distilgpt2-multiprompt / trainer_state.json
pszemraj's picture
End of training
ddd029f
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9997409997409998,
"global_step": 1930,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.00015,
"loss": 2.1476,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 2.1726,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 0.00045,
"loss": 2.1825,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 0.0006,
"loss": 2.1711,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 0.000599989854771552,
"loss": 2.187,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 0.0005999594197723798,
"loss": 2.2129,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 0.0005999086970609497,
"loss": 2.1951,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 0.000599837690067885,
"loss": 2.219,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 0.0005997464035957336,
"loss": 2.1978,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 0.000599634843818643,
"loss": 2.2003,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 0.0005995030182819427,
"loss": 2.2148,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 0.0005993509359016338,
"loss": 2.2266,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 0.0005991786069637863,
"loss": 2.2008,
"step": 65
},
{
"epoch": 0.07,
"learning_rate": 0.0005989860431238432,
"loss": 2.2105,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 0.000598773257405832,
"loss": 2.203,
"step": 75
},
{
"epoch": 0.08,
"learning_rate": 0.0005985402642014843,
"loss": 2.2201,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 0.000598287079269262,
"loss": 2.2313,
"step": 85
},
{
"epoch": 0.09,
"learning_rate": 0.0005980137197332915,
"loss": 2.1925,
"step": 90
},
{
"epoch": 0.1,
"learning_rate": 0.0005977202040822059,
"loss": 2.2056,
"step": 95
},
{
"epoch": 0.1,
"learning_rate": 0.000597406552167894,
"loss": 2.2045,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 0.0005970727852041579,
"loss": 2.2218,
"step": 105
},
{
"epoch": 0.11,
"learning_rate": 0.0005967189257652783,
"loss": 2.2225,
"step": 110
},
{
"epoch": 0.12,
"learning_rate": 0.0005963449977844876,
"loss": 2.2218,
"step": 115
},
{
"epoch": 0.12,
"learning_rate": 0.0005959510265523509,
"loss": 2.1974,
"step": 120
},
{
"epoch": 0.13,
"learning_rate": 0.0005955370387150558,
"loss": 2.2206,
"step": 125
},
{
"epoch": 0.13,
"learning_rate": 0.0005951030622726105,
"loss": 2.1967,
"step": 130
},
{
"epoch": 0.14,
"learning_rate": 0.0005946491265769492,
"loss": 2.21,
"step": 135
},
{
"epoch": 0.15,
"learning_rate": 0.0005941752623299472,
"loss": 2.2199,
"step": 140
},
{
"epoch": 0.15,
"learning_rate": 0.0005936815015813451,
"loss": 2.2225,
"step": 145
},
{
"epoch": 0.16,
"learning_rate": 0.0005931678777265801,
"loss": 2.2023,
"step": 150
},
{
"epoch": 0.16,
"learning_rate": 0.0005926344255045277,
"loss": 2.1881,
"step": 155
},
{
"epoch": 0.17,
"learning_rate": 0.0005920811809951525,
"loss": 2.1933,
"step": 160
},
{
"epoch": 0.17,
"learning_rate": 0.0005915081816170671,
"loss": 2.2102,
"step": 165
},
{
"epoch": 0.18,
"learning_rate": 0.0005909154661250024,
"loss": 2.219,
"step": 170
},
{
"epoch": 0.18,
"learning_rate": 0.0005903030746071855,
"loss": 2.2166,
"step": 175
},
{
"epoch": 0.19,
"learning_rate": 0.0005896710484826284,
"loss": 2.2027,
"step": 180
},
{
"epoch": 0.19,
"learning_rate": 0.0005890194304983277,
"loss": 2.215,
"step": 185
},
{
"epoch": 0.2,
"learning_rate": 0.0005883482647263717,
"loss": 2.2242,
"step": 190
},
{
"epoch": 0.2,
"learning_rate": 0.0005876575965609614,
"loss": 2.1957,
"step": 195
},
{
"epoch": 0.21,
"learning_rate": 0.0005869474727153385,
"loss": 2.2131,
"step": 200
},
{
"epoch": 0.21,
"learning_rate": 0.0005862179412186275,
"loss": 2.222,
"step": 205
},
{
"epoch": 0.22,
"learning_rate": 0.0005854690514125865,
"loss": 2.213,
"step": 210
},
{
"epoch": 0.22,
"learning_rate": 0.0005847008539482696,
"loss": 2.2116,
"step": 215
},
{
"epoch": 0.23,
"learning_rate": 0.000583913400782602,
"loss": 2.2077,
"step": 220
},
{
"epoch": 0.23,
"learning_rate": 0.0005831067451748655,
"loss": 2.2131,
"step": 225
},
{
"epoch": 0.24,
"learning_rate": 0.0005822809416830963,
"loss": 2.1922,
"step": 230
},
{
"epoch": 0.24,
"learning_rate": 0.0005814360461603949,
"loss": 2.2152,
"step": 235
},
{
"epoch": 0.25,
"learning_rate": 0.0005805721157511485,
"loss": 2.2043,
"step": 240
},
{
"epoch": 0.25,
"learning_rate": 0.0005796892088871661,
"loss": 2.2169,
"step": 245
},
{
"epoch": 0.26,
"learning_rate": 0.0005787873852837267,
"loss": 2.2207,
"step": 250
},
{
"epoch": 0.26,
"learning_rate": 0.0005778667059355403,
"loss": 2.1908,
"step": 255
},
{
"epoch": 0.27,
"learning_rate": 0.0005769272331126221,
"loss": 2.2244,
"step": 260
},
{
"epoch": 0.27,
"learning_rate": 0.0005759690303560815,
"loss": 2.2172,
"step": 265
},
{
"epoch": 0.28,
"learning_rate": 0.0005749921624738244,
"loss": 2.2123,
"step": 270
},
{
"epoch": 0.28,
"learning_rate": 0.0005739966955361696,
"loss": 2.2207,
"step": 275
},
{
"epoch": 0.29,
"learning_rate": 0.0005729826968713804,
"loss": 2.2079,
"step": 280
},
{
"epoch": 0.3,
"learning_rate": 0.0005719502350611107,
"loss": 2.1984,
"step": 285
},
{
"epoch": 0.3,
"learning_rate": 0.0005708993799357668,
"loss": 2.2085,
"step": 290
},
{
"epoch": 0.31,
"learning_rate": 0.0005698302025697842,
"loss": 2.1944,
"step": 295
},
{
"epoch": 0.31,
"learning_rate": 0.0005687427752768203,
"loss": 2.207,
"step": 300
},
{
"epoch": 0.32,
"learning_rate": 0.0005676371716048639,
"loss": 2.1949,
"step": 305
},
{
"epoch": 0.32,
"learning_rate": 0.0005665134663312602,
"loss": 2.2151,
"step": 310
},
{
"epoch": 0.33,
"learning_rate": 0.0005653717354576544,
"loss": 2.2086,
"step": 315
},
{
"epoch": 0.33,
"learning_rate": 0.0005642120562048497,
"loss": 2.2219,
"step": 320
},
{
"epoch": 0.34,
"learning_rate": 0.000563034507007586,
"loss": 2.2198,
"step": 325
},
{
"epoch": 0.34,
"learning_rate": 0.000561839167509234,
"loss": 2.1897,
"step": 330
},
{
"epoch": 0.35,
"learning_rate": 0.0005606261185564088,
"loss": 2.1839,
"step": 335
},
{
"epoch": 0.35,
"learning_rate": 0.000559395442193502,
"loss": 2.2104,
"step": 340
},
{
"epoch": 0.36,
"learning_rate": 0.0005581472216571329,
"loss": 2.2147,
"step": 345
},
{
"epoch": 0.36,
"learning_rate": 0.0005568815413705178,
"loss": 2.2079,
"step": 350
},
{
"epoch": 0.37,
"learning_rate": 0.0005555984869377613,
"loss": 2.1798,
"step": 355
},
{
"epoch": 0.37,
"learning_rate": 0.0005542981451380654,
"loss": 2.2226,
"step": 360
},
{
"epoch": 0.38,
"learning_rate": 0.0005529806039198609,
"loss": 2.2157,
"step": 365
},
{
"epoch": 0.38,
"learning_rate": 0.0005516459523948589,
"loss": 2.1927,
"step": 370
},
{
"epoch": 0.39,
"learning_rate": 0.0005502942808320234,
"loss": 2.2048,
"step": 375
},
{
"epoch": 0.39,
"learning_rate": 0.0005489256806514665,
"loss": 2.1928,
"step": 380
},
{
"epoch": 0.4,
"learning_rate": 0.0005475402444182646,
"loss": 2.2055,
"step": 385
},
{
"epoch": 0.4,
"learning_rate": 0.0005461380658361984,
"loss": 2.2125,
"step": 390
},
{
"epoch": 0.41,
"learning_rate": 0.0005447192397414148,
"loss": 2.2053,
"step": 395
},
{
"epoch": 0.41,
"learning_rate": 0.0005432838620960128,
"loss": 2.188,
"step": 400
},
{
"epoch": 0.42,
"learning_rate": 0.0005418320299815534,
"loss": 2.2037,
"step": 405
},
{
"epoch": 0.42,
"learning_rate": 0.0005403638415924928,
"loss": 2.2026,
"step": 410
},
{
"epoch": 0.43,
"learning_rate": 0.0005388793962295418,
"loss": 2.1892,
"step": 415
},
{
"epoch": 0.44,
"learning_rate": 0.0005373787942929494,
"loss": 2.2138,
"step": 420
},
{
"epoch": 0.44,
"learning_rate": 0.0005358621372757119,
"loss": 2.2269,
"step": 425
},
{
"epoch": 0.45,
"learning_rate": 0.0005343295277567086,
"loss": 2.2143,
"step": 430
},
{
"epoch": 0.45,
"learning_rate": 0.0005327810693937642,
"loss": 2.209,
"step": 435
},
{
"epoch": 0.46,
"learning_rate": 0.0005312168669166378,
"loss": 2.2103,
"step": 440
},
{
"epoch": 0.46,
"learning_rate": 0.0005296370261199389,
"loss": 2.1948,
"step": 445
},
{
"epoch": 0.47,
"learning_rate": 0.000528041653855973,
"loss": 2.2023,
"step": 450
},
{
"epoch": 0.47,
"learning_rate": 0.0005264308580275137,
"loss": 2.1733,
"step": 455
},
{
"epoch": 0.48,
"learning_rate": 0.0005248047475805057,
"loss": 2.1756,
"step": 460
},
{
"epoch": 0.48,
"learning_rate": 0.0005231634324966954,
"loss": 2.2086,
"step": 465
},
{
"epoch": 0.49,
"learning_rate": 0.0005215070237861924,
"loss": 2.203,
"step": 470
},
{
"epoch": 0.49,
"learning_rate": 0.000519835633479962,
"loss": 2.1826,
"step": 475
},
{
"epoch": 0.5,
"learning_rate": 0.0005181493746222475,
"loss": 2.1921,
"step": 480
},
{
"epoch": 0.5,
"learning_rate": 0.0005164483612629244,
"loss": 2.1718,
"step": 485
},
{
"epoch": 0.51,
"learning_rate": 0.0005147327084497868,
"loss": 2.2043,
"step": 490
},
{
"epoch": 0.51,
"learning_rate": 0.0005130025322207663,
"loss": 2.2003,
"step": 495
},
{
"epoch": 0.52,
"learning_rate": 0.0005112579495960835,
"loss": 2.1715,
"step": 500
},
{
"epoch": 0.52,
"learning_rate": 0.0005094990785703337,
"loss": 2.1775,
"step": 505
},
{
"epoch": 0.53,
"learning_rate": 0.0005077260381045057,
"loss": 2.2061,
"step": 510
},
{
"epoch": 0.53,
"learning_rate": 0.0005059389481179369,
"loss": 2.1998,
"step": 515
},
{
"epoch": 0.54,
"learning_rate": 0.0005041379294802017,
"loss": 2.1776,
"step": 520
},
{
"epoch": 0.54,
"learning_rate": 0.0005023231040029368,
"loss": 2.1867,
"step": 525
},
{
"epoch": 0.55,
"learning_rate": 0.0005004945944316028,
"loss": 2.1742,
"step": 530
},
{
"epoch": 0.55,
"learning_rate": 0.0004986525244371818,
"loss": 2.1963,
"step": 535
},
{
"epoch": 0.56,
"learning_rate": 0.000496797018607813,
"loss": 2.179,
"step": 540
},
{
"epoch": 0.56,
"learning_rate": 0.0004949282024403667,
"loss": 2.1885,
"step": 545
},
{
"epoch": 0.57,
"learning_rate": 0.0004930462023319559,
"loss": 2.1649,
"step": 550
},
{
"epoch": 0.57,
"learning_rate": 0.0004911511455713875,
"loss": 2.1903,
"step": 555
},
{
"epoch": 0.58,
"learning_rate": 0.0004892431603305532,
"loss": 2.1838,
"step": 560
},
{
"epoch": 0.59,
"learning_rate": 0.0004873223756557606,
"loss": 2.1915,
"step": 565
},
{
"epoch": 0.59,
"learning_rate": 0.0004853889214590053,
"loss": 2.2185,
"step": 570
},
{
"epoch": 0.6,
"learning_rate": 0.000483442928509184,
"loss": 2.1799,
"step": 575
},
{
"epoch": 0.6,
"learning_rate": 0.00048148452842325027,
"loss": 2.1717,
"step": 580
},
{
"epoch": 0.61,
"learning_rate": 0.0004795138536573126,
"loss": 2.1903,
"step": 585
},
{
"epoch": 0.61,
"learning_rate": 0.0004775310374976755,
"loss": 2.1837,
"step": 590
},
{
"epoch": 0.62,
"learning_rate": 0.00047553621405182513,
"loss": 2.1972,
"step": 595
},
{
"epoch": 0.62,
"learning_rate": 0.0004735295182393587,
"loss": 2.1858,
"step": 600
},
{
"epoch": 0.63,
"learning_rate": 0.000471511085782859,
"loss": 2.1872,
"step": 605
},
{
"epoch": 0.63,
"learning_rate": 0.0004694810531987154,
"loss": 2.1875,
"step": 610
},
{
"epoch": 0.64,
"learning_rate": 0.0004674395577878898,
"loss": 2.1759,
"step": 615
},
{
"epoch": 0.64,
"learning_rate": 0.0004653867376266313,
"loss": 2.1846,
"step": 620
},
{
"epoch": 0.65,
"learning_rate": 0.00046332273155713633,
"loss": 2.1937,
"step": 625
},
{
"epoch": 0.65,
"learning_rate": 0.00046124767917815883,
"loss": 2.2121,
"step": 630
},
{
"epoch": 0.66,
"learning_rate": 0.00045916172083556846,
"loss": 2.1887,
"step": 635
},
{
"epoch": 0.66,
"learning_rate": 0.0004570649976128579,
"loss": 2.1752,
"step": 640
},
{
"epoch": 0.67,
"learning_rate": 0.0004549576513216011,
"loss": 2.1745,
"step": 645
},
{
"epoch": 0.67,
"learning_rate": 0.00045283982449186163,
"loss": 2.1859,
"step": 650
},
{
"epoch": 0.68,
"learning_rate": 0.00045071166036255285,
"loss": 2.1767,
"step": 655
},
{
"epoch": 0.68,
"learning_rate": 0.00044857330287174994,
"loss": 2.1665,
"step": 660
},
{
"epoch": 0.69,
"learning_rate": 0.00044642489664695445,
"loss": 2.1911,
"step": 665
},
{
"epoch": 0.69,
"learning_rate": 0.0004442665869953128,
"loss": 2.1772,
"step": 670
},
{
"epoch": 0.7,
"learning_rate": 0.00044209851989378816,
"loss": 2.1772,
"step": 675
},
{
"epoch": 0.7,
"learning_rate": 0.0004399208419792873,
"loss": 2.1752,
"step": 680
},
{
"epoch": 0.71,
"learning_rate": 0.00043773370053874316,
"loss": 2.1915,
"step": 685
},
{
"epoch": 0.71,
"learning_rate": 0.0004355372434991529,
"loss": 2.1685,
"step": 690
},
{
"epoch": 0.72,
"learning_rate": 0.0004333316194175727,
"loss": 2.196,
"step": 695
},
{
"epoch": 0.73,
"learning_rate": 0.00043111697747107044,
"loss": 2.17,
"step": 700
},
{
"epoch": 0.73,
"learning_rate": 0.0004288934674466359,
"loss": 2.1712,
"step": 705
},
{
"epoch": 0.74,
"learning_rate": 0.00042666123973105033,
"loss": 2.1902,
"step": 710
},
{
"epoch": 0.74,
"learning_rate": 0.0004244204453007143,
"loss": 2.1583,
"step": 715
},
{
"epoch": 0.75,
"learning_rate": 0.0004221712357114373,
"loss": 2.1927,
"step": 720
},
{
"epoch": 0.75,
"learning_rate": 0.0004199137630881866,
"loss": 2.154,
"step": 725
},
{
"epoch": 0.76,
"learning_rate": 0.0004176481801147988,
"loss": 2.1736,
"step": 730
},
{
"epoch": 0.76,
"learning_rate": 0.0004153746400236528,
"loss": 2.1706,
"step": 735
},
{
"epoch": 0.77,
"learning_rate": 0.0004130932965853059,
"loss": 2.1758,
"step": 740
},
{
"epoch": 0.77,
"learning_rate": 0.0004108043040980939,
"loss": 2.1842,
"step": 745
},
{
"epoch": 0.78,
"learning_rate": 0.0004085078173776946,
"loss": 2.1766,
"step": 750
},
{
"epoch": 0.78,
"learning_rate": 0.0004062039917466577,
"loss": 2.1855,
"step": 755
},
{
"epoch": 0.79,
"learning_rate": 0.00040389298302389844,
"loss": 2.1974,
"step": 760
},
{
"epoch": 0.79,
"learning_rate": 0.00040157494751415977,
"loss": 2.1611,
"step": 765
},
{
"epoch": 0.8,
"learning_rate": 0.0003992500419974405,
"loss": 2.1799,
"step": 770
},
{
"epoch": 0.8,
"learning_rate": 0.00039691842371839106,
"loss": 2.1736,
"step": 775
},
{
"epoch": 0.81,
"learning_rate": 0.0003945802503756788,
"loss": 2.1534,
"step": 780
},
{
"epoch": 0.81,
"learning_rate": 0.0003922356801113217,
"loss": 2.1655,
"step": 785
},
{
"epoch": 0.82,
"learning_rate": 0.00038988487149999284,
"loss": 2.1789,
"step": 790
},
{
"epoch": 0.82,
"learning_rate": 0.0003875279835382949,
"loss": 2.1745,
"step": 795
},
{
"epoch": 0.83,
"learning_rate": 0.0003851651756340065,
"loss": 2.1541,
"step": 800
},
{
"epoch": 0.83,
"learning_rate": 0.00038279660759530054,
"loss": 2.1576,
"step": 805
},
{
"epoch": 0.84,
"learning_rate": 0.00038042243961993637,
"loss": 2.1808,
"step": 810
},
{
"epoch": 0.84,
"learning_rate": 0.0003780428322844236,
"loss": 2.1623,
"step": 815
},
{
"epoch": 0.85,
"learning_rate": 0.0003756579465331627,
"loss": 2.1794,
"step": 820
},
{
"epoch": 0.85,
"learning_rate": 0.0003732679436675586,
"loss": 2.1674,
"step": 825
},
{
"epoch": 0.86,
"learning_rate": 0.0003708729853351117,
"loss": 2.1941,
"step": 830
},
{
"epoch": 0.87,
"learning_rate": 0.00036847323351848484,
"loss": 2.155,
"step": 835
},
{
"epoch": 0.87,
"learning_rate": 0.00036606885052454727,
"loss": 2.159,
"step": 840
},
{
"epoch": 0.88,
"learning_rate": 0.00036365999897339723,
"loss": 2.1824,
"step": 845
},
{
"epoch": 0.88,
"learning_rate": 0.00036124684178736346,
"loss": 2.1599,
"step": 850
},
{
"epoch": 0.89,
"learning_rate": 0.00035882954217998544,
"loss": 2.1567,
"step": 855
},
{
"epoch": 0.89,
"learning_rate": 0.00035640826364497473,
"loss": 2.1514,
"step": 860
},
{
"epoch": 0.9,
"learning_rate": 0.00035398316994515717,
"loss": 2.1693,
"step": 865
},
{
"epoch": 0.9,
"learning_rate": 0.0003515544251013968,
"loss": 2.1699,
"step": 870
},
{
"epoch": 0.91,
"learning_rate": 0.0003491221933815021,
"loss": 2.1672,
"step": 875
},
{
"epoch": 0.91,
"learning_rate": 0.000346686639289116,
"loss": 2.1637,
"step": 880
},
{
"epoch": 0.92,
"learning_rate": 0.0003442479275525895,
"loss": 2.1591,
"step": 885
},
{
"epoch": 0.92,
"learning_rate": 0.00034180622311384066,
"loss": 2.1701,
"step": 890
},
{
"epoch": 0.93,
"learning_rate": 0.00033936169111719824,
"loss": 2.1534,
"step": 895
},
{
"epoch": 0.93,
"learning_rate": 0.0003369144968982327,
"loss": 2.178,
"step": 900
},
{
"epoch": 0.94,
"learning_rate": 0.00033446480597257327,
"loss": 2.1516,
"step": 905
},
{
"epoch": 0.94,
"learning_rate": 0.0003320127840247139,
"loss": 2.1581,
"step": 910
},
{
"epoch": 0.95,
"learning_rate": 0.00032955859689680654,
"loss": 2.1609,
"step": 915
},
{
"epoch": 0.95,
"learning_rate": 0.00032710241057744527,
"loss": 2.1462,
"step": 920
},
{
"epoch": 0.96,
"learning_rate": 0.0003246443911904385,
"loss": 2.1576,
"step": 925
},
{
"epoch": 0.96,
"learning_rate": 0.0003221847049835746,
"loss": 2.1653,
"step": 930
},
{
"epoch": 0.97,
"learning_rate": 0.0003197235183173767,
"loss": 2.1584,
"step": 935
},
{
"epoch": 0.97,
"learning_rate": 0.0003172609976538513,
"loss": 2.1607,
"step": 940
},
{
"epoch": 0.98,
"learning_rate": 0.0003147973095452296,
"loss": 2.1645,
"step": 945
},
{
"epoch": 0.98,
"learning_rate": 0.00031233262062270293,
"loss": 2.1436,
"step": 950
},
{
"epoch": 0.99,
"learning_rate": 0.00030986709758515244,
"loss": 2.1427,
"step": 955
},
{
"epoch": 0.99,
"learning_rate": 0.00030740090718787445,
"loss": 2.1642,
"step": 960
},
{
"epoch": 1.0,
"learning_rate": 0.0003049342162313021,
"loss": 2.1637,
"step": 965
},
{
"epoch": 1.0,
"eval_loss": 2.0581421852111816,
"eval_runtime": 38.5822,
"eval_samples_per_second": 336.269,
"eval_steps_per_second": 42.04,
"step": 965
},
{
"epoch": 1.01,
"learning_rate": 0.00030246719154972406,
"loss": 2.2293,
"step": 970
},
{
"epoch": 1.01,
"learning_rate": 0.0003,
"loss": 2.1221,
"step": 975
},
{
"epoch": 1.02,
"learning_rate": 0.00029753280845027595,
"loss": 2.1087,
"step": 980
},
{
"epoch": 1.02,
"learning_rate": 0.00029506578376869785,
"loss": 2.1146,
"step": 985
},
{
"epoch": 1.03,
"learning_rate": 0.0002925990928121255,
"loss": 2.0984,
"step": 990
},
{
"epoch": 1.03,
"learning_rate": 0.00029013290241484757,
"loss": 2.1275,
"step": 995
},
{
"epoch": 1.04,
"learning_rate": 0.00028766737937729707,
"loss": 2.1265,
"step": 1000
},
{
"epoch": 1.04,
"learning_rate": 0.0002852026904547704,
"loss": 2.1184,
"step": 1005
},
{
"epoch": 1.05,
"learning_rate": 0.00028273900234614867,
"loss": 2.1145,
"step": 1010
},
{
"epoch": 1.05,
"learning_rate": 0.00028027648168262324,
"loss": 2.1283,
"step": 1015
},
{
"epoch": 1.06,
"learning_rate": 0.0002778152950164254,
"loss": 2.1153,
"step": 1020
},
{
"epoch": 1.06,
"learning_rate": 0.00027535560880956143,
"loss": 2.1191,
"step": 1025
},
{
"epoch": 1.07,
"learning_rate": 0.0002728975894225548,
"loss": 2.1281,
"step": 1030
},
{
"epoch": 1.07,
"learning_rate": 0.00027044140310319336,
"loss": 2.1366,
"step": 1035
},
{
"epoch": 1.08,
"learning_rate": 0.0002679872159752861,
"loss": 2.1116,
"step": 1040
},
{
"epoch": 1.08,
"learning_rate": 0.00026553519402742673,
"loss": 2.1241,
"step": 1045
},
{
"epoch": 1.09,
"learning_rate": 0.00026308550310176736,
"loss": 2.1125,
"step": 1050
},
{
"epoch": 1.09,
"learning_rate": 0.0002606383088828017,
"loss": 2.1216,
"step": 1055
},
{
"epoch": 1.1,
"learning_rate": 0.0002581937768861593,
"loss": 2.1337,
"step": 1060
},
{
"epoch": 1.1,
"learning_rate": 0.00025575207244741047,
"loss": 2.1294,
"step": 1065
},
{
"epoch": 1.11,
"learning_rate": 0.00025331336071088403,
"loss": 2.1172,
"step": 1070
},
{
"epoch": 1.11,
"learning_rate": 0.0002508778066184978,
"loss": 2.115,
"step": 1075
},
{
"epoch": 1.12,
"learning_rate": 0.00024844557489860314,
"loss": 2.1072,
"step": 1080
},
{
"epoch": 1.12,
"learning_rate": 0.0002460168300548428,
"loss": 2.1149,
"step": 1085
},
{
"epoch": 1.13,
"learning_rate": 0.00024359173635502525,
"loss": 2.1015,
"step": 1090
},
{
"epoch": 1.13,
"learning_rate": 0.0002411704578200146,
"loss": 2.1159,
"step": 1095
},
{
"epoch": 1.14,
"learning_rate": 0.00023875315821263648,
"loss": 2.1136,
"step": 1100
},
{
"epoch": 1.15,
"learning_rate": 0.00023634000102660274,
"loss": 2.0963,
"step": 1105
},
{
"epoch": 1.15,
"learning_rate": 0.00023393114947545276,
"loss": 2.1234,
"step": 1110
},
{
"epoch": 1.16,
"learning_rate": 0.0002315267664815152,
"loss": 2.1048,
"step": 1115
},
{
"epoch": 1.16,
"learning_rate": 0.00022912701466488823,
"loss": 2.1299,
"step": 1120
},
{
"epoch": 1.17,
"learning_rate": 0.00022673205633244145,
"loss": 2.1266,
"step": 1125
},
{
"epoch": 1.17,
"learning_rate": 0.00022434205346683728,
"loss": 2.0937,
"step": 1130
},
{
"epoch": 1.18,
"learning_rate": 0.00022195716771557632,
"loss": 2.0877,
"step": 1135
},
{
"epoch": 1.18,
"learning_rate": 0.00021957756038006366,
"loss": 2.1252,
"step": 1140
},
{
"epoch": 1.19,
"learning_rate": 0.00021720339240469935,
"loss": 2.1106,
"step": 1145
},
{
"epoch": 1.19,
"learning_rate": 0.00021483482436599353,
"loss": 2.121,
"step": 1150
},
{
"epoch": 1.2,
"learning_rate": 0.0002124720164617051,
"loss": 2.0997,
"step": 1155
},
{
"epoch": 1.2,
"learning_rate": 0.00021011512850000716,
"loss": 2.0981,
"step": 1160
},
{
"epoch": 1.21,
"learning_rate": 0.00020776431988867825,
"loss": 2.1222,
"step": 1165
},
{
"epoch": 1.21,
"learning_rate": 0.00020541974962432123,
"loss": 2.092,
"step": 1170
},
{
"epoch": 1.22,
"learning_rate": 0.00020308157628160894,
"loss": 2.1113,
"step": 1175
},
{
"epoch": 1.22,
"learning_rate": 0.00020074995800255954,
"loss": 2.1055,
"step": 1180
},
{
"epoch": 1.23,
"learning_rate": 0.00019842505248584018,
"loss": 2.113,
"step": 1185
},
{
"epoch": 1.23,
"learning_rate": 0.00019610701697610154,
"loss": 2.1106,
"step": 1190
},
{
"epoch": 1.24,
"learning_rate": 0.00019379600825334228,
"loss": 2.1075,
"step": 1195
},
{
"epoch": 1.24,
"learning_rate": 0.0001914921826223053,
"loss": 2.0971,
"step": 1200
},
{
"epoch": 1.25,
"learning_rate": 0.00018919569590190614,
"loss": 2.1218,
"step": 1205
},
{
"epoch": 1.25,
"learning_rate": 0.00018690670341469403,
"loss": 2.1019,
"step": 1210
},
{
"epoch": 1.26,
"learning_rate": 0.0001846253599763472,
"loss": 2.1028,
"step": 1215
},
{
"epoch": 1.26,
"learning_rate": 0.0001823518198852012,
"loss": 2.0939,
"step": 1220
},
{
"epoch": 1.27,
"learning_rate": 0.00018008623691181345,
"loss": 2.1144,
"step": 1225
},
{
"epoch": 1.27,
"learning_rate": 0.00017782876428856274,
"loss": 2.1009,
"step": 1230
},
{
"epoch": 1.28,
"learning_rate": 0.0001755795546992856,
"loss": 2.1048,
"step": 1235
},
{
"epoch": 1.28,
"learning_rate": 0.00017333876026894967,
"loss": 2.0939,
"step": 1240
},
{
"epoch": 1.29,
"learning_rate": 0.00017110653255336398,
"loss": 2.1108,
"step": 1245
},
{
"epoch": 1.3,
"learning_rate": 0.0001688830225289296,
"loss": 2.0995,
"step": 1250
},
{
"epoch": 1.3,
"learning_rate": 0.00016666838058242725,
"loss": 2.1223,
"step": 1255
},
{
"epoch": 1.31,
"learning_rate": 0.0001644627565008471,
"loss": 2.0965,
"step": 1260
},
{
"epoch": 1.31,
"learning_rate": 0.0001622662994612568,
"loss": 2.1283,
"step": 1265
},
{
"epoch": 1.32,
"learning_rate": 0.00016007915802071268,
"loss": 2.1075,
"step": 1270
},
{
"epoch": 1.32,
"learning_rate": 0.00015790148010621184,
"loss": 2.1087,
"step": 1275
},
{
"epoch": 1.33,
"learning_rate": 0.0001557334130046871,
"loss": 2.104,
"step": 1280
},
{
"epoch": 1.33,
"learning_rate": 0.00015357510335304542,
"loss": 2.1068,
"step": 1285
},
{
"epoch": 1.34,
"learning_rate": 0.00015142669712825006,
"loss": 2.1104,
"step": 1290
},
{
"epoch": 1.34,
"learning_rate": 0.00014928833963744712,
"loss": 2.1141,
"step": 1295
},
{
"epoch": 1.35,
"learning_rate": 0.0001471601755081384,
"loss": 2.1172,
"step": 1300
},
{
"epoch": 1.35,
"learning_rate": 0.0001450423486783989,
"loss": 2.1235,
"step": 1305
},
{
"epoch": 1.36,
"learning_rate": 0.0001429350023871421,
"loss": 2.093,
"step": 1310
},
{
"epoch": 1.36,
"learning_rate": 0.00014083827916443163,
"loss": 2.1106,
"step": 1315
},
{
"epoch": 1.37,
"learning_rate": 0.00013875232082184111,
"loss": 2.1041,
"step": 1320
},
{
"epoch": 1.37,
"learning_rate": 0.00013667726844286365,
"loss": 2.1167,
"step": 1325
},
{
"epoch": 1.38,
"learning_rate": 0.00013461326237336873,
"loss": 2.0964,
"step": 1330
},
{
"epoch": 1.38,
"learning_rate": 0.00013256044221211013,
"loss": 2.1024,
"step": 1335
},
{
"epoch": 1.39,
"learning_rate": 0.00013051894680128463,
"loss": 2.1037,
"step": 1340
},
{
"epoch": 1.39,
"learning_rate": 0.00012848891421714094,
"loss": 2.1098,
"step": 1345
},
{
"epoch": 1.4,
"learning_rate": 0.00012647048176064125,
"loss": 2.0885,
"step": 1350
},
{
"epoch": 1.4,
"learning_rate": 0.0001244637859481749,
"loss": 2.0902,
"step": 1355
},
{
"epoch": 1.41,
"learning_rate": 0.0001224689625023245,
"loss": 2.1136,
"step": 1360
},
{
"epoch": 1.41,
"learning_rate": 0.00012048614634268736,
"loss": 2.1067,
"step": 1365
},
{
"epoch": 1.42,
"learning_rate": 0.00011851547157674971,
"loss": 2.0993,
"step": 1370
},
{
"epoch": 1.42,
"learning_rate": 0.000116557071490816,
"loss": 2.1005,
"step": 1375
},
{
"epoch": 1.43,
"learning_rate": 0.00011461107854099468,
"loss": 2.1053,
"step": 1380
},
{
"epoch": 1.44,
"learning_rate": 0.00011267762434423939,
"loss": 2.1033,
"step": 1385
},
{
"epoch": 1.44,
"learning_rate": 0.00011075683966944673,
"loss": 2.095,
"step": 1390
},
{
"epoch": 1.45,
"learning_rate": 0.00010884885442861251,
"loss": 2.094,
"step": 1395
},
{
"epoch": 1.45,
"learning_rate": 0.00010695379766804407,
"loss": 2.0858,
"step": 1400
},
{
"epoch": 1.46,
"learning_rate": 0.00010507179755963326,
"loss": 2.095,
"step": 1405
},
{
"epoch": 1.46,
"learning_rate": 0.00010320298139218698,
"loss": 2.092,
"step": 1410
},
{
"epoch": 1.47,
"learning_rate": 0.00010134747556281819,
"loss": 2.1107,
"step": 1415
},
{
"epoch": 1.47,
"learning_rate": 9.950540556839719e-05,
"loss": 2.0923,
"step": 1420
},
{
"epoch": 1.48,
"learning_rate": 9.767689599706314e-05,
"loss": 2.09,
"step": 1425
},
{
"epoch": 1.48,
"learning_rate": 9.586207051979835e-05,
"loss": 2.0879,
"step": 1430
},
{
"epoch": 1.49,
"learning_rate": 9.40610518820631e-05,
"loss": 2.0912,
"step": 1435
},
{
"epoch": 1.49,
"learning_rate": 9.22739618954943e-05,
"loss": 2.1017,
"step": 1440
},
{
"epoch": 1.5,
"learning_rate": 9.050092142966632e-05,
"loss": 2.1142,
"step": 1445
},
{
"epoch": 1.5,
"learning_rate": 8.87420504039165e-05,
"loss": 2.0917,
"step": 1450
},
{
"epoch": 1.51,
"learning_rate": 8.69974677792336e-05,
"loss": 2.0781,
"step": 1455
},
{
"epoch": 1.51,
"learning_rate": 8.526729155021318e-05,
"loss": 2.09,
"step": 1460
},
{
"epoch": 1.52,
"learning_rate": 8.355163873707559e-05,
"loss": 2.0823,
"step": 1465
},
{
"epoch": 1.52,
"learning_rate": 8.185062537775248e-05,
"loss": 2.0936,
"step": 1470
},
{
"epoch": 1.53,
"learning_rate": 8.016436652003797e-05,
"loss": 2.0889,
"step": 1475
},
{
"epoch": 1.53,
"learning_rate": 7.849297621380765e-05,
"loss": 2.0967,
"step": 1480
},
{
"epoch": 1.54,
"learning_rate": 7.683656750330468e-05,
"loss": 2.0874,
"step": 1485
},
{
"epoch": 1.54,
"learning_rate": 7.519525241949431e-05,
"loss": 2.1044,
"step": 1490
},
{
"epoch": 1.55,
"learning_rate": 7.356914197248624e-05,
"loss": 2.0911,
"step": 1495
},
{
"epoch": 1.55,
"learning_rate": 7.195834614402702e-05,
"loss": 2.1034,
"step": 1500
},
{
"epoch": 1.56,
"learning_rate": 7.036297388006104e-05,
"loss": 2.0972,
"step": 1505
},
{
"epoch": 1.56,
"learning_rate": 6.878313308336217e-05,
"loss": 2.0769,
"step": 1510
},
{
"epoch": 1.57,
"learning_rate": 6.721893060623574e-05,
"loss": 2.0717,
"step": 1515
},
{
"epoch": 1.57,
"learning_rate": 6.567047224329133e-05,
"loss": 2.1128,
"step": 1520
},
{
"epoch": 1.58,
"learning_rate": 6.413786272428815e-05,
"loss": 2.096,
"step": 1525
},
{
"epoch": 1.59,
"learning_rate": 6.262120570705059e-05,
"loss": 2.0823,
"step": 1530
},
{
"epoch": 1.59,
"learning_rate": 6.112060377045816e-05,
"loss": 2.1142,
"step": 1535
},
{
"epoch": 1.6,
"learning_rate": 5.963615840750731e-05,
"loss": 2.0755,
"step": 1540
},
{
"epoch": 1.6,
"learning_rate": 5.8167970018446596e-05,
"loss": 2.1061,
"step": 1545
},
{
"epoch": 1.61,
"learning_rate": 5.671613790398708e-05,
"loss": 2.098,
"step": 1550
},
{
"epoch": 1.61,
"learning_rate": 5.528076025858519e-05,
"loss": 2.0948,
"step": 1555
},
{
"epoch": 1.62,
"learning_rate": 5.3861934163801576e-05,
"loss": 2.0849,
"step": 1560
},
{
"epoch": 1.62,
"learning_rate": 5.245975558173535e-05,
"loss": 2.0689,
"step": 1565
},
{
"epoch": 1.63,
"learning_rate": 5.107431934853351e-05,
"loss": 2.1098,
"step": 1570
},
{
"epoch": 1.63,
"learning_rate": 4.970571916797655e-05,
"loss": 2.0803,
"step": 1575
},
{
"epoch": 1.64,
"learning_rate": 4.8354047605141154e-05,
"loss": 2.0872,
"step": 1580
},
{
"epoch": 1.64,
"learning_rate": 4.7019396080139124e-05,
"loss": 2.095,
"step": 1585
},
{
"epoch": 1.65,
"learning_rate": 4.570185486193457e-05,
"loss": 2.0779,
"step": 1590
},
{
"epoch": 1.65,
"learning_rate": 4.44015130622387e-05,
"loss": 2.093,
"step": 1595
},
{
"epoch": 1.66,
"learning_rate": 4.311845862948212e-05,
"loss": 2.0729,
"step": 1600
},
{
"epoch": 1.66,
"learning_rate": 4.185277834286706e-05,
"loss": 2.0871,
"step": 1605
},
{
"epoch": 1.67,
"learning_rate": 4.060455780649787e-05,
"loss": 2.0792,
"step": 1610
},
{
"epoch": 1.67,
"learning_rate": 3.9373881443591196e-05,
"loss": 2.0971,
"step": 1615
},
{
"epoch": 1.68,
"learning_rate": 3.816083249076608e-05,
"loss": 2.092,
"step": 1620
},
{
"epoch": 1.68,
"learning_rate": 3.696549299241398e-05,
"loss": 2.0963,
"step": 1625
},
{
"epoch": 1.69,
"learning_rate": 3.578794379515026e-05,
"loss": 2.0796,
"step": 1630
},
{
"epoch": 1.69,
"learning_rate": 3.462826454234563e-05,
"loss": 2.082,
"step": 1635
},
{
"epoch": 1.7,
"learning_rate": 3.348653366873971e-05,
"loss": 2.0833,
"step": 1640
},
{
"epoch": 1.7,
"learning_rate": 3.2362828395136165e-05,
"loss": 2.0829,
"step": 1645
},
{
"epoch": 1.71,
"learning_rate": 3.125722472317973e-05,
"loss": 2.103,
"step": 1650
},
{
"epoch": 1.71,
"learning_rate": 3.0169797430215724e-05,
"loss": 2.0883,
"step": 1655
},
{
"epoch": 1.72,
"learning_rate": 2.9100620064233116e-05,
"loss": 2.0958,
"step": 1660
},
{
"epoch": 1.73,
"learning_rate": 2.8049764938889264e-05,
"loss": 2.0925,
"step": 1665
},
{
"epoch": 1.73,
"learning_rate": 2.7017303128619606e-05,
"loss": 2.0865,
"step": 1670
},
{
"epoch": 1.74,
"learning_rate": 2.6003304463830366e-05,
"loss": 2.0671,
"step": 1675
},
{
"epoch": 1.74,
"learning_rate": 2.500783752617557e-05,
"loss": 2.0947,
"step": 1680
},
{
"epoch": 1.75,
"learning_rate": 2.4030969643918474e-05,
"loss": 2.0775,
"step": 1685
},
{
"epoch": 1.75,
"learning_rate": 2.3072766887377937e-05,
"loss": 2.1041,
"step": 1690
},
{
"epoch": 1.76,
"learning_rate": 2.2133294064459726e-05,
"loss": 2.1082,
"step": 1695
},
{
"epoch": 1.76,
"learning_rate": 2.1212614716273224e-05,
"loss": 2.0846,
"step": 1700
},
{
"epoch": 1.77,
"learning_rate": 2.031079111283387e-05,
"loss": 2.101,
"step": 1705
},
{
"epoch": 1.77,
"learning_rate": 1.942788424885151e-05,
"loss": 2.0922,
"step": 1710
},
{
"epoch": 1.78,
"learning_rate": 1.8563953839605107e-05,
"loss": 2.0757,
"step": 1715
},
{
"epoch": 1.78,
"learning_rate": 1.7719058316903577e-05,
"loss": 2.0798,
"step": 1720
},
{
"epoch": 1.79,
"learning_rate": 1.6893254825134415e-05,
"loss": 2.0884,
"step": 1725
},
{
"epoch": 1.79,
"learning_rate": 1.6086599217397965e-05,
"loss": 2.0843,
"step": 1730
},
{
"epoch": 1.8,
"learning_rate": 1.529914605173045e-05,
"loss": 2.0823,
"step": 1735
},
{
"epoch": 1.8,
"learning_rate": 1.4530948587413583e-05,
"loss": 2.0875,
"step": 1740
},
{
"epoch": 1.81,
"learning_rate": 1.3782058781372396e-05,
"loss": 2.0842,
"step": 1745
},
{
"epoch": 1.81,
"learning_rate": 1.3052527284661407e-05,
"loss": 2.0983,
"step": 1750
},
{
"epoch": 1.82,
"learning_rate": 1.2342403439038629e-05,
"loss": 2.0771,
"step": 1755
},
{
"epoch": 1.82,
"learning_rate": 1.165173527362817e-05,
"loss": 2.0831,
"step": 1760
},
{
"epoch": 1.83,
"learning_rate": 1.098056950167231e-05,
"loss": 2.0947,
"step": 1765
},
{
"epoch": 1.83,
"learning_rate": 1.0328951517371475e-05,
"loss": 2.093,
"step": 1770
},
{
"epoch": 1.84,
"learning_rate": 9.696925392814515e-06,
"loss": 2.0803,
"step": 1775
},
{
"epoch": 1.84,
"learning_rate": 9.084533874997534e-06,
"loss": 2.0798,
"step": 1780
},
{
"epoch": 1.85,
"learning_rate": 8.491818382932824e-06,
"loss": 2.0915,
"step": 1785
},
{
"epoch": 1.85,
"learning_rate": 7.918819004847488e-06,
"loss": 2.0742,
"step": 1790
},
{
"epoch": 1.86,
"learning_rate": 7.3655744954722155e-06,
"loss": 2.066,
"step": 1795
},
{
"epoch": 1.87,
"learning_rate": 6.832122273419849e-06,
"loss": 2.1094,
"step": 1800
},
{
"epoch": 1.87,
"learning_rate": 6.318498418654805e-06,
"loss": 2.0924,
"step": 1805
},
{
"epoch": 1.88,
"learning_rate": 5.824737670052693e-06,
"loss": 2.0867,
"step": 1810
},
{
"epoch": 1.88,
"learning_rate": 5.350873423050828e-06,
"loss": 2.0771,
"step": 1815
},
{
"epoch": 1.89,
"learning_rate": 4.8969377273894385e-06,
"loss": 2.0997,
"step": 1820
},
{
"epoch": 1.89,
"learning_rate": 4.4629612849440996e-06,
"loss": 2.0607,
"step": 1825
},
{
"epoch": 1.9,
"learning_rate": 4.048973447649095e-06,
"loss": 2.1042,
"step": 1830
},
{
"epoch": 1.9,
"learning_rate": 3.6550022155124035e-06,
"loss": 2.095,
"step": 1835
},
{
"epoch": 1.91,
"learning_rate": 3.2810742347216146e-06,
"loss": 2.0786,
"step": 1840
},
{
"epoch": 1.91,
"learning_rate": 2.927214795842037e-06,
"loss": 2.0814,
"step": 1845
},
{
"epoch": 1.92,
"learning_rate": 2.593447832105966e-06,
"loss": 2.0981,
"step": 1850
},
{
"epoch": 1.92,
"learning_rate": 2.279795917794014e-06,
"loss": 2.109,
"step": 1855
},
{
"epoch": 1.93,
"learning_rate": 1.9862802667083954e-06,
"loss": 2.0946,
"step": 1860
},
{
"epoch": 1.93,
"learning_rate": 1.7129207307379433e-06,
"loss": 2.0744,
"step": 1865
},
{
"epoch": 1.94,
"learning_rate": 1.4597357985156154e-06,
"loss": 2.0835,
"step": 1870
},
{
"epoch": 1.94,
"learning_rate": 1.2267425941679287e-06,
"loss": 2.0696,
"step": 1875
},
{
"epoch": 1.95,
"learning_rate": 1.0139568761567852e-06,
"loss": 2.0975,
"step": 1880
},
{
"epoch": 1.95,
"learning_rate": 8.213930362136578e-07,
"loss": 2.0809,
"step": 1885
},
{
"epoch": 1.96,
"learning_rate": 6.490640983661366e-07,
"loss": 2.0819,
"step": 1890
},
{
"epoch": 1.96,
"learning_rate": 4.969817180572321e-07,
"loss": 2.105,
"step": 1895
},
{
"epoch": 1.97,
"learning_rate": 3.6515618135687376e-07,
"loss": 2.0889,
"step": 1900
},
{
"epoch": 1.97,
"learning_rate": 2.5359640426629856e-07,
"loss": 2.0978,
"step": 1905
},
{
"epoch": 1.98,
"learning_rate": 1.623099321149679e-07,
"loss": 2.0995,
"step": 1910
},
{
"epoch": 1.98,
"learning_rate": 9.13029390503417e-08,
"loss": 2.0786,
"step": 1915
},
{
"epoch": 1.99,
"learning_rate": 4.058022762021274e-08,
"loss": 2.0808,
"step": 1920
},
{
"epoch": 1.99,
"learning_rate": 1.0145228447833164e-08,
"loss": 2.0796,
"step": 1925
},
{
"epoch": 2.0,
"learning_rate": 0.0,
"loss": 2.0885,
"step": 1930
},
{
"epoch": 2.0,
"eval_loss": 2.0213370323181152,
"eval_runtime": 38.6316,
"eval_samples_per_second": 335.839,
"eval_steps_per_second": 41.986,
"step": 1930
},
{
"epoch": 2.0,
"step": 1930,
"total_flos": 6.455806557526426e+16,
"train_loss": 2.144662865950036,
"train_runtime": 4258.8623,
"train_samples_per_second": 116.039,
"train_steps_per_second": 0.453
}
],
"max_steps": 1930,
"num_train_epochs": 2,
"total_flos": 6.455806557526426e+16,
"trial_name": null,
"trial_params": null
}