{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1424,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.08667389329222297,
      "learning_rate": 5e-05,
      "loss": 1.2996,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.09045727907955421,
      "learning_rate": 5e-05,
      "loss": 1.2954,
      "step": 2
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.09563085455184005,
      "learning_rate": 5e-05,
      "loss": 1.3904,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.09509304597101893,
      "learning_rate": 5e-05,
      "loss": 1.3129,
      "step": 4
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.11253528120530865,
      "learning_rate": 5e-05,
      "loss": 1.3848,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.10089982798628681,
      "learning_rate": 5e-05,
      "loss": 1.4346,
      "step": 6
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.10089306432221856,
      "learning_rate": 5e-05,
      "loss": 1.2888,
      "step": 7
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.10144502034709778,
      "learning_rate": 5e-05,
      "loss": 1.4566,
      "step": 8
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.0961164132224369,
      "learning_rate": 5e-05,
      "loss": 1.3295,
      "step": 9
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.09776728005057,
      "learning_rate": 5e-05,
      "loss": 1.3634,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.08499071966520562,
      "learning_rate": 5e-05,
      "loss": 1.2536,
      "step": 11
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.10825720796344761,
      "learning_rate": 5e-05,
      "loss": 1.3407,
      "step": 12
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.07801898249414914,
      "learning_rate": 5e-05,
      "loss": 1.3189,
      "step": 13
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.07574794344316574,
      "learning_rate": 5e-05,
      "loss": 1.211,
      "step": 14
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.24315419692813534,
      "learning_rate": 5e-05,
      "loss": 1.3227,
      "step": 15
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.08425261542212245,
      "learning_rate": 5e-05,
      "loss": 1.2089,
      "step": 16
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.08183851026470287,
      "learning_rate": 5e-05,
      "loss": 1.2836,
      "step": 17
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.09223487431428871,
      "learning_rate": 5e-05,
      "loss": 1.2208,
      "step": 18
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.11228483070641347,
      "learning_rate": 5e-05,
      "loss": 1.2418,
      "step": 19
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.08879742195116058,
      "learning_rate": 5e-05,
      "loss": 1.2513,
      "step": 20
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.09483580915314582,
      "learning_rate": 5e-05,
      "loss": 1.3948,
      "step": 21
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.08603858239218602,
      "learning_rate": 5e-05,
      "loss": 1.351,
      "step": 22
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.08992366856768315,
      "learning_rate": 5e-05,
      "loss": 1.3144,
      "step": 23
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.08406961509231002,
      "learning_rate": 5e-05,
      "loss": 1.3585,
      "step": 24
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.08228049509215797,
      "learning_rate": 5e-05,
      "loss": 1.326,
      "step": 25
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.07592322737164406,
      "learning_rate": 5e-05,
      "loss": 1.3401,
      "step": 26
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.07112576203109268,
      "learning_rate": 5e-05,
      "loss": 1.1088,
      "step": 27
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.07324863402169346,
      "learning_rate": 5e-05,
      "loss": 1.246,
      "step": 28
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.08175218998309366,
      "learning_rate": 5e-05,
      "loss": 1.2348,
      "step": 29
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.08583913360130707,
      "learning_rate": 5e-05,
      "loss": 1.3035,
      "step": 30
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.07502711247215474,
      "learning_rate": 5e-05,
      "loss": 1.3474,
      "step": 31
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.07696046839654648,
      "learning_rate": 5e-05,
      "loss": 1.1426,
      "step": 32
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.06820817315021704,
      "learning_rate": 5e-05,
      "loss": 1.2306,
      "step": 33
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.06819731681879962,
      "learning_rate": 5e-05,
      "loss": 1.3403,
      "step": 34
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.0709871911694856,
      "learning_rate": 5e-05,
      "loss": 1.3955,
      "step": 35
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.06763821790570135,
      "learning_rate": 5e-05,
      "loss": 1.2616,
      "step": 36
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.07062528242297304,
      "learning_rate": 5e-05,
      "loss": 1.325,
      "step": 37
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.06805561973834255,
      "learning_rate": 5e-05,
      "loss": 1.3175,
      "step": 38
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.08790825664947328,
      "learning_rate": 5e-05,
      "loss": 1.3043,
      "step": 39
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.07561069106434462,
      "learning_rate": 5e-05,
      "loss": 1.1732,
      "step": 40
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.07459745434540017,
      "learning_rate": 5e-05,
      "loss": 1.341,
      "step": 41
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.07394792035518542,
      "learning_rate": 5e-05,
      "loss": 1.2382,
      "step": 42
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.07712869041324996,
      "learning_rate": 5e-05,
      "loss": 1.3714,
      "step": 43
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.06940306526975415,
      "learning_rate": 5e-05,
      "loss": 1.309,
      "step": 44
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.06771778026975195,
      "learning_rate": 5e-05,
      "loss": 1.2311,
      "step": 45
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.0740395369124851,
      "learning_rate": 5e-05,
      "loss": 1.2489,
      "step": 46
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.07077413357484925,
      "learning_rate": 5e-05,
      "loss": 1.2386,
      "step": 47
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.0720737094586865,
      "learning_rate": 5e-05,
      "loss": 1.1696,
      "step": 48
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.07198070989104487,
      "learning_rate": 5e-05,
      "loss": 1.3194,
      "step": 49
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.08452050939944894,
      "learning_rate": 5e-05,
      "loss": 1.2328,
      "step": 50
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.08048845476567269,
      "learning_rate": 5e-05,
      "loss": 1.328,
      "step": 51
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.06994386093892287,
      "learning_rate": 5e-05,
      "loss": 1.2783,
      "step": 52
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.08769492336853892,
      "learning_rate": 5e-05,
      "loss": 1.2528,
      "step": 53
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.07783706354156507,
      "learning_rate": 5e-05,
      "loss": 1.2972,
      "step": 54
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.07037998648664866,
      "learning_rate": 5e-05,
      "loss": 1.2901,
      "step": 55
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.07248406059256986,
      "learning_rate": 5e-05,
      "loss": 1.2696,
      "step": 56
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.0730426997946999,
      "learning_rate": 5e-05,
      "loss": 1.3199,
      "step": 57
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.07371245539543211,
      "learning_rate": 5e-05,
      "loss": 1.1871,
      "step": 58
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.06789304450900832,
      "learning_rate": 5e-05,
      "loss": 1.2348,
      "step": 59
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.1476525689556603,
      "learning_rate": 5e-05,
      "loss": 1.2089,
      "step": 60
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.08237346280480178,
      "learning_rate": 5e-05,
      "loss": 1.307,
      "step": 61
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.07725835838817337,
      "learning_rate": 5e-05,
      "loss": 1.2057,
      "step": 62
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.07711157991602562,
      "learning_rate": 5e-05,
      "loss": 1.2259,
      "step": 63
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.07470511046688118,
      "learning_rate": 5e-05,
      "loss": 1.201,
      "step": 64
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.07309944563226711,
      "learning_rate": 5e-05,
      "loss": 1.2396,
      "step": 65
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.07933719744464587,
      "learning_rate": 5e-05,
      "loss": 1.1584,
      "step": 66
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.07649496283235623,
      "learning_rate": 5e-05,
      "loss": 1.333,
      "step": 67
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.11695602061284746,
      "learning_rate": 5e-05,
      "loss": 1.3591,
      "step": 68
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.07811310800925421,
      "learning_rate": 5e-05,
      "loss": 1.3388,
      "step": 69
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.07584429948947581,
      "learning_rate": 5e-05,
      "loss": 1.295,
      "step": 70
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.08073403862737152,
      "learning_rate": 5e-05,
      "loss": 1.2076,
      "step": 71
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.07720820931346752,
      "learning_rate": 5e-05,
      "loss": 1.297,
      "step": 72
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.07036654399509103,
      "learning_rate": 5e-05,
      "loss": 1.2311,
      "step": 73
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.0752611690575668,
      "learning_rate": 5e-05,
      "loss": 1.2585,
      "step": 74
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.10117990124794089,
      "learning_rate": 5e-05,
      "loss": 1.2026,
      "step": 75
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.07538403647241076,
      "learning_rate": 5e-05,
      "loss": 1.2268,
      "step": 76
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.07331262441864544,
      "learning_rate": 5e-05,
      "loss": 1.2595,
      "step": 77
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.09199888694287987,
      "learning_rate": 5e-05,
      "loss": 1.2137,
      "step": 78
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.08374160867498517,
      "learning_rate": 5e-05,
      "loss": 1.3628,
      "step": 79
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.07717125781677839,
      "learning_rate": 5e-05,
      "loss": 1.2651,
      "step": 80
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.08093764355996728,
      "learning_rate": 5e-05,
      "loss": 1.3122,
      "step": 81
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.08556679449347177,
      "learning_rate": 5e-05,
      "loss": 1.3326,
      "step": 82
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.09227553466496595,
      "learning_rate": 5e-05,
      "loss": 1.249,
      "step": 83
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.08102953860671439,
      "learning_rate": 5e-05,
      "loss": 1.302,
      "step": 84
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.07754129003679357,
      "learning_rate": 5e-05,
      "loss": 1.2505,
      "step": 85
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.07108985280852988,
      "learning_rate": 5e-05,
      "loss": 1.2064,
      "step": 86
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.07158298922127657,
      "learning_rate": 5e-05,
      "loss": 1.1823,
      "step": 87
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.08135521726556208,
      "learning_rate": 5e-05,
      "loss": 1.3405,
      "step": 88
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.08307657353416888,
      "learning_rate": 5e-05,
      "loss": 1.305,
      "step": 89
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.07889121728559233,
      "learning_rate": 5e-05,
      "loss": 1.2913,
      "step": 90
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.08268613381268089,
      "learning_rate": 5e-05,
      "loss": 1.2941,
      "step": 91
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.07894491012006483,
      "learning_rate": 5e-05,
      "loss": 1.3321,
      "step": 92
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.08455122305124131,
      "learning_rate": 5e-05,
      "loss": 1.192,
      "step": 93
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.1677625516738703,
      "learning_rate": 5e-05,
      "loss": 1.2806,
      "step": 94
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.25154398832533,
      "learning_rate": 5e-05,
      "loss": 1.3535,
      "step": 95
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.07611303051014763,
      "learning_rate": 5e-05,
      "loss": 1.2624,
      "step": 96
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.11344652547119116,
      "learning_rate": 5e-05,
      "loss": 1.1627,
      "step": 97
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.14434115169168604,
      "learning_rate": 5e-05,
      "loss": 1.1876,
      "step": 98
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.07458715411644555,
      "learning_rate": 5e-05,
      "loss": 1.2946,
      "step": 99
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.08544912002632542,
      "learning_rate": 5e-05,
      "loss": 1.2444,
      "step": 100
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.08171618538200655,
      "learning_rate": 5e-05,
      "loss": 1.2129,
      "step": 101
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.08255798880682443,
      "learning_rate": 5e-05,
      "loss": 1.3372,
      "step": 102
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.08947951396867447,
      "learning_rate": 5e-05,
      "loss": 1.332,
      "step": 103
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.0777659290508948,
      "learning_rate": 5e-05,
      "loss": 1.2014,
      "step": 104
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.08952849723664662,
      "learning_rate": 5e-05,
      "loss": 1.2483,
      "step": 105
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.09078615775230477,
      "learning_rate": 5e-05,
      "loss": 1.2853,
      "step": 106
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.0896534354898437,
      "learning_rate": 5e-05,
      "loss": 1.1306,
      "step": 107
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.08636961732695114,
      "learning_rate": 5e-05,
      "loss": 1.1913,
      "step": 108
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.08402924358963194,
      "learning_rate": 5e-05,
      "loss": 1.2316,
      "step": 109
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.08614677250811724,
      "learning_rate": 5e-05,
      "loss": 1.1496,
      "step": 110
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.09758783646953327,
      "learning_rate": 5e-05,
      "loss": 1.2526,
      "step": 111
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.11123906322423639,
      "learning_rate": 5e-05,
      "loss": 1.3143,
      "step": 112
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.07953490903350872,
      "learning_rate": 5e-05,
      "loss": 1.2608,
      "step": 113
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.08096533975103022,
      "learning_rate": 5e-05,
      "loss": 1.2899,
      "step": 114
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.09569417661442663,
      "learning_rate": 5e-05,
      "loss": 1.2204,
      "step": 115
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.07797798808759553,
      "learning_rate": 5e-05,
      "loss": 1.3607,
      "step": 116
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.09212254796343204,
      "learning_rate": 5e-05,
      "loss": 1.2617,
      "step": 117
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.08699394943161823,
      "learning_rate": 5e-05,
      "loss": 1.2948,
      "step": 118
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.08381286973096141,
      "learning_rate": 5e-05,
      "loss": 1.1897,
      "step": 119
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.08132336656290666,
      "learning_rate": 5e-05,
      "loss": 1.281,
      "step": 120
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.08386795924919085,
      "learning_rate": 5e-05,
      "loss": 1.2912,
      "step": 121
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.07665657252389507,
      "learning_rate": 5e-05,
      "loss": 1.2528,
      "step": 122
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.09075112331474103,
      "learning_rate": 5e-05,
      "loss": 1.3052,
      "step": 123
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.0998634337377465,
      "learning_rate": 5e-05,
      "loss": 1.2649,
      "step": 124
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.08488815637357822,
      "learning_rate": 5e-05,
      "loss": 1.2227,
      "step": 125
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.10212173798210869,
      "learning_rate": 5e-05,
      "loss": 1.2753,
      "step": 126
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.08261475705898018,
      "learning_rate": 5e-05,
      "loss": 1.2333,
      "step": 127
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.08383736010274866,
      "learning_rate": 5e-05,
      "loss": 1.2227,
      "step": 128
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.08707820434533624,
      "learning_rate": 5e-05,
      "loss": 1.2376,
      "step": 129
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.08073196834288653,
      "learning_rate": 5e-05,
      "loss": 1.2409,
      "step": 130
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.09335661069349774,
      "learning_rate": 5e-05,
      "loss": 1.2679,
      "step": 131
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.07975046183728626,
      "learning_rate": 5e-05,
      "loss": 1.1778,
      "step": 132
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.10411241749696298,
      "learning_rate": 5e-05,
      "loss": 1.2002,
      "step": 133
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.09271681351921757,
      "learning_rate": 5e-05,
      "loss": 1.1609,
      "step": 134
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.08175749124919046,
      "learning_rate": 5e-05,
      "loss": 1.2824,
      "step": 135
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.08489842461646079,
      "learning_rate": 5e-05,
      "loss": 1.1674,
      "step": 136
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.09042100379932565,
      "learning_rate": 5e-05,
      "loss": 1.1701,
      "step": 137
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.09804655799498443,
      "learning_rate": 5e-05,
      "loss": 1.2956,
      "step": 138
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.07847442132135601,
      "learning_rate": 5e-05,
      "loss": 1.3093,
      "step": 139
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.08770750121763184,
      "learning_rate": 5e-05,
      "loss": 1.2946,
      "step": 140
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.10158480784213657,
      "learning_rate": 5e-05,
      "loss": 1.2356,
      "step": 141
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.10135335196013266,
      "learning_rate": 5e-05,
      "loss": 1.3034,
      "step": 142
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.08382812027073917,
      "learning_rate": 5e-05,
      "loss": 1.3398,
      "step": 143
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.09584092766963259,
      "learning_rate": 5e-05,
      "loss": 1.2887,
      "step": 144
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.08976747468288296,
      "learning_rate": 5e-05,
      "loss": 1.2122,
      "step": 145
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.0824040159135501,
      "learning_rate": 5e-05,
      "loss": 1.2985,
      "step": 146
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.09428935899731097,
      "learning_rate": 5e-05,
      "loss": 1.2339,
      "step": 147
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.07975866363163563,
      "learning_rate": 5e-05,
      "loss": 1.2496,
      "step": 148
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.08671985922920832,
      "learning_rate": 5e-05,
      "loss": 1.3155,
      "step": 149
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.08501817899150449,
      "learning_rate": 5e-05,
      "loss": 1.216,
      "step": 150
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.09083889660830718,
      "learning_rate": 5e-05,
      "loss": 1.1607,
      "step": 151
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.08645635978804701,
      "learning_rate": 5e-05,
      "loss": 1.2367,
      "step": 152
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.09008336643659964,
      "learning_rate": 5e-05,
      "loss": 1.2224,
      "step": 153
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.08930348517009218,
      "learning_rate": 5e-05,
      "loss": 1.2816,
      "step": 154
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.07800593774723825,
      "learning_rate": 5e-05,
      "loss": 1.2283,
      "step": 155
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.07870429263081696,
      "learning_rate": 5e-05,
      "loss": 1.2229,
      "step": 156
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.08841870671121418,
      "learning_rate": 5e-05,
      "loss": 1.1674,
      "step": 157
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.15926423427086853,
      "learning_rate": 5e-05,
      "loss": 1.2827,
      "step": 158
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.09104370482645933,
      "learning_rate": 5e-05,
      "loss": 1.1922,
      "step": 159
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.08996245356427444,
      "learning_rate": 5e-05,
      "loss": 1.2393,
      "step": 160
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.08355593256579182,
      "learning_rate": 5e-05,
      "loss": 1.18,
      "step": 161
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.08613963433468404,
      "learning_rate": 5e-05,
      "loss": 1.2513,
      "step": 162
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.07824373219506703,
      "learning_rate": 5e-05,
      "loss": 1.2672,
      "step": 163
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.18032874105981436,
      "learning_rate": 5e-05,
      "loss": 1.2608,
      "step": 164
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.08775610122970826,
      "learning_rate": 5e-05,
      "loss": 1.2987,
      "step": 165
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.09364314363077682,
      "learning_rate": 5e-05,
      "loss": 1.3052,
      "step": 166
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.09100701495842761,
      "learning_rate": 5e-05,
      "loss": 1.2144,
      "step": 167
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.0847083094989299,
      "learning_rate": 5e-05,
      "loss": 1.2426,
      "step": 168
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.08867714842702075,
      "learning_rate": 5e-05,
      "loss": 1.1743,
      "step": 169
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.09247456282992296,
      "learning_rate": 5e-05,
      "loss": 1.2495,
      "step": 170
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.1060254132672116,
      "learning_rate": 5e-05,
      "loss": 1.2256,
      "step": 171
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.09214434586631197,
      "learning_rate": 5e-05,
      "loss": 1.2797,
      "step": 172
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.0818323059400522,
      "learning_rate": 5e-05,
      "loss": 1.1637,
      "step": 173
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.08731967992349708,
      "learning_rate": 5e-05,
      "loss": 1.2443,
      "step": 174
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.09012749151558586,
      "learning_rate": 5e-05,
      "loss": 1.2174,
      "step": 175
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.08863238488247215,
      "learning_rate": 5e-05,
      "loss": 1.296,
      "step": 176
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.09286714960933078,
      "learning_rate": 5e-05,
      "loss": 1.2342,
      "step": 177
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.09316153696727396,
      "learning_rate": 5e-05,
      "loss": 1.1848,
      "step": 178
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.08252849611179802,
      "learning_rate": 5e-05,
      "loss": 1.2113,
      "step": 179
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.09483532321449605,
      "learning_rate": 5e-05,
      "loss": 1.3477,
      "step": 180
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.08529609510104497,
      "learning_rate": 5e-05,
      "loss": 1.2457,
      "step": 181
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.08694739448894302,
      "learning_rate": 5e-05,
      "loss": 1.3046,
      "step": 182
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.09279919556230308,
      "learning_rate": 5e-05,
      "loss": 1.3031,
      "step": 183
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.08702565087109819,
      "learning_rate": 5e-05,
      "loss": 1.2848,
      "step": 184
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.09380380233696196,
      "learning_rate": 5e-05,
      "loss": 1.1916,
      "step": 185
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.08688165004745885,
      "learning_rate": 5e-05,
      "loss": 1.2123,
      "step": 186
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.09820840635443695,
      "learning_rate": 5e-05,
      "loss": 1.2032,
      "step": 187
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.09589255206537063,
      "learning_rate": 5e-05,
      "loss": 1.241,
      "step": 188
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.08807557974050134,
      "learning_rate": 5e-05,
      "loss": 1.3048,
      "step": 189
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0851856228850121,
      "learning_rate": 5e-05,
      "loss": 1.2052,
      "step": 190
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0934937983165827,
      "learning_rate": 5e-05,
      "loss": 1.2121,
      "step": 191
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.08374744566540891,
      "learning_rate": 5e-05,
      "loss": 1.2914,
      "step": 192
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.08750918563451558,
      "learning_rate": 5e-05,
      "loss": 1.2823,
      "step": 193
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.08869708414841139,
      "learning_rate": 5e-05,
      "loss": 1.2801,
      "step": 194
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.11960800847754802,
      "learning_rate": 5e-05,
      "loss": 1.3148,
      "step": 195
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.08976487676811867,
      "learning_rate": 5e-05,
      "loss": 1.2082,
      "step": 196
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.08453661418908805,
      "learning_rate": 5e-05,
      "loss": 1.3163,
      "step": 197
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.08962171718158313,
      "learning_rate": 5e-05,
      "loss": 1.1934,
      "step": 198
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.08257769819917804,
      "learning_rate": 5e-05,
      "loss": 1.2528,
      "step": 199
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.09925347017579209,
      "learning_rate": 5e-05,
      "loss": 1.2031,
      "step": 200
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.08906225826845884,
      "learning_rate": 5e-05,
      "loss": 1.2194,
      "step": 201
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.0942395349237732,
      "learning_rate": 5e-05,
      "loss": 1.178,
      "step": 202
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.09824155177800245,
      "learning_rate": 5e-05,
      "loss": 1.2475,
      "step": 203
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.10058855273546559,
      "learning_rate": 5e-05,
      "loss": 1.2937,
      "step": 204
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.09414156661731717,
      "learning_rate": 5e-05,
      "loss": 1.1772,
      "step": 205
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.09054559747969201,
      "learning_rate": 5e-05,
      "loss": 1.193,
      "step": 206
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.09536717414530912,
      "learning_rate": 5e-05,
      "loss": 1.307,
      "step": 207
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.08494148514851217,
      "learning_rate": 5e-05,
      "loss": 1.2225,
      "step": 208
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.08863261369887773,
      "learning_rate": 5e-05,
      "loss": 1.227,
      "step": 209
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.08582994520739551,
      "learning_rate": 5e-05,
      "loss": 1.2782,
      "step": 210
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.08790341158498588,
      "learning_rate": 5e-05,
      "loss": 1.2166,
      "step": 211
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.08519174171612676,
      "learning_rate": 5e-05,
      "loss": 1.1953,
      "step": 212
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.09248080147412965,
      "learning_rate": 5e-05,
      "loss": 1.3265,
      "step": 213
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.08567765786036889,
      "learning_rate": 5e-05,
      "loss": 1.312,
      "step": 214
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.0835142660273622,
      "learning_rate": 5e-05,
      "loss": 1.2368,
      "step": 215
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.08856004333772806,
      "learning_rate": 5e-05,
      "loss": 1.1784,
      "step": 216
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.08873223128935914,
      "learning_rate": 5e-05,
      "loss": 1.3025,
      "step": 217
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.08647493299244241,
      "learning_rate": 5e-05,
      "loss": 1.1954,
      "step": 218
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.09445285988148235,
      "learning_rate": 5e-05,
      "loss": 1.25,
      "step": 219
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.11092729662636047,
      "learning_rate": 5e-05,
      "loss": 1.3051,
      "step": 220
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.09774815964460999,
      "learning_rate": 5e-05,
      "loss": 1.2498,
      "step": 221
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.09827733571327216,
      "learning_rate": 5e-05,
      "loss": 1.2697,
      "step": 222
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.08569612523718341,
      "learning_rate": 5e-05,
      "loss": 1.2516,
      "step": 223
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.08163320323139941,
      "learning_rate": 5e-05,
      "loss": 1.2842,
      "step": 224
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.13696947151285582,
      "learning_rate": 5e-05,
      "loss": 1.1765,
      "step": 225
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.09525249130971891,
      "learning_rate": 5e-05,
      "loss": 1.2997,
      "step": 226
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.10987658522507797,
      "learning_rate": 5e-05,
      "loss": 1.2643,
      "step": 227
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.08843542171154735,
      "learning_rate": 5e-05,
      "loss": 1.2358,
      "step": 228
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.08739208171659757,
      "learning_rate": 5e-05,
      "loss": 1.2802,
      "step": 229
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.10011323980243902,
      "learning_rate": 5e-05,
      "loss": 1.1967,
      "step": 230
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.08597111030102798,
      "learning_rate": 5e-05,
      "loss": 1.2302,
      "step": 231
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.09179633281317666,
      "learning_rate": 5e-05,
      "loss": 1.2575,
      "step": 232
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.09528150968513077,
      "learning_rate": 5e-05,
      "loss": 1.2282,
      "step": 233
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.08106734899347699,
      "learning_rate": 5e-05,
      "loss": 1.2606,
      "step": 234
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.0930618107576243,
      "learning_rate": 5e-05,
      "loss": 1.2677,
      "step": 235
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.08303705141327221,
      "learning_rate": 5e-05,
      "loss": 1.3289,
      "step": 236
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.09159494271145804,
      "learning_rate": 5e-05,
      "loss": 1.2534,
      "step": 237
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.09025281712028028,
      "learning_rate": 5e-05,
      "loss": 1.1577,
      "step": 238
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.0886485132543316,
      "learning_rate": 5e-05,
      "loss": 1.1677,
      "step": 239
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.09261389531754648,
      "learning_rate": 5e-05,
      "loss": 1.2752,
      "step": 240
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.08496260150385654,
      "learning_rate": 5e-05,
      "loss": 1.2353,
      "step": 241
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.08356974381967604,
      "learning_rate": 5e-05,
      "loss": 1.1633,
      "step": 242
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.13720586549759095,
      "learning_rate": 5e-05,
      "loss": 1.1981,
      "step": 243
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.08991492270952986,
      "learning_rate": 5e-05,
      "loss": 1.2277,
      "step": 244
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.08280429043868678,
      "learning_rate": 5e-05,
      "loss": 1.2415,
      "step": 245
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.0850877529579615,
      "learning_rate": 5e-05,
      "loss": 1.0818,
      "step": 246
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.09180702494444304,
      "learning_rate": 5e-05,
      "loss": 1.2495,
      "step": 247
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.08742281930183199,
      "learning_rate": 5e-05,
      "loss": 1.309,
      "step": 248
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.09480410539183527,
      "learning_rate": 5e-05,
      "loss": 1.2493,
      "step": 249
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.08864291334102126,
      "learning_rate": 5e-05,
      "loss": 1.1224,
      "step": 250
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.1331463933659882,
      "learning_rate": 5e-05,
      "loss": 1.1975,
      "step": 251
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.08559446666097127,
      "learning_rate": 5e-05,
      "loss": 1.2604,
      "step": 252
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.0873395718049463,
      "learning_rate": 5e-05,
      "loss": 1.1965,
      "step": 253
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.09091016884233578,
      "learning_rate": 5e-05,
      "loss": 1.2809,
      "step": 254
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.07786084061903843,
      "learning_rate": 5e-05,
      "loss": 1.209,
      "step": 255
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.10081388065490703,
      "learning_rate": 5e-05,
      "loss": 1.3263,
      "step": 256
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.10082059674988177,
      "learning_rate": 5e-05,
      "loss": 1.2148,
      "step": 257
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.08564770363821494,
      "learning_rate": 5e-05,
      "loss": 1.3174,
      "step": 258
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.0952758942019198,
      "learning_rate": 5e-05,
      "loss": 1.2204,
      "step": 259
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.09881073855543142,
      "learning_rate": 5e-05,
      "loss": 1.2996,
      "step": 260
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.08733032423974088,
      "learning_rate": 5e-05,
      "loss": 1.2173,
      "step": 261
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.11515922448818783,
      "learning_rate": 5e-05,
      "loss": 1.2242,
      "step": 262
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.09177119070282434,
      "learning_rate": 5e-05,
      "loss": 1.2302,
      "step": 263
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.10216888435274363,
      "learning_rate": 5e-05,
      "loss": 1.2541,
      "step": 264
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.0944990608652097,
      "learning_rate": 5e-05,
      "loss": 1.1954,
      "step": 265
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.09399366717246797,
      "learning_rate": 5e-05,
      "loss": 1.3233,
      "step": 266
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.08753966644581422,
      "learning_rate": 5e-05,
      "loss": 1.2376,
      "step": 267
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.08766716380581922,
      "learning_rate": 5e-05,
      "loss": 1.2428,
      "step": 268
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.09700285494711312,
      "learning_rate": 5e-05,
      "loss": 1.2304,
      "step": 269
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.10359687500650869,
      "learning_rate": 5e-05,
      "loss": 1.2355,
      "step": 270
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.09285186919480592,
      "learning_rate": 5e-05,
      "loss": 1.2518,
      "step": 271
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.08843497139723314,
      "learning_rate": 5e-05,
      "loss": 1.2243,
      "step": 272
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.09033544598942958,
      "learning_rate": 5e-05,
      "loss": 1.1521,
      "step": 273
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.08935014610866102,
      "learning_rate": 5e-05,
      "loss": 1.2891,
      "step": 274
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.08877209475664807,
      "learning_rate": 5e-05,
      "loss": 1.2338,
      "step": 275
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.08620882239728929,
      "learning_rate": 5e-05,
      "loss": 1.3411,
      "step": 276
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.09866190499148263,
      "learning_rate": 5e-05,
      "loss": 1.2749,
      "step": 277
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.08740411789029733,
      "learning_rate": 5e-05,
      "loss": 1.2063,
      "step": 278
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.08539683234832028,
      "learning_rate": 5e-05,
      "loss": 1.1568,
      "step": 279
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.10362328643593488,
      "learning_rate": 5e-05,
      "loss": 1.1842,
      "step": 280
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.08632925887920927,
      "learning_rate": 5e-05,
      "loss": 1.2825,
      "step": 281
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.1474505092935928,
      "learning_rate": 5e-05,
      "loss": 1.1881,
      "step": 282
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.09000910585705812,
      "learning_rate": 5e-05,
      "loss": 1.2739,
      "step": 283
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.09833682566759666,
      "learning_rate": 5e-05,
      "loss": 1.1984,
      "step": 284
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.08079206912854661,
      "learning_rate": 5e-05,
      "loss": 1.2278,
      "step": 285
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.09010068492829859,
      "learning_rate": 5e-05,
      "loss": 1.2837,
      "step": 286
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.09983988726064333,
      "learning_rate": 5e-05,
      "loss": 1.2364,
      "step": 287
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.1949319967540023,
      "learning_rate": 5e-05,
      "loss": 1.2683,
      "step": 288
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.08987585052214384,
      "learning_rate": 5e-05,
      "loss": 1.1786,
      "step": 289
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.08979447515949317,
      "learning_rate": 5e-05,
      "loss": 1.2406,
      "step": 290
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.0868775798788883,
      "learning_rate": 5e-05,
      "loss": 1.1654,
      "step": 291
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.08790675919121381,
      "learning_rate": 5e-05,
      "loss": 1.3515,
      "step": 292
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.094346400666408,
      "learning_rate": 5e-05,
      "loss": 1.2509,
      "step": 293
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.18108569024807403,
      "learning_rate": 5e-05,
      "loss": 1.1853,
      "step": 294
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.08669665678623893,
      "learning_rate": 5e-05,
      "loss": 1.2177,
      "step": 295
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.09400313374318035,
      "learning_rate": 5e-05,
      "loss": 1.2741,
      "step": 296
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.08596356200590288,
      "learning_rate": 5e-05,
      "loss": 1.3281,
      "step": 297
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.0897491130014772,
      "learning_rate": 5e-05,
      "loss": 1.2531,
      "step": 298
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.08733436125874126,
      "learning_rate": 5e-05,
      "loss": 1.3443,
      "step": 299
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.08573312367040001,
      "learning_rate": 5e-05,
      "loss": 1.224,
      "step": 300
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.09557952530027969,
      "learning_rate": 5e-05,
      "loss": 1.1734,
      "step": 301
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.09774252440125493,
      "learning_rate": 5e-05,
      "loss": 1.3189,
      "step": 302
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.09209862644609934,
      "learning_rate": 5e-05,
      "loss": 1.1251,
      "step": 303
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.5862160971018138,
      "learning_rate": 5e-05,
      "loss": 1.2312,
      "step": 304
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.09270307269906179,
      "learning_rate": 5e-05,
      "loss": 1.2261,
      "step": 305
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.09279760165281023,
      "learning_rate": 5e-05,
      "loss": 1.2397,
      "step": 306
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.09814505877494192,
      "learning_rate": 5e-05,
      "loss": 1.2174,
      "step": 307
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.0990096436993457,
      "learning_rate": 5e-05,
      "loss": 1.2312,
      "step": 308
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.0829754840596578,
      "learning_rate": 5e-05,
      "loss": 1.1931,
      "step": 309
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.39215539694720825,
      "learning_rate": 5e-05,
      "loss": 1.2053,
      "step": 310
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.09334861604699533,
      "learning_rate": 5e-05,
      "loss": 1.2118,
      "step": 311
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.09386393833378456,
      "learning_rate": 5e-05,
      "loss": 1.1864,
      "step": 312
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.09608657479012335,
      "learning_rate": 5e-05,
      "loss": 1.21,
      "step": 313
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.0889092637084613,
      "learning_rate": 5e-05,
      "loss": 1.2773,
      "step": 314
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.08852000900017744,
      "learning_rate": 5e-05,
      "loss": 1.2122,
      "step": 315
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.0906176855815127,
      "learning_rate": 5e-05,
      "loss": 1.2912,
      "step": 316
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.13550666694900487,
      "learning_rate": 5e-05,
      "loss": 1.1409,
      "step": 317
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.20633475665889736,
      "learning_rate": 5e-05,
      "loss": 1.234,
      "step": 318
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.09273369896241038,
      "learning_rate": 5e-05,
      "loss": 1.2523,
      "step": 319
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.09021179515999266,
      "learning_rate": 5e-05,
      "loss": 1.1997,
      "step": 320
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.11573990924013423,
      "learning_rate": 5e-05,
      "loss": 1.2277,
      "step": 321
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.11133888827055353,
      "learning_rate": 5e-05,
      "loss": 1.2349,
      "step": 322
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.09036884546944374,
      "learning_rate": 5e-05,
      "loss": 1.2692,
      "step": 323
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.09273460183617792,
      "learning_rate": 5e-05,
      "loss": 1.2262,
      "step": 324
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.0897203674321421,
      "learning_rate": 5e-05,
      "loss": 1.2686,
      "step": 325
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.08586164598598854,
      "learning_rate": 5e-05,
      "loss": 1.2992,
      "step": 326
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.0876429588090545,
      "learning_rate": 5e-05,
      "loss": 1.1948,
      "step": 327
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.08454254473801266,
      "learning_rate": 5e-05,
      "loss": 1.2082,
      "step": 328
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.10205281527688667,
      "learning_rate": 5e-05,
      "loss": 1.247,
      "step": 329
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.1241707532303333,
      "learning_rate": 5e-05,
      "loss": 1.2656,
      "step": 330
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.09014618495881649,
      "learning_rate": 5e-05,
      "loss": 1.3096,
      "step": 331
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.09124011462605543,
      "learning_rate": 5e-05,
      "loss": 1.2806,
      "step": 332
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.09168935573514018,
      "learning_rate": 5e-05,
      "loss": 1.2553,
      "step": 333
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.08620339663683575,
      "learning_rate": 5e-05,
      "loss": 1.1868,
      "step": 334
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.08924777077687464,
      "learning_rate": 5e-05,
      "loss": 1.2245,
      "step": 335
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.10178521535423679,
      "learning_rate": 5e-05,
      "loss": 1.3737,
      "step": 336
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.09398893654170977,
      "learning_rate": 5e-05,
      "loss": 1.2885,
      "step": 337
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.08729984124548136,
      "learning_rate": 5e-05,
      "loss": 1.2033,
      "step": 338
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.08649677383098985,
      "learning_rate": 5e-05,
      "loss": 1.3026,
      "step": 339
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.09231926812728508,
      "learning_rate": 5e-05,
      "loss": 1.2129,
      "step": 340
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.09491184898321346,
      "learning_rate": 5e-05,
      "loss": 1.2036,
      "step": 341
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.0878659924898569,
      "learning_rate": 5e-05,
      "loss": 1.3329,
      "step": 342
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.09791214775489751,
      "learning_rate": 5e-05,
      "loss": 1.2281,
      "step": 343
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.08689911635107521,
      "learning_rate": 5e-05,
      "loss": 1.1929,
      "step": 344
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.1525002969052707,
      "learning_rate": 5e-05,
      "loss": 1.181,
      "step": 345
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.08497046240149246,
      "learning_rate": 5e-05,
      "loss": 1.1695,
      "step": 346
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.09489748293122932,
      "learning_rate": 5e-05,
      "loss": 1.239,
      "step": 347
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.08258793688853842,
      "learning_rate": 5e-05,
      "loss": 1.2295,
      "step": 348
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.08796622630175002,
      "learning_rate": 5e-05,
      "loss": 1.2632,
      "step": 349
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.08831850516260249,
      "learning_rate": 5e-05,
      "loss": 1.2755,
      "step": 350
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.0910930028581069,
      "learning_rate": 5e-05,
      "loss": 1.292,
      "step": 351
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.11500036507032467,
      "learning_rate": 5e-05,
      "loss": 1.3629,
      "step": 352
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.11617820145471644,
      "learning_rate": 5e-05,
      "loss": 1.2841,
      "step": 353
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.08536448061894295,
      "learning_rate": 5e-05,
      "loss": 1.2707,
      "step": 354
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.08905101614762531,
      "learning_rate": 5e-05,
      "loss": 1.2845,
      "step": 355
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.09715136566493858,
      "learning_rate": 5e-05,
      "loss": 1.1882,
      "step": 356
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.08700238865941963,
      "learning_rate": 5e-05,
      "loss": 1.218,
      "step": 357
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.08471677447492601,
      "learning_rate": 5e-05,
      "loss": 1.267,
      "step": 358
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.10297351790993844,
      "learning_rate": 5e-05,
      "loss": 1.2394,
      "step": 359
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.09972387244753816,
      "learning_rate": 5e-05,
      "loss": 1.2333,
      "step": 360
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.09585641462137544,
      "learning_rate": 5e-05,
      "loss": 1.1838,
      "step": 361
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.09222648513487403,
      "learning_rate": 5e-05,
      "loss": 1.1864,
      "step": 362
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.10905085748487696,
      "learning_rate": 5e-05,
      "loss": 1.2761,
      "step": 363
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.0870480307132673,
      "learning_rate": 5e-05,
      "loss": 1.1832,
      "step": 364
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.09611971365786509,
      "learning_rate": 5e-05,
      "loss": 1.2055,
      "step": 365
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.08708476499588201,
      "learning_rate": 5e-05,
      "loss": 1.2615,
      "step": 366
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.08627345445970362,
      "learning_rate": 5e-05,
      "loss": 1.2535,
      "step": 367
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.15348060051465828,
      "learning_rate": 5e-05,
      "loss": 1.2564,
      "step": 368
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.08297376468665693,
      "learning_rate": 5e-05,
      "loss": 1.2254,
      "step": 369
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.09508719239018505,
      "learning_rate": 5e-05,
      "loss": 1.2934,
      "step": 370
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.12194038273230035,
      "learning_rate": 5e-05,
      "loss": 1.2128,
      "step": 371
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.11423944805152593,
      "learning_rate": 5e-05,
      "loss": 1.2313,
      "step": 372
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.09659870039819161,
      "learning_rate": 5e-05,
      "loss": 1.3193,
      "step": 373
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.10532303440785686,
      "learning_rate": 5e-05,
      "loss": 1.1658,
      "step": 374
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.09396037558006054,
      "learning_rate": 5e-05,
      "loss": 1.3109,
      "step": 375
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.08646485393289115,
      "learning_rate": 5e-05,
      "loss": 1.234,
      "step": 376
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.6808951630234666,
      "learning_rate": 5e-05,
      "loss": 1.2478,
      "step": 377
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.09923824159858374,
      "learning_rate": 5e-05,
      "loss": 1.2106,
      "step": 378
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.09179741428225503,
      "learning_rate": 5e-05,
      "loss": 1.2459,
      "step": 379
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.08445702707658428,
      "learning_rate": 5e-05,
      "loss": 1.2344,
      "step": 380
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.09014028580273542,
      "learning_rate": 5e-05,
      "loss": 1.2846,
      "step": 381
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.09160934500793338,
      "learning_rate": 5e-05,
      "loss": 1.2917,
      "step": 382
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.08807606894331109,
      "learning_rate": 5e-05,
      "loss": 1.2065,
      "step": 383
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.274390352758179,
      "learning_rate": 5e-05,
      "loss": 1.2391,
      "step": 384
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.09427427568172006,
      "learning_rate": 5e-05,
      "loss": 1.2742,
      "step": 385
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.08959931932453016,
      "learning_rate": 5e-05,
      "loss": 1.156,
      "step": 386
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.09111988378067222,
      "learning_rate": 5e-05,
      "loss": 1.263,
      "step": 387
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.09200529039851428,
      "learning_rate": 5e-05,
      "loss": 1.262,
      "step": 388
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.10735809551883739,
      "learning_rate": 5e-05,
      "loss": 1.1889,
      "step": 389
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.0949718786848268,
      "learning_rate": 5e-05,
      "loss": 1.2839,
      "step": 390
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.0961142978717631,
      "learning_rate": 5e-05,
      "loss": 1.1699,
      "step": 391
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.09605304671582335,
      "learning_rate": 5e-05,
      "loss": 1.2185,
      "step": 392
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.09513429121879642,
      "learning_rate": 5e-05,
      "loss": 1.145,
      "step": 393
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.12298501280152162,
      "learning_rate": 5e-05,
      "loss": 1.2845,
      "step": 394
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.09036302179963046,
      "learning_rate": 5e-05,
      "loss": 1.2965,
      "step": 395
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.09264349991284292,
      "learning_rate": 5e-05,
      "loss": 1.2258,
      "step": 396
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.08976172362633462,
      "learning_rate": 5e-05,
      "loss": 1.1609,
      "step": 397
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.08993401888120962,
      "learning_rate": 5e-05,
      "loss": 1.132,
      "step": 398
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.1062719885812111,
      "learning_rate": 5e-05,
      "loss": 1.2533,
      "step": 399
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.09830204964453033,
      "learning_rate": 5e-05,
      "loss": 1.2583,
      "step": 400
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.23416064668117736,
      "learning_rate": 5e-05,
      "loss": 1.2447,
      "step": 401
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.12406687473928911,
      "learning_rate": 5e-05,
      "loss": 1.175,
      "step": 402
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.09451579111057025,
      "learning_rate": 5e-05,
      "loss": 1.2168,
      "step": 403
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.10898561049412687,
      "learning_rate": 5e-05,
      "loss": 1.1535,
      "step": 404
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.0925113621388591,
      "learning_rate": 5e-05,
      "loss": 1.1484,
      "step": 405
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.15223288687881376,
      "learning_rate": 5e-05,
      "loss": 1.1294,
      "step": 406
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.09556984444055779,
      "learning_rate": 5e-05,
      "loss": 1.2794,
      "step": 407
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.09785022213423893,
      "learning_rate": 5e-05,
      "loss": 1.176,
      "step": 408
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.10533900637109996,
      "learning_rate": 5e-05,
      "loss": 1.2352,
      "step": 409
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.10272929322025146,
      "learning_rate": 5e-05,
      "loss": 1.2611,
      "step": 410
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.10061997728558097,
      "learning_rate": 5e-05,
      "loss": 1.1915,
      "step": 411
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.10088267664927592,
      "learning_rate": 5e-05,
      "loss": 1.2349,
      "step": 412
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.09374930987913425,
      "learning_rate": 5e-05,
      "loss": 1.185,
      "step": 413
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.11521303955050079,
      "learning_rate": 5e-05,
      "loss": 1.2758,
      "step": 414
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.10178700476680842,
      "learning_rate": 5e-05,
      "loss": 1.2672,
      "step": 415
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.09804258149927716,
      "learning_rate": 5e-05,
      "loss": 1.1785,
      "step": 416
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.1052279442753329,
      "learning_rate": 5e-05,
      "loss": 1.2223,
      "step": 417
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.18317490027472128,
      "learning_rate": 5e-05,
      "loss": 1.2159,
      "step": 418
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.08991206745450332,
      "learning_rate": 5e-05,
      "loss": 1.2249,
      "step": 419
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.10437348818281557,
      "learning_rate": 5e-05,
      "loss": 1.2469,
      "step": 420
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.12639935743830863,
      "learning_rate": 5e-05,
      "loss": 1.1964,
      "step": 421
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.17550772921542432,
      "learning_rate": 5e-05,
      "loss": 1.2546,
      "step": 422
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.10916765791086883,
      "learning_rate": 5e-05,
      "loss": 1.287,
      "step": 423
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.11195095125404325,
      "learning_rate": 5e-05,
      "loss": 1.1399,
      "step": 424
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.10464162033679592,
      "learning_rate": 5e-05,
      "loss": 1.252,
      "step": 425
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.1422007878111932,
      "learning_rate": 5e-05,
      "loss": 1.3093,
      "step": 426
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.09646644642726107,
      "learning_rate": 5e-05,
      "loss": 1.1038,
      "step": 427
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.11969252954059995,
      "learning_rate": 5e-05,
      "loss": 1.3556,
      "step": 428
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.14302305454050254,
      "learning_rate": 5e-05,
      "loss": 1.253,
      "step": 429
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.1016643997546001,
      "learning_rate": 5e-05,
      "loss": 1.2539,
      "step": 430
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.09740846997917411,
      "learning_rate": 5e-05,
      "loss": 1.1299,
      "step": 431
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.11960995656060532,
      "learning_rate": 5e-05,
      "loss": 1.2244,
      "step": 432
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.13189794138210517,
      "learning_rate": 5e-05,
      "loss": 1.1457,
      "step": 433
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.10424668133969454,
      "learning_rate": 5e-05,
      "loss": 1.1982,
      "step": 434
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.0981321081963098,
      "learning_rate": 5e-05,
      "loss": 1.2044,
      "step": 435
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.09649032177723192,
      "learning_rate": 5e-05,
      "loss": 1.3012,
      "step": 436
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.10150706324371488,
      "learning_rate": 5e-05,
      "loss": 1.3317,
      "step": 437
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.10160318429416466,
      "learning_rate": 5e-05,
      "loss": 1.2627,
      "step": 438
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.0890625144677584,
      "learning_rate": 5e-05,
      "loss": 1.1692,
      "step": 439
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.11171587166184754,
      "learning_rate": 5e-05,
      "loss": 1.2245,
      "step": 440
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.13847591569097098,
      "learning_rate": 5e-05,
      "loss": 1.2836,
      "step": 441
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.09529199853803245,
      "learning_rate": 5e-05,
      "loss": 1.1555,
      "step": 442
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.09678894591057594,
      "learning_rate": 5e-05,
      "loss": 1.1751,
      "step": 443
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.11432300921186853,
      "learning_rate": 5e-05,
      "loss": 1.1568,
      "step": 444
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.08495476342246677,
      "learning_rate": 5e-05,
      "loss": 1.3804,
      "step": 445
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.09547703516468427,
      "learning_rate": 5e-05,
      "loss": 1.2004,
      "step": 446
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.10241446863877374,
      "learning_rate": 5e-05,
      "loss": 1.2716,
      "step": 447
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.10552735100687363,
      "learning_rate": 5e-05,
      "loss": 1.2046,
      "step": 448
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.08432451153889137,
      "learning_rate": 5e-05,
      "loss": 1.2623,
      "step": 449
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.09588923581765316,
      "learning_rate": 5e-05,
      "loss": 1.2843,
      "step": 450
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.09654932304570306,
      "learning_rate": 5e-05,
      "loss": 1.2058,
      "step": 451
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.09891455377934905,
      "learning_rate": 5e-05,
      "loss": 1.3826,
      "step": 452
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.0839148273966323,
      "learning_rate": 5e-05,
      "loss": 1.1561,
      "step": 453
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.09134099897491745,
      "learning_rate": 5e-05,
      "loss": 1.2411,
      "step": 454
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.11136514392856785,
      "learning_rate": 5e-05,
      "loss": 1.3289,
      "step": 455
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.09395579557584285,
      "learning_rate": 5e-05,
      "loss": 1.242,
      "step": 456
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.08882218477068878,
      "learning_rate": 5e-05,
      "loss": 1.2912,
      "step": 457
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.09720463330678311,
      "learning_rate": 5e-05,
      "loss": 1.164,
      "step": 458
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.09536872864789071,
      "learning_rate": 5e-05,
      "loss": 1.3001,
      "step": 459
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.10461146139466083,
      "learning_rate": 5e-05,
      "loss": 1.2665,
      "step": 460
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.09655182371714942,
      "learning_rate": 5e-05,
      "loss": 1.3421,
      "step": 461
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.08707150535037736,
      "learning_rate": 5e-05,
      "loss": 1.1887,
      "step": 462
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.08649148684083302,
      "learning_rate": 5e-05,
      "loss": 1.2537,
      "step": 463
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.08864329898350386,
      "learning_rate": 5e-05,
      "loss": 1.2289,
      "step": 464
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.08237439158374964,
      "learning_rate": 5e-05,
      "loss": 1.3317,
      "step": 465
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.08672733104514327,
      "learning_rate": 5e-05,
      "loss": 1.2911,
      "step": 466
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.0827910775243905,
      "learning_rate": 5e-05,
      "loss": 1.1791,
      "step": 467
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.1106203002142719,
      "learning_rate": 5e-05,
      "loss": 1.2744,
      "step": 468
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.0901945367612223,
      "learning_rate": 5e-05,
      "loss": 1.3298,
      "step": 469
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.09230318467875029,
      "learning_rate": 5e-05,
      "loss": 1.2271,
      "step": 470
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.09521443609898626,
      "learning_rate": 5e-05,
      "loss": 1.1468,
      "step": 471
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.0942535507748726,
      "learning_rate": 5e-05,
      "loss": 1.1731,
      "step": 472
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.09201271955453857,
      "learning_rate": 5e-05,
      "loss": 1.2212,
      "step": 473
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.08128850455351448,
      "learning_rate": 5e-05,
      "loss": 1.2136,
      "step": 474
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.10620042740932711,
      "learning_rate": 5e-05,
      "loss": 1.1852,
      "step": 475
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.0915936719583377,
      "learning_rate": 5e-05,
      "loss": 1.268,
      "step": 476
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.09057021272981364,
      "learning_rate": 5e-05,
      "loss": 1.1531,
      "step": 477
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.0883804485429764,
      "learning_rate": 5e-05,
      "loss": 1.3008,
      "step": 478
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.09701027219637508,
      "learning_rate": 5e-05,
      "loss": 1.3001,
      "step": 479
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.0992623444273281,
      "learning_rate": 5e-05,
      "loss": 1.3357,
      "step": 480
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.0928861673772843,
      "learning_rate": 5e-05,
      "loss": 1.1852,
      "step": 481
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.12092322563789983,
      "learning_rate": 5e-05,
      "loss": 1.2453,
      "step": 482
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.09600770042201742,
      "learning_rate": 5e-05,
      "loss": 1.255,
      "step": 483
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.11193934781672676,
      "learning_rate": 5e-05,
      "loss": 1.2766,
      "step": 484
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.09242666432521533,
      "learning_rate": 5e-05,
      "loss": 1.2101,
      "step": 485
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.09568248927731744,
      "learning_rate": 5e-05,
      "loss": 1.0978,
      "step": 486
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.08582432543883815,
      "learning_rate": 5e-05,
      "loss": 1.1554,
      "step": 487
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.09485167361850859,
      "learning_rate": 5e-05,
      "loss": 1.2416,
      "step": 488
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.09022911381360664,
      "learning_rate": 5e-05,
      "loss": 1.1792,
      "step": 489
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.10119753928947335,
      "learning_rate": 5e-05,
      "loss": 1.2419,
      "step": 490
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.09273871341221016,
      "learning_rate": 5e-05,
      "loss": 1.2451,
      "step": 491
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.12935815409522153,
      "learning_rate": 5e-05,
      "loss": 1.2029,
      "step": 492
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.08332668684798196,
      "learning_rate": 5e-05,
      "loss": 1.2665,
      "step": 493
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.09306656364478559,
      "learning_rate": 5e-05,
      "loss": 1.1738,
      "step": 494
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.0969375533472487,
      "learning_rate": 5e-05,
      "loss": 1.3214,
      "step": 495
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.08338803886851001,
      "learning_rate": 5e-05,
      "loss": 1.2015,
      "step": 496
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.09456316110967951,
      "learning_rate": 5e-05,
      "loss": 1.1432,
      "step": 497
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.08693678933618375,
      "learning_rate": 5e-05,
      "loss": 1.1972,
      "step": 498
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.09780253129721403,
      "learning_rate": 5e-05,
      "loss": 1.0717,
      "step": 499
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.10569441197996789,
      "learning_rate": 5e-05,
      "loss": 1.2729,
      "step": 500
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.10286492143515646,
      "learning_rate": 5e-05,
      "loss": 1.234,
      "step": 501
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.0910185735041866,
      "learning_rate": 5e-05,
      "loss": 1.1907,
      "step": 502
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.09275664617617299,
      "learning_rate": 5e-05,
      "loss": 1.2794,
      "step": 503
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.09128487009140039,
      "learning_rate": 5e-05,
      "loss": 1.2783,
      "step": 504
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.09904955332557805,
      "learning_rate": 5e-05,
      "loss": 1.1796,
      "step": 505
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.08925947605079272,
      "learning_rate": 5e-05,
      "loss": 1.2086,
      "step": 506
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.22704931044503435,
      "learning_rate": 5e-05,
      "loss": 1.3014,
      "step": 507
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.09220561130196987,
      "learning_rate": 5e-05,
      "loss": 1.1986,
      "step": 508
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.10748878494268495,
      "learning_rate": 5e-05,
      "loss": 1.2742,
      "step": 509
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.09099677912935496,
      "learning_rate": 5e-05,
      "loss": 1.1609,
      "step": 510
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.09169039515261505,
      "learning_rate": 5e-05,
      "loss": 1.2536,
      "step": 511
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.08524246790215907,
      "learning_rate": 5e-05,
      "loss": 1.206,
      "step": 512
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.17719467129480335,
      "learning_rate": 5e-05,
      "loss": 1.2534,
      "step": 513
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.09519313583555802,
      "learning_rate": 5e-05,
      "loss": 1.2505,
      "step": 514
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.09352280046231452,
      "learning_rate": 5e-05,
      "loss": 1.1092,
      "step": 515
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.0951263810551215,
      "learning_rate": 5e-05,
      "loss": 1.2591,
      "step": 516
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.09838751970931506,
      "learning_rate": 5e-05,
      "loss": 1.2617,
      "step": 517
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.0948229297871239,
      "learning_rate": 5e-05,
      "loss": 1.2743,
      "step": 518
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.0945440215643022,
      "learning_rate": 5e-05,
      "loss": 1.331,
      "step": 519
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.11637647970404298,
      "learning_rate": 5e-05,
      "loss": 1.2419,
      "step": 520
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.08932495455100235,
      "learning_rate": 5e-05,
      "loss": 1.2856,
      "step": 521
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.08908148234874731,
      "learning_rate": 5e-05,
      "loss": 1.2732,
      "step": 522
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.09684259375493993,
      "learning_rate": 5e-05,
      "loss": 1.2399,
      "step": 523
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.09624041473631541,
      "learning_rate": 5e-05,
      "loss": 1.2203,
      "step": 524
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.09789307170040781,
      "learning_rate": 5e-05,
      "loss": 1.2056,
      "step": 525
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.09270663219504559,
      "learning_rate": 5e-05,
      "loss": 1.2565,
      "step": 526
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.10274518440927816,
      "learning_rate": 5e-05,
      "loss": 1.2024,
      "step": 527
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.08963594413715927,
      "learning_rate": 5e-05,
      "loss": 1.3096,
      "step": 528
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.09075285786227485,
      "learning_rate": 5e-05,
      "loss": 1.13,
      "step": 529
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.0938384051794185,
      "learning_rate": 5e-05,
      "loss": 1.2874,
      "step": 530
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.08974315394544331,
      "learning_rate": 5e-05,
      "loss": 1.1766,
      "step": 531
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.10208489459703247,
      "learning_rate": 5e-05,
      "loss": 1.3835,
      "step": 532
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.11970068038104684,
      "learning_rate": 5e-05,
      "loss": 1.2526,
      "step": 533
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.09175875498268529,
      "learning_rate": 5e-05,
      "loss": 1.2134,
      "step": 534
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.16304765015201575,
      "learning_rate": 5e-05,
      "loss": 1.1869,
      "step": 535
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.0934152696898247,
      "learning_rate": 5e-05,
      "loss": 1.1683,
      "step": 536
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.0958139159703967,
      "learning_rate": 5e-05,
      "loss": 1.242,
      "step": 537
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.08766778926036489,
      "learning_rate": 5e-05,
      "loss": 1.2168,
      "step": 538
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.08617009411449289,
      "learning_rate": 5e-05,
      "loss": 1.1738,
      "step": 539
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.09322306508154198,
      "learning_rate": 5e-05,
      "loss": 1.2388,
      "step": 540
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.08797703950745679,
      "learning_rate": 5e-05,
      "loss": 1.2238,
      "step": 541
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.21576889587028528,
      "learning_rate": 5e-05,
      "loss": 1.3287,
      "step": 542
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.10736353355137965,
      "learning_rate": 5e-05,
      "loss": 1.1682,
      "step": 543
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.10113374100373243,
      "learning_rate": 5e-05,
      "loss": 1.3353,
      "step": 544
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.09712275336017097,
      "learning_rate": 5e-05,
      "loss": 1.2325,
      "step": 545
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.09476641064653353,
      "learning_rate": 5e-05,
      "loss": 1.2156,
      "step": 546
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.0965186360988305,
      "learning_rate": 5e-05,
      "loss": 1.2718,
      "step": 547
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.09150452088005474,
      "learning_rate": 5e-05,
      "loss": 1.2425,
      "step": 548
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.09151462508356896,
      "learning_rate": 5e-05,
      "loss": 1.2619,
      "step": 549
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.09072441382198769,
      "learning_rate": 5e-05,
      "loss": 1.2418,
      "step": 550
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.09455576398670734,
      "learning_rate": 5e-05,
      "loss": 1.2499,
      "step": 551
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.11715209715835109,
      "learning_rate": 5e-05,
      "loss": 1.2512,
      "step": 552
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.09015069313677429,
      "learning_rate": 5e-05,
      "loss": 1.2221,
      "step": 553
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.09099730119951754,
      "learning_rate": 5e-05,
      "loss": 1.3887,
      "step": 554
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.12008260193989902,
      "learning_rate": 5e-05,
      "loss": 1.2303,
      "step": 555
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.0954853601698297,
      "learning_rate": 5e-05,
      "loss": 1.3012,
      "step": 556
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.09033149982015323,
      "learning_rate": 5e-05,
      "loss": 1.198,
      "step": 557
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.08959245434326961,
      "learning_rate": 5e-05,
      "loss": 1.2328,
      "step": 558
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.09406315705504768,
      "learning_rate": 5e-05,
      "loss": 1.1844,
      "step": 559
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.09872861081261884,
      "learning_rate": 5e-05,
      "loss": 1.3282,
      "step": 560
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.09041718087545901,
      "learning_rate": 5e-05,
      "loss": 1.1816,
      "step": 561
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.09627804804863976,
      "learning_rate": 5e-05,
      "loss": 1.2859,
      "step": 562
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.09321543397429712,
      "learning_rate": 5e-05,
      "loss": 1.1685,
      "step": 563
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.10167814792024299,
      "learning_rate": 5e-05,
      "loss": 1.1443,
      "step": 564
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.08859079919809663,
      "learning_rate": 5e-05,
      "loss": 1.1557,
      "step": 565
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.12122065680973139,
      "learning_rate": 5e-05,
      "loss": 1.2822,
      "step": 566
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.1332255815827339,
      "learning_rate": 5e-05,
      "loss": 1.3126,
      "step": 567
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.09323771362490287,
      "learning_rate": 5e-05,
      "loss": 1.2537,
      "step": 568
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.09042911726751882,
      "learning_rate": 5e-05,
      "loss": 1.2238,
      "step": 569
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.09452288700761455,
      "learning_rate": 5e-05,
      "loss": 1.2769,
      "step": 570
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.11626814151913445,
      "learning_rate": 5e-05,
      "loss": 1.228,
      "step": 571
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.1002843815686134,
      "learning_rate": 5e-05,
      "loss": 1.1853,
      "step": 572
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.08672825325069114,
      "learning_rate": 5e-05,
      "loss": 1.2448,
      "step": 573
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.09913534884868135,
      "learning_rate": 5e-05,
      "loss": 1.1606,
      "step": 574
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.09593606249520897,
      "learning_rate": 5e-05,
      "loss": 1.2264,
      "step": 575
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.12973964748908556,
      "learning_rate": 5e-05,
      "loss": 1.2514,
      "step": 576
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.09657199392730052,
      "learning_rate": 5e-05,
      "loss": 1.2813,
      "step": 577
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.11761070678818837,
      "learning_rate": 5e-05,
      "loss": 1.1241,
      "step": 578
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.14490021925724572,
      "learning_rate": 5e-05,
      "loss": 1.1771,
      "step": 579
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.09146456504920918,
      "learning_rate": 5e-05,
      "loss": 1.2572,
      "step": 580
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.0932619127350976,
      "learning_rate": 5e-05,
      "loss": 1.2448,
      "step": 581
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.12824831041809026,
      "learning_rate": 5e-05,
      "loss": 1.2898,
      "step": 582
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.09178186690319479,
      "learning_rate": 5e-05,
      "loss": 1.2588,
      "step": 583
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.08677081631609211,
      "learning_rate": 5e-05,
      "loss": 1.228,
      "step": 584
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.09087600851766289,
      "learning_rate": 5e-05,
      "loss": 1.2739,
      "step": 585
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.08937232399362025,
      "learning_rate": 5e-05,
      "loss": 1.3397,
      "step": 586
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.09181498093360832,
      "learning_rate": 5e-05,
      "loss": 1.2337,
      "step": 587
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.08660421458268343,
      "learning_rate": 5e-05,
      "loss": 1.3066,
      "step": 588
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.09405547367950175,
      "learning_rate": 5e-05,
      "loss": 1.1865,
      "step": 589
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.10008203744489265,
      "learning_rate": 5e-05,
      "loss": 1.2958,
      "step": 590
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.08623872911953744,
      "learning_rate": 5e-05,
      "loss": 1.2459,
      "step": 591
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.08620542665467425,
      "learning_rate": 5e-05,
      "loss": 1.196,
      "step": 592
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.09154759789920437,
      "learning_rate": 5e-05,
      "loss": 1.2083,
      "step": 593
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.13411544381515045,
      "learning_rate": 5e-05,
      "loss": 1.2967,
      "step": 594
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.08207561526451417,
      "learning_rate": 5e-05,
      "loss": 1.3127,
      "step": 595
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.07989637752894571,
      "learning_rate": 5e-05,
      "loss": 1.2393,
      "step": 596
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.15303683065994178,
      "learning_rate": 5e-05,
      "loss": 1.2035,
      "step": 597
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.21126660740808512,
      "learning_rate": 5e-05,
      "loss": 1.2646,
      "step": 598
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.09235709112995891,
      "learning_rate": 5e-05,
      "loss": 1.1644,
      "step": 599
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.09107701199389144,
      "learning_rate": 5e-05,
      "loss": 1.2198,
      "step": 600
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.18076245165187252,
      "learning_rate": 5e-05,
      "loss": 1.2244,
      "step": 601
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.08540692042816288,
      "learning_rate": 5e-05,
      "loss": 1.2701,
      "step": 602
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.08928729191853955,
      "learning_rate": 5e-05,
      "loss": 1.182,
      "step": 603
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.1297085133397325,
      "learning_rate": 5e-05,
      "loss": 1.293,
      "step": 604
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.08886073686153889,
      "learning_rate": 5e-05,
      "loss": 1.2193,
      "step": 605
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.11184508387835462,
      "learning_rate": 5e-05,
      "loss": 1.3524,
      "step": 606
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.28617427730766865,
      "learning_rate": 5e-05,
      "loss": 1.2289,
      "step": 607
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.08913132440783965,
      "learning_rate": 5e-05,
      "loss": 1.276,
      "step": 608
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.09371699908947943,
      "learning_rate": 5e-05,
      "loss": 1.2011,
      "step": 609
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.08915675529087298,
      "learning_rate": 5e-05,
      "loss": 1.2712,
      "step": 610
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.09515513145486774,
      "learning_rate": 5e-05,
      "loss": 1.2654,
      "step": 611
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.09724889297080566,
      "learning_rate": 5e-05,
      "loss": 1.237,
      "step": 612
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.08500359571002307,
      "learning_rate": 5e-05,
      "loss": 1.2901,
      "step": 613
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.09873900572833598,
      "learning_rate": 5e-05,
      "loss": 1.2974,
      "step": 614
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.10190340329060169,
      "learning_rate": 5e-05,
      "loss": 1.2078,
      "step": 615
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.09278816113127145,
      "learning_rate": 5e-05,
      "loss": 1.2899,
      "step": 616
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.09368617495170674,
      "learning_rate": 5e-05,
      "loss": 1.1452,
      "step": 617
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.09206700755880094,
      "learning_rate": 5e-05,
      "loss": 1.2304,
      "step": 618
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.09539147296869752,
      "learning_rate": 5e-05,
      "loss": 1.1477,
      "step": 619
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.0943090483093122,
      "learning_rate": 5e-05,
      "loss": 1.3099,
      "step": 620
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.09840131619711731,
      "learning_rate": 5e-05,
      "loss": 1.2777,
      "step": 621
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.1017436445672807,
      "learning_rate": 5e-05,
      "loss": 1.3135,
      "step": 622
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.09353027935319465,
      "learning_rate": 5e-05,
      "loss": 1.2939,
      "step": 623
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.0992666673551347,
      "learning_rate": 5e-05,
      "loss": 1.1588,
      "step": 624
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.09621536648270135,
      "learning_rate": 5e-05,
      "loss": 1.1561,
      "step": 625
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.1803848705385315,
      "learning_rate": 5e-05,
      "loss": 1.2266,
      "step": 626
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.09940497512751059,
      "learning_rate": 5e-05,
      "loss": 1.1527,
      "step": 627
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.22301331748075162,
      "learning_rate": 5e-05,
      "loss": 1.1786,
      "step": 628
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.092299402565119,
      "learning_rate": 5e-05,
      "loss": 1.2165,
      "step": 629
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.08987088544034491,
      "learning_rate": 5e-05,
      "loss": 1.2376,
      "step": 630
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.09467737714738493,
      "learning_rate": 5e-05,
      "loss": 1.0809,
      "step": 631
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.09016867287270872,
      "learning_rate": 5e-05,
      "loss": 1.2832,
      "step": 632
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.09263823621699638,
      "learning_rate": 5e-05,
      "loss": 1.2468,
      "step": 633
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.10845579464729647,
      "learning_rate": 5e-05,
      "loss": 1.1989,
      "step": 634
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.0915070201812124,
      "learning_rate": 5e-05,
      "loss": 1.1566,
      "step": 635
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.10727575446689461,
      "learning_rate": 5e-05,
      "loss": 1.1929,
      "step": 636
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.09880718654639797,
      "learning_rate": 5e-05,
      "loss": 1.2715,
      "step": 637
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.08695192845612108,
      "learning_rate": 5e-05,
      "loss": 1.2251,
      "step": 638
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.13295672913473008,
      "learning_rate": 5e-05,
      "loss": 1.265,
      "step": 639
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.09226160620278051,
      "learning_rate": 5e-05,
      "loss": 1.1655,
      "step": 640
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.08658185721218865,
      "learning_rate": 5e-05,
      "loss": 1.2737,
      "step": 641
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.09485911206032513,
      "learning_rate": 5e-05,
      "loss": 1.3013,
      "step": 642
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.10327747818516794,
      "learning_rate": 5e-05,
      "loss": 1.23,
      "step": 643
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.08875036083861511,
      "learning_rate": 5e-05,
      "loss": 1.3161,
      "step": 644
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.09802151021128591,
      "learning_rate": 5e-05,
      "loss": 1.2579,
      "step": 645
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.09787376381900295,
      "learning_rate": 5e-05,
      "loss": 1.2211,
      "step": 646
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.09293215004126011,
      "learning_rate": 5e-05,
      "loss": 1.2328,
      "step": 647
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.40838285000644514,
      "learning_rate": 5e-05,
      "loss": 1.2187,
      "step": 648
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.09207947832303415,
      "learning_rate": 5e-05,
      "loss": 1.1493,
      "step": 649
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.08581277394743936,
      "learning_rate": 5e-05,
      "loss": 1.2583,
      "step": 650
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.08972806336651389,
      "learning_rate": 5e-05,
      "loss": 1.237,
      "step": 651
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.11051487901082263,
      "learning_rate": 5e-05,
      "loss": 1.1829,
      "step": 652
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.08982255157991624,
      "learning_rate": 5e-05,
      "loss": 1.2128,
      "step": 653
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.14123425840531084,
      "learning_rate": 5e-05,
      "loss": 1.2416,
      "step": 654
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.12880759387579782,
      "learning_rate": 5e-05,
      "loss": 1.2207,
      "step": 655
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.10248050833816658,
      "learning_rate": 5e-05,
      "loss": 1.2631,
      "step": 656
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.08455841358023947,
      "learning_rate": 5e-05,
      "loss": 1.2567,
      "step": 657
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.12583544117745254,
      "learning_rate": 5e-05,
      "loss": 1.1778,
      "step": 658
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.11324965961424767,
      "learning_rate": 5e-05,
      "loss": 1.1386,
      "step": 659
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.09691490439817214,
      "learning_rate": 5e-05,
      "loss": 1.1911,
      "step": 660
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.1072333014220056,
      "learning_rate": 5e-05,
      "loss": 1.1999,
      "step": 661
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.0950265977451683,
      "learning_rate": 5e-05,
      "loss": 1.1978,
      "step": 662
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.0929892818223546,
      "learning_rate": 5e-05,
      "loss": 1.2169,
      "step": 663
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.09469469542770795,
      "learning_rate": 5e-05,
      "loss": 1.2761,
      "step": 664
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.21751987444270846,
      "learning_rate": 5e-05,
      "loss": 1.1807,
      "step": 665
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.08556131295751274,
      "learning_rate": 5e-05,
      "loss": 1.2711,
      "step": 666
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.09282570232212695,
      "learning_rate": 5e-05,
      "loss": 1.1027,
      "step": 667
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.08955806312088513,
      "learning_rate": 5e-05,
      "loss": 1.2454,
      "step": 668
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.0845899407602786,
      "learning_rate": 5e-05,
      "loss": 1.1794,
      "step": 669
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.09356526088253121,
      "learning_rate": 5e-05,
      "loss": 1.2057,
      "step": 670
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.10643714572041506,
      "learning_rate": 5e-05,
      "loss": 1.2645,
      "step": 671
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.09507456774404864,
      "learning_rate": 5e-05,
      "loss": 1.3194,
      "step": 672
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.2056777048175019,
      "learning_rate": 5e-05,
      "loss": 1.2427,
      "step": 673
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.10110036392248033,
      "learning_rate": 5e-05,
      "loss": 1.2327,
      "step": 674
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.13002768789325456,
      "learning_rate": 5e-05,
      "loss": 1.1952,
      "step": 675
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.10033679290166875,
      "learning_rate": 5e-05,
      "loss": 1.2775,
      "step": 676
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.09391553624024601,
      "learning_rate": 5e-05,
      "loss": 1.2047,
      "step": 677
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.09611763781707118,
      "learning_rate": 5e-05,
      "loss": 1.102,
      "step": 678
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.10562455047638551,
      "learning_rate": 5e-05,
      "loss": 1.29,
      "step": 679
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.09690049590453258,
      "learning_rate": 5e-05,
      "loss": 1.1889,
      "step": 680
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.09350339672467371,
      "learning_rate": 5e-05,
      "loss": 1.2132,
      "step": 681
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.09794819805073643,
      "learning_rate": 5e-05,
      "loss": 1.1108,
      "step": 682
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.09235058797869976,
      "learning_rate": 5e-05,
      "loss": 1.2115,
      "step": 683
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.09624917985554393,
      "learning_rate": 5e-05,
      "loss": 1.3051,
      "step": 684
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.31721839996806295,
      "learning_rate": 5e-05,
      "loss": 1.2784,
      "step": 685
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.09556114849876468,
      "learning_rate": 5e-05,
      "loss": 1.2236,
      "step": 686
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.09368485871183255,
      "learning_rate": 5e-05,
      "loss": 1.1814,
      "step": 687
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.09802703013849685,
      "learning_rate": 5e-05,
      "loss": 1.2432,
      "step": 688
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.10087628906498335,
      "learning_rate": 5e-05,
      "loss": 1.2858,
      "step": 689
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.09413510463018016,
      "learning_rate": 5e-05,
      "loss": 1.3659,
      "step": 690
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.10392111027868062,
      "learning_rate": 5e-05,
      "loss": 1.1542,
      "step": 691
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.0906566542543004,
      "learning_rate": 5e-05,
      "loss": 1.2487,
      "step": 692
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.08715045299668721,
      "learning_rate": 5e-05,
      "loss": 1.2352,
      "step": 693
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.12929957216629626,
      "learning_rate": 5e-05,
      "loss": 1.3195,
      "step": 694
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.10703264606883131,
      "learning_rate": 5e-05,
      "loss": 1.2241,
      "step": 695
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.10154138617521206,
      "learning_rate": 5e-05,
      "loss": 1.2146,
      "step": 696
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.1179671151272554,
      "learning_rate": 5e-05,
      "loss": 1.2687,
      "step": 697
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.14179304986899552,
      "learning_rate": 5e-05,
      "loss": 1.1992,
      "step": 698
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.10046483798948673,
      "learning_rate": 5e-05,
      "loss": 1.3317,
      "step": 699
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.10141024718873726,
      "learning_rate": 5e-05,
      "loss": 1.2044,
      "step": 700
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.09932798087483034,
      "learning_rate": 5e-05,
      "loss": 1.3029,
      "step": 701
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.17373024837647805,
      "learning_rate": 5e-05,
      "loss": 1.2626,
      "step": 702
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.10303981160118214,
      "learning_rate": 5e-05,
      "loss": 1.1873,
      "step": 703
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.09963180786967149,
      "learning_rate": 5e-05,
      "loss": 1.2595,
      "step": 704
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.12652797136155272,
      "learning_rate": 5e-05,
      "loss": 1.3829,
      "step": 705
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.1012165700917821,
      "learning_rate": 5e-05,
      "loss": 1.1874,
      "step": 706
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.10453598557896276,
      "learning_rate": 5e-05,
      "loss": 1.3104,
      "step": 707
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.09942899214105919,
      "learning_rate": 5e-05,
      "loss": 1.2672,
      "step": 708
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.15326373835553098,
      "learning_rate": 5e-05,
      "loss": 1.362,
      "step": 709
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.429975024253803,
      "learning_rate": 5e-05,
      "loss": 1.2764,
      "step": 710
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.11153291143807398,
      "learning_rate": 5e-05,
      "loss": 1.2682,
      "step": 711
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.15133533987538889,
      "learning_rate": 5e-05,
      "loss": 1.1378,
      "step": 712
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.25668416002800687,
      "learning_rate": 5e-05,
      "loss": 1.1951,
      "step": 713
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.0963067674586202,
      "learning_rate": 5e-05,
      "loss": 1.2414,
      "step": 714
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.15451942034952437,
      "learning_rate": 5e-05,
      "loss": 1.2113,
      "step": 715
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.09981210233391376,
      "learning_rate": 5e-05,
      "loss": 1.2978,
      "step": 716
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.10076216800241435,
      "learning_rate": 5e-05,
      "loss": 1.2255,
      "step": 717
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.14548778281671867,
      "learning_rate": 5e-05,
      "loss": 1.2835,
      "step": 718
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.1016741952863245,
      "learning_rate": 5e-05,
      "loss": 1.2912,
      "step": 719
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.09960716934644352,
      "learning_rate": 5e-05,
      "loss": 0.9963,
      "step": 720
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.10640237229489667,
      "learning_rate": 5e-05,
      "loss": 1.3254,
      "step": 721
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.10233325113756409,
      "learning_rate": 5e-05,
      "loss": 1.1384,
      "step": 722
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.10014095700336226,
      "learning_rate": 5e-05,
      "loss": 1.1717,
      "step": 723
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.24673393128935722,
      "learning_rate": 5e-05,
      "loss": 1.1833,
      "step": 724
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.1765370153980564,
      "learning_rate": 5e-05,
      "loss": 1.167,
      "step": 725
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.09069059043020448,
      "learning_rate": 5e-05,
      "loss": 1.2299,
      "step": 726
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.09919444575477596,
      "learning_rate": 5e-05,
      "loss": 1.2114,
      "step": 727
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.10624614036476415,
      "learning_rate": 5e-05,
      "loss": 1.2148,
      "step": 728
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.11414826824845992,
      "learning_rate": 5e-05,
      "loss": 1.2473,
      "step": 729
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.09746044971388516,
      "learning_rate": 5e-05,
      "loss": 1.2744,
      "step": 730
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.09264686915487945,
      "learning_rate": 5e-05,
      "loss": 1.2411,
      "step": 731
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.1285248529691951,
      "learning_rate": 5e-05,
      "loss": 1.2455,
      "step": 732
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.10819000040646083,
      "learning_rate": 5e-05,
      "loss": 1.3297,
      "step": 733
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.10741312350360947,
      "learning_rate": 5e-05,
      "loss": 1.2665,
      "step": 734
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.08981878384046382,
      "learning_rate": 5e-05,
      "loss": 1.1661,
      "step": 735
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.09710771553318064,
      "learning_rate": 5e-05,
      "loss": 1.1958,
      "step": 736
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.09834809704812088,
      "learning_rate": 5e-05,
      "loss": 1.1861,
      "step": 737
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.11873488763336909,
      "learning_rate": 5e-05,
      "loss": 1.2457,
      "step": 738
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.4534657268027245,
      "learning_rate": 5e-05,
      "loss": 1.2153,
      "step": 739
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.09197575469543723,
      "learning_rate": 5e-05,
      "loss": 1.233,
      "step": 740
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.09298135208306929,
      "learning_rate": 5e-05,
      "loss": 1.2487,
      "step": 741
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.1002334003010323,
      "learning_rate": 5e-05,
      "loss": 1.2212,
      "step": 742
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.09679819558535252,
      "learning_rate": 5e-05,
      "loss": 1.2832,
      "step": 743
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.09623395785492658,
      "learning_rate": 5e-05,
      "loss": 1.1877,
      "step": 744
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.09631927188132637,
      "learning_rate": 5e-05,
      "loss": 1.325,
      "step": 745
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.10247557565649974,
      "learning_rate": 5e-05,
      "loss": 1.1731,
      "step": 746
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.1252184897594414,
      "learning_rate": 5e-05,
      "loss": 1.2998,
      "step": 747
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.10370387262827341,
      "learning_rate": 5e-05,
      "loss": 1.3172,
      "step": 748
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.0974762587376287,
      "learning_rate": 5e-05,
      "loss": 1.2268,
      "step": 749
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.1300763773985203,
      "learning_rate": 5e-05,
      "loss": 1.28,
      "step": 750
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.10416697475393953,
      "learning_rate": 5e-05,
      "loss": 1.2415,
      "step": 751
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.0953165467431355,
      "learning_rate": 5e-05,
      "loss": 1.224,
      "step": 752
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.15906087999039972,
      "learning_rate": 5e-05,
      "loss": 1.2541,
      "step": 753
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.10705539272146689,
      "learning_rate": 5e-05,
      "loss": 1.2195,
      "step": 754
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.10064863761184746,
      "learning_rate": 5e-05,
      "loss": 1.1485,
      "step": 755
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.09754148334053919,
      "learning_rate": 5e-05,
      "loss": 1.2517,
      "step": 756
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.10763212145768898,
      "learning_rate": 5e-05,
      "loss": 1.1744,
      "step": 757
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.1445971539574533,
      "learning_rate": 5e-05,
      "loss": 1.2038,
      "step": 758
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.10008128712969973,
      "learning_rate": 5e-05,
      "loss": 1.2221,
      "step": 759
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.11696802050684159,
      "learning_rate": 5e-05,
      "loss": 1.2129,
      "step": 760
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.10167310507443662,
      "learning_rate": 5e-05,
      "loss": 1.2254,
      "step": 761
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.79581504789477,
      "learning_rate": 5e-05,
      "loss": 1.2186,
      "step": 762
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.09638098726069541,
      "learning_rate": 5e-05,
      "loss": 1.2259,
      "step": 763
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.10875965264550522,
      "learning_rate": 5e-05,
      "loss": 1.2789,
      "step": 764
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.109777838254128,
      "learning_rate": 5e-05,
      "loss": 1.277,
      "step": 765
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.10856749686495373,
      "learning_rate": 5e-05,
      "loss": 1.2077,
      "step": 766
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.09838759573209178,
      "learning_rate": 5e-05,
      "loss": 1.2296,
      "step": 767
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.09877121767531931,
      "learning_rate": 5e-05,
      "loss": 1.2447,
      "step": 768
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.097516506898902,
      "learning_rate": 5e-05,
      "loss": 1.1415,
      "step": 769
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.15640033301410253,
      "learning_rate": 5e-05,
      "loss": 1.2098,
      "step": 770
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.43103323678783306,
      "learning_rate": 5e-05,
      "loss": 1.2478,
      "step": 771
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.1263132691072992,
      "learning_rate": 5e-05,
      "loss": 1.1549,
      "step": 772
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.22807536100092707,
      "learning_rate": 5e-05,
      "loss": 1.2675,
      "step": 773
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.10972162409171408,
      "learning_rate": 5e-05,
      "loss": 1.1569,
      "step": 774
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.11038434717003007,
      "learning_rate": 5e-05,
      "loss": 1.3608,
      "step": 775
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.17568265985553402,
      "learning_rate": 5e-05,
      "loss": 1.2267,
      "step": 776
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.11545287877132578,
      "learning_rate": 5e-05,
      "loss": 1.1519,
      "step": 777
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.14936270776039093,
      "learning_rate": 5e-05,
      "loss": 1.1398,
      "step": 778
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.4545001978738308,
      "learning_rate": 5e-05,
      "loss": 1.2197,
      "step": 779
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.1196390269385417,
      "learning_rate": 5e-05,
      "loss": 1.2172,
      "step": 780
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.11043124850191112,
      "learning_rate": 5e-05,
      "loss": 1.2616,
      "step": 781
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.11378426834643288,
      "learning_rate": 5e-05,
      "loss": 1.2639,
      "step": 782
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.11296570989843585,
      "learning_rate": 5e-05,
      "loss": 1.2778,
      "step": 783
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.11792262542869875,
      "learning_rate": 5e-05,
      "loss": 1.2381,
      "step": 784
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.1040175773065076,
      "learning_rate": 5e-05,
      "loss": 1.1977,
      "step": 785
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.10117229239881861,
      "learning_rate": 5e-05,
      "loss": 1.1884,
      "step": 786
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.11948040578958839,
      "learning_rate": 5e-05,
      "loss": 1.1862,
      "step": 787
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.11263044877607341,
      "learning_rate": 5e-05,
      "loss": 1.0975,
      "step": 788
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.10162187237638322,
      "learning_rate": 5e-05,
      "loss": 1.2881,
      "step": 789
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.09761584113237752,
      "learning_rate": 5e-05,
      "loss": 1.1133,
      "step": 790
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.10179676445024048,
      "learning_rate": 5e-05,
      "loss": 1.1925,
      "step": 791
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.10048619299055972,
      "learning_rate": 5e-05,
      "loss": 1.1626,
      "step": 792
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.10540479457335808,
      "learning_rate": 5e-05,
      "loss": 1.1609,
      "step": 793
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.09576741807479447,
      "learning_rate": 5e-05,
      "loss": 1.2164,
      "step": 794
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.10211722164324015,
      "learning_rate": 5e-05,
      "loss": 1.2733,
      "step": 795
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.0994069528386415,
      "learning_rate": 5e-05,
      "loss": 1.277,
      "step": 796
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.11702861428225478,
      "learning_rate": 5e-05,
      "loss": 1.3852,
      "step": 797
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.11569287694449525,
      "learning_rate": 5e-05,
      "loss": 1.1918,
      "step": 798
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.10796848173468654,
      "learning_rate": 5e-05,
      "loss": 1.2132,
      "step": 799
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.11356557024659053,
      "learning_rate": 5e-05,
      "loss": 1.1443,
      "step": 800
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.10035049988674814,
      "learning_rate": 5e-05,
      "loss": 1.2292,
      "step": 801
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.10133797526045685,
      "learning_rate": 5e-05,
      "loss": 1.2533,
      "step": 802
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.09720806286113348,
      "learning_rate": 5e-05,
      "loss": 1.2717,
      "step": 803
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.1031376804344581,
      "learning_rate": 5e-05,
      "loss": 1.1421,
      "step": 804
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.18830466286012526,
      "learning_rate": 5e-05,
      "loss": 1.1433,
      "step": 805
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.11603087901097664,
      "learning_rate": 5e-05,
      "loss": 1.2186,
      "step": 806
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.10478959523077212,
      "learning_rate": 5e-05,
      "loss": 1.2219,
      "step": 807
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.09553368510904443,
      "learning_rate": 5e-05,
      "loss": 1.2017,
      "step": 808
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.11042525638456162,
      "learning_rate": 5e-05,
      "loss": 1.2168,
      "step": 809
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.10169783065905559,
      "learning_rate": 5e-05,
      "loss": 1.2701,
      "step": 810
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.10292594868979561,
      "learning_rate": 5e-05,
      "loss": 1.2496,
      "step": 811
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.096388359121937,
      "learning_rate": 5e-05,
      "loss": 1.2348,
      "step": 812
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.09309208735472058,
      "learning_rate": 5e-05,
      "loss": 1.3132,
      "step": 813
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.09828706153194258,
      "learning_rate": 5e-05,
      "loss": 1.2129,
      "step": 814
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.10245628163747142,
      "learning_rate": 5e-05,
      "loss": 1.2323,
      "step": 815
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.09945742718624755,
      "learning_rate": 5e-05,
      "loss": 1.0269,
      "step": 816
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.10402570140552733,
      "learning_rate": 5e-05,
      "loss": 1.1454,
      "step": 817
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.10679095390597962,
      "learning_rate": 5e-05,
      "loss": 1.1737,
      "step": 818
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.11131020002635934,
      "learning_rate": 5e-05,
      "loss": 1.1798,
      "step": 819
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.19411752110726227,
      "learning_rate": 5e-05,
      "loss": 1.2349,
      "step": 820
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.12075632954232787,
      "learning_rate": 5e-05,
      "loss": 1.2102,
      "step": 821
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.14563663550644834,
      "learning_rate": 5e-05,
      "loss": 1.1971,
      "step": 822
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.10155568945220618,
      "learning_rate": 5e-05,
      "loss": 1.2767,
      "step": 823
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.14110329174351133,
      "learning_rate": 5e-05,
      "loss": 1.1161,
      "step": 824
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.1280627595012023,
      "learning_rate": 5e-05,
      "loss": 1.1679,
      "step": 825
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.10517376300859077,
      "learning_rate": 5e-05,
      "loss": 1.225,
      "step": 826
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.11688344813726845,
      "learning_rate": 5e-05,
      "loss": 1.1472,
      "step": 827
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.12875551575115213,
      "learning_rate": 5e-05,
      "loss": 1.3059,
      "step": 828
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.10331275620542076,
      "learning_rate": 5e-05,
      "loss": 1.1897,
      "step": 829
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.11814901122457233,
      "learning_rate": 5e-05,
      "loss": 1.2886,
      "step": 830
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.09471838984232255,
      "learning_rate": 5e-05,
      "loss": 1.2303,
      "step": 831
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.14860588114869513,
      "learning_rate": 5e-05,
      "loss": 1.1934,
      "step": 832
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.10584314236750857,
      "learning_rate": 5e-05,
      "loss": 1.2584,
      "step": 833
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.11520751891265056,
      "learning_rate": 5e-05,
      "loss": 1.1897,
      "step": 834
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.28001595194924067,
      "learning_rate": 5e-05,
      "loss": 1.3453,
      "step": 835
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.14806410459094513,
      "learning_rate": 5e-05,
      "loss": 1.2792,
      "step": 836
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.1297344607276581,
      "learning_rate": 5e-05,
      "loss": 1.1851,
      "step": 837
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.11593565387718859,
      "learning_rate": 5e-05,
      "loss": 1.2544,
      "step": 838
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.1436467271405091,
      "learning_rate": 5e-05,
      "loss": 1.1878,
      "step": 839
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.25345500969595197,
      "learning_rate": 5e-05,
      "loss": 1.28,
      "step": 840
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.2078365932479126,
      "learning_rate": 5e-05,
      "loss": 1.2371,
      "step": 841
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.1224506575042296,
      "learning_rate": 5e-05,
      "loss": 1.2283,
      "step": 842
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.10860704275988492,
      "learning_rate": 5e-05,
      "loss": 1.1925,
      "step": 843
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.13984158399146657,
      "learning_rate": 5e-05,
      "loss": 1.1854,
      "step": 844
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.1337763392877898,
      "learning_rate": 5e-05,
      "loss": 1.2313,
      "step": 845
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.10226803676816323,
      "learning_rate": 5e-05,
      "loss": 1.203,
      "step": 846
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.09320162293879738,
      "learning_rate": 5e-05,
      "loss": 1.2391,
      "step": 847
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.09409514812359136,
      "learning_rate": 5e-05,
      "loss": 1.2224,
      "step": 848
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.10052912222465865,
      "learning_rate": 5e-05,
      "loss": 1.2169,
      "step": 849
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.09906328558060296,
      "learning_rate": 5e-05,
      "loss": 1.1966,
      "step": 850
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.12102946778744055,
      "learning_rate": 5e-05,
      "loss": 1.2103,
      "step": 851
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.10113058133812584,
      "learning_rate": 5e-05,
      "loss": 1.268,
      "step": 852
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.10055161182595006,
      "learning_rate": 5e-05,
      "loss": 1.1344,
      "step": 853
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.09991313175496647,
      "learning_rate": 5e-05,
      "loss": 1.3187,
      "step": 854
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.12951627822859785,
      "learning_rate": 5e-05,
      "loss": 1.3176,
      "step": 855
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.09815170395943444,
      "learning_rate": 5e-05,
      "loss": 1.2497,
      "step": 856
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.12246225672826391,
      "learning_rate": 5e-05,
      "loss": 1.3025,
      "step": 857
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.0954537733224272,
      "learning_rate": 5e-05,
      "loss": 1.2217,
      "step": 858
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.09405780024619664,
      "learning_rate": 5e-05,
      "loss": 1.2256,
      "step": 859
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.10542056748781518,
      "learning_rate": 5e-05,
      "loss": 1.2219,
      "step": 860
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.09445376702773765,
      "learning_rate": 5e-05,
      "loss": 1.2511,
      "step": 861
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.10752474403917245,
      "learning_rate": 5e-05,
      "loss": 1.1942,
      "step": 862
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.0938429879577624,
      "learning_rate": 5e-05,
      "loss": 1.3777,
      "step": 863
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.10810466379307371,
      "learning_rate": 5e-05,
      "loss": 1.2441,
      "step": 864
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.10690895063667602,
      "learning_rate": 5e-05,
      "loss": 1.1865,
      "step": 865
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.12209367932915752,
      "learning_rate": 5e-05,
      "loss": 1.3176,
      "step": 866
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.102588124319327,
      "learning_rate": 5e-05,
      "loss": 1.1804,
      "step": 867
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.1060100472496696,
      "learning_rate": 5e-05,
      "loss": 1.2266,
      "step": 868
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.0983313694916884,
      "learning_rate": 5e-05,
      "loss": 1.2627,
      "step": 869
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.10303980986839666,
      "learning_rate": 5e-05,
      "loss": 1.2996,
      "step": 870
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.10680194565865087,
      "learning_rate": 5e-05,
      "loss": 1.2781,
      "step": 871
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.09979616568878538,
      "learning_rate": 5e-05,
      "loss": 1.3002,
      "step": 872
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.09267394233479663,
      "learning_rate": 5e-05,
      "loss": 1.2036,
      "step": 873
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.1149663518195294,
      "learning_rate": 5e-05,
      "loss": 1.1554,
      "step": 874
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.10237610394825647,
      "learning_rate": 5e-05,
      "loss": 1.3075,
      "step": 875
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.09245192145458844,
      "learning_rate": 5e-05,
      "loss": 1.2307,
      "step": 876
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.10589193198898804,
      "learning_rate": 5e-05,
      "loss": 1.2573,
      "step": 877
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.10126499777256248,
      "learning_rate": 5e-05,
      "loss": 1.1529,
      "step": 878
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.09660125908005594,
      "learning_rate": 5e-05,
      "loss": 1.2493,
      "step": 879
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.1247059817512293,
      "learning_rate": 5e-05,
      "loss": 1.229,
      "step": 880
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.09186685597728123,
      "learning_rate": 5e-05,
      "loss": 1.2894,
      "step": 881
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.10583196951125595,
      "learning_rate": 5e-05,
      "loss": 1.3119,
      "step": 882
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.09543741816461494,
      "learning_rate": 5e-05,
      "loss": 1.2534,
      "step": 883
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.10469972017765604,
      "learning_rate": 5e-05,
      "loss": 1.1627,
      "step": 884
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.10742474116808534,
      "learning_rate": 5e-05,
      "loss": 1.2241,
      "step": 885
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.10301119785274608,
      "learning_rate": 5e-05,
      "loss": 1.2369,
      "step": 886
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.11086391313945411,
      "learning_rate": 5e-05,
      "loss": 1.1584,
      "step": 887
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.09856150306496389,
      "learning_rate": 5e-05,
      "loss": 1.1314,
      "step": 888
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.09377525054933467,
      "learning_rate": 5e-05,
      "loss": 1.2545,
      "step": 889
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.09864051283641095,
      "learning_rate": 5e-05,
      "loss": 1.2924,
      "step": 890
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.09991766051946123,
      "learning_rate": 5e-05,
      "loss": 1.2165,
      "step": 891
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.0948527521839145,
      "learning_rate": 5e-05,
      "loss": 1.2812,
      "step": 892
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.09568181092038586,
      "learning_rate": 5e-05,
      "loss": 1.1717,
      "step": 893
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.0998176192734084,
      "learning_rate": 5e-05,
      "loss": 1.305,
      "step": 894
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.12039325363606615,
      "learning_rate": 5e-05,
      "loss": 1.2765,
      "step": 895
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.10924701771102203,
      "learning_rate": 5e-05,
      "loss": 1.2545,
      "step": 896
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.12035811393880431,
      "learning_rate": 5e-05,
      "loss": 1.1652,
      "step": 897
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.09142103086991352,
      "learning_rate": 5e-05,
      "loss": 1.2409,
      "step": 898
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.10267685463052927,
      "learning_rate": 5e-05,
      "loss": 1.1792,
      "step": 899
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.13250203781354886,
      "learning_rate": 5e-05,
      "loss": 1.2084,
      "step": 900
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.10834802537147774,
      "learning_rate": 5e-05,
      "loss": 1.1788,
      "step": 901
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.10561344797384954,
      "learning_rate": 5e-05,
      "loss": 1.2991,
      "step": 902
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.11364275040147816,
      "learning_rate": 5e-05,
      "loss": 1.2342,
      "step": 903
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.09882596512731058,
      "learning_rate": 5e-05,
      "loss": 1.2401,
      "step": 904
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.1598614608373347,
      "learning_rate": 5e-05,
      "loss": 1.1111,
      "step": 905
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.10379583645131088,
      "learning_rate": 5e-05,
      "loss": 1.242,
      "step": 906
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.10050971560567515,
      "learning_rate": 5e-05,
      "loss": 1.245,
      "step": 907
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.09733983912930413,
      "learning_rate": 5e-05,
      "loss": 1.2056,
      "step": 908
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.09728015607915742,
      "learning_rate": 5e-05,
      "loss": 1.259,
      "step": 909
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.09966988425633526,
      "learning_rate": 5e-05,
      "loss": 1.2024,
      "step": 910
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.10455978865642376,
      "learning_rate": 5e-05,
      "loss": 1.1231,
      "step": 911
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.09441860703901163,
      "learning_rate": 5e-05,
      "loss": 1.334,
      "step": 912
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.10730615783514179,
      "learning_rate": 5e-05,
      "loss": 1.2264,
      "step": 913
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.09947829609146572,
      "learning_rate": 5e-05,
      "loss": 1.0771,
      "step": 914
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.09963777107898805,
      "learning_rate": 5e-05,
      "loss": 1.186,
      "step": 915
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.09247240575157885,
      "learning_rate": 5e-05,
      "loss": 1.2108,
      "step": 916
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.10559239036702427,
      "learning_rate": 5e-05,
      "loss": 1.2395,
      "step": 917
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.09682297501448958,
      "learning_rate": 5e-05,
      "loss": 1.2698,
      "step": 918
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.16475050639429561,
      "learning_rate": 5e-05,
      "loss": 1.2197,
      "step": 919
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.11235995677493582,
      "learning_rate": 5e-05,
      "loss": 1.2784,
      "step": 920
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.47156079694933206,
      "learning_rate": 5e-05,
      "loss": 1.2786,
      "step": 921
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.11858338220188593,
      "learning_rate": 5e-05,
      "loss": 1.2193,
      "step": 922
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.23613792180343693,
      "learning_rate": 5e-05,
      "loss": 1.3102,
      "step": 923
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.0983111298091262,
      "learning_rate": 5e-05,
      "loss": 1.2385,
      "step": 924
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.11406810717062593,
      "learning_rate": 5e-05,
      "loss": 1.3788,
      "step": 925
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.11254524855462729,
      "learning_rate": 5e-05,
      "loss": 1.2784,
      "step": 926
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.15539104489315878,
      "learning_rate": 5e-05,
      "loss": 1.1682,
      "step": 927
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.11789469174067303,
      "learning_rate": 5e-05,
      "loss": 1.336,
      "step": 928
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.11349741317620189,
      "learning_rate": 5e-05,
      "loss": 1.2517,
      "step": 929
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.10919004596237217,
      "learning_rate": 5e-05,
      "loss": 1.216,
      "step": 930
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.1198831609531216,
      "learning_rate": 5e-05,
      "loss": 1.2071,
      "step": 931
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.10286766273135783,
      "learning_rate": 5e-05,
      "loss": 1.2043,
      "step": 932
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.09600011742192804,
      "learning_rate": 5e-05,
      "loss": 1.2604,
      "step": 933
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.22190196640417234,
      "learning_rate": 5e-05,
      "loss": 1.1831,
      "step": 934
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.10226010954520015,
      "learning_rate": 5e-05,
      "loss": 1.2089,
      "step": 935
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.11317533110892175,
      "learning_rate": 5e-05,
      "loss": 1.1593,
      "step": 936
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.11759030987224492,
      "learning_rate": 5e-05,
      "loss": 1.2899,
      "step": 937
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.1250834660376518,
      "learning_rate": 5e-05,
      "loss": 1.2589,
      "step": 938
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.14260058685971605,
      "learning_rate": 5e-05,
      "loss": 1.0978,
      "step": 939
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.09749870569187263,
      "learning_rate": 5e-05,
      "loss": 1.2144,
      "step": 940
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.10779307755110958,
      "learning_rate": 5e-05,
      "loss": 1.2084,
      "step": 941
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.14605707408138002,
      "learning_rate": 5e-05,
      "loss": 1.2735,
      "step": 942
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.11628990548806367,
      "learning_rate": 5e-05,
      "loss": 1.266,
      "step": 943
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.10230427023192927,
      "learning_rate": 5e-05,
      "loss": 1.2164,
      "step": 944
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.16410793851226396,
      "learning_rate": 5e-05,
      "loss": 1.2743,
      "step": 945
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.10765862205008636,
      "learning_rate": 5e-05,
      "loss": 1.2685,
      "step": 946
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.09907993502415698,
      "learning_rate": 5e-05,
      "loss": 1.2559,
      "step": 947
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.11889063526263191,
      "learning_rate": 5e-05,
      "loss": 1.234,
      "step": 948
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.10767936872705047,
      "learning_rate": 5e-05,
      "loss": 1.1664,
      "step": 949
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.09749757641604646,
      "learning_rate": 5e-05,
      "loss": 1.3048,
      "step": 950
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.23069423873119332,
      "learning_rate": 5e-05,
      "loss": 1.1651,
      "step": 951
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.10700583434758547,
      "learning_rate": 5e-05,
      "loss": 1.1825,
      "step": 952
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.10396836363765337,
      "learning_rate": 5e-05,
      "loss": 1.1863,
      "step": 953
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.10052794694013932,
      "learning_rate": 5e-05,
      "loss": 1.1817,
      "step": 954
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.09993466906494232,
      "learning_rate": 5e-05,
      "loss": 1.234,
      "step": 955
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.11687322712115825,
      "learning_rate": 5e-05,
      "loss": 1.2533,
      "step": 956
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.10225631433831812,
      "learning_rate": 5e-05,
      "loss": 1.3213,
      "step": 957
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.20386069596611658,
      "learning_rate": 5e-05,
      "loss": 1.182,
      "step": 958
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.10453133927250215,
      "learning_rate": 5e-05,
      "loss": 1.1637,
      "step": 959
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.14175585587210737,
      "learning_rate": 5e-05,
      "loss": 1.2288,
      "step": 960
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.10504359148798725,
      "learning_rate": 5e-05,
      "loss": 1.1047,
      "step": 961
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.1372710003561213,
      "learning_rate": 5e-05,
      "loss": 1.2389,
      "step": 962
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.09652492703220977,
      "learning_rate": 5e-05,
      "loss": 1.244,
      "step": 963
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.12853818698223418,
      "learning_rate": 5e-05,
      "loss": 1.2166,
      "step": 964
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.09514313666309156,
      "learning_rate": 5e-05,
      "loss": 1.2089,
      "step": 965
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.10694618628695444,
      "learning_rate": 5e-05,
      "loss": 1.2235,
      "step": 966
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.12224798699692742,
      "learning_rate": 5e-05,
      "loss": 1.1813,
      "step": 967
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.26234747554071813,
      "learning_rate": 5e-05,
      "loss": 1.2717,
      "step": 968
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.2223576763234531,
      "learning_rate": 5e-05,
      "loss": 1.1696,
      "step": 969
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.09541227160678786,
      "learning_rate": 5e-05,
      "loss": 1.2806,
      "step": 970
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.190855658030098,
      "learning_rate": 5e-05,
      "loss": 1.1567,
      "step": 971
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.09497325579586648,
      "learning_rate": 5e-05,
      "loss": 1.1967,
      "step": 972
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.11088288919053314,
      "learning_rate": 5e-05,
      "loss": 1.2721,
      "step": 973
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.10796216347531845,
      "learning_rate": 5e-05,
      "loss": 1.189,
      "step": 974
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.1480195977338028,
      "learning_rate": 5e-05,
      "loss": 1.2218,
      "step": 975
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.09927193222114575,
      "learning_rate": 5e-05,
      "loss": 1.1921,
      "step": 976
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.12996014889963342,
      "learning_rate": 5e-05,
      "loss": 1.1949,
      "step": 977
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.10121985656769747,
      "learning_rate": 5e-05,
      "loss": 1.2615,
      "step": 978
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.12529184737097637,
      "learning_rate": 5e-05,
      "loss": 1.242,
      "step": 979
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.09263455602695328,
      "learning_rate": 5e-05,
      "loss": 1.114,
      "step": 980
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.10771968620871182,
      "learning_rate": 5e-05,
      "loss": 1.2078,
      "step": 981
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.10216253778570993,
      "learning_rate": 5e-05,
      "loss": 1.1327,
      "step": 982
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.10818819544058149,
      "learning_rate": 5e-05,
      "loss": 1.1586,
      "step": 983
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.12823555056526956,
      "learning_rate": 5e-05,
      "loss": 1.2688,
      "step": 984
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.09924598713576864,
      "learning_rate": 5e-05,
      "loss": 1.2897,
      "step": 985
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.10450140329683655,
      "learning_rate": 5e-05,
      "loss": 1.2864,
      "step": 986
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.10811779229962425,
      "learning_rate": 5e-05,
      "loss": 1.2154,
      "step": 987
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.12094047182333562,
      "learning_rate": 5e-05,
      "loss": 1.2081,
      "step": 988
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.4600497792934725,
      "learning_rate": 5e-05,
      "loss": 1.3033,
      "step": 989
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.10852237288651734,
      "learning_rate": 5e-05,
      "loss": 1.2158,
      "step": 990
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.10195887833984932,
      "learning_rate": 5e-05,
      "loss": 1.1503,
      "step": 991
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.10399482935464686,
      "learning_rate": 5e-05,
      "loss": 1.2045,
      "step": 992
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.11118589790644104,
      "learning_rate": 5e-05,
      "loss": 1.2563,
      "step": 993
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.10465906043886859,
      "learning_rate": 5e-05,
      "loss": 1.2064,
      "step": 994
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.10013573706817067,
      "learning_rate": 5e-05,
      "loss": 1.209,
      "step": 995
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.1071570526430657,
      "learning_rate": 5e-05,
      "loss": 1.275,
      "step": 996
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.10919713500303668,
      "learning_rate": 5e-05,
      "loss": 1.288,
      "step": 997
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.11456205050457402,
      "learning_rate": 5e-05,
      "loss": 1.2305,
      "step": 998
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.12399882106372813,
      "learning_rate": 5e-05,
      "loss": 1.2837,
      "step": 999
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.10832642295721785,
      "learning_rate": 5e-05,
      "loss": 1.29,
      "step": 1000
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.10366791152273643,
      "learning_rate": 5e-05,
      "loss": 1.2974,
      "step": 1001
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.1003360742671259,
      "learning_rate": 5e-05,
      "loss": 1.1462,
      "step": 1002
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.1287165700820769,
      "learning_rate": 5e-05,
      "loss": 1.1544,
      "step": 1003
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.10869493803592062,
      "learning_rate": 5e-05,
      "loss": 1.2541,
      "step": 1004
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.10140977622387513,
      "learning_rate": 5e-05,
      "loss": 1.2757,
      "step": 1005
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.1044449979187249,
      "learning_rate": 5e-05,
      "loss": 1.2509,
      "step": 1006
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.10164122941659054,
      "learning_rate": 5e-05,
      "loss": 1.1214,
      "step": 1007
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.09656524427061954,
      "learning_rate": 5e-05,
      "loss": 1.2794,
      "step": 1008
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.10316130824172369,
      "learning_rate": 5e-05,
      "loss": 1.2456,
      "step": 1009
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.12661507350057447,
      "learning_rate": 5e-05,
      "loss": 1.3331,
      "step": 1010
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.09343343695130192,
      "learning_rate": 5e-05,
      "loss": 1.2193,
      "step": 1011
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.10105563782443838,
      "learning_rate": 5e-05,
      "loss": 1.1847,
      "step": 1012
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.09945667547651259,
      "learning_rate": 5e-05,
      "loss": 1.3234,
      "step": 1013
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.10631412051783554,
      "learning_rate": 5e-05,
      "loss": 1.2156,
      "step": 1014
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.10136339520159555,
      "learning_rate": 5e-05,
      "loss": 1.2395,
      "step": 1015
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.10386181257649985,
      "learning_rate": 5e-05,
      "loss": 1.1837,
      "step": 1016
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.11322232984171478,
      "learning_rate": 5e-05,
      "loss": 1.2568,
      "step": 1017
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.15564747896162864,
      "learning_rate": 5e-05,
      "loss": 1.208,
      "step": 1018
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.09815366710701164,
      "learning_rate": 5e-05,
      "loss": 1.2358,
      "step": 1019
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.0947005716750396,
      "learning_rate": 5e-05,
      "loss": 1.2339,
      "step": 1020
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.10681616135760118,
      "learning_rate": 5e-05,
      "loss": 1.1831,
      "step": 1021
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.13281012673783055,
      "learning_rate": 5e-05,
      "loss": 1.2644,
      "step": 1022
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.09877299158515507,
      "learning_rate": 5e-05,
      "loss": 1.2352,
      "step": 1023
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.12293371631329547,
      "learning_rate": 5e-05,
      "loss": 1.2489,
      "step": 1024
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.09705893021636595,
      "learning_rate": 5e-05,
      "loss": 1.1578,
      "step": 1025
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.10973605966782467,
      "learning_rate": 5e-05,
      "loss": 1.186,
      "step": 1026
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.10491996108084253,
      "learning_rate": 5e-05,
      "loss": 1.2308,
      "step": 1027
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.1044888405375428,
      "learning_rate": 5e-05,
      "loss": 1.2694,
      "step": 1028
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.13136089252156674,
      "learning_rate": 5e-05,
      "loss": 1.2088,
      "step": 1029
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.10099304079305634,
      "learning_rate": 5e-05,
      "loss": 1.1863,
      "step": 1030
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.1460377875439273,
      "learning_rate": 5e-05,
      "loss": 1.098,
      "step": 1031
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.10861430882064095,
      "learning_rate": 5e-05,
      "loss": 1.1955,
      "step": 1032
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.10496775010185377,
      "learning_rate": 5e-05,
      "loss": 1.1734,
      "step": 1033
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.10446995033363628,
      "learning_rate": 5e-05,
      "loss": 1.1894,
      "step": 1034
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.10549243265636632,
      "learning_rate": 5e-05,
      "loss": 1.1358,
      "step": 1035
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.10896447810159171,
      "learning_rate": 5e-05,
      "loss": 1.2034,
      "step": 1036
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.11061310703224005,
      "learning_rate": 5e-05,
      "loss": 1.1825,
      "step": 1037
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.16590775932321747,
      "learning_rate": 5e-05,
      "loss": 1.1903,
      "step": 1038
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.12514434847006461,
      "learning_rate": 5e-05,
      "loss": 1.3002,
      "step": 1039
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.15781803094359004,
      "learning_rate": 5e-05,
      "loss": 1.1637,
      "step": 1040
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.12413132010118058,
      "learning_rate": 5e-05,
      "loss": 1.2507,
      "step": 1041
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.18426087842596092,
      "learning_rate": 5e-05,
      "loss": 1.2318,
      "step": 1042
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.10635114094076911,
      "learning_rate": 5e-05,
      "loss": 1.2053,
      "step": 1043
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.10170843014452283,
      "learning_rate": 5e-05,
      "loss": 1.1673,
      "step": 1044
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.11318331074469846,
      "learning_rate": 5e-05,
      "loss": 1.2605,
      "step": 1045
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.17396111219741633,
      "learning_rate": 5e-05,
      "loss": 1.1856,
      "step": 1046
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.20923671082644354,
      "learning_rate": 5e-05,
      "loss": 1.2154,
      "step": 1047
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.11196845757564178,
      "learning_rate": 5e-05,
      "loss": 1.2044,
      "step": 1048
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.13055991020143282,
      "learning_rate": 5e-05,
      "loss": 1.1808,
      "step": 1049
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.10527238862728859,
      "learning_rate": 5e-05,
      "loss": 1.2132,
      "step": 1050
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.10907032731642057,
      "learning_rate": 5e-05,
      "loss": 1.2486,
      "step": 1051
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.11052964516050179,
      "learning_rate": 5e-05,
      "loss": 1.2098,
      "step": 1052
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.10449099870037604,
      "learning_rate": 5e-05,
      "loss": 1.3333,
      "step": 1053
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.1031383339280535,
      "learning_rate": 5e-05,
      "loss": 1.1824,
      "step": 1054
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.13227089922436905,
      "learning_rate": 5e-05,
      "loss": 1.2001,
      "step": 1055
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.09664835532955035,
      "learning_rate": 5e-05,
      "loss": 1.167,
      "step": 1056
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.11335851967004781,
      "learning_rate": 5e-05,
      "loss": 1.2281,
      "step": 1057
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.10498278152815924,
      "learning_rate": 5e-05,
      "loss": 1.1733,
      "step": 1058
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.10463428399728839,
      "learning_rate": 5e-05,
      "loss": 1.1869,
      "step": 1059
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.1067819882408397,
      "learning_rate": 5e-05,
      "loss": 1.2354,
      "step": 1060
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.106121227536998,
      "learning_rate": 5e-05,
      "loss": 1.2082,
      "step": 1061
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.12840621609678718,
      "learning_rate": 5e-05,
      "loss": 1.1806,
      "step": 1062
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.12471783967396649,
      "learning_rate": 5e-05,
      "loss": 1.2427,
      "step": 1063
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.10106792284786356,
      "learning_rate": 5e-05,
      "loss": 1.1918,
      "step": 1064
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.10469400899894957,
      "learning_rate": 5e-05,
      "loss": 1.3323,
      "step": 1065
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.09841756090169458,
      "learning_rate": 5e-05,
      "loss": 1.1394,
      "step": 1066
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.10521064721286782,
      "learning_rate": 5e-05,
      "loss": 1.2369,
      "step": 1067
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.1485189439001766,
      "learning_rate": 5e-05,
      "loss": 1.1872,
      "step": 1068
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.1079971402508067,
      "learning_rate": 5e-05,
      "loss": 1.1736,
      "step": 1069
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.3116945764054355,
      "learning_rate": 5e-05,
      "loss": 1.1337,
      "step": 1070
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.100199655243572,
      "learning_rate": 5e-05,
      "loss": 1.2735,
      "step": 1071
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.10810114625745185,
      "learning_rate": 5e-05,
      "loss": 1.1165,
      "step": 1072
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.10661802966803025,
      "learning_rate": 5e-05,
      "loss": 1.211,
      "step": 1073
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.1702498815516622,
      "learning_rate": 5e-05,
      "loss": 1.2107,
      "step": 1074
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.19737300799778165,
      "learning_rate": 5e-05,
      "loss": 1.2667,
      "step": 1075
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.14465651500853066,
      "learning_rate": 5e-05,
      "loss": 1.1231,
      "step": 1076
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.10265693402616242,
      "learning_rate": 5e-05,
      "loss": 1.1786,
      "step": 1077
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.14591430498719865,
      "learning_rate": 5e-05,
      "loss": 1.1901,
      "step": 1078
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.10532373028754374,
      "learning_rate": 5e-05,
      "loss": 1.2289,
      "step": 1079
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.11182699139962098,
      "learning_rate": 5e-05,
      "loss": 1.1806,
      "step": 1080
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.11423113268976091,
      "learning_rate": 5e-05,
      "loss": 1.2026,
      "step": 1081
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.13063554823255874,
      "learning_rate": 5e-05,
      "loss": 1.2587,
      "step": 1082
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.10791638156088533,
      "learning_rate": 5e-05,
      "loss": 1.0991,
      "step": 1083
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.11938249787224578,
      "learning_rate": 5e-05,
      "loss": 1.2406,
      "step": 1084
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.10902651597381753,
      "learning_rate": 5e-05,
      "loss": 1.2697,
      "step": 1085
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.10486855124377796,
      "learning_rate": 5e-05,
      "loss": 1.1325,
      "step": 1086
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.3453109872403924,
      "learning_rate": 5e-05,
      "loss": 1.1767,
      "step": 1087
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.11239569153139466,
      "learning_rate": 5e-05,
      "loss": 1.0797,
      "step": 1088
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.45855681572495244,
      "learning_rate": 5e-05,
      "loss": 1.2631,
      "step": 1089
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.1036145956775789,
      "learning_rate": 5e-05,
      "loss": 1.1923,
      "step": 1090
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.11355495090838764,
      "learning_rate": 5e-05,
      "loss": 1.2224,
      "step": 1091
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.10402736950459299,
      "learning_rate": 5e-05,
      "loss": 1.1325,
      "step": 1092
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.10464257964892076,
      "learning_rate": 5e-05,
      "loss": 1.3013,
      "step": 1093
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.2997750672110947,
      "learning_rate": 5e-05,
      "loss": 1.2847,
      "step": 1094
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.1038403157372341,
      "learning_rate": 5e-05,
      "loss": 1.1845,
      "step": 1095
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.10749180100362335,
      "learning_rate": 5e-05,
      "loss": 1.1651,
      "step": 1096
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.1239660329028446,
      "learning_rate": 5e-05,
      "loss": 1.2477,
      "step": 1097
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.14474184991191533,
      "learning_rate": 5e-05,
      "loss": 1.1866,
      "step": 1098
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.11037461451933651,
      "learning_rate": 5e-05,
      "loss": 1.1542,
      "step": 1099
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.106841448364413,
      "learning_rate": 5e-05,
      "loss": 1.2771,
      "step": 1100
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.11810389395422928,
      "learning_rate": 5e-05,
      "loss": 1.0569,
      "step": 1101
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.10533151633570667,
      "learning_rate": 5e-05,
      "loss": 1.288,
      "step": 1102
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.10717168365401805,
      "learning_rate": 5e-05,
      "loss": 1.1776,
      "step": 1103
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.0961612976475172,
      "learning_rate": 5e-05,
      "loss": 1.2076,
      "step": 1104
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.12243032566601864,
      "learning_rate": 5e-05,
      "loss": 1.2372,
      "step": 1105
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.10895416526413164,
      "learning_rate": 5e-05,
      "loss": 1.237,
      "step": 1106
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.15851208507114167,
      "learning_rate": 5e-05,
      "loss": 1.2776,
      "step": 1107
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.10017642682972655,
      "learning_rate": 5e-05,
      "loss": 1.1887,
      "step": 1108
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.11014110698632447,
      "learning_rate": 5e-05,
      "loss": 1.2839,
      "step": 1109
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.12226489365159669,
      "learning_rate": 5e-05,
      "loss": 1.3129,
      "step": 1110
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.12807374471444058,
      "learning_rate": 5e-05,
      "loss": 1.2599,
      "step": 1111
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.12259938643247845,
      "learning_rate": 5e-05,
      "loss": 1.1938,
      "step": 1112
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.0980980052185939,
      "learning_rate": 5e-05,
      "loss": 1.2428,
      "step": 1113
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.12319771896361019,
      "learning_rate": 5e-05,
      "loss": 1.316,
      "step": 1114
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.09716149046365014,
      "learning_rate": 5e-05,
      "loss": 1.1714,
      "step": 1115
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.10397951019093706,
      "learning_rate": 5e-05,
      "loss": 1.1,
      "step": 1116
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.10995082972128228,
      "learning_rate": 5e-05,
      "loss": 1.2488,
      "step": 1117
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.12451854257642488,
      "learning_rate": 5e-05,
      "loss": 1.2055,
      "step": 1118
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.1531437089478829,
      "learning_rate": 5e-05,
      "loss": 1.2104,
      "step": 1119
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.11493923874545948,
      "learning_rate": 5e-05,
      "loss": 1.2339,
      "step": 1120
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.12461445575609231,
      "learning_rate": 5e-05,
      "loss": 1.1558,
      "step": 1121
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.10520018544273198,
      "learning_rate": 5e-05,
      "loss": 1.0898,
      "step": 1122
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.10894887361146934,
      "learning_rate": 5e-05,
      "loss": 1.2124,
      "step": 1123
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.09840018449855767,
      "learning_rate": 5e-05,
      "loss": 1.2204,
      "step": 1124
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.11199058641987784,
      "learning_rate": 5e-05,
      "loss": 1.2546,
      "step": 1125
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.12408245293592914,
      "learning_rate": 5e-05,
      "loss": 1.1638,
      "step": 1126
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.10127521215119754,
      "learning_rate": 5e-05,
      "loss": 1.2653,
      "step": 1127
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.1399086035344601,
      "learning_rate": 5e-05,
      "loss": 1.2332,
      "step": 1128
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.11426115988130074,
      "learning_rate": 5e-05,
      "loss": 1.1353,
      "step": 1129
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.10395875125555352,
      "learning_rate": 5e-05,
      "loss": 1.1236,
      "step": 1130
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.10162172390578378,
      "learning_rate": 5e-05,
      "loss": 1.2529,
      "step": 1131
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.15889830320606954,
      "learning_rate": 5e-05,
      "loss": 1.2249,
      "step": 1132
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.10069562029591411,
      "learning_rate": 5e-05,
      "loss": 1.0911,
      "step": 1133
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.0988902826921912,
      "learning_rate": 5e-05,
      "loss": 1.2811,
      "step": 1134
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.10245904846153597,
      "learning_rate": 5e-05,
      "loss": 1.1767,
      "step": 1135
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.10011785338352583,
      "learning_rate": 5e-05,
      "loss": 1.231,
      "step": 1136
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.10463545323443652,
      "learning_rate": 5e-05,
      "loss": 1.1936,
      "step": 1137
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.10083707261198763,
      "learning_rate": 5e-05,
      "loss": 1.2133,
      "step": 1138
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.10492203552637583,
      "learning_rate": 5e-05,
      "loss": 1.2816,
      "step": 1139
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.12054430455453068,
      "learning_rate": 5e-05,
      "loss": 1.2614,
      "step": 1140
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.10179671312141375,
      "learning_rate": 5e-05,
      "loss": 1.1926,
      "step": 1141
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.1151371912064686,
      "learning_rate": 5e-05,
      "loss": 1.1968,
      "step": 1142
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.10399576378706286,
      "learning_rate": 5e-05,
      "loss": 1.2151,
      "step": 1143
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.12203535636977965,
      "learning_rate": 5e-05,
      "loss": 1.1495,
      "step": 1144
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.09290063978036708,
      "learning_rate": 5e-05,
      "loss": 1.2679,
      "step": 1145
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.10898289097335016,
      "learning_rate": 5e-05,
      "loss": 1.2008,
      "step": 1146
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.10148033448384093,
      "learning_rate": 5e-05,
      "loss": 1.322,
      "step": 1147
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.10834959113369981,
      "learning_rate": 5e-05,
      "loss": 1.2096,
      "step": 1148
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.10065777111501409,
      "learning_rate": 5e-05,
      "loss": 1.2288,
      "step": 1149
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.09631018069832553,
      "learning_rate": 5e-05,
      "loss": 1.2207,
      "step": 1150
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.3230353288983818,
      "learning_rate": 5e-05,
      "loss": 1.2501,
      "step": 1151
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.12702499368592196,
      "learning_rate": 5e-05,
      "loss": 1.2306,
      "step": 1152
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.10936572946474664,
      "learning_rate": 5e-05,
      "loss": 1.2404,
      "step": 1153
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.1177538068676181,
      "learning_rate": 5e-05,
      "loss": 1.2443,
      "step": 1154
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.10975006494672532,
      "learning_rate": 5e-05,
      "loss": 1.1036,
      "step": 1155
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.2197390336947409,
      "learning_rate": 5e-05,
      "loss": 1.2376,
      "step": 1156
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.10452116607674644,
      "learning_rate": 5e-05,
      "loss": 1.2399,
      "step": 1157
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.11607607047242494,
      "learning_rate": 5e-05,
      "loss": 1.1981,
      "step": 1158
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.10380754969804883,
      "learning_rate": 5e-05,
      "loss": 1.262,
      "step": 1159
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.11185829212786501,
      "learning_rate": 5e-05,
      "loss": 1.2712,
      "step": 1160
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.10179469200333552,
      "learning_rate": 5e-05,
      "loss": 1.2246,
      "step": 1161
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.11110636528358402,
      "learning_rate": 5e-05,
      "loss": 1.1113,
      "step": 1162
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.10042761084255272,
      "learning_rate": 5e-05,
      "loss": 1.267,
      "step": 1163
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.11312232886115434,
      "learning_rate": 5e-05,
      "loss": 1.274,
      "step": 1164
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.10089653412943035,
      "learning_rate": 5e-05,
      "loss": 1.139,
      "step": 1165
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.09343133217706687,
      "learning_rate": 5e-05,
      "loss": 1.1974,
      "step": 1166
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.12073081879301166,
      "learning_rate": 5e-05,
      "loss": 1.2073,
      "step": 1167
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.09852467020934617,
      "learning_rate": 5e-05,
      "loss": 1.2665,
      "step": 1168
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.10136884495861127,
      "learning_rate": 5e-05,
      "loss": 1.2409,
      "step": 1169
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.10022427968306054,
      "learning_rate": 5e-05,
      "loss": 1.1998,
      "step": 1170
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.0910322515063694,
      "learning_rate": 5e-05,
      "loss": 1.2836,
      "step": 1171
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.10437507814306135,
      "learning_rate": 5e-05,
      "loss": 1.2973,
      "step": 1172
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.10199438944121582,
      "learning_rate": 5e-05,
      "loss": 1.271,
      "step": 1173
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.09920544631583435,
      "learning_rate": 5e-05,
      "loss": 1.2717,
      "step": 1174
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.10804525830212407,
      "learning_rate": 5e-05,
      "loss": 1.23,
      "step": 1175
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.09912634214578551,
      "learning_rate": 5e-05,
      "loss": 1.2064,
      "step": 1176
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.12054697422829558,
      "learning_rate": 5e-05,
      "loss": 1.1208,
      "step": 1177
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.10122850210400991,
      "learning_rate": 5e-05,
      "loss": 1.1655,
      "step": 1178
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.0965851330147051,
      "learning_rate": 5e-05,
      "loss": 1.2477,
      "step": 1179
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.11218789799430838,
      "learning_rate": 5e-05,
      "loss": 1.1991,
      "step": 1180
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.15542937261692477,
      "learning_rate": 5e-05,
      "loss": 1.1494,
      "step": 1181
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.111541983858468,
      "learning_rate": 5e-05,
      "loss": 1.1802,
      "step": 1182
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.111410084332699,
      "learning_rate": 5e-05,
      "loss": 1.1395,
      "step": 1183
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.11619923573838167,
      "learning_rate": 5e-05,
      "loss": 1.3272,
      "step": 1184
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.10718441596644573,
      "learning_rate": 5e-05,
      "loss": 1.2276,
      "step": 1185
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.10801899868334196,
      "learning_rate": 5e-05,
      "loss": 1.0912,
      "step": 1186
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.15050847078799887,
      "learning_rate": 5e-05,
      "loss": 1.1554,
      "step": 1187
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.10919376860447183,
      "learning_rate": 5e-05,
      "loss": 1.1637,
      "step": 1188
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.10622165564978144,
      "learning_rate": 5e-05,
      "loss": 1.2543,
      "step": 1189
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.10810630217231784,
      "learning_rate": 5e-05,
      "loss": 1.2308,
      "step": 1190
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.10840706011043,
      "learning_rate": 5e-05,
      "loss": 1.276,
      "step": 1191
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.10246667696227883,
      "learning_rate": 5e-05,
      "loss": 1.2435,
      "step": 1192
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.0976182543352327,
      "learning_rate": 5e-05,
      "loss": 1.2223,
      "step": 1193
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.11112765591620033,
      "learning_rate": 5e-05,
      "loss": 1.1617,
      "step": 1194
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.09630889540310973,
      "learning_rate": 5e-05,
      "loss": 1.1156,
      "step": 1195
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.11227327495026782,
      "learning_rate": 5e-05,
      "loss": 1.1249,
      "step": 1196
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.12233812487333268,
      "learning_rate": 5e-05,
      "loss": 1.214,
      "step": 1197
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.09859226961924858,
      "learning_rate": 5e-05,
      "loss": 1.1707,
      "step": 1198
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.1219145840608869,
      "learning_rate": 5e-05,
      "loss": 1.1669,
      "step": 1199
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.10829044049284217,
      "learning_rate": 5e-05,
      "loss": 1.2756,
      "step": 1200
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.10932578968684246,
      "learning_rate": 5e-05,
      "loss": 1.2864,
      "step": 1201
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.12670280491084548,
      "learning_rate": 5e-05,
      "loss": 1.289,
      "step": 1202
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.09685526139167519,
      "learning_rate": 5e-05,
      "loss": 1.2881,
      "step": 1203
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.10583813949907528,
      "learning_rate": 5e-05,
      "loss": 1.2822,
      "step": 1204
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.10945130691209246,
      "learning_rate": 5e-05,
      "loss": 1.2269,
      "step": 1205
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.10921995222605822,
      "learning_rate": 5e-05,
      "loss": 1.2643,
      "step": 1206
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.0983530242970981,
      "learning_rate": 5e-05,
      "loss": 1.1867,
      "step": 1207
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.10929467514266258,
      "learning_rate": 5e-05,
      "loss": 1.2048,
      "step": 1208
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.10226448992517749,
      "learning_rate": 5e-05,
      "loss": 1.246,
      "step": 1209
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.12407437670976282,
      "learning_rate": 5e-05,
      "loss": 1.1378,
      "step": 1210
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.10460464410563199,
      "learning_rate": 5e-05,
      "loss": 1.2073,
      "step": 1211
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.1130481700493754,
      "learning_rate": 5e-05,
      "loss": 1.2146,
      "step": 1212
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.10898937707078646,
      "learning_rate": 5e-05,
      "loss": 1.2017,
      "step": 1213
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.10458208968254373,
      "learning_rate": 5e-05,
      "loss": 1.2241,
      "step": 1214
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.17157051460666153,
      "learning_rate": 5e-05,
      "loss": 1.2247,
      "step": 1215
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.11301909258134905,
      "learning_rate": 5e-05,
      "loss": 1.1742,
      "step": 1216
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.11090992344071807,
      "learning_rate": 5e-05,
      "loss": 1.2621,
      "step": 1217
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.19061726604876061,
      "learning_rate": 5e-05,
      "loss": 1.321,
      "step": 1218
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.11306033650929138,
      "learning_rate": 5e-05,
      "loss": 1.1946,
      "step": 1219
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.11054797742330863,
      "learning_rate": 5e-05,
      "loss": 1.1247,
      "step": 1220
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.12409173074359779,
      "learning_rate": 5e-05,
      "loss": 1.2783,
      "step": 1221
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.10116741290769664,
      "learning_rate": 5e-05,
      "loss": 1.2847,
      "step": 1222
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.10482518955704544,
      "learning_rate": 5e-05,
      "loss": 1.2904,
      "step": 1223
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.11115021294905844,
      "learning_rate": 5e-05,
      "loss": 1.2046,
      "step": 1224
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.1543937030512322,
      "learning_rate": 5e-05,
      "loss": 1.3135,
      "step": 1225
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.1024341754657176,
      "learning_rate": 5e-05,
      "loss": 1.1804,
      "step": 1226
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.10162401906455482,
      "learning_rate": 5e-05,
      "loss": 1.2233,
      "step": 1227
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.14714386441625504,
      "learning_rate": 5e-05,
      "loss": 1.3606,
      "step": 1228
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.14316956030100939,
      "learning_rate": 5e-05,
      "loss": 1.2321,
      "step": 1229
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.10717046646861364,
      "learning_rate": 5e-05,
      "loss": 1.2936,
      "step": 1230
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.10306250658030879,
      "learning_rate": 5e-05,
      "loss": 1.2919,
      "step": 1231
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.10398905424648734,
      "learning_rate": 5e-05,
      "loss": 1.2025,
      "step": 1232
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.10393126846253141,
      "learning_rate": 5e-05,
      "loss": 1.3078,
      "step": 1233
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.1228474547464257,
      "learning_rate": 5e-05,
      "loss": 1.2569,
      "step": 1234
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.18494956328524312,
      "learning_rate": 5e-05,
      "loss": 1.2019,
      "step": 1235
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.2089798375546016,
      "learning_rate": 5e-05,
      "loss": 1.2641,
      "step": 1236
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.1120639345674154,
      "learning_rate": 5e-05,
      "loss": 1.1805,
      "step": 1237
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.09869073334943725,
      "learning_rate": 5e-05,
      "loss": 1.1377,
      "step": 1238
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.0987004825345963,
      "learning_rate": 5e-05,
      "loss": 1.2975,
      "step": 1239
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.10117622099339955,
      "learning_rate": 5e-05,
      "loss": 1.2602,
      "step": 1240
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.27026743100111356,
      "learning_rate": 5e-05,
      "loss": 1.2129,
      "step": 1241
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.09600849716739375,
      "learning_rate": 5e-05,
      "loss": 1.2822,
      "step": 1242
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.09195470019743175,
      "learning_rate": 5e-05,
      "loss": 1.214,
      "step": 1243
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.21139686590673398,
      "learning_rate": 5e-05,
      "loss": 1.2527,
      "step": 1244
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.35125858508648117,
      "learning_rate": 5e-05,
      "loss": 1.059,
      "step": 1245
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.11357337969627455,
      "learning_rate": 5e-05,
      "loss": 1.2338,
      "step": 1246
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.1643801080348834,
      "learning_rate": 5e-05,
      "loss": 1.3028,
      "step": 1247
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.12090900207903225,
      "learning_rate": 5e-05,
      "loss": 1.3095,
      "step": 1248
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.11153656319798944,
      "learning_rate": 5e-05,
      "loss": 1.3215,
      "step": 1249
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.11707006072514332,
      "learning_rate": 5e-05,
      "loss": 1.1271,
      "step": 1250
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.11753420218744483,
      "learning_rate": 5e-05,
      "loss": 1.2146,
      "step": 1251
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.10357254508306929,
      "learning_rate": 5e-05,
      "loss": 1.1059,
      "step": 1252
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.09663866569935589,
      "learning_rate": 5e-05,
      "loss": 1.192,
      "step": 1253
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.1575776172648202,
      "learning_rate": 5e-05,
      "loss": 1.1684,
      "step": 1254
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.10326535906232145,
      "learning_rate": 5e-05,
      "loss": 1.1345,
      "step": 1255
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.10209137977079849,
      "learning_rate": 5e-05,
      "loss": 1.219,
      "step": 1256
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.13229065013863076,
      "learning_rate": 5e-05,
      "loss": 1.2622,
      "step": 1257
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.0906911459500279,
      "learning_rate": 5e-05,
      "loss": 1.181,
      "step": 1258
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.12023731835311281,
      "learning_rate": 5e-05,
      "loss": 1.2514,
      "step": 1259
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.10366397873766577,
      "learning_rate": 5e-05,
      "loss": 1.2729,
      "step": 1260
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.1247952402268157,
      "learning_rate": 5e-05,
      "loss": 1.2957,
      "step": 1261
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.09558557583720882,
      "learning_rate": 5e-05,
      "loss": 1.1755,
      "step": 1262
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.09793069365544155,
      "learning_rate": 5e-05,
      "loss": 1.2805,
      "step": 1263
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.11905319553833751,
      "learning_rate": 5e-05,
      "loss": 1.1488,
      "step": 1264
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.12667648557528083,
      "learning_rate": 5e-05,
      "loss": 1.1817,
      "step": 1265
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.17320168990875578,
      "learning_rate": 5e-05,
      "loss": 1.1387,
      "step": 1266
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.1278704824906583,
      "learning_rate": 5e-05,
      "loss": 1.2801,
      "step": 1267
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.09857146933191926,
      "learning_rate": 5e-05,
      "loss": 1.2289,
      "step": 1268
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.11033316991181887,
      "learning_rate": 5e-05,
      "loss": 1.2567,
      "step": 1269
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.9573844042386731,
      "learning_rate": 5e-05,
      "loss": 1.2047,
      "step": 1270
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.1051122250248032,
      "learning_rate": 5e-05,
      "loss": 1.2515,
      "step": 1271
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.1437255080680373,
      "learning_rate": 5e-05,
      "loss": 1.2482,
      "step": 1272
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.0991494729841633,
      "learning_rate": 5e-05,
      "loss": 1.2842,
      "step": 1273
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.0972414511934356,
      "learning_rate": 5e-05,
      "loss": 1.1815,
      "step": 1274
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.11533577527558092,
      "learning_rate": 5e-05,
      "loss": 1.2547,
      "step": 1275
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.17134502324827014,
      "learning_rate": 5e-05,
      "loss": 1.113,
      "step": 1276
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.10589478661864486,
      "learning_rate": 5e-05,
      "loss": 1.2786,
      "step": 1277
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.10422140839238593,
      "learning_rate": 5e-05,
      "loss": 1.2973,
      "step": 1278
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.10640150155678055,
      "learning_rate": 5e-05,
      "loss": 1.1525,
      "step": 1279
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.10199851060213333,
      "learning_rate": 5e-05,
      "loss": 1.1229,
      "step": 1280
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.1223477356844984,
      "learning_rate": 5e-05,
      "loss": 1.1436,
      "step": 1281
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.09854064368856022,
      "learning_rate": 5e-05,
      "loss": 1.2149,
      "step": 1282
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.12059049956928705,
      "learning_rate": 5e-05,
      "loss": 1.2748,
      "step": 1283
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.10009505515058299,
      "learning_rate": 5e-05,
      "loss": 1.2496,
      "step": 1284
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.1057531566096711,
      "learning_rate": 5e-05,
      "loss": 1.2263,
      "step": 1285
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.10577195617365408,
      "learning_rate": 5e-05,
      "loss": 1.2097,
      "step": 1286
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.1980193546773249,
      "learning_rate": 5e-05,
      "loss": 1.2558,
      "step": 1287
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.10620780530453745,
      "learning_rate": 5e-05,
      "loss": 1.1121,
      "step": 1288
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.10364754509557948,
      "learning_rate": 5e-05,
      "loss": 1.2278,
      "step": 1289
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.1268398552835006,
      "learning_rate": 5e-05,
      "loss": 1.2659,
      "step": 1290
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.11118097887284956,
      "learning_rate": 5e-05,
      "loss": 1.2535,
      "step": 1291
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.18499773138538006,
      "learning_rate": 5e-05,
      "loss": 1.1819,
      "step": 1292
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.14794438042883248,
      "learning_rate": 5e-05,
      "loss": 1.2723,
      "step": 1293
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.10378984669475717,
      "learning_rate": 5e-05,
      "loss": 1.3342,
      "step": 1294
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.3840623510789001,
      "learning_rate": 5e-05,
      "loss": 1.2473,
      "step": 1295
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.13499019720704672,
      "learning_rate": 5e-05,
      "loss": 1.1873,
      "step": 1296
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.11083415018038016,
      "learning_rate": 5e-05,
      "loss": 1.3038,
      "step": 1297
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.09774055063425115,
      "learning_rate": 5e-05,
      "loss": 1.1524,
      "step": 1298
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.09765011460774314,
      "learning_rate": 5e-05,
      "loss": 1.1562,
      "step": 1299
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.12959918677475585,
      "learning_rate": 5e-05,
      "loss": 1.2451,
      "step": 1300
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.10307521658627149,
      "learning_rate": 5e-05,
      "loss": 1.2482,
      "step": 1301
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.10889075695796573,
      "learning_rate": 5e-05,
      "loss": 1.2032,
      "step": 1302
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.10274428682413997,
      "learning_rate": 5e-05,
      "loss": 1.2095,
      "step": 1303
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.09870991788841747,
      "learning_rate": 5e-05,
      "loss": 1.1679,
      "step": 1304
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.1029976635960567,
      "learning_rate": 5e-05,
      "loss": 1.197,
      "step": 1305
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.11565596154580056,
      "learning_rate": 5e-05,
      "loss": 1.2518,
      "step": 1306
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.11358697176280404,
      "learning_rate": 5e-05,
      "loss": 1.231,
      "step": 1307
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.11584857396336613,
      "learning_rate": 5e-05,
      "loss": 1.2431,
      "step": 1308
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.10126436030422854,
      "learning_rate": 5e-05,
      "loss": 1.3353,
      "step": 1309
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.12509494789947387,
      "learning_rate": 5e-05,
      "loss": 1.2041,
      "step": 1310
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.1184327130883153,
      "learning_rate": 5e-05,
      "loss": 1.233,
      "step": 1311
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.10464714266664168,
      "learning_rate": 5e-05,
      "loss": 1.2261,
      "step": 1312
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.12514815355665904,
      "learning_rate": 5e-05,
      "loss": 1.1561,
      "step": 1313
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.12311991854330846,
      "learning_rate": 5e-05,
      "loss": 1.1087,
      "step": 1314
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.09295582031960702,
      "learning_rate": 5e-05,
      "loss": 1.2152,
      "step": 1315
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.14449588211116057,
      "learning_rate": 5e-05,
      "loss": 1.2647,
      "step": 1316
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.10235199468766547,
      "learning_rate": 5e-05,
      "loss": 1.2049,
      "step": 1317
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.11350422082691311,
      "learning_rate": 5e-05,
      "loss": 1.2558,
      "step": 1318
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.12144887004278876,
      "learning_rate": 5e-05,
      "loss": 1.2685,
      "step": 1319
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.10173889195958385,
      "learning_rate": 5e-05,
      "loss": 1.2801,
      "step": 1320
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.09330810178399741,
      "learning_rate": 5e-05,
      "loss": 1.2512,
      "step": 1321
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.20161533425887576,
      "learning_rate": 5e-05,
      "loss": 1.1789,
      "step": 1322
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.09777849402957198,
      "learning_rate": 5e-05,
      "loss": 1.2417,
      "step": 1323
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.10024832098891394,
      "learning_rate": 5e-05,
      "loss": 1.2915,
      "step": 1324
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.11258369856811815,
      "learning_rate": 5e-05,
      "loss": 1.2514,
      "step": 1325
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.12484690094005808,
      "learning_rate": 5e-05,
      "loss": 1.3151,
      "step": 1326
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.0935577575829671,
      "learning_rate": 5e-05,
      "loss": 1.2521,
      "step": 1327
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.1210684422035205,
      "learning_rate": 5e-05,
      "loss": 1.1265,
      "step": 1328
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.09207941251078382,
      "learning_rate": 5e-05,
      "loss": 1.2198,
      "step": 1329
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.12309544282600764,
      "learning_rate": 5e-05,
      "loss": 1.2424,
      "step": 1330
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.10064914884191513,
      "learning_rate": 5e-05,
      "loss": 1.187,
      "step": 1331
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.13995361473968207,
      "learning_rate": 5e-05,
      "loss": 1.1866,
      "step": 1332
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.10713021403389816,
      "learning_rate": 5e-05,
      "loss": 1.2787,
      "step": 1333
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.12386001378771107,
      "learning_rate": 5e-05,
      "loss": 1.2367,
      "step": 1334
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.14112063187119603,
      "learning_rate": 5e-05,
      "loss": 1.1763,
      "step": 1335
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.10156292242573838,
      "learning_rate": 5e-05,
      "loss": 1.2417,
      "step": 1336
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.5023353070726944,
      "learning_rate": 5e-05,
      "loss": 1.2568,
      "step": 1337
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.11115935835706549,
      "learning_rate": 5e-05,
      "loss": 1.2205,
      "step": 1338
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.10000845594414244,
      "learning_rate": 5e-05,
      "loss": 1.2893,
      "step": 1339
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.10195023988800359,
      "learning_rate": 5e-05,
      "loss": 1.2801,
      "step": 1340
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.3067232561424585,
      "learning_rate": 5e-05,
      "loss": 1.2299,
      "step": 1341
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.10005294161976021,
      "learning_rate": 5e-05,
      "loss": 1.2635,
      "step": 1342
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.0926599419663251,
      "learning_rate": 5e-05,
      "loss": 1.2824,
      "step": 1343
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.16997862964953497,
      "learning_rate": 5e-05,
      "loss": 1.2689,
      "step": 1344
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.10425373316842217,
      "learning_rate": 5e-05,
      "loss": 1.1412,
      "step": 1345
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.10116618450255803,
      "learning_rate": 5e-05,
      "loss": 1.3225,
      "step": 1346
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.09712297309677503,
      "learning_rate": 5e-05,
      "loss": 1.2455,
      "step": 1347
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.09526406291414628,
      "learning_rate": 5e-05,
      "loss": 1.2307,
      "step": 1348
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.10066316805603513,
      "learning_rate": 5e-05,
      "loss": 1.1478,
      "step": 1349
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.10664910103833464,
      "learning_rate": 5e-05,
      "loss": 1.1798,
      "step": 1350
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.09373044345316567,
      "learning_rate": 5e-05,
      "loss": 1.243,
      "step": 1351
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.09009331726599838,
      "learning_rate": 5e-05,
      "loss": 1.2168,
      "step": 1352
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.2485364577633018,
      "learning_rate": 5e-05,
      "loss": 1.2433,
      "step": 1353
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.09513898211847613,
      "learning_rate": 5e-05,
      "loss": 1.2525,
      "step": 1354
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.13329990401583716,
      "learning_rate": 5e-05,
      "loss": 1.2002,
      "step": 1355
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.10449667016871154,
      "learning_rate": 5e-05,
      "loss": 1.1616,
      "step": 1356
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.09994582726380859,
      "learning_rate": 5e-05,
      "loss": 1.3169,
      "step": 1357
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.09877612528109277,
      "learning_rate": 5e-05,
      "loss": 1.3307,
      "step": 1358
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.11189316406658582,
      "learning_rate": 5e-05,
      "loss": 1.2293,
      "step": 1359
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.10185356183272931,
      "learning_rate": 5e-05,
      "loss": 1.234,
      "step": 1360
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.09507739812915995,
      "learning_rate": 5e-05,
      "loss": 1.279,
      "step": 1361
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.1163942518914868,
      "learning_rate": 5e-05,
      "loss": 1.1431,
      "step": 1362
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.103983513284656,
      "learning_rate": 5e-05,
      "loss": 1.1965,
      "step": 1363
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.10693226780267162,
      "learning_rate": 5e-05,
      "loss": 1.2534,
      "step": 1364
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.10701702402784265,
      "learning_rate": 5e-05,
      "loss": 1.2336,
      "step": 1365
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.09508301897524707,
      "learning_rate": 5e-05,
      "loss": 1.1621,
      "step": 1366
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.13472707990301636,
      "learning_rate": 5e-05,
      "loss": 1.255,
      "step": 1367
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.09638639506299534,
      "learning_rate": 5e-05,
      "loss": 1.2698,
      "step": 1368
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.148927462211784,
      "learning_rate": 5e-05,
      "loss": 1.2054,
      "step": 1369
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.09799235041711472,
      "learning_rate": 5e-05,
      "loss": 1.2038,
      "step": 1370
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.09420136770495892,
      "learning_rate": 5e-05,
      "loss": 1.2759,
      "step": 1371
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.10327592707615818,
      "learning_rate": 5e-05,
      "loss": 1.3487,
      "step": 1372
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.10648587942616909,
      "learning_rate": 5e-05,
      "loss": 1.2778,
      "step": 1373
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.10077774041822993,
      "learning_rate": 5e-05,
      "loss": 1.1275,
      "step": 1374
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.10851390832620712,
      "learning_rate": 5e-05,
      "loss": 1.2849,
      "step": 1375
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.10685085492856919,
      "learning_rate": 5e-05,
      "loss": 1.213,
      "step": 1376
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.33132745678315667,
      "learning_rate": 5e-05,
      "loss": 1.213,
      "step": 1377
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.10144441234398532,
      "learning_rate": 5e-05,
      "loss": 1.2017,
      "step": 1378
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.11228015380290499,
      "learning_rate": 5e-05,
      "loss": 1.1263,
      "step": 1379
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.10619109907523792,
      "learning_rate": 5e-05,
      "loss": 1.2028,
      "step": 1380
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.09927912077152588,
      "learning_rate": 5e-05,
      "loss": 1.1571,
      "step": 1381
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.09836226270654248,
      "learning_rate": 5e-05,
      "loss": 1.263,
      "step": 1382
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.10152642676398088,
      "learning_rate": 5e-05,
      "loss": 1.2906,
      "step": 1383
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.09751898942054647,
      "learning_rate": 5e-05,
      "loss": 1.2299,
      "step": 1384
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.09928849404743591,
      "learning_rate": 5e-05,
      "loss": 1.2162,
      "step": 1385
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.12489116214026824,
      "learning_rate": 5e-05,
      "loss": 1.3218,
      "step": 1386
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.10882496396878796,
      "learning_rate": 5e-05,
      "loss": 1.1562,
      "step": 1387
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.10726176666870928,
      "learning_rate": 5e-05,
      "loss": 1.3121,
      "step": 1388
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.12451799281699823,
      "learning_rate": 5e-05,
      "loss": 1.2435,
      "step": 1389
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.1063201573835307,
      "learning_rate": 5e-05,
      "loss": 1.1881,
      "step": 1390
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.09591833849880978,
      "learning_rate": 5e-05,
      "loss": 1.0813,
      "step": 1391
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.3608436435573168,
      "learning_rate": 5e-05,
      "loss": 1.2783,
      "step": 1392
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.09891988026600457,
      "learning_rate": 5e-05,
      "loss": 1.2458,
      "step": 1393
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.10372056524311288,
      "learning_rate": 5e-05,
      "loss": 1.2561,
      "step": 1394
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.11010379879458275,
      "learning_rate": 5e-05,
      "loss": 1.1742,
      "step": 1395
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.11577814654777499,
      "learning_rate": 5e-05,
      "loss": 1.2133,
      "step": 1396
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.09703009817213572,
      "learning_rate": 5e-05,
      "loss": 1.2666,
      "step": 1397
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.10605693309881119,
      "learning_rate": 5e-05,
      "loss": 1.211,
      "step": 1398
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.0953969154407503,
      "learning_rate": 5e-05,
      "loss": 1.2302,
      "step": 1399
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.1029669098774183,
      "learning_rate": 5e-05,
      "loss": 1.2036,
      "step": 1400
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.09681823509122052,
      "learning_rate": 5e-05,
      "loss": 1.2951,
      "step": 1401
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.11807096310067436,
      "learning_rate": 5e-05,
      "loss": 1.2065,
      "step": 1402
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.10137146652403635,
      "learning_rate": 5e-05,
      "loss": 1.194,
      "step": 1403
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.11503441758843483,
      "learning_rate": 5e-05,
      "loss": 1.1471,
      "step": 1404
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.11321304873658063,
      "learning_rate": 5e-05,
      "loss": 1.1208,
      "step": 1405
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.09959691816355418,
      "learning_rate": 5e-05,
      "loss": 1.2474,
      "step": 1406
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.10519968487918019,
      "learning_rate": 5e-05,
      "loss": 1.1389,
      "step": 1407
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.09696908055955931,
      "learning_rate": 5e-05,
      "loss": 1.2006,
      "step": 1408
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.10702366666252838,
      "learning_rate": 5e-05,
      "loss": 1.2117,
      "step": 1409
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.10076704123424733,
      "learning_rate": 5e-05,
      "loss": 1.2251,
      "step": 1410
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.0962787350921078,
      "learning_rate": 5e-05,
      "loss": 1.2286,
      "step": 1411
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.1102003262142478,
      "learning_rate": 5e-05,
      "loss": 1.1348,
      "step": 1412
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.23382426797734182,
      "learning_rate": 5e-05,
      "loss": 1.2689,
      "step": 1413
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.09619878014992354,
      "learning_rate": 5e-05,
      "loss": 1.2346,
      "step": 1414
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.10064237772902627,
      "learning_rate": 5e-05,
      "loss": 1.273,
      "step": 1415
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.11448682188068181,
      "learning_rate": 5e-05,
      "loss": 1.1405,
      "step": 1416
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.09456193036336086,
      "learning_rate": 5e-05,
      "loss": 1.2273,
      "step": 1417
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.10228441609601326,
      "learning_rate": 5e-05,
      "loss": 1.1198,
      "step": 1418
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.09922567877919913,
      "learning_rate": 5e-05,
      "loss": 1.2631,
      "step": 1419
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.19004659340585958,
      "learning_rate": 5e-05,
      "loss": 1.1986,
      "step": 1420
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.10754500601228272,
      "learning_rate": 5e-05,
      "loss": 1.1851,
      "step": 1421
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.09350976680922973,
      "learning_rate": 5e-05,
      "loss": 1.3649,
      "step": 1422
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.09001639847887033,
      "learning_rate": 5e-05,
      "loss": 1.224,
      "step": 1423
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.12001633209272844,
      "learning_rate": 5e-05,
      "loss": 1.1618,
      "step": 1424
    },
    {
      "epoch": 2.0,
      "step": 1424,
      "total_flos": 6427604718452736.0,
      "train_loss": 1.233065366703138,
      "train_runtime": 53767.7286,
      "train_samples_per_second": 0.847,
      "train_steps_per_second": 0.026
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 1424,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "total_flos": 6427604718452736.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}