{
  "best_metric": 1.4878435134887695,
  "best_model_checkpoint": "lora_lr_pad/mistralai/Mistral-7B-Instruct-v0.2/unaligned/checkpoint-500",
  "epoch": 0.655150351887396,
  "eval_steps": 20,
  "global_step": 512,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012795905310300703,
      "grad_norm": 1.3359375,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.2562,
      "step": 1
    },
    {
      "epoch": 0.0025591810620601407,
      "grad_norm": 1.3671875,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.152,
      "step": 2
    },
    {
      "epoch": 0.003838771593090211,
      "grad_norm": 1.2734375,
      "learning_rate": 6e-06,
      "loss": 3.101,
      "step": 3
    },
    {
      "epoch": 0.005118362124120281,
      "grad_norm": 1.421875,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.2665,
      "step": 4
    },
    {
      "epoch": 0.006397952655150352,
      "grad_norm": 1.375,
      "learning_rate": 1e-05,
      "loss": 3.2401,
      "step": 5
    },
    {
      "epoch": 0.007677543186180422,
      "grad_norm": 1.3046875,
      "learning_rate": 1.2e-05,
      "loss": 3.1574,
      "step": 6
    },
    {
      "epoch": 0.008957133717210493,
      "grad_norm": 1.3515625,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 3.1197,
      "step": 7
    },
    {
      "epoch": 0.010236724248240563,
      "grad_norm": 1.4140625,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.2179,
      "step": 8
    },
    {
      "epoch": 0.011516314779270634,
      "grad_norm": 1.421875,
      "learning_rate": 1.8e-05,
      "loss": 3.2687,
      "step": 9
    },
    {
      "epoch": 0.012795905310300703,
      "grad_norm": 1.4609375,
      "learning_rate": 2e-05,
      "loss": 3.2973,
      "step": 10
    },
    {
      "epoch": 0.014075495841330775,
      "grad_norm": 1.3359375,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 3.1228,
      "step": 11
    },
    {
      "epoch": 0.015355086372360844,
      "grad_norm": 1.234375,
      "learning_rate": 2.4e-05,
      "loss": 3.0316,
      "step": 12
    },
    {
      "epoch": 0.016634676903390915,
      "grad_norm": 1.4765625,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 3.2293,
      "step": 13
    },
    {
      "epoch": 0.017914267434420986,
      "grad_norm": 1.4375,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 3.2405,
      "step": 14
    },
    {
      "epoch": 0.019193857965451054,
      "grad_norm": 1.453125,
      "learning_rate": 3e-05,
      "loss": 3.217,
      "step": 15
    },
    {
      "epoch": 0.020473448496481125,
      "grad_norm": 1.375,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 3.092,
      "step": 16
    },
    {
      "epoch": 0.021753039027511197,
      "grad_norm": 1.59375,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 3.2057,
      "step": 17
    },
    {
      "epoch": 0.023032629558541268,
      "grad_norm": 1.3984375,
      "learning_rate": 3.6e-05,
      "loss": 2.9932,
      "step": 18
    },
    {
      "epoch": 0.02431222008957134,
      "grad_norm": 1.546875,
      "learning_rate": 3.8e-05,
      "loss": 3.0673,
      "step": 19
    },
    {
      "epoch": 0.025591810620601407,
      "grad_norm": 1.5703125,
      "learning_rate": 4e-05,
      "loss": 2.9652,
      "step": 20
    },
    {
      "epoch": 0.025591810620601407,
      "eval_loss": 2.928436756134033,
      "eval_runtime": 103.8047,
      "eval_samples_per_second": 48.167,
      "eval_steps_per_second": 1.512,
      "step": 20
    },
    {
      "epoch": 0.026871401151631478,
      "grad_norm": 1.6875,
      "learning_rate": 4.2e-05,
      "loss": 2.9173,
      "step": 21
    },
    {
      "epoch": 0.02815099168266155,
      "grad_norm": 1.7890625,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.9455,
      "step": 22
    },
    {
      "epoch": 0.02943058221369162,
      "grad_norm": 1.7421875,
      "learning_rate": 4.600000000000001e-05,
      "loss": 2.909,
      "step": 23
    },
    {
      "epoch": 0.030710172744721688,
      "grad_norm": 1.7734375,
      "learning_rate": 4.8e-05,
      "loss": 2.8191,
      "step": 24
    },
    {
      "epoch": 0.03198976327575176,
      "grad_norm": 1.8515625,
      "learning_rate": 5e-05,
      "loss": 2.7853,
      "step": 25
    },
    {
      "epoch": 0.03326935380678183,
      "grad_norm": 1.7890625,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.7678,
      "step": 26
    },
    {
      "epoch": 0.0345489443378119,
      "grad_norm": 1.7890625,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 2.6028,
      "step": 27
    },
    {
      "epoch": 0.03582853486884197,
      "grad_norm": 1.8046875,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.6369,
      "step": 28
    },
    {
      "epoch": 0.037108125399872044,
      "grad_norm": 1.8984375,
      "learning_rate": 5.8e-05,
      "loss": 2.6158,
      "step": 29
    },
    {
      "epoch": 0.03838771593090211,
      "grad_norm": 1.59375,
      "learning_rate": 6e-05,
      "loss": 2.2824,
      "step": 30
    },
    {
      "epoch": 0.03966730646193218,
      "grad_norm": 1.6796875,
      "learning_rate": 6.2e-05,
      "loss": 2.4286,
      "step": 31
    },
    {
      "epoch": 0.04094689699296225,
      "grad_norm": 1.5625,
      "learning_rate": 6.400000000000001e-05,
      "loss": 2.2919,
      "step": 32
    },
    {
      "epoch": 0.04222648752399232,
      "grad_norm": 1.546875,
      "learning_rate": 6.6e-05,
      "loss": 2.2725,
      "step": 33
    },
    {
      "epoch": 0.04350607805502239,
      "grad_norm": 1.484375,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.202,
      "step": 34
    },
    {
      "epoch": 0.044785668586052464,
      "grad_norm": 1.375,
      "learning_rate": 7e-05,
      "loss": 2.1415,
      "step": 35
    },
    {
      "epoch": 0.046065259117082535,
      "grad_norm": 1.328125,
      "learning_rate": 7.2e-05,
      "loss": 2.0692,
      "step": 36
    },
    {
      "epoch": 0.04734484964811261,
      "grad_norm": 1.2734375,
      "learning_rate": 7.4e-05,
      "loss": 2.1186,
      "step": 37
    },
    {
      "epoch": 0.04862444017914268,
      "grad_norm": 1.046875,
      "learning_rate": 7.6e-05,
      "loss": 1.9482,
      "step": 38
    },
    {
      "epoch": 0.04990403071017274,
      "grad_norm": 0.88671875,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.8985,
      "step": 39
    },
    {
      "epoch": 0.05118362124120281,
      "grad_norm": 0.7421875,
      "learning_rate": 8e-05,
      "loss": 1.844,
      "step": 40
    },
    {
      "epoch": 0.05118362124120281,
      "eval_loss": 1.8063277006149292,
      "eval_runtime": 103.8793,
      "eval_samples_per_second": 48.133,
      "eval_steps_per_second": 1.511,
      "step": 40
    },
    {
      "epoch": 0.052463211772232884,
      "grad_norm": 0.6015625,
      "learning_rate": 8.2e-05,
      "loss": 1.8771,
      "step": 41
    },
    {
      "epoch": 0.053742802303262956,
      "grad_norm": 0.515625,
      "learning_rate": 8.4e-05,
      "loss": 1.7902,
      "step": 42
    },
    {
      "epoch": 0.05502239283429303,
      "grad_norm": 0.45703125,
      "learning_rate": 8.6e-05,
      "loss": 1.7946,
      "step": 43
    },
    {
      "epoch": 0.0563019833653231,
      "grad_norm": 0.458984375,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.751,
      "step": 44
    },
    {
      "epoch": 0.05758157389635317,
      "grad_norm": 0.52734375,
      "learning_rate": 9e-05,
      "loss": 1.7537,
      "step": 45
    },
    {
      "epoch": 0.05886116442738324,
      "grad_norm": 0.4765625,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.7619,
      "step": 46
    },
    {
      "epoch": 0.060140754958413305,
      "grad_norm": 0.5546875,
      "learning_rate": 9.4e-05,
      "loss": 1.7668,
      "step": 47
    },
    {
      "epoch": 0.061420345489443376,
      "grad_norm": 0.625,
      "learning_rate": 9.6e-05,
      "loss": 1.7556,
      "step": 48
    },
    {
      "epoch": 0.06269993602047345,
      "grad_norm": 0.75390625,
      "learning_rate": 9.8e-05,
      "loss": 1.7158,
      "step": 49
    },
    {
      "epoch": 0.06397952655150352,
      "grad_norm": 0.8828125,
      "learning_rate": 0.0001,
      "loss": 1.7301,
      "step": 50
    },
    {
      "epoch": 0.06525911708253358,
      "grad_norm": 0.9921875,
      "learning_rate": 0.00010200000000000001,
      "loss": 1.7979,
      "step": 51
    },
    {
      "epoch": 0.06653870761356366,
      "grad_norm": 0.84765625,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.6356,
      "step": 52
    },
    {
      "epoch": 0.06781829814459372,
      "grad_norm": 0.494140625,
      "learning_rate": 0.00010600000000000002,
      "loss": 1.6094,
      "step": 53
    },
    {
      "epoch": 0.0690978886756238,
      "grad_norm": 0.48046875,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.6467,
      "step": 54
    },
    {
      "epoch": 0.07037747920665387,
      "grad_norm": 0.44140625,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.576,
      "step": 55
    },
    {
      "epoch": 0.07165706973768395,
      "grad_norm": 0.384765625,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.6307,
      "step": 56
    },
    {
      "epoch": 0.07293666026871401,
      "grad_norm": 0.375,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.6133,
      "step": 57
    },
    {
      "epoch": 0.07421625079974409,
      "grad_norm": 0.33984375,
      "learning_rate": 0.000116,
      "loss": 1.6575,
      "step": 58
    },
    {
      "epoch": 0.07549584133077415,
      "grad_norm": 0.310546875,
      "learning_rate": 0.000118,
      "loss": 1.5782,
      "step": 59
    },
    {
      "epoch": 0.07677543186180422,
      "grad_norm": 0.29296875,
      "learning_rate": 0.00012,
      "loss": 1.6386,
      "step": 60
    },
    {
      "epoch": 0.07677543186180422,
      "eval_loss": 1.5920685529708862,
      "eval_runtime": 103.8813,
      "eval_samples_per_second": 48.132,
      "eval_steps_per_second": 1.511,
      "step": 60
    },
    {
      "epoch": 0.0780550223928343,
      "grad_norm": 0.2890625,
      "learning_rate": 0.000122,
      "loss": 1.5949,
      "step": 61
    },
    {
      "epoch": 0.07933461292386436,
      "grad_norm": 0.28125,
      "learning_rate": 0.000124,
      "loss": 1.6136,
      "step": 62
    },
    {
      "epoch": 0.08061420345489444,
      "grad_norm": 0.2890625,
      "learning_rate": 0.000126,
      "loss": 1.6135,
      "step": 63
    },
    {
      "epoch": 0.0818937939859245,
      "grad_norm": 0.287109375,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.5579,
      "step": 64
    },
    {
      "epoch": 0.08317338451695458,
      "grad_norm": 0.306640625,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.6174,
      "step": 65
    },
    {
      "epoch": 0.08445297504798464,
      "grad_norm": 0.28125,
      "learning_rate": 0.000132,
      "loss": 1.6687,
      "step": 66
    },
    {
      "epoch": 0.08573256557901472,
      "grad_norm": 0.30078125,
      "learning_rate": 0.000134,
      "loss": 1.604,
      "step": 67
    },
    {
      "epoch": 0.08701215611004479,
      "grad_norm": 0.3125,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.5936,
      "step": 68
    },
    {
      "epoch": 0.08829174664107485,
      "grad_norm": 0.27734375,
      "learning_rate": 0.000138,
      "loss": 1.5744,
      "step": 69
    },
    {
      "epoch": 0.08957133717210493,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00014,
      "loss": 1.5875,
      "step": 70
    },
    {
      "epoch": 0.09085092770313499,
      "grad_norm": 0.283203125,
      "learning_rate": 0.000142,
      "loss": 1.5938,
      "step": 71
    },
    {
      "epoch": 0.09213051823416507,
      "grad_norm": 0.291015625,
      "learning_rate": 0.000144,
      "loss": 1.5795,
      "step": 72
    },
    {
      "epoch": 0.09341010876519514,
      "grad_norm": 0.2578125,
      "learning_rate": 0.000146,
      "loss": 1.5642,
      "step": 73
    },
    {
      "epoch": 0.09468969929622521,
      "grad_norm": 0.255859375,
      "learning_rate": 0.000148,
      "loss": 1.6276,
      "step": 74
    },
    {
      "epoch": 0.09596928982725528,
      "grad_norm": 0.259765625,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.6222,
      "step": 75
    },
    {
      "epoch": 0.09724888035828536,
      "grad_norm": 0.232421875,
      "learning_rate": 0.000152,
      "loss": 1.5487,
      "step": 76
    },
    {
      "epoch": 0.09852847088931542,
      "grad_norm": 0.259765625,
      "learning_rate": 0.000154,
      "loss": 1.6183,
      "step": 77
    },
    {
      "epoch": 0.09980806142034548,
      "grad_norm": 0.228515625,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.5813,
      "step": 78
    },
    {
      "epoch": 0.10108765195137556,
      "grad_norm": 0.25,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.5332,
      "step": 79
    },
    {
      "epoch": 0.10236724248240563,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00016,
      "loss": 1.5553,
      "step": 80
    },
    {
      "epoch": 0.10236724248240563,
      "eval_loss": 1.5541130304336548,
      "eval_runtime": 103.8472,
      "eval_samples_per_second": 48.148,
      "eval_steps_per_second": 1.512,
      "step": 80
    },
    {
      "epoch": 0.1036468330134357,
      "grad_norm": 0.248046875,
      "learning_rate": 0.000162,
      "loss": 1.5697,
      "step": 81
    },
    {
      "epoch": 0.10492642354446577,
      "grad_norm": 0.251953125,
      "learning_rate": 0.000164,
      "loss": 1.5474,
      "step": 82
    },
    {
      "epoch": 0.10620601407549585,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.000166,
      "loss": 1.5834,
      "step": 83
    },
    {
      "epoch": 0.10748560460652591,
      "grad_norm": 0.2294921875,
      "learning_rate": 0.000168,
      "loss": 1.542,
      "step": 84
    },
    {
      "epoch": 0.10876519513755598,
      "grad_norm": 0.2265625,
      "learning_rate": 0.00017,
      "loss": 1.5841,
      "step": 85
    },
    {
      "epoch": 0.11004478566858605,
      "grad_norm": 0.25390625,
      "learning_rate": 0.000172,
      "loss": 1.515,
      "step": 86
    },
    {
      "epoch": 0.11132437619961612,
      "grad_norm": 0.244140625,
      "learning_rate": 0.000174,
      "loss": 1.5565,
      "step": 87
    },
    {
      "epoch": 0.1126039667306462,
      "grad_norm": 0.2197265625,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.6133,
      "step": 88
    },
    {
      "epoch": 0.11388355726167626,
      "grad_norm": 0.25,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.5476,
      "step": 89
    },
    {
      "epoch": 0.11516314779270634,
      "grad_norm": 0.25,
      "learning_rate": 0.00018,
      "loss": 1.5212,
      "step": 90
    },
    {
      "epoch": 0.1164427383237364,
      "grad_norm": 0.2216796875,
      "learning_rate": 0.000182,
      "loss": 1.5628,
      "step": 91
    },
    {
      "epoch": 0.11772232885476648,
      "grad_norm": 0.2353515625,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.4946,
      "step": 92
    },
    {
      "epoch": 0.11900191938579655,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.6303,
      "step": 93
    },
    {
      "epoch": 0.12028150991682661,
      "grad_norm": 0.24609375,
      "learning_rate": 0.000188,
      "loss": 1.5155,
      "step": 94
    },
    {
      "epoch": 0.12156110044785669,
      "grad_norm": 0.220703125,
      "learning_rate": 0.00019,
      "loss": 1.5652,
      "step": 95
    },
    {
      "epoch": 0.12284069097888675,
      "grad_norm": 0.2236328125,
      "learning_rate": 0.000192,
      "loss": 1.6042,
      "step": 96
    },
    {
      "epoch": 0.12412028150991683,
      "grad_norm": 0.263671875,
      "learning_rate": 0.000194,
      "loss": 1.5697,
      "step": 97
    },
    {
      "epoch": 0.1253998720409469,
      "grad_norm": 0.2294921875,
      "learning_rate": 0.000196,
      "loss": 1.4785,
      "step": 98
    },
    {
      "epoch": 0.12667946257197696,
      "grad_norm": 0.2236328125,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.4921,
      "step": 99
    },
    {
      "epoch": 0.12795905310300704,
      "grad_norm": 0.22265625,
      "learning_rate": 0.0002,
      "loss": 1.4985,
      "step": 100
    },
    {
      "epoch": 0.12795905310300704,
      "eval_loss": 1.5341166257858276,
      "eval_runtime": 103.7833,
      "eval_samples_per_second": 48.177,
      "eval_steps_per_second": 1.513,
      "step": 100
    },
    {
      "epoch": 0.12923864363403711,
      "grad_norm": 0.232421875,
      "learning_rate": 0.00019951456310679614,
      "loss": 1.494,
      "step": 101
    },
    {
      "epoch": 0.13051823416506717,
      "grad_norm": 0.236328125,
      "learning_rate": 0.00019902912621359224,
      "loss": 1.5407,
      "step": 102
    },
    {
      "epoch": 0.13179782469609724,
      "grad_norm": 0.236328125,
      "learning_rate": 0.00019854368932038837,
      "loss": 1.5755,
      "step": 103
    },
    {
      "epoch": 0.13307741522712732,
      "grad_norm": 0.2216796875,
      "learning_rate": 0.00019805825242718447,
      "loss": 1.5491,
      "step": 104
    },
    {
      "epoch": 0.1343570057581574,
      "grad_norm": 0.2421875,
      "learning_rate": 0.0001975728155339806,
      "loss": 1.5393,
      "step": 105
    },
    {
      "epoch": 0.13563659628918745,
      "grad_norm": 0.2236328125,
      "learning_rate": 0.0001970873786407767,
      "loss": 1.5657,
      "step": 106
    },
    {
      "epoch": 0.13691618682021753,
      "grad_norm": 0.2119140625,
      "learning_rate": 0.00019660194174757283,
      "loss": 1.5551,
      "step": 107
    },
    {
      "epoch": 0.1381957773512476,
      "grad_norm": 0.240234375,
      "learning_rate": 0.00019611650485436895,
      "loss": 1.5408,
      "step": 108
    },
    {
      "epoch": 0.13947536788227768,
      "grad_norm": 0.2373046875,
      "learning_rate": 0.00019563106796116505,
      "loss": 1.5375,
      "step": 109
    },
    {
      "epoch": 0.14075495841330773,
      "grad_norm": 0.216796875,
      "learning_rate": 0.00019514563106796118,
      "loss": 1.5578,
      "step": 110
    },
    {
      "epoch": 0.1420345489443378,
      "grad_norm": 0.240234375,
      "learning_rate": 0.00019466019417475728,
      "loss": 1.4969,
      "step": 111
    },
    {
      "epoch": 0.1433141394753679,
      "grad_norm": 0.244140625,
      "learning_rate": 0.0001941747572815534,
      "loss": 1.5347,
      "step": 112
    },
    {
      "epoch": 0.14459373000639794,
      "grad_norm": 0.287109375,
      "learning_rate": 0.00019368932038834954,
      "loss": 1.549,
      "step": 113
    },
    {
      "epoch": 0.14587332053742802,
      "grad_norm": 0.2470703125,
      "learning_rate": 0.00019320388349514564,
      "loss": 1.5749,
      "step": 114
    },
    {
      "epoch": 0.1471529110684581,
      "grad_norm": 0.2353515625,
      "learning_rate": 0.00019271844660194177,
      "loss": 1.5311,
      "step": 115
    },
    {
      "epoch": 0.14843250159948818,
      "grad_norm": 0.2275390625,
      "learning_rate": 0.00019223300970873787,
      "loss": 1.5678,
      "step": 116
    },
    {
      "epoch": 0.14971209213051823,
      "grad_norm": 0.259765625,
      "learning_rate": 0.000191747572815534,
      "loss": 1.616,
      "step": 117
    },
    {
      "epoch": 0.1509916826615483,
      "grad_norm": 0.2158203125,
      "learning_rate": 0.0001912621359223301,
      "loss": 1.5449,
      "step": 118
    },
    {
      "epoch": 0.15227127319257838,
      "grad_norm": 0.2373046875,
      "learning_rate": 0.00019077669902912623,
      "loss": 1.4975,
      "step": 119
    },
    {
      "epoch": 0.15355086372360843,
      "grad_norm": 0.234375,
      "learning_rate": 0.00019029126213592236,
      "loss": 1.5631,
      "step": 120
    },
    {
      "epoch": 0.15355086372360843,
      "eval_loss": 1.5212680101394653,
      "eval_runtime": 103.8151,
      "eval_samples_per_second": 48.163,
      "eval_steps_per_second": 1.512,
      "step": 120
    },
    {
      "epoch": 0.1548304542546385,
      "grad_norm": 0.2177734375,
      "learning_rate": 0.00018980582524271846,
      "loss": 1.5534,
      "step": 121
    },
    {
      "epoch": 0.1561100447856686,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00018932038834951458,
      "loss": 1.5329,
      "step": 122
    },
    {
      "epoch": 0.15738963531669867,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.00018883495145631069,
      "loss": 1.5372,
      "step": 123
    },
    {
      "epoch": 0.15866922584772872,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00018834951456310681,
      "loss": 1.5373,
      "step": 124
    },
    {
      "epoch": 0.1599488163787588,
      "grad_norm": 0.2421875,
      "learning_rate": 0.00018786407766990291,
      "loss": 1.5492,
      "step": 125
    },
    {
      "epoch": 0.16122840690978887,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00018737864077669904,
      "loss": 1.536,
      "step": 126
    },
    {
      "epoch": 0.16250799744081892,
      "grad_norm": 0.236328125,
      "learning_rate": 0.00018689320388349517,
      "loss": 1.5719,
      "step": 127
    },
    {
      "epoch": 0.163787587971849,
      "grad_norm": 0.248046875,
      "learning_rate": 0.00018640776699029127,
      "loss": 1.5101,
      "step": 128
    },
    {
      "epoch": 0.16506717850287908,
      "grad_norm": 0.22265625,
      "learning_rate": 0.0001859223300970874,
      "loss": 1.5896,
      "step": 129
    },
    {
      "epoch": 0.16634676903390916,
      "grad_norm": 0.220703125,
      "learning_rate": 0.0001854368932038835,
      "loss": 1.5791,
      "step": 130
    },
    {
      "epoch": 0.1676263595649392,
      "grad_norm": 0.251953125,
      "learning_rate": 0.00018495145631067963,
      "loss": 1.5013,
      "step": 131
    },
    {
      "epoch": 0.1689059500959693,
      "grad_norm": 0.2373046875,
      "learning_rate": 0.00018446601941747576,
      "loss": 1.5421,
      "step": 132
    },
    {
      "epoch": 0.17018554062699937,
      "grad_norm": 0.2373046875,
      "learning_rate": 0.00018398058252427186,
      "loss": 1.5329,
      "step": 133
    },
    {
      "epoch": 0.17146513115802944,
      "grad_norm": 0.2294921875,
      "learning_rate": 0.00018349514563106799,
      "loss": 1.5631,
      "step": 134
    },
    {
      "epoch": 0.1727447216890595,
      "grad_norm": 0.25390625,
      "learning_rate": 0.0001830097087378641,
      "loss": 1.5278,
      "step": 135
    },
    {
      "epoch": 0.17402431222008957,
      "grad_norm": 0.2431640625,
      "learning_rate": 0.00018252427184466022,
      "loss": 1.5548,
      "step": 136
    },
    {
      "epoch": 0.17530390275111965,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00018203883495145632,
      "loss": 1.5023,
      "step": 137
    },
    {
      "epoch": 0.1765834932821497,
      "grad_norm": 0.2333984375,
      "learning_rate": 0.00018155339805825244,
      "loss": 1.5062,
      "step": 138
    },
    {
      "epoch": 0.17786308381317978,
      "grad_norm": 0.265625,
      "learning_rate": 0.00018106796116504857,
      "loss": 1.5637,
      "step": 139
    },
    {
      "epoch": 0.17914267434420986,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00018058252427184467,
      "loss": 1.5201,
      "step": 140
    },
    {
      "epoch": 0.17914267434420986,
      "eval_loss": 1.513644814491272,
      "eval_runtime": 103.8133,
      "eval_samples_per_second": 48.163,
      "eval_steps_per_second": 1.512,
      "step": 140
    },
    {
      "epoch": 0.18042226487523993,
      "grad_norm": 0.2353515625,
      "learning_rate": 0.0001800970873786408,
      "loss": 1.5106,
      "step": 141
    },
    {
      "epoch": 0.18170185540626999,
      "grad_norm": 0.23046875,
      "learning_rate": 0.0001796116504854369,
      "loss": 1.5403,
      "step": 142
    },
    {
      "epoch": 0.18298144593730006,
      "grad_norm": 0.236328125,
      "learning_rate": 0.00017912621359223303,
      "loss": 1.5373,
      "step": 143
    },
    {
      "epoch": 0.18426103646833014,
      "grad_norm": 0.2421875,
      "learning_rate": 0.00017864077669902913,
      "loss": 1.5697,
      "step": 144
    },
    {
      "epoch": 0.1855406269993602,
      "grad_norm": 0.240234375,
      "learning_rate": 0.00017815533980582526,
      "loss": 1.5135,
      "step": 145
    },
    {
      "epoch": 0.18682021753039027,
      "grad_norm": 0.228515625,
      "learning_rate": 0.0001776699029126214,
      "loss": 1.5446,
      "step": 146
    },
    {
      "epoch": 0.18809980806142035,
      "grad_norm": 0.22265625,
      "learning_rate": 0.0001771844660194175,
      "loss": 1.5226,
      "step": 147
    },
    {
      "epoch": 0.18937939859245043,
      "grad_norm": 0.2275390625,
      "learning_rate": 0.00017669902912621362,
      "loss": 1.4343,
      "step": 148
    },
    {
      "epoch": 0.19065898912348048,
      "grad_norm": 0.232421875,
      "learning_rate": 0.00017621359223300972,
      "loss": 1.5509,
      "step": 149
    },
    {
      "epoch": 0.19193857965451055,
      "grad_norm": 0.234375,
      "learning_rate": 0.00017572815533980585,
      "loss": 1.5397,
      "step": 150
    },
    {
      "epoch": 0.19321817018554063,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00017524271844660195,
      "loss": 1.4796,
      "step": 151
    },
    {
      "epoch": 0.1944977607165707,
      "grad_norm": 0.2470703125,
      "learning_rate": 0.00017475728155339805,
      "loss": 1.5855,
      "step": 152
    },
    {
      "epoch": 0.19577735124760076,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.00017427184466019418,
      "loss": 1.5221,
      "step": 153
    },
    {
      "epoch": 0.19705694177863084,
      "grad_norm": 0.265625,
      "learning_rate": 0.00017378640776699028,
      "loss": 1.4963,
      "step": 154
    },
    {
      "epoch": 0.19833653230966092,
      "grad_norm": 0.236328125,
      "learning_rate": 0.0001733009708737864,
      "loss": 1.5379,
      "step": 155
    },
    {
      "epoch": 0.19961612284069097,
      "grad_norm": 0.220703125,
      "learning_rate": 0.00017281553398058253,
      "loss": 1.4701,
      "step": 156
    },
    {
      "epoch": 0.20089571337172105,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.00017233009708737864,
      "loss": 1.5133,
      "step": 157
    },
    {
      "epoch": 0.20217530390275112,
      "grad_norm": 0.251953125,
      "learning_rate": 0.00017184466019417476,
      "loss": 1.5238,
      "step": 158
    },
    {
      "epoch": 0.2034548944337812,
      "grad_norm": 0.2490234375,
      "learning_rate": 0.00017135922330097086,
      "loss": 1.5361,
      "step": 159
    },
    {
      "epoch": 0.20473448496481125,
      "grad_norm": 0.232421875,
      "learning_rate": 0.000170873786407767,
      "loss": 1.4585,
      "step": 160
    },
    {
      "epoch": 0.20473448496481125,
      "eval_loss": 1.5087493658065796,
      "eval_runtime": 103.8289,
      "eval_samples_per_second": 48.156,
      "eval_steps_per_second": 1.512,
      "step": 160
    },
    {
      "epoch": 0.20601407549584133,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.0001703883495145631,
      "loss": 1.5574,
      "step": 161
    },
    {
      "epoch": 0.2072936660268714,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.00016990291262135922,
      "loss": 1.4938,
      "step": 162
    },
    {
      "epoch": 0.20857325655790146,
      "grad_norm": 0.2431640625,
      "learning_rate": 0.00016941747572815535,
      "loss": 1.5307,
      "step": 163
    },
    {
      "epoch": 0.20985284708893154,
      "grad_norm": 0.23828125,
      "learning_rate": 0.00016893203883495145,
      "loss": 1.4849,
      "step": 164
    },
    {
      "epoch": 0.21113243761996162,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00016844660194174758,
      "loss": 1.4399,
      "step": 165
    },
    {
      "epoch": 0.2124120281509917,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00016796116504854368,
      "loss": 1.512,
      "step": 166
    },
    {
      "epoch": 0.21369161868202174,
      "grad_norm": 0.263671875,
      "learning_rate": 0.0001674757281553398,
      "loss": 1.5586,
      "step": 167
    },
    {
      "epoch": 0.21497120921305182,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.00016699029126213594,
      "loss": 1.5673,
      "step": 168
    },
    {
      "epoch": 0.2162507997440819,
      "grad_norm": 0.2392578125,
      "learning_rate": 0.00016650485436893204,
      "loss": 1.4893,
      "step": 169
    },
    {
      "epoch": 0.21753039027511195,
      "grad_norm": 0.244140625,
      "learning_rate": 0.00016601941747572817,
      "loss": 1.5885,
      "step": 170
    },
    {
      "epoch": 0.21880998080614203,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00016553398058252427,
      "loss": 1.5318,
      "step": 171
    },
    {
      "epoch": 0.2200895713371721,
      "grad_norm": 0.2392578125,
      "learning_rate": 0.0001650485436893204,
      "loss": 1.4523,
      "step": 172
    },
    {
      "epoch": 0.22136916186820219,
      "grad_norm": 0.255859375,
      "learning_rate": 0.0001645631067961165,
      "loss": 1.5486,
      "step": 173
    },
    {
      "epoch": 0.22264875239923224,
      "grad_norm": 0.234375,
      "learning_rate": 0.00016407766990291262,
      "loss": 1.4989,
      "step": 174
    },
    {
      "epoch": 0.22392834293026231,
      "grad_norm": 0.2421875,
      "learning_rate": 0.00016359223300970875,
      "loss": 1.5556,
      "step": 175
    },
    {
      "epoch": 0.2252079334612924,
      "grad_norm": 0.232421875,
      "learning_rate": 0.00016310679611650485,
      "loss": 1.545,
      "step": 176
    },
    {
      "epoch": 0.22648752399232247,
      "grad_norm": 0.2470703125,
      "learning_rate": 0.00016262135922330098,
      "loss": 1.4939,
      "step": 177
    },
    {
      "epoch": 0.22776711452335252,
      "grad_norm": 0.259765625,
      "learning_rate": 0.00016213592233009708,
      "loss": 1.4768,
      "step": 178
    },
    {
      "epoch": 0.2290467050543826,
      "grad_norm": 0.2578125,
      "learning_rate": 0.0001616504854368932,
      "loss": 1.494,
      "step": 179
    },
    {
      "epoch": 0.23032629558541268,
      "grad_norm": 0.259765625,
      "learning_rate": 0.0001611650485436893,
      "loss": 1.5361,
      "step": 180
    },
    {
      "epoch": 0.23032629558541268,
      "eval_loss": 1.5049980878829956,
      "eval_runtime": 103.8247,
      "eval_samples_per_second": 48.158,
      "eval_steps_per_second": 1.512,
      "step": 180
    },
    {
      "epoch": 0.23160588611644273,
      "grad_norm": 0.248046875,
      "learning_rate": 0.00016067961165048544,
      "loss": 1.5126,
      "step": 181
    },
    {
      "epoch": 0.2328854766474728,
      "grad_norm": 0.2216796875,
      "learning_rate": 0.00016019417475728157,
      "loss": 1.4835,
      "step": 182
    },
    {
      "epoch": 0.23416506717850288,
      "grad_norm": 0.251953125,
      "learning_rate": 0.00015970873786407767,
      "loss": 1.5131,
      "step": 183
    },
    {
      "epoch": 0.23544465770953296,
      "grad_norm": 0.259765625,
      "learning_rate": 0.0001592233009708738,
      "loss": 1.4804,
      "step": 184
    },
    {
      "epoch": 0.236724248240563,
      "grad_norm": 0.25,
      "learning_rate": 0.0001587378640776699,
      "loss": 1.6027,
      "step": 185
    },
    {
      "epoch": 0.2380038387715931,
      "grad_norm": 0.2373046875,
      "learning_rate": 0.00015825242718446603,
      "loss": 1.5373,
      "step": 186
    },
    {
      "epoch": 0.23928342930262317,
      "grad_norm": 0.2265625,
      "learning_rate": 0.00015776699029126213,
      "loss": 1.5531,
      "step": 187
    },
    {
      "epoch": 0.24056301983365322,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.00015728155339805825,
      "loss": 1.5101,
      "step": 188
    },
    {
      "epoch": 0.2418426103646833,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00015679611650485438,
      "loss": 1.538,
      "step": 189
    },
    {
      "epoch": 0.24312220089571338,
      "grad_norm": 0.2451171875,
      "learning_rate": 0.00015631067961165048,
      "loss": 1.526,
      "step": 190
    },
    {
      "epoch": 0.24440179142674345,
      "grad_norm": 0.248046875,
      "learning_rate": 0.0001558252427184466,
      "loss": 1.5275,
      "step": 191
    },
    {
      "epoch": 0.2456813819577735,
      "grad_norm": 0.2421875,
      "learning_rate": 0.0001553398058252427,
      "loss": 1.567,
      "step": 192
    },
    {
      "epoch": 0.24696097248880358,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00015485436893203884,
      "loss": 1.4457,
      "step": 193
    },
    {
      "epoch": 0.24824056301983366,
      "grad_norm": 0.2421875,
      "learning_rate": 0.00015436893203883497,
      "loss": 1.5728,
      "step": 194
    },
    {
      "epoch": 0.2495201535508637,
      "grad_norm": 0.2421875,
      "learning_rate": 0.00015388349514563107,
      "loss": 1.4829,
      "step": 195
    },
    {
      "epoch": 0.2507997440818938,
      "grad_norm": 0.23046875,
      "learning_rate": 0.0001533980582524272,
      "loss": 1.5093,
      "step": 196
    },
    {
      "epoch": 0.25207933461292387,
      "grad_norm": 0.259765625,
      "learning_rate": 0.0001529126213592233,
      "loss": 1.5079,
      "step": 197
    },
    {
      "epoch": 0.2533589251439539,
      "grad_norm": 0.2265625,
      "learning_rate": 0.00015242718446601943,
      "loss": 1.4996,
      "step": 198
    },
    {
      "epoch": 0.254638515674984,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.00015194174757281553,
      "loss": 1.4967,
      "step": 199
    },
    {
      "epoch": 0.2559181062060141,
      "grad_norm": 0.287109375,
      "learning_rate": 0.00015145631067961166,
      "loss": 1.485,
      "step": 200
    },
    {
      "epoch": 0.2559181062060141,
      "eval_loss": 1.5022693872451782,
      "eval_runtime": 103.8087,
      "eval_samples_per_second": 48.166,
      "eval_steps_per_second": 1.512,
      "step": 200
    },
    {
      "epoch": 0.2571976967370441,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00015097087378640778,
      "loss": 1.4926,
      "step": 201
    },
    {
      "epoch": 0.25847728726807423,
      "grad_norm": 0.232421875,
      "learning_rate": 0.00015048543689320389,
      "loss": 1.5215,
      "step": 202
    },
    {
      "epoch": 0.2597568777991043,
      "grad_norm": 0.2373046875,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.5674,
      "step": 203
    },
    {
      "epoch": 0.26103646833013433,
      "grad_norm": 0.240234375,
      "learning_rate": 0.00014951456310679611,
      "loss": 1.5157,
      "step": 204
    },
    {
      "epoch": 0.26231605886116444,
      "grad_norm": 0.2451171875,
      "learning_rate": 0.00014902912621359224,
      "loss": 1.4502,
      "step": 205
    },
    {
      "epoch": 0.2635956493921945,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00014854368932038834,
      "loss": 1.5289,
      "step": 206
    },
    {
      "epoch": 0.2648752399232246,
      "grad_norm": 0.24609375,
      "learning_rate": 0.00014805825242718447,
      "loss": 1.4454,
      "step": 207
    },
    {
      "epoch": 0.26615483045425464,
      "grad_norm": 0.236328125,
      "learning_rate": 0.0001475728155339806,
      "loss": 1.5132,
      "step": 208
    },
    {
      "epoch": 0.2674344209852847,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0001470873786407767,
      "loss": 1.5041,
      "step": 209
    },
    {
      "epoch": 0.2687140115163148,
      "grad_norm": 0.2353515625,
      "learning_rate": 0.00014660194174757283,
      "loss": 1.5313,
      "step": 210
    },
    {
      "epoch": 0.26999360204734485,
      "grad_norm": 0.24609375,
      "learning_rate": 0.00014611650485436893,
      "loss": 1.5156,
      "step": 211
    },
    {
      "epoch": 0.2712731925783749,
      "grad_norm": 0.2451171875,
      "learning_rate": 0.00014563106796116506,
      "loss": 1.4958,
      "step": 212
    },
    {
      "epoch": 0.272552783109405,
      "grad_norm": 0.2451171875,
      "learning_rate": 0.0001451456310679612,
      "loss": 1.5324,
      "step": 213
    },
    {
      "epoch": 0.27383237364043506,
      "grad_norm": 0.2451171875,
      "learning_rate": 0.0001446601941747573,
      "loss": 1.4894,
      "step": 214
    },
    {
      "epoch": 0.2751119641714651,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.00014417475728155342,
      "loss": 1.4462,
      "step": 215
    },
    {
      "epoch": 0.2763915547024952,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00014368932038834952,
      "loss": 1.5,
      "step": 216
    },
    {
      "epoch": 0.27767114523352526,
      "grad_norm": 0.296875,
      "learning_rate": 0.00014320388349514565,
      "loss": 1.5317,
      "step": 217
    },
    {
      "epoch": 0.27895073576455537,
      "grad_norm": 0.251953125,
      "learning_rate": 0.00014271844660194175,
      "loss": 1.5553,
      "step": 218
    },
    {
      "epoch": 0.2802303262955854,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00014223300970873787,
      "loss": 1.5055,
      "step": 219
    },
    {
      "epoch": 0.28150991682661547,
      "grad_norm": 0.25,
      "learning_rate": 0.000141747572815534,
      "loss": 1.5299,
      "step": 220
    },
    {
      "epoch": 0.28150991682661547,
      "eval_loss": 1.4998944997787476,
      "eval_runtime": 103.8007,
      "eval_samples_per_second": 48.169,
      "eval_steps_per_second": 1.513,
      "step": 220
    },
    {
      "epoch": 0.2827895073576456,
      "grad_norm": 0.2734375,
      "learning_rate": 0.0001412621359223301,
      "loss": 1.5298,
      "step": 221
    },
    {
      "epoch": 0.2840690978886756,
      "grad_norm": 0.25,
      "learning_rate": 0.00014077669902912623,
      "loss": 1.5178,
      "step": 222
    },
    {
      "epoch": 0.2853486884197057,
      "grad_norm": 0.244140625,
      "learning_rate": 0.00014029126213592233,
      "loss": 1.4975,
      "step": 223
    },
    {
      "epoch": 0.2866282789507358,
      "grad_norm": 0.2333984375,
      "learning_rate": 0.00013980582524271846,
      "loss": 1.5121,
      "step": 224
    },
    {
      "epoch": 0.28790786948176583,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00013932038834951456,
      "loss": 1.4838,
      "step": 225
    },
    {
      "epoch": 0.2891874600127959,
      "grad_norm": 0.265625,
      "learning_rate": 0.0001388349514563107,
      "loss": 1.4422,
      "step": 226
    },
    {
      "epoch": 0.290467050543826,
      "grad_norm": 0.2421875,
      "learning_rate": 0.00013834951456310682,
      "loss": 1.5315,
      "step": 227
    },
    {
      "epoch": 0.29174664107485604,
      "grad_norm": 0.271484375,
      "learning_rate": 0.00013786407766990292,
      "loss": 1.524,
      "step": 228
    },
    {
      "epoch": 0.2930262316058861,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00013737864077669905,
      "loss": 1.4314,
      "step": 229
    },
    {
      "epoch": 0.2943058221369162,
      "grad_norm": 0.2421875,
      "learning_rate": 0.00013689320388349515,
      "loss": 1.5496,
      "step": 230
    },
    {
      "epoch": 0.29558541266794625,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00013640776699029128,
      "loss": 1.5526,
      "step": 231
    },
    {
      "epoch": 0.29686500319897635,
      "grad_norm": 0.25,
      "learning_rate": 0.0001359223300970874,
      "loss": 1.427,
      "step": 232
    },
    {
      "epoch": 0.2981445937300064,
      "grad_norm": 0.267578125,
      "learning_rate": 0.0001354368932038835,
      "loss": 1.4646,
      "step": 233
    },
    {
      "epoch": 0.29942418426103645,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00013495145631067963,
      "loss": 1.5392,
      "step": 234
    },
    {
      "epoch": 0.30070377479206656,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00013446601941747573,
      "loss": 1.5333,
      "step": 235
    },
    {
      "epoch": 0.3019833653230966,
      "grad_norm": 0.2431640625,
      "learning_rate": 0.00013398058252427186,
      "loss": 1.5282,
      "step": 236
    },
    {
      "epoch": 0.30326295585412666,
      "grad_norm": 0.251953125,
      "learning_rate": 0.00013349514563106796,
      "loss": 1.4763,
      "step": 237
    },
    {
      "epoch": 0.30454254638515676,
      "grad_norm": 0.2734375,
      "learning_rate": 0.0001330097087378641,
      "loss": 1.5199,
      "step": 238
    },
    {
      "epoch": 0.3058221369161868,
      "grad_norm": 0.263671875,
      "learning_rate": 0.00013252427184466022,
      "loss": 1.5497,
      "step": 239
    },
    {
      "epoch": 0.30710172744721687,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00013203883495145632,
      "loss": 1.5539,
      "step": 240
    },
    {
      "epoch": 0.30710172744721687,
      "eval_loss": 1.4981228113174438,
      "eval_runtime": 103.819,
      "eval_samples_per_second": 48.161,
      "eval_steps_per_second": 1.512,
      "step": 240
    },
    {
      "epoch": 0.30838131797824697,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00013155339805825245,
      "loss": 1.5309,
      "step": 241
    },
    {
      "epoch": 0.309660908509277,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00013106796116504855,
      "loss": 1.4503,
      "step": 242
    },
    {
      "epoch": 0.31094049904030713,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00013058252427184468,
      "loss": 1.4718,
      "step": 243
    },
    {
      "epoch": 0.3122200895713372,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00013009708737864078,
      "loss": 1.4445,
      "step": 244
    },
    {
      "epoch": 0.31349968010236723,
      "grad_norm": 0.2392578125,
      "learning_rate": 0.0001296116504854369,
      "loss": 1.5606,
      "step": 245
    },
    {
      "epoch": 0.31477927063339733,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00012912621359223304,
      "loss": 1.4917,
      "step": 246
    },
    {
      "epoch": 0.3160588611644274,
      "grad_norm": 0.240234375,
      "learning_rate": 0.00012864077669902914,
      "loss": 1.5295,
      "step": 247
    },
    {
      "epoch": 0.31733845169545744,
      "grad_norm": 0.2890625,
      "learning_rate": 0.00012815533980582526,
      "loss": 1.5685,
      "step": 248
    },
    {
      "epoch": 0.31861804222648754,
      "grad_norm": 0.28515625,
      "learning_rate": 0.00012766990291262137,
      "loss": 1.4985,
      "step": 249
    },
    {
      "epoch": 0.3198976327575176,
      "grad_norm": 0.251953125,
      "learning_rate": 0.0001271844660194175,
      "loss": 1.4746,
      "step": 250
    },
    {
      "epoch": 0.32117722328854764,
      "grad_norm": 0.26953125,
      "learning_rate": 0.00012669902912621362,
      "loss": 1.5615,
      "step": 251
    },
    {
      "epoch": 0.32245681381957775,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.00012621359223300972,
      "loss": 1.4777,
      "step": 252
    },
    {
      "epoch": 0.3237364043506078,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00012572815533980585,
      "loss": 1.4152,
      "step": 253
    },
    {
      "epoch": 0.32501599488163785,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00012524271844660195,
      "loss": 1.4632,
      "step": 254
    },
    {
      "epoch": 0.32629558541266795,
      "grad_norm": 0.259765625,
      "learning_rate": 0.00012475728155339805,
      "loss": 1.5011,
      "step": 255
    },
    {
      "epoch": 0.327575175943698,
      "grad_norm": 0.244140625,
      "learning_rate": 0.00012427184466019418,
      "loss": 1.5339,
      "step": 256
    },
    {
      "epoch": 0.3288547664747281,
      "grad_norm": 0.271484375,
      "learning_rate": 0.00012378640776699028,
      "loss": 1.4776,
      "step": 257
    },
    {
      "epoch": 0.33013435700575816,
      "grad_norm": 0.265625,
      "learning_rate": 0.0001233009708737864,
      "loss": 1.4585,
      "step": 258
    },
    {
      "epoch": 0.3314139475367882,
      "grad_norm": 0.26171875,
      "learning_rate": 0.0001228155339805825,
      "loss": 1.4791,
      "step": 259
    },
    {
      "epoch": 0.3326935380678183,
      "grad_norm": 0.263671875,
      "learning_rate": 0.00012233009708737864,
      "loss": 1.521,
      "step": 260
    },
    {
      "epoch": 0.3326935380678183,
      "eval_loss": 1.4961707592010498,
      "eval_runtime": 103.7907,
      "eval_samples_per_second": 48.174,
      "eval_steps_per_second": 1.513,
      "step": 260
    },
    {
      "epoch": 0.33397312859884837,
      "grad_norm": 0.265625,
      "learning_rate": 0.00012184466019417475,
      "loss": 1.5015,
      "step": 261
    },
    {
      "epoch": 0.3352527191298784,
      "grad_norm": 0.26953125,
      "learning_rate": 0.00012135922330097087,
      "loss": 1.4732,
      "step": 262
    },
    {
      "epoch": 0.3365323096609085,
      "grad_norm": 0.294921875,
      "learning_rate": 0.00012087378640776698,
      "loss": 1.4832,
      "step": 263
    },
    {
      "epoch": 0.3378119001919386,
      "grad_norm": 0.271484375,
      "learning_rate": 0.0001203883495145631,
      "loss": 1.4629,
      "step": 264
    },
    {
      "epoch": 0.3390914907229686,
      "grad_norm": 0.265625,
      "learning_rate": 0.00011990291262135923,
      "loss": 1.5046,
      "step": 265
    },
    {
      "epoch": 0.34037108125399873,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00011941747572815534,
      "loss": 1.5724,
      "step": 266
    },
    {
      "epoch": 0.3416506717850288,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00011893203883495146,
      "loss": 1.4481,
      "step": 267
    },
    {
      "epoch": 0.3429302623160589,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00011844660194174757,
      "loss": 1.5081,
      "step": 268
    },
    {
      "epoch": 0.34420985284708894,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00011796116504854368,
      "loss": 1.5056,
      "step": 269
    },
    {
      "epoch": 0.345489443378119,
      "grad_norm": 0.26953125,
      "learning_rate": 0.0001174757281553398,
      "loss": 1.5279,
      "step": 270
    },
    {
      "epoch": 0.3467690339091491,
      "grad_norm": 0.244140625,
      "learning_rate": 0.00011699029126213593,
      "loss": 1.5293,
      "step": 271
    },
    {
      "epoch": 0.34804862444017914,
      "grad_norm": 0.271484375,
      "learning_rate": 0.00011650485436893204,
      "loss": 1.5436,
      "step": 272
    },
    {
      "epoch": 0.3493282149712092,
      "grad_norm": 0.259765625,
      "learning_rate": 0.00011601941747572816,
      "loss": 1.5806,
      "step": 273
    },
    {
      "epoch": 0.3506078055022393,
      "grad_norm": 0.271484375,
      "learning_rate": 0.00011553398058252427,
      "loss": 1.5412,
      "step": 274
    },
    {
      "epoch": 0.35188739603326935,
      "grad_norm": 0.283203125,
      "learning_rate": 0.00011504854368932039,
      "loss": 1.5225,
      "step": 275
    },
    {
      "epoch": 0.3531669865642994,
      "grad_norm": 0.2490234375,
      "learning_rate": 0.0001145631067961165,
      "loss": 1.6229,
      "step": 276
    },
    {
      "epoch": 0.3544465770953295,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00011407766990291261,
      "loss": 1.5231,
      "step": 277
    },
    {
      "epoch": 0.35572616762635956,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00011359223300970874,
      "loss": 1.481,
      "step": 278
    },
    {
      "epoch": 0.3570057581573896,
      "grad_norm": 0.265625,
      "learning_rate": 0.00011310679611650486,
      "loss": 1.544,
      "step": 279
    },
    {
      "epoch": 0.3582853486884197,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00011262135922330097,
      "loss": 1.5186,
      "step": 280
    },
    {
      "epoch": 0.3582853486884197,
      "eval_loss": 1.4947106838226318,
      "eval_runtime": 103.7757,
      "eval_samples_per_second": 48.181,
      "eval_steps_per_second": 1.513,
      "step": 280
    },
    {
      "epoch": 0.35956493921944976,
      "grad_norm": 0.2470703125,
      "learning_rate": 0.00011213592233009709,
      "loss": 1.5507,
      "step": 281
    },
    {
      "epoch": 0.36084452975047987,
      "grad_norm": 0.255859375,
      "learning_rate": 0.0001116504854368932,
      "loss": 1.5091,
      "step": 282
    },
    {
      "epoch": 0.3621241202815099,
      "grad_norm": 0.28125,
      "learning_rate": 0.00011116504854368932,
      "loss": 1.4962,
      "step": 283
    },
    {
      "epoch": 0.36340371081253997,
      "grad_norm": 0.251953125,
      "learning_rate": 0.00011067961165048544,
      "loss": 1.537,
      "step": 284
    },
    {
      "epoch": 0.3646833013435701,
      "grad_norm": 0.271484375,
      "learning_rate": 0.00011019417475728156,
      "loss": 1.5814,
      "step": 285
    },
    {
      "epoch": 0.3659628918746001,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00010970873786407767,
      "loss": 1.5328,
      "step": 286
    },
    {
      "epoch": 0.3672424824056302,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00010922330097087379,
      "loss": 1.5429,
      "step": 287
    },
    {
      "epoch": 0.3685220729366603,
      "grad_norm": 0.26953125,
      "learning_rate": 0.0001087378640776699,
      "loss": 1.489,
      "step": 288
    },
    {
      "epoch": 0.36980166346769033,
      "grad_norm": 0.248046875,
      "learning_rate": 0.00010825242718446602,
      "loss": 1.518,
      "step": 289
    },
    {
      "epoch": 0.3710812539987204,
      "grad_norm": 0.25,
      "learning_rate": 0.00010776699029126213,
      "loss": 1.5142,
      "step": 290
    },
    {
      "epoch": 0.3723608445297505,
      "grad_norm": 0.271484375,
      "learning_rate": 0.00010728155339805826,
      "loss": 1.5229,
      "step": 291
    },
    {
      "epoch": 0.37364043506078054,
      "grad_norm": 0.251953125,
      "learning_rate": 0.00010679611650485437,
      "loss": 1.4803,
      "step": 292
    },
    {
      "epoch": 0.37492002559181065,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00010631067961165049,
      "loss": 1.5791,
      "step": 293
    },
    {
      "epoch": 0.3761996161228407,
      "grad_norm": 0.2470703125,
      "learning_rate": 0.0001058252427184466,
      "loss": 1.5336,
      "step": 294
    },
    {
      "epoch": 0.37747920665387075,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00010533980582524272,
      "loss": 1.4581,
      "step": 295
    },
    {
      "epoch": 0.37875879718490085,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00010485436893203883,
      "loss": 1.4919,
      "step": 296
    },
    {
      "epoch": 0.3800383877159309,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00010436893203883496,
      "loss": 1.5778,
      "step": 297
    },
    {
      "epoch": 0.38131797824696095,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00010388349514563107,
      "loss": 1.4489,
      "step": 298
    },
    {
      "epoch": 0.38259756877799106,
      "grad_norm": 0.265625,
      "learning_rate": 0.00010339805825242719,
      "loss": 1.4704,
      "step": 299
    },
    {
      "epoch": 0.3838771593090211,
      "grad_norm": 0.267578125,
      "learning_rate": 0.0001029126213592233,
      "loss": 1.5316,
      "step": 300
    },
    {
      "epoch": 0.3838771593090211,
      "eval_loss": 1.4935728311538696,
      "eval_runtime": 103.76,
      "eval_samples_per_second": 48.188,
      "eval_steps_per_second": 1.513,
      "step": 300
    },
    {
      "epoch": 0.38515674984005116,
      "grad_norm": 0.265625,
      "learning_rate": 0.00010242718446601942,
      "loss": 1.5093,
      "step": 301
    },
    {
      "epoch": 0.38643634037108127,
      "grad_norm": 0.263671875,
      "learning_rate": 0.00010194174757281553,
      "loss": 1.4871,
      "step": 302
    },
    {
      "epoch": 0.3877159309021113,
      "grad_norm": 0.29296875,
      "learning_rate": 0.00010145631067961166,
      "loss": 1.4842,
      "step": 303
    },
    {
      "epoch": 0.3889955214331414,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00010097087378640778,
      "loss": 1.5545,
      "step": 304
    },
    {
      "epoch": 0.3902751119641715,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00010048543689320389,
      "loss": 1.5671,
      "step": 305
    },
    {
      "epoch": 0.3915547024952015,
      "grad_norm": 0.263671875,
      "learning_rate": 0.0001,
      "loss": 1.4817,
      "step": 306
    },
    {
      "epoch": 0.39283429302623163,
      "grad_norm": 0.275390625,
      "learning_rate": 9.951456310679612e-05,
      "loss": 1.4727,
      "step": 307
    },
    {
      "epoch": 0.3941138835572617,
      "grad_norm": 0.251953125,
      "learning_rate": 9.902912621359223e-05,
      "loss": 1.4717,
      "step": 308
    },
    {
      "epoch": 0.39539347408829173,
      "grad_norm": 0.2734375,
      "learning_rate": 9.854368932038835e-05,
      "loss": 1.4795,
      "step": 309
    },
    {
      "epoch": 0.39667306461932184,
      "grad_norm": 0.267578125,
      "learning_rate": 9.805825242718448e-05,
      "loss": 1.4475,
      "step": 310
    },
    {
      "epoch": 0.3979526551503519,
      "grad_norm": 0.283203125,
      "learning_rate": 9.757281553398059e-05,
      "loss": 1.4661,
      "step": 311
    },
    {
      "epoch": 0.39923224568138194,
      "grad_norm": 0.271484375,
      "learning_rate": 9.70873786407767e-05,
      "loss": 1.4808,
      "step": 312
    },
    {
      "epoch": 0.40051183621241204,
      "grad_norm": 0.29296875,
      "learning_rate": 9.660194174757282e-05,
      "loss": 1.5169,
      "step": 313
    },
    {
      "epoch": 0.4017914267434421,
      "grad_norm": 0.296875,
      "learning_rate": 9.611650485436893e-05,
      "loss": 1.4856,
      "step": 314
    },
    {
      "epoch": 0.40307101727447214,
      "grad_norm": 0.2578125,
      "learning_rate": 9.563106796116505e-05,
      "loss": 1.4995,
      "step": 315
    },
    {
      "epoch": 0.40435060780550225,
      "grad_norm": 0.28125,
      "learning_rate": 9.514563106796118e-05,
      "loss": 1.5682,
      "step": 316
    },
    {
      "epoch": 0.4056301983365323,
      "grad_norm": 0.265625,
      "learning_rate": 9.466019417475729e-05,
      "loss": 1.492,
      "step": 317
    },
    {
      "epoch": 0.4069097888675624,
      "grad_norm": 0.275390625,
      "learning_rate": 9.417475728155341e-05,
      "loss": 1.4706,
      "step": 318
    },
    {
      "epoch": 0.40818937939859246,
      "grad_norm": 0.265625,
      "learning_rate": 9.368932038834952e-05,
      "loss": 1.5184,
      "step": 319
    },
    {
      "epoch": 0.4094689699296225,
      "grad_norm": 0.283203125,
      "learning_rate": 9.320388349514564e-05,
      "loss": 1.5288,
      "step": 320
    },
    {
      "epoch": 0.4094689699296225,
      "eval_loss": 1.4924702644348145,
      "eval_runtime": 103.7588,
      "eval_samples_per_second": 48.189,
      "eval_steps_per_second": 1.513,
      "step": 320
    },
    {
      "epoch": 0.4107485604606526,
      "grad_norm": 0.275390625,
      "learning_rate": 9.271844660194175e-05,
      "loss": 1.5166,
      "step": 321
    },
    {
      "epoch": 0.41202815099168266,
      "grad_norm": 0.265625,
      "learning_rate": 9.223300970873788e-05,
      "loss": 1.5137,
      "step": 322
    },
    {
      "epoch": 0.4133077415227127,
      "grad_norm": 0.2890625,
      "learning_rate": 9.174757281553399e-05,
      "loss": 1.4874,
      "step": 323
    },
    {
      "epoch": 0.4145873320537428,
      "grad_norm": 0.27734375,
      "learning_rate": 9.126213592233011e-05,
      "loss": 1.4144,
      "step": 324
    },
    {
      "epoch": 0.41586692258477287,
      "grad_norm": 0.251953125,
      "learning_rate": 9.077669902912622e-05,
      "loss": 1.529,
      "step": 325
    },
    {
      "epoch": 0.4171465131158029,
      "grad_norm": 0.2578125,
      "learning_rate": 9.029126213592234e-05,
      "loss": 1.5507,
      "step": 326
    },
    {
      "epoch": 0.418426103646833,
      "grad_norm": 0.283203125,
      "learning_rate": 8.980582524271845e-05,
      "loss": 1.5447,
      "step": 327
    },
    {
      "epoch": 0.4197056941778631,
      "grad_norm": 0.2578125,
      "learning_rate": 8.932038834951457e-05,
      "loss": 1.556,
      "step": 328
    },
    {
      "epoch": 0.4209852847088932,
      "grad_norm": 0.2734375,
      "learning_rate": 8.88349514563107e-05,
      "loss": 1.4945,
      "step": 329
    },
    {
      "epoch": 0.42226487523992323,
      "grad_norm": 0.2578125,
      "learning_rate": 8.834951456310681e-05,
      "loss": 1.5668,
      "step": 330
    },
    {
      "epoch": 0.4235444657709533,
      "grad_norm": 0.259765625,
      "learning_rate": 8.786407766990292e-05,
      "loss": 1.501,
      "step": 331
    },
    {
      "epoch": 0.4248240563019834,
      "grad_norm": 0.259765625,
      "learning_rate": 8.737864077669902e-05,
      "loss": 1.5187,
      "step": 332
    },
    {
      "epoch": 0.42610364683301344,
      "grad_norm": 0.259765625,
      "learning_rate": 8.689320388349514e-05,
      "loss": 1.5736,
      "step": 333
    },
    {
      "epoch": 0.4273832373640435,
      "grad_norm": 0.28125,
      "learning_rate": 8.640776699029127e-05,
      "loss": 1.5085,
      "step": 334
    },
    {
      "epoch": 0.4286628278950736,
      "grad_norm": 0.25390625,
      "learning_rate": 8.592233009708738e-05,
      "loss": 1.4757,
      "step": 335
    },
    {
      "epoch": 0.42994241842610365,
      "grad_norm": 0.267578125,
      "learning_rate": 8.54368932038835e-05,
      "loss": 1.5243,
      "step": 336
    },
    {
      "epoch": 0.4312220089571337,
      "grad_norm": 0.26953125,
      "learning_rate": 8.495145631067961e-05,
      "loss": 1.5662,
      "step": 337
    },
    {
      "epoch": 0.4325015994881638,
      "grad_norm": 0.265625,
      "learning_rate": 8.446601941747573e-05,
      "loss": 1.433,
      "step": 338
    },
    {
      "epoch": 0.43378119001919385,
      "grad_norm": 0.283203125,
      "learning_rate": 8.398058252427184e-05,
      "loss": 1.5378,
      "step": 339
    },
    {
      "epoch": 0.4350607805502239,
      "grad_norm": 0.29296875,
      "learning_rate": 8.349514563106797e-05,
      "loss": 1.5276,
      "step": 340
    },
    {
      "epoch": 0.4350607805502239,
      "eval_loss": 1.4914450645446777,
      "eval_runtime": 103.7522,
      "eval_samples_per_second": 48.192,
      "eval_steps_per_second": 1.513,
      "step": 340
    },
    {
      "epoch": 0.436340371081254,
      "grad_norm": 0.2734375,
      "learning_rate": 8.300970873786408e-05,
      "loss": 1.4723,
      "step": 341
    },
    {
      "epoch": 0.43761996161228406,
      "grad_norm": 0.25390625,
      "learning_rate": 8.25242718446602e-05,
      "loss": 1.5185,
      "step": 342
    },
    {
      "epoch": 0.43889955214331416,
      "grad_norm": 0.271484375,
      "learning_rate": 8.203883495145631e-05,
      "loss": 1.5317,
      "step": 343
    },
    {
      "epoch": 0.4401791426743442,
      "grad_norm": 0.251953125,
      "learning_rate": 8.155339805825243e-05,
      "loss": 1.5254,
      "step": 344
    },
    {
      "epoch": 0.44145873320537427,
      "grad_norm": 0.259765625,
      "learning_rate": 8.106796116504854e-05,
      "loss": 1.5152,
      "step": 345
    },
    {
      "epoch": 0.44273832373640437,
      "grad_norm": 0.28125,
      "learning_rate": 8.058252427184466e-05,
      "loss": 1.4812,
      "step": 346
    },
    {
      "epoch": 0.4440179142674344,
      "grad_norm": 0.26953125,
      "learning_rate": 8.009708737864078e-05,
      "loss": 1.5023,
      "step": 347
    },
    {
      "epoch": 0.44529750479846447,
      "grad_norm": 0.291015625,
      "learning_rate": 7.96116504854369e-05,
      "loss": 1.4516,
      "step": 348
    },
    {
      "epoch": 0.4465770953294946,
      "grad_norm": 0.279296875,
      "learning_rate": 7.912621359223301e-05,
      "loss": 1.4349,
      "step": 349
    },
    {
      "epoch": 0.44785668586052463,
      "grad_norm": 0.28125,
      "learning_rate": 7.864077669902913e-05,
      "loss": 1.5181,
      "step": 350
    },
    {
      "epoch": 0.4491362763915547,
      "grad_norm": 0.27734375,
      "learning_rate": 7.815533980582524e-05,
      "loss": 1.4765,
      "step": 351
    },
    {
      "epoch": 0.4504158669225848,
      "grad_norm": 0.275390625,
      "learning_rate": 7.766990291262136e-05,
      "loss": 1.524,
      "step": 352
    },
    {
      "epoch": 0.45169545745361483,
      "grad_norm": 0.25,
      "learning_rate": 7.718446601941748e-05,
      "loss": 1.5236,
      "step": 353
    },
    {
      "epoch": 0.45297504798464494,
      "grad_norm": 0.2890625,
      "learning_rate": 7.66990291262136e-05,
      "loss": 1.5358,
      "step": 354
    },
    {
      "epoch": 0.454254638515675,
      "grad_norm": 0.244140625,
      "learning_rate": 7.621359223300971e-05,
      "loss": 1.5447,
      "step": 355
    },
    {
      "epoch": 0.45553422904670504,
      "grad_norm": 0.287109375,
      "learning_rate": 7.572815533980583e-05,
      "loss": 1.428,
      "step": 356
    },
    {
      "epoch": 0.45681381957773515,
      "grad_norm": 0.263671875,
      "learning_rate": 7.524271844660194e-05,
      "loss": 1.3921,
      "step": 357
    },
    {
      "epoch": 0.4580934101087652,
      "grad_norm": 0.2734375,
      "learning_rate": 7.475728155339806e-05,
      "loss": 1.5059,
      "step": 358
    },
    {
      "epoch": 0.45937300063979525,
      "grad_norm": 0.2734375,
      "learning_rate": 7.427184466019417e-05,
      "loss": 1.4832,
      "step": 359
    },
    {
      "epoch": 0.46065259117082535,
      "grad_norm": 0.279296875,
      "learning_rate": 7.37864077669903e-05,
      "loss": 1.5236,
      "step": 360
    },
    {
      "epoch": 0.46065259117082535,
      "eval_loss": 1.4904447793960571,
      "eval_runtime": 103.753,
      "eval_samples_per_second": 48.191,
      "eval_steps_per_second": 1.513,
      "step": 360
    },
    {
      "epoch": 0.4619321817018554,
      "grad_norm": 0.287109375,
      "learning_rate": 7.330097087378641e-05,
      "loss": 1.5008,
      "step": 361
    },
    {
      "epoch": 0.46321177223288545,
      "grad_norm": 0.28125,
      "learning_rate": 7.281553398058253e-05,
      "loss": 1.5244,
      "step": 362
    },
    {
      "epoch": 0.46449136276391556,
      "grad_norm": 0.27734375,
      "learning_rate": 7.233009708737864e-05,
      "loss": 1.5849,
      "step": 363
    },
    {
      "epoch": 0.4657709532949456,
      "grad_norm": 0.2490234375,
      "learning_rate": 7.184466019417476e-05,
      "loss": 1.4882,
      "step": 364
    },
    {
      "epoch": 0.46705054382597566,
      "grad_norm": 0.267578125,
      "learning_rate": 7.135922330097087e-05,
      "loss": 1.4905,
      "step": 365
    },
    {
      "epoch": 0.46833013435700577,
      "grad_norm": 0.267578125,
      "learning_rate": 7.0873786407767e-05,
      "loss": 1.4391,
      "step": 366
    },
    {
      "epoch": 0.4696097248880358,
      "grad_norm": 0.2451171875,
      "learning_rate": 7.038834951456312e-05,
      "loss": 1.5034,
      "step": 367
    },
    {
      "epoch": 0.4708893154190659,
      "grad_norm": 0.283203125,
      "learning_rate": 6.990291262135923e-05,
      "loss": 1.4928,
      "step": 368
    },
    {
      "epoch": 0.472168905950096,
      "grad_norm": 0.265625,
      "learning_rate": 6.941747572815534e-05,
      "loss": 1.5578,
      "step": 369
    },
    {
      "epoch": 0.473448496481126,
      "grad_norm": 0.287109375,
      "learning_rate": 6.893203883495146e-05,
      "loss": 1.5403,
      "step": 370
    },
    {
      "epoch": 0.47472808701215613,
      "grad_norm": 0.263671875,
      "learning_rate": 6.844660194174757e-05,
      "loss": 1.5081,
      "step": 371
    },
    {
      "epoch": 0.4760076775431862,
      "grad_norm": 0.267578125,
      "learning_rate": 6.79611650485437e-05,
      "loss": 1.5799,
      "step": 372
    },
    {
      "epoch": 0.47728726807421623,
      "grad_norm": 0.25390625,
      "learning_rate": 6.747572815533982e-05,
      "loss": 1.5097,
      "step": 373
    },
    {
      "epoch": 0.47856685860524634,
      "grad_norm": 0.26953125,
      "learning_rate": 6.699029126213593e-05,
      "loss": 1.5164,
      "step": 374
    },
    {
      "epoch": 0.4798464491362764,
      "grad_norm": 0.26171875,
      "learning_rate": 6.650485436893205e-05,
      "loss": 1.5139,
      "step": 375
    },
    {
      "epoch": 0.48112603966730644,
      "grad_norm": 0.251953125,
      "learning_rate": 6.601941747572816e-05,
      "loss": 1.4756,
      "step": 376
    },
    {
      "epoch": 0.48240563019833654,
      "grad_norm": 0.263671875,
      "learning_rate": 6.553398058252428e-05,
      "loss": 1.5325,
      "step": 377
    },
    {
      "epoch": 0.4836852207293666,
      "grad_norm": 0.283203125,
      "learning_rate": 6.504854368932039e-05,
      "loss": 1.4932,
      "step": 378
    },
    {
      "epoch": 0.4849648112603967,
      "grad_norm": 0.265625,
      "learning_rate": 6.456310679611652e-05,
      "loss": 1.5157,
      "step": 379
    },
    {
      "epoch": 0.48624440179142675,
      "grad_norm": 0.298828125,
      "learning_rate": 6.407766990291263e-05,
      "loss": 1.4882,
      "step": 380
    },
    {
      "epoch": 0.48624440179142675,
      "eval_loss": 1.4896763563156128,
      "eval_runtime": 103.7894,
      "eval_samples_per_second": 48.174,
      "eval_steps_per_second": 1.513,
      "step": 380
    },
    {
      "epoch": 0.4875239923224568,
      "grad_norm": 0.259765625,
      "learning_rate": 6.359223300970875e-05,
      "loss": 1.546,
      "step": 381
    },
    {
      "epoch": 0.4888035828534869,
      "grad_norm": 0.279296875,
      "learning_rate": 6.310679611650486e-05,
      "loss": 1.4907,
      "step": 382
    },
    {
      "epoch": 0.49008317338451696,
      "grad_norm": 0.2734375,
      "learning_rate": 6.262135922330098e-05,
      "loss": 1.4512,
      "step": 383
    },
    {
      "epoch": 0.491362763915547,
      "grad_norm": 0.26953125,
      "learning_rate": 6.213592233009709e-05,
      "loss": 1.5442,
      "step": 384
    },
    {
      "epoch": 0.4926423544465771,
      "grad_norm": 0.28125,
      "learning_rate": 6.16504854368932e-05,
      "loss": 1.4975,
      "step": 385
    },
    {
      "epoch": 0.49392194497760716,
      "grad_norm": 0.265625,
      "learning_rate": 6.116504854368932e-05,
      "loss": 1.534,
      "step": 386
    },
    {
      "epoch": 0.4952015355086372,
      "grad_norm": 0.27734375,
      "learning_rate": 6.0679611650485434e-05,
      "loss": 1.417,
      "step": 387
    },
    {
      "epoch": 0.4964811260396673,
      "grad_norm": 0.255859375,
      "learning_rate": 6.019417475728155e-05,
      "loss": 1.4766,
      "step": 388
    },
    {
      "epoch": 0.49776071657069737,
      "grad_norm": 0.283203125,
      "learning_rate": 5.970873786407767e-05,
      "loss": 1.4672,
      "step": 389
    },
    {
      "epoch": 0.4990403071017274,
      "grad_norm": 0.271484375,
      "learning_rate": 5.9223300970873785e-05,
      "loss": 1.5021,
      "step": 390
    },
    {
      "epoch": 0.5003198976327575,
      "grad_norm": 0.283203125,
      "learning_rate": 5.87378640776699e-05,
      "loss": 1.5723,
      "step": 391
    },
    {
      "epoch": 0.5015994881637876,
      "grad_norm": 0.271484375,
      "learning_rate": 5.825242718446602e-05,
      "loss": 1.5351,
      "step": 392
    },
    {
      "epoch": 0.5028790786948176,
      "grad_norm": 0.27734375,
      "learning_rate": 5.7766990291262135e-05,
      "loss": 1.5922,
      "step": 393
    },
    {
      "epoch": 0.5041586692258477,
      "grad_norm": 0.263671875,
      "learning_rate": 5.728155339805825e-05,
      "loss": 1.5,
      "step": 394
    },
    {
      "epoch": 0.5054382597568778,
      "grad_norm": 0.26953125,
      "learning_rate": 5.679611650485437e-05,
      "loss": 1.5057,
      "step": 395
    },
    {
      "epoch": 0.5067178502879078,
      "grad_norm": 0.255859375,
      "learning_rate": 5.6310679611650486e-05,
      "loss": 1.4968,
      "step": 396
    },
    {
      "epoch": 0.5079974408189379,
      "grad_norm": 0.27734375,
      "learning_rate": 5.58252427184466e-05,
      "loss": 1.4383,
      "step": 397
    },
    {
      "epoch": 0.509277031349968,
      "grad_norm": 0.2734375,
      "learning_rate": 5.533980582524272e-05,
      "loss": 1.5069,
      "step": 398
    },
    {
      "epoch": 0.510556621880998,
      "grad_norm": 0.265625,
      "learning_rate": 5.4854368932038836e-05,
      "loss": 1.4293,
      "step": 399
    },
    {
      "epoch": 0.5118362124120281,
      "grad_norm": 0.275390625,
      "learning_rate": 5.436893203883495e-05,
      "loss": 1.5098,
      "step": 400
    },
    {
      "epoch": 0.5118362124120281,
      "eval_loss": 1.4892088174819946,
      "eval_runtime": 103.7401,
      "eval_samples_per_second": 48.197,
      "eval_steps_per_second": 1.513,
      "step": 400
    },
    {
      "epoch": 0.5131158029430583,
      "grad_norm": 0.267578125,
      "learning_rate": 5.3883495145631065e-05,
      "loss": 1.4924,
      "step": 401
    },
    {
      "epoch": 0.5143953934740882,
      "grad_norm": 0.267578125,
      "learning_rate": 5.339805825242719e-05,
      "loss": 1.5093,
      "step": 402
    },
    {
      "epoch": 0.5156749840051184,
      "grad_norm": 0.271484375,
      "learning_rate": 5.29126213592233e-05,
      "loss": 1.5384,
      "step": 403
    },
    {
      "epoch": 0.5169545745361485,
      "grad_norm": 0.275390625,
      "learning_rate": 5.2427184466019416e-05,
      "loss": 1.5331,
      "step": 404
    },
    {
      "epoch": 0.5182341650671785,
      "grad_norm": 0.28515625,
      "learning_rate": 5.194174757281554e-05,
      "loss": 1.5009,
      "step": 405
    },
    {
      "epoch": 0.5195137555982086,
      "grad_norm": 0.255859375,
      "learning_rate": 5.145631067961165e-05,
      "loss": 1.4744,
      "step": 406
    },
    {
      "epoch": 0.5207933461292387,
      "grad_norm": 0.28125,
      "learning_rate": 5.0970873786407766e-05,
      "loss": 1.5178,
      "step": 407
    },
    {
      "epoch": 0.5220729366602687,
      "grad_norm": 0.263671875,
      "learning_rate": 5.048543689320389e-05,
      "loss": 1.4893,
      "step": 408
    },
    {
      "epoch": 0.5233525271912988,
      "grad_norm": 0.236328125,
      "learning_rate": 5e-05,
      "loss": 1.5309,
      "step": 409
    },
    {
      "epoch": 0.5246321177223289,
      "grad_norm": 0.30078125,
      "learning_rate": 4.951456310679612e-05,
      "loss": 1.4873,
      "step": 410
    },
    {
      "epoch": 0.525911708253359,
      "grad_norm": 0.2734375,
      "learning_rate": 4.902912621359224e-05,
      "loss": 1.5083,
      "step": 411
    },
    {
      "epoch": 0.527191298784389,
      "grad_norm": 0.25390625,
      "learning_rate": 4.854368932038835e-05,
      "loss": 1.5487,
      "step": 412
    },
    {
      "epoch": 0.5284708893154191,
      "grad_norm": 0.2578125,
      "learning_rate": 4.805825242718447e-05,
      "loss": 1.4886,
      "step": 413
    },
    {
      "epoch": 0.5297504798464492,
      "grad_norm": 0.265625,
      "learning_rate": 4.757281553398059e-05,
      "loss": 1.4687,
      "step": 414
    },
    {
      "epoch": 0.5310300703774792,
      "grad_norm": 0.267578125,
      "learning_rate": 4.7087378640776703e-05,
      "loss": 1.5612,
      "step": 415
    },
    {
      "epoch": 0.5323096609085093,
      "grad_norm": 0.26953125,
      "learning_rate": 4.660194174757282e-05,
      "loss": 1.534,
      "step": 416
    },
    {
      "epoch": 0.5335892514395394,
      "grad_norm": 0.296875,
      "learning_rate": 4.611650485436894e-05,
      "loss": 1.4985,
      "step": 417
    },
    {
      "epoch": 0.5348688419705694,
      "grad_norm": 0.259765625,
      "learning_rate": 4.5631067961165054e-05,
      "loss": 1.5042,
      "step": 418
    },
    {
      "epoch": 0.5361484325015995,
      "grad_norm": 0.267578125,
      "learning_rate": 4.514563106796117e-05,
      "loss": 1.5292,
      "step": 419
    },
    {
      "epoch": 0.5374280230326296,
      "grad_norm": 0.265625,
      "learning_rate": 4.466019417475728e-05,
      "loss": 1.4526,
      "step": 420
    },
    {
      "epoch": 0.5374280230326296,
      "eval_loss": 1.4887601137161255,
      "eval_runtime": 103.7847,
      "eval_samples_per_second": 48.177,
      "eval_steps_per_second": 1.513,
      "step": 420
    },
    {
      "epoch": 0.5387076135636596,
      "grad_norm": 0.275390625,
      "learning_rate": 4.4174757281553404e-05,
      "loss": 1.4529,
      "step": 421
    },
    {
      "epoch": 0.5399872040946897,
      "grad_norm": 0.271484375,
      "learning_rate": 4.368932038834951e-05,
      "loss": 1.4163,
      "step": 422
    },
    {
      "epoch": 0.5412667946257198,
      "grad_norm": 0.2578125,
      "learning_rate": 4.3203883495145634e-05,
      "loss": 1.5169,
      "step": 423
    },
    {
      "epoch": 0.5425463851567498,
      "grad_norm": 0.27734375,
      "learning_rate": 4.271844660194175e-05,
      "loss": 1.4888,
      "step": 424
    },
    {
      "epoch": 0.5438259756877799,
      "grad_norm": 0.265625,
      "learning_rate": 4.223300970873786e-05,
      "loss": 1.4733,
      "step": 425
    },
    {
      "epoch": 0.54510556621881,
      "grad_norm": 0.306640625,
      "learning_rate": 4.1747572815533984e-05,
      "loss": 1.503,
      "step": 426
    },
    {
      "epoch": 0.54638515674984,
      "grad_norm": 0.27734375,
      "learning_rate": 4.12621359223301e-05,
      "loss": 1.4406,
      "step": 427
    },
    {
      "epoch": 0.5476647472808701,
      "grad_norm": 0.267578125,
      "learning_rate": 4.077669902912621e-05,
      "loss": 1.4952,
      "step": 428
    },
    {
      "epoch": 0.5489443378119002,
      "grad_norm": 0.271484375,
      "learning_rate": 4.029126213592233e-05,
      "loss": 1.4837,
      "step": 429
    },
    {
      "epoch": 0.5502239283429302,
      "grad_norm": 0.28515625,
      "learning_rate": 3.980582524271845e-05,
      "loss": 1.6037,
      "step": 430
    },
    {
      "epoch": 0.5515035188739603,
      "grad_norm": 0.283203125,
      "learning_rate": 3.9320388349514564e-05,
      "loss": 1.4425,
      "step": 431
    },
    {
      "epoch": 0.5527831094049904,
      "grad_norm": 0.26953125,
      "learning_rate": 3.883495145631068e-05,
      "loss": 1.4502,
      "step": 432
    },
    {
      "epoch": 0.5540626999360204,
      "grad_norm": 0.291015625,
      "learning_rate": 3.83495145631068e-05,
      "loss": 1.4936,
      "step": 433
    },
    {
      "epoch": 0.5553422904670505,
      "grad_norm": 0.287109375,
      "learning_rate": 3.7864077669902914e-05,
      "loss": 1.5186,
      "step": 434
    },
    {
      "epoch": 0.5566218809980806,
      "grad_norm": 0.283203125,
      "learning_rate": 3.737864077669903e-05,
      "loss": 1.464,
      "step": 435
    },
    {
      "epoch": 0.5579014715291107,
      "grad_norm": 0.271484375,
      "learning_rate": 3.689320388349515e-05,
      "loss": 1.4973,
      "step": 436
    },
    {
      "epoch": 0.5591810620601407,
      "grad_norm": 0.2578125,
      "learning_rate": 3.6407766990291265e-05,
      "loss": 1.5231,
      "step": 437
    },
    {
      "epoch": 0.5604606525911708,
      "grad_norm": 0.255859375,
      "learning_rate": 3.592233009708738e-05,
      "loss": 1.5225,
      "step": 438
    },
    {
      "epoch": 0.5617402431222009,
      "grad_norm": 0.2734375,
      "learning_rate": 3.54368932038835e-05,
      "loss": 1.4312,
      "step": 439
    },
    {
      "epoch": 0.5630198336532309,
      "grad_norm": 0.27734375,
      "learning_rate": 3.4951456310679615e-05,
      "loss": 1.5529,
      "step": 440
    },
    {
      "epoch": 0.5630198336532309,
      "eval_loss": 1.4884061813354492,
      "eval_runtime": 103.7793,
      "eval_samples_per_second": 48.179,
      "eval_steps_per_second": 1.513,
      "step": 440
    },
    {
      "epoch": 0.564299424184261,
      "grad_norm": 0.2890625,
      "learning_rate": 3.446601941747573e-05,
      "loss": 1.4933,
      "step": 441
    },
    {
      "epoch": 0.5655790147152912,
      "grad_norm": 0.298828125,
      "learning_rate": 3.398058252427185e-05,
      "loss": 1.4352,
      "step": 442
    },
    {
      "epoch": 0.5668586052463211,
      "grad_norm": 0.271484375,
      "learning_rate": 3.3495145631067966e-05,
      "loss": 1.5062,
      "step": 443
    },
    {
      "epoch": 0.5681381957773513,
      "grad_norm": 0.279296875,
      "learning_rate": 3.300970873786408e-05,
      "loss": 1.5018,
      "step": 444
    },
    {
      "epoch": 0.5694177863083814,
      "grad_norm": 0.283203125,
      "learning_rate": 3.2524271844660195e-05,
      "loss": 1.5037,
      "step": 445
    },
    {
      "epoch": 0.5706973768394114,
      "grad_norm": 0.287109375,
      "learning_rate": 3.2038834951456316e-05,
      "loss": 1.5056,
      "step": 446
    },
    {
      "epoch": 0.5719769673704415,
      "grad_norm": 0.294921875,
      "learning_rate": 3.155339805825243e-05,
      "loss": 1.567,
      "step": 447
    },
    {
      "epoch": 0.5732565579014716,
      "grad_norm": 0.287109375,
      "learning_rate": 3.1067961165048545e-05,
      "loss": 1.4753,
      "step": 448
    },
    {
      "epoch": 0.5745361484325016,
      "grad_norm": 0.2734375,
      "learning_rate": 3.058252427184466e-05,
      "loss": 1.5731,
      "step": 449
    },
    {
      "epoch": 0.5758157389635317,
      "grad_norm": 0.265625,
      "learning_rate": 3.0097087378640774e-05,
      "loss": 1.4695,
      "step": 450
    },
    {
      "epoch": 0.5770953294945618,
      "grad_norm": 0.279296875,
      "learning_rate": 2.9611650485436892e-05,
      "loss": 1.4394,
      "step": 451
    },
    {
      "epoch": 0.5783749200255918,
      "grad_norm": 0.26953125,
      "learning_rate": 2.912621359223301e-05,
      "loss": 1.52,
      "step": 452
    },
    {
      "epoch": 0.5796545105566219,
      "grad_norm": 0.275390625,
      "learning_rate": 2.8640776699029125e-05,
      "loss": 1.5178,
      "step": 453
    },
    {
      "epoch": 0.580934101087652,
      "grad_norm": 0.298828125,
      "learning_rate": 2.8155339805825243e-05,
      "loss": 1.5035,
      "step": 454
    },
    {
      "epoch": 0.582213691618682,
      "grad_norm": 0.259765625,
      "learning_rate": 2.766990291262136e-05,
      "loss": 1.5201,
      "step": 455
    },
    {
      "epoch": 0.5834932821497121,
      "grad_norm": 0.259765625,
      "learning_rate": 2.7184466019417475e-05,
      "loss": 1.5495,
      "step": 456
    },
    {
      "epoch": 0.5847728726807422,
      "grad_norm": 0.27734375,
      "learning_rate": 2.6699029126213593e-05,
      "loss": 1.483,
      "step": 457
    },
    {
      "epoch": 0.5860524632117722,
      "grad_norm": 0.287109375,
      "learning_rate": 2.6213592233009708e-05,
      "loss": 1.5084,
      "step": 458
    },
    {
      "epoch": 0.5873320537428023,
      "grad_norm": 0.26953125,
      "learning_rate": 2.5728155339805826e-05,
      "loss": 1.5115,
      "step": 459
    },
    {
      "epoch": 0.5886116442738324,
      "grad_norm": 0.275390625,
      "learning_rate": 2.5242718446601944e-05,
      "loss": 1.4747,
      "step": 460
    },
    {
      "epoch": 0.5886116442738324,
      "eval_loss": 1.4881880283355713,
      "eval_runtime": 103.7794,
      "eval_samples_per_second": 48.179,
      "eval_steps_per_second": 1.513,
      "step": 460
    },
    {
      "epoch": 0.5898912348048625,
      "grad_norm": 0.265625,
      "learning_rate": 2.475728155339806e-05,
      "loss": 1.5567,
      "step": 461
    },
    {
      "epoch": 0.5911708253358925,
      "grad_norm": 0.2734375,
      "learning_rate": 2.4271844660194176e-05,
      "loss": 1.4473,
      "step": 462
    },
    {
      "epoch": 0.5924504158669226,
      "grad_norm": 0.263671875,
      "learning_rate": 2.3786407766990294e-05,
      "loss": 1.5204,
      "step": 463
    },
    {
      "epoch": 0.5937300063979527,
      "grad_norm": 0.283203125,
      "learning_rate": 2.330097087378641e-05,
      "loss": 1.537,
      "step": 464
    },
    {
      "epoch": 0.5950095969289827,
      "grad_norm": 0.251953125,
      "learning_rate": 2.2815533980582527e-05,
      "loss": 1.4269,
      "step": 465
    },
    {
      "epoch": 0.5962891874600128,
      "grad_norm": 0.259765625,
      "learning_rate": 2.233009708737864e-05,
      "loss": 1.452,
      "step": 466
    },
    {
      "epoch": 0.5975687779910429,
      "grad_norm": 0.271484375,
      "learning_rate": 2.1844660194174756e-05,
      "loss": 1.4702,
      "step": 467
    },
    {
      "epoch": 0.5988483685220729,
      "grad_norm": 0.263671875,
      "learning_rate": 2.1359223300970874e-05,
      "loss": 1.4577,
      "step": 468
    },
    {
      "epoch": 0.600127959053103,
      "grad_norm": 0.27734375,
      "learning_rate": 2.0873786407766992e-05,
      "loss": 1.5009,
      "step": 469
    },
    {
      "epoch": 0.6014075495841331,
      "grad_norm": 0.251953125,
      "learning_rate": 2.0388349514563107e-05,
      "loss": 1.4926,
      "step": 470
    },
    {
      "epoch": 0.6026871401151631,
      "grad_norm": 0.2890625,
      "learning_rate": 1.9902912621359225e-05,
      "loss": 1.5575,
      "step": 471
    },
    {
      "epoch": 0.6039667306461932,
      "grad_norm": 0.28125,
      "learning_rate": 1.941747572815534e-05,
      "loss": 1.4811,
      "step": 472
    },
    {
      "epoch": 0.6052463211772233,
      "grad_norm": 0.291015625,
      "learning_rate": 1.8932038834951457e-05,
      "loss": 1.496,
      "step": 473
    },
    {
      "epoch": 0.6065259117082533,
      "grad_norm": 0.26953125,
      "learning_rate": 1.8446601941747575e-05,
      "loss": 1.4922,
      "step": 474
    },
    {
      "epoch": 0.6078055022392834,
      "grad_norm": 0.28515625,
      "learning_rate": 1.796116504854369e-05,
      "loss": 1.5435,
      "step": 475
    },
    {
      "epoch": 0.6090850927703135,
      "grad_norm": 0.267578125,
      "learning_rate": 1.7475728155339808e-05,
      "loss": 1.5427,
      "step": 476
    },
    {
      "epoch": 0.6103646833013435,
      "grad_norm": 0.2333984375,
      "learning_rate": 1.6990291262135926e-05,
      "loss": 1.4921,
      "step": 477
    },
    {
      "epoch": 0.6116442738323736,
      "grad_norm": 0.26171875,
      "learning_rate": 1.650485436893204e-05,
      "loss": 1.4226,
      "step": 478
    },
    {
      "epoch": 0.6129238643634037,
      "grad_norm": 0.287109375,
      "learning_rate": 1.6019417475728158e-05,
      "loss": 1.4878,
      "step": 479
    },
    {
      "epoch": 0.6142034548944337,
      "grad_norm": 0.263671875,
      "learning_rate": 1.5533980582524273e-05,
      "loss": 1.5165,
      "step": 480
    },
    {
      "epoch": 0.6142034548944337,
      "eval_loss": 1.4879465103149414,
      "eval_runtime": 103.7919,
      "eval_samples_per_second": 48.173,
      "eval_steps_per_second": 1.513,
      "step": 480
    },
    {
      "epoch": 0.6154830454254638,
      "grad_norm": 0.28515625,
      "learning_rate": 1.5048543689320387e-05,
      "loss": 1.5134,
      "step": 481
    },
    {
      "epoch": 0.6167626359564939,
      "grad_norm": 0.28125,
      "learning_rate": 1.4563106796116505e-05,
      "loss": 1.4587,
      "step": 482
    },
    {
      "epoch": 0.6180422264875239,
      "grad_norm": 0.271484375,
      "learning_rate": 1.4077669902912621e-05,
      "loss": 1.4203,
      "step": 483
    },
    {
      "epoch": 0.619321817018554,
      "grad_norm": 0.28515625,
      "learning_rate": 1.3592233009708738e-05,
      "loss": 1.4245,
      "step": 484
    },
    {
      "epoch": 0.6206014075495841,
      "grad_norm": 0.279296875,
      "learning_rate": 1.3106796116504854e-05,
      "loss": 1.513,
      "step": 485
    },
    {
      "epoch": 0.6218809980806143,
      "grad_norm": 0.267578125,
      "learning_rate": 1.2621359223300972e-05,
      "loss": 1.5439,
      "step": 486
    },
    {
      "epoch": 0.6231605886116443,
      "grad_norm": 0.283203125,
      "learning_rate": 1.2135922330097088e-05,
      "loss": 1.5063,
      "step": 487
    },
    {
      "epoch": 0.6244401791426744,
      "grad_norm": 0.2734375,
      "learning_rate": 1.1650485436893204e-05,
      "loss": 1.4927,
      "step": 488
    },
    {
      "epoch": 0.6257197696737045,
      "grad_norm": 0.28515625,
      "learning_rate": 1.116504854368932e-05,
      "loss": 1.4943,
      "step": 489
    },
    {
      "epoch": 0.6269993602047345,
      "grad_norm": 0.2734375,
      "learning_rate": 1.0679611650485437e-05,
      "loss": 1.5125,
      "step": 490
    },
    {
      "epoch": 0.6282789507357646,
      "grad_norm": 0.263671875,
      "learning_rate": 1.0194174757281553e-05,
      "loss": 1.4396,
      "step": 491
    },
    {
      "epoch": 0.6295585412667947,
      "grad_norm": 0.275390625,
      "learning_rate": 9.70873786407767e-06,
      "loss": 1.4928,
      "step": 492
    },
    {
      "epoch": 0.6308381317978247,
      "grad_norm": 0.291015625,
      "learning_rate": 9.223300970873788e-06,
      "loss": 1.4664,
      "step": 493
    },
    {
      "epoch": 0.6321177223288548,
      "grad_norm": 0.279296875,
      "learning_rate": 8.737864077669904e-06,
      "loss": 1.4305,
      "step": 494
    },
    {
      "epoch": 0.6333973128598849,
      "grad_norm": 0.267578125,
      "learning_rate": 8.25242718446602e-06,
      "loss": 1.5016,
      "step": 495
    },
    {
      "epoch": 0.6346769033909149,
      "grad_norm": 0.28125,
      "learning_rate": 7.766990291262136e-06,
      "loss": 1.4641,
      "step": 496
    },
    {
      "epoch": 0.635956493921945,
      "grad_norm": 0.275390625,
      "learning_rate": 7.281553398058253e-06,
      "loss": 1.497,
      "step": 497
    },
    {
      "epoch": 0.6372360844529751,
      "grad_norm": 0.2578125,
      "learning_rate": 6.796116504854369e-06,
      "loss": 1.54,
      "step": 498
    },
    {
      "epoch": 0.6385156749840051,
      "grad_norm": 0.267578125,
      "learning_rate": 6.310679611650486e-06,
      "loss": 1.4769,
      "step": 499
    },
    {
      "epoch": 0.6397952655150352,
      "grad_norm": 0.2412109375,
      "learning_rate": 5.825242718446602e-06,
      "loss": 1.5592,
      "step": 500
    },
    {
      "epoch": 0.6397952655150352,
      "eval_loss": 1.4878435134887695,
      "eval_runtime": 103.7542,
      "eval_samples_per_second": 48.191,
      "eval_steps_per_second": 1.513,
      "step": 500
    },
    {
      "epoch": 0.6410748560460653,
      "grad_norm": 0.28515625,
      "learning_rate": 5.3398058252427185e-06,
      "loss": 1.4929,
      "step": 501
    },
    {
      "epoch": 0.6423544465770953,
      "grad_norm": 0.271484375,
      "learning_rate": 4.854368932038835e-06,
      "loss": 1.4825,
      "step": 502
    },
    {
      "epoch": 0.6436340371081254,
      "grad_norm": 0.2734375,
      "learning_rate": 4.368932038834952e-06,
      "loss": 1.5464,
      "step": 503
    },
    {
      "epoch": 0.6449136276391555,
      "grad_norm": 0.2890625,
      "learning_rate": 3.883495145631068e-06,
      "loss": 1.4797,
      "step": 504
    },
    {
      "epoch": 0.6461932181701855,
      "grad_norm": 0.298828125,
      "learning_rate": 3.3980582524271844e-06,
      "loss": 1.5039,
      "step": 505
    },
    {
      "epoch": 0.6474728087012156,
      "grad_norm": 0.296875,
      "learning_rate": 2.912621359223301e-06,
      "loss": 1.4895,
      "step": 506
    },
    {
      "epoch": 0.6487523992322457,
      "grad_norm": 0.265625,
      "learning_rate": 2.4271844660194174e-06,
      "loss": 1.4887,
      "step": 507
    },
    {
      "epoch": 0.6500319897632757,
      "grad_norm": 0.265625,
      "learning_rate": 1.941747572815534e-06,
      "loss": 1.4734,
      "step": 508
    },
    {
      "epoch": 0.6513115802943058,
      "grad_norm": 0.2578125,
      "learning_rate": 1.4563106796116506e-06,
      "loss": 1.4636,
      "step": 509
    },
    {
      "epoch": 0.6525911708253359,
      "grad_norm": 0.265625,
      "learning_rate": 9.70873786407767e-07,
      "loss": 1.5035,
      "step": 510
    },
    {
      "epoch": 0.653870761356366,
      "grad_norm": 0.251953125,
      "learning_rate": 4.854368932038835e-07,
      "loss": 1.5264,
      "step": 511
    },
    {
      "epoch": 0.655150351887396,
      "grad_norm": 0.259765625,
      "learning_rate": 0.0,
      "loss": 1.5441,
      "step": 512
    },
    {
      "epoch": 0.655150351887396,
      "step": 512,
      "total_flos": 3.6685588640169984e+17,
      "train_loss": 1.622293347492814,
      "train_runtime": 4726.6516,
      "train_samples_per_second": 6.933,
      "train_steps_per_second": 0.108
    },
    {
      "epoch": 0.655150351887396,
      "eval_loss": 1.4878435134887695,
      "eval_runtime": 103.7194,
      "eval_samples_per_second": 48.207,
      "eval_steps_per_second": 1.514,
      "step": 512
    }
  ],
  "logging_steps": 1,
  "max_steps": 512,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "total_flos": 3.6685588640169984e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}