CityU-Zongxian's picture
Upload 13 files
85024f1 verified
{"current_steps": 1, "total_steps": 261, "loss": 0.6931, "accuracy": 0.0, "lr": 1.0000000000000002e-06, "epoch": 0.0038305003591094086, "percentage": 0.38, "elapsed_time": "0:01:32", "remaining_time": "6:39:23", "throughput": 3932.99, "total_tokens": 362496}
{"current_steps": 2, "total_steps": 261, "loss": 0.6931, "accuracy": 0.0, "lr": 2.0000000000000003e-06, "epoch": 0.007661000718218817, "percentage": 0.77, "elapsed_time": "0:02:59", "remaining_time": "6:27:48", "throughput": 3996.88, "total_tokens": 718144}
{"current_steps": 3, "total_steps": 261, "loss": 0.6962, "accuracy": 0.5234375, "lr": 3e-06, "epoch": 0.011491501077328227, "percentage": 1.15, "elapsed_time": "0:04:26", "remaining_time": "6:22:14", "throughput": 4032.52, "total_tokens": 1075392}
{"current_steps": 4, "total_steps": 261, "loss": 0.6938, "accuracy": 0.5390625, "lr": 4.000000000000001e-06, "epoch": 0.015322001436437634, "percentage": 1.53, "elapsed_time": "0:05:54", "remaining_time": "6:20:02", "throughput": 4029.42, "total_tokens": 1430080}
{"current_steps": 5, "total_steps": 261, "loss": 0.6831, "accuracy": 0.5859375, "lr": 5e-06, "epoch": 0.019152501795547044, "percentage": 1.92, "elapsed_time": "0:07:21", "remaining_time": "6:16:37", "throughput": 4047.38, "total_tokens": 1786304}
{"current_steps": 6, "total_steps": 261, "loss": 0.7014, "accuracy": 0.4765625, "lr": 6e-06, "epoch": 0.022983002154656453, "percentage": 2.3, "elapsed_time": "0:08:46", "remaining_time": "6:13:13", "throughput": 4047.36, "total_tokens": 2132544}
{"current_steps": 7, "total_steps": 261, "loss": 0.6961, "accuracy": 0.515625, "lr": 7e-06, "epoch": 0.02681350251376586, "percentage": 2.68, "elapsed_time": "0:10:13", "remaining_time": "6:10:59", "throughput": 4057.04, "total_tokens": 2488832}
{"current_steps": 8, "total_steps": 261, "loss": 0.6955, "accuracy": 0.46875, "lr": 8.000000000000001e-06, "epoch": 0.03064400287287527, "percentage": 3.07, "elapsed_time": "0:11:44", "remaining_time": "6:11:18", "throughput": 4049.34, "total_tokens": 2852544}
{"current_steps": 9, "total_steps": 261, "loss": 0.6871, "accuracy": 0.546875, "lr": 9e-06, "epoch": 0.03447450323198468, "percentage": 3.45, "elapsed_time": "0:13:13", "remaining_time": "6:10:05", "throughput": 4061.05, "total_tokens": 3220608}
{"current_steps": 10, "total_steps": 261, "loss": 0.6906, "accuracy": 0.5078125, "lr": 1e-05, "epoch": 0.03830500359109409, "percentage": 3.83, "elapsed_time": "0:14:44", "remaining_time": "6:09:49", "throughput": 4063.27, "total_tokens": 3592128}
{"current_steps": 11, "total_steps": 261, "loss": 0.6908, "accuracy": 0.515625, "lr": 9.999608360361114e-06, "epoch": 0.0421355039502035, "percentage": 4.21, "elapsed_time": "0:16:13", "remaining_time": "6:08:49", "throughput": 4078.66, "total_tokens": 3971392}
{"current_steps": 12, "total_steps": 261, "loss": 0.6946, "accuracy": 0.5078125, "lr": 9.998433502797097e-06, "epoch": 0.045966004309312906, "percentage": 4.6, "elapsed_time": "0:17:41", "remaining_time": "6:07:03", "throughput": 4077.39, "total_tokens": 4327552}
{"current_steps": 13, "total_steps": 261, "loss": 0.6772, "accuracy": 0.6171875, "lr": 9.996475611356265e-06, "epoch": 0.049796504668422316, "percentage": 4.98, "elapsed_time": "0:19:12", "remaining_time": "6:06:31", "throughput": 4078.51, "total_tokens": 4701568}
{"current_steps": 14, "total_steps": 261, "loss": 0.6716, "accuracy": 0.6328125, "lr": 9.993734992753777e-06, "epoch": 0.05362700502753172, "percentage": 5.36, "elapsed_time": "0:20:39", "remaining_time": "6:04:26", "throughput": 4079.84, "total_tokens": 5056448}
{"current_steps": 15, "total_steps": 261, "loss": 0.6834, "accuracy": 0.5546875, "lr": 9.990212076323587e-06, "epoch": 0.05745750538664113, "percentage": 5.75, "elapsed_time": "0:22:03", "remaining_time": "6:01:40", "throughput": 4084.84, "total_tokens": 5405056}
{"current_steps": 16, "total_steps": 261, "loss": 0.673, "accuracy": 0.6484375, "lr": 9.98590741395118e-06, "epoch": 0.06128800574575054, "percentage": 6.13, "elapsed_time": "0:23:30", "remaining_time": "5:59:59", "throughput": 4082.25, "total_tokens": 5758464}
{"current_steps": 17, "total_steps": 261, "loss": 0.6778, "accuracy": 0.5859375, "lr": 9.980821679987125e-06, "epoch": 0.06511850610485995, "percentage": 6.51, "elapsed_time": "0:24:56", "remaining_time": "5:58:00", "throughput": 4087.02, "total_tokens": 6116480}
{"current_steps": 18, "total_steps": 261, "loss": 0.6699, "accuracy": 0.671875, "lr": 9.974955671141425e-06, "epoch": 0.06894900646396936, "percentage": 6.9, "elapsed_time": "0:26:26", "remaining_time": "5:56:59", "throughput": 4085.86, "total_tokens": 6482624}
{"current_steps": 19, "total_steps": 261, "loss": 0.668, "accuracy": 0.625, "lr": 9.968310306358715e-06, "epoch": 0.07277950682307877, "percentage": 7.28, "elapsed_time": "0:27:52", "remaining_time": "5:55:08", "throughput": 4086.03, "total_tokens": 6835712}
{"current_steps": 20, "total_steps": 261, "loss": 0.664, "accuracy": 0.609375, "lr": 9.960886626674302e-06, "epoch": 0.07661000718218818, "percentage": 7.66, "elapsed_time": "0:29:21", "remaining_time": "5:53:43", "throughput": 4078.29, "total_tokens": 7183040}
{"current_steps": 21, "total_steps": 261, "loss": 0.6632, "accuracy": 0.6640625, "lr": 9.952685795051078e-06, "epoch": 0.08044050754129758, "percentage": 8.05, "elapsed_time": "0:30:53", "remaining_time": "5:52:59", "throughput": 4075.03, "total_tokens": 7552000}
{"current_steps": 22, "total_steps": 261, "loss": 0.6619, "accuracy": 0.671875, "lr": 9.943709096197334e-06, "epoch": 0.084271007900407, "percentage": 8.43, "elapsed_time": "0:32:23", "remaining_time": "5:51:55", "throughput": 4074.12, "total_tokens": 7918784}
{"current_steps": 23, "total_steps": 261, "loss": 0.6536, "accuracy": 0.6640625, "lr": 9.933957936365515e-06, "epoch": 0.0881015082595164, "percentage": 8.81, "elapsed_time": "0:33:50", "remaining_time": "5:50:07", "throughput": 4076.26, "total_tokens": 8275392}
{"current_steps": 24, "total_steps": 261, "loss": 0.6412, "accuracy": 0.7265625, "lr": 9.9234338431319e-06, "epoch": 0.09193200861862581, "percentage": 9.2, "elapsed_time": "0:35:15", "remaining_time": "5:48:12", "throughput": 4079.58, "total_tokens": 8630976}
{"current_steps": 25, "total_steps": 261, "loss": 0.6345, "accuracy": 0.7265625, "lr": 9.912138465157325e-06, "epoch": 0.09576250897773522, "percentage": 9.58, "elapsed_time": "0:36:44", "remaining_time": "5:46:52", "throughput": 4079.71, "total_tokens": 8994496}
{"current_steps": 26, "total_steps": 261, "loss": 0.6366, "accuracy": 0.7421875, "lr": 9.900073571928887e-06, "epoch": 0.09959300933684463, "percentage": 9.96, "elapsed_time": "0:38:15", "remaining_time": "5:45:44", "throughput": 4079.68, "total_tokens": 9363648}
{"current_steps": 27, "total_steps": 261, "loss": 0.6203, "accuracy": 0.7265625, "lr": 9.887241053482756e-06, "epoch": 0.10342350969595403, "percentage": 10.34, "elapsed_time": "0:39:42", "remaining_time": "5:44:04", "throughput": 4078.96, "total_tokens": 9716544}
{"current_steps": 28, "total_steps": 261, "loss": 0.5958, "accuracy": 0.828125, "lr": 9.87364292010809e-06, "epoch": 0.10725401005506344, "percentage": 10.73, "elapsed_time": "0:41:06", "remaining_time": "5:42:01", "throughput": 4080.4, "total_tokens": 10062592}
{"current_steps": 29, "total_steps": 261, "loss": 0.6147, "accuracy": 0.7265625, "lr": 9.859281302032107e-06, "epoch": 0.11108451041417285, "percentage": 11.11, "elapsed_time": "0:42:32", "remaining_time": "5:40:18", "throughput": 4081.14, "total_tokens": 10416320}
{"current_steps": 30, "total_steps": 261, "loss": 0.6035, "accuracy": 0.796875, "lr": 9.844158449086372e-06, "epoch": 0.11491501077328226, "percentage": 11.49, "elapsed_time": "0:44:03", "remaining_time": "5:39:16", "throughput": 4079.92, "total_tokens": 10785856}
{"current_steps": 31, "total_steps": 261, "loss": 0.5897, "accuracy": 0.7578125, "lr": 9.828276730354353e-06, "epoch": 0.11874551113239167, "percentage": 11.88, "elapsed_time": "0:45:32", "remaining_time": "5:37:55", "throughput": 4080.34, "total_tokens": 11150656}
{"current_steps": 32, "total_steps": 261, "loss": 0.564, "accuracy": 0.8046875, "lr": 9.811638633800287e-06, "epoch": 0.12257601149150107, "percentage": 12.26, "elapsed_time": "0:46:56", "remaining_time": "5:35:55", "throughput": 4080.88, "total_tokens": 11493568}
{"current_steps": 33, "total_steps": 261, "loss": 0.5837, "accuracy": 0.75, "lr": 9.794246765879421e-06, "epoch": 0.1264065118506105, "percentage": 12.64, "elapsed_time": "0:48:26", "remaining_time": "5:34:38", "throughput": 4081.79, "total_tokens": 11861824}
{"current_steps": 34, "total_steps": 261, "loss": 0.5788, "accuracy": 0.7578125, "lr": 9.776103851129706e-06, "epoch": 0.1302370122097199, "percentage": 13.03, "elapsed_time": "0:49:55", "remaining_time": "5:33:22", "throughput": 4082.18, "total_tokens": 12229824}
{"current_steps": 35, "total_steps": 261, "loss": 0.5352, "accuracy": 0.8359375, "lr": 9.757212731744973e-06, "epoch": 0.13406751256882932, "percentage": 13.41, "elapsed_time": "0:51:30", "remaining_time": "5:32:36", "throughput": 4080.34, "total_tokens": 12610880}
{"current_steps": 36, "total_steps": 261, "loss": 0.5433, "accuracy": 0.8359375, "lr": 9.737576367129694e-06, "epoch": 0.1378980129279387, "percentage": 13.79, "elapsed_time": "0:52:56", "remaining_time": "5:30:52", "throughput": 4079.69, "total_tokens": 12958592}
{"current_steps": 37, "total_steps": 261, "loss": 0.554, "accuracy": 0.7265625, "lr": 9.717197833435367e-06, "epoch": 0.1417285132870481, "percentage": 14.18, "elapsed_time": "0:54:21", "remaining_time": "5:29:07", "throughput": 4080.53, "total_tokens": 13310336}
{"current_steps": 38, "total_steps": 261, "loss": 0.5275, "accuracy": 0.8046875, "lr": 9.696080323078621e-06, "epoch": 0.14555901364615753, "percentage": 14.56, "elapsed_time": "0:55:54", "remaining_time": "5:28:08", "throughput": 4078.15, "total_tokens": 13681920}
{"current_steps": 39, "total_steps": 261, "loss": 0.5439, "accuracy": 0.7890625, "lr": 9.67422714424111e-06, "epoch": 0.14938951400526693, "percentage": 14.94, "elapsed_time": "0:57:21", "remaining_time": "5:26:30", "throughput": 4077.67, "total_tokens": 14033792}
{"current_steps": 40, "total_steps": 261, "loss": 0.5058, "accuracy": 0.8515625, "lr": 9.651641720351262e-06, "epoch": 0.15322001436437635, "percentage": 15.33, "elapsed_time": "0:58:46", "remaining_time": "5:24:45", "throughput": 4080.71, "total_tokens": 14392064}
{"current_steps": 41, "total_steps": 261, "loss": 0.5153, "accuracy": 0.8125, "lr": 9.628327589547977e-06, "epoch": 0.15705051472348575, "percentage": 15.71, "elapsed_time": "1:00:13", "remaining_time": "5:23:10", "throughput": 4081.82, "total_tokens": 14750144}
{"current_steps": 42, "total_steps": 261, "loss": 0.5011, "accuracy": 0.8515625, "lr": 9.604288404126362e-06, "epoch": 0.16088101508259517, "percentage": 16.09, "elapsed_time": "1:01:41", "remaining_time": "5:21:41", "throughput": 4083.58, "total_tokens": 15115648}
{"current_steps": 43, "total_steps": 261, "loss": 0.5145, "accuracy": 0.875, "lr": 9.579527929965581e-06, "epoch": 0.16471151544170456, "percentage": 16.48, "elapsed_time": "1:03:06", "remaining_time": "5:19:57", "throughput": 4086.34, "total_tokens": 15473984}
{"current_steps": 44, "total_steps": 261, "loss": 0.4498, "accuracy": 0.84375, "lr": 9.554050045938893e-06, "epoch": 0.168542015800814, "percentage": 16.86, "elapsed_time": "1:04:33", "remaining_time": "5:18:22", "throughput": 4083.83, "total_tokens": 15818304}
{"current_steps": 45, "total_steps": 261, "loss": 0.4762, "accuracy": 0.828125, "lr": 9.52785874330602e-06, "epoch": 0.17237251615992338, "percentage": 17.24, "elapsed_time": "1:05:59", "remaining_time": "5:16:45", "throughput": 4084.61, "total_tokens": 16173312}
{"current_steps": 46, "total_steps": 261, "loss": 0.4698, "accuracy": 0.828125, "lr": 9.500958125087882e-06, "epoch": 0.1762030165190328, "percentage": 17.62, "elapsed_time": "1:07:31", "remaining_time": "5:15:34", "throughput": 4083.51, "total_tokens": 16542400}
{"current_steps": 47, "total_steps": 261, "loss": 0.4451, "accuracy": 0.921875, "lr": 9.473352405423845e-06, "epoch": 0.1800335168781422, "percentage": 18.01, "elapsed_time": "1:09:03", "remaining_time": "5:14:24", "throughput": 4080.5, "total_tokens": 16906368}
{"current_steps": 48, "total_steps": 261, "loss": 0.454, "accuracy": 0.8515625, "lr": 9.445045908911536e-06, "epoch": 0.18386401723725163, "percentage": 18.39, "elapsed_time": "1:10:25", "remaining_time": "5:12:31", "throughput": 4080.76, "total_tokens": 17244160}
{"current_steps": 49, "total_steps": 261, "loss": 0.4516, "accuracy": 0.8359375, "lr": 9.416043069929389e-06, "epoch": 0.18769451759636102, "percentage": 18.77, "elapsed_time": "1:11:53", "remaining_time": "5:11:01", "throughput": 4081.73, "total_tokens": 17605632}
{"current_steps": 50, "total_steps": 261, "loss": 0.4555, "accuracy": 0.8203125, "lr": 9.386348431941953e-06, "epoch": 0.19152501795547044, "percentage": 19.16, "elapsed_time": "1:13:22", "remaining_time": "5:09:37", "throughput": 4081.36, "total_tokens": 17966784}
{"current_steps": 51, "total_steps": 261, "loss": 0.3739, "accuracy": 0.90625, "lr": 9.355966646788152e-06, "epoch": 0.19535551831457984, "percentage": 19.54, "elapsed_time": "1:14:50", "remaining_time": "5:08:08", "throughput": 4082.02, "total_tokens": 18328768}
{"current_steps": 52, "total_steps": 261, "loss": 0.4577, "accuracy": 0.828125, "lr": 9.324902473952529e-06, "epoch": 0.19918601867368926, "percentage": 19.92, "elapsed_time": "1:16:17", "remaining_time": "5:06:36", "throughput": 4081.71, "total_tokens": 18682304}
{"current_steps": 53, "total_steps": 261, "loss": 0.3821, "accuracy": 0.8984375, "lr": 9.293160779819658e-06, "epoch": 0.20301651903279866, "percentage": 20.31, "elapsed_time": "1:17:44", "remaining_time": "5:05:07", "throughput": 4081.16, "total_tokens": 19037760}
{"current_steps": 54, "total_steps": 261, "loss": 0.3763, "accuracy": 0.8828125, "lr": 9.260746536911792e-06, "epoch": 0.20684701939190805, "percentage": 20.69, "elapsed_time": "1:19:11", "remaining_time": "5:03:32", "throughput": 4082.17, "total_tokens": 19394688}
{"current_steps": 55, "total_steps": 261, "loss": 0.3643, "accuracy": 0.859375, "lr": 9.227664823109884e-06, "epoch": 0.21067751975101748, "percentage": 21.07, "elapsed_time": "1:20:42", "remaining_time": "5:02:16", "throughput": 4080.82, "total_tokens": 19760704}
{"current_steps": 56, "total_steps": 261, "loss": 0.363, "accuracy": 0.890625, "lr": 9.193920820858113e-06, "epoch": 0.21450802011012687, "percentage": 21.46, "elapsed_time": "1:22:11", "remaining_time": "5:00:51", "throughput": 4080.53, "total_tokens": 20121856}
{"current_steps": 57, "total_steps": 261, "loss": 0.3473, "accuracy": 0.9375, "lr": 9.159519816352021e-06, "epoch": 0.2183385204692363, "percentage": 21.84, "elapsed_time": "1:23:39", "remaining_time": "4:59:23", "throughput": 4080.72, "total_tokens": 20482304}
{"current_steps": 58, "total_steps": 261, "loss": 0.3425, "accuracy": 0.8984375, "lr": 9.124467198710401e-06, "epoch": 0.2221690208283457, "percentage": 22.22, "elapsed_time": "1:25:02", "remaining_time": "4:57:39", "throughput": 4080.64, "total_tokens": 20822656}
{"current_steps": 59, "total_steps": 261, "loss": 0.3257, "accuracy": 0.9296875, "lr": 9.08876845913106e-06, "epoch": 0.22599952118745512, "percentage": 22.61, "elapsed_time": "1:26:31", "remaining_time": "4:56:12", "throughput": 4081.55, "total_tokens": 21187392}
{"current_steps": 60, "total_steps": 261, "loss": 0.3257, "accuracy": 0.9140625, "lr": 9.052429190030589e-06, "epoch": 0.2298300215465645, "percentage": 22.99, "elapsed_time": "1:27:58", "remaining_time": "4:54:43", "throughput": 4081.59, "total_tokens": 21545600}
{"current_steps": 61, "total_steps": 261, "loss": 0.3375, "accuracy": 0.890625, "lr": 9.015455084168279e-06, "epoch": 0.23366052190567393, "percentage": 23.37, "elapsed_time": "1:29:22", "remaining_time": "4:53:00", "throughput": 4081.92, "total_tokens": 21887936}
{"current_steps": 62, "total_steps": 261, "loss": 0.3398, "accuracy": 0.9140625, "lr": 8.977851933754317e-06, "epoch": 0.23749102226478333, "percentage": 23.75, "elapsed_time": "1:30:45", "remaining_time": "4:51:18", "throughput": 4082.68, "total_tokens": 22233024}
{"current_steps": 63, "total_steps": 261, "loss": 0.3274, "accuracy": 0.9140625, "lr": 8.939625629542401e-06, "epoch": 0.24132152262389275, "percentage": 24.14, "elapsed_time": "1:32:11", "remaining_time": "4:49:45", "throughput": 4082.91, "total_tokens": 22585472}
{"current_steps": 64, "total_steps": 261, "loss": 0.301, "accuracy": 0.921875, "lr": 8.900782159906927e-06, "epoch": 0.24515202298300215, "percentage": 24.52, "elapsed_time": "1:33:41", "remaining_time": "4:48:23", "throughput": 4081.95, "total_tokens": 22946880}
{"current_steps": 65, "total_steps": 261, "loss": 0.3119, "accuracy": 0.8984375, "lr": 8.861327609904859e-06, "epoch": 0.24898252334211157, "percentage": 24.9, "elapsed_time": "1:35:09", "remaining_time": "4:46:55", "throughput": 4081.85, "total_tokens": 23304320}
{"current_steps": 66, "total_steps": 261, "loss": 0.329, "accuracy": 0.8515625, "lr": 8.821268160322482e-06, "epoch": 0.252813023701221, "percentage": 25.29, "elapsed_time": "1:36:35", "remaining_time": "4:45:21", "throughput": 4083.75, "total_tokens": 23665536}
{"current_steps": 67, "total_steps": 261, "loss": 0.2801, "accuracy": 0.953125, "lr": 8.780610086707149e-06, "epoch": 0.25664352406033036, "percentage": 25.67, "elapsed_time": "1:38:00", "remaining_time": "4:43:48", "throughput": 4084.57, "total_tokens": 24021376}
{"current_steps": 68, "total_steps": 261, "loss": 0.2903, "accuracy": 0.9140625, "lr": 8.739359758384162e-06, "epoch": 0.2604740244194398, "percentage": 26.05, "elapsed_time": "1:39:30", "remaining_time": "4:42:25", "throughput": 4084.35, "total_tokens": 24385216}
{"current_steps": 69, "total_steps": 261, "loss": 0.2866, "accuracy": 0.9140625, "lr": 8.697523637458997e-06, "epoch": 0.2643045247785492, "percentage": 26.44, "elapsed_time": "1:41:02", "remaining_time": "4:41:09", "throughput": 4082.46, "total_tokens": 24750080}
{"current_steps": 70, "total_steps": 261, "loss": 0.2925, "accuracy": 0.875, "lr": 8.655108277804975e-06, "epoch": 0.26813502513765863, "percentage": 26.82, "elapsed_time": "1:42:30", "remaining_time": "4:39:43", "throughput": 4083.35, "total_tokens": 25116480}
{"current_steps": 71, "total_steps": 261, "loss": 0.2486, "accuracy": 0.9375, "lr": 8.612120324036548e-06, "epoch": 0.271965525496768, "percentage": 27.2, "elapsed_time": "1:43:56", "remaining_time": "4:38:08", "throughput": 4083.47, "total_tokens": 25465536}
{"current_steps": 72, "total_steps": 261, "loss": 0.261, "accuracy": 0.9140625, "lr": 8.568566510468392e-06, "epoch": 0.2757960258558774, "percentage": 27.59, "elapsed_time": "1:45:25", "remaining_time": "4:36:43", "throughput": 4084.3, "total_tokens": 25833344}
{"current_steps": 73, "total_steps": 261, "loss": 0.3015, "accuracy": 0.890625, "lr": 8.524453660060434e-06, "epoch": 0.27962652621498685, "percentage": 27.97, "elapsed_time": "1:46:49", "remaining_time": "4:35:06", "throughput": 4085.19, "total_tokens": 26183872}
{"current_steps": 74, "total_steps": 261, "loss": 0.3031, "accuracy": 0.8828125, "lr": 8.479788683348996e-06, "epoch": 0.2834570265740962, "percentage": 28.35, "elapsed_time": "1:48:17", "remaining_time": "4:33:40", "throughput": 4084.44, "total_tokens": 26539904}
{"current_steps": 75, "total_steps": 261, "loss": 0.2726, "accuracy": 0.8984375, "lr": 8.434578577364218e-06, "epoch": 0.28728752693320564, "percentage": 28.74, "elapsed_time": "1:49:43", "remaining_time": "4:32:07", "throughput": 4086.13, "total_tokens": 26902464}
{"current_steps": 76, "total_steps": 261, "loss": 0.2354, "accuracy": 0.9609375, "lr": 8.388830424533935e-06, "epoch": 0.29111802729231506, "percentage": 29.12, "elapsed_time": "1:51:15", "remaining_time": "4:30:50", "throughput": 4084.85, "total_tokens": 27269504}
{"current_steps": 77, "total_steps": 261, "loss": 0.2989, "accuracy": 0.8984375, "lr": 8.342551391574165e-06, "epoch": 0.2949485276514245, "percentage": 29.5, "elapsed_time": "1:52:44", "remaining_time": "4:29:23", "throughput": 4084.66, "total_tokens": 27629248}
{"current_steps": 78, "total_steps": 261, "loss": 0.2474, "accuracy": 0.9453125, "lr": 8.295748728366414e-06, "epoch": 0.29877902801053385, "percentage": 29.89, "elapsed_time": "1:54:09", "remaining_time": "4:27:51", "throughput": 4085.86, "total_tokens": 27988096}
{"current_steps": 79, "total_steps": 261, "loss": 0.2654, "accuracy": 0.9140625, "lr": 8.248429766821925e-06, "epoch": 0.3026095283696433, "percentage": 30.27, "elapsed_time": "1:55:37", "remaining_time": "4:26:21", "throughput": 4086.22, "total_tokens": 28346432}
{"current_steps": 80, "total_steps": 261, "loss": 0.2653, "accuracy": 0.8828125, "lr": 8.200601919733106e-06, "epoch": 0.3064400287287527, "percentage": 30.65, "elapsed_time": "1:57:09", "remaining_time": "4:25:04", "throughput": 4084.92, "total_tokens": 28715200}
{"current_steps": 81, "total_steps": 261, "loss": 0.2446, "accuracy": 0.875, "lr": 8.15227267961226e-06, "epoch": 0.3102705290878621, "percentage": 31.03, "elapsed_time": "1:58:34", "remaining_time": "4:23:29", "throughput": 4085.93, "total_tokens": 29068800}
{"current_steps": 82, "total_steps": 261, "loss": 0.2791, "accuracy": 0.921875, "lr": 8.10344961751785e-06, "epoch": 0.3141010294469715, "percentage": 31.42, "elapsed_time": "1:59:59", "remaining_time": "4:21:56", "throughput": 4085.66, "total_tokens": 29416000}
{"current_steps": 83, "total_steps": 261, "loss": 0.2383, "accuracy": 0.90625, "lr": 8.054140381868435e-06, "epoch": 0.3179315298060809, "percentage": 31.8, "elapsed_time": "2:01:24", "remaining_time": "4:20:21", "throughput": 4086.65, "total_tokens": 29768704}
{"current_steps": 84, "total_steps": 261, "loss": 0.2578, "accuracy": 0.921875, "lr": 8.004352697244516e-06, "epoch": 0.32176203016519034, "percentage": 32.18, "elapsed_time": "2:02:52", "remaining_time": "4:18:55", "throughput": 4088.34, "total_tokens": 30143360}
{"current_steps": 85, "total_steps": 261, "loss": 0.2276, "accuracy": 0.9453125, "lr": 7.954094363178421e-06, "epoch": 0.32559253052429976, "percentage": 32.57, "elapsed_time": "2:04:18", "remaining_time": "4:17:23", "throughput": 4088.75, "total_tokens": 30496832}
{"current_steps": 86, "total_steps": 261, "loss": 0.2369, "accuracy": 0.921875, "lr": 7.903373252932474e-06, "epoch": 0.32942303088340913, "percentage": 32.95, "elapsed_time": "2:05:46", "remaining_time": "4:15:55", "throughput": 4088.64, "total_tokens": 30854400}
{"current_steps": 87, "total_steps": 261, "loss": 0.261, "accuracy": 0.9140625, "lr": 7.852197312265592e-06, "epoch": 0.33325353124251855, "percentage": 33.33, "elapsed_time": "2:07:12", "remaining_time": "4:14:24", "throughput": 4089.53, "total_tokens": 31212288}
{"current_steps": 88, "total_steps": 261, "loss": 0.2214, "accuracy": 0.9375, "lr": 7.800574558188548e-06, "epoch": 0.337084031601628, "percentage": 33.72, "elapsed_time": "2:08:41", "remaining_time": "4:13:00", "throughput": 4089.17, "total_tokens": 31576000}
{"current_steps": 89, "total_steps": 261, "loss": 0.2836, "accuracy": 0.9140625, "lr": 7.748513077708044e-06, "epoch": 0.34091453196073734, "percentage": 34.1, "elapsed_time": "2:10:08", "remaining_time": "4:11:30", "throughput": 4089.12, "total_tokens": 31930560}
{"current_steps": 90, "total_steps": 261, "loss": 0.2046, "accuracy": 0.9375, "lr": 7.69602102655985e-06, "epoch": 0.34474503231984677, "percentage": 34.48, "elapsed_time": "2:11:37", "remaining_time": "4:10:05", "throughput": 4089.13, "total_tokens": 32295488}
{"current_steps": 91, "total_steps": 261, "loss": 0.1799, "accuracy": 0.9609375, "lr": 7.643106627931148e-06, "epoch": 0.3485755326789562, "percentage": 34.87, "elapsed_time": "2:13:09", "remaining_time": "4:08:45", "throughput": 4089.49, "total_tokens": 32673984}
{"current_steps": 92, "total_steps": 261, "loss": 0.2464, "accuracy": 0.921875, "lr": 7.5897781711723215e-06, "epoch": 0.3524060330380656, "percentage": 35.25, "elapsed_time": "2:14:37", "remaining_time": "4:07:17", "throughput": 4089.9, "total_tokens": 33035968}
{"current_steps": 93, "total_steps": 261, "loss": 0.2468, "accuracy": 0.90625, "lr": 7.536044010498396e-06, "epoch": 0.356236533397175, "percentage": 35.63, "elapsed_time": "2:16:04", "remaining_time": "4:05:49", "throughput": 4089.75, "total_tokens": 33392192}
{"current_steps": 94, "total_steps": 261, "loss": 0.1873, "accuracy": 0.953125, "lr": 7.48191256368028e-06, "epoch": 0.3600670337562844, "percentage": 36.02, "elapsed_time": "2:17:31", "remaining_time": "4:04:18", "throughput": 4091.43, "total_tokens": 33758976}
{"current_steps": 95, "total_steps": 261, "loss": 0.2136, "accuracy": 0.921875, "lr": 7.427392310726088e-06, "epoch": 0.36389753411539383, "percentage": 36.4, "elapsed_time": "2:18:59", "remaining_time": "4:02:51", "throughput": 4091.9, "total_tokens": 34123840}
{"current_steps": 96, "total_steps": 261, "loss": 0.1643, "accuracy": 0.9609375, "lr": 7.372491792552694e-06, "epoch": 0.36772803447450325, "percentage": 36.78, "elapsed_time": "2:20:29", "remaining_time": "4:01:27", "throughput": 4090.46, "total_tokens": 34479552}
{"current_steps": 97, "total_steps": 261, "loss": 0.2047, "accuracy": 0.9453125, "lr": 7.31721960964774e-06, "epoch": 0.3715585348336126, "percentage": 37.16, "elapsed_time": "2:21:56", "remaining_time": "3:59:59", "throughput": 4090.36, "total_tokens": 34835840}
{"current_steps": 98, "total_steps": 261, "loss": 0.2532, "accuracy": 0.8984375, "lr": 7.261584420722328e-06, "epoch": 0.37538903519272204, "percentage": 37.55, "elapsed_time": "2:23:27", "remaining_time": "3:58:35", "throughput": 4090.85, "total_tokens": 35210176}
{"current_steps": 99, "total_steps": 261, "loss": 0.199, "accuracy": 0.9375, "lr": 7.20559494135458e-06, "epoch": 0.37921953555183147, "percentage": 37.93, "elapsed_time": "2:24:54", "remaining_time": "3:57:06", "throughput": 4091.04, "total_tokens": 35568576}
{"current_steps": 100, "total_steps": 261, "loss": 0.2089, "accuracy": 0.921875, "lr": 7.149259942624287e-06, "epoch": 0.3830500359109409, "percentage": 38.31, "elapsed_time": "2:26:21", "remaining_time": "3:55:38", "throughput": 4091.32, "total_tokens": 35929024}
{"current_steps": 101, "total_steps": 261, "loss": 0.2212, "accuracy": 0.9375, "lr": 7.092588249738871e-06, "epoch": 0.38688053627005026, "percentage": 38.7, "elapsed_time": "2:27:51", "remaining_time": "3:54:13", "throughput": 4091.02, "total_tokens": 36292032}
{"current_steps": 102, "total_steps": 261, "loss": 0.2015, "accuracy": 0.8984375, "lr": 7.03558874065087e-06, "epoch": 0.3907110366291597, "percentage": 39.08, "elapsed_time": "2:29:16", "remaining_time": "3:52:41", "throughput": 4091.6, "total_tokens": 36647104}
{"current_steps": 103, "total_steps": 261, "loss": 0.198, "accuracy": 0.9453125, "lr": 6.978270344667143e-06, "epoch": 0.3945415369882691, "percentage": 39.46, "elapsed_time": "2:30:41", "remaining_time": "3:51:08", "throughput": 4092.11, "total_tokens": 36996736}
{"current_steps": 104, "total_steps": 261, "loss": 0.2626, "accuracy": 0.890625, "lr": 6.920642041050055e-06, "epoch": 0.3983720373473785, "percentage": 39.85, "elapsed_time": "2:32:06", "remaining_time": "3:49:36", "throughput": 4092.8, "total_tokens": 37351296}
{"current_steps": 105, "total_steps": 261, "loss": 0.1446, "accuracy": 0.9609375, "lr": 6.862712857610812e-06, "epoch": 0.4022025377064879, "percentage": 40.23, "elapsed_time": "2:33:34", "remaining_time": "3:48:10", "throughput": 4092.48, "total_tokens": 37710464}
{"current_steps": 106, "total_steps": 261, "loss": 0.2115, "accuracy": 0.9453125, "lr": 6.804491869295207e-06, "epoch": 0.4060330380655973, "percentage": 40.61, "elapsed_time": "2:35:03", "remaining_time": "3:46:44", "throughput": 4092.59, "total_tokens": 38075136}
{"current_steps": 107, "total_steps": 261, "loss": 0.1883, "accuracy": 0.9453125, "lr": 6.745988196761976e-06, "epoch": 0.40986353842470674, "percentage": 41.0, "elapsed_time": "2:36:30", "remaining_time": "3:45:15", "throughput": 4093.19, "total_tokens": 38438464}
{"current_steps": 108, "total_steps": 261, "loss": 0.1569, "accuracy": 0.953125, "lr": 6.687211004953992e-06, "epoch": 0.4136940387838161, "percentage": 41.38, "elapsed_time": "2:37:58", "remaining_time": "3:43:48", "throughput": 4091.92, "total_tokens": 38786112}
{"current_steps": 109, "total_steps": 261, "loss": 0.1728, "accuracy": 0.953125, "lr": 6.628169501662527e-06, "epoch": 0.41752453914292553, "percentage": 41.76, "elapsed_time": "2:39:23", "remaining_time": "3:42:16", "throughput": 4092.26, "total_tokens": 39137920}
{"current_steps": 110, "total_steps": 261, "loss": 0.2576, "accuracy": 0.890625, "lr": 6.568872936084789e-06, "epoch": 0.42135503950203496, "percentage": 42.15, "elapsed_time": "2:40:53", "remaining_time": "3:40:51", "throughput": 4091.61, "total_tokens": 39496896}
{"current_steps": 111, "total_steps": 261, "loss": 0.2094, "accuracy": 0.9140625, "lr": 6.509330597374993e-06, "epoch": 0.4251855398611444, "percentage": 42.53, "elapsed_time": "2:42:21", "remaining_time": "3:39:23", "throughput": 4092.24, "total_tokens": 39862784}
{"current_steps": 112, "total_steps": 261, "loss": 0.1943, "accuracy": 0.9453125, "lr": 6.44955181318915e-06, "epoch": 0.42901604022025375, "percentage": 42.91, "elapsed_time": "2:43:51", "remaining_time": "3:37:58", "throughput": 4092.07, "total_tokens": 40229504}
{"current_steps": 113, "total_steps": 261, "loss": 0.2281, "accuracy": 0.9140625, "lr": 6.389545948223841e-06, "epoch": 0.43284654057936317, "percentage": 43.3, "elapsed_time": "2:45:16", "remaining_time": "3:36:27", "throughput": 4092.07, "total_tokens": 40578304}
{"current_steps": 114, "total_steps": 261, "loss": 0.1579, "accuracy": 0.9609375, "lr": 6.329322402749181e-06, "epoch": 0.4366770409384726, "percentage": 43.68, "elapsed_time": "2:46:42", "remaining_time": "3:34:57", "throughput": 4091.79, "total_tokens": 40926400}
{"current_steps": 115, "total_steps": 261, "loss": 0.1995, "accuracy": 0.9296875, "lr": 6.2688906111362115e-06, "epoch": 0.440507541297582, "percentage": 44.06, "elapsed_time": "2:48:08", "remaining_time": "3:33:28", "throughput": 4092.02, "total_tokens": 41283008}
{"current_steps": 116, "total_steps": 261, "loss": 0.226, "accuracy": 0.90625, "lr": 6.208260040378946e-06, "epoch": 0.4443380416566914, "percentage": 44.44, "elapsed_time": "2:49:31", "remaining_time": "3:31:54", "throughput": 4091.76, "total_tokens": 41619520}
{"current_steps": 117, "total_steps": 261, "loss": 0.1644, "accuracy": 0.9453125, "lr": 6.147440188611324e-06, "epoch": 0.4481685420158008, "percentage": 44.83, "elapsed_time": "2:51:02", "remaining_time": "3:30:31", "throughput": 4091.12, "total_tokens": 41986368}
{"current_steps": 118, "total_steps": 261, "loss": 0.1757, "accuracy": 0.921875, "lr": 6.0864405836192575e-06, "epoch": 0.45199904237491023, "percentage": 45.21, "elapsed_time": "2:52:30", "remaining_time": "3:29:03", "throughput": 4091.14, "total_tokens": 42347008}
{"current_steps": 119, "total_steps": 261, "loss": 0.1706, "accuracy": 0.9453125, "lr": 6.025270781348055e-06, "epoch": 0.45582954273401965, "percentage": 45.59, "elapsed_time": "2:53:57", "remaining_time": "3:27:34", "throughput": 4090.86, "total_tokens": 42698240}
{"current_steps": 120, "total_steps": 261, "loss": 0.2021, "accuracy": 0.90625, "lr": 5.963940364405425e-06, "epoch": 0.459660043093129, "percentage": 45.98, "elapsed_time": "2:55:22", "remaining_time": "3:26:03", "throughput": 4091.35, "total_tokens": 43050688}
{"current_steps": 121, "total_steps": 261, "loss": 0.1728, "accuracy": 0.953125, "lr": 5.902458940560304e-06, "epoch": 0.46349054345223845, "percentage": 46.36, "elapsed_time": "2:56:50", "remaining_time": "3:24:36", "throughput": 4091.71, "total_tokens": 43415744}
{"current_steps": 122, "total_steps": 261, "loss": 0.1615, "accuracy": 0.9375, "lr": 5.8408361412377475e-06, "epoch": 0.46732104381134787, "percentage": 46.74, "elapsed_time": "2:58:18", "remaining_time": "3:23:08", "throughput": 4091.38, "total_tokens": 43769984}
{"current_steps": 123, "total_steps": 261, "loss": 0.1474, "accuracy": 0.96875, "lr": 5.779081620010104e-06, "epoch": 0.4711515441704573, "percentage": 47.13, "elapsed_time": "2:59:42", "remaining_time": "3:21:37", "throughput": 4092.35, "total_tokens": 44125376}
{"current_steps": 124, "total_steps": 261, "loss": 0.2012, "accuracy": 0.921875, "lr": 5.717205051084731e-06, "epoch": 0.47498204452956666, "percentage": 47.51, "elapsed_time": "3:01:11", "remaining_time": "3:20:10", "throughput": 4093.15, "total_tokens": 44496896}
{"current_steps": 125, "total_steps": 261, "loss": 0.1836, "accuracy": 0.9375, "lr": 5.655216127788472e-06, "epoch": 0.4788125448886761, "percentage": 47.89, "elapsed_time": "3:02:39", "remaining_time": "3:18:44", "throughput": 4092.94, "total_tokens": 44858496}
{"current_steps": 126, "total_steps": 261, "loss": 0.1678, "accuracy": 0.9375, "lr": 5.593124561049141e-06, "epoch": 0.4826430452477855, "percentage": 48.28, "elapsed_time": "3:04:06", "remaining_time": "3:17:15", "throughput": 4093.24, "total_tokens": 45215680}
{"current_steps": 127, "total_steps": 261, "loss": 0.1832, "accuracy": 0.9375, "lr": 5.530940077874248e-06, "epoch": 0.4864735456068949, "percentage": 48.66, "elapsed_time": "3:05:33", "remaining_time": "3:15:47", "throughput": 4093.55, "total_tokens": 45575872}
{"current_steps": 128, "total_steps": 261, "loss": 0.1594, "accuracy": 0.9453125, "lr": 5.468672419827208e-06, "epoch": 0.4903040459660043, "percentage": 49.04, "elapsed_time": "3:07:04", "remaining_time": "3:14:22", "throughput": 4093.98, "total_tokens": 45951488}
{"current_steps": 129, "total_steps": 261, "loss": 0.2112, "accuracy": 0.90625, "lr": 5.406331341501264e-06, "epoch": 0.4941345463251137, "percentage": 49.43, "elapsed_time": "3:08:35", "remaining_time": "3:12:58", "throughput": 4092.96, "total_tokens": 46313472}
{"current_steps": 130, "total_steps": 261, "loss": 0.1785, "accuracy": 0.9453125, "lr": 5.34392660899138e-06, "epoch": 0.49796504668422314, "percentage": 49.81, "elapsed_time": "3:10:07", "remaining_time": "3:11:34", "throughput": 4092.47, "total_tokens": 46683136}
{"current_steps": 131, "total_steps": 261, "loss": 0.1789, "accuracy": 0.9140625, "lr": 5.281467998364314e-06, "epoch": 0.5017955470433325, "percentage": 50.19, "elapsed_time": "3:11:31", "remaining_time": "3:10:03", "throughput": 4092.86, "total_tokens": 47033152}
{"current_steps": 132, "total_steps": 261, "loss": 0.1489, "accuracy": 0.9609375, "lr": 5.218965294127155e-06, "epoch": 0.505626047402442, "percentage": 50.57, "elapsed_time": "3:13:02", "remaining_time": "3:08:39", "throughput": 4092.88, "total_tokens": 47407552}
{"current_steps": 133, "total_steps": 261, "loss": 0.1521, "accuracy": 0.953125, "lr": 5.156428287694508e-06, "epoch": 0.5094565477615514, "percentage": 50.96, "elapsed_time": "3:14:35", "remaining_time": "3:07:16", "throughput": 4091.93, "total_tokens": 47777088}
{"current_steps": 134, "total_steps": 261, "loss": 0.1878, "accuracy": 0.921875, "lr": 5.093866775854618e-06, "epoch": 0.5132870481206607, "percentage": 51.34, "elapsed_time": "3:16:05", "remaining_time": "3:05:50", "throughput": 4092.13, "total_tokens": 48146176}
{"current_steps": 135, "total_steps": 261, "loss": 0.1465, "accuracy": 0.953125, "lr": 5.03129055923465e-06, "epoch": 0.5171175484797702, "percentage": 51.72, "elapsed_time": "3:17:30", "remaining_time": "3:04:20", "throughput": 4093.46, "total_tokens": 48511488}
{"current_steps": 136, "total_steps": 261, "loss": 0.1633, "accuracy": 0.9296875, "lr": 4.968709440765352e-06, "epoch": 0.5209480488388796, "percentage": 52.11, "elapsed_time": "3:18:53", "remaining_time": "3:02:47", "throughput": 4094.71, "total_tokens": 48862336}
{"current_steps": 137, "total_steps": 261, "loss": 0.182, "accuracy": 0.9375, "lr": 4.906133224145384e-06, "epoch": 0.5247785491979889, "percentage": 52.49, "elapsed_time": "3:20:21", "remaining_time": "3:01:21", "throughput": 4094.72, "total_tokens": 49226048}
{"current_steps": 138, "total_steps": 261, "loss": 0.2354, "accuracy": 0.875, "lr": 4.843571712305493e-06, "epoch": 0.5286090495570984, "percentage": 52.87, "elapsed_time": "3:21:48", "remaining_time": "2:59:52", "throughput": 4094.64, "total_tokens": 49581888}
{"current_steps": 139, "total_steps": 261, "loss": 0.1248, "accuracy": 0.9765625, "lr": 4.781034705872846e-06, "epoch": 0.5324395499162078, "percentage": 53.26, "elapsed_time": "3:23:14", "remaining_time": "2:58:23", "throughput": 4095.01, "total_tokens": 49936512}
{"current_steps": 140, "total_steps": 261, "loss": 0.1743, "accuracy": 0.9453125, "lr": 4.7185320016356865e-06, "epoch": 0.5362700502753173, "percentage": 53.64, "elapsed_time": "3:24:43", "remaining_time": "2:56:56", "throughput": 4095.6, "total_tokens": 50309824}
{"current_steps": 141, "total_steps": 261, "loss": 0.16, "accuracy": 0.9609375, "lr": 4.656073391008622e-06, "epoch": 0.5401005506344266, "percentage": 54.02, "elapsed_time": "3:26:06", "remaining_time": "2:55:24", "throughput": 4096.49, "total_tokens": 50659712}
{"current_steps": 142, "total_steps": 261, "loss": 0.1646, "accuracy": 0.96875, "lr": 4.593668658498737e-06, "epoch": 0.543931050993536, "percentage": 54.41, "elapsed_time": "3:27:32", "remaining_time": "2:53:55", "throughput": 4097.33, "total_tokens": 51020992}
{"current_steps": 143, "total_steps": 261, "loss": 0.134, "accuracy": 0.96875, "lr": 4.531327580172794e-06, "epoch": 0.5477615513526455, "percentage": 54.79, "elapsed_time": "3:28:59", "remaining_time": "2:52:27", "throughput": 4097.23, "total_tokens": 51378624}
{"current_steps": 144, "total_steps": 261, "loss": 0.1787, "accuracy": 0.9375, "lr": 4.469059922125753e-06, "epoch": 0.5515920517117548, "percentage": 55.17, "elapsed_time": "3:30:31", "remaining_time": "2:51:03", "throughput": 4097.65, "total_tokens": 51760384}
{"current_steps": 145, "total_steps": 261, "loss": 0.1561, "accuracy": 0.9453125, "lr": 4.4068754389508616e-06, "epoch": 0.5554225520708642, "percentage": 55.56, "elapsed_time": "3:31:55", "remaining_time": "2:49:32", "throughput": 4098.45, "total_tokens": 52114304}
{"current_steps": 146, "total_steps": 261, "loss": 0.1754, "accuracy": 0.9296875, "lr": 4.34478387221153e-06, "epoch": 0.5592530524299737, "percentage": 55.94, "elapsed_time": "3:33:26", "remaining_time": "2:48:07", "throughput": 4098.57, "total_tokens": 52486784}
{"current_steps": 147, "total_steps": 261, "loss": 0.1371, "accuracy": 0.9609375, "lr": 4.282794948915271e-06, "epoch": 0.5630835527890831, "percentage": 56.32, "elapsed_time": "3:34:50", "remaining_time": "2:46:36", "throughput": 4098.59, "total_tokens": 52831680}
{"current_steps": 148, "total_steps": 261, "loss": 0.1264, "accuracy": 0.9921875, "lr": 4.220918379989898e-06, "epoch": 0.5669140531481924, "percentage": 56.7, "elapsed_time": "3:36:12", "remaining_time": "2:45:04", "throughput": 4099.06, "total_tokens": 53175680}
{"current_steps": 149, "total_steps": 261, "loss": 0.1533, "accuracy": 0.9453125, "lr": 4.159163858762255e-06, "epoch": 0.5707445535073019, "percentage": 57.09, "elapsed_time": "3:37:41", "remaining_time": "2:43:37", "throughput": 4098.87, "total_tokens": 53537024}
{"current_steps": 150, "total_steps": 261, "loss": 0.1247, "accuracy": 0.984375, "lr": 4.097541059439698e-06, "epoch": 0.5745750538664113, "percentage": 57.47, "elapsed_time": "3:39:06", "remaining_time": "2:42:08", "throughput": 4099.58, "total_tokens": 53894528}
{"current_steps": 151, "total_steps": 261, "loss": 0.1545, "accuracy": 0.9609375, "lr": 4.036059635594578e-06, "epoch": 0.5784055542255208, "percentage": 57.85, "elapsed_time": "3:40:35", "remaining_time": "2:40:41", "throughput": 4099.78, "total_tokens": 54262848}
{"current_steps": 152, "total_steps": 261, "loss": 0.1238, "accuracy": 0.984375, "lr": 3.974729218651946e-06, "epoch": 0.5822360545846301, "percentage": 58.24, "elapsed_time": "3:42:07", "remaining_time": "2:39:16", "throughput": 4099.62, "total_tokens": 54635776}
{"current_steps": 153, "total_steps": 261, "loss": 0.1598, "accuracy": 0.9609375, "lr": 3.913559416380743e-06, "epoch": 0.5860665549437395, "percentage": 58.62, "elapsed_time": "3:43:37", "remaining_time": "2:37:50", "throughput": 4099.2, "total_tokens": 54999744}
{"current_steps": 154, "total_steps": 261, "loss": 0.1063, "accuracy": 0.9765625, "lr": 3.852559811388676e-06, "epoch": 0.589897055302849, "percentage": 59.0, "elapsed_time": "3:44:59", "remaining_time": "2:36:19", "throughput": 4099.09, "total_tokens": 55337280}
{"current_steps": 155, "total_steps": 261, "loss": 0.2155, "accuracy": 0.9296875, "lr": 3.791739959621054e-06, "epoch": 0.5937275556619583, "percentage": 59.39, "elapsed_time": "3:46:33", "remaining_time": "2:34:56", "throughput": 4097.79, "total_tokens": 55702336}
{"current_steps": 156, "total_steps": 261, "loss": 0.1484, "accuracy": 0.9609375, "lr": 3.7311093888637906e-06, "epoch": 0.5975580560210677, "percentage": 59.77, "elapsed_time": "3:48:04", "remaining_time": "2:33:30", "throughput": 4097.31, "total_tokens": 56070336}
{"current_steps": 157, "total_steps": 261, "loss": 0.1514, "accuracy": 0.953125, "lr": 3.670677597250819e-06, "epoch": 0.6013885563801772, "percentage": 60.15, "elapsed_time": "3:49:33", "remaining_time": "2:32:03", "throughput": 4096.96, "total_tokens": 56428800}
{"current_steps": 158, "total_steps": 261, "loss": 0.1324, "accuracy": 0.953125, "lr": 3.6104540517761594e-06, "epoch": 0.6052190567392866, "percentage": 60.54, "elapsed_time": "3:50:58", "remaining_time": "2:30:34", "throughput": 4097.35, "total_tokens": 56783040}
{"current_steps": 159, "total_steps": 261, "loss": 0.0982, "accuracy": 0.9921875, "lr": 3.55044818681085e-06, "epoch": 0.609049557098396, "percentage": 60.92, "elapsed_time": "3:52:26", "remaining_time": "2:29:06", "throughput": 4097.65, "total_tokens": 57145920}
{"current_steps": 160, "total_steps": 261, "loss": 0.1404, "accuracy": 0.9765625, "lr": 3.4906694026250075e-06, "epoch": 0.6128800574575054, "percentage": 61.3, "elapsed_time": "3:53:52", "remaining_time": "2:27:38", "throughput": 4097.73, "total_tokens": 57502528}
{"current_steps": 161, "total_steps": 261, "loss": 0.143, "accuracy": 0.9765625, "lr": 3.431127063915213e-06, "epoch": 0.6167105578166148, "percentage": 61.69, "elapsed_time": "3:55:19", "remaining_time": "2:26:09", "throughput": 4098.31, "total_tokens": 57864896}
{"current_steps": 162, "total_steps": 261, "loss": 0.1236, "accuracy": 0.9765625, "lr": 3.371830498337475e-06, "epoch": 0.6205410581757242, "percentage": 62.07, "elapsed_time": "3:56:48", "remaining_time": "2:24:42", "throughput": 4097.52, "total_tokens": 58218496}
{"current_steps": 163, "total_steps": 261, "loss": 0.1342, "accuracy": 0.9765625, "lr": 3.3127889950460094e-06, "epoch": 0.6243715585348336, "percentage": 62.45, "elapsed_time": "3:58:11", "remaining_time": "2:23:12", "throughput": 4097.7, "total_tokens": 58561152}
{"current_steps": 164, "total_steps": 261, "loss": 0.1939, "accuracy": 0.921875, "lr": 3.254011803238026e-06, "epoch": 0.628202058893943, "percentage": 62.84, "elapsed_time": "3:59:40", "remaining_time": "2:21:45", "throughput": 4097.57, "total_tokens": 58925504}
{"current_steps": 165, "total_steps": 261, "loss": 0.1649, "accuracy": 0.953125, "lr": 3.195508130704795e-06, "epoch": 0.6320325592530525, "percentage": 63.22, "elapsed_time": "4:01:03", "remaining_time": "2:20:15", "throughput": 4097.78, "total_tokens": 59269120}
{"current_steps": 166, "total_steps": 261, "loss": 0.1534, "accuracy": 0.9296875, "lr": 3.1372871423891894e-06, "epoch": 0.6358630596121618, "percentage": 63.6, "elapsed_time": "4:02:28", "remaining_time": "2:18:46", "throughput": 4098.03, "total_tokens": 59620928}
{"current_steps": 167, "total_steps": 261, "loss": 0.1166, "accuracy": 0.9765625, "lr": 3.079357958949946e-06, "epoch": 0.6396935599712712, "percentage": 63.98, "elapsed_time": "4:03:53", "remaining_time": "2:17:16", "throughput": 4098.59, "total_tokens": 59974656}
{"current_steps": 168, "total_steps": 261, "loss": 0.1577, "accuracy": 0.9609375, "lr": 3.021729655332858e-06, "epoch": 0.6435240603303807, "percentage": 64.37, "elapsed_time": "4:05:17", "remaining_time": "2:15:47", "throughput": 4099.23, "total_tokens": 60329216}
{"current_steps": 169, "total_steps": 261, "loss": 0.1012, "accuracy": 0.984375, "lr": 2.9644112593491315e-06, "epoch": 0.64735456068949, "percentage": 64.75, "elapsed_time": "4:06:45", "remaining_time": "2:14:19", "throughput": 4098.94, "total_tokens": 60686464}
{"current_steps": 170, "total_steps": 261, "loss": 0.1475, "accuracy": 0.9453125, "lr": 2.90741175026113e-06, "epoch": 0.6511850610485995, "percentage": 65.13, "elapsed_time": "4:08:12", "remaining_time": "2:12:52", "throughput": 4099.02, "total_tokens": 61046144}
{"current_steps": 171, "total_steps": 261, "loss": 0.148, "accuracy": 0.953125, "lr": 2.850740057375716e-06, "epoch": 0.6550155614077089, "percentage": 65.52, "elapsed_time": "4:09:39", "remaining_time": "2:11:23", "throughput": 4098.68, "total_tokens": 61395776}
{"current_steps": 172, "total_steps": 261, "loss": 0.1509, "accuracy": 0.953125, "lr": 2.7944050586454215e-06, "epoch": 0.6588460617668183, "percentage": 65.9, "elapsed_time": "4:11:04", "remaining_time": "2:09:54", "throughput": 4098.44, "total_tokens": 61739072}
{"current_steps": 173, "total_steps": 261, "loss": 0.1492, "accuracy": 0.9453125, "lr": 2.7384155792776724e-06, "epoch": 0.6626765621259277, "percentage": 66.28, "elapsed_time": "4:12:28", "remaining_time": "2:08:25", "throughput": 4098.87, "total_tokens": 62091840}
{"current_steps": 174, "total_steps": 261, "loss": 0.1385, "accuracy": 0.953125, "lr": 2.682780390352262e-06, "epoch": 0.6665070624850371, "percentage": 66.67, "elapsed_time": "4:13:57", "remaining_time": "2:06:58", "throughput": 4098.68, "total_tokens": 62452416}
{"current_steps": 175, "total_steps": 261, "loss": 0.1579, "accuracy": 0.9296875, "lr": 2.627508207447308e-06, "epoch": 0.6703375628441465, "percentage": 67.05, "elapsed_time": "4:15:28", "remaining_time": "2:05:32", "throughput": 4098.69, "total_tokens": 62826432}
{"current_steps": 176, "total_steps": 261, "loss": 0.1482, "accuracy": 0.953125, "lr": 2.5726076892739127e-06, "epoch": 0.674168063203256, "percentage": 67.43, "elapsed_time": "4:16:55", "remaining_time": "2:04:05", "throughput": 4098.95, "total_tokens": 63188736}
{"current_steps": 177, "total_steps": 261, "loss": 0.131, "accuracy": 0.9609375, "lr": 2.5180874363197217e-06, "epoch": 0.6779985635623653, "percentage": 67.82, "elapsed_time": "4:18:24", "remaining_time": "2:02:38", "throughput": 4099.42, "total_tokens": 63559040}
{"current_steps": 178, "total_steps": 261, "loss": 0.1255, "accuracy": 0.9609375, "lr": 2.463955989501607e-06, "epoch": 0.6818290639214747, "percentage": 68.2, "elapsed_time": "4:19:51", "remaining_time": "2:01:10", "throughput": 4099.42, "total_tokens": 63918080}
{"current_steps": 179, "total_steps": 261, "loss": 0.1311, "accuracy": 0.9765625, "lr": 2.41022182882768e-06, "epoch": 0.6856595642805842, "percentage": 68.58, "elapsed_time": "4:21:15", "remaining_time": "1:59:40", "throughput": 4099.73, "total_tokens": 64264384}
{"current_steps": 180, "total_steps": 261, "loss": 0.148, "accuracy": 0.953125, "lr": 2.356893372068855e-06, "epoch": 0.6894900646396935, "percentage": 68.97, "elapsed_time": "4:22:41", "remaining_time": "1:58:12", "throughput": 4100.27, "total_tokens": 64627520}
{"current_steps": 181, "total_steps": 261, "loss": 0.1238, "accuracy": 0.9921875, "lr": 2.3039789734401524e-06, "epoch": 0.693320564998803, "percentage": 69.35, "elapsed_time": "4:24:08", "remaining_time": "1:56:44", "throughput": 4100.34, "total_tokens": 64985472}
{"current_steps": 182, "total_steps": 261, "loss": 0.162, "accuracy": 0.9453125, "lr": 2.251486922291957e-06, "epoch": 0.6971510653579124, "percentage": 69.73, "elapsed_time": "4:25:32", "remaining_time": "1:55:15", "throughput": 4100.57, "total_tokens": 65333056}
{"current_steps": 183, "total_steps": 261, "loss": 0.1528, "accuracy": 0.953125, "lr": 2.1994254418114524e-06, "epoch": 0.7009815657170217, "percentage": 70.11, "elapsed_time": "4:27:03", "remaining_time": "1:53:49", "throughput": 4100.38, "total_tokens": 65701376}
{"current_steps": 184, "total_steps": 261, "loss": 0.1427, "accuracy": 0.9453125, "lr": 2.147802687734409e-06, "epoch": 0.7048120660761312, "percentage": 70.5, "elapsed_time": "4:28:31", "remaining_time": "1:52:22", "throughput": 4100.09, "total_tokens": 66057152}
{"current_steps": 185, "total_steps": 261, "loss": 0.1538, "accuracy": 0.953125, "lr": 2.0966267470675273e-06, "epoch": 0.7086425664352406, "percentage": 70.88, "elapsed_time": "4:29:58", "remaining_time": "1:50:54", "throughput": 4100.03, "total_tokens": 66413248}
{"current_steps": 186, "total_steps": 261, "loss": 0.1646, "accuracy": 0.9296875, "lr": 2.0459056368215786e-06, "epoch": 0.71247306679435, "percentage": 71.26, "elapsed_time": "4:31:26", "remaining_time": "1:49:26", "throughput": 4100.29, "total_tokens": 66777600}
{"current_steps": 187, "total_steps": 261, "loss": 0.1682, "accuracy": 0.9375, "lr": 1.9956473027554846e-06, "epoch": 0.7163035671534594, "percentage": 71.65, "elapsed_time": "4:32:53", "remaining_time": "1:47:59", "throughput": 4099.72, "total_tokens": 67126784}
{"current_steps": 188, "total_steps": 261, "loss": 0.1301, "accuracy": 0.96875, "lr": 1.9458596181315643e-06, "epoch": 0.7201340675125688, "percentage": 72.03, "elapsed_time": "4:34:20", "remaining_time": "1:46:31", "throughput": 4099.89, "total_tokens": 67486848}
{"current_steps": 189, "total_steps": 261, "loss": 0.1263, "accuracy": 0.96875, "lr": 1.8965503824821496e-06, "epoch": 0.7239645678716783, "percentage": 72.41, "elapsed_time": "4:35:45", "remaining_time": "1:45:03", "throughput": 4099.51, "total_tokens": 67830400}
{"current_steps": 190, "total_steps": 261, "loss": 0.1905, "accuracy": 0.953125, "lr": 1.84772732038774e-06, "epoch": 0.7277950682307877, "percentage": 72.8, "elapsed_time": "4:37:11", "remaining_time": "1:43:34", "throughput": 4099.75, "total_tokens": 68184448}
{"current_steps": 191, "total_steps": 261, "loss": 0.1212, "accuracy": 0.953125, "lr": 1.7993980802668947e-06, "epoch": 0.731625568589897, "percentage": 73.18, "elapsed_time": "4:38:39", "remaining_time": "1:42:07", "throughput": 4099.23, "total_tokens": 68536640}
{"current_steps": 192, "total_steps": 261, "loss": 0.1466, "accuracy": 0.9375, "lr": 1.7515702331780753e-06, "epoch": 0.7354560689490065, "percentage": 73.56, "elapsed_time": "4:40:03", "remaining_time": "1:40:38", "throughput": 4099.34, "total_tokens": 68881216}
{"current_steps": 193, "total_steps": 261, "loss": 0.1463, "accuracy": 0.9765625, "lr": 1.7042512716335873e-06, "epoch": 0.7392865693081159, "percentage": 73.95, "elapsed_time": "4:41:34", "remaining_time": "1:39:12", "throughput": 4099.51, "total_tokens": 69258368}
{"current_steps": 194, "total_steps": 261, "loss": 0.1093, "accuracy": 0.984375, "lr": 1.6574486084258369e-06, "epoch": 0.7431170696672252, "percentage": 74.33, "elapsed_time": "4:43:03", "remaining_time": "1:37:45", "throughput": 4099.1, "total_tokens": 69617152}
{"current_steps": 195, "total_steps": 261, "loss": 0.1382, "accuracy": 0.953125, "lr": 1.6111695754660667e-06, "epoch": 0.7469475700263347, "percentage": 74.71, "elapsed_time": "4:44:32", "remaining_time": "1:36:18", "throughput": 4098.82, "total_tokens": 69979072}
{"current_steps": 196, "total_steps": 261, "loss": 0.0859, "accuracy": 1.0, "lr": 1.5654214226357822e-06, "epoch": 0.7507780703854441, "percentage": 75.1, "elapsed_time": "4:46:00", "remaining_time": "1:34:50", "throughput": 4099.27, "total_tokens": 70344768}
{"current_steps": 197, "total_steps": 261, "loss": 0.1651, "accuracy": 0.953125, "lr": 1.5202113166510058e-06, "epoch": 0.7546085707445535, "percentage": 75.48, "elapsed_time": "4:47:32", "remaining_time": "1:33:24", "throughput": 4099.21, "total_tokens": 70721984}
{"current_steps": 198, "total_steps": 261, "loss": 0.1192, "accuracy": 0.96875, "lr": 1.475546339939568e-06, "epoch": 0.7584390711036629, "percentage": 75.86, "elapsed_time": "4:49:00", "remaining_time": "1:31:57", "throughput": 4099.16, "total_tokens": 71082368}
{"current_steps": 199, "total_steps": 261, "loss": 0.1352, "accuracy": 0.9453125, "lr": 1.4314334895316095e-06, "epoch": 0.7622695714627723, "percentage": 76.25, "elapsed_time": "4:50:28", "remaining_time": "1:30:30", "throughput": 4098.83, "total_tokens": 71436928}
{"current_steps": 200, "total_steps": 261, "loss": 0.1048, "accuracy": 0.984375, "lr": 1.3878796759634544e-06, "epoch": 0.7661000718218818, "percentage": 76.63, "elapsed_time": "4:51:59", "remaining_time": "1:29:03", "throughput": 4098.26, "total_tokens": 71801024}
{"current_steps": 201, "total_steps": 261, "loss": 0.1484, "accuracy": 0.9453125, "lr": 1.3448917221950264e-06, "epoch": 0.7699305721809911, "percentage": 77.01, "elapsed_time": "4:53:29", "remaining_time": "1:27:36", "throughput": 4098.42, "total_tokens": 72172800}
{"current_steps": 202, "total_steps": 261, "loss": 0.1119, "accuracy": 0.9609375, "lr": 1.3024763625410025e-06, "epoch": 0.7737610725401005, "percentage": 77.39, "elapsed_time": "4:54:58", "remaining_time": "1:26:09", "throughput": 4098.5, "total_tokens": 72536000}
{"current_steps": 203, "total_steps": 261, "loss": 0.1285, "accuracy": 0.96875, "lr": 1.2606402416158391e-06, "epoch": 0.77759157289921, "percentage": 77.78, "elapsed_time": "4:56:27", "remaining_time": "1:24:42", "throughput": 4098.32, "total_tokens": 72900672}
{"current_steps": 204, "total_steps": 261, "loss": 0.1443, "accuracy": 0.9375, "lr": 1.2193899132928539e-06, "epoch": 0.7814220732583194, "percentage": 78.16, "elapsed_time": "4:57:51", "remaining_time": "1:23:13", "throughput": 4098.16, "total_tokens": 73242240}
{"current_steps": 205, "total_steps": 261, "loss": 0.1508, "accuracy": 0.9453125, "lr": 1.1787318396775188e-06, "epoch": 0.7852525736174287, "percentage": 78.54, "elapsed_time": "4:59:20", "remaining_time": "1:21:46", "throughput": 4098.1, "total_tokens": 73604288}
{"current_steps": 206, "total_steps": 261, "loss": 0.1296, "accuracy": 0.953125, "lr": 1.138672390095143e-06, "epoch": 0.7890830739765382, "percentage": 78.93, "elapsed_time": "5:00:45", "remaining_time": "1:20:17", "throughput": 4098.24, "total_tokens": 73953984}
{"current_steps": 207, "total_steps": 261, "loss": 0.1864, "accuracy": 0.9375, "lr": 1.0992178400930753e-06, "epoch": 0.7929135743356476, "percentage": 79.31, "elapsed_time": "5:02:15", "remaining_time": "1:18:50", "throughput": 4098.3, "total_tokens": 74322752}
{"current_steps": 208, "total_steps": 261, "loss": 0.1169, "accuracy": 0.9765625, "lr": 1.0603743704575992e-06, "epoch": 0.796744074694757, "percentage": 79.69, "elapsed_time": "5:03:45", "remaining_time": "1:17:24", "throughput": 4098.15, "total_tokens": 74692672}
{"current_steps": 209, "total_steps": 261, "loss": 0.1366, "accuracy": 0.9609375, "lr": 1.0221480662456845e-06, "epoch": 0.8005745750538664, "percentage": 80.08, "elapsed_time": "5:05:12", "remaining_time": "1:15:56", "throughput": 4098.05, "total_tokens": 75043648}
{"current_steps": 210, "total_steps": 261, "loss": 0.1543, "accuracy": 0.953125, "lr": 9.845449158317216e-07, "epoch": 0.8044050754129758, "percentage": 80.46, "elapsed_time": "5:06:41", "remaining_time": "1:14:28", "throughput": 4098.07, "total_tokens": 75408832}
{"current_steps": 211, "total_steps": 261, "loss": 0.0999, "accuracy": 0.9765625, "lr": 9.475708099694125e-07, "epoch": 0.8082355757720853, "percentage": 80.84, "elapsed_time": "5:08:12", "remaining_time": "1:13:01", "throughput": 4097.32, "total_tokens": 75767744}
{"current_steps": 212, "total_steps": 261, "loss": 0.1413, "accuracy": 0.953125, "lr": 9.112315408689415e-07, "epoch": 0.8120660761311946, "percentage": 81.23, "elapsed_time": "5:09:42", "remaining_time": "1:11:34", "throughput": 4097.68, "total_tokens": 76143744}
{"current_steps": 213, "total_steps": 261, "loss": 0.1615, "accuracy": 0.9375, "lr": 8.755328012896002e-07, "epoch": 0.815896576490304, "percentage": 81.61, "elapsed_time": "5:11:08", "remaining_time": "1:10:06", "throughput": 4097.34, "total_tokens": 76490112}
{"current_steps": 214, "total_steps": 261, "loss": 0.1372, "accuracy": 0.953125, "lr": 8.404801836479809e-07, "epoch": 0.8197270768494135, "percentage": 81.99, "elapsed_time": "5:12:38", "remaining_time": "1:08:39", "throughput": 4097.61, "total_tokens": 76866048}
{"current_steps": 215, "total_steps": 261, "loss": 0.166, "accuracy": 0.9375, "lr": 8.060791791418887e-07, "epoch": 0.8235575772085229, "percentage": 82.38, "elapsed_time": "5:14:11", "remaining_time": "1:07:13", "throughput": 4097.09, "total_tokens": 77235840}
{"current_steps": 216, "total_steps": 261, "loss": 0.146, "accuracy": 0.9609375, "lr": 7.723351768901172e-07, "epoch": 0.8273880775676322, "percentage": 82.76, "elapsed_time": "5:15:37", "remaining_time": "1:05:45", "throughput": 4097.11, "total_tokens": 77590592}
{"current_steps": 217, "total_steps": 261, "loss": 0.14, "accuracy": 0.96875, "lr": 7.392534630882092e-07, "epoch": 0.8312185779267417, "percentage": 83.14, "elapsed_time": "5:17:05", "remaining_time": "1:04:17", "throughput": 4097.05, "total_tokens": 77947072}
{"current_steps": 218, "total_steps": 261, "loss": 0.1216, "accuracy": 0.9609375, "lr": 7.06839220180342e-07, "epoch": 0.8350490782858511, "percentage": 83.52, "elapsed_time": "5:18:31", "remaining_time": "1:02:49", "throughput": 4097.07, "total_tokens": 78299264}
{"current_steps": 219, "total_steps": 261, "loss": 0.1551, "accuracy": 0.9453125, "lr": 6.750975260474718e-07, "epoch": 0.8388795786449605, "percentage": 83.91, "elapsed_time": "5:19:56", "remaining_time": "1:01:21", "throughput": 4097.51, "total_tokens": 78658112}
{"current_steps": 220, "total_steps": 261, "loss": 0.1226, "accuracy": 0.9765625, "lr": 6.440333532118503e-07, "epoch": 0.8427100790040699, "percentage": 84.29, "elapsed_time": "5:21:27", "remaining_time": "0:59:54", "throughput": 4097.05, "total_tokens": 79021824}
{"current_steps": 221, "total_steps": 261, "loss": 0.1023, "accuracy": 0.96875, "lr": 6.136515680580479e-07, "epoch": 0.8465405793631793, "percentage": 84.67, "elapsed_time": "5:22:55", "remaining_time": "0:58:26", "throughput": 4096.91, "total_tokens": 79377856}
{"current_steps": 222, "total_steps": 261, "loss": 0.1229, "accuracy": 0.9765625, "lr": 5.839569300706127e-07, "epoch": 0.8503710797222888, "percentage": 85.06, "elapsed_time": "5:24:22", "remaining_time": "0:56:59", "throughput": 4096.9, "total_tokens": 79735616}
{"current_steps": 223, "total_steps": 261, "loss": 0.1372, "accuracy": 0.9609375, "lr": 5.549540910884649e-07, "epoch": 0.8542015800813981, "percentage": 85.44, "elapsed_time": "5:25:53", "remaining_time": "0:55:32", "throughput": 4096.63, "total_tokens": 80104704}
{"current_steps": 224, "total_steps": 261, "loss": 0.0964, "accuracy": 0.9765625, "lr": 5.266475945761562e-07, "epoch": 0.8580320804405075, "percentage": 85.82, "elapsed_time": "5:27:16", "remaining_time": "0:54:03", "throughput": 4096.99, "total_tokens": 80450752}
{"current_steps": 225, "total_steps": 261, "loss": 0.1466, "accuracy": 0.953125, "lr": 4.990418749121179e-07, "epoch": 0.861862580799617, "percentage": 86.21, "elapsed_time": "5:28:45", "remaining_time": "0:52:36", "throughput": 4097.12, "total_tokens": 80818432}
{"current_steps": 226, "total_steps": 261, "loss": 0.1024, "accuracy": 0.9765625, "lr": 4.721412566939804e-07, "epoch": 0.8656930811587263, "percentage": 86.59, "elapsed_time": "5:30:13", "remaining_time": "0:51:08", "throughput": 4097.01, "total_tokens": 81175296}
{"current_steps": 227, "total_steps": 261, "loss": 0.1219, "accuracy": 0.9453125, "lr": 4.4594995406110785e-07, "epoch": 0.8695235815178358, "percentage": 86.97, "elapsed_time": "5:31:41", "remaining_time": "0:49:40", "throughput": 4096.62, "total_tokens": 81528576}
{"current_steps": 228, "total_steps": 261, "loss": 0.1465, "accuracy": 0.9453125, "lr": 4.2047207003442003e-07, "epoch": 0.8733540818769452, "percentage": 87.36, "elapsed_time": "5:33:11", "remaining_time": "0:48:13", "throughput": 4096.35, "total_tokens": 81893888}
{"current_steps": 229, "total_steps": 261, "loss": 0.1393, "accuracy": 0.9453125, "lr": 3.957115958736374e-07, "epoch": 0.8771845822360546, "percentage": 87.74, "elapsed_time": "5:34:30", "remaining_time": "0:46:44", "throughput": 4096.52, "total_tokens": 82220416}
{"current_steps": 230, "total_steps": 261, "loss": 0.1189, "accuracy": 0.953125, "lr": 3.7167241045202474e-07, "epoch": 0.881015082595164, "percentage": 88.12, "elapsed_time": "5:35:58", "remaining_time": "0:45:16", "throughput": 4096.7, "total_tokens": 82582784}
{"current_steps": 231, "total_steps": 261, "loss": 0.1095, "accuracy": 0.96875, "lr": 3.483582796487395e-07, "epoch": 0.8848455829542734, "percentage": 88.51, "elapsed_time": "5:37:28", "remaining_time": "0:43:49", "throughput": 4096.49, "total_tokens": 82945856}
{"current_steps": 232, "total_steps": 261, "loss": 0.1139, "accuracy": 0.96875, "lr": 3.257728557588902e-07, "epoch": 0.8886760833133828, "percentage": 88.89, "elapsed_time": "5:38:59", "remaining_time": "0:42:22", "throughput": 4096.68, "total_tokens": 83325760}
{"current_steps": 233, "total_steps": 261, "loss": 0.0973, "accuracy": 1.0, "lr": 3.039196769213787e-07, "epoch": 0.8925065836724922, "percentage": 89.27, "elapsed_time": "5:40:25", "remaining_time": "0:40:54", "throughput": 4097.05, "total_tokens": 83684032}
{"current_steps": 234, "total_steps": 261, "loss": 0.1432, "accuracy": 0.9765625, "lr": 2.828021665646341e-07, "epoch": 0.8963370840316016, "percentage": 89.66, "elapsed_time": "5:41:54", "remaining_time": "0:39:27", "throughput": 4097.49, "total_tokens": 84058624}
{"current_steps": 235, "total_steps": 261, "loss": 0.1677, "accuracy": 0.9609375, "lr": 2.6242363287030617e-07, "epoch": 0.900167584390711, "percentage": 90.04, "elapsed_time": "5:43:21", "remaining_time": "0:37:59", "throughput": 4097.62, "total_tokens": 84418816}
{"current_steps": 236, "total_steps": 261, "loss": 0.1739, "accuracy": 0.9453125, "lr": 2.4278726825502696e-07, "epoch": 0.9039980847498205, "percentage": 90.42, "elapsed_time": "5:44:53", "remaining_time": "0:36:32", "throughput": 4097.57, "total_tokens": 84791232}
{"current_steps": 237, "total_steps": 261, "loss": 0.1351, "accuracy": 0.953125, "lr": 2.2389614887029564e-07, "epoch": 0.9078285851089298, "percentage": 90.8, "elapsed_time": "5:46:20", "remaining_time": "0:35:04", "throughput": 4097.59, "total_tokens": 85148544}
{"current_steps": 238, "total_steps": 261, "loss": 0.166, "accuracy": 0.9296875, "lr": 2.0575323412058036e-07, "epoch": 0.9116590854680393, "percentage": 91.19, "elapsed_time": "5:47:46", "remaining_time": "0:33:36", "throughput": 4098.08, "total_tokens": 85514624}
{"current_steps": 239, "total_steps": 261, "loss": 0.1315, "accuracy": 0.9609375, "lr": 1.8836136619971468e-07, "epoch": 0.9154895858271487, "percentage": 91.57, "elapsed_time": "5:49:10", "remaining_time": "0:32:08", "throughput": 4098.46, "total_tokens": 85866560}
{"current_steps": 240, "total_steps": 261, "loss": 0.1289, "accuracy": 0.96875, "lr": 1.7172326964564777e-07, "epoch": 0.919320086186258, "percentage": 91.95, "elapsed_time": "5:50:39", "remaining_time": "0:30:40", "throughput": 4098.3, "total_tokens": 86227584}
{"current_steps": 241, "total_steps": 261, "loss": 0.1732, "accuracy": 0.9296875, "lr": 1.5584155091362907e-07, "epoch": 0.9231505865453675, "percentage": 92.34, "elapsed_time": "5:52:09", "remaining_time": "0:29:13", "throughput": 4098.57, "total_tokens": 86599360}
{"current_steps": 242, "total_steps": 261, "loss": 0.1152, "accuracy": 0.9921875, "lr": 1.4071869796789427e-07, "epoch": 0.9269810869044769, "percentage": 92.72, "elapsed_time": "5:53:38", "remaining_time": "0:27:45", "throughput": 4098.44, "total_tokens": 86962112}
{"current_steps": 243, "total_steps": 261, "loss": 0.1161, "accuracy": 0.9765625, "lr": 1.263570798919106e-07, "epoch": 0.9308115872635863, "percentage": 93.1, "elapsed_time": "5:55:04", "remaining_time": "0:26:18", "throughput": 4098.65, "total_tokens": 87320064}
{"current_steps": 244, "total_steps": 261, "loss": 0.1322, "accuracy": 0.953125, "lr": 1.1275894651724517e-07, "epoch": 0.9346420876226957, "percentage": 93.49, "elapsed_time": "5:56:31", "remaining_time": "0:24:50", "throughput": 4098.33, "total_tokens": 87670976}
{"current_steps": 245, "total_steps": 261, "loss": 0.1165, "accuracy": 0.9765625, "lr": 9.992642807111486e-08, "epoch": 0.9384725879818051, "percentage": 93.87, "elapsed_time": "5:57:52", "remaining_time": "0:23:22", "throughput": 4098.35, "total_tokens": 88002176}
{"current_steps": 246, "total_steps": 261, "loss": 0.0834, "accuracy": 1.0, "lr": 8.78615348426759e-08, "epoch": 0.9423030883409146, "percentage": 94.25, "elapsed_time": "5:59:18", "remaining_time": "0:21:54", "throughput": 4098.23, "total_tokens": 88350976}
{"current_steps": 247, "total_steps": 261, "loss": 0.1083, "accuracy": 0.9765625, "lr": 7.656615686809976e-08, "epoch": 0.946133588700024, "percentage": 94.64, "elapsed_time": "6:00:48", "remaining_time": "0:20:27", "throughput": 4098.07, "total_tokens": 88715456}
{"current_steps": 248, "total_steps": 261, "loss": 0.1025, "accuracy": 0.9765625, "lr": 6.604206363448662e-08, "epoch": 0.9499640890591333, "percentage": 95.02, "elapsed_time": "6:02:16", "remaining_time": "0:18:59", "throughput": 4098.4, "total_tokens": 89086656}
{"current_steps": 249, "total_steps": 261, "loss": 0.1172, "accuracy": 0.96875, "lr": 5.6290903802665444e-08, "epoch": 0.9537945894182428, "percentage": 95.4, "elapsed_time": "6:03:50", "remaining_time": "0:17:32", "throughput": 4098.28, "total_tokens": 89469120}
{"current_steps": 250, "total_steps": 261, "loss": 0.178, "accuracy": 0.9453125, "lr": 4.7314204948923356e-08, "epoch": 0.9576250897773522, "percentage": 95.79, "elapsed_time": "6:05:19", "remaining_time": "0:16:04", "throughput": 4098.31, "total_tokens": 89832832}
{"current_steps": 251, "total_steps": 261, "loss": 0.1803, "accuracy": 0.921875, "lr": 3.911337332569876e-08, "epoch": 0.9614555901364615, "percentage": 96.17, "elapsed_time": "6:06:45", "remaining_time": "0:14:36", "throughput": 4098.24, "total_tokens": 90184960}
{"current_steps": 252, "total_steps": 261, "loss": 0.122, "accuracy": 0.9609375, "lr": 3.168969364128527e-08, "epoch": 0.965286090495571, "percentage": 96.55, "elapsed_time": "6:08:14", "remaining_time": "0:13:09", "throughput": 4097.87, "total_tokens": 90540608}
{"current_steps": 253, "total_steps": 261, "loss": 0.136, "accuracy": 0.9609375, "lr": 2.5044328858576105e-08, "epoch": 0.9691165908546804, "percentage": 96.93, "elapsed_time": "6:09:42", "remaining_time": "0:11:41", "throughput": 4097.92, "total_tokens": 90903552}
{"current_steps": 254, "total_steps": 261, "loss": 0.1234, "accuracy": 0.9609375, "lr": 1.917832001287645e-08, "epoch": 0.9729470912137897, "percentage": 97.32, "elapsed_time": "6:11:20", "remaining_time": "0:10:14", "throughput": 4096.7, "total_tokens": 91277824}
{"current_steps": 255, "total_steps": 261, "loss": 0.128, "accuracy": 0.96875, "lr": 1.4092586048820578e-08, "epoch": 0.9767775915728992, "percentage": 97.7, "elapsed_time": "6:12:47", "remaining_time": "0:08:46", "throughput": 4096.87, "total_tokens": 91637568}
{"current_steps": 256, "total_steps": 261, "loss": 0.1089, "accuracy": 0.9765625, "lr": 9.787923676414235e-09, "epoch": 0.9806080919320086, "percentage": 98.08, "elapsed_time": "6:14:13", "remaining_time": "0:07:18", "throughput": 4096.75, "total_tokens": 91986624}
{"current_steps": 257, "total_steps": 261, "loss": 0.1555, "accuracy": 0.9609375, "lr": 6.265007246223365e-09, "epoch": 0.9844385922911181, "percentage": 98.47, "elapsed_time": "6:15:44", "remaining_time": "0:05:50", "throughput": 4096.68, "total_tokens": 92359232}
{"current_steps": 258, "total_steps": 261, "loss": 0.1283, "accuracy": 0.9765625, "lr": 3.524388643736387e-09, "epoch": 0.9882690926502274, "percentage": 98.85, "elapsed_time": "6:17:14", "remaining_time": "0:04:23", "throughput": 4096.59, "total_tokens": 92725888}
{"current_steps": 259, "total_steps": 261, "loss": 0.1709, "accuracy": 0.921875, "lr": 1.566497202904471e-09, "epoch": 0.9920995930093368, "percentage": 99.23, "elapsed_time": "6:18:44", "remaining_time": "0:02:55", "throughput": 4096.49, "total_tokens": 93092224}
{"current_steps": 260, "total_steps": 261, "loss": 0.1259, "accuracy": 0.9609375, "lr": 3.916396388869981e-10, "epoch": 0.9959300933684463, "percentage": 99.62, "elapsed_time": "6:20:10", "remaining_time": "0:01:27", "throughput": 4096.79, "total_tokens": 93450688}
{"current_steps": 261, "total_steps": 261, "loss": 0.1391, "accuracy": 0.9609375, "lr": 0.0, "epoch": 0.9997605937275557, "percentage": 100.0, "elapsed_time": "6:21:36", "remaining_time": "0:00:00", "throughput": 4096.69, "total_tokens": 93801152}
{"current_steps": 261, "total_steps": 261, "epoch": 0.9997605937275557, "percentage": 100.0, "elapsed_time": "6:21:40", "remaining_time": "0:00:00", "throughput": 4096.07, "total_tokens": 93801152}