Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,1609 @@
+{
+  "<|0.00|>": 50364,
+  "<|0.02|>": 50365,
+  "<|0.04|>": 50366,
+  "<|0.06|>": 50367,
+  "<|0.08|>": 50368,
+  "<|0.10|>": 50369,
+  "<|0.12|>": 50370,
+  "<|0.14|>": 50371,
+  "<|0.16|>": 50372,
+  "<|0.18|>": 50373,
+  "<|0.20|>": 50374,
+  "<|0.22|>": 50375,
+  "<|0.24|>": 50376,
+  "<|0.26|>": 50377,
+  "<|0.28|>": 50378,
+  "<|0.30|>": 50379,
+  "<|0.32|>": 50380,
+  "<|0.34|>": 50381,
+  "<|0.36|>": 50382,
+  "<|0.38|>": 50383,
+  "<|0.40|>": 50384,
+  "<|0.42|>": 50385,
+  "<|0.44|>": 50386,
+  "<|0.46|>": 50387,
+  "<|0.48|>": 50388,
+  "<|0.50|>": 50389,
+  "<|0.52|>": 50390,
+  "<|0.54|>": 50391,
+  "<|0.56|>": 50392,
+  "<|0.58|>": 50393,
+  "<|0.60|>": 50394,
+  "<|0.62|>": 50395,
+  "<|0.64|>": 50396,
+  "<|0.66|>": 50397,
+  "<|0.68|>": 50398,
+  "<|0.70|>": 50399,
+  "<|0.72|>": 50400,
+  "<|0.74|>": 50401,
+  "<|0.76|>": 50402,
+  "<|0.78|>": 50403,
+  "<|0.80|>": 50404,
+  "<|0.82|>": 50405,
+  "<|0.84|>": 50406,
+  "<|0.86|>": 50407,
+  "<|0.88|>": 50408,
+  "<|0.90|>": 50409,
+  "<|0.92|>": 50410,
+  "<|0.94|>": 50411,
+  "<|0.96|>": 50412,
+  "<|0.98|>": 50413,
+  "<|1.00|>": 50414,
+  "<|1.02|>": 50415,
+  "<|1.04|>": 50416,
+  "<|1.06|>": 50417,
+  "<|1.08|>": 50418,
+  "<|1.10|>": 50419,
+  "<|1.12|>": 50420,
+  "<|1.14|>": 50421,
+  "<|1.16|>": 50422,
+  "<|1.18|>": 50423,
+  "<|1.20|>": 50424,
+  "<|1.22|>": 50425,
+  "<|1.24|>": 50426,
+  "<|1.26|>": 50427,
+  "<|1.28|>": 50428,
+  "<|1.30|>": 50429,
+  "<|1.32|>": 50430,
+  "<|1.34|>": 50431,
+  "<|1.36|>": 50432,
+  "<|1.38|>": 50433,
+  "<|1.40|>": 50434,
+  "<|1.42|>": 50435,
+  "<|1.44|>": 50436,
+  "<|1.46|>": 50437,
+  "<|1.48|>": 50438,
+  "<|1.50|>": 50439,
+  "<|1.52|>": 50440,
+  "<|1.54|>": 50441,
+  "<|1.56|>": 50442,
+  "<|1.58|>": 50443,
+  "<|1.60|>": 50444,
+  "<|1.62|>": 50445,
+  "<|1.64|>": 50446,
+  "<|1.66|>": 50447,
+  "<|1.68|>": 50448,
+  "<|1.70|>": 50449,
+  "<|1.72|>": 50450,
+  "<|1.74|>": 50451,
+  "<|1.76|>": 50452,
+  "<|1.78|>": 50453,
+  "<|1.80|>": 50454,
+  "<|1.82|>": 50455,
+  "<|1.84|>": 50456,
+  "<|1.86|>": 50457,
+  "<|1.88|>": 50458,
+  "<|1.90|>": 50459,
+  "<|1.92|>": 50460,
+  "<|1.94|>": 50461,
+  "<|1.96|>": 50462,
+  "<|1.98|>": 50463,
+  "<|10.00|>": 50864,
+  "<|10.02|>": 50865,
+  "<|10.04|>": 50866,
+  "<|10.06|>": 50867,
+  "<|10.08|>": 50868,
+  "<|10.10|>": 50869,
+  "<|10.12|>": 50870,
+  "<|10.14|>": 50871,
+  "<|10.16|>": 50872,
+  "<|10.18|>": 50873,
+  "<|10.20|>": 50874,
+  "<|10.22|>": 50875,
+  "<|10.24|>": 50876,
+  "<|10.26|>": 50877,
+  "<|10.28|>": 50878,
+  "<|10.30|>": 50879,
+  "<|10.32|>": 50880,
+  "<|10.34|>": 50881,
+  "<|10.36|>": 50882,
+  "<|10.38|>": 50883,
+  "<|10.40|>": 50884,
+  "<|10.42|>": 50885,
+  "<|10.44|>": 50886,
+  "<|10.46|>": 50887,
+  "<|10.48|>": 50888,
+  "<|10.50|>": 50889,
+  "<|10.52|>": 50890,
+  "<|10.54|>": 50891,
+  "<|10.56|>": 50892,
+  "<|10.58|>": 50893,
+  "<|10.60|>": 50894,
+  "<|10.62|>": 50895,
+  "<|10.64|>": 50896,
+  "<|10.66|>": 50897,
+  "<|10.68|>": 50898,
+  "<|10.70|>": 50899,
+  "<|10.72|>": 50900,
+  "<|10.74|>": 50901,
+  "<|10.76|>": 50902,
+  "<|10.78|>": 50903,
+  "<|10.80|>": 50904,
+  "<|10.82|>": 50905,
+  "<|10.84|>": 50906,
+  "<|10.86|>": 50907,
+  "<|10.88|>": 50908,
+  "<|10.90|>": 50909,
+  "<|10.92|>": 50910,
+  "<|10.94|>": 50911,
+  "<|10.96|>": 50912,
+  "<|10.98|>": 50913,
+  "<|11.00|>": 50914,
+  "<|11.02|>": 50915,
+  "<|11.04|>": 50916,
+  "<|11.06|>": 50917,
+  "<|11.08|>": 50918,
+  "<|11.10|>": 50919,
+  "<|11.12|>": 50920,
+  "<|11.14|>": 50921,
+  "<|11.16|>": 50922,
+  "<|11.18|>": 50923,
+  "<|11.20|>": 50924,
+  "<|11.22|>": 50925,
+  "<|11.24|>": 50926,
+  "<|11.26|>": 50927,
+  "<|11.28|>": 50928,
+  "<|11.30|>": 50929,
+  "<|11.32|>": 50930,
+  "<|11.34|>": 50931,
+  "<|11.36|>": 50932,
+  "<|11.38|>": 50933,
+  "<|11.40|>": 50934,
+  "<|11.42|>": 50935,
+  "<|11.44|>": 50936,
+  "<|11.46|>": 50937,
+  "<|11.48|>": 50938,
+  "<|11.50|>": 50939,
+  "<|11.52|>": 50940,
+  "<|11.54|>": 50941,
+  "<|11.56|>": 50942,
+  "<|11.58|>": 50943,
+  "<|11.60|>": 50944,
+  "<|11.62|>": 50945,
+  "<|11.64|>": 50946,
+  "<|11.66|>": 50947,
+  "<|11.68|>": 50948,
+  "<|11.70|>": 50949,
+  "<|11.72|>": 50950,
+  "<|11.74|>": 50951,
+  "<|11.76|>": 50952,
+  "<|11.78|>": 50953,
+  "<|11.80|>": 50954,
+  "<|11.82|>": 50955,
+  "<|11.84|>": 50956,
+  "<|11.86|>": 50957,
+  "<|11.88|>": 50958,
+  "<|11.90|>": 50959,
+  "<|11.92|>": 50960,
+  "<|11.94|>": 50961,
+  "<|11.96|>": 50962,
+  "<|11.98|>": 50963,
+  "<|12.00|>": 50964,
+  "<|12.02|>": 50965,
+  "<|12.04|>": 50966,
+  "<|12.06|>": 50967,
+  "<|12.08|>": 50968,
+  "<|12.10|>": 50969,
+  "<|12.12|>": 50970,
+  "<|12.14|>": 50971,
+  "<|12.16|>": 50972,
+  "<|12.18|>": 50973,
+  "<|12.20|>": 50974,
+  "<|12.22|>": 50975,
+  "<|12.24|>": 50976,
+  "<|12.26|>": 50977,
+  "<|12.28|>": 50978,
+  "<|12.30|>": 50979,
+  "<|12.32|>": 50980,
+  "<|12.34|>": 50981,
+  "<|12.36|>": 50982,
+  "<|12.38|>": 50983,
+  "<|12.40|>": 50984,
+  "<|12.42|>": 50985,
+  "<|12.44|>": 50986,
+  "<|12.46|>": 50987,
+  "<|12.48|>": 50988,
+  "<|12.50|>": 50989,
+  "<|12.52|>": 50990,
+  "<|12.54|>": 50991,
+  "<|12.56|>": 50992,
+  "<|12.58|>": 50993,
+  "<|12.60|>": 50994,
+  "<|12.62|>": 50995,
+  "<|12.64|>": 50996,
+  "<|12.66|>": 50997,
+  "<|12.68|>": 50998,
+  "<|12.70|>": 50999,
+  "<|12.72|>": 51000,
+  "<|12.74|>": 51001,
+  "<|12.76|>": 51002,
+  "<|12.78|>": 51003,
+  "<|12.80|>": 51004,
+  "<|12.82|>": 51005,
+  "<|12.84|>": 51006,
+  "<|12.86|>": 51007,
+  "<|12.88|>": 51008,
+  "<|12.90|>": 51009,
+  "<|12.92|>": 51010,
+  "<|12.94|>": 51011,
+  "<|12.96|>": 51012,
+  "<|12.98|>": 51013,
+  "<|13.00|>": 51014,
+  "<|13.02|>": 51015,
+  "<|13.04|>": 51016,
+  "<|13.06|>": 51017,
+  "<|13.08|>": 51018,
+  "<|13.10|>": 51019,
+  "<|13.12|>": 51020,
+  "<|13.14|>": 51021,
+  "<|13.16|>": 51022,
+  "<|13.18|>": 51023,
+  "<|13.20|>": 51024,
+  "<|13.22|>": 51025,
+  "<|13.24|>": 51026,
+  "<|13.26|>": 51027,
+  "<|13.28|>": 51028,
+  "<|13.30|>": 51029,
+  "<|13.32|>": 51030,
+  "<|13.34|>": 51031,
+  "<|13.36|>": 51032,
+  "<|13.38|>": 51033,
+  "<|13.40|>": 51034,
+  "<|13.42|>": 51035,
+  "<|13.44|>": 51036,
+  "<|13.46|>": 51037,
+  "<|13.48|>": 51038,
+  "<|13.50|>": 51039,
+  "<|13.52|>": 51040,
+  "<|13.54|>": 51041,
+  "<|13.56|>": 51042,
+  "<|13.58|>": 51043,
+  "<|13.60|>": 51044,
+  "<|13.62|>": 51045,
+  "<|13.64|>": 51046,
+  "<|13.66|>": 51047,
+  "<|13.68|>": 51048,
+  "<|13.70|>": 51049,
+  "<|13.72|>": 51050,
+  "<|13.74|>": 51051,
+  "<|13.76|>": 51052,
+  "<|13.78|>": 51053,
+  "<|13.80|>": 51054,
+  "<|13.82|>": 51055,
+  "<|13.84|>": 51056,
+  "<|13.86|>": 51057,
+  "<|13.88|>": 51058,
+  "<|13.90|>": 51059,
+  "<|13.92|>": 51060,
+  "<|13.94|>": 51061,
+  "<|13.96|>": 51062,
+  "<|13.98|>": 51063,
+  "<|14.00|>": 51064,
+  "<|14.02|>": 51065,
+  "<|14.04|>": 51066,
+  "<|14.06|>": 51067,
+  "<|14.08|>": 51068,
+  "<|14.10|>": 51069,
+  "<|14.12|>": 51070,
+  "<|14.14|>": 51071,
+  "<|14.16|>": 51072,
+  "<|14.18|>": 51073,
+  "<|14.20|>": 51074,
+  "<|14.22|>": 51075,
+  "<|14.24|>": 51076,
+  "<|14.26|>": 51077,
+  "<|14.28|>": 51078,
+  "<|14.30|>": 51079,
+  "<|14.32|>": 51080,
+  "<|14.34|>": 51081,
+  "<|14.36|>": 51082,
+  "<|14.38|>": 51083,
+  "<|14.40|>": 51084,
+  "<|14.42|>": 51085,
+  "<|14.44|>": 51086,
+  "<|14.46|>": 51087,
+  "<|14.48|>": 51088,
+  "<|14.50|>": 51089,
+  "<|14.52|>": 51090,
+  "<|14.54|>": 51091,
+  "<|14.56|>": 51092,
+  "<|14.58|>": 51093,
+  "<|14.60|>": 51094,
+  "<|14.62|>": 51095,
+  "<|14.64|>": 51096,
+  "<|14.66|>": 51097,
+  "<|14.68|>": 51098,
+  "<|14.70|>": 51099,
+  "<|14.72|>": 51100,
+  "<|14.74|>": 51101,
+  "<|14.76|>": 51102,
+  "<|14.78|>": 51103,
+  "<|14.80|>": 51104,
+  "<|14.82|>": 51105,
+  "<|14.84|>": 51106,
+  "<|14.86|>": 51107,
+  "<|14.88|>": 51108,
+  "<|14.90|>": 51109,
+  "<|14.92|>": 51110,
+  "<|14.94|>": 51111,
+  "<|14.96|>": 51112,
+  "<|14.98|>": 51113,
+  "<|15.00|>": 51114,
+  "<|15.02|>": 51115,
+  "<|15.04|>": 51116,
+  "<|15.06|>": 51117,
+  "<|15.08|>": 51118,
+  "<|15.10|>": 51119,
+  "<|15.12|>": 51120,
+  "<|15.14|>": 51121,
+  "<|15.16|>": 51122,
+  "<|15.18|>": 51123,
+  "<|15.20|>": 51124,
+  "<|15.22|>": 51125,
+  "<|15.24|>": 51126,
+  "<|15.26|>": 51127,
+  "<|15.28|>": 51128,
+  "<|15.30|>": 51129,
+  "<|15.32|>": 51130,
+  "<|15.34|>": 51131,
+  "<|15.36|>": 51132,
+  "<|15.38|>": 51133,
+  "<|15.40|>": 51134,
+  "<|15.42|>": 51135,
+  "<|15.44|>": 51136,
+  "<|15.46|>": 51137,
+  "<|15.48|>": 51138,
+  "<|15.50|>": 51139,
+  "<|15.52|>": 51140,
+  "<|15.54|>": 51141,
+  "<|15.56|>": 51142,
+  "<|15.58|>": 51143,
+  "<|15.60|>": 51144,
+  "<|15.62|>": 51145,
+  "<|15.64|>": 51146,
+  "<|15.66|>": 51147,
+  "<|15.68|>": 51148,
+  "<|15.70|>": 51149,
+  "<|15.72|>": 51150,
+  "<|15.74|>": 51151,
+  "<|15.76|>": 51152,
+  "<|15.78|>": 51153,
+  "<|15.80|>": 51154,
+  "<|15.82|>": 51155,
+  "<|15.84|>": 51156,
+  "<|15.86|>": 51157,
+  "<|15.88|>": 51158,
+  "<|15.90|>": 51159,
+  "<|15.92|>": 51160,
+  "<|15.94|>": 51161,
+  "<|15.96|>": 51162,
+  "<|15.98|>": 51163,
+  "<|16.00|>": 51164,
+  "<|16.02|>": 51165,
+  "<|16.04|>": 51166,
+  "<|16.06|>": 51167,
+  "<|16.08|>": 51168,
+  "<|16.10|>": 51169,
+  "<|16.12|>": 51170,
+  "<|16.14|>": 51171,
+  "<|16.16|>": 51172,
+  "<|16.18|>": 51173,
+  "<|16.20|>": 51174,
+  "<|16.22|>": 51175,
+  "<|16.24|>": 51176,
+  "<|16.26|>": 51177,
+  "<|16.28|>": 51178,
+  "<|16.30|>": 51179,
+  "<|16.32|>": 51180,
+  "<|16.34|>": 51181,
+  "<|16.36|>": 51182,
+  "<|16.38|>": 51183,
+  "<|16.40|>": 51184,
+  "<|16.42|>": 51185,
+  "<|16.44|>": 51186,
+  "<|16.46|>": 51187,
+  "<|16.48|>": 51188,
+  "<|16.50|>": 51189,
+  "<|16.52|>": 51190,
+  "<|16.54|>": 51191,
+  "<|16.56|>": 51192,
+  "<|16.58|>": 51193,
+  "<|16.60|>": 51194,
+  "<|16.62|>": 51195,
+  "<|16.64|>": 51196,
+  "<|16.66|>": 51197,
+  "<|16.68|>": 51198,
+  "<|16.70|>": 51199,
+  "<|16.72|>": 51200,
+  "<|16.74|>": 51201,
+  "<|16.76|>": 51202,
+  "<|16.78|>": 51203,
+  "<|16.80|>": 51204,
+  "<|16.82|>": 51205,
+  "<|16.84|>": 51206,
+  "<|16.86|>": 51207,
+  "<|16.88|>": 51208,
+  "<|16.90|>": 51209,
+  "<|16.92|>": 51210,
+  "<|16.94|>": 51211,
+  "<|16.96|>": 51212,
+  "<|16.98|>": 51213,
+  "<|17.00|>": 51214,
+  "<|17.02|>": 51215,
+  "<|17.04|>": 51216,
+  "<|17.06|>": 51217,
+  "<|17.08|>": 51218,
+  "<|17.10|>": 51219,
+  "<|17.12|>": 51220,
+  "<|17.14|>": 51221,
+  "<|17.16|>": 51222,
+  "<|17.18|>": 51223,
+  "<|17.20|>": 51224,
+  "<|17.22|>": 51225,
+  "<|17.24|>": 51226,
+  "<|17.26|>": 51227,
+  "<|17.28|>": 51228,
+  "<|17.30|>": 51229,
+  "<|17.32|>": 51230,
+  "<|17.34|>": 51231,
+  "<|17.36|>": 51232,
+  "<|17.38|>": 51233,
+  "<|17.40|>": 51234,
+  "<|17.42|>": 51235,
+  "<|17.44|>": 51236,
+  "<|17.46|>": 51237,
+  "<|17.48|>": 51238,
+  "<|17.50|>": 51239,
+  "<|17.52|>": 51240,
+  "<|17.54|>": 51241,
+  "<|17.56|>": 51242,
+  "<|17.58|>": 51243,
+  "<|17.60|>": 51244,
+  "<|17.62|>": 51245,
+  "<|17.64|>": 51246,
+  "<|17.66|>": 51247,
+  "<|17.68|>": 51248,
+  "<|17.70|>": 51249,
+  "<|17.72|>": 51250,
+  "<|17.74|>": 51251,
+  "<|17.76|>": 51252,
+  "<|17.78|>": 51253,
+  "<|17.80|>": 51254,
+  "<|17.82|>": 51255,
+  "<|17.84|>": 51256,
+  "<|17.86|>": 51257,
+  "<|17.88|>": 51258,
+  "<|17.90|>": 51259,
+  "<|17.92|>": 51260,
+  "<|17.94|>": 51261,
+  "<|17.96|>": 51262,
+  "<|17.98|>": 51263,
+  "<|18.00|>": 51264,
+  "<|18.02|>": 51265,
+  "<|18.04|>": 51266,
+  "<|18.06|>": 51267,
+  "<|18.08|>": 51268,
+  "<|18.10|>": 51269,
+  "<|18.12|>": 51270,
+  "<|18.14|>": 51271,
+  "<|18.16|>": 51272,
+  "<|18.18|>": 51273,
+  "<|18.20|>": 51274,
+  "<|18.22|>": 51275,
+  "<|18.24|>": 51276,
+  "<|18.26|>": 51277,
+  "<|18.28|>": 51278,
+  "<|18.30|>": 51279,
+  "<|18.32|>": 51280,
+  "<|18.34|>": 51281,
+  "<|18.36|>": 51282,
+  "<|18.38|>": 51283,
+  "<|18.40|>": 51284,
+  "<|18.42|>": 51285,
+  "<|18.44|>": 51286,
+  "<|18.46|>": 51287,
+  "<|18.48|>": 51288,
+  "<|18.50|>": 51289,
+  "<|18.52|>": 51290,
+  "<|18.54|>": 51291,
+  "<|18.56|>": 51292,
+  "<|18.58|>": 51293,
+  "<|18.60|>": 51294,
+  "<|18.62|>": 51295,
+  "<|18.64|>": 51296,
+  "<|18.66|>": 51297,
+  "<|18.68|>": 51298,
+  "<|18.70|>": 51299,
+  "<|18.72|>": 51300,
+  "<|18.74|>": 51301,
+  "<|18.76|>": 51302,
+  "<|18.78|>": 51303,
+  "<|18.80|>": 51304,
+  "<|18.82|>": 51305,
+  "<|18.84|>": 51306,
+  "<|18.86|>": 51307,
+  "<|18.88|>": 51308,
+  "<|18.90|>": 51309,
+  "<|18.92|>": 51310,
+  "<|18.94|>": 51311,
+  "<|18.96|>": 51312,
+  "<|18.98|>": 51313,
+  "<|19.00|>": 51314,
+  "<|19.02|>": 51315,
+  "<|19.04|>": 51316,
+  "<|19.06|>": 51317,
+  "<|19.08|>": 51318,
+  "<|19.10|>": 51319,
+  "<|19.12|>": 51320,
+  "<|19.14|>": 51321,
+  "<|19.16|>": 51322,
+  "<|19.18|>": 51323,
+  "<|19.20|>": 51324,
+  "<|19.22|>": 51325,
+  "<|19.24|>": 51326,
+  "<|19.26|>": 51327,
+  "<|19.28|>": 51328,
+  "<|19.30|>": 51329,
+  "<|19.32|>": 51330,
+  "<|19.34|>": 51331,
+  "<|19.36|>": 51332,
+  "<|19.38|>": 51333,
+  "<|19.40|>": 51334,
+  "<|19.42|>": 51335,
+  "<|19.44|>": 51336,
+  "<|19.46|>": 51337,
+  "<|19.48|>": 51338,
+  "<|19.50|>": 51339,
+  "<|19.52|>": 51340,
+  "<|19.54|>": 51341,
+  "<|19.56|>": 51342,
+  "<|19.58|>": 51343,
+  "<|19.60|>": 51344,
+  "<|19.62|>": 51345,
+  "<|19.64|>": 51346,
+  "<|19.66|>": 51347,
+  "<|19.68|>": 51348,
+  "<|19.70|>": 51349,
+  "<|19.72|>": 51350,
+  "<|19.74|>": 51351,
+  "<|19.76|>": 51352,
+  "<|19.78|>": 51353,
+  "<|19.80|>": 51354,
+  "<|19.82|>": 51355,
+  "<|19.84|>": 51356,
+  "<|19.86|>": 51357,
+  "<|19.88|>": 51358,
+  "<|19.90|>": 51359,
+  "<|19.92|>": 51360,
+  "<|19.94|>": 51361,
+  "<|19.96|>": 51362,
+  "<|19.98|>": 51363,
+  "<|2.00|>": 50464,
+  "<|2.02|>": 50465,
+  "<|2.04|>": 50466,
+  "<|2.06|>": 50467,
+  "<|2.08|>": 50468,
+  "<|2.10|>": 50469,
+  "<|2.12|>": 50470,
+  "<|2.14|>": 50471,
+  "<|2.16|>": 50472,
+  "<|2.18|>": 50473,
+  "<|2.20|>": 50474,
+  "<|2.22|>": 50475,
+  "<|2.24|>": 50476,
+  "<|2.26|>": 50477,
+  "<|2.28|>": 50478,
+  "<|2.30|>": 50479,
+  "<|2.32|>": 50480,
+  "<|2.34|>": 50481,
+  "<|2.36|>": 50482,
+  "<|2.38|>": 50483,
+  "<|2.40|>": 50484,
+  "<|2.42|>": 50485,
+  "<|2.44|>": 50486,
+  "<|2.46|>": 50487,
+  "<|2.48|>": 50488,
+  "<|2.50|>": 50489,
+  "<|2.52|>": 50490,
+  "<|2.54|>": 50491,
+  "<|2.56|>": 50492,
+  "<|2.58|>": 50493,
+  "<|2.60|>": 50494,
+  "<|2.62|>": 50495,
+  "<|2.64|>": 50496,
+  "<|2.66|>": 50497,
+  "<|2.68|>": 50498,
+  "<|2.70|>": 50499,
+  "<|2.72|>": 50500,
+  "<|2.74|>": 50501,
+  "<|2.76|>": 50502,
+  "<|2.78|>": 50503,
+  "<|2.80|>": 50504,
+  "<|2.82|>": 50505,
+  "<|2.84|>": 50506,
+  "<|2.86|>": 50507,
+  "<|2.88|>": 50508,
+  "<|2.90|>": 50509,
+  "<|2.92|>": 50510,
+  "<|2.94|>": 50511,
+  "<|2.96|>": 50512,
+  "<|2.98|>": 50513,
+  "<|20.00|>": 51364,
+  "<|20.02|>": 51365,
+  "<|20.04|>": 51366,
+  "<|20.06|>": 51367,
+  "<|20.08|>": 51368,
+  "<|20.10|>": 51369,
+  "<|20.12|>": 51370,
+  "<|20.14|>": 51371,
+  "<|20.16|>": 51372,
+  "<|20.18|>": 51373,
+  "<|20.20|>": 51374,
+  "<|20.22|>": 51375,
+  "<|20.24|>": 51376,
+  "<|20.26|>": 51377,
+  "<|20.28|>": 51378,
+  "<|20.30|>": 51379,
+  "<|20.32|>": 51380,
+  "<|20.34|>": 51381,
+  "<|20.36|>": 51382,
+  "<|20.38|>": 51383,
+  "<|20.40|>": 51384,
+  "<|20.42|>": 51385,
+  "<|20.44|>": 51386,
+  "<|20.46|>": 51387,
+  "<|20.48|>": 51388,
+  "<|20.50|>": 51389,
+  "<|20.52|>": 51390,
+  "<|20.54|>": 51391,
+  "<|20.56|>": 51392,
+  "<|20.58|>": 51393,
+  "<|20.60|>": 51394,
+  "<|20.62|>": 51395,
+  "<|20.64|>": 51396,
+  "<|20.66|>": 51397,
+  "<|20.68|>": 51398,
+  "<|20.70|>": 51399,
+  "<|20.72|>": 51400,
+  "<|20.74|>": 51401,
+  "<|20.76|>": 51402,
+  "<|20.78|>": 51403,
+  "<|20.80|>": 51404,
+  "<|20.82|>": 51405,
+  "<|20.84|>": 51406,
+  "<|20.86|>": 51407,
+  "<|20.88|>": 51408,
+  "<|20.90|>": 51409,
+  "<|20.92|>": 51410,
+  "<|20.94|>": 51411,
+  "<|20.96|>": 51412,
+  "<|20.98|>": 51413,
+  "<|21.00|>": 51414,
+  "<|21.02|>": 51415,
+  "<|21.04|>": 51416,
+  "<|21.06|>": 51417,
+  "<|21.08|>": 51418,
+  "<|21.10|>": 51419,
+  "<|21.12|>": 51420,
+  "<|21.14|>": 51421,
+  "<|21.16|>": 51422,
+  "<|21.18|>": 51423,
+  "<|21.20|>": 51424,
+  "<|21.22|>": 51425,
+  "<|21.24|>": 51426,
+  "<|21.26|>": 51427,
+  "<|21.28|>": 51428,
+  "<|21.30|>": 51429,
+  "<|21.32|>": 51430,
+  "<|21.34|>": 51431,
+  "<|21.36|>": 51432,
+  "<|21.38|>": 51433,
+  "<|21.40|>": 51434,
+  "<|21.42|>": 51435,
+  "<|21.44|>": 51436,
+  "<|21.46|>": 51437,
+  "<|21.48|>": 51438,
+  "<|21.50|>": 51439,
+  "<|21.52|>": 51440,
+  "<|21.54|>": 51441,
+  "<|21.56|>": 51442,
+  "<|21.58|>": 51443,
+  "<|21.60|>": 51444,
+  "<|21.62|>": 51445,
+  "<|21.64|>": 51446,
+  "<|21.66|>": 51447,
+  "<|21.68|>": 51448,
+  "<|21.70|>": 51449,
+  "<|21.72|>": 51450,
+  "<|21.74|>": 51451,
+  "<|21.76|>": 51452,
+  "<|21.78|>": 51453,
+  "<|21.80|>": 51454,
+  "<|21.82|>": 51455,
+  "<|21.84|>": 51456,
+  "<|21.86|>": 51457,
+  "<|21.88|>": 51458,
+  "<|21.90|>": 51459,
+  "<|21.92|>": 51460,
+  "<|21.94|>": 51461,
+  "<|21.96|>": 51462,
+  "<|21.98|>": 51463,
+  "<|22.00|>": 51464,
+  "<|22.02|>": 51465,
+  "<|22.04|>": 51466,
+  "<|22.06|>": 51467,
+  "<|22.08|>": 51468,
+  "<|22.10|>": 51469,
+  "<|22.12|>": 51470,
+  "<|22.14|>": 51471,
+  "<|22.16|>": 51472,
+  "<|22.18|>": 51473,
+  "<|22.20|>": 51474,
+  "<|22.22|>": 51475,
+  "<|22.24|>": 51476,
+  "<|22.26|>": 51477,
+  "<|22.28|>": 51478,
+  "<|22.30|>": 51479,
+  "<|22.32|>": 51480,
+  "<|22.34|>": 51481,
+  "<|22.36|>": 51482,
+  "<|22.38|>": 51483,
+  "<|22.40|>": 51484,
+  "<|22.42|>": 51485,
+  "<|22.44|>": 51486,
+  "<|22.46|>": 51487,
+  "<|22.48|>": 51488,
+  "<|22.50|>": 51489,
+  "<|22.52|>": 51490,
+  "<|22.54|>": 51491,
+  "<|22.56|>": 51492,
+  "<|22.58|>": 51493,
+  "<|22.60|>": 51494,
+  "<|22.62|>": 51495,
+  "<|22.64|>": 51496,
+  "<|22.66|>": 51497,
+  "<|22.68|>": 51498,
+  "<|22.70|>": 51499,
+  "<|22.72|>": 51500,
+  "<|22.74|>": 51501,
+  "<|22.76|>": 51502,
+  "<|22.78|>": 51503,
+  "<|22.80|>": 51504,
+  "<|22.82|>": 51505,
+  "<|22.84|>": 51506,
+  "<|22.86|>": 51507,
+  "<|22.88|>": 51508,
+  "<|22.90|>": 51509,
+  "<|22.92|>": 51510,
+  "<|22.94|>": 51511,
+  "<|22.96|>": 51512,
+  "<|22.98|>": 51513,
+  "<|23.00|>": 51514,
+  "<|23.02|>": 51515,
+  "<|23.04|>": 51516,
+  "<|23.06|>": 51517,
+  "<|23.08|>": 51518,
+  "<|23.10|>": 51519,
+  "<|23.12|>": 51520,
+  "<|23.14|>": 51521,
+  "<|23.16|>": 51522,
+  "<|23.18|>": 51523,
+  "<|23.20|>": 51524,
+  "<|23.22|>": 51525,
+  "<|23.24|>": 51526,
+  "<|23.26|>": 51527,
+  "<|23.28|>": 51528,
+  "<|23.30|>": 51529,
+  "<|23.32|>": 51530,
+  "<|23.34|>": 51531,
+  "<|23.36|>": 51532,
+  "<|23.38|>": 51533,
+  "<|23.40|>": 51534,
+  "<|23.42|>": 51535,
+  "<|23.44|>": 51536,
+  "<|23.46|>": 51537,
+  "<|23.48|>": 51538,
+  "<|23.50|>": 51539,
+  "<|23.52|>": 51540,
+  "<|23.54|>": 51541,
+  "<|23.56|>": 51542,
+  "<|23.58|>": 51543,
+  "<|23.60|>": 51544,
+  "<|23.62|>": 51545,
+  "<|23.64|>": 51546,
+  "<|23.66|>": 51547,
+  "<|23.68|>": 51548,
+  "<|23.70|>": 51549,
+  "<|23.72|>": 51550,
+  "<|23.74|>": 51551,
+  "<|23.76|>": 51552,
+  "<|23.78|>": 51553,
+  "<|23.80|>": 51554,
+  "<|23.82|>": 51555,
+  "<|23.84|>": 51556,
+  "<|23.86|>": 51557,
+  "<|23.88|>": 51558,
+  "<|23.90|>": 51559,
+  "<|23.92|>": 51560,
+  "<|23.94|>": 51561,
+  "<|23.96|>": 51562,
+  "<|23.98|>": 51563,
+  "<|24.00|>": 51564,
+  "<|24.02|>": 51565,
+  "<|24.04|>": 51566,
+  "<|24.06|>": 51567,
+  "<|24.08|>": 51568,
+  "<|24.10|>": 51569,
+  "<|24.12|>": 51570,
+  "<|24.14|>": 51571,
+  "<|24.16|>": 51572,
+  "<|24.18|>": 51573,
+  "<|24.20|>": 51574,
+  "<|24.22|>": 51575,
+  "<|24.24|>": 51576,
+  "<|24.26|>": 51577,
+  "<|24.28|>": 51578,
+  "<|24.30|>": 51579,
+  "<|24.32|>": 51580,
+  "<|24.34|>": 51581,
+  "<|24.36|>": 51582,
+  "<|24.38|>": 51583,
+  "<|24.40|>": 51584,
+  "<|24.42|>": 51585,
+  "<|24.44|>": 51586,
+  "<|24.46|>": 51587,
+  "<|24.48|>": 51588,
+  "<|24.50|>": 51589,
+  "<|24.52|>": 51590,
+  "<|24.54|>": 51591,
+  "<|24.56|>": 51592,
+  "<|24.58|>": 51593,
+  "<|24.60|>": 51594,
+  "<|24.62|>": 51595,
+  "<|24.64|>": 51596,
+  "<|24.66|>": 51597,
+  "<|24.68|>": 51598,
+  "<|24.70|>": 51599,
+  "<|24.72|>": 51600,
+  "<|24.74|>": 51601,
+  "<|24.76|>": 51602,
+  "<|24.78|>": 51603,
+  "<|24.80|>": 51604,
+  "<|24.82|>": 51605,
+  "<|24.84|>": 51606,
+  "<|24.86|>": 51607,
+  "<|24.88|>": 51608,
+  "<|24.90|>": 51609,
+  "<|24.92|>": 51610,
+  "<|24.94|>": 51611,
+  "<|24.96|>": 51612,
+  "<|24.98|>": 51613,
+  "<|25.00|>": 51614,
+  "<|25.02|>": 51615,
+  "<|25.04|>": 51616,
+  "<|25.06|>": 51617,
+  "<|25.08|>": 51618,
+  "<|25.10|>": 51619,
+  "<|25.12|>": 51620,
+  "<|25.14|>": 51621,
+  "<|25.16|>": 51622,
+  "<|25.18|>": 51623,
+  "<|25.20|>": 51624,
+  "<|25.22|>": 51625,
+  "<|25.24|>": 51626,
+  "<|25.26|>": 51627,
+  "<|25.28|>": 51628,
+  "<|25.30|>": 51629,
+  "<|25.32|>": 51630,
+  "<|25.34|>": 51631,
+  "<|25.36|>": 51632,
+  "<|25.38|>": 51633,
+  "<|25.40|>": 51634,
+  "<|25.42|>": 51635,
+  "<|25.44|>": 51636,
+  "<|25.46|>": 51637,
+  "<|25.48|>": 51638,
+  "<|25.50|>": 51639,
+  "<|25.52|>": 51640,
+  "<|25.54|>": 51641,
+  "<|25.56|>": 51642,
+  "<|25.58|>": 51643,
+  "<|25.60|>": 51644,
+  "<|25.62|>": 51645,
+  "<|25.64|>": 51646,
+  "<|25.66|>": 51647,
+  "<|25.68|>": 51648,
+  "<|25.70|>": 51649,
+  "<|25.72|>": 51650,
+  "<|25.74|>": 51651,
+  "<|25.76|>": 51652,
+  "<|25.78|>": 51653,
+  "<|25.80|>": 51654,
+  "<|25.82|>": 51655,
+  "<|25.84|>": 51656,
+  "<|25.86|>": 51657,
+  "<|25.88|>": 51658,
+  "<|25.90|>": 51659,
+  "<|25.92|>": 51660,
+  "<|25.94|>": 51661,
+  "<|25.96|>": 51662,
+  "<|25.98|>": 51663,
+  "<|26.00|>": 51664,
+  "<|26.02|>": 51665,
+  "<|26.04|>": 51666,
+  "<|26.06|>": 51667,
+  "<|26.08|>": 51668,
+  "<|26.10|>": 51669,
+  "<|26.12|>": 51670,
+  "<|26.14|>": 51671,
+  "<|26.16|>": 51672,
+  "<|26.18|>": 51673,
+  "<|26.20|>": 51674,
+  "<|26.22|>": 51675,
+  "<|26.24|>": 51676,
+  "<|26.26|>": 51677,
+  "<|26.28|>": 51678,
+  "<|26.30|>": 51679,
+  "<|26.32|>": 51680,
+  "<|26.34|>": 51681,
+  "<|26.36|>": 51682,
+  "<|26.38|>": 51683,
+  "<|26.40|>": 51684,
+  "<|26.42|>": 51685,
+  "<|26.44|>": 51686,
+  "<|26.46|>": 51687,
+  "<|26.48|>": 51688,
+  "<|26.50|>": 51689,
+  "<|26.52|>": 51690,
+  "<|26.54|>": 51691,
+  "<|26.56|>": 51692,
+  "<|26.58|>": 51693,
+  "<|26.60|>": 51694,
+  "<|26.62|>": 51695,
+  "<|26.64|>": 51696,
+  "<|26.66|>": 51697,
+  "<|26.68|>": 51698,
+  "<|26.70|>": 51699,
+  "<|26.72|>": 51700,
+  "<|26.74|>": 51701,
+  "<|26.76|>": 51702,
+  "<|26.78|>": 51703,
+  "<|26.80|>": 51704,
+  "<|26.82|>": 51705,
+  "<|26.84|>": 51706,
+  "<|26.86|>": 51707,
+  "<|26.88|>": 51708,
+  "<|26.90|>": 51709,
+  "<|26.92|>": 51710,
+  "<|26.94|>": 51711,
+  "<|26.96|>": 51712,
+  "<|26.98|>": 51713,
+  "<|27.00|>": 51714,
+  "<|27.02|>": 51715,
+  "<|27.04|>": 51716,
+  "<|27.06|>": 51717,
+  "<|27.08|>": 51718,
+  "<|27.10|>": 51719,
+  "<|27.12|>": 51720,
+  "<|27.14|>": 51721,
+  "<|27.16|>": 51722,
+  "<|27.18|>": 51723,
+  "<|27.20|>": 51724,
+  "<|27.22|>": 51725,
+  "<|27.24|>": 51726,
+  "<|27.26|>": 51727,
+  "<|27.28|>": 51728,
+  "<|27.30|>": 51729,
+  "<|27.32|>": 51730,
+  "<|27.34|>": 51731,
+  "<|27.36|>": 51732,
+  "<|27.38|>": 51733,
+  "<|27.40|>": 51734,
+  "<|27.42|>": 51735,
+  "<|27.44|>": 51736,
+  "<|27.46|>": 51737,
+  "<|27.48|>": 51738,
+  "<|27.50|>": 51739,
+  "<|27.52|>": 51740,
+  "<|27.54|>": 51741,
+  "<|27.56|>": 51742,
+  "<|27.58|>": 51743,
+  "<|27.60|>": 51744,
+  "<|27.62|>": 51745,
+  "<|27.64|>": 51746,
+  "<|27.66|>": 51747,
+  "<|27.68|>": 51748,
+  "<|27.70|>": 51749,
+  "<|27.72|>": 51750,
+  "<|27.74|>": 51751,
+  "<|27.76|>": 51752,
+  "<|27.78|>": 51753,
+  "<|27.80|>": 51754,
+  "<|27.82|>": 51755,
+  "<|27.84|>": 51756,
+  "<|27.86|>": 51757,
+  "<|27.88|>": 51758,
+  "<|27.90|>": 51759,
+  "<|27.92|>": 51760,
+  "<|27.94|>": 51761,
+  "<|27.96|>": 51762,
+  "<|27.98|>": 51763,
+  "<|28.00|>": 51764,
+  "<|28.02|>": 51765,
+  "<|28.04|>": 51766,
+  "<|28.06|>": 51767,
+  "<|28.08|>": 51768,
+  "<|28.10|>": 51769,
+  "<|28.12|>": 51770,
+  "<|28.14|>": 51771,
+  "<|28.16|>": 51772,
+  "<|28.18|>": 51773,
+  "<|28.20|>": 51774,
+  "<|28.22|>": 51775,
+  "<|28.24|>": 51776,
+  "<|28.26|>": 51777,
+  "<|28.28|>": 51778,
+  "<|28.30|>": 51779,
+  "<|28.32|>": 51780,
+  "<|28.34|>": 51781,
+  "<|28.36|>": 51782,
+  "<|28.38|>": 51783,
+  "<|28.40|>": 51784,
+  "<|28.42|>": 51785,
+  "<|28.44|>": 51786,
+  "<|28.46|>": 51787,
+  "<|28.48|>": 51788,
+  "<|28.50|>": 51789,
+  "<|28.52|>": 51790,
+  "<|28.54|>": 51791,
+  "<|28.56|>": 51792,
+  "<|28.58|>": 51793,
+  "<|28.60|>": 51794,
+  "<|28.62|>": 51795,
+  "<|28.64|>": 51796,
+  "<|28.66|>": 51797,
+  "<|28.68|>": 51798,
+  "<|28.70|>": 51799,
+  "<|28.72|>": 51800,
+  "<|28.74|>": 51801,
+  "<|28.76|>": 51802,
+  "<|28.78|>": 51803,
+  "<|28.80|>": 51804,
+  "<|28.82|>": 51805,
+  "<|28.84|>": 51806,
+  "<|28.86|>": 51807,
+  "<|28.88|>": 51808,
+  "<|28.90|>": 51809,
+  "<|28.92|>": 51810,
+  "<|28.94|>": 51811,
+  "<|28.96|>": 51812,
+  "<|28.98|>": 51813,
+  "<|29.00|>": 51814,
+  "<|29.02|>": 51815,
+  "<|29.04|>": 51816,
+  "<|29.06|>": 51817,
+  "<|29.08|>": 51818,
+  "<|29.10|>": 51819,
+  "<|29.12|>": 51820,
+  "<|29.14|>": 51821,
+  "<|29.16|>": 51822,
+  "<|29.18|>": 51823,
+  "<|29.20|>": 51824,
+  "<|29.22|>": 51825,
+  "<|29.24|>": 51826,
+  "<|29.26|>": 51827,
+  "<|29.28|>": 51828,
+  "<|29.30|>": 51829,
+  "<|29.32|>": 51830,
+  "<|29.34|>": 51831,
+  "<|29.36|>": 51832,
+  "<|29.38|>": 51833,
+  "<|29.40|>": 51834,
+  "<|29.42|>": 51835,
+  "<|29.44|>": 51836,
+  "<|29.46|>": 51837,
+  "<|29.48|>": 51838,
+  "<|29.50|>": 51839,
+  "<|29.52|>": 51840,
+  "<|29.54|>": 51841,
+  "<|29.56|>": 51842,
+  "<|29.58|>": 51843,
+  "<|29.60|>": 51844,
+  "<|29.62|>": 51845,
+  "<|29.64|>": 51846,
+  "<|29.66|>": 51847,
+  "<|29.68|>": 51848,
+  "<|29.70|>": 51849,
+  "<|29.72|>": 51850,
+  "<|29.74|>": 51851,
+  "<|29.76|>": 51852,
+  "<|29.78|>": 51853,
+  "<|29.80|>": 51854,
+  "<|29.82|>": 51855,
+  "<|29.84|>": 51856,
+  "<|29.86|>": 51857,
+  "<|29.88|>": 51858,
+  "<|29.90|>": 51859,
+  "<|29.92|>": 51860,
+  "<|29.94|>": 51861,
+  "<|29.96|>": 51862,
+  "<|29.98|>": 51863,
+  "<|3.00|>": 50514,
+  "<|3.02|>": 50515,
+  "<|3.04|>": 50516,
+  "<|3.06|>": 50517,
+  "<|3.08|>": 50518,
+  "<|3.10|>": 50519,
+  "<|3.12|>": 50520,
+  "<|3.14|>": 50521,
+  "<|3.16|>": 50522,
+  "<|3.18|>": 50523,
+  "<|3.20|>": 50524,
+  "<|3.22|>": 50525,
+  "<|3.24|>": 50526,
+  "<|3.26|>": 50527,
+  "<|3.28|>": 50528,
+  "<|3.30|>": 50529,
+  "<|3.32|>": 50530,
+  "<|3.34|>": 50531,
+  "<|3.36|>": 50532,
+  "<|3.38|>": 50533,
+  "<|3.40|>": 50534,
+  "<|3.42|>": 50535,
+  "<|3.44|>": 50536,
+  "<|3.46|>": 50537,
+  "<|3.48|>": 50538,
+  "<|3.50|>": 50539,
+  "<|3.52|>": 50540,
+  "<|3.54|>": 50541,
+  "<|3.56|>": 50542,
+  "<|3.58|>": 50543,
+  "<|3.60|>": 50544,
+  "<|3.62|>": 50545,
+  "<|3.64|>": 50546,
+  "<|3.66|>": 50547,
+  "<|3.68|>": 50548,
+  "<|3.70|>": 50549,
+  "<|3.72|>": 50550,
+  "<|3.74|>": 50551,
+  "<|3.76|>": 50552,
+  "<|3.78|>": 50553,
+  "<|3.80|>": 50554,
+  "<|3.82|>": 50555,
+  "<|3.84|>": 50556,
+  "<|3.86|>": 50557,
+  "<|3.88|>": 50558,
+  "<|3.90|>": 50559,
+  "<|3.92|>": 50560,
+  "<|3.94|>": 50561,
+  "<|3.96|>": 50562,
+  "<|3.98|>": 50563,
+  "<|30.00|>": 51864,
+  "<|4.00|>": 50564,
+  "<|4.02|>": 50565,
+  "<|4.04|>": 50566,
+  "<|4.06|>": 50567,
+  "<|4.08|>": 50568,
+  "<|4.10|>": 50569,
+  "<|4.12|>": 50570,
+  "<|4.14|>": 50571,
+  "<|4.16|>": 50572,
+  "<|4.18|>": 50573,
+  "<|4.20|>": 50574,
+  "<|4.22|>": 50575,
+  "<|4.24|>": 50576,
+  "<|4.26|>": 50577,
+  "<|4.28|>": 50578,
+  "<|4.30|>": 50579,
+  "<|4.32|>": 50580,
+  "<|4.34|>": 50581,
+  "<|4.36|>": 50582,
+  "<|4.38|>": 50583,
+  "<|4.40|>": 50584,
+  "<|4.42|>": 50585,
+  "<|4.44|>": 50586,
+  "<|4.46|>": 50587,
+  "<|4.48|>": 50588,
+  "<|4.50|>": 50589,
+  "<|4.52|>": 50590,
+  "<|4.54|>": 50591,
+  "<|4.56|>": 50592,
+  "<|4.58|>": 50593,
+  "<|4.60|>": 50594,
+  "<|4.62|>": 50595,
+  "<|4.64|>": 50596,
+  "<|4.66|>": 50597,
+  "<|4.68|>": 50598,
+  "<|4.70|>": 50599,
+  "<|4.72|>": 50600,
+  "<|4.74|>": 50601,
+  "<|4.76|>": 50602,
+  "<|4.78|>": 50603,
+  "<|4.80|>": 50604,
+  "<|4.82|>": 50605,
+  "<|4.84|>": 50606,
+  "<|4.86|>": 50607,
+  "<|4.88|>": 50608,
+  "<|4.90|>": 50609,
+  "<|4.92|>": 50610,
+  "<|4.94|>": 50611,
+  "<|4.96|>": 50612,
+  "<|4.98|>": 50613,
+  "<|5.00|>": 50614,
+  "<|5.02|>": 50615,
+  "<|5.04|>": 50616,
+  "<|5.06|>": 50617,
+  "<|5.08|>": 50618,
+  "<|5.10|>": 50619,
+  "<|5.12|>": 50620,
+  "<|5.14|>": 50621,
+  "<|5.16|>": 50622,
+  "<|5.18|>": 50623,
+  "<|5.20|>": 50624,
+  "<|5.22|>": 50625,
+  "<|5.24|>": 50626,
+  "<|5.26|>": 50627,
+  "<|5.28|>": 50628,
+  "<|5.30|>": 50629,
+  "<|5.32|>": 50630,
+  "<|5.34|>": 50631,
+  "<|5.36|>": 50632,
+  "<|5.38|>": 50633,
+  "<|5.40|>": 50634,
+  "<|5.42|>": 50635,
+  "<|5.44|>": 50636,
+  "<|5.46|>": 50637,
+  "<|5.48|>": 50638,
+  "<|5.50|>": 50639,
+  "<|5.52|>": 50640,
+  "<|5.54|>": 50641,
+  "<|5.56|>": 50642,
+  "<|5.58|>": 50643,
+  "<|5.60|>": 50644,
+  "<|5.62|>": 50645,
+  "<|5.64|>": 50646,
+  "<|5.66|>": 50647,
+  "<|5.68|>": 50648,
+  "<|5.70|>": 50649,
+  "<|5.72|>": 50650,
+  "<|5.74|>": 50651,
+  "<|5.76|>": 50652,
+  "<|5.78|>": 50653,
+  "<|5.80|>": 50654,
+  "<|5.82|>": 50655,
+  "<|5.84|>": 50656,
+  "<|5.86|>": 50657,
+  "<|5.88|>": 50658,
+  "<|5.90|>": 50659,
+  "<|5.92|>": 50660,
+  "<|5.94|>": 50661,
+  "<|5.96|>": 50662,
+  "<|5.98|>": 50663,
+  "<|6.00|>": 50664,
+  "<|6.02|>": 50665,
+  "<|6.04|>": 50666,
+  "<|6.06|>": 50667,
+  "<|6.08|>": 50668,
+  "<|6.10|>": 50669,
+  "<|6.12|>": 50670,
+  "<|6.14|>": 50671,
+  "<|6.16|>": 50672,
+  "<|6.18|>": 50673,
+  "<|6.20|>": 50674,
+  "<|6.22|>": 50675,
+  "<|6.24|>": 50676,
+  "<|6.26|>": 50677,
+  "<|6.28|>": 50678,
+  "<|6.30|>": 50679,
+  "<|6.32|>": 50680,
+  "<|6.34|>": 50681,
+  "<|6.36|>": 50682,
+  "<|6.38|>": 50683,
+  "<|6.40|>": 50684,
+  "<|6.42|>": 50685,
+  "<|6.44|>": 50686,
+  "<|6.46|>": 50687,
+  "<|6.48|>": 50688,
+  "<|6.50|>": 50689,
+  "<|6.52|>": 50690,
+  "<|6.54|>": 50691,
+  "<|6.56|>": 50692,
+  "<|6.58|>": 50693,
+  "<|6.60|>": 50694,
+  "<|6.62|>": 50695,
+  "<|6.64|>": 50696,
+  "<|6.66|>": 50697,
+  "<|6.68|>": 50698,
+  "<|6.70|>": 50699,
+  "<|6.72|>": 50700,
+  "<|6.74|>": 50701,
+  "<|6.76|>": 50702,
+  "<|6.78|>": 50703,
+  "<|6.80|>": 50704,
+  "<|6.82|>": 50705,
+  "<|6.84|>": 50706,
+  "<|6.86|>": 50707,
+  "<|6.88|>": 50708,
+  "<|6.90|>": 50709,
+  "<|6.92|>": 50710,
+  "<|6.94|>": 50711,
+  "<|6.96|>": 50712,
+  "<|6.98|>": 50713,
+  "<|7.00|>": 50714,
+  "<|7.02|>": 50715,
+  "<|7.04|>": 50716,
+  "<|7.06|>": 50717,
+  "<|7.08|>": 50718,
+  "<|7.10|>": 50719,
+  "<|7.12|>": 50720,
+  "<|7.14|>": 50721,
+  "<|7.16|>": 50722,
+  "<|7.18|>": 50723,
+  "<|7.20|>": 50724,
+  "<|7.22|>": 50725,
+  "<|7.24|>": 50726,
+  "<|7.26|>": 50727,
+  "<|7.28|>": 50728,
+  "<|7.30|>": 50729,
+  "<|7.32|>": 50730,
+  "<|7.34|>": 50731,
+  "<|7.36|>": 50732,
+  "<|7.38|>": 50733,
+  "<|7.40|>": 50734,
+  "<|7.42|>": 50735,
+  "<|7.44|>": 50736,
+  "<|7.46|>": 50737,
+  "<|7.48|>": 50738,
+  "<|7.50|>": 50739,
+  "<|7.52|>": 50740,
+  "<|7.54|>": 50741,
+  "<|7.56|>": 50742,
+  "<|7.58|>": 50743,
+  "<|7.60|>": 50744,
+  "<|7.62|>": 50745,
+  "<|7.64|>": 50746,
+  "<|7.66|>": 50747,
+  "<|7.68|>": 50748,
+  "<|7.70|>": 50749,
+  "<|7.72|>": 50750,
+  "<|7.74|>": 50751,
+  "<|7.76|>": 50752,
+  "<|7.78|>": 50753,
+  "<|7.80|>": 50754,
+  "<|7.82|>": 50755,
+  "<|7.84|>": 50756,
+  "<|7.86|>": 50757,
+  "<|7.88|>": 50758,
+  "<|7.90|>": 50759,
+  "<|7.92|>": 50760,
+  "<|7.94|>": 50761,
+  "<|7.96|>": 50762,
+  "<|7.98|>": 50763,
+  "<|8.00|>": 50764,
+  "<|8.02|>": 50765,
+  "<|8.04|>": 50766,
+  "<|8.06|>": 50767,
+  "<|8.08|>": 50768,
+  "<|8.10|>": 50769,
+  "<|8.12|>": 50770,
+  "<|8.14|>": 50771,
+  "<|8.16|>": 50772,
+  "<|8.18|>": 50773,
+  "<|8.20|>": 50774,
+  "<|8.22|>": 50775,
+  "<|8.24|>": 50776,
+  "<|8.26|>": 50777,
+  "<|8.28|>": 50778,
+  "<|8.30|>": 50779,
+  "<|8.32|>": 50780,
+  "<|8.34|>": 50781,
+  "<|8.36|>": 50782,
+  "<|8.38|>": 50783,
+  "<|8.40|>": 50784,
+  "<|8.42|>": 50785,
+  "<|8.44|>": 50786,
+  "<|8.46|>": 50787,
+  "<|8.48|>": 50788,
+  "<|8.50|>": 50789,
+  "<|8.52|>": 50790,
+  "<|8.54|>": 50791,
+  "<|8.56|>": 50792,
+  "<|8.58|>": 50793,
+  "<|8.60|>": 50794,
+  "<|8.62|>": 50795,
+  "<|8.64|>": 50796,
+  "<|8.66|>": 50797,
+  "<|8.68|>": 50798,
+  "<|8.70|>": 50799,
+  "<|8.72|>": 50800,
+  "<|8.74|>": 50801,
+  "<|8.76|>": 50802,
+  "<|8.78|>": 50803,
+  "<|8.80|>": 50804,
+  "<|8.82|>": 50805,
+  "<|8.84|>": 50806,
+  "<|8.86|>": 50807,
+  "<|8.88|>": 50808,
+  "<|8.90|>": 50809,
+  "<|8.92|>": 50810,
+  "<|8.94|>": 50811,
+  "<|8.96|>": 50812,
+  "<|8.98|>": 50813,
+  "<|9.00|>": 50814,
+  "<|9.02|>": 50815,
+  "<|9.04|>": 50816,
+  "<|9.06|>": 50817,
+  "<|9.08|>": 50818,
+  "<|9.10|>": 50819,
+  "<|9.12|>": 50820,
+  "<|9.14|>": 50821,
+  "<|9.16|>": 50822,
+  "<|9.18|>": 50823,
+  "<|9.20|>": 50824,
+  "<|9.22|>": 50825,
+  "<|9.24|>": 50826,
+  "<|9.26|>": 50827,
+  "<|9.28|>": 50828,
+  "<|9.30|>": 50829,
+  "<|9.32|>": 50830,
+  "<|9.34|>": 50831,
+  "<|9.36|>": 50832,
+  "<|9.38|>": 50833,
+  "<|9.40|>": 50834,
+  "<|9.42|>": 50835,
+  "<|9.44|>": 50836,
+  "<|9.46|>": 50837,
+  "<|9.48|>": 50838,
+  "<|9.50|>": 50839,
+  "<|9.52|>": 50840,
+  "<|9.54|>": 50841,
+  "<|9.56|>": 50842,
+  "<|9.58|>": 50843,
+  "<|9.60|>": 50844,
+  "<|9.62|>": 50845,
+  "<|9.64|>": 50846,
+  "<|9.66|>": 50847,
+  "<|9.68|>": 50848,
+  "<|9.70|>": 50849,
+  "<|9.72|>": 50850,
+  "<|9.74|>": 50851,
+  "<|9.76|>": 50852,
+  "<|9.78|>": 50853,
+  "<|9.80|>": 50854,
+  "<|9.82|>": 50855,
+  "<|9.84|>": 50856,
+  "<|9.86|>": 50857,
+  "<|9.88|>": 50858,
+  "<|9.90|>": 50859,
+  "<|9.92|>": 50860,
+  "<|9.94|>": 50861,
+  "<|9.96|>": 50862,
+  "<|9.98|>": 50863,
+  "<|af|>": 50327,
+  "<|am|>": 50334,
+  "<|ar|>": 50272,
+  "<|as|>": 50350,
+  "<|az|>": 50304,
+  "<|ba|>": 50355,
+  "<|be|>": 50330,
+  "<|bg|>": 50292,
+  "<|bn|>": 50302,
+  "<|bo|>": 50347,
+  "<|br|>": 50309,
+  "<|bs|>": 50315,
+  "<|ca|>": 50270,
+  "<|cs|>": 50283,
+  "<|cy|>": 50297,
+  "<|da|>": 50285,
+  "<|de|>": 50261,
+  "<|el|>": 50281,
+  "<|en|>": 50259,
+  "<|es|>": 50262,
+  "<|et|>": 50307,
+  "<|eu|>": 50310,
+  "<|fa|>": 50300,
+  "<|fi|>": 50277,
+  "<|fo|>": 50338,
+  "<|fr|>": 50265,
+  "<|gl|>": 50319,
+  "<|gu|>": 50333,
+  "<|haw|>": 50352,
+  "<|ha|>": 50354,
+  "<|he|>": 50279,
+  "<|hi|>": 50276,
+  "<|hr|>": 50291,
+  "<|ht|>": 50339,
+  "<|hu|>": 50286,
+  "<|hy|>": 50312,
+  "<|id|>": 50275,
+  "<|is|>": 50311,
+  "<|it|>": 50274,
+  "<|ja|>": 50266,
+  "<|jw|>": 50356,
+  "<|ka|>": 50329,
+  "<|kk|>": 50316,
+  "<|km|>": 50323,
+  "<|kn|>": 50306,
+  "<|ko|>": 50264,
+  "<|la|>": 50294,
+  "<|lb|>": 50345,
+  "<|ln|>": 50353,
+  "<|lo|>": 50336,
+  "<|lt|>": 50293,
+  "<|lv|>": 50301,
+  "<|mg|>": 50349,
+  "<|mi|>": 50295,
+  "<|mk|>": 50308,
+  "<|ml|>": 50296,
+  "<|mn|>": 50314,
+  "<|mr|>": 50320,
+  "<|ms|>": 50282,
+  "<|mt|>": 50343,
+  "<|my|>": 50346,
+  "<|ne|>": 50313,
+  "<|nl|>": 50271,
+  "<|nn|>": 50342,
+  "<|nocaptions|>": 50362,
+  "<|notimestamps|>": 50363,
+  "<|no|>": 50288,
+  "<|oc|>": 50328,
+  "<|pa|>": 50321,
+  "<|pl|>": 50269,
+  "<|ps|>": 50340,
+  "<|pt|>": 50267,
+  "<|ro|>": 50284,
+  "<|ru|>": 50263,
+  "<|sa|>": 50344,
+  "<|sd|>": 50332,
+  "<|si|>": 50322,
+  "<|sk|>": 50298,
+  "<|sl|>": 50305,
+  "<|sn|>": 50324,
+  "<|so|>": 50326,
+  "<|sq|>": 50317,
+  "<|sr|>": 50303,
+  "<|startoflm|>": 50360,
+  "<|startofprev|>": 50361,
+  "<|startoftranscript|>": 50258,
+  "<|su|>": 50357,
+  "<|sv|>": 50273,
+  "<|sw|>": 50318,
+  "<|ta|>": 50287,
+  "<|te|>": 50299,
+  "<|tg|>": 50331,
+  "<|th|>": 50289,
+  "<|tk|>": 50341,
+  "<|tl|>": 50348,
+  "<|transcribe|>": 50359,
+  "<|translate|>": 50358,
+  "<|tr|>": 50268,
+  "<|tt|>": 50351,
+  "<|uk|>": 50280,
+  "<|ur|>": 50290,
+  "<|uz|>": 50337,
+  "<|vi|>": 50278,
+  "<|yi|>": 50335,
+  "<|yo|>": 50325,
+  "<|zh|>": 50260
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 2.368016360865792e+20,
+    "train_loss": 0.13068210890056783,
+    "train_runtime": 7851.6825,
+    "train_samples_per_second": 104.595,
+    "train_steps_per_second": 0.817
+}

checkpoint-1604/config.json

@@ -0,0 +1,60 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "bfloat16",
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50276
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

checkpoint-1604/generation_config.json

@@ -0,0 +1,168 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "language": "hi",
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.57.3"
+}

checkpoint-1604/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d2c6a86c2141d35793f97e9b498e81e327073d4c66bdf92e8f8e46253489850
+size 483525680

checkpoint-1604/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d278e3c5a3b42f6a6ea2898a4b0d2caa4f8a21c240c263e232a08b9417171941
+size 954914801

checkpoint-1604/preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

checkpoint-1604/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ddab86cc1c9f982b5731cb67adda734f9d0a48c4f6c7ac62bfc9b83f6773abf
+size 14645

checkpoint-1604/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2228a6cd4d6deca5e57d8a2a0916c723dc226d1b78c1eb4c6983395cbf91ef5d
+size 1465

checkpoint-1604/trainer_state.json

@@ -0,0 +1,1162 @@
+{
+  "best_global_step": 1604,
+  "best_metric": 0.1406659632921219,
+  "best_model_checkpoint": "/workspace/whisper-finetuning/models/whisper-small-hi-uncurated-reverse-mft-1-1-1/checkpoint-1604",
+  "epoch": 1.0,
+  "eval_steps": 1604,
+  "global_step": 1604,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006234413965087282,
+      "grad_norm": 7.5625,
+      "learning_rate": 1.4018691588785048e-07,
+      "loss": 0.7058,
+      "step": 10
+    },
+    {
+      "epoch": 0.012468827930174564,
+      "grad_norm": 7.6875,
+      "learning_rate": 2.959501557632399e-07,
+      "loss": 0.6474,
+      "step": 20
+    },
+    {
+      "epoch": 0.018703241895261846,
+      "grad_norm": 7.46875,
+      "learning_rate": 4.517133956386293e-07,
+      "loss": 0.656,
+      "step": 30
+    },
+    {
+      "epoch": 0.02493765586034913,
+      "grad_norm": 7.34375,
+      "learning_rate": 6.074766355140187e-07,
+      "loss": 0.6401,
+      "step": 40
+    },
+    {
+      "epoch": 0.03117206982543641,
+      "grad_norm": 7.25,
+      "learning_rate": 7.632398753894081e-07,
+      "loss": 0.6713,
+      "step": 50
+    },
+    {
+      "epoch": 0.03740648379052369,
+      "grad_norm": 7.375,
+      "learning_rate": 9.190031152647975e-07,
+      "loss": 0.6306,
+      "step": 60
+    },
+    {
+      "epoch": 0.043640897755610975,
+      "grad_norm": 7.0,
+      "learning_rate": 1.074766355140187e-06,
+      "loss": 0.6438,
+      "step": 70
+    },
+    {
+      "epoch": 0.04987531172069826,
+      "grad_norm": 8.0,
+      "learning_rate": 1.2305295950155765e-06,
+      "loss": 0.6173,
+      "step": 80
+    },
+    {
+      "epoch": 0.05610972568578554,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.3862928348909658e-06,
+      "loss": 0.5933,
+      "step": 90
+    },
+    {
+      "epoch": 0.06234413965087282,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.542056074766355e-06,
+      "loss": 0.5895,
+      "step": 100
+    },
+    {
+      "epoch": 0.0685785536159601,
+      "grad_norm": 7.90625,
+      "learning_rate": 1.6978193146417446e-06,
+      "loss": 0.5901,
+      "step": 110
+    },
+    {
+      "epoch": 0.07481296758104738,
+      "grad_norm": 7.8125,
+      "learning_rate": 1.8535825545171341e-06,
+      "loss": 0.5616,
+      "step": 120
+    },
+    {
+      "epoch": 0.08104738154613467,
+      "grad_norm": 7.65625,
+      "learning_rate": 2.0093457943925234e-06,
+      "loss": 0.5733,
+      "step": 130
+    },
+    {
+      "epoch": 0.08728179551122195,
+      "grad_norm": 7.75,
+      "learning_rate": 2.165109034267913e-06,
+      "loss": 0.5738,
+      "step": 140
+    },
+    {
+      "epoch": 0.09351620947630923,
+      "grad_norm": 7.09375,
+      "learning_rate": 2.3208722741433024e-06,
+      "loss": 0.574,
+      "step": 150
+    },
+    {
+      "epoch": 0.09975062344139651,
+      "grad_norm": 7.59375,
+      "learning_rate": 2.476635514018692e-06,
+      "loss": 0.5626,
+      "step": 160
+    },
+    {
+      "epoch": 0.1059850374064838,
+      "grad_norm": 7.0,
+      "learning_rate": 2.632398753894081e-06,
+      "loss": 0.5831,
+      "step": 170
+    },
+    {
+      "epoch": 0.11221945137157108,
+      "grad_norm": 7.6875,
+      "learning_rate": 2.7881619937694705e-06,
+      "loss": 0.5733,
+      "step": 180
+    },
+    {
+      "epoch": 0.11845386533665836,
+      "grad_norm": 7.0,
+      "learning_rate": 2.94392523364486e-06,
+      "loss": 0.564,
+      "step": 190
+    },
+    {
+      "epoch": 0.12468827930174564,
+      "grad_norm": 7.4375,
+      "learning_rate": 3.099688473520249e-06,
+      "loss": 0.5558,
+      "step": 200
+    },
+    {
+      "epoch": 0.13092269326683292,
+      "grad_norm": 7.03125,
+      "learning_rate": 3.2554517133956386e-06,
+      "loss": 0.5621,
+      "step": 210
+    },
+    {
+      "epoch": 0.1371571072319202,
+      "grad_norm": 7.4375,
+      "learning_rate": 3.411214953271028e-06,
+      "loss": 0.5494,
+      "step": 220
+    },
+    {
+      "epoch": 0.1433915211970075,
+      "grad_norm": 8.5,
+      "learning_rate": 3.5669781931464176e-06,
+      "loss": 0.529,
+      "step": 230
+    },
+    {
+      "epoch": 0.14962593516209477,
+      "grad_norm": 7.59375,
+      "learning_rate": 3.722741433021807e-06,
+      "loss": 0.4425,
+      "step": 240
+    },
+    {
+      "epoch": 0.15586034912718205,
+      "grad_norm": 3.859375,
+      "learning_rate": 3.878504672897196e-06,
+      "loss": 0.4133,
+      "step": 250
+    },
+    {
+      "epoch": 0.16209476309226933,
+      "grad_norm": 4.78125,
+      "learning_rate": 4.034267912772586e-06,
+      "loss": 0.38,
+      "step": 260
+    },
+    {
+      "epoch": 0.16832917705735662,
+      "grad_norm": 3.25,
+      "learning_rate": 4.190031152647975e-06,
+      "loss": 0.3687,
+      "step": 270
+    },
+    {
+      "epoch": 0.1745635910224439,
+      "grad_norm": 4.34375,
+      "learning_rate": 4.345794392523365e-06,
+      "loss": 0.3483,
+      "step": 280
+    },
+    {
+      "epoch": 0.18079800498753118,
+      "grad_norm": 2.953125,
+      "learning_rate": 4.501557632398754e-06,
+      "loss": 0.313,
+      "step": 290
+    },
+    {
+      "epoch": 0.18703241895261846,
+      "grad_norm": 3.53125,
+      "learning_rate": 4.657320872274144e-06,
+      "loss": 0.3015,
+      "step": 300
+    },
+    {
+      "epoch": 0.19326683291770574,
+      "grad_norm": 2.859375,
+      "learning_rate": 4.813084112149533e-06,
+      "loss": 0.2972,
+      "step": 310
+    },
+    {
+      "epoch": 0.19950124688279303,
+      "grad_norm": 2.734375,
+      "learning_rate": 4.968847352024923e-06,
+      "loss": 0.267,
+      "step": 320
+    },
+    {
+      "epoch": 0.2057356608478803,
+      "grad_norm": 1.71875,
+      "learning_rate": 5.124610591900312e-06,
+      "loss": 0.2438,
+      "step": 330
+    },
+    {
+      "epoch": 0.2119700748129676,
+      "grad_norm": 1.8828125,
+      "learning_rate": 5.280373831775702e-06,
+      "loss": 0.2143,
+      "step": 340
+    },
+    {
+      "epoch": 0.21820448877805487,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.436137071651091e-06,
+      "loss": 0.222,
+      "step": 350
+    },
+    {
+      "epoch": 0.22443890274314215,
+      "grad_norm": 1.6875,
+      "learning_rate": 5.591900311526481e-06,
+      "loss": 0.2028,
+      "step": 360
+    },
+    {
+      "epoch": 0.23067331670822944,
+      "grad_norm": 1.203125,
+      "learning_rate": 5.747663551401869e-06,
+      "loss": 0.2069,
+      "step": 370
+    },
+    {
+      "epoch": 0.23690773067331672,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.903426791277259e-06,
+      "loss": 0.1742,
+      "step": 380
+    },
+    {
+      "epoch": 0.243142144638404,
+      "grad_norm": 1.28125,
+      "learning_rate": 6.059190031152648e-06,
+      "loss": 0.1695,
+      "step": 390
+    },
+    {
+      "epoch": 0.24937655860349128,
+      "grad_norm": 1.4140625,
+      "learning_rate": 6.214953271028038e-06,
+      "loss": 0.1531,
+      "step": 400
+    },
+    {
+      "epoch": 0.25561097256857856,
+      "grad_norm": 1.3359375,
+      "learning_rate": 6.370716510903427e-06,
+      "loss": 0.15,
+      "step": 410
+    },
+    {
+      "epoch": 0.26184538653366585,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.526479750778817e-06,
+      "loss": 0.1335,
+      "step": 420
+    },
+    {
+      "epoch": 0.26807980049875313,
+      "grad_norm": 1.6015625,
+      "learning_rate": 6.682242990654206e-06,
+      "loss": 0.1319,
+      "step": 430
+    },
+    {
+      "epoch": 0.2743142144638404,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.838006230529596e-06,
+      "loss": 0.1324,
+      "step": 440
+    },
+    {
+      "epoch": 0.2805486284289277,
+      "grad_norm": 2.3125,
+      "learning_rate": 6.993769470404985e-06,
+      "loss": 0.1398,
+      "step": 450
+    },
+    {
+      "epoch": 0.286783042394015,
+      "grad_norm": 1.046875,
+      "learning_rate": 7.149532710280375e-06,
+      "loss": 0.1515,
+      "step": 460
+    },
+    {
+      "epoch": 0.29301745635910226,
+      "grad_norm": 1.84375,
+      "learning_rate": 7.305295950155764e-06,
+      "loss": 0.1532,
+      "step": 470
+    },
+    {
+      "epoch": 0.29925187032418954,
+      "grad_norm": 1.1171875,
+      "learning_rate": 7.461059190031154e-06,
+      "loss": 0.1515,
+      "step": 480
+    },
+    {
+      "epoch": 0.3054862842892768,
+      "grad_norm": 2.546875,
+      "learning_rate": 7.616822429906543e-06,
+      "loss": 0.1701,
+      "step": 490
+    },
+    {
+      "epoch": 0.3117206982543641,
+      "grad_norm": 1.171875,
+      "learning_rate": 7.772585669781933e-06,
+      "loss": 0.1711,
+      "step": 500
+    },
+    {
+      "epoch": 0.3179551122194514,
+      "grad_norm": 1.953125,
+      "learning_rate": 7.928348909657322e-06,
+      "loss": 0.1831,
+      "step": 510
+    },
+    {
+      "epoch": 0.32418952618453867,
+      "grad_norm": 1.1484375,
+      "learning_rate": 8.084112149532712e-06,
+      "loss": 0.165,
+      "step": 520
+    },
+    {
+      "epoch": 0.33042394014962595,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.2398753894081e-06,
+      "loss": 0.1688,
+      "step": 530
+    },
+    {
+      "epoch": 0.33665835411471323,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.395638629283491e-06,
+      "loss": 0.1683,
+      "step": 540
+    },
+    {
+      "epoch": 0.3428927680798005,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.55140186915888e-06,
+      "loss": 0.1693,
+      "step": 550
+    },
+    {
+      "epoch": 0.3491271820448878,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.707165109034268e-06,
+      "loss": 0.1761,
+      "step": 560
+    },
+    {
+      "epoch": 0.3553615960099751,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.862928348909659e-06,
+      "loss": 0.1681,
+      "step": 570
+    },
+    {
+      "epoch": 0.36159600997506236,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.018691588785047e-06,
+      "loss": 0.1618,
+      "step": 580
+    },
+    {
+      "epoch": 0.36783042394014964,
+      "grad_norm": 1.2265625,
+      "learning_rate": 9.174454828660438e-06,
+      "loss": 0.1696,
+      "step": 590
+    },
+    {
+      "epoch": 0.3740648379052369,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.330218068535826e-06,
+      "loss": 0.1407,
+      "step": 600
+    },
+    {
+      "epoch": 0.3802992518703242,
+      "grad_norm": 1.140625,
+      "learning_rate": 9.485981308411217e-06,
+      "loss": 0.1569,
+      "step": 610
+    },
+    {
+      "epoch": 0.3865336658354115,
+      "grad_norm": 0.921875,
+      "learning_rate": 9.641744548286605e-06,
+      "loss": 0.1404,
+      "step": 620
+    },
+    {
+      "epoch": 0.39276807980049877,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.797507788161996e-06,
+      "loss": 0.1505,
+      "step": 630
+    },
+    {
+      "epoch": 0.39900249376558605,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.953271028037384e-06,
+      "loss": 0.1205,
+      "step": 640
+    },
+    {
+      "epoch": 0.40523690773067333,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.99996373549532e-06,
+      "loss": 0.1139,
+      "step": 650
+    },
+    {
+      "epoch": 0.4114713216957606,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.999786114697945e-06,
+      "loss": 0.1127,
+      "step": 660
+    },
+    {
+      "epoch": 0.4177057356608479,
+      "grad_norm": 0.8359375,
+      "learning_rate": 9.999460482032132e-06,
+      "loss": 0.1018,
+      "step": 670
+    },
+    {
+      "epoch": 0.4239401496259352,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.998986847137795e-06,
+      "loss": 0.1058,
+      "step": 680
+    },
+    {
+      "epoch": 0.43017456359102246,
+      "grad_norm": 0.68359375,
+      "learning_rate": 9.998365224036252e-06,
+      "loss": 0.0972,
+      "step": 690
+    },
+    {
+      "epoch": 0.43640897755610975,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.997595631129806e-06,
+      "loss": 0.1083,
+      "step": 700
+    },
+    {
+      "epoch": 0.442643391521197,
+      "grad_norm": 3.421875,
+      "learning_rate": 9.996678091201213e-06,
+      "loss": 0.1209,
+      "step": 710
+    },
+    {
+      "epoch": 0.4488778054862843,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.99561263141299e-06,
+      "loss": 0.1233,
+      "step": 720
+    },
+    {
+      "epoch": 0.4551122194513716,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.994399283306628e-06,
+      "loss": 0.1257,
+      "step": 730
+    },
+    {
+      "epoch": 0.4613466334164589,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.993038082801648e-06,
+      "loss": 0.1274,
+      "step": 740
+    },
+    {
+      "epoch": 0.46758104738154616,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.991529070194539e-06,
+      "loss": 0.1228,
+      "step": 750
+    },
+    {
+      "epoch": 0.47381546134663344,
+      "grad_norm": 0.890625,
+      "learning_rate": 9.989872290157566e-06,
+      "loss": 0.1249,
+      "step": 760
+    },
+    {
+      "epoch": 0.4800498753117207,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.988067791737449e-06,
+      "loss": 0.1193,
+      "step": 770
+    },
+    {
+      "epoch": 0.486284289276808,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.986115628353911e-06,
+      "loss": 0.1207,
+      "step": 780
+    },
+    {
+      "epoch": 0.4925187032418953,
+      "grad_norm": 1.125,
+      "learning_rate": 9.984015857798095e-06,
+      "loss": 0.1197,
+      "step": 790
+    },
+    {
+      "epoch": 0.49875311720698257,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.981768542230847e-06,
+      "loss": 0.1325,
+      "step": 800
+    },
+    {
+      "epoch": 0.5049875311720698,
+      "grad_norm": 0.98046875,
+      "learning_rate": 9.979373748180896e-06,
+      "loss": 0.132,
+      "step": 810
+    },
+    {
+      "epoch": 0.5112219451371571,
+      "grad_norm": 0.96484375,
+      "learning_rate": 9.976831546542858e-06,
+      "loss": 0.1356,
+      "step": 820
+    },
+    {
+      "epoch": 0.5174563591022444,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.974142012575156e-06,
+      "loss": 0.1313,
+      "step": 830
+    },
+    {
+      "epoch": 0.5236907730673317,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.971305225897788e-06,
+      "loss": 0.1333,
+      "step": 840
+    },
+    {
+      "epoch": 0.529925187032419,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.968321270489963e-06,
+      "loss": 0.1247,
+      "step": 850
+    },
+    {
+      "epoch": 0.5361596009975063,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.965190234687622e-06,
+      "loss": 0.1316,
+      "step": 860
+    },
+    {
+      "epoch": 0.5423940149625935,
+      "grad_norm": 0.625,
+      "learning_rate": 9.961912211180824e-06,
+      "loss": 0.1281,
+      "step": 870
+    },
+    {
+      "epoch": 0.5486284289276808,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.958487297010997e-06,
+      "loss": 0.1346,
+      "step": 880
+    },
+    {
+      "epoch": 0.5548628428927681,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.954915593568066e-06,
+      "loss": 0.1349,
+      "step": 890
+    },
+    {
+      "epoch": 0.5610972568578554,
+      "grad_norm": 1.3828125,
+      "learning_rate": 9.951197206587455e-06,
+      "loss": 0.1319,
+      "step": 900
+    },
+    {
+      "epoch": 0.5673316708229427,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.947332246146952e-06,
+      "loss": 0.1303,
+      "step": 910
+    },
+    {
+      "epoch": 0.57356608478803,
+      "grad_norm": 1.1875,
+      "learning_rate": 9.943320826663458e-06,
+      "loss": 0.1356,
+      "step": 920
+    },
+    {
+      "epoch": 0.5798004987531172,
+      "grad_norm": 0.69921875,
+      "learning_rate": 9.939163066889587e-06,
+      "loss": 0.1324,
+      "step": 930
+    },
+    {
+      "epoch": 0.5860349127182045,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.934859089910167e-06,
+      "loss": 0.1468,
+      "step": 940
+    },
+    {
+      "epoch": 0.5922693266832918,
+      "grad_norm": 0.82421875,
+      "learning_rate": 9.93040902313858e-06,
+      "loss": 0.1377,
+      "step": 950
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "grad_norm": 1.2734375,
+      "learning_rate": 9.925812998313005e-06,
+      "loss": 0.1332,
+      "step": 960
+    },
+    {
+      "epoch": 0.6047381546134664,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.921071151492501e-06,
+      "loss": 0.1382,
+      "step": 970
+    },
+    {
+      "epoch": 0.6109725685785536,
+      "grad_norm": 1.359375,
+      "learning_rate": 9.916183623053e-06,
+      "loss": 0.1419,
+      "step": 980
+    },
+    {
+      "epoch": 0.6172069825436409,
+      "grad_norm": 1.171875,
+      "learning_rate": 9.91115055768313e-06,
+      "loss": 0.1392,
+      "step": 990
+    },
+    {
+      "epoch": 0.6234413965087282,
+      "grad_norm": 1.375,
+      "learning_rate": 9.905972104379948e-06,
+      "loss": 0.1337,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6296758104738155,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.900648416444524e-06,
+      "loss": 0.1244,
+      "step": 1010
+    },
+    {
+      "epoch": 0.6359102244389028,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.895179651477396e-06,
+      "loss": 0.1303,
+      "step": 1020
+    },
+    {
+      "epoch": 0.64214463840399,
+      "grad_norm": 1.0546875,
+      "learning_rate": 9.889565971373916e-06,
+      "loss": 0.1253,
+      "step": 1030
+    },
+    {
+      "epoch": 0.6483790523690773,
+      "grad_norm": 1.78125,
+      "learning_rate": 9.883807542319447e-06,
+      "loss": 0.1274,
+      "step": 1040
+    },
+    {
+      "epoch": 0.6546134663341646,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.877904534784451e-06,
+      "loss": 0.1158,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6608478802992519,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.871857123519439e-06,
+      "loss": 0.1314,
+      "step": 1060
+    },
+    {
+      "epoch": 0.6670822942643392,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.865665487549796e-06,
+      "loss": 0.1236,
+      "step": 1070
+    },
+    {
+      "epoch": 0.6733167082294265,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.859329810170487e-06,
+      "loss": 0.1344,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6795511221945137,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.85285027894062e-06,
+      "loss": 0.1185,
+      "step": 1090
+    },
+    {
+      "epoch": 0.685785536159601,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.846227085677909e-06,
+      "loss": 0.1348,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6920199501246883,
+      "grad_norm": 1.21875,
+      "learning_rate": 9.83946042645298e-06,
+      "loss": 0.1302,
+      "step": 1110
+    },
+    {
+      "epoch": 0.6982543640897756,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.832550501583582e-06,
+      "loss": 0.1501,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7044887780548629,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.82549751562864e-06,
+      "loss": 0.1474,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7107231920199502,
+      "grad_norm": 1.75,
+      "learning_rate": 9.818301677382212e-06,
+      "loss": 0.1688,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7169576059850374,
+      "grad_norm": 2.46875,
+      "learning_rate": 9.810963199867302e-06,
+      "loss": 0.1695,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7231920199501247,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.80348230032956e-06,
+      "loss": 0.1561,
+      "step": 1160
+    },
+    {
+      "epoch": 0.729426433915212,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.79585920023084e-06,
+      "loss": 0.1424,
+      "step": 1170
+    },
+    {
+      "epoch": 0.7356608478802993,
+      "grad_norm": 1.375,
+      "learning_rate": 9.788094125242655e-06,
+      "loss": 0.154,
+      "step": 1180
+    },
+    {
+      "epoch": 0.7418952618453866,
+      "grad_norm": 1.125,
+      "learning_rate": 9.780187305239491e-06,
+      "loss": 0.1447,
+      "step": 1190
+    },
+    {
+      "epoch": 0.7481296758104738,
+      "grad_norm": 1.2890625,
+      "learning_rate": 9.772138974291999e-06,
+      "loss": 0.1364,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7543640897755611,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.763949370660072e-06,
+      "loss": 0.1317,
+      "step": 1210
+    },
+    {
+      "epoch": 0.7605985037406484,
+      "grad_norm": 1.875,
+      "learning_rate": 9.755618736785786e-06,
+      "loss": 0.1438,
+      "step": 1220
+    },
+    {
+      "epoch": 0.7668329177057357,
+      "grad_norm": 0.84765625,
+      "learning_rate": 9.747147319286232e-06,
+      "loss": 0.1186,
+      "step": 1230
+    },
+    {
+      "epoch": 0.773067331670823,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.738535368946202e-06,
+      "loss": 0.1271,
+      "step": 1240
+    },
+    {
+      "epoch": 0.7793017456359103,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.729783140710773e-06,
+      "loss": 0.113,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7855361596009975,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.72089089367776e-06,
+      "loss": 0.1232,
+      "step": 1260
+    },
+    {
+      "epoch": 0.7917705735660848,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.711858891090044e-06,
+      "loss": 0.1098,
+      "step": 1270
+    },
+    {
+      "epoch": 0.7980049875311721,
+      "grad_norm": 1.3515625,
+      "learning_rate": 9.70268740032778e-06,
+      "loss": 0.1112,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8042394014962594,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.693376692900476e-06,
+      "loss": 0.1112,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8104738154613467,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.683927044438963e-06,
+      "loss": 0.1076,
+      "step": 1300
+    },
+    {
+      "epoch": 0.816708229426434,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.674338734687236e-06,
+      "loss": 0.1102,
+      "step": 1310
+    },
+    {
+      "epoch": 0.8229426433915212,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.664612047494162e-06,
+      "loss": 0.1079,
+      "step": 1320
+    },
+    {
+      "epoch": 0.8291770573566085,
+      "grad_norm": 0.8359375,
+      "learning_rate": 9.65474727080509e-06,
+      "loss": 0.1145,
+      "step": 1330
+    },
+    {
+      "epoch": 0.8354114713216958,
+      "grad_norm": 0.8359375,
+      "learning_rate": 9.644744696653316e-06,
+      "loss": 0.1086,
+      "step": 1340
+    },
+    {
+      "epoch": 0.8416458852867831,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.63460462115145e-06,
+      "loss": 0.118,
+      "step": 1350
+    },
+    {
+      "epoch": 0.8478802992518704,
+      "grad_norm": 0.75,
+      "learning_rate": 9.624327344482629e-06,
+      "loss": 0.1165,
+      "step": 1360
+    },
+    {
+      "epoch": 0.8541147132169576,
+      "grad_norm": 0.96484375,
+      "learning_rate": 9.613913170891659e-06,
+      "loss": 0.1176,
+      "step": 1370
+    },
+    {
+      "epoch": 0.8603491271820449,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.60336240867598e-06,
+      "loss": 0.1108,
+      "step": 1380
+    },
+    {
+      "epoch": 0.8665835411471322,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.592675370176565e-06,
+      "loss": 0.1124,
+      "step": 1390
+    },
+    {
+      "epoch": 0.8728179551122195,
+      "grad_norm": 0.67578125,
+      "learning_rate": 9.581852371768652e-06,
+      "loss": 0.1032,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8790523690773068,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.57089373385239e-06,
+      "loss": 0.1003,
+      "step": 1410
+    },
+    {
+      "epoch": 0.885286783042394,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.559799780843353e-06,
+      "loss": 0.0995,
+      "step": 1420
+    },
+    {
+      "epoch": 0.8915211970074813,
+      "grad_norm": 0.828125,
+      "learning_rate": 9.548570841162931e-06,
+      "loss": 0.0949,
+      "step": 1430
+    },
+    {
+      "epoch": 0.8977556109725686,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.537207247228612e-06,
+      "loss": 0.0989,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9039900249376559,
+      "grad_norm": 0.71484375,
+      "learning_rate": 9.525709335444142e-06,
+      "loss": 0.0936,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9102244389027432,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.51407744618956e-06,
+      "loss": 0.0871,
+      "step": 1460
+    },
+    {
+      "epoch": 0.9164588528678305,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.502311923811131e-06,
+      "loss": 0.1,
+      "step": 1470
+    },
+    {
+      "epoch": 0.9226932668329177,
+      "grad_norm": 0.6953125,
+      "learning_rate": 9.490413116611143e-06,
+      "loss": 0.0937,
+      "step": 1480
+    },
+    {
+      "epoch": 0.928927680798005,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.478381376837603e-06,
+      "loss": 0.0932,
+      "step": 1490
+    },
+    {
+      "epoch": 0.9351620947630923,
+      "grad_norm": 0.546875,
+      "learning_rate": 9.466217060673804e-06,
+      "loss": 0.0945,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9413965087281796,
+      "grad_norm": 1.0,
+      "learning_rate": 9.45392052822778e-06,
+      "loss": 0.1,
+      "step": 1510
+    },
+    {
+      "epoch": 0.9476309226932669,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.441492143521656e-06,
+      "loss": 0.0973,
+      "step": 1520
+    },
+    {
+      "epoch": 0.9538653366583542,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.428932274480855e-06,
+      "loss": 0.1023,
+      "step": 1530
+    },
+    {
+      "epoch": 0.9600997506234414,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.416241292923223e-06,
+      "loss": 0.0997,
+      "step": 1540
+    },
+    {
+      "epoch": 0.9663341645885287,
+      "grad_norm": 0.8671875,
+      "learning_rate": 9.403419574548007e-06,
+      "loss": 0.1,
+      "step": 1550
+    },
+    {
+      "epoch": 0.972568578553616,
+      "grad_norm": 0.9765625,
+      "learning_rate": 9.390467498924745e-06,
+      "loss": 0.1077,
+      "step": 1560
+    },
+    {
+      "epoch": 0.9788029925187033,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.377385449482018e-06,
+      "loss": 0.1115,
+      "step": 1570
+    },
+    {
+      "epoch": 0.9850374064837906,
+      "grad_norm": 1.203125,
+      "learning_rate": 9.36417381349611e-06,
+      "loss": 0.1176,
+      "step": 1580
+    },
+    {
+      "epoch": 0.9912718204488778,
+      "grad_norm": 1.3125,
+      "learning_rate": 9.35083298207954e-06,
+      "loss": 0.1207,
+      "step": 1590
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.337363350169475e-06,
+      "loss": 0.1157,
+      "step": 1600
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1406659632921219,
+      "eval_runtime": 575.0322,
+      "eval_samples_per_second": 12.749,
+      "eval_steps_per_second": 0.798,
+      "step": 1604
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6416,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 1604,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.92004090216448e+19,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1604/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf798d7f5818756a03915c5bc6b925db9c5083056b25bf0861802b46be39289d
+size 6161

checkpoint-3208/config.json

@@ -0,0 +1,60 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "bfloat16",
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50276
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

checkpoint-3208/generation_config.json

@@ -0,0 +1,168 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "language": "hi",
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.57.3"
+}

checkpoint-3208/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3321955db79144f9da70aebadfcbc64cb2917896459857b0b8d08583315a08bd
+size 483525680

checkpoint-3208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b590524c6d02cebeef5cada69ce6253dcc0a6a4c39e25755bbee1adb987bf797
+size 954914801

checkpoint-3208/preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

checkpoint-3208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa00815e7b7f22f2e420286552742444c704853e04694a55c1465d652ab21e2
+size 14645

checkpoint-3208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e0c7ef4437eb47f99e6e95c85e7d7db0d0e78f495e9d96b96b9ef21165ad34
+size 1465

checkpoint-3208/trainer_state.json

@@ -0,0 +1,2290 @@
+{
+  "best_global_step": 3208,
+  "best_metric": 0.13248766958713531,
+  "best_model_checkpoint": "/workspace/whisper-finetuning/models/whisper-small-hi-uncurated-reverse-mft-1-1-1/checkpoint-3208",
+  "epoch": 2.0,
+  "eval_steps": 1604,
+  "global_step": 3208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006234413965087282,
+      "grad_norm": 7.5625,
+      "learning_rate": 1.4018691588785048e-07,
+      "loss": 0.7058,
+      "step": 10
+    },
+    {
+      "epoch": 0.012468827930174564,
+      "grad_norm": 7.6875,
+      "learning_rate": 2.959501557632399e-07,
+      "loss": 0.6474,
+      "step": 20
+    },
+    {
+      "epoch": 0.018703241895261846,
+      "grad_norm": 7.46875,
+      "learning_rate": 4.517133956386293e-07,
+      "loss": 0.656,
+      "step": 30
+    },
+    {
+      "epoch": 0.02493765586034913,
+      "grad_norm": 7.34375,
+      "learning_rate": 6.074766355140187e-07,
+      "loss": 0.6401,
+      "step": 40
+    },
+    {
+      "epoch": 0.03117206982543641,
+      "grad_norm": 7.25,
+      "learning_rate": 7.632398753894081e-07,
+      "loss": 0.6713,
+      "step": 50
+    },
+    {
+      "epoch": 0.03740648379052369,
+      "grad_norm": 7.375,
+      "learning_rate": 9.190031152647975e-07,
+      "loss": 0.6306,
+      "step": 60
+    },
+    {
+      "epoch": 0.043640897755610975,
+      "grad_norm": 7.0,
+      "learning_rate": 1.074766355140187e-06,
+      "loss": 0.6438,
+      "step": 70
+    },
+    {
+      "epoch": 0.04987531172069826,
+      "grad_norm": 8.0,
+      "learning_rate": 1.2305295950155765e-06,
+      "loss": 0.6173,
+      "step": 80
+    },
+    {
+      "epoch": 0.05610972568578554,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.3862928348909658e-06,
+      "loss": 0.5933,
+      "step": 90
+    },
+    {
+      "epoch": 0.06234413965087282,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.542056074766355e-06,
+      "loss": 0.5895,
+      "step": 100
+    },
+    {
+      "epoch": 0.0685785536159601,
+      "grad_norm": 7.90625,
+      "learning_rate": 1.6978193146417446e-06,
+      "loss": 0.5901,
+      "step": 110
+    },
+    {
+      "epoch": 0.07481296758104738,
+      "grad_norm": 7.8125,
+      "learning_rate": 1.8535825545171341e-06,
+      "loss": 0.5616,
+      "step": 120
+    },
+    {
+      "epoch": 0.08104738154613467,
+      "grad_norm": 7.65625,
+      "learning_rate": 2.0093457943925234e-06,
+      "loss": 0.5733,
+      "step": 130
+    },
+    {
+      "epoch": 0.08728179551122195,
+      "grad_norm": 7.75,
+      "learning_rate": 2.165109034267913e-06,
+      "loss": 0.5738,
+      "step": 140
+    },
+    {
+      "epoch": 0.09351620947630923,
+      "grad_norm": 7.09375,
+      "learning_rate": 2.3208722741433024e-06,
+      "loss": 0.574,
+      "step": 150
+    },
+    {
+      "epoch": 0.09975062344139651,
+      "grad_norm": 7.59375,
+      "learning_rate": 2.476635514018692e-06,
+      "loss": 0.5626,
+      "step": 160
+    },
+    {
+      "epoch": 0.1059850374064838,
+      "grad_norm": 7.0,
+      "learning_rate": 2.632398753894081e-06,
+      "loss": 0.5831,
+      "step": 170
+    },
+    {
+      "epoch": 0.11221945137157108,
+      "grad_norm": 7.6875,
+      "learning_rate": 2.7881619937694705e-06,
+      "loss": 0.5733,
+      "step": 180
+    },
+    {
+      "epoch": 0.11845386533665836,
+      "grad_norm": 7.0,
+      "learning_rate": 2.94392523364486e-06,
+      "loss": 0.564,
+      "step": 190
+    },
+    {
+      "epoch": 0.12468827930174564,
+      "grad_norm": 7.4375,
+      "learning_rate": 3.099688473520249e-06,
+      "loss": 0.5558,
+      "step": 200
+    },
+    {
+      "epoch": 0.13092269326683292,
+      "grad_norm": 7.03125,
+      "learning_rate": 3.2554517133956386e-06,
+      "loss": 0.5621,
+      "step": 210
+    },
+    {
+      "epoch": 0.1371571072319202,
+      "grad_norm": 7.4375,
+      "learning_rate": 3.411214953271028e-06,
+      "loss": 0.5494,
+      "step": 220
+    },
+    {
+      "epoch": 0.1433915211970075,
+      "grad_norm": 8.5,
+      "learning_rate": 3.5669781931464176e-06,
+      "loss": 0.529,
+      "step": 230
+    },
+    {
+      "epoch": 0.14962593516209477,
+      "grad_norm": 7.59375,
+      "learning_rate": 3.722741433021807e-06,
+      "loss": 0.4425,
+      "step": 240
+    },
+    {
+      "epoch": 0.15586034912718205,
+      "grad_norm": 3.859375,
+      "learning_rate": 3.878504672897196e-06,
+      "loss": 0.4133,
+      "step": 250
+    },
+    {
+      "epoch": 0.16209476309226933,
+      "grad_norm": 4.78125,
+      "learning_rate": 4.034267912772586e-06,
+      "loss": 0.38,
+      "step": 260
+    },
+    {
+      "epoch": 0.16832917705735662,
+      "grad_norm": 3.25,
+      "learning_rate": 4.190031152647975e-06,
+      "loss": 0.3687,
+      "step": 270
+    },
+    {
+      "epoch": 0.1745635910224439,
+      "grad_norm": 4.34375,
+      "learning_rate": 4.345794392523365e-06,
+      "loss": 0.3483,
+      "step": 280
+    },
+    {
+      "epoch": 0.18079800498753118,
+      "grad_norm": 2.953125,
+      "learning_rate": 4.501557632398754e-06,
+      "loss": 0.313,
+      "step": 290
+    },
+    {
+      "epoch": 0.18703241895261846,
+      "grad_norm": 3.53125,
+      "learning_rate": 4.657320872274144e-06,
+      "loss": 0.3015,
+      "step": 300
+    },
+    {
+      "epoch": 0.19326683291770574,
+      "grad_norm": 2.859375,
+      "learning_rate": 4.813084112149533e-06,
+      "loss": 0.2972,
+      "step": 310
+    },
+    {
+      "epoch": 0.19950124688279303,
+      "grad_norm": 2.734375,
+      "learning_rate": 4.968847352024923e-06,
+      "loss": 0.267,
+      "step": 320
+    },
+    {
+      "epoch": 0.2057356608478803,
+      "grad_norm": 1.71875,
+      "learning_rate": 5.124610591900312e-06,
+      "loss": 0.2438,
+      "step": 330
+    },
+    {
+      "epoch": 0.2119700748129676,
+      "grad_norm": 1.8828125,
+      "learning_rate": 5.280373831775702e-06,
+      "loss": 0.2143,
+      "step": 340
+    },
+    {
+      "epoch": 0.21820448877805487,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.436137071651091e-06,
+      "loss": 0.222,
+      "step": 350
+    },
+    {
+      "epoch": 0.22443890274314215,
+      "grad_norm": 1.6875,
+      "learning_rate": 5.591900311526481e-06,
+      "loss": 0.2028,
+      "step": 360
+    },
+    {
+      "epoch": 0.23067331670822944,
+      "grad_norm": 1.203125,
+      "learning_rate": 5.747663551401869e-06,
+      "loss": 0.2069,
+      "step": 370
+    },
+    {
+      "epoch": 0.23690773067331672,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.903426791277259e-06,
+      "loss": 0.1742,
+      "step": 380
+    },
+    {
+      "epoch": 0.243142144638404,
+      "grad_norm": 1.28125,
+      "learning_rate": 6.059190031152648e-06,
+      "loss": 0.1695,
+      "step": 390
+    },
+    {
+      "epoch": 0.24937655860349128,
+      "grad_norm": 1.4140625,
+      "learning_rate": 6.214953271028038e-06,
+      "loss": 0.1531,
+      "step": 400
+    },
+    {
+      "epoch": 0.25561097256857856,
+      "grad_norm": 1.3359375,
+      "learning_rate": 6.370716510903427e-06,
+      "loss": 0.15,
+      "step": 410
+    },
+    {
+      "epoch": 0.26184538653366585,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.526479750778817e-06,
+      "loss": 0.1335,
+      "step": 420
+    },
+    {
+      "epoch": 0.26807980049875313,
+      "grad_norm": 1.6015625,
+      "learning_rate": 6.682242990654206e-06,
+      "loss": 0.1319,
+      "step": 430
+    },
+    {
+      "epoch": 0.2743142144638404,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.838006230529596e-06,
+      "loss": 0.1324,
+      "step": 440
+    },
+    {
+      "epoch": 0.2805486284289277,
+      "grad_norm": 2.3125,
+      "learning_rate": 6.993769470404985e-06,
+      "loss": 0.1398,
+      "step": 450
+    },
+    {
+      "epoch": 0.286783042394015,
+      "grad_norm": 1.046875,
+      "learning_rate": 7.149532710280375e-06,
+      "loss": 0.1515,
+      "step": 460
+    },
+    {
+      "epoch": 0.29301745635910226,
+      "grad_norm": 1.84375,
+      "learning_rate": 7.305295950155764e-06,
+      "loss": 0.1532,
+      "step": 470
+    },
+    {
+      "epoch": 0.29925187032418954,
+      "grad_norm": 1.1171875,
+      "learning_rate": 7.461059190031154e-06,
+      "loss": 0.1515,
+      "step": 480
+    },
+    {
+      "epoch": 0.3054862842892768,
+      "grad_norm": 2.546875,
+      "learning_rate": 7.616822429906543e-06,
+      "loss": 0.1701,
+      "step": 490
+    },
+    {
+      "epoch": 0.3117206982543641,
+      "grad_norm": 1.171875,
+      "learning_rate": 7.772585669781933e-06,
+      "loss": 0.1711,
+      "step": 500
+    },
+    {
+      "epoch": 0.3179551122194514,
+      "grad_norm": 1.953125,
+      "learning_rate": 7.928348909657322e-06,
+      "loss": 0.1831,
+      "step": 510
+    },
+    {
+      "epoch": 0.32418952618453867,
+      "grad_norm": 1.1484375,
+      "learning_rate": 8.084112149532712e-06,
+      "loss": 0.165,
+      "step": 520
+    },
+    {
+      "epoch": 0.33042394014962595,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.2398753894081e-06,
+      "loss": 0.1688,
+      "step": 530
+    },
+    {
+      "epoch": 0.33665835411471323,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.395638629283491e-06,
+      "loss": 0.1683,
+      "step": 540
+    },
+    {
+      "epoch": 0.3428927680798005,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.55140186915888e-06,
+      "loss": 0.1693,
+      "step": 550
+    },
+    {
+      "epoch": 0.3491271820448878,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.707165109034268e-06,
+      "loss": 0.1761,
+      "step": 560
+    },
+    {
+      "epoch": 0.3553615960099751,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.862928348909659e-06,
+      "loss": 0.1681,
+      "step": 570
+    },
+    {
+      "epoch": 0.36159600997506236,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.018691588785047e-06,
+      "loss": 0.1618,
+      "step": 580
+    },
+    {
+      "epoch": 0.36783042394014964,
+      "grad_norm": 1.2265625,
+      "learning_rate": 9.174454828660438e-06,
+      "loss": 0.1696,
+      "step": 590
+    },
+    {
+      "epoch": 0.3740648379052369,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.330218068535826e-06,
+      "loss": 0.1407,
+      "step": 600
+    },
+    {
+      "epoch": 0.3802992518703242,
+      "grad_norm": 1.140625,
+      "learning_rate": 9.485981308411217e-06,
+      "loss": 0.1569,
+      "step": 610
+    },
+    {
+      "epoch": 0.3865336658354115,
+      "grad_norm": 0.921875,
+      "learning_rate": 9.641744548286605e-06,
+      "loss": 0.1404,
+      "step": 620
+    },
+    {
+      "epoch": 0.39276807980049877,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.797507788161996e-06,
+      "loss": 0.1505,
+      "step": 630
+    },
+    {
+      "epoch": 0.39900249376558605,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.953271028037384e-06,
+      "loss": 0.1205,
+      "step": 640
+    },
+    {
+      "epoch": 0.40523690773067333,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.99996373549532e-06,
+      "loss": 0.1139,
+      "step": 650
+    },
+    {
+      "epoch": 0.4114713216957606,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.999786114697945e-06,
+      "loss": 0.1127,
+      "step": 660
+    },
+    {
+      "epoch": 0.4177057356608479,
+      "grad_norm": 0.8359375,
+      "learning_rate": 9.999460482032132e-06,
+      "loss": 0.1018,
+      "step": 670
+    },
+    {
+      "epoch": 0.4239401496259352,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.998986847137795e-06,
+      "loss": 0.1058,
+      "step": 680
+    },
+    {
+      "epoch": 0.43017456359102246,
+      "grad_norm": 0.68359375,
+      "learning_rate": 9.998365224036252e-06,
+      "loss": 0.0972,
+      "step": 690
+    },
+    {
+      "epoch": 0.43640897755610975,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.997595631129806e-06,
+      "loss": 0.1083,
+      "step": 700
+    },
+    {
+      "epoch": 0.442643391521197,
+      "grad_norm": 3.421875,
+      "learning_rate": 9.996678091201213e-06,
+      "loss": 0.1209,
+      "step": 710
+    },
+    {
+      "epoch": 0.4488778054862843,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.99561263141299e-06,
+      "loss": 0.1233,
+      "step": 720
+    },
+    {
+      "epoch": 0.4551122194513716,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.994399283306628e-06,
+      "loss": 0.1257,
+      "step": 730
+    },
+    {
+      "epoch": 0.4613466334164589,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.993038082801648e-06,
+      "loss": 0.1274,
+      "step": 740
+    },
+    {
+      "epoch": 0.46758104738154616,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.991529070194539e-06,
+      "loss": 0.1228,
+      "step": 750
+    },
+    {
+      "epoch": 0.47381546134663344,
+      "grad_norm": 0.890625,
+      "learning_rate": 9.989872290157566e-06,
+      "loss": 0.1249,
+      "step": 760
+    },
+    {
+      "epoch": 0.4800498753117207,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.988067791737449e-06,
+      "loss": 0.1193,
+      "step": 770
+    },
+    {
+      "epoch": 0.486284289276808,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.986115628353911e-06,
+      "loss": 0.1207,
+      "step": 780
+    },
+    {
+      "epoch": 0.4925187032418953,
+      "grad_norm": 1.125,
+      "learning_rate": 9.984015857798095e-06,
+      "loss": 0.1197,
+      "step": 790
+    },
+    {
+      "epoch": 0.49875311720698257,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.981768542230847e-06,
+      "loss": 0.1325,
+      "step": 800
+    },
+    {
+      "epoch": 0.5049875311720698,
+      "grad_norm": 0.98046875,
+      "learning_rate": 9.979373748180896e-06,
+      "loss": 0.132,
+      "step": 810
+    },
+    {
+      "epoch": 0.5112219451371571,
+      "grad_norm": 0.96484375,
+      "learning_rate": 9.976831546542858e-06,
+      "loss": 0.1356,
+      "step": 820
+    },
+    {
+      "epoch": 0.5174563591022444,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.974142012575156e-06,
+      "loss": 0.1313,
+      "step": 830
+    },
+    {
+      "epoch": 0.5236907730673317,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.971305225897788e-06,
+      "loss": 0.1333,
+      "step": 840
+    },
+    {
+      "epoch": 0.529925187032419,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.968321270489963e-06,
+      "loss": 0.1247,
+      "step": 850
+    },
+    {
+      "epoch": 0.5361596009975063,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.965190234687622e-06,
+      "loss": 0.1316,
+      "step": 860
+    },
+    {
+      "epoch": 0.5423940149625935,
+      "grad_norm": 0.625,
+      "learning_rate": 9.961912211180824e-06,
+      "loss": 0.1281,
+      "step": 870
+    },
+    {
+      "epoch": 0.5486284289276808,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.958487297010997e-06,
+      "loss": 0.1346,
+      "step": 880
+    },
+    {
+      "epoch": 0.5548628428927681,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.954915593568066e-06,
+      "loss": 0.1349,
+      "step": 890
+    },
+    {
+      "epoch": 0.5610972568578554,
+      "grad_norm": 1.3828125,
+      "learning_rate": 9.951197206587455e-06,
+      "loss": 0.1319,
+      "step": 900
+    },
+    {
+      "epoch": 0.5673316708229427,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.947332246146952e-06,
+      "loss": 0.1303,
+      "step": 910
+    },
+    {
+      "epoch": 0.57356608478803,
+      "grad_norm": 1.1875,
+      "learning_rate": 9.943320826663458e-06,
+      "loss": 0.1356,
+      "step": 920
+    },
+    {
+      "epoch": 0.5798004987531172,
+      "grad_norm": 0.69921875,
+      "learning_rate": 9.939163066889587e-06,
+      "loss": 0.1324,
+      "step": 930
+    },
+    {
+      "epoch": 0.5860349127182045,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.934859089910167e-06,
+      "loss": 0.1468,
+      "step": 940
+    },
+    {
+      "epoch": 0.5922693266832918,
+      "grad_norm": 0.82421875,
+      "learning_rate": 9.93040902313858e-06,
+      "loss": 0.1377,
+      "step": 950
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "grad_norm": 1.2734375,
+      "learning_rate": 9.925812998313005e-06,
+      "loss": 0.1332,
+      "step": 960
+    },
+    {
+      "epoch": 0.6047381546134664,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.921071151492501e-06,
+      "loss": 0.1382,
+      "step": 970
+    },
+    {
+      "epoch": 0.6109725685785536,
+      "grad_norm": 1.359375,
+      "learning_rate": 9.916183623053e-06,
+      "loss": 0.1419,
+      "step": 980
+    },
+    {
+      "epoch": 0.6172069825436409,
+      "grad_norm": 1.171875,
+      "learning_rate": 9.91115055768313e-06,
+      "loss": 0.1392,
+      "step": 990
+    },
+    {
+      "epoch": 0.6234413965087282,
+      "grad_norm": 1.375,
+      "learning_rate": 9.905972104379948e-06,
+      "loss": 0.1337,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6296758104738155,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.900648416444524e-06,
+      "loss": 0.1244,
+      "step": 1010
+    },
+    {
+      "epoch": 0.6359102244389028,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.895179651477396e-06,
+      "loss": 0.1303,
+      "step": 1020
+    },
+    {
+      "epoch": 0.64214463840399,
+      "grad_norm": 1.0546875,
+      "learning_rate": 9.889565971373916e-06,
+      "loss": 0.1253,
+      "step": 1030
+    },
+    {
+      "epoch": 0.6483790523690773,
+      "grad_norm": 1.78125,
+      "learning_rate": 9.883807542319447e-06,
+      "loss": 0.1274,
+      "step": 1040
+    },
+    {
+      "epoch": 0.6546134663341646,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.877904534784451e-06,
+      "loss": 0.1158,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6608478802992519,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.871857123519439e-06,
+      "loss": 0.1314,
+      "step": 1060
+    },
+    {
+      "epoch": 0.6670822942643392,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.865665487549796e-06,
+      "loss": 0.1236,
+      "step": 1070
+    },
+    {
+      "epoch": 0.6733167082294265,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.859329810170487e-06,
+      "loss": 0.1344,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6795511221945137,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.85285027894062e-06,
+      "loss": 0.1185,
+      "step": 1090
+    },
+    {
+      "epoch": 0.685785536159601,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.846227085677909e-06,
+      "loss": 0.1348,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6920199501246883,
+      "grad_norm": 1.21875,
+      "learning_rate": 9.83946042645298e-06,
+      "loss": 0.1302,
+      "step": 1110
+    },
+    {
+      "epoch": 0.6982543640897756,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.832550501583582e-06,
+      "loss": 0.1501,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7044887780548629,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.82549751562864e-06,
+      "loss": 0.1474,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7107231920199502,
+      "grad_norm": 1.75,
+      "learning_rate": 9.818301677382212e-06,
+      "loss": 0.1688,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7169576059850374,
+      "grad_norm": 2.46875,
+      "learning_rate": 9.810963199867302e-06,
+      "loss": 0.1695,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7231920199501247,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.80348230032956e-06,
+      "loss": 0.1561,
+      "step": 1160
+    },
+    {
+      "epoch": 0.729426433915212,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.79585920023084e-06,
+      "loss": 0.1424,
+      "step": 1170
+    },
+    {
+      "epoch": 0.7356608478802993,
+      "grad_norm": 1.375,
+      "learning_rate": 9.788094125242655e-06,
+      "loss": 0.154,
+      "step": 1180
+    },
+    {
+      "epoch": 0.7418952618453866,
+      "grad_norm": 1.125,
+      "learning_rate": 9.780187305239491e-06,
+      "loss": 0.1447,
+      "step": 1190
+    },
+    {
+      "epoch": 0.7481296758104738,
+      "grad_norm": 1.2890625,
+      "learning_rate": 9.772138974291999e-06,
+      "loss": 0.1364,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7543640897755611,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.763949370660072e-06,
+      "loss": 0.1317,
+      "step": 1210
+    },
+    {
+      "epoch": 0.7605985037406484,
+      "grad_norm": 1.875,
+      "learning_rate": 9.755618736785786e-06,
+      "loss": 0.1438,
+      "step": 1220
+    },
+    {
+      "epoch": 0.7668329177057357,
+      "grad_norm": 0.84765625,
+      "learning_rate": 9.747147319286232e-06,
+      "loss": 0.1186,
+      "step": 1230
+    },
+    {
+      "epoch": 0.773067331670823,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.738535368946202e-06,
+      "loss": 0.1271,
+      "step": 1240
+    },
+    {
+      "epoch": 0.7793017456359103,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.729783140710773e-06,
+      "loss": 0.113,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7855361596009975,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.72089089367776e-06,
+      "loss": 0.1232,
+      "step": 1260
+    },
+    {
+      "epoch": 0.7917705735660848,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.711858891090044e-06,
+      "loss": 0.1098,
+      "step": 1270
+    },
+    {
+      "epoch": 0.7980049875311721,
+      "grad_norm": 1.3515625,
+      "learning_rate": 9.70268740032778e-06,
+      "loss": 0.1112,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8042394014962594,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.693376692900476e-06,
+      "loss": 0.1112,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8104738154613467,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.683927044438963e-06,
+      "loss": 0.1076,
+      "step": 1300
+    },
+    {
+      "epoch": 0.816708229426434,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.674338734687236e-06,
+      "loss": 0.1102,
+      "step": 1310
+    },
+    {
+      "epoch": 0.8229426433915212,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.664612047494162e-06,
+      "loss": 0.1079,
+      "step": 1320
+    },
+    {
+      "epoch": 0.8291770573566085,
+      "grad_norm": 0.8359375,
+      "learning_rate": 9.65474727080509e-06,
+      "loss": 0.1145,
+      "step": 1330
+    },
+    {
+      "epoch": 0.8354114713216958,
+      "grad_norm": 0.8359375,
+      "learning_rate": 9.644744696653316e-06,
+      "loss": 0.1086,
+      "step": 1340
+    },
+    {
+      "epoch": 0.8416458852867831,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.63460462115145e-06,
+      "loss": 0.118,
+      "step": 1350
+    },
+    {
+      "epoch": 0.8478802992518704,
+      "grad_norm": 0.75,
+      "learning_rate": 9.624327344482629e-06,
+      "loss": 0.1165,
+      "step": 1360
+    },
+    {
+      "epoch": 0.8541147132169576,
+      "grad_norm": 0.96484375,
+      "learning_rate": 9.613913170891659e-06,
+      "loss": 0.1176,
+      "step": 1370
+    },
+    {
+      "epoch": 0.8603491271820449,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.60336240867598e-06,
+      "loss": 0.1108,
+      "step": 1380
+    },
+    {
+      "epoch": 0.8665835411471322,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.592675370176565e-06,
+      "loss": 0.1124,
+      "step": 1390
+    },
+    {
+      "epoch": 0.8728179551122195,
+      "grad_norm": 0.67578125,
+      "learning_rate": 9.581852371768652e-06,
+      "loss": 0.1032,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8790523690773068,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.57089373385239e-06,
+      "loss": 0.1003,
+      "step": 1410
+    },
+    {
+      "epoch": 0.885286783042394,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.559799780843353e-06,
+      "loss": 0.0995,
+      "step": 1420
+    },
+    {
+      "epoch": 0.8915211970074813,
+      "grad_norm": 0.828125,
+      "learning_rate": 9.548570841162931e-06,
+      "loss": 0.0949,
+      "step": 1430
+    },
+    {
+      "epoch": 0.8977556109725686,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.537207247228612e-06,
+      "loss": 0.0989,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9039900249376559,
+      "grad_norm": 0.71484375,
+      "learning_rate": 9.525709335444142e-06,
+      "loss": 0.0936,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9102244389027432,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.51407744618956e-06,
+      "loss": 0.0871,
+      "step": 1460
+    },
+    {
+      "epoch": 0.9164588528678305,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.502311923811131e-06,
+      "loss": 0.1,
+      "step": 1470
+    },
+    {
+      "epoch": 0.9226932668329177,
+      "grad_norm": 0.6953125,
+      "learning_rate": 9.490413116611143e-06,
+      "loss": 0.0937,
+      "step": 1480
+    },
+    {
+      "epoch": 0.928927680798005,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.478381376837603e-06,
+      "loss": 0.0932,
+      "step": 1490
+    },
+    {
+      "epoch": 0.9351620947630923,
+      "grad_norm": 0.546875,
+      "learning_rate": 9.466217060673804e-06,
+      "loss": 0.0945,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9413965087281796,
+      "grad_norm": 1.0,
+      "learning_rate": 9.45392052822778e-06,
+      "loss": 0.1,
+      "step": 1510
+    },
+    {
+      "epoch": 0.9476309226932669,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.441492143521656e-06,
+      "loss": 0.0973,
+      "step": 1520
+    },
+    {
+      "epoch": 0.9538653366583542,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.428932274480855e-06,
+      "loss": 0.1023,
+      "step": 1530
+    },
+    {
+      "epoch": 0.9600997506234414,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.416241292923223e-06,
+      "loss": 0.0997,
+      "step": 1540
+    },
+    {
+      "epoch": 0.9663341645885287,
+      "grad_norm": 0.8671875,
+      "learning_rate": 9.403419574548007e-06,
+      "loss": 0.1,
+      "step": 1550
+    },
+    {
+      "epoch": 0.972568578553616,
+      "grad_norm": 0.9765625,
+      "learning_rate": 9.390467498924745e-06,
+      "loss": 0.1077,
+      "step": 1560
+    },
+    {
+      "epoch": 0.9788029925187033,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.377385449482018e-06,
+      "loss": 0.1115,
+      "step": 1570
+    },
+    {
+      "epoch": 0.9850374064837906,
+      "grad_norm": 1.203125,
+      "learning_rate": 9.36417381349611e-06,
+      "loss": 0.1176,
+      "step": 1580
+    },
+    {
+      "epoch": 0.9912718204488778,
+      "grad_norm": 1.3125,
+      "learning_rate": 9.35083298207954e-06,
+      "loss": 0.1207,
+      "step": 1590
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.337363350169475e-06,
+      "loss": 0.1157,
+      "step": 1600
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1406659632921219,
+      "eval_runtime": 575.0322,
+      "eval_samples_per_second": 12.749,
+      "eval_steps_per_second": 0.798,
+      "step": 1604
+    },
+    {
+      "epoch": 1.0037406483790523,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.323765316516054e-06,
+      "loss": 0.1062,
+      "step": 1610
+    },
+    {
+      "epoch": 1.0099750623441397,
+      "grad_norm": 0.67578125,
+      "learning_rate": 9.310039283670566e-06,
+      "loss": 0.1037,
+      "step": 1620
+    },
+    {
+      "epoch": 1.0162094763092269,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.296185657973548e-06,
+      "loss": 0.1087,
+      "step": 1630
+    },
+    {
+      "epoch": 1.0224438902743143,
+      "grad_norm": 0.8125,
+      "learning_rate": 9.282204849542752e-06,
+      "loss": 0.1012,
+      "step": 1640
+    },
+    {
+      "epoch": 1.0286783042394014,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.268097272260993e-06,
+      "loss": 0.1325,
+      "step": 1650
+    },
+    {
+      "epoch": 1.0349127182044888,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.253863343763914e-06,
+      "loss": 0.1402,
+      "step": 1660
+    },
+    {
+      "epoch": 1.041147132169576,
+      "grad_norm": 1.2578125,
+      "learning_rate": 9.23950348542761e-06,
+      "loss": 0.1371,
+      "step": 1670
+    },
+    {
+      "epoch": 1.0473815461346634,
+      "grad_norm": 1.2578125,
+      "learning_rate": 9.225018122356157e-06,
+      "loss": 0.1463,
+      "step": 1680
+    },
+    {
+      "epoch": 1.0536159600997506,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.210407683369033e-06,
+      "loss": 0.1436,
+      "step": 1690
+    },
+    {
+      "epoch": 1.059850374064838,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.19567260098841e-06,
+      "loss": 0.1308,
+      "step": 1700
+    },
+    {
+      "epoch": 1.0660847880299251,
+      "grad_norm": 1.25,
+      "learning_rate": 9.180813311426365e-06,
+      "loss": 0.1431,
+      "step": 1710
+    },
+    {
+      "epoch": 1.0723192019950125,
+      "grad_norm": 1.375,
+      "learning_rate": 9.16583025457196e-06,
+      "loss": 0.1416,
+      "step": 1720
+    },
+    {
+      "epoch": 1.0785536159600997,
+      "grad_norm": 1.2109375,
+      "learning_rate": 9.15072387397821e-06,
+      "loss": 0.1397,
+      "step": 1730
+    },
+    {
+      "epoch": 1.084788029925187,
+      "grad_norm": 1.2890625,
+      "learning_rate": 9.135494616848975e-06,
+      "loss": 0.1393,
+      "step": 1740
+    },
+    {
+      "epoch": 1.0910224438902743,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.1201429340257e-06,
+      "loss": 0.1181,
+      "step": 1750
+    },
+    {
+      "epoch": 1.0972568578553616,
+      "grad_norm": 1.21875,
+      "learning_rate": 9.104669279974074e-06,
+      "loss": 0.123,
+      "step": 1760
+    },
+    {
+      "epoch": 1.1034912718204488,
+      "grad_norm": 0.81640625,
+      "learning_rate": 9.089074112770585e-06,
+      "loss": 0.1036,
+      "step": 1770
+    },
+    {
+      "epoch": 1.1097256857855362,
+      "grad_norm": 1.125,
+      "learning_rate": 9.073357894088947e-06,
+      "loss": 0.1092,
+      "step": 1780
+    },
+    {
+      "epoch": 1.1159600997506234,
+      "grad_norm": 0.953125,
+      "learning_rate": 9.057521089186445e-06,
+      "loss": 0.1085,
+      "step": 1790
+    },
+    {
+      "epoch": 1.1221945137157108,
+      "grad_norm": 1.1640625,
+      "learning_rate": 9.041564166890146e-06,
+      "loss": 0.1106,
+      "step": 1800
+    },
+    {
+      "epoch": 1.128428927680798,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.025487599583035e-06,
+      "loss": 0.1015,
+      "step": 1810
+    },
+    {
+      "epoch": 1.1346633416458853,
+      "grad_norm": 0.89453125,
+      "learning_rate": 9.009291863190025e-06,
+      "loss": 0.106,
+      "step": 1820
+    },
+    {
+      "epoch": 1.1408977556109725,
+      "grad_norm": 1.1484375,
+      "learning_rate": 8.992977437163866e-06,
+      "loss": 0.1114,
+      "step": 1830
+    },
+    {
+      "epoch": 1.14713216957606,
+      "grad_norm": 0.86328125,
+      "learning_rate": 8.976544804470954e-06,
+      "loss": 0.1144,
+      "step": 1840
+    },
+    {
+      "epoch": 1.153366583541147,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.95999445157703e-06,
+      "loss": 0.1131,
+      "step": 1850
+    },
+    {
+      "epoch": 1.1596009975062345,
+      "grad_norm": 0.7109375,
+      "learning_rate": 8.943326868432786e-06,
+      "loss": 0.1093,
+      "step": 1860
+    },
+    {
+      "epoch": 1.1658354114713216,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.926542548459354e-06,
+      "loss": 0.1083,
+      "step": 1870
+    },
+    {
+      "epoch": 1.172069825436409,
+      "grad_norm": 0.625,
+      "learning_rate": 8.9096419885337e-06,
+      "loss": 0.1009,
+      "step": 1880
+    },
+    {
+      "epoch": 1.1783042394014962,
+      "grad_norm": 1.296875,
+      "learning_rate": 8.892625688973914e-06,
+      "loss": 0.1082,
+      "step": 1890
+    },
+    {
+      "epoch": 1.1845386533665836,
+      "grad_norm": 0.76953125,
+      "learning_rate": 8.875494153524409e-06,
+      "loss": 0.1008,
+      "step": 1900
+    },
+    {
+      "epoch": 1.1907730673316708,
+      "grad_norm": 1.2578125,
+      "learning_rate": 8.858247889340987e-06,
+      "loss": 0.1034,
+      "step": 1910
+    },
+    {
+      "epoch": 1.1970074812967582,
+      "grad_norm": 0.69921875,
+      "learning_rate": 8.840887406975851e-06,
+      "loss": 0.0973,
+      "step": 1920
+    },
+    {
+      "epoch": 1.2032418952618453,
+      "grad_norm": 1.2890625,
+      "learning_rate": 8.823413220362468e-06,
+      "loss": 0.0972,
+      "step": 1930
+    },
+    {
+      "epoch": 1.2094763092269327,
+      "grad_norm": 0.84375,
+      "learning_rate": 8.80582584680037e-06,
+      "loss": 0.0923,
+      "step": 1940
+    },
+    {
+      "epoch": 1.21571072319202,
+      "grad_norm": 0.71875,
+      "learning_rate": 8.788125806939833e-06,
+      "loss": 0.0939,
+      "step": 1950
+    },
+    {
+      "epoch": 1.2219451371571073,
+      "grad_norm": 0.8671875,
+      "learning_rate": 8.770313624766467e-06,
+      "loss": 0.0912,
+      "step": 1960
+    },
+    {
+      "epoch": 1.2281795511221945,
+      "grad_norm": 0.73046875,
+      "learning_rate": 8.7523898275857e-06,
+      "loss": 0.0912,
+      "step": 1970
+    },
+    {
+      "epoch": 1.2344139650872819,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.734354946007173e-06,
+      "loss": 0.0889,
+      "step": 1980
+    },
+    {
+      "epoch": 1.240648379052369,
+      "grad_norm": 0.8125,
+      "learning_rate": 8.716209513929027e-06,
+      "loss": 0.0919,
+      "step": 1990
+    },
+    {
+      "epoch": 1.2468827930174564,
+      "grad_norm": 0.8046875,
+      "learning_rate": 8.697954068522104e-06,
+      "loss": 0.0875,
+      "step": 2000
+    },
+    {
+      "epoch": 1.2531172069825436,
+      "grad_norm": 0.9140625,
+      "learning_rate": 8.679589150214035e-06,
+      "loss": 0.0892,
+      "step": 2010
+    },
+    {
+      "epoch": 1.259351620947631,
+      "grad_norm": 0.859375,
+      "learning_rate": 8.661115302673255e-06,
+      "loss": 0.0843,
+      "step": 2020
+    },
+    {
+      "epoch": 1.2655860349127181,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.642533072792894e-06,
+      "loss": 0.0808,
+      "step": 2030
+    },
+    {
+      "epoch": 1.2718204488778055,
+      "grad_norm": 0.76171875,
+      "learning_rate": 8.623843010674597e-06,
+      "loss": 0.0861,
+      "step": 2040
+    },
+    {
+      "epoch": 1.2780548628428927,
+      "grad_norm": 1.28125,
+      "learning_rate": 8.605045669612238e-06,
+      "loss": 0.0892,
+      "step": 2050
+    },
+    {
+      "epoch": 1.28428927680798,
+      "grad_norm": 0.78125,
+      "learning_rate": 8.586141606075533e-06,
+      "loss": 0.0916,
+      "step": 2060
+    },
+    {
+      "epoch": 1.2905236907730673,
+      "grad_norm": 1.34375,
+      "learning_rate": 8.567131379693574e-06,
+      "loss": 0.0954,
+      "step": 2070
+    },
+    {
+      "epoch": 1.2967581047381547,
+      "grad_norm": 0.78125,
+      "learning_rate": 8.548015553238263e-06,
+      "loss": 0.1045,
+      "step": 2080
+    },
+    {
+      "epoch": 1.3029925187032418,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.52879469260764e-06,
+      "loss": 0.1074,
+      "step": 2090
+    },
+    {
+      "epoch": 1.3092269326683292,
+      "grad_norm": 1.0234375,
+      "learning_rate": 8.509469366809152e-06,
+      "loss": 0.1111,
+      "step": 2100
+    },
+    {
+      "epoch": 1.3154613466334164,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.49004014794278e-06,
+      "loss": 0.113,
+      "step": 2110
+    },
+    {
+      "epoch": 1.3216957605985038,
+      "grad_norm": 0.99609375,
+      "learning_rate": 8.470507611184132e-06,
+      "loss": 0.1259,
+      "step": 2120
+    },
+    {
+      "epoch": 1.327930174563591,
+      "grad_norm": 1.109375,
+      "learning_rate": 8.450872334767391e-06,
+      "loss": 0.1255,
+      "step": 2130
+    },
+    {
+      "epoch": 1.3341645885286784,
+      "grad_norm": 1.0390625,
+      "learning_rate": 8.431134899968213e-06,
+      "loss": 0.1215,
+      "step": 2140
+    },
+    {
+      "epoch": 1.3403990024937655,
+      "grad_norm": 1.078125,
+      "learning_rate": 8.411295891086516e-06,
+      "loss": 0.125,
+      "step": 2150
+    },
+    {
+      "epoch": 1.346633416458853,
+      "grad_norm": 1.0234375,
+      "learning_rate": 8.391355895429173e-06,
+      "loss": 0.1331,
+      "step": 2160
+    },
+    {
+      "epoch": 1.35286783042394,
+      "grad_norm": 1.015625,
+      "learning_rate": 8.371315503292644e-06,
+      "loss": 0.1285,
+      "step": 2170
+    },
+    {
+      "epoch": 1.3591022443890275,
+      "grad_norm": 0.859375,
+      "learning_rate": 8.351175307945478e-06,
+      "loss": 0.131,
+      "step": 2180
+    },
+    {
+      "epoch": 1.3653366583541147,
+      "grad_norm": 1.09375,
+      "learning_rate": 8.330935905610772e-06,
+      "loss": 0.1277,
+      "step": 2190
+    },
+    {
+      "epoch": 1.371571072319202,
+      "grad_norm": 0.90625,
+      "learning_rate": 8.310597895448507e-06,
+      "loss": 0.1196,
+      "step": 2200
+    },
+    {
+      "epoch": 1.3778054862842892,
+      "grad_norm": 0.99609375,
+      "learning_rate": 8.290161879537815e-06,
+      "loss": 0.1219,
+      "step": 2210
+    },
+    {
+      "epoch": 1.3840399002493766,
+      "grad_norm": 0.703125,
+      "learning_rate": 8.269628462859155e-06,
+      "loss": 0.1134,
+      "step": 2220
+    },
+    {
+      "epoch": 1.3902743142144638,
+      "grad_norm": 0.83984375,
+      "learning_rate": 8.2489982532764e-06,
+      "loss": 0.1101,
+      "step": 2230
+    },
+    {
+      "epoch": 1.3965087281795512,
+      "grad_norm": 0.65625,
+      "learning_rate": 8.228271861518853e-06,
+      "loss": 0.1005,
+      "step": 2240
+    },
+    {
+      "epoch": 1.4027431421446384,
+      "grad_norm": 1.0234375,
+      "learning_rate": 8.207449901163155e-06,
+      "loss": 0.095,
+      "step": 2250
+    },
+    {
+      "epoch": 1.4089775561097257,
+      "grad_norm": 0.68359375,
+      "learning_rate": 8.186532988615124e-06,
+      "loss": 0.0937,
+      "step": 2260
+    },
+    {
+      "epoch": 1.415211970074813,
+      "grad_norm": 0.7734375,
+      "learning_rate": 8.165521743091507e-06,
+      "loss": 0.0947,
+      "step": 2270
+    },
+    {
+      "epoch": 1.4214463840399003,
+      "grad_norm": 0.625,
+      "learning_rate": 8.144416786601658e-06,
+      "loss": 0.0898,
+      "step": 2280
+    },
+    {
+      "epoch": 1.4276807980049875,
+      "grad_norm": 0.59375,
+      "learning_rate": 8.12321874392911e-06,
+      "loss": 0.0841,
+      "step": 2290
+    },
+    {
+      "epoch": 1.4339152119700749,
+      "grad_norm": 0.61328125,
+      "learning_rate": 8.101928242613087e-06,
+      "loss": 0.0804,
+      "step": 2300
+    },
+    {
+      "epoch": 1.440149625935162,
+      "grad_norm": 0.9140625,
+      "learning_rate": 8.080545912929928e-06,
+      "loss": 0.0862,
+      "step": 2310
+    },
+    {
+      "epoch": 1.4463840399002494,
+      "grad_norm": 0.76171875,
+      "learning_rate": 8.059072387874426e-06,
+      "loss": 0.0876,
+      "step": 2320
+    },
+    {
+      "epoch": 1.4526184538653366,
+      "grad_norm": 0.953125,
+      "learning_rate": 8.037508303141082e-06,
+      "loss": 0.1,
+      "step": 2330
+    },
+    {
+      "epoch": 1.458852867830424,
+      "grad_norm": 0.6953125,
+      "learning_rate": 8.015854297105302e-06,
+      "loss": 0.0925,
+      "step": 2340
+    },
+    {
+      "epoch": 1.4650872817955112,
+      "grad_norm": 0.73828125,
+      "learning_rate": 7.994111010804483e-06,
+      "loss": 0.0998,
+      "step": 2350
+    },
+    {
+      "epoch": 1.4713216957605986,
+      "grad_norm": 0.76171875,
+      "learning_rate": 7.972279087919051e-06,
+      "loss": 0.0921,
+      "step": 2360
+    },
+    {
+      "epoch": 1.4775561097256857,
+      "grad_norm": 0.77734375,
+      "learning_rate": 7.95035917475339e-06,
+      "loss": 0.0966,
+      "step": 2370
+    },
+    {
+      "epoch": 1.4837905236907731,
+      "grad_norm": 0.87109375,
+      "learning_rate": 7.928351920216719e-06,
+      "loss": 0.0924,
+      "step": 2380
+    },
+    {
+      "epoch": 1.4900249376558603,
+      "grad_norm": 0.98828125,
+      "learning_rate": 7.90625797580388e-06,
+      "loss": 0.0997,
+      "step": 2390
+    },
+    {
+      "epoch": 1.4962593516209477,
+      "grad_norm": 0.796875,
+      "learning_rate": 7.884077995576048e-06,
+      "loss": 0.1113,
+      "step": 2400
+    },
+    {
+      "epoch": 1.5024937655860349,
+      "grad_norm": 0.921875,
+      "learning_rate": 7.861812636141377e-06,
+      "loss": 0.1085,
+      "step": 2410
+    },
+    {
+      "epoch": 1.508728179551122,
+      "grad_norm": 0.83984375,
+      "learning_rate": 7.839462556635553e-06,
+      "loss": 0.1135,
+      "step": 2420
+    },
+    {
+      "epoch": 1.5149625935162094,
+      "grad_norm": 0.78515625,
+      "learning_rate": 7.817028418702284e-06,
+      "loss": 0.108,
+      "step": 2430
+    },
+    {
+      "epoch": 1.5211970074812968,
+      "grad_norm": 0.8828125,
+      "learning_rate": 7.794510886473714e-06,
+      "loss": 0.1108,
+      "step": 2440
+    },
+    {
+      "epoch": 1.527431421446384,
+      "grad_norm": 0.71484375,
+      "learning_rate": 7.771910626550762e-06,
+      "loss": 0.1122,
+      "step": 2450
+    },
+    {
+      "epoch": 1.5336658354114712,
+      "grad_norm": 0.90234375,
+      "learning_rate": 7.749228307983387e-06,
+      "loss": 0.1167,
+      "step": 2460
+    },
+    {
+      "epoch": 1.5399002493765586,
+      "grad_norm": 0.68359375,
+      "learning_rate": 7.726464602250784e-06,
+      "loss": 0.1149,
+      "step": 2470
+    },
+    {
+      "epoch": 1.546134663341646,
+      "grad_norm": 0.93359375,
+      "learning_rate": 7.703620183241502e-06,
+      "loss": 0.1164,
+      "step": 2480
+    },
+    {
+      "epoch": 1.5523690773067331,
+      "grad_norm": 0.609375,
+      "learning_rate": 7.680695727233502e-06,
+      "loss": 0.1251,
+      "step": 2490
+    },
+    {
+      "epoch": 1.5586034912718203,
+      "grad_norm": 1.0234375,
+      "learning_rate": 7.657691912874124e-06,
+      "loss": 0.1216,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5648379052369077,
+      "grad_norm": 0.65625,
+      "learning_rate": 7.63460942116001e-06,
+      "loss": 0.1232,
+      "step": 2510
+    },
+    {
+      "epoch": 1.571072319201995,
+      "grad_norm": 1.1875,
+      "learning_rate": 7.611448935416934e-06,
+      "loss": 0.1231,
+      "step": 2520
+    },
+    {
+      "epoch": 1.5773067331670823,
+      "grad_norm": 0.63671875,
+      "learning_rate": 7.588211141279584e-06,
+      "loss": 0.1198,
+      "step": 2530
+    },
+    {
+      "epoch": 1.5835411471321694,
+      "grad_norm": 0.91015625,
+      "learning_rate": 7.564896726671247e-06,
+      "loss": 0.1186,
+      "step": 2540
+    },
+    {
+      "epoch": 1.5897755610972568,
+      "grad_norm": 0.76171875,
+      "learning_rate": 7.541506381783463e-06,
+      "loss": 0.1171,
+      "step": 2550
+    },
+    {
+      "epoch": 1.5960099750623442,
+      "grad_norm": 0.89453125,
+      "learning_rate": 7.518040799055583e-06,
+      "loss": 0.1105,
+      "step": 2560
+    },
+    {
+      "epoch": 1.6022443890274314,
+      "grad_norm": 0.8359375,
+      "learning_rate": 7.4945006731542746e-06,
+      "loss": 0.1142,
+      "step": 2570
+    },
+    {
+      "epoch": 1.6084788029925186,
+      "grad_norm": 1.1015625,
+      "learning_rate": 7.470886700952947e-06,
+      "loss": 0.1108,
+      "step": 2580
+    },
+    {
+      "epoch": 1.614713216957606,
+      "grad_norm": 0.81640625,
+      "learning_rate": 7.447199581511135e-06,
+      "loss": 0.1162,
+      "step": 2590
+    },
+    {
+      "epoch": 1.6209476309226933,
+      "grad_norm": 1.03125,
+      "learning_rate": 7.423440016053795e-06,
+      "loss": 0.1192,
+      "step": 2600
+    },
+    {
+      "epoch": 1.6271820448877805,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.399608707950553e-06,
+      "loss": 0.113,
+      "step": 2610
+    },
+    {
+      "epoch": 1.6334164588528677,
+      "grad_norm": 1.3125,
+      "learning_rate": 7.375706362694873e-06,
+      "loss": 0.1059,
+      "step": 2620
+    },
+    {
+      "epoch": 1.639650872817955,
+      "grad_norm": 1.0859375,
+      "learning_rate": 7.351733687883183e-06,
+      "loss": 0.1063,
+      "step": 2630
+    },
+    {
+      "epoch": 1.6458852867830425,
+      "grad_norm": 1.140625,
+      "learning_rate": 7.327691393193918e-06,
+      "loss": 0.103,
+      "step": 2640
+    },
+    {
+      "epoch": 1.6521197007481296,
+      "grad_norm": 0.84765625,
+      "learning_rate": 7.303580190366513e-06,
+      "loss": 0.1001,
+      "step": 2650
+    },
+    {
+      "epoch": 1.6583541147132168,
+      "grad_norm": 1.3515625,
+      "learning_rate": 7.279400793180341e-06,
+      "loss": 0.1064,
+      "step": 2660
+    },
+    {
+      "epoch": 1.6645885286783042,
+      "grad_norm": 1.09375,
+      "learning_rate": 7.255153917433572e-06,
+      "loss": 0.1037,
+      "step": 2670
+    },
+    {
+      "epoch": 1.6708229426433916,
+      "grad_norm": 1.4921875,
+      "learning_rate": 7.230840280921987e-06,
+      "loss": 0.1118,
+      "step": 2680
+    },
+    {
+      "epoch": 1.6770573566084788,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.206460603417731e-06,
+      "loss": 0.1057,
+      "step": 2690
+    },
+    {
+      "epoch": 1.683291770573566,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.182015606648e-06,
+      "loss": 0.1188,
+      "step": 2700
+    },
+    {
+      "epoch": 1.6895261845386533,
+      "grad_norm": 1.265625,
+      "learning_rate": 7.1575060142736785e-06,
+      "loss": 0.1122,
+      "step": 2710
+    },
+    {
+      "epoch": 1.6957605985037407,
+      "grad_norm": 1.3828125,
+      "learning_rate": 7.132932551867917e-06,
+      "loss": 0.1223,
+      "step": 2720
+    },
+    {
+      "epoch": 1.701995012468828,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.108295946894654e-06,
+      "loss": 0.1168,
+      "step": 2730
+    },
+    {
+      "epoch": 1.708229426433915,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.083596928687071e-06,
+      "loss": 0.1327,
+      "step": 2740
+    },
+    {
+      "epoch": 1.7144638403990025,
+      "grad_norm": 2.015625,
+      "learning_rate": 7.058836228426016e-06,
+      "loss": 0.1321,
+      "step": 2750
+    },
+    {
+      "epoch": 1.7206982543640899,
+      "grad_norm": 1.390625,
+      "learning_rate": 7.034014579118344e-06,
+      "loss": 0.1302,
+      "step": 2760
+    },
+    {
+      "epoch": 1.726932668329177,
+      "grad_norm": 1.7265625,
+      "learning_rate": 7.009132715575227e-06,
+      "loss": 0.1261,
+      "step": 2770
+    },
+    {
+      "epoch": 1.7331670822942642,
+      "grad_norm": 1.3515625,
+      "learning_rate": 6.9841913743903986e-06,
+      "loss": 0.127,
+      "step": 2780
+    },
+    {
+      "epoch": 1.7394014962593516,
+      "grad_norm": 1.2734375,
+      "learning_rate": 6.959191293918344e-06,
+      "loss": 0.1238,
+      "step": 2790
+    },
+    {
+      "epoch": 1.745635910224439,
+      "grad_norm": 1.671875,
+      "learning_rate": 6.934133214252448e-06,
+      "loss": 0.1335,
+      "step": 2800
+    },
+    {
+      "epoch": 1.7518703241895262,
+      "grad_norm": 1.234375,
+      "learning_rate": 6.909017877203078e-06,
+      "loss": 0.1174,
+      "step": 2810
+    },
+    {
+      "epoch": 1.7581047381546133,
+      "grad_norm": 1.421875,
+      "learning_rate": 6.883846026275635e-06,
+      "loss": 0.1222,
+      "step": 2820
+    },
+    {
+      "epoch": 1.7643391521197007,
+      "grad_norm": 0.83203125,
+      "learning_rate": 6.8586184066485315e-06,
+      "loss": 0.1038,
+      "step": 2830
+    },
+    {
+      "epoch": 1.770573566084788,
+      "grad_norm": 1.1796875,
+      "learning_rate": 6.833335765151138e-06,
+      "loss": 0.1181,
+      "step": 2840
+    },
+    {
+      "epoch": 1.7768079800498753,
+      "grad_norm": 0.84375,
+      "learning_rate": 6.807998850241675e-06,
+      "loss": 0.103,
+      "step": 2850
+    },
+    {
+      "epoch": 1.7830423940149625,
+      "grad_norm": 1.1796875,
+      "learning_rate": 6.782608411985048e-06,
+      "loss": 0.1074,
+      "step": 2860
+    },
+    {
+      "epoch": 1.7892768079800498,
+      "grad_norm": 0.734375,
+      "learning_rate": 6.757165202030653e-06,
+      "loss": 0.092,
+      "step": 2870
+    },
+    {
+      "epoch": 1.7955112219451372,
+      "grad_norm": 1.3125,
+      "learning_rate": 6.731669973590119e-06,
+      "loss": 0.0946,
+      "step": 2880
+    },
+    {
+      "epoch": 1.8017456359102244,
+      "grad_norm": 0.66796875,
+      "learning_rate": 6.706123481415012e-06,
+      "loss": 0.0974,
+      "step": 2890
+    },
+    {
+      "epoch": 1.8079800498753116,
+      "grad_norm": 1.046875,
+      "learning_rate": 6.680526481774492e-06,
+      "loss": 0.0962,
+      "step": 2900
+    },
+    {
+      "epoch": 1.814214463840399,
+      "grad_norm": 0.66015625,
+      "learning_rate": 6.65487973243292e-06,
+      "loss": 0.1,
+      "step": 2910
+    },
+    {
+      "epoch": 1.8204488778054864,
+      "grad_norm": 0.82421875,
+      "learning_rate": 6.629183992627432e-06,
+      "loss": 0.0944,
+      "step": 2920
+    },
+    {
+      "epoch": 1.8266832917705735,
+      "grad_norm": 0.60546875,
+      "learning_rate": 6.603440023045463e-06,
+      "loss": 0.0986,
+      "step": 2930
+    },
+    {
+      "epoch": 1.8329177057356607,
+      "grad_norm": 0.81640625,
+      "learning_rate": 6.577648585802219e-06,
+      "loss": 0.1031,
+      "step": 2940
+    },
+    {
+      "epoch": 1.839152119700748,
+      "grad_norm": 0.69140625,
+      "learning_rate": 6.551810444418123e-06,
+      "loss": 0.1016,
+      "step": 2950
+    },
+    {
+      "epoch": 1.8453865336658355,
+      "grad_norm": 0.78125,
+      "learning_rate": 6.5259263637962166e-06,
+      "loss": 0.0981,
+      "step": 2960
+    },
+    {
+      "epoch": 1.8516209476309227,
+      "grad_norm": 0.81640625,
+      "learning_rate": 6.499997110199502e-06,
+      "loss": 0.1068,
+      "step": 2970
+    },
+    {
+      "epoch": 1.8578553615960098,
+      "grad_norm": 0.66015625,
+      "learning_rate": 6.474023451228269e-06,
+      "loss": 0.0914,
+      "step": 2980
+    },
+    {
+      "epoch": 1.8640897755610972,
+      "grad_norm": 0.72265625,
+      "learning_rate": 6.448006155797371e-06,
+      "loss": 0.0989,
+      "step": 2990
+    },
+    {
+      "epoch": 1.8703241895261846,
+      "grad_norm": 0.546875,
+      "learning_rate": 6.421945994113453e-06,
+      "loss": 0.0872,
+      "step": 3000
+    },
+    {
+      "epoch": 1.8765586034912718,
+      "grad_norm": 0.73046875,
+      "learning_rate": 6.395843737652166e-06,
+      "loss": 0.0882,
+      "step": 3010
+    },
+    {
+      "epoch": 1.882793017456359,
+      "grad_norm": 0.71875,
+      "learning_rate": 6.3697001591353106e-06,
+      "loss": 0.0881,
+      "step": 3020
+    },
+    {
+      "epoch": 1.8890274314214464,
+      "grad_norm": 0.5859375,
+      "learning_rate": 6.343516032507975e-06,
+      "loss": 0.0906,
+      "step": 3030
+    },
+    {
+      "epoch": 1.8952618453865338,
+      "grad_norm": 0.59765625,
+      "learning_rate": 6.31729213291562e-06,
+      "loss": 0.0885,
+      "step": 3040
+    },
+    {
+      "epoch": 1.901496259351621,
+      "grad_norm": 0.65234375,
+      "learning_rate": 6.29102923668113e-06,
+      "loss": 0.0843,
+      "step": 3050
+    },
+    {
+      "epoch": 1.907730673316708,
+      "grad_norm": 0.6796875,
+      "learning_rate": 6.26472812128183e-06,
+      "loss": 0.083,
+      "step": 3060
+    },
+    {
+      "epoch": 1.9139650872817955,
+      "grad_norm": 0.64453125,
+      "learning_rate": 6.238389565326476e-06,
+      "loss": 0.091,
+      "step": 3070
+    },
+    {
+      "epoch": 1.9201995012468829,
+      "grad_norm": 0.6484375,
+      "learning_rate": 6.212014348532195e-06,
+      "loss": 0.0785,
+      "step": 3080
+    },
+    {
+      "epoch": 1.92643391521197,
+      "grad_norm": 0.6796875,
+      "learning_rate": 6.185603251701411e-06,
+      "loss": 0.0866,
+      "step": 3090
+    },
+    {
+      "epoch": 1.9326683291770572,
+      "grad_norm": 0.578125,
+      "learning_rate": 6.159157056698729e-06,
+      "loss": 0.0794,
+      "step": 3100
+    },
+    {
+      "epoch": 1.9389027431421446,
+      "grad_norm": 0.94921875,
+      "learning_rate": 6.132676546427786e-06,
+      "loss": 0.0894,
+      "step": 3110
+    },
+    {
+      "epoch": 1.945137157107232,
+      "grad_norm": 0.58203125,
+      "learning_rate": 6.1061625048080775e-06,
+      "loss": 0.0875,
+      "step": 3120
+    },
+    {
+      "epoch": 1.9513715710723192,
+      "grad_norm": 1.0859375,
+      "learning_rate": 6.079615716751747e-06,
+      "loss": 0.0925,
+      "step": 3130
+    },
+    {
+      "epoch": 1.9576059850374063,
+      "grad_norm": 1.1796875,
+      "learning_rate": 6.05303696814035e-06,
+      "loss": 0.0896,
+      "step": 3140
+    },
+    {
+      "epoch": 1.9638403990024937,
+      "grad_norm": 0.71484375,
+      "learning_rate": 6.026427045801596e-06,
+      "loss": 0.0996,
+      "step": 3150
+    },
+    {
+      "epoch": 1.9700748129675811,
+      "grad_norm": 1.0234375,
+      "learning_rate": 5.999786737486046e-06,
+      "loss": 0.1047,
+      "step": 3160
+    },
+    {
+      "epoch": 1.9763092269326683,
+      "grad_norm": 0.62109375,
+      "learning_rate": 5.973116831843798e-06,
+      "loss": 0.0937,
+      "step": 3170
+    },
+    {
+      "epoch": 1.9825436408977555,
+      "grad_norm": 0.9609375,
+      "learning_rate": 5.946418118401141e-06,
+      "loss": 0.1042,
+      "step": 3180
+    },
+    {
+      "epoch": 1.9887780548628429,
+      "grad_norm": 1.078125,
+      "learning_rate": 5.919691387537175e-06,
+      "loss": 0.1031,
+      "step": 3190
+    },
+    {
+      "epoch": 1.9950124688279303,
+      "grad_norm": 1.0390625,
+      "learning_rate": 5.892937430460421e-06,
+      "loss": 0.1041,
+      "step": 3200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.13248766958713531,
+      "eval_runtime": 306.0427,
+      "eval_samples_per_second": 23.954,
+      "eval_steps_per_second": 1.5,
+      "step": 3208
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6416,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 1604,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.184008180432896e+20,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf798d7f5818756a03915c5bc6b925db9c5083056b25bf0861802b46be39289d
+size 6161

checkpoint-4812/config.json

@@ -0,0 +1,60 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "bfloat16",
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50276
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

checkpoint-4812/generation_config.json

@@ -0,0 +1,168 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "language": "hi",
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.57.3"
+}

checkpoint-4812/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae6048bdb2c8d485d47fd8958b2f70ee98bf9a2c4d4dfd154d1570248fce5105
+size 483525680

checkpoint-4812/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0458e8c591d099db43128c938151e814f4427d5b773935cecef2645235f86847
+size 954914801

checkpoint-4812/preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

checkpoint-4812/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307fedd2dc19c70f634b6fef21f6d982150b747fb3e0c9d99b196ac27dbaafc6
+size 14645

checkpoint-4812/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:519697e74855c0c2b4938d504436a3b4df40dfdebe2295e38eee150d1593361b
+size 1465

checkpoint-4812/trainer_state.json

@@ -0,0 +1,3425 @@
+{
+  "best_global_step": 4812,
+  "best_metric": 0.1314818561077118,
+  "best_model_checkpoint": "/workspace/whisper-finetuning/models/whisper-small-hi-uncurated-reverse-mft-1-1-1/checkpoint-4812",
+  "epoch": 3.0,
+  "eval_steps": 1604,
+  "global_step": 4812,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006234413965087282,
+      "grad_norm": 7.5625,
+      "learning_rate": 1.4018691588785048e-07,
+      "loss": 0.7058,
+      "step": 10
+    },
+    {
+      "epoch": 0.012468827930174564,
+      "grad_norm": 7.6875,
+      "learning_rate": 2.959501557632399e-07,
+      "loss": 0.6474,
+      "step": 20
+    },
+    {
+      "epoch": 0.018703241895261846,
+      "grad_norm": 7.46875,
+      "learning_rate": 4.517133956386293e-07,
+      "loss": 0.656,
+      "step": 30
+    },
+    {
+      "epoch": 0.02493765586034913,
+      "grad_norm": 7.34375,
+      "learning_rate": 6.074766355140187e-07,
+      "loss": 0.6401,
+      "step": 40
+    },
+    {
+      "epoch": 0.03117206982543641,
+      "grad_norm": 7.25,
+      "learning_rate": 7.632398753894081e-07,
+      "loss": 0.6713,
+      "step": 50
+    },
+    {
+      "epoch": 0.03740648379052369,
+      "grad_norm": 7.375,
+      "learning_rate": 9.190031152647975e-07,
+      "loss": 0.6306,
+      "step": 60
+    },
+    {
+      "epoch": 0.043640897755610975,
+      "grad_norm": 7.0,
+      "learning_rate": 1.074766355140187e-06,
+      "loss": 0.6438,
+      "step": 70
+    },
+    {
+      "epoch": 0.04987531172069826,
+      "grad_norm": 8.0,
+      "learning_rate": 1.2305295950155765e-06,
+      "loss": 0.6173,
+      "step": 80
+    },
+    {
+      "epoch": 0.05610972568578554,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.3862928348909658e-06,
+      "loss": 0.5933,
+      "step": 90
+    },
+    {
+      "epoch": 0.06234413965087282,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.542056074766355e-06,
+      "loss": 0.5895,
+      "step": 100
+    },
+    {
+      "epoch": 0.0685785536159601,
+      "grad_norm": 7.90625,
+      "learning_rate": 1.6978193146417446e-06,
+      "loss": 0.5901,
+      "step": 110
+    },
+    {
+      "epoch": 0.07481296758104738,
+      "grad_norm": 7.8125,
+      "learning_rate": 1.8535825545171341e-06,
+      "loss": 0.5616,
+      "step": 120
+    },
+    {
+      "epoch": 0.08104738154613467,
+      "grad_norm": 7.65625,
+      "learning_rate": 2.0093457943925234e-06,
+      "loss": 0.5733,
+      "step": 130
+    },
+    {
+      "epoch": 0.08728179551122195,
+      "grad_norm": 7.75,
+      "learning_rate": 2.165109034267913e-06,
+      "loss": 0.5738,
+      "step": 140
+    },
+    {
+      "epoch": 0.09351620947630923,
+      "grad_norm": 7.09375,
+      "learning_rate": 2.3208722741433024e-06,
+      "loss": 0.574,
+      "step": 150
+    },
+    {
+      "epoch": 0.09975062344139651,
+      "grad_norm": 7.59375,
+      "learning_rate": 2.476635514018692e-06,
+      "loss": 0.5626,
+      "step": 160
+    },
+    {
+      "epoch": 0.1059850374064838,
+      "grad_norm": 7.0,
+      "learning_rate": 2.632398753894081e-06,
+      "loss": 0.5831,
+      "step": 170
+    },
+    {
+      "epoch": 0.11221945137157108,
+      "grad_norm": 7.6875,
+      "learning_rate": 2.7881619937694705e-06,
+      "loss": 0.5733,
+      "step": 180
+    },
+    {
+      "epoch": 0.11845386533665836,
+      "grad_norm": 7.0,
+      "learning_rate": 2.94392523364486e-06,
+      "loss": 0.564,
+      "step": 190
+    },
+    {
+      "epoch": 0.12468827930174564,
+      "grad_norm": 7.4375,
+      "learning_rate": 3.099688473520249e-06,
+      "loss": 0.5558,
+      "step": 200
+    },
+    {
+      "epoch": 0.13092269326683292,
+      "grad_norm": 7.03125,
+      "learning_rate": 3.2554517133956386e-06,
+      "loss": 0.5621,
+      "step": 210
+    },
+    {
+      "epoch": 0.1371571072319202,
+      "grad_norm": 7.4375,
+      "learning_rate": 3.411214953271028e-06,
+      "loss": 0.5494,
+      "step": 220
+    },
+    {
+      "epoch": 0.1433915211970075,
+      "grad_norm": 8.5,
+      "learning_rate": 3.5669781931464176e-06,
+      "loss": 0.529,
+      "step": 230
+    },
+    {
+      "epoch": 0.14962593516209477,
+      "grad_norm": 7.59375,
+      "learning_rate": 3.722741433021807e-06,
+      "loss": 0.4425,
+      "step": 240
+    },
+    {
+      "epoch": 0.15586034912718205,
+      "grad_norm": 3.859375,
+      "learning_rate": 3.878504672897196e-06,
+      "loss": 0.4133,
+      "step": 250
+    },
+    {
+      "epoch": 0.16209476309226933,
+      "grad_norm": 4.78125,
+      "learning_rate": 4.034267912772586e-06,
+      "loss": 0.38,
+      "step": 260
+    },
+    {
+      "epoch": 0.16832917705735662,
+      "grad_norm": 3.25,
+      "learning_rate": 4.190031152647975e-06,
+      "loss": 0.3687,
+      "step": 270
+    },
+    {
+      "epoch": 0.1745635910224439,
+      "grad_norm": 4.34375,
+      "learning_rate": 4.345794392523365e-06,
+      "loss": 0.3483,
+      "step": 280
+    },
+    {
+      "epoch": 0.18079800498753118,
+      "grad_norm": 2.953125,
+      "learning_rate": 4.501557632398754e-06,
+      "loss": 0.313,
+      "step": 290
+    },
+    {
+      "epoch": 0.18703241895261846,
+      "grad_norm": 3.53125,
+      "learning_rate": 4.657320872274144e-06,
+      "loss": 0.3015,
+      "step": 300
+    },
+    {
+      "epoch": 0.19326683291770574,
+      "grad_norm": 2.859375,
+      "learning_rate": 4.813084112149533e-06,
+      "loss": 0.2972,
+      "step": 310
+    },
+    {
+      "epoch": 0.19950124688279303,
+      "grad_norm": 2.734375,
+      "learning_rate": 4.968847352024923e-06,
+      "loss": 0.267,
+      "step": 320
+    },
+    {
+      "epoch": 0.2057356608478803,
+      "grad_norm": 1.71875,
+      "learning_rate": 5.124610591900312e-06,
+      "loss": 0.2438,
+      "step": 330
+    },
+    {
+      "epoch": 0.2119700748129676,
+      "grad_norm": 1.8828125,
+      "learning_rate": 5.280373831775702e-06,
+      "loss": 0.2143,
+      "step": 340
+    },
+    {
+      "epoch": 0.21820448877805487,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.436137071651091e-06,
+      "loss": 0.222,
+      "step": 350
+    },
+    {
+      "epoch": 0.22443890274314215,
+      "grad_norm": 1.6875,
+      "learning_rate": 5.591900311526481e-06,
+      "loss": 0.2028,
+      "step": 360
+    },
+    {
+      "epoch": 0.23067331670822944,
+      "grad_norm": 1.203125,
+      "learning_rate": 5.747663551401869e-06,
+      "loss": 0.2069,
+      "step": 370
+    },
+    {
+      "epoch": 0.23690773067331672,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.903426791277259e-06,
+      "loss": 0.1742,
+      "step": 380
+    },
+    {
+      "epoch": 0.243142144638404,
+      "grad_norm": 1.28125,
+      "learning_rate": 6.059190031152648e-06,
+      "loss": 0.1695,
+      "step": 390
+    },
+    {
+      "epoch": 0.24937655860349128,
+      "grad_norm": 1.4140625,
+      "learning_rate": 6.214953271028038e-06,
+      "loss": 0.1531,
+      "step": 400
+    },
+    {
+      "epoch": 0.25561097256857856,
+      "grad_norm": 1.3359375,
+      "learning_rate": 6.370716510903427e-06,
+      "loss": 0.15,
+      "step": 410
+    },
+    {
+      "epoch": 0.26184538653366585,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.526479750778817e-06,
+      "loss": 0.1335,
+      "step": 420
+    },
+    {
+      "epoch": 0.26807980049875313,
+      "grad_norm": 1.6015625,
+      "learning_rate": 6.682242990654206e-06,
+      "loss": 0.1319,
+      "step": 430
+    },
+    {
+      "epoch": 0.2743142144638404,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.838006230529596e-06,
+      "loss": 0.1324,
+      "step": 440
+    },
+    {
+      "epoch": 0.2805486284289277,
+      "grad_norm": 2.3125,
+      "learning_rate": 6.993769470404985e-06,
+      "loss": 0.1398,
+      "step": 450
+    },
+    {
+      "epoch": 0.286783042394015,
+      "grad_norm": 1.046875,
+      "learning_rate": 7.149532710280375e-06,
+      "loss": 0.1515,
+      "step": 460
+    },
+    {
+      "epoch": 0.29301745635910226,
+      "grad_norm": 1.84375,
+      "learning_rate": 7.305295950155764e-06,
+      "loss": 0.1532,
+      "step": 470
+    },
+    {
+      "epoch": 0.29925187032418954,
+      "grad_norm": 1.1171875,
+      "learning_rate": 7.461059190031154e-06,
+      "loss": 0.1515,
+      "step": 480
+    },
+    {
+      "epoch": 0.3054862842892768,
+      "grad_norm": 2.546875,
+      "learning_rate": 7.616822429906543e-06,
+      "loss": 0.1701,
+      "step": 490
+    },
+    {
+      "epoch": 0.3117206982543641,
+      "grad_norm": 1.171875,
+      "learning_rate": 7.772585669781933e-06,
+      "loss": 0.1711,
+      "step": 500
+    },
+    {
+      "epoch": 0.3179551122194514,
+      "grad_norm": 1.953125,
+      "learning_rate": 7.928348909657322e-06,
+      "loss": 0.1831,
+      "step": 510
+    },
+    {
+      "epoch": 0.32418952618453867,
+      "grad_norm": 1.1484375,
+      "learning_rate": 8.084112149532712e-06,
+      "loss": 0.165,
+      "step": 520
+    },
+    {
+      "epoch": 0.33042394014962595,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.2398753894081e-06,
+      "loss": 0.1688,
+      "step": 530
+    },
+    {
+      "epoch": 0.33665835411471323,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.395638629283491e-06,
+      "loss": 0.1683,
+      "step": 540
+    },
+    {
+      "epoch": 0.3428927680798005,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.55140186915888e-06,
+      "loss": 0.1693,
+      "step": 550
+    },
+    {
+      "epoch": 0.3491271820448878,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.707165109034268e-06,
+      "loss": 0.1761,
+      "step": 560
+    },
+    {
+      "epoch": 0.3553615960099751,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.862928348909659e-06,
+      "loss": 0.1681,
+      "step": 570
+    },
+    {
+      "epoch": 0.36159600997506236,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.018691588785047e-06,
+      "loss": 0.1618,
+      "step": 580
+    },
+    {
+      "epoch": 0.36783042394014964,
+      "grad_norm": 1.2265625,
+      "learning_rate": 9.174454828660438e-06,
+      "loss": 0.1696,
+      "step": 590
+    },
+    {
+      "epoch": 0.3740648379052369,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.330218068535826e-06,
+      "loss": 0.1407,
+      "step": 600
+    },
+    {
+      "epoch": 0.3802992518703242,
+      "grad_norm": 1.140625,
+      "learning_rate": 9.485981308411217e-06,
+      "loss": 0.1569,
+      "step": 610
+    },
+    {
+      "epoch": 0.3865336658354115,
+      "grad_norm": 0.921875,
+      "learning_rate": 9.641744548286605e-06,
+      "loss": 0.1404,
+      "step": 620
+    },
+    {
+      "epoch": 0.39276807980049877,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.797507788161996e-06,
+      "loss": 0.1505,
+      "step": 630
+    },
+    {
+      "epoch": 0.39900249376558605,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.953271028037384e-06,
+      "loss": 0.1205,
+      "step": 640
+    },
+    {
+      "epoch": 0.40523690773067333,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.99996373549532e-06,
+      "loss": 0.1139,
+      "step": 650
+    },
+    {
+      "epoch": 0.4114713216957606,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.999786114697945e-06,
+      "loss": 0.1127,
+      "step": 660
+    },
+    {
+      "epoch": 0.4177057356608479,
+      "grad_norm": 0.8359375,
+      "learning_rate": 9.999460482032132e-06,
+      "loss": 0.1018,
+      "step": 670
+    },
+    {
+      "epoch": 0.4239401496259352,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.998986847137795e-06,
+      "loss": 0.1058,
+      "step": 680
+    },
+    {
+      "epoch": 0.43017456359102246,
+      "grad_norm": 0.68359375,
+      "learning_rate": 9.998365224036252e-06,
+      "loss": 0.0972,
+      "step": 690
+    },
+    {
+      "epoch": 0.43640897755610975,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.997595631129806e-06,
+      "loss": 0.1083,
+      "step": 700
+    },
+    {
+      "epoch": 0.442643391521197,
+      "grad_norm": 3.421875,
+      "learning_rate": 9.996678091201213e-06,
+      "loss": 0.1209,
+      "step": 710
+    },
+    {
+      "epoch": 0.4488778054862843,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.99561263141299e-06,
+      "loss": 0.1233,
+      "step": 720
+    },
+    {
+      "epoch": 0.4551122194513716,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.994399283306628e-06,
+      "loss": 0.1257,
+      "step": 730
+    },
+    {
+      "epoch": 0.4613466334164589,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.993038082801648e-06,
+      "loss": 0.1274,
+      "step": 740
+    },
+    {
+      "epoch": 0.46758104738154616,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.991529070194539e-06,
+      "loss": 0.1228,
+      "step": 750
+    },
+    {
+      "epoch": 0.47381546134663344,
+      "grad_norm": 0.890625,
+      "learning_rate": 9.989872290157566e-06,
+      "loss": 0.1249,
+      "step": 760
+    },
+    {
+      "epoch": 0.4800498753117207,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.988067791737449e-06,
+      "loss": 0.1193,
+      "step": 770
+    },
+    {
+      "epoch": 0.486284289276808,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.986115628353911e-06,
+      "loss": 0.1207,
+      "step": 780
+    },
+    {
+      "epoch": 0.4925187032418953,
+      "grad_norm": 1.125,
+      "learning_rate": 9.984015857798095e-06,
+      "loss": 0.1197,
+      "step": 790
+    },
+    {
+      "epoch": 0.49875311720698257,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.981768542230847e-06,
+      "loss": 0.1325,
+      "step": 800
+    },
+    {
+      "epoch": 0.5049875311720698,
+      "grad_norm": 0.98046875,
+      "learning_rate": 9.979373748180896e-06,
+      "loss": 0.132,
+      "step": 810
+    },
+    {
+      "epoch": 0.5112219451371571,
+      "grad_norm": 0.96484375,
+      "learning_rate": 9.976831546542858e-06,
+      "loss": 0.1356,
+      "step": 820
+    },
+    {
+      "epoch": 0.5174563591022444,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.974142012575156e-06,
+      "loss": 0.1313,
+      "step": 830
+    },
+    {
+      "epoch": 0.5236907730673317,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.971305225897788e-06,
+      "loss": 0.1333,
+      "step": 840
+    },
+    {
+      "epoch": 0.529925187032419,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.968321270489963e-06,
+      "loss": 0.1247,
+      "step": 850
+    },
+    {
+      "epoch": 0.5361596009975063,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.965190234687622e-06,
+      "loss": 0.1316,
+      "step": 860
+    },
+    {
+      "epoch": 0.5423940149625935,
+      "grad_norm": 0.625,
+      "learning_rate": 9.961912211180824e-06,
+      "loss": 0.1281,
+      "step": 870
+    },
+    {
+      "epoch": 0.5486284289276808,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.958487297010997e-06,
+      "loss": 0.1346,
+      "step": 880
+    },
+    {
+      "epoch": 0.5548628428927681,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.954915593568066e-06,
+      "loss": 0.1349,
+      "step": 890
+    },
+    {
+      "epoch": 0.5610972568578554,
+      "grad_norm": 1.3828125,
+      "learning_rate": 9.951197206587455e-06,
+      "loss": 0.1319,
+      "step": 900
+    },
+    {
+      "epoch": 0.5673316708229427,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.947332246146952e-06,
+      "loss": 0.1303,
+      "step": 910
+    },
+    {
+      "epoch": 0.57356608478803,
+      "grad_norm": 1.1875,
+      "learning_rate": 9.943320826663458e-06,
+      "loss": 0.1356,
+      "step": 920
+    },
+    {
+      "epoch": 0.5798004987531172,
+      "grad_norm": 0.69921875,
+      "learning_rate": 9.939163066889587e-06,
+      "loss": 0.1324,
+      "step": 930
+    },
+    {
+      "epoch": 0.5860349127182045,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.934859089910167e-06,
+      "loss": 0.1468,
+      "step": 940
+    },
+    {
+      "epoch": 0.5922693266832918,
+      "grad_norm": 0.82421875,
+      "learning_rate": 9.93040902313858e-06,
+      "loss": 0.1377,
+      "step": 950
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "grad_norm": 1.2734375,
+      "learning_rate": 9.925812998313005e-06,
+      "loss": 0.1332,
+      "step": 960
+    },
+    {
+      "epoch": 0.6047381546134664,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.921071151492501e-06,
+      "loss": 0.1382,
+      "step": 970
+    },
+    {
+      "epoch": 0.6109725685785536,
+      "grad_norm": 1.359375,
+      "learning_rate": 9.916183623053e-06,
+      "loss": 0.1419,
+      "step": 980
+    },
+    {
+      "epoch": 0.6172069825436409,
+      "grad_norm": 1.171875,
+      "learning_rate": 9.91115055768313e-06,
+      "loss": 0.1392,
+      "step": 990
+    },
+    {
+      "epoch": 0.6234413965087282,
+      "grad_norm": 1.375,
+      "learning_rate": 9.905972104379948e-06,
+      "loss": 0.1337,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6296758104738155,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.900648416444524e-06,
+      "loss": 0.1244,
+      "step": 1010
+    },
+    {
+      "epoch": 0.6359102244389028,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.895179651477396e-06,
+      "loss": 0.1303,
+      "step": 1020
+    },
+    {
+      "epoch": 0.64214463840399,
+      "grad_norm": 1.0546875,
+      "learning_rate": 9.889565971373916e-06,
+      "loss": 0.1253,
+      "step": 1030
+    },
+    {
+      "epoch": 0.6483790523690773,
+      "grad_norm": 1.78125,
+      "learning_rate": 9.883807542319447e-06,
+      "loss": 0.1274,
+      "step": 1040
+    },
+    {
+      "epoch": 0.6546134663341646,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.877904534784451e-06,
+      "loss": 0.1158,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6608478802992519,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.871857123519439e-06,
+      "loss": 0.1314,
+      "step": 1060
+    },
+    {
+      "epoch": 0.6670822942643392,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.865665487549796e-06,
+      "loss": 0.1236,
+      "step": 1070
+    },
+    {
+      "epoch": 0.6733167082294265,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.859329810170487e-06,
+      "loss": 0.1344,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6795511221945137,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.85285027894062e-06,
+      "loss": 0.1185,
+      "step": 1090
+    },
+    {
+      "epoch": 0.685785536159601,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.846227085677909e-06,
+      "loss": 0.1348,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6920199501246883,
+      "grad_norm": 1.21875,
+      "learning_rate": 9.83946042645298e-06,
+      "loss": 0.1302,
+      "step": 1110
+    },
+    {
+      "epoch": 0.6982543640897756,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.832550501583582e-06,
+      "loss": 0.1501,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7044887780548629,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.82549751562864e-06,
+      "loss": 0.1474,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7107231920199502,
+      "grad_norm": 1.75,
+      "learning_rate": 9.818301677382212e-06,
+      "loss": 0.1688,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7169576059850374,
+      "grad_norm": 2.46875,
+      "learning_rate": 9.810963199867302e-06,
+      "loss": 0.1695,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7231920199501247,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.80348230032956e-06,
+      "loss": 0.1561,
+      "step": 1160
+    },
+    {
+      "epoch": 0.729426433915212,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.79585920023084e-06,
+      "loss": 0.1424,
+      "step": 1170
+    },
+    {
+      "epoch": 0.7356608478802993,
+      "grad_norm": 1.375,
+      "learning_rate": 9.788094125242655e-06,
+      "loss": 0.154,
+      "step": 1180
+    },
+    {
+      "epoch": 0.7418952618453866,
+      "grad_norm": 1.125,
+      "learning_rate": 9.780187305239491e-06,
+      "loss": 0.1447,
+      "step": 1190
+    },
+    {
+      "epoch": 0.7481296758104738,
+      "grad_norm": 1.2890625,
+      "learning_rate": 9.772138974291999e-06,
+      "loss": 0.1364,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7543640897755611,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.763949370660072e-06,
+      "loss": 0.1317,
+      "step": 1210
+    },
+    {
+      "epoch": 0.7605985037406484,
+      "grad_norm": 1.875,
+      "learning_rate": 9.755618736785786e-06,
+      "loss": 0.1438,
+      "step": 1220
+    },
+    {
+      "epoch": 0.7668329177057357,
+      "grad_norm": 0.84765625,
+      "learning_rate": 9.747147319286232e-06,
+      "loss": 0.1186,
+      "step": 1230
+    },
+    {
+      "epoch": 0.773067331670823,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.738535368946202e-06,
+      "loss": 0.1271,
+      "step": 1240
+    },
+    {
+      "epoch": 0.7793017456359103,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.729783140710773e-06,
+      "loss": 0.113,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7855361596009975,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.72089089367776e-06,
+      "loss": 0.1232,
+      "step": 1260
+    },
+    {
+      "epoch": 0.7917705735660848,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.711858891090044e-06,
+      "loss": 0.1098,
+      "step": 1270
+    },
+    {
+      "epoch": 0.7980049875311721,
+      "grad_norm": 1.3515625,
+      "learning_rate": 9.70268740032778e-06,
+      "loss": 0.1112,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8042394014962594,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.693376692900476e-06,
+      "loss": 0.1112,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8104738154613467,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.683927044438963e-06,
+      "loss": 0.1076,
+      "step": 1300
+    },
+    {
+      "epoch": 0.816708229426434,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.674338734687236e-06,
+      "loss": 0.1102,
+      "step": 1310
+    },
+    {
+      "epoch": 0.8229426433915212,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.664612047494162e-06,
+      "loss": 0.1079,
+      "step": 1320
+    },
+    {
+      "epoch": 0.8291770573566085,
+      "grad_norm": 0.8359375,
+      "learning_rate": 9.65474727080509e-06,
+      "loss": 0.1145,
+      "step": 1330
+    },
+    {
+      "epoch": 0.8354114713216958,
+      "grad_norm": 0.8359375,
+      "learning_rate": 9.644744696653316e-06,
+      "loss": 0.1086,
+      "step": 1340
+    },
+    {
+      "epoch": 0.8416458852867831,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.63460462115145e-06,
+      "loss": 0.118,
+      "step": 1350
+    },
+    {
+      "epoch": 0.8478802992518704,
+      "grad_norm": 0.75,
+      "learning_rate": 9.624327344482629e-06,
+      "loss": 0.1165,
+      "step": 1360
+    },
+    {
+      "epoch": 0.8541147132169576,
+      "grad_norm": 0.96484375,
+      "learning_rate": 9.613913170891659e-06,
+      "loss": 0.1176,
+      "step": 1370
+    },
+    {
+      "epoch": 0.8603491271820449,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.60336240867598e-06,
+      "loss": 0.1108,
+      "step": 1380
+    },
+    {
+      "epoch": 0.8665835411471322,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.592675370176565e-06,
+      "loss": 0.1124,
+      "step": 1390
+    },
+    {
+      "epoch": 0.8728179551122195,
+      "grad_norm": 0.67578125,
+      "learning_rate": 9.581852371768652e-06,
+      "loss": 0.1032,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8790523690773068,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.57089373385239e-06,
+      "loss": 0.1003,
+      "step": 1410
+    },
+    {
+      "epoch": 0.885286783042394,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.559799780843353e-06,
+      "loss": 0.0995,
+      "step": 1420
+    },
+    {
+      "epoch": 0.8915211970074813,
+      "grad_norm": 0.828125,
+      "learning_rate": 9.548570841162931e-06,
+      "loss": 0.0949,
+      "step": 1430
+    },
+    {
+      "epoch": 0.8977556109725686,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.537207247228612e-06,
+      "loss": 0.0989,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9039900249376559,
+      "grad_norm": 0.71484375,
+      "learning_rate": 9.525709335444142e-06,
+      "loss": 0.0936,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9102244389027432,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.51407744618956e-06,
+      "loss": 0.0871,
+      "step": 1460
+    },
+    {
+      "epoch": 0.9164588528678305,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.502311923811131e-06,
+      "loss": 0.1,
+      "step": 1470
+    },
+    {
+      "epoch": 0.9226932668329177,
+      "grad_norm": 0.6953125,
+      "learning_rate": 9.490413116611143e-06,
+      "loss": 0.0937,
+      "step": 1480
+    },
+    {
+      "epoch": 0.928927680798005,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.478381376837603e-06,
+      "loss": 0.0932,
+      "step": 1490
+    },
+    {
+      "epoch": 0.9351620947630923,
+      "grad_norm": 0.546875,
+      "learning_rate": 9.466217060673804e-06,
+      "loss": 0.0945,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9413965087281796,
+      "grad_norm": 1.0,
+      "learning_rate": 9.45392052822778e-06,
+      "loss": 0.1,
+      "step": 1510
+    },
+    {
+      "epoch": 0.9476309226932669,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.441492143521656e-06,
+      "loss": 0.0973,
+      "step": 1520
+    },
+    {
+      "epoch": 0.9538653366583542,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.428932274480855e-06,
+      "loss": 0.1023,
+      "step": 1530
+    },
+    {
+      "epoch": 0.9600997506234414,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.416241292923223e-06,
+      "loss": 0.0997,
+      "step": 1540
+    },
+    {
+      "epoch": 0.9663341645885287,
+      "grad_norm": 0.8671875,
+      "learning_rate": 9.403419574548007e-06,
+      "loss": 0.1,
+      "step": 1550
+    },
+    {
+      "epoch": 0.972568578553616,
+      "grad_norm": 0.9765625,
+      "learning_rate": 9.390467498924745e-06,
+      "loss": 0.1077,
+      "step": 1560
+    },
+    {
+      "epoch": 0.9788029925187033,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.377385449482018e-06,
+      "loss": 0.1115,
+      "step": 1570
+    },
+    {
+      "epoch": 0.9850374064837906,
+      "grad_norm": 1.203125,
+      "learning_rate": 9.36417381349611e-06,
+      "loss": 0.1176,
+      "step": 1580
+    },
+    {
+      "epoch": 0.9912718204488778,
+      "grad_norm": 1.3125,
+      "learning_rate": 9.35083298207954e-06,
+      "loss": 0.1207,
+      "step": 1590
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.337363350169475e-06,
+      "loss": 0.1157,
+      "step": 1600
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1406659632921219,
+      "eval_runtime": 575.0322,
+      "eval_samples_per_second": 12.749,
+      "eval_steps_per_second": 0.798,
+      "step": 1604
+    },
+    {
+      "epoch": 1.0037406483790523,
+      "grad_norm": 0.59765625,
+      "learning_rate": 9.323765316516054e-06,
+      "loss": 0.1062,
+      "step": 1610
+    },
+    {
+      "epoch": 1.0099750623441397,
+      "grad_norm": 0.67578125,
+      "learning_rate": 9.310039283670566e-06,
+      "loss": 0.1037,
+      "step": 1620
+    },
+    {
+      "epoch": 1.0162094763092269,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.296185657973548e-06,
+      "loss": 0.1087,
+      "step": 1630
+    },
+    {
+      "epoch": 1.0224438902743143,
+      "grad_norm": 0.8125,
+      "learning_rate": 9.282204849542752e-06,
+      "loss": 0.1012,
+      "step": 1640
+    },
+    {
+      "epoch": 1.0286783042394014,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.268097272260993e-06,
+      "loss": 0.1325,
+      "step": 1650
+    },
+    {
+      "epoch": 1.0349127182044888,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.253863343763914e-06,
+      "loss": 0.1402,
+      "step": 1660
+    },
+    {
+      "epoch": 1.041147132169576,
+      "grad_norm": 1.2578125,
+      "learning_rate": 9.23950348542761e-06,
+      "loss": 0.1371,
+      "step": 1670
+    },
+    {
+      "epoch": 1.0473815461346634,
+      "grad_norm": 1.2578125,
+      "learning_rate": 9.225018122356157e-06,
+      "loss": 0.1463,
+      "step": 1680
+    },
+    {
+      "epoch": 1.0536159600997506,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.210407683369033e-06,
+      "loss": 0.1436,
+      "step": 1690
+    },
+    {
+      "epoch": 1.059850374064838,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.19567260098841e-06,
+      "loss": 0.1308,
+      "step": 1700
+    },
+    {
+      "epoch": 1.0660847880299251,
+      "grad_norm": 1.25,
+      "learning_rate": 9.180813311426365e-06,
+      "loss": 0.1431,
+      "step": 1710
+    },
+    {
+      "epoch": 1.0723192019950125,
+      "grad_norm": 1.375,
+      "learning_rate": 9.16583025457196e-06,
+      "loss": 0.1416,
+      "step": 1720
+    },
+    {
+      "epoch": 1.0785536159600997,
+      "grad_norm": 1.2109375,
+      "learning_rate": 9.15072387397821e-06,
+      "loss": 0.1397,
+      "step": 1730
+    },
+    {
+      "epoch": 1.084788029925187,
+      "grad_norm": 1.2890625,
+      "learning_rate": 9.135494616848975e-06,
+      "loss": 0.1393,
+      "step": 1740
+    },
+    {
+      "epoch": 1.0910224438902743,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.1201429340257e-06,
+      "loss": 0.1181,
+      "step": 1750
+    },
+    {
+      "epoch": 1.0972568578553616,
+      "grad_norm": 1.21875,
+      "learning_rate": 9.104669279974074e-06,
+      "loss": 0.123,
+      "step": 1760
+    },
+    {
+      "epoch": 1.1034912718204488,
+      "grad_norm": 0.81640625,
+      "learning_rate": 9.089074112770585e-06,
+      "loss": 0.1036,
+      "step": 1770
+    },
+    {
+      "epoch": 1.1097256857855362,
+      "grad_norm": 1.125,
+      "learning_rate": 9.073357894088947e-06,
+      "loss": 0.1092,
+      "step": 1780
+    },
+    {
+      "epoch": 1.1159600997506234,
+      "grad_norm": 0.953125,
+      "learning_rate": 9.057521089186445e-06,
+      "loss": 0.1085,
+      "step": 1790
+    },
+    {
+      "epoch": 1.1221945137157108,
+      "grad_norm": 1.1640625,
+      "learning_rate": 9.041564166890146e-06,
+      "loss": 0.1106,
+      "step": 1800
+    },
+    {
+      "epoch": 1.128428927680798,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.025487599583035e-06,
+      "loss": 0.1015,
+      "step": 1810
+    },
+    {
+      "epoch": 1.1346633416458853,
+      "grad_norm": 0.89453125,
+      "learning_rate": 9.009291863190025e-06,
+      "loss": 0.106,
+      "step": 1820
+    },
+    {
+      "epoch": 1.1408977556109725,
+      "grad_norm": 1.1484375,
+      "learning_rate": 8.992977437163866e-06,
+      "loss": 0.1114,
+      "step": 1830
+    },
+    {
+      "epoch": 1.14713216957606,
+      "grad_norm": 0.86328125,
+      "learning_rate": 8.976544804470954e-06,
+      "loss": 0.1144,
+      "step": 1840
+    },
+    {
+      "epoch": 1.153366583541147,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.95999445157703e-06,
+      "loss": 0.1131,
+      "step": 1850
+    },
+    {
+      "epoch": 1.1596009975062345,
+      "grad_norm": 0.7109375,
+      "learning_rate": 8.943326868432786e-06,
+      "loss": 0.1093,
+      "step": 1860
+    },
+    {
+      "epoch": 1.1658354114713216,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.926542548459354e-06,
+      "loss": 0.1083,
+      "step": 1870
+    },
+    {
+      "epoch": 1.172069825436409,
+      "grad_norm": 0.625,
+      "learning_rate": 8.9096419885337e-06,
+      "loss": 0.1009,
+      "step": 1880
+    },
+    {
+      "epoch": 1.1783042394014962,
+      "grad_norm": 1.296875,
+      "learning_rate": 8.892625688973914e-06,
+      "loss": 0.1082,
+      "step": 1890
+    },
+    {
+      "epoch": 1.1845386533665836,
+      "grad_norm": 0.76953125,
+      "learning_rate": 8.875494153524409e-06,
+      "loss": 0.1008,
+      "step": 1900
+    },
+    {
+      "epoch": 1.1907730673316708,
+      "grad_norm": 1.2578125,
+      "learning_rate": 8.858247889340987e-06,
+      "loss": 0.1034,
+      "step": 1910
+    },
+    {
+      "epoch": 1.1970074812967582,
+      "grad_norm": 0.69921875,
+      "learning_rate": 8.840887406975851e-06,
+      "loss": 0.0973,
+      "step": 1920
+    },
+    {
+      "epoch": 1.2032418952618453,
+      "grad_norm": 1.2890625,
+      "learning_rate": 8.823413220362468e-06,
+      "loss": 0.0972,
+      "step": 1930
+    },
+    {
+      "epoch": 1.2094763092269327,
+      "grad_norm": 0.84375,
+      "learning_rate": 8.80582584680037e-06,
+      "loss": 0.0923,
+      "step": 1940
+    },
+    {
+      "epoch": 1.21571072319202,
+      "grad_norm": 0.71875,
+      "learning_rate": 8.788125806939833e-06,
+      "loss": 0.0939,
+      "step": 1950
+    },
+    {
+      "epoch": 1.2219451371571073,
+      "grad_norm": 0.8671875,
+      "learning_rate": 8.770313624766467e-06,
+      "loss": 0.0912,
+      "step": 1960
+    },
+    {
+      "epoch": 1.2281795511221945,
+      "grad_norm": 0.73046875,
+      "learning_rate": 8.7523898275857e-06,
+      "loss": 0.0912,
+      "step": 1970
+    },
+    {
+      "epoch": 1.2344139650872819,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.734354946007173e-06,
+      "loss": 0.0889,
+      "step": 1980
+    },
+    {
+      "epoch": 1.240648379052369,
+      "grad_norm": 0.8125,
+      "learning_rate": 8.716209513929027e-06,
+      "loss": 0.0919,
+      "step": 1990
+    },
+    {
+      "epoch": 1.2468827930174564,
+      "grad_norm": 0.8046875,
+      "learning_rate": 8.697954068522104e-06,
+      "loss": 0.0875,
+      "step": 2000
+    },
+    {
+      "epoch": 1.2531172069825436,
+      "grad_norm": 0.9140625,
+      "learning_rate": 8.679589150214035e-06,
+      "loss": 0.0892,
+      "step": 2010
+    },
+    {
+      "epoch": 1.259351620947631,
+      "grad_norm": 0.859375,
+      "learning_rate": 8.661115302673255e-06,
+      "loss": 0.0843,
+      "step": 2020
+    },
+    {
+      "epoch": 1.2655860349127181,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.642533072792894e-06,
+      "loss": 0.0808,
+      "step": 2030
+    },
+    {
+      "epoch": 1.2718204488778055,
+      "grad_norm": 0.76171875,
+      "learning_rate": 8.623843010674597e-06,
+      "loss": 0.0861,
+      "step": 2040
+    },
+    {
+      "epoch": 1.2780548628428927,
+      "grad_norm": 1.28125,
+      "learning_rate": 8.605045669612238e-06,
+      "loss": 0.0892,
+      "step": 2050
+    },
+    {
+      "epoch": 1.28428927680798,
+      "grad_norm": 0.78125,
+      "learning_rate": 8.586141606075533e-06,
+      "loss": 0.0916,
+      "step": 2060
+    },
+    {
+      "epoch": 1.2905236907730673,
+      "grad_norm": 1.34375,
+      "learning_rate": 8.567131379693574e-06,
+      "loss": 0.0954,
+      "step": 2070
+    },
+    {
+      "epoch": 1.2967581047381547,
+      "grad_norm": 0.78125,
+      "learning_rate": 8.548015553238263e-06,
+      "loss": 0.1045,
+      "step": 2080
+    },
+    {
+      "epoch": 1.3029925187032418,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.52879469260764e-06,
+      "loss": 0.1074,
+      "step": 2090
+    },
+    {
+      "epoch": 1.3092269326683292,
+      "grad_norm": 1.0234375,
+      "learning_rate": 8.509469366809152e-06,
+      "loss": 0.1111,
+      "step": 2100
+    },
+    {
+      "epoch": 1.3154613466334164,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.49004014794278e-06,
+      "loss": 0.113,
+      "step": 2110
+    },
+    {
+      "epoch": 1.3216957605985038,
+      "grad_norm": 0.99609375,
+      "learning_rate": 8.470507611184132e-06,
+      "loss": 0.1259,
+      "step": 2120
+    },
+    {
+      "epoch": 1.327930174563591,
+      "grad_norm": 1.109375,
+      "learning_rate": 8.450872334767391e-06,
+      "loss": 0.1255,
+      "step": 2130
+    },
+    {
+      "epoch": 1.3341645885286784,
+      "grad_norm": 1.0390625,
+      "learning_rate": 8.431134899968213e-06,
+      "loss": 0.1215,
+      "step": 2140
+    },
+    {
+      "epoch": 1.3403990024937655,
+      "grad_norm": 1.078125,
+      "learning_rate": 8.411295891086516e-06,
+      "loss": 0.125,
+      "step": 2150
+    },
+    {
+      "epoch": 1.346633416458853,
+      "grad_norm": 1.0234375,
+      "learning_rate": 8.391355895429173e-06,
+      "loss": 0.1331,
+      "step": 2160
+    },
+    {
+      "epoch": 1.35286783042394,
+      "grad_norm": 1.015625,
+      "learning_rate": 8.371315503292644e-06,
+      "loss": 0.1285,
+      "step": 2170
+    },
+    {
+      "epoch": 1.3591022443890275,
+      "grad_norm": 0.859375,
+      "learning_rate": 8.351175307945478e-06,
+      "loss": 0.131,
+      "step": 2180
+    },
+    {
+      "epoch": 1.3653366583541147,
+      "grad_norm": 1.09375,
+      "learning_rate": 8.330935905610772e-06,
+      "loss": 0.1277,
+      "step": 2190
+    },
+    {
+      "epoch": 1.371571072319202,
+      "grad_norm": 0.90625,
+      "learning_rate": 8.310597895448507e-06,
+      "loss": 0.1196,
+      "step": 2200
+    },
+    {
+      "epoch": 1.3778054862842892,
+      "grad_norm": 0.99609375,
+      "learning_rate": 8.290161879537815e-06,
+      "loss": 0.1219,
+      "step": 2210
+    },
+    {
+      "epoch": 1.3840399002493766,
+      "grad_norm": 0.703125,
+      "learning_rate": 8.269628462859155e-06,
+      "loss": 0.1134,
+      "step": 2220
+    },
+    {
+      "epoch": 1.3902743142144638,
+      "grad_norm": 0.83984375,
+      "learning_rate": 8.2489982532764e-06,
+      "loss": 0.1101,
+      "step": 2230
+    },
+    {
+      "epoch": 1.3965087281795512,
+      "grad_norm": 0.65625,
+      "learning_rate": 8.228271861518853e-06,
+      "loss": 0.1005,
+      "step": 2240
+    },
+    {
+      "epoch": 1.4027431421446384,
+      "grad_norm": 1.0234375,
+      "learning_rate": 8.207449901163155e-06,
+      "loss": 0.095,
+      "step": 2250
+    },
+    {
+      "epoch": 1.4089775561097257,
+      "grad_norm": 0.68359375,
+      "learning_rate": 8.186532988615124e-06,
+      "loss": 0.0937,
+      "step": 2260
+    },
+    {
+      "epoch": 1.415211970074813,
+      "grad_norm": 0.7734375,
+      "learning_rate": 8.165521743091507e-06,
+      "loss": 0.0947,
+      "step": 2270
+    },
+    {
+      "epoch": 1.4214463840399003,
+      "grad_norm": 0.625,
+      "learning_rate": 8.144416786601658e-06,
+      "loss": 0.0898,
+      "step": 2280
+    },
+    {
+      "epoch": 1.4276807980049875,
+      "grad_norm": 0.59375,
+      "learning_rate": 8.12321874392911e-06,
+      "loss": 0.0841,
+      "step": 2290
+    },
+    {
+      "epoch": 1.4339152119700749,
+      "grad_norm": 0.61328125,
+      "learning_rate": 8.101928242613087e-06,
+      "loss": 0.0804,
+      "step": 2300
+    },
+    {
+      "epoch": 1.440149625935162,
+      "grad_norm": 0.9140625,
+      "learning_rate": 8.080545912929928e-06,
+      "loss": 0.0862,
+      "step": 2310
+    },
+    {
+      "epoch": 1.4463840399002494,
+      "grad_norm": 0.76171875,
+      "learning_rate": 8.059072387874426e-06,
+      "loss": 0.0876,
+      "step": 2320
+    },
+    {
+      "epoch": 1.4526184538653366,
+      "grad_norm": 0.953125,
+      "learning_rate": 8.037508303141082e-06,
+      "loss": 0.1,
+      "step": 2330
+    },
+    {
+      "epoch": 1.458852867830424,
+      "grad_norm": 0.6953125,
+      "learning_rate": 8.015854297105302e-06,
+      "loss": 0.0925,
+      "step": 2340
+    },
+    {
+      "epoch": 1.4650872817955112,
+      "grad_norm": 0.73828125,
+      "learning_rate": 7.994111010804483e-06,
+      "loss": 0.0998,
+      "step": 2350
+    },
+    {
+      "epoch": 1.4713216957605986,
+      "grad_norm": 0.76171875,
+      "learning_rate": 7.972279087919051e-06,
+      "loss": 0.0921,
+      "step": 2360
+    },
+    {
+      "epoch": 1.4775561097256857,
+      "grad_norm": 0.77734375,
+      "learning_rate": 7.95035917475339e-06,
+      "loss": 0.0966,
+      "step": 2370
+    },
+    {
+      "epoch": 1.4837905236907731,
+      "grad_norm": 0.87109375,
+      "learning_rate": 7.928351920216719e-06,
+      "loss": 0.0924,
+      "step": 2380
+    },
+    {
+      "epoch": 1.4900249376558603,
+      "grad_norm": 0.98828125,
+      "learning_rate": 7.90625797580388e-06,
+      "loss": 0.0997,
+      "step": 2390
+    },
+    {
+      "epoch": 1.4962593516209477,
+      "grad_norm": 0.796875,
+      "learning_rate": 7.884077995576048e-06,
+      "loss": 0.1113,
+      "step": 2400
+    },
+    {
+      "epoch": 1.5024937655860349,
+      "grad_norm": 0.921875,
+      "learning_rate": 7.861812636141377e-06,
+      "loss": 0.1085,
+      "step": 2410
+    },
+    {
+      "epoch": 1.508728179551122,
+      "grad_norm": 0.83984375,
+      "learning_rate": 7.839462556635553e-06,
+      "loss": 0.1135,
+      "step": 2420
+    },
+    {
+      "epoch": 1.5149625935162094,
+      "grad_norm": 0.78515625,
+      "learning_rate": 7.817028418702284e-06,
+      "loss": 0.108,
+      "step": 2430
+    },
+    {
+      "epoch": 1.5211970074812968,
+      "grad_norm": 0.8828125,
+      "learning_rate": 7.794510886473714e-06,
+      "loss": 0.1108,
+      "step": 2440
+    },
+    {
+      "epoch": 1.527431421446384,
+      "grad_norm": 0.71484375,
+      "learning_rate": 7.771910626550762e-06,
+      "loss": 0.1122,
+      "step": 2450
+    },
+    {
+      "epoch": 1.5336658354114712,
+      "grad_norm": 0.90234375,
+      "learning_rate": 7.749228307983387e-06,
+      "loss": 0.1167,
+      "step": 2460
+    },
+    {
+      "epoch": 1.5399002493765586,
+      "grad_norm": 0.68359375,
+      "learning_rate": 7.726464602250784e-06,
+      "loss": 0.1149,
+      "step": 2470
+    },
+    {
+      "epoch": 1.546134663341646,
+      "grad_norm": 0.93359375,
+      "learning_rate": 7.703620183241502e-06,
+      "loss": 0.1164,
+      "step": 2480
+    },
+    {
+      "epoch": 1.5523690773067331,
+      "grad_norm": 0.609375,
+      "learning_rate": 7.680695727233502e-06,
+      "loss": 0.1251,
+      "step": 2490
+    },
+    {
+      "epoch": 1.5586034912718203,
+      "grad_norm": 1.0234375,
+      "learning_rate": 7.657691912874124e-06,
+      "loss": 0.1216,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5648379052369077,
+      "grad_norm": 0.65625,
+      "learning_rate": 7.63460942116001e-06,
+      "loss": 0.1232,
+      "step": 2510
+    },
+    {
+      "epoch": 1.571072319201995,
+      "grad_norm": 1.1875,
+      "learning_rate": 7.611448935416934e-06,
+      "loss": 0.1231,
+      "step": 2520
+    },
+    {
+      "epoch": 1.5773067331670823,
+      "grad_norm": 0.63671875,
+      "learning_rate": 7.588211141279584e-06,
+      "loss": 0.1198,
+      "step": 2530
+    },
+    {
+      "epoch": 1.5835411471321694,
+      "grad_norm": 0.91015625,
+      "learning_rate": 7.564896726671247e-06,
+      "loss": 0.1186,
+      "step": 2540
+    },
+    {
+      "epoch": 1.5897755610972568,
+      "grad_norm": 0.76171875,
+      "learning_rate": 7.541506381783463e-06,
+      "loss": 0.1171,
+      "step": 2550
+    },
+    {
+      "epoch": 1.5960099750623442,
+      "grad_norm": 0.89453125,
+      "learning_rate": 7.518040799055583e-06,
+      "loss": 0.1105,
+      "step": 2560
+    },
+    {
+      "epoch": 1.6022443890274314,
+      "grad_norm": 0.8359375,
+      "learning_rate": 7.4945006731542746e-06,
+      "loss": 0.1142,
+      "step": 2570
+    },
+    {
+      "epoch": 1.6084788029925186,
+      "grad_norm": 1.1015625,
+      "learning_rate": 7.470886700952947e-06,
+      "loss": 0.1108,
+      "step": 2580
+    },
+    {
+      "epoch": 1.614713216957606,
+      "grad_norm": 0.81640625,
+      "learning_rate": 7.447199581511135e-06,
+      "loss": 0.1162,
+      "step": 2590
+    },
+    {
+      "epoch": 1.6209476309226933,
+      "grad_norm": 1.03125,
+      "learning_rate": 7.423440016053795e-06,
+      "loss": 0.1192,
+      "step": 2600
+    },
+    {
+      "epoch": 1.6271820448877805,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.399608707950553e-06,
+      "loss": 0.113,
+      "step": 2610
+    },
+    {
+      "epoch": 1.6334164588528677,
+      "grad_norm": 1.3125,
+      "learning_rate": 7.375706362694873e-06,
+      "loss": 0.1059,
+      "step": 2620
+    },
+    {
+      "epoch": 1.639650872817955,
+      "grad_norm": 1.0859375,
+      "learning_rate": 7.351733687883183e-06,
+      "loss": 0.1063,
+      "step": 2630
+    },
+    {
+      "epoch": 1.6458852867830425,
+      "grad_norm": 1.140625,
+      "learning_rate": 7.327691393193918e-06,
+      "loss": 0.103,
+      "step": 2640
+    },
+    {
+      "epoch": 1.6521197007481296,
+      "grad_norm": 0.84765625,
+      "learning_rate": 7.303580190366513e-06,
+      "loss": 0.1001,
+      "step": 2650
+    },
+    {
+      "epoch": 1.6583541147132168,
+      "grad_norm": 1.3515625,
+      "learning_rate": 7.279400793180341e-06,
+      "loss": 0.1064,
+      "step": 2660
+    },
+    {
+      "epoch": 1.6645885286783042,
+      "grad_norm": 1.09375,
+      "learning_rate": 7.255153917433572e-06,
+      "loss": 0.1037,
+      "step": 2670
+    },
+    {
+      "epoch": 1.6708229426433916,
+      "grad_norm": 1.4921875,
+      "learning_rate": 7.230840280921987e-06,
+      "loss": 0.1118,
+      "step": 2680
+    },
+    {
+      "epoch": 1.6770573566084788,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.206460603417731e-06,
+      "loss": 0.1057,
+      "step": 2690
+    },
+    {
+      "epoch": 1.683291770573566,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.182015606648e-06,
+      "loss": 0.1188,
+      "step": 2700
+    },
+    {
+      "epoch": 1.6895261845386533,
+      "grad_norm": 1.265625,
+      "learning_rate": 7.1575060142736785e-06,
+      "loss": 0.1122,
+      "step": 2710
+    },
+    {
+      "epoch": 1.6957605985037407,
+      "grad_norm": 1.3828125,
+      "learning_rate": 7.132932551867917e-06,
+      "loss": 0.1223,
+      "step": 2720
+    },
+    {
+      "epoch": 1.701995012468828,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.108295946894654e-06,
+      "loss": 0.1168,
+      "step": 2730
+    },
+    {
+      "epoch": 1.708229426433915,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.083596928687071e-06,
+      "loss": 0.1327,
+      "step": 2740
+    },
+    {
+      "epoch": 1.7144638403990025,
+      "grad_norm": 2.015625,
+      "learning_rate": 7.058836228426016e-06,
+      "loss": 0.1321,
+      "step": 2750
+    },
+    {
+      "epoch": 1.7206982543640899,
+      "grad_norm": 1.390625,
+      "learning_rate": 7.034014579118344e-06,
+      "loss": 0.1302,
+      "step": 2760
+    },
+    {
+      "epoch": 1.726932668329177,
+      "grad_norm": 1.7265625,
+      "learning_rate": 7.009132715575227e-06,
+      "loss": 0.1261,
+      "step": 2770
+    },
+    {
+      "epoch": 1.7331670822942642,
+      "grad_norm": 1.3515625,
+      "learning_rate": 6.9841913743903986e-06,
+      "loss": 0.127,
+      "step": 2780
+    },
+    {
+      "epoch": 1.7394014962593516,
+      "grad_norm": 1.2734375,
+      "learning_rate": 6.959191293918344e-06,
+      "loss": 0.1238,
+      "step": 2790
+    },
+    {
+      "epoch": 1.745635910224439,
+      "grad_norm": 1.671875,
+      "learning_rate": 6.934133214252448e-06,
+      "loss": 0.1335,
+      "step": 2800
+    },
+    {
+      "epoch": 1.7518703241895262,
+      "grad_norm": 1.234375,
+      "learning_rate": 6.909017877203078e-06,
+      "loss": 0.1174,
+      "step": 2810
+    },
+    {
+      "epoch": 1.7581047381546133,
+      "grad_norm": 1.421875,
+      "learning_rate": 6.883846026275635e-06,
+      "loss": 0.1222,
+      "step": 2820
+    },
+    {
+      "epoch": 1.7643391521197007,
+      "grad_norm": 0.83203125,
+      "learning_rate": 6.8586184066485315e-06,
+      "loss": 0.1038,
+      "step": 2830
+    },
+    {
+      "epoch": 1.770573566084788,
+      "grad_norm": 1.1796875,
+      "learning_rate": 6.833335765151138e-06,
+      "loss": 0.1181,
+      "step": 2840
+    },
+    {
+      "epoch": 1.7768079800498753,
+      "grad_norm": 0.84375,
+      "learning_rate": 6.807998850241675e-06,
+      "loss": 0.103,
+      "step": 2850
+    },
+    {
+      "epoch": 1.7830423940149625,
+      "grad_norm": 1.1796875,
+      "learning_rate": 6.782608411985048e-06,
+      "loss": 0.1074,
+      "step": 2860
+    },
+    {
+      "epoch": 1.7892768079800498,
+      "grad_norm": 0.734375,
+      "learning_rate": 6.757165202030653e-06,
+      "loss": 0.092,
+      "step": 2870
+    },
+    {
+      "epoch": 1.7955112219451372,
+      "grad_norm": 1.3125,
+      "learning_rate": 6.731669973590119e-06,
+      "loss": 0.0946,
+      "step": 2880
+    },
+    {
+      "epoch": 1.8017456359102244,
+      "grad_norm": 0.66796875,
+      "learning_rate": 6.706123481415012e-06,
+      "loss": 0.0974,
+      "step": 2890
+    },
+    {
+      "epoch": 1.8079800498753116,
+      "grad_norm": 1.046875,
+      "learning_rate": 6.680526481774492e-06,
+      "loss": 0.0962,
+      "step": 2900
+    },
+    {
+      "epoch": 1.814214463840399,
+      "grad_norm": 0.66015625,
+      "learning_rate": 6.65487973243292e-06,
+      "loss": 0.1,
+      "step": 2910
+    },
+    {
+      "epoch": 1.8204488778054864,
+      "grad_norm": 0.82421875,
+      "learning_rate": 6.629183992627432e-06,
+      "loss": 0.0944,
+      "step": 2920
+    },
+    {
+      "epoch": 1.8266832917705735,
+      "grad_norm": 0.60546875,
+      "learning_rate": 6.603440023045463e-06,
+      "loss": 0.0986,
+      "step": 2930
+    },
+    {
+      "epoch": 1.8329177057356607,
+      "grad_norm": 0.81640625,
+      "learning_rate": 6.577648585802219e-06,
+      "loss": 0.1031,
+      "step": 2940
+    },
+    {
+      "epoch": 1.839152119700748,
+      "grad_norm": 0.69140625,
+      "learning_rate": 6.551810444418123e-06,
+      "loss": 0.1016,
+      "step": 2950
+    },
+    {
+      "epoch": 1.8453865336658355,
+      "grad_norm": 0.78125,
+      "learning_rate": 6.5259263637962166e-06,
+      "loss": 0.0981,
+      "step": 2960
+    },
+    {
+      "epoch": 1.8516209476309227,
+      "grad_norm": 0.81640625,
+      "learning_rate": 6.499997110199502e-06,
+      "loss": 0.1068,
+      "step": 2970
+    },
+    {
+      "epoch": 1.8578553615960098,
+      "grad_norm": 0.66015625,
+      "learning_rate": 6.474023451228269e-06,
+      "loss": 0.0914,
+      "step": 2980
+    },
+    {
+      "epoch": 1.8640897755610972,
+      "grad_norm": 0.72265625,
+      "learning_rate": 6.448006155797371e-06,
+      "loss": 0.0989,
+      "step": 2990
+    },
+    {
+      "epoch": 1.8703241895261846,
+      "grad_norm": 0.546875,
+      "learning_rate": 6.421945994113453e-06,
+      "loss": 0.0872,
+      "step": 3000
+    },
+    {
+      "epoch": 1.8765586034912718,
+      "grad_norm": 0.73046875,
+      "learning_rate": 6.395843737652166e-06,
+      "loss": 0.0882,
+      "step": 3010
+    },
+    {
+      "epoch": 1.882793017456359,
+      "grad_norm": 0.71875,
+      "learning_rate": 6.3697001591353106e-06,
+      "loss": 0.0881,
+      "step": 3020
+    },
+    {
+      "epoch": 1.8890274314214464,
+      "grad_norm": 0.5859375,
+      "learning_rate": 6.343516032507975e-06,
+      "loss": 0.0906,
+      "step": 3030
+    },
+    {
+      "epoch": 1.8952618453865338,
+      "grad_norm": 0.59765625,
+      "learning_rate": 6.31729213291562e-06,
+      "loss": 0.0885,
+      "step": 3040
+    },
+    {
+      "epoch": 1.901496259351621,
+      "grad_norm": 0.65234375,
+      "learning_rate": 6.29102923668113e-06,
+      "loss": 0.0843,
+      "step": 3050
+    },
+    {
+      "epoch": 1.907730673316708,
+      "grad_norm": 0.6796875,
+      "learning_rate": 6.26472812128183e-06,
+      "loss": 0.083,
+      "step": 3060
+    },
+    {
+      "epoch": 1.9139650872817955,
+      "grad_norm": 0.64453125,
+      "learning_rate": 6.238389565326476e-06,
+      "loss": 0.091,
+      "step": 3070
+    },
+    {
+      "epoch": 1.9201995012468829,
+      "grad_norm": 0.6484375,
+      "learning_rate": 6.212014348532195e-06,
+      "loss": 0.0785,
+      "step": 3080
+    },
+    {
+      "epoch": 1.92643391521197,
+      "grad_norm": 0.6796875,
+      "learning_rate": 6.185603251701411e-06,
+      "loss": 0.0866,
+      "step": 3090
+    },
+    {
+      "epoch": 1.9326683291770572,
+      "grad_norm": 0.578125,
+      "learning_rate": 6.159157056698729e-06,
+      "loss": 0.0794,
+      "step": 3100
+    },
+    {
+      "epoch": 1.9389027431421446,
+      "grad_norm": 0.94921875,
+      "learning_rate": 6.132676546427786e-06,
+      "loss": 0.0894,
+      "step": 3110
+    },
+    {
+      "epoch": 1.945137157107232,
+      "grad_norm": 0.58203125,
+      "learning_rate": 6.1061625048080775e-06,
+      "loss": 0.0875,
+      "step": 3120
+    },
+    {
+      "epoch": 1.9513715710723192,
+      "grad_norm": 1.0859375,
+      "learning_rate": 6.079615716751747e-06,
+      "loss": 0.0925,
+      "step": 3130
+    },
+    {
+      "epoch": 1.9576059850374063,
+      "grad_norm": 1.1796875,
+      "learning_rate": 6.05303696814035e-06,
+      "loss": 0.0896,
+      "step": 3140
+    },
+    {
+      "epoch": 1.9638403990024937,
+      "grad_norm": 0.71484375,
+      "learning_rate": 6.026427045801596e-06,
+      "loss": 0.0996,
+      "step": 3150
+    },
+    {
+      "epoch": 1.9700748129675811,
+      "grad_norm": 1.0234375,
+      "learning_rate": 5.999786737486046e-06,
+      "loss": 0.1047,
+      "step": 3160
+    },
+    {
+      "epoch": 1.9763092269326683,
+      "grad_norm": 0.62109375,
+      "learning_rate": 5.973116831843798e-06,
+      "loss": 0.0937,
+      "step": 3170
+    },
+    {
+      "epoch": 1.9825436408977555,
+      "grad_norm": 0.9609375,
+      "learning_rate": 5.946418118401141e-06,
+      "loss": 0.1042,
+      "step": 3180
+    },
+    {
+      "epoch": 1.9887780548628429,
+      "grad_norm": 1.078125,
+      "learning_rate": 5.919691387537175e-06,
+      "loss": 0.1031,
+      "step": 3190
+    },
+    {
+      "epoch": 1.9950124688279303,
+      "grad_norm": 1.0390625,
+      "learning_rate": 5.892937430460421e-06,
+      "loss": 0.1041,
+      "step": 3200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.13248766958713531,
+      "eval_runtime": 306.0427,
+      "eval_samples_per_second": 23.954,
+      "eval_steps_per_second": 1.5,
+      "step": 3208
+    },
+    {
+      "epoch": 2.0012468827930174,
+      "grad_norm": 0.58984375,
+      "learning_rate": 5.866157039185394e-06,
+      "loss": 0.1026,
+      "step": 3210
+    },
+    {
+      "epoch": 2.0074812967581046,
+      "grad_norm": 0.55078125,
+      "learning_rate": 5.839351006509157e-06,
+      "loss": 0.0896,
+      "step": 3220
+    },
+    {
+      "epoch": 2.013715710723192,
+      "grad_norm": 0.71875,
+      "learning_rate": 5.812520125987853e-06,
+      "loss": 0.0974,
+      "step": 3230
+    },
+    {
+      "epoch": 2.0199501246882794,
+      "grad_norm": 0.6015625,
+      "learning_rate": 5.785665191913212e-06,
+      "loss": 0.0853,
+      "step": 3240
+    },
+    {
+      "epoch": 2.0261845386533666,
+      "grad_norm": 0.890625,
+      "learning_rate": 5.758786999289032e-06,
+      "loss": 0.1034,
+      "step": 3250
+    },
+    {
+      "epoch": 2.0324189526184537,
+      "grad_norm": 1.2734375,
+      "learning_rate": 5.7318863438076555e-06,
+      "loss": 0.1115,
+      "step": 3260
+    },
+    {
+      "epoch": 2.0386533665835413,
+      "grad_norm": 1.25,
+      "learning_rate": 5.7049640218264046e-06,
+      "loss": 0.1235,
+      "step": 3270
+    },
+    {
+      "epoch": 2.0448877805486285,
+      "grad_norm": 1.6171875,
+      "learning_rate": 5.678020830344006e-06,
+      "loss": 0.1282,
+      "step": 3280
+    },
+    {
+      "epoch": 2.0511221945137157,
+      "grad_norm": 1.015625,
+      "learning_rate": 5.651057566977006e-06,
+      "loss": 0.1233,
+      "step": 3290
+    },
+    {
+      "epoch": 2.057356608478803,
+      "grad_norm": 1.28125,
+      "learning_rate": 5.624075029936144e-06,
+      "loss": 0.1232,
+      "step": 3300
+    },
+    {
+      "epoch": 2.0635910224438905,
+      "grad_norm": 1.171875,
+      "learning_rate": 5.5970740180027365e-06,
+      "loss": 0.1188,
+      "step": 3310
+    },
+    {
+      "epoch": 2.0698254364089776,
+      "grad_norm": 1.421875,
+      "learning_rate": 5.570055330505019e-06,
+      "loss": 0.1154,
+      "step": 3320
+    },
+    {
+      "epoch": 2.076059850374065,
+      "grad_norm": 1.1328125,
+      "learning_rate": 5.543019767294492e-06,
+      "loss": 0.1238,
+      "step": 3330
+    },
+    {
+      "epoch": 2.082294264339152,
+      "grad_norm": 1.1953125,
+      "learning_rate": 5.515968128722238e-06,
+      "loss": 0.1338,
+      "step": 3340
+    },
+    {
+      "epoch": 2.0885286783042396,
+      "grad_norm": 1.109375,
+      "learning_rate": 5.488901215615228e-06,
+      "loss": 0.1136,
+      "step": 3350
+    },
+    {
+      "epoch": 2.0947630922693268,
+      "grad_norm": 1.125,
+      "learning_rate": 5.461819829252611e-06,
+      "loss": 0.1214,
+      "step": 3360
+    },
+    {
+      "epoch": 2.100997506234414,
+      "grad_norm": 0.8359375,
+      "learning_rate": 5.434724771342006e-06,
+      "loss": 0.1043,
+      "step": 3370
+    },
+    {
+      "epoch": 2.107231920199501,
+      "grad_norm": 1.046875,
+      "learning_rate": 5.407616843995751e-06,
+      "loss": 0.1008,
+      "step": 3380
+    },
+    {
+      "epoch": 2.1134663341645887,
+      "grad_norm": 0.8046875,
+      "learning_rate": 5.380496849707171e-06,
+      "loss": 0.0991,
+      "step": 3390
+    },
+    {
+      "epoch": 2.119700748129676,
+      "grad_norm": 1.0859375,
+      "learning_rate": 5.353365591326815e-06,
+      "loss": 0.0986,
+      "step": 3400
+    },
+    {
+      "epoch": 2.125935162094763,
+      "grad_norm": 0.82421875,
+      "learning_rate": 5.326223872038688e-06,
+      "loss": 0.0935,
+      "step": 3410
+    },
+    {
+      "epoch": 2.1321695760598502,
+      "grad_norm": 0.94921875,
+      "learning_rate": 5.29907249533648e-06,
+      "loss": 0.1011,
+      "step": 3420
+    },
+    {
+      "epoch": 2.138403990024938,
+      "grad_norm": 1.171875,
+      "learning_rate": 5.271912264999773e-06,
+      "loss": 0.102,
+      "step": 3430
+    },
+    {
+      "epoch": 2.144638403990025,
+      "grad_norm": 0.8359375,
+      "learning_rate": 5.24474398507025e-06,
+      "loss": 0.094,
+      "step": 3440
+    },
+    {
+      "epoch": 2.150872817955112,
+      "grad_norm": 1.03125,
+      "learning_rate": 5.21756845982789e-06,
+      "loss": 0.1098,
+      "step": 3450
+    },
+    {
+      "epoch": 2.1571072319201994,
+      "grad_norm": 0.7265625,
+      "learning_rate": 5.190386493767159e-06,
+      "loss": 0.0993,
+      "step": 3460
+    },
+    {
+      "epoch": 2.163341645885287,
+      "grad_norm": 1.6484375,
+      "learning_rate": 5.163198891573198e-06,
+      "loss": 0.1034,
+      "step": 3470
+    },
+    {
+      "epoch": 2.169576059850374,
+      "grad_norm": 0.62109375,
+      "learning_rate": 5.136006458097995e-06,
+      "loss": 0.0926,
+      "step": 3480
+    },
+    {
+      "epoch": 2.1758104738154613,
+      "grad_norm": 1.140625,
+      "learning_rate": 5.108809998336564e-06,
+      "loss": 0.104,
+      "step": 3490
+    },
+    {
+      "epoch": 2.1820448877805485,
+      "grad_norm": 0.64453125,
+      "learning_rate": 5.081610317403107e-06,
+      "loss": 0.0998,
+      "step": 3500
+    },
+    {
+      "epoch": 2.188279301745636,
+      "grad_norm": 1.5390625,
+      "learning_rate": 5.054408220507192e-06,
+      "loss": 0.0967,
+      "step": 3510
+    },
+    {
+      "epoch": 2.1945137157107233,
+      "grad_norm": 0.6796875,
+      "learning_rate": 5.027204512929901e-06,
+      "loss": 0.0905,
+      "step": 3520
+    },
+    {
+      "epoch": 2.2007481296758105,
+      "grad_norm": 0.8984375,
+      "learning_rate": 5e-06,
+      "loss": 0.0929,
+      "step": 3530
+    },
+    {
+      "epoch": 2.2069825436408976,
+      "grad_norm": 0.74609375,
+      "learning_rate": 4.972795487070101e-06,
+      "loss": 0.0895,
+      "step": 3540
+    },
+    {
+      "epoch": 2.213216957605985,
+      "grad_norm": 0.859375,
+      "learning_rate": 4.945591779492809e-06,
+      "loss": 0.0879,
+      "step": 3550
+    },
+    {
+      "epoch": 2.2194513715710724,
+      "grad_norm": 0.796875,
+      "learning_rate": 4.918389682596894e-06,
+      "loss": 0.0817,
+      "step": 3560
+    },
+    {
+      "epoch": 2.2256857855361596,
+      "grad_norm": 0.625,
+      "learning_rate": 4.891190001663438e-06,
+      "loss": 0.0826,
+      "step": 3570
+    },
+    {
+      "epoch": 2.2319201995012468,
+      "grad_norm": 1.375,
+      "learning_rate": 4.863993541902006e-06,
+      "loss": 0.0856,
+      "step": 3580
+    },
+    {
+      "epoch": 2.2381546134663344,
+      "grad_norm": 0.73828125,
+      "learning_rate": 4.836801108426803e-06,
+      "loss": 0.0842,
+      "step": 3590
+    },
+    {
+      "epoch": 2.2443890274314215,
+      "grad_norm": 0.90625,
+      "learning_rate": 4.809613506232842e-06,
+      "loss": 0.0801,
+      "step": 3600
+    },
+    {
+      "epoch": 2.2506234413965087,
+      "grad_norm": 0.98046875,
+      "learning_rate": 4.782431540172112e-06,
+      "loss": 0.0807,
+      "step": 3610
+    },
+    {
+      "epoch": 2.256857855361596,
+      "grad_norm": 0.796875,
+      "learning_rate": 4.755256014929752e-06,
+      "loss": 0.0832,
+      "step": 3620
+    },
+    {
+      "epoch": 2.263092269326683,
+      "grad_norm": 1.3203125,
+      "learning_rate": 4.7280877350002285e-06,
+      "loss": 0.0874,
+      "step": 3630
+    },
+    {
+      "epoch": 2.2693266832917707,
+      "grad_norm": 0.63671875,
+      "learning_rate": 4.700927504663521e-06,
+      "loss": 0.0787,
+      "step": 3640
+    },
+    {
+      "epoch": 2.275561097256858,
+      "grad_norm": 1.7265625,
+      "learning_rate": 4.673776127961313e-06,
+      "loss": 0.0829,
+      "step": 3650
+    },
+    {
+      "epoch": 2.281795511221945,
+      "grad_norm": 0.80859375,
+      "learning_rate": 4.646634408673186e-06,
+      "loss": 0.0902,
+      "step": 3660
+    },
+    {
+      "epoch": 2.2880299251870326,
+      "grad_norm": 1.578125,
+      "learning_rate": 4.6195031502928305e-06,
+      "loss": 0.0901,
+      "step": 3670
+    },
+    {
+      "epoch": 2.29426433915212,
+      "grad_norm": 0.9453125,
+      "learning_rate": 4.59238315600425e-06,
+      "loss": 0.0953,
+      "step": 3680
+    },
+    {
+      "epoch": 2.300498753117207,
+      "grad_norm": 1.4453125,
+      "learning_rate": 4.565275228657995e-06,
+      "loss": 0.1089,
+      "step": 3690
+    },
+    {
+      "epoch": 2.306733167082294,
+      "grad_norm": 0.91796875,
+      "learning_rate": 4.5381801707473896e-06,
+      "loss": 0.1097,
+      "step": 3700
+    },
+    {
+      "epoch": 2.3129675810473813,
+      "grad_norm": 1.3203125,
+      "learning_rate": 4.511098784384775e-06,
+      "loss": 0.1038,
+      "step": 3710
+    },
+    {
+      "epoch": 2.319201995012469,
+      "grad_norm": 0.90625,
+      "learning_rate": 4.484031871277764e-06,
+      "loss": 0.1133,
+      "step": 3720
+    },
+    {
+      "epoch": 2.325436408977556,
+      "grad_norm": 1.0859375,
+      "learning_rate": 4.456980232705509e-06,
+      "loss": 0.1202,
+      "step": 3730
+    },
+    {
+      "epoch": 2.3316708229426433,
+      "grad_norm": 0.8828125,
+      "learning_rate": 4.429944669494983e-06,
+      "loss": 0.1226,
+      "step": 3740
+    },
+    {
+      "epoch": 2.337905236907731,
+      "grad_norm": 1.046875,
+      "learning_rate": 4.402925981997265e-06,
+      "loss": 0.1185,
+      "step": 3750
+    },
+    {
+      "epoch": 2.344139650872818,
+      "grad_norm": 1.2265625,
+      "learning_rate": 4.375924970063857e-06,
+      "loss": 0.1283,
+      "step": 3760
+    },
+    {
+      "epoch": 2.3503740648379052,
+      "grad_norm": 0.95703125,
+      "learning_rate": 4.3489424330229945e-06,
+      "loss": 0.1271,
+      "step": 3770
+    },
+    {
+      "epoch": 2.3566084788029924,
+      "grad_norm": 0.8671875,
+      "learning_rate": 4.321979169655994e-06,
+      "loss": 0.1222,
+      "step": 3780
+    },
+    {
+      "epoch": 2.3628428927680796,
+      "grad_norm": 0.90234375,
+      "learning_rate": 4.295035978173597e-06,
+      "loss": 0.1215,
+      "step": 3790
+    },
+    {
+      "epoch": 2.369077306733167,
+      "grad_norm": 0.921875,
+      "learning_rate": 4.268113656192346e-06,
+      "loss": 0.1202,
+      "step": 3800
+    },
+    {
+      "epoch": 2.3753117206982544,
+      "grad_norm": 0.96875,
+      "learning_rate": 4.24121300071097e-06,
+      "loss": 0.1122,
+      "step": 3810
+    },
+    {
+      "epoch": 2.3815461346633415,
+      "grad_norm": 0.8046875,
+      "learning_rate": 4.214334808086791e-06,
+      "loss": 0.1062,
+      "step": 3820
+    },
+    {
+      "epoch": 2.387780548628429,
+      "grad_norm": 1.1015625,
+      "learning_rate": 4.187479874012149e-06,
+      "loss": 0.1096,
+      "step": 3830
+    },
+    {
+      "epoch": 2.3940149625935163,
+      "grad_norm": 0.8359375,
+      "learning_rate": 4.160648993490844e-06,
+      "loss": 0.1034,
+      "step": 3840
+    },
+    {
+      "epoch": 2.4002493765586035,
+      "grad_norm": 0.9296875,
+      "learning_rate": 4.133842960814608e-06,
+      "loss": 0.0979,
+      "step": 3850
+    },
+    {
+      "epoch": 2.4064837905236907,
+      "grad_norm": 0.73046875,
+      "learning_rate": 4.1070625695395796e-06,
+      "loss": 0.0963,
+      "step": 3860
+    },
+    {
+      "epoch": 2.412718204488778,
+      "grad_norm": 0.71875,
+      "learning_rate": 4.080308612462826e-06,
+      "loss": 0.0864,
+      "step": 3870
+    },
+    {
+      "epoch": 2.4189526184538654,
+      "grad_norm": 0.62890625,
+      "learning_rate": 4.05358188159886e-06,
+      "loss": 0.0775,
+      "step": 3880
+    },
+    {
+      "epoch": 2.4251870324189526,
+      "grad_norm": 0.765625,
+      "learning_rate": 4.0268831681562025e-06,
+      "loss": 0.0839,
+      "step": 3890
+    },
+    {
+      "epoch": 2.43142144638404,
+      "grad_norm": 0.6171875,
+      "learning_rate": 4.000213262513955e-06,
+      "loss": 0.0784,
+      "step": 3900
+    },
+    {
+      "epoch": 2.4376558603491274,
+      "grad_norm": 0.87890625,
+      "learning_rate": 3.973572954198406e-06,
+      "loss": 0.0881,
+      "step": 3910
+    },
+    {
+      "epoch": 2.4438902743142146,
+      "grad_norm": 1.140625,
+      "learning_rate": 3.946963031859651e-06,
+      "loss": 0.0851,
+      "step": 3920
+    },
+    {
+      "epoch": 2.4501246882793017,
+      "grad_norm": 0.62890625,
+      "learning_rate": 3.920384283248255e-06,
+      "loss": 0.091,
+      "step": 3930
+    },
+    {
+      "epoch": 2.456359102244389,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.893837495191923e-06,
+      "loss": 0.0886,
+      "step": 3940
+    },
+    {
+      "epoch": 2.462593516209476,
+      "grad_norm": 0.828125,
+      "learning_rate": 3.867323453572214e-06,
+      "loss": 0.0928,
+      "step": 3950
+    },
+    {
+      "epoch": 2.4688279301745637,
+      "grad_norm": 0.7734375,
+      "learning_rate": 3.840842943301271e-06,
+      "loss": 0.0939,
+      "step": 3960
+    },
+    {
+      "epoch": 2.475062344139651,
+      "grad_norm": 1.1171875,
+      "learning_rate": 3.8143967482985888e-06,
+      "loss": 0.0935,
+      "step": 3970
+    },
+    {
+      "epoch": 2.481296758104738,
+      "grad_norm": 0.7890625,
+      "learning_rate": 3.7879856514678054e-06,
+      "loss": 0.0917,
+      "step": 3980
+    },
+    {
+      "epoch": 2.4875311720698257,
+      "grad_norm": 0.83984375,
+      "learning_rate": 3.761610434673525e-06,
+      "loss": 0.0961,
+      "step": 3990
+    },
+    {
+      "epoch": 2.493765586034913,
+      "grad_norm": 0.97265625,
+      "learning_rate": 3.7352718787181695e-06,
+      "loss": 0.1018,
+      "step": 4000
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.96484375,
+      "learning_rate": 3.708970763318871e-06,
+      "loss": 0.1017,
+      "step": 4010
+    },
+    {
+      "epoch": 2.506234413965087,
+      "grad_norm": 0.83984375,
+      "learning_rate": 3.6827078670843803e-06,
+      "loss": 0.1084,
+      "step": 4020
+    },
+    {
+      "epoch": 2.5124688279301743,
+      "grad_norm": 0.95703125,
+      "learning_rate": 3.6564839674920254e-06,
+      "loss": 0.1056,
+      "step": 4030
+    },
+    {
+      "epoch": 2.518703241895262,
+      "grad_norm": 0.84375,
+      "learning_rate": 3.6302998408646907e-06,
+      "loss": 0.1137,
+      "step": 4040
+    },
+    {
+      "epoch": 2.524937655860349,
+      "grad_norm": 0.86328125,
+      "learning_rate": 3.6041562623478355e-06,
+      "loss": 0.1134,
+      "step": 4050
+    },
+    {
+      "epoch": 2.5311720698254363,
+      "grad_norm": 1.0078125,
+      "learning_rate": 3.5780540058865475e-06,
+      "loss": 0.1163,
+      "step": 4060
+    },
+    {
+      "epoch": 2.537406483790524,
+      "grad_norm": 0.7265625,
+      "learning_rate": 3.5519938442026303e-06,
+      "loss": 0.1089,
+      "step": 4070
+    },
+    {
+      "epoch": 2.543640897755611,
+      "grad_norm": 1.03125,
+      "learning_rate": 3.525976548771731e-06,
+      "loss": 0.1126,
+      "step": 4080
+    },
+    {
+      "epoch": 2.5498753117206983,
+      "grad_norm": 0.734375,
+      "learning_rate": 3.500002889800499e-06,
+      "loss": 0.1134,
+      "step": 4090
+    },
+    {
+      "epoch": 2.5561097256857854,
+      "grad_norm": 1.0703125,
+      "learning_rate": 3.4740736362037843e-06,
+      "loss": 0.1194,
+      "step": 4100
+    },
+    {
+      "epoch": 2.5623441396508726,
+      "grad_norm": 0.58203125,
+      "learning_rate": 3.4481895555818767e-06,
+      "loss": 0.1212,
+      "step": 4110
+    },
+    {
+      "epoch": 2.56857855361596,
+      "grad_norm": 1.1796875,
+      "learning_rate": 3.422351414197782e-06,
+      "loss": 0.1205,
+      "step": 4120
+    },
+    {
+      "epoch": 2.5748129675810474,
+      "grad_norm": 0.640625,
+      "learning_rate": 3.396559976954538e-06,
+      "loss": 0.1172,
+      "step": 4130
+    },
+    {
+      "epoch": 2.5810473815461346,
+      "grad_norm": 1.109375,
+      "learning_rate": 3.370816007372567e-06,
+      "loss": 0.113,
+      "step": 4140
+    },
+    {
+      "epoch": 2.587281795511222,
+      "grad_norm": 0.68359375,
+      "learning_rate": 3.3451202675670812e-06,
+      "loss": 0.1117,
+      "step": 4150
+    },
+    {
+      "epoch": 2.5935162094763093,
+      "grad_norm": 0.91015625,
+      "learning_rate": 3.319473518225509e-06,
+      "loss": 0.1149,
+      "step": 4160
+    },
+    {
+      "epoch": 2.5997506234413965,
+      "grad_norm": 0.81640625,
+      "learning_rate": 3.293876518584988e-06,
+      "loss": 0.1109,
+      "step": 4170
+    },
+    {
+      "epoch": 2.6059850374064837,
+      "grad_norm": 1.1484375,
+      "learning_rate": 3.268330026409881e-06,
+      "loss": 0.1052,
+      "step": 4180
+    },
+    {
+      "epoch": 2.612219451371571,
+      "grad_norm": 1.0546875,
+      "learning_rate": 3.2428347979693475e-06,
+      "loss": 0.1108,
+      "step": 4190
+    },
+    {
+      "epoch": 2.6184538653366585,
+      "grad_norm": 1.1328125,
+      "learning_rate": 3.217391588014953e-06,
+      "loss": 0.1083,
+      "step": 4200
+    },
+    {
+      "epoch": 2.6246882793017456,
+      "grad_norm": 0.90234375,
+      "learning_rate": 3.192001149758327e-06,
+      "loss": 0.1077,
+      "step": 4210
+    },
+    {
+      "epoch": 2.630922693266833,
+      "grad_norm": 1.1875,
+      "learning_rate": 3.1666642348488623e-06,
+      "loss": 0.1062,
+      "step": 4220
+    },
+    {
+      "epoch": 2.6371571072319204,
+      "grad_norm": 1.140625,
+      "learning_rate": 3.1413815933514693e-06,
+      "loss": 0.1013,
+      "step": 4230
+    },
+    {
+      "epoch": 2.6433915211970076,
+      "grad_norm": 1.2578125,
+      "learning_rate": 3.1161539737243658e-06,
+      "loss": 0.1071,
+      "step": 4240
+    },
+    {
+      "epoch": 2.6496259351620948,
+      "grad_norm": 1.15625,
+      "learning_rate": 3.0909821227969223e-06,
+      "loss": 0.1081,
+      "step": 4250
+    },
+    {
+      "epoch": 2.655860349127182,
+      "grad_norm": 1.3515625,
+      "learning_rate": 3.0658667857475543e-06,
+      "loss": 0.0987,
+      "step": 4260
+    },
+    {
+      "epoch": 2.662094763092269,
+      "grad_norm": 1.046875,
+      "learning_rate": 3.040808706081657e-06,
+      "loss": 0.0991,
+      "step": 4270
+    },
+    {
+      "epoch": 2.6683291770573567,
+      "grad_norm": 1.546875,
+      "learning_rate": 3.015808625609602e-06,
+      "loss": 0.1051,
+      "step": 4280
+    },
+    {
+      "epoch": 2.674563591022444,
+      "grad_norm": 1.0390625,
+      "learning_rate": 2.9908672844247734e-06,
+      "loss": 0.11,
+      "step": 4290
+    },
+    {
+      "epoch": 2.680798004987531,
+      "grad_norm": 1.5703125,
+      "learning_rate": 2.965985420881657e-06,
+      "loss": 0.117,
+      "step": 4300
+    },
+    {
+      "epoch": 2.6870324189526187,
+      "grad_norm": 1.0078125,
+      "learning_rate": 2.941163771573986e-06,
+      "loss": 0.1073,
+      "step": 4310
+    },
+    {
+      "epoch": 2.693266832917706,
+      "grad_norm": 1.46875,
+      "learning_rate": 2.9164030713129287e-06,
+      "loss": 0.1171,
+      "step": 4320
+    },
+    {
+      "epoch": 2.699501246882793,
+      "grad_norm": 1.3984375,
+      "learning_rate": 2.8917040531053463e-06,
+      "loss": 0.1211,
+      "step": 4330
+    },
+    {
+      "epoch": 2.70573566084788,
+      "grad_norm": 1.4453125,
+      "learning_rate": 2.8670674481320843e-06,
+      "loss": 0.1193,
+      "step": 4340
+    },
+    {
+      "epoch": 2.7119700748129674,
+      "grad_norm": 1.78125,
+      "learning_rate": 2.8424939857263235e-06,
+      "loss": 0.1313,
+      "step": 4350
+    },
+    {
+      "epoch": 2.718204488778055,
+      "grad_norm": 1.359375,
+      "learning_rate": 2.817984393352004e-06,
+      "loss": 0.127,
+      "step": 4360
+    },
+    {
+      "epoch": 2.724438902743142,
+      "grad_norm": 1.6484375,
+      "learning_rate": 2.7935393965822723e-06,
+      "loss": 0.1304,
+      "step": 4370
+    },
+    {
+      "epoch": 2.7306733167082293,
+      "grad_norm": 1.296875,
+      "learning_rate": 2.769159719078015e-06,
+      "loss": 0.1248,
+      "step": 4380
+    },
+    {
+      "epoch": 2.736907730673317,
+      "grad_norm": 1.1796875,
+      "learning_rate": 2.7448460825664305e-06,
+      "loss": 0.1135,
+      "step": 4390
+    },
+    {
+      "epoch": 2.743142144638404,
+      "grad_norm": 1.421875,
+      "learning_rate": 2.720599206819661e-06,
+      "loss": 0.1189,
+      "step": 4400
+    },
+    {
+      "epoch": 2.7493765586034913,
+      "grad_norm": 1.203125,
+      "learning_rate": 2.696419809633489e-06,
+      "loss": 0.118,
+      "step": 4410
+    },
+    {
+      "epoch": 2.7556109725685785,
+      "grad_norm": 1.3828125,
+      "learning_rate": 2.6723086068060856e-06,
+      "loss": 0.1165,
+      "step": 4420
+    },
+    {
+      "epoch": 2.7618453865336656,
+      "grad_norm": 1.015625,
+      "learning_rate": 2.648266312116819e-06,
+      "loss": 0.1088,
+      "step": 4430
+    },
+    {
+      "epoch": 2.7680798004987532,
+      "grad_norm": 1.34375,
+      "learning_rate": 2.624293637305128e-06,
+      "loss": 0.1167,
+      "step": 4440
+    },
+    {
+      "epoch": 2.7743142144638404,
+      "grad_norm": 0.78125,
+      "learning_rate": 2.600391292049449e-06,
+      "loss": 0.0962,
+      "step": 4450
+    },
+    {
+      "epoch": 2.7805486284289276,
+      "grad_norm": 1.4765625,
+      "learning_rate": 2.576559983946206e-06,
+      "loss": 0.1098,
+      "step": 4460
+    },
+    {
+      "epoch": 2.786783042394015,
+      "grad_norm": 0.69921875,
+      "learning_rate": 2.552800418488869e-06,
+      "loss": 0.0913,
+      "step": 4470
+    },
+    {
+      "epoch": 2.7930174563591024,
+      "grad_norm": 1.34375,
+      "learning_rate": 2.5291132990470558e-06,
+      "loss": 0.0936,
+      "step": 4480
+    },
+    {
+      "epoch": 2.7992518703241895,
+      "grad_norm": 0.69140625,
+      "learning_rate": 2.5054993268457284e-06,
+      "loss": 0.092,
+      "step": 4490
+    },
+    {
+      "epoch": 2.8054862842892767,
+      "grad_norm": 1.0546875,
+      "learning_rate": 2.4819592009444175e-06,
+      "loss": 0.0904,
+      "step": 4500
+    },
+    {
+      "epoch": 2.811720698254364,
+      "grad_norm": 0.6171875,
+      "learning_rate": 2.4584936182165387e-06,
+      "loss": 0.0915,
+      "step": 4510
+    },
+    {
+      "epoch": 2.8179551122194515,
+      "grad_norm": 0.84765625,
+      "learning_rate": 2.4351032733287556e-06,
+      "loss": 0.088,
+      "step": 4520
+    },
+    {
+      "epoch": 2.8241895261845387,
+      "grad_norm": 0.70703125,
+      "learning_rate": 2.4117888587204193e-06,
+      "loss": 0.1044,
+      "step": 4530
+    },
+    {
+      "epoch": 2.830423940149626,
+      "grad_norm": 0.7109375,
+      "learning_rate": 2.388551064583067e-06,
+      "loss": 0.0914,
+      "step": 4540
+    },
+    {
+      "epoch": 2.8366583541147135,
+      "grad_norm": 0.6953125,
+      "learning_rate": 2.3653905788399917e-06,
+      "loss": 0.1078,
+      "step": 4550
+    },
+    {
+      "epoch": 2.8428927680798006,
+      "grad_norm": 0.73046875,
+      "learning_rate": 2.342308087125877e-06,
+      "loss": 0.0925,
+      "step": 4560
+    },
+    {
+      "epoch": 2.849127182044888,
+      "grad_norm": 0.71484375,
+      "learning_rate": 2.319304272766499e-06,
+      "loss": 0.1053,
+      "step": 4570
+    },
+    {
+      "epoch": 2.855361596009975,
+      "grad_norm": 0.6328125,
+      "learning_rate": 2.2963798167584996e-06,
+      "loss": 0.0968,
+      "step": 4580
+    },
+    {
+      "epoch": 2.861596009975062,
+      "grad_norm": 0.8125,
+      "learning_rate": 2.2735353977492187e-06,
+      "loss": 0.0963,
+      "step": 4590
+    },
+    {
+      "epoch": 2.8678304239401498,
+      "grad_norm": 0.62890625,
+      "learning_rate": 2.250771692016615e-06,
+      "loss": 0.0919,
+      "step": 4600
+    },
+    {
+      "epoch": 2.874064837905237,
+      "grad_norm": 0.83203125,
+      "learning_rate": 2.22808937344924e-06,
+      "loss": 0.0897,
+      "step": 4610
+    },
+    {
+      "epoch": 2.880299251870324,
+      "grad_norm": 0.57421875,
+      "learning_rate": 2.2054891135262875e-06,
+      "loss": 0.0876,
+      "step": 4620
+    },
+    {
+      "epoch": 2.8865336658354117,
+      "grad_norm": 0.8125,
+      "learning_rate": 2.1829715812977175e-06,
+      "loss": 0.0875,
+      "step": 4630
+    },
+    {
+      "epoch": 2.892768079800499,
+      "grad_norm": 0.65625,
+      "learning_rate": 2.160537443364448e-06,
+      "loss": 0.0872,
+      "step": 4640
+    },
+    {
+      "epoch": 2.899002493765586,
+      "grad_norm": 0.75,
+      "learning_rate": 2.138187363858624e-06,
+      "loss": 0.0909,
+      "step": 4650
+    },
+    {
+      "epoch": 2.9052369077306732,
+      "grad_norm": 0.625,
+      "learning_rate": 2.1159220044239533e-06,
+      "loss": 0.0851,
+      "step": 4660
+    },
+    {
+      "epoch": 2.9114713216957604,
+      "grad_norm": 0.59765625,
+      "learning_rate": 2.093742024196123e-06,
+      "loss": 0.0765,
+      "step": 4670
+    },
+    {
+      "epoch": 2.917705735660848,
+      "grad_norm": 0.62890625,
+      "learning_rate": 2.071648079783283e-06,
+      "loss": 0.0857,
+      "step": 4680
+    },
+    {
+      "epoch": 2.923940149625935,
+      "grad_norm": 0.71484375,
+      "learning_rate": 2.049640825246613e-06,
+      "loss": 0.084,
+      "step": 4690
+    },
+    {
+      "epoch": 2.9301745635910224,
+      "grad_norm": 0.609375,
+      "learning_rate": 2.027720912080951e-06,
+      "loss": 0.0778,
+      "step": 4700
+    },
+    {
+      "epoch": 2.93640897755611,
+      "grad_norm": 0.83203125,
+      "learning_rate": 2.005888989195518e-06,
+      "loss": 0.0858,
+      "step": 4710
+    },
+    {
+      "epoch": 2.942643391521197,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.9841457028947007e-06,
+      "loss": 0.0849,
+      "step": 4720
+    },
+    {
+      "epoch": 2.9488778054862843,
+      "grad_norm": 1.1796875,
+      "learning_rate": 1.962491696858921e-06,
+      "loss": 0.094,
+      "step": 4730
+    },
+    {
+      "epoch": 2.9551122194513715,
+      "grad_norm": 0.63671875,
+      "learning_rate": 1.940927612125577e-06,
+      "loss": 0.0892,
+      "step": 4740
+    },
+    {
+      "epoch": 2.9613466334164587,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.919454087070073e-06,
+      "loss": 0.0942,
+      "step": 4750
+    },
+    {
+      "epoch": 2.9675810473815463,
+      "grad_norm": 0.68359375,
+      "learning_rate": 1.8980717573869134e-06,
+      "loss": 0.0969,
+      "step": 4760
+    },
+    {
+      "epoch": 2.9738154613466334,
+      "grad_norm": 1.1796875,
+      "learning_rate": 1.8767812560708909e-06,
+      "loss": 0.1004,
+      "step": 4770
+    },
+    {
+      "epoch": 2.9800498753117206,
+      "grad_norm": 0.62890625,
+      "learning_rate": 1.8555832133983425e-06,
+      "loss": 0.1073,
+      "step": 4780
+    },
+    {
+      "epoch": 2.9862842892768082,
+      "grad_norm": 0.95703125,
+      "learning_rate": 1.8344782569084946e-06,
+      "loss": 0.0957,
+      "step": 4790
+    },
+    {
+      "epoch": 2.9925187032418954,
+      "grad_norm": 1.0390625,
+      "learning_rate": 1.813467011384879e-06,
+      "loss": 0.1025,
+      "step": 4800
+    },
+    {
+      "epoch": 2.9987531172069826,
+      "grad_norm": 1.1328125,
+      "learning_rate": 1.7925500988368466e-06,
+      "loss": 0.1014,
+      "step": 4810
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.1314818561077118,
+      "eval_runtime": 458.5148,
+      "eval_samples_per_second": 15.989,
+      "eval_steps_per_second": 1.001,
+      "step": 4812
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6416,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 1604,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.776012270649344e+20,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4812/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf798d7f5818756a03915c5bc6b925db9c5083056b25bf0861802b46be39289d
+size 6161

checkpoint-6416/config.json

@@ -0,0 +1,60 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "bfloat16",
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50276
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

checkpoint-6416/generation_config.json

@@ -0,0 +1,168 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "language": "hi",
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.57.3"
+}

checkpoint-6416/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6112aec5be65d145282be01438eb6379acfc57a59247b29353c7b762385d8b6b
+size 483525680

checkpoint-6416/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a052f24569a5ee865f194bf883666201f04ce42a6a0b11c05ad3ee69e32570fb
+size 954914801

checkpoint-6416/preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

checkpoint-6416/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6792127011b5c91c4aaca1d92e2216b4f2d64748140eec0ea5496a910ccad1a
+size 14645

checkpoint-6416/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b8be68a2d7f4eab9493419fd06d59ec467181edea535f67d4062ae7f8a6cb0
+size 1465

checkpoint-6416/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf798d7f5818756a03915c5bc6b925db9c5083056b25bf0861802b46be39289d
+size 6161

config.json

@@ -0,0 +1,60 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "bfloat16",
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50276
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

generation_config.json

@@ -0,0 +1,168 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "language": "hi",
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6112aec5be65d145282be01438eb6379acfc57a59247b29353c7b762385d8b6b
+size 483525680

normalizer.json

@@ -0,0 +1,1742 @@
+{
+  "accessorise": "accessorize",
+  "accessorised": "accessorized",
+  "accessorises": "accessorizes",
+  "accessorising": "accessorizing",
+  "acclimatisation": "acclimatization",
+  "acclimatise": "acclimatize",
+  "acclimatised": "acclimatized",
+  "acclimatises": "acclimatizes",
+  "acclimatising": "acclimatizing",
+  "accoutrements": "accouterments",
+  "aeon": "eon",
+  "aeons": "eons",
+  "aerogramme": "aerogram",
+  "aerogrammes": "aerograms",
+  "aeroplane": "airplane",
+  "aeroplanes": "airplanes",
+  "aesthete": "esthete",
+  "aesthetes": "esthetes",
+  "aesthetic": "esthetic",
+  "aesthetically": "esthetically",
+  "aesthetics": "esthetics",
+  "aetiology": "etiology",
+  "ageing": "aging",
+  "aggrandisement": "aggrandizement",
+  "agonise": "agonize",
+  "agonised": "agonized",
+  "agonises": "agonizes",
+  "agonising": "agonizing",
+  "agonisingly": "agonizingly",
+  "almanack": "almanac",
+  "almanacks": "almanacs",
+  "aluminium": "aluminum",
+  "amortisable": "amortizable",
+  "amortisation": "amortization",
+  "amortisations": "amortizations",
+  "amortise": "amortize",
+  "amortised": "amortized",
+  "amortises": "amortizes",
+  "amortising": "amortizing",
+  "amphitheatre": "amphitheater",
+  "amphitheatres": "amphitheaters",
+  "anaemia": "anemia",
+  "anaemic": "anemic",
+  "anaesthesia": "anesthesia",
+  "anaesthetic": "anesthetic",
+  "anaesthetics": "anesthetics",
+  "anaesthetise": "anesthetize",
+  "anaesthetised": "anesthetized",
+  "anaesthetises": "anesthetizes",
+  "anaesthetising": "anesthetizing",
+  "anaesthetist": "anesthetist",
+  "anaesthetists": "anesthetists",
+  "anaesthetize": "anesthetize",
+  "anaesthetized": "anesthetized",
+  "anaesthetizes": "anesthetizes",
+  "anaesthetizing": "anesthetizing",
+  "analogue": "analog",
+  "analogues": "analogs",
+  "analyse": "analyze",
+  "analysed": "analyzed",
+  "analyses": "analyzes",
+  "analysing": "analyzing",
+  "anglicise": "anglicize",
+  "anglicised": "anglicized",
+  "anglicises": "anglicizes",
+  "anglicising": "anglicizing",
+  "annualised": "annualized",
+  "antagonise": "antagonize",
+  "antagonised": "antagonized",
+  "antagonises": "antagonizes",
+  "antagonising": "antagonizing",
+  "apologise": "apologize",
+  "apologised": "apologized",
+  "apologises": "apologizes",
+  "apologising": "apologizing",
+  "appal": "appall",
+  "appals": "appalls",
+  "appetiser": "appetizer",
+  "appetisers": "appetizers",
+  "appetising": "appetizing",
+  "appetisingly": "appetizingly",
+  "arbour": "arbor",
+  "arbours": "arbors",
+  "archaeologically": "archeologically",
+  "archaeologist": "archeologist",
+  "archaeologists": "archeologists",
+  "archaeology": "archeology</span>",
+  "archeological": "archaeological",
+  "ardour": "ardor",
+  "armour": "armor",
+  "armoured": "armored",
+  "armourer": "armorer",
+  "armourers": "armorers",
+  "armouries": "armories",
+  "armoury": "armory",
+  "artefact": "artifact",
+  "artefacts": "artifacts",
+  "authorise": "authorize",
+  "authorised": "authorized",
+  "authorises": "authorizes",
+  "authorising": "authorizing",
+  "axe": "ax",
+  "backpedalled": "backpedaled",
+  "backpedalling": "backpedaling",
+  "bannister": "banister",
+  "bannisters": "banisters",
+  "baptise": "baptize",
+  "baptised": "baptized",
+  "baptises": "baptizes",
+  "baptising": "baptizing",
+  "bastardise": "bastardize",
+  "bastardised": "bastardized",
+  "bastardises": "bastardizes",
+  "bastardising": "bastardizing",
+  "battleax": "battleaxe",
+  "baulk": "balk",
+  "baulked": "balked",
+  "baulking": "balking",
+  "baulks": "balks",
+  "bedevilled": "bedeviled",
+  "bedevilling": "bedeviling",
+  "behaviour": "behavior",
+  "behavioural": "behavioral",
+  "behaviourism": "behaviorism",
+  "behaviourist": "behaviorist",
+  "behaviourists": "behaviorists",
+  "behaviours": "behaviors",
+  "behove": "behoove",
+  "behoved": "behooved",
+  "behoves": "behooves",
+  "bejewelled": "bejeweled",
+  "belabour": "belabor",
+  "belaboured": "belabored",
+  "belabouring": "belaboring",
+  "belabours": "belabors",
+  "bevelled": "beveled",
+  "bevvies": "bevies",
+  "bevvy": "bevy",
+  "biassed": "biased",
+  "biassing": "biasing",
+  "bingeing": "binging",
+  "bougainvillaea": "bougainvillea",
+  "bougainvillaeas": "bougainvilleas",
+  "bowdlerise": "bowdlerize",
+  "bowdlerised": "bowdlerized",
+  "bowdlerises": "bowdlerizes",
+  "bowdlerising": "bowdlerizing",
+  "breathalyse": "breathalyze",
+  "breathalysed": "breathalyzed",
+  "breathalyser": "breathalyzer",
+  "breathalysers": "breathalyzers",
+  "breathalyses": "breathalyzes",
+  "breathalysing": "breathalyzing",
+  "brutalise": "brutalize",
+  "brutalised": "brutalized",
+  "brutalises": "brutalizes",
+  "brutalising": "brutalizing",
+  "busses": "buses",
+  "bussing": "busing",
+  "caesarean": "cesarean",
+  "caesareans": "cesareans",
+  "calibre": "caliber",
+  "calibres": "calibers",
+  "calliper": "caliper",
+  "callipers": "calipers",
+  "callisthenics": "calisthenics",
+  "canalise": "canalize",
+  "canalised": "canalized",
+  "canalises": "canalizes",
+  "canalising": "canalizing",
+  "cancelation": "cancellation",
+  "cancelations": "cancellations",
+  "cancelled": "canceled",
+  "cancelling": "canceling",
+  "candour": "candor",
+  "cannibalise": "cannibalize",
+  "cannibalised": "cannibalized",
+  "cannibalises": "cannibalizes",
+  "cannibalising": "cannibalizing",
+  "canonise": "canonize",
+  "canonised": "canonized",
+  "canonises": "canonizes",
+  "canonising": "canonizing",
+  "capitalise": "capitalize",
+  "capitalised": "capitalized",
+  "capitalises": "capitalizes",
+  "capitalising": "capitalizing",
+  "caramelise": "caramelize",
+  "caramelised": "caramelized",
+  "caramelises": "caramelizes",
+  "caramelising": "caramelizing",
+  "carbonise": "carbonize",
+  "carbonised": "carbonized",
+  "carbonises": "carbonizes",
+  "carbonising": "carbonizing",
+  "carolled": "caroled",
+  "carolling": "caroling",
+  "catalogue": "catalog",
+  "catalogued": "cataloged",
+  "catalogues": "catalogs",
+  "cataloguing": "cataloging",
+  "catalyse": "catalyze",
+  "catalysed": "catalyzed",
+  "catalyses": "catalyzes",
+  "catalysing": "catalyzing",
+  "categorise": "categorize",
+  "categorised": "categorized",
+  "categorises": "categorizes",
+  "categorising": "categorizing",
+  "cauterise": "cauterize",
+  "cauterised": "cauterized",
+  "cauterises": "cauterizes",
+  "cauterising": "cauterizing",
+  "cavilled": "caviled",
+  "cavilling": "caviling",
+  "centigramme": "centigram",
+  "centigrammes": "centigrams",
+  "centilitre": "centiliter",
+  "centilitres": "centiliters",
+  "centimetre": "centimeter",
+  "centimetres": "centimeters",
+  "centralise": "centralize",
+  "centralised": "centralized",
+  "centralises": "centralizes",
+  "centralising": "centralizing",
+  "centre": "center",
+  "centred": "centered",
+  "centrefold": "centerfold",
+  "centrefolds": "centerfolds",
+  "centrepiece": "centerpiece",
+  "centrepieces": "centerpieces",
+  "centres": "centers",
+  "channelled": "channeled",
+  "channelling": "channeling",
+  "characterise": "characterize",
+  "characterised": "characterized",
+  "characterises": "characterizes",
+  "characterising": "characterizing",
+  "cheque": "check",
+  "chequebook": "checkbook",
+  "chequebooks": "checkbooks",
+  "chequered": "checkered",
+  "cheques": "checks",
+  "chilli": "chili",
+  "chimaera": "chimera",
+  "chimaeras": "chimeras",
+  "chiselled": "chiseled",
+  "chiselling": "chiseling",
+  "circularise": "circularize",
+  "circularised": "circularized",
+  "circularises": "circularizes",
+  "circularising": "circularizing",
+  "civilise": "civilize",
+  "civilised": "civilized",
+  "civilises": "civilizes",
+  "civilising": "civilizing",
+  "clamour": "clamor",
+  "clamoured": "clamored",
+  "clamouring": "clamoring",
+  "clamours": "clamors",
+  "clangour": "clangor",
+  "clarinettist": "clarinetist",
+  "clarinettists": "clarinetists",
+  "collectivise": "collectivize",
+  "collectivised": "collectivized",
+  "collectivises": "collectivizes",
+  "collectivising": "collectivizing",
+  "colonisation": "colonization",
+  "colonise": "colonize",
+  "colonised": "colonized",
+  "coloniser": "colonizer",
+  "colonisers": "colonizers",
+  "colonises": "colonizes",
+  "colonising": "colonizing",
+  "colour": "color",
+  "colourant": "colorant",
+  "colourants": "colorants",
+  "coloured": "colored",
+  "coloureds": "coloreds",
+  "colourful": "colorful",
+  "colourfully": "colorfully",
+  "colouring": "coloring",
+  "colourize": "colorize",
+  "colourized": "colorized",
+  "colourizes": "colorizes",
+  "colourizing": "colorizing",
+  "colourless": "colorless",
+  "colours": "colors",
+  "commercialise": "commercialize",
+  "commercialised": "commercialized",
+  "commercialises": "commercializes",
+  "commercialising": "commercializing",
+  "compartmentalise": "compartmentalize",
+  "compartmentalised": "compartmentalized",
+  "compartmentalises": "compartmentalizes",
+  "compartmentalising": "compartmentalizing",
+  "computerise": "computerize",
+  "computerised": "computerized",
+  "computerises": "computerizes",
+  "computerising": "computerizing",
+  "conceptualise": "conceptualize",
+  "conceptualised": "conceptualized",
+  "conceptualises": "conceptualizes",
+  "conceptualising": "conceptualizing",
+  "connexion": "connection",
+  "connexions": "connections",
+  "contextualise": "contextualize",
+  "contextualised": "contextualized",
+  "contextualises": "contextualizes",
+  "contextualising": "contextualizing",
+  "cosier": "cozier",
+  "cosies": "cozies",
+  "cosiest": "coziest",
+  "cosily": "cozily",
+  "cosiness": "coziness",
+  "cosy": "cozy",
+  "councillor": "councilor",
+  "councillors": "councilors",
+  "counselled": "counseled",
+  "counselling": "counseling",
+  "counsellor": "counselor",
+  "counsellors": "counselors",
+  "crenelated": "crenellated",
+  "criminalise": "criminalize",
+  "criminalised": "criminalized",
+  "criminalises": "criminalizes",
+  "criminalising": "criminalizing",
+  "criticise": "criticize",
+  "criticised": "criticized",
+  "criticises": "criticizes",
+  "criticising": "criticizing",
+  "crueller": "crueler",
+  "cruellest": "cruelest",
+  "crystallisation": "crystallization",
+  "crystallise": "crystallize",
+  "crystallised": "crystallized",
+  "crystallises": "crystallizes",
+  "crystallising": "crystallizing",
+  "cudgelled": "cudgeled",
+  "cudgelling": "cudgeling",
+  "customise": "customize",
+  "customised": "customized",
+  "customises": "customizes",
+  "customising": "customizing",
+  "cypher": "cipher",
+  "cyphers": "ciphers",
+  "decentralisation": "decentralization",
+  "decentralise": "decentralize",
+  "decentralised": "decentralized",
+  "decentralises": "decentralizes",
+  "decentralising": "decentralizing",
+  "decriminalisation": "decriminalization",
+  "decriminalise": "decriminalize",
+  "decriminalised": "decriminalized",
+  "decriminalises": "decriminalizes",
+  "decriminalising": "decriminalizing",
+  "defence": "defense",
+  "defenceless": "defenseless",
+  "defences": "defenses",
+  "dehumanisation": "dehumanization",
+  "dehumanise": "dehumanize",
+  "dehumanised": "dehumanized",
+  "dehumanises": "dehumanizes",
+  "dehumanising": "dehumanizing",
+  "demeanour": "demeanor",
+  "demilitarisation": "demilitarization",
+  "demilitarise": "demilitarize",
+  "demilitarised": "demilitarized",
+  "demilitarises": "demilitarizes",
+  "demilitarising": "demilitarizing",
+  "demobilisation": "demobilization",
+  "demobilise": "demobilize",
+  "demobilised": "demobilized",
+  "demobilises": "demobilizes",
+  "demobilising": "demobilizing",
+  "democratisation": "democratization",
+  "democratise": "democratize",
+  "democratised": "democratized",
+  "democratises": "democratizes",
+  "democratising": "democratizing",
+  "demonise": "demonize",
+  "demonised": "demonized",
+  "demonises": "demonizes",
+  "demonising": "demonizing",
+  "demoralisation": "demoralization",
+  "demoralise": "demoralize",
+  "demoralised": "demoralized",
+  "demoralises": "demoralizes",
+  "demoralising": "demoralizing",
+  "denationalisation": "denationalization",
+  "denationalise": "denationalize",
+  "denationalised": "denationalized",
+  "denationalises": "denationalizes",
+  "denationalising": "denationalizing",
+  "deodorise": "deodorize",
+  "deodorised": "deodorized",
+  "deodorises": "deodorizes",
+  "deodorising": "deodorizing",
+  "depersonalise": "depersonalize",
+  "depersonalised": "depersonalized",
+  "depersonalises": "depersonalizes",
+  "depersonalising": "depersonalizing",
+  "deputise": "deputize",
+  "deputised": "deputized",
+  "deputises": "deputizes",
+  "deputising": "deputizing",
+  "desensitisation": "desensitization",
+  "desensitise": "desensitize",
+  "desensitised": "desensitized",
+  "desensitises": "desensitizes",
+  "desensitising": "desensitizing",
+  "destabilisation": "destabilization",
+  "destabilise": "destabilize",
+  "destabilised": "destabilized",
+  "destabilises": "destabilizes",
+  "destabilising": "destabilizing",
+  "dialled": "dialed",
+  "dialling": "dialing",
+  "dialogue": "dialog",
+  "dialogues": "dialogs",
+  "diarrhoea": "diarrhea",
+  "digitise": "digitize",
+  "digitised": "digitized",
+  "digitises": "digitizes",
+  "digitising": "digitizing",
+  "disc": "disk",
+  "discolour": "discolor",
+  "discoloured": "discolored",
+  "discolouring": "discoloring",
+  "discolours": "discolors",
+  "discs": "disks",
+  "disembowelled": "disemboweled",
+  "disembowelling": "disemboweling",
+  "disfavour": "disfavor",
+  "dishevelled": "disheveled",
+  "dishonour": "dishonor",
+  "dishonourable": "dishonorable",
+  "dishonourably": "dishonorably",
+  "dishonoured": "dishonored",
+  "dishonouring": "dishonoring",
+  "dishonours": "dishonors",
+  "disorganisation": "disorganization",
+  "disorganised": "disorganized",
+  "distil": "distill",
+  "distils": "distills",
+  "dramatisation": "dramatization",
+  "dramatisations": "dramatizations",
+  "dramatise": "dramatize",
+  "dramatised": "dramatized",
+  "dramatises": "dramatizes",
+  "dramatising": "dramatizing",
+  "draught": "draft",
+  "draughtboard": "draftboard",
+  "draughtboards": "draftboards",
+  "draughtier": "draftier",
+  "draughtiest": "draftiest",
+  "draughts": "drafts",
+  "draughtsman": "draftsman",
+  "draughtsmanship": "draftsmanship",
+  "draughtsmen": "draftsmen",
+  "draughtswoman": "draftswoman",
+  "draughtswomen": "draftswomen",
+  "draughty": "drafty",
+  "drivelled": "driveled",
+  "drivelling": "driveling",
+  "duelled": "dueled",
+  "duelling": "dueling",
+  "economise": "economize",
+  "economised": "economized",
+  "economises": "economizes",
+  "economising": "economizing",
+  "editorialise": "editorialize",
+  "editorialised": "editorialized",
+  "editorialises": "editorializes",
+  "editorialising": "editorializing",
+  "edoema": "edema",
+  "empathise": "empathize",
+  "empathised": "empathized",
+  "empathises": "empathizes",
+  "empathising": "empathizing",
+  "emphasise": "emphasize",
+  "emphasised": "emphasized",
+  "emphasises": "emphasizes",
+  "emphasising": "emphasizing",
+  "enamelled": "enameled",
+  "enamelling": "enameling",
+  "enamoured": "enamored",
+  "encyclopaedia": "encyclopedia",
+  "encyclopaedias": "encyclopedias",
+  "encyclopaedic": "encyclopedic",
+  "endeavour": "endeavor",
+  "endeavoured": "endeavored",
+  "endeavouring": "endeavoring",
+  "endeavours": "endeavors",
+  "energise": "energize",
+  "energised": "energized",
+  "energises": "energizes",
+  "energising": "energizing",
+  "enrol": "enroll",
+  "enrols": "enrolls",
+  "enthral": "enthrall",
+  "enthrals": "enthralls",
+  "epaulette": "epaulet",
+  "epaulettes": "epaulets",
+  "epicentre": "epicenter",
+  "epicentres": "epicenters",
+  "epilogue": "epilog",
+  "epilogues": "epilogs",
+  "epitomise": "epitomize",
+  "epitomised": "epitomized",
+  "epitomises": "epitomizes",
+  "epitomising": "epitomizing",
+  "equalisation": "equalization",
+  "equalise": "equalize",
+  "equalised": "equalized",
+  "equaliser": "equalizer",
+  "equalisers": "equalizers",
+  "equalises": "equalizes",
+  "equalising": "equalizing",
+  "eulogise": "eulogize",
+  "eulogised": "eulogized",
+  "eulogises": "eulogizes",
+  "eulogising": "eulogizing",
+  "evangelise": "evangelize",
+  "evangelised": "evangelized",
+  "evangelises": "evangelizes",
+  "evangelising": "evangelizing",
+  "exorcise": "exorcize",
+  "exorcised": "exorcized",
+  "exorcises": "exorcizes",
+  "exorcising": "exorcizing",
+  "extemporisation": "extemporization",
+  "extemporise": "extemporize",
+  "extemporised": "extemporized",
+  "extemporises": "extemporizes",
+  "extemporising": "extemporizing",
+  "externalisation": "externalization",
+  "externalisations": "externalizations",
+  "externalise": "externalize",
+  "externalised": "externalized",
+  "externalises": "externalizes",
+  "externalising": "externalizing",
+  "factorise": "factorize",
+  "factorised": "factorized",
+  "factorises": "factorizes",
+  "factorising": "factorizing",
+  "faecal": "fecal",
+  "faeces": "feces",
+  "familiarisation": "familiarization",
+  "familiarise": "familiarize",
+  "familiarised": "familiarized",
+  "familiarises": "familiarizes",
+  "familiarising": "familiarizing",
+  "fantasise": "fantasize",
+  "fantasised": "fantasized",
+  "fantasises": "fantasizes",
+  "fantasising": "fantasizing",
+  "favour": "favor",
+  "favourable": "favorable",
+  "favourably": "favorably",
+  "favoured": "favored",
+  "favouring": "favoring",
+  "favourite": "favorite",
+  "favourites": "favorites",
+  "favouritism": "favoritism",
+  "favours": "favors",
+  "feminise": "feminize",
+  "feminised": "feminized",
+  "feminises": "feminizes",
+  "feminising": "feminizing",
+  "fertilisation": "fertilization",
+  "fertilise": "fertilize",
+  "fertilised": "fertilized",
+  "fertiliser": "fertilizer",
+  "fertilisers": "fertilizers",
+  "fertilises": "fertilizes",
+  "fertilising": "fertilizing",
+  "fervour": "fervor",
+  "fibre": "fiber",
+  "fibreglass": "fiberglass",
+  "fibres": "fibers",
+  "fictionalisation": "fictionalization",
+  "fictionalisations": "fictionalizations",
+  "fictionalise": "fictionalize",
+  "fictionalised": "fictionalized",
+  "fictionalises": "fictionalizes",
+  "fictionalising": "fictionalizing",
+  "fillet": "filet",
+  "filleted": "fileted",
+  "filleting": "fileting",
+  "fillets": "filets",
+  "finalisation": "finalization",
+  "finalise": "finalize",
+  "finalised": "finalized",
+  "finalises": "finalizes",
+  "finalising": "finalizing",
+  "flautist": "flutist",
+  "flautists": "flutists",
+  "flavour": "flavor",
+  "flavoured": "flavored",
+  "flavouring": "flavoring",
+  "flavourings": "flavorings",
+  "flavourless": "flavorless",
+  "flavours": "flavors",
+  "flavoursome": "flavorsome",
+  "flyer / flier": "flier / flyer",
+  "foetal": "fetal",
+  "foetid": "fetid",
+  "foetus": "fetus",
+  "foetuses": "fetuses",
+  "formalisation": "formalization",
+  "formalise": "formalize",
+  "formalised": "formalized",
+  "formalises": "formalizes",
+  "formalising": "formalizing",
+  "fossilisation": "fossilization",
+  "fossilise": "fossilize",
+  "fossilised": "fossilized",
+  "fossilises": "fossilizes",
+  "fossilising": "fossilizing",
+  "fraternisation": "fraternization",
+  "fraternise": "fraternize",
+  "fraternised": "fraternized",
+  "fraternises": "fraternizes",
+  "fraternising": "fraternizing",
+  "fulfil": "fulfill",
+  "fulfilment": "fulfillment",
+  "fulfils": "fulfills",
+  "funnelled": "funneled",
+  "funnelling": "funneling",
+  "gage": "gauge",
+  "gaged": "gauged",
+  "gages": "gauges",
+  "gaging": "gauging",
+  "galvanise": "galvanize",
+  "galvanised": "galvanized",
+  "galvanises": "galvanizes",
+  "galvanising": "galvanizing",
+  "gambolled": "gamboled",
+  "gambolling": "gamboling",
+  "gaol": "jail",
+  "gaolbird": "jailbird",
+  "gaolbirds": "jailbirds",
+  "gaolbreak": "jailbreak",
+  "gaolbreaks": "jailbreaks",
+  "gaoled": "jailed",
+  "gaoler": "jailer",
+  "gaolers": "jailers",
+  "gaoling": "jailing",
+  "gaols": "jails",
+  "gasses": "gases",
+  "generalisation": "generalization",
+  "generalisations": "generalizations",
+  "generalise": "generalize",
+  "generalised": "generalized",
+  "generalises": "generalizes",
+  "generalising": "generalizing",
+  "ghettoise": "ghettoize",
+  "ghettoised": "ghettoized",
+  "ghettoises": "ghettoizes",
+  "ghettoising": "ghettoizing",
+  "gipsies": "gypsies",
+  "glamor": "glamour",
+  "glamorise": "glamorize",
+  "glamorised": "glamorized",
+  "glamorises": "glamorizes",
+  "glamorising": "glamorizing",
+  "globalisation": "globalization",
+  "globalise": "globalize",
+  "globalised": "globalized",
+  "globalises": "globalizes",
+  "globalising": "globalizing",
+  "glueing": "gluing",
+  "goitre": "goiter",
+  "goitres": "goiters",
+  "gonorrhoea": "gonorrhea",
+  "gramme": "gram",
+  "grammes": "grams",
+  "gravelled": "graveled",
+  "grey": "gray",
+  "greyed": "grayed",
+  "greying": "graying",
+  "greyish": "grayish",
+  "greyness": "grayness",
+  "greys": "grays",
+  "grovelled": "groveled",
+  "grovelling": "groveling",
+  "groyne": "groin",
+  "groynes": "groins",
+  "gruelling": "grueling",
+  "gruellingly": "gruelingly",
+  "gryphon": "griffin",
+  "gryphons": "griffins",
+  "gynaecological": "gynecological",
+  "gynaecologist": "gynecologist",
+  "gynaecologists": "gynecologists",
+  "gynaecology": "gynecology",
+  "haematological": "hematological",
+  "haematologist": "hematologist",
+  "haematologists": "hematologists",
+  "haematology": "hematology",
+  "haemoglobin": "hemoglobin",
+  "haemophilia": "hemophilia",
+  "haemophiliac": "hemophiliac",
+  "haemophiliacs": "hemophiliacs",
+  "haemorrhage": "hemorrhage",
+  "haemorrhaged": "hemorrhaged",
+  "haemorrhages": "hemorrhages",
+  "haemorrhaging": "hemorrhaging",
+  "haemorrhoids": "hemorrhoids",
+  "harbour": "harbor",
+  "harboured": "harbored",
+  "harbouring": "harboring",
+  "harbours": "harbors",
+  "harmonisation": "harmonization",
+  "harmonise": "harmonize",
+  "harmonised": "harmonized",
+  "harmonises": "harmonizes",
+  "harmonising": "harmonizing",
+  "homoeopath": "homeopath",
+  "homoeopathic": "homeopathic",
+  "homoeopaths": "homeopaths",
+  "homoeopathy": "homeopathy",
+  "homogenise": "homogenize",
+  "homogenised": "homogenized",
+  "homogenises": "homogenizes",
+  "homogenising": "homogenizing",
+  "honour": "honor",
+  "honourable": "honorable",
+  "honourably": "honorably",
+  "honoured": "honored",
+  "honouring": "honoring",
+  "honours": "honors",
+  "hospitalisation": "hospitalization",
+  "hospitalise": "hospitalize",
+  "hospitalised": "hospitalized",
+  "hospitalises": "hospitalizes",
+  "hospitalising": "hospitalizing",
+  "humanise": "humanize",
+  "humanised": "humanized",
+  "humanises": "humanizes",
+  "humanising": "humanizing",
+  "humour": "humor",
+  "humoured": "humored",
+  "humouring": "humoring",
+  "humourless": "humorless",
+  "humours": "humors",
+  "hybridise": "hybridize",
+  "hybridised": "hybridized",
+  "hybridises": "hybridizes",
+  "hybridising": "hybridizing",
+  "hypnotise": "hypnotize",
+  "hypnotised": "hypnotized",
+  "hypnotises": "hypnotizes",
+  "hypnotising": "hypnotizing",
+  "hypothesise": "hypothesize",
+  "hypothesised": "hypothesized",
+  "hypothesises": "hypothesizes",
+  "hypothesising": "hypothesizing",
+  "idealisation": "idealization",
+  "idealise": "idealize",
+  "idealised": "idealized",
+  "idealises": "idealizes",
+  "idealising": "idealizing",
+  "idolise": "idolize",
+  "idolised": "idolized",
+  "idolises": "idolizes",
+  "idolising": "idolizing",
+  "immobilisation": "immobilization",
+  "immobilise": "immobilize",
+  "immobilised": "immobilized",
+  "immobiliser": "immobilizer",
+  "immobilisers": "immobilizers",
+  "immobilises": "immobilizes",
+  "immobilising": "immobilizing",
+  "immortalise": "immortalize",
+  "immortalised": "immortalized",
+  "immortalises": "immortalizes",
+  "immortalising": "immortalizing",
+  "immunisation": "immunization",
+  "immunise": "immunize",
+  "immunised": "immunized",
+  "immunises": "immunizes",
+  "immunising": "immunizing",
+  "impanelled": "impaneled",
+  "impanelling": "impaneling",
+  "imperilled": "imperiled",
+  "imperilling": "imperiling",
+  "individualise": "individualize",
+  "individualised": "individualized",
+  "individualises": "individualizes",
+  "individualising": "individualizing",
+  "industrialise": "industrialize",
+  "industrialised": "industrialized",
+  "industrialises": "industrializes",
+  "industrialising": "industrializing",
+  "inflexion": "inflection",
+  "inflexions": "inflections",
+  "initialise": "initialize",
+  "initialised": "initialized",
+  "initialises": "initializes",
+  "initialising": "initializing",
+  "initialled": "initialed",
+  "initialling": "initialing",
+  "instal": "install",
+  "instalment": "installment",
+  "instalments": "installments",
+  "instals": "installs",
+  "instil": "instill",
+  "instils": "instills",
+  "institutionalisation": "institutionalization",
+  "institutionalise": "institutionalize",
+  "institutionalised": "institutionalized",
+  "institutionalises": "institutionalizes",
+  "institutionalising": "institutionalizing",
+  "intellectualise": "intellectualize",
+  "intellectualised": "intellectualized",
+  "intellectualises": "intellectualizes",
+  "intellectualising": "intellectualizing",
+  "internalisation": "internalization",
+  "internalise": "internalize",
+  "internalised": "internalized",
+  "internalises": "internalizes",
+  "internalising": "internalizing",
+  "internationalisation": "internationalization",
+  "internationalise": "internationalize",
+  "internationalised": "internationalized",
+  "internationalises": "internationalizes",
+  "internationalising": "internationalizing",
+  "ionisation": "ionization",
+  "ionise": "ionize",
+  "ionised": "ionized",
+  "ioniser": "ionizer",
+  "ionisers": "ionizers",
+  "ionises": "ionizes",
+  "ionising": "ionizing",
+  "italicise": "italicize",
+  "italicised": "italicized",
+  "italicises": "italicizes",
+  "italicising": "italicizing",
+  "itemise": "itemize",
+  "itemised": "itemized",
+  "itemises": "itemizes",
+  "itemising": "itemizing",
+  "jeopardise": "jeopardize",
+  "jeopardised": "jeopardized",
+  "jeopardises": "jeopardizes",
+  "jeopardising": "jeopardizing",
+  "jewelled": "jeweled",
+  "jeweller": "jeweler",
+  "jewellers": "jewelers",
+  "jewellery": "jewelry",
+  "judgement": "judgment",
+  "kilogramme": "kilogram",
+  "kilogrammes": "kilograms",
+  "kilometre": "kilometer",
+  "kilometres": "kilometers",
+  "labelled": "labeled",
+  "labelling": "labeling",
+  "labour": "labor",
+  "laboured": "labored",
+  "labourer": "laborer",
+  "labourers": "laborers",
+  "labouring": "laboring",
+  "labours": "labors",
+  "lacklustre": "lackluster",
+  "legalisation": "legalization",
+  "legalise": "legalize",
+  "legalised": "legalized",
+  "legalises": "legalizes",
+  "legalising": "legalizing",
+  "legitimise": "legitimize",
+  "legitimised": "legitimized",
+  "legitimises": "legitimizes",
+  "legitimising": "legitimizing",
+  "leukaemia": "leukemia",
+  "levelled": "leveled",
+  "leveller": "leveler",
+  "levellers": "levelers",
+  "levelling": "leveling",
+  "libelled": "libeled",
+  "libelling": "libeling",
+  "libellous": "libelous",
+  "liberalisation": "liberalization",
+  "liberalise": "liberalize",
+  "liberalised": "liberalized",
+  "liberalises": "liberalizes",
+  "liberalising": "liberalizing",
+  "licence": "license",
+  "licenced": "licensed",
+  "licences": "licenses",
+  "licencing": "licensing",
+  "likeable": "likable",
+  "lionisation": "lionization",
+  "lionise": "lionize",
+  "lionised": "lionized",
+  "lionises": "lionizes",
+  "lionising": "lionizing",
+  "liquidise": "liquidize",
+  "liquidised": "liquidized",
+  "liquidiser": "liquidizer",
+  "liquidisers": "liquidizers",
+  "liquidises": "liquidizes",
+  "liquidising": "liquidizing",
+  "litre": "liter",
+  "litres": "liters",
+  "localise": "localize",
+  "localised": "localized",
+  "localises": "localizes",
+  "localising": "localizing",
+  "louvre": "louver",
+  "louvred": "louvered",
+  "louvres": "louvers",
+  "lustre": "luster",
+  "magnetise": "magnetize",
+  "magnetised": "magnetized",
+  "magnetises": "magnetizes",
+  "magnetising": "magnetizing",
+  "manoeuvrability": "maneuverability",
+  "manoeuvrable": "maneuverable",
+  "manoeuvre": "maneuver",
+  "manoeuvred": "maneuvered",
+  "manoeuvres": "maneuvers",
+  "manoeuvring": "maneuvering",
+  "manoeuvrings": "maneuverings",
+  "marginalisation": "marginalization",
+  "marginalise": "marginalize",
+  "marginalised": "marginalized",
+  "marginalises": "marginalizes",
+  "marginalising": "marginalizing",
+  "marshalled": "marshaled",
+  "marshalling": "marshaling",
+  "marvelled": "marveled",
+  "marvelling": "marveling",
+  "marvellous": "marvelous",
+  "marvellously": "marvelously",
+  "materialisation": "materialization",
+  "materialise": "materialize",
+  "materialised": "materialized",
+  "materialises": "materializes",
+  "materialising": "materializing",
+  "maximisation": "maximization",
+  "maximise": "maximize",
+  "maximised": "maximized",
+  "maximises": "maximizes",
+  "maximising": "maximizing",
+  "meagre": "meager",
+  "mechanisation": "mechanization",
+  "mechanise": "mechanize",
+  "mechanised": "mechanized",
+  "mechanises": "mechanizes",
+  "mechanising": "mechanizing",
+  "mediaeval": "medieval",
+  "memorialise": "memorialize",
+  "memorialised": "memorialized",
+  "memorialises": "memorializes",
+  "memorialising": "memorializing",
+  "memorise": "memorize",
+  "memorised": "memorized",
+  "memorises": "memorizes",
+  "memorising": "memorizing",
+  "mesmerise": "mesmerize",
+  "mesmerised": "mesmerized",
+  "mesmerises": "mesmerizes",
+  "mesmerising": "mesmerizing",
+  "metabolise": "metabolize",
+  "metabolised": "metabolized",
+  "metabolises": "metabolizes",
+  "metabolising": "metabolizing",
+  "metre": "meter",
+  "metres": "meters",
+  "mhm": "hmm",
+  "micrometre": "micrometer",
+  "micrometres": "micrometers",
+  "militarise": "militarize",
+  "militarised": "militarized",
+  "militarises": "militarizes",
+  "militarising": "militarizing",
+  "milligramme": "milligram",
+  "milligrammes": "milligrams",
+  "millilitre": "milliliter",
+  "millilitres": "milliliters",
+  "millimetre": "millimeter",
+  "millimetres": "millimeters",
+  "miniaturisation": "miniaturization",
+  "miniaturise": "miniaturize",
+  "miniaturised": "miniaturized",
+  "miniaturises": "miniaturizes",
+  "miniaturising": "miniaturizing",
+  "minibusses": "minibuses",
+  "minimise": "minimize",
+  "minimised": "minimized",
+  "minimises": "minimizes",
+  "minimising": "minimizing",
+  "misbehaviour": "misbehavior",
+  "misdemeanour": "misdemeanor",
+  "misdemeanours": "misdemeanors",
+  "misspelt": "misspelled",
+  "mitre": "miter",
+  "mitres": "miters",
+  "mm": "hmm",
+  "mmm": "hmm",
+  "mobilisation": "mobilization",
+  "mobilise": "mobilize",
+  "mobilised": "mobilized",
+  "mobilises": "mobilizes",
+  "mobilising": "mobilizing",
+  "modelled": "modeled",
+  "modeller": "modeler",
+  "modellers": "modelers",
+  "modelling": "modeling",
+  "modernise": "modernize",
+  "modernised": "modernized",
+  "modernises": "modernizes",
+  "modernising": "modernizing",
+  "moisturise": "moisturize",
+  "moisturised": "moisturized",
+  "moisturiser": "moisturizer",
+  "moisturisers": "moisturizers",
+  "moisturises": "moisturizes",
+  "moisturising": "moisturizing",
+  "monologue": "monolog",
+  "monologues": "monologs",
+  "monopolisation": "monopolization",
+  "monopolise": "monopolize",
+  "monopolised": "monopolized",
+  "monopolises": "monopolizes",
+  "monopolising": "monopolizing",
+  "moralise": "moralize",
+  "moralised": "moralized",
+  "moralises": "moralizes",
+  "moralising": "moralizing",
+  "motorised": "motorized",
+  "mould": "mold",
+  "moulded": "molded",
+  "moulder": "molder",
+  "mouldered": "moldered",
+  "mouldering": "moldering",
+  "moulders": "molders",
+  "mouldier": "moldier",
+  "mouldiest": "moldiest",
+  "moulding": "molding",
+  "mouldings": "moldings",
+  "moulds": "molds",
+  "mouldy": "moldy",
+  "moult": "molt",
+  "moulted": "molted",
+  "moulting": "molting",
+  "moults": "molts",
+  "moustache": "mustache",
+  "moustached": "mustached",
+  "moustaches": "mustaches",
+  "moustachioed": "mustachioed",
+  "multicoloured": "multicolored",
+  "nationalisation": "nationalization",
+  "nationalisations": "nationalizations",
+  "nationalise": "nationalize",
+  "nationalised": "nationalized",
+  "nationalises": "nationalizes",
+  "nationalising": "nationalizing",
+  "naturalisation": "naturalization",
+  "naturalise": "naturalize",
+  "naturalised": "naturalized",
+  "naturalises": "naturalizes",
+  "naturalising": "naturalizing",
+  "neighbour": "neighbor",
+  "neighbourhood": "neighborhood",
+  "neighbourhoods": "neighborhoods",
+  "neighbouring": "neighboring",
+  "neighbourliness": "neighborliness",
+  "neighbourly": "neighborly",
+  "neighbours": "neighbors",
+  "neutralisation": "neutralization",
+  "neutralise": "neutralize",
+  "neutralised": "neutralized",
+  "neutralises": "neutralizes",
+  "neutralising": "neutralizing",
+  "normalisation": "normalization",
+  "normalise": "normalize",
+  "normalised": "normalized",
+  "normalises": "normalizes",
+  "normalising": "normalizing",
+  "odour": "odor",
+  "odourless": "odorless",
+  "odours": "odors",
+  "oesophagus": "esophagus",
+  "oesophaguses": "esophaguses",
+  "oestrogen": "estrogen",
+  "offence": "offense",
+  "offences": "offenses",
+  "omelette": "omelet",
+  "omelettes": "omelets",
+  "optimise": "optimize",
+  "optimised": "optimized",
+  "optimises": "optimizes",
+  "optimising": "optimizing",
+  "organisation": "organization",
+  "organisational": "organizational",
+  "organisations": "organizations",
+  "organise": "organize",
+  "organised": "organized",
+  "organiser": "organizer",
+  "organisers": "organizers",
+  "organises": "organizes",
+  "organising": "organizing",
+  "orthopaedic": "orthopedic",
+  "orthopaedics": "orthopedics",
+  "ostracise": "ostracize",
+  "ostracised": "ostracized",
+  "ostracises": "ostracizes",
+  "ostracising": "ostracizing",
+  "outmanoeuvre": "outmaneuver",
+  "outmanoeuvred": "outmaneuvered",
+  "outmanoeuvres": "outmaneuvers",
+  "outmanoeuvring": "outmaneuvering",
+  "overemphasise": "overemphasize",
+  "overemphasised": "overemphasized",
+  "overemphasises": "overemphasizes",
+  "overemphasising": "overemphasizing",
+  "oxidisation": "oxidization",
+  "oxidise": "oxidize",
+  "oxidised": "oxidized",
+  "oxidises": "oxidizes",
+  "oxidising": "oxidizing",
+  "paederast": "pederast",
+  "paederasts": "pederasts",
+  "paediatric": "pediatric",
+  "paediatrician": "pediatrician",
+  "paediatricians": "pediatricians",
+  "paediatrics": "pediatrics",
+  "paedophile": "pedophile",
+  "paedophiles": "pedophiles",
+  "paedophilia": "pedophilia",
+  "palaeolithic": "paleolithic",
+  "palaeontologist": "paleontologist",
+  "palaeontologists": "paleontologists",
+  "palaeontology": "paleontology",
+  "panelled": "paneled",
+  "panelling": "paneling",
+  "panellist": "panelist",
+  "panellists": "panelists",
+  "paralyse": "paralyze",
+  "paralysed": "paralyzed",
+  "paralyses": "paralyzes",
+  "paralysing": "paralyzing",
+  "parcelled": "parceled",
+  "parcelling": "parceling",
+  "parlour": "parlor",
+  "parlours": "parlors",
+  "particularise": "particularize",
+  "particularised": "particularized",
+  "particularises": "particularizes",
+  "particularising": "particularizing",
+  "passivisation": "passivization",
+  "passivise": "passivize",
+  "passivised": "passivized",
+  "passivises": "passivizes",
+  "passivising": "passivizing",
+  "pasteurisation": "pasteurization",
+  "pasteurise": "pasteurize",
+  "pasteurised": "pasteurized",
+  "pasteurises": "pasteurizes",
+  "pasteurising": "pasteurizing",
+  "patronise": "patronize",
+  "patronised": "patronized",
+  "patronises": "patronizes",
+  "patronising": "patronizing",
+  "patronisingly": "patronizingly",
+  "pedalled": "pedaled",
+  "pedalling": "pedaling",
+  "pedestrianisation": "pedestrianization",
+  "pedestrianise": "pedestrianize",
+  "pedestrianised": "pedestrianized",
+  "pedestrianises": "pedestrianizes",
+  "pedestrianising": "pedestrianizing",
+  "penalise": "penalize",
+  "penalised": "penalized",
+  "penalises": "penalizes",
+  "penalising": "penalizing",
+  "pencilled": "penciled",
+  "pencilling": "penciling",
+  "personalise": "personalize",
+  "personalised": "personalized",
+  "personalises": "personalizes",
+  "personalising": "personalizing",
+  "pharmacopoeia": "pharmacopeia",
+  "pharmacopoeias": "pharmacopeias",
+  "philosophise": "philosophize",
+  "philosophised": "philosophized",
+  "philosophises": "philosophizes",
+  "philosophising": "philosophizing",
+  "philtre": "filter",
+  "philtres": "filters",
+  "phoney": "phony",
+  "plagiarise": "plagiarize",
+  "plagiarised": "plagiarized",
+  "plagiarises": "plagiarizes",
+  "plagiarising": "plagiarizing",
+  "plough": "plow",
+  "ploughed": "plowed",
+  "ploughing": "plowing",
+  "ploughman": "plowman",
+  "ploughmen": "plowmen",
+  "ploughs": "plows",
+  "ploughshare": "plowshare",
+  "ploughshares": "plowshares",
+  "polarisation": "polarization",
+  "polarise": "polarize",
+  "polarised": "polarized",
+  "polarises": "polarizes",
+  "polarising": "polarizing",
+  "politicisation": "politicization",
+  "politicise": "politicize",
+  "politicised": "politicized",
+  "politicises": "politicizes",
+  "politicising": "politicizing",
+  "popularisation": "popularization",
+  "popularise": "popularize",
+  "popularised": "popularized",
+  "popularises": "popularizes",
+  "popularising": "popularizing",
+  "pouffe": "pouf",
+  "pouffes": "poufs",
+  "practise": "practice",
+  "practised": "practiced",
+  "practises": "practices",
+  "practising": "practicing",
+  "praesidium": "presidium",
+  "praesidiums": "presidiums",
+  "pressurisation": "pressurization",
+  "pressurise": "pressurize",
+  "pressurised": "pressurized",
+  "pressurises": "pressurizes",
+  "pressurising": "pressurizing",
+  "pretence": "pretense",
+  "pretences": "pretenses",
+  "primaeval": "primeval",
+  "prioritisation": "prioritization",
+  "prioritise": "prioritize",
+  "prioritised": "prioritized",
+  "prioritises": "prioritizes",
+  "prioritising": "prioritizing",
+  "privatisation": "privatization",
+  "privatisations": "privatizations",
+  "privatise": "privatize",
+  "privatised": "privatized",
+  "privatises": "privatizes",
+  "privatising": "privatizing",
+  "professionalisation": "professionalization",
+  "professionalise": "professionalize",
+  "professionalised": "professionalized",
+  "professionalises": "professionalizes",
+  "professionalising": "professionalizing",
+  "programme": "program",
+  "programmes": "programs",
+  "prologue": "prolog",
+  "prologues": "prologs",
+  "propagandise": "propagandize",
+  "propagandised": "propagandized",
+  "propagandises": "propagandizes",
+  "propagandising": "propagandizing",
+  "proselytise": "proselytize",
+  "proselytised": "proselytized",
+  "proselytiser": "proselytizer",
+  "proselytisers": "proselytizers",
+  "proselytises": "proselytizes",
+  "proselytising": "proselytizing",
+  "psychoanalyse": "psychoanalyze",
+  "psychoanalysed": "psychoanalyzed",
+  "psychoanalyses": "psychoanalyzes",
+  "psychoanalysing": "psychoanalyzing",
+  "publicise": "publicize",
+  "publicised": "publicized",
+  "publicises": "publicizes",
+  "publicising": "publicizing",
+  "pulverisation": "pulverization",
+  "pulverise": "pulverize",
+  "pulverised": "pulverized",
+  "pulverises": "pulverizes",
+  "pulverising": "pulverizing",
+  "pummelled": "pummel",
+  "pummelling": "pummeled",
+  "pyjama": "pajama",
+  "pyjamas": "pajamas",
+  "pzazz": "pizzazz",
+  "quarrelled": "quarreled",
+  "quarrelling": "quarreling",
+  "radicalise": "radicalize",
+  "radicalised": "radicalized",
+  "radicalises": "radicalizes",
+  "radicalising": "radicalizing",
+  "rancour": "rancor",
+  "randomise": "randomize",
+  "randomised": "randomized",
+  "randomises": "randomizes",
+  "randomising": "randomizing",
+  "rationalisation": "rationalization",
+  "rationalisations": "rationalizations",
+  "rationalise": "rationalize",
+  "rationalised": "rationalized",
+  "rationalises": "rationalizes",
+  "rationalising": "rationalizing",
+  "ravelled": "raveled",
+  "ravelling": "raveling",
+  "realisable": "realizable",
+  "realisation": "realization",
+  "realisations": "realizations",
+  "realise": "realize",
+  "realised": "realized",
+  "realises": "realizes",
+  "realising": "realizing",
+  "recognisable": "recognizable",
+  "recognisably": "recognizably",
+  "recognisance": "recognizance",
+  "recognise": "recognize",
+  "recognised": "recognized",
+  "recognises": "recognizes",
+  "recognising": "recognizing",
+  "reconnoitre": "reconnoiter",
+  "reconnoitred": "reconnoitered",
+  "reconnoitres": "reconnoiters",
+  "reconnoitring": "reconnoitering",
+  "refuelled": "refueled",
+  "refuelling": "refueling",
+  "regularisation": "regularization",
+  "regularise": "regularize",
+  "regularised": "regularized",
+  "regularises": "regularizes",
+  "regularising": "regularizing",
+  "remodelled": "remodeled",
+  "remodelling": "remodeling",
+  "remould": "remold",
+  "remoulded": "remolded",
+  "remoulding": "remolding",
+  "remoulds": "remolds",
+  "reorganisation": "reorganization",
+  "reorganisations": "reorganizations",
+  "reorganise": "reorganize",
+  "reorganised": "reorganized",
+  "reorganises": "reorganizes",
+  "reorganising": "reorganizing",
+  "revelled": "reveled",
+  "reveller": "reveler",
+  "revellers": "revelers",
+  "revelling": "reveling",
+  "revitalise": "revitalize",
+  "revitalised": "revitalized",
+  "revitalises": "revitalizes",
+  "revitalising": "revitalizing",
+  "revolutionise": "revolutionize",
+  "revolutionised": "revolutionized",
+  "revolutionises": "revolutionizes",
+  "revolutionising": "revolutionizing",
+  "rhapsodise": "rhapsodize",
+  "rhapsodised": "rhapsodized",
+  "rhapsodises": "rhapsodizes",
+  "rhapsodising": "rhapsodizing",
+  "rigour": "rigor",
+  "rigours": "rigors",
+  "ritualised": "ritualized",
+  "rivalled": "rivaled",
+  "rivalling": "rivaling",
+  "romanticise": "romanticize",
+  "romanticised": "romanticized",
+  "romanticises": "romanticizes",
+  "romanticising": "romanticizing",
+  "rumour": "rumor",
+  "rumoured": "rumored",
+  "rumours": "rumors",
+  "sabre": "saber",
+  "sabres": "sabers",
+  "saltpetre": "saltpeter",
+  "sanitise": "sanitize",
+  "sanitised": "sanitized",
+  "sanitises": "sanitizes",
+  "sanitising": "sanitizing",
+  "satirise": "satirize",
+  "satirised": "satirized",
+  "satirises": "satirizes",
+  "satirising": "satirizing",
+  "saviour": "savior",
+  "saviours": "saviors",
+  "savour": "savor",
+  "savoured": "savored",
+  "savouries": "savories",
+  "savouring": "savoring",
+  "savours": "savors",
+  "savoury": "savory",
+  "scandalise": "scandalize",
+  "scandalised": "scandalized",
+  "scandalises": "scandalizes",
+  "scandalising": "scandalizing",
+  "sceptic": "skeptic",
+  "sceptical": "skeptical",
+  "sceptically": "skeptically",
+  "scepticism": "skepticism",
+  "sceptics": "skeptics",
+  "sceptre": "scepter",
+  "sceptres": "scepters",
+  "scrutinise": "scrutinize",
+  "scrutinised": "scrutinized",
+  "scrutinises": "scrutinizes",
+  "scrutinising": "scrutinizing",
+  "secularisation": "secularization",
+  "secularise": "secularize",
+  "secularised": "secularized",
+  "secularises": "secularizes",
+  "secularising": "secularizing",
+  "sensationalise": "sensationalize",
+  "sensationalised": "sensationalized",
+  "sensationalises": "sensationalizes",
+  "sensationalising": "sensationalizing",
+  "sensitise": "sensitize",
+  "sensitised": "sensitized",
+  "sensitises": "sensitizes",
+  "sensitising": "sensitizing",
+  "sentimentalise": "sentimentalize",
+  "sentimentalised": "sentimentalized",
+  "sentimentalises": "sentimentalizes",
+  "sentimentalising": "sentimentalizing",
+  "sepulchre": "sepulcher",
+  "sepulchres": "sepulchers",
+  "serialisation": "serialization",
+  "serialisations": "serializations",
+  "serialise": "serialize",
+  "serialised": "serialized",
+  "serialises": "serializes",
+  "serialising": "serializing",
+  "sermonise": "sermonize",
+  "sermonised": "sermonized",
+  "sermonises": "sermonizes",
+  "sermonising": "sermonizing",
+  "sheikh": "sheik",
+  "shovelled": "shoveled",
+  "shovelling": "shoveling",
+  "shrivelled": "shriveled",
+  "shrivelling": "shriveling",
+  "signalise": "signalize",
+  "signalised": "signalized",
+  "signalises": "signalizes",
+  "signalising": "signalizing",
+  "signalled": "signaled",
+  "signalling": "signaling",
+  "smoulder": "smolder",
+  "smouldered": "smoldered",
+  "smouldering": "smoldering",
+  "smoulders": "smolders",
+  "snivelled": "sniveled",
+  "snivelling": "sniveling",
+  "snorkelled": "snorkeled",
+  "snorkelling": "snorkeling",
+  "snowplough": "snowplow",
+  "snowploughs": "snowplow",
+  "socialisation": "socialization",
+  "socialise": "socialize",
+  "socialised": "socialized",
+  "socialises": "socializes",
+  "socialising": "socializing",
+  "sodomise": "sodomize",
+  "sodomised": "sodomized",
+  "sodomises": "sodomizes",
+  "sodomising": "sodomizing",
+  "solemnise": "solemnize",
+  "solemnised": "solemnized",
+  "solemnises": "solemnizes",
+  "solemnising": "solemnizing",
+  "sombre": "somber",
+  "specialisation": "specialization",
+  "specialisations": "specializations",
+  "specialise": "specialize",
+  "specialised": "specialized",
+  "specialises": "specializes",
+  "specialising": "specializing",
+  "spectre": "specter",
+  "spectres": "specters",
+  "spiralled": "spiraled",
+  "spiralling": "spiraling",
+  "splendour": "splendor",
+  "splendours": "splendors",
+  "squirrelled": "squirreled",
+  "squirrelling": "squirreling",
+  "stabilisation": "stabilization",
+  "stabilise": "stabilize",
+  "stabilised": "stabilized",
+  "stabiliser": "stabilizer",
+  "stabilisers": "stabilizers",
+  "stabilises": "stabilizes",
+  "stabilising": "stabilizing",
+  "standardisation": "standardization",
+  "standardise": "standardize",
+  "standardised": "standardized",
+  "standardises": "standardizes",
+  "standardising": "standardizing",
+  "stencilled": "stenciled",
+  "stencilling": "stenciling",
+  "sterilisation": "sterilization",
+  "sterilisations": "sterilizations",
+  "sterilise": "sterilize",
+  "sterilised": "sterilized",
+  "steriliser": "sterilizer",
+  "sterilisers": "sterilizers",
+  "sterilises": "sterilizes",
+  "sterilising": "sterilizing",
+  "stigmatisation": "stigmatization",
+  "stigmatise": "stigmatize",
+  "stigmatised": "stigmatized",
+  "stigmatises": "stigmatizes",
+  "stigmatising": "stigmatizing",
+  "storey": "story",
+  "storeys": "stories",
+  "subsidisation": "subsidization",
+  "subsidise": "subsidize",
+  "subsidised": "subsidized",
+  "subsidiser": "subsidizer",
+  "subsidisers": "subsidizers",
+  "subsidises": "subsidizes",
+  "subsidising": "subsidizing",
+  "succour": "succor",
+  "succoured": "succored",
+  "succouring": "succoring",
+  "succours": "succors",
+  "sulphate": "sulfate",
+  "sulphates": "sulfates",
+  "sulphide": "sulfide",
+  "sulphides": "sulfides",
+  "sulphur": "sulfur",
+  "sulphurous": "sulfurous",
+  "summarise": "summarize",
+  "summarised": "summarized",
+  "summarises": "summarizes",
+  "summarising": "summarizing",
+  "swivelled": "swiveled",
+  "swivelling": "swiveling",
+  "symbolise": "symbolize",
+  "symbolised": "symbolized",
+  "symbolises": "symbolizes",
+  "symbolising": "symbolizing",
+  "sympathise": "sympathize",
+  "sympathised": "sympathized",
+  "sympathiser": "sympathizer",
+  "sympathisers": "sympathizers",
+  "sympathises": "sympathizes",
+  "sympathising": "sympathizing",
+  "synchronisation": "synchronization",
+  "synchronise": "synchronize",
+  "synchronised": "synchronized",
+  "synchronises": "synchronizes",
+  "synchronising": "synchronizing",
+  "synthesise": "synthesize",
+  "synthesised": "synthesized",
+  "synthesiser": "synthesizer",
+  "synthesisers": "synthesizers",
+  "synthesises": "synthesizes",
+  "synthesising": "synthesizing",
+  "syphon": "siphon",
+  "syphoned": "siphoned",
+  "syphoning": "siphoning",
+  "syphons": "siphons",
+  "systematisation": "systematization",
+  "systematise": "systematize",
+  "systematised": "systematized",
+  "systematises": "systematizes",
+  "systematising": "systematizing",
+  "tantalise": "tantalize",
+  "tantalised": "tantalized",
+  "tantalises": "tantalizes",
+  "tantalising": "tantalizing",
+  "tantalisingly": "tantalizingly",
+  "tasselled": "tasseled",
+  "technicolour": "technicolor",
+  "temporise": "temporize",
+  "temporised": "temporized",
+  "temporises": "temporizes",
+  "temporising": "temporizing",
+  "tenderise": "tenderize",
+  "tenderised": "tenderized",
+  "tenderises": "tenderizes",
+  "tenderising": "tenderizing",
+  "terrorise": "terrorize",
+  "terrorised": "terrorized",
+  "terrorises": "terrorizes",
+  "terrorising": "terrorizing",
+  "theatre": "theater",
+  "theatregoer": "theatergoer",
+  "theatregoers": "theatergoers",
+  "theatres": "theaters",
+  "theorise": "theorize",
+  "theorised": "theorized",
+  "theorises": "theorizes",
+  "theorising": "theorizing",
+  "tonne": "ton",
+  "tonnes": "tons",
+  "towelled": "toweled",
+  "towelling": "toweling",
+  "toxaemia": "toxemia",
+  "tranquillise": "tranquilize",
+  "tranquillised": "tranquilized",
+  "tranquilliser": "tranquilizer",
+  "tranquillisers": "tranquilizers",
+  "tranquillises": "tranquilizes",
+  "tranquillising": "tranquilizing",
+  "tranquillity": "tranquility",
+  "tranquillize": "tranquilize",
+  "tranquillized": "tranquilized",
+  "tranquillizer": "tranquilizer",
+  "tranquillizers": "tranquilizers",
+  "tranquillizes": "tranquilizes",
+  "tranquillizing": "tranquilizing",
+  "tranquilly": "tranquility",
+  "transistorised": "transistorized",
+  "traumatise": "traumatize",
+  "traumatised": "traumatized",
+  "traumatises": "traumatizes",
+  "traumatising": "traumatizing",
+  "travelled": "traveled",
+  "traveller": "traveler",
+  "travellers": "travelers",
+  "travelling": "traveling",
+  "travelog": "travelogue",
+  "travelogs": "travelogues",
+  "trialled": "trialed",
+  "trialling": "trialing",
+  "tricolour": "tricolor",
+  "tricolours": "tricolors",
+  "trivialise": "trivialize",
+  "trivialised": "trivialized",
+  "trivialises": "trivializes",
+  "trivialising": "trivializing",
+  "tumour": "tumor",
+  "tumours": "tumors",
+  "tunnelled": "tunneled",
+  "tunnelling": "tunneling",
+  "tyrannise": "tyrannize",
+  "tyrannised": "tyrannized",
+  "tyrannises": "tyrannizes",
+  "tyrannising": "tyrannizing",
+  "tyre": "tire",
+  "tyres": "tires",
+  "unauthorised": "unauthorized",
+  "uncivilised": "uncivilized",
+  "underutilised": "underutilized",
+  "unequalled": "unequaled",
+  "unfavourable": "unfavorable",
+  "unfavourably": "unfavorably",
+  "unionisation": "unionization",
+  "unionise": "unionize",
+  "unionised": "unionized",
+  "unionises": "unionizes",
+  "unionising": "unionizing",
+  "unorganised": "unorganized",
+  "unravelled": "unraveled",
+  "unravelling": "unraveling",
+  "unrecognisable": "unrecognizable",
+  "unrecognised": "unrecognized",
+  "unrivalled": "unrivaled",
+  "unsavoury": "unsavory",
+  "untrammelled": "untrammeled",
+  "urbanisation": "urbanization",
+  "urbanise": "urbanize",
+  "urbanised": "urbanized",
+  "urbanises": "urbanizes",
+  "urbanising": "urbanizing",
+  "utilisable": "utilizable",
+  "utilisation": "utilization",
+  "utilise": "utilize",
+  "utilised": "utilized",
+  "utilises": "utilizes",
+  "utilising": "utilizing",
+  "valour": "valor",
+  "vandalise": "vandalize",
+  "vandalised": "vandalized",
+  "vandalises": "vandalizes",
+  "vandalising": "vandalizing",
+  "vaporisation": "vaporization",
+  "vaporise": "vaporize",
+  "vaporised": "vaporized",
+  "vaporises": "vaporizes",
+  "vaporising": "vaporizing",
+  "vapour": "vapor",
+  "vapours": "vapors",
+  "verbalise": "verbalize",
+  "verbalised": "verbalized",
+  "verbalises": "verbalizes",
+  "verbalising": "verbalizing",
+  "victimisation": "victimization",
+  "victimise": "victimize",
+  "victimised": "victimized",
+  "victimises": "victimizes",
+  "victimising": "victimizing",
+  "videodisc": "videodisk",
+  "videodiscs": "videodisks",
+  "vigour": "vigor",
+  "visualisation": "visualization",
+  "visualisations": "visualizations",
+  "visualise": "visualize",
+  "visualised": "visualized",
+  "visualises": "visualizes",
+  "visualising": "visualizing",
+  "vocalisation": "vocalization",
+  "vocalisations": "vocalizations",
+  "vocalise": "vocalize",
+  "vocalised": "vocalized",
+  "vocalises": "vocalizes",
+  "vocalising": "vocalizing",
+  "vulcanised": "vulcanized",
+  "vulgarisation": "vulgarization",
+  "vulgarise": "vulgarize",
+  "vulgarised": "vulgarized",
+  "vulgarises": "vulgarizes",
+  "vulgarising": "vulgarizing",
+  "waggon": "wagon",
+  "waggons": "wagons",
+  "watercolour": "watercolor",
+  "watercolours": "watercolors",
+  "weaselled": "weaseled",
+  "weaselling": "weaseling",
+  "westernisation": "westernization",
+  "westernise": "westernize",
+  "westernised": "westernized",
+  "westernises": "westernizes",
+  "westernising": "westernizing",
+  "womanise": "womanize",
+  "womanised": "womanized",
+  "womaniser": "womanizer",
+  "womanisers": "womanizers",
+  "womanises": "womanizes",
+  "womanising": "womanizing",
+  "woollen": "woolen",
+  "woollens": "woolens",
+  "woollies": "woolies",
+  "woolly": "wooly",
+  "worshipped": "worshiped",
+  "worshipper": "worshiper",
+  "worshipping": "worshiping",
+  "yodelled": "yodeled",
+  "yodelling": "yodeling",
+  "yoghourt": "yogurt",
+  "yoghourts": "yogurts",
+  "yoghurt": "yogurt",
+  "yoghurts": "yogurts"
+}

preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/Mar02_20-05-18_e8b3d67d0624/events.out.tfevents.1772481938.e8b3d67d0624.553480.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ddff40952f3e463272eace1b1e37247328eee7ddedbd3649507c7441e3f1b0
+size 142666

special_tokens_map.json

@@ -0,0 +1,139 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|he|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 2.368016360865792e+20,
+    "train_loss": 0.13068210890056783,
+    "train_runtime": 7851.6825,
+    "train_samples_per_second": 104.595,
+    "train_steps_per_second": 0.817
+}