hp_ablations_qwen_lr1e-5 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
e0f9672 verified
{"current_steps": 10, "total_steps": 1314, "loss": 0.7412, "learning_rate": 1e-05, "epoch": 0.022792022792022793, "percentage": 0.76, "elapsed_time": "0:08:48", "remaining_time": "19:08:58"}
{"current_steps": 20, "total_steps": 1314, "loss": 0.6876, "learning_rate": 1e-05, "epoch": 0.045584045584045586, "percentage": 1.52, "elapsed_time": "0:17:32", "remaining_time": "18:55:02"}
{"current_steps": 30, "total_steps": 1314, "loss": 0.666, "learning_rate": 1e-05, "epoch": 0.06837606837606838, "percentage": 2.28, "elapsed_time": "0:26:15", "remaining_time": "18:44:02"}
{"current_steps": 40, "total_steps": 1314, "loss": 0.6638, "learning_rate": 1e-05, "epoch": 0.09116809116809117, "percentage": 3.04, "elapsed_time": "0:34:59", "remaining_time": "18:34:20"}
{"current_steps": 50, "total_steps": 1314, "loss": 0.6608, "learning_rate": 1e-05, "epoch": 0.11396011396011396, "percentage": 3.81, "elapsed_time": "0:43:42", "remaining_time": "18:24:55"}
{"current_steps": 60, "total_steps": 1314, "loss": 0.6445, "learning_rate": 1e-05, "epoch": 0.13675213675213677, "percentage": 4.57, "elapsed_time": "0:52:25", "remaining_time": "18:15:46"}
{"current_steps": 70, "total_steps": 1314, "loss": 0.6448, "learning_rate": 1e-05, "epoch": 0.15954415954415954, "percentage": 5.33, "elapsed_time": "1:01:09", "remaining_time": "18:06:47"}
{"current_steps": 80, "total_steps": 1314, "loss": 0.6497, "learning_rate": 1e-05, "epoch": 0.18233618233618235, "percentage": 6.09, "elapsed_time": "1:09:52", "remaining_time": "17:57:55"}
{"current_steps": 90, "total_steps": 1314, "loss": 0.6353, "learning_rate": 1e-05, "epoch": 0.20512820512820512, "percentage": 6.85, "elapsed_time": "1:18:36", "remaining_time": "17:49:05"}
{"current_steps": 100, "total_steps": 1314, "loss": 0.6368, "learning_rate": 1e-05, "epoch": 0.22792022792022792, "percentage": 7.61, "elapsed_time": "1:27:20", "remaining_time": "17:40:16"}
{"current_steps": 110, "total_steps": 1314, "loss": 0.6284, "learning_rate": 1e-05, "epoch": 0.25071225071225073, "percentage": 8.37, "elapsed_time": "1:36:04", "remaining_time": "17:31:33"}
{"current_steps": 120, "total_steps": 1314, "loss": 0.6366, "learning_rate": 1e-05, "epoch": 0.27350427350427353, "percentage": 9.13, "elapsed_time": "1:44:47", "remaining_time": "17:22:45"}
{"current_steps": 130, "total_steps": 1314, "loss": 0.6377, "learning_rate": 1e-05, "epoch": 0.2962962962962963, "percentage": 9.89, "elapsed_time": "1:53:31", "remaining_time": "17:13:57"}
{"current_steps": 140, "total_steps": 1314, "loss": 0.6398, "learning_rate": 1e-05, "epoch": 0.3190883190883191, "percentage": 10.65, "elapsed_time": "2:02:15", "remaining_time": "17:05:11"}
{"current_steps": 150, "total_steps": 1314, "loss": 0.6323, "learning_rate": 1e-05, "epoch": 0.3418803418803419, "percentage": 11.42, "elapsed_time": "2:10:59", "remaining_time": "16:56:31"}
{"current_steps": 160, "total_steps": 1314, "loss": 0.6376, "learning_rate": 1e-05, "epoch": 0.3646723646723647, "percentage": 12.18, "elapsed_time": "2:19:43", "remaining_time": "16:47:47"}
{"current_steps": 170, "total_steps": 1314, "loss": 0.6294, "learning_rate": 1e-05, "epoch": 0.38746438746438744, "percentage": 12.94, "elapsed_time": "2:28:27", "remaining_time": "16:39:00"}
{"current_steps": 180, "total_steps": 1314, "loss": 0.635, "learning_rate": 1e-05, "epoch": 0.41025641025641024, "percentage": 13.7, "elapsed_time": "2:37:10", "remaining_time": "16:30:13"}
{"current_steps": 190, "total_steps": 1314, "loss": 0.6276, "learning_rate": 1e-05, "epoch": 0.43304843304843305, "percentage": 14.46, "elapsed_time": "2:45:54", "remaining_time": "16:21:27"}
{"current_steps": 200, "total_steps": 1314, "loss": 0.6356, "learning_rate": 1e-05, "epoch": 0.45584045584045585, "percentage": 15.22, "elapsed_time": "2:54:37", "remaining_time": "16:12:41"}
{"current_steps": 210, "total_steps": 1314, "loss": 0.6319, "learning_rate": 1e-05, "epoch": 0.47863247863247865, "percentage": 15.98, "elapsed_time": "3:03:21", "remaining_time": "16:03:54"}
{"current_steps": 220, "total_steps": 1314, "loss": 0.6357, "learning_rate": 1e-05, "epoch": 0.5014245014245015, "percentage": 16.74, "elapsed_time": "3:12:04", "remaining_time": "15:55:07"}
{"current_steps": 230, "total_steps": 1314, "loss": 0.6314, "learning_rate": 1e-05, "epoch": 0.5242165242165242, "percentage": 17.5, "elapsed_time": "3:20:47", "remaining_time": "15:46:21"}
{"current_steps": 240, "total_steps": 1314, "loss": 0.6271, "learning_rate": 1e-05, "epoch": 0.5470085470085471, "percentage": 18.26, "elapsed_time": "3:29:30", "remaining_time": "15:37:32"}
{"current_steps": 250, "total_steps": 1314, "loss": 0.6321, "learning_rate": 1e-05, "epoch": 0.5698005698005698, "percentage": 19.03, "elapsed_time": "3:38:13", "remaining_time": "15:28:45"}
{"current_steps": 260, "total_steps": 1314, "loss": 0.6303, "learning_rate": 1e-05, "epoch": 0.5925925925925926, "percentage": 19.79, "elapsed_time": "3:46:56", "remaining_time": "15:19:59"}
{"current_steps": 270, "total_steps": 1314, "loss": 0.6274, "learning_rate": 1e-05, "epoch": 0.6153846153846154, "percentage": 20.55, "elapsed_time": "3:55:39", "remaining_time": "15:11:13"}
{"current_steps": 280, "total_steps": 1314, "loss": 0.6382, "learning_rate": 1e-05, "epoch": 0.6381766381766382, "percentage": 21.31, "elapsed_time": "4:04:22", "remaining_time": "15:02:25"}
{"current_steps": 290, "total_steps": 1314, "loss": 0.6269, "learning_rate": 1e-05, "epoch": 0.6609686609686609, "percentage": 22.07, "elapsed_time": "4:13:05", "remaining_time": "14:53:39"}
{"current_steps": 300, "total_steps": 1314, "loss": 0.6249, "learning_rate": 1e-05, "epoch": 0.6837606837606838, "percentage": 22.83, "elapsed_time": "4:21:48", "remaining_time": "14:44:53"}
{"current_steps": 310, "total_steps": 1314, "loss": 0.6248, "learning_rate": 1e-05, "epoch": 0.7065527065527065, "percentage": 23.59, "elapsed_time": "4:30:31", "remaining_time": "14:36:09"}
{"current_steps": 320, "total_steps": 1314, "loss": 0.6254, "learning_rate": 1e-05, "epoch": 0.7293447293447294, "percentage": 24.35, "elapsed_time": "4:39:14", "remaining_time": "14:27:24"}
{"current_steps": 330, "total_steps": 1314, "loss": 0.622, "learning_rate": 1e-05, "epoch": 0.7521367521367521, "percentage": 25.11, "elapsed_time": "4:47:57", "remaining_time": "14:18:39"}
{"current_steps": 340, "total_steps": 1314, "loss": 0.6277, "learning_rate": 1e-05, "epoch": 0.7749287749287749, "percentage": 25.88, "elapsed_time": "4:56:40", "remaining_time": "14:09:53"}
{"current_steps": 350, "total_steps": 1314, "loss": 0.6348, "learning_rate": 1e-05, "epoch": 0.7977207977207977, "percentage": 26.64, "elapsed_time": "5:05:23", "remaining_time": "14:01:08"}
{"current_steps": 360, "total_steps": 1314, "loss": 0.6267, "learning_rate": 1e-05, "epoch": 0.8205128205128205, "percentage": 27.4, "elapsed_time": "5:14:06", "remaining_time": "13:52:23"}
{"current_steps": 370, "total_steps": 1314, "loss": 0.6203, "learning_rate": 1e-05, "epoch": 0.8433048433048433, "percentage": 28.16, "elapsed_time": "5:22:49", "remaining_time": "13:43:37"}
{"current_steps": 380, "total_steps": 1314, "loss": 0.6326, "learning_rate": 1e-05, "epoch": 0.8660968660968661, "percentage": 28.92, "elapsed_time": "5:31:32", "remaining_time": "13:34:53"}
{"current_steps": 390, "total_steps": 1314, "loss": 0.6312, "learning_rate": 1e-05, "epoch": 0.8888888888888888, "percentage": 29.68, "elapsed_time": "5:40:15", "remaining_time": "13:26:09"}
{"current_steps": 400, "total_steps": 1314, "loss": 0.6343, "learning_rate": 1e-05, "epoch": 0.9116809116809117, "percentage": 30.44, "elapsed_time": "5:48:58", "remaining_time": "13:17:25"}
{"current_steps": 410, "total_steps": 1314, "loss": 0.6306, "learning_rate": 1e-05, "epoch": 0.9344729344729344, "percentage": 31.2, "elapsed_time": "5:57:42", "remaining_time": "13:08:41"}
{"current_steps": 420, "total_steps": 1314, "loss": 0.6176, "learning_rate": 1e-05, "epoch": 0.9572649572649573, "percentage": 31.96, "elapsed_time": "6:06:25", "remaining_time": "12:59:58"}
{"current_steps": 430, "total_steps": 1314, "loss": 0.6304, "learning_rate": 1e-05, "epoch": 0.98005698005698, "percentage": 32.72, "elapsed_time": "6:15:08", "remaining_time": "12:51:13"}
{"current_steps": 438, "total_steps": 1314, "eval_loss": 0.621112048625946, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:29:53", "remaining_time": "12:59:46"}
{"current_steps": 440, "total_steps": 1314, "loss": 0.6403, "learning_rate": 1e-05, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:32:17", "remaining_time": "12:59:14"}
{"current_steps": 450, "total_steps": 1314, "loss": 0.5777, "learning_rate": 1e-05, "epoch": 1.0262108262108263, "percentage": 34.25, "elapsed_time": "6:41:01", "remaining_time": "12:49:57"}
{"current_steps": 460, "total_steps": 1314, "loss": 0.5713, "learning_rate": 1e-05, "epoch": 1.049002849002849, "percentage": 35.01, "elapsed_time": "6:49:45", "remaining_time": "12:40:42"}
{"current_steps": 470, "total_steps": 1314, "loss": 0.5722, "learning_rate": 1e-05, "epoch": 1.0717948717948718, "percentage": 35.77, "elapsed_time": "6:58:28", "remaining_time": "12:31:28"}
{"current_steps": 480, "total_steps": 1314, "loss": 0.5799, "learning_rate": 1e-05, "epoch": 1.0945868945868946, "percentage": 36.53, "elapsed_time": "7:07:12", "remaining_time": "12:22:16"}
{"current_steps": 490, "total_steps": 1314, "loss": 0.5849, "learning_rate": 1e-05, "epoch": 1.1173789173789175, "percentage": 37.29, "elapsed_time": "7:15:55", "remaining_time": "12:13:04"}
{"current_steps": 500, "total_steps": 1314, "loss": 0.5755, "learning_rate": 1e-05, "epoch": 1.1401709401709401, "percentage": 38.05, "elapsed_time": "7:24:39", "remaining_time": "12:03:53"}
{"current_steps": 510, "total_steps": 1314, "loss": 0.5736, "learning_rate": 1e-05, "epoch": 1.162962962962963, "percentage": 38.81, "elapsed_time": "7:33:22", "remaining_time": "11:54:44"}
{"current_steps": 520, "total_steps": 1314, "loss": 0.5794, "learning_rate": 1e-05, "epoch": 1.1857549857549858, "percentage": 39.57, "elapsed_time": "7:42:06", "remaining_time": "11:45:36"}
{"current_steps": 530, "total_steps": 1314, "loss": 0.5731, "learning_rate": 1e-05, "epoch": 1.2085470085470085, "percentage": 40.33, "elapsed_time": "7:50:51", "remaining_time": "11:36:30"}
{"current_steps": 540, "total_steps": 1314, "loss": 0.5831, "learning_rate": 1e-05, "epoch": 1.2313390313390313, "percentage": 41.1, "elapsed_time": "7:59:36", "remaining_time": "11:27:25"}
{"current_steps": 550, "total_steps": 1314, "loss": 0.5798, "learning_rate": 1e-05, "epoch": 1.2541310541310542, "percentage": 41.86, "elapsed_time": "8:08:20", "remaining_time": "11:18:21"}
{"current_steps": 560, "total_steps": 1314, "loss": 0.5818, "learning_rate": 1e-05, "epoch": 1.2769230769230768, "percentage": 42.62, "elapsed_time": "8:17:04", "remaining_time": "11:09:17"}
{"current_steps": 570, "total_steps": 1314, "loss": 0.5762, "learning_rate": 1e-05, "epoch": 1.2997150997150997, "percentage": 43.38, "elapsed_time": "8:25:48", "remaining_time": "11:00:12"}
{"current_steps": 580, "total_steps": 1314, "loss": 0.5747, "learning_rate": 1e-05, "epoch": 1.3225071225071225, "percentage": 44.14, "elapsed_time": "8:34:32", "remaining_time": "10:51:09"}
{"current_steps": 590, "total_steps": 1314, "loss": 0.5744, "learning_rate": 1e-05, "epoch": 1.3452991452991454, "percentage": 44.9, "elapsed_time": "8:43:16", "remaining_time": "10:42:07"}
{"current_steps": 600, "total_steps": 1314, "loss": 0.5801, "learning_rate": 1e-05, "epoch": 1.368091168091168, "percentage": 45.66, "elapsed_time": "8:52:00", "remaining_time": "10:33:05"}
{"current_steps": 610, "total_steps": 1314, "loss": 0.5802, "learning_rate": 1e-05, "epoch": 1.390883190883191, "percentage": 46.42, "elapsed_time": "9:00:44", "remaining_time": "10:24:04"}
{"current_steps": 620, "total_steps": 1314, "loss": 0.5831, "learning_rate": 1e-05, "epoch": 1.4136752136752135, "percentage": 47.18, "elapsed_time": "9:09:28", "remaining_time": "10:15:03"}
{"current_steps": 630, "total_steps": 1314, "loss": 0.5813, "learning_rate": 1e-05, "epoch": 1.4364672364672364, "percentage": 47.95, "elapsed_time": "9:18:12", "remaining_time": "10:06:03"}
{"current_steps": 640, "total_steps": 1314, "loss": 0.5762, "learning_rate": 1e-05, "epoch": 1.4592592592592593, "percentage": 48.71, "elapsed_time": "9:26:56", "remaining_time": "9:57:03"}
{"current_steps": 650, "total_steps": 1314, "loss": 0.5744, "learning_rate": 1e-05, "epoch": 1.4820512820512821, "percentage": 49.47, "elapsed_time": "9:35:40", "remaining_time": "9:48:04"}
{"current_steps": 660, "total_steps": 1314, "loss": 0.5742, "learning_rate": 1e-05, "epoch": 1.504843304843305, "percentage": 50.23, "elapsed_time": "9:44:23", "remaining_time": "9:39:05"}
{"current_steps": 670, "total_steps": 1314, "loss": 0.5816, "learning_rate": 1e-05, "epoch": 1.5276353276353276, "percentage": 50.99, "elapsed_time": "9:53:07", "remaining_time": "9:30:06"}
{"current_steps": 680, "total_steps": 1314, "loss": 0.5707, "learning_rate": 1e-05, "epoch": 1.5504273504273505, "percentage": 51.75, "elapsed_time": "10:01:51", "remaining_time": "9:21:08"}
{"current_steps": 690, "total_steps": 1314, "loss": 0.5744, "learning_rate": 1e-05, "epoch": 1.573219373219373, "percentage": 52.51, "elapsed_time": "10:10:35", "remaining_time": "9:12:11"}
{"current_steps": 700, "total_steps": 1314, "loss": 0.59, "learning_rate": 1e-05, "epoch": 1.596011396011396, "percentage": 53.27, "elapsed_time": "10:19:19", "remaining_time": "9:03:14"}
{"current_steps": 710, "total_steps": 1314, "loss": 0.5774, "learning_rate": 1e-05, "epoch": 1.6188034188034188, "percentage": 54.03, "elapsed_time": "10:28:03", "remaining_time": "8:54:17"}
{"current_steps": 720, "total_steps": 1314, "loss": 0.5818, "learning_rate": 1e-05, "epoch": 1.6415954415954417, "percentage": 54.79, "elapsed_time": "10:36:48", "remaining_time": "8:45:21"}
{"current_steps": 730, "total_steps": 1314, "loss": 0.5752, "learning_rate": 1e-05, "epoch": 1.6643874643874645, "percentage": 55.56, "elapsed_time": "10:45:32", "remaining_time": "8:36:25"}
{"current_steps": 740, "total_steps": 1314, "loss": 0.5765, "learning_rate": 1e-05, "epoch": 1.6871794871794872, "percentage": 56.32, "elapsed_time": "10:54:16", "remaining_time": "8:27:30"}
{"current_steps": 750, "total_steps": 1314, "loss": 0.574, "learning_rate": 1e-05, "epoch": 1.7099715099715098, "percentage": 57.08, "elapsed_time": "11:03:00", "remaining_time": "8:18:35"}
{"current_steps": 760, "total_steps": 1314, "loss": 0.5776, "learning_rate": 1e-05, "epoch": 1.7327635327635327, "percentage": 57.84, "elapsed_time": "11:11:44", "remaining_time": "8:09:40"}
{"current_steps": 770, "total_steps": 1314, "loss": 0.5743, "learning_rate": 1e-05, "epoch": 1.7555555555555555, "percentage": 58.6, "elapsed_time": "11:20:28", "remaining_time": "8:00:45"}
{"current_steps": 780, "total_steps": 1314, "loss": 0.5816, "learning_rate": 1e-05, "epoch": 1.7783475783475784, "percentage": 59.36, "elapsed_time": "11:29:12", "remaining_time": "7:51:50"}
{"current_steps": 790, "total_steps": 1314, "loss": 0.5793, "learning_rate": 1e-05, "epoch": 1.8011396011396013, "percentage": 60.12, "elapsed_time": "11:37:56", "remaining_time": "7:42:56"}
{"current_steps": 800, "total_steps": 1314, "loss": 0.5666, "learning_rate": 1e-05, "epoch": 1.823931623931624, "percentage": 60.88, "elapsed_time": "11:46:40", "remaining_time": "7:34:02"}
{"current_steps": 810, "total_steps": 1314, "loss": 0.5742, "learning_rate": 1e-05, "epoch": 1.8467236467236468, "percentage": 61.64, "elapsed_time": "11:55:24", "remaining_time": "7:25:08"}
{"current_steps": 820, "total_steps": 1314, "loss": 0.5721, "learning_rate": 1e-05, "epoch": 1.8695156695156694, "percentage": 62.4, "elapsed_time": "12:04:08", "remaining_time": "7:16:14"}
{"current_steps": 830, "total_steps": 1314, "loss": 0.5758, "learning_rate": 1e-05, "epoch": 1.8923076923076922, "percentage": 63.17, "elapsed_time": "12:12:51", "remaining_time": "7:07:21"}
{"current_steps": 840, "total_steps": 1314, "loss": 0.5803, "learning_rate": 1e-05, "epoch": 1.915099715099715, "percentage": 63.93, "elapsed_time": "12:21:35", "remaining_time": "6:58:28"}
{"current_steps": 850, "total_steps": 1314, "loss": 0.5786, "learning_rate": 1e-05, "epoch": 1.937891737891738, "percentage": 64.69, "elapsed_time": "12:30:19", "remaining_time": "6:49:35"}
{"current_steps": 860, "total_steps": 1314, "loss": 0.5798, "learning_rate": 1e-05, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:39:03", "remaining_time": "6:40:42"}
{"current_steps": 870, "total_steps": 1314, "loss": 0.5774, "learning_rate": 1e-05, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:47:47", "remaining_time": "6:31:50"}
{"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6186357736587524, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:01:13", "remaining_time": "6:29:16"}
{"current_steps": 880, "total_steps": 1314, "loss": 0.5896, "learning_rate": 1e-05, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:04:59", "remaining_time": "6:27:08"}
{"current_steps": 890, "total_steps": 1314, "loss": 0.5143, "learning_rate": 1e-05, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:13:44", "remaining_time": "6:18:08"}
{"current_steps": 900, "total_steps": 1314, "loss": 0.5277, "learning_rate": 1e-05, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:22:28", "remaining_time": "6:09:08"}
{"current_steps": 910, "total_steps": 1314, "loss": 0.5262, "learning_rate": 1e-05, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:31:12", "remaining_time": "6:00:08"}
{"current_steps": 920, "total_steps": 1314, "loss": 0.529, "learning_rate": 1e-05, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:39:56", "remaining_time": "5:51:09"}
{"current_steps": 930, "total_steps": 1314, "loss": 0.5279, "learning_rate": 1e-05, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:48:41", "remaining_time": "5:42:10"}
{"current_steps": 940, "total_steps": 1314, "loss": 0.523, "learning_rate": 1e-05, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "13:57:24", "remaining_time": "5:33:10"}
{"current_steps": 950, "total_steps": 1314, "loss": 0.5239, "learning_rate": 1e-05, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:06:08", "remaining_time": "5:24:12"}
{"current_steps": 960, "total_steps": 1314, "loss": 0.5291, "learning_rate": 1e-05, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:14:52", "remaining_time": "5:15:14"}
{"current_steps": 970, "total_steps": 1314, "loss": 0.529, "learning_rate": 1e-05, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:23:36", "remaining_time": "5:06:16"}
{"current_steps": 980, "total_steps": 1314, "loss": 0.5197, "learning_rate": 1e-05, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:32:20", "remaining_time": "4:57:18"}
{"current_steps": 990, "total_steps": 1314, "loss": 0.5287, "learning_rate": 1e-05, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:41:04", "remaining_time": "4:48:21"}
{"current_steps": 1000, "total_steps": 1314, "loss": 0.5293, "learning_rate": 1e-05, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:49:48", "remaining_time": "4:39:23"}
{"current_steps": 1010, "total_steps": 1314, "loss": 0.5269, "learning_rate": 1e-05, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "14:58:32", "remaining_time": "4:30:27"}
{"current_steps": 1020, "total_steps": 1314, "loss": 0.5298, "learning_rate": 1e-05, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:07:16", "remaining_time": "4:21:30"}
{"current_steps": 1030, "total_steps": 1314, "loss": 0.5311, "learning_rate": 1e-05, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:16:00", "remaining_time": "4:12:34"}
{"current_steps": 1040, "total_steps": 1314, "loss": 0.5299, "learning_rate": 1e-05, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:24:44", "remaining_time": "4:03:37"}
{"current_steps": 1050, "total_steps": 1314, "loss": 0.5292, "learning_rate": 1e-05, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:33:28", "remaining_time": "3:54:42"}
{"current_steps": 1060, "total_steps": 1314, "loss": 0.537, "learning_rate": 1e-05, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:42:11", "remaining_time": "3:45:46"}
{"current_steps": 1070, "total_steps": 1314, "loss": 0.5397, "learning_rate": 1e-05, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:50:55", "remaining_time": "3:36:50"}
{"current_steps": 1080, "total_steps": 1314, "loss": 0.5354, "learning_rate": 1e-05, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "15:59:39", "remaining_time": "3:27:55"}
{"current_steps": 1090, "total_steps": 1314, "loss": 0.5339, "learning_rate": 1e-05, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:08:24", "remaining_time": "3:19:00"}
{"current_steps": 1100, "total_steps": 1314, "loss": 0.5394, "learning_rate": 1e-05, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:17:08", "remaining_time": "3:10:05"}
{"current_steps": 1110, "total_steps": 1314, "loss": 0.5341, "learning_rate": 1e-05, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:25:52", "remaining_time": "3:01:11"}
{"current_steps": 1120, "total_steps": 1314, "loss": 0.5322, "learning_rate": 1e-05, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:34:36", "remaining_time": "2:52:16"}
{"current_steps": 1130, "total_steps": 1314, "loss": 0.5319, "learning_rate": 1e-05, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:43:21", "remaining_time": "2:43:22"}
{"current_steps": 1140, "total_steps": 1314, "loss": 0.5318, "learning_rate": 1e-05, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:52:06", "remaining_time": "2:34:28"}
{"current_steps": 1150, "total_steps": 1314, "loss": 0.5324, "learning_rate": 1e-05, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:00:50", "remaining_time": "2:25:34"}
{"current_steps": 1160, "total_steps": 1314, "loss": 0.5338, "learning_rate": 1e-05, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:09:34", "remaining_time": "2:16:41"}
{"current_steps": 1170, "total_steps": 1314, "loss": 0.5361, "learning_rate": 1e-05, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:18:18", "remaining_time": "2:07:47"}
{"current_steps": 1180, "total_steps": 1314, "loss": 0.5316, "learning_rate": 1e-05, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:27:03", "remaining_time": "1:58:54"}
{"current_steps": 1190, "total_steps": 1314, "loss": 0.5331, "learning_rate": 1e-05, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:35:48", "remaining_time": "1:50:00"}
{"current_steps": 1200, "total_steps": 1314, "loss": 0.5362, "learning_rate": 1e-05, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:44:32", "remaining_time": "1:41:07"}
{"current_steps": 1210, "total_steps": 1314, "loss": 0.5394, "learning_rate": 1e-05, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:53:16", "remaining_time": "1:32:14"}
{"current_steps": 1220, "total_steps": 1314, "loss": 0.5301, "learning_rate": 1e-05, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:02:00", "remaining_time": "1:23:22"}
{"current_steps": 1230, "total_steps": 1314, "loss": 0.5286, "learning_rate": 1e-05, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:10:45", "remaining_time": "1:14:29"}
{"current_steps": 1240, "total_steps": 1314, "loss": 0.5428, "learning_rate": 1e-05, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:19:29", "remaining_time": "1:05:36"}
{"current_steps": 1250, "total_steps": 1314, "loss": 0.5393, "learning_rate": 1e-05, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:28:14", "remaining_time": "0:56:44"}
{"current_steps": 1260, "total_steps": 1314, "loss": 0.5369, "learning_rate": 1e-05, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:36:58", "remaining_time": "0:47:52"}
{"current_steps": 1270, "total_steps": 1314, "loss": 0.5381, "learning_rate": 1e-05, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:45:42", "remaining_time": "0:39:00"}
{"current_steps": 1280, "total_steps": 1314, "loss": 0.5288, "learning_rate": 1e-05, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:54:27", "remaining_time": "0:30:08"}
{"current_steps": 1290, "total_steps": 1314, "loss": 0.5293, "learning_rate": 1e-05, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:03:10", "remaining_time": "0:21:16"}
{"current_steps": 1300, "total_steps": 1314, "loss": 0.5303, "learning_rate": 1e-05, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:11:54", "remaining_time": "0:12:24"}
{"current_steps": 1310, "total_steps": 1314, "loss": 0.5394, "learning_rate": 1e-05, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:20:38", "remaining_time": "0:03:32"}
{"current_steps": 1314, "total_steps": 1314, "eval_loss": 0.6266428232192993, "epoch": 2.996011396011396, "percentage": 100.0, "elapsed_time": "19:32:42", "remaining_time": "0:00:00"}
{"current_steps": 1314, "total_steps": 1314, "epoch": 2.996011396011396, "percentage": 100.0, "elapsed_time": "19:34:06", "remaining_time": "0:00:00"}