v12_user_cot_focus_lr15e6 / trainer_log.jsonl
lldois's picture
Upload v12_user_cot_focus_lr15e6 model without checkpoints
ac32a93 verified
Raw
History Blame Contribute Delete
38.3 kB
{"current_steps": 5, "total_steps": 927, "loss": 2.6865272521972656, "lr": 2.1428571428571427e-06, "epoch": 0.005398110661268556, "percentage": 0.54, "elapsed_time": "0:00:42", "remaining_time": "2:11:26"}
{"current_steps": 10, "total_steps": 927, "loss": 2.7759025573730467, "lr": 4.821428571428572e-06, "epoch": 0.010796221322537112, "percentage": 1.08, "elapsed_time": "0:01:25", "remaining_time": "2:10:31"}
{"current_steps": 15, "total_steps": 927, "loss": 2.3364213943481444, "lr": 7.5e-06, "epoch": 0.016194331983805668, "percentage": 1.62, "elapsed_time": "0:02:10", "remaining_time": "2:11:59"}
{"current_steps": 20, "total_steps": 927, "loss": 2.357875442504883, "lr": 1.0178571428571429e-05, "epoch": 0.021592442645074223, "percentage": 2.16, "elapsed_time": "0:02:53", "remaining_time": "2:10:53"}
{"current_steps": 25, "total_steps": 927, "loss": 2.113478088378906, "lr": 1.2857142857142857e-05, "epoch": 0.02699055330634278, "percentage": 2.7, "elapsed_time": "0:03:35", "remaining_time": "2:09:18"}
{"current_steps": 30, "total_steps": 927, "loss": 2.0126585006713866, "lr": 1.4999954205725012e-05, "epoch": 0.032388663967611336, "percentage": 3.24, "elapsed_time": "0:04:19", "remaining_time": "2:09:24"}
{"current_steps": 35, "total_steps": 927, "loss": 1.952888298034668, "lr": 1.4998351464818896e-05, "epoch": 0.037786774628879895, "percentage": 3.78, "elapsed_time": "0:05:01", "remaining_time": "2:08:07"}
{"current_steps": 40, "total_steps": 927, "loss": 1.7912431716918946, "lr": 1.4994459569363502e-05, "epoch": 0.043184885290148446, "percentage": 4.31, "elapsed_time": "0:05:45", "remaining_time": "2:07:50"}
{"current_steps": 45, "total_steps": 927, "loss": 1.7172063827514648, "lr": 1.4988279707506684e-05, "epoch": 0.048582995951417005, "percentage": 4.85, "elapsed_time": "0:06:29", "remaining_time": "2:07:21"}
{"current_steps": 50, "total_steps": 927, "loss": 1.6440818786621094, "lr": 1.4979813765884318e-05, "epoch": 0.05398110661268556, "percentage": 5.39, "elapsed_time": "0:07:13", "remaining_time": "2:06:50"}
{"current_steps": 55, "total_steps": 927, "loss": 1.691044235229492, "lr": 1.4969064329044335e-05, "epoch": 0.059379217273954114, "percentage": 5.93, "elapsed_time": "0:07:58", "remaining_time": "2:06:29"}
{"current_steps": 60, "total_steps": 927, "loss": 1.6486940383911133, "lr": 1.4956034678657697e-05, "epoch": 0.06477732793522267, "percentage": 6.47, "elapsed_time": "0:08:42", "remaining_time": "2:05:57"}
{"current_steps": 65, "total_steps": 927, "loss": 1.621745491027832, "lr": 1.4940728792516532e-05, "epoch": 0.07017543859649122, "percentage": 7.01, "elapsed_time": "0:09:26", "remaining_time": "2:05:17"}
{"current_steps": 70, "total_steps": 927, "loss": 1.7037588119506837, "lr": 1.492315134331978e-05, "epoch": 0.07557354925775979, "percentage": 7.55, "elapsed_time": "0:10:09", "remaining_time": "2:04:16"}
{"current_steps": 75, "total_steps": 927, "loss": 1.5873713493347168, "lr": 1.490330769724665e-05, "epoch": 0.08097165991902834, "percentage": 8.09, "elapsed_time": "0:10:52", "remaining_time": "2:03:34"}
{"current_steps": 80, "total_steps": 927, "loss": 1.5764989852905273, "lr": 1.4881203912318417e-05, "epoch": 0.08636977058029689, "percentage": 8.63, "elapsed_time": "0:11:36", "remaining_time": "2:02:49"}
{"current_steps": 85, "total_steps": 927, "loss": 1.6242074966430664, "lr": 1.4856846736548972e-05, "epoch": 0.09176788124156546, "percentage": 9.17, "elapsed_time": "0:12:19", "remaining_time": "2:02:07"}
{"current_steps": 90, "total_steps": 927, "loss": 1.5501031875610352, "lr": 1.4830243605884732e-05, "epoch": 0.09716599190283401, "percentage": 9.71, "elapsed_time": "0:13:04", "remaining_time": "2:01:32"}
{"current_steps": 95, "total_steps": 927, "loss": 1.7399942398071289, "lr": 1.4801402641934543e-05, "epoch": 0.10256410256410256, "percentage": 10.25, "elapsed_time": "0:13:46", "remaining_time": "2:00:39"}
{"current_steps": 100, "total_steps": 927, "loss": 1.5935526847839356, "lr": 1.4770332649490248e-05, "epoch": 0.10796221322537113, "percentage": 10.79, "elapsed_time": "0:14:30", "remaining_time": "2:00:00"}
{"current_steps": 105, "total_steps": 927, "loss": 1.6135421752929688, "lr": 1.4737043113838703e-05, "epoch": 0.11336032388663968, "percentage": 11.33, "elapsed_time": "0:15:12", "remaining_time": "1:59:03"}
{"current_steps": 110, "total_steps": 927, "loss": 1.4750379562377929, "lr": 1.4701544197866017e-05, "epoch": 0.11875843454790823, "percentage": 11.87, "elapsed_time": "0:15:57", "remaining_time": "1:58:31"}
{"current_steps": 115, "total_steps": 927, "loss": 1.5500977516174317, "lr": 1.4663846738954966e-05, "epoch": 0.1241565452091768, "percentage": 12.41, "elapsed_time": "0:16:40", "remaining_time": "1:57:42"}
{"current_steps": 120, "total_steps": 927, "loss": 1.4977538108825683, "lr": 1.4623962245676462e-05, "epoch": 0.12955465587044535, "percentage": 12.94, "elapsed_time": "0:17:24", "remaining_time": "1:57:04"}
{"current_steps": 125, "total_steps": 927, "loss": 1.5538610458374023, "lr": 1.4581902894276133e-05, "epoch": 0.1349527665317139, "percentage": 13.48, "elapsed_time": "0:18:07", "remaining_time": "1:56:17"}
{"current_steps": 130, "total_steps": 927, "loss": 1.5750856399536133, "lr": 1.4537681524957061e-05, "epoch": 0.14035087719298245, "percentage": 14.02, "elapsed_time": "0:18:50", "remaining_time": "1:55:27"}
{"current_steps": 135, "total_steps": 927, "loss": 1.5172950744628906, "lr": 1.4491311637959828e-05, "epoch": 0.145748987854251, "percentage": 14.56, "elapsed_time": "0:19:33", "remaining_time": "1:54:46"}
{"current_steps": 140, "total_steps": 927, "loss": 1.4594326972961427, "lr": 1.4442807389441062e-05, "epoch": 0.15114709851551958, "percentage": 15.1, "elapsed_time": "0:20:18", "remaining_time": "1:54:09"}
{"current_steps": 145, "total_steps": 927, "loss": 1.5347204208374023, "lr": 1.439218358715173e-05, "epoch": 0.15654520917678813, "percentage": 15.64, "elapsed_time": "0:21:02", "remaining_time": "1:53:27"}
{"current_steps": 150, "total_steps": 927, "loss": 1.490595531463623, "lr": 1.4339455685916516e-05, "epoch": 0.16194331983805668, "percentage": 16.18, "elapsed_time": "0:21:45", "remaining_time": "1:52:43"}
{"current_steps": 155, "total_steps": 927, "loss": 1.4158689498901367, "lr": 1.4284639782915652e-05, "epoch": 0.16734143049932523, "percentage": 16.72, "elapsed_time": "0:22:27", "remaining_time": "1:51:50"}
{"current_steps": 160, "total_steps": 927, "loss": 1.4857367515563964, "lr": 1.4227752612770654e-05, "epoch": 0.17273954116059378, "percentage": 17.26, "elapsed_time": "0:23:12", "remaining_time": "1:51:13"}
{"current_steps": 165, "total_steps": 927, "loss": 1.5408924102783204, "lr": 1.4168811542435435e-05, "epoch": 0.17813765182186234, "percentage": 17.8, "elapsed_time": "0:23:56", "remaining_time": "1:50:33"}
{"current_steps": 170, "total_steps": 927, "loss": 1.6404100418090821, "lr": 1.4107834565894396e-05, "epoch": 0.18353576248313092, "percentage": 18.34, "elapsed_time": "0:24:37", "remaining_time": "1:49:40"}
{"current_steps": 175, "total_steps": 927, "loss": 1.5440165519714355, "lr": 1.4044840298669085e-05, "epoch": 0.18893387314439947, "percentage": 18.88, "elapsed_time": "0:25:20", "remaining_time": "1:48:55"}
{"current_steps": 180, "total_steps": 927, "loss": 1.4469735145568847, "lr": 1.3979847972135099e-05, "epoch": 0.19433198380566802, "percentage": 19.42, "elapsed_time": "0:26:04", "remaining_time": "1:48:14"}
{"current_steps": 185, "total_steps": 927, "loss": 1.4575271606445312, "lr": 1.391287742765099e-05, "epoch": 0.19973009446693657, "percentage": 19.96, "elapsed_time": "0:26:48", "remaining_time": "1:47:32"}
{"current_steps": 190, "total_steps": 927, "loss": 1.468193817138672, "lr": 1.3843949110500939e-05, "epoch": 0.20512820512820512, "percentage": 20.5, "elapsed_time": "0:27:33", "remaining_time": "1:46:52"}
{"current_steps": 195, "total_steps": 927, "loss": 1.380112075805664, "lr": 1.3773084063653057e-05, "epoch": 0.21052631578947367, "percentage": 21.04, "elapsed_time": "0:28:17", "remaining_time": "1:46:13"}
{"current_steps": 200, "total_steps": 927, "loss": 1.4284241676330567, "lr": 1.3700303921335235e-05, "epoch": 0.21592442645074225, "percentage": 21.57, "elapsed_time": "0:29:01", "remaining_time": "1:45:30"}
{"current_steps": 205, "total_steps": 927, "loss": 1.4978090286254884, "lr": 1.3625630902430466e-05, "epoch": 0.2213225371120108, "percentage": 22.11, "elapsed_time": "0:29:43", "remaining_time": "1:44:42"}
{"current_steps": 210, "total_steps": 927, "loss": 1.4717984199523926, "lr": 1.3549087803693715e-05, "epoch": 0.22672064777327935, "percentage": 22.65, "elapsed_time": "0:30:25", "remaining_time": "1:43:54"}
{"current_steps": 215, "total_steps": 927, "loss": 1.5032032966613769, "lr": 1.3470697992792328e-05, "epoch": 0.2321187584345479, "percentage": 23.19, "elapsed_time": "0:31:08", "remaining_time": "1:43:09"}
{"current_steps": 220, "total_steps": 927, "loss": 1.539174461364746, "lr": 1.339048540117218e-05, "epoch": 0.23751686909581646, "percentage": 23.73, "elapsed_time": "0:31:51", "remaining_time": "1:42:21"}
{"current_steps": 225, "total_steps": 927, "loss": 1.4706098556518554, "lr": 1.3308474516751701e-05, "epoch": 0.242914979757085, "percentage": 24.27, "elapsed_time": "0:32:34", "remaining_time": "1:41:39"}
{"current_steps": 230, "total_steps": 927, "loss": 1.4873103141784667, "lr": 1.322469037644601e-05, "epoch": 0.2483130904183536, "percentage": 24.81, "elapsed_time": "0:33:18", "remaining_time": "1:40:55"}
{"current_steps": 235, "total_steps": 927, "loss": 1.4533129692077638, "lr": 1.3139158558523457e-05, "epoch": 0.25371120107962214, "percentage": 25.35, "elapsed_time": "0:34:02", "remaining_time": "1:40:14"}
{"current_steps": 240, "total_steps": 927, "loss": 1.5055602073669434, "lr": 1.3051905174796882e-05, "epoch": 0.2591093117408907, "percentage": 25.89, "elapsed_time": "0:34:44", "remaining_time": "1:39:25"}
{"current_steps": 245, "total_steps": 927, "loss": 1.4806604385375977, "lr": 1.296295686265202e-05, "epoch": 0.26450742240215924, "percentage": 26.43, "elapsed_time": "0:35:25", "remaining_time": "1:38:37"}
{"current_steps": 250, "total_steps": 927, "loss": 1.463977336883545, "lr": 1.2872340776915414e-05, "epoch": 0.2699055330634278, "percentage": 26.97, "elapsed_time": "0:36:08", "remaining_time": "1:37:52"}
{"current_steps": 255, "total_steps": 927, "loss": 1.445403480529785, "lr": 1.2780084581564391e-05, "epoch": 0.27530364372469635, "percentage": 27.51, "elapsed_time": "0:36:51", "remaining_time": "1:37:08"}
{"current_steps": 260, "total_steps": 927, "loss": 1.4426302909851074, "lr": 1.2686216441281581e-05, "epoch": 0.2807017543859649, "percentage": 28.05, "elapsed_time": "0:37:36", "remaining_time": "1:36:27"}
{"current_steps": 265, "total_steps": 927, "loss": 1.4424419403076172, "lr": 1.2590765012856599e-05, "epoch": 0.28609986504723345, "percentage": 28.59, "elapsed_time": "0:38:19", "remaining_time": "1:35:45"}
{"current_steps": 270, "total_steps": 927, "loss": 1.3920962333679199, "lr": 1.2493759436437467e-05, "epoch": 0.291497975708502, "percentage": 29.13, "elapsed_time": "0:39:03", "remaining_time": "1:35:01"}
{"current_steps": 275, "total_steps": 927, "loss": 1.481032943725586, "lr": 1.2395229326634489e-05, "epoch": 0.2968960863697706, "percentage": 29.67, "elapsed_time": "0:39:47", "remaining_time": "1:34:20"}
{"current_steps": 280, "total_steps": 927, "loss": 1.3904236793518066, "lr": 1.2295204763479281e-05, "epoch": 0.30229419703103916, "percentage": 30.2, "elapsed_time": "0:40:31", "remaining_time": "1:33:39"}
{"current_steps": 285, "total_steps": 927, "loss": 1.4106941223144531, "lr": 1.2193716283241692e-05, "epoch": 0.3076923076923077, "percentage": 30.74, "elapsed_time": "0:41:16", "remaining_time": "1:32:57"}
{"current_steps": 290, "total_steps": 927, "loss": 1.4160966873168945, "lr": 1.2090794869107473e-05, "epoch": 0.31309041835357626, "percentage": 31.28, "elapsed_time": "0:41:59", "remaining_time": "1:32:13"}
{"current_steps": 295, "total_steps": 927, "loss": 1.392179298400879, "lr": 1.1986471941719478e-05, "epoch": 0.3184885290148448, "percentage": 31.82, "elapsed_time": "0:42:42", "remaining_time": "1:31:29"}
{"current_steps": 300, "total_steps": 927, "loss": 1.4000489234924316, "lr": 1.1880779349585331e-05, "epoch": 0.32388663967611336, "percentage": 32.36, "elapsed_time": "0:43:26", "remaining_time": "1:30:46"}
{"current_steps": 305, "total_steps": 927, "loss": 1.482375717163086, "lr": 1.1773749359354481e-05, "epoch": 0.3292847503373819, "percentage": 32.9, "elapsed_time": "0:44:09", "remaining_time": "1:30:02"}
{"current_steps": 310, "total_steps": 927, "loss": 1.5753582000732422, "lr": 1.166541464596757e-05, "epoch": 0.33468286099865047, "percentage": 33.44, "elapsed_time": "0:44:49", "remaining_time": "1:29:12"}
{"current_steps": 315, "total_steps": 927, "loss": 1.3877858161926269, "lr": 1.1555808282681187e-05, "epoch": 0.340080971659919, "percentage": 33.98, "elapsed_time": "0:45:33", "remaining_time": "1:28:31"}
{"current_steps": 320, "total_steps": 927, "loss": 1.3945396423339844, "lr": 1.1444963730971009e-05, "epoch": 0.34547908232118757, "percentage": 34.52, "elapsed_time": "0:46:17", "remaining_time": "1:27:48"}
{"current_steps": 325, "total_steps": 927, "loss": 1.3506329536437989, "lr": 1.1332914830316416e-05, "epoch": 0.3508771929824561, "percentage": 35.06, "elapsed_time": "0:47:01", "remaining_time": "1:27:05"}
{"current_steps": 330, "total_steps": 927, "loss": 1.4695911407470703, "lr": 1.121969578786973e-05, "epoch": 0.3562753036437247, "percentage": 35.6, "elapsed_time": "0:47:44", "remaining_time": "1:26:21"}
{"current_steps": 335, "total_steps": 927, "loss": 1.350149440765381, "lr": 1.1105341168013172e-05, "epoch": 0.3616734143049933, "percentage": 36.14, "elapsed_time": "0:48:28", "remaining_time": "1:25:39"}
{"current_steps": 340, "total_steps": 927, "loss": 1.4387104034423828, "lr": 1.098988588180679e-05, "epoch": 0.36707152496626183, "percentage": 36.68, "elapsed_time": "0:49:11", "remaining_time": "1:24:55"}
{"current_steps": 345, "total_steps": 927, "loss": 1.3866162300109863, "lr": 1.0873365176330553e-05, "epoch": 0.3724696356275304, "percentage": 37.22, "elapsed_time": "0:49:55", "remaining_time": "1:24:12"}
{"current_steps": 350, "total_steps": 927, "loss": 1.4232500076293946, "lr": 1.0755814623923825e-05, "epoch": 0.37786774628879893, "percentage": 37.76, "elapsed_time": "0:50:37", "remaining_time": "1:23:28"}
{"current_steps": 355, "total_steps": 927, "loss": 1.483820629119873, "lr": 1.0637270111325591e-05, "epoch": 0.3832658569500675, "percentage": 38.3, "elapsed_time": "0:51:20", "remaining_time": "1:22:43"}
{"current_steps": 360, "total_steps": 927, "loss": 1.429130458831787, "lr": 1.0517767828718664e-05, "epoch": 0.38866396761133604, "percentage": 38.83, "elapsed_time": "0:52:04", "remaining_time": "1:22:00"}
{"current_steps": 365, "total_steps": 927, "loss": 1.435228157043457, "lr": 1.0397344258681267e-05, "epoch": 0.3940620782726046, "percentage": 39.37, "elapsed_time": "0:52:47", "remaining_time": "1:21:17"}
{"current_steps": 370, "total_steps": 927, "loss": 1.508815097808838, "lr": 1.027603616504936e-05, "epoch": 0.39946018893387314, "percentage": 39.91, "elapsed_time": "0:53:28", "remaining_time": "1:20:30"}
{"current_steps": 375, "total_steps": 927, "loss": 1.486521339416504, "lr": 1.0153880581693075e-05, "epoch": 0.4048582995951417, "percentage": 40.45, "elapsed_time": "0:54:11", "remaining_time": "1:19:46"}
{"current_steps": 380, "total_steps": 927, "loss": 1.3994467735290528, "lr": 1.0030914801210753e-05, "epoch": 0.41025641025641024, "percentage": 40.99, "elapsed_time": "0:54:56", "remaining_time": "1:19:05"}
{"current_steps": 385, "total_steps": 927, "loss": 1.417519474029541, "lr": 9.907176363543956e-06, "epoch": 0.4156545209176788, "percentage": 41.53, "elapsed_time": "0:55:39", "remaining_time": "1:18:21"}
{"current_steps": 390, "total_steps": 927, "loss": 1.485072708129883, "lr": 9.782703044516986e-06, "epoch": 0.42105263157894735, "percentage": 42.07, "elapsed_time": "0:56:23", "remaining_time": "1:17:38"}
{"current_steps": 395, "total_steps": 927, "loss": 1.4095831871032716, "lr": 9.657532844304396e-06, "epoch": 0.42645074224021595, "percentage": 42.61, "elapsed_time": "0:57:06", "remaining_time": "1:16:55"}
{"current_steps": 400, "total_steps": 927, "loss": 1.5393587112426759, "lr": 9.531703975829994e-06, "epoch": 0.4318488529014845, "percentage": 43.15, "elapsed_time": "0:57:48", "remaining_time": "1:16:10"}
{"current_steps": 405, "total_steps": 927, "loss": 1.4214500427246093, "lr": 9.405254853100927e-06, "epoch": 0.43724696356275305, "percentage": 43.69, "elapsed_time": "0:58:32", "remaining_time": "1:15:26"}
{"current_steps": 410, "total_steps": 927, "loss": 1.3928979873657226, "lr": 9.278224079480331e-06, "epoch": 0.4426450742240216, "percentage": 44.23, "elapsed_time": "0:59:17", "remaining_time": "1:14:45"}
{"current_steps": 415, "total_steps": 927, "loss": 1.4364460945129394, "lr": 9.150650435902215e-06, "epoch": 0.44804318488529016, "percentage": 44.77, "elapsed_time": "0:59:59", "remaining_time": "1:14:00"}
{"current_steps": 420, "total_steps": 927, "loss": 1.3835034370422363, "lr": 9.022572869032115e-06, "epoch": 0.4534412955465587, "percentage": 45.31, "elapsed_time": "1:00:43", "remaining_time": "1:13:17"}
{"current_steps": 425, "total_steps": 927, "loss": 1.4032472610473632, "lr": 8.894030479377152e-06, "epoch": 0.45883940620782726, "percentage": 45.85, "elapsed_time": "1:01:26", "remaining_time": "1:12:33"}
{"current_steps": 430, "total_steps": 927, "loss": 1.3748113632202148, "lr": 8.765062509349134e-06, "epoch": 0.4642375168690958, "percentage": 46.39, "elapsed_time": "1:02:10", "remaining_time": "1:11:51"}
{"current_steps": 435, "total_steps": 927, "loss": 1.4337423324584961, "lr": 8.635708331284326e-06, "epoch": 0.46963562753036436, "percentage": 46.93, "elapsed_time": "1:02:53", "remaining_time": "1:11:07"}
{"current_steps": 440, "total_steps": 927, "loss": 1.4276753425598145, "lr": 8.506007435423558e-06, "epoch": 0.4750337381916329, "percentage": 47.46, "elapsed_time": "1:03:36", "remaining_time": "1:10:24"}
{"current_steps": 445, "total_steps": 927, "loss": 1.3890512466430665, "lr": 8.375999417856343e-06, "epoch": 0.48043184885290147, "percentage": 48.0, "elapsed_time": "1:04:19", "remaining_time": "1:09:40"}
{"current_steps": 450, "total_steps": 927, "loss": 1.4220175743103027, "lr": 8.24572396843268e-06, "epoch": 0.48582995951417, "percentage": 48.54, "elapsed_time": "1:05:02", "remaining_time": "1:08:56"}
{"current_steps": 455, "total_steps": 927, "loss": 1.4079001426696778, "lr": 8.11522085864622e-06, "epoch": 0.49122807017543857, "percentage": 49.08, "elapsed_time": "1:05:46", "remaining_time": "1:08:13"}
{"current_steps": 460, "total_steps": 927, "loss": 1.369932270050049, "lr": 7.984529929492535e-06, "epoch": 0.4966261808367072, "percentage": 49.62, "elapsed_time": "1:06:31", "remaining_time": "1:07:32"}
{"current_steps": 465, "total_steps": 927, "loss": 1.269005298614502, "lr": 7.853691079306129e-06, "epoch": 0.5020242914979757, "percentage": 50.16, "elapsed_time": "1:07:16", "remaining_time": "1:06:50"}
{"current_steps": 470, "total_steps": 927, "loss": 1.3606270790100097, "lr": 7.722744251579988e-06, "epoch": 0.5074224021592443, "percentage": 50.7, "elapsed_time": "1:08:00", "remaining_time": "1:06:07"}
{"current_steps": 475, "total_steps": 927, "loss": 1.4284911155700684, "lr": 7.591729422771317e-06, "epoch": 0.5128205128205128, "percentage": 51.24, "elapsed_time": "1:08:44", "remaining_time": "1:05:24"}
{"current_steps": 480, "total_steps": 927, "loss": 1.449836254119873, "lr": 7.460686590097202e-06, "epoch": 0.5182186234817814, "percentage": 51.78, "elapsed_time": "1:09:27", "remaining_time": "1:04:40"}
{"current_steps": 485, "total_steps": 927, "loss": 1.3596923828125, "lr": 7.3296557593239795e-06, "epoch": 0.5236167341430499, "percentage": 52.32, "elapsed_time": "1:10:11", "remaining_time": "1:03:57"}
{"current_steps": 490, "total_steps": 927, "loss": 1.3217558860778809, "lr": 7.1986769325539485e-06, "epoch": 0.5290148448043185, "percentage": 52.86, "elapsed_time": "1:10:55", "remaining_time": "1:03:15"}
{"current_steps": 495, "total_steps": 927, "loss": 1.4159544944763183, "lr": 7.067790096013219e-06, "epoch": 0.5344129554655871, "percentage": 53.4, "elapsed_time": "1:11:38", "remaining_time": "1:02:31"}
{"current_steps": 500, "total_steps": 927, "loss": 1.4698023796081543, "lr": 6.93703520784442e-06, "epoch": 0.5398110661268556, "percentage": 53.94, "elapsed_time": "1:12:21", "remaining_time": "1:01:47"}
{"current_steps": 505, "total_steps": 927, "loss": 1.4592896461486817, "lr": 6.806452185907963e-06, "epoch": 0.5452091767881242, "percentage": 54.48, "elapsed_time": "1:13:04", "remaining_time": "1:01:04"}
{"current_steps": 510, "total_steps": 927, "loss": 1.440026092529297, "lr": 6.676080895595617e-06, "epoch": 0.5506072874493927, "percentage": 55.02, "elapsed_time": "1:13:47", "remaining_time": "1:00:20"}
{"current_steps": 515, "total_steps": 927, "loss": 1.4954944610595704, "lr": 6.545961137660077e-06, "epoch": 0.5560053981106613, "percentage": 55.56, "elapsed_time": "1:14:29", "remaining_time": "0:59:35"}
{"current_steps": 520, "total_steps": 927, "loss": 1.4568126678466797, "lr": 6.416132636064301e-06, "epoch": 0.5614035087719298, "percentage": 56.09, "elapsed_time": "1:15:12", "remaining_time": "0:58:52"}
{"current_steps": 525, "total_steps": 927, "loss": 1.4184711456298829, "lr": 6.2866350258542645e-06, "epoch": 0.5668016194331984, "percentage": 56.63, "elapsed_time": "1:15:55", "remaining_time": "0:58:08"}
{"current_steps": 530, "total_steps": 927, "loss": 1.4063173294067384, "lr": 6.157507841058874e-06, "epoch": 0.5721997300944669, "percentage": 57.17, "elapsed_time": "1:16:37", "remaining_time": "0:57:24"}
{"current_steps": 535, "total_steps": 927, "loss": 1.3004539489746094, "lr": 6.028790502620701e-06, "epoch": 0.5775978407557355, "percentage": 57.71, "elapsed_time": "1:17:23", "remaining_time": "0:56:42"}
{"current_steps": 540, "total_steps": 927, "loss": 1.3872806549072265, "lr": 5.900522306361271e-06, "epoch": 0.582995951417004, "percentage": 58.25, "elapsed_time": "1:18:06", "remaining_time": "0:55:58"}
{"current_steps": 545, "total_steps": 927, "loss": 1.3209671020507812, "lr": 5.772742410984511e-06, "epoch": 0.5883940620782726, "percentage": 58.79, "elapsed_time": "1:18:51", "remaining_time": "0:55:16"}
{"current_steps": 550, "total_steps": 927, "loss": 1.5138866424560546, "lr": 5.645489826122098e-06, "epoch": 0.5937921727395412, "percentage": 59.33, "elapsed_time": "1:19:32", "remaining_time": "0:54:31"}
{"current_steps": 555, "total_steps": 927, "loss": 1.383652400970459, "lr": 5.518803400424286e-06, "epoch": 0.5991902834008097, "percentage": 59.87, "elapsed_time": "1:20:15", "remaining_time": "0:53:47"}
{"current_steps": 560, "total_steps": 927, "loss": 1.4016658782958984, "lr": 5.392721809699897e-06, "epoch": 0.6045883940620783, "percentage": 60.41, "elapsed_time": "1:20:59", "remaining_time": "0:53:04"}
{"current_steps": 565, "total_steps": 927, "loss": 1.3988656997680664, "lr": 5.267283545109068e-06, "epoch": 0.6099865047233468, "percentage": 60.95, "elapsed_time": "1:21:42", "remaining_time": "0:52:21"}
{"current_steps": 570, "total_steps": 927, "loss": 1.4131988525390624, "lr": 5.142526901412366e-06, "epoch": 0.6153846153846154, "percentage": 61.49, "elapsed_time": "1:22:25", "remaining_time": "0:51:37"}
{"current_steps": 575, "total_steps": 927, "loss": 1.3934114456176758, "lr": 5.018489965279887e-06, "epoch": 0.6207827260458839, "percentage": 62.03, "elapsed_time": "1:23:08", "remaining_time": "0:50:54"}
{"current_steps": 580, "total_steps": 927, "loss": 1.3578675270080567, "lr": 4.895210603663849e-06, "epoch": 0.6261808367071525, "percentage": 62.57, "elapsed_time": "1:23:53", "remaining_time": "0:50:11"}
{"current_steps": 585, "total_steps": 927, "loss": 1.4002360343933105, "lr": 4.772726452238277e-06, "epoch": 0.631578947368421, "percentage": 63.11, "elapsed_time": "1:24:37", "remaining_time": "0:49:28"}
{"current_steps": 590, "total_steps": 927, "loss": 1.2647083282470704, "lr": 4.651074903909303e-06, "epoch": 0.6369770580296896, "percentage": 63.65, "elapsed_time": "1:25:21", "remaining_time": "0:48:45"}
{"current_steps": 595, "total_steps": 927, "loss": 1.402871036529541, "lr": 4.5302930973995636e-06, "epoch": 0.6423751686909581, "percentage": 64.19, "elapsed_time": "1:26:05", "remaining_time": "0:48:02"}
{"current_steps": 600, "total_steps": 927, "loss": 1.3439860343933105, "lr": 4.4104179059102066e-06, "epoch": 0.6477732793522267, "percentage": 64.72, "elapsed_time": "1:26:48", "remaining_time": "0:47:18"}
{"current_steps": 605, "total_steps": 927, "loss": 1.3316984176635742, "lr": 4.291485925863952e-06, "epoch": 0.6531713900134952, "percentage": 65.26, "elapsed_time": "1:27:32", "remaining_time": "0:46:35"}
{"current_steps": 610, "total_steps": 927, "loss": 1.4628570556640625, "lr": 4.173533465732669e-06, "epoch": 0.6585695006747638, "percentage": 65.8, "elapsed_time": "1:28:15", "remaining_time": "0:45:51"}
{"current_steps": 615, "total_steps": 927, "loss": 1.3681221961975099, "lr": 4.056596534952823e-06, "epoch": 0.6639676113360324, "percentage": 66.34, "elapsed_time": "1:28:58", "remaining_time": "0:45:08"}
{"current_steps": 620, "total_steps": 927, "loss": 1.4698673248291017, "lr": 3.940710832932262e-06, "epoch": 0.6693657219973009, "percentage": 66.88, "elapsed_time": "1:29:41", "remaining_time": "0:44:24"}
{"current_steps": 625, "total_steps": 927, "loss": 1.3489319801330566, "lr": 3.8259117381516e-06, "epoch": 0.6747638326585695, "percentage": 67.42, "elapsed_time": "1:30:25", "remaining_time": "0:43:41"}
{"current_steps": 630, "total_steps": 927, "loss": 1.3783289909362793, "lr": 3.712234297363618e-06, "epoch": 0.680161943319838, "percentage": 67.96, "elapsed_time": "1:31:09", "remaining_time": "0:42:58"}
{"current_steps": 635, "total_steps": 927, "loss": 1.5137944221496582, "lr": 3.5997132148939237e-06, "epoch": 0.6855600539811066, "percentage": 68.5, "elapsed_time": "1:31:52", "remaining_time": "0:42:14"}
{"current_steps": 640, "total_steps": 927, "loss": 1.2776326179504394, "lr": 3.488382842046137e-06, "epoch": 0.6909581646423751, "percentage": 69.04, "elapsed_time": "1:32:37", "remaining_time": "0:41:32"}
{"current_steps": 645, "total_steps": 927, "loss": 1.3425775527954102, "lr": 3.3782771666148696e-06, "epoch": 0.6963562753036437, "percentage": 69.58, "elapsed_time": "1:33:21", "remaining_time": "0:40:49"}
{"current_steps": 650, "total_steps": 927, "loss": 1.3643362998962403, "lr": 3.26942980250965e-06, "epoch": 0.7017543859649122, "percentage": 70.12, "elapsed_time": "1:34:06", "remaining_time": "0:40:06"}
{"current_steps": 655, "total_steps": 927, "loss": 1.4447607040405273, "lr": 3.1618739794930366e-06, "epoch": 0.7071524966261808, "percentage": 70.66, "elapsed_time": "1:34:50", "remaining_time": "0:39:23"}
{"current_steps": 660, "total_steps": 927, "loss": 1.406121826171875, "lr": 3.055642533035964e-06, "epoch": 0.7125506072874493, "percentage": 71.2, "elapsed_time": "1:35:33", "remaining_time": "0:38:39"}
{"current_steps": 665, "total_steps": 927, "loss": 1.2962283134460448, "lr": 2.9507678942934702e-06, "epoch": 0.717948717948718, "percentage": 71.74, "elapsed_time": "1:36:18", "remaining_time": "0:37:56"}
{"current_steps": 670, "total_steps": 927, "loss": 1.3783414840698243, "lr": 2.8472820802038847e-06, "epoch": 0.7233468286099866, "percentage": 72.28, "elapsed_time": "1:37:01", "remaining_time": "0:37:13"}
{"current_steps": 675, "total_steps": 927, "loss": 1.3261849403381347, "lr": 2.745216683714428e-06, "epoch": 0.728744939271255, "percentage": 72.82, "elapsed_time": "1:37:46", "remaining_time": "0:36:30"}
{"current_steps": 680, "total_steps": 927, "loss": 1.5042543411254883, "lr": 2.6446028641362934e-06, "epoch": 0.7341430499325237, "percentage": 73.35, "elapsed_time": "1:38:30", "remaining_time": "0:35:46"}
{"current_steps": 685, "total_steps": 927, "loss": 1.3572941780090333, "lr": 2.5454713376320764e-06, "epoch": 0.7395411605937922, "percentage": 73.89, "elapsed_time": "1:39:14", "remaining_time": "0:35:03"}
{"current_steps": 690, "total_steps": 927, "loss": 1.3866613388061524, "lr": 2.4478523678385194e-06, "epoch": 0.7449392712550608, "percentage": 74.43, "elapsed_time": "1:39:58", "remaining_time": "0:34:20"}
{"current_steps": 695, "total_steps": 927, "loss": 1.4149866104125977, "lr": 2.3517757566273827e-06, "epoch": 0.7503373819163293, "percentage": 74.97, "elapsed_time": "1:40:40", "remaining_time": "0:33:36"}
{"current_steps": 700, "total_steps": 927, "loss": 1.3730114936828612, "lr": 2.257270835007314e-06, "epoch": 0.7557354925775979, "percentage": 75.51, "elapsed_time": "1:41:24", "remaining_time": "0:32:53"}
{"current_steps": 705, "total_steps": 927, "loss": 1.2785679817199707, "lr": 2.1643664541694376e-06, "epoch": 0.7611336032388664, "percentage": 76.05, "elapsed_time": "1:42:08", "remaining_time": "0:32:09"}
{"current_steps": 710, "total_steps": 927, "loss": 1.229942226409912, "lr": 2.073090976679452e-06, "epoch": 0.766531713900135, "percentage": 76.59, "elapsed_time": "1:42:53", "remaining_time": "0:31:26"}
{"current_steps": 715, "total_steps": 927, "loss": 1.3718143463134767, "lr": 1.983472267818883e-06, "epoch": 0.7719298245614035, "percentage": 77.13, "elapsed_time": "1:43:35", "remaining_time": "0:30:43"}
{"current_steps": 720, "total_steps": 927, "loss": 1.402730655670166, "lr": 1.8955376870781552e-06, "epoch": 0.7773279352226721, "percentage": 77.67, "elapsed_time": "1:44:19", "remaining_time": "0:29:59"}
{"current_steps": 725, "total_steps": 927, "loss": 1.3430524826049806, "lr": 1.8093140798040686e-06, "epoch": 0.7827260458839406, "percentage": 78.21, "elapsed_time": "1:45:03", "remaining_time": "0:29:16"}
{"current_steps": 730, "total_steps": 927, "loss": 1.4013592720031738, "lr": 1.7248277690042604e-06, "epoch": 0.7881241565452092, "percentage": 78.75, "elapsed_time": "1:45:45", "remaining_time": "0:28:32"}
{"current_steps": 735, "total_steps": 927, "loss": 1.407256507873535, "lr": 1.642104547311099e-06, "epoch": 0.7935222672064778, "percentage": 79.29, "elapsed_time": "1:46:28", "remaining_time": "0:27:48"}
{"current_steps": 740, "total_steps": 927, "loss": 1.4018988609313965, "lr": 1.5611696691075208e-06, "epoch": 0.7989203778677463, "percentage": 79.83, "elapsed_time": "1:47:11", "remaining_time": "0:27:05"}
{"current_steps": 745, "total_steps": 927, "loss": 1.3888368606567383, "lr": 1.4820478428171713e-06, "epoch": 0.8043184885290149, "percentage": 80.37, "elapsed_time": "1:47:55", "remaining_time": "0:26:22"}
{"current_steps": 750, "total_steps": 927, "loss": 1.444268035888672, "lr": 1.4047632233612263e-06, "epoch": 0.8097165991902834, "percentage": 80.91, "elapsed_time": "1:48:38", "remaining_time": "0:25:38"}
{"current_steps": 755, "total_steps": 927, "loss": 1.4442663192749023, "lr": 1.3293394047841987e-06, "epoch": 0.815114709851552, "percentage": 81.45, "elapsed_time": "1:49:22", "remaining_time": "0:24:55"}
{"current_steps": 760, "total_steps": 927, "loss": 1.4278512001037598, "lr": 1.2557994130509583e-06, "epoch": 0.8205128205128205, "percentage": 81.98, "elapsed_time": "1:50:05", "remaining_time": "0:24:11"}
{"current_steps": 765, "total_steps": 927, "loss": 1.4104692459106445, "lr": 1.184165699017195e-06, "epoch": 0.8259109311740891, "percentage": 82.52, "elapsed_time": "1:50:48", "remaining_time": "0:23:27"}
{"current_steps": 770, "total_steps": 927, "loss": 1.3686716079711914, "lr": 1.1144601315754397e-06, "epoch": 0.8313090418353576, "percentage": 83.06, "elapsed_time": "1:51:32", "remaining_time": "0:22:44"}
{"current_steps": 775, "total_steps": 927, "loss": 1.4443007469177247, "lr": 1.0467039909787668e-06, "epoch": 0.8367071524966262, "percentage": 83.6, "elapsed_time": "1:52:14", "remaining_time": "0:22:00"}
{"current_steps": 780, "total_steps": 927, "loss": 1.411851978302002, "lr": 9.809179623441958e-07, "epoch": 0.8421052631578947, "percentage": 84.14, "elapsed_time": "1:52:56", "remaining_time": "0:21:17"}
{"current_steps": 785, "total_steps": 927, "loss": 1.491429901123047, "lr": 9.171221293377735e-07, "epoch": 0.8475033738191633, "percentage": 84.68, "elapsed_time": "1:53:39", "remaining_time": "0:20:33"}
{"current_steps": 790, "total_steps": 927, "loss": 1.3643847465515138, "lr": 8.553359680432815e-07, "epoch": 0.8529014844804319, "percentage": 85.22, "elapsed_time": "1:54:22", "remaining_time": "0:19:50"}
{"current_steps": 795, "total_steps": 927, "loss": 1.3733964920043946, "lr": 7.95578341016428e-07, "epoch": 0.8582995951417004, "percentage": 85.76, "elapsed_time": "1:55:06", "remaining_time": "0:19:06"}
{"current_steps": 800, "total_steps": 927, "loss": 1.270117950439453, "lr": 7.378674915263359e-07, "epoch": 0.863697705802969, "percentage": 86.3, "elapsed_time": "1:55:52", "remaining_time": "0:18:23"}
{"current_steps": 805, "total_steps": 927, "loss": 1.4278650283813477, "lr": 6.822210379861002e-07, "epoch": 0.8690958164642375, "percentage": 86.84, "elapsed_time": "1:56:35", "remaining_time": "0:17:40"}
{"current_steps": 810, "total_steps": 927, "loss": 1.388138484954834, "lr": 6.286559685741076e-07, "epoch": 0.8744939271255061, "percentage": 87.38, "elapsed_time": "1:57:19", "remaining_time": "0:16:56"}
{"current_steps": 815, "total_steps": 927, "loss": 1.5160203933715821, "lr": 5.77188636047746e-07, "epoch": 0.8798920377867746, "percentage": 87.92, "elapsed_time": "1:58:02", "remaining_time": "0:16:13"}
{"current_steps": 820, "total_steps": 927, "loss": 1.3769659042358398, "lr": 5.278347527511174e-07, "epoch": 0.8852901484480432, "percentage": 88.46, "elapsed_time": "1:58:46", "remaining_time": "0:15:29"}
{"current_steps": 825, "total_steps": 927, "loss": 1.4992185592651368, "lr": 4.806093858182428e-07, "epoch": 0.8906882591093117, "percentage": 89.0, "elapsed_time": "1:59:28", "remaining_time": "0:14:46"}
{"current_steps": 830, "total_steps": 927, "loss": 1.3635730743408203, "lr": 4.3552695257325775e-07, "epoch": 0.8960863697705803, "percentage": 89.54, "elapsed_time": "2:00:11", "remaining_time": "0:14:02"}
{"current_steps": 835, "total_steps": 927, "loss": 1.4149579048156737, "lr": 3.9260121612898244e-07, "epoch": 0.9014844804318488, "percentage": 90.08, "elapsed_time": "2:00:53", "remaining_time": "0:13:19"}
{"current_steps": 840, "total_steps": 927, "loss": 1.4671350479125977, "lr": 3.5184528118520296e-07, "epoch": 0.9068825910931174, "percentage": 90.61, "elapsed_time": "2:01:35", "remaining_time": "0:12:35"}
{"current_steps": 845, "total_steps": 927, "loss": 1.413409423828125, "lr": 3.132715900279809e-07, "epoch": 0.9122807017543859, "percentage": 91.15, "elapsed_time": "2:02:18", "remaining_time": "0:11:52"}
{"current_steps": 850, "total_steps": 927, "loss": 1.399053192138672, "lr": 2.768919187311614e-07, "epoch": 0.9176788124156545, "percentage": 91.69, "elapsed_time": "2:03:01", "remaining_time": "0:11:08"}
{"current_steps": 855, "total_steps": 927, "loss": 1.3476950645446777, "lr": 2.4271737356129585e-07, "epoch": 0.9230769230769231, "percentage": 92.23, "elapsed_time": "2:03:44", "remaining_time": "0:10:25"}
{"current_steps": 860, "total_steps": 927, "loss": 1.3789938926696776, "lr": 2.107583875870267e-07, "epoch": 0.9284750337381916, "percentage": 92.77, "elapsed_time": "2:04:27", "remaining_time": "0:09:41"}
{"current_steps": 865, "total_steps": 927, "loss": 1.3317445755004882, "lr": 1.810247174940058e-07, "epoch": 0.9338731443994602, "percentage": 93.31, "elapsed_time": "2:05:10", "remaining_time": "0:08:58"}
{"current_steps": 870, "total_steps": 927, "loss": 1.4837261199951173, "lr": 1.5352544060629136e-07, "epoch": 0.9392712550607287, "percentage": 93.85, "elapsed_time": "2:05:52", "remaining_time": "0:08:14"}
{"current_steps": 875, "total_steps": 927, "loss": 1.2977308273315429, "lr": 1.282689521151581e-07, "epoch": 0.9446693657219973, "percentage": 94.39, "elapsed_time": "2:06:36", "remaining_time": "0:07:31"}
{"current_steps": 880, "total_steps": 927, "loss": 1.3634986877441406, "lr": 1.0526296251614554e-07, "epoch": 0.9500674763832658, "percentage": 94.93, "elapsed_time": "2:07:20", "remaining_time": "0:06:48"}
{"current_steps": 885, "total_steps": 927, "loss": 1.5160835266113282, "lr": 8.451449525514021e-08, "epoch": 0.9554655870445344, "percentage": 95.47, "elapsed_time": "2:08:02", "remaining_time": "0:06:04"}
{"current_steps": 890, "total_steps": 927, "loss": 1.5019266128540039, "lr": 6.602988458420417e-08, "epoch": 0.9608636977058029, "percentage": 96.01, "elapsed_time": "2:08:44", "remaining_time": "0:05:21"}
{"current_steps": 895, "total_steps": 927, "loss": 1.4313615798950194, "lr": 4.981477362780429e-08, "epoch": 0.9662618083670715, "percentage": 96.55, "elapsed_time": "2:09:28", "remaining_time": "0:04:37"}
{"current_steps": 900, "total_steps": 927, "loss": 1.4134346008300782, "lr": 3.587411266003371e-08, "epoch": 0.97165991902834, "percentage": 97.09, "elapsed_time": "2:10:12", "remaining_time": "0:03:54"}
{"current_steps": 905, "total_steps": 927, "loss": 1.3511739730834962, "lr": 2.4212157593359873e-08, "epoch": 0.9770580296896086, "percentage": 97.63, "elapsed_time": "2:10:54", "remaining_time": "0:03:10"}
{"current_steps": 910, "total_steps": 927, "loss": 1.348922061920166, "lr": 1.4832468679341348e-08, "epoch": 0.9824561403508771, "percentage": 98.17, "elapsed_time": "2:11:38", "remaining_time": "0:02:27"}
{"current_steps": 915, "total_steps": 927, "loss": 1.4228689193725585, "lr": 7.737909421730583e-09, "epoch": 0.9878542510121457, "percentage": 98.71, "elapsed_time": "2:12:20", "remaining_time": "0:01:44"}
{"current_steps": 920, "total_steps": 927, "loss": 1.319122886657715, "lr": 2.930645702277357e-09, "epoch": 0.9932523616734144, "percentage": 99.24, "elapsed_time": "2:13:03", "remaining_time": "0:01:00"}
{"current_steps": 925, "total_steps": 927, "loss": 1.3635743141174317, "lr": 4.1214511951603864e-10, "epoch": 0.9986504723346828, "percentage": 99.78, "elapsed_time": "2:13:47", "remaining_time": "0:00:17"}
{"current_steps": 927, "total_steps": 927, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "2:13:59", "remaining_time": "0:00:00"}