330 lines
78 KiB
JSON
330 lines
78 KiB
JSON
{"current_steps": 5, "total_steps": 1644, "loss": 1.469, "lr": 4.999926966182812e-05, "epoch": 0.00913033553983109, "percentage": 0.3, "elapsed_time": "0:00:37", "remaining_time": "3:24:07", "throughput": 834.18, "total_tokens": 31168}
|
|
{"current_steps": 10, "total_steps": 1644, "loss": 1.5127, "lr": 4.999630273613799e-05, "epoch": 0.01826067107966218, "percentage": 0.61, "elapsed_time": "0:01:10", "remaining_time": "3:11:28", "throughput": 839.03, "total_tokens": 58992}
|
|
{"current_steps": 15, "total_steps": 1644, "loss": 1.44, "lr": 4.999105384744215e-05, "epoch": 0.027391006619493265, "percentage": 0.91, "elapsed_time": "0:01:43", "remaining_time": "3:07:04", "throughput": 844.64, "total_tokens": 87296}
|
|
{"current_steps": 20, "total_steps": 1644, "loss": 1.4987, "lr": 4.998352347492226e-05, "epoch": 0.03652134215932436, "percentage": 1.22, "elapsed_time": "0:02:16", "remaining_time": "3:04:06", "throughput": 842.78, "total_tokens": 114656}
|
|
{"current_steps": 25, "total_steps": 1644, "loss": 1.4058, "lr": 4.9973712306041256e-05, "epoch": 0.045651677699155443, "percentage": 1.52, "elapsed_time": "0:02:49", "remaining_time": "3:02:49", "throughput": 847.67, "total_tokens": 143584}
|
|
{"current_steps": 30, "total_steps": 1644, "loss": 1.4049, "lr": 4.996162123648058e-05, "epoch": 0.05478201323898653, "percentage": 1.82, "elapsed_time": "0:03:22", "remaining_time": "3:01:35", "throughput": 850.44, "total_tokens": 172224}
|
|
{"current_steps": 35, "total_steps": 1644, "loss": 1.4239, "lr": 4.99472513700584e-05, "epoch": 0.06391234877881762, "percentage": 2.13, "elapsed_time": "0:03:55", "remaining_time": "3:00:22", "throughput": 850.7, "total_tokens": 200272}
|
|
{"current_steps": 40, "total_steps": 1644, "loss": 1.389, "lr": 4.993060401862888e-05, "epoch": 0.07304268431864872, "percentage": 2.43, "elapsed_time": "0:04:27", "remaining_time": "2:59:03", "throughput": 849.34, "total_tokens": 227552}
|
|
{"current_steps": 45, "total_steps": 1644, "loss": 1.3187, "lr": 4.9911680701962384e-05, "epoch": 0.0821730198584798, "percentage": 2.74, "elapsed_time": "0:05:01", "remaining_time": "2:58:17", "throughput": 851.42, "total_tokens": 256320}
|
|
{"current_steps": 50, "total_steps": 1644, "loss": 1.31, "lr": 4.989048314760674e-05, "epoch": 0.09130335539831089, "percentage": 3.04, "elapsed_time": "0:05:35", "remaining_time": "2:58:03", "throughput": 856.96, "total_tokens": 287184}
|
|
{"current_steps": 55, "total_steps": 1644, "loss": 1.3295, "lr": 4.9867013290729535e-05, "epoch": 0.10043369093814197, "percentage": 3.35, "elapsed_time": "0:06:07", "remaining_time": "2:57:04", "throughput": 856.18, "total_tokens": 314864}
|
|
{"current_steps": 60, "total_steps": 1644, "loss": 1.2718, "lr": 4.984127327394146e-05, "epoch": 0.10956402647797306, "percentage": 3.65, "elapsed_time": "0:06:40", "remaining_time": "2:56:13", "throughput": 856.16, "total_tokens": 342912}
|
|
{"current_steps": 65, "total_steps": 1644, "loss": 1.2547, "lr": 4.981326544710065e-05, "epoch": 0.11869436201780416, "percentage": 3.95, "elapsed_time": "0:07:12", "remaining_time": "2:55:16", "throughput": 854.86, "total_tokens": 370064}
|
|
{"current_steps": 70, "total_steps": 1644, "loss": 1.302, "lr": 4.978299236709826e-05, "epoch": 0.12782469755763523, "percentage": 4.26, "elapsed_time": "0:07:46", "remaining_time": "2:54:48", "throughput": 856.68, "total_tokens": 399584}
|
|
{"current_steps": 75, "total_steps": 1644, "loss": 1.2328, "lr": 4.975045679762496e-05, "epoch": 0.13695503309746634, "percentage": 4.56, "elapsed_time": "0:08:20", "remaining_time": "2:54:28", "throughput": 860.35, "total_tokens": 430528}
|
|
{"current_steps": 80, "total_steps": 1644, "loss": 1.296, "lr": 4.9715661708918624e-05, "epoch": 0.14608536863729743, "percentage": 4.87, "elapsed_time": "0:08:53", "remaining_time": "2:53:57", "throughput": 861.72, "total_tokens": 460080}
|
|
{"current_steps": 85, "total_steps": 1644, "loss": 1.3248, "lr": 4.9678610277493275e-05, "epoch": 0.15521570417712852, "percentage": 5.17, "elapsed_time": "0:09:26", "remaining_time": "2:53:18", "throughput": 861.08, "total_tokens": 488176}
|
|
{"current_steps": 90, "total_steps": 1644, "loss": 1.207, "lr": 4.9639305885848975e-05, "epoch": 0.1643460397169596, "percentage": 5.47, "elapsed_time": "0:10:00", "remaining_time": "2:52:42", "throughput": 861.29, "total_tokens": 516896}
|
|
{"current_steps": 95, "total_steps": 1644, "loss": 1.2342, "lr": 4.959775212216308e-05, "epoch": 0.1734763752567907, "percentage": 5.78, "elapsed_time": "0:10:34", "remaining_time": "2:52:20", "throughput": 863.2, "total_tokens": 547440}
|
|
{"current_steps": 100, "total_steps": 1644, "loss": 1.1931, "lr": 4.955395277996268e-05, "epoch": 0.18260671079662177, "percentage": 6.08, "elapsed_time": "0:11:07", "remaining_time": "2:51:50", "throughput": 864.21, "total_tokens": 577088}
|
|
{"current_steps": 105, "total_steps": 1644, "loss": 1.2122, "lr": 4.9507911857778256e-05, "epoch": 0.19173704633645286, "percentage": 6.39, "elapsed_time": "0:11:42", "remaining_time": "2:51:38", "throughput": 863.9, "total_tokens": 606976}
|
|
{"current_steps": 110, "total_steps": 1644, "loss": 1.2973, "lr": 4.9459633558778684e-05, "epoch": 0.20086738187628395, "percentage": 6.69, "elapsed_time": "0:12:15", "remaining_time": "2:50:52", "throughput": 862.94, "total_tokens": 634416}
|
|
{"current_steps": 115, "total_steps": 1644, "loss": 1.2483, "lr": 4.940912229038745e-05, "epoch": 0.20999771741611503, "percentage": 7.0, "elapsed_time": "0:12:47", "remaining_time": "2:49:59", "throughput": 860.58, "total_tokens": 660192}
|
|
{"current_steps": 120, "total_steps": 1644, "loss": 1.1153, "lr": 4.9356382663880366e-05, "epoch": 0.21912805295594612, "percentage": 7.3, "elapsed_time": "0:13:19", "remaining_time": "2:49:19", "throughput": 859.99, "total_tokens": 687936}
|
|
{"current_steps": 125, "total_steps": 1644, "loss": 1.2269, "lr": 4.930141949396454e-05, "epoch": 0.22825838849577723, "percentage": 7.6, "elapsed_time": "0:13:53", "remaining_time": "2:48:45", "throughput": 860.43, "total_tokens": 716960}
|
|
{"current_steps": 130, "total_steps": 1644, "loss": 1.1324, "lr": 4.9244237798338866e-05, "epoch": 0.23738872403560832, "percentage": 7.91, "elapsed_time": "0:14:26", "remaining_time": "2:48:07", "throughput": 860.09, "total_tokens": 744976}
|
|
{"current_steps": 135, "total_steps": 1644, "loss": 1.1818, "lr": 4.918484279723592e-05, "epoch": 0.2465190595754394, "percentage": 8.21, "elapsed_time": "0:14:58", "remaining_time": "2:47:25", "throughput": 859.22, "total_tokens": 772176}
|
|
{"current_steps": 140, "total_steps": 1644, "loss": 1.1243, "lr": 4.9123239912945423e-05, "epoch": 0.25564939511527046, "percentage": 8.52, "elapsed_time": "0:15:33", "remaining_time": "2:47:07", "throughput": 861.88, "total_tokens": 804528}
|
|
{"current_steps": 145, "total_steps": 1644, "loss": 1.2134, "lr": 4.9059434769319205e-05, "epoch": 0.2647797306551016, "percentage": 8.82, "elapsed_time": "0:16:05", "remaining_time": "2:46:22", "throughput": 860.64, "total_tokens": 831056}
|
|
{"current_steps": 150, "total_steps": 1644, "loss": 1.0775, "lr": 4.899343319125781e-05, "epoch": 0.2739100661949327, "percentage": 9.12, "elapsed_time": "0:16:39", "remaining_time": "2:45:59", "throughput": 862.5, "total_tokens": 862416}
|
|
{"current_steps": 155, "total_steps": 1644, "loss": 1.2069, "lr": 4.892524120417872e-05, "epoch": 0.28304040173476375, "percentage": 9.43, "elapsed_time": "0:17:12", "remaining_time": "2:45:14", "throughput": 861.61, "total_tokens": 889264}
|
|
{"current_steps": 160, "total_steps": 1644, "loss": 1.1649, "lr": 4.8854865033466275e-05, "epoch": 0.29217073727459486, "percentage": 9.73, "elapsed_time": "0:17:44", "remaining_time": "2:44:35", "throughput": 861.33, "total_tokens": 917104}
|
|
{"current_steps": 165, "total_steps": 1644, "loss": 1.1495, "lr": 4.878231110390337e-05, "epoch": 0.3013010728144259, "percentage": 10.04, "elapsed_time": "0:18:18", "remaining_time": "2:44:06", "throughput": 862.32, "total_tokens": 947280}
|
|
{"current_steps": 170, "total_steps": 1644, "loss": 1.1231, "lr": 4.870758603908489e-05, "epoch": 0.31043140835425703, "percentage": 10.34, "elapsed_time": "0:18:52", "remaining_time": "2:43:41", "throughput": 864.0, "total_tokens": 978704}
|
|
{"current_steps": 175, "total_steps": 1644, "loss": 1.0885, "lr": 4.863069666081307e-05, "epoch": 0.3195617438940881, "percentage": 10.64, "elapsed_time": "0:19:25", "remaining_time": "2:43:00", "throughput": 863.35, "total_tokens": 1005904}
|
|
{"current_steps": 180, "total_steps": 1644, "loss": 1.1022, "lr": 4.855164998847466e-05, "epoch": 0.3286920794339192, "percentage": 10.95, "elapsed_time": "0:19:58", "remaining_time": "2:42:25", "throughput": 863.43, "total_tokens": 1034624}
|
|
{"current_steps": 185, "total_steps": 1644, "loss": 1.1223, "lr": 4.8470453238400195e-05, "epoch": 0.33782241497375026, "percentage": 11.25, "elapsed_time": "0:20:29", "remaining_time": "2:41:36", "throughput": 861.53, "total_tokens": 1059280}
|
|
{"current_steps": 190, "total_steps": 1644, "loss": 1.0287, "lr": 4.8387113823205096e-05, "epoch": 0.3469527505135814, "percentage": 11.56, "elapsed_time": "0:21:03", "remaining_time": "2:41:05", "throughput": 862.14, "total_tokens": 1088960}
|
|
{"current_steps": 195, "total_steps": 1644, "loss": 1.1138, "lr": 4.8301639351113065e-05, "epoch": 0.3560830860534125, "percentage": 11.86, "elapsed_time": "0:21:34", "remaining_time": "2:40:17", "throughput": 860.49, "total_tokens": 1113712}
|
|
{"current_steps": 200, "total_steps": 1644, "loss": 1.1149, "lr": 4.821403762526143e-05, "epoch": 0.36521342159324355, "percentage": 12.17, "elapsed_time": "0:22:06", "remaining_time": "2:39:40", "throughput": 860.36, "total_tokens": 1141696}
|
|
{"current_steps": 205, "total_steps": 1644, "loss": 1.1954, "lr": 4.812431664298883e-05, "epoch": 0.37434375713307466, "percentage": 12.47, "elapsed_time": "0:22:42", "remaining_time": "2:39:21", "throughput": 860.43, "total_tokens": 1172000}
|
|
{"current_steps": 210, "total_steps": 1644, "loss": 1.0426, "lr": 4.803248459510511e-05, "epoch": 0.3834740926729057, "percentage": 12.77, "elapsed_time": "0:23:15", "remaining_time": "2:38:48", "throughput": 860.83, "total_tokens": 1201136}
|
|
{"current_steps": 215, "total_steps": 1644, "loss": 1.2254, "lr": 4.7938549865143544e-05, "epoch": 0.39260442821273683, "percentage": 13.08, "elapsed_time": "0:23:47", "remaining_time": "2:38:08", "throughput": 860.08, "total_tokens": 1227792}
|
|
{"current_steps": 220, "total_steps": 1644, "loss": 1.0323, "lr": 4.7842521028595526e-05, "epoch": 0.4017347637525679, "percentage": 13.38, "elapsed_time": "0:24:21", "remaining_time": "2:37:39", "throughput": 860.93, "total_tokens": 1258240}
|
|
{"current_steps": 225, "total_steps": 1644, "loss": 0.9971, "lr": 4.7744406852127653e-05, "epoch": 0.410865099292399, "percentage": 13.69, "elapsed_time": "0:24:55", "remaining_time": "2:37:13", "throughput": 862.28, "total_tokens": 1289744}
|
|
{"current_steps": 230, "total_steps": 1644, "loss": 1.0328, "lr": 4.764421629278144e-05, "epoch": 0.41999543483223006, "percentage": 13.99, "elapsed_time": "0:25:27", "remaining_time": "2:36:29", "throughput": 861.03, "total_tokens": 1315040}
|
|
{"current_steps": 235, "total_steps": 1644, "loss": 1.0546, "lr": 4.754195849715557e-05, "epoch": 0.4291257703720612, "percentage": 14.29, "elapsed_time": "0:26:00", "remaining_time": "2:35:58", "throughput": 861.65, "total_tokens": 1344848}
|
|
{"current_steps": 240, "total_steps": 1644, "loss": 1.1701, "lr": 4.743764280057092e-05, "epoch": 0.43825610591189224, "percentage": 14.6, "elapsed_time": "0:26:33", "remaining_time": "2:35:19", "throughput": 861.08, "total_tokens": 1371728}
|
|
{"current_steps": 245, "total_steps": 1644, "loss": 1.0949, "lr": 4.73312787262183e-05, "epoch": 0.44738644145172335, "percentage": 14.9, "elapsed_time": "0:27:05", "remaining_time": "2:34:41", "throughput": 860.64, "total_tokens": 1398896}
|
|
{"current_steps": 250, "total_steps": 1644, "loss": 1.1142, "lr": 4.722287598428907e-05, "epoch": 0.45651677699155446, "percentage": 15.21, "elapsed_time": "0:27:37", "remaining_time": "2:34:02", "throughput": 859.97, "total_tokens": 1425376}
|
|
{"current_steps": 255, "total_steps": 1644, "loss": 1.0364, "lr": 4.711244447108866e-05, "epoch": 0.4656471125313855, "percentage": 15.51, "elapsed_time": "0:28:09", "remaining_time": "2:33:24", "throughput": 859.48, "total_tokens": 1452416}
|
|
{"current_steps": 260, "total_steps": 1644, "loss": 1.0669, "lr": 4.6999994268133166e-05, "epoch": 0.47477744807121663, "percentage": 15.82, "elapsed_time": "0:28:42", "remaining_time": "2:32:51", "throughput": 859.84, "total_tokens": 1481440}
|
|
{"current_steps": 265, "total_steps": 1644, "loss": 1.007, "lr": 4.6885535641228904e-05, "epoch": 0.4839077836110477, "percentage": 16.12, "elapsed_time": "0:29:16", "remaining_time": "2:32:18", "throughput": 859.99, "total_tokens": 1510240}
|
|
{"current_steps": 270, "total_steps": 1644, "loss": 0.9444, "lr": 4.676907903953531e-05, "epoch": 0.4930381191508788, "percentage": 16.42, "elapsed_time": "0:29:48", "remaining_time": "2:31:43", "throughput": 859.86, "total_tokens": 1538208}
|
|
{"current_steps": 275, "total_steps": 1644, "loss": 1.0157, "lr": 4.665063509461097e-05, "epoch": 0.5021684546907099, "percentage": 16.73, "elapsed_time": "0:30:21", "remaining_time": "2:31:10", "throughput": 859.98, "total_tokens": 1566880}
|
|
{"current_steps": 280, "total_steps": 1644, "loss": 1.0188, "lr": 4.6530214619443037e-05, "epoch": 0.5112987902305409, "percentage": 17.03, "elapsed_time": "0:30:54", "remaining_time": "2:30:33", "throughput": 859.53, "total_tokens": 1593904}
|
|
{"current_steps": 285, "total_steps": 1644, "loss": 0.9333, "lr": 4.640782860746011e-05, "epoch": 0.520429125770372, "percentage": 17.34, "elapsed_time": "0:31:27", "remaining_time": "2:29:58", "throughput": 859.24, "total_tokens": 1621440}
|
|
{"current_steps": 290, "total_steps": 1644, "loss": 0.9435, "lr": 4.628348823152863e-05, "epoch": 0.5295594613102032, "percentage": 17.64, "elapsed_time": "0:32:00", "remaining_time": "2:29:25", "throughput": 859.31, "total_tokens": 1650064}
|
|
{"current_steps": 295, "total_steps": 1644, "loss": 0.9418, "lr": 4.615720484293286e-05, "epoch": 0.5386897968500343, "percentage": 17.94, "elapsed_time": "0:32:32", "remaining_time": "2:28:49", "throughput": 859.02, "total_tokens": 1677472}
|
|
{"current_steps": 300, "total_steps": 1644, "loss": 0.9934, "lr": 4.602898997033861e-05, "epoch": 0.5478201323898654, "percentage": 18.25, "elapsed_time": "0:33:06", "remaining_time": "2:28:18", "throughput": 859.28, "total_tokens": 1706672}
|
|
{"current_steps": 305, "total_steps": 1644, "loss": 1.0952, "lr": 4.58988553187408e-05, "epoch": 0.5569504679296964, "percentage": 18.55, "elapsed_time": "0:33:40", "remaining_time": "2:27:48", "throughput": 858.69, "total_tokens": 1734704}
|
|
{"current_steps": 310, "total_steps": 1644, "loss": 0.9632, "lr": 4.576681276839483e-05, "epoch": 0.5660808034695275, "percentage": 18.86, "elapsed_time": "0:34:13", "remaining_time": "2:27:15", "throughput": 858.75, "total_tokens": 1763312}
|
|
{"current_steps": 315, "total_steps": 1644, "loss": 0.931, "lr": 4.5632874373732035e-05, "epoch": 0.5752111390093586, "percentage": 19.16, "elapsed_time": "0:34:45", "remaining_time": "2:26:38", "throughput": 858.17, "total_tokens": 1789616}
|
|
{"current_steps": 320, "total_steps": 1644, "loss": 1.0103, "lr": 4.549705236225922e-05, "epoch": 0.5843414745491897, "percentage": 19.46, "elapsed_time": "0:35:18", "remaining_time": "2:26:04", "throughput": 858.16, "total_tokens": 1817760}
|
|
{"current_steps": 325, "total_steps": 1644, "loss": 0.9518, "lr": 4.5359359133442356e-05, "epoch": 0.5934718100890207, "percentage": 19.77, "elapsed_time": "0:35:50", "remaining_time": "2:25:29", "throughput": 858.08, "total_tokens": 1845664}
|
|
{"current_steps": 330, "total_steps": 1644, "loss": 0.8974, "lr": 4.521980725757466e-05, "epoch": 0.6026021456288518, "percentage": 20.07, "elapsed_time": "0:36:24", "remaining_time": "2:24:58", "throughput": 858.47, "total_tokens": 1875392}
|
|
{"current_steps": 335, "total_steps": 1644, "loss": 0.9171, "lr": 4.5078409474628966e-05, "epoch": 0.611732481168683, "percentage": 20.38, "elapsed_time": "0:36:57", "remaining_time": "2:24:23", "throughput": 858.14, "total_tokens": 1902592}
|
|
{"current_steps": 340, "total_steps": 1644, "loss": 0.899, "lr": 4.4935178693094714e-05, "epoch": 0.6208628167085141, "percentage": 20.68, "elapsed_time": "0:37:30", "remaining_time": "2:23:50", "throughput": 858.26, "total_tokens": 1931328}
|
|
{"current_steps": 345, "total_steps": 1644, "loss": 0.8964, "lr": 4.4790127988799494e-05, "epoch": 0.6299931522483452, "percentage": 20.99, "elapsed_time": "0:38:03", "remaining_time": "2:23:18", "throughput": 858.48, "total_tokens": 1960528}
|
|
{"current_steps": 350, "total_steps": 1644, "loss": 1.0919, "lr": 4.464327060371529e-05, "epoch": 0.6391234877881762, "percentage": 21.29, "elapsed_time": "0:38:35", "remaining_time": "2:22:42", "throughput": 858.03, "total_tokens": 1987168}
|
|
{"current_steps": 355, "total_steps": 1644, "loss": 1.0469, "lr": 4.449461994474968e-05, "epoch": 0.6482538233280073, "percentage": 21.59, "elapsed_time": "0:39:08", "remaining_time": "2:22:08", "throughput": 857.86, "total_tokens": 2014832}
|
|
{"current_steps": 360, "total_steps": 1644, "loss": 0.8841, "lr": 4.434418958252179e-05, "epoch": 0.6573841588678384, "percentage": 21.9, "elapsed_time": "0:39:42", "remaining_time": "2:21:35", "throughput": 858.02, "total_tokens": 2043840}
|
|
{"current_steps": 365, "total_steps": 1644, "loss": 1.0016, "lr": 4.4191993250123483e-05, "epoch": 0.6665144944076695, "percentage": 22.2, "elapsed_time": "0:40:15", "remaining_time": "2:21:04", "throughput": 858.21, "total_tokens": 2073120}
|
|
{"current_steps": 370, "total_steps": 1644, "loss": 0.9584, "lr": 4.4038044841865614e-05, "epoch": 0.6756448299475005, "percentage": 22.51, "elapsed_time": "0:40:47", "remaining_time": "2:20:26", "throughput": 857.44, "total_tokens": 2098384}
|
|
{"current_steps": 375, "total_steps": 1644, "loss": 0.9964, "lr": 4.388235841200956e-05, "epoch": 0.6847751654873316, "percentage": 22.81, "elapsed_time": "0:41:20", "remaining_time": "2:19:53", "throughput": 857.55, "total_tokens": 2127008}
|
|
{"current_steps": 380, "total_steps": 1644, "loss": 0.9808, "lr": 4.3724948173484216e-05, "epoch": 0.6939055010271628, "percentage": 23.11, "elapsed_time": "0:41:52", "remaining_time": "2:19:18", "throughput": 857.4, "total_tokens": 2154624}
|
|
{"current_steps": 385, "total_steps": 1644, "loss": 0.9126, "lr": 4.356582849658845e-05, "epoch": 0.7030358365669939, "percentage": 23.42, "elapsed_time": "0:42:26", "remaining_time": "2:18:48", "throughput": 857.82, "total_tokens": 2184768}
|
|
{"current_steps": 390, "total_steps": 1644, "loss": 0.8749, "lr": 4.340501390767924e-05, "epoch": 0.712166172106825, "percentage": 23.72, "elapsed_time": "0:43:00", "remaining_time": "2:18:17", "throughput": 858.1, "total_tokens": 2214336}
|
|
{"current_steps": 395, "total_steps": 1644, "loss": 0.9203, "lr": 4.324251908784546e-05, "epoch": 0.721296507646656, "percentage": 24.03, "elapsed_time": "0:43:33", "remaining_time": "2:17:44", "throughput": 858.29, "total_tokens": 2243296}
|
|
{"current_steps": 400, "total_steps": 1644, "loss": 0.8857, "lr": 4.3078358871567706e-05, "epoch": 0.7304268431864871, "percentage": 24.33, "elapsed_time": "0:44:07", "remaining_time": "2:17:13", "throughput": 858.7, "total_tokens": 2273424}
|
|
{"current_steps": 405, "total_steps": 1644, "loss": 0.9175, "lr": 4.291254824536396e-05, "epoch": 0.7395571787263182, "percentage": 24.64, "elapsed_time": "0:44:42", "remaining_time": "2:16:45", "throughput": 858.62, "total_tokens": 2303040}
|
|
{"current_steps": 410, "total_steps": 1644, "loss": 0.9572, "lr": 4.274510234642148e-05, "epoch": 0.7486875142661493, "percentage": 24.94, "elapsed_time": "0:45:14", "remaining_time": "2:16:10", "throughput": 858.42, "total_tokens": 2330352}
|
|
{"current_steps": 415, "total_steps": 1644, "loss": 1.0534, "lr": 4.257603646121484e-05, "epoch": 0.7578178498059803, "percentage": 25.24, "elapsed_time": "0:45:47", "remaining_time": "2:15:35", "throughput": 858.3, "total_tokens": 2357968}
|
|
{"current_steps": 420, "total_steps": 1644, "loss": 0.8583, "lr": 4.240536602411048e-05, "epoch": 0.7669481853458114, "percentage": 25.55, "elapsed_time": "0:46:20", "remaining_time": "2:15:03", "throughput": 858.4, "total_tokens": 2386800}
|
|
{"current_steps": 425, "total_steps": 1644, "loss": 0.8049, "lr": 4.22331066159576e-05, "epoch": 0.7760785208856426, "percentage": 25.85, "elapsed_time": "0:46:53", "remaining_time": "2:14:30", "throughput": 858.68, "total_tokens": 2416224}
|
|
{"current_steps": 430, "total_steps": 1644, "loss": 0.9599, "lr": 4.205927396266577e-05, "epoch": 0.7852088564254737, "percentage": 26.16, "elapsed_time": "0:47:27", "remaining_time": "2:13:58", "throughput": 858.76, "total_tokens": 2445120}
|
|
{"current_steps": 435, "total_steps": 1644, "loss": 0.8874, "lr": 4.188388393376933e-05, "epoch": 0.7943391919653047, "percentage": 26.46, "elapsed_time": "0:48:00", "remaining_time": "2:13:25", "throughput": 858.73, "total_tokens": 2473312}
|
|
{"current_steps": 440, "total_steps": 1644, "loss": 0.8944, "lr": 4.1706952540978545e-05, "epoch": 0.8034695275051358, "percentage": 26.76, "elapsed_time": "0:48:32", "remaining_time": "2:12:50", "throughput": 858.55, "total_tokens": 2500800}
|
|
{"current_steps": 445, "total_steps": 1644, "loss": 0.9774, "lr": 4.152849593671793e-05, "epoch": 0.8125998630449669, "percentage": 27.07, "elapsed_time": "0:49:05", "remaining_time": "2:12:17", "throughput": 858.61, "total_tokens": 2529392}
|
|
{"current_steps": 450, "total_steps": 1644, "loss": 0.8543, "lr": 4.134853041265162e-05, "epoch": 0.821730198584798, "percentage": 27.37, "elapsed_time": "0:49:39", "remaining_time": "2:11:45", "throughput": 859.04, "total_tokens": 2559536}
|
|
{"current_steps": 455, "total_steps": 1644, "loss": 0.8293, "lr": 4.11670723981961e-05, "epoch": 0.8308605341246291, "percentage": 27.68, "elapsed_time": "0:50:12", "remaining_time": "2:11:12", "throughput": 859.07, "total_tokens": 2588144}
|
|
{"current_steps": 460, "total_steps": 1644, "loss": 0.9264, "lr": 4.098413845902033e-05, "epoch": 0.8399908696644601, "percentage": 27.98, "elapsed_time": "0:50:46", "remaining_time": "2:10:41", "throughput": 859.36, "total_tokens": 2617968}
|
|
{"current_steps": 465, "total_steps": 1644, "loss": 0.9641, "lr": 4.079974529553341e-05, "epoch": 0.8491212052042912, "percentage": 28.28, "elapsed_time": "0:51:19", "remaining_time": "2:10:08", "throughput": 859.44, "total_tokens": 2646896}
|
|
{"current_steps": 470, "total_steps": 1644, "loss": 0.805, "lr": 4.061390974135997e-05, "epoch": 0.8582515407441224, "percentage": 28.59, "elapsed_time": "0:51:52", "remaining_time": "2:09:33", "throughput": 859.28, "total_tokens": 2674288}
|
|
{"current_steps": 475, "total_steps": 1644, "loss": 1.0411, "lr": 4.042664876180341e-05, "epoch": 0.8673818762839535, "percentage": 28.89, "elapsed_time": "0:52:24", "remaining_time": "2:08:57", "throughput": 858.91, "total_tokens": 2700464}
|
|
{"current_steps": 480, "total_steps": 1644, "loss": 0.8638, "lr": 4.0237979452297094e-05, "epoch": 0.8765122118237845, "percentage": 29.2, "elapsed_time": "0:52:58", "remaining_time": "2:08:27", "throughput": 859.55, "total_tokens": 2732112}
|
|
{"current_steps": 485, "total_steps": 1644, "loss": 1.0152, "lr": 4.0047919036843675e-05, "epoch": 0.8856425473636156, "percentage": 29.5, "elapsed_time": "0:53:30", "remaining_time": "2:07:51", "throughput": 859.07, "total_tokens": 2757872}
|
|
{"current_steps": 490, "total_steps": 1644, "loss": 0.9046, "lr": 3.985648486644267e-05, "epoch": 0.8947728829034467, "percentage": 29.81, "elapsed_time": "0:54:03", "remaining_time": "2:07:18", "throughput": 859.04, "total_tokens": 2786192}
|
|
{"current_steps": 495, "total_steps": 1644, "loss": 0.8428, "lr": 3.966369441750648e-05, "epoch": 0.9039032184432778, "percentage": 30.11, "elapsed_time": "0:54:35", "remaining_time": "2:06:42", "throughput": 858.64, "total_tokens": 2812368}
|
|
{"current_steps": 500, "total_steps": 1644, "loss": 0.8138, "lr": 3.9469565290264906e-05, "epoch": 0.9130335539831089, "percentage": 30.41, "elapsed_time": "0:55:08", "remaining_time": "2:06:09", "throughput": 858.66, "total_tokens": 2840912}
|
|
{"current_steps": 505, "total_steps": 1644, "loss": 0.8349, "lr": 3.92741152071584e-05, "epoch": 0.9221638895229399, "percentage": 30.72, "elapsed_time": "0:55:43", "remaining_time": "2:05:40", "throughput": 858.45, "total_tokens": 2870000}
|
|
{"current_steps": 510, "total_steps": 1644, "loss": 0.883, "lr": 3.907736201122014e-05, "epoch": 0.931294225062771, "percentage": 31.02, "elapsed_time": "0:56:16", "remaining_time": "2:05:07", "throughput": 858.66, "total_tokens": 2899328}
|
|
{"current_steps": 515, "total_steps": 1644, "loss": 0.8141, "lr": 3.8879323664447096e-05, "epoch": 0.9404245606026022, "percentage": 31.33, "elapsed_time": "0:56:50", "remaining_time": "2:04:35", "throughput": 858.89, "total_tokens": 2928832}
|
|
{"current_steps": 520, "total_steps": 1644, "loss": 0.8964, "lr": 3.8680018246160295e-05, "epoch": 0.9495548961424333, "percentage": 31.63, "elapsed_time": "0:57:22", "remaining_time": "2:04:01", "throughput": 858.74, "total_tokens": 2956352}
|
|
{"current_steps": 525, "total_steps": 1644, "loss": 0.7845, "lr": 3.8479463951354245e-05, "epoch": 0.9586852316822643, "percentage": 31.93, "elapsed_time": "0:57:55", "remaining_time": "2:03:28", "throughput": 858.79, "total_tokens": 2985072}
|
|
{"current_steps": 530, "total_steps": 1644, "loss": 0.9675, "lr": 3.827767908903592e-05, "epoch": 0.9678155672220954, "percentage": 32.24, "elapsed_time": "0:58:28", "remaining_time": "2:02:55", "throughput": 858.76, "total_tokens": 3013200}
|
|
{"current_steps": 535, "total_steps": 1644, "loss": 0.9429, "lr": 3.8074682080553335e-05, "epoch": 0.9769459027619265, "percentage": 32.54, "elapsed_time": "0:59:02", "remaining_time": "2:02:23", "throughput": 859.21, "total_tokens": 3044064}
|
|
{"current_steps": 540, "total_steps": 1644, "loss": 0.9034, "lr": 3.7870491457913714e-05, "epoch": 0.9860762383017576, "percentage": 32.85, "elapsed_time": "0:59:35", "remaining_time": "2:01:49", "throughput": 858.95, "total_tokens": 3071008}
|
|
{"current_steps": 545, "total_steps": 1644, "loss": 0.8696, "lr": 3.7665125862091765e-05, "epoch": 0.9952065738415887, "percentage": 33.15, "elapsed_time": "1:00:08", "remaining_time": "2:01:17", "throughput": 859.09, "total_tokens": 3100256}
|
|
{"current_steps": 550, "total_steps": 1644, "loss": 0.9914, "lr": 3.7458604041327874e-05, "epoch": 1.0036521342159324, "percentage": 33.45, "elapsed_time": "1:00:38", "remaining_time": "2:00:37", "throughput": 858.83, "total_tokens": 3125104}
|
|
{"current_steps": 555, "total_steps": 1644, "loss": 0.7924, "lr": 3.725094484941654e-05, "epoch": 1.0127824697557635, "percentage": 33.76, "elapsed_time": "1:01:11", "remaining_time": "2:00:04", "throughput": 858.78, "total_tokens": 3153200}
|
|
{"current_steps": 560, "total_steps": 1644, "loss": 0.7542, "lr": 3.704216724398515e-05, "epoch": 1.0219128052955946, "percentage": 34.06, "elapsed_time": "1:01:44", "remaining_time": "1:59:30", "throughput": 858.67, "total_tokens": 3180768}
|
|
{"current_steps": 565, "total_steps": 1644, "loss": 0.7216, "lr": 3.683229028476334e-05, "epoch": 1.0310431408354257, "percentage": 34.37, "elapsed_time": "1:02:16", "remaining_time": "1:58:56", "throughput": 858.51, "total_tokens": 3208032}
|
|
{"current_steps": 570, "total_steps": 1644, "loss": 0.8276, "lr": 3.6621333131842994e-05, "epoch": 1.0401734763752568, "percentage": 34.67, "elapsed_time": "1:02:49", "remaining_time": "1:58:22", "throughput": 858.31, "total_tokens": 3235216}
|
|
{"current_steps": 575, "total_steps": 1644, "loss": 0.8081, "lr": 3.640931504392902e-05, "epoch": 1.049303811915088, "percentage": 34.98, "elapsed_time": "1:03:22", "remaining_time": "1:57:49", "throughput": 858.44, "total_tokens": 3264128}
|
|
{"current_steps": 580, "total_steps": 1644, "loss": 0.7503, "lr": 3.6196255376581254e-05, "epoch": 1.058434147454919, "percentage": 35.28, "elapsed_time": "1:03:54", "remaining_time": "1:57:14", "throughput": 858.31, "total_tokens": 3291488}
|
|
{"current_steps": 585, "total_steps": 1644, "loss": 0.7449, "lr": 3.598217358044743e-05, "epoch": 1.0675644829947502, "percentage": 35.58, "elapsed_time": "1:04:28", "remaining_time": "1:56:42", "throughput": 858.46, "total_tokens": 3320544}
|
|
{"current_steps": 590, "total_steps": 1644, "loss": 0.7779, "lr": 3.576708919948747e-05, "epoch": 1.076694818534581, "percentage": 35.89, "elapsed_time": "1:05:01", "remaining_time": "1:56:10", "throughput": 858.72, "total_tokens": 3350544}
|
|
{"current_steps": 595, "total_steps": 1644, "loss": 0.7257, "lr": 3.5551021869189286e-05, "epoch": 1.0858251540744122, "percentage": 36.19, "elapsed_time": "1:05:35", "remaining_time": "1:55:38", "throughput": 859.04, "total_tokens": 3380800}
|
|
{"current_steps": 600, "total_steps": 1644, "loss": 0.7348, "lr": 3.533399131477624e-05, "epoch": 1.0949554896142433, "percentage": 36.5, "elapsed_time": "1:06:08", "remaining_time": "1:55:05", "throughput": 859.01, "total_tokens": 3408976}
|
|
{"current_steps": 605, "total_steps": 1644, "loss": 0.814, "lr": 3.511601734940636e-05, "epoch": 1.1040858251540744, "percentage": 36.8, "elapsed_time": "1:06:42", "remaining_time": "1:54:33", "throughput": 858.8, "total_tokens": 3437392}
|
|
{"current_steps": 610, "total_steps": 1644, "loss": 0.6645, "lr": 3.489711987236357e-05, "epoch": 1.1132161606939055, "percentage": 37.1, "elapsed_time": "1:07:15", "remaining_time": "1:54:00", "throughput": 858.74, "total_tokens": 3465184}
|
|
{"current_steps": 615, "total_steps": 1644, "loss": 0.7804, "lr": 3.467731886724104e-05, "epoch": 1.1223464962337366, "percentage": 37.41, "elapsed_time": "1:07:48", "remaining_time": "1:53:26", "throughput": 858.73, "total_tokens": 3493520}
|
|
{"current_steps": 620, "total_steps": 1644, "loss": 0.8645, "lr": 3.445663440011685e-05, "epoch": 1.1314768317735677, "percentage": 37.71, "elapsed_time": "1:08:20", "remaining_time": "1:52:52", "throughput": 858.48, "total_tokens": 3520400}
|
|
{"current_steps": 625, "total_steps": 1644, "loss": 0.7509, "lr": 3.42350866177221e-05, "epoch": 1.1406071673133988, "percentage": 38.02, "elapsed_time": "1:08:54", "remaining_time": "1:52:20", "throughput": 858.7, "total_tokens": 3550208}
|
|
{"current_steps": 630, "total_steps": 1644, "loss": 0.738, "lr": 3.4012695745601694e-05, "epoch": 1.1497375028532297, "percentage": 38.32, "elapsed_time": "1:09:27", "remaining_time": "1:51:48", "throughput": 858.81, "total_tokens": 3579424}
|
|
{"current_steps": 635, "total_steps": 1644, "loss": 0.731, "lr": 3.378948208626792e-05, "epoch": 1.158867838393061, "percentage": 38.63, "elapsed_time": "1:10:01", "remaining_time": "1:51:15", "throughput": 858.83, "total_tokens": 3608096}
|
|
{"current_steps": 640, "total_steps": 1644, "loss": 0.6878, "lr": 3.356546601734692e-05, "epoch": 1.167998173932892, "percentage": 38.93, "elapsed_time": "1:10:34", "remaining_time": "1:50:42", "throughput": 858.79, "total_tokens": 3636352}
|
|
{"current_steps": 645, "total_steps": 1644, "loss": 0.6777, "lr": 3.3340667989718494e-05, "epoch": 1.177128509472723, "percentage": 39.23, "elapsed_time": "1:11:07", "remaining_time": "1:50:09", "throughput": 858.84, "total_tokens": 3665104}
|
|
{"current_steps": 650, "total_steps": 1644, "loss": 0.8185, "lr": 3.3115108525648995e-05, "epoch": 1.1862588450125542, "percentage": 39.54, "elapsed_time": "1:11:40", "remaining_time": "1:49:35", "throughput": 858.76, "total_tokens": 3692784}
|
|
{"current_steps": 655, "total_steps": 1644, "loss": 0.7367, "lr": 3.288880821691785e-05, "epoch": 1.1953891805523853, "percentage": 39.84, "elapsed_time": "1:12:12", "remaining_time": "1:49:02", "throughput": 858.67, "total_tokens": 3720544}
|
|
{"current_steps": 660, "total_steps": 1644, "loss": 0.7812, "lr": 3.2661787722937705e-05, "epoch": 1.2045195160922164, "percentage": 40.15, "elapsed_time": "1:12:45", "remaining_time": "1:48:29", "throughput": 858.63, "total_tokens": 3748640}
|
|
{"current_steps": 665, "total_steps": 1644, "loss": 0.6602, "lr": 3.2434067768868365e-05, "epoch": 1.2136498516320475, "percentage": 40.45, "elapsed_time": "1:13:19", "remaining_time": "1:47:57", "throughput": 858.96, "total_tokens": 3779312}
|
|
{"current_steps": 670, "total_steps": 1644, "loss": 0.7918, "lr": 3.220566914372477e-05, "epoch": 1.2227801871718786, "percentage": 40.75, "elapsed_time": "1:13:52", "remaining_time": "1:47:23", "throughput": 858.9, "total_tokens": 3807232}
|
|
{"current_steps": 675, "total_steps": 1644, "loss": 0.6596, "lr": 3.1976612698479104e-05, "epoch": 1.2319105227117095, "percentage": 41.06, "elapsed_time": "1:14:25", "remaining_time": "1:46:50", "throughput": 858.9, "total_tokens": 3835568}
|
|
{"current_steps": 680, "total_steps": 1644, "loss": 0.595, "lr": 3.174691934415727e-05, "epoch": 1.2410408582515409, "percentage": 41.36, "elapsed_time": "1:14:59", "remaining_time": "1:46:18", "throughput": 859.24, "total_tokens": 3866240}
|
|
{"current_steps": 685, "total_steps": 1644, "loss": 0.7421, "lr": 3.151661004992992e-05, "epoch": 1.2501711937913718, "percentage": 41.67, "elapsed_time": "1:15:32", "remaining_time": "1:45:45", "throughput": 859.23, "total_tokens": 3894400}
|
|
{"current_steps": 690, "total_steps": 1644, "loss": 0.8241, "lr": 3.128570584119806e-05, "epoch": 1.2593015293312029, "percentage": 41.97, "elapsed_time": "1:16:03", "remaining_time": "1:45:09", "throughput": 858.6, "total_tokens": 3917984}
|
|
{"current_steps": 695, "total_steps": 1644, "loss": 0.7889, "lr": 3.105422779767369e-05, "epoch": 1.268431864871034, "percentage": 42.27, "elapsed_time": "1:16:35", "remaining_time": "1:44:34", "throughput": 858.29, "total_tokens": 3943952}
|
|
{"current_steps": 700, "total_steps": 1644, "loss": 0.8462, "lr": 3.08221970514553e-05, "epoch": 1.277562200410865, "percentage": 42.58, "elapsed_time": "1:17:07", "remaining_time": "1:44:00", "throughput": 858.12, "total_tokens": 3970976}
|
|
{"current_steps": 705, "total_steps": 1644, "loss": 0.8064, "lr": 3.058963478509879e-05, "epoch": 1.2866925359506962, "percentage": 42.88, "elapsed_time": "1:17:41", "remaining_time": "1:43:28", "throughput": 857.86, "total_tokens": 3998816}
|
|
{"current_steps": 710, "total_steps": 1644, "loss": 0.7113, "lr": 3.0356562229683534e-05, "epoch": 1.2958228714905273, "percentage": 43.19, "elapsed_time": "1:18:13", "remaining_time": "1:42:54", "throughput": 857.75, "total_tokens": 4026144}
|
|
{"current_steps": 715, "total_steps": 1644, "loss": 0.7086, "lr": 3.0123000662874272e-05, "epoch": 1.3049532070303584, "percentage": 43.49, "elapsed_time": "1:18:46", "remaining_time": "1:42:20", "throughput": 857.58, "total_tokens": 4053232}
|
|
{"current_steps": 720, "total_steps": 1644, "loss": 0.6923, "lr": 2.9888971406978584e-05, "epoch": 1.3140835425701893, "percentage": 43.8, "elapsed_time": "1:19:19", "remaining_time": "1:41:47", "throughput": 857.53, "total_tokens": 4080992}
|
|
{"current_steps": 725, "total_steps": 1644, "loss": 0.7034, "lr": 2.965449582700031e-05, "epoch": 1.3232138781100207, "percentage": 44.1, "elapsed_time": "1:19:52", "remaining_time": "1:41:14", "throughput": 857.46, "total_tokens": 4108944}
|
|
{"current_steps": 730, "total_steps": 1644, "loss": 0.7029, "lr": 2.9419595328689138e-05, "epoch": 1.3323442136498516, "percentage": 44.4, "elapsed_time": "1:20:25", "remaining_time": "1:40:41", "throughput": 857.55, "total_tokens": 4137872}
|
|
{"current_steps": 735, "total_steps": 1644, "loss": 0.7442, "lr": 2.918429135658638e-05, "epoch": 1.3414745491896827, "percentage": 44.71, "elapsed_time": "1:20:58", "remaining_time": "1:40:08", "throughput": 857.69, "total_tokens": 4167120}
|
|
{"current_steps": 740, "total_steps": 1644, "loss": 0.6896, "lr": 2.8948605392067322e-05, "epoch": 1.3506048847295138, "percentage": 45.01, "elapsed_time": "1:21:32", "remaining_time": "1:39:36", "throughput": 857.92, "total_tokens": 4197456}
|
|
{"current_steps": 745, "total_steps": 1644, "loss": 0.7188, "lr": 2.8712558951380097e-05, "epoch": 1.359735220269345, "percentage": 45.32, "elapsed_time": "1:22:06", "remaining_time": "1:39:04", "throughput": 858.05, "total_tokens": 4226784}
|
|
{"current_steps": 750, "total_steps": 1644, "loss": 0.7536, "lr": 2.847617358368142e-05, "epoch": 1.368865555809176, "percentage": 45.62, "elapsed_time": "1:22:40", "remaining_time": "1:38:32", "throughput": 858.33, "total_tokens": 4257552}
|
|
{"current_steps": 755, "total_steps": 1644, "loss": 0.6742, "lr": 2.8239470869069357e-05, "epoch": 1.3779958913490071, "percentage": 45.92, "elapsed_time": "1:23:13", "remaining_time": "1:37:59", "throughput": 858.27, "total_tokens": 4285344}
|
|
{"current_steps": 760, "total_steps": 1644, "loss": 0.6787, "lr": 2.800247241661321e-05, "epoch": 1.3871262268888382, "percentage": 46.23, "elapsed_time": "1:23:46", "remaining_time": "1:37:26", "throughput": 858.28, "total_tokens": 4313920}
|
|
{"current_steps": 765, "total_steps": 1644, "loss": 0.8232, "lr": 2.776519986238079e-05, "epoch": 1.3962565624286691, "percentage": 46.53, "elapsed_time": "1:24:18", "remaining_time": "1:36:52", "throughput": 858.22, "total_tokens": 4341584}
|
|
{"current_steps": 770, "total_steps": 1644, "loss": 0.7529, "lr": 2.75276748674632e-05, "epoch": 1.4053868979685005, "percentage": 46.84, "elapsed_time": "1:24:51", "remaining_time": "1:36:19", "throughput": 858.1, "total_tokens": 4369072}
|
|
{"current_steps": 775, "total_steps": 1644, "loss": 0.7612, "lr": 2.7289919115997374e-05, "epoch": 1.4145172335083314, "percentage": 47.14, "elapsed_time": "1:25:24", "remaining_time": "1:35:45", "throughput": 858.08, "total_tokens": 4397152}
|
|
{"current_steps": 780, "total_steps": 1644, "loss": 0.777, "lr": 2.7051954313186484e-05, "epoch": 1.4236475690481625, "percentage": 47.45, "elapsed_time": "1:25:56", "remaining_time": "1:35:11", "throughput": 857.8, "total_tokens": 4423120}
|
|
{"current_steps": 785, "total_steps": 1644, "loss": 0.7732, "lr": 2.6813802183318404e-05, "epoch": 1.4327779045879936, "percentage": 47.75, "elapsed_time": "1:26:29", "remaining_time": "1:34:38", "throughput": 857.81, "total_tokens": 4451328}
|
|
{"current_steps": 790, "total_steps": 1644, "loss": 0.6874, "lr": 2.6575484467782486e-05, "epoch": 1.4419082401278247, "percentage": 48.05, "elapsed_time": "1:27:02", "remaining_time": "1:34:05", "throughput": 857.88, "total_tokens": 4480256}
|
|
{"current_steps": 795, "total_steps": 1644, "loss": 0.6866, "lr": 2.633702292308473e-05, "epoch": 1.4510385756676558, "percentage": 48.36, "elapsed_time": "1:27:35", "remaining_time": "1:33:32", "throughput": 858.01, "total_tokens": 4509584}
|
|
{"current_steps": 800, "total_steps": 1644, "loss": 0.6184, "lr": 2.60984393188616e-05, "epoch": 1.460168911207487, "percentage": 48.66, "elapsed_time": "1:28:08", "remaining_time": "1:32:59", "throughput": 857.91, "total_tokens": 4537136}
|
|
{"current_steps": 805, "total_steps": 1644, "loss": 0.6364, "lr": 2.5859755435892597e-05, "epoch": 1.469299246747318, "percentage": 48.97, "elapsed_time": "1:28:42", "remaining_time": "1:32:27", "throughput": 857.71, "total_tokens": 4565424}
|
|
{"current_steps": 810, "total_steps": 1644, "loss": 0.7312, "lr": 2.5620993064111902e-05, "epoch": 1.478429582287149, "percentage": 49.27, "elapsed_time": "1:29:15", "remaining_time": "1:31:54", "throughput": 857.63, "total_tokens": 4592976}
|
|
{"current_steps": 815, "total_steps": 1644, "loss": 0.6735, "lr": 2.538217400061907e-05, "epoch": 1.4875599178269803, "percentage": 49.57, "elapsed_time": "1:29:48", "remaining_time": "1:31:21", "throughput": 857.79, "total_tokens": 4622416}
|
|
{"current_steps": 820, "total_steps": 1644, "loss": 0.5681, "lr": 2.5143320047689173e-05, "epoch": 1.4966902533668112, "percentage": 49.88, "elapsed_time": "1:30:21", "remaining_time": "1:30:47", "throughput": 857.56, "total_tokens": 4648848}
|
|
{"current_steps": 825, "total_steps": 1644, "loss": 0.7154, "lr": 2.49044530107824e-05, "epoch": 1.5058205889066423, "percentage": 50.18, "elapsed_time": "1:30:53", "remaining_time": "1:30:13", "throughput": 857.25, "total_tokens": 4674688}
|
|
{"current_steps": 830, "total_steps": 1644, "loss": 0.659, "lr": 2.4665594696553428e-05, "epoch": 1.5149509244464734, "percentage": 50.49, "elapsed_time": "1:31:24", "remaining_time": "1:29:39", "throughput": 856.95, "total_tokens": 4700240}
|
|
{"current_steps": 835, "total_steps": 1644, "loss": 0.66, "lr": 2.4426766910860585e-05, "epoch": 1.5240812599863045, "percentage": 50.79, "elapsed_time": "1:31:58", "remaining_time": "1:29:06", "throughput": 857.08, "total_tokens": 4729648}
|
|
{"current_steps": 840, "total_steps": 1644, "loss": 0.8048, "lr": 2.4187991456775217e-05, "epoch": 1.5332115955261356, "percentage": 51.09, "elapsed_time": "1:32:31", "remaining_time": "1:28:33", "throughput": 857.23, "total_tokens": 4758944}
|
|
{"current_steps": 845, "total_steps": 1644, "loss": 0.6516, "lr": 2.3949290132591197e-05, "epoch": 1.5423419310659665, "percentage": 51.4, "elapsed_time": "1:33:04", "remaining_time": "1:28:00", "throughput": 857.24, "total_tokens": 4787360}
|
|
{"current_steps": 850, "total_steps": 1644, "loss": 0.6813, "lr": 2.3710684729834954e-05, "epoch": 1.5514722666057978, "percentage": 51.7, "elapsed_time": "1:33:37", "remaining_time": "1:27:27", "throughput": 857.25, "total_tokens": 4815712}
|
|
{"current_steps": 855, "total_steps": 1644, "loss": 0.7308, "lr": 2.3472197031276e-05, "epoch": 1.5606026021456287, "percentage": 52.01, "elapsed_time": "1:34:11", "remaining_time": "1:26:54", "throughput": 857.41, "total_tokens": 4845280}
|
|
{"current_steps": 860, "total_steps": 1644, "loss": 0.7728, "lr": 2.3233848808938453e-05, "epoch": 1.56973293768546, "percentage": 52.31, "elapsed_time": "1:34:44", "remaining_time": "1:26:21", "throughput": 857.47, "total_tokens": 4873936}
|
|
{"current_steps": 865, "total_steps": 1644, "loss": 0.6673, "lr": 2.299566182211333e-05, "epoch": 1.578863273225291, "percentage": 52.62, "elapsed_time": "1:35:16", "remaining_time": "1:25:48", "throughput": 857.38, "total_tokens": 4901104}
|
|
{"current_steps": 870, "total_steps": 1644, "loss": 0.7155, "lr": 2.275765781537215e-05, "epoch": 1.587993608765122, "percentage": 52.92, "elapsed_time": "1:35:49", "remaining_time": "1:25:15", "throughput": 857.4, "total_tokens": 4929696}
|
|
{"current_steps": 875, "total_steps": 1644, "loss": 0.6372, "lr": 2.251985851658181e-05, "epoch": 1.5971239443049532, "percentage": 53.22, "elapsed_time": "1:36:23", "remaining_time": "1:24:42", "throughput": 857.54, "total_tokens": 4959408}
|
|
{"current_steps": 880, "total_steps": 1644, "loss": 0.7021, "lr": 2.228228563492098e-05, "epoch": 1.6062542798447843, "percentage": 53.53, "elapsed_time": "1:36:56", "remaining_time": "1:24:09", "throughput": 857.66, "total_tokens": 4988800}
|
|
{"current_steps": 885, "total_steps": 1644, "loss": 0.6923, "lr": 2.2044960858898277e-05, "epoch": 1.6153846153846154, "percentage": 53.83, "elapsed_time": "1:37:30", "remaining_time": "1:23:37", "throughput": 857.84, "total_tokens": 5018752}
|
|
{"current_steps": 890, "total_steps": 1644, "loss": 0.6426, "lr": 2.1807905854372242e-05, "epoch": 1.6245149509244463, "percentage": 54.14, "elapsed_time": "1:38:03", "remaining_time": "1:23:04", "throughput": 857.93, "total_tokens": 5047792}
|
|
{"current_steps": 895, "total_steps": 1644, "loss": 0.5618, "lr": 2.1571142262573457e-05, "epoch": 1.6336452864642776, "percentage": 54.44, "elapsed_time": "1:38:36", "remaining_time": "1:22:31", "throughput": 857.97, "total_tokens": 5076528}
|
|
{"current_steps": 900, "total_steps": 1644, "loss": 0.616, "lr": 2.133469169812879e-05, "epoch": 1.6427756220041085, "percentage": 54.74, "elapsed_time": "1:39:08", "remaining_time": "1:21:57", "throughput": 857.64, "total_tokens": 5101504}
|
|
{"current_steps": 905, "total_steps": 1644, "loss": 0.6574, "lr": 2.109857574708826e-05, "epoch": 1.6519059575439399, "percentage": 55.05, "elapsed_time": "1:39:42", "remaining_time": "1:21:24", "throughput": 857.4, "total_tokens": 5129104}
|
|
{"current_steps": 910, "total_steps": 1644, "loss": 0.6823, "lr": 2.086281596495434e-05, "epoch": 1.6610362930837708, "percentage": 55.35, "elapsed_time": "1:40:14", "remaining_time": "1:20:51", "throughput": 857.31, "total_tokens": 5156640}
|
|
{"current_steps": 915, "total_steps": 1644, "loss": 0.5728, "lr": 2.0627433874714115e-05, "epoch": 1.6701666286236019, "percentage": 55.66, "elapsed_time": "1:40:47", "remaining_time": "1:20:18", "throughput": 857.31, "total_tokens": 5184848}
|
|
{"current_steps": 920, "total_steps": 1644, "loss": 0.7025, "lr": 2.0392450964874415e-05, "epoch": 1.679296964163433, "percentage": 55.96, "elapsed_time": "1:41:20", "remaining_time": "1:19:45", "throughput": 857.28, "total_tokens": 5212928}
|
|
{"current_steps": 925, "total_steps": 1644, "loss": 0.5986, "lr": 2.015788868750009e-05, "epoch": 1.688427299703264, "percentage": 56.27, "elapsed_time": "1:41:54", "remaining_time": "1:19:12", "throughput": 857.53, "total_tokens": 5243568}
|
|
{"current_steps": 930, "total_steps": 1644, "loss": 0.6195, "lr": 1.9923768456255594e-05, "epoch": 1.6975576352430952, "percentage": 56.57, "elapsed_time": "1:42:26", "remaining_time": "1:18:39", "throughput": 857.32, "total_tokens": 5269840}
|
|
{"current_steps": 935, "total_steps": 1644, "loss": 0.6283, "lr": 1.969011164445011e-05, "epoch": 1.7066879707829261, "percentage": 56.87, "elapsed_time": "1:43:00", "remaining_time": "1:18:06", "throughput": 857.41, "total_tokens": 5299120}
|
|
{"current_steps": 940, "total_steps": 1644, "loss": 0.5767, "lr": 1.9456939583086303e-05, "epoch": 1.7158183063227574, "percentage": 57.18, "elapsed_time": "1:43:33", "remaining_time": "1:17:33", "throughput": 857.51, "total_tokens": 5328464}
|
|
{"current_steps": 945, "total_steps": 1644, "loss": 0.5237, "lr": 1.9224273558913024e-05, "epoch": 1.7249486418625883, "percentage": 57.48, "elapsed_time": "1:44:05", "remaining_time": "1:17:00", "throughput": 857.34, "total_tokens": 5354896}
|
|
{"current_steps": 950, "total_steps": 1644, "loss": 0.7184, "lr": 1.8992134812481915e-05, "epoch": 1.7340789774024197, "percentage": 57.79, "elapsed_time": "1:44:39", "remaining_time": "1:16:27", "throughput": 857.4, "total_tokens": 5383856}
|
|
{"current_steps": 955, "total_steps": 1644, "loss": 0.6595, "lr": 1.876054453620841e-05, "epoch": 1.7432093129422506, "percentage": 58.09, "elapsed_time": "1:45:12", "remaining_time": "1:15:54", "throughput": 857.47, "total_tokens": 5412864}
|
|
{"current_steps": 960, "total_steps": 1644, "loss": 0.6161, "lr": 1.852952387243698e-05, "epoch": 1.7523396484820817, "percentage": 58.39, "elapsed_time": "1:45:45", "remaining_time": "1:15:21", "throughput": 857.5, "total_tokens": 5441392}
|
|
{"current_steps": 965, "total_steps": 1644, "loss": 0.6076, "lr": 1.829909391151103e-05, "epoch": 1.7614699840219128, "percentage": 58.7, "elapsed_time": "1:46:19", "remaining_time": "1:14:48", "throughput": 857.63, "total_tokens": 5470928}
|
|
{"current_steps": 970, "total_steps": 1644, "loss": 0.5543, "lr": 1.8069275689847466e-05, "epoch": 1.770600319561744, "percentage": 59.0, "elapsed_time": "1:46:52", "remaining_time": "1:14:15", "throughput": 857.76, "total_tokens": 5500576}
|
|
{"current_steps": 975, "total_steps": 1644, "loss": 0.6496, "lr": 1.784009018801634e-05, "epoch": 1.779730655101575, "percentage": 59.31, "elapsed_time": "1:47:25", "remaining_time": "1:13:42", "throughput": 857.7, "total_tokens": 5528288}
|
|
{"current_steps": 980, "total_steps": 1644, "loss": 0.6315, "lr": 1.7611558328825384e-05, "epoch": 1.788860990641406, "percentage": 59.61, "elapsed_time": "1:47:58", "remaining_time": "1:13:09", "throughput": 857.79, "total_tokens": 5557472}
|
|
{"current_steps": 985, "total_steps": 1644, "loss": 0.5654, "lr": 1.738370097541e-05, "epoch": 1.7979913261812372, "percentage": 59.91, "elapsed_time": "1:48:31", "remaining_time": "1:12:36", "throughput": 857.71, "total_tokens": 5585120}
|
|
{"current_steps": 990, "total_steps": 1644, "loss": 0.5803, "lr": 1.7156538929328593e-05, "epoch": 1.8071216617210681, "percentage": 60.22, "elapsed_time": "1:49:04", "remaining_time": "1:12:03", "throughput": 857.74, "total_tokens": 5613760}
|
|
{"current_steps": 995, "total_steps": 1644, "loss": 0.5516, "lr": 1.6930092928663532e-05, "epoch": 1.8162519972608995, "percentage": 60.52, "elapsed_time": "1:49:38", "remaining_time": "1:11:30", "throughput": 857.88, "total_tokens": 5643504}
|
|
{"current_steps": 1000, "total_steps": 1644, "loss": 0.653, "lr": 1.6704383646127973e-05, "epoch": 1.8253823328007304, "percentage": 60.83, "elapsed_time": "1:50:11", "remaining_time": "1:10:57", "throughput": 857.9, "total_tokens": 5671936}
|
|
{"current_steps": 1005, "total_steps": 1644, "loss": 0.6456, "lr": 1.6479431687178584e-05, "epoch": 1.8345126683405615, "percentage": 61.13, "elapsed_time": "1:50:46", "remaining_time": "1:10:25", "throughput": 857.82, "total_tokens": 5701200}
|
|
{"current_steps": 1010, "total_steps": 1644, "loss": 0.6778, "lr": 1.6255257588134426e-05, "epoch": 1.8436430038803926, "percentage": 61.44, "elapsed_time": "1:51:18", "remaining_time": "1:09:52", "throughput": 857.68, "total_tokens": 5728032}
|
|
{"current_steps": 1015, "total_steps": 1644, "loss": 0.6779, "lr": 1.603188181430216e-05, "epoch": 1.8527733394202237, "percentage": 61.74, "elapsed_time": "1:51:51", "remaining_time": "1:09:19", "throughput": 857.65, "total_tokens": 5756080}
|
|
{"current_steps": 1020, "total_steps": 1644, "loss": 0.5039, "lr": 1.580932475810772e-05, "epoch": 1.8619036749600548, "percentage": 62.04, "elapsed_time": "1:52:25", "remaining_time": "1:08:46", "throughput": 857.77, "total_tokens": 5785760}
|
|
{"current_steps": 1025, "total_steps": 1644, "loss": 0.6694, "lr": 1.5587606737234654e-05, "epoch": 1.8710340104998857, "percentage": 62.35, "elapsed_time": "1:52:57", "remaining_time": "1:08:13", "throughput": 857.78, "total_tokens": 5813936}
|
|
{"current_steps": 1030, "total_steps": 1644, "loss": 0.5749, "lr": 1.5366747992769287e-05, "epoch": 1.880164346039717, "percentage": 62.65, "elapsed_time": "1:53:31", "remaining_time": "1:07:40", "throughput": 857.95, "total_tokens": 5844128}
|
|
{"current_steps": 1035, "total_steps": 1644, "loss": 0.5602, "lr": 1.5146768687352864e-05, "epoch": 1.889294681579548, "percentage": 62.96, "elapsed_time": "1:54:04", "remaining_time": "1:07:07", "throughput": 857.95, "total_tokens": 5872512}
|
|
{"current_steps": 1040, "total_steps": 1644, "loss": 0.645, "lr": 1.4927688903340836e-05, "epoch": 1.8984250171193793, "percentage": 63.26, "elapsed_time": "1:54:37", "remaining_time": "1:06:33", "throughput": 857.78, "total_tokens": 5898992}
|
|
{"current_steps": 1045, "total_steps": 1644, "loss": 0.6209, "lr": 1.4709528640969552e-05, "epoch": 1.9075553526592102, "percentage": 63.56, "elapsed_time": "1:55:10", "remaining_time": "1:06:01", "throughput": 858.0, "total_tokens": 5929632}
|
|
{"current_steps": 1050, "total_steps": 1644, "loss": 0.5908, "lr": 1.4492307816530375e-05, "epoch": 1.9166856881990413, "percentage": 63.87, "elapsed_time": "1:55:43", "remaining_time": "1:05:28", "throughput": 857.9, "total_tokens": 5956832}
|
|
{"current_steps": 1055, "total_steps": 1644, "loss": 0.5957, "lr": 1.4276046260551462e-05, "epoch": 1.9258160237388724, "percentage": 64.17, "elapsed_time": "1:56:16", "remaining_time": "1:04:54", "throughput": 857.91, "total_tokens": 5985104}
|
|
{"current_steps": 1060, "total_steps": 1644, "loss": 0.6543, "lr": 1.4060763715987418e-05, "epoch": 1.9349463592787035, "percentage": 64.48, "elapsed_time": "1:56:48", "remaining_time": "1:04:21", "throughput": 857.7, "total_tokens": 6010992}
|
|
{"current_steps": 1065, "total_steps": 1644, "loss": 0.5055, "lr": 1.3846479836416929e-05, "epoch": 1.9440766948185346, "percentage": 64.78, "elapsed_time": "1:57:22", "remaining_time": "1:03:48", "throughput": 857.84, "total_tokens": 6041008}
|
|
{"current_steps": 1070, "total_steps": 1644, "loss": 0.5246, "lr": 1.3633214184248521e-05, "epoch": 1.9532070303583655, "percentage": 65.09, "elapsed_time": "1:57:55", "remaining_time": "1:03:15", "throughput": 857.97, "total_tokens": 6070832}
|
|
{"current_steps": 1075, "total_steps": 1644, "loss": 0.5412, "lr": 1.342098622893469e-05, "epoch": 1.9623373658981969, "percentage": 65.39, "elapsed_time": "1:58:29", "remaining_time": "1:02:42", "throughput": 858.06, "total_tokens": 6100064}
|
|
{"current_steps": 1080, "total_steps": 1644, "loss": 0.624, "lr": 1.3209815345194496e-05, "epoch": 1.9714677014380277, "percentage": 65.69, "elapsed_time": "1:59:01", "remaining_time": "1:02:09", "throughput": 857.94, "total_tokens": 6127088}
|
|
{"current_steps": 1085, "total_steps": 1644, "loss": 0.5854, "lr": 1.2999720811244767e-05, "epoch": 1.980598036977859, "percentage": 66.0, "elapsed_time": "1:59:34", "remaining_time": "1:01:36", "throughput": 857.89, "total_tokens": 6154768}
|
|
{"current_steps": 1090, "total_steps": 1644, "loss": 0.5972, "lr": 1.2790721807040216e-05, "epoch": 1.98972837251769, "percentage": 66.3, "elapsed_time": "2:00:06", "remaining_time": "1:01:02", "throughput": 857.79, "total_tokens": 6181824}
|
|
{"current_steps": 1095, "total_steps": 1644, "loss": 0.5627, "lr": 1.2582837412522418e-05, "epoch": 1.998858708057521, "percentage": 66.61, "elapsed_time": "2:00:40", "remaining_time": "1:00:30", "throughput": 857.96, "total_tokens": 6211904}
|
|
{"current_steps": 1100, "total_steps": 1644, "loss": 0.544, "lr": 1.2376086605877976e-05, "epoch": 2.0073042684318647, "percentage": 66.91, "elapsed_time": "2:01:10", "remaining_time": "0:59:55", "throughput": 857.97, "total_tokens": 6238272}
|
|
{"current_steps": 1105, "total_steps": 1644, "loss": 0.4701, "lr": 1.2170488261805978e-05, "epoch": 2.016434603971696, "percentage": 67.21, "elapsed_time": "2:01:45", "remaining_time": "0:59:23", "throughput": 857.99, "total_tokens": 6268288}
|
|
{"current_steps": 1110, "total_steps": 1644, "loss": 0.4359, "lr": 1.1966061149794846e-05, "epoch": 2.025564939511527, "percentage": 67.52, "elapsed_time": "2:02:19", "remaining_time": "0:58:51", "throughput": 858.21, "total_tokens": 6299168}
|
|
{"current_steps": 1115, "total_steps": 1644, "loss": 0.4436, "lr": 1.176282393240888e-05, "epoch": 2.0346952750513583, "percentage": 67.82, "elapsed_time": "2:02:53", "remaining_time": "0:58:18", "throughput": 858.35, "total_tokens": 6329296}
|
|
{"current_steps": 1120, "total_steps": 1644, "loss": 0.5898, "lr": 1.1560795163584492e-05, "epoch": 2.043825610591189, "percentage": 68.13, "elapsed_time": "2:03:26", "remaining_time": "0:57:45", "throughput": 858.3, "total_tokens": 6356992}
|
|
{"current_steps": 1125, "total_steps": 1644, "loss": 0.5882, "lr": 1.1359993286936382e-05, "epoch": 2.0529559461310205, "percentage": 68.43, "elapsed_time": "2:03:58", "remaining_time": "0:57:11", "throughput": 858.05, "total_tokens": 6382256}
|
|
{"current_steps": 1130, "total_steps": 1644, "loss": 0.4388, "lr": 1.1160436634073786e-05, "epoch": 2.0620862816708514, "percentage": 68.73, "elapsed_time": "2:04:30", "remaining_time": "0:56:38", "throughput": 858.0, "total_tokens": 6410016}
|
|
{"current_steps": 1135, "total_steps": 1644, "loss": 0.5827, "lr": 1.0962143422926929e-05, "epoch": 2.0712166172106823, "percentage": 69.04, "elapsed_time": "2:05:04", "remaining_time": "0:56:05", "throughput": 858.03, "total_tokens": 6438768}
|
|
{"current_steps": 1140, "total_steps": 1644, "loss": 0.5261, "lr": 1.0765131756083899e-05, "epoch": 2.0803469527505136, "percentage": 69.34, "elapsed_time": "2:05:36", "remaining_time": "0:55:32", "throughput": 857.97, "total_tokens": 6466400}
|
|
{"current_steps": 1145, "total_steps": 1644, "loss": 0.5661, "lr": 1.0569419619138012e-05, "epoch": 2.0894772882903445, "percentage": 69.65, "elapsed_time": "2:06:09", "remaining_time": "0:54:58", "throughput": 857.88, "total_tokens": 6493488}
|
|
{"current_steps": 1150, "total_steps": 1644, "loss": 0.538, "lr": 1.0375024879045889e-05, "epoch": 2.098607623830176, "percentage": 69.95, "elapsed_time": "2:06:41", "remaining_time": "0:54:25", "throughput": 857.82, "total_tokens": 6521104}
|
|
{"current_steps": 1155, "total_steps": 1644, "loss": 0.7164, "lr": 1.0181965282496289e-05, "epoch": 2.1077379593700067, "percentage": 70.26, "elapsed_time": "2:07:14", "remaining_time": "0:53:52", "throughput": 857.75, "total_tokens": 6548832}
|
|
{"current_steps": 1160, "total_steps": 1644, "loss": 0.5611, "lr": 9.990258454290055e-06, "epoch": 2.116868294909838, "percentage": 70.56, "elapsed_time": "2:07:48", "remaining_time": "0:53:19", "throughput": 857.8, "total_tokens": 6577648}
|
|
{"current_steps": 1165, "total_steps": 1644, "loss": 0.5341, "lr": 9.799921895731062e-06, "epoch": 2.125998630449669, "percentage": 70.86, "elapsed_time": "2:08:20", "remaining_time": "0:52:46", "throughput": 857.7, "total_tokens": 6604720}
|
|
{"current_steps": 1170, "total_steps": 1644, "loss": 0.4899, "lr": 9.610972983028493e-06, "epoch": 2.1351289659895003, "percentage": 71.17, "elapsed_time": "2:08:52", "remaining_time": "0:52:12", "throughput": 857.6, "total_tokens": 6631696}
|
|
{"current_steps": 1175, "total_steps": 1644, "loss": 0.6115, "lr": 9.423428965710554e-06, "epoch": 2.144259301529331, "percentage": 71.47, "elapsed_time": "2:09:25", "remaining_time": "0:51:39", "throughput": 857.59, "total_tokens": 6659728}
|
|
{"current_steps": 1180, "total_steps": 1644, "loss": 0.5713, "lr": 9.237306965049677e-06, "epoch": 2.153389637069162, "percentage": 71.78, "elapsed_time": "2:09:59", "remaining_time": "0:51:06", "throughput": 857.66, "total_tokens": 6688928}
|
|
{"current_steps": 1185, "total_steps": 1644, "loss": 0.5144, "lr": 9.05262397249955e-06, "epoch": 2.1625199726089934, "percentage": 72.08, "elapsed_time": "2:10:32", "remaining_time": "0:50:33", "throughput": 857.7, "total_tokens": 6717488}
|
|
{"current_steps": 1190, "total_steps": 1644, "loss": 0.5139, "lr": 8.869396848143893e-06, "epoch": 2.1716503081488243, "percentage": 72.38, "elapsed_time": "2:11:05", "remaining_time": "0:50:00", "throughput": 857.78, "total_tokens": 6746864}
|
|
{"current_steps": 1195, "total_steps": 1644, "loss": 0.5763, "lr": 8.687642319157279e-06, "epoch": 2.1807806436886557, "percentage": 72.69, "elapsed_time": "2:11:38", "remaining_time": "0:49:27", "throughput": 857.78, "total_tokens": 6775216}
|
|
{"current_steps": 1200, "total_steps": 1644, "loss": 0.5669, "lr": 8.507376978278053e-06, "epoch": 2.1899109792284865, "percentage": 72.99, "elapsed_time": "2:12:12", "remaining_time": "0:48:55", "throughput": 858.01, "total_tokens": 6806496}
|
|
{"current_steps": 1205, "total_steps": 1644, "loss": 0.5508, "lr": 8.328617282293591e-06, "epoch": 2.199041314768318, "percentage": 73.3, "elapsed_time": "2:12:47", "remaining_time": "0:48:22", "throughput": 857.95, "total_tokens": 6835744}
|
|
{"current_steps": 1210, "total_steps": 1644, "loss": 0.5538, "lr": 8.151379550537894e-06, "epoch": 2.2081716503081488, "percentage": 73.6, "elapsed_time": "2:13:20", "remaining_time": "0:47:49", "throughput": 858.01, "total_tokens": 6864560}
|
|
{"current_steps": 1215, "total_steps": 1644, "loss": 0.4806, "lr": 7.975679963401772e-06, "epoch": 2.21730198584798, "percentage": 73.91, "elapsed_time": "2:13:53", "remaining_time": "0:47:16", "throughput": 858.04, "total_tokens": 6893360}
|
|
{"current_steps": 1220, "total_steps": 1644, "loss": 0.4594, "lr": 7.801534560855703e-06, "epoch": 2.226432321387811, "percentage": 74.21, "elapsed_time": "2:14:27", "remaining_time": "0:46:43", "throughput": 858.1, "total_tokens": 6922336}
|
|
{"current_steps": 1225, "total_steps": 1644, "loss": 0.4625, "lr": 7.628959240985514e-06, "epoch": 2.235562656927642, "percentage": 74.51, "elapsed_time": "2:15:00", "remaining_time": "0:46:10", "throughput": 858.25, "total_tokens": 6952464}
|
|
{"current_steps": 1230, "total_steps": 1644, "loss": 0.5248, "lr": 7.457969758541009e-06, "epoch": 2.2446929924674732, "percentage": 74.82, "elapsed_time": "2:15:32", "remaining_time": "0:45:37", "throughput": 858.06, "total_tokens": 6978480}
|
|
{"current_steps": 1235, "total_steps": 1644, "loss": 0.5796, "lr": 7.288581723497689e-06, "epoch": 2.253823328007304, "percentage": 75.12, "elapsed_time": "2:16:05", "remaining_time": "0:45:04", "throughput": 858.05, "total_tokens": 7006576}
|
|
{"current_steps": 1240, "total_steps": 1644, "loss": 0.4509, "lr": 7.12081059963168e-06, "epoch": 2.2629536635471355, "percentage": 75.43, "elapsed_time": "2:16:38", "remaining_time": "0:44:31", "throughput": 858.04, "total_tokens": 7034848}
|
|
{"current_steps": 1245, "total_steps": 1644, "loss": 0.4935, "lr": 6.954671703108034e-06, "epoch": 2.2720839990869663, "percentage": 75.73, "elapsed_time": "2:17:12", "remaining_time": "0:43:58", "throughput": 858.16, "total_tokens": 7064656}
|
|
{"current_steps": 1250, "total_steps": 1644, "loss": 0.5073, "lr": 6.790180201082439e-06, "epoch": 2.2812143346267977, "percentage": 76.03, "elapsed_time": "2:17:45", "remaining_time": "0:43:25", "throughput": 858.2, "total_tokens": 7093536}
|
|
{"current_steps": 1255, "total_steps": 1644, "loss": 0.4892, "lr": 6.627351110316635e-06, "epoch": 2.2903446701666286, "percentage": 76.34, "elapsed_time": "2:18:19", "remaining_time": "0:42:52", "throughput": 858.22, "total_tokens": 7122352}
|
|
{"current_steps": 1260, "total_steps": 1644, "loss": 0.5268, "lr": 6.466199295807471e-06, "epoch": 2.2994750057064595, "percentage": 76.64, "elapsed_time": "2:18:51", "remaining_time": "0:42:19", "throughput": 858.15, "total_tokens": 7149840}
|
|
{"current_steps": 1265, "total_steps": 1644, "loss": 0.5226, "lr": 6.306739469429859e-06, "epoch": 2.308605341246291, "percentage": 76.95, "elapsed_time": "2:19:23", "remaining_time": "0:41:45", "throughput": 857.94, "total_tokens": 7175312}
|
|
{"current_steps": 1270, "total_steps": 1644, "loss": 0.4098, "lr": 6.1489861885936805e-06, "epoch": 2.317735676786122, "percentage": 77.25, "elapsed_time": "2:19:57", "remaining_time": "0:41:12", "throughput": 858.07, "total_tokens": 7205408}
|
|
{"current_steps": 1275, "total_steps": 1644, "loss": 0.5064, "lr": 5.992953854914838e-06, "epoch": 2.326866012325953, "percentage": 77.55, "elapsed_time": "2:20:28", "remaining_time": "0:40:39", "throughput": 857.86, "total_tokens": 7230896}
|
|
{"current_steps": 1280, "total_steps": 1644, "loss": 0.486, "lr": 5.838656712900487e-06, "epoch": 2.335996347865784, "percentage": 77.86, "elapsed_time": "2:21:01", "remaining_time": "0:40:06", "throughput": 857.82, "total_tokens": 7258640}
|
|
{"current_steps": 1285, "total_steps": 1644, "loss": 0.5659, "lr": 5.686108848648624e-06, "epoch": 2.3451266834056153, "percentage": 78.16, "elapsed_time": "2:21:34", "remaining_time": "0:39:33", "throughput": 857.87, "total_tokens": 7287552}
|
|
{"current_steps": 1290, "total_steps": 1644, "loss": 0.5572, "lr": 5.535324188562157e-06, "epoch": 2.354257018945446, "percentage": 78.47, "elapsed_time": "2:22:07", "remaining_time": "0:39:00", "throughput": 857.82, "total_tokens": 7315152}
|
|
{"current_steps": 1295, "total_steps": 1644, "loss": 0.5891, "lr": 5.386316498077492e-06, "epoch": 2.3633873544852775, "percentage": 78.77, "elapsed_time": "2:22:39", "remaining_time": "0:38:26", "throughput": 857.72, "total_tokens": 7341792}
|
|
{"current_steps": 1300, "total_steps": 1644, "loss": 0.5121, "lr": 5.239099380407916e-06, "epoch": 2.3725176900251084, "percentage": 79.08, "elapsed_time": "2:23:12", "remaining_time": "0:37:53", "throughput": 857.66, "total_tokens": 7369360}
|
|
{"current_steps": 1305, "total_steps": 1644, "loss": 0.4585, "lr": 5.09368627530169e-06, "epoch": 2.3816480255649397, "percentage": 79.38, "elapsed_time": "2:23:47", "remaining_time": "0:37:21", "throughput": 857.71, "total_tokens": 7399936}
|
|
{"current_steps": 1310, "total_steps": 1644, "loss": 0.5115, "lr": 4.950090457815129e-06, "epoch": 2.3907783611047706, "percentage": 79.68, "elapsed_time": "2:24:19", "remaining_time": "0:36:47", "throughput": 857.56, "total_tokens": 7426080}
|
|
{"current_steps": 1315, "total_steps": 1644, "loss": 0.3663, "lr": 4.808325037100691e-06, "epoch": 2.3999086966446015, "percentage": 79.99, "elapsed_time": "2:25:01", "remaining_time": "0:36:17", "throughput": 856.67, "total_tokens": 7454432}
|
|
{"current_steps": 1320, "total_steps": 1644, "loss": 0.4918, "lr": 4.6684029552101886e-06, "epoch": 2.409039032184433, "percentage": 80.29, "elapsed_time": "2:25:35", "remaining_time": "0:35:44", "throughput": 856.82, "total_tokens": 7484848}
|
|
{"current_steps": 1325, "total_steps": 1644, "loss": 0.4168, "lr": 4.530336985913333e-06, "epoch": 2.4181693677242637, "percentage": 80.6, "elapsed_time": "2:26:09", "remaining_time": "0:35:11", "throughput": 856.92, "total_tokens": 7514592}
|
|
{"current_steps": 1330, "total_steps": 1644, "loss": 0.4658, "lr": 4.394139733531555e-06, "epoch": 2.427299703264095, "percentage": 80.9, "elapsed_time": "2:26:43", "remaining_time": "0:34:38", "throughput": 857.11, "total_tokens": 7545680}
|
|
{"current_steps": 1335, "total_steps": 1644, "loss": 0.4081, "lr": 4.259823631787346e-06, "epoch": 2.436430038803926, "percentage": 81.2, "elapsed_time": "2:27:17", "remaining_time": "0:34:05", "throughput": 857.2, "total_tokens": 7575472}
|
|
{"current_steps": 1340, "total_steps": 1644, "loss": 0.4739, "lr": 4.127400942669141e-06, "epoch": 2.4455603743437573, "percentage": 81.51, "elapsed_time": "2:27:50", "remaining_time": "0:33:32", "throughput": 857.23, "total_tokens": 7604016}
|
|
{"current_steps": 1345, "total_steps": 1644, "loss": 0.3149, "lr": 3.996883755311917e-06, "epoch": 2.454690709883588, "percentage": 81.81, "elapsed_time": "2:28:25", "remaining_time": "0:32:59", "throughput": 857.5, "total_tokens": 7636112}
|
|
{"current_steps": 1350, "total_steps": 1644, "loss": 0.565, "lr": 3.868283984893542e-06, "epoch": 2.463821045423419, "percentage": 82.12, "elapsed_time": "2:28:58", "remaining_time": "0:32:26", "throughput": 857.55, "total_tokens": 7665152}
|
|
{"current_steps": 1355, "total_steps": 1644, "loss": 0.4656, "lr": 3.741613371547023e-06, "epoch": 2.4729513809632504, "percentage": 82.42, "elapsed_time": "2:29:30", "remaining_time": "0:31:53", "throughput": 857.47, "total_tokens": 7692112}
|
|
{"current_steps": 1360, "total_steps": 1644, "loss": 0.4552, "lr": 3.6168834792887103e-06, "epoch": 2.4820817165030817, "percentage": 82.73, "elapsed_time": "2:30:03", "remaining_time": "0:31:20", "throughput": 857.44, "total_tokens": 7720064}
|
|
{"current_steps": 1365, "total_steps": 1644, "loss": 0.4571, "lr": 3.494105694962596e-06, "epoch": 2.4912120520429126, "percentage": 83.03, "elapsed_time": "2:30:37", "remaining_time": "0:30:47", "throughput": 857.63, "total_tokens": 7751040}
|
|
{"current_steps": 1370, "total_steps": 1644, "loss": 0.5344, "lr": 3.373291227200806e-06, "epoch": 2.5003423875827435, "percentage": 83.33, "elapsed_time": "2:31:09", "remaining_time": "0:30:13", "throughput": 857.46, "total_tokens": 7776944}
|
|
{"current_steps": 1375, "total_steps": 1644, "loss": 0.501, "lr": 3.2544511054003246e-06, "epoch": 2.509472723122575, "percentage": 83.64, "elapsed_time": "2:31:42", "remaining_time": "0:29:40", "throughput": 857.44, "total_tokens": 7804880}
|
|
{"current_steps": 1380, "total_steps": 1644, "loss": 0.5723, "lr": 3.1375961787160983e-06, "epoch": 2.5186030586624057, "percentage": 83.94, "elapsed_time": "2:32:15", "remaining_time": "0:29:07", "throughput": 857.51, "total_tokens": 7834144}
|
|
{"current_steps": 1385, "total_steps": 1644, "loss": 0.5347, "lr": 3.0227371150706035e-06, "epoch": 2.527733394202237, "percentage": 84.25, "elapsed_time": "2:32:48", "remaining_time": "0:28:34", "throughput": 857.49, "total_tokens": 7862112}
|
|
{"current_steps": 1390, "total_steps": 1644, "loss": 0.4727, "lr": 2.9098844001799407e-06, "epoch": 2.536863729742068, "percentage": 84.55, "elapsed_time": "2:33:21", "remaining_time": "0:28:01", "throughput": 857.44, "total_tokens": 7889648}
|
|
{"current_steps": 1395, "total_steps": 1644, "loss": 0.6187, "lr": 2.7990483365965825e-06, "epoch": 2.5459940652818993, "percentage": 84.85, "elapsed_time": "2:33:54", "remaining_time": "0:27:28", "throughput": 857.44, "total_tokens": 7917840}
|
|
{"current_steps": 1400, "total_steps": 1644, "loss": 0.5945, "lr": 2.6902390427688273e-06, "epoch": 2.55512440082173, "percentage": 85.16, "elapsed_time": "2:34:27", "remaining_time": "0:26:55", "throughput": 857.44, "total_tokens": 7945968}
|
|
{"current_steps": 1405, "total_steps": 1644, "loss": 0.5123, "lr": 2.5834664521170504e-06, "epoch": 2.564254736361561, "percentage": 85.46, "elapsed_time": "2:35:02", "remaining_time": "0:26:22", "throughput": 857.49, "total_tokens": 7976608}
|
|
{"current_steps": 1410, "total_steps": 1644, "loss": 0.4564, "lr": 2.4787403121268955e-06, "epoch": 2.5733850719013924, "percentage": 85.77, "elapsed_time": "2:35:35", "remaining_time": "0:25:49", "throughput": 857.52, "total_tokens": 8005312}
|
|
{"current_steps": 1415, "total_steps": 1644, "loss": 0.5329, "lr": 2.3760701834593806e-06, "epoch": 2.5825154074412233, "percentage": 86.07, "elapsed_time": "2:36:07", "remaining_time": "0:25:16", "throughput": 857.44, "total_tokens": 8032320}
|
|
{"current_steps": 1420, "total_steps": 1644, "loss": 0.5803, "lr": 2.2754654390780924e-06, "epoch": 2.5916457429810547, "percentage": 86.37, "elapsed_time": "2:36:40", "remaining_time": "0:24:42", "throughput": 857.36, "total_tokens": 8059600}
|
|
{"current_steps": 1425, "total_steps": 1644, "loss": 0.4759, "lr": 2.1769352633935175e-06, "epoch": 2.6007760785208855, "percentage": 86.68, "elapsed_time": "2:37:14", "remaining_time": "0:24:09", "throughput": 857.53, "total_tokens": 8090544}
|
|
{"current_steps": 1430, "total_steps": 1644, "loss": 0.4964, "lr": 2.0804886514245726e-06, "epoch": 2.609906414060717, "percentage": 86.98, "elapsed_time": "2:37:47", "remaining_time": "0:23:36", "throughput": 857.44, "total_tokens": 8117472}
|
|
{"current_steps": 1435, "total_steps": 1644, "loss": 0.4652, "lr": 1.986134407977416e-06, "epoch": 2.6190367496005478, "percentage": 87.29, "elapsed_time": "2:38:19", "remaining_time": "0:23:03", "throughput": 857.43, "total_tokens": 8145360}
|
|
{"current_steps": 1440, "total_steps": 1644, "loss": 0.5859, "lr": 1.8938811468416695e-06, "epoch": 2.6281670851403787, "percentage": 87.59, "elapsed_time": "2:38:51", "remaining_time": "0:22:30", "throughput": 857.3, "total_tokens": 8171552}
|
|
{"current_steps": 1445, "total_steps": 1644, "loss": 0.6222, "lr": 1.8037372900040289e-06, "epoch": 2.63729742068021, "percentage": 87.9, "elapsed_time": "2:39:24", "remaining_time": "0:21:57", "throughput": 857.27, "total_tokens": 8199280}
|
|
{"current_steps": 1450, "total_steps": 1644, "loss": 0.3722, "lr": 1.7157110668794108e-06, "epoch": 2.6464277562200413, "percentage": 88.2, "elapsed_time": "2:39:56", "remaining_time": "0:21:23", "throughput": 857.22, "total_tokens": 8226656}
|
|
{"current_steps": 1455, "total_steps": 1644, "loss": 0.5299, "lr": 1.6298105135596569e-06, "epoch": 2.6555580917598722, "percentage": 88.5, "elapsed_time": "2:40:30", "remaining_time": "0:20:50", "throughput": 857.23, "total_tokens": 8255232}
|
|
{"current_steps": 1460, "total_steps": 1644, "loss": 0.447, "lr": 1.5460434720799278e-06, "epoch": 2.664688427299703, "percentage": 88.81, "elapsed_time": "2:41:02", "remaining_time": "0:20:17", "throughput": 857.12, "total_tokens": 8281744}
|
|
{"current_steps": 1465, "total_steps": 1644, "loss": 0.3965, "lr": 1.464417589702774e-06, "epoch": 2.6738187628395345, "percentage": 89.11, "elapsed_time": "2:41:35", "remaining_time": "0:19:44", "throughput": 857.14, "total_tokens": 8310384}
|
|
{"current_steps": 1470, "total_steps": 1644, "loss": 0.4579, "lr": 1.3849403182199988e-06, "epoch": 2.6829490983793653, "percentage": 89.42, "elapsed_time": "2:42:09", "remaining_time": "0:19:11", "throughput": 857.25, "total_tokens": 8340384}
|
|
{"current_steps": 1475, "total_steps": 1644, "loss": 0.5361, "lr": 1.3076189132723764e-06, "epoch": 2.6920794339191967, "percentage": 89.72, "elapsed_time": "2:42:41", "remaining_time": "0:18:38", "throughput": 857.23, "total_tokens": 8368224}
|
|
{"current_steps": 1480, "total_steps": 1644, "loss": 0.4439, "lr": 1.2324604336872658e-06, "epoch": 2.7012097694590276, "percentage": 90.02, "elapsed_time": "2:43:16", "remaining_time": "0:18:05", "throughput": 857.38, "total_tokens": 8398976}
|
|
{"current_steps": 1485, "total_steps": 1644, "loss": 0.3843, "lr": 1.159471740834195e-06, "epoch": 2.710340104998859, "percentage": 90.33, "elapsed_time": "2:43:48", "remaining_time": "0:17:32", "throughput": 857.3, "total_tokens": 8426000}
|
|
{"current_steps": 1490, "total_steps": 1644, "loss": 0.4191, "lr": 1.0886594979984816e-06, "epoch": 2.71947044053869, "percentage": 90.63, "elapsed_time": "2:44:20", "remaining_time": "0:16:59", "throughput": 857.21, "total_tokens": 8452800}
|
|
{"current_steps": 1495, "total_steps": 1644, "loss": 0.4898, "lr": 1.0200301697729204e-06, "epoch": 2.7286007760785207, "percentage": 90.94, "elapsed_time": "2:44:52", "remaining_time": "0:16:25", "throughput": 857.05, "total_tokens": 8478592}
|
|
{"current_steps": 1500, "total_steps": 1644, "loss": 0.4288, "lr": 9.535900214676097e-07, "epoch": 2.737731111618352, "percentage": 91.24, "elapsed_time": "2:45:25", "remaining_time": "0:15:52", "throughput": 857.0, "total_tokens": 8506240}
|
|
{"current_steps": 1505, "total_steps": 1644, "loss": 0.4114, "lr": 8.893451185379958e-07, "epoch": 2.746861447158183, "percentage": 91.55, "elapsed_time": "2:45:59", "remaining_time": "0:15:19", "throughput": 856.85, "total_tokens": 8533840}
|
|
{"current_steps": 1510, "total_steps": 1644, "loss": 0.4987, "lr": 8.273013260311379e-07, "epoch": 2.7559917826980143, "percentage": 91.85, "elapsed_time": "2:46:31", "remaining_time": "0:14:46", "throughput": 856.68, "total_tokens": 8559296}
|
|
{"current_steps": 1515, "total_steps": 1644, "loss": 0.4648, "lr": 7.674643080502724e-07, "epoch": 2.765122118237845, "percentage": 92.15, "elapsed_time": "2:59:21", "remaining_time": "0:15:16", "throughput": 798.02, "total_tokens": 8587664}
|
|
{"current_steps": 1520, "total_steps": 1644, "loss": 0.5213, "lr": 7.098395272377295e-07, "epoch": 2.7742524537776765, "percentage": 92.46, "elapsed_time": "2:59:53", "remaining_time": "0:14:40", "throughput": 798.11, "total_tokens": 8614480}
|
|
{"current_steps": 1525, "total_steps": 1644, "loss": 0.499, "lr": 6.544322442762318e-07, "epoch": 2.7833827893175074, "percentage": 92.76, "elapsed_time": "3:00:26", "remaining_time": "0:14:04", "throughput": 798.29, "total_tokens": 8642960}
|
|
{"current_steps": 1530, "total_steps": 1644, "loss": 0.4285, "lr": 6.012475174086485e-07, "epoch": 2.7925131248573383, "percentage": 93.07, "elapsed_time": "3:00:59", "remaining_time": "0:13:29", "throughput": 798.47, "total_tokens": 8671248}
|
|
{"current_steps": 1535, "total_steps": 1644, "loss": 0.4615, "lr": 5.502902019762002e-07, "epoch": 2.8016434603971696, "percentage": 93.37, "elapsed_time": "3:01:32", "remaining_time": "0:12:53", "throughput": 798.61, "total_tokens": 8698912}
|
|
{"current_steps": 1540, "total_steps": 1644, "loss": 0.4648, "lr": 5.015649499752279e-07, "epoch": 2.810773795937001, "percentage": 93.67, "elapsed_time": "3:02:05", "remaining_time": "0:12:17", "throughput": 798.77, "total_tokens": 8726896}
|
|
{"current_steps": 1545, "total_steps": 1644, "loss": 0.4858, "lr": 4.5507620963247954e-07, "epoch": 2.819904131476832, "percentage": 93.98, "elapsed_time": "3:02:36", "remaining_time": "0:11:42", "throughput": 798.76, "total_tokens": 8751920}
|
|
{"current_steps": 1550, "total_steps": 1644, "loss": 0.4944, "lr": 4.1082822499903253e-07, "epoch": 2.8290344670166627, "percentage": 94.28, "elapsed_time": "3:03:09", "remaining_time": "0:11:06", "throughput": 798.92, "total_tokens": 8780080}
|
|
{"current_steps": 1555, "total_steps": 1644, "loss": 0.4598, "lr": 3.6882503556285307e-07, "epoch": 2.838164802556494, "percentage": 94.59, "elapsed_time": "3:03:41", "remaining_time": "0:10:30", "throughput": 798.9, "total_tokens": 8804880}
|
|
{"current_steps": 1560, "total_steps": 1644, "loss": 0.4981, "lr": 3.290704758800139e-07, "epoch": 2.847295138096325, "percentage": 94.89, "elapsed_time": "3:04:15", "remaining_time": "0:09:55", "throughput": 799.16, "total_tokens": 8834736}
|
|
{"current_steps": 1565, "total_steps": 1644, "loss": 0.5183, "lr": 2.915681752246241e-07, "epoch": 2.8564254736361563, "percentage": 95.19, "elapsed_time": "3:04:47", "remaining_time": "0:09:19", "throughput": 799.31, "total_tokens": 8862544}
|
|
{"current_steps": 1570, "total_steps": 1644, "loss": 0.4789, "lr": 2.563215572575273e-07, "epoch": 2.865555809175987, "percentage": 95.5, "elapsed_time": "3:05:21", "remaining_time": "0:08:44", "throughput": 799.6, "total_tokens": 8892720}
|
|
{"current_steps": 1575, "total_steps": 1644, "loss": 0.4666, "lr": 2.2333383971372413e-07, "epoch": 2.8746861447158185, "percentage": 95.8, "elapsed_time": "3:05:53", "remaining_time": "0:08:08", "throughput": 799.65, "total_tokens": 8918880}
|
|
{"current_steps": 1580, "total_steps": 1644, "loss": 0.4199, "lr": 1.9260803410863226e-07, "epoch": 2.8838164802556494, "percentage": 96.11, "elapsed_time": "3:06:28", "remaining_time": "0:07:33", "throughput": 800.12, "total_tokens": 8952352}
|
|
{"current_steps": 1585, "total_steps": 1644, "loss": 0.4318, "lr": 1.641469454631561e-07, "epoch": 2.8929468157954803, "percentage": 96.41, "elapsed_time": "3:07:02", "remaining_time": "0:06:57", "throughput": 800.36, "total_tokens": 8981984}
|
|
{"current_steps": 1590, "total_steps": 1644, "loss": 0.36, "lr": 1.3795317204761128e-07, "epoch": 2.9020771513353116, "percentage": 96.72, "elapsed_time": "3:07:36", "remaining_time": "0:06:22", "throughput": 800.67, "total_tokens": 9012864}
|
|
{"current_steps": 1595, "total_steps": 1644, "loss": 0.4392, "lr": 1.140291051445197e-07, "epoch": 2.9112074868751425, "percentage": 97.02, "elapsed_time": "3:08:09", "remaining_time": "0:05:46", "throughput": 800.81, "total_tokens": 9040848}
|
|
{"current_steps": 1600, "total_steps": 1644, "loss": 0.4489, "lr": 9.237692883031502e-08, "epoch": 2.920337822414974, "percentage": 97.32, "elapsed_time": "3:08:43", "remaining_time": "0:05:11", "throughput": 801.1, "total_tokens": 9071104}
|
|
{"current_steps": 1605, "total_steps": 1644, "loss": 0.5492, "lr": 7.29986197759408e-08, "epoch": 2.9294681579548048, "percentage": 97.63, "elapsed_time": "3:09:18", "remaining_time": "0:04:36", "throughput": 801.33, "total_tokens": 9101904}
|
|
{"current_steps": 1610, "total_steps": 1644, "loss": 0.503, "lr": 5.589594706640055e-08, "epoch": 2.938598493494636, "percentage": 97.93, "elapsed_time": "3:09:52", "remaining_time": "0:04:00", "throughput": 801.57, "total_tokens": 9131728}
|
|
{"current_steps": 1615, "total_steps": 1644, "loss": 0.4689, "lr": 4.1070472039259065e-08, "epoch": 2.947728829034467, "percentage": 98.24, "elapsed_time": "3:10:26", "remaining_time": "0:03:25", "throughput": 801.85, "total_tokens": 9162144}
|
|
{"current_steps": 1620, "total_steps": 1644, "loss": 0.542, "lr": 2.8523548142103673e-08, "epoch": 2.956859164574298, "percentage": 98.54, "elapsed_time": "3:10:58", "remaining_time": "0:02:49", "throughput": 801.98, "total_tokens": 9189808}
|
|
{"current_steps": 1625, "total_steps": 1644, "loss": 0.3969, "lr": 1.825632080897366e-08, "epoch": 2.965989500114129, "percentage": 98.84, "elapsed_time": "3:11:32", "remaining_time": "0:02:14", "throughput": 802.24, "total_tokens": 9220032}
|
|
{"current_steps": 1630, "total_steps": 1644, "loss": 0.496, "lr": 1.026972735581333e-08, "epoch": 2.9751198356539605, "percentage": 99.15, "elapsed_time": "3:12:05", "remaining_time": "0:01:38", "throughput": 802.42, "total_tokens": 9248592}
|
|
{"current_steps": 1635, "total_steps": 1644, "loss": 0.5585, "lr": 4.564496894882142e-09, "epoch": 2.9842501711937914, "percentage": 99.45, "elapsed_time": "3:12:38", "remaining_time": "0:01:03", "throughput": 802.55, "total_tokens": 9276416}
|
|
{"current_steps": 1640, "total_steps": 1644, "loss": 0.4553, "lr": 1.1411502681996088e-09, "epoch": 2.9933805067336223, "percentage": 99.76, "elapsed_time": "3:13:12", "remaining_time": "0:00:28", "throughput": 802.8, "total_tokens": 9306352}
|
|
{"current_steps": 1644, "total_steps": 1644, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:13:38", "remaining_time": "0:00:00", "throughput": 802.91, "total_tokens": 9328224}
|