hp_ablations_gemma_bsz256 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
38f938b verified
{"current_steps": 10, "total_steps": 2658, "loss": 0.7474, "learning_rate": 5e-06, "epoch": 0.011283497884344146, "percentage": 0.38, "elapsed_time": "0:07:35", "remaining_time": "1 day, 9:30:08"}
{"current_steps": 20, "total_steps": 2658, "loss": 0.6794, "learning_rate": 5e-06, "epoch": 0.022566995768688293, "percentage": 0.75, "elapsed_time": "0:15:06", "remaining_time": "1 day, 9:13:48"}
{"current_steps": 30, "total_steps": 2658, "loss": 0.6697, "learning_rate": 5e-06, "epoch": 0.03385049365303244, "percentage": 1.13, "elapsed_time": "0:22:38", "remaining_time": "1 day, 9:03:29"}
{"current_steps": 40, "total_steps": 2658, "loss": 0.6592, "learning_rate": 5e-06, "epoch": 0.045133991537376586, "percentage": 1.5, "elapsed_time": "0:30:10", "remaining_time": "1 day, 8:54:34"}
{"current_steps": 50, "total_steps": 2658, "loss": 0.6527, "learning_rate": 5e-06, "epoch": 0.056417489421720736, "percentage": 1.88, "elapsed_time": "0:37:41", "remaining_time": "1 day, 8:45:51"}
{"current_steps": 60, "total_steps": 2658, "loss": 0.6546, "learning_rate": 5e-06, "epoch": 0.06770098730606489, "percentage": 2.26, "elapsed_time": "0:45:12", "remaining_time": "1 day, 8:37:36"}
{"current_steps": 70, "total_steps": 2658, "loss": 0.632, "learning_rate": 5e-06, "epoch": 0.07898448519040903, "percentage": 2.63, "elapsed_time": "0:52:44", "remaining_time": "1 day, 8:29:39"}
{"current_steps": 80, "total_steps": 2658, "loss": 0.636, "learning_rate": 5e-06, "epoch": 0.09026798307475317, "percentage": 3.01, "elapsed_time": "1:00:15", "remaining_time": "1 day, 8:21:42"}
{"current_steps": 90, "total_steps": 2658, "loss": 0.6225, "learning_rate": 5e-06, "epoch": 0.10155148095909731, "percentage": 3.39, "elapsed_time": "1:07:46", "remaining_time": "1 day, 8:14:00"}
{"current_steps": 100, "total_steps": 2658, "loss": 0.6362, "learning_rate": 5e-06, "epoch": 0.11283497884344147, "percentage": 3.76, "elapsed_time": "1:15:18", "remaining_time": "1 day, 8:06:13"}
{"current_steps": 110, "total_steps": 2658, "loss": 0.6325, "learning_rate": 5e-06, "epoch": 0.12411847672778561, "percentage": 4.14, "elapsed_time": "1:22:49", "remaining_time": "1 day, 7:58:29"}
{"current_steps": 120, "total_steps": 2658, "loss": 0.6271, "learning_rate": 5e-06, "epoch": 0.13540197461212977, "percentage": 4.51, "elapsed_time": "1:30:20", "remaining_time": "1 day, 7:50:51"}
{"current_steps": 130, "total_steps": 2658, "loss": 0.6273, "learning_rate": 5e-06, "epoch": 0.1466854724964739, "percentage": 4.89, "elapsed_time": "1:37:52", "remaining_time": "1 day, 7:43:10"}
{"current_steps": 140, "total_steps": 2658, "loss": 0.6252, "learning_rate": 5e-06, "epoch": 0.15796897038081806, "percentage": 5.27, "elapsed_time": "1:45:23", "remaining_time": "1 day, 7:35:33"}
{"current_steps": 150, "total_steps": 2658, "loss": 0.6287, "learning_rate": 5e-06, "epoch": 0.1692524682651622, "percentage": 5.64, "elapsed_time": "1:52:55", "remaining_time": "1 day, 7:28:00"}
{"current_steps": 160, "total_steps": 2658, "loss": 0.6284, "learning_rate": 5e-06, "epoch": 0.18053596614950634, "percentage": 6.02, "elapsed_time": "2:00:26", "remaining_time": "1 day, 7:20:23"}
{"current_steps": 170, "total_steps": 2658, "loss": 0.6264, "learning_rate": 5e-06, "epoch": 0.1918194640338505, "percentage": 6.4, "elapsed_time": "2:07:57", "remaining_time": "1 day, 7:12:48"}
{"current_steps": 180, "total_steps": 2658, "loss": 0.6253, "learning_rate": 5e-06, "epoch": 0.20310296191819463, "percentage": 6.77, "elapsed_time": "2:15:29", "remaining_time": "1 day, 7:05:15"}
{"current_steps": 190, "total_steps": 2658, "loss": 0.6264, "learning_rate": 5e-06, "epoch": 0.2143864598025388, "percentage": 7.15, "elapsed_time": "2:23:00", "remaining_time": "1 day, 6:57:39"}
{"current_steps": 200, "total_steps": 2658, "loss": 0.6238, "learning_rate": 5e-06, "epoch": 0.22566995768688294, "percentage": 7.52, "elapsed_time": "2:30:31", "remaining_time": "1 day, 6:50:02"}
{"current_steps": 210, "total_steps": 2658, "loss": 0.619, "learning_rate": 5e-06, "epoch": 0.23695345557122707, "percentage": 7.9, "elapsed_time": "2:38:03", "remaining_time": "1 day, 6:42:28"}
{"current_steps": 220, "total_steps": 2658, "loss": 0.6145, "learning_rate": 5e-06, "epoch": 0.24823695345557123, "percentage": 8.28, "elapsed_time": "2:45:34", "remaining_time": "1 day, 6:34:52"}
{"current_steps": 230, "total_steps": 2658, "loss": 0.6179, "learning_rate": 5e-06, "epoch": 0.25952045133991536, "percentage": 8.65, "elapsed_time": "2:53:05", "remaining_time": "1 day, 6:27:13"}
{"current_steps": 240, "total_steps": 2658, "loss": 0.615, "learning_rate": 5e-06, "epoch": 0.27080394922425954, "percentage": 9.03, "elapsed_time": "3:00:36", "remaining_time": "1 day, 6:19:37"}
{"current_steps": 250, "total_steps": 2658, "loss": 0.614, "learning_rate": 5e-06, "epoch": 0.2820874471086037, "percentage": 9.41, "elapsed_time": "3:08:07", "remaining_time": "1 day, 6:12:02"}
{"current_steps": 260, "total_steps": 2658, "loss": 0.6207, "learning_rate": 5e-06, "epoch": 0.2933709449929478, "percentage": 9.78, "elapsed_time": "3:15:39", "remaining_time": "1 day, 6:04:31"}
{"current_steps": 270, "total_steps": 2658, "loss": 0.6138, "learning_rate": 5e-06, "epoch": 0.304654442877292, "percentage": 10.16, "elapsed_time": "3:23:10", "remaining_time": "1 day, 5:56:59"}
{"current_steps": 280, "total_steps": 2658, "loss": 0.6107, "learning_rate": 5e-06, "epoch": 0.3159379407616361, "percentage": 10.53, "elapsed_time": "3:30:42", "remaining_time": "1 day, 5:49:28"}
{"current_steps": 290, "total_steps": 2658, "loss": 0.614, "learning_rate": 5e-06, "epoch": 0.32722143864598024, "percentage": 10.91, "elapsed_time": "3:38:13", "remaining_time": "1 day, 5:41:56"}
{"current_steps": 300, "total_steps": 2658, "loss": 0.6113, "learning_rate": 5e-06, "epoch": 0.3385049365303244, "percentage": 11.29, "elapsed_time": "3:45:44", "remaining_time": "1 day, 5:34:23"}
{"current_steps": 310, "total_steps": 2658, "loss": 0.6122, "learning_rate": 5e-06, "epoch": 0.34978843441466856, "percentage": 11.66, "elapsed_time": "3:53:16", "remaining_time": "1 day, 5:26:51"}
{"current_steps": 320, "total_steps": 2658, "loss": 0.6167, "learning_rate": 5e-06, "epoch": 0.3610719322990127, "percentage": 12.04, "elapsed_time": "4:00:47", "remaining_time": "1 day, 5:19:20"}
{"current_steps": 330, "total_steps": 2658, "loss": 0.606, "learning_rate": 5e-06, "epoch": 0.3723554301833568, "percentage": 12.42, "elapsed_time": "4:08:19", "remaining_time": "1 day, 5:11:46"}
{"current_steps": 340, "total_steps": 2658, "loss": 0.6155, "learning_rate": 5e-06, "epoch": 0.383638928067701, "percentage": 12.79, "elapsed_time": "4:15:50", "remaining_time": "1 day, 5:04:14"}
{"current_steps": 350, "total_steps": 2658, "loss": 0.6172, "learning_rate": 5e-06, "epoch": 0.39492242595204513, "percentage": 13.17, "elapsed_time": "4:23:22", "remaining_time": "1 day, 4:56:43"}
{"current_steps": 360, "total_steps": 2658, "loss": 0.5985, "learning_rate": 5e-06, "epoch": 0.40620592383638926, "percentage": 13.54, "elapsed_time": "4:30:53", "remaining_time": "1 day, 4:49:10"}
{"current_steps": 370, "total_steps": 2658, "loss": 0.6154, "learning_rate": 5e-06, "epoch": 0.41748942172073344, "percentage": 13.92, "elapsed_time": "4:38:24", "remaining_time": "1 day, 4:41:39"}
{"current_steps": 380, "total_steps": 2658, "loss": 0.5897, "learning_rate": 5e-06, "epoch": 0.4287729196050776, "percentage": 14.3, "elapsed_time": "4:45:56", "remaining_time": "1 day, 4:34:08"}
{"current_steps": 390, "total_steps": 2658, "loss": 0.6157, "learning_rate": 5e-06, "epoch": 0.4400564174894217, "percentage": 14.67, "elapsed_time": "4:53:28", "remaining_time": "1 day, 4:26:38"}
{"current_steps": 400, "total_steps": 2658, "loss": 0.603, "learning_rate": 5e-06, "epoch": 0.4513399153737659, "percentage": 15.05, "elapsed_time": "5:00:59", "remaining_time": "1 day, 4:19:06"}
{"current_steps": 410, "total_steps": 2658, "loss": 0.6061, "learning_rate": 5e-06, "epoch": 0.46262341325811, "percentage": 15.43, "elapsed_time": "5:08:31", "remaining_time": "1 day, 4:11:34"}
{"current_steps": 420, "total_steps": 2658, "loss": 0.6051, "learning_rate": 5e-06, "epoch": 0.47390691114245415, "percentage": 15.8, "elapsed_time": "5:16:02", "remaining_time": "1 day, 4:04:03"}
{"current_steps": 430, "total_steps": 2658, "loss": 0.5976, "learning_rate": 5e-06, "epoch": 0.48519040902679833, "percentage": 16.18, "elapsed_time": "5:23:33", "remaining_time": "1 day, 3:56:31"}
{"current_steps": 440, "total_steps": 2658, "loss": 0.5968, "learning_rate": 5e-06, "epoch": 0.49647390691114246, "percentage": 16.55, "elapsed_time": "5:31:05", "remaining_time": "1 day, 3:48:59"}
{"current_steps": 450, "total_steps": 2658, "loss": 0.6096, "learning_rate": 5e-06, "epoch": 0.5077574047954866, "percentage": 16.93, "elapsed_time": "5:38:36", "remaining_time": "1 day, 3:41:27"}
{"current_steps": 460, "total_steps": 2658, "loss": 0.6032, "learning_rate": 5e-06, "epoch": 0.5190409026798307, "percentage": 17.31, "elapsed_time": "5:46:08", "remaining_time": "1 day, 3:33:57"}
{"current_steps": 470, "total_steps": 2658, "loss": 0.6002, "learning_rate": 5e-06, "epoch": 0.5303244005641748, "percentage": 17.68, "elapsed_time": "5:53:39", "remaining_time": "1 day, 3:26:25"}
{"current_steps": 480, "total_steps": 2658, "loss": 0.6104, "learning_rate": 5e-06, "epoch": 0.5416078984485191, "percentage": 18.06, "elapsed_time": "6:01:11", "remaining_time": "1 day, 3:18:54"}
{"current_steps": 490, "total_steps": 2658, "loss": 0.5912, "learning_rate": 5e-06, "epoch": 0.5528913963328632, "percentage": 18.43, "elapsed_time": "6:08:42", "remaining_time": "1 day, 3:11:22"}
{"current_steps": 500, "total_steps": 2658, "loss": 0.6079, "learning_rate": 5e-06, "epoch": 0.5641748942172073, "percentage": 18.81, "elapsed_time": "6:16:14", "remaining_time": "1 day, 3:03:51"}
{"current_steps": 510, "total_steps": 2658, "loss": 0.6036, "learning_rate": 5e-06, "epoch": 0.5754583921015515, "percentage": 19.19, "elapsed_time": "6:23:45", "remaining_time": "1 day, 2:56:19"}
{"current_steps": 520, "total_steps": 2658, "loss": 0.6003, "learning_rate": 5e-06, "epoch": 0.5867418899858956, "percentage": 19.56, "elapsed_time": "6:31:17", "remaining_time": "1 day, 2:48:47"}
{"current_steps": 530, "total_steps": 2658, "loss": 0.5916, "learning_rate": 5e-06, "epoch": 0.5980253878702397, "percentage": 19.94, "elapsed_time": "6:38:48", "remaining_time": "1 day, 2:41:16"}
{"current_steps": 540, "total_steps": 2658, "loss": 0.6036, "learning_rate": 5e-06, "epoch": 0.609308885754584, "percentage": 20.32, "elapsed_time": "6:46:20", "remaining_time": "1 day, 2:33:45"}
{"current_steps": 550, "total_steps": 2658, "loss": 0.6034, "learning_rate": 5e-06, "epoch": 0.6205923836389281, "percentage": 20.69, "elapsed_time": "6:53:51", "remaining_time": "1 day, 2:26:12"}
{"current_steps": 560, "total_steps": 2658, "loss": 0.605, "learning_rate": 5e-06, "epoch": 0.6318758815232722, "percentage": 21.07, "elapsed_time": "7:01:23", "remaining_time": "1 day, 2:18:41"}
{"current_steps": 570, "total_steps": 2658, "loss": 0.5974, "learning_rate": 5e-06, "epoch": 0.6431593794076164, "percentage": 21.44, "elapsed_time": "7:08:54", "remaining_time": "1 day, 2:11:08"}
{"current_steps": 580, "total_steps": 2658, "loss": 0.5977, "learning_rate": 5e-06, "epoch": 0.6544428772919605, "percentage": 21.82, "elapsed_time": "7:16:25", "remaining_time": "1 day, 2:03:36"}
{"current_steps": 590, "total_steps": 2658, "loss": 0.607, "learning_rate": 5e-06, "epoch": 0.6657263751763046, "percentage": 22.2, "elapsed_time": "7:23:56", "remaining_time": "1 day, 1:56:03"}
{"current_steps": 600, "total_steps": 2658, "loss": 0.6015, "learning_rate": 5e-06, "epoch": 0.6770098730606487, "percentage": 22.57, "elapsed_time": "7:31:27", "remaining_time": "1 day, 1:48:30"}
{"current_steps": 610, "total_steps": 2658, "loss": 0.603, "learning_rate": 5e-06, "epoch": 0.688293370944993, "percentage": 22.95, "elapsed_time": "7:38:58", "remaining_time": "1 day, 1:40:57"}
{"current_steps": 620, "total_steps": 2658, "loss": 0.5924, "learning_rate": 5e-06, "epoch": 0.6995768688293371, "percentage": 23.33, "elapsed_time": "7:46:29", "remaining_time": "1 day, 1:33:25"}
{"current_steps": 630, "total_steps": 2658, "loss": 0.5999, "learning_rate": 5e-06, "epoch": 0.7108603667136812, "percentage": 23.7, "elapsed_time": "7:54:00", "remaining_time": "1 day, 1:25:52"}
{"current_steps": 640, "total_steps": 2658, "loss": 0.6008, "learning_rate": 5e-06, "epoch": 0.7221438645980254, "percentage": 24.08, "elapsed_time": "8:01:32", "remaining_time": "1 day, 1:18:21"}
{"current_steps": 650, "total_steps": 2658, "loss": 0.5954, "learning_rate": 5e-06, "epoch": 0.7334273624823695, "percentage": 24.45, "elapsed_time": "8:09:03", "remaining_time": "1 day, 1:10:48"}
{"current_steps": 660, "total_steps": 2658, "loss": 0.5975, "learning_rate": 5e-06, "epoch": 0.7447108603667136, "percentage": 24.83, "elapsed_time": "8:16:34", "remaining_time": "1 day, 1:03:15"}
{"current_steps": 670, "total_steps": 2658, "loss": 0.6023, "learning_rate": 5e-06, "epoch": 0.7559943582510579, "percentage": 25.21, "elapsed_time": "8:24:05", "remaining_time": "1 day, 0:55:42"}
{"current_steps": 680, "total_steps": 2658, "loss": 0.59, "learning_rate": 5e-06, "epoch": 0.767277856135402, "percentage": 25.58, "elapsed_time": "8:31:36", "remaining_time": "1 day, 0:48:09"}
{"current_steps": 690, "total_steps": 2658, "loss": 0.5931, "learning_rate": 5e-06, "epoch": 0.7785613540197461, "percentage": 25.96, "elapsed_time": "8:39:07", "remaining_time": "1 day, 0:40:38"}
{"current_steps": 700, "total_steps": 2658, "loss": 0.6005, "learning_rate": 5e-06, "epoch": 0.7898448519040903, "percentage": 26.34, "elapsed_time": "8:46:39", "remaining_time": "1 day, 0:33:07"}
{"current_steps": 710, "total_steps": 2658, "loss": 0.5888, "learning_rate": 5e-06, "epoch": 0.8011283497884344, "percentage": 26.71, "elapsed_time": "8:54:10", "remaining_time": "1 day, 0:25:34"}
{"current_steps": 720, "total_steps": 2658, "loss": 0.6029, "learning_rate": 5e-06, "epoch": 0.8124118476727785, "percentage": 27.09, "elapsed_time": "9:01:41", "remaining_time": "1 day, 0:18:02"}
{"current_steps": 730, "total_steps": 2658, "loss": 0.6004, "learning_rate": 5e-06, "epoch": 0.8236953455571228, "percentage": 27.46, "elapsed_time": "9:09:13", "remaining_time": "1 day, 0:10:32"}
{"current_steps": 740, "total_steps": 2658, "loss": 0.6062, "learning_rate": 5e-06, "epoch": 0.8349788434414669, "percentage": 27.84, "elapsed_time": "9:16:44", "remaining_time": "1 day, 0:03:01"}
{"current_steps": 750, "total_steps": 2658, "loss": 0.6012, "learning_rate": 5e-06, "epoch": 0.846262341325811, "percentage": 28.22, "elapsed_time": "9:24:16", "remaining_time": "23:55:30"}
{"current_steps": 760, "total_steps": 2658, "loss": 0.5986, "learning_rate": 5e-06, "epoch": 0.8575458392101551, "percentage": 28.59, "elapsed_time": "9:31:47", "remaining_time": "23:47:59"}
{"current_steps": 770, "total_steps": 2658, "loss": 0.598, "learning_rate": 5e-06, "epoch": 0.8688293370944993, "percentage": 28.97, "elapsed_time": "9:39:19", "remaining_time": "23:40:29"}
{"current_steps": 780, "total_steps": 2658, "loss": 0.5899, "learning_rate": 5e-06, "epoch": 0.8801128349788434, "percentage": 29.35, "elapsed_time": "9:46:51", "remaining_time": "23:32:58"}
{"current_steps": 790, "total_steps": 2658, "loss": 0.5959, "learning_rate": 5e-06, "epoch": 0.8913963328631875, "percentage": 29.72, "elapsed_time": "9:54:23", "remaining_time": "23:25:28"}
{"current_steps": 800, "total_steps": 2658, "loss": 0.5966, "learning_rate": 5e-06, "epoch": 0.9026798307475318, "percentage": 30.1, "elapsed_time": "10:01:55", "remaining_time": "23:17:57"}
{"current_steps": 810, "total_steps": 2658, "loss": 0.5977, "learning_rate": 5e-06, "epoch": 0.9139633286318759, "percentage": 30.47, "elapsed_time": "10:09:27", "remaining_time": "23:10:27"}
{"current_steps": 820, "total_steps": 2658, "loss": 0.5903, "learning_rate": 5e-06, "epoch": 0.92524682651622, "percentage": 30.85, "elapsed_time": "10:16:58", "remaining_time": "23:02:55"}
{"current_steps": 830, "total_steps": 2658, "loss": 0.5926, "learning_rate": 5e-06, "epoch": 0.9365303244005642, "percentage": 31.23, "elapsed_time": "10:24:30", "remaining_time": "22:55:24"}
{"current_steps": 840, "total_steps": 2658, "loss": 0.5968, "learning_rate": 5e-06, "epoch": 0.9478138222849083, "percentage": 31.6, "elapsed_time": "10:32:01", "remaining_time": "22:47:53"}
{"current_steps": 850, "total_steps": 2658, "loss": 0.5946, "learning_rate": 5e-06, "epoch": 0.9590973201692524, "percentage": 31.98, "elapsed_time": "10:39:33", "remaining_time": "22:40:23"}
{"current_steps": 860, "total_steps": 2658, "loss": 0.5837, "learning_rate": 5e-06, "epoch": 0.9703808180535967, "percentage": 32.36, "elapsed_time": "10:47:05", "remaining_time": "22:32:52"}
{"current_steps": 870, "total_steps": 2658, "loss": 0.5998, "learning_rate": 5e-06, "epoch": 0.9816643159379408, "percentage": 32.73, "elapsed_time": "10:54:37", "remaining_time": "22:25:21"}
{"current_steps": 880, "total_steps": 2658, "loss": 0.5875, "learning_rate": 5e-06, "epoch": 0.9929478138222849, "percentage": 33.11, "elapsed_time": "11:02:08", "remaining_time": "22:17:50"}
{"current_steps": 886, "total_steps": 2658, "eval_loss": 0.5916627049446106, "epoch": 0.9997179125528914, "percentage": 33.33, "elapsed_time": "11:18:30", "remaining_time": "22:37:01"}
{"current_steps": 890, "total_steps": 2658, "loss": 0.6038, "learning_rate": 5e-06, "epoch": 1.004231311706629, "percentage": 33.48, "elapsed_time": "11:22:43", "remaining_time": "22:36:13"}
{"current_steps": 900, "total_steps": 2658, "loss": 0.5204, "learning_rate": 5e-06, "epoch": 1.0155148095909732, "percentage": 33.86, "elapsed_time": "11:30:14", "remaining_time": "22:28:17"}
{"current_steps": 910, "total_steps": 2658, "loss": 0.5098, "learning_rate": 5e-06, "epoch": 1.0267983074753173, "percentage": 34.24, "elapsed_time": "11:37:46", "remaining_time": "22:20:20"}
{"current_steps": 920, "total_steps": 2658, "loss": 0.5147, "learning_rate": 5e-06, "epoch": 1.0380818053596614, "percentage": 34.61, "elapsed_time": "11:45:18", "remaining_time": "22:12:24"}
{"current_steps": 930, "total_steps": 2658, "loss": 0.532, "learning_rate": 5e-06, "epoch": 1.0493653032440056, "percentage": 34.99, "elapsed_time": "11:52:49", "remaining_time": "22:04:29"}
{"current_steps": 940, "total_steps": 2658, "loss": 0.5232, "learning_rate": 5e-06, "epoch": 1.0606488011283497, "percentage": 35.36, "elapsed_time": "12:00:21", "remaining_time": "21:56:34"}
{"current_steps": 950, "total_steps": 2658, "loss": 0.5182, "learning_rate": 5e-06, "epoch": 1.071932299012694, "percentage": 35.74, "elapsed_time": "12:07:53", "remaining_time": "21:48:40"}
{"current_steps": 960, "total_steps": 2658, "loss": 0.5156, "learning_rate": 5e-06, "epoch": 1.0832157968970382, "percentage": 36.12, "elapsed_time": "12:15:25", "remaining_time": "21:40:46"}
{"current_steps": 970, "total_steps": 2658, "loss": 0.5255, "learning_rate": 5e-06, "epoch": 1.0944992947813823, "percentage": 36.49, "elapsed_time": "12:22:57", "remaining_time": "21:32:53"}
{"current_steps": 980, "total_steps": 2658, "loss": 0.5275, "learning_rate": 5e-06, "epoch": 1.1057827926657264, "percentage": 36.87, "elapsed_time": "12:30:28", "remaining_time": "21:25:00"}
{"current_steps": 990, "total_steps": 2658, "loss": 0.5266, "learning_rate": 5e-06, "epoch": 1.1170662905500706, "percentage": 37.25, "elapsed_time": "12:37:59", "remaining_time": "21:17:06"}
{"current_steps": 1000, "total_steps": 2658, "loss": 0.5245, "learning_rate": 5e-06, "epoch": 1.1283497884344147, "percentage": 37.62, "elapsed_time": "12:45:31", "remaining_time": "21:09:14"}
{"current_steps": 1010, "total_steps": 2658, "loss": 0.5272, "learning_rate": 5e-06, "epoch": 1.1396332863187588, "percentage": 38.0, "elapsed_time": "12:53:03", "remaining_time": "21:01:22"}
{"current_steps": 1020, "total_steps": 2658, "loss": 0.5269, "learning_rate": 5e-06, "epoch": 1.150916784203103, "percentage": 38.37, "elapsed_time": "13:00:34", "remaining_time": "20:53:31"}
{"current_steps": 1030, "total_steps": 2658, "loss": 0.5226, "learning_rate": 5e-06, "epoch": 1.162200282087447, "percentage": 38.75, "elapsed_time": "13:08:06", "remaining_time": "20:45:40"}
{"current_steps": 1040, "total_steps": 2658, "loss": 0.5175, "learning_rate": 5e-06, "epoch": 1.1734837799717912, "percentage": 39.13, "elapsed_time": "13:15:38", "remaining_time": "20:37:50"}
{"current_steps": 1050, "total_steps": 2658, "loss": 0.5241, "learning_rate": 5e-06, "epoch": 1.1847672778561353, "percentage": 39.5, "elapsed_time": "13:23:10", "remaining_time": "20:29:59"}
{"current_steps": 1060, "total_steps": 2658, "loss": 0.5291, "learning_rate": 5e-06, "epoch": 1.1960507757404795, "percentage": 39.88, "elapsed_time": "13:30:41", "remaining_time": "20:22:09"}
{"current_steps": 1070, "total_steps": 2658, "loss": 0.5249, "learning_rate": 5e-06, "epoch": 1.2073342736248236, "percentage": 40.26, "elapsed_time": "13:38:13", "remaining_time": "20:14:19"}
{"current_steps": 1080, "total_steps": 2658, "loss": 0.5235, "learning_rate": 5e-06, "epoch": 1.2186177715091677, "percentage": 40.63, "elapsed_time": "13:45:44", "remaining_time": "20:06:30"}
{"current_steps": 1090, "total_steps": 2658, "loss": 0.5283, "learning_rate": 5e-06, "epoch": 1.229901269393512, "percentage": 41.01, "elapsed_time": "13:53:16", "remaining_time": "19:58:41"}
{"current_steps": 1100, "total_steps": 2658, "loss": 0.5288, "learning_rate": 5e-06, "epoch": 1.2411847672778562, "percentage": 41.38, "elapsed_time": "14:00:47", "remaining_time": "19:50:52"}
{"current_steps": 1110, "total_steps": 2658, "loss": 0.5195, "learning_rate": 5e-06, "epoch": 1.2524682651622003, "percentage": 41.76, "elapsed_time": "14:08:19", "remaining_time": "19:43:04"}
{"current_steps": 1120, "total_steps": 2658, "loss": 0.542, "learning_rate": 5e-06, "epoch": 1.2637517630465445, "percentage": 42.14, "elapsed_time": "14:15:51", "remaining_time": "19:35:16"}
{"current_steps": 1130, "total_steps": 2658, "loss": 0.5287, "learning_rate": 5e-06, "epoch": 1.2750352609308886, "percentage": 42.51, "elapsed_time": "14:23:23", "remaining_time": "19:27:29"}
{"current_steps": 1140, "total_steps": 2658, "loss": 0.5267, "learning_rate": 5e-06, "epoch": 1.2863187588152327, "percentage": 42.89, "elapsed_time": "14:30:55", "remaining_time": "19:19:42"}
{"current_steps": 1150, "total_steps": 2658, "loss": 0.5289, "learning_rate": 5e-06, "epoch": 1.2976022566995769, "percentage": 43.27, "elapsed_time": "14:38:26", "remaining_time": "19:11:54"}
{"current_steps": 1160, "total_steps": 2658, "loss": 0.5267, "learning_rate": 5e-06, "epoch": 1.308885754583921, "percentage": 43.64, "elapsed_time": "14:45:58", "remaining_time": "19:04:08"}
{"current_steps": 1170, "total_steps": 2658, "loss": 0.5305, "learning_rate": 5e-06, "epoch": 1.320169252468265, "percentage": 44.02, "elapsed_time": "14:53:30", "remaining_time": "18:56:21"}
{"current_steps": 1180, "total_steps": 2658, "loss": 0.5262, "learning_rate": 5e-06, "epoch": 1.3314527503526092, "percentage": 44.39, "elapsed_time": "15:01:01", "remaining_time": "18:48:34"}
{"current_steps": 1190, "total_steps": 2658, "loss": 0.5391, "learning_rate": 5e-06, "epoch": 1.3427362482369536, "percentage": 44.77, "elapsed_time": "15:08:33", "remaining_time": "18:40:48"}
{"current_steps": 1200, "total_steps": 2658, "loss": 0.5272, "learning_rate": 5e-06, "epoch": 1.3540197461212977, "percentage": 45.15, "elapsed_time": "15:16:05", "remaining_time": "18:33:02"}
{"current_steps": 1210, "total_steps": 2658, "loss": 0.5294, "learning_rate": 5e-06, "epoch": 1.3653032440056418, "percentage": 45.52, "elapsed_time": "15:23:37", "remaining_time": "18:25:17"}
{"current_steps": 1220, "total_steps": 2658, "loss": 0.5237, "learning_rate": 5e-06, "epoch": 1.376586741889986, "percentage": 45.9, "elapsed_time": "15:31:08", "remaining_time": "18:17:31"}
{"current_steps": 1230, "total_steps": 2658, "loss": 0.5239, "learning_rate": 5e-06, "epoch": 1.38787023977433, "percentage": 46.28, "elapsed_time": "15:38:40", "remaining_time": "18:09:46"}
{"current_steps": 1240, "total_steps": 2658, "loss": 0.5371, "learning_rate": 5e-06, "epoch": 1.3991537376586742, "percentage": 46.65, "elapsed_time": "15:46:11", "remaining_time": "18:02:00"}
{"current_steps": 1250, "total_steps": 2658, "loss": 0.5346, "learning_rate": 5e-06, "epoch": 1.4104372355430184, "percentage": 47.03, "elapsed_time": "15:53:42", "remaining_time": "17:54:15"}
{"current_steps": 1260, "total_steps": 2658, "loss": 0.5239, "learning_rate": 5e-06, "epoch": 1.4217207334273625, "percentage": 47.4, "elapsed_time": "16:01:13", "remaining_time": "17:46:30"}
{"current_steps": 1270, "total_steps": 2658, "loss": 0.5266, "learning_rate": 5e-06, "epoch": 1.4330042313117066, "percentage": 47.78, "elapsed_time": "16:08:45", "remaining_time": "17:38:46"}
{"current_steps": 1280, "total_steps": 2658, "loss": 0.5315, "learning_rate": 5e-06, "epoch": 1.4442877291960508, "percentage": 48.16, "elapsed_time": "16:16:17", "remaining_time": "17:31:02"}
{"current_steps": 1290, "total_steps": 2658, "loss": 0.5275, "learning_rate": 5e-06, "epoch": 1.4555712270803949, "percentage": 48.53, "elapsed_time": "16:23:49", "remaining_time": "17:23:18"}
{"current_steps": 1300, "total_steps": 2658, "loss": 0.5322, "learning_rate": 5e-06, "epoch": 1.466854724964739, "percentage": 48.91, "elapsed_time": "16:31:21", "remaining_time": "17:15:35"}
{"current_steps": 1310, "total_steps": 2658, "loss": 0.538, "learning_rate": 5e-06, "epoch": 1.4781382228490831, "percentage": 49.29, "elapsed_time": "16:38:53", "remaining_time": "17:07:52"}
{"current_steps": 1320, "total_steps": 2658, "loss": 0.5289, "learning_rate": 5e-06, "epoch": 1.4894217207334273, "percentage": 49.66, "elapsed_time": "16:46:26", "remaining_time": "17:00:09"}
{"current_steps": 1330, "total_steps": 2658, "loss": 0.5253, "learning_rate": 5e-06, "epoch": 1.5007052186177714, "percentage": 50.04, "elapsed_time": "16:53:58", "remaining_time": "16:52:26"}
{"current_steps": 1340, "total_steps": 2658, "loss": 0.5324, "learning_rate": 5e-06, "epoch": 1.5119887165021155, "percentage": 50.41, "elapsed_time": "17:01:30", "remaining_time": "16:44:44"}
{"current_steps": 1350, "total_steps": 2658, "loss": 0.5214, "learning_rate": 5e-06, "epoch": 1.5232722143864597, "percentage": 50.79, "elapsed_time": "17:09:02", "remaining_time": "16:37:01"}
{"current_steps": 1360, "total_steps": 2658, "loss": 0.5252, "learning_rate": 5e-06, "epoch": 1.5345557122708038, "percentage": 51.17, "elapsed_time": "17:16:34", "remaining_time": "16:29:19"}
{"current_steps": 1370, "total_steps": 2658, "loss": 0.5251, "learning_rate": 5e-06, "epoch": 1.5458392101551481, "percentage": 51.54, "elapsed_time": "17:24:06", "remaining_time": "16:21:37"}
{"current_steps": 1380, "total_steps": 2658, "loss": 0.5248, "learning_rate": 5e-06, "epoch": 1.5571227080394923, "percentage": 51.92, "elapsed_time": "17:31:38", "remaining_time": "16:13:54"}
{"current_steps": 1390, "total_steps": 2658, "loss": 0.5323, "learning_rate": 5e-06, "epoch": 1.5684062059238364, "percentage": 52.29, "elapsed_time": "17:39:10", "remaining_time": "16:06:12"}
{"current_steps": 1400, "total_steps": 2658, "loss": 0.5255, "learning_rate": 5e-06, "epoch": 1.5796897038081805, "percentage": 52.67, "elapsed_time": "17:46:42", "remaining_time": "15:58:30"}
{"current_steps": 1410, "total_steps": 2658, "loss": 0.5339, "learning_rate": 5e-06, "epoch": 1.5909732016925247, "percentage": 53.05, "elapsed_time": "17:54:14", "remaining_time": "15:50:49"}
{"current_steps": 1420, "total_steps": 2658, "loss": 0.5298, "learning_rate": 5e-06, "epoch": 1.6022566995768688, "percentage": 53.42, "elapsed_time": "18:01:46", "remaining_time": "15:43:07"}
{"current_steps": 1430, "total_steps": 2658, "loss": 0.5478, "learning_rate": 5e-06, "epoch": 1.6135401974612131, "percentage": 53.8, "elapsed_time": "18:09:18", "remaining_time": "15:35:26"}
{"current_steps": 1440, "total_steps": 2658, "loss": 0.531, "learning_rate": 5e-06, "epoch": 1.6248236953455573, "percentage": 54.18, "elapsed_time": "18:16:50", "remaining_time": "15:27:44"}
{"current_steps": 1450, "total_steps": 2658, "loss": 0.5225, "learning_rate": 5e-06, "epoch": 1.6361071932299014, "percentage": 54.55, "elapsed_time": "18:24:22", "remaining_time": "15:20:03"}
{"current_steps": 1460, "total_steps": 2658, "loss": 0.5257, "learning_rate": 5e-06, "epoch": 1.6473906911142455, "percentage": 54.93, "elapsed_time": "18:31:54", "remaining_time": "15:12:22"}
{"current_steps": 1470, "total_steps": 2658, "loss": 0.5412, "learning_rate": 5e-06, "epoch": 1.6586741889985896, "percentage": 55.3, "elapsed_time": "18:39:26", "remaining_time": "15:04:41"}
{"current_steps": 1480, "total_steps": 2658, "loss": 0.5367, "learning_rate": 5e-06, "epoch": 1.6699576868829338, "percentage": 55.68, "elapsed_time": "18:46:58", "remaining_time": "14:57:00"}
{"current_steps": 1490, "total_steps": 2658, "loss": 0.5293, "learning_rate": 5e-06, "epoch": 1.681241184767278, "percentage": 56.06, "elapsed_time": "18:54:30", "remaining_time": "14:49:20"}
{"current_steps": 1500, "total_steps": 2658, "loss": 0.5323, "learning_rate": 5e-06, "epoch": 1.692524682651622, "percentage": 56.43, "elapsed_time": "19:02:02", "remaining_time": "14:41:39"}
{"current_steps": 1510, "total_steps": 2658, "loss": 0.5263, "learning_rate": 5e-06, "epoch": 1.7038081805359662, "percentage": 56.81, "elapsed_time": "19:09:34", "remaining_time": "14:33:58"}
{"current_steps": 1520, "total_steps": 2658, "loss": 0.5334, "learning_rate": 5e-06, "epoch": 1.7150916784203103, "percentage": 57.19, "elapsed_time": "19:17:06", "remaining_time": "14:26:18"}
{"current_steps": 1530, "total_steps": 2658, "loss": 0.5305, "learning_rate": 5e-06, "epoch": 1.7263751763046544, "percentage": 57.56, "elapsed_time": "19:24:38", "remaining_time": "14:18:38"}
{"current_steps": 1540, "total_steps": 2658, "loss": 0.5304, "learning_rate": 5e-06, "epoch": 1.7376586741889986, "percentage": 57.94, "elapsed_time": "19:32:11", "remaining_time": "14:10:58"}
{"current_steps": 1550, "total_steps": 2658, "loss": 0.5216, "learning_rate": 5e-06, "epoch": 1.7489421720733427, "percentage": 58.31, "elapsed_time": "19:39:42", "remaining_time": "14:03:18"}
{"current_steps": 1560, "total_steps": 2658, "loss": 0.5322, "learning_rate": 5e-06, "epoch": 1.7602256699576868, "percentage": 58.69, "elapsed_time": "19:47:15", "remaining_time": "13:55:38"}
{"current_steps": 1570, "total_steps": 2658, "loss": 0.5321, "learning_rate": 5e-06, "epoch": 1.771509167842031, "percentage": 59.07, "elapsed_time": "19:54:46", "remaining_time": "13:47:58"}
{"current_steps": 1580, "total_steps": 2658, "loss": 0.5288, "learning_rate": 5e-06, "epoch": 1.782792665726375, "percentage": 59.44, "elapsed_time": "20:02:18", "remaining_time": "13:40:18"}
{"current_steps": 1590, "total_steps": 2658, "loss": 0.5219, "learning_rate": 5e-06, "epoch": 1.7940761636107192, "percentage": 59.82, "elapsed_time": "20:09:50", "remaining_time": "13:32:39"}
{"current_steps": 1600, "total_steps": 2658, "loss": 0.5292, "learning_rate": 5e-06, "epoch": 1.8053596614950633, "percentage": 60.2, "elapsed_time": "20:17:22", "remaining_time": "13:24:59"}
{"current_steps": 1610, "total_steps": 2658, "loss": 0.5381, "learning_rate": 5e-06, "epoch": 1.8166431593794075, "percentage": 60.57, "elapsed_time": "20:24:53", "remaining_time": "13:17:19"}
{"current_steps": 1620, "total_steps": 2658, "loss": 0.5344, "learning_rate": 5e-06, "epoch": 1.8279266572637518, "percentage": 60.95, "elapsed_time": "20:32:25", "remaining_time": "13:09:39"}
{"current_steps": 1630, "total_steps": 2658, "loss": 0.5201, "learning_rate": 5e-06, "epoch": 1.839210155148096, "percentage": 61.32, "elapsed_time": "20:39:57", "remaining_time": "13:02:00"}
{"current_steps": 1640, "total_steps": 2658, "loss": 0.5272, "learning_rate": 5e-06, "epoch": 1.85049365303244, "percentage": 61.7, "elapsed_time": "20:47:29", "remaining_time": "12:54:21"}
{"current_steps": 1650, "total_steps": 2658, "loss": 0.5381, "learning_rate": 5e-06, "epoch": 1.8617771509167842, "percentage": 62.08, "elapsed_time": "20:55:01", "remaining_time": "12:46:42"}
{"current_steps": 1660, "total_steps": 2658, "loss": 0.5325, "learning_rate": 5e-06, "epoch": 1.8730606488011283, "percentage": 62.45, "elapsed_time": "21:02:33", "remaining_time": "12:39:03"}
{"current_steps": 1670, "total_steps": 2658, "loss": 0.5308, "learning_rate": 5e-06, "epoch": 1.8843441466854725, "percentage": 62.83, "elapsed_time": "21:10:05", "remaining_time": "12:31:24"}
{"current_steps": 1680, "total_steps": 2658, "loss": 0.5401, "learning_rate": 5e-06, "epoch": 1.8956276445698168, "percentage": 63.21, "elapsed_time": "21:17:37", "remaining_time": "12:23:45"}
{"current_steps": 1690, "total_steps": 2658, "loss": 0.5209, "learning_rate": 5e-06, "epoch": 1.906911142454161, "percentage": 63.58, "elapsed_time": "21:25:09", "remaining_time": "12:16:06"}
{"current_steps": 1700, "total_steps": 2658, "loss": 0.5274, "learning_rate": 5e-06, "epoch": 1.918194640338505, "percentage": 63.96, "elapsed_time": "21:32:40", "remaining_time": "12:08:27"}
{"current_steps": 1710, "total_steps": 2658, "loss": 0.5293, "learning_rate": 5e-06, "epoch": 1.9294781382228492, "percentage": 64.33, "elapsed_time": "21:40:12", "remaining_time": "12:00:49"}
{"current_steps": 1720, "total_steps": 2658, "loss": 0.5288, "learning_rate": 5e-06, "epoch": 1.9407616361071933, "percentage": 64.71, "elapsed_time": "21:47:44", "remaining_time": "11:53:10"}
{"current_steps": 1730, "total_steps": 2658, "loss": 0.5289, "learning_rate": 5e-06, "epoch": 1.9520451339915375, "percentage": 65.09, "elapsed_time": "21:55:16", "remaining_time": "11:45:31"}
{"current_steps": 1740, "total_steps": 2658, "loss": 0.5418, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "22:02:47", "remaining_time": "11:37:53"}
{"current_steps": 1750, "total_steps": 2658, "loss": 0.5402, "learning_rate": 5e-06, "epoch": 1.9746121297602257, "percentage": 65.84, "elapsed_time": "22:10:19", "remaining_time": "11:30:14"}
{"current_steps": 1760, "total_steps": 2658, "loss": 0.5268, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:17:50", "remaining_time": "11:22:36"}
{"current_steps": 1770, "total_steps": 2658, "loss": 0.5215, "learning_rate": 5e-06, "epoch": 1.997179125528914, "percentage": 66.59, "elapsed_time": "22:25:22", "remaining_time": "11:14:58"}
{"current_steps": 1772, "total_steps": 2658, "eval_loss": 0.5913873910903931, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:38:52", "remaining_time": "11:19:26"}
{"current_steps": 1780, "total_steps": 2658, "loss": 0.5208, "learning_rate": 5e-06, "epoch": 2.008462623413258, "percentage": 66.97, "elapsed_time": "22:45:59", "remaining_time": "11:13:47"}
{"current_steps": 1790, "total_steps": 2658, "loss": 0.4524, "learning_rate": 5e-06, "epoch": 2.0197461212976022, "percentage": 67.34, "elapsed_time": "22:53:30", "remaining_time": "11:06:02"}
{"current_steps": 1800, "total_steps": 2658, "loss": 0.4428, "learning_rate": 5e-06, "epoch": 2.0310296191819464, "percentage": 67.72, "elapsed_time": "23:01:02", "remaining_time": "10:58:17"}
{"current_steps": 1810, "total_steps": 2658, "loss": 0.4497, "learning_rate": 5e-06, "epoch": 2.0423131170662905, "percentage": 68.1, "elapsed_time": "23:08:33", "remaining_time": "10:50:33"}
{"current_steps": 1820, "total_steps": 2658, "loss": 0.4501, "learning_rate": 5e-06, "epoch": 2.0535966149506346, "percentage": 68.47, "elapsed_time": "23:16:05", "remaining_time": "10:42:49"}
{"current_steps": 1830, "total_steps": 2658, "loss": 0.4366, "learning_rate": 5e-06, "epoch": 2.0648801128349787, "percentage": 68.85, "elapsed_time": "23:23:37", "remaining_time": "10:35:04"}
{"current_steps": 1840, "total_steps": 2658, "loss": 0.45, "learning_rate": 5e-06, "epoch": 2.076163610719323, "percentage": 69.22, "elapsed_time": "23:31:09", "remaining_time": "10:27:21"}
{"current_steps": 1850, "total_steps": 2658, "loss": 0.4487, "learning_rate": 5e-06, "epoch": 2.087447108603667, "percentage": 69.6, "elapsed_time": "23:38:41", "remaining_time": "10:19:37"}
{"current_steps": 1860, "total_steps": 2658, "loss": 0.4524, "learning_rate": 5e-06, "epoch": 2.098730606488011, "percentage": 69.98, "elapsed_time": "23:46:12", "remaining_time": "10:11:53"}
{"current_steps": 1870, "total_steps": 2658, "loss": 0.4554, "learning_rate": 5e-06, "epoch": 2.1100141043723553, "percentage": 70.35, "elapsed_time": "23:53:44", "remaining_time": "10:04:09"}
{"current_steps": 1880, "total_steps": 2658, "loss": 0.4545, "learning_rate": 5e-06, "epoch": 2.1212976022566994, "percentage": 70.73, "elapsed_time": "1 day, 0:01:15", "remaining_time": "9:56:26"}
{"current_steps": 1890, "total_steps": 2658, "loss": 0.4576, "learning_rate": 5e-06, "epoch": 2.1325811001410435, "percentage": 71.11, "elapsed_time": "1 day, 0:08:47", "remaining_time": "9:48:42"}
{"current_steps": 1900, "total_steps": 2658, "loss": 0.456, "learning_rate": 5e-06, "epoch": 2.143864598025388, "percentage": 71.48, "elapsed_time": "1 day, 0:16:19", "remaining_time": "9:40:59"}
{"current_steps": 1910, "total_steps": 2658, "loss": 0.4555, "learning_rate": 5e-06, "epoch": 2.155148095909732, "percentage": 71.86, "elapsed_time": "1 day, 0:23:51", "remaining_time": "9:33:16"}
{"current_steps": 1920, "total_steps": 2658, "loss": 0.4516, "learning_rate": 5e-06, "epoch": 2.1664315937940763, "percentage": 72.23, "elapsed_time": "1 day, 0:31:23", "remaining_time": "9:25:33"}
{"current_steps": 1930, "total_steps": 2658, "loss": 0.4554, "learning_rate": 5e-06, "epoch": 2.1777150916784205, "percentage": 72.61, "elapsed_time": "1 day, 0:38:55", "remaining_time": "9:17:51"}
{"current_steps": 1940, "total_steps": 2658, "loss": 0.4501, "learning_rate": 5e-06, "epoch": 2.1889985895627646, "percentage": 72.99, "elapsed_time": "1 day, 0:46:26", "remaining_time": "9:10:08"}
{"current_steps": 1950, "total_steps": 2658, "loss": 0.4439, "learning_rate": 5e-06, "epoch": 2.2002820874471087, "percentage": 73.36, "elapsed_time": "1 day, 0:53:58", "remaining_time": "9:02:25"}
{"current_steps": 1960, "total_steps": 2658, "loss": 0.4514, "learning_rate": 5e-06, "epoch": 2.211565585331453, "percentage": 73.74, "elapsed_time": "1 day, 1:01:30", "remaining_time": "8:54:43"}
{"current_steps": 1970, "total_steps": 2658, "loss": 0.4443, "learning_rate": 5e-06, "epoch": 2.222849083215797, "percentage": 74.12, "elapsed_time": "1 day, 1:09:01", "remaining_time": "8:47:00"}
{"current_steps": 1980, "total_steps": 2658, "loss": 0.4508, "learning_rate": 5e-06, "epoch": 2.234132581100141, "percentage": 74.49, "elapsed_time": "1 day, 1:16:33", "remaining_time": "8:39:18"}
{"current_steps": 1990, "total_steps": 2658, "loss": 0.4533, "learning_rate": 5e-06, "epoch": 2.2454160789844853, "percentage": 74.87, "elapsed_time": "1 day, 1:24:05", "remaining_time": "8:31:36"}
{"current_steps": 2000, "total_steps": 2658, "loss": 0.4591, "learning_rate": 5e-06, "epoch": 2.2566995768688294, "percentage": 75.24, "elapsed_time": "1 day, 1:31:36", "remaining_time": "8:23:53"}
{"current_steps": 2010, "total_steps": 2658, "loss": 0.4583, "learning_rate": 5e-06, "epoch": 2.2679830747531735, "percentage": 75.62, "elapsed_time": "1 day, 1:39:08", "remaining_time": "8:16:11"}
{"current_steps": 2020, "total_steps": 2658, "loss": 0.4665, "learning_rate": 5e-06, "epoch": 2.2792665726375176, "percentage": 76.0, "elapsed_time": "1 day, 1:46:39", "remaining_time": "8:08:30"}
{"current_steps": 2030, "total_steps": 2658, "loss": 0.4626, "learning_rate": 5e-06, "epoch": 2.2905500705218618, "percentage": 76.37, "elapsed_time": "1 day, 1:54:11", "remaining_time": "8:00:48"}
{"current_steps": 2040, "total_steps": 2658, "loss": 0.4529, "learning_rate": 5e-06, "epoch": 2.301833568406206, "percentage": 76.75, "elapsed_time": "1 day, 2:01:43", "remaining_time": "7:53:06"}
{"current_steps": 2050, "total_steps": 2658, "loss": 0.4533, "learning_rate": 5e-06, "epoch": 2.31311706629055, "percentage": 77.13, "elapsed_time": "1 day, 2:09:15", "remaining_time": "7:45:25"}
{"current_steps": 2060, "total_steps": 2658, "loss": 0.4694, "learning_rate": 5e-06, "epoch": 2.324400564174894, "percentage": 77.5, "elapsed_time": "1 day, 2:16:47", "remaining_time": "7:37:43"}
{"current_steps": 2070, "total_steps": 2658, "loss": 0.4571, "learning_rate": 5e-06, "epoch": 2.3356840620592383, "percentage": 77.88, "elapsed_time": "1 day, 2:24:18", "remaining_time": "7:30:02"}
{"current_steps": 2080, "total_steps": 2658, "loss": 0.4637, "learning_rate": 5e-06, "epoch": 2.3469675599435824, "percentage": 78.25, "elapsed_time": "1 day, 2:31:50", "remaining_time": "7:22:20"}
{"current_steps": 2090, "total_steps": 2658, "loss": 0.454, "learning_rate": 5e-06, "epoch": 2.3582510578279265, "percentage": 78.63, "elapsed_time": "1 day, 2:39:22", "remaining_time": "7:14:39"}
{"current_steps": 2100, "total_steps": 2658, "loss": 0.4621, "learning_rate": 5e-06, "epoch": 2.3695345557122707, "percentage": 79.01, "elapsed_time": "1 day, 2:46:54", "remaining_time": "7:06:58"}
{"current_steps": 2110, "total_steps": 2658, "loss": 0.4616, "learning_rate": 5e-06, "epoch": 2.380818053596615, "percentage": 79.38, "elapsed_time": "1 day, 2:54:25", "remaining_time": "6:59:17"}
{"current_steps": 2120, "total_steps": 2658, "loss": 0.4544, "learning_rate": 5e-06, "epoch": 2.392101551480959, "percentage": 79.76, "elapsed_time": "1 day, 3:01:57", "remaining_time": "6:51:36"}
{"current_steps": 2130, "total_steps": 2658, "loss": 0.4612, "learning_rate": 5e-06, "epoch": 2.403385049365303, "percentage": 80.14, "elapsed_time": "1 day, 3:09:28", "remaining_time": "6:43:55"}
{"current_steps": 2140, "total_steps": 2658, "loss": 0.4567, "learning_rate": 5e-06, "epoch": 2.414668547249647, "percentage": 80.51, "elapsed_time": "1 day, 3:17:00", "remaining_time": "6:36:14"}
{"current_steps": 2150, "total_steps": 2658, "loss": 0.4624, "learning_rate": 5e-06, "epoch": 2.4259520451339913, "percentage": 80.89, "elapsed_time": "1 day, 3:24:32", "remaining_time": "6:28:34"}
{"current_steps": 2160, "total_steps": 2658, "loss": 0.4621, "learning_rate": 5e-06, "epoch": 2.4372355430183354, "percentage": 81.26, "elapsed_time": "1 day, 3:32:05", "remaining_time": "6:20:53"}
{"current_steps": 2170, "total_steps": 2658, "loss": 0.4602, "learning_rate": 5e-06, "epoch": 2.44851904090268, "percentage": 81.64, "elapsed_time": "1 day, 3:39:37", "remaining_time": "6:13:13"}
{"current_steps": 2180, "total_steps": 2658, "loss": 0.461, "learning_rate": 5e-06, "epoch": 2.459802538787024, "percentage": 82.02, "elapsed_time": "1 day, 3:47:09", "remaining_time": "6:05:33"}
{"current_steps": 2190, "total_steps": 2658, "loss": 0.4631, "learning_rate": 5e-06, "epoch": 2.4710860366713683, "percentage": 82.39, "elapsed_time": "1 day, 3:54:40", "remaining_time": "5:57:52"}
{"current_steps": 2200, "total_steps": 2658, "loss": 0.4638, "learning_rate": 5e-06, "epoch": 2.4823695345557124, "percentage": 82.77, "elapsed_time": "1 day, 4:02:12", "remaining_time": "5:50:12"}
{"current_steps": 2210, "total_steps": 2658, "loss": 0.4702, "learning_rate": 5e-06, "epoch": 2.4936530324400565, "percentage": 83.15, "elapsed_time": "1 day, 4:09:44", "remaining_time": "5:42:32"}
{"current_steps": 2220, "total_steps": 2658, "loss": 0.4636, "learning_rate": 5e-06, "epoch": 2.5049365303244007, "percentage": 83.52, "elapsed_time": "1 day, 4:17:16", "remaining_time": "5:34:51"}
{"current_steps": 2230, "total_steps": 2658, "loss": 0.457, "learning_rate": 5e-06, "epoch": 2.516220028208745, "percentage": 83.9, "elapsed_time": "1 day, 4:24:47", "remaining_time": "5:27:11"}
{"current_steps": 2240, "total_steps": 2658, "loss": 0.4603, "learning_rate": 5e-06, "epoch": 2.527503526093089, "percentage": 84.27, "elapsed_time": "1 day, 4:32:19", "remaining_time": "5:19:31"}
{"current_steps": 2250, "total_steps": 2658, "loss": 0.4598, "learning_rate": 5e-06, "epoch": 2.538787023977433, "percentage": 84.65, "elapsed_time": "1 day, 4:39:50", "remaining_time": "5:11:51"}
{"current_steps": 2260, "total_steps": 2658, "loss": 0.4665, "learning_rate": 5e-06, "epoch": 2.550070521861777, "percentage": 85.03, "elapsed_time": "1 day, 4:47:22", "remaining_time": "5:04:12"}
{"current_steps": 2270, "total_steps": 2658, "loss": 0.4612, "learning_rate": 5e-06, "epoch": 2.5613540197461213, "percentage": 85.4, "elapsed_time": "1 day, 4:54:54", "remaining_time": "4:56:32"}
{"current_steps": 2280, "total_steps": 2658, "loss": 0.4607, "learning_rate": 5e-06, "epoch": 2.5726375176304654, "percentage": 85.78, "elapsed_time": "1 day, 5:02:26", "remaining_time": "4:48:52"}
{"current_steps": 2290, "total_steps": 2658, "loss": 0.4549, "learning_rate": 5e-06, "epoch": 2.5839210155148096, "percentage": 86.16, "elapsed_time": "1 day, 5:09:58", "remaining_time": "4:41:13"}
{"current_steps": 2300, "total_steps": 2658, "loss": 0.4694, "learning_rate": 5e-06, "epoch": 2.5952045133991537, "percentage": 86.53, "elapsed_time": "1 day, 5:17:30", "remaining_time": "4:33:33"}
{"current_steps": 2310, "total_steps": 2658, "loss": 0.4663, "learning_rate": 5e-06, "epoch": 2.606488011283498, "percentage": 86.91, "elapsed_time": "1 day, 5:25:01", "remaining_time": "4:25:54"}
{"current_steps": 2320, "total_steps": 2658, "loss": 0.4664, "learning_rate": 5e-06, "epoch": 2.617771509167842, "percentage": 87.28, "elapsed_time": "1 day, 5:32:33", "remaining_time": "4:18:14"}
{"current_steps": 2330, "total_steps": 2658, "loss": 0.4543, "learning_rate": 5e-06, "epoch": 2.629055007052186, "percentage": 87.66, "elapsed_time": "1 day, 5:40:05", "remaining_time": "4:10:35"}
{"current_steps": 2340, "total_steps": 2658, "loss": 0.4559, "learning_rate": 5e-06, "epoch": 2.64033850493653, "percentage": 88.04, "elapsed_time": "1 day, 5:47:37", "remaining_time": "4:02:55"}
{"current_steps": 2350, "total_steps": 2658, "loss": 0.4635, "learning_rate": 5e-06, "epoch": 2.6516220028208743, "percentage": 88.41, "elapsed_time": "1 day, 5:55:08", "remaining_time": "3:55:16"}
{"current_steps": 2360, "total_steps": 2658, "loss": 0.4686, "learning_rate": 5e-06, "epoch": 2.6629055007052185, "percentage": 88.79, "elapsed_time": "1 day, 6:02:40", "remaining_time": "3:47:37"}
{"current_steps": 2370, "total_steps": 2658, "loss": 0.46, "learning_rate": 5e-06, "epoch": 2.6741889985895626, "percentage": 89.16, "elapsed_time": "1 day, 6:10:11", "remaining_time": "3:39:58"}
{"current_steps": 2380, "total_steps": 2658, "loss": 0.4727, "learning_rate": 5e-06, "epoch": 2.685472496473907, "percentage": 89.54, "elapsed_time": "1 day, 6:17:43", "remaining_time": "3:32:19"}
{"current_steps": 2390, "total_steps": 2658, "loss": 0.4667, "learning_rate": 5e-06, "epoch": 2.6967559943582513, "percentage": 89.92, "elapsed_time": "1 day, 6:25:14", "remaining_time": "3:24:40"}
{"current_steps": 2400, "total_steps": 2658, "loss": 0.465, "learning_rate": 5e-06, "epoch": 2.7080394922425954, "percentage": 90.29, "elapsed_time": "1 day, 6:32:46", "remaining_time": "3:17:01"}
{"current_steps": 2410, "total_steps": 2658, "loss": 0.4659, "learning_rate": 5e-06, "epoch": 2.7193229901269396, "percentage": 90.67, "elapsed_time": "1 day, 6:40:18", "remaining_time": "3:09:22"}
{"current_steps": 2420, "total_steps": 2658, "loss": 0.4679, "learning_rate": 5e-06, "epoch": 2.7306064880112837, "percentage": 91.05, "elapsed_time": "1 day, 6:47:50", "remaining_time": "3:01:43"}
{"current_steps": 2430, "total_steps": 2658, "loss": 0.4628, "learning_rate": 5e-06, "epoch": 2.741889985895628, "percentage": 91.42, "elapsed_time": "1 day, 6:55:22", "remaining_time": "2:54:05"}
{"current_steps": 2440, "total_steps": 2658, "loss": 0.4654, "learning_rate": 5e-06, "epoch": 2.753173483779972, "percentage": 91.8, "elapsed_time": "1 day, 7:02:54", "remaining_time": "2:46:26"}
{"current_steps": 2450, "total_steps": 2658, "loss": 0.4697, "learning_rate": 5e-06, "epoch": 2.764456981664316, "percentage": 92.17, "elapsed_time": "1 day, 7:10:26", "remaining_time": "2:38:47"}
{"current_steps": 2460, "total_steps": 2658, "loss": 0.4705, "learning_rate": 5e-06, "epoch": 2.77574047954866, "percentage": 92.55, "elapsed_time": "1 day, 7:17:57", "remaining_time": "2:31:09"}
{"current_steps": 2470, "total_steps": 2658, "loss": 0.4641, "learning_rate": 5e-06, "epoch": 2.7870239774330043, "percentage": 92.93, "elapsed_time": "1 day, 7:25:29", "remaining_time": "2:23:30"}
{"current_steps": 2480, "total_steps": 2658, "loss": 0.4726, "learning_rate": 5e-06, "epoch": 2.7983074753173485, "percentage": 93.3, "elapsed_time": "1 day, 7:33:01", "remaining_time": "2:15:52"}
{"current_steps": 2490, "total_steps": 2658, "loss": 0.4734, "learning_rate": 5e-06, "epoch": 2.8095909732016926, "percentage": 93.68, "elapsed_time": "1 day, 7:40:33", "remaining_time": "2:08:13"}
{"current_steps": 2500, "total_steps": 2658, "loss": 0.4644, "learning_rate": 5e-06, "epoch": 2.8208744710860367, "percentage": 94.06, "elapsed_time": "1 day, 7:48:05", "remaining_time": "2:00:35"}
{"current_steps": 2510, "total_steps": 2658, "loss": 0.4794, "learning_rate": 5e-06, "epoch": 2.832157968970381, "percentage": 94.43, "elapsed_time": "1 day, 7:55:37", "remaining_time": "1:52:57"}
{"current_steps": 2520, "total_steps": 2658, "loss": 0.4628, "learning_rate": 5e-06, "epoch": 2.843441466854725, "percentage": 94.81, "elapsed_time": "1 day, 8:03:08", "remaining_time": "1:45:18"}
{"current_steps": 2530, "total_steps": 2658, "loss": 0.4715, "learning_rate": 5e-06, "epoch": 2.854724964739069, "percentage": 95.18, "elapsed_time": "1 day, 8:10:40", "remaining_time": "1:37:40"}
{"current_steps": 2540, "total_steps": 2658, "loss": 0.4633, "learning_rate": 5e-06, "epoch": 2.8660084626234132, "percentage": 95.56, "elapsed_time": "1 day, 8:18:12", "remaining_time": "1:30:02"}
{"current_steps": 2550, "total_steps": 2658, "loss": 0.4689, "learning_rate": 5e-06, "epoch": 2.8772919605077574, "percentage": 95.94, "elapsed_time": "1 day, 8:25:43", "remaining_time": "1:22:24"}
{"current_steps": 2560, "total_steps": 2658, "loss": 0.4659, "learning_rate": 5e-06, "epoch": 2.8885754583921015, "percentage": 96.31, "elapsed_time": "1 day, 8:33:15", "remaining_time": "1:14:46"}
{"current_steps": 2570, "total_steps": 2658, "loss": 0.4668, "learning_rate": 5e-06, "epoch": 2.8998589562764456, "percentage": 96.69, "elapsed_time": "1 day, 8:40:47", "remaining_time": "1:07:08"}
{"current_steps": 2580, "total_steps": 2658, "loss": 0.4723, "learning_rate": 5e-06, "epoch": 2.9111424541607898, "percentage": 97.07, "elapsed_time": "1 day, 8:48:19", "remaining_time": "0:59:30"}
{"current_steps": 2590, "total_steps": 2658, "loss": 0.4631, "learning_rate": 5e-06, "epoch": 2.922425952045134, "percentage": 97.44, "elapsed_time": "1 day, 8:55:50", "remaining_time": "0:51:52"}
{"current_steps": 2600, "total_steps": 2658, "loss": 0.4686, "learning_rate": 5e-06, "epoch": 2.933709449929478, "percentage": 97.82, "elapsed_time": "1 day, 9:03:22", "remaining_time": "0:44:14"}
{"current_steps": 2610, "total_steps": 2658, "loss": 0.4641, "learning_rate": 5e-06, "epoch": 2.944992947813822, "percentage": 98.19, "elapsed_time": "1 day, 9:10:54", "remaining_time": "0:36:36"}
{"current_steps": 2620, "total_steps": 2658, "loss": 0.4748, "learning_rate": 5e-06, "epoch": 2.9562764456981663, "percentage": 98.57, "elapsed_time": "1 day, 9:18:26", "remaining_time": "0:28:59"}
{"current_steps": 2630, "total_steps": 2658, "loss": 0.472, "learning_rate": 5e-06, "epoch": 2.9675599435825104, "percentage": 98.95, "elapsed_time": "1 day, 9:25:58", "remaining_time": "0:21:21"}
{"current_steps": 2640, "total_steps": 2658, "loss": 0.4627, "learning_rate": 5e-06, "epoch": 2.9788434414668545, "percentage": 99.32, "elapsed_time": "1 day, 9:33:30", "remaining_time": "0:13:43"}
{"current_steps": 2650, "total_steps": 2658, "loss": 0.4672, "learning_rate": 5e-06, "epoch": 2.9901269393511987, "percentage": 99.7, "elapsed_time": "1 day, 9:41:01", "remaining_time": "0:06:06"}
{"current_steps": 2658, "total_steps": 2658, "eval_loss": 0.6162799000740051, "epoch": 2.9991537376586743, "percentage": 100.0, "elapsed_time": "1 day, 10:00:11", "remaining_time": "0:00:00"}
{"current_steps": 2658, "total_steps": 2658, "epoch": 2.9991537376586743, "percentage": 100.0, "elapsed_time": "1 day, 10:01:55", "remaining_time": "0:00:00"}