oh_v1.3_camel_math_x2 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
558f7bc verified
{"current_steps": 10, "total_steps": 870, "loss": 1.0121, "lr": 5e-06, "epoch": 0.03442340791738382, "percentage": 1.15, "elapsed_time": "0:09:41", "remaining_time": "13:53:10"}
{"current_steps": 20, "total_steps": 870, "loss": 0.8959, "lr": 5e-06, "epoch": 0.06884681583476764, "percentage": 2.3, "elapsed_time": "0:19:18", "remaining_time": "13:40:24"}
{"current_steps": 30, "total_steps": 870, "loss": 0.877, "lr": 5e-06, "epoch": 0.10327022375215146, "percentage": 3.45, "elapsed_time": "0:28:54", "remaining_time": "13:29:38"}
{"current_steps": 40, "total_steps": 870, "loss": 0.8454, "lr": 5e-06, "epoch": 0.13769363166953527, "percentage": 4.6, "elapsed_time": "0:38:31", "remaining_time": "13:19:24"}
{"current_steps": 50, "total_steps": 870, "loss": 0.8155, "lr": 5e-06, "epoch": 0.1721170395869191, "percentage": 5.75, "elapsed_time": "0:48:08", "remaining_time": "13:09:37"}
{"current_steps": 60, "total_steps": 870, "loss": 0.7988, "lr": 5e-06, "epoch": 0.20654044750430292, "percentage": 6.9, "elapsed_time": "0:57:46", "remaining_time": "12:59:51"}
{"current_steps": 70, "total_steps": 870, "loss": 0.7889, "lr": 5e-06, "epoch": 0.24096385542168675, "percentage": 8.05, "elapsed_time": "1:07:23", "remaining_time": "12:50:07"}
{"current_steps": 80, "total_steps": 870, "loss": 0.7806, "lr": 5e-06, "epoch": 0.27538726333907054, "percentage": 9.2, "elapsed_time": "1:16:59", "remaining_time": "12:40:17"}
{"current_steps": 90, "total_steps": 870, "loss": 0.7705, "lr": 5e-06, "epoch": 0.3098106712564544, "percentage": 10.34, "elapsed_time": "1:26:36", "remaining_time": "12:30:36"}
{"current_steps": 100, "total_steps": 870, "loss": 0.7613, "lr": 5e-06, "epoch": 0.3442340791738382, "percentage": 11.49, "elapsed_time": "1:36:12", "remaining_time": "12:20:51"}
{"current_steps": 110, "total_steps": 870, "loss": 0.761, "lr": 5e-06, "epoch": 0.37865748709122204, "percentage": 12.64, "elapsed_time": "1:45:50", "remaining_time": "12:11:14"}
{"current_steps": 120, "total_steps": 870, "loss": 0.7555, "lr": 5e-06, "epoch": 0.41308089500860584, "percentage": 13.79, "elapsed_time": "1:55:27", "remaining_time": "12:01:34"}
{"current_steps": 130, "total_steps": 870, "loss": 0.7507, "lr": 5e-06, "epoch": 0.4475043029259897, "percentage": 14.94, "elapsed_time": "2:05:04", "remaining_time": "11:51:56"}
{"current_steps": 140, "total_steps": 870, "loss": 0.7474, "lr": 5e-06, "epoch": 0.4819277108433735, "percentage": 16.09, "elapsed_time": "2:14:41", "remaining_time": "11:42:16"}
{"current_steps": 150, "total_steps": 870, "loss": 0.7452, "lr": 5e-06, "epoch": 0.5163511187607573, "percentage": 17.24, "elapsed_time": "2:24:17", "remaining_time": "11:32:36"}
{"current_steps": 160, "total_steps": 870, "loss": 0.7461, "lr": 5e-06, "epoch": 0.5507745266781411, "percentage": 18.39, "elapsed_time": "2:33:53", "remaining_time": "11:22:51"}
{"current_steps": 170, "total_steps": 870, "loss": 0.7467, "lr": 5e-06, "epoch": 0.5851979345955249, "percentage": 19.54, "elapsed_time": "2:43:28", "remaining_time": "11:13:09"}
{"current_steps": 180, "total_steps": 870, "loss": 0.7483, "lr": 5e-06, "epoch": 0.6196213425129088, "percentage": 20.69, "elapsed_time": "2:53:06", "remaining_time": "11:03:33"}
{"current_steps": 190, "total_steps": 870, "loss": 0.7424, "lr": 5e-06, "epoch": 0.6540447504302926, "percentage": 21.84, "elapsed_time": "3:02:42", "remaining_time": "10:53:55"}
{"current_steps": 200, "total_steps": 870, "loss": 0.7393, "lr": 5e-06, "epoch": 0.6884681583476764, "percentage": 22.99, "elapsed_time": "3:12:19", "remaining_time": "10:44:18"}
{"current_steps": 210, "total_steps": 870, "loss": 0.734, "lr": 5e-06, "epoch": 0.7228915662650602, "percentage": 24.14, "elapsed_time": "3:21:55", "remaining_time": "10:34:37"}
{"current_steps": 220, "total_steps": 870, "loss": 0.7344, "lr": 5e-06, "epoch": 0.7573149741824441, "percentage": 25.29, "elapsed_time": "3:31:30", "remaining_time": "10:24:55"}
{"current_steps": 230, "total_steps": 870, "loss": 0.7332, "lr": 5e-06, "epoch": 0.7917383820998278, "percentage": 26.44, "elapsed_time": "3:41:07", "remaining_time": "10:15:18"}
{"current_steps": 240, "total_steps": 870, "loss": 0.7323, "lr": 5e-06, "epoch": 0.8261617900172117, "percentage": 27.59, "elapsed_time": "3:50:44", "remaining_time": "10:05:41"}
{"current_steps": 250, "total_steps": 870, "loss": 0.7311, "lr": 5e-06, "epoch": 0.8605851979345955, "percentage": 28.74, "elapsed_time": "4:00:21", "remaining_time": "9:56:04"}
{"current_steps": 260, "total_steps": 870, "loss": 0.73, "lr": 5e-06, "epoch": 0.8950086058519794, "percentage": 29.89, "elapsed_time": "4:09:58", "remaining_time": "9:46:28"}
{"current_steps": 270, "total_steps": 870, "loss": 0.7274, "lr": 5e-06, "epoch": 0.9294320137693631, "percentage": 31.03, "elapsed_time": "4:19:35", "remaining_time": "9:36:52"}
{"current_steps": 280, "total_steps": 870, "loss": 0.7281, "lr": 5e-06, "epoch": 0.963855421686747, "percentage": 32.18, "elapsed_time": "4:29:13", "remaining_time": "9:27:17"}
{"current_steps": 290, "total_steps": 870, "loss": 0.73, "lr": 5e-06, "epoch": 0.9982788296041308, "percentage": 33.33, "elapsed_time": "4:38:49", "remaining_time": "9:17:38"}
{"current_steps": 290, "total_steps": 870, "eval_loss": 0.7240723967552185, "epoch": 0.9982788296041308, "percentage": 33.33, "elapsed_time": "4:44:28", "remaining_time": "9:28:57"}
{"current_steps": 300, "total_steps": 870, "loss": 0.7164, "lr": 5e-06, "epoch": 1.0327022375215147, "percentage": 34.48, "elapsed_time": "4:54:50", "remaining_time": "9:20:12"}
{"current_steps": 310, "total_steps": 870, "loss": 0.6796, "lr": 5e-06, "epoch": 1.0671256454388984, "percentage": 35.63, "elapsed_time": "5:04:29", "remaining_time": "9:10:02"}
{"current_steps": 320, "total_steps": 870, "loss": 0.6731, "lr": 5e-06, "epoch": 1.1015490533562822, "percentage": 36.78, "elapsed_time": "5:14:07", "remaining_time": "8:59:54"}
{"current_steps": 330, "total_steps": 870, "loss": 0.6804, "lr": 5e-06, "epoch": 1.1359724612736661, "percentage": 37.93, "elapsed_time": "5:23:46", "remaining_time": "8:49:49"}
{"current_steps": 340, "total_steps": 870, "loss": 0.676, "lr": 5e-06, "epoch": 1.1703958691910499, "percentage": 39.08, "elapsed_time": "5:33:25", "remaining_time": "8:39:44"}
{"current_steps": 350, "total_steps": 870, "loss": 0.6758, "lr": 5e-06, "epoch": 1.2048192771084336, "percentage": 40.23, "elapsed_time": "5:43:03", "remaining_time": "8:29:41"}
{"current_steps": 360, "total_steps": 870, "loss": 0.6812, "lr": 5e-06, "epoch": 1.2392426850258176, "percentage": 41.38, "elapsed_time": "5:52:42", "remaining_time": "8:19:40"}
{"current_steps": 370, "total_steps": 870, "loss": 0.6829, "lr": 5e-06, "epoch": 1.2736660929432013, "percentage": 42.53, "elapsed_time": "6:02:21", "remaining_time": "8:09:40"}
{"current_steps": 380, "total_steps": 870, "loss": 0.6787, "lr": 5e-06, "epoch": 1.3080895008605853, "percentage": 43.68, "elapsed_time": "6:11:59", "remaining_time": "7:59:40"}
{"current_steps": 390, "total_steps": 870, "loss": 0.6793, "lr": 5e-06, "epoch": 1.342512908777969, "percentage": 44.83, "elapsed_time": "6:21:37", "remaining_time": "7:49:41"}
{"current_steps": 400, "total_steps": 870, "loss": 0.6774, "lr": 5e-06, "epoch": 1.3769363166953528, "percentage": 45.98, "elapsed_time": "6:31:16", "remaining_time": "7:39:44"}
{"current_steps": 410, "total_steps": 870, "loss": 0.6812, "lr": 5e-06, "epoch": 1.4113597246127367, "percentage": 47.13, "elapsed_time": "6:40:53", "remaining_time": "7:29:46"}
{"current_steps": 420, "total_steps": 870, "loss": 0.6747, "lr": 5e-06, "epoch": 1.4457831325301205, "percentage": 48.28, "elapsed_time": "6:50:32", "remaining_time": "7:19:51"}
{"current_steps": 430, "total_steps": 870, "loss": 0.6764, "lr": 5e-06, "epoch": 1.4802065404475044, "percentage": 49.43, "elapsed_time": "7:00:11", "remaining_time": "7:09:57"}
{"current_steps": 440, "total_steps": 870, "loss": 0.6744, "lr": 5e-06, "epoch": 1.5146299483648882, "percentage": 50.57, "elapsed_time": "7:09:49", "remaining_time": "7:00:03"}
{"current_steps": 450, "total_steps": 870, "loss": 0.6728, "lr": 5e-06, "epoch": 1.549053356282272, "percentage": 51.72, "elapsed_time": "7:19:27", "remaining_time": "6:50:09"}
{"current_steps": 460, "total_steps": 870, "loss": 0.6761, "lr": 5e-06, "epoch": 1.5834767641996557, "percentage": 52.87, "elapsed_time": "7:29:05", "remaining_time": "6:40:16"}
{"current_steps": 470, "total_steps": 870, "loss": 0.6792, "lr": 5e-06, "epoch": 1.6179001721170396, "percentage": 54.02, "elapsed_time": "7:38:43", "remaining_time": "6:30:24"}
{"current_steps": 480, "total_steps": 870, "loss": 0.6768, "lr": 5e-06, "epoch": 1.6523235800344234, "percentage": 55.17, "elapsed_time": "7:48:22", "remaining_time": "6:20:33"}
{"current_steps": 490, "total_steps": 870, "loss": 0.677, "lr": 5e-06, "epoch": 1.6867469879518073, "percentage": 56.32, "elapsed_time": "7:58:00", "remaining_time": "6:10:41"}
{"current_steps": 500, "total_steps": 870, "loss": 0.6799, "lr": 5e-06, "epoch": 1.721170395869191, "percentage": 57.47, "elapsed_time": "8:07:38", "remaining_time": "6:00:51"}
{"current_steps": 510, "total_steps": 870, "loss": 0.6773, "lr": 5e-06, "epoch": 1.7555938037865748, "percentage": 58.62, "elapsed_time": "8:17:16", "remaining_time": "5:51:00"}
{"current_steps": 520, "total_steps": 870, "loss": 0.6761, "lr": 5e-06, "epoch": 1.7900172117039586, "percentage": 59.77, "elapsed_time": "8:26:54", "remaining_time": "5:41:11"}
{"current_steps": 530, "total_steps": 870, "loss": 0.6736, "lr": 5e-06, "epoch": 1.8244406196213425, "percentage": 60.92, "elapsed_time": "8:36:32", "remaining_time": "5:31:22"}
{"current_steps": 540, "total_steps": 870, "loss": 0.6724, "lr": 5e-06, "epoch": 1.8588640275387265, "percentage": 62.07, "elapsed_time": "8:46:11", "remaining_time": "5:21:33"}
{"current_steps": 550, "total_steps": 870, "loss": 0.6745, "lr": 5e-06, "epoch": 1.8932874354561102, "percentage": 63.22, "elapsed_time": "8:55:49", "remaining_time": "5:11:44"}
{"current_steps": 560, "total_steps": 870, "loss": 0.6744, "lr": 5e-06, "epoch": 1.927710843373494, "percentage": 64.37, "elapsed_time": "9:05:26", "remaining_time": "5:01:56"}
{"current_steps": 570, "total_steps": 870, "loss": 0.6755, "lr": 5e-06, "epoch": 1.9621342512908777, "percentage": 65.52, "elapsed_time": "9:15:04", "remaining_time": "4:52:08"}
{"current_steps": 580, "total_steps": 870, "loss": 0.6787, "lr": 5e-06, "epoch": 1.9965576592082617, "percentage": 66.67, "elapsed_time": "9:24:41", "remaining_time": "4:42:20"}
{"current_steps": 581, "total_steps": 870, "eval_loss": 0.7113586664199829, "epoch": 2.0, "percentage": 66.78, "elapsed_time": "9:30:46", "remaining_time": "4:43:54"}
{"current_steps": 590, "total_steps": 870, "loss": 0.6659, "lr": 5e-06, "epoch": 2.0309810671256456, "percentage": 67.82, "elapsed_time": "9:40:39", "remaining_time": "4:35:33"}
{"current_steps": 600, "total_steps": 870, "loss": 0.6232, "lr": 5e-06, "epoch": 2.0654044750430294, "percentage": 68.97, "elapsed_time": "9:50:15", "remaining_time": "4:25:37"}
{"current_steps": 610, "total_steps": 870, "loss": 0.6239, "lr": 5e-06, "epoch": 2.099827882960413, "percentage": 70.11, "elapsed_time": "9:59:52", "remaining_time": "4:15:41"}
{"current_steps": 620, "total_steps": 870, "loss": 0.6196, "lr": 5e-06, "epoch": 2.134251290877797, "percentage": 71.26, "elapsed_time": "10:09:29", "remaining_time": "4:05:45"}
{"current_steps": 630, "total_steps": 870, "loss": 0.6257, "lr": 5e-06, "epoch": 2.1686746987951806, "percentage": 72.41, "elapsed_time": "10:19:05", "remaining_time": "3:55:50"}
{"current_steps": 640, "total_steps": 870, "loss": 0.6232, "lr": 5e-06, "epoch": 2.2030981067125643, "percentage": 73.56, "elapsed_time": "10:28:40", "remaining_time": "3:45:55"}
{"current_steps": 650, "total_steps": 870, "loss": 0.6203, "lr": 5e-06, "epoch": 2.2375215146299485, "percentage": 74.71, "elapsed_time": "10:38:18", "remaining_time": "3:36:02"}
{"current_steps": 660, "total_steps": 870, "loss": 0.6254, "lr": 5e-06, "epoch": 2.2719449225473323, "percentage": 75.86, "elapsed_time": "10:47:55", "remaining_time": "3:26:09"}
{"current_steps": 670, "total_steps": 870, "loss": 0.6301, "lr": 5e-06, "epoch": 2.306368330464716, "percentage": 77.01, "elapsed_time": "10:57:32", "remaining_time": "3:16:16"}
{"current_steps": 680, "total_steps": 870, "loss": 0.6279, "lr": 5e-06, "epoch": 2.3407917383820998, "percentage": 78.16, "elapsed_time": "11:07:08", "remaining_time": "3:06:24"}
{"current_steps": 690, "total_steps": 870, "loss": 0.6287, "lr": 5e-06, "epoch": 2.3752151462994835, "percentage": 79.31, "elapsed_time": "11:16:45", "remaining_time": "2:56:32"}
{"current_steps": 700, "total_steps": 870, "loss": 0.6295, "lr": 5e-06, "epoch": 2.4096385542168672, "percentage": 80.46, "elapsed_time": "11:26:22", "remaining_time": "2:46:41"}
{"current_steps": 710, "total_steps": 870, "loss": 0.6277, "lr": 5e-06, "epoch": 2.4440619621342514, "percentage": 81.61, "elapsed_time": "11:35:58", "remaining_time": "2:36:50"}
{"current_steps": 720, "total_steps": 870, "loss": 0.6293, "lr": 5e-06, "epoch": 2.478485370051635, "percentage": 82.76, "elapsed_time": "11:45:35", "remaining_time": "2:26:59"}
{"current_steps": 730, "total_steps": 870, "loss": 0.6287, "lr": 5e-06, "epoch": 2.512908777969019, "percentage": 83.91, "elapsed_time": "11:55:11", "remaining_time": "2:17:09"}
{"current_steps": 740, "total_steps": 870, "loss": 0.6294, "lr": 5e-06, "epoch": 2.5473321858864026, "percentage": 85.06, "elapsed_time": "12:04:47", "remaining_time": "2:07:19"}
{"current_steps": 750, "total_steps": 870, "loss": 0.6232, "lr": 5e-06, "epoch": 2.581755593803787, "percentage": 86.21, "elapsed_time": "12:14:24", "remaining_time": "1:57:30"}
{"current_steps": 760, "total_steps": 870, "loss": 0.6291, "lr": 5e-06, "epoch": 2.6161790017211706, "percentage": 87.36, "elapsed_time": "12:24:01", "remaining_time": "1:47:41"}
{"current_steps": 770, "total_steps": 870, "loss": 0.6283, "lr": 5e-06, "epoch": 2.6506024096385543, "percentage": 88.51, "elapsed_time": "12:33:38", "remaining_time": "1:37:52"}
{"current_steps": 780, "total_steps": 870, "loss": 0.6305, "lr": 5e-06, "epoch": 2.685025817555938, "percentage": 89.66, "elapsed_time": "12:43:14", "remaining_time": "1:28:03"}
{"current_steps": 790, "total_steps": 870, "loss": 0.6255, "lr": 5e-06, "epoch": 2.719449225473322, "percentage": 90.8, "elapsed_time": "12:52:51", "remaining_time": "1:18:15"}
{"current_steps": 800, "total_steps": 870, "loss": 0.6314, "lr": 5e-06, "epoch": 2.7538726333907055, "percentage": 91.95, "elapsed_time": "13:02:28", "remaining_time": "1:08:27"}
{"current_steps": 810, "total_steps": 870, "loss": 0.6261, "lr": 5e-06, "epoch": 2.7882960413080893, "percentage": 93.1, "elapsed_time": "13:12:05", "remaining_time": "0:58:40"}
{"current_steps": 820, "total_steps": 870, "loss": 0.6266, "lr": 5e-06, "epoch": 2.8227194492254735, "percentage": 94.25, "elapsed_time": "13:21:43", "remaining_time": "0:48:53"}
{"current_steps": 830, "total_steps": 870, "loss": 0.6278, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.4, "elapsed_time": "13:31:19", "remaining_time": "0:39:06"}
{"current_steps": 840, "total_steps": 870, "loss": 0.6272, "lr": 5e-06, "epoch": 2.891566265060241, "percentage": 96.55, "elapsed_time": "13:40:57", "remaining_time": "0:29:19"}
{"current_steps": 850, "total_steps": 870, "loss": 0.6304, "lr": 5e-06, "epoch": 2.9259896729776247, "percentage": 97.7, "elapsed_time": "13:50:33", "remaining_time": "0:19:32"}
{"current_steps": 860, "total_steps": 870, "loss": 0.631, "lr": 5e-06, "epoch": 2.960413080895009, "percentage": 98.85, "elapsed_time": "14:00:11", "remaining_time": "0:09:46"}
{"current_steps": 870, "total_steps": 870, "loss": 0.6305, "lr": 5e-06, "epoch": 2.9948364888123926, "percentage": 100.0, "elapsed_time": "14:09:49", "remaining_time": "0:00:00"}
{"current_steps": 870, "total_steps": 870, "eval_loss": 0.7126539349555969, "epoch": 2.9948364888123926, "percentage": 100.0, "elapsed_time": "14:16:17", "remaining_time": "0:00:00"}
{"current_steps": 870, "total_steps": 870, "epoch": 2.9948364888123926, "percentage": 100.0, "elapsed_time": "14:17:44", "remaining_time": "0:00:00"}