Files
v40_scratch_source_paper_mi…/trainer_log.jsonl

73 lines
14 KiB
Plaintext
Raw Permalink Normal View History

{"current_steps": 10, "total_steps": 714, "loss": 2.139740753173828, "lr": 1.2272727272727274e-06, "epoch": 0.021019442984760904, "percentage": 1.4, "elapsed_time": "0:01:21", "remaining_time": "1:35:40"}
{"current_steps": 20, "total_steps": 714, "loss": 2.2081624984741213, "lr": 2.590909090909091e-06, "epoch": 0.04203888596952181, "percentage": 2.8, "elapsed_time": "0:02:44", "remaining_time": "1:35:03"}
{"current_steps": 30, "total_steps": 714, "loss": 2.0339645385742187, "lr": 2.999242629561838e-06, "epoch": 0.0630583289542827, "percentage": 4.2, "elapsed_time": "0:04:03", "remaining_time": "1:32:40"}
{"current_steps": 40, "total_steps": 714, "loss": 2.0348079681396483, "lr": 2.995534901109399e-06, "epoch": 0.08407777193904362, "percentage": 5.6, "elapsed_time": "0:05:20", "remaining_time": "1:30:03"}
{"current_steps": 50, "total_steps": 714, "loss": 1.950754165649414, "lr": 2.9887453367135033e-06, "epoch": 0.10509721492380451, "percentage": 7.0, "elapsed_time": "0:06:42", "remaining_time": "1:29:05"}
{"current_steps": 60, "total_steps": 714, "loss": 1.9394699096679688, "lr": 2.9788879275712665e-06, "epoch": 0.1261166579085654, "percentage": 8.4, "elapsed_time": "0:08:01", "remaining_time": "1:27:27"}
{"current_steps": 70, "total_steps": 714, "loss": 1.880813980102539, "lr": 2.9659829867611603e-06, "epoch": 0.14713610089332632, "percentage": 9.8, "elapsed_time": "0:09:21", "remaining_time": "1:26:08"}
{"current_steps": 80, "total_steps": 714, "loss": 1.8970605850219726, "lr": 2.9500571073840264e-06, "epoch": 0.16815554387808723, "percentage": 11.2, "elapsed_time": "0:10:40", "remaining_time": "1:24:35"}
{"current_steps": 90, "total_steps": 714, "loss": 1.8591070175170898, "lr": 2.931143107762901e-06, "epoch": 0.18917498686284814, "percentage": 12.61, "elapsed_time": "0:12:01", "remaining_time": "1:23:23"}
{"current_steps": 100, "total_steps": 714, "loss": 1.892710304260254, "lr": 2.909279963814576e-06, "epoch": 0.21019442984760903, "percentage": 14.01, "elapsed_time": "0:13:18", "remaining_time": "1:21:44"}
{"current_steps": 110, "total_steps": 714, "loss": 1.8118453979492188, "lr": 2.8845127287322656e-06, "epoch": 0.23121387283236994, "percentage": 15.41, "elapsed_time": "0:14:35", "remaining_time": "1:20:04"}
{"current_steps": 120, "total_steps": 714, "loss": 1.8849889755249023, "lr": 2.8568924401448738e-06, "epoch": 0.2522333158171308, "percentage": 16.81, "elapsed_time": "0:15:54", "remaining_time": "1:18:45"}
{"current_steps": 130, "total_steps": 714, "loss": 1.8813108444213866, "lr": 2.826476014944193e-06, "epoch": 0.27325275880189176, "percentage": 18.21, "elapsed_time": "0:17:12", "remaining_time": "1:17:19"}
{"current_steps": 140, "total_steps": 714, "loss": 1.9071147918701172, "lr": 2.7933261319967516e-06, "epoch": 0.29427220178665264, "percentage": 19.61, "elapsed_time": "0:18:29", "remaining_time": "1:15:48"}
{"current_steps": 150, "total_steps": 714, "loss": 1.8963701248168945, "lr": 2.7575111029820103e-06, "epoch": 0.3152916447714136, "percentage": 21.01, "elapsed_time": "0:19:48", "remaining_time": "1:14:27"}
{"current_steps": 160, "total_steps": 714, "loss": 1.9282533645629882, "lr": 2.7191047316230743e-06, "epoch": 0.33631108775617446, "percentage": 22.41, "elapsed_time": "0:21:07", "remaining_time": "1:13:09"}
{"current_steps": 170, "total_steps": 714, "loss": 1.7661924362182617, "lr": 2.6781861615999896e-06, "epoch": 0.35733053074093535, "percentage": 23.81, "elapsed_time": "0:22:27", "remaining_time": "1:11:52"}
{"current_steps": 180, "total_steps": 714, "loss": 1.784163475036621, "lr": 2.6348397134590424e-06, "epoch": 0.3783499737256963, "percentage": 25.21, "elapsed_time": "0:23:45", "remaining_time": "1:10:27"}
{"current_steps": 190, "total_steps": 714, "loss": 1.8109502792358398, "lr": 2.5891547108541323e-06, "epoch": 0.39936941671045717, "percentage": 26.61, "elapsed_time": "0:25:05", "remaining_time": "1:09:10"}
{"current_steps": 200, "total_steps": 714, "loss": 1.821950912475586, "lr": 2.5412252964782867e-06, "epoch": 0.42038885969521805, "percentage": 28.01, "elapsed_time": "0:26:22", "remaining_time": "1:07:48"}
{"current_steps": 210, "total_steps": 714, "loss": 1.9059152603149414, "lr": 2.4911502380646164e-06, "epoch": 0.441408302679979, "percentage": 29.41, "elapsed_time": "0:27:41", "remaining_time": "1:06:26"}
{"current_steps": 220, "total_steps": 714, "loss": 1.8420991897583008, "lr": 2.4390327248564994e-06, "epoch": 0.4624277456647399, "percentage": 30.81, "elapsed_time": "0:28:58", "remaining_time": "1:05:03"}
{"current_steps": 230, "total_steps": 714, "loss": 1.890372085571289, "lr": 2.3849801549663886e-06, "epoch": 0.4834471886495008, "percentage": 32.21, "elapsed_time": "0:30:17", "remaining_time": "1:03:44"}
{"current_steps": 240, "total_steps": 714, "loss": 1.8288061141967773, "lr": 2.3291039140614475e-06, "epoch": 0.5044666316342616, "percentage": 33.61, "elapsed_time": "0:31:36", "remaining_time": "1:02:25"}
{"current_steps": 250, "total_steps": 714, "loss": 1.8653709411621093, "lr": 2.2715191458320545e-06, "epoch": 0.5254860746190226, "percentage": 35.01, "elapsed_time": "0:32:57", "remaining_time": "1:01:09"}
{"current_steps": 260, "total_steps": 714, "loss": 1.771567153930664, "lr": 2.212344514716194e-06, "epoch": 0.5465055176037835, "percentage": 36.41, "elapsed_time": "0:34:15", "remaining_time": "0:59:49"}
{"current_steps": 270, "total_steps": 714, "loss": 1.7724361419677734, "lr": 2.151701961368664e-06, "epoch": 0.5675249605885444, "percentage": 37.82, "elapsed_time": "0:35:37", "remaining_time": "0:58:34"}
{"current_steps": 280, "total_steps": 714, "loss": 1.7283151626586915, "lr": 2.0897164513790135e-06, "epoch": 0.5885444035733053, "percentage": 39.22, "elapsed_time": "0:36:57", "remaining_time": "0:57:17"}
{"current_steps": 290, "total_steps": 714, "loss": 1.7711864471435548, "lr": 2.026515717756026e-06, "epoch": 0.6095638465580662, "percentage": 40.62, "elapsed_time": "0:38:17", "remaining_time": "0:55:58"}
{"current_steps": 300, "total_steps": 714, "loss": 1.7970991134643555, "lr": 1.9622299977094044e-06, "epoch": 0.6305832895428272, "percentage": 42.02, "elapsed_time": "0:39:33", "remaining_time": "0:54:35"}
{"current_steps": 310, "total_steps": 714, "loss": 1.8020233154296874, "lr": 1.8969917642710664e-06, "epoch": 0.651602732527588, "percentage": 43.42, "elapsed_time": "0:40:50", "remaining_time": "0:53:13"}
{"current_steps": 320, "total_steps": 714, "loss": 1.8001415252685546, "lr": 1.830935453309108e-06, "epoch": 0.6726221755123489, "percentage": 44.82, "elapsed_time": "0:42:09", "remaining_time": "0:51:53"}
{"current_steps": 330, "total_steps": 714, "loss": 1.75347843170166, "lr": 1.764197186496962e-06, "epoch": 0.6936416184971098, "percentage": 46.22, "elapsed_time": "0:43:28", "remaining_time": "0:50:34"}
{"current_steps": 340, "total_steps": 714, "loss": 1.809716033935547, "lr": 1.6969144908086306e-06, "epoch": 0.7146610614818707, "percentage": 47.62, "elapsed_time": "0:44:49", "remaining_time": "0:49:18"}
{"current_steps": 350, "total_steps": 714, "loss": 1.7866138458251952, "lr": 1.6292260151180326e-06, "epoch": 0.7356805044666316, "percentage": 49.02, "elapsed_time": "0:46:09", "remaining_time": "0:48:00"}
{"current_steps": 360, "total_steps": 714, "loss": 1.8378917694091796, "lr": 1.5612712444864579e-06, "epoch": 0.7566999474513926, "percentage": 50.42, "elapsed_time": "0:47:28", "remaining_time": "0:46:40"}
{"current_steps": 370, "total_steps": 714, "loss": 1.7029869079589843, "lr": 1.4931902127268951e-06, "epoch": 0.7777193904361535, "percentage": 51.82, "elapsed_time": "0:48:45", "remaining_time": "0:45:19"}
{"current_steps": 380, "total_steps": 714, "loss": 1.7460771560668946, "lr": 1.4251232138375584e-06, "epoch": 0.7987388334209143, "percentage": 53.22, "elapsed_time": "0:50:02", "remaining_time": "0:43:59"}
{"current_steps": 390, "total_steps": 714, "loss": 1.7742759704589843, "lr": 1.3572105128992455e-06, "epoch": 0.8197582764056752, "percentage": 54.62, "elapsed_time": "0:51:20", "remaining_time": "0:42:38"}
{"current_steps": 400, "total_steps": 714, "loss": 1.8007017135620118, "lr": 1.2895920570322904e-06, "epoch": 0.8407777193904361, "percentage": 56.02, "elapsed_time": "0:52:39", "remaining_time": "0:41:20"}
{"current_steps": 410, "total_steps": 714, "loss": 1.7528308868408202, "lr": 1.2224071870087317e-06, "epoch": 0.8617971623751971, "percentage": 57.42, "elapsed_time": "0:53:58", "remaining_time": "0:40:01"}
{"current_steps": 420, "total_steps": 714, "loss": 1.8043436050415038, "lr": 1.1557943501139813e-06, "epoch": 0.882816605359958, "percentage": 58.82, "elapsed_time": "0:55:18", "remaining_time": "0:38:43"}
{"current_steps": 430, "total_steps": 714, "loss": 1.7981443405151367, "lr": 1.0898908148496853e-06, "epoch": 0.9038360483447189, "percentage": 60.22, "elapsed_time": "0:56:37", "remaining_time": "0:37:23"}
{"current_steps": 440, "total_steps": 714, "loss": 1.7500328063964843, "lr": 1.0248323880657068e-06, "epoch": 0.9248554913294798, "percentage": 61.62, "elapsed_time": "0:57:54", "remaining_time": "0:36:03"}
{"current_steps": 450, "total_steps": 714, "loss": 1.7884363174438476, "lr": 9.607531351041108e-07, "epoch": 0.9458749343142406, "percentage": 63.03, "elapsed_time": "0:59:13", "remaining_time": "0:34:44"}
{"current_steps": 460, "total_steps": 714, "loss": 1.714197540283203, "lr": 8.977851035318654e-07, "epoch": 0.9668943772990016, "percentage": 64.43, "elapsed_time": "1:00:31", "remaining_time": "0:33:24"}
{"current_steps": 470, "total_steps": 714, "loss": 1.7554092407226562, "lr": 8.360580510315521e-07, "epoch": 0.9879138202837625, "percentage": 65.83, "elapsed_time": "1:01:51", "remaining_time": "0:32:06"}
{"current_steps": 480, "total_steps": 714, "loss": 1.7379329681396485, "lr": 7.756991780108238e-07, "epoch": 1.0084077771939044, "percentage": 67.23, "elapsed_time": "1:03:08", "remaining_time": "0:30:47"}
{"current_steps": 490, "total_steps": 714, "loss": 1.692732810974121, "lr": 7.168328654816127e-07, "epoch": 1.0294272201786652, "percentage": 68.63, "elapsed_time": "1:04:30", "remaining_time": "0:29:29"}
{"current_steps": 500, "total_steps": 714, "loss": 1.8081771850585937, "lr": 6.595804187492498e-07, "epoch": 1.0504466631634262, "percentage": 70.03, "elapsed_time": "1:05:48", "remaining_time": "0:28:09"}
{"current_steps": 510, "total_steps": 714, "loss": 1.7980724334716798, "lr": 6.0405981743966e-07, "epoch": 1.0714661061481872, "percentage": 71.43, "elapsed_time": "1:07:06", "remaining_time": "0:26:50"}
{"current_steps": 520, "total_steps": 714, "loss": 1.764889907836914, "lr": 5.503854723797599e-07, "epoch": 1.092485549132948, "percentage": 72.83, "elapsed_time": "1:08:24", "remaining_time": "0:25:31"}
{"current_steps": 530, "total_steps": 714, "loss": 1.7189857482910156, "lr": 4.986679898320476e-07, "epoch": 1.113504992117709, "percentage": 74.23, "elapsed_time": "1:09:42", "remaining_time": "0:24:12"}
{"current_steps": 540, "total_steps": 714, "loss": 1.7537565231323242, "lr": 4.490139435692261e-07, "epoch": 1.1345244351024697, "percentage": 75.63, "elapsed_time": "1:11:01", "remaining_time": "0:22:53"}
{"current_steps": 550, "total_steps": 714, "loss": 1.6921497344970704, "lr": 4.0152565525854467e-07, "epoch": 1.1555438780872307, "percentage": 77.03, "elapsed_time": "1:12:20", "remaining_time": "0:21:34"}
{"current_steps": 560, "total_steps": 714, "loss": 1.7711572647094727, "lr": 3.5630098360841646e-07, "epoch": 1.1765633210719917, "percentage": 78.43, "elapsed_time": "1:13:38", "remaining_time": "0:20:15"}
{"current_steps": 570, "total_steps": 714, "loss": 1.6838041305541993, "lr": 3.134331227118171e-07, "epoch": 1.1975827640567525, "percentage": 79.83, "elapsed_time": "1:14:55", "remaining_time": "0:18:55"}
{"current_steps": 580, "total_steps": 714, "loss": 1.73205509185791, "lr": 2.7301041000201746e-07, "epoch": 1.2186022070415135, "percentage": 81.23, "elapsed_time": "1:16:15", "remaining_time": "0:17:37"}
{"current_steps": 590, "total_steps": 714, "loss": 1.7526542663574218, "lr": 2.351161442163905e-07, "epoch": 1.2396216500262742, "percentage": 82.63, "elapsed_time": "1:17:33", "remaining_time": "0:16:18"}
{"current_steps": 600, "total_steps": 714, "loss": 1.7869752883911132, "lr": 1.998284137434206e-07, "epoch": 1.2606410930110352, "percentage": 84.03, "elapsed_time": "1:18:50", "remaining_time": "0:14:58"}
{"current_steps": 610, "total_steps": 714, "loss": 1.828580093383789, "lr": 1.6721993570662926e-07, "epoch": 1.2816605359957962, "percentage": 85.43, "elapsed_time": "1:20:08", "remaining_time": "0:13:39"}
{"current_steps": 620, "total_steps": 714, "loss": 1.7601003646850586, "lr": 1.3735790611702274e-07, "epoch": 1.302679978980557, "percentage": 86.83, "elapsed_time": "1:21:25", "remaining_time": "0:12:20"}
{"current_steps": 630, "total_steps": 714, "loss": 1.7960094451904296, "lr": 1.1030386140284865e-07, "epoch": 1.323699421965318, "percentage": 88.24, "elapsed_time": "1:22:44", "remaining_time": "0:11:01"}
{"current_steps": 640, "total_steps": 714, "loss": 1.7016435623168946, "lr": 8.611355160200623e-08, "epoch": 1.3447188649500788, "percentage": 89.64, "elapsed_time": "1:24:04", "remaining_time": "0:09:43"}
{"current_steps": 650, "total_steps": 714, "loss": 1.7239088058471679, "lr": 6.483682547842001e-08, "epoch": 1.3657383079348397, "percentage": 91.04, "elapsed_time": "1:25:24", "remaining_time": "0:08:24"}
{"current_steps": 660, "total_steps": 714, "loss": 1.7699031829833984, "lr": 4.651752779912233e-08, "epoch": 1.3867577509196005, "percentage": 92.44, "elapsed_time": "1:26:43", "remaining_time": "0:07:05"}
{"current_steps": 670, "total_steps": 714, "loss": 1.8059171676635741, "lr": 3.1193408983715475e-08, "epoch": 1.4077771939043615, "percentage": 93.84, "elapsed_time": "1:28:03", "remaining_time": "0:05:46"}
{"current_steps": 680, "total_steps": 714, "loss": 1.7002668380737305, "lr": 1.8896047312406683e-08, "epoch": 1.4287966368891225, "percentage": 95.24, "elapsed_time": "1:29:20", "remaining_time": "0:04:28"}
{"current_steps": 690, "total_steps": 714, "loss": 1.7966609954833985, "lr": 9.650783852917178e-09, "epoch": 1.4498160798738833, "percentage": 96.64, "elapsed_time": "1:30:40", "remaining_time": "0:03:09"}
{"current_steps": 700, "total_steps": 714, "loss": 1.7154333114624023, "lr": 3.4766702403609684e-09, "epoch": 1.4708355228586443, "percentage": 98.04, "elapsed_time": "1:32:01", "remaining_time": "0:01:50"}
{"current_steps": 710, "total_steps": 714, "loss": 1.7977441787719726, "lr": 3.8642941770372644e-10, "epoch": 1.4918549658434053, "percentage": 99.44, "elapsed_time": "1:33:17", "remaining_time": "0:00:31"}
{"current_steps": 714, "total_steps": 714, "epoch": 1.5002627430373097, "percentage": 100.0, "elapsed_time": "1:33:47", "remaining_time": "0:00:00"}