PEFT
Safetensors
SmolTalk-Nemo / trainer_state.json
Delta-Vector's picture
Upload folder using huggingface_hub
b094887 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.020906724647983023,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 4.181344929596605e-05,
"grad_norm": 0.40560808777809143,
"learning_rate": 4e-05,
"loss": 1.0882,
"step": 1
},
{
"epoch": 8.36268985919321e-05,
"grad_norm": 0.5086776614189148,
"learning_rate": 8e-05,
"loss": 1.2032,
"step": 2
},
{
"epoch": 0.00012544034788789814,
"grad_norm": 0.37056657671928406,
"learning_rate": 0.00012,
"loss": 1.0877,
"step": 3
},
{
"epoch": 0.0001672537971838642,
"grad_norm": 0.3852301836013794,
"learning_rate": 0.00016,
"loss": 0.8978,
"step": 4
},
{
"epoch": 0.00020906724647983023,
"grad_norm": 0.2954806089401245,
"learning_rate": 0.0002,
"loss": 0.9203,
"step": 5
},
{
"epoch": 0.0002508806957757963,
"grad_norm": 0.34586089849472046,
"learning_rate": 0.0001995959595959596,
"loss": 1.0795,
"step": 6
},
{
"epoch": 0.00029269414507176236,
"grad_norm": 0.35712841153144836,
"learning_rate": 0.0001991919191919192,
"loss": 1.6382,
"step": 7
},
{
"epoch": 0.0003345075943677284,
"grad_norm": 0.3133651316165924,
"learning_rate": 0.00019878787878787878,
"loss": 1.0971,
"step": 8
},
{
"epoch": 0.00037632104366369445,
"grad_norm": 0.311149537563324,
"learning_rate": 0.00019838383838383837,
"loss": 1.1428,
"step": 9
},
{
"epoch": 0.00041813449295966047,
"grad_norm": 0.3039856553077698,
"learning_rate": 0.000197979797979798,
"loss": 0.9836,
"step": 10
},
{
"epoch": 0.00045994794225562654,
"grad_norm": 0.24750354886054993,
"learning_rate": 0.0001975757575757576,
"loss": 0.9899,
"step": 11
},
{
"epoch": 0.0005017613915515926,
"grad_norm": 0.28363236784935,
"learning_rate": 0.0001971717171717172,
"loss": 0.9879,
"step": 12
},
{
"epoch": 0.0005435748408475586,
"grad_norm": 0.352985143661499,
"learning_rate": 0.00019676767676767677,
"loss": 1.2943,
"step": 13
},
{
"epoch": 0.0005853882901435247,
"grad_norm": 0.3262224793434143,
"learning_rate": 0.00019636363636363636,
"loss": 1.0721,
"step": 14
},
{
"epoch": 0.0006272017394394907,
"grad_norm": 0.2579759359359741,
"learning_rate": 0.00019595959595959596,
"loss": 0.9534,
"step": 15
},
{
"epoch": 0.0006690151887354568,
"grad_norm": 0.29768794775009155,
"learning_rate": 0.00019555555555555556,
"loss": 1.1008,
"step": 16
},
{
"epoch": 0.0007108286380314228,
"grad_norm": 0.2844472825527191,
"learning_rate": 0.00019515151515151516,
"loss": 0.9638,
"step": 17
},
{
"epoch": 0.0007526420873273889,
"grad_norm": 0.29892027378082275,
"learning_rate": 0.00019474747474747476,
"loss": 1.0082,
"step": 18
},
{
"epoch": 0.0007944555366233549,
"grad_norm": 0.33687111735343933,
"learning_rate": 0.00019434343434343435,
"loss": 1.2364,
"step": 19
},
{
"epoch": 0.0008362689859193209,
"grad_norm": 0.29574063420295715,
"learning_rate": 0.00019393939393939395,
"loss": 0.9705,
"step": 20
},
{
"epoch": 0.000878082435215287,
"grad_norm": 0.3137240409851074,
"learning_rate": 0.00019353535353535355,
"loss": 0.9793,
"step": 21
},
{
"epoch": 0.0009198958845112531,
"grad_norm": 0.25476816296577454,
"learning_rate": 0.00019313131313131315,
"loss": 1.0001,
"step": 22
},
{
"epoch": 0.0009617093338072191,
"grad_norm": 0.2840677797794342,
"learning_rate": 0.00019272727272727274,
"loss": 1.3237,
"step": 23
},
{
"epoch": 0.0010035227831031851,
"grad_norm": 0.27187085151672363,
"learning_rate": 0.00019232323232323232,
"loss": 1.0067,
"step": 24
},
{
"epoch": 0.0010453362323991511,
"grad_norm": 0.2687990069389343,
"learning_rate": 0.00019191919191919191,
"loss": 1.1918,
"step": 25
},
{
"epoch": 0.0010871496816951172,
"grad_norm": 0.2793806791305542,
"learning_rate": 0.0001915151515151515,
"loss": 0.9764,
"step": 26
},
{
"epoch": 0.0011289631309910832,
"grad_norm": 0.30926743149757385,
"learning_rate": 0.00019111111111111114,
"loss": 1.249,
"step": 27
},
{
"epoch": 0.0011707765802870494,
"grad_norm": 0.24233047664165497,
"learning_rate": 0.00019070707070707073,
"loss": 0.8826,
"step": 28
},
{
"epoch": 0.0012125900295830154,
"grad_norm": 0.2891562879085541,
"learning_rate": 0.0001903030303030303,
"loss": 0.9811,
"step": 29
},
{
"epoch": 0.0012544034788789815,
"grad_norm": 0.2661428153514862,
"learning_rate": 0.0001898989898989899,
"loss": 1.0042,
"step": 30
},
{
"epoch": 0.0012962169281749475,
"grad_norm": 0.28110119700431824,
"learning_rate": 0.0001894949494949495,
"loss": 0.9914,
"step": 31
},
{
"epoch": 0.0013380303774709135,
"grad_norm": 0.24006132781505585,
"learning_rate": 0.0001890909090909091,
"loss": 0.9096,
"step": 32
},
{
"epoch": 0.0013798438267668795,
"grad_norm": 0.2505486011505127,
"learning_rate": 0.0001886868686868687,
"loss": 1.2024,
"step": 33
},
{
"epoch": 0.0014216572760628455,
"grad_norm": 0.2601507306098938,
"learning_rate": 0.0001882828282828283,
"loss": 0.9725,
"step": 34
},
{
"epoch": 0.0014634707253588116,
"grad_norm": 0.25052663683891296,
"learning_rate": 0.0001878787878787879,
"loss": 1.4409,
"step": 35
},
{
"epoch": 0.0015052841746547778,
"grad_norm": 0.2797248661518097,
"learning_rate": 0.0001874747474747475,
"loss": 1.0476,
"step": 36
},
{
"epoch": 0.0015470976239507438,
"grad_norm": 0.22307826578617096,
"learning_rate": 0.0001870707070707071,
"loss": 0.826,
"step": 37
},
{
"epoch": 0.0015889110732467098,
"grad_norm": 0.2908446490764618,
"learning_rate": 0.0001866666666666667,
"loss": 0.8436,
"step": 38
},
{
"epoch": 0.0016307245225426759,
"grad_norm": 0.2313789427280426,
"learning_rate": 0.00018626262626262628,
"loss": 0.976,
"step": 39
},
{
"epoch": 0.0016725379718386419,
"grad_norm": 0.2308812439441681,
"learning_rate": 0.00018585858585858586,
"loss": 0.9195,
"step": 40
},
{
"epoch": 0.001714351421134608,
"grad_norm": 0.29213932156562805,
"learning_rate": 0.00018545454545454545,
"loss": 0.9328,
"step": 41
},
{
"epoch": 0.001756164870430574,
"grad_norm": 0.24189592897891998,
"learning_rate": 0.00018505050505050505,
"loss": 1.2261,
"step": 42
},
{
"epoch": 0.00179797831972654,
"grad_norm": 0.2668328285217285,
"learning_rate": 0.00018464646464646465,
"loss": 0.9107,
"step": 43
},
{
"epoch": 0.0018397917690225062,
"grad_norm": 0.2463718056678772,
"learning_rate": 0.00018424242424242427,
"loss": 0.9482,
"step": 44
},
{
"epoch": 0.0018816052183184722,
"grad_norm": 0.2651210129261017,
"learning_rate": 0.00018383838383838384,
"loss": 0.9202,
"step": 45
},
{
"epoch": 0.0019234186676144382,
"grad_norm": 0.23657365143299103,
"learning_rate": 0.00018343434343434344,
"loss": 0.9263,
"step": 46
},
{
"epoch": 0.001965232116910404,
"grad_norm": 0.2667325735092163,
"learning_rate": 0.00018303030303030304,
"loss": 1.0621,
"step": 47
},
{
"epoch": 0.0020070455662063703,
"grad_norm": 0.25392603874206543,
"learning_rate": 0.00018262626262626264,
"loss": 0.8932,
"step": 48
},
{
"epoch": 0.0020488590155023365,
"grad_norm": 0.23611199855804443,
"learning_rate": 0.00018222222222222224,
"loss": 0.9531,
"step": 49
},
{
"epoch": 0.0020906724647983023,
"grad_norm": 0.23251543939113617,
"learning_rate": 0.00018181818181818183,
"loss": 1.0771,
"step": 50
},
{
"epoch": 0.0021324859140942685,
"grad_norm": 0.2778080403804779,
"learning_rate": 0.0001814141414141414,
"loss": 0.8916,
"step": 51
},
{
"epoch": 0.0021742993633902343,
"grad_norm": 0.23373359441757202,
"learning_rate": 0.00018101010101010103,
"loss": 0.9641,
"step": 52
},
{
"epoch": 0.0022161128126862006,
"grad_norm": 0.3123236894607544,
"learning_rate": 0.00018060606060606063,
"loss": 0.915,
"step": 53
},
{
"epoch": 0.0022579262619821664,
"grad_norm": 0.40312856435775757,
"learning_rate": 0.00018020202020202023,
"loss": 1.0666,
"step": 54
},
{
"epoch": 0.0022997397112781326,
"grad_norm": 0.2284204065799713,
"learning_rate": 0.0001797979797979798,
"loss": 0.9649,
"step": 55
},
{
"epoch": 0.002341553160574099,
"grad_norm": 0.24177253246307373,
"learning_rate": 0.0001793939393939394,
"loss": 1.0698,
"step": 56
},
{
"epoch": 0.0023833666098700646,
"grad_norm": 0.24964472651481628,
"learning_rate": 0.000178989898989899,
"loss": 0.9042,
"step": 57
},
{
"epoch": 0.002425180059166031,
"grad_norm": 0.2380153387784958,
"learning_rate": 0.0001785858585858586,
"loss": 1.0326,
"step": 58
},
{
"epoch": 0.0024669935084619967,
"grad_norm": 0.3179625868797302,
"learning_rate": 0.0001781818181818182,
"loss": 1.1221,
"step": 59
},
{
"epoch": 0.002508806957757963,
"grad_norm": 0.26389947533607483,
"learning_rate": 0.00017777777777777779,
"loss": 0.9786,
"step": 60
},
{
"epoch": 0.0025506204070539287,
"grad_norm": 0.30544987320899963,
"learning_rate": 0.00017737373737373738,
"loss": 0.9644,
"step": 61
},
{
"epoch": 0.002592433856349895,
"grad_norm": 0.36304402351379395,
"learning_rate": 0.00017696969696969698,
"loss": 0.9074,
"step": 62
},
{
"epoch": 0.002634247305645861,
"grad_norm": 0.23597782850265503,
"learning_rate": 0.00017656565656565658,
"loss": 1.0777,
"step": 63
},
{
"epoch": 0.002676060754941827,
"grad_norm": 0.26906973123550415,
"learning_rate": 0.00017616161616161618,
"loss": 0.8205,
"step": 64
},
{
"epoch": 0.0027178742042377932,
"grad_norm": 0.2425510138273239,
"learning_rate": 0.00017575757575757578,
"loss": 0.9539,
"step": 65
},
{
"epoch": 0.002759687653533759,
"grad_norm": 0.2500934600830078,
"learning_rate": 0.00017535353535353535,
"loss": 0.9296,
"step": 66
},
{
"epoch": 0.0028015011028297253,
"grad_norm": 0.2523915469646454,
"learning_rate": 0.00017494949494949494,
"loss": 0.8812,
"step": 67
},
{
"epoch": 0.002843314552125691,
"grad_norm": 0.2539198398590088,
"learning_rate": 0.00017454545454545454,
"loss": 0.9064,
"step": 68
},
{
"epoch": 0.0028851280014216573,
"grad_norm": 0.27413180470466614,
"learning_rate": 0.00017414141414141414,
"loss": 0.9405,
"step": 69
},
{
"epoch": 0.002926941450717623,
"grad_norm": 0.2472667247056961,
"learning_rate": 0.00017373737373737377,
"loss": 0.9883,
"step": 70
},
{
"epoch": 0.0029687549000135894,
"grad_norm": 0.3356216549873352,
"learning_rate": 0.00017333333333333334,
"loss": 0.981,
"step": 71
},
{
"epoch": 0.0030105683493095556,
"grad_norm": 0.24823850393295288,
"learning_rate": 0.00017292929292929293,
"loss": 0.9839,
"step": 72
},
{
"epoch": 0.0030523817986055214,
"grad_norm": 0.23737181723117828,
"learning_rate": 0.00017252525252525253,
"loss": 0.9648,
"step": 73
},
{
"epoch": 0.0030941952479014876,
"grad_norm": 0.28804993629455566,
"learning_rate": 0.00017212121212121213,
"loss": 1.022,
"step": 74
},
{
"epoch": 0.0031360086971974534,
"grad_norm": 0.2285371720790863,
"learning_rate": 0.00017171717171717173,
"loss": 1.0481,
"step": 75
},
{
"epoch": 0.0031778221464934197,
"grad_norm": 0.23818029463291168,
"learning_rate": 0.00017131313131313133,
"loss": 1.0973,
"step": 76
},
{
"epoch": 0.0032196355957893855,
"grad_norm": 0.2709192931652069,
"learning_rate": 0.0001709090909090909,
"loss": 0.8675,
"step": 77
},
{
"epoch": 0.0032614490450853517,
"grad_norm": 0.23118779063224792,
"learning_rate": 0.00017050505050505052,
"loss": 0.8699,
"step": 78
},
{
"epoch": 0.003303262494381318,
"grad_norm": 0.24262340366840363,
"learning_rate": 0.00017010101010101012,
"loss": 1.2814,
"step": 79
},
{
"epoch": 0.0033450759436772838,
"grad_norm": 0.2542665898799896,
"learning_rate": 0.00016969696969696972,
"loss": 0.9736,
"step": 80
},
{
"epoch": 0.00338688939297325,
"grad_norm": 0.28399115800857544,
"learning_rate": 0.00016929292929292932,
"loss": 0.8836,
"step": 81
},
{
"epoch": 0.003428702842269216,
"grad_norm": 0.24225646257400513,
"learning_rate": 0.00016888888888888889,
"loss": 0.9176,
"step": 82
},
{
"epoch": 0.003470516291565182,
"grad_norm": 0.24356476962566376,
"learning_rate": 0.00016848484848484848,
"loss": 0.9305,
"step": 83
},
{
"epoch": 0.003512329740861148,
"grad_norm": 0.24460910260677338,
"learning_rate": 0.00016808080808080808,
"loss": 0.8662,
"step": 84
},
{
"epoch": 0.003554143190157114,
"grad_norm": 0.29980015754699707,
"learning_rate": 0.00016767676767676768,
"loss": 1.0232,
"step": 85
},
{
"epoch": 0.00359595663945308,
"grad_norm": 0.23906633257865906,
"learning_rate": 0.00016727272727272728,
"loss": 1.315,
"step": 86
},
{
"epoch": 0.003637770088749046,
"grad_norm": 0.23798798024654388,
"learning_rate": 0.00016686868686868688,
"loss": 0.8968,
"step": 87
},
{
"epoch": 0.0036795835380450123,
"grad_norm": 0.30493396520614624,
"learning_rate": 0.00016646464646464647,
"loss": 1.0255,
"step": 88
},
{
"epoch": 0.003721396987340978,
"grad_norm": 0.23409593105316162,
"learning_rate": 0.00016606060606060607,
"loss": 0.8587,
"step": 89
},
{
"epoch": 0.0037632104366369444,
"grad_norm": 0.24599049985408783,
"learning_rate": 0.00016565656565656567,
"loss": 0.8342,
"step": 90
},
{
"epoch": 0.00380502388593291,
"grad_norm": 0.25307658314704895,
"learning_rate": 0.00016525252525252527,
"loss": 1.0266,
"step": 91
},
{
"epoch": 0.0038468373352288764,
"grad_norm": 0.23210497200489044,
"learning_rate": 0.00016484848484848487,
"loss": 0.9955,
"step": 92
},
{
"epoch": 0.0038886507845248422,
"grad_norm": 0.23097635805606842,
"learning_rate": 0.00016444444444444444,
"loss": 0.8772,
"step": 93
},
{
"epoch": 0.003930464233820808,
"grad_norm": 0.2318320870399475,
"learning_rate": 0.00016404040404040403,
"loss": 0.9421,
"step": 94
},
{
"epoch": 0.003972277683116775,
"grad_norm": 0.2513769268989563,
"learning_rate": 0.00016363636363636366,
"loss": 0.916,
"step": 95
},
{
"epoch": 0.0040140911324127405,
"grad_norm": 0.24191761016845703,
"learning_rate": 0.00016323232323232326,
"loss": 0.9845,
"step": 96
},
{
"epoch": 0.004055904581708706,
"grad_norm": 0.2810687720775604,
"learning_rate": 0.00016282828282828283,
"loss": 0.9531,
"step": 97
},
{
"epoch": 0.004097718031004673,
"grad_norm": 0.24600476026535034,
"learning_rate": 0.00016242424242424243,
"loss": 1.0229,
"step": 98
},
{
"epoch": 0.004139531480300639,
"grad_norm": 0.22848957777023315,
"learning_rate": 0.00016202020202020202,
"loss": 0.9169,
"step": 99
},
{
"epoch": 0.004181344929596605,
"grad_norm": 0.23503725230693817,
"learning_rate": 0.00016161616161616162,
"loss": 0.9684,
"step": 100
},
{
"epoch": 0.00422315837889257,
"grad_norm": 0.24198566377162933,
"learning_rate": 0.00016121212121212122,
"loss": 0.9396,
"step": 101
},
{
"epoch": 0.004264971828188537,
"grad_norm": 0.23596572875976562,
"learning_rate": 0.00016080808080808082,
"loss": 0.9273,
"step": 102
},
{
"epoch": 0.004306785277484503,
"grad_norm": 0.25463101267814636,
"learning_rate": 0.0001604040404040404,
"loss": 1.0802,
"step": 103
},
{
"epoch": 0.004348598726780469,
"grad_norm": 0.25411441922187805,
"learning_rate": 0.00016,
"loss": 1.1421,
"step": 104
},
{
"epoch": 0.004390412176076435,
"grad_norm": 0.2431924194097519,
"learning_rate": 0.0001595959595959596,
"loss": 0.8269,
"step": 105
},
{
"epoch": 0.004432225625372401,
"grad_norm": 0.2581568956375122,
"learning_rate": 0.0001591919191919192,
"loss": 1.0813,
"step": 106
},
{
"epoch": 0.004474039074668367,
"grad_norm": 0.2607171833515167,
"learning_rate": 0.0001587878787878788,
"loss": 0.9057,
"step": 107
},
{
"epoch": 0.004515852523964333,
"grad_norm": 0.2493910789489746,
"learning_rate": 0.00015838383838383838,
"loss": 1.0084,
"step": 108
},
{
"epoch": 0.004557665973260299,
"grad_norm": 0.24666810035705566,
"learning_rate": 0.00015797979797979798,
"loss": 0.9075,
"step": 109
},
{
"epoch": 0.004599479422556265,
"grad_norm": 0.27022406458854675,
"learning_rate": 0.00015757575757575757,
"loss": 1.0225,
"step": 110
},
{
"epoch": 0.004641292871852231,
"grad_norm": 0.23321093618869781,
"learning_rate": 0.00015717171717171717,
"loss": 0.9117,
"step": 111
},
{
"epoch": 0.004683106321148198,
"grad_norm": 0.2494395226240158,
"learning_rate": 0.0001567676767676768,
"loss": 0.9428,
"step": 112
},
{
"epoch": 0.0047249197704441635,
"grad_norm": 0.23083235323429108,
"learning_rate": 0.00015636363636363637,
"loss": 0.9327,
"step": 113
},
{
"epoch": 0.004766733219740129,
"grad_norm": 0.23585864901542664,
"learning_rate": 0.00015595959595959597,
"loss": 0.9037,
"step": 114
},
{
"epoch": 0.004808546669036095,
"grad_norm": 0.27985578775405884,
"learning_rate": 0.00015555555555555556,
"loss": 0.9358,
"step": 115
},
{
"epoch": 0.004850360118332062,
"grad_norm": 0.23428787291049957,
"learning_rate": 0.00015515151515151516,
"loss": 0.9044,
"step": 116
},
{
"epoch": 0.004892173567628028,
"grad_norm": 0.2439994215965271,
"learning_rate": 0.00015474747474747476,
"loss": 0.8798,
"step": 117
},
{
"epoch": 0.004933987016923993,
"grad_norm": 0.2722432315349579,
"learning_rate": 0.00015434343434343436,
"loss": 0.9357,
"step": 118
},
{
"epoch": 0.00497580046621996,
"grad_norm": 0.23857751488685608,
"learning_rate": 0.00015393939393939393,
"loss": 0.8666,
"step": 119
},
{
"epoch": 0.005017613915515926,
"grad_norm": 0.2787211239337921,
"learning_rate": 0.00015353535353535353,
"loss": 1.1073,
"step": 120
},
{
"epoch": 0.005059427364811892,
"grad_norm": 0.398342490196228,
"learning_rate": 0.00015313131313131315,
"loss": 0.8607,
"step": 121
},
{
"epoch": 0.0051012408141078575,
"grad_norm": 0.24997954070568085,
"learning_rate": 0.00015272727272727275,
"loss": 0.9571,
"step": 122
},
{
"epoch": 0.005143054263403824,
"grad_norm": 0.24160504341125488,
"learning_rate": 0.00015232323232323235,
"loss": 0.956,
"step": 123
},
{
"epoch": 0.00518486771269979,
"grad_norm": 0.25686195492744446,
"learning_rate": 0.00015191919191919192,
"loss": 0.9241,
"step": 124
},
{
"epoch": 0.005226681161995756,
"grad_norm": 0.22665072977542877,
"learning_rate": 0.00015151515151515152,
"loss": 1.1356,
"step": 125
},
{
"epoch": 0.005268494611291722,
"grad_norm": 0.2378469556570053,
"learning_rate": 0.0001511111111111111,
"loss": 0.7726,
"step": 126
},
{
"epoch": 0.005310308060587688,
"grad_norm": 0.24122726917266846,
"learning_rate": 0.0001507070707070707,
"loss": 0.9809,
"step": 127
},
{
"epoch": 0.005352121509883654,
"grad_norm": 0.2466202676296234,
"learning_rate": 0.0001503030303030303,
"loss": 1.1704,
"step": 128
},
{
"epoch": 0.00539393495917962,
"grad_norm": 0.22361689805984497,
"learning_rate": 0.0001498989898989899,
"loss": 0.8598,
"step": 129
},
{
"epoch": 0.0054357484084755865,
"grad_norm": 0.7460150718688965,
"learning_rate": 0.0001494949494949495,
"loss": 0.8546,
"step": 130
},
{
"epoch": 0.005477561857771552,
"grad_norm": 0.2460203766822815,
"learning_rate": 0.0001490909090909091,
"loss": 0.8975,
"step": 131
},
{
"epoch": 0.005519375307067518,
"grad_norm": 0.3213840425014496,
"learning_rate": 0.0001486868686868687,
"loss": 1.6733,
"step": 132
},
{
"epoch": 0.005561188756363484,
"grad_norm": 0.27876222133636475,
"learning_rate": 0.0001482828282828283,
"loss": 1.0187,
"step": 133
},
{
"epoch": 0.0056030022056594506,
"grad_norm": 0.23614326119422913,
"learning_rate": 0.0001478787878787879,
"loss": 0.844,
"step": 134
},
{
"epoch": 0.005644815654955416,
"grad_norm": 0.2533978521823883,
"learning_rate": 0.00014747474747474747,
"loss": 0.898,
"step": 135
},
{
"epoch": 0.005686629104251382,
"grad_norm": 0.24515709280967712,
"learning_rate": 0.00014707070707070706,
"loss": 0.996,
"step": 136
},
{
"epoch": 0.005728442553547349,
"grad_norm": 0.2675986588001251,
"learning_rate": 0.00014666666666666666,
"loss": 0.8699,
"step": 137
},
{
"epoch": 0.005770256002843315,
"grad_norm": 0.2421002835035324,
"learning_rate": 0.0001462626262626263,
"loss": 0.8972,
"step": 138
},
{
"epoch": 0.0058120694521392804,
"grad_norm": 0.23082560300827026,
"learning_rate": 0.00014585858585858586,
"loss": 1.0161,
"step": 139
},
{
"epoch": 0.005853882901435246,
"grad_norm": 0.2547732889652252,
"learning_rate": 0.00014545454545454546,
"loss": 1.1966,
"step": 140
},
{
"epoch": 0.005895696350731213,
"grad_norm": 0.23530864715576172,
"learning_rate": 0.00014505050505050505,
"loss": 0.7928,
"step": 141
},
{
"epoch": 0.005937509800027179,
"grad_norm": 0.23042874038219452,
"learning_rate": 0.00014464646464646465,
"loss": 0.867,
"step": 142
},
{
"epoch": 0.0059793232493231445,
"grad_norm": 0.248691588640213,
"learning_rate": 0.00014424242424242425,
"loss": 1.0603,
"step": 143
},
{
"epoch": 0.006021136698619111,
"grad_norm": 0.2555006742477417,
"learning_rate": 0.00014383838383838385,
"loss": 0.8947,
"step": 144
},
{
"epoch": 0.006062950147915077,
"grad_norm": 0.23735029995441437,
"learning_rate": 0.00014343434343434342,
"loss": 1.0781,
"step": 145
},
{
"epoch": 0.006104763597211043,
"grad_norm": 0.24833717942237854,
"learning_rate": 0.00014303030303030304,
"loss": 1.0187,
"step": 146
},
{
"epoch": 0.006146577046507009,
"grad_norm": 0.24587538838386536,
"learning_rate": 0.00014262626262626264,
"loss": 1.0539,
"step": 147
},
{
"epoch": 0.006188390495802975,
"grad_norm": 0.3016100227832794,
"learning_rate": 0.00014222222222222224,
"loss": 1.0549,
"step": 148
},
{
"epoch": 0.006230203945098941,
"grad_norm": 0.2518560588359833,
"learning_rate": 0.00014181818181818184,
"loss": 0.8378,
"step": 149
},
{
"epoch": 0.006272017394394907,
"grad_norm": 0.2270629107952118,
"learning_rate": 0.0001414141414141414,
"loss": 0.9084,
"step": 150
},
{
"epoch": 0.0063138308436908736,
"grad_norm": 0.23446914553642273,
"learning_rate": 0.000141010101010101,
"loss": 0.8835,
"step": 151
},
{
"epoch": 0.006355644292986839,
"grad_norm": 0.2495182901620865,
"learning_rate": 0.0001406060606060606,
"loss": 0.9397,
"step": 152
},
{
"epoch": 0.006397457742282805,
"grad_norm": 0.23422032594680786,
"learning_rate": 0.0001402020202020202,
"loss": 0.8999,
"step": 153
},
{
"epoch": 0.006439271191578771,
"grad_norm": 0.24570149183273315,
"learning_rate": 0.0001397979797979798,
"loss": 0.8705,
"step": 154
},
{
"epoch": 0.006481084640874738,
"grad_norm": 0.24084314703941345,
"learning_rate": 0.0001393939393939394,
"loss": 1.0292,
"step": 155
},
{
"epoch": 0.006522898090170703,
"grad_norm": 0.24169977009296417,
"learning_rate": 0.000138989898989899,
"loss": 1.0477,
"step": 156
},
{
"epoch": 0.006564711539466669,
"grad_norm": 0.30937832593917847,
"learning_rate": 0.0001385858585858586,
"loss": 0.8633,
"step": 157
},
{
"epoch": 0.006606524988762636,
"grad_norm": 0.2462792694568634,
"learning_rate": 0.0001381818181818182,
"loss": 0.9523,
"step": 158
},
{
"epoch": 0.006648338438058602,
"grad_norm": 0.24839982390403748,
"learning_rate": 0.0001377777777777778,
"loss": 0.8883,
"step": 159
},
{
"epoch": 0.0066901518873545675,
"grad_norm": 0.26970499753952026,
"learning_rate": 0.0001373737373737374,
"loss": 0.977,
"step": 160
},
{
"epoch": 0.006731965336650533,
"grad_norm": 0.23205144703388214,
"learning_rate": 0.00013696969696969696,
"loss": 0.8326,
"step": 161
},
{
"epoch": 0.0067737787859465,
"grad_norm": 0.22048699855804443,
"learning_rate": 0.00013656565656565656,
"loss": 0.9275,
"step": 162
},
{
"epoch": 0.006815592235242466,
"grad_norm": 0.2242291122674942,
"learning_rate": 0.00013616161616161618,
"loss": 1.0271,
"step": 163
},
{
"epoch": 0.006857405684538432,
"grad_norm": 0.23565801978111267,
"learning_rate": 0.00013575757575757578,
"loss": 0.9698,
"step": 164
},
{
"epoch": 0.006899219133834398,
"grad_norm": 0.2281644642353058,
"learning_rate": 0.00013535353535353538,
"loss": 0.9465,
"step": 165
},
{
"epoch": 0.006941032583130364,
"grad_norm": 0.2199249565601349,
"learning_rate": 0.00013494949494949495,
"loss": 0.8248,
"step": 166
},
{
"epoch": 0.00698284603242633,
"grad_norm": 0.24014709889888763,
"learning_rate": 0.00013454545454545455,
"loss": 0.8373,
"step": 167
},
{
"epoch": 0.007024659481722296,
"grad_norm": 0.21667098999023438,
"learning_rate": 0.00013414141414141414,
"loss": 0.8571,
"step": 168
},
{
"epoch": 0.007066472931018262,
"grad_norm": 0.24447870254516602,
"learning_rate": 0.00013373737373737374,
"loss": 0.8982,
"step": 169
},
{
"epoch": 0.007108286380314228,
"grad_norm": 0.23860566318035126,
"learning_rate": 0.00013333333333333334,
"loss": 0.8526,
"step": 170
},
{
"epoch": 0.007150099829610194,
"grad_norm": 0.24474593997001648,
"learning_rate": 0.00013292929292929294,
"loss": 1.0394,
"step": 171
},
{
"epoch": 0.00719191327890616,
"grad_norm": 0.2439136952161789,
"learning_rate": 0.00013252525252525254,
"loss": 1.0494,
"step": 172
},
{
"epoch": 0.007233726728202126,
"grad_norm": 0.297108918428421,
"learning_rate": 0.00013212121212121213,
"loss": 0.9123,
"step": 173
},
{
"epoch": 0.007275540177498092,
"grad_norm": 0.27741479873657227,
"learning_rate": 0.00013171717171717173,
"loss": 0.8491,
"step": 174
},
{
"epoch": 0.007317353626794058,
"grad_norm": 0.2641980051994324,
"learning_rate": 0.00013131313131313133,
"loss": 0.979,
"step": 175
},
{
"epoch": 0.007359167076090025,
"grad_norm": 0.2425202876329422,
"learning_rate": 0.00013090909090909093,
"loss": 0.9736,
"step": 176
},
{
"epoch": 0.0074009805253859905,
"grad_norm": 0.23964577913284302,
"learning_rate": 0.0001305050505050505,
"loss": 0.8817,
"step": 177
},
{
"epoch": 0.007442793974681956,
"grad_norm": 0.2516103982925415,
"learning_rate": 0.0001301010101010101,
"loss": 0.8659,
"step": 178
},
{
"epoch": 0.007484607423977922,
"grad_norm": 0.22955065965652466,
"learning_rate": 0.0001296969696969697,
"loss": 0.8342,
"step": 179
},
{
"epoch": 0.007526420873273889,
"grad_norm": 0.22402727603912354,
"learning_rate": 0.00012929292929292932,
"loss": 0.9327,
"step": 180
},
{
"epoch": 0.007568234322569855,
"grad_norm": 0.25410568714141846,
"learning_rate": 0.00012888888888888892,
"loss": 1.0478,
"step": 181
},
{
"epoch": 0.00761004777186582,
"grad_norm": 0.23707789182662964,
"learning_rate": 0.0001284848484848485,
"loss": 0.8722,
"step": 182
},
{
"epoch": 0.007651861221161787,
"grad_norm": 0.23372212052345276,
"learning_rate": 0.00012808080808080809,
"loss": 0.9666,
"step": 183
},
{
"epoch": 0.007693674670457753,
"grad_norm": 0.2657679319381714,
"learning_rate": 0.00012767676767676768,
"loss": 0.9168,
"step": 184
},
{
"epoch": 0.007735488119753719,
"grad_norm": 0.232729971408844,
"learning_rate": 0.00012727272727272728,
"loss": 0.9536,
"step": 185
},
{
"epoch": 0.0077773015690496845,
"grad_norm": 0.24871906638145447,
"learning_rate": 0.00012686868686868688,
"loss": 0.8709,
"step": 186
},
{
"epoch": 0.007819115018345651,
"grad_norm": 0.2266804724931717,
"learning_rate": 0.00012646464646464645,
"loss": 0.7653,
"step": 187
},
{
"epoch": 0.007860928467641616,
"grad_norm": 0.33394861221313477,
"learning_rate": 0.00012606060606060605,
"loss": 0.8725,
"step": 188
},
{
"epoch": 0.007902741916937583,
"grad_norm": 0.2425292581319809,
"learning_rate": 0.00012565656565656567,
"loss": 1.132,
"step": 189
},
{
"epoch": 0.00794455536623355,
"grad_norm": 0.23621080815792084,
"learning_rate": 0.00012525252525252527,
"loss": 0.8396,
"step": 190
},
{
"epoch": 0.007986368815529514,
"grad_norm": 0.24612073600292206,
"learning_rate": 0.00012484848484848487,
"loss": 0.972,
"step": 191
},
{
"epoch": 0.008028182264825481,
"grad_norm": 0.25840047001838684,
"learning_rate": 0.00012444444444444444,
"loss": 0.8906,
"step": 192
},
{
"epoch": 0.008069995714121448,
"grad_norm": 0.24181440472602844,
"learning_rate": 0.00012404040404040404,
"loss": 1.0273,
"step": 193
},
{
"epoch": 0.008111809163417413,
"grad_norm": 0.3590998351573944,
"learning_rate": 0.00012363636363636364,
"loss": 1.147,
"step": 194
},
{
"epoch": 0.00815362261271338,
"grad_norm": 0.2476431131362915,
"learning_rate": 0.00012323232323232323,
"loss": 0.891,
"step": 195
},
{
"epoch": 0.008195436062009346,
"grad_norm": 0.2410716712474823,
"learning_rate": 0.00012282828282828283,
"loss": 0.866,
"step": 196
},
{
"epoch": 0.008237249511305311,
"grad_norm": 0.2341095358133316,
"learning_rate": 0.00012242424242424243,
"loss": 0.759,
"step": 197
},
{
"epoch": 0.008279062960601278,
"grad_norm": 0.27347663044929504,
"learning_rate": 0.00012202020202020204,
"loss": 0.8231,
"step": 198
},
{
"epoch": 0.008320876409897244,
"grad_norm": 0.25028082728385925,
"learning_rate": 0.00012161616161616162,
"loss": 0.8105,
"step": 199
},
{
"epoch": 0.00836268985919321,
"grad_norm": 0.2492472380399704,
"learning_rate": 0.00012121212121212122,
"loss": 1.1087,
"step": 200
},
{
"epoch": 0.008404503308489176,
"grad_norm": 0.2771161198616028,
"learning_rate": 0.00012080808080808082,
"loss": 0.9027,
"step": 201
},
{
"epoch": 0.00844631675778514,
"grad_norm": 0.2624797821044922,
"learning_rate": 0.0001204040404040404,
"loss": 0.9253,
"step": 202
},
{
"epoch": 0.008488130207081107,
"grad_norm": 0.2410314977169037,
"learning_rate": 0.00012,
"loss": 1.0309,
"step": 203
},
{
"epoch": 0.008529943656377074,
"grad_norm": 0.24546155333518982,
"learning_rate": 0.0001195959595959596,
"loss": 0.8802,
"step": 204
},
{
"epoch": 0.008571757105673039,
"grad_norm": 0.24980226159095764,
"learning_rate": 0.00011919191919191919,
"loss": 0.9942,
"step": 205
},
{
"epoch": 0.008613570554969006,
"grad_norm": 0.2516646683216095,
"learning_rate": 0.0001187878787878788,
"loss": 0.8756,
"step": 206
},
{
"epoch": 0.008655384004264972,
"grad_norm": 0.25329509377479553,
"learning_rate": 0.0001183838383838384,
"loss": 0.8372,
"step": 207
},
{
"epoch": 0.008697197453560937,
"grad_norm": 0.25397980213165283,
"learning_rate": 0.00011797979797979799,
"loss": 1.0079,
"step": 208
},
{
"epoch": 0.008739010902856904,
"grad_norm": 0.24071095883846283,
"learning_rate": 0.00011757575757575758,
"loss": 1.0293,
"step": 209
},
{
"epoch": 0.00878082435215287,
"grad_norm": 0.389687180519104,
"learning_rate": 0.00011717171717171717,
"loss": 1.0059,
"step": 210
},
{
"epoch": 0.008822637801448836,
"grad_norm": 0.22953416407108307,
"learning_rate": 0.00011676767676767677,
"loss": 0.8209,
"step": 211
},
{
"epoch": 0.008864451250744802,
"grad_norm": 0.2266966998577118,
"learning_rate": 0.00011636363636363636,
"loss": 0.8586,
"step": 212
},
{
"epoch": 0.008906264700040769,
"grad_norm": 0.2559443414211273,
"learning_rate": 0.00011595959595959596,
"loss": 0.9447,
"step": 213
},
{
"epoch": 0.008948078149336734,
"grad_norm": 0.5596910119056702,
"learning_rate": 0.00011555555555555555,
"loss": 1.2531,
"step": 214
},
{
"epoch": 0.0089898915986327,
"grad_norm": 0.2317219227552414,
"learning_rate": 0.00011515151515151516,
"loss": 0.8568,
"step": 215
},
{
"epoch": 0.009031705047928665,
"grad_norm": 0.3438588082790375,
"learning_rate": 0.00011474747474747476,
"loss": 0.9468,
"step": 216
},
{
"epoch": 0.009073518497224632,
"grad_norm": 0.22755320370197296,
"learning_rate": 0.00011434343434343435,
"loss": 0.9324,
"step": 217
},
{
"epoch": 0.009115331946520599,
"grad_norm": 0.2534794807434082,
"learning_rate": 0.00011393939393939394,
"loss": 0.8957,
"step": 218
},
{
"epoch": 0.009157145395816564,
"grad_norm": 0.24701672792434692,
"learning_rate": 0.00011353535353535354,
"loss": 0.9667,
"step": 219
},
{
"epoch": 0.00919895884511253,
"grad_norm": 0.31640544533729553,
"learning_rate": 0.00011313131313131313,
"loss": 1.1742,
"step": 220
},
{
"epoch": 0.009240772294408497,
"grad_norm": 0.2641148865222931,
"learning_rate": 0.00011272727272727272,
"loss": 0.9829,
"step": 221
},
{
"epoch": 0.009282585743704462,
"grad_norm": 0.2502177357673645,
"learning_rate": 0.00011232323232323232,
"loss": 0.9928,
"step": 222
},
{
"epoch": 0.009324399193000429,
"grad_norm": 0.2609913647174835,
"learning_rate": 0.00011191919191919193,
"loss": 0.9089,
"step": 223
},
{
"epoch": 0.009366212642296395,
"grad_norm": 0.224997416138649,
"learning_rate": 0.00011151515151515153,
"loss": 0.765,
"step": 224
},
{
"epoch": 0.00940802609159236,
"grad_norm": 0.243513286113739,
"learning_rate": 0.00011111111111111112,
"loss": 0.9159,
"step": 225
},
{
"epoch": 0.009449839540888327,
"grad_norm": 0.22938188910484314,
"learning_rate": 0.00011070707070707071,
"loss": 0.9849,
"step": 226
},
{
"epoch": 0.009491652990184292,
"grad_norm": 0.229000061750412,
"learning_rate": 0.00011030303030303031,
"loss": 0.8655,
"step": 227
},
{
"epoch": 0.009533466439480259,
"grad_norm": 0.25807130336761475,
"learning_rate": 0.0001098989898989899,
"loss": 1.2809,
"step": 228
},
{
"epoch": 0.009575279888776225,
"grad_norm": 0.2382730096578598,
"learning_rate": 0.0001094949494949495,
"loss": 0.8781,
"step": 229
},
{
"epoch": 0.00961709333807219,
"grad_norm": 0.26861903071403503,
"learning_rate": 0.00010909090909090909,
"loss": 1.0295,
"step": 230
},
{
"epoch": 0.009658906787368157,
"grad_norm": 0.24532069265842438,
"learning_rate": 0.00010868686868686868,
"loss": 1.0323,
"step": 231
},
{
"epoch": 0.009700720236664124,
"grad_norm": 0.24853605031967163,
"learning_rate": 0.0001082828282828283,
"loss": 1.0719,
"step": 232
},
{
"epoch": 0.009742533685960088,
"grad_norm": 0.20883065462112427,
"learning_rate": 0.00010787878787878789,
"loss": 0.8916,
"step": 233
},
{
"epoch": 0.009784347135256055,
"grad_norm": 0.24370087683200836,
"learning_rate": 0.00010747474747474748,
"loss": 1.0241,
"step": 234
},
{
"epoch": 0.009826160584552022,
"grad_norm": 0.23309852182865143,
"learning_rate": 0.00010707070707070708,
"loss": 1.1354,
"step": 235
},
{
"epoch": 0.009867974033847987,
"grad_norm": 0.25597742199897766,
"learning_rate": 0.00010666666666666667,
"loss": 1.0021,
"step": 236
},
{
"epoch": 0.009909787483143953,
"grad_norm": 0.28911975026130676,
"learning_rate": 0.00010626262626262626,
"loss": 1.1514,
"step": 237
},
{
"epoch": 0.00995160093243992,
"grad_norm": 0.25332438945770264,
"learning_rate": 0.00010585858585858586,
"loss": 0.9619,
"step": 238
},
{
"epoch": 0.009993414381735885,
"grad_norm": 0.24337036907672882,
"learning_rate": 0.00010545454545454545,
"loss": 0.8732,
"step": 239
},
{
"epoch": 0.010035227831031852,
"grad_norm": 0.2372404932975769,
"learning_rate": 0.00010505050505050507,
"loss": 1.0061,
"step": 240
},
{
"epoch": 0.010077041280327817,
"grad_norm": 0.24123457074165344,
"learning_rate": 0.00010464646464646466,
"loss": 0.8788,
"step": 241
},
{
"epoch": 0.010118854729623783,
"grad_norm": 0.2372557669878006,
"learning_rate": 0.00010424242424242425,
"loss": 0.9747,
"step": 242
},
{
"epoch": 0.01016066817891975,
"grad_norm": 0.2557818591594696,
"learning_rate": 0.00010383838383838385,
"loss": 0.9637,
"step": 243
},
{
"epoch": 0.010202481628215715,
"grad_norm": 0.28526052832603455,
"learning_rate": 0.00010343434343434344,
"loss": 0.9005,
"step": 244
},
{
"epoch": 0.010244295077511682,
"grad_norm": 0.23231786489486694,
"learning_rate": 0.00010303030303030303,
"loss": 0.9581,
"step": 245
},
{
"epoch": 0.010286108526807648,
"grad_norm": 0.23651888966560364,
"learning_rate": 0.00010262626262626263,
"loss": 0.8459,
"step": 246
},
{
"epoch": 0.010327921976103613,
"grad_norm": 0.23777161538600922,
"learning_rate": 0.00010222222222222222,
"loss": 1.0758,
"step": 247
},
{
"epoch": 0.01036973542539958,
"grad_norm": 0.23822389543056488,
"learning_rate": 0.00010181818181818181,
"loss": 0.7813,
"step": 248
},
{
"epoch": 0.010411548874695547,
"grad_norm": 0.23809131979942322,
"learning_rate": 0.00010141414141414143,
"loss": 0.8993,
"step": 249
},
{
"epoch": 0.010453362323991511,
"grad_norm": 0.2509913742542267,
"learning_rate": 0.00010101010101010102,
"loss": 0.9896,
"step": 250
},
{
"epoch": 0.010495175773287478,
"grad_norm": 0.2638259828090668,
"learning_rate": 0.00010060606060606062,
"loss": 0.9422,
"step": 251
},
{
"epoch": 0.010536989222583445,
"grad_norm": 0.2861965000629425,
"learning_rate": 0.0001002020202020202,
"loss": 1.3454,
"step": 252
},
{
"epoch": 0.01057880267187941,
"grad_norm": 0.22580929100513458,
"learning_rate": 9.97979797979798e-05,
"loss": 0.8397,
"step": 253
},
{
"epoch": 0.010620616121175376,
"grad_norm": 0.28948256373405457,
"learning_rate": 9.939393939393939e-05,
"loss": 0.9765,
"step": 254
},
{
"epoch": 0.010662429570471341,
"grad_norm": 0.23788274824619293,
"learning_rate": 9.8989898989899e-05,
"loss": 0.8737,
"step": 255
},
{
"epoch": 0.010704243019767308,
"grad_norm": 0.22695161402225494,
"learning_rate": 9.85858585858586e-05,
"loss": 0.8152,
"step": 256
},
{
"epoch": 0.010746056469063275,
"grad_norm": 0.25142139196395874,
"learning_rate": 9.818181818181818e-05,
"loss": 1.0436,
"step": 257
},
{
"epoch": 0.01078786991835924,
"grad_norm": 0.27463334798812866,
"learning_rate": 9.777777777777778e-05,
"loss": 0.8589,
"step": 258
},
{
"epoch": 0.010829683367655206,
"grad_norm": 0.4538915753364563,
"learning_rate": 9.737373737373738e-05,
"loss": 0.737,
"step": 259
},
{
"epoch": 0.010871496816951173,
"grad_norm": 0.26711520552635193,
"learning_rate": 9.696969696969698e-05,
"loss": 0.818,
"step": 260
},
{
"epoch": 0.010913310266247138,
"grad_norm": 0.23684343695640564,
"learning_rate": 9.656565656565657e-05,
"loss": 0.946,
"step": 261
},
{
"epoch": 0.010955123715543105,
"grad_norm": 0.42562970519065857,
"learning_rate": 9.616161616161616e-05,
"loss": 1.2192,
"step": 262
},
{
"epoch": 0.010996937164839071,
"grad_norm": 0.27775582671165466,
"learning_rate": 9.575757575757576e-05,
"loss": 0.9631,
"step": 263
},
{
"epoch": 0.011038750614135036,
"grad_norm": 0.25754961371421814,
"learning_rate": 9.535353535353537e-05,
"loss": 0.9597,
"step": 264
},
{
"epoch": 0.011080564063431003,
"grad_norm": 0.23732782900333405,
"learning_rate": 9.494949494949495e-05,
"loss": 0.8945,
"step": 265
},
{
"epoch": 0.011122377512726968,
"grad_norm": 0.2573186755180359,
"learning_rate": 9.454545454545455e-05,
"loss": 1.1693,
"step": 266
},
{
"epoch": 0.011164190962022934,
"grad_norm": 0.251562237739563,
"learning_rate": 9.414141414141415e-05,
"loss": 0.8797,
"step": 267
},
{
"epoch": 0.011206004411318901,
"grad_norm": 0.2521072328090668,
"learning_rate": 9.373737373737375e-05,
"loss": 0.8824,
"step": 268
},
{
"epoch": 0.011247817860614866,
"grad_norm": 0.2662065625190735,
"learning_rate": 9.333333333333334e-05,
"loss": 1.1883,
"step": 269
},
{
"epoch": 0.011289631309910833,
"grad_norm": 0.30695080757141113,
"learning_rate": 9.292929292929293e-05,
"loss": 0.9089,
"step": 270
},
{
"epoch": 0.0113314447592068,
"grad_norm": 0.2501082122325897,
"learning_rate": 9.252525252525253e-05,
"loss": 0.8987,
"step": 271
},
{
"epoch": 0.011373258208502764,
"grad_norm": 0.31777051091194153,
"learning_rate": 9.212121212121214e-05,
"loss": 0.8668,
"step": 272
},
{
"epoch": 0.011415071657798731,
"grad_norm": 0.2766760289669037,
"learning_rate": 9.171717171717172e-05,
"loss": 0.8515,
"step": 273
},
{
"epoch": 0.011456885107094698,
"grad_norm": 0.2550426721572876,
"learning_rate": 9.131313131313132e-05,
"loss": 0.9963,
"step": 274
},
{
"epoch": 0.011498698556390663,
"grad_norm": 0.251042902469635,
"learning_rate": 9.090909090909092e-05,
"loss": 0.9898,
"step": 275
},
{
"epoch": 0.01154051200568663,
"grad_norm": 0.38854333758354187,
"learning_rate": 9.050505050505052e-05,
"loss": 1.2522,
"step": 276
},
{
"epoch": 0.011582325454982596,
"grad_norm": 0.2607441842556,
"learning_rate": 9.010101010101011e-05,
"loss": 0.9177,
"step": 277
},
{
"epoch": 0.011624138904278561,
"grad_norm": 0.25769656896591187,
"learning_rate": 8.96969696969697e-05,
"loss": 1.0015,
"step": 278
},
{
"epoch": 0.011665952353574528,
"grad_norm": 0.24730388820171356,
"learning_rate": 8.92929292929293e-05,
"loss": 0.9052,
"step": 279
},
{
"epoch": 0.011707765802870492,
"grad_norm": 0.6939902305603027,
"learning_rate": 8.888888888888889e-05,
"loss": 0.9031,
"step": 280
},
{
"epoch": 0.01174957925216646,
"grad_norm": 0.25303369760513306,
"learning_rate": 8.848484848484849e-05,
"loss": 1.0284,
"step": 281
},
{
"epoch": 0.011791392701462426,
"grad_norm": 0.2289949506521225,
"learning_rate": 8.808080808080809e-05,
"loss": 0.9984,
"step": 282
},
{
"epoch": 0.01183320615075839,
"grad_norm": 0.2644393742084503,
"learning_rate": 8.767676767676767e-05,
"loss": 0.916,
"step": 283
},
{
"epoch": 0.011875019600054357,
"grad_norm": 0.2542804181575775,
"learning_rate": 8.727272727272727e-05,
"loss": 0.9033,
"step": 284
},
{
"epoch": 0.011916833049350324,
"grad_norm": 0.24902841448783875,
"learning_rate": 8.686868686868688e-05,
"loss": 0.9286,
"step": 285
},
{
"epoch": 0.011958646498646289,
"grad_norm": 0.23429153859615326,
"learning_rate": 8.646464646464647e-05,
"loss": 1.0874,
"step": 286
},
{
"epoch": 0.012000459947942256,
"grad_norm": 0.25169599056243896,
"learning_rate": 8.606060606060606e-05,
"loss": 0.9954,
"step": 287
},
{
"epoch": 0.012042273397238222,
"grad_norm": 0.23120075464248657,
"learning_rate": 8.565656565656566e-05,
"loss": 1.1458,
"step": 288
},
{
"epoch": 0.012084086846534187,
"grad_norm": 0.22807276248931885,
"learning_rate": 8.525252525252526e-05,
"loss": 1.0239,
"step": 289
},
{
"epoch": 0.012125900295830154,
"grad_norm": 0.24436655640602112,
"learning_rate": 8.484848484848486e-05,
"loss": 0.9598,
"step": 290
},
{
"epoch": 0.01216771374512612,
"grad_norm": 0.23763546347618103,
"learning_rate": 8.444444444444444e-05,
"loss": 0.9101,
"step": 291
},
{
"epoch": 0.012209527194422086,
"grad_norm": 0.24896766245365143,
"learning_rate": 8.404040404040404e-05,
"loss": 0.8942,
"step": 292
},
{
"epoch": 0.012251340643718052,
"grad_norm": 0.24986594915390015,
"learning_rate": 8.363636363636364e-05,
"loss": 0.8077,
"step": 293
},
{
"epoch": 0.012293154093014017,
"grad_norm": 0.2502870261669159,
"learning_rate": 8.323232323232324e-05,
"loss": 1.1444,
"step": 294
},
{
"epoch": 0.012334967542309984,
"grad_norm": 0.24926161766052246,
"learning_rate": 8.282828282828283e-05,
"loss": 0.831,
"step": 295
},
{
"epoch": 0.01237678099160595,
"grad_norm": 0.2518724203109741,
"learning_rate": 8.242424242424243e-05,
"loss": 0.9086,
"step": 296
},
{
"epoch": 0.012418594440901915,
"grad_norm": 0.2385004758834839,
"learning_rate": 8.202020202020202e-05,
"loss": 0.9899,
"step": 297
},
{
"epoch": 0.012460407890197882,
"grad_norm": 0.25030574202537537,
"learning_rate": 8.161616161616163e-05,
"loss": 0.9781,
"step": 298
},
{
"epoch": 0.012502221339493849,
"grad_norm": 0.22869014739990234,
"learning_rate": 8.121212121212121e-05,
"loss": 1.0988,
"step": 299
},
{
"epoch": 0.012544034788789814,
"grad_norm": 0.24000000953674316,
"learning_rate": 8.080808080808081e-05,
"loss": 0.8357,
"step": 300
},
{
"epoch": 0.01258584823808578,
"grad_norm": 0.24710014462471008,
"learning_rate": 8.040404040404041e-05,
"loss": 1.0953,
"step": 301
},
{
"epoch": 0.012627661687381747,
"grad_norm": 0.22500193119049072,
"learning_rate": 8e-05,
"loss": 0.7748,
"step": 302
},
{
"epoch": 0.012669475136677712,
"grad_norm": 0.25450679659843445,
"learning_rate": 7.95959595959596e-05,
"loss": 0.8359,
"step": 303
},
{
"epoch": 0.012711288585973679,
"grad_norm": 0.22793394327163696,
"learning_rate": 7.919191919191919e-05,
"loss": 0.8044,
"step": 304
},
{
"epoch": 0.012753102035269644,
"grad_norm": 0.22946174442768097,
"learning_rate": 7.878787878787879e-05,
"loss": 0.9852,
"step": 305
},
{
"epoch": 0.01279491548456561,
"grad_norm": 0.2390022873878479,
"learning_rate": 7.83838383838384e-05,
"loss": 0.9619,
"step": 306
},
{
"epoch": 0.012836728933861577,
"grad_norm": 0.24073170125484467,
"learning_rate": 7.797979797979798e-05,
"loss": 0.8367,
"step": 307
},
{
"epoch": 0.012878542383157542,
"grad_norm": 0.39702296257019043,
"learning_rate": 7.757575757575758e-05,
"loss": 0.9108,
"step": 308
},
{
"epoch": 0.012920355832453509,
"grad_norm": 0.23761232197284698,
"learning_rate": 7.717171717171718e-05,
"loss": 0.8308,
"step": 309
},
{
"epoch": 0.012962169281749475,
"grad_norm": 0.2543574273586273,
"learning_rate": 7.676767676767676e-05,
"loss": 0.9373,
"step": 310
},
{
"epoch": 0.01300398273104544,
"grad_norm": 0.24255353212356567,
"learning_rate": 7.636363636363637e-05,
"loss": 0.9015,
"step": 311
},
{
"epoch": 0.013045796180341407,
"grad_norm": 0.2566438615322113,
"learning_rate": 7.595959595959596e-05,
"loss": 1.1357,
"step": 312
},
{
"epoch": 0.013087609629637374,
"grad_norm": 0.2688029110431671,
"learning_rate": 7.555555555555556e-05,
"loss": 0.8863,
"step": 313
},
{
"epoch": 0.013129423078933338,
"grad_norm": 0.23739837110042572,
"learning_rate": 7.515151515151515e-05,
"loss": 0.8883,
"step": 314
},
{
"epoch": 0.013171236528229305,
"grad_norm": 0.22725465893745422,
"learning_rate": 7.474747474747475e-05,
"loss": 0.8158,
"step": 315
},
{
"epoch": 0.013213049977525272,
"grad_norm": 0.24793623387813568,
"learning_rate": 7.434343434343435e-05,
"loss": 0.9712,
"step": 316
},
{
"epoch": 0.013254863426821237,
"grad_norm": 0.23433813452720642,
"learning_rate": 7.393939393939395e-05,
"loss": 0.8579,
"step": 317
},
{
"epoch": 0.013296676876117203,
"grad_norm": 0.25578951835632324,
"learning_rate": 7.353535353535353e-05,
"loss": 0.8847,
"step": 318
},
{
"epoch": 0.013338490325413168,
"grad_norm": 0.2506163716316223,
"learning_rate": 7.313131313131314e-05,
"loss": 0.9251,
"step": 319
},
{
"epoch": 0.013380303774709135,
"grad_norm": 0.25213074684143066,
"learning_rate": 7.272727272727273e-05,
"loss": 1.1687,
"step": 320
},
{
"epoch": 0.013422117224005102,
"grad_norm": 0.3329940140247345,
"learning_rate": 7.232323232323233e-05,
"loss": 0.8728,
"step": 321
},
{
"epoch": 0.013463930673301067,
"grad_norm": 0.23659250140190125,
"learning_rate": 7.191919191919192e-05,
"loss": 1.0519,
"step": 322
},
{
"epoch": 0.013505744122597033,
"grad_norm": 0.2429414689540863,
"learning_rate": 7.151515151515152e-05,
"loss": 0.8684,
"step": 323
},
{
"epoch": 0.013547557571893,
"grad_norm": 0.24055901169776917,
"learning_rate": 7.111111111111112e-05,
"loss": 0.8534,
"step": 324
},
{
"epoch": 0.013589371021188965,
"grad_norm": 0.22518864274024963,
"learning_rate": 7.07070707070707e-05,
"loss": 0.8576,
"step": 325
},
{
"epoch": 0.013631184470484932,
"grad_norm": 0.241339311003685,
"learning_rate": 7.03030303030303e-05,
"loss": 1.2583,
"step": 326
},
{
"epoch": 0.013672997919780898,
"grad_norm": 0.23949019610881805,
"learning_rate": 6.98989898989899e-05,
"loss": 0.8277,
"step": 327
},
{
"epoch": 0.013714811369076863,
"grad_norm": 0.2371453493833542,
"learning_rate": 6.94949494949495e-05,
"loss": 0.9066,
"step": 328
},
{
"epoch": 0.01375662481837283,
"grad_norm": 0.24365493655204773,
"learning_rate": 6.90909090909091e-05,
"loss": 0.9856,
"step": 329
},
{
"epoch": 0.013798438267668797,
"grad_norm": 0.24753199517726898,
"learning_rate": 6.86868686868687e-05,
"loss": 0.929,
"step": 330
},
{
"epoch": 0.013840251716964761,
"grad_norm": 0.23612220585346222,
"learning_rate": 6.828282828282828e-05,
"loss": 0.901,
"step": 331
},
{
"epoch": 0.013882065166260728,
"grad_norm": 0.2376374900341034,
"learning_rate": 6.787878787878789e-05,
"loss": 0.8999,
"step": 332
},
{
"epoch": 0.013923878615556693,
"grad_norm": 0.24799491465091705,
"learning_rate": 6.747474747474747e-05,
"loss": 1.0791,
"step": 333
},
{
"epoch": 0.01396569206485266,
"grad_norm": 0.25469231605529785,
"learning_rate": 6.707070707070707e-05,
"loss": 1.2027,
"step": 334
},
{
"epoch": 0.014007505514148626,
"grad_norm": 0.25871676206588745,
"learning_rate": 6.666666666666667e-05,
"loss": 0.9871,
"step": 335
},
{
"epoch": 0.014049318963444591,
"grad_norm": 0.34988638758659363,
"learning_rate": 6.626262626262627e-05,
"loss": 1.1281,
"step": 336
},
{
"epoch": 0.014091132412740558,
"grad_norm": 0.25281211733818054,
"learning_rate": 6.585858585858587e-05,
"loss": 0.9106,
"step": 337
},
{
"epoch": 0.014132945862036525,
"grad_norm": 0.24838191270828247,
"learning_rate": 6.545454545454546e-05,
"loss": 0.7975,
"step": 338
},
{
"epoch": 0.01417475931133249,
"grad_norm": 0.2549956142902374,
"learning_rate": 6.505050505050505e-05,
"loss": 0.9658,
"step": 339
},
{
"epoch": 0.014216572760628456,
"grad_norm": 0.2315448373556137,
"learning_rate": 6.464646464646466e-05,
"loss": 0.7873,
"step": 340
},
{
"epoch": 0.014258386209924423,
"grad_norm": 0.2548529803752899,
"learning_rate": 6.424242424242424e-05,
"loss": 0.8015,
"step": 341
},
{
"epoch": 0.014300199659220388,
"grad_norm": 0.30752018094062805,
"learning_rate": 6.383838383838384e-05,
"loss": 1.1019,
"step": 342
},
{
"epoch": 0.014342013108516355,
"grad_norm": 0.24216066300868988,
"learning_rate": 6.343434343434344e-05,
"loss": 0.9709,
"step": 343
},
{
"epoch": 0.01438382655781232,
"grad_norm": 0.2470254749059677,
"learning_rate": 6.303030303030302e-05,
"loss": 0.9155,
"step": 344
},
{
"epoch": 0.014425640007108286,
"grad_norm": 0.24255427718162537,
"learning_rate": 6.262626262626264e-05,
"loss": 0.8818,
"step": 345
},
{
"epoch": 0.014467453456404253,
"grad_norm": 0.2458990067243576,
"learning_rate": 6.222222222222222e-05,
"loss": 0.8466,
"step": 346
},
{
"epoch": 0.014509266905700218,
"grad_norm": 0.24900957942008972,
"learning_rate": 6.181818181818182e-05,
"loss": 0.9408,
"step": 347
},
{
"epoch": 0.014551080354996184,
"grad_norm": 0.21387742459774017,
"learning_rate": 6.141414141414142e-05,
"loss": 0.9453,
"step": 348
},
{
"epoch": 0.014592893804292151,
"grad_norm": 0.2548189163208008,
"learning_rate": 6.101010101010102e-05,
"loss": 0.8626,
"step": 349
},
{
"epoch": 0.014634707253588116,
"grad_norm": 0.24375221133232117,
"learning_rate": 6.060606060606061e-05,
"loss": 1.155,
"step": 350
},
{
"epoch": 0.014676520702884083,
"grad_norm": 0.2517179548740387,
"learning_rate": 6.02020202020202e-05,
"loss": 1.1613,
"step": 351
},
{
"epoch": 0.01471833415218005,
"grad_norm": 0.24023565649986267,
"learning_rate": 5.97979797979798e-05,
"loss": 0.8669,
"step": 352
},
{
"epoch": 0.014760147601476014,
"grad_norm": 0.24070222675800323,
"learning_rate": 5.93939393939394e-05,
"loss": 0.8611,
"step": 353
},
{
"epoch": 0.014801961050771981,
"grad_norm": 0.2375120222568512,
"learning_rate": 5.8989898989898996e-05,
"loss": 0.7702,
"step": 354
},
{
"epoch": 0.014843774500067948,
"grad_norm": 0.3407435417175293,
"learning_rate": 5.858585858585859e-05,
"loss": 1.177,
"step": 355
},
{
"epoch": 0.014885587949363913,
"grad_norm": 0.23410116136074066,
"learning_rate": 5.818181818181818e-05,
"loss": 0.7849,
"step": 356
},
{
"epoch": 0.01492740139865988,
"grad_norm": 0.2335258275270462,
"learning_rate": 5.7777777777777776e-05,
"loss": 1.1725,
"step": 357
},
{
"epoch": 0.014969214847955844,
"grad_norm": 0.26608511805534363,
"learning_rate": 5.737373737373738e-05,
"loss": 1.0011,
"step": 358
},
{
"epoch": 0.015011028297251811,
"grad_norm": 0.24040436744689941,
"learning_rate": 5.696969696969697e-05,
"loss": 1.0564,
"step": 359
},
{
"epoch": 0.015052841746547778,
"grad_norm": 0.24156856536865234,
"learning_rate": 5.6565656565656563e-05,
"loss": 0.8725,
"step": 360
},
{
"epoch": 0.015094655195843742,
"grad_norm": 0.24838483333587646,
"learning_rate": 5.616161616161616e-05,
"loss": 0.9089,
"step": 361
},
{
"epoch": 0.01513646864513971,
"grad_norm": 0.2677476704120636,
"learning_rate": 5.5757575757575766e-05,
"loss": 1.0275,
"step": 362
},
{
"epoch": 0.015178282094435676,
"grad_norm": 0.2671316862106323,
"learning_rate": 5.535353535353536e-05,
"loss": 0.9059,
"step": 363
},
{
"epoch": 0.01522009554373164,
"grad_norm": 0.24810616672039032,
"learning_rate": 5.494949494949495e-05,
"loss": 1.3121,
"step": 364
},
{
"epoch": 0.015261908993027607,
"grad_norm": 0.28861334919929504,
"learning_rate": 5.4545454545454546e-05,
"loss": 0.9855,
"step": 365
},
{
"epoch": 0.015303722442323574,
"grad_norm": 0.25211018323898315,
"learning_rate": 5.414141414141415e-05,
"loss": 1.1369,
"step": 366
},
{
"epoch": 0.015345535891619539,
"grad_norm": 1.231808066368103,
"learning_rate": 5.373737373737374e-05,
"loss": 0.8406,
"step": 367
},
{
"epoch": 0.015387349340915506,
"grad_norm": 0.5400699973106384,
"learning_rate": 5.333333333333333e-05,
"loss": 0.848,
"step": 368
},
{
"epoch": 0.015429162790211472,
"grad_norm": 0.29320618510246277,
"learning_rate": 5.292929292929293e-05,
"loss": 0.891,
"step": 369
},
{
"epoch": 0.015470976239507437,
"grad_norm": 0.24232591688632965,
"learning_rate": 5.2525252525252536e-05,
"loss": 0.8838,
"step": 370
},
{
"epoch": 0.015512789688803404,
"grad_norm": 0.25413283705711365,
"learning_rate": 5.212121212121213e-05,
"loss": 1.1661,
"step": 371
},
{
"epoch": 0.015554603138099369,
"grad_norm": 0.246323823928833,
"learning_rate": 5.171717171717172e-05,
"loss": 1.2153,
"step": 372
},
{
"epoch": 0.015596416587395336,
"grad_norm": 0.25972479581832886,
"learning_rate": 5.1313131313131316e-05,
"loss": 0.9155,
"step": 373
},
{
"epoch": 0.015638230036691302,
"grad_norm": 0.24290485680103302,
"learning_rate": 5.090909090909091e-05,
"loss": 0.9279,
"step": 374
},
{
"epoch": 0.01568004348598727,
"grad_norm": 0.27079811692237854,
"learning_rate": 5.050505050505051e-05,
"loss": 0.8916,
"step": 375
},
{
"epoch": 0.015721856935283232,
"grad_norm": 0.24520574510097504,
"learning_rate": 5.01010101010101e-05,
"loss": 0.9716,
"step": 376
},
{
"epoch": 0.0157636703845792,
"grad_norm": 0.26845109462738037,
"learning_rate": 4.9696969696969694e-05,
"loss": 1.1215,
"step": 377
},
{
"epoch": 0.015805483833875165,
"grad_norm": 0.2476051151752472,
"learning_rate": 4.92929292929293e-05,
"loss": 1.0693,
"step": 378
},
{
"epoch": 0.015847297283171132,
"grad_norm": 0.24062906205654144,
"learning_rate": 4.888888888888889e-05,
"loss": 1.0149,
"step": 379
},
{
"epoch": 0.0158891107324671,
"grad_norm": 0.25070905685424805,
"learning_rate": 4.848484848484849e-05,
"loss": 0.9091,
"step": 380
},
{
"epoch": 0.015930924181763065,
"grad_norm": 0.24878452718257904,
"learning_rate": 4.808080808080808e-05,
"loss": 0.8852,
"step": 381
},
{
"epoch": 0.01597273763105903,
"grad_norm": 0.30614715814590454,
"learning_rate": 4.7676767676767684e-05,
"loss": 1.1909,
"step": 382
},
{
"epoch": 0.016014551080354995,
"grad_norm": 0.2441512942314148,
"learning_rate": 4.7272727272727275e-05,
"loss": 0.8701,
"step": 383
},
{
"epoch": 0.016056364529650962,
"grad_norm": 0.24012567102909088,
"learning_rate": 4.686868686868687e-05,
"loss": 1.0274,
"step": 384
},
{
"epoch": 0.01609817797894693,
"grad_norm": 0.2303936928510666,
"learning_rate": 4.6464646464646464e-05,
"loss": 0.7405,
"step": 385
},
{
"epoch": 0.016139991428242895,
"grad_norm": 0.3310977518558502,
"learning_rate": 4.606060606060607e-05,
"loss": 1.0769,
"step": 386
},
{
"epoch": 0.016181804877538862,
"grad_norm": 0.2602216899394989,
"learning_rate": 4.565656565656566e-05,
"loss": 0.9418,
"step": 387
},
{
"epoch": 0.016223618326834825,
"grad_norm": 0.2928454279899597,
"learning_rate": 4.525252525252526e-05,
"loss": 0.9771,
"step": 388
},
{
"epoch": 0.016265431776130792,
"grad_norm": 0.31059637665748596,
"learning_rate": 4.484848484848485e-05,
"loss": 0.9948,
"step": 389
},
{
"epoch": 0.01630724522542676,
"grad_norm": 0.2816385328769684,
"learning_rate": 4.4444444444444447e-05,
"loss": 1.0794,
"step": 390
},
{
"epoch": 0.016349058674722725,
"grad_norm": 0.24497491121292114,
"learning_rate": 4.4040404040404044e-05,
"loss": 0.8346,
"step": 391
},
{
"epoch": 0.016390872124018692,
"grad_norm": 0.24517390131950378,
"learning_rate": 4.3636363636363636e-05,
"loss": 0.9661,
"step": 392
},
{
"epoch": 0.016432685573314655,
"grad_norm": 0.2598320543766022,
"learning_rate": 4.3232323232323234e-05,
"loss": 0.8785,
"step": 393
},
{
"epoch": 0.016474499022610622,
"grad_norm": 0.2503718137741089,
"learning_rate": 4.282828282828283e-05,
"loss": 0.9695,
"step": 394
},
{
"epoch": 0.01651631247190659,
"grad_norm": 0.26278936862945557,
"learning_rate": 4.242424242424243e-05,
"loss": 0.8845,
"step": 395
},
{
"epoch": 0.016558125921202555,
"grad_norm": 0.2547891139984131,
"learning_rate": 4.202020202020202e-05,
"loss": 0.9383,
"step": 396
},
{
"epoch": 0.016599939370498522,
"grad_norm": 0.2657267153263092,
"learning_rate": 4.161616161616162e-05,
"loss": 0.9293,
"step": 397
},
{
"epoch": 0.01664175281979449,
"grad_norm": 0.6090709567070007,
"learning_rate": 4.1212121212121216e-05,
"loss": 0.9352,
"step": 398
},
{
"epoch": 0.01668356626909045,
"grad_norm": 0.24619267880916595,
"learning_rate": 4.0808080808080814e-05,
"loss": 1.1351,
"step": 399
},
{
"epoch": 0.01672537971838642,
"grad_norm": 0.2917110025882721,
"learning_rate": 4.0404040404040405e-05,
"loss": 1.9349,
"step": 400
},
{
"epoch": 0.016767193167682385,
"grad_norm": 0.2464229017496109,
"learning_rate": 4e-05,
"loss": 0.8333,
"step": 401
},
{
"epoch": 0.01680900661697835,
"grad_norm": 0.257079154253006,
"learning_rate": 3.9595959595959594e-05,
"loss": 0.8843,
"step": 402
},
{
"epoch": 0.01685082006627432,
"grad_norm": 0.3248063325881958,
"learning_rate": 3.91919191919192e-05,
"loss": 0.9127,
"step": 403
},
{
"epoch": 0.01689263351557028,
"grad_norm": 0.2488846629858017,
"learning_rate": 3.878787878787879e-05,
"loss": 0.9772,
"step": 404
},
{
"epoch": 0.016934446964866248,
"grad_norm": 0.26537787914276123,
"learning_rate": 3.838383838383838e-05,
"loss": 1.088,
"step": 405
},
{
"epoch": 0.016976260414162215,
"grad_norm": 0.25171270966529846,
"learning_rate": 3.797979797979798e-05,
"loss": 0.9058,
"step": 406
},
{
"epoch": 0.01701807386345818,
"grad_norm": 0.27759164571762085,
"learning_rate": 3.757575757575758e-05,
"loss": 1.0035,
"step": 407
},
{
"epoch": 0.017059887312754148,
"grad_norm": 0.25512200593948364,
"learning_rate": 3.7171717171717175e-05,
"loss": 0.8536,
"step": 408
},
{
"epoch": 0.017101700762050115,
"grad_norm": 0.2517940104007721,
"learning_rate": 3.6767676767676766e-05,
"loss": 1.1496,
"step": 409
},
{
"epoch": 0.017143514211346078,
"grad_norm": 0.23167800903320312,
"learning_rate": 3.6363636363636364e-05,
"loss": 0.8153,
"step": 410
},
{
"epoch": 0.017185327660642045,
"grad_norm": 0.24471765756607056,
"learning_rate": 3.595959595959596e-05,
"loss": 0.9054,
"step": 411
},
{
"epoch": 0.01722714110993801,
"grad_norm": 0.24124263226985931,
"learning_rate": 3.555555555555556e-05,
"loss": 0.85,
"step": 412
},
{
"epoch": 0.017268954559233978,
"grad_norm": 0.24065597355365753,
"learning_rate": 3.515151515151515e-05,
"loss": 0.9375,
"step": 413
},
{
"epoch": 0.017310768008529945,
"grad_norm": 0.24606922268867493,
"learning_rate": 3.474747474747475e-05,
"loss": 0.8626,
"step": 414
},
{
"epoch": 0.017352581457825908,
"grad_norm": 0.24860136210918427,
"learning_rate": 3.434343434343435e-05,
"loss": 1.054,
"step": 415
},
{
"epoch": 0.017394394907121875,
"grad_norm": 0.23613376915454865,
"learning_rate": 3.3939393939393945e-05,
"loss": 0.847,
"step": 416
},
{
"epoch": 0.01743620835641784,
"grad_norm": 0.2380017638206482,
"learning_rate": 3.3535353535353536e-05,
"loss": 1.0066,
"step": 417
},
{
"epoch": 0.017478021805713808,
"grad_norm": 0.2586548626422882,
"learning_rate": 3.3131313131313134e-05,
"loss": 1.0471,
"step": 418
},
{
"epoch": 0.017519835255009775,
"grad_norm": 0.2610139548778534,
"learning_rate": 3.272727272727273e-05,
"loss": 0.8697,
"step": 419
},
{
"epoch": 0.01756164870430574,
"grad_norm": 0.24659010767936707,
"learning_rate": 3.232323232323233e-05,
"loss": 0.9905,
"step": 420
},
{
"epoch": 0.017603462153601705,
"grad_norm": 0.25451886653900146,
"learning_rate": 3.191919191919192e-05,
"loss": 0.9753,
"step": 421
},
{
"epoch": 0.01764527560289767,
"grad_norm": 0.2710777223110199,
"learning_rate": 3.151515151515151e-05,
"loss": 0.9521,
"step": 422
},
{
"epoch": 0.017687089052193638,
"grad_norm": 0.26839956641197205,
"learning_rate": 3.111111111111111e-05,
"loss": 0.9345,
"step": 423
},
{
"epoch": 0.017728902501489605,
"grad_norm": 0.24387024343013763,
"learning_rate": 3.070707070707071e-05,
"loss": 0.9738,
"step": 424
},
{
"epoch": 0.01777071595078557,
"grad_norm": 0.2604621350765228,
"learning_rate": 3.0303030303030306e-05,
"loss": 0.9345,
"step": 425
},
{
"epoch": 0.017812529400081538,
"grad_norm": 0.2625117599964142,
"learning_rate": 2.98989898989899e-05,
"loss": 0.8845,
"step": 426
},
{
"epoch": 0.0178543428493775,
"grad_norm": 0.2582264542579651,
"learning_rate": 2.9494949494949498e-05,
"loss": 0.9636,
"step": 427
},
{
"epoch": 0.017896156298673468,
"grad_norm": 0.23798999190330505,
"learning_rate": 2.909090909090909e-05,
"loss": 0.7743,
"step": 428
},
{
"epoch": 0.017937969747969434,
"grad_norm": 0.25542187690734863,
"learning_rate": 2.868686868686869e-05,
"loss": 1.0229,
"step": 429
},
{
"epoch": 0.0179797831972654,
"grad_norm": 0.23531381785869598,
"learning_rate": 2.8282828282828282e-05,
"loss": 1.0469,
"step": 430
},
{
"epoch": 0.018021596646561368,
"grad_norm": 0.2434222549200058,
"learning_rate": 2.7878787878787883e-05,
"loss": 0.8244,
"step": 431
},
{
"epoch": 0.01806341009585733,
"grad_norm": 0.2635379135608673,
"learning_rate": 2.7474747474747474e-05,
"loss": 0.9535,
"step": 432
},
{
"epoch": 0.018105223545153298,
"grad_norm": 0.25633907318115234,
"learning_rate": 2.7070707070707075e-05,
"loss": 0.8982,
"step": 433
},
{
"epoch": 0.018147036994449264,
"grad_norm": 0.25313177704811096,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.8999,
"step": 434
},
{
"epoch": 0.01818885044374523,
"grad_norm": 0.2359696477651596,
"learning_rate": 2.6262626262626268e-05,
"loss": 0.8759,
"step": 435
},
{
"epoch": 0.018230663893041198,
"grad_norm": 0.29557114839553833,
"learning_rate": 2.585858585858586e-05,
"loss": 0.9535,
"step": 436
},
{
"epoch": 0.018272477342337164,
"grad_norm": 0.24904978275299072,
"learning_rate": 2.5454545454545454e-05,
"loss": 0.8796,
"step": 437
},
{
"epoch": 0.018314290791633128,
"grad_norm": 0.271016001701355,
"learning_rate": 2.505050505050505e-05,
"loss": 1.0809,
"step": 438
},
{
"epoch": 0.018356104240929094,
"grad_norm": 0.2593722641468048,
"learning_rate": 2.464646464646465e-05,
"loss": 0.9418,
"step": 439
},
{
"epoch": 0.01839791769022506,
"grad_norm": 0.2632979452610016,
"learning_rate": 2.4242424242424244e-05,
"loss": 1.0064,
"step": 440
},
{
"epoch": 0.018439731139521028,
"grad_norm": 0.26291918754577637,
"learning_rate": 2.3838383838383842e-05,
"loss": 1.3494,
"step": 441
},
{
"epoch": 0.018481544588816994,
"grad_norm": 0.28495603799819946,
"learning_rate": 2.3434343434343436e-05,
"loss": 1.064,
"step": 442
},
{
"epoch": 0.018523358038112957,
"grad_norm": 0.25690269470214844,
"learning_rate": 2.3030303030303034e-05,
"loss": 1.1179,
"step": 443
},
{
"epoch": 0.018565171487408924,
"grad_norm": 0.24951989948749542,
"learning_rate": 2.262626262626263e-05,
"loss": 1.0345,
"step": 444
},
{
"epoch": 0.01860698493670489,
"grad_norm": 0.2684321701526642,
"learning_rate": 2.2222222222222223e-05,
"loss": 0.8994,
"step": 445
},
{
"epoch": 0.018648798386000857,
"grad_norm": 0.36709463596343994,
"learning_rate": 2.1818181818181818e-05,
"loss": 0.9514,
"step": 446
},
{
"epoch": 0.018690611835296824,
"grad_norm": 0.23593302071094513,
"learning_rate": 2.1414141414141416e-05,
"loss": 0.822,
"step": 447
},
{
"epoch": 0.01873242528459279,
"grad_norm": 0.23129960894584656,
"learning_rate": 2.101010101010101e-05,
"loss": 0.9689,
"step": 448
},
{
"epoch": 0.018774238733888754,
"grad_norm": 0.2726437449455261,
"learning_rate": 2.0606060606060608e-05,
"loss": 0.9463,
"step": 449
},
{
"epoch": 0.01881605218318472,
"grad_norm": 0.2599771320819855,
"learning_rate": 2.0202020202020203e-05,
"loss": 0.9269,
"step": 450
},
{
"epoch": 0.018857865632480687,
"grad_norm": 0.23631487786769867,
"learning_rate": 1.9797979797979797e-05,
"loss": 0.8803,
"step": 451
},
{
"epoch": 0.018899679081776654,
"grad_norm": 0.25362351536750793,
"learning_rate": 1.9393939393939395e-05,
"loss": 0.8708,
"step": 452
},
{
"epoch": 0.01894149253107262,
"grad_norm": 0.251736044883728,
"learning_rate": 1.898989898989899e-05,
"loss": 0.8972,
"step": 453
},
{
"epoch": 0.018983305980368584,
"grad_norm": 0.26444554328918457,
"learning_rate": 1.8585858585858588e-05,
"loss": 0.8354,
"step": 454
},
{
"epoch": 0.01902511942966455,
"grad_norm": 0.2520543336868286,
"learning_rate": 1.8181818181818182e-05,
"loss": 0.8819,
"step": 455
},
{
"epoch": 0.019066932878960517,
"grad_norm": 0.23527085781097412,
"learning_rate": 1.777777777777778e-05,
"loss": 0.8326,
"step": 456
},
{
"epoch": 0.019108746328256484,
"grad_norm": 0.2357388734817505,
"learning_rate": 1.7373737373737375e-05,
"loss": 0.903,
"step": 457
},
{
"epoch": 0.01915055977755245,
"grad_norm": 0.25031155347824097,
"learning_rate": 1.6969696969696972e-05,
"loss": 0.9328,
"step": 458
},
{
"epoch": 0.019192373226848417,
"grad_norm": 0.26259344816207886,
"learning_rate": 1.6565656565656567e-05,
"loss": 0.9971,
"step": 459
},
{
"epoch": 0.01923418667614438,
"grad_norm": 0.24670587480068207,
"learning_rate": 1.6161616161616165e-05,
"loss": 0.7794,
"step": 460
},
{
"epoch": 0.019276000125440347,
"grad_norm": 0.2741599678993225,
"learning_rate": 1.5757575757575756e-05,
"loss": 1.0328,
"step": 461
},
{
"epoch": 0.019317813574736314,
"grad_norm": 0.24906563758850098,
"learning_rate": 1.5353535353535354e-05,
"loss": 0.8901,
"step": 462
},
{
"epoch": 0.01935962702403228,
"grad_norm": 0.2557568848133087,
"learning_rate": 1.494949494949495e-05,
"loss": 0.7847,
"step": 463
},
{
"epoch": 0.019401440473328247,
"grad_norm": 0.26695290207862854,
"learning_rate": 1.4545454545454545e-05,
"loss": 0.9652,
"step": 464
},
{
"epoch": 0.019443253922624214,
"grad_norm": 0.3295172154903412,
"learning_rate": 1.4141414141414141e-05,
"loss": 0.8916,
"step": 465
},
{
"epoch": 0.019485067371920177,
"grad_norm": 0.252997487783432,
"learning_rate": 1.3737373737373737e-05,
"loss": 1.1284,
"step": 466
},
{
"epoch": 0.019526880821216144,
"grad_norm": 0.5548291802406311,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.1207,
"step": 467
},
{
"epoch": 0.01956869427051211,
"grad_norm": 0.24896806478500366,
"learning_rate": 1.292929292929293e-05,
"loss": 0.9405,
"step": 468
},
{
"epoch": 0.019610507719808077,
"grad_norm": 0.2600722312927246,
"learning_rate": 1.2525252525252526e-05,
"loss": 1.0259,
"step": 469
},
{
"epoch": 0.019652321169104044,
"grad_norm": 0.24259240925312042,
"learning_rate": 1.2121212121212122e-05,
"loss": 0.986,
"step": 470
},
{
"epoch": 0.019694134618400007,
"grad_norm": 0.36460819840431213,
"learning_rate": 1.1717171717171718e-05,
"loss": 0.9039,
"step": 471
},
{
"epoch": 0.019735948067695974,
"grad_norm": 0.2529830038547516,
"learning_rate": 1.1313131313131314e-05,
"loss": 0.9908,
"step": 472
},
{
"epoch": 0.01977776151699194,
"grad_norm": 0.25467124581336975,
"learning_rate": 1.0909090909090909e-05,
"loss": 0.9427,
"step": 473
},
{
"epoch": 0.019819574966287907,
"grad_norm": 0.2367878407239914,
"learning_rate": 1.0505050505050505e-05,
"loss": 0.8862,
"step": 474
},
{
"epoch": 0.019861388415583874,
"grad_norm": 0.2721892297267914,
"learning_rate": 1.0101010101010101e-05,
"loss": 1.2878,
"step": 475
},
{
"epoch": 0.01990320186487984,
"grad_norm": 0.2348298728466034,
"learning_rate": 9.696969696969698e-06,
"loss": 0.773,
"step": 476
},
{
"epoch": 0.019945015314175803,
"grad_norm": 0.24767175316810608,
"learning_rate": 9.292929292929294e-06,
"loss": 0.9322,
"step": 477
},
{
"epoch": 0.01998682876347177,
"grad_norm": 0.240976944565773,
"learning_rate": 8.88888888888889e-06,
"loss": 0.8514,
"step": 478
},
{
"epoch": 0.020028642212767737,
"grad_norm": 0.261461079120636,
"learning_rate": 8.484848484848486e-06,
"loss": 1.1966,
"step": 479
},
{
"epoch": 0.020070455662063703,
"grad_norm": 0.2758338749408722,
"learning_rate": 8.080808080808082e-06,
"loss": 1.1045,
"step": 480
},
{
"epoch": 0.02011226911135967,
"grad_norm": 0.2313009798526764,
"learning_rate": 7.676767676767677e-06,
"loss": 0.7291,
"step": 481
},
{
"epoch": 0.020154082560655633,
"grad_norm": 0.2852662205696106,
"learning_rate": 7.272727272727272e-06,
"loss": 1.298,
"step": 482
},
{
"epoch": 0.0201958960099516,
"grad_norm": 0.24057692289352417,
"learning_rate": 6.8686868686868685e-06,
"loss": 0.9034,
"step": 483
},
{
"epoch": 0.020237709459247567,
"grad_norm": 0.2478017508983612,
"learning_rate": 6.464646464646465e-06,
"loss": 0.825,
"step": 484
},
{
"epoch": 0.020279522908543533,
"grad_norm": 0.23157985508441925,
"learning_rate": 6.060606060606061e-06,
"loss": 1.0841,
"step": 485
},
{
"epoch": 0.0203213363578395,
"grad_norm": 0.2523317039012909,
"learning_rate": 5.656565656565657e-06,
"loss": 1.0396,
"step": 486
},
{
"epoch": 0.020363149807135467,
"grad_norm": 0.25328120589256287,
"learning_rate": 5.2525252525252526e-06,
"loss": 0.9431,
"step": 487
},
{
"epoch": 0.02040496325643143,
"grad_norm": 0.2451692521572113,
"learning_rate": 4.848484848484849e-06,
"loss": 1.0761,
"step": 488
},
{
"epoch": 0.020446776705727397,
"grad_norm": 0.24553346633911133,
"learning_rate": 4.444444444444445e-06,
"loss": 1.1271,
"step": 489
},
{
"epoch": 0.020488590155023363,
"grad_norm": 0.36932989954948425,
"learning_rate": 4.040404040404041e-06,
"loss": 0.9458,
"step": 490
},
{
"epoch": 0.02053040360431933,
"grad_norm": 0.2384217381477356,
"learning_rate": 3.636363636363636e-06,
"loss": 0.9282,
"step": 491
},
{
"epoch": 0.020572217053615297,
"grad_norm": 0.25285932421684265,
"learning_rate": 3.2323232323232324e-06,
"loss": 0.9416,
"step": 492
},
{
"epoch": 0.02061403050291126,
"grad_norm": 0.6776081919670105,
"learning_rate": 2.8282828282828286e-06,
"loss": 1.0684,
"step": 493
},
{
"epoch": 0.020655843952207226,
"grad_norm": 0.4594746530056,
"learning_rate": 2.4242424242424244e-06,
"loss": 1.1019,
"step": 494
},
{
"epoch": 0.020697657401503193,
"grad_norm": 0.24249747395515442,
"learning_rate": 2.0202020202020206e-06,
"loss": 0.9081,
"step": 495
},
{
"epoch": 0.02073947085079916,
"grad_norm": 0.24494624137878418,
"learning_rate": 1.6161616161616162e-06,
"loss": 0.8783,
"step": 496
},
{
"epoch": 0.020781284300095126,
"grad_norm": 0.26583802700042725,
"learning_rate": 1.2121212121212122e-06,
"loss": 0.8981,
"step": 497
},
{
"epoch": 0.020823097749391093,
"grad_norm": 0.29171836376190186,
"learning_rate": 8.080808080808081e-07,
"loss": 0.8406,
"step": 498
},
{
"epoch": 0.020864911198687056,
"grad_norm": 0.31394335627555847,
"learning_rate": 4.0404040404040405e-07,
"loss": 1.0501,
"step": 499
},
{
"epoch": 0.020906724647983023,
"grad_norm": 0.2837514281272888,
"learning_rate": 0.0,
"loss": 1.2815,
"step": 500
}
],
"logging_steps": 1,
"max_steps": 500,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 5.7182011785216e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}