master-base-pretrained-wiki / trainer_state.json
lx865712528's picture
add ckpts
932f4d6
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 7.61392489388835,
"global_step": 80000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"learning_rate": 7.109546016941087e-06,
"loss": 49.9771,
"step": 500
},
{
"epoch": 0.1,
"learning_rate": 1.4247644427524506e-05,
"loss": 43.393,
"step": 1000
},
{
"epoch": 0.14,
"learning_rate": 2.1385742838107926e-05,
"loss": 39.2346,
"step": 1500
},
{
"epoch": 0.19,
"learning_rate": 2.852384124869135e-05,
"loss": 35.6806,
"step": 2000
},
{
"epoch": 0.24,
"learning_rate": 3.566193965927477e-05,
"loss": 33.5102,
"step": 2500
},
{
"epoch": 0.29,
"learning_rate": 4.280003806985819e-05,
"loss": 32.3278,
"step": 3000
},
{
"epoch": 0.33,
"learning_rate": 4.993813648044161e-05,
"loss": 31.4953,
"step": 3500
},
{
"epoch": 0.38,
"learning_rate": 5.707623489102503e-05,
"loss": 30.816,
"step": 4000
},
{
"epoch": 0.43,
"learning_rate": 6.421433330160845e-05,
"loss": 30.252,
"step": 4500
},
{
"epoch": 0.48,
"learning_rate": 7.135243171219186e-05,
"loss": 29.7712,
"step": 5000
},
{
"epoch": 0.52,
"learning_rate": 7.849053012277528e-05,
"loss": 29.3302,
"step": 5500
},
{
"epoch": 0.57,
"learning_rate": 8.56286285333587e-05,
"loss": 28.9378,
"step": 6000
},
{
"epoch": 0.62,
"learning_rate": 9.276672694394213e-05,
"loss": 28.5842,
"step": 6500
},
{
"epoch": 0.67,
"learning_rate": 9.990482535452555e-05,
"loss": 28.2426,
"step": 7000
},
{
"epoch": 0.71,
"learning_rate": 0.00010704292376510896,
"loss": 27.9328,
"step": 7500
},
{
"epoch": 0.76,
"learning_rate": 0.00011416674597887122,
"loss": 27.6412,
"step": 8000
},
{
"epoch": 0.81,
"learning_rate": 0.00012129056819263346,
"loss": 27.364,
"step": 8500
},
{
"epoch": 0.86,
"learning_rate": 0.0001284286666032169,
"loss": 27.1143,
"step": 9000
},
{
"epoch": 0.9,
"learning_rate": 0.00013556676501380032,
"loss": 26.8555,
"step": 9500
},
{
"epoch": 0.95,
"learning_rate": 0.00014270486342438373,
"loss": 26.6034,
"step": 10000
},
{
"epoch": 1.0,
"learning_rate": 0.00014984296183496716,
"loss": 26.3698,
"step": 10500
},
{
"epoch": 1.05,
"learning_rate": 0.00015698106024555057,
"loss": 26.1622,
"step": 11000
},
{
"epoch": 1.09,
"learning_rate": 0.000164119158656134,
"loss": 25.9071,
"step": 11500
},
{
"epoch": 1.14,
"learning_rate": 0.0001712572570667174,
"loss": 25.7091,
"step": 12000
},
{
"epoch": 1.19,
"learning_rate": 0.0001783953554773008,
"loss": 25.5191,
"step": 12500
},
{
"epoch": 1.24,
"learning_rate": 0.00018553345388788427,
"loss": 25.3345,
"step": 13000
},
{
"epoch": 1.28,
"learning_rate": 0.0001926572761016465,
"loss": 25.1661,
"step": 13500
},
{
"epoch": 1.33,
"learning_rate": 0.0001997953745122299,
"loss": 25.0167,
"step": 14000
},
{
"epoch": 1.38,
"learning_rate": 0.00020693347292281334,
"loss": 24.8676,
"step": 14500
},
{
"epoch": 1.43,
"learning_rate": 0.00021407157133339675,
"loss": 24.7221,
"step": 15000
},
{
"epoch": 1.48,
"learning_rate": 0.00022119539354715904,
"loss": 24.5844,
"step": 15500
},
{
"epoch": 1.52,
"learning_rate": 0.00022831921576092128,
"loss": 24.4609,
"step": 16000
},
{
"epoch": 1.57,
"learning_rate": 0.00023545731417150468,
"loss": 24.3188,
"step": 16500
},
{
"epoch": 1.62,
"learning_rate": 0.0002425954125820881,
"loss": 24.1855,
"step": 17000
},
{
"epoch": 1.67,
"learning_rate": 0.0002497049585990292,
"loss": 24.0573,
"step": 17500
},
{
"epoch": 1.71,
"learning_rate": 0.0002568430570096126,
"loss": 23.9433,
"step": 18000
},
{
"epoch": 1.76,
"learning_rate": 0.000263981155420196,
"loss": 23.8441,
"step": 18500
},
{
"epoch": 1.81,
"learning_rate": 0.0002711192538307794,
"loss": 23.7344,
"step": 19000
},
{
"epoch": 1.86,
"learning_rate": 0.0002782573522413629,
"loss": 23.6054,
"step": 19500
},
{
"epoch": 1.9,
"learning_rate": 0.0002853811744551251,
"loss": 23.5031,
"step": 20000
},
{
"epoch": 1.95,
"learning_rate": 0.0002925192728657086,
"loss": 23.409,
"step": 20500
},
{
"epoch": 2.0,
"learning_rate": 0.000299657371276292,
"loss": 23.2973,
"step": 21000
},
{
"epoch": 2.05,
"learning_rate": 0.00029924653405666063,
"loss": 23.1983,
"step": 21500
},
{
"epoch": 2.09,
"learning_rate": 0.00029845341201104026,
"loss": 23.0667,
"step": 22000
},
{
"epoch": 2.14,
"learning_rate": 0.00029766028996541983,
"loss": 22.9586,
"step": 22500
},
{
"epoch": 2.19,
"learning_rate": 0.00029686716791979946,
"loss": 22.8611,
"step": 23000
},
{
"epoch": 2.24,
"learning_rate": 0.0002960740458741791,
"loss": 22.7729,
"step": 23500
},
{
"epoch": 2.28,
"learning_rate": 0.0002952809238285587,
"loss": 22.6924,
"step": 24000
},
{
"epoch": 2.33,
"learning_rate": 0.00029448780178293834,
"loss": 22.6076,
"step": 24500
},
{
"epoch": 2.38,
"learning_rate": 0.00029369467973731797,
"loss": 22.536,
"step": 25000
},
{
"epoch": 2.43,
"learning_rate": 0.0002929015576916976,
"loss": 22.4573,
"step": 25500
},
{
"epoch": 2.47,
"learning_rate": 0.00029210843564607717,
"loss": 22.3945,
"step": 26000
},
{
"epoch": 2.52,
"learning_rate": 0.0002913153136004568,
"loss": 22.3224,
"step": 26500
},
{
"epoch": 2.57,
"learning_rate": 0.0002905221915548364,
"loss": 22.2743,
"step": 27000
},
{
"epoch": 2.62,
"learning_rate": 0.00028972906950921605,
"loss": 22.2017,
"step": 27500
},
{
"epoch": 2.66,
"learning_rate": 0.0002889359474635957,
"loss": 22.1405,
"step": 28000
},
{
"epoch": 2.71,
"learning_rate": 0.0002881428254179753,
"loss": 22.0828,
"step": 28500
},
{
"epoch": 2.76,
"learning_rate": 0.00028734970337235494,
"loss": 22.0215,
"step": 29000
},
{
"epoch": 2.81,
"learning_rate": 0.00028655658132673457,
"loss": 21.9786,
"step": 29500
},
{
"epoch": 2.86,
"learning_rate": 0.0002857650455252054,
"loss": 21.9217,
"step": 30000
},
{
"epoch": 2.9,
"learning_rate": 0.0002849750959677675,
"loss": 21.8631,
"step": 30500
},
{
"epoch": 2.95,
"learning_rate": 0.00028418197392214713,
"loss": 21.8205,
"step": 31000
},
{
"epoch": 3.0,
"learning_rate": 0.00028338885187652676,
"loss": 21.7683,
"step": 31500
},
{
"epoch": 3.05,
"learning_rate": 0.0002825957298309064,
"loss": 21.7244,
"step": 32000
},
{
"epoch": 3.09,
"learning_rate": 0.00028180260778528596,
"loss": 21.6501,
"step": 32500
},
{
"epoch": 3.14,
"learning_rate": 0.0002810094857396656,
"loss": 21.6091,
"step": 33000
},
{
"epoch": 3.19,
"learning_rate": 0.00028021794993813643,
"loss": 21.5633,
"step": 33500
},
{
"epoch": 3.24,
"learning_rate": 0.0002794280003806986,
"loss": 21.521,
"step": 34000
},
{
"epoch": 3.28,
"learning_rate": 0.0002786348783350782,
"loss": 21.485,
"step": 34500
},
{
"epoch": 3.33,
"learning_rate": 0.0002778417562894578,
"loss": 21.4439,
"step": 35000
},
{
"epoch": 3.38,
"learning_rate": 0.0002770486342438374,
"loss": 21.3951,
"step": 35500
},
{
"epoch": 3.43,
"learning_rate": 0.00027625551219821704,
"loss": 21.3558,
"step": 36000
},
{
"epoch": 3.47,
"learning_rate": 0.00027546239015259667,
"loss": 21.3135,
"step": 36500
},
{
"epoch": 3.52,
"learning_rate": 0.0002746692681069763,
"loss": 21.2646,
"step": 37000
},
{
"epoch": 3.57,
"learning_rate": 0.0002738761460613559,
"loss": 21.2365,
"step": 37500
},
{
"epoch": 3.62,
"learning_rate": 0.00027308302401573555,
"loss": 21.2025,
"step": 38000
},
{
"epoch": 3.66,
"learning_rate": 0.00027228990197011513,
"loss": 21.156,
"step": 38500
},
{
"epoch": 3.71,
"learning_rate": 0.00027149677992449476,
"loss": 21.1298,
"step": 39000
},
{
"epoch": 3.76,
"learning_rate": 0.0002707036578788744,
"loss": 21.1058,
"step": 39500
},
{
"epoch": 3.81,
"learning_rate": 0.000269910535833254,
"loss": 21.0673,
"step": 40000
},
{
"epoch": 3.85,
"learning_rate": 0.00026911741378763364,
"loss": 21.0313,
"step": 40500
},
{
"epoch": 3.9,
"learning_rate": 0.00026832429174201327,
"loss": 21.003,
"step": 41000
},
{
"epoch": 3.95,
"learning_rate": 0.00026753116969639284,
"loss": 20.9636,
"step": 41500
},
{
"epoch": 4.0,
"learning_rate": 0.00026673804765077247,
"loss": 20.9453,
"step": 42000
},
{
"epoch": 4.04,
"learning_rate": 0.0002659449256051521,
"loss": 20.9264,
"step": 42500
},
{
"epoch": 4.09,
"learning_rate": 0.0002651518035595317,
"loss": 20.8611,
"step": 43000
},
{
"epoch": 4.14,
"learning_rate": 0.00026436026775800256,
"loss": 20.8391,
"step": 43500
},
{
"epoch": 4.19,
"learning_rate": 0.0002635671457123822,
"loss": 20.8082,
"step": 44000
},
{
"epoch": 4.24,
"learning_rate": 0.0002627740236667618,
"loss": 20.7882,
"step": 44500
},
{
"epoch": 4.28,
"learning_rate": 0.00026198090162114144,
"loss": 20.7546,
"step": 45000
},
{
"epoch": 4.33,
"learning_rate": 0.00026118777957552107,
"loss": 20.7187,
"step": 45500
},
{
"epoch": 4.38,
"learning_rate": 0.00026039465752990065,
"loss": 20.7079,
"step": 46000
},
{
"epoch": 4.43,
"learning_rate": 0.0002596047079724628,
"loss": 20.6731,
"step": 46500
},
{
"epoch": 4.47,
"learning_rate": 0.0002588115859268424,
"loss": 20.656,
"step": 47000
},
{
"epoch": 4.52,
"learning_rate": 0.000258018463881222,
"loss": 20.6342,
"step": 47500
},
{
"epoch": 4.57,
"learning_rate": 0.00025722534183560163,
"loss": 20.6155,
"step": 48000
},
{
"epoch": 4.62,
"learning_rate": 0.00025643380603407247,
"loss": 20.587,
"step": 48500
},
{
"epoch": 4.66,
"learning_rate": 0.0002556406839884521,
"loss": 20.5652,
"step": 49000
},
{
"epoch": 4.71,
"learning_rate": 0.0002548475619428317,
"loss": 20.5426,
"step": 49500
},
{
"epoch": 4.76,
"learning_rate": 0.00025405443989721135,
"loss": 20.5183,
"step": 50000
},
{
"epoch": 4.81,
"learning_rate": 0.000253261317851591,
"loss": 20.4988,
"step": 50500
},
{
"epoch": 4.85,
"learning_rate": 0.0002524681958059706,
"loss": 20.4794,
"step": 51000
},
{
"epoch": 4.9,
"learning_rate": 0.00025167507376035024,
"loss": 20.4558,
"step": 51500
},
{
"epoch": 4.95,
"learning_rate": 0.00025088195171472986,
"loss": 20.4292,
"step": 52000
},
{
"epoch": 5.0,
"learning_rate": 0.00025008882966910944,
"loss": 20.4047,
"step": 52500
},
{
"epoch": 5.04,
"learning_rate": 0.00024929888011167154,
"loss": 20.404,
"step": 53000
},
{
"epoch": 5.09,
"learning_rate": 0.00024850575806605117,
"loss": 20.3589,
"step": 53500
},
{
"epoch": 5.14,
"learning_rate": 0.00024771422226452206,
"loss": 20.3373,
"step": 54000
},
{
"epoch": 5.19,
"learning_rate": 0.0002469211002189017,
"loss": 20.3208,
"step": 54500
},
{
"epoch": 5.23,
"learning_rate": 0.00024612797817328126,
"loss": 20.2981,
"step": 55000
},
{
"epoch": 5.28,
"learning_rate": 0.0002453348561276609,
"loss": 20.2951,
"step": 55500
},
{
"epoch": 5.33,
"learning_rate": 0.0002445417340820405,
"loss": 20.2748,
"step": 56000
},
{
"epoch": 5.38,
"learning_rate": 0.00024374861203642015,
"loss": 20.2582,
"step": 56500
},
{
"epoch": 5.42,
"learning_rate": 0.00024295548999079977,
"loss": 20.2498,
"step": 57000
},
{
"epoch": 5.47,
"learning_rate": 0.0002421623679451794,
"loss": 20.2228,
"step": 57500
},
{
"epoch": 5.52,
"learning_rate": 0.00024136924589955903,
"loss": 20.2119,
"step": 58000
},
{
"epoch": 5.57,
"learning_rate": 0.0002405761238539386,
"loss": 20.1897,
"step": 58500
},
{
"epoch": 5.62,
"learning_rate": 0.00023978300180831823,
"loss": 20.1715,
"step": 59000
},
{
"epoch": 5.66,
"learning_rate": 0.00023898987976269786,
"loss": 20.1637,
"step": 59500
},
{
"epoch": 5.71,
"learning_rate": 0.00023819675771707748,
"loss": 20.1498,
"step": 60000
},
{
"epoch": 5.76,
"learning_rate": 0.0002374036356714571,
"loss": 20.1365,
"step": 60500
},
{
"epoch": 5.81,
"learning_rate": 0.00023661209986992798,
"loss": 20.119,
"step": 61000
},
{
"epoch": 5.85,
"learning_rate": 0.0002358189778243076,
"loss": 20.1109,
"step": 61500
},
{
"epoch": 5.9,
"learning_rate": 0.00023502585577868718,
"loss": 20.1085,
"step": 62000
},
{
"epoch": 5.95,
"learning_rate": 0.0002342327337330668,
"loss": 20.0777,
"step": 62500
},
{
"epoch": 6.0,
"learning_rate": 0.00023344278417562894,
"loss": 20.0649,
"step": 63000
},
{
"epoch": 6.04,
"learning_rate": 0.00023264966213000857,
"loss": 20.0717,
"step": 63500
},
{
"epoch": 6.09,
"learning_rate": 0.00023185654008438817,
"loss": 20.0345,
"step": 64000
},
{
"epoch": 6.14,
"learning_rate": 0.0002310634180387678,
"loss": 20.0282,
"step": 64500
},
{
"epoch": 6.19,
"learning_rate": 0.0002302702959931474,
"loss": 20.012,
"step": 65000
},
{
"epoch": 6.23,
"learning_rate": 0.00022947717394752702,
"loss": 20.0094,
"step": 65500
},
{
"epoch": 6.28,
"learning_rate": 0.00022868405190190665,
"loss": 19.9956,
"step": 66000
},
{
"epoch": 6.33,
"learning_rate": 0.00022789092985628628,
"loss": 19.9879,
"step": 66500
},
{
"epoch": 6.38,
"learning_rate": 0.00022710098029884838,
"loss": 19.9747,
"step": 67000
},
{
"epoch": 6.42,
"learning_rate": 0.000226307858253228,
"loss": 19.9557,
"step": 67500
},
{
"epoch": 6.47,
"learning_rate": 0.00022551473620760758,
"loss": 19.9602,
"step": 68000
},
{
"epoch": 6.52,
"learning_rate": 0.0002247216141619872,
"loss": 19.9466,
"step": 68500
},
{
"epoch": 6.57,
"learning_rate": 0.00022392849211636684,
"loss": 19.9366,
"step": 69000
},
{
"epoch": 6.61,
"learning_rate": 0.00022314171504711142,
"loss": 19.9531,
"step": 69500
},
{
"epoch": 6.66,
"learning_rate": 0.00022234859300149104,
"loss": 19.929,
"step": 70000
},
{
"epoch": 6.71,
"learning_rate": 0.00022155547095587067,
"loss": 19.9242,
"step": 70500
},
{
"epoch": 6.76,
"learning_rate": 0.0002207623489102503,
"loss": 19.9227,
"step": 71000
},
{
"epoch": 6.8,
"learning_rate": 0.0002199692268646299,
"loss": 19.9067,
"step": 71500
},
{
"epoch": 6.85,
"learning_rate": 0.00021917610481900953,
"loss": 19.8972,
"step": 72000
},
{
"epoch": 6.9,
"learning_rate": 0.00021838298277338916,
"loss": 19.8938,
"step": 72500
},
{
"epoch": 6.95,
"learning_rate": 0.00021758986072776878,
"loss": 19.8794,
"step": 73000
},
{
"epoch": 7.0,
"learning_rate": 0.00021679673868214838,
"loss": 19.8704,
"step": 73500
},
{
"epoch": 7.04,
"learning_rate": 0.000216003616636528,
"loss": 19.8757,
"step": 74000
},
{
"epoch": 7.09,
"learning_rate": 0.0002152104945909076,
"loss": 19.8342,
"step": 74500
},
{
"epoch": 7.14,
"learning_rate": 0.00021441737254528724,
"loss": 19.8257,
"step": 75000
},
{
"epoch": 7.19,
"learning_rate": 0.00021362425049966687,
"loss": 19.8177,
"step": 75500
},
{
"epoch": 7.23,
"learning_rate": 0.0002128311284540465,
"loss": 19.8072,
"step": 76000
},
{
"epoch": 7.28,
"learning_rate": 0.00021203800640842612,
"loss": 19.7952,
"step": 76500
},
{
"epoch": 7.33,
"learning_rate": 0.00021124488436280575,
"loss": 19.7894,
"step": 77000
},
{
"epoch": 7.38,
"learning_rate": 0.00021045652104945906,
"loss": 19.8001,
"step": 77500
},
{
"epoch": 7.42,
"learning_rate": 0.0002096633990038387,
"loss": 19.7767,
"step": 78000
},
{
"epoch": 7.47,
"learning_rate": 0.00020887027695821832,
"loss": 19.7795,
"step": 78500
},
{
"epoch": 7.52,
"learning_rate": 0.00020807715491259795,
"loss": 19.7661,
"step": 79000
},
{
"epoch": 7.57,
"learning_rate": 0.00020728561911106879,
"loss": 19.7486,
"step": 79500
},
{
"epoch": 7.61,
"learning_rate": 0.0002064924970654484,
"loss": 19.7425,
"step": 80000
}
],
"max_steps": 210140,
"num_train_epochs": 20,
"total_flos": 0.0,
"trial_name": null,
"trial_params": null
}