{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9997999866657777,
  "eval_steps": 500,
  "global_step": 3749,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 1.3359375,
      "learning_rate": 5.333333333333335e-07,
      "loss": 2.017,
      "step": 10
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.734375,
      "learning_rate": 1.066666666666667e-06,
      "loss": 2.3713,
      "step": 20
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.234375,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 2.1764,
      "step": 30
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.90234375,
      "learning_rate": 2.133333333333334e-06,
      "loss": 2.1757,
      "step": 40
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.4453125,
      "learning_rate": 2.666666666666667e-06,
      "loss": 2.1736,
      "step": 50
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.125,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 2.1865,
      "step": 60
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.1328125,
      "learning_rate": 3.7333333333333337e-06,
      "loss": 2.0263,
      "step": 70
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.015625,
      "learning_rate": 4.266666666666668e-06,
      "loss": 1.9312,
      "step": 80
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.171875,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.8754,
      "step": 90
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.70703125,
      "learning_rate": 5.333333333333334e-06,
      "loss": 1.7123,
      "step": 100
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.90625,
      "learning_rate": 5.8666666666666675e-06,
      "loss": 1.8266,
      "step": 110
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.97265625,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.6079,
      "step": 120
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.7578125,
      "learning_rate": 6.9333333333333344e-06,
      "loss": 1.5006,
      "step": 130
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.3359375,
      "learning_rate": 7.4666666666666675e-06,
      "loss": 1.4158,
      "step": 140
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.068359375,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.3677,
      "step": 150
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.384765625,
      "learning_rate": 8.533333333333335e-06,
      "loss": 1.374,
      "step": 160
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.296875,
      "learning_rate": 9.066666666666667e-06,
      "loss": 1.3052,
      "step": 170
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.0927734375,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.275,
      "step": 180
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.10498046875,
      "learning_rate": 1.0133333333333335e-05,
      "loss": 1.2574,
      "step": 190
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.09765625,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 1.2239,
      "step": 200
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.2109375,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 1.1565,
      "step": 210
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.392578125,
      "learning_rate": 1.1733333333333335e-05,
      "loss": 1.1758,
      "step": 220
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.138671875,
      "learning_rate": 1.2266666666666667e-05,
      "loss": 1.1843,
      "step": 230
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.22265625,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 1.1936,
      "step": 240
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.07861328125,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.1426,
      "step": 250
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.051513671875,
      "learning_rate": 1.3866666666666669e-05,
      "loss": 1.114,
      "step": 260
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.08154296875,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 1.1195,
      "step": 270
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.043701171875,
      "learning_rate": 1.4933333333333335e-05,
      "loss": 1.1256,
      "step": 280
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.041015625,
      "learning_rate": 1.546666666666667e-05,
      "loss": 1.102,
      "step": 290
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.1103515625,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.0762,
      "step": 300
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.0419921875,
      "learning_rate": 1.6533333333333333e-05,
      "loss": 1.0761,
      "step": 310
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.09765625,
      "learning_rate": 1.706666666666667e-05,
      "loss": 1.0501,
      "step": 320
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.041015625,
      "learning_rate": 1.76e-05,
      "loss": 1.0105,
      "step": 330
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.10302734375,
      "learning_rate": 1.8133333333333335e-05,
      "loss": 1.0232,
      "step": 340
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.035888671875,
      "learning_rate": 1.866666666666667e-05,
      "loss": 0.989,
      "step": 350
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.034423828125,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.9894,
      "step": 360
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.0830078125,
      "learning_rate": 1.9733333333333336e-05,
      "loss": 0.9824,
      "step": 370
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.0439453125,
      "learning_rate": 1.999989162756852e-05,
      "loss": 0.9569,
      "step": 380
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.034912109375,
      "learning_rate": 1.999902466221011e-05,
      "loss": 0.928,
      "step": 390
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.061767578125,
      "learning_rate": 1.9997290806656996e-05,
      "loss": 0.9349,
      "step": 400
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.03369140625,
      "learning_rate": 1.9994690211230084e-05,
      "loss": 0.9489,
      "step": 410
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.0289306640625,
      "learning_rate": 1.999122310139442e-05,
      "loss": 0.916,
      "step": 420
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.034912109375,
      "learning_rate": 1.9986889777739686e-05,
      "loss": 0.9541,
      "step": 430
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.02978515625,
      "learning_rate": 1.9981690615954097e-05,
      "loss": 0.9155,
      "step": 440
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.0263671875,
      "learning_rate": 1.9975626066791855e-05,
      "loss": 0.9015,
      "step": 450
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.0269775390625,
      "learning_rate": 1.996869665603406e-05,
      "loss": 0.9115,
      "step": 460
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.047119140625,
      "learning_rate": 1.996090298444313e-05,
      "loss": 0.896,
      "step": 470
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.0291748046875,
      "learning_rate": 1.9952245727710723e-05,
      "loss": 0.8855,
      "step": 480
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.193359375,
      "learning_rate": 1.9942725636399136e-05,
      "loss": 0.9084,
      "step": 490
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.02783203125,
      "learning_rate": 1.9932343535876255e-05,
      "loss": 0.8899,
      "step": 500
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.392578125,
      "learning_rate": 1.9921100326243977e-05,
      "loss": 0.8952,
      "step": 510
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.038330078125,
      "learning_rate": 1.9908996982260196e-05,
      "loss": 0.8857,
      "step": 520
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.09521484375,
      "learning_rate": 1.9896034553254284e-05,
      "loss": 0.8677,
      "step": 530
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.03076171875,
      "learning_rate": 1.988221416303611e-05,
      "loss": 0.8637,
      "step": 540
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.041748046875,
      "learning_rate": 1.986753700979861e-05,
      "loss": 0.8384,
      "step": 550
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.026611328125,
      "learning_rate": 1.985200436601392e-05,
      "loss": 0.9015,
      "step": 560
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.05419921875,
      "learning_rate": 1.9835617578323038e-05,
      "loss": 0.8564,
      "step": 570
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.0281982421875,
      "learning_rate": 1.9818378067419092e-05,
      "loss": 0.8183,
      "step": 580
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.0252685546875,
      "learning_rate": 1.9800287327924152e-05,
      "loss": 0.8358,
      "step": 590
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.059814453125,
      "learning_rate": 1.9781346928259662e-05,
      "loss": 0.8564,
      "step": 600
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.0235595703125,
      "learning_rate": 1.9761558510510453e-05,
      "loss": 0.8295,
      "step": 610
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.0255126953125,
      "learning_rate": 1.974092379028239e-05,
      "loss": 0.8403,
      "step": 620
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.064453125,
      "learning_rate": 1.9719444556553616e-05,
      "loss": 0.8582,
      "step": 630
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.0267333984375,
      "learning_rate": 1.969712267151948e-05,
      "loss": 0.8328,
      "step": 640
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.03564453125,
      "learning_rate": 1.9673960070431043e-05,
      "loss": 0.8571,
      "step": 650
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.031494140625,
      "learning_rate": 1.9649958761427364e-05,
      "loss": 0.824,
      "step": 660
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.026123046875,
      "learning_rate": 1.9625120825361326e-05,
      "loss": 0.8418,
      "step": 670
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.0247802734375,
      "learning_rate": 1.9599448415619283e-05,
      "loss": 0.8267,
      "step": 680
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.026123046875,
      "learning_rate": 1.957294375793435e-05,
      "loss": 0.8677,
      "step": 690
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.031005859375,
      "learning_rate": 1.954560915019343e-05,
      "loss": 0.827,
      "step": 700
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.031494140625,
      "learning_rate": 1.951744696223801e-05,
      "loss": 0.8303,
      "step": 710
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.024169921875,
      "learning_rate": 1.9488459635658687e-05,
      "loss": 0.8455,
      "step": 720
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.041259765625,
      "learning_rate": 1.945864968358349e-05,
      "loss": 0.8297,
      "step": 730
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.026611328125,
      "learning_rate": 1.9428019690460008e-05,
      "loss": 0.8516,
      "step": 740
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.0269775390625,
      "learning_rate": 1.939657231183132e-05,
      "loss": 0.8538,
      "step": 750
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.037109375,
      "learning_rate": 1.9364310274105758e-05,
      "loss": 0.8045,
      "step": 760
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.034423828125,
      "learning_rate": 1.933123637432054e-05,
      "loss": 0.8436,
      "step": 770
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.023681640625,
      "learning_rate": 1.929735347989929e-05,
      "loss": 0.8123,
      "step": 780
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.0238037109375,
      "learning_rate": 1.92626645284034e-05,
      "loss": 0.8184,
      "step": 790
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.047119140625,
      "learning_rate": 1.92271725272774e-05,
      "loss": 0.8222,
      "step": 800
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.0277099609375,
      "learning_rate": 1.919088055358818e-05,
      "loss": 0.8434,
      "step": 810
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.224609375,
      "learning_rate": 1.9153791753758236e-05,
      "loss": 0.8413,
      "step": 820
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.05517578125,
      "learning_rate": 1.911590934329288e-05,
      "loss": 0.8323,
      "step": 830
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.1201171875,
      "learning_rate": 1.9077236606501465e-05,
      "loss": 0.7935,
      "step": 840
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.022705078125,
      "learning_rate": 1.903777689621263e-05,
      "loss": 0.8186,
      "step": 850
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.0242919921875,
      "learning_rate": 1.899753363348364e-05,
      "loss": 0.8094,
      "step": 860
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.0267333984375,
      "learning_rate": 1.895651030730378e-05,
      "loss": 0.8265,
      "step": 870
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.031494140625,
      "learning_rate": 1.891471047429186e-05,
      "loss": 0.9105,
      "step": 880
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.030517578125,
      "learning_rate": 1.8872137758387873e-05,
      "loss": 0.8028,
      "step": 890
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.0263671875,
      "learning_rate": 1.8828795850538804e-05,
      "loss": 0.8322,
      "step": 900
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.0240478515625,
      "learning_rate": 1.8784688508378655e-05,
      "loss": 0.798,
      "step": 910
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.0277099609375,
      "learning_rate": 1.8739819555902626e-05,
      "loss": 0.8202,
      "step": 920
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.025146484375,
      "learning_rate": 1.8694192883135632e-05,
      "loss": 0.8819,
      "step": 930
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.027587890625,
      "learning_rate": 1.8647812445795003e-05,
      "loss": 0.8273,
      "step": 940
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.0291748046875,
      "learning_rate": 1.8600682264947566e-05,
      "loss": 0.8294,
      "step": 950
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.033447265625,
      "learning_rate": 1.8552806426661022e-05,
      "loss": 0.8222,
      "step": 960
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.185546875,
      "learning_rate": 1.8504189081649678e-05,
      "loss": 0.8109,
      "step": 970
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.0284423828125,
      "learning_rate": 1.8454834444914607e-05,
      "loss": 0.7972,
      "step": 980
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.0225830078125,
      "learning_rate": 1.8404746795378218e-05,
      "loss": 0.8107,
      "step": 990
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.087890625,
      "learning_rate": 1.8353930475513268e-05,
      "loss": 0.8208,
      "step": 1000
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0272216796875,
      "learning_rate": 1.8302389890966404e-05,
      "loss": 0.7933,
      "step": 1010
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.049072265625,
      "learning_rate": 1.8250129510176183e-05,
      "loss": 0.814,
      "step": 1020
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0225830078125,
      "learning_rate": 1.8197153863985686e-05,
      "loss": 0.8251,
      "step": 1030
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.024658203125,
      "learning_rate": 1.8143467545249694e-05,
      "loss": 0.7962,
      "step": 1040
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.0263671875,
      "learning_rate": 1.8089075208436507e-05,
      "loss": 0.8164,
      "step": 1050
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.0223388671875,
      "learning_rate": 1.8033981569224404e-05,
      "loss": 0.8081,
      "step": 1060
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.026123046875,
      "learning_rate": 1.797819140409282e-05,
      "loss": 0.8211,
      "step": 1070
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.0252685546875,
      "learning_rate": 1.7921709549908222e-05,
      "loss": 0.8526,
      "step": 1080
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.030517578125,
      "learning_rate": 1.7864540903504777e-05,
      "loss": 0.8195,
      "step": 1090
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.0230712890625,
      "learning_rate": 1.7806690421259794e-05,
      "loss": 0.7951,
      "step": 1100
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.04443359375,
      "learning_rate": 1.774816311866404e-05,
      "loss": 0.8389,
      "step": 1110
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.023681640625,
      "learning_rate": 1.768896406988689e-05,
      "loss": 0.8031,
      "step": 1120
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.0281982421875,
      "learning_rate": 1.7629098407336415e-05,
      "loss": 0.8188,
      "step": 1130
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.0242919921875,
      "learning_rate": 1.756857132121443e-05,
      "loss": 0.8232,
      "step": 1140
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.043701171875,
      "learning_rate": 1.7507388059066492e-05,
      "loss": 0.8126,
      "step": 1150
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.06982421875,
      "learning_rate": 1.7445553925326963e-05,
      "loss": 0.7775,
      "step": 1160
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.049560546875,
      "learning_rate": 1.7383074280859132e-05,
      "loss": 0.8205,
      "step": 1170
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.0240478515625,
      "learning_rate": 1.7319954542490448e-05,
      "loss": 0.8158,
      "step": 1180
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.041259765625,
      "learning_rate": 1.725620018254286e-05,
      "loss": 0.8146,
      "step": 1190
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.271484375,
      "learning_rate": 1.7191816728358435e-05,
      "loss": 0.8259,
      "step": 1200
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.021240234375,
      "learning_rate": 1.71268097618201e-05,
      "loss": 0.8213,
      "step": 1210
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.02490234375,
      "learning_rate": 1.706118491886774e-05,
      "loss": 0.7947,
      "step": 1220
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.0296630859375,
      "learning_rate": 1.6994947889009563e-05,
      "loss": 0.8364,
      "step": 1230
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.0247802734375,
      "learning_rate": 1.692810441482884e-05,
      "loss": 0.8268,
      "step": 1240
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.0238037109375,
      "learning_rate": 1.6860660291486023e-05,
      "loss": 0.7868,
      "step": 1250
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.02392578125,
      "learning_rate": 1.6792621366216338e-05,
      "loss": 0.8402,
      "step": 1260
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.036865234375,
      "learning_rate": 1.6723993537822837e-05,
      "loss": 0.81,
      "step": 1270
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.06298828125,
      "learning_rate": 1.6654782756164983e-05,
      "loss": 0.8151,
      "step": 1280
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.0235595703125,
      "learning_rate": 1.6584995021642814e-05,
      "loss": 0.7716,
      "step": 1290
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.0252685546875,
      "learning_rate": 1.651463638467673e-05,
      "loss": 0.8236,
      "step": 1300
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.031005859375,
      "learning_rate": 1.6443712945182933e-05,
      "loss": 0.7794,
      "step": 1310
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.03955078125,
      "learning_rate": 1.637223085204457e-05,
      "loss": 0.8222,
      "step": 1320
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.049560546875,
      "learning_rate": 1.630019630257865e-05,
      "loss": 0.8134,
      "step": 1330
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.0244140625,
      "learning_rate": 1.6227615541998756e-05,
      "loss": 0.8209,
      "step": 1340
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.0301513671875,
      "learning_rate": 1.6154494862873588e-05,
      "loss": 0.79,
      "step": 1350
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.0240478515625,
      "learning_rate": 1.6080840604581435e-05,
      "loss": 0.812,
      "step": 1360
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.0260009765625,
      "learning_rate": 1.600665915276054e-05,
      "loss": 0.8119,
      "step": 1370
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.0732421875,
      "learning_rate": 1.5931956938755494e-05,
      "loss": 0.8073,
      "step": 1380
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.0220947265625,
      "learning_rate": 1.585674043905966e-05,
      "loss": 0.8205,
      "step": 1390
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.0255126953125,
      "learning_rate": 1.5781016174753675e-05,
      "loss": 0.8222,
      "step": 1400
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.0302734375,
      "learning_rate": 1.5704790710940074e-05,
      "loss": 0.8307,
      "step": 1410
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.028076171875,
      "learning_rate": 1.5628070656174135e-05,
      "loss": 0.8038,
      "step": 1420
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.0233154296875,
      "learning_rate": 1.5550862661890918e-05,
      "loss": 0.7824,
      "step": 1430
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.0252685546875,
      "learning_rate": 1.547317342182861e-05,
      "loss": 0.7891,
      "step": 1440
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.058837890625,
      "learning_rate": 1.5395009671448186e-05,
      "loss": 0.8051,
      "step": 1450
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.0284423828125,
      "learning_rate": 1.5316378187349476e-05,
      "loss": 0.7899,
      "step": 1460
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.02734375,
      "learning_rate": 1.5237285786683638e-05,
      "loss": 0.827,
      "step": 1470
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.034912109375,
      "learning_rate": 1.515773932656213e-05,
      "loss": 0.8107,
      "step": 1480
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.0213623046875,
      "learning_rate": 1.5077745703462228e-05,
      "loss": 0.7785,
      "step": 1490
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.0274658203125,
      "learning_rate": 1.4997311852629097e-05,
      "loss": 0.8053,
      "step": 1500
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.029296875,
      "learning_rate": 1.4916444747474542e-05,
      "loss": 0.8034,
      "step": 1510
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.023681640625,
      "learning_rate": 1.4835151398972424e-05,
      "loss": 0.8117,
      "step": 1520
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.0303955078125,
      "learning_rate": 1.475343885505083e-05,
      "loss": 0.7811,
      "step": 1530
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.166015625,
      "learning_rate": 1.4671314199981019e-05,
      "loss": 0.8069,
      "step": 1540
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.024658203125,
      "learning_rate": 1.4588784553763262e-05,
      "loss": 0.8312,
      "step": 1550
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.035888671875,
      "learning_rate": 1.4505857071509523e-05,
      "loss": 0.8132,
      "step": 1560
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.04736328125,
      "learning_rate": 1.4422538942823158e-05,
      "loss": 0.812,
      "step": 1570
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.024658203125,
      "learning_rate": 1.4338837391175582e-05,
      "loss": 0.822,
      "step": 1580
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.025146484375,
      "learning_rate": 1.425475967328001e-05,
      "loss": 0.8269,
      "step": 1590
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.046630859375,
      "learning_rate": 1.4170313078462318e-05,
      "loss": 0.8027,
      "step": 1600
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.115234375,
      "learning_rate": 1.4085504928029086e-05,
      "loss": 0.8123,
      "step": 1610
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.0269775390625,
      "learning_rate": 1.4000342574632846e-05,
      "loss": 0.8028,
      "step": 1620
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.0284423828125,
      "learning_rate": 1.3914833401634642e-05,
      "loss": 0.7812,
      "step": 1630
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.036865234375,
      "learning_rate": 1.3828984822463895e-05,
      "loss": 0.8294,
      "step": 1640
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.03369140625,
      "learning_rate": 1.3742804279975686e-05,
      "loss": 0.8118,
      "step": 1650
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.0235595703125,
      "learning_rate": 1.3656299245805476e-05,
      "loss": 0.8086,
      "step": 1660
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.03955078125,
      "learning_rate": 1.3569477219721336e-05,
      "loss": 0.8155,
      "step": 1670
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.0262451171875,
      "learning_rate": 1.3482345728973742e-05,
      "loss": 0.8394,
      "step": 1680
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.0252685546875,
      "learning_rate": 1.3394912327642966e-05,
      "loss": 0.8172,
      "step": 1690
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.0291748046875,
      "learning_rate": 1.330718459598417e-05,
      "loss": 0.7993,
      "step": 1700
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.0311279296875,
      "learning_rate": 1.3219170139770213e-05,
      "loss": 0.7824,
      "step": 1710
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.0380859375,
      "learning_rate": 1.3130876589632243e-05,
      "loss": 0.7982,
      "step": 1720
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.037109375,
      "learning_rate": 1.3042311600398157e-05,
      "loss": 0.8093,
      "step": 1730
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.03271484375,
      "learning_rate": 1.2953482850428927e-05,
      "loss": 0.7864,
      "step": 1740
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.0225830078125,
      "learning_rate": 1.2864398040952921e-05,
      "loss": 0.778,
      "step": 1750
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.025634765625,
      "learning_rate": 1.2775064895398217e-05,
      "loss": 0.7869,
      "step": 1760
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.0274658203125,
      "learning_rate": 1.2685491158723003e-05,
      "loss": 0.8012,
      "step": 1770
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.0289306640625,
      "learning_rate": 1.2595684596744112e-05,
      "loss": 0.8385,
      "step": 1780
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.045166015625,
      "learning_rate": 1.250565299546374e-05,
      "loss": 0.8062,
      "step": 1790
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.025146484375,
      "learning_rate": 1.2415404160394429e-05,
      "loss": 0.8076,
      "step": 1800
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.0240478515625,
      "learning_rate": 1.2324945915882334e-05,
      "loss": 0.7864,
      "step": 1810
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.03125,
      "learning_rate": 1.2234286104428884e-05,
      "loss": 0.833,
      "step": 1820
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.07275390625,
      "learning_rate": 1.2143432586010851e-05,
      "loss": 0.7848,
      "step": 1830
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.037109375,
      "learning_rate": 1.2052393237398916e-05,
      "loss": 0.7838,
      "step": 1840
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.0771484375,
      "learning_rate": 1.1961175951474766e-05,
      "loss": 0.808,
      "step": 1850
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.0238037109375,
      "learning_rate": 1.1869788636546801e-05,
      "loss": 0.8076,
      "step": 1860
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.028076171875,
      "learning_rate": 1.1778239215664512e-05,
      "loss": 0.8196,
      "step": 1870
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.0322265625,
      "learning_rate": 1.1686535625931566e-05,
      "loss": 0.7873,
      "step": 1880
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.046630859375,
      "learning_rate": 1.1594685817817673e-05,
      "loss": 0.8126,
      "step": 1890
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.02490234375,
      "learning_rate": 1.1502697754469315e-05,
      "loss": 0.8462,
      "step": 1900
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.029296875,
      "learning_rate": 1.141057941101935e-05,
      "loss": 0.8273,
      "step": 1910
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.02294921875,
      "learning_rate": 1.1318338773895596e-05,
      "loss": 0.8222,
      "step": 1920
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.026611328125,
      "learning_rate": 1.1225983840128418e-05,
      "loss": 0.7724,
      "step": 1930
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.0400390625,
      "learning_rate": 1.1133522616657417e-05,
      "loss": 0.8072,
      "step": 1940
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.0286865234375,
      "learning_rate": 1.104096311963724e-05,
      "loss": 0.8306,
      "step": 1950
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.026611328125,
      "learning_rate": 1.0948313373742606e-05,
      "loss": 0.7973,
      "step": 1960
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.037841796875,
      "learning_rate": 1.0855581411472576e-05,
      "loss": 0.8385,
      "step": 1970
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.02197265625,
      "learning_rate": 1.076277527245417e-05,
      "loss": 0.8238,
      "step": 1980
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.0284423828125,
      "learning_rate": 1.0669903002745343e-05,
      "loss": 0.8102,
      "step": 1990
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.1826171875,
      "learning_rate": 1.0576972654137411e-05,
      "loss": 0.8189,
      "step": 2000
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.0247802734375,
      "learning_rate": 1.0483992283456992e-05,
      "loss": 0.7938,
      "step": 2010
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.0218505859375,
      "learning_rate": 1.0390969951867482e-05,
      "loss": 0.8171,
      "step": 2020
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.0311279296875,
      "learning_rate": 1.0297913724170187e-05,
      "loss": 0.8082,
      "step": 2030
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.0238037109375,
      "learning_rate": 1.0204831668105117e-05,
      "loss": 0.7972,
      "step": 2040
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.0218505859375,
      "learning_rate": 1.011173185365154e-05,
      "loss": 0.7743,
      "step": 2050
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.03515625,
      "learning_rate": 1.0018622352328331e-05,
      "loss": 0.8095,
      "step": 2060
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.03564453125,
      "learning_rate": 9.92551123649419e-06,
      "loss": 0.796,
      "step": 2070
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.02197265625,
      "learning_rate": 9.832406578647789e-06,
      "loss": 0.7923,
      "step": 2080
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.0230712890625,
      "learning_rate": 9.739316450727914e-06,
      "loss": 0.8106,
      "step": 2090
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.0244140625,
      "learning_rate": 9.646248923413639e-06,
      "loss": 0.7871,
      "step": 2100
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.027099609375,
      "learning_rate": 9.553212065424625e-06,
      "loss": 0.798,
      "step": 2110
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.0341796875,
      "learning_rate": 9.460213942821578e-06,
      "loss": 0.795,
      "step": 2120
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.023681640625,
      "learning_rate": 9.367262618306947e-06,
      "loss": 0.8001,
      "step": 2130
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.02294921875,
      "learning_rate": 9.274366150525902e-06,
      "loss": 0.766,
      "step": 2140
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.02587890625,
      "learning_rate": 9.181532593367675e-06,
      "loss": 0.7999,
      "step": 2150
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.0224609375,
      "learning_rate": 9.0887699952673e-06,
      "loss": 0.813,
      "step": 2160
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.035400390625,
      "learning_rate": 8.996086398507848e-06,
      "loss": 0.8108,
      "step": 2170
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.0267333984375,
      "learning_rate": 8.903489838523167e-06,
      "loss": 0.841,
      "step": 2180
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.02783203125,
      "learning_rate": 8.81098834320124e-06,
      "loss": 0.8204,
      "step": 2190
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.03759765625,
      "learning_rate": 8.71858993218818e-06,
      "loss": 0.7937,
      "step": 2200
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.04931640625,
      "learning_rate": 8.626302616192955e-06,
      "loss": 0.799,
      "step": 2210
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.025634765625,
      "learning_rate": 8.534134396292875e-06,
      "loss": 0.8033,
      "step": 2220
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.0277099609375,
      "learning_rate": 8.442093263239913e-06,
      "loss": 0.8089,
      "step": 2230
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.0228271484375,
      "learning_rate": 8.350187196767942e-06,
      "loss": 0.792,
      "step": 2240
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.047607421875,
      "learning_rate": 8.258424164900899e-06,
      "loss": 0.8242,
      "step": 2250
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.0250244140625,
      "learning_rate": 8.166812123261982e-06,
      "loss": 0.8058,
      "step": 2260
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.0283203125,
      "learning_rate": 8.075359014383914e-06,
      "loss": 0.8084,
      "step": 2270
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.0228271484375,
      "learning_rate": 7.984072767020359e-06,
      "loss": 0.7894,
      "step": 2280
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.0419921875,
      "learning_rate": 7.892961295458496e-06,
      "loss": 0.7993,
      "step": 2290
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.0260009765625,
      "learning_rate": 7.802032498832895e-06,
      "loss": 0.8036,
      "step": 2300
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.0235595703125,
      "learning_rate": 7.71129426044066e-06,
      "loss": 0.7973,
      "step": 2310
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.0242919921875,
      "learning_rate": 7.620754447057985e-06,
      "loss": 0.7964,
      "step": 2320
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.036376953125,
      "learning_rate": 7.530420908258111e-06,
      "loss": 0.777,
      "step": 2330
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.029541015625,
      "learning_rate": 7.4403014757308e-06,
      "loss": 0.8116,
      "step": 2340
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.0263671875,
      "learning_rate": 7.350403962603335e-06,
      "loss": 0.8267,
      "step": 2350
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.031982421875,
      "learning_rate": 7.260736162763149e-06,
      "loss": 0.8153,
      "step": 2360
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.1923828125,
      "learning_rate": 7.171305850182113e-06,
      "loss": 0.8026,
      "step": 2370
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.03466796875,
      "learning_rate": 7.082120778242554e-06,
      "loss": 0.8198,
      "step": 2380
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.034423828125,
      "learning_rate": 6.993188679065048e-06,
      "loss": 0.7804,
      "step": 2390
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.0245361328125,
      "learning_rate": 6.904517262838082e-06,
      "loss": 0.8251,
      "step": 2400
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.047607421875,
      "learning_rate": 6.8161142171495785e-06,
      "loss": 0.849,
      "step": 2410
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.02880859375,
      "learning_rate": 6.72798720632042e-06,
      "loss": 0.7912,
      "step": 2420
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.0245361328125,
      "learning_rate": 6.640143870739956e-06,
      "loss": 0.7864,
      "step": 2430
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.02392578125,
      "learning_rate": 6.552591826203616e-06,
      "loss": 0.7713,
      "step": 2440
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.023681640625,
      "learning_rate": 6.4653386632526275e-06,
      "loss": 0.7925,
      "step": 2450
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.045166015625,
      "learning_rate": 6.378391946515937e-06,
      "loss": 0.8402,
      "step": 2460
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.023681640625,
      "learning_rate": 6.291759214054383e-06,
      "loss": 0.8032,
      "step": 2470
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.0238037109375,
      "learning_rate": 6.205447976707154e-06,
      "loss": 0.7891,
      "step": 2480
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.08935546875,
      "learning_rate": 6.119465717440629e-06,
      "loss": 0.819,
      "step": 2490
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.0283203125,
      "learning_rate": 6.033819890699616e-06,
      "loss": 0.8318,
      "step": 2500
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.0240478515625,
      "learning_rate": 5.94851792176107e-06,
      "loss": 0.8241,
      "step": 2510
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.0311279296875,
      "learning_rate": 5.863567206090348e-06,
      "loss": 0.7844,
      "step": 2520
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.025634765625,
      "learning_rate": 5.778975108700031e-06,
      "loss": 0.8273,
      "step": 2530
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.03759765625,
      "learning_rate": 5.694748963511396e-06,
      "loss": 0.8117,
      "step": 2540
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.0238037109375,
      "learning_rate": 5.610896072718603e-06,
      "loss": 0.8067,
      "step": 2550
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.0213623046875,
      "learning_rate": 5.527423706155586e-06,
      "loss": 0.7988,
      "step": 2560
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.0230712890625,
      "learning_rate": 5.4443391006657896e-06,
      "loss": 0.8286,
      "step": 2570
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.033447265625,
      "learning_rate": 5.361649459474756e-06,
      "loss": 0.8054,
      "step": 2580
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.0233154296875,
      "learning_rate": 5.279361951565618e-06,
      "loss": 0.7801,
      "step": 2590
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.027587890625,
      "learning_rate": 5.197483711057569e-06,
      "loss": 0.8107,
      "step": 2600
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.0247802734375,
      "learning_rate": 5.116021836587353e-06,
      "loss": 0.8273,
      "step": 2610
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.0235595703125,
      "learning_rate": 5.0349833906938235e-06,
      "loss": 0.7919,
      "step": 2620
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.0240478515625,
      "learning_rate": 4.954375399205655e-06,
      "loss": 0.8371,
      "step": 2630
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.0257568359375,
      "learning_rate": 4.8742048506322045e-06,
      "loss": 0.7882,
      "step": 2640
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.027099609375,
      "learning_rate": 4.794478695557631e-06,
      "loss": 0.8149,
      "step": 2650
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.02685546875,
      "learning_rate": 4.715203846038312e-06,
      "loss": 0.8254,
      "step": 2660
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.08447265625,
      "learning_rate": 4.636387175003558e-06,
      "loss": 0.8249,
      "step": 2670
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.0264892578125,
      "learning_rate": 4.558035515659768e-06,
      "loss": 0.8004,
      "step": 2680
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.0230712890625,
      "learning_rate": 4.480155660898001e-06,
      "loss": 0.7959,
      "step": 2690
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.0341796875,
      "learning_rate": 4.402754362705051e-06,
      "loss": 0.786,
      "step": 2700
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.033203125,
      "learning_rate": 4.325838331578061e-06,
      "loss": 0.7948,
      "step": 2710
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.0269775390625,
      "learning_rate": 4.249414235942755e-06,
      "loss": 0.7959,
      "step": 2720
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.045654296875,
      "learning_rate": 4.173488701575274e-06,
      "loss": 0.775,
      "step": 2730
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.0341796875,
      "learning_rate": 4.098068311027772e-06,
      "loss": 0.7992,
      "step": 2740
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.02783203125,
      "learning_rate": 4.023159603057698e-06,
      "loss": 0.8045,
      "step": 2750
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.0244140625,
      "learning_rate": 3.948769072060927e-06,
      "loss": 0.7903,
      "step": 2760
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.0458984375,
      "learning_rate": 3.874903167508688e-06,
      "loss": 0.7974,
      "step": 2770
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.026123046875,
      "learning_rate": 3.801568293388421e-06,
      "loss": 0.7766,
      "step": 2780
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.0400390625,
      "learning_rate": 3.728770807648574e-06,
      "loss": 0.8202,
      "step": 2790
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.0250244140625,
      "learning_rate": 3.6565170216473744e-06,
      "loss": 0.8047,
      "step": 2800
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.04931640625,
      "learning_rate": 3.584813199605658e-06,
      "loss": 0.8324,
      "step": 2810
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.0255126953125,
      "learning_rate": 3.513665558063771e-06,
      "loss": 0.8203,
      "step": 2820
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.034912109375,
      "learning_rate": 3.4430802653426176e-06,
      "loss": 0.7997,
      "step": 2830
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.06298828125,
      "learning_rate": 3.373063441008877e-06,
      "loss": 0.7783,
      "step": 2840
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.03857421875,
      "learning_rate": 3.303621155344453e-06,
      "loss": 0.8088,
      "step": 2850
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.0250244140625,
      "learning_rate": 3.234759428820198e-06,
      "loss": 0.8231,
      "step": 2860
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.0235595703125,
      "learning_rate": 3.1664842315739586e-06,
      "loss": 0.8005,
      "step": 2870
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.03076171875,
      "learning_rate": 3.098801482892966e-06,
      "loss": 0.7926,
      "step": 2880
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.11962890625,
      "learning_rate": 3.031717050700659e-06,
      "loss": 0.7926,
      "step": 2890
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.045166015625,
      "learning_rate": 2.9652367510479476e-06,
      "loss": 0.8127,
      "step": 2900
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.021728515625,
      "learning_rate": 2.899366347608974e-06,
      "loss": 0.8046,
      "step": 2910
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.036865234375,
      "learning_rate": 2.834111551181423e-06,
      "loss": 0.7647,
      "step": 2920
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.0260009765625,
      "learning_rate": 2.7694780191914005e-06,
      "loss": 0.7985,
      "step": 2930
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.04052734375,
      "learning_rate": 2.7054713552029577e-06,
      "loss": 0.841,
      "step": 2940
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.041748046875,
      "learning_rate": 2.6420971084322745e-06,
      "loss": 0.7775,
      "step": 2950
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.0244140625,
      "learning_rate": 2.5793607732665402e-06,
      "loss": 0.7954,
      "step": 2960
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.03125,
      "learning_rate": 2.5172677887876416e-06,
      "loss": 0.7875,
      "step": 2970
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.02490234375,
      "learning_rate": 2.455823538300569e-06,
      "loss": 0.8065,
      "step": 2980
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.0224609375,
      "learning_rate": 2.3950333488667178e-06,
      "loss": 0.8201,
      "step": 2990
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.06298828125,
      "learning_rate": 2.3349024908420403e-06,
      "loss": 0.813,
      "step": 3000
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.03076171875,
      "learning_rate": 2.2754361774201217e-06,
      "loss": 0.8076,
      "step": 3010
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.0341796875,
      "learning_rate": 2.2166395641802076e-06,
      "loss": 0.8135,
      "step": 3020
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.0673828125,
      "learning_rate": 2.1585177486402275e-06,
      "loss": 0.8095,
      "step": 3030
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.0341796875,
      "learning_rate": 2.101075769814855e-06,
      "loss": 0.7985,
      "step": 3040
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.04150390625,
      "learning_rate": 2.0443186077786358e-06,
      "loss": 0.7976,
      "step": 3050
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.04736328125,
      "learning_rate": 1.9882511832342297e-06,
      "loss": 0.7868,
      "step": 3060
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.0262451171875,
      "learning_rate": 1.9328783570857954e-06,
      "loss": 0.8072,
      "step": 3070
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.04296875,
      "learning_rate": 1.8782049300175698e-06,
      "loss": 0.7931,
      "step": 3080
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.0269775390625,
      "learning_rate": 1.8242356420776485e-06,
      "loss": 0.8185,
      "step": 3090
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.033447265625,
      "learning_rate": 1.7709751722670466e-06,
      "loss": 0.8391,
      "step": 3100
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.0274658203125,
      "learning_rate": 1.718428138134034e-06,
      "loss": 0.8502,
      "step": 3110
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.02783203125,
      "learning_rate": 1.666599095373811e-06,
      "loss": 0.8185,
      "step": 3120
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.025390625,
      "learning_rate": 1.6154925374335362e-06,
      "loss": 0.806,
      "step": 3130
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.0225830078125,
      "learning_rate": 1.5651128951227613e-06,
      "loss": 0.783,
      "step": 3140
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.033935546875,
      "learning_rate": 1.5154645362292853e-06,
      "loss": 0.8159,
      "step": 3150
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.025390625,
      "learning_rate": 1.4665517651404814e-06,
      "loss": 0.7793,
      "step": 3160
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.0220947265625,
      "learning_rate": 1.4183788224701201e-06,
      "loss": 0.7754,
      "step": 3170
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.0269775390625,
      "learning_rate": 1.370949884690711e-06,
      "loss": 0.847,
      "step": 3180
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.035888671875,
      "learning_rate": 1.3242690637714228e-06,
      "loss": 0.8014,
      "step": 3190
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.0238037109375,
      "learning_rate": 1.2783404068215776e-06,
      "loss": 0.8235,
      "step": 3200
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.033447265625,
      "learning_rate": 1.2331678957397819e-06,
      "loss": 0.7997,
      "step": 3210
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.033203125,
      "learning_rate": 1.1887554468687046e-06,
      "loss": 0.8159,
      "step": 3220
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.033935546875,
      "learning_rate": 1.145106910655538e-06,
      "loss": 0.8392,
      "step": 3230
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.023193359375,
      "learning_rate": 1.1022260713181786e-06,
      "loss": 0.8266,
      "step": 3240
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.03662109375,
      "learning_rate": 1.0601166465171387e-06,
      "loss": 0.8209,
      "step": 3250
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.0294189453125,
      "learning_rate": 1.0187822870332398e-06,
      "loss": 0.8021,
      "step": 3260
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.051025390625,
      "learning_rate": 9.782265764510968e-07,
      "loss": 0.7938,
      "step": 3270
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.0291748046875,
      "learning_rate": 9.384530308484275e-07,
      "loss": 0.8007,
      "step": 3280
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.0279541015625,
      "learning_rate": 8.99465098491229e-07,
      "loss": 0.8097,
      "step": 3290
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.032470703125,
      "learning_rate": 8.612661595348038e-07,
      "loss": 0.8029,
      "step": 3300
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.0234375,
      "learning_rate": 8.238595257307225e-07,
      "loss": 0.8079,
      "step": 3310
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.03125,
      "learning_rate": 7.872484401397018e-07,
      "loss": 0.8074,
      "step": 3320
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.024658203125,
      "learning_rate": 7.514360768504314e-07,
      "loss": 0.7961,
      "step": 3330
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.03125,
      "learning_rate": 7.164255407043986e-07,
      "loss": 0.7701,
      "step": 3340
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.0269775390625,
      "learning_rate": 6.822198670266989e-07,
      "loss": 0.8165,
      "step": 3350
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.0277099609375,
      "learning_rate": 6.488220213628837e-07,
      "loss": 0.8097,
      "step": 3360
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.0322265625,
      "learning_rate": 6.16234899221858e-07,
      "loss": 0.8073,
      "step": 3370
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.0234375,
      "learning_rate": 5.844613258248411e-07,
      "loss": 0.7865,
      "step": 3380
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.130859375,
      "learning_rate": 5.535040558604299e-07,
      "loss": 0.8182,
      "step": 3390
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.0233154296875,
      "learning_rate": 5.233657732457775e-07,
      "loss": 0.78,
      "step": 3400
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.0284423828125,
      "learning_rate": 4.940490908938977e-07,
      "loss": 0.7961,
      "step": 3410
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.0478515625,
      "learning_rate": 4.6555655048713953e-07,
      "loss": 0.7946,
      "step": 3420
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.023193359375,
      "learning_rate": 4.3789062225682356e-07,
      "loss": 0.8022,
      "step": 3430
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.060302734375,
      "learning_rate": 4.1105370476908104e-07,
      "loss": 0.8201,
      "step": 3440
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.042236328125,
      "learning_rate": 3.8504812471690687e-07,
      "loss": 0.8014,
      "step": 3450
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.02392578125,
      "learning_rate": 3.598761367184367e-07,
      "loss": 0.7995,
      "step": 3460
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.02880859375,
      "learning_rate": 3.3553992312148177e-07,
      "loss": 0.8139,
      "step": 3470
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.029052734375,
      "learning_rate": 3.1204159381432174e-07,
      "loss": 0.8127,
      "step": 3480
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.028564453125,
      "learning_rate": 2.8938318604278314e-07,
      "loss": 0.8009,
      "step": 3490
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.03173828125,
      "learning_rate": 2.675666642336172e-07,
      "loss": 0.8319,
      "step": 3500
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.031494140625,
      "learning_rate": 2.4659391982418626e-07,
      "loss": 0.8413,
      "step": 3510
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.08642578125,
      "learning_rate": 2.264667710984836e-07,
      "loss": 0.8194,
      "step": 3520
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.0289306640625,
      "learning_rate": 2.0718696302949092e-07,
      "loss": 0.8128,
      "step": 3530
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.0771484375,
      "learning_rate": 1.8875616712789257e-07,
      "loss": 0.8008,
      "step": 3540
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.024658203125,
      "learning_rate": 1.7117598129716362e-07,
      "loss": 0.7753,
      "step": 3550
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.0260009765625,
      "learning_rate": 1.544479296950341e-07,
      "loss": 0.802,
      "step": 3560
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.025634765625,
      "learning_rate": 1.385734626013435e-07,
      "loss": 0.7936,
      "step": 3570
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.0240478515625,
      "learning_rate": 1.2355395629231493e-07,
      "loss": 0.7956,
      "step": 3580
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.08251953125,
      "learning_rate": 1.0939071292122572e-07,
      "loss": 0.7769,
      "step": 3590
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.0279541015625,
      "learning_rate": 9.608496040551918e-08,
      "loss": 0.7957,
      "step": 3600
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.0277099609375,
      "learning_rate": 8.363785232034849e-08,
      "loss": 0.814,
      "step": 3610
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.03173828125,
      "learning_rate": 7.205046779856007e-08,
      "loss": 0.8155,
      "step": 3620
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.03173828125,
      "learning_rate": 6.132381143713728e-08,
      "loss": 0.8364,
      "step": 3630
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.0264892578125,
      "learning_rate": 5.1458813210106815e-08,
      "loss": 0.8173,
      "step": 3640
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.038818359375,
      "learning_rate": 4.245632838791092e-08,
      "loss": 0.8085,
      "step": 3650
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.0225830078125,
      "learning_rate": 3.431713746325449e-08,
      "loss": 0.8195,
      "step": 3660
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.0751953125,
      "learning_rate": 2.7041946083442573e-08,
      "loss": 0.8029,
      "step": 3670
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.06494140625,
      "learning_rate": 2.0631384989202585e-08,
      "loss": 0.8359,
      "step": 3680
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.030517578125,
      "learning_rate": 1.5086009959995875e-08,
      "loss": 0.8233,
      "step": 3690
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.0228271484375,
      "learning_rate": 1.0406301765837346e-08,
      "loss": 0.7743,
      "step": 3700
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.024658203125,
      "learning_rate": 6.592666125614377e-09,
      "loss": 0.7764,
      "step": 3710
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.023193359375,
      "learning_rate": 3.645433671908283e-09,
      "loss": 0.798,
      "step": 3720
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.0260009765625,
      "learning_rate": 1.5648599223316852e-09,
      "loss": 0.8119,
      "step": 3730
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.0247802734375,
      "learning_rate": 3.5112525737734935e-10,
      "loss": 0.8295,
      "step": 3740
    }
  ],
  "logging_steps": 10,
  "max_steps": 3749,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1.2690756062895145e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}