{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0588235294117645,
  "eval_steps": 500,
  "global_step": 240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.00019922390686882426,
      "loss": 1.5465,
      "step": 1
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019842381085730289,
      "loss": 1.4494,
      "step": 2
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019762371484578152,
      "loss": 1.2437,
      "step": 3
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019682361883426012,
      "loss": 1.3019,
      "step": 4
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019602352282273875,
      "loss": 1.4664,
      "step": 5
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019522342681121735,
      "loss": 1.1706,
      "step": 6
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019442333079969598,
      "loss": 1.2089,
      "step": 7
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019362323478817458,
      "loss": 1.0329,
      "step": 8
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001928231387766532,
      "loss": 1.3136,
      "step": 9
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019202304276513184,
      "loss": 1.0903,
      "step": 10
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019122294675361044,
      "loss": 1.089,
      "step": 11
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019042285074208904,
      "loss": 1.2918,
      "step": 12
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018962275473056767,
      "loss": 1.0208,
      "step": 13
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001888226587190463,
      "loss": 1.2414,
      "step": 14
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00018802256270752493,
      "loss": 0.8309,
      "step": 15
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00018722246669600353,
      "loss": 1.0701,
      "step": 16
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018642237068448213,
      "loss": 1.103,
      "step": 17
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018562227467296076,
      "loss": 1.1536,
      "step": 18
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001848221786614394,
      "loss": 0.9786,
      "step": 19
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000184022082649918,
      "loss": 1.0474,
      "step": 20
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018322198663839662,
      "loss": 0.9066,
      "step": 21
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018242189062687522,
      "loss": 1.0756,
      "step": 22
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00018162179461535385,
      "loss": 0.9649,
      "step": 23
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00018082169860383248,
      "loss": 1.0698,
      "step": 24
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00018002160259231108,
      "loss": 1.0971,
      "step": 25
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001792215065807897,
      "loss": 1.0154,
      "step": 26
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00017842141056926834,
      "loss": 1.2113,
      "step": 27
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00017762131455774694,
      "loss": 1.0433,
      "step": 28
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00017682121854622554,
      "loss": 0.9149,
      "step": 29
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00017602112253470417,
      "loss": 1.294,
      "step": 30
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001752210265231828,
      "loss": 0.8756,
      "step": 31
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00017442093051166143,
      "loss": 0.9514,
      "step": 32
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00017362083450014,
      "loss": 0.7657,
      "step": 33
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00017282073848861863,
      "loss": 0.9848,
      "step": 34
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00017202064247709726,
      "loss": 0.9737,
      "step": 35
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001712205464655759,
      "loss": 0.6804,
      "step": 36
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001704204504540545,
      "loss": 1.0733,
      "step": 37
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001696203544425331,
      "loss": 0.984,
      "step": 38
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00016882025843101172,
      "loss": 0.7753,
      "step": 39
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00016802016241949035,
      "loss": 0.9925,
      "step": 40
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00016722006640796896,
      "loss": 0.4777,
      "step": 41
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00016641997039644758,
      "loss": 0.8519,
      "step": 42
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00016561987438492621,
      "loss": 0.8004,
      "step": 43
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00016481977837340482,
      "loss": 0.8533,
      "step": 44
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00016401968236188344,
      "loss": 0.5997,
      "step": 45
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00016321958635036205,
      "loss": 0.7882,
      "step": 46
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00016241949033884068,
      "loss": 1.0804,
      "step": 47
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0001616193943273193,
      "loss": 0.4132,
      "step": 48
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001608192983157979,
      "loss": 0.9914,
      "step": 49
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001600192023042765,
      "loss": 0.3964,
      "step": 50
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00015921910629275514,
      "loss": 0.5703,
      "step": 51
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00015841901028123377,
      "loss": 0.7238,
      "step": 52
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00015761891426971237,
      "loss": 0.6712,
      "step": 53
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015681881825819097,
      "loss": 0.6738,
      "step": 54
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001560187222466696,
      "loss": 0.6217,
      "step": 55
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015521862623514823,
      "loss": 0.5953,
      "step": 56
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00015441853022362686,
      "loss": 0.8303,
      "step": 57
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015361843421210546,
      "loss": 0.6253,
      "step": 58
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001528183382005841,
      "loss": 0.3754,
      "step": 59
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001520182421890627,
      "loss": 0.6664,
      "step": 60
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00015121814617754132,
      "loss": 0.6756,
      "step": 61
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00015041805016601992,
      "loss": 0.8601,
      "step": 62
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00014961795415449855,
      "loss": 0.6088,
      "step": 63
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014881785814297718,
      "loss": 0.5837,
      "step": 64
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00014801776213145578,
      "loss": 0.5813,
      "step": 65
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00014721766611993438,
      "loss": 0.672,
      "step": 66
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.000146417570108413,
      "loss": 0.9818,
      "step": 67
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00014561747409689164,
      "loss": 0.7044,
      "step": 68
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00014481737808537027,
      "loss": 0.4525,
      "step": 69
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00014401728207384887,
      "loss": 0.3649,
      "step": 70
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00014321718606232747,
      "loss": 0.4089,
      "step": 71
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001424170900508061,
      "loss": 0.4102,
      "step": 72
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00014161699403928473,
      "loss": 0.2403,
      "step": 73
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00014081689802776333,
      "loss": 0.3113,
      "step": 74
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00014001680201624196,
      "loss": 0.5503,
      "step": 75
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00013921670600472056,
      "loss": 0.6021,
      "step": 76
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0001384166099931992,
      "loss": 0.5271,
      "step": 77
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00013761651398167782,
      "loss": 0.3207,
      "step": 78
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00013681641797015642,
      "loss": 0.4899,
      "step": 79
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00013601632195863505,
      "loss": 0.3858,
      "step": 80
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00013521622594711365,
      "loss": 0.4361,
      "step": 81
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00013441612993559228,
      "loss": 0.3672,
      "step": 82
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00013361603392407088,
      "loss": 0.5378,
      "step": 83
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00013281593791254951,
      "loss": 0.3577,
      "step": 84
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00013201584190102814,
      "loss": 0.2658,
      "step": 85
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00013121574588950674,
      "loss": 0.2015,
      "step": 86
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00013041564987798535,
      "loss": 0.4888,
      "step": 87
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00012961555386646398,
      "loss": 0.3641,
      "step": 88
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0001288154578549426,
      "loss": 0.3613,
      "step": 89
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.00012801536184342123,
      "loss": 0.3576,
      "step": 90
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.00012721526583189984,
      "loss": 0.1833,
      "step": 91
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00012641516982037844,
      "loss": 0.1528,
      "step": 92
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.00012561507380885707,
      "loss": 0.5194,
      "step": 93
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0001248149777973357,
      "loss": 0.543,
      "step": 94
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0001240148817858143,
      "loss": 0.2746,
      "step": 95
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00012321478577429293,
      "loss": 0.1863,
      "step": 96
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.00012241468976277153,
      "loss": 0.4064,
      "step": 97
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.00012161459375125014,
      "loss": 0.4429,
      "step": 98
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.00012081449773972877,
      "loss": 0.32,
      "step": 99
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.00012001440172820739,
      "loss": 0.266,
      "step": 100
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00011921430571668602,
      "loss": 0.4243,
      "step": 101
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00011841420970516463,
      "loss": 0.381,
      "step": 102
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.00011761411369364323,
      "loss": 0.1964,
      "step": 103
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.00011681401768212186,
      "loss": 0.2786,
      "step": 104
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.00011601392167060048,
      "loss": 0.2606,
      "step": 105
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0001152138256590791,
      "loss": 0.1124,
      "step": 106
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00011441372964755772,
      "loss": 0.242,
      "step": 107
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.00011361363363603632,
      "loss": 0.1387,
      "step": 108
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.00011281353762451494,
      "loss": 0.1772,
      "step": 109
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.00011201344161299357,
      "loss": 0.1568,
      "step": 110
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.00011121334560147218,
      "loss": 0.2883,
      "step": 111
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.00011041324958995081,
      "loss": 0.2013,
      "step": 112
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.00010961315357842943,
      "loss": 0.2457,
      "step": 113
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.00010881305756690803,
      "loss": 0.1284,
      "step": 114
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.00010801296155538665,
      "loss": 0.1901,
      "step": 115
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.00010721286554386528,
      "loss": 0.1334,
      "step": 116
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.00010641276953234389,
      "loss": 0.1461,
      "step": 117
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.00010561267352082252,
      "loss": 0.2129,
      "step": 118
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.00010481257750930111,
      "loss": 0.0939,
      "step": 119
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.00010401248149777974,
      "loss": 0.1209,
      "step": 120
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.00010321238548625835,
      "loss": 0.1331,
      "step": 121
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.00010241228947473698,
      "loss": 0.0941,
      "step": 122
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.0001016121934632156,
      "loss": 0.2107,
      "step": 123
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.0001008120974516942,
      "loss": 0.2211,
      "step": 124
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.00010001200144017281,
      "loss": 0.145,
      "step": 125
    },
    {
      "epoch": 3.71,
      "learning_rate": 9.921190542865144e-05,
      "loss": 0.1024,
      "step": 126
    },
    {
      "epoch": 3.74,
      "learning_rate": 9.841180941713006e-05,
      "loss": 0.0663,
      "step": 127
    },
    {
      "epoch": 3.76,
      "learning_rate": 9.761171340560867e-05,
      "loss": 0.1352,
      "step": 128
    },
    {
      "epoch": 3.79,
      "learning_rate": 9.681161739408729e-05,
      "loss": 0.2258,
      "step": 129
    },
    {
      "epoch": 3.82,
      "learning_rate": 9.601152138256592e-05,
      "loss": 0.1926,
      "step": 130
    },
    {
      "epoch": 3.85,
      "learning_rate": 9.521142537104452e-05,
      "loss": 0.1149,
      "step": 131
    },
    {
      "epoch": 3.88,
      "learning_rate": 9.441132935952315e-05,
      "loss": 0.1301,
      "step": 132
    },
    {
      "epoch": 3.91,
      "learning_rate": 9.361123334800176e-05,
      "loss": 0.0552,
      "step": 133
    },
    {
      "epoch": 3.94,
      "learning_rate": 9.281113733648038e-05,
      "loss": 0.1837,
      "step": 134
    },
    {
      "epoch": 3.97,
      "learning_rate": 9.2011041324959e-05,
      "loss": 0.1085,
      "step": 135
    },
    {
      "epoch": 4.0,
      "learning_rate": 9.121094531343761e-05,
      "loss": 0.2303,
      "step": 136
    },
    {
      "epoch": 4.03,
      "learning_rate": 9.041084930191624e-05,
      "loss": 0.0498,
      "step": 137
    },
    {
      "epoch": 4.06,
      "learning_rate": 8.961075329039486e-05,
      "loss": 0.0452,
      "step": 138
    },
    {
      "epoch": 4.09,
      "learning_rate": 8.881065727887347e-05,
      "loss": 0.1161,
      "step": 139
    },
    {
      "epoch": 4.12,
      "learning_rate": 8.801056126735209e-05,
      "loss": 0.0441,
      "step": 140
    },
    {
      "epoch": 4.15,
      "learning_rate": 8.721046525583072e-05,
      "loss": 0.0704,
      "step": 141
    },
    {
      "epoch": 4.18,
      "learning_rate": 8.641036924430932e-05,
      "loss": 0.1103,
      "step": 142
    },
    {
      "epoch": 4.21,
      "learning_rate": 8.561027323278795e-05,
      "loss": 0.0313,
      "step": 143
    },
    {
      "epoch": 4.24,
      "learning_rate": 8.481017722126655e-05,
      "loss": 0.0494,
      "step": 144
    },
    {
      "epoch": 4.26,
      "learning_rate": 8.401008120974518e-05,
      "loss": 0.0805,
      "step": 145
    },
    {
      "epoch": 4.29,
      "learning_rate": 8.320998519822379e-05,
      "loss": 0.0512,
      "step": 146
    },
    {
      "epoch": 4.32,
      "learning_rate": 8.240988918670241e-05,
      "loss": 0.0442,
      "step": 147
    },
    {
      "epoch": 4.35,
      "learning_rate": 8.160979317518102e-05,
      "loss": 0.0944,
      "step": 148
    },
    {
      "epoch": 4.38,
      "learning_rate": 8.080969716365965e-05,
      "loss": 0.0621,
      "step": 149
    },
    {
      "epoch": 4.41,
      "learning_rate": 8.000960115213825e-05,
      "loss": 0.1191,
      "step": 150
    },
    {
      "epoch": 4.44,
      "learning_rate": 7.920950514061688e-05,
      "loss": 0.1518,
      "step": 151
    },
    {
      "epoch": 4.47,
      "learning_rate": 7.840940912909548e-05,
      "loss": 0.1002,
      "step": 152
    },
    {
      "epoch": 4.5,
      "learning_rate": 7.760931311757411e-05,
      "loss": 0.0803,
      "step": 153
    },
    {
      "epoch": 4.53,
      "learning_rate": 7.680921710605273e-05,
      "loss": 0.0582,
      "step": 154
    },
    {
      "epoch": 4.56,
      "learning_rate": 7.600912109453134e-05,
      "loss": 0.0745,
      "step": 155
    },
    {
      "epoch": 4.59,
      "learning_rate": 7.520902508300996e-05,
      "loss": 0.0844,
      "step": 156
    },
    {
      "epoch": 4.62,
      "learning_rate": 7.440892907148859e-05,
      "loss": 0.056,
      "step": 157
    },
    {
      "epoch": 4.65,
      "learning_rate": 7.360883305996719e-05,
      "loss": 0.1091,
      "step": 158
    },
    {
      "epoch": 4.68,
      "learning_rate": 7.280873704844582e-05,
      "loss": 0.0561,
      "step": 159
    },
    {
      "epoch": 4.71,
      "learning_rate": 7.200864103692444e-05,
      "loss": 0.0815,
      "step": 160
    },
    {
      "epoch": 4.74,
      "learning_rate": 7.120854502540305e-05,
      "loss": 0.0704,
      "step": 161
    },
    {
      "epoch": 4.76,
      "learning_rate": 7.040844901388167e-05,
      "loss": 0.0954,
      "step": 162
    },
    {
      "epoch": 4.79,
      "learning_rate": 6.960835300236028e-05,
      "loss": 0.0915,
      "step": 163
    },
    {
      "epoch": 4.82,
      "learning_rate": 6.880825699083891e-05,
      "loss": 0.0539,
      "step": 164
    },
    {
      "epoch": 4.85,
      "learning_rate": 6.800816097931753e-05,
      "loss": 0.0694,
      "step": 165
    },
    {
      "epoch": 4.88,
      "learning_rate": 6.720806496779614e-05,
      "loss": 0.0763,
      "step": 166
    },
    {
      "epoch": 4.91,
      "learning_rate": 6.640796895627476e-05,
      "loss": 0.0388,
      "step": 167
    },
    {
      "epoch": 4.94,
      "learning_rate": 6.560787294475337e-05,
      "loss": 0.1189,
      "step": 168
    },
    {
      "epoch": 4.97,
      "learning_rate": 6.480777693323199e-05,
      "loss": 0.0441,
      "step": 169
    },
    {
      "epoch": 5.0,
      "learning_rate": 6.400768092171062e-05,
      "loss": 0.0801,
      "step": 170
    },
    {
      "epoch": 5.03,
      "learning_rate": 6.320758491018922e-05,
      "loss": 0.027,
      "step": 171
    },
    {
      "epoch": 5.06,
      "learning_rate": 6.240748889866785e-05,
      "loss": 0.0346,
      "step": 172
    },
    {
      "epoch": 5.09,
      "learning_rate": 6.160739288714646e-05,
      "loss": 0.0385,
      "step": 173
    },
    {
      "epoch": 5.12,
      "learning_rate": 6.080729687562507e-05,
      "loss": 0.0575,
      "step": 174
    },
    {
      "epoch": 5.15,
      "learning_rate": 6.0007200864103694e-05,
      "loss": 0.042,
      "step": 175
    },
    {
      "epoch": 5.18,
      "learning_rate": 5.9207104852582316e-05,
      "loss": 0.0521,
      "step": 176
    },
    {
      "epoch": 5.21,
      "learning_rate": 5.840700884106093e-05,
      "loss": 0.054,
      "step": 177
    },
    {
      "epoch": 5.24,
      "learning_rate": 5.760691282953955e-05,
      "loss": 0.0503,
      "step": 178
    },
    {
      "epoch": 5.26,
      "learning_rate": 5.680681681801816e-05,
      "loss": 0.0285,
      "step": 179
    },
    {
      "epoch": 5.29,
      "learning_rate": 5.6006720806496785e-05,
      "loss": 0.0281,
      "step": 180
    },
    {
      "epoch": 5.32,
      "learning_rate": 5.520662479497541e-05,
      "loss": 0.0402,
      "step": 181
    },
    {
      "epoch": 5.35,
      "learning_rate": 5.4406528783454015e-05,
      "loss": 0.04,
      "step": 182
    },
    {
      "epoch": 5.38,
      "learning_rate": 5.360643277193264e-05,
      "loss": 0.044,
      "step": 183
    },
    {
      "epoch": 5.41,
      "learning_rate": 5.280633676041126e-05,
      "loss": 0.0264,
      "step": 184
    },
    {
      "epoch": 5.44,
      "learning_rate": 5.200624074888987e-05,
      "loss": 0.0379,
      "step": 185
    },
    {
      "epoch": 5.47,
      "learning_rate": 5.120614473736849e-05,
      "loss": 0.037,
      "step": 186
    },
    {
      "epoch": 5.5,
      "learning_rate": 5.04060487258471e-05,
      "loss": 0.0422,
      "step": 187
    },
    {
      "epoch": 5.53,
      "learning_rate": 4.960595271432572e-05,
      "loss": 0.0313,
      "step": 188
    },
    {
      "epoch": 5.56,
      "learning_rate": 4.880585670280434e-05,
      "loss": 0.0241,
      "step": 189
    },
    {
      "epoch": 5.59,
      "learning_rate": 4.800576069128296e-05,
      "loss": 0.0546,
      "step": 190
    },
    {
      "epoch": 5.62,
      "learning_rate": 4.7205664679761575e-05,
      "loss": 0.0305,
      "step": 191
    },
    {
      "epoch": 5.65,
      "learning_rate": 4.640556866824019e-05,
      "loss": 0.0364,
      "step": 192
    },
    {
      "epoch": 5.68,
      "learning_rate": 4.5605472656718805e-05,
      "loss": 0.0329,
      "step": 193
    },
    {
      "epoch": 5.71,
      "learning_rate": 4.480537664519743e-05,
      "loss": 0.0453,
      "step": 194
    },
    {
      "epoch": 5.74,
      "learning_rate": 4.400528063367604e-05,
      "loss": 0.0386,
      "step": 195
    },
    {
      "epoch": 5.76,
      "learning_rate": 4.320518462215466e-05,
      "loss": 0.0401,
      "step": 196
    },
    {
      "epoch": 5.79,
      "learning_rate": 4.2405088610633274e-05,
      "loss": 0.0527,
      "step": 197
    },
    {
      "epoch": 5.82,
      "learning_rate": 4.1604992599111896e-05,
      "loss": 0.0342,
      "step": 198
    },
    {
      "epoch": 5.85,
      "learning_rate": 4.080489658759051e-05,
      "loss": 0.0336,
      "step": 199
    },
    {
      "epoch": 5.88,
      "learning_rate": 4.000480057606913e-05,
      "loss": 0.034,
      "step": 200
    },
    {
      "epoch": 5.91,
      "learning_rate": 3.920470456454774e-05,
      "loss": 0.0316,
      "step": 201
    },
    {
      "epoch": 5.94,
      "learning_rate": 3.8404608553026365e-05,
      "loss": 0.0537,
      "step": 202
    },
    {
      "epoch": 5.97,
      "learning_rate": 3.760451254150498e-05,
      "loss": 0.0348,
      "step": 203
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.6804416529983595e-05,
      "loss": 0.0525,
      "step": 204
    },
    {
      "epoch": 6.03,
      "learning_rate": 3.600432051846222e-05,
      "loss": 0.0264,
      "step": 205
    },
    {
      "epoch": 6.06,
      "learning_rate": 3.520422450694083e-05,
      "loss": 0.0216,
      "step": 206
    },
    {
      "epoch": 6.09,
      "learning_rate": 3.4404128495419455e-05,
      "loss": 0.0232,
      "step": 207
    },
    {
      "epoch": 6.12,
      "learning_rate": 3.360403248389807e-05,
      "loss": 0.0342,
      "step": 208
    },
    {
      "epoch": 6.15,
      "learning_rate": 3.2803936472376686e-05,
      "loss": 0.0196,
      "step": 209
    },
    {
      "epoch": 6.18,
      "learning_rate": 3.200384046085531e-05,
      "loss": 0.0292,
      "step": 210
    },
    {
      "epoch": 6.21,
      "learning_rate": 3.1203744449333924e-05,
      "loss": 0.02,
      "step": 211
    },
    {
      "epoch": 6.24,
      "learning_rate": 3.0403648437812536e-05,
      "loss": 0.0243,
      "step": 212
    },
    {
      "epoch": 6.26,
      "learning_rate": 2.9603552426291158e-05,
      "loss": 0.0223,
      "step": 213
    },
    {
      "epoch": 6.29,
      "learning_rate": 2.8803456414769773e-05,
      "loss": 0.017,
      "step": 214
    },
    {
      "epoch": 6.32,
      "learning_rate": 2.8003360403248392e-05,
      "loss": 0.0201,
      "step": 215
    },
    {
      "epoch": 6.35,
      "learning_rate": 2.7203264391727008e-05,
      "loss": 0.0368,
      "step": 216
    },
    {
      "epoch": 6.38,
      "learning_rate": 2.640316838020563e-05,
      "loss": 0.0228,
      "step": 217
    },
    {
      "epoch": 6.41,
      "learning_rate": 2.5603072368684245e-05,
      "loss": 0.0241,
      "step": 218
    },
    {
      "epoch": 6.44,
      "learning_rate": 2.480297635716286e-05,
      "loss": 0.025,
      "step": 219
    },
    {
      "epoch": 6.47,
      "learning_rate": 2.400288034564148e-05,
      "loss": 0.0261,
      "step": 220
    },
    {
      "epoch": 6.5,
      "learning_rate": 2.3202784334120095e-05,
      "loss": 0.026,
      "step": 221
    },
    {
      "epoch": 6.53,
      "learning_rate": 2.2402688322598714e-05,
      "loss": 0.0242,
      "step": 222
    },
    {
      "epoch": 6.56,
      "learning_rate": 2.160259231107733e-05,
      "loss": 0.029,
      "step": 223
    },
    {
      "epoch": 6.59,
      "learning_rate": 2.0802496299555948e-05,
      "loss": 0.0305,
      "step": 224
    },
    {
      "epoch": 6.62,
      "learning_rate": 2.0002400288034563e-05,
      "loss": 0.0263,
      "step": 225
    },
    {
      "epoch": 6.65,
      "learning_rate": 1.9202304276513182e-05,
      "loss": 0.021,
      "step": 226
    },
    {
      "epoch": 6.68,
      "learning_rate": 1.8402208264991798e-05,
      "loss": 0.0295,
      "step": 227
    },
    {
      "epoch": 6.71,
      "learning_rate": 1.7602112253470417e-05,
      "loss": 0.0276,
      "step": 228
    },
    {
      "epoch": 6.74,
      "learning_rate": 1.6802016241949035e-05,
      "loss": 0.023,
      "step": 229
    },
    {
      "epoch": 6.76,
      "learning_rate": 1.6001920230427654e-05,
      "loss": 0.0251,
      "step": 230
    },
    {
      "epoch": 6.79,
      "learning_rate": 1.5201824218906268e-05,
      "loss": 0.0415,
      "step": 231
    },
    {
      "epoch": 6.82,
      "learning_rate": 1.4401728207384887e-05,
      "loss": 0.0292,
      "step": 232
    },
    {
      "epoch": 6.85,
      "learning_rate": 1.3601632195863504e-05,
      "loss": 0.0268,
      "step": 233
    },
    {
      "epoch": 6.88,
      "learning_rate": 1.2801536184342123e-05,
      "loss": 0.0265,
      "step": 234
    },
    {
      "epoch": 6.91,
      "learning_rate": 1.200144017282074e-05,
      "loss": 0.0208,
      "step": 235
    },
    {
      "epoch": 6.94,
      "learning_rate": 1.1201344161299357e-05,
      "loss": 0.0231,
      "step": 236
    },
    {
      "epoch": 6.97,
      "learning_rate": 1.0401248149777974e-05,
      "loss": 0.022,
      "step": 237
    },
    {
      "epoch": 7.0,
      "learning_rate": 9.601152138256591e-06,
      "loss": 0.0242,
      "step": 238
    },
    {
      "epoch": 7.03,
      "learning_rate": 8.801056126735208e-06,
      "loss": 0.0155,
      "step": 239
    },
    {
      "epoch": 7.06,
      "learning_rate": 8.000960115213827e-06,
      "loss": 0.0183,
      "step": 240
    }
  ],
  "logging_steps": 1,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 20,
  "total_flos": 1.5323280428875776e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}