model_3306a0fb / checkpoint-385 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
7610bbb verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 385,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012987012987012988,
"grad_norm": 30.513944625854492,
"learning_rate": 5.0000000000000004e-08,
"loss": 4.1013,
"step": 1
},
{
"epoch": 0.025974025974025976,
"grad_norm": 30.965682983398438,
"learning_rate": 1.0000000000000001e-07,
"loss": 4.1757,
"step": 2
},
{
"epoch": 0.03896103896103896,
"grad_norm": 30.834516525268555,
"learning_rate": 1.5000000000000002e-07,
"loss": 4.1371,
"step": 3
},
{
"epoch": 0.05194805194805195,
"grad_norm": 30.98870849609375,
"learning_rate": 2.0000000000000002e-07,
"loss": 4.0543,
"step": 4
},
{
"epoch": 0.06493506493506493,
"grad_norm": 30.404874801635742,
"learning_rate": 2.5000000000000004e-07,
"loss": 4.09,
"step": 5
},
{
"epoch": 0.07792207792207792,
"grad_norm": 31.433774948120117,
"learning_rate": 3.0000000000000004e-07,
"loss": 4.1777,
"step": 6
},
{
"epoch": 0.09090909090909091,
"grad_norm": 30.850692749023438,
"learning_rate": 3.5000000000000004e-07,
"loss": 4.142,
"step": 7
},
{
"epoch": 0.1038961038961039,
"grad_norm": 31.00360870361328,
"learning_rate": 4.0000000000000003e-07,
"loss": 4.1115,
"step": 8
},
{
"epoch": 0.11688311688311688,
"grad_norm": 31.221616744995117,
"learning_rate": 4.5000000000000003e-07,
"loss": 4.1585,
"step": 9
},
{
"epoch": 0.12987012987012986,
"grad_norm": 30.560623168945312,
"learning_rate": 5.000000000000001e-07,
"loss": 4.1155,
"step": 10
},
{
"epoch": 0.14285714285714285,
"grad_norm": 30.089527130126953,
"learning_rate": 5.5e-07,
"loss": 4.0638,
"step": 11
},
{
"epoch": 0.15584415584415584,
"grad_norm": 30.662569046020508,
"learning_rate": 6.000000000000001e-07,
"loss": 4.0152,
"step": 12
},
{
"epoch": 0.16883116883116883,
"grad_norm": 29.455503463745117,
"learning_rate": 6.5e-07,
"loss": 3.9501,
"step": 13
},
{
"epoch": 0.18181818181818182,
"grad_norm": 28.851863861083984,
"learning_rate": 7.000000000000001e-07,
"loss": 3.9066,
"step": 14
},
{
"epoch": 0.19480519480519481,
"grad_norm": 27.41941261291504,
"learning_rate": 7.5e-07,
"loss": 3.816,
"step": 15
},
{
"epoch": 0.2077922077922078,
"grad_norm": 25.754905700683594,
"learning_rate": 8.000000000000001e-07,
"loss": 3.6715,
"step": 16
},
{
"epoch": 0.22077922077922077,
"grad_norm": 24.467802047729492,
"learning_rate": 8.500000000000001e-07,
"loss": 3.6226,
"step": 17
},
{
"epoch": 0.23376623376623376,
"grad_norm": 23.671884536743164,
"learning_rate": 9.000000000000001e-07,
"loss": 3.5756,
"step": 18
},
{
"epoch": 0.24675324675324675,
"grad_norm": 21.28356170654297,
"learning_rate": 9.500000000000001e-07,
"loss": 3.3822,
"step": 19
},
{
"epoch": 0.2597402597402597,
"grad_norm": 20.54037857055664,
"learning_rate": 1.0000000000000002e-06,
"loss": 3.3799,
"step": 20
},
{
"epoch": 0.2727272727272727,
"grad_norm": 18.18222427368164,
"learning_rate": 1.0500000000000001e-06,
"loss": 3.1964,
"step": 21
},
{
"epoch": 0.2857142857142857,
"grad_norm": 17.782703399658203,
"learning_rate": 1.1e-06,
"loss": 3.1745,
"step": 22
},
{
"epoch": 0.2987012987012987,
"grad_norm": 15.965900421142578,
"learning_rate": 1.1500000000000002e-06,
"loss": 2.9002,
"step": 23
},
{
"epoch": 0.3116883116883117,
"grad_norm": 16.00725746154785,
"learning_rate": 1.2000000000000002e-06,
"loss": 2.9123,
"step": 24
},
{
"epoch": 0.3246753246753247,
"grad_norm": 15.301984786987305,
"learning_rate": 1.25e-06,
"loss": 2.6531,
"step": 25
},
{
"epoch": 0.33766233766233766,
"grad_norm": 16.359207153320312,
"learning_rate": 1.3e-06,
"loss": 2.6089,
"step": 26
},
{
"epoch": 0.35064935064935066,
"grad_norm": 17.74176025390625,
"learning_rate": 1.3500000000000002e-06,
"loss": 2.4805,
"step": 27
},
{
"epoch": 0.36363636363636365,
"grad_norm": 18.702547073364258,
"learning_rate": 1.4000000000000001e-06,
"loss": 2.3312,
"step": 28
},
{
"epoch": 0.37662337662337664,
"grad_norm": 18.44041633605957,
"learning_rate": 1.45e-06,
"loss": 2.2273,
"step": 29
},
{
"epoch": 0.38961038961038963,
"grad_norm": 15.867247581481934,
"learning_rate": 1.5e-06,
"loss": 2.0514,
"step": 30
},
{
"epoch": 0.4025974025974026,
"grad_norm": 13.97642707824707,
"learning_rate": 1.5500000000000002e-06,
"loss": 1.8689,
"step": 31
},
{
"epoch": 0.4155844155844156,
"grad_norm": 13.599323272705078,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.7907,
"step": 32
},
{
"epoch": 0.42857142857142855,
"grad_norm": 13.204086303710938,
"learning_rate": 1.6500000000000003e-06,
"loss": 1.6537,
"step": 33
},
{
"epoch": 0.44155844155844154,
"grad_norm": 13.255966186523438,
"learning_rate": 1.7000000000000002e-06,
"loss": 1.5693,
"step": 34
},
{
"epoch": 0.45454545454545453,
"grad_norm": 13.00086784362793,
"learning_rate": 1.75e-06,
"loss": 1.3916,
"step": 35
},
{
"epoch": 0.4675324675324675,
"grad_norm": 12.996549606323242,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.2734,
"step": 36
},
{
"epoch": 0.4805194805194805,
"grad_norm": 12.506110191345215,
"learning_rate": 1.85e-06,
"loss": 1.1444,
"step": 37
},
{
"epoch": 0.4935064935064935,
"grad_norm": 12.379636764526367,
"learning_rate": 1.9000000000000002e-06,
"loss": 1.033,
"step": 38
},
{
"epoch": 0.5064935064935064,
"grad_norm": 12.38772201538086,
"learning_rate": 1.9500000000000004e-06,
"loss": 0.8932,
"step": 39
},
{
"epoch": 0.5194805194805194,
"grad_norm": 12.370598793029785,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.7914,
"step": 40
},
{
"epoch": 0.5324675324675324,
"grad_norm": 11.510255813598633,
"learning_rate": 2.05e-06,
"loss": 0.6336,
"step": 41
},
{
"epoch": 0.5454545454545454,
"grad_norm": 10.088979721069336,
"learning_rate": 2.1000000000000002e-06,
"loss": 0.5115,
"step": 42
},
{
"epoch": 0.5584415584415584,
"grad_norm": 9.241965293884277,
"learning_rate": 2.15e-06,
"loss": 0.416,
"step": 43
},
{
"epoch": 0.5714285714285714,
"grad_norm": 7.457204341888428,
"learning_rate": 2.2e-06,
"loss": 0.2947,
"step": 44
},
{
"epoch": 0.5844155844155844,
"grad_norm": 6.164954662322998,
"learning_rate": 2.25e-06,
"loss": 0.2202,
"step": 45
},
{
"epoch": 0.5974025974025974,
"grad_norm": 4.587556838989258,
"learning_rate": 2.3000000000000004e-06,
"loss": 0.1721,
"step": 46
},
{
"epoch": 0.6103896103896104,
"grad_norm": 3.2366952896118164,
"learning_rate": 2.35e-06,
"loss": 0.1451,
"step": 47
},
{
"epoch": 0.6233766233766234,
"grad_norm": 2.397469997406006,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.1116,
"step": 48
},
{
"epoch": 0.6363636363636364,
"grad_norm": 1.872839093208313,
"learning_rate": 2.4500000000000003e-06,
"loss": 0.1,
"step": 49
},
{
"epoch": 0.6493506493506493,
"grad_norm": 1.2464176416397095,
"learning_rate": 2.5e-06,
"loss": 0.1024,
"step": 50
},
{
"epoch": 0.6623376623376623,
"grad_norm": 1.0786665678024292,
"learning_rate": 2.55e-06,
"loss": 0.087,
"step": 51
},
{
"epoch": 0.6753246753246753,
"grad_norm": 1.10042142868042,
"learning_rate": 2.6e-06,
"loss": 0.0838,
"step": 52
},
{
"epoch": 0.6883116883116883,
"grad_norm": 0.9031299948692322,
"learning_rate": 2.6500000000000005e-06,
"loss": 0.0804,
"step": 53
},
{
"epoch": 0.7012987012987013,
"grad_norm": 0.8072167634963989,
"learning_rate": 2.7000000000000004e-06,
"loss": 0.0786,
"step": 54
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.6948329210281372,
"learning_rate": 2.7500000000000004e-06,
"loss": 0.0773,
"step": 55
},
{
"epoch": 0.7272727272727273,
"grad_norm": 0.6062957644462585,
"learning_rate": 2.8000000000000003e-06,
"loss": 0.0756,
"step": 56
},
{
"epoch": 0.7402597402597403,
"grad_norm": 0.4804394841194153,
"learning_rate": 2.85e-06,
"loss": 0.0697,
"step": 57
},
{
"epoch": 0.7532467532467533,
"grad_norm": 0.5353919863700867,
"learning_rate": 2.9e-06,
"loss": 0.0697,
"step": 58
},
{
"epoch": 0.7662337662337663,
"grad_norm": 0.4344547390937805,
"learning_rate": 2.95e-06,
"loss": 0.0704,
"step": 59
},
{
"epoch": 0.7792207792207793,
"grad_norm": 0.574044942855835,
"learning_rate": 3e-06,
"loss": 0.0778,
"step": 60
},
{
"epoch": 0.7922077922077922,
"grad_norm": 0.5392284393310547,
"learning_rate": 3.05e-06,
"loss": 0.0658,
"step": 61
},
{
"epoch": 0.8051948051948052,
"grad_norm": 0.5098194479942322,
"learning_rate": 3.1000000000000004e-06,
"loss": 0.0661,
"step": 62
},
{
"epoch": 0.8181818181818182,
"grad_norm": 0.3733481168746948,
"learning_rate": 3.1500000000000003e-06,
"loss": 0.0667,
"step": 63
},
{
"epoch": 0.8311688311688312,
"grad_norm": 0.3714415431022644,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.0635,
"step": 64
},
{
"epoch": 0.8441558441558441,
"grad_norm": 0.37473437190055847,
"learning_rate": 3.2500000000000002e-06,
"loss": 0.0661,
"step": 65
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.35993579030036926,
"learning_rate": 3.3000000000000006e-06,
"loss": 0.0637,
"step": 66
},
{
"epoch": 0.8701298701298701,
"grad_norm": 0.41175705194473267,
"learning_rate": 3.3500000000000005e-06,
"loss": 0.0646,
"step": 67
},
{
"epoch": 0.8831168831168831,
"grad_norm": 0.29564622044563293,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.0627,
"step": 68
},
{
"epoch": 0.8961038961038961,
"grad_norm": 0.3018590211868286,
"learning_rate": 3.45e-06,
"loss": 0.0613,
"step": 69
},
{
"epoch": 0.9090909090909091,
"grad_norm": 0.499183714389801,
"learning_rate": 3.5e-06,
"loss": 0.0664,
"step": 70
},
{
"epoch": 0.922077922077922,
"grad_norm": 0.3450847864151001,
"learning_rate": 3.5500000000000003e-06,
"loss": 0.0589,
"step": 71
},
{
"epoch": 0.935064935064935,
"grad_norm": 0.26693543791770935,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.0633,
"step": 72
},
{
"epoch": 0.948051948051948,
"grad_norm": 0.2867635190486908,
"learning_rate": 3.65e-06,
"loss": 0.062,
"step": 73
},
{
"epoch": 0.961038961038961,
"grad_norm": 0.3328873813152313,
"learning_rate": 3.7e-06,
"loss": 0.0587,
"step": 74
},
{
"epoch": 0.974025974025974,
"grad_norm": 0.33611243963241577,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.058,
"step": 75
},
{
"epoch": 0.987012987012987,
"grad_norm": 0.2983446419239044,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.0632,
"step": 76
},
{
"epoch": 1.0,
"grad_norm": 0.3246895372867584,
"learning_rate": 3.85e-06,
"loss": 0.0583,
"step": 77
},
{
"epoch": 1.0129870129870129,
"grad_norm": 0.2912401556968689,
"learning_rate": 3.900000000000001e-06,
"loss": 0.0609,
"step": 78
},
{
"epoch": 1.025974025974026,
"grad_norm": 0.37205109000205994,
"learning_rate": 3.95e-06,
"loss": 0.0646,
"step": 79
},
{
"epoch": 1.0389610389610389,
"grad_norm": 0.2430678755044937,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0567,
"step": 80
},
{
"epoch": 1.051948051948052,
"grad_norm": 0.32996001839637756,
"learning_rate": 4.05e-06,
"loss": 0.0517,
"step": 81
},
{
"epoch": 1.0649350649350648,
"grad_norm": 0.274720698595047,
"learning_rate": 4.1e-06,
"loss": 0.0579,
"step": 82
},
{
"epoch": 1.077922077922078,
"grad_norm": 0.3047677278518677,
"learning_rate": 4.15e-06,
"loss": 0.0575,
"step": 83
},
{
"epoch": 1.0909090909090908,
"grad_norm": 0.2987304925918579,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.0576,
"step": 84
},
{
"epoch": 1.103896103896104,
"grad_norm": 0.32784077525138855,
"learning_rate": 4.25e-06,
"loss": 0.0607,
"step": 85
},
{
"epoch": 1.1168831168831168,
"grad_norm": 0.254140704870224,
"learning_rate": 4.3e-06,
"loss": 0.0582,
"step": 86
},
{
"epoch": 1.12987012987013,
"grad_norm": 0.2915174663066864,
"learning_rate": 4.350000000000001e-06,
"loss": 0.0614,
"step": 87
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.2874818444252014,
"learning_rate": 4.4e-06,
"loss": 0.0541,
"step": 88
},
{
"epoch": 1.155844155844156,
"grad_norm": 0.27614182233810425,
"learning_rate": 4.450000000000001e-06,
"loss": 0.0556,
"step": 89
},
{
"epoch": 1.1688311688311688,
"grad_norm": 0.3335096836090088,
"learning_rate": 4.5e-06,
"loss": 0.0601,
"step": 90
},
{
"epoch": 1.1818181818181819,
"grad_norm": 0.2302844524383545,
"learning_rate": 4.5500000000000005e-06,
"loss": 0.056,
"step": 91
},
{
"epoch": 1.1948051948051948,
"grad_norm": 0.22703984379768372,
"learning_rate": 4.600000000000001e-06,
"loss": 0.0577,
"step": 92
},
{
"epoch": 1.2077922077922079,
"grad_norm": 0.2960239350795746,
"learning_rate": 4.65e-06,
"loss": 0.0597,
"step": 93
},
{
"epoch": 1.2207792207792207,
"grad_norm": 0.20548498630523682,
"learning_rate": 4.7e-06,
"loss": 0.0531,
"step": 94
},
{
"epoch": 1.2337662337662338,
"grad_norm": 0.2792559564113617,
"learning_rate": 4.75e-06,
"loss": 0.0552,
"step": 95
},
{
"epoch": 1.2467532467532467,
"grad_norm": 0.25889474153518677,
"learning_rate": 4.800000000000001e-06,
"loss": 0.053,
"step": 96
},
{
"epoch": 1.2597402597402598,
"grad_norm": 0.2224734127521515,
"learning_rate": 4.85e-06,
"loss": 0.0528,
"step": 97
},
{
"epoch": 1.2727272727272727,
"grad_norm": 0.2264651507139206,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.0545,
"step": 98
},
{
"epoch": 1.2857142857142856,
"grad_norm": 0.29424387216567993,
"learning_rate": 4.95e-06,
"loss": 0.0571,
"step": 99
},
{
"epoch": 1.2987012987012987,
"grad_norm": 0.3200651705265045,
"learning_rate": 5e-06,
"loss": 0.0605,
"step": 100
},
{
"epoch": 1.3116883116883118,
"grad_norm": 0.284705251455307,
"learning_rate": 4.999905856597241e-06,
"loss": 0.0512,
"step": 101
},
{
"epoch": 1.3246753246753247,
"grad_norm": 0.25781720876693726,
"learning_rate": 4.999623433479346e-06,
"loss": 0.053,
"step": 102
},
{
"epoch": 1.3376623376623376,
"grad_norm": 0.2585068643093109,
"learning_rate": 4.999152751916936e-06,
"loss": 0.0557,
"step": 103
},
{
"epoch": 1.3506493506493507,
"grad_norm": 0.24417804181575775,
"learning_rate": 4.99849384735926e-06,
"loss": 0.0599,
"step": 104
},
{
"epoch": 1.3636363636363638,
"grad_norm": 0.2860206067562103,
"learning_rate": 4.997646769431532e-06,
"loss": 0.053,
"step": 105
},
{
"epoch": 1.3766233766233766,
"grad_norm": 0.22996841371059418,
"learning_rate": 4.9966115819311926e-06,
"loss": 0.0544,
"step": 106
},
{
"epoch": 1.3896103896103895,
"grad_norm": 0.2630089819431305,
"learning_rate": 4.9953883628231e-06,
"loss": 0.0509,
"step": 107
},
{
"epoch": 1.4025974025974026,
"grad_norm": 0.2588723599910736,
"learning_rate": 4.99397720423366e-06,
"loss": 0.0521,
"step": 108
},
{
"epoch": 1.4155844155844157,
"grad_norm": 0.3795599937438965,
"learning_rate": 4.992378212443891e-06,
"loss": 0.0527,
"step": 109
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.3013223111629486,
"learning_rate": 4.990591507881416e-06,
"loss": 0.0523,
"step": 110
},
{
"epoch": 1.4415584415584415,
"grad_norm": 0.24418188631534576,
"learning_rate": 4.988617225111392e-06,
"loss": 0.0494,
"step": 111
},
{
"epoch": 1.4545454545454546,
"grad_norm": 0.3064674735069275,
"learning_rate": 4.986455512826377e-06,
"loss": 0.0438,
"step": 112
},
{
"epoch": 1.4675324675324675,
"grad_norm": 0.2957422137260437,
"learning_rate": 4.984106533835132e-06,
"loss": 0.0496,
"step": 113
},
{
"epoch": 1.4805194805194806,
"grad_norm": 0.21359635889530182,
"learning_rate": 4.981570465050357e-06,
"loss": 0.0508,
"step": 114
},
{
"epoch": 1.4935064935064934,
"grad_norm": 0.20495343208312988,
"learning_rate": 4.978847497475369e-06,
"loss": 0.0535,
"step": 115
},
{
"epoch": 1.5064935064935066,
"grad_norm": 0.26068198680877686,
"learning_rate": 4.975937836189712e-06,
"loss": 0.0485,
"step": 116
},
{
"epoch": 1.5194805194805194,
"grad_norm": 0.26806536316871643,
"learning_rate": 4.97284170033372e-06,
"loss": 0.0505,
"step": 117
},
{
"epoch": 1.5324675324675323,
"grad_norm": 0.24916547536849976,
"learning_rate": 4.969559323092004e-06,
"loss": 0.0507,
"step": 118
},
{
"epoch": 1.5454545454545454,
"grad_norm": 0.26345163583755493,
"learning_rate": 4.966090951675893e-06,
"loss": 0.049,
"step": 119
},
{
"epoch": 1.5584415584415585,
"grad_norm": 0.2529750168323517,
"learning_rate": 4.962436847304818e-06,
"loss": 0.0471,
"step": 120
},
{
"epoch": 1.5714285714285714,
"grad_norm": 0.2879778742790222,
"learning_rate": 4.958597285186635e-06,
"loss": 0.047,
"step": 121
},
{
"epoch": 1.5844155844155843,
"grad_norm": 0.24268512427806854,
"learning_rate": 4.954572554496897e-06,
"loss": 0.0448,
"step": 122
},
{
"epoch": 1.5974025974025974,
"grad_norm": 0.3030378520488739,
"learning_rate": 4.950362958357078e-06,
"loss": 0.0483,
"step": 123
},
{
"epoch": 1.6103896103896105,
"grad_norm": 0.3552945852279663,
"learning_rate": 4.945968813811743e-06,
"loss": 0.0518,
"step": 124
},
{
"epoch": 1.6233766233766234,
"grad_norm": 0.32233837246894836,
"learning_rate": 4.941390451804668e-06,
"loss": 0.0488,
"step": 125
},
{
"epoch": 1.6363636363636362,
"grad_norm": 0.24810399115085602,
"learning_rate": 4.936628217153914e-06,
"loss": 0.0487,
"step": 126
},
{
"epoch": 1.6493506493506493,
"grad_norm": 0.2843495011329651,
"learning_rate": 4.931682468525863e-06,
"loss": 0.0485,
"step": 127
},
{
"epoch": 1.6623376623376624,
"grad_norm": 0.4453549087047577,
"learning_rate": 4.9265535784081965e-06,
"loss": 0.0441,
"step": 128
},
{
"epoch": 1.6753246753246753,
"grad_norm": 0.2711978852748871,
"learning_rate": 4.92124193308185e-06,
"loss": 0.0456,
"step": 129
},
{
"epoch": 1.6883116883116882,
"grad_norm": 0.2913718521595001,
"learning_rate": 4.915747932591916e-06,
"loss": 0.0478,
"step": 130
},
{
"epoch": 1.7012987012987013,
"grad_norm": 0.26739779114723206,
"learning_rate": 4.910071990717516e-06,
"loss": 0.0418,
"step": 131
},
{
"epoch": 1.7142857142857144,
"grad_norm": 0.33316293358802795,
"learning_rate": 4.9042145349406335e-06,
"loss": 0.0466,
"step": 132
},
{
"epoch": 1.7272727272727273,
"grad_norm": 0.3216155469417572,
"learning_rate": 4.898176006413925e-06,
"loss": 0.043,
"step": 133
},
{
"epoch": 1.7402597402597402,
"grad_norm": 0.3745043873786926,
"learning_rate": 4.891956859927489e-06,
"loss": 0.0471,
"step": 134
},
{
"epoch": 1.7532467532467533,
"grad_norm": 0.2518353760242462,
"learning_rate": 4.885557563874614e-06,
"loss": 0.045,
"step": 135
},
{
"epoch": 1.7662337662337664,
"grad_norm": 0.29494860768318176,
"learning_rate": 4.8789786002165055e-06,
"loss": 0.0437,
"step": 136
},
{
"epoch": 1.7792207792207793,
"grad_norm": 0.2658509612083435,
"learning_rate": 4.872220464445983e-06,
"loss": 0.0523,
"step": 137
},
{
"epoch": 1.7922077922077921,
"grad_norm": 0.3264024257659912,
"learning_rate": 4.865283665550167e-06,
"loss": 0.047,
"step": 138
},
{
"epoch": 1.8051948051948052,
"grad_norm": 0.29048386216163635,
"learning_rate": 4.8581687259721375e-06,
"loss": 0.0513,
"step": 139
},
{
"epoch": 1.8181818181818183,
"grad_norm": 0.21431702375411987,
"learning_rate": 4.850876181571592e-06,
"loss": 0.0426,
"step": 140
},
{
"epoch": 1.8311688311688312,
"grad_norm": 0.29871106147766113,
"learning_rate": 4.843406581584487e-06,
"loss": 0.0498,
"step": 141
},
{
"epoch": 1.844155844155844,
"grad_norm": 0.2374885231256485,
"learning_rate": 4.83576048858167e-06,
"loss": 0.0423,
"step": 142
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.32642969489097595,
"learning_rate": 4.8279384784265124e-06,
"loss": 0.043,
"step": 143
},
{
"epoch": 1.87012987012987,
"grad_norm": 0.3235689103603363,
"learning_rate": 4.8199411402315356e-06,
"loss": 0.0431,
"step": 144
},
{
"epoch": 1.883116883116883,
"grad_norm": 0.25325465202331543,
"learning_rate": 4.811769076314044e-06,
"loss": 0.0405,
"step": 145
},
{
"epoch": 1.896103896103896,
"grad_norm": 0.25112220644950867,
"learning_rate": 4.803422902150762e-06,
"loss": 0.0399,
"step": 146
},
{
"epoch": 1.9090909090909092,
"grad_norm": 0.2481043040752411,
"learning_rate": 4.794903246331477e-06,
"loss": 0.0405,
"step": 147
},
{
"epoch": 1.922077922077922,
"grad_norm": 0.28779706358909607,
"learning_rate": 4.786210750511701e-06,
"loss": 0.0407,
"step": 148
},
{
"epoch": 1.935064935064935,
"grad_norm": 0.2663511335849762,
"learning_rate": 4.777346069364343e-06,
"loss": 0.0404,
"step": 149
},
{
"epoch": 1.948051948051948,
"grad_norm": 0.27789220213890076,
"learning_rate": 4.7683098705303995e-06,
"loss": 0.0384,
"step": 150
},
{
"epoch": 1.9610389610389611,
"grad_norm": 0.34537413716316223,
"learning_rate": 4.7591028345686765e-06,
"loss": 0.0466,
"step": 151
},
{
"epoch": 1.974025974025974,
"grad_norm": 0.3259763717651367,
"learning_rate": 4.749725654904529e-06,
"loss": 0.0398,
"step": 152
},
{
"epoch": 1.987012987012987,
"grad_norm": 0.3018707036972046,
"learning_rate": 4.740179037777639e-06,
"loss": 0.0415,
"step": 153
},
{
"epoch": 2.0,
"grad_norm": 0.27019912004470825,
"learning_rate": 4.730463702188824e-06,
"loss": 0.0428,
"step": 154
},
{
"epoch": 2.012987012987013,
"grad_norm": 0.34202930331230164,
"learning_rate": 4.720580379845884e-06,
"loss": 0.04,
"step": 155
},
{
"epoch": 2.0259740259740258,
"grad_norm": 0.23893073201179504,
"learning_rate": 4.710529815108496e-06,
"loss": 0.0352,
"step": 156
},
{
"epoch": 2.038961038961039,
"grad_norm": 0.3122200071811676,
"learning_rate": 4.700312764932151e-06,
"loss": 0.0369,
"step": 157
},
{
"epoch": 2.051948051948052,
"grad_norm": 0.37174174189567566,
"learning_rate": 4.689929998811145e-06,
"loss": 0.035,
"step": 158
},
{
"epoch": 2.064935064935065,
"grad_norm": 0.30702632665634155,
"learning_rate": 4.679382298720625e-06,
"loss": 0.0335,
"step": 159
},
{
"epoch": 2.0779220779220777,
"grad_norm": 0.2560974955558777,
"learning_rate": 4.668670459057693e-06,
"loss": 0.0307,
"step": 160
},
{
"epoch": 2.090909090909091,
"grad_norm": 0.25084158778190613,
"learning_rate": 4.657795286581576e-06,
"loss": 0.033,
"step": 161
},
{
"epoch": 2.103896103896104,
"grad_norm": 0.25736576318740845,
"learning_rate": 4.64675760035287e-06,
"loss": 0.0336,
"step": 162
},
{
"epoch": 2.116883116883117,
"grad_norm": 0.29564720392227173,
"learning_rate": 4.635558231671846e-06,
"loss": 0.0325,
"step": 163
},
{
"epoch": 2.1298701298701297,
"grad_norm": 0.32640376687049866,
"learning_rate": 4.624198024015845e-06,
"loss": 0.0336,
"step": 164
},
{
"epoch": 2.142857142857143,
"grad_norm": 0.27138862013816833,
"learning_rate": 4.612677832975751e-06,
"loss": 0.0324,
"step": 165
},
{
"epoch": 2.155844155844156,
"grad_norm": 0.28909239172935486,
"learning_rate": 4.6009985261915536e-06,
"loss": 0.0351,
"step": 166
},
{
"epoch": 2.168831168831169,
"grad_norm": 0.26905709505081177,
"learning_rate": 4.5891609832869964e-06,
"loss": 0.0348,
"step": 167
},
{
"epoch": 2.1818181818181817,
"grad_norm": 0.3421840965747833,
"learning_rate": 4.577166095803336e-06,
"loss": 0.0362,
"step": 168
},
{
"epoch": 2.1948051948051948,
"grad_norm": 0.37504997849464417,
"learning_rate": 4.565014767132191e-06,
"loss": 0.038,
"step": 169
},
{
"epoch": 2.207792207792208,
"grad_norm": 0.3792576789855957,
"learning_rate": 4.552707912447504e-06,
"loss": 0.0345,
"step": 170
},
{
"epoch": 2.220779220779221,
"grad_norm": 0.38099661469459534,
"learning_rate": 4.540246458636619e-06,
"loss": 0.0265,
"step": 171
},
{
"epoch": 2.2337662337662336,
"grad_norm": 0.40823256969451904,
"learning_rate": 4.527631344230466e-06,
"loss": 0.0368,
"step": 172
},
{
"epoch": 2.2467532467532467,
"grad_norm": 0.28929030895233154,
"learning_rate": 4.514863519332882e-06,
"loss": 0.0282,
"step": 173
},
{
"epoch": 2.25974025974026,
"grad_norm": 0.32313477993011475,
"learning_rate": 4.501943945549054e-06,
"loss": 0.0292,
"step": 174
},
{
"epoch": 2.2727272727272725,
"grad_norm": 0.4433124363422394,
"learning_rate": 4.488873595913092e-06,
"loss": 0.0298,
"step": 175
},
{
"epoch": 2.2857142857142856,
"grad_norm": 0.32401469349861145,
"learning_rate": 4.475653454814746e-06,
"loss": 0.0296,
"step": 176
},
{
"epoch": 2.2987012987012987,
"grad_norm": 0.35543468594551086,
"learning_rate": 4.4622845179252735e-06,
"loss": 0.0313,
"step": 177
},
{
"epoch": 2.311688311688312,
"grad_norm": 0.37388646602630615,
"learning_rate": 4.44876779212244e-06,
"loss": 0.0305,
"step": 178
},
{
"epoch": 2.324675324675325,
"grad_norm": 0.33474496006965637,
"learning_rate": 4.435104295414697e-06,
"loss": 0.0289,
"step": 179
},
{
"epoch": 2.3376623376623376,
"grad_norm": 0.33111104369163513,
"learning_rate": 4.421295056864501e-06,
"loss": 0.0312,
"step": 180
},
{
"epoch": 2.3506493506493507,
"grad_norm": 0.3842385709285736,
"learning_rate": 4.407341116510818e-06,
"loss": 0.0278,
"step": 181
},
{
"epoch": 2.3636363636363638,
"grad_norm": 0.4244345724582672,
"learning_rate": 4.3932435252907914e-06,
"loss": 0.0275,
"step": 182
},
{
"epoch": 2.3766233766233764,
"grad_norm": 0.5842180252075195,
"learning_rate": 4.379003344960585e-06,
"loss": 0.035,
"step": 183
},
{
"epoch": 2.3896103896103895,
"grad_norm": 0.35604268312454224,
"learning_rate": 4.364621648015426e-06,
"loss": 0.0275,
"step": 184
},
{
"epoch": 2.4025974025974026,
"grad_norm": 0.41529580950737,
"learning_rate": 4.3500995176088235e-06,
"loss": 0.0315,
"step": 185
},
{
"epoch": 2.4155844155844157,
"grad_norm": 0.4051007926464081,
"learning_rate": 4.335438047470996e-06,
"loss": 0.0271,
"step": 186
},
{
"epoch": 2.4285714285714284,
"grad_norm": 0.33859074115753174,
"learning_rate": 4.320638341826494e-06,
"loss": 0.0271,
"step": 187
},
{
"epoch": 2.4415584415584415,
"grad_norm": 0.33747461438179016,
"learning_rate": 4.305701515311037e-06,
"loss": 0.0235,
"step": 188
},
{
"epoch": 2.4545454545454546,
"grad_norm": 0.3473111093044281,
"learning_rate": 4.290628692887564e-06,
"loss": 0.0284,
"step": 189
},
{
"epoch": 2.4675324675324677,
"grad_norm": 0.3321944773197174,
"learning_rate": 4.27542100976151e-06,
"loss": 0.024,
"step": 190
},
{
"epoch": 2.4805194805194803,
"grad_norm": 0.3281101584434509,
"learning_rate": 4.260079611295303e-06,
"loss": 0.0262,
"step": 191
},
{
"epoch": 2.4935064935064934,
"grad_norm": 0.4142085611820221,
"learning_rate": 4.244605652922108e-06,
"loss": 0.0218,
"step": 192
},
{
"epoch": 2.5064935064935066,
"grad_norm": 0.3764965832233429,
"learning_rate": 4.229000300058802e-06,
"loss": 0.0238,
"step": 193
},
{
"epoch": 2.5194805194805197,
"grad_norm": 0.4414701461791992,
"learning_rate": 4.2132647280182e-06,
"loss": 0.0267,
"step": 194
},
{
"epoch": 2.5324675324675323,
"grad_norm": 0.4074808657169342,
"learning_rate": 4.197400121920539e-06,
"loss": 0.022,
"step": 195
},
{
"epoch": 2.5454545454545454,
"grad_norm": 0.5768939852714539,
"learning_rate": 4.1814076766042206e-06,
"loss": 0.0311,
"step": 196
},
{
"epoch": 2.5584415584415585,
"grad_norm": 0.35587024688720703,
"learning_rate": 4.165288596535821e-06,
"loss": 0.0246,
"step": 197
},
{
"epoch": 2.571428571428571,
"grad_norm": 0.36500850319862366,
"learning_rate": 4.149044095719377e-06,
"loss": 0.0195,
"step": 198
},
{
"epoch": 2.5844155844155843,
"grad_norm": 0.3946477472782135,
"learning_rate": 4.132675397604956e-06,
"loss": 0.0208,
"step": 199
},
{
"epoch": 2.5974025974025974,
"grad_norm": 0.3371339440345764,
"learning_rate": 4.11618373499651e-06,
"loss": 0.0204,
"step": 200
},
{
"epoch": 2.6103896103896105,
"grad_norm": 0.41154706478118896,
"learning_rate": 4.099570349959025e-06,
"loss": 0.0223,
"step": 201
},
{
"epoch": 2.6233766233766236,
"grad_norm": 0.39301300048828125,
"learning_rate": 4.082836493724981e-06,
"loss": 0.0204,
"step": 202
},
{
"epoch": 2.6363636363636362,
"grad_norm": 0.3674089014530182,
"learning_rate": 4.065983426600113e-06,
"loss": 0.0195,
"step": 203
},
{
"epoch": 2.6493506493506493,
"grad_norm": 0.40296265482902527,
"learning_rate": 4.0490124178684884e-06,
"loss": 0.021,
"step": 204
},
{
"epoch": 2.6623376623376624,
"grad_norm": 0.4691706895828247,
"learning_rate": 4.031924745696916e-06,
"loss": 0.0179,
"step": 205
},
{
"epoch": 2.675324675324675,
"grad_norm": 0.44443100690841675,
"learning_rate": 4.014721697038678e-06,
"loss": 0.0242,
"step": 206
},
{
"epoch": 2.688311688311688,
"grad_norm": 0.31682541966438293,
"learning_rate": 3.997404567536606e-06,
"loss": 0.0193,
"step": 207
},
{
"epoch": 2.7012987012987013,
"grad_norm": 0.33720874786376953,
"learning_rate": 3.979974661425497e-06,
"loss": 0.0212,
"step": 208
},
{
"epoch": 2.7142857142857144,
"grad_norm": 0.41582977771759033,
"learning_rate": 3.962433291433889e-06,
"loss": 0.0242,
"step": 209
},
{
"epoch": 2.7272727272727275,
"grad_norm": 0.4688783884048462,
"learning_rate": 3.944781778685189e-06,
"loss": 0.0218,
"step": 210
},
{
"epoch": 2.74025974025974,
"grad_norm": 0.3696669638156891,
"learning_rate": 3.927021452598177e-06,
"loss": 0.0209,
"step": 211
},
{
"epoch": 2.7532467532467533,
"grad_norm": 0.36734238266944885,
"learning_rate": 3.909153650786878e-06,
"loss": 0.0165,
"step": 212
},
{
"epoch": 2.7662337662337664,
"grad_norm": 0.33928048610687256,
"learning_rate": 3.891179718959822e-06,
"loss": 0.0137,
"step": 213
},
{
"epoch": 2.779220779220779,
"grad_norm": 0.656510055065155,
"learning_rate": 3.873101010818692e-06,
"loss": 0.0258,
"step": 214
},
{
"epoch": 2.792207792207792,
"grad_norm": 0.5539777278900146,
"learning_rate": 3.8549188879563685e-06,
"loss": 0.0208,
"step": 215
},
{
"epoch": 2.8051948051948052,
"grad_norm": 0.4914684593677521,
"learning_rate": 3.836634719754385e-06,
"loss": 0.0192,
"step": 216
},
{
"epoch": 2.8181818181818183,
"grad_norm": 0.38955259323120117,
"learning_rate": 3.818249883279791e-06,
"loss": 0.0185,
"step": 217
},
{
"epoch": 2.8311688311688314,
"grad_norm": 0.45634275674819946,
"learning_rate": 3.7997657631814366e-06,
"loss": 0.0202,
"step": 218
},
{
"epoch": 2.844155844155844,
"grad_norm": 0.41473978757858276,
"learning_rate": 3.781183751585693e-06,
"loss": 0.0133,
"step": 219
},
{
"epoch": 2.857142857142857,
"grad_norm": 0.6281463503837585,
"learning_rate": 3.762505247991601e-06,
"loss": 0.0188,
"step": 220
},
{
"epoch": 2.87012987012987,
"grad_norm": 0.34762486815452576,
"learning_rate": 3.7437316591654726e-06,
"loss": 0.0199,
"step": 221
},
{
"epoch": 2.883116883116883,
"grad_norm": 0.43128135800361633,
"learning_rate": 3.724864399034932e-06,
"loss": 0.0175,
"step": 222
},
{
"epoch": 2.896103896103896,
"grad_norm": 0.4040665328502655,
"learning_rate": 3.7059048885824367e-06,
"loss": 0.0119,
"step": 223
},
{
"epoch": 2.909090909090909,
"grad_norm": 0.4182071089744568,
"learning_rate": 3.686854555738249e-06,
"loss": 0.0171,
"step": 224
},
{
"epoch": 2.9220779220779223,
"grad_norm": 0.38667839765548706,
"learning_rate": 3.6677148352728947e-06,
"loss": 0.0155,
"step": 225
},
{
"epoch": 2.935064935064935,
"grad_norm": 0.3983423709869385,
"learning_rate": 3.6484871686891044e-06,
"loss": 0.013,
"step": 226
},
{
"epoch": 2.948051948051948,
"grad_norm": 0.48213276267051697,
"learning_rate": 3.629173004113245e-06,
"loss": 0.0131,
"step": 227
},
{
"epoch": 2.961038961038961,
"grad_norm": 0.4538249969482422,
"learning_rate": 3.609773796186256e-06,
"loss": 0.0137,
"step": 228
},
{
"epoch": 2.974025974025974,
"grad_norm": 0.4226680397987366,
"learning_rate": 3.590291005954094e-06,
"loss": 0.0144,
"step": 229
},
{
"epoch": 2.987012987012987,
"grad_norm": 0.603485107421875,
"learning_rate": 3.570726100757693e-06,
"loss": 0.0179,
"step": 230
},
{
"epoch": 3.0,
"grad_norm": 0.5114914774894714,
"learning_rate": 3.5510805541224536e-06,
"loss": 0.0134,
"step": 231
},
{
"epoch": 3.012987012987013,
"grad_norm": 0.5039042830467224,
"learning_rate": 3.5313558456472623e-06,
"loss": 0.0113,
"step": 232
},
{
"epoch": 3.0259740259740258,
"grad_norm": 0.37786880135536194,
"learning_rate": 3.511553460893059e-06,
"loss": 0.0089,
"step": 233
},
{
"epoch": 3.038961038961039,
"grad_norm": 0.31840819120407104,
"learning_rate": 3.4916748912709506e-06,
"loss": 0.0078,
"step": 234
},
{
"epoch": 3.051948051948052,
"grad_norm": 0.3462812006473541,
"learning_rate": 3.4717216339298852e-06,
"loss": 0.0095,
"step": 235
},
{
"epoch": 3.064935064935065,
"grad_norm": 0.28717392683029175,
"learning_rate": 3.4516951916438974e-06,
"loss": 0.0043,
"step": 236
},
{
"epoch": 3.0779220779220777,
"grad_norm": 0.4881342649459839,
"learning_rate": 3.4315970726989244e-06,
"loss": 0.0109,
"step": 237
},
{
"epoch": 3.090909090909091,
"grad_norm": 0.34244024753570557,
"learning_rate": 3.4114287907792115e-06,
"loss": 0.0047,
"step": 238
},
{
"epoch": 3.103896103896104,
"grad_norm": 0.3604426085948944,
"learning_rate": 3.3911918648533094e-06,
"loss": 0.0059,
"step": 239
},
{
"epoch": 3.116883116883117,
"grad_norm": 0.34059545397758484,
"learning_rate": 3.3708878190596724e-06,
"loss": 0.0037,
"step": 240
},
{
"epoch": 3.1298701298701297,
"grad_norm": 0.350000262260437,
"learning_rate": 3.3505181825918685e-06,
"loss": 0.0059,
"step": 241
},
{
"epoch": 3.142857142857143,
"grad_norm": 0.4721887409687042,
"learning_rate": 3.33008448958341e-06,
"loss": 0.0082,
"step": 242
},
{
"epoch": 3.155844155844156,
"grad_norm": 0.3560850918292999,
"learning_rate": 3.3095882789922102e-06,
"loss": 0.007,
"step": 243
},
{
"epoch": 3.168831168831169,
"grad_norm": 0.385452002286911,
"learning_rate": 3.289031094484675e-06,
"loss": 0.0047,
"step": 244
},
{
"epoch": 3.1818181818181817,
"grad_norm": 0.3492503762245178,
"learning_rate": 3.2684144843194453e-06,
"loss": 0.0053,
"step": 245
},
{
"epoch": 3.1948051948051948,
"grad_norm": 0.3584858179092407,
"learning_rate": 3.2477400012307885e-06,
"loss": 0.0077,
"step": 246
},
{
"epoch": 3.207792207792208,
"grad_norm": 0.2692736089229584,
"learning_rate": 3.2270092023116564e-06,
"loss": 0.0031,
"step": 247
},
{
"epoch": 3.220779220779221,
"grad_norm": 0.33909231424331665,
"learning_rate": 3.206223648896409e-06,
"loss": 0.0051,
"step": 248
},
{
"epoch": 3.2337662337662336,
"grad_norm": 0.47461092472076416,
"learning_rate": 3.1853849064432296e-06,
"loss": 0.0053,
"step": 249
},
{
"epoch": 3.2467532467532467,
"grad_norm": 0.46319177746772766,
"learning_rate": 3.1644945444162155e-06,
"loss": 0.0076,
"step": 250
},
{
"epoch": 3.25974025974026,
"grad_norm": 0.3297309875488281,
"learning_rate": 3.14355413616718e-06,
"loss": 0.0035,
"step": 251
},
{
"epoch": 3.2727272727272725,
"grad_norm": 0.3955172598361969,
"learning_rate": 3.1225652588171534e-06,
"loss": 0.0047,
"step": 252
},
{
"epoch": 3.2857142857142856,
"grad_norm": 0.2394171506166458,
"learning_rate": 3.1015294931376035e-06,
"loss": 0.0025,
"step": 253
},
{
"epoch": 3.2987012987012987,
"grad_norm": 0.24900038540363312,
"learning_rate": 3.080448423431377e-06,
"loss": 0.0028,
"step": 254
},
{
"epoch": 3.311688311688312,
"grad_norm": 0.3579304814338684,
"learning_rate": 3.059323637413385e-06,
"loss": 0.0031,
"step": 255
},
{
"epoch": 3.324675324675325,
"grad_norm": 0.2939773499965668,
"learning_rate": 3.0381567260910166e-06,
"loss": 0.0037,
"step": 256
},
{
"epoch": 3.3376623376623376,
"grad_norm": 0.39939820766448975,
"learning_rate": 3.016949283644319e-06,
"loss": 0.0055,
"step": 257
},
{
"epoch": 3.3506493506493507,
"grad_norm": 0.4479775130748749,
"learning_rate": 2.9957029073059276e-06,
"loss": 0.0038,
"step": 258
},
{
"epoch": 3.3636363636363638,
"grad_norm": 0.3758586049079895,
"learning_rate": 2.9744191972407754e-06,
"loss": 0.0034,
"step": 259
},
{
"epoch": 3.3766233766233764,
"grad_norm": 0.31011316180229187,
"learning_rate": 2.9530997564255728e-06,
"loss": 0.0022,
"step": 260
},
{
"epoch": 3.3896103896103895,
"grad_norm": 0.5502382516860962,
"learning_rate": 2.931746190528082e-06,
"loss": 0.0021,
"step": 261
},
{
"epoch": 3.4025974025974026,
"grad_norm": 0.285674512386322,
"learning_rate": 2.9103601077861875e-06,
"loss": 0.0027,
"step": 262
},
{
"epoch": 3.4155844155844157,
"grad_norm": 0.3391030430793762,
"learning_rate": 2.888943118886771e-06,
"loss": 0.0037,
"step": 263
},
{
"epoch": 3.4285714285714284,
"grad_norm": 0.313784122467041,
"learning_rate": 2.8674968368444004e-06,
"loss": 0.002,
"step": 264
},
{
"epoch": 3.4415584415584415,
"grad_norm": 0.2796953618526459,
"learning_rate": 2.8460228768798507e-06,
"loss": 0.0026,
"step": 265
},
{
"epoch": 3.4545454545454546,
"grad_norm": 0.3058723509311676,
"learning_rate": 2.8245228562984518e-06,
"loss": 0.0025,
"step": 266
},
{
"epoch": 3.4675324675324677,
"grad_norm": 0.54490727186203,
"learning_rate": 2.80299839436828e-06,
"loss": 0.0043,
"step": 267
},
{
"epoch": 3.4805194805194803,
"grad_norm": 0.41025906801223755,
"learning_rate": 2.781451112198208e-06,
"loss": 0.0027,
"step": 268
},
{
"epoch": 3.4935064935064934,
"grad_norm": 0.35861679911613464,
"learning_rate": 2.7598826326158045e-06,
"loss": 0.004,
"step": 269
},
{
"epoch": 3.5064935064935066,
"grad_norm": 0.40969038009643555,
"learning_rate": 2.738294580045119e-06,
"loss": 0.0031,
"step": 270
},
{
"epoch": 3.5194805194805197,
"grad_norm": 0.4820692241191864,
"learning_rate": 2.7166885803843347e-06,
"loss": 0.0027,
"step": 271
},
{
"epoch": 3.5324675324675323,
"grad_norm": 0.3031913936138153,
"learning_rate": 2.695066260883313e-06,
"loss": 0.0013,
"step": 272
},
{
"epoch": 3.5454545454545454,
"grad_norm": 0.3935272693634033,
"learning_rate": 2.67342925002104e-06,
"loss": 0.0027,
"step": 273
},
{
"epoch": 3.5584415584415585,
"grad_norm": 0.2262854278087616,
"learning_rate": 2.65177917738298e-06,
"loss": 0.0019,
"step": 274
},
{
"epoch": 3.571428571428571,
"grad_norm": 0.2690446972846985,
"learning_rate": 2.6301176735383382e-06,
"loss": 0.0014,
"step": 275
},
{
"epoch": 3.5844155844155843,
"grad_norm": 0.33330366015434265,
"learning_rate": 2.6084463699172594e-06,
"loss": 0.0025,
"step": 276
},
{
"epoch": 3.5974025974025974,
"grad_norm": 0.3452131748199463,
"learning_rate": 2.586766898687955e-06,
"loss": 0.0018,
"step": 277
},
{
"epoch": 3.6103896103896105,
"grad_norm": 0.3789026737213135,
"learning_rate": 2.56508089263378e-06,
"loss": 0.001,
"step": 278
},
{
"epoch": 3.6233766233766236,
"grad_norm": 0.3677704334259033,
"learning_rate": 2.5433899850302552e-06,
"loss": 0.0013,
"step": 279
},
{
"epoch": 3.6363636363636362,
"grad_norm": 0.4359056055545807,
"learning_rate": 2.521695809522061e-06,
"loss": 0.0032,
"step": 280
},
{
"epoch": 3.6493506493506493,
"grad_norm": 0.2561199367046356,
"learning_rate": 2.5e-06,
"loss": 0.0018,
"step": 281
},
{
"epoch": 3.6623376623376624,
"grad_norm": 0.39096924662590027,
"learning_rate": 2.4783041904779386e-06,
"loss": 0.0031,
"step": 282
},
{
"epoch": 3.675324675324675,
"grad_norm": 0.3999404013156891,
"learning_rate": 2.4566100149697456e-06,
"loss": 0.0019,
"step": 283
},
{
"epoch": 3.688311688311688,
"grad_norm": 0.8379652500152588,
"learning_rate": 2.4349191073662203e-06,
"loss": 0.004,
"step": 284
},
{
"epoch": 3.7012987012987013,
"grad_norm": 0.3195594847202301,
"learning_rate": 2.4132331013120454e-06,
"loss": 0.0011,
"step": 285
},
{
"epoch": 3.7142857142857144,
"grad_norm": 0.2558881342411041,
"learning_rate": 2.3915536300827414e-06,
"loss": 0.001,
"step": 286
},
{
"epoch": 3.7272727272727275,
"grad_norm": 0.284496933221817,
"learning_rate": 2.3698823264616635e-06,
"loss": 0.0018,
"step": 287
},
{
"epoch": 3.74025974025974,
"grad_norm": 0.20427702367305756,
"learning_rate": 2.348220822617021e-06,
"loss": 0.0014,
"step": 288
},
{
"epoch": 3.7532467532467533,
"grad_norm": 0.32599779963493347,
"learning_rate": 2.32657074997896e-06,
"loss": 0.002,
"step": 289
},
{
"epoch": 3.7662337662337664,
"grad_norm": 0.3040351867675781,
"learning_rate": 2.3049337391166884e-06,
"loss": 0.0011,
"step": 290
},
{
"epoch": 3.779220779220779,
"grad_norm": 0.2709053158760071,
"learning_rate": 2.2833114196156657e-06,
"loss": 0.0008,
"step": 291
},
{
"epoch": 3.792207792207792,
"grad_norm": 0.2777629792690277,
"learning_rate": 2.261705419954882e-06,
"loss": 0.0014,
"step": 292
},
{
"epoch": 3.8051948051948052,
"grad_norm": 0.3083540201187134,
"learning_rate": 2.2401173673841963e-06,
"loss": 0.0016,
"step": 293
},
{
"epoch": 3.8181818181818183,
"grad_norm": 0.1168127954006195,
"learning_rate": 2.2185488878017934e-06,
"loss": 0.0005,
"step": 294
},
{
"epoch": 3.8311688311688314,
"grad_norm": 0.25492948293685913,
"learning_rate": 2.1970016056317202e-06,
"loss": 0.001,
"step": 295
},
{
"epoch": 3.844155844155844,
"grad_norm": 0.3559608459472656,
"learning_rate": 2.1754771437015495e-06,
"loss": 0.0009,
"step": 296
},
{
"epoch": 3.857142857142857,
"grad_norm": 0.43275198340415955,
"learning_rate": 2.1539771231201497e-06,
"loss": 0.002,
"step": 297
},
{
"epoch": 3.87012987012987,
"grad_norm": 0.35539472103118896,
"learning_rate": 2.1325031631555996e-06,
"loss": 0.0012,
"step": 298
},
{
"epoch": 3.883116883116883,
"grad_norm": 0.2857511341571808,
"learning_rate": 2.11105688111323e-06,
"loss": 0.0017,
"step": 299
},
{
"epoch": 3.896103896103896,
"grad_norm": 0.22510217130184174,
"learning_rate": 2.0896398922138124e-06,
"loss": 0.0007,
"step": 300
},
{
"epoch": 3.909090909090909,
"grad_norm": 0.15990178287029266,
"learning_rate": 2.0682538094719183e-06,
"loss": 0.0011,
"step": 301
},
{
"epoch": 3.9220779220779223,
"grad_norm": 0.11588839441537857,
"learning_rate": 2.0469002435744285e-06,
"loss": 0.0007,
"step": 302
},
{
"epoch": 3.935064935064935,
"grad_norm": 0.36557283997535706,
"learning_rate": 2.0255808027592263e-06,
"loss": 0.0008,
"step": 303
},
{
"epoch": 3.948051948051948,
"grad_norm": 0.2867473363876343,
"learning_rate": 2.004297092694073e-06,
"loss": 0.001,
"step": 304
},
{
"epoch": 3.961038961038961,
"grad_norm": 0.270842969417572,
"learning_rate": 1.9830507163556815e-06,
"loss": 0.0008,
"step": 305
},
{
"epoch": 3.974025974025974,
"grad_norm": 0.24662533402442932,
"learning_rate": 1.9618432739089843e-06,
"loss": 0.0006,
"step": 306
},
{
"epoch": 3.987012987012987,
"grad_norm": 0.12252429127693176,
"learning_rate": 1.9406763625866155e-06,
"loss": 0.0004,
"step": 307
},
{
"epoch": 4.0,
"grad_norm": 0.24726521968841553,
"learning_rate": 1.9195515765686237e-06,
"loss": 0.0004,
"step": 308
},
{
"epoch": 4.012987012987013,
"grad_norm": 0.04255533963441849,
"learning_rate": 1.8984705068623976e-06,
"loss": 0.0002,
"step": 309
},
{
"epoch": 4.025974025974026,
"grad_norm": 0.0485837422311306,
"learning_rate": 1.8774347411828472e-06,
"loss": 0.0002,
"step": 310
},
{
"epoch": 4.038961038961039,
"grad_norm": 0.06497793644666672,
"learning_rate": 1.8564458638328203e-06,
"loss": 0.0005,
"step": 311
},
{
"epoch": 4.0519480519480515,
"grad_norm": 0.06974362581968307,
"learning_rate": 1.835505455583786e-06,
"loss": 0.0002,
"step": 312
},
{
"epoch": 4.064935064935065,
"grad_norm": 0.10802063345909119,
"learning_rate": 1.8146150935567712e-06,
"loss": 0.0004,
"step": 313
},
{
"epoch": 4.077922077922078,
"grad_norm": 0.04839176684617996,
"learning_rate": 1.7937763511035904e-06,
"loss": 0.0002,
"step": 314
},
{
"epoch": 4.090909090909091,
"grad_norm": 0.16950847208499908,
"learning_rate": 1.7729907976883443e-06,
"loss": 0.0006,
"step": 315
},
{
"epoch": 4.103896103896104,
"grad_norm": 0.060468755662441254,
"learning_rate": 1.7522599987692113e-06,
"loss": 0.0001,
"step": 316
},
{
"epoch": 4.116883116883117,
"grad_norm": 0.054468460381031036,
"learning_rate": 1.7315855156805558e-06,
"loss": 0.0002,
"step": 317
},
{
"epoch": 4.12987012987013,
"grad_norm": 0.05310998484492302,
"learning_rate": 1.7109689055153261e-06,
"loss": 0.0002,
"step": 318
},
{
"epoch": 4.142857142857143,
"grad_norm": 0.1378607451915741,
"learning_rate": 1.690411721007791e-06,
"loss": 0.0004,
"step": 319
},
{
"epoch": 4.1558441558441555,
"grad_norm": 0.01266263797879219,
"learning_rate": 1.6699155104165903e-06,
"loss": 0.0001,
"step": 320
},
{
"epoch": 4.1688311688311686,
"grad_norm": 0.17714223265647888,
"learning_rate": 1.6494818174081317e-06,
"loss": 0.001,
"step": 321
},
{
"epoch": 4.181818181818182,
"grad_norm": 0.03800169378519058,
"learning_rate": 1.6291121809403287e-06,
"loss": 0.0002,
"step": 322
},
{
"epoch": 4.194805194805195,
"grad_norm": 0.17321327328681946,
"learning_rate": 1.6088081351466908e-06,
"loss": 0.0008,
"step": 323
},
{
"epoch": 4.207792207792208,
"grad_norm": 0.019961990416049957,
"learning_rate": 1.588571209220789e-06,
"loss": 0.0001,
"step": 324
},
{
"epoch": 4.220779220779221,
"grad_norm": 0.040765196084976196,
"learning_rate": 1.5684029273010762e-06,
"loss": 0.0002,
"step": 325
},
{
"epoch": 4.233766233766234,
"grad_norm": 0.06156046316027641,
"learning_rate": 1.5483048083561036e-06,
"loss": 0.0003,
"step": 326
},
{
"epoch": 4.246753246753247,
"grad_norm": 0.06152096390724182,
"learning_rate": 1.5282783660701154e-06,
"loss": 0.0003,
"step": 327
},
{
"epoch": 4.259740259740259,
"grad_norm": 0.010597504675388336,
"learning_rate": 1.5083251087290506e-06,
"loss": 0.0001,
"step": 328
},
{
"epoch": 4.2727272727272725,
"grad_norm": 0.0316089391708374,
"learning_rate": 1.4884465391069415e-06,
"loss": 0.0001,
"step": 329
},
{
"epoch": 4.285714285714286,
"grad_norm": 0.02659175731241703,
"learning_rate": 1.4686441543527374e-06,
"loss": 0.0002,
"step": 330
},
{
"epoch": 4.298701298701299,
"grad_norm": 0.02682899683713913,
"learning_rate": 1.4489194458775468e-06,
"loss": 0.0002,
"step": 331
},
{
"epoch": 4.311688311688312,
"grad_norm": 0.01274723932147026,
"learning_rate": 1.4292738992423066e-06,
"loss": 0.0001,
"step": 332
},
{
"epoch": 4.324675324675325,
"grad_norm": 0.10610726475715637,
"learning_rate": 1.409708994045907e-06,
"loss": 0.0005,
"step": 333
},
{
"epoch": 4.337662337662338,
"grad_norm": 0.018574735149741173,
"learning_rate": 1.3902262038137449e-06,
"loss": 0.0001,
"step": 334
},
{
"epoch": 4.35064935064935,
"grad_norm": 0.03301926702260971,
"learning_rate": 1.3708269958867565e-06,
"loss": 0.0002,
"step": 335
},
{
"epoch": 4.363636363636363,
"grad_norm": 0.05397050827741623,
"learning_rate": 1.3515128313108966e-06,
"loss": 0.0001,
"step": 336
},
{
"epoch": 4.376623376623376,
"grad_norm": 0.5025430917739868,
"learning_rate": 1.3322851647271057e-06,
"loss": 0.0008,
"step": 337
},
{
"epoch": 4.3896103896103895,
"grad_norm": 0.06098180264234543,
"learning_rate": 1.3131454442617523e-06,
"loss": 0.0002,
"step": 338
},
{
"epoch": 4.402597402597403,
"grad_norm": 0.02098267152905464,
"learning_rate": 1.2940951114175637e-06,
"loss": 0.0001,
"step": 339
},
{
"epoch": 4.415584415584416,
"grad_norm": 0.044198423624038696,
"learning_rate": 1.275135600965068e-06,
"loss": 0.0002,
"step": 340
},
{
"epoch": 4.428571428571429,
"grad_norm": 0.014930199831724167,
"learning_rate": 1.2562683408345279e-06,
"loss": 0.0002,
"step": 341
},
{
"epoch": 4.441558441558442,
"grad_norm": 0.33325693011283875,
"learning_rate": 1.237494752008399e-06,
"loss": 0.0006,
"step": 342
},
{
"epoch": 4.454545454545454,
"grad_norm": 0.031100880354642868,
"learning_rate": 1.2188162484143077e-06,
"loss": 0.0002,
"step": 343
},
{
"epoch": 4.467532467532467,
"grad_norm": 0.03873937577009201,
"learning_rate": 1.2002342368185638e-06,
"loss": 0.0001,
"step": 344
},
{
"epoch": 4.48051948051948,
"grad_norm": 0.22393281757831573,
"learning_rate": 1.18175011672021e-06,
"loss": 0.0005,
"step": 345
},
{
"epoch": 4.4935064935064934,
"grad_norm": 0.06489652395248413,
"learning_rate": 1.163365280245615e-06,
"loss": 0.0002,
"step": 346
},
{
"epoch": 4.5064935064935066,
"grad_norm": 0.04202171042561531,
"learning_rate": 1.1450811120436319e-06,
"loss": 0.0002,
"step": 347
},
{
"epoch": 4.51948051948052,
"grad_norm": 0.03509971871972084,
"learning_rate": 1.1268989891813085e-06,
"loss": 0.0002,
"step": 348
},
{
"epoch": 4.532467532467533,
"grad_norm": 0.013964281417429447,
"learning_rate": 1.1088202810401789e-06,
"loss": 0.0001,
"step": 349
},
{
"epoch": 4.545454545454545,
"grad_norm": 0.025696441531181335,
"learning_rate": 1.0908463492131227e-06,
"loss": 0.0001,
"step": 350
},
{
"epoch": 4.558441558441558,
"grad_norm": 0.03067847713828087,
"learning_rate": 1.0729785474018243e-06,
"loss": 0.0002,
"step": 351
},
{
"epoch": 4.571428571428571,
"grad_norm": 0.06406523287296295,
"learning_rate": 1.0552182213148119e-06,
"loss": 0.0002,
"step": 352
},
{
"epoch": 4.584415584415584,
"grad_norm": 0.02622838132083416,
"learning_rate": 1.0375667085661115e-06,
"loss": 0.0001,
"step": 353
},
{
"epoch": 4.597402597402597,
"grad_norm": 0.026939135044813156,
"learning_rate": 1.020025338574504e-06,
"loss": 0.0001,
"step": 354
},
{
"epoch": 4.6103896103896105,
"grad_norm": 0.009263522922992706,
"learning_rate": 1.0025954324633949e-06,
"loss": 0.0001,
"step": 355
},
{
"epoch": 4.623376623376624,
"grad_norm": 0.1577068418264389,
"learning_rate": 9.852783029613224e-07,
"loss": 0.0002,
"step": 356
},
{
"epoch": 4.636363636363637,
"grad_norm": 0.026724133640527725,
"learning_rate": 9.680752543030844e-07,
"loss": 0.0001,
"step": 357
},
{
"epoch": 4.64935064935065,
"grad_norm": 0.017666451632976532,
"learning_rate": 9.509875821315126e-07,
"loss": 0.0001,
"step": 358
},
{
"epoch": 4.662337662337662,
"grad_norm": 0.035038791596889496,
"learning_rate": 9.340165733998877e-07,
"loss": 0.0001,
"step": 359
},
{
"epoch": 4.675324675324675,
"grad_norm": 0.05781812220811844,
"learning_rate": 9.171635062750189e-07,
"loss": 0.0002,
"step": 360
},
{
"epoch": 4.688311688311688,
"grad_norm": 0.021358780562877655,
"learning_rate": 9.004296500409759e-07,
"loss": 0.0001,
"step": 361
},
{
"epoch": 4.701298701298701,
"grad_norm": 0.014494797214865685,
"learning_rate": 8.838162650034912e-07,
"loss": 0.0001,
"step": 362
},
{
"epoch": 4.714285714285714,
"grad_norm": 0.01157679595053196,
"learning_rate": 8.673246023950449e-07,
"loss": 0.0001,
"step": 363
},
{
"epoch": 4.7272727272727275,
"grad_norm": 0.015167619101703167,
"learning_rate": 8.509559042806237e-07,
"loss": 0.0001,
"step": 364
},
{
"epoch": 4.740259740259741,
"grad_norm": 0.01940612867474556,
"learning_rate": 8.347114034641807e-07,
"loss": 0.0001,
"step": 365
},
{
"epoch": 4.753246753246753,
"grad_norm": 0.07376569509506226,
"learning_rate": 8.185923233957802e-07,
"loss": 0.0001,
"step": 366
},
{
"epoch": 4.766233766233766,
"grad_norm": 0.015078631229698658,
"learning_rate": 8.025998780794622e-07,
"loss": 0.0001,
"step": 367
},
{
"epoch": 4.779220779220779,
"grad_norm": 0.03011564165353775,
"learning_rate": 7.867352719818008e-07,
"loss": 0.0002,
"step": 368
},
{
"epoch": 4.792207792207792,
"grad_norm": 0.017493847757577896,
"learning_rate": 7.709996999411984e-07,
"loss": 0.0001,
"step": 369
},
{
"epoch": 4.805194805194805,
"grad_norm": 0.02849338948726654,
"learning_rate": 7.553943470778927e-07,
"loss": 0.0001,
"step": 370
},
{
"epoch": 4.818181818181818,
"grad_norm": 0.038560837507247925,
"learning_rate": 7.399203887046977e-07,
"loss": 0.0001,
"step": 371
},
{
"epoch": 4.8311688311688314,
"grad_norm": 0.020657677203416824,
"learning_rate": 7.245789902384908e-07,
"loss": 0.0001,
"step": 372
},
{
"epoch": 4.8441558441558445,
"grad_norm": 0.030862174928188324,
"learning_rate": 7.093713071124361e-07,
"loss": 0.0001,
"step": 373
},
{
"epoch": 4.857142857142857,
"grad_norm": 0.02041393704712391,
"learning_rate": 6.942984846889639e-07,
"loss": 0.0002,
"step": 374
},
{
"epoch": 4.87012987012987,
"grad_norm": 0.04283998906612396,
"learning_rate": 6.793616581735063e-07,
"loss": 0.0002,
"step": 375
},
{
"epoch": 4.883116883116883,
"grad_norm": 0.010590342804789543,
"learning_rate": 6.645619525290043e-07,
"loss": 0.0001,
"step": 376
},
{
"epoch": 4.896103896103896,
"grad_norm": 0.012111359275877476,
"learning_rate": 6.499004823911772e-07,
"loss": 0.0001,
"step": 377
},
{
"epoch": 4.909090909090909,
"grad_norm": 0.05435957387089729,
"learning_rate": 6.353783519845752e-07,
"loss": 0.0002,
"step": 378
},
{
"epoch": 4.922077922077922,
"grad_norm": 0.030580980703234673,
"learning_rate": 6.209966550394162e-07,
"loss": 0.0001,
"step": 379
},
{
"epoch": 4.935064935064935,
"grad_norm": 0.026306739076972008,
"learning_rate": 6.067564747092095e-07,
"loss": 0.0001,
"step": 380
},
{
"epoch": 4.948051948051948,
"grad_norm": 0.01105985976755619,
"learning_rate": 5.926588834891823e-07,
"loss": 0.0001,
"step": 381
},
{
"epoch": 4.961038961038961,
"grad_norm": 0.011411640793085098,
"learning_rate": 5.787049431354996e-07,
"loss": 0.0001,
"step": 382
},
{
"epoch": 4.974025974025974,
"grad_norm": 0.013728387653827667,
"learning_rate": 5.648957045853043e-07,
"loss": 0.0001,
"step": 383
},
{
"epoch": 4.987012987012987,
"grad_norm": 0.016256002709269524,
"learning_rate": 5.512322078775603e-07,
"loss": 0.0001,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.01369263231754303,
"learning_rate": 5.377154820747271e-07,
"loss": 0.0001,
"step": 385
}
],
"logging_steps": 1,
"max_steps": 462,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 77,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8.604015918768456e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}