Training in progress, step 1000, checkpoint

Browse files

Files changed (15) hide show

last-checkpoint/added_tokens.json +1509 -1507
last-checkpoint/config.json +4 -4
last-checkpoint/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
last-checkpoint/global_step1000/mp_rank_00_model_states.pt +3 -0
last-checkpoint/latest +1 -0
last-checkpoint/model.safetensors +2 -2
last-checkpoint/preprocessor_config.json +1 -1
last-checkpoint/rng_state.pth +1 -1
last-checkpoint/scheduler.pt +1 -1
last-checkpoint/special_tokens_map.json +2 -2
last-checkpoint/tokenizer_config.json +0 -0
last-checkpoint/trainer_state.json +175 -2785
last-checkpoint/training_args.bin +2 -2
last-checkpoint/vocab.json +0 -1
last-checkpoint/zero_to_fp32.py +760 -0

last-checkpoint/added_tokens.json CHANGED Viewed

@@ -1,1505 +1,1505 @@
 {
-  "<|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,
@@ -1518,6 +1518,7 @@
   "<|da|>": 50285,
   "<|de|>": 50261,
   "<|el|>": 50281,
   "<|en|>": 50259,
   "<|es|>": 50262,
   "<|et|>": 50307,
@@ -1564,8 +1565,8 @@
   "<|ne|>": 50313,
   "<|nl|>": 50271,
   "<|nn|>": 50342,
-  "<|nocaptions|>": 50362,
-  "<|notimestamps|>": 50363,
   "<|no|>": 50288,
   "<|oc|>": 50328,
   "<|pa|>": 50321,
@@ -1583,8 +1584,8 @@
   "<|so|>": 50326,
   "<|sq|>": 50317,
   "<|sr|>": 50303,
-  "<|startoflm|>": 50360,
-  "<|startofprev|>": 50361,
   "<|startoftranscript|>": 50258,
   "<|su|>": 50357,
   "<|sv|>": 50273,
@@ -1595,8 +1596,8 @@
   "<|th|>": 50289,
   "<|tk|>": 50341,
   "<|tl|>": 50348,
-  "<|transcribe|>": 50359,
-  "<|translate|>": 50358,
   "<|tr|>": 50268,
   "<|tt|>": 50351,
   "<|uk|>": 50280,
@@ -1605,5 +1606,6 @@
   "<|vi|>": 50278,
   "<|yi|>": 50335,
   "<|yo|>": 50325,
   "<|zh|>": 50260
 }

 {
+  "<|0.00|>": 50365,
+  "<|0.02|>": 50366,
+  "<|0.04|>": 50367,
+  "<|0.06|>": 50368,
+  "<|0.08|>": 50369,
+  "<|0.10|>": 50370,
+  "<|0.12|>": 50371,
+  "<|0.14|>": 50372,
+  "<|0.16|>": 50373,
+  "<|0.18|>": 50374,
+  "<|0.20|>": 50375,
+  "<|0.22|>": 50376,
+  "<|0.24|>": 50377,
+  "<|0.26|>": 50378,
+  "<|0.28|>": 50379,
+  "<|0.30|>": 50380,
+  "<|0.32|>": 50381,
+  "<|0.34|>": 50382,
+  "<|0.36|>": 50383,
+  "<|0.38|>": 50384,
+  "<|0.40|>": 50385,
+  "<|0.42|>": 50386,
+  "<|0.44|>": 50387,
+  "<|0.46|>": 50388,
+  "<|0.48|>": 50389,
+  "<|0.50|>": 50390,
+  "<|0.52|>": 50391,
+  "<|0.54|>": 50392,
+  "<|0.56|>": 50393,
+  "<|0.58|>": 50394,
+  "<|0.60|>": 50395,
+  "<|0.62|>": 50396,
+  "<|0.64|>": 50397,
+  "<|0.66|>": 50398,
+  "<|0.68|>": 50399,
+  "<|0.70|>": 50400,
+  "<|0.72|>": 50401,
+  "<|0.74|>": 50402,
+  "<|0.76|>": 50403,
+  "<|0.78|>": 50404,
+  "<|0.80|>": 50405,
+  "<|0.82|>": 50406,
+  "<|0.84|>": 50407,
+  "<|0.86|>": 50408,
+  "<|0.88|>": 50409,
+  "<|0.90|>": 50410,
+  "<|0.92|>": 50411,
+  "<|0.94|>": 50412,
+  "<|0.96|>": 50413,
+  "<|0.98|>": 50414,
+  "<|1.00|>": 50415,
+  "<|1.02|>": 50416,
+  "<|1.04|>": 50417,
+  "<|1.06|>": 50418,
+  "<|1.08|>": 50419,
+  "<|1.10|>": 50420,
+  "<|1.12|>": 50421,
+  "<|1.14|>": 50422,
+  "<|1.16|>": 50423,
+  "<|1.18|>": 50424,
+  "<|1.20|>": 50425,
+  "<|1.22|>": 50426,
+  "<|1.24|>": 50427,
+  "<|1.26|>": 50428,
+  "<|1.28|>": 50429,
+  "<|1.30|>": 50430,
+  "<|1.32|>": 50431,
+  "<|1.34|>": 50432,
+  "<|1.36|>": 50433,
+  "<|1.38|>": 50434,
+  "<|1.40|>": 50435,
+  "<|1.42|>": 50436,
+  "<|1.44|>": 50437,
+  "<|1.46|>": 50438,
+  "<|1.48|>": 50439,
+  "<|1.50|>": 50440,
+  "<|1.52|>": 50441,
+  "<|1.54|>": 50442,
+  "<|1.56|>": 50443,
+  "<|1.58|>": 50444,
+  "<|1.60|>": 50445,
+  "<|1.62|>": 50446,
+  "<|1.64|>": 50447,
+  "<|1.66|>": 50448,
+  "<|1.68|>": 50449,
+  "<|1.70|>": 50450,
+  "<|1.72|>": 50451,
+  "<|1.74|>": 50452,
+  "<|1.76|>": 50453,
+  "<|1.78|>": 50454,
+  "<|1.80|>": 50455,
+  "<|1.82|>": 50456,
+  "<|1.84|>": 50457,
+  "<|1.86|>": 50458,
+  "<|1.88|>": 50459,
+  "<|1.90|>": 50460,
+  "<|1.92|>": 50461,
+  "<|1.94|>": 50462,
+  "<|1.96|>": 50463,
+  "<|1.98|>": 50464,
+  "<|10.00|>": 50865,
+  "<|10.02|>": 50866,
+  "<|10.04|>": 50867,
+  "<|10.06|>": 50868,
+  "<|10.08|>": 50869,
+  "<|10.10|>": 50870,
+  "<|10.12|>": 50871,
+  "<|10.14|>": 50872,
+  "<|10.16|>": 50873,
+  "<|10.18|>": 50874,
+  "<|10.20|>": 50875,
+  "<|10.22|>": 50876,
+  "<|10.24|>": 50877,
+  "<|10.26|>": 50878,
+  "<|10.28|>": 50879,
+  "<|10.30|>": 50880,
+  "<|10.32|>": 50881,
+  "<|10.34|>": 50882,
+  "<|10.36|>": 50883,
+  "<|10.38|>": 50884,
+  "<|10.40|>": 50885,
+  "<|10.42|>": 50886,
+  "<|10.44|>": 50887,
+  "<|10.46|>": 50888,
+  "<|10.48|>": 50889,
+  "<|10.50|>": 50890,
+  "<|10.52|>": 50891,
+  "<|10.54|>": 50892,
+  "<|10.56|>": 50893,
+  "<|10.58|>": 50894,
+  "<|10.60|>": 50895,
+  "<|10.62|>": 50896,
+  "<|10.64|>": 50897,
+  "<|10.66|>": 50898,
+  "<|10.68|>": 50899,
+  "<|10.70|>": 50900,
+  "<|10.72|>": 50901,
+  "<|10.74|>": 50902,
+  "<|10.76|>": 50903,
+  "<|10.78|>": 50904,
+  "<|10.80|>": 50905,
+  "<|10.82|>": 50906,
+  "<|10.84|>": 50907,
+  "<|10.86|>": 50908,
+  "<|10.88|>": 50909,
+  "<|10.90|>": 50910,
+  "<|10.92|>": 50911,
+  "<|10.94|>": 50912,
+  "<|10.96|>": 50913,
+  "<|10.98|>": 50914,
+  "<|11.00|>": 50915,
+  "<|11.02|>": 50916,
+  "<|11.04|>": 50917,
+  "<|11.06|>": 50918,
+  "<|11.08|>": 50919,
+  "<|11.10|>": 50920,
+  "<|11.12|>": 50921,
+  "<|11.14|>": 50922,
+  "<|11.16|>": 50923,
+  "<|11.18|>": 50924,
+  "<|11.20|>": 50925,
+  "<|11.22|>": 50926,
+  "<|11.24|>": 50927,
+  "<|11.26|>": 50928,
+  "<|11.28|>": 50929,
+  "<|11.30|>": 50930,
+  "<|11.32|>": 50931,
+  "<|11.34|>": 50932,
+  "<|11.36|>": 50933,
+  "<|11.38|>": 50934,
+  "<|11.40|>": 50935,
+  "<|11.42|>": 50936,
+  "<|11.44|>": 50937,
+  "<|11.46|>": 50938,
+  "<|11.48|>": 50939,
+  "<|11.50|>": 50940,
+  "<|11.52|>": 50941,
+  "<|11.54|>": 50942,
+  "<|11.56|>": 50943,
+  "<|11.58|>": 50944,
+  "<|11.60|>": 50945,
+  "<|11.62|>": 50946,
+  "<|11.64|>": 50947,
+  "<|11.66|>": 50948,
+  "<|11.68|>": 50949,
+  "<|11.70|>": 50950,
+  "<|11.72|>": 50951,
+  "<|11.74|>": 50952,
+  "<|11.76|>": 50953,
+  "<|11.78|>": 50954,
+  "<|11.80|>": 50955,
+  "<|11.82|>": 50956,
+  "<|11.84|>": 50957,
+  "<|11.86|>": 50958,
+  "<|11.88|>": 50959,
+  "<|11.90|>": 50960,
+  "<|11.92|>": 50961,
+  "<|11.94|>": 50962,
+  "<|11.96|>": 50963,
+  "<|11.98|>": 50964,
+  "<|12.00|>": 50965,
+  "<|12.02|>": 50966,
+  "<|12.04|>": 50967,
+  "<|12.06|>": 50968,
+  "<|12.08|>": 50969,
+  "<|12.10|>": 50970,
+  "<|12.12|>": 50971,
+  "<|12.14|>": 50972,
+  "<|12.16|>": 50973,
+  "<|12.18|>": 50974,
+  "<|12.20|>": 50975,
+  "<|12.22|>": 50976,
+  "<|12.24|>": 50977,
+  "<|12.26|>": 50978,
+  "<|12.28|>": 50979,
+  "<|12.30|>": 50980,
+  "<|12.32|>": 50981,
+  "<|12.34|>": 50982,
+  "<|12.36|>": 50983,
+  "<|12.38|>": 50984,
+  "<|12.40|>": 50985,
+  "<|12.42|>": 50986,
+  "<|12.44|>": 50987,
+  "<|12.46|>": 50988,
+  "<|12.48|>": 50989,
+  "<|12.50|>": 50990,
+  "<|12.52|>": 50991,
+  "<|12.54|>": 50992,
+  "<|12.56|>": 50993,
+  "<|12.58|>": 50994,
+  "<|12.60|>": 50995,
+  "<|12.62|>": 50996,
+  "<|12.64|>": 50997,
+  "<|12.66|>": 50998,
+  "<|12.68|>": 50999,
+  "<|12.70|>": 51000,
+  "<|12.72|>": 51001,
+  "<|12.74|>": 51002,
+  "<|12.76|>": 51003,
+  "<|12.78|>": 51004,
+  "<|12.80|>": 51005,
+  "<|12.82|>": 51006,
+  "<|12.84|>": 51007,
+  "<|12.86|>": 51008,
+  "<|12.88|>": 51009,
+  "<|12.90|>": 51010,
+  "<|12.92|>": 51011,
+  "<|12.94|>": 51012,
+  "<|12.96|>": 51013,
+  "<|12.98|>": 51014,
+  "<|13.00|>": 51015,
+  "<|13.02|>": 51016,
+  "<|13.04|>": 51017,
+  "<|13.06|>": 51018,
+  "<|13.08|>": 51019,
+  "<|13.10|>": 51020,
+  "<|13.12|>": 51021,
+  "<|13.14|>": 51022,
+  "<|13.16|>": 51023,
+  "<|13.18|>": 51024,
+  "<|13.20|>": 51025,
+  "<|13.22|>": 51026,
+  "<|13.24|>": 51027,
+  "<|13.26|>": 51028,
+  "<|13.28|>": 51029,
+  "<|13.30|>": 51030,
+  "<|13.32|>": 51031,
+  "<|13.34|>": 51032,
+  "<|13.36|>": 51033,
+  "<|13.38|>": 51034,
+  "<|13.40|>": 51035,
+  "<|13.42|>": 51036,
+  "<|13.44|>": 51037,
+  "<|13.46|>": 51038,
+  "<|13.48|>": 51039,
+  "<|13.50|>": 51040,
+  "<|13.52|>": 51041,
+  "<|13.54|>": 51042,
+  "<|13.56|>": 51043,
+  "<|13.58|>": 51044,
+  "<|13.60|>": 51045,
+  "<|13.62|>": 51046,
+  "<|13.64|>": 51047,
+  "<|13.66|>": 51048,
+  "<|13.68|>": 51049,
+  "<|13.70|>": 51050,
+  "<|13.72|>": 51051,
+  "<|13.74|>": 51052,
+  "<|13.76|>": 51053,
+  "<|13.78|>": 51054,
+  "<|13.80|>": 51055,
+  "<|13.82|>": 51056,
+  "<|13.84|>": 51057,
+  "<|13.86|>": 51058,
+  "<|13.88|>": 51059,
+  "<|13.90|>": 51060,
+  "<|13.92|>": 51061,
+  "<|13.94|>": 51062,
+  "<|13.96|>": 51063,
+  "<|13.98|>": 51064,
+  "<|14.00|>": 51065,
+  "<|14.02|>": 51066,
+  "<|14.04|>": 51067,
+  "<|14.06|>": 51068,
+  "<|14.08|>": 51069,
+  "<|14.10|>": 51070,
+  "<|14.12|>": 51071,
+  "<|14.14|>": 51072,
+  "<|14.16|>": 51073,
+  "<|14.18|>": 51074,
+  "<|14.20|>": 51075,
+  "<|14.22|>": 51076,
+  "<|14.24|>": 51077,
+  "<|14.26|>": 51078,
+  "<|14.28|>": 51079,
+  "<|14.30|>": 51080,
+  "<|14.32|>": 51081,
+  "<|14.34|>": 51082,
+  "<|14.36|>": 51083,
+  "<|14.38|>": 51084,
+  "<|14.40|>": 51085,
+  "<|14.42|>": 51086,
+  "<|14.44|>": 51087,
+  "<|14.46|>": 51088,
+  "<|14.48|>": 51089,
+  "<|14.50|>": 51090,
+  "<|14.52|>": 51091,
+  "<|14.54|>": 51092,
+  "<|14.56|>": 51093,
+  "<|14.58|>": 51094,
+  "<|14.60|>": 51095,
+  "<|14.62|>": 51096,
+  "<|14.64|>": 51097,
+  "<|14.66|>": 51098,
+  "<|14.68|>": 51099,
+  "<|14.70|>": 51100,
+  "<|14.72|>": 51101,
+  "<|14.74|>": 51102,
+  "<|14.76|>": 51103,
+  "<|14.78|>": 51104,
+  "<|14.80|>": 51105,
+  "<|14.82|>": 51106,
+  "<|14.84|>": 51107,
+  "<|14.86|>": 51108,
+  "<|14.88|>": 51109,
+  "<|14.90|>": 51110,
+  "<|14.92|>": 51111,
+  "<|14.94|>": 51112,
+  "<|14.96|>": 51113,
+  "<|14.98|>": 51114,
+  "<|15.00|>": 51115,
+  "<|15.02|>": 51116,
+  "<|15.04|>": 51117,
+  "<|15.06|>": 51118,
+  "<|15.08|>": 51119,
+  "<|15.10|>": 51120,
+  "<|15.12|>": 51121,
+  "<|15.14|>": 51122,
+  "<|15.16|>": 51123,
+  "<|15.18|>": 51124,
+  "<|15.20|>": 51125,
+  "<|15.22|>": 51126,
+  "<|15.24|>": 51127,
+  "<|15.26|>": 51128,
+  "<|15.28|>": 51129,
+  "<|15.30|>": 51130,
+  "<|15.32|>": 51131,
+  "<|15.34|>": 51132,
+  "<|15.36|>": 51133,
+  "<|15.38|>": 51134,
+  "<|15.40|>": 51135,
+  "<|15.42|>": 51136,
+  "<|15.44|>": 51137,
+  "<|15.46|>": 51138,
+  "<|15.48|>": 51139,
+  "<|15.50|>": 51140,
+  "<|15.52|>": 51141,
+  "<|15.54|>": 51142,
+  "<|15.56|>": 51143,
+  "<|15.58|>": 51144,
+  "<|15.60|>": 51145,
+  "<|15.62|>": 51146,
+  "<|15.64|>": 51147,
+  "<|15.66|>": 51148,
+  "<|15.68|>": 51149,
+  "<|15.70|>": 51150,
+  "<|15.72|>": 51151,
+  "<|15.74|>": 51152,
+  "<|15.76|>": 51153,
+  "<|15.78|>": 51154,
+  "<|15.80|>": 51155,
+  "<|15.82|>": 51156,
+  "<|15.84|>": 51157,
+  "<|15.86|>": 51158,
+  "<|15.88|>": 51159,
+  "<|15.90|>": 51160,
+  "<|15.92|>": 51161,
+  "<|15.94|>": 51162,
+  "<|15.96|>": 51163,
+  "<|15.98|>": 51164,
+  "<|16.00|>": 51165,
+  "<|16.02|>": 51166,
+  "<|16.04|>": 51167,
+  "<|16.06|>": 51168,
+  "<|16.08|>": 51169,
+  "<|16.10|>": 51170,
+  "<|16.12|>": 51171,
+  "<|16.14|>": 51172,
+  "<|16.16|>": 51173,
+  "<|16.18|>": 51174,
+  "<|16.20|>": 51175,
+  "<|16.22|>": 51176,
+  "<|16.24|>": 51177,
+  "<|16.26|>": 51178,
+  "<|16.28|>": 51179,
+  "<|16.30|>": 51180,
+  "<|16.32|>": 51181,
+  "<|16.34|>": 51182,
+  "<|16.36|>": 51183,
+  "<|16.38|>": 51184,
+  "<|16.40|>": 51185,
+  "<|16.42|>": 51186,
+  "<|16.44|>": 51187,
+  "<|16.46|>": 51188,
+  "<|16.48|>": 51189,
+  "<|16.50|>": 51190,
+  "<|16.52|>": 51191,
+  "<|16.54|>": 51192,
+  "<|16.56|>": 51193,
+  "<|16.58|>": 51194,
+  "<|16.60|>": 51195,
+  "<|16.62|>": 51196,
+  "<|16.64|>": 51197,
+  "<|16.66|>": 51198,
+  "<|16.68|>": 51199,
+  "<|16.70|>": 51200,
+  "<|16.72|>": 51201,
+  "<|16.74|>": 51202,
+  "<|16.76|>": 51203,
+  "<|16.78|>": 51204,
+  "<|16.80|>": 51205,
+  "<|16.82|>": 51206,
+  "<|16.84|>": 51207,
+  "<|16.86|>": 51208,
+  "<|16.88|>": 51209,
+  "<|16.90|>": 51210,
+  "<|16.92|>": 51211,
+  "<|16.94|>": 51212,
+  "<|16.96|>": 51213,
+  "<|16.98|>": 51214,
+  "<|17.00|>": 51215,
+  "<|17.02|>": 51216,
+  "<|17.04|>": 51217,
+  "<|17.06|>": 51218,
+  "<|17.08|>": 51219,
+  "<|17.10|>": 51220,
+  "<|17.12|>": 51221,
+  "<|17.14|>": 51222,
+  "<|17.16|>": 51223,
+  "<|17.18|>": 51224,
+  "<|17.20|>": 51225,
+  "<|17.22|>": 51226,
+  "<|17.24|>": 51227,
+  "<|17.26|>": 51228,
+  "<|17.28|>": 51229,
+  "<|17.30|>": 51230,
+  "<|17.32|>": 51231,
+  "<|17.34|>": 51232,
+  "<|17.36|>": 51233,
+  "<|17.38|>": 51234,
+  "<|17.40|>": 51235,
+  "<|17.42|>": 51236,
+  "<|17.44|>": 51237,
+  "<|17.46|>": 51238,
+  "<|17.48|>": 51239,
+  "<|17.50|>": 51240,
+  "<|17.52|>": 51241,
+  "<|17.54|>": 51242,
+  "<|17.56|>": 51243,
+  "<|17.58|>": 51244,
+  "<|17.60|>": 51245,
+  "<|17.62|>": 51246,
+  "<|17.64|>": 51247,
+  "<|17.66|>": 51248,
+  "<|17.68|>": 51249,
+  "<|17.70|>": 51250,
+  "<|17.72|>": 51251,
+  "<|17.74|>": 51252,
+  "<|17.76|>": 51253,
+  "<|17.78|>": 51254,
+  "<|17.80|>": 51255,
+  "<|17.82|>": 51256,
+  "<|17.84|>": 51257,
+  "<|17.86|>": 51258,
+  "<|17.88|>": 51259,
+  "<|17.90|>": 51260,
+  "<|17.92|>": 51261,
+  "<|17.94|>": 51262,
+  "<|17.96|>": 51263,
+  "<|17.98|>": 51264,
+  "<|18.00|>": 51265,
+  "<|18.02|>": 51266,
+  "<|18.04|>": 51267,
+  "<|18.06|>": 51268,
+  "<|18.08|>": 51269,
+  "<|18.10|>": 51270,
+  "<|18.12|>": 51271,
+  "<|18.14|>": 51272,
+  "<|18.16|>": 51273,
+  "<|18.18|>": 51274,
+  "<|18.20|>": 51275,
+  "<|18.22|>": 51276,
+  "<|18.24|>": 51277,
+  "<|18.26|>": 51278,
+  "<|18.28|>": 51279,
+  "<|18.30|>": 51280,
+  "<|18.32|>": 51281,
+  "<|18.34|>": 51282,
+  "<|18.36|>": 51283,
+  "<|18.38|>": 51284,
+  "<|18.40|>": 51285,
+  "<|18.42|>": 51286,
+  "<|18.44|>": 51287,
+  "<|18.46|>": 51288,
+  "<|18.48|>": 51289,
+  "<|18.50|>": 51290,
+  "<|18.52|>": 51291,
+  "<|18.54|>": 51292,
+  "<|18.56|>": 51293,
+  "<|18.58|>": 51294,
+  "<|18.60|>": 51295,
+  "<|18.62|>": 51296,
+  "<|18.64|>": 51297,
+  "<|18.66|>": 51298,
+  "<|18.68|>": 51299,
+  "<|18.70|>": 51300,
+  "<|18.72|>": 51301,
+  "<|18.74|>": 51302,
+  "<|18.76|>": 51303,
+  "<|18.78|>": 51304,
+  "<|18.80|>": 51305,
+  "<|18.82|>": 51306,
+  "<|18.84|>": 51307,
+  "<|18.86|>": 51308,
+  "<|18.88|>": 51309,
+  "<|18.90|>": 51310,
+  "<|18.92|>": 51311,
+  "<|18.94|>": 51312,
+  "<|18.96|>": 51313,
+  "<|18.98|>": 51314,
+  "<|19.00|>": 51315,
+  "<|19.02|>": 51316,
+  "<|19.04|>": 51317,
+  "<|19.06|>": 51318,
+  "<|19.08|>": 51319,
+  "<|19.10|>": 51320,
+  "<|19.12|>": 51321,
+  "<|19.14|>": 51322,
+  "<|19.16|>": 51323,
+  "<|19.18|>": 51324,
+  "<|19.20|>": 51325,
+  "<|19.22|>": 51326,
+  "<|19.24|>": 51327,
+  "<|19.26|>": 51328,
+  "<|19.28|>": 51329,
+  "<|19.30|>": 51330,
+  "<|19.32|>": 51331,
+  "<|19.34|>": 51332,
+  "<|19.36|>": 51333,
+  "<|19.38|>": 51334,
+  "<|19.40|>": 51335,
+  "<|19.42|>": 51336,
+  "<|19.44|>": 51337,
+  "<|19.46|>": 51338,
+  "<|19.48|>": 51339,
+  "<|19.50|>": 51340,
+  "<|19.52|>": 51341,
+  "<|19.54|>": 51342,
+  "<|19.56|>": 51343,
+  "<|19.58|>": 51344,
+  "<|19.60|>": 51345,
+  "<|19.62|>": 51346,
+  "<|19.64|>": 51347,
+  "<|19.66|>": 51348,
+  "<|19.68|>": 51349,
+  "<|19.70|>": 51350,
+  "<|19.72|>": 51351,
+  "<|19.74|>": 51352,
+  "<|19.76|>": 51353,
+  "<|19.78|>": 51354,
+  "<|19.80|>": 51355,
+  "<|19.82|>": 51356,
+  "<|19.84|>": 51357,
+  "<|19.86|>": 51358,
+  "<|19.88|>": 51359,
+  "<|19.90|>": 51360,
+  "<|19.92|>": 51361,
+  "<|19.94|>": 51362,
+  "<|19.96|>": 51363,
+  "<|19.98|>": 51364,
+  "<|2.00|>": 50465,
+  "<|2.02|>": 50466,
+  "<|2.04|>": 50467,
+  "<|2.06|>": 50468,
+  "<|2.08|>": 50469,
+  "<|2.10|>": 50470,
+  "<|2.12|>": 50471,
+  "<|2.14|>": 50472,
+  "<|2.16|>": 50473,
+  "<|2.18|>": 50474,
+  "<|2.20|>": 50475,
+  "<|2.22|>": 50476,
+  "<|2.24|>": 50477,
+  "<|2.26|>": 50478,
+  "<|2.28|>": 50479,
+  "<|2.30|>": 50480,
+  "<|2.32|>": 50481,
+  "<|2.34|>": 50482,
+  "<|2.36|>": 50483,
+  "<|2.38|>": 50484,
+  "<|2.40|>": 50485,
+  "<|2.42|>": 50486,
+  "<|2.44|>": 50487,
+  "<|2.46|>": 50488,
+  "<|2.48|>": 50489,
+  "<|2.50|>": 50490,
+  "<|2.52|>": 50491,
+  "<|2.54|>": 50492,
+  "<|2.56|>": 50493,
+  "<|2.58|>": 50494,
+  "<|2.60|>": 50495,
+  "<|2.62|>": 50496,
+  "<|2.64|>": 50497,
+  "<|2.66|>": 50498,
+  "<|2.68|>": 50499,
+  "<|2.70|>": 50500,
+  "<|2.72|>": 50501,
+  "<|2.74|>": 50502,
+  "<|2.76|>": 50503,
+  "<|2.78|>": 50504,
+  "<|2.80|>": 50505,
+  "<|2.82|>": 50506,
+  "<|2.84|>": 50507,
+  "<|2.86|>": 50508,
+  "<|2.88|>": 50509,
+  "<|2.90|>": 50510,
+  "<|2.92|>": 50511,
+  "<|2.94|>": 50512,
+  "<|2.96|>": 50513,
+  "<|2.98|>": 50514,
+  "<|20.00|>": 51365,
+  "<|20.02|>": 51366,
+  "<|20.04|>": 51367,
+  "<|20.06|>": 51368,
+  "<|20.08|>": 51369,
+  "<|20.10|>": 51370,
+  "<|20.12|>": 51371,
+  "<|20.14|>": 51372,
+  "<|20.16|>": 51373,
+  "<|20.18|>": 51374,
+  "<|20.20|>": 51375,
+  "<|20.22|>": 51376,
+  "<|20.24|>": 51377,
+  "<|20.26|>": 51378,
+  "<|20.28|>": 51379,
+  "<|20.30|>": 51380,
+  "<|20.32|>": 51381,
+  "<|20.34|>": 51382,
+  "<|20.36|>": 51383,
+  "<|20.38|>": 51384,
+  "<|20.40|>": 51385,
+  "<|20.42|>": 51386,
+  "<|20.44|>": 51387,
+  "<|20.46|>": 51388,
+  "<|20.48|>": 51389,
+  "<|20.50|>": 51390,
+  "<|20.52|>": 51391,
+  "<|20.54|>": 51392,
+  "<|20.56|>": 51393,
+  "<|20.58|>": 51394,
+  "<|20.60|>": 51395,
+  "<|20.62|>": 51396,
+  "<|20.64|>": 51397,
+  "<|20.66|>": 51398,
+  "<|20.68|>": 51399,
+  "<|20.70|>": 51400,
+  "<|20.72|>": 51401,
+  "<|20.74|>": 51402,
+  "<|20.76|>": 51403,
+  "<|20.78|>": 51404,
+  "<|20.80|>": 51405,
+  "<|20.82|>": 51406,
+  "<|20.84|>": 51407,
+  "<|20.86|>": 51408,
+  "<|20.88|>": 51409,
+  "<|20.90|>": 51410,
+  "<|20.92|>": 51411,
+  "<|20.94|>": 51412,
+  "<|20.96|>": 51413,
+  "<|20.98|>": 51414,
+  "<|21.00|>": 51415,
+  "<|21.02|>": 51416,
+  "<|21.04|>": 51417,
+  "<|21.06|>": 51418,
+  "<|21.08|>": 51419,
+  "<|21.10|>": 51420,
+  "<|21.12|>": 51421,
+  "<|21.14|>": 51422,
+  "<|21.16|>": 51423,
+  "<|21.18|>": 51424,
+  "<|21.20|>": 51425,
+  "<|21.22|>": 51426,
+  "<|21.24|>": 51427,
+  "<|21.26|>": 51428,
+  "<|21.28|>": 51429,
+  "<|21.30|>": 51430,
+  "<|21.32|>": 51431,
+  "<|21.34|>": 51432,
+  "<|21.36|>": 51433,
+  "<|21.38|>": 51434,
+  "<|21.40|>": 51435,
+  "<|21.42|>": 51436,
+  "<|21.44|>": 51437,
+  "<|21.46|>": 51438,
+  "<|21.48|>": 51439,
+  "<|21.50|>": 51440,
+  "<|21.52|>": 51441,
+  "<|21.54|>": 51442,
+  "<|21.56|>": 51443,
+  "<|21.58|>": 51444,
+  "<|21.60|>": 51445,
+  "<|21.62|>": 51446,
+  "<|21.64|>": 51447,
+  "<|21.66|>": 51448,
+  "<|21.68|>": 51449,
+  "<|21.70|>": 51450,
+  "<|21.72|>": 51451,
+  "<|21.74|>": 51452,
+  "<|21.76|>": 51453,
+  "<|21.78|>": 51454,
+  "<|21.80|>": 51455,
+  "<|21.82|>": 51456,
+  "<|21.84|>": 51457,
+  "<|21.86|>": 51458,
+  "<|21.88|>": 51459,
+  "<|21.90|>": 51460,
+  "<|21.92|>": 51461,
+  "<|21.94|>": 51462,
+  "<|21.96|>": 51463,
+  "<|21.98|>": 51464,
+  "<|22.00|>": 51465,
+  "<|22.02|>": 51466,
+  "<|22.04|>": 51467,
+  "<|22.06|>": 51468,
+  "<|22.08|>": 51469,
+  "<|22.10|>": 51470,
+  "<|22.12|>": 51471,
+  "<|22.14|>": 51472,
+  "<|22.16|>": 51473,
+  "<|22.18|>": 51474,
+  "<|22.20|>": 51475,
+  "<|22.22|>": 51476,
+  "<|22.24|>": 51477,
+  "<|22.26|>": 51478,
+  "<|22.28|>": 51479,
+  "<|22.30|>": 51480,
+  "<|22.32|>": 51481,
+  "<|22.34|>": 51482,
+  "<|22.36|>": 51483,
+  "<|22.38|>": 51484,
+  "<|22.40|>": 51485,
+  "<|22.42|>": 51486,
+  "<|22.44|>": 51487,
+  "<|22.46|>": 51488,
+  "<|22.48|>": 51489,
+  "<|22.50|>": 51490,
+  "<|22.52|>": 51491,
+  "<|22.54|>": 51492,
+  "<|22.56|>": 51493,
+  "<|22.58|>": 51494,
+  "<|22.60|>": 51495,
+  "<|22.62|>": 51496,
+  "<|22.64|>": 51497,
+  "<|22.66|>": 51498,
+  "<|22.68|>": 51499,
+  "<|22.70|>": 51500,
+  "<|22.72|>": 51501,
+  "<|22.74|>": 51502,
+  "<|22.76|>": 51503,
+  "<|22.78|>": 51504,
+  "<|22.80|>": 51505,
+  "<|22.82|>": 51506,
+  "<|22.84|>": 51507,
+  "<|22.86|>": 51508,
+  "<|22.88|>": 51509,
+  "<|22.90|>": 51510,
+  "<|22.92|>": 51511,
+  "<|22.94|>": 51512,
+  "<|22.96|>": 51513,
+  "<|22.98|>": 51514,
+  "<|23.00|>": 51515,
+  "<|23.02|>": 51516,
+  "<|23.04|>": 51517,
+  "<|23.06|>": 51518,
+  "<|23.08|>": 51519,
+  "<|23.10|>": 51520,
+  "<|23.12|>": 51521,
+  "<|23.14|>": 51522,
+  "<|23.16|>": 51523,
+  "<|23.18|>": 51524,
+  "<|23.20|>": 51525,
+  "<|23.22|>": 51526,
+  "<|23.24|>": 51527,
+  "<|23.26|>": 51528,
+  "<|23.28|>": 51529,
+  "<|23.30|>": 51530,
+  "<|23.32|>": 51531,
+  "<|23.34|>": 51532,
+  "<|23.36|>": 51533,
+  "<|23.38|>": 51534,
+  "<|23.40|>": 51535,
+  "<|23.42|>": 51536,
+  "<|23.44|>": 51537,
+  "<|23.46|>": 51538,
+  "<|23.48|>": 51539,
+  "<|23.50|>": 51540,
+  "<|23.52|>": 51541,
+  "<|23.54|>": 51542,
+  "<|23.56|>": 51543,
+  "<|23.58|>": 51544,
+  "<|23.60|>": 51545,
+  "<|23.62|>": 51546,
+  "<|23.64|>": 51547,
+  "<|23.66|>": 51548,
+  "<|23.68|>": 51549,
+  "<|23.70|>": 51550,
+  "<|23.72|>": 51551,
+  "<|23.74|>": 51552,
+  "<|23.76|>": 51553,
+  "<|23.78|>": 51554,
+  "<|23.80|>": 51555,
+  "<|23.82|>": 51556,
+  "<|23.84|>": 51557,
+  "<|23.86|>": 51558,
+  "<|23.88|>": 51559,
+  "<|23.90|>": 51560,
+  "<|23.92|>": 51561,
+  "<|23.94|>": 51562,
+  "<|23.96|>": 51563,
+  "<|23.98|>": 51564,
+  "<|24.00|>": 51565,
+  "<|24.02|>": 51566,
+  "<|24.04|>": 51567,
+  "<|24.06|>": 51568,
+  "<|24.08|>": 51569,
+  "<|24.10|>": 51570,
+  "<|24.12|>": 51571,
+  "<|24.14|>": 51572,
+  "<|24.16|>": 51573,
+  "<|24.18|>": 51574,
+  "<|24.20|>": 51575,
+  "<|24.22|>": 51576,
+  "<|24.24|>": 51577,
+  "<|24.26|>": 51578,
+  "<|24.28|>": 51579,
+  "<|24.30|>": 51580,
+  "<|24.32|>": 51581,
+  "<|24.34|>": 51582,
+  "<|24.36|>": 51583,
+  "<|24.38|>": 51584,
+  "<|24.40|>": 51585,
+  "<|24.42|>": 51586,
+  "<|24.44|>": 51587,
+  "<|24.46|>": 51588,
+  "<|24.48|>": 51589,
+  "<|24.50|>": 51590,
+  "<|24.52|>": 51591,
+  "<|24.54|>": 51592,
+  "<|24.56|>": 51593,
+  "<|24.58|>": 51594,
+  "<|24.60|>": 51595,
+  "<|24.62|>": 51596,
+  "<|24.64|>": 51597,
+  "<|24.66|>": 51598,
+  "<|24.68|>": 51599,
+  "<|24.70|>": 51600,
+  "<|24.72|>": 51601,
+  "<|24.74|>": 51602,
+  "<|24.76|>": 51603,
+  "<|24.78|>": 51604,
+  "<|24.80|>": 51605,
+  "<|24.82|>": 51606,
+  "<|24.84|>": 51607,
+  "<|24.86|>": 51608,
+  "<|24.88|>": 51609,
+  "<|24.90|>": 51610,
+  "<|24.92|>": 51611,
+  "<|24.94|>": 51612,
+  "<|24.96|>": 51613,
+  "<|24.98|>": 51614,
+  "<|25.00|>": 51615,
+  "<|25.02|>": 51616,
+  "<|25.04|>": 51617,
+  "<|25.06|>": 51618,
+  "<|25.08|>": 51619,
+  "<|25.10|>": 51620,
+  "<|25.12|>": 51621,
+  "<|25.14|>": 51622,
+  "<|25.16|>": 51623,
+  "<|25.18|>": 51624,
+  "<|25.20|>": 51625,
+  "<|25.22|>": 51626,
+  "<|25.24|>": 51627,
+  "<|25.26|>": 51628,
+  "<|25.28|>": 51629,
+  "<|25.30|>": 51630,
+  "<|25.32|>": 51631,
+  "<|25.34|>": 51632,
+  "<|25.36|>": 51633,
+  "<|25.38|>": 51634,
+  "<|25.40|>": 51635,
+  "<|25.42|>": 51636,
+  "<|25.44|>": 51637,
+  "<|25.46|>": 51638,
+  "<|25.48|>": 51639,
+  "<|25.50|>": 51640,
+  "<|25.52|>": 51641,
+  "<|25.54|>": 51642,
+  "<|25.56|>": 51643,
+  "<|25.58|>": 51644,
+  "<|25.60|>": 51645,
+  "<|25.62|>": 51646,
+  "<|25.64|>": 51647,
+  "<|25.66|>": 51648,
+  "<|25.68|>": 51649,
+  "<|25.70|>": 51650,
+  "<|25.72|>": 51651,
+  "<|25.74|>": 51652,
+  "<|25.76|>": 51653,
+  "<|25.78|>": 51654,
+  "<|25.80|>": 51655,
+  "<|25.82|>": 51656,
+  "<|25.84|>": 51657,
+  "<|25.86|>": 51658,
+  "<|25.88|>": 51659,
+  "<|25.90|>": 51660,
+  "<|25.92|>": 51661,
+  "<|25.94|>": 51662,
+  "<|25.96|>": 51663,
+  "<|25.98|>": 51664,
+  "<|26.00|>": 51665,
+  "<|26.02|>": 51666,
+  "<|26.04|>": 51667,
+  "<|26.06|>": 51668,
+  "<|26.08|>": 51669,
+  "<|26.10|>": 51670,
+  "<|26.12|>": 51671,
+  "<|26.14|>": 51672,
+  "<|26.16|>": 51673,
+  "<|26.18|>": 51674,
+  "<|26.20|>": 51675,
+  "<|26.22|>": 51676,
+  "<|26.24|>": 51677,
+  "<|26.26|>": 51678,
+  "<|26.28|>": 51679,
+  "<|26.30|>": 51680,
+  "<|26.32|>": 51681,
+  "<|26.34|>": 51682,
+  "<|26.36|>": 51683,
+  "<|26.38|>": 51684,
+  "<|26.40|>": 51685,
+  "<|26.42|>": 51686,
+  "<|26.44|>": 51687,
+  "<|26.46|>": 51688,
+  "<|26.48|>": 51689,
+  "<|26.50|>": 51690,
+  "<|26.52|>": 51691,
+  "<|26.54|>": 51692,
+  "<|26.56|>": 51693,
+  "<|26.58|>": 51694,
+  "<|26.60|>": 51695,
+  "<|26.62|>": 51696,
+  "<|26.64|>": 51697,
+  "<|26.66|>": 51698,
+  "<|26.68|>": 51699,
+  "<|26.70|>": 51700,
+  "<|26.72|>": 51701,
+  "<|26.74|>": 51702,
+  "<|26.76|>": 51703,
+  "<|26.78|>": 51704,
+  "<|26.80|>": 51705,
+  "<|26.82|>": 51706,
+  "<|26.84|>": 51707,
+  "<|26.86|>": 51708,
+  "<|26.88|>": 51709,
+  "<|26.90|>": 51710,
+  "<|26.92|>": 51711,
+  "<|26.94|>": 51712,
+  "<|26.96|>": 51713,
+  "<|26.98|>": 51714,
+  "<|27.00|>": 51715,
+  "<|27.02|>": 51716,
+  "<|27.04|>": 51717,
+  "<|27.06|>": 51718,
+  "<|27.08|>": 51719,
+  "<|27.10|>": 51720,
+  "<|27.12|>": 51721,
+  "<|27.14|>": 51722,
+  "<|27.16|>": 51723,
+  "<|27.18|>": 51724,
+  "<|27.20|>": 51725,
+  "<|27.22|>": 51726,
+  "<|27.24|>": 51727,
+  "<|27.26|>": 51728,
+  "<|27.28|>": 51729,
+  "<|27.30|>": 51730,
+  "<|27.32|>": 51731,
+  "<|27.34|>": 51732,
+  "<|27.36|>": 51733,
+  "<|27.38|>": 51734,
+  "<|27.40|>": 51735,
+  "<|27.42|>": 51736,
+  "<|27.44|>": 51737,
+  "<|27.46|>": 51738,
+  "<|27.48|>": 51739,
+  "<|27.50|>": 51740,
+  "<|27.52|>": 51741,
+  "<|27.54|>": 51742,
+  "<|27.56|>": 51743,
+  "<|27.58|>": 51744,
+  "<|27.60|>": 51745,
+  "<|27.62|>": 51746,
+  "<|27.64|>": 51747,
+  "<|27.66|>": 51748,
+  "<|27.68|>": 51749,
+  "<|27.70|>": 51750,
+  "<|27.72|>": 51751,
+  "<|27.74|>": 51752,
+  "<|27.76|>": 51753,
+  "<|27.78|>": 51754,
+  "<|27.80|>": 51755,
+  "<|27.82|>": 51756,
+  "<|27.84|>": 51757,
+  "<|27.86|>": 51758,
+  "<|27.88|>": 51759,
+  "<|27.90|>": 51760,
+  "<|27.92|>": 51761,
+  "<|27.94|>": 51762,
+  "<|27.96|>": 51763,
+  "<|27.98|>": 51764,
+  "<|28.00|>": 51765,
+  "<|28.02|>": 51766,
+  "<|28.04|>": 51767,
+  "<|28.06|>": 51768,
+  "<|28.08|>": 51769,
+  "<|28.10|>": 51770,
+  "<|28.12|>": 51771,
+  "<|28.14|>": 51772,
+  "<|28.16|>": 51773,
+  "<|28.18|>": 51774,
+  "<|28.20|>": 51775,
+  "<|28.22|>": 51776,
+  "<|28.24|>": 51777,
+  "<|28.26|>": 51778,
+  "<|28.28|>": 51779,
+  "<|28.30|>": 51780,
+  "<|28.32|>": 51781,
+  "<|28.34|>": 51782,
+  "<|28.36|>": 51783,
+  "<|28.38|>": 51784,
+  "<|28.40|>": 51785,
+  "<|28.42|>": 51786,
+  "<|28.44|>": 51787,
+  "<|28.46|>": 51788,
+  "<|28.48|>": 51789,
+  "<|28.50|>": 51790,
+  "<|28.52|>": 51791,
+  "<|28.54|>": 51792,
+  "<|28.56|>": 51793,
+  "<|28.58|>": 51794,
+  "<|28.60|>": 51795,
+  "<|28.62|>": 51796,
+  "<|28.64|>": 51797,
+  "<|28.66|>": 51798,
+  "<|28.68|>": 51799,
+  "<|28.70|>": 51800,
+  "<|28.72|>": 51801,
+  "<|28.74|>": 51802,
+  "<|28.76|>": 51803,
+  "<|28.78|>": 51804,
+  "<|28.80|>": 51805,
+  "<|28.82|>": 51806,
+  "<|28.84|>": 51807,
+  "<|28.86|>": 51808,
+  "<|28.88|>": 51809,
+  "<|28.90|>": 51810,
+  "<|28.92|>": 51811,
+  "<|28.94|>": 51812,
+  "<|28.96|>": 51813,
+  "<|28.98|>": 51814,
+  "<|29.00|>": 51815,
+  "<|29.02|>": 51816,
+  "<|29.04|>": 51817,
+  "<|29.06|>": 51818,
+  "<|29.08|>": 51819,
+  "<|29.10|>": 51820,
+  "<|29.12|>": 51821,
+  "<|29.14|>": 51822,
+  "<|29.16|>": 51823,
+  "<|29.18|>": 51824,
+  "<|29.20|>": 51825,
+  "<|29.22|>": 51826,
+  "<|29.24|>": 51827,
+  "<|29.26|>": 51828,
+  "<|29.28|>": 51829,
+  "<|29.30|>": 51830,
+  "<|29.32|>": 51831,
+  "<|29.34|>": 51832,
+  "<|29.36|>": 51833,
+  "<|29.38|>": 51834,
+  "<|29.40|>": 51835,
+  "<|29.42|>": 51836,
+  "<|29.44|>": 51837,
+  "<|29.46|>": 51838,
+  "<|29.48|>": 51839,
+  "<|29.50|>": 51840,
+  "<|29.52|>": 51841,
+  "<|29.54|>": 51842,
+  "<|29.56|>": 51843,
+  "<|29.58|>": 51844,
+  "<|29.60|>": 51845,
+  "<|29.62|>": 51846,
+  "<|29.64|>": 51847,
+  "<|29.66|>": 51848,
+  "<|29.68|>": 51849,
+  "<|29.70|>": 51850,
+  "<|29.72|>": 51851,
+  "<|29.74|>": 51852,
+  "<|29.76|>": 51853,
+  "<|29.78|>": 51854,
+  "<|29.80|>": 51855,
+  "<|29.82|>": 51856,
+  "<|29.84|>": 51857,
+  "<|29.86|>": 51858,
+  "<|29.88|>": 51859,
+  "<|29.90|>": 51860,
+  "<|29.92|>": 51861,
+  "<|29.94|>": 51862,
+  "<|29.96|>": 51863,
+  "<|29.98|>": 51864,
+  "<|3.00|>": 50515,
+  "<|3.02|>": 50516,
+  "<|3.04|>": 50517,
+  "<|3.06|>": 50518,
+  "<|3.08|>": 50519,
+  "<|3.10|>": 50520,
+  "<|3.12|>": 50521,
+  "<|3.14|>": 50522,
+  "<|3.16|>": 50523,
+  "<|3.18|>": 50524,
+  "<|3.20|>": 50525,
+  "<|3.22|>": 50526,
+  "<|3.24|>": 50527,
+  "<|3.26|>": 50528,
+  "<|3.28|>": 50529,
+  "<|3.30|>": 50530,
+  "<|3.32|>": 50531,
+  "<|3.34|>": 50532,
+  "<|3.36|>": 50533,
+  "<|3.38|>": 50534,
+  "<|3.40|>": 50535,
+  "<|3.42|>": 50536,
+  "<|3.44|>": 50537,
+  "<|3.46|>": 50538,
+  "<|3.48|>": 50539,
+  "<|3.50|>": 50540,
+  "<|3.52|>": 50541,
+  "<|3.54|>": 50542,
+  "<|3.56|>": 50543,
+  "<|3.58|>": 50544,
+  "<|3.60|>": 50545,
+  "<|3.62|>": 50546,
+  "<|3.64|>": 50547,
+  "<|3.66|>": 50548,
+  "<|3.68|>": 50549,
+  "<|3.70|>": 50550,
+  "<|3.72|>": 50551,
+  "<|3.74|>": 50552,
+  "<|3.76|>": 50553,
+  "<|3.78|>": 50554,
+  "<|3.80|>": 50555,
+  "<|3.82|>": 50556,
+  "<|3.84|>": 50557,
+  "<|3.86|>": 50558,
+  "<|3.88|>": 50559,
+  "<|3.90|>": 50560,
+  "<|3.92|>": 50561,
+  "<|3.94|>": 50562,
+  "<|3.96|>": 50563,
+  "<|3.98|>": 50564,
+  "<|30.00|>": 51865,
+  "<|4.00|>": 50565,
+  "<|4.02|>": 50566,
+  "<|4.04|>": 50567,
+  "<|4.06|>": 50568,
+  "<|4.08|>": 50569,
+  "<|4.10|>": 50570,
+  "<|4.12|>": 50571,
+  "<|4.14|>": 50572,
+  "<|4.16|>": 50573,
+  "<|4.18|>": 50574,
+  "<|4.20|>": 50575,
+  "<|4.22|>": 50576,
+  "<|4.24|>": 50577,
+  "<|4.26|>": 50578,
+  "<|4.28|>": 50579,
+  "<|4.30|>": 50580,
+  "<|4.32|>": 50581,
+  "<|4.34|>": 50582,
+  "<|4.36|>": 50583,
+  "<|4.38|>": 50584,
+  "<|4.40|>": 50585,
+  "<|4.42|>": 50586,
+  "<|4.44|>": 50587,
+  "<|4.46|>": 50588,
+  "<|4.48|>": 50589,
+  "<|4.50|>": 50590,
+  "<|4.52|>": 50591,
+  "<|4.54|>": 50592,
+  "<|4.56|>": 50593,
+  "<|4.58|>": 50594,
+  "<|4.60|>": 50595,
+  "<|4.62|>": 50596,
+  "<|4.64|>": 50597,
+  "<|4.66|>": 50598,
+  "<|4.68|>": 50599,
+  "<|4.70|>": 50600,
+  "<|4.72|>": 50601,
+  "<|4.74|>": 50602,
+  "<|4.76|>": 50603,
+  "<|4.78|>": 50604,
+  "<|4.80|>": 50605,
+  "<|4.82|>": 50606,
+  "<|4.84|>": 50607,
+  "<|4.86|>": 50608,
+  "<|4.88|>": 50609,
+  "<|4.90|>": 50610,
+  "<|4.92|>": 50611,
+  "<|4.94|>": 50612,
+  "<|4.96|>": 50613,
+  "<|4.98|>": 50614,
+  "<|5.00|>": 50615,
+  "<|5.02|>": 50616,
+  "<|5.04|>": 50617,
+  "<|5.06|>": 50618,
+  "<|5.08|>": 50619,
+  "<|5.10|>": 50620,
+  "<|5.12|>": 50621,
+  "<|5.14|>": 50622,
+  "<|5.16|>": 50623,
+  "<|5.18|>": 50624,
+  "<|5.20|>": 50625,
+  "<|5.22|>": 50626,
+  "<|5.24|>": 50627,
+  "<|5.26|>": 50628,
+  "<|5.28|>": 50629,
+  "<|5.30|>": 50630,
+  "<|5.32|>": 50631,
+  "<|5.34|>": 50632,
+  "<|5.36|>": 50633,
+  "<|5.38|>": 50634,
+  "<|5.40|>": 50635,
+  "<|5.42|>": 50636,
+  "<|5.44|>": 50637,
+  "<|5.46|>": 50638,
+  "<|5.48|>": 50639,
+  "<|5.50|>": 50640,
+  "<|5.52|>": 50641,
+  "<|5.54|>": 50642,
+  "<|5.56|>": 50643,
+  "<|5.58|>": 50644,
+  "<|5.60|>": 50645,
+  "<|5.62|>": 50646,
+  "<|5.64|>": 50647,
+  "<|5.66|>": 50648,
+  "<|5.68|>": 50649,
+  "<|5.70|>": 50650,
+  "<|5.72|>": 50651,
+  "<|5.74|>": 50652,
+  "<|5.76|>": 50653,
+  "<|5.78|>": 50654,
+  "<|5.80|>": 50655,
+  "<|5.82|>": 50656,
+  "<|5.84|>": 50657,
+  "<|5.86|>": 50658,
+  "<|5.88|>": 50659,
+  "<|5.90|>": 50660,
+  "<|5.92|>": 50661,
+  "<|5.94|>": 50662,
+  "<|5.96|>": 50663,
+  "<|5.98|>": 50664,
+  "<|6.00|>": 50665,
+  "<|6.02|>": 50666,
+  "<|6.04|>": 50667,
+  "<|6.06|>": 50668,
+  "<|6.08|>": 50669,
+  "<|6.10|>": 50670,
+  "<|6.12|>": 50671,
+  "<|6.14|>": 50672,
+  "<|6.16|>": 50673,
+  "<|6.18|>": 50674,
+  "<|6.20|>": 50675,
+  "<|6.22|>": 50676,
+  "<|6.24|>": 50677,
+  "<|6.26|>": 50678,
+  "<|6.28|>": 50679,
+  "<|6.30|>": 50680,
+  "<|6.32|>": 50681,
+  "<|6.34|>": 50682,
+  "<|6.36|>": 50683,
+  "<|6.38|>": 50684,
+  "<|6.40|>": 50685,
+  "<|6.42|>": 50686,
+  "<|6.44|>": 50687,
+  "<|6.46|>": 50688,
+  "<|6.48|>": 50689,
+  "<|6.50|>": 50690,
+  "<|6.52|>": 50691,
+  "<|6.54|>": 50692,
+  "<|6.56|>": 50693,
+  "<|6.58|>": 50694,
+  "<|6.60|>": 50695,
+  "<|6.62|>": 50696,
+  "<|6.64|>": 50697,
+  "<|6.66|>": 50698,
+  "<|6.68|>": 50699,
+  "<|6.70|>": 50700,
+  "<|6.72|>": 50701,
+  "<|6.74|>": 50702,
+  "<|6.76|>": 50703,
+  "<|6.78|>": 50704,
+  "<|6.80|>": 50705,
+  "<|6.82|>": 50706,
+  "<|6.84|>": 50707,
+  "<|6.86|>": 50708,
+  "<|6.88|>": 50709,
+  "<|6.90|>": 50710,
+  "<|6.92|>": 50711,
+  "<|6.94|>": 50712,
+  "<|6.96|>": 50713,
+  "<|6.98|>": 50714,
+  "<|7.00|>": 50715,
+  "<|7.02|>": 50716,
+  "<|7.04|>": 50717,
+  "<|7.06|>": 50718,
+  "<|7.08|>": 50719,
+  "<|7.10|>": 50720,
+  "<|7.12|>": 50721,
+  "<|7.14|>": 50722,
+  "<|7.16|>": 50723,
+  "<|7.18|>": 50724,
+  "<|7.20|>": 50725,
+  "<|7.22|>": 50726,
+  "<|7.24|>": 50727,
+  "<|7.26|>": 50728,
+  "<|7.28|>": 50729,
+  "<|7.30|>": 50730,
+  "<|7.32|>": 50731,
+  "<|7.34|>": 50732,
+  "<|7.36|>": 50733,
+  "<|7.38|>": 50734,
+  "<|7.40|>": 50735,
+  "<|7.42|>": 50736,
+  "<|7.44|>": 50737,
+  "<|7.46|>": 50738,
+  "<|7.48|>": 50739,
+  "<|7.50|>": 50740,
+  "<|7.52|>": 50741,
+  "<|7.54|>": 50742,
+  "<|7.56|>": 50743,
+  "<|7.58|>": 50744,
+  "<|7.60|>": 50745,
+  "<|7.62|>": 50746,
+  "<|7.64|>": 50747,
+  "<|7.66|>": 50748,
+  "<|7.68|>": 50749,
+  "<|7.70|>": 50750,
+  "<|7.72|>": 50751,
+  "<|7.74|>": 50752,
+  "<|7.76|>": 50753,
+  "<|7.78|>": 50754,
+  "<|7.80|>": 50755,
+  "<|7.82|>": 50756,
+  "<|7.84|>": 50757,
+  "<|7.86|>": 50758,
+  "<|7.88|>": 50759,
+  "<|7.90|>": 50760,
+  "<|7.92|>": 50761,
+  "<|7.94|>": 50762,
+  "<|7.96|>": 50763,
+  "<|7.98|>": 50764,
+  "<|8.00|>": 50765,
+  "<|8.02|>": 50766,
+  "<|8.04|>": 50767,
+  "<|8.06|>": 50768,
+  "<|8.08|>": 50769,
+  "<|8.10|>": 50770,
+  "<|8.12|>": 50771,
+  "<|8.14|>": 50772,
+  "<|8.16|>": 50773,
+  "<|8.18|>": 50774,
+  "<|8.20|>": 50775,
+  "<|8.22|>": 50776,
+  "<|8.24|>": 50777,
+  "<|8.26|>": 50778,
+  "<|8.28|>": 50779,
+  "<|8.30|>": 50780,
+  "<|8.32|>": 50781,
+  "<|8.34|>": 50782,
+  "<|8.36|>": 50783,
+  "<|8.38|>": 50784,
+  "<|8.40|>": 50785,
+  "<|8.42|>": 50786,
+  "<|8.44|>": 50787,
+  "<|8.46|>": 50788,
+  "<|8.48|>": 50789,
+  "<|8.50|>": 50790,
+  "<|8.52|>": 50791,
+  "<|8.54|>": 50792,
+  "<|8.56|>": 50793,
+  "<|8.58|>": 50794,
+  "<|8.60|>": 50795,
+  "<|8.62|>": 50796,
+  "<|8.64|>": 50797,
+  "<|8.66|>": 50798,
+  "<|8.68|>": 50799,
+  "<|8.70|>": 50800,
+  "<|8.72|>": 50801,
+  "<|8.74|>": 50802,
+  "<|8.76|>": 50803,
+  "<|8.78|>": 50804,
+  "<|8.80|>": 50805,
+  "<|8.82|>": 50806,
+  "<|8.84|>": 50807,
+  "<|8.86|>": 50808,
+  "<|8.88|>": 50809,
+  "<|8.90|>": 50810,
+  "<|8.92|>": 50811,
+  "<|8.94|>": 50812,
+  "<|8.96|>": 50813,
+  "<|8.98|>": 50814,
+  "<|9.00|>": 50815,
+  "<|9.02|>": 50816,
+  "<|9.04|>": 50817,
+  "<|9.06|>": 50818,
+  "<|9.08|>": 50819,
+  "<|9.10|>": 50820,
+  "<|9.12|>": 50821,
+  "<|9.14|>": 50822,
+  "<|9.16|>": 50823,
+  "<|9.18|>": 50824,
+  "<|9.20|>": 50825,
+  "<|9.22|>": 50826,
+  "<|9.24|>": 50827,
+  "<|9.26|>": 50828,
+  "<|9.28|>": 50829,
+  "<|9.30|>": 50830,
+  "<|9.32|>": 50831,
+  "<|9.34|>": 50832,
+  "<|9.36|>": 50833,
+  "<|9.38|>": 50834,
+  "<|9.40|>": 50835,
+  "<|9.42|>": 50836,
+  "<|9.44|>": 50837,
+  "<|9.46|>": 50838,
+  "<|9.48|>": 50839,
+  "<|9.50|>": 50840,
+  "<|9.52|>": 50841,
+  "<|9.54|>": 50842,
+  "<|9.56|>": 50843,
+  "<|9.58|>": 50844,
+  "<|9.60|>": 50845,
+  "<|9.62|>": 50846,
+  "<|9.64|>": 50847,
+  "<|9.66|>": 50848,
+  "<|9.68|>": 50849,
+  "<|9.70|>": 50850,
+  "<|9.72|>": 50851,
+  "<|9.74|>": 50852,
+  "<|9.76|>": 50853,
+  "<|9.78|>": 50854,
+  "<|9.80|>": 50855,
+  "<|9.82|>": 50856,
+  "<|9.84|>": 50857,
+  "<|9.86|>": 50858,
+  "<|9.88|>": 50859,
+  "<|9.90|>": 50860,
+  "<|9.92|>": 50861,
+  "<|9.94|>": 50862,
+  "<|9.96|>": 50863,
+  "<|9.98|>": 50864,
   "<|af|>": 50327,
   "<|am|>": 50334,
   "<|ar|>": 50272,
   "<|da|>": 50285,
   "<|de|>": 50261,
   "<|el|>": 50281,
+  "<|endoftext|>": 50257,
   "<|en|>": 50259,
   "<|es|>": 50262,
   "<|et|>": 50307,
   "<|ne|>": 50313,
   "<|nl|>": 50271,
   "<|nn|>": 50342,
+  "<|nospeech|>": 50363,
+  "<|notimestamps|>": 50364,
   "<|no|>": 50288,
   "<|oc|>": 50328,
   "<|pa|>": 50321,
   "<|so|>": 50326,
   "<|sq|>": 50317,
   "<|sr|>": 50303,
+  "<|startoflm|>": 50361,
+  "<|startofprev|>": 50362,
   "<|startoftranscript|>": 50258,
   "<|su|>": 50357,
   "<|sv|>": 50273,
   "<|th|>": 50289,
   "<|tk|>": 50341,
   "<|tl|>": 50348,
+  "<|transcribe|>": 50360,
+  "<|translate|>": 50359,
   "<|tr|>": 50268,
   "<|tt|>": 50351,
   "<|uk|>": 50280,
   "<|vi|>": 50278,
   "<|yi|>": 50335,
   "<|yo|>": 50325,
+  "<|yue|>": 50358,
   "<|zh|>": 50260
 }

last-checkpoint/config.json CHANGED Viewed

@@ -14,7 +14,7 @@
   "decoder_attention_heads": 8,
   "decoder_ffn_dim": 2048,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 2,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
   "encoder_attention_heads": 8,
@@ -29,11 +29,11 @@
     ],
     [
       2,
-      50359
     ],
     [
       3,
-      50363
     ]
   ],
   "init_std": 0.02,
@@ -53,7 +53,7 @@
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.48.3",
   "use_cache": true,
   "use_weighted_layer_sum": false,

   "decoder_attention_heads": 8,
   "decoder_ffn_dim": 2048,
   "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
   "encoder_attention_heads": 8,
     ],
     [
       2,
+      50360
     ],
     [
       3,
+      50364
     ]
   ],
   "init_std": 0.02,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.48.3",
   "use_cache": true,
   "use_weighted_layer_sum": false,

last-checkpoint/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ffed1c4b62e71b3ac467dd7d73441e3e9bcaf21927aa3a3a6b59ac5324ff663d
+size 761059696

last-checkpoint/global_step1000/mp_rank_00_model_states.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:05d0081bd55bbeb14fd8f3ea82f05c76379648353359ac1e17863ce23dcaedd4
+size 129965712

last-checkpoint/latest ADDED Viewed

	@@ -0,0 +1 @@


1	+ global_step1000

last-checkpoint/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1172332b4f4cf2ce6af9c26f710924116b9939c47b97977e6e6ac30b8704561
-size 223144592

 version https://git-lfs.github.com/spec/v1
+oid sha256:e8483c37faf3d85258253e75bc0440ac3555e32e5464cd4a298260f708bcc016
+size 181508256

last-checkpoint/preprocessor_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "chunk_length": 30,
   "feature_extractor_type": "WhisperFeatureExtractor",
-  "feature_size": 80,
   "hop_length": 160,
   "n_fft": 400,
   "n_samples": 480000,

 {
   "chunk_length": 30,
   "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
   "hop_length": 160,
   "n_fft": 400,
   "n_samples": 480000,

last-checkpoint/rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b83c8e2618548ad0a6cb55d5f9e419ee82c921eaf0cb178e6e4f4700b370bc6
 size 14244

 version https://git-lfs.github.com/spec/v1
+oid sha256:e0da2a816195a08312d7656fb111d92b08e16f2513648f66a8a00f69acac89b1
 size 14244

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6158b7f4e5c150fe6ade940825c51c282bf26d832e5e702ff0db258a477b79
 size 1064

 version https://git-lfs.github.com/spec/v1
+oid sha256:cbadae7a908ca2ec608dd3ceac8b5aab1986323a21358ba9a060e8f696f7e6fb
 size 1064

last-checkpoint/special_tokens_map.json CHANGED Viewed

@@ -1,6 +1,5 @@
 {
   "additional_special_tokens": [
-    "<|endoftext|>",
     "<|startoftranscript|>",
     "<|en|>",
     "<|zh|>",
@@ -101,11 +100,12 @@
     "<|ba|>",
     "<|jw|>",
     "<|su|>",
     "<|translate|>",
     "<|transcribe|>",
     "<|startoflm|>",
     "<|startofprev|>",
-    "<|nocaptions|>",
     "<|notimestamps|>"
   ],
   "bos_token": {

 {
   "additional_special_tokens": [
     "<|startoftranscript|>",
     "<|en|>",
     "<|zh|>",
     "<|ba|>",
     "<|jw|>",
     "<|su|>",
+    "<|yue|>",
     "<|translate|>",
     "<|transcribe|>",
     "<|startoflm|>",
     "<|startofprev|>",
+    "<|nospeech|>",
     "<|notimestamps|>"
   ],
   "bos_token": {

last-checkpoint/tokenizer_config.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -1,2918 +1,308 @@
 {
-  "best_metric": 95.4926921263555,
-  "best_model_checkpoint": "./iteboshi_temp/checkpoint-4000",
-  "epoch": 16.50206440957886,
   "eval_steps": 1000,
-  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.04128819157720892,
-      "grad_norm": 48.469512939453125,
       "learning_rate": 1.0000000000000002e-06,
-      "loss": 17.381,
       "step": 25
     },
     {
-      "epoch": 0.08257638315441784,
-      "grad_norm": 52.77425003051758,
-      "learning_rate": 1.9600000000000003e-06,
-      "loss": 15.9672,
       "step": 50
     },
     {
-      "epoch": 0.12386457473162675,
-      "grad_norm": 63.97101974487305,
-      "learning_rate": 2.96e-06,
-      "loss": 12.6578,
       "step": 75
     },
     {
-      "epoch": 0.16515276630883569,
-      "grad_norm": 26.345178604125977,
-      "learning_rate": 3.96e-06,
-      "loss": 8.2932,
       "step": 100
     },
     {
-      "epoch": 0.20644095788604458,
-      "grad_norm": 12.366632461547852,
-      "learning_rate": 4.960000000000001e-06,
-      "loss": 6.2485,
       "step": 125
     },
     {
-      "epoch": 0.2477291494632535,
-      "grad_norm": 9.131484985351562,
-      "learning_rate": 5.9600000000000005e-06,
-      "loss": 5.0845,
       "step": 150
     },
     {
-      "epoch": 0.28901734104046245,
-      "grad_norm": 8.288640975952148,
-      "learning_rate": 6.96e-06,
-      "loss": 4.5216,
       "step": 175
     },
     {
-      "epoch": 0.33030553261767137,
-      "grad_norm": 8.107129096984863,
-      "learning_rate": 7.960000000000002e-06,
-      "loss": 4.2152,
       "step": 200
     },
     {
-      "epoch": 0.37159372419488024,
-      "grad_norm": 8.564615249633789,
-      "learning_rate": 8.96e-06,
-      "loss": 4.095,
       "step": 225
     },
     {
-      "epoch": 0.41288191577208916,
-      "grad_norm": 8.67183780670166,
-      "learning_rate": 9.960000000000001e-06,
-      "loss": 3.9264,
       "step": 250
     },
     {
-      "epoch": 0.4541701073492981,
-      "grad_norm": 8.779706954956055,
-      "learning_rate": 1.0960000000000002e-05,
-      "loss": 3.7974,
       "step": 275
     },
     {
-      "epoch": 0.495458298926507,
-      "grad_norm": 8.62621021270752,
-      "learning_rate": 1.196e-05,
-      "loss": 3.7625,
       "step": 300
     },
     {
-      "epoch": 0.5367464905037159,
-      "grad_norm": 9.157522201538086,
-      "learning_rate": 1.2960000000000001e-05,
-      "loss": 3.6965,
       "step": 325
     },
     {
-      "epoch": 0.5780346820809249,
-      "grad_norm": 8.446877479553223,
-      "learning_rate": 1.396e-05,
-      "loss": 3.6216,
       "step": 350
     },
     {
-      "epoch": 0.6193228736581338,
-      "grad_norm": 8.873468399047852,
-      "learning_rate": 1.496e-05,
-      "loss": 3.5455,
       "step": 375
     },
     {
-      "epoch": 0.6606110652353427,
-      "grad_norm": 7.768847465515137,
-      "learning_rate": 1.5960000000000003e-05,
-      "loss": 3.4952,
       "step": 400
     },
     {
-      "epoch": 0.7018992568125516,
-      "grad_norm": 8.365340232849121,
-      "learning_rate": 1.696e-05,
-      "loss": 3.414,
       "step": 425
     },
     {
-      "epoch": 0.7431874483897605,
-      "grad_norm": 7.865358829498291,
-      "learning_rate": 1.796e-05,
-      "loss": 3.3472,
       "step": 450
     },
     {
-      "epoch": 0.7844756399669695,
-      "grad_norm": 8.56877613067627,
-      "learning_rate": 1.896e-05,
-      "loss": 3.3018,
       "step": 475
     },
     {
-      "epoch": 0.8257638315441783,
-      "grad_norm": 9.091480255126953,
-      "learning_rate": 1.9960000000000002e-05,
-      "loss": 3.255,
       "step": 500
     },
     {
-      "epoch": 0.8670520231213873,
-      "grad_norm": 8.974713325500488,
-      "learning_rate": 1.9949473684210527e-05,
-      "loss": 3.1519,
       "step": 525
     },
     {
-      "epoch": 0.9083402146985962,
-      "grad_norm": 9.134045600891113,
-      "learning_rate": 1.989684210526316e-05,
-      "loss": 3.0334,
       "step": 550
     },
     {
-      "epoch": 0.9496284062758051,
-      "grad_norm": 10.075201988220215,
-      "learning_rate": 1.984421052631579e-05,
-      "loss": 2.9656,
       "step": 575
     },
     {
-      "epoch": 0.990916597853014,
-      "grad_norm": 9.26815128326416,
-      "learning_rate": 1.9791578947368423e-05,
-      "loss": 2.8884,
       "step": 600
     },
     {
-      "epoch": 1.0313790255986788,
-      "grad_norm": 8.885565757751465,
-      "learning_rate": 1.9738947368421057e-05,
-      "loss": 2.7179,
       "step": 625
     },
     {
-      "epoch": 1.0726672171758878,
-      "grad_norm": 8.9259672164917,
-      "learning_rate": 1.9686315789473687e-05,
-      "loss": 2.6417,
       "step": 650
     },
     {
-      "epoch": 1.1139554087530965,
-      "grad_norm": 10.3223295211792,
-      "learning_rate": 1.9633684210526316e-05,
-      "loss": 2.5669,
       "step": 675
     },
     {
-      "epoch": 1.1552436003303055,
-      "grad_norm": 10.508142471313477,
-      "learning_rate": 1.958105263157895e-05,
-      "loss": 2.5026,
       "step": 700
     },
     {
-      "epoch": 1.1965317919075145,
-      "grad_norm": 9.78288745880127,
-      "learning_rate": 1.952842105263158e-05,
-      "loss": 2.3907,
       "step": 725
     },
     {
-      "epoch": 1.2378199834847234,
-      "grad_norm": 9.629091262817383,
-      "learning_rate": 1.9475789473684213e-05,
-      "loss": 2.3983,
       "step": 750
     },
     {
-      "epoch": 1.2791081750619324,
-      "grad_norm": 9.543179512023926,
-      "learning_rate": 1.9423157894736843e-05,
-      "loss": 2.283,
       "step": 775
     },
     {
-      "epoch": 1.3203963666391412,
-      "grad_norm": 9.676267623901367,
-      "learning_rate": 1.9370526315789476e-05,
-      "loss": 2.2519,
       "step": 800
     },
     {
-      "epoch": 1.3616845582163501,
-      "grad_norm": 9.192870140075684,
-      "learning_rate": 1.9317894736842106e-05,
-      "loss": 2.1516,
       "step": 825
     },
     {
-      "epoch": 1.402972749793559,
-      "grad_norm": 9.859146118164062,
-      "learning_rate": 1.926526315789474e-05,
-      "loss": 2.1643,
       "step": 850
     },
     {
-      "epoch": 1.4442609413707679,
-      "grad_norm": 9.815247535705566,
-      "learning_rate": 1.921263157894737e-05,
-      "loss": 2.0514,
       "step": 875
     },
     {
-      "epoch": 1.4855491329479769,
-      "grad_norm": 10.037995338439941,
-      "learning_rate": 1.916e-05,
-      "loss": 2.0867,
       "step": 900
     },
     {
-      "epoch": 1.5268373245251858,
-      "grad_norm": 9.680682182312012,
-      "learning_rate": 1.9107368421052633e-05,
-      "loss": 1.999,
       "step": 925
     },
     {
-      "epoch": 1.5681255161023948,
-      "grad_norm": 9.410001754760742,
-      "learning_rate": 1.9054736842105263e-05,
-      "loss": 1.954,
       "step": 950
     },
     {
-      "epoch": 1.6094137076796038,
-      "grad_norm": 8.89158821105957,
-      "learning_rate": 1.9002105263157896e-05,
-      "loss": 1.92,
       "step": 975
     },
     {
-      "epoch": 1.6507018992568125,
-      "grad_norm": 9.326930046081543,
-      "learning_rate": 1.894947368421053e-05,
-      "loss": 1.8339,
       "step": 1000
     },
     {
-      "epoch": 1.6507018992568125,
-      "eval_cer": 93.62053351369322,
-      "eval_loss": 1.911484956741333,
-      "eval_runtime": 801.8096,
-      "eval_samples_per_second": 13.196,
-      "eval_steps_per_second": 1.1,
-      "eval_wer": 99.67939651107967,
       "step": 1000
-    },
-    {
-      "epoch": 1.6919900908340215,
-      "grad_norm": 9.614924430847168,
-      "learning_rate": 1.889684210526316e-05,
-      "loss": 1.8351,
-      "step": 1025
-    },
-    {
-      "epoch": 1.7332782824112303,
-      "grad_norm": 9.912728309631348,
-      "learning_rate": 1.8844210526315793e-05,
-      "loss": 1.7924,
-      "step": 1050
-    },
-    {
-      "epoch": 1.7745664739884393,
-      "grad_norm": 9.571353912353516,
-      "learning_rate": 1.8791578947368423e-05,
-      "loss": 1.7655,
-      "step": 1075
-    },
-    {
-      "epoch": 1.8158546655656482,
-      "grad_norm": 9.284981727600098,
-      "learning_rate": 1.8738947368421056e-05,
-      "loss": 1.7737,
-      "step": 1100
-    },
-    {
-      "epoch": 1.8571428571428572,
-      "grad_norm": 10.073586463928223,
-      "learning_rate": 1.8686315789473686e-05,
-      "loss": 1.7343,
-      "step": 1125
-    },
-    {
-      "epoch": 1.8984310487200662,
-      "grad_norm": 8.913012504577637,
-      "learning_rate": 1.8633684210526316e-05,
-      "loss": 1.6881,
-      "step": 1150
-    },
-    {
-      "epoch": 1.939719240297275,
-      "grad_norm": 9.885432243347168,
-      "learning_rate": 1.858105263157895e-05,
-      "loss": 1.6909,
-      "step": 1175
-    },
-    {
-      "epoch": 1.981007431874484,
-      "grad_norm": 9.40440559387207,
-      "learning_rate": 1.852842105263158e-05,
-      "loss": 1.6276,
-      "step": 1200
-    },
-    {
-      "epoch": 2.0214698596201486,
-      "grad_norm": 10.476126670837402,
-      "learning_rate": 1.8475789473684212e-05,
-      "loss": 1.5264,
-      "step": 1225
-    },
-    {
-      "epoch": 2.0627580511973576,
-      "grad_norm": 8.929309844970703,
-      "learning_rate": 1.8423157894736842e-05,
-      "loss": 1.4139,
-      "step": 1250
-    },
-    {
-      "epoch": 2.1040462427745665,
-      "grad_norm": 9.487678527832031,
-      "learning_rate": 1.8370526315789476e-05,
-      "loss": 1.4765,
-      "step": 1275
-    },
-    {
-      "epoch": 2.1453344343517755,
-      "grad_norm": 9.428024291992188,
-      "learning_rate": 1.831789473684211e-05,
-      "loss": 1.4275,
-      "step": 1300
-    },
-    {
-      "epoch": 2.1866226259289845,
-      "grad_norm": 9.300884246826172,
-      "learning_rate": 1.826526315789474e-05,
-      "loss": 1.4115,
-      "step": 1325
-    },
-    {
-      "epoch": 2.227910817506193,
-      "grad_norm": 9.60734748840332,
-      "learning_rate": 1.821263157894737e-05,
-      "loss": 1.4087,
-      "step": 1350
-    },
-    {
-      "epoch": 2.269199009083402,
-      "grad_norm": 8.660606384277344,
-      "learning_rate": 1.8160000000000002e-05,
-      "loss": 1.3658,
-      "step": 1375
-    },
-    {
-      "epoch": 2.310487200660611,
-      "grad_norm": 9.169739723205566,
-      "learning_rate": 1.8107368421052632e-05,
-      "loss": 1.3645,
-      "step": 1400
-    },
-    {
-      "epoch": 2.35177539223782,
-      "grad_norm": 9.20264720916748,
-      "learning_rate": 1.8054736842105266e-05,
-      "loss": 1.328,
-      "step": 1425
-    },
-    {
-      "epoch": 2.393063583815029,
-      "grad_norm": 9.625157356262207,
-      "learning_rate": 1.8002105263157896e-05,
-      "loss": 1.3095,
-      "step": 1450
-    },
-    {
-      "epoch": 2.434351775392238,
-      "grad_norm": 8.743439674377441,
-      "learning_rate": 1.794947368421053e-05,
-      "loss": 1.3244,
-      "step": 1475
-    },
-    {
-      "epoch": 2.475639966969447,
-      "grad_norm": 9.378725051879883,
-      "learning_rate": 1.789684210526316e-05,
-      "loss": 1.2695,
-      "step": 1500
-    },
-    {
-      "epoch": 2.516928158546656,
-      "grad_norm": 9.474600791931152,
-      "learning_rate": 1.7844210526315792e-05,
-      "loss": 1.3238,
-      "step": 1525
-    },
-    {
-      "epoch": 2.558216350123865,
-      "grad_norm": 8.615851402282715,
-      "learning_rate": 1.7791578947368422e-05,
-      "loss": 1.2829,
-      "step": 1550
-    },
-    {
-      "epoch": 2.5995045417010734,
-      "grad_norm": 8.702414512634277,
-      "learning_rate": 1.7738947368421052e-05,
-      "loss": 1.2914,
-      "step": 1575
-    },
-    {
-      "epoch": 2.6407927332782823,
-      "grad_norm": 9.374676704406738,
-      "learning_rate": 1.7686315789473685e-05,
-      "loss": 1.2769,
-      "step": 1600
-    },
-    {
-      "epoch": 2.6820809248554913,
-      "grad_norm": 8.985688209533691,
-      "learning_rate": 1.7633684210526315e-05,
-      "loss": 1.25,
-      "step": 1625
-    },
-    {
-      "epoch": 2.7233691164327003,
-      "grad_norm": 8.864657402038574,
-      "learning_rate": 1.758105263157895e-05,
-      "loss": 1.2028,
-      "step": 1650
-    },
-    {
-      "epoch": 2.7646573080099093,
-      "grad_norm": 8.514275550842285,
-      "learning_rate": 1.7528421052631582e-05,
-      "loss": 1.2477,
-      "step": 1675
-    },
-    {
-      "epoch": 2.805945499587118,
-      "grad_norm": 9.147972106933594,
-      "learning_rate": 1.7475789473684212e-05,
-      "loss": 1.2103,
-      "step": 1700
-    },
-    {
-      "epoch": 2.847233691164327,
-      "grad_norm": 9.296348571777344,
-      "learning_rate": 1.7423157894736845e-05,
-      "loss": 1.2437,
-      "step": 1725
-    },
-    {
-      "epoch": 2.8885218827415358,
-      "grad_norm": 9.178862571716309,
-      "learning_rate": 1.7370526315789475e-05,
-      "loss": 1.1999,
-      "step": 1750
-    },
-    {
-      "epoch": 2.9298100743187447,
-      "grad_norm": 8.8689603805542,
-      "learning_rate": 1.731789473684211e-05,
-      "loss": 1.167,
-      "step": 1775
-    },
-    {
-      "epoch": 2.9710982658959537,
-      "grad_norm": 8.430618286132812,
-      "learning_rate": 1.726526315789474e-05,
-      "loss": 1.1616,
-      "step": 1800
-    },
-    {
-      "epoch": 3.0115606936416186,
-      "grad_norm": 8.175687789916992,
-      "learning_rate": 1.721263157894737e-05,
-      "loss": 1.1536,
-      "step": 1825
-    },
-    {
-      "epoch": 3.0528488852188276,
-      "grad_norm": 8.549736022949219,
-      "learning_rate": 1.7160000000000002e-05,
-      "loss": 1.0421,
-      "step": 1850
-    },
-    {
-      "epoch": 3.094137076796036,
-      "grad_norm": 8.512212753295898,
-      "learning_rate": 1.710736842105263e-05,
-      "loss": 1.0288,
-      "step": 1875
-    },
-    {
-      "epoch": 3.135425268373245,
-      "grad_norm": 7.529111385345459,
-      "learning_rate": 1.7054736842105265e-05,
-      "loss": 0.9965,
-      "step": 1900
-    },
-    {
-      "epoch": 3.176713459950454,
-      "grad_norm": 8.706369400024414,
-      "learning_rate": 1.7002105263157895e-05,
-      "loss": 1.0262,
-      "step": 1925
-    },
-    {
-      "epoch": 3.218001651527663,
-      "grad_norm": 8.718097686767578,
-      "learning_rate": 1.6949473684210528e-05,
-      "loss": 1.0232,
-      "step": 1950
-    },
-    {
-      "epoch": 3.259289843104872,
-      "grad_norm": 9.124544143676758,
-      "learning_rate": 1.689684210526316e-05,
-      "loss": 1.0104,
-      "step": 1975
-    },
-    {
-      "epoch": 3.300578034682081,
-      "grad_norm": 7.853435039520264,
-      "learning_rate": 1.684421052631579e-05,
-      "loss": 0.9948,
-      "step": 2000
-    },
-    {
-      "epoch": 3.300578034682081,
-      "eval_cer": 59.421319913335545,
-      "eval_loss": 1.2762852907180786,
-      "eval_runtime": 738.0908,
-      "eval_samples_per_second": 14.336,
-      "eval_steps_per_second": 1.195,
-      "eval_wer": 97.35030645921735,
-      "step": 2000
-    },
-    {
-      "epoch": 3.34186622625929,
-      "grad_norm": 7.776848793029785,
-      "learning_rate": 1.6791578947368425e-05,
-      "loss": 0.9834,
-      "step": 2025
-    },
-    {
-      "epoch": 3.383154417836499,
-      "grad_norm": 8.306714057922363,
-      "learning_rate": 1.6738947368421055e-05,
-      "loss": 1.0036,
-      "step": 2050
-    },
-    {
-      "epoch": 3.424442609413708,
-      "grad_norm": 9.474985122680664,
-      "learning_rate": 1.6686315789473685e-05,
-      "loss": 1.0534,
-      "step": 2075
-    },
-    {
-      "epoch": 3.4657308009909165,
-      "grad_norm": 7.486320972442627,
-      "learning_rate": 1.6633684210526318e-05,
-      "loss": 0.9673,
-      "step": 2100
-    },
-    {
-      "epoch": 3.5070189925681254,
-      "grad_norm": 8.373710632324219,
-      "learning_rate": 1.6581052631578948e-05,
-      "loss": 1.0009,
-      "step": 2125
-    },
-    {
-      "epoch": 3.5483071841453344,
-      "grad_norm": 8.073158264160156,
-      "learning_rate": 1.652842105263158e-05,
-      "loss": 1.0142,
-      "step": 2150
-    },
-    {
-      "epoch": 3.5895953757225434,
-      "grad_norm": 8.070113182067871,
-      "learning_rate": 1.647578947368421e-05,
-      "loss": 0.9742,
-      "step": 2175
-    },
-    {
-      "epoch": 3.6308835672997524,
-      "grad_norm": 7.891678333282471,
-      "learning_rate": 1.6423157894736845e-05,
-      "loss": 1.0163,
-      "step": 2200
-    },
-    {
-      "epoch": 3.6721717588769613,
-      "grad_norm": 7.933286666870117,
-      "learning_rate": 1.6370526315789475e-05,
-      "loss": 0.9442,
-      "step": 2225
-    },
-    {
-      "epoch": 3.71345995045417,
-      "grad_norm": 8.791912078857422,
-      "learning_rate": 1.6317894736842105e-05,
-      "loss": 0.9295,
-      "step": 2250
-    },
-    {
-      "epoch": 3.754748142031379,
-      "grad_norm": 7.6395583152771,
-      "learning_rate": 1.6265263157894738e-05,
-      "loss": 0.9328,
-      "step": 2275
-    },
-    {
-      "epoch": 3.796036333608588,
-      "grad_norm": 8.580839157104492,
-      "learning_rate": 1.6212631578947368e-05,
-      "loss": 0.9779,
-      "step": 2300
-    },
-    {
-      "epoch": 3.837324525185797,
-      "grad_norm": 8.464973449707031,
-      "learning_rate": 1.616e-05,
-      "loss": 0.923,
-      "step": 2325
-    },
-    {
-      "epoch": 3.878612716763006,
-      "grad_norm": 8.684146881103516,
-      "learning_rate": 1.6107368421052634e-05,
-      "loss": 0.9842,
-      "step": 2350
-    },
-    {
-      "epoch": 3.9199009083402148,
-      "grad_norm": 8.286194801330566,
-      "learning_rate": 1.6054736842105264e-05,
-      "loss": 0.9283,
-      "step": 2375
-    },
-    {
-      "epoch": 3.9611890999174237,
-      "grad_norm": 8.621734619140625,
-      "learning_rate": 1.6002105263157898e-05,
-      "loss": 0.9424,
-      "step": 2400
-    },
-    {
-      "epoch": 4.001651527663088,
-      "grad_norm": 7.654041767120361,
-      "learning_rate": 1.5949473684210528e-05,
-      "loss": 0.9083,
-      "step": 2425
-    },
-    {
-      "epoch": 4.042939719240297,
-      "grad_norm": 8.66199016571045,
-      "learning_rate": 1.589684210526316e-05,
-      "loss": 0.8082,
-      "step": 2450
-    },
-    {
-      "epoch": 4.084227910817506,
-      "grad_norm": 7.401526927947998,
-      "learning_rate": 1.584421052631579e-05,
-      "loss": 0.7986,
-      "step": 2475
-    },
-    {
-      "epoch": 4.125516102394715,
-      "grad_norm": 6.765837669372559,
-      "learning_rate": 1.579157894736842e-05,
-      "loss": 0.8111,
-      "step": 2500
-    },
-    {
-      "epoch": 4.166804293971924,
-      "grad_norm": 7.28730583190918,
-      "learning_rate": 1.5738947368421054e-05,
-      "loss": 0.8089,
-      "step": 2525
-    },
-    {
-      "epoch": 4.208092485549133,
-      "grad_norm": 7.018956661224365,
-      "learning_rate": 1.5686315789473684e-05,
-      "loss": 0.7773,
-      "step": 2550
-    },
-    {
-      "epoch": 4.249380677126342,
-      "grad_norm": 8.369226455688477,
-      "learning_rate": 1.5633684210526318e-05,
-      "loss": 0.7895,
-      "step": 2575
-    },
-    {
-      "epoch": 4.290668868703551,
-      "grad_norm": 8.268858909606934,
-      "learning_rate": 1.5581052631578947e-05,
-      "loss": 0.857,
-      "step": 2600
-    },
-    {
-      "epoch": 4.33195706028076,
-      "grad_norm": 7.69369649887085,
-      "learning_rate": 1.552842105263158e-05,
-      "loss": 0.807,
-      "step": 2625
-    },
-    {
-      "epoch": 4.373245251857969,
-      "grad_norm": 8.12571907043457,
-      "learning_rate": 1.547578947368421e-05,
-      "loss": 0.8066,
-      "step": 2650
-    },
-    {
-      "epoch": 4.414533443435178,
-      "grad_norm": 9.947578430175781,
-      "learning_rate": 1.5423157894736844e-05,
-      "loss": 0.8245,
-      "step": 2675
-    },
-    {
-      "epoch": 4.455821635012386,
-      "grad_norm": 7.1731791496276855,
-      "learning_rate": 1.5370526315789477e-05,
-      "loss": 0.809,
-      "step": 2700
-    },
-    {
-      "epoch": 4.497109826589595,
-      "grad_norm": 8.121570587158203,
-      "learning_rate": 1.5317894736842107e-05,
-      "loss": 0.8382,
-      "step": 2725
-    },
-    {
-      "epoch": 4.538398018166804,
-      "grad_norm": 8.422553062438965,
-      "learning_rate": 1.5265263157894737e-05,
-      "loss": 0.8017,
-      "step": 2750
-    },
-    {
-      "epoch": 4.579686209744013,
-      "grad_norm": 9.263009071350098,
-      "learning_rate": 1.521263157894737e-05,
-      "loss": 0.805,
-      "step": 2775
-    },
-    {
-      "epoch": 4.620974401321222,
-      "grad_norm": 8.761811256408691,
-      "learning_rate": 1.516e-05,
-      "loss": 0.7896,
-      "step": 2800
-    },
-    {
-      "epoch": 4.662262592898431,
-      "grad_norm": 7.018781661987305,
-      "learning_rate": 1.5107368421052632e-05,
-      "loss": 0.764,
-      "step": 2825
-    },
-    {
-      "epoch": 4.70355078447564,
-      "grad_norm": 8.710026741027832,
-      "learning_rate": 1.5054736842105264e-05,
-      "loss": 0.7673,
-      "step": 2850
-    },
-    {
-      "epoch": 4.744838976052849,
-      "grad_norm": 7.182971954345703,
-      "learning_rate": 1.5002105263157895e-05,
-      "loss": 0.7649,
-      "step": 2875
-    },
-    {
-      "epoch": 4.786127167630058,
-      "grad_norm": 8.922381401062012,
-      "learning_rate": 1.4949473684210527e-05,
-      "loss": 0.8047,
-      "step": 2900
-    },
-    {
-      "epoch": 4.827415359207267,
-      "grad_norm": 7.456427097320557,
-      "learning_rate": 1.4896842105263159e-05,
-      "loss": 0.7793,
-      "step": 2925
-    },
-    {
-      "epoch": 4.868703550784476,
-      "grad_norm": 8.16557502746582,
-      "learning_rate": 1.484421052631579e-05,
-      "loss": 0.7642,
-      "step": 2950
-    },
-    {
-      "epoch": 4.909991742361685,
-      "grad_norm": 7.600188255310059,
-      "learning_rate": 1.4791578947368422e-05,
-      "loss": 0.7719,
-      "step": 2975
-    },
-    {
-      "epoch": 4.951279933938894,
-      "grad_norm": 7.850863456726074,
-      "learning_rate": 1.4738947368421055e-05,
-      "loss": 0.7577,
-      "step": 3000
-    },
-    {
-      "epoch": 4.951279933938894,
-      "eval_cer": 53.34678390058808,
-      "eval_loss": 1.1084543466567993,
-      "eval_runtime": 754.0137,
-      "eval_samples_per_second": 14.033,
-      "eval_steps_per_second": 1.17,
-      "eval_wer": 96.64309288071664,
-      "step": 3000
-    },
-    {
-      "epoch": 4.992568125516103,
-      "grad_norm": 7.915883541107178,
-      "learning_rate": 1.4686315789473687e-05,
-      "loss": 0.7496,
-      "step": 3025
-    },
-    {
-      "epoch": 5.033030553261767,
-      "grad_norm": 7.240871906280518,
-      "learning_rate": 1.4633684210526317e-05,
-      "loss": 0.687,
-      "step": 3050
-    },
-    {
-      "epoch": 5.074318744838976,
-      "grad_norm": 7.480823516845703,
-      "learning_rate": 1.4581052631578949e-05,
-      "loss": 0.6601,
-      "step": 3075
-    },
-    {
-      "epoch": 5.115606936416185,
-      "grad_norm": 7.587548732757568,
-      "learning_rate": 1.452842105263158e-05,
-      "loss": 0.6831,
-      "step": 3100
-    },
-    {
-      "epoch": 5.156895127993394,
-      "grad_norm": 7.099322319030762,
-      "learning_rate": 1.4475789473684212e-05,
-      "loss": 0.6658,
-      "step": 3125
-    },
-    {
-      "epoch": 5.198183319570603,
-      "grad_norm": 7.174043655395508,
-      "learning_rate": 1.4423157894736843e-05,
-      "loss": 0.6704,
-      "step": 3150
-    },
-    {
-      "epoch": 5.239471511147812,
-      "grad_norm": 6.899098873138428,
-      "learning_rate": 1.4370526315789475e-05,
-      "loss": 0.65,
-      "step": 3175
-    },
-    {
-      "epoch": 5.280759702725021,
-      "grad_norm": 7.519511699676514,
-      "learning_rate": 1.4317894736842107e-05,
-      "loss": 0.6665,
-      "step": 3200
-    },
-    {
-      "epoch": 5.32204789430223,
-      "grad_norm": 7.408304214477539,
-      "learning_rate": 1.4265263157894738e-05,
-      "loss": 0.6398,
-      "step": 3225
-    },
-    {
-      "epoch": 5.363336085879438,
-      "grad_norm": 7.133185386657715,
-      "learning_rate": 1.4212631578947368e-05,
-      "loss": 0.6802,
-      "step": 3250
-    },
-    {
-      "epoch": 5.404624277456647,
-      "grad_norm": 7.851741313934326,
-      "learning_rate": 1.416e-05,
-      "loss": 0.6327,
-      "step": 3275
-    },
-    {
-      "epoch": 5.445912469033856,
-      "grad_norm": 7.773444175720215,
-      "learning_rate": 1.4107368421052632e-05,
-      "loss": 0.6998,
-      "step": 3300
-    },
-    {
-      "epoch": 5.487200660611065,
-      "grad_norm": 8.28067398071289,
-      "learning_rate": 1.4054736842105263e-05,
-      "loss": 0.6726,
-      "step": 3325
-    },
-    {
-      "epoch": 5.528488852188274,
-      "grad_norm": 6.886124134063721,
-      "learning_rate": 1.4002105263157897e-05,
-      "loss": 0.6418,
-      "step": 3350
-    },
-    {
-      "epoch": 5.569777043765483,
-      "grad_norm": 6.617015361785889,
-      "learning_rate": 1.3949473684210528e-05,
-      "loss": 0.6613,
-      "step": 3375
-    },
-    {
-      "epoch": 5.611065235342692,
-      "grad_norm": 7.447840690612793,
-      "learning_rate": 1.389684210526316e-05,
-      "loss": 0.6608,
-      "step": 3400
-    },
-    {
-      "epoch": 5.652353426919901,
-      "grad_norm": 7.151592254638672,
-      "learning_rate": 1.3844210526315791e-05,
-      "loss": 0.6409,
-      "step": 3425
-    },
-    {
-      "epoch": 5.69364161849711,
-      "grad_norm": 7.587296962738037,
-      "learning_rate": 1.3791578947368423e-05,
-      "loss": 0.6483,
-      "step": 3450
-    },
-    {
-      "epoch": 5.734929810074319,
-      "grad_norm": 7.848781585693359,
-      "learning_rate": 1.3738947368421055e-05,
-      "loss": 0.6638,
-      "step": 3475
-    },
-    {
-      "epoch": 5.776218001651528,
-      "grad_norm": 7.8602986335754395,
-      "learning_rate": 1.3686315789473685e-05,
-      "loss": 0.6464,
-      "step": 3500
-    },
-    {
-      "epoch": 5.817506193228737,
-      "grad_norm": 7.792623043060303,
-      "learning_rate": 1.3633684210526316e-05,
-      "loss": 0.6641,
-      "step": 3525
-    },
-    {
-      "epoch": 5.858794384805946,
-      "grad_norm": 7.796040058135986,
-      "learning_rate": 1.3581052631578948e-05,
-      "loss": 0.6529,
-      "step": 3550
-    },
-    {
-      "epoch": 5.900082576383154,
-      "grad_norm": 7.527121543884277,
-      "learning_rate": 1.352842105263158e-05,
-      "loss": 0.6458,
-      "step": 3575
-    },
-    {
-      "epoch": 5.941370767960363,
-      "grad_norm": 6.546653747558594,
-      "learning_rate": 1.3475789473684211e-05,
-      "loss": 0.6087,
-      "step": 3600
-    },
-    {
-      "epoch": 5.982658959537572,
-      "grad_norm": 8.012529373168945,
-      "learning_rate": 1.3423157894736843e-05,
-      "loss": 0.6298,
-      "step": 3625
-    },
-    {
-      "epoch": 6.023121387283237,
-      "grad_norm": 7.391585350036621,
-      "learning_rate": 1.3370526315789475e-05,
-      "loss": 0.5543,
-      "step": 3650
-    },
-    {
-      "epoch": 6.064409578860446,
-      "grad_norm": 6.664039134979248,
-      "learning_rate": 1.3317894736842108e-05,
-      "loss": 0.5252,
-      "step": 3675
-    },
-    {
-      "epoch": 6.105697770437655,
-      "grad_norm": 6.451517105102539,
-      "learning_rate": 1.326526315789474e-05,
-      "loss": 0.5712,
-      "step": 3700
-    },
-    {
-      "epoch": 6.146985962014864,
-      "grad_norm": 6.391648292541504,
-      "learning_rate": 1.321263157894737e-05,
-      "loss": 0.5664,
-      "step": 3725
-    },
-    {
-      "epoch": 6.188274153592072,
-      "grad_norm": 6.524181842803955,
-      "learning_rate": 1.3160000000000001e-05,
-      "loss": 0.5514,
-      "step": 3750
-    },
-    {
-      "epoch": 6.229562345169281,
-      "grad_norm": 6.788370609283447,
-      "learning_rate": 1.3107368421052633e-05,
-      "loss": 0.5693,
-      "step": 3775
-    },
-    {
-      "epoch": 6.27085053674649,
-      "grad_norm": 6.802549839019775,
-      "learning_rate": 1.3054736842105264e-05,
-      "loss": 0.5332,
-      "step": 3800
-    },
-    {
-      "epoch": 6.312138728323699,
-      "grad_norm": 6.864429473876953,
-      "learning_rate": 1.3002105263157896e-05,
-      "loss": 0.5582,
-      "step": 3825
-    },
-    {
-      "epoch": 6.353426919900908,
-      "grad_norm": 7.168697357177734,
-      "learning_rate": 1.2949473684210528e-05,
-      "loss": 0.5471,
-      "step": 3850
-    },
-    {
-      "epoch": 6.394715111478117,
-      "grad_norm": 6.500988960266113,
-      "learning_rate": 1.289684210526316e-05,
-      "loss": 0.5472,
-      "step": 3875
-    },
-    {
-      "epoch": 6.436003303055326,
-      "grad_norm": 6.378172874450684,
-      "learning_rate": 1.2844210526315791e-05,
-      "loss": 0.5512,
-      "step": 3900
-    },
-    {
-      "epoch": 6.477291494632535,
-      "grad_norm": 6.865861415863037,
-      "learning_rate": 1.279157894736842e-05,
-      "loss": 0.5739,
-      "step": 3925
-    },
-    {
-      "epoch": 6.518579686209744,
-      "grad_norm": 6.929198741912842,
-      "learning_rate": 1.2738947368421052e-05,
-      "loss": 0.5654,
-      "step": 3950
-    },
-    {
-      "epoch": 6.559867877786953,
-      "grad_norm": 6.951797008514404,
-      "learning_rate": 1.2686315789473684e-05,
-      "loss": 0.5422,
-      "step": 3975
-    },
-    {
-      "epoch": 6.601156069364162,
-      "grad_norm": 7.957674980163574,
-      "learning_rate": 1.2633684210526316e-05,
-      "loss": 0.5464,
-      "step": 4000
-    },
-    {
-      "epoch": 6.601156069364162,
-      "eval_cer": 48.25066202010707,
-      "eval_loss": 1.0574802160263062,
-      "eval_runtime": 742.515,
-      "eval_samples_per_second": 14.25,
-      "eval_steps_per_second": 1.188,
-      "eval_wer": 95.4926921263555,
-      "step": 4000
-    },
-    {
-      "epoch": 6.642444260941371,
-      "grad_norm": 7.094240665435791,
-      "learning_rate": 1.2581052631578949e-05,
-      "loss": 0.5365,
-      "step": 4025
-    },
-    {
-      "epoch": 6.68373245251858,
-      "grad_norm": 8.255016326904297,
-      "learning_rate": 1.252842105263158e-05,
-      "loss": 0.5768,
-      "step": 4050
-    },
-    {
-      "epoch": 6.725020644095789,
-      "grad_norm": 7.434171676635742,
-      "learning_rate": 1.2475789473684212e-05,
-      "loss": 0.5892,
-      "step": 4075
-    },
-    {
-      "epoch": 6.766308835672998,
-      "grad_norm": 6.989074230194092,
-      "learning_rate": 1.2423157894736844e-05,
-      "loss": 0.5494,
-      "step": 4100
-    },
-    {
-      "epoch": 6.807597027250207,
-      "grad_norm": 6.808770656585693,
-      "learning_rate": 1.2370526315789476e-05,
-      "loss": 0.5281,
-      "step": 4125
-    },
-    {
-      "epoch": 6.848885218827416,
-      "grad_norm": 7.470989227294922,
-      "learning_rate": 1.2317894736842107e-05,
-      "loss": 0.5499,
-      "step": 4150
-    },
-    {
-      "epoch": 6.890173410404624,
-      "grad_norm": 7.557090759277344,
-      "learning_rate": 1.2265263157894737e-05,
-      "loss": 0.5413,
-      "step": 4175
-    },
-    {
-      "epoch": 6.931461601981833,
-      "grad_norm": 7.504119396209717,
-      "learning_rate": 1.2212631578947369e-05,
-      "loss": 0.513,
-      "step": 4200
-    },
-    {
-      "epoch": 6.972749793559042,
-      "grad_norm": 6.75087308883667,
-      "learning_rate": 1.216e-05,
-      "loss": 0.5343,
-      "step": 4225
-    },
-    {
-      "epoch": 7.013212221304707,
-      "grad_norm": 5.9934515953063965,
-      "learning_rate": 1.2107368421052632e-05,
-      "loss": 0.4879,
-      "step": 4250
-    },
-    {
-      "epoch": 7.054500412881916,
-      "grad_norm": 6.634411334991455,
-      "learning_rate": 1.2054736842105264e-05,
-      "loss": 0.4454,
-      "step": 4275
-    },
-    {
-      "epoch": 7.095788604459124,
-      "grad_norm": 7.614193916320801,
-      "learning_rate": 1.2002105263157895e-05,
-      "loss": 0.4392,
-      "step": 4300
-    },
-    {
-      "epoch": 7.137076796036333,
-      "grad_norm": 5.324835777282715,
-      "learning_rate": 1.1949473684210527e-05,
-      "loss": 0.456,
-      "step": 4325
-    },
-    {
-      "epoch": 7.178364987613542,
-      "grad_norm": 6.1424241065979,
-      "learning_rate": 1.189684210526316e-05,
-      "loss": 0.46,
-      "step": 4350
-    },
-    {
-      "epoch": 7.219653179190751,
-      "grad_norm": 7.1868767738342285,
-      "learning_rate": 1.1844210526315792e-05,
-      "loss": 0.4591,
-      "step": 4375
-    },
-    {
-      "epoch": 7.26094137076796,
-      "grad_norm": 6.41041374206543,
-      "learning_rate": 1.1791578947368424e-05,
-      "loss": 0.4618,
-      "step": 4400
-    },
-    {
-      "epoch": 7.302229562345169,
-      "grad_norm": 6.095521450042725,
-      "learning_rate": 1.1738947368421054e-05,
-      "loss": 0.4692,
-      "step": 4425
-    },
-    {
-      "epoch": 7.343517753922378,
-      "grad_norm": 6.523583889007568,
-      "learning_rate": 1.1686315789473685e-05,
-      "loss": 0.4631,
-      "step": 4450
-    },
-    {
-      "epoch": 7.384805945499587,
-      "grad_norm": 6.192616939544678,
-      "learning_rate": 1.1633684210526317e-05,
-      "loss": 0.4689,
-      "step": 4475
-    },
-    {
-      "epoch": 7.426094137076796,
-      "grad_norm": 5.833901882171631,
-      "learning_rate": 1.1581052631578948e-05,
-      "loss": 0.4472,
-      "step": 4500
-    },
-    {
-      "epoch": 7.467382328654005,
-      "grad_norm": 7.350675582885742,
-      "learning_rate": 1.152842105263158e-05,
-      "loss": 0.472,
-      "step": 4525
-    },
-    {
-      "epoch": 7.508670520231214,
-      "grad_norm": 6.825387477874756,
-      "learning_rate": 1.1475789473684212e-05,
-      "loss": 0.4773,
-      "step": 4550
-    },
-    {
-      "epoch": 7.549958711808423,
-      "grad_norm": 7.2338762283325195,
-      "learning_rate": 1.1423157894736843e-05,
-      "loss": 0.4515,
-      "step": 4575
-    },
-    {
-      "epoch": 7.591246903385632,
-      "grad_norm": 7.510733604431152,
-      "learning_rate": 1.1370526315789473e-05,
-      "loss": 0.4676,
-      "step": 4600
-    },
-    {
-      "epoch": 7.632535094962841,
-      "grad_norm": 6.926485538482666,
-      "learning_rate": 1.1317894736842105e-05,
-      "loss": 0.4692,
-      "step": 4625
-    },
-    {
-      "epoch": 7.673823286540049,
-      "grad_norm": 7.200405120849609,
-      "learning_rate": 1.1265263157894737e-05,
-      "loss": 0.4874,
-      "step": 4650
-    },
-    {
-      "epoch": 7.715111478117258,
-      "grad_norm": 7.665420055389404,
-      "learning_rate": 1.1212631578947368e-05,
-      "loss": 0.4515,
-      "step": 4675
-    },
-    {
-      "epoch": 7.756399669694467,
-      "grad_norm": 6.377760410308838,
-      "learning_rate": 1.1160000000000002e-05,
-      "loss": 0.4639,
-      "step": 4700
-    },
-    {
-      "epoch": 7.797687861271676,
-      "grad_norm": 7.134575366973877,
-      "learning_rate": 1.1107368421052633e-05,
-      "loss": 0.4543,
-      "step": 4725
-    },
-    {
-      "epoch": 7.838976052848885,
-      "grad_norm": 6.138679027557373,
-      "learning_rate": 1.1054736842105265e-05,
-      "loss": 0.4276,
-      "step": 4750
-    },
-    {
-      "epoch": 7.880264244426094,
-      "grad_norm": 6.741207122802734,
-      "learning_rate": 1.1002105263157896e-05,
-      "loss": 0.4975,
-      "step": 4775
-    },
-    {
-      "epoch": 7.921552436003303,
-      "grad_norm": 6.514609336853027,
-      "learning_rate": 1.0949473684210528e-05,
-      "loss": 0.4841,
-      "step": 4800
-    },
-    {
-      "epoch": 7.962840627580512,
-      "grad_norm": 6.2714009284973145,
-      "learning_rate": 1.089684210526316e-05,
-      "loss": 0.4658,
-      "step": 4825
-    },
-    {
-      "epoch": 8.003303055326176,
-      "grad_norm": 7.009129524230957,
-      "learning_rate": 1.084421052631579e-05,
-      "loss": 0.4919,
-      "step": 4850
-    },
-    {
-      "epoch": 8.044591246903385,
-      "grad_norm": 6.334277153015137,
-      "learning_rate": 1.0791578947368421e-05,
-      "loss": 0.3873,
-      "step": 4875
-    },
-    {
-      "epoch": 8.085879438480594,
-      "grad_norm": 6.403853416442871,
-      "learning_rate": 1.0738947368421053e-05,
-      "loss": 0.3961,
-      "step": 4900
-    },
-    {
-      "epoch": 8.127167630057803,
-      "grad_norm": 6.143258571624756,
-      "learning_rate": 1.0686315789473685e-05,
-      "loss": 0.3699,
-      "step": 4925
-    },
-    {
-      "epoch": 8.168455821635012,
-      "grad_norm": 6.0696539878845215,
-      "learning_rate": 1.0633684210526316e-05,
-      "loss": 0.3858,
-      "step": 4950
-    },
-    {
-      "epoch": 8.209744013212221,
-      "grad_norm": 6.363874435424805,
-      "learning_rate": 1.0581052631578948e-05,
-      "loss": 0.392,
-      "step": 4975
-    },
-    {
-      "epoch": 8.25103220478943,
-      "grad_norm": 5.990923881530762,
-      "learning_rate": 1.052842105263158e-05,
-      "loss": 0.4182,
-      "step": 5000
-    },
-    {
-      "epoch": 8.25103220478943,
-      "eval_cer": 47.292882280788234,
-      "eval_loss": 1.0573757886886597,
-      "eval_runtime": 732.0504,
-      "eval_samples_per_second": 14.454,
-      "eval_steps_per_second": 1.205,
-      "eval_wer": 96.23762376237623,
-      "step": 5000
-    },
-    {
-      "epoch": 8.29232039636664,
-      "grad_norm": 5.979728698730469,
-      "learning_rate": 1.047578947368421e-05,
-      "loss": 0.38,
-      "step": 5025
-    },
-    {
-      "epoch": 8.333608587943848,
-      "grad_norm": 6.235442161560059,
-      "learning_rate": 1.0423157894736844e-05,
-      "loss": 0.3823,
-      "step": 5050
-    },
-    {
-      "epoch": 8.374896779521057,
-      "grad_norm": 6.0435471534729,
-      "learning_rate": 1.0370526315789476e-05,
-      "loss": 0.3889,
-      "step": 5075
-    },
-    {
-      "epoch": 8.416184971098266,
-      "grad_norm": 5.2331624031066895,
-      "learning_rate": 1.0317894736842106e-05,
-      "loss": 0.4002,
-      "step": 5100
-    },
-    {
-      "epoch": 8.457473162675475,
-      "grad_norm": 5.645880699157715,
-      "learning_rate": 1.0265263157894738e-05,
-      "loss": 0.395,
-      "step": 5125
-    },
-    {
-      "epoch": 8.498761354252684,
-      "grad_norm": 6.611478805541992,
-      "learning_rate": 1.021263157894737e-05,
-      "loss": 0.3964,
-      "step": 5150
-    },
-    {
-      "epoch": 8.540049545829893,
-      "grad_norm": 5.404575347900391,
-      "learning_rate": 1.0160000000000001e-05,
-      "loss": 0.3886,
-      "step": 5175
-    },
-    {
-      "epoch": 8.581337737407102,
-      "grad_norm": 7.283960819244385,
-      "learning_rate": 1.0107368421052633e-05,
-      "loss": 0.4193,
-      "step": 5200
-    },
-    {
-      "epoch": 8.622625928984311,
-      "grad_norm": 6.334190368652344,
-      "learning_rate": 1.0054736842105264e-05,
-      "loss": 0.4129,
-      "step": 5225
-    },
-    {
-      "epoch": 8.66391412056152,
-      "grad_norm": 6.392534255981445,
-      "learning_rate": 1.0002105263157896e-05,
-      "loss": 0.3832,
-      "step": 5250
-    },
-    {
-      "epoch": 8.705202312138729,
-      "grad_norm": 6.049492359161377,
-      "learning_rate": 9.949473684210526e-06,
-      "loss": 0.4008,
-      "step": 5275
-    },
-    {
-      "epoch": 8.746490503715938,
-      "grad_norm": 5.881133556365967,
-      "learning_rate": 9.89684210526316e-06,
-      "loss": 0.3927,
-      "step": 5300
-    },
-    {
-      "epoch": 8.787778695293147,
-      "grad_norm": 6.470844745635986,
-      "learning_rate": 9.84421052631579e-06,
-      "loss": 0.4036,
-      "step": 5325
-    },
-    {
-      "epoch": 8.829066886870356,
-      "grad_norm": 6.188573837280273,
-      "learning_rate": 9.791578947368422e-06,
-      "loss": 0.394,
-      "step": 5350
-    },
-    {
-      "epoch": 8.870355078447563,
-      "grad_norm": 6.691900730133057,
-      "learning_rate": 9.738947368421054e-06,
-      "loss": 0.399,
-      "step": 5375
-    },
-    {
-      "epoch": 8.911643270024772,
-      "grad_norm": 6.903393745422363,
-      "learning_rate": 9.686315789473684e-06,
-      "loss": 0.3999,
-      "step": 5400
-    },
-    {
-      "epoch": 8.952931461601981,
-      "grad_norm": 6.473091125488281,
-      "learning_rate": 9.633684210526316e-06,
-      "loss": 0.3833,
-      "step": 5425
-    },
-    {
-      "epoch": 8.99421965317919,
-      "grad_norm": 6.615601062774658,
-      "learning_rate": 9.581052631578947e-06,
-      "loss": 0.3961,
-      "step": 5450
-    },
-    {
-      "epoch": 9.034682080924856,
-      "grad_norm": 5.409454345703125,
-      "learning_rate": 9.52842105263158e-06,
-      "loss": 0.3184,
-      "step": 5475
-    },
-    {
-      "epoch": 9.075970272502065,
-      "grad_norm": 4.625083923339844,
-      "learning_rate": 9.475789473684212e-06,
-      "loss": 0.308,
-      "step": 5500
-    },
-    {
-      "epoch": 9.117258464079274,
-      "grad_norm": 6.347021579742432,
-      "learning_rate": 9.423157894736842e-06,
-      "loss": 0.3087,
-      "step": 5525
-    },
-    {
-      "epoch": 9.158546655656481,
-      "grad_norm": 6.036218166351318,
-      "learning_rate": 9.370526315789474e-06,
-      "loss": 0.3361,
-      "step": 5550
-    },
-    {
-      "epoch": 9.19983484723369,
-      "grad_norm": 6.974196910858154,
-      "learning_rate": 9.317894736842105e-06,
-      "loss": 0.3277,
-      "step": 5575
-    },
-    {
-      "epoch": 9.2411230388109,
-      "grad_norm": 6.37134313583374,
-      "learning_rate": 9.265263157894737e-06,
-      "loss": 0.3227,
-      "step": 5600
-    },
-    {
-      "epoch": 9.282411230388108,
-      "grad_norm": 5.647594928741455,
-      "learning_rate": 9.21263157894737e-06,
-      "loss": 0.3408,
-      "step": 5625
-    },
-    {
-      "epoch": 9.323699421965317,
-      "grad_norm": 5.690819263458252,
-      "learning_rate": 9.16e-06,
-      "loss": 0.3431,
-      "step": 5650
-    },
-    {
-      "epoch": 9.364987613542526,
-      "grad_norm": 6.394257545471191,
-      "learning_rate": 9.107368421052632e-06,
-      "loss": 0.3684,
-      "step": 5675
-    },
-    {
-      "epoch": 9.406275805119735,
-      "grad_norm": 5.489740371704102,
-      "learning_rate": 9.054736842105264e-06,
-      "loss": 0.3401,
-      "step": 5700
-    },
-    {
-      "epoch": 9.447563996696944,
-      "grad_norm": 5.952576637268066,
-      "learning_rate": 9.002105263157895e-06,
-      "loss": 0.3485,
-      "step": 5725
-    },
-    {
-      "epoch": 9.488852188274153,
-      "grad_norm": 5.653362274169922,
-      "learning_rate": 8.949473684210527e-06,
-      "loss": 0.349,
-      "step": 5750
-    },
-    {
-      "epoch": 9.530140379851362,
-      "grad_norm": 6.067948341369629,
-      "learning_rate": 8.896842105263159e-06,
-      "loss": 0.3629,
-      "step": 5775
-    },
-    {
-      "epoch": 9.571428571428571,
-      "grad_norm": 5.475063800811768,
-      "learning_rate": 8.84421052631579e-06,
-      "loss": 0.3207,
-      "step": 5800
-    },
-    {
-      "epoch": 9.61271676300578,
-      "grad_norm": 6.7783308029174805,
-      "learning_rate": 8.791578947368422e-06,
-      "loss": 0.3454,
-      "step": 5825
-    },
-    {
-      "epoch": 9.65400495458299,
-      "grad_norm": 5.636470317840576,
-      "learning_rate": 8.738947368421053e-06,
-      "loss": 0.3408,
-      "step": 5850
-    },
-    {
-      "epoch": 9.695293146160198,
-      "grad_norm": 5.290091037750244,
-      "learning_rate": 8.686315789473685e-06,
-      "loss": 0.3229,
-      "step": 5875
-    },
-    {
-      "epoch": 9.736581337737407,
-      "grad_norm": 5.795228481292725,
-      "learning_rate": 8.633684210526317e-06,
-      "loss": 0.36,
-      "step": 5900
-    },
-    {
-      "epoch": 9.777869529314616,
-      "grad_norm": 5.348466396331787,
-      "learning_rate": 8.581052631578948e-06,
-      "loss": 0.3358,
-      "step": 5925
-    },
-    {
-      "epoch": 9.819157720891825,
-      "grad_norm": 5.813995361328125,
-      "learning_rate": 8.528421052631578e-06,
-      "loss": 0.349,
-      "step": 5950
-    },
-    {
-      "epoch": 9.860445912469034,
-      "grad_norm": 5.806293964385986,
-      "learning_rate": 8.475789473684212e-06,
-      "loss": 0.3493,
-      "step": 5975
-    },
-    {
-      "epoch": 9.901734104046243,
-      "grad_norm": 6.348217487335205,
-      "learning_rate": 8.423157894736843e-06,
-      "loss": 0.3164,
-      "step": 6000
-    },
-    {
-      "epoch": 9.901734104046243,
-      "eval_cer": 49.44172503525042,
-      "eval_loss": 1.0615819692611694,
-      "eval_runtime": 712.2161,
-      "eval_samples_per_second": 14.856,
-      "eval_steps_per_second": 1.238,
-      "eval_wer": 96.38849599245638,
-      "step": 6000
-    },
-    {
-      "epoch": 9.943022295623452,
-      "grad_norm": 5.729813575744629,
-      "learning_rate": 8.370526315789475e-06,
-      "loss": 0.3253,
-      "step": 6025
-    },
-    {
-      "epoch": 9.984310487200661,
-      "grad_norm": 7.191168785095215,
-      "learning_rate": 8.317894736842107e-06,
-      "loss": 0.3433,
-      "step": 6050
-    },
-    {
-      "epoch": 10.024772914946325,
-      "grad_norm": 6.767040729522705,
-      "learning_rate": 8.265263157894737e-06,
-      "loss": 0.2875,
-      "step": 6075
-    },
-    {
-      "epoch": 10.066061106523534,
-      "grad_norm": 5.048575401306152,
-      "learning_rate": 8.212631578947368e-06,
-      "loss": 0.2773,
-      "step": 6100
-    },
-    {
-      "epoch": 10.107349298100743,
-      "grad_norm": 4.836114883422852,
-      "learning_rate": 8.16e-06,
-      "loss": 0.2889,
-      "step": 6125
-    },
-    {
-      "epoch": 10.148637489677952,
-      "grad_norm": 4.830049514770508,
-      "learning_rate": 8.107368421052633e-06,
-      "loss": 0.3004,
-      "step": 6150
-    },
-    {
-      "epoch": 10.189925681255161,
-      "grad_norm": 5.718193054199219,
-      "learning_rate": 8.054736842105265e-06,
-      "loss": 0.2989,
-      "step": 6175
-    },
-    {
-      "epoch": 10.23121387283237,
-      "grad_norm": 7.24569034576416,
-      "learning_rate": 8.002105263157895e-06,
-      "loss": 0.2712,
-      "step": 6200
-    },
-    {
-      "epoch": 10.27250206440958,
-      "grad_norm": 6.074246883392334,
-      "learning_rate": 7.949473684210526e-06,
-      "loss": 0.2899,
-      "step": 6225
-    },
-    {
-      "epoch": 10.313790255986788,
-      "grad_norm": 5.600971698760986,
-      "learning_rate": 7.896842105263158e-06,
-      "loss": 0.3,
-      "step": 6250
-    },
-    {
-      "epoch": 10.355078447563997,
-      "grad_norm": 6.002727508544922,
-      "learning_rate": 7.84421052631579e-06,
-      "loss": 0.2895,
-      "step": 6275
-    },
-    {
-      "epoch": 10.396366639141206,
-      "grad_norm": 5.616031169891357,
-      "learning_rate": 7.793684210526316e-06,
-      "loss": 0.3123,
-      "step": 6300
-    },
-    {
-      "epoch": 10.437654830718415,
-      "grad_norm": 5.227489948272705,
-      "learning_rate": 7.741052631578948e-06,
-      "loss": 0.2796,
-      "step": 6325
-    },
-    {
-      "epoch": 10.478943022295624,
-      "grad_norm": 5.6762261390686035,
-      "learning_rate": 7.68842105263158e-06,
-      "loss": 0.3061,
-      "step": 6350
-    },
-    {
-      "epoch": 10.520231213872833,
-      "grad_norm": 4.9320197105407715,
-      "learning_rate": 7.635789473684211e-06,
-      "loss": 0.2779,
-      "step": 6375
-    },
-    {
-      "epoch": 10.561519405450042,
-      "grad_norm": 5.518511772155762,
-      "learning_rate": 7.583157894736842e-06,
-      "loss": 0.2861,
-      "step": 6400
-    },
-    {
-      "epoch": 10.602807597027251,
-      "grad_norm": 5.470175266265869,
-      "learning_rate": 7.5305263157894745e-06,
-      "loss": 0.279,
-      "step": 6425
-    },
-    {
-      "epoch": 10.64409578860446,
-      "grad_norm": 4.248904228210449,
-      "learning_rate": 7.477894736842106e-06,
-      "loss": 0.3054,
-      "step": 6450
-    },
-    {
-      "epoch": 10.685383980181667,
-      "grad_norm": 6.3203935623168945,
-      "learning_rate": 7.425263157894738e-06,
-      "loss": 0.3168,
-      "step": 6475
-    },
-    {
-      "epoch": 10.726672171758876,
-      "grad_norm": 5.901068687438965,
-      "learning_rate": 7.3726315789473694e-06,
-      "loss": 0.3103,
-      "step": 6500
-    },
-    {
-      "epoch": 10.767960363336085,
-      "grad_norm": 6.379432678222656,
-      "learning_rate": 7.32e-06,
-      "loss": 0.2715,
-      "step": 6525
-    },
-    {
-      "epoch": 10.809248554913294,
-      "grad_norm": 5.802628040313721,
-      "learning_rate": 7.267368421052632e-06,
-      "loss": 0.2981,
-      "step": 6550
-    },
-    {
-      "epoch": 10.850536746490503,
-      "grad_norm": 6.295346260070801,
-      "learning_rate": 7.2147368421052635e-06,
-      "loss": 0.2676,
-      "step": 6575
-    },
-    {
-      "epoch": 10.891824938067712,
-      "grad_norm": 5.411930561065674,
-      "learning_rate": 7.162105263157896e-06,
-      "loss": 0.2809,
-      "step": 6600
-    },
-    {
-      "epoch": 10.933113129644921,
-      "grad_norm": 5.577861309051514,
-      "learning_rate": 7.109473684210528e-06,
-      "loss": 0.2473,
-      "step": 6625
-    },
-    {
-      "epoch": 10.97440132122213,
-      "grad_norm": 5.272998332977295,
-      "learning_rate": 7.056842105263158e-06,
-      "loss": 0.2931,
-      "step": 6650
-    },
-    {
-      "epoch": 11.014863748967795,
-      "grad_norm": 5.220921993255615,
-      "learning_rate": 7.00421052631579e-06,
-      "loss": 0.2772,
-      "step": 6675
-    },
-    {
-      "epoch": 11.056151940545003,
-      "grad_norm": 4.028062343597412,
-      "learning_rate": 6.951578947368422e-06,
-      "loss": 0.2511,
-      "step": 6700
-    },
-    {
-      "epoch": 11.097440132122212,
-      "grad_norm": 4.835925579071045,
-      "learning_rate": 6.8989473684210525e-06,
-      "loss": 0.2502,
-      "step": 6725
-    },
-    {
-      "epoch": 11.138728323699421,
-      "grad_norm": 5.920368194580078,
-      "learning_rate": 6.846315789473684e-06,
-      "loss": 0.2438,
-      "step": 6750
-    },
-    {
-      "epoch": 11.18001651527663,
-      "grad_norm": 5.114356517791748,
-      "learning_rate": 6.793684210526317e-06,
-      "loss": 0.2478,
-      "step": 6775
-    },
-    {
-      "epoch": 11.22130470685384,
-      "grad_norm": 4.871094703674316,
-      "learning_rate": 6.741052631578948e-06,
-      "loss": 0.2504,
-      "step": 6800
-    },
-    {
-      "epoch": 11.262592898431048,
-      "grad_norm": 4.20628547668457,
-      "learning_rate": 6.68842105263158e-06,
-      "loss": 0.2316,
-      "step": 6825
-    },
-    {
-      "epoch": 11.303881090008257,
-      "grad_norm": 5.95331335067749,
-      "learning_rate": 6.635789473684211e-06,
-      "loss": 0.2524,
-      "step": 6850
-    },
-    {
-      "epoch": 11.345169281585466,
-      "grad_norm": 5.462084770202637,
-      "learning_rate": 6.583157894736842e-06,
-      "loss": 0.2488,
-      "step": 6875
-    },
-    {
-      "epoch": 11.386457473162675,
-      "grad_norm": 4.980792999267578,
-      "learning_rate": 6.530526315789474e-06,
-      "loss": 0.2344,
-      "step": 6900
-    },
-    {
-      "epoch": 11.427745664739884,
-      "grad_norm": 5.869212627410889,
-      "learning_rate": 6.477894736842106e-06,
-      "loss": 0.2484,
-      "step": 6925
-    },
-    {
-      "epoch": 11.469033856317093,
-      "grad_norm": 5.4397873878479,
-      "learning_rate": 6.425263157894738e-06,
-      "loss": 0.2523,
-      "step": 6950
-    },
-    {
-      "epoch": 11.510322047894302,
-      "grad_norm": 5.890199661254883,
-      "learning_rate": 6.372631578947369e-06,
-      "loss": 0.2565,
-      "step": 6975
-    },
-    {
-      "epoch": 11.551610239471511,
-      "grad_norm": 4.83267879486084,
-      "learning_rate": 6.3200000000000005e-06,
-      "loss": 0.2319,
-      "step": 7000
-    },
-    {
-      "epoch": 11.551610239471511,
-      "eval_cer": 49.55349466371671,
-      "eval_loss": 1.0929207801818848,
-      "eval_runtime": 718.5035,
-      "eval_samples_per_second": 14.726,
-      "eval_steps_per_second": 1.228,
-      "eval_wer": 96.25648279113625,
-      "step": 7000
-    },
-    {
-      "epoch": 11.59289843104872,
-      "grad_norm": 6.01038932800293,
-      "learning_rate": 6.267368421052632e-06,
-      "loss": 0.2703,
-      "step": 7025
-    },
-    {
-      "epoch": 11.63418662262593,
-      "grad_norm": 4.515256404876709,
-      "learning_rate": 6.214736842105264e-06,
-      "loss": 0.2497,
-      "step": 7050
-    },
-    {
-      "epoch": 11.675474814203138,
-      "grad_norm": 5.914691925048828,
-      "learning_rate": 6.1621052631578945e-06,
-      "loss": 0.2374,
-      "step": 7075
-    },
-    {
-      "epoch": 11.716763005780347,
-      "grad_norm": 5.570655822753906,
-      "learning_rate": 6.109473684210527e-06,
-      "loss": 0.253,
-      "step": 7100
-    },
-    {
-      "epoch": 11.758051197357556,
-      "grad_norm": 5.9783244132995605,
-      "learning_rate": 6.056842105263159e-06,
-      "loss": 0.2364,
-      "step": 7125
-    },
-    {
-      "epoch": 11.799339388934765,
-      "grad_norm": 5.595921516418457,
-      "learning_rate": 6.00421052631579e-06,
-      "loss": 0.2375,
-      "step": 7150
-    },
-    {
-      "epoch": 11.840627580511974,
-      "grad_norm": 4.966527938842773,
-      "learning_rate": 5.951578947368422e-06,
-      "loss": 0.2652,
-      "step": 7175
-    },
-    {
-      "epoch": 11.881915772089183,
-      "grad_norm": 4.243671894073486,
-      "learning_rate": 5.898947368421053e-06,
-      "loss": 0.2348,
-      "step": 7200
-    },
-    {
-      "epoch": 11.923203963666392,
-      "grad_norm": 4.7744669914245605,
-      "learning_rate": 5.846315789473684e-06,
-      "loss": 0.2461,
-      "step": 7225
-    },
-    {
-      "epoch": 11.964492155243601,
-      "grad_norm": 4.887286186218262,
-      "learning_rate": 5.793684210526316e-06,
-      "loss": 0.2466,
-      "step": 7250
-    },
-    {
-      "epoch": 12.004954582989265,
-      "grad_norm": 4.767704963684082,
-      "learning_rate": 5.7410526315789485e-06,
-      "loss": 0.2628,
-      "step": 7275
-    },
-    {
-      "epoch": 12.046242774566474,
-      "grad_norm": 3.731494426727295,
-      "learning_rate": 5.68842105263158e-06,
-      "loss": 0.2121,
-      "step": 7300
-    },
-    {
-      "epoch": 12.087530966143683,
-      "grad_norm": 4.329957962036133,
-      "learning_rate": 5.635789473684211e-06,
-      "loss": 0.208,
-      "step": 7325
-    },
-    {
-      "epoch": 12.128819157720892,
-      "grad_norm": 4.992996692657471,
-      "learning_rate": 5.5831578947368425e-06,
-      "loss": 0.2007,
-      "step": 7350
-    },
-    {
-      "epoch": 12.170107349298101,
-      "grad_norm": 4.756143093109131,
-      "learning_rate": 5.530526315789474e-06,
-      "loss": 0.2084,
-      "step": 7375
-    },
-    {
-      "epoch": 12.21139554087531,
-      "grad_norm": 5.0002827644348145,
-      "learning_rate": 5.477894736842105e-06,
-      "loss": 0.2285,
-      "step": 7400
-    },
-    {
-      "epoch": 12.25268373245252,
-      "grad_norm": 3.5156126022338867,
-      "learning_rate": 5.425263157894737e-06,
-      "loss": 0.214,
-      "step": 7425
-    },
-    {
-      "epoch": 12.293971924029728,
-      "grad_norm": 4.908341884613037,
-      "learning_rate": 5.372631578947369e-06,
-      "loss": 0.2023,
-      "step": 7450
-    },
-    {
-      "epoch": 12.335260115606937,
-      "grad_norm": 5.120205879211426,
-      "learning_rate": 5.320000000000001e-06,
-      "loss": 0.2199,
-      "step": 7475
-    },
-    {
-      "epoch": 12.376548307184144,
-      "grad_norm": 5.24783992767334,
-      "learning_rate": 5.267368421052632e-06,
-      "loss": 0.1918,
-      "step": 7500
-    },
-    {
-      "epoch": 12.417836498761353,
-      "grad_norm": 4.663553714752197,
-      "learning_rate": 5.214736842105263e-06,
-      "loss": 0.2018,
-      "step": 7525
-    },
-    {
-      "epoch": 12.459124690338562,
-      "grad_norm": 4.562893867492676,
-      "learning_rate": 5.162105263157895e-06,
-      "loss": 0.2141,
-      "step": 7550
-    },
-    {
-      "epoch": 12.500412881915771,
-      "grad_norm": 5.8733062744140625,
-      "learning_rate": 5.1094736842105264e-06,
-      "loss": 0.2359,
-      "step": 7575
-    },
-    {
-      "epoch": 12.54170107349298,
-      "grad_norm": 7.215207576751709,
-      "learning_rate": 5.056842105263158e-06,
-      "loss": 0.2422,
-      "step": 7600
-    },
-    {
-      "epoch": 12.58298926507019,
-      "grad_norm": 4.633525371551514,
-      "learning_rate": 5.0042105263157906e-06,
-      "loss": 0.2188,
-      "step": 7625
-    },
-    {
-      "epoch": 12.624277456647398,
-      "grad_norm": 5.8343305587768555,
-      "learning_rate": 4.951578947368421e-06,
-      "loss": 0.2169,
-      "step": 7650
-    },
-    {
-      "epoch": 12.665565648224607,
-      "grad_norm": 3.9599239826202393,
-      "learning_rate": 4.898947368421053e-06,
-      "loss": 0.2275,
-      "step": 7675
-    },
-    {
-      "epoch": 12.706853839801816,
-      "grad_norm": 5.128805637359619,
-      "learning_rate": 4.846315789473685e-06,
-      "loss": 0.2095,
-      "step": 7700
-    },
-    {
-      "epoch": 12.748142031379025,
-      "grad_norm": 4.6408162117004395,
-      "learning_rate": 4.793684210526316e-06,
-      "loss": 0.1983,
-      "step": 7725
-    },
-    {
-      "epoch": 12.789430222956234,
-      "grad_norm": 4.684074878692627,
-      "learning_rate": 4.741052631578948e-06,
-      "loss": 0.2247,
-      "step": 7750
-    },
-    {
-      "epoch": 12.830718414533443,
-      "grad_norm": 4.256105422973633,
-      "learning_rate": 4.6884210526315795e-06,
-      "loss": 0.2164,
-      "step": 7775
-    },
-    {
-      "epoch": 12.872006606110652,
-      "grad_norm": 4.794992446899414,
-      "learning_rate": 4.63578947368421e-06,
-      "loss": 0.2133,
-      "step": 7800
-    },
-    {
-      "epoch": 12.913294797687861,
-      "grad_norm": 6.137476921081543,
-      "learning_rate": 4.583157894736843e-06,
-      "loss": 0.2434,
-      "step": 7825
-    },
-    {
-      "epoch": 12.95458298926507,
-      "grad_norm": 4.048770427703857,
-      "learning_rate": 4.5305263157894744e-06,
-      "loss": 0.2031,
-      "step": 7850
-    },
-    {
-      "epoch": 12.995871180842279,
-      "grad_norm": 4.465664863586426,
-      "learning_rate": 4.477894736842105e-06,
-      "loss": 0.2296,
-      "step": 7875
-    },
-    {
-      "epoch": 13.036333608587944,
-      "grad_norm": 4.5229668617248535,
-      "learning_rate": 4.425263157894737e-06,
-      "loss": 0.189,
-      "step": 7900
-    },
-    {
-      "epoch": 13.077621800165153,
-      "grad_norm": 3.7040534019470215,
-      "learning_rate": 4.3726315789473685e-06,
-      "loss": 0.1951,
-      "step": 7925
-    },
-    {
-      "epoch": 13.118909991742361,
-      "grad_norm": 4.726925373077393,
-      "learning_rate": 4.32e-06,
-      "loss": 0.1743,
-      "step": 7950
-    },
-    {
-      "epoch": 13.16019818331957,
-      "grad_norm": 4.432371616363525,
-      "learning_rate": 4.267368421052632e-06,
-      "loss": 0.1948,
-      "step": 7975
-    },
-    {
-      "epoch": 13.20148637489678,
-      "grad_norm": 6.360472679138184,
-      "learning_rate": 4.214736842105263e-06,
-      "loss": 0.1899,
-      "step": 8000
-    },
-    {
-      "epoch": 13.20148637489678,
-      "eval_cer": 48.673667075533345,
-      "eval_loss": 1.1223334074020386,
-      "eval_runtime": 698.1183,
-      "eval_samples_per_second": 15.156,
-      "eval_steps_per_second": 1.263,
-      "eval_wer": 97.27487034417727,
-      "step": 8000
-    },
-    {
-      "epoch": 13.242774566473988,
-      "grad_norm": 4.355146408081055,
-      "learning_rate": 4.162105263157895e-06,
-      "loss": 0.207,
-      "step": 8025
-    },
-    {
-      "epoch": 13.284062758051197,
-      "grad_norm": 4.026797771453857,
-      "learning_rate": 4.109473684210527e-06,
-      "loss": 0.1656,
-      "step": 8050
-    },
-    {
-      "epoch": 13.325350949628406,
-      "grad_norm": 4.001533031463623,
-      "learning_rate": 4.056842105263158e-06,
-      "loss": 0.1899,
-      "step": 8075
-    },
-    {
-      "epoch": 13.366639141205615,
-      "grad_norm": 3.8727056980133057,
-      "learning_rate": 4.00421052631579e-06,
-      "loss": 0.1919,
-      "step": 8100
-    },
-    {
-      "epoch": 13.407927332782824,
-      "grad_norm": 4.644744873046875,
-      "learning_rate": 3.951578947368422e-06,
-      "loss": 0.1987,
-      "step": 8125
-    },
-    {
-      "epoch": 13.449215524360033,
-      "grad_norm": 4.7693071365356445,
-      "learning_rate": 3.898947368421052e-06,
-      "loss": 0.185,
-      "step": 8150
-    },
-    {
-      "epoch": 13.490503715937242,
-      "grad_norm": 5.065967082977295,
-      "learning_rate": 3.846315789473685e-06,
-      "loss": 0.1811,
-      "step": 8175
-    },
-    {
-      "epoch": 13.531791907514451,
-      "grad_norm": 3.682410955429077,
-      "learning_rate": 3.793684210526316e-06,
-      "loss": 0.2118,
-      "step": 8200
-    },
-    {
-      "epoch": 13.57308009909166,
-      "grad_norm": 4.680816650390625,
-      "learning_rate": 3.7410526315789473e-06,
-      "loss": 0.1995,
-      "step": 8225
-    },
-    {
-      "epoch": 13.61436829066887,
-      "grad_norm": 5.313553333282471,
-      "learning_rate": 3.6884210526315794e-06,
-      "loss": 0.1871,
-      "step": 8250
-    },
-    {
-      "epoch": 13.655656482246078,
-      "grad_norm": 4.104048728942871,
-      "learning_rate": 3.635789473684211e-06,
-      "loss": 0.1861,
-      "step": 8275
-    },
-    {
-      "epoch": 13.696944673823287,
-      "grad_norm": 4.6280293464660645,
-      "learning_rate": 3.5831578947368422e-06,
-      "loss": 0.1936,
-      "step": 8300
-    },
-    {
-      "epoch": 13.738232865400496,
-      "grad_norm": 5.779093265533447,
-      "learning_rate": 3.5305263157894743e-06,
-      "loss": 0.1899,
-      "step": 8325
-    },
-    {
-      "epoch": 13.779521056977705,
-      "grad_norm": 3.84360933303833,
-      "learning_rate": 3.4778947368421055e-06,
-      "loss": 0.1937,
-      "step": 8350
-    },
-    {
-      "epoch": 13.820809248554914,
-      "grad_norm": 5.995066165924072,
-      "learning_rate": 3.425263157894737e-06,
-      "loss": 0.1976,
-      "step": 8375
-    },
-    {
-      "epoch": 13.862097440132121,
-      "grad_norm": 5.045938491821289,
-      "learning_rate": 3.3726315789473683e-06,
-      "loss": 0.177,
-      "step": 8400
-    },
-    {
-      "epoch": 13.90338563170933,
-      "grad_norm": 4.3831658363342285,
-      "learning_rate": 3.3200000000000004e-06,
-      "loss": 0.1831,
-      "step": 8425
-    },
-    {
-      "epoch": 13.94467382328654,
-      "grad_norm": 5.6045002937316895,
-      "learning_rate": 3.267368421052632e-06,
-      "loss": 0.177,
-      "step": 8450
-    },
-    {
-      "epoch": 13.985962014863748,
-      "grad_norm": 5.313602447509766,
-      "learning_rate": 3.2147368421052633e-06,
-      "loss": 0.2106,
-      "step": 8475
-    },
-    {
-      "epoch": 14.026424442609414,
-      "grad_norm": 4.277268409729004,
-      "learning_rate": 3.1621052631578953e-06,
-      "loss": 0.1697,
-      "step": 8500
-    },
-    {
-      "epoch": 14.067712634186623,
-      "grad_norm": 4.43281364440918,
-      "learning_rate": 3.1094736842105265e-06,
-      "loss": 0.1655,
-      "step": 8525
-    },
-    {
-      "epoch": 14.109000825763832,
-      "grad_norm": 5.5066304206848145,
-      "learning_rate": 3.056842105263158e-06,
-      "loss": 0.1611,
-      "step": 8550
-    },
-    {
-      "epoch": 14.15028901734104,
-      "grad_norm": 5.53204345703125,
-      "learning_rate": 3.0042105263157894e-06,
-      "loss": 0.1808,
-      "step": 8575
-    },
-    {
-      "epoch": 14.191577208918249,
-      "grad_norm": 4.399189472198486,
-      "learning_rate": 2.9515789473684214e-06,
-      "loss": 0.1487,
-      "step": 8600
-    },
-    {
-      "epoch": 14.232865400495458,
-      "grad_norm": 4.710522174835205,
-      "learning_rate": 2.8989473684210526e-06,
-      "loss": 0.1684,
-      "step": 8625
-    },
-    {
-      "epoch": 14.274153592072667,
-      "grad_norm": 4.319856643676758,
-      "learning_rate": 2.8463157894736843e-06,
-      "loss": 0.1626,
-      "step": 8650
-    },
-    {
-      "epoch": 14.315441783649876,
-      "grad_norm": 5.691439628601074,
-      "learning_rate": 2.7936842105263163e-06,
-      "loss": 0.1734,
-      "step": 8675
-    },
-    {
-      "epoch": 14.356729975227084,
-      "grad_norm": 5.005030632019043,
-      "learning_rate": 2.7410526315789476e-06,
-      "loss": 0.1627,
-      "step": 8700
-    },
-    {
-      "epoch": 14.398018166804293,
-      "grad_norm": 4.130620002746582,
-      "learning_rate": 2.688421052631579e-06,
-      "loss": 0.1718,
-      "step": 8725
-    },
-    {
-      "epoch": 14.439306358381502,
-      "grad_norm": 3.437147617340088,
-      "learning_rate": 2.635789473684211e-06,
-      "loss": 0.1756,
-      "step": 8750
-    },
-    {
-      "epoch": 14.480594549958711,
-      "grad_norm": 4.4854044914245605,
-      "learning_rate": 2.5831578947368425e-06,
-      "loss": 0.1671,
-      "step": 8775
-    },
-    {
-      "epoch": 14.52188274153592,
-      "grad_norm": 5.259097099304199,
-      "learning_rate": 2.5305263157894737e-06,
-      "loss": 0.1782,
-      "step": 8800
-    },
-    {
-      "epoch": 14.56317093311313,
-      "grad_norm": 3.7995481491088867,
-      "learning_rate": 2.4778947368421053e-06,
-      "loss": 0.1684,
-      "step": 8825
-    },
-    {
-      "epoch": 14.604459124690338,
-      "grad_norm": 4.331813335418701,
-      "learning_rate": 2.425263157894737e-06,
-      "loss": 0.1757,
-      "step": 8850
-    },
-    {
-      "epoch": 14.645747316267547,
-      "grad_norm": 5.367282867431641,
-      "learning_rate": 2.3726315789473686e-06,
-      "loss": 0.1796,
-      "step": 8875
-    },
-    {
-      "epoch": 14.687035507844756,
-      "grad_norm": 5.606546401977539,
-      "learning_rate": 2.3200000000000002e-06,
-      "loss": 0.1911,
-      "step": 8900
-    },
-    {
-      "epoch": 14.728323699421965,
-      "grad_norm": 3.9387214183807373,
-      "learning_rate": 2.267368421052632e-06,
-      "loss": 0.1666,
-      "step": 8925
-    },
-    {
-      "epoch": 14.769611890999174,
-      "grad_norm": 4.426852703094482,
-      "learning_rate": 2.2147368421052635e-06,
-      "loss": 0.1717,
-      "step": 8950
-    },
-    {
-      "epoch": 14.810900082576383,
-      "grad_norm": 3.4610788822174072,
-      "learning_rate": 2.1621052631578947e-06,
-      "loss": 0.168,
-      "step": 8975
-    },
-    {
-      "epoch": 14.852188274153592,
-      "grad_norm": 4.5235676765441895,
-      "learning_rate": 2.1094736842105264e-06,
-      "loss": 0.1425,
-      "step": 9000
-    },
-    {
-      "epoch": 14.852188274153592,
-      "eval_cer": 48.44840828585512,
-      "eval_loss": 1.142202377319336,
-      "eval_runtime": 701.7243,
-      "eval_samples_per_second": 15.079,
-      "eval_steps_per_second": 1.257,
-      "eval_wer": 96.61480433757662,
-      "step": 9000
-    },
-    {
-      "epoch": 14.893476465730801,
-      "grad_norm": 4.106043815612793,
-      "learning_rate": 2.058947368421053e-06,
-      "loss": 0.1853,
-      "step": 9025
-    },
-    {
-      "epoch": 14.93476465730801,
-      "grad_norm": 4.604458808898926,
-      "learning_rate": 2.0063157894736843e-06,
-      "loss": 0.1725,
-      "step": 9050
-    },
-    {
-      "epoch": 14.97605284888522,
-      "grad_norm": 5.01749324798584,
-      "learning_rate": 1.953684210526316e-06,
-      "loss": 0.1566,
-      "step": 9075
-    },
-    {
-      "epoch": 15.016515276630884,
-      "grad_norm": 3.69610857963562,
-      "learning_rate": 1.9010526315789476e-06,
-      "loss": 0.1791,
-      "step": 9100
-    },
-    {
-      "epoch": 15.057803468208093,
-      "grad_norm": 3.566075563430786,
-      "learning_rate": 1.848421052631579e-06,
-      "loss": 0.1626,
-      "step": 9125
-    },
-    {
-      "epoch": 15.099091659785302,
-      "grad_norm": 3.8838043212890625,
-      "learning_rate": 1.7957894736842108e-06,
-      "loss": 0.1507,
-      "step": 9150
-    },
-    {
-      "epoch": 15.14037985136251,
-      "grad_norm": 4.462072372436523,
-      "learning_rate": 1.7431578947368423e-06,
-      "loss": 0.1682,
-      "step": 9175
-    },
-    {
-      "epoch": 15.18166804293972,
-      "grad_norm": 5.543285846710205,
-      "learning_rate": 1.6905263157894739e-06,
-      "loss": 0.141,
-      "step": 9200
-    },
-    {
-      "epoch": 15.222956234516928,
-      "grad_norm": 4.328714847564697,
-      "learning_rate": 1.6378947368421053e-06,
-      "loss": 0.1747,
-      "step": 9225
-    },
-    {
-      "epoch": 15.264244426094137,
-      "grad_norm": 3.924700975418091,
-      "learning_rate": 1.585263157894737e-06,
-      "loss": 0.1727,
-      "step": 9250
-    },
-    {
-      "epoch": 15.305532617671346,
-      "grad_norm": 4.647414207458496,
-      "learning_rate": 1.5326315789473686e-06,
-      "loss": 0.1512,
-      "step": 9275
-    },
-    {
-      "epoch": 15.346820809248555,
-      "grad_norm": 3.2526192665100098,
-      "learning_rate": 1.48e-06,
-      "loss": 0.1521,
-      "step": 9300
-    },
-    {
-      "epoch": 15.388109000825764,
-      "grad_norm": 3.697683334350586,
-      "learning_rate": 1.4273684210526317e-06,
-      "loss": 0.1498,
-      "step": 9325
-    },
-    {
-      "epoch": 15.429397192402973,
-      "grad_norm": 3.709627866744995,
-      "learning_rate": 1.374736842105263e-06,
-      "loss": 0.1654,
-      "step": 9350
-    },
-    {
-      "epoch": 15.470685383980182,
-      "grad_norm": 3.7767739295959473,
-      "learning_rate": 1.322105263157895e-06,
-      "loss": 0.1466,
-      "step": 9375
-    },
-    {
-      "epoch": 15.511973575557391,
-      "grad_norm": 3.6882431507110596,
-      "learning_rate": 1.2694736842105266e-06,
-      "loss": 0.1496,
-      "step": 9400
-    },
-    {
-      "epoch": 15.5532617671346,
-      "grad_norm": 3.9242100715637207,
-      "learning_rate": 1.216842105263158e-06,
-      "loss": 0.1491,
-      "step": 9425
-    },
-    {
-      "epoch": 15.59454995871181,
-      "grad_norm": 5.024509429931641,
-      "learning_rate": 1.1642105263157896e-06,
-      "loss": 0.1549,
-      "step": 9450
-    },
-    {
-      "epoch": 15.635838150289018,
-      "grad_norm": 4.048088550567627,
-      "learning_rate": 1.1115789473684213e-06,
-      "loss": 0.1564,
-      "step": 9475
-    },
-    {
-      "epoch": 15.677126341866225,
-      "grad_norm": 4.535757541656494,
-      "learning_rate": 1.0589473684210527e-06,
-      "loss": 0.1548,
-      "step": 9500
-    },
-    {
-      "epoch": 15.718414533443434,
-      "grad_norm": 4.47163200378418,
-      "learning_rate": 1.0063157894736843e-06,
-      "loss": 0.1521,
-      "step": 9525
-    },
-    {
-      "epoch": 15.759702725020643,
-      "grad_norm": 3.4826717376708984,
-      "learning_rate": 9.536842105263158e-07,
-      "loss": 0.151,
-      "step": 9550
-    },
-    {
-      "epoch": 15.800990916597852,
-      "grad_norm": 3.6962897777557373,
-      "learning_rate": 9.010526315789474e-07,
-      "loss": 0.1611,
-      "step": 9575
-    },
-    {
-      "epoch": 15.842279108175061,
-      "grad_norm": 3.6767818927764893,
-      "learning_rate": 8.48421052631579e-07,
-      "loss": 0.1594,
-      "step": 9600
-    },
-    {
-      "epoch": 15.88356729975227,
-      "grad_norm": 2.950598955154419,
-      "learning_rate": 7.957894736842107e-07,
-      "loss": 0.1583,
-      "step": 9625
-    },
-    {
-      "epoch": 15.92485549132948,
-      "grad_norm": 4.535677909851074,
-      "learning_rate": 7.431578947368422e-07,
-      "loss": 0.1743,
-      "step": 9650
-    },
-    {
-      "epoch": 15.966143682906688,
-      "grad_norm": 3.578261613845825,
-      "learning_rate": 6.905263157894737e-07,
-      "loss": 0.1279,
-      "step": 9675
-    },
-    {
-      "epoch": 16.006606110652353,
-      "grad_norm": 3.0115976333618164,
-      "learning_rate": 6.378947368421053e-07,
-      "loss": 0.1442,
-      "step": 9700
-    },
-    {
-      "epoch": 16.04789430222956,
-      "grad_norm": 4.302647590637207,
-      "learning_rate": 5.852631578947369e-07,
-      "loss": 0.1524,
-      "step": 9725
-    },
-    {
-      "epoch": 16.08918249380677,
-      "grad_norm": 3.516667366027832,
-      "learning_rate": 5.326315789473684e-07,
-      "loss": 0.1431,
-      "step": 9750
-    },
-    {
-      "epoch": 16.13047068538398,
-      "grad_norm": 3.802489757537842,
-      "learning_rate": 4.800000000000001e-07,
-      "loss": 0.1607,
-      "step": 9775
-    },
-    {
-      "epoch": 16.17175887696119,
-      "grad_norm": 2.9078941345214844,
-      "learning_rate": 4.273684210526316e-07,
-      "loss": 0.134,
-      "step": 9800
-    },
-    {
-      "epoch": 16.213047068538398,
-      "grad_norm": 3.3042197227478027,
-      "learning_rate": 3.7473684210526323e-07,
-      "loss": 0.1614,
-      "step": 9825
-    },
-    {
-      "epoch": 16.254335260115607,
-      "grad_norm": 4.696882724761963,
-      "learning_rate": 3.2210526315789476e-07,
-      "loss": 0.1379,
-      "step": 9850
-    },
-    {
-      "epoch": 16.295623451692816,
-      "grad_norm": 4.522494316101074,
-      "learning_rate": 2.6947368421052635e-07,
-      "loss": 0.1586,
-      "step": 9875
-    },
-    {
-      "epoch": 16.336911643270025,
-      "grad_norm": 4.257038593292236,
-      "learning_rate": 2.168421052631579e-07,
-      "loss": 0.1423,
-      "step": 9900
-    },
-    {
-      "epoch": 16.378199834847234,
-      "grad_norm": 4.159156799316406,
-      "learning_rate": 1.642105263157895e-07,
-      "loss": 0.1617,
-      "step": 9925
-    },
-    {
-      "epoch": 16.419488026424442,
-      "grad_norm": 4.338253974914551,
-      "learning_rate": 1.1157894736842106e-07,
-      "loss": 0.1597,
-      "step": 9950
-    },
-    {
-      "epoch": 16.46077621800165,
-      "grad_norm": 5.437859058380127,
-      "learning_rate": 5.8947368421052637e-08,
-      "loss": 0.1629,
-      "step": 9975
-    },
-    {
-      "epoch": 16.50206440957886,
-      "grad_norm": 4.178699970245361,
-      "learning_rate": 6.315789473684211e-09,
-      "loss": 0.161,
-      "step": 10000
-    },
-    {
-      "epoch": 16.50206440957886,
-      "eval_cer": 49.64348354407163,
-      "eval_loss": 1.1519368886947632,
-      "eval_runtime": 708.8725,
-      "eval_samples_per_second": 14.927,
-      "eval_steps_per_second": 1.244,
-      "eval_wer": 96.77510608203677,
-      "step": 10000
     }
   ],
   "logging_steps": 25,
-  "max_steps": 10000,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 17,
   "save_steps": 1000,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -2921,13 +311,13 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.949150849531904e+19,
-  "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null
 }

 {
+  "best_metric": 99.20792079207921,
+  "best_model_checkpoint": "./iteboshi_temp/checkpoint-1000",
+  "epoch": 1.1013215859030836,
   "eval_steps": 1000,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "epoch": 0.02753303964757709,
+      "grad_norm": 8.593878746032715,
       "learning_rate": 1.0000000000000002e-06,
+      "loss": 11.2184,
       "step": 25
     },
     {
+      "epoch": 0.05506607929515418,
+      "grad_norm": 5.720788955688477,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 9.9763,
       "step": 50
     },
     {
+      "epoch": 0.08259911894273128,
+      "grad_norm": 3.1753361225128174,
+      "learning_rate": 3e-06,
+      "loss": 7.2986,
       "step": 75
     },
     {
+      "epoch": 0.11013215859030837,
+      "grad_norm": 1.9015727043151855,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 5.6306,
       "step": 100
     },
     {
+      "epoch": 0.13766519823788545,
+      "grad_norm": 1.7933436632156372,
+      "learning_rate": 5e-06,
+      "loss": 4.7211,
       "step": 125
     },
     {
+      "epoch": 0.16519823788546256,
+      "grad_norm": 1.9143211841583252,
+      "learning_rate": 6e-06,
+      "loss": 4.1871,
       "step": 150
     },
     {
+      "epoch": 0.19273127753303965,
+      "grad_norm": 1.8120731115341187,
+      "learning_rate": 7e-06,
+      "loss": 3.728,
       "step": 175
     },
     {
+      "epoch": 0.22026431718061673,
+      "grad_norm": 1.5976663827896118,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.3999,
       "step": 200
     },
     {
+      "epoch": 0.24779735682819384,
+      "grad_norm": 1.4841374158859253,
+      "learning_rate": 9e-06,
+      "loss": 3.1248,
       "step": 225
     },
     {
+      "epoch": 0.2753303964757709,
+      "grad_norm": 1.571273922920227,
+      "learning_rate": 1e-05,
+      "loss": 2.9023,
       "step": 250
     },
     {
+      "epoch": 0.30286343612334804,
+      "grad_norm": 1.5719149112701416,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 2.6609,
       "step": 275
     },
     {
+      "epoch": 0.3303964757709251,
+      "grad_norm": 1.4737190008163452,
+      "learning_rate": 1.2e-05,
+      "loss": 2.4913,
       "step": 300
     },
     {
+      "epoch": 0.3579295154185022,
+      "grad_norm": 1.5062530040740967,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 2.3478,
       "step": 325
     },
     {
+      "epoch": 0.3854625550660793,
+      "grad_norm": 1.5584601163864136,
+      "learning_rate": 1.4e-05,
+      "loss": 2.2405,
       "step": 350
     },
     {
+      "epoch": 0.4129955947136564,
+      "grad_norm": 1.5639300346374512,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.0632,
       "step": 375
     },
     {
+      "epoch": 0.44052863436123346,
+      "grad_norm": 1.574596881866455,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.9272,
       "step": 400
     },
     {
+      "epoch": 0.46806167400881055,
+      "grad_norm": 1.5253156423568726,
+      "learning_rate": 1.7e-05,
+      "loss": 1.8261,
       "step": 425
     },
     {
+      "epoch": 0.4955947136563877,
+      "grad_norm": 1.5775047540664673,
+      "learning_rate": 1.8e-05,
+      "loss": 1.7746,
       "step": 450
     },
     {
+      "epoch": 0.5231277533039648,
+      "grad_norm": 1.388596534729004,
+      "learning_rate": 1.9e-05,
+      "loss": 1.709,
       "step": 475
     },
     {
+      "epoch": 0.5506607929515418,
+      "grad_norm": 1.2958333492279053,
+      "learning_rate": 2e-05,
+      "loss": 1.6352,
       "step": 500
     },
     {
+      "epoch": 0.5781938325991189,
+      "grad_norm": 1.3782161474227905,
+      "learning_rate": 1.9974358974358975e-05,
+      "loss": 1.5945,
       "step": 525
     },
     {
+      "epoch": 0.6057268722466961,
+      "grad_norm": 1.3231383562088013,
+      "learning_rate": 1.994871794871795e-05,
+      "loss": 1.5081,
       "step": 550
     },
     {
+      "epoch": 0.6332599118942731,
+      "grad_norm": 1.4640569686889648,
+      "learning_rate": 1.9923076923076926e-05,
+      "loss": 1.4445,
       "step": 575
     },
     {
+      "epoch": 0.6607929515418502,
+      "grad_norm": 1.2492103576660156,
+      "learning_rate": 1.98974358974359e-05,
+      "loss": 1.4051,
       "step": 600
     },
     {
+      "epoch": 0.6883259911894273,
+      "grad_norm": 1.7467623949050903,
+      "learning_rate": 1.9871794871794873e-05,
+      "loss": 1.3562,
       "step": 625
     },
     {
+      "epoch": 0.7158590308370044,
+      "grad_norm": 1.420554757118225,
+      "learning_rate": 1.9846153846153847e-05,
+      "loss": 1.3596,
       "step": 650
     },
     {
+      "epoch": 0.7433920704845814,
+      "grad_norm": 1.239926815032959,
+      "learning_rate": 1.9820512820512824e-05,
+      "loss": 1.3058,
       "step": 675
     },
     {
+      "epoch": 0.7709251101321586,
+      "grad_norm": 1.1721984148025513,
+      "learning_rate": 1.9794871794871798e-05,
+      "loss": 1.2863,
       "step": 700
     },
     {
+      "epoch": 0.7984581497797357,
+      "grad_norm": 1.3416831493377686,
+      "learning_rate": 1.976923076923077e-05,
+      "loss": 1.3276,
       "step": 725
     },
     {
+      "epoch": 0.8259911894273128,
+      "grad_norm": 1.4568818807601929,
+      "learning_rate": 1.9743589743589745e-05,
+      "loss": 1.3027,
       "step": 750
     },
     {
+      "epoch": 0.8535242290748899,
+      "grad_norm": 1.4908838272094727,
+      "learning_rate": 1.9717948717948722e-05,
+      "loss": 1.2134,
       "step": 775
     },
     {
+      "epoch": 0.8810572687224669,
+      "grad_norm": 1.3530240058898926,
+      "learning_rate": 1.9692307692307696e-05,
+      "loss": 1.2212,
       "step": 800
     },
     {
+      "epoch": 0.9085903083700441,
+      "grad_norm": 1.1275429725646973,
+      "learning_rate": 1.9666666666666666e-05,
+      "loss": 1.1196,
       "step": 825
     },
     {
+      "epoch": 0.9361233480176211,
+      "grad_norm": 1.3054031133651733,
+      "learning_rate": 1.9641025641025643e-05,
+      "loss": 1.14,
       "step": 850
     },
     {
+      "epoch": 0.9636563876651982,
+      "grad_norm": 1.0485919713974,
+      "learning_rate": 1.9615384615384617e-05,
+      "loss": 1.1557,
       "step": 875
     },
     {
+      "epoch": 0.9911894273127754,
+      "grad_norm": 1.1853173971176147,
+      "learning_rate": 1.958974358974359e-05,
+      "loss": 1.1259,
       "step": 900
     },
     {
+      "epoch": 1.0187224669603525,
+      "grad_norm": 1.0613934993743896,
+      "learning_rate": 1.9564102564102564e-05,
+      "loss": 1.0608,
       "step": 925
     },
     {
+      "epoch": 1.0462555066079295,
+      "grad_norm": 1.2642765045166016,
+      "learning_rate": 1.953846153846154e-05,
+      "loss": 0.9548,
       "step": 950
     },
     {
+      "epoch": 1.0737885462555066,
+      "grad_norm": 1.2651335000991821,
+      "learning_rate": 1.9512820512820515e-05,
+      "loss": 0.9568,
       "step": 975
     },
     {
+      "epoch": 1.1013215859030836,
+      "grad_norm": 1.0594816207885742,
+      "learning_rate": 1.9487179487179488e-05,
+      "loss": 0.9609,
       "step": 1000
     },
     {
+      "epoch": 1.1013215859030836,
+      "eval_cer": 98.0001834168262,
+      "eval_loss": 1.1190180778503418,
+      "eval_runtime": 1035.5852,
+      "eval_samples_per_second": 10.217,
+      "eval_steps_per_second": 2.555,
+      "eval_wer": 99.20792079207921,
       "step": 1000
     }
   ],
   "logging_steps": 25,
+  "max_steps": 20000,
   "num_input_tokens_seen": 0,
+  "num_train_epochs": 23,
   "save_steps": 1000,
   "stateful_callbacks": {
     "TrainerControl": {
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
+  "total_flos": 1.6881707400350925e+18,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8fe144e7bbecfefafbc5f7ba6e25af714f15b9643283e39c2a95c6ef7dcd775
-size 5560

 version https://git-lfs.github.com/spec/v1
+oid sha256:6af773437c2683442b487a292e99dfac19fe476b5315a9fe09845da921d84893
+size 6776

last-checkpoint/vocab.json CHANGED Viewed

@@ -314,7 +314,6 @@
   ";;": 35746,
   "<": 27,
   "</": 3433,
-  "<|endoftext|>": 50257,
   "=": 28,
   "=\"": 13114,
   "=\"#": 34106,

   ";;": 35746,
   "<": 27,
   "</": 3433,
   "=": 28,
   "=\"": 13114,
   "=\"#": 34106,

last-checkpoint/zero_to_fp32.py ADDED Viewed

	@@ -0,0 +1,760 @@

+#!/usr/bin/env python
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+# DeepSpeed Team
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+debug = 0
+# load to cpu
+device = torch.device('cpu')
+def atoi(text):
+    return int(text) if text.isdigit() else text
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+    return file
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+    return ckpt_files
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+        ds_version = state_dict.get(DS_VERSION, None)
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+    return zero_model_states
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+    if type(world_size) is list:
+        world_size = max(world_size)
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+    model_files = get_model_state_files(ds_checkpoint_dir)
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        state_dict[name] = frozen_param_fragments[name]
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+    return state_dict
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+    offset *= world_size
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+    return state_dict
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+    Returns:
+        - pytorch ``state_dict``
+    A typical usage might be ::
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    Returns:
+        - ``model`: modified model
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+    A typical usage might be ::
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+    return model
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+    debug = args.debug
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)