hp_ablations_mistral_lr1e-5 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
beb2779 verified
{"current_steps": 10, "total_steps": 1479, "loss": 1.3197, "learning_rate": 1e-05, "epoch": 0.020253164556962026, "percentage": 0.68, "elapsed_time": "0:09:17", "remaining_time": "22:44:52"}
{"current_steps": 20, "total_steps": 1479, "loss": 0.7042, "learning_rate": 1e-05, "epoch": 0.04050632911392405, "percentage": 1.35, "elapsed_time": "0:18:30", "remaining_time": "22:30:32"}
{"current_steps": 30, "total_steps": 1479, "loss": 0.6472, "learning_rate": 1e-05, "epoch": 0.060759493670886074, "percentage": 2.03, "elapsed_time": "0:27:44", "remaining_time": "22:20:00"}
{"current_steps": 40, "total_steps": 1479, "loss": 0.6266, "learning_rate": 1e-05, "epoch": 0.0810126582278481, "percentage": 2.7, "elapsed_time": "0:36:58", "remaining_time": "22:09:59"}
{"current_steps": 50, "total_steps": 1479, "loss": 0.6144, "learning_rate": 1e-05, "epoch": 0.10126582278481013, "percentage": 3.38, "elapsed_time": "0:46:11", "remaining_time": "22:00:17"}
{"current_steps": 60, "total_steps": 1479, "loss": 0.608, "learning_rate": 1e-05, "epoch": 0.12151898734177215, "percentage": 4.06, "elapsed_time": "0:55:25", "remaining_time": "21:50:47"}
{"current_steps": 70, "total_steps": 1479, "loss": 0.6034, "learning_rate": 1e-05, "epoch": 0.14177215189873418, "percentage": 4.73, "elapsed_time": "1:04:39", "remaining_time": "21:41:24"}
{"current_steps": 80, "total_steps": 1479, "loss": 0.599, "learning_rate": 1e-05, "epoch": 0.1620253164556962, "percentage": 5.41, "elapsed_time": "1:13:53", "remaining_time": "21:32:02"}
{"current_steps": 90, "total_steps": 1479, "loss": 0.5981, "learning_rate": 1e-05, "epoch": 0.18227848101265823, "percentage": 6.09, "elapsed_time": "1:23:06", "remaining_time": "21:22:38"}
{"current_steps": 100, "total_steps": 1479, "loss": 0.6011, "learning_rate": 1e-05, "epoch": 0.20253164556962025, "percentage": 6.76, "elapsed_time": "1:32:20", "remaining_time": "21:13:22"}
{"current_steps": 110, "total_steps": 1479, "loss": 0.5939, "learning_rate": 1e-05, "epoch": 0.22278481012658227, "percentage": 7.44, "elapsed_time": "1:41:34", "remaining_time": "21:04:03"}
{"current_steps": 120, "total_steps": 1479, "loss": 0.5912, "learning_rate": 1e-05, "epoch": 0.2430379746835443, "percentage": 8.11, "elapsed_time": "1:50:47", "remaining_time": "20:54:43"}
{"current_steps": 130, "total_steps": 1479, "loss": 0.5897, "learning_rate": 1e-05, "epoch": 0.26329113924050634, "percentage": 8.79, "elapsed_time": "2:00:01", "remaining_time": "20:45:31"}
{"current_steps": 140, "total_steps": 1479, "loss": 0.5788, "learning_rate": 1e-05, "epoch": 0.28354430379746837, "percentage": 9.47, "elapsed_time": "2:09:15", "remaining_time": "20:36:16"}
{"current_steps": 150, "total_steps": 1479, "loss": 0.588, "learning_rate": 1e-05, "epoch": 0.3037974683544304, "percentage": 10.14, "elapsed_time": "2:18:28", "remaining_time": "20:26:56"}
{"current_steps": 160, "total_steps": 1479, "loss": 0.5863, "learning_rate": 1e-05, "epoch": 0.3240506329113924, "percentage": 10.82, "elapsed_time": "2:27:43", "remaining_time": "20:17:45"}
{"current_steps": 170, "total_steps": 1479, "loss": 0.588, "learning_rate": 1e-05, "epoch": 0.34430379746835443, "percentage": 11.49, "elapsed_time": "2:36:56", "remaining_time": "20:08:28"}
{"current_steps": 180, "total_steps": 1479, "loss": 0.5843, "learning_rate": 1e-05, "epoch": 0.36455696202531646, "percentage": 12.17, "elapsed_time": "2:46:11", "remaining_time": "19:59:17"}
{"current_steps": 190, "total_steps": 1479, "loss": 0.5829, "learning_rate": 1e-05, "epoch": 0.3848101265822785, "percentage": 12.85, "elapsed_time": "2:55:25", "remaining_time": "19:50:08"}
{"current_steps": 200, "total_steps": 1479, "loss": 0.5779, "learning_rate": 1e-05, "epoch": 0.4050632911392405, "percentage": 13.52, "elapsed_time": "3:04:39", "remaining_time": "19:40:50"}
{"current_steps": 210, "total_steps": 1479, "loss": 0.5738, "learning_rate": 1e-05, "epoch": 0.4253164556962025, "percentage": 14.2, "elapsed_time": "3:13:52", "remaining_time": "19:31:33"}
{"current_steps": 220, "total_steps": 1479, "loss": 0.5793, "learning_rate": 1e-05, "epoch": 0.44556962025316454, "percentage": 14.87, "elapsed_time": "3:23:06", "remaining_time": "19:22:18"}
{"current_steps": 230, "total_steps": 1479, "loss": 0.5789, "learning_rate": 1e-05, "epoch": 0.46582278481012657, "percentage": 15.55, "elapsed_time": "3:32:20", "remaining_time": "19:13:05"}
{"current_steps": 240, "total_steps": 1479, "loss": 0.5747, "learning_rate": 1e-05, "epoch": 0.4860759493670886, "percentage": 16.23, "elapsed_time": "3:41:33", "remaining_time": "19:03:48"}
{"current_steps": 250, "total_steps": 1479, "loss": 0.5796, "learning_rate": 1e-05, "epoch": 0.5063291139240507, "percentage": 16.9, "elapsed_time": "3:50:47", "remaining_time": "18:54:32"}
{"current_steps": 260, "total_steps": 1479, "loss": 0.5666, "learning_rate": 1e-05, "epoch": 0.5265822784810127, "percentage": 17.58, "elapsed_time": "4:00:01", "remaining_time": "18:45:19"}
{"current_steps": 270, "total_steps": 1479, "loss": 0.5721, "learning_rate": 1e-05, "epoch": 0.5468354430379747, "percentage": 18.26, "elapsed_time": "4:09:14", "remaining_time": "18:36:02"}
{"current_steps": 280, "total_steps": 1479, "loss": 0.5649, "learning_rate": 1e-05, "epoch": 0.5670886075949367, "percentage": 18.93, "elapsed_time": "4:18:28", "remaining_time": "18:26:51"}
{"current_steps": 290, "total_steps": 1479, "loss": 0.566, "learning_rate": 1e-05, "epoch": 0.5873417721518988, "percentage": 19.61, "elapsed_time": "4:27:43", "remaining_time": "18:17:40"}
{"current_steps": 300, "total_steps": 1479, "loss": 0.5671, "learning_rate": 1e-05, "epoch": 0.6075949367088608, "percentage": 20.28, "elapsed_time": "4:36:57", "remaining_time": "18:08:28"}
{"current_steps": 310, "total_steps": 1479, "loss": 0.5745, "learning_rate": 1e-05, "epoch": 0.6278481012658228, "percentage": 20.96, "elapsed_time": "4:46:12", "remaining_time": "17:59:15"}
{"current_steps": 320, "total_steps": 1479, "loss": 0.5707, "learning_rate": 1e-05, "epoch": 0.6481012658227848, "percentage": 21.64, "elapsed_time": "4:55:26", "remaining_time": "17:50:02"}
{"current_steps": 330, "total_steps": 1479, "loss": 0.5694, "learning_rate": 1e-05, "epoch": 0.6683544303797468, "percentage": 22.31, "elapsed_time": "5:04:40", "remaining_time": "17:40:50"}
{"current_steps": 340, "total_steps": 1479, "loss": 0.5696, "learning_rate": 1e-05, "epoch": 0.6886075949367089, "percentage": 22.99, "elapsed_time": "5:13:55", "remaining_time": "17:31:39"}
{"current_steps": 350, "total_steps": 1479, "loss": 0.5715, "learning_rate": 1e-05, "epoch": 0.7088607594936709, "percentage": 23.66, "elapsed_time": "5:23:10", "remaining_time": "17:22:28"}
{"current_steps": 360, "total_steps": 1479, "loss": 0.5743, "learning_rate": 1e-05, "epoch": 0.7291139240506329, "percentage": 24.34, "elapsed_time": "5:32:25", "remaining_time": "17:13:16"}
{"current_steps": 370, "total_steps": 1479, "loss": 0.5675, "learning_rate": 1e-05, "epoch": 0.7493670886075949, "percentage": 25.02, "elapsed_time": "5:41:40", "remaining_time": "17:04:05"}
{"current_steps": 380, "total_steps": 1479, "loss": 0.5642, "learning_rate": 1e-05, "epoch": 0.769620253164557, "percentage": 25.69, "elapsed_time": "5:50:55", "remaining_time": "16:54:53"}
{"current_steps": 390, "total_steps": 1479, "loss": 0.5669, "learning_rate": 1e-05, "epoch": 0.789873417721519, "percentage": 26.37, "elapsed_time": "6:00:09", "remaining_time": "16:45:39"}
{"current_steps": 400, "total_steps": 1479, "loss": 0.5664, "learning_rate": 1e-05, "epoch": 0.810126582278481, "percentage": 27.05, "elapsed_time": "6:09:23", "remaining_time": "16:36:26"}
{"current_steps": 410, "total_steps": 1479, "loss": 0.5604, "learning_rate": 1e-05, "epoch": 0.830379746835443, "percentage": 27.72, "elapsed_time": "6:18:38", "remaining_time": "16:27:13"}
{"current_steps": 420, "total_steps": 1479, "loss": 0.5693, "learning_rate": 1e-05, "epoch": 0.850632911392405, "percentage": 28.4, "elapsed_time": "6:27:52", "remaining_time": "16:17:59"}
{"current_steps": 430, "total_steps": 1479, "loss": 0.5633, "learning_rate": 1e-05, "epoch": 0.8708860759493671, "percentage": 29.07, "elapsed_time": "6:37:06", "remaining_time": "16:08:45"}
{"current_steps": 440, "total_steps": 1479, "loss": 0.5691, "learning_rate": 1e-05, "epoch": 0.8911392405063291, "percentage": 29.75, "elapsed_time": "6:46:19", "remaining_time": "15:59:29"}
{"current_steps": 450, "total_steps": 1479, "loss": 0.5603, "learning_rate": 1e-05, "epoch": 0.9113924050632911, "percentage": 30.43, "elapsed_time": "6:55:34", "remaining_time": "15:50:15"}
{"current_steps": 460, "total_steps": 1479, "loss": 0.5655, "learning_rate": 1e-05, "epoch": 0.9316455696202531, "percentage": 31.1, "elapsed_time": "7:04:48", "remaining_time": "15:41:01"}
{"current_steps": 470, "total_steps": 1479, "loss": 0.5664, "learning_rate": 1e-05, "epoch": 0.9518987341772152, "percentage": 31.78, "elapsed_time": "7:14:02", "remaining_time": "15:31:47"}
{"current_steps": 480, "total_steps": 1479, "loss": 0.5637, "learning_rate": 1e-05, "epoch": 0.9721518987341772, "percentage": 32.45, "elapsed_time": "7:23:15", "remaining_time": "15:22:32"}
{"current_steps": 490, "total_steps": 1479, "loss": 0.56, "learning_rate": 1e-05, "epoch": 0.9924050632911392, "percentage": 33.13, "elapsed_time": "7:32:29", "remaining_time": "15:13:17"}
{"current_steps": 493, "total_steps": 1479, "eval_loss": 0.07033738493919373, "epoch": 0.9984810126582279, "percentage": 33.33, "elapsed_time": "7:44:20", "remaining_time": "15:28:40"}
{"current_steps": 500, "total_steps": 1479, "loss": 0.4975, "learning_rate": 1e-05, "epoch": 1.0126582278481013, "percentage": 33.81, "elapsed_time": "7:51:14", "remaining_time": "15:22:41"}
{"current_steps": 510, "total_steps": 1479, "loss": 0.4476, "learning_rate": 1e-05, "epoch": 1.0329113924050632, "percentage": 34.48, "elapsed_time": "8:00:30", "remaining_time": "15:12:57"}
{"current_steps": 520, "total_steps": 1479, "loss": 0.4419, "learning_rate": 1e-05, "epoch": 1.0531645569620254, "percentage": 35.16, "elapsed_time": "8:09:45", "remaining_time": "15:03:14"}
{"current_steps": 530, "total_steps": 1479, "loss": 0.4418, "learning_rate": 1e-05, "epoch": 1.0734177215189873, "percentage": 35.84, "elapsed_time": "8:19:01", "remaining_time": "14:53:32"}
{"current_steps": 540, "total_steps": 1479, "loss": 0.4368, "learning_rate": 1e-05, "epoch": 1.0936708860759494, "percentage": 36.51, "elapsed_time": "8:28:16", "remaining_time": "14:43:49"}
{"current_steps": 550, "total_steps": 1479, "loss": 0.4393, "learning_rate": 1e-05, "epoch": 1.1139240506329113, "percentage": 37.19, "elapsed_time": "8:37:30", "remaining_time": "14:34:07"}
{"current_steps": 560, "total_steps": 1479, "loss": 0.4357, "learning_rate": 1e-05, "epoch": 1.1341772151898735, "percentage": 37.86, "elapsed_time": "8:46:46", "remaining_time": "14:24:28"}
{"current_steps": 570, "total_steps": 1479, "loss": 0.4424, "learning_rate": 1e-05, "epoch": 1.1544303797468354, "percentage": 38.54, "elapsed_time": "8:56:01", "remaining_time": "14:14:49"}
{"current_steps": 580, "total_steps": 1479, "loss": 0.4415, "learning_rate": 1e-05, "epoch": 1.1746835443037975, "percentage": 39.22, "elapsed_time": "9:05:17", "remaining_time": "14:05:11"}
{"current_steps": 590, "total_steps": 1479, "loss": 0.4357, "learning_rate": 1e-05, "epoch": 1.1949367088607594, "percentage": 39.89, "elapsed_time": "9:14:31", "remaining_time": "13:55:33"}
{"current_steps": 600, "total_steps": 1479, "loss": 0.4442, "learning_rate": 1e-05, "epoch": 1.2151898734177216, "percentage": 40.57, "elapsed_time": "9:23:46", "remaining_time": "13:45:56"}
{"current_steps": 610, "total_steps": 1479, "loss": 0.4419, "learning_rate": 1e-05, "epoch": 1.2354430379746835, "percentage": 41.24, "elapsed_time": "9:33:02", "remaining_time": "13:36:21"}
{"current_steps": 620, "total_steps": 1479, "loss": 0.4471, "learning_rate": 1e-05, "epoch": 1.2556962025316456, "percentage": 41.92, "elapsed_time": "9:42:17", "remaining_time": "13:26:45"}
{"current_steps": 630, "total_steps": 1479, "loss": 0.4503, "learning_rate": 1e-05, "epoch": 1.2759493670886077, "percentage": 42.6, "elapsed_time": "9:51:32", "remaining_time": "13:17:10"}
{"current_steps": 640, "total_steps": 1479, "loss": 0.4504, "learning_rate": 1e-05, "epoch": 1.2962025316455696, "percentage": 43.27, "elapsed_time": "10:00:47", "remaining_time": "13:07:36"}
{"current_steps": 650, "total_steps": 1479, "loss": 0.4546, "learning_rate": 1e-05, "epoch": 1.3164556962025316, "percentage": 43.95, "elapsed_time": "10:10:03", "remaining_time": "12:58:03"}
{"current_steps": 660, "total_steps": 1479, "loss": 0.444, "learning_rate": 1e-05, "epoch": 1.3367088607594937, "percentage": 44.62, "elapsed_time": "10:19:17", "remaining_time": "12:48:29"}
{"current_steps": 670, "total_steps": 1479, "loss": 0.4589, "learning_rate": 1e-05, "epoch": 1.3569620253164558, "percentage": 45.3, "elapsed_time": "10:28:32", "remaining_time": "12:38:56"}
{"current_steps": 680, "total_steps": 1479, "loss": 0.4565, "learning_rate": 1e-05, "epoch": 1.3772151898734177, "percentage": 45.98, "elapsed_time": "10:37:47", "remaining_time": "12:29:23"}
{"current_steps": 690, "total_steps": 1479, "loss": 0.4556, "learning_rate": 1e-05, "epoch": 1.3974683544303796, "percentage": 46.65, "elapsed_time": "10:47:02", "remaining_time": "12:19:52"}
{"current_steps": 700, "total_steps": 1479, "loss": 0.4524, "learning_rate": 1e-05, "epoch": 1.4177215189873418, "percentage": 47.33, "elapsed_time": "10:56:17", "remaining_time": "12:10:21"}
{"current_steps": 710, "total_steps": 1479, "loss": 0.4591, "learning_rate": 1e-05, "epoch": 1.437974683544304, "percentage": 48.01, "elapsed_time": "11:05:33", "remaining_time": "12:00:51"}
{"current_steps": 720, "total_steps": 1479, "loss": 0.4602, "learning_rate": 1e-05, "epoch": 1.4582278481012658, "percentage": 48.68, "elapsed_time": "11:14:49", "remaining_time": "11:51:22"}
{"current_steps": 730, "total_steps": 1479, "loss": 0.4638, "learning_rate": 1e-05, "epoch": 1.4784810126582277, "percentage": 49.36, "elapsed_time": "11:24:04", "remaining_time": "11:41:52"}
{"current_steps": 740, "total_steps": 1479, "loss": 0.4553, "learning_rate": 1e-05, "epoch": 1.4987341772151899, "percentage": 50.03, "elapsed_time": "11:33:18", "remaining_time": "11:32:22"}
{"current_steps": 750, "total_steps": 1479, "loss": 0.458, "learning_rate": 1e-05, "epoch": 1.518987341772152, "percentage": 50.71, "elapsed_time": "11:42:33", "remaining_time": "11:22:53"}
{"current_steps": 760, "total_steps": 1479, "loss": 0.4591, "learning_rate": 1e-05, "epoch": 1.539240506329114, "percentage": 51.39, "elapsed_time": "11:51:48", "remaining_time": "11:13:24"}
{"current_steps": 770, "total_steps": 1479, "loss": 0.4589, "learning_rate": 1e-05, "epoch": 1.5594936708860758, "percentage": 52.06, "elapsed_time": "12:01:04", "remaining_time": "11:03:57"}
{"current_steps": 780, "total_steps": 1479, "loss": 0.4596, "learning_rate": 1e-05, "epoch": 1.579746835443038, "percentage": 52.74, "elapsed_time": "12:10:19", "remaining_time": "10:54:29"}
{"current_steps": 790, "total_steps": 1479, "loss": 0.4613, "learning_rate": 1e-05, "epoch": 1.6, "percentage": 53.41, "elapsed_time": "12:19:34", "remaining_time": "10:45:01"}
{"current_steps": 800, "total_steps": 1479, "loss": 0.458, "learning_rate": 1e-05, "epoch": 1.620253164556962, "percentage": 54.09, "elapsed_time": "12:28:50", "remaining_time": "10:35:34"}
{"current_steps": 810, "total_steps": 1479, "loss": 0.4518, "learning_rate": 1e-05, "epoch": 1.640506329113924, "percentage": 54.77, "elapsed_time": "12:38:06", "remaining_time": "10:26:08"}
{"current_steps": 820, "total_steps": 1479, "loss": 0.4609, "learning_rate": 1e-05, "epoch": 1.660759493670886, "percentage": 55.44, "elapsed_time": "12:47:21", "remaining_time": "10:16:41"}
{"current_steps": 830, "total_steps": 1479, "loss": 0.4572, "learning_rate": 1e-05, "epoch": 1.6810126582278482, "percentage": 56.12, "elapsed_time": "12:56:37", "remaining_time": "10:07:15"}
{"current_steps": 840, "total_steps": 1479, "loss": 0.4592, "learning_rate": 1e-05, "epoch": 1.70126582278481, "percentage": 56.8, "elapsed_time": "13:05:52", "remaining_time": "9:57:49"}
{"current_steps": 850, "total_steps": 1479, "loss": 0.4614, "learning_rate": 1e-05, "epoch": 1.721518987341772, "percentage": 57.47, "elapsed_time": "13:15:08", "remaining_time": "9:48:24"}
{"current_steps": 860, "total_steps": 1479, "loss": 0.462, "learning_rate": 1e-05, "epoch": 1.7417721518987341, "percentage": 58.15, "elapsed_time": "13:24:23", "remaining_time": "9:38:58"}
{"current_steps": 870, "total_steps": 1479, "loss": 0.4656, "learning_rate": 1e-05, "epoch": 1.7620253164556963, "percentage": 58.82, "elapsed_time": "13:33:39", "remaining_time": "9:29:33"}
{"current_steps": 880, "total_steps": 1479, "loss": 0.4669, "learning_rate": 1e-05, "epoch": 1.7822784810126582, "percentage": 59.5, "elapsed_time": "13:42:54", "remaining_time": "9:20:07"}
{"current_steps": 890, "total_steps": 1479, "loss": 0.4643, "learning_rate": 1e-05, "epoch": 1.80253164556962, "percentage": 60.18, "elapsed_time": "13:52:08", "remaining_time": "9:10:42"}
{"current_steps": 900, "total_steps": 1479, "loss": 0.4634, "learning_rate": 1e-05, "epoch": 1.8227848101265822, "percentage": 60.85, "elapsed_time": "14:01:23", "remaining_time": "9:01:17"}
{"current_steps": 910, "total_steps": 1479, "loss": 0.4653, "learning_rate": 1e-05, "epoch": 1.8430379746835444, "percentage": 61.53, "elapsed_time": "14:10:37", "remaining_time": "8:51:52"}
{"current_steps": 920, "total_steps": 1479, "loss": 0.4642, "learning_rate": 1e-05, "epoch": 1.8632911392405065, "percentage": 62.2, "elapsed_time": "14:19:52", "remaining_time": "8:42:28"}
{"current_steps": 930, "total_steps": 1479, "loss": 0.4617, "learning_rate": 1e-05, "epoch": 1.8835443037974684, "percentage": 62.88, "elapsed_time": "14:29:07", "remaining_time": "8:33:03"}
{"current_steps": 940, "total_steps": 1479, "loss": 0.4645, "learning_rate": 1e-05, "epoch": 1.9037974683544303, "percentage": 63.56, "elapsed_time": "14:38:22", "remaining_time": "8:23:39"}
{"current_steps": 950, "total_steps": 1479, "loss": 0.4658, "learning_rate": 1e-05, "epoch": 1.9240506329113924, "percentage": 64.23, "elapsed_time": "14:47:36", "remaining_time": "8:14:15"}
{"current_steps": 960, "total_steps": 1479, "loss": 0.4695, "learning_rate": 1e-05, "epoch": 1.9443037974683546, "percentage": 64.91, "elapsed_time": "14:56:50", "remaining_time": "8:04:51"}
{"current_steps": 970, "total_steps": 1479, "loss": 0.4675, "learning_rate": 1e-05, "epoch": 1.9645569620253165, "percentage": 65.58, "elapsed_time": "15:06:04", "remaining_time": "7:55:27"}
{"current_steps": 980, "total_steps": 1479, "loss": 0.4685, "learning_rate": 1e-05, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:15:18", "remaining_time": "7:46:03"}
{"current_steps": 987, "total_steps": 1479, "eval_loss": 0.07146137207746506, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:30:33", "remaining_time": "7:43:51"}
{"current_steps": 990, "total_steps": 1479, "loss": 0.4323, "learning_rate": 1e-05, "epoch": 2.0050632911392405, "percentage": 66.94, "elapsed_time": "15:34:02", "remaining_time": "7:41:21"}
{"current_steps": 1000, "total_steps": 1479, "loss": 0.3341, "learning_rate": 1e-05, "epoch": 2.0253164556962027, "percentage": 67.61, "elapsed_time": "15:43:16", "remaining_time": "7:31:49"}
{"current_steps": 1010, "total_steps": 1479, "loss": 0.3244, "learning_rate": 1e-05, "epoch": 2.0455696202531644, "percentage": 68.29, "elapsed_time": "15:52:32", "remaining_time": "7:22:19"}
{"current_steps": 1020, "total_steps": 1479, "loss": 0.3184, "learning_rate": 1e-05, "epoch": 2.0658227848101265, "percentage": 68.97, "elapsed_time": "16:01:47", "remaining_time": "7:12:48"}
{"current_steps": 1030, "total_steps": 1479, "loss": 0.3194, "learning_rate": 1e-05, "epoch": 2.0860759493670886, "percentage": 69.64, "elapsed_time": "16:11:02", "remaining_time": "7:03:17"}
{"current_steps": 1040, "total_steps": 1479, "loss": 0.3174, "learning_rate": 1e-05, "epoch": 2.1063291139240508, "percentage": 70.32, "elapsed_time": "16:20:17", "remaining_time": "6:53:47"}
{"current_steps": 1050, "total_steps": 1479, "loss": 0.3271, "learning_rate": 1e-05, "epoch": 2.1265822784810124, "percentage": 70.99, "elapsed_time": "16:29:32", "remaining_time": "6:44:18"}
{"current_steps": 1060, "total_steps": 1479, "loss": 0.3226, "learning_rate": 1e-05, "epoch": 2.1468354430379746, "percentage": 71.67, "elapsed_time": "16:38:48", "remaining_time": "6:34:48"}
{"current_steps": 1070, "total_steps": 1479, "loss": 0.3272, "learning_rate": 1e-05, "epoch": 2.1670886075949367, "percentage": 72.35, "elapsed_time": "16:48:04", "remaining_time": "6:25:19"}
{"current_steps": 1080, "total_steps": 1479, "loss": 0.3254, "learning_rate": 1e-05, "epoch": 2.187341772151899, "percentage": 73.02, "elapsed_time": "16:57:20", "remaining_time": "6:15:51"}
{"current_steps": 1090, "total_steps": 1479, "loss": 0.3232, "learning_rate": 1e-05, "epoch": 2.207594936708861, "percentage": 73.7, "elapsed_time": "17:06:36", "remaining_time": "6:06:22"}
{"current_steps": 1100, "total_steps": 1479, "loss": 0.3303, "learning_rate": 1e-05, "epoch": 2.2278481012658227, "percentage": 74.37, "elapsed_time": "17:15:51", "remaining_time": "5:56:54"}
{"current_steps": 1110, "total_steps": 1479, "loss": 0.3268, "learning_rate": 1e-05, "epoch": 2.248101265822785, "percentage": 75.05, "elapsed_time": "17:25:07", "remaining_time": "5:47:25"}
{"current_steps": 1120, "total_steps": 1479, "loss": 0.3295, "learning_rate": 1e-05, "epoch": 2.268354430379747, "percentage": 75.73, "elapsed_time": "17:34:23", "remaining_time": "5:37:58"}
{"current_steps": 1130, "total_steps": 1479, "loss": 0.3314, "learning_rate": 1e-05, "epoch": 2.2886075949367086, "percentage": 76.4, "elapsed_time": "17:43:38", "remaining_time": "5:28:30"}
{"current_steps": 1140, "total_steps": 1479, "loss": 0.3281, "learning_rate": 1e-05, "epoch": 2.3088607594936708, "percentage": 77.08, "elapsed_time": "17:52:54", "remaining_time": "5:19:02"}
{"current_steps": 1150, "total_steps": 1479, "loss": 0.3331, "learning_rate": 1e-05, "epoch": 2.329113924050633, "percentage": 77.76, "elapsed_time": "18:02:09", "remaining_time": "5:09:35"}
{"current_steps": 1160, "total_steps": 1479, "loss": 0.3338, "learning_rate": 1e-05, "epoch": 2.349367088607595, "percentage": 78.43, "elapsed_time": "18:11:25", "remaining_time": "5:00:08"}
{"current_steps": 1170, "total_steps": 1479, "loss": 0.3345, "learning_rate": 1e-05, "epoch": 2.369620253164557, "percentage": 79.11, "elapsed_time": "18:20:39", "remaining_time": "4:50:41"}
{"current_steps": 1180, "total_steps": 1479, "loss": 0.3349, "learning_rate": 1e-05, "epoch": 2.389873417721519, "percentage": 79.78, "elapsed_time": "18:29:55", "remaining_time": "4:41:14"}
{"current_steps": 1190, "total_steps": 1479, "loss": 0.3358, "learning_rate": 1e-05, "epoch": 2.410126582278481, "percentage": 80.46, "elapsed_time": "18:39:11", "remaining_time": "4:31:48"}
{"current_steps": 1200, "total_steps": 1479, "loss": 0.3343, "learning_rate": 1e-05, "epoch": 2.430379746835443, "percentage": 81.14, "elapsed_time": "18:48:28", "remaining_time": "4:22:22"}
{"current_steps": 1210, "total_steps": 1479, "loss": 0.3346, "learning_rate": 1e-05, "epoch": 2.4506329113924052, "percentage": 81.81, "elapsed_time": "18:57:44", "remaining_time": "4:12:56"}
{"current_steps": 1220, "total_steps": 1479, "loss": 0.339, "learning_rate": 1e-05, "epoch": 2.470886075949367, "percentage": 82.49, "elapsed_time": "19:06:59", "remaining_time": "4:03:30"}
{"current_steps": 1230, "total_steps": 1479, "loss": 0.3403, "learning_rate": 1e-05, "epoch": 2.491139240506329, "percentage": 83.16, "elapsed_time": "19:16:14", "remaining_time": "3:54:04"}
{"current_steps": 1240, "total_steps": 1479, "loss": 0.344, "learning_rate": 1e-05, "epoch": 2.511392405063291, "percentage": 83.84, "elapsed_time": "19:25:30", "remaining_time": "3:44:38"}
{"current_steps": 1250, "total_steps": 1479, "loss": 0.3385, "learning_rate": 1e-05, "epoch": 2.5316455696202533, "percentage": 84.52, "elapsed_time": "19:34:44", "remaining_time": "3:35:12"}
{"current_steps": 1260, "total_steps": 1479, "loss": 0.3362, "learning_rate": 1e-05, "epoch": 2.5518987341772155, "percentage": 85.19, "elapsed_time": "19:44:00", "remaining_time": "3:25:47"}
{"current_steps": 1270, "total_steps": 1479, "loss": 0.3422, "learning_rate": 1e-05, "epoch": 2.572151898734177, "percentage": 85.87, "elapsed_time": "19:53:16", "remaining_time": "3:16:22"}
{"current_steps": 1280, "total_steps": 1479, "loss": 0.3434, "learning_rate": 1e-05, "epoch": 2.5924050632911393, "percentage": 86.54, "elapsed_time": "20:02:32", "remaining_time": "3:06:57"}
{"current_steps": 1290, "total_steps": 1479, "loss": 0.3491, "learning_rate": 1e-05, "epoch": 2.6126582278481014, "percentage": 87.22, "elapsed_time": "20:11:47", "remaining_time": "2:57:32"}
{"current_steps": 1300, "total_steps": 1479, "loss": 0.3441, "learning_rate": 1e-05, "epoch": 2.632911392405063, "percentage": 87.9, "elapsed_time": "20:21:03", "remaining_time": "2:48:07"}
{"current_steps": 1310, "total_steps": 1479, "loss": 0.3449, "learning_rate": 1e-05, "epoch": 2.6531645569620252, "percentage": 88.57, "elapsed_time": "20:30:19", "remaining_time": "2:38:43"}
{"current_steps": 1320, "total_steps": 1479, "loss": 0.3478, "learning_rate": 1e-05, "epoch": 2.6734177215189874, "percentage": 89.25, "elapsed_time": "20:39:37", "remaining_time": "2:29:19"}
{"current_steps": 1330, "total_steps": 1479, "loss": 0.3492, "learning_rate": 1e-05, "epoch": 2.6936708860759495, "percentage": 89.93, "elapsed_time": "20:48:52", "remaining_time": "2:19:54"}
{"current_steps": 1340, "total_steps": 1479, "loss": 0.349, "learning_rate": 1e-05, "epoch": 2.7139240506329116, "percentage": 90.6, "elapsed_time": "20:58:08", "remaining_time": "2:10:30"}
{"current_steps": 1350, "total_steps": 1479, "loss": 0.3494, "learning_rate": 1e-05, "epoch": 2.7341772151898733, "percentage": 91.28, "elapsed_time": "21:07:24", "remaining_time": "2:01:06"}
{"current_steps": 1360, "total_steps": 1479, "loss": 0.3455, "learning_rate": 1e-05, "epoch": 2.7544303797468355, "percentage": 91.95, "elapsed_time": "21:16:40", "remaining_time": "1:51:42"}
{"current_steps": 1370, "total_steps": 1479, "loss": 0.3513, "learning_rate": 1e-05, "epoch": 2.7746835443037976, "percentage": 92.63, "elapsed_time": "21:25:56", "remaining_time": "1:42:18"}
{"current_steps": 1380, "total_steps": 1479, "loss": 0.349, "learning_rate": 1e-05, "epoch": 2.7949367088607593, "percentage": 93.31, "elapsed_time": "21:35:12", "remaining_time": "1:32:55"}
{"current_steps": 1390, "total_steps": 1479, "loss": 0.3518, "learning_rate": 1e-05, "epoch": 2.8151898734177214, "percentage": 93.98, "elapsed_time": "21:44:28", "remaining_time": "1:23:31"}
{"current_steps": 1400, "total_steps": 1479, "loss": 0.3463, "learning_rate": 1e-05, "epoch": 2.8354430379746836, "percentage": 94.66, "elapsed_time": "21:53:44", "remaining_time": "1:14:07"}
{"current_steps": 1410, "total_steps": 1479, "loss": 0.3542, "learning_rate": 1e-05, "epoch": 2.8556962025316457, "percentage": 95.33, "elapsed_time": "22:03:00", "remaining_time": "1:04:44"}
{"current_steps": 1420, "total_steps": 1479, "loss": 0.3516, "learning_rate": 1e-05, "epoch": 2.875949367088608, "percentage": 96.01, "elapsed_time": "22:12:15", "remaining_time": "0:55:21"}
{"current_steps": 1430, "total_steps": 1479, "loss": 0.3518, "learning_rate": 1e-05, "epoch": 2.8962025316455695, "percentage": 96.69, "elapsed_time": "22:21:32", "remaining_time": "0:45:58"}
{"current_steps": 1440, "total_steps": 1479, "loss": 0.3535, "learning_rate": 1e-05, "epoch": 2.9164556962025316, "percentage": 97.36, "elapsed_time": "22:30:47", "remaining_time": "0:36:35"}
{"current_steps": 1450, "total_steps": 1479, "loss": 0.3621, "learning_rate": 1e-05, "epoch": 2.9367088607594938, "percentage": 98.04, "elapsed_time": "22:40:03", "remaining_time": "0:27:12"}
{"current_steps": 1460, "total_steps": 1479, "loss": 0.3521, "learning_rate": 1e-05, "epoch": 2.9569620253164555, "percentage": 98.72, "elapsed_time": "22:49:20", "remaining_time": "0:17:49"}
{"current_steps": 1470, "total_steps": 1479, "loss": 0.356, "learning_rate": 1e-05, "epoch": 2.9772151898734176, "percentage": 99.39, "elapsed_time": "22:58:35", "remaining_time": "0:08:26"}
{"current_steps": 1479, "total_steps": 1479, "eval_loss": 0.07828417420387268, "epoch": 2.9954430379746837, "percentage": 100.0, "elapsed_time": "23:16:29", "remaining_time": "0:00:00"}
{"current_steps": 1479, "total_steps": 1479, "epoch": 2.9954430379746837, "percentage": 100.0, "elapsed_time": "23:17:49", "remaining_time": "0:00:00"}