{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001,
      "grad_norm": 1.7063226699829102,
      "learning_rate": 4.995e-05,
      "loss": 9.6305,
      "step": 10
    },
    {
      "epoch": 0.002,
      "grad_norm": 1.467505693435669,
      "learning_rate": 4.99e-05,
      "loss": 8.8474,
      "step": 20
    },
    {
      "epoch": 0.003,
      "grad_norm": 1.3338744640350342,
      "learning_rate": 4.9850000000000006e-05,
      "loss": 8.4272,
      "step": 30
    },
    {
      "epoch": 0.004,
      "grad_norm": 1.194218635559082,
      "learning_rate": 4.9800000000000004e-05,
      "loss": 7.9969,
      "step": 40
    },
    {
      "epoch": 0.005,
      "grad_norm": 0.9542586207389832,
      "learning_rate": 4.975e-05,
      "loss": 7.8018,
      "step": 50
    },
    {
      "epoch": 0.006,
      "grad_norm": 0.8312947154045105,
      "learning_rate": 4.97e-05,
      "loss": 7.5303,
      "step": 60
    },
    {
      "epoch": 0.007,
      "grad_norm": 0.6978892683982849,
      "learning_rate": 4.965e-05,
      "loss": 7.3733,
      "step": 70
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.6895764470100403,
      "learning_rate": 4.96e-05,
      "loss": 7.2434,
      "step": 80
    },
    {
      "epoch": 0.009,
      "grad_norm": 0.5555976033210754,
      "learning_rate": 4.9550000000000005e-05,
      "loss": 7.0877,
      "step": 90
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.836391806602478,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 7.0338,
      "step": 100
    },
    {
      "epoch": 0.011,
      "grad_norm": 0.782464861869812,
      "learning_rate": 4.945e-05,
      "loss": 6.878,
      "step": 110
    },
    {
      "epoch": 0.012,
      "grad_norm": 1.3705933094024658,
      "learning_rate": 4.94e-05,
      "loss": 6.5874,
      "step": 120
    },
    {
      "epoch": 0.013,
      "grad_norm": 0.7560775876045227,
      "learning_rate": 4.935e-05,
      "loss": 6.4978,
      "step": 130
    },
    {
      "epoch": 0.014,
      "grad_norm": 1.3238508701324463,
      "learning_rate": 4.93e-05,
      "loss": 6.3998,
      "step": 140
    },
    {
      "epoch": 0.015,
      "grad_norm": 0.7834548950195312,
      "learning_rate": 4.9250000000000004e-05,
      "loss": 6.2838,
      "step": 150
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.762347400188446,
      "learning_rate": 4.92e-05,
      "loss": 6.0387,
      "step": 160
    },
    {
      "epoch": 0.017,
      "grad_norm": 0.7799501419067383,
      "learning_rate": 4.915e-05,
      "loss": 6.0241,
      "step": 170
    },
    {
      "epoch": 0.018,
      "grad_norm": 0.7948866486549377,
      "learning_rate": 4.91e-05,
      "loss": 5.8776,
      "step": 180
    },
    {
      "epoch": 0.019,
      "grad_norm": 0.9890483021736145,
      "learning_rate": 4.905e-05,
      "loss": 5.747,
      "step": 190
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.9131263494491577,
      "learning_rate": 4.9e-05,
      "loss": 5.644,
      "step": 200
    },
    {
      "epoch": 0.021,
      "grad_norm": 1.7073436975479126,
      "learning_rate": 4.8950000000000004e-05,
      "loss": 5.778,
      "step": 210
    },
    {
      "epoch": 0.022,
      "grad_norm": 0.8059922456741333,
      "learning_rate": 4.89e-05,
      "loss": 5.4755,
      "step": 220
    },
    {
      "epoch": 0.023,
      "grad_norm": 1.2500686645507812,
      "learning_rate": 4.885e-05,
      "loss": 5.3769,
      "step": 230
    },
    {
      "epoch": 0.024,
      "grad_norm": 1.3848680257797241,
      "learning_rate": 4.88e-05,
      "loss": 5.2105,
      "step": 240
    },
    {
      "epoch": 0.025,
      "grad_norm": 1.2381746768951416,
      "learning_rate": 4.875e-05,
      "loss": 5.1444,
      "step": 250
    },
    {
      "epoch": 0.026,
      "grad_norm": 2.7005224227905273,
      "learning_rate": 4.87e-05,
      "loss": 5.1608,
      "step": 260
    },
    {
      "epoch": 0.027,
      "grad_norm": 1.1472671031951904,
      "learning_rate": 4.8650000000000003e-05,
      "loss": 4.9456,
      "step": 270
    },
    {
      "epoch": 0.028,
      "grad_norm": 1.9849270582199097,
      "learning_rate": 4.86e-05,
      "loss": 4.8466,
      "step": 280
    },
    {
      "epoch": 0.029,
      "grad_norm": 1.857001781463623,
      "learning_rate": 4.855e-05,
      "loss": 4.7323,
      "step": 290
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.6731220483779907,
      "learning_rate": 4.85e-05,
      "loss": 4.5786,
      "step": 300
    },
    {
      "epoch": 0.031,
      "grad_norm": 1.7968906164169312,
      "learning_rate": 4.845e-05,
      "loss": 4.4588,
      "step": 310
    },
    {
      "epoch": 0.032,
      "grad_norm": 1.7908226251602173,
      "learning_rate": 4.8400000000000004e-05,
      "loss": 4.3645,
      "step": 320
    },
    {
      "epoch": 0.033,
      "grad_norm": 2.538881540298462,
      "learning_rate": 4.835e-05,
      "loss": 4.1489,
      "step": 330
    },
    {
      "epoch": 0.034,
      "grad_norm": 2.306257486343384,
      "learning_rate": 4.83e-05,
      "loss": 3.9798,
      "step": 340
    },
    {
      "epoch": 0.035,
      "grad_norm": 2.1730940341949463,
      "learning_rate": 4.825e-05,
      "loss": 4.0231,
      "step": 350
    },
    {
      "epoch": 0.036,
      "grad_norm": 2.4211463928222656,
      "learning_rate": 4.82e-05,
      "loss": 3.8495,
      "step": 360
    },
    {
      "epoch": 0.037,
      "grad_norm": 2.3698794841766357,
      "learning_rate": 4.815e-05,
      "loss": 3.6977,
      "step": 370
    },
    {
      "epoch": 0.038,
      "grad_norm": 2.147799491882324,
      "learning_rate": 4.8100000000000004e-05,
      "loss": 3.8008,
      "step": 380
    },
    {
      "epoch": 0.039,
      "grad_norm": 2.3577606678009033,
      "learning_rate": 4.805e-05,
      "loss": 3.6983,
      "step": 390
    },
    {
      "epoch": 0.04,
      "grad_norm": 2.065912961959839,
      "learning_rate": 4.8e-05,
      "loss": 3.5738,
      "step": 400
    },
    {
      "epoch": 0.041,
      "grad_norm": 2.930288314819336,
      "learning_rate": 4.795e-05,
      "loss": 3.5117,
      "step": 410
    },
    {
      "epoch": 0.042,
      "grad_norm": 2.3703155517578125,
      "learning_rate": 4.79e-05,
      "loss": 3.2483,
      "step": 420
    },
    {
      "epoch": 0.043,
      "grad_norm": 2.6050736904144287,
      "learning_rate": 4.785e-05,
      "loss": 3.2342,
      "step": 430
    },
    {
      "epoch": 0.044,
      "grad_norm": 2.0790674686431885,
      "learning_rate": 4.78e-05,
      "loss": 3.1452,
      "step": 440
    },
    {
      "epoch": 0.045,
      "grad_norm": 2.2497427463531494,
      "learning_rate": 4.775e-05,
      "loss": 3.0316,
      "step": 450
    },
    {
      "epoch": 0.046,
      "grad_norm": 2.507902145385742,
      "learning_rate": 4.77e-05,
      "loss": 2.8938,
      "step": 460
    },
    {
      "epoch": 0.047,
      "grad_norm": 2.517744541168213,
      "learning_rate": 4.765e-05,
      "loss": 2.8137,
      "step": 470
    },
    {
      "epoch": 0.048,
      "grad_norm": 3.9981460571289062,
      "learning_rate": 4.76e-05,
      "loss": 2.9864,
      "step": 480
    },
    {
      "epoch": 0.049,
      "grad_norm": 2.265026569366455,
      "learning_rate": 4.755e-05,
      "loss": 2.7839,
      "step": 490
    },
    {
      "epoch": 0.05,
      "grad_norm": 2.257293701171875,
      "learning_rate": 4.75e-05,
      "loss": 2.6834,
      "step": 500
    },
    {
      "epoch": 0.051,
      "grad_norm": 2.6932270526885986,
      "learning_rate": 4.745e-05,
      "loss": 2.5755,
      "step": 510
    },
    {
      "epoch": 0.052,
      "grad_norm": 1.7177081108093262,
      "learning_rate": 4.74e-05,
      "loss": 2.425,
      "step": 520
    },
    {
      "epoch": 0.053,
      "grad_norm": 2.2452073097229004,
      "learning_rate": 4.735e-05,
      "loss": 2.5261,
      "step": 530
    },
    {
      "epoch": 0.054,
      "grad_norm": 2.2109947204589844,
      "learning_rate": 4.73e-05,
      "loss": 2.3825,
      "step": 540
    },
    {
      "epoch": 0.055,
      "grad_norm": 2.574531078338623,
      "learning_rate": 4.7249999999999997e-05,
      "loss": 2.3087,
      "step": 550
    },
    {
      "epoch": 0.056,
      "grad_norm": 2.3631017208099365,
      "learning_rate": 4.72e-05,
      "loss": 2.3099,
      "step": 560
    },
    {
      "epoch": 0.057,
      "grad_norm": 2.3809709548950195,
      "learning_rate": 4.715e-05,
      "loss": 2.3001,
      "step": 570
    },
    {
      "epoch": 0.058,
      "grad_norm": 2.0683534145355225,
      "learning_rate": 4.71e-05,
      "loss": 2.0813,
      "step": 580
    },
    {
      "epoch": 0.059,
      "grad_norm": 2.5471837520599365,
      "learning_rate": 4.705e-05,
      "loss": 2.0378,
      "step": 590
    },
    {
      "epoch": 0.06,
      "grad_norm": 2.585564374923706,
      "learning_rate": 4.7e-05,
      "loss": 2.2062,
      "step": 600
    },
    {
      "epoch": 0.061,
      "grad_norm": 2.062100648880005,
      "learning_rate": 4.695e-05,
      "loss": 1.9914,
      "step": 610
    },
    {
      "epoch": 0.062,
      "grad_norm": 2.1019210815429688,
      "learning_rate": 4.69e-05,
      "loss": 1.9635,
      "step": 620
    },
    {
      "epoch": 0.063,
      "grad_norm": 2.630436658859253,
      "learning_rate": 4.685000000000001e-05,
      "loss": 1.9123,
      "step": 630
    },
    {
      "epoch": 0.064,
      "grad_norm": 2.1028494834899902,
      "learning_rate": 4.6800000000000006e-05,
      "loss": 1.7583,
      "step": 640
    },
    {
      "epoch": 0.065,
      "grad_norm": 2.392193078994751,
      "learning_rate": 4.6750000000000005e-05,
      "loss": 1.7532,
      "step": 650
    },
    {
      "epoch": 0.066,
      "grad_norm": 2.004413366317749,
      "learning_rate": 4.6700000000000003e-05,
      "loss": 1.6978,
      "step": 660
    },
    {
      "epoch": 0.067,
      "grad_norm": 2.210513114929199,
      "learning_rate": 4.665e-05,
      "loss": 1.6311,
      "step": 670
    },
    {
      "epoch": 0.068,
      "grad_norm": 1.8464936017990112,
      "learning_rate": 4.660000000000001e-05,
      "loss": 1.5507,
      "step": 680
    },
    {
      "epoch": 0.069,
      "grad_norm": 2.0246541500091553,
      "learning_rate": 4.655000000000001e-05,
      "loss": 1.5637,
      "step": 690
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.199751138687134,
      "learning_rate": 4.6500000000000005e-05,
      "loss": 1.5603,
      "step": 700
    },
    {
      "epoch": 0.071,
      "grad_norm": 2.2002196311950684,
      "learning_rate": 4.6450000000000004e-05,
      "loss": 1.4558,
      "step": 710
    },
    {
      "epoch": 0.072,
      "grad_norm": 1.7826759815216064,
      "learning_rate": 4.64e-05,
      "loss": 1.4309,
      "step": 720
    },
    {
      "epoch": 0.073,
      "grad_norm": 1.760297417640686,
      "learning_rate": 4.635e-05,
      "loss": 1.3531,
      "step": 730
    },
    {
      "epoch": 0.074,
      "grad_norm": 2.0505475997924805,
      "learning_rate": 4.630000000000001e-05,
      "loss": 1.3641,
      "step": 740
    },
    {
      "epoch": 0.075,
      "grad_norm": 2.1375396251678467,
      "learning_rate": 4.6250000000000006e-05,
      "loss": 1.3259,
      "step": 750
    },
    {
      "epoch": 0.076,
      "grad_norm": 1.8252328634262085,
      "learning_rate": 4.6200000000000005e-05,
      "loss": 1.2026,
      "step": 760
    },
    {
      "epoch": 0.077,
      "grad_norm": 1.8945906162261963,
      "learning_rate": 4.6150000000000004e-05,
      "loss": 1.2878,
      "step": 770
    },
    {
      "epoch": 0.078,
      "grad_norm": 1.7990881204605103,
      "learning_rate": 4.61e-05,
      "loss": 1.1853,
      "step": 780
    },
    {
      "epoch": 0.079,
      "grad_norm": 1.4897470474243164,
      "learning_rate": 4.605e-05,
      "loss": 1.1279,
      "step": 790
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.2804617881774902,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.0804,
      "step": 800
    },
    {
      "epoch": 0.081,
      "grad_norm": 1.4800664186477661,
      "learning_rate": 4.5950000000000006e-05,
      "loss": 1.0361,
      "step": 810
    },
    {
      "epoch": 0.082,
      "grad_norm": 1.3526049852371216,
      "learning_rate": 4.5900000000000004e-05,
      "loss": 1.0585,
      "step": 820
    },
    {
      "epoch": 0.083,
      "grad_norm": 1.534173607826233,
      "learning_rate": 4.585e-05,
      "loss": 1.0206,
      "step": 830
    },
    {
      "epoch": 0.084,
      "grad_norm": 1.4844435453414917,
      "learning_rate": 4.58e-05,
      "loss": 0.9758,
      "step": 840
    },
    {
      "epoch": 0.085,
      "grad_norm": 1.533679485321045,
      "learning_rate": 4.575e-05,
      "loss": 0.9168,
      "step": 850
    },
    {
      "epoch": 0.086,
      "grad_norm": 1.456162691116333,
      "learning_rate": 4.5700000000000006e-05,
      "loss": 0.8913,
      "step": 860
    },
    {
      "epoch": 0.087,
      "grad_norm": 1.7335631847381592,
      "learning_rate": 4.5650000000000005e-05,
      "loss": 0.9154,
      "step": 870
    },
    {
      "epoch": 0.088,
      "grad_norm": 1.3331761360168457,
      "learning_rate": 4.5600000000000004e-05,
      "loss": 0.8483,
      "step": 880
    },
    {
      "epoch": 0.089,
      "grad_norm": 1.6703053712844849,
      "learning_rate": 4.555e-05,
      "loss": 0.8116,
      "step": 890
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.275975227355957,
      "learning_rate": 4.55e-05,
      "loss": 0.7869,
      "step": 900
    },
    {
      "epoch": 0.091,
      "grad_norm": 1.3800309896469116,
      "learning_rate": 4.545000000000001e-05,
      "loss": 0.7637,
      "step": 910
    },
    {
      "epoch": 0.092,
      "grad_norm": 1.9472386837005615,
      "learning_rate": 4.5400000000000006e-05,
      "loss": 0.7212,
      "step": 920
    },
    {
      "epoch": 0.093,
      "grad_norm": 1.3451333045959473,
      "learning_rate": 4.5350000000000005e-05,
      "loss": 0.6829,
      "step": 930
    },
    {
      "epoch": 0.094,
      "grad_norm": 1.5209784507751465,
      "learning_rate": 4.53e-05,
      "loss": 0.729,
      "step": 940
    },
    {
      "epoch": 0.095,
      "grad_norm": 1.3944469690322876,
      "learning_rate": 4.525e-05,
      "loss": 0.6732,
      "step": 950
    },
    {
      "epoch": 0.096,
      "grad_norm": 1.2177132368087769,
      "learning_rate": 4.52e-05,
      "loss": 0.6188,
      "step": 960
    },
    {
      "epoch": 0.097,
      "grad_norm": 1.5988528728485107,
      "learning_rate": 4.5150000000000006e-05,
      "loss": 0.6622,
      "step": 970
    },
    {
      "epoch": 0.098,
      "grad_norm": 1.3636531829833984,
      "learning_rate": 4.5100000000000005e-05,
      "loss": 0.5792,
      "step": 980
    },
    {
      "epoch": 0.099,
      "grad_norm": 1.377453088760376,
      "learning_rate": 4.5050000000000004e-05,
      "loss": 0.6062,
      "step": 990
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.295713186264038,
      "learning_rate": 4.5e-05,
      "loss": 0.5709,
      "step": 1000
    },
    {
      "epoch": 0.101,
      "grad_norm": 1.35196852684021,
      "learning_rate": 4.495e-05,
      "loss": 0.5521,
      "step": 1010
    },
    {
      "epoch": 0.102,
      "grad_norm": 1.0617187023162842,
      "learning_rate": 4.49e-05,
      "loss": 0.5147,
      "step": 1020
    },
    {
      "epoch": 0.103,
      "grad_norm": 1.3035167455673218,
      "learning_rate": 4.4850000000000006e-05,
      "loss": 0.5081,
      "step": 1030
    },
    {
      "epoch": 0.104,
      "grad_norm": 1.2835568189620972,
      "learning_rate": 4.4800000000000005e-05,
      "loss": 0.5,
      "step": 1040
    },
    {
      "epoch": 0.105,
      "grad_norm": 1.0403038263320923,
      "learning_rate": 4.4750000000000004e-05,
      "loss": 0.4825,
      "step": 1050
    },
    {
      "epoch": 0.106,
      "grad_norm": 0.9538235068321228,
      "learning_rate": 4.47e-05,
      "loss": 0.4316,
      "step": 1060
    },
    {
      "epoch": 0.107,
      "grad_norm": 1.4246289730072021,
      "learning_rate": 4.465e-05,
      "loss": 0.4304,
      "step": 1070
    },
    {
      "epoch": 0.108,
      "grad_norm": 1.1217833757400513,
      "learning_rate": 4.46e-05,
      "loss": 0.4397,
      "step": 1080
    },
    {
      "epoch": 0.109,
      "grad_norm": 1.0411335229873657,
      "learning_rate": 4.4550000000000005e-05,
      "loss": 0.4057,
      "step": 1090
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.8498069643974304,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 0.3933,
      "step": 1100
    },
    {
      "epoch": 0.111,
      "grad_norm": 1.1270406246185303,
      "learning_rate": 4.445e-05,
      "loss": 0.366,
      "step": 1110
    },
    {
      "epoch": 0.112,
      "grad_norm": 1.189041256904602,
      "learning_rate": 4.44e-05,
      "loss": 0.3407,
      "step": 1120
    },
    {
      "epoch": 0.113,
      "grad_norm": 0.9837467670440674,
      "learning_rate": 4.435e-05,
      "loss": 0.3511,
      "step": 1130
    },
    {
      "epoch": 0.114,
      "grad_norm": 1.0432955026626587,
      "learning_rate": 4.43e-05,
      "loss": 0.3381,
      "step": 1140
    },
    {
      "epoch": 0.115,
      "grad_norm": 0.9529951810836792,
      "learning_rate": 4.4250000000000005e-05,
      "loss": 0.3189,
      "step": 1150
    },
    {
      "epoch": 0.116,
      "grad_norm": 1.008836030960083,
      "learning_rate": 4.4200000000000004e-05,
      "loss": 0.3077,
      "step": 1160
    },
    {
      "epoch": 0.117,
      "grad_norm": 1.0005086660385132,
      "learning_rate": 4.415e-05,
      "loss": 0.3001,
      "step": 1170
    },
    {
      "epoch": 0.118,
      "grad_norm": 1.1065175533294678,
      "learning_rate": 4.41e-05,
      "loss": 0.28,
      "step": 1180
    },
    {
      "epoch": 0.119,
      "grad_norm": 0.6701949834823608,
      "learning_rate": 4.405e-05,
      "loss": 0.2692,
      "step": 1190
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.7154658436775208,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.2663,
      "step": 1200
    },
    {
      "epoch": 0.121,
      "grad_norm": 0.6997113823890686,
      "learning_rate": 4.3950000000000004e-05,
      "loss": 0.2595,
      "step": 1210
    },
    {
      "epoch": 0.122,
      "grad_norm": 0.9047608971595764,
      "learning_rate": 4.39e-05,
      "loss": 0.2558,
      "step": 1220
    },
    {
      "epoch": 0.123,
      "grad_norm": 0.8508415222167969,
      "learning_rate": 4.385e-05,
      "loss": 0.2459,
      "step": 1230
    },
    {
      "epoch": 0.124,
      "grad_norm": 0.6505220532417297,
      "learning_rate": 4.38e-05,
      "loss": 0.2236,
      "step": 1240
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.5360460877418518,
      "learning_rate": 4.375e-05,
      "loss": 0.2189,
      "step": 1250
    },
    {
      "epoch": 0.126,
      "grad_norm": 0.560817539691925,
      "learning_rate": 4.3700000000000005e-05,
      "loss": 0.2166,
      "step": 1260
    },
    {
      "epoch": 0.127,
      "grad_norm": 0.7089666128158569,
      "learning_rate": 4.3650000000000004e-05,
      "loss": 0.2026,
      "step": 1270
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.5265817046165466,
      "learning_rate": 4.36e-05,
      "loss": 0.197,
      "step": 1280
    },
    {
      "epoch": 0.129,
      "grad_norm": 0.6629377007484436,
      "learning_rate": 4.355e-05,
      "loss": 0.1934,
      "step": 1290
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.0730735063552856,
      "learning_rate": 4.35e-05,
      "loss": 0.1807,
      "step": 1300
    },
    {
      "epoch": 0.131,
      "grad_norm": 0.6990699172019958,
      "learning_rate": 4.345e-05,
      "loss": 0.1845,
      "step": 1310
    },
    {
      "epoch": 0.132,
      "grad_norm": 0.5047340393066406,
      "learning_rate": 4.3400000000000005e-05,
      "loss": 0.1725,
      "step": 1320
    },
    {
      "epoch": 0.133,
      "grad_norm": 0.6830994486808777,
      "learning_rate": 4.335e-05,
      "loss": 0.1687,
      "step": 1330
    },
    {
      "epoch": 0.134,
      "grad_norm": 0.5861710906028748,
      "learning_rate": 4.33e-05,
      "loss": 0.1671,
      "step": 1340
    },
    {
      "epoch": 0.135,
      "grad_norm": 0.43594300746917725,
      "learning_rate": 4.325e-05,
      "loss": 0.1467,
      "step": 1350
    },
    {
      "epoch": 0.136,
      "grad_norm": 0.44587692618370056,
      "learning_rate": 4.32e-05,
      "loss": 0.1509,
      "step": 1360
    },
    {
      "epoch": 0.137,
      "grad_norm": 0.5523977875709534,
      "learning_rate": 4.315e-05,
      "loss": 0.1434,
      "step": 1370
    },
    {
      "epoch": 0.138,
      "grad_norm": 0.6139170527458191,
      "learning_rate": 4.3100000000000004e-05,
      "loss": 0.1433,
      "step": 1380
    },
    {
      "epoch": 0.139,
      "grad_norm": 0.6169497966766357,
      "learning_rate": 4.305e-05,
      "loss": 0.1365,
      "step": 1390
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.49120134115219116,
      "learning_rate": 4.3e-05,
      "loss": 0.1287,
      "step": 1400
    },
    {
      "epoch": 0.141,
      "grad_norm": 0.451753169298172,
      "learning_rate": 4.295e-05,
      "loss": 0.1142,
      "step": 1410
    },
    {
      "epoch": 0.142,
      "grad_norm": 0.5429627895355225,
      "learning_rate": 4.29e-05,
      "loss": 0.134,
      "step": 1420
    },
    {
      "epoch": 0.143,
      "grad_norm": 0.7613041400909424,
      "learning_rate": 4.285e-05,
      "loss": 0.1391,
      "step": 1430
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.4953358471393585,
      "learning_rate": 4.2800000000000004e-05,
      "loss": 0.1197,
      "step": 1440
    },
    {
      "epoch": 0.145,
      "grad_norm": 0.3657626509666443,
      "learning_rate": 4.275e-05,
      "loss": 0.1071,
      "step": 1450
    },
    {
      "epoch": 0.146,
      "grad_norm": 0.44240206480026245,
      "learning_rate": 4.27e-05,
      "loss": 0.1111,
      "step": 1460
    },
    {
      "epoch": 0.147,
      "grad_norm": 0.5007165670394897,
      "learning_rate": 4.265e-05,
      "loss": 0.1056,
      "step": 1470
    },
    {
      "epoch": 0.148,
      "grad_norm": 0.4580256938934326,
      "learning_rate": 4.26e-05,
      "loss": 0.1049,
      "step": 1480
    },
    {
      "epoch": 0.149,
      "grad_norm": 0.4970822036266327,
      "learning_rate": 4.2550000000000004e-05,
      "loss": 0.1032,
      "step": 1490
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.4138182997703552,
      "learning_rate": 4.25e-05,
      "loss": 0.0961,
      "step": 1500
    },
    {
      "epoch": 0.151,
      "grad_norm": 0.4013712406158447,
      "learning_rate": 4.245e-05,
      "loss": 0.0949,
      "step": 1510
    },
    {
      "epoch": 0.152,
      "grad_norm": 0.3868940770626068,
      "learning_rate": 4.24e-05,
      "loss": 0.0837,
      "step": 1520
    },
    {
      "epoch": 0.153,
      "grad_norm": 0.3113015294075012,
      "learning_rate": 4.235e-05,
      "loss": 0.0909,
      "step": 1530
    },
    {
      "epoch": 0.154,
      "grad_norm": 0.3569623529911041,
      "learning_rate": 4.23e-05,
      "loss": 0.0908,
      "step": 1540
    },
    {
      "epoch": 0.155,
      "grad_norm": 0.3841746151447296,
      "learning_rate": 4.2250000000000004e-05,
      "loss": 0.0806,
      "step": 1550
    },
    {
      "epoch": 0.156,
      "grad_norm": 0.6565550565719604,
      "learning_rate": 4.22e-05,
      "loss": 0.075,
      "step": 1560
    },
    {
      "epoch": 0.157,
      "grad_norm": 0.4816874563694,
      "learning_rate": 4.215e-05,
      "loss": 0.0858,
      "step": 1570
    },
    {
      "epoch": 0.158,
      "grad_norm": 0.30408933758735657,
      "learning_rate": 4.21e-05,
      "loss": 0.0704,
      "step": 1580
    },
    {
      "epoch": 0.159,
      "grad_norm": 0.43388792872428894,
      "learning_rate": 4.205e-05,
      "loss": 0.0671,
      "step": 1590
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.33304253220558167,
      "learning_rate": 4.2e-05,
      "loss": 0.07,
      "step": 1600
    },
    {
      "epoch": 0.161,
      "grad_norm": 0.4260387420654297,
      "learning_rate": 4.195e-05,
      "loss": 0.0691,
      "step": 1610
    },
    {
      "epoch": 0.162,
      "grad_norm": 0.37930798530578613,
      "learning_rate": 4.19e-05,
      "loss": 0.0715,
      "step": 1620
    },
    {
      "epoch": 0.163,
      "grad_norm": 0.3198983669281006,
      "learning_rate": 4.185e-05,
      "loss": 0.0651,
      "step": 1630
    },
    {
      "epoch": 0.164,
      "grad_norm": 0.3510359823703766,
      "learning_rate": 4.18e-05,
      "loss": 0.058,
      "step": 1640
    },
    {
      "epoch": 0.165,
      "grad_norm": 0.41047966480255127,
      "learning_rate": 4.175e-05,
      "loss": 0.065,
      "step": 1650
    },
    {
      "epoch": 0.166,
      "grad_norm": 0.3054174482822418,
      "learning_rate": 4.17e-05,
      "loss": 0.0564,
      "step": 1660
    },
    {
      "epoch": 0.167,
      "grad_norm": 0.29319772124290466,
      "learning_rate": 4.165e-05,
      "loss": 0.0599,
      "step": 1670
    },
    {
      "epoch": 0.168,
      "grad_norm": 0.257354736328125,
      "learning_rate": 4.16e-05,
      "loss": 0.0536,
      "step": 1680
    },
    {
      "epoch": 0.169,
      "grad_norm": 0.25215694308280945,
      "learning_rate": 4.155e-05,
      "loss": 0.0587,
      "step": 1690
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.4573931097984314,
      "learning_rate": 4.15e-05,
      "loss": 0.0524,
      "step": 1700
    },
    {
      "epoch": 0.171,
      "grad_norm": 0.3514876663684845,
      "learning_rate": 4.145e-05,
      "loss": 0.0551,
      "step": 1710
    },
    {
      "epoch": 0.172,
      "grad_norm": 0.3239930272102356,
      "learning_rate": 4.14e-05,
      "loss": 0.0499,
      "step": 1720
    },
    {
      "epoch": 0.173,
      "grad_norm": 0.20213039219379425,
      "learning_rate": 4.135e-05,
      "loss": 0.0521,
      "step": 1730
    },
    {
      "epoch": 0.174,
      "grad_norm": 0.21831783652305603,
      "learning_rate": 4.13e-05,
      "loss": 0.0469,
      "step": 1740
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.2585163712501526,
      "learning_rate": 4.125e-05,
      "loss": 0.0469,
      "step": 1750
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.21717113256454468,
      "learning_rate": 4.12e-05,
      "loss": 0.0455,
      "step": 1760
    },
    {
      "epoch": 0.177,
      "grad_norm": 0.27248838543891907,
      "learning_rate": 4.115e-05,
      "loss": 0.046,
      "step": 1770
    },
    {
      "epoch": 0.178,
      "grad_norm": 0.2503461241722107,
      "learning_rate": 4.11e-05,
      "loss": 0.0447,
      "step": 1780
    },
    {
      "epoch": 0.179,
      "grad_norm": 0.27404382824897766,
      "learning_rate": 4.105e-05,
      "loss": 0.0437,
      "step": 1790
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.23549066483974457,
      "learning_rate": 4.1e-05,
      "loss": 0.0423,
      "step": 1800
    },
    {
      "epoch": 0.181,
      "grad_norm": 0.19369937479496002,
      "learning_rate": 4.095e-05,
      "loss": 0.0408,
      "step": 1810
    },
    {
      "epoch": 0.182,
      "grad_norm": 0.20560242235660553,
      "learning_rate": 4.09e-05,
      "loss": 0.0379,
      "step": 1820
    },
    {
      "epoch": 0.183,
      "grad_norm": 0.34989863634109497,
      "learning_rate": 4.085e-05,
      "loss": 0.0364,
      "step": 1830
    },
    {
      "epoch": 0.184,
      "grad_norm": 0.2310326248407364,
      "learning_rate": 4.08e-05,
      "loss": 0.0385,
      "step": 1840
    },
    {
      "epoch": 0.185,
      "grad_norm": 0.21055462956428528,
      "learning_rate": 4.075e-05,
      "loss": 0.0351,
      "step": 1850
    },
    {
      "epoch": 0.186,
      "grad_norm": 0.3251895308494568,
      "learning_rate": 4.07e-05,
      "loss": 0.0381,
      "step": 1860
    },
    {
      "epoch": 0.187,
      "grad_norm": 0.2887445390224457,
      "learning_rate": 4.065e-05,
      "loss": 0.0341,
      "step": 1870
    },
    {
      "epoch": 0.188,
      "grad_norm": 0.15948843955993652,
      "learning_rate": 4.0600000000000004e-05,
      "loss": 0.0313,
      "step": 1880
    },
    {
      "epoch": 0.189,
      "grad_norm": 0.2413359135389328,
      "learning_rate": 4.055e-05,
      "loss": 0.0338,
      "step": 1890
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.2132706493139267,
      "learning_rate": 4.05e-05,
      "loss": 0.0339,
      "step": 1900
    },
    {
      "epoch": 0.191,
      "grad_norm": 0.17968431115150452,
      "learning_rate": 4.045000000000001e-05,
      "loss": 0.0317,
      "step": 1910
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.15828929841518402,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 0.0302,
      "step": 1920
    },
    {
      "epoch": 0.193,
      "grad_norm": 0.18106874823570251,
      "learning_rate": 4.0350000000000005e-05,
      "loss": 0.0331,
      "step": 1930
    },
    {
      "epoch": 0.194,
      "grad_norm": 0.34827324748039246,
      "learning_rate": 4.0300000000000004e-05,
      "loss": 0.032,
      "step": 1940
    },
    {
      "epoch": 0.195,
      "grad_norm": 0.21621111035346985,
      "learning_rate": 4.025e-05,
      "loss": 0.0317,
      "step": 1950
    },
    {
      "epoch": 0.196,
      "grad_norm": 0.2159423679113388,
      "learning_rate": 4.02e-05,
      "loss": 0.0296,
      "step": 1960
    },
    {
      "epoch": 0.197,
      "grad_norm": 0.17750391364097595,
      "learning_rate": 4.015000000000001e-05,
      "loss": 0.0297,
      "step": 1970
    },
    {
      "epoch": 0.198,
      "grad_norm": 0.13952311873435974,
      "learning_rate": 4.0100000000000006e-05,
      "loss": 0.0279,
      "step": 1980
    },
    {
      "epoch": 0.199,
      "grad_norm": 0.19622887670993805,
      "learning_rate": 4.0050000000000004e-05,
      "loss": 0.0278,
      "step": 1990
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.14959514141082764,
      "learning_rate": 4e-05,
      "loss": 0.0251,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.3924406673408e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}