Files
qwen3-14b-fft-if/trainer_log.jsonl

89 lines
17 KiB
Plaintext
Raw Normal View History

{"current_steps": 10, "total_steps": 874, "loss": 0.9488, "lr": 1.0227272727272729e-06, "epoch": 0.02288329519450801, "percentage": 1.14, "elapsed_time": "0:02:33", "remaining_time": "3:40:55"}
{"current_steps": 20, "total_steps": 874, "loss": 0.8935, "lr": 2.1590909090909092e-06, "epoch": 0.04576659038901602, "percentage": 2.29, "elapsed_time": "0:04:56", "remaining_time": "3:30:57"}
{"current_steps": 30, "total_steps": 874, "loss": 0.8345, "lr": 3.2954545454545456e-06, "epoch": 0.06864988558352403, "percentage": 3.43, "elapsed_time": "0:07:25", "remaining_time": "3:28:57"}
{"current_steps": 40, "total_steps": 874, "loss": 0.7483, "lr": 4.4318181818181824e-06, "epoch": 0.09153318077803203, "percentage": 4.58, "elapsed_time": "0:09:54", "remaining_time": "3:26:28"}
{"current_steps": 50, "total_steps": 874, "loss": 0.7619, "lr": 5.568181818181818e-06, "epoch": 0.11441647597254005, "percentage": 5.72, "elapsed_time": "0:12:18", "remaining_time": "3:22:54"}
{"current_steps": 60, "total_steps": 874, "loss": 0.7492, "lr": 6.704545454545454e-06, "epoch": 0.13729977116704806, "percentage": 6.86, "elapsed_time": "0:14:40", "remaining_time": "3:19:07"}
{"current_steps": 70, "total_steps": 874, "loss": 0.7519, "lr": 7.840909090909091e-06, "epoch": 0.16018306636155608, "percentage": 8.01, "elapsed_time": "0:17:03", "remaining_time": "3:15:54"}
{"current_steps": 80, "total_steps": 874, "loss": 0.7103, "lr": 8.977272727272727e-06, "epoch": 0.18306636155606407, "percentage": 9.15, "elapsed_time": "0:19:25", "remaining_time": "3:12:48"}
{"current_steps": 90, "total_steps": 874, "loss": 0.7069, "lr": 9.999960061285353e-06, "epoch": 0.20594965675057209, "percentage": 10.3, "elapsed_time": "0:21:47", "remaining_time": "3:09:51"}
{"current_steps": 100, "total_steps": 874, "loss": 0.7032, "lr": 9.995168187508393e-06, "epoch": 0.2288329519450801, "percentage": 11.44, "elapsed_time": "0:24:07", "remaining_time": "3:06:43"}
{"current_steps": 110, "total_steps": 874, "loss": 0.7216, "lr": 9.98239734155262e-06, "epoch": 0.2517162471395881, "percentage": 12.59, "elapsed_time": "0:26:35", "remaining_time": "3:04:38"}
{"current_steps": 120, "total_steps": 874, "loss": 0.7085, "lr": 9.961667922776125e-06, "epoch": 0.2745995423340961, "percentage": 13.73, "elapsed_time": "0:28:56", "remaining_time": "3:01:53"}
{"current_steps": 130, "total_steps": 874, "loss": 0.7104, "lr": 9.93301304306814e-06, "epoch": 0.2974828375286041, "percentage": 14.87, "elapsed_time": "0:31:23", "remaining_time": "2:59:39"}
{"current_steps": 140, "total_steps": 874, "loss": 0.6963, "lr": 9.896478473958147e-06, "epoch": 0.32036613272311215, "percentage": 16.02, "elapsed_time": "0:33:40", "remaining_time": "2:56:33"}
{"current_steps": 150, "total_steps": 874, "loss": 0.6751, "lr": 9.852122573503283e-06, "epoch": 0.34324942791762014, "percentage": 17.16, "elapsed_time": "0:36:05", "remaining_time": "2:54:11"}
{"current_steps": 160, "total_steps": 874, "loss": 0.6757, "lr": 9.800016193070789e-06, "epoch": 0.36613272311212813, "percentage": 18.31, "elapsed_time": "0:38:22", "remaining_time": "2:51:14"}
{"current_steps": 170, "total_steps": 874, "loss": 0.7119, "lr": 9.740242564164433e-06, "epoch": 0.3890160183066362, "percentage": 19.45, "elapsed_time": "0:40:40", "remaining_time": "2:48:27"}
{"current_steps": 180, "total_steps": 874, "loss": 0.6598, "lr": 9.672897165475657e-06, "epoch": 0.41189931350114417, "percentage": 20.59, "elapsed_time": "0:43:06", "remaining_time": "2:46:14"}
{"current_steps": 190, "total_steps": 874, "loss": 0.713, "lr": 9.59808757037183e-06, "epoch": 0.43478260869565216, "percentage": 21.74, "elapsed_time": "0:45:36", "remaining_time": "2:44:10"}
{"current_steps": 200, "total_steps": 874, "loss": 0.6708, "lr": 9.515933275065218e-06, "epoch": 0.4576659038901602, "percentage": 22.88, "elapsed_time": "0:47:48", "remaining_time": "2:41:06"}
{"current_steps": 210, "total_steps": 874, "loss": 0.6929, "lr": 9.426565507737139e-06, "epoch": 0.4805491990846682, "percentage": 24.03, "elapsed_time": "0:50:15", "remaining_time": "2:38:53"}
{"current_steps": 220, "total_steps": 874, "loss": 0.6417, "lr": 9.330127018922195e-06, "epoch": 0.5034324942791762, "percentage": 25.17, "elapsed_time": "0:52:39", "remaining_time": "2:36:31"}
{"current_steps": 230, "total_steps": 874, "loss": 0.6499, "lr": 9.226771853487411e-06, "epoch": 0.5263157894736842, "percentage": 26.32, "elapsed_time": "0:54:59", "remaining_time": "2:33:58"}
{"current_steps": 240, "total_steps": 874, "loss": 0.6627, "lr": 9.116665104570513e-06, "epoch": 0.5491990846681922, "percentage": 27.46, "elapsed_time": "0:57:25", "remaining_time": "2:31:42"}
{"current_steps": 250, "total_steps": 874, "loss": 0.6766, "lr": 8.999982649870377e-06, "epoch": 0.5720823798627003, "percentage": 28.6, "elapsed_time": "0:59:53", "remaining_time": "2:29:29"}
{"current_steps": 260, "total_steps": 874, "loss": 0.6843, "lr": 8.876910870710885e-06, "epoch": 0.5949656750572082, "percentage": 29.75, "elapsed_time": "1:02:22", "remaining_time": "2:27:17"}
{"current_steps": 270, "total_steps": 874, "loss": 0.6844, "lr": 8.747646354326948e-06, "epoch": 0.6178489702517163, "percentage": 30.89, "elapsed_time": "1:04:34", "remaining_time": "2:24:27"}
{"current_steps": 280, "total_steps": 874, "loss": 0.6511, "lr": 8.612395579848244e-06, "epoch": 0.6407322654462243, "percentage": 32.04, "elapsed_time": "1:07:01", "remaining_time": "2:22:11"}
{"current_steps": 290, "total_steps": 874, "loss": 0.6631, "lr": 8.47137458848224e-06, "epoch": 0.6636155606407322, "percentage": 33.18, "elapsed_time": "1:09:22", "remaining_time": "2:19:42"}
{"current_steps": 300, "total_steps": 874, "loss": 0.6871, "lr": 8.324808638423353e-06, "epoch": 0.6864988558352403, "percentage": 34.32, "elapsed_time": "1:11:45", "remaining_time": "2:17:18"}
{"current_steps": 310, "total_steps": 874, "loss": 0.6249, "lr": 8.172931845039471e-06, "epoch": 0.7093821510297483, "percentage": 35.47, "elapsed_time": "1:14:09", "remaining_time": "2:14:55"}
{"current_steps": 320, "total_steps": 874, "loss": 0.6492, "lr": 8.01598680691057e-06, "epoch": 0.7322654462242563, "percentage": 36.61, "elapsed_time": "1:16:34", "remaining_time": "2:12:33"}
{"current_steps": 330, "total_steps": 874, "loss": 0.6619, "lr": 7.854224218316761e-06, "epoch": 0.7551487414187643, "percentage": 37.76, "elapsed_time": "1:18:44", "remaining_time": "2:09:48"}
{"current_steps": 340, "total_steps": 874, "loss": 0.6729, "lr": 7.687902468794803e-06, "epoch": 0.7780320366132724, "percentage": 38.9, "elapsed_time": "1:21:19", "remaining_time": "2:07:43"}
{"current_steps": 350, "total_steps": 874, "loss": 0.631, "lr": 7.517287230402639e-06, "epoch": 0.8009153318077803, "percentage": 40.05, "elapsed_time": "1:23:32", "remaining_time": "2:05:03"}
{"current_steps": 360, "total_steps": 874, "loss": 0.6195, "lr": 7.342651033351325e-06, "epoch": 0.8237986270022883, "percentage": 41.19, "elapsed_time": "1:25:47", "remaining_time": "2:02:29"}
{"current_steps": 370, "total_steps": 874, "loss": 0.6352, "lr": 7.164272830682161e-06, "epoch": 0.8466819221967964, "percentage": 42.33, "elapsed_time": "1:28:08", "remaining_time": "2:00:04"}
{"current_steps": 380, "total_steps": 874, "loss": 0.6549, "lr": 6.9824375526843705e-06, "epoch": 0.8695652173913043, "percentage": 43.48, "elapsed_time": "1:30:35", "remaining_time": "1:57:45"}
{"current_steps": 390, "total_steps": 874, "loss": 0.6593, "lr": 6.797435651765123e-06, "epoch": 0.8924485125858124, "percentage": 44.62, "elapsed_time": "1:32:58", "remaining_time": "1:55:23"}
{"current_steps": 400, "total_steps": 874, "loss": 0.6141, "lr": 6.609562638498845e-06, "epoch": 0.9153318077803204, "percentage": 45.77, "elapsed_time": "1:35:36", "remaining_time": "1:53:17"}
{"current_steps": 410, "total_steps": 874, "loss": 0.6194, "lr": 6.419118609596948e-06, "epoch": 0.9382151029748284, "percentage": 46.91, "elapsed_time": "1:37:59", "remaining_time": "1:50:53"}
{"current_steps": 420, "total_steps": 874, "loss": 0.6406, "lr": 6.2264077685519246e-06, "epoch": 0.9610983981693364, "percentage": 48.05, "elapsed_time": "1:40:16", "remaining_time": "1:48:23"}
{"current_steps": 430, "total_steps": 874, "loss": 0.6515, "lr": 6.031737939721538e-06, "epoch": 0.9839816933638444, "percentage": 49.2, "elapsed_time": "1:42:43", "remaining_time": "1:46:03"}
{"current_steps": 440, "total_steps": 874, "loss": 0.6155, "lr": 5.835420076629273e-06, "epoch": 1.0068649885583525, "percentage": 50.34, "elapsed_time": "1:44:57", "remaining_time": "1:43:31"}
{"current_steps": 450, "total_steps": 874, "loss": 0.4827, "lr": 5.6377677652664345e-06, "epoch": 1.0297482837528604, "percentage": 51.49, "elapsed_time": "1:47:26", "remaining_time": "1:41:13"}
{"current_steps": 460, "total_steps": 874, "loss": 0.5285, "lr": 5.439096723189316e-06, "epoch": 1.0526315789473684, "percentage": 52.63, "elapsed_time": "1:49:58", "remaining_time": "1:38:58"}
{"current_steps": 470, "total_steps": 874, "loss": 0.4976, "lr": 5.239724295211541e-06, "epoch": 1.0755148741418765, "percentage": 53.78, "elapsed_time": "1:52:23", "remaining_time": "1:36:36"}
{"current_steps": 480, "total_steps": 874, "loss": 0.4919, "lr": 5.03996894649711e-06, "epoch": 1.0983981693363845, "percentage": 54.92, "elapsed_time": "1:54:50", "remaining_time": "1:34:16"}
{"current_steps": 490, "total_steps": 874, "loss": 0.4691, "lr": 4.840149753863887e-06, "epoch": 1.1212814645308924, "percentage": 56.06, "elapsed_time": "1:57:08", "remaining_time": "1:31:47"}
{"current_steps": 500, "total_steps": 874, "loss": 0.4929, "lr": 4.640585896110054e-06, "epoch": 1.1441647597254005, "percentage": 57.21, "elapsed_time": "1:59:42", "remaining_time": "1:29:32"}
{"current_steps": 510, "total_steps": 874, "loss": 0.4885, "lr": 4.441596144177681e-06, "epoch": 1.1670480549199085, "percentage": 58.35, "elapsed_time": "2:02:41", "remaining_time": "1:27:34"}
{"current_steps": 520, "total_steps": 874, "loss": 0.4682, "lr": 4.243498351967761e-06, "epoch": 1.1899313501144164, "percentage": 59.5, "elapsed_time": "2:05:04", "remaining_time": "1:25:08"}
{"current_steps": 530, "total_steps": 874, "loss": 0.4791, "lr": 4.046608948620098e-06, "epoch": 1.2128146453089246, "percentage": 60.64, "elapsed_time": "2:07:30", "remaining_time": "1:22:45"}
{"current_steps": 540, "total_steps": 874, "loss": 0.4732, "lr": 3.8512424330689855e-06, "epoch": 1.2356979405034325, "percentage": 61.78, "elapsed_time": "2:09:51", "remaining_time": "1:20:19"}
{"current_steps": 550, "total_steps": 874, "loss": 0.4849, "lr": 3.657710871682115e-06, "epoch": 1.2585812356979404, "percentage": 62.93, "elapsed_time": "2:12:12", "remaining_time": "1:17:53"}
{"current_steps": 560, "total_steps": 874, "loss": 0.4804, "lr": 3.466323399785072e-06, "epoch": 1.2814645308924484, "percentage": 64.07, "elapsed_time": "2:14:43", "remaining_time": "1:15:32"}
{"current_steps": 570, "total_steps": 874, "loss": 0.4926, "lr": 3.2773857278677414e-06, "epoch": 1.3043478260869565, "percentage": 65.22, "elapsed_time": "2:17:10", "remaining_time": "1:13:09"}
{"current_steps": 580, "total_steps": 874, "loss": 0.5041, "lr": 3.0911996532612966e-06, "epoch": 1.3272311212814645, "percentage": 66.36, "elapsed_time": "2:19:27", "remaining_time": "1:10:41"}
{"current_steps": 590, "total_steps": 874, "loss": 0.473, "lr": 2.9080625780658455e-06, "epoch": 1.3501144164759724, "percentage": 67.51, "elapsed_time": "2:21:48", "remaining_time": "1:08:15"}
{"current_steps": 600, "total_steps": 874, "loss": 0.4664, "lr": 2.7282670340987465e-06, "epoch": 1.3729977116704806, "percentage": 68.65, "elapsed_time": "2:24:27", "remaining_time": "1:05:57"}
{"current_steps": 610, "total_steps": 874, "loss": 0.4872, "lr": 2.552100215622401e-06, "epoch": 1.3958810068649885, "percentage": 69.79, "elapsed_time": "2:26:43", "remaining_time": "1:03:30"}
{"current_steps": 620, "total_steps": 874, "loss": 0.5043, "lr": 2.379843520597937e-06, "epoch": 1.4187643020594964, "percentage": 70.94, "elapsed_time": "2:29:15", "remaining_time": "1:01:09"}
{"current_steps": 630, "total_steps": 874, "loss": 0.5273, "lr": 2.2117721011975366e-06, "epoch": 1.4416475972540046, "percentage": 72.08, "elapsed_time": "2:31:34", "remaining_time": "0:58:42"}
{"current_steps": 640, "total_steps": 874, "loss": 0.4862, "lr": 2.0481544242934105e-06, "epoch": 1.4645308924485125, "percentage": 73.23, "elapsed_time": "2:33:53", "remaining_time": "0:56:15"}
{"current_steps": 650, "total_steps": 874, "loss": 0.4729, "lr": 1.8892518426254363e-06, "epoch": 1.4874141876430205, "percentage": 74.37, "elapsed_time": "2:36:17", "remaining_time": "0:53:51"}
{"current_steps": 660, "total_steps": 874, "loss": 0.5103, "lr": 1.735318177332503e-06, "epoch": 1.5102974828375286, "percentage": 75.51, "elapsed_time": "2:38:40", "remaining_time": "0:51:27"}
{"current_steps": 670, "total_steps": 874, "loss": 0.4903, "lr": 1.5865993125143297e-06, "epoch": 1.5331807780320366, "percentage": 76.66, "elapsed_time": "2:41:06", "remaining_time": "0:49:03"}
{"current_steps": 680, "total_steps": 874, "loss": 0.4755, "lr": 1.4433328024714583e-06, "epoch": 1.5560640732265445, "percentage": 77.8, "elapsed_time": "2:43:25", "remaining_time": "0:46:37"}
{"current_steps": 690, "total_steps": 874, "loss": 0.4482, "lr": 1.3057474922507124e-06, "epoch": 1.5789473684210527, "percentage": 78.95, "elapsed_time": "2:45:51", "remaining_time": "0:44:13"}
{"current_steps": 700, "total_steps": 874, "loss": 0.4944, "lr": 1.1740631521023176e-06, "epoch": 1.6018306636155606, "percentage": 80.09, "elapsed_time": "2:48:08", "remaining_time": "0:41:47"}
{"current_steps": 710, "total_steps": 874, "loss": 0.4975, "lr": 1.0484901264325026e-06, "epoch": 1.6247139588100685, "percentage": 81.24, "elapsed_time": "2:50:33", "remaining_time": "0:39:23"}
{"current_steps": 720, "total_steps": 874, "loss": 0.4457, "lr": 9.292289978123892e-07, "epoch": 1.6475972540045767, "percentage": 82.38, "elapsed_time": "2:52:50", "remaining_time": "0:36:58"}
{"current_steps": 730, "total_steps": 874, "loss": 0.4953, "lr": 8.16470266579813e-07, "epoch": 1.6704805491990846, "percentage": 83.52, "elapsed_time": "2:55:21", "remaining_time": "0:34:35"}
{"current_steps": 740, "total_steps": 874, "loss": 0.4719, "lr": 7.103940465458936e-07, "epoch": 1.6933638443935926, "percentage": 84.67, "elapsed_time": "2:57:47", "remaining_time": "0:32:11"}
{"current_steps": 750, "total_steps": 874, "loss": 0.4789, "lr": 6.111697772923836e-07, "epoch": 1.7162471395881007, "percentage": 85.81, "elapsed_time": "3:00:07", "remaining_time": "0:29:46"}
{"current_steps": 760, "total_steps": 874, "loss": 0.4781, "lr": 5.189559535193839e-07, "epoch": 1.7391304347826086, "percentage": 86.96, "elapsed_time": "3:02:23", "remaining_time": "0:27:21"}
{"current_steps": 770, "total_steps": 874, "loss": 0.4713, "lr": 4.338998718757315e-07, "epoch": 1.7620137299771166, "percentage": 88.1, "elapsed_time": "3:04:40", "remaining_time": "0:24:56"}
{"current_steps": 780, "total_steps": 874, "loss": 0.5064, "lr": 3.5613739567645246e-07, "epoch": 1.7848970251716247, "percentage": 89.24, "elapsed_time": "3:07:05", "remaining_time": "0:22:32"}
{"current_steps": 790, "total_steps": 874, "loss": 0.4907, "lr": 2.8579273788312433e-07, "epoch": 1.8077803203661327, "percentage": 90.39, "elapsed_time": "3:09:32", "remaining_time": "0:20:09"}
{"current_steps": 800, "total_steps": 874, "loss": 0.4547, "lr": 2.2297826269378653e-07, "epoch": 1.8306636155606406, "percentage": 91.53, "elapsed_time": "3:11:52", "remaining_time": "0:17:44"}
{"current_steps": 810, "total_steps": 874, "loss": 0.4939, "lr": 1.6779430605933233e-07, "epoch": 1.8535469107551488, "percentage": 92.68, "elapsed_time": "3:14:10", "remaining_time": "0:15:20"}
{"current_steps": 820, "total_steps": 874, "loss": 0.5068, "lr": 1.203290154130754e-07, "epoch": 1.8764302059496567, "percentage": 93.82, "elapsed_time": "3:16:28", "remaining_time": "0:12:56"}
{"current_steps": 830, "total_steps": 874, "loss": 0.4447, "lr": 8.065820886950404e-08, "epoch": 1.8993135011441646, "percentage": 94.97, "elapsed_time": "3:18:58", "remaining_time": "0:10:32"}
{"current_steps": 840, "total_steps": 874, "loss": 0.4844, "lr": 4.8845254117120265e-08, "epoch": 1.9221967963386728, "percentage": 96.11, "elapsed_time": "3:21:34", "remaining_time": "0:08:09"}
{"current_steps": 850, "total_steps": 874, "loss": 0.4735, "lr": 2.4940967198821553e-08, "epoch": 1.9450800915331807, "percentage": 97.25, "elapsed_time": "3:23:51", "remaining_time": "0:05:45"}
{"current_steps": 860, "total_steps": 874, "loss": 0.457, "lr": 8.983531341500984e-09, "epoch": 1.9679633867276887, "percentage": 98.4, "elapsed_time": "3:26:19", "remaining_time": "0:03:21"}
{"current_steps": 870, "total_steps": 874, "loss": 0.4556, "lr": 9.984359645276443e-10, "epoch": 1.9908466819221968, "percentage": 99.54, "elapsed_time": "3:28:41", "remaining_time": "0:00:57"}
{"current_steps": 874, "total_steps": 874, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:30:17", "remaining_time": "0:00:00"}