oh_v1.3_airoboros_x4 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
30e55ad verified
{"current_steps": 10, "total_steps": 864, "loss": 1.0247, "lr": 5e-06, "epoch": 0.03466204506065858, "percentage": 1.16, "elapsed_time": "0:09:40", "remaining_time": "13:46:21"}
{"current_steps": 20, "total_steps": 864, "loss": 0.9061, "lr": 5e-06, "epoch": 0.06932409012131716, "percentage": 2.31, "elapsed_time": "0:19:16", "remaining_time": "13:33:43"}
{"current_steps": 30, "total_steps": 864, "loss": 0.8729, "lr": 5e-06, "epoch": 0.10398613518197573, "percentage": 3.47, "elapsed_time": "0:28:52", "remaining_time": "13:22:51"}
{"current_steps": 40, "total_steps": 864, "loss": 0.8422, "lr": 5e-06, "epoch": 0.1386481802426343, "percentage": 4.63, "elapsed_time": "0:38:29", "remaining_time": "13:12:49"}
{"current_steps": 50, "total_steps": 864, "loss": 0.8226, "lr": 5e-06, "epoch": 0.1733102253032929, "percentage": 5.79, "elapsed_time": "0:48:05", "remaining_time": "13:02:48"}
{"current_steps": 60, "total_steps": 864, "loss": 0.8035, "lr": 5e-06, "epoch": 0.20797227036395147, "percentage": 6.94, "elapsed_time": "0:57:40", "remaining_time": "12:52:50"}
{"current_steps": 70, "total_steps": 864, "loss": 0.7971, "lr": 5e-06, "epoch": 0.24263431542461006, "percentage": 8.1, "elapsed_time": "1:07:15", "remaining_time": "12:42:55"}
{"current_steps": 80, "total_steps": 864, "loss": 0.7891, "lr": 5e-06, "epoch": 0.2772963604852686, "percentage": 9.26, "elapsed_time": "1:16:50", "remaining_time": "12:33:07"}
{"current_steps": 90, "total_steps": 864, "loss": 0.7823, "lr": 5e-06, "epoch": 0.3119584055459272, "percentage": 10.42, "elapsed_time": "1:26:26", "remaining_time": "12:23:22"}
{"current_steps": 100, "total_steps": 864, "loss": 0.7697, "lr": 5e-06, "epoch": 0.3466204506065858, "percentage": 11.57, "elapsed_time": "1:36:02", "remaining_time": "12:13:46"}
{"current_steps": 110, "total_steps": 864, "loss": 0.7641, "lr": 5e-06, "epoch": 0.38128249566724437, "percentage": 12.73, "elapsed_time": "1:45:38", "remaining_time": "12:04:06"}
{"current_steps": 120, "total_steps": 864, "loss": 0.7695, "lr": 5e-06, "epoch": 0.41594454072790293, "percentage": 13.89, "elapsed_time": "1:55:14", "remaining_time": "11:54:29"}
{"current_steps": 130, "total_steps": 864, "loss": 0.7702, "lr": 5e-06, "epoch": 0.4506065857885615, "percentage": 15.05, "elapsed_time": "2:04:49", "remaining_time": "11:44:47"}
{"current_steps": 140, "total_steps": 864, "loss": 0.7635, "lr": 5e-06, "epoch": 0.4852686308492201, "percentage": 16.2, "elapsed_time": "2:14:25", "remaining_time": "11:35:09"}
{"current_steps": 150, "total_steps": 864, "loss": 0.7577, "lr": 5e-06, "epoch": 0.5199306759098787, "percentage": 17.36, "elapsed_time": "2:24:01", "remaining_time": "11:25:31"}
{"current_steps": 160, "total_steps": 864, "loss": 0.7597, "lr": 5e-06, "epoch": 0.5545927209705372, "percentage": 18.52, "elapsed_time": "2:33:36", "remaining_time": "11:15:52"}
{"current_steps": 170, "total_steps": 864, "loss": 0.752, "lr": 5e-06, "epoch": 0.5892547660311959, "percentage": 19.68, "elapsed_time": "2:43:11", "remaining_time": "11:06:12"}
{"current_steps": 180, "total_steps": 864, "loss": 0.7527, "lr": 5e-06, "epoch": 0.6239168110918544, "percentage": 20.83, "elapsed_time": "2:52:47", "remaining_time": "10:56:36"}
{"current_steps": 190, "total_steps": 864, "loss": 0.7491, "lr": 5e-06, "epoch": 0.658578856152513, "percentage": 21.99, "elapsed_time": "3:02:23", "remaining_time": "10:47:01"}
{"current_steps": 200, "total_steps": 864, "loss": 0.7471, "lr": 5e-06, "epoch": 0.6932409012131716, "percentage": 23.15, "elapsed_time": "3:11:59", "remaining_time": "10:37:24"}
{"current_steps": 210, "total_steps": 864, "loss": 0.7488, "lr": 5e-06, "epoch": 0.7279029462738301, "percentage": 24.31, "elapsed_time": "3:21:34", "remaining_time": "10:27:47"}
{"current_steps": 220, "total_steps": 864, "loss": 0.744, "lr": 5e-06, "epoch": 0.7625649913344887, "percentage": 25.46, "elapsed_time": "3:31:11", "remaining_time": "10:18:11"}
{"current_steps": 230, "total_steps": 864, "loss": 0.7438, "lr": 5e-06, "epoch": 0.7972270363951474, "percentage": 26.62, "elapsed_time": "3:40:46", "remaining_time": "10:08:34"}
{"current_steps": 240, "total_steps": 864, "loss": 0.7402, "lr": 5e-06, "epoch": 0.8318890814558059, "percentage": 27.78, "elapsed_time": "3:50:21", "remaining_time": "9:58:55"}
{"current_steps": 250, "total_steps": 864, "loss": 0.7449, "lr": 5e-06, "epoch": 0.8665511265164645, "percentage": 28.94, "elapsed_time": "3:59:57", "remaining_time": "9:49:19"}
{"current_steps": 260, "total_steps": 864, "loss": 0.7378, "lr": 5e-06, "epoch": 0.901213171577123, "percentage": 30.09, "elapsed_time": "4:09:32", "remaining_time": "9:39:42"}
{"current_steps": 270, "total_steps": 864, "loss": 0.7439, "lr": 5e-06, "epoch": 0.9358752166377816, "percentage": 31.25, "elapsed_time": "4:19:08", "remaining_time": "9:30:07"}
{"current_steps": 280, "total_steps": 864, "loss": 0.7382, "lr": 5e-06, "epoch": 0.9705372616984402, "percentage": 32.41, "elapsed_time": "4:28:44", "remaining_time": "9:20:30"}
{"current_steps": 288, "total_steps": 864, "eval_loss": 0.7344536185264587, "epoch": 0.9982668977469671, "percentage": 33.33, "elapsed_time": "4:41:54", "remaining_time": "9:23:49"}
{"current_steps": 290, "total_steps": 864, "loss": 0.779, "lr": 5e-06, "epoch": 1.005632582322357, "percentage": 33.56, "elapsed_time": "4:44:39", "remaining_time": "9:23:26"}
{"current_steps": 300, "total_steps": 864, "loss": 0.6889, "lr": 5e-06, "epoch": 1.0402946273830156, "percentage": 34.72, "elapsed_time": "4:54:15", "remaining_time": "9:13:12"}
{"current_steps": 310, "total_steps": 864, "loss": 0.687, "lr": 5e-06, "epoch": 1.074956672443674, "percentage": 35.88, "elapsed_time": "5:03:51", "remaining_time": "9:03:02"}
{"current_steps": 320, "total_steps": 864, "loss": 0.6872, "lr": 5e-06, "epoch": 1.1096187175043328, "percentage": 37.04, "elapsed_time": "5:13:27", "remaining_time": "8:52:53"}
{"current_steps": 330, "total_steps": 864, "loss": 0.6858, "lr": 5e-06, "epoch": 1.1442807625649913, "percentage": 38.19, "elapsed_time": "5:23:04", "remaining_time": "8:42:48"}
{"current_steps": 340, "total_steps": 864, "loss": 0.684, "lr": 5e-06, "epoch": 1.1789428076256498, "percentage": 39.35, "elapsed_time": "5:32:40", "remaining_time": "8:32:43"}
{"current_steps": 350, "total_steps": 864, "loss": 0.6855, "lr": 5e-06, "epoch": 1.2136048526863086, "percentage": 40.51, "elapsed_time": "5:42:16", "remaining_time": "8:22:39"}
{"current_steps": 360, "total_steps": 864, "loss": 0.686, "lr": 5e-06, "epoch": 1.248266897746967, "percentage": 41.67, "elapsed_time": "5:51:51", "remaining_time": "8:12:36"}
{"current_steps": 370, "total_steps": 864, "loss": 0.6819, "lr": 5e-06, "epoch": 1.2829289428076256, "percentage": 42.82, "elapsed_time": "6:01:27", "remaining_time": "8:02:35"}
{"current_steps": 380, "total_steps": 864, "loss": 0.6851, "lr": 5e-06, "epoch": 1.317590987868284, "percentage": 43.98, "elapsed_time": "6:11:04", "remaining_time": "7:52:37"}
{"current_steps": 390, "total_steps": 864, "loss": 0.6868, "lr": 5e-06, "epoch": 1.3522530329289428, "percentage": 45.14, "elapsed_time": "6:20:40", "remaining_time": "7:42:39"}
{"current_steps": 400, "total_steps": 864, "loss": 0.6834, "lr": 5e-06, "epoch": 1.3869150779896013, "percentage": 46.3, "elapsed_time": "6:30:16", "remaining_time": "7:32:43"}
{"current_steps": 410, "total_steps": 864, "loss": 0.6832, "lr": 5e-06, "epoch": 1.4215771230502598, "percentage": 47.45, "elapsed_time": "6:39:51", "remaining_time": "7:22:46"}
{"current_steps": 420, "total_steps": 864, "loss": 0.6842, "lr": 5e-06, "epoch": 1.4562391681109186, "percentage": 48.61, "elapsed_time": "6:49:27", "remaining_time": "7:12:51"}
{"current_steps": 430, "total_steps": 864, "loss": 0.6844, "lr": 5e-06, "epoch": 1.490901213171577, "percentage": 49.77, "elapsed_time": "6:59:03", "remaining_time": "7:02:57"}
{"current_steps": 440, "total_steps": 864, "loss": 0.6791, "lr": 5e-06, "epoch": 1.5255632582322356, "percentage": 50.93, "elapsed_time": "7:08:39", "remaining_time": "6:53:04"}
{"current_steps": 450, "total_steps": 864, "loss": 0.6817, "lr": 5e-06, "epoch": 1.5602253032928943, "percentage": 52.08, "elapsed_time": "7:18:14", "remaining_time": "6:43:11"}
{"current_steps": 460, "total_steps": 864, "loss": 0.684, "lr": 5e-06, "epoch": 1.5948873483535528, "percentage": 53.24, "elapsed_time": "7:27:51", "remaining_time": "6:33:20"}
{"current_steps": 470, "total_steps": 864, "loss": 0.681, "lr": 5e-06, "epoch": 1.6295493934142113, "percentage": 54.4, "elapsed_time": "7:37:26", "remaining_time": "6:23:28"}
{"current_steps": 480, "total_steps": 864, "loss": 0.6806, "lr": 5e-06, "epoch": 1.66421143847487, "percentage": 55.56, "elapsed_time": "7:47:02", "remaining_time": "6:13:38"}
{"current_steps": 490, "total_steps": 864, "loss": 0.6792, "lr": 5e-06, "epoch": 1.6988734835355286, "percentage": 56.71, "elapsed_time": "7:56:38", "remaining_time": "6:03:48"}
{"current_steps": 500, "total_steps": 864, "loss": 0.6789, "lr": 5e-06, "epoch": 1.733535528596187, "percentage": 57.87, "elapsed_time": "8:06:14", "remaining_time": "5:53:59"}
{"current_steps": 510, "total_steps": 864, "loss": 0.6822, "lr": 5e-06, "epoch": 1.7681975736568458, "percentage": 59.03, "elapsed_time": "8:15:49", "remaining_time": "5:44:09"}
{"current_steps": 520, "total_steps": 864, "loss": 0.6825, "lr": 5e-06, "epoch": 1.8028596187175043, "percentage": 60.19, "elapsed_time": "8:25:25", "remaining_time": "5:34:21"}
{"current_steps": 530, "total_steps": 864, "loss": 0.6769, "lr": 5e-06, "epoch": 1.8375216637781628, "percentage": 61.34, "elapsed_time": "8:35:02", "remaining_time": "5:24:34"}
{"current_steps": 540, "total_steps": 864, "loss": 0.6782, "lr": 5e-06, "epoch": 1.8721837088388216, "percentage": 62.5, "elapsed_time": "8:44:39", "remaining_time": "5:14:47"}
{"current_steps": 550, "total_steps": 864, "loss": 0.6846, "lr": 5e-06, "epoch": 1.90684575389948, "percentage": 63.66, "elapsed_time": "8:54:14", "remaining_time": "5:05:00"}
{"current_steps": 560, "total_steps": 864, "loss": 0.6787, "lr": 5e-06, "epoch": 1.9415077989601386, "percentage": 64.81, "elapsed_time": "9:03:50", "remaining_time": "4:55:13"}
{"current_steps": 570, "total_steps": 864, "loss": 0.6785, "lr": 5e-06, "epoch": 1.9761698440207973, "percentage": 65.97, "elapsed_time": "9:13:27", "remaining_time": "4:45:28"}
{"current_steps": 576, "total_steps": 864, "eval_loss": 0.7195846438407898, "epoch": 1.9969670710571923, "percentage": 66.67, "elapsed_time": "9:25:00", "remaining_time": "4:42:30"}
{"current_steps": 580, "total_steps": 864, "loss": 0.7064, "lr": 5e-06, "epoch": 2.011265164644714, "percentage": 67.13, "elapsed_time": "9:29:29", "remaining_time": "4:38:51"}
{"current_steps": 590, "total_steps": 864, "loss": 0.6269, "lr": 5e-06, "epoch": 2.0459272097053725, "percentage": 68.29, "elapsed_time": "9:39:06", "remaining_time": "4:28:56"}
{"current_steps": 600, "total_steps": 864, "loss": 0.6204, "lr": 5e-06, "epoch": 2.080589254766031, "percentage": 69.44, "elapsed_time": "9:48:42", "remaining_time": "4:19:01"}
{"current_steps": 610, "total_steps": 864, "loss": 0.6251, "lr": 5e-06, "epoch": 2.11525129982669, "percentage": 70.6, "elapsed_time": "9:58:18", "remaining_time": "4:09:07"}
{"current_steps": 620, "total_steps": 864, "loss": 0.6274, "lr": 5e-06, "epoch": 2.149913344887348, "percentage": 71.76, "elapsed_time": "10:07:53", "remaining_time": "3:59:14"}
{"current_steps": 630, "total_steps": 864, "loss": 0.6267, "lr": 5e-06, "epoch": 2.184575389948007, "percentage": 72.92, "elapsed_time": "10:17:29", "remaining_time": "3:49:21"}
{"current_steps": 640, "total_steps": 864, "loss": 0.6284, "lr": 5e-06, "epoch": 2.2192374350086657, "percentage": 74.07, "elapsed_time": "10:27:05", "remaining_time": "3:39:28"}
{"current_steps": 650, "total_steps": 864, "loss": 0.6334, "lr": 5e-06, "epoch": 2.253899480069324, "percentage": 75.23, "elapsed_time": "10:36:40", "remaining_time": "3:29:36"}
{"current_steps": 660, "total_steps": 864, "loss": 0.6292, "lr": 5e-06, "epoch": 2.2885615251299827, "percentage": 76.39, "elapsed_time": "10:46:17", "remaining_time": "3:19:45"}
{"current_steps": 670, "total_steps": 864, "loss": 0.6299, "lr": 5e-06, "epoch": 2.3232235701906414, "percentage": 77.55, "elapsed_time": "10:55:53", "remaining_time": "3:09:54"}
{"current_steps": 680, "total_steps": 864, "loss": 0.6342, "lr": 5e-06, "epoch": 2.3578856152512997, "percentage": 78.7, "elapsed_time": "11:05:29", "remaining_time": "3:00:04"}
{"current_steps": 690, "total_steps": 864, "loss": 0.6315, "lr": 5e-06, "epoch": 2.3925476603119584, "percentage": 79.86, "elapsed_time": "11:15:06", "remaining_time": "2:50:14"}
{"current_steps": 700, "total_steps": 864, "loss": 0.631, "lr": 5e-06, "epoch": 2.427209705372617, "percentage": 81.02, "elapsed_time": "11:24:43", "remaining_time": "2:40:25"}
{"current_steps": 710, "total_steps": 864, "loss": 0.6295, "lr": 5e-06, "epoch": 2.4618717504332754, "percentage": 82.18, "elapsed_time": "11:34:18", "remaining_time": "2:30:35"}
{"current_steps": 720, "total_steps": 864, "loss": 0.6315, "lr": 5e-06, "epoch": 2.496533795493934, "percentage": 83.33, "elapsed_time": "11:43:54", "remaining_time": "2:20:46"}
{"current_steps": 730, "total_steps": 864, "loss": 0.6362, "lr": 5e-06, "epoch": 2.5311958405545925, "percentage": 84.49, "elapsed_time": "11:53:29", "remaining_time": "2:10:58"}
{"current_steps": 740, "total_steps": 864, "loss": 0.6303, "lr": 5e-06, "epoch": 2.565857885615251, "percentage": 85.65, "elapsed_time": "12:03:04", "remaining_time": "2:01:09"}
{"current_steps": 750, "total_steps": 864, "loss": 0.6285, "lr": 5e-06, "epoch": 2.60051993067591, "percentage": 86.81, "elapsed_time": "12:12:39", "remaining_time": "1:51:21"}
{"current_steps": 760, "total_steps": 864, "loss": 0.6339, "lr": 5e-06, "epoch": 2.635181975736568, "percentage": 87.96, "elapsed_time": "12:22:15", "remaining_time": "1:41:34"}
{"current_steps": 770, "total_steps": 864, "loss": 0.6326, "lr": 5e-06, "epoch": 2.669844020797227, "percentage": 89.12, "elapsed_time": "12:31:52", "remaining_time": "1:31:47"}
{"current_steps": 780, "total_steps": 864, "loss": 0.6295, "lr": 5e-06, "epoch": 2.7045060658578857, "percentage": 90.28, "elapsed_time": "12:41:27", "remaining_time": "1:22:00"}
{"current_steps": 790, "total_steps": 864, "loss": 0.6253, "lr": 5e-06, "epoch": 2.739168110918544, "percentage": 91.44, "elapsed_time": "12:51:02", "remaining_time": "1:12:13"}
{"current_steps": 800, "total_steps": 864, "loss": 0.6328, "lr": 5e-06, "epoch": 2.7738301559792027, "percentage": 92.59, "elapsed_time": "13:00:38", "remaining_time": "1:02:27"}
{"current_steps": 810, "total_steps": 864, "loss": 0.6346, "lr": 5e-06, "epoch": 2.8084922010398614, "percentage": 93.75, "elapsed_time": "13:10:14", "remaining_time": "0:52:40"}
{"current_steps": 820, "total_steps": 864, "loss": 0.6331, "lr": 5e-06, "epoch": 2.8431542461005197, "percentage": 94.91, "elapsed_time": "13:19:50", "remaining_time": "0:42:55"}
{"current_steps": 830, "total_steps": 864, "loss": 0.6274, "lr": 5e-06, "epoch": 2.8778162911611784, "percentage": 96.06, "elapsed_time": "13:29:26", "remaining_time": "0:33:09"}
{"current_steps": 840, "total_steps": 864, "loss": 0.632, "lr": 5e-06, "epoch": 2.912478336221837, "percentage": 97.22, "elapsed_time": "13:39:02", "remaining_time": "0:23:24"}
{"current_steps": 850, "total_steps": 864, "loss": 0.6307, "lr": 5e-06, "epoch": 2.9471403812824954, "percentage": 98.38, "elapsed_time": "13:48:39", "remaining_time": "0:13:38"}
{"current_steps": 860, "total_steps": 864, "loss": 0.6293, "lr": 5e-06, "epoch": 2.981802426343154, "percentage": 99.54, "elapsed_time": "13:58:15", "remaining_time": "0:03:53"}
{"current_steps": 864, "total_steps": 864, "eval_loss": 0.720524787902832, "epoch": 2.995667244367418, "percentage": 100.0, "elapsed_time": "14:08:29", "remaining_time": "0:00:00"}
{"current_steps": 864, "total_steps": 864, "epoch": 2.995667244367418, "percentage": 100.0, "elapsed_time": "14:10:00", "remaining_time": "0:00:00"}