_rate": 2e-05,
      "loss": 0.8197,
      "step": 1160
    },
    {
      "epoch": 0.09566639411283728,
      "grad_norm": 0.655982494354248,
      "learning_rate": 2e-05,
      "loss": 0.789,
      "step": 1170
    },
    {
      "epoch": 0.0964840556009812,
      "grad_norm": 0.41751641035079956,
      "learning_rate": 2e-05,
      "loss": 0.7995,
      "step": 1180
    },
    {
      "epoch": 0.0973017170891251,
      "grad_norm": 0.470846027135849,
      "learning_rate": 2e-05,
      "loss": 0.8322,
      "step": 1190
    },
    {
      "epoch": 0.09811937857726902,
      "grad_norm": 0.4337841272354126,
      "learning_rate": 2e-05,
      "loss": 0.814,
      "step": 1200
    },
    {
      "epoch": 0.09893704006541292,
      "grad_norm": 0.47191646695137024,
      "learning_rate": 2e-05,
      "loss": 0.8039,
      "step": 1210
    },
    {
      "epoch": 0.09975470155355683,
      "grad_norm": 0.43299242854118347,
      "learning_rate": 2e-05,
      "loss": 0.8096,
      "step": 1220
    },
    {
      "epoch": 0.10057236304170074,
      "grad_norm": 0.4392620623111725,
      "learning_rate": 2e-05,
      "loss": 0.811,
      "step": 1230
    },
    {
      "epoch": 0.10139002452984465,
      "grad_norm": 0.4958798885345459,
      "learning_rate": 2e-05,
      "loss": 0.821,
      "step": 1240
    },
    {
      "epoch": 0.10220768601798855,
      "grad_norm": 0.449624240398407,
      "learning_rate": 2e-05,
      "loss": 0.8024,
      "step": 1250
    },
    {
      "epoch": 0.10302534750613246,
      "grad_norm": 0.5577616095542908,
      "learning_rate": 2e-05,
      "loss": 0.7876,
      "step": 1260
    },
    {
      "epoch": 0.10384300899427637,
      "grad_norm": 0.4583219289779663,
      "learning_rate": 2e-05,
      "loss": 0.7821,
      "step": 1270
    },
    {
      "epoch": 0.10466067048242028,
      "grad_norm": 0.4646966755390167,
      "learning_rate": 2e-05,
      "loss": 0.791,
      "step": 1280
    },
    {
      "epoch": 0.1054783319705642,
      "grad_norm": 0.4247964918613434,
      "learning_rate": 2e-05,
      "loss": 0.78,
      "step": 1290
    },
    {
      "epoch": 0.10629599345870809,
      "grad_norm": 0.46946001052856445,
      "learning_rate": 2e-05,
      "loss": 0.7948,
      "step": 1300
    },
    {
      "epoch": 0.107113654946852,
      "grad_norm": 0.43030065298080444,
      "learning_rate": 2e-05,
      "loss": 0.8059,
      "step": 1310
    },
    {
      "epoch": 0.10793131643499591,
      "grad_norm": 0.4443809986114502,
      "learning_rate": 2e-05,
      "loss": 0.7681,
      "step": 1320
    },
    {
      "epoch": 0.10874897792313983,
      "grad_norm": 0.4212033748626709,
      "learning_rate": 2e-05,
      "loss": 0.7689,
      "step": 1330
    },
    {
      "epoch": 0.10956663941128372,
      "grad_norm": 0.486328125,
      "learning_rate": 2e-05,
      "loss": 0.7612,
      "step": 1340
    },
    {
      "epoch": 0.11038430089942763,
      "grad_norm": 0.43208643794059753,
      "learning_rate": 2e-05,
      "loss": 0.8189,
      "step": 1350
    },
    {
      "epoch": 0.11120196238757155,
      "grad_norm": 0.4304050803184509,
      "learning_rate": 2e-05,
      "loss": 0.7886,
      "step": 1360
    },
    {
      "epoch": 0.11201962387571546,
      "grad_norm": 0.4358374774456024,
      "learning_rate": 2e-05,
      "loss": 0.7838,
      "step": 1370
    },
    {
      "epoch": 0.11283728536385937,
      "grad_norm": 0.4316851794719696,
      "learning_rate": 2e-05,
      "loss": 0.7945,
      "step": 1380
    },
    {
      "epoch": 0.11365494685200327,
      "grad_norm": 0.43443015217781067,
      "learning_rate": 2e-05,
      "loss": 0.8029,
      "step": 1390
    },
    {
      "epoch": 0.11447260834014718,
      "grad_norm": 0.4291702210903168,
      "learning_rate": 2e-05,
      "loss": 0.8028,
      "step": 1400
    },
    {
      "epoch": 0.11529026982829109,
      "grad_norm": 0.4630155861377716,
      "learning_rate": 2e-05,
      "loss": 0.7724,
      "step": 1410
    },
    {
      "epoch": 0.116107931316435,
      "grad_norm": 0.4348618686199188,
      "learning_rate": 2e-05,
      "loss": 0.7816,
      "step": 1420
    },
    {
      "epoch": 0.1169255928045789,
      "grad_norm": 0.4198819100856781,
      "learning_rate": 2e-05,
      "loss": 0.7851,
      "step": 1430
    },
    {
      "epoch": 0.11774325429272281,
      "grad_norm": 0.4539889991283417,
      "learning_rate": 2e-05,
      "loss": 0.7691,
      "step": 1440
    },
    {
      "epoch": 0.11856091578086672,
      "grad_norm": 0.4621836245059967,
      "learning_rate": 2e-05,
      "loss": 0.7858,
      "step": 1450
    },
    {
      "epoch": 0.11937857726901063,
      "grad_norm": 0.44036760926246643,
      "learning_rate": 2e-05,
      "loss": 0.7865,
      "step": 1460
    },
    {
      "epoch": 0.12019623875715454,
      "grad_norm": 0.4228440225124359,
      "learning_rate": 2e-05,
      "loss": 0.7579,
      "step": 1470
    },
    {
      "epoch": 0.12101390024529844,
      "grad_norm": 0.435478150844574,
      "learning_rate": 2e-05,
      "loss": 0.7823,
      "step": 1480
    },
    {
      "epoch": 0.12183156173344235,
      "grad_norm": 0.4398757815361023,
      "learning_rate": 2e-05,
      "loss": 0.7727,
      "step": 1490
    },
    {
      "epoch": 0.12264922322158626,
      "grad_norm": 0.42032548785209656,
      "learning_rate": 2e-05,
      "loss": 0.7772,
      "step": 1500
    },
    {
      "epoch": 0.12346688470973018,
      "grad_norm": 1.2638468742370605,
      "learning_rate": 2e-05,
      "loss": 0.8029,
      "step": 1510
    },
    {
      "epoch": 0.12428454619787407,
      "grad_norm": 0.4492338001728058,
      "learning_rate": 2e-05,
      "loss": 0.7976,
      "step": 1520
    },
    {
      "epoch": 0.12510220768601799,
      "grad_norm": 0.4194067120552063,
      "learning_rate": 2e-05,
      "loss": 0.7729,
      "step": 1530
    },
    {
      "epoch": 0.1259198691741619,
      "grad_norm": 0.4248548150062561,
      "learning_rate": 2e-05,
      "loss": 0.7832,
      "step": 1540
    },
    {
      "epoch": 0.1267375306623058,
      "grad_norm": 0.44248121976852417,
      "learning_rate": 2e-05,
      "loss": 0.7993,
      "step": 1550
    },
    {
      "epoch": 0.12755519215044972,
      "grad_norm": 0.4308151304721832,
      "learning_rate": 2e-05,
      "loss": 0.8292,
      "step": 1560
    },
    {
      "epoch": 0.12837285363859363,
      "grad_norm": 0.46226322650909424,
      "learning_rate": 2e-05,
      "loss": 0.7998,
      "step": 1570
    },
    {
      "epoch": 0.12919051512673754,
      "grad_norm": 0.6823664307594299,
      "learning_rate": 2e-05,
      "loss": 0.7797,
      "step": 1580
    },
    {
      "epoch": 0.13000817661488143,
      "grad_norm": 0.49192625284194946,
      "learning_rate": 2e-05,
      "loss": 0.792,
      "step": 1590
    },
    {
      "epoch": 0.13082583810302534,
      "grad_norm": 0.46564188599586487,
      "learning_rate": 2e-05,
      "loss": 0.7812,
      "step": 1600
    },
    {
      "epoch": 0.13164349959116925,
      "grad_norm": 0.4175106883049011,
      "learning_rate": 2e-05,
      "loss": 0.8088,
      "step": 1610
    },
    {
      "epoch": 0.13246116107931316,
      "grad_norm": 0.43853816390037537,
      "learning_rate": 2e-05,
      "loss": 0.7881,
      "step": 1620
    },
    {
      "epoch": 0.13327882256745707,
      "grad_norm": 0.48302924633026123,
      "learning_rate": 2e-05,
      "loss": 0.7913,
      "step": 1630
    },
    {
      "epoch": 0.13409648405560098,
      "grad_norm": 0.6604704856872559,
      "learning_rate": 2e-05,
      "loss": 0.7709,
      "step": 1640
    },
    {
      "epoch": 0.1349141455437449,
      "grad_norm": 0.523360550403595,
      "learning_rate": 2e-05,
      "loss": 0.7948,
      "step": 1650
    },
    {
      "epoch": 0.1357318070318888,
      "grad_norm": 0.41866135597229004,
      "learning_rate": 2e-05,
      "loss": 0.7374,
      "step": 1660
    },
    {
      "epoch": 0.13654946852003272,
      "grad_norm": 0.43435412645339966,
      "learning_rate": 2e-05,
      "loss": 0.7516,
      "step": 1670
    },
    {
      "epoch": 0.1373671300081766,
      "grad_norm": 0.4378770887851715,
      "learning_rate": 2e-05,
      "loss": 0.7793,
      "step": 1680
    },
    {
      "epoch": 0.1381847914963205,
      "grad_norm": 0.4642718434333801,
      "learning_rate": 2e-05,
      "loss": 0.7891,
      "step": 1690
    },
    {
      "epoch": 0.13900245298446443,
      "grad_norm": 0.4553477168083191,
      "learning_rate": 2e-05,
      "loss": 0.7693,
      "step": 1700
    },
    {
      "epoch": 0.13982011447260834,
      "grad_norm": 0.44605308771133423,
      "learning_rate": 2e-05,
      "loss": 0.7894,
      "step": 1710
    },
    {
      "epoch": 0.14063777596075225,
      "grad_norm": 0.4435379207134247,
      "learning_rate": 2e-05,
      "loss": 0.7834,
      "step": 1720
    },
    {
      "epoch": 0.14145543744889616,
      "grad_norm": 0.43862536549568176,
      "learning_rate": 2e-05,
      "loss": 0.7783,
      "step": 1730
    },
    {
      "epoch": 0.14227309893704007,
      "grad_norm": 0.3968248963356018,
      "learning_rate": 2e-05,
      "loss": 0.7753,
      "step": 1740
    },
    {
      "epoch": 0.14309076042518398,
      "grad_norm": 0.43859657645225525,
      "learning_rate": 2e-05,
      "loss": 0.8167,
      "step": 1750
    },
    {
      "epoch": 0.1439084219133279,
      "grad_norm": 0.4324052035808563,
      "learning_rate": 2e-05,
      "loss": 0.7865,
      "step": 1760
    },
    {
      "epoch": 0.14472608340147178,
      "grad_norm": 0.43473488092422485,
      "learning_rate": 2e-05,
      "loss": 0.8224,
      "step": 1770
    },
    {
      "epoch": 0.1455437448896157,
      "grad_norm": 0.42597419023513794,
      "learning_rate": 2e-05,
      "loss": 0.7985,
      "step": 1780
    },
    {
      "epoch": 0.1463614063777596,
      "grad_norm": 0.48900550603866577,
      "learning_rate": 2e-05,
      "loss": 0.7562,
      "step": 1790
    },
    {
      "epoch": 0.1471790678659035,
      "grad_norm": 0.4394257068634033,
      "learning_rate": 2e-05,
      "loss": 0.7721,
      "step": 1800
    },
    {
      "epoch": 0.14799672935404742,
      "grad_norm": 0.43295830488204956,
      "learning_rate": 2e-05,
      "loss": 0.7727,
      "step": 1810
    },
    {
      "epoch": 0.14881439084219134,
      "grad_norm": 0.4200812578201294,
      "learning_rate": 2e-05,
      "loss": 0.7866,
      "step": 1820
    },
    {
      "epoch": 0.14963205233033525,
      "grad_norm": 0.4190243184566498,
      "learning_rate": 2e-05,
      "loss": 0.7765,
      "step": 1830
    },
    {
      "epoch": 0.15044971381847916,
      "grad_norm": 0.45326995849609375,
      "learning_rate": 2e-05,
      "loss": 0.7871,
      "step": 1840
    },
    {
      "epoch": 0.15126737530662307,
      "grad_norm": 0.4055960476398468,
      "learning_rate": 2e-05,
      "loss": 0.7632,
      "step": 1850
    },
    {
      "epoch": 0.15208503679476695,
      "grad_norm": 0.48894283175468445,
      "learning_rate": 2e-05,
      "loss": 0.7756,
      "step": 1860
    },
    {
      "epoch": 0.15290269828291086,
      "grad_norm": 0.4656607508659363,
      "learning_rate": 2e-05,
      "loss": 0.7726,
      "step": 1870
    },
    {
      "epoch": 0.15372035977105478,
      "grad_norm": 0.4367874562740326,
      "learning_rate": 2e-05,
      "loss": 0.7772,
      "step": 1880
    },
    {
      "epoch": 0.1545380212591987,
      "grad_norm": 0.4750969707965851,
      "learning_rate": 2e-05,
      "loss": 0.7712,
      "step": 1890
    },
    {
      "epoch": 0.1553556827473426,
      "grad_norm": 0.4409693479537964,
      "learning_rate": 2e-05,
      "loss": 0.7904,
      "step": 1900
    },
    {
      "epoch": 0.1561733442354865,
      "grad_norm": 0.4396913945674896,
      "learning_rate": 2e-05,
      "loss": 0.7597,
      "step": 1910
    },
    {
      "epoch": 0.15699100572363042,
      "grad_norm": 0.41550886631011963,
      "learning_rate": 2e-05,
      "loss": 0.7812,
      "step": 1920
    },
    {
      "epoch": 0.15780866721177433,
      "grad_norm": 0.42665189504623413,
      "learning_rate": 2e-05,
      "loss": 0.7871,
      "step": 1930
    },
    {
      "epoch": 0.15862632869991825,
      "grad_norm": 0.4286573827266693,
      "learning_rate": 2e-05,
      "loss": 0.7736,
      "step": 1940
    },
    {
      "epoch": 0.15944399018806213,
      "grad_norm": 0.42506206035614014,
      "learning_rate": 2e-05,
      "loss": 0.7784,
      "step": 1950
    },
    {
      "epoch": 0.16026165167620604,
      "grad_norm": 0.46702292561531067,
      "learning_rate": 2e-05,
      "loss": 0.7703,
      "step": 1960
    },
    {
      "epoch": 0.16107931316434995,
      "grad_norm": 0.43847423791885376,
      "learning_rate": 2e-05,
      "loss": 0.7656,
      "step": 1970
    },
    {
      "epoch": 0.16189697465249386,
      "grad_norm": 0.4711706042289734,
      "learning_rate": 2e-05,
      "loss": 0.7657,
      "step": 1980
    },
    {
      "epoch": 0.16271463614063778,
      "grad_norm": 0.5090168118476868,
      "learning_rate": 2e-05,
      "loss": 0.7592,
      "step": 1990
    },
    {
      "epoch": 0.1635322976287817,
      "grad_norm": 0.46786943078041077,
      "learning_rate": 2e-05,
      "loss": 0.7921,
      "step": 2000
    },
    {
      "epoch": 0.1643499591169256,
      "grad_norm": 0.4125913977622986,
      "learning_rate": 2e-05,
      "loss": 0.7831,
      "step": 2010
    },
    {
      "epoch": 0.1651676206050695,
      "grad_norm": 0.4442942440509796,
      "learning_rate": 2e-05,
      "loss": 0.7536,
      "step": 2020
    },
    {
      "epoch": 0.16598528209321342,
      "grad_norm": 0.4498803913593292,
      "learning_rate": 2e-05,
      "loss": 0.7825,
      "step": 2030
    },
    {
      "epoch": 0.1668029435813573,
      "grad_norm": 0.4364321529865265,
      "learning_rate": 2e-05,
      "loss": 0.7899,
      "step": 2040
    },
    {
      "epoch": 0.16762060506950122,
      "grad_norm": 0.4316538870334625,
      "learning_rate": 2e-05,
      "loss": 0.7791,
      "step": 2050
    },
    {
      "epoch": 0.16843826655764513,
      "grad_norm": 0.45543980598449707,
      "learning_rate": 2e-05,
      "loss": 0.7882,
      "step": 2060
    },
    {
      "epoch": 0.16925592804578904,
      "grad_norm": 0.4247235953807831,
      "learning_rate": 2e-05,
      "loss": 0.7986,
      "step": 2070
    },
    {
      "epoch": 0.17007358953393295,
      "grad_norm": 0.4491972029209137,
      "learning_rate": 2e-05,
      "loss": 0.8298,
      "step": 2080
    },
    {
      "epoch": 0.17089125102207686,
      "grad_norm": 0.4386272132396698,
      "learning_rate": 2e-05,
      "loss": 0.7572,
      "step": 2090
    },
    {
      "epoch": 0.17170891251022077,
      "grad_norm": 0.4444292485713959,
      "learning_rate": 2e-05,
      "loss": 0.7801,
      "step": 2100
    },
    {
      "epoch": 0.17252657399836469,
      "grad_norm": 0.4270576238632202,
      "learning_rate": 2e-05,
      "loss": 0.7656,
      "step": 2110
    },
    {
      "epoch": 0.1733442354865086,
      "grad_norm": 0.436068594455719,
      "learning_rate": 2e-05,
      "loss": 0.7444,
      "step": 2120
    },
    {
      "epoch": 0.17416189697465248,
      "grad_norm": 0.42339572310447693,
      "learning_rate": 2e-05,
      "loss": 0.7805,
      "step": 2130
    },
    {
      "epoch": 0.1749795584627964,
      "grad_norm": 0.4199734628200531,
      "learning_rate": 2e-05,
      "loss": 0.7519,
      "step": 2140
    },
    {
      "epoch": 0.1757972199509403,
      "grad_norm": 0.4218316376209259,
      "learning_rate": 2e-05,
      "loss": 0.7825,
      "step": 2150
    },
    {
      "epoch": 0.17661488143908421,
      "grad_norm": 0.417795330286026,
      "learning_rate": 2e-05,
      "loss": 0.7871,
      "step": 2160
    },
    {
      "epoch": 0.17743254292722813,
      "grad_norm": 0.4626673460006714,
      "learning_rate": 2e-05,
      "loss": 0.7771,
      "step": 2170
    },
    {
      "epoch": 0.17825020441537204,
      "grad_norm": 0.468065470457077,
      "learning_rate": 2e-05,
      "loss": 0.7915,
      "step": 2180
    },
    {
      "epoch": 0.17906786590351595,
      "grad_norm": 0.4166199564933777,
      "learning_rate": 2e-05,
      "loss": 0.7726,
      "step": 2190
    },
    {
      "epoch": 0.17988552739165986,
      "grad_norm": 0.42800837755203247,
      "learning_rate": 2e-05,
      "loss": 0.7725,
      "step": 2200
    },
    {
      "epoch": 0.18070318887980377,
      "grad_norm": 0.4120378792285919,
      "learning_rate": 2e-05,
      "loss": 0.743,
      "step": 2210
    },
    {
      "epoch": 0.18152085036794766,
      "grad_norm": 0.5455228686332703,
      "learning_rate": 2e-05,
      "loss": 0.7318,
      "step": 2220
    },
    {
      "epoch": 0.18233851185609157,
      "grad_norm": 0.4296571612358093,
      "learning_rate": 2e-05,
      "loss": 0.7928,
      "step": 2230
    },
    {
      "epoch": 0.18315617334423548,
      "grad_norm": 0.4547067880630493,
      "learning_rate": 2e-05,
      "loss": 0.7747,
      "step": 2240
    },
    {
      "epoch": 0.1839738348323794,
      "grad_norm": 0.4168989956378937,
      "learning_rate": 2e-05,
      "loss": 0.7923,
      "step": 2250
    },
    {
      "epoch": 0.1847914963205233,
      "grad_norm": 0.44426074624061584,
      "learning_rate": 2e-05,
      "loss": 0.7748,
      "step": 2260
    },
    {
      "epoch": 0.1856091578086672,
      "grad_norm": 0.4370101988315582,
      "learning_rate": 2e-05,
      "loss": 0.7758,
      "step": 2270
    },
    {
      "epoch": 0.18642681929681112,
      "grad_norm": 0.49895063042640686,
      "learning_rate": 2e-05,
      "loss": 0.7619,
      "step": 2280
    },
    {
      "epoch": 0.18724448078495504,
      "grad_norm": 0.40498825907707214,
      "learning_rate": 2e-05,
      "loss": 0.7709,
      "step": 2290
    },
    {
      "epoch": 0.18806214227309895,
      "grad_norm": 0.4341062903404236,
      "learning_rate": 2e-05,
      "loss": 0.7862,
      "step": 2300
    },
    {
      "epoch": 0.18887980376124286,
      "grad_norm": 0.46437665820121765,
      "learning_rate": 2e-05,
      "loss": 0.8152,
      "step": 2310
    },
    {
      "epoch": 0.18969746524938674,
      "grad_norm": 0.43534669280052185,
      "learning_rate": 2e-05,
      "loss": 0.764,
      "step": 2320
    },
    {
      "epoch": 0.19051512673753065,
      "grad_norm": 0.44681885838508606,
      "learning_rate": 2e-05,
      "loss": 0.7873,
      "step": 2330
    },
    {
      "epoch": 0.19133278822567457,
      "grad_norm": 0.45268961787223816,
      "learning_rate": 2e-05,
      "loss": 0.7995,
      "step": 2340
    },
    {
      "epoch": 0.19215044971381848,
      "grad_norm": 0.41534167528152466,
      "learning_rate": 2e-05,
      "loss": 0.7722,
      "step": 2350
    },
    {
      "epoch": 0.1929681112019624,
      "grad_norm": 0.44464072585105896,
      "learning_rate": 2e-05,
      "loss": 0.7842,
      "step": 2360
    },
    {
      "epoch": 0.1937857726901063,
      "grad_norm": 0.4211314618587494,
      "learning_rate": 2e-05,
      "loss": 0.7756,
      "step": 2370
    },
    {
      "epoch": 0.1946034341782502,
      "grad_norm": 0.44980642199516296,
      "learning_rate": 2e-05,
      "loss": 0.7635,
      "step": 2380
    },
    {
      "epoch": 0.19542109566639412,
      "grad_norm": 0.43298453092575073,
      "learning_rate": 2e-05,
      "loss": 0.7998,
      "step": 2390
    },
    {
      "epoch": 0.19623875715453803,
      "grad_norm": 0.4239964485168457,
      "learning_rate": 2e-05,
      "loss": 0.7589,
      "step": 2400
    },
    {
      "epoch": 0.19705641864268192,
      "grad_norm": 0.4066570997238159,
      "learning_rate": 2e-05,
      "loss": 0.779,
      "step": 2410
    },
    {
      "epoch": 0.19787408013082583,
      "grad_norm": 0.47745639085769653,
      "learning_rate": 2e-05,
      "loss": 0.7877,
      "step": 2420
    },
    {
      "epoch": 0.19869174161896974,
      "grad_norm": 0.4101332426071167,
      "learning_rate": 2e-05,
      "loss": 0.8011,
      "step": 2430
    },
    {
      "epoch": 0.19950940310711365,
      "grad_norm": 0.4742473065853119,
      "learning_rate": 2e-05,
      "loss": 0.7922,
      "step": 2440
    },
    {
      "epoch": 0.20032706459525756,
      "grad_norm": 0.4261021316051483,
      "learning_rate": 2e-05,
      "loss": 0.751,
      "step": 2450
    },
    {
      "epoch": 0.20114472608340148,
      "grad_norm": 0.5145176649093628,
      "learning_rate": 2e-05,
      "loss": 0.7285,
      "step": 2460
    },
    {
      "epoch": 0.2019623875715454,
      "grad_norm": 0.40921565890312195,
      "learning_rate": 2e-05,
      "loss": 0.7871,
      "step": 2470
    },
    {
      "epoch": 0.2027800490596893,
      "grad_norm": 0.44564947485923767,
      "learning_rate": 2e-05,
      "loss": 0.8052,
      "step": 2480
    },
    {
      "epoch": 0.2035977105478332,
      "grad_norm": 0.42048290371894836,
      "learning_rate": 2e-05,
      "loss": 0.8011,
      "step": 2490
    },
    {
      "epoch": 0.2044153720359771,
      "grad_norm": 0.408529669046402,
      "learning_rate": 2e-05,
      "loss": 0.7733,
      "step": 2500
    },
    {
      "epoch": 0.205233033524121,
      "grad_norm": 0.42771342396736145,
      "learning_rate": 2e-05,
      "loss": 0.7809,
      "step": 2510
    },
    {
      "epoch": 0.20605069501226492,
      "grad_norm": 0.39116600155830383,
      "learning_rate": 2e-05,
      "loss": 0.7621,
      "step": 2520
    },
    {
      "epoch": 0.20686835650040883,
      "grad_norm": 0.43292510509490967,
      "learning_rate": 2e-05,
      "loss": 0.7797,
      "step": 2530
    },
    {
      "epoch": 0.20768601798855274,
      "grad_norm": 0.40812504291534424,
      "learning_rate": 2e-05,
      "loss": 0.7545,
      "step": 2540
    },
    {
      "epoch": 0.20850367947669665,
      "grad_norm": 0.42122846841812134,
      "learning_rate": 1.9980979278401095e-05,
      "loss": 0.7574,
      "step": 2550
    },
    {
      "epoch": 0.20932134096484056,
      "grad_norm": 0.4099932312965393,
      "learning_rate": 1.982924955463327e-05,
      "loss": 0.7841,
      "step": 2560
    },
    {
      "epoch": 0.21013900245298447,
      "grad_norm": 0.4781613349914551,
      "learning_rate": 1.9528108298328235e-05,
      "loss": 0.7697,
      "step": 2570
    },
    {
      "epoch": 0.2109566639411284,
      "grad_norm": 0.4076142907142639,
      "learning_rate": 1.9082156473635994e-05,
      "loss": 0.751,
      "step": 2580
    },
    {
      "epoch": 0.21177432542927227,
      "grad_norm": 0.37984731793403625,
      "learning_rate": 1.8498207522139434e-05,
      "loss": 0.7486,
      "step": 2590
    },
    {
      "epoch": 0.21259198691741618,
      "grad_norm": 0.4122683107852936,
      "learning_rate": 1.7785183264196977e-05,
      "loss": 0.7738,
      "step": 2600
    },
    {
      "epoch": 0.2134096484055601,
      "grad_norm": 0.4006371796131134,
      "learning_rate": 1.6953977587577846e-05,
      "loss": 0.7398,
      "step": 2610
    },
    {
      "epoch": 0.214227309893704,
      "grad_norm": 0.42201295495033264,
      "learning_rate": 1.601729000601297e-05,
      "loss": 0.7445,
      "step": 2620
    },
    {
      "epoch": 0.21504497138184792,
      "grad_norm": 0.47633713483810425,
      "learning_rate": 1.4989431630624763e-05,
      "loss": 0.7829,
      "step": 2630
    },
    {
      "epoch": 0.21586263286999183,
      "grad_norm": 0.4022769033908844,
      "learning_rate": 1.3886106518686746e-05,
      "loss": 0.8046,
      "step": 2640
    },
    {
      "epoch": 0.21668029435813574,
      "grad_norm": 0.39716070890426636,
      "learning_rate": 1.2724171740359612e-05,
      "loss": 0.7572,
      "step": 2650
    },
    {
      "epoch": 0.21749795584627965,
      "grad_norm": 0.41379281878471375,
      "learning_rate": 1.1521379829206218e-05,
      "loss": 0.7607,
      "step": 2660
    },
    {
      "epoch": 0.21831561733442356,
      "grad_norm": 0.46306541562080383,
      "learning_rate": 1.029610755143595e-05,
      "loss": 0.7779,
      "step": 2670
    },
    {
      "epoch": 0.21913327882256745,
      "grad_norm": 0.4066726863384247,
      "learning_rate": 9.067075137857348e-06,
      "loss": 0.7356,
      "step": 2680
    },
    {
      "epoch": 0.21995094031071136,
      "grad_norm": 0.39531978964805603,
      "learning_rate": 7.853060268232525e-06,
      "loss": 0.7703,
      "step": 2690
    },
    {
      "epoch": 0.22076860179885527,
      "grad_norm": 0.3976958096027374,
      "learning_rate": 6.672611177902054e-06,
      "loss": 0.7693,
      "step": 2700
    },
    {
      "epoch": 0.22158626328699918,
      "grad_norm": 0.9513207077980042,
      "learning_rate": 5.543763269959312e-06,
      "loss": 0.7995,
      "step": 2710
    },
    {
      "epoch": 0.2224039247751431,
      "grad_norm": 0.4046993851661682,
      "learning_rate": 4.483763562693867e-06,
      "loss": 0.7373,
      "step": 2720
    },
    {
      "epoch": 0.223221586263287,
      "grad_norm": 0.4631391763687134,
      "learning_rate": 3.508807182313187e-06,
      "loss": 0.7737,
      "step": 2730
    },
    {
      "epoch": 0.22403924775143091,
      "grad_norm": 0.379557341337204,
      "learning_rate": 2.6337899269187294e-06,
      "loss": 0.7593,
      "step": 2740
    },
    {
      "epoch": 0.22485690923957483,
      "grad_norm": 0.3898264467716217,
      "learning_rate": 1.8720806821693126e-06,
      "loss": 0.7576,
      "step": 2750
    },
    {
      "epoch": 0.22567457072771874,
      "grad_norm": 0.39198824763298035,
      "learning_rate": 1.2353171657619887e-06,
      "loss": 0.7272,
      "step": 2760
    },
    {
      "epoch": 0.22649223221586262,
      "grad_norm": 0.4044579863548279,
      "learning_rate": 7.332281214330356e-07,
      "loss": 0.7568,
      "step": 2770
    },
    {
      "epoch": 0.22730989370400653,
      "grad_norm": 0.4269305169582367,
      "learning_rate": 3.73484679074808e-07,
      "loss": 0.7298,
      "step": 2780
    },
    {
      "epoch": 0.22812755519215044,
      "grad_norm": 0.37593910098075867,
      "learning_rate": 1.61583151951702e-07,
      "loss": 0.7645,
      "step": 2790
    },
    {
      "epoch": 0.22878168438266558,
      "step": 2798,
      "total_flos": 1.1366756130249245e+19,
      "train_loss": 0.06918619631698424,
      "train_runtime": 2302.6271,
      "train_samples_per_second": 14.582,
      "train_steps_per_second": 1.215
    }
  ],
  "logging_steps": 10,
  "max_steps": 2798,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 159,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1366756130249245e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}