dd_un-mdl-8b-inst / .ipynb_checkpoints /trainer_log-checkpoint.jsonl
qxsecureserver's picture
Upload folder using huggingface_hub
74f10f8 verified
{"current_steps": 10, "total_steps": 1515, "loss": 1.4192, "learning_rate": 4.347826086956522e-06, "epoch": 0.019770171753367108, "percentage": 0.66, "elapsed_time": "0:02:04", "remaining_time": "5:12:51"}
{"current_steps": 20, "total_steps": 1515, "loss": 0.9179, "learning_rate": 8.695652173913044e-06, "epoch": 0.039540343506734216, "percentage": 1.32, "elapsed_time": "0:03:59", "remaining_time": "4:58:39"}
{"current_steps": 30, "total_steps": 1515, "loss": 0.6842, "learning_rate": 1.3043478260869566e-05, "epoch": 0.059310515260101324, "percentage": 1.98, "elapsed_time": "0:05:58", "remaining_time": "4:56:09"}
{"current_steps": 40, "total_steps": 1515, "loss": 0.5843, "learning_rate": 1.739130434782609e-05, "epoch": 0.07908068701346843, "percentage": 2.64, "elapsed_time": "0:07:54", "remaining_time": "4:51:24"}
{"current_steps": 50, "total_steps": 1515, "loss": 0.5283, "learning_rate": 1.999963411593758e-05, "epoch": 0.09885085876683554, "percentage": 3.3, "elapsed_time": "0:09:53", "remaining_time": "4:49:58"}
{"current_steps": 60, "total_steps": 1515, "loss": 0.513, "learning_rate": 1.9995518227714435e-05, "epoch": 0.11862103052020265, "percentage": 3.96, "elapsed_time": "0:11:46", "remaining_time": "4:45:41"}
{"current_steps": 70, "total_steps": 1515, "loss": 0.498, "learning_rate": 1.9986830984827473e-05, "epoch": 0.13839120227356974, "percentage": 4.62, "elapsed_time": "0:13:40", "remaining_time": "4:42:21"}
{"current_steps": 80, "total_steps": 1515, "loss": 0.4801, "learning_rate": 1.9973576360304135e-05, "epoch": 0.15816137402693686, "percentage": 5.28, "elapsed_time": "0:15:35", "remaining_time": "4:39:32"}
{"current_steps": 90, "total_steps": 1515, "loss": 0.4764, "learning_rate": 1.9955760416020185e-05, "epoch": 0.17793154578030396, "percentage": 5.94, "elapsed_time": "0:17:32", "remaining_time": "4:37:44"}
{"current_steps": 100, "total_steps": 1515, "loss": 0.4707, "learning_rate": 1.9933391299927346e-05, "epoch": 0.19770171753367108, "percentage": 6.6, "elapsed_time": "0:19:37", "remaining_time": "4:37:38"}
{"current_steps": 110, "total_steps": 1515, "loss": 0.4438, "learning_rate": 1.9906479242326927e-05, "epoch": 0.21747188928703817, "percentage": 7.26, "elapsed_time": "0:21:32", "remaining_time": "4:35:10"}
{"current_steps": 120, "total_steps": 1515, "loss": 0.4507, "learning_rate": 1.987503655119108e-05, "epoch": 0.2372420610404053, "percentage": 7.92, "elapsed_time": "0:23:26", "remaining_time": "4:32:30"}
{"current_steps": 130, "total_steps": 1515, "loss": 0.4489, "learning_rate": 1.9839077606533878e-05, "epoch": 0.2570122327937724, "percentage": 8.58, "elapsed_time": "0:25:29", "remaining_time": "4:31:33"}
{"current_steps": 140, "total_steps": 1515, "loss": 0.4507, "learning_rate": 1.9798618853834747e-05, "epoch": 0.2767824045471395, "percentage": 9.24, "elapsed_time": "0:27:28", "remaining_time": "4:29:48"}
{"current_steps": 150, "total_steps": 1515, "loss": 0.4542, "learning_rate": 1.975367879651728e-05, "epoch": 0.29655257630050663, "percentage": 9.9, "elapsed_time": "0:29:30", "remaining_time": "4:28:30"}
{"current_steps": 160, "total_steps": 1515, "loss": 0.439, "learning_rate": 1.970427798748689e-05, "epoch": 0.3163227480538737, "percentage": 10.56, "elapsed_time": "0:31:23", "remaining_time": "4:25:53"}
{"current_steps": 170, "total_steps": 1515, "loss": 0.4281, "learning_rate": 1.965043901973111e-05, "epoch": 0.3360929198072408, "percentage": 11.22, "elapsed_time": "0:33:16", "remaining_time": "4:23:17"}
{"current_steps": 180, "total_steps": 1515, "loss": 0.4255, "learning_rate": 1.9592186515986932e-05, "epoch": 0.3558630915606079, "percentage": 11.88, "elapsed_time": "0:35:09", "remaining_time": "4:20:47"}
{"current_steps": 190, "total_steps": 1515, "loss": 0.4275, "learning_rate": 1.9529547117479802e-05, "epoch": 0.37563326331397506, "percentage": 12.54, "elapsed_time": "0:37:05", "remaining_time": "4:18:42"}
{"current_steps": 200, "total_steps": 1515, "loss": 0.4391, "learning_rate": 1.9462549471739546e-05, "epoch": 0.39540343506734216, "percentage": 13.2, "elapsed_time": "0:39:11", "remaining_time": "4:17:39"}
{"current_steps": 210, "total_steps": 1515, "loss": 0.4316, "learning_rate": 1.939122421949868e-05, "epoch": 0.41517360682070925, "percentage": 13.86, "elapsed_time": "0:41:30", "remaining_time": "4:17:58"}
{"current_steps": 220, "total_steps": 1515, "loss": 0.4309, "learning_rate": 1.931560398067915e-05, "epoch": 0.43494377857407635, "percentage": 14.52, "elapsed_time": "0:43:33", "remaining_time": "4:16:24"}
{"current_steps": 230, "total_steps": 1515, "loss": 0.4228, "learning_rate": 1.923572333947395e-05, "epoch": 0.4547139503274435, "percentage": 15.18, "elapsed_time": "0:45:34", "remaining_time": "4:14:37"}
{"current_steps": 240, "total_steps": 1515, "loss": 0.4132, "learning_rate": 1.9151618828530347e-05, "epoch": 0.4744841220808106, "percentage": 15.84, "elapsed_time": "0:47:29", "remaining_time": "4:12:15"}
{"current_steps": 250, "total_steps": 1515, "loss": 0.4201, "learning_rate": 1.9063328912242047e-05, "epoch": 0.4942542938341777, "percentage": 16.5, "elapsed_time": "0:49:22", "remaining_time": "4:09:51"}
{"current_steps": 260, "total_steps": 1515, "loss": 0.4175, "learning_rate": 1.8970893969157852e-05, "epoch": 0.5140244655875448, "percentage": 17.16, "elapsed_time": "0:51:17", "remaining_time": "4:07:35"}
{"current_steps": 270, "total_steps": 1515, "loss": 0.4063, "learning_rate": 1.8874356273514934e-05, "epoch": 0.5337946373409119, "percentage": 17.82, "elapsed_time": "0:53:16", "remaining_time": "4:05:41"}
{"current_steps": 280, "total_steps": 1515, "loss": 0.4218, "learning_rate": 1.8773759975905098e-05, "epoch": 0.553564809094279, "percentage": 18.48, "elapsed_time": "0:55:20", "remaining_time": "4:04:07"}
{"current_steps": 290, "total_steps": 1515, "loss": 0.4134, "learning_rate": 1.8669151083082955e-05, "epoch": 0.5733349808476461, "percentage": 19.14, "elapsed_time": "0:57:20", "remaining_time": "4:02:13"}
{"current_steps": 300, "total_steps": 1515, "loss": 0.3988, "learning_rate": 1.8560577436925144e-05, "epoch": 0.5931051526010133, "percentage": 19.8, "elapsed_time": "0:59:28", "remaining_time": "4:00:50"}
{"current_steps": 310, "total_steps": 1515, "loss": 0.4175, "learning_rate": 1.8448088692550337e-05, "epoch": 0.6128753243543803, "percentage": 20.46, "elapsed_time": "1:01:28", "remaining_time": "3:58:58"}
{"current_steps": 320, "total_steps": 1515, "loss": 0.409, "learning_rate": 1.833173629560993e-05, "epoch": 0.6326454961077475, "percentage": 21.12, "elapsed_time": "1:03:27", "remaining_time": "3:56:58"}
{"current_steps": 330, "total_steps": 1515, "loss": 0.3997, "learning_rate": 1.8211573458759854e-05, "epoch": 0.6524156678611145, "percentage": 21.78, "elapsed_time": "1:05:25", "remaining_time": "3:54:55"}
{"current_steps": 340, "total_steps": 1515, "loss": 0.4015, "learning_rate": 1.80876551373243e-05, "epoch": 0.6721858396144816, "percentage": 22.44, "elapsed_time": "1:07:16", "remaining_time": "3:52:30"}
{"current_steps": 350, "total_steps": 1515, "loss": 0.4048, "learning_rate": 1.7960038004162426e-05, "epoch": 0.6919560113678488, "percentage": 23.1, "elapsed_time": "1:09:16", "remaining_time": "3:50:34"}
{"current_steps": 360, "total_steps": 1515, "loss": 0.4075, "learning_rate": 1.7828780423749536e-05, "epoch": 0.7117261831212158, "percentage": 23.76, "elapsed_time": "1:11:17", "remaining_time": "3:48:43"}
{"current_steps": 370, "total_steps": 1515, "loss": 0.4102, "learning_rate": 1.769394242548469e-05, "epoch": 0.731496354874583, "percentage": 24.42, "elapsed_time": "1:13:20", "remaining_time": "3:46:57"}
{"current_steps": 380, "total_steps": 1515, "loss": 0.396, "learning_rate": 1.755558567623678e-05, "epoch": 0.7512665266279501, "percentage": 25.08, "elapsed_time": "1:15:30", "remaining_time": "3:45:33"}
{"current_steps": 390, "total_steps": 1515, "loss": 0.4063, "learning_rate": 1.741377345214184e-05, "epoch": 0.7710366983813172, "percentage": 25.74, "elapsed_time": "1:17:33", "remaining_time": "3:43:42"}
{"current_steps": 400, "total_steps": 1515, "loss": 0.4066, "learning_rate": 1.7268570609664253e-05, "epoch": 0.7908068701346843, "percentage": 26.4, "elapsed_time": "1:19:43", "remaining_time": "3:42:13"}
{"current_steps": 410, "total_steps": 1515, "loss": 0.3848, "learning_rate": 1.71200435559353e-05, "epoch": 0.8105770418880514, "percentage": 27.06, "elapsed_time": "1:21:47", "remaining_time": "3:40:26"}
{"current_steps": 420, "total_steps": 1515, "loss": 0.3882, "learning_rate": 1.6968260218382484e-05, "epoch": 0.8303472136414185, "percentage": 27.72, "elapsed_time": "1:23:45", "remaining_time": "3:38:22"}
{"current_steps": 430, "total_steps": 1515, "loss": 0.3957, "learning_rate": 1.6813290013663573e-05, "epoch": 0.8501173853947857, "percentage": 28.38, "elapsed_time": "1:25:47", "remaining_time": "3:36:27"}
{"current_steps": 440, "total_steps": 1515, "loss": 0.3958, "learning_rate": 1.665520381591955e-05, "epoch": 0.8698875571481527, "percentage": 29.04, "elapsed_time": "1:27:59", "remaining_time": "3:34:57"}
{"current_steps": 450, "total_steps": 1515, "loss": 0.3846, "learning_rate": 1.6494073924361012e-05, "epoch": 0.8896577289015198, "percentage": 29.7, "elapsed_time": "1:29:50", "remaining_time": "3:32:37"}
{"current_steps": 460, "total_steps": 1515, "loss": 0.3925, "learning_rate": 1.6329974030202803e-05, "epoch": 0.909427900654887, "percentage": 30.36, "elapsed_time": "1:31:46", "remaining_time": "3:30:28"}
{"current_steps": 470, "total_steps": 1515, "loss": 0.3806, "learning_rate": 1.6162979182962068e-05, "epoch": 0.929198072408254, "percentage": 31.02, "elapsed_time": "1:33:50", "remaining_time": "3:28:39"}
{"current_steps": 480, "total_steps": 1515, "loss": 0.4075, "learning_rate": 1.5993165756135035e-05, "epoch": 0.9489682441616212, "percentage": 31.68, "elapsed_time": "1:36:09", "remaining_time": "3:27:20"}
{"current_steps": 490, "total_steps": 1515, "loss": 0.3771, "learning_rate": 1.5820611412268366e-05, "epoch": 0.9687384159149882, "percentage": 32.34, "elapsed_time": "1:38:20", "remaining_time": "3:25:42"}
{"current_steps": 500, "total_steps": 1515, "loss": 0.3869, "learning_rate": 1.564539506744091e-05, "epoch": 0.9885085876683554, "percentage": 33.0, "elapsed_time": "1:40:15", "remaining_time": "3:23:32"}
{"current_steps": 500, "total_steps": 1515, "eval_loss": 0.39637455344200134, "epoch": 0.9885085876683554, "percentage": 33.0, "elapsed_time": "1:41:37", "remaining_time": "3:26:17"}
{"current_steps": 510, "total_steps": 1515, "loss": 0.356, "learning_rate": 1.546759685517219e-05, "epoch": 1.0082787594217224, "percentage": 33.66, "elapsed_time": "1:44:11", "remaining_time": "3:25:20"}
{"current_steps": 520, "total_steps": 1515, "loss": 0.3228, "learning_rate": 1.528729808977412e-05, "epoch": 1.0280489311750896, "percentage": 34.32, "elapsed_time": "1:46:14", "remaining_time": "3:23:18"}
{"current_steps": 530, "total_steps": 1515, "loss": 0.3182, "learning_rate": 1.5104581229162674e-05, "epoch": 1.0478191029284567, "percentage": 34.98, "elapsed_time": "1:48:23", "remaining_time": "3:21:26"}
{"current_steps": 540, "total_steps": 1515, "loss": 0.3171, "learning_rate": 1.4919529837146529e-05, "epoch": 1.0675892746818239, "percentage": 35.64, "elapsed_time": "1:50:31", "remaining_time": "3:19:33"}
{"current_steps": 550, "total_steps": 1515, "loss": 0.3202, "learning_rate": 1.4732228545209993e-05, "epoch": 1.087359446435191, "percentage": 36.3, "elapsed_time": "1:52:31", "remaining_time": "3:17:25"}
{"current_steps": 560, "total_steps": 1515, "loss": 0.3121, "learning_rate": 1.4542763013807568e-05, "epoch": 1.107129618188558, "percentage": 36.96, "elapsed_time": "1:54:37", "remaining_time": "3:15:28"}
{"current_steps": 570, "total_steps": 1515, "loss": 0.3179, "learning_rate": 1.4351219893187984e-05, "epoch": 1.126899789941925, "percentage": 37.62, "elapsed_time": "1:56:39", "remaining_time": "3:13:23"}
{"current_steps": 580, "total_steps": 1515, "loss": 0.3112, "learning_rate": 1.4157686783765534e-05, "epoch": 1.1466699616952922, "percentage": 38.28, "elapsed_time": "1:58:36", "remaining_time": "3:11:11"}
{"current_steps": 590, "total_steps": 1515, "loss": 0.32, "learning_rate": 1.3962252196056847e-05, "epoch": 1.1664401334486594, "percentage": 38.94, "elapsed_time": "2:00:38", "remaining_time": "3:09:08"}
{"current_steps": 600, "total_steps": 1515, "loss": 0.3156, "learning_rate": 1.3765005510201466e-05, "epoch": 1.1862103052020265, "percentage": 39.6, "elapsed_time": "2:02:27", "remaining_time": "3:06:44"}
{"current_steps": 610, "total_steps": 1515, "loss": 0.3196, "learning_rate": 1.3566036935084692e-05, "epoch": 1.2059804769553935, "percentage": 40.26, "elapsed_time": "2:04:31", "remaining_time": "3:04:44"}
{"current_steps": 620, "total_steps": 1515, "loss": 0.3218, "learning_rate": 1.3365437467081406e-05, "epoch": 1.2257506487087606, "percentage": 40.92, "elapsed_time": "2:06:25", "remaining_time": "3:02:29"}
{"current_steps": 630, "total_steps": 1515, "loss": 0.315, "learning_rate": 1.3163298848439758e-05, "epoch": 1.2455208204621278, "percentage": 41.58, "elapsed_time": "2:08:28", "remaining_time": "3:00:29"}
{"current_steps": 640, "total_steps": 1515, "loss": 0.3221, "learning_rate": 1.2959713525323725e-05, "epoch": 1.265290992215495, "percentage": 42.24, "elapsed_time": "2:10:26", "remaining_time": "2:58:19"}
{"current_steps": 650, "total_steps": 1515, "loss": 0.3111, "learning_rate": 1.2754774605533728e-05, "epoch": 1.285061163968862, "percentage": 42.9, "elapsed_time": "2:12:21", "remaining_time": "2:56:07"}
{"current_steps": 660, "total_steps": 1515, "loss": 0.3151, "learning_rate": 1.2548575815924689e-05, "epoch": 1.3048313357222292, "percentage": 43.56, "elapsed_time": "2:14:22", "remaining_time": "2:54:04"}
{"current_steps": 670, "total_steps": 1515, "loss": 0.31, "learning_rate": 1.234121145954094e-05, "epoch": 1.3246015074755961, "percentage": 44.22, "elapsed_time": "2:16:16", "remaining_time": "2:51:52"}
{"current_steps": 680, "total_steps": 1515, "loss": 0.3139, "learning_rate": 1.2132776372487634e-05, "epoch": 1.3443716792289633, "percentage": 44.88, "elapsed_time": "2:18:13", "remaining_time": "2:49:44"}
{"current_steps": 690, "total_steps": 1515, "loss": 0.3147, "learning_rate": 1.1923365880558345e-05, "epoch": 1.3641418509823304, "percentage": 45.54, "elapsed_time": "2:20:15", "remaining_time": "2:47:41"}
{"current_steps": 700, "total_steps": 1515, "loss": 0.3153, "learning_rate": 1.1713075755638748e-05, "epoch": 1.3839120227356976, "percentage": 46.2, "elapsed_time": "2:22:20", "remaining_time": "2:45:43"}
{"current_steps": 710, "total_steps": 1515, "loss": 0.3137, "learning_rate": 1.1502002171906248e-05, "epoch": 1.4036821944890647, "percentage": 46.86, "elapsed_time": "2:24:16", "remaining_time": "2:43:34"}
{"current_steps": 720, "total_steps": 1515, "loss": 0.301, "learning_rate": 1.1290241661845649e-05, "epoch": 1.4234523662424317, "percentage": 47.52, "elapsed_time": "2:26:14", "remaining_time": "2:41:28"}
{"current_steps": 730, "total_steps": 1515, "loss": 0.3114, "learning_rate": 1.1077891072100944e-05, "epoch": 1.4432225379957988, "percentage": 48.18, "elapsed_time": "2:28:13", "remaining_time": "2:39:23"}
{"current_steps": 740, "total_steps": 1515, "loss": 0.3132, "learning_rate": 1.0865047519183411e-05, "epoch": 1.462992709749166, "percentage": 48.84, "elapsed_time": "2:30:12", "remaining_time": "2:37:18"}
{"current_steps": 750, "total_steps": 1515, "loss": 0.3032, "learning_rate": 1.065180834505634e-05, "epoch": 1.482762881502533, "percentage": 49.5, "elapsed_time": "2:32:05", "remaining_time": "2:35:08"}
{"current_steps": 760, "total_steps": 1515, "loss": 0.3113, "learning_rate": 1.0438271072616584e-05, "epoch": 1.5025330532559003, "percentage": 50.17, "elapsed_time": "2:34:24", "remaining_time": "2:33:23"}
{"current_steps": 770, "total_steps": 1515, "loss": 0.3219, "learning_rate": 1.022453336109341e-05, "epoch": 1.5223032250092672, "percentage": 50.83, "elapsed_time": "2:36:25", "remaining_time": "2:31:21"}
{"current_steps": 780, "total_steps": 1515, "loss": 0.3134, "learning_rate": 1.001069296138499e-05, "epoch": 1.5420733967626343, "percentage": 51.49, "elapsed_time": "2:38:17", "remaining_time": "2:29:10"}
{"current_steps": 790, "total_steps": 1515, "loss": 0.3126, "learning_rate": 9.796847671352948e-06, "epoch": 1.5618435685160015, "percentage": 52.15, "elapsed_time": "2:40:14", "remaining_time": "2:27:03"}
{"current_steps": 800, "total_steps": 1515, "loss": 0.3039, "learning_rate": 9.583095291095454e-06, "epoch": 1.5816137402693686, "percentage": 52.81, "elapsed_time": "2:42:10", "remaining_time": "2:24:56"}
{"current_steps": 810, "total_steps": 1515, "loss": 0.3043, "learning_rate": 9.36953357821928e-06, "epoch": 1.6013839120227358, "percentage": 53.47, "elapsed_time": "2:44:09", "remaining_time": "2:22:52"}
{"current_steps": 820, "total_steps": 1515, "loss": 0.296, "learning_rate": 9.156260203131299e-06, "epoch": 1.6211540837761027, "percentage": 54.13, "elapsed_time": "2:46:20", "remaining_time": "2:20:58"}
{"current_steps": 830, "total_steps": 1515, "loss": 0.2962, "learning_rate": 8.943372704369844e-06, "epoch": 1.64092425552947, "percentage": 54.79, "elapsed_time": "2:48:20", "remaining_time": "2:18:56"}
{"current_steps": 840, "total_steps": 1515, "loss": 0.3129, "learning_rate": 8.730968443996411e-06, "epoch": 1.660694427282837, "percentage": 55.45, "elapsed_time": "2:50:27", "remaining_time": "2:16:58"}
{"current_steps": 850, "total_steps": 1515, "loss": 0.3119, "learning_rate": 8.519144563068037e-06, "epoch": 1.6804645990362042, "percentage": 56.11, "elapsed_time": "2:52:27", "remaining_time": "2:14:55"}
{"current_steps": 860, "total_steps": 1515, "loss": 0.3056, "learning_rate": 8.30799793721077e-06, "epoch": 1.7002347707895713, "percentage": 56.77, "elapsed_time": "2:54:17", "remaining_time": "2:12:44"}
{"current_steps": 870, "total_steps": 1515, "loss": 0.311, "learning_rate": 8.097625132314529e-06, "epoch": 1.7200049425429382, "percentage": 57.43, "elapsed_time": "2:56:10", "remaining_time": "2:10:36"}
{"current_steps": 880, "total_steps": 1515, "loss": 0.3047, "learning_rate": 7.888122360369617e-06, "epoch": 1.7397751142963056, "percentage": 58.09, "elapsed_time": "2:58:07", "remaining_time": "2:08:31"}
{"current_steps": 890, "total_steps": 1515, "loss": 0.3011, "learning_rate": 7.67958543546509e-06, "epoch": 1.7595452860496725, "percentage": 58.75, "elapsed_time": "3:00:00", "remaining_time": "2:06:24"}
{"current_steps": 900, "total_steps": 1515, "loss": 0.2958, "learning_rate": 7.472109729969097e-06, "epoch": 1.7793154578030397, "percentage": 59.41, "elapsed_time": "3:02:00", "remaining_time": "2:04:22"}
{"current_steps": 910, "total_steps": 1515, "loss": 0.3035, "learning_rate": 7.2657901309112325e-06, "epoch": 1.7990856295564068, "percentage": 60.07, "elapsed_time": "3:03:53", "remaining_time": "2:02:15"}
{"current_steps": 920, "total_steps": 1515, "loss": 0.3134, "learning_rate": 7.060720996586878e-06, "epoch": 1.8188558013097738, "percentage": 60.73, "elapsed_time": "3:05:51", "remaining_time": "2:00:12"}
{"current_steps": 930, "total_steps": 1515, "loss": 0.3055, "learning_rate": 6.85699611340333e-06, "epoch": 1.8386259730631411, "percentage": 61.39, "elapsed_time": "3:07:57", "remaining_time": "1:58:14"}
{"current_steps": 940, "total_steps": 1515, "loss": 0.3043, "learning_rate": 6.654708652987475e-06, "epoch": 1.858396144816508, "percentage": 62.05, "elapsed_time": "3:09:46", "remaining_time": "1:56:05"}
{"current_steps": 950, "total_steps": 1515, "loss": 0.3048, "learning_rate": 6.453951129574644e-06, "epoch": 1.8781663165698752, "percentage": 62.71, "elapsed_time": "3:11:46", "remaining_time": "1:54:03"}
{"current_steps": 960, "total_steps": 1515, "loss": 0.3006, "learning_rate": 6.254815357698118e-06, "epoch": 1.8979364883232424, "percentage": 63.37, "elapsed_time": "3:13:50", "remaining_time": "1:52:03"}
{"current_steps": 970, "total_steps": 1515, "loss": 0.3025, "learning_rate": 6.05739241019862e-06, "epoch": 1.9177066600766093, "percentage": 64.03, "elapsed_time": "3:15:56", "remaining_time": "1:50:05"}
{"current_steps": 980, "total_steps": 1515, "loss": 0.2956, "learning_rate": 5.861772576573028e-06, "epoch": 1.9374768318299767, "percentage": 64.69, "elapsed_time": "3:18:00", "remaining_time": "1:48:06"}
{"current_steps": 990, "total_steps": 1515, "loss": 0.3091, "learning_rate": 5.668045321681328e-06, "epoch": 1.9572470035833436, "percentage": 65.35, "elapsed_time": "3:20:05", "remaining_time": "1:46:06"}
{"current_steps": 1000, "total_steps": 1515, "loss": 0.2999, "learning_rate": 5.476299244830734e-06, "epoch": 1.9770171753367107, "percentage": 66.01, "elapsed_time": "3:22:15", "remaining_time": "1:44:09"}
{"current_steps": 1000, "total_steps": 1515, "eval_loss": 0.3708229959011078, "epoch": 1.9770171753367107, "percentage": 66.01, "elapsed_time": "3:23:37", "remaining_time": "1:44:51"}
{"current_steps": 1010, "total_steps": 1515, "loss": 0.3066, "learning_rate": 5.28662203925562e-06, "epoch": 1.9967873470900779, "percentage": 66.67, "elapsed_time": "3:26:12", "remaining_time": "1:43:06"}
{"current_steps": 1020, "total_steps": 1515, "loss": 0.2574, "learning_rate": 5.099100452011876e-06, "epoch": 2.016557518843445, "percentage": 67.33, "elapsed_time": "3:28:10", "remaining_time": "1:41:01"}
{"current_steps": 1030, "total_steps": 1515, "loss": 0.2297, "learning_rate": 4.9138202443039625e-06, "epoch": 2.036327690596812, "percentage": 67.99, "elapsed_time": "3:30:18", "remaining_time": "1:39:01"}
{"current_steps": 1040, "total_steps": 1515, "loss": 0.2445, "learning_rate": 4.730866152262841e-06, "epoch": 2.056097862350179, "percentage": 68.65, "elapsed_time": "3:32:14", "remaining_time": "1:36:56"}
{"current_steps": 1050, "total_steps": 1515, "loss": 0.2505, "learning_rate": 4.550321848192731e-06, "epoch": 2.0758680341035465, "percentage": 69.31, "elapsed_time": "3:34:12", "remaining_time": "1:34:51"}
{"current_steps": 1060, "total_steps": 1515, "loss": 0.2494, "learning_rate": 4.3722699023043634e-06, "epoch": 2.0956382058569134, "percentage": 69.97, "elapsed_time": "3:36:10", "remaining_time": "1:32:47"}
{"current_steps": 1070, "total_steps": 1515, "loss": 0.239, "learning_rate": 4.196791744952291e-06, "epoch": 2.1154083776102803, "percentage": 70.63, "elapsed_time": "3:38:09", "remaining_time": "1:30:43"}
{"current_steps": 1080, "total_steps": 1515, "loss": 0.2463, "learning_rate": 4.023967629393498e-06, "epoch": 2.1351785493636477, "percentage": 71.29, "elapsed_time": "3:40:19", "remaining_time": "1:28:44"}
{"current_steps": 1090, "total_steps": 1515, "loss": 0.2455, "learning_rate": 3.853876595084332e-06, "epoch": 2.1549487211170146, "percentage": 71.95, "elapsed_time": "3:42:18", "remaining_time": "1:26:40"}
{"current_steps": 1100, "total_steps": 1515, "loss": 0.2406, "learning_rate": 3.68659643153258e-06, "epoch": 2.174718892870382, "percentage": 72.61, "elapsed_time": "3:44:21", "remaining_time": "1:24:38"}
{"current_steps": 1110, "total_steps": 1515, "loss": 0.2333, "learning_rate": 3.5222036427211704e-06, "epoch": 2.194489064623749, "percentage": 73.27, "elapsed_time": "3:46:30", "remaining_time": "1:22:38"}
{"current_steps": 1120, "total_steps": 1515, "loss": 0.2397, "learning_rate": 3.360773412119801e-06, "epoch": 2.214259236377116, "percentage": 73.93, "elapsed_time": "3:48:26", "remaining_time": "1:20:34"}
{"current_steps": 1130, "total_steps": 1515, "loss": 0.2394, "learning_rate": 3.202379568300511e-06, "epoch": 2.2340294081304832, "percentage": 74.59, "elapsed_time": "3:50:22", "remaining_time": "1:18:29"}
{"current_steps": 1140, "total_steps": 1515, "loss": 0.2319, "learning_rate": 3.0470945511728856e-06, "epoch": 2.25379957988385, "percentage": 75.25, "elapsed_time": "3:52:14", "remaining_time": "1:16:23"}
{"current_steps": 1150, "total_steps": 1515, "loss": 0.2461, "learning_rate": 2.8949893788543505e-06, "epoch": 2.2735697516372175, "percentage": 75.91, "elapsed_time": "3:54:16", "remaining_time": "1:14:21"}
{"current_steps": 1160, "total_steps": 1515, "loss": 0.2391, "learning_rate": 2.74613361519073e-06, "epoch": 2.2933399233905845, "percentage": 76.57, "elapsed_time": "3:56:14", "remaining_time": "1:12:17"}
{"current_steps": 1170, "total_steps": 1515, "loss": 0.2532, "learning_rate": 2.60059533794187e-06, "epoch": 2.3131100951439514, "percentage": 77.23, "elapsed_time": "3:58:16", "remaining_time": "1:10:15"}
{"current_steps": 1180, "total_steps": 1515, "loss": 0.2442, "learning_rate": 2.458441107646935e-06, "epoch": 2.3328802668973188, "percentage": 77.89, "elapsed_time": "4:00:18", "remaining_time": "1:08:13"}
{"current_steps": 1190, "total_steps": 1515, "loss": 0.2374, "learning_rate": 2.3197359371835802e-06, "epoch": 2.3526504386506857, "percentage": 78.55, "elapsed_time": "4:02:20", "remaining_time": "1:06:11"}
{"current_steps": 1200, "total_steps": 1515, "loss": 0.2383, "learning_rate": 2.1845432620349338e-06, "epoch": 2.372420610404053, "percentage": 79.21, "elapsed_time": "4:04:26", "remaining_time": "1:04:09"}
{"current_steps": 1210, "total_steps": 1515, "loss": 0.2388, "learning_rate": 2.0529249112779824e-06, "epoch": 2.39219078215742, "percentage": 79.87, "elapsed_time": "4:06:28", "remaining_time": "1:02:07"}
{"current_steps": 1220, "total_steps": 1515, "loss": 0.2437, "learning_rate": 1.924941079306647e-06, "epoch": 2.411960953910787, "percentage": 80.53, "elapsed_time": "4:08:32", "remaining_time": "1:00:05"}
{"current_steps": 1230, "total_steps": 1515, "loss": 0.2482, "learning_rate": 1.8006502983024332e-06, "epoch": 2.4317311256641543, "percentage": 81.19, "elapsed_time": "4:10:31", "remaining_time": "0:58:02"}
{"current_steps": 1240, "total_steps": 1515, "loss": 0.2313, "learning_rate": 1.6801094114653082e-06, "epoch": 2.451501297417521, "percentage": 81.85, "elapsed_time": "4:12:30", "remaining_time": "0:56:00"}
{"current_steps": 1250, "total_steps": 1515, "loss": 0.2403, "learning_rate": 1.5633735470170108e-06, "epoch": 2.4712714691708886, "percentage": 82.51, "elapsed_time": "4:14:44", "remaining_time": "0:54:00"}
{"current_steps": 1260, "total_steps": 1515, "loss": 0.2442, "learning_rate": 1.4504960929886746e-06, "epoch": 2.4910416409242555, "percentage": 83.17, "elapsed_time": "4:16:46", "remaining_time": "0:51:57"}
{"current_steps": 1270, "total_steps": 1515, "loss": 0.239, "learning_rate": 1.3415286728043374e-06, "epoch": 2.5108118126776224, "percentage": 83.83, "elapsed_time": "4:18:39", "remaining_time": "0:49:54"}
{"current_steps": 1280, "total_steps": 1515, "loss": 0.2385, "learning_rate": 1.2365211216714523e-06, "epoch": 2.53058198443099, "percentage": 84.49, "elapsed_time": "4:20:41", "remaining_time": "0:47:51"}
{"current_steps": 1290, "total_steps": 1515, "loss": 0.2482, "learning_rate": 1.135521463789232e-06, "epoch": 2.5503521561843567, "percentage": 85.15, "elapsed_time": "4:22:35", "remaining_time": "0:45:48"}
{"current_steps": 1300, "total_steps": 1515, "loss": 0.2381, "learning_rate": 1.0385758903852406e-06, "epoch": 2.570122327937724, "percentage": 85.81, "elapsed_time": "4:24:36", "remaining_time": "0:43:45"}
{"current_steps": 1310, "total_steps": 1515, "loss": 0.2405, "learning_rate": 9.457287385902836e-07, "epoch": 2.589892499691091, "percentage": 86.47, "elapsed_time": "4:26:34", "remaining_time": "0:41:43"}
{"current_steps": 1320, "total_steps": 1515, "loss": 0.2304, "learning_rate": 8.570224711612385e-07, "epoch": 2.6096626714444584, "percentage": 87.13, "elapsed_time": "4:28:30", "remaining_time": "0:39:39"}
{"current_steps": 1330, "total_steps": 1515, "loss": 0.2259, "learning_rate": 7.724976570611254e-07, "epoch": 2.6294328431978253, "percentage": 87.79, "elapsed_time": "4:30:25", "remaining_time": "0:37:36"}
{"current_steps": 1340, "total_steps": 1515, "loss": 0.2318, "learning_rate": 6.921929529052729e-07, "epoch": 2.6492030149511923, "percentage": 88.45, "elapsed_time": "4:32:27", "remaining_time": "0:35:34"}
{"current_steps": 1350, "total_steps": 1515, "loss": 0.2377, "learning_rate": 6.161450852820872e-07, "epoch": 2.6689731867045596, "percentage": 89.11, "elapsed_time": "4:34:24", "remaining_time": "0:33:32"}
{"current_steps": 1360, "total_steps": 1515, "loss": 0.2402, "learning_rate": 5.443888339565018e-07, "epoch": 2.6887433584579266, "percentage": 89.77, "elapsed_time": "4:36:35", "remaining_time": "0:31:31"}
{"current_steps": 1370, "total_steps": 1515, "loss": 0.2401, "learning_rate": 4.769570159637782e-07, "epoch": 2.7085135302112935, "percentage": 90.43, "elapsed_time": "4:38:28", "remaining_time": "0:29:28"}
{"current_steps": 1380, "total_steps": 1515, "loss": 0.2306, "learning_rate": 4.138804706009547e-07, "epoch": 2.728283701964661, "percentage": 91.09, "elapsed_time": "4:40:32", "remaining_time": "0:27:26"}
{"current_steps": 1390, "total_steps": 1515, "loss": 0.2407, "learning_rate": 3.5518804532278736e-07, "epoch": 2.748053873718028, "percentage": 91.75, "elapsed_time": "4:42:22", "remaining_time": "0:25:23"}
{"current_steps": 1400, "total_steps": 1515, "loss": 0.227, "learning_rate": 3.0090658254864013e-07, "epoch": 2.767824045471395, "percentage": 92.41, "elapsed_time": "4:44:24", "remaining_time": "0:23:21"}
{"current_steps": 1410, "total_steps": 1515, "loss": 0.2306, "learning_rate": 2.5106090738636014e-07, "epoch": 2.787594217224762, "percentage": 93.07, "elapsed_time": "4:46:27", "remaining_time": "0:21:19"}
{"current_steps": 1420, "total_steps": 1515, "loss": 0.242, "learning_rate": 2.0567381627875639e-07, "epoch": 2.8073643889781295, "percentage": 93.73, "elapsed_time": "4:48:30", "remaining_time": "0:19:18"}
{"current_steps": 1430, "total_steps": 1515, "loss": 0.2309, "learning_rate": 1.6476606657786386e-07, "epoch": 2.8271345607314964, "percentage": 94.39, "elapsed_time": "4:50:28", "remaining_time": "0:17:15"}
{"current_steps": 1440, "total_steps": 1515, "loss": 0.2287, "learning_rate": 1.2835636705176403e-07, "epoch": 2.8469047324848633, "percentage": 95.05, "elapsed_time": "4:52:21", "remaining_time": "0:15:13"}
{"current_steps": 1450, "total_steps": 1515, "loss": 0.2469, "learning_rate": 9.64613693283123e-08, "epoch": 2.8666749042382307, "percentage": 95.71, "elapsed_time": "4:54:24", "remaining_time": "0:13:11"}
{"current_steps": 1460, "total_steps": 1515, "loss": 0.2458, "learning_rate": 6.909566027966996e-08, "epoch": 2.8864450759915976, "percentage": 96.37, "elapsed_time": "4:56:19", "remaining_time": "0:11:09"}
{"current_steps": 1470, "total_steps": 1515, "loss": 0.2456, "learning_rate": 4.6271755351144923e-08, "epoch": 2.9062152477449645, "percentage": 97.03, "elapsed_time": "4:58:22", "remaining_time": "0:09:08"}
{"current_steps": 1480, "total_steps": 1515, "loss": 0.2413, "learning_rate": 2.8000092837368042e-08, "epoch": 2.925985419498332, "percentage": 97.69, "elapsed_time": "5:00:13", "remaining_time": "0:07:06"}
{"current_steps": 1490, "total_steps": 1515, "loss": 0.2388, "learning_rate": 1.4289029108436325e-08, "epoch": 2.945755591251699, "percentage": 98.35, "elapsed_time": "5:02:13", "remaining_time": "0:05:04"}
{"current_steps": 1500, "total_steps": 1515, "loss": 0.2454, "learning_rate": 5.14483478821437e-09, "epoch": 2.965525763005066, "percentage": 99.01, "elapsed_time": "5:04:19", "remaining_time": "0:03:02"}
{"current_steps": 1500, "total_steps": 1515, "eval_loss": 0.37777501344680786, "epoch": 2.965525763005066, "percentage": 99.01, "elapsed_time": "5:05:41", "remaining_time": "0:03:03"}
{"current_steps": 1510, "total_steps": 1515, "loss": 0.2349, "learning_rate": 5.716918865195098e-10, "epoch": 2.985295934758433, "percentage": 99.67, "elapsed_time": "5:08:31", "remaining_time": "0:01:01"}
{"current_steps": 1515, "total_steps": 1515, "epoch": 2.995181020635117, "percentage": 100.0, "elapsed_time": "5:10:14", "remaining_time": "0:00:00"}