WanjiaAlicia's picture
Upload model
ee6b175 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 405,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012345679012345678,
"grad_norm": 5.322886485316676,
"learning_rate": 1.951219512195122e-06,
"loss": 0.8713,
"step": 1
},
{
"epoch": 0.024691358024691357,
"grad_norm": 5.297045656067237,
"learning_rate": 3.902439024390244e-06,
"loss": 0.8617,
"step": 2
},
{
"epoch": 0.037037037037037035,
"grad_norm": 4.964177426655451,
"learning_rate": 5.853658536585366e-06,
"loss": 0.8557,
"step": 3
},
{
"epoch": 0.04938271604938271,
"grad_norm": 3.773649879416999,
"learning_rate": 7.804878048780489e-06,
"loss": 0.8258,
"step": 4
},
{
"epoch": 0.06172839506172839,
"grad_norm": 2.0170140516019943,
"learning_rate": 9.756097560975611e-06,
"loss": 0.7756,
"step": 5
},
{
"epoch": 0.07407407407407407,
"grad_norm": 3.884073569291856,
"learning_rate": 1.1707317073170731e-05,
"loss": 0.786,
"step": 6
},
{
"epoch": 0.08641975308641975,
"grad_norm": 4.3463765308085005,
"learning_rate": 1.3658536585365855e-05,
"loss": 0.7873,
"step": 7
},
{
"epoch": 0.09876543209876543,
"grad_norm": 4.931673812582102,
"learning_rate": 1.5609756097560978e-05,
"loss": 0.7584,
"step": 8
},
{
"epoch": 0.1111111111111111,
"grad_norm": 3.834447178572324,
"learning_rate": 1.75609756097561e-05,
"loss": 0.7462,
"step": 9
},
{
"epoch": 0.12345679012345678,
"grad_norm": 2.179837729025759,
"learning_rate": 1.9512195121951222e-05,
"loss": 0.6981,
"step": 10
},
{
"epoch": 0.13580246913580246,
"grad_norm": 2.101488664762724,
"learning_rate": 2.1463414634146344e-05,
"loss": 0.6788,
"step": 11
},
{
"epoch": 0.14814814814814814,
"grad_norm": 1.5969780288722668,
"learning_rate": 2.3414634146341463e-05,
"loss": 0.6542,
"step": 12
},
{
"epoch": 0.16049382716049382,
"grad_norm": 1.2878152911707546,
"learning_rate": 2.536585365853659e-05,
"loss": 0.6401,
"step": 13
},
{
"epoch": 0.1728395061728395,
"grad_norm": 1.110122058562916,
"learning_rate": 2.731707317073171e-05,
"loss": 0.6224,
"step": 14
},
{
"epoch": 0.18518518518518517,
"grad_norm": 0.9441382009144876,
"learning_rate": 2.926829268292683e-05,
"loss": 0.6147,
"step": 15
},
{
"epoch": 0.19753086419753085,
"grad_norm": 1.0755606503445887,
"learning_rate": 3.1219512195121955e-05,
"loss": 0.608,
"step": 16
},
{
"epoch": 0.20987654320987653,
"grad_norm": 1.0317574737428319,
"learning_rate": 3.3170731707317074e-05,
"loss": 0.5964,
"step": 17
},
{
"epoch": 0.2222222222222222,
"grad_norm": 1.1016699420428528,
"learning_rate": 3.51219512195122e-05,
"loss": 0.5827,
"step": 18
},
{
"epoch": 0.2345679012345679,
"grad_norm": 1.2684998671325824,
"learning_rate": 3.7073170731707325e-05,
"loss": 0.5863,
"step": 19
},
{
"epoch": 0.24691358024691357,
"grad_norm": 1.1450067110010247,
"learning_rate": 3.9024390243902444e-05,
"loss": 0.5828,
"step": 20
},
{
"epoch": 0.25925925925925924,
"grad_norm": 0.9761661263181526,
"learning_rate": 4.097560975609756e-05,
"loss": 0.5699,
"step": 21
},
{
"epoch": 0.2716049382716049,
"grad_norm": 0.8094703924890408,
"learning_rate": 4.292682926829269e-05,
"loss": 0.5705,
"step": 22
},
{
"epoch": 0.2839506172839506,
"grad_norm": 1.1556501519240183,
"learning_rate": 4.4878048780487814e-05,
"loss": 0.5505,
"step": 23
},
{
"epoch": 0.2962962962962963,
"grad_norm": 1.1904158496263302,
"learning_rate": 4.6829268292682926e-05,
"loss": 0.5564,
"step": 24
},
{
"epoch": 0.30864197530864196,
"grad_norm": 1.3992365789774508,
"learning_rate": 4.878048780487805e-05,
"loss": 0.5517,
"step": 25
},
{
"epoch": 0.32098765432098764,
"grad_norm": 0.7997862572956267,
"learning_rate": 5.073170731707318e-05,
"loss": 0.5488,
"step": 26
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.952625422206775,
"learning_rate": 5.26829268292683e-05,
"loss": 0.5494,
"step": 27
},
{
"epoch": 0.345679012345679,
"grad_norm": 1.5935135402175304,
"learning_rate": 5.463414634146342e-05,
"loss": 0.5527,
"step": 28
},
{
"epoch": 0.35802469135802467,
"grad_norm": 1.2248225513278832,
"learning_rate": 5.658536585365854e-05,
"loss": 0.5404,
"step": 29
},
{
"epoch": 0.37037037037037035,
"grad_norm": 1.1987238686766297,
"learning_rate": 5.853658536585366e-05,
"loss": 0.5467,
"step": 30
},
{
"epoch": 0.38271604938271603,
"grad_norm": 1.7560415296488376,
"learning_rate": 6.0487804878048785e-05,
"loss": 0.5427,
"step": 31
},
{
"epoch": 0.3950617283950617,
"grad_norm": 0.9869800217044912,
"learning_rate": 6.243902439024391e-05,
"loss": 0.5364,
"step": 32
},
{
"epoch": 0.4074074074074074,
"grad_norm": 1.3759308961313441,
"learning_rate": 6.439024390243903e-05,
"loss": 0.535,
"step": 33
},
{
"epoch": 0.41975308641975306,
"grad_norm": 0.848280656571499,
"learning_rate": 6.634146341463415e-05,
"loss": 0.5255,
"step": 34
},
{
"epoch": 0.43209876543209874,
"grad_norm": 1.5834791375974373,
"learning_rate": 6.829268292682927e-05,
"loss": 0.5463,
"step": 35
},
{
"epoch": 0.4444444444444444,
"grad_norm": 1.3946299749030078,
"learning_rate": 7.02439024390244e-05,
"loss": 0.5329,
"step": 36
},
{
"epoch": 0.4567901234567901,
"grad_norm": 2.4553544008908896,
"learning_rate": 7.219512195121952e-05,
"loss": 0.5469,
"step": 37
},
{
"epoch": 0.4691358024691358,
"grad_norm": 1.4448518801644223,
"learning_rate": 7.414634146341465e-05,
"loss": 0.5384,
"step": 38
},
{
"epoch": 0.48148148148148145,
"grad_norm": 2.366228950235355,
"learning_rate": 7.609756097560976e-05,
"loss": 0.5331,
"step": 39
},
{
"epoch": 0.49382716049382713,
"grad_norm": 1.606851424746494,
"learning_rate": 7.804878048780489e-05,
"loss": 0.5387,
"step": 40
},
{
"epoch": 0.5061728395061729,
"grad_norm": 1.5736626742577726,
"learning_rate": 8e-05,
"loss": 0.5215,
"step": 41
},
{
"epoch": 0.5185185185185185,
"grad_norm": 1.9430399946541783,
"learning_rate": 7.999851021266518e-05,
"loss": 0.5218,
"step": 42
},
{
"epoch": 0.5308641975308642,
"grad_norm": 1.5970596690336833,
"learning_rate": 7.999404096163398e-05,
"loss": 0.5249,
"step": 43
},
{
"epoch": 0.5432098765432098,
"grad_norm": 1.3518955116038844,
"learning_rate": 7.998659257981813e-05,
"loss": 0.5125,
"step": 44
},
{
"epoch": 0.5555555555555556,
"grad_norm": 1.065342246785812,
"learning_rate": 7.997616562204282e-05,
"loss": 0.516,
"step": 45
},
{
"epoch": 0.5679012345679012,
"grad_norm": 0.961399130642479,
"learning_rate": 7.996276086500558e-05,
"loss": 0.5175,
"step": 46
},
{
"epoch": 0.5802469135802469,
"grad_norm": 1.6746336809141793,
"learning_rate": 7.994637930721825e-05,
"loss": 0.517,
"step": 47
},
{
"epoch": 0.5925925925925926,
"grad_norm": 1.5584433959820718,
"learning_rate": 7.99270221689327e-05,
"loss": 0.5192,
"step": 48
},
{
"epoch": 0.6049382716049383,
"grad_norm": 1.1658481619505876,
"learning_rate": 7.990469089204992e-05,
"loss": 0.5026,
"step": 49
},
{
"epoch": 0.6172839506172839,
"grad_norm": 1.1432735287000564,
"learning_rate": 7.987938714001254e-05,
"loss": 0.5051,
"step": 50
},
{
"epoch": 0.6296296296296297,
"grad_norm": 1.6729263804344565,
"learning_rate": 7.985111279768106e-05,
"loss": 0.5208,
"step": 51
},
{
"epoch": 0.6419753086419753,
"grad_norm": 1.8058261166724783,
"learning_rate": 7.981986997119334e-05,
"loss": 0.5028,
"step": 52
},
{
"epoch": 0.654320987654321,
"grad_norm": 0.9551798887699284,
"learning_rate": 7.978566098780771e-05,
"loss": 0.5023,
"step": 53
},
{
"epoch": 0.6666666666666666,
"grad_norm": 2.6120888775776003,
"learning_rate": 7.974848839572971e-05,
"loss": 0.5073,
"step": 54
},
{
"epoch": 0.6790123456790124,
"grad_norm": 1.6504732308976957,
"learning_rate": 7.970835496392216e-05,
"loss": 0.5197,
"step": 55
},
{
"epoch": 0.691358024691358,
"grad_norm": 2.4813850162470694,
"learning_rate": 7.9665263681899e-05,
"loss": 0.5065,
"step": 56
},
{
"epoch": 0.7037037037037037,
"grad_norm": 2.0085317140110464,
"learning_rate": 7.961921775950254e-05,
"loss": 0.5186,
"step": 57
},
{
"epoch": 0.7160493827160493,
"grad_norm": 2.1727130740463254,
"learning_rate": 7.957022062666436e-05,
"loss": 0.5138,
"step": 58
},
{
"epoch": 0.7283950617283951,
"grad_norm": 1.7923872395834526,
"learning_rate": 7.951827593314987e-05,
"loss": 0.5154,
"step": 59
},
{
"epoch": 0.7407407407407407,
"grad_norm": 1.6455141916519003,
"learning_rate": 7.946338754828639e-05,
"loss": 0.508,
"step": 60
},
{
"epoch": 0.7530864197530864,
"grad_norm": 1.2020850632554296,
"learning_rate": 7.940555956067495e-05,
"loss": 0.5029,
"step": 61
},
{
"epoch": 0.7654320987654321,
"grad_norm": 1.4345699160882657,
"learning_rate": 7.934479627788576e-05,
"loss": 0.5081,
"step": 62
},
{
"epoch": 0.7777777777777778,
"grad_norm": 1.1706979555619268,
"learning_rate": 7.928110222613723e-05,
"loss": 0.5013,
"step": 63
},
{
"epoch": 0.7901234567901234,
"grad_norm": 1.0822260503444048,
"learning_rate": 7.921448214995895e-05,
"loss": 0.5009,
"step": 64
},
{
"epoch": 0.8024691358024691,
"grad_norm": 0.9538983846582979,
"learning_rate": 7.914494101183822e-05,
"loss": 0.5048,
"step": 65
},
{
"epoch": 0.8148148148148148,
"grad_norm": 1.2772663076589637,
"learning_rate": 7.907248399185037e-05,
"loss": 0.5068,
"step": 66
},
{
"epoch": 0.8271604938271605,
"grad_norm": 0.9753447960969902,
"learning_rate": 7.899711648727294e-05,
"loss": 0.4967,
"step": 67
},
{
"epoch": 0.8395061728395061,
"grad_norm": 1.278582421674819,
"learning_rate": 7.891884411218364e-05,
"loss": 0.4876,
"step": 68
},
{
"epoch": 0.8518518518518519,
"grad_norm": 1.2296613613599487,
"learning_rate": 7.883767269704209e-05,
"loss": 0.4902,
"step": 69
},
{
"epoch": 0.8641975308641975,
"grad_norm": 1.1659409845757795,
"learning_rate": 7.875360828825562e-05,
"loss": 0.4926,
"step": 70
},
{
"epoch": 0.8765432098765432,
"grad_norm": 0.9109060592449263,
"learning_rate": 7.866665714772879e-05,
"loss": 0.4992,
"step": 71
},
{
"epoch": 0.8888888888888888,
"grad_norm": 1.1413101315936145,
"learning_rate": 7.8576825752397e-05,
"loss": 0.4944,
"step": 72
},
{
"epoch": 0.9012345679012346,
"grad_norm": 1.5501956716372292,
"learning_rate": 7.848412079374403e-05,
"loss": 0.5036,
"step": 73
},
{
"epoch": 0.9135802469135802,
"grad_norm": 0.8833612034769314,
"learning_rate": 7.838854917730351e-05,
"loss": 0.4956,
"step": 74
},
{
"epoch": 0.9259259259259259,
"grad_norm": 1.6382790184141087,
"learning_rate": 7.829011802214464e-05,
"loss": 0.5049,
"step": 75
},
{
"epoch": 0.9382716049382716,
"grad_norm": 0.8824015261456967,
"learning_rate": 7.818883466034184e-05,
"loss": 0.5073,
"step": 76
},
{
"epoch": 0.9506172839506173,
"grad_norm": 1.8874422790227483,
"learning_rate": 7.808470663642856e-05,
"loss": 0.5038,
"step": 77
},
{
"epoch": 0.9629629629629629,
"grad_norm": 1.151698216260373,
"learning_rate": 7.797774170683542e-05,
"loss": 0.4987,
"step": 78
},
{
"epoch": 0.9753086419753086,
"grad_norm": 1.8822125796547127,
"learning_rate": 7.786794783931225e-05,
"loss": 0.4955,
"step": 79
},
{
"epoch": 0.9876543209876543,
"grad_norm": 1.3793553962064276,
"learning_rate": 7.775533321233471e-05,
"loss": 0.5098,
"step": 80
},
{
"epoch": 1.0,
"grad_norm": 1.4900485689809222,
"learning_rate": 7.763990621449507e-05,
"loss": 0.4941,
"step": 81
},
{
"epoch": 1.0123456790123457,
"grad_norm": 1.2191759152743815,
"learning_rate": 7.752167544387728e-05,
"loss": 0.4824,
"step": 82
},
{
"epoch": 1.0246913580246915,
"grad_norm": 0.9817036892343542,
"learning_rate": 7.740064970741661e-05,
"loss": 0.4677,
"step": 83
},
{
"epoch": 1.037037037037037,
"grad_norm": 0.9505715870347944,
"learning_rate": 7.727683802024347e-05,
"loss": 0.4755,
"step": 84
},
{
"epoch": 1.0493827160493827,
"grad_norm": 0.9315786466714934,
"learning_rate": 7.715024960501209e-05,
"loss": 0.4626,
"step": 85
},
{
"epoch": 1.0617283950617284,
"grad_norm": 1.088912497598927,
"learning_rate": 7.702089389121335e-05,
"loss": 0.4699,
"step": 86
},
{
"epoch": 1.074074074074074,
"grad_norm": 0.7664961821150688,
"learning_rate": 7.688878051447243e-05,
"loss": 0.4632,
"step": 87
},
{
"epoch": 1.0864197530864197,
"grad_norm": 0.7118117556462173,
"learning_rate": 7.675391931583109e-05,
"loss": 0.4694,
"step": 88
},
{
"epoch": 1.0987654320987654,
"grad_norm": 0.8838029650550034,
"learning_rate": 7.661632034101466e-05,
"loss": 0.4685,
"step": 89
},
{
"epoch": 1.1111111111111112,
"grad_norm": 1.0456749479001006,
"learning_rate": 7.64759938396836e-05,
"loss": 0.4652,
"step": 90
},
{
"epoch": 1.123456790123457,
"grad_norm": 0.9296714999836658,
"learning_rate": 7.633295026467016e-05,
"loss": 0.4557,
"step": 91
},
{
"epoch": 1.1358024691358024,
"grad_norm": 0.7784127512214979,
"learning_rate": 7.618720027119966e-05,
"loss": 0.4576,
"step": 92
},
{
"epoch": 1.1481481481481481,
"grad_norm": 0.7773052206833756,
"learning_rate": 7.603875471609677e-05,
"loss": 0.4602,
"step": 93
},
{
"epoch": 1.1604938271604939,
"grad_norm": 1.1454144308753773,
"learning_rate": 7.588762465697693e-05,
"loss": 0.4624,
"step": 94
},
{
"epoch": 1.1728395061728394,
"grad_norm": 0.9378102331091442,
"learning_rate": 7.573382135142253e-05,
"loss": 0.4641,
"step": 95
},
{
"epoch": 1.1851851851851851,
"grad_norm": 0.9068527199171179,
"learning_rate": 7.55773562561444e-05,
"loss": 0.4498,
"step": 96
},
{
"epoch": 1.1975308641975309,
"grad_norm": 0.9300994723441598,
"learning_rate": 7.541824102612839e-05,
"loss": 0.46,
"step": 97
},
{
"epoch": 1.2098765432098766,
"grad_norm": 1.0104590943724414,
"learning_rate": 7.525648751376726e-05,
"loss": 0.456,
"step": 98
},
{
"epoch": 1.2222222222222223,
"grad_norm": 1.0168144609561725,
"learning_rate": 7.509210776797768e-05,
"loss": 0.4585,
"step": 99
},
{
"epoch": 1.2345679012345678,
"grad_norm": 0.8394713299392315,
"learning_rate": 7.492511403330284e-05,
"loss": 0.4543,
"step": 100
},
{
"epoch": 1.2469135802469136,
"grad_norm": 0.6254433810264461,
"learning_rate": 7.475551874900027e-05,
"loss": 0.4535,
"step": 101
},
{
"epoch": 1.2592592592592593,
"grad_norm": 0.6014772324908465,
"learning_rate": 7.458333454811531e-05,
"loss": 0.4558,
"step": 102
},
{
"epoch": 1.2716049382716048,
"grad_norm": 0.6719474936653222,
"learning_rate": 7.440857425654004e-05,
"loss": 0.4474,
"step": 103
},
{
"epoch": 1.2839506172839505,
"grad_norm": 0.8289366172315764,
"learning_rate": 7.42312508920579e-05,
"loss": 0.452,
"step": 104
},
{
"epoch": 1.2962962962962963,
"grad_norm": 1.1119177471943609,
"learning_rate": 7.405137766337406e-05,
"loss": 0.4615,
"step": 105
},
{
"epoch": 1.308641975308642,
"grad_norm": 1.1864543763821342,
"learning_rate": 7.386896796913137e-05,
"loss": 0.4595,
"step": 106
},
{
"epoch": 1.3209876543209877,
"grad_norm": 0.7739869856668281,
"learning_rate": 7.368403539691247e-05,
"loss": 0.4526,
"step": 107
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.7500250889954546,
"learning_rate": 7.349659372222755e-05,
"loss": 0.4499,
"step": 108
},
{
"epoch": 1.345679012345679,
"grad_norm": 1.0110160098128433,
"learning_rate": 7.330665690748825e-05,
"loss": 0.4598,
"step": 109
},
{
"epoch": 1.3580246913580247,
"grad_norm": 1.240318418546968,
"learning_rate": 7.311423910096764e-05,
"loss": 0.4531,
"step": 110
},
{
"epoch": 1.3703703703703702,
"grad_norm": 0.7673358482948583,
"learning_rate": 7.291935463574626e-05,
"loss": 0.4472,
"step": 111
},
{
"epoch": 1.382716049382716,
"grad_norm": 0.9290397269601804,
"learning_rate": 7.272201802864452e-05,
"loss": 0.4524,
"step": 112
},
{
"epoch": 1.3950617283950617,
"grad_norm": 1.200427789224473,
"learning_rate": 7.25222439791413e-05,
"loss": 0.4531,
"step": 113
},
{
"epoch": 1.4074074074074074,
"grad_norm": 0.8914574952010766,
"learning_rate": 7.232004736827907e-05,
"loss": 0.4614,
"step": 114
},
{
"epoch": 1.4197530864197532,
"grad_norm": 1.072583649734927,
"learning_rate": 7.21154432575553e-05,
"loss": 0.4528,
"step": 115
},
{
"epoch": 1.4320987654320987,
"grad_norm": 0.7180130997337799,
"learning_rate": 7.190844688780065e-05,
"loss": 0.4492,
"step": 116
},
{
"epoch": 1.4444444444444444,
"grad_norm": 0.672503509002727,
"learning_rate": 7.169907367804363e-05,
"loss": 0.4533,
"step": 117
},
{
"epoch": 1.4567901234567902,
"grad_norm": 0.69958335114305,
"learning_rate": 7.148733922436201e-05,
"loss": 0.446,
"step": 118
},
{
"epoch": 1.4691358024691357,
"grad_norm": 0.7653453417783888,
"learning_rate": 7.12732592987212e-05,
"loss": 0.4456,
"step": 119
},
{
"epoch": 1.4814814814814814,
"grad_norm": 0.6310721044962515,
"learning_rate": 7.105684984779928e-05,
"loss": 0.4444,
"step": 120
},
{
"epoch": 1.4938271604938271,
"grad_norm": 0.6151795732030567,
"learning_rate": 7.083812699179919e-05,
"loss": 0.4465,
"step": 121
},
{
"epoch": 1.5061728395061729,
"grad_norm": 0.6874616448091606,
"learning_rate": 7.061710702324799e-05,
"loss": 0.4508,
"step": 122
},
{
"epoch": 1.5185185185185186,
"grad_norm": 0.6395722108011573,
"learning_rate": 7.039380640578316e-05,
"loss": 0.4462,
"step": 123
},
{
"epoch": 1.5308641975308643,
"grad_norm": 1.0391636044709032,
"learning_rate": 7.016824177292629e-05,
"loss": 0.4506,
"step": 124
},
{
"epoch": 1.5432098765432098,
"grad_norm": 1.209612143815189,
"learning_rate": 6.994042992684406e-05,
"loss": 0.444,
"step": 125
},
{
"epoch": 1.5555555555555556,
"grad_norm": 0.6126615919119747,
"learning_rate": 6.971038783709658e-05,
"loss": 0.4503,
"step": 126
},
{
"epoch": 1.567901234567901,
"grad_norm": 0.7148367458249104,
"learning_rate": 6.947813263937347e-05,
"loss": 0.4606,
"step": 127
},
{
"epoch": 1.5802469135802468,
"grad_norm": 1.0428988763055895,
"learning_rate": 6.924368163421733e-05,
"loss": 0.4467,
"step": 128
},
{
"epoch": 1.5925925925925926,
"grad_norm": 1.1843461844631857,
"learning_rate": 6.900705228573507e-05,
"loss": 0.452,
"step": 129
},
{
"epoch": 1.6049382716049383,
"grad_norm": 0.7127612179405008,
"learning_rate": 6.876826222029699e-05,
"loss": 0.4497,
"step": 130
},
{
"epoch": 1.617283950617284,
"grad_norm": 0.48971010045507035,
"learning_rate": 6.852732922522385e-05,
"loss": 0.4452,
"step": 131
},
{
"epoch": 1.6296296296296298,
"grad_norm": 0.6614951195691181,
"learning_rate": 6.828427124746191e-05,
"loss": 0.4499,
"step": 132
},
{
"epoch": 1.6419753086419753,
"grad_norm": 0.759726041736274,
"learning_rate": 6.803910639224598e-05,
"loss": 0.4479,
"step": 133
},
{
"epoch": 1.654320987654321,
"grad_norm": 0.7326050738916848,
"learning_rate": 6.77918529217509e-05,
"loss": 0.4485,
"step": 134
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.664731323528839,
"learning_rate": 6.754252925373109e-05,
"loss": 0.4369,
"step": 135
},
{
"epoch": 1.6790123456790123,
"grad_norm": 0.6194905151290093,
"learning_rate": 6.729115396014871e-05,
"loss": 0.4392,
"step": 136
},
{
"epoch": 1.691358024691358,
"grad_norm": 0.7257710866052547,
"learning_rate": 6.703774576579018e-05,
"loss": 0.4466,
"step": 137
},
{
"epoch": 1.7037037037037037,
"grad_norm": 0.913815195106407,
"learning_rate": 6.678232354687144e-05,
"loss": 0.4485,
"step": 138
},
{
"epoch": 1.7160493827160495,
"grad_norm": 1.1501420885353775,
"learning_rate": 6.652490632963182e-05,
"loss": 0.4419,
"step": 139
},
{
"epoch": 1.7283950617283952,
"grad_norm": 0.7814972803848219,
"learning_rate": 6.626551328891681e-05,
"loss": 0.4421,
"step": 140
},
{
"epoch": 1.7407407407407407,
"grad_norm": 0.6809040763876827,
"learning_rate": 6.600416374674978e-05,
"loss": 0.4446,
"step": 141
},
{
"epoch": 1.7530864197530864,
"grad_norm": 0.6937546616216443,
"learning_rate": 6.57408771708926e-05,
"loss": 0.4439,
"step": 142
},
{
"epoch": 1.765432098765432,
"grad_norm": 0.6133971132082513,
"learning_rate": 6.547567317339557e-05,
"loss": 0.4405,
"step": 143
},
{
"epoch": 1.7777777777777777,
"grad_norm": 0.5795946877354976,
"learning_rate": 6.520857150913655e-05,
"loss": 0.4468,
"step": 144
},
{
"epoch": 1.7901234567901234,
"grad_norm": 0.6272260508720054,
"learning_rate": 6.493959207434934e-05,
"loss": 0.4403,
"step": 145
},
{
"epoch": 1.8024691358024691,
"grad_norm": 0.6607250320416114,
"learning_rate": 6.466875490514173e-05,
"loss": 0.4441,
"step": 146
},
{
"epoch": 1.8148148148148149,
"grad_norm": 0.666515803916981,
"learning_rate": 6.439608017600292e-05,
"loss": 0.4367,
"step": 147
},
{
"epoch": 1.8271604938271606,
"grad_norm": 0.6563646888406403,
"learning_rate": 6.412158819830082e-05,
"loss": 0.4383,
"step": 148
},
{
"epoch": 1.8395061728395061,
"grad_norm": 0.6751228037264413,
"learning_rate": 6.384529941876902e-05,
"loss": 0.4443,
"step": 149
},
{
"epoch": 1.8518518518518519,
"grad_norm": 0.6037023672290093,
"learning_rate": 6.356723441798375e-05,
"loss": 0.4343,
"step": 150
},
{
"epoch": 1.8641975308641974,
"grad_norm": 0.7575004210332137,
"learning_rate": 6.328741390883084e-05,
"loss": 0.436,
"step": 151
},
{
"epoch": 1.876543209876543,
"grad_norm": 1.053664259204655,
"learning_rate": 6.300585873496279e-05,
"loss": 0.4446,
"step": 152
},
{
"epoch": 1.8888888888888888,
"grad_norm": 1.143162590447998,
"learning_rate": 6.272258986924624e-05,
"loss": 0.4376,
"step": 153
},
{
"epoch": 1.9012345679012346,
"grad_norm": 0.8056844525604071,
"learning_rate": 6.243762841219958e-05,
"loss": 0.4425,
"step": 154
},
{
"epoch": 1.9135802469135803,
"grad_norm": 0.7005815828988159,
"learning_rate": 6.215099559042132e-05,
"loss": 0.4438,
"step": 155
},
{
"epoch": 1.925925925925926,
"grad_norm": 0.5395123726786041,
"learning_rate": 6.186271275500885e-05,
"loss": 0.4451,
"step": 156
},
{
"epoch": 1.9382716049382716,
"grad_norm": 0.447328421246998,
"learning_rate": 6.157280137996797e-05,
"loss": 0.4496,
"step": 157
},
{
"epoch": 1.9506172839506173,
"grad_norm": 0.5525549829334637,
"learning_rate": 6.128128306061347e-05,
"loss": 0.4406,
"step": 158
},
{
"epoch": 1.9629629629629628,
"grad_norm": 0.6119311049360817,
"learning_rate": 6.098817951196032e-05,
"loss": 0.4432,
"step": 159
},
{
"epoch": 1.9753086419753085,
"grad_norm": 0.5999595846933212,
"learning_rate": 6.0693512567106275e-05,
"loss": 0.4396,
"step": 160
},
{
"epoch": 1.9876543209876543,
"grad_norm": 0.6329428597314521,
"learning_rate": 6.0397304175605444e-05,
"loss": 0.4397,
"step": 161
},
{
"epoch": 2.0,
"grad_norm": 0.6165900475914675,
"learning_rate": 6.009957640183333e-05,
"loss": 0.4339,
"step": 162
},
{
"epoch": 2.0123456790123457,
"grad_norm": 0.6175294635421779,
"learning_rate": 5.980035142334326e-05,
"loss": 0.4037,
"step": 163
},
{
"epoch": 2.0246913580246915,
"grad_norm": 0.5464603695576591,
"learning_rate": 5.94996515292144e-05,
"loss": 0.4069,
"step": 164
},
{
"epoch": 2.037037037037037,
"grad_norm": 0.5961811075021233,
"learning_rate": 5.919749911839146e-05,
"loss": 0.4072,
"step": 165
},
{
"epoch": 2.049382716049383,
"grad_norm": 0.7162072119334066,
"learning_rate": 5.8893916698016154e-05,
"loss": 0.409,
"step": 166
},
{
"epoch": 2.0617283950617282,
"grad_norm": 0.7531665562571003,
"learning_rate": 5.858892688175075e-05,
"loss": 0.4054,
"step": 167
},
{
"epoch": 2.074074074074074,
"grad_norm": 0.6634967768803004,
"learning_rate": 5.828255238809352e-05,
"loss": 0.4102,
"step": 168
},
{
"epoch": 2.0864197530864197,
"grad_norm": 0.5214973502711097,
"learning_rate": 5.797481603868646e-05,
"loss": 0.4093,
"step": 169
},
{
"epoch": 2.0987654320987654,
"grad_norm": 0.48817555796705103,
"learning_rate": 5.766574075661538e-05,
"loss": 0.4056,
"step": 170
},
{
"epoch": 2.111111111111111,
"grad_norm": 0.46995270511301984,
"learning_rate": 5.735534956470233e-05,
"loss": 0.4017,
"step": 171
},
{
"epoch": 2.123456790123457,
"grad_norm": 0.4001954795848698,
"learning_rate": 5.7043665583790627e-05,
"loss": 0.4043,
"step": 172
},
{
"epoch": 2.1358024691358026,
"grad_norm": 0.3352773336486886,
"learning_rate": 5.673071203102261e-05,
"loss": 0.3978,
"step": 173
},
{
"epoch": 2.148148148148148,
"grad_norm": 0.36429657583588576,
"learning_rate": 5.641651221811028e-05,
"loss": 0.405,
"step": 174
},
{
"epoch": 2.1604938271604937,
"grad_norm": 0.3696795489355164,
"learning_rate": 5.6101089549598704e-05,
"loss": 0.4015,
"step": 175
},
{
"epoch": 2.1728395061728394,
"grad_norm": 0.37732718419035066,
"learning_rate": 5.578446752112273e-05,
"loss": 0.3993,
"step": 176
},
{
"epoch": 2.185185185185185,
"grad_norm": 0.3610852145730118,
"learning_rate": 5.546666971765675e-05,
"loss": 0.401,
"step": 177
},
{
"epoch": 2.197530864197531,
"grad_norm": 0.375404848711513,
"learning_rate": 5.5147719811757914e-05,
"loss": 0.4013,
"step": 178
},
{
"epoch": 2.2098765432098766,
"grad_norm": 0.39144573818004924,
"learning_rate": 5.4827641561802716e-05,
"loss": 0.4037,
"step": 179
},
{
"epoch": 2.2222222222222223,
"grad_norm": 0.46921938093624016,
"learning_rate": 5.4506458810217286e-05,
"loss": 0.4084,
"step": 180
},
{
"epoch": 2.234567901234568,
"grad_norm": 0.39178530019945007,
"learning_rate": 5.4184195481701425e-05,
"loss": 0.3974,
"step": 181
},
{
"epoch": 2.246913580246914,
"grad_norm": 0.31454106942243093,
"learning_rate": 5.38608755814464e-05,
"loss": 0.3996,
"step": 182
},
{
"epoch": 2.259259259259259,
"grad_norm": 0.32288914490706055,
"learning_rate": 5.353652319334682e-05,
"loss": 0.4026,
"step": 183
},
{
"epoch": 2.271604938271605,
"grad_norm": 0.3480461509407278,
"learning_rate": 5.321116247820669e-05,
"loss": 0.409,
"step": 184
},
{
"epoch": 2.2839506172839505,
"grad_norm": 0.32317305352669917,
"learning_rate": 5.288481767193963e-05,
"loss": 0.3992,
"step": 185
},
{
"epoch": 2.2962962962962963,
"grad_norm": 0.3491754615190072,
"learning_rate": 5.2557513083763605e-05,
"loss": 0.4106,
"step": 186
},
{
"epoch": 2.308641975308642,
"grad_norm": 0.2654352934184053,
"learning_rate": 5.2229273094390124e-05,
"loss": 0.395,
"step": 187
},
{
"epoch": 2.3209876543209877,
"grad_norm": 0.240507325939916,
"learning_rate": 5.190012215420812e-05,
"loss": 0.3962,
"step": 188
},
{
"epoch": 2.3333333333333335,
"grad_norm": 0.3096781461722714,
"learning_rate": 5.1570084781462716e-05,
"loss": 0.4009,
"step": 189
},
{
"epoch": 2.3456790123456788,
"grad_norm": 0.3254620628162861,
"learning_rate": 5.123918556042878e-05,
"loss": 0.4003,
"step": 190
},
{
"epoch": 2.3580246913580245,
"grad_norm": 0.30442823004858754,
"learning_rate": 5.0907449139579755e-05,
"loss": 0.407,
"step": 191
},
{
"epoch": 2.3703703703703702,
"grad_norm": 0.24609813176288364,
"learning_rate": 5.057490022975156e-05,
"loss": 0.406,
"step": 192
},
{
"epoch": 2.382716049382716,
"grad_norm": 0.2645811599665009,
"learning_rate": 5.024156360230189e-05,
"loss": 0.4087,
"step": 193
},
{
"epoch": 2.3950617283950617,
"grad_norm": 0.29950051962612906,
"learning_rate": 4.9907464087265045e-05,
"loss": 0.4051,
"step": 194
},
{
"epoch": 2.4074074074074074,
"grad_norm": 0.25413630356733447,
"learning_rate": 4.9572626571502316e-05,
"loss": 0.4115,
"step": 195
},
{
"epoch": 2.419753086419753,
"grad_norm": 0.1982329593965016,
"learning_rate": 4.9237075996848235e-05,
"loss": 0.4009,
"step": 196
},
{
"epoch": 2.432098765432099,
"grad_norm": 0.2793566075797078,
"learning_rate": 4.890083735825258e-05,
"loss": 0.4018,
"step": 197
},
{
"epoch": 2.4444444444444446,
"grad_norm": 0.2501185111375193,
"learning_rate": 4.8563935701918646e-05,
"loss": 0.4005,
"step": 198
},
{
"epoch": 2.45679012345679,
"grad_norm": 0.2508812489655374,
"learning_rate": 4.8226396123437466e-05,
"loss": 0.4024,
"step": 199
},
{
"epoch": 2.4691358024691357,
"grad_norm": 0.23763312456408484,
"learning_rate": 4.788824376591849e-05,
"loss": 0.3938,
"step": 200
},
{
"epoch": 2.4814814814814814,
"grad_norm": 0.2505474740052618,
"learning_rate": 4.754950381811667e-05,
"loss": 0.4098,
"step": 201
},
{
"epoch": 2.493827160493827,
"grad_norm": 0.32543257673329773,
"learning_rate": 4.721020151255624e-05,
"loss": 0.4008,
"step": 202
},
{
"epoch": 2.506172839506173,
"grad_norm": 0.31344361733289505,
"learning_rate": 4.6870362123651056e-05,
"loss": 0.3958,
"step": 203
},
{
"epoch": 2.5185185185185186,
"grad_norm": 0.2808667743552056,
"learning_rate": 4.6530010965821984e-05,
"loss": 0.3935,
"step": 204
},
{
"epoch": 2.5308641975308643,
"grad_norm": 0.2799818958240018,
"learning_rate": 4.618917339161125e-05,
"loss": 0.3975,
"step": 205
},
{
"epoch": 2.5432098765432096,
"grad_norm": 0.40415793903369035,
"learning_rate": 4.584787478979394e-05,
"loss": 0.4012,
"step": 206
},
{
"epoch": 2.5555555555555554,
"grad_norm": 0.36820613398161905,
"learning_rate": 4.550614058348674e-05,
"loss": 0.3935,
"step": 207
},
{
"epoch": 2.567901234567901,
"grad_norm": 0.22878484205266533,
"learning_rate": 4.516399622825428e-05,
"loss": 0.4017,
"step": 208
},
{
"epoch": 2.580246913580247,
"grad_norm": 0.2526602623885084,
"learning_rate": 4.4821467210212924e-05,
"loss": 0.3986,
"step": 209
},
{
"epoch": 2.5925925925925926,
"grad_norm": 0.2857441977382452,
"learning_rate": 4.4478579044132314e-05,
"loss": 0.3983,
"step": 210
},
{
"epoch": 2.6049382716049383,
"grad_norm": 0.31335609029960937,
"learning_rate": 4.41353572715348e-05,
"loss": 0.4084,
"step": 211
},
{
"epoch": 2.617283950617284,
"grad_norm": 0.29329552295291217,
"learning_rate": 4.379182745879289e-05,
"loss": 0.4,
"step": 212
},
{
"epoch": 2.6296296296296298,
"grad_norm": 0.2464006577647208,
"learning_rate": 4.344801519522478e-05,
"loss": 0.3981,
"step": 213
},
{
"epoch": 2.6419753086419755,
"grad_norm": 0.21757828305891083,
"learning_rate": 4.310394609118826e-05,
"loss": 0.4109,
"step": 214
},
{
"epoch": 2.6543209876543212,
"grad_norm": 0.3210249559146646,
"learning_rate": 4.2759645776172996e-05,
"loss": 0.4069,
"step": 215
},
{
"epoch": 2.6666666666666665,
"grad_norm": 0.3477320907889876,
"learning_rate": 4.241513989689145e-05,
"loss": 0.4008,
"step": 216
},
{
"epoch": 2.6790123456790123,
"grad_norm": 0.24803139007843356,
"learning_rate": 4.2070454115368385e-05,
"loss": 0.3977,
"step": 217
},
{
"epoch": 2.691358024691358,
"grad_norm": 0.20440440035218216,
"learning_rate": 4.1725614107029387e-05,
"loss": 0.4001,
"step": 218
},
{
"epoch": 2.7037037037037037,
"grad_norm": 0.27538798360958056,
"learning_rate": 4.138064555878833e-05,
"loss": 0.3981,
"step": 219
},
{
"epoch": 2.7160493827160495,
"grad_norm": 0.2858784452038823,
"learning_rate": 4.1035574167133905e-05,
"loss": 0.4023,
"step": 220
},
{
"epoch": 2.728395061728395,
"grad_norm": 0.2008423560120923,
"learning_rate": 4.069042563621555e-05,
"loss": 0.4079,
"step": 221
},
{
"epoch": 2.7407407407407405,
"grad_norm": 0.24293176835950328,
"learning_rate": 4.034522567592876e-05,
"loss": 0.407,
"step": 222
},
{
"epoch": 2.753086419753086,
"grad_norm": 0.3091409408215162,
"learning_rate": 4e-05,
"loss": 0.3969,
"step": 223
},
{
"epoch": 2.765432098765432,
"grad_norm": 0.31288462010722656,
"learning_rate": 3.965477432407125e-05,
"loss": 0.4031,
"step": 224
},
{
"epoch": 2.7777777777777777,
"grad_norm": 0.2567222355035599,
"learning_rate": 3.9309574363784465e-05,
"loss": 0.3973,
"step": 225
},
{
"epoch": 2.7901234567901234,
"grad_norm": 0.19069072798190304,
"learning_rate": 3.8964425832866115e-05,
"loss": 0.3994,
"step": 226
},
{
"epoch": 2.802469135802469,
"grad_norm": 0.3116244915598422,
"learning_rate": 3.861935444121169e-05,
"loss": 0.4046,
"step": 227
},
{
"epoch": 2.814814814814815,
"grad_norm": 0.28128541699160603,
"learning_rate": 3.827438589297062e-05,
"loss": 0.3999,
"step": 228
},
{
"epoch": 2.8271604938271606,
"grad_norm": 0.167533219149008,
"learning_rate": 3.792954588463162e-05,
"loss": 0.3929,
"step": 229
},
{
"epoch": 2.8395061728395063,
"grad_norm": 0.2904700089197945,
"learning_rate": 3.758486010310856e-05,
"loss": 0.4033,
"step": 230
},
{
"epoch": 2.851851851851852,
"grad_norm": 0.222742797773903,
"learning_rate": 3.7240354223827004e-05,
"loss": 0.3952,
"step": 231
},
{
"epoch": 2.8641975308641974,
"grad_norm": 0.22495887212575763,
"learning_rate": 3.6896053908811755e-05,
"loss": 0.4007,
"step": 232
},
{
"epoch": 2.876543209876543,
"grad_norm": 0.20272044370534606,
"learning_rate": 3.655198480477523e-05,
"loss": 0.3965,
"step": 233
},
{
"epoch": 2.888888888888889,
"grad_norm": 0.20159603268883686,
"learning_rate": 3.6208172541207114e-05,
"loss": 0.4026,
"step": 234
},
{
"epoch": 2.9012345679012346,
"grad_norm": 0.1857016078801328,
"learning_rate": 3.5864642728465205e-05,
"loss": 0.4019,
"step": 235
},
{
"epoch": 2.9135802469135803,
"grad_norm": 0.19657456599113443,
"learning_rate": 3.552142095586769e-05,
"loss": 0.3935,
"step": 236
},
{
"epoch": 2.925925925925926,
"grad_norm": 0.20263796973832712,
"learning_rate": 3.517853278978708e-05,
"loss": 0.4024,
"step": 237
},
{
"epoch": 2.9382716049382713,
"grad_norm": 0.21927632477325718,
"learning_rate": 3.4836003771745736e-05,
"loss": 0.4058,
"step": 238
},
{
"epoch": 2.950617283950617,
"grad_norm": 0.18668045348448897,
"learning_rate": 3.449385941651328e-05,
"loss": 0.4016,
"step": 239
},
{
"epoch": 2.962962962962963,
"grad_norm": 0.22387285374410273,
"learning_rate": 3.415212521020609e-05,
"loss": 0.3998,
"step": 240
},
{
"epoch": 2.9753086419753085,
"grad_norm": 0.1986946786033834,
"learning_rate": 3.381082660838875e-05,
"loss": 0.3994,
"step": 241
},
{
"epoch": 2.9876543209876543,
"grad_norm": 0.17106247031701255,
"learning_rate": 3.346998903417803e-05,
"loss": 0.3948,
"step": 242
},
{
"epoch": 3.0,
"grad_norm": 0.19730260856315138,
"learning_rate": 3.312963787634896e-05,
"loss": 0.3809,
"step": 243
},
{
"epoch": 3.0123456790123457,
"grad_norm": 0.22215703145843618,
"learning_rate": 3.2789798487443775e-05,
"loss": 0.3664,
"step": 244
},
{
"epoch": 3.0246913580246915,
"grad_norm": 0.18982786875890348,
"learning_rate": 3.245049618188334e-05,
"loss": 0.3702,
"step": 245
},
{
"epoch": 3.037037037037037,
"grad_norm": 0.2659144149445534,
"learning_rate": 3.2111756234081525e-05,
"loss": 0.369,
"step": 246
},
{
"epoch": 3.049382716049383,
"grad_norm": 0.21145023138083482,
"learning_rate": 3.177360387656254e-05,
"loss": 0.37,
"step": 247
},
{
"epoch": 3.0617283950617282,
"grad_norm": 0.24865516246035863,
"learning_rate": 3.143606429808136e-05,
"loss": 0.3701,
"step": 248
},
{
"epoch": 3.074074074074074,
"grad_norm": 0.2308219847168512,
"learning_rate": 3.109916264174743e-05,
"loss": 0.3707,
"step": 249
},
{
"epoch": 3.0864197530864197,
"grad_norm": 0.2246388176582276,
"learning_rate": 3.076292400315179e-05,
"loss": 0.3735,
"step": 250
},
{
"epoch": 3.0987654320987654,
"grad_norm": 0.22125008039208874,
"learning_rate": 3.0427373428497704e-05,
"loss": 0.3682,
"step": 251
},
{
"epoch": 3.111111111111111,
"grad_norm": 0.20085617720181384,
"learning_rate": 3.0092535912734965e-05,
"loss": 0.3668,
"step": 252
},
{
"epoch": 3.123456790123457,
"grad_norm": 0.2177257993468155,
"learning_rate": 2.9758436397698118e-05,
"loss": 0.3653,
"step": 253
},
{
"epoch": 3.1358024691358026,
"grad_norm": 0.2087241919659811,
"learning_rate": 2.9425099770248446e-05,
"loss": 0.3711,
"step": 254
},
{
"epoch": 3.148148148148148,
"grad_norm": 0.1946566571469163,
"learning_rate": 2.9092550860420252e-05,
"loss": 0.3624,
"step": 255
},
{
"epoch": 3.1604938271604937,
"grad_norm": 0.22054171431244854,
"learning_rate": 2.8760814439571233e-05,
"loss": 0.3685,
"step": 256
},
{
"epoch": 3.1728395061728394,
"grad_norm": 0.17240280564444063,
"learning_rate": 2.8429915218537297e-05,
"loss": 0.3674,
"step": 257
},
{
"epoch": 3.185185185185185,
"grad_norm": 0.1848593449888633,
"learning_rate": 2.809987784579189e-05,
"loss": 0.3608,
"step": 258
},
{
"epoch": 3.197530864197531,
"grad_norm": 0.18266249121254657,
"learning_rate": 2.7770726905609896e-05,
"loss": 0.3642,
"step": 259
},
{
"epoch": 3.2098765432098766,
"grad_norm": 0.16073855445767077,
"learning_rate": 2.74424869162364e-05,
"loss": 0.3563,
"step": 260
},
{
"epoch": 3.2222222222222223,
"grad_norm": 0.17531367979315252,
"learning_rate": 2.7115182328060385e-05,
"loss": 0.3676,
"step": 261
},
{
"epoch": 3.234567901234568,
"grad_norm": 0.14796201932709915,
"learning_rate": 2.678883752179333e-05,
"loss": 0.3625,
"step": 262
},
{
"epoch": 3.246913580246914,
"grad_norm": 0.19310186654814873,
"learning_rate": 2.6463476806653185e-05,
"loss": 0.3585,
"step": 263
},
{
"epoch": 3.259259259259259,
"grad_norm": 0.17358347178863473,
"learning_rate": 2.61391244185536e-05,
"loss": 0.3605,
"step": 264
},
{
"epoch": 3.271604938271605,
"grad_norm": 0.17684421859741475,
"learning_rate": 2.5815804518298575e-05,
"loss": 0.3677,
"step": 265
},
{
"epoch": 3.2839506172839505,
"grad_norm": 0.203480321127498,
"learning_rate": 2.549354118978272e-05,
"loss": 0.3678,
"step": 266
},
{
"epoch": 3.2962962962962963,
"grad_norm": 0.17547188883389694,
"learning_rate": 2.51723584381973e-05,
"loss": 0.3608,
"step": 267
},
{
"epoch": 3.308641975308642,
"grad_norm": 0.18602067695611346,
"learning_rate": 2.4852280188242096e-05,
"loss": 0.3678,
"step": 268
},
{
"epoch": 3.3209876543209877,
"grad_norm": 0.17140539371210345,
"learning_rate": 2.453333028234325e-05,
"loss": 0.3638,
"step": 269
},
{
"epoch": 3.3333333333333335,
"grad_norm": 0.15224985187441373,
"learning_rate": 2.4215532478877283e-05,
"loss": 0.3597,
"step": 270
},
{
"epoch": 3.3456790123456788,
"grad_norm": 0.16134052410438623,
"learning_rate": 2.3898910450401306e-05,
"loss": 0.3667,
"step": 271
},
{
"epoch": 3.3580246913580245,
"grad_norm": 0.14386569537644786,
"learning_rate": 2.3583487781889737e-05,
"loss": 0.3709,
"step": 272
},
{
"epoch": 3.3703703703703702,
"grad_norm": 0.15151232350322325,
"learning_rate": 2.3269287968977406e-05,
"loss": 0.3637,
"step": 273
},
{
"epoch": 3.382716049382716,
"grad_norm": 0.15707589935891128,
"learning_rate": 2.2956334416209404e-05,
"loss": 0.3735,
"step": 274
},
{
"epoch": 3.3950617283950617,
"grad_norm": 0.1477749720910393,
"learning_rate": 2.264465043529768e-05,
"loss": 0.3622,
"step": 275
},
{
"epoch": 3.4074074074074074,
"grad_norm": 0.14885929712006027,
"learning_rate": 2.233425924338463e-05,
"loss": 0.3644,
"step": 276
},
{
"epoch": 3.419753086419753,
"grad_norm": 0.14340772251052653,
"learning_rate": 2.2025183961313542e-05,
"loss": 0.3687,
"step": 277
},
{
"epoch": 3.432098765432099,
"grad_norm": 0.13763533911676756,
"learning_rate": 2.1717447611906496e-05,
"loss": 0.3663,
"step": 278
},
{
"epoch": 3.4444444444444446,
"grad_norm": 0.14639101329943424,
"learning_rate": 2.141107311824926e-05,
"loss": 0.3689,
"step": 279
},
{
"epoch": 3.45679012345679,
"grad_norm": 0.1276571096925691,
"learning_rate": 2.1106083301983852e-05,
"loss": 0.3618,
"step": 280
},
{
"epoch": 3.4691358024691357,
"grad_norm": 0.14363458047447658,
"learning_rate": 2.0802500881608557e-05,
"loss": 0.3727,
"step": 281
},
{
"epoch": 3.4814814814814814,
"grad_norm": 0.12886295792105223,
"learning_rate": 2.0500348470785614e-05,
"loss": 0.3692,
"step": 282
},
{
"epoch": 3.493827160493827,
"grad_norm": 0.1490463167300804,
"learning_rate": 2.0199648576656744e-05,
"loss": 0.3636,
"step": 283
},
{
"epoch": 3.506172839506173,
"grad_norm": 0.12848412841426096,
"learning_rate": 1.9900423598166685e-05,
"loss": 0.3651,
"step": 284
},
{
"epoch": 3.5185185185185186,
"grad_norm": 0.15574442730245652,
"learning_rate": 1.9602695824394576e-05,
"loss": 0.3651,
"step": 285
},
{
"epoch": 3.5308641975308643,
"grad_norm": 0.13229685022791354,
"learning_rate": 1.9306487432893725e-05,
"loss": 0.3662,
"step": 286
},
{
"epoch": 3.5432098765432096,
"grad_norm": 0.12772394530331901,
"learning_rate": 1.901182048803968e-05,
"loss": 0.3651,
"step": 287
},
{
"epoch": 3.5555555555555554,
"grad_norm": 0.1465151284584716,
"learning_rate": 1.8718716939386543e-05,
"loss": 0.3698,
"step": 288
},
{
"epoch": 3.567901234567901,
"grad_norm": 0.14047354187123118,
"learning_rate": 1.8427198620032037e-05,
"loss": 0.3661,
"step": 289
},
{
"epoch": 3.580246913580247,
"grad_norm": 0.1410397043933752,
"learning_rate": 1.8137287244991162e-05,
"loss": 0.3708,
"step": 290
},
{
"epoch": 3.5925925925925926,
"grad_norm": 0.14850797574149896,
"learning_rate": 1.7849004409578678e-05,
"loss": 0.37,
"step": 291
},
{
"epoch": 3.6049382716049383,
"grad_norm": 0.14770512288892354,
"learning_rate": 1.7562371587800422e-05,
"loss": 0.3621,
"step": 292
},
{
"epoch": 3.617283950617284,
"grad_norm": 0.1301969671247391,
"learning_rate": 1.7277410130753775e-05,
"loss": 0.3705,
"step": 293
},
{
"epoch": 3.6296296296296298,
"grad_norm": 0.13324724802934845,
"learning_rate": 1.6994141265037222e-05,
"loss": 0.3583,
"step": 294
},
{
"epoch": 3.6419753086419755,
"grad_norm": 0.12335331492186778,
"learning_rate": 1.6712586091169183e-05,
"loss": 0.3706,
"step": 295
},
{
"epoch": 3.6543209876543212,
"grad_norm": 0.12483228986767417,
"learning_rate": 1.6432765582016257e-05,
"loss": 0.3627,
"step": 296
},
{
"epoch": 3.6666666666666665,
"grad_norm": 0.1224822064632684,
"learning_rate": 1.615470058123099e-05,
"loss": 0.3683,
"step": 297
},
{
"epoch": 3.6790123456790123,
"grad_norm": 0.12870125642053606,
"learning_rate": 1.5878411801699182e-05,
"loss": 0.3677,
"step": 298
},
{
"epoch": 3.691358024691358,
"grad_norm": 0.11464105740669171,
"learning_rate": 1.5603919823997083e-05,
"loss": 0.3725,
"step": 299
},
{
"epoch": 3.7037037037037037,
"grad_norm": 0.1259473229571899,
"learning_rate": 1.5331245094858277e-05,
"loss": 0.3632,
"step": 300
},
{
"epoch": 3.7160493827160495,
"grad_norm": 0.11989849457004843,
"learning_rate": 1.5060407925650662e-05,
"loss": 0.363,
"step": 301
},
{
"epoch": 3.728395061728395,
"grad_norm": 0.11838170070815705,
"learning_rate": 1.4791428490863462e-05,
"loss": 0.3636,
"step": 302
},
{
"epoch": 3.7407407407407405,
"grad_norm": 0.11542631237011597,
"learning_rate": 1.4524326826604442e-05,
"loss": 0.3662,
"step": 303
},
{
"epoch": 3.753086419753086,
"grad_norm": 0.10853513336233153,
"learning_rate": 1.425912282910741e-05,
"loss": 0.3612,
"step": 304
},
{
"epoch": 3.765432098765432,
"grad_norm": 0.12927711782224877,
"learning_rate": 1.3995836253250233e-05,
"loss": 0.3632,
"step": 305
},
{
"epoch": 3.7777777777777777,
"grad_norm": 0.11124438692244316,
"learning_rate": 1.3734486711083199e-05,
"loss": 0.3656,
"step": 306
},
{
"epoch": 3.7901234567901234,
"grad_norm": 0.11829671034615585,
"learning_rate": 1.3475093670368202e-05,
"loss": 0.3625,
"step": 307
},
{
"epoch": 3.802469135802469,
"grad_norm": 0.1171711805914509,
"learning_rate": 1.3217676453128583e-05,
"loss": 0.3681,
"step": 308
},
{
"epoch": 3.814814814814815,
"grad_norm": 0.12136369786981609,
"learning_rate": 1.2962254234209826e-05,
"loss": 0.3702,
"step": 309
},
{
"epoch": 3.8271604938271606,
"grad_norm": 0.11625055457136292,
"learning_rate": 1.2708846039851306e-05,
"loss": 0.3596,
"step": 310
},
{
"epoch": 3.8395061728395063,
"grad_norm": 0.1249883414445167,
"learning_rate": 1.2457470746268912e-05,
"loss": 0.3597,
"step": 311
},
{
"epoch": 3.851851851851852,
"grad_norm": 0.11998786571991671,
"learning_rate": 1.2208147078249106e-05,
"loss": 0.3705,
"step": 312
},
{
"epoch": 3.8641975308641974,
"grad_norm": 0.12324835771363575,
"learning_rate": 1.1960893607754022e-05,
"loss": 0.378,
"step": 313
},
{
"epoch": 3.876543209876543,
"grad_norm": 0.13292216219148154,
"learning_rate": 1.1715728752538103e-05,
"loss": 0.3709,
"step": 314
},
{
"epoch": 3.888888888888889,
"grad_norm": 0.12363035327325136,
"learning_rate": 1.1472670774776159e-05,
"loss": 0.3734,
"step": 315
},
{
"epoch": 3.9012345679012346,
"grad_norm": 0.12095948017126495,
"learning_rate": 1.123173777970303e-05,
"loss": 0.3644,
"step": 316
},
{
"epoch": 3.9135802469135803,
"grad_norm": 0.12223767053256172,
"learning_rate": 1.0992947714264952e-05,
"loss": 0.3639,
"step": 317
},
{
"epoch": 3.925925925925926,
"grad_norm": 0.11556671111818939,
"learning_rate": 1.0756318365782672e-05,
"loss": 0.3705,
"step": 318
},
{
"epoch": 3.9382716049382713,
"grad_norm": 0.11863503874267803,
"learning_rate": 1.0521867360626534e-05,
"loss": 0.3649,
"step": 319
},
{
"epoch": 3.950617283950617,
"grad_norm": 0.1220737146765024,
"learning_rate": 1.028961216290342e-05,
"loss": 0.3702,
"step": 320
},
{
"epoch": 3.962962962962963,
"grad_norm": 0.10688177437745146,
"learning_rate": 1.0059570073155953e-05,
"loss": 0.3686,
"step": 321
},
{
"epoch": 3.9753086419753085,
"grad_norm": 0.1115239690090056,
"learning_rate": 9.831758227073714e-06,
"loss": 0.3622,
"step": 322
},
{
"epoch": 3.9876543209876543,
"grad_norm": 0.1013118549435552,
"learning_rate": 9.606193594216852e-06,
"loss": 0.3662,
"step": 323
},
{
"epoch": 4.0,
"grad_norm": 0.13078127831261904,
"learning_rate": 9.382892976752024e-06,
"loss": 0.3514,
"step": 324
},
{
"epoch": 4.012345679012346,
"grad_norm": 0.14120097496571368,
"learning_rate": 9.161873008200816e-06,
"loss": 0.3447,
"step": 325
},
{
"epoch": 4.0246913580246915,
"grad_norm": 0.131610168014187,
"learning_rate": 8.943150152200734e-06,
"loss": 0.3564,
"step": 326
},
{
"epoch": 4.037037037037037,
"grad_norm": 0.1197175249959368,
"learning_rate": 8.72674070127881e-06,
"loss": 0.3399,
"step": 327
},
{
"epoch": 4.049382716049383,
"grad_norm": 0.1381715130606439,
"learning_rate": 8.512660775637998e-06,
"loss": 0.3434,
"step": 328
},
{
"epoch": 4.061728395061729,
"grad_norm": 0.13276158035183344,
"learning_rate": 8.300926321956391e-06,
"loss": 0.3416,
"step": 329
},
{
"epoch": 4.074074074074074,
"grad_norm": 0.13242822539056381,
"learning_rate": 8.091553112199362e-06,
"loss": 0.3518,
"step": 330
},
{
"epoch": 4.08641975308642,
"grad_norm": 0.12212877221315457,
"learning_rate": 7.884556742444704e-06,
"loss": 0.3446,
"step": 331
},
{
"epoch": 4.098765432098766,
"grad_norm": 0.11698141950653529,
"learning_rate": 7.679952631720944e-06,
"loss": 0.3466,
"step": 332
},
{
"epoch": 4.111111111111111,
"grad_norm": 0.1304559116220868,
"learning_rate": 7.477756020858695e-06,
"loss": 0.355,
"step": 333
},
{
"epoch": 4.1234567901234565,
"grad_norm": 0.13089784593559015,
"learning_rate": 7.277981971355487e-06,
"loss": 0.3432,
"step": 334
},
{
"epoch": 4.135802469135802,
"grad_norm": 0.12263988117511435,
"learning_rate": 7.080645364253747e-06,
"loss": 0.3451,
"step": 335
},
{
"epoch": 4.148148148148148,
"grad_norm": 0.11728846389962917,
"learning_rate": 6.885760899032368e-06,
"loss": 0.345,
"step": 336
},
{
"epoch": 4.160493827160494,
"grad_norm": 0.11392519861587432,
"learning_rate": 6.69334309251175e-06,
"loss": 0.3472,
"step": 337
},
{
"epoch": 4.172839506172839,
"grad_norm": 0.12602381332743814,
"learning_rate": 6.503406277772457e-06,
"loss": 0.345,
"step": 338
},
{
"epoch": 4.185185185185185,
"grad_norm": 0.10134725138589995,
"learning_rate": 6.31596460308753e-06,
"loss": 0.3431,
"step": 339
},
{
"epoch": 4.197530864197531,
"grad_norm": 0.11429337446344612,
"learning_rate": 6.1310320308686354e-06,
"loss": 0.3492,
"step": 340
},
{
"epoch": 4.209876543209877,
"grad_norm": 0.12482104702813673,
"learning_rate": 5.9486223366259555e-06,
"loss": 0.3406,
"step": 341
},
{
"epoch": 4.222222222222222,
"grad_norm": 0.11483630989866628,
"learning_rate": 5.768749107942105e-06,
"loss": 0.3458,
"step": 342
},
{
"epoch": 4.234567901234568,
"grad_norm": 0.10641915634927608,
"learning_rate": 5.5914257434599705e-06,
"loss": 0.3427,
"step": 343
},
{
"epoch": 4.246913580246914,
"grad_norm": 0.11187178257279115,
"learning_rate": 5.416665451884706e-06,
"loss": 0.3478,
"step": 344
},
{
"epoch": 4.2592592592592595,
"grad_norm": 0.10328829320916721,
"learning_rate": 5.24448125099974e-06,
"loss": 0.3604,
"step": 345
},
{
"epoch": 4.271604938271605,
"grad_norm": 0.10325046605157456,
"learning_rate": 5.074885966697167e-06,
"loss": 0.3439,
"step": 346
},
{
"epoch": 4.283950617283951,
"grad_norm": 0.09783875518175919,
"learning_rate": 4.9078922320223225e-06,
"loss": 0.338,
"step": 347
},
{
"epoch": 4.296296296296296,
"grad_norm": 0.09584121801157325,
"learning_rate": 4.7435124862327445e-06,
"loss": 0.3456,
"step": 348
},
{
"epoch": 4.308641975308642,
"grad_norm": 0.10257946096157032,
"learning_rate": 4.581758973871609e-06,
"loss": 0.3435,
"step": 349
},
{
"epoch": 4.320987654320987,
"grad_norm": 0.09622559695473883,
"learning_rate": 4.422643743855611e-06,
"loss": 0.3387,
"step": 350
},
{
"epoch": 4.333333333333333,
"grad_norm": 0.08985291405803897,
"learning_rate": 4.266178648577484e-06,
"loss": 0.3465,
"step": 351
},
{
"epoch": 4.345679012345679,
"grad_norm": 0.09083798833221284,
"learning_rate": 4.112375343023076e-06,
"loss": 0.3402,
"step": 352
},
{
"epoch": 4.3580246913580245,
"grad_norm": 0.0928368108514207,
"learning_rate": 3.961245283903239e-06,
"loss": 0.3417,
"step": 353
},
{
"epoch": 4.37037037037037,
"grad_norm": 0.09858890680167014,
"learning_rate": 3.812799728800354e-06,
"loss": 0.3494,
"step": 354
},
{
"epoch": 4.382716049382716,
"grad_norm": 0.09253195368124226,
"learning_rate": 3.6670497353298396e-06,
"loss": 0.3486,
"step": 355
},
{
"epoch": 4.395061728395062,
"grad_norm": 0.09138349778139458,
"learning_rate": 3.5240061603163977e-06,
"loss": 0.3439,
"step": 356
},
{
"epoch": 4.407407407407407,
"grad_norm": 0.09207502583455726,
"learning_rate": 3.3836796589853484e-06,
"loss": 0.3399,
"step": 357
},
{
"epoch": 4.419753086419753,
"grad_norm": 0.09098178054496783,
"learning_rate": 3.246080684168913e-06,
"loss": 0.3374,
"step": 358
},
{
"epoch": 4.432098765432099,
"grad_norm": 0.09461477122622283,
"learning_rate": 3.11121948552759e-06,
"loss": 0.347,
"step": 359
},
{
"epoch": 4.444444444444445,
"grad_norm": 0.08873177760685183,
"learning_rate": 2.9791061087866625e-06,
"loss": 0.3517,
"step": 360
},
{
"epoch": 4.45679012345679,
"grad_norm": 0.08923078431705038,
"learning_rate": 2.849750394987907e-06,
"loss": 0.3507,
"step": 361
},
{
"epoch": 4.469135802469136,
"grad_norm": 0.09262596320456881,
"learning_rate": 2.7231619797565278e-06,
"loss": 0.3462,
"step": 362
},
{
"epoch": 4.481481481481482,
"grad_norm": 0.09034563106603927,
"learning_rate": 2.5993502925834115e-06,
"loss": 0.3475,
"step": 363
},
{
"epoch": 4.493827160493828,
"grad_norm": 0.08464664656906902,
"learning_rate": 2.4783245561227264e-06,
"loss": 0.3436,
"step": 364
},
{
"epoch": 4.506172839506172,
"grad_norm": 0.08516291301856833,
"learning_rate": 2.3600937855049467e-06,
"loss": 0.3489,
"step": 365
},
{
"epoch": 4.518518518518518,
"grad_norm": 0.08613713073759806,
"learning_rate": 2.244666787665297e-06,
"loss": 0.3479,
"step": 366
},
{
"epoch": 4.530864197530864,
"grad_norm": 0.08766949672032548,
"learning_rate": 2.1320521606877653e-06,
"loss": 0.3491,
"step": 367
},
{
"epoch": 4.54320987654321,
"grad_norm": 0.08233473579098213,
"learning_rate": 2.022258293164585e-06,
"loss": 0.3444,
"step": 368
},
{
"epoch": 4.555555555555555,
"grad_norm": 0.08546306867171963,
"learning_rate": 1.9152933635714354e-06,
"loss": 0.3402,
"step": 369
},
{
"epoch": 4.567901234567901,
"grad_norm": 0.0838918934654388,
"learning_rate": 1.8111653396581762e-06,
"loss": 0.3497,
"step": 370
},
{
"epoch": 4.580246913580247,
"grad_norm": 0.08391928692735219,
"learning_rate": 1.709881977855372e-06,
"loss": 0.3451,
"step": 371
},
{
"epoch": 4.592592592592593,
"grad_norm": 0.0871181996609232,
"learning_rate": 1.6114508226965009e-06,
"loss": 0.3446,
"step": 372
},
{
"epoch": 4.604938271604938,
"grad_norm": 0.08989815759315828,
"learning_rate": 1.5158792062559813e-06,
"loss": 0.3472,
"step": 373
},
{
"epoch": 4.617283950617284,
"grad_norm": 0.08525583975432947,
"learning_rate": 1.4231742476029965e-06,
"loss": 0.3464,
"step": 374
},
{
"epoch": 4.62962962962963,
"grad_norm": 0.08702616238335954,
"learning_rate": 1.33334285227122e-06,
"loss": 0.3464,
"step": 375
},
{
"epoch": 4.6419753086419755,
"grad_norm": 0.0798577947590892,
"learning_rate": 1.2463917117443968e-06,
"loss": 0.3485,
"step": 376
},
{
"epoch": 4.654320987654321,
"grad_norm": 0.08199514353400199,
"learning_rate": 1.1623273029579195e-06,
"loss": 0.3466,
"step": 377
},
{
"epoch": 4.666666666666667,
"grad_norm": 0.08036935320442855,
"learning_rate": 1.0811558878163698e-06,
"loss": 0.3449,
"step": 378
},
{
"epoch": 4.679012345679013,
"grad_norm": 0.09004723861019338,
"learning_rate": 1.0028835127270553e-06,
"loss": 0.3429,
"step": 379
},
{
"epoch": 4.6913580246913575,
"grad_norm": 0.08561873370258896,
"learning_rate": 9.275160081496337e-07,
"loss": 0.346,
"step": 380
},
{
"epoch": 4.703703703703704,
"grad_norm": 0.08084419918008226,
"learning_rate": 8.550589881617877e-07,
"loss": 0.3416,
"step": 381
},
{
"epoch": 4.716049382716049,
"grad_norm": 0.08104505949528973,
"learning_rate": 7.85517850041062e-07,
"loss": 0.3398,
"step": 382
},
{
"epoch": 4.728395061728395,
"grad_norm": 0.08076162479144416,
"learning_rate": 7.188977738627901e-07,
"loss": 0.3453,
"step": 383
},
{
"epoch": 4.7407407407407405,
"grad_norm": 0.07770391544716708,
"learning_rate": 6.552037221142593e-07,
"loss": 0.3393,
"step": 384
},
{
"epoch": 4.753086419753086,
"grad_norm": 0.08331286393559116,
"learning_rate": 5.944404393250481e-07,
"loss": 0.3416,
"step": 385
},
{
"epoch": 4.765432098765432,
"grad_norm": 0.0804668471427177,
"learning_rate": 5.366124517136184e-07,
"loss": 0.342,
"step": 386
},
{
"epoch": 4.777777777777778,
"grad_norm": 0.08538622755026046,
"learning_rate": 4.817240668501421e-07,
"loss": 0.3401,
"step": 387
},
{
"epoch": 4.790123456790123,
"grad_norm": 0.08146413045412997,
"learning_rate": 4.297793733356548e-07,
"loss": 0.3427,
"step": 388
},
{
"epoch": 4.802469135802469,
"grad_norm": 0.08133595326521681,
"learning_rate": 3.807822404974726e-07,
"loss": 0.3483,
"step": 389
},
{
"epoch": 4.814814814814815,
"grad_norm": 0.07919579475608875,
"learning_rate": 3.3473631810100103e-07,
"loss": 0.3327,
"step": 390
},
{
"epoch": 4.827160493827161,
"grad_norm": 0.08123223258851157,
"learning_rate": 2.916450360778411e-07,
"loss": 0.3365,
"step": 391
},
{
"epoch": 4.839506172839506,
"grad_norm": 0.08257891936662312,
"learning_rate": 2.5151160427029584e-07,
"loss": 0.3475,
"step": 392
},
{
"epoch": 4.851851851851852,
"grad_norm": 0.07932897839921949,
"learning_rate": 2.1433901219229502e-07,
"loss": 0.3467,
"step": 393
},
{
"epoch": 4.864197530864198,
"grad_norm": 0.08087497808227699,
"learning_rate": 1.8013002880667096e-07,
"loss": 0.3445,
"step": 394
},
{
"epoch": 4.8765432098765435,
"grad_norm": 0.09555289840502959,
"learning_rate": 1.4888720231894138e-07,
"loss": 0.3489,
"step": 395
},
{
"epoch": 4.888888888888889,
"grad_norm": 0.07961294947105259,
"learning_rate": 1.2061285998746562e-07,
"loss": 0.3469,
"step": 396
},
{
"epoch": 4.901234567901234,
"grad_norm": 0.08343057365407185,
"learning_rate": 9.530910795009895e-08,
"loss": 0.3448,
"step": 397
},
{
"epoch": 4.91358024691358,
"grad_norm": 0.07711854846564468,
"learning_rate": 7.297783106730016e-08,
"loss": 0.341,
"step": 398
},
{
"epoch": 4.925925925925926,
"grad_norm": 0.07943450346405932,
"learning_rate": 5.362069278175508e-08,
"loss": 0.347,
"step": 399
},
{
"epoch": 4.938271604938271,
"grad_norm": 0.07870891626937102,
"learning_rate": 3.7239134994426775e-08,
"loss": 0.3399,
"step": 400
},
{
"epoch": 4.950617283950617,
"grad_norm": 0.08172348680504911,
"learning_rate": 2.3834377957183684e-08,
"loss": 0.3363,
"step": 401
},
{
"epoch": 4.962962962962963,
"grad_norm": 0.08219122509641905,
"learning_rate": 1.3407420181885678e-08,
"loss": 0.3397,
"step": 402
},
{
"epoch": 4.9753086419753085,
"grad_norm": 0.079358090049586,
"learning_rate": 5.959038366021297e-09,
"loss": 0.3475,
"step": 403
},
{
"epoch": 4.987654320987654,
"grad_norm": 0.07720406166190734,
"learning_rate": 1.4897873348340697e-09,
"loss": 0.344,
"step": 404
},
{
"epoch": 5.0,
"grad_norm": 0.08228065193505166,
"learning_rate": 0.0,
"loss": 0.3412,
"step": 405
},
{
"epoch": 5.0,
"step": 405,
"total_flos": 6794337614561280.0,
"train_loss": 0.42579232314486565,
"train_runtime": 5653.6163,
"train_samples_per_second": 36.455,
"train_steps_per_second": 0.072
}
],
"logging_steps": 1,
"max_steps": 405,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6794337614561280.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}