{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23361442765300158,
  "eval_steps": 500,
  "global_step": 2798,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008349336227769892,
      "grad_norm": 4.207607746124268,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 1.5395,
      "step": 10
    },
    {
      "epoch": 0.0016698672455539784,
      "grad_norm": 2.644784450531006,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 1.3507,
      "step": 20
    },
    {
      "epoch": 0.0025048008683309676,
      "grad_norm": 1.4334214925765991,
      "learning_rate": 3.342134831460675e-06,
      "loss": 1.2368,
      "step": 30
    },
    {
      "epoch": 0.003339734491107957,
      "grad_norm": 1.1798350811004639,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 1.0269,
      "step": 40
    },
    {
      "epoch": 0.004174668113884946,
      "grad_norm": 0.9337137937545776,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 0.835,
      "step": 50
    },
    {
      "epoch": 0.005009601736661935,
      "grad_norm": 0.5626512765884399,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 0.8018,
      "step": 60
    },
    {
      "epoch": 0.0058445353594389245,
      "grad_norm": 0.5007433891296387,
      "learning_rate": 7.814044943820226e-06,
      "loss": 0.7772,
      "step": 70
    },
    {
      "epoch": 0.006679468982215914,
      "grad_norm": 0.4939042329788208,
      "learning_rate": 8.932022471910112e-06,
      "loss": 0.7392,
      "step": 80
    },
    {
      "epoch": 0.007514402604992903,
      "grad_norm": 0.5686920285224915,
      "learning_rate": 1.005e-05,
      "loss": 0.7669,
      "step": 90
    },
    {
      "epoch": 0.008349336227769892,
      "grad_norm": 0.5208467245101929,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.7672,
      "step": 100
    },
    {
      "epoch": 0.009184269850546881,
      "grad_norm": 0.4716687500476837,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.7388,
      "step": 110
    },
    {
      "epoch": 0.01001920347332387,
      "grad_norm": 0.4500362277030945,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.7456,
      "step": 120
    },
    {
      "epoch": 0.01085413709610086,
      "grad_norm": 0.4907788336277008,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.7577,
      "step": 130
    },
    {
      "epoch": 0.011689070718877849,
      "grad_norm": 0.46692827343940735,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.7618,
      "step": 140
    },
    {
      "epoch": 0.012524004341654838,
      "grad_norm": 0.5163733959197998,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.7743,
      "step": 150
    },
    {
      "epoch": 0.013358937964431827,
      "grad_norm": 0.459434449672699,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.8005,
      "step": 160
    },
    {
      "epoch": 0.014193871587208817,
      "grad_norm": 0.48260498046875,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.7283,
      "step": 170
    },
    {
      "epoch": 0.015028805209985806,
      "grad_norm": 0.6386128067970276,
      "learning_rate": 2e-05,
      "loss": 0.7521,
      "step": 180
    },
    {
      "epoch": 0.015863738832762795,
      "grad_norm": 0.450025737285614,
      "learning_rate": 2e-05,
      "loss": 0.6999,
      "step": 190
    },
    {
      "epoch": 0.016698672455539784,
      "grad_norm": 0.4777669310569763,
      "learning_rate": 2e-05,
      "loss": 0.7388,
      "step": 200
    },
    {
      "epoch": 0.017533606078316773,
      "grad_norm": 0.44185250997543335,
      "learning_rate": 2e-05,
      "loss": 0.7528,
      "step": 210
    },
    {
      "epoch": 0.018368539701093763,
      "grad_norm": 0.48510533571243286,
      "learning_rate": 2e-05,
      "loss": 0.7419,
      "step": 220
    },
    {
      "epoch": 0.019203473323870752,
      "grad_norm": 0.4384409487247467,
      "learning_rate": 2e-05,
      "loss": 0.76,
      "step": 230
    },
    {
      "epoch": 0.02003840694664774,
      "grad_norm": 0.4512603282928467,
      "learning_rate": 2e-05,
      "loss": 0.7694,
      "step": 240
    },
    {
      "epoch": 0.02087334056942473,
      "grad_norm": 0.4747536778450012,
      "learning_rate": 2e-05,
      "loss": 0.756,
      "step": 250
    },
    {
      "epoch": 0.02170827419220172,
      "grad_norm": 0.4111518859863281,
      "learning_rate": 2e-05,
      "loss": 0.7286,
      "step": 260
    },
    {
      "epoch": 0.02254320781497871,
      "grad_norm": 0.39627984166145325,
      "learning_rate": 2e-05,
      "loss": 0.7802,
      "step": 270
    },
    {
      "epoch": 0.023378141437755698,
      "grad_norm": 0.45961877703666687,
      "learning_rate": 2e-05,
      "loss": 0.7671,
      "step": 280
    },
    {
      "epoch": 0.024213075060532687,
      "grad_norm": 0.4554557502269745,
      "learning_rate": 2e-05,
      "loss": 0.7404,
      "step": 290
    },
    {
      "epoch": 0.025048008683309676,
      "grad_norm": 0.4171745479106903,
      "learning_rate": 2e-05,
      "loss": 0.7177,
      "step": 300
    },
    {
      "epoch": 0.025882942306086665,
      "grad_norm": 0.42183369398117065,
      "learning_rate": 2e-05,
      "loss": 0.7447,
      "step": 310
    },
    {
      "epoch": 0.026717875928863655,
      "grad_norm": 0.9629115462303162,
      "learning_rate": 2e-05,
      "loss": 0.7802,
      "step": 320
    },
    {
      "epoch": 0.027552809551640644,
      "grad_norm": 0.3929850161075592,
      "learning_rate": 2e-05,
      "loss": 0.7022,
      "step": 330
    },
    {
      "epoch": 0.028387743174417633,
      "grad_norm": 0.4160802364349365,
      "learning_rate": 2e-05,
      "loss": 0.7431,
      "step": 340
    },
    {
      "epoch": 0.029222676797194622,
      "grad_norm": 0.43566712737083435,
      "learning_rate": 2e-05,
      "loss": 0.7409,
      "step": 350
    },
    {
      "epoch": 0.03005761041997161,
      "grad_norm": 0.47777512669563293,
      "learning_rate": 2e-05,
      "loss": 0.7661,
      "step": 360
    },
    {
      "epoch": 0.0308925440427486,
      "grad_norm": 0.45962175726890564,
      "learning_rate": 2e-05,
      "loss": 0.7364,
      "step": 370
    },
    {
      "epoch": 0.03172747766552559,
      "grad_norm": 0.4599931240081787,
      "learning_rate": 2e-05,
      "loss": 0.7255,
      "step": 380
    },
    {
      "epoch": 0.03256241128830258,
      "grad_norm": 0.42078301310539246,
      "learning_rate": 2e-05,
      "loss": 0.7568,
      "step": 390
    },
    {
      "epoch": 0.03339734491107957,
      "grad_norm": 0.41342827677726746,
      "learning_rate": 2e-05,
      "loss": 0.746,
      "step": 400
    },
    {
      "epoch": 0.03423227853385656,
      "grad_norm": 0.4753192663192749,
      "learning_rate": 2e-05,
      "loss": 0.7098,
      "step": 410
    },
    {
      "epoch": 0.03506721215663355,
      "grad_norm": 0.42074984312057495,
      "learning_rate": 2e-05,
      "loss": 0.7348,
      "step": 420
    },
    {
      "epoch": 0.03590214577941054,
      "grad_norm": 0.3717345893383026,
      "learning_rate": 2e-05,
      "loss": 0.7215,
      "step": 430
    },
    {
      "epoch": 0.036737079402187525,
      "grad_norm": 0.4751165509223938,
      "learning_rate": 2e-05,
      "loss": 0.7147,
      "step": 440
    },
    {
      "epoch": 0.03757201302496452,
      "grad_norm": 0.44281241297721863,
      "learning_rate": 2e-05,
      "loss": 0.7324,
      "step": 450
    },
    {
      "epoch": 0.038406946647741504,
      "grad_norm": 0.42347100377082825,
      "learning_rate": 2e-05,
      "loss": 0.7286,
      "step": 460
    },
    {
      "epoch": 0.039241880270518496,
      "grad_norm": 0.46966537833213806,
      "learning_rate": 2e-05,
      "loss": 0.7474,
      "step": 470
    },
    {
      "epoch": 0.04007681389329548,
      "grad_norm": 0.4589572548866272,
      "learning_rate": 2e-05,
      "loss": 0.7644,
      "step": 480
    },
    {
      "epoch": 0.040911747516072475,
      "grad_norm": 0.39805424213409424,
      "learning_rate": 2e-05,
      "loss": 0.6949,
      "step": 490
    },
    {
      "epoch": 0.04174668113884946,
      "grad_norm": 0.36458325386047363,
      "learning_rate": 2e-05,
      "loss": 0.7205,
      "step": 500
    },
    {
      "epoch": 0.04258161476162645,
      "grad_norm": 0.457324355840683,
      "learning_rate": 2e-05,
      "loss": 0.7049,
      "step": 510
    },
    {
      "epoch": 0.04341654838440344,
      "grad_norm": 0.39649268984794617,
      "learning_rate": 2e-05,
      "loss": 0.7298,
      "step": 520
    },
    {
      "epoch": 0.04425148200718043,
      "grad_norm": 0.4664701819419861,
      "learning_rate": 2e-05,
      "loss": 0.748,
      "step": 530
    },
    {
      "epoch": 0.04508641562995742,
      "grad_norm": 0.41996926069259644,
      "learning_rate": 2e-05,
      "loss": 0.7382,
      "step": 540
    },
    {
      "epoch": 0.04592134925273441,
      "grad_norm": 0.4385315179824829,
      "learning_rate": 2e-05,
      "loss": 0.7303,
      "step": 550
    },
    {
      "epoch": 0.046756282875511396,
      "grad_norm": 0.3684557378292084,
      "learning_rate": 2e-05,
      "loss": 0.723,
      "step": 560
    },
    {
      "epoch": 0.04759121649828839,
      "grad_norm": 0.4108535051345825,
      "learning_rate": 2e-05,
      "loss": 0.7505,
      "step": 570
    },
    {
      "epoch": 0.048426150121065374,
      "grad_norm": 0.4387914538383484,
      "learning_rate": 2e-05,
      "loss": 0.7649,
      "step": 580
    },
    {
      "epoch": 0.04926108374384237,
      "grad_norm": 0.9331011772155762,
      "learning_rate": 2e-05,
      "loss": 0.7209,
      "step": 590
    },
    {
      "epoch": 0.05009601736661935,
      "grad_norm": 0.4378844201564789,
      "learning_rate": 2e-05,
      "loss": 0.7596,
      "step": 600
    },
    {
      "epoch": 0.050930950989396345,
      "grad_norm": 0.41000136733055115,
      "learning_rate": 2e-05,
      "loss": 0.7652,
      "step": 610
    },
    {
      "epoch": 0.05176588461217333,
      "grad_norm": 0.3994877338409424,
      "learning_rate": 2e-05,
      "loss": 0.7096,
      "step": 620
    },
    {
      "epoch": 0.052600818234950324,
      "grad_norm": 0.4212743937969208,
      "learning_rate": 2e-05,
      "loss": 0.7607,
      "step": 630
    },
    {
      "epoch": 0.05343575185772731,
      "grad_norm": 0.4719401001930237,
      "learning_rate": 2e-05,
      "loss": 0.6994,
      "step": 640
    },
    {
      "epoch": 0.0542706854805043,
      "grad_norm": 0.45361122488975525,
      "learning_rate": 2e-05,
      "loss": 0.7521,
      "step": 650
    },
    {
      "epoch": 0.05510561910328129,
      "grad_norm": 0.3882407546043396,
      "learning_rate": 2e-05,
      "loss": 0.73,
      "step": 660
    },
    {
      "epoch": 0.05594055272605828,
      "grad_norm": 0.3987034559249878,
      "learning_rate": 2e-05,
      "loss": 0.7175,
      "step": 670
    },
    {
      "epoch": 0.056775486348835266,
      "grad_norm": 0.4764518141746521,
      "learning_rate": 2e-05,
      "loss": 0.7383,
      "step": 680
    },
    {
      "epoch": 0.05761041997161226,
      "grad_norm": 0.38849174976348877,
      "learning_rate": 2e-05,
      "loss": 0.7296,
      "step": 690
    },
    {
      "epoch": 0.058445353594389245,
      "grad_norm": 0.40971478819847107,
      "learning_rate": 2e-05,
      "loss": 0.7273,
      "step": 700
    },
    {
      "epoch": 0.05928028721716624,
      "grad_norm": 0.4441114068031311,
      "learning_rate": 2e-05,
      "loss": 0.7249,
      "step": 710
    },
    {
      "epoch": 0.06011522083994322,
      "grad_norm": 0.3833942413330078,
      "learning_rate": 2e-05,
      "loss": 0.7136,
      "step": 720
    },
    {
      "epoch": 0.060950154462720216,
      "grad_norm": 0.3802347779273987,
      "learning_rate": 2e-05,
      "loss": 0.7393,
      "step": 730
    },
    {
      "epoch": 0.0617850880854972,
      "grad_norm": 0.4086751639842987,
      "learning_rate": 2e-05,
      "loss": 0.7152,
      "step": 740
    },
    {
      "epoch": 0.06262002170827419,
      "grad_norm": 0.39086148142814636,
      "learning_rate": 2e-05,
      "loss": 0.7204,
      "step": 750
    },
    {
      "epoch": 0.06345495533105118,
      "grad_norm": 0.4143637418746948,
      "learning_rate": 2e-05,
      "loss": 0.7363,
      "step": 760
    },
    {
      "epoch": 0.06428988895382817,
      "grad_norm": 0.40541625022888184,
      "learning_rate": 2e-05,
      "loss": 0.7047,
      "step": 770
    },
    {
      "epoch": 0.06512482257660517,
      "grad_norm": 0.43499815464019775,
      "learning_rate": 2e-05,
      "loss": 0.7313,
      "step": 780
    },
    {
      "epoch": 0.06595975619938214,
      "grad_norm": 0.4995516836643219,
      "learning_rate": 2e-05,
      "loss": 0.7217,
      "step": 790
    },
    {
      "epoch": 0.06679468982215914,
      "grad_norm": 0.39953678846359253,
      "learning_rate": 2e-05,
      "loss": 0.7396,
      "step": 800
    },
    {
      "epoch": 0.06762962344493613,
      "grad_norm": 0.38989365100860596,
      "learning_rate": 2e-05,
      "loss": 0.7378,
      "step": 810
    },
    {
      "epoch": 0.06846455706771312,
      "grad_norm": 0.5271377563476562,
      "learning_rate": 2e-05,
      "loss": 0.7208,
      "step": 820
    },
    {
      "epoch": 0.0692994906904901,
      "grad_norm": 0.41988226771354675,
      "learning_rate": 2e-05,
      "loss": 0.7384,
      "step": 830
    },
    {
      "epoch": 0.0701344243132671,
      "grad_norm": 0.6820985078811646,
      "learning_rate": 2e-05,
      "loss": 0.721,
      "step": 840
    },
    {
      "epoch": 0.07096935793604409,
      "grad_norm": 0.45111504197120667,
      "learning_rate": 2e-05,
      "loss": 0.7292,
      "step": 850
    },
    {
      "epoch": 0.07180429155882108,
      "grad_norm": 0.42547836899757385,
      "learning_rate": 2e-05,
      "loss": 0.7111,
      "step": 860
    },
    {
      "epoch": 0.07263922518159806,
      "grad_norm": 0.4102250635623932,
      "learning_rate": 2e-05,
      "loss": 0.7237,
      "step": 870
    },
    {
      "epoch": 0.07347415880437505,
      "grad_norm": 0.39390629529953003,
      "learning_rate": 2e-05,
      "loss": 0.7549,
      "step": 880
    },
    {
      "epoch": 0.07430909242715204,
      "grad_norm": 0.45642760396003723,
      "learning_rate": 2e-05,
      "loss": 0.7633,
      "step": 890
    },
    {
      "epoch": 0.07514402604992904,
      "grad_norm": 0.4338949918746948,
      "learning_rate": 2e-05,
      "loss": 0.7234,
      "step": 900
    },
    {
      "epoch": 0.07597895967270601,
      "grad_norm": 0.4457014501094818,
      "learning_rate": 2e-05,
      "loss": 0.697,
      "step": 910
    },
    {
      "epoch": 0.07681389329548301,
      "grad_norm": 0.3864661157131195,
      "learning_rate": 2e-05,
      "loss": 0.7454,
      "step": 920
    },
    {
      "epoch": 0.07764882691826,
      "grad_norm": 0.4558520019054413,
      "learning_rate": 2e-05,
      "loss": 0.7176,
      "step": 930
    },
    {
      "epoch": 0.07848376054103699,
      "grad_norm": 0.40667447447776794,
      "learning_rate": 2e-05,
      "loss": 0.7354,
      "step": 940
    },
    {
      "epoch": 0.07931869416381397,
      "grad_norm": 0.4572715759277344,
      "learning_rate": 2e-05,
      "loss": 0.7536,
      "step": 950
    },
    {
      "epoch": 0.08015362778659096,
      "grad_norm": 0.3982183337211609,
      "learning_rate": 2e-05,
      "loss": 0.7087,
      "step": 960
    },
    {
      "epoch": 0.08098856140936796,
      "grad_norm": 0.3888983428478241,
      "learning_rate": 2e-05,
      "loss": 0.7578,
      "step": 970
    },
    {
      "epoch": 0.08182349503214495,
      "grad_norm": 0.40478619933128357,
      "learning_rate": 2e-05,
      "loss": 0.7126,
      "step": 980
    },
    {
      "epoch": 0.08265842865492193,
      "grad_norm": 0.48754480481147766,
      "learning_rate": 2e-05,
      "loss": 0.7314,
      "step": 990
    },
    {
      "epoch": 0.08349336227769892,
      "grad_norm": 0.38438543677330017,
      "learning_rate": 2e-05,
      "loss": 0.7413,
      "step": 1000
    },
    {
      "epoch": 0.08432829590047591,
      "grad_norm": 0.42465469241142273,
      "learning_rate": 2e-05,
      "loss": 0.7318,
      "step": 1010
    },
    {
      "epoch": 0.0851632295232529,
      "grad_norm": 0.5940709114074707,
      "learning_rate": 2e-05,
      "loss": 0.6863,
      "step": 1020
    },
    {
      "epoch": 0.08599816314602989,
      "grad_norm": 0.374142587184906,
      "learning_rate": 2e-05,
      "loss": 0.7137,
      "step": 1030
    },
    {
      "epoch": 0.08683309676880688,
      "grad_norm": 0.36702439188957214,
      "learning_rate": 2e-05,
      "loss": 0.6892,
      "step": 1040
    },
    {
      "epoch": 0.08766803039158387,
      "grad_norm": 0.363119900226593,
      "learning_rate": 2e-05,
      "loss": 0.7154,
      "step": 1050
    },
    {
      "epoch": 0.08850296401436086,
      "grad_norm": 0.4007730782032013,
      "learning_rate": 2e-05,
      "loss": 0.7001,
      "step": 1060
    },
    {
      "epoch": 0.08933789763713784,
      "grad_norm": 0.3801772892475128,
      "learning_rate": 2e-05,
      "loss": 0.713,
      "step": 1070
    },
    {
      "epoch": 0.09017283125991483,
      "grad_norm": 0.37953799962997437,
      "learning_rate": 2e-05,
      "loss": 0.6904,
      "step": 1080
    },
    {
      "epoch": 0.09100776488269183,
      "grad_norm": 0.3767666518688202,
      "learning_rate": 2e-05,
      "loss": 0.6867,
      "step": 1090
    },
    {
      "epoch": 0.09184269850546882,
      "grad_norm": 0.3752429187297821,
      "learning_rate": 2e-05,
      "loss": 0.6739,
      "step": 1100
    },
    {
      "epoch": 0.0926776321282458,
      "grad_norm": 0.4051717221736908,
      "learning_rate": 2e-05,
      "loss": 0.7001,
      "step": 1110
    },
    {
      "epoch": 0.09351256575102279,
      "grad_norm": 0.389317125082016,
      "learning_rate": 2e-05,
      "loss": 0.7089,
      "step": 1120
    },
    {
      "epoch": 0.09434749937379978,
      "grad_norm": 0.39081355929374695,
      "learning_rate": 2e-05,
      "loss": 0.7491,
      "step": 1130
    },
    {
      "epoch": 0.09518243299657678,
      "grad_norm": 0.9384667873382568,
      "learning_rate": 2e-05,
      "loss": 0.7606,
      "step": 1140
    },
    {
      "epoch": 0.09601736661935376,
      "grad_norm": 0.4086635708808899,
      "learning_rate": 2e-05,
      "loss": 0.6873,
      "step": 1150
    },
    {
      "epoch": 0.09685230024213075,
      "grad_norm": 0.5528045892715454,
      "learning_rate": 2e-05,
      "loss": 0.7105,
      "step": 1160
    },
    {
      "epoch": 0.09768723386490774,
      "grad_norm": 0.4137111306190491,
      "learning_rate": 2e-05,
      "loss": 0.7286,
      "step": 1170
    },
    {
      "epoch": 0.09852216748768473,
      "grad_norm": 0.3765595555305481,
      "learning_rate": 2e-05,
      "loss": 0.7176,
      "step": 1180
    },
    {
      "epoch": 0.09935710111046171,
      "grad_norm": 0.363838791847229,
      "learning_rate": 2e-05,
      "loss": 0.7176,
      "step": 1190
    },
    {
      "epoch": 0.1001920347332387,
      "grad_norm": 0.37655600905418396,
      "learning_rate": 2e-05,
      "loss": 0.72,
      "step": 1200
    },
    {
      "epoch": 0.1010269683560157,
      "grad_norm": 0.4103720784187317,
      "learning_rate": 2e-05,
      "loss": 0.6947,
      "step": 1210
    },
    {
      "epoch": 0.10186190197879269,
      "grad_norm": 0.4416528046131134,
      "learning_rate": 2e-05,
      "loss": 0.6984,
      "step": 1220
    },
    {
      "epoch": 0.10269683560156967,
      "grad_norm": 0.4061998724937439,
      "learning_rate": 2e-05,
      "loss": 0.705,
      "step": 1230
    },
    {
      "epoch": 0.10353176922434666,
      "grad_norm": 0.3562486171722412,
      "learning_rate": 2e-05,
      "loss": 0.6997,
      "step": 1240
    },
    {
      "epoch": 0.10436670284712365,
      "grad_norm": 0.3291058838367462,
      "learning_rate": 2e-05,
      "loss": 0.699,
      "step": 1250
    },
    {
      "epoch": 0.10520163646990065,
      "grad_norm": 0.36545422673225403,
      "learning_rate": 2e-05,
      "loss": 0.7427,
      "step": 1260
    },
    {
      "epoch": 0.10603657009267763,
      "grad_norm": 0.3796237111091614,
      "learning_rate": 2e-05,
      "loss": 0.7175,
      "step": 1270
    },
    {
      "epoch": 0.10687150371545462,
      "grad_norm": 0.3584843873977661,
      "learning_rate": 2e-05,
      "loss": 0.6931,
      "step": 1280
    },
    {
      "epoch": 0.10770643733823161,
      "grad_norm": 0.4039587676525116,
      "learning_rate": 2e-05,
      "loss": 0.709,
      "step": 1290
    },
    {
      "epoch": 0.1085413709610086,
      "grad_norm": 0.5920600295066833,
      "learning_rate": 2e-05,
      "loss": 0.7284,
      "step": 1300
    },
    {
      "epoch": 0.10937630458378558,
      "grad_norm": 0.41448742151260376,
      "learning_rate": 2e-05,
      "loss": 0.6784,
      "step": 1310
    },
    {
      "epoch": 0.11021123820656258,
      "grad_norm": 0.385707288980484,
      "learning_rate": 2e-05,
      "loss": 0.6937,
      "step": 1320
    },
    {
      "epoch": 0.11104617182933957,
      "grad_norm": 0.4448997974395752,
      "learning_rate": 2e-05,
      "loss": 0.7125,
      "step": 1330
    },
    {
      "epoch": 0.11188110545211656,
      "grad_norm": 0.46152302622795105,
      "learning_rate": 2e-05,
      "loss": 0.7389,
      "step": 1340
    },
    {
      "epoch": 0.11271603907489354,
      "grad_norm": 0.3662891089916229,
      "learning_rate": 2e-05,
      "loss": 0.7253,
      "step": 1350
    },
    {
      "epoch": 0.11355097269767053,
      "grad_norm": 0.40756434202194214,
      "learning_rate": 2e-05,
      "loss": 0.6773,
      "step": 1360
    },
    {
      "epoch": 0.11438590632044753,
      "grad_norm": 0.3913949728012085,
      "learning_rate": 2e-05,
      "loss": 0.7047,
      "step": 1370
    },
    {
      "epoch": 0.11522083994322452,
      "grad_norm": 0.3753698170185089,
      "learning_rate": 2e-05,
      "loss": 0.7021,
      "step": 1380
    },
    {
      "epoch": 0.1160557735660015,
      "grad_norm": 0.3978191614151001,
      "learning_rate": 2e-05,
      "loss": 0.7258,
      "step": 1390
    },
    {
      "epoch": 0.11689070718877849,
      "grad_norm": 0.3952433168888092,
      "learning_rate": 2e-05,
      "loss": 0.7125,
      "step": 1400
    },
    {
      "epoch": 0.11772564081155548,
      "grad_norm": 0.37945103645324707,
      "learning_rate": 2e-05,
      "loss": 0.6866,
      "step": 1410
    },
    {
      "epoch": 0.11856057443433247,
      "grad_norm": 0.37956511974334717,
      "learning_rate": 2e-05,
      "loss": 0.7207,
      "step": 1420
    },
    {
      "epoch": 0.11939550805710945,
      "grad_norm": 0.46238476037979126,
      "learning_rate": 2e-05,
      "loss": 0.7116,
      "step": 1430
    },
    {
      "epoch": 0.12023044167988645,
      "grad_norm": 0.5139086842536926,
      "learning_rate": 2e-05,
      "loss": 0.7079,
      "step": 1440
    },
    {
      "epoch": 0.12106537530266344,
      "grad_norm": 0.39234450459480286,
      "learning_rate": 2e-05,
      "loss": 0.7373,
      "step": 1450
    },
    {
      "epoch": 0.12190030892544043,
      "grad_norm": 0.35747602581977844,
      "learning_rate": 2e-05,
      "loss": 0.7352,
      "step": 1460
    },
    {
      "epoch": 0.12273524254821741,
      "grad_norm": 0.3996635675430298,
      "learning_rate": 2e-05,
      "loss": 0.6851,
      "step": 1470
    },
    {
      "epoch": 0.1235701761709944,
      "grad_norm": 0.4240017235279083,
      "learning_rate": 2e-05,
      "loss": 0.6853,
      "step": 1480
    },
    {
      "epoch": 0.1244051097937714,
      "grad_norm": 0.37402406334877014,
      "learning_rate": 2e-05,
      "loss": 0.7145,
      "step": 1490
    },
    {
      "epoch": 0.12524004341654837,
      "grad_norm": 0.3979440927505493,
      "learning_rate": 2e-05,
      "loss": 0.6867,
      "step": 1500
    },
    {
      "epoch": 0.12607497703932538,
      "grad_norm": 0.4218880534172058,
      "learning_rate": 2e-05,
      "loss": 0.7233,
      "step": 1510
    },
    {
      "epoch": 0.12690991066210236,
      "grad_norm": 0.4031672477722168,
      "learning_rate": 2e-05,
      "loss": 0.6906,
      "step": 1520
    },
    {
      "epoch": 0.12774484428487934,
      "grad_norm": 0.38655754923820496,
      "learning_rate": 2e-05,
      "loss": 0.6809,
      "step": 1530
    },
    {
      "epoch": 0.12857977790765635,
      "grad_norm": 0.3993000090122223,
      "learning_rate": 2e-05,
      "loss": 0.6899,
      "step": 1540
    },
    {
      "epoch": 0.12941471153043332,
      "grad_norm": 0.3644014596939087,
      "learning_rate": 2e-05,
      "loss": 0.6774,
      "step": 1550
    },
    {
      "epoch": 0.13024964515321033,
      "grad_norm": 0.38217946887016296,
      "learning_rate": 2e-05,
      "loss": 0.7211,
      "step": 1560
    },
    {
      "epoch": 0.1310845787759873,
      "grad_norm": 0.41936999559402466,
      "learning_rate": 2e-05,
      "loss": 0.7166,
      "step": 1570
    },
    {
      "epoch": 0.1319195123987643,
      "grad_norm": 0.3735484480857849,
      "learning_rate": 2e-05,
      "loss": 0.7103,
      "step": 1580
    },
    {
      "epoch": 0.1327544460215413,
      "grad_norm": 0.3685668706893921,
      "learning_rate": 2e-05,
      "loss": 0.6766,
      "step": 1590
    },
    {
      "epoch": 0.13358937964431827,
      "grad_norm": 0.4097385108470917,
      "learning_rate": 2e-05,
      "loss": 0.6958,
      "step": 1600
    },
    {
      "epoch": 0.13442431326709525,
      "grad_norm": 0.3247581422328949,
      "learning_rate": 2e-05,
      "loss": 0.7003,
      "step": 1610
    },
    {
      "epoch": 0.13525924688987226,
      "grad_norm": 0.3488894999027252,
      "learning_rate": 2e-05,
      "loss": 0.6967,
      "step": 1620
    },
    {
      "epoch": 0.13609418051264924,
      "grad_norm": 0.3828565180301666,
      "learning_rate": 2e-05,
      "loss": 0.7062,
      "step": 1630
    },
    {
      "epoch": 0.13692911413542624,
      "grad_norm": 0.39991557598114014,
      "learning_rate": 2e-05,
      "loss": 0.7122,
      "step": 1640
    },
    {
      "epoch": 0.13776404775820322,
      "grad_norm": 0.38803574442863464,
      "learning_rate": 2e-05,
      "loss": 0.7119,
      "step": 1650
    },
    {
      "epoch": 0.1385989813809802,
      "grad_norm": 0.39794668555259705,
      "learning_rate": 2e-05,
      "loss": 0.7072,
      "step": 1660
    },
    {
      "epoch": 0.1394339150037572,
      "grad_norm": 0.3571108877658844,
      "learning_rate": 2e-05,
      "loss": 0.6655,
      "step": 1670
    },
    {
      "epoch": 0.1402688486265342,
      "grad_norm": 0.3803035020828247,
      "learning_rate": 2e-05,
      "loss": 0.6978,
      "step": 1680
    },
    {
      "epoch": 0.14110378224931117,
      "grad_norm": 0.3964841663837433,
      "learning_rate": 2e-05,
      "loss": 0.7039,
      "step": 1690
    },
    {
      "epoch": 0.14193871587208817,
      "grad_norm": 0.3538469970226288,
      "learning_rate": 2e-05,
      "loss": 0.6992,
      "step": 1700
    },
    {
      "epoch": 0.14277364949486515,
      "grad_norm": 0.33465176820755005,
      "learning_rate": 2e-05,
      "loss": 0.6412,
      "step": 1710
    },
    {
      "epoch": 0.14360858311764216,
      "grad_norm": 0.39754611253738403,
      "learning_rate": 2e-05,
      "loss": 0.6957,
      "step": 1720
    },
    {
      "epoch": 0.14444351674041914,
      "grad_norm": 0.35193371772766113,
      "learning_rate": 2e-05,
      "loss": 0.6739,
      "step": 1730
    },
    {
      "epoch": 0.14527845036319612,
      "grad_norm": 0.36387869715690613,
      "learning_rate": 2e-05,
      "loss": 0.6811,
      "step": 1740
    },
    {
      "epoch": 0.14611338398597312,
      "grad_norm": 0.381991446018219,
      "learning_rate": 2e-05,
      "loss": 0.7192,
      "step": 1750
    },
    {
      "epoch": 0.1469483176087501,
      "grad_norm": 0.3615923523902893,
      "learning_rate": 2e-05,
      "loss": 0.677,
      "step": 1760
    },
    {
      "epoch": 0.1477832512315271,
      "grad_norm": 0.40365681052207947,
      "learning_rate": 2e-05,
      "loss": 0.6913,
      "step": 1770
    },
    {
      "epoch": 0.1486181848543041,
      "grad_norm": 0.44782131910324097,
      "learning_rate": 2e-05,
      "loss": 0.6924,
      "step": 1780
    },
    {
      "epoch": 0.14945311847708107,
      "grad_norm": 0.3924279808998108,
      "learning_rate": 2e-05,
      "loss": 0.7324,
      "step": 1790
    },
    {
      "epoch": 0.15028805209985807,
      "grad_norm": 0.35536661744117737,
      "learning_rate": 2e-05,
      "loss": 0.7101,
      "step": 1800
    },
    {
      "epoch": 0.15112298572263505,
      "grad_norm": 0.3691920340061188,
      "learning_rate": 2e-05,
      "loss": 0.6661,
      "step": 1810
    },
    {
      "epoch": 0.15195791934541203,
      "grad_norm": 0.37451237440109253,
      "learning_rate": 2e-05,
      "loss": 0.6778,
      "step": 1820
    },
    {
      "epoch": 0.15279285296818904,
      "grad_norm": 0.3587948977947235,
      "learning_rate": 2e-05,
      "loss": 0.6813,
      "step": 1830
    },
    {
      "epoch": 0.15362778659096601,
      "grad_norm": 0.46211594343185425,
      "learning_rate": 2e-05,
      "loss": 0.7048,
      "step": 1840
    },
    {
      "epoch": 0.15446272021374302,
      "grad_norm": 0.40670573711395264,
      "learning_rate": 2e-05,
      "loss": 0.7348,
      "step": 1850
    },
    {
      "epoch": 0.15529765383652,
      "grad_norm": 0.3951846659183502,
      "learning_rate": 2e-05,
      "loss": 0.7042,
      "step": 1860
    },
    {
      "epoch": 0.15613258745929698,
      "grad_norm": 0.3904159665107727,
      "learning_rate": 2e-05,
      "loss": 0.6851,
      "step": 1870
    },
    {
      "epoch": 0.15696752108207399,
      "grad_norm": 0.3530999720096588,
      "learning_rate": 2e-05,
      "loss": 0.7255,
      "step": 1880
    },
    {
      "epoch": 0.15780245470485096,
      "grad_norm": 0.37747418880462646,
      "learning_rate": 2e-05,
      "loss": 0.6937,
      "step": 1890
    },
    {
      "epoch": 0.15863738832762794,
      "grad_norm": 0.4633552134037018,
      "learning_rate": 2e-05,
      "loss": 0.6803,
      "step": 1900
    },
    {
      "epoch": 0.15947232195040495,
      "grad_norm": 0.3634198307991028,
      "learning_rate": 2e-05,
      "loss": 0.6702,
      "step": 1910
    },
    {
      "epoch": 0.16030725557318193,
      "grad_norm": 0.41056016087532043,
      "learning_rate": 2e-05,
      "loss": 0.7026,
      "step": 1920
    },
    {
      "epoch": 0.16114218919595893,
      "grad_norm": 0.3515470027923584,
      "learning_rate": 2e-05,
      "loss": 0.6895,
      "step": 1930
    },
    {
      "epoch": 0.1619771228187359,
      "grad_norm": 0.4402310848236084,
      "learning_rate": 2e-05,
      "loss": 0.7225,
      "step": 1940
    },
    {
      "epoch": 0.1628120564415129,
      "grad_norm": 0.3933682441711426,
      "learning_rate": 2e-05,
      "loss": 0.6916,
      "step": 1950
    },
    {
      "epoch": 0.1636469900642899,
      "grad_norm": 0.3949870467185974,
      "learning_rate": 2e-05,
      "loss": 0.7104,
      "step": 1960
    },
    {
      "epoch": 0.16448192368706688,
      "grad_norm": 0.3670644164085388,
      "learning_rate": 2e-05,
      "loss": 0.6781,
      "step": 1970
    },
    {
      "epoch": 0.16531685730984386,
      "grad_norm": 0.5817918181419373,
      "learning_rate": 2e-05,
      "loss": 0.717,
      "step": 1980
    },
    {
      "epoch": 0.16615179093262086,
      "grad_norm": 0.37324586510658264,
      "learning_rate": 2e-05,
      "loss": 0.7014,
      "step": 1990
    },
    {
      "epoch": 0.16698672455539784,
      "grad_norm": 0.3925936222076416,
      "learning_rate": 2e-05,
      "loss": 0.7129,
      "step": 2000
    },
    {
      "epoch": 0.16782165817817485,
      "grad_norm": 0.3621346950531006,
      "learning_rate": 2e-05,
      "loss": 0.6613,
      "step": 2010
    },
    {
      "epoch": 0.16865659180095183,
      "grad_norm": 0.412337988615036,
      "learning_rate": 2e-05,
      "loss": 0.7007,
      "step": 2020
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 0.3621259331703186,
      "learning_rate": 2e-05,
      "loss": 0.6655,
      "step": 2030
    },
    {
      "epoch": 0.1703264590465058,
      "grad_norm": 0.37553828954696655,
      "learning_rate": 2e-05,
      "loss": 0.666,
      "step": 2040
    },
    {
      "epoch": 0.1711613926692828,
      "grad_norm": 0.724480390548706,
      "learning_rate": 2e-05,
      "loss": 0.706,
      "step": 2050
    },
    {
      "epoch": 0.17199632629205977,
      "grad_norm": 0.4094829559326172,
      "learning_rate": 2e-05,
      "loss": 0.6642,
      "step": 2060
    },
    {
      "epoch": 0.17283125991483678,
      "grad_norm": 0.36326175928115845,
      "learning_rate": 2e-05,
      "loss": 0.6942,
      "step": 2070
    },
    {
      "epoch": 0.17366619353761376,
      "grad_norm": 0.3996007740497589,
      "learning_rate": 2e-05,
      "loss": 0.7191,
      "step": 2080
    },
    {
      "epoch": 0.17450112716039076,
      "grad_norm": 0.3675718903541565,
      "learning_rate": 2e-05,
      "loss": 0.6668,
      "step": 2090
    },
    {
      "epoch": 0.17533606078316774,
      "grad_norm": 0.4024317264556885,
      "learning_rate": 2e-05,
      "loss": 0.6919,
      "step": 2100
    },
    {
      "epoch": 0.17617099440594472,
      "grad_norm": 0.3986123204231262,
      "learning_rate": 2e-05,
      "loss": 0.716,
      "step": 2110
    },
    {
      "epoch": 0.17700592802872173,
      "grad_norm": 0.42046478390693665,
      "learning_rate": 2e-05,
      "loss": 0.717,
      "step": 2120
    },
    {
      "epoch": 0.1778408616514987,
      "grad_norm": 0.3795027732849121,
      "learning_rate": 2e-05,
      "loss": 0.7137,
      "step": 2130
    },
    {
      "epoch": 0.17867579527427568,
      "grad_norm": 0.39188075065612793,
      "learning_rate": 2e-05,
      "loss": 0.6503,
      "step": 2140
    },
    {
      "epoch": 0.1795107288970527,
      "grad_norm": 0.36276236176490784,
      "learning_rate": 2e-05,
      "loss": 0.6619,
      "step": 2150
    },
    {
      "epoch": 0.18034566251982967,
      "grad_norm": 0.3488128185272217,
      "learning_rate": 2e-05,
      "loss": 0.687,
      "step": 2160
    },
    {
      "epoch": 0.18118059614260668,
      "grad_norm": 0.44784921407699585,
      "learning_rate": 2e-05,
      "loss": 0.6882,
      "step": 2170
    },
    {
      "epoch": 0.18201552976538365,
      "grad_norm": 0.6095040440559387,
      "learning_rate": 2e-05,
      "loss": 0.7301,
      "step": 2180
    },
    {
      "epoch": 0.18285046338816063,
      "grad_norm": 0.3424732983112335,
      "learning_rate": 2e-05,
      "loss": 0.6673,
      "step": 2190
    },
    {
      "epoch": 0.18368539701093764,
      "grad_norm": 0.3422916531562805,
      "learning_rate": 2e-05,
      "loss": 0.7132,
      "step": 2200
    },
    {
      "epoch": 0.18452033063371462,
      "grad_norm": 0.35164374113082886,
      "learning_rate": 2e-05,
      "loss": 0.6696,
      "step": 2210
    },
    {
      "epoch": 0.1853552642564916,
      "grad_norm": 0.401510089635849,
      "learning_rate": 2e-05,
      "loss": 0.6992,
      "step": 2220
    },
    {
      "epoch": 0.1861901978792686,
      "grad_norm": 0.38584569096565247,
      "learning_rate": 2e-05,
      "loss": 0.7115,
      "step": 2230
    },
    {
      "epoch": 0.18702513150204558,
      "grad_norm": 0.3581119477748871,
      "learning_rate": 2e-05,
      "loss": 0.6684,
      "step": 2240
    },
    {
      "epoch": 0.1878600651248226,
      "grad_norm": 0.3552808463573456,
      "learning_rate": 2e-05,
      "loss": 0.6978,
      "step": 2250
    },
    {
      "epoch": 0.18869499874759957,
      "grad_norm": 0.3791872262954712,
      "learning_rate": 2e-05,
      "loss": 0.6649,
      "step": 2260
    },
    {
      "epoch": 0.18952993237037655,
      "grad_norm": 0.4128217399120331,
      "learning_rate": 2e-05,
      "loss": 0.7044,
      "step": 2270
    },
    {
      "epoch": 0.19036486599315355,
      "grad_norm": 0.6670289635658264,
      "learning_rate": 2e-05,
      "loss": 0.7054,
      "step": 2280
    },
    {
      "epoch": 0.19119979961593053,
      "grad_norm": 0.36319422721862793,
      "learning_rate": 2e-05,
      "loss": 0.7108,
      "step": 2290
    },
    {
      "epoch": 0.1920347332387075,
      "grad_norm": 0.37692052125930786,
      "learning_rate": 2e-05,
      "loss": 0.6655,
      "step": 2300
    },
    {
      "epoch": 0.19286966686148452,
      "grad_norm": 0.3617495894432068,
      "learning_rate": 2e-05,
      "loss": 0.6873,
      "step": 2310
    },
    {
      "epoch": 0.1937046004842615,
      "grad_norm": 0.4157564640045166,
      "learning_rate": 2e-05,
      "loss": 0.685,
      "step": 2320
    },
    {
      "epoch": 0.1945395341070385,
      "grad_norm": 0.38732683658599854,
      "learning_rate": 2e-05,
      "loss": 0.679,
      "step": 2330
    },
    {
      "epoch": 0.19537446772981548,
      "grad_norm": 0.4144394099712372,
      "learning_rate": 2e-05,
      "loss": 0.656,
      "step": 2340
    },
    {
      "epoch": 0.19620940135259246,
      "grad_norm": 0.48212432861328125,
      "learning_rate": 2e-05,
      "loss": 0.6674,
      "step": 2350
    },
    {
      "epoch": 0.19704433497536947,
      "grad_norm": 0.4362604022026062,
      "learning_rate": 2e-05,
      "loss": 0.667,
      "step": 2360
    },
    {
      "epoch": 0.19787926859814645,
      "grad_norm": 0.3660829961299896,
      "learning_rate": 2e-05,
      "loss": 0.6783,
      "step": 2370
    },
    {
      "epoch": 0.19871420222092342,
      "grad_norm": 0.4227180778980255,
      "learning_rate": 2e-05,
      "loss": 0.6965,
      "step": 2380
    },
    {
      "epoch": 0.19954913584370043,
      "grad_norm": 0.3671033978462219,
      "learning_rate": 2e-05,
      "loss": 0.7108,
      "step": 2390
    },
    {
      "epoch": 0.2003840694664774,
      "grad_norm": 0.35155659914016724,
      "learning_rate": 2e-05,
      "loss": 0.7087,
      "step": 2400
    },
    {
      "epoch": 0.20121900308925442,
      "grad_norm": 0.3577719032764435,
      "learning_rate": 2e-05,
      "loss": 0.6577,
      "step": 2410
    },
    {
      "epoch": 0.2020539367120314,
      "grad_norm": 0.43237510323524475,
      "learning_rate": 2e-05,
      "loss": 0.7113,
      "step": 2420
    },
    {
      "epoch": 0.20288887033480837,
      "grad_norm": 0.34467509388923645,
      "learning_rate": 2e-05,
      "loss": 0.6869,
      "step": 2430
    },
    {
      "epoch": 0.20372380395758538,
      "grad_norm": 0.41257065534591675,
      "learning_rate": 2e-05,
      "loss": 0.6879,
      "step": 2440
    },
    {
      "epoch": 0.20455873758036236,
      "grad_norm": 0.3533078730106354,
      "learning_rate": 2e-05,
      "loss": 0.6751,
      "step": 2450
    },
    {
      "epoch": 0.20539367120313934,
      "grad_norm": 0.36549070477485657,
      "learning_rate": 2e-05,
      "loss": 0.6968,
      "step": 2460
    },
    {
      "epoch": 0.20622860482591635,
      "grad_norm": 0.3747435212135315,
      "learning_rate": 2e-05,
      "loss": 0.6889,
      "step": 2470
    },
    {
      "epoch": 0.20706353844869332,
      "grad_norm": 0.3561590313911438,
      "learning_rate": 2e-05,
      "loss": 0.6331,
      "step": 2480
    },
    {
      "epoch": 0.20789847207147033,
      "grad_norm": 0.3813934326171875,
      "learning_rate": 2e-05,
      "loss": 0.6936,
      "step": 2490
    },
    {
      "epoch": 0.2087334056942473,
      "grad_norm": 0.3568154573440552,
      "learning_rate": 2e-05,
      "loss": 0.661,
      "step": 2500
    },
    {
      "epoch": 0.2095683393170243,
      "grad_norm": 0.39197221398353577,
      "learning_rate": 2e-05,
      "loss": 0.7107,
      "step": 2510
    },
    {
      "epoch": 0.2104032729398013,
      "grad_norm": 0.4126400351524353,
      "learning_rate": 2e-05,
      "loss": 0.6868,
      "step": 2520
    },
    {
      "epoch": 0.21123820656257827,
      "grad_norm": 0.3978210985660553,
      "learning_rate": 2e-05,
      "loss": 0.6903,
      "step": 2530
    },
    {
      "epoch": 0.21207314018535525,
      "grad_norm": 0.3680487871170044,
      "learning_rate": 2e-05,
      "loss": 0.6785,
      "step": 2540
    },
    {
      "epoch": 0.21290807380813226,
      "grad_norm": 1.4108221530914307,
      "learning_rate": 1.9980979278401095e-05,
      "loss": 0.6436,
      "step": 2550
    },
    {
      "epoch": 0.21374300743090924,
      "grad_norm": 0.34988802671432495,
      "learning_rate": 1.982924955463327e-05,
      "loss": 0.6661,
      "step": 2560
    },
    {
      "epoch": 0.21457794105368624,
      "grad_norm": 0.3819575607776642,
      "learning_rate": 1.9528108298328235e-05,
      "loss": 0.6845,
      "step": 2570
    },
    {
      "epoch": 0.21541287467646322,
      "grad_norm": 0.3862430453300476,
      "learning_rate": 1.9082156473635994e-05,
      "loss": 0.6776,
      "step": 2580
    },
    {
      "epoch": 0.2162478082992402,
      "grad_norm": 0.36327627301216125,
      "learning_rate": 1.8498207522139434e-05,
      "loss": 0.6908,
      "step": 2590
    },
    {
      "epoch": 0.2170827419220172,
      "grad_norm": 0.38857272267341614,
      "learning_rate": 1.7785183264196977e-05,
      "loss": 0.7114,
      "step": 2600
    },
    {
      "epoch": 0.2179176755447942,
      "grad_norm": 0.35029637813568115,
      "learning_rate": 1.6953977587577846e-05,
      "loss": 0.6991,
      "step": 2610
    },
    {
      "epoch": 0.21875260916757117,
      "grad_norm": 0.368362158536911,
      "learning_rate": 1.601729000601297e-05,
      "loss": 0.6687,
      "step": 2620
    },
    {
      "epoch": 0.21958754279034817,
      "grad_norm": 0.3649303913116455,
      "learning_rate": 1.4989431630624763e-05,
      "loss": 0.676,
      "step": 2630
    },
    {
      "epoch": 0.22042247641312515,
      "grad_norm": 0.34498000144958496,
      "learning_rate": 1.3886106518686746e-05,
      "loss": 0.6769,
      "step": 2640
    },
    {
      "epoch": 0.22125741003590216,
      "grad_norm": 0.37302762269973755,
      "learning_rate": 1.2724171740359612e-05,
      "loss": 0.6483,
      "step": 2650
    },
    {
      "epoch": 0.22209234365867914,
      "grad_norm": 0.34686750173568726,
      "learning_rate": 1.1521379829206218e-05,
      "loss": 0.7027,
      "step": 2660
    },
    {
      "epoch": 0.22292727728145612,
      "grad_norm": 0.3529242277145386,
      "learning_rate": 1.029610755143595e-05,
      "loss": 0.6653,
      "step": 2670
    },
    {
      "epoch": 0.22376221090423312,
      "grad_norm": 0.3444066047668457,
      "learning_rate": 9.067075137857348e-06,
      "loss": 0.6943,
      "step": 2680
    },
    {
      "epoch": 0.2245971445270101,
      "grad_norm": 0.345114141702652,
      "learning_rate": 7.853060268232525e-06,
      "loss": 0.669,
      "step": 2690
    },
    {
      "epoch": 0.22543207814978708,
      "grad_norm": 0.3696736991405487,
      "learning_rate": 6.672611177902054e-06,
      "loss": 0.68,
      "step": 2700
    },
    {
      "epoch": 0.2262670117725641,
      "grad_norm": 0.3432908356189728,
      "learning_rate": 5.543763269959312e-06,
      "loss": 0.69,
      "step": 2710
    },
    {
      "epoch": 0.22710194539534106,
      "grad_norm": 0.37657374143600464,
      "learning_rate": 4.483763562693867e-06,
      "loss": 0.6731,
      "step": 2720
    },
    {
      "epoch": 0.22793687901811807,
      "grad_norm": 0.34410977363586426,
      "learning_rate": 3.508807182313187e-06,
      "loss": 0.6885,
      "step": 2730
    },
    {
      "epoch": 0.22877181264089505,
      "grad_norm": 0.38116762042045593,
      "learning_rate": 2.6337899269187294e-06,
      "loss": 0.6915,
      "step": 2740
    },
    {
      "epoch": 0.22960674626367203,
      "grad_norm": 0.3558911681175232,
      "learning_rate": 1.8720806821693126e-06,
      "loss": 0.6957,
      "step": 2750
    },
    {
      "epoch": 0.23044167988644904,
      "grad_norm": 0.3307079076766968,
      "learning_rate": 1.2353171657619887e-06,
      "loss": 0.7067,
      "step": 2760
    },
    {
      "epoch": 0.23127661350922601,
      "grad_norm": 0.36070752143859863,
      "learning_rate": 7.332281214330356e-07,
      "loss": 0.6887,
      "step": 2770
    },
    {
      "epoch": 0.232111547132003,
      "grad_norm": 0.37823721766471863,
      "learning_rate": 3.73484679074808e-07,
      "loss": 0.6586,
      "step": 2780
    },
    {
      "epoch": 0.23294648075478,
      "grad_norm": 0.3465072512626648,
      "learning_rate": 1.61583151951702e-07,
      "loss": 0.6571,
      "step": 2790
    },
    {
      "epoch": 0.23361442765300158,
      "step": 2798,
      "total_flos": 1.1366756130249245e+19,
      "train_loss": 0.06184470440508043,
      "train_runtime": 2300.2617,
      "train_samples_per_second": 14.597,
      "train_steps_per_second": 1.216
    }
  ],
  "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
}