{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2497099509147702,
  "eval_steps": 500,
  "global_step": 2798,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000892458723784025,
      "grad_norm": 3.045154571533203,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 1.3662,
      "step": 10
    },
    {
      "epoch": 0.00178491744756805,
      "grad_norm": 2.2175650596618652,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 1.4403,
      "step": 20
    },
    {
      "epoch": 0.002677376171352075,
      "grad_norm": 1.860337734222412,
      "learning_rate": 3.342134831460675e-06,
      "loss": 1.1652,
      "step": 30
    },
    {
      "epoch": 0.0035698348951361,
      "grad_norm": 0.9244102239608765,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 0.9807,
      "step": 40
    },
    {
      "epoch": 0.004462293618920125,
      "grad_norm": 0.6792669296264648,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 0.8353,
      "step": 50
    },
    {
      "epoch": 0.00535475234270415,
      "grad_norm": 0.47331929206848145,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 0.8033,
      "step": 60
    },
    {
      "epoch": 0.006247211066488175,
      "grad_norm": 0.44425472617149353,
      "learning_rate": 7.814044943820226e-06,
      "loss": 0.7722,
      "step": 70
    },
    {
      "epoch": 0.0071396697902722,
      "grad_norm": 0.48765331506729126,
      "learning_rate": 8.932022471910112e-06,
      "loss": 0.7988,
      "step": 80
    },
    {
      "epoch": 0.008032128514056224,
      "grad_norm": 0.5558447241783142,
      "learning_rate": 1.005e-05,
      "loss": 0.7813,
      "step": 90
    },
    {
      "epoch": 0.00892458723784025,
      "grad_norm": 0.4752425253391266,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.7892,
      "step": 100
    },
    {
      "epoch": 0.009817045961624275,
      "grad_norm": 0.4644387364387512,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.7592,
      "step": 110
    },
    {
      "epoch": 0.0107095046854083,
      "grad_norm": 0.5231781601905823,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.7798,
      "step": 120
    },
    {
      "epoch": 0.011601963409192326,
      "grad_norm": 0.5505983233451843,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.778,
      "step": 130
    },
    {
      "epoch": 0.01249442213297635,
      "grad_norm": 0.805553138256073,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.7573,
      "step": 140
    },
    {
      "epoch": 0.013386880856760375,
      "grad_norm": 0.4206564724445343,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.7692,
      "step": 150
    },
    {
      "epoch": 0.0142793395805444,
      "grad_norm": 0.49315696954727173,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.7773,
      "step": 160
    },
    {
      "epoch": 0.015171798304328426,
      "grad_norm": 0.5224491953849792,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.7728,
      "step": 170
    },
    {
      "epoch": 0.01606425702811245,
      "grad_norm": 0.43197882175445557,
      "learning_rate": 2e-05,
      "loss": 0.7919,
      "step": 180
    },
    {
      "epoch": 0.016956715751896476,
      "grad_norm": 0.49200326204299927,
      "learning_rate": 2e-05,
      "loss": 0.7639,
      "step": 190
    },
    {
      "epoch": 0.0178491744756805,
      "grad_norm": 0.44408541917800903,
      "learning_rate": 2e-05,
      "loss": 0.7361,
      "step": 200
    },
    {
      "epoch": 0.018741633199464525,
      "grad_norm": 0.5795125961303711,
      "learning_rate": 2e-05,
      "loss": 0.8062,
      "step": 210
    },
    {
      "epoch": 0.01963409192324855,
      "grad_norm": 0.4349335730075836,
      "learning_rate": 2e-05,
      "loss": 0.7885,
      "step": 220
    },
    {
      "epoch": 0.020526550647032574,
      "grad_norm": 0.4409690201282501,
      "learning_rate": 2e-05,
      "loss": 0.7942,
      "step": 230
    },
    {
      "epoch": 0.0214190093708166,
      "grad_norm": 0.43803665041923523,
      "learning_rate": 2e-05,
      "loss": 0.7597,
      "step": 240
    },
    {
      "epoch": 0.022311468094600623,
      "grad_norm": 0.43824803829193115,
      "learning_rate": 2e-05,
      "loss": 0.7669,
      "step": 250
    },
    {
      "epoch": 0.02320392681838465,
      "grad_norm": 0.43911799788475037,
      "learning_rate": 2e-05,
      "loss": 0.7453,
      "step": 260
    },
    {
      "epoch": 0.024096385542168676,
      "grad_norm": 0.39943230152130127,
      "learning_rate": 2e-05,
      "loss": 0.7293,
      "step": 270
    },
    {
      "epoch": 0.0249888442659527,
      "grad_norm": 0.44129323959350586,
      "learning_rate": 2e-05,
      "loss": 0.8173,
      "step": 280
    },
    {
      "epoch": 0.025881302989736725,
      "grad_norm": 0.40437787771224976,
      "learning_rate": 2e-05,
      "loss": 0.7626,
      "step": 290
    },
    {
      "epoch": 0.02677376171352075,
      "grad_norm": 0.46044057607650757,
      "learning_rate": 2e-05,
      "loss": 0.7705,
      "step": 300
    },
    {
      "epoch": 0.027666220437304774,
      "grad_norm": 0.5197446346282959,
      "learning_rate": 2e-05,
      "loss": 0.7439,
      "step": 310
    },
    {
      "epoch": 0.0285586791610888,
      "grad_norm": 0.4308314323425293,
      "learning_rate": 2e-05,
      "loss": 0.8261,
      "step": 320
    },
    {
      "epoch": 0.029451137884872823,
      "grad_norm": 0.43585020303726196,
      "learning_rate": 2e-05,
      "loss": 0.7583,
      "step": 330
    },
    {
      "epoch": 0.03034359660865685,
      "grad_norm": 0.43804678320884705,
      "learning_rate": 2e-05,
      "loss": 0.7712,
      "step": 340
    },
    {
      "epoch": 0.031236055332440876,
      "grad_norm": 0.4321230351924896,
      "learning_rate": 2e-05,
      "loss": 0.7558,
      "step": 350
    },
    {
      "epoch": 0.0321285140562249,
      "grad_norm": 0.426249623298645,
      "learning_rate": 2e-05,
      "loss": 0.7652,
      "step": 360
    },
    {
      "epoch": 0.03302097278000892,
      "grad_norm": 0.4081008732318878,
      "learning_rate": 2e-05,
      "loss": 0.7536,
      "step": 370
    },
    {
      "epoch": 0.03391343150379295,
      "grad_norm": 0.6208111047744751,
      "learning_rate": 2e-05,
      "loss": 0.7511,
      "step": 380
    },
    {
      "epoch": 0.03480589022757698,
      "grad_norm": 0.45165306329727173,
      "learning_rate": 2e-05,
      "loss": 0.7612,
      "step": 390
    },
    {
      "epoch": 0.035698348951361,
      "grad_norm": 0.8442327380180359,
      "learning_rate": 2e-05,
      "loss": 0.7757,
      "step": 400
    },
    {
      "epoch": 0.036590807675145026,
      "grad_norm": 0.43777230381965637,
      "learning_rate": 2e-05,
      "loss": 0.7554,
      "step": 410
    },
    {
      "epoch": 0.03748326639892905,
      "grad_norm": 0.4242396950721741,
      "learning_rate": 2e-05,
      "loss": 0.7437,
      "step": 420
    },
    {
      "epoch": 0.038375725122713075,
      "grad_norm": 0.44561508297920227,
      "learning_rate": 2e-05,
      "loss": 0.7579,
      "step": 430
    },
    {
      "epoch": 0.0392681838464971,
      "grad_norm": 0.4057537615299225,
      "learning_rate": 2e-05,
      "loss": 0.7672,
      "step": 440
    },
    {
      "epoch": 0.040160642570281124,
      "grad_norm": 0.4248247444629669,
      "learning_rate": 2e-05,
      "loss": 0.7517,
      "step": 450
    },
    {
      "epoch": 0.04105310129406515,
      "grad_norm": 0.38674187660217285,
      "learning_rate": 2e-05,
      "loss": 0.7649,
      "step": 460
    },
    {
      "epoch": 0.04194556001784917,
      "grad_norm": 0.4590655267238617,
      "learning_rate": 2e-05,
      "loss": 0.7138,
      "step": 470
    },
    {
      "epoch": 0.0428380187416332,
      "grad_norm": 0.38914060592651367,
      "learning_rate": 2e-05,
      "loss": 0.7533,
      "step": 480
    },
    {
      "epoch": 0.04373047746541722,
      "grad_norm": 0.4345904588699341,
      "learning_rate": 2e-05,
      "loss": 0.7323,
      "step": 490
    },
    {
      "epoch": 0.04462293618920125,
      "grad_norm": 0.372398316860199,
      "learning_rate": 2e-05,
      "loss": 0.722,
      "step": 500
    },
    {
      "epoch": 0.04551539491298527,
      "grad_norm": 0.39427366852760315,
      "learning_rate": 2e-05,
      "loss": 0.7649,
      "step": 510
    },
    {
      "epoch": 0.0464078536367693,
      "grad_norm": 0.45776817202568054,
      "learning_rate": 2e-05,
      "loss": 0.761,
      "step": 520
    },
    {
      "epoch": 0.04730031236055333,
      "grad_norm": 0.4311637282371521,
      "learning_rate": 2e-05,
      "loss": 0.7761,
      "step": 530
    },
    {
      "epoch": 0.04819277108433735,
      "grad_norm": 0.3782254457473755,
      "learning_rate": 2e-05,
      "loss": 0.734,
      "step": 540
    },
    {
      "epoch": 0.049085229808121376,
      "grad_norm": 0.4318030774593353,
      "learning_rate": 2e-05,
      "loss": 0.7658,
      "step": 550
    },
    {
      "epoch": 0.0499776885319054,
      "grad_norm": 0.4350939691066742,
      "learning_rate": 2e-05,
      "loss": 0.7765,
      "step": 560
    },
    {
      "epoch": 0.050870147255689425,
      "grad_norm": 0.4095909595489502,
      "learning_rate": 2e-05,
      "loss": 0.76,
      "step": 570
    },
    {
      "epoch": 0.05176260597947345,
      "grad_norm": 0.3846561908721924,
      "learning_rate": 2e-05,
      "loss": 0.7516,
      "step": 580
    },
    {
      "epoch": 0.052655064703257475,
      "grad_norm": 0.4147850573062897,
      "learning_rate": 2e-05,
      "loss": 0.7674,
      "step": 590
    },
    {
      "epoch": 0.0535475234270415,
      "grad_norm": 0.41225138306617737,
      "learning_rate": 2e-05,
      "loss": 0.7489,
      "step": 600
    },
    {
      "epoch": 0.054439982150825524,
      "grad_norm": 0.4051811099052429,
      "learning_rate": 2e-05,
      "loss": 0.7396,
      "step": 610
    },
    {
      "epoch": 0.05533244087460955,
      "grad_norm": 0.3863374590873718,
      "learning_rate": 2e-05,
      "loss": 0.7477,
      "step": 620
    },
    {
      "epoch": 0.05622489959839357,
      "grad_norm": 0.3682566285133362,
      "learning_rate": 2e-05,
      "loss": 0.7675,
      "step": 630
    },
    {
      "epoch": 0.0571173583221776,
      "grad_norm": 0.38680627942085266,
      "learning_rate": 2e-05,
      "loss": 0.7149,
      "step": 640
    },
    {
      "epoch": 0.05800981704596162,
      "grad_norm": 0.4512251317501068,
      "learning_rate": 2e-05,
      "loss": 0.7598,
      "step": 650
    },
    {
      "epoch": 0.058902275769745646,
      "grad_norm": 0.45277082920074463,
      "learning_rate": 2e-05,
      "loss": 0.7227,
      "step": 660
    },
    {
      "epoch": 0.05979473449352968,
      "grad_norm": 0.4341653287410736,
      "learning_rate": 2e-05,
      "loss": 0.7798,
      "step": 670
    },
    {
      "epoch": 0.0606871932173137,
      "grad_norm": 0.4053642749786377,
      "learning_rate": 2e-05,
      "loss": 0.7448,
      "step": 680
    },
    {
      "epoch": 0.06157965194109773,
      "grad_norm": 0.4231747090816498,
      "learning_rate": 2e-05,
      "loss": 0.7582,
      "step": 690
    },
    {
      "epoch": 0.06247211066488175,
      "grad_norm": 0.3956149220466614,
      "learning_rate": 2e-05,
      "loss": 0.7584,
      "step": 700
    },
    {
      "epoch": 0.06336456938866578,
      "grad_norm": 0.4424019157886505,
      "learning_rate": 2e-05,
      "loss": 0.731,
      "step": 710
    },
    {
      "epoch": 0.0642570281124498,
      "grad_norm": 0.44977128505706787,
      "learning_rate": 2e-05,
      "loss": 0.7346,
      "step": 720
    },
    {
      "epoch": 0.06514948683623382,
      "grad_norm": 0.4080374240875244,
      "learning_rate": 2e-05,
      "loss": 0.7478,
      "step": 730
    },
    {
      "epoch": 0.06604194556001784,
      "grad_norm": 0.40351366996765137,
      "learning_rate": 2e-05,
      "loss": 0.7308,
      "step": 740
    },
    {
      "epoch": 0.06693440428380187,
      "grad_norm": 0.3880046606063843,
      "learning_rate": 2e-05,
      "loss": 0.7466,
      "step": 750
    },
    {
      "epoch": 0.0678268630075859,
      "grad_norm": 0.3946651518344879,
      "learning_rate": 2e-05,
      "loss": 0.7579,
      "step": 760
    },
    {
      "epoch": 0.06871932173136992,
      "grad_norm": 0.3880173861980438,
      "learning_rate": 2e-05,
      "loss": 0.7346,
      "step": 770
    },
    {
      "epoch": 0.06961178045515395,
      "grad_norm": 0.38916459679603577,
      "learning_rate": 2e-05,
      "loss": 0.7219,
      "step": 780
    },
    {
      "epoch": 0.07050423917893797,
      "grad_norm": 0.3937828838825226,
      "learning_rate": 2e-05,
      "loss": 0.76,
      "step": 790
    },
    {
      "epoch": 0.071396697902722,
      "grad_norm": 0.43031296133995056,
      "learning_rate": 2e-05,
      "loss": 0.758,
      "step": 800
    },
    {
      "epoch": 0.07228915662650602,
      "grad_norm": 0.4201333224773407,
      "learning_rate": 2e-05,
      "loss": 0.7449,
      "step": 810
    },
    {
      "epoch": 0.07318161535029005,
      "grad_norm": 0.3999972343444824,
      "learning_rate": 2e-05,
      "loss": 0.7487,
      "step": 820
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.39585524797439575,
      "learning_rate": 2e-05,
      "loss": 0.7076,
      "step": 830
    },
    {
      "epoch": 0.0749665327978581,
      "grad_norm": 0.3961842656135559,
      "learning_rate": 2e-05,
      "loss": 0.7031,
      "step": 840
    },
    {
      "epoch": 0.07585899152164212,
      "grad_norm": 0.3905622363090515,
      "learning_rate": 2e-05,
      "loss": 0.7484,
      "step": 850
    },
    {
      "epoch": 0.07675145024542615,
      "grad_norm": 0.40534672141075134,
      "learning_rate": 2e-05,
      "loss": 0.739,
      "step": 860
    },
    {
      "epoch": 0.07764390896921017,
      "grad_norm": 0.38796329498291016,
      "learning_rate": 2e-05,
      "loss": 0.7236,
      "step": 870
    },
    {
      "epoch": 0.0785363676929942,
      "grad_norm": 0.5421860218048096,
      "learning_rate": 2e-05,
      "loss": 0.7263,
      "step": 880
    },
    {
      "epoch": 0.07942882641677822,
      "grad_norm": 0.4691896140575409,
      "learning_rate": 2e-05,
      "loss": 0.7289,
      "step": 890
    },
    {
      "epoch": 0.08032128514056225,
      "grad_norm": 0.4255770742893219,
      "learning_rate": 2e-05,
      "loss": 0.7399,
      "step": 900
    },
    {
      "epoch": 0.08121374386434628,
      "grad_norm": 0.3914809823036194,
      "learning_rate": 2e-05,
      "loss": 0.7908,
      "step": 910
    },
    {
      "epoch": 0.0821062025881303,
      "grad_norm": 0.3992801010608673,
      "learning_rate": 2e-05,
      "loss": 0.7144,
      "step": 920
    },
    {
      "epoch": 0.08299866131191433,
      "grad_norm": 0.3806823194026947,
      "learning_rate": 2e-05,
      "loss": 0.7471,
      "step": 930
    },
    {
      "epoch": 0.08389112003569835,
      "grad_norm": 0.546196460723877,
      "learning_rate": 2e-05,
      "loss": 0.6958,
      "step": 940
    },
    {
      "epoch": 0.08478357875948238,
      "grad_norm": 0.5522550344467163,
      "learning_rate": 2e-05,
      "loss": 0.7481,
      "step": 950
    },
    {
      "epoch": 0.0856760374832664,
      "grad_norm": 0.421906977891922,
      "learning_rate": 2e-05,
      "loss": 0.7771,
      "step": 960
    },
    {
      "epoch": 0.08656849620705043,
      "grad_norm": 0.381605327129364,
      "learning_rate": 2e-05,
      "loss": 0.7512,
      "step": 970
    },
    {
      "epoch": 0.08746095493083444,
      "grad_norm": 0.5547103881835938,
      "learning_rate": 2e-05,
      "loss": 0.7529,
      "step": 980
    },
    {
      "epoch": 0.08835341365461848,
      "grad_norm": 0.41171810030937195,
      "learning_rate": 2e-05,
      "loss": 0.7224,
      "step": 990
    },
    {
      "epoch": 0.0892458723784025,
      "grad_norm": 0.3596498370170593,
      "learning_rate": 2e-05,
      "loss": 0.7414,
      "step": 1000
    },
    {
      "epoch": 0.09013833110218653,
      "grad_norm": 0.46202516555786133,
      "learning_rate": 2e-05,
      "loss": 0.7322,
      "step": 1010
    },
    {
      "epoch": 0.09103078982597054,
      "grad_norm": 0.39855870604515076,
      "learning_rate": 2e-05,
      "loss": 0.7243,
      "step": 1020
    },
    {
      "epoch": 0.09192324854975457,
      "grad_norm": 0.38900578022003174,
      "learning_rate": 2e-05,
      "loss": 0.7178,
      "step": 1030
    },
    {
      "epoch": 0.0928157072735386,
      "grad_norm": 0.4451678395271301,
      "learning_rate": 2e-05,
      "loss": 0.7473,
      "step": 1040
    },
    {
      "epoch": 0.09370816599732262,
      "grad_norm": 0.3663797676563263,
      "learning_rate": 2e-05,
      "loss": 0.7148,
      "step": 1050
    },
    {
      "epoch": 0.09460062472110665,
      "grad_norm": 0.3737003803253174,
      "learning_rate": 2e-05,
      "loss": 0.7308,
      "step": 1060
    },
    {
      "epoch": 0.09549308344489067,
      "grad_norm": 0.5132238864898682,
      "learning_rate": 2e-05,
      "loss": 0.7483,
      "step": 1070
    },
    {
      "epoch": 0.0963855421686747,
      "grad_norm": 0.39757436513900757,
      "learning_rate": 2e-05,
      "loss": 0.7055,
      "step": 1080
    },
    {
      "epoch": 0.09727800089245872,
      "grad_norm": 0.3889594078063965,
      "learning_rate": 2e-05,
      "loss": 0.7647,
      "step": 1090
    },
    {
      "epoch": 0.09817045961624275,
      "grad_norm": 0.40366658568382263,
      "learning_rate": 2e-05,
      "loss": 0.7453,
      "step": 1100
    },
    {
      "epoch": 0.09906291834002677,
      "grad_norm": 0.37995877861976624,
      "learning_rate": 2e-05,
      "loss": 0.7417,
      "step": 1110
    },
    {
      "epoch": 0.0999553770638108,
      "grad_norm": 0.3837803304195404,
      "learning_rate": 2e-05,
      "loss": 0.728,
      "step": 1120
    },
    {
      "epoch": 0.10084783578759482,
      "grad_norm": 0.37044045329093933,
      "learning_rate": 2e-05,
      "loss": 0.7216,
      "step": 1130
    },
    {
      "epoch": 0.10174029451137885,
      "grad_norm": 0.3822389245033264,
      "learning_rate": 2e-05,
      "loss": 0.7075,
      "step": 1140
    },
    {
      "epoch": 0.10263275323516287,
      "grad_norm": 0.3520481288433075,
      "learning_rate": 2e-05,
      "loss": 0.7131,
      "step": 1150
    },
    {
      "epoch": 0.1035252119589469,
      "grad_norm": 0.38390985131263733,
      "learning_rate": 2e-05,
      "loss": 0.7559,
      "step": 1160
    },
    {
      "epoch": 0.10441767068273092,
      "grad_norm": 0.3780132830142975,
      "learning_rate": 2e-05,
      "loss": 0.7224,
      "step": 1170
    },
    {
      "epoch": 0.10531012940651495,
      "grad_norm": 0.4197860062122345,
      "learning_rate": 2e-05,
      "loss": 0.7275,
      "step": 1180
    },
    {
      "epoch": 0.10620258813029898,
      "grad_norm": 0.3551185131072998,
      "learning_rate": 2e-05,
      "loss": 0.7118,
      "step": 1190
    },
    {
      "epoch": 0.107095046854083,
      "grad_norm": 0.36302730441093445,
      "learning_rate": 2e-05,
      "loss": 0.7032,
      "step": 1200
    },
    {
      "epoch": 0.10798750557786703,
      "grad_norm": 0.4428386688232422,
      "learning_rate": 2e-05,
      "loss": 0.7687,
      "step": 1210
    },
    {
      "epoch": 0.10887996430165105,
      "grad_norm": 0.3998299539089203,
      "learning_rate": 2e-05,
      "loss": 0.7204,
      "step": 1220
    },
    {
      "epoch": 0.10977242302543508,
      "grad_norm": 0.3677099347114563,
      "learning_rate": 2e-05,
      "loss": 0.7057,
      "step": 1230
    },
    {
      "epoch": 0.1106648817492191,
      "grad_norm": 0.4453865885734558,
      "learning_rate": 2e-05,
      "loss": 0.7309,
      "step": 1240
    },
    {
      "epoch": 0.11155734047300313,
      "grad_norm": 0.35671019554138184,
      "learning_rate": 2e-05,
      "loss": 0.6845,
      "step": 1250
    },
    {
      "epoch": 0.11244979919678715,
      "grad_norm": 0.38202935457229614,
      "learning_rate": 2e-05,
      "loss": 0.72,
      "step": 1260
    },
    {
      "epoch": 0.11334225792057118,
      "grad_norm": 0.38386300206184387,
      "learning_rate": 2e-05,
      "loss": 0.7228,
      "step": 1270
    },
    {
      "epoch": 0.1142347166443552,
      "grad_norm": 0.41439297795295715,
      "learning_rate": 2e-05,
      "loss": 0.7334,
      "step": 1280
    },
    {
      "epoch": 0.11512717536813923,
      "grad_norm": 0.39205095171928406,
      "learning_rate": 2e-05,
      "loss": 0.7325,
      "step": 1290
    },
    {
      "epoch": 0.11601963409192324,
      "grad_norm": 0.4260752201080322,
      "learning_rate": 2e-05,
      "loss": 0.7129,
      "step": 1300
    },
    {
      "epoch": 0.11691209281570727,
      "grad_norm": 0.35168108344078064,
      "learning_rate": 2e-05,
      "loss": 0.7003,
      "step": 1310
    },
    {
      "epoch": 0.11780455153949129,
      "grad_norm": 0.354591965675354,
      "learning_rate": 2e-05,
      "loss": 0.7081,
      "step": 1320
    },
    {
      "epoch": 0.11869701026327532,
      "grad_norm": 0.3994496762752533,
      "learning_rate": 2e-05,
      "loss": 0.7348,
      "step": 1330
    },
    {
      "epoch": 0.11958946898705936,
      "grad_norm": 0.3687463402748108,
      "learning_rate": 2e-05,
      "loss": 0.7138,
      "step": 1340
    },
    {
      "epoch": 0.12048192771084337,
      "grad_norm": 0.3527894914150238,
      "learning_rate": 2e-05,
      "loss": 0.7331,
      "step": 1350
    },
    {
      "epoch": 0.1213743864346274,
      "grad_norm": 0.39547526836395264,
      "learning_rate": 2e-05,
      "loss": 0.6874,
      "step": 1360
    },
    {
      "epoch": 0.12226684515841142,
      "grad_norm": 0.35508838295936584,
      "learning_rate": 2e-05,
      "loss": 0.7588,
      "step": 1370
    },
    {
      "epoch": 0.12315930388219545,
      "grad_norm": 0.3983374238014221,
      "learning_rate": 2e-05,
      "loss": 0.7383,
      "step": 1380
    },
    {
      "epoch": 0.12405176260597947,
      "grad_norm": 0.35641518235206604,
      "learning_rate": 2e-05,
      "loss": 0.7357,
      "step": 1390
    },
    {
      "epoch": 0.1249442213297635,
      "grad_norm": 0.41379478573799133,
      "learning_rate": 2e-05,
      "loss": 0.7257,
      "step": 1400
    },
    {
      "epoch": 0.12583668005354753,
      "grad_norm": 0.39988917112350464,
      "learning_rate": 2e-05,
      "loss": 0.7272,
      "step": 1410
    },
    {
      "epoch": 0.12672913877733155,
      "grad_norm": 0.3463815152645111,
      "learning_rate": 2e-05,
      "loss": 0.7595,
      "step": 1420
    },
    {
      "epoch": 0.12762159750111557,
      "grad_norm": 0.36326804757118225,
      "learning_rate": 2e-05,
      "loss": 0.6967,
      "step": 1430
    },
    {
      "epoch": 0.1285140562248996,
      "grad_norm": 0.3950536251068115,
      "learning_rate": 2e-05,
      "loss": 0.686,
      "step": 1440
    },
    {
      "epoch": 0.12940651494868363,
      "grad_norm": 0.43041136860847473,
      "learning_rate": 2e-05,
      "loss": 0.7122,
      "step": 1450
    },
    {
      "epoch": 0.13029897367246765,
      "grad_norm": 0.40778934955596924,
      "learning_rate": 2e-05,
      "loss": 0.7107,
      "step": 1460
    },
    {
      "epoch": 0.13119143239625167,
      "grad_norm": 0.37620630860328674,
      "learning_rate": 2e-05,
      "loss": 0.7352,
      "step": 1470
    },
    {
      "epoch": 0.13208389112003568,
      "grad_norm": 0.34521961212158203,
      "learning_rate": 2e-05,
      "loss": 0.725,
      "step": 1480
    },
    {
      "epoch": 0.13297634984381973,
      "grad_norm": 0.4491102397441864,
      "learning_rate": 2e-05,
      "loss": 0.7313,
      "step": 1490
    },
    {
      "epoch": 0.13386880856760375,
      "grad_norm": 0.3915207087993622,
      "learning_rate": 2e-05,
      "loss": 0.7185,
      "step": 1500
    },
    {
      "epoch": 0.13476126729138777,
      "grad_norm": 0.40829235315322876,
      "learning_rate": 2e-05,
      "loss": 0.7266,
      "step": 1510
    },
    {
      "epoch": 0.1356537260151718,
      "grad_norm": 0.4085201323032379,
      "learning_rate": 2e-05,
      "loss": 0.7142,
      "step": 1520
    },
    {
      "epoch": 0.13654618473895583,
      "grad_norm": 0.3529062569141388,
      "learning_rate": 2e-05,
      "loss": 0.7092,
      "step": 1530
    },
    {
      "epoch": 0.13743864346273985,
      "grad_norm": 0.360169917345047,
      "learning_rate": 2e-05,
      "loss": 0.7402,
      "step": 1540
    },
    {
      "epoch": 0.13833110218652386,
      "grad_norm": 0.4295094907283783,
      "learning_rate": 2e-05,
      "loss": 0.7528,
      "step": 1550
    },
    {
      "epoch": 0.1392235609103079,
      "grad_norm": 0.38765519857406616,
      "learning_rate": 2e-05,
      "loss": 0.7173,
      "step": 1560
    },
    {
      "epoch": 0.14011601963409193,
      "grad_norm": 0.4022582769393921,
      "learning_rate": 2e-05,
      "loss": 0.6994,
      "step": 1570
    },
    {
      "epoch": 0.14100847835787594,
      "grad_norm": 0.39251431822776794,
      "learning_rate": 2e-05,
      "loss": 0.7394,
      "step": 1580
    },
    {
      "epoch": 0.14190093708165996,
      "grad_norm": 0.4118332862854004,
      "learning_rate": 2e-05,
      "loss": 0.7361,
      "step": 1590
    },
    {
      "epoch": 0.142793395805444,
      "grad_norm": 0.39799195528030396,
      "learning_rate": 2e-05,
      "loss": 0.6995,
      "step": 1600
    },
    {
      "epoch": 0.14368585452922802,
      "grad_norm": 0.35336437821388245,
      "learning_rate": 2e-05,
      "loss": 0.755,
      "step": 1610
    },
    {
      "epoch": 0.14457831325301204,
      "grad_norm": 0.39616140723228455,
      "learning_rate": 2e-05,
      "loss": 0.7043,
      "step": 1620
    },
    {
      "epoch": 0.14547077197679606,
      "grad_norm": 0.3775366246700287,
      "learning_rate": 2e-05,
      "loss": 0.723,
      "step": 1630
    },
    {
      "epoch": 0.1463632307005801,
      "grad_norm": 0.38130348920822144,
      "learning_rate": 2e-05,
      "loss": 0.7029,
      "step": 1640
    },
    {
      "epoch": 0.14725568942436412,
      "grad_norm": 0.7423177361488342,
      "learning_rate": 2e-05,
      "loss": 0.7276,
      "step": 1650
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.3703177273273468,
      "learning_rate": 2e-05,
      "loss": 0.7094,
      "step": 1660
    },
    {
      "epoch": 0.14904060687193219,
      "grad_norm": 0.36464789509773254,
      "learning_rate": 2e-05,
      "loss": 0.6968,
      "step": 1670
    },
    {
      "epoch": 0.1499330655957162,
      "grad_norm": 0.3765050172805786,
      "learning_rate": 2e-05,
      "loss": 0.73,
      "step": 1680
    },
    {
      "epoch": 0.15082552431950022,
      "grad_norm": 0.36146077513694763,
      "learning_rate": 2e-05,
      "loss": 0.6911,
      "step": 1690
    },
    {
      "epoch": 0.15171798304328424,
      "grad_norm": 0.3474405109882355,
      "learning_rate": 2e-05,
      "loss": 0.7045,
      "step": 1700
    },
    {
      "epoch": 0.15261044176706828,
      "grad_norm": 0.396933913230896,
      "learning_rate": 2e-05,
      "loss": 0.7363,
      "step": 1710
    },
    {
      "epoch": 0.1535029004908523,
      "grad_norm": 0.37580183148384094,
      "learning_rate": 2e-05,
      "loss": 0.7219,
      "step": 1720
    },
    {
      "epoch": 0.15439535921463632,
      "grad_norm": 0.3710784614086151,
      "learning_rate": 2e-05,
      "loss": 0.7089,
      "step": 1730
    },
    {
      "epoch": 0.15528781793842034,
      "grad_norm": 0.36403852701187134,
      "learning_rate": 2e-05,
      "loss": 0.7111,
      "step": 1740
    },
    {
      "epoch": 0.15618027666220438,
      "grad_norm": 0.5121102333068848,
      "learning_rate": 2e-05,
      "loss": 0.7,
      "step": 1750
    },
    {
      "epoch": 0.1570727353859884,
      "grad_norm": 0.38486865162849426,
      "learning_rate": 2e-05,
      "loss": 0.7475,
      "step": 1760
    },
    {
      "epoch": 0.15796519410977242,
      "grad_norm": 0.35487449169158936,
      "learning_rate": 2e-05,
      "loss": 0.7121,
      "step": 1770
    },
    {
      "epoch": 0.15885765283355643,
      "grad_norm": 0.36509183049201965,
      "learning_rate": 2e-05,
      "loss": 0.7385,
      "step": 1780
    },
    {
      "epoch": 0.15975011155734048,
      "grad_norm": 0.43019792437553406,
      "learning_rate": 2e-05,
      "loss": 0.7413,
      "step": 1790
    },
    {
      "epoch": 0.1606425702811245,
      "grad_norm": 0.3725093901157379,
      "learning_rate": 2e-05,
      "loss": 0.7075,
      "step": 1800
    },
    {
      "epoch": 0.16153502900490851,
      "grad_norm": 0.4121997356414795,
      "learning_rate": 2e-05,
      "loss": 0.7195,
      "step": 1810
    },
    {
      "epoch": 0.16242748772869256,
      "grad_norm": 0.36837446689605713,
      "learning_rate": 2e-05,
      "loss": 0.7398,
      "step": 1820
    },
    {
      "epoch": 0.16331994645247658,
      "grad_norm": 0.3591003715991974,
      "learning_rate": 2e-05,
      "loss": 0.7011,
      "step": 1830
    },
    {
      "epoch": 0.1642124051762606,
      "grad_norm": 0.38240692019462585,
      "learning_rate": 2e-05,
      "loss": 0.7141,
      "step": 1840
    },
    {
      "epoch": 0.1651048639000446,
      "grad_norm": 0.3967023491859436,
      "learning_rate": 2e-05,
      "loss": 0.7348,
      "step": 1850
    },
    {
      "epoch": 0.16599732262382866,
      "grad_norm": 0.5831686854362488,
      "learning_rate": 2e-05,
      "loss": 0.7106,
      "step": 1860
    },
    {
      "epoch": 0.16688978134761268,
      "grad_norm": 0.3728710412979126,
      "learning_rate": 2e-05,
      "loss": 0.6938,
      "step": 1870
    },
    {
      "epoch": 0.1677822400713967,
      "grad_norm": 0.4233781695365906,
      "learning_rate": 2e-05,
      "loss": 0.7282,
      "step": 1880
    },
    {
      "epoch": 0.1686746987951807,
      "grad_norm": 0.38467922806739807,
      "learning_rate": 2e-05,
      "loss": 0.7001,
      "step": 1890
    },
    {
      "epoch": 0.16956715751896476,
      "grad_norm": 0.35904461145401,
      "learning_rate": 2e-05,
      "loss": 0.713,
      "step": 1900
    },
    {
      "epoch": 0.17045961624274877,
      "grad_norm": 0.3828829526901245,
      "learning_rate": 2e-05,
      "loss": 0.6828,
      "step": 1910
    },
    {
      "epoch": 0.1713520749665328,
      "grad_norm": 0.35955435037612915,
      "learning_rate": 2e-05,
      "loss": 0.7209,
      "step": 1920
    },
    {
      "epoch": 0.17224453369031684,
      "grad_norm": 0.3535810708999634,
      "learning_rate": 2e-05,
      "loss": 0.7072,
      "step": 1930
    },
    {
      "epoch": 0.17313699241410085,
      "grad_norm": 0.3620419502258301,
      "learning_rate": 2e-05,
      "loss": 0.7045,
      "step": 1940
    },
    {
      "epoch": 0.17402945113788487,
      "grad_norm": 0.37288907170295715,
      "learning_rate": 2e-05,
      "loss": 0.7701,
      "step": 1950
    },
    {
      "epoch": 0.1749219098616689,
      "grad_norm": 0.36177289485931396,
      "learning_rate": 2e-05,
      "loss": 0.695,
      "step": 1960
    },
    {
      "epoch": 0.17581436858545293,
      "grad_norm": 0.46705108880996704,
      "learning_rate": 2e-05,
      "loss": 0.7036,
      "step": 1970
    },
    {
      "epoch": 0.17670682730923695,
      "grad_norm": 0.38864728808403015,
      "learning_rate": 2e-05,
      "loss": 0.695,
      "step": 1980
    },
    {
      "epoch": 0.17759928603302097,
      "grad_norm": 0.3607434332370758,
      "learning_rate": 2e-05,
      "loss": 0.7111,
      "step": 1990
    },
    {
      "epoch": 0.178491744756805,
      "grad_norm": 0.36717599630355835,
      "learning_rate": 2e-05,
      "loss": 0.691,
      "step": 2000
    },
    {
      "epoch": 0.17938420348058903,
      "grad_norm": 0.36441174149513245,
      "learning_rate": 2e-05,
      "loss": 0.6795,
      "step": 2010
    },
    {
      "epoch": 0.18027666220437305,
      "grad_norm": 0.42372533679008484,
      "learning_rate": 2e-05,
      "loss": 0.7215,
      "step": 2020
    },
    {
      "epoch": 0.18116912092815707,
      "grad_norm": 0.41000911593437195,
      "learning_rate": 2e-05,
      "loss": 0.7257,
      "step": 2030
    },
    {
      "epoch": 0.18206157965194109,
      "grad_norm": 0.40014421939849854,
      "learning_rate": 2e-05,
      "loss": 0.702,
      "step": 2040
    },
    {
      "epoch": 0.18295403837572513,
      "grad_norm": 0.3575685918331146,
      "learning_rate": 2e-05,
      "loss": 0.7076,
      "step": 2050
    },
    {
      "epoch": 0.18384649709950915,
      "grad_norm": 0.3880053460597992,
      "learning_rate": 2e-05,
      "loss": 0.6628,
      "step": 2060
    },
    {
      "epoch": 0.18473895582329317,
      "grad_norm": 0.3879825472831726,
      "learning_rate": 2e-05,
      "loss": 0.711,
      "step": 2070
    },
    {
      "epoch": 0.1856314145470772,
      "grad_norm": 0.3911679983139038,
      "learning_rate": 2e-05,
      "loss": 0.7285,
      "step": 2080
    },
    {
      "epoch": 0.18652387327086123,
      "grad_norm": 0.35667601227760315,
      "learning_rate": 2e-05,
      "loss": 0.7385,
      "step": 2090
    },
    {
      "epoch": 0.18741633199464525,
      "grad_norm": 0.4055507779121399,
      "learning_rate": 2e-05,
      "loss": 0.7087,
      "step": 2100
    },
    {
      "epoch": 0.18830879071842926,
      "grad_norm": 0.34139570593833923,
      "learning_rate": 2e-05,
      "loss": 0.7122,
      "step": 2110
    },
    {
      "epoch": 0.1892012494422133,
      "grad_norm": 0.40417465567588806,
      "learning_rate": 2e-05,
      "loss": 0.7251,
      "step": 2120
    },
    {
      "epoch": 0.19009370816599733,
      "grad_norm": 0.41374412178993225,
      "learning_rate": 2e-05,
      "loss": 0.6949,
      "step": 2130
    },
    {
      "epoch": 0.19098616688978134,
      "grad_norm": 0.3738286793231964,
      "learning_rate": 2e-05,
      "loss": 0.6991,
      "step": 2140
    },
    {
      "epoch": 0.19187862561356536,
      "grad_norm": 0.36283162236213684,
      "learning_rate": 2e-05,
      "loss": 0.7033,
      "step": 2150
    },
    {
      "epoch": 0.1927710843373494,
      "grad_norm": 0.40305814146995544,
      "learning_rate": 2e-05,
      "loss": 0.7036,
      "step": 2160
    },
    {
      "epoch": 0.19366354306113343,
      "grad_norm": 0.4250462055206299,
      "learning_rate": 2e-05,
      "loss": 0.7248,
      "step": 2170
    },
    {
      "epoch": 0.19455600178491744,
      "grad_norm": 0.3769831359386444,
      "learning_rate": 2e-05,
      "loss": 0.7055,
      "step": 2180
    },
    {
      "epoch": 0.19544846050870146,
      "grad_norm": 0.35918813943862915,
      "learning_rate": 2e-05,
      "loss": 0.676,
      "step": 2190
    },
    {
      "epoch": 0.1963409192324855,
      "grad_norm": 0.3661561906337738,
      "learning_rate": 2e-05,
      "loss": 0.7058,
      "step": 2200
    },
    {
      "epoch": 0.19723337795626952,
      "grad_norm": 0.32479768991470337,
      "learning_rate": 2e-05,
      "loss": 0.6975,
      "step": 2210
    },
    {
      "epoch": 0.19812583668005354,
      "grad_norm": 0.36116334795951843,
      "learning_rate": 2e-05,
      "loss": 0.7006,
      "step": 2220
    },
    {
      "epoch": 0.1990182954038376,
      "grad_norm": 0.3757176995277405,
      "learning_rate": 2e-05,
      "loss": 0.6867,
      "step": 2230
    },
    {
      "epoch": 0.1999107541276216,
      "grad_norm": 0.3349403440952301,
      "learning_rate": 2e-05,
      "loss": 0.7119,
      "step": 2240
    },
    {
      "epoch": 0.20080321285140562,
      "grad_norm": 0.41477563977241516,
      "learning_rate": 2e-05,
      "loss": 0.6737,
      "step": 2250
    },
    {
      "epoch": 0.20169567157518964,
      "grad_norm": 0.7723550796508789,
      "learning_rate": 2e-05,
      "loss": 0.7063,
      "step": 2260
    },
    {
      "epoch": 0.20258813029897368,
      "grad_norm": 0.3693602979183197,
      "learning_rate": 2e-05,
      "loss": 0.7431,
      "step": 2270
    },
    {
      "epoch": 0.2034805890227577,
      "grad_norm": 0.4255744218826294,
      "learning_rate": 2e-05,
      "loss": 0.7051,
      "step": 2280
    },
    {
      "epoch": 0.20437304774654172,
      "grad_norm": 0.3678276836872101,
      "learning_rate": 2e-05,
      "loss": 0.6955,
      "step": 2290
    },
    {
      "epoch": 0.20526550647032574,
      "grad_norm": 0.39403510093688965,
      "learning_rate": 2e-05,
      "loss": 0.6889,
      "step": 2300
    },
    {
      "epoch": 0.20615796519410978,
      "grad_norm": 0.3570137023925781,
      "learning_rate": 2e-05,
      "loss": 0.7089,
      "step": 2310
    },
    {
      "epoch": 0.2070504239178938,
      "grad_norm": 0.3645356297492981,
      "learning_rate": 2e-05,
      "loss": 0.7132,
      "step": 2320
    },
    {
      "epoch": 0.20794288264167782,
      "grad_norm": 0.36887142062187195,
      "learning_rate": 2e-05,
      "loss": 0.7095,
      "step": 2330
    },
    {
      "epoch": 0.20883534136546184,
      "grad_norm": 0.3418295085430145,
      "learning_rate": 2e-05,
      "loss": 0.7006,
      "step": 2340
    },
    {
      "epoch": 0.20972780008924588,
      "grad_norm": 0.3889702260494232,
      "learning_rate": 2e-05,
      "loss": 0.7043,
      "step": 2350
    },
    {
      "epoch": 0.2106202588130299,
      "grad_norm": 0.3959186375141144,
      "learning_rate": 2e-05,
      "loss": 0.7222,
      "step": 2360
    },
    {
      "epoch": 0.21151271753681392,
      "grad_norm": 0.34344956278800964,
      "learning_rate": 2e-05,
      "loss": 0.708,
      "step": 2370
    },
    {
      "epoch": 0.21240517626059796,
      "grad_norm": 0.3525504171848297,
      "learning_rate": 2e-05,
      "loss": 0.7142,
      "step": 2380
    },
    {
      "epoch": 0.21329763498438198,
      "grad_norm": 0.36897340416908264,
      "learning_rate": 2e-05,
      "loss": 0.7233,
      "step": 2390
    },
    {
      "epoch": 0.214190093708166,
      "grad_norm": 0.3377510607242584,
      "learning_rate": 2e-05,
      "loss": 0.72,
      "step": 2400
    },
    {
      "epoch": 0.21508255243195,
      "grad_norm": 0.39910000562667847,
      "learning_rate": 2e-05,
      "loss": 0.7211,
      "step": 2410
    },
    {
      "epoch": 0.21597501115573406,
      "grad_norm": 0.3923272490501404,
      "learning_rate": 2e-05,
      "loss": 0.6979,
      "step": 2420
    },
    {
      "epoch": 0.21686746987951808,
      "grad_norm": 0.4154103398323059,
      "learning_rate": 2e-05,
      "loss": 0.7031,
      "step": 2430
    },
    {
      "epoch": 0.2177599286033021,
      "grad_norm": 0.40713241696357727,
      "learning_rate": 2e-05,
      "loss": 0.6988,
      "step": 2440
    },
    {
      "epoch": 0.2186523873270861,
      "grad_norm": 0.3655557930469513,
      "learning_rate": 2e-05,
      "loss": 0.6843,
      "step": 2450
    },
    {
      "epoch": 0.21954484605087016,
      "grad_norm": 0.3539635241031647,
      "learning_rate": 2e-05,
      "loss": 0.7085,
      "step": 2460
    },
    {
      "epoch": 0.22043730477465417,
      "grad_norm": 0.41050246357917786,
      "learning_rate": 2e-05,
      "loss": 0.6647,
      "step": 2470
    },
    {
      "epoch": 0.2213297634984382,
      "grad_norm": 0.36172372102737427,
      "learning_rate": 2e-05,
      "loss": 0.706,
      "step": 2480
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.5249997973442078,
      "learning_rate": 2e-05,
      "loss": 0.7144,
      "step": 2490
    },
    {
      "epoch": 0.22311468094600626,
      "grad_norm": 0.3864399194717407,
      "learning_rate": 2e-05,
      "loss": 0.7189,
      "step": 2500
    },
    {
      "epoch": 0.22400713966979027,
      "grad_norm": 0.4319363236427307,
      "learning_rate": 2e-05,
      "loss": 0.7015,
      "step": 2510
    },
    {
      "epoch": 0.2248995983935743,
      "grad_norm": 0.3635087013244629,
      "learning_rate": 2e-05,
      "loss": 0.6695,
      "step": 2520
    },
    {
      "epoch": 0.22579205711735834,
      "grad_norm": 0.35824811458587646,
      "learning_rate": 2e-05,
      "loss": 0.6949,
      "step": 2530
    },
    {
      "epoch": 0.22668451584114235,
      "grad_norm": 0.375846803188324,
      "learning_rate": 2e-05,
      "loss": 0.7237,
      "step": 2540
    },
    {
      "epoch": 0.22757697456492637,
      "grad_norm": 0.35961419343948364,
      "learning_rate": 1.9980979278401095e-05,
      "loss": 0.6959,
      "step": 2550
    },
    {
      "epoch": 0.2284694332887104,
      "grad_norm": 0.39512118697166443,
      "learning_rate": 1.982924955463327e-05,
      "loss": 0.7104,
      "step": 2560
    },
    {
      "epoch": 0.22936189201249443,
      "grad_norm": 0.3508082330226898,
      "learning_rate": 1.9528108298328235e-05,
      "loss": 0.6941,
      "step": 2570
    },
    {
      "epoch": 0.23025435073627845,
      "grad_norm": 0.3879809081554413,
      "learning_rate": 1.9082156473635994e-05,
      "loss": 0.7203,
      "step": 2580
    },
    {
      "epoch": 0.23114680946006247,
      "grad_norm": 0.4604385793209076,
      "learning_rate": 1.8498207522139434e-05,
      "loss": 0.718,
      "step": 2590
    },
    {
      "epoch": 0.2320392681838465,
      "grad_norm": 0.3951204717159271,
      "learning_rate": 1.7785183264196977e-05,
      "loss": 0.7057,
      "step": 2600
    },
    {
      "epoch": 0.23293172690763053,
      "grad_norm": 0.3495982587337494,
      "learning_rate": 1.6953977587577846e-05,
      "loss": 0.7049,
      "step": 2610
    },
    {
      "epoch": 0.23382418563141455,
      "grad_norm": 0.3494509160518646,
      "learning_rate": 1.601729000601297e-05,
      "loss": 0.7195,
      "step": 2620
    },
    {
      "epoch": 0.23471664435519857,
      "grad_norm": 0.34791481494903564,
      "learning_rate": 1.4989431630624763e-05,
      "loss": 0.6918,
      "step": 2630
    },
    {
      "epoch": 0.23560910307898258,
      "grad_norm": 0.3591028153896332,
      "learning_rate": 1.3886106518686746e-05,
      "loss": 0.7093,
      "step": 2640
    },
    {
      "epoch": 0.23650156180276663,
      "grad_norm": 0.3378075063228607,
      "learning_rate": 1.2724171740359612e-05,
      "loss": 0.7053,
      "step": 2650
    },
    {
      "epoch": 0.23739402052655065,
      "grad_norm": 0.3907321095466614,
      "learning_rate": 1.1521379829206218e-05,
      "loss": 0.6889,
      "step": 2660
    },
    {
      "epoch": 0.23828647925033467,
      "grad_norm": 0.3725852370262146,
      "learning_rate": 1.029610755143595e-05,
      "loss": 0.702,
      "step": 2670
    },
    {
      "epoch": 0.2391789379741187,
      "grad_norm": 0.3822772800922394,
      "learning_rate": 9.067075137857348e-06,
      "loss": 0.7077,
      "step": 2680
    },
    {
      "epoch": 0.24007139669790273,
      "grad_norm": 0.36839449405670166,
      "learning_rate": 7.853060268232525e-06,
      "loss": 0.699,
      "step": 2690
    },
    {
      "epoch": 0.24096385542168675,
      "grad_norm": 0.3252454102039337,
      "learning_rate": 6.672611177902054e-06,
      "loss": 0.6998,
      "step": 2700
    },
    {
      "epoch": 0.24185631414547076,
      "grad_norm": 0.3273606300354004,
      "learning_rate": 5.543763269959312e-06,
      "loss": 0.7108,
      "step": 2710
    },
    {
      "epoch": 0.2427487728692548,
      "grad_norm": 0.382530152797699,
      "learning_rate": 4.483763562693867e-06,
      "loss": 0.6987,
      "step": 2720
    },
    {
      "epoch": 0.24364123159303883,
      "grad_norm": 0.4303949177265167,
      "learning_rate": 3.508807182313187e-06,
      "loss": 0.654,
      "step": 2730
    },
    {
      "epoch": 0.24453369031682284,
      "grad_norm": 0.33196231722831726,
      "learning_rate": 2.6337899269187294e-06,
      "loss": 0.701,
      "step": 2740
    },
    {
      "epoch": 0.24542614904060686,
      "grad_norm": 0.3858130872249603,
      "learning_rate": 1.8720806821693126e-06,
      "loss": 0.6825,
      "step": 2750
    },
    {
      "epoch": 0.2463186077643909,
      "grad_norm": 0.3374707102775574,
      "learning_rate": 1.2353171657619887e-06,
      "loss": 0.6735,
      "step": 2760
    },
    {
      "epoch": 0.24721106648817492,
      "grad_norm": 0.33217793703079224,
      "learning_rate": 7.332281214330356e-07,
      "loss": 0.6985,
      "step": 2770
    },
    {
      "epoch": 0.24810352521195894,
      "grad_norm": 0.33184701204299927,
      "learning_rate": 3.73484679074808e-07,
      "loss": 0.6864,
      "step": 2780
    },
    {
      "epoch": 0.24899598393574296,
      "grad_norm": 0.3601723611354828,
      "learning_rate": 1.61583151951702e-07,
      "loss": 0.6839,
      "step": 2790
    },
    {
      "epoch": 0.2497099509147702,
      "step": 2798,
      "total_flos": 1.1366756130249245e+19,
      "train_loss": 0.06320346875903093,
      "train_runtime": 2328.1685,
      "train_samples_per_second": 14.422,
      "train_steps_per_second": 1.202
    }
  ],
  "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
}