Team Ai
Modelpublic

cuong1692001/Terminal-scientific_computing

sourceHugging Faceotherupdated 4mo agoView on Hugging Face
0likes8downloads
trainer_log.jsonl1953 linesDownload Raw Back to root
1{"current_steps": 5, "total_steps": 9742, "loss": 0.6884, "lr": 9.99999584028644e-06, "epoch": 0.0010264832683227264, "percentage": 0.05, "elapsed_time": "0:00:31", "remaining_time": "17:01:45", "throughput": 9176.48, "total_tokens": 288880}2{"current_steps": 10, "total_steps": 9742, "loss": 0.6057, "lr": 9.999978941461961e-06, "epoch": 0.0020529665366454527, "percentage": 0.1, "elapsed_time": "0:01:05", "remaining_time": "17:43:33", "throughput": 9059.31, "total_tokens": 594024}3{"current_steps": 15, "total_steps": 9742, "loss": 0.5585, "lr": 9.999949043588364e-06, "epoch": 0.003079449804968179, "percentage": 0.15, "elapsed_time": "0:01:32", "remaining_time": "16:44:12", "throughput": 9509.93, "total_tokens": 883616}4{"current_steps": 5, "total_steps": 9742, "loss": 0.6885, "lr": 9.99999584028644e-06, "epoch": 0.0010264832683227264, "percentage": 0.05, "elapsed_time": "0:00:31", "remaining_time": "16:48:06", "throughput": 9300.73, "total_tokens": 288880}5{"current_steps": 10, "total_steps": 9742, "loss": 0.6061, "lr": 9.999978941461961e-06, "epoch": 0.0020529665366454527, "percentage": 0.1, "elapsed_time": "0:01:05", "remaining_time": "17:39:07", "throughput": 9097.13, "total_tokens": 594024}6{"current_steps": 15, "total_steps": 9742, "loss": 0.5583, "lr": 9.999949043588364e-06, "epoch": 0.003079449804968179, "percentage": 0.15, "elapsed_time": "0:01:32", "remaining_time": "16:44:32", "throughput": 9506.71, "total_tokens": 883616}7{"current_steps": 20, "total_steps": 9742, "loss": 0.5532, "lr": 9.999906146743383e-06, "epoch": 0.0041059330732909054, "percentage": 0.21, "elapsed_time": "0:01:58", "remaining_time": "16:00:41", "throughput": 9615.5, "total_tokens": 1140208}8{"current_steps": 25, "total_steps": 9742, "loss": 0.5169, "lr": 9.999850251038536e-06, "epoch": 0.005132416341613631, "percentage": 0.26, "elapsed_time": "0:02:29", "remaining_time": "16:10:32", "throughput": 9316.66, "total_tokens": 1395832}9{"current_steps": 30, "total_steps": 9742, "loss": 0.5023, "lr": 9.999781356619146e-06, "epoch": 0.006158899609936358, "percentage": 0.31, "elapsed_time": "0:03:01", "remaining_time": "16:17:28", "throughput": 9242.0, "total_tokens": 1674296}10{"current_steps": 35, "total_steps": 9742, "loss": 0.4917, "lr": 9.999699463664327e-06, "epoch": 0.007185382878259084, "percentage": 0.36, "elapsed_time": "0:03:25", "remaining_time": "15:49:22", "throughput": 9555.09, "total_tokens": 1962496}11{"current_steps": 40, "total_steps": 9742, "loss": 0.4884, "lr": 9.999604572386982e-06, "epoch": 0.008211866146581811, "percentage": 0.41, "elapsed_time": "0:03:54", "remaining_time": "15:46:24", "throughput": 9672.19, "total_tokens": 2264416}12{"current_steps": 45, "total_steps": 9742, "loss": 0.4867, "lr": 9.999496683033817e-06, "epoch": 0.009238349414904538, "percentage": 0.46, "elapsed_time": "0:04:23", "remaining_time": "15:47:04", "throughput": 9669.87, "total_tokens": 2549952}13{"current_steps": 50, "total_steps": 9742, "loss": 0.4769, "lr": 9.999375795885318e-06, "epoch": 0.010264832683227263, "percentage": 0.51, "elapsed_time": "0:04:57", "remaining_time": "16:00:28", "throughput": 9451.38, "total_tokens": 2809896}14{"current_steps": 55, "total_steps": 9742, "loss": 0.496, "lr": 9.999241911255774e-06, "epoch": 0.01129131595154999, "percentage": 0.56, "elapsed_time": "0:05:33", "remaining_time": "16:17:50", "throughput": 9349.78, "total_tokens": 3114560}15{"current_steps": 60, "total_steps": 9742, "loss": 0.4818, "lr": 9.99909502949326e-06, "epoch": 0.012317799219872716, "percentage": 0.62, "elapsed_time": "0:06:02", "remaining_time": "16:15:12", "throughput": 9332.25, "total_tokens": 3383920}16{"current_steps": 65, "total_steps": 9742, "loss": 0.4822, "lr": 9.998935150979644e-06, "epoch": 0.013344282488195443, "percentage": 0.67, "elapsed_time": "0:06:29", "remaining_time": "16:07:41", "throughput": 9330.46, "total_tokens": 3638840}17{"current_steps": 70, "total_steps": 9742, "loss": 0.4848, "lr": 9.99876227613058e-06, "epoch": 0.014370765756518168, "percentage": 0.72, "elapsed_time": "0:07:00", "remaining_time": "16:07:55", "throughput": 9270.48, "total_tokens": 3896512}18{"current_steps": 75, "total_steps": 9742, "loss": 0.4626, "lr": 9.998576405395512e-06, "epoch": 0.015397249024840895, "percentage": 0.77, "elapsed_time": "0:07:33", "remaining_time": "16:13:16", "throughput": 9225.83, "total_tokens": 4179824}19{"current_steps": 80, "total_steps": 9742, "loss": 0.4428, "lr": 9.998377539257669e-06, "epoch": 0.016423732293163622, "percentage": 0.82, "elapsed_time": "0:07:59", "remaining_time": "16:05:53", "throughput": 9248.64, "total_tokens": 4437944}20{"current_steps": 85, "total_steps": 9742, "loss": 0.4362, "lr": 9.998165678234071e-06, "epoch": 0.01745021556148635, "percentage": 0.87, "elapsed_time": "0:08:28", "remaining_time": "16:02:32", "throughput": 9246.9, "total_tokens": 4700480}21{"current_steps": 90, "total_steps": 9742, "loss": 0.4782, "lr": 9.997940822875514e-06, "epoch": 0.018476698829809075, "percentage": 0.92, "elapsed_time": "0:09:04", "remaining_time": "16:12:42", "throughput": 9150.1, "total_tokens": 4979472}22{"current_steps": 95, "total_steps": 9742, "loss": 0.4564, "lr": 9.997702973766586e-06, "epoch": 0.019503182098131802, "percentage": 0.98, "elapsed_time": "0:09:34", "remaining_time": "16:11:33", "throughput": 9188.26, "total_tokens": 5274512}23{"current_steps": 100, "total_steps": 9742, "loss": 0.4263, "lr": 9.997452131525647e-06, "epoch": 0.020529665366454525, "percentage": 1.03, "elapsed_time": "0:10:10", "remaining_time": "16:20:34", "throughput": 9091.85, "total_tokens": 5547736}24{"current_steps": 105, "total_steps": 9742, "loss": 0.4807, "lr": 9.997188296804848e-06, "epoch": 0.021556148634777252, "percentage": 1.08, "elapsed_time": "0:10:41", "remaining_time": "16:20:57", "throughput": 9082.4, "total_tokens": 5824416}25{"current_steps": 110, "total_steps": 9742, "loss": 0.4666, "lr": 9.996911470290107e-06, "epoch": 0.02258263190309998, "percentage": 1.13, "elapsed_time": "0:11:09", "remaining_time": "16:17:08", "throughput": 9109.61, "total_tokens": 6099384}26{"current_steps": 115, "total_steps": 9742, "loss": 0.4539, "lr": 9.996621652701127e-06, "epoch": 0.023609115171422706, "percentage": 1.18, "elapsed_time": "0:11:43", "remaining_time": "16:21:53", "throughput": 9059.82, "total_tokens": 6375920}27{"current_steps": 120, "total_steps": 9742, "loss": 0.4803, "lr": 9.99631884479138e-06, "epoch": 0.024635598439745433, "percentage": 1.23, "elapsed_time": "0:12:14", "remaining_time": "16:21:19", "throughput": 9071.64, "total_tokens": 6661424}28{"current_steps": 125, "total_steps": 9742, "loss": 0.4897, "lr": 9.99600304734811e-06, "epoch": 0.02566208170806816, "percentage": 1.28, "elapsed_time": "0:12:46", "remaining_time": "16:22:34", "throughput": 9058.61, "total_tokens": 6941384}29{"current_steps": 130, "total_steps": 9742, "loss": 0.4609, "lr": 9.995674261192339e-06, "epoch": 0.026688564976390886, "percentage": 1.33, "elapsed_time": "0:13:19", "remaining_time": "16:25:33", "throughput": 9022.36, "total_tokens": 7215808}30{"current_steps": 135, "total_steps": 9742, "loss": 0.4521, "lr": 9.995332487178848e-06, "epoch": 0.02771504824471361, "percentage": 1.39, "elapsed_time": "0:13:54", "remaining_time": "16:29:32", "throughput": 8985.16, "total_tokens": 7496440}31{"current_steps": 140, "total_steps": 9742, "loss": 0.4183, "lr": 9.99497772619619e-06, "epoch": 0.028741531513036336, "percentage": 1.44, "elapsed_time": "0:14:23", "remaining_time": "16:27:15", "throughput": 8980.15, "total_tokens": 7755872}32{"current_steps": 145, "total_steps": 9742, "loss": 0.411, "lr": 9.994609979166677e-06, "epoch": 0.029768014781359063, "percentage": 1.49, "elapsed_time": "0:14:50", "remaining_time": "16:22:19", "throughput": 9023.65, "total_tokens": 8035704}33{"current_steps": 150, "total_steps": 9742, "loss": 0.4551, "lr": 9.99422924704639e-06, "epoch": 0.03079449804968179, "percentage": 1.54, "elapsed_time": "0:15:21", "remaining_time": "16:22:10", "throughput": 9041.72, "total_tokens": 8332528}34{"current_steps": 155, "total_steps": 9742, "loss": 0.4441, "lr": 9.99383553082516e-06, "epoch": 0.03182098131800452, "percentage": 1.59, "elapsed_time": "0:15:55", "remaining_time": "16:24:29", "throughput": 9005.6, "total_tokens": 8600584}35{"current_steps": 160, "total_steps": 9742, "loss": 0.442, "lr": 9.993428831526583e-06, "epoch": 0.032847464586327244, "percentage": 1.64, "elapsed_time": "0:16:27", "remaining_time": "16:25:18", "throughput": 8990.02, "total_tokens": 8874504}36{"current_steps": 165, "total_steps": 9742, "loss": 0.4264, "lr": 9.993009150208e-06, "epoch": 0.03387394785464997, "percentage": 1.69, "elapsed_time": "0:17:02", "remaining_time": "16:29:11", "throughput": 8972.51, "total_tokens": 9174808}37{"current_steps": 170, "total_steps": 9742, "loss": 0.4516, "lr": 9.99257648796051e-06, "epoch": 0.0349004311229727, "percentage": 1.75, "elapsed_time": "0:17:31", "remaining_time": "16:26:35", "throughput": 9001.52, "total_tokens": 9463536}38{"current_steps": 175, "total_steps": 9742, "loss": 0.452, "lr": 9.992130845908956e-06, "epoch": 0.035926914391295424, "percentage": 1.8, "elapsed_time": "0:18:04", "remaining_time": "16:28:00", "throughput": 8979.56, "total_tokens": 9737080}39{"current_steps": 180, "total_steps": 9742, "loss": 0.4833, "lr": 9.991672225211928e-06, "epoch": 0.03695339765961815, "percentage": 1.85, "elapsed_time": "0:18:32", "remaining_time": "16:24:41", "throughput": 9008.31, "total_tokens": 10018904}40{"current_steps": 185, "total_steps": 9742, "loss": 0.4474, "lr": 9.991200627061757e-06, "epoch": 0.03797988092794088, "percentage": 1.9, "elapsed_time": "0:19:05", "remaining_time": "16:26:14", "throughput": 8991.18, "total_tokens": 10299080}41{"current_steps": 190, "total_steps": 9742, "loss": 0.4477, "lr": 9.990716052684515e-06, "epoch": 0.039006364196263604, "percentage": 1.95, "elapsed_time": "0:19:37", "remaining_time": "16:26:53", "throughput": 8988.85, "total_tokens": 10587232}42{"current_steps": 195, "total_steps": 9742, "loss": 0.436, "lr": 9.990218503340007e-06, "epoch": 0.040032847464586324, "percentage": 2.0, "elapsed_time": "0:20:02", "remaining_time": "16:21:36", "throughput": 9025.21, "total_tokens": 10857048}43{"current_steps": 200, "total_steps": 9742, "loss": 0.4474, "lr": 9.989707980321772e-06, "epoch": 0.04105933073290905, "percentage": 2.05, "elapsed_time": "0:20:25", "remaining_time": "16:14:18", "throughput": 9099.92, "total_tokens": 11149960}44{"current_steps": 205, "total_steps": 9742, "loss": 0.4411, "lr": 9.989184484957081e-06, "epoch": 0.04208581400123178, "percentage": 2.1, "elapsed_time": "0:20:54", "remaining_time": "16:12:34", "throughput": 9115.13, "total_tokens": 11433584}45{"current_steps": 210, "total_steps": 9742, "loss": 0.3998, "lr": 9.988648018606926e-06, "epoch": 0.043112297269554505, "percentage": 2.16, "elapsed_time": "0:21:26", "remaining_time": "16:12:58", "throughput": 9105.49, "total_tokens": 11710848}46{"current_steps": 215, "total_steps": 9742, "loss": 0.4286, "lr": 9.988098582666022e-06, "epoch": 0.04413878053787723, "percentage": 2.21, "elapsed_time": "0:21:53", "remaining_time": "16:09:47", "throughput": 9121.28, "total_tokens": 11977560}47{"current_steps": 220, "total_steps": 9742, "loss": 0.4306, "lr": 9.987536178562806e-06, "epoch": 0.04516526380619996, "percentage": 2.26, "elapsed_time": "0:22:25", "remaining_time": "16:10:43", "throughput": 9111.54, "total_tokens": 12261280}48{"current_steps": 225, "total_steps": 9742, "loss": 0.4373, "lr": 9.986960807759428e-06, "epoch": 0.046191747074522685, "percentage": 2.31, "elapsed_time": "0:22:57", "remaining_time": "16:11:00", "throughput": 9095.65, "total_tokens": 12528344}49{"current_steps": 230, "total_steps": 9742, "loss": 0.4402, "lr": 9.986372471751749e-06, "epoch": 0.04721823034284541, "percentage": 2.36, "elapsed_time": "0:23:26", "remaining_time": "16:09:44", "throughput": 9109.64, "total_tokens": 12816320}50{"current_steps": 235, "total_steps": 9742, "loss": 0.466, "lr": 9.985771172069337e-06, "epoch": 0.04824471361116814, "percentage": 2.41, "elapsed_time": "0:23:57", "remaining_time": "16:09:19", "throughput": 9121.56, "total_tokens": 13113376}51{"current_steps": 240, "total_steps": 9742, "loss": 0.4307, "lr": 9.98515691027546e-06, "epoch": 0.049271196879490865, "percentage": 2.46, "elapsed_time": "0:24:24", "remaining_time": "16:06:14", "throughput": 9135.27, "total_tokens": 13376944}52{"current_steps": 245, "total_steps": 9742, "loss": 0.4355, "lr": 9.984529687967094e-06, "epoch": 0.05029768014781359, "percentage": 2.51, "elapsed_time": "0:24:59", "remaining_time": "16:08:31", "throughput": 9115.15, "total_tokens": 13664848}53{"current_steps": 250, "total_steps": 9742, "loss": 0.4257, "lr": 9.983889506774902e-06, "epoch": 0.05132416341613632, "percentage": 2.57, "elapsed_time": "0:25:32", "remaining_time": "16:09:44", "throughput": 9081.16, "total_tokens": 13916624}54{"current_steps": 255, "total_steps": 9742, "loss": 0.402, "lr": 9.98323636836324e-06, "epoch": 0.052350646684459046, "percentage": 2.62, "elapsed_time": "0:26:05", "remaining_time": "16:10:51", "throughput": 9078.12, "total_tokens": 14213848}55{"current_steps": 260, "total_steps": 9742, "loss": 0.3991, "lr": 9.982570274430152e-06, "epoch": 0.05337712995278177, "percentage": 2.67, "elapsed_time": "0:26:36", "remaining_time": "16:10:25", "throughput": 9066.62, "total_tokens": 14475360}56{"current_steps": 265, "total_steps": 9742, "loss": 0.4315, "lr": 9.98189122670736e-06, "epoch": 0.0544036132211045, "percentage": 2.72, "elapsed_time": "0:27:09", "remaining_time": "16:11:00", "throughput": 9063.6, "total_tokens": 14765488}57{"current_steps": 270, "total_steps": 9742, "loss": 0.4272, "lr": 9.981199226960272e-06, "epoch": 0.05543009648942722, "percentage": 2.77, "elapsed_time": "0:27:37", "remaining_time": "16:08:54", "throughput": 9073.16, "total_tokens": 15035456}58{"current_steps": 275, "total_steps": 9742, "loss": 0.4489, "lr": 9.980494276987957e-06, "epoch": 0.056456579757749946, "percentage": 2.82, "elapsed_time": "0:28:07", "remaining_time": "16:08:04", "throughput": 9070.56, "total_tokens": 15304240}59{"current_steps": 280, "total_steps": 9742, "loss": 0.4397, "lr": 9.979776378623163e-06, "epoch": 0.05748306302607267, "percentage": 2.87, "elapsed_time": "0:28:32", "remaining_time": "16:04:15", "throughput": 9104.41, "total_tokens": 15587400}60{"current_steps": 285, "total_steps": 9742, "loss": 0.4099, "lr": 9.979045533732294e-06, "epoch": 0.0585095462943954, "percentage": 2.93, "elapsed_time": "0:29:01", "remaining_time": "16:02:54", "throughput": 9112.8, "total_tokens": 15866456}61{"current_steps": 290, "total_steps": 9742, "loss": 0.4569, "lr": 9.978301744215418e-06, "epoch": 0.059536029562718126, "percentage": 2.98, "elapsed_time": "0:29:28", "remaining_time": "16:00:41", "throughput": 9123.99, "total_tokens": 16135824}62{"current_steps": 295, "total_steps": 9742, "loss": 0.4223, "lr": 9.977545012006254e-06, "epoch": 0.06056251283104085, "percentage": 3.03, "elapsed_time": "0:30:07", "remaining_time": "16:04:39", "throughput": 9088.11, "total_tokens": 16425752}63{"current_steps": 300, "total_steps": 9742, "loss": 0.4077, "lr": 9.97677533907217e-06, "epoch": 0.06158899609936358, "percentage": 3.08, "elapsed_time": "0:30:38", "remaining_time": "16:04:11", "throughput": 9080.26, "total_tokens": 16690656}64{"current_steps": 305, "total_steps": 9742, "loss": 0.4447, "lr": 9.975992727414177e-06, "epoch": 0.06261547936768631, "percentage": 3.13, "elapsed_time": "0:31:08", "remaining_time": "16:03:42", "throughput": 9070.06, "total_tokens": 16950272}65{"current_steps": 310, "total_steps": 9742, "loss": 0.4192, "lr": 9.975197179066925e-06, "epoch": 0.06364196263600903, "percentage": 3.18, "elapsed_time": "0:31:38", "remaining_time": "16:02:31", "throughput": 9073.27, "total_tokens": 17222032}66{"current_steps": 315, "total_steps": 9742, "loss": 0.43, "lr": 9.974388696098699e-06, "epoch": 0.06466844590433175, "percentage": 3.23, "elapsed_time": "0:32:06", "remaining_time": "16:00:57", "throughput": 9091.86, "total_tokens": 17516576}67{"current_steps": 320, "total_steps": 9742, "loss": 0.4351, "lr": 9.973567280611407e-06, "epoch": 0.06569492917265449, "percentage": 3.28, "elapsed_time": "0:32:41", "remaining_time": "16:02:25", "throughput": 9075.43, "total_tokens": 17798968}68{"current_steps": 325, "total_steps": 9742, "loss": 0.4248, "lr": 9.972732934740586e-06, "epoch": 0.0667214124409772, "percentage": 3.34, "elapsed_time": "0:33:06", "remaining_time": "15:59:30", "throughput": 9094.06, "total_tokens": 18068920}69{"current_steps": 330, "total_steps": 9742, "loss": 0.423, "lr": 9.971885660655381e-06, "epoch": 0.06774789570929994, "percentage": 3.39, "elapsed_time": "0:33:30", "remaining_time": "15:55:41", "throughput": 9117.73, "total_tokens": 18331136}70{"current_steps": 335, "total_steps": 9742, "loss": 0.4236, "lr": 9.971025460558556e-06, "epoch": 0.06877437897762266, "percentage": 3.44, "elapsed_time": "0:34:02", "remaining_time": "15:55:58", "throughput": 9103.47, "total_tokens": 18595112}71{"current_steps": 340, "total_steps": 9742, "loss": 0.4037, "lr": 9.970152336686476e-06, "epoch": 0.0698008622459454, "percentage": 3.49, "elapsed_time": "0:34:29", "remaining_time": "15:53:48", "throughput": 9120.69, "total_tokens": 18875496}72{"current_steps": 345, "total_steps": 9742, "loss": 0.4363, "lr": 9.969266291309105e-06, "epoch": 0.07082734551426811, "percentage": 3.54, "elapsed_time": "0:35:05", "remaining_time": "15:55:37", "throughput": 9099.28, "total_tokens": 19154760}73{"current_steps": 350, "total_steps": 9742, "loss": 0.411, "lr": 9.968367326730006e-06, "epoch": 0.07185382878259085, "percentage": 3.59, "elapsed_time": "0:35:35", "remaining_time": "15:55:02", "throughput": 9094.56, "total_tokens": 19420800}74{"current_steps": 355, "total_steps": 9742, "loss": 0.4022, "lr": 9.967455445286322e-06, "epoch": 0.07288031205091357, "percentage": 3.64, "elapsed_time": "0:36:09", "remaining_time": "15:56:19", "throughput": 9086.67, "total_tokens": 19717864}75{"current_steps": 360, "total_steps": 9742, "loss": 0.4041, "lr": 9.966530649348785e-06, "epoch": 0.0739067953192363, "percentage": 3.7, "elapsed_time": "0:36:41", "remaining_time": "15:56:02", "throughput": 9073.02, "total_tokens": 19970288}76{"current_steps": 365, "total_steps": 9742, "loss": 0.4342, "lr": 9.965592941321695e-06, "epoch": 0.07493327858755902, "percentage": 3.75, "elapsed_time": "0:37:11", "remaining_time": "15:55:28", "throughput": 9070.3, "total_tokens": 20240480}77{"current_steps": 370, "total_steps": 9742, "loss": 0.4351, "lr": 9.964642323642927e-06, "epoch": 0.07595976185588175, "percentage": 3.8, "elapsed_time": "0:37:40", "remaining_time": "15:54:07", "throughput": 9087.55, "total_tokens": 20538768}78{"current_steps": 375, "total_steps": 9742, "loss": 0.4334, "lr": 9.963678798783915e-06, "epoch": 0.07698624512420447, "percentage": 3.85, "elapsed_time": "0:38:14", "remaining_time": "15:55:22", "throughput": 9076.76, "total_tokens": 20829744}79{"current_steps": 380, "total_steps": 9742, "loss": 0.4069, "lr": 9.962702369249654e-06, "epoch": 0.07801272839252721, "percentage": 3.9, "elapsed_time": "0:38:50", "remaining_time": "15:56:50", "throughput": 9064.12, "total_tokens": 21121776}80{"current_steps": 385, "total_steps": 9742, "loss": 0.3852, "lr": 9.961713037578681e-06, "epoch": 0.07903921166084993, "percentage": 3.95, "elapsed_time": "0:39:26", "remaining_time": "15:58:44", "throughput": 9037.85, "total_tokens": 21391480}81{"current_steps": 390, "total_steps": 9742, "loss": 0.4256, "lr": 9.960710806343087e-06, "epoch": 0.08006569492917265, "percentage": 4.0, "elapsed_time": "0:39:58", "remaining_time": "15:58:28", "throughput": 9026.06, "total_tokens": 21646720}82{"current_steps": 395, "total_steps": 9742, "loss": 0.4055, "lr": 9.95969567814849e-06, "epoch": 0.08109217819749538, "percentage": 4.05, "elapsed_time": "0:40:25", "remaining_time": "15:56:38", "throughput": 9045.8, "total_tokens": 21941880}83{"current_steps": 400, "total_steps": 9742, "loss": 0.4025, "lr": 9.95866765563404e-06, "epoch": 0.0821186614658181, "percentage": 4.11, "elapsed_time": "0:40:59", "remaining_time": "15:57:12", "throughput": 9044.09, "total_tokens": 22240600}84{"current_steps": 405, "total_steps": 9742, "loss": 0.4349, "lr": 9.957626741472412e-06, "epoch": 0.08314514473414084, "percentage": 4.16, "elapsed_time": "0:41:30", "remaining_time": "15:56:59", "throughput": 9034.76, "total_tokens": 22502152}85{"current_steps": 410, "total_steps": 9742, "loss": 0.3863, "lr": 9.9565729383698e-06, "epoch": 0.08417162800246356, "percentage": 4.21, "elapsed_time": "0:42:04", "remaining_time": "15:57:49", "throughput": 9020.54, "total_tokens": 22775944}86{"current_steps": 415, "total_steps": 9742, "loss": 0.4178, "lr": 9.955506249065899e-06, "epoch": 0.08519811127078629, "percentage": 4.26, "elapsed_time": "0:42:35", "remaining_time": "15:57:20", "throughput": 9029.91, "total_tokens": 23078536}87{"current_steps": 420, "total_steps": 9742, "loss": 0.4287, "lr": 9.954426676333913e-06, "epoch": 0.08622459453910901, "percentage": 4.31, "elapsed_time": "0:43:06", "remaining_time": "15:56:47", "throughput": 9035.8, "total_tokens": 23370864}88{"current_steps": 425, "total_steps": 9742, "loss": 0.3814, "lr": 9.953334222980534e-06, "epoch": 0.08725107780743174, "percentage": 4.36, "elapsed_time": "0:43:35", "remaining_time": "15:55:43", "throughput": 9032.63, "total_tokens": 23627032}89{"current_steps": 430, "total_steps": 9742, "loss": 0.4337, "lr": 9.952228891845948e-06, "epoch": 0.08827756107575446, "percentage": 4.41, "elapsed_time": "0:44:04", "remaining_time": "15:54:32", "throughput": 9035.3, "total_tokens": 23895208}90{"current_steps": 435, "total_steps": 9742, "loss": 0.3777, "lr": 9.951110685803818e-06, "epoch": 0.0893040443440772, "percentage": 4.47, "elapsed_time": "0:44:34", "remaining_time": "15:53:36", "throughput": 9039.39, "total_tokens": 24173656}91{"current_steps": 440, "total_steps": 9742, "loss": 0.429, "lr": 9.949979607761277e-06, "epoch": 0.09033052761239992, "percentage": 4.52, "elapsed_time": "0:45:11", "remaining_time": "15:55:17", "throughput": 9013.26, "total_tokens": 24436936}92{"current_steps": 445, "total_steps": 9742, "loss": 0.4235, "lr": 9.948835660658927e-06, "epoch": 0.09135701088072265, "percentage": 4.57, "elapsed_time": "0:45:42", "remaining_time": "15:55:05", "throughput": 9006.16, "total_tokens": 24703048}93{"current_steps": 450, "total_steps": 9742, "loss": 0.3906, "lr": 9.947678847470824e-06, "epoch": 0.09238349414904537, "percentage": 4.62, "elapsed_time": "0:46:09", "remaining_time": "15:53:10", "throughput": 9022.39, "total_tokens": 24989080}94{"current_steps": 455, "total_steps": 9742, "loss": 0.4507, "lr": 9.946509171204474e-06, "epoch": 0.0934099774173681, "percentage": 4.67, "elapsed_time": "0:46:38", "remaining_time": "15:51:50", "throughput": 9026.12, "total_tokens": 25255168}95{"current_steps": 460, "total_steps": 9742, "loss": 0.4001, "lr": 9.94532663490083e-06, "epoch": 0.09443646068569082, "percentage": 4.72, "elapsed_time": "0:47:10", "remaining_time": "15:51:46", "throughput": 9028.31, "total_tokens": 25551208}96{"current_steps": 465, "total_steps": 9742, "loss": 0.4023, "lr": 9.944131241634271e-06, "epoch": 0.09546294395401354, "percentage": 4.77, "elapsed_time": "0:47:33", "remaining_time": "15:48:47", "throughput": 9044.18, "total_tokens": 25806800}97{"current_steps": 470, "total_steps": 9742, "loss": 0.3859, "lr": 9.942922994512608e-06, "epoch": 0.09648942722233628, "percentage": 4.82, "elapsed_time": "0:48:05", "remaining_time": "15:48:37", "throughput": 9041.55, "total_tokens": 26086312}98{"current_steps": 475, "total_steps": 9742, "loss": 0.3876, "lr": 9.941701896677063e-06, "epoch": 0.097515910490659, "percentage": 4.88, "elapsed_time": "0:48:37", "remaining_time": "15:48:46", "throughput": 9033.6, "total_tokens": 26359192}99{"current_steps": 480, "total_steps": 9742, "loss": 0.3967, "lr": 9.940467951302275e-06, "epoch": 0.09854239375898173, "percentage": 4.93, "elapsed_time": "0:49:04", "remaining_time": "15:47:03", "throughput": 9036.57, "total_tokens": 26611464}100{"current_steps": 485, "total_steps": 9742, "loss": 0.4038, "lr": 9.939221161596279e-06, "epoch": 0.09956887702730445, "percentage": 4.98, "elapsed_time": "0:49:28", "remaining_time": "15:44:27", "throughput": 9056.08, "total_tokens": 26887208}101{"current_steps": 490, "total_steps": 9742, "loss": 0.4222, "lr": 9.937961530800503e-06, "epoch": 0.10059536029562718, "percentage": 5.03, "elapsed_time": "0:49:57", "remaining_time": "15:43:14", "throughput": 9058.75, "total_tokens": 27151856}102{"current_steps": 495, "total_steps": 9742, "loss": 0.4178, "lr": 9.936689062189766e-06, "epoch": 0.1016218435639499, "percentage": 5.08, "elapsed_time": "0:50:29", "remaining_time": "15:43:16", "throughput": 9054.66, "total_tokens": 27432352}103{"current_steps": 500, "total_steps": 9742, "loss": 0.4136, "lr": 9.935403759072255e-06, "epoch": 0.10264832683227264, "percentage": 5.13, "elapsed_time": "0:50:58", "remaining_time": "15:42:14", "throughput": 9053.21, "total_tokens": 27689784}104{"current_steps": 505, "total_steps": 9742, "loss": 0.4181, "lr": 9.934105624789529e-06, "epoch": 0.10367481010059536, "percentage": 5.18, "elapsed_time": "0:51:33", "remaining_time": "15:42:59", "throughput": 9048.38, "total_tokens": 27989320}105{"current_steps": 510, "total_steps": 9742, "loss": 0.3975, "lr": 9.932794662716506e-06, "epoch": 0.10470129336891809, "percentage": 5.24, "elapsed_time": "0:52:05", "remaining_time": "15:42:55", "throughput": 9044.44, "total_tokens": 28267480}106{"current_steps": 515, "total_steps": 9742, "loss": 0.3981, "lr": 9.931470876261446e-06, "epoch": 0.10572777663724081, "percentage": 5.29, "elapsed_time": "0:52:32", "remaining_time": "15:41:23", "throughput": 9056.15, "total_tokens": 28550488}107{"current_steps": 520, "total_steps": 9742, "loss": 0.3935, "lr": 9.930134268865964e-06, "epoch": 0.10675425990556354, "percentage": 5.34, "elapsed_time": "0:52:59", "remaining_time": "15:39:39", "throughput": 9066.9, "total_tokens": 28824160}108{"current_steps": 525, "total_steps": 9742, "loss": 0.4142, "lr": 9.928784844004996e-06, "epoch": 0.10778074317388626, "percentage": 5.39, "elapsed_time": "0:53:27", "remaining_time": "15:38:25", "throughput": 9075.96, "total_tokens": 29108080}109{"current_steps": 530, "total_steps": 9742, "loss": 0.4082, "lr": 9.927422605186805e-06, "epoch": 0.108807226442209, "percentage": 5.44, "elapsed_time": "0:53:56", "remaining_time": "15:37:35", "throughput": 9075.76, "total_tokens": 29374424}110{"current_steps": 535, "total_steps": 9742, "loss": 0.4339, "lr": 9.92604755595297e-06, "epoch": 0.10983370971053172, "percentage": 5.49, "elapsed_time": "0:54:23", "remaining_time": "15:36:01", "throughput": 9083.39, "total_tokens": 29643072}111{"current_steps": 540, "total_steps": 9742, "loss": 0.4168, "lr": 9.92465969987837e-06, "epoch": 0.11086019297885444, "percentage": 5.54, "elapsed_time": "0:54:51", "remaining_time": "15:34:43", "throughput": 9090.67, "total_tokens": 29918824}112{"current_steps": 545, "total_steps": 9742, "loss": 0.3992, "lr": 9.92325904057118e-06, "epoch": 0.11188667624717717, "percentage": 5.59, "elapsed_time": "0:55:17", "remaining_time": "15:32:55", "throughput": 9104.48, "total_tokens": 30199936}113{"current_steps": 550, "total_steps": 9742, "loss": 0.4203, "lr": 9.921845581672868e-06, "epoch": 0.11291315951549989, "percentage": 5.65, "elapsed_time": "0:55:53", "remaining_time": "15:34:04", "throughput": 9090.51, "total_tokens": 30483936}114{"current_steps": 555, "total_steps": 9742, "loss": 0.4241, "lr": 9.920419326858174e-06, "epoch": 0.11393964278382263, "percentage": 5.7, "elapsed_time": "0:56:26", "remaining_time": "15:34:22", "throughput": 9079.32, "total_tokens": 30749936}115{"current_steps": 560, "total_steps": 9742, "loss": 0.41, "lr": 9.9189802798351e-06, "epoch": 0.11496612605214535, "percentage": 5.75, "elapsed_time": "0:57:00", "remaining_time": "15:34:42", "throughput": 9067.4, "total_tokens": 31014472}116{"current_steps": 565, "total_steps": 9742, "loss": 0.4018, "lr": 9.917528444344915e-06, "epoch": 0.11599260932046808, "percentage": 5.8, "elapsed_time": "0:57:31", "remaining_time": "15:34:18", "throughput": 9062.92, "total_tokens": 31279368}117{"current_steps": 570, "total_steps": 9742, "loss": 0.4069, "lr": 9.916063824162128e-06, "epoch": 0.1170190925887908, "percentage": 5.85, "elapsed_time": "0:58:04", "remaining_time": "15:34:28", "throughput": 9060.83, "total_tokens": 31571872}118{"current_steps": 575, "total_steps": 9742, "loss": 0.4259, "lr": 9.91458642309449e-06, "epoch": 0.11804557585711353, "percentage": 5.9, "elapsed_time": "0:58:38", "remaining_time": "15:34:49", "throughput": 9050.5, "total_tokens": 31841432}119{"current_steps": 580, "total_steps": 9742, "loss": 0.4027, "lr": 9.91309624498298e-06, "epoch": 0.11907205912543625, "percentage": 5.95, "elapsed_time": "0:59:10", "remaining_time": "15:34:43", "throughput": 9047.87, "total_tokens": 32123264}120{"current_steps": 585, "total_steps": 9742, "loss": 0.4196, "lr": 9.91159329370179e-06, "epoch": 0.12009854239375899, "percentage": 6.0, "elapsed_time": "0:59:36", "remaining_time": "15:32:56", "throughput": 9055.86, "total_tokens": 32384448}121{"current_steps": 590, "total_steps": 9742, "loss": 0.4162, "lr": 9.910077573158331e-06, "epoch": 0.1211250256620817, "percentage": 6.06, "elapsed_time": "1:00:06", "remaining_time": "15:32:16", "throughput": 9059.25, "total_tokens": 32668032}122{"current_steps": 595, "total_steps": 9742, "loss": 0.4161, "lr": 9.9085490872932e-06, "epoch": 0.12215150893040444, "percentage": 6.11, "elapsed_time": "1:00:35", "remaining_time": "15:31:24", "throughput": 9063.6, "total_tokens": 32948160}123{"current_steps": 600, "total_steps": 9742, "loss": 0.4063, "lr": 9.907007840080185e-06, "epoch": 0.12317799219872716, "percentage": 6.16, "elapsed_time": "1:01:01", "remaining_time": "15:29:41", "throughput": 9076.07, "total_tokens": 33227592}124{"current_steps": 605, "total_steps": 9742, "loss": 0.3885, "lr": 9.905453835526257e-06, "epoch": 0.1242044754670499, "percentage": 6.21, "elapsed_time": "1:01:30", "remaining_time": "15:28:48", "throughput": 9081.89, "total_tokens": 33512568}125{"current_steps": 610, "total_steps": 9742, "loss": 0.4029, "lr": 9.903887077671545e-06, "epoch": 0.12523095873537263, "percentage": 6.26, "elapsed_time": "1:02:02", "remaining_time": "15:28:51", "throughput": 9078.3, "total_tokens": 33796112}126{"current_steps": 615, "total_steps": 9742, "loss": 0.4292, "lr": 9.902307570589343e-06, "epoch": 0.12625744200369535, "percentage": 6.31, "elapsed_time": "1:02:33", "remaining_time": "15:28:30", "throughput": 9081.99, "total_tokens": 34092904}127{"current_steps": 620, "total_steps": 9742, "loss": 0.3906, "lr": 9.90071531838608e-06, "epoch": 0.12728392527201807, "percentage": 6.36, "elapsed_time": "1:03:11", "remaining_time": "15:29:42", "throughput": 9062.31, "total_tokens": 34358664}128{"current_steps": 625, "total_steps": 9742, "loss": 0.4295, "lr": 9.899110325201335e-06, "epoch": 0.1283104085403408, "percentage": 6.42, "elapsed_time": "1:03:45", "remaining_time": "15:30:07", "throughput": 9058.13, "total_tokens": 34654488}129{"current_steps": 630, "total_steps": 9742, "loss": 0.4312, "lr": 9.897492595207795e-06, "epoch": 0.1293368918086635, "percentage": 6.47, "elapsed_time": "1:04:13", "remaining_time": "15:28:57", "throughput": 9060.28, "total_tokens": 34915200}130{"current_steps": 635, "total_steps": 9742, "loss": 0.3987, "lr": 9.895862132611272e-06, "epoch": 0.13036337507698625, "percentage": 6.52, "elapsed_time": "1:04:44", "remaining_time": "15:28:31", "throughput": 9054.77, "total_tokens": 35174168}131{"current_steps": 640, "total_steps": 9742, "loss": 0.3868, "lr": 9.894218941650675e-06, "epoch": 0.13138985834530897, "percentage": 6.57, "elapsed_time": "1:05:17", "remaining_time": "15:28:34", "throughput": 9053.75, "total_tokens": 35468232}132{"current_steps": 645, "total_steps": 9742, "loss": 0.4125, "lr": 9.892563026598005e-06, "epoch": 0.1324163416136317, "percentage": 6.62, "elapsed_time": "1:05:48", "remaining_time": "15:28:09", "throughput": 9055.32, "total_tokens": 35754968}133{"current_steps": 650, "total_steps": 9742, "loss": 0.4038, "lr": 9.890894391758348e-06, "epoch": 0.1334428248819544, "percentage": 6.67, "elapsed_time": "1:06:19", "remaining_time": "15:27:47", "throughput": 9050.56, "total_tokens": 36018760}134{"current_steps": 655, "total_steps": 9742, "loss": 0.4156, "lr": 9.889213041469851e-06, "epoch": 0.13446930815027716, "percentage": 6.72, "elapsed_time": "1:06:56", "remaining_time": "15:28:37", "throughput": 9039.65, "total_tokens": 36304872}135{"current_steps": 660, "total_steps": 9742, "loss": 0.4439, "lr": 9.887518980103728e-06, "epoch": 0.13549579141859988, "percentage": 6.77, "elapsed_time": "1:07:25", "remaining_time": "15:27:53", "throughput": 9042.89, "total_tokens": 36586512}136{"current_steps": 665, "total_steps": 9742, "loss": 0.4078, "lr": 9.885812212064231e-06, "epoch": 0.1365222746869226, "percentage": 6.83, "elapsed_time": "1:07:50", "remaining_time": "15:26:03", "throughput": 9055.22, "total_tokens": 36860904}137{"current_steps": 670, "total_steps": 9742, "loss": 0.4144, "lr": 9.884092741788655e-06, "epoch": 0.13754875795524532, "percentage": 6.88, "elapsed_time": "1:08:19", "remaining_time": "15:25:12", "throughput": 9058.22, "total_tokens": 37136944}138{"current_steps": 675, "total_steps": 9742, "loss": 0.3993, "lr": 9.88236057374731e-06, "epoch": 0.13857524122356807, "percentage": 6.93, "elapsed_time": "1:08:46", "remaining_time": "15:23:46", "throughput": 9065.67, "total_tokens": 37407120}139{"current_steps": 680, "total_steps": 9742, "loss": 0.4006, "lr": 9.880615712443526e-06, "epoch": 0.1396017244918908, "percentage": 6.98, "elapsed_time": "1:09:17", "remaining_time": "15:23:28", "throughput": 9061.99, "total_tokens": 37677512}140{"current_steps": 685, "total_steps": 9742, "loss": 0.4039, "lr": 9.878858162413627e-06, "epoch": 0.1406282077602135, "percentage": 7.03, "elapsed_time": "1:09:48", "remaining_time": "15:23:04", "throughput": 9055.23, "total_tokens": 37930968}141{"current_steps": 690, "total_steps": 9742, "loss": 0.441, "lr": 9.87708792822693e-06, "epoch": 0.14165469102853623, "percentage": 7.08, "elapsed_time": "1:10:21", "remaining_time": "15:22:57", "throughput": 9058.86, "total_tokens": 38239280}142{"current_steps": 695, "total_steps": 9742, "loss": 0.3925, "lr": 9.875305014485726e-06, "epoch": 0.14268117429685895, "percentage": 7.13, "elapsed_time": "1:10:46", "remaining_time": "15:21:15", "throughput": 9073.49, "total_tokens": 38528968}143{"current_steps": 700, "total_steps": 9742, "loss": 0.4303, "lr": 9.873509425825271e-06, "epoch": 0.1437076575651817, "percentage": 7.19, "elapsed_time": "1:11:12", "remaining_time": "15:19:52", "throughput": 9084.19, "total_tokens": 38814808}144{"current_steps": 705, "total_steps": 9742, "loss": 0.4035, "lr": 9.871701166913775e-06, "epoch": 0.14473414083350442, "percentage": 7.24, "elapsed_time": "1:11:42", "remaining_time": "15:19:16", "throughput": 9082.02, "total_tokens": 39078904}145{"current_steps": 710, "total_steps": 9742, "loss": 0.392, "lr": 9.869880242452385e-06, "epoch": 0.14576062410182714, "percentage": 7.29, "elapsed_time": "1:12:15", "remaining_time": "15:19:09", "throughput": 9084.08, "total_tokens": 39381704}146{"current_steps": 715, "total_steps": 9742, "loss": 0.4275, "lr": 9.86804665717518e-06, "epoch": 0.14678710737014986, "percentage": 7.34, "elapsed_time": "1:12:41", "remaining_time": "15:17:47", "throughput": 9092.64, "total_tokens": 39659264}147{"current_steps": 720, "total_steps": 9742, "loss": 0.4388, "lr": 9.86620041584915e-06, "epoch": 0.1478135906384726, "percentage": 7.39, "elapsed_time": "1:13:07", "remaining_time": "15:16:15", "throughput": 9097.34, "total_tokens": 39913000}148{"current_steps": 725, "total_steps": 9742, "loss": 0.3994, "lr": 9.864341523274197e-06, "epoch": 0.14884007390679532, "percentage": 7.44, "elapsed_time": "1:13:38", "remaining_time": "15:15:50", "throughput": 9090.19, "total_tokens": 40162128}149{"current_steps": 730, "total_steps": 9742, "loss": 0.4216, "lr": 9.862469984283103e-06, "epoch": 0.14986655717511804, "percentage": 7.49, "elapsed_time": "1:14:08", "remaining_time": "15:15:22", "throughput": 9089.53, "total_tokens": 40438584}150{"current_steps": 735, "total_steps": 9742, "loss": 0.4096, "lr": 9.860585803741536e-06, "epoch": 0.15089304044344076, "percentage": 7.54, "elapsed_time": "1:14:35", "remaining_time": "15:14:10", "throughput": 9094.52, "total_tokens": 40706728}151{"current_steps": 740, "total_steps": 9742, "loss": 0.4079, "lr": 9.85868898654803e-06, "epoch": 0.1519195237117635, "percentage": 7.6, "elapsed_time": "1:15:00", "remaining_time": "15:12:29", "throughput": 9103.47, "total_tokens": 40971152}152{"current_steps": 745, "total_steps": 9742, "loss": 0.3692, "lr": 9.856779537633968e-06, "epoch": 0.15294600698008623, "percentage": 7.65, "elapsed_time": "1:15:28", "remaining_time": "15:11:23", "throughput": 9110.47, "total_tokens": 41253392}153{"current_steps": 750, "total_steps": 9742, "loss": 0.3953, "lr": 9.854857461963572e-06, "epoch": 0.15397249024840895, "percentage": 7.7, "elapsed_time": "1:15:57", "remaining_time": "15:10:38", "throughput": 9110.62, "total_tokens": 41519168}154{"current_steps": 755, "total_steps": 9742, "loss": 0.385, "lr": 9.852922764533899e-06, "epoch": 0.15499897351673167, "percentage": 7.75, "elapsed_time": "1:16:21", "remaining_time": "15:08:52", "throughput": 9123.55, "total_tokens": 41797328}155{"current_steps": 760, "total_steps": 9742, "loss": 0.3368, "lr": 9.850975450374814e-06, "epoch": 0.15602545678505442, "percentage": 7.8, "elapsed_time": "1:16:56", "remaining_time": "15:09:22", "throughput": 9117.28, "total_tokens": 42092360}156{"current_steps": 765, "total_steps": 9742, "loss": 0.3918, "lr": 9.849015524548982e-06, "epoch": 0.15705194005337714, "percentage": 7.85, "elapsed_time": "1:17:31", "remaining_time": "15:09:47", "throughput": 9112.0, "total_tokens": 42387680}157{"current_steps": 770, "total_steps": 9742, "loss": 0.3917, "lr": 9.847042992151864e-06, "epoch": 0.15807842332169986, "percentage": 7.9, "elapsed_time": "1:17:56", "remaining_time": "15:08:12", "throughput": 9122.9, "total_tokens": 42664952}158{"current_steps": 775, "total_steps": 9742, "loss": 0.3954, "lr": 9.845057858311686e-06, "epoch": 0.15910490659002258, "percentage": 7.96, "elapsed_time": "1:18:29", "remaining_time": "15:08:12", "throughput": 9123.3, "total_tokens": 42967576}159{"current_steps": 780, "total_steps": 9742, "loss": 0.4286, "lr": 9.843060128189444e-06, "epoch": 0.1601313898583453, "percentage": 8.01, "elapsed_time": "1:19:03", "remaining_time": "15:08:16", "throughput": 9113.73, "total_tokens": 43226816}160{"current_steps": 785, "total_steps": 9742, "loss": 0.3849, "lr": 9.841049806978874e-06, "epoch": 0.16115787312666804, "percentage": 8.06, "elapsed_time": "1:19:31", "remaining_time": "15:07:28", "throughput": 9116.79, "total_tokens": 43504208}161{"current_steps": 790, "total_steps": 9742, "loss": 0.3994, "lr": 9.839026899906454e-06, "epoch": 0.16218435639499076, "percentage": 8.11, "elapsed_time": "1:20:03", "remaining_time": "15:07:15", "throughput": 9113.88, "total_tokens": 43781288}162{"current_steps": 795, "total_steps": 9742, "loss": 0.3811, "lr": 9.83699141223138e-06, "epoch": 0.16321083966331348, "percentage": 8.16, "elapsed_time": "1:20:39", "remaining_time": "15:07:41", "throughput": 9104.17, "total_tokens": 44057600}163{"current_steps": 800, "total_steps": 9742, "loss": 0.3975, "lr": 9.834943349245554e-06, "epoch": 0.1642373229316362, "percentage": 8.21, "elapsed_time": "1:21:08", "remaining_time": "15:06:58", "throughput": 9102.37, "total_tokens": 44315800}164{"current_steps": 805, "total_steps": 9742, "loss": 0.4086, "lr": 9.832882716273572e-06, "epoch": 0.16526380619995895, "percentage": 8.26, "elapsed_time": "1:21:31", "remaining_time": "15:05:07", "throughput": 9112.23, "total_tokens": 44574728}165{"current_steps": 810, "total_steps": 9742, "loss": 0.4374, "lr": 9.830809518672713e-06, "epoch": 0.16629028946828167, "percentage": 8.31, "elapsed_time": "1:22:02", "remaining_time": "15:04:38", "throughput": 9110.04, "total_tokens": 44841696}166{"current_steps": 815, "total_steps": 9742, "loss": 0.4077, "lr": 9.828723761832914e-06, "epoch": 0.1673167727366044, "percentage": 8.37, "elapsed_time": "1:22:33", "remaining_time": "15:04:22", "throughput": 9105.31, "total_tokens": 45107512}167{"current_steps": 820, "total_steps": 9742, "loss": 0.4018, "lr": 9.826625451176777e-06, "epoch": 0.1683432560049271, "percentage": 8.42, "elapsed_time": "1:23:08", "remaining_time": "15:04:39", "throughput": 9100.03, "total_tokens": 45397560}168{"current_steps": 825, "total_steps": 9742, "loss": 0.4106, "lr": 9.824514592159526e-06, "epoch": 0.16936973927324986, "percentage": 8.47, "elapsed_time": "1:23:41", "remaining_time": "15:04:32", "throughput": 9096.02, "total_tokens": 45673792}169{"current_steps": 830, "total_steps": 9742, "loss": 0.4032, "lr": 9.82239119026902e-06, "epoch": 0.17039622254157258, "percentage": 8.52, "elapsed_time": "1:24:10", "remaining_time": "15:03:52", "throughput": 9097.06, "total_tokens": 45948088}170{"current_steps": 835, "total_steps": 9742, "loss": 0.4133, "lr": 9.820255251025724e-06, "epoch": 0.1714227058098953, "percentage": 8.57, "elapsed_time": "1:24:33", "remaining_time": "15:02:04", "throughput": 9105.72, "total_tokens": 46202368}171{"current_steps": 840, "total_steps": 9742, "loss": 0.4139, "lr": 9.818106779982693e-06, "epoch": 0.17244918907821802, "percentage": 8.62, "elapsed_time": "1:25:07", "remaining_time": "15:02:10", "throughput": 9104.33, "total_tokens": 46502728}172{"current_steps": 845, "total_steps": 9742, "loss": 0.3952, "lr": 9.81594578272557e-06, "epoch": 0.17347567234654074, "percentage": 8.67, "elapsed_time": "1:25:35", "remaining_time": "15:01:11", "throughput": 9107.14, "total_tokens": 46769456}173{"current_steps": 850, "total_steps": 9742, "loss": 0.3809, "lr": 9.81377226487256e-06, "epoch": 0.17450215561486349, "percentage": 8.73, "elapsed_time": "1:25:57", "remaining_time": "14:59:17", "throughput": 9119.1, "total_tokens": 47035008}174{"current_steps": 855, "total_steps": 9742, "loss": 0.4097, "lr": 9.811586232074421e-06, "epoch": 0.1755286388831862, "percentage": 8.78, "elapsed_time": "1:26:27", "remaining_time": "14:58:36", "throughput": 9118.02, "total_tokens": 47297160}175{"current_steps": 860, "total_steps": 9742, "loss": 0.3973, "lr": 9.809387690014446e-06, "epoch": 0.17655512215150893, "percentage": 8.83, "elapsed_time": "1:26:54", "remaining_time": "14:57:33", "throughput": 9119.29, "total_tokens": 47551656}176{"current_steps": 865, "total_steps": 9742, "loss": 0.4118, "lr": 9.807176644408449e-06, "epoch": 0.17758160541983165, "percentage": 8.88, "elapsed_time": "1:27:27", "remaining_time": "14:57:35", "throughput": 9111.66, "total_tokens": 47816256}177{"current_steps": 870, "total_steps": 9742, "loss": 0.4037, "lr": 9.804953101004752e-06, "epoch": 0.1786080886881544, "percentage": 8.93, "elapsed_time": "1:27:56", "remaining_time": "14:56:44", "throughput": 9112.58, "total_tokens": 48079224}178{"current_steps": 875, "total_steps": 9742, "loss": 0.4027, "lr": 9.80271706558417e-06, "epoch": 0.1796345719564771, "percentage": 8.98, "elapsed_time": "1:28:29", "remaining_time": "14:56:45", "throughput": 9111.01, "total_tokens": 48375632}179{"current_steps": 880, "total_steps": 9742, "loss": 0.399, "lr": 9.800468543959996e-06, "epoch": 0.18066105522479983, "percentage": 9.03, "elapsed_time": "1:28:56", "remaining_time": "14:55:45", "throughput": 9112.66, "total_tokens": 48633536}180{"current_steps": 885, "total_steps": 9742, "loss": 0.4037, "lr": 9.798207541977981e-06, "epoch": 0.18168753849312255, "percentage": 9.08, "elapsed_time": "1:29:26", "remaining_time": "14:55:06", "throughput": 9113.36, "total_tokens": 48906416}181{"current_steps": 890, "total_steps": 9742, "loss": 0.39, "lr": 9.795934065516327e-06, "epoch": 0.1827140217614453, "percentage": 9.14, "elapsed_time": "1:29:59", "remaining_time": "14:55:00", "throughput": 9103.95, "total_tokens": 49153520}182{"current_steps": 895, "total_steps": 9742, "loss": 0.3825, "lr": 9.793648120485661e-06, "epoch": 0.18374050502976802, "percentage": 9.19, "elapsed_time": "1:30:22", "remaining_time": "14:53:21", "throughput": 9119.63, "total_tokens": 49452096}183{"current_steps": 900, "total_steps": 9742, "loss": 0.3786, "lr": 9.791349712829037e-06, "epoch": 0.18476698829809074, "percentage": 9.24, "elapsed_time": "1:30:51", "remaining_time": "14:52:36", "throughput": 9124.58, "total_tokens": 49741408}184{"current_steps": 905, "total_steps": 9742, "loss": 0.3624, "lr": 9.789038848521897e-06, "epoch": 0.18579347156641346, "percentage": 9.29, "elapsed_time": "1:31:21", "remaining_time": "14:52:00", "throughput": 9127.77, "total_tokens": 50029976}185{"current_steps": 910, "total_steps": 9742, "loss": 0.4021, "lr": 9.786715533572078e-06, "epoch": 0.1868199548347362, "percentage": 9.34, "elapsed_time": "1:31:44", "remaining_time": "14:50:25", "throughput": 9140.88, "total_tokens": 50317320}186{"current_steps": 915, "total_steps": 9742, "loss": 0.3904, "lr": 9.78437977401978e-06, "epoch": 0.18784643810305893, "percentage": 9.39, "elapsed_time": "1:32:09", "remaining_time": "14:49:04", "throughput": 9149.61, "total_tokens": 50594504}187{"current_steps": 920, "total_steps": 9742, "loss": 0.4011, "lr": 9.78203157593756e-06, "epoch": 0.18887292137138165, "percentage": 9.44, "elapsed_time": "1:32:34", "remaining_time": "14:47:47", "throughput": 9156.9, "total_tokens": 50866192}188{"current_steps": 925, "total_steps": 9742, "loss": 0.4268, "lr": 9.779670945430314e-06, "epoch": 0.18989940463970437, "percentage": 9.49, "elapsed_time": "1:33:08", "remaining_time": "14:47:49", "throughput": 9155.22, "total_tokens": 51164768}189{"current_steps": 930, "total_steps": 9742, "loss": 0.3648, "lr": 9.777297888635254e-06, "epoch": 0.1909258879080271, "percentage": 9.55, "elapsed_time": "1:33:39", "remaining_time": "14:47:24", "throughput": 9152.3, "total_tokens": 51429384}190{"current_steps": 935, "total_steps": 9742, "loss": 0.4002, "lr": 9.774912411721907e-06, "epoch": 0.19195237117634983, "percentage": 9.6, "elapsed_time": "1:34:08", "remaining_time": "14:46:48", "throughput": 9155.84, "total_tokens": 51720872}191{"current_steps": 940, "total_steps": 9742, "loss": 0.4016, "lr": 9.772514520892081e-06, "epoch": 0.19297885444467255, "percentage": 9.65, "elapsed_time": "1:34:41", "remaining_time": "14:46:44", "throughput": 9147.94, "total_tokens": 51978264}192{"current_steps": 945, "total_steps": 9742, "loss": 0.4119, "lr": 9.770104222379866e-06, "epoch": 0.19400533771299527, "percentage": 9.7, "elapsed_time": "1:35:12", "remaining_time": "14:46:13", "throughput": 9143.05, "total_tokens": 52225240}193{"current_steps": 950, "total_steps": 9742, "loss": 0.3798, "lr": 9.767681522451603e-06, "epoch": 0.195031820981318, "percentage": 9.75, "elapsed_time": "1:35:41", "remaining_time": "14:45:32", "throughput": 9148.21, "total_tokens": 52520544}194{"current_steps": 955, "total_steps": 9742, "loss": 0.3788, "lr": 9.765246427405883e-06, "epoch": 0.19605830424964074, "percentage": 9.8, "elapsed_time": "1:36:08", "remaining_time": "14:44:39", "throughput": 9149.5, "total_tokens": 52782048}195{"current_steps": 960, "total_steps": 9742, "loss": 0.4148, "lr": 9.76279894357351e-06, "epoch": 0.19708478751796346, "percentage": 9.85, "elapsed_time": "1:36:42", "remaining_time": "14:44:37", "throughput": 9139.23, "total_tokens": 53027024}196{"current_steps": 965, "total_steps": 9742, "loss": 0.402, "lr": 9.760339077317508e-06, "epoch": 0.19811127078628618, "percentage": 9.91, "elapsed_time": "1:37:07", "remaining_time": "14:43:24", "throughput": 9141.76, "total_tokens": 53275432}197{"current_steps": 970, "total_steps": 9742, "loss": 0.4055, "lr": 9.757866835033088e-06, "epoch": 0.1991377540546089, "percentage": 9.96, "elapsed_time": "1:37:37", "remaining_time": "14:42:54", "throughput": 9143.47, "total_tokens": 53560864}198{"current_steps": 975, "total_steps": 9742, "loss": 0.4072, "lr": 9.755382223147634e-06, "epoch": 0.20016423732293165, "percentage": 10.01, "elapsed_time": "1:38:09", "remaining_time": "14:42:33", "throughput": 9138.86, "total_tokens": 53819904}199{"current_steps": 980, "total_steps": 9742, "loss": 0.3843, "lr": 9.752885248120694e-06, "epoch": 0.20119072059125437, "percentage": 10.06, "elapsed_time": "1:38:45", "remaining_time": "14:43:01", "throughput": 9127.47, "total_tokens": 54087136}200{"current_steps": 985, "total_steps": 9742, "loss": 0.4068, "lr": 9.750375916443952e-06, "epoch": 0.2022172038595771, "percentage": 10.11, "elapsed_time": "1:39:18", "remaining_time": "14:42:50", "throughput": 9124.7, "total_tokens": 54366328}201{"current_steps": 990, "total_steps": 9742, "loss": 0.3879, "lr": 9.747854234641228e-06, "epoch": 0.2032436871278998, "percentage": 10.16, "elapsed_time": "1:39:49", "remaining_time": "14:42:28", "throughput": 9120.6, "total_tokens": 54626720}202{"current_steps": 995, "total_steps": 9742, "loss": 0.4271, "lr": 9.745320209268434e-06, "epoch": 0.20427017039622253, "percentage": 10.21, "elapsed_time": "1:40:17", "remaining_time": "14:41:42", "throughput": 9124.02, "total_tokens": 54907000}203{"current_steps": 1000, "total_steps": 9742, "loss": 0.4215, "lr": 9.742773846913587e-06, "epoch": 0.20529665366454528, "percentage": 10.26, "elapsed_time": "1:40:43", "remaining_time": "14:40:30", "throughput": 9130.18, "total_tokens": 55176896}204{"current_steps": 1005, "total_steps": 9742, "loss": 0.3892, "lr": 9.740215154196773e-06, "epoch": 0.206323136932868, "percentage": 10.32, "elapsed_time": "1:41:14", "remaining_time": "14:40:05", "throughput": 9131.78, "total_tokens": 55467192}205{"current_steps": 1010, "total_steps": 9742, "loss": 0.42, "lr": 9.737644137770133e-06, "epoch": 0.20734962020119072, "percentage": 10.37, "elapsed_time": "1:41:44", "remaining_time": "14:39:32", "throughput": 9134.74, "total_tokens": 55758608}206{"current_steps": 1015, "total_steps": 9742, "loss": 0.3819, "lr": 9.735060804317848e-06, "epoch": 0.20837610346951344, "percentage": 10.42, "elapsed_time": "1:42:13", "remaining_time": "14:38:58", "throughput": 9138.05, "total_tokens": 56051288}207{"current_steps": 1020, "total_steps": 9742, "loss": 0.4072, "lr": 9.732465160556123e-06, "epoch": 0.20940258673783618, "percentage": 10.47, "elapsed_time": "1:42:40", "remaining_time": "14:37:58", "throughput": 9144.15, "total_tokens": 56332704}208{"current_steps": 1025, "total_steps": 9742, "loss": 0.3906, "lr": 9.729857213233169e-06, "epoch": 0.2104290700061589, "percentage": 10.52, "elapsed_time": "1:43:11", "remaining_time": "14:37:31", "throughput": 9144.95, "total_tokens": 56617584}209{"current_steps": 1030, "total_steps": 9742, "loss": 0.3835, "lr": 9.727236969129176e-06, "epoch": 0.21145555327448162, "percentage": 10.57, "elapsed_time": "1:43:45", "remaining_time": "14:37:39", "throughput": 9141.01, "total_tokens": 56910048}210{"current_steps": 1035, "total_steps": 9742, "loss": 0.3745, "lr": 9.724604435056316e-06, "epoch": 0.21248203654280434, "percentage": 10.62, "elapsed_time": "1:44:16", "remaining_time": "14:37:10", "throughput": 9139.89, "total_tokens": 57180336}211{"current_steps": 1040, "total_steps": 9742, "loss": 0.3863, "lr": 9.721959617858699e-06, "epoch": 0.2135085198111271, "percentage": 10.68, "elapsed_time": "1:44:52", "remaining_time": "14:37:27", "throughput": 9133.84, "total_tokens": 57470840}212{"current_steps": 1045, "total_steps": 9742, "loss": 0.3809, "lr": 9.71930252441238e-06, "epoch": 0.2145350030794498, "percentage": 10.73, "elapsed_time": "1:45:22", "remaining_time": "14:36:57", "throughput": 9134.7, "total_tokens": 57752368}213{"current_steps": 1050, "total_steps": 9742, "loss": 0.3808, "lr": 9.716633161625324e-06, "epoch": 0.21556148634777253, "percentage": 10.78, "elapsed_time": "1:45:47", "remaining_time": "14:35:41", "throughput": 9142.1, "total_tokens": 58025184}214{"current_steps": 1055, "total_steps": 9742, "loss": 0.4014, "lr": 9.713951536437395e-06, "epoch": 0.21658796961609525, "percentage": 10.83, "elapsed_time": "1:46:13", "remaining_time": "14:34:41", "throughput": 9146.8, "total_tokens": 58298672}215{"current_steps": 1060, "total_steps": 9742, "loss": 0.4047, "lr": 9.71125765582034e-06, "epoch": 0.217614452884418, "percentage": 10.88, "elapsed_time": "1:46:47", "remaining_time": "14:34:41", "throughput": 9145.72, "total_tokens": 58601896}216{"current_steps": 1065, "total_steps": 9742, "loss": 0.4043, "lr": 9.708551526777767e-06, "epoch": 0.21864093615274072, "percentage": 10.93, "elapsed_time": "1:47:18", "remaining_time": "14:34:15", "throughput": 9145.86, "total_tokens": 58883896}217{"current_steps": 1070, "total_steps": 9742, "loss": 0.4093, "lr": 9.705833156345124e-06, "epoch": 0.21966741942106344, "percentage": 10.98, "elapsed_time": "1:47:46", "remaining_time": "14:33:29", "throughput": 9148.85, "total_tokens": 59162000}218{"current_steps": 1075, "total_steps": 9742, "loss": 0.3818, "lr": 9.703102551589686e-06, "epoch": 0.22069390268938616, "percentage": 11.03, "elapsed_time": "1:48:13", "remaining_time": "14:32:36", "throughput": 9156.76, "total_tokens": 59463376}219{"current_steps": 1080, "total_steps": 9742, "loss": 0.3997, "lr": 9.700359719610538e-06, "epoch": 0.22172038595770888, "percentage": 11.09, "elapsed_time": "1:48:45", "remaining_time": "14:32:17", "throughput": 9149.99, "total_tokens": 59709480}220{"current_steps": 1085, "total_steps": 9742, "loss": 0.4014, "lr": 9.697604667538549e-06, "epoch": 0.22274686922603162, "percentage": 11.14, "elapsed_time": "1:49:16", "remaining_time": "14:31:50", "throughput": 9150.2, "total_tokens": 59990656}221{"current_steps": 1090, "total_steps": 9742, "loss": 0.3833, "lr": 9.694837402536366e-06, "epoch": 0.22377335249435434, "percentage": 11.19, "elapsed_time": "1:49:48", "remaining_time": "14:31:36", "throughput": 9145.99, "total_tokens": 60257344}222{"current_steps": 1095, "total_steps": 9742, "loss": 0.3773, "lr": 9.692057931798376e-06, "epoch": 0.22479983576267706, "percentage": 11.24, "elapsed_time": "1:50:18", "remaining_time": "14:31:03", "throughput": 9149.91, "total_tokens": 60557448}223{"current_steps": 1100, "total_steps": 9742, "loss": 0.3737, "lr": 9.689266262550709e-06, "epoch": 0.22582631903099978, "percentage": 11.29, "elapsed_time": "1:50:46", "remaining_time": "14:30:18", "throughput": 9151.08, "total_tokens": 60823608}224{"current_steps": 1105, "total_steps": 9742, "loss": 0.4051, "lr": 9.686462402051202e-06, "epoch": 0.22685280229932253, "percentage": 11.34, "elapsed_time": "1:51:14", "remaining_time": "14:29:25", "throughput": 9150.58, "total_tokens": 61071016}225{"current_steps": 1110, "total_steps": 9742, "loss": 0.3886, "lr": 9.68364635758939e-06, "epoch": 0.22787928556764525, "percentage": 11.39, "elapsed_time": "1:51:42", "remaining_time": "14:28:42", "throughput": 9149.44, "total_tokens": 61323840}226{"current_steps": 1115, "total_steps": 9742, "loss": 0.3904, "lr": 9.680818136486484e-06, "epoch": 0.22890576883596797, "percentage": 11.45, "elapsed_time": "1:52:13", "remaining_time": "14:28:19", "throughput": 9144.63, "total_tokens": 61575856}227{"current_steps": 1120, "total_steps": 9742, "loss": 0.343, "lr": 9.677977746095356e-06, "epoch": 0.2299322521042907, "percentage": 11.5, "elapsed_time": "1:52:41", "remaining_time": "14:27:34", "throughput": 9144.86, "total_tokens": 61837064}228{"current_steps": 1125, "total_steps": 9742, "loss": 0.3674, "lr": 9.675125193800508e-06, "epoch": 0.23095873537261344, "percentage": 11.55, "elapsed_time": "1:53:18", "remaining_time": "14:27:49", "throughput": 9138.54, "total_tokens": 62123856}229{"current_steps": 1130, "total_steps": 9742, "loss": 0.4015, "lr": 9.672260487018064e-06, "epoch": 0.23198521864093616, "percentage": 11.6, "elapsed_time": "1:53:54", "remaining_time": "14:28:04", "throughput": 9132.1, "total_tokens": 62409392}230{"current_steps": 1135, "total_steps": 9742, "loss": 0.4069, "lr": 9.669383633195749e-06, "epoch": 0.23301170190925888, "percentage": 11.65, "elapsed_time": "1:54:20", "remaining_time": "14:27:02", "throughput": 9135.18, "total_tokens": 62669136}231{"current_steps": 1140, "total_steps": 9742, "loss": 0.4329, "lr": 9.666494639812869e-06, "epoch": 0.2340381851775816, "percentage": 11.7, "elapsed_time": "1:54:48", "remaining_time": "14:26:18", "throughput": 9139.98, "total_tokens": 62961288}232{"current_steps": 1145, "total_steps": 9742, "loss": 0.4111, "lr": 9.663593514380287e-06, "epoch": 0.23506466844590435, "percentage": 11.75, "elapsed_time": "1:55:18", "remaining_time": "14:25:46", "throughput": 9140.35, "total_tokens": 63237704}233{"current_steps": 1150, "total_steps": 9742, "loss": 0.3868, "lr": 9.660680264440409e-06, "epoch": 0.23609115171422707, "percentage": 11.8, "elapsed_time": "1:55:47", "remaining_time": "14:25:08", "throughput": 9142.75, "total_tokens": 63520648}234{"current_steps": 1155, "total_steps": 9742, "loss": 0.3724, "lr": 9.657754897567167e-06, "epoch": 0.23711763498254979, "percentage": 11.86, "elapsed_time": "1:56:15", "remaining_time": "14:24:20", "throughput": 9143.09, "total_tokens": 63777576}235{"current_steps": 1160, "total_steps": 9742, "loss": 0.3976, "lr": 9.654817421365985e-06, "epoch": 0.2381441182508725, "percentage": 11.91, "elapsed_time": "1:56:44", "remaining_time": "14:23:40", "throughput": 9145.51, "total_tokens": 64059128}236{"current_steps": 1165, "total_steps": 9742, "loss": 0.4093, "lr": 9.651867843473777e-06, "epoch": 0.23917060151919523, "percentage": 11.96, "elapsed_time": "1:57:14", "remaining_time": "14:23:09", "throughput": 9147.89, "total_tokens": 64350424}237{"current_steps": 1170, "total_steps": 9742, "loss": 0.4158, "lr": 9.648906171558917e-06, "epoch": 0.24019708478751797, "percentage": 12.01, "elapsed_time": "1:57:48", "remaining_time": "14:23:06", "throughput": 9140.55, "total_tokens": 64609232}238{"current_steps": 1175, "total_steps": 9742, "loss": 0.4281, "lr": 9.645932413321222e-06, "epoch": 0.2412235680558407, "percentage": 12.06, "elapsed_time": "1:58:15", "remaining_time": "14:22:13", "throughput": 9144.67, "total_tokens": 64885544}239{"current_steps": 1180, "total_steps": 9742, "loss": 0.3876, "lr": 9.642946576491928e-06, "epoch": 0.2422500513241634, "percentage": 12.11, "elapsed_time": "1:58:45", "remaining_time": "14:21:39", "throughput": 9142.05, "total_tokens": 65138256}240{"current_steps": 1185, "total_steps": 9742, "loss": 0.3415, "lr": 9.639948668833677e-06, "epoch": 0.24327653459248613, "percentage": 12.16, "elapsed_time": "1:59:13", "remaining_time": "14:20:55", "throughput": 9144.26, "total_tokens": 65412144}241{"current_steps": 1190, "total_steps": 9742, "loss": 0.4069, "lr": 9.636938698140493e-06, "epoch": 0.24430301786080888, "percentage": 12.22, "elapsed_time": "1:59:47", "remaining_time": "14:20:55", "throughput": 9138.63, "total_tokens": 65687160}242{"current_steps": 1195, "total_steps": 9742, "loss": 0.3792, "lr": 9.633916672237758e-06, "epoch": 0.2453295011291316, "percentage": 12.27, "elapsed_time": "2:00:16", "remaining_time": "14:20:15", "throughput": 9139.21, "total_tokens": 65954408}243{"current_steps": 1200, "total_steps": 9742, "loss": 0.4269, "lr": 9.630882598982198e-06, "epoch": 0.24635598439745432, "percentage": 12.32, "elapsed_time": "2:00:48", "remaining_time": "14:19:53", "throughput": 9136.35, "total_tokens": 66220408}244{"current_steps": 1205, "total_steps": 9742, "loss": 0.394, "lr": 9.627836486261862e-06, "epoch": 0.24738246766577704, "percentage": 12.37, "elapsed_time": "2:01:19", "remaining_time": "14:19:31", "throughput": 9134.07, "total_tokens": 66490176}245{"current_steps": 1210, "total_steps": 9742, "loss": 0.3611, "lr": 9.624778341996094e-06, "epoch": 0.2484089509340998, "percentage": 12.42, "elapsed_time": "2:01:39", "remaining_time": "14:17:50", "throughput": 9146.54, "total_tokens": 66765120}246{"current_steps": 1215, "total_steps": 9742, "loss": 0.414, "lr": 9.621708174135525e-06, "epoch": 0.2494354342024225, "percentage": 12.47, "elapsed_time": "2:02:03", "remaining_time": "14:16:39", "throughput": 9153.88, "total_tokens": 67041624}247{"current_steps": 1220, "total_steps": 9742, "loss": 0.4116, "lr": 9.618625990662037e-06, "epoch": 0.25046191747074525, "percentage": 12.52, "elapsed_time": "2:02:32", "remaining_time": "14:15:59", "throughput": 9156.68, "total_tokens": 67324976}248{"current_steps": 1225, "total_steps": 9742, "loss": 0.4159, "lr": 9.615531799588756e-06, "epoch": 0.251488400739068, "percentage": 12.57, "elapsed_time": "2:03:05", "remaining_time": "14:15:49", "throughput": 9152.72, "total_tokens": 67598248}249{"current_steps": 1230, "total_steps": 9742, "loss": 0.4094, "lr": 9.612425608960024e-06, "epoch": 0.2525148840073907, "percentage": 12.63, "elapsed_time": "2:03:35", "remaining_time": "14:15:17", "throughput": 9150.26, "total_tokens": 67853912}250{"current_steps": 1235, "total_steps": 9742, "loss": 0.3986, "lr": 9.60930742685138e-06, "epoch": 0.2535413672757134, "percentage": 12.68, "elapsed_time": "2:04:05", "remaining_time": "14:14:47", "throughput": 9150.02, "total_tokens": 68127224}251{"current_steps": 1240, "total_steps": 9742, "loss": 0.3954, "lr": 9.606177261369541e-06, "epoch": 0.25456785054403613, "percentage": 12.73, "elapsed_time": "2:04:35", "remaining_time": "14:14:18", "throughput": 9149.99, "total_tokens": 68405248}252{"current_steps": 1245, "total_steps": 9742, "loss": 0.3992, "lr": 9.603035120652373e-06, "epoch": 0.25559433381235885, "percentage": 12.78, "elapsed_time": "2:05:01", "remaining_time": "14:13:17", "throughput": 9152.23, "total_tokens": 68656376}253{"current_steps": 1250, "total_steps": 9742, "loss": 0.3987, "lr": 9.59988101286888e-06, "epoch": 0.2566208170806816, "percentage": 12.83, "elapsed_time": "2:05:34", "remaining_time": "14:13:05", "throughput": 9149.82, "total_tokens": 68937976}254{"current_steps": 1255, "total_steps": 9742, "loss": 0.4021, "lr": 9.596714946219178e-06, "epoch": 0.2576473003490043, "percentage": 12.88, "elapsed_time": "2:06:07", "remaining_time": "14:12:56", "throughput": 9144.98, "total_tokens": 69206080}255{"current_steps": 1260, "total_steps": 9742, "loss": 0.3469, "lr": 9.593536928934471e-06, "epoch": 0.258673783617327, "percentage": 12.93, "elapsed_time": "2:06:42", "remaining_time": "14:12:54", "throughput": 9137.83, "total_tokens": 69465936}256{"current_steps": 1265, "total_steps": 9742, "loss": 0.3713, "lr": 9.590346969277036e-06, "epoch": 0.2597002668856498, "percentage": 12.99, "elapsed_time": "2:07:16", "remaining_time": "14:12:52", "throughput": 9133.85, "total_tokens": 69748616}257{"current_steps": 1270, "total_steps": 9742, "loss": 0.3485, "lr": 9.587145075540194e-06, "epoch": 0.2607267501539725, "percentage": 13.04, "elapsed_time": "2:07:50", "remaining_time": "14:12:47", "throughput": 9127.47, "total_tokens": 70010128}258{"current_steps": 1275, "total_steps": 9742, "loss": 0.4265, "lr": 9.583931256048298e-06, "epoch": 0.26175323342229523, "percentage": 13.09, "elapsed_time": "2:08:15", "remaining_time": "14:11:43", "throughput": 9136.53, "total_tokens": 70309552}259{"current_steps": 1280, "total_steps": 9742, "loss": 0.4018, "lr": 9.580705519156698e-06, "epoch": 0.26277971669061795, "percentage": 13.14, "elapsed_time": "2:08:41", "remaining_time": "14:10:48", "throughput": 9142.83, "total_tokens": 70599336}260{"current_steps": 1285, "total_steps": 9742, "loss": 0.3787, "lr": 9.577467873251738e-06, "epoch": 0.26380619995894067, "percentage": 13.19, "elapsed_time": "2:09:08", "remaining_time": "14:09:58", "throughput": 9144.16, "total_tokens": 70857296}261{"current_steps": 1290, "total_steps": 9742, "loss": 0.3822, "lr": 9.574218326750713e-06, "epoch": 0.2648326832272634, "percentage": 13.24, "elapsed_time": "2:09:40", "remaining_time": "14:09:36", "throughput": 9142.47, "total_tokens": 71131832}262{"current_steps": 1295, "total_steps": 9742, "loss": 0.3977, "lr": 9.570956888101861e-06, "epoch": 0.2658591664955861, "percentage": 13.29, "elapsed_time": "2:10:10", "remaining_time": "14:09:06", "throughput": 9142.81, "total_tokens": 71410840}263{"current_steps": 1300, "total_steps": 9742, "loss": 0.4066, "lr": 9.567683565784343e-06, "epoch": 0.2668856497639088, "percentage": 13.34, "elapsed_time": "2:10:41", "remaining_time": "14:08:42", "throughput": 9140.72, "total_tokens": 71678072}264{"current_steps": 1305, "total_steps": 9742, "loss": 0.3834, "lr": 9.564398368308203e-06, "epoch": 0.26791213303223155, "percentage": 13.4, "elapsed_time": "2:11:07", "remaining_time": "14:07:42", "throughput": 9147.63, "total_tokens": 71966536}265{"current_steps": 1310, "total_steps": 9742, "loss": 0.3872, "lr": 9.56110130421437e-06, "epoch": 0.2689386163005543, "percentage": 13.45, "elapsed_time": "2:11:38", "remaining_time": "14:07:21", "throughput": 9142.48, "total_tokens": 72213720}266{"current_steps": 1315, "total_steps": 9742, "loss": 0.3924, "lr": 9.557792382074621e-06, "epoch": 0.26996509956887704, "percentage": 13.5, "elapsed_time": "2:12:10", "remaining_time": "14:07:02", "throughput": 9140.61, "total_tokens": 72491216}267{"current_steps": 1320, "total_steps": 9742, "loss": 0.3815, "lr": 9.554471610491557e-06, "epoch": 0.27099158283719976, "percentage": 13.55, "elapsed_time": "2:12:45", "remaining_time": "14:07:03", "throughput": 9136.02, "total_tokens": 72774936}268{"current_steps": 1325, "total_steps": 9742, "loss": 0.3814, "lr": 9.55113899809859e-06, "epoch": 0.2720180661055225, "percentage": 13.6, "elapsed_time": "2:13:12", "remaining_time": "14:06:09", "throughput": 9140.05, "total_tokens": 73047616}269{"current_steps": 1330, "total_steps": 9742, "loss": 0.3797, "lr": 9.547794553559916e-06, "epoch": 0.2730445493738452, "percentage": 13.65, "elapsed_time": "2:13:39", "remaining_time": "14:05:22", "throughput": 9145.43, "total_tokens": 73343128}270{"current_steps": 1335, "total_steps": 9742, "loss": 0.3966, "lr": 9.544438285570492e-06, "epoch": 0.2740710326421679, "percentage": 13.7, "elapsed_time": "2:14:10", "remaining_time": "14:04:57", "throughput": 9143.76, "total_tokens": 73611840}271{"current_steps": 1340, "total_steps": 9742, "loss": 0.399, "lr": 9.54107020285601e-06, "epoch": 0.27509751591049064, "percentage": 13.75, "elapsed_time": "2:14:41", "remaining_time": "14:04:30", "throughput": 9141.76, "total_tokens": 73876512}272{"current_steps": 1345, "total_steps": 9742, "loss": 0.4061, "lr": 9.537690314172887e-06, "epoch": 0.27612399917881336, "percentage": 13.81, "elapsed_time": "2:15:12", "remaining_time": "14:04:05", "throughput": 9141.83, "total_tokens": 74160248}273{"current_steps": 1350, "total_steps": 9742, "loss": 0.3756, "lr": 9.534298628308221e-06, "epoch": 0.27715048244713614, "percentage": 13.86, "elapsed_time": "2:15:40", "remaining_time": "14:03:26", "throughput": 9143.13, "total_tokens": 74433736}274{"current_steps": 1355, "total_steps": 9742, "loss": 0.4074, "lr": 9.530895154079791e-06, "epoch": 0.27817696571545886, "percentage": 13.91, "elapsed_time": "2:16:11", "remaining_time": "14:02:57", "throughput": 9140.54, "total_tokens": 74689240}275{"current_steps": 1360, "total_steps": 9742, "loss": 0.3769, "lr": 9.527479900336022e-06, "epoch": 0.2792034489837816, "percentage": 13.96, "elapsed_time": "2:16:39", "remaining_time": "14:02:13", "throughput": 9139.52, "total_tokens": 74936904}276{"current_steps": 1365, "total_steps": 9742, "loss": 0.3765, "lr": 9.524052875955956e-06, "epoch": 0.2802299322521043, "percentage": 14.01, "elapsed_time": "2:17:07", "remaining_time": "14:01:31", "throughput": 9141.18, "total_tokens": 75207928}277{"current_steps": 1370, "total_steps": 9742, "loss": 0.3771, "lr": 9.520614089849247e-06, "epoch": 0.281256415520427, "percentage": 14.06, "elapsed_time": "2:17:34", "remaining_time": "14:00:40", "throughput": 9142.63, "total_tokens": 75464336}278{"current_steps": 1375, "total_steps": 9742, "loss": 0.3793, "lr": 9.517163550956121e-06, "epoch": 0.28228289878874974, "percentage": 14.11, "elapsed_time": "2:17:58", "remaining_time": "13:59:36", "throughput": 9149.49, "total_tokens": 75745936}279{"current_steps": 1380, "total_steps": 9742, "loss": 0.3833, "lr": 9.51370126824736e-06, "epoch": 0.28330938205707246, "percentage": 14.17, "elapsed_time": "2:18:29", "remaining_time": "13:59:09", "throughput": 9148.58, "total_tokens": 76018784}280{"current_steps": 1385, "total_steps": 9742, "loss": 0.3853, "lr": 9.51022725072428e-06, "epoch": 0.2843358653253952, "percentage": 14.22, "elapsed_time": "2:19:03", "remaining_time": "13:59:04", "throughput": 9146.39, "total_tokens": 76312920}281{"current_steps": 1390, "total_steps": 9742, "loss": 0.4051, "lr": 9.506741507418703e-06, "epoch": 0.2853623485937179, "percentage": 14.27, "elapsed_time": "2:19:36", "remaining_time": "13:58:51", "throughput": 9143.82, "total_tokens": 76593616}282{"current_steps": 1395, "total_steps": 9742, "loss": 0.3896, "lr": 9.503244047392936e-06, "epoch": 0.28638883186204067, "percentage": 14.32, "elapsed_time": "2:20:05", "remaining_time": "13:58:11", "throughput": 9146.93, "total_tokens": 76880568}283{"current_steps": 1400, "total_steps": 9742, "loss": 0.3902, "lr": 9.499734879739752e-06, "epoch": 0.2874153151303634, "percentage": 14.37, "elapsed_time": "2:20:38", "remaining_time": "13:58:03", "throughput": 9141.34, "total_tokens": 77142664}284{"current_steps": 1405, "total_steps": 9742, "loss": 0.3641, "lr": 9.496214013582352e-06, "epoch": 0.2884417983986861, "percentage": 14.42, "elapsed_time": "2:21:07", "remaining_time": "13:57:25", "throughput": 9141.31, "total_tokens": 77405616}285{"current_steps": 1410, "total_steps": 9742, "loss": 0.3858, "lr": 9.492681458074362e-06, "epoch": 0.28946828166700883, "percentage": 14.47, "elapsed_time": "2:21:33", "remaining_time": "13:56:30", "throughput": 9147.22, "total_tokens": 77692176}286{"current_steps": 1415, "total_steps": 9742, "loss": 0.4173, "lr": 9.489137222399791e-06, "epoch": 0.29049476493533155, "percentage": 14.52, "elapsed_time": "2:22:08", "remaining_time": "13:56:29", "throughput": 9145.14, "total_tokens": 77995624}287{"current_steps": 1420, "total_steps": 9742, "loss": 0.3632, "lr": 9.485581315773016e-06, "epoch": 0.29152124820365427, "percentage": 14.58, "elapsed_time": "2:22:43", "remaining_time": "13:56:29", "throughput": 9140.6, "total_tokens": 78279416}288{"current_steps": 1425, "total_steps": 9742, "loss": 0.3467, "lr": 9.482013747438758e-06, "epoch": 0.292547731471977, "percentage": 14.63, "elapsed_time": "2:23:12", "remaining_time": "13:55:51", "throughput": 9141.52, "total_tokens": 78551128}289{"current_steps": 1430, "total_steps": 9742, "loss": 0.3931, "lr": 9.478434526672056e-06, "epoch": 0.2935742147402997, "percentage": 14.68, "elapsed_time": "2:23:46", "remaining_time": "13:55:45", "throughput": 9135.74, "total_tokens": 78813976}290{"current_steps": 1435, "total_steps": 9742, "loss": 0.3819, "lr": 9.474843662778242e-06, "epoch": 0.2946006980086225, "percentage": 14.73, "elapsed_time": "2:24:12", "remaining_time": "13:54:49", "throughput": 9140.22, "total_tokens": 79087344}291{"current_steps": 1440, "total_steps": 9742, "loss": 0.3881, "lr": 9.471241165092917e-06, "epoch": 0.2956271812769452, "percentage": 14.78, "elapsed_time": "2:24:46", "remaining_time": "13:54:39", "throughput": 9135.97, "total_tokens": 79358856}292{"current_steps": 1445, "total_steps": 9742, "loss": 0.3656, "lr": 9.46762704298193e-06, "epoch": 0.2966536645452679, "percentage": 14.83, "elapsed_time": "2:25:12", "remaining_time": "13:53:47", "throughput": 9139.72, "total_tokens": 79632448}293{"current_steps": 1450, "total_steps": 9742, "loss": 0.3737, "lr": 9.464001305841351e-06, "epoch": 0.29768014781359065, "percentage": 14.88, "elapsed_time": "2:25:48", "remaining_time": "13:53:47", "throughput": 9137.73, "total_tokens": 79938648}294{"current_steps": 1455, "total_steps": 9742, "loss": 0.366, "lr": 9.460363963097448e-06, "epoch": 0.29870663108191337, "percentage": 14.94, "elapsed_time": "2:26:21", "remaining_time": "13:53:34", "throughput": 9133.86, "total_tokens": 80207696}295{"current_steps": 1460, "total_steps": 9742, "loss": 0.3763, "lr": 9.45671502420666e-06, "epoch": 0.2997331143502361, "percentage": 14.99, "elapsed_time": "2:26:43", "remaining_time": "13:52:17", "throughput": 9140.36, "total_tokens": 80465928}296{"current_steps": 1465, "total_steps": 9742, "loss": 0.4038, "lr": 9.45305449865557e-06, "epoch": 0.3007595976185588, "percentage": 15.04, "elapsed_time": "2:27:13", "remaining_time": "13:51:45", "throughput": 9141.09, "total_tokens": 80743880}297{"current_steps": 1470, "total_steps": 9742, "loss": 0.3692, "lr": 9.449382395960895e-06, "epoch": 0.3017860808868815, "percentage": 15.09, "elapsed_time": "2:27:39", "remaining_time": "13:50:55", "throughput": 9145.73, "total_tokens": 81028600}298{"current_steps": 1475, "total_steps": 9742, "loss": 0.3921, "lr": 9.44569872566944e-06, "epoch": 0.30281256415520424, "percentage": 15.14, "elapsed_time": "2:28:13", "remaining_time": "13:50:45", "throughput": 9138.6, "total_tokens": 81272960}299{"current_steps": 1480, "total_steps": 9742, "loss": 0.4097, "lr": 9.442003497358086e-06, "epoch": 0.303839047423527, "percentage": 15.19, "elapsed_time": "2:28:49", "remaining_time": "13:50:49", "throughput": 9132.24, "total_tokens": 81548824}300{"current_steps": 1485, "total_steps": 9742, "loss": 0.3846, "lr": 9.438296720633766e-06, "epoch": 0.30486553069184974, "percentage": 15.24, "elapsed_time": "2:29:18", "remaining_time": "13:50:13", "throughput": 9130.44, "total_tokens": 81798456}301{"current_steps": 1490, "total_steps": 9742, "loss": 0.4247, "lr": 9.434578405133437e-06, "epoch": 0.30589201396017246, "percentage": 15.29, "elapsed_time": "2:29:50", "remaining_time": "13:49:53", "throughput": 9129.28, "total_tokens": 82080512}302{"current_steps": 1495, "total_steps": 9742, "loss": 0.373, "lr": 9.43084856052405e-06, "epoch": 0.3069184972284952, "percentage": 15.35, "elapsed_time": "2:30:23", "remaining_time": "13:49:39", "throughput": 9127.26, "total_tokens": 82363472}303{"current_steps": 1500, "total_steps": 9742, "loss": 0.3618, "lr": 9.427107196502536e-06, "epoch": 0.3079449804968179, "percentage": 15.4, "elapsed_time": "2:30:52", "remaining_time": "13:49:00", "throughput": 9128.57, "total_tokens": 82637104}304{"current_steps": 1505, "total_steps": 9742, "loss": 0.388, "lr": 9.423354322795768e-06, "epoch": 0.3089714637651406, "percentage": 15.45, "elapsed_time": "2:31:22", "remaining_time": "13:48:28", "throughput": 9129.12, "total_tokens": 82914152}305{"current_steps": 1510, "total_steps": 9742, "loss": 0.4166, "lr": 9.419589949160545e-06, "epoch": 0.30999794703346334, "percentage": 15.5, "elapsed_time": "2:31:47", "remaining_time": "13:47:29", "throughput": 9134.74, "total_tokens": 83192696}306{"current_steps": 1515, "total_steps": 9742, "loss": 0.3529, "lr": 9.415814085383566e-06, "epoch": 0.31102443030178606, "percentage": 15.55, "elapsed_time": "2:32:16", "remaining_time": "13:46:52", "throughput": 9138.62, "total_tokens": 83492416}307{"current_steps": 1520, "total_steps": 9742, "loss": 0.3625, "lr": 9.412026741281397e-06, "epoch": 0.31205091357010883, "percentage": 15.6, "elapsed_time": "2:32:47", "remaining_time": "13:46:30", "throughput": 9136.59, "total_tokens": 83762448}308{"current_steps": 1525, "total_steps": 9742, "loss": 0.4068, "lr": 9.408227926700455e-06, "epoch": 0.31307739683843155, "percentage": 15.65, "elapsed_time": "2:33:15", "remaining_time": "13:45:46", "throughput": 9133.68, "total_tokens": 83987216}309{"current_steps": 1530, "total_steps": 9742, "loss": 0.3683, "lr": 9.40441765151698e-06, "epoch": 0.3141038801067543, "percentage": 15.71, "elapsed_time": "2:33:46", "remaining_time": "13:45:19", "throughput": 9132.9, "total_tokens": 84261144}310{"current_steps": 1535, "total_steps": 9742, "loss": 0.4075, "lr": 9.400595925636999e-06, "epoch": 0.315130363375077, "percentage": 15.76, "elapsed_time": "2:34:11", "remaining_time": "13:44:21", "throughput": 9139.29, "total_tokens": 84547976}311{"current_steps": 1540, "total_steps": 9742, "loss": 0.4, "lr": 9.39676275899632e-06, "epoch": 0.3161568466433997, "percentage": 15.81, "elapsed_time": "2:34:41", "remaining_time": "13:43:53", "throughput": 9138.66, "total_tokens": 84821000}312{"current_steps": 1545, "total_steps": 9742, "loss": 0.4078, "lr": 9.392918161560485e-06, "epoch": 0.31718332991172243, "percentage": 15.86, "elapsed_time": "2:35:13", "remaining_time": "13:43:34", "throughput": 9138.85, "total_tokens": 85117688}313{"current_steps": 1550, "total_steps": 9742, "loss": 0.4009, "lr": 9.38906214332476e-06, "epoch": 0.31820981318004515, "percentage": 15.91, "elapsed_time": "2:35:47", "remaining_time": "13:43:23", "throughput": 9135.29, "total_tokens": 85393312}314{"current_steps": 1555, "total_steps": 9742, "loss": 0.3819, "lr": 9.385194714314102e-06, "epoch": 0.3192362964483679, "percentage": 15.96, "elapsed_time": "2:36:19", "remaining_time": "13:43:03", "throughput": 9132.73, "total_tokens": 85661408}315{"current_steps": 1560, "total_steps": 9742, "loss": 0.4371, "lr": 9.381315884583133e-06, "epoch": 0.3202627797166906, "percentage": 16.01, "elapsed_time": "2:36:54", "remaining_time": "13:42:57", "throughput": 9128.37, "total_tokens": 85937768}316{"current_steps": 1565, "total_steps": 9742, "loss": 0.3568, "lr": 9.377425664216115e-06, "epoch": 0.32128926298501337, "percentage": 16.06, "elapsed_time": "2:37:21", "remaining_time": "13:42:09", "throughput": 9131.3, "total_tokens": 86210264}317{"current_steps": 1570, "total_steps": 9742, "loss": 0.3871, "lr": 9.373524063326922e-06, "epoch": 0.3223157462533361, "percentage": 16.12, "elapsed_time": "2:37:56", "remaining_time": "13:42:06", "throughput": 9127.55, "total_tokens": 86498016}318{"current_steps": 1575, "total_steps": 9742, "loss": 0.3624, "lr": 9.36961109205902e-06, "epoch": 0.3233422295216588, "percentage": 16.17, "elapsed_time": "2:38:32", "remaining_time": "13:42:05", "throughput": 9122.79, "total_tokens": 86779352}319{"current_steps": 1580, "total_steps": 9742, "loss": 0.3487, "lr": 9.365686760585431e-06, "epoch": 0.32436871278998153, "percentage": 16.22, "elapsed_time": "2:39:02", "remaining_time": "13:41:36", "throughput": 9122.34, "total_tokens": 87051968}320{"current_steps": 1585, "total_steps": 9742, "loss": 0.3681, "lr": 9.361751079108713e-06, "epoch": 0.32539519605830425, "percentage": 16.27, "elapsed_time": "2:39:36", "remaining_time": "13:41:22", "throughput": 9118.21, "total_tokens": 87316832}321{"current_steps": 1590, "total_steps": 9742, "loss": 0.3944, "lr": 9.357804057860934e-06, "epoch": 0.32642167932662697, "percentage": 16.32, "elapsed_time": "2:39:59", "remaining_time": "13:40:19", "throughput": 9127.3, "total_tokens": 87621136}322{"current_steps": 1595, "total_steps": 9742, "loss": 0.3944, "lr": 9.353845707103641e-06, "epoch": 0.3274481625949497, "percentage": 16.37, "elapsed_time": "2:40:32", "remaining_time": "13:40:01", "throughput": 9124.94, "total_tokens": 87897104}323{"current_steps": 1600, "total_steps": 9742, "loss": 0.3953, "lr": 9.349876037127837e-06, "epoch": 0.3284746458632724, "percentage": 16.42, "elapsed_time": "2:41:04", "remaining_time": "13:39:40", "throughput": 9124.13, "total_tokens": 88180712}324{"current_steps": 1605, "total_steps": 9742, "loss": 0.4261, "lr": 9.345895058253952e-06, "epoch": 0.3295011291315951, "percentage": 16.48, "elapsed_time": "2:41:34", "remaining_time": "13:39:10", "throughput": 9125.18, "total_tokens": 88466008}325{"current_steps": 1610, "total_steps": 9742, "loss": 0.3736, "lr": 9.341902780831817e-06, "epoch": 0.3305276123999179, "percentage": 16.53, "elapsed_time": "2:42:03", "remaining_time": "13:38:30", "throughput": 9129.4, "total_tokens": 88765776}326{"current_steps": 1615, "total_steps": 9742, "loss": 0.3809, "lr": 9.33789921524064e-06, "epoch": 0.3315540956682406, "percentage": 16.58, "elapsed_time": "2:42:25", "remaining_time": "13:37:19", "throughput": 9138.37, "total_tokens": 89054128}327{"current_steps": 1620, "total_steps": 9742, "loss": 0.4149, "lr": 9.333884371888972e-06, "epoch": 0.33258057893656334, "percentage": 16.63, "elapsed_time": "2:42:51", "remaining_time": "13:36:32", "throughput": 9140.86, "total_tokens": 89323440}328{"current_steps": 1625, "total_steps": 9742, "loss": 0.3681, "lr": 9.329858261214687e-06, "epoch": 0.33360706220488606, "percentage": 16.68, "elapsed_time": "2:43:25", "remaining_time": "13:36:18", "throughput": 9139.83, "total_tokens": 89619168}329{"current_steps": 1630, "total_steps": 9742, "loss": 0.3953, "lr": 9.32582089368495e-06, "epoch": 0.3346335454732088, "percentage": 16.73, "elapsed_time": "2:43:59", "remaining_time": "13:36:05", "throughput": 9136.68, "total_tokens": 89895968}330{"current_steps": 1635, "total_steps": 9742, "loss": 0.3997, "lr": 9.321772279796193e-06, "epoch": 0.3356600287415315, "percentage": 16.78, "elapsed_time": "2:44:29", "remaining_time": "13:35:37", "throughput": 9136.36, "total_tokens": 90172056}331{"current_steps": 1640, "total_steps": 9742, "loss": 0.3724, "lr": 9.31771243007409e-06, "epoch": 0.3366865120098542, "percentage": 16.83, "elapsed_time": "2:45:01", "remaining_time": "13:35:17", "throughput": 9135.07, "total_tokens": 90454048}332{"current_steps": 1645, "total_steps": 9742, "loss": 0.3843, "lr": 9.313641355073517e-06, "epoch": 0.33771299527817694, "percentage": 16.89, "elapsed_time": "2:45:34", "remaining_time": "13:34:57", "throughput": 9132.53, "total_tokens": 90722792}333{"current_steps": 1650, "total_steps": 9742, "loss": 0.3426, "lr": 9.309559065378544e-06, "epoch": 0.3387394785464997, "percentage": 16.94, "elapsed_time": "2:46:04", "remaining_time": "13:34:30", "throughput": 9132.76, "total_tokens": 91006744}334{"current_steps": 1655, "total_steps": 9742, "loss": 0.3952, "lr": 9.30546557160239e-06, "epoch": 0.33976596181482244, "percentage": 16.99, "elapsed_time": "2:46:32", "remaining_time": "13:33:47", "throughput": 9133.85, "total_tokens": 91271056}335{"current_steps": 1660, "total_steps": 9742, "loss": 0.3837, "lr": 9.301360884387408e-06, "epoch": 0.34079244508314516, "percentage": 17.04, "elapsed_time": "2:47:04", "remaining_time": "13:33:27", "throughput": 9131.47, "total_tokens": 91540880}336{"current_steps": 1665, "total_steps": 9742, "loss": 0.3988, "lr": 9.297245014405045e-06, "epoch": 0.3418189283514679, "percentage": 17.09, "elapsed_time": "2:47:38", "remaining_time": "13:33:12", "throughput": 9126.23, "total_tokens": 91792464}337{"current_steps": 1670, "total_steps": 9742, "loss": 0.3797, "lr": 9.293117972355828e-06, "epoch": 0.3428454116197906, "percentage": 17.14, "elapsed_time": "2:48:09", "remaining_time": "13:32:48", "throughput": 9124.38, "total_tokens": 92061096}338{"current_steps": 1675, "total_steps": 9742, "loss": 0.3788, "lr": 9.288979768969327e-06, "epoch": 0.3438718948881133, "percentage": 17.19, "elapsed_time": "2:48:37", "remaining_time": "13:32:07", "throughput": 9126.05, "total_tokens": 92333200}339{"current_steps": 1680, "total_steps": 9742, "loss": 0.375, "lr": 9.284830415004126e-06, "epoch": 0.34489837815643604, "percentage": 17.24, "elapsed_time": "2:49:06", "remaining_time": "13:31:31", "throughput": 9126.92, "total_tokens": 92606848}340{"current_steps": 1685, "total_steps": 9742, "loss": 0.3738, "lr": 9.280669921247805e-06, "epoch": 0.34592486142475876, "percentage": 17.3, "elapsed_time": "2:49:34", "remaining_time": "13:30:48", "throughput": 9129.9, "total_tokens": 92888392}341{"current_steps": 1690, "total_steps": 9742, "loss": 0.3922, "lr": 9.2764982985169e-06, "epoch": 0.3469513446930815, "percentage": 17.35, "elapsed_time": "2:50:02", "remaining_time": "13:30:09", "throughput": 9132.29, "total_tokens": 93172112}342{"current_steps": 1695, "total_steps": 9742, "loss": 0.418, "lr": 9.272315557656884e-06, "epoch": 0.34797782796140425, "percentage": 17.4, "elapsed_time": "2:50:32", "remaining_time": "13:29:41", "throughput": 9130.27, "total_tokens": 93429968}343{"current_steps": 1700, "total_steps": 9742, "loss": 0.3772, "lr": 9.268121709542133e-06, "epoch": 0.34900431122972697, "percentage": 17.45, "elapsed_time": "2:51:02", "remaining_time": "13:29:09", "throughput": 9130.54, "total_tokens": 93705920}344{"current_steps": 1705, "total_steps": 9742, "loss": 0.3931, "lr": 9.2639167650759e-06, "epoch": 0.3500307944980497, "percentage": 17.5, "elapsed_time": "2:51:34", "remaining_time": "13:28:47", "throughput": 9130.98, "total_tokens": 94001848}345{"current_steps": 1710, "total_steps": 9742, "loss": 0.4019, "lr": 9.259700735190287e-06, "epoch": 0.3510572777663724, "percentage": 17.55, "elapsed_time": "2:52:06", "remaining_time": "13:28:25", "throughput": 9128.91, "total_tokens": 94272672}346{"current_steps": 1715, "total_steps": 9742, "loss": 0.362, "lr": 9.255473630846218e-06, "epoch": 0.35208376103469513, "percentage": 17.6, "elapsed_time": "2:52:38", "remaining_time": "13:28:04", "throughput": 9128.75, "total_tokens": 94562880}347{"current_steps": 1720, "total_steps": 9742, "loss": 0.374, "lr": 9.251235463033403e-06, "epoch": 0.35311024430301785, "percentage": 17.66, "elapsed_time": "2:53:07", "remaining_time": "13:27:25", "throughput": 9132.03, "total_tokens": 94857288}348{"current_steps": 1725, "total_steps": 9742, "loss": 0.3755, "lr": 9.246986242770324e-06, "epoch": 0.35413672757134057, "percentage": 17.71, "elapsed_time": "2:53:37", "remaining_time": "13:26:54", "throughput": 9131.26, "total_tokens": 95122568}349{"current_steps": 1730, "total_steps": 9742, "loss": 0.3609, "lr": 9.242725981104186e-06, "epoch": 0.3551632108396633, "percentage": 17.76, "elapsed_time": "2:54:10", "remaining_time": "13:26:40", "throughput": 9129.15, "total_tokens": 95407816}350{"current_steps": 1735, "total_steps": 9742, "loss": 0.4095, "lr": 9.238454689110909e-06, "epoch": 0.35618969410798607, "percentage": 17.81, "elapsed_time": "2:54:45", "remaining_time": "13:26:28", "throughput": 9127.44, "total_tokens": 95702056}351{"current_steps": 1740, "total_steps": 9742, "loss": 0.4068, "lr": 9.234172377895085e-06, "epoch": 0.3572161773763088, "percentage": 17.86, "elapsed_time": "2:55:13", "remaining_time": "13:25:51", "throughput": 9128.53, "total_tokens": 95975016}352{"current_steps": 1745, "total_steps": 9742, "loss": 0.3663, "lr": 9.229879058589959e-06, "epoch": 0.3582426606446315, "percentage": 17.91, "elapsed_time": "2:55:37", "remaining_time": "13:24:52", "throughput": 9134.02, "total_tokens": 96251688}353{"current_steps": 1750, "total_steps": 9742, "loss": 0.357, "lr": 9.22557474235739e-06, "epoch": 0.3592691439129542, "percentage": 17.96, "elapsed_time": "2:56:15", "remaining_time": "13:24:55", "throughput": 9128.37, "total_tokens": 96535208}354{"current_steps": 1755, "total_steps": 9742, "loss": 0.3711, "lr": 9.221259440387827e-06, "epoch": 0.36029562718127695, "percentage": 18.01, "elapsed_time": "2:56:48", "remaining_time": "13:24:39", "throughput": 9126.48, "total_tokens": 96819032}355{"current_steps": 1760, "total_steps": 9742, "loss": 0.3872, "lr": 9.216933163900284e-06, "epoch": 0.36132211044959966, "percentage": 18.07, "elapsed_time": "2:57:20", "remaining_time": "13:24:14", "throughput": 9126.1, "total_tokens": 97101776}356{"current_steps": 1765, "total_steps": 9742, "loss": 0.3871, "lr": 9.212595924142304e-06, "epoch": 0.3623485937179224, "percentage": 18.12, "elapsed_time": "2:57:55", "remaining_time": "13:24:07", "throughput": 9122.74, "total_tokens": 97388728}357{"current_steps": 1770, "total_steps": 9742, "loss": 0.371, "lr": 9.208247732389933e-06, "epoch": 0.3633750769862451, "percentage": 18.17, "elapsed_time": "2:58:30", "remaining_time": "13:24:00", "throughput": 9117.61, "total_tokens": 97656424}358{"current_steps": 1775, "total_steps": 9742, "loss": 0.3718, "lr": 9.203888599947687e-06, "epoch": 0.3644015602545678, "percentage": 18.22, "elapsed_time": "2:59:02", "remaining_time": "13:23:36", "throughput": 9115.94, "total_tokens": 97927272}359{"current_steps": 1780, "total_steps": 9742, "loss": 0.3715, "lr": 9.199518538148534e-06, "epoch": 0.3654280435228906, "percentage": 18.27, "elapsed_time": "2:59:23", "remaining_time": "13:22:23", "throughput": 9123.34, "total_tokens": 98195560}360{"current_steps": 1785, "total_steps": 9742, "loss": 0.3847, "lr": 9.19513755835385e-06, "epoch": 0.3664545267912133, "percentage": 18.32, "elapsed_time": "2:59:58", "remaining_time": "13:22:17", "throughput": 9117.34, "total_tokens": 98455248}361{"current_steps": 1790, "total_steps": 9742, "loss": 0.3821, "lr": 9.190745671953397e-06, "epoch": 0.36748101005953604, "percentage": 18.37, "elapsed_time": "3:00:28", "remaining_time": "13:21:45", "throughput": 9116.77, "total_tokens": 98720968}362{"current_steps": 1795, "total_steps": 9742, "loss": 0.3864, "lr": 9.18634289036529e-06, "epoch": 0.36850749332785876, "percentage": 18.43, "elapsed_time": "3:00:57", "remaining_time": "13:21:09", "throughput": 9117.72, "total_tokens": 98995776}363{"current_steps": 1800, "total_steps": 9742, "loss": 0.3606, "lr": 9.181929225035975e-06, "epoch": 0.3695339765961815, "percentage": 18.48, "elapsed_time": "3:01:29", "remaining_time": "13:20:47", "throughput": 9114.25, "total_tokens": 99250240}364{"current_steps": 1805, "total_steps": 9742, "loss": 0.4084, "lr": 9.17750468744019e-06, "epoch": 0.3705604598645042, "percentage": 18.53, "elapsed_time": "3:02:00", "remaining_time": "13:20:20", "throughput": 9114.44, "total_tokens": 99534592}365{"current_steps": 1810, "total_steps": 9742, "loss": 0.4159, "lr": 9.173069289080941e-06, "epoch": 0.3715869431328269, "percentage": 18.58, "elapsed_time": "3:02:29", "remaining_time": "13:19:45", "throughput": 9115.13, "total_tokens": 99808488}366{"current_steps": 1815, "total_steps": 9742, "loss": 0.3281, "lr": 9.168623041489466e-06, "epoch": 0.37261342640114964, "percentage": 18.63, "elapsed_time": "3:02:58", "remaining_time": "13:19:07", "throughput": 9117.37, "total_tokens": 100092744}367{"current_steps": 1820, "total_steps": 9742, "loss": 0.3644, "lr": 9.164165956225213e-06, "epoch": 0.3736399096694724, "percentage": 18.68, "elapsed_time": "3:03:26", "remaining_time": "13:18:30", "throughput": 9118.84, "total_tokens": 100369960}368{"current_steps": 1825, "total_steps": 9742, "loss": 0.3722, "lr": 9.159698044875806e-06, "epoch": 0.37466639293779513, "percentage": 18.73, "elapsed_time": "3:03:57", "remaining_time": "13:18:02", "throughput": 9119.08, "total_tokens": 100654448}369{"current_steps": 1830, "total_steps": 9742, "loss": 0.3816, "lr": 9.155219319057013e-06, "epoch": 0.37569287620611785, "percentage": 18.78, "elapsed_time": "3:04:26", "remaining_time": "13:17:25", "throughput": 9117.75, "total_tokens": 100901408}370{"current_steps": 1835, "total_steps": 9742, "loss": 0.3876, "lr": 9.15072979041272e-06, "epoch": 0.3767193594744406, "percentage": 18.84, "elapsed_time": "3:04:57", "remaining_time": "13:16:57", "throughput": 9117.43, "total_tokens": 101177256}371{"current_steps": 1840, "total_steps": 9742, "loss": 0.4001, "lr": 9.146229470614894e-06, "epoch": 0.3777458427427633, "percentage": 18.89, "elapsed_time": "3:05:25", "remaining_time": "13:16:18", "throughput": 9117.75, "total_tokens": 101437712}372{"current_steps": 1845, "total_steps": 9742, "loss": 0.3627, "lr": 9.14171837136356e-06, "epoch": 0.378772326011086, "percentage": 18.94, "elapsed_time": "3:05:56", "remaining_time": "13:15:51", "throughput": 9116.72, "total_tokens": 101709136}373{"current_steps": 1850, "total_steps": 9742, "loss": 0.3642, "lr": 9.13719650438677e-06, "epoch": 0.37979880927940873, "percentage": 18.99, "elapsed_time": "3:06:21", "remaining_time": "13:15:00", "throughput": 9122.67, "total_tokens": 102007080}374{"current_steps": 1855, "total_steps": 9742, "loss": 0.3622, "lr": 9.132663881440566e-06, "epoch": 0.38082529254773145, "percentage": 19.04, "elapsed_time": "3:06:50", "remaining_time": "13:14:22", "throughput": 9123.02, "total_tokens": 102270264}375{"current_steps": 1860, "total_steps": 9742, "loss": 0.3514, "lr": 9.128120514308957e-06, "epoch": 0.3818517758160542, "percentage": 19.09, "elapsed_time": "3:07:21", "remaining_time": "13:13:56", "throughput": 9122.9, "total_tokens": 102552472}376{"current_steps": 1865, "total_steps": 9742, "loss": 0.3878, "lr": 9.12356641480388e-06, "epoch": 0.38287825908437695, "percentage": 19.14, "elapsed_time": "3:07:57", "remaining_time": "13:13:51", "throughput": 9116.65, "total_tokens": 102813560}377{"current_steps": 1870, "total_steps": 9742, "loss": 0.3678, "lr": 9.11900159476518e-06, "epoch": 0.38390474235269967, "percentage": 19.2, "elapsed_time": "3:08:36", "remaining_time": "13:13:56", "throughput": 9111.26, "total_tokens": 103103200}378{"current_steps": 1875, "total_steps": 9742, "loss": 0.3519, "lr": 9.11442606606057e-06, "epoch": 0.3849312256210224, "percentage": 19.25, "elapsed_time": "3:09:04", "remaining_time": "13:13:17", "throughput": 9113.6, "total_tokens": 103386392}379{"current_steps": 1880, "total_steps": 9742, "loss": 0.3841, "lr": 9.109839840585606e-06, "epoch": 0.3859577088893451, "percentage": 19.3, "elapsed_time": "3:09:29", "remaining_time": "13:12:26", "throughput": 9117.26, "total_tokens": 103659440}380{"current_steps": 1885, "total_steps": 9742, "loss": 0.3631, "lr": 9.105242930263652e-06, "epoch": 0.38698419215766783, "percentage": 19.35, "elapsed_time": "3:10:06", "remaining_time": "13:12:22", "throughput": 9111.13, "total_tokens": 103923216}381{"current_steps": 1890, "total_steps": 9742, "loss": 0.3476, "lr": 9.100635347045848e-06, "epoch": 0.38801067542599055, "percentage": 19.4, "elapsed_time": "3:10:41", "remaining_time": "13:12:13", "throughput": 9105.9, "total_tokens": 104184752}382{"current_steps": 1895, "total_steps": 9742, "loss": 0.3708, "lr": 9.096017102911088e-06, "epoch": 0.38903715869431327, "percentage": 19.45, "elapsed_time": "3:11:08", "remaining_time": "13:11:28", "throughput": 9109.01, "total_tokens": 104462584}383{"current_steps": 1900, "total_steps": 9742, "loss": 0.3925, "lr": 9.091388209865977e-06, "epoch": 0.390063641962636, "percentage": 19.5, "elapsed_time": "3:11:33", "remaining_time": "13:10:39", "throughput": 9113.84, "total_tokens": 104753208}384{"current_steps": 1905, "total_steps": 9742, "loss": 0.3763, "lr": 9.086748679944807e-06, "epoch": 0.39109012523095876, "percentage": 19.55, "elapsed_time": "3:12:03", "remaining_time": "13:10:05", "throughput": 9116.05, "total_tokens": 105045664}385{"current_steps": 1910, "total_steps": 9742, "loss": 0.3929, "lr": 9.082098525209527e-06, "epoch": 0.3921166084992815, "percentage": 19.61, "elapsed_time": "3:12:36", "remaining_time": "13:09:47", "throughput": 9113.55, "total_tokens": 105321368}386{"current_steps": 1915, "total_steps": 9742, "loss": 0.3732, "lr": 9.077437757749703e-06, "epoch": 0.3931430917676042, "percentage": 19.66, "elapsed_time": "3:13:01", "remaining_time": "13:08:57", "throughput": 9118.87, "total_tokens": 105613880}387{"current_steps": 1920, "total_steps": 9742, "loss": 0.3402, "lr": 9.072766389682497e-06, "epoch": 0.3941695750359269, "percentage": 19.71, "elapsed_time": "3:13:29", "remaining_time": "13:08:16", "throughput": 9120.92, "total_tokens": 105889896}388{"current_steps": 1925, "total_steps": 9742, "loss": 0.38, "lr": 9.068084433152629e-06, "epoch": 0.39519605830424964, "percentage": 19.76, "elapsed_time": "3:13:53", "remaining_time": "13:07:22", "throughput": 9124.22, "total_tokens": 106149496}389{"current_steps": 1930, "total_steps": 9742, "loss": 0.4144, "lr": 9.063391900332345e-06, "epoch": 0.39622254157257236, "percentage": 19.81, "elapsed_time": "3:14:29", "remaining_time": "13:07:13", "throughput": 9121.36, "total_tokens": 106440488}390{"current_steps": 1935, "total_steps": 9742, "loss": 0.3994, "lr": 9.05868880342139e-06, "epoch": 0.3972490248408951, "percentage": 19.86, "elapsed_time": "3:15:06", "remaining_time": "13:07:11", "throughput": 9116.22, "total_tokens": 106718288}391{"current_steps": 1940, "total_steps": 9742, "loss": 0.3832, "lr": 9.053975154646973e-06, "epoch": 0.3982755081092178, "percentage": 19.91, "elapsed_time": "3:15:34", "remaining_time": "13:06:30", "throughput": 9117.13, "total_tokens": 106981680}392{"current_steps": 1945, "total_steps": 9742, "loss": 0.3693, "lr": 9.049250966263736e-06, "epoch": 0.3993019913775405, "percentage": 19.97, "elapsed_time": "3:16:04", "remaining_time": "13:06:00", "throughput": 9120.17, "total_tokens": 107293864}393{"current_steps": 1950, "total_steps": 9742, "loss": 0.3761, "lr": 9.044516250553723e-06, "epoch": 0.4003284746458633, "percentage": 20.02, "elapsed_time": "3:16:32", "remaining_time": "13:05:22", "throughput": 9120.62, "total_tokens": 107556880}394{"current_steps": 1955, "total_steps": 9742, "loss": 0.3785, "lr": 9.039771019826344e-06, "epoch": 0.401354957914186, "percentage": 20.07, "elapsed_time": "3:16:59", "remaining_time": "13:04:39", "throughput": 9123.81, "total_tokens": 107841080}395{"current_steps": 1960, "total_steps": 9742, "loss": 0.3536, "lr": 9.035015286418352e-06, "epoch": 0.40238144118250874, "percentage": 20.12, "elapsed_time": "3:17:33", "remaining_time": "13:04:23", "throughput": 9121.85, "total_tokens": 108126376}396{"current_steps": 1965, "total_steps": 9742, "loss": 0.3593, "lr": 9.030249062693799e-06, "epoch": 0.40340792445083146, "percentage": 20.17, "elapsed_time": "3:17:56", "remaining_time": "13:03:25", "throughput": 9128.0, "total_tokens": 108410568}397{"current_steps": 1970, "total_steps": 9742, "loss": 0.329, "lr": 9.025472361044011e-06, "epoch": 0.4044344077191542, "percentage": 20.22, "elapsed_time": "3:18:31", "remaining_time": "13:03:12", "throughput": 9125.55, "total_tokens": 108697000}398{"current_steps": 1975, "total_steps": 9742, "loss": 0.3962, "lr": 9.02068519388756e-06, "epoch": 0.4054608909874769, "percentage": 20.27, "elapsed_time": "3:19:02", "remaining_time": "13:02:46", "throughput": 9125.35, "total_tokens": 108981792}399{"current_steps": 1980, "total_steps": 9742, "loss": 0.3612, "lr": 9.015887573670222e-06, "epoch": 0.4064873742557996, "percentage": 20.32, "elapsed_time": "3:19:35", "remaining_time": "13:02:26", "throughput": 9125.37, "total_tokens": 109281464}400{"current_steps": 1985, "total_steps": 9742, "loss": 0.4048, "lr": 9.011079512864945e-06, "epoch": 0.40751385752412234, "percentage": 20.38, "elapsed_time": "3:20:07", "remaining_time": "13:02:02", "throughput": 9125.0, "total_tokens": 109566360}401{"current_steps": 1990, "total_steps": 9742, "loss": 0.3988, "lr": 9.006261023971832e-06, "epoch": 0.40854034079244506, "percentage": 20.43, "elapsed_time": "3:20:39", "remaining_time": "13:01:40", "throughput": 9124.1, "total_tokens": 109851168}402{"current_steps": 1995, "total_steps": 9742, "loss": 0.3597, "lr": 9.001432119518086e-06, "epoch": 0.40956682406076783, "percentage": 20.48, "elapsed_time": "3:21:07", "remaining_time": "13:01:01", "throughput": 9124.32, "total_tokens": 110109216}403{"current_steps": 2000, "total_steps": 9742, "loss": 0.378, "lr": 8.996592812057992e-06, "epoch": 0.41059330732909055, "percentage": 20.53, "elapsed_time": "3:21:41", "remaining_time": "13:00:46", "throughput": 9121.87, "total_tokens": 110391344}404{"current_steps": 2005, "total_steps": 9742, "loss": 0.3424, "lr": 8.991743114172885e-06, "epoch": 0.41161979059741327, "percentage": 20.58, "elapsed_time": "3:22:12", "remaining_time": "13:00:16", "throughput": 9121.87, "total_tokens": 110667896}405{"current_steps": 2010, "total_steps": 9742, "loss": 0.384, "lr": 8.986883038471112e-06, "epoch": 0.412646273865736, "percentage": 20.63, "elapsed_time": "3:22:48", "remaining_time": "13:00:11", "throughput": 9115.22, "total_tokens": 110923032}406{"current_steps": 2015, "total_steps": 9742, "loss": 0.3459, "lr": 8.982012597587996e-06, "epoch": 0.4136727571340587, "percentage": 20.68, "elapsed_time": "3:23:11", "remaining_time": "12:59:12", "throughput": 9123.24, "total_tokens": 111230128}407{"current_steps": 2020, "total_steps": 9742, "loss": 0.3821, "lr": 8.977131804185812e-06, "epoch": 0.41469924040238143, "percentage": 20.73, "elapsed_time": "3:23:42", "remaining_time": "12:58:45", "throughput": 9121.25, "total_tokens": 111487816}408{"current_steps": 2025, "total_steps": 9742, "loss": 0.3523, "lr": 8.972240670953745e-06, "epoch": 0.41572572367070415, "percentage": 20.79, "elapsed_time": "3:24:09", "remaining_time": "12:58:03", "throughput": 9124.77, "total_tokens": 111778264}409{"current_steps": 2030, "total_steps": 9742, "loss": 0.3754, "lr": 8.967339210607868e-06, "epoch": 0.41675220693902687, "percentage": 20.84, "elapsed_time": "3:24:42", "remaining_time": "12:57:40", "throughput": 9121.92, "total_tokens": 112038640}410{"current_steps": 2035, "total_steps": 9742, "loss": 0.3533, "lr": 8.962427435891096e-06, "epoch": 0.41777869020734965, "percentage": 20.89, "elapsed_time": "3:25:14", "remaining_time": "12:57:18", "throughput": 9121.36, "total_tokens": 112327240}411{"current_steps": 2040, "total_steps": 9742, "loss": 0.359, "lr": 8.957505359573168e-06, "epoch": 0.41880517347567237, "percentage": 20.94, "elapsed_time": "3:25:44", "remaining_time": "12:56:47", "throughput": 9123.67, "total_tokens": 112629680}412{"current_steps": 2045, "total_steps": 9742, "loss": 0.4055, "lr": 8.952572994450595e-06, "epoch": 0.4198316567439951, "percentage": 20.99, "elapsed_time": "3:26:17", "remaining_time": "12:56:25", "throughput": 9120.57, "total_tokens": 112886768}413{"current_steps": 2050, "total_steps": 9742, "loss": 0.3695, "lr": 8.947630353346646e-06, "epoch": 0.4208581400123178, "percentage": 21.04, "elapsed_time": "3:26:48", "remaining_time": "12:55:57", "throughput": 9120.33, "total_tokens": 113165448}414{"current_steps": 2055, "total_steps": 9742, "loss": 0.3782, "lr": 8.9426774491113e-06, "epoch": 0.4218846232806405, "percentage": 21.09, "elapsed_time": "3:27:21", "remaining_time": "12:55:40", "throughput": 9118.72, "total_tokens": 113454864}415{"current_steps": 2060, "total_steps": 9742, "loss": 0.3477, "lr": 8.937714294621221e-06, "epoch": 0.42291110654896324, "percentage": 21.15, "elapsed_time": "3:27:50", "remaining_time": "12:55:03", "throughput": 9119.9, "total_tokens": 113728464}416{"current_steps": 2065, "total_steps": 9742, "loss": 0.4016, "lr": 8.932740902779722e-06, "epoch": 0.42393758981728596, "percentage": 21.2, "elapsed_time": "3:28:16", "remaining_time": "12:54:18", "throughput": 9119.65, "total_tokens": 113966064}417{"current_steps": 2070, "total_steps": 9742, "loss": 0.3685, "lr": 8.92775728651673e-06, "epoch": 0.4249640730856087, "percentage": 21.25, "elapsed_time": "3:28:42", "remaining_time": "12:53:30", "throughput": 9123.33, "total_tokens": 114243408}418{"current_steps": 2075, "total_steps": 9742, "loss": 0.3798, "lr": 8.922763458788753e-06, "epoch": 0.4259905563539314, "percentage": 21.3, "elapsed_time": "3:29:12", "remaining_time": "12:53:01", "throughput": 9121.76, "total_tokens": 114503720}419{"current_steps": 2080, "total_steps": 9742, "loss": 0.3715, "lr": 8.917759432578848e-06, "epoch": 0.4270170396222542, "percentage": 21.35, "elapsed_time": "3:29:42", "remaining_time": "12:52:31", "throughput": 9121.92, "total_tokens": 114780056}420{"current_steps": 2085, "total_steps": 9742, "loss": 0.3723, "lr": 8.912745220896587e-06, "epoch": 0.4280435228905769, "percentage": 21.4, "elapsed_time": "3:30:12", "remaining_time": "12:51:59", "throughput": 9119.61, "total_tokens": 115023352}421{"current_steps": 2090, "total_steps": 9742, "loss": 0.3844, "lr": 8.907720836778022e-06, "epoch": 0.4290700061588996, "percentage": 21.45, "elapsed_time": "3:30:46", "remaining_time": "12:51:40", "throughput": 9113.66, "total_tokens": 115252744}422{"current_steps": 2095, "total_steps": 9742, "loss": 0.3987, "lr": 8.902686293285651e-06, "epoch": 0.43009648942722234, "percentage": 21.5, "elapsed_time": "3:31:17", "remaining_time": "12:51:13", "throughput": 9112.74, "total_tokens": 115525368}423{"current_steps": 2100, "total_steps": 9742, "loss": 0.3405, "lr": 8.897641603508384e-06, "epoch": 0.43112297269554506, "percentage": 21.56, "elapsed_time": "3:31:48", "remaining_time": "12:50:45", "throughput": 9111.4, "total_tokens": 115788216}424{"current_steps": 2105, "total_steps": 9742, "loss": 0.353, "lr": 8.892586780561512e-06, "epoch": 0.4321494559638678, "percentage": 21.61, "elapsed_time": "3:32:14", "remaining_time": "12:50:02", "throughput": 9113.41, "total_tokens": 116057456}425{"current_steps": 2110, "total_steps": 9742, "loss": 0.3604, "lr": 8.887521837586668e-06, "epoch": 0.4331759392321905, "percentage": 21.66, "elapsed_time": "3:32:39", "remaining_time": "12:49:10", "throughput": 9117.81, "total_tokens": 116336008}426{"current_steps": 2115, "total_steps": 9742, "loss": 0.4022, "lr": 8.882446787751794e-06, "epoch": 0.4342024225005132, "percentage": 21.71, "elapsed_time": "3:33:04", "remaining_time": "12:48:21", "throughput": 9122.05, "total_tokens": 116618776}427{"current_steps": 2120, "total_steps": 9742, "loss": 0.3649, "lr": 8.877361644251112e-06, "epoch": 0.435228905768836, "percentage": 21.76, "elapsed_time": "3:33:35", "remaining_time": "12:47:55", "throughput": 9121.2, "total_tokens": 116892696}428{"current_steps": 2125, "total_steps": 9742, "loss": 0.3777, "lr": 8.872266420305084e-06, "epoch": 0.4362553890371587, "percentage": 21.81, "elapsed_time": "3:34:04", "remaining_time": "12:47:19", "throughput": 9121.49, "total_tokens": 117159048}429{"current_steps": 2130, "total_steps": 9742, "loss": 0.3813, "lr": 8.867161129160378e-06, "epoch": 0.43728187230548143, "percentage": 21.86, "elapsed_time": "3:34:24", "remaining_time": "12:46:14", "throughput": 9125.93, "total_tokens": 117403016}430{"current_steps": 2135, "total_steps": 9742, "loss": 0.3711, "lr": 8.862045784089836e-06, "epoch": 0.43830835557380415, "percentage": 21.92, "elapsed_time": "3:34:56", "remaining_time": "12:45:49", "throughput": 9125.33, "total_tokens": 117682400}431{"current_steps": 2140, "total_steps": 9742, "loss": 0.359, "lr": 8.85692039839244e-06, "epoch": 0.4393348388421269, "percentage": 21.97, "elapsed_time": "3:35:26", "remaining_time": "12:45:20", "throughput": 9125.23, "total_tokens": 117959968}432{"current_steps": 2145, "total_steps": 9742, "loss": 0.3455, "lr": 8.851784985393272e-06, "epoch": 0.4403613221104496, "percentage": 22.02, "elapsed_time": "3:36:02", "remaining_time": "12:45:10", "throughput": 9122.61, "total_tokens": 118254560}433{"current_steps": 2150, "total_steps": 9742, "loss": 0.3948, "lr": 8.846639558443487e-06, "epoch": 0.4413878053787723, "percentage": 22.07, "elapsed_time": "3:36:39", "remaining_time": "12:45:04", "throughput": 9116.32, "total_tokens": 118509536}434{"current_steps": 2155, "total_steps": 9742, "loss": 0.3904, "lr": 8.84148413092027e-06, "epoch": 0.44241428864709503, "percentage": 22.12, "elapsed_time": "3:37:07", "remaining_time": "12:44:24", "throughput": 9118.51, "total_tokens": 118790016}435{"current_steps": 2160, "total_steps": 9742, "loss": 0.3628, "lr": 8.836318716226811e-06, "epoch": 0.44344077191541775, "percentage": 22.17, "elapsed_time": "3:37:40", "remaining_time": "12:44:05", "throughput": 9116.65, "total_tokens": 119070304}436{"current_steps": 2165, "total_steps": 9742, "loss": 0.3622, "lr": 8.831143327792264e-06, "epoch": 0.44446725518374053, "percentage": 22.22, "elapsed_time": "3:38:07", "remaining_time": "12:43:22", "throughput": 9116.3, "total_tokens": 119308672}437{"current_steps": 2170, "total_steps": 9742, "loss": 0.3955, "lr": 8.825957979071708e-06, "epoch": 0.44549373845206325, "percentage": 22.27, "elapsed_time": "3:38:34", "remaining_time": "12:42:41", "throughput": 9116.77, "total_tokens": 119561232}438{"current_steps": 2175, "total_steps": 9742, "loss": 0.4025, "lr": 8.820762683546122e-06, "epoch": 0.44652022172038597, "percentage": 22.33, "elapsed_time": "3:39:05", "remaining_time": "12:42:15", "throughput": 9115.97, "total_tokens": 119838176}439{"current_steps": 2180, "total_steps": 9742, "loss": 0.357, "lr": 8.815557454722346e-06, "epoch": 0.4475467049887087, "percentage": 22.38, "elapsed_time": "3:39:40", "remaining_time": "12:42:00", "throughput": 9113.84, "total_tokens": 120124400}440{"current_steps": 2185, "total_steps": 9742, "loss": 0.3646, "lr": 8.810342306133034e-06, "epoch": 0.4485731882570314, "percentage": 22.43, "elapsed_time": "3:40:06", "remaining_time": "12:41:17", "throughput": 9118.49, "total_tokens": 120426984}441{"current_steps": 2190, "total_steps": 9742, "loss": 0.3707, "lr": 8.805117251336647e-06, "epoch": 0.4495996715253541, "percentage": 22.48, "elapsed_time": "3:40:34", "remaining_time": "12:40:38", "throughput": 9120.86, "total_tokens": 120711768}442{"current_steps": 2195, "total_steps": 9742, "loss": 0.3687, "lr": 8.799882303917384e-06, "epoch": 0.45062615479367685, "percentage": 22.53, "elapsed_time": "3:40:59", "remaining_time": "12:39:50", "throughput": 9123.73, "total_tokens": 120978968}443{"current_steps": 2200, "total_steps": 9742, "loss": 0.38, "lr": 8.794637477485174e-06, "epoch": 0.45165263806199957, "percentage": 22.58, "elapsed_time": "3:41:27", "remaining_time": "12:39:12", "throughput": 9125.85, "total_tokens": 121261872}444{"current_steps": 2205, "total_steps": 9742, "loss": 0.3654, "lr": 8.789382785675624e-06, "epoch": 0.45267912133032234, "percentage": 22.63, "elapsed_time": "3:41:56", "remaining_time": "12:38:36", "throughput": 9126.85, "total_tokens": 121535128}445{"current_steps": 2210, "total_steps": 9742, "loss": 0.381, "lr": 8.784118242149993e-06, "epoch": 0.45370560459864506, "percentage": 22.69, "elapsed_time": "3:42:28", "remaining_time": "12:38:12", "throughput": 9126.1, "total_tokens": 121816576}446{"current_steps": 2215, "total_steps": 9742, "loss": 0.3795, "lr": 8.778843860595147e-06, "epoch": 0.4547320878669678, "percentage": 22.74, "elapsed_time": "3:43:00", "remaining_time": "12:37:48", "throughput": 9124.71, "total_tokens": 122091104}447{"current_steps": 2220, "total_steps": 9742, "loss": 0.3559, "lr": 8.773559654723535e-06, "epoch": 0.4557585711352905, "percentage": 22.79, "elapsed_time": "3:43:33", "remaining_time": "12:37:28", "throughput": 9123.18, "total_tokens": 122373528}448{"current_steps": 2225, "total_steps": 9742, "loss": 0.3629, "lr": 8.768265638273146e-06, "epoch": 0.4567850544036132, "percentage": 22.84, "elapsed_time": "3:43:53", "remaining_time": "12:36:24", "throughput": 9130.16, "total_tokens": 122652288}449{"current_steps": 2230, "total_steps": 9742, "loss": 0.3809, "lr": 8.76296182500747e-06, "epoch": 0.45781153767193594, "percentage": 22.89, "elapsed_time": "3:44:27", "remaining_time": "12:36:05", "throughput": 9128.03, "total_tokens": 122928824}450{"current_steps": 2235, "total_steps": 9742, "loss": 0.3571, "lr": 8.757648228715478e-06, "epoch": 0.45883802094025866, "percentage": 22.94, "elapsed_time": "3:44:56", "remaining_time": "12:35:31", "throughput": 9127.17, "total_tokens": 123180960}451{"current_steps": 2240, "total_steps": 9742, "loss": 0.3712, "lr": 8.752324863211561e-06, "epoch": 0.4598645042085814, "percentage": 22.99, "elapsed_time": "3:45:28", "remaining_time": "12:35:08", "throughput": 9125.3, "total_tokens": 123453232}452{"current_steps": 2245, "total_steps": 9742, "loss": 0.3756, "lr": 8.74699174233552e-06, "epoch": 0.4608909874769041, "percentage": 23.04, "elapsed_time": "3:46:02", "remaining_time": "12:34:49", "throughput": 9122.93, "total_tokens": 123726440}453{"current_steps": 2250, "total_steps": 9742, "loss": 0.3762, "lr": 8.741648879952509e-06, "epoch": 0.4619174707452269, "percentage": 23.1, "elapsed_time": "3:46:32", "remaining_time": "12:34:20", "throughput": 9122.9, "total_tokens": 124005544}454{"current_steps": 2255, "total_steps": 9742, "loss": 0.3606, "lr": 8.736296289953015e-06, "epoch": 0.4629439540135496, "percentage": 23.15, "elapsed_time": "3:47:01", "remaining_time": "12:33:47", "throughput": 9125.4, "total_tokens": 124305536}455{"current_steps": 2260, "total_steps": 9742, "loss": 0.3477, "lr": 8.730933986252814e-06, "epoch": 0.4639704372818723, "percentage": 23.2, "elapsed_time": "3:47:33", "remaining_time": "12:33:20", "throughput": 9127.33, "total_tokens": 124618000}456{"current_steps": 2265, "total_steps": 9742, "loss": 0.3798, "lr": 8.725561982792933e-06, "epoch": 0.46499692055019504, "percentage": 23.25, "elapsed_time": "3:48:03", "remaining_time": "12:32:51", "throughput": 9127.39, "total_tokens": 124896184}457{"current_steps": 2270, "total_steps": 9742, "loss": 0.3994, "lr": 8.720180293539619e-06, "epoch": 0.46602340381851776, "percentage": 23.3, "elapsed_time": "3:48:32", "remaining_time": "12:32:14", "throughput": 9129.75, "total_tokens": 125187200}458{"current_steps": 2275, "total_steps": 9742, "loss": 0.3809, "lr": 8.7147889324843e-06, "epoch": 0.4670498870868405, "percentage": 23.35, "elapsed_time": "3:49:02", "remaining_time": "12:31:44", "throughput": 9130.16, "total_tokens": 125467808}459{"current_steps": 2280, "total_steps": 9742, "loss": 0.3621, "lr": 8.709387913643545e-06, "epoch": 0.4680763703551632, "percentage": 23.4, "elapsed_time": "3:49:31", "remaining_time": "12:31:11", "throughput": 9128.34, "total_tokens": 125710512}460{"current_steps": 2285, "total_steps": 9742, "loss": 0.3527, "lr": 8.703977251059038e-06, "epoch": 0.4691028536234859, "percentage": 23.46, "elapsed_time": "3:50:04", "remaining_time": "12:30:50", "throughput": 9127.17, "total_tokens": 125997480}461{"current_steps": 2290, "total_steps": 9742, "loss": 0.3654, "lr": 8.698556958797533e-06, "epoch": 0.4701293368918087, "percentage": 23.51, "elapsed_time": "3:50:39", "remaining_time": "12:30:34", "throughput": 9124.42, "total_tokens": 126274144}462{"current_steps": 2295, "total_steps": 9742, "loss": 0.3624, "lr": 8.693127050950814e-06, "epoch": 0.4711558201601314, "percentage": 23.56, "elapsed_time": "3:51:06", "remaining_time": "12:29:56", "throughput": 9126.37, "total_tokens": 126553464}463{"current_steps": 2300, "total_steps": 9742, "loss": 0.4061, "lr": 8.687687541635673e-06, "epoch": 0.47218230342845413, "percentage": 23.61, "elapsed_time": "3:51:42", "remaining_time": "12:29:43", "throughput": 9123.72, "total_tokens": 126842600}464{"current_steps": 2305, "total_steps": 9742, "loss": 0.3861, "lr": 8.682238444993857e-06, "epoch": 0.47320878669677685, "percentage": 23.66, "elapsed_time": "3:52:15", "remaining_time": "12:29:22", "throughput": 9120.92, "total_tokens": 127105336}465{"current_steps": 2310, "total_steps": 9742, "loss": 0.3768, "lr": 8.676779775192042e-06, "epoch": 0.47423526996509957, "percentage": 23.71, "elapsed_time": "3:52:48", "remaining_time": "12:29:01", "throughput": 9119.98, "total_tokens": 127394688}466{"current_steps": 2315, "total_steps": 9742, "loss": 0.3808, "lr": 8.671311546421787e-06, "epoch": 0.4752617532334223, "percentage": 23.76, "elapsed_time": "3:53:20", "remaining_time": "12:28:37", "throughput": 9118.42, "total_tokens": 127664672}467{"current_steps": 2320, "total_steps": 9742, "loss": 0.385, "lr": 8.665833772899512e-06, "epoch": 0.476288236501745, "percentage": 23.81, "elapsed_time": "3:53:50", "remaining_time": "12:28:04", "throughput": 9118.39, "total_tokens": 127931632}468{"current_steps": 2325, "total_steps": 9742, "loss": 0.3948, "lr": 8.660346468866445e-06, "epoch": 0.47731471977006773, "percentage": 23.87, "elapsed_time": "3:54:20", "remaining_time": "12:27:35", "throughput": 9119.34, "total_tokens": 128224472}469{"current_steps": 2330, "total_steps": 9742, "loss": 0.3749, "lr": 8.654849648588592e-06, "epoch": 0.47834120303839045, "percentage": 23.92, "elapsed_time": "3:54:49", "remaining_time": "12:27:01", "throughput": 9120.95, "total_tokens": 128512112}470{"current_steps": 2335, "total_steps": 9742, "loss": 0.3892, "lr": 8.6493433263567e-06, "epoch": 0.4793676863067132, "percentage": 23.97, "elapsed_time": "3:55:22", "remaining_time": "12:26:40", "throughput": 9120.71, "total_tokens": 128810592}471{"current_steps": 2340, "total_steps": 9742, "loss": 0.3661, "lr": 8.643827516486221e-06, "epoch": 0.48039416957503595, "percentage": 24.02, "elapsed_time": "3:55:52", "remaining_time": "12:26:06", "throughput": 9120.01, "total_tokens": 129066336}472{"current_steps": 2345, "total_steps": 9742, "loss": 0.3741, "lr": 8.638302233317272e-06, "epoch": 0.48142065284335867, "percentage": 24.07, "elapsed_time": "3:56:22", "remaining_time": "12:25:35", "throughput": 9120.28, "total_tokens": 129345000}473{"current_steps": 2350, "total_steps": 9742, "loss": 0.3649, "lr": 8.632767491214599e-06, "epoch": 0.4824471361116814, "percentage": 24.12, "elapsed_time": "3:56:43", "remaining_time": "12:24:37", "throughput": 9124.29, "total_tokens": 129595312}474{"current_steps": 2355, "total_steps": 9742, "loss": 0.3637, "lr": 8.627223304567537e-06, "epoch": 0.4834736193800041, "percentage": 24.17, "elapsed_time": "3:57:07", "remaining_time": "12:23:48", "throughput": 9128.47, "total_tokens": 129876520}475{"current_steps": 2360, "total_steps": 9742, "loss": 0.3589, "lr": 8.621669687789983e-06, "epoch": 0.4845001026483268, "percentage": 24.23, "elapsed_time": "3:57:36", "remaining_time": "12:23:15", "throughput": 9129.24, "total_tokens": 130154440}476{"current_steps": 2365, "total_steps": 9742, "loss": 0.334, "lr": 8.616106655320342e-06, "epoch": 0.48552658591664954, "percentage": 24.28, "elapsed_time": "3:58:00", "remaining_time": "12:22:23", "throughput": 9132.08, "total_tokens": 130407048}477{"current_steps": 2370, "total_steps": 9742, "loss": 0.3797, "lr": 8.6105342216215e-06, "epoch": 0.48655306918497226, "percentage": 24.33, "elapsed_time": "3:58:32", "remaining_time": "12:21:59", "throughput": 9130.04, "total_tokens": 130672792}478{"current_steps": 2375, "total_steps": 9742, "loss": 0.3768, "lr": 8.604952401180788e-06, "epoch": 0.487579552453295, "percentage": 24.38, "elapsed_time": "3:59:02", "remaining_time": "12:21:28", "throughput": 9130.32, "total_tokens": 130948976}479{"current_steps": 2380, "total_steps": 9742, "loss": 0.3913, "lr": 8.599361208509938e-06, "epoch": 0.48860603572161776, "percentage": 24.43, "elapsed_time": "3:59:32", "remaining_time": "12:20:56", "throughput": 9129.84, "total_tokens": 131214392}480{"current_steps": 2385, "total_steps": 9742, "loss": 0.3703, "lr": 8.593760658145048e-06, "epoch": 0.4896325189899405, "percentage": 24.48, "elapsed_time": "4:00:03", "remaining_time": "12:20:30", "throughput": 9130.31, "total_tokens": 131508128}481{"current_steps": 2390, "total_steps": 9742, "loss": 0.3944, "lr": 8.588150764646549e-06, "epoch": 0.4906590022582632, "percentage": 24.53, "elapsed_time": "4:00:37", "remaining_time": "12:20:10", "throughput": 9128.45, "total_tokens": 131788912}482{"current_steps": 2395, "total_steps": 9742, "loss": 0.3636, "lr": 8.582531542599153e-06, "epoch": 0.4916854855265859, "percentage": 24.58, "elapsed_time": "4:01:07", "remaining_time": "12:19:41", "throughput": 9127.59, "total_tokens": 132055608}483{"current_steps": 2400, "total_steps": 9742, "loss": 0.3891, "lr": 8.576903006611835e-06, "epoch": 0.49271196879490864, "percentage": 24.64, "elapsed_time": "4:01:41", "remaining_time": "12:19:22", "throughput": 9124.77, "total_tokens": 132323680}484{"current_steps": 2405, "total_steps": 9742, "loss": 0.3554, "lr": 8.571265171317775e-06, "epoch": 0.49373845206323136, "percentage": 24.69, "elapsed_time": "4:02:04", "remaining_time": "12:18:31", "throughput": 9126.3, "total_tokens": 132559344}485{"current_steps": 2410, "total_steps": 9742, "loss": 0.3886, "lr": 8.56561805137434e-06, "epoch": 0.4947649353315541, "percentage": 24.74, "elapsed_time": "4:02:35", "remaining_time": "12:18:01", "throughput": 9126.46, "total_tokens": 132836808}486{"current_steps": 2415, "total_steps": 9742, "loss": 0.3772, "lr": 8.559961661463025e-06, "epoch": 0.4957914185998768, "percentage": 24.79, "elapsed_time": "4:03:06", "remaining_time": "12:17:36", "throughput": 9123.56, "total_tokens": 133085288}487{"current_steps": 2420, "total_steps": 9742, "loss": 0.3822, "lr": 8.554296016289434e-06, "epoch": 0.4968179018681996, "percentage": 24.84, "elapsed_time": "4:03:33", "remaining_time": "12:16:54", "throughput": 9125.68, "total_tokens": 133355752}488{"current_steps": 2425, "total_steps": 9742, "loss": 0.3701, "lr": 8.548621130583225e-06, "epoch": 0.4978443851365223, "percentage": 24.89, "elapsed_time": "4:04:00", "remaining_time": "12:16:14", "throughput": 9128.46, "total_tokens": 133642344}489{"current_steps": 2430, "total_steps": 9742, "loss": 0.3817, "lr": 8.542937019098086e-06, "epoch": 0.498870868404845, "percentage": 24.94, "elapsed_time": "4:04:34", "remaining_time": "12:15:55", "throughput": 9126.58, "total_tokens": 133924528}490{"current_steps": 2435, "total_steps": 9742, "loss": 0.3482, "lr": 8.537243696611688e-06, "epoch": 0.49989735167316773, "percentage": 24.99, "elapsed_time": "4:04:57", "remaining_time": "12:15:04", "throughput": 9130.81, "total_tokens": 134200648}491{"current_steps": 2440, "total_steps": 9742, "loss": 0.3832, "lr": 8.531541177925649e-06, "epoch": 0.5009238349414905, "percentage": 25.05, "elapsed_time": "4:05:23", "remaining_time": "12:14:22", "throughput": 9132.96, "total_tokens": 134469528}492{"current_steps": 2445, "total_steps": 9742, "loss": 0.3682, "lr": 8.525829477865494e-06, "epoch": 0.5019503182098132, "percentage": 25.1, "elapsed_time": "4:05:55", "remaining_time": "12:13:58", "throughput": 9131.95, "total_tokens": 134750304}493{"current_steps": 2450, "total_steps": 9742, "loss": 0.3356, "lr": 8.520108611280622e-06, "epoch": 0.502976801478136, "percentage": 25.15, "elapsed_time": "4:06:24", "remaining_time": "12:13:22", "throughput": 9133.22, "total_tokens": 135027080}494{"current_steps": 2455, "total_steps": 9742, "loss": 0.3324, "lr": 8.514378593044259e-06, "epoch": 0.5040032847464586, "percentage": 25.2, "elapsed_time": "4:06:57", "remaining_time": "12:13:01", "throughput": 9131.69, "total_tokens": 135307712}495{"current_steps": 2460, "total_steps": 9742, "loss": 0.3875, "lr": 8.508639438053426e-06, "epoch": 0.5050297680147814, "percentage": 25.25, "elapsed_time": "4:07:23", "remaining_time": "12:12:19", "throughput": 9134.63, "total_tokens": 135592288}496{"current_steps": 2465, "total_steps": 9742, "loss": 0.372, "lr": 8.5028911612289e-06, "epoch": 0.506056251283104, "percentage": 25.3, "elapsed_time": "4:07:49", "remaining_time": "12:11:36", "throughput": 9137.93, "total_tokens": 135875280}497{"current_steps": 2470, "total_steps": 9742, "loss": 0.3828, "lr": 8.497133777515163e-06, "epoch": 0.5070827345514268, "percentage": 25.35, "elapsed_time": "4:08:17", "remaining_time": "12:10:59", "throughput": 9139.75, "total_tokens": 136158120}498{"current_steps": 2475, "total_steps": 9742, "loss": 0.3631, "lr": 8.491367301880389e-06, "epoch": 0.5081092178197495, "percentage": 25.41, "elapsed_time": "4:08:48", "remaining_time": "12:10:33", "throughput": 9138.55, "total_tokens": 136426480}499{"current_steps": 2480, "total_steps": 9742, "loss": 0.3849, "lr": 8.485591749316376e-06, "epoch": 0.5091357010880723, "percentage": 25.46, "elapsed_time": "4:09:20", "remaining_time": "12:10:06", "throughput": 9138.59, "total_tokens": 136715560}500{"current_steps": 2485, "total_steps": 9742, "loss": 0.3604, "lr": 8.47980713483853e-06, "epoch": 0.510162184356395, "percentage": 25.51, "elapsed_time": "4:09:44", "remaining_time": "12:09:18", "throughput": 9142.71, "total_tokens": 136995336}501{"current_steps": 2490, "total_steps": 9742, "loss": 0.3464, "lr": 8.474013473485808e-06, "epoch": 0.5111886676247177, "percentage": 25.56, "elapsed_time": "4:10:13", "remaining_time": "12:08:46", "throughput": 9143.87, "total_tokens": 137281832}502{"current_steps": 2495, "total_steps": 9742, "loss": 0.375, "lr": 8.46821078032069e-06, "epoch": 0.5122151508930405, "percentage": 25.61, "elapsed_time": "4:10:39", "remaining_time": "12:08:02", "throughput": 9147.34, "total_tokens": 137567472}503{"current_steps": 2500, "total_steps": 9742, "loss": 0.3527, "lr": 8.462399070429144e-06, "epoch": 0.5132416341613631, "percentage": 25.66, "elapsed_time": "4:11:10", "remaining_time": "12:07:36", "throughput": 9148.08, "total_tokens": 137865800}504{"current_steps": 2505, "total_steps": 9742, "loss": 0.3753, "lr": 8.456578358920568e-06, "epoch": 0.5142681174296859, "percentage": 25.71, "elapsed_time": "4:11:45", "remaining_time": "12:07:19", "throughput": 9145.65, "total_tokens": 138148824}505{"current_steps": 2510, "total_steps": 9742, "loss": 0.3539, "lr": 8.450748660927772e-06, "epoch": 0.5152946006980086, "percentage": 25.76, "elapsed_time": "4:12:15", "remaining_time": "12:06:50", "throughput": 9144.79, "total_tokens": 138414544}506{"current_steps": 2515, "total_steps": 9742, "loss": 0.3681, "lr": 8.444909991606927e-06, "epoch": 0.5163210839663314, "percentage": 25.82, "elapsed_time": "4:12:46", "remaining_time": "12:06:20", "throughput": 9145.3, "total_tokens": 138698296}507{"current_steps": 2520, "total_steps": 9742, "loss": 0.3897, "lr": 8.439062366137523e-06, "epoch": 0.517347567234654, "percentage": 25.87, "elapsed_time": "4:13:19", "remaining_time": "12:05:58", "throughput": 9142.66, "total_tokens": 138960712}508{"current_steps": 2525, "total_steps": 9742, "loss": 0.3745, "lr": 8.433205799722342e-06, "epoch": 0.5183740505029768, "percentage": 25.92, "elapsed_time": "4:13:50", "remaining_time": "12:05:33", "throughput": 9141.69, "total_tokens": 139236888}509{"current_steps": 2530, "total_steps": 9742, "loss": 0.3994, "lr": 8.427340307587403e-06, "epoch": 0.5194005337712996, "percentage": 25.97, "elapsed_time": "4:14:23", "remaining_time": "12:05:10", "throughput": 9139.68, "total_tokens": 139504976}510{"current_steps": 2535, "total_steps": 9742, "loss": 0.3476, "lr": 8.421465904981939e-06, "epoch": 0.5204270170396222, "percentage": 26.02, "elapsed_time": "4:14:55", "remaining_time": "12:04:46", "throughput": 9139.62, "total_tokens": 139798336}511{"current_steps": 2540, "total_steps": 9742, "loss": 0.3665, "lr": 8.415582607178342e-06, "epoch": 0.521453500307945, "percentage": 26.07, "elapsed_time": "4:15:22", "remaining_time": "12:04:07", "throughput": 9141.89, "total_tokens": 140081072}512{"current_steps": 2545, "total_steps": 9742, "loss": 0.3726, "lr": 8.409690429472128e-06, "epoch": 0.5224799835762677, "percentage": 26.12, "elapsed_time": "4:15:50", "remaining_time": "12:03:29", "throughput": 9144.67, "total_tokens": 140376296}513{"current_steps": 2550, "total_steps": 9742, "loss": 0.3594, "lr": 8.403789387181908e-06, "epoch": 0.5235064668445905, "percentage": 26.18, "elapsed_time": "4:16:26", "remaining_time": "12:03:16", "throughput": 9141.38, "total_tokens": 140654592}514{"current_steps": 2555, "total_steps": 9742, "loss": 0.3702, "lr": 8.397879495649332e-06, "epoch": 0.5245329501129131, "percentage": 26.23, "elapsed_time": "4:16:52", "remaining_time": "12:02:34", "throughput": 9143.28, "total_tokens": 140922320}515{"current_steps": 2560, "total_steps": 9742, "loss": 0.3738, "lr": 8.39196077023906e-06, "epoch": 0.5255594333812359, "percentage": 26.28, "elapsed_time": "4:17:20", "remaining_time": "12:01:57", "throughput": 9145.01, "total_tokens": 141201232}516{"current_steps": 2565, "total_steps": 9742, "loss": 0.3525, "lr": 8.386033226338719e-06, "epoch": 0.5265859166495586, "percentage": 26.33, "elapsed_time": "4:17:48", "remaining_time": "12:01:22", "throughput": 9144.89, "total_tokens": 141461640}517{"current_steps": 2570, "total_steps": 9742, "loss": 0.3884, "lr": 8.380096879358857e-06, "epoch": 0.5276123999178813, "percentage": 26.38, "elapsed_time": "4:18:20", "remaining_time": "12:00:57", "throughput": 9144.37, "total_tokens": 141744872}518{"current_steps": 2575, "total_steps": 9742, "loss": 0.3963, "lr": 8.374151744732912e-06, "epoch": 0.5286388831862041, "percentage": 26.43, "elapsed_time": "4:18:53", "remaining_time": "12:00:34", "throughput": 9143.76, "total_tokens": 142034168}519{"current_steps": 2580, "total_steps": 9742, "loss": 0.3781, "lr": 8.368197837917171e-06, "epoch": 0.5296653664545268, "percentage": 26.48, "elapsed_time": "4:19:27", "remaining_time": "12:00:14", "throughput": 9142.52, "total_tokens": 142325328}520{"current_steps": 2585, "total_steps": 9742, "loss": 0.3456, "lr": 8.362235174390725e-06, "epoch": 0.5306918497228496, "percentage": 26.53, "elapsed_time": "4:19:55", "remaining_time": "11:59:37", "throughput": 9143.72, "total_tokens": 142596872}521{"current_steps": 2590, "total_steps": 9742, "loss": 0.3935, "lr": 8.356263769655429e-06, "epoch": 0.5317183329911722, "percentage": 26.59, "elapsed_time": "4:20:29", "remaining_time": "11:59:17", "throughput": 9142.7, "total_tokens": 142891336}522{"current_steps": 2595, "total_steps": 9742, "loss": 0.3731, "lr": 8.350283639235864e-06, "epoch": 0.532744816259495, "percentage": 26.64, "elapsed_time": "4:20:57", "remaining_time": "11:58:43", "throughput": 9143.05, "total_tokens": 143157912}523{"current_steps": 2600, "total_steps": 9742, "loss": 0.3651, "lr": 8.3442947986793e-06, "epoch": 0.5337712995278177, "percentage": 26.69, "elapsed_time": "4:21:31", "remaining_time": "11:58:22", "throughput": 9141.11, "total_tokens": 143435704}524{"current_steps": 2605, "total_steps": 9742, "loss": 0.3708, "lr": 8.338297263555646e-06, "epoch": 0.5347977827961404, "percentage": 26.74, "elapsed_time": "4:22:02", "remaining_time": "11:57:56", "throughput": 9139.58, "total_tokens": 143700264}525{"current_steps": 2610, "total_steps": 9742, "loss": 0.3626, "lr": 8.332291049457422e-06, "epoch": 0.5358242660644631, "percentage": 26.79, "elapsed_time": "4:22:35", "remaining_time": "11:57:34", "throughput": 9140.02, "total_tokens": 144009544}526{"current_steps": 2615, "total_steps": 9742, "loss": 0.394, "lr": 8.326276171999706e-06, "epoch": 0.5368507493327859, "percentage": 26.84, "elapsed_time": "4:23:07", "remaining_time": "11:57:08", "throughput": 9139.38, "total_tokens": 144289064}527{"current_steps": 2620, "total_steps": 9742, "loss": 0.3789, "lr": 8.320252646820103e-06, "epoch": 0.5378772326011086, "percentage": 26.89, "elapsed_time": "4:23:34", "remaining_time": "11:56:28", "throughput": 9141.77, "total_tokens": 144571784}528{"current_steps": 2625, "total_steps": 9742, "loss": 0.4146, "lr": 8.314220489578693e-06, "epoch": 0.5389037158694313, "percentage": 26.95, "elapsed_time": "4:24:00", "remaining_time": "11:55:47", "throughput": 9144.17, "total_tokens": 144847928}529{"current_steps": 2630, "total_steps": 9742, "loss": 0.3658, "lr": 8.308179715958011e-06, "epoch": 0.5399301991377541, "percentage": 27.0, "elapsed_time": "4:24:30", "remaining_time": "11:55:17", "throughput": 9143.46, "total_tokens": 145113360}530{"current_steps": 2635, "total_steps": 9742, "loss": 0.3921, "lr": 8.302130341662984e-06, "epoch": 0.5409566824060767, "percentage": 27.05, "elapsed_time": "4:25:03", "remaining_time": "11:54:53", "throughput": 9142.61, "total_tokens": 145396984}531{"current_steps": 2640, "total_steps": 9742, "loss": 0.3454, "lr": 8.296072382420898e-06, "epoch": 0.5419831656743995, "percentage": 27.1, "elapsed_time": "4:25:39", "remaining_time": "11:54:39", "throughput": 9138.42, "total_tokens": 145662496}532{"current_steps": 2645, "total_steps": 9742, "loss": 0.3666, "lr": 8.290005853981366e-06, "epoch": 0.5430096489427222, "percentage": 27.15, "elapsed_time": "4:26:13", "remaining_time": "11:54:18", "throughput": 9138.09, "total_tokens": 145963744}533{"current_steps": 2650, "total_steps": 9742, "loss": 0.3788, "lr": 8.283930772116269e-06, "epoch": 0.544036132211045, "percentage": 27.2, "elapsed_time": "4:26:41", "remaining_time": "11:53:44", "throughput": 9138.79, "total_tokens": 146238456}534{"current_steps": 2655, "total_steps": 9742, "loss": 0.3702, "lr": 8.277847152619736e-06, "epoch": 0.5450626154793677, "percentage": 27.25, "elapsed_time": "4:27:10", "remaining_time": "11:53:10", "throughput": 9141.09, "total_tokens": 146538000}535{"current_steps": 2660, "total_steps": 9742, "loss": 0.389, "lr": 8.271755011308084e-06, "epoch": 0.5460890987476904, "percentage": 27.3, "elapsed_time": "4:27:42", "remaining_time": "11:52:44", "throughput": 9139.99, "total_tokens": 146809856}536{"current_steps": 2665, "total_steps": 9742, "loss": 0.3613, "lr": 8.26565436401979e-06, "epoch": 0.5471155820160132, "percentage": 27.36, "elapsed_time": "4:28:16", "remaining_time": "11:52:24", "throughput": 9136.62, "total_tokens": 147068064}537{"current_steps": 2670, "total_steps": 9742, "loss": 0.3793, "lr": 8.259545226615445e-06, "epoch": 0.5481420652843358, "percentage": 27.41, "elapsed_time": "4:28:46", "remaining_time": "11:51:55", "throughput": 9136.56, "total_tokens": 147344104}538{"current_steps": 2675, "total_steps": 9742, "loss": 0.343, "lr": 8.253427614977707e-06, "epoch": 0.5491685485526586, "percentage": 27.46, "elapsed_time": "4:29:18", "remaining_time": "11:51:28", "throughput": 9134.98, "total_tokens": 147607984}539{"current_steps": 2680, "total_steps": 9742, "loss": 0.3781, "lr": 8.247301545011274e-06, "epoch": 0.5501950318209813, "percentage": 27.51, "elapsed_time": "4:29:45", "remaining_time": "11:50:48", "throughput": 9136.48, "total_tokens": 147874032}540{"current_steps": 2685, "total_steps": 9742, "loss": 0.3872, "lr": 8.241167032642827e-06, "epoch": 0.5512215150893041, "percentage": 27.56, "elapsed_time": "4:30:14", "remaining_time": "11:50:16", "throughput": 9136.75, "total_tokens": 148148912}541{"current_steps": 2690, "total_steps": 9742, "loss": 0.3953, "lr": 8.235024093821002e-06, "epoch": 0.5522479983576267, "percentage": 27.61, "elapsed_time": "4:30:44", "remaining_time": "11:49:45", "throughput": 9136.43, "total_tokens": 148414504}542{"current_steps": 2695, "total_steps": 9742, "loss": 0.3452, "lr": 8.228872744516336e-06, "epoch": 0.5532744816259495, "percentage": 27.66, "elapsed_time": "4:31:10", "remaining_time": "11:49:03", "throughput": 9137.51, "total_tokens": 148668008}543{"current_steps": 2700, "total_steps": 9742, "loss": 0.3722, "lr": 8.222713000721237e-06, "epoch": 0.5543009648942723, "percentage": 27.72, "elapsed_time": "4:31:44", "remaining_time": "11:48:45", "throughput": 9135.51, "total_tokens": 148951912}544{"current_steps": 2705, "total_steps": 9742, "loss": 0.3586, "lr": 8.216544878449932e-06, "epoch": 0.5553274481625949, "percentage": 27.77, "elapsed_time": "4:32:11", "remaining_time": "11:48:07", "throughput": 9136.56, "total_tokens": 149217808}545{"current_steps": 2710, "total_steps": 9742, "loss": 0.3978, "lr": 8.210368393738437e-06, "epoch": 0.5563539314309177, "percentage": 27.82, "elapsed_time": "4:32:40", "remaining_time": "11:47:33", "throughput": 9136.73, "total_tokens": 149482264}546{"current_steps": 2715, "total_steps": 9742, "loss": 0.3847, "lr": 8.204183562644504e-06, "epoch": 0.5573804146992404, "percentage": 27.87, "elapsed_time": "4:33:11", "remaining_time": "11:47:05", "throughput": 9137.12, "total_tokens": 149772480}547{"current_steps": 2720, "total_steps": 9742, "loss": 0.3505, "lr": 8.197990401247582e-06, "epoch": 0.5584068979675632, "percentage": 27.92, "elapsed_time": "4:33:36", "remaining_time": "11:46:21", "throughput": 9140.1, "total_tokens": 150050176}548{"current_steps": 2725, "total_steps": 9742, "loss": 0.3416, "lr": 8.191788925648784e-06, "epoch": 0.5594333812358858, "percentage": 27.97, "elapsed_time": "4:34:01", "remaining_time": "11:45:36", "throughput": 9143.02, "total_tokens": 150321896}549{"current_steps": 2730, "total_steps": 9742, "loss": 0.3705, "lr": 8.185579151970836e-06, "epoch": 0.5604598645042086, "percentage": 28.02, "elapsed_time": "4:34:31", "remaining_time": "11:45:07", "throughput": 9142.65, "total_tokens": 150593224}550{"current_steps": 2735, "total_steps": 9742, "loss": 0.3486, "lr": 8.179361096358033e-06, "epoch": 0.5614863477725313, "percentage": 28.07, "elapsed_time": "4:35:06", "remaining_time": "11:44:49", "throughput": 9138.12, "total_tokens": 150838760}551{"current_steps": 2740, "total_steps": 9742, "loss": 0.3479, "lr": 8.173134774976208e-06, "epoch": 0.562512831040854, "percentage": 28.13, "elapsed_time": "4:35:39", "remaining_time": "11:44:27", "throughput": 9135.84, "total_tokens": 151106128}552{"current_steps": 2745, "total_steps": 9742, "loss": 0.3683, "lr": 8.16690020401268e-06, "epoch": 0.5635393143091768, "percentage": 28.18, "elapsed_time": "4:36:11", "remaining_time": "11:43:59", "throughput": 9137.33, "total_tokens": 151415256}553{"current_steps": 2750, "total_steps": 9742, "loss": 0.3767, "lr": 8.160657399676215e-06, "epoch": 0.5645657975774995, "percentage": 28.23, "elapsed_time": "4:36:43", "remaining_time": "11:43:35", "throughput": 9136.82, "total_tokens": 151705424}554{"current_steps": 2755, "total_steps": 9742, "loss": 0.3518, "lr": 8.154406378196986e-06, "epoch": 0.5655922808458222, "percentage": 28.28, "elapsed_time": "4:37:12", "remaining_time": "11:43:00", "throughput": 9137.07, "total_tokens": 151968232}555{"current_steps": 2760, "total_steps": 9742, "loss": 0.3771, "lr": 8.148147155826531e-06, "epoch": 0.5666187641141449, "percentage": 28.33, "elapsed_time": "4:37:40", "remaining_time": "11:42:26", "throughput": 9140.01, "total_tokens": 152277136}556{"current_steps": 2765, "total_steps": 9742, "loss": 0.3716, "lr": 8.141879748837703e-06, "epoch": 0.5676452473824677, "percentage": 28.38, "elapsed_time": "4:38:12", "remaining_time": "11:42:00", "throughput": 9138.5, "total_tokens": 152543408}557{"current_steps": 2770, "total_steps": 9742, "loss": 0.3594, "lr": 8.135604173524638e-06, "epoch": 0.5686717306507904, "percentage": 28.43, "elapsed_time": "4:38:44", "remaining_time": "11:41:36", "throughput": 9135.77, "total_tokens": 152794784}558{"current_steps": 2775, "total_steps": 9742, "loss": 0.3552, "lr": 8.129320446202708e-06, "epoch": 0.5696982139191131, "percentage": 28.48, "elapsed_time": "4:39:12", "remaining_time": "11:40:58", "throughput": 9137.46, "total_tokens": 153073752}559{"current_steps": 2780, "total_steps": 9742, "loss": 0.3681, "lr": 8.123028583208476e-06, "epoch": 0.5707246971874358, "percentage": 28.54, "elapsed_time": "4:39:48", "remaining_time": "11:40:44", "throughput": 9135.54, "total_tokens": 153376088}560{"current_steps": 2785, "total_steps": 9742, "loss": 0.3669, "lr": 8.11672860089966e-06, "epoch": 0.5717511804557586, "percentage": 28.59, "elapsed_time": "4:40:15", "remaining_time": "11:40:06", "throughput": 9138.95, "total_tokens": 153678088}561{"current_steps": 2790, "total_steps": 9742, "loss": 0.3998, "lr": 8.110420515655082e-06, "epoch": 0.5727776637240813, "percentage": 28.64, "elapsed_time": "4:40:49", "remaining_time": "11:39:43", "throughput": 9137.49, "total_tokens": 153958112}562{"current_steps": 2795, "total_steps": 9742, "loss": 0.3629, "lr": 8.104104343874636e-06, "epoch": 0.573804146992404, "percentage": 28.69, "elapsed_time": "4:41:25", "remaining_time": "11:39:28", "throughput": 9134.36, "total_tokens": 154237184}563{"current_steps": 2800, "total_steps": 9742, "loss": 0.3554, "lr": 8.097780101979236e-06, "epoch": 0.5748306302607268, "percentage": 28.74, "elapsed_time": "4:41:56", "remaining_time": "11:39:00", "throughput": 9134.88, "total_tokens": 154530152}564{"current_steps": 2805, "total_steps": 9742, "loss": 0.3558, "lr": 8.091447806410777e-06, "epoch": 0.5758571135290494, "percentage": 28.79, "elapsed_time": "4:42:23", "remaining_time": "11:38:23", "throughput": 9136.76, "total_tokens": 154810816}565{"current_steps": 2810, "total_steps": 9742, "loss": 0.3856, "lr": 8.085107473632092e-06, "epoch": 0.5768835967973722, "percentage": 28.84, "elapsed_time": "4:42:53", "remaining_time": "11:37:51", "throughput": 9135.37, "total_tokens": 155055920}566{"current_steps": 2815, "total_steps": 9742, "loss": 0.391, "lr": 8.078759120126911e-06, "epoch": 0.5779100800656949, "percentage": 28.9, "elapsed_time": "4:43:26", "remaining_time": "11:37:28", "throughput": 9134.6, "total_tokens": 155345048}567{"current_steps": 2820, "total_steps": 9742, "loss": 0.3549, "lr": 8.072402762399815e-06, "epoch": 0.5789365633340177, "percentage": 28.95, "elapsed_time": "4:43:53", "remaining_time": "11:36:50", "throughput": 9135.81, "total_tokens": 155613152}568{"current_steps": 2825, "total_steps": 9742, "loss": 0.3827, "lr": 8.066038416976194e-06, "epoch": 0.5799630466023403, "percentage": 29.0, "elapsed_time": "4:44:25", "remaining_time": "11:36:23", "throughput": 9133.65, "total_tokens": 155866832}569{"current_steps": 2830, "total_steps": 9742, "loss": 0.3552, "lr": 8.059666100402209e-06, "epoch": 0.5809895298706631, "percentage": 29.05, "elapsed_time": "4:44:55", "remaining_time": "11:35:54", "throughput": 9133.84, "total_tokens": 156150944}570{"current_steps": 2835, "total_steps": 9742, "loss": 0.3817, "lr": 8.053285829244734e-06, "epoch": 0.5820160131389859, "percentage": 29.1, "elapsed_time": "4:45:27", "remaining_time": "11:35:28", "throughput": 9131.81, "total_tokens": 156405608}571{"current_steps": 2840, "total_steps": 9742, "loss": 0.3918, "lr": 8.046897620091336e-06, "epoch": 0.5830424964073085, "percentage": 29.15, "elapsed_time": "4:45:56", "remaining_time": "11:34:56", "throughput": 9131.82, "total_tokens": 156673952}572{"current_steps": 2845, "total_steps": 9742, "loss": 0.3985, "lr": 8.040501489550212e-06, "epoch": 0.5840689796756313, "percentage": 29.2, "elapsed_time": "4:46:26", "remaining_time": "11:34:24", "throughput": 9131.39, "total_tokens": 156937592}573{"current_steps": 2850, "total_steps": 9742, "loss": 0.3696, "lr": 8.034097454250156e-06, "epoch": 0.585095462943954, "percentage": 29.25, "elapsed_time": "4:46:55", "remaining_time": "11:33:50", "throughput": 9132.67, "total_tokens": 157220168}574{"current_steps": 2855, "total_steps": 9742, "loss": 0.3656, "lr": 8.027685530840512e-06, "epoch": 0.5861219462122768, "percentage": 29.31, "elapsed_time": "4:47:25", "remaining_time": "11:33:20", "throughput": 9133.04, "total_tokens": 157501704}575{"current_steps": 2860, "total_steps": 9742, "loss": 0.391, "lr": 8.02126573599113e-06, "epoch": 0.5871484294805994, "percentage": 29.36, "elapsed_time": "4:47:56", "remaining_time": "11:32:53", "throughput": 9131.06, "total_tokens": 157755824}576{"current_steps": 2865, "total_steps": 9742, "loss": 0.3419, "lr": 8.014838086392326e-06, "epoch": 0.5881749127489222, "percentage": 29.41, "elapsed_time": "4:48:27", "remaining_time": "11:32:23", "throughput": 9130.57, "total_tokens": 158025424}577{"current_steps": 2870, "total_steps": 9742, "loss": 0.3772, "lr": 8.008402598754842e-06, "epoch": 0.589201396017245, "percentage": 29.46, "elapsed_time": "4:48:50", "remaining_time": "11:31:36", "throughput": 9133.43, "total_tokens": 158284968}578{"current_steps": 2875, "total_steps": 9742, "loss": 0.3521, "lr": 8.001959289809787e-06, "epoch": 0.5902278792855676, "percentage": 29.51, "elapsed_time": "4:49:22", "remaining_time": "11:31:11", "throughput": 9130.57, "total_tokens": 158532008}579{"current_steps": 2880, "total_steps": 9742, "loss": 0.3464, "lr": 7.995508176308609e-06, "epoch": 0.5912543625538904, "percentage": 29.56, "elapsed_time": "4:49:51", "remaining_time": "11:30:38", "throughput": 9130.87, "total_tokens": 158802360}580{"current_steps": 2885, "total_steps": 9742, "loss": 0.3681, "lr": 7.989049275023051e-06, "epoch": 0.5922808458222131, "percentage": 29.61, "elapsed_time": "4:50:19", "remaining_time": "11:30:02", "throughput": 9130.8, "total_tokens": 159054024}581{"current_steps": 2890, "total_steps": 9742, "loss": 0.3801, "lr": 7.982582602745094e-06, "epoch": 0.5933073290905359, "percentage": 29.67, "elapsed_time": "4:50:53", "remaining_time": "11:29:41", "throughput": 9129.07, "total_tokens": 159335944}582{"current_steps": 2895, "total_steps": 9742, "loss": 0.3719, "lr": 7.976108176286933e-06, "epoch": 0.5943338123588585, "percentage": 29.72, "elapsed_time": "4:51:23", "remaining_time": "11:29:09", "throughput": 9129.95, "total_tokens": 159620496}583{"current_steps": 2900, "total_steps": 9742, "loss": 0.3851, "lr": 7.96962601248091e-06, "epoch": 0.5953602956271813, "percentage": 29.77, "elapsed_time": "4:51:52", "remaining_time": "11:28:38", "throughput": 9129.89, "total_tokens": 159889832}584{"current_steps": 2905, "total_steps": 9742, "loss": 0.3713, "lr": 7.963136128179495e-06, "epoch": 0.596386778895504, "percentage": 29.82, "elapsed_time": "4:52:25", "remaining_time": "11:28:14", "throughput": 9127.95, "total_tokens": 160157016}585{"current_steps": 2910, "total_steps": 9742, "loss": 0.3855, "lr": 7.95663854025522e-06, "epoch": 0.5974132621638267, "percentage": 29.87, "elapsed_time": "4:52:47", "remaining_time": "11:27:24", "throughput": 9133.4, "total_tokens": 160450024}586{"current_steps": 2915, "total_steps": 9742, "loss": 0.3843, "lr": 7.950133265600649e-06, "epoch": 0.5984397454321495, "percentage": 29.92, "elapsed_time": "4:53:15", "remaining_time": "11:26:48", "throughput": 9133.58, "total_tokens": 160708432}587{"current_steps": 2920, "total_steps": 9742, "loss": 0.3619, "lr": 7.943620321128331e-06, "epoch": 0.5994662287004722, "percentage": 29.97, "elapsed_time": "4:53:46", "remaining_time": "11:26:20", "throughput": 9133.79, "total_tokens": 160993552}588{"current_steps": 2925, "total_steps": 9742, "loss": 0.3611, "lr": 7.937099723770756e-06, "epoch": 0.600492711968795, "percentage": 30.02, "elapsed_time": "4:54:16", "remaining_time": "11:25:51", "throughput": 9134.3, "total_tokens": 161283160}589{"current_steps": 2930, "total_steps": 9742, "loss": 0.3799, "lr": 7.930571490480307e-06, "epoch": 0.6015191952371176, "percentage": 30.08, "elapsed_time": "4:54:50", "remaining_time": "11:25:28", "throughput": 9131.23, "total_tokens": 161536096}590{"current_steps": 2935, "total_steps": 9742, "loss": 0.3478, "lr": 7.924035638229219e-06, "epoch": 0.6025456785054404, "percentage": 30.13, "elapsed_time": "4:55:14", "remaining_time": "11:24:43", "throughput": 9132.54, "total_tokens": 161774976}591{"current_steps": 2940, "total_steps": 9742, "loss": 0.3758, "lr": 7.91749218400954e-06, "epoch": 0.603572161773763, "percentage": 30.18, "elapsed_time": "4:55:48", "remaining_time": "11:24:22", "throughput": 9131.87, "total_tokens": 162075840}592{"current_steps": 2945, "total_steps": 9742, "loss": 0.3655, "lr": 7.910941144833076e-06, "epoch": 0.6045986450420858, "percentage": 30.23, "elapsed_time": "4:56:19", "remaining_time": "11:23:54", "throughput": 9131.58, "total_tokens": 162352800}593{"current_steps": 2950, "total_steps": 9742, "loss": 0.3738, "lr": 7.904382537731354e-06, "epoch": 0.6056251283104085, "percentage": 30.28, "elapsed_time": "4:56:39", "remaining_time": "11:23:00", "throughput": 9137.16, "total_tokens": 162635736}594{"current_steps": 2955, "total_steps": 9742, "loss": 0.3284, "lr": 7.897816379755578e-06, "epoch": 0.6066516115787313, "percentage": 30.33, "elapsed_time": "4:57:08", "remaining_time": "11:22:28", "throughput": 9138.63, "total_tokens": 162928192}595{"current_steps": 2960, "total_steps": 9742, "loss": 0.3751, "lr": 7.891242687976584e-06, "epoch": 0.607678094847054, "percentage": 30.38, "elapsed_time": "4:57:39", "remaining_time": "11:22:00", "throughput": 9139.15, "total_tokens": 163223056}596{"current_steps": 2965, "total_steps": 9742, "loss": 0.3728, "lr": 7.884661479484788e-06, "epoch": 0.6087045781153767, "percentage": 30.44, "elapsed_time": "4:58:08", "remaining_time": "11:21:27", "throughput": 9139.41, "total_tokens": 163492576}597{"current_steps": 2970, "total_steps": 9742, "loss": 0.3526, "lr": 7.878072771390156e-06, "epoch": 0.6097310613836995, "percentage": 30.49, "elapsed_time": "4:58:37", "remaining_time": "11:20:55", "throughput": 9140.37, "total_tokens": 163775800}598{"current_steps": 2975, "total_steps": 9742, "loss": 0.3749, "lr": 7.871476580822146e-06, "epoch": 0.6107575446520221, "percentage": 30.54, "elapsed_time": "4:59:04", "remaining_time": "11:20:17", "throughput": 9143.65, "total_tokens": 164078504}599{"current_steps": 2980, "total_steps": 9742, "loss": 0.3884, "lr": 7.864872924929673e-06, "epoch": 0.6117840279203449, "percentage": 30.59, "elapsed_time": "4:59:29", "remaining_time": "11:19:35", "throughput": 9146.75, "total_tokens": 164364880}600{"current_steps": 2985, "total_steps": 9742, "loss": 0.3791, "lr": 7.85826182088106e-06, "epoch": 0.6128105111886676, "percentage": 30.64, "elapsed_time": "4:59:58", "remaining_time": "11:19:03", "throughput": 9147.06, "total_tokens": 164636800}601{"current_steps": 2990, "total_steps": 9742, "loss": 0.382, "lr": 7.851643285863988e-06, "epoch": 0.6138369944569904, "percentage": 30.69, "elapsed_time": "5:00:30", "remaining_time": "11:18:37", "throughput": 9146.08, "total_tokens": 164911056}602{"current_steps": 2995, "total_steps": 9742, "loss": 0.4141, "lr": 7.845017337085466e-06, "epoch": 0.614863477725313, "percentage": 30.74, "elapsed_time": "5:00:56", "remaining_time": "11:17:57", "throughput": 9148.48, "total_tokens": 165192464}603{"current_steps": 3000, "total_steps": 9742, "loss": 0.3671, "lr": 7.83838399177177e-06, "epoch": 0.6158899609936358, "percentage": 30.79, "elapsed_time": "5:01:30", "remaining_time": "11:17:34", "throughput": 9146.68, "total_tokens": 165465928}604{"current_steps": 3005, "total_steps": 9742, "loss": 0.358, "lr": 7.831743267168412e-06, "epoch": 0.6169164442619586, "percentage": 30.85, "elapsed_time": "5:01:54", "remaining_time": "11:16:52", "throughput": 9149.0, "total_tokens": 165734056}605{"current_steps": 3010, "total_steps": 9742, "loss": 0.3688, "lr": 7.825095180540086e-06, "epoch": 0.6179429275302812, "percentage": 30.9, "elapsed_time": "5:02:24", "remaining_time": "11:16:20", "throughput": 9150.06, "total_tokens": 166020464}606{"current_steps": 3015, "total_steps": 9742, "loss": 0.3857, "lr": 7.818439749170621e-06, "epoch": 0.618969410798604, "percentage": 30.95, "elapsed_time": "5:02:47", "remaining_time": "11:15:34", "throughput": 9154.93, "total_tokens": 166320760}607{"current_steps": 3020, "total_steps": 9742, "loss": 0.3818, "lr": 7.811776990362951e-06, "epoch": 0.6199958940669267, "percentage": 31.0, "elapsed_time": "5:03:13", "remaining_time": "11:14:54", "throughput": 9156.46, "total_tokens": 166583800}608{"current_steps": 3025, "total_steps": 9742, "loss": 0.3475, "lr": 7.805106921439053e-06, "epoch": 0.6210223773352495, "percentage": 31.05, "elapsed_time": "5:03:35", "remaining_time": "11:14:06", "throughput": 9159.32, "total_tokens": 166839064}609{"current_steps": 3030, "total_steps": 9742, "loss": 0.3522, "lr": 7.798429559739911e-06, "epoch": 0.6220488606035721, "percentage": 31.1, "elapsed_time": "5:04:08", "remaining_time": "11:13:43", "throughput": 9157.07, "total_tokens": 167100432}610{"current_steps": 3035, "total_steps": 9742, "loss": 0.3813, "lr": 7.791744922625466e-06, "epoch": 0.6230753438718949, "percentage": 31.15, "elapsed_time": "5:04:39", "remaining_time": "11:13:16", "throughput": 9156.72, "total_tokens": 167384624}611{"current_steps": 3040, "total_steps": 9742, "loss": 0.3495, "lr": 7.78505302747458e-06, "epoch": 0.6241018271402177, "percentage": 31.21, "elapsed_time": "5:05:10", "remaining_time": "11:12:48", "throughput": 9155.35, "total_tokens": 167642016}612{"current_steps": 3045, "total_steps": 9742, "loss": 0.3296, "lr": 7.778353891684978e-06, "epoch": 0.6251283104085403, "percentage": 31.26, "elapsed_time": "5:05:45", "remaining_time": "11:12:28", "throughput": 9154.12, "total_tokens": 167939160}613{"current_steps": 3050, "total_steps": 9742, "loss": 0.3581, "lr": 7.771647532673215e-06, "epoch": 0.6261547936768631, "percentage": 31.31, "elapsed_time": "5:06:17", "remaining_time": "11:12:02", "throughput": 9153.74, "total_tokens": 168222808}614{"current_steps": 3055, "total_steps": 9742, "loss": 0.3518, "lr": 7.764933967874623e-06, "epoch": 0.6271812769451858, "percentage": 31.36, "elapsed_time": "5:06:48", "remaining_time": "11:11:34", "throughput": 9153.73, "total_tokens": 168509032}615{"current_steps": 3060, "total_steps": 9742, "loss": 0.3727, "lr": 7.758213214743264e-06, "epoch": 0.6282077602135085, "percentage": 31.41, "elapsed_time": "5:07:22", "remaining_time": "11:11:11", "throughput": 9151.07, "total_tokens": 168765832}616{"current_steps": 3065, "total_steps": 9742, "loss": 0.3726, "lr": 7.751485290751893e-06, "epoch": 0.6292342434818312, "percentage": 31.46, "elapsed_time": "5:07:56", "remaining_time": "11:10:51", "throughput": 9148.91, "total_tokens": 169043184}617{"current_steps": 3070, "total_steps": 9742, "loss": 0.3587, "lr": 7.744750213391907e-06, "epoch": 0.630260726750154, "percentage": 31.51, "elapsed_time": "5:08:27", "remaining_time": "11:10:22", "throughput": 9148.98, "total_tokens": 169326592}618{"current_steps": 3075, "total_steps": 9742, "loss": 0.3763, "lr": 7.738008000173301e-06, "epoch": 0.6312872100184767, "percentage": 31.56, "elapsed_time": "5:08:58", "remaining_time": "11:09:54", "throughput": 9147.75, "total_tokens": 169586184}619{"current_steps": 3080, "total_steps": 9742, "loss": 0.3762, "lr": 7.731258668624619e-06, "epoch": 0.6323136932867994, "percentage": 31.62, "elapsed_time": "5:09:24", "remaining_time": "11:09:15", "throughput": 9148.81, "total_tokens": 169844928}620{"current_steps": 3085, "total_steps": 9742, "loss": 0.3978, "lr": 7.724502236292915e-06, "epoch": 0.6333401765551222, "percentage": 31.67, "elapsed_time": "5:09:53", "remaining_time": "11:08:42", "throughput": 9150.95, "total_tokens": 170147680}621{"current_steps": 3090, "total_steps": 9742, "loss": 0.3623, "lr": 7.717738720743699e-06, "epoch": 0.6343666598234449, "percentage": 31.72, "elapsed_time": "5:10:26", "remaining_time": "11:08:18", "throughput": 9148.59, "total_tokens": 170406008}622{"current_steps": 3095, "total_steps": 9742, "loss": 0.3646, "lr": 7.710968139560904e-06, "epoch": 0.6353931430917676, "percentage": 31.77, "elapsed_time": "5:10:57", "remaining_time": "11:07:50", "throughput": 9148.72, "total_tokens": 170694272}623{"current_steps": 3100, "total_steps": 9742, "loss": 0.3792, "lr": 7.704190510346825e-06, "epoch": 0.6364196263600903, "percentage": 31.82, "elapsed_time": "5:11:30", "remaining_time": "11:07:25", "throughput": 9147.9, "total_tokens": 170978584}624{"current_steps": 3105, "total_steps": 9742, "loss": 0.3649, "lr": 7.697405850722081e-06, "epoch": 0.6374461096284131, "percentage": 31.87, "elapsed_time": "5:12:06", "remaining_time": "11:07:07", "throughput": 9145.59, "total_tokens": 171260736}625{"current_steps": 3110, "total_steps": 9742, "loss": 0.3708, "lr": 7.690614178325576e-06, "epoch": 0.6384725928967357, "percentage": 31.92, "elapsed_time": "5:12:31", "remaining_time": "11:06:27", "throughput": 9145.97, "total_tokens": 171502056}626{"current_steps": 3115, "total_steps": 9742, "loss": 0.3967, "lr": 7.683815510814437e-06, "epoch": 0.6394990761650585, "percentage": 31.97, "elapsed_time": "5:12:53", "remaining_time": "11:05:40", "throughput": 9149.48, "total_tokens": 171769864}627{"current_steps": 3120, "total_steps": 9742, "loss": 0.3816, "lr": 7.677009865863983e-06, "epoch": 0.6405255594333812, "percentage": 32.03, "elapsed_time": "5:13:22", "remaining_time": "11:05:06", "throughput": 9151.37, "total_tokens": 172067424}628{"current_steps": 3125, "total_steps": 9742, "loss": 0.3637, "lr": 7.67019726116767e-06, "epoch": 0.641552042701704, "percentage": 32.08, "elapsed_time": "5:13:51", "remaining_time": "11:04:35", "throughput": 9150.28, "total_tokens": 172316552}629{"current_steps": 3130, "total_steps": 9742, "loss": 0.3548, "lr": 7.66337771443705e-06, "epoch": 0.6425785259700267, "percentage": 32.13, "elapsed_time": "5:14:26", "remaining_time": "11:04:14", "throughput": 9147.67, "total_tokens": 172584504}630{"current_steps": 3135, "total_steps": 9742, "loss": 0.3713, "lr": 7.656551243401722e-06, "epoch": 0.6436050092383494, "percentage": 32.18, "elapsed_time": "5:14:59", "remaining_time": "11:03:51", "throughput": 9146.67, "total_tokens": 172871536}631{"current_steps": 3140, "total_steps": 9742, "loss": 0.386, "lr": 7.649717865809285e-06, "epoch": 0.6446314925066722, "percentage": 32.23, "elapsed_time": "5:15:25", "remaining_time": "11:03:11", "throughput": 9148.03, "total_tokens": 173128768}632{"current_steps": 3145, "total_steps": 9742, "loss": 0.3496, "lr": 7.642877599425301e-06, "epoch": 0.6456579757749948, "percentage": 32.28, "elapsed_time": "5:15:58", "remaining_time": "11:02:48", "throughput": 9146.59, "total_tokens": 173408800}633{"current_steps": 3150, "total_steps": 9742, "loss": 0.3637, "lr": 7.636030462033233e-06, "epoch": 0.6466844590433176, "percentage": 32.33, "elapsed_time": "5:16:21", "remaining_time": "11:02:02", "throughput": 9151.58, "total_tokens": 173710480}634{"current_steps": 3155, "total_steps": 9742, "loss": 0.3852, "lr": 7.6291764714344115e-06, "epoch": 0.6477109423116403, "percentage": 32.39, "elapsed_time": "5:16:55", "remaining_time": "11:01:40", "throughput": 9150.26, "total_tokens": 173996072}635{"current_steps": 3160, "total_steps": 9742, "loss": 0.3488, "lr": 7.622315645447985e-06, "epoch": 0.6487374255799631, "percentage": 32.44, "elapsed_time": "5:17:18", "remaining_time": "11:00:54", "throughput": 9153.5, "total_tokens": 174265176}636{"current_steps": 3165, "total_steps": 9742, "loss": 0.3617, "lr": 7.61544800191087e-06, "epoch": 0.6497639088482857, "percentage": 32.49, "elapsed_time": "5:17:47", "remaining_time": "11:00:23", "throughput": 9154.59, "total_tokens": 174556504}637{"current_steps": 3170, "total_steps": 9742, "loss": 0.3626, "lr": 7.608573558677708e-06, "epoch": 0.6507903921166085, "percentage": 32.54, "elapsed_time": "5:18:17", "remaining_time": "10:59:53", "throughput": 9154.74, "total_tokens": 174837136}638{"current_steps": 3175, "total_steps": 9742, "loss": 0.3782, "lr": 7.601692333620822e-06, "epoch": 0.6518168753849313, "percentage": 32.59, "elapsed_time": "5:18:48", "remaining_time": "10:59:23", "throughput": 9155.45, "total_tokens": 175127800}639{"current_steps": 3180, "total_steps": 9742, "loss": 0.395, "lr": 7.594804344630162e-06, "epoch": 0.6528433586532539, "percentage": 32.64, "elapsed_time": "5:19:19", "remaining_time": "10:58:55", "throughput": 9155.07, "total_tokens": 175404464}640{"current_steps": 3185, "total_steps": 9742, "loss": 0.3503, "lr": 7.587909609613264e-06, "epoch": 0.6538698419215767, "percentage": 32.69, "elapsed_time": "5:19:52", "remaining_time": "10:58:31", "throughput": 9153.86, "total_tokens": 175685352}641{"current_steps": 3190, "total_steps": 9742, "loss": 0.3427, "lr": 7.581008146495208e-06, "epoch": 0.6548963251898994, "percentage": 32.74, "elapsed_time": "5:20:22", "remaining_time": "10:58:02", "throughput": 9152.18, "total_tokens": 175931240}642{"current_steps": 3195, "total_steps": 9742, "loss": 0.3473, "lr": 7.574099973218554e-06, "epoch": 0.6559228084582222, "percentage": 32.8, "elapsed_time": "5:20:57", "remaining_time": "10:57:41", "throughput": 9150.05, "total_tokens": 176208760}643{"current_steps": 3200, "total_steps": 9742, "loss": 0.3655, "lr": 7.56718510774332e-06, "epoch": 0.6569492917265448, "percentage": 32.85, "elapsed_time": "5:21:25", "remaining_time": "10:57:07", "throughput": 9152.56, "total_tokens": 176513256}644{"current_steps": 3205, "total_steps": 9742, "loss": 0.3549, "lr": 7.560263568046915e-06, "epoch": 0.6579757749948676, "percentage": 32.9, "elapsed_time": "5:21:56", "remaining_time": "10:56:38", "throughput": 9152.92, "total_tokens": 176800672}645{"current_steps": 3210, "total_steps": 9742, "loss": 0.3724, "lr": 7.553335372124101e-06, "epoch": 0.6590022582631903, "percentage": 32.95, "elapsed_time": "5:22:24", "remaining_time": "10:56:04", "throughput": 9154.73, "total_tokens": 177095544}646{"current_steps": 3215, "total_steps": 9742, "loss": 0.3432, "lr": 7.546400537986947e-06, "epoch": 0.660028741531513, "percentage": 33.0, "elapsed_time": "5:22:50", "remaining_time": "10:55:25", "throughput": 9156.49, "total_tokens": 177364104}647{"current_steps": 3220, "total_steps": 9742, "loss": 0.3595, "lr": 7.539459083664777e-06, "epoch": 0.6610552247998358, "percentage": 33.05, "elapsed_time": "5:23:21", "remaining_time": "10:54:56", "throughput": 9155.75, "total_tokens": 177633880}648{"current_steps": 3225, "total_steps": 9742, "loss": 0.3669, "lr": 7.532511027204131e-06, "epoch": 0.6620817080681585, "percentage": 33.1, "elapsed_time": "5:23:53", "remaining_time": "10:54:30", "throughput": 9155.63, "total_tokens": 177924776}649{"current_steps": 3230, "total_steps": 9742, "loss": 0.37, "lr": 7.525556386668708e-06, "epoch": 0.6631081913364812, "percentage": 33.16, "elapsed_time": "5:24:16", "remaining_time": "10:53:46", "throughput": 9158.61, "total_tokens": 178195296}650{"current_steps": 3235, "total_steps": 9742, "loss": 0.3633, "lr": 7.518595180139328e-06, "epoch": 0.6641346746048039, "percentage": 33.21, "elapsed_time": "5:24:46", "remaining_time": "10:53:15", "throughput": 9158.05, "total_tokens": 178457504}651{"current_steps": 3240, "total_steps": 9742, "loss": 0.3711, "lr": 7.511627425713881e-06, "epoch": 0.6651611578731267, "percentage": 33.26, "elapsed_time": "5:25:15", "remaining_time": "10:52:44", "throughput": 9157.98, "total_tokens": 178725144}652{"current_steps": 3245, "total_steps": 9742, "loss": 0.3669, "lr": 7.504653141507278e-06, "epoch": 0.6661876411414493, "percentage": 33.31, "elapsed_time": "5:25:44", "remaining_time": "10:52:12", "throughput": 9157.83, "total_tokens": 178989136}653{"current_steps": 3250, "total_steps": 9742, "loss": 0.3537, "lr": 7.4976723456514075e-06, "epoch": 0.6672141244097721, "percentage": 33.36, "elapsed_time": "5:26:12", "remaining_time": "10:51:36", "throughput": 9157.84, "total_tokens": 179239208}654{"current_steps": 3255, "total_steps": 9742, "loss": 0.3509, "lr": 7.490685056295093e-06, "epoch": 0.6682406076780949, "percentage": 33.41, "elapsed_time": "5:26:44", "remaining_time": "10:51:09", "throughput": 9157.2, "total_tokens": 179519184}655{"current_steps": 3260, "total_steps": 9742, "loss": 0.3308, "lr": 7.483691291604026e-06, "epoch": 0.6692670909464176, "percentage": 33.46, "elapsed_time": "5:27:12", "remaining_time": "10:50:36", "throughput": 9158.87, "total_tokens": 179811072}656{"current_steps": 3265, "total_steps": 9742, "loss": 0.3861, "lr": 7.476691069760749e-06, "epoch": 0.6702935742147403, "percentage": 33.51, "elapsed_time": "5:27:45", "remaining_time": "10:50:11", "throughput": 9157.65, "total_tokens": 180087472}657{"current_steps": 3270, "total_steps": 9742, "loss": 0.3866, "lr": 7.469684408964579e-06, "epoch": 0.671320057483063, "percentage": 33.57, "elapsed_time": "5:28:14", "remaining_time": "10:49:39", "throughput": 9158.35, "total_tokens": 180367360}658{"current_steps": 3275, "total_steps": 9742, "loss": 0.3843, "lr": 7.462671327431579e-06, "epoch": 0.6723465407513858, "percentage": 33.62, "elapsed_time": "5:28:43", "remaining_time": "10:49:07", "throughput": 9158.35, "total_tokens": 180638440}659{"current_steps": 3280, "total_steps": 9742, "loss": 0.3814, "lr": 7.455651843394508e-06, "epoch": 0.6733730240197084, "percentage": 33.67, "elapsed_time": "5:29:09", "remaining_time": "10:48:29", "throughput": 9160.03, "total_tokens": 180910264}660{"current_steps": 3285, "total_steps": 9742, "loss": 0.3643, "lr": 7.448625975102761e-06, "epoch": 0.6743995072880312, "percentage": 33.72, "elapsed_time": "5:29:36", "remaining_time": "10:47:52", "throughput": 9161.12, "total_tokens": 181175896}661{"current_steps": 3290, "total_steps": 9742, "loss": 0.3615, "lr": 7.441593740822342e-06, "epoch": 0.6754259905563539, "percentage": 33.77, "elapsed_time": "5:30:01", "remaining_time": "10:47:11", "throughput": 9163.89, "total_tokens": 181455272}662{"current_steps": 3295, "total_steps": 9742, "loss": 0.366, "lr": 7.434555158835794e-06, "epoch": 0.6764524738246767, "percentage": 33.82, "elapsed_time": "5:30:30", "remaining_time": "10:46:41", "throughput": 9164.2, "total_tokens": 181735096}663{"current_steps": 3300, "total_steps": 9742, "loss": 0.3658, "lr": 7.4275102474421716e-06, "epoch": 0.6774789570929994, "percentage": 33.87, "elapsed_time": "5:31:01", "remaining_time": "10:46:12", "throughput": 9163.52, "total_tokens": 182004248}664{"current_steps": 3305, "total_steps": 9742, "loss": 0.3795, "lr": 7.420459024956982e-06, "epoch": 0.6785054403613221, "percentage": 33.93, "elapsed_time": "5:31:26", "remaining_time": "10:45:32", "throughput": 9163.83, "total_tokens": 182240000}665{"current_steps": 3310, "total_steps": 9742, "loss": 0.3475, "lr": 7.413401509712138e-06, "epoch": 0.6795319236296449, "percentage": 33.98, "elapsed_time": "5:32:00", "remaining_time": "10:45:09", "throughput": 9162.49, "total_tokens": 182518880}666{"current_steps": 3315, "total_steps": 9742, "loss": 0.3732, "lr": 7.406337720055919e-06, "epoch": 0.6805584068979675, "percentage": 34.03, "elapsed_time": "5:32:27", "remaining_time": "10:44:33", "throughput": 9163.19, "total_tokens": 182782792}667{"current_steps": 3320, "total_steps": 9742, "loss": 0.3532, "lr": 7.399267674352906e-06, "epoch": 0.6815848901662903, "percentage": 34.08, "elapsed_time": "5:32:56", "remaining_time": "10:44:01", "throughput": 9164.66, "total_tokens": 183079968}668{"current_steps": 3325, "total_steps": 9742, "loss": 0.3784, "lr": 7.392191390983954e-06, "epoch": 0.682611373434613, "percentage": 34.13, "elapsed_time": "5:33:26", "remaining_time": "10:43:31", "throughput": 9163.58, "total_tokens": 183332856}669{"current_steps": 3330, "total_steps": 9742, "loss": 0.3688, "lr": 7.385108888346132e-06, "epoch": 0.6836378567029358, "percentage": 34.18, "elapsed_time": "5:33:51", "remaining_time": "10:42:51", "throughput": 9165.38, "total_tokens": 183597720}670{"current_steps": 3335, "total_steps": 9742, "loss": 0.384, "lr": 7.378020184852676e-06, "epoch": 0.6846643399712584, "percentage": 34.23, "elapsed_time": "5:34:24", "remaining_time": "10:42:27", "throughput": 9164.59, "total_tokens": 183886008}671{"current_steps": 3340, "total_steps": 9742, "loss": 0.3312, "lr": 7.370925298932944e-06, "epoch": 0.6856908232395812, "percentage": 34.28, "elapsed_time": "5:34:56", "remaining_time": "10:42:00", "throughput": 9165.27, "total_tokens": 184191800}672{"current_steps": 3345, "total_steps": 9742, "loss": 0.3266, "lr": 7.363824249032371e-06, "epoch": 0.686717306507904, "percentage": 34.34, "elapsed_time": "5:35:27", "remaining_time": "10:41:31", "throughput": 9164.6, "total_tokens": 184456792}673{"current_steps": 3350, "total_steps": 9742, "loss": 0.3768, "lr": 7.35671705361241e-06, "epoch": 0.6877437897762266, "percentage": 34.39, "elapsed_time": "5:35:56", "remaining_time": "10:41:00", "throughput": 9165.2, "total_tokens": 184742792}674{"current_steps": 3355, "total_steps": 9742, "loss": 0.3694, "lr": 7.349603731150497e-06, "epoch": 0.6887702730445494, "percentage": 34.44, "elapsed_time": "5:36:27", "remaining_time": "10:40:32", "throughput": 9164.96, "total_tokens": 185020296}675{"current_steps": 3360, "total_steps": 9742, "loss": 0.3613, "lr": 7.342484300139998e-06, "epoch": 0.6897967563128721, "percentage": 34.49, "elapsed_time": "5:36:58", "remaining_time": "10:40:03", "throughput": 9165.49, "total_tokens": 185316720}676{"current_steps": 3365, "total_steps": 9742, "loss": 0.3748, "lr": 7.335358779090153e-06, "epoch": 0.6908232395811948, "percentage": 34.54, "elapsed_time": "5:37:29", "remaining_time": "10:39:34", "throughput": 9165.73, "total_tokens": 185599712}677{"current_steps": 3370, "total_steps": 9742, "loss": 0.3588, "lr": 7.328227186526044e-06, "epoch": 0.6918497228495175, "percentage": 34.59, "elapsed_time": "5:38:00", "remaining_time": "10:39:05", "throughput": 9164.81, "total_tokens": 185864096}678{"current_steps": 3375, "total_steps": 9742, "loss": 0.3963, "lr": 7.321089540988529e-06, "epoch": 0.6928762061178403, "percentage": 34.64, "elapsed_time": "5:38:27", "remaining_time": "10:38:29", "throughput": 9165.54, "total_tokens": 186126144}679{"current_steps": 3380, "total_steps": 9742, "loss": 0.3609, "lr": 7.313945861034211e-06, "epoch": 0.693902689386163, "percentage": 34.7, "elapsed_time": "5:38:58", "remaining_time": "10:38:02", "throughput": 9165.13, "total_tokens": 186405176}680{"current_steps": 3385, "total_steps": 9742, "loss": 0.3485, "lr": 7.3067961652353765e-06, "epoch": 0.6949291726544857, "percentage": 34.75, "elapsed_time": "5:39:27", "remaining_time": "10:37:30", "throughput": 9165.9, "total_tokens": 186688008}681{"current_steps": 3390, "total_steps": 9742, "loss": 0.3532, "lr": 7.299640472179953e-06, "epoch": 0.6959556559228085, "percentage": 34.8, "elapsed_time": "5:39:58", "remaining_time": "10:37:01", "throughput": 9164.9, "total_tokens": 186948472}682{"current_steps": 3395, "total_steps": 9742, "loss": 0.3785, "lr": 7.292478800471459e-06, "epoch": 0.6969821391911312, "percentage": 34.85, "elapsed_time": "5:40:25", "remaining_time": "10:36:25", "throughput": 9164.65, "total_tokens": 187191568}683{"current_steps": 3400, "total_steps": 9742, "loss": 0.3739, "lr": 7.285311168728958e-06, "epoch": 0.6980086224594539, "percentage": 34.9, "elapsed_time": "5:40:58", "remaining_time": "10:36:00", "throughput": 9164.9, "total_tokens": 187496160}684{"current_steps": 3405, "total_steps": 9742, "loss": 0.3565, "lr": 7.278137595587008e-06, "epoch": 0.6990351057277766, "percentage": 34.95, "elapsed_time": "5:41:28", "remaining_time": "10:35:30", "throughput": 9165.07, "total_tokens": 187776256}685{"current_steps": 3410, "total_steps": 9742, "loss": 0.3414, "lr": 7.270958099695614e-06, "epoch": 0.7000615889960994, "percentage": 35.0, "elapsed_time": "5:42:00", "remaining_time": "10:35:04", "throughput": 9163.08, "total_tokens": 188033256}686{"current_steps": 3415, "total_steps": 9742, "loss": 0.3603, "lr": 7.263772699720179e-06, "epoch": 0.701088072264422, "percentage": 35.05, "elapsed_time": "5:42:36", "remaining_time": "10:34:45", "throughput": 9160.87, "total_tokens": 188317200}687{"current_steps": 3420, "total_steps": 9742, "loss": 0.3653, "lr": 7.256581414341452e-06, "epoch": 0.7021145555327448, "percentage": 35.11, "elapsed_time": "5:43:09", "remaining_time": "10:34:20", "throughput": 9159.59, "total_tokens": 188589400}688{"current_steps": 3425, "total_steps": 9742, "loss": 0.3498, "lr": 7.24938426225549e-06, "epoch": 0.7031410388010676, "percentage": 35.16, "elapsed_time": "5:43:42", "remaining_time": "10:33:55", "throughput": 9158.21, "total_tokens": 188864256}689{"current_steps": 3430, "total_steps": 9742, "loss": 0.3784, "lr": 7.242181262173595e-06, "epoch": 0.7041675220693903, "percentage": 35.21, "elapsed_time": "5:44:15", "remaining_time": "10:33:30", "throughput": 9156.54, "total_tokens": 189132920}690{"current_steps": 3435, "total_steps": 9742, "loss": 0.3518, "lr": 7.234972432822279e-06, "epoch": 0.705194005337713, "percentage": 35.26, "elapsed_time": "5:44:45", "remaining_time": "10:33:00", "throughput": 9157.34, "total_tokens": 189425104}691{"current_steps": 3440, "total_steps": 9742, "loss": 0.3468, "lr": 7.227757792943207e-06, "epoch": 0.7062204886060357, "percentage": 35.31, "elapsed_time": "5:45:14", "remaining_time": "10:32:29", "throughput": 9158.08, "total_tokens": 189708512}692{"current_steps": 3445, "total_steps": 9742, "loss": 0.3956, "lr": 7.220537361293146e-06, "epoch": 0.7072469718743585, "percentage": 35.36, "elapsed_time": "5:45:47", "remaining_time": "10:32:03", "throughput": 9156.06, "total_tokens": 189966184}693{"current_steps": 3450, "total_steps": 9742, "loss": 0.3607, "lr": 7.213311156643927e-06, "epoch": 0.7082734551426811, "percentage": 35.41, "elapsed_time": "5:46:19", "remaining_time": "10:31:37", "throughput": 9154.98, "total_tokens": 190236664}694{"current_steps": 3455, "total_steps": 9742, "loss": 0.3774, "lr": 7.206079197782384e-06, "epoch": 0.7092999384110039, "percentage": 35.46, "elapsed_time": "5:46:45", "remaining_time": "10:30:59", "throughput": 9156.12, "total_tokens": 190498752}695{"current_steps": 3460, "total_steps": 9742, "loss": 0.3855, "lr": 7.198841503510319e-06, "epoch": 0.7103264216793266, "percentage": 35.52, "elapsed_time": "5:47:19", "remaining_time": "10:30:35", "throughput": 9155.18, "total_tokens": 190785416}696{"current_steps": 3465, "total_steps": 9742, "loss": 0.3468, "lr": 7.191598092644435e-06, "epoch": 0.7113529049476494, "percentage": 35.57, "elapsed_time": "5:47:46", "remaining_time": "10:30:00", "throughput": 9156.04, "total_tokens": 191051536}697{"current_steps": 3470, "total_steps": 9742, "loss": 0.3436, "lr": 7.184348984016305e-06, "epoch": 0.7123793882159721, "percentage": 35.62, "elapsed_time": "5:48:19", "remaining_time": "10:29:34", "throughput": 9155.28, "total_tokens": 191336904}698{"current_steps": 3475, "total_steps": 9742, "loss": 0.3494, "lr": 7.17709419647231e-06, "epoch": 0.7134058714842948, "percentage": 35.67, "elapsed_time": "5:48:50", "remaining_time": "10:29:06", "throughput": 9155.0, "total_tokens": 191615944}699{"current_steps": 3480, "total_steps": 9742, "loss": 0.3506, "lr": 7.169833748873598e-06, "epoch": 0.7144323547526176, "percentage": 35.72, "elapsed_time": "5:49:19", "remaining_time": "10:28:34", "throughput": 9156.44, "total_tokens": 191912664}700{"current_steps": 3485, "total_steps": 9742, "loss": 0.3831, "lr": 7.162567660096035e-06, "epoch": 0.7154588380209402, "percentage": 35.77, "elapsed_time": "5:49:47", "remaining_time": "10:28:00", "throughput": 9157.3, "total_tokens": 192185200}701{"current_steps": 3490, "total_steps": 9742, "loss": 0.3479, "lr": 7.155295949030143e-06, "epoch": 0.716485321289263, "percentage": 35.82, "elapsed_time": "5:50:20", "remaining_time": "10:27:37", "throughput": 9155.71, "total_tokens": 192461864}702{"current_steps": 3495, "total_steps": 9742, "loss": 0.3559, "lr": 7.1480186345810735e-06, "epoch": 0.7175118045575857, "percentage": 35.88, "elapsed_time": "5:50:50", "remaining_time": "10:27:05", "throughput": 9156.37, "total_tokens": 192746592}703{"current_steps": 3500, "total_steps": 9742, "loss": 0.387, "lr": 7.140735735668536e-06, "epoch": 0.7185382878259085, "percentage": 35.93, "elapsed_time": "5:51:16", "remaining_time": "10:26:28", "throughput": 9157.22, "total_tokens": 193004160}704{"current_steps": 3505, "total_steps": 9742, "loss": 0.3896, "lr": 7.133447271226764e-06, "epoch": 0.7195647710942311, "percentage": 35.98, "elapsed_time": "5:51:44", "remaining_time": "10:25:55", "throughput": 9159.18, "total_tokens": 193303720}705{"current_steps": 3510, "total_steps": 9742, "loss": 0.347, "lr": 7.126153260204458e-06, "epoch": 0.7205912543625539, "percentage": 36.03, "elapsed_time": "5:52:10", "remaining_time": "10:25:16", "throughput": 9160.38, "total_tokens": 193561584}706{"current_steps": 3515, "total_steps": 9742, "loss": 0.3409, "lr": 7.1188537215647405e-06, "epoch": 0.7216177376308767, "percentage": 36.08, "elapsed_time": "5:52:43", "remaining_time": "10:24:51", "throughput": 9158.13, "total_tokens": 193816240}707{"current_steps": 3520, "total_steps": 9742, "loss": 0.3554, "lr": 7.111548674285102e-06, "epoch": 0.7226442208991993, "percentage": 36.13, "elapsed_time": "5:53:14", "remaining_time": "10:24:23", "throughput": 9157.47, "total_tokens": 194089072}708{"current_steps": 3525, "total_steps": 9742, "loss": 0.3777, "lr": 7.1042381373573575e-06, "epoch": 0.7236707041675221, "percentage": 36.18, "elapsed_time": "5:53:43", "remaining_time": "10:23:51", "throughput": 9157.4, "total_tokens": 194350840}709{"current_steps": 3530, "total_steps": 9742, "loss": 0.3323, "lr": 7.096922129787593e-06, "epoch": 0.7246971874358448, "percentage": 36.23, "elapsed_time": "5:54:09", "remaining_time": "10:23:13", "throughput": 9159.08, "total_tokens": 194621712}710{"current_steps": 3535, "total_steps": 9742, "loss": 0.3616, "lr": 7.089600670596116e-06, "epoch": 0.7257236707041675, "percentage": 36.29, "elapsed_time": "5:54:40", "remaining_time": "10:22:45", "throughput": 9159.39, "total_tokens": 194912424}711{"current_steps": 3540, "total_steps": 9742, "loss": 0.4046, "lr": 7.082273778817409e-06, "epoch": 0.7267501539724902, "percentage": 36.34, "elapsed_time": "5:55:06", "remaining_time": "10:22:08", "throughput": 9159.83, "total_tokens": 195163568}712{"current_steps": 3545, "total_steps": 9742, "loss": 0.3598, "lr": 7.074941473500075e-06, "epoch": 0.727776637240813, "percentage": 36.39, "elapsed_time": "5:55:37", "remaining_time": "10:21:40", "throughput": 9160.25, "total_tokens": 195459040}713{"current_steps": 3550, "total_steps": 9742, "loss": 0.3903, "lr": 7.067603773706799e-06, "epoch": 0.7288031205091356, "percentage": 36.44, "elapsed_time": "5:56:12", "remaining_time": "10:21:17", "throughput": 9159.36, "total_tokens": 195755232}714{"current_steps": 3555, "total_steps": 9742, "loss": 0.357, "lr": 7.060260698514279e-06, "epoch": 0.7298296037774584, "percentage": 36.49, "elapsed_time": "5:56:46", "remaining_time": "10:20:54", "throughput": 9158.78, "total_tokens": 196053520}715{"current_steps": 3560, "total_steps": 9742, "loss": 0.3285, "lr": 7.052912267013199e-06, "epoch": 0.7308560870457812, "percentage": 36.54, "elapsed_time": "5:57:21", "remaining_time": "10:20:33", "throughput": 9155.14, "total_tokens": 196300800}716{"current_steps": 3565, "total_steps": 9742, "loss": 0.3821, "lr": 7.0455584983081615e-06, "epoch": 0.7318825703141039, "percentage": 36.59, "elapsed_time": "5:57:55", "remaining_time": "10:20:09", "throughput": 9152.6, "total_tokens": 196555376}717{"current_steps": 3570, "total_steps": 9742, "loss": 0.3497, "lr": 7.0381994115176476e-06, "epoch": 0.7329090535824266, "percentage": 36.65, "elapsed_time": "5:58:25", "remaining_time": "10:19:40", "throughput": 9152.09, "total_tokens": 196821496}718{"current_steps": 3575, "total_steps": 9742, "loss": 0.3447, "lr": 7.030835025773966e-06, "epoch": 0.7339355368507493, "percentage": 36.7, "elapsed_time": "5:58:59", "remaining_time": "10:19:16", "throughput": 9150.46, "total_tokens": 197097056}719{"current_steps": 3580, "total_steps": 9742, "loss": 0.3581, "lr": 7.023465360223197e-06, "epoch": 0.7349620201190721, "percentage": 36.75, "elapsed_time": "5:59:29", "remaining_time": "10:18:45", "throughput": 9149.23, "total_tokens": 197343240}720{"current_steps": 3585, "total_steps": 9742, "loss": 0.3629, "lr": 7.016090434025151e-06, "epoch": 0.7359885033873947, "percentage": 36.8, "elapsed_time": "5:59:58", "remaining_time": "10:18:13", "throughput": 9149.34, "total_tokens": 197607496}721{"current_steps": 3590, "total_steps": 9742, "loss": 0.3536, "lr": 7.008710266353316e-06, "epoch": 0.7370149866557175, "percentage": 36.85, "elapsed_time": "6:00:28", "remaining_time": "10:17:43", "throughput": 9149.21, "total_tokens": 197881960}722{"current_steps": 3595, "total_steps": 9742, "loss": 0.3547, "lr": 7.001324876394803e-06, "epoch": 0.7380414699240402, "percentage": 36.9, "elapsed_time": "6:00:58", "remaining_time": "10:17:13", "throughput": 9148.98, "total_tokens": 198151480}723{"current_steps": 3600, "total_steps": 9742, "loss": 0.3835, "lr": 6.993934283350303e-06, "epoch": 0.739067953192363, "percentage": 36.95, "elapsed_time": "6:01:27", "remaining_time": "10:16:40", "throughput": 9149.36, "total_tokens": 198423264}724{"current_steps": 3605, "total_steps": 9742, "loss": 0.3595, "lr": 6.986538506434033e-06, "epoch": 0.7400944364606857, "percentage": 37.0, "elapsed_time": "6:02:02", "remaining_time": "10:16:18", "throughput": 9147.77, "total_tokens": 198708688}725{"current_steps": 3610, "total_steps": 9742, "loss": 0.3432, "lr": 6.979137564873688e-06, "epoch": 0.7411209197290084, "percentage": 37.06, "elapsed_time": "6:02:31", "remaining_time": "10:15:47", "throughput": 9147.69, "total_tokens": 198975800}726{"current_steps": 3615, "total_steps": 9742, "loss": 0.382, "lr": 6.9717314779103896e-06, "epoch": 0.7421474029973312, "percentage": 37.11, "elapsed_time": "6:03:05", "remaining_time": "10:15:24", "throughput": 9146.95, "total_tokens": 199275424}727{"current_steps": 3620, "total_steps": 9742, "loss": 0.3687, "lr": 6.964320264798636e-06, "epoch": 0.7431738862656538, "percentage": 37.16, "elapsed_time": "6:03:35", "remaining_time": "10:14:53", "throughput": 9147.55, "total_tokens": 199556848}728{"current_steps": 3625, "total_steps": 9742, "loss": 0.3625, "lr": 6.956903944806254e-06, "epoch": 0.7442003695339766, "percentage": 37.21, "elapsed_time": "6:04:09", "remaining_time": "10:14:29", "throughput": 9145.85, "total_tokens": 199831672}729{"current_steps": 3630, "total_steps": 9742, "loss": 0.3602, "lr": 6.949482537214346e-06, "epoch": 0.7452268528022993, "percentage": 37.26, "elapsed_time": "6:04:42", "remaining_time": "10:14:05", "throughput": 9144.66, "total_tokens": 200112160}730{"current_steps": 3635, "total_steps": 9742, "loss": 0.3532, "lr": 6.94205606131724e-06, "epoch": 0.746253336070622, "percentage": 37.31, "elapsed_time": "6:05:10", "remaining_time": "10:13:30", "throughput": 9145.26, "total_tokens": 200374168}731{"current_steps": 3640, "total_steps": 9742, "loss": 0.3703, "lr": 6.9346245364224455e-06, "epoch": 0.7472798193389448, "percentage": 37.36, "elapsed_time": "6:05:36", "remaining_time": "10:12:54", "throughput": 9147.13, "total_tokens": 200658192}732{"current_steps": 3645, "total_steps": 9742, "loss": 0.3616, "lr": 6.927187981850591e-06, "epoch": 0.7483063026072675, "percentage": 37.42, "elapsed_time": "6:06:05", "remaining_time": "10:12:21", "throughput": 9148.66, "total_tokens": 200955200}733{"current_steps": 3650, "total_steps": 9742, "loss": 0.3507, "lr": 6.91974641693539e-06, "epoch": 0.7493327858755903, "percentage": 37.47, "elapsed_time": "6:06:35", "remaining_time": "10:11:51", "throughput": 9148.64, "total_tokens": 201229744}734{"current_steps": 3655, "total_steps": 9742, "loss": 0.3291, "lr": 6.9122998610235756e-06, "epoch": 0.7503592691439129, "percentage": 37.52, "elapsed_time": "6:07:01", "remaining_time": "10:11:13", "throughput": 9150.58, "total_tokens": 201506520}735{"current_steps": 3660, "total_steps": 9742, "loss": 0.3481, "lr": 6.904848333474857e-06, "epoch": 0.7513857524122357, "percentage": 37.57, "elapsed_time": "6:07:33", "remaining_time": "10:10:48", "throughput": 9149.39, "total_tokens": 201780352}736{"current_steps": 3665, "total_steps": 9742, "loss": 0.34, "lr": 6.897391853661874e-06, "epoch": 0.7524122356805584, "percentage": 37.62, "elapsed_time": "6:08:06", "remaining_time": "10:10:21", "throughput": 9147.18, "total_tokens": 202027984}737{"current_steps": 3670, "total_steps": 9742, "loss": 0.3377, "lr": 6.889930440970134e-06, "epoch": 0.7534387189488811, "percentage": 37.67, "elapsed_time": "6:08:36", "remaining_time": "10:09:51", "throughput": 9148.6, "total_tokens": 202335104}738{"current_steps": 3675, "total_steps": 9742, "loss": 0.3443, "lr": 6.882464114797974e-06, "epoch": 0.7544652022172038, "percentage": 37.72, "elapsed_time": "6:09:08", "remaining_time": "10:09:24", "throughput": 9146.7, "total_tokens": 202585256}739{"current_steps": 3680, "total_steps": 9742, "loss": 0.3385, "lr": 6.874992894556506e-06, "epoch": 0.7554916854855266, "percentage": 37.77, "elapsed_time": "6:09:35", "remaining_time": "10:08:48", "throughput": 9148.36, "total_tokens": 202866224}740{"current_steps": 3685, "total_steps": 9742, "loss": 0.3527, "lr": 6.8675167996695604e-06, "epoch": 0.7565181687538494, "percentage": 37.83, "elapsed_time": "6:10:07", "remaining_time": "10:08:21", "throughput": 9148.04, "total_tokens": 203150904}741{"current_steps": 3690, "total_steps": 9742, "loss": 0.3534, "lr": 6.860035849573645e-06, "epoch": 0.757544652022172, "percentage": 37.88, "elapsed_time": "6:10:37", "remaining_time": "10:07:52", "throughput": 9146.81, "total_tokens": 203403088}742{"current_steps": 3695, "total_steps": 9742, "loss": 0.3735, "lr": 6.85255006371789e-06, "epoch": 0.7585711352904948, "percentage": 37.93, "elapsed_time": "6:11:07", "remaining_time": "10:07:22", "throughput": 9147.04, "total_tokens": 203684888}743{"current_steps": 3700, "total_steps": 9742, "loss": 0.3744, "lr": 6.845059461563996e-06, "epoch": 0.7595976185588175, "percentage": 37.98, "elapsed_time": "6:11:33", "remaining_time": "10:06:45", "throughput": 9148.14, "total_tokens": 203948456}744{"current_steps": 3705, "total_steps": 9742, "loss": 0.3606, "lr": 6.837564062586187e-06, "epoch": 0.7606241018271402, "percentage": 38.03, "elapsed_time": "6:12:06", "remaining_time": "10:06:19", "throughput": 9146.7, "total_tokens": 204213872}745{"current_steps": 3710, "total_steps": 9742, "loss": 0.3607, "lr": 6.830063886271158e-06, "epoch": 0.7616505850954629, "percentage": 38.08, "elapsed_time": "6:12:33", "remaining_time": "10:05:44", "throughput": 9147.88, "total_tokens": 204491584}746{"current_steps": 3715, "total_steps": 9742, "loss": 0.3391, "lr": 6.82255895211802e-06, "epoch": 0.7626770683637857, "percentage": 38.13, "elapsed_time": "6:13:04", "remaining_time": "10:05:15", "throughput": 9146.89, "total_tokens": 204751544}747{"current_steps": 3720, "total_steps": 9742, "loss": 0.3664, "lr": 6.815049279638259e-06, "epoch": 0.7637035516321083, "percentage": 38.19, "elapsed_time": "6:13:34", "remaining_time": "10:04:44", "throughput": 9146.97, "total_tokens": 205021200}748{"current_steps": 3725, "total_steps": 9742, "loss": 0.3617, "lr": 6.807534888355676e-06, "epoch": 0.7647300349004311, "percentage": 38.24, "elapsed_time": "6:14:02", "remaining_time": "10:04:11", "throughput": 9147.55, "total_tokens": 205293568}749{"current_steps": 3730, "total_steps": 9742, "loss": 0.3446, "lr": 6.8000157978063454e-06, "epoch": 0.7657565181687539, "percentage": 38.29, "elapsed_time": "6:14:32", "remaining_time": "10:03:40", "throughput": 9148.33, "total_tokens": 205582872}750{"current_steps": 3735, "total_steps": 9742, "loss": 0.342, "lr": 6.792492027538548e-06, "epoch": 0.7667830014370766, "percentage": 38.34, "elapsed_time": "6:15:07", "remaining_time": "10:03:18", "throughput": 9146.53, "total_tokens": 205863152}751{"current_steps": 3740, "total_steps": 9742, "loss": 0.3628, "lr": 6.784963597112746e-06, "epoch": 0.7678094847053993, "percentage": 38.39, "elapsed_time": "6:15:41", "remaining_time": "10:02:55", "throughput": 9144.65, "total_tokens": 206136032}752{"current_steps": 3745, "total_steps": 9742, "loss": 0.3632, "lr": 6.777430526101503e-06, "epoch": 0.768835967973722, "percentage": 38.44, "elapsed_time": "6:16:12", "remaining_time": "10:02:25", "throughput": 9143.65, "total_tokens": 206393840}753{"current_steps": 3750, "total_steps": 9742, "loss": 0.3484, "lr": 6.769892834089455e-06, "epoch": 0.7698624512420448, "percentage": 38.49, "elapsed_time": "6:16:41", "remaining_time": "10:01:53", "throughput": 9142.52, "total_tokens": 206630448}754{"current_steps": 3755, "total_steps": 9742, "loss": 0.3598, "lr": 6.762350540673254e-06, "epoch": 0.7708889345103674, "percentage": 38.54, "elapsed_time": "6:17:13", "remaining_time": "10:01:27", "throughput": 9141.87, "total_tokens": 206914608}755{"current_steps": 3760, "total_steps": 9742, "loss": 0.3745, "lr": 6.754803665461507e-06, "epoch": 0.7719154177786902, "percentage": 38.6, "elapsed_time": "6:17:45", "remaining_time": "10:01:00", "throughput": 9140.02, "total_tokens": 207167592}756{"current_steps": 3765, "total_steps": 9742, "loss": 0.3843, "lr": 6.7472522280747385e-06, "epoch": 0.7729419010470129, "percentage": 38.65, "elapsed_time": "6:18:15", "remaining_time": "10:00:29", "throughput": 9138.87, "total_tokens": 207412256}757{"current_steps": 3770, "total_steps": 9742, "loss": 0.3226, "lr": 6.739696248145331e-06, "epoch": 0.7739683843153357, "percentage": 38.7, "elapsed_time": "6:18:52", "remaining_time": "10:00:10", "throughput": 9136.48, "total_tokens": 207698912}758{"current_steps": 3775, "total_steps": 9742, "loss": 0.3661, "lr": 6.7321357453174805e-06, "epoch": 0.7749948675836584, "percentage": 38.75, "elapsed_time": "6:19:21", "remaining_time": "9:59:38", "throughput": 9135.48, "total_tokens": 207941064}759{"current_steps": 3780, "total_steps": 9742, "loss": 0.3533, "lr": 6.724570739247137e-06, "epoch": 0.7760213508519811, "percentage": 38.8, "elapsed_time": "6:19:53", "remaining_time": "9:59:10", "throughput": 9135.34, "total_tokens": 208225856}760{"current_steps": 3785, "total_steps": 9742, "loss": 0.3422, "lr": 6.717001249601961e-06, "epoch": 0.7770478341203039, "percentage": 38.85, "elapsed_time": "6:20:23", "remaining_time": "9:58:41", "throughput": 9135.74, "total_tokens": 208513984}761{"current_steps": 3790, "total_steps": 9742, "loss": 0.3504, "lr": 6.70942729606127e-06, "epoch": 0.7780743173886265, "percentage": 38.9, "elapsed_time": "6:20:48", "remaining_time": "9:58:03", "throughput": 9136.5, "total_tokens": 208759776}762{"current_steps": 3795, "total_steps": 9742, "loss": 0.359, "lr": 6.701848898315985e-06, "epoch": 0.7791008006569493, "percentage": 38.96, "elapsed_time": "6:21:18", "remaining_time": "9:57:32", "throughput": 9136.22, "total_tokens": 209025456}763{"current_steps": 3800, "total_steps": 9742, "loss": 0.3576, "lr": 6.694266076068581e-06, "epoch": 0.780127283925272, "percentage": 39.01, "elapsed_time": "6:21:45", "remaining_time": "9:56:56", "throughput": 9137.27, "total_tokens": 209293040}764{"current_steps": 3805, "total_steps": 9742, "loss": 0.3633, "lr": 6.686678849033038e-06, "epoch": 0.7811537671935948, "percentage": 39.06, "elapsed_time": "6:22:12", "remaining_time": "9:56:22", "throughput": 9138.72, "total_tokens": 209577096}765{"current_steps": 3810, "total_steps": 9742, "loss": 0.3582, "lr": 6.679087236934787e-06, "epoch": 0.7821802504619175, "percentage": 39.11, "elapsed_time": "6:22:39", "remaining_time": "9:55:46", "throughput": 9139.99, "total_tokens": 209846704}766{"current_steps": 3815, "total_steps": 9742, "loss": 0.3913, "lr": 6.671491259510656e-06, "epoch": 0.7832067337302402, "percentage": 39.16, "elapsed_time": "6:23:14", "remaining_time": "9:55:24", "throughput": 9137.44, "total_tokens": 210109472}767{"current_steps": 3820, "total_steps": 9742, "loss": 0.3165, "lr": 6.663890936508828e-06, "epoch": 0.784233216998563, "percentage": 39.21, "elapsed_time": "6:23:40", "remaining_time": "9:54:48", "throughput": 9138.67, "total_tokens": 210378800}768{"current_steps": 3825, "total_steps": 9742, "loss": 0.3624, "lr": 6.656286287688779e-06, "epoch": 0.7852597002668856, "percentage": 39.26, "elapsed_time": "6:24:04", "remaining_time": "9:54:08", "throughput": 9140.48, "total_tokens": 210641960}769{"current_steps": 3830, "total_steps": 9742, "loss": 0.371, "lr": 6.648677332821234e-06, "epoch": 0.7862861835352084, "percentage": 39.31, "elapsed_time": "6:24:37", "remaining_time": "9:53:43", "throughput": 9140.48, "total_tokens": 210942376}770{"current_steps": 3835, "total_steps": 9742, "loss": 0.3753, "lr": 6.641064091688112e-06, "epoch": 0.7873126668035311, "percentage": 39.37, "elapsed_time": "6:25:07", "remaining_time": "9:53:12", "throughput": 9140.35, "total_tokens": 211210920}771{"current_steps": 3840, "total_steps": 9742, "loss": 0.3537, "lr": 6.6334465840824725e-06, "epoch": 0.7883391500718538, "percentage": 39.42, "elapsed_time": "6:25:39", "remaining_time": "9:52:44", "throughput": 9139.68, "total_tokens": 211487880}772{"current_steps": 3845, "total_steps": 9742, "loss": 0.3605, "lr": 6.625824829808475e-06, "epoch": 0.7893656333401765, "percentage": 39.47, "elapsed_time": "6:26:07", "remaining_time": "9:52:10", "throughput": 9139.74, "total_tokens": 211740576}773{"current_steps": 3850, "total_steps": 9742, "loss": 0.3477, "lr": 6.61819884868131e-06, "epoch": 0.7903921166084993, "percentage": 39.52, "elapsed_time": "6:26:38", "remaining_time": "9:51:42", "throughput": 9139.21, "total_tokens": 212013088}774{"current_steps": 3855, "total_steps": 9742, "loss": 0.3529, "lr": 6.610568660527164e-06, "epoch": 0.7914185998768221, "percentage": 39.57, "elapsed_time": "6:27:10", "remaining_time": "9:51:16", "throughput": 9138.29, "total_tokens": 212290080}775{"current_steps": 3860, "total_steps": 9742, "loss": 0.3526, "lr": 6.602934285183158e-06, "epoch": 0.7924450831451447, "percentage": 39.62, "elapsed_time": "6:27:42", "remaining_time": "9:50:48", "throughput": 9137.46, "total_tokens": 212560096}776{"current_steps": 3865, "total_steps": 9742, "loss": 0.3244, "lr": 6.5952957424973e-06, "epoch": 0.7934715664134675, "percentage": 39.67, "elapsed_time": "6:28:11", "remaining_time": "9:50:16", "throughput": 9138.14, "total_tokens": 212841408}777{"current_steps": 3870, "total_steps": 9742, "loss": 0.3564, "lr": 6.587653052328432e-06, "epoch": 0.7944980496817902, "percentage": 39.72, "elapsed_time": "6:28:39", "remaining_time": "9:49:43", "throughput": 9138.43, "total_tokens": 213105544}778{"current_steps": 3875, "total_steps": 9742, "loss": 0.3288, "lr": 6.580006234546178e-06, "epoch": 0.7955245329501129, "percentage": 39.78, "elapsed_time": "6:29:05", "remaining_time": "9:49:06", "throughput": 9139.16, "total_tokens": 213356416}779{"current_steps": 3880, "total_steps": 9742, "loss": 0.3477, "lr": 6.572355309030894e-06, "epoch": 0.7965510162184356, "percentage": 39.83, "elapsed_time": "6:29:42", "remaining_time": "9:48:46", "throughput": 9136.76, "total_tokens": 213636376}780{"current_steps": 3885, "total_steps": 9742, "loss": 0.3272, "lr": 6.564700295673616e-06, "epoch": 0.7975774994867584, "percentage": 39.88, "elapsed_time": "6:30:13", "remaining_time": "9:48:18", "throughput": 9136.52, "total_tokens": 213920072}781{"current_steps": 3890, "total_steps": 9742, "loss": 0.3657, "lr": 6.557041214376006e-06, "epoch": 0.798603982755081, "percentage": 39.93, "elapsed_time": "6:30:44", "remaining_time": "9:47:49", "throughput": 9136.61, "total_tokens": 214203952}782{"current_steps": 3895, "total_steps": 9742, "loss": 0.391, "lr": 6.549378085050302e-06, "epoch": 0.7996304660234038, "percentage": 39.98, "elapsed_time": "6:31:12", "remaining_time": "9:47:16", "throughput": 9137.46, "total_tokens": 214483056}783{"current_steps": 3900, "total_steps": 9742, "loss": 0.355, "lr": 6.541710927619268e-06, "epoch": 0.8006569492917266, "percentage": 40.03, "elapsed_time": "6:31:39", "remaining_time": "9:46:41", "throughput": 9138.09, "total_tokens": 214741424}784{"current_steps": 3905, "total_steps": 9742, "loss": 0.3683, "lr": 6.534039762016138e-06, "epoch": 0.8016834325600493, "percentage": 40.08, "elapsed_time": "6:32:07", "remaining_time": "9:46:08", "throughput": 9139.83, "total_tokens": 215039480}785{"current_steps": 3910, "total_steps": 9742, "loss": 0.3612, "lr": 6.526364608184569e-06, "epoch": 0.802709915828372, "percentage": 40.14, "elapsed_time": "6:32:35", "remaining_time": "9:45:34", "throughput": 9141.15, "total_tokens": 215322448}786{"current_steps": 3915, "total_steps": 9742, "loss": 0.3403, "lr": 6.518685486078584e-06, "epoch": 0.8037363990966947, "percentage": 40.19, "elapsed_time": "6:33:00", "remaining_time": "9:44:57", "throughput": 9143.04, "total_tokens": 215601792}787{"current_steps": 3920, "total_steps": 9742, "loss": 0.3508, "lr": 6.5110024156625254e-06, "epoch": 0.8047628823650175, "percentage": 40.24, "elapsed_time": "6:33:34", "remaining_time": "9:44:32", "throughput": 9141.57, "total_tokens": 215875040}788{"current_steps": 3925, "total_steps": 9742, "loss": 0.3902, "lr": 6.503315416910998e-06, "epoch": 0.8057893656333401, "percentage": 40.29, "elapsed_time": "6:33:58", "remaining_time": "9:43:52", "throughput": 9144.63, "total_tokens": 216162656}789{"current_steps": 3930, "total_steps": 9742, "loss": 0.366, "lr": 6.495624509808821e-06, "epoch": 0.8068158489016629, "percentage": 40.34, "elapsed_time": "6:34:30", "remaining_time": "9:43:26", "throughput": 9142.95, "total_tokens": 216419936}790{"current_steps": 3935, "total_steps": 9742, "loss": 0.3869, "lr": 6.487929714350977e-06, "epoch": 0.8078423321699856, "percentage": 40.39, "elapsed_time": "6:34:57", "remaining_time": "9:42:51", "throughput": 9143.64, "total_tokens": 216682184}791{"current_steps": 3940, "total_steps": 9742, "loss": 0.3611, "lr": 6.48023105054255e-06, "epoch": 0.8088688154383084, "percentage": 40.44, "elapsed_time": "6:35:29", "remaining_time": "9:42:24", "throughput": 9142.28, "total_tokens": 216945712}792{"current_steps": 3945, "total_steps": 9742, "loss": 0.3651, "lr": 6.472528538398693e-06, "epoch": 0.8098952987066311, "percentage": 40.49, "elapsed_time": "6:36:08", "remaining_time": "9:42:06", "throughput": 9140.51, "total_tokens": 217252176}793{"current_steps": 3950, "total_steps": 9742, "loss": 0.3694, "lr": 6.4648221979445504e-06, "epoch": 0.8109217819749538, "percentage": 40.55, "elapsed_time": "6:36:37", "remaining_time": "9:41:35", "throughput": 9139.83, "total_tokens": 217507008}794{"current_steps": 3955, "total_steps": 9742, "loss": 0.3626, "lr": 6.457112049215228e-06, "epoch": 0.8119482652432766, "percentage": 40.6, "elapsed_time": "6:37:07", "remaining_time": "9:41:04", "throughput": 9140.49, "total_tokens": 217795272}795{"current_steps": 3960, "total_steps": 9742, "loss": 0.3435, "lr": 6.449398112255735e-06, "epoch": 0.8129747485115992, "percentage": 40.65, "elapsed_time": "6:37:38", "remaining_time": "9:40:35", "throughput": 9140.35, "total_tokens": 218074632}796{"current_steps": 3965, "total_steps": 9742, "loss": 0.3645, "lr": 6.441680407120919e-06, "epoch": 0.814001231779922, "percentage": 40.7, "elapsed_time": "6:38:09", "remaining_time": "9:40:07", "throughput": 9140.04, "total_tokens": 218352096}797{"current_steps": 3970, "total_steps": 9742, "loss": 0.3698, "lr": 6.433958953875434e-06, "epoch": 0.8150277150482447, "percentage": 40.75, "elapsed_time": "6:38:39", "remaining_time": "9:39:37", "throughput": 9140.4, "total_tokens": 218637896}798{"current_steps": 3975, "total_steps": 9742, "loss": 0.3566, "lr": 6.426233772593673e-06, "epoch": 0.8160541983165674, "percentage": 40.8, "elapsed_time": "6:39:07", "remaining_time": "9:39:03", "throughput": 9142.06, "total_tokens": 218927616}799{"current_steps": 3980, "total_steps": 9742, "loss": 0.3887, "lr": 6.418504883359723e-06, "epoch": 0.8170806815848901, "percentage": 40.85, "elapsed_time": "6:39:43", "remaining_time": "9:38:41", "throughput": 9140.93, "total_tokens": 219228256}800{"current_steps": 3985, "total_steps": 9742, "loss": 0.3621, "lr": 6.410772306267311e-06, "epoch": 0.8181071648532129, "percentage": 40.91, "elapsed_time": "6:40:11", "remaining_time": "9:38:08", "throughput": 9142.05, "total_tokens": 219516392}801{"current_steps": 3990, "total_steps": 9742, "loss": 0.3616, "lr": 6.40303606141975e-06, "epoch": 0.8191336481215357, "percentage": 40.96, "elapsed_time": "6:40:48", "remaining_time": "9:37:47", "throughput": 9139.75, "total_tokens": 219793448}802{"current_steps": 3995, "total_steps": 9742, "loss": 0.332, "lr": 6.395296168929892e-06, "epoch": 0.8201601313898583, "percentage": 41.01, "elapsed_time": "6:41:24", "remaining_time": "9:37:26", "throughput": 9137.72, "total_tokens": 220077520}803{"current_steps": 4000, "total_steps": 9742, "loss": 0.3656, "lr": 6.38755264892007e-06, "epoch": 0.8211866146581811, "percentage": 41.06, "elapsed_time": "6:41:52", "remaining_time": "9:36:53", "throughput": 9138.94, "total_tokens": 220365960}804{"current_steps": 4005, "total_steps": 9742, "loss": 0.3748, "lr": 6.379805521522049e-06, "epoch": 0.8222130979265038, "percentage": 41.11, "elapsed_time": "6:42:16", "remaining_time": "9:36:14", "throughput": 9141.27, "total_tokens": 220635248}805{"current_steps": 4010, "total_steps": 9742, "loss": 0.3686, "lr": 6.37205480687697e-06, "epoch": 0.8232395811948265, "percentage": 41.16, "elapsed_time": "6:42:46", "remaining_time": "9:35:44", "throughput": 9140.75, "total_tokens": 220898720}806{"current_steps": 4015, "total_steps": 9742, "loss": 0.3608, "lr": 6.364300525135302e-06, "epoch": 0.8242660644631492, "percentage": 41.21, "elapsed_time": "6:43:23", "remaining_time": "9:35:24", "throughput": 9137.58, "total_tokens": 221162192}807{"current_steps": 4020, "total_steps": 9742, "loss": 0.3327, "lr": 6.356542696456787e-06, "epoch": 0.825292547731472, "percentage": 41.26, "elapsed_time": "6:43:53", "remaining_time": "9:34:52", "throughput": 9137.54, "total_tokens": 221430888}808{"current_steps": 4025, "total_steps": 9742, "loss": 0.3421, "lr": 6.348781341010394e-06, "epoch": 0.8263190309997948, "percentage": 41.32, "elapsed_time": "6:44:25", "remaining_time": "9:34:25", "throughput": 9136.64, "total_tokens": 221702136}809{"current_steps": 4030, "total_steps": 9742, "loss": 0.3865, "lr": 6.341016478974249e-06, "epoch": 0.8273455142681174, "percentage": 41.37, "elapsed_time": "6:44:54", "remaining_time": "9:33:54", "throughput": 9137.5, "total_tokens": 221994600}810{"current_steps": 4035, "total_steps": 9742, "loss": 0.3407, "lr": 6.3332481305356065e-06, "epoch": 0.8283719975364402, "percentage": 41.42, "elapsed_time": "6:45:31", "remaining_time": "9:33:33", "throughput": 9134.79, "total_tokens": 222262744}811{"current_steps": 4040, "total_steps": 9742, "loss": 0.3568, "lr": 6.325476315890779e-06, "epoch": 0.8293984808047629, "percentage": 41.47, "elapsed_time": "6:46:01", "remaining_time": "9:33:03", "throughput": 9135.14, "total_tokens": 222542944}812{"current_steps": 4045, "total_steps": 9742, "loss": 0.3459, "lr": 6.317701055245091e-06, "epoch": 0.8304249640730856, "percentage": 41.52, "elapsed_time": "6:46:35", "remaining_time": "9:32:38", "throughput": 9133.31, "total_tokens": 222810936}813{"current_steps": 4050, "total_steps": 9742, "loss": 0.3593, "lr": 6.309922368812828e-06, "epoch": 0.8314514473414083, "percentage": 41.57, "elapsed_time": "6:47:03", "remaining_time": "9:32:05", "throughput": 9134.26, "total_tokens": 223086912}814{"current_steps": 4055, "total_steps": 9742, "loss": 0.3693, "lr": 6.3021402768171794e-06, "epoch": 0.8324779306097311, "percentage": 41.62, "elapsed_time": "6:47:32", "remaining_time": "9:31:34", "throughput": 9135.64, "total_tokens": 223392680}815{"current_steps": 4060, "total_steps": 9742, "loss": 0.3632, "lr": 6.29435479949019e-06, "epoch": 0.8335044138780537, "percentage": 41.68, "elapsed_time": "6:48:04", "remaining_time": "9:31:05", "throughput": 9135.77, "total_tokens": 223682200}816{"current_steps": 4065, "total_steps": 9742, "loss": 0.3419, "lr": 6.286565957072704e-06, "epoch": 0.8345308971463765, "percentage": 41.73, "elapsed_time": "6:48:35", "remaining_time": "9:30:37", "throughput": 9134.8, "total_tokens": 223943144}817{"current_steps": 4070, "total_steps": 9742, "loss": 0.3703, "lr": 6.278773769814319e-06, "epoch": 0.8355573804146993, "percentage": 41.78, "elapsed_time": "6:49:10", "remaining_time": "9:30:13", "throughput": 9132.82, "total_tokens": 224211104}818{"current_steps": 4075, "total_steps": 9742, "loss": 0.3547, "lr": 6.270978257973322e-06, "epoch": 0.836583863683022, "percentage": 41.83, "elapsed_time": "6:49:37", "remaining_time": "9:29:39", "throughput": 9134.11, "total_tokens": 224492344}819{"current_steps": 4080, "total_steps": 9742, "loss": 0.3776, "lr": 6.263179441816649e-06, "epoch": 0.8376103469513447, "percentage": 41.88, "elapsed_time": "6:50:08", "remaining_time": "9:29:10", "throughput": 9133.63, "total_tokens": 224763936}820{"current_steps": 4085, "total_steps": 9742, "loss": 0.3227, "lr": 6.2553773416198224e-06, "epoch": 0.8386368302196674, "percentage": 41.93, "elapsed_time": "6:50:31", "remaining_time": "9:28:30", "throughput": 9136.84, "total_tokens": 225052864}821{"current_steps": 4090, "total_steps": 9742, "loss": 0.3462, "lr": 6.247571977666907e-06, "epoch": 0.8396633134879902, "percentage": 41.98, "elapsed_time": "6:51:01", "remaining_time": "9:27:59", "throughput": 9137.35, "total_tokens": 225340472}822{"current_steps": 4095, "total_steps": 9742, "loss": 0.3682, "lr": 6.239763370250447e-06, "epoch": 0.8406897967563128, "percentage": 42.03, "elapsed_time": "6:51:31", "remaining_time": "9:27:29", "throughput": 9138.25, "total_tokens": 225637176}823{"current_steps": 4100, "total_steps": 9742, "loss": 0.3557, "lr": 6.231951539671424e-06, "epoch": 0.8417162800246356, "percentage": 42.09, "elapsed_time": "6:52:10", "remaining_time": "9:27:12", "throughput": 9135.92, "total_tokens": 225938776}824{"current_steps": 4105, "total_steps": 9742, "loss": 0.366, "lr": 6.2241365062391965e-06, "epoch": 0.8427427632929583, "percentage": 42.14, "elapsed_time": "6:52:37", "remaining_time": "9:26:37", "throughput": 9135.91, "total_tokens": 226184160}825{"current_steps": 4110, "total_steps": 9742, "loss": 0.3732, "lr": 6.2163182902714505e-06, "epoch": 0.843769246561281, "percentage": 42.19, "elapsed_time": "6:53:03", "remaining_time": "9:26:01", "throughput": 9138.04, "total_tokens": 226474368}826{"current_steps": 4115, "total_steps": 9742, "loss": 0.3479, "lr": 6.20849691209415e-06, "epoch": 0.8447957298296038, "percentage": 42.24, "elapsed_time": "6:53:33", "remaining_time": "9:25:30", "throughput": 9138.72, "total_tokens": 226761256}827{"current_steps": 4120, "total_steps": 9742, "loss": 0.3834, "lr": 6.20067239204147e-06, "epoch": 0.8458222130979265, "percentage": 42.29, "elapsed_time": "6:54:03", "remaining_time": "9:25:00", "throughput": 9138.77, "total_tokens": 227038920}828{"current_steps": 4125, "total_steps": 9742, "loss": 0.372, "lr": 6.192844750455766e-06, "epoch": 0.8468486963662493, "percentage": 42.34, "elapsed_time": "6:54:31", "remaining_time": "9:24:27", "throughput": 9140.2, "total_tokens": 227330208}829{"current_steps": 4130, "total_steps": 9742, "loss": 0.3276, "lr": 6.1850140076875e-06, "epoch": 0.8478751796345719, "percentage": 42.39, "elapsed_time": "6:54:59", "remaining_time": "9:23:54", "throughput": 9141.42, "total_tokens": 227618504}830{"current_steps": 4135, "total_steps": 9742, "loss": 0.3419, "lr": 6.1771801840952e-06, "epoch": 0.8489016629028947, "percentage": 42.45, "elapsed_time": "6:55:35", "remaining_time": "9:23:31", "throughput": 9139.63, "total_tokens": 227899664}831{"current_steps": 4140, "total_steps": 9742, "loss": 0.3732, "lr": 6.169343300045405e-06, "epoch": 0.8499281461712174, "percentage": 42.5, "elapsed_time": "6:56:06", "remaining_time": "9:23:03", "throughput": 9138.41, "total_tokens": 228156872}832{"current_steps": 4145, "total_steps": 9742, "loss": 0.3452, "lr": 6.161503375912606e-06, "epoch": 0.8509546294395401, "percentage": 42.55, "elapsed_time": "6:56:37", "remaining_time": "9:22:34", "throughput": 9138.16, "total_tokens": 228431624}833{"current_steps": 4150, "total_steps": 9742, "loss": 0.3761, "lr": 6.153660432079205e-06, "epoch": 0.8519811127078628, "percentage": 42.6, "elapsed_time": "6:57:02", "remaining_time": "9:21:57", "throughput": 9139.79, "total_tokens": 228700712}834{"current_steps": 4155, "total_steps": 9742, "loss": 0.3628, "lr": 6.145814488935448e-06, "epoch": 0.8530075959761856, "percentage": 42.65, "elapsed_time": "6:57:38", "remaining_time": "9:21:34", "throughput": 9137.53, "total_tokens": 228972288}835{"current_steps": 4160, "total_steps": 9742, "loss": 0.3947, "lr": 6.137965566879379e-06, "epoch": 0.8540340792445084, "percentage": 42.7, "elapsed_time": "6:58:12", "remaining_time": "9:21:09", "throughput": 9136.92, "total_tokens": 229265992}836{"current_steps": 4165, "total_steps": 9742, "loss": 0.3168, "lr": 6.130113686316792e-06, "epoch": 0.855060562512831, "percentage": 42.75, "elapsed_time": "6:58:37", "remaining_time": "9:20:32", "throughput": 9138.42, "total_tokens": 229530032}837{"current_steps": 4170, "total_steps": 9742, "loss": 0.3576, "lr": 6.122258867661165e-06, "epoch": 0.8560870457811538, "percentage": 42.8, "elapsed_time": "6:59:07", "remaining_time": "9:20:02", "throughput": 9138.44, "total_tokens": 229809528}838{"current_steps": 4175, "total_steps": 9742, "loss": 0.3762, "lr": 6.114401131333624e-06, "epoch": 0.8571135290494765, "percentage": 42.86, "elapsed_time": "6:59:41", "remaining_time": "9:19:36", "throughput": 9137.74, "total_tokens": 230098472}839{"current_steps": 4180, "total_steps": 9742, "loss": 0.3855, "lr": 6.1065404977628715e-06, "epoch": 0.8581400123177992, "percentage": 42.91, "elapsed_time": "7:00:03", "remaining_time": "9:18:56", "throughput": 9140.51, "total_tokens": 230375152}840{"current_steps": 4185, "total_steps": 9742, "loss": 0.352, "lr": 6.098676987385147e-06, "epoch": 0.8591664955861219, "percentage": 42.96, "elapsed_time": "7:00:34", "remaining_time": "9:18:27", "throughput": 9140.3, "total_tokens": 230650608}841{"current_steps": 4190, "total_steps": 9742, "loss": 0.3421, "lr": 6.090810620644168e-06, "epoch": 0.8601929788544447, "percentage": 43.01, "elapsed_time": "7:01:03", "remaining_time": "9:17:55", "throughput": 9141.08, "total_tokens": 230931584}842{"current_steps": 4195, "total_steps": 9742, "loss": 0.3204, "lr": 6.082941417991077e-06, "epoch": 0.8612194621227675, "percentage": 43.06, "elapsed_time": "7:01:32", "remaining_time": "9:17:24", "throughput": 9140.71, "total_tokens": 231192896}843{"current_steps": 4200, "total_steps": 9742, "loss": 0.3438, "lr": 6.075069399884392e-06, "epoch": 0.8622459453910901, "percentage": 43.11, "elapsed_time": "7:01:58", "remaining_time": "9:16:48", "throughput": 9142.2, "total_tokens": 231470984}844{"current_steps": 4205, "total_steps": 9742, "loss": 0.3527, "lr": 6.06719458678995e-06, "epoch": 0.8632724286594129, "percentage": 43.16, "elapsed_time": "7:02:31", "remaining_time": "9:16:22", "throughput": 9139.75, "total_tokens": 231706624}845{"current_steps": 4210, "total_steps": 9742, "loss": 0.3826, "lr": 6.0593169991808535e-06, "epoch": 0.8642989119277356, "percentage": 43.21, "elapsed_time": "7:02:59", "remaining_time": "9:15:49", "throughput": 9141.43, "total_tokens": 232005912}846{"current_steps": 4215, "total_steps": 9742, "loss": 0.3653, "lr": 6.051436657537415e-06, "epoch": 0.8653253951960583, "percentage": 43.27, "elapsed_time": "7:03:35", "remaining_time": "9:15:27", "throughput": 9139.57, "total_tokens": 232290616}847{"current_steps": 4220, "total_steps": 9742, "loss": 0.3399, "lr": 6.0435535823471145e-06, "epoch": 0.866351878464381, "percentage": 43.32, "elapsed_time": "7:04:04", "remaining_time": "9:14:55", "throughput": 9139.85, "total_tokens": 232562712}848{"current_steps": 4225, "total_steps": 9742, "loss": 0.3243, "lr": 6.035667794104532e-06, "epoch": 0.8673783617327038, "percentage": 43.37, "elapsed_time": "7:04:33", "remaining_time": "9:14:22", "throughput": 9139.81, "total_tokens": 232819392}849{"current_steps": 4230, "total_steps": 9742, "loss": 0.3359, "lr": 6.027779313311306e-06, "epoch": 0.8684048450010264, "percentage": 43.42, "elapsed_time": "7:04:58", "remaining_time": "9:13:46", "throughput": 9140.5, "total_tokens": 233066672}850{"current_steps": 4235, "total_steps": 9742, "loss": 0.3615, "lr": 6.01988816047607e-06, "epoch": 0.8694313282693492, "percentage": 43.47, "elapsed_time": "7:05:28", "remaining_time": "9:13:16", "throughput": 9140.91, "total_tokens": 233354360}851{"current_steps": 4240, "total_steps": 9742, "loss": 0.3598, "lr": 6.0119943561144075e-06, "epoch": 0.870457811537672, "percentage": 43.52, "elapsed_time": "7:06:01", "remaining_time": "9:12:49", "throughput": 9140.3, "total_tokens": 233639680}852{"current_steps": 4245, "total_steps": 9742, "loss": 0.3367, "lr": 6.004097920748798e-06, "epoch": 0.8714842948059947, "percentage": 43.57, "elapsed_time": "7:06:34", "remaining_time": "9:12:23", "throughput": 9138.86, "total_tokens": 233904392}853{"current_steps": 4250, "total_steps": 9742, "loss": 0.3104, "lr": 5.996198874908554e-06, "epoch": 0.8725107780743174, "percentage": 43.63, "elapsed_time": "7:07:06", "remaining_time": "9:11:55", "throughput": 9138.29, "total_tokens": 234182016}854{"current_steps": 4255, "total_steps": 9742, "loss": 0.3649, "lr": 5.988297239129783e-06, "epoch": 0.8735372613426401, "percentage": 43.68, "elapsed_time": "7:07:33", "remaining_time": "9:11:21", "throughput": 9138.15, "total_tokens": 234427728}855{"current_steps": 4260, "total_steps": 9742, "loss": 0.3508, "lr": 5.980393033955319e-06, "epoch": 0.8745637446109629, "percentage": 43.73, "elapsed_time": "7:08:00", "remaining_time": "9:10:46", "throughput": 9138.28, "total_tokens": 234674736}856{"current_steps": 4265, "total_steps": 9742, "loss": 0.3664, "lr": 5.97248627993468e-06, "epoch": 0.8755902278792855, "percentage": 43.78, "elapsed_time": "7:08:26", "remaining_time": "9:10:11", "throughput": 9139.96, "total_tokens": 234954576}857{"current_steps": 4270, "total_steps": 9742, "loss": 0.3562, "lr": 5.96457699762401e-06, "epoch": 0.8766167111476083, "percentage": 43.83, "elapsed_time": "7:08:55", "remaining_time": "9:09:39", "throughput": 9140.97, "total_tokens": 235245616}858{"current_steps": 4275, "total_steps": 9742, "loss": 0.3662, "lr": 5.956665207586023e-06, "epoch": 0.877643194415931, "percentage": 43.88, "elapsed_time": "7:09:28", "remaining_time": "9:09:12", "throughput": 9140.46, "total_tokens": 235531600}859{"current_steps": 4280, "total_steps": 9742, "loss": 0.3277, "lr": 5.948750930389958e-06, "epoch": 0.8786696776842537, "percentage": 43.93, "elapsed_time": "7:10:04", "remaining_time": "9:08:50", "throughput": 9138.02, "total_tokens": 235799912}860{"current_steps": 4285, "total_steps": 9742, "loss": 0.3503, "lr": 5.940834186611515e-06, "epoch": 0.8796961609525765, "percentage": 43.98, "elapsed_time": "7:10:33", "remaining_time": "9:08:19", "throughput": 9139.0, "total_tokens": 236092840}861{"current_steps": 4290, "total_steps": 9742, "loss": 0.3668, "lr": 5.932914996832809e-06, "epoch": 0.8807226442208992, "percentage": 44.04, "elapsed_time": "7:10:56", "remaining_time": "9:07:40", "throughput": 9142.24, "total_tokens": 236385968}862{"current_steps": 4295, "total_steps": 9742, "loss": 0.3486, "lr": 5.9249933816423166e-06, "epoch": 0.881749127489222, "percentage": 44.09, "elapsed_time": "7:11:30", "remaining_time": "9:07:15", "throughput": 9141.31, "total_tokens": 236675368}863{"current_steps": 4300, "total_steps": 9742, "loss": 0.3103, "lr": 5.917069361634815e-06, "epoch": 0.8827756107575446, "percentage": 44.14, "elapsed_time": "7:12:03", "remaining_time": "9:06:48", "throughput": 9139.52, "total_tokens": 236929368}864{"current_steps": 4305, "total_steps": 9742, "loss": 0.3519, "lr": 5.909142957411337e-06, "epoch": 0.8838020940258674, "percentage": 44.19, "elapsed_time": "7:12:30", "remaining_time": "9:06:14", "throughput": 9140.42, "total_tokens": 237202640}865{"current_steps": 4310, "total_steps": 9742, "loss": 0.3813, "lr": 5.901214189579112e-06, "epoch": 0.8848285772941901, "percentage": 44.24, "elapsed_time": "7:12:58", "remaining_time": "9:05:40", "throughput": 9141.31, "total_tokens": 237474408}866{"current_steps": 4315, "total_steps": 9742, "loss": 0.3415, "lr": 5.893283078751516e-06, "epoch": 0.8858550605625128, "percentage": 44.29, "elapsed_time": "7:13:27", "remaining_time": "9:05:09", "throughput": 9141.72, "total_tokens": 237752096}867{"current_steps": 4320, "total_steps": 9742, "loss": 0.3499, "lr": 5.885349645548018e-06, "epoch": 0.8868815438308355, "percentage": 44.34, "elapsed_time": "7:13:56", "remaining_time": "9:04:38", "throughput": 9141.26, "total_tokens": 238009976}868{"current_steps": 4325, "total_steps": 9742, "loss": 0.366, "lr": 5.877413910594119e-06, "epoch": 0.8879080270991583, "percentage": 44.4, "elapsed_time": "7:14:24", "remaining_time": "9:04:05", "throughput": 9141.7, "total_tokens": 238274760}869{"current_steps": 4330, "total_steps": 9742, "loss": 0.3539, "lr": 5.8694758945213084e-06, "epoch": 0.8889345103674811, "percentage": 44.45, "elapsed_time": "7:14:58", "remaining_time": "9:03:40", "throughput": 9140.14, "total_tokens": 238544064}870{"current_steps": 4335, "total_steps": 9742, "loss": 0.3577, "lr": 5.8615356179670055e-06, "epoch": 0.8899609936358037, "percentage": 44.5, "elapsed_time": "7:15:27", "remaining_time": "9:03:08", "throughput": 9139.54, "total_tokens": 238789408}871{"current_steps": 4340, "total_steps": 9742, "loss": 0.3393, "lr": 5.8535931015745065e-06, "epoch": 0.8909874769041265, "percentage": 44.55, "elapsed_time": "7:15:58", "remaining_time": "9:02:39", "throughput": 9139.96, "total_tokens": 239089272}872{"current_steps": 4345, "total_steps": 9742, "loss": 0.3757, "lr": 5.8456483659929305e-06, "epoch": 0.8920139601724492, "percentage": 44.6, "elapsed_time": "7:16:21", "remaining_time": "9:01:59", "throughput": 9143.19, "total_tokens": 239378008}873{"current_steps": 4350, "total_steps": 9742, "loss": 0.3553, "lr": 5.837701431877166e-06, "epoch": 0.8930404434407719, "percentage": 44.65, "elapsed_time": "7:16:53", "remaining_time": "9:01:32", "throughput": 9141.08, "total_tokens": 239617848}874{"current_steps": 4355, "total_steps": 9742, "loss": 0.3451, "lr": 5.8297523198878184e-06, "epoch": 0.8940669267090946, "percentage": 44.7, "elapsed_time": "7:17:20", "remaining_time": "9:00:58", "throughput": 9142.01, "total_tokens": 239892088}875{"current_steps": 4360, "total_steps": 9742, "loss": 0.3561, "lr": 5.821801050691153e-06, "epoch": 0.8950934099774174, "percentage": 44.75, "elapsed_time": "7:17:54", "remaining_time": "9:00:32", "throughput": 9141.66, "total_tokens": 240189008}876{"current_steps": 4365, "total_steps": 9742, "loss": 0.3503, "lr": 5.813847644959044e-06, "epoch": 0.89611989324574, "percentage": 44.81, "elapsed_time": "7:18:25", "remaining_time": "9:00:04", "throughput": 9141.31, "total_tokens": 240466432}877{"current_steps": 4370, "total_steps": 9742, "loss": 0.3623, "lr": 5.805892123368923e-06, "epoch": 0.8971463765140628, "percentage": 44.86, "elapsed_time": "7:18:53", "remaining_time": "8:59:31", "throughput": 9141.88, "total_tokens": 240739368}878{"current_steps": 4375, "total_steps": 9742, "loss": 0.3253, "lr": 5.797934506603717e-06, "epoch": 0.8981728597823856, "percentage": 44.91, "elapsed_time": "7:19:28", "remaining_time": "8:59:07", "throughput": 9140.62, "total_tokens": 241024608}879{"current_steps": 4380, "total_steps": 9742, "loss": 0.334, "lr": 5.789974815351806e-06, "epoch": 0.8991993430507083, "percentage": 44.96, "elapsed_time": "7:19:59", "remaining_time": "8:58:38", "throughput": 9140.26, "total_tokens": 241298584}880{"current_steps": 4385, "total_steps": 9742, "loss": 0.3743, "lr": 5.78201307030696e-06, "epoch": 0.900225826319031, "percentage": 45.01, "elapsed_time": "7:20:24", "remaining_time": "8:58:01", "throughput": 9141.66, "total_tokens": 241560272}881{"current_steps": 4390, "total_steps": 9742, "loss": 0.3408, "lr": 5.77404929216829e-06, "epoch": 0.9012523095873537, "percentage": 45.06, "elapsed_time": "7:20:57", "remaining_time": "8:57:35", "throughput": 9140.35, "total_tokens": 241829760}882{"current_steps": 4395, "total_steps": 9742, "loss": 0.3628, "lr": 5.766083501640191e-06, "epoch": 0.9022787928556765, "percentage": 45.11, "elapsed_time": "7:21:26", "remaining_time": "8:57:03", "throughput": 9140.85, "total_tokens": 242105472}883{"current_steps": 4400, "total_steps": 9742, "loss": 0.3148, "lr": 5.75811571943229e-06, "epoch": 0.9033052761239991, "percentage": 45.17, "elapsed_time": "7:21:53", "remaining_time": "8:56:29", "throughput": 9142.41, "total_tokens": 242397152}884{"current_steps": 4405, "total_steps": 9742, "loss": 0.3208, "lr": 5.750145966259393e-06, "epoch": 0.9043317593923219, "percentage": 45.22, "elapsed_time": "7:22:19", "remaining_time": "8:55:54", "throughput": 9143.95, "total_tokens": 242676416}885{"current_steps": 4410, "total_steps": 9742, "loss": 0.3402, "lr": 5.742174262841431e-06, "epoch": 0.9053582426606447, "percentage": 45.27, "elapsed_time": "7:22:52", "remaining_time": "8:55:27", "throughput": 9143.36, "total_tokens": 242961400}886{"current_steps": 4415, "total_steps": 9742, "loss": 0.3541, "lr": 5.734200629903403e-06, "epoch": 0.9063847259289673, "percentage": 45.32, "elapsed_time": "7:23:20", "remaining_time": "8:54:54", "throughput": 9144.52, "total_tokens": 243244336}887{"current_steps": 4420, "total_steps": 9742, "loss": 0.3553, "lr": 5.7262250881753255e-06, "epoch": 0.9074112091972901, "percentage": 45.37, "elapsed_time": "7:23:52", "remaining_time": "8:54:27", "throughput": 9143.94, "total_tokens": 243526664}888{"current_steps": 4425, "total_steps": 9742, "loss": 0.3604, "lr": 5.718247658392178e-06, "epoch": 0.9084376924656128, "percentage": 45.42, "elapsed_time": "7:24:25", "remaining_time": "8:54:00", "throughput": 9143.46, "total_tokens": 243815632}889{"current_steps": 4430, "total_steps": 9742, "loss": 0.3548, "lr": 5.710268361293848e-06, "epoch": 0.9094641757339356, "percentage": 45.47, "elapsed_time": "7:24:58", "remaining_time": "8:53:34", "throughput": 9143.35, "total_tokens": 244115704}890{"current_steps": 4435, "total_steps": 9742, "loss": 0.3352, "lr": 5.70228721762508e-06, "epoch": 0.9104906590022582, "percentage": 45.52, "elapsed_time": "7:25:30", "remaining_time": "8:53:06", "throughput": 9142.39, "total_tokens": 244384448}891{"current_steps": 4440, "total_steps": 9742, "loss": 0.3158, "lr": 5.694304248135413e-06, "epoch": 0.911517142270581, "percentage": 45.58, "elapsed_time": "7:25:59", "remaining_time": "8:52:35", "throughput": 9141.94, "total_tokens": 244637632}892{"current_steps": 4445, "total_steps": 9742, "loss": 0.3426, "lr": 5.686319473579141e-06, "epoch": 0.9125436255389037, "percentage": 45.63, "elapsed_time": "7:26:24", "remaining_time": "8:51:59", "throughput": 9143.77, "total_tokens": 244915776}893{"current_steps": 4450, "total_steps": 9742, "loss": 0.3641, "lr": 5.678332914715242e-06, "epoch": 0.9135701088072264, "percentage": 45.68, "elapsed_time": "7:26:59", "remaining_time": "8:51:34", "throughput": 9141.85, "total_tokens": 245180312}894{"current_steps": 4455, "total_steps": 9742, "loss": 0.3465, "lr": 5.670344592307342e-06, "epoch": 0.9145965920755492, "percentage": 45.73, "elapsed_time": "7:27:20", "remaining_time": "8:50:52", "throughput": 9144.65, "total_tokens": 245445592}895{"current_steps": 4460, "total_steps": 9742, "loss": 0.3685, "lr": 5.662354527123646e-06, "epoch": 0.9156230753438719, "percentage": 45.78, "elapsed_time": "7:27:56", "remaining_time": "8:50:29", "throughput": 9142.39, "total_tokens": 245714200}896{"current_steps": 4465, "total_steps": 9742, "loss": 0.3912, "lr": 5.6543627399368905e-06, "epoch": 0.9166495586121947, "percentage": 45.83, "elapsed_time": "7:28:32", "remaining_time": "8:50:06", "throughput": 9140.9, "total_tokens": 246006256}897{"current_steps": 4470, "total_steps": 9742, "loss": 0.3612, "lr": 5.646369251524292e-06, "epoch": 0.9176760418805173, "percentage": 45.88, "elapsed_time": "7:29:01", "remaining_time": "8:49:35", "throughput": 9142.1, "total_tokens": 246302064}898{"current_steps": 4475, "total_steps": 9742, "loss": 0.376, "lr": 5.6383740826674856e-06, "epoch": 0.9187025251488401, "percentage": 45.94, "elapsed_time": "7:29:29", "remaining_time": "8:49:02", "throughput": 9142.88, "total_tokens": 246580688}899{"current_steps": 4480, "total_steps": 9742, "loss": 0.341, "lr": 5.630377254152478e-06, "epoch": 0.9197290084171628, "percentage": 45.99, "elapsed_time": "7:30:02", "remaining_time": "8:48:35", "throughput": 9141.73, "total_tokens": 246846144}900{"current_steps": 4485, "total_steps": 9742, "loss": 0.3759, "lr": 5.622378786769591e-06, "epoch": 0.9207554916854855, "percentage": 46.04, "elapsed_time": "7:30:29", "remaining_time": "8:48:02", "throughput": 9142.67, "total_tokens": 247123392}901{"current_steps": 4490, "total_steps": 9742, "loss": 0.3566, "lr": 5.614378701313405e-06, "epoch": 0.9217819749538082, "percentage": 46.09, "elapsed_time": "7:30:55", "remaining_time": "8:47:26", "throughput": 9143.53, "total_tokens": 247381704}902{"current_steps": 4495, "total_steps": 9742, "loss": 0.3729, "lr": 5.606377018582708e-06, "epoch": 0.922808458222131, "percentage": 46.14, "elapsed_time": "7:31:21", "remaining_time": "8:46:52", "throughput": 9144.01, "total_tokens": 247636400}903{"current_steps": 4500, "total_steps": 9742, "loss": 0.3361, "lr": 5.598373759380445e-06, "epoch": 0.9238349414904538, "percentage": 46.19, "elapsed_time": "7:31:47", "remaining_time": "8:46:17", "throughput": 9145.3, "total_tokens": 247908904}904{"current_steps": 4505, "total_steps": 9742, "loss": 0.3552, "lr": 5.590368944513649e-06, "epoch": 0.9248614247587764, "percentage": 46.24, "elapsed_time": "7:32:13", "remaining_time": "8:45:42", "throughput": 9147.0, "total_tokens": 248194040}905{"current_steps": 4510, "total_steps": 9742, "loss": 0.3548, "lr": 5.582362594793409e-06, "epoch": 0.9258879080270992, "percentage": 46.29, "elapsed_time": "7:32:50", "remaining_time": "8:45:20", "throughput": 9145.29, "total_tokens": 248484184}906{"current_steps": 4515, "total_steps": 9742, "loss": 0.3224, "lr": 5.5743547310347975e-06, "epoch": 0.9269143912954219, "percentage": 46.35, "elapsed_time": "7:33:26", "remaining_time": "8:44:57", "throughput": 9143.08, "total_tokens": 248752656}907{"current_steps": 4520, "total_steps": 9742, "loss": 0.3429, "lr": 5.566345374056825e-06, "epoch": 0.9279408745637446, "percentage": 46.4, "elapsed_time": "7:34:01", "remaining_time": "8:44:32", "throughput": 9141.39, "total_tokens": 249026640}908{"current_steps": 4525, "total_steps": 9742, "loss": 0.3472, "lr": 5.5583345446823856e-06, "epoch": 0.9289673578320673, "percentage": 46.45, "elapsed_time": "7:34:27", "remaining_time": "8:43:57", "throughput": 9142.88, "total_tokens": 249304304}909{"current_steps": 4530, "total_steps": 9742, "loss": 0.3424, "lr": 5.550322263738197e-06, "epoch": 0.9299938411003901, "percentage": 46.5, "elapsed_time": "7:34:58", "remaining_time": "8:43:28", "throughput": 9142.21, "total_tokens": 249571072}910{"current_steps": 4535, "total_steps": 9742, "loss": 0.3599, "lr": 5.5423085520547556e-06, "epoch": 0.9310203243687127, "percentage": 46.55, "elapsed_time": "7:35:28", "remaining_time": "8:42:58", "throughput": 9143.07, "total_tokens": 249867832}911{"current_steps": 4540, "total_steps": 9742, "loss": 0.3472, "lr": 5.534293430466276e-06, "epoch": 0.9320468076370355, "percentage": 46.6, "elapsed_time": "7:35:54", "remaining_time": "8:42:22", "throughput": 9144.59, "total_tokens": 250144088}912{"current_steps": 4545, "total_steps": 9742, "loss": 0.347, "lr": 5.526276919810637e-06, "epoch": 0.9330732909053583, "percentage": 46.65, "elapsed_time": "7:36:22", "remaining_time": "8:41:50", "throughput": 9144.94, "total_tokens": 250410368}913{"current_steps": 4550, "total_steps": 9742, "loss": 0.3237, "lr": 5.5182590409293305e-06, "epoch": 0.934099774173681, "percentage": 46.7, "elapsed_time": "7:36:52", "remaining_time": "8:41:20", "throughput": 9144.44, "total_tokens": 250675720}914{"current_steps": 4555, "total_steps": 9742, "loss": 0.3989, "lr": 5.510239814667401e-06, "epoch": 0.9351262574420037, "percentage": 46.76, "elapsed_time": "7:37:24", "remaining_time": "8:40:52", "throughput": 9144.47, "total_tokens": 250968512}915{"current_steps": 4560, "total_steps": 9742, "loss": 0.3469, "lr": 5.5022192618734035e-06, "epoch": 0.9361527407103264, "percentage": 46.81, "elapsed_time": "7:37:54", "remaining_time": "8:40:22", "throughput": 9144.69, "total_tokens": 251245648}916{"current_steps": 4565, "total_steps": 9742, "loss": 0.371, "lr": 5.494197403399337e-06, "epoch": 0.9371792239786492, "percentage": 46.86, "elapsed_time": "7:38:19", "remaining_time": "8:39:46", "throughput": 9146.24, "total_tokens": 251518792}917{"current_steps": 4570, "total_steps": 9742, "loss": 0.3592, "lr": 5.486174260100595e-06, "epoch": 0.9382057072469718, "percentage": 46.91, "elapsed_time": "7:38:50", "remaining_time": "8:39:16", "throughput": 9146.43, "total_tokens": 251801792}918{"current_steps": 4575, "total_steps": 9742, "loss": 0.3851, "lr": 5.478149852835912e-06, "epoch": 0.9392321905152946, "percentage": 46.96, "elapsed_time": "7:39:20", "remaining_time": "8:38:46", "throughput": 9147.19, "total_tokens": 252097144}919{"current_steps": 4580, "total_steps": 9742, "loss": 0.3601, "lr": 5.4701242024673105e-06, "epoch": 0.9402586737836174, "percentage": 47.01, "elapsed_time": "7:39:50", "remaining_time": "8:38:16", "throughput": 9146.27, "total_tokens": 252349240}920{"current_steps": 4585, "total_steps": 9742, "loss": 0.3515, "lr": 5.462097329860039e-06, "epoch": 0.94128515705194, "percentage": 47.06, "elapsed_time": "7:40:17", "remaining_time": "8:37:43", "throughput": 9146.04, "total_tokens": 252595248}921{"current_steps": 4590, "total_steps": 9742, "loss": 0.3489, "lr": 5.454069255882531e-06, "epoch": 0.9423116403202628, "percentage": 47.12, "elapsed_time": "7:40:51", "remaining_time": "8:37:17", "throughput": 9144.09, "total_tokens": 252849784}922{"current_steps": 4595, "total_steps": 9742, "loss": 0.3646, "lr": 5.446040001406341e-06, "epoch": 0.9433381235885855, "percentage": 47.17, "elapsed_time": "7:41:22", "remaining_time": "8:36:47", "throughput": 9143.82, "total_tokens": 253121736}923{"current_steps": 4600, "total_steps": 9742, "loss": 0.3266, "lr": 5.438009587306089e-06, "epoch": 0.9443646068569083, "percentage": 47.22, "elapsed_time": "7:41:59", "remaining_time": "8:36:25", "throughput": 9141.4, "total_tokens": 253392832}924{"current_steps": 4605, "total_steps": 9742, "loss": 0.3384, "lr": 5.429978034459412e-06, "epoch": 0.9453910901252309, "percentage": 47.27, "elapsed_time": "7:42:26", "remaining_time": "8:35:52", "throughput": 9142.12, "total_tokens": 253666240}925{"current_steps": 4610, "total_steps": 9742, "loss": 0.3647, "lr": 5.42194536374691e-06, "epoch": 0.9464175733935537, "percentage": 47.32, "elapsed_time": "7:42:57", "remaining_time": "8:35:23", "throughput": 9141.86, "total_tokens": 253942008}926{"current_steps": 4615, "total_steps": 9742, "loss": 0.3715, "lr": 5.4139115960520875e-06, "epoch": 0.9474440566618764, "percentage": 47.37, "elapsed_time": "7:43:33", "remaining_time": "8:34:59", "throughput": 9139.77, "total_tokens": 254208448}927{"current_steps": 4620, "total_steps": 9742, "loss": 0.3558, "lr": 5.405876752261297e-06, "epoch": 0.9484705399301991, "percentage": 47.42, "elapsed_time": "7:44:04", "remaining_time": "8:34:29", "throughput": 9139.31, "total_tokens": 254476904}928{"current_steps": 4625, "total_steps": 9742, "loss": 0.3557, "lr": 5.397840853263696e-06, "epoch": 0.9494970231985219, "percentage": 47.47, "elapsed_time": "7:44:35", "remaining_time": "8:34:00", "throughput": 9138.88, "total_tokens": 254747256}929{"current_steps": 4630, "total_steps": 9742, "loss": 0.3437, "lr": 5.389803919951181e-06, "epoch": 0.9505235064668446, "percentage": 47.53, "elapsed_time": "7:45:06", "remaining_time": "8:33:32", "throughput": 9138.49, "total_tokens": 255026208}930{"current_steps": 4635, "total_steps": 9742, "loss": 0.3442, "lr": 5.3817659732183354e-06, "epoch": 0.9515499897351674, "percentage": 47.58, "elapsed_time": "7:45:43", "remaining_time": "8:33:08", "throughput": 9136.26, "total_tokens": 255296472}931{"current_steps": 4640, "total_steps": 9742, "loss": 0.355, "lr": 5.3737270339623845e-06, "epoch": 0.95257647300349, "percentage": 47.63, "elapsed_time": "7:46:21", "remaining_time": "8:32:47", "throughput": 9133.61, "total_tokens": 255567624}932{"current_steps": 4645, "total_steps": 9742, "loss": 0.3262, "lr": 5.365687123083126e-06, "epoch": 0.9536029562718128, "percentage": 47.68, "elapsed_time": "7:46:53", "remaining_time": "8:32:19", "throughput": 9133.56, "total_tokens": 255860512}933{"current_steps": 4650, "total_steps": 9742, "loss": 0.3318, "lr": 5.357646261482889e-06, "epoch": 0.9546294395401355, "percentage": 47.73, "elapsed_time": "7:47:20", "remaining_time": "8:31:45", "throughput": 9135.66, "total_tokens": 256163984}934{"current_steps": 4655, "total_steps": 9742, "loss": 0.3552, "lr": 5.3496044700664725e-06, "epoch": 0.9556559228084582, "percentage": 47.78, "elapsed_time": "7:47:44", "remaining_time": "8:31:08", "throughput": 9138.15, "total_tokens": 256456480}935{"current_steps": 4660, "total_steps": 9742, "loss": 0.3293, "lr": 5.341561769741092e-06, "epoch": 0.9566824060767809, "percentage": 47.83, "elapsed_time": "7:48:15", "remaining_time": "8:30:40", "throughput": 9138.7, "total_tokens": 256758544}936{"current_steps": 4665, "total_steps": 9742, "loss": 0.3731, "lr": 5.333518181416328e-06, "epoch": 0.9577088893451037, "percentage": 47.89, "elapsed_time": "7:48:45", "remaining_time": "8:30:09", "throughput": 9139.19, "total_tokens": 257048088}937{"current_steps": 4670, "total_steps": 9742, "loss": 0.3121, "lr": 5.325473726004068e-06, "epoch": 0.9587353726134265, "percentage": 47.94, "elapsed_time": "7:49:20", "remaining_time": "8:29:44", "throughput": 9138.81, "total_tokens": 257349816}938{"current_steps": 4675, "total_steps": 9742, "loss": 0.336, "lr": 5.317428424418452e-06, "epoch": 0.9597618558817491, "percentage": 47.99, "elapsed_time": "7:49:54", "remaining_time": "8:29:18", "throughput": 9138.59, "total_tokens": 257654696}939{"current_steps": 4680, "total_steps": 9742, "loss": 0.3551, "lr": 5.309382297575826e-06, "epoch": 0.9607883391500719, "percentage": 48.04, "elapsed_time": "7:50:24", "remaining_time": "8:28:48", "throughput": 9139.53, "total_tokens": 257956856}940{"current_steps": 4685, "total_steps": 9742, "loss": 0.344, "lr": 5.301335366394675e-06, "epoch": 0.9618148224183946, "percentage": 48.09, "elapsed_time": "7:50:53", "remaining_time": "8:28:17", "throughput": 9139.52, "total_tokens": 258224736}941{"current_steps": 4690, "total_steps": 9742, "loss": 0.3467, "lr": 5.29328765179558e-06, "epoch": 0.9628413056867173, "percentage": 48.14, "elapsed_time": "7:51:27", "remaining_time": "8:27:50", "throughput": 9138.5, "total_tokens": 258503064}942{"current_steps": 4695, "total_steps": 9742, "loss": 0.3553, "lr": 5.285239174701156e-06, "epoch": 0.96386778895504, "percentage": 48.19, "elapsed_time": "7:51:56", "remaining_time": "8:27:19", "throughput": 9139.37, "total_tokens": 258792920}943{"current_steps": 4700, "total_steps": 9742, "loss": 0.3512, "lr": 5.277189956035998e-06, "epoch": 0.9648942722233628, "percentage": 48.24, "elapsed_time": "7:52:27", "remaining_time": "8:26:49", "throughput": 9138.96, "total_tokens": 259062192}944{"current_steps": 4705, "total_steps": 9742, "loss": 0.3548, "lr": 5.269140016726636e-06, "epoch": 0.9659207554916854, "percentage": 48.3, "elapsed_time": "7:52:59", "remaining_time": "8:26:22", "throughput": 9139.1, "total_tokens": 259367432}945{"current_steps": 4710, "total_steps": 9742, "loss": 0.3634, "lr": 5.261089377701466e-06, "epoch": 0.9669472387600082, "percentage": 48.35, "elapsed_time": "7:53:29", "remaining_time": "8:25:52", "throughput": 9139.71, "total_tokens": 259657648}946{"current_steps": 4715, "total_steps": 9742, "loss": 0.3573, "lr": 5.253038059890711e-06, "epoch": 0.967973722028331, "percentage": 48.4, "elapsed_time": "7:53:58", "remaining_time": "8:25:20", "throughput": 9140.64, "total_tokens": 259945584}947{"current_steps": 4720, "total_steps": 9742, "loss": 0.3663, "lr": 5.244986084226349e-06, "epoch": 0.9690002052966536, "percentage": 48.45, "elapsed_time": "7:54:30", "remaining_time": "8:24:51", "throughput": 9139.8, "total_tokens": 260210296}948{"current_steps": 4725, "total_steps": 9742, "loss": 0.3736, "lr": 5.236933471642076e-06, "epoch": 0.9700266885649764, "percentage": 48.5, "elapsed_time": "7:54:58", "remaining_time": "8:24:19", "throughput": 9140.33, "total_tokens": 260486616}949{"current_steps": 4730, "total_steps": 9742, "loss": 0.3707, "lr": 5.228880243073244e-06, "epoch": 0.9710531718332991, "percentage": 48.55, "elapsed_time": "7:55:29", "remaining_time": "8:23:50", "throughput": 9140.38, "total_tokens": 260773600}950{"current_steps": 4735, "total_steps": 9742, "loss": 0.4129, "lr": 5.2208264194568e-06, "epoch": 0.9720796551016219, "percentage": 48.6, "elapsed_time": "7:56:02", "remaining_time": "8:23:23", "throughput": 9139.77, "total_tokens": 261058816}951{"current_steps": 4740, "total_steps": 9742, "loss": 0.3353, "lr": 5.212772021731244e-06, "epoch": 0.9731061383699445, "percentage": 48.66, "elapsed_time": "7:56:35", "remaining_time": "8:22:56", "throughput": 9138.89, "total_tokens": 261333176}952{"current_steps": 4745, "total_steps": 9742, "loss": 0.3419, "lr": 5.204717070836566e-06, "epoch": 0.9741326216382673, "percentage": 48.71, "elapsed_time": "7:57:10", "remaining_time": "8:22:31", "throughput": 9137.96, "total_tokens": 261625240}953{"current_steps": 4750, "total_steps": 9742, "loss": 0.341, "lr": 5.196661587714195e-06, "epoch": 0.97515910490659, "percentage": 48.76, "elapsed_time": "7:57:44", "remaining_time": "8:22:04", "throughput": 9137.05, "total_tokens": 261906080}954{"current_steps": 4755, "total_steps": 9742, "loss": 0.3403, "lr": 5.188605593306943e-06, "epoch": 0.9761855881749127, "percentage": 48.81, "elapsed_time": "7:58:09", "remaining_time": "8:21:29", "throughput": 9137.24, "total_tokens": 262142992}955{"current_steps": 4760, "total_steps": 9742, "loss": 0.3371, "lr": 5.180549108558951e-06, "epoch": 0.9772120714432355, "percentage": 48.86, "elapsed_time": "7:58:36", "remaining_time": "8:20:56", "throughput": 9137.37, "total_tokens": 262395520}956{"current_steps": 4765, "total_steps": 9742, "loss": 0.3418, "lr": 5.172492154415635e-06, "epoch": 0.9782385547115582, "percentage": 48.91, "elapsed_time": "7:59:11", "remaining_time": "8:20:30", "throughput": 9135.82, "total_tokens": 262664448}957{"current_steps": 4770, "total_steps": 9742, "loss": 0.3544, "lr": 5.164434751823635e-06, "epoch": 0.979265037979881, "percentage": 48.96, "elapsed_time": "7:59:36", "remaining_time": "8:19:55", "throughput": 9136.61, "total_tokens": 262919560}958{"current_steps": 4775, "total_steps": 9742, "loss": 0.3375, "lr": 5.1563769217307505e-06, "epoch": 0.9802915212482036, "percentage": 49.01, "elapsed_time": "8:00:04", "remaining_time": "8:19:22", "throughput": 9137.66, "total_tokens": 263207176}959{"current_steps": 4780, "total_steps": 9742, "loss": 0.3259, "lr": 5.148318685085895e-06, "epoch": 0.9813180045165264, "percentage": 49.07, "elapsed_time": "8:00:32", "remaining_time": "8:18:50", "throughput": 9138.62, "total_tokens": 263491280}960{"current_steps": 4785, "total_steps": 9742, "loss": 0.3447, "lr": 5.1402600628390445e-06, "epoch": 0.9823444877848491, "percentage": 49.12, "elapsed_time": "8:00:59", "remaining_time": "8:18:17", "throughput": 9139.64, "total_tokens": 263768944}961{"current_steps": 4790, "total_steps": 9742, "loss": 0.345, "lr": 5.132201075941166e-06, "epoch": 0.9833709710531718, "percentage": 49.17, "elapsed_time": "8:01:29", "remaining_time": "8:17:46", "throughput": 9139.81, "total_tokens": 264044864}962{"current_steps": 4795, "total_steps": 9742, "loss": 0.3159, "lr": 5.124141745344186e-06, "epoch": 0.9843974543214946, "percentage": 49.22, "elapsed_time": "8:02:00", "remaining_time": "8:17:17", "throughput": 9139.4, "total_tokens": 264314368}963{"current_steps": 4800, "total_steps": 9742, "loss": 0.357, "lr": 5.1160820920009155e-06, "epoch": 0.9854239375898173, "percentage": 49.27, "elapsed_time": "8:02:35", "remaining_time": "8:16:51", "throughput": 9138.14, "total_tokens": 264597400}964{"current_steps": 4805, "total_steps": 9742, "loss": 0.325, "lr": 5.108022136865011e-06, "epoch": 0.98645042085814, "percentage": 49.32, "elapsed_time": "8:03:03", "remaining_time": "8:16:20", "throughput": 9138.16, "total_tokens": 264858440}965{"current_steps": 4810, "total_steps": 9742, "loss": 0.326, "lr": 5.099961900890914e-06, "epoch": 0.9874769041264627, "percentage": 49.37, "elapsed_time": "8:03:37", "remaining_time": "8:15:53", "throughput": 9137.18, "total_tokens": 265139872}966{"current_steps": 4815, "total_steps": 9742, "loss": 0.3482, "lr": 5.0919014050337875e-06, "epoch": 0.9885033873947855, "percentage": 49.43, "elapsed_time": "8:04:11", "remaining_time": "8:15:27", "throughput": 9136.03, "total_tokens": 265419712}967{"current_steps": 4820, "total_steps": 9742, "loss": 0.3362, "lr": 5.0838406702494816e-06, "epoch": 0.9895298706631082, "percentage": 49.48, "elapsed_time": "8:04:38", "remaining_time": "8:14:53", "throughput": 9136.31, "total_tokens": 265667312}968{"current_steps": 4825, "total_steps": 9742, "loss": 0.3324, "lr": 5.075779717494458e-06, "epoch": 0.9905563539314309, "percentage": 49.53, "elapsed_time": "8:05:07", "remaining_time": "8:14:22", "throughput": 9137.61, "total_tokens": 265974904}969{"current_steps": 4830, "total_steps": 9742, "loss": 0.3534, "lr": 5.067718567725751e-06, "epoch": 0.9915828371997536, "percentage": 49.58, "elapsed_time": "8:05:35", "remaining_time": "8:13:49", "throughput": 9138.63, "total_tokens": 266256544}970{"current_steps": 4835, "total_steps": 9742, "loss": 0.3413, "lr": 5.0596572419009045e-06, "epoch": 0.9926093204680764, "percentage": 49.63, "elapsed_time": "8:06:05", "remaining_time": "8:13:19", "throughput": 9138.75, "total_tokens": 266533584}971{"current_steps": 4840, "total_steps": 9742, "loss": 0.3261, "lr": 5.051595760977922e-06, "epoch": 0.9936358037363991, "percentage": 49.68, "elapsed_time": "8:06:34", "remaining_time": "8:12:48", "throughput": 9139.09, "total_tokens": 266815096}972{"current_steps": 4845, "total_steps": 9742, "loss": 0.3723, "lr": 5.043534145915209e-06, "epoch": 0.9946622870047218, "percentage": 49.73, "elapsed_time": "8:07:07", "remaining_time": "8:12:21", "throughput": 9138.04, "total_tokens": 267086184}973{"current_steps": 4850, "total_steps": 9742, "loss": 0.3442, "lr": 5.035472417671517e-06, "epoch": 0.9956887702730446, "percentage": 49.78, "elapsed_time": "8:07:41", "remaining_time": "8:11:54", "throughput": 9137.89, "total_tokens": 267385416}974{"current_steps": 4855, "total_steps": 9742, "loss": 0.3443, "lr": 5.027410597205898e-06, "epoch": 0.9967152535413673, "percentage": 49.84, "elapsed_time": "8:08:07", "remaining_time": "8:11:20", "throughput": 9139.23, "total_tokens": 267664352}975{"current_steps": 4860, "total_steps": 9742, "loss": 0.3368, "lr": 5.019348705477639e-06, "epoch": 0.99774173680969, "percentage": 49.89, "elapsed_time": "8:08:35", "remaining_time": "8:10:48", "throughput": 9140.4, "total_tokens": 267958320}976{"current_steps": 4865, "total_steps": 9742, "loss": 0.3714, "lr": 5.011286763446214e-06, "epoch": 0.9987682200780127, "percentage": 49.94, "elapsed_time": "8:09:11", "remaining_time": "8:10:24", "throughput": 9138.61, "total_tokens": 268236264}977{"current_steps": 4870, "total_steps": 9742, "loss": 0.3553, "lr": 5.003224792071225e-06, "epoch": 0.9997947033463355, "percentage": 49.99, "elapsed_time": "8:09:40", "remaining_time": "8:09:52", "throughput": 9138.21, "total_tokens": 268482200}978{"current_steps": 4875, "total_steps": 9742, "loss": 0.2939, "lr": 4.995162812312357e-06, "epoch": 1.0008211866146581, "percentage": 50.04, "elapsed_time": "8:11:53", "remaining_time": "8:11:05", "throughput": 9106.59, "total_tokens": 268767416}979{"current_steps": 4880, "total_steps": 9742, "loss": 0.3002, "lr": 4.987100845129309e-06, "epoch": 1.001847669882981, "percentage": 50.09, "elapsed_time": "8:12:24", "remaining_time": "8:10:35", "throughput": 9106.23, "total_tokens": 269038384}980{"current_steps": 4885, "total_steps": 9742, "loss": 0.3041, "lr": 4.979038911481752e-06, "epoch": 1.0028741531513037, "percentage": 50.14, "elapsed_time": "8:12:55", "remaining_time": "8:10:05", "throughput": 9105.5, "total_tokens": 269296304}981{"current_steps": 4890, "total_steps": 9742, "loss": 0.2939, "lr": 4.970977032329268e-06, "epoch": 1.0039006364196263, "percentage": 50.2, "elapsed_time": "8:13:24", "remaining_time": "8:09:34", "throughput": 9106.01, "total_tokens": 269583520}982{"current_steps": 4895, "total_steps": 9742, "loss": 0.2877, "lr": 4.962915228631298e-06, "epoch": 1.004927119687949, "percentage": 50.25, "elapsed_time": "8:13:52", "remaining_time": "8:09:02", "throughput": 9106.71, "total_tokens": 269858072}983{"current_steps": 4900, "total_steps": 9742, "loss": 0.2903, "lr": 4.954853521347087e-06, "epoch": 1.005953602956272, "percentage": 50.3, "elapsed_time": "8:14:24", "remaining_time": "8:08:32", "throughput": 9106.62, "total_tokens": 270140016}984{"current_steps": 4905, "total_steps": 9742, "loss": 0.2894, "lr": 4.946791931435629e-06, "epoch": 1.0069800862245946, "percentage": 50.35, "elapsed_time": "8:14:46", "remaining_time": "8:07:54", "throughput": 9109.12, "total_tokens": 270415248}985{"current_steps": 4910, "total_steps": 9742, "loss": 0.2949, "lr": 4.938730479855614e-06, "epoch": 1.0080065694929172, "percentage": 50.4, "elapsed_time": "8:15:16", "remaining_time": "8:07:24", "throughput": 9108.82, "total_tokens": 270680752}986{"current_steps": 4915, "total_steps": 9742, "loss": 0.2985, "lr": 4.930669187565371e-06, "epoch": 1.00903305276124, "percentage": 50.45, "elapsed_time": "8:15:46", "remaining_time": "8:06:53", "throughput": 9108.93, "total_tokens": 270958712}987{"current_steps": 4920, "total_steps": 9742, "loss": 0.2837, "lr": 4.922608075522811e-06, "epoch": 1.0100595360295628, "percentage": 50.5, "elapsed_time": "8:16:14", "remaining_time": "8:06:21", "throughput": 9109.68, "total_tokens": 271240016}988{"current_steps": 4925, "total_steps": 9742, "loss": 0.3214, "lr": 4.9145471646853866e-06, "epoch": 1.0110860192978854, "percentage": 50.55, "elapsed_time": "8:16:41", "remaining_time": "8:05:47", "throughput": 9111.32, "total_tokens": 271530072}989{"current_steps": 4930, "total_steps": 9742, "loss": 0.2893, "lr": 4.906486476010018e-06, "epoch": 1.012112502566208, "percentage": 50.61, "elapsed_time": "8:17:10", "remaining_time": "8:05:16", "throughput": 9111.71, "total_tokens": 271803640}990{"current_steps": 4935, "total_steps": 9742, "loss": 0.2953, "lr": 4.89842603045305e-06, "epoch": 1.013138985834531, "percentage": 50.66, "elapsed_time": "8:17:45", "remaining_time": "8:04:51", "throughput": 9110.53, "total_tokens": 272093248}991{"current_steps": 4940, "total_steps": 9742, "loss": 0.2854, "lr": 4.8903658489702e-06, "epoch": 1.0141654691028537, "percentage": 50.71, "elapsed_time": "8:18:18", "remaining_time": "8:04:23", "throughput": 9109.42, "total_tokens": 272356224}992{"current_steps": 4945, "total_steps": 9742, "loss": 0.3015, "lr": 4.882305952516492e-06, "epoch": 1.0151919523711763, "percentage": 50.76, "elapsed_time": "8:18:49", "remaining_time": "8:03:54", "throughput": 9109.51, "total_tokens": 272647552}993{"current_steps": 4950, "total_steps": 9742, "loss": 0.2902, "lr": 4.874246362046216e-06, "epoch": 1.016218435639499, "percentage": 50.81, "elapsed_time": "8:19:26", "remaining_time": "8:03:29", "throughput": 9108.01, "total_tokens": 272932280}994{"current_steps": 4955, "total_steps": 9742, "loss": 0.301, "lr": 4.866187098512856e-06, "epoch": 1.0172449189078219, "percentage": 50.86, "elapsed_time": "8:19:57", "remaining_time": "8:03:00", "throughput": 9108.46, "total_tokens": 273232976}995{"current_steps": 4960, "total_steps": 9742, "loss": 0.3071, "lr": 4.858128182869059e-06, "epoch": 1.0182714021761445, "percentage": 50.91, "elapsed_time": "8:20:20", "remaining_time": "8:02:23", "throughput": 9110.34, "total_tokens": 273498848}996{"current_steps": 4965, "total_steps": 9742, "loss": 0.2901, "lr": 4.8500696360665615e-06, "epoch": 1.0192978854444672, "percentage": 50.96, "elapsed_time": "8:20:53", "remaining_time": "8:01:55", "throughput": 9109.56, "total_tokens": 273778288}997{"current_steps": 4970, "total_steps": 9742, "loss": 0.286, "lr": 4.8420114790561365e-06, "epoch": 1.02032436871279, "percentage": 51.02, "elapsed_time": "8:21:19", "remaining_time": "8:01:21", "throughput": 9110.99, "total_tokens": 274053216}998{"current_steps": 4975, "total_steps": 9742, "loss": 0.2777, "lr": 4.833953732787549e-06, "epoch": 1.0213508519811128, "percentage": 51.07, "elapsed_time": "8:21:48", "remaining_time": "8:00:49", "throughput": 9110.73, "total_tokens": 274310296}999{"current_steps": 4980, "total_steps": 9742, "loss": 0.3064, "lr": 4.8258964182094985e-06, "epoch": 1.0223773352494354, "percentage": 51.12, "elapsed_time": "8:22:16", "remaining_time": "8:00:17", "throughput": 9111.05, "total_tokens": 274576824}1000{"current_steps": 4985, "total_steps": 9742, "loss": 0.2915, "lr": 4.817839556269556e-06, "epoch": 1.023403818517758, "percentage": 51.17, "elapsed_time": "8:22:50", "remaining_time": "7:59:50", "throughput": 9110.26, "total_tokens": 274860544}1001{"current_steps": 4990, "total_steps": 9742, "loss": 0.2905, "lr": 4.809783167914118e-06, "epoch": 1.024430301786081, "percentage": 51.22, "elapsed_time": "8:23:18", "remaining_time": "7:59:18", "throughput": 9110.7, "total_tokens": 275132432}1002{"current_steps": 4995, "total_steps": 9742, "loss": 0.315, "lr": 4.801727274088353e-06, "epoch": 1.0254567850544036, "percentage": 51.27, "elapsed_time": "8:23:49", "remaining_time": "7:58:48", "throughput": 9109.74, "total_tokens": 275385376}1003{"current_steps": 5000, "total_steps": 9742, "loss": 0.2908, "lr": 4.793671895736138e-06, "epoch": 1.0264832683227263, "percentage": 51.32, "elapsed_time": "8:24:22", "remaining_time": "7:58:21", "throughput": 9109.57, "total_tokens": 275680872}1004{"current_steps": 5005, "total_steps": 9742, "loss": 0.2964, "lr": 4.785617053800017e-06, "epoch": 1.027509751591049, "percentage": 51.38, "elapsed_time": "8:24:54", "remaining_time": "7:57:52", "throughput": 9109.07, "total_tokens": 275955352}1005{"current_steps": 5010, "total_steps": 9742, "loss": 0.2886, "lr": 4.777562769221129e-06, "epoch": 1.0285362348593718, "percentage": 51.43, "elapsed_time": "8:25:24", "remaining_time": "7:57:21", "throughput": 9110.09, "total_tokens": 276257936}1006{"current_steps": 5015, "total_steps": 9742, "loss": 0.3296, "lr": 4.769509062939177e-06, "epoch": 1.0295627181276945, "percentage": 51.48, "elapsed_time": "8:25:56", "remaining_time": "7:56:53", "throughput": 9109.19, "total_tokens": 276523656}1007{"current_steps": 5020, "total_steps": 9742, "loss": 0.2914, "lr": 4.761455955892351e-06, "epoch": 1.0305892013960172, "percentage": 51.53, "elapsed_time": "8:26:19", "remaining_time": "7:56:15", "throughput": 9111.64, "total_tokens": 276804672}1008{"current_steps": 5025, "total_steps": 9742, "loss": 0.3088, "lr": 4.753403469017284e-06, "epoch": 1.03161568466434, "percentage": 51.58, "elapsed_time": "8:26:57", "remaining_time": "7:55:52", "throughput": 9109.39, "total_tokens": 277083176}1009{"current_steps": 5030, "total_steps": 9742, "loss": 0.281, "lr": 4.745351623249003e-06, "epoch": 1.0326421679326627, "percentage": 51.63, "elapsed_time": "8:27:28", "remaining_time": "7:55:23", "throughput": 9109.1, "total_tokens": 277355344}1010{"current_steps": 5035, "total_steps": 9742, "loss": 0.3055, "lr": 4.737300439520862e-06, "epoch": 1.0336686512009854, "percentage": 51.68, "elapsed_time": "8:28:03", "remaining_time": "7:54:57", "throughput": 9107.38, "total_tokens": 277620656}1011{"current_steps": 5040, "total_steps": 9742, "loss": 0.2832, "lr": 4.729249938764496e-06, "epoch": 1.034695134469308, "percentage": 51.73, "elapsed_time": "8:28:35", "remaining_time": "7:54:28", "throughput": 9106.81, "total_tokens": 277898096}1012{"current_steps": 5045, "total_steps": 9742, "loss": 0.3048, "lr": 4.7212001419097585e-06, "epoch": 1.035721617737631, "percentage": 51.79, "elapsed_time": "8:29:02", "remaining_time": "7:53:55", "throughput": 9108.2, "total_tokens": 278186496}1013{"current_steps": 5050, "total_steps": 9742, "loss": 0.278, "lr": 4.713151069884687e-06, "epoch": 1.0367481010059536, "percentage": 51.84, "elapsed_time": "8:29:39", "remaining_time": "7:53:31", "throughput": 9105.91, "total_tokens": 278451720}1014{"current_steps": 5055, "total_steps": 9742, "loss": 0.2709, "lr": 4.705102743615425e-06, "epoch": 1.0377745842742763, "percentage": 51.89, "elapsed_time": "8:30:11", "remaining_time": "7:53:03", "throughput": 9105.36, "total_tokens": 278733104}1015{"current_steps": 5060, "total_steps": 9742, "loss": 0.3041, "lr": 4.697055184026173e-06, "epoch": 1.0388010675425992, "percentage": 51.94, "elapsed_time": "8:30:41", "remaining_time": "7:52:32", "throughput": 9104.98, "total_tokens": 278994888}1016{"current_steps": 5065, "total_steps": 9742, "loss": 0.3213, "lr": 4.689008412039146e-06, "epoch": 1.0398275508109218, "percentage": 51.99, "elapsed_time": "8:31:14", "remaining_time": "7:52:04", "throughput": 9104.17, "total_tokens": 279268680}1017{"current_steps": 5070, "total_steps": 9742, "loss": 0.2934, "lr": 4.680962448574512e-06, "epoch": 1.0408540340792445, "percentage": 52.04, "elapsed_time": "8:31:47", "remaining_time": "7:51:36", "throughput": 9104.17, "total_tokens": 279564976}1018{"current_steps": 5075, "total_steps": 9742, "loss": 0.2802, "lr": 4.67291731455033e-06, "epoch": 1.0418805173475671, "percentage": 52.09, "elapsed_time": "8:32:15", "remaining_time": "7:51:04", "throughput": 9104.74, "total_tokens": 279836056}1019{"current_steps": 5080, "total_steps": 9742, "loss": 0.2959, "lr": 4.664873030882507e-06, "epoch": 1.04290700061589, "percentage": 52.15, "elapsed_time": "8:32:47", "remaining_time": "7:50:36", "throughput": 9103.43, "total_tokens": 280091616}1020{"current_steps": 5085, "total_steps": 9742, "loss": 0.2938, "lr": 4.656829618484741e-06, "epoch": 1.0439334838842127, "percentage": 52.2, "elapsed_time": "8:33:18", "remaining_time": "7:50:06", "throughput": 9103.2, "total_tokens": 280369128}1021{"current_steps": 5090, "total_steps": 9742, "loss": 0.2668, "lr": 4.648787098268463e-06, "epoch": 1.0449599671525354, "percentage": 52.25, "elapsed_time": "8:33:46", "remaining_time": "7:49:33", "throughput": 9104.17, "total_tokens": 280648224}1022{"current_steps": 5095, "total_steps": 9742, "loss": 0.2834, "lr": 4.640745491142782e-06, "epoch": 1.045986450420858, "percentage": 52.3, "elapsed_time": "8:34:14", "remaining_time": "7:49:01", "throughput": 9104.97, "total_tokens": 280931784}1023{"current_steps": 5100, "total_steps": 9742, "loss": 0.2971, "lr": 4.6327048180144335e-06, "epoch": 1.047012933689181, "percentage": 52.35, "elapsed_time": "8:34:42", "remaining_time": "7:48:29", "throughput": 9105.27, "total_tokens": 281192768}1024{"current_steps": 5105, "total_steps": 9742, "loss": 0.3003, "lr": 4.624665099787732e-06, "epoch": 1.0480394169575036, "percentage": 52.4, "elapsed_time": "8:35:08", "remaining_time": "7:47:55", "throughput": 9106.28, "total_tokens": 281462840}1025{"current_steps": 5110, "total_steps": 9742, "loss": 0.2885, "lr": 4.6166263573645e-06, "epoch": 1.0490659002258262, "percentage": 52.45, "elapsed_time": "8:35:37", "remaining_time": "7:47:23", "throughput": 9105.89, "total_tokens": 281710520}1026{"current_steps": 5115, "total_steps": 9742, "loss": 0.2871, "lr": 4.608588611644026e-06, "epoch": 1.0500923834941491, "percentage": 52.5, "elapsed_time": "8:36:12", "remaining_time": "7:46:57", "throughput": 9104.19, "total_tokens": 281981736}1027{"current_steps": 5120, "total_steps": 9742, "loss": 0.2752, "lr": 4.600551883523012e-06, "epoch": 1.0511188667624718, "percentage": 52.56, "elapsed_time": "8:36:44", "remaining_time": "7:46:28", "throughput": 9103.74, "total_tokens": 282255392}1028{"current_steps": 5125, "total_steps": 9742, "loss": 0.3039, "lr": 4.592516193895509e-06, "epoch": 1.0521453500307945, "percentage": 52.61, "elapsed_time": "8:37:18", "remaining_time": "7:46:01", "throughput": 9102.24, "total_tokens": 282515856}1029{"current_steps": 5130, "total_steps": 9742, "loss": 0.3125, "lr": 4.5844815636528685e-06, "epoch": 1.0531718332991171, "percentage": 52.66, "elapsed_time": "8:37:41", "remaining_time": "7:45:25", "throughput": 9102.95, "total_tokens": 282750568}1030{"current_steps": 5135, "total_steps": 9742, "loss": 0.2948, "lr": 4.576448013683691e-06, "epoch": 1.05419831656744, "percentage": 52.71, "elapsed_time": "8:38:11", "remaining_time": "7:44:54", "throughput": 9102.98, "total_tokens": 283023600}1031{"current_steps": 5140, "total_steps": 9742, "loss": 0.3001, "lr": 4.568415564873766e-06, "epoch": 1.0552247998357627, "percentage": 52.76, "elapsed_time": "8:38:44", "remaining_time": "7:44:26", "throughput": 9102.33, "total_tokens": 283305672}1032{"current_steps": 5145, "total_steps": 9742, "loss": 0.3073, "lr": 4.560384238106022e-06, "epoch": 1.0562512831040853, "percentage": 52.81, "elapsed_time": "8:39:10", "remaining_time": "7:43:52", "throughput": 9103.37, "total_tokens": 283572688}1033{"current_steps": 5150, "total_steps": 9742, "loss": 0.3021, "lr": 4.5523540542604645e-06, "epoch": 1.0572777663724082, "percentage": 52.86, "elapsed_time": "8:39:38", "remaining_time": "7:43:20", "throughput": 9103.84, "total_tokens": 283845784}1034{"current_steps": 5155, "total_steps": 9742, "loss": 0.3106, "lr": 4.544325034214139e-06, "epoch": 1.0583042496407309, "percentage": 52.92, "elapsed_time": "8:40:12", "remaining_time": "7:42:53", "throughput": 9101.82, "total_tokens": 284087456}1035{"current_steps": 5160, "total_steps": 9742, "loss": 0.2889, "lr": 4.536297198841054e-06, "epoch": 1.0593307329090536, "percentage": 52.97, "elapsed_time": "8:40:38", "remaining_time": "7:42:18", "throughput": 9103.64, "total_tokens": 284379840}1036{"current_steps": 5165, "total_steps": 9742, "loss": 0.3161, "lr": 4.5282705690121445e-06, "epoch": 1.0603572161773762, "percentage": 53.02, "elapsed_time": "8:41:11", "remaining_time": "7:41:51", "throughput": 9102.78, "total_tokens": 284660608}1037{"current_steps": 5170, "total_steps": 9742, "loss": 0.2971, "lr": 4.5202451655952064e-06, "epoch": 1.061383699445699, "percentage": 53.07, "elapsed_time": "8:41:42", "remaining_time": "7:41:21", "throughput": 9102.49, "total_tokens": 284929616}1038{"current_steps": 5175, "total_steps": 9742, "loss": 0.31, "lr": 4.512221009454855e-06, "epoch": 1.0624101827140218, "percentage": 53.12, "elapsed_time": "8:42:10", "remaining_time": "7:40:49", "throughput": 9103.18, "total_tokens": 285208464}1039{"current_steps": 5180, "total_steps": 9742, "loss": 0.2871, "lr": 4.504198121452456e-06, "epoch": 1.0634366659823444, "percentage": 53.17, "elapsed_time": "8:42:45", "remaining_time": "7:40:23", "throughput": 9101.3, "total_tokens": 285470768}1040{"current_steps": 5185, "total_steps": 9742, "loss": 0.3143, "lr": 4.49617652244608e-06, "epoch": 1.0644631492506673, "percentage": 53.22, "elapsed_time": "8:43:14", "remaining_time": "7:39:52", "throughput": 9101.82, "total_tokens": 285749152}1041{"current_steps": 5190, "total_steps": 9742, "loss": 0.3272, "lr": 4.488156233290445e-06, "epoch": 1.06548963251899, "percentage": 53.27, "elapsed_time": "8:43:42", "remaining_time": "7:39:20", "throughput": 9101.09, "total_tokens": 285983168}1042{"current_steps": 5195, "total_steps": 9742, "loss": 0.2707, "lr": 4.4801372748368686e-06, "epoch": 1.0665161157873126, "percentage": 53.33, "elapsed_time": "8:44:14", "remaining_time": "7:38:51", "throughput": 9100.68, "total_tokens": 286261464}1043{"current_steps": 5200, "total_steps": 9742, "loss": 0.3205, "lr": 4.472119667933204e-06, "epoch": 1.0675425990556353, "percentage": 53.38, "elapsed_time": "8:44:48", "remaining_time": "7:38:23", "throughput": 9099.7, "total_tokens": 286535680}1044{"current_steps": 5205, "total_steps": 9742, "loss": 0.2762, "lr": 4.464103433423791e-06, "epoch": 1.0685690823239582, "percentage": 53.43, "elapsed_time": "8:45:19", "remaining_time": "7:37:54", "throughput": 9098.92, "total_tokens": 286795120}1045{"current_steps": 5210, "total_steps": 9742, "loss": 0.2915, "lr": 4.456088592149405e-06, "epoch": 1.0695955655922809, "percentage": 53.48, "elapsed_time": "8:45:46", "remaining_time": "7:37:21", "throughput": 9098.96, "total_tokens": 287043168}1046{"current_steps": 5215, "total_steps": 9742, "loss": 0.3004, "lr": 4.448075164947197e-06, "epoch": 1.0706220488606035, "percentage": 53.53, "elapsed_time": "8:46:15", "remaining_time": "7:36:50", "throughput": 9099.2, "total_tokens": 287315376}1047{"current_steps": 5220, "total_steps": 9742, "loss": 0.3049, "lr": 4.44006317265064e-06, "epoch": 1.0716485321289264, "percentage": 53.58, "elapsed_time": "8:46:45", "remaining_time": "7:36:19", "throughput": 9100.14, "total_tokens": 287614616}1048{"current_steps": 5225, "total_steps": 9742, "loss": 0.3068, "lr": 4.4320526360894755e-06, "epoch": 1.072675015397249, "percentage": 53.63, "elapsed_time": "8:47:13", "remaining_time": "7:35:47", "throughput": 9099.82, "total_tokens": 287861488}1049{"current_steps": 5230, "total_steps": 9742, "loss": 0.2833, "lr": 4.424043576089668e-06, "epoch": 1.0737014986655717, "percentage": 53.69, "elapsed_time": "8:47:44", "remaining_time": "7:35:17", "throughput": 9100.27, "total_tokens": 288157168}1050{"current_steps": 5235, "total_steps": 9742, "loss": 0.2777, "lr": 4.416036013473336e-06, "epoch": 1.0747279819338944, "percentage": 53.74, "elapsed_time": "8:48:21", "remaining_time": "7:34:53", "throughput": 9098.18, "total_tokens": 288428816}1051{"current_steps": 5240, "total_steps": 9742, "loss": 0.2842, "lr": 4.408029969058703e-06, "epoch": 1.0757544652022173, "percentage": 53.79, "elapsed_time": "8:48:53", "remaining_time": "7:34:24", "throughput": 9098.06, "total_tokens": 288714624}1052{"current_steps": 5245, "total_steps": 9742, "loss": 0.3174, "lr": 4.400025463660058e-06, "epoch": 1.07678094847054, "percentage": 53.84, "elapsed_time": "8:49:25", "remaining_time": "7:33:55", "throughput": 9098.4, "total_tokens": 289018088}1053{"current_steps": 5250, "total_steps": 9742, "loss": 0.2817, "lr": 4.392022518087675e-06, "epoch": 1.0778074317388626, "percentage": 53.89, "elapsed_time": "8:49:57", "remaining_time": "7:33:26", "throughput": 9098.28, "total_tokens": 289304360}1054{"current_steps": 5255, "total_steps": 9742, "loss": 0.3004, "lr": 4.3840211531477774e-06, "epoch": 1.0788339150071853, "percentage": 53.94, "elapsed_time": "8:50:31", "remaining_time": "7:32:59", "throughput": 9097.06, "total_tokens": 289572512}1055{"current_steps": 5260, "total_steps": 9742, "loss": 0.3046, "lr": 4.376021389642481e-06, "epoch": 1.0798603982755082, "percentage": 53.99, "elapsed_time": "8:50:57", "remaining_time": "7:32:25", "throughput": 9098.62, "total_tokens": 289863704}1056{"current_steps": 5265, "total_steps": 9742, "loss": 0.3073, "lr": 4.368023248369739e-06, "epoch": 1.0808868815438308, "percentage": 54.04, "elapsed_time": "8:51:23", "remaining_time": "7:31:51", "throughput": 9099.26, "total_tokens": 290119056}1057{"current_steps": 5270, "total_steps": 9742, "loss": 0.2927, "lr": 4.360026750123284e-06, "epoch": 1.0819133648121535, "percentage": 54.1, "elapsed_time": "8:51:55", "remaining_time": "7:31:22", "throughput": 9098.67, "total_tokens": 290388848}1058{"current_steps": 5275, "total_steps": 9742, "loss": 0.2963, "lr": 4.352031915692576e-06, "epoch": 1.0829398480804764, "percentage": 54.15, "elapsed_time": "8:52:23", "remaining_time": "7:30:50", "throughput": 9099.74, "total_tokens": 290678256}1059{"current_steps": 5280, "total_steps": 9742, "loss": 0.2698, "lr": 4.344038765862757e-06, "epoch": 1.083966331348799, "percentage": 54.2, "elapsed_time": "8:52:52", "remaining_time": "7:30:19", "throughput": 9099.81, "total_tokens": 290945904}1060{"current_steps": 5285, "total_steps": 9742, "loss": 0.2922, "lr": 4.336047321414579e-06, "epoch": 1.0849928146171217, "percentage": 54.25, "elapsed_time": "8:53:19", "remaining_time": "7:29:46", "throughput": 9100.45, "total_tokens": 291213640}1061{"current_steps": 5290, "total_steps": 9742, "loss": 0.2879, "lr": 4.328057603124368e-06, "epoch": 1.0860192978854444, "percentage": 54.3, "elapsed_time": "8:53:45", "remaining_time": "7:29:12", "throughput": 9101.77, "total_tokens": 291493136}1062{"current_steps": 5295, "total_steps": 9742, "loss": 0.3047, "lr": 4.320069631763957e-06, "epoch": 1.0870457811537673, "percentage": 54.35, "elapsed_time": "8:54:13", "remaining_time": "7:28:40", "throughput": 9102.19, "total_tokens": 291757704}1063{"current_steps": 5300, "total_steps": 9742, "loss": 0.2984, "lr": 4.312083428100642e-06, "epoch": 1.08807226442209, "percentage": 54.4, "elapsed_time": "8:54:51", "remaining_time": "7:28:16", "throughput": 9100.31, "total_tokens": 292045576}1064{"current_steps": 5305, "total_steps": 9742, "loss": 0.3112, "lr": 4.304099012897121e-06, "epoch": 1.0890987476904126, "percentage": 54.45, "elapsed_time": "8:55:16", "remaining_time": "7:27:41", "throughput": 9101.25, "total_tokens": 292299376}1065{"current_steps": 5310, "total_steps": 9742, "loss": 0.3022, "lr": 4.296116406911443e-06, "epoch": 1.0901252309587353, "percentage": 54.51, "elapsed_time": "8:55:42", "remaining_time": "7:27:07", "throughput": 9102.72, "total_tokens": 292582288}1066{"current_steps": 5315, "total_steps": 9742, "loss": 0.2897, "lr": 4.288135630896949e-06, "epoch": 1.0911517142270581, "percentage": 54.56, "elapsed_time": "8:56:13", "remaining_time": "7:26:37", "throughput": 9103.2, "total_tokens": 292878144}1067{"current_steps": 5320, "total_steps": 9742, "loss": 0.3205, "lr": 4.280156705602232e-06, "epoch": 1.0921781974953808, "percentage": 54.61, "elapsed_time": "8:56:42", "remaining_time": "7:26:06", "throughput": 9102.97, "total_tokens": 293139672}1068{"current_steps": 5325, "total_steps": 9742, "loss": 0.291, "lr": 4.2721796517710654e-06, "epoch": 1.0932046807637035, "percentage": 54.66, "elapsed_time": "8:57:09", "remaining_time": "7:25:33", "throughput": 9104.07, "total_tokens": 293420872}1069{"current_steps": 5330, "total_steps": 9742, "loss": 0.2921, "lr": 4.2642044901423555e-06, "epoch": 1.0942311640320264, "percentage": 54.71, "elapsed_time": "8:57:34", "remaining_time": "7:24:59", "throughput": 9105.46, "total_tokens": 293690624}1070{"current_steps": 5335, "total_steps": 9742, "loss": 0.2856, "lr": 4.256231241450101e-06, "epoch": 1.095257647300349, "percentage": 54.76, "elapsed_time": "8:58:01", "remaining_time": "7:24:26", "throughput": 9105.75, "total_tokens": 293947088}1071{"current_steps": 5340, "total_steps": 9742, "loss": 0.2833, "lr": 4.248259926423313e-06, "epoch": 1.0962841305686717, "percentage": 54.81, "elapsed_time": "8:58:24", "remaining_time": "7:23:50", "throughput": 9107.7, "total_tokens": 294221360}1072{"current_steps": 5345, "total_steps": 9742, "loss": 0.2897, "lr": 4.240290565785985e-06, "epoch": 1.0973106138369944, "percentage": 54.87, "elapsed_time": "8:58:51", "remaining_time": "7:23:16", "throughput": 9108.8, "total_tokens": 294497360}1073{"current_steps": 5350, "total_steps": 9742, "loss": 0.2711, "lr": 4.232323180257024e-06, "epoch": 1.0983370971053172, "percentage": 54.92, "elapsed_time": "8:59:18", "remaining_time": "7:22:44", "throughput": 9109.65, "total_tokens": 294777088}1074{"current_steps": 5355, "total_steps": 9742, "loss": 0.3118, "lr": 4.2243577905502065e-06, "epoch": 1.09936358037364, "percentage": 54.97, "elapsed_time": "8:59:50", "remaining_time": "7:22:15", "throughput": 9110.07, "total_tokens": 295082344}1075{"current_steps": 5360, "total_steps": 9742, "loss": 0.3016, "lr": 4.216394417374118e-06, "epoch": 1.1003900636419626, "percentage": 55.02, "elapsed_time": "9:00:20", "remaining_time": "7:21:45", "throughput": 9110.16, "total_tokens": 295356816}1076{"current_steps": 5365, "total_steps": 9742, "loss": 0.2873, "lr": 4.2084330814321e-06, "epoch": 1.1014165469102855, "percentage": 55.07, "elapsed_time": "9:00:50", "remaining_time": "7:21:14", "throughput": 9110.41, "total_tokens": 295638992}1077{"current_steps": 5370, "total_steps": 9742, "loss": 0.2767, "lr": 4.2004738034222e-06, "epoch": 1.1024430301786081, "percentage": 55.12, "elapsed_time": "9:01:19", "remaining_time": "7:20:43", "throughput": 9110.91, "total_tokens": 295921880}1078{"current_steps": 5375, "total_steps": 9742, "loss": 0.2901, "lr": 4.192516604037116e-06, "epoch": 1.1034695134469308, "percentage": 55.17, "elapsed_time": "9:01:53", "remaining_time": "7:20:15", "throughput": 9110.48, "total_tokens": 296209400}1079{"current_steps": 5380, "total_steps": 9742, "loss": 0.3029, "lr": 4.184561503964138e-06, "epoch": 1.1044959967152534, "percentage": 55.22, "elapsed_time": "9:02:20", "remaining_time": "7:19:42", "throughput": 9111.85, "total_tokens": 296500888}1080{"current_steps": 5385, "total_steps": 9742, "loss": 0.2865, "lr": 4.1766085238851e-06, "epoch": 1.1055224799835763, "percentage": 55.28, "elapsed_time": "9:02:55", "remaining_time": "7:19:16", "throughput": 9110.64, "total_tokens": 296785600}1081{"current_steps": 5390, "total_steps": 9742, "loss": 0.2862, "lr": 4.168657684476326e-06, "epoch": 1.106548963251899, "percentage": 55.33, "elapsed_time": "9:03:26", "remaining_time": "7:18:47", "throughput": 9110.73, "total_tokens": 297072760}1082{"current_steps": 5395, "total_steps": 9742, "loss": 0.2654, "lr": 4.1607090064085745e-06, "epoch": 1.1075754465202217, "percentage": 55.38, "elapsed_time": "9:03:59", "remaining_time": "7:18:19", "throughput": 9110.11, "total_tokens": 297351912}1083{"current_steps": 5400, "total_steps": 9742, "loss": 0.2934, "lr": 4.152762510346981e-06, "epoch": 1.1086019297885445, "percentage": 55.43, "elapsed_time": "9:04:29", "remaining_time": "7:17:49", "throughput": 9109.79, "total_tokens": 297616752}1084{"current_steps": 5405, "total_steps": 9742, "loss": 0.2955, "lr": 4.1448182169510136e-06, "epoch": 1.1096284130568672, "percentage": 55.48, "elapsed_time": "9:04:59", "remaining_time": "7:17:18", "throughput": 9109.61, "total_tokens": 297877672}1085{"current_steps": 5410, "total_steps": 9742, "loss": 0.3181, "lr": 4.13687614687441e-06, "epoch": 1.1106548963251899, "percentage": 55.53, "elapsed_time": "9:05:30", "remaining_time": "7:16:48", "throughput": 9108.7, "total_tokens": 298128472}1086{"current_steps": 5415, "total_steps": 9742, "loss": 0.2944, "lr": 4.128936320765131e-06, "epoch": 1.1116813795935125, "percentage": 55.58, "elapsed_time": "9:05:57", "remaining_time": "7:16:15", "throughput": 9109.59, "total_tokens": 298408672}1087{"current_steps": 5420, "total_steps": 9742, "loss": 0.2804, "lr": 4.120998759265296e-06, "epoch": 1.1127078628618354, "percentage": 55.64, "elapsed_time": "9:06:29", "remaining_time": "7:15:46", "throughput": 9109.03, "total_tokens": 298675904}1088{"current_steps": 5425, "total_steps": 9742, "loss": 0.3023, "lr": 4.113063483011149e-06, "epoch": 1.113734346130158, "percentage": 55.69, "elapsed_time": "9:06:57", "remaining_time": "7:15:14", "throughput": 9110.31, "total_tokens": 298977904}1089{"current_steps": 5430, "total_steps": 9742, "loss": 0.2733, "lr": 4.105130512632983e-06, "epoch": 1.1147608293984808, "percentage": 55.74, "elapsed_time": "9:07:26", "remaining_time": "7:14:43", "throughput": 9110.1, "total_tokens": 299232712}1090{"current_steps": 5435, "total_steps": 9742, "loss": 0.3028, "lr": 4.0971998687551e-06, "epoch": 1.1157873126668036, "percentage": 55.79, "elapsed_time": "9:07:56", "remaining_time": "7:14:13", "throughput": 9110.2, "total_tokens": 299514600}1091{"current_steps": 5440, "total_steps": 9742, "loss": 0.2852, "lr": 4.0892715719957485e-06, "epoch": 1.1168137959351263, "percentage": 55.84, "elapsed_time": "9:08:29", "remaining_time": "7:13:45", "throughput": 9109.06, "total_tokens": 299775960}1092{"current_steps": 5445, "total_steps": 9742, "loss": 0.3168, "lr": 4.081345642967086e-06, "epoch": 1.117840279203449, "percentage": 55.89, "elapsed_time": "9:09:01", "remaining_time": "7:13:16", "throughput": 9108.93, "total_tokens": 300066048}1093{"current_steps": 5450, "total_steps": 9742, "loss": 0.2873, "lr": 4.0734221022751025e-06, "epoch": 1.1188667624717716, "percentage": 55.94, "elapsed_time": "9:09:35", "remaining_time": "7:12:48", "throughput": 9108.44, "total_tokens": 300353184}1094{"current_steps": 5455, "total_steps": 9742, "loss": 0.3107, "lr": 4.065500970519585e-06, "epoch": 1.1198932457400945, "percentage": 55.99, "elapsed_time": "9:10:04", "remaining_time": "7:12:17", "throughput": 9109.39, "total_tokens": 300651664}1095{"current_steps": 5460, "total_steps": 9742, "loss": 0.2907, "lr": 4.057582268294057e-06, "epoch": 1.1209197290084172, "percentage": 56.05, "elapsed_time": "9:10:28", "remaining_time": "7:11:42", "throughput": 9110.56, "total_tokens": 300911784}1096{"current_steps": 5465, "total_steps": 9742, "loss": 0.3032, "lr": 4.049666016185726e-06, "epoch": 1.1219462122767399, "percentage": 56.1, "elapsed_time": "9:10:59", "remaining_time": "7:11:12", "throughput": 9110.24, "total_tokens": 301178000}1097{"current_steps": 5470, "total_steps": 9742, "loss": 0.3097, "lr": 4.041752234775427e-06, "epoch": 1.1229726955450625, "percentage": 56.15, "elapsed_time": "9:11:27", "remaining_time": "7:10:40", "throughput": 9110.4, "total_tokens": 301435736}1098{"current_steps": 5475, "total_steps": 9742, "loss": 0.2901, "lr": 4.033840944637571e-06, "epoch": 1.1239991788133854, "percentage": 56.2, "elapsed_time": "9:11:54", "remaining_time": "7:10:08", "throughput": 9111.64, "total_tokens": 301726464}1099{"current_steps": 5480, "total_steps": 9742, "loss": 0.3128, "lr": 4.025932166340099e-06, "epoch": 1.125025662081708, "percentage": 56.25, "elapsed_time": "9:12:23", "remaining_time": "7:09:36", "throughput": 9112.89, "total_tokens": 302029920}1100{"current_steps": 5485, "total_steps": 9742, "loss": 0.27, "lr": 4.018025920444415e-06, "epoch": 1.1260521453500307, "percentage": 56.3, "elapsed_time": "9:12:52", "remaining_time": "7:09:05", "throughput": 9113.34, "total_tokens": 302309984}1101{"current_steps": 5490, "total_steps": 9742, "loss": 0.3054, "lr": 4.01012222750534e-06, "epoch": 1.1270786286183536, "percentage": 56.35, "elapsed_time": "9:13:23", "remaining_time": "7:08:36", "throughput": 9113.46, "total_tokens": 302602576}1102{"current_steps": 5495, "total_steps": 9742, "loss": 0.3106, "lr": 4.002221108071063e-06, "epoch": 1.1281051118866763, "percentage": 56.41, "elapsed_time": "9:13:52", "remaining_time": "7:08:05", "throughput": 9114.11, "total_tokens": 302886408}1103{"current_steps": 5500, "total_steps": 9742, "loss": 0.2995, "lr": 3.9943225826830745e-06, "epoch": 1.129131595154999, "percentage": 56.46, "elapsed_time": "9:14:17", "remaining_time": "7:07:30", "throughput": 9115.79, "total_tokens": 303171992}1104{"current_steps": 5505, "total_steps": 9742, "loss": 0.3024, "lr": 3.986426671876128e-06, "epoch": 1.1301580784233216, "percentage": 56.51, "elapsed_time": "9:14:49", "remaining_time": "7:07:02", "throughput": 9115.9, "total_tokens": 303467944}1105{"current_steps": 5510, "total_steps": 9742, "loss": 0.3083, "lr": 3.978533396178171e-06, "epoch": 1.1311845616916445, "percentage": 56.56, "elapsed_time": "9:15:15", "remaining_time": "7:06:28", "throughput": 9117.17, "total_tokens": 303744352}1106{"current_steps": 5515, "total_steps": 9742, "loss": 0.3276, "lr": 3.970642776110314e-06, "epoch": 1.1322110449599672, "percentage": 56.61, "elapsed_time": "9:15:46", "remaining_time": "7:05:58", "throughput": 9117.27, "total_tokens": 304030224}1107{"current_steps": 5520, "total_steps": 9742, "loss": 0.2978, "lr": 3.962754832186748e-06, "epoch": 1.1332375282282898, "percentage": 56.66, "elapsed_time": "9:16:16", "remaining_time": "7:05:28", "throughput": 9116.57, "total_tokens": 304279144}1108{"current_steps": 5525, "total_steps": 9742, "loss": 0.2905, "lr": 3.954869584914717e-06, "epoch": 1.1342640114966125, "percentage": 56.71, "elapsed_time": "9:16:44", "remaining_time": "7:04:56", "throughput": 9117.59, "total_tokens": 304567752}1109{"current_steps": 5530, "total_steps": 9742, "loss": 0.2784, "lr": 3.946987054794447e-06, "epoch": 1.1352904947649354, "percentage": 56.76, "elapsed_time": "9:17:13", "remaining_time": "7:04:25", "throughput": 9118.45, "total_tokens": 304861424}1110{"current_steps": 5535, "total_steps": 9742, "loss": 0.3037, "lr": 3.939107262319108e-06, "epoch": 1.136316978033258, "percentage": 56.82, "elapsed_time": "9:17:31", "remaining_time": "7:03:45", "throughput": 9120.97, "total_tokens": 305111432}1111{"current_steps": 5540, "total_steps": 9742, "loss": 0.2864, "lr": 3.931230227974746e-06, "epoch": 1.1373434613015807, "percentage": 56.87, "elapsed_time": "9:17:59", "remaining_time": "7:03:13", "throughput": 9121.8, "total_tokens": 305396352}1112{"current_steps": 5545, "total_steps": 9742, "loss": 0.2786, "lr": 3.923355972240238e-06, "epoch": 1.1383699445699036, "percentage": 56.92, "elapsed_time": "9:18:24", "remaining_time": "7:02:39", "throughput": 9122.87, "total_tokens": 305661792}1113{"current_steps": 5550, "total_steps": 9742, "loss": 0.3035, "lr": 3.915484515587239e-06, "epoch": 1.1393964278382263, "percentage": 56.97, "elapsed_time": "9:18:50", "remaining_time": "7:02:06", "throughput": 9123.55, "total_tokens": 305917064}1114{"current_steps": 5555, "total_steps": 9742, "loss": 0.2954, "lr": 3.907615878480127e-06, "epoch": 1.140422911106549, "percentage": 57.02, "elapsed_time": "9:19:19", "remaining_time": "7:01:34", "throughput": 9123.92, "total_tokens": 306194112}1115{"current_steps": 5560, "total_steps": 9742, "loss": 0.2914, "lr": 3.8997500813759446e-06, "epoch": 1.1414493943748716, "percentage": 57.07, "elapsed_time": "9:19:49", "remaining_time": "7:01:04", "throughput": 9123.21, "total_tokens": 306445872}1116{"current_steps": 5565, "total_steps": 9742, "loss": 0.2755, "lr": 3.891887144724354e-06, "epoch": 1.1424758776431945, "percentage": 57.12, "elapsed_time": "9:20:13", "remaining_time": "7:00:30", "throughput": 9124.36, "total_tokens": 306705400}1117{"current_steps": 5570, "total_steps": 9742, "loss": 0.2875, "lr": 3.884027088967585e-06, "epoch": 1.1435023609115171, "percentage": 57.18, "elapsed_time": "9:20:46", "remaining_time": "7:00:01", "throughput": 9123.91, "total_tokens": 306990536}1118{"current_steps": 5575, "total_steps": 9742, "loss": 0.2687, "lr": 3.876169934540372e-06, "epoch": 1.1445288441798398, "percentage": 57.23, "elapsed_time": "9:21:12", "remaining_time": "6:59:28", "throughput": 9124.86, "total_tokens": 307260968}1119{"current_steps": 5580, "total_steps": 9742, "loss": 0.3015, "lr": 3.868315701869907e-06, "epoch": 1.1455553274481627, "percentage": 57.28, "elapsed_time": "9:21:45", "remaining_time": "6:59:00", "throughput": 9124.65, "total_tokens": 307550096}1120{"current_steps": 5585, "total_steps": 9742, "loss": 0.2995, "lr": 3.860464411375791e-06, "epoch": 1.1465818107164854, "percentage": 57.33, "elapsed_time": "9:22:19", "remaining_time": "6:58:33", "throughput": 9123.45, "total_tokens": 307823200}1121{"current_steps": 5590, "total_steps": 9742, "loss": 0.2914, "lr": 3.852616083469968e-06, "epoch": 1.147608293984808, "percentage": 57.38, "elapsed_time": "9:22:54", "remaining_time": "6:58:06", "throughput": 9123.0, "total_tokens": 308124024}1122{"current_steps": 5595, "total_steps": 9742, "loss": 0.3141, "lr": 3.844770738556688e-06, "epoch": 1.1486347772531307, "percentage": 57.43, "elapsed_time": "9:23:22", "remaining_time": "6:57:34", "throughput": 9123.68, "total_tokens": 308406264}1123{"current_steps": 5600, "total_steps": 9742, "loss": 0.287, "lr": 3.8369283970324355e-06, "epoch": 1.1496612605214536, "percentage": 57.48, "elapsed_time": "9:23:49", "remaining_time": "6:57:01", "throughput": 9124.68, "total_tokens": 308681976}1124{"current_steps": 5605, "total_steps": 9742, "loss": 0.2857, "lr": 3.8290890792859e-06, "epoch": 1.1506877437897762, "percentage": 57.53, "elapsed_time": "9:24:16", "remaining_time": "6:56:29", "throughput": 9125.69, "total_tokens": 308966576}1125{"current_steps": 5610, "total_steps": 9742, "loss": 0.2776, "lr": 3.821252805697898e-06, "epoch": 1.151714227058099, "percentage": 57.59, "elapsed_time": "9:24:49", "remaining_time": "6:56:01", "throughput": 9124.96, "total_tokens": 309243056}1126{"current_steps": 5615, "total_steps": 9742, "loss": 0.2882, "lr": 3.8134195966413383e-06, "epoch": 1.1527407103264218, "percentage": 57.64, "elapsed_time": "9:25:18", "remaining_time": "6:55:29", "throughput": 9124.63, "total_tokens": 309490672}1127{"current_steps": 5620, "total_steps": 9742, "loss": 0.2754, "lr": 3.805589472481159e-06, "epoch": 1.1537671935947444, "percentage": 57.69, "elapsed_time": "9:25:49", "remaining_time": "6:55:00", "throughput": 9124.72, "total_tokens": 309780192}1128{"current_steps": 5625, "total_steps": 9742, "loss": 0.2942, "lr": 3.7977624535742815e-06, "epoch": 1.154793676863067, "percentage": 57.74, "elapsed_time": "9:26:19", "remaining_time": "6:54:29", "throughput": 9125.68, "total_tokens": 310086008}1129{"current_steps": 5630, "total_steps": 9742, "loss": 0.3041, "lr": 3.7899385602695505e-06, "epoch": 1.1558201601313898, "percentage": 57.79, "elapsed_time": "9:26:49", "remaining_time": "6:53:59", "throughput": 9126.0, "total_tokens": 310370792}1130{"current_steps": 5635, "total_steps": 9742, "loss": 0.2915, "lr": 3.7821178129076864e-06, "epoch": 1.1568466433997127, "percentage": 57.84, "elapsed_time": "9:27:14", "remaining_time": "6:53:25", "throughput": 9127.42, "total_tokens": 310647024}1131{"current_steps": 5640, "total_steps": 9742, "loss": 0.2984, "lr": 3.7743002318212324e-06, "epoch": 1.1578731266680353, "percentage": 57.89, "elapsed_time": "9:27:42", "remaining_time": "6:52:53", "throughput": 9127.39, "total_tokens": 310900816}1132{"current_steps": 5645, "total_steps": 9742, "loss": 0.3119, "lr": 3.766485837334498e-06, "epoch": 1.158899609936358, "percentage": 57.94, "elapsed_time": "9:28:20", "remaining_time": "6:52:29", "throughput": 9124.9, "total_tokens": 311163240}1133{"current_steps": 5650, "total_steps": 9742, "loss": 0.288, "lr": 3.758674649763506e-06, "epoch": 1.1599260932046809, "percentage": 58.0, "elapsed_time": "9:28:53", "remaining_time": "6:52:01", "throughput": 9124.68, "total_tokens": 311459152}1134{"current_steps": 5655, "total_steps": 9742, "loss": 0.2986, "lr": 3.750866689415945e-06, "epoch": 1.1609525764730035, "percentage": 58.05, "elapsed_time": "9:29:24", "remaining_time": "6:51:31", "throughput": 9124.31, "total_tokens": 311725120}1135{"current_steps": 5660, "total_steps": 9742, "loss": 0.2943, "lr": 3.7430619765911137e-06, "epoch": 1.1619790597413262, "percentage": 58.1, "elapsed_time": "9:29:59", "remaining_time": "6:51:04", "throughput": 9123.18, "total_tokens": 312007952}1136{"current_steps": 5665, "total_steps": 9742, "loss": 0.2839, "lr": 3.7352605315798658e-06, "epoch": 1.1630055430096489, "percentage": 58.15, "elapsed_time": "9:30:36", "remaining_time": "6:50:39", "throughput": 9121.82, "total_tokens": 312298008}1137{"current_steps": 5670, "total_steps": 9742, "loss": 0.3151, "lr": 3.7274623746645587e-06, "epoch": 1.1640320262779718, "percentage": 58.2, "elapsed_time": "9:31:10", "remaining_time": "6:50:12", "throughput": 9120.16, "total_tokens": 312554440}1138{"current_steps": 5675, "total_steps": 9742, "loss": 0.2744, "lr": 3.7196675261190063e-06, "epoch": 1.1650585095462944, "percentage": 58.25, "elapsed_time": "9:31:43", "remaining_time": "6:49:43", "throughput": 9119.55, "total_tokens": 312829504}1139{"current_steps": 5680, "total_steps": 9742, "loss": 0.2807, "lr": 3.7118760062084146e-06, "epoch": 1.166084992814617, "percentage": 58.3, "elapsed_time": "9:32:07", "remaining_time": "6:49:08", "throughput": 9121.19, "total_tokens": 313106496}1140{"current_steps": 5685, "total_steps": 9742, "loss": 0.3131, "lr": 3.7040878351893418e-06, "epoch": 1.16711147608294, "percentage": 58.36, "elapsed_time": "9:32:40", "remaining_time": "6:48:40", "throughput": 9120.44, "total_tokens": 313384160}1141{"current_steps": 5690, "total_steps": 9742, "loss": 0.3041, "lr": 3.6963030333096316e-06, "epoch": 1.1681379593512626, "percentage": 58.41, "elapsed_time": "9:33:04", "remaining_time": "6:48:06", "throughput": 9122.08, "total_tokens": 313660784}1142{"current_steps": 5695, "total_steps": 9742, "loss": 0.2812, "lr": 3.6885216208083807e-06, "epoch": 1.1691644426195853, "percentage": 58.46, "elapsed_time": "9:33:38", "remaining_time": "6:47:38", "throughput": 9121.45, "total_tokens": 313943216}1143{"current_steps": 5700, "total_steps": 9742, "loss": 0.2998, "lr": 3.680743617915861e-06, "epoch": 1.170190925887908, "percentage": 58.51, "elapsed_time": "9:34:07", "remaining_time": "6:47:07", "throughput": 9122.07, "total_tokens": 314235576}1144{"current_steps": 5705, "total_steps": 9742, "loss": 0.3125, "lr": 3.6729690448534884e-06, "epoch": 1.1712174091562308, "percentage": 58.56, "elapsed_time": "9:34:33", "remaining_time": "6:46:34", "throughput": 9123.54, "total_tokens": 314523768}1145{"current_steps": 5710, "total_steps": 9742, "loss": 0.3114, "lr": 3.665197921833759e-06, "epoch": 1.1722438924245535, "percentage": 58.61, "elapsed_time": "9:35:04", "remaining_time": "6:46:04", "throughput": 9123.23, "total_tokens": 314792136}1146{"current_steps": 5715, "total_steps": 9742, "loss": 0.3112, "lr": 3.657430269060201e-06, "epoch": 1.1732703756928762, "percentage": 58.66, "elapsed_time": "9:35:32", "remaining_time": "6:45:32", "throughput": 9123.64, "total_tokens": 315061944}1147{"current_steps": 5720, "total_steps": 9742, "loss": 0.3086, "lr": 3.649666106727318e-06, "epoch": 1.1742968589611988, "percentage": 58.71, "elapsed_time": "9:36:09", "remaining_time": "6:45:07", "throughput": 9122.29, "total_tokens": 315353312}1148{"current_steps": 5725, "total_steps": 9742, "loss": 0.2924, "lr": 3.6419054550205403e-06, "epoch": 1.1753233422295217, "percentage": 58.77, "elapsed_time": "9:36:38", "remaining_time": "6:44:36", "throughput": 9122.42, "total_tokens": 315617384}1149{"current_steps": 5730, "total_steps": 9742, "loss": 0.277, "lr": 3.6341483341161734e-06, "epoch": 1.1763498254978444, "percentage": 58.82, "elapsed_time": "9:37:08", "remaining_time": "6:44:05", "throughput": 9122.96, "total_tokens": 315911840}1150{"current_steps": 5735, "total_steps": 9742, "loss": 0.273, "lr": 3.6263947641813415e-06, "epoch": 1.177376308766167, "percentage": 58.87, "elapsed_time": "9:37:44", "remaining_time": "6:43:39", "throughput": 9121.13, "total_tokens": 316175496}1151{"current_steps": 5740, "total_steps": 9742, "loss": 0.3101, "lr": 3.6186447653739333e-06, "epoch": 1.1784027920344897, "percentage": 58.92, "elapsed_time": "9:38:16", "remaining_time": "6:43:11", "throughput": 9120.09, "total_tokens": 316439808}1152{"current_steps": 5745, "total_steps": 9742, "loss": 0.3058, "lr": 3.6108983578425584e-06, "epoch": 1.1794292753028126, "percentage": 58.97, "elapsed_time": "9:38:50", "remaining_time": "6:42:43", "throughput": 9119.24, "total_tokens": 316717328}1153{"current_steps": 5750, "total_steps": 9742, "loss": 0.2658, "lr": 3.603155561726489e-06, "epoch": 1.1804557585711353, "percentage": 59.02, "elapsed_time": "9:39:20", "remaining_time": "6:42:12", "throughput": 9119.74, "total_tokens": 317004640}1154{"current_steps": 5755, "total_steps": 9742, "loss": 0.299, "lr": 3.5954163971556076e-06, "epoch": 1.181482241839458, "percentage": 59.07, "elapsed_time": "9:39:52", "remaining_time": "6:41:44", "throughput": 9118.58, "total_tokens": 317262688}1155{"current_steps": 5760, "total_steps": 9742, "loss": 0.2896, "lr": 3.587680884250353e-06, "epoch": 1.1825087251077808, "percentage": 59.13, "elapsed_time": "9:40:19", "remaining_time": "6:41:11", "throughput": 9118.66, "total_tokens": 317511344}1156{"current_steps": 5765, "total_steps": 9742, "loss": 0.3173, "lr": 3.5799490431216737e-06, "epoch": 1.1835352083761035, "percentage": 59.18, "elapsed_time": "9:40:50", "remaining_time": "6:40:41", "throughput": 9118.21, "total_tokens": 317777656}1157{"current_steps": 5770, "total_steps": 9742, "loss": 0.2948, "lr": 3.572220893870971e-06, "epoch": 1.1845616916444262, "percentage": 59.23, "elapsed_time": "9:41:19", "remaining_time": "6:40:10", "throughput": 9118.7, "total_tokens": 318053224}1158{"current_steps": 5775, "total_steps": 9742, "loss": 0.3009, "lr": 3.5644964565900484e-06, "epoch": 1.1855881749127488, "percentage": 59.28, "elapsed_time": "9:41:48", "remaining_time": "6:39:39", "throughput": 9119.07, "total_tokens": 318336512}1159{"current_steps": 5780, "total_steps": 9742, "loss": 0.3004, "lr": 3.556775751361055e-06, "epoch": 1.1866146581810717, "percentage": 59.33, "elapsed_time": "9:42:18", "remaining_time": "6:39:09", "throughput": 9118.35, "total_tokens": 318583224}1160{"current_steps": 5785, "total_steps": 9742, "loss": 0.2888, "lr": 3.5490587982564463e-06, "epoch": 1.1876411414493944, "percentage": 59.38, "elapsed_time": "9:42:52", "remaining_time": "6:38:41", "throughput": 9117.55, "total_tokens": 318864656}1161{"current_steps": 5790, "total_steps": 9742, "loss": 0.3131, "lr": 3.5413456173389128e-06, "epoch": 1.188667624717717, "percentage": 59.43, "elapsed_time": "9:43:19", "remaining_time": "6:38:08", "throughput": 9118.6, "total_tokens": 319144224}1162{"current_steps": 5795, "total_steps": 9742, "loss": 0.296, "lr": 3.533636228661342e-06, "epoch": 1.18969410798604, "percentage": 59.48, "elapsed_time": "9:43:42", "remaining_time": "6:37:34", "throughput": 9120.04, "total_tokens": 319410272}1163{"current_steps": 5800, "total_steps": 9742, "loss": 0.2982, "lr": 3.525930652266767e-06, "epoch": 1.1907205912543626, "percentage": 59.54, "elapsed_time": "9:44:17", "remaining_time": "6:37:06", "throughput": 9118.99, "total_tokens": 319687696}1164{"current_steps": 5805, "total_steps": 9742, "loss": 0.28, "lr": 3.5182289081883012e-06, "epoch": 1.1917470745226852, "percentage": 59.59, "elapsed_time": "9:44:42", "remaining_time": "6:36:33", "throughput": 9120.07, "total_tokens": 319957392}1165{"current_steps": 5810, "total_steps": 9742, "loss": 0.2978, "lr": 3.510531016449102e-06, "epoch": 1.192773557791008, "percentage": 59.64, "elapsed_time": "9:45:21", "remaining_time": "6:36:09", "throughput": 9117.31, "total_tokens": 320216392}1166{"current_steps": 5815, "total_steps": 9742, "loss": 0.2932, "lr": 3.5028369970623056e-06, "epoch": 1.1938000410593308, "percentage": 59.69, "elapsed_time": "9:45:55", "remaining_time": "6:35:41", "throughput": 9116.56, "total_tokens": 320498544}1167{"current_steps": 5820, "total_steps": 9742, "loss": 0.2818, "lr": 3.4951468700309855e-06, "epoch": 1.1948265243276535, "percentage": 59.74, "elapsed_time": "9:46:22", "remaining_time": "6:35:08", "throughput": 9117.02, "total_tokens": 320758664}1168{"current_steps": 5825, "total_steps": 9742, "loss": 0.3102, "lr": 3.4874606553480934e-06, "epoch": 1.1958530075959761, "percentage": 59.79, "elapsed_time": "9:46:55", "remaining_time": "6:34:40", "throughput": 9115.8, "total_tokens": 321015648}1169{"current_steps": 5830, "total_steps": 9742, "loss": 0.2945, "lr": 3.4797783729964085e-06, "epoch": 1.196879490864299, "percentage": 59.84, "elapsed_time": "9:47:15", "remaining_time": "6:34:03", "throughput": 9117.84, "total_tokens": 321275968}1170{"current_steps": 5835, "total_steps": 9742, "loss": 0.3167, "lr": 3.472100042948488e-06, "epoch": 1.1979059741326217, "percentage": 59.9, "elapsed_time": "9:47:45", "remaining_time": "6:33:32", "throughput": 9118.05, "total_tokens": 321550696}1171{"current_steps": 5840, "total_steps": 9742, "loss": 0.3062, "lr": 3.4644256851666157e-06, "epoch": 1.1989324574009443, "percentage": 59.95, "elapsed_time": "9:48:18", "remaining_time": "6:33:04", "throughput": 9117.16, "total_tokens": 321824224}1172{"current_steps": 5845, "total_steps": 9742, "loss": 0.276, "lr": 3.456755319602746e-06, "epoch": 1.199958940669267, "percentage": 60.0, "elapsed_time": "9:48:50", "remaining_time": "6:32:35", "throughput": 9116.42, "total_tokens": 322083664}1173{"current_steps": 5850, "total_steps": 9742, "loss": 0.3022, "lr": 3.4490889661984515e-06, "epoch": 1.20098542393759, "percentage": 60.05, "elapsed_time": "9:49:22", "remaining_time": "6:32:06", "throughput": 9116.26, "total_tokens": 322375200}1174{"current_steps": 5855, "total_steps": 9742, "loss": 0.2942, "lr": 3.441426644884882e-06, "epoch": 1.2020119072059126, "percentage": 60.1, "elapsed_time": "9:49:53", "remaining_time": "6:31:36", "throughput": 9115.73, "total_tokens": 322634928}1175{"current_steps": 5860, "total_steps": 9742, "loss": 0.3006, "lr": 3.4337683755826966e-06, "epoch": 1.2030383904742352, "percentage": 60.15, "elapsed_time": "9:50:18", "remaining_time": "6:31:03", "throughput": 9117.13, "total_tokens": 322912800}1176{"current_steps": 5865, "total_steps": 9742, "loss": 0.2961, "lr": 3.4261141782020246e-06, "epoch": 1.204064873742558, "percentage": 60.2, "elapsed_time": "9:50:48", "remaining_time": "6:30:32", "throughput": 9116.4, "total_tokens": 323161240}1177{"current_steps": 5870, "total_steps": 9742, "loss": 0.2944, "lr": 3.4184640726424034e-06, "epoch": 1.2050913570108808, "percentage": 60.25, "elapsed_time": "9:51:18", "remaining_time": "6:30:02", "throughput": 9116.29, "total_tokens": 323435584}1178{"current_steps": 5875, "total_steps": 9742, "loss": 0.279, "lr": 3.4108180787927425e-06, "epoch": 1.2061178402792034, "percentage": 60.31, "elapsed_time": "9:51:48", "remaining_time": "6:29:31", "throughput": 9116.03, "total_tokens": 323693768}1179{"current_steps": 5880, "total_steps": 9742, "loss": 0.276, "lr": 3.403176216531251e-06, "epoch": 1.207144323547526, "percentage": 60.36, "elapsed_time": "9:52:20", "remaining_time": "6:29:03", "throughput": 9116.11, "total_tokens": 323995112}1180{"current_steps": 5885, "total_steps": 9742, "loss": 0.2962, "lr": 3.395538505725401e-06, "epoch": 1.208170806815849, "percentage": 60.41, "elapsed_time": "9:52:45", "remaining_time": "6:28:29", "throughput": 9116.97, "total_tokens": 324253888}1181{"current_steps": 5890, "total_steps": 9742, "loss": 0.2944, "lr": 3.3879049662318746e-06, "epoch": 1.2091972900841716, "percentage": 60.46, "elapsed_time": "9:53:07", "remaining_time": "6:27:53", "throughput": 9119.7, "total_tokens": 324548104}1182{"current_steps": 5895, "total_steps": 9742, "loss": 0.3023, "lr": 3.3802756178965048e-06, "epoch": 1.2102237733524943, "percentage": 60.51, "elapsed_time": "9:53:39", "remaining_time": "6:27:24", "throughput": 9118.75, "total_tokens": 324800960}1183{"current_steps": 5900, "total_steps": 9742, "loss": 0.2854, "lr": 3.37265048055423e-06, "epoch": 1.2112502566208172, "percentage": 60.56, "elapsed_time": "9:54:05", "remaining_time": "6:26:51", "throughput": 9119.08, "total_tokens": 325051000}1184{"current_steps": 5905, "total_steps": 9742, "loss": 0.281, "lr": 3.3650295740290396e-06, "epoch": 1.2122767398891399, "percentage": 60.61, "elapsed_time": "9:54:28", "remaining_time": "6:26:17", "throughput": 9120.87, "total_tokens": 325328352}1185{"current_steps": 5910, "total_steps": 9742, "loss": 0.2894, "lr": 3.357412918133926e-06, "epoch": 1.2133032231574625, "percentage": 60.67, "elapsed_time": "9:54:59", "remaining_time": "6:25:47", "throughput": 9120.59, "total_tokens": 325598080}1186{"current_steps": 5915, "total_steps": 9742, "loss": 0.2945, "lr": 3.3498005326708305e-06, "epoch": 1.2143297064257852, "percentage": 60.72, "elapsed_time": "9:55:27", "remaining_time": "6:25:15", "throughput": 9120.56, "total_tokens": 325853264}1187{"current_steps": 5920, "total_steps": 9742, "loss": 0.2897, "lr": 3.342192437430587e-06, "epoch": 1.215356189694108, "percentage": 60.77, "elapsed_time": "9:55:57", "remaining_time": "6:24:45", "throughput": 9121.37, "total_tokens": 326157488}1188{"current_steps": 5925, "total_steps": 9742, "loss": 0.2859, "lr": 3.334588652192885e-06, "epoch": 1.2163826729624307, "percentage": 60.82, "elapsed_time": "9:56:30", "remaining_time": "6:24:16", "throughput": 9121.07, "total_tokens": 326448176}1189{"current_steps": 5930, "total_steps": 9742, "loss": 0.2952, "lr": 3.3269891967261993e-06, "epoch": 1.2174091562307534, "percentage": 60.87, "elapsed_time": "9:57:00", "remaining_time": "6:23:46", "throughput": 9120.75, "total_tokens": 326711184}1190{"current_steps": 5935, "total_steps": 9742, "loss": 0.2889, "lr": 3.3193940907877532e-06, "epoch": 1.218435639499076, "percentage": 60.92, "elapsed_time": "9:57:24", "remaining_time": "6:23:12", "throughput": 9122.66, "total_tokens": 326998496}1191{"current_steps": 5940, "total_steps": 9742, "loss": 0.2813, "lr": 3.3118033541234596e-06, "epoch": 1.219462122767399, "percentage": 60.97, "elapsed_time": "9:57:51", "remaining_time": "6:22:39", "throughput": 9123.97, "total_tokens": 327286016}1192{"current_steps": 5945, "total_steps": 9742, "loss": 0.3128, "lr": 3.3042170064678757e-06, "epoch": 1.2204886060357216, "percentage": 61.02, "elapsed_time": "9:58:22", "remaining_time": "6:22:10", "throughput": 9123.86, "total_tokens": 327565680}1193{"current_steps": 5950, "total_steps": 9742, "loss": 0.2936, "lr": 3.296635067544145e-06, "epoch": 1.2215150893040443, "percentage": 61.08, "elapsed_time": "9:58:50", "remaining_time": "6:21:38", "throughput": 9124.68, "total_tokens": 327854360}1194{"current_steps": 5955, "total_steps": 9742, "loss": 0.2745, "lr": 3.2890575570639506e-06, "epoch": 1.222541572572367, "percentage": 61.13, "elapsed_time": "9:59:21", "remaining_time": "6:21:08", "throughput": 9124.87, "total_tokens": 328139872}1195{"current_steps": 5960, "total_steps": 9742, "loss": 0.2612, "lr": 3.281484494727457e-06, "epoch": 1.2235680558406898, "percentage": 61.18, "elapsed_time": "9:59:43", "remaining_time": "6:20:33", "throughput": 9126.49, "total_tokens": 328405224}1196{"current_steps": 5965, "total_steps": 9742, "loss": 0.293, "lr": 3.273915900223277e-06, "epoch": 1.2245945391090125, "percentage": 61.23, "elapsed_time": "10:00:07", "remaining_time": "6:19:59", "throughput": 9128.33, "total_tokens": 328687872}1197{"current_steps": 5970, "total_steps": 9742, "loss": 0.2856, "lr": 3.266351793228393e-06, "epoch": 1.2256210223773352, "percentage": 61.28, "elapsed_time": "10:00:34", "remaining_time": "6:19:27", "throughput": 9128.63, "total_tokens": 328942096}1198{"current_steps": 5975, "total_steps": 9742, "loss": 0.2997, "lr": 3.258792193408129e-06, "epoch": 1.226647505645658, "percentage": 61.33, "elapsed_time": "10:01:01", "remaining_time": "6:18:55", "throughput": 9128.82, "total_tokens": 329197104}1199{"current_steps": 5980, "total_steps": 9742, "loss": 0.3042, "lr": 3.2512371204160912e-06, "epoch": 1.2276739889139807, "percentage": 61.38, "elapsed_time": "10:01:30", "remaining_time": "6:18:24", "throughput": 9129.07, "total_tokens": 329471744}1200{"current_steps": 5985, "total_steps": 9742, "loss": 0.3012, "lr": 3.243686593894115e-06, "epoch": 1.2287004721823034, "percentage": 61.44, "elapsed_time": "10:02:04", "remaining_time": "6:17:56", "throughput": 9128.26, "total_tokens": 329753360}

Showing the first 1,200 of 1953 lines. Download the file for the rest.