chchen's picture
Training in progress, step 1500
829d993 verified
raw
history blame
34.8 kB
{"current_steps": 10, "total_steps": 3325, "loss": 1.3292, "lr": 3.003003003003003e-06, "epoch": 0.015023474178403756, "percentage": 0.3, "elapsed_time": "0:01:32", "remaining_time": "8:29:54"}
{"current_steps": 20, "total_steps": 3325, "loss": 1.3844, "lr": 6.006006006006006e-06, "epoch": 0.03004694835680751, "percentage": 0.6, "elapsed_time": "0:03:03", "remaining_time": "8:25:03"}
{"current_steps": 30, "total_steps": 3325, "loss": 1.1953, "lr": 9.00900900900901e-06, "epoch": 0.04507042253521127, "percentage": 0.9, "elapsed_time": "0:04:39", "remaining_time": "8:32:02"}
{"current_steps": 40, "total_steps": 3325, "loss": 0.8062, "lr": 1.2012012012012012e-05, "epoch": 0.06009389671361502, "percentage": 1.2, "elapsed_time": "0:06:20", "remaining_time": "8:40:21"}
{"current_steps": 50, "total_steps": 3325, "loss": 0.4971, "lr": 1.5015015015015016e-05, "epoch": 0.07511737089201878, "percentage": 1.5, "elapsed_time": "0:08:02", "remaining_time": "8:46:13"}
{"current_steps": 50, "total_steps": 3325, "eval_loss": 0.3236617147922516, "epoch": 0.07511737089201878, "percentage": 1.5, "elapsed_time": "0:11:37", "remaining_time": "12:41:39"}
{"current_steps": 60, "total_steps": 3325, "loss": 0.3049, "lr": 1.801801801801802e-05, "epoch": 0.09014084507042254, "percentage": 1.8, "elapsed_time": "0:13:24", "remaining_time": "12:09:23"}
{"current_steps": 70, "total_steps": 3325, "loss": 0.1795, "lr": 2.102102102102102e-05, "epoch": 0.10516431924882629, "percentage": 2.11, "elapsed_time": "0:15:08", "remaining_time": "11:44:03"}
{"current_steps": 80, "total_steps": 3325, "loss": 0.1482, "lr": 2.4024024024024024e-05, "epoch": 0.12018779342723004, "percentage": 2.41, "elapsed_time": "0:16:54", "remaining_time": "11:25:59"}
{"current_steps": 90, "total_steps": 3325, "loss": 0.0928, "lr": 2.702702702702703e-05, "epoch": 0.1352112676056338, "percentage": 2.71, "elapsed_time": "0:18:39", "remaining_time": "11:10:52"}
{"current_steps": 100, "total_steps": 3325, "loss": 0.1179, "lr": 3.0030030030030033e-05, "epoch": 0.15023474178403756, "percentage": 3.01, "elapsed_time": "0:20:25", "remaining_time": "10:58:39"}
{"current_steps": 100, "total_steps": 3325, "eval_loss": 0.09419180452823639, "epoch": 0.15023474178403756, "percentage": 3.01, "elapsed_time": "0:24:09", "remaining_time": "12:59:15"}
{"current_steps": 110, "total_steps": 3325, "loss": 0.1185, "lr": 3.3033033033033035e-05, "epoch": 0.1652582159624413, "percentage": 3.31, "elapsed_time": "0:25:58", "remaining_time": "12:39:19"}
{"current_steps": 120, "total_steps": 3325, "loss": 0.0985, "lr": 3.603603603603604e-05, "epoch": 0.18028169014084508, "percentage": 3.61, "elapsed_time": "0:27:44", "remaining_time": "12:21:00"}
{"current_steps": 130, "total_steps": 3325, "loss": 0.0828, "lr": 3.903903903903904e-05, "epoch": 0.19530516431924883, "percentage": 3.91, "elapsed_time": "0:29:30", "remaining_time": "12:05:15"}
{"current_steps": 140, "total_steps": 3325, "loss": 0.1053, "lr": 4.204204204204204e-05, "epoch": 0.21032863849765257, "percentage": 4.21, "elapsed_time": "0:31:18", "remaining_time": "11:52:08"}
{"current_steps": 150, "total_steps": 3325, "loss": 0.0891, "lr": 4.5045045045045046e-05, "epoch": 0.22535211267605634, "percentage": 4.51, "elapsed_time": "0:33:06", "remaining_time": "11:40:54"}
{"current_steps": 150, "total_steps": 3325, "eval_loss": 0.07970932126045227, "epoch": 0.22535211267605634, "percentage": 4.51, "elapsed_time": "0:36:51", "remaining_time": "13:00:18"}
{"current_steps": 160, "total_steps": 3325, "loss": 0.0755, "lr": 4.804804804804805e-05, "epoch": 0.2403755868544601, "percentage": 4.81, "elapsed_time": "0:38:40", "remaining_time": "12:45:00"}
{"current_steps": 170, "total_steps": 3325, "loss": 0.0569, "lr": 5.105105105105106e-05, "epoch": 0.25539906103286386, "percentage": 5.11, "elapsed_time": "0:40:27", "remaining_time": "12:30:48"}
{"current_steps": 180, "total_steps": 3325, "loss": 0.0744, "lr": 5.405405405405406e-05, "epoch": 0.2704225352112676, "percentage": 5.41, "elapsed_time": "0:42:15", "remaining_time": "12:18:18"}
{"current_steps": 190, "total_steps": 3325, "loss": 0.0684, "lr": 5.705705705705706e-05, "epoch": 0.28544600938967135, "percentage": 5.71, "elapsed_time": "0:44:03", "remaining_time": "12:06:58"}
{"current_steps": 200, "total_steps": 3325, "loss": 0.0539, "lr": 6.0060060060060066e-05, "epoch": 0.3004694835680751, "percentage": 6.02, "elapsed_time": "0:45:50", "remaining_time": "11:56:22"}
{"current_steps": 200, "total_steps": 3325, "eval_loss": 0.05980731174349785, "epoch": 0.3004694835680751, "percentage": 6.02, "elapsed_time": "0:49:37", "remaining_time": "12:55:26"}
{"current_steps": 210, "total_steps": 3325, "loss": 0.054, "lr": 6.306306306306306e-05, "epoch": 0.3154929577464789, "percentage": 6.32, "elapsed_time": "0:51:28", "remaining_time": "12:43:26"}
{"current_steps": 220, "total_steps": 3325, "loss": 0.0645, "lr": 6.606606606606607e-05, "epoch": 0.3305164319248826, "percentage": 6.62, "elapsed_time": "0:53:16", "remaining_time": "12:31:59"}
{"current_steps": 230, "total_steps": 3325, "loss": 0.0527, "lr": 6.906906906906907e-05, "epoch": 0.3455399061032864, "percentage": 6.92, "elapsed_time": "0:55:04", "remaining_time": "12:21:06"}
{"current_steps": 240, "total_steps": 3325, "loss": 0.0622, "lr": 7.207207207207208e-05, "epoch": 0.36056338028169016, "percentage": 7.22, "elapsed_time": "0:56:52", "remaining_time": "12:11:01"}
{"current_steps": 250, "total_steps": 3325, "loss": 0.065, "lr": 7.507507507507507e-05, "epoch": 0.3755868544600939, "percentage": 7.52, "elapsed_time": "0:58:40", "remaining_time": "12:01:43"}
{"current_steps": 250, "total_steps": 3325, "eval_loss": 0.05752342566847801, "epoch": 0.3755868544600939, "percentage": 7.52, "elapsed_time": "1:02:29", "remaining_time": "12:48:37"}
{"current_steps": 260, "total_steps": 3325, "loss": 0.0526, "lr": 7.807807807807808e-05, "epoch": 0.39061032863849765, "percentage": 7.82, "elapsed_time": "1:04:19", "remaining_time": "12:38:16"}
{"current_steps": 270, "total_steps": 3325, "loss": 0.0638, "lr": 8.108108108108109e-05, "epoch": 0.4056338028169014, "percentage": 8.12, "elapsed_time": "1:06:07", "remaining_time": "12:28:11"}
{"current_steps": 280, "total_steps": 3325, "loss": 0.0646, "lr": 8.408408408408409e-05, "epoch": 0.42065727699530514, "percentage": 8.42, "elapsed_time": "1:07:55", "remaining_time": "12:18:41"}
{"current_steps": 290, "total_steps": 3325, "loss": 0.0644, "lr": 8.70870870870871e-05, "epoch": 0.4356807511737089, "percentage": 8.72, "elapsed_time": "1:09:43", "remaining_time": "12:09:42"}
{"current_steps": 300, "total_steps": 3325, "loss": 0.052, "lr": 9.009009009009009e-05, "epoch": 0.4507042253521127, "percentage": 9.02, "elapsed_time": "1:11:31", "remaining_time": "12:01:15"}
{"current_steps": 300, "total_steps": 3325, "eval_loss": 0.053021036088466644, "epoch": 0.4507042253521127, "percentage": 9.02, "elapsed_time": "1:15:16", "remaining_time": "12:38:57"}
{"current_steps": 310, "total_steps": 3325, "loss": 0.0449, "lr": 9.30930930930931e-05, "epoch": 0.46572769953051646, "percentage": 9.32, "elapsed_time": "1:17:06", "remaining_time": "12:29:56"}
{"current_steps": 320, "total_steps": 3325, "loss": 0.0598, "lr": 9.60960960960961e-05, "epoch": 0.4807511737089202, "percentage": 9.62, "elapsed_time": "1:18:55", "remaining_time": "12:21:05"}
{"current_steps": 330, "total_steps": 3325, "loss": 0.0561, "lr": 9.90990990990991e-05, "epoch": 0.49577464788732395, "percentage": 9.92, "elapsed_time": "1:20:43", "remaining_time": "12:12:36"}
{"current_steps": 340, "total_steps": 3325, "loss": 0.0683, "lr": 9.999864944989638e-05, "epoch": 0.5107981220657277, "percentage": 10.23, "elapsed_time": "1:22:30", "remaining_time": "12:04:20"}
{"current_steps": 350, "total_steps": 3325, "loss": 0.0535, "lr": 9.999203468625017e-05, "epoch": 0.5258215962441315, "percentage": 10.53, "elapsed_time": "1:24:17", "remaining_time": "11:56:26"}
{"current_steps": 350, "total_steps": 3325, "eval_loss": 0.054493363946676254, "epoch": 0.5258215962441315, "percentage": 10.53, "elapsed_time": "1:28:04", "remaining_time": "12:28:38"}
{"current_steps": 360, "total_steps": 3325, "loss": 0.0634, "lr": 9.997990837719421e-05, "epoch": 0.5408450704225352, "percentage": 10.83, "elapsed_time": "1:29:56", "remaining_time": "12:20:44"}
{"current_steps": 370, "total_steps": 3325, "loss": 0.0451, "lr": 9.996227185963554e-05, "epoch": 0.5558685446009389, "percentage": 11.13, "elapsed_time": "1:31:43", "remaining_time": "12:12:35"}
{"current_steps": 380, "total_steps": 3325, "loss": 0.0467, "lr": 9.993912707797329e-05, "epoch": 0.5708920187793427, "percentage": 11.43, "elapsed_time": "1:33:31", "remaining_time": "12:04:45"}
{"current_steps": 390, "total_steps": 3325, "loss": 0.0493, "lr": 9.99104765838842e-05, "epoch": 0.5859154929577465, "percentage": 11.73, "elapsed_time": "1:35:19", "remaining_time": "11:57:21"}
{"current_steps": 400, "total_steps": 3325, "loss": 0.0512, "lr": 9.987632353604151e-05, "epoch": 0.6009389671361502, "percentage": 12.03, "elapsed_time": "1:37:07", "remaining_time": "11:50:13"}
{"current_steps": 400, "total_steps": 3325, "eval_loss": 0.04660526290535927, "epoch": 0.6009389671361502, "percentage": 12.03, "elapsed_time": "1:40:54", "remaining_time": "12:17:50"}
{"current_steps": 410, "total_steps": 3325, "loss": 0.0459, "lr": 9.98366716997665e-05, "epoch": 0.615962441314554, "percentage": 12.33, "elapsed_time": "1:42:43", "remaining_time": "12:10:19"}
{"current_steps": 420, "total_steps": 3325, "loss": 0.0478, "lr": 9.979152544661354e-05, "epoch": 0.6309859154929578, "percentage": 12.63, "elapsed_time": "1:44:31", "remaining_time": "12:02:58"}
{"current_steps": 430, "total_steps": 3325, "loss": 0.0498, "lr": 9.974088975388802e-05, "epoch": 0.6460093896713615, "percentage": 12.93, "elapsed_time": "1:46:19", "remaining_time": "11:55:51"}
{"current_steps": 440, "total_steps": 3325, "loss": 0.0489, "lr": 9.968477020409766e-05, "epoch": 0.6610328638497652, "percentage": 13.23, "elapsed_time": "1:48:08", "remaining_time": "11:49:07"}
{"current_steps": 450, "total_steps": 3325, "loss": 0.0597, "lr": 9.962317298433705e-05, "epoch": 0.676056338028169, "percentage": 13.53, "elapsed_time": "1:49:55", "remaining_time": "11:42:20"}
{"current_steps": 450, "total_steps": 3325, "eval_loss": 0.049538787454366684, "epoch": 0.676056338028169, "percentage": 13.53, "elapsed_time": "1:53:42", "remaining_time": "12:06:26"}
{"current_steps": 460, "total_steps": 3325, "loss": 0.0595, "lr": 9.955610488560551e-05, "epoch": 0.6910798122065728, "percentage": 13.83, "elapsed_time": "1:55:33", "remaining_time": "11:59:45"}
{"current_steps": 470, "total_steps": 3325, "loss": 0.061, "lr": 9.948357330205842e-05, "epoch": 0.7061032863849765, "percentage": 14.14, "elapsed_time": "1:57:22", "remaining_time": "11:52:57"}
{"current_steps": 480, "total_steps": 3325, "loss": 0.032, "lr": 9.940558623019201e-05, "epoch": 0.7211267605633803, "percentage": 14.44, "elapsed_time": "1:59:09", "remaining_time": "11:46:16"}
{"current_steps": 490, "total_steps": 3325, "loss": 0.0486, "lr": 9.932215226796172e-05, "epoch": 0.7361502347417841, "percentage": 14.74, "elapsed_time": "2:00:57", "remaining_time": "11:39:49"}
{"current_steps": 500, "total_steps": 3325, "loss": 0.0509, "lr": 9.923328061383435e-05, "epoch": 0.7511737089201878, "percentage": 15.04, "elapsed_time": "2:02:45", "remaining_time": "11:33:33"}
{"current_steps": 500, "total_steps": 3325, "eval_loss": 0.046869516372680664, "epoch": 0.7511737089201878, "percentage": 15.04, "elapsed_time": "2:06:34", "remaining_time": "11:55:06"}
{"current_steps": 510, "total_steps": 3325, "loss": 0.049, "lr": 9.913898106577393e-05, "epoch": 0.7661971830985915, "percentage": 15.34, "elapsed_time": "2:08:24", "remaining_time": "11:48:44"}
{"current_steps": 520, "total_steps": 3325, "loss": 0.0405, "lr": 9.903926402016153e-05, "epoch": 0.7812206572769953, "percentage": 15.64, "elapsed_time": "2:10:12", "remaining_time": "11:42:22"}
{"current_steps": 530, "total_steps": 3325, "loss": 0.0452, "lr": 9.893414047064897e-05, "epoch": 0.7962441314553991, "percentage": 15.94, "elapsed_time": "2:12:01", "remaining_time": "11:36:16"}
{"current_steps": 540, "total_steps": 3325, "loss": 0.0483, "lr": 9.88236220069469e-05, "epoch": 0.8112676056338028, "percentage": 16.24, "elapsed_time": "2:13:50", "remaining_time": "11:30:16"}
{"current_steps": 550, "total_steps": 3325, "loss": 0.0624, "lr": 9.870772081354705e-05, "epoch": 0.8262910798122066, "percentage": 16.54, "elapsed_time": "2:15:39", "remaining_time": "11:24:28"}
{"current_steps": 550, "total_steps": 3325, "eval_loss": 0.04311800375580788, "epoch": 0.8262910798122066, "percentage": 16.54, "elapsed_time": "2:19:25", "remaining_time": "11:43:28"}
{"current_steps": 560, "total_steps": 3325, "loss": 0.0493, "lr": 9.858644966837878e-05, "epoch": 0.8413145539906103, "percentage": 16.84, "elapsed_time": "2:21:16", "remaining_time": "11:37:33"}
{"current_steps": 570, "total_steps": 3325, "loss": 0.038, "lr": 9.845982194140051e-05, "epoch": 0.856338028169014, "percentage": 17.14, "elapsed_time": "2:23:06", "remaining_time": "11:31:42"}
{"current_steps": 580, "total_steps": 3325, "loss": 0.0435, "lr": 9.832785159312559e-05, "epoch": 0.8713615023474178, "percentage": 17.44, "elapsed_time": "2:24:55", "remaining_time": "11:25:54"}
{"current_steps": 590, "total_steps": 3325, "loss": 0.0389, "lr": 9.819055317308317e-05, "epoch": 0.8863849765258216, "percentage": 17.74, "elapsed_time": "2:26:43", "remaining_time": "11:20:10"}
{"current_steps": 600, "total_steps": 3325, "loss": 0.035, "lr": 9.804794181821422e-05, "epoch": 0.9014084507042254, "percentage": 18.05, "elapsed_time": "2:28:32", "remaining_time": "11:14:38"}
{"current_steps": 600, "total_steps": 3325, "eval_loss": 0.04581260681152344, "epoch": 0.9014084507042254, "percentage": 18.05, "elapsed_time": "2:32:21", "remaining_time": "11:31:56"}
{"current_steps": 610, "total_steps": 3325, "loss": 0.0477, "lr": 9.790003325120261e-05, "epoch": 0.9164319248826291, "percentage": 18.35, "elapsed_time": "2:34:13", "remaining_time": "11:26:25"}
{"current_steps": 620, "total_steps": 3325, "loss": 0.0565, "lr": 9.774684377874178e-05, "epoch": 0.9314553990610329, "percentage": 18.65, "elapsed_time": "2:36:01", "remaining_time": "11:20:43"}
{"current_steps": 630, "total_steps": 3325, "loss": 0.0356, "lr": 9.758839028973692e-05, "epoch": 0.9464788732394366, "percentage": 18.95, "elapsed_time": "2:37:50", "remaining_time": "11:15:12"}
{"current_steps": 640, "total_steps": 3325, "loss": 0.0467, "lr": 9.742469025344298e-05, "epoch": 0.9615023474178404, "percentage": 19.25, "elapsed_time": "2:39:39", "remaining_time": "11:09:47"}
{"current_steps": 650, "total_steps": 3325, "loss": 0.0546, "lr": 9.725576171753874e-05, "epoch": 0.9765258215962441, "percentage": 19.55, "elapsed_time": "2:41:28", "remaining_time": "11:04:32"}
{"current_steps": 650, "total_steps": 3325, "eval_loss": 0.04435986280441284, "epoch": 0.9765258215962441, "percentage": 19.55, "elapsed_time": "2:45:17", "remaining_time": "11:20:13"}
{"current_steps": 660, "total_steps": 3325, "loss": 0.0396, "lr": 9.708162330613708e-05, "epoch": 0.9915492957746479, "percentage": 19.85, "elapsed_time": "2:47:07", "remaining_time": "11:14:49"}
{"current_steps": 670, "total_steps": 3325, "loss": 0.0434, "lr": 9.690229421773167e-05, "epoch": 1.0065727699530516, "percentage": 20.15, "elapsed_time": "2:48:56", "remaining_time": "11:09:28"}
{"current_steps": 680, "total_steps": 3325, "loss": 0.0369, "lr": 9.67177942230804e-05, "epoch": 1.0215962441314554, "percentage": 20.45, "elapsed_time": "2:50:46", "remaining_time": "11:04:17"}
{"current_steps": 690, "total_steps": 3325, "loss": 0.0409, "lr": 9.652814366302568e-05, "epoch": 1.036619718309859, "percentage": 20.75, "elapsed_time": "2:52:37", "remaining_time": "10:59:14"}
{"current_steps": 700, "total_steps": 3325, "loss": 0.0404, "lr": 9.633336344625185e-05, "epoch": 1.051643192488263, "percentage": 21.05, "elapsed_time": "2:54:25", "remaining_time": "10:54:06"}
{"current_steps": 700, "total_steps": 3325, "eval_loss": 0.04425961896777153, "epoch": 1.051643192488263, "percentage": 21.05, "elapsed_time": "2:58:16", "remaining_time": "11:08:30"}
{"current_steps": 710, "total_steps": 3325, "loss": 0.029, "lr": 9.61334750469801e-05, "epoch": 1.0666666666666667, "percentage": 21.35, "elapsed_time": "3:00:08", "remaining_time": "11:03:28"}
{"current_steps": 720, "total_steps": 3325, "loss": 0.0373, "lr": 9.592850050260089e-05, "epoch": 1.0816901408450703, "percentage": 21.65, "elapsed_time": "3:01:57", "remaining_time": "10:58:21"}
{"current_steps": 730, "total_steps": 3325, "loss": 0.0328, "lr": 9.571846241124446e-05, "epoch": 1.0967136150234742, "percentage": 21.95, "elapsed_time": "3:03:45", "remaining_time": "10:53:14"}
{"current_steps": 740, "total_steps": 3325, "loss": 0.028, "lr": 9.55033839292893e-05, "epoch": 1.1117370892018779, "percentage": 22.26, "elapsed_time": "3:05:35", "remaining_time": "10:48:18"}
{"current_steps": 750, "total_steps": 3325, "loss": 0.0342, "lr": 9.52832887688093e-05, "epoch": 1.1267605633802817, "percentage": 22.56, "elapsed_time": "3:07:24", "remaining_time": "10:43:26"}
{"current_steps": 750, "total_steps": 3325, "eval_loss": 0.043438900262117386, "epoch": 1.1267605633802817, "percentage": 22.56, "elapsed_time": "3:11:15", "remaining_time": "10:56:38"}
{"current_steps": 760, "total_steps": 3325, "loss": 0.0391, "lr": 9.50582011949595e-05, "epoch": 1.1417840375586854, "percentage": 22.86, "elapsed_time": "3:13:04", "remaining_time": "10:51:39"}
{"current_steps": 770, "total_steps": 3325, "loss": 0.0354, "lr": 9.482814602330084e-05, "epoch": 1.1568075117370893, "percentage": 23.16, "elapsed_time": "3:14:54", "remaining_time": "10:46:43"}
{"current_steps": 780, "total_steps": 3325, "loss": 0.0386, "lr": 9.459314861706435e-05, "epoch": 1.171830985915493, "percentage": 23.46, "elapsed_time": "3:16:43", "remaining_time": "10:41:53"}
{"current_steps": 790, "total_steps": 3325, "loss": 0.0291, "lr": 9.435323488435488e-05, "epoch": 1.1868544600938966, "percentage": 23.76, "elapsed_time": "3:18:33", "remaining_time": "10:37:09"}
{"current_steps": 800, "total_steps": 3325, "loss": 0.0298, "lr": 9.410843127529473e-05, "epoch": 1.2018779342723005, "percentage": 24.06, "elapsed_time": "3:20:23", "remaining_time": "10:32:30"}
{"current_steps": 800, "total_steps": 3325, "eval_loss": 0.04284869506955147, "epoch": 1.2018779342723005, "percentage": 24.06, "elapsed_time": "3:24:12", "remaining_time": "10:44:31"}
{"current_steps": 810, "total_steps": 3325, "loss": 0.0371, "lr": 9.385876477910765e-05, "epoch": 1.2169014084507042, "percentage": 24.36, "elapsed_time": "3:26:05", "remaining_time": "10:39:54"}
{"current_steps": 820, "total_steps": 3325, "loss": 0.0379, "lr": 9.360426292114314e-05, "epoch": 1.231924882629108, "percentage": 24.66, "elapsed_time": "3:27:55", "remaining_time": "10:35:11"}
{"current_steps": 830, "total_steps": 3325, "loss": 0.0334, "lr": 9.334495375984212e-05, "epoch": 1.2469483568075117, "percentage": 24.96, "elapsed_time": "3:29:45", "remaining_time": "10:30:33"}
{"current_steps": 840, "total_steps": 3325, "loss": 0.0305, "lr": 9.30808658836432e-05, "epoch": 1.2619718309859156, "percentage": 25.26, "elapsed_time": "3:31:34", "remaining_time": "10:25:53"}
{"current_steps": 850, "total_steps": 3325, "loss": 0.0348, "lr": 9.281202840783108e-05, "epoch": 1.2769953051643192, "percentage": 25.56, "elapsed_time": "3:33:23", "remaining_time": "10:21:21"}
{"current_steps": 850, "total_steps": 3325, "eval_loss": 0.04067714512348175, "epoch": 1.2769953051643192, "percentage": 25.56, "elapsed_time": "3:37:16", "remaining_time": "10:32:37"}
{"current_steps": 860, "total_steps": 3325, "loss": 0.0285, "lr": 9.253847097132655e-05, "epoch": 1.292018779342723, "percentage": 25.86, "elapsed_time": "3:39:07", "remaining_time": "10:28:03"}
{"current_steps": 870, "total_steps": 3325, "loss": 0.0285, "lr": 9.226022373341882e-05, "epoch": 1.3070422535211268, "percentage": 26.17, "elapsed_time": "3:40:55", "remaining_time": "10:23:25"}
{"current_steps": 880, "total_steps": 3325, "loss": 0.0263, "lr": 9.19773173704406e-05, "epoch": 1.3220657276995305, "percentage": 26.47, "elapsed_time": "3:42:45", "remaining_time": "10:18:55"}
{"current_steps": 890, "total_steps": 3325, "loss": 0.0371, "lr": 9.168978307238594e-05, "epoch": 1.3370892018779343, "percentage": 26.77, "elapsed_time": "3:44:35", "remaining_time": "10:14:28"}
{"current_steps": 900, "total_steps": 3325, "loss": 0.0291, "lr": 9.13976525394717e-05, "epoch": 1.352112676056338, "percentage": 27.07, "elapsed_time": "3:46:27", "remaining_time": "10:10:09"}
{"current_steps": 900, "total_steps": 3325, "eval_loss": 0.0397120825946331, "epoch": 1.352112676056338, "percentage": 27.07, "elapsed_time": "3:50:16", "remaining_time": "10:20:28"}
{"current_steps": 910, "total_steps": 3325, "loss": 0.0295, "lr": 9.110095797864263e-05, "epoch": 1.3671361502347419, "percentage": 27.37, "elapsed_time": "3:52:09", "remaining_time": "10:16:06"}
{"current_steps": 920, "total_steps": 3325, "loss": 0.0317, "lr": 9.079973210002051e-05, "epoch": 1.3821596244131455, "percentage": 27.67, "elapsed_time": "3:53:58", "remaining_time": "10:11:39"}
{"current_steps": 930, "total_steps": 3325, "loss": 0.044, "lr": 9.049400811329807e-05, "epoch": 1.3971830985915492, "percentage": 27.97, "elapsed_time": "3:55:49", "remaining_time": "10:07:19"}
{"current_steps": 940, "total_steps": 3325, "loss": 0.0267, "lr": 9.01838197240775e-05, "epoch": 1.412206572769953, "percentage": 28.27, "elapsed_time": "3:57:38", "remaining_time": "10:02:58"}
{"current_steps": 950, "total_steps": 3325, "loss": 0.0373, "lr": 8.986920113015461e-05, "epoch": 1.4272300469483568, "percentage": 28.57, "elapsed_time": "3:59:28", "remaining_time": "9:58:40"}
{"current_steps": 950, "total_steps": 3325, "eval_loss": 0.03974553570151329, "epoch": 1.4272300469483568, "percentage": 28.57, "elapsed_time": "4:03:20", "remaining_time": "10:08:20"}
{"current_steps": 960, "total_steps": 3325, "loss": 0.0277, "lr": 8.955018701774846e-05, "epoch": 1.4422535211267606, "percentage": 28.87, "elapsed_time": "4:05:13", "remaining_time": "10:04:07"}
{"current_steps": 970, "total_steps": 3325, "loss": 0.0418, "lr": 8.922681255767731e-05, "epoch": 1.4572769953051643, "percentage": 29.17, "elapsed_time": "4:07:03", "remaining_time": "9:59:49"}
{"current_steps": 980, "total_steps": 3325, "loss": 0.035, "lr": 8.889911340148112e-05, "epoch": 1.4723004694835682, "percentage": 29.47, "elapsed_time": "4:08:52", "remaining_time": "9:55:30"}
{"current_steps": 990, "total_steps": 3325, "loss": 0.0315, "lr": 8.856712567749095e-05, "epoch": 1.4873239436619718, "percentage": 29.77, "elapsed_time": "4:10:41", "remaining_time": "9:51:17"}
{"current_steps": 1000, "total_steps": 3325, "loss": 0.0289, "lr": 8.82308859868459e-05, "epoch": 1.5023474178403755, "percentage": 30.08, "elapsed_time": "4:12:32", "remaining_time": "9:47:10"}
{"current_steps": 1000, "total_steps": 3325, "eval_loss": 0.04059433564543724, "epoch": 1.5023474178403755, "percentage": 30.08, "elapsed_time": "4:16:24", "remaining_time": "9:56:10"}
{"current_steps": 1010, "total_steps": 3325, "loss": 0.0332, "lr": 8.789043139945795e-05, "epoch": 1.5173708920187794, "percentage": 30.38, "elapsed_time": "4:18:15", "remaining_time": "9:51:56"}
{"current_steps": 1020, "total_steps": 3325, "loss": 0.0419, "lr": 8.754579944992491e-05, "epoch": 1.532394366197183, "percentage": 30.68, "elapsed_time": "4:20:05", "remaining_time": "9:47:45"}
{"current_steps": 1030, "total_steps": 3325, "loss": 0.0327, "lr": 8.719702813339248e-05, "epoch": 1.5474178403755867, "percentage": 30.98, "elapsed_time": "4:21:55", "remaining_time": "9:43:37"}
{"current_steps": 1040, "total_steps": 3325, "loss": 0.0305, "lr": 8.684415590136518e-05, "epoch": 1.5624413145539906, "percentage": 31.28, "elapsed_time": "4:23:46", "remaining_time": "9:39:31"}
{"current_steps": 1050, "total_steps": 3325, "loss": 0.0339, "lr": 8.648722165746722e-05, "epoch": 1.5774647887323945, "percentage": 31.58, "elapsed_time": "4:25:35", "remaining_time": "9:35:26"}
{"current_steps": 1050, "total_steps": 3325, "eval_loss": 0.0449674129486084, "epoch": 1.5774647887323945, "percentage": 31.58, "elapsed_time": "4:29:24", "remaining_time": "9:43:42"}
{"current_steps": 1060, "total_steps": 3325, "loss": 0.0273, "lr": 8.61262647531534e-05, "epoch": 1.5924882629107981, "percentage": 31.88, "elapsed_time": "4:31:17", "remaining_time": "9:39:41"}
{"current_steps": 1070, "total_steps": 3325, "loss": 0.0349, "lr": 8.576132498337068e-05, "epoch": 1.6075117370892018, "percentage": 32.18, "elapsed_time": "4:33:07", "remaining_time": "9:35:37"}
{"current_steps": 1080, "total_steps": 3325, "loss": 0.0332, "lr": 8.539244258217088e-05, "epoch": 1.6225352112676057, "percentage": 32.48, "elapsed_time": "4:34:57", "remaining_time": "9:31:33"}
{"current_steps": 1090, "total_steps": 3325, "loss": 0.0408, "lr": 8.501965821827485e-05, "epoch": 1.6375586854460094, "percentage": 32.78, "elapsed_time": "4:36:46", "remaining_time": "9:27:31"}
{"current_steps": 1100, "total_steps": 3325, "loss": 0.0244, "lr": 8.464301299058892e-05, "epoch": 1.652582159624413, "percentage": 33.08, "elapsed_time": "4:38:36", "remaining_time": "9:23:33"}
{"current_steps": 1100, "total_steps": 3325, "eval_loss": 0.04117948189377785, "epoch": 1.652582159624413, "percentage": 33.08, "elapsed_time": "4:42:29", "remaining_time": "9:31:23"}
{"current_steps": 1110, "total_steps": 3325, "loss": 0.0296, "lr": 8.426254842367374e-05, "epoch": 1.667605633802817, "percentage": 33.38, "elapsed_time": "4:44:19", "remaining_time": "9:27:22"}
{"current_steps": 1120, "total_steps": 3325, "loss": 0.0382, "lr": 8.387830646316623e-05, "epoch": 1.6826291079812208, "percentage": 33.68, "elapsed_time": "4:46:09", "remaining_time": "9:23:23"}
{"current_steps": 1130, "total_steps": 3325, "loss": 0.0285, "lr": 8.349032947115525e-05, "epoch": 1.6976525821596244, "percentage": 33.98, "elapsed_time": "4:48:00", "remaining_time": "9:19:26"}
{"current_steps": 1140, "total_steps": 3325, "loss": 0.0422, "lr": 8.309866022151107e-05, "epoch": 1.712676056338028, "percentage": 34.29, "elapsed_time": "4:49:51", "remaining_time": "9:15:33"}
{"current_steps": 1150, "total_steps": 3325, "loss": 0.0288, "lr": 8.270334189516983e-05, "epoch": 1.727699530516432, "percentage": 34.59, "elapsed_time": "4:51:41", "remaining_time": "9:11:40"}
{"current_steps": 1150, "total_steps": 3325, "eval_loss": 0.04018314927816391, "epoch": 1.727699530516432, "percentage": 34.59, "elapsed_time": "4:55:30", "remaining_time": "9:18:53"}
{"current_steps": 1160, "total_steps": 3325, "loss": 0.0418, "lr": 8.230441807537277e-05, "epoch": 1.7427230046948357, "percentage": 34.89, "elapsed_time": "4:57:22", "remaining_time": "9:15:01"}
{"current_steps": 1170, "total_steps": 3325, "loss": 0.0272, "lr": 8.190193274286122e-05, "epoch": 1.7577464788732393, "percentage": 35.19, "elapsed_time": "4:59:12", "remaining_time": "9:11:06"}
{"current_steps": 1180, "total_steps": 3325, "loss": 0.0336, "lr": 8.149593027102789e-05, "epoch": 1.7727699530516432, "percentage": 35.49, "elapsed_time": "5:01:03", "remaining_time": "9:07:14"}
{"current_steps": 1190, "total_steps": 3325, "loss": 0.0282, "lr": 8.108645542102469e-05, "epoch": 1.787793427230047, "percentage": 35.79, "elapsed_time": "5:02:52", "remaining_time": "9:03:23"}
{"current_steps": 1200, "total_steps": 3325, "loss": 0.036, "lr": 8.067355333682798e-05, "epoch": 1.8028169014084507, "percentage": 36.09, "elapsed_time": "5:04:41", "remaining_time": "8:59:34"}
{"current_steps": 1200, "total_steps": 3325, "eval_loss": 0.03951646015048027, "epoch": 1.8028169014084507, "percentage": 36.09, "elapsed_time": "5:08:35", "remaining_time": "9:06:27"}
{"current_steps": 1210, "total_steps": 3325, "loss": 0.0257, "lr": 8.025726954026138e-05, "epoch": 1.8178403755868544, "percentage": 36.39, "elapsed_time": "5:10:27", "remaining_time": "9:02:39"}
{"current_steps": 1220, "total_steps": 3325, "loss": 0.0305, "lr": 7.983764992597716e-05, "epoch": 1.8328638497652583, "percentage": 36.69, "elapsed_time": "5:12:17", "remaining_time": "8:58:49"}
{"current_steps": 1230, "total_steps": 3325, "loss": 0.0321, "lr": 7.94147407563964e-05, "epoch": 1.847887323943662, "percentage": 36.99, "elapsed_time": "5:14:06", "remaining_time": "8:55:00"}
{"current_steps": 1240, "total_steps": 3325, "loss": 0.0352, "lr": 7.89885886566086e-05, "epoch": 1.8629107981220656, "percentage": 37.29, "elapsed_time": "5:15:58", "remaining_time": "8:51:16"}
{"current_steps": 1250, "total_steps": 3325, "loss": 0.0334, "lr": 7.855924060923141e-05, "epoch": 1.8779342723004695, "percentage": 37.59, "elapsed_time": "5:17:49", "remaining_time": "8:47:34"}
{"current_steps": 1250, "total_steps": 3325, "eval_loss": 0.039211343973875046, "epoch": 1.8779342723004695, "percentage": 37.59, "elapsed_time": "5:21:40", "remaining_time": "8:53:59"}
{"current_steps": 1260, "total_steps": 3325, "loss": 0.0346, "lr": 7.812674394923077e-05, "epoch": 1.8929577464788734, "percentage": 37.89, "elapsed_time": "5:23:33", "remaining_time": "8:50:15"}
{"current_steps": 1270, "total_steps": 3325, "loss": 0.0317, "lr": 7.769114635870231e-05, "epoch": 1.907981220657277, "percentage": 38.2, "elapsed_time": "5:25:24", "remaining_time": "8:46:32"}
{"current_steps": 1280, "total_steps": 3325, "loss": 0.0341, "lr": 7.725249586161463e-05, "epoch": 1.9230046948356807, "percentage": 38.5, "elapsed_time": "5:27:14", "remaining_time": "8:42:49"}
{"current_steps": 1290, "total_steps": 3325, "loss": 0.0299, "lr": 7.68108408185145e-05, "epoch": 1.9380281690140846, "percentage": 38.8, "elapsed_time": "5:29:05", "remaining_time": "8:39:08"}
{"current_steps": 1300, "total_steps": 3325, "loss": 0.0568, "lr": 7.636622992119536e-05, "epoch": 1.9530516431924883, "percentage": 39.1, "elapsed_time": "5:30:53", "remaining_time": "8:35:25"}
{"current_steps": 1300, "total_steps": 3325, "eval_loss": 0.04275708645582199, "epoch": 1.9530516431924883, "percentage": 39.1, "elapsed_time": "5:34:39", "remaining_time": "8:41:17"}
{"current_steps": 1310, "total_steps": 3325, "loss": 0.0371, "lr": 7.591871218732902e-05, "epoch": 1.968075117370892, "percentage": 39.4, "elapsed_time": "5:36:29", "remaining_time": "8:37:34"}
{"current_steps": 1320, "total_steps": 3325, "loss": 0.0443, "lr": 7.54683369550616e-05, "epoch": 1.9830985915492958, "percentage": 39.7, "elapsed_time": "5:38:17", "remaining_time": "8:33:50"}
{"current_steps": 1330, "total_steps": 3325, "loss": 0.034, "lr": 7.501515387757404e-05, "epoch": 1.9981220657276997, "percentage": 40.0, "elapsed_time": "5:40:03", "remaining_time": "8:30:05"}
{"current_steps": 1340, "total_steps": 3325, "loss": 0.0376, "lr": 7.455921291760796e-05, "epoch": 2.013145539906103, "percentage": 40.3, "elapsed_time": "5:41:51", "remaining_time": "8:26:23"}
{"current_steps": 1350, "total_steps": 3325, "loss": 0.0206, "lr": 7.410056434195725e-05, "epoch": 2.028169014084507, "percentage": 40.6, "elapsed_time": "5:43:38", "remaining_time": "8:22:44"}
{"current_steps": 1350, "total_steps": 3325, "eval_loss": 0.04088796302676201, "epoch": 2.028169014084507, "percentage": 40.6, "elapsed_time": "5:47:24", "remaining_time": "8:28:14"}
{"current_steps": 1360, "total_steps": 3325, "loss": 0.0218, "lr": 7.363925871592629e-05, "epoch": 2.043192488262911, "percentage": 40.9, "elapsed_time": "5:49:13", "remaining_time": "8:24:34"}
{"current_steps": 1370, "total_steps": 3325, "loss": 0.019, "lr": 7.317534689775528e-05, "epoch": 2.0582159624413148, "percentage": 41.2, "elapsed_time": "5:51:00", "remaining_time": "8:20:52"}
{"current_steps": 1380, "total_steps": 3325, "loss": 0.016, "lr": 7.270888003301304e-05, "epoch": 2.073239436619718, "percentage": 41.5, "elapsed_time": "5:52:46", "remaining_time": "8:17:12"}
{"current_steps": 1390, "total_steps": 3325, "loss": 0.0205, "lr": 7.22399095489584e-05, "epoch": 2.088262910798122, "percentage": 41.8, "elapsed_time": "5:54:33", "remaining_time": "8:13:34"}
{"current_steps": 1400, "total_steps": 3325, "loss": 0.0226, "lr": 7.176848714887042e-05, "epoch": 2.103286384976526, "percentage": 42.11, "elapsed_time": "5:56:20", "remaining_time": "8:09:57"}
{"current_steps": 1400, "total_steps": 3325, "eval_loss": 0.04083973169326782, "epoch": 2.103286384976526, "percentage": 42.11, "elapsed_time": "6:00:00", "remaining_time": "8:15:01"}
{"current_steps": 1410, "total_steps": 3325, "loss": 0.021, "lr": 7.129466480634806e-05, "epoch": 2.1183098591549294, "percentage": 42.41, "elapsed_time": "6:01:49", "remaining_time": "8:11:25"}
{"current_steps": 1420, "total_steps": 3325, "loss": 0.0184, "lr": 7.081849475958042e-05, "epoch": 2.1333333333333333, "percentage": 42.71, "elapsed_time": "6:03:36", "remaining_time": "8:07:47"}
{"current_steps": 1430, "total_steps": 3325, "loss": 0.0181, "lr": 7.034002950558723e-05, "epoch": 2.148356807511737, "percentage": 43.01, "elapsed_time": "6:05:21", "remaining_time": "8:04:10"}
{"current_steps": 1440, "total_steps": 3325, "loss": 0.0225, "lr": 6.985932179443144e-05, "epoch": 2.1633802816901406, "percentage": 43.31, "elapsed_time": "6:07:06", "remaining_time": "8:00:33"}
{"current_steps": 1450, "total_steps": 3325, "loss": 0.0257, "lr": 6.937642462340342e-05, "epoch": 2.1784037558685445, "percentage": 43.61, "elapsed_time": "6:08:52", "remaining_time": "7:56:59"}
{"current_steps": 1450, "total_steps": 3325, "eval_loss": 0.04065319150686264, "epoch": 2.1784037558685445, "percentage": 43.61, "elapsed_time": "6:12:34", "remaining_time": "8:01:46"}
{"current_steps": 1460, "total_steps": 3325, "loss": 0.0183, "lr": 6.889139123117817e-05, "epoch": 2.1934272300469484, "percentage": 43.91, "elapsed_time": "6:14:22", "remaining_time": "7:58:13"}
{"current_steps": 1470, "total_steps": 3325, "loss": 0.0242, "lr": 6.840427509194575e-05, "epoch": 2.2084507042253523, "percentage": 44.21, "elapsed_time": "6:16:07", "remaining_time": "7:54:38"}
{"current_steps": 1480, "total_steps": 3325, "loss": 0.015, "lr": 6.791512990951597e-05, "epoch": 2.2234741784037557, "percentage": 44.51, "elapsed_time": "6:17:51", "remaining_time": "7:51:03"}
{"current_steps": 1490, "total_steps": 3325, "loss": 0.0254, "lr": 6.74240096113975e-05, "epoch": 2.2384976525821596, "percentage": 44.81, "elapsed_time": "6:19:38", "remaining_time": "7:47:32"}
{"current_steps": 1500, "total_steps": 3325, "loss": 0.0138, "lr": 6.693096834285256e-05, "epoch": 2.2535211267605635, "percentage": 45.11, "elapsed_time": "6:21:24", "remaining_time": "7:44:02"}
{"current_steps": 1500, "total_steps": 3325, "eval_loss": 0.04137204959988594, "epoch": 2.2535211267605635, "percentage": 45.11, "elapsed_time": "6:25:05", "remaining_time": "7:48:31"}