{
  "best_metric": 66.9763,
  "best_model_checkpoint": "Meta-Llama-3.1-8B-Instruct-finetuned/checkpoint-400",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025,
      "grad_norm": 0.5086380243301392,
      "learning_rate": 1.9950000000000004e-05,
      "loss": 2.3289,
      "step": 1
    },
    {
      "epoch": 0.005,
      "grad_norm": 0.8586075305938721,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 3.1847,
      "step": 2
    },
    {
      "epoch": 0.0075,
      "grad_norm": 0.7075896859169006,
      "learning_rate": 1.985e-05,
      "loss": 2.7698,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.41437870264053345,
      "learning_rate": 1.98e-05,
      "loss": 2.5479,
      "step": 4
    },
    {
      "epoch": 0.0125,
      "grad_norm": 0.4806264638900757,
      "learning_rate": 1.9750000000000002e-05,
      "loss": 2.6004,
      "step": 5
    },
    {
      "epoch": 0.015,
      "grad_norm": 0.5133494734764099,
      "learning_rate": 1.97e-05,
      "loss": 2.7935,
      "step": 6
    },
    {
      "epoch": 0.0175,
      "grad_norm": 0.4955611824989319,
      "learning_rate": 1.9650000000000003e-05,
      "loss": 2.5868,
      "step": 7
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.5297004580497742,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 2.8002,
      "step": 8
    },
    {
      "epoch": 0.0225,
      "grad_norm": 0.3629765510559082,
      "learning_rate": 1.955e-05,
      "loss": 2.6765,
      "step": 9
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.40658852458000183,
      "learning_rate": 1.95e-05,
      "loss": 2.4437,
      "step": 10
    },
    {
      "epoch": 0.0275,
      "grad_norm": 0.7563017010688782,
      "learning_rate": 1.9450000000000002e-05,
      "loss": 2.7119,
      "step": 11
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.5557965636253357,
      "learning_rate": 1.94e-05,
      "loss": 3.0774,
      "step": 12
    },
    {
      "epoch": 0.0325,
      "grad_norm": 0.5341749787330627,
      "learning_rate": 1.9350000000000003e-05,
      "loss": 2.9765,
      "step": 13
    },
    {
      "epoch": 0.035,
      "grad_norm": 0.3685285449028015,
      "learning_rate": 1.93e-05,
      "loss": 2.7085,
      "step": 14
    },
    {
      "epoch": 0.0375,
      "grad_norm": 0.5424759387969971,
      "learning_rate": 1.925e-05,
      "loss": 2.6293,
      "step": 15
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.4518626630306244,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 2.4085,
      "step": 16
    },
    {
      "epoch": 0.0425,
      "grad_norm": 0.3510679006576538,
      "learning_rate": 1.915e-05,
      "loss": 2.3645,
      "step": 17
    },
    {
      "epoch": 0.045,
      "grad_norm": 0.5852112174034119,
      "learning_rate": 1.91e-05,
      "loss": 3.1263,
      "step": 18
    },
    {
      "epoch": 0.0475,
      "grad_norm": 0.9667254686355591,
      "learning_rate": 1.9050000000000002e-05,
      "loss": 3.5084,
      "step": 19
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.4582698941230774,
      "learning_rate": 1.9e-05,
      "loss": 3.012,
      "step": 20
    },
    {
      "epoch": 0.0525,
      "grad_norm": 0.6149416565895081,
      "learning_rate": 1.8950000000000003e-05,
      "loss": 2.7546,
      "step": 21
    },
    {
      "epoch": 0.055,
      "grad_norm": 0.4512835144996643,
      "learning_rate": 1.8900000000000002e-05,
      "loss": 2.5626,
      "step": 22
    },
    {
      "epoch": 0.0575,
      "grad_norm": 0.739122748374939,
      "learning_rate": 1.885e-05,
      "loss": 2.9673,
      "step": 23
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.6391552686691284,
      "learning_rate": 1.88e-05,
      "loss": 3.0665,
      "step": 24
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.5419601202011108,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 2.3289,
      "step": 25
    },
    {
      "epoch": 0.065,
      "grad_norm": 1.0033130645751953,
      "learning_rate": 1.8700000000000004e-05,
      "loss": 2.9624,
      "step": 26
    },
    {
      "epoch": 0.0675,
      "grad_norm": 0.6456469297409058,
      "learning_rate": 1.8650000000000003e-05,
      "loss": 2.3933,
      "step": 27
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.5043237209320068,
      "learning_rate": 1.86e-05,
      "loss": 2.8812,
      "step": 28
    },
    {
      "epoch": 0.0725,
      "grad_norm": 0.6468444466590881,
      "learning_rate": 1.855e-05,
      "loss": 2.7498,
      "step": 29
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.7163925766944885,
      "learning_rate": 1.8500000000000002e-05,
      "loss": 2.9495,
      "step": 30
    },
    {
      "epoch": 0.0775,
      "grad_norm": 0.8370097875595093,
      "learning_rate": 1.845e-05,
      "loss": 2.8212,
      "step": 31
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.48631641268730164,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 2.379,
      "step": 32
    },
    {
      "epoch": 0.0825,
      "grad_norm": 1.7928434610366821,
      "learning_rate": 1.8350000000000002e-05,
      "loss": 3.1519,
      "step": 33
    },
    {
      "epoch": 0.085,
      "grad_norm": 0.6675847172737122,
      "learning_rate": 1.83e-05,
      "loss": 3.0783,
      "step": 34
    },
    {
      "epoch": 0.0875,
      "grad_norm": 0.7228886485099792,
      "learning_rate": 1.825e-05,
      "loss": 3.1486,
      "step": 35
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.744644820690155,
      "learning_rate": 1.8200000000000002e-05,
      "loss": 2.5763,
      "step": 36
    },
    {
      "epoch": 0.0925,
      "grad_norm": 2.355612277984619,
      "learning_rate": 1.815e-05,
      "loss": 3.3755,
      "step": 37
    },
    {
      "epoch": 0.095,
      "grad_norm": 0.9405584335327148,
      "learning_rate": 1.8100000000000003e-05,
      "loss": 3.1682,
      "step": 38
    },
    {
      "epoch": 0.0975,
      "grad_norm": 0.7231965661048889,
      "learning_rate": 1.805e-05,
      "loss": 2.6062,
      "step": 39
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.8962283730506897,
      "learning_rate": 1.8e-05,
      "loss": 3.2604,
      "step": 40
    },
    {
      "epoch": 0.1025,
      "grad_norm": 0.4068661630153656,
      "learning_rate": 1.795e-05,
      "loss": 2.4424,
      "step": 41
    },
    {
      "epoch": 0.105,
      "grad_norm": 0.8694533109664917,
      "learning_rate": 1.79e-05,
      "loss": 2.6876,
      "step": 42
    },
    {
      "epoch": 0.1075,
      "grad_norm": 0.624096691608429,
      "learning_rate": 1.785e-05,
      "loss": 2.3869,
      "step": 43
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.0791139602661133,
      "learning_rate": 1.7800000000000002e-05,
      "loss": 3.2583,
      "step": 44
    },
    {
      "epoch": 0.1125,
      "grad_norm": 0.711621880531311,
      "learning_rate": 1.775e-05,
      "loss": 2.7002,
      "step": 45
    },
    {
      "epoch": 0.115,
      "grad_norm": 0.46927714347839355,
      "learning_rate": 1.77e-05,
      "loss": 2.3851,
      "step": 46
    },
    {
      "epoch": 0.1175,
      "grad_norm": 0.7309519648551941,
      "learning_rate": 1.7650000000000002e-05,
      "loss": 2.3945,
      "step": 47
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.7145869135856628,
      "learning_rate": 1.76e-05,
      "loss": 2.4627,
      "step": 48
    },
    {
      "epoch": 0.1225,
      "grad_norm": 1.159073829650879,
      "learning_rate": 1.755e-05,
      "loss": 2.6211,
      "step": 49
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.8457475304603577,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 2.7707,
      "step": 50
    },
    {
      "epoch": 0.1275,
      "grad_norm": 0.8868067264556885,
      "learning_rate": 1.7450000000000004e-05,
      "loss": 2.9123,
      "step": 51
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.7379621863365173,
      "learning_rate": 1.7400000000000003e-05,
      "loss": 2.7426,
      "step": 52
    },
    {
      "epoch": 0.1325,
      "grad_norm": 0.7611985802650452,
      "learning_rate": 1.735e-05,
      "loss": 2.7205,
      "step": 53
    },
    {
      "epoch": 0.135,
      "grad_norm": 0.4997944235801697,
      "learning_rate": 1.73e-05,
      "loss": 2.1109,
      "step": 54
    },
    {
      "epoch": 0.1375,
      "grad_norm": 0.7576261758804321,
      "learning_rate": 1.7250000000000003e-05,
      "loss": 2.9695,
      "step": 55
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.5478056073188782,
      "learning_rate": 1.72e-05,
      "loss": 2.6197,
      "step": 56
    },
    {
      "epoch": 0.1425,
      "grad_norm": 0.6078264713287354,
      "learning_rate": 1.7150000000000004e-05,
      "loss": 2.4308,
      "step": 57
    },
    {
      "epoch": 0.145,
      "grad_norm": 2.7619869709014893,
      "learning_rate": 1.7100000000000002e-05,
      "loss": 2.964,
      "step": 58
    },
    {
      "epoch": 0.1475,
      "grad_norm": 0.7455095052719116,
      "learning_rate": 1.705e-05,
      "loss": 2.9467,
      "step": 59
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.794147789478302,
      "learning_rate": 1.7e-05,
      "loss": 2.8496,
      "step": 60
    },
    {
      "epoch": 0.1525,
      "grad_norm": 1.1698209047317505,
      "learning_rate": 1.6950000000000002e-05,
      "loss": 3.213,
      "step": 61
    },
    {
      "epoch": 0.155,
      "grad_norm": 0.425815612077713,
      "learning_rate": 1.69e-05,
      "loss": 2.5624,
      "step": 62
    },
    {
      "epoch": 0.1575,
      "grad_norm": 0.5705508589744568,
      "learning_rate": 1.6850000000000003e-05,
      "loss": 1.9561,
      "step": 63
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.791164755821228,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 2.8788,
      "step": 64
    },
    {
      "epoch": 0.1625,
      "grad_norm": 0.539487361907959,
      "learning_rate": 1.675e-05,
      "loss": 2.9631,
      "step": 65
    },
    {
      "epoch": 0.165,
      "grad_norm": 0.6165200471878052,
      "learning_rate": 1.67e-05,
      "loss": 2.731,
      "step": 66
    },
    {
      "epoch": 0.1675,
      "grad_norm": 0.4418243169784546,
      "learning_rate": 1.665e-05,
      "loss": 2.7103,
      "step": 67
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.0445636510849,
      "learning_rate": 1.66e-05,
      "loss": 3.3579,
      "step": 68
    },
    {
      "epoch": 0.1725,
      "grad_norm": 1.2330797910690308,
      "learning_rate": 1.6550000000000002e-05,
      "loss": 2.9892,
      "step": 69
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.6254209876060486,
      "learning_rate": 1.65e-05,
      "loss": 2.5447,
      "step": 70
    },
    {
      "epoch": 0.1775,
      "grad_norm": 1.1451466083526611,
      "learning_rate": 1.645e-05,
      "loss": 2.9316,
      "step": 71
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.9813737869262695,
      "learning_rate": 1.64e-05,
      "loss": 2.6544,
      "step": 72
    },
    {
      "epoch": 0.1825,
      "grad_norm": 0.6040698885917664,
      "learning_rate": 1.635e-05,
      "loss": 2.9732,
      "step": 73
    },
    {
      "epoch": 0.185,
      "grad_norm": 1.079363465309143,
      "learning_rate": 1.63e-05,
      "loss": 2.7277,
      "step": 74
    },
    {
      "epoch": 0.1875,
      "grad_norm": 1.183262586593628,
      "learning_rate": 1.6250000000000002e-05,
      "loss": 3.4225,
      "step": 75
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.024534821510315,
      "learning_rate": 1.62e-05,
      "loss": 2.6733,
      "step": 76
    },
    {
      "epoch": 0.1925,
      "grad_norm": 0.7848602533340454,
      "learning_rate": 1.6150000000000003e-05,
      "loss": 2.2153,
      "step": 77
    },
    {
      "epoch": 0.195,
      "grad_norm": 0.9561752676963806,
      "learning_rate": 1.6100000000000002e-05,
      "loss": 2.868,
      "step": 78
    },
    {
      "epoch": 0.1975,
      "grad_norm": 0.7831237316131592,
      "learning_rate": 1.605e-05,
      "loss": 3.3643,
      "step": 79
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.0299983024597168,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.8384,
      "step": 80
    },
    {
      "epoch": 0.2025,
      "grad_norm": 0.7254953384399414,
      "learning_rate": 1.595e-05,
      "loss": 2.3374,
      "step": 81
    },
    {
      "epoch": 0.205,
      "grad_norm": 1.1295499801635742,
      "learning_rate": 1.5900000000000004e-05,
      "loss": 2.7828,
      "step": 82
    },
    {
      "epoch": 0.2075,
      "grad_norm": 1.5047646760940552,
      "learning_rate": 1.5850000000000002e-05,
      "loss": 3.3818,
      "step": 83
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.1679288148880005,
      "learning_rate": 1.58e-05,
      "loss": 2.8351,
      "step": 84
    },
    {
      "epoch": 0.2125,
      "grad_norm": 1.0215470790863037,
      "learning_rate": 1.575e-05,
      "loss": 2.8807,
      "step": 85
    },
    {
      "epoch": 0.215,
      "grad_norm": 0.8660721778869629,
      "learning_rate": 1.5700000000000002e-05,
      "loss": 2.9657,
      "step": 86
    },
    {
      "epoch": 0.2175,
      "grad_norm": 1.3509225845336914,
      "learning_rate": 1.565e-05,
      "loss": 3.2028,
      "step": 87
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.8548119068145752,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 2.7189,
      "step": 88
    },
    {
      "epoch": 0.2225,
      "grad_norm": 0.6334153413772583,
      "learning_rate": 1.5550000000000002e-05,
      "loss": 2.7275,
      "step": 89
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.9550497531890869,
      "learning_rate": 1.55e-05,
      "loss": 2.6446,
      "step": 90
    },
    {
      "epoch": 0.2275,
      "grad_norm": 1.1148252487182617,
      "learning_rate": 1.545e-05,
      "loss": 2.5969,
      "step": 91
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.5404387712478638,
      "learning_rate": 1.54e-05,
      "loss": 2.9074,
      "step": 92
    },
    {
      "epoch": 0.2325,
      "grad_norm": 0.5893303155899048,
      "learning_rate": 1.535e-05,
      "loss": 2.4446,
      "step": 93
    },
    {
      "epoch": 0.235,
      "grad_norm": 0.8293983936309814,
      "learning_rate": 1.5300000000000003e-05,
      "loss": 2.881,
      "step": 94
    },
    {
      "epoch": 0.2375,
      "grad_norm": 0.647366464138031,
      "learning_rate": 1.525e-05,
      "loss": 2.303,
      "step": 95
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.5540935397148132,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 2.5093,
      "step": 96
    },
    {
      "epoch": 0.2425,
      "grad_norm": 0.8777411580085754,
      "learning_rate": 1.515e-05,
      "loss": 2.9024,
      "step": 97
    },
    {
      "epoch": 0.245,
      "grad_norm": 1.4827839136123657,
      "learning_rate": 1.5100000000000001e-05,
      "loss": 3.5164,
      "step": 98
    },
    {
      "epoch": 0.2475,
      "grad_norm": 1.0348917245864868,
      "learning_rate": 1.505e-05,
      "loss": 3.2313,
      "step": 99
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.6850854754447937,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 2.4828,
      "step": 100
    },
    {
      "epoch": 0.2525,
      "grad_norm": 1.2222882509231567,
      "learning_rate": 1.4950000000000003e-05,
      "loss": 2.63,
      "step": 101
    },
    {
      "epoch": 0.255,
      "grad_norm": 1.0515038967132568,
      "learning_rate": 1.4900000000000001e-05,
      "loss": 3.3098,
      "step": 102
    },
    {
      "epoch": 0.2575,
      "grad_norm": 1.3674108982086182,
      "learning_rate": 1.4850000000000002e-05,
      "loss": 2.7831,
      "step": 103
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.6067950129508972,
      "learning_rate": 1.48e-05,
      "loss": 2.4279,
      "step": 104
    },
    {
      "epoch": 0.2625,
      "grad_norm": 1.3909555673599243,
      "learning_rate": 1.4750000000000003e-05,
      "loss": 2.6093,
      "step": 105
    },
    {
      "epoch": 0.265,
      "grad_norm": 0.7833155393600464,
      "learning_rate": 1.4700000000000002e-05,
      "loss": 2.4604,
      "step": 106
    },
    {
      "epoch": 0.2675,
      "grad_norm": 0.9903278946876526,
      "learning_rate": 1.4650000000000002e-05,
      "loss": 2.886,
      "step": 107
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.8194913268089294,
      "learning_rate": 1.46e-05,
      "loss": 2.7935,
      "step": 108
    },
    {
      "epoch": 0.2725,
      "grad_norm": 1.1634082794189453,
      "learning_rate": 1.4550000000000001e-05,
      "loss": 3.3633,
      "step": 109
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.5949274897575378,
      "learning_rate": 1.45e-05,
      "loss": 2.2084,
      "step": 110
    },
    {
      "epoch": 0.2775,
      "grad_norm": 0.8783496618270874,
      "learning_rate": 1.4450000000000002e-05,
      "loss": 3.1123,
      "step": 111
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.2037030458450317,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 3.0479,
      "step": 112
    },
    {
      "epoch": 0.2825,
      "grad_norm": 0.7056751847267151,
      "learning_rate": 1.4350000000000002e-05,
      "loss": 2.2833,
      "step": 113
    },
    {
      "epoch": 0.285,
      "grad_norm": 1.687018871307373,
      "learning_rate": 1.43e-05,
      "loss": 3.0165,
      "step": 114
    },
    {
      "epoch": 0.2875,
      "grad_norm": 1.1513874530792236,
      "learning_rate": 1.425e-05,
      "loss": 2.8763,
      "step": 115
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.7570899128913879,
      "learning_rate": 1.4200000000000001e-05,
      "loss": 2.7981,
      "step": 116
    },
    {
      "epoch": 0.2925,
      "grad_norm": 1.3397407531738281,
      "learning_rate": 1.4150000000000002e-05,
      "loss": 2.7536,
      "step": 117
    },
    {
      "epoch": 0.295,
      "grad_norm": 0.710766613483429,
      "learning_rate": 1.41e-05,
      "loss": 2.2904,
      "step": 118
    },
    {
      "epoch": 0.2975,
      "grad_norm": 1.6919655799865723,
      "learning_rate": 1.4050000000000001e-05,
      "loss": 3.1436,
      "step": 119
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.8802596926689148,
      "learning_rate": 1.4e-05,
      "loss": 2.969,
      "step": 120
    },
    {
      "epoch": 0.3025,
      "grad_norm": 1.3881422281265259,
      "learning_rate": 1.3950000000000002e-05,
      "loss": 2.7345,
      "step": 121
    },
    {
      "epoch": 0.305,
      "grad_norm": 1.0002195835113525,
      "learning_rate": 1.39e-05,
      "loss": 2.5324,
      "step": 122
    },
    {
      "epoch": 0.3075,
      "grad_norm": 0.7784033417701721,
      "learning_rate": 1.3850000000000001e-05,
      "loss": 2.4744,
      "step": 123
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.422712802886963,
      "learning_rate": 1.38e-05,
      "loss": 3.0338,
      "step": 124
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.775004506111145,
      "learning_rate": 1.375e-05,
      "loss": 2.5653,
      "step": 125
    },
    {
      "epoch": 0.315,
      "grad_norm": 0.8815636038780212,
      "learning_rate": 1.3700000000000003e-05,
      "loss": 2.7117,
      "step": 126
    },
    {
      "epoch": 0.3175,
      "grad_norm": 0.7529321312904358,
      "learning_rate": 1.3650000000000001e-05,
      "loss": 2.2918,
      "step": 127
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.1694319248199463,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 2.7757,
      "step": 128
    },
    {
      "epoch": 0.3225,
      "grad_norm": 1.25980544090271,
      "learning_rate": 1.355e-05,
      "loss": 2.8813,
      "step": 129
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.8933326005935669,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 2.6694,
      "step": 130
    },
    {
      "epoch": 0.3275,
      "grad_norm": 1.1248258352279663,
      "learning_rate": 1.3450000000000002e-05,
      "loss": 2.9221,
      "step": 131
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.1657884120941162,
      "learning_rate": 1.3400000000000002e-05,
      "loss": 2.7624,
      "step": 132
    },
    {
      "epoch": 0.3325,
      "grad_norm": 0.6563082337379456,
      "learning_rate": 1.3350000000000001e-05,
      "loss": 2.6828,
      "step": 133
    },
    {
      "epoch": 0.335,
      "grad_norm": 1.9324404001235962,
      "learning_rate": 1.3300000000000001e-05,
      "loss": 3.3839,
      "step": 134
    },
    {
      "epoch": 0.3375,
      "grad_norm": 1.4225391149520874,
      "learning_rate": 1.325e-05,
      "loss": 3.0225,
      "step": 135
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.3360658884048462,
      "learning_rate": 1.3200000000000002e-05,
      "loss": 2.8966,
      "step": 136
    },
    {
      "epoch": 0.3425,
      "grad_norm": 0.8045865297317505,
      "learning_rate": 1.3150000000000001e-05,
      "loss": 2.7465,
      "step": 137
    },
    {
      "epoch": 0.345,
      "grad_norm": 0.9894474744796753,
      "learning_rate": 1.3100000000000002e-05,
      "loss": 2.0347,
      "step": 138
    },
    {
      "epoch": 0.3475,
      "grad_norm": 1.2224481105804443,
      "learning_rate": 1.305e-05,
      "loss": 2.5152,
      "step": 139
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.8339478373527527,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 2.8098,
      "step": 140
    },
    {
      "epoch": 0.3525,
      "grad_norm": 0.8256344795227051,
      "learning_rate": 1.295e-05,
      "loss": 2.6257,
      "step": 141
    },
    {
      "epoch": 0.355,
      "grad_norm": 1.3551095724105835,
      "learning_rate": 1.2900000000000002e-05,
      "loss": 3.1719,
      "step": 142
    },
    {
      "epoch": 0.3575,
      "grad_norm": 0.7657787203788757,
      "learning_rate": 1.285e-05,
      "loss": 2.4577,
      "step": 143
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.8604536652565002,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 2.8134,
      "step": 144
    },
    {
      "epoch": 0.3625,
      "grad_norm": 1.6100467443466187,
      "learning_rate": 1.275e-05,
      "loss": 2.9813,
      "step": 145
    },
    {
      "epoch": 0.365,
      "grad_norm": 1.0728399753570557,
      "learning_rate": 1.27e-05,
      "loss": 2.9336,
      "step": 146
    },
    {
      "epoch": 0.3675,
      "grad_norm": 0.7545064687728882,
      "learning_rate": 1.2650000000000001e-05,
      "loss": 2.4588,
      "step": 147
    },
    {
      "epoch": 0.37,
      "grad_norm": 1.1295570135116577,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 2.1661,
      "step": 148
    },
    {
      "epoch": 0.3725,
      "grad_norm": 1.0526827573776245,
      "learning_rate": 1.255e-05,
      "loss": 2.6463,
      "step": 149
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.834685742855072,
      "learning_rate": 1.25e-05,
      "loss": 2.3916,
      "step": 150
    },
    {
      "epoch": 0.3775,
      "grad_norm": 0.6503292918205261,
      "learning_rate": 1.2450000000000003e-05,
      "loss": 2.3776,
      "step": 151
    },
    {
      "epoch": 0.38,
      "grad_norm": 1.1130701303482056,
      "learning_rate": 1.2400000000000002e-05,
      "loss": 2.1929,
      "step": 152
    },
    {
      "epoch": 0.3825,
      "grad_norm": 1.4437247514724731,
      "learning_rate": 1.2350000000000002e-05,
      "loss": 3.055,
      "step": 153
    },
    {
      "epoch": 0.385,
      "grad_norm": 1.0600138902664185,
      "learning_rate": 1.23e-05,
      "loss": 2.7314,
      "step": 154
    },
    {
      "epoch": 0.3875,
      "grad_norm": 0.8913452625274658,
      "learning_rate": 1.2250000000000001e-05,
      "loss": 2.519,
      "step": 155
    },
    {
      "epoch": 0.39,
      "grad_norm": 1.1115096807479858,
      "learning_rate": 1.22e-05,
      "loss": 2.2607,
      "step": 156
    },
    {
      "epoch": 0.3925,
      "grad_norm": 1.2785054445266724,
      "learning_rate": 1.2150000000000002e-05,
      "loss": 3.0773,
      "step": 157
    },
    {
      "epoch": 0.395,
      "grad_norm": 1.3286359310150146,
      "learning_rate": 1.2100000000000001e-05,
      "loss": 2.9653,
      "step": 158
    },
    {
      "epoch": 0.3975,
      "grad_norm": 1.0843842029571533,
      "learning_rate": 1.2050000000000002e-05,
      "loss": 2.5038,
      "step": 159
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.6999257206916809,
      "learning_rate": 1.2e-05,
      "loss": 2.2963,
      "step": 160
    },
    {
      "epoch": 0.4025,
      "grad_norm": 1.3845021724700928,
      "learning_rate": 1.195e-05,
      "loss": 2.0538,
      "step": 161
    },
    {
      "epoch": 0.405,
      "grad_norm": 0.8387379050254822,
      "learning_rate": 1.1900000000000001e-05,
      "loss": 2.6954,
      "step": 162
    },
    {
      "epoch": 0.4075,
      "grad_norm": 1.5070502758026123,
      "learning_rate": 1.1850000000000002e-05,
      "loss": 3.4584,
      "step": 163
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.3833943605422974,
      "learning_rate": 1.18e-05,
      "loss": 2.603,
      "step": 164
    },
    {
      "epoch": 0.4125,
      "grad_norm": 1.2640782594680786,
      "learning_rate": 1.1750000000000001e-05,
      "loss": 2.6054,
      "step": 165
    },
    {
      "epoch": 0.415,
      "grad_norm": 1.2189885377883911,
      "learning_rate": 1.17e-05,
      "loss": 2.5489,
      "step": 166
    },
    {
      "epoch": 0.4175,
      "grad_norm": 0.9442604184150696,
      "learning_rate": 1.1650000000000002e-05,
      "loss": 2.9024,
      "step": 167
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.966208815574646,
      "learning_rate": 1.16e-05,
      "loss": 2.6491,
      "step": 168
    },
    {
      "epoch": 0.4225,
      "grad_norm": 1.126082181930542,
      "learning_rate": 1.1550000000000001e-05,
      "loss": 2.789,
      "step": 169
    },
    {
      "epoch": 0.425,
      "grad_norm": 0.9639744162559509,
      "learning_rate": 1.15e-05,
      "loss": 2.9103,
      "step": 170
    },
    {
      "epoch": 0.4275,
      "grad_norm": 1.8708701133728027,
      "learning_rate": 1.145e-05,
      "loss": 3.8013,
      "step": 171
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.8368299603462219,
      "learning_rate": 1.14e-05,
      "loss": 2.8514,
      "step": 172
    },
    {
      "epoch": 0.4325,
      "grad_norm": 0.9027671813964844,
      "learning_rate": 1.1350000000000001e-05,
      "loss": 2.8475,
      "step": 173
    },
    {
      "epoch": 0.435,
      "grad_norm": 0.7692644596099854,
      "learning_rate": 1.13e-05,
      "loss": 2.4503,
      "step": 174
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.9505887627601624,
      "learning_rate": 1.125e-05,
      "loss": 2.3865,
      "step": 175
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.6154547333717346,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 2.2003,
      "step": 176
    },
    {
      "epoch": 0.4425,
      "grad_norm": 0.9452154040336609,
      "learning_rate": 1.1150000000000002e-05,
      "loss": 2.5568,
      "step": 177
    },
    {
      "epoch": 0.445,
      "grad_norm": 0.932019054889679,
      "learning_rate": 1.1100000000000002e-05,
      "loss": 2.7934,
      "step": 178
    },
    {
      "epoch": 0.4475,
      "grad_norm": 0.8905855417251587,
      "learning_rate": 1.1050000000000001e-05,
      "loss": 2.5882,
      "step": 179
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.787998378276825,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 2.3595,
      "step": 180
    },
    {
      "epoch": 0.4525,
      "grad_norm": 1.048705816268921,
      "learning_rate": 1.095e-05,
      "loss": 2.344,
      "step": 181
    },
    {
      "epoch": 0.455,
      "grad_norm": 1.480038046836853,
      "learning_rate": 1.0900000000000002e-05,
      "loss": 2.6574,
      "step": 182
    },
    {
      "epoch": 0.4575,
      "grad_norm": 1.0186829566955566,
      "learning_rate": 1.0850000000000001e-05,
      "loss": 2.5634,
      "step": 183
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.0724053382873535,
      "learning_rate": 1.0800000000000002e-05,
      "loss": 2.3537,
      "step": 184
    },
    {
      "epoch": 0.4625,
      "grad_norm": 1.1065270900726318,
      "learning_rate": 1.075e-05,
      "loss": 2.3363,
      "step": 185
    },
    {
      "epoch": 0.465,
      "grad_norm": 1.0963391065597534,
      "learning_rate": 1.0700000000000001e-05,
      "loss": 2.8301,
      "step": 186
    },
    {
      "epoch": 0.4675,
      "grad_norm": 1.0181528329849243,
      "learning_rate": 1.065e-05,
      "loss": 2.3469,
      "step": 187
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.9789475202560425,
      "learning_rate": 1.0600000000000002e-05,
      "loss": 2.4968,
      "step": 188
    },
    {
      "epoch": 0.4725,
      "grad_norm": 0.9361099600791931,
      "learning_rate": 1.055e-05,
      "loss": 2.7079,
      "step": 189
    },
    {
      "epoch": 0.475,
      "grad_norm": 1.1060682535171509,
      "learning_rate": 1.0500000000000001e-05,
      "loss": 2.6673,
      "step": 190
    },
    {
      "epoch": 0.4775,
      "grad_norm": 0.7775200605392456,
      "learning_rate": 1.045e-05,
      "loss": 2.4824,
      "step": 191
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.3691951036453247,
      "learning_rate": 1.04e-05,
      "loss": 2.8986,
      "step": 192
    },
    {
      "epoch": 0.4825,
      "grad_norm": 1.13148033618927,
      "learning_rate": 1.0350000000000001e-05,
      "loss": 2.524,
      "step": 193
    },
    {
      "epoch": 0.485,
      "grad_norm": 1.0336346626281738,
      "learning_rate": 1.0300000000000001e-05,
      "loss": 2.5613,
      "step": 194
    },
    {
      "epoch": 0.4875,
      "grad_norm": 1.716963768005371,
      "learning_rate": 1.025e-05,
      "loss": 3.1095,
      "step": 195
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.8384996056556702,
      "learning_rate": 1.02e-05,
      "loss": 3.0394,
      "step": 196
    },
    {
      "epoch": 0.4925,
      "grad_norm": 1.4971530437469482,
      "learning_rate": 1.015e-05,
      "loss": 3.0766,
      "step": 197
    },
    {
      "epoch": 0.495,
      "grad_norm": 1.282583236694336,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 2.016,
      "step": 198
    },
    {
      "epoch": 0.4975,
      "grad_norm": 0.7084432244300842,
      "learning_rate": 1.005e-05,
      "loss": 2.4533,
      "step": 199
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.0756547451019287,
      "learning_rate": 1e-05,
      "loss": 2.8562,
      "step": 200
    },
    {
      "epoch": 0.5025,
      "grad_norm": 1.582619071006775,
      "learning_rate": 9.950000000000001e-06,
      "loss": 3.0876,
      "step": 201
    },
    {
      "epoch": 0.505,
      "grad_norm": 1.0258393287658691,
      "learning_rate": 9.9e-06,
      "loss": 2.4419,
      "step": 202
    },
    {
      "epoch": 0.5075,
      "grad_norm": 1.2243763208389282,
      "learning_rate": 9.85e-06,
      "loss": 2.6982,
      "step": 203
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.9121052622795105,
      "learning_rate": 9.800000000000001e-06,
      "loss": 2.7505,
      "step": 204
    },
    {
      "epoch": 0.5125,
      "grad_norm": 1.0946589708328247,
      "learning_rate": 9.75e-06,
      "loss": 2.5225,
      "step": 205
    },
    {
      "epoch": 0.515,
      "grad_norm": 1.5404136180877686,
      "learning_rate": 9.7e-06,
      "loss": 2.7569,
      "step": 206
    },
    {
      "epoch": 0.5175,
      "grad_norm": 2.3309805393218994,
      "learning_rate": 9.65e-06,
      "loss": 3.2281,
      "step": 207
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.3618017435073853,
      "learning_rate": 9.600000000000001e-06,
      "loss": 2.4756,
      "step": 208
    },
    {
      "epoch": 0.5225,
      "grad_norm": 1.309582233428955,
      "learning_rate": 9.55e-06,
      "loss": 2.9163,
      "step": 209
    },
    {
      "epoch": 0.525,
      "grad_norm": 1.01054048538208,
      "learning_rate": 9.5e-06,
      "loss": 2.5883,
      "step": 210
    },
    {
      "epoch": 0.5275,
      "grad_norm": 1.077317476272583,
      "learning_rate": 9.450000000000001e-06,
      "loss": 2.7063,
      "step": 211
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.1660407781600952,
      "learning_rate": 9.4e-06,
      "loss": 2.2638,
      "step": 212
    },
    {
      "epoch": 0.5325,
      "grad_norm": 1.070369839668274,
      "learning_rate": 9.350000000000002e-06,
      "loss": 2.5768,
      "step": 213
    },
    {
      "epoch": 0.535,
      "grad_norm": 1.653826355934143,
      "learning_rate": 9.3e-06,
      "loss": 3.2656,
      "step": 214
    },
    {
      "epoch": 0.5375,
      "grad_norm": 1.7478209733963013,
      "learning_rate": 9.250000000000001e-06,
      "loss": 3.1918,
      "step": 215
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.5557425022125244,
      "learning_rate": 9.200000000000002e-06,
      "loss": 3.317,
      "step": 216
    },
    {
      "epoch": 0.5425,
      "grad_norm": 0.7344517707824707,
      "learning_rate": 9.15e-06,
      "loss": 2.444,
      "step": 217
    },
    {
      "epoch": 0.545,
      "grad_norm": 1.3143254518508911,
      "learning_rate": 9.100000000000001e-06,
      "loss": 2.5553,
      "step": 218
    },
    {
      "epoch": 0.5475,
      "grad_norm": 0.7797951698303223,
      "learning_rate": 9.050000000000001e-06,
      "loss": 2.1852,
      "step": 219
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.4703871011734009,
      "learning_rate": 9e-06,
      "loss": 2.4204,
      "step": 220
    },
    {
      "epoch": 0.5525,
      "grad_norm": 1.1021125316619873,
      "learning_rate": 8.95e-06,
      "loss": 3.0355,
      "step": 221
    },
    {
      "epoch": 0.555,
      "grad_norm": 1.8875423669815063,
      "learning_rate": 8.900000000000001e-06,
      "loss": 2.5834,
      "step": 222
    },
    {
      "epoch": 0.5575,
      "grad_norm": 1.5867810249328613,
      "learning_rate": 8.85e-06,
      "loss": 2.9359,
      "step": 223
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.0237711668014526,
      "learning_rate": 8.8e-06,
      "loss": 2.7608,
      "step": 224
    },
    {
      "epoch": 0.5625,
      "grad_norm": 0.7836809754371643,
      "learning_rate": 8.750000000000001e-06,
      "loss": 2.5303,
      "step": 225
    },
    {
      "epoch": 0.565,
      "grad_norm": 0.8862155079841614,
      "learning_rate": 8.700000000000001e-06,
      "loss": 2.7468,
      "step": 226
    },
    {
      "epoch": 0.5675,
      "grad_norm": 1.3247358798980713,
      "learning_rate": 8.65e-06,
      "loss": 2.501,
      "step": 227
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.2541866302490234,
      "learning_rate": 8.6e-06,
      "loss": 2.5587,
      "step": 228
    },
    {
      "epoch": 0.5725,
      "grad_norm": 0.7479645013809204,
      "learning_rate": 8.550000000000001e-06,
      "loss": 2.2071,
      "step": 229
    },
    {
      "epoch": 0.575,
      "grad_norm": 1.4009301662445068,
      "learning_rate": 8.5e-06,
      "loss": 2.9907,
      "step": 230
    },
    {
      "epoch": 0.5775,
      "grad_norm": 1.2885963916778564,
      "learning_rate": 8.45e-06,
      "loss": 2.4376,
      "step": 231
    },
    {
      "epoch": 0.58,
      "grad_norm": 1.4628698825836182,
      "learning_rate": 8.400000000000001e-06,
      "loss": 2.378,
      "step": 232
    },
    {
      "epoch": 0.5825,
      "grad_norm": 1.5401051044464111,
      "learning_rate": 8.35e-06,
      "loss": 2.4052,
      "step": 233
    },
    {
      "epoch": 0.585,
      "grad_norm": 1.3357149362564087,
      "learning_rate": 8.3e-06,
      "loss": 2.1,
      "step": 234
    },
    {
      "epoch": 0.5875,
      "grad_norm": 0.828890323638916,
      "learning_rate": 8.25e-06,
      "loss": 2.1579,
      "step": 235
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.4550373554229736,
      "learning_rate": 8.2e-06,
      "loss": 3.0067,
      "step": 236
    },
    {
      "epoch": 0.5925,
      "grad_norm": 1.0677258968353271,
      "learning_rate": 8.15e-06,
      "loss": 2.7238,
      "step": 237
    },
    {
      "epoch": 0.595,
      "grad_norm": 0.9987130761146545,
      "learning_rate": 8.1e-06,
      "loss": 2.6472,
      "step": 238
    },
    {
      "epoch": 0.5975,
      "grad_norm": 1.0116266012191772,
      "learning_rate": 8.050000000000001e-06,
      "loss": 2.806,
      "step": 239
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.281691312789917,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.7574,
      "step": 240
    },
    {
      "epoch": 0.6025,
      "grad_norm": 1.1807749271392822,
      "learning_rate": 7.950000000000002e-06,
      "loss": 2.2562,
      "step": 241
    },
    {
      "epoch": 0.605,
      "grad_norm": 0.8675217628479004,
      "learning_rate": 7.9e-06,
      "loss": 2.5751,
      "step": 242
    },
    {
      "epoch": 0.6075,
      "grad_norm": 1.2328344583511353,
      "learning_rate": 7.850000000000001e-06,
      "loss": 2.753,
      "step": 243
    },
    {
      "epoch": 0.61,
      "grad_norm": 2.0627636909484863,
      "learning_rate": 7.800000000000002e-06,
      "loss": 2.7131,
      "step": 244
    },
    {
      "epoch": 0.6125,
      "grad_norm": 1.6751055717468262,
      "learning_rate": 7.75e-06,
      "loss": 3.2299,
      "step": 245
    },
    {
      "epoch": 0.615,
      "grad_norm": 0.7668905258178711,
      "learning_rate": 7.7e-06,
      "loss": 2.7974,
      "step": 246
    },
    {
      "epoch": 0.6175,
      "grad_norm": 1.6743037700653076,
      "learning_rate": 7.650000000000001e-06,
      "loss": 2.2918,
      "step": 247
    },
    {
      "epoch": 0.62,
      "grad_norm": 1.9343725442886353,
      "learning_rate": 7.600000000000001e-06,
      "loss": 2.9281,
      "step": 248
    },
    {
      "epoch": 0.6225,
      "grad_norm": 0.9057416319847107,
      "learning_rate": 7.5500000000000006e-06,
      "loss": 2.8679,
      "step": 249
    },
    {
      "epoch": 0.625,
      "grad_norm": 1.1523922681808472,
      "learning_rate": 7.500000000000001e-06,
      "loss": 2.5185,
      "step": 250
    },
    {
      "epoch": 0.6275,
      "grad_norm": 1.1341513395309448,
      "learning_rate": 7.450000000000001e-06,
      "loss": 2.0536,
      "step": 251
    },
    {
      "epoch": 0.63,
      "grad_norm": 2.606443405151367,
      "learning_rate": 7.4e-06,
      "loss": 3.3494,
      "step": 252
    },
    {
      "epoch": 0.6325,
      "grad_norm": 0.7551514506340027,
      "learning_rate": 7.350000000000001e-06,
      "loss": 2.4611,
      "step": 253
    },
    {
      "epoch": 0.635,
      "grad_norm": 1.4550762176513672,
      "learning_rate": 7.3e-06,
      "loss": 2.6206,
      "step": 254
    },
    {
      "epoch": 0.6375,
      "grad_norm": 1.5378979444503784,
      "learning_rate": 7.25e-06,
      "loss": 2.9399,
      "step": 255
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.8729074001312256,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 2.8517,
      "step": 256
    },
    {
      "epoch": 0.6425,
      "grad_norm": 0.8619707822799683,
      "learning_rate": 7.15e-06,
      "loss": 2.7855,
      "step": 257
    },
    {
      "epoch": 0.645,
      "grad_norm": 1.3895457983016968,
      "learning_rate": 7.100000000000001e-06,
      "loss": 2.8384,
      "step": 258
    },
    {
      "epoch": 0.6475,
      "grad_norm": 1.3270301818847656,
      "learning_rate": 7.05e-06,
      "loss": 2.421,
      "step": 259
    },
    {
      "epoch": 0.65,
      "grad_norm": 1.5464551448822021,
      "learning_rate": 7e-06,
      "loss": 2.7851,
      "step": 260
    },
    {
      "epoch": 0.6525,
      "grad_norm": 0.8114046454429626,
      "learning_rate": 6.95e-06,
      "loss": 2.3022,
      "step": 261
    },
    {
      "epoch": 0.655,
      "grad_norm": 1.6738479137420654,
      "learning_rate": 6.9e-06,
      "loss": 2.8703,
      "step": 262
    },
    {
      "epoch": 0.6575,
      "grad_norm": 1.7005109786987305,
      "learning_rate": 6.850000000000001e-06,
      "loss": 2.7839,
      "step": 263
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.8630906939506531,
      "learning_rate": 6.800000000000001e-06,
      "loss": 2.9775,
      "step": 264
    },
    {
      "epoch": 0.6625,
      "grad_norm": 1.465364694595337,
      "learning_rate": 6.750000000000001e-06,
      "loss": 2.7382,
      "step": 265
    },
    {
      "epoch": 0.665,
      "grad_norm": 1.5297225713729858,
      "learning_rate": 6.700000000000001e-06,
      "loss": 2.4168,
      "step": 266
    },
    {
      "epoch": 0.6675,
      "grad_norm": 2.0528006553649902,
      "learning_rate": 6.650000000000001e-06,
      "loss": 3.1659,
      "step": 267
    },
    {
      "epoch": 0.67,
      "grad_norm": 1.2365155220031738,
      "learning_rate": 6.600000000000001e-06,
      "loss": 2.2999,
      "step": 268
    },
    {
      "epoch": 0.6725,
      "grad_norm": 1.0112578868865967,
      "learning_rate": 6.550000000000001e-06,
      "loss": 2.4545,
      "step": 269
    },
    {
      "epoch": 0.675,
      "grad_norm": 1.8111435174942017,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 2.4034,
      "step": 270
    },
    {
      "epoch": 0.6775,
      "grad_norm": 1.0683218240737915,
      "learning_rate": 6.450000000000001e-06,
      "loss": 2.5293,
      "step": 271
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.8343501687049866,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 2.2964,
      "step": 272
    },
    {
      "epoch": 0.6825,
      "grad_norm": 0.7243903279304504,
      "learning_rate": 6.35e-06,
      "loss": 2.7022,
      "step": 273
    },
    {
      "epoch": 0.685,
      "grad_norm": 0.7344633936882019,
      "learning_rate": 6.300000000000001e-06,
      "loss": 2.657,
      "step": 274
    },
    {
      "epoch": 0.6875,
      "grad_norm": 0.8676360249519348,
      "learning_rate": 6.25e-06,
      "loss": 2.401,
      "step": 275
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.8793882131576538,
      "learning_rate": 6.200000000000001e-06,
      "loss": 2.4567,
      "step": 276
    },
    {
      "epoch": 0.6925,
      "grad_norm": 1.3876687288284302,
      "learning_rate": 6.15e-06,
      "loss": 2.4355,
      "step": 277
    },
    {
      "epoch": 0.695,
      "grad_norm": 1.6055662631988525,
      "learning_rate": 6.1e-06,
      "loss": 2.813,
      "step": 278
    },
    {
      "epoch": 0.6975,
      "grad_norm": 1.2520968914031982,
      "learning_rate": 6.0500000000000005e-06,
      "loss": 2.9245,
      "step": 279
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.8885823488235474,
      "learning_rate": 6e-06,
      "loss": 2.6111,
      "step": 280
    },
    {
      "epoch": 0.7025,
      "grad_norm": 1.6512576341629028,
      "learning_rate": 5.950000000000001e-06,
      "loss": 2.9193,
      "step": 281
    },
    {
      "epoch": 0.705,
      "grad_norm": 0.7407610416412354,
      "learning_rate": 5.9e-06,
      "loss": 2.1398,
      "step": 282
    },
    {
      "epoch": 0.7075,
      "grad_norm": 2.1687231063842773,
      "learning_rate": 5.85e-06,
      "loss": 2.9846,
      "step": 283
    },
    {
      "epoch": 0.71,
      "grad_norm": 2.4894940853118896,
      "learning_rate": 5.8e-06,
      "loss": 3.2657,
      "step": 284
    },
    {
      "epoch": 0.7125,
      "grad_norm": 0.9962525367736816,
      "learning_rate": 5.75e-06,
      "loss": 2.5076,
      "step": 285
    },
    {
      "epoch": 0.715,
      "grad_norm": 3.0593910217285156,
      "learning_rate": 5.7e-06,
      "loss": 3.4797,
      "step": 286
    },
    {
      "epoch": 0.7175,
      "grad_norm": 1.8267052173614502,
      "learning_rate": 5.65e-06,
      "loss": 3.0976,
      "step": 287
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.4683566093444824,
      "learning_rate": 5.600000000000001e-06,
      "loss": 2.8335,
      "step": 288
    },
    {
      "epoch": 0.7225,
      "grad_norm": 1.1253299713134766,
      "learning_rate": 5.550000000000001e-06,
      "loss": 2.6241,
      "step": 289
    },
    {
      "epoch": 0.725,
      "grad_norm": 0.9860060214996338,
      "learning_rate": 5.500000000000001e-06,
      "loss": 2.4915,
      "step": 290
    },
    {
      "epoch": 0.7275,
      "grad_norm": 1.5636118650436401,
      "learning_rate": 5.450000000000001e-06,
      "loss": 2.7474,
      "step": 291
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.8544251918792725,
      "learning_rate": 5.400000000000001e-06,
      "loss": 2.5836,
      "step": 292
    },
    {
      "epoch": 0.7325,
      "grad_norm": 1.4845181703567505,
      "learning_rate": 5.3500000000000004e-06,
      "loss": 2.5001,
      "step": 293
    },
    {
      "epoch": 0.735,
      "grad_norm": 0.9682713747024536,
      "learning_rate": 5.300000000000001e-06,
      "loss": 2.3704,
      "step": 294
    },
    {
      "epoch": 0.7375,
      "grad_norm": 1.139123558998108,
      "learning_rate": 5.2500000000000006e-06,
      "loss": 2.498,
      "step": 295
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.9582972526550293,
      "learning_rate": 5.2e-06,
      "loss": 2.8401,
      "step": 296
    },
    {
      "epoch": 0.7425,
      "grad_norm": 1.2214773893356323,
      "learning_rate": 5.150000000000001e-06,
      "loss": 2.4964,
      "step": 297
    },
    {
      "epoch": 0.745,
      "grad_norm": 1.5916988849639893,
      "learning_rate": 5.1e-06,
      "loss": 2.789,
      "step": 298
    },
    {
      "epoch": 0.7475,
      "grad_norm": 1.3175058364868164,
      "learning_rate": 5.050000000000001e-06,
      "loss": 2.2842,
      "step": 299
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.5208394527435303,
      "learning_rate": 5e-06,
      "loss": 2.6268,
      "step": 300
    },
    {
      "epoch": 0.7525,
      "grad_norm": 1.6970012187957764,
      "learning_rate": 4.95e-06,
      "loss": 3.0989,
      "step": 301
    },
    {
      "epoch": 0.755,
      "grad_norm": 1.0863839387893677,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 2.5363,
      "step": 302
    },
    {
      "epoch": 0.7575,
      "grad_norm": 1.4228333234786987,
      "learning_rate": 4.85e-06,
      "loss": 2.2384,
      "step": 303
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.1009355783462524,
      "learning_rate": 4.800000000000001e-06,
      "loss": 2.5118,
      "step": 304
    },
    {
      "epoch": 0.7625,
      "grad_norm": 1.626090168952942,
      "learning_rate": 4.75e-06,
      "loss": 3.0346,
      "step": 305
    },
    {
      "epoch": 0.765,
      "grad_norm": 1.7524985074996948,
      "learning_rate": 4.7e-06,
      "loss": 2.866,
      "step": 306
    },
    {
      "epoch": 0.7675,
      "grad_norm": 0.9619413614273071,
      "learning_rate": 4.65e-06,
      "loss": 2.7082,
      "step": 307
    },
    {
      "epoch": 0.77,
      "grad_norm": 1.0346368551254272,
      "learning_rate": 4.600000000000001e-06,
      "loss": 2.5831,
      "step": 308
    },
    {
      "epoch": 0.7725,
      "grad_norm": 1.3571815490722656,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 2.8175,
      "step": 309
    },
    {
      "epoch": 0.775,
      "grad_norm": 0.9211217761039734,
      "learning_rate": 4.5e-06,
      "loss": 2.2162,
      "step": 310
    },
    {
      "epoch": 0.7775,
      "grad_norm": 0.9217227101325989,
      "learning_rate": 4.450000000000001e-06,
      "loss": 2.5447,
      "step": 311
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.4442232847213745,
      "learning_rate": 4.4e-06,
      "loss": 2.5516,
      "step": 312
    },
    {
      "epoch": 0.7825,
      "grad_norm": 2.173661470413208,
      "learning_rate": 4.350000000000001e-06,
      "loss": 2.8237,
      "step": 313
    },
    {
      "epoch": 0.785,
      "grad_norm": 1.0328022241592407,
      "learning_rate": 4.3e-06,
      "loss": 2.5789,
      "step": 314
    },
    {
      "epoch": 0.7875,
      "grad_norm": 1.6845656633377075,
      "learning_rate": 4.25e-06,
      "loss": 2.7861,
      "step": 315
    },
    {
      "epoch": 0.79,
      "grad_norm": 2.003690242767334,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 2.8247,
      "step": 316
    },
    {
      "epoch": 0.7925,
      "grad_norm": 0.9073178172111511,
      "learning_rate": 4.15e-06,
      "loss": 2.0476,
      "step": 317
    },
    {
      "epoch": 0.795,
      "grad_norm": 1.2052966356277466,
      "learning_rate": 4.1e-06,
      "loss": 2.577,
      "step": 318
    },
    {
      "epoch": 0.7975,
      "grad_norm": 1.3335316181182861,
      "learning_rate": 4.05e-06,
      "loss": 2.871,
      "step": 319
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.2898180484771729,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.7909,
      "step": 320
    },
    {
      "epoch": 0.8025,
      "grad_norm": 0.8960414528846741,
      "learning_rate": 3.95e-06,
      "loss": 2.4136,
      "step": 321
    },
    {
      "epoch": 0.805,
      "grad_norm": 1.0490525960922241,
      "learning_rate": 3.900000000000001e-06,
      "loss": 2.1799,
      "step": 322
    },
    {
      "epoch": 0.8075,
      "grad_norm": 1.658100962638855,
      "learning_rate": 3.85e-06,
      "loss": 2.7796,
      "step": 323
    },
    {
      "epoch": 0.81,
      "grad_norm": 1.0821839570999146,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 2.7519,
      "step": 324
    },
    {
      "epoch": 0.8125,
      "grad_norm": 1.4786803722381592,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 2.7704,
      "step": 325
    },
    {
      "epoch": 0.815,
      "grad_norm": 1.3606433868408203,
      "learning_rate": 3.7e-06,
      "loss": 2.7433,
      "step": 326
    },
    {
      "epoch": 0.8175,
      "grad_norm": 1.033447265625,
      "learning_rate": 3.65e-06,
      "loss": 2.8468,
      "step": 327
    },
    {
      "epoch": 0.82,
      "grad_norm": 2.0277504920959473,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 3.0979,
      "step": 328
    },
    {
      "epoch": 0.8225,
      "grad_norm": 1.764878749847412,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 2.6579,
      "step": 329
    },
    {
      "epoch": 0.825,
      "grad_norm": 1.2304050922393799,
      "learning_rate": 3.5e-06,
      "loss": 3.1515,
      "step": 330
    },
    {
      "epoch": 0.8275,
      "grad_norm": 1.0954989194869995,
      "learning_rate": 3.45e-06,
      "loss": 2.4466,
      "step": 331
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.0179721117019653,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 2.6192,
      "step": 332
    },
    {
      "epoch": 0.8325,
      "grad_norm": 2.0626888275146484,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 3.1367,
      "step": 333
    },
    {
      "epoch": 0.835,
      "grad_norm": 1.400158405303955,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 2.3225,
      "step": 334
    },
    {
      "epoch": 0.8375,
      "grad_norm": 1.2611231803894043,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 2.6106,
      "step": 335
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.3621522188186646,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 2.3755,
      "step": 336
    },
    {
      "epoch": 0.8425,
      "grad_norm": 1.694920539855957,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 3.0504,
      "step": 337
    },
    {
      "epoch": 0.845,
      "grad_norm": 1.3278639316558838,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 2.7587,
      "step": 338
    },
    {
      "epoch": 0.8475,
      "grad_norm": 1.1720857620239258,
      "learning_rate": 3.05e-06,
      "loss": 2.4512,
      "step": 339
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.203119158744812,
      "learning_rate": 3e-06,
      "loss": 2.5373,
      "step": 340
    },
    {
      "epoch": 0.8525,
      "grad_norm": 1.8672972917556763,
      "learning_rate": 2.95e-06,
      "loss": 2.8789,
      "step": 341
    },
    {
      "epoch": 0.855,
      "grad_norm": 1.5473331212997437,
      "learning_rate": 2.9e-06,
      "loss": 2.511,
      "step": 342
    },
    {
      "epoch": 0.8575,
      "grad_norm": 1.230299711227417,
      "learning_rate": 2.85e-06,
      "loss": 2.4508,
      "step": 343
    },
    {
      "epoch": 0.86,
      "grad_norm": 2.5387115478515625,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 3.2151,
      "step": 344
    },
    {
      "epoch": 0.8625,
      "grad_norm": 0.8814523816108704,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 2.5838,
      "step": 345
    },
    {
      "epoch": 0.865,
      "grad_norm": 1.4973145723342896,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 2.529,
      "step": 346
    },
    {
      "epoch": 0.8675,
      "grad_norm": 0.9681499004364014,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 2.5989,
      "step": 347
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.991982638835907,
      "learning_rate": 2.6e-06,
      "loss": 2.7449,
      "step": 348
    },
    {
      "epoch": 0.8725,
      "grad_norm": 1.0481587648391724,
      "learning_rate": 2.55e-06,
      "loss": 2.4512,
      "step": 349
    },
    {
      "epoch": 0.875,
      "grad_norm": 1.8113739490509033,
      "learning_rate": 2.5e-06,
      "loss": 2.6997,
      "step": 350
    },
    {
      "epoch": 0.8775,
      "grad_norm": 1.1605638265609741,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 2.4487,
      "step": 351
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.8704707622528076,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 2.5544,
      "step": 352
    },
    {
      "epoch": 0.8825,
      "grad_norm": 1.5997426509857178,
      "learning_rate": 2.35e-06,
      "loss": 2.079,
      "step": 353
    },
    {
      "epoch": 0.885,
      "grad_norm": 0.9046956300735474,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 2.6991,
      "step": 354
    },
    {
      "epoch": 0.8875,
      "grad_norm": 0.8987280130386353,
      "learning_rate": 2.25e-06,
      "loss": 2.3281,
      "step": 355
    },
    {
      "epoch": 0.89,
      "grad_norm": 2.1055095195770264,
      "learning_rate": 2.2e-06,
      "loss": 2.942,
      "step": 356
    },
    {
      "epoch": 0.8925,
      "grad_norm": 1.0179944038391113,
      "learning_rate": 2.15e-06,
      "loss": 2.6226,
      "step": 357
    },
    {
      "epoch": 0.895,
      "grad_norm": 0.8908201456069946,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 2.5437,
      "step": 358
    },
    {
      "epoch": 0.8975,
      "grad_norm": 0.9919204711914062,
      "learning_rate": 2.05e-06,
      "loss": 2.6167,
      "step": 359
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.3533128499984741,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.7656,
      "step": 360
    },
    {
      "epoch": 0.9025,
      "grad_norm": 1.5116089582443237,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 2.7985,
      "step": 361
    },
    {
      "epoch": 0.905,
      "grad_norm": 1.1233296394348145,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 2.4902,
      "step": 362
    },
    {
      "epoch": 0.9075,
      "grad_norm": 1.3624063730239868,
      "learning_rate": 1.85e-06,
      "loss": 2.4763,
      "step": 363
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.012367606163025,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 2.6233,
      "step": 364
    },
    {
      "epoch": 0.9125,
      "grad_norm": 1.2850728034973145,
      "learning_rate": 1.75e-06,
      "loss": 2.6726,
      "step": 365
    },
    {
      "epoch": 0.915,
      "grad_norm": 1.139714002609253,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 2.4277,
      "step": 366
    },
    {
      "epoch": 0.9175,
      "grad_norm": 1.702054500579834,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 2.784,
      "step": 367
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.5244337320327759,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 2.4983,
      "step": 368
    },
    {
      "epoch": 0.9225,
      "grad_norm": 0.990729808807373,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 2.6408,
      "step": 369
    },
    {
      "epoch": 0.925,
      "grad_norm": 1.6035521030426025,
      "learning_rate": 1.5e-06,
      "loss": 2.7656,
      "step": 370
    },
    {
      "epoch": 0.9275,
      "grad_norm": 1.727439045906067,
      "learning_rate": 1.45e-06,
      "loss": 2.2137,
      "step": 371
    },
    {
      "epoch": 0.93,
      "grad_norm": 1.45046865940094,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 2.4762,
      "step": 372
    },
    {
      "epoch": 0.9325,
      "grad_norm": 1.8131942749023438,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 2.9507,
      "step": 373
    },
    {
      "epoch": 0.935,
      "grad_norm": 1.0772196054458618,
      "learning_rate": 1.3e-06,
      "loss": 2.2929,
      "step": 374
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.9250187277793884,
      "learning_rate": 1.25e-06,
      "loss": 2.5877,
      "step": 375
    },
    {
      "epoch": 0.94,
      "grad_norm": 1.2243655920028687,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 2.4348,
      "step": 376
    },
    {
      "epoch": 0.9425,
      "grad_norm": 1.745672345161438,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 2.9214,
      "step": 377
    },
    {
      "epoch": 0.945,
      "grad_norm": 1.6701159477233887,
      "learning_rate": 1.1e-06,
      "loss": 2.6747,
      "step": 378
    },
    {
      "epoch": 0.9475,
      "grad_norm": 1.5345369577407837,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 3.255,
      "step": 379
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.5753200054168701,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 2.3063,
      "step": 380
    },
    {
      "epoch": 0.9525,
      "grad_norm": 0.9224236011505127,
      "learning_rate": 9.500000000000001e-07,
      "loss": 2.8304,
      "step": 381
    },
    {
      "epoch": 0.955,
      "grad_norm": 2.8468313217163086,
      "learning_rate": 9.000000000000001e-07,
      "loss": 2.9737,
      "step": 382
    },
    {
      "epoch": 0.9575,
      "grad_norm": 1.5169612169265747,
      "learning_rate": 8.500000000000001e-07,
      "loss": 2.5457,
      "step": 383
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.4313298463821411,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.7448,
      "step": 384
    },
    {
      "epoch": 0.9625,
      "grad_norm": 0.887591540813446,
      "learning_rate": 7.5e-07,
      "loss": 2.7407,
      "step": 385
    },
    {
      "epoch": 0.965,
      "grad_norm": 1.2013964653015137,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.8123,
      "step": 386
    },
    {
      "epoch": 0.9675,
      "grad_norm": 1.089685082435608,
      "learning_rate": 6.5e-07,
      "loss": 2.735,
      "step": 387
    },
    {
      "epoch": 0.97,
      "grad_norm": 1.808695673942566,
      "learning_rate": 6.000000000000001e-07,
      "loss": 3.1463,
      "step": 388
    },
    {
      "epoch": 0.9725,
      "grad_norm": 0.9855251908302307,
      "learning_rate": 5.5e-07,
      "loss": 2.662,
      "step": 389
    },
    {
      "epoch": 0.975,
      "grad_norm": 0.8635110259056091,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.6258,
      "step": 390
    },
    {
      "epoch": 0.9775,
      "grad_norm": 0.9996857047080994,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.4871,
      "step": 391
    },
    {
      "epoch": 0.98,
      "grad_norm": 1.132926344871521,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.3769,
      "step": 392
    },
    {
      "epoch": 0.9825,
      "grad_norm": 1.0772877931594849,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.7185,
      "step": 393
    },
    {
      "epoch": 0.985,
      "grad_norm": 0.8307743668556213,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.357,
      "step": 394
    },
    {
      "epoch": 0.9875,
      "grad_norm": 0.8545295000076294,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.4623,
      "step": 395
    },
    {
      "epoch": 0.99,
      "grad_norm": 1.0141770839691162,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.6182,
      "step": 396
    },
    {
      "epoch": 0.9925,
      "grad_norm": 1.289717435836792,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.5772,
      "step": 397
    },
    {
      "epoch": 0.995,
      "grad_norm": 1.5395151376724243,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.6248,
      "step": 398
    },
    {
      "epoch": 0.9975,
      "grad_norm": 1.0455236434936523,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.5632,
      "step": 399
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.0527230501174927,
      "learning_rate": 0.0,
      "loss": 2.5029,
      "step": 400
    },
    {
      "epoch": 1.0,
      "eval_runtime": 66.9763,
      "eval_samples_per_second": 2.986,
      "eval_steps_per_second": 1.493,
      "step": 400
    }
  ],
  "logging_steps": 1,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}