zrrraa's picture
test
578c498
{"current_steps": 5, "total_steps": 160, "loss": 2.8056, "lr": 4.987961816680492e-05, "epoch": 0.1532567049808429, "percentage": 3.12, "elapsed_time": "0:09:45", "remaining_time": "5:02:26", "throughput": 2239.08, "total_tokens": 1310720}
{"current_steps": 10, "total_steps": 160, "loss": 2.6896, "lr": 4.951963201008076e-05, "epoch": 0.3065134099616858, "percentage": 6.25, "elapsed_time": "0:19:31", "remaining_time": "4:52:56", "throughput": 2237.22, "total_tokens": 2621440}
{"current_steps": 15, "total_steps": 160, "loss": 2.6174, "lr": 4.892350839330522e-05, "epoch": 0.45977011494252873, "percentage": 9.38, "elapsed_time": "0:29:18", "remaining_time": "4:43:18", "throughput": 2236.16, "total_tokens": 3932160}
{"current_steps": 20, "total_steps": 160, "loss": 2.6063, "lr": 4.8096988312782174e-05, "epoch": 0.6130268199233716, "percentage": 12.5, "elapsed_time": "0:39:05", "remaining_time": "4:33:37", "throughput": 2235.42, "total_tokens": 5242880}
{"current_steps": 25, "total_steps": 160, "loss": 2.5881, "lr": 4.7048031608708876e-05, "epoch": 0.7662835249042146, "percentage": 15.62, "elapsed_time": "0:48:52", "remaining_time": "4:23:55", "throughput": 2234.75, "total_tokens": 6553600}
{"current_steps": 30, "total_steps": 160, "loss": 2.5797, "lr": 4.5786740307563636e-05, "epoch": 0.9195402298850575, "percentage": 18.75, "elapsed_time": "0:58:40", "remaining_time": "4:14:13", "throughput": 2234.15, "total_tokens": 7864320}
{"current_steps": 35, "total_steps": 160, "loss": 3.0665, "lr": 4.4325261334068426e-05, "epoch": 1.0919540229885056, "percentage": 21.88, "elapsed_time": "1:08:42", "remaining_time": "4:05:22", "throughput": 2233.66, "total_tokens": 9207808}
{"current_steps": 40, "total_steps": 160, "loss": 2.5453, "lr": 4.267766952966369e-05, "epoch": 1.2452107279693487, "percentage": 25.0, "elapsed_time": "1:18:30", "remaining_time": "3:55:31", "throughput": 2232.93, "total_tokens": 10518528}
{"current_steps": 45, "total_steps": 160, "loss": 2.5496, "lr": 4.085983210409114e-05, "epoch": 1.3984674329501916, "percentage": 28.12, "elapsed_time": "1:28:19", "remaining_time": "3:45:42", "throughput": 2232.18, "total_tokens": 11829248}
{"current_steps": 50, "total_steps": 160, "loss": 2.5288, "lr": 3.888925582549006e-05, "epoch": 1.5517241379310345, "percentage": 31.25, "elapsed_time": "1:38:08", "remaining_time": "3:35:54", "throughput": 2231.47, "total_tokens": 13139968}
{"current_steps": 55, "total_steps": 160, "loss": 2.5052, "lr": 3.678491842064995e-05, "epoch": 1.7049808429118773, "percentage": 34.38, "elapsed_time": "1:48:00", "remaining_time": "3:26:11", "throughput": 2230.01, "total_tokens": 14450688}
{"current_steps": 60, "total_steps": 160, "loss": 2.5119, "lr": 3.456708580912725e-05, "epoch": 1.8582375478927204, "percentage": 37.5, "elapsed_time": "1:57:49", "remaining_time": "3:16:22", "throughput": 2229.48, "total_tokens": 15761408}
{"current_steps": 65, "total_steps": 160, "loss": 2.9943, "lr": 3.225711693136156e-05, "epoch": 2.0306513409961684, "percentage": 40.62, "elapsed_time": "2:07:54", "remaining_time": "3:06:56", "throughput": 2228.86, "total_tokens": 17104896}
{"current_steps": 70, "total_steps": 160, "loss": 2.4739, "lr": 2.9877258050403212e-05, "epoch": 2.1839080459770113, "percentage": 43.75, "elapsed_time": "2:17:44", "remaining_time": "2:57:05", "throughput": 2228.32, "total_tokens": 18415616}
{"current_steps": 75, "total_steps": 160, "loss": 2.488, "lr": 2.7450428508239024e-05, "epoch": 2.3371647509578546, "percentage": 46.88, "elapsed_time": "2:27:34", "remaining_time": "2:47:15", "throughput": 2227.75, "total_tokens": 19726336}
{"current_steps": 80, "total_steps": 160, "loss": 2.4769, "lr": 2.5e-05, "epoch": 2.4904214559386975, "percentage": 50.0, "elapsed_time": "2:37:25", "remaining_time": "2:37:25", "throughput": 2227.21, "total_tokens": 21037056}
{"current_steps": 85, "total_steps": 160, "loss": 2.4775, "lr": 2.2549571491760986e-05, "epoch": 2.6436781609195403, "percentage": 53.12, "elapsed_time": "2:47:15", "remaining_time": "2:27:35", "throughput": 2226.78, "total_tokens": 22347776}
{"current_steps": 90, "total_steps": 160, "loss": 2.4609, "lr": 2.0122741949596797e-05, "epoch": 2.796934865900383, "percentage": 56.25, "elapsed_time": "2:57:06", "remaining_time": "2:17:45", "throughput": 2226.34, "total_tokens": 23658496}
{"current_steps": 95, "total_steps": 160, "loss": 2.451, "lr": 1.7742883068638447e-05, "epoch": 2.950191570881226, "percentage": 59.38, "elapsed_time": "3:06:57", "remaining_time": "2:07:55", "throughput": 2225.93, "total_tokens": 24969216}
{"current_steps": 100, "total_steps": 160, "loss": 2.9574, "lr": 1.5432914190872757e-05, "epoch": 3.1226053639846745, "percentage": 62.5, "elapsed_time": "3:17:03", "remaining_time": "1:58:13", "throughput": 2225.55, "total_tokens": 26312704}
{"current_steps": 105, "total_steps": 160, "loss": 2.4421, "lr": 1.3215081579350058e-05, "epoch": 3.2758620689655173, "percentage": 65.62, "elapsed_time": "3:26:56", "remaining_time": "1:48:23", "throughput": 2224.75, "total_tokens": 27623424}
{"current_steps": 110, "total_steps": 160, "loss": 2.4503, "lr": 1.1110744174509952e-05, "epoch": 3.42911877394636, "percentage": 68.75, "elapsed_time": "3:36:47", "remaining_time": "1:38:32", "throughput": 2224.42, "total_tokens": 28934144}
{"current_steps": 115, "total_steps": 160, "loss": 2.449, "lr": 9.140167895908867e-06, "epoch": 3.582375478927203, "percentage": 71.88, "elapsed_time": "3:46:38", "remaining_time": "1:28:41", "throughput": 2224.12, "total_tokens": 30244864}
{"current_steps": 120, "total_steps": 160, "loss": 2.4431, "lr": 7.3223304703363135e-06, "epoch": 3.735632183908046, "percentage": 75.0, "elapsed_time": "3:56:29", "remaining_time": "1:18:49", "throughput": 2223.85, "total_tokens": 31555584}
{"current_steps": 125, "total_steps": 160, "loss": 2.4269, "lr": 5.674738665931575e-06, "epoch": 3.888888888888889, "percentage": 78.12, "elapsed_time": "4:06:20", "remaining_time": "1:08:58", "throughput": 2223.6, "total_tokens": 32866304}
{"current_steps": 130, "total_steps": 160, "loss": 2.8999, "lr": 4.213259692436367e-06, "epoch": 4.061302681992337, "percentage": 81.25, "elapsed_time": "4:16:26", "remaining_time": "0:59:10", "throughput": 2223.32, "total_tokens": 34209792}
{"current_steps": 135, "total_steps": 160, "loss": 2.4248, "lr": 2.9519683912911266e-06, "epoch": 4.21455938697318, "percentage": 84.38, "elapsed_time": "4:26:18", "remaining_time": "0:49:18", "throughput": 2223.08, "total_tokens": 35520512}
{"current_steps": 140, "total_steps": 160, "loss": 2.4492, "lr": 1.9030116872178316e-06, "epoch": 4.3678160919540225, "percentage": 87.5, "elapsed_time": "4:36:09", "remaining_time": "0:39:27", "throughput": 2222.86, "total_tokens": 36831232}
{"current_steps": 145, "total_steps": 160, "loss": 2.4198, "lr": 1.0764916066947794e-06, "epoch": 4.521072796934866, "percentage": 90.62, "elapsed_time": "4:46:00", "remaining_time": "0:29:35", "throughput": 2222.63, "total_tokens": 38141952}
{"current_steps": 150, "total_steps": 160, "loss": 2.4283, "lr": 4.803679899192392e-07, "epoch": 4.674329501915709, "percentage": 93.75, "elapsed_time": "4:55:51", "remaining_time": "0:19:43", "throughput": 2222.45, "total_tokens": 39452672}
{"current_steps": 155, "total_steps": 160, "loss": 2.4316, "lr": 1.2038183319507955e-07, "epoch": 4.827586206896552, "percentage": 96.88, "elapsed_time": "5:05:45", "remaining_time": "0:09:51", "throughput": 2222.01, "total_tokens": 40763392}
{"current_steps": 160, "total_steps": 160, "loss": 2.4379, "lr": 0.0, "epoch": 4.980842911877395, "percentage": 100.0, "elapsed_time": "5:15:36", "remaining_time": "0:00:00", "throughput": 2221.84, "total_tokens": 42074112}
{"current_steps": 160, "total_steps": 160, "epoch": 4.980842911877395, "percentage": 100.0, "elapsed_time": "5:15:38", "remaining_time": "0:00:00", "throughput": 2221.57, "total_tokens": 42074112}