chchen's picture
Training in progress, step 500
ee159a5 verified
raw
history blame
11.6 kB
{"current_steps": 10, "total_steps": 3275, "loss": 1.4201, "lr": 3.0487804878048782e-06, "epoch": 0.015265718919950386, "percentage": 0.31, "elapsed_time": "0:01:18", "remaining_time": "7:06:45"}
{"current_steps": 20, "total_steps": 3275, "loss": 1.3361, "lr": 6.0975609756097564e-06, "epoch": 0.030531437839900772, "percentage": 0.61, "elapsed_time": "0:02:35", "remaining_time": "7:01:47"}
{"current_steps": 30, "total_steps": 3275, "loss": 1.1539, "lr": 9.146341463414634e-06, "epoch": 0.04579715675985116, "percentage": 0.92, "elapsed_time": "0:03:52", "remaining_time": "6:59:19"}
{"current_steps": 40, "total_steps": 3275, "loss": 0.8971, "lr": 1.2195121951219513e-05, "epoch": 0.061062875679801544, "percentage": 1.22, "elapsed_time": "0:05:09", "remaining_time": "6:57:49"}
{"current_steps": 50, "total_steps": 3275, "loss": 0.4799, "lr": 1.524390243902439e-05, "epoch": 0.07632859459975193, "percentage": 1.53, "elapsed_time": "0:06:27", "remaining_time": "6:56:39"}
{"current_steps": 50, "total_steps": 3275, "eval_loss": 0.2933095097541809, "epoch": 0.07632859459975193, "percentage": 1.53, "elapsed_time": "0:09:07", "remaining_time": "9:48:01"}
{"current_steps": 60, "total_steps": 3275, "loss": 0.2509, "lr": 1.8292682926829268e-05, "epoch": 0.09159431351970232, "percentage": 1.83, "elapsed_time": "0:10:29", "remaining_time": "9:22:22"}
{"current_steps": 70, "total_steps": 3275, "loss": 0.2104, "lr": 2.134146341463415e-05, "epoch": 0.10686003243965271, "percentage": 2.14, "elapsed_time": "0:11:47", "remaining_time": "8:59:47"}
{"current_steps": 80, "total_steps": 3275, "loss": 0.1552, "lr": 2.4390243902439026e-05, "epoch": 0.12212575135960309, "percentage": 2.44, "elapsed_time": "0:13:04", "remaining_time": "8:42:07"}
{"current_steps": 90, "total_steps": 3275, "loss": 0.1008, "lr": 2.7439024390243906e-05, "epoch": 0.13739147027955348, "percentage": 2.75, "elapsed_time": "0:14:21", "remaining_time": "8:28:07"}
{"current_steps": 100, "total_steps": 3275, "loss": 0.1053, "lr": 3.048780487804878e-05, "epoch": 0.15265718919950386, "percentage": 3.05, "elapsed_time": "0:15:39", "remaining_time": "8:17:01"}
{"current_steps": 100, "total_steps": 3275, "eval_loss": 0.07661888748407364, "epoch": 0.15265718919950386, "percentage": 3.05, "elapsed_time": "0:18:19", "remaining_time": "9:41:35"}
{"current_steps": 110, "total_steps": 3275, "loss": 0.0829, "lr": 3.353658536585366e-05, "epoch": 0.16792290811945426, "percentage": 3.36, "elapsed_time": "0:19:40", "remaining_time": "9:26:00"}
{"current_steps": 120, "total_steps": 3275, "loss": 0.0803, "lr": 3.6585365853658535e-05, "epoch": 0.18318862703940464, "percentage": 3.66, "elapsed_time": "0:20:57", "remaining_time": "9:10:56"}
{"current_steps": 130, "total_steps": 3275, "loss": 0.0772, "lr": 3.9634146341463416e-05, "epoch": 0.19845434595935502, "percentage": 3.97, "elapsed_time": "0:22:14", "remaining_time": "8:58:08"}
{"current_steps": 140, "total_steps": 3275, "loss": 0.0777, "lr": 4.26829268292683e-05, "epoch": 0.21372006487930542, "percentage": 4.27, "elapsed_time": "0:23:32", "remaining_time": "8:46:59"}
{"current_steps": 150, "total_steps": 3275, "loss": 0.0594, "lr": 4.573170731707318e-05, "epoch": 0.2289857837992558, "percentage": 4.58, "elapsed_time": "0:24:49", "remaining_time": "8:37:16"}
{"current_steps": 150, "total_steps": 3275, "eval_loss": 0.072237528860569, "epoch": 0.2289857837992558, "percentage": 4.58, "elapsed_time": "0:27:29", "remaining_time": "9:32:40"}
{"current_steps": 160, "total_steps": 3275, "loss": 0.0845, "lr": 4.878048780487805e-05, "epoch": 0.24425150271920618, "percentage": 4.89, "elapsed_time": "0:28:51", "remaining_time": "9:21:47"}
{"current_steps": 170, "total_steps": 3275, "loss": 0.0777, "lr": 5.182926829268293e-05, "epoch": 0.2595172216391566, "percentage": 5.19, "elapsed_time": "0:30:09", "remaining_time": "9:10:41"}
{"current_steps": 180, "total_steps": 3275, "loss": 0.0886, "lr": 5.487804878048781e-05, "epoch": 0.27478294055910696, "percentage": 5.5, "elapsed_time": "0:31:26", "remaining_time": "9:00:36"}
{"current_steps": 190, "total_steps": 3275, "loss": 0.0648, "lr": 5.792682926829268e-05, "epoch": 0.29004865947905734, "percentage": 5.8, "elapsed_time": "0:32:43", "remaining_time": "8:51:24"}
{"current_steps": 200, "total_steps": 3275, "loss": 0.0586, "lr": 6.097560975609756e-05, "epoch": 0.3053143783990077, "percentage": 6.11, "elapsed_time": "0:34:00", "remaining_time": "8:42:59"}
{"current_steps": 200, "total_steps": 3275, "eval_loss": 0.053653329610824585, "epoch": 0.3053143783990077, "percentage": 6.11, "elapsed_time": "0:36:40", "remaining_time": "9:23:53"}
{"current_steps": 210, "total_steps": 3275, "loss": 0.0569, "lr": 6.402439024390244e-05, "epoch": 0.3205800973189581, "percentage": 6.41, "elapsed_time": "0:38:02", "remaining_time": "9:15:13"}
{"current_steps": 220, "total_steps": 3275, "loss": 0.0523, "lr": 6.707317073170732e-05, "epoch": 0.3358458162389085, "percentage": 6.72, "elapsed_time": "0:39:20", "remaining_time": "9:06:12"}
{"current_steps": 230, "total_steps": 3275, "loss": 0.045, "lr": 7.012195121951219e-05, "epoch": 0.3511115351588589, "percentage": 7.02, "elapsed_time": "0:40:37", "remaining_time": "8:57:48"}
{"current_steps": 240, "total_steps": 3275, "loss": 0.0667, "lr": 7.317073170731707e-05, "epoch": 0.3663772540788093, "percentage": 7.33, "elapsed_time": "0:41:54", "remaining_time": "8:49:59"}
{"current_steps": 250, "total_steps": 3275, "loss": 0.066, "lr": 7.621951219512195e-05, "epoch": 0.38164297299875966, "percentage": 7.63, "elapsed_time": "0:43:11", "remaining_time": "8:42:43"}
{"current_steps": 250, "total_steps": 3275, "eval_loss": 0.0550156868994236, "epoch": 0.38164297299875966, "percentage": 7.63, "elapsed_time": "0:45:51", "remaining_time": "9:14:57"}
{"current_steps": 260, "total_steps": 3275, "loss": 0.0635, "lr": 7.926829268292683e-05, "epoch": 0.39690869191871003, "percentage": 7.94, "elapsed_time": "0:47:14", "remaining_time": "9:07:43"}
{"current_steps": 270, "total_steps": 3275, "loss": 0.0653, "lr": 8.231707317073171e-05, "epoch": 0.4121744108386604, "percentage": 8.24, "elapsed_time": "0:48:31", "remaining_time": "9:00:00"}
{"current_steps": 280, "total_steps": 3275, "loss": 0.0568, "lr": 8.53658536585366e-05, "epoch": 0.42744012975861084, "percentage": 8.55, "elapsed_time": "0:49:48", "remaining_time": "8:52:48"}
{"current_steps": 290, "total_steps": 3275, "loss": 0.0629, "lr": 8.841463414634147e-05, "epoch": 0.4427058486785612, "percentage": 8.85, "elapsed_time": "0:51:05", "remaining_time": "8:45:58"}
{"current_steps": 300, "total_steps": 3275, "loss": 0.0553, "lr": 9.146341463414635e-05, "epoch": 0.4579715675985116, "percentage": 9.16, "elapsed_time": "0:52:23", "remaining_time": "8:39:33"}
{"current_steps": 300, "total_steps": 3275, "eval_loss": 0.055096790194511414, "epoch": 0.4579715675985116, "percentage": 9.16, "elapsed_time": "0:55:03", "remaining_time": "9:05:58"}
{"current_steps": 310, "total_steps": 3275, "loss": 0.067, "lr": 9.451219512195122e-05, "epoch": 0.473237286518462, "percentage": 9.47, "elapsed_time": "0:56:25", "remaining_time": "8:59:42"}
{"current_steps": 320, "total_steps": 3275, "loss": 0.05, "lr": 9.75609756097561e-05, "epoch": 0.48850300543841235, "percentage": 9.77, "elapsed_time": "0:57:43", "remaining_time": "8:52:59"}
{"current_steps": 330, "total_steps": 3275, "loss": 0.0552, "lr": 9.999988635788465e-05, "epoch": 0.5037687243583627, "percentage": 10.08, "elapsed_time": "0:59:00", "remaining_time": "8:46:34"}
{"current_steps": 340, "total_steps": 3275, "loss": 0.0437, "lr": 9.999590893808788e-05, "epoch": 0.5190344432783132, "percentage": 10.38, "elapsed_time": "1:00:17", "remaining_time": "8:40:31"}
{"current_steps": 350, "total_steps": 3275, "loss": 0.0468, "lr": 9.998624992909386e-05, "epoch": 0.5343001621982635, "percentage": 10.69, "elapsed_time": "1:01:35", "remaining_time": "8:34:42"}
{"current_steps": 350, "total_steps": 3275, "eval_loss": 0.04763290658593178, "epoch": 0.5343001621982635, "percentage": 10.69, "elapsed_time": "1:04:15", "remaining_time": "8:56:59"}
{"current_steps": 360, "total_steps": 3275, "loss": 0.0503, "lr": 9.997091042856284e-05, "epoch": 0.5495658811182139, "percentage": 10.99, "elapsed_time": "1:05:36", "remaining_time": "8:51:16"}
{"current_steps": 370, "total_steps": 3275, "loss": 0.0576, "lr": 9.994989217969224e-05, "epoch": 0.5648316000381643, "percentage": 11.3, "elapsed_time": "1:06:54", "remaining_time": "8:45:16"}
{"current_steps": 380, "total_steps": 3275, "loss": 0.0706, "lr": 9.992319757101863e-05, "epoch": 0.5800973189581147, "percentage": 11.6, "elapsed_time": "1:08:11", "remaining_time": "8:39:30"}
{"current_steps": 390, "total_steps": 3275, "loss": 0.0597, "lr": 9.98908296361462e-05, "epoch": 0.5953630378780651, "percentage": 11.91, "elapsed_time": "1:09:28", "remaining_time": "8:33:58"}
{"current_steps": 400, "total_steps": 3275, "loss": 0.0515, "lr": 9.98527920534021e-05, "epoch": 0.6106287567980154, "percentage": 12.21, "elapsed_time": "1:10:46", "remaining_time": "8:28:39"}
{"current_steps": 400, "total_steps": 3275, "eval_loss": 0.04808073118329048, "epoch": 0.6106287567980154, "percentage": 12.21, "elapsed_time": "1:13:26", "remaining_time": "8:47:49"}
{"current_steps": 410, "total_steps": 3275, "loss": 0.0517, "lr": 9.980908914541844e-05, "epoch": 0.6258944757179659, "percentage": 12.52, "elapsed_time": "1:14:47", "remaining_time": "8:42:40"}
{"current_steps": 420, "total_steps": 3275, "loss": 0.0514, "lr": 9.975972587864095e-05, "epoch": 0.6411601946379162, "percentage": 12.82, "elapsed_time": "1:16:05", "remaining_time": "8:37:14"}
{"current_steps": 430, "total_steps": 3275, "loss": 0.041, "lr": 9.970470786276467e-05, "epoch": 0.6564259135578666, "percentage": 13.13, "elapsed_time": "1:17:23", "remaining_time": "8:32:00"}
{"current_steps": 440, "total_steps": 3275, "loss": 0.0507, "lr": 9.964404135009648e-05, "epoch": 0.671691632477817, "percentage": 13.44, "elapsed_time": "1:18:40", "remaining_time": "8:26:57"}
{"current_steps": 450, "total_steps": 3275, "loss": 0.0562, "lr": 9.957773323484454e-05, "epoch": 0.6869573513977674, "percentage": 13.74, "elapsed_time": "1:19:58", "remaining_time": "8:22:01"}
{"current_steps": 450, "total_steps": 3275, "eval_loss": 0.04656098783016205, "epoch": 0.6869573513977674, "percentage": 13.74, "elapsed_time": "1:22:38", "remaining_time": "8:38:45"}
{"current_steps": 460, "total_steps": 3275, "loss": 0.0496, "lr": 9.950579105233483e-05, "epoch": 0.7022230703177178, "percentage": 14.05, "elapsed_time": "1:23:59", "remaining_time": "8:34:01"}
{"current_steps": 470, "total_steps": 3275, "loss": 0.0425, "lr": 9.94282229781548e-05, "epoch": 0.7174887892376681, "percentage": 14.35, "elapsed_time": "1:25:17", "remaining_time": "8:29:00"}
{"current_steps": 480, "total_steps": 3275, "loss": 0.0541, "lr": 9.934503782722438e-05, "epoch": 0.7327545081576186, "percentage": 14.66, "elapsed_time": "1:26:34", "remaining_time": "8:24:05"}
{"current_steps": 490, "total_steps": 3275, "loss": 0.0369, "lr": 9.925624505279411e-05, "epoch": 0.748020227077569, "percentage": 14.96, "elapsed_time": "1:27:51", "remaining_time": "8:19:21"}
{"current_steps": 500, "total_steps": 3275, "loss": 0.0347, "lr": 9.916185474537098e-05, "epoch": 0.7632859459975193, "percentage": 15.27, "elapsed_time": "1:29:09", "remaining_time": "8:14:47"}
{"current_steps": 500, "total_steps": 3275, "eval_loss": 0.04013669118285179, "epoch": 0.7632859459975193, "percentage": 15.27, "elapsed_time": "1:31:48", "remaining_time": "8:29:34"}