{"current_steps": 5, "total_steps": 37500, "loss": 0.9941, "lr": 4.999999859632294e-05, "epoch": 0.0004, "percentage": 0.01, "elapsed_time": "0:00:07", "remaining_time": "14:54:26", "throughput": 1260.96, "total_tokens": 9024} {"current_steps": 5, "total_steps": 37500, "loss": 0.9941, "lr": 4.999999859632294e-05, "epoch": 0.0004, "percentage": 0.01, "elapsed_time": "0:00:07", "remaining_time": "14:58:39", "throughput": 1255.03, "total_tokens": 9024} {"current_steps": 10, "total_steps": 37500, "loss": 0.7894, "lr": 4.999999289388517e-05, "epoch": 0.0008, "percentage": 0.03, "elapsed_time": "0:00:13", "remaining_time": "14:22:55", "throughput": 1402.41, "total_tokens": 19368} {"current_steps": 15, "total_steps": 37500, "loss": 1.0334, "lr": 4.999998280495786e-05, "epoch": 0.0012, "percentage": 0.04, "elapsed_time": "0:00:20", "remaining_time": "13:56:04", "throughput": 1376.51, "total_tokens": 27632} {"current_steps": 20, "total_steps": 37500, "loss": 0.8944, "lr": 4.999996832954279e-05, "epoch": 0.0016, "percentage": 0.05, "elapsed_time": "0:00:26", "remaining_time": "13:46:40", "throughput": 1401.55, "total_tokens": 37096} {"current_steps": 25, "total_steps": 37500, "loss": 0.8099, "lr": 4.9999949467642495e-05, "epoch": 0.002, "percentage": 0.07, "elapsed_time": "0:00:32", "remaining_time": "13:38:45", "throughput": 1377.26, "total_tokens": 45136} {"current_steps": 30, "total_steps": 37500, "loss": 0.7783, "lr": 4.9999926219260286e-05, "epoch": 0.0024, "percentage": 0.08, "elapsed_time": "0:00:39", "remaining_time": "13:38:26", "throughput": 1381.81, "total_tokens": 54328} {"current_steps": 35, "total_steps": 37500, "loss": 0.9789, "lr": 4.9999898584400235e-05, "epoch": 0.0028, "percentage": 0.09, "elapsed_time": "0:00:45", "remaining_time": "13:34:21", "throughput": 1371.92, "total_tokens": 62624} {"current_steps": 40, "total_steps": 37500, "loss": 0.8949, "lr": 4.99998665630672e-05, "epoch": 0.0032, "percentage": 0.11, "elapsed_time": "0:00:52", "remaining_time": "13:31:43", "throughput": 1377.68, "total_tokens": 71648} {"current_steps": 45, "total_steps": 37500, "loss": 0.8798, "lr": 4.99998301552668e-05, "epoch": 0.0036, "percentage": 0.12, "elapsed_time": "0:00:58", "remaining_time": "13:30:13", "throughput": 1373.68, "total_tokens": 80232} {"current_steps": 50, "total_steps": 37500, "loss": 0.7365, "lr": 4.999978936100542e-05, "epoch": 0.004, "percentage": 0.13, "elapsed_time": "0:01:04", "remaining_time": "13:29:59", "throughput": 1369.92, "total_tokens": 88888} {"current_steps": 55, "total_steps": 37500, "loss": 0.704, "lr": 4.999974418029022e-05, "epoch": 0.0044, "percentage": 0.15, "elapsed_time": "0:01:11", "remaining_time": "13:34:11", "throughput": 1389.76, "total_tokens": 99720} {"current_steps": 60, "total_steps": 37500, "loss": 0.7568, "lr": 4.999969461312912e-05, "epoch": 0.0048, "percentage": 0.16, "elapsed_time": "0:01:18", "remaining_time": "13:36:48", "throughput": 1379.89, "total_tokens": 108376} {"current_steps": 5, "total_steps": 6252, "loss": 0.9716, "lr": 4.999994949996767e-05, "epoch": 0.0023999520009599807, "percentage": 0.08, "elapsed_time": "0:00:08", "remaining_time": "2:56:02", "throughput": 6426.1, "total_tokens": 54328} {"current_steps": 10, "total_steps": 6252, "loss": 0.9707, "lr": 4.9999744343936e-05, "epoch": 0.004799904001919961, "percentage": 0.16, "elapsed_time": "0:00:16", "remaining_time": "2:47:56", "throughput": 6713.44, "total_tokens": 108376} {"current_steps": 15, "total_steps": 6252, "loss": 0.8624, "lr": 4.999938137694701e-05, "epoch": 0.007199856002879942, "percentage": 0.24, "elapsed_time": "0:00:24", "remaining_time": "2:47:53", "throughput": 6761.64, "total_tokens": 163816} {"current_steps": 20, "total_steps": 6252, "loss": 0.831, "lr": 4.999886060129194e-05, "epoch": 0.009599808003839923, "percentage": 0.32, "elapsed_time": "0:00:33", "remaining_time": "2:52:02", "throughput": 6798.61, "total_tokens": 225216} {"current_steps": 5, "total_steps": 6252, "loss": 0.9716, "lr": 4.999994949996767e-05, "epoch": 0.0023999520009599807, "percentage": 0.08, "elapsed_time": "0:00:08", "remaining_time": "2:52:45", "throughput": 6548.24, "total_tokens": 54328} {"current_steps": 10, "total_steps": 6252, "loss": 0.9705, "lr": 4.9999744343936e-05, "epoch": 0.004799904001919961, "percentage": 0.16, "elapsed_time": "0:00:15", "remaining_time": "2:45:51", "throughput": 6797.8, "total_tokens": 108376} {"current_steps": 15, "total_steps": 6252, "loss": 0.8622, "lr": 4.999938137694701e-05, "epoch": 0.007199856002879942, "percentage": 0.24, "elapsed_time": "0:00:24", "remaining_time": "2:46:40", "throughput": 6811.11, "total_tokens": 163816} {"current_steps": 20, "total_steps": 6252, "loss": 0.8309, "lr": 4.999886060129194e-05, "epoch": 0.009599808003839923, "percentage": 0.32, "elapsed_time": "0:00:33", "remaining_time": "2:51:23", "throughput": 6824.19, "total_tokens": 225216} {"current_steps": 25, "total_steps": 6252, "loss": 0.8118, "lr": 4.999818202025819e-05, "epoch": 0.011999760004799903, "percentage": 0.4, "elapsed_time": "0:00:40", "remaining_time": "2:47:57", "throughput": 6907.95, "total_tokens": 279480} {"current_steps": 30, "total_steps": 6252, "loss": 0.7763, "lr": 4.999734563812929e-05, "epoch": 0.014399712005759884, "percentage": 0.48, "elapsed_time": "0:00:48", "remaining_time": "2:48:43", "throughput": 6920.9, "total_tokens": 337816} {"current_steps": 35, "total_steps": 6252, "loss": 0.7919, "lr": 4.9996351460184923e-05, "epoch": 0.016799664006719867, "percentage": 0.56, "elapsed_time": "0:00:57", "remaining_time": "2:49:33", "throughput": 6896.02, "total_tokens": 394952} {"current_steps": 40, "total_steps": 6252, "loss": 0.7095, "lr": 4.9995199492700826e-05, "epoch": 0.019199616007679846, "percentage": 0.64, "elapsed_time": "0:01:05", "remaining_time": "2:50:11", "throughput": 6913.61, "total_tokens": 454608} {"current_steps": 45, "total_steps": 6252, "loss": 0.7347, "lr": 4.9993889742948806e-05, "epoch": 0.021599568008639828, "percentage": 0.72, "elapsed_time": "0:01:13", "remaining_time": "2:50:02", "throughput": 6898.73, "total_tokens": 510256} {"current_steps": 50, "total_steps": 6252, "loss": 0.7461, "lr": 4.9992422219196656e-05, "epoch": 0.023999520009599807, "percentage": 0.8, "elapsed_time": "0:01:22", "remaining_time": "2:50:13", "throughput": 6899.34, "total_tokens": 568112} {"current_steps": 55, "total_steps": 6252, "loss": 0.7168, "lr": 4.9990796930708125e-05, "epoch": 0.02639947201055979, "percentage": 0.88, "elapsed_time": "0:01:30", "remaining_time": "2:50:19", "throughput": 6900.38, "total_tokens": 625896} {"current_steps": 60, "total_steps": 6252, "loss": 0.7117, "lr": 4.9989013887742856e-05, "epoch": 0.02879942401151977, "percentage": 0.96, "elapsed_time": "0:01:38", "remaining_time": "2:48:52", "throughput": 6904.04, "total_tokens": 677856} {"current_steps": 65, "total_steps": 6252, "loss": 0.6441, "lr": 4.998707310155631e-05, "epoch": 0.03119937601247975, "percentage": 1.04, "elapsed_time": "0:01:47", "remaining_time": "2:50:26", "throughput": 6894.79, "total_tokens": 740792} {"current_steps": 70, "total_steps": 6252, "loss": 0.617, "lr": 4.99849745843997e-05, "epoch": 0.03359932801343973, "percentage": 1.12, "elapsed_time": "0:01:55", "remaining_time": "2:49:36", "throughput": 6905.97, "total_tokens": 795784} {"current_steps": 75, "total_steps": 6252, "loss": 0.685, "lr": 4.998271834951993e-05, "epoch": 0.03599928001439971, "percentage": 1.2, "elapsed_time": "0:02:03", "remaining_time": "2:49:00", "throughput": 6920.11, "total_tokens": 852016} {"current_steps": 80, "total_steps": 6252, "loss": 0.6505, "lr": 4.998030441115949e-05, "epoch": 0.03839923201535969, "percentage": 1.28, "elapsed_time": "0:02:11", "remaining_time": "2:49:08", "throughput": 6911.78, "total_tokens": 909224} {"current_steps": 85, "total_steps": 6252, "loss": 0.6212, "lr": 4.9977732784556355e-05, "epoch": 0.04079918401631968, "percentage": 1.36, "elapsed_time": "0:02:18", "remaining_time": "2:48:04", "throughput": 6903.88, "total_tokens": 959568} {"current_steps": 90, "total_steps": 6252, "loss": 0.6978, "lr": 4.997500348594394e-05, "epoch": 0.043199136017279656, "percentage": 1.44, "elapsed_time": "0:02:26", "remaining_time": "2:47:31", "throughput": 6884.75, "total_tokens": 1010696} {"current_steps": 95, "total_steps": 6252, "loss": 0.6212, "lr": 4.997211653255096e-05, "epoch": 0.045599088018239635, "percentage": 1.52, "elapsed_time": "0:02:35", "remaining_time": "2:47:39", "throughput": 6879.93, "total_tokens": 1067912} {"current_steps": 100, "total_steps": 6252, "loss": 0.6182, "lr": 4.996907194260129e-05, "epoch": 0.047999040019199614, "percentage": 1.6, "elapsed_time": "0:02:44", "remaining_time": "2:48:28", "throughput": 6860.39, "total_tokens": 1127264} {"current_steps": 105, "total_steps": 6252, "loss": 0.6254, "lr": 4.996586973531394e-05, "epoch": 0.0503989920201596, "percentage": 1.68, "elapsed_time": "0:02:52", "remaining_time": "2:48:19", "throughput": 6858.79, "total_tokens": 1183208} {"current_steps": 110, "total_steps": 6252, "loss": 0.5758, "lr": 4.9962509930902836e-05, "epoch": 0.05279894402111958, "percentage": 1.76, "elapsed_time": "0:03:01", "remaining_time": "2:48:34", "throughput": 6862.39, "total_tokens": 1243128} {"current_steps": 115, "total_steps": 6252, "loss": 0.6427, "lr": 4.9958992550576754e-05, "epoch": 0.05519889602207956, "percentage": 1.84, "elapsed_time": "0:03:08", "remaining_time": "2:47:53", "throughput": 6858.43, "total_tokens": 1294648} {"current_steps": 120, "total_steps": 6252, "loss": 0.6416, "lr": 4.9955317616539174e-05, "epoch": 0.05759884802303954, "percentage": 1.92, "elapsed_time": "0:03:16", "remaining_time": "2:47:32", "throughput": 6857.98, "total_tokens": 1349136} {"current_steps": 125, "total_steps": 6252, "loss": 0.6039, "lr": 4.9951485151988126e-05, "epoch": 0.05999880002399952, "percentage": 2.0, "elapsed_time": "0:03:24", "remaining_time": "2:47:21", "throughput": 6850.28, "total_tokens": 1403304} {"current_steps": 130, "total_steps": 6252, "loss": 0.6365, "lr": 4.994749518111604e-05, "epoch": 0.0623987520249595, "percentage": 2.08, "elapsed_time": "0:03:32", "remaining_time": "2:46:59", "throughput": 6865.23, "total_tokens": 1460712} {"current_steps": 135, "total_steps": 6252, "loss": 0.5757, "lr": 4.9943347729109646e-05, "epoch": 0.06479870402591949, "percentage": 2.16, "elapsed_time": "0:03:41", "remaining_time": "2:46:55", "throughput": 6862.37, "total_tokens": 1516920} {"current_steps": 140, "total_steps": 6252, "loss": 0.6484, "lr": 4.993904282214972e-05, "epoch": 0.06719865602687947, "percentage": 2.24, "elapsed_time": "0:03:48", "remaining_time": "2:46:30", "throughput": 6857.5, "total_tokens": 1569296} {"current_steps": 145, "total_steps": 6252, "loss": 0.5967, "lr": 4.993458048741102e-05, "epoch": 0.06959860802783945, "percentage": 2.32, "elapsed_time": "0:03:57", "remaining_time": "2:46:44", "throughput": 6852.12, "total_tokens": 1627720} {"current_steps": 150, "total_steps": 6252, "loss": 0.6705, "lr": 4.992996075306203e-05, "epoch": 0.07199856002879942, "percentage": 2.4, "elapsed_time": "0:04:05", "remaining_time": "2:46:27", "throughput": 6845.43, "total_tokens": 1680600} {"current_steps": 155, "total_steps": 6252, "loss": 0.5925, "lr": 4.992518364826484e-05, "epoch": 0.0743985120297594, "percentage": 2.48, "elapsed_time": "0:04:13", "remaining_time": "2:45:57", "throughput": 6843.47, "total_tokens": 1732368} {"current_steps": 160, "total_steps": 6252, "loss": 0.5695, "lr": 4.9920249203174945e-05, "epoch": 0.07679846403071938, "percentage": 2.56, "elapsed_time": "0:04:22", "remaining_time": "2:46:17", "throughput": 6848.4, "total_tokens": 1794680} {"current_steps": 165, "total_steps": 6252, "loss": 0.5549, "lr": 4.9915157448941044e-05, "epoch": 0.07919841603167936, "percentage": 2.64, "elapsed_time": "0:04:30", "remaining_time": "2:46:10", "throughput": 6860.26, "total_tokens": 1854040} {"current_steps": 170, "total_steps": 6252, "loss": 0.5701, "lr": 4.9909908417704835e-05, "epoch": 0.08159836803263935, "percentage": 2.72, "elapsed_time": "0:04:38", "remaining_time": "2:45:54", "throughput": 6860.17, "total_tokens": 1908808} {"current_steps": 175, "total_steps": 6252, "loss": 0.5478, "lr": 4.990450214260086e-05, "epoch": 0.08399832003359933, "percentage": 2.8, "elapsed_time": "0:04:46", "remaining_time": "2:45:55", "throughput": 6858.51, "total_tokens": 1966184} {"current_steps": 180, "total_steps": 6252, "loss": 0.5816, "lr": 4.9898938657756234e-05, "epoch": 0.08639827203455931, "percentage": 2.88, "elapsed_time": "0:04:55", "remaining_time": "2:45:59", "throughput": 6853.1, "total_tokens": 2023280} {"current_steps": 185, "total_steps": 6252, "loss": 0.6243, "lr": 4.989321799829048e-05, "epoch": 0.08879822403551929, "percentage": 2.96, "elapsed_time": "0:05:03", "remaining_time": "2:45:48", "throughput": 6853.61, "total_tokens": 2079160} {"current_steps": 190, "total_steps": 6252, "loss": 0.5903, "lr": 4.988734020031527e-05, "epoch": 0.09119817603647927, "percentage": 3.04, "elapsed_time": "0:05:10", "remaining_time": "2:45:09", "throughput": 6856.19, "total_tokens": 2129480} {"current_steps": 195, "total_steps": 6252, "loss": 0.5232, "lr": 4.9881305300934225e-05, "epoch": 0.09359812803743925, "percentage": 3.12, "elapsed_time": "0:05:19", "remaining_time": "2:45:12", "throughput": 6860.04, "total_tokens": 2189160} {"current_steps": 200, "total_steps": 6252, "loss": 0.5846, "lr": 4.987511333824266e-05, "epoch": 0.09599808003839923, "percentage": 3.2, "elapsed_time": "0:05:27", "remaining_time": "2:45:02", "throughput": 6868.78, "total_tokens": 2247704} {"current_steps": 205, "total_steps": 6252, "loss": 0.589, "lr": 4.986876435132736e-05, "epoch": 0.0983980320393592, "percentage": 3.28, "elapsed_time": "0:05:35", "remaining_time": "2:45:03", "throughput": 6871.24, "total_tokens": 2307040} {"current_steps": 210, "total_steps": 6252, "loss": 0.5737, "lr": 4.9862258380266325e-05, "epoch": 0.1007979840403192, "percentage": 3.36, "elapsed_time": "0:05:43", "remaining_time": "2:44:36", "throughput": 6867.81, "total_tokens": 2357488} {"current_steps": 215, "total_steps": 6252, "loss": 0.6138, "lr": 4.985559546612851e-05, "epoch": 0.10319793604127918, "percentage": 3.44, "elapsed_time": "0:05:51", "remaining_time": "2:44:18", "throughput": 6875.57, "total_tokens": 2414064} {"current_steps": 220, "total_steps": 6252, "loss": 0.5923, "lr": 4.984877565097359e-05, "epoch": 0.10559788804223916, "percentage": 3.52, "elapsed_time": "0:05:59", "remaining_time": "2:44:14", "throughput": 6880.15, "total_tokens": 2472744} {"current_steps": 225, "total_steps": 6252, "loss": 0.55, "lr": 4.984179897785166e-05, "epoch": 0.10799784004319914, "percentage": 3.6, "elapsed_time": "0:06:07", "remaining_time": "2:44:00", "throughput": 6883.87, "total_tokens": 2529024} {"current_steps": 230, "total_steps": 6252, "loss": 0.618, "lr": 4.983466549080299e-05, "epoch": 0.11039779204415912, "percentage": 3.68, "elapsed_time": "0:06:15", "remaining_time": "2:43:54", "throughput": 6881.61, "total_tokens": 2584864} {"current_steps": 235, "total_steps": 6252, "loss": 0.6055, "lr": 4.9827375234857735e-05, "epoch": 0.1127977440451191, "percentage": 3.76, "elapsed_time": "0:06:23", "remaining_time": "2:43:32", "throughput": 6885.27, "total_tokens": 2638696} {"current_steps": 240, "total_steps": 6252, "loss": 0.5962, "lr": 4.981992825603566e-05, "epoch": 0.11519769604607907, "percentage": 3.84, "elapsed_time": "0:06:31", "remaining_time": "2:43:29", "throughput": 6892.86, "total_tokens": 2699160} {"current_steps": 245, "total_steps": 6252, "loss": 0.5556, "lr": 4.981232460134584e-05, "epoch": 0.11759764804703907, "percentage": 3.92, "elapsed_time": "0:06:39", "remaining_time": "2:43:26", "throughput": 6891.94, "total_tokens": 2756440} {"current_steps": 250, "total_steps": 6252, "loss": 0.6064, "lr": 4.980456431878636e-05, "epoch": 0.11999760004799905, "percentage": 4.0, "elapsed_time": "0:06:48", "remaining_time": "2:43:20", "throughput": 6887.35, "total_tokens": 2811584} {"current_steps": 255, "total_steps": 6252, "loss": 0.622, "lr": 4.9796647457344034e-05, "epoch": 0.12239755204895902, "percentage": 4.08, "elapsed_time": "0:06:56", "remaining_time": "2:43:04", "throughput": 6885.49, "total_tokens": 2864600} {"current_steps": 260, "total_steps": 6252, "loss": 0.5792, "lr": 4.9788574066994074e-05, "epoch": 0.124797504049919, "percentage": 4.16, "elapsed_time": "0:07:04", "remaining_time": "2:42:54", "throughput": 6885.87, "total_tokens": 2920384} {"current_steps": 265, "total_steps": 6252, "loss": 0.5464, "lr": 4.978034419869977e-05, "epoch": 0.12719745605087898, "percentage": 4.24, "elapsed_time": "0:07:12", "remaining_time": "2:42:51", "throughput": 6881.62, "total_tokens": 2976400} {"current_steps": 270, "total_steps": 6252, "loss": 0.5769, "lr": 4.977195790441219e-05, "epoch": 0.12959740805183897, "percentage": 4.32, "elapsed_time": "0:07:20", "remaining_time": "2:42:43", "throughput": 6879.62, "total_tokens": 3031640} {"current_steps": 275, "total_steps": 6252, "loss": 0.5853, "lr": 4.976341523706986e-05, "epoch": 0.13199736005279894, "percentage": 4.4, "elapsed_time": "0:07:28", "remaining_time": "2:42:27", "throughput": 6885.85, "total_tokens": 3088304} {"current_steps": 280, "total_steps": 6252, "loss": 0.5715, "lr": 4.975471625059837e-05, "epoch": 0.13439731205375893, "percentage": 4.48, "elapsed_time": "0:07:36", "remaining_time": "2:42:21", "throughput": 6889.93, "total_tokens": 3146984} {"current_steps": 285, "total_steps": 6252, "loss": 0.5492, "lr": 4.9745860999910093e-05, "epoch": 0.1367972640547189, "percentage": 4.56, "elapsed_time": "0:07:45", "remaining_time": "2:42:22", "throughput": 6890.38, "total_tokens": 3206416} {"current_steps": 290, "total_steps": 6252, "loss": 0.6008, "lr": 4.973684954090384e-05, "epoch": 0.1391972160556789, "percentage": 4.64, "elapsed_time": "0:07:53", "remaining_time": "2:42:16", "throughput": 6891.96, "total_tokens": 3263920} {"current_steps": 295, "total_steps": 6252, "loss": 0.5588, "lr": 4.972768193046446e-05, "epoch": 0.14159716805663886, "percentage": 4.72, "elapsed_time": "0:08:01", "remaining_time": "2:42:04", "throughput": 6889.97, "total_tokens": 3318032} {"current_steps": 300, "total_steps": 6252, "loss": 0.5692, "lr": 4.971835822646254e-05, "epoch": 0.14399712005759885, "percentage": 4.8, "elapsed_time": "0:08:09", "remaining_time": "2:41:57", "throughput": 6886.59, "total_tokens": 3373136} {"current_steps": 305, "total_steps": 6252, "loss": 0.5801, "lr": 4.9708878487753976e-05, "epoch": 0.14639707205855884, "percentage": 4.88, "elapsed_time": "0:08:17", "remaining_time": "2:41:46", "throughput": 6886.04, "total_tokens": 3428032} {"current_steps": 310, "total_steps": 6252, "loss": 0.5601, "lr": 4.969924277417963e-05, "epoch": 0.1487970240595188, "percentage": 4.96, "elapsed_time": "0:08:25", "remaining_time": "2:41:35", "throughput": 6884.51, "total_tokens": 3482432} {"current_steps": 315, "total_steps": 6252, "loss": 0.6167, "lr": 4.968945114656499e-05, "epoch": 0.1511969760604788, "percentage": 5.04, "elapsed_time": "0:08:33", "remaining_time": "2:41:22", "throughput": 6891.02, "total_tokens": 3540200} {"current_steps": 320, "total_steps": 6252, "loss": 0.5528, "lr": 4.967950366671973e-05, "epoch": 0.15359692806143876, "percentage": 5.12, "elapsed_time": "0:08:40", "remaining_time": "2:40:57", "throughput": 6891.95, "total_tokens": 3590376} {"current_steps": 325, "total_steps": 6252, "loss": 0.582, "lr": 4.966940039743734e-05, "epoch": 0.15599688006239876, "percentage": 5.2, "elapsed_time": "0:08:49", "remaining_time": "2:40:51", "throughput": 6897.37, "total_tokens": 3650392} {"current_steps": 330, "total_steps": 6252, "loss": 0.6262, "lr": 4.965914140249475e-05, "epoch": 0.15839683206335872, "percentage": 5.28, "elapsed_time": "0:08:56", "remaining_time": "2:40:35", "throughput": 6892.92, "total_tokens": 3700960} {"current_steps": 335, "total_steps": 6252, "loss": 0.555, "lr": 4.9648726746651875e-05, "epoch": 0.16079678406431872, "percentage": 5.36, "elapsed_time": "0:09:04", "remaining_time": "2:40:24", "throughput": 6895.14, "total_tokens": 3757192} {"current_steps": 340, "total_steps": 6252, "loss": 0.5747, "lr": 4.9638156495651265e-05, "epoch": 0.1631967360652787, "percentage": 5.44, "elapsed_time": "0:09:12", "remaining_time": "2:40:07", "throughput": 6899.76, "total_tokens": 3812168} {"current_steps": 345, "total_steps": 6252, "loss": 0.562, "lr": 4.9627430716217674e-05, "epoch": 0.16559668806623867, "percentage": 5.52, "elapsed_time": "0:09:21", "remaining_time": "2:40:10", "throughput": 6900.89, "total_tokens": 3873432} {"current_steps": 350, "total_steps": 6252, "loss": 0.5751, "lr": 4.96165494760576e-05, "epoch": 0.16799664006719867, "percentage": 5.6, "elapsed_time": "0:09:29", "remaining_time": "2:40:03", "throughput": 6897.35, "total_tokens": 3928216} {"current_steps": 355, "total_steps": 6252, "loss": 0.5283, "lr": 4.96055128438589e-05, "epoch": 0.17039659206815863, "percentage": 5.68, "elapsed_time": "0:09:37", "remaining_time": "2:40:00", "throughput": 6896.3, "total_tokens": 3985672} {"current_steps": 360, "total_steps": 6252, "loss": 0.5688, "lr": 4.959432088929036e-05, "epoch": 0.17279654406911862, "percentage": 5.76, "elapsed_time": "0:09:46", "remaining_time": "2:39:51", "throughput": 6897.83, "total_tokens": 4042336} {"current_steps": 365, "total_steps": 6252, "loss": 0.5236, "lr": 4.958297368300122e-05, "epoch": 0.1751964960700786, "percentage": 5.84, "elapsed_time": "0:09:54", "remaining_time": "2:39:42", "throughput": 6896.1, "total_tokens": 4097248} {"current_steps": 370, "total_steps": 6252, "loss": 0.5569, "lr": 4.957147129662074e-05, "epoch": 0.17759644807103858, "percentage": 5.92, "elapsed_time": "0:10:02", "remaining_time": "2:39:32", "throughput": 6896.34, "total_tokens": 4152816} {"current_steps": 375, "total_steps": 6252, "loss": 0.5558, "lr": 4.9559813802757785e-05, "epoch": 0.17999640007199855, "percentage": 6.0, "elapsed_time": "0:10:10", "remaining_time": "2:39:28", "throughput": 6896.46, "total_tokens": 4210824} {"current_steps": 380, "total_steps": 6252, "loss": 0.5055, "lr": 4.954800127500031e-05, "epoch": 0.18239635207295854, "percentage": 6.08, "elapsed_time": "0:10:18", "remaining_time": "2:39:21", "throughput": 6890.63, "total_tokens": 4263672} {"current_steps": 385, "total_steps": 6252, "loss": 0.5524, "lr": 4.953603378791493e-05, "epoch": 0.18479630407391853, "percentage": 6.16, "elapsed_time": "0:10:26", "remaining_time": "2:39:10", "throughput": 6891.58, "total_tokens": 4319024} {"current_steps": 390, "total_steps": 6252, "loss": 0.5653, "lr": 4.952391141704644e-05, "epoch": 0.1871962560748785, "percentage": 6.24, "elapsed_time": "0:10:34", "remaining_time": "2:39:01", "throughput": 6894.94, "total_tokens": 4377064} {"current_steps": 395, "total_steps": 6252, "loss": 0.6034, "lr": 4.951163423891735e-05, "epoch": 0.1895962080758385, "percentage": 6.32, "elapsed_time": "0:10:43", "remaining_time": "2:38:57", "throughput": 6895.33, "total_tokens": 4434984} {"current_steps": 400, "total_steps": 6252, "loss": 0.5667, "lr": 4.949920233102736e-05, "epoch": 0.19199616007679846, "percentage": 6.4, "elapsed_time": "0:10:50", "remaining_time": "2:38:43", "throughput": 6901.11, "total_tokens": 4492368} {"current_steps": 405, "total_steps": 6252, "loss": 0.5445, "lr": 4.948661577185295e-05, "epoch": 0.19439611207775845, "percentage": 6.48, "elapsed_time": "0:10:59", "remaining_time": "2:38:40", "throughput": 6898.22, "total_tokens": 4549008} {"current_steps": 410, "total_steps": 6252, "loss": 0.5462, "lr": 4.947387464084679e-05, "epoch": 0.1967960640787184, "percentage": 6.56, "elapsed_time": "0:11:08", "remaining_time": "2:38:41", "throughput": 6897.38, "total_tokens": 4609072} {"current_steps": 415, "total_steps": 6252, "loss": 0.5855, "lr": 4.9460979018437314e-05, "epoch": 0.1991960160796784, "percentage": 6.64, "elapsed_time": "0:11:16", "remaining_time": "2:38:31", "throughput": 6894.72, "total_tokens": 4662560} {"current_steps": 420, "total_steps": 6252, "loss": 0.5909, "lr": 4.944792898602818e-05, "epoch": 0.2015959680806384, "percentage": 6.72, "elapsed_time": "0:11:24", "remaining_time": "2:38:24", "throughput": 6894.33, "total_tokens": 4719248} {"current_steps": 425, "total_steps": 6252, "loss": 0.5211, "lr": 4.943472462599775e-05, "epoch": 0.20399592008159836, "percentage": 6.8, "elapsed_time": "0:11:32", "remaining_time": "2:38:16", "throughput": 6892.68, "total_tokens": 4774096} {"current_steps": 430, "total_steps": 6252, "loss": 0.5245, "lr": 4.942136602169858e-05, "epoch": 0.20639587208255836, "percentage": 6.88, "elapsed_time": "0:11:40", "remaining_time": "2:38:06", "throughput": 6897.36, "total_tokens": 4832616} {"current_steps": 435, "total_steps": 6252, "loss": 0.5304, "lr": 4.94078532574569e-05, "epoch": 0.20879582408351832, "percentage": 6.96, "elapsed_time": "0:11:48", "remaining_time": "2:37:57", "throughput": 6895.52, "total_tokens": 4887208} {"current_steps": 440, "total_steps": 6252, "loss": 0.5879, "lr": 4.939418641857209e-05, "epoch": 0.21119577608447831, "percentage": 7.04, "elapsed_time": "0:11:56", "remaining_time": "2:37:48", "throughput": 6895.24, "total_tokens": 4942504} {"current_steps": 445, "total_steps": 6252, "loss": 0.5854, "lr": 4.938036559131608e-05, "epoch": 0.21359572808543828, "percentage": 7.12, "elapsed_time": "0:12:04", "remaining_time": "2:37:38", "throughput": 6895.31, "total_tokens": 4997880} {"current_steps": 450, "total_steps": 6252, "loss": 0.5545, "lr": 4.9366390862932896e-05, "epoch": 0.21599568008639827, "percentage": 7.2, "elapsed_time": "0:12:13", "remaining_time": "2:37:33", "throughput": 6901.48, "total_tokens": 5060096} {"current_steps": 455, "total_steps": 6252, "loss": 0.528, "lr": 4.9352262321638056e-05, "epoch": 0.21839563208735827, "percentage": 7.28, "elapsed_time": "0:12:21", "remaining_time": "2:37:28", "throughput": 6904.54, "total_tokens": 5120168} {"current_steps": 460, "total_steps": 6252, "loss": 0.5462, "lr": 4.9337980056618006e-05, "epoch": 0.22079558408831823, "percentage": 7.36, "elapsed_time": "0:12:29", "remaining_time": "2:37:22", "throughput": 6901.62, "total_tokens": 5175776} {"current_steps": 465, "total_steps": 6252, "loss": 0.5399, "lr": 4.932354415802959e-05, "epoch": 0.22319553608927822, "percentage": 7.44, "elapsed_time": "0:12:38", "remaining_time": "2:37:14", "throughput": 6901.32, "total_tokens": 5232032} {"current_steps": 470, "total_steps": 6252, "loss": 0.5224, "lr": 4.9308954716999464e-05, "epoch": 0.2255954880902382, "percentage": 7.52, "elapsed_time": "0:12:46", "remaining_time": "2:37:10", "throughput": 6904.3, "total_tokens": 5292688} {"current_steps": 475, "total_steps": 6252, "loss": 0.5335, "lr": 4.92942118256235e-05, "epoch": 0.22799544009119818, "percentage": 7.6, "elapsed_time": "0:12:55", "remaining_time": "2:37:08", "throughput": 6905.15, "total_tokens": 5353096} {"current_steps": 480, "total_steps": 6252, "loss": 0.4755, "lr": 4.9279315576966265e-05, "epoch": 0.23039539209215815, "percentage": 7.68, "elapsed_time": "0:13:04", "remaining_time": "2:37:08", "throughput": 6903.22, "total_tokens": 5412360} {"current_steps": 485, "total_steps": 6252, "loss": 0.5725, "lr": 4.926426606506036e-05, "epoch": 0.23279534409311814, "percentage": 7.76, "elapsed_time": "0:13:12", "remaining_time": "2:36:58", "throughput": 6901.37, "total_tokens": 5466664} {"current_steps": 490, "total_steps": 6252, "loss": 0.5181, "lr": 4.924906338490586e-05, "epoch": 0.23519529609407813, "percentage": 7.84, "elapsed_time": "0:13:20", "remaining_time": "2:36:57", "throughput": 6900.35, "total_tokens": 5526480} {"current_steps": 495, "total_steps": 6252, "loss": 0.5586, "lr": 4.9233707632469746e-05, "epoch": 0.2375952480950381, "percentage": 7.92, "elapsed_time": "0:13:28", "remaining_time": "2:36:45", "throughput": 6899.36, "total_tokens": 5579704} {"current_steps": 500, "total_steps": 6252, "loss": 0.5465, "lr": 4.921819890468523e-05, "epoch": 0.2399952000959981, "percentage": 8.0, "elapsed_time": "0:13:36", "remaining_time": "2:36:34", "throughput": 6898.12, "total_tokens": 5633168} {"current_steps": 505, "total_steps": 6252, "loss": 0.488, "lr": 4.9202537299451215e-05, "epoch": 0.24239515209695806, "percentage": 8.08, "elapsed_time": "0:13:45", "remaining_time": "2:36:29", "throughput": 6899.4, "total_tokens": 5692232} {"current_steps": 510, "total_steps": 6252, "loss": 0.5354, "lr": 4.9186722915631626e-05, "epoch": 0.24479510409791805, "percentage": 8.16, "elapsed_time": "0:13:53", "remaining_time": "2:36:27", "throughput": 6898.33, "total_tokens": 5751464} {"current_steps": 515, "total_steps": 6252, "loss": 0.6093, "lr": 4.9170755853054806e-05, "epoch": 0.247195056098878, "percentage": 8.24, "elapsed_time": "0:14:02", "remaining_time": "2:36:19", "throughput": 6902.24, "total_tokens": 5811696} {"current_steps": 520, "total_steps": 6252, "loss": 0.5436, "lr": 4.915463621251287e-05, "epoch": 0.249595008099838, "percentage": 8.32, "elapsed_time": "0:14:10", "remaining_time": "2:36:15", "throughput": 6898.16, "total_tokens": 5867200} {"current_steps": 525, "total_steps": 6252, "loss": 0.5537, "lr": 4.913836409576112e-05, "epoch": 0.25199496010079797, "percentage": 8.4, "elapsed_time": "0:14:18", "remaining_time": "2:36:07", "throughput": 6899.17, "total_tokens": 5924320} {"current_steps": 530, "total_steps": 6252, "loss": 0.5392, "lr": 4.912193960551732e-05, "epoch": 0.25439491210175796, "percentage": 8.48, "elapsed_time": "0:14:26", "remaining_time": "2:35:56", "throughput": 6899.79, "total_tokens": 5979680} {"current_steps": 535, "total_steps": 6252, "loss": 0.5776, "lr": 4.9105362845461114e-05, "epoch": 0.25679486410271796, "percentage": 8.56, "elapsed_time": "0:14:34", "remaining_time": "2:35:47", "throughput": 6902.39, "total_tokens": 6037568} {"current_steps": 540, "total_steps": 6252, "loss": 0.5463, "lr": 4.9088633920233345e-05, "epoch": 0.25919481610367795, "percentage": 8.64, "elapsed_time": "0:14:43", "remaining_time": "2:35:41", "throughput": 6899.14, "total_tokens": 6092712} {"current_steps": 545, "total_steps": 6252, "loss": 0.6055, "lr": 4.907175293543541e-05, "epoch": 0.2615947681046379, "percentage": 8.72, "elapsed_time": "0:14:51", "remaining_time": "2:35:30", "throughput": 6899.7, "total_tokens": 6147664} {"current_steps": 550, "total_steps": 6252, "loss": 0.6124, "lr": 4.905471999762857e-05, "epoch": 0.2639947201055979, "percentage": 8.8, "elapsed_time": "0:14:58", "remaining_time": "2:35:17", "throughput": 6898.16, "total_tokens": 6199352} {"current_steps": 555, "total_steps": 6252, "loss": 0.5247, "lr": 4.9037535214333287e-05, "epoch": 0.2663946721065579, "percentage": 8.88, "elapsed_time": "0:15:06", "remaining_time": "2:35:08", "throughput": 6898.08, "total_tokens": 6255144} {"current_steps": 560, "total_steps": 6252, "loss": 0.5647, "lr": 4.9020198694028565e-05, "epoch": 0.26879462410751787, "percentage": 8.96, "elapsed_time": "0:15:14", "remaining_time": "2:34:53", "throughput": 6897.33, "total_tokens": 6306704} {"current_steps": 565, "total_steps": 6252, "loss": 0.4978, "lr": 4.900271054615123e-05, "epoch": 0.2711945761084778, "percentage": 9.04, "elapsed_time": "0:15:23", "remaining_time": "2:34:54", "throughput": 6894.21, "total_tokens": 6366360} {"current_steps": 570, "total_steps": 6252, "loss": 0.545, "lr": 4.898507088109527e-05, "epoch": 0.2735945281094378, "percentage": 9.12, "elapsed_time": "0:15:31", "remaining_time": "2:34:44", "throughput": 6894.39, "total_tokens": 6421288} {"current_steps": 575, "total_steps": 6252, "loss": 0.5454, "lr": 4.8967279810211114e-05, "epoch": 0.2759944801103978, "percentage": 9.2, "elapsed_time": "0:15:39", "remaining_time": "2:34:38", "throughput": 6894.91, "total_tokens": 6479424} {"current_steps": 580, "total_steps": 6252, "loss": 0.5506, "lr": 4.894933744580496e-05, "epoch": 0.2783944321113578, "percentage": 9.28, "elapsed_time": "0:15:47", "remaining_time": "2:34:26", "throughput": 6896.27, "total_tokens": 6534464} {"current_steps": 585, "total_steps": 6252, "loss": 0.5536, "lr": 4.893124390113802e-05, "epoch": 0.2807943841123178, "percentage": 9.36, "elapsed_time": "0:15:55", "remaining_time": "2:34:12", "throughput": 6896.59, "total_tokens": 6587088} {"current_steps": 590, "total_steps": 6252, "loss": 0.5646, "lr": 4.8912999290425854e-05, "epoch": 0.2831943361132777, "percentage": 9.44, "elapsed_time": "0:16:03", "remaining_time": "2:34:01", "throughput": 6896.55, "total_tokens": 6641552} {"current_steps": 595, "total_steps": 6252, "loss": 0.5492, "lr": 4.889460372883762e-05, "epoch": 0.2855942881142377, "percentage": 9.52, "elapsed_time": "0:16:11", "remaining_time": "2:33:54", "throughput": 6893.36, "total_tokens": 6695296} {"current_steps": 600, "total_steps": 6252, "loss": 0.5629, "lr": 4.887605733249535e-05, "epoch": 0.2879942401151977, "percentage": 9.6, "elapsed_time": "0:16:19", "remaining_time": "2:33:44", "throughput": 6895.82, "total_tokens": 6753000} {"current_steps": 605, "total_steps": 6252, "loss": 0.5165, "lr": 4.885736021847322e-05, "epoch": 0.2903941921161577, "percentage": 9.68, "elapsed_time": "0:16:27", "remaining_time": "2:33:37", "throughput": 6894.89, "total_tokens": 6808816} {"current_steps": 610, "total_steps": 6252, "loss": 0.5292, "lr": 4.883851250479682e-05, "epoch": 0.2927941441171177, "percentage": 9.76, "elapsed_time": "0:16:35", "remaining_time": "2:33:28", "throughput": 6896.62, "total_tokens": 6866616} {"current_steps": 615, "total_steps": 6252, "loss": 0.5368, "lr": 4.881951431044241e-05, "epoch": 0.2951940961180776, "percentage": 9.84, "elapsed_time": "0:16:44", "remaining_time": "2:33:24", "throughput": 6896.8, "total_tokens": 6926136} {"current_steps": 620, "total_steps": 6252, "loss": 0.5104, "lr": 4.8800365755336114e-05, "epoch": 0.2975940481190376, "percentage": 9.92, "elapsed_time": "0:16:52", "remaining_time": "2:33:17", "throughput": 6896.27, "total_tokens": 6982680} {"current_steps": 625, "total_steps": 6252, "loss": 0.5729, "lr": 4.8781066960353264e-05, "epoch": 0.2999940001199976, "percentage": 10.0, "elapsed_time": "0:17:00", "remaining_time": "2:33:05", "throughput": 6895.31, "total_tokens": 7035152} {"current_steps": 630, "total_steps": 6252, "loss": 0.5777, "lr": 4.876161804731756e-05, "epoch": 0.3023939521209576, "percentage": 10.08, "elapsed_time": "0:17:07", "remaining_time": "2:32:53", "throughput": 6893.22, "total_tokens": 7085976} {"current_steps": 635, "total_steps": 6252, "loss": 0.5729, "lr": 4.87420191390003e-05, "epoch": 0.30479390412191754, "percentage": 10.16, "elapsed_time": "0:17:15", "remaining_time": "2:32:40", "throughput": 6894.03, "total_tokens": 7139560} {"current_steps": 640, "total_steps": 6252, "loss": 0.5212, "lr": 4.872227035911967e-05, "epoch": 0.30719385612287753, "percentage": 10.24, "elapsed_time": "0:17:23", "remaining_time": "2:32:28", "throughput": 6895.19, "total_tokens": 7194016} {"current_steps": 645, "total_steps": 6252, "loss": 0.5227, "lr": 4.87023718323399e-05, "epoch": 0.3095938081238375, "percentage": 10.32, "elapsed_time": "0:17:31", "remaining_time": "2:32:20", "throughput": 6894.35, "total_tokens": 7249352} {"current_steps": 650, "total_steps": 6252, "loss": 0.5057, "lr": 4.868232368427048e-05, "epoch": 0.3119937601247975, "percentage": 10.4, "elapsed_time": "0:17:40", "remaining_time": "2:32:21", "throughput": 6894.02, "total_tokens": 7312768} {"current_steps": 655, "total_steps": 6252, "loss": 0.522, "lr": 4.8662126041465414e-05, "epoch": 0.3143937121257575, "percentage": 10.48, "elapsed_time": "0:17:48", "remaining_time": "2:32:13", "throughput": 6896.74, "total_tokens": 7371440} {"current_steps": 660, "total_steps": 6252, "loss": 0.5712, "lr": 4.864177903142237e-05, "epoch": 0.31679366412671744, "percentage": 10.56, "elapsed_time": "0:17:57", "remaining_time": "2:32:05", "throughput": 6897.16, "total_tokens": 7428856} {"current_steps": 665, "total_steps": 6252, "loss": 0.5763, "lr": 4.862128278258191e-05, "epoch": 0.31919361612767744, "percentage": 10.64, "elapsed_time": "0:18:04", "remaining_time": "2:31:55", "throughput": 6896.72, "total_tokens": 7482928} {"current_steps": 670, "total_steps": 6252, "loss": 0.5921, "lr": 4.8600637424326676e-05, "epoch": 0.32159356812863743, "percentage": 10.72, "elapsed_time": "0:18:12", "remaining_time": "2:31:45", "throughput": 6896.25, "total_tokens": 7537000} {"current_steps": 675, "total_steps": 6252, "loss": 0.5164, "lr": 4.8579843086980536e-05, "epoch": 0.3239935201295974, "percentage": 10.8, "elapsed_time": "0:18:22", "remaining_time": "2:31:46", "throughput": 6895.77, "total_tokens": 7600512} {"current_steps": 680, "total_steps": 6252, "loss": 0.4963, "lr": 4.855889990180781e-05, "epoch": 0.3263934721305574, "percentage": 10.88, "elapsed_time": "0:18:30", "remaining_time": "2:31:39", "throughput": 6893.52, "total_tokens": 7655032} {"current_steps": 685, "total_steps": 6252, "loss": 0.5042, "lr": 4.853780800101241e-05, "epoch": 0.32879342413151735, "percentage": 10.96, "elapsed_time": "0:18:38", "remaining_time": "2:31:30", "throughput": 6892.6, "total_tokens": 7709432} {"current_steps": 690, "total_steps": 6252, "loss": 0.5505, "lr": 4.851656751773702e-05, "epoch": 0.33119337613247735, "percentage": 11.04, "elapsed_time": "0:18:46", "remaining_time": "2:31:24", "throughput": 6893.07, "total_tokens": 7768248} {"current_steps": 695, "total_steps": 6252, "loss": 0.5219, "lr": 4.849517858606225e-05, "epoch": 0.33359332813343734, "percentage": 11.12, "elapsed_time": "0:18:55", "remaining_time": "2:31:15", "throughput": 6891.58, "total_tokens": 7821976} {"current_steps": 700, "total_steps": 6252, "loss": 0.541, "lr": 4.84736413410058e-05, "epoch": 0.33599328013439733, "percentage": 11.2, "elapsed_time": "0:19:02", "remaining_time": "2:31:05", "throughput": 6890.32, "total_tokens": 7875264} {"current_steps": 705, "total_steps": 6252, "loss": 0.5666, "lr": 4.8451955918521586e-05, "epoch": 0.33839323213535727, "percentage": 11.28, "elapsed_time": "0:19:10", "remaining_time": "2:30:54", "throughput": 6890.56, "total_tokens": 7929656} {"current_steps": 710, "total_steps": 6252, "loss": 0.5295, "lr": 4.84301224554989e-05, "epoch": 0.34079318413631726, "percentage": 11.36, "elapsed_time": "0:19:18", "remaining_time": "2:30:42", "throughput": 6889.46, "total_tokens": 7980872} {"current_steps": 715, "total_steps": 6252, "loss": 0.5509, "lr": 4.840814108976154e-05, "epoch": 0.34319313613727725, "percentage": 11.44, "elapsed_time": "0:19:26", "remaining_time": "2:30:33", "throughput": 6890.44, "total_tokens": 8037376} {"current_steps": 720, "total_steps": 6252, "loss": 0.54, "lr": 4.838601196006694e-05, "epoch": 0.34559308813823725, "percentage": 11.52, "elapsed_time": "0:19:34", "remaining_time": "2:30:27", "throughput": 6888.68, "total_tokens": 8094024} {"current_steps": 725, "total_steps": 6252, "loss": 0.5663, "lr": 4.8363735206105276e-05, "epoch": 0.34799304013919724, "percentage": 11.6, "elapsed_time": "0:19:43", "remaining_time": "2:30:19", "throughput": 6890.23, "total_tokens": 8152456} {"current_steps": 730, "total_steps": 6252, "loss": 0.5171, "lr": 4.8341310968498656e-05, "epoch": 0.3503929921401572, "percentage": 11.68, "elapsed_time": "0:19:51", "remaining_time": "2:30:09", "throughput": 6889.76, "total_tokens": 8206424} {"current_steps": 735, "total_steps": 6252, "loss": 0.5407, "lr": 4.831873938880012e-05, "epoch": 0.35279294414111717, "percentage": 11.76, "elapsed_time": "0:19:59", "remaining_time": "2:30:01", "throughput": 6889.93, "total_tokens": 8262160} {"current_steps": 740, "total_steps": 6252, "loss": 0.5729, "lr": 4.829602060949282e-05, "epoch": 0.35519289614207716, "percentage": 11.84, "elapsed_time": "0:20:07", "remaining_time": "2:29:50", "throughput": 6889.9, "total_tokens": 8316480} {"current_steps": 745, "total_steps": 6252, "loss": 0.4796, "lr": 4.827315477398914e-05, "epoch": 0.35759284814303716, "percentage": 11.92, "elapsed_time": "0:20:16", "remaining_time": "2:29:51", "throughput": 6888.37, "total_tokens": 8379024} {"current_steps": 750, "total_steps": 6252, "loss": 0.5178, "lr": 4.825014202662972e-05, "epoch": 0.3599928001439971, "percentage": 12.0, "elapsed_time": "0:20:24", "remaining_time": "2:29:43", "throughput": 6889.28, "total_tokens": 8436408} {"current_steps": 755, "total_steps": 6252, "loss": 0.5436, "lr": 4.82269825126826e-05, "epoch": 0.3623927521449571, "percentage": 12.08, "elapsed_time": "0:20:33", "remaining_time": "2:29:38", "throughput": 6888.43, "total_tokens": 8494184} {"current_steps": 760, "total_steps": 6252, "loss": 0.5761, "lr": 4.8203676378342263e-05, "epoch": 0.3647927041459171, "percentage": 12.16, "elapsed_time": "0:20:40", "remaining_time": "2:29:23", "throughput": 6887.47, "total_tokens": 8543600} {"current_steps": 765, "total_steps": 6252, "loss": 0.5519, "lr": 4.818022377072876e-05, "epoch": 0.36719265614687707, "percentage": 12.24, "elapsed_time": "0:20:49", "remaining_time": "2:29:20", "throughput": 6885.12, "total_tokens": 8601672} {"current_steps": 770, "total_steps": 6252, "loss": 0.5488, "lr": 4.8156624837886744e-05, "epoch": 0.36959260814783707, "percentage": 12.32, "elapsed_time": "0:20:57", "remaining_time": "2:29:11", "throughput": 6883.5, "total_tokens": 8654824} {"current_steps": 775, "total_steps": 6252, "loss": 0.5093, "lr": 4.813287972878454e-05, "epoch": 0.371992560148797, "percentage": 12.4, "elapsed_time": "0:21:05", "remaining_time": "2:29:03", "throughput": 6882.13, "total_tokens": 8709032} {"current_steps": 780, "total_steps": 6252, "loss": 0.5451, "lr": 4.810898859331322e-05, "epoch": 0.374392512149757, "percentage": 12.48, "elapsed_time": "0:21:13", "remaining_time": "2:28:54", "throughput": 6882.94, "total_tokens": 8766264} {"current_steps": 785, "total_steps": 6252, "loss": 0.4965, "lr": 4.8084951582285634e-05, "epoch": 0.376792464150717, "percentage": 12.56, "elapsed_time": "0:21:21", "remaining_time": "2:28:42", "throughput": 6884.41, "total_tokens": 8820344} {"current_steps": 790, "total_steps": 6252, "loss": 0.5298, "lr": 4.80607688474355e-05, "epoch": 0.379192416151677, "percentage": 12.64, "elapsed_time": "0:21:29", "remaining_time": "2:28:36", "throughput": 6886.83, "total_tokens": 8881528} {"current_steps": 795, "total_steps": 6252, "loss": 0.5278, "lr": 4.803644054141639e-05, "epoch": 0.381592368152637, "percentage": 12.72, "elapsed_time": "0:21:38", "remaining_time": "2:28:30", "throughput": 6887.04, "total_tokens": 8939712} {"current_steps": 800, "total_steps": 6252, "loss": 0.548, "lr": 4.8011966817800804e-05, "epoch": 0.3839923201535969, "percentage": 12.8, "elapsed_time": "0:21:46", "remaining_time": "2:28:21", "throughput": 6886.5, "total_tokens": 8994888} {"current_steps": 805, "total_steps": 6252, "loss": 0.5446, "lr": 4.79873478310792e-05, "epoch": 0.3863922721545569, "percentage": 12.88, "elapsed_time": "0:21:53", "remaining_time": "2:28:10", "throughput": 6889.24, "total_tokens": 9052200} {"current_steps": 810, "total_steps": 6252, "loss": 0.5531, "lr": 4.796258373665899e-05, "epoch": 0.3887922241555169, "percentage": 12.96, "elapsed_time": "0:22:02", "remaining_time": "2:28:02", "throughput": 6888.29, "total_tokens": 9106936} {"current_steps": 815, "total_steps": 6252, "loss": 0.5786, "lr": 4.793767469086361e-05, "epoch": 0.3911921761564769, "percentage": 13.04, "elapsed_time": "0:22:09", "remaining_time": "2:27:51", "throughput": 6886.9, "total_tokens": 9158400} {"current_steps": 820, "total_steps": 6252, "loss": 0.5285, "lr": 4.791262085093147e-05, "epoch": 0.3935921281574368, "percentage": 13.12, "elapsed_time": "0:22:18", "remaining_time": "2:27:45", "throughput": 6888.13, "total_tokens": 9218552} {"current_steps": 825, "total_steps": 6252, "loss": 0.5481, "lr": 4.788742237501499e-05, "epoch": 0.3959920801583968, "percentage": 13.2, "elapsed_time": "0:22:26", "remaining_time": "2:27:36", "throughput": 6887.52, "total_tokens": 9272768} {"current_steps": 830, "total_steps": 6252, "loss": 0.5457, "lr": 4.786207942217965e-05, "epoch": 0.3983920321593568, "percentage": 13.28, "elapsed_time": "0:22:34", "remaining_time": "2:27:26", "throughput": 6887.4, "total_tokens": 9327048} {"current_steps": 835, "total_steps": 6252, "loss": 0.5067, "lr": 4.783659215240289e-05, "epoch": 0.4007919841603168, "percentage": 13.36, "elapsed_time": "0:22:43", "remaining_time": "2:27:23", "throughput": 6887.63, "total_tokens": 9389344} {"current_steps": 840, "total_steps": 6252, "loss": 0.5576, "lr": 4.78109607265732e-05, "epoch": 0.4031919361612768, "percentage": 13.44, "elapsed_time": "0:22:51", "remaining_time": "2:27:16", "throughput": 6886.57, "total_tokens": 9444656} {"current_steps": 845, "total_steps": 6252, "loss": 0.5566, "lr": 4.778518530648899e-05, "epoch": 0.40559188816223674, "percentage": 13.52, "elapsed_time": "0:22:59", "remaining_time": "2:27:08", "throughput": 6885.31, "total_tokens": 9499464} {"current_steps": 850, "total_steps": 6252, "loss": 0.5486, "lr": 4.77592660548577e-05, "epoch": 0.40799184016319673, "percentage": 13.6, "elapsed_time": "0:23:07", "remaining_time": "2:26:59", "throughput": 6884.31, "total_tokens": 9553432} {"current_steps": 855, "total_steps": 6252, "loss": 0.5289, "lr": 4.7733203135294676e-05, "epoch": 0.4103917921641567, "percentage": 13.68, "elapsed_time": "0:23:15", "remaining_time": "2:26:51", "throughput": 6882.93, "total_tokens": 9608536} {"current_steps": 860, "total_steps": 6252, "loss": 0.5261, "lr": 4.770699671232216e-05, "epoch": 0.4127917441651167, "percentage": 13.76, "elapsed_time": "0:23:23", "remaining_time": "2:26:41", "throughput": 6882.45, "total_tokens": 9661208} {"current_steps": 865, "total_steps": 6252, "loss": 0.5306, "lr": 4.768064695136829e-05, "epoch": 0.41519169616607665, "percentage": 13.84, "elapsed_time": "0:23:32", "remaining_time": "2:26:34", "throughput": 6884.37, "total_tokens": 9721752} {"current_steps": 870, "total_steps": 6252, "loss": 0.5549, "lr": 4.765415401876599e-05, "epoch": 0.41759164816703664, "percentage": 13.92, "elapsed_time": "0:23:40", "remaining_time": "2:26:26", "throughput": 6885.41, "total_tokens": 9779768} {"current_steps": 875, "total_steps": 6252, "loss": 0.5355, "lr": 4.7627518081751975e-05, "epoch": 0.41999160016799664, "percentage": 14.0, "elapsed_time": "0:23:48", "remaining_time": "2:26:19", "throughput": 6884.32, "total_tokens": 9835272} {"current_steps": 880, "total_steps": 6252, "loss": 0.5411, "lr": 4.760073930846569e-05, "epoch": 0.42239155216895663, "percentage": 14.08, "elapsed_time": "0:23:56", "remaining_time": "2:26:08", "throughput": 6885.4, "total_tokens": 9890512} {"current_steps": 885, "total_steps": 6252, "loss": 0.5432, "lr": 4.75738178679482e-05, "epoch": 0.4247915041699166, "percentage": 14.16, "elapsed_time": "0:24:04", "remaining_time": "2:25:58", "throughput": 6885.79, "total_tokens": 9944392} {"current_steps": 890, "total_steps": 6252, "loss": 0.4997, "lr": 4.754675393014117e-05, "epoch": 0.42719145617087656, "percentage": 14.24, "elapsed_time": "0:24:12", "remaining_time": "2:25:49", "throughput": 6884.84, "total_tokens": 9999080} {"current_steps": 895, "total_steps": 6252, "loss": 0.5276, "lr": 4.751954766588581e-05, "epoch": 0.42959140817183655, "percentage": 14.32, "elapsed_time": "0:24:20", "remaining_time": "2:25:44", "throughput": 6881.71, "total_tokens": 10053320} {"current_steps": 900, "total_steps": 6252, "loss": 0.4801, "lr": 4.749219924692172e-05, "epoch": 0.43199136017279655, "percentage": 14.4, "elapsed_time": "0:24:29", "remaining_time": "2:25:38", "throughput": 6881.92, "total_tokens": 10112592} {"current_steps": 905, "total_steps": 6252, "loss": 0.4976, "lr": 4.7464708845885877e-05, "epoch": 0.43439131217375654, "percentage": 14.48, "elapsed_time": "0:24:37", "remaining_time": "2:25:31", "throughput": 6880.66, "total_tokens": 10168072} {"current_steps": 910, "total_steps": 6252, "loss": 0.5343, "lr": 4.7437076636311514e-05, "epoch": 0.43679126417471653, "percentage": 14.56, "elapsed_time": "0:24:46", "remaining_time": "2:25:23", "throughput": 6878.47, "total_tokens": 10221648} {"current_steps": 915, "total_steps": 6252, "loss": 0.4946, "lr": 4.7409302792627044e-05, "epoch": 0.43919121617567647, "percentage": 14.64, "elapsed_time": "0:24:54", "remaining_time": "2:25:18", "throughput": 6879.88, "total_tokens": 10284000} {"current_steps": 920, "total_steps": 6252, "loss": 0.5109, "lr": 4.738138749015492e-05, "epoch": 0.44159116817663646, "percentage": 14.72, "elapsed_time": "0:25:02", "remaining_time": "2:25:10", "throughput": 6880.46, "total_tokens": 10340768} {"current_steps": 925, "total_steps": 6252, "loss": 0.5082, "lr": 4.735333090511056e-05, "epoch": 0.44399112017759645, "percentage": 14.8, "elapsed_time": "0:25:11", "remaining_time": "2:25:05", "throughput": 6880.37, "total_tokens": 10400928} {"current_steps": 930, "total_steps": 6252, "loss": 0.5612, "lr": 4.732513321460127e-05, "epoch": 0.44639107217855645, "percentage": 14.88, "elapsed_time": "0:25:19", "remaining_time": "2:24:57", "throughput": 6879.85, "total_tokens": 10456208} {"current_steps": 935, "total_steps": 6252, "loss": 0.5253, "lr": 4.729679459662502e-05, "epoch": 0.4487910241795164, "percentage": 14.96, "elapsed_time": "0:25:28", "remaining_time": "2:24:52", "throughput": 6877.87, "total_tokens": 10513352} {"current_steps": 940, "total_steps": 6252, "loss": 0.5403, "lr": 4.726831523006944e-05, "epoch": 0.4511909761804764, "percentage": 15.04, "elapsed_time": "0:25:37", "remaining_time": "2:24:48", "throughput": 6873.86, "total_tokens": 10568872} {"current_steps": 945, "total_steps": 6252, "loss": 0.5332, "lr": 4.7239695294710586e-05, "epoch": 0.45359092818143637, "percentage": 15.12, "elapsed_time": "0:25:45", "remaining_time": "2:24:40", "throughput": 6873.45, "total_tokens": 10623984} {"current_steps": 950, "total_steps": 6252, "loss": 0.572, "lr": 4.7210934971211906e-05, "epoch": 0.45599088018239636, "percentage": 15.2, "elapsed_time": "0:25:53", "remaining_time": "2:24:28", "throughput": 6872.77, "total_tokens": 10675064} {"current_steps": 955, "total_steps": 6252, "loss": 0.4812, "lr": 4.718203444112301e-05, "epoch": 0.45839083218335636, "percentage": 15.28, "elapsed_time": "0:26:01", "remaining_time": "2:24:22", "throughput": 6874.15, "total_tokens": 10735624} {"current_steps": 960, "total_steps": 6252, "loss": 0.4681, "lr": 4.7152993886878585e-05, "epoch": 0.4607907841843163, "percentage": 15.36, "elapsed_time": "0:26:09", "remaining_time": "2:24:12", "throughput": 6874.88, "total_tokens": 10790472} {"current_steps": 965, "total_steps": 6252, "loss": 0.508, "lr": 4.712381349179721e-05, "epoch": 0.4631907361852763, "percentage": 15.44, "elapsed_time": "0:26:17", "remaining_time": "2:24:01", "throughput": 6875.47, "total_tokens": 10844896} {"current_steps": 970, "total_steps": 6252, "loss": 0.4988, "lr": 4.709449344008021e-05, "epoch": 0.4655906881862363, "percentage": 15.52, "elapsed_time": "0:26:26", "remaining_time": "2:23:56", "throughput": 6874.24, "total_tokens": 10902552} {"current_steps": 975, "total_steps": 6252, "loss": 0.5755, "lr": 4.706503391681049e-05, "epoch": 0.46799064018719627, "percentage": 15.6, "elapsed_time": "0:26:33", "remaining_time": "2:23:44", "throughput": 6875.26, "total_tokens": 10956224} {"current_steps": 980, "total_steps": 6252, "loss": 0.5283, "lr": 4.7035435107951384e-05, "epoch": 0.47039059218815626, "percentage": 15.67, "elapsed_time": "0:26:41", "remaining_time": "2:23:36", "throughput": 6874.97, "total_tokens": 11011072} {"current_steps": 985, "total_steps": 6252, "loss": 0.4954, "lr": 4.700569720034545e-05, "epoch": 0.4727905441891162, "percentage": 15.75, "elapsed_time": "0:26:49", "remaining_time": "2:23:27", "throughput": 6874.67, "total_tokens": 11066344} {"current_steps": 990, "total_steps": 6252, "loss": 0.5431, "lr": 4.697582038171332e-05, "epoch": 0.4751904961900762, "percentage": 15.83, "elapsed_time": "0:26:57", "remaining_time": "2:23:19", "throughput": 6873.63, "total_tokens": 11121472} {"current_steps": 995, "total_steps": 6252, "loss": 0.4836, "lr": 4.694580484065248e-05, "epoch": 0.4775904481910362, "percentage": 15.91, "elapsed_time": "0:27:07", "remaining_time": "2:23:16", "throughput": 6871.98, "total_tokens": 11181736} {"current_steps": 1000, "total_steps": 6252, "loss": 0.4765, "lr": 4.6915650766636156e-05, "epoch": 0.4799904001919962, "percentage": 15.99, "elapsed_time": "0:27:15", "remaining_time": "2:23:10", "throughput": 6873.35, "total_tokens": 11241912} {"current_steps": 1005, "total_steps": 6252, "loss": 0.523, "lr": 4.6885358350011986e-05, "epoch": 0.4823903521929561, "percentage": 16.07, "elapsed_time": "0:27:23", "remaining_time": "2:23:02", "throughput": 6871.71, "total_tokens": 11296568} {"current_steps": 1010, "total_steps": 6252, "loss": 0.4891, "lr": 4.6854927782000954e-05, "epoch": 0.4847903041939161, "percentage": 16.15, "elapsed_time": "0:27:32", "remaining_time": "2:22:54", "throughput": 6871.46, "total_tokens": 11351944} {"current_steps": 1015, "total_steps": 6252, "loss": 0.502, "lr": 4.6824359254696105e-05, "epoch": 0.4871902561948761, "percentage": 16.23, "elapsed_time": "0:27:41", "remaining_time": "2:22:50", "throughput": 6869.17, "total_tokens": 11410584} {"current_steps": 1020, "total_steps": 6252, "loss": 0.5451, "lr": 4.6793652961061364e-05, "epoch": 0.4895902081958361, "percentage": 16.31, "elapsed_time": "0:27:49", "remaining_time": "2:22:43", "throughput": 6867.39, "total_tokens": 11465560} {"current_steps": 1025, "total_steps": 6252, "loss": 0.5277, "lr": 4.676280909493028e-05, "epoch": 0.4919901601967961, "percentage": 16.39, "elapsed_time": "0:27:58", "remaining_time": "2:22:37", "throughput": 6867.09, "total_tokens": 11523960} {"current_steps": 1030, "total_steps": 6252, "loss": 0.4885, "lr": 4.673182785100485e-05, "epoch": 0.494390112197756, "percentage": 16.47, "elapsed_time": "0:28:07", "remaining_time": "2:22:34", "throughput": 6865.99, "total_tokens": 11584904} {"current_steps": 1035, "total_steps": 6252, "loss": 0.5266, "lr": 4.6700709424854274e-05, "epoch": 0.496790064198716, "percentage": 16.55, "elapsed_time": "0:28:16", "remaining_time": "2:22:30", "throughput": 6863.61, "total_tokens": 11642456} {"current_steps": 1040, "total_steps": 6252, "loss": 0.5813, "lr": 4.66694540129137e-05, "epoch": 0.499190016199676, "percentage": 16.63, "elapsed_time": "0:28:24", "remaining_time": "2:22:19", "throughput": 6864.38, "total_tokens": 11696912} {"current_steps": 1045, "total_steps": 6252, "loss": 0.4875, "lr": 4.6638061812483005e-05, "epoch": 0.501589968200636, "percentage": 16.71, "elapsed_time": "0:28:32", "remaining_time": "2:22:12", "throughput": 6865.0, "total_tokens": 11755104} {"current_steps": 1050, "total_steps": 6252, "loss": 0.5367, "lr": 4.660653302172554e-05, "epoch": 0.5039899202015959, "percentage": 16.79, "elapsed_time": "0:28:40", "remaining_time": "2:22:03", "throughput": 6865.18, "total_tokens": 11810984} {"current_steps": 1055, "total_steps": 6252, "loss": 0.5314, "lr": 4.6574867839666895e-05, "epoch": 0.5063898722025559, "percentage": 16.87, "elapsed_time": "0:28:48", "remaining_time": "2:21:54", "throughput": 6862.77, "total_tokens": 11862312} {"current_steps": 1060, "total_steps": 6252, "loss": 0.5496, "lr": 4.654306646619361e-05, "epoch": 0.5087898242035159, "percentage": 16.95, "elapsed_time": "0:28:57", "remaining_time": "2:21:49", "throughput": 6862.8, "total_tokens": 11923072} {"current_steps": 1065, "total_steps": 6252, "loss": 0.5205, "lr": 4.6511129102051954e-05, "epoch": 0.5111897762044759, "percentage": 17.03, "elapsed_time": "0:29:05", "remaining_time": "2:21:40", "throughput": 6862.97, "total_tokens": 11978568} {"current_steps": 1070, "total_steps": 6252, "loss": 0.4768, "lr": 4.647905594884663e-05, "epoch": 0.5135897282054359, "percentage": 17.11, "elapsed_time": "0:29:14", "remaining_time": "2:21:35", "throughput": 6860.38, "total_tokens": 12035000} {"current_steps": 1075, "total_steps": 6252, "loss": 0.5136, "lr": 4.6446847209039504e-05, "epoch": 0.5159896802063959, "percentage": 17.19, "elapsed_time": "0:29:22", "remaining_time": "2:21:28", "throughput": 6862.63, "total_tokens": 12096040} {"current_steps": 1080, "total_steps": 6252, "loss": 0.5022, "lr": 4.6414503085948334e-05, "epoch": 0.5183896322073559, "percentage": 17.27, "elapsed_time": "0:29:30", "remaining_time": "2:21:17", "throughput": 6862.34, "total_tokens": 12148448} {"current_steps": 1085, "total_steps": 6252, "loss": 0.5196, "lr": 4.63820237837455e-05, "epoch": 0.5207895842083158, "percentage": 17.35, "elapsed_time": "0:29:38", "remaining_time": "2:21:08", "throughput": 6864.33, "total_tokens": 12207120} {"current_steps": 1090, "total_steps": 6252, "loss": 0.5566, "lr": 4.634940950745668e-05, "epoch": 0.5231895362092758, "percentage": 17.43, "elapsed_time": "0:29:46", "remaining_time": "2:21:00", "throughput": 6862.96, "total_tokens": 12261136} {"current_steps": 1095, "total_steps": 6252, "loss": 0.5483, "lr": 4.631666046295959e-05, "epoch": 0.5255894882102358, "percentage": 17.51, "elapsed_time": "0:29:54", "remaining_time": "2:20:52", "throughput": 6861.13, "total_tokens": 12313856} {"current_steps": 1100, "total_steps": 6252, "loss": 0.5072, "lr": 4.628377685698268e-05, "epoch": 0.5279894402111958, "percentage": 17.59, "elapsed_time": "0:30:02", "remaining_time": "2:20:43", "throughput": 6860.25, "total_tokens": 12367984} {"current_steps": 1105, "total_steps": 6252, "loss": 0.5316, "lr": 4.6250758897103775e-05, "epoch": 0.5303893922121558, "percentage": 17.67, "elapsed_time": "0:30:10", "remaining_time": "2:20:34", "throughput": 6860.07, "total_tokens": 12422128} {"current_steps": 1110, "total_steps": 6252, "loss": 0.4781, "lr": 4.621760679174887e-05, "epoch": 0.5327893442131157, "percentage": 17.75, "elapsed_time": "0:30:18", "remaining_time": "2:20:25", "throughput": 6860.34, "total_tokens": 12477576} {"current_steps": 1115, "total_steps": 6252, "loss": 0.5028, "lr": 4.618432075019071e-05, "epoch": 0.5351892962140757, "percentage": 17.83, "elapsed_time": "0:30:26", "remaining_time": "2:20:17", "throughput": 6862.21, "total_tokens": 12536840} {"current_steps": 1120, "total_steps": 6252, "loss": 0.5637, "lr": 4.615090098254753e-05, "epoch": 0.5375892482150357, "percentage": 17.91, "elapsed_time": "0:30:35", "remaining_time": "2:20:08", "throughput": 6862.23, "total_tokens": 12592424} {"current_steps": 1125, "total_steps": 6252, "loss": 0.5276, "lr": 4.6117347699781706e-05, "epoch": 0.5399892002159957, "percentage": 17.99, "elapsed_time": "0:30:43", "remaining_time": "2:20:02", "throughput": 6861.53, "total_tokens": 12650424} {"current_steps": 1130, "total_steps": 6252, "loss": 0.518, "lr": 4.608366111369843e-05, "epoch": 0.5423891522169556, "percentage": 18.07, "elapsed_time": "0:30:51", "remaining_time": "2:19:53", "throughput": 6861.77, "total_tokens": 12706224} {"current_steps": 1135, "total_steps": 6252, "loss": 0.4956, "lr": 4.6049841436944385e-05, "epoch": 0.5447891042179156, "percentage": 18.15, "elapsed_time": "0:31:00", "remaining_time": "2:19:49", "throughput": 6860.97, "total_tokens": 12767096} {"current_steps": 1140, "total_steps": 6252, "loss": 0.539, "lr": 4.6015888883006364e-05, "epoch": 0.5471890562188756, "percentage": 18.23, "elapsed_time": "0:31:08", "remaining_time": "2:19:39", "throughput": 6861.1, "total_tokens": 12821808} {"current_steps": 1145, "total_steps": 6252, "loss": 0.5163, "lr": 4.598180366620996e-05, "epoch": 0.5495890082198356, "percentage": 18.31, "elapsed_time": "0:31:16", "remaining_time": "2:19:31", "throughput": 6859.96, "total_tokens": 12874928} {"current_steps": 1150, "total_steps": 6252, "loss": 0.5662, "lr": 4.594758600171821e-05, "epoch": 0.5519889602207956, "percentage": 18.39, "elapsed_time": "0:31:24", "remaining_time": "2:19:20", "throughput": 6860.13, "total_tokens": 12927848} {"current_steps": 1155, "total_steps": 6252, "loss": 0.493, "lr": 4.591323610553021e-05, "epoch": 0.5543889122217556, "percentage": 18.47, "elapsed_time": "0:31:32", "remaining_time": "2:19:11", "throughput": 6861.32, "total_tokens": 12985640} {"current_steps": 1160, "total_steps": 6252, "loss": 0.5289, "lr": 4.587875419447979e-05, "epoch": 0.5567888642227156, "percentage": 18.55, "elapsed_time": "0:31:41", "remaining_time": "2:19:04", "throughput": 6860.22, "total_tokens": 13041608} {"current_steps": 1165, "total_steps": 6252, "loss": 0.4997, "lr": 4.5844140486234086e-05, "epoch": 0.5591888162236756, "percentage": 18.63, "elapsed_time": "0:31:49", "remaining_time": "2:18:56", "throughput": 6858.65, "total_tokens": 13094240} {"current_steps": 1170, "total_steps": 6252, "loss": 0.5155, "lr": 4.580939519929226e-05, "epoch": 0.5615887682246355, "percentage": 18.71, "elapsed_time": "0:31:57", "remaining_time": "2:18:47", "throughput": 6859.2, "total_tokens": 13150544} {"current_steps": 1175, "total_steps": 6252, "loss": 0.4927, "lr": 4.577451855298402e-05, "epoch": 0.5639887202255955, "percentage": 18.79, "elapsed_time": "0:32:05", "remaining_time": "2:18:40", "throughput": 6860.22, "total_tokens": 13211016} {"current_steps": 1180, "total_steps": 6252, "loss": 0.5525, "lr": 4.5739510767468295e-05, "epoch": 0.5663886722265554, "percentage": 18.87, "elapsed_time": "0:32:14", "remaining_time": "2:18:34", "throughput": 6859.37, "total_tokens": 13269168} {"current_steps": 1185, "total_steps": 6252, "loss": 0.5094, "lr": 4.570437206373183e-05, "epoch": 0.5687886242275154, "percentage": 18.95, "elapsed_time": "0:32:22", "remaining_time": "2:18:27", "throughput": 6859.56, "total_tokens": 13326336} {"current_steps": 1190, "total_steps": 6252, "loss": 0.5036, "lr": 4.5669102663587795e-05, "epoch": 0.5711885762284754, "percentage": 19.03, "elapsed_time": "0:32:30", "remaining_time": "2:18:17", "throughput": 6860.66, "total_tokens": 13382784} {"current_steps": 1195, "total_steps": 6252, "loss": 0.523, "lr": 4.563370278967437e-05, "epoch": 0.5735885282294354, "percentage": 19.11, "elapsed_time": "0:32:38", "remaining_time": "2:18:08", "throughput": 6860.76, "total_tokens": 13438016} {"current_steps": 1200, "total_steps": 6252, "loss": 0.562, "lr": 4.559817266545337e-05, "epoch": 0.5759884802303954, "percentage": 19.19, "elapsed_time": "0:32:46", "remaining_time": "2:17:59", "throughput": 6861.13, "total_tokens": 13492904} {"current_steps": 1205, "total_steps": 6252, "loss": 0.5257, "lr": 4.5562512515208816e-05, "epoch": 0.5783884322313554, "percentage": 19.27, "elapsed_time": "0:32:54", "remaining_time": "2:17:48", "throughput": 6862.1, "total_tokens": 13546992} {"current_steps": 1210, "total_steps": 6252, "loss": 0.5234, "lr": 4.5526722564045486e-05, "epoch": 0.5807883842323154, "percentage": 19.35, "elapsed_time": "0:33:01", "remaining_time": "2:17:38", "throughput": 6861.74, "total_tokens": 13599704} {"current_steps": 1215, "total_steps": 6252, "loss": 0.4522, "lr": 4.5490803037887556e-05, "epoch": 0.5831883362332754, "percentage": 19.43, "elapsed_time": "0:33:10", "remaining_time": "2:17:31", "throughput": 6862.65, "total_tokens": 13658840} {"current_steps": 1220, "total_steps": 6252, "loss": 0.504, "lr": 4.545475416347714e-05, "epoch": 0.5855882882342354, "percentage": 19.51, "elapsed_time": "0:33:18", "remaining_time": "2:17:22", "throughput": 6861.64, "total_tokens": 13712920} {"current_steps": 1225, "total_steps": 6252, "loss": 0.5473, "lr": 4.5418576168372864e-05, "epoch": 0.5879882402351952, "percentage": 19.59, "elapsed_time": "0:33:26", "remaining_time": "2:17:12", "throughput": 6862.93, "total_tokens": 13768056} {"current_steps": 1230, "total_steps": 6252, "loss": 0.5321, "lr": 4.538226928094841e-05, "epoch": 0.5903881922361552, "percentage": 19.67, "elapsed_time": "0:33:34", "remaining_time": "2:17:05", "throughput": 6863.29, "total_tokens": 13826288} {"current_steps": 1235, "total_steps": 6252, "loss": 0.5578, "lr": 4.534583373039112e-05, "epoch": 0.5927881442371152, "percentage": 19.75, "elapsed_time": "0:33:42", "remaining_time": "2:16:55", "throughput": 6863.23, "total_tokens": 13880688} {"current_steps": 1240, "total_steps": 6252, "loss": 0.5097, "lr": 4.530926974670052e-05, "epoch": 0.5951880962380752, "percentage": 19.83, "elapsed_time": "0:33:50", "remaining_time": "2:16:47", "throughput": 6863.28, "total_tokens": 13937072} {"current_steps": 1245, "total_steps": 6252, "loss": 0.5038, "lr": 4.5272577560686834e-05, "epoch": 0.5975880482390352, "percentage": 19.91, "elapsed_time": "0:33:58", "remaining_time": "2:16:38", "throughput": 6862.99, "total_tokens": 13990528} {"current_steps": 1250, "total_steps": 6252, "loss": 0.5304, "lr": 4.523575740396962e-05, "epoch": 0.5999880002399952, "percentage": 19.99, "elapsed_time": "0:34:06", "remaining_time": "2:16:30", "throughput": 6861.74, "total_tokens": 14044296} {"current_steps": 1255, "total_steps": 6252, "loss": 0.4927, "lr": 4.5198809508976206e-05, "epoch": 0.6023879522409552, "percentage": 20.07, "elapsed_time": "0:34:15", "remaining_time": "2:16:23", "throughput": 6861.68, "total_tokens": 14102520} {"current_steps": 1260, "total_steps": 6252, "loss": 0.5067, "lr": 4.516173410894028e-05, "epoch": 0.6047879042419152, "percentage": 20.15, "elapsed_time": "0:34:22", "remaining_time": "2:16:12", "throughput": 6861.43, "total_tokens": 14153848} {"current_steps": 1265, "total_steps": 6252, "loss": 0.528, "lr": 4.512453143790042e-05, "epoch": 0.6071878562428752, "percentage": 20.23, "elapsed_time": "0:34:30", "remaining_time": "2:16:04", "throughput": 6861.68, "total_tokens": 14210416} {"current_steps": 1270, "total_steps": 6252, "loss": 0.5395, "lr": 4.508720173069859e-05, "epoch": 0.6095878082438351, "percentage": 20.31, "elapsed_time": "0:34:39", "remaining_time": "2:15:55", "throughput": 6860.63, "total_tokens": 14263360} {"current_steps": 1275, "total_steps": 6252, "loss": 0.522, "lr": 4.5049745222978665e-05, "epoch": 0.6119877602447951, "percentage": 20.39, "elapsed_time": "0:34:47", "remaining_time": "2:15:46", "throughput": 6861.37, "total_tokens": 14320200} {"current_steps": 1280, "total_steps": 6252, "loss": 0.5303, "lr": 4.501216215118498e-05, "epoch": 0.6143877122457551, "percentage": 20.47, "elapsed_time": "0:34:55", "remaining_time": "2:15:38", "throughput": 6861.75, "total_tokens": 14376904} {"current_steps": 1285, "total_steps": 6252, "loss": 0.5027, "lr": 4.497445275256076e-05, "epoch": 0.616787664246715, "percentage": 20.55, "elapsed_time": "0:35:03", "remaining_time": "2:15:31", "throughput": 6861.36, "total_tokens": 14434888} {"current_steps": 1290, "total_steps": 6252, "loss": 0.5192, "lr": 4.4936617265146696e-05, "epoch": 0.619187616247675, "percentage": 20.63, "elapsed_time": "0:35:12", "remaining_time": "2:15:23", "throughput": 6860.41, "total_tokens": 14489232} {"current_steps": 1295, "total_steps": 6252, "loss": 0.5137, "lr": 4.489865592777941e-05, "epoch": 0.621587568248635, "percentage": 20.71, "elapsed_time": "0:35:19", "remaining_time": "2:15:14", "throughput": 6860.33, "total_tokens": 14543200} {"current_steps": 1300, "total_steps": 6252, "loss": 0.5647, "lr": 4.486056898008996e-05, "epoch": 0.623987520249595, "percentage": 20.79, "elapsed_time": "0:35:27", "remaining_time": "2:15:05", "throughput": 6860.26, "total_tokens": 14597160} {"current_steps": 1305, "total_steps": 6252, "loss": 0.5372, "lr": 4.48223566625023e-05, "epoch": 0.626387472250555, "percentage": 20.87, "elapsed_time": "0:35:35", "remaining_time": "2:14:57", "throughput": 6861.49, "total_tokens": 14656120} {"current_steps": 1310, "total_steps": 6252, "loss": 0.4987, "lr": 4.47840192162318e-05, "epoch": 0.628787424251515, "percentage": 20.95, "elapsed_time": "0:35:44", "remaining_time": "2:14:49", "throughput": 6862.14, "total_tokens": 14715168} {"current_steps": 1315, "total_steps": 6252, "loss": 0.5242, "lr": 4.47455568832837e-05, "epoch": 0.6311873762524749, "percentage": 21.03, "elapsed_time": "0:35:52", "remaining_time": "2:14:40", "throughput": 6863.08, "total_tokens": 14771992} {"current_steps": 1320, "total_steps": 6252, "loss": 0.5488, "lr": 4.470696990645158e-05, "epoch": 0.6335873282534349, "percentage": 21.11, "elapsed_time": "0:36:00", "remaining_time": "2:14:33", "throughput": 6862.01, "total_tokens": 14827224} {"current_steps": 1325, "total_steps": 6252, "loss": 0.5578, "lr": 4.4668258529315855e-05, "epoch": 0.6359872802543949, "percentage": 21.19, "elapsed_time": "0:36:08", "remaining_time": "2:14:23", "throughput": 6862.13, "total_tokens": 14880216} {"current_steps": 1330, "total_steps": 6252, "loss": 0.4897, "lr": 4.462942299624219e-05, "epoch": 0.6383872322553549, "percentage": 21.27, "elapsed_time": "0:36:16", "remaining_time": "2:14:15", "throughput": 6862.82, "total_tokens": 14938264} {"current_steps": 1335, "total_steps": 6252, "loss": 0.5071, "lr": 4.459046355238e-05, "epoch": 0.6407871842563149, "percentage": 21.35, "elapsed_time": "0:36:24", "remaining_time": "2:14:07", "throughput": 6863.72, "total_tokens": 14996424} {"current_steps": 1340, "total_steps": 6252, "loss": 0.5117, "lr": 4.455138044366088e-05, "epoch": 0.6431871362572749, "percentage": 21.43, "elapsed_time": "0:36:33", "remaining_time": "2:13:59", "throughput": 6864.39, "total_tokens": 15054880} {"current_steps": 1345, "total_steps": 6252, "loss": 0.4721, "lr": 4.4512173916797085e-05, "epoch": 0.6455870882582349, "percentage": 21.51, "elapsed_time": "0:36:42", "remaining_time": "2:13:53", "throughput": 6865.28, "total_tokens": 15117888} {"current_steps": 1350, "total_steps": 6252, "loss": 0.554, "lr": 4.447284421927991e-05, "epoch": 0.6479870402591948, "percentage": 21.59, "elapsed_time": "0:36:50", "remaining_time": "2:13:48", "throughput": 6863.63, "total_tokens": 15175016} {"current_steps": 1355, "total_steps": 6252, "loss": 0.5125, "lr": 4.443339159937818e-05, "epoch": 0.6503869922601548, "percentage": 21.67, "elapsed_time": "0:36:58", "remaining_time": "2:13:39", "throughput": 6863.89, "total_tokens": 15230944} {"current_steps": 1360, "total_steps": 6252, "loss": 0.5286, "lr": 4.439381630613668e-05, "epoch": 0.6527869442611148, "percentage": 21.75, "elapsed_time": "0:37:07", "remaining_time": "2:13:31", "throughput": 6863.75, "total_tokens": 15287896} {"current_steps": 1365, "total_steps": 6252, "loss": 0.6131, "lr": 4.435411858937456e-05, "epoch": 0.6551868962620747, "percentage": 21.83, "elapsed_time": "0:37:15", "remaining_time": "2:13:21", "throughput": 6864.62, "total_tokens": 15342584} {"current_steps": 1370, "total_steps": 6252, "loss": 0.5062, "lr": 4.431429869968378e-05, "epoch": 0.6575868482630347, "percentage": 21.91, "elapsed_time": "0:37:23", "remaining_time": "2:13:14", "throughput": 6866.29, "total_tokens": 15404096} {"current_steps": 1375, "total_steps": 6252, "loss": 0.4943, "lr": 4.427435688842748e-05, "epoch": 0.6599868002639947, "percentage": 21.99, "elapsed_time": "0:37:31", "remaining_time": "2:13:06", "throughput": 6866.88, "total_tokens": 15462616} {"current_steps": 1380, "total_steps": 6252, "loss": 0.5096, "lr": 4.423429340773847e-05, "epoch": 0.6623867522649547, "percentage": 22.07, "elapsed_time": "0:37:40", "remaining_time": "2:12:58", "throughput": 6867.06, "total_tokens": 15519912} {"current_steps": 1385, "total_steps": 6252, "loss": 0.5394, "lr": 4.41941085105176e-05, "epoch": 0.6647867042659147, "percentage": 22.15, "elapsed_time": "0:37:48", "remaining_time": "2:12:50", "throughput": 6867.14, "total_tokens": 15576136} {"current_steps": 1390, "total_steps": 6252, "loss": 0.4537, "lr": 4.415380245043213e-05, "epoch": 0.6671866562668747, "percentage": 22.23, "elapsed_time": "0:37:56", "remaining_time": "2:12:43", "throughput": 6867.12, "total_tokens": 15633480} {"current_steps": 1395, "total_steps": 6252, "loss": 0.5155, "lr": 4.4113375481914186e-05, "epoch": 0.6695866082678347, "percentage": 22.31, "elapsed_time": "0:38:04", "remaining_time": "2:12:34", "throughput": 6866.45, "total_tokens": 15688200} {"current_steps": 1400, "total_steps": 6252, "loss": 0.5255, "lr": 4.407282786015913e-05, "epoch": 0.6719865602687947, "percentage": 22.39, "elapsed_time": "0:38:12", "remaining_time": "2:12:25", "throughput": 6866.49, "total_tokens": 15742392} {"current_steps": 1405, "total_steps": 6252, "loss": 0.5122, "lr": 4.403215984112392e-05, "epoch": 0.6743865122697547, "percentage": 22.47, "elapsed_time": "0:38:21", "remaining_time": "2:12:18", "throughput": 6866.31, "total_tokens": 15799472} {"current_steps": 1410, "total_steps": 6252, "loss": 0.511, "lr": 4.3991371681525556e-05, "epoch": 0.6767864642707145, "percentage": 22.55, "elapsed_time": "0:38:29", "remaining_time": "2:12:12", "throughput": 6865.6, "total_tokens": 15858960} {"current_steps": 1415, "total_steps": 6252, "loss": 0.5375, "lr": 4.395046363883941e-05, "epoch": 0.6791864162716745, "percentage": 22.63, "elapsed_time": "0:38:37", "remaining_time": "2:12:03", "throughput": 6866.39, "total_tokens": 15915472} {"current_steps": 1420, "total_steps": 6252, "loss": 0.5682, "lr": 4.390943597129761e-05, "epoch": 0.6815863682726345, "percentage": 22.71, "elapsed_time": "0:38:45", "remaining_time": "2:11:53", "throughput": 6867.5, "total_tokens": 15970752} {"current_steps": 1425, "total_steps": 6252, "loss": 0.5164, "lr": 4.3868288937887445e-05, "epoch": 0.6839863202735945, "percentage": 22.79, "elapsed_time": "0:38:53", "remaining_time": "2:11:45", "throughput": 6866.84, "total_tokens": 16025456} {"current_steps": 1430, "total_steps": 6252, "loss": 0.5524, "lr": 4.382702279834965e-05, "epoch": 0.6863862722745545, "percentage": 22.87, "elapsed_time": "0:39:01", "remaining_time": "2:11:35", "throughput": 6866.09, "total_tokens": 16075744} {"current_steps": 1435, "total_steps": 6252, "loss": 0.497, "lr": 4.378563781317687e-05, "epoch": 0.6887862242755145, "percentage": 22.95, "elapsed_time": "0:39:10", "remaining_time": "2:11:29", "throughput": 6866.21, "total_tokens": 16137672} {"current_steps": 1440, "total_steps": 6252, "loss": 0.4888, "lr": 4.374413424361195e-05, "epoch": 0.6911861762764745, "percentage": 23.03, "elapsed_time": "0:39:18", "remaining_time": "2:11:22", "throughput": 6867.5, "total_tokens": 16199088} {"current_steps": 1445, "total_steps": 6252, "loss": 0.5343, "lr": 4.370251235164625e-05, "epoch": 0.6935861282774345, "percentage": 23.11, "elapsed_time": "0:39:27", "remaining_time": "2:11:14", "throughput": 6866.58, "total_tokens": 16253792} {"current_steps": 1450, "total_steps": 6252, "loss": 0.4848, "lr": 4.366077240001813e-05, "epoch": 0.6959860802783945, "percentage": 23.19, "elapsed_time": "0:39:36", "remaining_time": "2:11:08", "throughput": 6867.24, "total_tokens": 16316608} {"current_steps": 1455, "total_steps": 6252, "loss": 0.4847, "lr": 4.361891465221112e-05, "epoch": 0.6983860322793544, "percentage": 23.27, "elapsed_time": "0:39:44", "remaining_time": "2:11:01", "throughput": 6867.91, "total_tokens": 16375648} {"current_steps": 1460, "total_steps": 6252, "loss": 0.5295, "lr": 4.3576939372452394e-05, "epoch": 0.7007859842803144, "percentage": 23.35, "elapsed_time": "0:39:52", "remaining_time": "2:10:52", "throughput": 6866.94, "total_tokens": 16429360} {"current_steps": 1465, "total_steps": 6252, "loss": 0.5144, "lr": 4.353484682571101e-05, "epoch": 0.7031859362812743, "percentage": 23.43, "elapsed_time": "0:40:00", "remaining_time": "2:10:43", "throughput": 6865.59, "total_tokens": 16480088} {"current_steps": 1470, "total_steps": 6252, "loss": 0.4636, "lr": 4.349263727769629e-05, "epoch": 0.7055858882822343, "percentage": 23.51, "elapsed_time": "0:40:08", "remaining_time": "2:10:36", "throughput": 6865.97, "total_tokens": 16538968} {"current_steps": 1475, "total_steps": 6252, "loss": 0.5415, "lr": 4.3450310994856135e-05, "epoch": 0.7079858402831943, "percentage": 23.59, "elapsed_time": "0:40:17", "remaining_time": "2:10:28", "throughput": 6865.59, "total_tokens": 16595104} {"current_steps": 1480, "total_steps": 6252, "loss": 0.5367, "lr": 4.3407868244375315e-05, "epoch": 0.7103857922841543, "percentage": 23.67, "elapsed_time": "0:40:25", "remaining_time": "2:10:19", "throughput": 6865.58, "total_tokens": 16650488} {"current_steps": 1485, "total_steps": 6252, "loss": 0.4729, "lr": 4.3365309294173825e-05, "epoch": 0.7127857442851143, "percentage": 23.75, "elapsed_time": "0:40:32", "remaining_time": "2:10:09", "throughput": 6864.78, "total_tokens": 16701384} {"current_steps": 1490, "total_steps": 6252, "loss": 0.5373, "lr": 4.332263441290515e-05, "epoch": 0.7151856962860743, "percentage": 23.83, "elapsed_time": "0:40:40", "remaining_time": "2:09:59", "throughput": 6865.38, "total_tokens": 16754152} {"current_steps": 1495, "total_steps": 6252, "loss": 0.5037, "lr": 4.3279843869954604e-05, "epoch": 0.7175856482870343, "percentage": 23.91, "elapsed_time": "0:40:48", "remaining_time": "2:09:49", "throughput": 6865.93, "total_tokens": 16809056} {"current_steps": 1500, "total_steps": 6252, "loss": 0.5324, "lr": 4.3236937935437614e-05, "epoch": 0.7199856002879942, "percentage": 23.99, "elapsed_time": "0:40:55", "remaining_time": "2:09:39", "throughput": 6865.82, "total_tokens": 16859504} {"current_steps": 1505, "total_steps": 6252, "loss": 0.5109, "lr": 4.3193916880198004e-05, "epoch": 0.7223855522889542, "percentage": 24.07, "elapsed_time": "0:41:04", "remaining_time": "2:09:32", "throughput": 6865.95, "total_tokens": 16919952} {"current_steps": 1510, "total_steps": 6252, "loss": 0.5425, "lr": 4.3150780975806315e-05, "epoch": 0.7247855042899142, "percentage": 24.15, "elapsed_time": "0:41:12", "remaining_time": "2:09:24", "throughput": 6866.07, "total_tokens": 16976592} {"current_steps": 1515, "total_steps": 6252, "loss": 0.515, "lr": 4.310753049455806e-05, "epoch": 0.7271854562908742, "percentage": 24.23, "elapsed_time": "0:41:20", "remaining_time": "2:09:16", "throughput": 6866.51, "total_tokens": 17034816} {"current_steps": 1520, "total_steps": 6252, "loss": 0.5271, "lr": 4.3064165709472036e-05, "epoch": 0.7295854082918342, "percentage": 24.31, "elapsed_time": "0:41:28", "remaining_time": "2:09:06", "throughput": 6867.72, "total_tokens": 17088560} {"current_steps": 1525, "total_steps": 6252, "loss": 0.5055, "lr": 4.3020686894288564e-05, "epoch": 0.7319853602927942, "percentage": 24.39, "elapsed_time": "0:41:36", "remaining_time": "2:08:56", "throughput": 6868.71, "total_tokens": 17144640} {"current_steps": 1530, "total_steps": 6252, "loss": 0.48, "lr": 4.2977094323467784e-05, "epoch": 0.7343853122937541, "percentage": 24.47, "elapsed_time": "0:41:44", "remaining_time": "2:08:48", "throughput": 6868.39, "total_tokens": 17200416} {"current_steps": 1535, "total_steps": 6252, "loss": 0.4972, "lr": 4.293338827218794e-05, "epoch": 0.7367852642947141, "percentage": 24.55, "elapsed_time": "0:41:52", "remaining_time": "2:08:40", "throughput": 6868.52, "total_tokens": 17256344} {"current_steps": 1540, "total_steps": 6252, "loss": 0.4691, "lr": 4.288956901634359e-05, "epoch": 0.7391852162956741, "percentage": 24.63, "elapsed_time": "0:42:00", "remaining_time": "2:08:33", "throughput": 6868.37, "total_tokens": 17314072} {"current_steps": 1545, "total_steps": 6252, "loss": 0.4942, "lr": 4.2845636832543914e-05, "epoch": 0.741585168296634, "percentage": 24.71, "elapsed_time": "0:42:09", "remaining_time": "2:08:25", "throughput": 6869.07, "total_tokens": 17373728} {"current_steps": 1550, "total_steps": 6252, "loss": 0.5119, "lr": 4.2801591998110946e-05, "epoch": 0.743985120297594, "percentage": 24.79, "elapsed_time": "0:42:16", "remaining_time": "2:08:15", "throughput": 6869.46, "total_tokens": 17425920} {"current_steps": 1555, "total_steps": 6252, "loss": 0.5201, "lr": 4.275743479107785e-05, "epoch": 0.746385072298554, "percentage": 24.87, "elapsed_time": "0:42:24", "remaining_time": "2:08:06", "throughput": 6868.84, "total_tokens": 17480304} {"current_steps": 1560, "total_steps": 6252, "loss": 0.517, "lr": 4.271316549018708e-05, "epoch": 0.748785024299514, "percentage": 24.95, "elapsed_time": "0:42:33", "remaining_time": "2:07:58", "throughput": 6870.26, "total_tokens": 17539776} {"current_steps": 1565, "total_steps": 6252, "loss": 0.4894, "lr": 4.2668784374888756e-05, "epoch": 0.751184976300474, "percentage": 25.03, "elapsed_time": "0:42:41", "remaining_time": "2:07:51", "throughput": 6869.22, "total_tokens": 17595928} {"current_steps": 1570, "total_steps": 6252, "loss": 0.5213, "lr": 4.262429172533878e-05, "epoch": 0.753584928301434, "percentage": 25.11, "elapsed_time": "0:42:49", "remaining_time": "2:07:42", "throughput": 6870.04, "total_tokens": 17651664} {"current_steps": 1575, "total_steps": 6252, "loss": 0.506, "lr": 4.257968782239714e-05, "epoch": 0.755984880302394, "percentage": 25.19, "elapsed_time": "0:42:56", "remaining_time": "2:07:32", "throughput": 6870.3, "total_tokens": 17703960} {"current_steps": 1580, "total_steps": 6252, "loss": 0.5073, "lr": 4.2534972947626094e-05, "epoch": 0.758384832303354, "percentage": 25.27, "elapsed_time": "0:43:05", "remaining_time": "2:07:24", "throughput": 6870.05, "total_tokens": 17761448} {"current_steps": 1585, "total_steps": 6252, "loss": 0.5265, "lr": 4.249014738328842e-05, "epoch": 0.760784784304314, "percentage": 25.35, "elapsed_time": "0:43:13", "remaining_time": "2:07:15", "throughput": 6871.41, "total_tokens": 17817984} {"current_steps": 1590, "total_steps": 6252, "loss": 0.5244, "lr": 4.2445211412345615e-05, "epoch": 0.763184736305274, "percentage": 25.43, "elapsed_time": "0:43:21", "remaining_time": "2:07:06", "throughput": 6871.89, "total_tokens": 17874768} {"current_steps": 1595, "total_steps": 6252, "loss": 0.5406, "lr": 4.240016531845612e-05, "epoch": 0.7655846883062338, "percentage": 25.51, "elapsed_time": "0:43:29", "remaining_time": "2:06:58", "throughput": 6871.92, "total_tokens": 17931864} {"current_steps": 1600, "total_steps": 6252, "loss": 0.4871, "lr": 4.235500938597354e-05, "epoch": 0.7679846403071938, "percentage": 25.59, "elapsed_time": "0:43:37", "remaining_time": "2:06:49", "throughput": 6872.27, "total_tokens": 17985744} {"current_steps": 1605, "total_steps": 6252, "loss": 0.5015, "lr": 4.230974389994483e-05, "epoch": 0.7703845923081538, "percentage": 25.67, "elapsed_time": "0:43:45", "remaining_time": "2:06:41", "throughput": 6872.95, "total_tokens": 18044152} {"current_steps": 1610, "total_steps": 6252, "loss": 0.541, "lr": 4.226436914610849e-05, "epoch": 0.7727845443091138, "percentage": 25.75, "elapsed_time": "0:43:53", "remaining_time": "2:06:32", "throughput": 6873.48, "total_tokens": 18100976} {"current_steps": 1615, "total_steps": 6252, "loss": 0.5314, "lr": 4.2218885410892785e-05, "epoch": 0.7751844963100738, "percentage": 25.83, "elapsed_time": "0:44:01", "remaining_time": "2:06:22", "throughput": 6874.7, "total_tokens": 18156240} {"current_steps": 1620, "total_steps": 6252, "loss": 0.4875, "lr": 4.2173292981413914e-05, "epoch": 0.7775844483110338, "percentage": 25.91, "elapsed_time": "0:44:09", "remaining_time": "2:06:15", "throughput": 6875.23, "total_tokens": 18216472} {"current_steps": 1625, "total_steps": 6252, "loss": 0.4954, "lr": 4.212759214547424e-05, "epoch": 0.7799844003119938, "percentage": 25.99, "elapsed_time": "0:44:17", "remaining_time": "2:06:06", "throughput": 6875.63, "total_tokens": 18271168} {"current_steps": 1630, "total_steps": 6252, "loss": 0.4939, "lr": 4.2081783191560405e-05, "epoch": 0.7823843523129538, "percentage": 26.07, "elapsed_time": "0:44:25", "remaining_time": "2:05:57", "throughput": 6875.96, "total_tokens": 18326128} {"current_steps": 1635, "total_steps": 6252, "loss": 0.4995, "lr": 4.203586640884156e-05, "epoch": 0.7847843043139138, "percentage": 26.15, "elapsed_time": "0:44:33", "remaining_time": "2:05:49", "throughput": 6876.58, "total_tokens": 18385280} {"current_steps": 1640, "total_steps": 6252, "loss": 0.5198, "lr": 4.1989842087167534e-05, "epoch": 0.7871842563148737, "percentage": 26.23, "elapsed_time": "0:44:42", "remaining_time": "2:05:43", "throughput": 6876.05, "total_tokens": 18444000} {"current_steps": 1645, "total_steps": 6252, "loss": 0.4696, "lr": 4.1943710517066984e-05, "epoch": 0.7895842083158336, "percentage": 26.31, "elapsed_time": "0:44:50", "remaining_time": "2:05:35", "throughput": 6876.16, "total_tokens": 18500344} {"current_steps": 1650, "total_steps": 6252, "loss": 0.4777, "lr": 4.1897471989745575e-05, "epoch": 0.7919841603167936, "percentage": 26.39, "elapsed_time": "0:44:58", "remaining_time": "2:05:25", "throughput": 6876.1, "total_tokens": 18553136} {"current_steps": 1655, "total_steps": 6252, "loss": 0.525, "lr": 4.185112679708415e-05, "epoch": 0.7943841123177536, "percentage": 26.47, "elapsed_time": "0:45:06", "remaining_time": "2:05:17", "throughput": 6876.54, "total_tokens": 18610264} {"current_steps": 1660, "total_steps": 6252, "loss": 0.4906, "lr": 4.180467523163686e-05, "epoch": 0.7967840643187136, "percentage": 26.55, "elapsed_time": "0:45:14", "remaining_time": "2:05:10", "throughput": 6877.06, "total_tokens": 18670624} {"current_steps": 1665, "total_steps": 6252, "loss": 0.4851, "lr": 4.175811758662935e-05, "epoch": 0.7991840163196736, "percentage": 26.63, "elapsed_time": "0:45:23", "remaining_time": "2:05:02", "throughput": 6876.6, "total_tokens": 18727824} {"current_steps": 1670, "total_steps": 6252, "loss": 0.4694, "lr": 4.1711454155956895e-05, "epoch": 0.8015839683206336, "percentage": 26.71, "elapsed_time": "0:45:31", "remaining_time": "2:04:53", "throughput": 6878.03, "total_tokens": 18785440} {"current_steps": 1675, "total_steps": 6252, "loss": 0.5254, "lr": 4.166468523418251e-05, "epoch": 0.8039839203215936, "percentage": 26.79, "elapsed_time": "0:45:39", "remaining_time": "2:04:45", "throughput": 6877.26, "total_tokens": 18839288} {"current_steps": 1680, "total_steps": 6252, "loss": 0.5521, "lr": 4.1617811116535176e-05, "epoch": 0.8063838723225536, "percentage": 26.87, "elapsed_time": "0:45:47", "remaining_time": "2:04:35", "throughput": 6877.87, "total_tokens": 18893696} {"current_steps": 1685, "total_steps": 6252, "loss": 0.5444, "lr": 4.1570832098907874e-05, "epoch": 0.8087838243235135, "percentage": 26.95, "elapsed_time": "0:45:54", "remaining_time": "2:04:26", "throughput": 6878.03, "total_tokens": 18946504} {"current_steps": 1690, "total_steps": 6252, "loss": 0.5321, "lr": 4.152374847785579e-05, "epoch": 0.8111837763244735, "percentage": 27.03, "elapsed_time": "0:46:03", "remaining_time": "2:04:18", "throughput": 6877.9, "total_tokens": 19003664} {"current_steps": 1695, "total_steps": 6252, "loss": 0.4826, "lr": 4.1476560550594414e-05, "epoch": 0.8135837283254335, "percentage": 27.11, "elapsed_time": "0:46:10", "remaining_time": "2:04:09", "throughput": 6877.49, "total_tokens": 19056544} {"current_steps": 1700, "total_steps": 6252, "loss": 0.5543, "lr": 4.142926861499768e-05, "epoch": 0.8159836803263935, "percentage": 27.19, "elapsed_time": "0:46:18", "remaining_time": "2:03:59", "throughput": 6876.91, "total_tokens": 19107344} {"current_steps": 1705, "total_steps": 6252, "loss": 0.505, "lr": 4.138187296959606e-05, "epoch": 0.8183836323273534, "percentage": 27.27, "elapsed_time": "0:46:26", "remaining_time": "2:03:50", "throughput": 6877.2, "total_tokens": 19162000} {"current_steps": 1710, "total_steps": 6252, "loss": 0.522, "lr": 4.13343739135747e-05, "epoch": 0.8207835843283134, "percentage": 27.35, "elapsed_time": "0:46:34", "remaining_time": "2:03:41", "throughput": 6877.72, "total_tokens": 19217512} {"current_steps": 1715, "total_steps": 6252, "loss": 0.5411, "lr": 4.128677174677153e-05, "epoch": 0.8231835363292734, "percentage": 27.43, "elapsed_time": "0:46:42", "remaining_time": "2:03:33", "throughput": 6878.52, "total_tokens": 19276384} {"current_steps": 1720, "total_steps": 6252, "loss": 0.513, "lr": 4.123906676967536e-05, "epoch": 0.8255834883302334, "percentage": 27.51, "elapsed_time": "0:46:50", "remaining_time": "2:03:24", "throughput": 6878.32, "total_tokens": 19328432} {"current_steps": 1725, "total_steps": 6252, "loss": 0.5244, "lr": 4.1191259283424e-05, "epoch": 0.8279834403311934, "percentage": 27.59, "elapsed_time": "0:46:58", "remaining_time": "2:03:15", "throughput": 6878.34, "total_tokens": 19384016} {"current_steps": 1730, "total_steps": 6252, "loss": 0.5471, "lr": 4.1143349589802326e-05, "epoch": 0.8303833923321533, "percentage": 27.67, "elapsed_time": "0:47:06", "remaining_time": "2:03:07", "throughput": 6879.03, "total_tokens": 19442016} {"current_steps": 1735, "total_steps": 6252, "loss": 0.5352, "lr": 4.1095337991240436e-05, "epoch": 0.8327833443331133, "percentage": 27.75, "elapsed_time": "0:47:14", "remaining_time": "2:02:58", "throughput": 6879.4, "total_tokens": 19496880} {"current_steps": 1740, "total_steps": 6252, "loss": 0.4709, "lr": 4.104722479081167e-05, "epoch": 0.8351832963340733, "percentage": 27.83, "elapsed_time": "0:47:22", "remaining_time": "2:02:49", "throughput": 6880.78, "total_tokens": 19555656} {"current_steps": 1745, "total_steps": 6252, "loss": 0.5104, "lr": 4.099901029223075e-05, "epoch": 0.8375832483350333, "percentage": 27.91, "elapsed_time": "0:47:29", "remaining_time": "2:02:40", "throughput": 6881.26, "total_tokens": 19610352} {"current_steps": 1750, "total_steps": 6252, "loss": 0.5151, "lr": 4.095069479985183e-05, "epoch": 0.8399832003359933, "percentage": 27.99, "elapsed_time": "0:47:38", "remaining_time": "2:02:32", "throughput": 6880.77, "total_tokens": 19666656} {"current_steps": 1755, "total_steps": 6252, "loss": 0.5355, "lr": 4.090227861866659e-05, "epoch": 0.8423831523369533, "percentage": 28.07, "elapsed_time": "0:47:46", "remaining_time": "2:02:24", "throughput": 6881.17, "total_tokens": 19723528} {"current_steps": 1760, "total_steps": 6252, "loss": 0.5475, "lr": 4.085376205430233e-05, "epoch": 0.8447831043379133, "percentage": 28.15, "elapsed_time": "0:47:53", "remaining_time": "2:02:15", "throughput": 6880.94, "total_tokens": 19775232} {"current_steps": 1765, "total_steps": 6252, "loss": 0.5043, "lr": 4.080514541301998e-05, "epoch": 0.8471830563388733, "percentage": 28.23, "elapsed_time": "0:48:01", "remaining_time": "2:02:06", "throughput": 6882.12, "total_tokens": 19832592} {"current_steps": 1770, "total_steps": 6252, "loss": 0.5501, "lr": 4.075642900171223e-05, "epoch": 0.8495830083398332, "percentage": 28.31, "elapsed_time": "0:48:09", "remaining_time": "2:01:56", "throughput": 6882.68, "total_tokens": 19886104} {"current_steps": 1775, "total_steps": 6252, "loss": 0.5666, "lr": 4.070761312790157e-05, "epoch": 0.8519829603407932, "percentage": 28.39, "elapsed_time": "0:48:17", "remaining_time": "2:01:48", "throughput": 6882.93, "total_tokens": 19944808} {"current_steps": 1780, "total_steps": 6252, "loss": 0.5026, "lr": 4.065869809973833e-05, "epoch": 0.8543829123417531, "percentage": 28.47, "elapsed_time": "0:48:25", "remaining_time": "2:01:39", "throughput": 6883.38, "total_tokens": 20000048} {"current_steps": 1785, "total_steps": 6252, "loss": 0.4991, "lr": 4.060968422599879e-05, "epoch": 0.8567828643427131, "percentage": 28.55, "elapsed_time": "0:48:33", "remaining_time": "2:01:31", "throughput": 6883.07, "total_tokens": 20054800} {"current_steps": 1790, "total_steps": 6252, "loss": 0.5496, "lr": 4.0560571816083156e-05, "epoch": 0.8591828163436731, "percentage": 28.63, "elapsed_time": "0:48:41", "remaining_time": "2:01:23", "throughput": 6883.11, "total_tokens": 20111120} {"current_steps": 1795, "total_steps": 6252, "loss": 0.4827, "lr": 4.051136118001364e-05, "epoch": 0.8615827683446331, "percentage": 28.71, "elapsed_time": "0:48:49", "remaining_time": "2:01:14", "throughput": 6883.27, "total_tokens": 20165552} {"current_steps": 1800, "total_steps": 6252, "loss": 0.4949, "lr": 4.046205262843254e-05, "epoch": 0.8639827203455931, "percentage": 28.79, "elapsed_time": "0:48:58", "remaining_time": "2:01:07", "throughput": 6881.98, "total_tokens": 20221072} {"current_steps": 1805, "total_steps": 6252, "loss": 0.4844, "lr": 4.041264647260022e-05, "epoch": 0.8663826723465531, "percentage": 28.87, "elapsed_time": "0:49:07", "remaining_time": "2:01:02", "throughput": 6878.74, "total_tokens": 20277640} {"current_steps": 1810, "total_steps": 6252, "loss": 0.4938, "lr": 4.036314302439319e-05, "epoch": 0.8687826243475131, "percentage": 28.95, "elapsed_time": "0:49:15", "remaining_time": "2:00:53", "throughput": 6879.12, "total_tokens": 20333328} {"current_steps": 1815, "total_steps": 6252, "loss": 0.5246, "lr": 4.031354259630209e-05, "epoch": 0.8711825763484731, "percentage": 29.03, "elapsed_time": "0:49:23", "remaining_time": "2:00:45", "throughput": 6879.94, "total_tokens": 20389752} {"current_steps": 1820, "total_steps": 6252, "loss": 0.5467, "lr": 4.026384550142978e-05, "epoch": 0.8735825283494331, "percentage": 29.11, "elapsed_time": "0:49:31", "remaining_time": "2:00:36", "throughput": 6880.77, "total_tokens": 20447184} {"current_steps": 1825, "total_steps": 6252, "loss": 0.4753, "lr": 4.0214052053489304e-05, "epoch": 0.875982480350393, "percentage": 29.19, "elapsed_time": "0:49:39", "remaining_time": "2:00:27", "throughput": 6880.99, "total_tokens": 20501512} {"current_steps": 1830, "total_steps": 6252, "loss": 0.5134, "lr": 4.016416256680194e-05, "epoch": 0.8783824323513529, "percentage": 29.27, "elapsed_time": "0:49:47", "remaining_time": "2:00:18", "throughput": 6881.34, "total_tokens": 20556688} {"current_steps": 1835, "total_steps": 6252, "loss": 0.4771, "lr": 4.011417735629522e-05, "epoch": 0.8807823843523129, "percentage": 29.35, "elapsed_time": "0:49:55", "remaining_time": "2:00:10", "throughput": 6881.11, "total_tokens": 20613504} {"current_steps": 1840, "total_steps": 6252, "loss": 0.4904, "lr": 4.006409673750094e-05, "epoch": 0.8831823363532729, "percentage": 29.43, "elapsed_time": "0:50:04", "remaining_time": "2:00:03", "throughput": 6880.59, "total_tokens": 20670776} {"current_steps": 1845, "total_steps": 6252, "loss": 0.5172, "lr": 4.0013921026553125e-05, "epoch": 0.8855822883542329, "percentage": 29.51, "elapsed_time": "0:50:12", "remaining_time": "1:59:55", "throughput": 6880.83, "total_tokens": 20726776} {"current_steps": 1850, "total_steps": 6252, "loss": 0.5168, "lr": 3.9963650540186116e-05, "epoch": 0.8879822403551929, "percentage": 29.59, "elapsed_time": "0:50:20", "remaining_time": "1:59:47", "throughput": 6879.65, "total_tokens": 20781792} {"current_steps": 1855, "total_steps": 6252, "loss": 0.551, "lr": 3.991328559573248e-05, "epoch": 0.8903821923561529, "percentage": 29.67, "elapsed_time": "0:50:28", "remaining_time": "1:59:38", "throughput": 6879.72, "total_tokens": 20835512} {"current_steps": 1860, "total_steps": 6252, "loss": 0.5242, "lr": 3.9862826511121085e-05, "epoch": 0.8927821443571129, "percentage": 29.75, "elapsed_time": "0:50:36", "remaining_time": "1:59:28", "throughput": 6879.74, "total_tokens": 20887216} {"current_steps": 1865, "total_steps": 6252, "loss": 0.5273, "lr": 3.981227360487504e-05, "epoch": 0.8951820963580729, "percentage": 29.83, "elapsed_time": "0:50:44", "remaining_time": "1:59:20", "throughput": 6879.76, "total_tokens": 20943744} {"current_steps": 1870, "total_steps": 6252, "loss": 0.5006, "lr": 3.976162719610972e-05, "epoch": 0.8975820483590328, "percentage": 29.91, "elapsed_time": "0:50:53", "remaining_time": "1:59:14", "throughput": 6875.43, "total_tokens": 20991568} {"current_steps": 1875, "total_steps": 6252, "loss": 0.5214, "lr": 3.971088760453071e-05, "epoch": 0.8999820003599928, "percentage": 29.99, "elapsed_time": "0:51:01", "remaining_time": "1:59:07", "throughput": 6873.97, "total_tokens": 21047408} {"current_steps": 1880, "total_steps": 6252, "loss": 0.5172, "lr": 3.966005515043183e-05, "epoch": 0.9023819523609528, "percentage": 30.07, "elapsed_time": "0:51:10", "remaining_time": "1:58:59", "throughput": 6874.35, "total_tokens": 21105344} {"current_steps": 1885, "total_steps": 6252, "loss": 0.5581, "lr": 3.960913015469311e-05, "epoch": 0.9047819043619127, "percentage": 30.15, "elapsed_time": "0:51:18", "remaining_time": "1:58:51", "throughput": 6874.31, "total_tokens": 21161704} {"current_steps": 1890, "total_steps": 6252, "loss": 0.5006, "lr": 3.95581129387787e-05, "epoch": 0.9071818563628727, "percentage": 30.23, "elapsed_time": "0:51:27", "remaining_time": "1:58:46", "throughput": 6872.27, "total_tokens": 21220960} {"current_steps": 1895, "total_steps": 6252, "loss": 0.5143, "lr": 3.950700382473494e-05, "epoch": 0.9095818083638327, "percentage": 30.31, "elapsed_time": "0:51:37", "remaining_time": "1:58:41", "throughput": 6871.72, "total_tokens": 21285456} {"current_steps": 1900, "total_steps": 6252, "loss": 0.5133, "lr": 3.9455803135188265e-05, "epoch": 0.9119817603647927, "percentage": 30.39, "elapsed_time": "0:51:45", "remaining_time": "1:58:33", "throughput": 6871.81, "total_tokens": 21340656} {"current_steps": 1905, "total_steps": 6252, "loss": 0.4716, "lr": 3.940451119334315e-05, "epoch": 0.9143817123657527, "percentage": 30.47, "elapsed_time": "0:51:54", "remaining_time": "1:58:27", "throughput": 6871.41, "total_tokens": 21402256} {"current_steps": 1910, "total_steps": 6252, "loss": 0.4752, "lr": 3.935312832298014e-05, "epoch": 0.9167816643667127, "percentage": 30.55, "elapsed_time": "0:52:02", "remaining_time": "1:58:18", "throughput": 6871.63, "total_tokens": 21456968} {"current_steps": 1915, "total_steps": 6252, "loss": 0.5358, "lr": 3.9301654848453744e-05, "epoch": 0.9191816163676726, "percentage": 30.63, "elapsed_time": "0:52:10", "remaining_time": "1:58:09", "throughput": 6871.5, "total_tokens": 21510880} {"current_steps": 1920, "total_steps": 6252, "loss": 0.508, "lr": 3.9250091094690424e-05, "epoch": 0.9215815683686326, "percentage": 30.71, "elapsed_time": "0:52:19", "remaining_time": "1:58:03", "throughput": 6869.8, "total_tokens": 21567176} {"current_steps": 1925, "total_steps": 6252, "loss": 0.4969, "lr": 3.9198437387186514e-05, "epoch": 0.9239815203695926, "percentage": 30.79, "elapsed_time": "0:52:27", "remaining_time": "1:57:53", "throughput": 6868.84, "total_tokens": 21616728} {"current_steps": 1930, "total_steps": 6252, "loss": 0.5231, "lr": 3.914669405200619e-05, "epoch": 0.9263814723705526, "percentage": 30.87, "elapsed_time": "0:52:34", "remaining_time": "1:57:44", "throughput": 6869.2, "total_tokens": 21669600} {"current_steps": 1935, "total_steps": 6252, "loss": 0.5557, "lr": 3.909486141577941e-05, "epoch": 0.9287814243715126, "percentage": 30.95, "elapsed_time": "0:52:42", "remaining_time": "1:57:36", "throughput": 6868.91, "total_tokens": 21725144} {"current_steps": 1940, "total_steps": 6252, "loss": 0.5202, "lr": 3.904293980569983e-05, "epoch": 0.9311813763724726, "percentage": 31.03, "elapsed_time": "0:52:51", "remaining_time": "1:57:29", "throughput": 6867.44, "total_tokens": 21780960} {"current_steps": 1945, "total_steps": 6252, "loss": 0.4965, "lr": 3.899092954952276e-05, "epoch": 0.9335813283734326, "percentage": 31.11, "elapsed_time": "0:53:00", "remaining_time": "1:57:23", "throughput": 6864.66, "total_tokens": 21835904} {"current_steps": 1950, "total_steps": 6252, "loss": 0.5271, "lr": 3.89388309755631e-05, "epoch": 0.9359812803743925, "percentage": 31.19, "elapsed_time": "0:53:08", "remaining_time": "1:57:14", "throughput": 6864.77, "total_tokens": 21890264} {"current_steps": 1955, "total_steps": 6252, "loss": 0.513, "lr": 3.888664441269324e-05, "epoch": 0.9383812323753525, "percentage": 31.27, "elapsed_time": "0:53:16", "remaining_time": "1:57:06", "throughput": 6864.3, "total_tokens": 21943944} {"current_steps": 1960, "total_steps": 6252, "loss": 0.4975, "lr": 3.8834370190341016e-05, "epoch": 0.9407811843763125, "percentage": 31.35, "elapsed_time": "0:53:25", "remaining_time": "1:56:58", "throughput": 6864.16, "total_tokens": 22000688} {"current_steps": 1965, "total_steps": 6252, "loss": 0.5142, "lr": 3.8782008638487585e-05, "epoch": 0.9431811363772724, "percentage": 31.43, "elapsed_time": "0:53:33", "remaining_time": "1:56:50", "throughput": 6864.14, "total_tokens": 22056928} {"current_steps": 1970, "total_steps": 6252, "loss": 0.5345, "lr": 3.872956008766541e-05, "epoch": 0.9455810883782324, "percentage": 31.51, "elapsed_time": "0:53:41", "remaining_time": "1:56:41", "throughput": 6863.76, "total_tokens": 22109984} {"current_steps": 1975, "total_steps": 6252, "loss": 0.519, "lr": 3.867702486895611e-05, "epoch": 0.9479810403791924, "percentage": 31.59, "elapsed_time": "0:53:49", "remaining_time": "1:56:33", "throughput": 6864.34, "total_tokens": 22167792} {"current_steps": 1980, "total_steps": 6252, "loss": 0.4549, "lr": 3.86244033139884e-05, "epoch": 0.9503809923801524, "percentage": 31.67, "elapsed_time": "0:53:57", "remaining_time": "1:56:24", "throughput": 6865.15, "total_tokens": 22224944} {"current_steps": 1985, "total_steps": 6252, "loss": 0.4988, "lr": 3.857169575493601e-05, "epoch": 0.9527809443811124, "percentage": 31.75, "elapsed_time": "0:54:05", "remaining_time": "1:56:16", "throughput": 6865.52, "total_tokens": 22280208} {"current_steps": 1990, "total_steps": 6252, "loss": 0.5948, "lr": 3.851890252451553e-05, "epoch": 0.9551808963820724, "percentage": 31.83, "elapsed_time": "0:54:12", "remaining_time": "1:56:06", "throughput": 6865.72, "total_tokens": 22331688} {"current_steps": 1995, "total_steps": 6252, "loss": 0.4765, "lr": 3.846602395598441e-05, "epoch": 0.9575808483830324, "percentage": 31.91, "elapsed_time": "0:54:21", "remaining_time": "1:55:58", "throughput": 6865.8, "total_tokens": 22391056} {"current_steps": 2000, "total_steps": 6252, "loss": 0.5067, "lr": 3.8413060383138735e-05, "epoch": 0.9599808003839924, "percentage": 31.99, "elapsed_time": "0:54:28", "remaining_time": "1:55:49", "throughput": 6865.96, "total_tokens": 22442560} {"current_steps": 2005, "total_steps": 6252, "loss": 0.441, "lr": 3.836001214031122e-05, "epoch": 0.9623807523849524, "percentage": 32.07, "elapsed_time": "0:54:37", "remaining_time": "1:55:41", "throughput": 6866.84, "total_tokens": 22504640} {"current_steps": 2010, "total_steps": 6252, "loss": 0.4923, "lr": 3.830687956236907e-05, "epoch": 0.9647807043859122, "percentage": 32.15, "elapsed_time": "0:54:45", "remaining_time": "1:55:33", "throughput": 6868.18, "total_tokens": 22565448} {"current_steps": 2015, "total_steps": 6252, "loss": 0.4971, "lr": 3.8253662984711795e-05, "epoch": 0.9671806563868722, "percentage": 32.23, "elapsed_time": "0:54:53", "remaining_time": "1:55:25", "throughput": 6867.62, "total_tokens": 22618928} {"current_steps": 2020, "total_steps": 6252, "loss": 0.4979, "lr": 3.820036274326922e-05, "epoch": 0.9695806083878322, "percentage": 32.31, "elapsed_time": "0:55:01", "remaining_time": "1:55:16", "throughput": 6868.2, "total_tokens": 22674720} {"current_steps": 2025, "total_steps": 6252, "loss": 0.48, "lr": 3.8146979174499265e-05, "epoch": 0.9719805603887922, "percentage": 32.39, "elapsed_time": "0:55:09", "remaining_time": "1:55:08", "throughput": 6869.45, "total_tokens": 22734768} {"current_steps": 2030, "total_steps": 6252, "loss": 0.4802, "lr": 3.809351261538585e-05, "epoch": 0.9743805123897522, "percentage": 32.47, "elapsed_time": "0:55:17", "remaining_time": "1:55:00", "throughput": 6869.46, "total_tokens": 22792864} {"current_steps": 2035, "total_steps": 6252, "loss": 0.5393, "lr": 3.8039963403436806e-05, "epoch": 0.9767804643907122, "percentage": 32.55, "elapsed_time": "0:55:26", "remaining_time": "1:54:53", "throughput": 6867.47, "total_tokens": 22846392} {"current_steps": 2040, "total_steps": 6252, "loss": 0.5505, "lr": 3.798633187668166e-05, "epoch": 0.9791804163916722, "percentage": 32.63, "elapsed_time": "0:55:36", "remaining_time": "1:54:49", "throughput": 6862.48, "total_tokens": 22899608} {"current_steps": 2045, "total_steps": 6252, "loss": 0.4829, "lr": 3.793261837366959e-05, "epoch": 0.9815803683926322, "percentage": 32.71, "elapsed_time": "0:55:47", "remaining_time": "1:54:47", "throughput": 6858.07, "total_tokens": 22960648} {"current_steps": 2050, "total_steps": 6252, "loss": 0.5252, "lr": 3.7878823233467234e-05, "epoch": 0.9839803203935922, "percentage": 32.79, "elapsed_time": "0:55:57", "remaining_time": "1:54:42", "throughput": 6854.87, "total_tokens": 23017960} {"current_steps": 2055, "total_steps": 6252, "loss": 0.5098, "lr": 3.782494679565656e-05, "epoch": 0.9863802723945521, "percentage": 32.87, "elapsed_time": "0:56:07", "remaining_time": "1:54:38", "throughput": 6850.94, "total_tokens": 23073264} {"current_steps": 2060, "total_steps": 6252, "loss": 0.4722, "lr": 3.777098940033275e-05, "epoch": 0.988780224395512, "percentage": 32.95, "elapsed_time": "0:56:18", "remaining_time": "1:54:36", "throughput": 6845.53, "total_tokens": 23130952} {"current_steps": 2065, "total_steps": 6252, "loss": 0.512, "lr": 3.7716951388102e-05, "epoch": 0.991180176396472, "percentage": 33.03, "elapsed_time": "0:56:29", "remaining_time": "1:54:33", "throughput": 6839.31, "total_tokens": 23184912} {"current_steps": 2070, "total_steps": 6252, "loss": 0.5002, "lr": 3.766283310007943e-05, "epoch": 0.993580128397432, "percentage": 33.11, "elapsed_time": "0:56:38", "remaining_time": "1:54:25", "throughput": 6838.77, "total_tokens": 23238656} {"current_steps": 2075, "total_steps": 6252, "loss": 0.5014, "lr": 3.7608634877886885e-05, "epoch": 0.995980080398392, "percentage": 33.19, "elapsed_time": "0:56:45", "remaining_time": "1:54:16", "throughput": 6838.96, "total_tokens": 23293008} {"current_steps": 2080, "total_steps": 6252, "loss": 0.4932, "lr": 3.755435706365079e-05, "epoch": 0.998380032399352, "percentage": 33.27, "elapsed_time": "0:56:54", "remaining_time": "1:54:08", "throughput": 6838.69, "total_tokens": 23349040} {"current_steps": 2085, "total_steps": 6252, "loss": 0.5376, "lr": 3.7500000000000003e-05, "epoch": 1.000479990400192, "percentage": 33.35, "elapsed_time": "0:57:01", "remaining_time": "1:53:57", "throughput": 6839.5, "total_tokens": 23400800} {"current_steps": 2090, "total_steps": 6252, "loss": 0.4811, "lr": 3.7445564030063646e-05, "epoch": 1.002879942401152, "percentage": 33.43, "elapsed_time": "0:57:09", "remaining_time": "1:53:49", "throughput": 6839.62, "total_tokens": 23456048} {"current_steps": 2095, "total_steps": 6252, "loss": 0.4931, "lr": 3.739104949746893e-05, "epoch": 1.005279894402112, "percentage": 33.51, "elapsed_time": "0:57:17", "remaining_time": "1:53:40", "throughput": 6840.17, "total_tokens": 23511576} {"current_steps": 2100, "total_steps": 6252, "loss": 0.4666, "lr": 3.7336456746339e-05, "epoch": 1.0076798464030718, "percentage": 33.59, "elapsed_time": "0:57:25", "remaining_time": "1:53:31", "throughput": 6840.52, "total_tokens": 23567088} {"current_steps": 2105, "total_steps": 6252, "loss": 0.4806, "lr": 3.728178612129075e-05, "epoch": 1.010079798404032, "percentage": 33.67, "elapsed_time": "0:57:33", "remaining_time": "1:53:24", "throughput": 6840.39, "total_tokens": 23626528} {"current_steps": 2110, "total_steps": 6252, "loss": 0.4856, "lr": 3.722703796743267e-05, "epoch": 1.0124797504049918, "percentage": 33.75, "elapsed_time": "0:57:42", "remaining_time": "1:53:16", "throughput": 6840.0, "total_tokens": 23681288} {"current_steps": 2115, "total_steps": 6252, "loss": 0.5198, "lr": 3.7172212630362627e-05, "epoch": 1.014879702405952, "percentage": 33.83, "elapsed_time": "0:57:50", "remaining_time": "1:53:08", "throughput": 6840.72, "total_tokens": 23740272} {"current_steps": 2120, "total_steps": 6252, "loss": 0.5217, "lr": 3.7117310456165696e-05, "epoch": 1.0172796544069118, "percentage": 33.91, "elapsed_time": "0:57:58", "remaining_time": "1:53:00", "throughput": 6840.37, "total_tokens": 23796168} {"current_steps": 2125, "total_steps": 6252, "loss": 0.5463, "lr": 3.7062331791412045e-05, "epoch": 1.019679606407872, "percentage": 33.99, "elapsed_time": "0:58:06", "remaining_time": "1:52:51", "throughput": 6840.83, "total_tokens": 23852288} {"current_steps": 2130, "total_steps": 6252, "loss": 0.5069, "lr": 3.700727698315463e-05, "epoch": 1.0220795584088318, "percentage": 34.07, "elapsed_time": "0:58:14", "remaining_time": "1:52:42", "throughput": 6840.76, "total_tokens": 23906400} {"current_steps": 2135, "total_steps": 6252, "loss": 0.4976, "lr": 3.6952146378927095e-05, "epoch": 1.024479510409792, "percentage": 34.15, "elapsed_time": "0:58:23", "remaining_time": "1:52:35", "throughput": 6841.6, "total_tokens": 23966288} {"current_steps": 2140, "total_steps": 6252, "loss": 0.4863, "lr": 3.689694032674153e-05, "epoch": 1.0268794624107518, "percentage": 34.23, "elapsed_time": "0:58:31", "remaining_time": "1:52:28", "throughput": 6839.55, "total_tokens": 24019784} {"current_steps": 2145, "total_steps": 6252, "loss": 0.5026, "lr": 3.684165917508628e-05, "epoch": 1.0292794144117117, "percentage": 34.31, "elapsed_time": "0:58:42", "remaining_time": "1:52:24", "throughput": 6834.7, "total_tokens": 24075104} {"current_steps": 2150, "total_steps": 6252, "loss": 0.5197, "lr": 3.678630327292381e-05, "epoch": 1.0316793664126718, "percentage": 34.39, "elapsed_time": "0:58:50", "remaining_time": "1:52:15", "throughput": 6833.77, "total_tokens": 24125896} {"current_steps": 2155, "total_steps": 6252, "loss": 0.4873, "lr": 3.673087296968838e-05, "epoch": 1.0340793184136317, "percentage": 34.47, "elapsed_time": "0:58:58", "remaining_time": "1:52:07", "throughput": 6833.83, "total_tokens": 24182088} {"current_steps": 2160, "total_steps": 6252, "loss": 0.515, "lr": 3.667536861528396e-05, "epoch": 1.0364792704145918, "percentage": 34.55, "elapsed_time": "0:59:07", "remaining_time": "1:51:59", "throughput": 6834.48, "total_tokens": 24242048} {"current_steps": 2165, "total_steps": 6252, "loss": 0.486, "lr": 3.661979056008191e-05, "epoch": 1.0388792224155516, "percentage": 34.63, "elapsed_time": "0:59:14", "remaining_time": "1:51:50", "throughput": 6834.55, "total_tokens": 24294336} {"current_steps": 2170, "total_steps": 6252, "loss": 0.5121, "lr": 3.6564139154918895e-05, "epoch": 1.0412791744165117, "percentage": 34.71, "elapsed_time": "0:59:22", "remaining_time": "1:51:41", "throughput": 6835.13, "total_tokens": 24348872} {"current_steps": 2175, "total_steps": 6252, "loss": 0.5462, "lr": 3.6508414751094556e-05, "epoch": 1.0436791264174716, "percentage": 34.79, "elapsed_time": "0:59:30", "remaining_time": "1:51:31", "throughput": 6835.25, "total_tokens": 24402136} {"current_steps": 2180, "total_steps": 6252, "loss": 0.4975, "lr": 3.6452617700369345e-05, "epoch": 1.0460790784184317, "percentage": 34.87, "elapsed_time": "0:59:37", "remaining_time": "1:51:22", "throughput": 6835.13, "total_tokens": 24451792} {"current_steps": 2185, "total_steps": 6252, "loss": 0.568, "lr": 3.639674835496232e-05, "epoch": 1.0484790304193916, "percentage": 34.95, "elapsed_time": "0:59:45", "remaining_time": "1:51:13", "throughput": 6835.89, "total_tokens": 24508800} {"current_steps": 2190, "total_steps": 6252, "loss": 0.5024, "lr": 3.634080706754887e-05, "epoch": 1.0508789824203515, "percentage": 35.03, "elapsed_time": "0:59:53", "remaining_time": "1:51:05", "throughput": 6836.69, "total_tokens": 24567000} {"current_steps": 2195, "total_steps": 6252, "loss": 0.5057, "lr": 3.628479419125852e-05, "epoch": 1.0532789344213116, "percentage": 35.11, "elapsed_time": "1:00:02", "remaining_time": "1:50:57", "throughput": 6837.55, "total_tokens": 24629752} {"current_steps": 2200, "total_steps": 6252, "loss": 0.5329, "lr": 3.6228710079672734e-05, "epoch": 1.0556788864222715, "percentage": 35.19, "elapsed_time": "1:00:10", "remaining_time": "1:50:49", "throughput": 6837.67, "total_tokens": 24685968} {"current_steps": 2205, "total_steps": 6252, "loss": 0.5114, "lr": 3.6172555086822615e-05, "epoch": 1.0580788384232316, "percentage": 35.27, "elapsed_time": "1:00:18", "remaining_time": "1:50:40", "throughput": 6838.94, "total_tokens": 24745552} {"current_steps": 2210, "total_steps": 6252, "loss": 0.4939, "lr": 3.6116329567186724e-05, "epoch": 1.0604787904241915, "percentage": 35.35, "elapsed_time": "1:00:26", "remaining_time": "1:50:31", "throughput": 6839.3, "total_tokens": 24799856} {"current_steps": 2215, "total_steps": 6252, "loss": 0.5289, "lr": 3.6060033875688804e-05, "epoch": 1.0628787424251516, "percentage": 35.43, "elapsed_time": "1:00:33", "remaining_time": "1:50:22", "throughput": 6840.07, "total_tokens": 24853952} {"current_steps": 2220, "total_steps": 6252, "loss": 0.5015, "lr": 3.600366836769557e-05, "epoch": 1.0652786944261114, "percentage": 35.51, "elapsed_time": "1:00:41", "remaining_time": "1:50:13", "throughput": 6841.05, "total_tokens": 24911328} {"current_steps": 2225, "total_steps": 6252, "loss": 0.4982, "lr": 3.5947233399014444e-05, "epoch": 1.0676786464270716, "percentage": 35.59, "elapsed_time": "1:00:49", "remaining_time": "1:50:05", "throughput": 6840.9, "total_tokens": 24967496} {"current_steps": 2230, "total_steps": 6252, "loss": 0.4706, "lr": 3.589072932589134e-05, "epoch": 1.0700785984280314, "percentage": 35.67, "elapsed_time": "1:00:58", "remaining_time": "1:49:57", "throughput": 6842.0, "total_tokens": 25028408} {"current_steps": 2235, "total_steps": 6252, "loss": 0.5351, "lr": 3.583415650500837e-05, "epoch": 1.0724785504289913, "percentage": 35.75, "elapsed_time": "1:01:05", "remaining_time": "1:49:48", "throughput": 6842.46, "total_tokens": 25082672} {"current_steps": 2240, "total_steps": 6252, "loss": 0.5137, "lr": 3.577751529348163e-05, "epoch": 1.0748785024299514, "percentage": 35.83, "elapsed_time": "1:01:13", "remaining_time": "1:49:40", "throughput": 6842.57, "total_tokens": 25138272} {"current_steps": 2245, "total_steps": 6252, "loss": 0.4984, "lr": 3.572080604885894e-05, "epoch": 1.0772784544309113, "percentage": 35.91, "elapsed_time": "1:01:22", "remaining_time": "1:49:32", "throughput": 6842.8, "total_tokens": 25198880} {"current_steps": 2250, "total_steps": 6252, "loss": 0.4745, "lr": 3.566402912911755e-05, "epoch": 1.0796784064318714, "percentage": 35.99, "elapsed_time": "1:01:31", "remaining_time": "1:49:25", "throughput": 6842.42, "total_tokens": 25255672} {"current_steps": 2255, "total_steps": 6252, "loss": 0.4705, "lr": 3.560718489266194e-05, "epoch": 1.0820783584328313, "percentage": 36.07, "elapsed_time": "1:01:38", "remaining_time": "1:49:16", "throughput": 6842.71, "total_tokens": 25310096} {"current_steps": 2260, "total_steps": 6252, "loss": 0.529, "lr": 3.555027369832151e-05, "epoch": 1.0844783104337914, "percentage": 36.15, "elapsed_time": "1:01:46", "remaining_time": "1:49:07", "throughput": 6842.87, "total_tokens": 25365416} {"current_steps": 2265, "total_steps": 6252, "loss": 0.4974, "lr": 3.5493295905348334e-05, "epoch": 1.0868782624347513, "percentage": 36.23, "elapsed_time": "1:01:55", "remaining_time": "1:48:59", "throughput": 6842.77, "total_tokens": 25421480} {"current_steps": 2270, "total_steps": 6252, "loss": 0.4618, "lr": 3.54362518734149e-05, "epoch": 1.0892782144357114, "percentage": 36.31, "elapsed_time": "1:02:03", "remaining_time": "1:48:51", "throughput": 6843.35, "total_tokens": 25482160} {"current_steps": 2275, "total_steps": 6252, "loss": 0.5266, "lr": 3.537914196261181e-05, "epoch": 1.0916781664366713, "percentage": 36.39, "elapsed_time": "1:02:11", "remaining_time": "1:48:43", "throughput": 6843.35, "total_tokens": 25538416} {"current_steps": 2280, "total_steps": 6252, "loss": 0.5244, "lr": 3.5321966533445547e-05, "epoch": 1.0940781184376314, "percentage": 36.47, "elapsed_time": "1:02:19", "remaining_time": "1:48:35", "throughput": 6843.65, "total_tokens": 25594328} {"current_steps": 2285, "total_steps": 6252, "loss": 0.5011, "lr": 3.526472594683617e-05, "epoch": 1.0964780704385912, "percentage": 36.55, "elapsed_time": "1:02:27", "remaining_time": "1:48:26", "throughput": 6843.4, "total_tokens": 25647608} {"current_steps": 2290, "total_steps": 6252, "loss": 0.5229, "lr": 3.5207420564115045e-05, "epoch": 1.0988780224395511, "percentage": 36.63, "elapsed_time": "1:02:35", "remaining_time": "1:48:17", "throughput": 6844.07, "total_tokens": 25702960} {"current_steps": 2295, "total_steps": 6252, "loss": 0.5035, "lr": 3.515005074702256e-05, "epoch": 1.1012779744405112, "percentage": 36.71, "elapsed_time": "1:02:43", "remaining_time": "1:48:09", "throughput": 6844.02, "total_tokens": 25758120} {"current_steps": 2300, "total_steps": 6252, "loss": 0.4939, "lr": 3.509261685770585e-05, "epoch": 1.1036779264414711, "percentage": 36.79, "elapsed_time": "1:02:52", "remaining_time": "1:48:01", "throughput": 6844.37, "total_tokens": 25817024} {"current_steps": 2305, "total_steps": 6252, "loss": 0.5389, "lr": 3.5035119258716495e-05, "epoch": 1.1060778784424312, "percentage": 36.87, "elapsed_time": "1:03:00", "remaining_time": "1:47:54", "throughput": 6844.19, "total_tokens": 25876744} {"current_steps": 2310, "total_steps": 6252, "loss": 0.49, "lr": 3.497755831300828e-05, "epoch": 1.108477830443391, "percentage": 36.95, "elapsed_time": "1:03:08", "remaining_time": "1:47:45", "throughput": 6843.3, "total_tokens": 25928600} {"current_steps": 2315, "total_steps": 6252, "loss": 0.4658, "lr": 3.491993438393481e-05, "epoch": 1.1108777824443512, "percentage": 37.03, "elapsed_time": "1:03:17", "remaining_time": "1:47:37", "throughput": 6843.26, "total_tokens": 25985192} {"current_steps": 2320, "total_steps": 6252, "loss": 0.5464, "lr": 3.486224783524731e-05, "epoch": 1.113277734445311, "percentage": 37.11, "elapsed_time": "1:03:24", "remaining_time": "1:47:28", "throughput": 6844.04, "total_tokens": 26040520} {"current_steps": 2325, "total_steps": 6252, "loss": 0.5227, "lr": 3.480449903109229e-05, "epoch": 1.1156776864462712, "percentage": 37.19, "elapsed_time": "1:03:32", "remaining_time": "1:47:19", "throughput": 6844.29, "total_tokens": 26093336} {"current_steps": 2330, "total_steps": 6252, "loss": 0.4759, "lr": 3.474668833600923e-05, "epoch": 1.118077638447231, "percentage": 37.27, "elapsed_time": "1:03:40", "remaining_time": "1:47:10", "throughput": 6844.16, "total_tokens": 26148320} {"current_steps": 2335, "total_steps": 6252, "loss": 0.5181, "lr": 3.4688816114928327e-05, "epoch": 1.120477590448191, "percentage": 37.35, "elapsed_time": "1:03:48", "remaining_time": "1:47:02", "throughput": 6844.98, "total_tokens": 26206080} {"current_steps": 2340, "total_steps": 6252, "loss": 0.4938, "lr": 3.4630882733168116e-05, "epoch": 1.122877542449151, "percentage": 37.43, "elapsed_time": "1:03:56", "remaining_time": "1:46:53", "throughput": 6845.58, "total_tokens": 26262688} {"current_steps": 2345, "total_steps": 6252, "loss": 0.4681, "lr": 3.4572888556433246e-05, "epoch": 1.125277494450111, "percentage": 37.51, "elapsed_time": "1:04:04", "remaining_time": "1:46:45", "throughput": 6845.72, "total_tokens": 26321160} {"current_steps": 2350, "total_steps": 6252, "loss": 0.4631, "lr": 3.451483395081212e-05, "epoch": 1.127677446451071, "percentage": 37.59, "elapsed_time": "1:04:13", "remaining_time": "1:46:37", "throughput": 6845.91, "total_tokens": 26378192} {"current_steps": 2355, "total_steps": 6252, "loss": 0.4676, "lr": 3.445671928277461e-05, "epoch": 1.130077398452031, "percentage": 37.67, "elapsed_time": "1:04:20", "remaining_time": "1:46:28", "throughput": 6845.7, "total_tokens": 26430848} {"current_steps": 2360, "total_steps": 6252, "loss": 0.4904, "lr": 3.4398544919169715e-05, "epoch": 1.132477350452991, "percentage": 37.75, "elapsed_time": "1:04:28", "remaining_time": "1:46:20", "throughput": 6846.76, "total_tokens": 26489064} {"current_steps": 2365, "total_steps": 6252, "loss": 0.5352, "lr": 3.4340311227223273e-05, "epoch": 1.134877302453951, "percentage": 37.83, "elapsed_time": "1:04:36", "remaining_time": "1:46:11", "throughput": 6846.55, "total_tokens": 26543528} {"current_steps": 2370, "total_steps": 6252, "loss": 0.5051, "lr": 3.428201857453562e-05, "epoch": 1.137277254454911, "percentage": 37.91, "elapsed_time": "1:04:44", "remaining_time": "1:46:02", "throughput": 6846.65, "total_tokens": 26596928} {"current_steps": 2375, "total_steps": 6252, "loss": 0.4361, "lr": 3.422366732907931e-05, "epoch": 1.139677206455871, "percentage": 37.99, "elapsed_time": "1:04:53", "remaining_time": "1:45:55", "throughput": 6846.4, "total_tokens": 26654072} {"current_steps": 2380, "total_steps": 6252, "loss": 0.488, "lr": 3.416525785919673e-05, "epoch": 1.1420771584568308, "percentage": 38.07, "elapsed_time": "1:05:00", "remaining_time": "1:45:46", "throughput": 6846.44, "total_tokens": 26707464} {"current_steps": 2385, "total_steps": 6252, "loss": 0.4326, "lr": 3.410679053359784e-05, "epoch": 1.1444771104577909, "percentage": 38.15, "elapsed_time": "1:05:09", "remaining_time": "1:45:38", "throughput": 6846.56, "total_tokens": 26766704} {"current_steps": 2390, "total_steps": 6252, "loss": 0.4831, "lr": 3.404826572135779e-05, "epoch": 1.1468770624587508, "percentage": 38.23, "elapsed_time": "1:05:18", "remaining_time": "1:45:31", "throughput": 6846.05, "total_tokens": 26826328} {"current_steps": 2395, "total_steps": 6252, "loss": 0.4909, "lr": 3.398968379191462e-05, "epoch": 1.1492770144597109, "percentage": 38.31, "elapsed_time": "1:05:26", "remaining_time": "1:45:23", "throughput": 6846.24, "total_tokens": 26880888} {"current_steps": 2400, "total_steps": 6252, "loss": 0.4903, "lr": 3.393104511506694e-05, "epoch": 1.1516769664606707, "percentage": 38.39, "elapsed_time": "1:05:34", "remaining_time": "1:45:14", "throughput": 6846.96, "total_tokens": 26937800} {"current_steps": 2405, "total_steps": 6252, "loss": 0.4994, "lr": 3.387235006097155e-05, "epoch": 1.1540769184616309, "percentage": 38.47, "elapsed_time": "1:05:41", "remaining_time": "1:45:05", "throughput": 6847.74, "total_tokens": 26993776} {"current_steps": 2410, "total_steps": 6252, "loss": 0.4745, "lr": 3.381359900014116e-05, "epoch": 1.1564768704625907, "percentage": 38.55, "elapsed_time": "1:05:50", "remaining_time": "1:44:58", "throughput": 6847.82, "total_tokens": 27053440} {"current_steps": 2415, "total_steps": 6252, "loss": 0.5404, "lr": 3.375479230344199e-05, "epoch": 1.1588768224635508, "percentage": 38.63, "elapsed_time": "1:05:58", "remaining_time": "1:44:49", "throughput": 6847.11, "total_tokens": 27104744} {"current_steps": 2420, "total_steps": 6252, "loss": 0.5069, "lr": 3.369593034209149e-05, "epoch": 1.1612767744645107, "percentage": 38.71, "elapsed_time": "1:06:06", "remaining_time": "1:44:41", "throughput": 6846.54, "total_tokens": 27159864} {"current_steps": 2425, "total_steps": 6252, "loss": 0.4541, "lr": 3.363701348765597e-05, "epoch": 1.1636767264654706, "percentage": 38.79, "elapsed_time": "1:06:15", "remaining_time": "1:44:34", "throughput": 6846.03, "total_tokens": 27219344} {"current_steps": 2430, "total_steps": 6252, "loss": 0.4447, "lr": 3.3578042112048226e-05, "epoch": 1.1660766784664307, "percentage": 38.87, "elapsed_time": "1:06:24", "remaining_time": "1:44:27", "throughput": 6845.89, "total_tokens": 27279536} {"current_steps": 2435, "total_steps": 6252, "loss": 0.5227, "lr": 3.351901658752524e-05, "epoch": 1.1684766304673906, "percentage": 38.95, "elapsed_time": "1:06:32", "remaining_time": "1:44:18", "throughput": 6846.39, "total_tokens": 27336160} {"current_steps": 2440, "total_steps": 6252, "loss": 0.4813, "lr": 3.34599372866858e-05, "epoch": 1.1708765824683507, "percentage": 39.03, "elapsed_time": "1:06:41", "remaining_time": "1:44:10", "throughput": 6846.36, "total_tokens": 27393304} {"current_steps": 2445, "total_steps": 6252, "loss": 0.5101, "lr": 3.3400804582468154e-05, "epoch": 1.1732765344693106, "percentage": 39.11, "elapsed_time": "1:06:48", "remaining_time": "1:44:01", "throughput": 6846.47, "total_tokens": 27444632} {"current_steps": 2450, "total_steps": 6252, "loss": 0.4709, "lr": 3.334161884814769e-05, "epoch": 1.1756764864702707, "percentage": 39.19, "elapsed_time": "1:06:56", "remaining_time": "1:43:53", "throughput": 6847.12, "total_tokens": 27502576} {"current_steps": 2455, "total_steps": 6252, "loss": 0.5498, "lr": 3.3282380457334505e-05, "epoch": 1.1780764384712306, "percentage": 39.27, "elapsed_time": "1:07:04", "remaining_time": "1:43:44", "throughput": 6847.31, "total_tokens": 27559352} {"current_steps": 2460, "total_steps": 6252, "loss": 0.507, "lr": 3.3223089783971114e-05, "epoch": 1.1804763904721907, "percentage": 39.35, "elapsed_time": "1:07:12", "remaining_time": "1:43:36", "throughput": 6847.99, "total_tokens": 27615472} {"current_steps": 2465, "total_steps": 6252, "loss": 0.498, "lr": 3.3163747202330066e-05, "epoch": 1.1828763424731505, "percentage": 39.43, "elapsed_time": "1:07:20", "remaining_time": "1:43:27", "throughput": 6848.83, "total_tokens": 27671096} {"current_steps": 2470, "total_steps": 6252, "loss": 0.5188, "lr": 3.310435308701156e-05, "epoch": 1.1852762944741104, "percentage": 39.51, "elapsed_time": "1:07:27", "remaining_time": "1:43:18", "throughput": 6848.56, "total_tokens": 27722512} {"current_steps": 2475, "total_steps": 6252, "loss": 0.4861, "lr": 3.304490781294114e-05, "epoch": 1.1876762464750705, "percentage": 39.59, "elapsed_time": "1:07:35", "remaining_time": "1:43:09", "throughput": 6849.13, "total_tokens": 27778280} {"current_steps": 2480, "total_steps": 6252, "loss": 0.4792, "lr": 3.2985411755367246e-05, "epoch": 1.1900761984760304, "percentage": 39.67, "elapsed_time": "1:07:44", "remaining_time": "1:43:01", "throughput": 6849.4, "total_tokens": 27839424} {"current_steps": 2485, "total_steps": 6252, "loss": 0.4599, "lr": 3.292586528985894e-05, "epoch": 1.1924761504769905, "percentage": 39.75, "elapsed_time": "1:07:52", "remaining_time": "1:42:53", "throughput": 6849.6, "total_tokens": 27894440} {"current_steps": 2490, "total_steps": 6252, "loss": 0.4936, "lr": 3.2866268792303424e-05, "epoch": 1.1948761024779504, "percentage": 39.83, "elapsed_time": "1:08:02", "remaining_time": "1:42:47", "throughput": 6849.28, "total_tokens": 27959096} {"current_steps": 2495, "total_steps": 6252, "loss": 0.5008, "lr": 3.2806622638903764e-05, "epoch": 1.1972760544789105, "percentage": 39.91, "elapsed_time": "1:08:09", "remaining_time": "1:42:37", "throughput": 6849.42, "total_tokens": 28010352} {"current_steps": 2500, "total_steps": 6252, "loss": 0.5232, "lr": 3.274692720617649e-05, "epoch": 1.1996760064798704, "percentage": 39.99, "elapsed_time": "1:08:18", "remaining_time": "1:42:30", "throughput": 6848.92, "total_tokens": 28067424} {"current_steps": 2505, "total_steps": 6252, "loss": 0.4749, "lr": 3.2687182870949185e-05, "epoch": 1.2020759584808305, "percentage": 40.07, "elapsed_time": "1:08:26", "remaining_time": "1:42:22", "throughput": 6849.56, "total_tokens": 28126704} {"current_steps": 2510, "total_steps": 6252, "loss": 0.4965, "lr": 3.2627390010358133e-05, "epoch": 1.2044759104817904, "percentage": 40.15, "elapsed_time": "1:08:34", "remaining_time": "1:42:14", "throughput": 6849.56, "total_tokens": 28184072} {"current_steps": 2515, "total_steps": 6252, "loss": 0.489, "lr": 3.256754900184593e-05, "epoch": 1.2068758624827503, "percentage": 40.23, "elapsed_time": "1:08:42", "remaining_time": "1:42:05", "throughput": 6849.77, "total_tokens": 28237608} {"current_steps": 2520, "total_steps": 6252, "loss": 0.449, "lr": 3.2507660223159115e-05, "epoch": 1.2092758144837104, "percentage": 40.31, "elapsed_time": "1:08:51", "remaining_time": "1:41:58", "throughput": 6850.22, "total_tokens": 28299544} {"current_steps": 2525, "total_steps": 6252, "loss": 0.4269, "lr": 3.2447724052345786e-05, "epoch": 1.2116757664846702, "percentage": 40.39, "elapsed_time": "1:08:59", "remaining_time": "1:41:50", "throughput": 6850.41, "total_tokens": 28357640} {"current_steps": 2530, "total_steps": 6252, "loss": 0.4937, "lr": 3.238774086775317e-05, "epoch": 1.2140757184856303, "percentage": 40.47, "elapsed_time": "1:09:07", "remaining_time": "1:41:41", "throughput": 6850.36, "total_tokens": 28411848} {"current_steps": 2535, "total_steps": 6252, "loss": 0.473, "lr": 3.2327711048025314e-05, "epoch": 1.2164756704865902, "percentage": 40.55, "elapsed_time": "1:09:15", "remaining_time": "1:41:33", "throughput": 6849.71, "total_tokens": 28465072} {"current_steps": 2540, "total_steps": 6252, "loss": 0.5217, "lr": 3.226763497210061e-05, "epoch": 1.2188756224875503, "percentage": 40.63, "elapsed_time": "1:09:22", "remaining_time": "1:41:23", "throughput": 6849.81, "total_tokens": 28513584} {"current_steps": 2545, "total_steps": 6252, "loss": 0.5058, "lr": 3.2207513019209455e-05, "epoch": 1.2212755744885102, "percentage": 40.71, "elapsed_time": "1:09:30", "remaining_time": "1:41:15", "throughput": 6850.1, "total_tokens": 28569888} {"current_steps": 2550, "total_steps": 6252, "loss": 0.4699, "lr": 3.2147345568871874e-05, "epoch": 1.2236755264894703, "percentage": 40.79, "elapsed_time": "1:09:38", "remaining_time": "1:41:06", "throughput": 6850.21, "total_tokens": 28623888} {"current_steps": 2555, "total_steps": 6252, "loss": 0.4585, "lr": 3.208713300089504e-05, "epoch": 1.2260754784904302, "percentage": 40.87, "elapsed_time": "1:09:47", "remaining_time": "1:40:58", "throughput": 6849.79, "total_tokens": 28680088} {"current_steps": 2560, "total_steps": 6252, "loss": 0.4872, "lr": 3.2026875695370975e-05, "epoch": 1.22847543049139, "percentage": 40.95, "elapsed_time": "1:09:54", "remaining_time": "1:40:49", "throughput": 6850.35, "total_tokens": 28733184} {"current_steps": 2565, "total_steps": 6252, "loss": 0.5134, "lr": 3.1966574032674074e-05, "epoch": 1.2308753824923502, "percentage": 41.03, "elapsed_time": "1:10:02", "remaining_time": "1:40:40", "throughput": 6850.88, "total_tokens": 28787400} {"current_steps": 2570, "total_steps": 6252, "loss": 0.4758, "lr": 3.190622839345878e-05, "epoch": 1.23327533449331, "percentage": 41.11, "elapsed_time": "1:10:09", "remaining_time": "1:40:31", "throughput": 6850.87, "total_tokens": 28840944} {"current_steps": 2575, "total_steps": 6252, "loss": 0.5343, "lr": 3.184583915865709e-05, "epoch": 1.2356752864942702, "percentage": 41.19, "elapsed_time": "1:10:17", "remaining_time": "1:40:21", "throughput": 6851.41, "total_tokens": 28893352} {"current_steps": 2580, "total_steps": 6252, "loss": 0.4822, "lr": 3.178540670947624e-05, "epoch": 1.23807523849523, "percentage": 41.27, "elapsed_time": "1:10:25", "remaining_time": "1:40:14", "throughput": 6851.38, "total_tokens": 28952544} {"current_steps": 2585, "total_steps": 6252, "loss": 0.4529, "lr": 3.172493142739622e-05, "epoch": 1.2404751904961901, "percentage": 41.35, "elapsed_time": "1:10:33", "remaining_time": "1:40:05", "throughput": 6851.62, "total_tokens": 29007344} {"current_steps": 2590, "total_steps": 6252, "loss": 0.5018, "lr": 3.1664413694167424e-05, "epoch": 1.24287514249715, "percentage": 41.43, "elapsed_time": "1:10:42", "remaining_time": "1:39:57", "throughput": 6851.85, "total_tokens": 29065880} {"current_steps": 2595, "total_steps": 6252, "loss": 0.5014, "lr": 3.160385389180822e-05, "epoch": 1.2452750944981101, "percentage": 41.51, "elapsed_time": "1:10:50", "remaining_time": "1:39:50", "throughput": 6851.01, "total_tokens": 29120600} {"current_steps": 2600, "total_steps": 6252, "loss": 0.4823, "lr": 3.154325240260254e-05, "epoch": 1.24767504649907, "percentage": 41.59, "elapsed_time": "1:10:58", "remaining_time": "1:39:41", "throughput": 6850.67, "total_tokens": 29174832} {"current_steps": 2605, "total_steps": 6252, "loss": 0.4527, "lr": 3.148260960909745e-05, "epoch": 1.25007499850003, "percentage": 41.67, "elapsed_time": "1:11:06", "remaining_time": "1:39:33", "throughput": 6850.44, "total_tokens": 29228680} {"current_steps": 2610, "total_steps": 6252, "loss": 0.5152, "lr": 3.1421925894100745e-05, "epoch": 1.25247495050099, "percentage": 41.75, "elapsed_time": "1:11:14", "remaining_time": "1:39:24", "throughput": 6850.59, "total_tokens": 29282976} {"current_steps": 2615, "total_steps": 6252, "loss": 0.5055, "lr": 3.1361201640678554e-05, "epoch": 1.2548749025019499, "percentage": 41.83, "elapsed_time": "1:11:22", "remaining_time": "1:39:16", "throughput": 6850.3, "total_tokens": 29337384} {"current_steps": 2620, "total_steps": 6252, "loss": 0.4808, "lr": 3.130043723215291e-05, "epoch": 1.25727485450291, "percentage": 41.91, "elapsed_time": "1:11:31", "remaining_time": "1:39:09", "throughput": 6850.3, "total_tokens": 29398256} {"current_steps": 2625, "total_steps": 6252, "loss": 0.5101, "lr": 3.123963305209932e-05, "epoch": 1.2596748065038699, "percentage": 41.99, "elapsed_time": "1:11:39", "remaining_time": "1:39:00", "throughput": 6850.79, "total_tokens": 29455288} {"current_steps": 2630, "total_steps": 6252, "loss": 0.468, "lr": 3.1178789484344326e-05, "epoch": 1.26207475850483, "percentage": 42.07, "elapsed_time": "1:11:47", "remaining_time": "1:38:52", "throughput": 6850.84, "total_tokens": 29513208} {"current_steps": 2635, "total_steps": 6252, "loss": 0.5214, "lr": 3.1117906912963124e-05, "epoch": 1.2644747105057899, "percentage": 42.15, "elapsed_time": "1:11:55", "remaining_time": "1:38:44", "throughput": 6850.9, "total_tokens": 29566424} {"current_steps": 2640, "total_steps": 6252, "loss": 0.5059, "lr": 3.105698572227712e-05, "epoch": 1.26687466250675, "percentage": 42.23, "elapsed_time": "1:12:04", "remaining_time": "1:38:36", "throughput": 6850.32, "total_tokens": 29621112} {"current_steps": 2645, "total_steps": 6252, "loss": 0.4705, "lr": 3.0996026296851516e-05, "epoch": 1.2692746145077098, "percentage": 42.31, "elapsed_time": "1:12:11", "remaining_time": "1:38:26", "throughput": 6850.48, "total_tokens": 29672896} {"current_steps": 2650, "total_steps": 6252, "loss": 0.4753, "lr": 3.093502902149285e-05, "epoch": 1.2716745665086697, "percentage": 42.39, "elapsed_time": "1:12:19", "remaining_time": "1:38:17", "throughput": 6850.23, "total_tokens": 29724344} {"current_steps": 2655, "total_steps": 6252, "loss": 0.5218, "lr": 3.087399428124659e-05, "epoch": 1.2740745185096298, "percentage": 42.47, "elapsed_time": "1:12:27", "remaining_time": "1:38:09", "throughput": 6850.44, "total_tokens": 29779744} {"current_steps": 2660, "total_steps": 6252, "loss": 0.4784, "lr": 3.081292246139473e-05, "epoch": 1.2764744705105897, "percentage": 42.55, "elapsed_time": "1:12:35", "remaining_time": "1:38:01", "throughput": 6850.35, "total_tokens": 29834824} {"current_steps": 2665, "total_steps": 6252, "loss": 0.4886, "lr": 3.0751813947453265e-05, "epoch": 1.2788744225115498, "percentage": 42.63, "elapsed_time": "1:12:42", "remaining_time": "1:37:52", "throughput": 6851.15, "total_tokens": 29890520} {"current_steps": 2670, "total_steps": 6252, "loss": 0.5277, "lr": 3.069066912516991e-05, "epoch": 1.2812743745125097, "percentage": 42.71, "elapsed_time": "1:12:50", "remaining_time": "1:37:43", "throughput": 6851.51, "total_tokens": 29945288} {"current_steps": 2675, "total_steps": 6252, "loss": 0.5158, "lr": 3.0629488380521504e-05, "epoch": 1.2836743265134698, "percentage": 42.79, "elapsed_time": "1:12:58", "remaining_time": "1:37:35", "throughput": 6851.5, "total_tokens": 30001032} {"current_steps": 2680, "total_steps": 6252, "loss": 0.5022, "lr": 3.056827209971167e-05, "epoch": 1.2860742785144297, "percentage": 42.87, "elapsed_time": "1:13:07", "remaining_time": "1:37:27", "throughput": 6850.81, "total_tokens": 30057416} {"current_steps": 2685, "total_steps": 6252, "loss": 0.4875, "lr": 3.0507020669168367e-05, "epoch": 1.2884742305153898, "percentage": 42.95, "elapsed_time": "1:13:15", "remaining_time": "1:37:19", "throughput": 6850.99, "total_tokens": 30113512} {"current_steps": 2690, "total_steps": 6252, "loss": 0.4872, "lr": 3.044573447554141e-05, "epoch": 1.2908741825163497, "percentage": 43.03, "elapsed_time": "1:13:24", "remaining_time": "1:37:11", "throughput": 6850.8, "total_tokens": 30171064} {"current_steps": 2695, "total_steps": 6252, "loss": 0.4715, "lr": 3.038441390570008e-05, "epoch": 1.2932741345173095, "percentage": 43.11, "elapsed_time": "1:13:32", "remaining_time": "1:37:03", "throughput": 6850.79, "total_tokens": 30226872} {"current_steps": 2700, "total_steps": 6252, "loss": 0.5249, "lr": 3.0323059346730666e-05, "epoch": 1.2956740865182697, "percentage": 43.19, "elapsed_time": "1:13:40", "remaining_time": "1:36:55", "throughput": 6850.64, "total_tokens": 30281784} {"current_steps": 2705, "total_steps": 6252, "loss": 0.5334, "lr": 3.026167118593396e-05, "epoch": 1.2980740385192295, "percentage": 43.27, "elapsed_time": "1:13:48", "remaining_time": "1:36:46", "throughput": 6850.62, "total_tokens": 30336824} {"current_steps": 2710, "total_steps": 6252, "loss": 0.4795, "lr": 3.0200249810822922e-05, "epoch": 1.3004739905201896, "percentage": 43.35, "elapsed_time": "1:13:56", "remaining_time": "1:36:38", "throughput": 6850.17, "total_tokens": 30391968} {"current_steps": 2715, "total_steps": 6252, "loss": 0.5054, "lr": 3.0138795609120156e-05, "epoch": 1.3028739425211495, "percentage": 43.43, "elapsed_time": "1:14:05", "remaining_time": "1:36:30", "throughput": 6849.94, "total_tokens": 30448056} {"current_steps": 2720, "total_steps": 6252, "loss": 0.4871, "lr": 3.0077308968755484e-05, "epoch": 1.3052738945221096, "percentage": 43.51, "elapsed_time": "1:14:14", "remaining_time": "1:36:23", "throughput": 6849.75, "total_tokens": 30509528} {"current_steps": 2725, "total_steps": 6252, "loss": 0.5235, "lr": 3.0015790277863504e-05, "epoch": 1.3076738465230695, "percentage": 43.59, "elapsed_time": "1:14:22", "remaining_time": "1:36:15", "throughput": 6849.28, "total_tokens": 30564064} {"current_steps": 2730, "total_steps": 6252, "loss": 0.5481, "lr": 2.9954239924781114e-05, "epoch": 1.3100737985240296, "percentage": 43.67, "elapsed_time": "1:14:29", "remaining_time": "1:36:06", "throughput": 6849.66, "total_tokens": 30617256} {"current_steps": 2735, "total_steps": 6252, "loss": 0.4882, "lr": 2.9892658298045105e-05, "epoch": 1.3124737505249895, "percentage": 43.75, "elapsed_time": "1:14:38", "remaining_time": "1:35:58", "throughput": 6850.47, "total_tokens": 30676776} {"current_steps": 2740, "total_steps": 6252, "loss": 0.5133, "lr": 2.983104578638966e-05, "epoch": 1.3148737025259494, "percentage": 43.83, "elapsed_time": "1:14:46", "remaining_time": "1:35:50", "throughput": 6849.81, "total_tokens": 30729600} {"current_steps": 2745, "total_steps": 6252, "loss": 0.4772, "lr": 2.976940277874395e-05, "epoch": 1.3172736545269095, "percentage": 43.91, "elapsed_time": "1:14:53", "remaining_time": "1:35:41", "throughput": 6850.66, "total_tokens": 30786720} {"current_steps": 2750, "total_steps": 6252, "loss": 0.5323, "lr": 2.9707729664229623e-05, "epoch": 1.3196736065278696, "percentage": 43.99, "elapsed_time": "1:15:02", "remaining_time": "1:35:33", "throughput": 6851.2, "total_tokens": 30844488} {"current_steps": 2755, "total_steps": 6252, "loss": 0.5318, "lr": 2.964602683215839e-05, "epoch": 1.3220735585288295, "percentage": 44.07, "elapsed_time": "1:15:10", "remaining_time": "1:35:25", "throughput": 6851.0, "total_tokens": 30901200} {"current_steps": 2760, "total_steps": 6252, "loss": 0.4453, "lr": 2.958429467202956e-05, "epoch": 1.3244735105297893, "percentage": 44.15, "elapsed_time": "1:15:19", "remaining_time": "1:35:17", "throughput": 6850.14, "total_tokens": 30957496} {"current_steps": 2765, "total_steps": 6252, "loss": 0.4547, "lr": 2.9522533573527568e-05, "epoch": 1.3268734625307494, "percentage": 44.23, "elapsed_time": "1:15:27", "remaining_time": "1:35:09", "throughput": 6850.0, "total_tokens": 31014440} {"current_steps": 2770, "total_steps": 6252, "loss": 0.4866, "lr": 2.9460743926519524e-05, "epoch": 1.3292734145317093, "percentage": 44.31, "elapsed_time": "1:15:35", "remaining_time": "1:35:01", "throughput": 6849.91, "total_tokens": 31069232} {"current_steps": 2775, "total_steps": 6252, "loss": 0.4363, "lr": 2.9398926121052757e-05, "epoch": 1.3316733665326694, "percentage": 44.39, "elapsed_time": "1:15:43", "remaining_time": "1:34:53", "throughput": 6850.08, "total_tokens": 31124192} {"current_steps": 2780, "total_steps": 6252, "loss": 0.5387, "lr": 2.933708054735232e-05, "epoch": 1.3340733185336293, "percentage": 44.47, "elapsed_time": "1:15:51", "remaining_time": "1:34:44", "throughput": 6850.38, "total_tokens": 31181208} {"current_steps": 2785, "total_steps": 6252, "loss": 0.4733, "lr": 2.9275207595818587e-05, "epoch": 1.3364732705345892, "percentage": 44.55, "elapsed_time": "1:16:00", "remaining_time": "1:34:36", "throughput": 6850.48, "total_tokens": 31238792} {"current_steps": 2790, "total_steps": 6252, "loss": 0.4498, "lr": 2.9213307657024747e-05, "epoch": 1.3388732225355493, "percentage": 44.63, "elapsed_time": "1:16:08", "remaining_time": "1:34:28", "throughput": 6850.17, "total_tokens": 31293408} {"current_steps": 2795, "total_steps": 6252, "loss": 0.4626, "lr": 2.9151381121714326e-05, "epoch": 1.3412731745365094, "percentage": 44.71, "elapsed_time": "1:16:16", "remaining_time": "1:34:20", "throughput": 6850.67, "total_tokens": 31351360} {"current_steps": 2800, "total_steps": 6252, "loss": 0.5147, "lr": 2.9089428380798765e-05, "epoch": 1.3436731265374693, "percentage": 44.79, "elapsed_time": "1:16:24", "remaining_time": "1:34:12", "throughput": 6850.65, "total_tokens": 31408064} {"current_steps": 2805, "total_steps": 6252, "loss": 0.5005, "lr": 2.9027449825354914e-05, "epoch": 1.3460730785384292, "percentage": 44.87, "elapsed_time": "1:16:33", "remaining_time": "1:34:05", "throughput": 6849.9, "total_tokens": 31465944} {"current_steps": 2810, "total_steps": 6252, "loss": 0.5212, "lr": 2.8965445846622575e-05, "epoch": 1.3484730305393893, "percentage": 44.95, "elapsed_time": "1:16:41", "remaining_time": "1:33:56", "throughput": 6849.67, "total_tokens": 31519296} {"current_steps": 2815, "total_steps": 6252, "loss": 0.4881, "lr": 2.8903416836002046e-05, "epoch": 1.3508729825403492, "percentage": 45.03, "elapsed_time": "1:16:49", "remaining_time": "1:33:47", "throughput": 6850.03, "total_tokens": 31575040} {"current_steps": 2820, "total_steps": 6252, "loss": 0.5284, "lr": 2.8841363185051627e-05, "epoch": 1.3532729345413093, "percentage": 45.11, "elapsed_time": "1:16:57", "remaining_time": "1:33:39", "throughput": 6849.87, "total_tokens": 31627864} {"current_steps": 2825, "total_steps": 6252, "loss": 0.5337, "lr": 2.877928528548518e-05, "epoch": 1.3556728865422691, "percentage": 45.19, "elapsed_time": "1:17:05", "remaining_time": "1:33:30", "throughput": 6849.96, "total_tokens": 31681448} {"current_steps": 2830, "total_steps": 6252, "loss": 0.4355, "lr": 2.871718352916961e-05, "epoch": 1.358072838543229, "percentage": 45.27, "elapsed_time": "1:17:12", "remaining_time": "1:33:21", "throughput": 6850.34, "total_tokens": 31734720} {"current_steps": 2835, "total_steps": 6252, "loss": 0.522, "lr": 2.8655058308122435e-05, "epoch": 1.3604727905441891, "percentage": 45.35, "elapsed_time": "1:17:20", "remaining_time": "1:33:12", "throughput": 6850.35, "total_tokens": 31786472} {"current_steps": 2840, "total_steps": 6252, "loss": 0.4825, "lr": 2.8592910014509284e-05, "epoch": 1.3628727425451492, "percentage": 45.43, "elapsed_time": "1:17:28", "remaining_time": "1:33:04", "throughput": 6849.72, "total_tokens": 31842040} {"current_steps": 2845, "total_steps": 6252, "loss": 0.4791, "lr": 2.853073904064144e-05, "epoch": 1.3652726945461091, "percentage": 45.51, "elapsed_time": "1:17:37", "remaining_time": "1:32:57", "throughput": 6849.34, "total_tokens": 31901936} {"current_steps": 2850, "total_steps": 6252, "loss": 0.4962, "lr": 2.8468545778973365e-05, "epoch": 1.367672646547069, "percentage": 45.59, "elapsed_time": "1:17:45", "remaining_time": "1:32:49", "throughput": 6848.88, "total_tokens": 31955760} {"current_steps": 2855, "total_steps": 6252, "loss": 0.5193, "lr": 2.8406330622100185e-05, "epoch": 1.370072598548029, "percentage": 45.67, "elapsed_time": "1:17:54", "remaining_time": "1:32:41", "throughput": 6849.1, "total_tokens": 32012936} {"current_steps": 2860, "total_steps": 6252, "loss": 0.4838, "lr": 2.834409396275526e-05, "epoch": 1.372472550548989, "percentage": 45.75, "elapsed_time": "1:18:03", "remaining_time": "1:32:34", "throughput": 6849.28, "total_tokens": 32075400} {"current_steps": 2865, "total_steps": 6252, "loss": 0.5193, "lr": 2.8281836193807677e-05, "epoch": 1.374872502549949, "percentage": 45.83, "elapsed_time": "1:18:10", "remaining_time": "1:32:25", "throughput": 6849.38, "total_tokens": 32127560} {"current_steps": 2870, "total_steps": 6252, "loss": 0.563, "lr": 2.821955770825978e-05, "epoch": 1.377272454550909, "percentage": 45.91, "elapsed_time": "1:18:18", "remaining_time": "1:32:16", "throughput": 6849.87, "total_tokens": 32182368} {"current_steps": 2875, "total_steps": 6252, "loss": 0.4983, "lr": 2.81572588992447e-05, "epoch": 1.3796724065518688, "percentage": 45.99, "elapsed_time": "1:18:26", "remaining_time": "1:32:08", "throughput": 6849.37, "total_tokens": 32238704} {"current_steps": 2880, "total_steps": 6252, "loss": 0.4887, "lr": 2.809494016002382e-05, "epoch": 1.382072358552829, "percentage": 46.07, "elapsed_time": "1:18:37", "remaining_time": "1:32:03", "throughput": 6846.91, "total_tokens": 32299312} {"current_steps": 2885, "total_steps": 6252, "loss": 0.4676, "lr": 2.8032601883984373e-05, "epoch": 1.384472310553789, "percentage": 46.15, "elapsed_time": "1:18:47", "remaining_time": "1:31:56", "throughput": 6844.41, "total_tokens": 32353968} {"current_steps": 2890, "total_steps": 6252, "loss": 0.5187, "lr": 2.7970244464636907e-05, "epoch": 1.386872262554749, "percentage": 46.23, "elapsed_time": "1:18:56", "remaining_time": "1:31:50", "throughput": 6841.52, "total_tokens": 32408248} {"current_steps": 2895, "total_steps": 6252, "loss": 0.5009, "lr": 2.7907868295612805e-05, "epoch": 1.3892722145557088, "percentage": 46.31, "elapsed_time": "1:19:06", "remaining_time": "1:31:44", "throughput": 6838.87, "total_tokens": 32461008} {"current_steps": 2900, "total_steps": 6252, "loss": 0.4448, "lr": 2.7845473770661816e-05, "epoch": 1.391672166556669, "percentage": 46.39, "elapsed_time": "1:19:16", "remaining_time": "1:31:38", "throughput": 6836.69, "total_tokens": 32519744} {"current_steps": 2905, "total_steps": 6252, "loss": 0.4562, "lr": 2.7783061283649547e-05, "epoch": 1.3940721185576288, "percentage": 46.47, "elapsed_time": "1:19:27", "remaining_time": "1:31:32", "throughput": 6832.85, "total_tokens": 32575104} {"current_steps": 2910, "total_steps": 6252, "loss": 0.4771, "lr": 2.7720631228555003e-05, "epoch": 1.396472070558589, "percentage": 46.55, "elapsed_time": "1:19:38", "remaining_time": "1:31:27", "throughput": 6829.98, "total_tokens": 32633880} {"current_steps": 2915, "total_steps": 6252, "loss": 0.5213, "lr": 2.7658183999468096e-05, "epoch": 1.3988720225595488, "percentage": 46.63, "elapsed_time": "1:19:47", "remaining_time": "1:31:20", "throughput": 6827.59, "total_tokens": 32687728} {"current_steps": 2920, "total_steps": 6252, "loss": 0.4879, "lr": 2.759571999058712e-05, "epoch": 1.4012719745605087, "percentage": 46.71, "elapsed_time": "1:19:58", "remaining_time": "1:31:15", "throughput": 6823.96, "total_tokens": 32744776} {"current_steps": 2925, "total_steps": 6252, "loss": 0.4801, "lr": 2.7533239596216326e-05, "epoch": 1.4036719265614688, "percentage": 46.79, "elapsed_time": "1:20:08", "remaining_time": "1:31:09", "throughput": 6821.15, "total_tokens": 32802640} {"current_steps": 2930, "total_steps": 6252, "loss": 0.4811, "lr": 2.747074321076336e-05, "epoch": 1.4060718785624289, "percentage": 46.87, "elapsed_time": "1:20:19", "remaining_time": "1:31:04", "throughput": 6817.65, "total_tokens": 32858848} {"current_steps": 2935, "total_steps": 6252, "loss": 0.4749, "lr": 2.7408231228736854e-05, "epoch": 1.4084718305633888, "percentage": 46.94, "elapsed_time": "1:20:29", "remaining_time": "1:30:58", "throughput": 6815.32, "total_tokens": 32915328} {"current_steps": 2940, "total_steps": 6252, "loss": 0.5214, "lr": 2.7345704044743857e-05, "epoch": 1.4108717825643486, "percentage": 47.02, "elapsed_time": "1:20:39", "remaining_time": "1:30:51", "throughput": 6812.79, "total_tokens": 32970256} {"current_steps": 2945, "total_steps": 6252, "loss": 0.5137, "lr": 2.7283162053487406e-05, "epoch": 1.4132717345653087, "percentage": 47.1, "elapsed_time": "1:20:49", "remaining_time": "1:30:45", "throughput": 6810.25, "total_tokens": 33024728} {"current_steps": 2950, "total_steps": 6252, "loss": 0.4864, "lr": 2.7220605649763997e-05, "epoch": 1.4156716865662686, "percentage": 47.18, "elapsed_time": "1:20:59", "remaining_time": "1:30:39", "throughput": 6807.86, "total_tokens": 33083776} {"current_steps": 2955, "total_steps": 6252, "loss": 0.4656, "lr": 2.71580352284611e-05, "epoch": 1.4180716385672287, "percentage": 47.26, "elapsed_time": "1:21:10", "remaining_time": "1:30:33", "throughput": 6805.28, "total_tokens": 33141792} {"current_steps": 2960, "total_steps": 6252, "loss": 0.4626, "lr": 2.7095451184554684e-05, "epoch": 1.4204715905681886, "percentage": 47.34, "elapsed_time": "1:21:19", "remaining_time": "1:30:27", "throughput": 6803.75, "total_tokens": 33200320} {"current_steps": 2965, "total_steps": 6252, "loss": 0.5166, "lr": 2.7032853913106702e-05, "epoch": 1.4228715425691485, "percentage": 47.42, "elapsed_time": "1:21:29", "remaining_time": "1:30:20", "throughput": 6802.21, "total_tokens": 33258192} {"current_steps": 2970, "total_steps": 6252, "loss": 0.4709, "lr": 2.697024380926261e-05, "epoch": 1.4252714945701086, "percentage": 47.5, "elapsed_time": "1:21:39", "remaining_time": "1:30:14", "throughput": 6799.51, "total_tokens": 33315416} {"current_steps": 2975, "total_steps": 6252, "loss": 0.4682, "lr": 2.6907621268248867e-05, "epoch": 1.4276714465710687, "percentage": 47.58, "elapsed_time": "1:21:50", "remaining_time": "1:30:09", "throughput": 6796.04, "total_tokens": 33374248} {"current_steps": 2980, "total_steps": 6252, "loss": 0.4795, "lr": 2.6844986685370438e-05, "epoch": 1.4300713985720286, "percentage": 47.66, "elapsed_time": "1:22:00", "remaining_time": "1:30:02", "throughput": 6793.79, "total_tokens": 33430576} {"current_steps": 2985, "total_steps": 6252, "loss": 0.5081, "lr": 2.6782340456008304e-05, "epoch": 1.4324713505729885, "percentage": 47.74, "elapsed_time": "1:22:10", "remaining_time": "1:29:56", "throughput": 6790.7, "total_tokens": 33481872} {"current_steps": 2990, "total_steps": 6252, "loss": 0.5238, "lr": 2.6719682975616972e-05, "epoch": 1.4348713025739486, "percentage": 47.82, "elapsed_time": "1:22:20", "remaining_time": "1:29:49", "throughput": 6788.2, "total_tokens": 33535608} {"current_steps": 2995, "total_steps": 6252, "loss": 0.4628, "lr": 2.6657014639721963e-05, "epoch": 1.4372712545749085, "percentage": 47.9, "elapsed_time": "1:22:30", "remaining_time": "1:29:43", "throughput": 6786.22, "total_tokens": 33595176} {"current_steps": 3000, "total_steps": 6252, "loss": 0.4726, "lr": 2.659433584391733e-05, "epoch": 1.4396712065758686, "percentage": 47.98, "elapsed_time": "1:22:40", "remaining_time": "1:29:37", "throughput": 6784.34, "total_tokens": 33655192} {"current_steps": 3005, "total_steps": 6252, "loss": 0.5086, "lr": 2.6531646983863135e-05, "epoch": 1.4420711585768284, "percentage": 48.06, "elapsed_time": "1:22:51", "remaining_time": "1:29:31", "throughput": 6781.17, "total_tokens": 33710344} {"current_steps": 3010, "total_steps": 6252, "loss": 0.4855, "lr": 2.6468948455283006e-05, "epoch": 1.4444711105777883, "percentage": 48.14, "elapsed_time": "1:23:00", "remaining_time": "1:29:24", "throughput": 6778.44, "total_tokens": 33762880} {"current_steps": 3015, "total_steps": 6252, "loss": 0.5121, "lr": 2.6406240653961562e-05, "epoch": 1.4468710625787484, "percentage": 48.22, "elapsed_time": "1:23:10", "remaining_time": "1:29:18", "throughput": 6775.39, "total_tokens": 33814912} {"current_steps": 3020, "total_steps": 6252, "loss": 0.4822, "lr": 2.6343523975741995e-05, "epoch": 1.4492710145797085, "percentage": 48.3, "elapsed_time": "1:23:20", "remaining_time": "1:29:11", "throughput": 6772.91, "total_tokens": 33869336} {"current_steps": 3025, "total_steps": 6252, "loss": 0.5094, "lr": 2.628079881652351e-05, "epoch": 1.4516709665806684, "percentage": 48.38, "elapsed_time": "1:23:30", "remaining_time": "1:29:04", "throughput": 6770.4, "total_tokens": 33921376} {"current_steps": 3030, "total_steps": 6252, "loss": 0.4494, "lr": 2.6218065572258847e-05, "epoch": 1.4540709185816283, "percentage": 48.46, "elapsed_time": "1:23:41", "remaining_time": "1:28:59", "throughput": 6767.31, "total_tokens": 33979216} {"current_steps": 3035, "total_steps": 6252, "loss": 0.5281, "lr": 2.6155324638951795e-05, "epoch": 1.4564708705825884, "percentage": 48.54, "elapsed_time": "1:23:52", "remaining_time": "1:28:53", "throughput": 6763.93, "total_tokens": 34036320} {"current_steps": 3040, "total_steps": 6252, "loss": 0.5001, "lr": 2.6092576412654668e-05, "epoch": 1.4588708225835483, "percentage": 48.62, "elapsed_time": "1:24:02", "remaining_time": "1:28:47", "throughput": 6761.18, "total_tokens": 34090128} {"current_steps": 3045, "total_steps": 6252, "loss": 0.4876, "lr": 2.602982128946583e-05, "epoch": 1.4612707745845084, "percentage": 48.7, "elapsed_time": "1:24:12", "remaining_time": "1:28:41", "throughput": 6759.1, "total_tokens": 34148400} {"current_steps": 3050, "total_steps": 6252, "loss": 0.4316, "lr": 2.596705966552718e-05, "epoch": 1.4636707265854683, "percentage": 48.78, "elapsed_time": "1:24:23", "remaining_time": "1:28:35", "throughput": 6755.49, "total_tokens": 34205656} {"current_steps": 3055, "total_steps": 6252, "loss": 0.5168, "lr": 2.5904291937021623e-05, "epoch": 1.4660706785864281, "percentage": 48.86, "elapsed_time": "1:24:33", "remaining_time": "1:28:29", "throughput": 6752.22, "total_tokens": 34256136} {"current_steps": 3060, "total_steps": 6252, "loss": 0.4756, "lr": 2.5841518500170647e-05, "epoch": 1.4684706305873882, "percentage": 48.94, "elapsed_time": "1:24:43", "remaining_time": "1:28:23", "throughput": 6749.15, "total_tokens": 34311976} {"current_steps": 3065, "total_steps": 6252, "loss": 0.4665, "lr": 2.5778739751231747e-05, "epoch": 1.4708705825883484, "percentage": 49.02, "elapsed_time": "1:24:54", "remaining_time": "1:28:17", "throughput": 6746.71, "total_tokens": 34370640} {"current_steps": 3070, "total_steps": 6252, "loss": 0.4652, "lr": 2.5715956086495947e-05, "epoch": 1.4732705345893082, "percentage": 49.1, "elapsed_time": "1:25:03", "remaining_time": "1:28:09", "throughput": 6744.6, "total_tokens": 34421432} {"current_steps": 3075, "total_steps": 6252, "loss": 0.4909, "lr": 2.565316790228532e-05, "epoch": 1.4756704865902681, "percentage": 49.18, "elapsed_time": "1:25:13", "remaining_time": "1:28:03", "throughput": 6742.51, "total_tokens": 34478304} {"current_steps": 3080, "total_steps": 6252, "loss": 0.4865, "lr": 2.5590375594950443e-05, "epoch": 1.4780704385912282, "percentage": 49.26, "elapsed_time": "1:25:23", "remaining_time": "1:27:56", "throughput": 6740.61, "total_tokens": 34532640} {"current_steps": 3085, "total_steps": 6252, "loss": 0.503, "lr": 2.5527579560867947e-05, "epoch": 1.480470390592188, "percentage": 49.34, "elapsed_time": "1:25:34", "remaining_time": "1:27:51", "throughput": 6737.59, "total_tokens": 34597280} {"current_steps": 3090, "total_steps": 6252, "loss": 0.4799, "lr": 2.546478019643797e-05, "epoch": 1.4828703425931482, "percentage": 49.42, "elapsed_time": "1:25:45", "remaining_time": "1:27:45", "throughput": 6734.44, "total_tokens": 34654488} {"current_steps": 3095, "total_steps": 6252, "loss": 0.4463, "lr": 2.540197789808168e-05, "epoch": 1.485270294594108, "percentage": 49.5, "elapsed_time": "1:25:58", "remaining_time": "1:27:41", "throughput": 6730.01, "total_tokens": 34716120} {"current_steps": 3100, "total_steps": 6252, "loss": 0.4597, "lr": 2.5339173062238774e-05, "epoch": 1.487670246595068, "percentage": 49.58, "elapsed_time": "1:26:10", "remaining_time": "1:27:37", "throughput": 6725.54, "total_tokens": 34777640} {"current_steps": 3105, "total_steps": 6252, "loss": 0.5084, "lr": 2.5276366085364937e-05, "epoch": 1.490070198596028, "percentage": 49.66, "elapsed_time": "1:26:21", "remaining_time": "1:27:31", "throughput": 6722.61, "total_tokens": 34831992} {"current_steps": 3110, "total_steps": 6252, "loss": 0.4786, "lr": 2.52135573639294e-05, "epoch": 1.4924701505969882, "percentage": 49.74, "elapsed_time": "1:26:31", "remaining_time": "1:27:24", "throughput": 6721.57, "total_tokens": 34894736} {"current_steps": 3115, "total_steps": 6252, "loss": 0.5175, "lr": 2.5150747294412398e-05, "epoch": 1.494870102597948, "percentage": 49.82, "elapsed_time": "1:26:41", "remaining_time": "1:27:18", "throughput": 6719.38, "total_tokens": 34951296} {"current_steps": 3120, "total_steps": 6252, "loss": 0.451, "lr": 2.508793627330267e-05, "epoch": 1.497270054598908, "percentage": 49.9, "elapsed_time": "1:26:51", "remaining_time": "1:27:11", "throughput": 6717.25, "total_tokens": 35006168} {"current_steps": 3125, "total_steps": 6252, "loss": 0.5077, "lr": 2.502512469709497e-05, "epoch": 1.499670006599868, "percentage": 49.98, "elapsed_time": "1:27:01", "remaining_time": "1:27:04", "throughput": 6714.71, "total_tokens": 35059176} {"current_steps": 3130, "total_steps": 6252, "loss": 0.4924, "lr": 2.4962312962287544e-05, "epoch": 1.5020699586008281, "percentage": 50.06, "elapsed_time": "1:27:10", "remaining_time": "1:26:57", "throughput": 6713.32, "total_tokens": 35114264} {"current_steps": 3135, "total_steps": 6252, "loss": 0.5004, "lr": 2.4899501465379644e-05, "epoch": 1.504469910601788, "percentage": 50.14, "elapsed_time": "1:27:20", "remaining_time": "1:26:50", "throughput": 6710.34, "total_tokens": 35168424} {"current_steps": 3140, "total_steps": 6252, "loss": 0.5145, "lr": 2.4836690602869044e-05, "epoch": 1.506869862602748, "percentage": 50.22, "elapsed_time": "1:27:30", "remaining_time": "1:26:43", "throughput": 6708.59, "total_tokens": 35224296} {"current_steps": 3145, "total_steps": 6252, "loss": 0.4889, "lr": 2.4773880771249477e-05, "epoch": 1.5092698146037078, "percentage": 50.3, "elapsed_time": "1:27:41", "remaining_time": "1:26:37", "throughput": 6705.65, "total_tokens": 35280088} {"current_steps": 3150, "total_steps": 6252, "loss": 0.4967, "lr": 2.4711072367008176e-05, "epoch": 1.511669766604668, "percentage": 50.38, "elapsed_time": "1:27:51", "remaining_time": "1:26:31", "throughput": 6704.13, "total_tokens": 35340720} {"current_steps": 3155, "total_steps": 6252, "loss": 0.4843, "lr": 2.4648265786623388e-05, "epoch": 1.514069718605628, "percentage": 50.46, "elapsed_time": "1:28:01", "remaining_time": "1:26:24", "throughput": 6701.49, "total_tokens": 35397240} {"current_steps": 3160, "total_steps": 6252, "loss": 0.5011, "lr": 2.4585461426561818e-05, "epoch": 1.5164696706065879, "percentage": 50.54, "elapsed_time": "1:28:13", "remaining_time": "1:26:19", "throughput": 6699.2, "total_tokens": 35460504} {"current_steps": 3165, "total_steps": 6252, "loss": 0.512, "lr": 2.452265968327618e-05, "epoch": 1.5188696226075478, "percentage": 50.62, "elapsed_time": "1:28:23", "remaining_time": "1:26:12", "throughput": 6697.31, "total_tokens": 35517032} {"current_steps": 3170, "total_steps": 6252, "loss": 0.4807, "lr": 2.4459860953202635e-05, "epoch": 1.5212695746085079, "percentage": 50.7, "elapsed_time": "1:28:31", "remaining_time": "1:26:04", "throughput": 6695.7, "total_tokens": 35567328} {"current_steps": 3175, "total_steps": 6252, "loss": 0.4578, "lr": 2.4397065632758374e-05, "epoch": 1.523669526609468, "percentage": 50.78, "elapsed_time": "1:28:41", "remaining_time": "1:25:57", "throughput": 6694.08, "total_tokens": 35622032} {"current_steps": 3180, "total_steps": 6252, "loss": 0.512, "lr": 2.4334274118339014e-05, "epoch": 1.5260694786104279, "percentage": 50.86, "elapsed_time": "1:28:51", "remaining_time": "1:25:50", "throughput": 6693.25, "total_tokens": 35684184} {"current_steps": 3185, "total_steps": 6252, "loss": 0.5011, "lr": 2.4271486806316173e-05, "epoch": 1.5284694306113877, "percentage": 50.94, "elapsed_time": "1:29:01", "remaining_time": "1:25:43", "throughput": 6691.63, "total_tokens": 35741544} {"current_steps": 3190, "total_steps": 6252, "loss": 0.4627, "lr": 2.420870409303495e-05, "epoch": 1.5308693826123476, "percentage": 51.02, "elapsed_time": "1:29:10", "remaining_time": "1:25:35", "throughput": 6690.36, "total_tokens": 35797096} {"current_steps": 3195, "total_steps": 6252, "loss": 0.4672, "lr": 2.4145926374811395e-05, "epoch": 1.5332693346133077, "percentage": 51.1, "elapsed_time": "1:29:20", "remaining_time": "1:25:28", "throughput": 6688.26, "total_tokens": 35849520} {"current_steps": 3200, "total_steps": 6252, "loss": 0.4645, "lr": 2.4083154047930014e-05, "epoch": 1.5356692866142678, "percentage": 51.18, "elapsed_time": "1:29:31", "remaining_time": "1:25:23", "throughput": 6685.07, "total_tokens": 35908672} {"current_steps": 3205, "total_steps": 6252, "loss": 0.4833, "lr": 2.4020387508641322e-05, "epoch": 1.5380692386152277, "percentage": 51.26, "elapsed_time": "1:29:41", "remaining_time": "1:25:16", "throughput": 6682.18, "total_tokens": 35963328} {"current_steps": 3210, "total_steps": 6252, "loss": 0.4763, "lr": 2.3957627153159277e-05, "epoch": 1.5404691906161876, "percentage": 51.34, "elapsed_time": "1:29:52", "remaining_time": "1:25:09", "throughput": 6680.47, "total_tokens": 36021192} {"current_steps": 3215, "total_steps": 6252, "loss": 0.4768, "lr": 2.3894873377658788e-05, "epoch": 1.5428691426171477, "percentage": 51.42, "elapsed_time": "1:30:02", "remaining_time": "1:25:03", "throughput": 6678.04, "total_tokens": 36078448} {"current_steps": 3220, "total_steps": 6252, "loss": 0.502, "lr": 2.383212657827324e-05, "epoch": 1.5452690946181078, "percentage": 51.5, "elapsed_time": "1:30:12", "remaining_time": "1:24:56", "throughput": 6675.81, "total_tokens": 36132656} {"current_steps": 3225, "total_steps": 6252, "loss": 0.4883, "lr": 2.3769387151092e-05, "epoch": 1.5476690466190677, "percentage": 51.58, "elapsed_time": "1:30:22", "remaining_time": "1:24:49", "throughput": 6674.13, "total_tokens": 36191712} {"current_steps": 3230, "total_steps": 6252, "loss": 0.5341, "lr": 2.370665549215787e-05, "epoch": 1.5500689986200276, "percentage": 51.66, "elapsed_time": "1:30:32", "remaining_time": "1:24:43", "throughput": 6671.41, "total_tokens": 36245160} {"current_steps": 3235, "total_steps": 6252, "loss": 0.4849, "lr": 2.3643931997464617e-05, "epoch": 1.5524689506209874, "percentage": 51.74, "elapsed_time": "1:30:43", "remaining_time": "1:24:36", "throughput": 6669.43, "total_tokens": 36303576} {"current_steps": 3240, "total_steps": 6252, "loss": 0.4583, "lr": 2.35812170629545e-05, "epoch": 1.5548689026219475, "percentage": 51.82, "elapsed_time": "1:30:53", "remaining_time": "1:24:29", "throughput": 6667.84, "total_tokens": 36360840} {"current_steps": 3245, "total_steps": 6252, "loss": 0.4604, "lr": 2.351851108451571e-05, "epoch": 1.5572688546229077, "percentage": 51.9, "elapsed_time": "1:31:03", "remaining_time": "1:24:22", "throughput": 6666.63, "total_tokens": 36422200} {"current_steps": 3250, "total_steps": 6252, "loss": 0.5048, "lr": 2.34558144579799e-05, "epoch": 1.5596688066238675, "percentage": 51.98, "elapsed_time": "1:31:13", "remaining_time": "1:24:15", "throughput": 6664.74, "total_tokens": 36476632} {"current_steps": 3255, "total_steps": 6252, "loss": 0.5113, "lr": 2.339312757911973e-05, "epoch": 1.5620687586248274, "percentage": 52.06, "elapsed_time": "1:31:22", "remaining_time": "1:24:07", "throughput": 6663.32, "total_tokens": 36529792} {"current_steps": 3260, "total_steps": 6252, "loss": 0.5005, "lr": 2.3330450843646296e-05, "epoch": 1.5644687106257875, "percentage": 52.14, "elapsed_time": "1:31:32", "remaining_time": "1:24:00", "throughput": 6661.09, "total_tokens": 36586016} {"current_steps": 3265, "total_steps": 6252, "loss": 0.4804, "lr": 2.3267784647206658e-05, "epoch": 1.5668686626267476, "percentage": 52.22, "elapsed_time": "1:31:42", "remaining_time": "1:23:53", "throughput": 6659.35, "total_tokens": 36641112} {"current_steps": 3270, "total_steps": 6252, "loss": 0.4928, "lr": 2.3205129385381355e-05, "epoch": 1.5692686146277075, "percentage": 52.3, "elapsed_time": "1:31:52", "remaining_time": "1:23:46", "throughput": 6657.08, "total_tokens": 36697088} {"current_steps": 3275, "total_steps": 6252, "loss": 0.4872, "lr": 2.3142485453681925e-05, "epoch": 1.5716685666286674, "percentage": 52.38, "elapsed_time": "1:32:03", "remaining_time": "1:23:41", "throughput": 6654.28, "total_tokens": 36755920} {"current_steps": 3280, "total_steps": 6252, "loss": 0.5391, "lr": 2.307985324754835e-05, "epoch": 1.5740685186296273, "percentage": 52.46, "elapsed_time": "1:32:13", "remaining_time": "1:23:34", "throughput": 6651.93, "total_tokens": 36811304} {"current_steps": 3285, "total_steps": 6252, "loss": 0.4955, "lr": 2.3017233162346608e-05, "epoch": 1.5764684706305874, "percentage": 52.54, "elapsed_time": "1:32:23", "remaining_time": "1:23:26", "throughput": 6650.89, "total_tokens": 36868680} {"current_steps": 3290, "total_steps": 6252, "loss": 0.4775, "lr": 2.295462559336618e-05, "epoch": 1.5788684226315475, "percentage": 52.62, "elapsed_time": "1:32:33", "remaining_time": "1:23:19", "throughput": 6649.49, "total_tokens": 36925400} {"current_steps": 3295, "total_steps": 6252, "loss": 0.457, "lr": 2.2892030935817517e-05, "epoch": 1.5812683746325074, "percentage": 52.7, "elapsed_time": "1:32:43", "remaining_time": "1:23:12", "throughput": 6647.45, "total_tokens": 36984032} {"current_steps": 3300, "total_steps": 6252, "loss": 0.5231, "lr": 2.2829449584829558e-05, "epoch": 1.5836683266334672, "percentage": 52.78, "elapsed_time": "1:32:53", "remaining_time": "1:23:05", "throughput": 6645.45, "total_tokens": 37038928} {"current_steps": 3305, "total_steps": 6252, "loss": 0.5044, "lr": 2.2766881935447275e-05, "epoch": 1.5860682786344273, "percentage": 52.86, "elapsed_time": "1:33:03", "remaining_time": "1:22:58", "throughput": 6643.27, "total_tokens": 37092208} {"current_steps": 3310, "total_steps": 6252, "loss": 0.4753, "lr": 2.2704328382629138e-05, "epoch": 1.5884682306353874, "percentage": 52.94, "elapsed_time": "1:33:12", "remaining_time": "1:22:50", "throughput": 6642.29, "total_tokens": 37147680} {"current_steps": 3315, "total_steps": 6252, "loss": 0.4796, "lr": 2.264178932124462e-05, "epoch": 1.5908681826363473, "percentage": 53.02, "elapsed_time": "1:33:21", "remaining_time": "1:22:43", "throughput": 6641.28, "total_tokens": 37203656} {"current_steps": 3320, "total_steps": 6252, "loss": 0.4852, "lr": 2.257926514607171e-05, "epoch": 1.5932681346373072, "percentage": 53.1, "elapsed_time": "1:33:32", "remaining_time": "1:22:36", "throughput": 6639.88, "total_tokens": 37263520} {"current_steps": 3325, "total_steps": 6252, "loss": 0.5121, "lr": 2.2516756251794463e-05, "epoch": 1.595668086638267, "percentage": 53.18, "elapsed_time": "1:33:41", "remaining_time": "1:22:28", "throughput": 6638.23, "total_tokens": 37318192} {"current_steps": 3330, "total_steps": 6252, "loss": 0.5128, "lr": 2.245426303300044e-05, "epoch": 1.5980680386392272, "percentage": 53.26, "elapsed_time": "1:33:51", "remaining_time": "1:22:21", "throughput": 6636.34, "total_tokens": 37374224} {"current_steps": 3335, "total_steps": 6252, "loss": 0.4835, "lr": 2.2391785884178256e-05, "epoch": 1.6004679906401873, "percentage": 53.34, "elapsed_time": "1:34:02", "remaining_time": "1:22:15", "throughput": 6634.81, "total_tokens": 37435240} {"current_steps": 3340, "total_steps": 6252, "loss": 0.4575, "lr": 2.2329325199715114e-05, "epoch": 1.6028679426411472, "percentage": 53.42, "elapsed_time": "1:34:12", "remaining_time": "1:22:07", "throughput": 6633.09, "total_tokens": 37492120} {"current_steps": 3345, "total_steps": 6252, "loss": 0.4922, "lr": 2.226688137389425e-05, "epoch": 1.605267894642107, "percentage": 53.5, "elapsed_time": "1:34:22", "remaining_time": "1:22:00", "throughput": 6631.22, "total_tokens": 37548408} {"current_steps": 3350, "total_steps": 6252, "loss": 0.4807, "lr": 2.220445480089248e-05, "epoch": 1.6076678466430672, "percentage": 53.58, "elapsed_time": "1:34:34", "remaining_time": "1:21:55", "throughput": 6628.16, "total_tokens": 37610280} {"current_steps": 3355, "total_steps": 6252, "loss": 0.5322, "lr": 2.214204587477774e-05, "epoch": 1.6100677986440273, "percentage": 53.66, "elapsed_time": "1:34:44", "remaining_time": "1:21:48", "throughput": 6626.57, "total_tokens": 37668512} {"current_steps": 3360, "total_steps": 6252, "loss": 0.4843, "lr": 2.207965498950655e-05, "epoch": 1.6124677506449872, "percentage": 53.74, "elapsed_time": "1:34:54", "remaining_time": "1:21:41", "throughput": 6625.52, "total_tokens": 37727112} {"current_steps": 3365, "total_steps": 6252, "loss": 0.4732, "lr": 2.2017282538921556e-05, "epoch": 1.614867702645947, "percentage": 53.82, "elapsed_time": "1:35:03", "remaining_time": "1:21:33", "throughput": 6624.04, "total_tokens": 37780192} {"current_steps": 3370, "total_steps": 6252, "loss": 0.5115, "lr": 2.1954928916749006e-05, "epoch": 1.617267654646907, "percentage": 53.9, "elapsed_time": "1:35:13", "remaining_time": "1:21:26", "throughput": 6622.47, "total_tokens": 37839376} {"current_steps": 3375, "total_steps": 6252, "loss": 0.5177, "lr": 2.1892594516596343e-05, "epoch": 1.619667606647867, "percentage": 53.98, "elapsed_time": "1:35:23", "remaining_time": "1:21:18", "throughput": 6620.92, "total_tokens": 37894296} {"current_steps": 3380, "total_steps": 6252, "loss": 0.4848, "lr": 2.183027973194964e-05, "epoch": 1.6220675586488271, "percentage": 54.06, "elapsed_time": "1:35:33", "remaining_time": "1:21:11", "throughput": 6619.47, "total_tokens": 37951552} {"current_steps": 3385, "total_steps": 6252, "loss": 0.4927, "lr": 2.176798495617114e-05, "epoch": 1.624467510649787, "percentage": 54.14, "elapsed_time": "1:35:42", "remaining_time": "1:21:04", "throughput": 6618.91, "total_tokens": 38011968} {"current_steps": 3390, "total_steps": 6252, "loss": 0.4888, "lr": 2.1705710582496815e-05, "epoch": 1.6268674626507469, "percentage": 54.22, "elapsed_time": "1:35:52", "remaining_time": "1:20:56", "throughput": 6617.32, "total_tokens": 38067280} {"current_steps": 3395, "total_steps": 6252, "loss": 0.5178, "lr": 2.1643457004033807e-05, "epoch": 1.629267414651707, "percentage": 54.3, "elapsed_time": "1:36:03", "remaining_time": "1:20:49", "throughput": 6615.16, "total_tokens": 38124912} {"current_steps": 3400, "total_steps": 6252, "loss": 0.5112, "lr": 2.1581224613758005e-05, "epoch": 1.631667366652667, "percentage": 54.38, "elapsed_time": "1:36:12", "remaining_time": "1:20:42", "throughput": 6613.71, "total_tokens": 38178808} {"current_steps": 3405, "total_steps": 6252, "loss": 0.5106, "lr": 2.1519013804511562e-05, "epoch": 1.634067318653627, "percentage": 54.46, "elapsed_time": "1:36:22", "remaining_time": "1:20:34", "throughput": 6612.1, "total_tokens": 38233976} {"current_steps": 3410, "total_steps": 6252, "loss": 0.501, "lr": 2.145682496900039e-05, "epoch": 1.6364672706545869, "percentage": 54.54, "elapsed_time": "1:36:32", "remaining_time": "1:20:27", "throughput": 6610.81, "total_tokens": 38291736} {"current_steps": 3415, "total_steps": 6252, "loss": 0.4836, "lr": 2.1394658499791684e-05, "epoch": 1.6388672226555467, "percentage": 54.62, "elapsed_time": "1:36:40", "remaining_time": "1:20:18", "throughput": 6610.86, "total_tokens": 38347056} {"current_steps": 3420, "total_steps": 6252, "loss": 0.5138, "lr": 2.1332514789311448e-05, "epoch": 1.6412671746565068, "percentage": 54.7, "elapsed_time": "1:36:48", "remaining_time": "1:20:09", "throughput": 6611.2, "total_tokens": 38399184} {"current_steps": 3425, "total_steps": 6252, "loss": 0.4522, "lr": 2.1270394229842044e-05, "epoch": 1.643667126657467, "percentage": 54.78, "elapsed_time": "1:36:56", "remaining_time": "1:20:00", "throughput": 6612.19, "total_tokens": 38456896} {"current_steps": 3430, "total_steps": 6252, "loss": 0.4847, "lr": 2.1208297213519686e-05, "epoch": 1.6460670786584268, "percentage": 54.86, "elapsed_time": "1:37:03", "remaining_time": "1:19:51", "throughput": 6612.95, "total_tokens": 38512168} {"current_steps": 3435, "total_steps": 6252, "loss": 0.4733, "lr": 2.1146224132331944e-05, "epoch": 1.6484670306593867, "percentage": 54.94, "elapsed_time": "1:37:11", "remaining_time": "1:19:42", "throughput": 6614.11, "total_tokens": 38573240} {"current_steps": 3440, "total_steps": 6252, "loss": 0.5236, "lr": 2.1084175378115344e-05, "epoch": 1.6508669826603468, "percentage": 55.02, "elapsed_time": "1:37:19", "remaining_time": "1:19:33", "throughput": 6614.7, "total_tokens": 38624080} {"current_steps": 3445, "total_steps": 6252, "loss": 0.5226, "lr": 2.1022151342552815e-05, "epoch": 1.653266934661307, "percentage": 55.1, "elapsed_time": "1:37:26", "remaining_time": "1:19:24", "throughput": 6615.47, "total_tokens": 38679488} {"current_steps": 3450, "total_steps": 6252, "loss": 0.4533, "lr": 2.0960152417171243e-05, "epoch": 1.6556668866622668, "percentage": 55.18, "elapsed_time": "1:37:35", "remaining_time": "1:19:15", "throughput": 6615.81, "total_tokens": 38736136} {"current_steps": 3455, "total_steps": 6252, "loss": 0.483, "lr": 2.089817899333904e-05, "epoch": 1.6580668386632267, "percentage": 55.26, "elapsed_time": "1:37:42", "remaining_time": "1:19:06", "throughput": 6616.25, "total_tokens": 38788592} {"current_steps": 3460, "total_steps": 6252, "loss": 0.4556, "lr": 2.083623146226362e-05, "epoch": 1.6604667906641866, "percentage": 55.34, "elapsed_time": "1:37:50", "remaining_time": "1:18:57", "throughput": 6616.98, "total_tokens": 38846528} {"current_steps": 3465, "total_steps": 6252, "loss": 0.545, "lr": 2.0774310214988942e-05, "epoch": 1.6628667426651467, "percentage": 55.42, "elapsed_time": "1:37:59", "remaining_time": "1:18:48", "throughput": 6616.16, "total_tokens": 38896768} {"current_steps": 3470, "total_steps": 6252, "loss": 0.4741, "lr": 2.071241564239305e-05, "epoch": 1.6652666946661068, "percentage": 55.5, "elapsed_time": "1:38:08", "remaining_time": "1:18:41", "throughput": 6614.76, "total_tokens": 38952672} {"current_steps": 3475, "total_steps": 6252, "loss": 0.4831, "lr": 2.0650548135185618e-05, "epoch": 1.6676666466670667, "percentage": 55.58, "elapsed_time": "1:38:18", "remaining_time": "1:18:33", "throughput": 6612.72, "total_tokens": 39007376} {"current_steps": 3480, "total_steps": 6252, "loss": 0.5174, "lr": 2.0588708083905468e-05, "epoch": 1.6700665986680265, "percentage": 55.66, "elapsed_time": "1:38:29", "remaining_time": "1:18:26", "throughput": 6610.98, "total_tokens": 39064568} {"current_steps": 3485, "total_steps": 6252, "loss": 0.5055, "lr": 2.0526895878918077e-05, "epoch": 1.6724665506689866, "percentage": 55.74, "elapsed_time": "1:38:38", "remaining_time": "1:18:19", "throughput": 6609.43, "total_tokens": 39117320} {"current_steps": 3490, "total_steps": 6252, "loss": 0.5316, "lr": 2.0465111910413192e-05, "epoch": 1.6748665026699467, "percentage": 55.82, "elapsed_time": "1:38:47", "remaining_time": "1:18:10", "throughput": 6608.9, "total_tokens": 39171840} {"current_steps": 3495, "total_steps": 6252, "loss": 0.4517, "lr": 2.040335656840228e-05, "epoch": 1.6772664546709066, "percentage": 55.9, "elapsed_time": "1:38:54", "remaining_time": "1:18:01", "throughput": 6609.39, "total_tokens": 39226624} {"current_steps": 3500, "total_steps": 6252, "loss": 0.5067, "lr": 2.03416302427161e-05, "epoch": 1.6796664066718665, "percentage": 55.98, "elapsed_time": "1:39:02", "remaining_time": "1:17:52", "throughput": 6610.26, "total_tokens": 39284168} {"current_steps": 3505, "total_steps": 6252, "loss": 0.5064, "lr": 2.027993332300227e-05, "epoch": 1.6820663586728264, "percentage": 56.06, "elapsed_time": "1:39:11", "remaining_time": "1:17:44", "throughput": 6610.6, "total_tokens": 39340120} {"current_steps": 3510, "total_steps": 6252, "loss": 0.4523, "lr": 2.021826619872278e-05, "epoch": 1.6844663106737865, "percentage": 56.14, "elapsed_time": "1:39:19", "remaining_time": "1:17:35", "throughput": 6611.41, "total_tokens": 39399136} {"current_steps": 3515, "total_steps": 6252, "loss": 0.4804, "lr": 2.0156629259151515e-05, "epoch": 1.6868662626747466, "percentage": 56.22, "elapsed_time": "1:39:27", "remaining_time": "1:17:26", "throughput": 6612.2, "total_tokens": 39456808} {"current_steps": 3520, "total_steps": 6252, "loss": 0.4838, "lr": 2.0095022893371826e-05, "epoch": 1.6892662146757065, "percentage": 56.3, "elapsed_time": "1:39:35", "remaining_time": "1:17:18", "throughput": 6612.57, "total_tokens": 39516000} {"current_steps": 3525, "total_steps": 6252, "loss": 0.4669, "lr": 2.0033447490274083e-05, "epoch": 1.6916661666766664, "percentage": 56.38, "elapsed_time": "1:39:43", "remaining_time": "1:17:08", "throughput": 6612.98, "total_tokens": 39569280} {"current_steps": 3530, "total_steps": 6252, "loss": 0.5031, "lr": 1.99719034385532e-05, "epoch": 1.6940661186776265, "percentage": 56.46, "elapsed_time": "1:39:51", "remaining_time": "1:17:00", "throughput": 6613.35, "total_tokens": 39625464} {"current_steps": 3535, "total_steps": 6252, "loss": 0.4991, "lr": 1.9910391126706158e-05, "epoch": 1.6964660706785866, "percentage": 56.54, "elapsed_time": "1:39:59", "remaining_time": "1:16:51", "throughput": 6613.12, "total_tokens": 39676928} {"current_steps": 3540, "total_steps": 6252, "loss": 0.4548, "lr": 1.9848910943029624e-05, "epoch": 1.6988660226795465, "percentage": 56.62, "elapsed_time": "1:40:08", "remaining_time": "1:16:43", "throughput": 6613.02, "total_tokens": 39734168} {"current_steps": 3545, "total_steps": 6252, "loss": 0.4886, "lr": 1.978746327561741e-05, "epoch": 1.7012659746805063, "percentage": 56.7, "elapsed_time": "1:40:16", "remaining_time": "1:16:34", "throughput": 6613.9, "total_tokens": 39795520} {"current_steps": 3550, "total_steps": 6252, "loss": 0.4737, "lr": 1.972604851235811e-05, "epoch": 1.7036659266814662, "percentage": 56.78, "elapsed_time": "1:40:25", "remaining_time": "1:16:26", "throughput": 6613.77, "total_tokens": 39851264} {"current_steps": 3555, "total_steps": 6252, "loss": 0.5013, "lr": 1.9664667040932577e-05, "epoch": 1.7060658786824263, "percentage": 56.86, "elapsed_time": "1:40:32", "remaining_time": "1:16:16", "throughput": 6614.33, "total_tokens": 39904120} {"current_steps": 3560, "total_steps": 6252, "loss": 0.4541, "lr": 1.9603319248811542e-05, "epoch": 1.7084658306833864, "percentage": 56.94, "elapsed_time": "1:40:40", "remaining_time": "1:16:07", "throughput": 6614.69, "total_tokens": 39957104} {"current_steps": 3565, "total_steps": 6252, "loss": 0.5057, "lr": 1.9542005523253103e-05, "epoch": 1.7108657826843463, "percentage": 57.02, "elapsed_time": "1:40:48", "remaining_time": "1:15:58", "throughput": 6615.46, "total_tokens": 40014640} {"current_steps": 3570, "total_steps": 6252, "loss": 0.5071, "lr": 1.948072625130032e-05, "epoch": 1.7132657346853062, "percentage": 57.1, "elapsed_time": "1:40:56", "remaining_time": "1:15:49", "throughput": 6616.46, "total_tokens": 40071928} {"current_steps": 3575, "total_steps": 6252, "loss": 0.5099, "lr": 1.9419481819778785e-05, "epoch": 1.7156656866862663, "percentage": 57.18, "elapsed_time": "1:41:03", "remaining_time": "1:15:40", "throughput": 6617.46, "total_tokens": 40125856} {"current_steps": 3580, "total_steps": 6252, "loss": 0.4823, "lr": 1.9358272615294153e-05, "epoch": 1.7180656386872264, "percentage": 57.26, "elapsed_time": "1:41:11", "remaining_time": "1:15:31", "throughput": 6617.84, "total_tokens": 40181760} {"current_steps": 3585, "total_steps": 6252, "loss": 0.5261, "lr": 1.9297099024229675e-05, "epoch": 1.7204655906881863, "percentage": 57.34, "elapsed_time": "1:41:19", "remaining_time": "1:15:22", "throughput": 6618.54, "total_tokens": 40236472} {"current_steps": 3590, "total_steps": 6252, "loss": 0.4674, "lr": 1.923596143274385e-05, "epoch": 1.7228655426891462, "percentage": 57.42, "elapsed_time": "1:41:27", "remaining_time": "1:15:13", "throughput": 6619.22, "total_tokens": 40295104} {"current_steps": 3595, "total_steps": 6252, "loss": 0.5175, "lr": 1.9174860226767876e-05, "epoch": 1.725265494690106, "percentage": 57.5, "elapsed_time": "1:41:35", "remaining_time": "1:15:04", "throughput": 6619.37, "total_tokens": 40345800} {"current_steps": 3600, "total_steps": 6252, "loss": 0.5171, "lr": 1.91137957920033e-05, "epoch": 1.7276654466910661, "percentage": 57.58, "elapsed_time": "1:41:43", "remaining_time": "1:14:56", "throughput": 6619.88, "total_tokens": 40402256} {"current_steps": 3605, "total_steps": 6252, "loss": 0.4883, "lr": 1.905276851391954e-05, "epoch": 1.7300653986920262, "percentage": 57.66, "elapsed_time": "1:41:51", "remaining_time": "1:14:47", "throughput": 6619.9, "total_tokens": 40458888} {"current_steps": 3610, "total_steps": 6252, "loss": 0.4852, "lr": 1.899177877775146e-05, "epoch": 1.7324653506929861, "percentage": 57.74, "elapsed_time": "1:41:59", "remaining_time": "1:14:38", "throughput": 6620.31, "total_tokens": 40516112} {"current_steps": 3615, "total_steps": 6252, "loss": 0.5067, "lr": 1.8930826968496943e-05, "epoch": 1.734865302693946, "percentage": 57.82, "elapsed_time": "1:42:08", "remaining_time": "1:14:30", "throughput": 6620.74, "total_tokens": 40572824} {"current_steps": 3620, "total_steps": 6252, "loss": 0.4881, "lr": 1.8869913470914448e-05, "epoch": 1.7372652546949061, "percentage": 57.9, "elapsed_time": "1:42:16", "remaining_time": "1:14:21", "throughput": 6621.2, "total_tokens": 40631656} {"current_steps": 3625, "total_steps": 6252, "loss": 0.5206, "lr": 1.880903866952062e-05, "epoch": 1.7396652066958662, "percentage": 57.98, "elapsed_time": "1:42:24", "remaining_time": "1:14:13", "throughput": 6621.31, "total_tokens": 40687064} {"current_steps": 3630, "total_steps": 6252, "loss": 0.4979, "lr": 1.8748202948587813e-05, "epoch": 1.742065158696826, "percentage": 58.06, "elapsed_time": "1:42:33", "remaining_time": "1:14:04", "throughput": 6621.63, "total_tokens": 40743400} {"current_steps": 3635, "total_steps": 6252, "loss": 0.4632, "lr": 1.8687406692141673e-05, "epoch": 1.744465110697786, "percentage": 58.14, "elapsed_time": "1:42:41", "remaining_time": "1:13:56", "throughput": 6621.84, "total_tokens": 40802376} {"current_steps": 3640, "total_steps": 6252, "loss": 0.4851, "lr": 1.8626650283958762e-05, "epoch": 1.7468650626987459, "percentage": 58.22, "elapsed_time": "1:42:49", "remaining_time": "1:13:47", "throughput": 6621.94, "total_tokens": 40854616} {"current_steps": 3645, "total_steps": 6252, "loss": 0.4573, "lr": 1.8565934107564068e-05, "epoch": 1.749265014699706, "percentage": 58.3, "elapsed_time": "1:42:58", "remaining_time": "1:13:38", "throughput": 6621.9, "total_tokens": 40911032} {"current_steps": 3650, "total_steps": 6252, "loss": 0.4862, "lr": 1.8505258546228623e-05, "epoch": 1.751664966700666, "percentage": 58.38, "elapsed_time": "1:43:06", "remaining_time": "1:13:30", "throughput": 6622.56, "total_tokens": 40970312} {"current_steps": 3655, "total_steps": 6252, "loss": 0.4606, "lr": 1.8444623982967098e-05, "epoch": 1.754064918701626, "percentage": 58.46, "elapsed_time": "1:43:14", "remaining_time": "1:13:21", "throughput": 6622.91, "total_tokens": 41028576} {"current_steps": 3660, "total_steps": 6252, "loss": 0.4504, "lr": 1.8384030800535332e-05, "epoch": 1.7564648707025858, "percentage": 58.54, "elapsed_time": "1:43:23", "remaining_time": "1:13:13", "throughput": 6623.29, "total_tokens": 41088352} {"current_steps": 3665, "total_steps": 6252, "loss": 0.5408, "lr": 1.832347938142796e-05, "epoch": 1.758864822703546, "percentage": 58.62, "elapsed_time": "1:43:31", "remaining_time": "1:13:04", "throughput": 6624.03, "total_tokens": 41144096} {"current_steps": 3670, "total_steps": 6252, "loss": 0.4798, "lr": 1.8262970107875994e-05, "epoch": 1.761264774704506, "percentage": 58.7, "elapsed_time": "1:43:38", "remaining_time": "1:12:55", "throughput": 6624.86, "total_tokens": 41199488} {"current_steps": 3675, "total_steps": 6252, "loss": 0.5226, "lr": 1.8202503361844393e-05, "epoch": 1.763664726705466, "percentage": 58.78, "elapsed_time": "1:43:46", "remaining_time": "1:12:46", "throughput": 6625.32, "total_tokens": 41254392} {"current_steps": 3680, "total_steps": 6252, "loss": 0.5196, "lr": 1.8142079525029672e-05, "epoch": 1.7660646787064258, "percentage": 58.86, "elapsed_time": "1:43:54", "remaining_time": "1:12:37", "throughput": 6625.84, "total_tokens": 41310952} {"current_steps": 3685, "total_steps": 6252, "loss": 0.4813, "lr": 1.808169897885745e-05, "epoch": 1.7684646307073857, "percentage": 58.94, "elapsed_time": "1:44:02", "remaining_time": "1:12:28", "throughput": 6625.86, "total_tokens": 41363784} {"current_steps": 3690, "total_steps": 6252, "loss": 0.4864, "lr": 1.802136210448012e-05, "epoch": 1.7708645827083458, "percentage": 59.02, "elapsed_time": "1:44:10", "remaining_time": "1:12:19", "throughput": 6626.38, "total_tokens": 41418736} {"current_steps": 3695, "total_steps": 6252, "loss": 0.451, "lr": 1.796106928277437e-05, "epoch": 1.773264534709306, "percentage": 59.1, "elapsed_time": "1:44:19", "remaining_time": "1:12:11", "throughput": 6626.92, "total_tokens": 41480096} {"current_steps": 3700, "total_steps": 6252, "loss": 0.4405, "lr": 1.7900820894338786e-05, "epoch": 1.7756644867102658, "percentage": 59.18, "elapsed_time": "1:44:27", "remaining_time": "1:12:02", "throughput": 6627.58, "total_tokens": 41535640} {"current_steps": 3705, "total_steps": 6252, "loss": 0.51, "lr": 1.7840617319491527e-05, "epoch": 1.7780644387112257, "percentage": 59.26, "elapsed_time": "1:44:35", "remaining_time": "1:11:53", "throughput": 6627.85, "total_tokens": 41592104} {"current_steps": 3710, "total_steps": 6252, "loss": 0.4488, "lr": 1.7780458938267807e-05, "epoch": 1.7804643907121858, "percentage": 59.34, "elapsed_time": "1:44:43", "remaining_time": "1:11:45", "throughput": 6628.26, "total_tokens": 41649776} {"current_steps": 3715, "total_steps": 6252, "loss": 0.4581, "lr": 1.772034613041758e-05, "epoch": 1.7828643427131459, "percentage": 59.42, "elapsed_time": "1:44:51", "remaining_time": "1:11:36", "throughput": 6628.78, "total_tokens": 41707280} {"current_steps": 3720, "total_steps": 6252, "loss": 0.4598, "lr": 1.7660279275403124e-05, "epoch": 1.7852642947141057, "percentage": 59.5, "elapsed_time": "1:45:00", "remaining_time": "1:11:28", "throughput": 6629.35, "total_tokens": 41765768} {"current_steps": 3725, "total_steps": 6252, "loss": 0.4783, "lr": 1.7600258752396626e-05, "epoch": 1.7876642467150656, "percentage": 59.58, "elapsed_time": "1:45:08", "remaining_time": "1:11:19", "throughput": 6629.44, "total_tokens": 41819576} {"current_steps": 3730, "total_steps": 6252, "loss": 0.4821, "lr": 1.754028494027782e-05, "epoch": 1.7900641987160257, "percentage": 59.66, "elapsed_time": "1:45:16", "remaining_time": "1:11:10", "throughput": 6629.91, "total_tokens": 41876528} {"current_steps": 3735, "total_steps": 6252, "loss": 0.4984, "lr": 1.748035821763154e-05, "epoch": 1.7924641507169856, "percentage": 59.74, "elapsed_time": "1:45:24", "remaining_time": "1:11:01", "throughput": 6630.42, "total_tokens": 41933488} {"current_steps": 3740, "total_steps": 6252, "loss": 0.4707, "lr": 1.7420478962745424e-05, "epoch": 1.7948641027179457, "percentage": 59.82, "elapsed_time": "1:45:32", "remaining_time": "1:10:53", "throughput": 6630.95, "total_tokens": 41989264} {"current_steps": 3745, "total_steps": 6252, "loss": 0.5113, "lr": 1.736064755360742e-05, "epoch": 1.7972640547189056, "percentage": 59.9, "elapsed_time": "1:45:40", "remaining_time": "1:10:44", "throughput": 6631.23, "total_tokens": 42045264} {"current_steps": 3750, "total_steps": 6252, "loss": 0.4807, "lr": 1.7300864367903462e-05, "epoch": 1.7996640067198655, "percentage": 59.98, "elapsed_time": "1:45:48", "remaining_time": "1:10:35", "throughput": 6632.12, "total_tokens": 42103712} {"current_steps": 3755, "total_steps": 6252, "loss": 0.5129, "lr": 1.7241129783015108e-05, "epoch": 1.8020639587208256, "percentage": 60.06, "elapsed_time": "1:45:56", "remaining_time": "1:10:26", "throughput": 6632.34, "total_tokens": 42156568} {"current_steps": 3760, "total_steps": 6252, "loss": 0.4709, "lr": 1.7181444176017077e-05, "epoch": 1.8044639107217857, "percentage": 60.14, "elapsed_time": "1:46:04", "remaining_time": "1:10:18", "throughput": 6632.82, "total_tokens": 42214056} {"current_steps": 3765, "total_steps": 6252, "loss": 0.4609, "lr": 1.7121807923674926e-05, "epoch": 1.8068638627227456, "percentage": 60.22, "elapsed_time": "1:46:12", "remaining_time": "1:10:09", "throughput": 6633.07, "total_tokens": 42270872} {"current_steps": 3770, "total_steps": 6252, "loss": 0.5136, "lr": 1.7062221402442678e-05, "epoch": 1.8092638147237055, "percentage": 60.3, "elapsed_time": "1:46:20", "remaining_time": "1:10:00", "throughput": 6633.36, "total_tokens": 42324392} {"current_steps": 3775, "total_steps": 6252, "loss": 0.465, "lr": 1.7002684988460417e-05, "epoch": 1.8116637667246656, "percentage": 60.38, "elapsed_time": "1:46:28", "remaining_time": "1:09:52", "throughput": 6633.7, "total_tokens": 42381736} {"current_steps": 3780, "total_steps": 6252, "loss": 0.4924, "lr": 1.694319905755193e-05, "epoch": 1.8140637187256254, "percentage": 60.46, "elapsed_time": "1:46:39", "remaining_time": "1:09:45", "throughput": 6631.82, "total_tokens": 42442312} {"current_steps": 3785, "total_steps": 6252, "loss": 0.468, "lr": 1.6883763985222305e-05, "epoch": 1.8164636707265855, "percentage": 60.54, "elapsed_time": "1:46:49", "remaining_time": "1:09:37", "throughput": 6630.48, "total_tokens": 42496896} {"current_steps": 3790, "total_steps": 6252, "loss": 0.5271, "lr": 1.6824380146655633e-05, "epoch": 1.8188636227275454, "percentage": 60.62, "elapsed_time": "1:46:59", "remaining_time": "1:09:29", "throughput": 6629.3, "total_tokens": 42554600} {"current_steps": 3795, "total_steps": 6252, "loss": 0.5052, "lr": 1.6765047916712545e-05, "epoch": 1.8212635747285053, "percentage": 60.7, "elapsed_time": "1:47:09", "remaining_time": "1:09:22", "throughput": 6627.76, "total_tokens": 42611168} {"current_steps": 3800, "total_steps": 6252, "loss": 0.4572, "lr": 1.6705767669927914e-05, "epoch": 1.8236635267294654, "percentage": 60.78, "elapsed_time": "1:47:20", "remaining_time": "1:09:15", "throughput": 6625.48, "total_tokens": 42668344} {"current_steps": 3805, "total_steps": 6252, "loss": 0.4514, "lr": 1.6646539780508478e-05, "epoch": 1.8260634787304255, "percentage": 60.86, "elapsed_time": "1:47:30", "remaining_time": "1:09:08", "throughput": 6623.8, "total_tokens": 42725880} {"current_steps": 3810, "total_steps": 6252, "loss": 0.4553, "lr": 1.658736462233045e-05, "epoch": 1.8284634307313854, "percentage": 60.94, "elapsed_time": "1:47:40", "remaining_time": "1:09:00", "throughput": 6622.56, "total_tokens": 42785824} {"current_steps": 3815, "total_steps": 6252, "loss": 0.5347, "lr": 1.6528242568937174e-05, "epoch": 1.8308633827323453, "percentage": 61.02, "elapsed_time": "1:47:50", "remaining_time": "1:08:53", "throughput": 6620.93, "total_tokens": 42840440} {"current_steps": 3820, "total_steps": 6252, "loss": 0.5028, "lr": 1.6469173993536787e-05, "epoch": 1.8332633347333054, "percentage": 61.1, "elapsed_time": "1:48:00", "remaining_time": "1:08:45", "throughput": 6619.25, "total_tokens": 42893576} {"current_steps": 3825, "total_steps": 6252, "loss": 0.4997, "lr": 1.641015926899985e-05, "epoch": 1.8356632867342653, "percentage": 61.18, "elapsed_time": "1:48:10", "remaining_time": "1:08:38", "throughput": 6618.24, "total_tokens": 42952744} {"current_steps": 3830, "total_steps": 6252, "loss": 0.5076, "lr": 1.6351198767856978e-05, "epoch": 1.8380632387352254, "percentage": 61.26, "elapsed_time": "1:48:18", "remaining_time": "1:08:29", "throughput": 6618.3, "total_tokens": 43010768} {"current_steps": 3835, "total_steps": 6252, "loss": 0.4789, "lr": 1.6292292862296482e-05, "epoch": 1.8404631907361853, "percentage": 61.34, "elapsed_time": "1:48:26", "remaining_time": "1:08:20", "throughput": 6618.72, "total_tokens": 43067120} {"current_steps": 3840, "total_steps": 6252, "loss": 0.472, "lr": 1.6233441924162085e-05, "epoch": 1.8428631427371451, "percentage": 61.42, "elapsed_time": "1:48:34", "remaining_time": "1:08:12", "throughput": 6619.49, "total_tokens": 43124944} {"current_steps": 3845, "total_steps": 6252, "loss": 0.4968, "lr": 1.617464632495048e-05, "epoch": 1.8452630947381052, "percentage": 61.5, "elapsed_time": "1:48:42", "remaining_time": "1:08:03", "throughput": 6620.25, "total_tokens": 43181496} {"current_steps": 3850, "total_steps": 6252, "loss": 0.4799, "lr": 1.611590643580906e-05, "epoch": 1.8476630467390653, "percentage": 61.58, "elapsed_time": "1:48:51", "remaining_time": "1:07:54", "throughput": 6620.06, "total_tokens": 43236224} {"current_steps": 3855, "total_steps": 6252, "loss": 0.4825, "lr": 1.6057222627533554e-05, "epoch": 1.8500629987400252, "percentage": 61.66, "elapsed_time": "1:48:59", "remaining_time": "1:07:46", "throughput": 6620.23, "total_tokens": 43291464} {"current_steps": 3860, "total_steps": 6252, "loss": 0.4525, "lr": 1.599859527056566e-05, "epoch": 1.852462950740985, "percentage": 61.74, "elapsed_time": "1:49:07", "remaining_time": "1:07:37", "throughput": 6620.62, "total_tokens": 43349520} {"current_steps": 3865, "total_steps": 6252, "loss": 0.4601, "lr": 1.594002473499073e-05, "epoch": 1.8548629027419452, "percentage": 61.82, "elapsed_time": "1:49:16", "remaining_time": "1:07:29", "throughput": 6621.06, "total_tokens": 43410208} {"current_steps": 3870, "total_steps": 6252, "loss": 0.4458, "lr": 1.588151139053544e-05, "epoch": 1.857262854742905, "percentage": 61.9, "elapsed_time": "1:49:24", "remaining_time": "1:07:20", "throughput": 6621.38, "total_tokens": 43469344} {"current_steps": 3875, "total_steps": 6252, "loss": 0.4859, "lr": 1.5823055606565458e-05, "epoch": 1.8596628067438652, "percentage": 61.98, "elapsed_time": "1:49:33", "remaining_time": "1:07:12", "throughput": 6621.12, "total_tokens": 43526440} {"current_steps": 3880, "total_steps": 6252, "loss": 0.4795, "lr": 1.5764657752083072e-05, "epoch": 1.862062758744825, "percentage": 62.06, "elapsed_time": "1:49:42", "remaining_time": "1:07:04", "throughput": 6621.33, "total_tokens": 43583936} {"current_steps": 3885, "total_steps": 6252, "loss": 0.4707, "lr": 1.5706318195724894e-05, "epoch": 1.864462710745785, "percentage": 62.14, "elapsed_time": "1:49:50", "remaining_time": "1:06:55", "throughput": 6621.76, "total_tokens": 43639480} {"current_steps": 3890, "total_steps": 6252, "loss": 0.4557, "lr": 1.5648037305759566e-05, "epoch": 1.866862662746745, "percentage": 62.22, "elapsed_time": "1:49:57", "remaining_time": "1:06:46", "throughput": 6621.86, "total_tokens": 43690520} {"current_steps": 3895, "total_steps": 6252, "loss": 0.4621, "lr": 1.5589815450085355e-05, "epoch": 1.8692626147477052, "percentage": 62.3, "elapsed_time": "1:50:06", "remaining_time": "1:06:37", "throughput": 6622.25, "total_tokens": 43749480} {"current_steps": 3900, "total_steps": 6252, "loss": 0.4627, "lr": 1.5531652996227885e-05, "epoch": 1.871662566748665, "percentage": 62.38, "elapsed_time": "1:50:13", "remaining_time": "1:06:28", "throughput": 6622.37, "total_tokens": 43799824} {"current_steps": 3905, "total_steps": 6252, "loss": 0.4806, "lr": 1.5473550311337833e-05, "epoch": 1.874062518749625, "percentage": 62.46, "elapsed_time": "1:50:22", "remaining_time": "1:06:20", "throughput": 6622.85, "total_tokens": 43858032} {"current_steps": 3910, "total_steps": 6252, "loss": 0.4767, "lr": 1.541550776218855e-05, "epoch": 1.876462470750585, "percentage": 62.54, "elapsed_time": "1:50:30", "remaining_time": "1:06:11", "throughput": 6623.28, "total_tokens": 43914232} {"current_steps": 3915, "total_steps": 6252, "loss": 0.4582, "lr": 1.535752571517379e-05, "epoch": 1.878862422751545, "percentage": 62.62, "elapsed_time": "1:50:38", "remaining_time": "1:06:02", "throughput": 6623.9, "total_tokens": 43970744} {"current_steps": 3920, "total_steps": 6252, "loss": 0.4725, "lr": 1.529960453630538e-05, "epoch": 1.881262374752505, "percentage": 62.7, "elapsed_time": "1:50:46", "remaining_time": "1:05:53", "throughput": 6624.63, "total_tokens": 44028408} {"current_steps": 3925, "total_steps": 6252, "loss": 0.4661, "lr": 1.5241744591210954e-05, "epoch": 1.883662326753465, "percentage": 62.78, "elapsed_time": "1:50:54", "remaining_time": "1:05:45", "throughput": 6625.08, "total_tokens": 44085968} {"current_steps": 3930, "total_steps": 6252, "loss": 0.5171, "lr": 1.5183946245131563e-05, "epoch": 1.8860622787544248, "percentage": 62.86, "elapsed_time": "1:51:02", "remaining_time": "1:05:36", "throughput": 6625.51, "total_tokens": 44143360} {"current_steps": 3935, "total_steps": 6252, "loss": 0.4935, "lr": 1.5126209862919427e-05, "epoch": 1.8884622307553849, "percentage": 62.94, "elapsed_time": "1:51:09", "remaining_time": "1:05:27", "throughput": 6625.85, "total_tokens": 44193864} {"current_steps": 3940, "total_steps": 6252, "loss": 0.5181, "lr": 1.506853580903564e-05, "epoch": 1.890862182756345, "percentage": 63.02, "elapsed_time": "1:51:17", "remaining_time": "1:05:18", "throughput": 6626.47, "total_tokens": 44249464} {"current_steps": 3945, "total_steps": 6252, "loss": 0.445, "lr": 1.5010924447547808e-05, "epoch": 1.8932621347573049, "percentage": 63.1, "elapsed_time": "1:51:25", "remaining_time": "1:05:09", "throughput": 6626.92, "total_tokens": 44306480} {"current_steps": 3950, "total_steps": 6252, "loss": 0.4933, "lr": 1.4953376142127828e-05, "epoch": 1.8956620867582648, "percentage": 63.18, "elapsed_time": "1:51:33", "remaining_time": "1:05:00", "throughput": 6627.75, "total_tokens": 44363776} {"current_steps": 3955, "total_steps": 6252, "loss": 0.4952, "lr": 1.4895891256049548e-05, "epoch": 1.8980620387592249, "percentage": 63.26, "elapsed_time": "1:51:41", "remaining_time": "1:04:52", "throughput": 6627.88, "total_tokens": 44419016} {"current_steps": 3960, "total_steps": 6252, "loss": 0.5036, "lr": 1.483847015218647e-05, "epoch": 1.900461990760185, "percentage": 63.34, "elapsed_time": "1:51:49", "remaining_time": "1:04:43", "throughput": 6628.19, "total_tokens": 44473296} {"current_steps": 3965, "total_steps": 6252, "loss": 0.4709, "lr": 1.4781113193009466e-05, "epoch": 1.9028619427611448, "percentage": 63.42, "elapsed_time": "1:51:58", "remaining_time": "1:04:35", "throughput": 6628.57, "total_tokens": 44533064} {"current_steps": 3970, "total_steps": 6252, "loss": 0.487, "lr": 1.472382074058451e-05, "epoch": 1.9052618947621047, "percentage": 63.5, "elapsed_time": "1:52:06", "remaining_time": "1:04:26", "throughput": 6629.27, "total_tokens": 44591088} {"current_steps": 3975, "total_steps": 6252, "loss": 0.4822, "lr": 1.4666593156570376e-05, "epoch": 1.9076618467630646, "percentage": 63.58, "elapsed_time": "1:52:13", "remaining_time": "1:04:17", "throughput": 6629.38, "total_tokens": 44639864} {"current_steps": 3980, "total_steps": 6252, "loss": 0.4792, "lr": 1.460943080221635e-05, "epoch": 1.9100617987640247, "percentage": 63.66, "elapsed_time": "1:52:22", "remaining_time": "1:04:08", "throughput": 6629.59, "total_tokens": 44697568} {"current_steps": 3985, "total_steps": 6252, "loss": 0.4861, "lr": 1.4552334038359938e-05, "epoch": 1.9124617507649848, "percentage": 63.74, "elapsed_time": "1:52:29", "remaining_time": "1:03:59", "throughput": 6629.99, "total_tokens": 44750848} {"current_steps": 3990, "total_steps": 6252, "loss": 0.4546, "lr": 1.4495303225424656e-05, "epoch": 1.9148617027659447, "percentage": 63.82, "elapsed_time": "1:52:37", "remaining_time": "1:03:51", "throughput": 6629.89, "total_tokens": 44804648} {"current_steps": 3995, "total_steps": 6252, "loss": 0.5007, "lr": 1.4438338723417654e-05, "epoch": 1.9172616547669046, "percentage": 63.9, "elapsed_time": "1:52:46", "remaining_time": "1:03:42", "throughput": 6630.11, "total_tokens": 44860632} {"current_steps": 4000, "total_steps": 6252, "loss": 0.5301, "lr": 1.4381440891927512e-05, "epoch": 1.9196616067678647, "percentage": 63.98, "elapsed_time": "1:52:54", "remaining_time": "1:03:33", "throughput": 6630.16, "total_tokens": 44913712} {"current_steps": 4005, "total_steps": 6252, "loss": 0.5028, "lr": 1.432461009012196e-05, "epoch": 1.9220615587688248, "percentage": 64.06, "elapsed_time": "1:53:02", "remaining_time": "1:03:25", "throughput": 6630.64, "total_tokens": 44970992} {"current_steps": 4010, "total_steps": 6252, "loss": 0.4618, "lr": 1.4267846676745598e-05, "epoch": 1.9244615107697847, "percentage": 64.14, "elapsed_time": "1:53:10", "remaining_time": "1:03:16", "throughput": 6630.48, "total_tokens": 45024328} {"current_steps": 4015, "total_steps": 6252, "loss": 0.5078, "lr": 1.4211151010117627e-05, "epoch": 1.9268614627707445, "percentage": 64.22, "elapsed_time": "1:53:18", "remaining_time": "1:03:08", "throughput": 6630.86, "total_tokens": 45082296} {"current_steps": 4020, "total_steps": 6252, "loss": 0.4823, "lr": 1.4154523448129597e-05, "epoch": 1.9292614147717044, "percentage": 64.3, "elapsed_time": "1:53:26", "remaining_time": "1:02:59", "throughput": 6631.25, "total_tokens": 45137992} {"current_steps": 4025, "total_steps": 6252, "loss": 0.4639, "lr": 1.4097964348243172e-05, "epoch": 1.9316613667726645, "percentage": 64.38, "elapsed_time": "1:53:35", "remaining_time": "1:02:50", "throughput": 6631.5, "total_tokens": 45197208} {"current_steps": 4030, "total_steps": 6252, "loss": 0.4599, "lr": 1.4041474067487814e-05, "epoch": 1.9340613187736246, "percentage": 64.46, "elapsed_time": "1:53:43", "remaining_time": "1:02:42", "throughput": 6631.94, "total_tokens": 45256040} {"current_steps": 4035, "total_steps": 6252, "loss": 0.4903, "lr": 1.3985052962458593e-05, "epoch": 1.9364612707745845, "percentage": 64.54, "elapsed_time": "1:53:51", "remaining_time": "1:02:33", "throughput": 6632.51, "total_tokens": 45311968} {"current_steps": 4040, "total_steps": 6252, "loss": 0.4939, "lr": 1.3928701389313897e-05, "epoch": 1.9388612227755444, "percentage": 64.62, "elapsed_time": "1:53:59", "remaining_time": "1:02:24", "throughput": 6632.37, "total_tokens": 45361584} {"current_steps": 4045, "total_steps": 6252, "loss": 0.4876, "lr": 1.3872419703773187e-05, "epoch": 1.9412611747765045, "percentage": 64.7, "elapsed_time": "1:54:07", "remaining_time": "1:02:16", "throughput": 6632.87, "total_tokens": 45421616} {"current_steps": 4050, "total_steps": 6252, "loss": 0.5142, "lr": 1.3816208261114755e-05, "epoch": 1.9436611267774646, "percentage": 64.78, "elapsed_time": "1:54:15", "remaining_time": "1:02:07", "throughput": 6633.53, "total_tokens": 45475784} {"current_steps": 4055, "total_steps": 6252, "loss": 0.4949, "lr": 1.3760067416173511e-05, "epoch": 1.9460610787784245, "percentage": 64.86, "elapsed_time": "1:54:23", "remaining_time": "1:01:58", "throughput": 6633.73, "total_tokens": 45529816} {"current_steps": 4060, "total_steps": 6252, "loss": 0.4917, "lr": 1.3703997523338688e-05, "epoch": 1.9484610307793844, "percentage": 64.94, "elapsed_time": "1:54:30", "remaining_time": "1:01:49", "throughput": 6634.56, "total_tokens": 45585432} {"current_steps": 4065, "total_steps": 6252, "loss": 0.4542, "lr": 1.3647998936551643e-05, "epoch": 1.9508609827803443, "percentage": 65.02, "elapsed_time": "1:54:39", "remaining_time": "1:01:40", "throughput": 6634.99, "total_tokens": 45642256} {"current_steps": 4070, "total_steps": 6252, "loss": 0.4767, "lr": 1.3592072009303603e-05, "epoch": 1.9532609347813044, "percentage": 65.1, "elapsed_time": "1:54:47", "remaining_time": "1:01:32", "throughput": 6635.69, "total_tokens": 45700704} {"current_steps": 4075, "total_steps": 6252, "loss": 0.4649, "lr": 1.3536217094633471e-05, "epoch": 1.9556608867822645, "percentage": 65.18, "elapsed_time": "1:54:55", "remaining_time": "1:01:23", "throughput": 6635.71, "total_tokens": 45754672} {"current_steps": 4080, "total_steps": 6252, "loss": 0.4794, "lr": 1.3480434545125562e-05, "epoch": 1.9580608387832243, "percentage": 65.26, "elapsed_time": "1:55:02", "remaining_time": "1:01:14", "throughput": 6635.94, "total_tokens": 45805360} {"current_steps": 4085, "total_steps": 6252, "loss": 0.5073, "lr": 1.3424724712907355e-05, "epoch": 1.9604607907841842, "percentage": 65.34, "elapsed_time": "1:55:10", "remaining_time": "1:01:05", "throughput": 6636.39, "total_tokens": 45859408} {"current_steps": 4090, "total_steps": 6252, "loss": 0.4844, "lr": 1.3369087949647352e-05, "epoch": 1.9628607427851443, "percentage": 65.42, "elapsed_time": "1:55:18", "remaining_time": "1:00:57", "throughput": 6636.85, "total_tokens": 45915912} {"current_steps": 4095, "total_steps": 6252, "loss": 0.4683, "lr": 1.3313524606552763e-05, "epoch": 1.9652606947861044, "percentage": 65.5, "elapsed_time": "1:55:26", "remaining_time": "1:00:48", "throughput": 6637.04, "total_tokens": 45972424} {"current_steps": 4100, "total_steps": 6252, "loss": 0.4847, "lr": 1.3258035034367338e-05, "epoch": 1.9676606467870643, "percentage": 65.58, "elapsed_time": "1:55:34", "remaining_time": "1:00:39", "throughput": 6637.47, "total_tokens": 46029616} {"current_steps": 4105, "total_steps": 6252, "loss": 0.5131, "lr": 1.3202619583369189e-05, "epoch": 1.9700605987880242, "percentage": 65.66, "elapsed_time": "1:55:43", "remaining_time": "1:00:31", "throughput": 6637.18, "total_tokens": 46087816} {"current_steps": 4110, "total_steps": 6252, "loss": 0.496, "lr": 1.3147278603368487e-05, "epoch": 1.972460550788984, "percentage": 65.74, "elapsed_time": "1:55:51", "remaining_time": "1:00:22", "throughput": 6637.55, "total_tokens": 46141504} {"current_steps": 4115, "total_steps": 6252, "loss": 0.4513, "lr": 1.3092012443705332e-05, "epoch": 1.9748605027899442, "percentage": 65.82, "elapsed_time": "1:56:00", "remaining_time": "1:00:14", "throughput": 6638.05, "total_tokens": 46202072} {"current_steps": 4120, "total_steps": 6252, "loss": 0.4997, "lr": 1.3036821453247506e-05, "epoch": 1.9772604547909043, "percentage": 65.9, "elapsed_time": "1:56:08", "remaining_time": "1:00:05", "throughput": 6638.27, "total_tokens": 46258400} {"current_steps": 4125, "total_steps": 6252, "loss": 0.5062, "lr": 1.2981705980388295e-05, "epoch": 1.9796604067918642, "percentage": 65.98, "elapsed_time": "1:56:15", "remaining_time": "0:59:57", "throughput": 6638.5, "total_tokens": 46309656} {"current_steps": 4130, "total_steps": 6252, "loss": 0.4891, "lr": 1.2926666373044294e-05, "epoch": 1.982060358792824, "percentage": 66.06, "elapsed_time": "1:56:24", "remaining_time": "0:59:48", "throughput": 6638.87, "total_tokens": 46366888} {"current_steps": 4135, "total_steps": 6252, "loss": 0.5002, "lr": 1.2871702978653163e-05, "epoch": 1.9844603107937842, "percentage": 66.14, "elapsed_time": "1:56:31", "remaining_time": "0:59:39", "throughput": 6639.19, "total_tokens": 46419304} {"current_steps": 4140, "total_steps": 6252, "loss": 0.5105, "lr": 1.28168161441715e-05, "epoch": 1.9868602627947443, "percentage": 66.22, "elapsed_time": "1:56:39", "remaining_time": "0:59:30", "throughput": 6639.44, "total_tokens": 46469520} {"current_steps": 4145, "total_steps": 6252, "loss": 0.5154, "lr": 1.27620062160726e-05, "epoch": 1.9892602147957041, "percentage": 66.3, "elapsed_time": "1:56:46", "remaining_time": "0:59:21", "throughput": 6639.55, "total_tokens": 46523240} {"current_steps": 4150, "total_steps": 6252, "loss": 0.5361, "lr": 1.2707273540344274e-05, "epoch": 1.991660166796664, "percentage": 66.38, "elapsed_time": "1:56:55", "remaining_time": "0:59:13", "throughput": 6639.71, "total_tokens": 46577712} {"current_steps": 4155, "total_steps": 6252, "loss": 0.4873, "lr": 1.265261846248672e-05, "epoch": 1.994060118797624, "percentage": 66.46, "elapsed_time": "1:57:02", "remaining_time": "0:59:04", "throughput": 6639.91, "total_tokens": 46629984} {"current_steps": 4160, "total_steps": 6252, "loss": 0.4779, "lr": 1.2598041327510254e-05, "epoch": 1.996460070798584, "percentage": 66.54, "elapsed_time": "1:57:11", "remaining_time": "0:58:56", "throughput": 6639.71, "total_tokens": 46689664} {"current_steps": 4165, "total_steps": 6252, "loss": 0.4451, "lr": 1.25435424799332e-05, "epoch": 1.9988600227995441, "percentage": 66.62, "elapsed_time": "1:57:21", "remaining_time": "0:58:48", "throughput": 6639.97, "total_tokens": 46752192} {"current_steps": 4170, "total_steps": 6252, "loss": 0.4431, "lr": 1.2489122263779684e-05, "epoch": 2.000959980800384, "percentage": 66.7, "elapsed_time": "1:57:28", "remaining_time": "0:58:39", "throughput": 6639.97, "total_tokens": 46800120} {"current_steps": 4175, "total_steps": 6252, "loss": 0.4561, "lr": 1.2434781022577476e-05, "epoch": 2.003359932801344, "percentage": 66.78, "elapsed_time": "1:57:36", "remaining_time": "0:58:30", "throughput": 6640.36, "total_tokens": 46859352} {"current_steps": 4180, "total_steps": 6252, "loss": 0.4531, "lr": 1.2380519099355831e-05, "epoch": 2.005759884802304, "percentage": 66.86, "elapsed_time": "1:57:44", "remaining_time": "0:58:22", "throughput": 6641.03, "total_tokens": 46918656} {"current_steps": 4185, "total_steps": 6252, "loss": 0.5048, "lr": 1.2326336836643274e-05, "epoch": 2.008159836803264, "percentage": 66.94, "elapsed_time": "1:57:53", "remaining_time": "0:58:13", "throughput": 6641.12, "total_tokens": 46976896} {"current_steps": 4190, "total_steps": 6252, "loss": 0.4846, "lr": 1.227223457646551e-05, "epoch": 2.010559788804224, "percentage": 67.02, "elapsed_time": "1:58:01", "remaining_time": "0:58:05", "throughput": 6641.61, "total_tokens": 47033584} {"current_steps": 4195, "total_steps": 6252, "loss": 0.497, "lr": 1.22182126603432e-05, "epoch": 2.012959740805184, "percentage": 67.1, "elapsed_time": "1:58:09", "remaining_time": "0:57:56", "throughput": 6641.77, "total_tokens": 47084560} {"current_steps": 4200, "total_steps": 6252, "loss": 0.4671, "lr": 1.2164271429289837e-05, "epoch": 2.0153596928061437, "percentage": 67.18, "elapsed_time": "1:58:17", "remaining_time": "0:57:47", "throughput": 6641.98, "total_tokens": 47141040} {"current_steps": 4205, "total_steps": 6252, "loss": 0.4329, "lr": 1.2110411223809612e-05, "epoch": 2.017759644807104, "percentage": 67.26, "elapsed_time": "1:58:27", "remaining_time": "0:57:39", "throughput": 6640.59, "total_tokens": 47198656} {"current_steps": 4210, "total_steps": 6252, "loss": 0.4903, "lr": 1.2056632383895217e-05, "epoch": 2.020159596808064, "percentage": 67.34, "elapsed_time": "1:58:36", "remaining_time": "0:57:31", "throughput": 6639.85, "total_tokens": 47255504} {"current_steps": 4215, "total_steps": 6252, "loss": 0.4788, "lr": 1.2002935249025732e-05, "epoch": 2.0225595488090238, "percentage": 67.42, "elapsed_time": "1:58:46", "remaining_time": "0:57:24", "throughput": 6638.27, "total_tokens": 47307728} {"current_steps": 4220, "total_steps": 6252, "loss": 0.4692, "lr": 1.1949320158164466e-05, "epoch": 2.0249595008099837, "percentage": 67.5, "elapsed_time": "1:58:56", "remaining_time": "0:57:16", "throughput": 6637.12, "total_tokens": 47365504} {"current_steps": 4225, "total_steps": 6252, "loss": 0.4565, "lr": 1.1895787449756834e-05, "epoch": 2.027359452810944, "percentage": 67.58, "elapsed_time": "1:59:07", "remaining_time": "0:57:08", "throughput": 6635.36, "total_tokens": 47424664} {"current_steps": 4230, "total_steps": 6252, "loss": 0.5177, "lr": 1.1842337461728232e-05, "epoch": 2.029759404811904, "percentage": 67.66, "elapsed_time": "1:59:18", "remaining_time": "0:57:01", "throughput": 6633.46, "total_tokens": 47482624} {"current_steps": 4235, "total_steps": 6252, "loss": 0.4509, "lr": 1.1788970531481832e-05, "epoch": 2.0321593568128637, "percentage": 67.74, "elapsed_time": "1:59:28", "remaining_time": "0:56:54", "throughput": 6631.63, "total_tokens": 47541264} {"current_steps": 4240, "total_steps": 6252, "loss": 0.5111, "lr": 1.1735686995896559e-05, "epoch": 2.0345593088138236, "percentage": 67.82, "elapsed_time": "1:59:38", "remaining_time": "0:56:46", "throughput": 6630.47, "total_tokens": 47596256} {"current_steps": 4245, "total_steps": 6252, "loss": 0.5576, "lr": 1.1682487191324868e-05, "epoch": 2.0369592608147835, "percentage": 67.9, "elapsed_time": "1:59:48", "remaining_time": "0:56:38", "throughput": 6628.95, "total_tokens": 47649808} {"current_steps": 4250, "total_steps": 6252, "loss": 0.4836, "lr": 1.1629371453590671e-05, "epoch": 2.039359212815744, "percentage": 67.98, "elapsed_time": "1:59:58", "remaining_time": "0:56:30", "throughput": 6627.67, "total_tokens": 47709328} {"current_steps": 4255, "total_steps": 6252, "loss": 0.5057, "lr": 1.1576340117987233e-05, "epoch": 2.0417591648167037, "percentage": 68.06, "elapsed_time": "2:00:09", "remaining_time": "0:56:23", "throughput": 6625.8, "total_tokens": 47765800} {"current_steps": 4260, "total_steps": 6252, "loss": 0.4447, "lr": 1.1523393519274996e-05, "epoch": 2.0441591168176636, "percentage": 68.14, "elapsed_time": "2:00:18", "remaining_time": "0:56:15", "throughput": 6624.92, "total_tokens": 47820320} {"current_steps": 4265, "total_steps": 6252, "loss": 0.5101, "lr": 1.1470531991679523e-05, "epoch": 2.0465590688186235, "percentage": 68.22, "elapsed_time": "2:00:28", "remaining_time": "0:56:07", "throughput": 6623.61, "total_tokens": 47876928} {"current_steps": 4270, "total_steps": 6252, "loss": 0.4432, "lr": 1.1417755868889343e-05, "epoch": 2.048959020819584, "percentage": 68.3, "elapsed_time": "2:00:37", "remaining_time": "0:55:59", "throughput": 6622.87, "total_tokens": 47933280} {"current_steps": 4275, "total_steps": 6252, "loss": 0.4606, "lr": 1.1365065484053895e-05, "epoch": 2.0513589728205437, "percentage": 68.38, "elapsed_time": "2:00:47", "remaining_time": "0:55:51", "throughput": 6621.89, "total_tokens": 47991280} {"current_steps": 4280, "total_steps": 6252, "loss": 0.4669, "lr": 1.1312461169781383e-05, "epoch": 2.0537589248215036, "percentage": 68.46, "elapsed_time": "2:00:57", "remaining_time": "0:55:43", "throughput": 6620.46, "total_tokens": 48045896} {"current_steps": 4285, "total_steps": 6252, "loss": 0.4849, "lr": 1.1259943258136682e-05, "epoch": 2.0561588768224635, "percentage": 68.54, "elapsed_time": "2:01:07", "remaining_time": "0:55:36", "throughput": 6618.89, "total_tokens": 48105824} {"current_steps": 4290, "total_steps": 6252, "loss": 0.4956, "lr": 1.1207512080639273e-05, "epoch": 2.0585588288234233, "percentage": 68.62, "elapsed_time": "2:01:17", "remaining_time": "0:55:28", "throughput": 6617.4, "total_tokens": 48160632} {"current_steps": 4295, "total_steps": 6252, "loss": 0.4357, "lr": 1.1155167968261105e-05, "epoch": 2.0609587808243837, "percentage": 68.7, "elapsed_time": "2:01:28", "remaining_time": "0:55:20", "throughput": 6615.85, "total_tokens": 48217992} {"current_steps": 4300, "total_steps": 6252, "loss": 0.4907, "lr": 1.1102911251424526e-05, "epoch": 2.0633587328253435, "percentage": 68.78, "elapsed_time": "2:01:38", "remaining_time": "0:55:13", "throughput": 6614.42, "total_tokens": 48276216} {"current_steps": 4305, "total_steps": 6252, "loss": 0.4687, "lr": 1.1050742260000226e-05, "epoch": 2.0657586848263034, "percentage": 68.86, "elapsed_time": "2:01:48", "remaining_time": "0:55:05", "throughput": 6613.18, "total_tokens": 48331296} {"current_steps": 4310, "total_steps": 6252, "loss": 0.4574, "lr": 1.0998661323305107e-05, "epoch": 2.0681586368272633, "percentage": 68.94, "elapsed_time": "2:01:57", "remaining_time": "0:54:57", "throughput": 6612.35, "total_tokens": 48387368} {"current_steps": 4315, "total_steps": 6252, "loss": 0.5004, "lr": 1.094666877010023e-05, "epoch": 2.0705585888282236, "percentage": 69.02, "elapsed_time": "2:02:07", "remaining_time": "0:54:49", "throughput": 6610.5, "total_tokens": 48440296} {"current_steps": 4320, "total_steps": 6252, "loss": 0.4747, "lr": 1.0894764928588721e-05, "epoch": 2.0729585408291835, "percentage": 69.1, "elapsed_time": "2:02:16", "remaining_time": "0:54:41", "throughput": 6609.44, "total_tokens": 48492496} {"current_steps": 4325, "total_steps": 6252, "loss": 0.5137, "lr": 1.0842950126413742e-05, "epoch": 2.0753584928301434, "percentage": 69.18, "elapsed_time": "2:02:26", "remaining_time": "0:54:33", "throughput": 6608.45, "total_tokens": 48549184} {"current_steps": 4330, "total_steps": 6252, "loss": 0.4573, "lr": 1.0791224690656384e-05, "epoch": 2.0777584448311033, "percentage": 69.26, "elapsed_time": "2:02:34", "remaining_time": "0:54:24", "throughput": 6608.07, "total_tokens": 48601016} {"current_steps": 4335, "total_steps": 6252, "loss": 0.4814, "lr": 1.0739588947833593e-05, "epoch": 2.080158396832063, "percentage": 69.34, "elapsed_time": "2:02:43", "remaining_time": "0:54:16", "throughput": 6607.52, "total_tokens": 48655504} {"current_steps": 4340, "total_steps": 6252, "loss": 0.4997, "lr": 1.068804322389616e-05, "epoch": 2.0825583488330235, "percentage": 69.42, "elapsed_time": "2:02:52", "remaining_time": "0:54:08", "throughput": 6606.74, "total_tokens": 48708616} {"current_steps": 4345, "total_steps": 6252, "loss": 0.4459, "lr": 1.06365878442266e-05, "epoch": 2.0849583008339834, "percentage": 69.5, "elapsed_time": "2:03:01", "remaining_time": "0:53:59", "throughput": 6606.54, "total_tokens": 48769440} {"current_steps": 4350, "total_steps": 6252, "loss": 0.4882, "lr": 1.0585223133637143e-05, "epoch": 2.0873582528349433, "percentage": 69.58, "elapsed_time": "2:03:10", "remaining_time": "0:53:51", "throughput": 6606.4, "total_tokens": 48827720} {"current_steps": 4355, "total_steps": 6252, "loss": 0.5322, "lr": 1.053394941636768e-05, "epoch": 2.089758204835903, "percentage": 69.66, "elapsed_time": "2:03:18", "remaining_time": "0:53:42", "throughput": 6606.57, "total_tokens": 48879552} {"current_steps": 4360, "total_steps": 6252, "loss": 0.4515, "lr": 1.0482767016083694e-05, "epoch": 2.0921581568368635, "percentage": 69.74, "elapsed_time": "2:03:26", "remaining_time": "0:53:33", "throughput": 6607.08, "total_tokens": 48932848} {"current_steps": 4365, "total_steps": 6252, "loss": 0.5213, "lr": 1.0431676255874232e-05, "epoch": 2.0945581088378233, "percentage": 69.82, "elapsed_time": "2:03:34", "remaining_time": "0:53:25", "throughput": 6607.7, "total_tokens": 48989744} {"current_steps": 4370, "total_steps": 6252, "loss": 0.4821, "lr": 1.0380677458249852e-05, "epoch": 2.0969580608387832, "percentage": 69.9, "elapsed_time": "2:03:41", "remaining_time": "0:53:16", "throughput": 6608.2, "total_tokens": 49043888} {"current_steps": 4375, "total_steps": 6252, "loss": 0.5018, "lr": 1.0329770945140618e-05, "epoch": 2.099358012839743, "percentage": 69.98, "elapsed_time": "2:03:49", "remaining_time": "0:53:07", "throughput": 6608.72, "total_tokens": 49099976} {"current_steps": 4380, "total_steps": 6252, "loss": 0.5266, "lr": 1.0278957037894048e-05, "epoch": 2.101757964840703, "percentage": 70.06, "elapsed_time": "2:03:57", "remaining_time": "0:52:58", "throughput": 6609.39, "total_tokens": 49158168} {"current_steps": 4385, "total_steps": 6252, "loss": 0.4906, "lr": 1.0228236057273063e-05, "epoch": 2.1041579168416633, "percentage": 70.14, "elapsed_time": "2:04:05", "remaining_time": "0:52:49", "throughput": 6609.71, "total_tokens": 49209920} {"current_steps": 4390, "total_steps": 6252, "loss": 0.5067, "lr": 1.0177608323454008e-05, "epoch": 2.106557868842623, "percentage": 70.22, "elapsed_time": "2:04:12", "remaining_time": "0:52:41", "throughput": 6609.88, "total_tokens": 49262384} {"current_steps": 4395, "total_steps": 6252, "loss": 0.4642, "lr": 1.0127074156024594e-05, "epoch": 2.108957820843583, "percentage": 70.3, "elapsed_time": "2:04:20", "remaining_time": "0:52:32", "throughput": 6610.0, "total_tokens": 49315632} {"current_steps": 4400, "total_steps": 6252, "loss": 0.4984, "lr": 1.0076633873981883e-05, "epoch": 2.111357772844543, "percentage": 70.38, "elapsed_time": "2:04:28", "remaining_time": "0:52:23", "throughput": 6610.27, "total_tokens": 49371384} {"current_steps": 4405, "total_steps": 6252, "loss": 0.4767, "lr": 1.0026287795730319e-05, "epoch": 2.1137577248455033, "percentage": 70.46, "elapsed_time": "2:04:37", "remaining_time": "0:52:15", "throughput": 6610.22, "total_tokens": 49426056} {"current_steps": 4410, "total_steps": 6252, "loss": 0.491, "lr": 9.976036239079656e-06, "epoch": 2.116157676846463, "percentage": 70.54, "elapsed_time": "2:04:45", "remaining_time": "0:52:06", "throughput": 6610.17, "total_tokens": 49483160} {"current_steps": 4415, "total_steps": 6252, "loss": 0.4566, "lr": 9.925879521242978e-06, "epoch": 2.118557628847423, "percentage": 70.62, "elapsed_time": "2:04:54", "remaining_time": "0:51:58", "throughput": 6609.73, "total_tokens": 49537568} {"current_steps": 4420, "total_steps": 6252, "loss": 0.4878, "lr": 9.87581795883473e-06, "epoch": 2.120957580848383, "percentage": 70.7, "elapsed_time": "2:05:03", "remaining_time": "0:51:49", "throughput": 6609.72, "total_tokens": 49594120} {"current_steps": 4425, "total_steps": 6252, "loss": 0.4871, "lr": 9.825851867868646e-06, "epoch": 2.123357532849343, "percentage": 70.78, "elapsed_time": "2:05:11", "remaining_time": "0:51:41", "throughput": 6609.66, "total_tokens": 49647944} {"current_steps": 4430, "total_steps": 6252, "loss": 0.4747, "lr": 9.775981563755835e-06, "epoch": 2.125757484850303, "percentage": 70.86, "elapsed_time": "2:05:20", "remaining_time": "0:51:33", "throughput": 6608.82, "total_tokens": 49702848} {"current_steps": 4435, "total_steps": 6252, "loss": 0.4871, "lr": 9.726207361302716e-06, "epoch": 2.128157436851263, "percentage": 70.94, "elapsed_time": "2:05:30", "remaining_time": "0:51:25", "throughput": 6606.89, "total_tokens": 49754336} {"current_steps": 4440, "total_steps": 6252, "loss": 0.4813, "lr": 9.676529574709104e-06, "epoch": 2.130557388852223, "percentage": 71.02, "elapsed_time": "2:05:43", "remaining_time": "0:51:18", "throughput": 6604.43, "total_tokens": 49818104} {"current_steps": 4445, "total_steps": 6252, "loss": 0.5196, "lr": 9.62694851756616e-06, "epoch": 2.132957340853183, "percentage": 71.1, "elapsed_time": "2:05:53", "remaining_time": "0:51:10", "throughput": 6602.61, "total_tokens": 49872640} {"current_steps": 4450, "total_steps": 6252, "loss": 0.441, "lr": 9.577464502854432e-06, "epoch": 2.135357292854143, "percentage": 71.18, "elapsed_time": "2:06:03", "remaining_time": "0:51:02", "throughput": 6601.26, "total_tokens": 49929176} {"current_steps": 4455, "total_steps": 6252, "loss": 0.4755, "lr": 9.528077842941929e-06, "epoch": 2.137757244855103, "percentage": 71.26, "elapsed_time": "2:06:14", "remaining_time": "0:50:55", "throughput": 6599.11, "total_tokens": 49984040} {"current_steps": 4460, "total_steps": 6252, "loss": 0.4841, "lr": 9.478788849582071e-06, "epoch": 2.140157196856063, "percentage": 71.34, "elapsed_time": "2:06:24", "remaining_time": "0:50:47", "throughput": 6597.02, "total_tokens": 50036368} {"current_steps": 4465, "total_steps": 6252, "loss": 0.4813, "lr": 9.42959783391176e-06, "epoch": 2.1425571488570228, "percentage": 71.42, "elapsed_time": "2:06:34", "remaining_time": "0:50:39", "throughput": 6595.59, "total_tokens": 50091376} {"current_steps": 4470, "total_steps": 6252, "loss": 0.4844, "lr": 9.38050510644944e-06, "epoch": 2.1449571008579826, "percentage": 71.5, "elapsed_time": "2:06:44", "remaining_time": "0:50:31", "throughput": 6594.66, "total_tokens": 50148472} {"current_steps": 4475, "total_steps": 6252, "loss": 0.4784, "lr": 9.331510977093077e-06, "epoch": 2.147357052858943, "percentage": 71.58, "elapsed_time": "2:06:54", "remaining_time": "0:50:23", "throughput": 6592.76, "total_tokens": 50202392} {"current_steps": 4480, "total_steps": 6252, "loss": 0.4473, "lr": 9.282615755118266e-06, "epoch": 2.149757004859903, "percentage": 71.66, "elapsed_time": "2:07:05", "remaining_time": "0:50:16", "throughput": 6591.39, "total_tokens": 50262048} {"current_steps": 4485, "total_steps": 6252, "loss": 0.4611, "lr": 9.23381974917622e-06, "epoch": 2.1521569568608627, "percentage": 71.74, "elapsed_time": "2:07:15", "remaining_time": "0:50:08", "throughput": 6589.71, "total_tokens": 50318512} {"current_steps": 4490, "total_steps": 6252, "loss": 0.4622, "lr": 9.185123267291881e-06, "epoch": 2.1545569088618226, "percentage": 71.82, "elapsed_time": "2:07:25", "remaining_time": "0:50:00", "throughput": 6588.1, "total_tokens": 50371472} {"current_steps": 4495, "total_steps": 6252, "loss": 0.501, "lr": 9.136526616861921e-06, "epoch": 2.156956860862783, "percentage": 71.9, "elapsed_time": "2:07:36", "remaining_time": "0:49:52", "throughput": 6586.26, "total_tokens": 50425888} {"current_steps": 4500, "total_steps": 6252, "loss": 0.4828, "lr": 9.088030104652829e-06, "epoch": 2.159356812863743, "percentage": 71.98, "elapsed_time": "2:07:46", "remaining_time": "0:49:44", "throughput": 6585.2, "total_tokens": 50484136} {"current_steps": 4505, "total_steps": 6252, "loss": 0.463, "lr": 9.03963403679899e-06, "epoch": 2.1617567648647027, "percentage": 72.06, "elapsed_time": "2:07:56", "remaining_time": "0:49:37", "throughput": 6583.44, "total_tokens": 50540376} {"current_steps": 4510, "total_steps": 6252, "loss": 0.4948, "lr": 8.99133871880071e-06, "epoch": 2.1641567168656626, "percentage": 72.14, "elapsed_time": "2:08:06", "remaining_time": "0:49:29", "throughput": 6581.92, "total_tokens": 50594968} {"current_steps": 4515, "total_steps": 6252, "loss": 0.4919, "lr": 8.943144455522314e-06, "epoch": 2.1665566688666225, "percentage": 72.22, "elapsed_time": "2:08:17", "remaining_time": "0:49:21", "throughput": 6580.11, "total_tokens": 50649296} {"current_steps": 4520, "total_steps": 6252, "loss": 0.4279, "lr": 8.895051551190248e-06, "epoch": 2.168956620867583, "percentage": 72.3, "elapsed_time": "2:08:27", "remaining_time": "0:49:13", "throughput": 6578.59, "total_tokens": 50706696} {"current_steps": 4525, "total_steps": 6252, "loss": 0.4776, "lr": 8.847060309391084e-06, "epoch": 2.1713565728685427, "percentage": 72.38, "elapsed_time": "2:08:37", "remaining_time": "0:49:05", "throughput": 6577.15, "total_tokens": 50758984} {"current_steps": 4530, "total_steps": 6252, "loss": 0.4821, "lr": 8.799171033069695e-06, "epoch": 2.1737565248695025, "percentage": 72.46, "elapsed_time": "2:08:47", "remaining_time": "0:48:57", "throughput": 6575.84, "total_tokens": 50812536} {"current_steps": 4535, "total_steps": 6252, "loss": 0.4698, "lr": 8.75138402452725e-06, "epoch": 2.1761564768704624, "percentage": 72.54, "elapsed_time": "2:08:56", "remaining_time": "0:48:49", "throughput": 6574.6, "total_tokens": 50867192} {"current_steps": 4540, "total_steps": 6252, "loss": 0.4612, "lr": 8.7036995854194e-06, "epoch": 2.1785564288714228, "percentage": 72.62, "elapsed_time": "2:09:06", "remaining_time": "0:48:41", "throughput": 6574.09, "total_tokens": 50925384} {"current_steps": 4545, "total_steps": 6252, "loss": 0.4939, "lr": 8.656118016754292e-06, "epoch": 2.1809563808723826, "percentage": 72.7, "elapsed_time": "2:09:17", "remaining_time": "0:48:33", "throughput": 6572.41, "total_tokens": 50983216} {"current_steps": 4550, "total_steps": 6252, "loss": 0.5204, "lr": 8.608639618890702e-06, "epoch": 2.1833563328733425, "percentage": 72.78, "elapsed_time": "2:09:27", "remaining_time": "0:48:25", "throughput": 6570.83, "total_tokens": 51038664} {"current_steps": 4555, "total_steps": 6252, "loss": 0.4907, "lr": 8.561264691536172e-06, "epoch": 2.1857562848743024, "percentage": 72.86, "elapsed_time": "2:09:37", "remaining_time": "0:48:17", "throughput": 6570.01, "total_tokens": 51096648} {"current_steps": 4560, "total_steps": 6252, "loss": 0.5114, "lr": 8.51399353374506e-06, "epoch": 2.1881562368752627, "percentage": 72.94, "elapsed_time": "2:09:47", "remaining_time": "0:48:09", "throughput": 6568.84, "total_tokens": 51152456} {"current_steps": 4565, "total_steps": 6252, "loss": 0.4822, "lr": 8.466826443916667e-06, "epoch": 2.1905561888762226, "percentage": 73.02, "elapsed_time": "2:09:56", "remaining_time": "0:48:01", "throughput": 6568.17, "total_tokens": 51207840} {"current_steps": 4570, "total_steps": 6252, "loss": 0.4849, "lr": 8.4197637197934e-06, "epoch": 2.1929561408771825, "percentage": 73.1, "elapsed_time": "2:10:06", "remaining_time": "0:47:53", "throughput": 6566.84, "total_tokens": 51261448} {"current_steps": 4575, "total_steps": 6252, "loss": 0.467, "lr": 8.37280565845884e-06, "epoch": 2.1953560928781424, "percentage": 73.18, "elapsed_time": "2:10:16", "remaining_time": "0:47:45", "throughput": 6565.5, "total_tokens": 51317720} {"current_steps": 4580, "total_steps": 6252, "loss": 0.4851, "lr": 8.325952556335878e-06, "epoch": 2.1977560448791023, "percentage": 73.26, "elapsed_time": "2:10:25", "remaining_time": "0:47:36", "throughput": 6564.46, "total_tokens": 51372576} {"current_steps": 4585, "total_steps": 6252, "loss": 0.5434, "lr": 8.279204709184843e-06, "epoch": 2.2001559968800626, "percentage": 73.34, "elapsed_time": "2:10:35", "remaining_time": "0:47:28", "throughput": 6562.49, "total_tokens": 51422552} {"current_steps": 4590, "total_steps": 6252, "loss": 0.5217, "lr": 8.232562412101674e-06, "epoch": 2.2025559488810225, "percentage": 73.42, "elapsed_time": "2:10:46", "remaining_time": "0:47:21", "throughput": 6560.85, "total_tokens": 51477960} {"current_steps": 4595, "total_steps": 6252, "loss": 0.4839, "lr": 8.186025959515995e-06, "epoch": 2.2049559008819823, "percentage": 73.5, "elapsed_time": "2:10:56", "remaining_time": "0:47:13", "throughput": 6559.8, "total_tokens": 51537952} {"current_steps": 4600, "total_steps": 6252, "loss": 0.4497, "lr": 8.139595645189282e-06, "epoch": 2.2073558528829422, "percentage": 73.58, "elapsed_time": "2:11:06", "remaining_time": "0:47:05", "throughput": 6558.68, "total_tokens": 51592688} {"current_steps": 4605, "total_steps": 6252, "loss": 0.4774, "lr": 8.09327176221305e-06, "epoch": 2.209755804883902, "percentage": 73.66, "elapsed_time": "2:11:16", "remaining_time": "0:46:56", "throughput": 6557.25, "total_tokens": 51645280} {"current_steps": 4610, "total_steps": 6252, "loss": 0.5308, "lr": 8.047054603006931e-06, "epoch": 2.2121557568848624, "percentage": 73.74, "elapsed_time": "2:11:26", "remaining_time": "0:46:48", "throughput": 6555.48, "total_tokens": 51698536} {"current_steps": 4615, "total_steps": 6252, "loss": 0.4422, "lr": 8.000944459316864e-06, "epoch": 2.2145557088858223, "percentage": 73.82, "elapsed_time": "2:11:37", "remaining_time": "0:46:41", "throughput": 6553.63, "total_tokens": 51756256} {"current_steps": 4620, "total_steps": 6252, "loss": 0.5049, "lr": 7.954941622213272e-06, "epoch": 2.216955660886782, "percentage": 73.9, "elapsed_time": "2:11:47", "remaining_time": "0:46:33", "throughput": 6552.66, "total_tokens": 51813256} {"current_steps": 4625, "total_steps": 6252, "loss": 0.4541, "lr": 7.909046382089203e-06, "epoch": 2.219355612887742, "percentage": 73.98, "elapsed_time": "2:11:57", "remaining_time": "0:46:25", "throughput": 6551.16, "total_tokens": 51867560} {"current_steps": 4630, "total_steps": 6252, "loss": 0.4918, "lr": 7.863259028658485e-06, "epoch": 2.2217555648887024, "percentage": 74.06, "elapsed_time": "2:12:07", "remaining_time": "0:46:17", "throughput": 6549.68, "total_tokens": 51920280} {"current_steps": 4635, "total_steps": 6252, "loss": 0.4356, "lr": 7.817579850953904e-06, "epoch": 2.2241555168896623, "percentage": 74.14, "elapsed_time": "2:12:19", "remaining_time": "0:46:09", "throughput": 6546.86, "total_tokens": 51975984} {"current_steps": 4640, "total_steps": 6252, "loss": 0.5007, "lr": 7.77200913732542e-06, "epoch": 2.226555468890622, "percentage": 74.22, "elapsed_time": "2:12:28", "remaining_time": "0:46:01", "throughput": 6546.07, "total_tokens": 52031784} {"current_steps": 4645, "total_steps": 6252, "loss": 0.4482, "lr": 7.72654717543828e-06, "epoch": 2.228955420891582, "percentage": 74.3, "elapsed_time": "2:12:38", "remaining_time": "0:45:53", "throughput": 6544.6, "total_tokens": 52086728} {"current_steps": 4650, "total_steps": 6252, "loss": 0.4219, "lr": 7.681194252271242e-06, "epoch": 2.2313553728925424, "percentage": 74.38, "elapsed_time": "2:12:48", "remaining_time": "0:45:45", "throughput": 6543.86, "total_tokens": 52143544} {"current_steps": 4655, "total_steps": 6252, "loss": 0.4771, "lr": 7.635950654114782e-06, "epoch": 2.2337553248935023, "percentage": 74.46, "elapsed_time": "2:12:58", "remaining_time": "0:45:37", "throughput": 6542.87, "total_tokens": 52203016} {"current_steps": 4660, "total_steps": 6252, "loss": 0.4791, "lr": 7.5908166665692285e-06, "epoch": 2.236155276894462, "percentage": 74.54, "elapsed_time": "2:13:08", "remaining_time": "0:45:29", "throughput": 6541.76, "total_tokens": 52258320} {"current_steps": 4665, "total_steps": 6252, "loss": 0.4895, "lr": 7.545792574543003e-06, "epoch": 2.238555228895422, "percentage": 74.62, "elapsed_time": "2:13:18", "remaining_time": "0:45:21", "throughput": 6540.31, "total_tokens": 52313336} {"current_steps": 4670, "total_steps": 6252, "loss": 0.5019, "lr": 7.500878662250818e-06, "epoch": 2.240955180896382, "percentage": 74.7, "elapsed_time": "2:13:28", "remaining_time": "0:45:12", "throughput": 6538.97, "total_tokens": 52366728} {"current_steps": 4675, "total_steps": 6252, "loss": 0.4622, "lr": 7.456075213211883e-06, "epoch": 2.2433551328973422, "percentage": 74.78, "elapsed_time": "2:13:38", "remaining_time": "0:45:04", "throughput": 6537.51, "total_tokens": 52423136} {"current_steps": 4680, "total_steps": 6252, "loss": 0.4422, "lr": 7.411382510248091e-06, "epoch": 2.245755084898302, "percentage": 74.86, "elapsed_time": "2:13:48", "remaining_time": "0:44:56", "throughput": 6536.52, "total_tokens": 52480088} {"current_steps": 4685, "total_steps": 6252, "loss": 0.4774, "lr": 7.366800835482246e-06, "epoch": 2.248155036899262, "percentage": 74.94, "elapsed_time": "2:13:58", "remaining_time": "0:44:48", "throughput": 6535.94, "total_tokens": 52538696} {"current_steps": 4690, "total_steps": 6252, "loss": 0.4537, "lr": 7.3223304703363135e-06, "epoch": 2.250554988900222, "percentage": 75.02, "elapsed_time": "2:14:09", "remaining_time": "0:44:40", "throughput": 6534.21, "total_tokens": 52598800} {"current_steps": 4695, "total_steps": 6252, "loss": 0.4435, "lr": 7.277971695529592e-06, "epoch": 2.2529549409011818, "percentage": 75.1, "elapsed_time": "2:14:20", "remaining_time": "0:44:32", "throughput": 6533.03, "total_tokens": 52657280} {"current_steps": 4700, "total_steps": 6252, "loss": 0.455, "lr": 7.233724791076968e-06, "epoch": 2.255354892902142, "percentage": 75.18, "elapsed_time": "2:14:30", "remaining_time": "0:44:24", "throughput": 6532.0, "total_tokens": 52713952} {"current_steps": 4705, "total_steps": 6252, "loss": 0.4506, "lr": 7.189590036287167e-06, "epoch": 2.257754844903102, "percentage": 75.26, "elapsed_time": "2:14:40", "remaining_time": "0:44:16", "throughput": 6530.62, "total_tokens": 52772688} {"current_steps": 4710, "total_steps": 6252, "loss": 0.4944, "lr": 7.145567709760942e-06, "epoch": 2.260154796904062, "percentage": 75.34, "elapsed_time": "2:14:51", "remaining_time": "0:44:08", "throughput": 6529.3, "total_tokens": 52829984} {"current_steps": 4715, "total_steps": 6252, "loss": 0.485, "lr": 7.1016580893893514e-06, "epoch": 2.2625547489050217, "percentage": 75.42, "elapsed_time": "2:15:02", "remaining_time": "0:44:01", "throughput": 6527.49, "total_tokens": 52888368} {"current_steps": 4720, "total_steps": 6252, "loss": 0.4722, "lr": 7.057861452352005e-06, "epoch": 2.264954700905982, "percentage": 75.5, "elapsed_time": "2:15:12", "remaining_time": "0:43:53", "throughput": 6526.43, "total_tokens": 52945664} {"current_steps": 4725, "total_steps": 6252, "loss": 0.5043, "lr": 7.014178075115305e-06, "epoch": 2.267354652906942, "percentage": 75.58, "elapsed_time": "2:15:22", "remaining_time": "0:43:44", "throughput": 6525.24, "total_tokens": 53001096} {"current_steps": 4730, "total_steps": 6252, "loss": 0.4978, "lr": 6.9706082334306895e-06, "epoch": 2.269754604907902, "percentage": 75.66, "elapsed_time": "2:15:32", "remaining_time": "0:43:36", "throughput": 6524.04, "total_tokens": 53054936} {"current_steps": 4735, "total_steps": 6252, "loss": 0.4493, "lr": 6.927152202332898e-06, "epoch": 2.2721545569088617, "percentage": 75.74, "elapsed_time": "2:15:42", "remaining_time": "0:43:28", "throughput": 6523.16, "total_tokens": 53115032} {"current_steps": 4740, "total_steps": 6252, "loss": 0.5082, "lr": 6.883810256138268e-06, "epoch": 2.274554508909822, "percentage": 75.82, "elapsed_time": "2:15:52", "remaining_time": "0:43:20", "throughput": 6521.82, "total_tokens": 53168048} {"current_steps": 4745, "total_steps": 6252, "loss": 0.4622, "lr": 6.8405826684429495e-06, "epoch": 2.276954460910782, "percentage": 75.9, "elapsed_time": "2:16:03", "remaining_time": "0:43:12", "throughput": 6520.39, "total_tokens": 53228112} {"current_steps": 4750, "total_steps": 6252, "loss": 0.475, "lr": 6.7974697121212044e-06, "epoch": 2.279354412911742, "percentage": 75.98, "elapsed_time": "2:16:12", "remaining_time": "0:43:04", "throughput": 6519.59, "total_tokens": 53282056} {"current_steps": 4755, "total_steps": 6252, "loss": 0.4444, "lr": 6.754471659323708e-06, "epoch": 2.2817543649127017, "percentage": 76.06, "elapsed_time": "2:16:21", "remaining_time": "0:42:55", "throughput": 6519.75, "total_tokens": 53342728} {"current_steps": 4760, "total_steps": 6252, "loss": 0.4833, "lr": 6.711588781475786e-06, "epoch": 2.2841543169136616, "percentage": 76.14, "elapsed_time": "2:16:29", "remaining_time": "0:42:47", "throughput": 6520.0, "total_tokens": 53397656} {"current_steps": 4765, "total_steps": 6252, "loss": 0.4532, "lr": 6.668821349275714e-06, "epoch": 2.286554268914622, "percentage": 76.22, "elapsed_time": "2:16:38", "remaining_time": "0:42:38", "throughput": 6519.93, "total_tokens": 53452736} {"current_steps": 4770, "total_steps": 6252, "loss": 0.4679, "lr": 6.626169632693041e-06, "epoch": 2.2889542209155818, "percentage": 76.3, "elapsed_time": "2:16:46", "remaining_time": "0:42:29", "throughput": 6520.13, "total_tokens": 53510640} {"current_steps": 4775, "total_steps": 6252, "loss": 0.4336, "lr": 6.5836339009668564e-06, "epoch": 2.2913541729165416, "percentage": 76.38, "elapsed_time": "2:16:56", "remaining_time": "0:42:21", "throughput": 6519.86, "total_tokens": 53568536} {"current_steps": 4780, "total_steps": 6252, "loss": 0.4903, "lr": 6.541214422604078e-06, "epoch": 2.2937541249175015, "percentage": 76.46, "elapsed_time": "2:17:04", "remaining_time": "0:42:12", "throughput": 6519.99, "total_tokens": 53623272} {"current_steps": 4785, "total_steps": 6252, "loss": 0.4665, "lr": 6.49891146537778e-06, "epoch": 2.2961540769184614, "percentage": 76.54, "elapsed_time": "2:17:13", "remaining_time": "0:42:04", "throughput": 6520.14, "total_tokens": 53680840} {"current_steps": 4790, "total_steps": 6252, "loss": 0.4648, "lr": 6.456725296325511e-06, "epoch": 2.2985540289194217, "percentage": 76.62, "elapsed_time": "2:17:21", "remaining_time": "0:41:55", "throughput": 6520.1, "total_tokens": 53736888} {"current_steps": 4795, "total_steps": 6252, "loss": 0.4426, "lr": 6.414656181747578e-06, "epoch": 2.3009539809203816, "percentage": 76.7, "elapsed_time": "2:17:30", "remaining_time": "0:41:46", "throughput": 6520.23, "total_tokens": 53793888} {"current_steps": 4800, "total_steps": 6252, "loss": 0.4942, "lr": 6.3727043872053775e-06, "epoch": 2.3033539329213415, "percentage": 76.78, "elapsed_time": "2:17:39", "remaining_time": "0:41:38", "throughput": 6520.31, "total_tokens": 53853120} {"current_steps": 4805, "total_steps": 6252, "loss": 0.4601, "lr": 6.330870177519749e-06, "epoch": 2.3057538849223014, "percentage": 76.86, "elapsed_time": "2:17:47", "remaining_time": "0:41:29", "throughput": 6520.48, "total_tokens": 53911008} {"current_steps": 4810, "total_steps": 6252, "loss": 0.4975, "lr": 6.2891538167692525e-06, "epoch": 2.3081538369232617, "percentage": 76.94, "elapsed_time": "2:17:56", "remaining_time": "0:41:21", "throughput": 6520.9, "total_tokens": 53970856} {"current_steps": 4815, "total_steps": 6252, "loss": 0.5108, "lr": 6.247555568288524e-06, "epoch": 2.3105537889242216, "percentage": 77.02, "elapsed_time": "2:18:04", "remaining_time": "0:41:12", "throughput": 6520.97, "total_tokens": 54024760} {"current_steps": 4820, "total_steps": 6252, "loss": 0.4972, "lr": 6.2060756946666385e-06, "epoch": 2.3129537409251815, "percentage": 77.1, "elapsed_time": "2:18:13", "remaining_time": "0:41:03", "throughput": 6520.85, "total_tokens": 54079992} {"current_steps": 4825, "total_steps": 6252, "loss": 0.4765, "lr": 6.164714457745416e-06, "epoch": 2.3153536929261413, "percentage": 77.18, "elapsed_time": "2:18:21", "remaining_time": "0:40:55", "throughput": 6520.99, "total_tokens": 54137056} {"current_steps": 4830, "total_steps": 6252, "loss": 0.502, "lr": 6.123472118617779e-06, "epoch": 2.3177536449271017, "percentage": 77.26, "elapsed_time": "2:18:29", "remaining_time": "0:40:46", "throughput": 6520.87, "total_tokens": 54187216} {"current_steps": 4835, "total_steps": 6252, "loss": 0.5223, "lr": 6.082348937626103e-06, "epoch": 2.3201535969280616, "percentage": 77.34, "elapsed_time": "2:18:38", "remaining_time": "0:40:37", "throughput": 6520.94, "total_tokens": 54243408} {"current_steps": 4840, "total_steps": 6252, "loss": 0.4379, "lr": 6.041345174360602e-06, "epoch": 2.3225535489290214, "percentage": 77.42, "elapsed_time": "2:18:47", "remaining_time": "0:40:29", "throughput": 6521.06, "total_tokens": 54300888} {"current_steps": 4845, "total_steps": 6252, "loss": 0.425, "lr": 6.0004610876576385e-06, "epoch": 2.3249535009299813, "percentage": 77.5, "elapsed_time": "2:18:55", "remaining_time": "0:40:20", "throughput": 6521.14, "total_tokens": 54359080} {"current_steps": 4850, "total_steps": 6252, "loss": 0.4783, "lr": 5.9596969355981165e-06, "epoch": 2.327353452930941, "percentage": 77.58, "elapsed_time": "2:19:03", "remaining_time": "0:40:11", "throughput": 6521.61, "total_tokens": 54414784} {"current_steps": 4855, "total_steps": 6252, "loss": 0.4625, "lr": 5.9190529755058786e-06, "epoch": 2.3297534049319015, "percentage": 77.66, "elapsed_time": "2:19:12", "remaining_time": "0:40:03", "throughput": 6521.04, "total_tokens": 54469544} {"current_steps": 4860, "total_steps": 6252, "loss": 0.4517, "lr": 5.878529463946028e-06, "epoch": 2.3321533569328614, "percentage": 77.74, "elapsed_time": "2:19:22", "remaining_time": "0:39:55", "throughput": 6520.43, "total_tokens": 54525088} {"current_steps": 4865, "total_steps": 6252, "loss": 0.4848, "lr": 5.838126656723353e-06, "epoch": 2.3345533089338213, "percentage": 77.82, "elapsed_time": "2:19:32", "remaining_time": "0:39:46", "throughput": 6519.27, "total_tokens": 54581656} {"current_steps": 4870, "total_steps": 6252, "loss": 0.4535, "lr": 5.797844808880681e-06, "epoch": 2.336953260934781, "percentage": 77.9, "elapsed_time": "2:19:41", "remaining_time": "0:39:38", "throughput": 6518.14, "total_tokens": 54633656} {"current_steps": 4875, "total_steps": 6252, "loss": 0.5149, "lr": 5.757684174697306e-06, "epoch": 2.339353212935741, "percentage": 77.98, "elapsed_time": "2:19:52", "remaining_time": "0:39:30", "throughput": 6516.62, "total_tokens": 54688552} {"current_steps": 4880, "total_steps": 6252, "loss": 0.4811, "lr": 5.717645007687333e-06, "epoch": 2.3417531649367014, "percentage": 78.06, "elapsed_time": "2:20:01", "remaining_time": "0:39:22", "throughput": 6516.1, "total_tokens": 54745736} {"current_steps": 4885, "total_steps": 6252, "loss": 0.4531, "lr": 5.677727560598117e-06, "epoch": 2.3441531169376613, "percentage": 78.13, "elapsed_time": "2:20:11", "remaining_time": "0:39:13", "throughput": 6514.75, "total_tokens": 54801056} {"current_steps": 4890, "total_steps": 6252, "loss": 0.428, "lr": 5.637932085408665e-06, "epoch": 2.346553068938621, "percentage": 78.21, "elapsed_time": "2:20:22", "remaining_time": "0:39:05", "throughput": 6513.86, "total_tokens": 54862792} {"current_steps": 4895, "total_steps": 6252, "loss": 0.5082, "lr": 5.598258833328024e-06, "epoch": 2.348953020939581, "percentage": 78.29, "elapsed_time": "2:20:32", "remaining_time": "0:38:57", "throughput": 6512.6, "total_tokens": 54917120} {"current_steps": 4900, "total_steps": 6252, "loss": 0.4747, "lr": 5.558708054793702e-06, "epoch": 2.3513529729405414, "percentage": 78.37, "elapsed_time": "2:20:42", "remaining_time": "0:38:49", "throughput": 6511.28, "total_tokens": 54970952} {"current_steps": 4905, "total_steps": 6252, "loss": 0.4653, "lr": 5.519279999470114e-06, "epoch": 2.3537529249415012, "percentage": 78.45, "elapsed_time": "2:20:53", "remaining_time": "0:38:41", "throughput": 6509.96, "total_tokens": 55030344} {"current_steps": 4910, "total_steps": 6252, "loss": 0.4505, "lr": 5.47997491624696e-06, "epoch": 2.356152876942461, "percentage": 78.53, "elapsed_time": "2:21:03", "remaining_time": "0:38:33", "throughput": 6508.84, "total_tokens": 55089240} {"current_steps": 4915, "total_steps": 6252, "loss": 0.4951, "lr": 5.440793053237703e-06, "epoch": 2.358552828943421, "percentage": 78.61, "elapsed_time": "2:21:12", "remaining_time": "0:38:24", "throughput": 6508.72, "total_tokens": 55145288} {"current_steps": 4920, "total_steps": 6252, "loss": 0.4555, "lr": 5.401734657777949e-06, "epoch": 2.3609527809443813, "percentage": 78.69, "elapsed_time": "2:21:21", "remaining_time": "0:38:16", "throughput": 6508.29, "total_tokens": 55202104} {"current_steps": 4925, "total_steps": 6252, "loss": 0.4936, "lr": 5.362799976423946e-06, "epoch": 2.363352732945341, "percentage": 78.77, "elapsed_time": "2:21:30", "remaining_time": "0:38:07", "throughput": 6508.17, "total_tokens": 55259704} {"current_steps": 4930, "total_steps": 6252, "loss": 0.4645, "lr": 5.323989254950973e-06, "epoch": 2.365752684946301, "percentage": 78.85, "elapsed_time": "2:21:39", "remaining_time": "0:37:59", "throughput": 6507.99, "total_tokens": 55317744} {"current_steps": 4935, "total_steps": 6252, "loss": 0.4797, "lr": 5.285302738351813e-06, "epoch": 2.368152636947261, "percentage": 78.93, "elapsed_time": "2:21:47", "remaining_time": "0:37:50", "throughput": 6508.44, "total_tokens": 55372296} {"current_steps": 4940, "total_steps": 6252, "loss": 0.4606, "lr": 5.246740670835227e-06, "epoch": 2.370552588948221, "percentage": 79.01, "elapsed_time": "2:21:57", "remaining_time": "0:37:42", "throughput": 6508.42, "total_tokens": 55433904} {"current_steps": 4945, "total_steps": 6252, "loss": 0.4901, "lr": 5.208303295824368e-06, "epoch": 2.372952540949181, "percentage": 79.09, "elapsed_time": "2:22:05", "remaining_time": "0:37:33", "throughput": 6508.5, "total_tokens": 55489480} {"current_steps": 4950, "total_steps": 6252, "loss": 0.4489, "lr": 5.16999085595527e-06, "epoch": 2.375352492950141, "percentage": 79.17, "elapsed_time": "2:22:14", "remaining_time": "0:37:24", "throughput": 6508.69, "total_tokens": 55548432} {"current_steps": 4955, "total_steps": 6252, "loss": 0.4751, "lr": 5.1318035930753295e-06, "epoch": 2.377752444951101, "percentage": 79.25, "elapsed_time": "2:22:24", "remaining_time": "0:37:16", "throughput": 6508.01, "total_tokens": 55606952} {"current_steps": 4960, "total_steps": 6252, "loss": 0.4716, "lr": 5.09374174824174e-06, "epoch": 2.380152396952061, "percentage": 79.33, "elapsed_time": "2:22:33", "remaining_time": "0:37:08", "throughput": 6507.96, "total_tokens": 55665912} {"current_steps": 4965, "total_steps": 6252, "loss": 0.4208, "lr": 5.0558055617200205e-06, "epoch": 2.3825523489530207, "percentage": 79.41, "elapsed_time": "2:22:41", "remaining_time": "0:36:59", "throughput": 6508.27, "total_tokens": 55719624} {"current_steps": 4970, "total_steps": 6252, "loss": 0.4832, "lr": 5.0179952729824395e-06, "epoch": 2.384952300953981, "percentage": 79.49, "elapsed_time": "2:22:50", "remaining_time": "0:36:50", "throughput": 6508.08, "total_tokens": 55774472} {"current_steps": 4975, "total_steps": 6252, "loss": 0.5135, "lr": 4.980311120706569e-06, "epoch": 2.387352252954941, "percentage": 79.57, "elapsed_time": "2:22:58", "remaining_time": "0:36:41", "throughput": 6508.07, "total_tokens": 55826392} {"current_steps": 4980, "total_steps": 6252, "loss": 0.5443, "lr": 4.942753342773718e-06, "epoch": 2.389752204955901, "percentage": 79.65, "elapsed_time": "2:23:06", "remaining_time": "0:36:33", "throughput": 6508.15, "total_tokens": 55880968} {"current_steps": 4985, "total_steps": 6252, "loss": 0.4719, "lr": 4.90532217626746e-06, "epoch": 2.3921521569568607, "percentage": 79.73, "elapsed_time": "2:23:14", "remaining_time": "0:36:24", "throughput": 6507.81, "total_tokens": 55933504} {"current_steps": 4990, "total_steps": 6252, "loss": 0.4971, "lr": 4.868017857472157e-06, "epoch": 2.394552108957821, "percentage": 79.81, "elapsed_time": "2:23:22", "remaining_time": "0:36:15", "throughput": 6507.84, "total_tokens": 55986736} {"current_steps": 4995, "total_steps": 6252, "loss": 0.471, "lr": 4.830840621871416e-06, "epoch": 2.396952060958781, "percentage": 79.89, "elapsed_time": "2:23:32", "remaining_time": "0:36:07", "throughput": 6507.25, "total_tokens": 56042472} {"current_steps": 5000, "total_steps": 6252, "loss": 0.5096, "lr": 4.793790704146639e-06, "epoch": 2.3993520129597408, "percentage": 79.97, "elapsed_time": "2:23:40", "remaining_time": "0:35:58", "throughput": 6507.04, "total_tokens": 56094608} {"current_steps": 5005, "total_steps": 6252, "loss": 0.4545, "lr": 4.756868338175552e-06, "epoch": 2.4017519649607006, "percentage": 80.05, "elapsed_time": "2:23:48", "remaining_time": "0:35:49", "throughput": 6507.51, "total_tokens": 56152192} {"current_steps": 5010, "total_steps": 6252, "loss": 0.482, "lr": 4.7200737570306765e-06, "epoch": 2.404151916961661, "percentage": 80.13, "elapsed_time": "2:23:57", "remaining_time": "0:35:41", "throughput": 6507.75, "total_tokens": 56209072} {"current_steps": 5015, "total_steps": 6252, "loss": 0.4701, "lr": 4.683407192977923e-06, "epoch": 2.406551868962621, "percentage": 80.21, "elapsed_time": "2:24:05", "remaining_time": "0:35:32", "throughput": 6507.83, "total_tokens": 56265496} {"current_steps": 5020, "total_steps": 6252, "loss": 0.4906, "lr": 4.646868877475083e-06, "epoch": 2.4089518209635807, "percentage": 80.29, "elapsed_time": "2:24:14", "remaining_time": "0:35:24", "throughput": 6507.89, "total_tokens": 56324336} {"current_steps": 5025, "total_steps": 6252, "loss": 0.4497, "lr": 4.610459041170376e-06, "epoch": 2.4113517729645406, "percentage": 80.37, "elapsed_time": "2:24:24", "remaining_time": "0:35:15", "throughput": 6508.09, "total_tokens": 56387160} {"current_steps": 5030, "total_steps": 6252, "loss": 0.4473, "lr": 4.574177913900992e-06, "epoch": 2.4137517249655005, "percentage": 80.45, "elapsed_time": "2:24:32", "remaining_time": "0:35:06", "throughput": 6508.93, "total_tokens": 56450040} {"current_steps": 5035, "total_steps": 6252, "loss": 0.5403, "lr": 4.538025724691647e-06, "epoch": 2.416151676966461, "percentage": 80.53, "elapsed_time": "2:24:40", "remaining_time": "0:34:58", "throughput": 6509.66, "total_tokens": 56509192} {"current_steps": 5040, "total_steps": 6252, "loss": 0.4535, "lr": 4.502002701753149e-06, "epoch": 2.4185516289674207, "percentage": 80.61, "elapsed_time": "2:24:49", "remaining_time": "0:34:49", "throughput": 6509.69, "total_tokens": 56564168} {"current_steps": 5045, "total_steps": 6252, "loss": 0.4666, "lr": 4.4661090724809286e-06, "epoch": 2.4209515809683806, "percentage": 80.69, "elapsed_time": "2:24:57", "remaining_time": "0:34:40", "throughput": 6509.56, "total_tokens": 56619720} {"current_steps": 5050, "total_steps": 6252, "loss": 0.4685, "lr": 4.430345063453614e-06, "epoch": 2.4233515329693405, "percentage": 80.77, "elapsed_time": "2:25:06", "remaining_time": "0:34:32", "throughput": 6509.06, "total_tokens": 56674064} {"current_steps": 5055, "total_steps": 6252, "loss": 0.5077, "lr": 4.394710900431628e-06, "epoch": 2.4257514849703004, "percentage": 80.85, "elapsed_time": "2:25:15", "remaining_time": "0:34:23", "throughput": 6509.01, "total_tokens": 56730176} {"current_steps": 5060, "total_steps": 6252, "loss": 0.4711, "lr": 4.359206808355715e-06, "epoch": 2.4281514369712607, "percentage": 80.93, "elapsed_time": "2:25:24", "remaining_time": "0:34:15", "throughput": 6509.17, "total_tokens": 56786912} {"current_steps": 5065, "total_steps": 6252, "loss": 0.468, "lr": 4.32383301134556e-06, "epoch": 2.4305513889722206, "percentage": 81.01, "elapsed_time": "2:25:33", "remaining_time": "0:34:06", "throughput": 6509.35, "total_tokens": 56846864} {"current_steps": 5070, "total_steps": 6252, "loss": 0.4722, "lr": 4.288589732698365e-06, "epoch": 2.4329513409731804, "percentage": 81.09, "elapsed_time": "2:25:41", "remaining_time": "0:33:58", "throughput": 6509.43, "total_tokens": 56903624} {"current_steps": 5075, "total_steps": 6252, "loss": 0.4879, "lr": 4.253477194887423e-06, "epoch": 2.4353512929741403, "percentage": 81.17, "elapsed_time": "2:25:50", "remaining_time": "0:33:49", "throughput": 6509.24, "total_tokens": 56961168} {"current_steps": 5080, "total_steps": 6252, "loss": 0.4762, "lr": 4.218495619560725e-06, "epoch": 2.4377512449751007, "percentage": 81.25, "elapsed_time": "2:25:59", "remaining_time": "0:33:40", "throughput": 6509.32, "total_tokens": 57017760} {"current_steps": 5085, "total_steps": 6252, "loss": 0.4934, "lr": 4.1836452275395624e-06, "epoch": 2.4401511969760605, "percentage": 81.33, "elapsed_time": "2:26:08", "remaining_time": "0:33:32", "throughput": 6509.19, "total_tokens": 57072760} {"current_steps": 5090, "total_steps": 6252, "loss": 0.4518, "lr": 4.148926238817141e-06, "epoch": 2.4425511489770204, "percentage": 81.41, "elapsed_time": "2:26:16", "remaining_time": "0:33:23", "throughput": 6509.47, "total_tokens": 57128592} {"current_steps": 5095, "total_steps": 6252, "loss": 0.4542, "lr": 4.114338872557175e-06, "epoch": 2.4449511009779803, "percentage": 81.49, "elapsed_time": "2:26:24", "remaining_time": "0:33:14", "throughput": 6509.54, "total_tokens": 57184720} {"current_steps": 5100, "total_steps": 6252, "loss": 0.4811, "lr": 4.079883347092506e-06, "epoch": 2.4473510529789406, "percentage": 81.57, "elapsed_time": "2:26:34", "remaining_time": "0:33:06", "throughput": 6509.88, "total_tokens": 57248888} {"current_steps": 5105, "total_steps": 6252, "loss": 0.454, "lr": 4.045559879923747e-06, "epoch": 2.4497510049799005, "percentage": 81.65, "elapsed_time": "2:26:42", "remaining_time": "0:32:57", "throughput": 6510.05, "total_tokens": 57307744} {"current_steps": 5110, "total_steps": 6252, "loss": 0.4506, "lr": 4.011368687717867e-06, "epoch": 2.4521509569808604, "percentage": 81.73, "elapsed_time": "2:26:51", "remaining_time": "0:32:49", "throughput": 6510.4, "total_tokens": 57363824} {"current_steps": 5115, "total_steps": 6252, "loss": 0.4614, "lr": 3.977309986306874e-06, "epoch": 2.4545509089818203, "percentage": 81.81, "elapsed_time": "2:26:59", "remaining_time": "0:32:40", "throughput": 6510.85, "total_tokens": 57422952} {"current_steps": 5120, "total_steps": 6252, "loss": 0.5036, "lr": 3.943383990686425e-06, "epoch": 2.45695086098278, "percentage": 81.89, "elapsed_time": "2:27:07", "remaining_time": "0:32:31", "throughput": 6510.81, "total_tokens": 57475568} {"current_steps": 5125, "total_steps": 6252, "loss": 0.4741, "lr": 3.909590915014455e-06, "epoch": 2.4593508129837405, "percentage": 81.97, "elapsed_time": "2:27:16", "remaining_time": "0:32:23", "throughput": 6511.12, "total_tokens": 57533000} {"current_steps": 5130, "total_steps": 6252, "loss": 0.4555, "lr": 3.875930972609851e-06, "epoch": 2.4617507649847004, "percentage": 82.05, "elapsed_time": "2:27:24", "remaining_time": "0:32:14", "throughput": 6511.43, "total_tokens": 57591416} {"current_steps": 5135, "total_steps": 6252, "loss": 0.4948, "lr": 3.842404375951089e-06, "epoch": 2.4641507169856602, "percentage": 82.13, "elapsed_time": "2:27:33", "remaining_time": "0:32:05", "throughput": 6511.6, "total_tokens": 57648120} {"current_steps": 5140, "total_steps": 6252, "loss": 0.4747, "lr": 3.809011336674917e-06, "epoch": 2.46655066898662, "percentage": 82.21, "elapsed_time": "2:27:41", "remaining_time": "0:31:57", "throughput": 6511.64, "total_tokens": 57705096} {"current_steps": 5145, "total_steps": 6252, "loss": 0.4711, "lr": 3.7757520655749863e-06, "epoch": 2.46895062098758, "percentage": 82.29, "elapsed_time": "2:27:50", "remaining_time": "0:31:48", "throughput": 6511.52, "total_tokens": 57760000} {"current_steps": 5150, "total_steps": 6252, "loss": 0.4566, "lr": 3.7426267726005354e-06, "epoch": 2.4713505729885403, "percentage": 82.37, "elapsed_time": "2:27:59", "remaining_time": "0:31:39", "throughput": 6511.32, "total_tokens": 57814992} {"current_steps": 5155, "total_steps": 6252, "loss": 0.4552, "lr": 3.709635666855077e-06, "epoch": 2.4737505249895, "percentage": 82.45, "elapsed_time": "2:28:08", "remaining_time": "0:31:31", "throughput": 6511.03, "total_tokens": 57870400} {"current_steps": 5160, "total_steps": 6252, "loss": 0.425, "lr": 3.6767789565950563e-06, "epoch": 2.47615047699046, "percentage": 82.53, "elapsed_time": "2:28:16", "remaining_time": "0:31:22", "throughput": 6511.66, "total_tokens": 57932208} {"current_steps": 5165, "total_steps": 6252, "loss": 0.4413, "lr": 3.64405684922855e-06, "epoch": 2.4785504289914204, "percentage": 82.61, "elapsed_time": "2:28:24", "remaining_time": "0:31:14", "throughput": 6512.05, "total_tokens": 57989280} {"current_steps": 5170, "total_steps": 6252, "loss": 0.521, "lr": 3.611469551313959e-06, "epoch": 2.4809503809923803, "percentage": 82.69, "elapsed_time": "2:28:33", "remaining_time": "0:31:05", "throughput": 6512.37, "total_tokens": 58045968} {"current_steps": 5175, "total_steps": 6252, "loss": 0.4989, "lr": 3.579017268558693e-06, "epoch": 2.48335033299334, "percentage": 82.77, "elapsed_time": "2:28:40", "remaining_time": "0:30:56", "throughput": 6512.68, "total_tokens": 58098536} {"current_steps": 5180, "total_steps": 6252, "loss": 0.498, "lr": 3.5467002058178764e-06, "epoch": 2.4857502849943, "percentage": 82.85, "elapsed_time": "2:28:49", "remaining_time": "0:30:47", "throughput": 6512.5, "total_tokens": 58153656} {"current_steps": 5185, "total_steps": 6252, "loss": 0.4513, "lr": 3.514518567093056e-06, "epoch": 2.48815023699526, "percentage": 82.93, "elapsed_time": "2:28:58", "remaining_time": "0:30:39", "throughput": 6512.34, "total_tokens": 58208960} {"current_steps": 5190, "total_steps": 6252, "loss": 0.4757, "lr": 3.4824725555309272e-06, "epoch": 2.4905501889962203, "percentage": 83.01, "elapsed_time": "2:29:06", "remaining_time": "0:30:30", "throughput": 6513.0, "total_tokens": 58268880} {"current_steps": 5195, "total_steps": 6252, "loss": 0.4926, "lr": 3.4505623734220226e-06, "epoch": 2.49295014099718, "percentage": 83.09, "elapsed_time": "2:29:14", "remaining_time": "0:30:21", "throughput": 6513.4, "total_tokens": 58323184} {"current_steps": 5200, "total_steps": 6252, "loss": 0.5169, "lr": 3.4187882221994564e-06, "epoch": 2.49535009299814, "percentage": 83.17, "elapsed_time": "2:29:22", "remaining_time": "0:30:13", "throughput": 6513.53, "total_tokens": 58379592} {"current_steps": 5205, "total_steps": 6252, "loss": 0.4625, "lr": 3.3871503024376554e-06, "epoch": 2.4977500449991, "percentage": 83.25, "elapsed_time": "2:29:31", "remaining_time": "0:30:04", "throughput": 6514.07, "total_tokens": 58439472} {"current_steps": 5210, "total_steps": 6252, "loss": 0.4478, "lr": 3.3556488138510674e-06, "epoch": 2.50014999700006, "percentage": 83.33, "elapsed_time": "2:29:40", "remaining_time": "0:29:56", "throughput": 6514.3, "total_tokens": 58498776} {"current_steps": 5215, "total_steps": 6252, "loss": 0.4552, "lr": 3.3242839552929366e-06, "epoch": 2.50254994900102, "percentage": 83.41, "elapsed_time": "2:29:48", "remaining_time": "0:29:47", "throughput": 6514.71, "total_tokens": 58559344} {"current_steps": 5220, "total_steps": 6252, "loss": 0.4537, "lr": 3.2930559247540267e-06, "epoch": 2.50494990100198, "percentage": 83.49, "elapsed_time": "2:29:57", "remaining_time": "0:29:38", "throughput": 6514.38, "total_tokens": 58614416} {"current_steps": 5225, "total_steps": 6252, "loss": 0.5041, "lr": 3.2619649193613626e-06, "epoch": 2.50734985300294, "percentage": 83.57, "elapsed_time": "2:30:06", "remaining_time": "0:29:30", "throughput": 6514.1, "total_tokens": 58667216} {"current_steps": 5230, "total_steps": 6252, "loss": 0.5123, "lr": 3.2310111353770045e-06, "epoch": 2.5097498050038998, "percentage": 83.65, "elapsed_time": "2:30:14", "remaining_time": "0:29:21", "throughput": 6514.28, "total_tokens": 58722648} {"current_steps": 5235, "total_steps": 6252, "loss": 0.466, "lr": 3.2001947681967987e-06, "epoch": 2.5121497570048597, "percentage": 83.73, "elapsed_time": "2:30:23", "remaining_time": "0:29:13", "throughput": 6514.08, "total_tokens": 58780640} {"current_steps": 5240, "total_steps": 6252, "loss": 0.4855, "lr": 3.169516012349161e-06, "epoch": 2.51454970900582, "percentage": 83.81, "elapsed_time": "2:30:32", "remaining_time": "0:29:04", "throughput": 6513.92, "total_tokens": 58839080} {"current_steps": 5245, "total_steps": 6252, "loss": 0.5462, "lr": 3.138975061493815e-06, "epoch": 2.51694966100678, "percentage": 83.89, "elapsed_time": "2:30:41", "remaining_time": "0:28:55", "throughput": 6513.42, "total_tokens": 58888056} {"current_steps": 5250, "total_steps": 6252, "loss": 0.4879, "lr": 3.1085721084205987e-06, "epoch": 2.5193496130077397, "percentage": 83.97, "elapsed_time": "2:30:49", "remaining_time": "0:28:47", "throughput": 6513.8, "total_tokens": 58948912} {"current_steps": 5255, "total_steps": 6252, "loss": 0.434, "lr": 3.078307345048251e-06, "epoch": 2.5217495650087, "percentage": 84.05, "elapsed_time": "2:30:58", "remaining_time": "0:28:38", "throughput": 6513.94, "total_tokens": 59005656} {"current_steps": 5260, "total_steps": 6252, "loss": 0.4226, "lr": 3.0481809624231667e-06, "epoch": 2.52414951700966, "percentage": 84.13, "elapsed_time": "2:31:07", "remaining_time": "0:28:30", "throughput": 6514.14, "total_tokens": 59064880} {"current_steps": 5265, "total_steps": 6252, "loss": 0.4881, "lr": 3.018193150718224e-06, "epoch": 2.52654946901062, "percentage": 84.21, "elapsed_time": "2:31:15", "remaining_time": "0:28:21", "throughput": 6514.36, "total_tokens": 59122920} {"current_steps": 5270, "total_steps": 6252, "loss": 0.4949, "lr": 2.9883440992315744e-06, "epoch": 2.5289494210115797, "percentage": 84.29, "elapsed_time": "2:31:24", "remaining_time": "0:28:12", "throughput": 6514.73, "total_tokens": 59180768} {"current_steps": 5275, "total_steps": 6252, "loss": 0.4584, "lr": 2.9586339963854402e-06, "epoch": 2.5313493730125396, "percentage": 84.37, "elapsed_time": "2:31:33", "remaining_time": "0:28:04", "throughput": 6514.26, "total_tokens": 59236392} {"current_steps": 5280, "total_steps": 6252, "loss": 0.5001, "lr": 2.929063029724924e-06, "epoch": 2.5337493250135, "percentage": 84.45, "elapsed_time": "2:31:41", "remaining_time": "0:27:55", "throughput": 6514.31, "total_tokens": 59288152} {"current_steps": 5285, "total_steps": 6252, "loss": 0.4752, "lr": 2.8996313859168373e-06, "epoch": 2.53614927701446, "percentage": 84.53, "elapsed_time": "2:31:49", "remaining_time": "0:27:46", "throughput": 6515.14, "total_tokens": 59350448} {"current_steps": 5290, "total_steps": 6252, "loss": 0.5058, "lr": 2.8703392507485244e-06, "epoch": 2.5385492290154197, "percentage": 84.61, "elapsed_time": "2:31:58", "remaining_time": "0:27:38", "throughput": 6515.08, "total_tokens": 59405224} {"current_steps": 5295, "total_steps": 6252, "loss": 0.5101, "lr": 2.8411868091266614e-06, "epoch": 2.5409491810163796, "percentage": 84.69, "elapsed_time": "2:32:05", "remaining_time": "0:27:29", "throughput": 6515.59, "total_tokens": 59459408} {"current_steps": 5300, "total_steps": 6252, "loss": 0.4509, "lr": 2.812174245076121e-06, "epoch": 2.5433491330173394, "percentage": 84.77, "elapsed_time": "2:32:14", "remaining_time": "0:27:20", "throughput": 6515.96, "total_tokens": 59519864} {"current_steps": 5305, "total_steps": 6252, "loss": 0.5337, "lr": 2.783301741738803e-06, "epoch": 2.5457490850182998, "percentage": 84.85, "elapsed_time": "2:32:22", "remaining_time": "0:27:12", "throughput": 6516.33, "total_tokens": 59575648} {"current_steps": 5310, "total_steps": 6252, "loss": 0.4446, "lr": 2.75456948137246e-06, "epoch": 2.5481490370192597, "percentage": 84.93, "elapsed_time": "2:32:30", "remaining_time": "0:27:03", "throughput": 6516.53, "total_tokens": 59631568} {"current_steps": 5315, "total_steps": 6252, "loss": 0.4515, "lr": 2.725977645349567e-06, "epoch": 2.5505489890202195, "percentage": 85.01, "elapsed_time": "2:32:38", "remaining_time": "0:26:54", "throughput": 6517.05, "total_tokens": 59688168} {"current_steps": 5320, "total_steps": 6252, "loss": 0.4743, "lr": 2.6975264141561792e-06, "epoch": 2.5529489410211794, "percentage": 85.09, "elapsed_time": "2:32:47", "remaining_time": "0:26:46", "throughput": 6517.53, "total_tokens": 59750784} {"current_steps": 5325, "total_steps": 6252, "loss": 0.4835, "lr": 2.6692159673907674e-06, "epoch": 2.5553488930221393, "percentage": 85.17, "elapsed_time": "2:32:56", "remaining_time": "0:26:37", "throughput": 6517.18, "total_tokens": 59804776} {"current_steps": 5330, "total_steps": 6252, "loss": 0.4954, "lr": 2.641046483763107e-06, "epoch": 2.5577488450230996, "percentage": 85.25, "elapsed_time": "2:33:04", "remaining_time": "0:26:28", "throughput": 6517.49, "total_tokens": 59862336} {"current_steps": 5335, "total_steps": 6252, "loss": 0.5017, "lr": 2.613018141093143e-06, "epoch": 2.5601487970240595, "percentage": 85.33, "elapsed_time": "2:33:13", "remaining_time": "0:26:20", "throughput": 6517.43, "total_tokens": 59920072} {"current_steps": 5340, "total_steps": 6252, "loss": 0.4951, "lr": 2.585131116309872e-06, "epoch": 2.5625487490250194, "percentage": 85.41, "elapsed_time": "2:33:22", "remaining_time": "0:26:11", "throughput": 6517.58, "total_tokens": 59975568} {"current_steps": 5345, "total_steps": 6252, "loss": 0.4706, "lr": 2.557385585450217e-06, "epoch": 2.5649487010259797, "percentage": 85.49, "elapsed_time": "2:33:31", "remaining_time": "0:26:03", "throughput": 6517.8, "total_tokens": 60036392} {"current_steps": 5350, "total_steps": 6252, "loss": 0.4893, "lr": 2.529781723657915e-06, "epoch": 2.5673486530269396, "percentage": 85.57, "elapsed_time": "2:33:40", "remaining_time": "0:25:54", "throughput": 6517.61, "total_tokens": 60093024} {"current_steps": 5355, "total_steps": 6252, "loss": 0.5055, "lr": 2.5023197051824267e-06, "epoch": 2.5697486050278995, "percentage": 85.65, "elapsed_time": "2:33:48", "remaining_time": "0:25:45", "throughput": 6517.55, "total_tokens": 60144920} {"current_steps": 5360, "total_steps": 6252, "loss": 0.5167, "lr": 2.4749997033778228e-06, "epoch": 2.5721485570288594, "percentage": 85.73, "elapsed_time": "2:33:56", "remaining_time": "0:25:37", "throughput": 6517.95, "total_tokens": 60203224} {"current_steps": 5365, "total_steps": 6252, "loss": 0.4896, "lr": 2.4478218907016877e-06, "epoch": 2.5745485090298192, "percentage": 85.81, "elapsed_time": "2:34:05", "remaining_time": "0:25:28", "throughput": 6517.87, "total_tokens": 60259032} {"current_steps": 5370, "total_steps": 6252, "loss": 0.5132, "lr": 2.4207864387140512e-06, "epoch": 2.5769484610307796, "percentage": 85.89, "elapsed_time": "2:34:13", "remaining_time": "0:25:19", "throughput": 6517.14, "total_tokens": 60308024} {"current_steps": 5375, "total_steps": 6252, "loss": 0.5086, "lr": 2.3938935180762707e-06, "epoch": 2.5793484130317395, "percentage": 85.97, "elapsed_time": "2:34:21", "remaining_time": "0:25:11", "throughput": 6517.59, "total_tokens": 60362552} {"current_steps": 5380, "total_steps": 6252, "loss": 0.5001, "lr": 2.36714329854999e-06, "epoch": 2.5817483650326993, "percentage": 86.05, "elapsed_time": "2:34:29", "remaining_time": "0:25:02", "throughput": 6517.57, "total_tokens": 60415520} {"current_steps": 5385, "total_steps": 6252, "loss": 0.493, "lr": 2.3405359489960365e-06, "epoch": 2.584148317033659, "percentage": 86.13, "elapsed_time": "2:34:37", "remaining_time": "0:24:53", "throughput": 6517.92, "total_tokens": 60469016} {"current_steps": 5390, "total_steps": 6252, "loss": 0.537, "lr": 2.314071637373394e-06, "epoch": 2.586548269034619, "percentage": 86.21, "elapsed_time": "2:34:46", "remaining_time": "0:24:45", "throughput": 6517.8, "total_tokens": 60528736} {"current_steps": 5395, "total_steps": 6252, "loss": 0.5101, "lr": 2.2877505307380976e-06, "epoch": 2.5889482210355794, "percentage": 86.29, "elapsed_time": "2:34:54", "remaining_time": "0:24:36", "throughput": 6518.25, "total_tokens": 60585352} {"current_steps": 5400, "total_steps": 6252, "loss": 0.4426, "lr": 2.2615727952422033e-06, "epoch": 2.5913481730365393, "percentage": 86.37, "elapsed_time": "2:35:03", "remaining_time": "0:24:27", "throughput": 6518.55, "total_tokens": 60645192} {"current_steps": 5405, "total_steps": 6252, "loss": 0.4401, "lr": 2.235538596132747e-06, "epoch": 2.593748125037499, "percentage": 86.45, "elapsed_time": "2:35:14", "remaining_time": "0:24:19", "throughput": 6517.49, "total_tokens": 60705872} {"current_steps": 5410, "total_steps": 6252, "loss": 0.466, "lr": 2.2096480977506883e-06, "epoch": 2.596148077038459, "percentage": 86.53, "elapsed_time": "2:35:24", "remaining_time": "0:24:11", "throughput": 6516.75, "total_tokens": 60766448} {"current_steps": 5415, "total_steps": 6252, "loss": 0.4647, "lr": 2.183901463529861e-06, "epoch": 2.598548029039419, "percentage": 86.61, "elapsed_time": "2:35:35", "remaining_time": "0:24:02", "throughput": 6515.19, "total_tokens": 60820832} {"current_steps": 5420, "total_steps": 6252, "loss": 0.4435, "lr": 2.1582988559959773e-06, "epoch": 2.6009479810403793, "percentage": 86.69, "elapsed_time": "2:35:46", "remaining_time": "0:23:54", "throughput": 6513.84, "total_tokens": 60879048} {"current_steps": 5425, "total_steps": 6252, "loss": 0.4641, "lr": 2.132840436765568e-06, "epoch": 2.603347933041339, "percentage": 86.77, "elapsed_time": "2:35:55", "remaining_time": "0:23:46", "throughput": 6512.48, "total_tokens": 60927720} {"current_steps": 5430, "total_steps": 6252, "loss": 0.4677, "lr": 2.1075263665449737e-06, "epoch": 2.605747885042299, "percentage": 86.85, "elapsed_time": "2:36:05", "remaining_time": "0:23:37", "throughput": 6511.23, "total_tokens": 60981576} {"current_steps": 5435, "total_steps": 6252, "loss": 0.4929, "lr": 2.082356805129332e-06, "epoch": 2.6081478370432594, "percentage": 86.93, "elapsed_time": "2:36:16", "remaining_time": "0:23:29", "throughput": 6510.14, "total_tokens": 61039448} {"current_steps": 5440, "total_steps": 6252, "loss": 0.4886, "lr": 2.0573319114015775e-06, "epoch": 2.6105477890442192, "percentage": 87.01, "elapsed_time": "2:36:26", "remaining_time": "0:23:21", "throughput": 6508.85, "total_tokens": 61093640} {"current_steps": 5445, "total_steps": 6252, "loss": 0.4697, "lr": 2.0324518433314206e-06, "epoch": 2.612947741045179, "percentage": 87.09, "elapsed_time": "2:36:36", "remaining_time": "0:23:12", "throughput": 6507.77, "total_tokens": 61149808} {"current_steps": 5450, "total_steps": 6252, "loss": 0.4645, "lr": 2.0077167579743593e-06, "epoch": 2.615347693046139, "percentage": 87.17, "elapsed_time": "2:36:46", "remaining_time": "0:23:04", "throughput": 6506.8, "total_tokens": 61206176} {"current_steps": 5455, "total_steps": 6252, "loss": 0.4667, "lr": 1.9831268114706925e-06, "epoch": 2.617747645047099, "percentage": 87.25, "elapsed_time": "2:36:57", "remaining_time": "0:22:55", "throughput": 6505.86, "total_tokens": 61266712} {"current_steps": 5460, "total_steps": 6252, "loss": 0.4644, "lr": 1.958682159044531e-06, "epoch": 2.620147597048059, "percentage": 87.33, "elapsed_time": "2:37:06", "remaining_time": "0:22:47", "throughput": 6505.01, "total_tokens": 61319856} {"current_steps": 5465, "total_steps": 6252, "loss": 0.5007, "lr": 1.934382955002803e-06, "epoch": 2.622547549049019, "percentage": 87.41, "elapsed_time": "2:37:17", "remaining_time": "0:22:39", "throughput": 6503.74, "total_tokens": 61377048} {"current_steps": 5470, "total_steps": 6252, "loss": 0.4658, "lr": 1.9102293527343163e-06, "epoch": 2.624947501049979, "percentage": 87.49, "elapsed_time": "2:37:27", "remaining_time": "0:22:30", "throughput": 6502.4, "total_tokens": 61434248} {"current_steps": 5475, "total_steps": 6252, "loss": 0.4968, "lr": 1.886221504708746e-06, "epoch": 2.627347453050939, "percentage": 87.57, "elapsed_time": "2:37:38", "remaining_time": "0:22:22", "throughput": 6501.19, "total_tokens": 61494600} {"current_steps": 5480, "total_steps": 6252, "loss": 0.4606, "lr": 1.8623595624757045e-06, "epoch": 2.6297474050518987, "percentage": 87.65, "elapsed_time": "2:37:49", "remaining_time": "0:22:13", "throughput": 6500.51, "total_tokens": 61555232} {"current_steps": 5485, "total_steps": 6252, "loss": 0.4647, "lr": 1.8386436766637593e-06, "epoch": 2.632147357052859, "percentage": 87.73, "elapsed_time": "2:37:59", "remaining_time": "0:22:05", "throughput": 6499.51, "total_tokens": 61610480} {"current_steps": 5490, "total_steps": 6252, "loss": 0.4742, "lr": 1.8150739969795245e-06, "epoch": 2.634547309053819, "percentage": 87.81, "elapsed_time": "2:38:09", "remaining_time": "0:21:57", "throughput": 6498.75, "total_tokens": 61666936} {"current_steps": 5495, "total_steps": 6252, "loss": 0.5121, "lr": 1.7916506722066573e-06, "epoch": 2.636947261054779, "percentage": 87.89, "elapsed_time": "2:38:18", "remaining_time": "0:21:48", "throughput": 6498.37, "total_tokens": 61723152} {"current_steps": 5500, "total_steps": 6252, "loss": 0.5282, "lr": 1.7683738502049658e-06, "epoch": 2.639347213055739, "percentage": 87.97, "elapsed_time": "2:38:28", "remaining_time": "0:21:40", "throughput": 6497.43, "total_tokens": 61779792} {"current_steps": 5505, "total_steps": 6252, "loss": 0.5226, "lr": 1.7452436779094527e-06, "epoch": 2.6417471650566986, "percentage": 88.05, "elapsed_time": "2:38:38", "remaining_time": "0:21:31", "throughput": 6496.83, "total_tokens": 61837696} {"current_steps": 5510, "total_steps": 6252, "loss": 0.4645, "lr": 1.7222603013294036e-06, "epoch": 2.644147117057659, "percentage": 88.13, "elapsed_time": "2:38:48", "remaining_time": "0:21:23", "throughput": 6495.82, "total_tokens": 61896032} {"current_steps": 5515, "total_steps": 6252, "loss": 0.4943, "lr": 1.6994238655474394e-06, "epoch": 2.646547069058619, "percentage": 88.21, "elapsed_time": "2:38:58", "remaining_time": "0:21:14", "throughput": 6494.76, "total_tokens": 61949384} {"current_steps": 5520, "total_steps": 6252, "loss": 0.5109, "lr": 1.6767345147186336e-06, "epoch": 2.6489470210595787, "percentage": 88.29, "elapsed_time": "2:39:07", "remaining_time": "0:21:06", "throughput": 6493.83, "total_tokens": 62002592} {"current_steps": 5525, "total_steps": 6252, "loss": 0.4477, "lr": 1.6541923920695756e-06, "epoch": 2.651346973060539, "percentage": 88.37, "elapsed_time": "2:39:18", "remaining_time": "0:20:57", "throughput": 6492.31, "total_tokens": 62055040} {"current_steps": 5530, "total_steps": 6252, "loss": 0.5174, "lr": 1.6317976398974782e-06, "epoch": 2.653746925061499, "percentage": 88.45, "elapsed_time": "2:39:27", "remaining_time": "0:20:49", "throughput": 6491.56, "total_tokens": 62109976} {"current_steps": 5535, "total_steps": 6252, "loss": 0.4668, "lr": 1.6095503995692762e-06, "epoch": 2.6561468770624588, "percentage": 88.53, "elapsed_time": "2:39:37", "remaining_time": "0:20:40", "throughput": 6491.03, "total_tokens": 62167376} {"current_steps": 5540, "total_steps": 6252, "loss": 0.4676, "lr": 1.5874508115207408e-06, "epoch": 2.6585468290634187, "percentage": 88.61, "elapsed_time": "2:39:47", "remaining_time": "0:20:32", "throughput": 6489.62, "total_tokens": 62221488} {"current_steps": 5545, "total_steps": 6252, "loss": 0.4947, "lr": 1.5654990152555837e-06, "epoch": 2.6609467810643785, "percentage": 88.69, "elapsed_time": "2:39:57", "remaining_time": "0:20:23", "throughput": 6488.63, "total_tokens": 62277176} {"current_steps": 5550, "total_steps": 6252, "loss": 0.4875, "lr": 1.5436951493445762e-06, "epoch": 2.663346733065339, "percentage": 88.77, "elapsed_time": "2:40:07", "remaining_time": "0:20:15", "throughput": 6487.75, "total_tokens": 62330544} {"current_steps": 5555, "total_steps": 6252, "loss": 0.5035, "lr": 1.5220393514246895e-06, "epoch": 2.6657466850662987, "percentage": 88.85, "elapsed_time": "2:40:16", "remaining_time": "0:20:06", "throughput": 6486.78, "total_tokens": 62381768} {"current_steps": 5560, "total_steps": 6252, "loss": 0.4839, "lr": 1.5005317581982092e-06, "epoch": 2.6681466370672586, "percentage": 88.93, "elapsed_time": "2:40:26", "remaining_time": "0:19:58", "throughput": 6485.92, "total_tokens": 62436944} {"current_steps": 5565, "total_steps": 6252, "loss": 0.4973, "lr": 1.479172505431875e-06, "epoch": 2.6705465890682185, "percentage": 89.01, "elapsed_time": "2:40:36", "remaining_time": "0:19:49", "throughput": 6484.96, "total_tokens": 62491352} {"current_steps": 5570, "total_steps": 6252, "loss": 0.486, "lr": 1.4579617279560393e-06, "epoch": 2.6729465410691784, "percentage": 89.09, "elapsed_time": "2:40:46", "remaining_time": "0:19:41", "throughput": 6484.18, "total_tokens": 62546464} {"current_steps": 5575, "total_steps": 6252, "loss": 0.4729, "lr": 1.4368995596637902e-06, "epoch": 2.6753464930701387, "percentage": 89.17, "elapsed_time": "2:40:56", "remaining_time": "0:19:32", "throughput": 6482.68, "total_tokens": 62602496} {"current_steps": 5580, "total_steps": 6252, "loss": 0.4894, "lr": 1.415986133510122e-06, "epoch": 2.6777464450710986, "percentage": 89.25, "elapsed_time": "2:41:08", "remaining_time": "0:19:24", "throughput": 6481.42, "total_tokens": 62664360} {"current_steps": 5585, "total_steps": 6252, "loss": 0.4524, "lr": 1.395221581511097e-06, "epoch": 2.6801463970720585, "percentage": 89.33, "elapsed_time": "2:41:18", "remaining_time": "0:19:15", "throughput": 6480.74, "total_tokens": 62721848} {"current_steps": 5590, "total_steps": 6252, "loss": 0.4765, "lr": 1.3746060347430118e-06, "epoch": 2.682546349073019, "percentage": 89.41, "elapsed_time": "2:41:27", "remaining_time": "0:19:07", "throughput": 6479.97, "total_tokens": 62776544} {"current_steps": 5595, "total_steps": 6252, "loss": 0.4656, "lr": 1.354139623341566e-06, "epoch": 2.6849463010739782, "percentage": 89.49, "elapsed_time": "2:41:38", "remaining_time": "0:18:58", "throughput": 6478.81, "total_tokens": 62834048} {"current_steps": 5600, "total_steps": 6252, "loss": 0.4573, "lr": 1.3338224765010315e-06, "epoch": 2.6873462530749386, "percentage": 89.57, "elapsed_time": "2:41:49", "remaining_time": "0:18:50", "throughput": 6477.47, "total_tokens": 62894360} {"current_steps": 5605, "total_steps": 6252, "loss": 0.4944, "lr": 1.3136547224734646e-06, "epoch": 2.6897462050758985, "percentage": 89.65, "elapsed_time": "2:42:00", "remaining_time": "0:18:42", "throughput": 6476.13, "total_tokens": 62952560} {"current_steps": 5610, "total_steps": 6252, "loss": 0.4829, "lr": 1.2936364885678676e-06, "epoch": 2.6921461570768583, "percentage": 89.73, "elapsed_time": "2:42:09", "remaining_time": "0:18:33", "throughput": 6475.6, "total_tokens": 63006360} {"current_steps": 5615, "total_steps": 6252, "loss": 0.4819, "lr": 1.2737679011493947e-06, "epoch": 2.6945461090778187, "percentage": 89.81, "elapsed_time": "2:42:20", "remaining_time": "0:18:24", "throughput": 6474.74, "total_tokens": 63065920} {"current_steps": 5620, "total_steps": 6252, "loss": 0.4717, "lr": 1.2540490856385672e-06, "epoch": 2.6969460610787785, "percentage": 89.89, "elapsed_time": "2:42:31", "remaining_time": "0:18:16", "throughput": 6473.26, "total_tokens": 63121320} {"current_steps": 5625, "total_steps": 6252, "loss": 0.462, "lr": 1.23448016651046e-06, "epoch": 2.6993460130797384, "percentage": 89.97, "elapsed_time": "2:42:40", "remaining_time": "0:18:07", "throughput": 6472.62, "total_tokens": 63176440} {"current_steps": 5630, "total_steps": 6252, "loss": 0.4332, "lr": 1.215061267293932e-06, "epoch": 2.7017459650806983, "percentage": 90.05, "elapsed_time": "2:42:52", "remaining_time": "0:17:59", "throughput": 6471.71, "total_tokens": 63242712} {"current_steps": 5635, "total_steps": 6252, "loss": 0.4613, "lr": 1.195792510570834e-06, "epoch": 2.704145917081658, "percentage": 90.13, "elapsed_time": "2:43:02", "remaining_time": "0:17:51", "throughput": 6470.34, "total_tokens": 63294640} {"current_steps": 5640, "total_steps": 6252, "loss": 0.4588, "lr": 1.1766740179752572e-06, "epoch": 2.7065458690826185, "percentage": 90.21, "elapsed_time": "2:43:13", "remaining_time": "0:17:42", "throughput": 6469.14, "total_tokens": 63353040} {"current_steps": 5645, "total_steps": 6252, "loss": 0.5275, "lr": 1.1577059101927385e-06, "epoch": 2.7089458210835784, "percentage": 90.29, "elapsed_time": "2:43:23", "remaining_time": "0:17:34", "throughput": 6468.24, "total_tokens": 63408480} {"current_steps": 5650, "total_steps": 6252, "loss": 0.4728, "lr": 1.138888306959504e-06, "epoch": 2.7113457730845383, "percentage": 90.37, "elapsed_time": "2:43:34", "remaining_time": "0:17:25", "throughput": 6466.37, "total_tokens": 63465824} {"current_steps": 5655, "total_steps": 6252, "loss": 0.4897, "lr": 1.1202213270617322e-06, "epoch": 2.713745725085498, "percentage": 90.45, "elapsed_time": "2:43:44", "remaining_time": "0:17:17", "throughput": 6465.35, "total_tokens": 63518744} {"current_steps": 5660, "total_steps": 6252, "loss": 0.4849, "lr": 1.101705088334795e-06, "epoch": 2.716145677086458, "percentage": 90.53, "elapsed_time": "2:43:53", "remaining_time": "0:17:08", "throughput": 6464.73, "total_tokens": 63573232} {"current_steps": 5665, "total_steps": 6252, "loss": 0.4778, "lr": 1.0833397076624897e-06, "epoch": 2.7185456290874184, "percentage": 90.61, "elapsed_time": "2:44:03", "remaining_time": "0:17:00", "throughput": 6463.64, "total_tokens": 63626872} {"current_steps": 5670, "total_steps": 6252, "loss": 0.5255, "lr": 1.065125300976344e-06, "epoch": 2.7209455810883783, "percentage": 90.69, "elapsed_time": "2:44:12", "remaining_time": "0:16:51", "throughput": 6463.23, "total_tokens": 63680184} {"current_steps": 5675, "total_steps": 6252, "loss": 0.5119, "lr": 1.0470619832548461e-06, "epoch": 2.723345533089338, "percentage": 90.77, "elapsed_time": "2:44:21", "remaining_time": "0:16:42", "throughput": 6462.59, "total_tokens": 63732752} {"current_steps": 5680, "total_steps": 6252, "loss": 0.4683, "lr": 1.0291498685227441e-06, "epoch": 2.7257454850902985, "percentage": 90.85, "elapsed_time": "2:44:33", "remaining_time": "0:16:34", "throughput": 6461.06, "total_tokens": 63790384} {"current_steps": 5685, "total_steps": 6252, "loss": 0.4943, "lr": 1.0113890698503076e-06, "epoch": 2.7281454370912583, "percentage": 90.93, "elapsed_time": "2:44:43", "remaining_time": "0:16:25", "throughput": 6459.81, "total_tokens": 63845528} {"current_steps": 5690, "total_steps": 6252, "loss": 0.4989, "lr": 9.937796993526343e-07, "epoch": 2.7305453890922182, "percentage": 91.01, "elapsed_time": "2:44:53", "remaining_time": "0:16:17", "throughput": 6458.56, "total_tokens": 63898616} {"current_steps": 5695, "total_steps": 6252, "loss": 0.4506, "lr": 9.763218681889203e-07, "epoch": 2.732945341093178, "percentage": 91.09, "elapsed_time": "2:45:02", "remaining_time": "0:16:08", "throughput": 6458.04, "total_tokens": 63953600} {"current_steps": 5700, "total_steps": 6252, "loss": 0.4606, "lr": 9.59015686561779e-07, "epoch": 2.735345293094138, "percentage": 91.17, "elapsed_time": "2:45:13", "remaining_time": "0:16:00", "throughput": 6457.13, "total_tokens": 64012184} {"current_steps": 5705, "total_steps": 6252, "loss": 0.4545, "lr": 9.418612637165286e-07, "epoch": 2.7377452450950983, "percentage": 91.25, "elapsed_time": "2:45:24", "remaining_time": "0:15:51", "throughput": 6455.48, "total_tokens": 64065248} {"current_steps": 5710, "total_steps": 6252, "loss": 0.5299, "lr": 9.24858707940518e-07, "epoch": 2.740145197096058, "percentage": 91.33, "elapsed_time": "2:45:34", "remaining_time": "0:15:43", "throughput": 6454.05, "total_tokens": 64120216} {"current_steps": 5715, "total_steps": 6252, "loss": 0.4609, "lr": 9.08008126562418e-07, "epoch": 2.742545149097018, "percentage": 91.41, "elapsed_time": "2:45:45", "remaining_time": "0:15:34", "throughput": 6453.0, "total_tokens": 64181128} {"current_steps": 5720, "total_steps": 6252, "loss": 0.464, "lr": 8.913096259515835e-07, "epoch": 2.744945101097978, "percentage": 91.49, "elapsed_time": "2:45:54", "remaining_time": "0:15:25", "throughput": 6452.82, "total_tokens": 64234984} {"current_steps": 5725, "total_steps": 6252, "loss": 0.4932, "lr": 8.747633115173404e-07, "epoch": 2.747345053098938, "percentage": 91.57, "elapsed_time": "2:46:02", "remaining_time": "0:15:17", "throughput": 6452.92, "total_tokens": 64290040} {"current_steps": 5730, "total_steps": 6252, "loss": 0.4344, "lr": 8.583692877083465e-07, "epoch": 2.749745005099898, "percentage": 91.65, "elapsed_time": "2:46:11", "remaining_time": "0:15:08", "throughput": 6453.12, "total_tokens": 64347256} {"current_steps": 5735, "total_steps": 6252, "loss": 0.4921, "lr": 8.421276580119236e-07, "epoch": 2.752144957100858, "percentage": 91.73, "elapsed_time": "2:46:20", "remaining_time": "0:14:59", "throughput": 6453.0, "total_tokens": 64401448} {"current_steps": 5740, "total_steps": 6252, "loss": 0.4953, "lr": 8.260385249534042e-07, "epoch": 2.754544909101818, "percentage": 91.81, "elapsed_time": "2:46:28", "remaining_time": "0:14:50", "throughput": 6452.99, "total_tokens": 64457576} {"current_steps": 5745, "total_steps": 6252, "loss": 0.4595, "lr": 8.101019900954881e-07, "epoch": 2.756944861102778, "percentage": 91.89, "elapsed_time": "2:46:38", "remaining_time": "0:14:42", "throughput": 6452.72, "total_tokens": 64515152} {"current_steps": 5750, "total_steps": 6252, "loss": 0.4843, "lr": 7.943181540375988e-07, "epoch": 2.7593448131037377, "percentage": 91.97, "elapsed_time": "2:46:46", "remaining_time": "0:14:33", "throughput": 6453.0, "total_tokens": 64573768} {"current_steps": 5755, "total_steps": 6252, "loss": 0.4595, "lr": 7.786871164152415e-07, "epoch": 2.761744765104698, "percentage": 92.05, "elapsed_time": "2:46:54", "remaining_time": "0:14:24", "throughput": 6453.46, "total_tokens": 64626520} {"current_steps": 5760, "total_steps": 6252, "loss": 0.4565, "lr": 7.632089758993932e-07, "epoch": 2.764144717105658, "percentage": 92.13, "elapsed_time": "2:47:02", "remaining_time": "0:14:16", "throughput": 6453.82, "total_tokens": 64683224} {"current_steps": 5765, "total_steps": 6252, "loss": 0.4728, "lr": 7.478838301958502e-07, "epoch": 2.766544669106618, "percentage": 92.21, "elapsed_time": "2:47:10", "remaining_time": "0:14:07", "throughput": 6453.87, "total_tokens": 64738056} {"current_steps": 5770, "total_steps": 6252, "loss": 0.4835, "lr": 7.327117760446478e-07, "epoch": 2.768944621107578, "percentage": 92.29, "elapsed_time": "2:47:18", "remaining_time": "0:13:58", "throughput": 6453.94, "total_tokens": 64790592} {"current_steps": 5775, "total_steps": 6252, "loss": 0.4922, "lr": 7.17692909219414e-07, "epoch": 2.771344573108538, "percentage": 92.37, "elapsed_time": "2:47:27", "remaining_time": "0:13:49", "throughput": 6453.54, "total_tokens": 64844640} {"current_steps": 5780, "total_steps": 6252, "loss": 0.4473, "lr": 7.028273245267947e-07, "epoch": 2.773744525109498, "percentage": 92.45, "elapsed_time": "2:47:36", "remaining_time": "0:13:41", "throughput": 6453.66, "total_tokens": 64903320} {"current_steps": 5785, "total_steps": 6252, "loss": 0.5196, "lr": 6.881151158058263e-07, "epoch": 2.7761444771104578, "percentage": 92.53, "elapsed_time": "2:47:46", "remaining_time": "0:13:32", "throughput": 6453.56, "total_tokens": 64963432} {"current_steps": 5790, "total_steps": 6252, "loss": 0.4862, "lr": 6.735563759273783e-07, "epoch": 2.7785444291114176, "percentage": 92.61, "elapsed_time": "2:47:54", "remaining_time": "0:13:23", "throughput": 6453.81, "total_tokens": 65020920} {"current_steps": 5795, "total_steps": 6252, "loss": 0.4557, "lr": 6.591511967935282e-07, "epoch": 2.780944381112378, "percentage": 92.69, "elapsed_time": "2:48:03", "remaining_time": "0:13:15", "throughput": 6454.12, "total_tokens": 65077720} {"current_steps": 5800, "total_steps": 6252, "loss": 0.4682, "lr": 6.448996693370179e-07, "epoch": 2.783344333113338, "percentage": 92.77, "elapsed_time": "2:48:12", "remaining_time": "0:13:06", "throughput": 6453.87, "total_tokens": 65133616} {"current_steps": 5805, "total_steps": 6252, "loss": 0.4646, "lr": 6.308018835206541e-07, "epoch": 2.7857442851142977, "percentage": 92.85, "elapsed_time": "2:48:20", "remaining_time": "0:12:57", "throughput": 6453.95, "total_tokens": 65187840} {"current_steps": 5810, "total_steps": 6252, "loss": 0.472, "lr": 6.168579283367476e-07, "epoch": 2.7881442371152576, "percentage": 92.93, "elapsed_time": "2:48:28", "remaining_time": "0:12:49", "throughput": 6453.9, "total_tokens": 65240368} {"current_steps": 5815, "total_steps": 6252, "loss": 0.4831, "lr": 6.030678918065552e-07, "epoch": 2.7905441891162175, "percentage": 93.01, "elapsed_time": "2:48:37", "remaining_time": "0:12:40", "throughput": 6453.66, "total_tokens": 65295184} {"current_steps": 5820, "total_steps": 6252, "loss": 0.4951, "lr": 5.894318609797222e-07, "epoch": 2.792944141117178, "percentage": 93.09, "elapsed_time": "2:48:45", "remaining_time": "0:12:31", "throughput": 6454.12, "total_tokens": 65351248} {"current_steps": 5825, "total_steps": 6252, "loss": 0.4852, "lr": 5.759499219337328e-07, "epoch": 2.7953440931181377, "percentage": 93.17, "elapsed_time": "2:48:53", "remaining_time": "0:12:22", "throughput": 6454.53, "total_tokens": 65405976} {"current_steps": 5830, "total_steps": 6252, "loss": 0.4505, "lr": 5.626221597733655e-07, "epoch": 2.7977440451190976, "percentage": 93.25, "elapsed_time": "2:49:01", "remaining_time": "0:12:14", "throughput": 6455.08, "total_tokens": 65466136} {"current_steps": 5835, "total_steps": 6252, "loss": 0.5448, "lr": 5.494486586301528e-07, "epoch": 2.8001439971200575, "percentage": 93.33, "elapsed_time": "2:49:09", "remaining_time": "0:12:05", "throughput": 6455.2, "total_tokens": 65518496} {"current_steps": 5840, "total_steps": 6252, "loss": 0.4865, "lr": 5.364295016618643e-07, "epoch": 2.8025439491210173, "percentage": 93.41, "elapsed_time": "2:49:17", "remaining_time": "0:11:56", "throughput": 6455.86, "total_tokens": 65577616} {"current_steps": 5845, "total_steps": 6252, "loss": 0.4664, "lr": 5.235647710519626e-07, "epoch": 2.8049439011219777, "percentage": 93.49, "elapsed_time": "2:49:26", "remaining_time": "0:11:47", "throughput": 6455.96, "total_tokens": 65634592} {"current_steps": 5850, "total_steps": 6252, "loss": 0.4649, "lr": 5.108545480090931e-07, "epoch": 2.8073438531229375, "percentage": 93.57, "elapsed_time": "2:49:34", "remaining_time": "0:11:39", "throughput": 6456.24, "total_tokens": 65691480} {"current_steps": 5855, "total_steps": 6252, "loss": 0.4969, "lr": 4.982989127665816e-07, "epoch": 2.8097438051238974, "percentage": 93.65, "elapsed_time": "2:49:43", "remaining_time": "0:11:30", "throughput": 6456.25, "total_tokens": 65745568} {"current_steps": 5860, "total_steps": 6252, "loss": 0.4742, "lr": 4.858979445819089e-07, "epoch": 2.8121437571248578, "percentage": 93.73, "elapsed_time": "2:49:50", "remaining_time": "0:11:21", "throughput": 6456.73, "total_tokens": 65799784} {"current_steps": 5865, "total_steps": 6252, "loss": 0.4561, "lr": 4.7365172173621796e-07, "epoch": 2.8145437091258176, "percentage": 93.81, "elapsed_time": "2:49:59", "remaining_time": "0:11:13", "throughput": 6456.88, "total_tokens": 65856528} {"current_steps": 5870, "total_steps": 6252, "loss": 0.4425, "lr": 4.615603215338299e-07, "epoch": 2.8169436611267775, "percentage": 93.89, "elapsed_time": "2:50:08", "remaining_time": "0:11:04", "throughput": 6456.8, "total_tokens": 65911144} {"current_steps": 5875, "total_steps": 6252, "loss": 0.4873, "lr": 4.496238203017422e-07, "epoch": 2.8193436131277374, "percentage": 93.97, "elapsed_time": "2:50:16", "remaining_time": "0:10:55", "throughput": 6457.47, "total_tokens": 65971080} {"current_steps": 5880, "total_steps": 6252, "loss": 0.4867, "lr": 4.3784229338915406e-07, "epoch": 2.8217435651286973, "percentage": 94.05, "elapsed_time": "2:50:24", "remaining_time": "0:10:46", "throughput": 6457.55, "total_tokens": 66026344} {"current_steps": 5885, "total_steps": 6252, "loss": 0.4813, "lr": 4.262158151669804e-07, "epoch": 2.8241435171296576, "percentage": 94.13, "elapsed_time": "2:50:33", "remaining_time": "0:10:38", "throughput": 6457.69, "total_tokens": 66082360} {"current_steps": 5890, "total_steps": 6252, "loss": 0.4968, "lr": 4.147444590274052e-07, "epoch": 2.8265434691306175, "percentage": 94.21, "elapsed_time": "2:50:41", "remaining_time": "0:10:29", "throughput": 6457.71, "total_tokens": 66134928} {"current_steps": 5895, "total_steps": 6252, "loss": 0.4744, "lr": 4.0342829738339583e-07, "epoch": 2.8289434211315774, "percentage": 94.29, "elapsed_time": "2:50:49", "remaining_time": "0:10:20", "throughput": 6458.1, "total_tokens": 66190032} {"current_steps": 5900, "total_steps": 6252, "loss": 0.4819, "lr": 3.922674016682504e-07, "epoch": 2.8313433731325373, "percentage": 94.37, "elapsed_time": "2:50:56", "remaining_time": "0:10:11", "throughput": 6458.5, "total_tokens": 66244312} {"current_steps": 5905, "total_steps": 6252, "loss": 0.4424, "lr": 3.812618423351622e-07, "epoch": 2.833743325133497, "percentage": 94.45, "elapsed_time": "2:51:05", "remaining_time": "0:10:03", "throughput": 6459.04, "total_tokens": 66305552} {"current_steps": 5910, "total_steps": 6252, "loss": 0.4926, "lr": 3.704116888567505e-07, "epoch": 2.8361432771344575, "percentage": 94.53, "elapsed_time": "2:51:13", "remaining_time": "0:09:54", "throughput": 6459.08, "total_tokens": 66358648} {"current_steps": 5915, "total_steps": 6252, "loss": 0.4706, "lr": 3.597170097246416e-07, "epoch": 2.8385432291354173, "percentage": 94.61, "elapsed_time": "2:51:23", "remaining_time": "0:09:45", "throughput": 6458.86, "total_tokens": 66417384} {"current_steps": 5920, "total_steps": 6252, "loss": 0.4945, "lr": 3.4917787244902743e-07, "epoch": 2.8409431811363772, "percentage": 94.69, "elapsed_time": "2:51:33", "remaining_time": "0:09:37", "throughput": 6458.28, "total_tokens": 66477648} {"current_steps": 5925, "total_steps": 6252, "loss": 0.495, "lr": 3.387943435582436e-07, "epoch": 2.843343133137337, "percentage": 94.77, "elapsed_time": "2:51:42", "remaining_time": "0:09:28", "throughput": 6457.71, "total_tokens": 66532464} {"current_steps": 5930, "total_steps": 6252, "loss": 0.4263, "lr": 3.285664885983447e-07, "epoch": 2.845743085138297, "percentage": 94.85, "elapsed_time": "2:51:52", "remaining_time": "0:09:19", "throughput": 6457.07, "total_tokens": 66589296} {"current_steps": 5935, "total_steps": 6252, "loss": 0.4473, "lr": 3.184943721326938e-07, "epoch": 2.8481430371392573, "percentage": 94.93, "elapsed_time": "2:52:02", "remaining_time": "0:09:11", "throughput": 6456.69, "total_tokens": 66648144} {"current_steps": 5940, "total_steps": 6252, "loss": 0.4773, "lr": 3.0857805774155423e-07, "epoch": 2.850542989140217, "percentage": 95.01, "elapsed_time": "2:52:11", "remaining_time": "0:09:02", "throughput": 6456.24, "total_tokens": 66702560} {"current_steps": 5945, "total_steps": 6252, "loss": 0.5113, "lr": 2.988176080216898e-07, "epoch": 2.852942941141177, "percentage": 95.09, "elapsed_time": "2:52:21", "remaining_time": "0:08:54", "throughput": 6455.44, "total_tokens": 66757360} {"current_steps": 5950, "total_steps": 6252, "loss": 0.5225, "lr": 2.892130845859653e-07, "epoch": 2.8553428931421374, "percentage": 95.17, "elapsed_time": "2:52:31", "remaining_time": "0:08:45", "throughput": 6454.45, "total_tokens": 66813080} {"current_steps": 5955, "total_steps": 6252, "loss": 0.4474, "lr": 2.7976454806296906e-07, "epoch": 2.8577428451430973, "percentage": 95.25, "elapsed_time": "2:52:41", "remaining_time": "0:08:36", "throughput": 6453.64, "total_tokens": 66870744} {"current_steps": 5960, "total_steps": 6252, "loss": 0.4552, "lr": 2.7047205809660746e-07, "epoch": 2.860142797144057, "percentage": 95.33, "elapsed_time": "2:52:51", "remaining_time": "0:08:28", "throughput": 6452.61, "total_tokens": 66926176} {"current_steps": 5965, "total_steps": 6252, "loss": 0.461, "lr": 2.6133567334575e-07, "epoch": 2.862542749145017, "percentage": 95.41, "elapsed_time": "2:53:01", "remaining_time": "0:08:19", "throughput": 6452.07, "total_tokens": 66982736} {"current_steps": 5970, "total_steps": 6252, "loss": 0.4649, "lr": 2.523554514838544e-07, "epoch": 2.864942701145977, "percentage": 95.49, "elapsed_time": "2:53:11", "remaining_time": "0:08:10", "throughput": 6451.32, "total_tokens": 67040256} {"current_steps": 5975, "total_steps": 6252, "loss": 0.5227, "lr": 2.435314491985974e-07, "epoch": 2.8673426531469373, "percentage": 95.57, "elapsed_time": "2:53:21", "remaining_time": "0:08:02", "throughput": 6450.86, "total_tokens": 67098776} {"current_steps": 5980, "total_steps": 6252, "loss": 0.4989, "lr": 2.3486372219151675e-07, "epoch": 2.869742605147897, "percentage": 95.65, "elapsed_time": "2:53:31", "remaining_time": "0:07:53", "throughput": 6449.76, "total_tokens": 67151768} {"current_steps": 5985, "total_steps": 6252, "loss": 0.4962, "lr": 2.263523251776617e-07, "epoch": 2.872142557148857, "percentage": 95.73, "elapsed_time": "2:53:42", "remaining_time": "0:07:44", "throughput": 6448.9, "total_tokens": 67210600} {"current_steps": 5990, "total_steps": 6252, "loss": 0.5162, "lr": 2.1799731188525407e-07, "epoch": 2.874542509149817, "percentage": 95.81, "elapsed_time": "2:53:51", "remaining_time": "0:07:36", "throughput": 6447.98, "total_tokens": 67263744} {"current_steps": 5995, "total_steps": 6252, "loss": 0.449, "lr": 2.0979873505533876e-07, "epoch": 2.876942461150777, "percentage": 95.89, "elapsed_time": "2:54:01", "remaining_time": "0:07:27", "throughput": 6446.81, "total_tokens": 67316560} {"current_steps": 6000, "total_steps": 6252, "loss": 0.4849, "lr": 2.0175664644145053e-07, "epoch": 2.879342413151737, "percentage": 95.97, "elapsed_time": "2:54:12", "remaining_time": "0:07:19", "throughput": 6445.62, "total_tokens": 67373408} {"current_steps": 6005, "total_steps": 6252, "loss": 0.4332, "lr": 1.9387109680930327e-07, "epoch": 2.881742365152697, "percentage": 96.05, "elapsed_time": "2:54:23", "remaining_time": "0:07:10", "throughput": 6444.4, "total_tokens": 67428800} {"current_steps": 6010, "total_steps": 6252, "loss": 0.4459, "lr": 1.8614213593644846e-07, "epoch": 2.884142317153657, "percentage": 96.13, "elapsed_time": "2:54:33", "remaining_time": "0:07:01", "throughput": 6443.82, "total_tokens": 67490440} {"current_steps": 6015, "total_steps": 6252, "loss": 0.4779, "lr": 1.7856981261197002e-07, "epoch": 2.8865422691546168, "percentage": 96.21, "elapsed_time": "2:54:43", "remaining_time": "0:06:53", "throughput": 6443.27, "total_tokens": 67545608} {"current_steps": 6020, "total_steps": 6252, "loss": 0.4598, "lr": 1.7115417463618722e-07, "epoch": 2.8889422211555766, "percentage": 96.29, "elapsed_time": "2:54:52", "remaining_time": "0:06:44", "throughput": 6442.46, "total_tokens": 67595400} {"current_steps": 6025, "total_steps": 6252, "loss": 0.4797, "lr": 1.638952688203327e-07, "epoch": 2.891342173156537, "percentage": 96.37, "elapsed_time": "2:55:01", "remaining_time": "0:06:35", "throughput": 6441.86, "total_tokens": 67646720} {"current_steps": 6030, "total_steps": 6252, "loss": 0.4915, "lr": 1.567931409862694e-07, "epoch": 2.893742125157497, "percentage": 96.45, "elapsed_time": "2:55:10", "remaining_time": "0:06:26", "throughput": 6440.94, "total_tokens": 67700752} {"current_steps": 6035, "total_steps": 6252, "loss": 0.4946, "lr": 1.4984783596619922e-07, "epoch": 2.8961420771584567, "percentage": 96.53, "elapsed_time": "2:55:20", "remaining_time": "0:06:18", "throughput": 6440.2, "total_tokens": 67755144} {"current_steps": 6040, "total_steps": 6252, "loss": 0.4919, "lr": 1.430593976023825e-07, "epoch": 2.898542029159417, "percentage": 96.61, "elapsed_time": "2:55:31", "remaining_time": "0:06:09", "throughput": 6439.23, "total_tokens": 67814680} {"current_steps": 6045, "total_steps": 6252, "loss": 0.5055, "lr": 1.3642786874685233e-07, "epoch": 2.900941981160377, "percentage": 96.69, "elapsed_time": "2:55:41", "remaining_time": "0:06:00", "throughput": 6438.12, "total_tokens": 67867648} {"current_steps": 6050, "total_steps": 6252, "loss": 0.459, "lr": 1.299532912611534e-07, "epoch": 2.903341933161337, "percentage": 96.77, "elapsed_time": "2:55:50", "remaining_time": "0:05:52", "throughput": 6437.7, "total_tokens": 67922728} {"current_steps": 6055, "total_steps": 6252, "loss": 0.4636, "lr": 1.2363570601608143e-07, "epoch": 2.9057418851622967, "percentage": 96.85, "elapsed_time": "2:56:00", "remaining_time": "0:05:43", "throughput": 6437.01, "total_tokens": 67975200} {"current_steps": 6060, "total_steps": 6252, "loss": 0.4612, "lr": 1.1747515289140254e-07, "epoch": 2.9081418371632566, "percentage": 96.93, "elapsed_time": "2:56:10", "remaining_time": "0:05:34", "throughput": 6435.61, "total_tokens": 68029864} {"current_steps": 6065, "total_steps": 6252, "loss": 0.5042, "lr": 1.1147167077562859e-07, "epoch": 2.910541789164217, "percentage": 97.01, "elapsed_time": "2:56:20", "remaining_time": "0:05:26", "throughput": 6434.41, "total_tokens": 68079824} {"current_steps": 6070, "total_steps": 6252, "loss": 0.4287, "lr": 1.0562529756576179e-07, "epoch": 2.912941741165177, "percentage": 97.09, "elapsed_time": "2:56:30", "remaining_time": "0:05:17", "throughput": 6433.49, "total_tokens": 68136632} {"current_steps": 6075, "total_steps": 6252, "loss": 0.4994, "lr": 9.993607016704209e-08, "epoch": 2.9153416931661367, "percentage": 97.17, "elapsed_time": "2:56:41", "remaining_time": "0:05:08", "throughput": 6432.56, "total_tokens": 68192816} {"current_steps": 6080, "total_steps": 6252, "loss": 0.5164, "lr": 9.440402449274188e-08, "epoch": 2.9177416451670966, "percentage": 97.25, "elapsed_time": "2:56:50", "remaining_time": "0:05:00", "throughput": 6431.71, "total_tokens": 68244208} {"current_steps": 6085, "total_steps": 6252, "loss": 0.4609, "lr": 8.902919546390776e-08, "epoch": 2.9201415971680564, "percentage": 97.33, "elapsed_time": "2:57:00", "remaining_time": "0:04:51", "throughput": 6430.79, "total_tokens": 68300352} {"current_steps": 6090, "total_steps": 6252, "loss": 0.5296, "lr": 8.381161700916906e-08, "epoch": 2.9225415491690168, "percentage": 97.41, "elapsed_time": "2:57:10", "remaining_time": "0:04:42", "throughput": 6429.91, "total_tokens": 68350392} {"current_steps": 6095, "total_steps": 6252, "loss": 0.5012, "lr": 7.87513220644992e-08, "epoch": 2.9249415011699766, "percentage": 97.49, "elapsed_time": "2:57:19", "remaining_time": "0:04:34", "throughput": 6429.15, "total_tokens": 68405152} {"current_steps": 6100, "total_steps": 6252, "loss": 0.5022, "lr": 7.384834257302687e-08, "epoch": 2.9273414531709365, "percentage": 97.57, "elapsed_time": "2:57:30", "remaining_time": "0:04:25", "throughput": 6428.12, "total_tokens": 68461336} {"current_steps": 6105, "total_steps": 6252, "loss": 0.477, "lr": 6.910270948482789e-08, "epoch": 2.9297414051718964, "percentage": 97.65, "elapsed_time": "2:57:39", "remaining_time": "0:04:16", "throughput": 6427.11, "total_tokens": 68512936} {"current_steps": 6110, "total_steps": 6252, "loss": 0.4894, "lr": 6.451445275671986e-08, "epoch": 2.9321413571728563, "percentage": 97.73, "elapsed_time": "2:57:50", "remaining_time": "0:04:07", "throughput": 6426.32, "total_tokens": 68569728} {"current_steps": 6115, "total_steps": 6252, "loss": 0.4685, "lr": 6.008360135208724e-08, "epoch": 2.9345413091738166, "percentage": 97.81, "elapsed_time": "2:58:00", "remaining_time": "0:03:59", "throughput": 6425.4, "total_tokens": 68623976} {"current_steps": 6120, "total_steps": 6252, "loss": 0.4904, "lr": 5.581018324069543e-08, "epoch": 2.9369412611747765, "percentage": 97.89, "elapsed_time": "2:58:11", "remaining_time": "0:03:50", "throughput": 6423.97, "total_tokens": 68679096} {"current_steps": 6125, "total_steps": 6252, "loss": 0.4671, "lr": 5.169422539850477e-08, "epoch": 2.9393412131757364, "percentage": 97.97, "elapsed_time": "2:58:20", "remaining_time": "0:03:41", "throughput": 6423.39, "total_tokens": 68734576} {"current_steps": 6130, "total_steps": 6252, "loss": 0.469, "lr": 4.773575380750961e-08, "epoch": 2.9417411651766967, "percentage": 98.05, "elapsed_time": "2:58:30", "remaining_time": "0:03:33", "throughput": 6422.71, "total_tokens": 68793128} {"current_steps": 6135, "total_steps": 6252, "loss": 0.5031, "lr": 4.393479345557727e-08, "epoch": 2.9441411171776566, "percentage": 98.13, "elapsed_time": "2:58:41", "remaining_time": "0:03:24", "throughput": 6421.73, "total_tokens": 68847592} {"current_steps": 6140, "total_steps": 6252, "loss": 0.4709, "lr": 4.0291368336276e-08, "epoch": 2.9465410691786165, "percentage": 98.21, "elapsed_time": "2:58:51", "remaining_time": "0:03:15", "throughput": 6420.64, "total_tokens": 68905096} {"current_steps": 6145, "total_steps": 6252, "loss": 0.4638, "lr": 3.6805501448744505e-08, "epoch": 2.9489410211795763, "percentage": 98.29, "elapsed_time": "2:59:01", "remaining_time": "0:03:07", "throughput": 6419.97, "total_tokens": 68960224} {"current_steps": 6150, "total_steps": 6252, "loss": 0.5143, "lr": 3.347721479751986e-08, "epoch": 2.9513409731805362, "percentage": 98.37, "elapsed_time": "2:59:11", "remaining_time": "0:02:58", "throughput": 6419.16, "total_tokens": 69014200} {"current_steps": 6155, "total_steps": 6252, "loss": 0.4258, "lr": 3.0306529392426507e-08, "epoch": 2.9537409251814966, "percentage": 98.45, "elapsed_time": "2:59:21", "remaining_time": "0:02:49", "throughput": 6418.38, "total_tokens": 69071584} {"current_steps": 6160, "total_steps": 6252, "loss": 0.4785, "lr": 2.72934652484208e-08, "epoch": 2.9561408771824564, "percentage": 98.53, "elapsed_time": "2:59:31", "remaining_time": "0:02:40", "throughput": 6417.61, "total_tokens": 69125824} {"current_steps": 6165, "total_steps": 6252, "loss": 0.5019, "lr": 2.4438041385480003e-08, "epoch": 2.9585408291834163, "percentage": 98.61, "elapsed_time": "2:59:42", "remaining_time": "0:02:32", "throughput": 6416.51, "total_tokens": 69183992} {"current_steps": 6170, "total_steps": 6252, "loss": 0.4764, "lr": 2.174027582848015e-08, "epoch": 2.960940781184376, "percentage": 98.69, "elapsed_time": "2:59:52", "remaining_time": "0:02:23", "throughput": 6415.7, "total_tokens": 69243264} {"current_steps": 6175, "total_steps": 6252, "loss": 0.499, "lr": 1.92001856070656e-08, "epoch": 2.963340733185336, "percentage": 98.77, "elapsed_time": "3:00:03", "remaining_time": "0:02:14", "throughput": 6414.53, "total_tokens": 69299200} {"current_steps": 6180, "total_steps": 6252, "loss": 0.4397, "lr": 1.6817786755568553e-08, "epoch": 2.9657406851862964, "percentage": 98.85, "elapsed_time": "3:00:12", "remaining_time": "0:02:05", "throughput": 6413.92, "total_tokens": 69352824} {"current_steps": 6185, "total_steps": 6252, "loss": 0.452, "lr": 1.4593094312889688e-08, "epoch": 2.9681406371872563, "percentage": 98.93, "elapsed_time": "3:00:22", "remaining_time": "0:01:57", "throughput": 6413.67, "total_tokens": 69415024} {"current_steps": 6190, "total_steps": 6252, "loss": 0.4915, "lr": 1.2526122322401024e-08, "epoch": 2.970540589188216, "percentage": 99.01, "elapsed_time": "3:00:32", "remaining_time": "0:01:48", "throughput": 6413.15, "total_tokens": 69471512} {"current_steps": 6195, "total_steps": 6252, "loss": 0.4443, "lr": 1.0616883831873758e-08, "epoch": 2.972940541189176, "percentage": 99.09, "elapsed_time": "3:00:42", "remaining_time": "0:01:39", "throughput": 6412.47, "total_tokens": 69527768} {"current_steps": 6200, "total_steps": 6252, "loss": 0.4387, "lr": 8.86539089338112e-09, "epoch": 2.975340493190136, "percentage": 99.17, "elapsed_time": "3:00:52", "remaining_time": "0:01:31", "throughput": 6411.77, "total_tokens": 69583024} {"current_steps": 6205, "total_steps": 6252, "loss": 0.4519, "lr": 7.271654563223429e-09, "epoch": 2.9777404451910963, "percentage": 99.25, "elapsed_time": "3:01:03", "remaining_time": "0:01:22", "throughput": 6410.59, "total_tokens": 69639080} {"current_steps": 6210, "total_steps": 6252, "loss": 0.5355, "lr": 5.835684901869809e-09, "epoch": 2.980140397192056, "percentage": 99.33, "elapsed_time": "3:01:13", "remaining_time": "0:01:13", "throughput": 6409.61, "total_tokens": 69695440} {"current_steps": 6215, "total_steps": 6252, "loss": 0.4775, "lr": 4.5574909738804735e-09, "epoch": 2.982540349193016, "percentage": 99.41, "elapsed_time": "3:01:24", "remaining_time": "0:01:04", "throughput": 6408.68, "total_tokens": 69752488} {"current_steps": 6220, "total_steps": 6252, "loss": 0.4861, "lr": 3.4370808478595417e-09, "epoch": 2.9849403011939764, "percentage": 99.49, "elapsed_time": "3:01:33", "remaining_time": "0:00:56", "throughput": 6407.66, "total_tokens": 69804712} {"current_steps": 6225, "total_steps": 6252, "loss": 0.4641, "lr": 2.474461596396749e-09, "epoch": 2.9873402531949362, "percentage": 99.57, "elapsed_time": "3:01:43", "remaining_time": "0:00:47", "throughput": 6407.71, "total_tokens": 69863384} {"current_steps": 6230, "total_steps": 6252, "loss": 0.4785, "lr": 1.6696392960341423e-09, "epoch": 2.989740205195896, "percentage": 99.65, "elapsed_time": "3:01:51", "remaining_time": "0:00:38", "throughput": 6407.78, "total_tokens": 69920712} {"current_steps": 6235, "total_steps": 6252, "loss": 0.4529, "lr": 1.022619027207794e-09, "epoch": 2.992140157196856, "percentage": 99.73, "elapsed_time": "3:02:00", "remaining_time": "0:00:29", "throughput": 6408.14, "total_tokens": 69978976} {"current_steps": 6240, "total_steps": 6252, "loss": 0.4621, "lr": 5.334048742394737e-10, "epoch": 2.994540109197816, "percentage": 99.81, "elapsed_time": "3:02:09", "remaining_time": "0:00:21", "throughput": 6408.3, "total_tokens": 70037816} {"current_steps": 6245, "total_steps": 6252, "loss": 0.4757, "lr": 2.0199992529501554e-10, "epoch": 2.996940061198776, "percentage": 99.89, "elapsed_time": "3:02:17", "remaining_time": "0:00:12", "throughput": 6408.68, "total_tokens": 70098000} {"current_steps": 6250, "total_steps": 6252, "loss": 0.463, "lr": 2.8406272370440357e-11, "epoch": 2.999340013199736, "percentage": 99.97, "elapsed_time": "3:02:26", "remaining_time": "0:00:03", "throughput": 6408.75, "total_tokens": 70153968} {"current_steps": 6252, "total_steps": 6252, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:02:29", "remaining_time": "0:00:00", "throughput": 6408.53, "total_tokens": 70167528} {"current_steps": 6255, "total_steps": 8139, "loss": 0.9897, "lr": 6.33061148994144e-06, "epoch": 2.305593954474242, "percentage": 76.85, "elapsed_time": "0:00:32", "remaining_time": "0:00:09", "throughput": 2167625.39, "total_tokens": 70311904}